0 files changed, 0 insertions, 0 deletions
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 1fd5acdc73c6..ac12eaf11755 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -76,24 +76,11 @@ config WIREGUARD
 	tristate "WireGuard secure network tunnel"
 	depends on NET && INET
 	depends on IPV6 || !IPV6
-	depends on !KMSAN # KMSAN doesn't support the crypto configs below
 	select NET_UDP_TUNNEL
 	select DST_CACHE
-	select CRYPTO
 	select CRYPTO_LIB_CURVE25519
 	select CRYPTO_LIB_CHACHA20POLY1305
-	select CRYPTO_CHACHA20_X86_64 if X86 && 64BIT
-	select CRYPTO_POLY1305_X86_64 if X86 && 64BIT
-	select CRYPTO_BLAKE2S_X86 if X86 && 64BIT
-	select CRYPTO_CURVE25519_X86 if X86 && 64BIT
-	select CRYPTO_CHACHA20_NEON if ARM || (ARM64 && KERNEL_MODE_NEON)
-	select CRYPTO_POLY1305_NEON if ARM64 && KERNEL_MODE_NEON
-	select CRYPTO_POLY1305_ARM if ARM
-	select CRYPTO_BLAKE2S_ARM if ARM
-	select CRYPTO_CURVE25519_NEON if ARM && KERNEL_MODE_NEON
-	select CRYPTO_CHACHA_MIPS if CPU_MIPS32_R2
-	select CRYPTO_POLY1305_MIPS if MIPS
-	select CRYPTO_CHACHA_S390 if S390
+	select CRYPTO_LIB_UTILS
 	help
 	  WireGuard is a secure, fast, and easy to use replacement for IPSec
 	  that uses modern cryptography and clever networking tricks. It's
@@ -115,6 +102,21 @@ config WIREGUARD_DEBUG
 
 	  Say N here unless you know what you're doing.
 
+config OVPN
+	tristate "OpenVPN data channel offload"
+	depends on NET && INET
+	depends on IPV6 || !IPV6
+	select DST_CACHE
+	select NET_UDP_TUNNEL
+	select CRYPTO
+	select CRYPTO_AES
+	select CRYPTO_GCM
+	select CRYPTO_CHACHA20POLY1305
+	select STREAM_PARSER
+	help
+	  This module enhances the performance of the OpenVPN userspace software
+	  by offloading the data channel processing to kernelspace.
+
 config EQUALIZER
 	tristate "EQL (serial line load balancing) support"
 	help
@@ -518,30 +520,6 @@ source "drivers/net/hippi/Kconfig"
 
 source "drivers/net/ipa/Kconfig"
 
-config NET_SB1000
-	tristate "General Instruments Surfboard 1000"
-	depends on ISA && PNP
-	help
-	  This is a driver for the General Instrument (also known as
-	  NextLevel) SURFboard 1000 internal
-	  cable modem. This is an ISA card which is used by a number of cable
-	  TV companies to provide cable modem access. It's a one-way
-	  downstream-only cable modem, meaning that your upstream net link is
-	  provided by your regular phone modem.
-
-	  At present this driver only compiles as a module, so say M here if
-	  you have this card. The module will be called sb1000. Then read
-	  <file:Documentation/networking/device_drivers/cable/sb1000.rst> for
-	  information on how to use this module, as it needs special ppp
-	  scripts for establishing a connection. Further documentation
-	  and the necessary scripts can be found at:
-
-	  <http://www.jacksonville.net/~fventuri/>
-	  <http://home.adelphia.net/~siglercm/sb1000.html>
-	  <http://linuxpower.cx/~cable/>
-
-	  If you don't have this card, of course say N.
-
 source "drivers/net/phy/Kconfig"
 
 source "drivers/net/pse-pd/Kconfig"
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 13743d0e83b5..73bc63ecd65f 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_IPVLAN) += ipvlan/
 obj-$(CONFIG_IPVTAP) += ipvlan/
 obj-$(CONFIG_DUMMY) += dummy.o
 obj-$(CONFIG_WIREGUARD) += wireguard/
+obj-$(CONFIG_OVPN) += ovpn/
 obj-$(CONFIG_EQUALIZER) += eql.o
 obj-$(CONFIG_IFB) += ifb.o
 obj-$(CONFIG_MACSEC) += macsec.o
@@ -69,7 +70,6 @@ obj-$(CONFIG_PPPOL2TP) += ppp/
 obj-$(CONFIG_PPTP) += ppp/
 obj-$(CONFIG_SLIP) += slip/
 obj-$(CONFIG_SLHC) += slip/
-obj-$(CONFIG_NET_SB1000) += sb1000.o
 obj-$(CONFIG_SUNGEM_PHY) += sungem_phy.o
 obj-$(CONFIG_WAN) += wan/
 obj-$(CONFIG_WLAN) += wireless/
diff --git a/drivers/net/Space.c b/drivers/net/Space.c
index dc50797a2ed0..c01e2c2f7d6c 100644
--- a/drivers/net/Space.c
+++ b/drivers/net/Space.c
@@ -67,8 +67,7 @@ static int netdev_boot_setup_add(char *name, struct ifmap *map)
 	s = dev_boot_setup;
 	for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
 		if (s[i].name[0] == '\0' || s[i].name[0] == ' ') {
-			memset(s[i].name, 0, sizeof(s[i].name));
-			strscpy(s[i].name, name, IFNAMSIZ);
+			strscpy_pad(s[i].name, name);
 			memcpy(&s[i].map, map, sizeof(s[i].map));
 			break;
 		}
diff --git a/drivers/net/amt.c b/drivers/net/amt.c
index 98c6205ed19f..902c817a0dea 100644
--- a/drivers/net/amt.c
+++ b/drivers/net/amt.c
@@ -11,6 +11,7 @@
 #include <linux/net.h>
 #include <linux/igmp.h>
 #include <linux/workqueue.h>
+#include <net/flow.h>
 #include <net/pkt_sched.h>
 #include <net/net_namespace.h>
 #include <net/ip.h>
@@ -28,6 +29,7 @@
 #include <net/addrconf.h>
 #include <net/ip6_route.h>
 #include <net/inet_common.h>
+#include <net/inet_dscp.h>
 #include <net/ip6_checksum.h>
 
 static struct workqueue_struct *amt_wq;
@@ -979,7 +981,7 @@ static void amt_event_send_request(struct amt_dev *amt)
 	amt->req_cnt++;
 out:
 	exp = min_t(u32, (1 * (1 << amt->req_cnt)), AMT_MAX_REQ_TIMEOUT);
-	mod_delayed_work(amt_wq, &amt->req_wq, msecs_to_jiffies(exp * 1000));
+	mod_delayed_work(amt_wq, &amt->req_wq, secs_to_jiffies(exp));
 }
 
 static void amt_req_work(struct work_struct *work)
@@ -1018,7 +1020,7 @@ static bool amt_send_membership_update(struct amt_dev *amt,
 	fl4.flowi4_oif         = amt->stream_dev->ifindex;
 	fl4.daddr              = amt->remote_ip;
 	fl4.saddr              = amt->local_ip;
-	fl4.flowi4_tos         = AMT_TOS;
+	fl4.flowi4_dscp        = inet_dsfield_to_dscp(AMT_TOS);
 	fl4.flowi4_proto       = IPPROTO_UDP;
 	rt = ip_route_output_key(amt->net, &fl4);
 	if (IS_ERR(rt)) {
@@ -1046,7 +1048,8 @@ static bool amt_send_membership_update(struct amt_dev *amt,
 			    amt->gw_port,
 			    amt->relay_port,
 			    false,
-			    false);
+			    false,
+			    0);
 	amt_update_gw_status(amt, AMT_STATUS_SENT_UPDATE, true);
 	return false;
 }
@@ -1103,7 +1106,8 @@ static void amt_send_multicast_data(struct amt_dev *amt,
 			    amt->relay_port,
 			    tunnel->source_port,
 			    false,
-			    false);
+			    false,
+			    0);
 }
 
 static bool amt_send_membership_query(struct amt_dev *amt,
@@ -1131,7 +1135,7 @@ static bool amt_send_membership_query(struct amt_dev *amt,
 	fl4.flowi4_oif         = amt->stream_dev->ifindex;
 	fl4.daddr              = tunnel->ip4;
 	fl4.saddr              = amt->local_ip;
-	fl4.flowi4_tos         = AMT_TOS;
+	fl4.flowi4_dscp        = inet_dsfield_to_dscp(AMT_TOS);
 	fl4.flowi4_proto       = IPPROTO_UDP;
 	rt = ip_route_output_key(amt->net, &fl4);
 	if (IS_ERR(rt)) {
@@ -1161,7 +1165,8 @@ static bool amt_send_membership_query(struct amt_dev *amt,
 			    amt->relay_port,
 			    tunnel->source_port,
 			    false,
-			    false);
+			    false,
+			    0);
 	amt_update_relay_status(tunnel, AMT_STATUS_SENT_QUERY, true);
 	return false;
 }
@@ -3099,7 +3104,7 @@ static void amt_link_setup(struct net_device *dev)
 	dev->addr_len		= 0;
 	dev->priv_flags		|= IFF_NO_QUEUE;
 	dev->lltx		= true;
-	dev->netns_local	= true;
+	dev->netns_immutable	= true;
 	dev->features		|= NETIF_F_GSO_SOFTWARE;
 	dev->hw_features	|= NETIF_F_SG | NETIF_F_HW_CSUM;
 	dev->hw_features	|= NETIF_F_FRAGLIST | NETIF_F_RXCSUM;
@@ -3161,14 +3166,17 @@ static int amt_validate(struct nlattr *tb[], struct nlattr *data[],
 	return 0;
 }
 
-static int amt_newlink(struct net *net, struct net_device *dev,
-		       struct nlattr *tb[], struct nlattr *data[],
+static int amt_newlink(struct net_device *dev,
+		       struct rtnl_newlink_params *params,
 		       struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct amt_dev *amt = netdev_priv(dev);
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	int err = -EINVAL;
 
-	amt->net = net;
+	amt->net = link_net;
 	amt->mode = nla_get_u32(data[IFLA_AMT_MODE]);
 
 	if (data[IFLA_AMT_MAX_TUNNELS] &&
@@ -3183,7 +3191,7 @@ static int amt_newlink(struct net *net, struct net_device *dev,
 	amt->hash_buckets = AMT_HSIZE;
 	amt->nr_tunnels = 0;
 	get_random_bytes(&amt->hash_seed, sizeof(amt->hash_seed));
-	amt->stream_dev = dev_get_by_index(net,
+	amt->stream_dev = dev_get_by_index(link_net,
 					   nla_get_u32(data[IFLA_AMT_LINK]));
 	if (!amt->stream_dev) {
 		NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_LINK],
diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c
index 530c15d6a5eb..882972604c82 100644
--- a/drivers/net/arcnet/arcnet.c
+++ b/drivers/net/arcnet/arcnet.c
@@ -382,7 +382,7 @@ static void arcdev_setup(struct net_device *dev)
 
 static void arcnet_timer(struct timer_list *t)
 {
-	struct arcnet_local *lp = from_timer(lp, t, timer);
+	struct arcnet_local *lp = timer_container_of(lp, t, timer);
 	struct net_device *dev = lp->dev;
 
 	spin_lock_irq(&lp->lock);
@@ -616,7 +616,7 @@ int arcnet_close(struct net_device *dev)
 	struct arcnet_local *lp = netdev_priv(dev);
 
 	arcnet_led_event(dev, ARCNET_LED_EVENT_STOP);
-	del_timer_sync(&lp->timer);
+	timer_delete_sync(&lp->timer);
 
 	netif_stop_queue(dev);
 	netif_carrier_off(dev);
diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c
index c5e571ec94c9..0472bcdff130 100644
--- a/drivers/net/arcnet/com20020-pci.c
+++ b/drivers/net/arcnet/com20020-pci.c
@@ -251,18 +251,33 @@ static int com20020pci_probe(struct pci_dev *pdev,
 			card->tx_led.default_trigger = devm_kasprintf(&pdev->dev,
 							GFP_KERNEL, "arc%d-%d-tx",
 							dev->dev_id, i);
+			if (!card->tx_led.default_trigger) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
 							"pci:green:tx:%d-%d",
 							dev->dev_id, i);
-
+			if (!card->tx_led.name) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->tx_led.dev = &dev->dev;
 			card->recon_led.brightness_set = led_recon_set;
 			card->recon_led.default_trigger = devm_kasprintf(&pdev->dev,
 							GFP_KERNEL, "arc%d-%d-recon",
 							dev->dev_id, i);
+			if (!card->recon_led.default_trigger) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
 							"pci:red:recon:%d-%d",
 							dev->dev_id, i);
+			if (!card->recon_led.name) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->recon_led.dev = &dev->dev;
 
 			ret = devm_led_classdev_register(&pdev->dev, &card->tx_led);
diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index 70814303aab8..0df3208783ad 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -362,8 +362,8 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	udp_tunnel_xmit_skb(rt, sock->sk, skb, saddr, info->key.u.ipv4.dst,
 			    tos, ttl, df, sport, bareudp->port,
 			    !net_eq(bareudp->net, dev_net(bareudp->dev)),
-			    !test_bit(IP_TUNNEL_CSUM_BIT,
-				      info->key.tun_flags));
+			    !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags),
+			    0);
 	return 0;
 
 free_dst:
@@ -431,7 +431,8 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 			     &saddr, &daddr, prio, ttl,
 			     info->key.label, sport, bareudp->port,
 			     !test_bit(IP_TUNNEL_CSUM_BIT,
-				       info->key.tun_flags));
+				       info->key.tun_flags),
+			     0);
 	return 0;
 
 free_dst:
@@ -698,10 +699,13 @@ static void bareudp_dellink(struct net_device *dev, struct list_head *head)
 	unregister_netdevice_queue(dev, head);
 }
 
-static int bareudp_newlink(struct net *net, struct net_device *dev,
-			   struct nlattr *tb[], struct nlattr *data[],
+static int bareudp_newlink(struct net_device *dev,
+			   struct rtnl_newlink_params *params,
 			   struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	struct bareudp_conf conf;
 	int err;
 
@@ -709,7 +713,7 @@ static int bareudp_newlink(struct net *net, struct net_device *dev,
 	if (err)
 		return err;
 
-	err = bareudp_configure(net, dev, &conf, extack);
+	err = bareudp_configure(link_net, dev, &conf, extack);
 	if (err)
 		return err;
 
@@ -774,27 +778,19 @@ static __net_init int bareudp_init_net(struct net *net)
 	return 0;
 }
 
-static void bareudp_destroy_tunnels(struct net *net, struct list_head *head)
+static void __net_exit bareudp_exit_rtnl_net(struct net *net,
+					     struct list_head *dev_kill_list)
 {
 	struct bareudp_net *bn = net_generic(net, bareudp_net_id);
 	struct bareudp_dev *bareudp, *next;
 
 	list_for_each_entry_safe(bareudp, next, &bn->bareudp_list, next)
-		unregister_netdevice_queue(bareudp->dev, head);
-}
-
-static void __net_exit bareudp_exit_batch_rtnl(struct list_head *net_list,
-					       struct list_head *dev_kill_list)
-{
-	struct net *net;
-
-	list_for_each_entry(net, net_list, exit_list)
-		bareudp_destroy_tunnels(net, dev_kill_list);
+		bareudp_dellink(bareudp->dev, dev_kill_list);
 }
 
 static struct pernet_operations bareudp_net_ops = {
 	.init = bareudp_init_net,
-	.exit_batch_rtnl = bareudp_exit_batch_rtnl,
+	.exit_rtnl = bareudp_exit_rtnl_net,
 	.id   = &bareudp_net_id,
 	.size = sizeof(struct bareudp_net),
 };
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index c6807e473ab7..1a8de2bf8655 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -76,6 +76,7 @@ enum ad_link_speed_type {
 	AD_LINK_SPEED_200000MBPS,
 	AD_LINK_SPEED_400000MBPS,
 	AD_LINK_SPEED_800000MBPS,
+	AD_LINK_SPEED_1600000MBPS,
 };
 
 /* compare MAC addresses */
@@ -95,13 +96,13 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker);
 static void ad_mux_machine(struct port *port, bool *update_slave_arr);
 static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port);
 static void ad_tx_machine(struct port *port);
-static void ad_periodic_machine(struct port *port, struct bond_params *bond_params);
+static void ad_periodic_machine(struct port *port);
 static void ad_port_selection_logic(struct port *port, bool *update_slave_arr);
 static void ad_agg_selection_logic(struct aggregator *aggregator,
 				   bool *update_slave_arr);
 static void ad_clear_agg(struct aggregator *aggregator);
 static void ad_initialize_agg(struct aggregator *aggregator);
-static void ad_initialize_port(struct port *port, int lacp_fast);
+static void ad_initialize_port(struct port *port, const struct bond_params *bond_params);
 static void ad_enable_collecting(struct port *port);
 static void ad_disable_distributing(struct port *port,
 				    bool *update_slave_arr);
@@ -300,6 +301,7 @@ static inline int __check_agg_selection_timer(struct port *port)
  *     %AD_LINK_SPEED_200000MBPS
  *     %AD_LINK_SPEED_400000MBPS
  *     %AD_LINK_SPEED_800000MBPS
+ *     %AD_LINK_SPEED_1600000MBPS
  */
 static u16 __get_link_speed(struct port *port)
 {
@@ -379,6 +381,10 @@ static u16 __get_link_speed(struct port *port)
 			speed = AD_LINK_SPEED_800000MBPS;
 			break;
 
+		case SPEED_1600000:
+			speed = AD_LINK_SPEED_1600000MBPS;
+			break;
+
 		default:
 			/* unknown speed value from ethtool. shouldn't happen */
 			if (slave->speed != SPEED_UNKNOWN)
@@ -436,6 +442,7 @@ static void __ad_actor_update_port(struct port *port)
 
 	port->actor_system = BOND_AD_INFO(bond).system.sys_mac_addr;
 	port->actor_system_priority = BOND_AD_INFO(bond).system.sys_priority;
+	port->actor_port_priority = SLAVE_AD_INFO(port->slave)->port_priority;
 }
 
 /* Conversions */
@@ -746,6 +753,18 @@ static int __agg_active_ports(struct aggregator *agg)
 	return active;
 }
 
+static unsigned int __agg_ports_priority(const struct aggregator *agg)
+{
+	struct port *port = agg->lag_ports;
+	unsigned int prio = 0;
+
+	for (; port; port = port->next_port_in_aggregator)
+		if (port->is_enabled)
+			prio += port->actor_port_priority;
+
+	return prio;
+}
+
 /**
  * __get_agg_bandwidth - get the total bandwidth of an aggregator
  * @aggregator: the aggregator we're looking at
@@ -809,6 +828,9 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator)
 		case AD_LINK_SPEED_800000MBPS:
 			bandwidth = nports * 800000;
 			break;
+		case AD_LINK_SPEED_1600000MBPS:
+			bandwidth = nports * 1600000;
+			break;
 		default:
 			bandwidth = 0; /* to silence the compiler */
 		}
@@ -982,6 +1004,17 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker)
 	return 0;
 }
 
+static void ad_cond_set_peer_notif(struct port *port)
+{
+	struct bonding *bond = port->slave->bond;
+
+	if (bond->params.broadcast_neighbor && rtnl_trylock()) {
+		bond->send_peer_notif = bond->params.num_peer_notif *
+			max(1, bond->params.peer_notif_delay);
+		rtnl_unlock();
+	}
+}
+
 /**
  * ad_mux_machine - handle a port's mux state machine
  * @port: the port we're looking at
@@ -1296,10 +1329,16 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
 			 * case of EXPIRED even if LINK_DOWN didn't arrive for
 			 * the port.
 			 */
-			port->partner_oper.port_state &= ~LACP_STATE_SYNCHRONIZATION;
 			port->sm_vars &= ~AD_PORT_MATCHED;
+			/* Based on IEEE 8021AX-2014, Figure 6-18 - Receive
+			 * machine state diagram, the statue should be
+			 * Partner_Oper_Port_State.Synchronization = FALSE;
+			 * Partner_Oper_Port_State.LACP_Timeout = Short Timeout;
+			 * start current_while_timer(Short Timeout);
+			 * Actor_Oper_Port_State.Expired = TRUE;
+			 */
+			port->partner_oper.port_state &= ~LACP_STATE_SYNCHRONIZATION;
 			port->partner_oper.port_state |= LACP_STATE_LACP_TIMEOUT;
-			port->partner_oper.port_state |= LACP_STATE_LACP_ACTIVITY;
 			port->sm_rx_timer_counter = __ad_timer_to_ticks(AD_CURRENT_WHILE_TIMER, (u16)(AD_SHORT_TIMEOUT));
 			port->actor_oper_port_state |= LACP_STATE_EXPIRED;
 			port->sm_vars |= AD_PORT_CHURNED;
@@ -1378,7 +1417,7 @@ static void ad_tx_machine(struct port *port)
 	/* check if tx timer expired, to verify that we do not send more than
 	 * 3 packets per second
 	 */
-	if (port->sm_tx_timer_counter && !(--port->sm_tx_timer_counter)) {
+	if (!port->sm_tx_timer_counter || !(--port->sm_tx_timer_counter)) {
 		/* check if there is something to send */
 		if (port->ntt && (port->sm_vars & AD_PORT_LACP_ENABLED)) {
 			__update_lacpdu_from_port(port);
@@ -1393,23 +1432,23 @@ static void ad_tx_machine(struct port *port)
 				 * again until demanded
 				 */
 				port->ntt = false;
+
+				/* restart tx timer(to verify that we will not
+				 * exceed AD_MAX_TX_IN_SECOND
+				 */
+				port->sm_tx_timer_counter = ad_ticks_per_sec / AD_MAX_TX_IN_SECOND;
 			}
 		}
-		/* restart tx timer(to verify that we will not exceed
-		 * AD_MAX_TX_IN_SECOND
-		 */
-		port->sm_tx_timer_counter = ad_ticks_per_sec/AD_MAX_TX_IN_SECOND;
 	}
 }
 
 /**
  * ad_periodic_machine - handle a port's periodic state machine
  * @port: the port we're looking at
- * @bond_params: bond parameters we will use
  *
  * Turn ntt flag on priodically to perform periodic transmission of lacpdu's.
  */
-static void ad_periodic_machine(struct port *port, struct bond_params *bond_params)
+static void ad_periodic_machine(struct port *port)
 {
 	periodic_states_t last_state;
 
@@ -1418,8 +1457,7 @@ static void ad_periodic_machine(struct port *port, struct bond_params *bond_para
 
 	/* check if port was reinitialized */
 	if (((port->sm_vars & AD_PORT_BEGIN) || !(port->sm_vars & AD_PORT_LACP_ENABLED) || !port->is_enabled) ||
-	    (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY)) ||
-	    !bond_params->lacp_active) {
+	    (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY))) {
 		port->sm_periodic_state = AD_NO_PERIODIC;
 	}
 	/* check if state machine should change state */
@@ -1691,6 +1729,9 @@ static struct aggregator *ad_agg_selection_test(struct aggregator *best,
 	 * 4.  Therefore, current and best both have partner replies or
 	 *     both do not, so perform selection policy:
 	 *
+	 * BOND_AD_PRIO: Select by total priority of ports. If priority
+	 *     is equal, select by count.
+	 *
 	 * BOND_AD_COUNT: Select by count of ports.  If count is equal,
 	 *     select by bandwidth.
 	 *
@@ -1712,6 +1753,14 @@ static struct aggregator *ad_agg_selection_test(struct aggregator *best,
 		return best;
 
 	switch (__get_agg_selection_mode(curr->lag_ports)) {
+	case BOND_AD_PRIO:
+		if (__agg_ports_priority(curr) > __agg_ports_priority(best))
+			return curr;
+
+		if (__agg_ports_priority(curr) < __agg_ports_priority(best))
+			return best;
+
+		fallthrough;
 	case BOND_AD_COUNT:
 		if (__agg_active_ports(curr) > __agg_active_ports(best))
 			return curr;
@@ -1777,6 +1826,10 @@ static int agg_device_up(const struct aggregator *agg)
  * (slaves), and reselect whenever a link state change takes place or the
  * set of slaves in the bond changes.
  *
+ * BOND_AD_PRIO: select the aggregator with highest total priority of ports
+ * (slaves), and reselect whenever a link state change takes place or the
+ * set of slaves in the bond changes.
+ *
  * FIXME: this function MUST be called with the first agg in the bond, or
  * __get_active_agg() won't work correctly. This function should be better
  * called with the bond itself, and retrieve the first agg from it.
@@ -1943,16 +1996,16 @@ static void ad_initialize_agg(struct aggregator *aggregator)
 /**
  * ad_initialize_port - initialize a given port's parameters
  * @port: the port we're looking at
- * @lacp_fast: boolean. whether fast periodic should be used
+ * @bond_params: bond parameters we will use
  */
-static void ad_initialize_port(struct port *port, int lacp_fast)
+static void ad_initialize_port(struct port *port, const struct bond_params *bond_params)
 {
 	static const struct port_params tmpl = {
 		.system_priority = 0xffff,
 		.key             = 1,
 		.port_number     = 1,
 		.port_priority   = 0xff,
-		.port_state      = 1,
+		.port_state      = 0,
 	};
 	static const struct lacpdu lacpdu = {
 		.subtype		= 0x01,
@@ -1970,12 +2023,14 @@ static void ad_initialize_port(struct port *port, int lacp_fast)
 		port->actor_port_priority = 0xff;
 		port->actor_port_aggregator_identifier = 0;
 		port->ntt = false;
-		port->actor_admin_port_state = LACP_STATE_AGGREGATION |
-					       LACP_STATE_LACP_ACTIVITY;
-		port->actor_oper_port_state  = LACP_STATE_AGGREGATION |
-					       LACP_STATE_LACP_ACTIVITY;
+		port->actor_admin_port_state = LACP_STATE_AGGREGATION;
+		port->actor_oper_port_state  = LACP_STATE_AGGREGATION;
+		if (bond_params->lacp_active) {
+			port->actor_admin_port_state |= LACP_STATE_LACP_ACTIVITY;
+			port->actor_oper_port_state  |= LACP_STATE_LACP_ACTIVITY;
+		}
 
-		if (lacp_fast)
+		if (bond_params->lacp_fast)
 			port->actor_oper_port_state |= LACP_STATE_LACP_TIMEOUT;
 
 		memcpy(&port->partner_admin, &tmpl, sizeof(tmpl));
@@ -2061,6 +2116,8 @@ static void ad_enable_collecting_distributing(struct port *port,
 		__enable_port(port);
 		/* Slave array needs update */
 		*update_slave_arr = true;
+		/* Should notify peers if possible */
+		ad_cond_set_peer_notif(port);
 	}
 }
 
@@ -2187,7 +2244,10 @@ void bond_3ad_bind_slave(struct slave *slave)
 		/* port initialization */
 		port = &(SLAVE_AD_INFO(slave)->port);
 
-		ad_initialize_port(port, bond->params.lacp_fast);
+		ad_initialize_port(port, &bond->params);
+
+		/* Port priority is initialized. Update it to slave's ad info */
+		SLAVE_AD_INFO(slave)->port_priority = port->actor_port_priority;
 
 		port->slave = slave;
 		port->actor_port_number = SLAVE_AD_INFO(slave)->id;
@@ -2499,7 +2559,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 		}
 
 		ad_rx_machine(NULL, port);
-		ad_periodic_machine(port, &bond->params);
+		ad_periodic_machine(port);
 		ad_port_selection_logic(port, &update_slave_arr);
 		ad_mux_machine(port, &update_slave_arr);
 		ad_tx_machine(port);
@@ -2869,6 +2929,31 @@ void bond_3ad_update_lacp_rate(struct bonding *bond)
 	spin_unlock_bh(&bond->mode_lock);
 }
 
+/**
+ * bond_3ad_update_lacp_active - change the lacp active
+ * @bond: bonding struct
+ *
+ * Update actor_oper_port_state when lacp_active is modified.
+ */
+void bond_3ad_update_lacp_active(struct bonding *bond)
+{
+	struct port *port = NULL;
+	struct list_head *iter;
+	struct slave *slave;
+	int lacp_active;
+
+	lacp_active = bond->params.lacp_active;
+	spin_lock_bh(&bond->mode_lock);
+	bond_for_each_slave(bond, slave, iter) {
+		port = &(SLAVE_AD_INFO(slave)->port);
+		if (lacp_active)
+			port->actor_oper_port_state |= LACP_STATE_LACP_ACTIVITY;
+		else
+			port->actor_oper_port_state &= ~LACP_STATE_LACP_ACTIVITY;
+	}
+	spin_unlock_bh(&bond->mode_lock);
+}
+
 size_t bond_3ad_stats_size(void)
 {
 	return nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_RX */
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 7edf0fd58c34..2d37b07c8215 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1035,7 +1035,7 @@ static int alb_set_slave_mac_addr(struct slave *slave, const u8 addr[],
 	 */
 	memcpy(ss.__data, addr, len);
 	ss.ss_family = dev->type;
-	if (dev_set_mac_address(dev, (struct sockaddr *)&ss, NULL)) {
+	if (dev_set_mac_address(dev, &ss, NULL)) {
 		slave_err(slave->bond->dev, dev, "dev_set_mac_address on slave failed! ALB mode requires that the base driver support setting the hw address also when the network device's interface is open\n");
 		return -EOPNOTSUPP;
 	}
@@ -1273,8 +1273,7 @@ unwind:
 			break;
 		bond_hw_addr_copy(tmp_addr, rollback_slave->dev->dev_addr,
 				  rollback_slave->dev->addr_len);
-		dev_set_mac_address(rollback_slave->dev,
-				    (struct sockaddr *)&ss, NULL);
+		dev_set_mac_address(rollback_slave->dev, &ss, NULL);
 		dev_addr_set(rollback_slave->dev, tmp_addr);
 	}
 
@@ -1763,8 +1762,7 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 				  bond->dev->addr_len);
 		ss.ss_family = bond->dev->type;
 		/* we don't care if it can't change its mac, best effort */
-		dev_set_mac_address(new_slave->dev, (struct sockaddr *)&ss,
-				    NULL);
+		dev_set_mac_address(new_slave->dev, &ss, NULL);
 
 		dev_addr_set(new_slave->dev, tmp_addr);
 	}
diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c
index b19492a7f6ad..8adbec7c5084 100644
--- a/drivers/net/bonding/bond_debugfs.c
+++ b/drivers/net/bonding/bond_debugfs.c
@@ -63,13 +63,8 @@ void bond_debug_unregister(struct bonding *bond)
 
 void bond_debug_reregister(struct bonding *bond)
 {
-	struct dentry *d;
-
-	d = debugfs_rename(bonding_debug_root, bond->debug_dir,
-			   bonding_debug_root, bond->dev->name);
-	if (!IS_ERR(d)) {
-		bond->debug_dir = d;
-	} else {
+	int err = debugfs_change_name(bond->debug_dir, "%s", bond->dev->name);
+	if (err) {
 		netdev_warn(bond->dev, "failed to reregister, so just unregister old one\n");
 		bond_debug_unregister(bond);
 	}
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 7b78c2bada81..3d56339a8a10 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -90,6 +90,7 @@
 #include <net/tls.h>
 #endif
 #include <net/ip6_route.h>
+#include <net/netdev_lock.h>
 #include <net/xdp.h>
 
 #include "bonding_priv.h"
@@ -141,8 +142,7 @@ module_param(downdelay, int, 0);
 MODULE_PARM_DESC(downdelay, "Delay before considering link down, "
 			    "in milliseconds");
 module_param(use_carrier, int, 0);
-MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; "
-			      "0 for off, 1 for on (default)");
+MODULE_PARM_DESC(use_carrier, "option obsolete, use_carrier cannot be disabled");
 module_param(mode, charp, 0);
 MODULE_PARM_DESC(mode, "Mode of operation; 0 for balance-rr, "
 		       "1 for active-backup, 2 for balance-xor, "
@@ -211,6 +211,8 @@ atomic_t netpoll_block_tx = ATOMIC_INIT(0);
 
 unsigned int bond_net_id __read_mostly;
 
+DEFINE_STATIC_KEY_FALSE(bond_bcast_neigh_enabled);
+
 static const struct flow_dissector_key flow_keys_bonding_keys[] = {
 	{
 		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
@@ -322,9 +324,9 @@ static bool bond_sk_check(struct bonding *bond)
 	}
 }
 
-static bool bond_xdp_check(struct bonding *bond)
+bool bond_xdp_check(struct bonding *bond, int mode)
 {
-	switch (BOND_MODE(bond)) {
+	switch (mode) {
 	case BOND_MODE_ROUNDROBIN:
 	case BOND_MODE_ACTIVEBACKUP:
 		return true;
@@ -432,9 +434,6 @@ static struct net_device *bond_ipsec_dev(struct xfrm_state *xs)
 	struct bonding *bond;
 	struct slave *slave;
 
-	if (!bond_dev)
-		return NULL;
-
 	bond = netdev_priv(bond_dev);
 	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
 		return NULL;
@@ -455,13 +454,14 @@ static struct net_device *bond_ipsec_dev(struct xfrm_state *xs)
 
 /**
  * bond_ipsec_add_sa - program device with a security association
+ * @bond_dev: pointer to the bond net device
  * @xs: pointer to transformer state struct
  * @extack: extack point to fill failure reason
  **/
-static int bond_ipsec_add_sa(struct xfrm_state *xs,
+static int bond_ipsec_add_sa(struct net_device *bond_dev,
+			     struct xfrm_state *xs,
 			     struct netlink_ext_ack *extack)
 {
-	struct net_device *bond_dev = xs->xso.dev;
 	struct net_device *real_dev;
 	netdevice_tracker tracker;
 	struct bond_ipsec *ipsec;
@@ -497,9 +497,9 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs,
 		goto out;
 	}
 
-	xs->xso.real_dev = real_dev;
-	err = real_dev->xfrmdev_ops->xdo_dev_state_add(xs, extack);
+	err = real_dev->xfrmdev_ops->xdo_dev_state_add(real_dev, xs, extack);
 	if (!err) {
+		xs->xso.real_dev = real_dev;
 		ipsec->xs = xs;
 		INIT_LIST_HEAD(&ipsec->list);
 		mutex_lock(&bond->ipsec_lock);
@@ -541,11 +541,25 @@ static void bond_ipsec_add_sa_all(struct bonding *bond)
 		if (ipsec->xs->xso.real_dev == real_dev)
 			continue;
 
-		ipsec->xs->xso.real_dev = real_dev;
-		if (real_dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) {
+		if (real_dev->xfrmdev_ops->xdo_dev_state_add(real_dev,
+							     ipsec->xs, NULL)) {
 			slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__);
-			ipsec->xs->xso.real_dev = NULL;
+			continue;
 		}
+
+		spin_lock_bh(&ipsec->xs->lock);
+		/* xs might have been killed by the user during the migration
+		 * to the new dev, but bond_ipsec_del_sa() should have done
+		 * nothing, as xso.real_dev is NULL.
+		 * Delete it from the device we just added it to. The pending
+		 * bond_ipsec_free_sa() call will do the rest of the cleanup.
+		 */
+		if (ipsec->xs->km.state == XFRM_STATE_DEAD &&
+		    real_dev->xfrmdev_ops->xdo_dev_state_delete)
+			real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev,
+								    ipsec->xs);
+		ipsec->xs->xso.real_dev = real_dev;
+		spin_unlock_bh(&ipsec->xs->lock);
 	}
 out:
 	mutex_unlock(&bond->ipsec_lock);
@@ -553,54 +567,27 @@ out:
 
 /**
  * bond_ipsec_del_sa - clear out this specific SA
+ * @bond_dev: pointer to the bond net device
  * @xs: pointer to transformer state struct
  **/
-static void bond_ipsec_del_sa(struct xfrm_state *xs)
+static void bond_ipsec_del_sa(struct net_device *bond_dev,
+			      struct xfrm_state *xs)
 {
-	struct net_device *bond_dev = xs->xso.dev;
 	struct net_device *real_dev;
-	netdevice_tracker tracker;
-	struct bond_ipsec *ipsec;
-	struct bonding *bond;
-	struct slave *slave;
 
-	if (!bond_dev)
+	if (!bond_dev || !xs->xso.real_dev)
 		return;
 
-	rcu_read_lock();
-	bond = netdev_priv(bond_dev);
-	slave = rcu_dereference(bond->curr_active_slave);
-	real_dev = slave ? slave->dev : NULL;
-	netdev_hold(real_dev, &tracker, GFP_ATOMIC);
-	rcu_read_unlock();
-
-	if (!slave)
-		goto out;
-
-	if (!xs->xso.real_dev)
-		goto out;
-
-	WARN_ON(xs->xso.real_dev != real_dev);
+	real_dev = xs->xso.real_dev;
 
 	if (!real_dev->xfrmdev_ops ||
 	    !real_dev->xfrmdev_ops->xdo_dev_state_delete ||
 	    netif_is_bond_master(real_dev)) {
 		slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__);
-		goto out;
+		return;
 	}
 
-	real_dev->xfrmdev_ops->xdo_dev_state_delete(xs);
-out:
-	netdev_put(real_dev, &tracker);
-	mutex_lock(&bond->ipsec_lock);
-	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
-		if (ipsec->xs == xs) {
-			list_del(&ipsec->list);
-			kfree(ipsec);
-			break;
-		}
-	}
-	mutex_unlock(&bond->ipsec_lock);
+	real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev, xs);
 }
 
 static void bond_ipsec_del_sa_all(struct bonding *bond)
@@ -626,46 +613,55 @@ static void bond_ipsec_del_sa_all(struct bonding *bond)
 			slave_warn(bond_dev, real_dev,
 				   "%s: no slave xdo_dev_state_delete\n",
 				   __func__);
-		} else {
-			real_dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
-			if (real_dev->xfrmdev_ops->xdo_dev_state_free)
-				real_dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs);
+			continue;
 		}
+
+		spin_lock_bh(&ipsec->xs->lock);
+		ipsec->xs->xso.real_dev = NULL;
+		/* Don't double delete states killed by the user. */
+		if (ipsec->xs->km.state != XFRM_STATE_DEAD)
+			real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev,
+								    ipsec->xs);
+		spin_unlock_bh(&ipsec->xs->lock);
+
+		if (real_dev->xfrmdev_ops->xdo_dev_state_free)
+			real_dev->xfrmdev_ops->xdo_dev_state_free(real_dev,
+								  ipsec->xs);
 	}
 	mutex_unlock(&bond->ipsec_lock);
 }
 
-static void bond_ipsec_free_sa(struct xfrm_state *xs)
+static void bond_ipsec_free_sa(struct net_device *bond_dev,
+			       struct xfrm_state *xs)
 {
-	struct net_device *bond_dev = xs->xso.dev;
 	struct net_device *real_dev;
-	netdevice_tracker tracker;
+	struct bond_ipsec *ipsec;
 	struct bonding *bond;
-	struct slave *slave;
 
 	if (!bond_dev)
 		return;
 
-	rcu_read_lock();
 	bond = netdev_priv(bond_dev);
-	slave = rcu_dereference(bond->curr_active_slave);
-	real_dev = slave ? slave->dev : NULL;
-	netdev_hold(real_dev, &tracker, GFP_ATOMIC);
-	rcu_read_unlock();
-
-	if (!slave)
-		goto out;
 
+	mutex_lock(&bond->ipsec_lock);
 	if (!xs->xso.real_dev)
 		goto out;
 
-	WARN_ON(xs->xso.real_dev != real_dev);
+	real_dev = xs->xso.real_dev;
 
-	if (real_dev && real_dev->xfrmdev_ops &&
+	xs->xso.real_dev = NULL;
+	if (real_dev->xfrmdev_ops &&
 	    real_dev->xfrmdev_ops->xdo_dev_state_free)
-		real_dev->xfrmdev_ops->xdo_dev_state_free(xs);
+		real_dev->xfrmdev_ops->xdo_dev_state_free(real_dev, xs);
 out:
-	netdev_put(real_dev, &tracker);
+	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+		if (ipsec->xs == xs) {
+			list_del(&ipsec->list);
+			kfree(ipsec);
+			break;
+		}
+	}
+	mutex_unlock(&bond->ipsec_lock);
 }
 
 /**
@@ -676,22 +672,16 @@ out:
 static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
 {
 	struct net_device *real_dev;
-	bool ok = false;
 
 	rcu_read_lock();
 	real_dev = bond_ipsec_dev(xs);
-	if (!real_dev)
-		goto out;
-
-	if (!real_dev->xfrmdev_ops ||
-	    !real_dev->xfrmdev_ops->xdo_dev_offload_ok ||
-	    netif_is_bond_master(real_dev))
-		goto out;
+	if (!real_dev || netif_is_bond_master(real_dev)) {
+		rcu_read_unlock();
+		return false;
+	}
 
-	ok = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
-out:
 	rcu_read_unlock();
-	return ok;
+	return true;
 }
 
 /**
@@ -839,73 +829,6 @@ const char *bond_slave_link_status(s8 link)
 	}
 }
 
-/* if <dev> supports MII link status reporting, check its link status.
- *
- * We either do MII/ETHTOOL ioctls, or check netif_carrier_ok(),
- * depending upon the setting of the use_carrier parameter.
- *
- * Return either BMSR_LSTATUS, meaning that the link is up (or we
- * can't tell and just pretend it is), or 0, meaning that the link is
- * down.
- *
- * If reporting is non-zero, instead of faking link up, return -1 if
- * both ETHTOOL and MII ioctls fail (meaning the device does not
- * support them).  If use_carrier is set, return whatever it says.
- * It'd be nice if there was a good way to tell if a driver supports
- * netif_carrier, but there really isn't.
- */
-static int bond_check_dev_link(struct bonding *bond,
-			       struct net_device *slave_dev, int reporting)
-{
-	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
-	int (*ioctl)(struct net_device *, struct ifreq *, int);
-	struct ifreq ifr;
-	struct mii_ioctl_data *mii;
-
-	if (!reporting && !netif_running(slave_dev))
-		return 0;
-
-	if (bond->params.use_carrier)
-		return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0;
-
-	/* Try to get link status using Ethtool first. */
-	if (slave_dev->ethtool_ops->get_link)
-		return slave_dev->ethtool_ops->get_link(slave_dev) ?
-			BMSR_LSTATUS : 0;
-
-	/* Ethtool can't be used, fallback to MII ioctls. */
-	ioctl = slave_ops->ndo_eth_ioctl;
-	if (ioctl) {
-		/* TODO: set pointer to correct ioctl on a per team member
-		 *       bases to make this more efficient. that is, once
-		 *       we determine the correct ioctl, we will always
-		 *       call it and not the others for that team
-		 *       member.
-		 */
-
-		/* We cannot assume that SIOCGMIIPHY will also read a
-		 * register; not all network drivers (e.g., e100)
-		 * support that.
-		 */
-
-		/* Yes, the mii is overlaid on the ifreq.ifr_ifru */
-		strscpy_pad(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
-		mii = if_mii(&ifr);
-		if (ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) {
-			mii->reg_num = MII_BMSR;
-			if (ioctl(slave_dev, &ifr, SIOCGMIIREG) == 0)
-				return mii->val_out & BMSR_LSTATUS;
-		}
-	}
-
-	/* If reporting, report that either there's no ndo_eth_ioctl,
-	 * or both SIOCGMIIREG and get_link failed (meaning that we
-	 * cannot report link status).  If not reporting, pretend
-	 * we're ok.
-	 */
-	return reporting ? -1 : BMSR_LSTATUS;
-}
-
 /*----------------------------- Multicast list ------------------------------*/
 
 /* Push the promiscuity flag down to appropriate slaves */
@@ -1045,7 +968,7 @@ static int bond_set_dev_addr(struct net_device *bond_dev,
 
 	slave_dbg(bond_dev, slave_dev, "bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n",
 		  bond_dev, slave_dev, slave_dev->addr_len);
-	err = dev_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL);
+	err = netif_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL);
 	if (err)
 		return err;
 
@@ -1119,8 +1042,7 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 			ss.ss_family = bond->dev->type;
 		}
 
-		rv = dev_set_mac_address(new_active->dev,
-					 (struct sockaddr *)&ss, NULL);
+		rv = dev_set_mac_address(new_active->dev, &ss, NULL);
 		if (rv) {
 			slave_err(bond->dev, new_active->dev, "Error %d setting MAC of new active slave\n",
 				  -rv);
@@ -1134,8 +1056,7 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 				  new_active->dev->addr_len);
 		ss.ss_family = old_active->dev->type;
 
-		rv = dev_set_mac_address(old_active->dev,
-					 (struct sockaddr *)&ss, NULL);
+		rv = dev_set_mac_address(old_active->dev, &ss, NULL);
 		if (rv)
 			slave_err(bond->dev, old_active->dev, "Error %d setting MAC of old active slave\n",
 				  -rv);
@@ -1244,17 +1165,32 @@ static struct slave *bond_find_best_slave(struct bonding *bond)
 /* must be called in RCU critical section or with RTNL held */
 static bool bond_should_notify_peers(struct bonding *bond)
 {
-	struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave);
+	struct bond_up_slave *usable;
+	struct slave *slave = NULL;
 
-	if (!slave || !bond->send_peer_notif ||
+	if (!bond->send_peer_notif ||
 	    bond->send_peer_notif %
 	    max(1, bond->params.peer_notif_delay) != 0 ||
-	    !netif_carrier_ok(bond->dev) ||
-	    test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
+	    !netif_carrier_ok(bond->dev))
 		return false;
 
+	/* The send_peer_notif is set by active-backup or 8023ad
+	 * mode, and cleared in bond_close() when changing mode.
+	 * It is safe to only check bond mode here.
+	 */
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
+		usable = rcu_dereference_rtnl(bond->usable_slaves);
+		if (!usable || !READ_ONCE(usable->count))
+			return false;
+	} else {
+		slave = rcu_dereference_rtnl(bond->curr_active_slave);
+		if (!slave || test_bit(__LINK_STATE_LINKWATCH_PENDING,
+				       &slave->dev->state))
+			return false;
+	}
+
 	netdev_dbg(bond->dev, "bond_should_notify_peers: slave %s\n",
-		   slave ? slave->dev->name : "NULL");
+		   slave ? slave->dev->name : "all");
 
 	return true;
 }
@@ -1532,97 +1468,6 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
 	return features;
 }
 
-#define BOND_VLAN_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
-				 NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \
-				 NETIF_F_GSO_ENCAP_ALL | \
-				 NETIF_F_HIGHDMA | NETIF_F_LRO)
-
-#define BOND_ENC_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
-				 NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE)
-
-#define BOND_MPLS_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
-				 NETIF_F_GSO_SOFTWARE)
-
-
-static void bond_compute_features(struct bonding *bond)
-{
-	unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
-					IFF_XMIT_DST_RELEASE_PERM;
-	netdev_features_t gso_partial_features = NETIF_F_GSO_ESP;
-	netdev_features_t vlan_features = BOND_VLAN_FEATURES;
-	netdev_features_t enc_features  = BOND_ENC_FEATURES;
-#ifdef CONFIG_XFRM_OFFLOAD
-	netdev_features_t xfrm_features  = BOND_XFRM_FEATURES;
-#endif /* CONFIG_XFRM_OFFLOAD */
-	netdev_features_t mpls_features  = BOND_MPLS_FEATURES;
-	struct net_device *bond_dev = bond->dev;
-	struct list_head *iter;
-	struct slave *slave;
-	unsigned short max_hard_header_len = ETH_HLEN;
-	unsigned int tso_max_size = TSO_MAX_SIZE;
-	u16 tso_max_segs = TSO_MAX_SEGS;
-
-	if (!bond_has_slaves(bond))
-		goto done;
-
-	vlan_features = netdev_base_features(vlan_features);
-	mpls_features = netdev_base_features(mpls_features);
-
-	bond_for_each_slave(bond, slave, iter) {
-		vlan_features = netdev_increment_features(vlan_features,
-			slave->dev->vlan_features, BOND_VLAN_FEATURES);
-
-		enc_features = netdev_increment_features(enc_features,
-							 slave->dev->hw_enc_features,
-							 BOND_ENC_FEATURES);
-
-#ifdef CONFIG_XFRM_OFFLOAD
-		xfrm_features = netdev_increment_features(xfrm_features,
-							  slave->dev->hw_enc_features,
-							  BOND_XFRM_FEATURES);
-#endif /* CONFIG_XFRM_OFFLOAD */
-
-		if (slave->dev->hw_enc_features & NETIF_F_GSO_PARTIAL)
-			gso_partial_features &= slave->dev->gso_partial_features;
-
-		mpls_features = netdev_increment_features(mpls_features,
-							  slave->dev->mpls_features,
-							  BOND_MPLS_FEATURES);
-
-		dst_release_flag &= slave->dev->priv_flags;
-		if (slave->dev->hard_header_len > max_hard_header_len)
-			max_hard_header_len = slave->dev->hard_header_len;
-
-		tso_max_size = min(tso_max_size, slave->dev->tso_max_size);
-		tso_max_segs = min(tso_max_segs, slave->dev->tso_max_segs);
-	}
-	bond_dev->hard_header_len = max_hard_header_len;
-
-	if (gso_partial_features & NETIF_F_GSO_ESP)
-		bond_dev->gso_partial_features |= NETIF_F_GSO_ESP;
-	else
-		bond_dev->gso_partial_features &= ~NETIF_F_GSO_ESP;
-
-done:
-	bond_dev->vlan_features = vlan_features;
-	bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
-				    NETIF_F_HW_VLAN_CTAG_TX |
-				    NETIF_F_HW_VLAN_STAG_TX;
-#ifdef CONFIG_XFRM_OFFLOAD
-	bond_dev->hw_enc_features |= xfrm_features;
-#endif /* CONFIG_XFRM_OFFLOAD */
-	bond_dev->mpls_features = mpls_features;
-	netif_set_tso_max_segs(bond_dev, tso_max_segs);
-	netif_set_tso_max_size(bond_dev, tso_max_size);
-
-	bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
-	if ((bond_dev->priv_flags & IFF_XMIT_DST_RELEASE_PERM) &&
-	    dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM))
-		bond_dev->priv_flags |= IFF_XMIT_DST_RELEASE;
-
-	netdev_change_features(bond_dev);
-}
-
 static void bond_setup_by_slave(struct net_device *bond_dev,
 				struct net_device *slave_dev)
 {
@@ -1937,7 +1782,7 @@ void bond_xdp_set_features(struct net_device *bond_dev)
 
 	ASSERT_RTNL();
 
-	if (!bond_xdp_check(bond) || !bond_has_slaves(bond)) {
+	if (!bond_xdp_check(bond, BOND_MODE(bond)) || !bond_has_slaves(bond)) {
 		xdp_clear_features_flag(bond_dev);
 		return;
 	}
@@ -1958,7 +1803,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
 	struct slave *new_slave = NULL, *prev_slave;
 	struct sockaddr_storage ss;
-	int link_reporting;
 	int res = 0, i;
 
 	if (slave_dev->flags & IFF_MASTER &&
@@ -1968,12 +1812,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		return -EPERM;
 	}
 
-	if (!bond->params.use_carrier &&
-	    slave_dev->ethtool_ops->get_link == NULL &&
-	    slave_ops->ndo_eth_ioctl == NULL) {
-		slave_warn(bond_dev, slave_dev, "no link monitoring support\n");
-	}
-
 	/* already in-use? */
 	if (netdev_is_rx_handler_busy(slave_dev)) {
 		SLAVE_NL_ERR(bond_dev, slave_dev, extack,
@@ -2122,15 +1960,27 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		 * set the master's mac address to that of the first slave
 		 */
 		memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
-		ss.ss_family = slave_dev->type;
-		res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss,
-					  extack);
-		if (res) {
-			slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res);
-			goto err_restore_mtu;
-		}
+	} else if (bond->params.fail_over_mac == BOND_FOM_FOLLOW &&
+		   BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP &&
+		   bond_has_slaves(bond) &&
+		   memcmp(slave_dev->dev_addr, bond_dev->dev_addr, bond_dev->addr_len) == 0) {
+		/* Set slave to random address to avoid duplicate mac
+		 * address in later fail over.
+		 */
+		eth_random_addr(ss.__data);
+	} else {
+		goto skip_mac_set;
+	}
+
+	ss.ss_family = slave_dev->type;
+	res = dev_set_mac_address(slave_dev, &ss, extack);
+	if (res) {
+		slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res);
+		goto err_restore_mtu;
 	}
 
+skip_mac_set:
+
 	/* set no_addrconf flag before open to prevent IPv6 addrconf */
 	slave_dev->priv_flags |= IFF_NO_ADDRCONF;
 
@@ -2176,29 +2026,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 
 	new_slave->last_tx = new_slave->last_rx;
 
-	if (bond->params.miimon && !bond->params.use_carrier) {
-		link_reporting = bond_check_dev_link(bond, slave_dev, 1);
-
-		if ((link_reporting == -1) && !bond->params.arp_interval) {
-			/* miimon is set but a bonded network driver
-			 * does not support ETHTOOL/MII and
-			 * arp_interval is not set.  Note: if
-			 * use_carrier is enabled, we will never go
-			 * here (because netif_carrier is always
-			 * supported); thus, we don't need to change
-			 * the messages for netif_carrier.
-			 */
-			slave_warn(bond_dev, slave_dev, "MII and ETHTOOL support not available for slave, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details\n");
-		} else if (link_reporting == -1) {
-			/* unable get link status using mii/ethtool */
-			slave_warn(bond_dev, slave_dev, "can't get link status from slave; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface\n");
-		}
-	}
-
 	/* check for initial state */
 	new_slave->link = BOND_LINK_NOCHANGE;
 	if (bond->params.miimon) {
-		if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) {
+		if (netif_running(slave_dev) && netif_carrier_ok(slave_dev)) {
 			if (bond->params.updelay) {
 				bond_set_slave_link_state(new_slave,
 							  BOND_LINK_BACK,
@@ -2351,7 +2182,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	}
 
 	bond->slave_cnt++;
-	bond_compute_features(bond);
+	netdev_compute_master_upper_features(bond->dev, true);
 	bond_set_carrier(bond);
 
 	/* Needs to be called before bond_select_active_slave(), which will
@@ -2365,7 +2196,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		unblock_netpoll_tx();
 	}
 
-	if (bond_mode_can_use_xmit_hash(bond))
+	/* broadcast mode uses the all_slaves to loop through slaves. */
+	if (bond_mode_can_use_xmit_hash(bond) ||
+	    BOND_MODE(bond) == BOND_MODE_BROADCAST)
 		bond_update_slave_arr(bond, NULL);
 
 	if (!slave_dev->netdev_ops->ndo_bpf ||
@@ -2451,7 +2284,7 @@ err_restore_mac:
 		bond_hw_addr_copy(ss.__data, new_slave->perm_hwaddr,
 				  new_slave->dev->addr_len);
 		ss.ss_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL);
+		dev_set_mac_address(slave_dev, &ss, NULL);
 	}
 
 err_restore_mtu:
@@ -2541,7 +2374,8 @@ static int __bond_release_one(struct net_device *bond_dev,
 
 	bond_upper_dev_unlink(bond, slave);
 
-	if (bond_mode_can_use_xmit_hash(bond))
+	if (bond_mode_can_use_xmit_hash(bond) ||
+	    BOND_MODE(bond) == BOND_MODE_BROADCAST)
 		bond_update_slave_arr(bond, slave);
 
 	slave_info(bond_dev, slave_dev, "Releasing %s interface\n",
@@ -2551,7 +2385,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 
 	RCU_INIT_POINTER(bond->current_arp_slave, NULL);
 
-	if (!all && (!bond->params.fail_over_mac ||
+	if (!all && (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
 		     BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) {
 		if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) &&
 		    bond_has_slaves(bond))
@@ -2603,7 +2437,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 		call_netdevice_notifiers(NETDEV_RELEASE, bond->dev);
 	}
 
-	bond_compute_features(bond);
+	netdev_compute_master_upper_features(bond->dev, true);
 	if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) &&
 	    (old_features & NETIF_F_VLAN_CHALLENGED))
 		slave_info(bond_dev, slave_dev, "last VLAN challenged slave left bond - VLAN blocking is removed\n");
@@ -2645,13 +2479,16 @@ static int __bond_release_one(struct net_device *bond_dev,
 		bond_hw_addr_copy(ss.__data, slave->perm_hwaddr,
 				  slave->dev->addr_len);
 		ss.ss_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL);
+		dev_set_mac_address(slave_dev, &ss, NULL);
 	}
 
-	if (unregister)
-		__dev_set_mtu(slave_dev, slave->original_mtu);
-	else
+	if (unregister) {
+		netdev_lock_ops(slave_dev);
+		__netif_set_mtu(slave_dev, slave->original_mtu);
+		netdev_unlock_ops(slave_dev);
+	} else {
 		dev_set_mtu(slave_dev, slave->original_mtu);
+	}
 
 	if (!netif_is_bond_master(slave_dev))
 		slave_dev->priv_flags &= ~IFF_BONDING;
@@ -2737,7 +2574,8 @@ static int bond_miimon_inspect(struct bonding *bond)
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
-		link_state = bond_check_dev_link(bond, slave->dev, 0);
+		link_state = netif_running(slave->dev) &&
+			     netif_carrier_ok(slave->dev);
 
 		switch (slave->link) {
 		case BOND_LINK_UP:
@@ -2946,7 +2784,7 @@ static void bond_mii_monitor(struct work_struct *work)
 {
 	struct bonding *bond = container_of(work, struct bonding,
 					    mii_work.work);
-	bool should_notify_peers = false;
+	bool should_notify_peers;
 	bool commit;
 	unsigned long delay;
 	struct slave *slave;
@@ -2958,30 +2796,33 @@ static void bond_mii_monitor(struct work_struct *work)
 		goto re_arm;
 
 	rcu_read_lock();
+
 	should_notify_peers = bond_should_notify_peers(bond);
 	commit = !!bond_miimon_inspect(bond);
-	if (bond->send_peer_notif) {
-		rcu_read_unlock();
-		if (rtnl_trylock()) {
-			bond->send_peer_notif--;
-			rtnl_unlock();
-		}
-	} else {
-		rcu_read_unlock();
-	}
 
-	if (commit) {
+	rcu_read_unlock();
+
+	if (commit || bond->send_peer_notif) {
 		/* Race avoidance with bond_close cancel of workqueue */
 		if (!rtnl_trylock()) {
 			delay = 1;
-			should_notify_peers = false;
 			goto re_arm;
 		}
 
-		bond_for_each_slave(bond, slave, iter) {
-			bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER);
+		if (commit) {
+			bond_for_each_slave(bond, slave, iter) {
+				bond_commit_link_state(slave,
+						       BOND_SLAVE_NOTIFY_LATER);
+			}
+			bond_miimon_commit(bond);
+		}
+
+		if (bond->send_peer_notif) {
+			bond->send_peer_notif--;
+			if (should_notify_peers)
+				call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
+							 bond->dev);
 		}
-		bond_miimon_commit(bond);
 
 		rtnl_unlock();	/* might sleep, hold no other locks */
 	}
@@ -2989,13 +2830,6 @@ static void bond_mii_monitor(struct work_struct *work)
 re_arm:
 	if (bond->params.miimon)
 		queue_delayed_work(bond->wq, &bond->mii_work, delay);
-
-	if (should_notify_peers) {
-		if (!rtnl_trylock())
-			return;
-		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
-		rtnl_unlock();
-	}
 }
 
 static int bond_upper_dev_walk(struct net_device *upper,
@@ -3333,7 +3167,6 @@ static void bond_ns_send_all(struct bonding *bond, struct slave *slave)
 		/* Find out through which dev should the packet go */
 		memset(&fl6, 0, sizeof(struct flowi6));
 		fl6.daddr = targets[i];
-		fl6.flowi6_oif = bond->dev->ifindex;
 
 		dst = ip6_route_output(dev_net(bond->dev), NULL, &fl6);
 		if (dst->error) {
@@ -4104,7 +3937,7 @@ static int bond_slave_netdev_event(unsigned long event,
 	case NETDEV_FEAT_CHANGE:
 		if (!bond->notifier_ctx) {
 			bond->notifier_ctx = true;
-			bond_compute_features(bond);
+			netdev_compute_master_upper_features(bond->dev, true);
 			bond->notifier_ctx = false;
 		}
 		break;
@@ -4217,7 +4050,7 @@ static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, const void *
 	}
 
 	if (l34 && *ip_proto >= 0)
-		fk->ports.ports = __skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen);
+		fk->ports.ports = skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen);
 
 	return true;
 }
@@ -4389,7 +4222,7 @@ void bond_work_init_all(struct bonding *bond)
 	INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler);
 }
 
-static void bond_work_cancel_all(struct bonding *bond)
+void bond_work_cancel_all(struct bonding *bond)
 {
 	cancel_delayed_work_sync(&bond->mii_work);
 	cancel_delayed_work_sync(&bond->arp_work);
@@ -4451,6 +4284,9 @@ static int bond_open(struct net_device *bond_dev)
 
 		bond_for_each_slave(bond, slave, iter)
 			dev_mc_add(slave->dev, lacpdu_mcast_addr);
+
+		if (bond->params.broadcast_neighbor)
+			static_branch_inc(&bond_bcast_neigh_enabled);
 	}
 
 	if (bond_mode_can_use_xmit_hash(bond))
@@ -4470,6 +4306,10 @@ static int bond_close(struct net_device *bond_dev)
 		bond_alb_deinitialize(bond);
 	bond->recv_probe = NULL;
 
+	if (BOND_MODE(bond) == BOND_MODE_8023AD &&
+	    bond->params.broadcast_neighbor)
+		static_branch_dec(&bond_bcast_neigh_enabled);
+
 	if (bond_uses_primary(bond)) {
 		rcu_read_lock();
 		slave = rcu_dereference(bond->curr_active_slave);
@@ -4929,8 +4769,7 @@ unwind:
 		if (rollback_slave == slave)
 			break;
 
-		tmp_res = dev_set_mac_address(rollback_slave->dev,
-					      (struct sockaddr *)&tmp_ss, NULL);
+		tmp_res = dev_set_mac_address(rollback_slave->dev, &tmp_ss, NULL);
 		if (tmp_res) {
 			slave_dbg(bond_dev, rollback_slave->dev, "%s: unwind err %d\n",
 				   __func__, tmp_res);
@@ -5306,6 +5145,37 @@ static struct slave *bond_xdp_xmit_3ad_xor_slave_get(struct bonding *bond,
 	return slaves->arr[hash % count];
 }
 
+static bool bond_should_broadcast_neighbor(struct sk_buff *skb,
+					   struct net_device *dev)
+{
+	struct bonding *bond = netdev_priv(dev);
+	struct {
+		struct ipv6hdr ip6;
+		struct icmp6hdr icmp6;
+	} *combined, _combined;
+
+	if (!static_branch_unlikely(&bond_bcast_neigh_enabled))
+		return false;
+
+	if (!bond->params.broadcast_neighbor)
+		return false;
+
+	if (skb->protocol == htons(ETH_P_ARP))
+		return true;
+
+	if (skb->protocol == htons(ETH_P_IPV6)) {
+		combined = skb_header_pointer(skb, skb_mac_header_len(skb),
+					      sizeof(_combined),
+					      &_combined);
+		if (combined && combined->ip6.nexthdr == NEXTHDR_ICMP &&
+		    (combined->icmp6.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION ||
+		     combined->icmp6.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT))
+			return true;
+	}
+
+	return false;
+}
+
 /* Use this Xmit function for 3AD as well as XOR modes. The current
  * usable slave array is formed in the control path. The xmit function
  * just calculates hash and sends the packet out.
@@ -5325,17 +5195,27 @@ static netdev_tx_t bond_3ad_xor_xmit(struct sk_buff *skb,
 	return bond_tx_drop(dev, skb);
 }
 
-/* in broadcast mode, we send everything to all usable interfaces. */
+/* in broadcast mode, we send everything to all or usable slave interfaces.
+ * under rcu_read_lock when this function is called.
+ */
 static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb,
-				       struct net_device *bond_dev)
+				       struct net_device *bond_dev,
+				       bool all_slaves)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct slave *slave = NULL;
-	struct list_head *iter;
+	struct bond_up_slave *slaves;
 	bool xmit_suc = false;
 	bool skb_used = false;
+	int slaves_count, i;
 
-	bond_for_each_slave_rcu(bond, slave, iter) {
+	if (all_slaves)
+		slaves = rcu_dereference(bond->all_slaves);
+	else
+		slaves = rcu_dereference(bond->usable_slaves);
+
+	slaves_count = slaves ? READ_ONCE(slaves->count) : 0;
+	for (i = 0; i < slaves_count; i++) {
+		struct slave *slave = slaves->arr[i];
 		struct sk_buff *skb2;
 
 		if (!(bond_slave_is_up(slave) && slave->link == BOND_LINK_UP))
@@ -5573,10 +5453,13 @@ static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev
 	case BOND_MODE_ACTIVEBACKUP:
 		return bond_xmit_activebackup(skb, dev);
 	case BOND_MODE_8023AD:
+		if (bond_should_broadcast_neighbor(skb, dev))
+			return bond_xmit_broadcast(skb, dev, false);
+		fallthrough;
 	case BOND_MODE_XOR:
 		return bond_3ad_xor_xmit(skb, dev);
 	case BOND_MODE_BROADCAST:
-		return bond_xmit_broadcast(skb, dev);
+		return bond_xmit_broadcast(skb, dev, true);
 	case BOND_MODE_ALB:
 		return bond_alb_xmit(skb, dev);
 	case BOND_MODE_TLB:
@@ -5699,7 +5582,7 @@ static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 
 	ASSERT_RTNL();
 
-	if (!bond_xdp_check(bond)) {
+	if (!bond_xdp_check(bond, BOND_MODE(bond))) {
 		BOND_NL_ERR(dev, extack,
 			    "No native XDP support for the current bonding mode");
 		return -EOPNOTSUPP;
@@ -6028,7 +5911,7 @@ void bond_setup(struct net_device *bond_dev)
 	bond_dev->lltx = true;
 
 	/* Don't allow bond devices to change network namespaces. */
-	bond_dev->netns_local = true;
+	bond_dev->netns_immutable = true;
 
 	/* By default, we declare the bond to be fully
 	 * VLAN hardware accelerated capable. Special
@@ -6037,7 +5920,7 @@ void bond_setup(struct net_device *bond_dev)
 	 * capable
 	 */
 
-	bond_dev->hw_features = BOND_VLAN_FEATURES |
+	bond_dev->hw_features = MASTER_UPPER_DEV_VLAN_FEATURES |
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER |
 				NETIF_F_HW_VLAN_STAG_RX |
@@ -6046,6 +5929,7 @@ void bond_setup(struct net_device *bond_dev)
 	bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL;
 	bond_dev->features |= bond_dev->hw_features;
 	bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+	bond_dev->features |= NETIF_F_GSO_PARTIAL;
 #ifdef CONFIG_XFRM_OFFLOAD
 	bond_dev->hw_features |= BOND_XFRM_FEATURES;
 	/* Only enable XFRM features if this is an active-backup config */
@@ -6184,10 +6068,10 @@ static int __init bond_check_params(struct bond_params *params)
 		downdelay = 0;
 	}
 
-	if ((use_carrier != 0) && (use_carrier != 1)) {
-		pr_warn("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n",
-			use_carrier);
-		use_carrier = 1;
+	if (use_carrier != 1) {
+		pr_err("Error: invalid use_carrier parameter (%d)\n",
+		       use_carrier);
+		return -EINVAL;
 	}
 
 	if (num_peer_notif < 0 || num_peer_notif > 255) {
@@ -6434,7 +6318,6 @@ static int __init bond_check_params(struct bond_params *params)
 	params->updelay = updelay;
 	params->downdelay = downdelay;
 	params->peer_notif_delay = 0;
-	params->use_carrier = use_carrier;
 	params->lacp_active = 1;
 	params->lacp_fast = lacp_fast;
 	params->primary[0] = 0;
@@ -6451,6 +6334,7 @@ static int __init bond_check_params(struct bond_params *params)
 	eth_zero_addr(params->ad_actor_system);
 	params->ad_user_port_key = ad_user_port_key;
 	params->coupled_control = 1;
+	params->broadcast_neighbor = 0;
 	if (packets_per_slave > 0) {
 		params->reciprocal_packets_per_slave =
 			reciprocal_value(packets_per_slave);
@@ -6563,7 +6447,7 @@ static int __net_init bond_net_init(struct net *net)
 
 /* According to commit 69b0216ac255 ("bonding: fix bonding_masters
  * race condition in bond unloading") we need to remove sysfs files
- * before we remove our devices (done later in bond_net_exit_batch_rtnl())
+ * before we remove our devices (done later in bond_net_exit_rtnl())
  */
 static void __net_exit bond_net_pre_exit(struct net *net)
 {
@@ -6572,25 +6456,20 @@ static void __net_exit bond_net_pre_exit(struct net *net)
 	bond_destroy_sysfs(bn);
 }
 
-static void __net_exit bond_net_exit_batch_rtnl(struct list_head *net_list,
-						struct list_head *dev_kill_list)
+static void __net_exit bond_net_exit_rtnl(struct net *net,
+					  struct list_head *dev_kill_list)
 {
-	struct bond_net *bn;
-	struct net *net;
+	struct bond_net *bn = net_generic(net, bond_net_id);
+	struct bonding *bond, *tmp_bond;
 
 	/* Kill off any bonds created after unregistering bond rtnl ops */
-	list_for_each_entry(net, net_list, exit_list) {
-		struct bonding *bond, *tmp_bond;
-
-		bn = net_generic(net, bond_net_id);
-		list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list)
-			unregister_netdevice_queue(bond->dev, dev_kill_list);
-	}
+	list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list)
+		unregister_netdevice_queue(bond->dev, dev_kill_list);
 }
 
 /* According to commit 23fa5c2caae0 ("bonding: destroy proc directory
  * only after all bonds are gone") bond_destroy_proc_dir() is called
- * after bond_net_exit_batch_rtnl() has completed.
+ * after bond_net_exit_rtnl() has completed.
  */
 static void __net_exit bond_net_exit_batch(struct list_head *net_list)
 {
@@ -6606,7 +6485,7 @@ static void __net_exit bond_net_exit_batch(struct list_head *net_list)
 static struct pernet_operations bond_net_ops = {
 	.init = bond_net_init,
 	.pre_exit = bond_net_pre_exit,
-	.exit_batch_rtnl = bond_net_exit_batch_rtnl,
+	.exit_rtnl = bond_net_exit_rtnl,
 	.exit_batch = bond_net_exit_batch,
 	.id   = &bond_net_id,
 	.size = sizeof(struct bond_net),
@@ -6674,3 +6553,4 @@ module_exit(bonding_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION(DRV_DESCRIPTION);
 MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others");
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 2a6a424806aa..286f11c517f7 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -28,6 +28,7 @@ static size_t bond_get_slave_size(const struct net_device *bond_dev,
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE */
 		nla_total_size(sizeof(u16)) +	/* IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE */
 		nla_total_size(sizeof(s32)) +	/* IFLA_BOND_SLAVE_PRIO */
+		nla_total_size(sizeof(u16)) +	/* IFLA_BOND_SLAVE_ACTOR_PORT_PRIO */
 		0;
 }
 
@@ -77,6 +78,10 @@ static int bond_fill_slave_info(struct sk_buff *skb,
 					ad_port->partner_oper.port_state))
 				goto nla_put_failure;
 		}
+
+		if (nla_put_u16(skb, IFLA_BOND_SLAVE_ACTOR_PORT_PRIO,
+				SLAVE_AD_INFO(slave)->port_priority))
+			goto nla_put_failure;
 	}
 
 	return 0;
@@ -124,11 +129,13 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_MISSED_MAX]		= { .type = NLA_U8 },
 	[IFLA_BOND_NS_IP6_TARGET]	= { .type = NLA_NESTED },
 	[IFLA_BOND_COUPLED_CONTROL]	= { .type = NLA_U8 },
+	[IFLA_BOND_BROADCAST_NEIGH]	= { .type = NLA_U8 },
 };
 
 static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = {
 	[IFLA_BOND_SLAVE_QUEUE_ID]	= { .type = NLA_U16 },
 	[IFLA_BOND_SLAVE_PRIO]		= { .type = NLA_S32 },
+	[IFLA_BOND_SLAVE_ACTOR_PORT_PRIO]	= { .type = NLA_U16 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -179,6 +186,16 @@ static int bond_slave_changelink(struct net_device *bond_dev,
 			return err;
 	}
 
+	if (data[IFLA_BOND_SLAVE_ACTOR_PORT_PRIO]) {
+		u16 ad_prio = nla_get_u16(data[IFLA_BOND_SLAVE_ACTOR_PORT_PRIO]);
+
+		bond_opt_slave_initval(&newval, &slave_dev, ad_prio);
+		err = __bond_opt_set(bond, BOND_OPT_ACTOR_PORT_PRIO, &newval,
+				     data[IFLA_BOND_SLAVE_ACTOR_PORT_PRIO], extack);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
@@ -258,13 +275,11 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[],
 			return err;
 	}
 	if (data[IFLA_BOND_USE_CARRIER]) {
-		int use_carrier = nla_get_u8(data[IFLA_BOND_USE_CARRIER]);
-
-		bond_opt_initval(&newval, use_carrier);
-		err = __bond_opt_set(bond, BOND_OPT_USE_CARRIER, &newval,
-				     data[IFLA_BOND_USE_CARRIER], extack);
-		if (err)
-			return err;
+		if (nla_get_u8(data[IFLA_BOND_USE_CARRIER]) != 1) {
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_BOND_USE_CARRIER],
+					    "option obsolete, use_carrier cannot be disabled");
+			return -EINVAL;
+		}
 	}
 	if (data[IFLA_BOND_ARP_INTERVAL]) {
 		int arp_interval = nla_get_u32(data[IFLA_BOND_ARP_INTERVAL]);
@@ -561,25 +576,39 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[],
 			return err;
 	}
 
+	if (data[IFLA_BOND_BROADCAST_NEIGH]) {
+		int broadcast_neigh = nla_get_u8(data[IFLA_BOND_BROADCAST_NEIGH]);
+
+		bond_opt_initval(&newval, broadcast_neigh);
+		err = __bond_opt_set(bond, BOND_OPT_BROADCAST_NEIGH, &newval,
+				     data[IFLA_BOND_BROADCAST_NEIGH], extack);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
-static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
-			struct nlattr *tb[], struct nlattr *data[],
+static int bond_newlink(struct net_device *bond_dev,
+			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
+	struct bonding *bond = netdev_priv(bond_dev);
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	int err;
 
-	err = bond_changelink(bond_dev, tb, data, extack);
-	if (err < 0)
+	err = register_netdevice(bond_dev);
+	if (err)
 		return err;
 
-	err = register_netdevice(bond_dev);
-	if (!err) {
-		struct bonding *bond = netdev_priv(bond_dev);
+	netif_carrier_off(bond_dev);
+	bond_work_init_all(bond);
 
-		netif_carrier_off(bond_dev);
-		bond_work_init_all(bond);
+	err = bond_changelink(bond_dev, tb, data, extack);
+	if (err) {
+		bond_work_cancel_all(bond);
+		unregister_netdevice(bond_dev);
 	}
 
 	return err;
@@ -628,6 +657,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(struct nlattr)) +
 		nla_total_size(sizeof(struct in6_addr)) * BOND_MAX_NS_TARGETS +
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_COUPLED_CONTROL */
+		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_BROADCAST_NEIGH */
 		0;
 }
 
@@ -674,7 +704,7 @@ static int bond_fill_info(struct sk_buff *skb,
 			bond->params.peer_notif_delay * bond->params.miimon))
 		goto nla_put_failure;
 
-	if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, bond->params.use_carrier))
+	if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, 1))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval))
@@ -791,6 +821,10 @@ static int bond_fill_info(struct sk_buff *skb,
 		       bond->params.coupled_control))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_BOND_BROADCAST_NEIGH,
+		       bond->params.broadcast_neighbor))
+		goto nla_put_failure;
+
 	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		struct ad_info info;
 
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 327b6ecdc77e..384499c869b8 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -79,6 +79,8 @@ static int bond_option_tlb_dynamic_lb_set(struct bonding *bond,
 				  const struct bond_opt_value *newval);
 static int bond_option_ad_actor_sys_prio_set(struct bonding *bond,
 					     const struct bond_opt_value *newval);
+static int bond_option_actor_port_prio_set(struct bonding *bond,
+					   const struct bond_opt_value *newval);
 static int bond_option_ad_actor_system_set(struct bonding *bond,
 					   const struct bond_opt_value *newval);
 static int bond_option_ad_user_port_key_set(struct bonding *bond,
@@ -87,6 +89,8 @@ static int bond_option_missed_max_set(struct bonding *bond,
 				      const struct bond_opt_value *newval);
 static int bond_option_coupled_control_set(struct bonding *bond,
 					   const struct bond_opt_value *newval);
+static int bond_option_broadcast_neigh_set(struct bonding *bond,
+					   const struct bond_opt_value *newval);
 
 static const struct bond_opt_value bond_mode_tbl[] = {
 	{ "balance-rr",    BOND_MODE_ROUNDROBIN,   BOND_VALFLAG_DEFAULT},
@@ -158,10 +162,11 @@ static const struct bond_opt_value bond_lacp_rate_tbl[] = {
 };
 
 static const struct bond_opt_value bond_ad_select_tbl[] = {
-	{ "stable",    BOND_AD_STABLE,    BOND_VALFLAG_DEFAULT},
-	{ "bandwidth", BOND_AD_BANDWIDTH, 0},
-	{ "count",     BOND_AD_COUNT,     0},
-	{ NULL,        -1,                0},
+	{ "stable",          BOND_AD_STABLE,    BOND_VALFLAG_DEFAULT},
+	{ "bandwidth",       BOND_AD_BANDWIDTH, 0},
+	{ "count",           BOND_AD_COUNT,     0},
+	{ "actor_port_prio", BOND_AD_PRIO,      0},
+	{ NULL,              -1,                0},
 };
 
 static const struct bond_opt_value bond_num_peer_notif_tbl[] = {
@@ -185,7 +190,6 @@ static const struct bond_opt_value bond_primary_reselect_tbl[] = {
 };
 
 static const struct bond_opt_value bond_use_carrier_tbl[] = {
-	{ "off", 0,  0},
 	{ "on",  1,  BOND_VALFLAG_DEFAULT},
 	{ NULL,  -1, 0}
 };
@@ -240,6 +244,12 @@ static const struct bond_opt_value bond_coupled_control_tbl[] = {
 	{ NULL,  -1, 0},
 };
 
+static const struct bond_opt_value bond_broadcast_neigh_tbl[] = {
+	{ "off", 0, BOND_VALFLAG_DEFAULT},
+	{ "on",	 1, 0},
+	{ NULL,  -1, 0}
+};
+
 static const struct bond_option bond_opts[BOND_OPT_LAST] = {
 	[BOND_OPT_MODE] = {
 		.id = BOND_OPT_MODE,
@@ -362,7 +372,7 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = {
 	[BOND_OPT_AD_SELECT] = {
 		.id = BOND_OPT_AD_SELECT,
 		.name = "ad_select",
-		.desc = "803.ad aggregation selection logic",
+		.desc = "802.3ad aggregation selection logic",
 		.flags = BOND_OPTFLAG_IFDOWN,
 		.values = bond_ad_select_tbl,
 		.set = bond_option_ad_select_set
@@ -411,7 +421,7 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = {
 	[BOND_OPT_USE_CARRIER] = {
 		.id = BOND_OPT_USE_CARRIER,
 		.name = "use_carrier",
-		.desc = "Use netif_carrier_ok (vs MII ioctls) in miimon",
+		.desc = "option obsolete, use_carrier cannot be disabled",
 		.values = bond_use_carrier_tbl,
 		.set = bond_option_use_carrier_set
 	},
@@ -476,6 +486,13 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = {
 		.values = bond_ad_actor_sys_prio_tbl,
 		.set = bond_option_ad_actor_sys_prio_set,
 	},
+	[BOND_OPT_ACTOR_PORT_PRIO] = {
+		.id = BOND_OPT_ACTOR_PORT_PRIO,
+		.name = "actor_port_prio",
+		.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)),
+		.flags = BOND_OPTFLAG_RAWVAL,
+		.set = bond_option_actor_port_prio_set,
+	},
 	[BOND_OPT_AD_ACTOR_SYSTEM] = {
 		.id = BOND_OPT_AD_ACTOR_SYSTEM,
 		.name = "ad_actor_system",
@@ -513,6 +530,14 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = {
 		.flags = BOND_OPTFLAG_IFDOWN,
 		.values = bond_coupled_control_tbl,
 		.set = bond_option_coupled_control_set,
+	},
+	[BOND_OPT_BROADCAST_NEIGH] = {
+		.id = BOND_OPT_BROADCAST_NEIGH,
+		.name = "broadcast_neighbor",
+		.desc = "Broadcast neighbor packets to all active slaves",
+		.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)),
+		.values = bond_broadcast_neigh_tbl,
+		.set = bond_option_broadcast_neigh_set,
 	}
 };
 
@@ -868,6 +893,9 @@ static bool bond_set_xfrm_features(struct bonding *bond)
 static int bond_option_mode_set(struct bonding *bond,
 				const struct bond_opt_value *newval)
 {
+	if (bond->xdp_prog && !bond_xdp_check(bond, newval->value))
+		return -EOPNOTSUPP;
+
 	if (!bond_mode_uses_arp(newval->value)) {
 		if (bond->params.arp_interval) {
 			netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
@@ -891,6 +919,13 @@ static int bond_option_mode_set(struct bonding *bond,
 	bond->params.arp_validate = BOND_ARP_VALIDATE_NONE;
 	bond->params.mode = newval->value;
 
+	/* When changing mode, the bond device is down, we may reduce
+	 * the bond_bcast_neigh_enabled in bond_close() if broadcast_neighbor
+	 * enabled in 8023ad mode. Therefore, only clear broadcast_neighbor
+	 * to 0.
+	 */
+	bond->params.broadcast_neighbor = 0;
+
 	if (bond->dev->reg_state == NETREG_REGISTERED) {
 		bool update = false;
 
@@ -1065,10 +1100,6 @@ static int bond_option_peer_notif_delay_set(struct bonding *bond,
 static int bond_option_use_carrier_set(struct bonding *bond,
 				       const struct bond_opt_value *newval)
 {
-	netdev_dbg(bond->dev, "Setting use_carrier to %llu\n",
-		   newval->value);
-	bond->params.use_carrier = newval->value;
-
 	return 0;
 }
 
@@ -1242,10 +1273,28 @@ static bool slave_can_set_ns_maddr(const struct bonding *bond, struct slave *sla
 	       slave->dev->flags & IFF_MULTICAST;
 }
 
+/**
+ * slave_set_ns_maddrs - add/del all NS mac addresses for slave
+ * @bond: bond device
+ * @slave: slave device
+ * @add: add or remove all the NS mac addresses
+ *
+ * This function tries to add or delete all the NS mac addresses on the slave
+ *
+ * Note, the IPv6 NS target address is the unicast address in Neighbor
+ * Solicitation (NS) message. The dest address of NS message should be
+ * solicited-node multicast address of the target. The dest mac of NS message
+ * is converted from the solicited-node multicast address.
+ *
+ * This function is called when
+ *   * arp_validate changes
+ *   * enslaving, releasing new slaves
+ */
 static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add)
 {
 	struct in6_addr *targets = bond->params.ns_targets;
 	char slot_maddr[MAX_ADDR_LEN];
+	struct in6_addr mcaddr;
 	int i;
 
 	if (!slave_can_set_ns_maddr(bond, slave))
@@ -1255,7 +1304,8 @@ static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool
 		if (ipv6_addr_any(&targets[i]))
 			break;
 
-		if (!ndisc_mc_map(&targets[i], slot_maddr, slave->dev, 0)) {
+		addrconf_addr_solict_mult(&targets[i], &mcaddr);
+		if (!ndisc_mc_map(&mcaddr, slot_maddr, slave->dev, 0)) {
 			if (add)
 				dev_mc_add(slave->dev, slot_maddr);
 			else
@@ -1278,23 +1328,43 @@ void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave)
 	slave_set_ns_maddrs(bond, slave, false);
 }
 
+/**
+ * slave_set_ns_maddr - set new NS mac address for slave
+ * @bond: bond device
+ * @slave: slave device
+ * @target: the new IPv6 target
+ * @slot: the old IPv6 target in the slot
+ *
+ * This function tries to replace the old mac address to new one on the slave.
+ *
+ * Note, the target/slot IPv6 address is the unicast address in Neighbor
+ * Solicitation (NS) message. The dest address of NS message should be
+ * solicited-node multicast address of the target. The dest mac of NS message
+ * is converted from the solicited-node multicast address.
+ *
+ * This function is called when
+ *   * An IPv6 NS target is added or removed.
+ */
 static void slave_set_ns_maddr(struct bonding *bond, struct slave *slave,
 			       struct in6_addr *target, struct in6_addr *slot)
 {
-	char target_maddr[MAX_ADDR_LEN], slot_maddr[MAX_ADDR_LEN];
+	char mac_addr[MAX_ADDR_LEN];
+	struct in6_addr mcast_addr;
 
 	if (!bond->params.arp_validate || !slave_can_set_ns_maddr(bond, slave))
 		return;
 
-	/* remove the previous maddr from slave */
+	/* remove the previous mac addr from slave */
+	addrconf_addr_solict_mult(slot, &mcast_addr);
 	if (!ipv6_addr_any(slot) &&
-	    !ndisc_mc_map(slot, slot_maddr, slave->dev, 0))
-		dev_mc_del(slave->dev, slot_maddr);
+	    !ndisc_mc_map(&mcast_addr, mac_addr, slave->dev, 0))
+		dev_mc_del(slave->dev, mac_addr);
 
-	/* add new maddr on slave if target is set */
+	/* add new mac addr on slave if target is set */
+	addrconf_addr_solict_mult(target, &mcast_addr);
 	if (!ipv6_addr_any(target) &&
-	    !ndisc_mc_map(target, target_maddr, slave->dev, 0))
-		dev_mc_add(slave->dev, target_maddr);
+	    !ndisc_mc_map(&mcast_addr, mac_addr, slave->dev, 0))
+		dev_mc_add(slave->dev, mac_addr);
 }
 
 static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot,
@@ -1595,6 +1665,7 @@ static int bond_option_lacp_active_set(struct bonding *bond,
 	netdev_dbg(bond->dev, "Setting LACP active to %s (%llu)\n",
 		   newval->string, newval->value);
 	bond->params.lacp_active = newval->value;
+	bond_3ad_update_lacp_active(bond);
 
 	return 0;
 }
@@ -1751,6 +1822,26 @@ static int bond_option_ad_actor_sys_prio_set(struct bonding *bond,
 	return 0;
 }
 
+static int bond_option_actor_port_prio_set(struct bonding *bond,
+					   const struct bond_opt_value *newval)
+{
+	struct slave *slave;
+
+	slave = bond_slave_get_rtnl(newval->slave_dev);
+	if (!slave) {
+		netdev_dbg(bond->dev, "%s called on NULL slave\n", __func__);
+		return -ENODEV;
+	}
+
+	netdev_dbg(newval->slave_dev, "Setting actor_port_prio to %llu\n",
+		   newval->value);
+
+	SLAVE_AD_INFO(slave)->port_priority = newval->value;
+	bond_3ad_update_ad_actor_settings(bond);
+
+	return 0;
+}
+
 static int bond_option_ad_actor_system_set(struct bonding *bond,
 					   const struct bond_opt_value *newval)
 {
@@ -1798,3 +1889,22 @@ static int bond_option_coupled_control_set(struct bonding *bond,
 	bond->params.coupled_control = newval->value;
 	return 0;
 }
+
+static int bond_option_broadcast_neigh_set(struct bonding *bond,
+					   const struct bond_opt_value *newval)
+{
+	if (bond->params.broadcast_neighbor == newval->value)
+		return 0;
+
+	bond->params.broadcast_neighbor = newval->value;
+	if (bond->dev->flags & IFF_UP) {
+		if (bond->params.broadcast_neighbor)
+			static_branch_inc(&bond_bcast_neigh_enabled);
+		else
+			static_branch_dec(&bond_bcast_neigh_enabled);
+	}
+
+	netdev_dbg(bond->dev, "Setting broadcast_neighbor to %s (%llu)\n",
+		   newval->string, newval->value);
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 1e13bb170515..9a75ad3181ab 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -467,14 +467,12 @@ static ssize_t bonding_show_primary_reselect(struct device *d,
 static DEVICE_ATTR(primary_reselect, 0644,
 		   bonding_show_primary_reselect, bonding_sysfs_store_option);
 
-/* Show the use_carrier flag. */
+/* use_carrier is obsolete, but print value for compatibility */
 static ssize_t bonding_show_carrier(struct device *d,
 				    struct device_attribute *attr,
 				    char *buf)
 {
-	struct bonding *bond = to_bond(d);
-
-	return sysfs_emit(buf, "%d\n", bond->params.use_carrier);
+	return sysfs_emit(buf, "1\n");
 }
 static DEVICE_ATTR(use_carrier, 0644,
 		   bonding_show_carrier, bonding_sysfs_store_option);
diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c
index ed3a589def6b..c398ac42eae9 100644
--- a/drivers/net/caif/caif_serial.c
+++ b/drivers/net/caif/caif_serial.c
@@ -126,15 +126,6 @@ static inline void debugfs_rx(struct ser_device *ser, const u8 *data, int size)
 	ser->rx_blob.data = ser->rx_data;
 	ser->rx_blob.size = size;
 }
-
-static inline void debugfs_tx(struct ser_device *ser, const u8 *data, int size)
-{
-	if (size > sizeof(ser->tx_data))
-		size = sizeof(ser->tx_data);
-	memcpy(ser->tx_data, data, size);
-	ser->tx_blob.data = ser->tx_data;
-	ser->tx_blob.size = size;
-}
 #else
 static inline void debugfs_init(struct ser_device *ser, struct tty_struct *tty)
 {
@@ -151,11 +142,6 @@ static inline void update_tty_status(struct ser_device *ser)
 static inline void debugfs_rx(struct ser_device *ser, const u8 *data, int size)
 {
 }
-
-static inline void debugfs_tx(struct ser_device *ser, const u8 *data, int size)
-{
-}
-
 #endif
 
 static void ldisc_receive(struct tty_struct *tty, const u8 *data,
@@ -344,7 +330,7 @@ static int ldisc_open(struct tty_struct *tty)
 	ser->tty = tty_kref_get(tty);
 	ser->dev = dev;
 	debugfs_init(ser, tty);
-	tty->receive_room = N_TTY_BUF_SIZE;
+	tty->receive_room = 4096;
 	tty->disc_data = ser;
 	set_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
 	rtnl_lock();
diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c
index 7fea00c7ca8a..c60386bf2d1a 100644
--- a/drivers/net/caif/caif_virtio.c
+++ b/drivers/net/caif/caif_virtio.c
@@ -745,7 +745,7 @@ err:
 
 	if (cfv->vr_rx)
 		vdev->vringh_config->del_vrhs(cfv->vdev);
-	if (cfv->vdev)
+	if (cfv->vq_tx)
 		vdev->config->del_vqs(cfv->vdev);
 	free_netdev(netdev);
 	return err;
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index cf989bea9aa3..e15e320db476 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -124,6 +124,23 @@ config CAN_CAN327
 
 	  If this driver is built as a module, it will be called can327.
 
+config CAN_DUMMY
+	tristate "Dummy CAN"
+	help
+	  A dummy CAN module supporting Classical CAN, CAN FD and CAN XL. It
+	  exposes bittiming values which can be configured through the netlink
+	  interface.
+
+	  The module will simply echo any frame sent to it. If debug messages
+	  are activated, it prints all the CAN bittiming information in the
+	  kernel log. Aside from that it does nothing.
+
+	  This is convenient for testing the CAN netlink interface. Most of the
+	  users will never need this. If unsure, say NO.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called dummy-can.
+
 config CAN_FLEXCAN
 	tristate "Support for Freescale FLEXCAN based chips"
 	depends on OF || COLDFIRE || COMPILE_TEST
@@ -154,6 +171,7 @@ config CAN_JANZ_ICAN3
 config CAN_KVASER_PCIEFD
 	depends on PCI
 	tristate "Kvaser PCIe FD cards"
+	select NET_DEVLINK
 	help
 	  This is a driver for the Kvaser PCI Express CAN FD family.
 
@@ -201,7 +219,7 @@ config CAN_SUN4I
 	  be called sun4i_can.
 
 config CAN_TI_HECC
-	depends on ARM
+	depends on ARM || COMPILE_TEST
 	tristate "TI High End CAN Controller"
 	select CAN_RX_OFFLOAD
 	help
diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile
index a71db2cfe990..d7bc10a6b8ea 100644
--- a/drivers/net/can/Makefile
+++ b/drivers/net/can/Makefile
@@ -21,11 +21,12 @@ obj-$(CONFIG_CAN_CAN327)	+= can327.o
 obj-$(CONFIG_CAN_CC770)		+= cc770/
 obj-$(CONFIG_CAN_C_CAN)		+= c_can/
 obj-$(CONFIG_CAN_CTUCANFD)	+= ctucanfd/
+obj-$(CONFIG_CAN_DUMMY)		+= dummy_can.o
 obj-$(CONFIG_CAN_FLEXCAN)	+= flexcan/
 obj-$(CONFIG_CAN_GRCAN)		+= grcan.o
 obj-$(CONFIG_CAN_IFI_CANFD)	+= ifi_canfd/
 obj-$(CONFIG_CAN_JANZ_ICAN3)	+= janz-ican3.o
-obj-$(CONFIG_CAN_KVASER_PCIEFD)	+= kvaser_pciefd.o
+obj-$(CONFIG_CAN_KVASER_PCIEFD)	+= kvaser_pciefd/
 obj-$(CONFIG_CAN_MSCAN)		+= mscan/
 obj-$(CONFIG_CAN_M_CAN)		+= m_can/
 obj-$(CONFIG_CAN_PEAK_PCIEFD)	+= peak_canfd/
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index 191707d7e3da..c2a3a4eef5b2 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -948,7 +948,6 @@ static const struct net_device_ops at91_netdev_ops = {
 	.ndo_open	= at91_open,
 	.ndo_stop	= at91_close,
 	.ndo_start_xmit	= at91_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops at91_ethtool_ops = {
diff --git a/drivers/net/can/bxcan.c b/drivers/net/can/bxcan.c
index bfc60eb33dc3..baf494d20bef 100644
--- a/drivers/net/can/bxcan.c
+++ b/drivers/net/can/bxcan.c
@@ -227,7 +227,7 @@ static void bxcan_enable_filters(struct bxcan_priv *priv, enum bxcan_cfg cfg)
 	 * mask mode with 32 bits width.
 	 */
 
-	/* Enter filter initialization mode and assing filters to CAN
+	/* Enter filter initialization mode and assign filters to CAN
 	 * controllers.
 	 */
 	regmap_update_bits(priv->gcan, BXCAN_FMR_REG,
@@ -842,7 +842,7 @@ static netdev_tx_t bxcan_start_xmit(struct sk_buff *skb,
 	u32 id;
 	int i, j;
 
-	if (can_dropped_invalid_skb(ndev, skb))
+	if (can_dev_dropped_skb(ndev, skb))
 		return NETDEV_TX_OK;
 
 	if (bxcan_tx_busy(priv))
@@ -881,7 +881,6 @@ static const struct net_device_ops bxcan_netdev_ops = {
 	.ndo_open = bxcan_open,
 	.ndo_stop = bxcan_stop,
 	.ndo_start_xmit = bxcan_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops bxcan_ethtool_ops = {
diff --git a/drivers/net/can/c_can/c_can_main.c b/drivers/net/can/c_can/c_can_main.c
index cc371d0c9f3c..3702cac7fbf0 100644
--- a/drivers/net/can/c_can/c_can_main.c
+++ b/drivers/net/can/c_can/c_can_main.c
@@ -1362,7 +1362,6 @@ static const struct net_device_ops c_can_netdev_ops = {
 	.ndo_open = c_can_open,
 	.ndo_stop = c_can_close,
 	.ndo_start_xmit = c_can_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 int register_c_can_dev(struct net_device *dev)
diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index 6cba9717a6d8..19c86b94a40e 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -269,30 +269,22 @@ static int c_can_plat_probe(struct platform_device *pdev)
 
 	/* get the appropriate clk */
 	clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(clk)) {
-		ret = PTR_ERR(clk);
-		goto exit;
-	}
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
 
 	/* get the platform data */
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		ret = irq;
-		goto exit;
-	}
+	if (irq < 0)
+		return irq;
 
 	addr = devm_platform_get_and_ioremap_resource(pdev, 0, &mem);
-	if (IS_ERR(addr)) {
-		ret =  PTR_ERR(addr);
-		goto exit;
-	}
+	if (IS_ERR(addr))
+		return PTR_ERR(addr);
 
 	/* allocate the c_can device */
 	dev = alloc_c_can_dev(drvdata->msg_obj_num);
-	if (!dev) {
-		ret = -ENOMEM;
-		goto exit;
-	}
+	if (!dev)
+		return -ENOMEM;
 
 	priv = netdev_priv(dev);
 	switch (drvdata->id) {
@@ -324,33 +316,22 @@ static int c_can_plat_probe(struct platform_device *pdev)
 		/* Check if we need custom RAMINIT via syscon. Mostly for TI
 		 * platforms. Only supported with DT boot.
 		 */
-		if (np && of_property_read_bool(np, "syscon-raminit")) {
+		if (np && of_property_present(np, "syscon-raminit")) {
+			unsigned int args[2];
 			u32 id;
 			struct c_can_raminit *raminit = &priv->raminit_sys;
 
 			ret = -EINVAL;
-			raminit->syscon = syscon_regmap_lookup_by_phandle(np,
-									  "syscon-raminit");
+			raminit->syscon = syscon_regmap_lookup_by_phandle_args(np,
+									       "syscon-raminit",
+									       2, args);
 			if (IS_ERR(raminit->syscon)) {
-				/* can fail with -EPROBE_DEFER */
 				ret = PTR_ERR(raminit->syscon);
-				free_c_can_dev(dev);
-				return ret;
-			}
-
-			if (of_property_read_u32_index(np, "syscon-raminit", 1,
-						       &raminit->reg)) {
-				dev_err(&pdev->dev,
-					"couldn't get the RAMINIT reg. offset!\n");
 				goto exit_free_device;
 			}
 
-			if (of_property_read_u32_index(np, "syscon-raminit", 2,
-						       &id)) {
-				dev_err(&pdev->dev,
-					"couldn't get the CAN instance ID\n");
-				goto exit_free_device;
-			}
+			raminit->reg = args[0];
+			id = args[1];
 
 			if (id >= drvdata->raminit_num) {
 				dev_err(&pdev->dev,
@@ -385,18 +366,17 @@ static int c_can_plat_probe(struct platform_device *pdev)
 	if (ret) {
 		dev_err(&pdev->dev, "registering %s failed (err=%d)\n",
 			KBUILD_MODNAME, ret);
-		goto exit_free_device;
+		goto exit_pm_runtime;
 	}
 
 	dev_info(&pdev->dev, "%s device registered (regs=%p, irq=%d)\n",
 		 KBUILD_MODNAME, priv->base, dev->irq);
 	return 0;
 
-exit_free_device:
+exit_pm_runtime:
 	pm_runtime_disable(priv->device);
+exit_free_device:
 	free_c_can_dev(dev);
-exit:
-	dev_err(&pdev->dev, "probe failed\n");
 
 	return ret;
 }
diff --git a/drivers/net/can/can327.c b/drivers/net/can/can327.c
index 24af63961030..b66fc16aedd2 100644
--- a/drivers/net/can/can327.c
+++ b/drivers/net/can/can327.c
@@ -849,7 +849,6 @@ static const struct net_device_ops can327_netdev_ops = {
 	.ndo_open = can327_netdev_open,
 	.ndo_stop = can327_netdev_close,
 	.ndo_start_xmit = can327_netdev_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops can327_ethtool_ops = {
diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c
index 30909f3aab57..8d5abd643c06 100644
--- a/drivers/net/can/cc770/cc770.c
+++ b/drivers/net/can/cc770/cc770.c
@@ -834,7 +834,6 @@ static const struct net_device_ops cc770_netdev_ops = {
 	.ndo_open = cc770_open,
 	.ndo_stop = cc770_close,
 	.ndo_start_xmit = cc770_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops cc770_ethtool_ops = {
diff --git a/drivers/net/can/ctucanfd/ctucanfd_base.c b/drivers/net/can/ctucanfd/ctucanfd_base.c
index 64c349fd4600..1e6b9e3dc2fe 100644
--- a/drivers/net/can/ctucanfd/ctucanfd_base.c
+++ b/drivers/net/can/ctucanfd/ctucanfd_base.c
@@ -275,7 +275,7 @@ static int ctucan_set_bittiming(struct net_device *ndev)
 static int ctucan_set_data_bittiming(struct net_device *ndev)
 {
 	struct ctucan_priv *priv = netdev_priv(ndev);
-	struct can_bittiming *dbt = &priv->can.data_bittiming;
+	struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 
 	/* Note that dbt may be modified here */
 	return ctucan_set_btr(ndev, dbt, false);
@@ -290,7 +290,7 @@ static int ctucan_set_data_bittiming(struct net_device *ndev)
 static int ctucan_set_secondary_sample_point(struct net_device *ndev)
 {
 	struct ctucan_priv *priv = netdev_priv(ndev);
-	struct can_bittiming *dbt = &priv->can.data_bittiming;
+	struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	int ssp_offset = 0;
 	u32 ssp_cfg = 0; /* No SSP by default */
 
@@ -506,11 +506,12 @@ static bool ctucan_is_txt_buf_writable(struct ctucan_priv *priv, u8 buf)
  * @buf:	TXT Buffer index to which frame is inserted (0-based)
  * @isfdf:	True - CAN FD Frame, False - CAN 2.0 Frame
  *
- * Return: True - Frame inserted successfully
- *	   False - Frame was not inserted due to one of:
- *			1. TXT Buffer is not writable (it is in wrong state)
- *			2. Invalid TXT buffer index
- *			3. Invalid frame length
+ * Return:
+ * * True - Frame inserted successfully
+ * * False - Frame was not inserted due to one of:
+ *	1. TXT Buffer is not writable (it is in wrong state)
+ *	2. Invalid TXT buffer index
+ *	3. Invalid frame length
  */
 static bool ctucan_insert_frame(struct ctucan_priv *priv, const struct canfd_frame *cf, u8 buf,
 				bool isfdf)
@@ -867,10 +868,12 @@ static void ctucan_err_interrupt(struct net_device *ndev, u32 isr)
 			}
 			break;
 		case CAN_STATE_ERROR_ACTIVE:
-			cf->can_id |= CAN_ERR_CNT;
-			cf->data[1] = CAN_ERR_CRTL_ACTIVE;
-			cf->data[6] = bec.txerr;
-			cf->data[7] = bec.rxerr;
+			if (skb) {
+				cf->can_id |= CAN_ERR_CNT;
+				cf->data[1] = CAN_ERR_CRTL_ACTIVE;
+				cf->data[6] = bec.txerr;
+				cf->data[7] = bec.rxerr;
+			}
 			break;
 		default:
 			netdev_warn(ndev, "unhandled error state (%d:%s)!\n",
@@ -1298,7 +1301,6 @@ static const struct net_device_ops ctucan_netdev_ops = {
 	.ndo_open	= ctucan_open,
 	.ndo_stop	= ctucan_close,
 	.ndo_start_xmit	= ctucan_start_xmit,
-	.ndo_change_mtu	= can_change_mtu,
 };
 
 static const struct ethtool_ops ctucan_ethtool_ops = {
@@ -1356,12 +1358,12 @@ int ctucan_probe_common(struct device *dev, void __iomem *addr, int irq, unsigne
 	priv->ntxbufs = ntxbufs;
 	priv->dev = dev;
 	priv->can.bittiming_const = &ctu_can_fd_bit_timing_max;
-	priv->can.data_bittiming_const = &ctu_can_fd_bit_timing_data_max;
+	priv->can.fd.data_bittiming_const = &ctu_can_fd_bit_timing_data_max;
 	priv->can.do_set_mode = ctucan_do_set_mode;
 
 	/* Needed for timing adjustment to be performed as soon as possible */
 	priv->can.do_set_bittiming = ctucan_set_bittiming;
-	priv->can.do_set_data_bittiming = ctucan_set_data_bittiming;
+	priv->can.fd.do_set_data_bittiming = ctucan_set_data_bittiming;
 
 	priv->can.do_get_berr_counter = ctucan_get_berr_counter;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK
diff --git a/drivers/net/can/dev/bittiming.c b/drivers/net/can/dev/bittiming.c
index 0b93900b1dfa..8f82418230ce 100644
--- a/drivers/net/can/dev/bittiming.c
+++ b/drivers/net/can/dev/bittiming.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2005 Marc Kleine-Budde, Pengutronix
  * Copyright (C) 2006 Andrey Volkov, Varma Electronics
  * Copyright (C) 2008-2009 Wolfgang Grandegger <wg@grandegger.com>
+ * Copyright (c) 2025 Vincent Mailhol <mailhol@kernel.org>
  */
 
 #include <linux/can/dev.h>
@@ -151,3 +152,65 @@ int can_get_bittiming(const struct net_device *dev, struct can_bittiming *bt,
 
 	return -EINVAL;
 }
+
+int can_validate_pwm_bittiming(const struct net_device *dev,
+			       const struct can_pwm *pwm,
+			       struct netlink_ext_ack *extack)
+{
+	const struct can_priv *priv = netdev_priv(dev);
+	u32 xl_bit_time_tqmin = can_bit_time_tqmin(&priv->xl.data_bittiming);
+	u32 nom_bit_time_tqmin = can_bit_time_tqmin(&priv->bittiming);
+	u32 pwms_ns = can_tqmin_to_ns(pwm->pwms, priv->clock.freq);
+	u32 pwml_ns = can_tqmin_to_ns(pwm->pwml, priv->clock.freq);
+
+	if (pwms_ns + pwml_ns > CAN_PWM_NS_MAX) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "The PWM symbol duration: %u ns may not exceed %u ns",
+				   pwms_ns + pwml_ns, CAN_PWM_NS_MAX);
+		return -EINVAL;
+	}
+
+	if (pwms_ns < CAN_PWM_DECODE_NS) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "PWMS: %u ns shall be at least %u ns",
+				   pwms_ns, CAN_PWM_DECODE_NS);
+		return -EINVAL;
+	}
+
+	if (pwm->pwms >= pwm->pwml) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "PWMS: %u tqmin shall be smaller than PWML: %u tqmin",
+				   pwm->pwms, pwm->pwml);
+		return -EINVAL;
+	}
+
+	if (pwml_ns - pwms_ns < 2 * CAN_PWM_DECODE_NS) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "At least %u ns shall separate PWMS: %u ns from PMWL: %u ns",
+				   2 * CAN_PWM_DECODE_NS, pwms_ns, pwml_ns);
+		return -EINVAL;
+	}
+
+	if (xl_bit_time_tqmin % (pwm->pwms + pwm->pwml) != 0) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "PWM duration: %u tqmin does not divide XL's bit time: %u tqmin",
+				   pwm->pwms + pwm->pwml, xl_bit_time_tqmin);
+		return -EINVAL;
+	}
+
+	if (pwm->pwmo >= pwm->pwms + pwm->pwml) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "PWMO: %u tqmin can not be greater than PWMS + PWML: %u tqmin",
+				   pwm->pwmo, pwm->pwms + pwm->pwml);
+		return -EINVAL;
+	}
+
+	if (nom_bit_time_tqmin % (pwm->pwms + pwm->pwml) != pwm->pwmo) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "Can not assemble nominal bit time: %u tqmin out of PWMS + PMWL and PWMO",
+				   nom_bit_time_tqmin);
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/can/dev/calc_bittiming.c b/drivers/net/can/dev/calc_bittiming.c
index 3809c148fb88..cc4022241553 100644
--- a/drivers/net/can/dev/calc_bittiming.c
+++ b/drivers/net/can/dev/calc_bittiming.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2005 Marc Kleine-Budde, Pengutronix
  * Copyright (C) 2006 Andrey Volkov, Varma Electronics
  * Copyright (C) 2008-2009 Wolfgang Grandegger <wg@grandegger.com>
+ * Copyright (C) 2021-2025 Vincent Mailhol <mailhol@kernel.org>
  */
 
 #include <linux/units.h>
@@ -9,6 +10,33 @@
 
 #define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */
 
+/* CiA recommended sample points for Non Return to Zero encoding. */
+static int can_calc_sample_point_nrz(const struct can_bittiming *bt)
+{
+	if (bt->bitrate > 800 * KILO /* BPS */)
+		return 750;
+
+	if (bt->bitrate > 500 * KILO /* BPS */)
+		return 800;
+
+	return 875;
+}
+
+/* Sample points for Pulse-Width Modulation encoding. */
+static int can_calc_sample_point_pwm(const struct can_bittiming *bt)
+{
+	if (bt->bitrate > 15 * MEGA /* BPS */)
+		return 625;
+
+	if (bt->bitrate > 9 * MEGA /* BPS */)
+		return 600;
+
+	if (bt->bitrate > 4 * MEGA /* BPS */)
+		return 560;
+
+	return 520;
+}
+
 /* Bit-timing calculation derived from:
  *
  * Code based on LinCAN sources and H8S2638 project
@@ -23,7 +51,7 @@
  */
 static int
 can_update_sample_point(const struct can_bittiming_const *btc,
-			const unsigned int sample_point_nominal, const unsigned int tseg,
+			const unsigned int sample_point_reference, const unsigned int tseg,
 			unsigned int *tseg1_ptr, unsigned int *tseg2_ptr,
 			unsigned int *sample_point_error_ptr)
 {
@@ -34,7 +62,7 @@ can_update_sample_point(const struct can_bittiming_const *btc,
 
 	for (i = 0; i <= 1; i++) {
 		tseg2 = tseg + CAN_SYNC_SEG -
-			(sample_point_nominal * (tseg + CAN_SYNC_SEG)) /
+			(sample_point_reference * (tseg + CAN_SYNC_SEG)) /
 			1000 - i;
 		tseg2 = clamp(tseg2, btc->tseg2_min, btc->tseg2_max);
 		tseg1 = tseg - tseg2;
@@ -45,9 +73,9 @@ can_update_sample_point(const struct can_bittiming_const *btc,
 
 		sample_point = 1000 * (tseg + CAN_SYNC_SEG - tseg2) /
 			(tseg + CAN_SYNC_SEG);
-		sample_point_error = abs(sample_point_nominal - sample_point);
+		sample_point_error = abs(sample_point_reference - sample_point);
 
-		if (sample_point <= sample_point_nominal &&
+		if (sample_point <= sample_point_reference &&
 		    sample_point_error < best_sample_point_error) {
 			best_sample_point = sample_point;
 			best_sample_point_error = sample_point_error;
@@ -67,28 +95,24 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt,
 {
 	struct can_priv *priv = netdev_priv(dev);
 	unsigned int bitrate;			/* current bitrate */
-	unsigned int bitrate_error;		/* difference between current and nominal value */
+	unsigned int bitrate_error;		/* diff between calculated and reference value */
 	unsigned int best_bitrate_error = UINT_MAX;
-	unsigned int sample_point_error;	/* difference between current and nominal value */
+	unsigned int sample_point_error;	/* diff between calculated and reference value */
 	unsigned int best_sample_point_error = UINT_MAX;
-	unsigned int sample_point_nominal;	/* nominal sample point */
+	unsigned int sample_point_reference;	/* reference sample point */
 	unsigned int best_tseg = 0;		/* current best value for tseg */
 	unsigned int best_brp = 0;		/* current best value for brp */
 	unsigned int brp, tsegall, tseg, tseg1 = 0, tseg2 = 0;
 	u64 v64;
 	int err;
 
-	/* Use CiA recommended sample points */
-	if (bt->sample_point) {
-		sample_point_nominal = bt->sample_point;
-	} else {
-		if (bt->bitrate > 800 * KILO /* BPS */)
-			sample_point_nominal = 750;
-		else if (bt->bitrate > 500 * KILO /* BPS */)
-			sample_point_nominal = 800;
-		else
-			sample_point_nominal = 875;
-	}
+	if (bt->sample_point)
+		sample_point_reference = bt->sample_point;
+	else if (btc == priv->xl.data_bittiming_const &&
+		 (priv->ctrlmode & CAN_CTRLMODE_XL_TMS))
+		sample_point_reference = can_calc_sample_point_pwm(bt);
+	else
+		sample_point_reference = can_calc_sample_point_nrz(bt);
 
 	/* tseg even = round down, odd = round up */
 	for (tseg = (btc->tseg1_max + btc->tseg2_max) * 2 + 1;
@@ -114,7 +138,7 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt,
 		if (bitrate_error < best_bitrate_error)
 			best_sample_point_error = UINT_MAX;
 
-		can_update_sample_point(btc, sample_point_nominal, tseg / 2,
+		can_update_sample_point(btc, sample_point_reference, tseg / 2,
 					&tseg1, &tseg2, &sample_point_error);
 		if (sample_point_error >= best_sample_point_error)
 			continue;
@@ -129,23 +153,26 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt,
 	}
 
 	if (best_bitrate_error) {
-		/* Error in one-tenth of a percent */
-		v64 = (u64)best_bitrate_error * 1000;
+		/* Error in one-hundredth of a percent */
+		v64 = (u64)best_bitrate_error * 10000;
 		do_div(v64, bt->bitrate);
 		bitrate_error = (u32)v64;
+		/* print at least 0.01% if the error is smaller */
+		bitrate_error = max(bitrate_error, 1U);
 		if (bitrate_error > CAN_CALC_MAX_ERROR) {
 			NL_SET_ERR_MSG_FMT(extack,
-					   "bitrate error: %u.%u%% too high",
-					   bitrate_error / 10, bitrate_error % 10);
+					   "bitrate error: %u.%02u%% too high",
+					   bitrate_error / 100,
+					   bitrate_error % 100);
 			return -EINVAL;
 		}
 		NL_SET_ERR_MSG_FMT(extack,
-				   "bitrate error: %u.%u%%",
-				   bitrate_error / 10, bitrate_error % 10);
+				   "bitrate error: %u.%02u%%",
+				   bitrate_error / 100, bitrate_error % 100);
 	}
 
 	/* real sample point */
-	bt->sample_point = can_update_sample_point(btc, sample_point_nominal,
+	bt->sample_point = can_update_sample_point(btc, sample_point_reference,
 						   best_tseg, &tseg1, &tseg2,
 						   NULL);
 
@@ -173,13 +200,15 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt,
 
 void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const,
 		   const struct can_bittiming *dbt,
-		   u32 *ctrlmode, u32 ctrlmode_supported)
+		   u32 tdc_mask, u32 *ctrlmode, u32 ctrlmode_supported)
 
 {
-	if (!tdc_const || !(ctrlmode_supported & CAN_CTRLMODE_TDC_AUTO))
+	u32 tdc_auto = tdc_mask & CAN_CTRLMODE_TDC_AUTO_MASK;
+
+	if (!tdc_const || !(ctrlmode_supported & tdc_auto))
 		return;
 
-	*ctrlmode &= ~CAN_CTRLMODE_TDC_MASK;
+	*ctrlmode &= ~tdc_mask;
 
 	/* As specified in ISO 11898-1 section 11.3.3 "Transmitter
 	 * delay compensation" (TDC) is only applicable if data BRP is
@@ -193,6 +222,41 @@ void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const,
 		if (sample_point_in_tc < tdc_const->tdco_min)
 			return;
 		tdc->tdco = min(sample_point_in_tc, tdc_const->tdco_max);
-		*ctrlmode |= CAN_CTRLMODE_TDC_AUTO;
+		*ctrlmode |= tdc_auto;
 	}
 }
+
+int can_calc_pwm(struct net_device *dev, struct netlink_ext_ack *extack)
+{
+	struct can_priv *priv = netdev_priv(dev);
+	const struct can_pwm_const *pwm_const = priv->xl.pwm_const;
+	struct can_pwm *pwm = &priv->xl.pwm;
+	u32 xl_tqmin = can_bit_time_tqmin(&priv->xl.data_bittiming);
+	u32 xl_ns = can_tqmin_to_ns(xl_tqmin, priv->clock.freq);
+	u32 nom_tqmin = can_bit_time_tqmin(&priv->bittiming);
+	int pwm_per_bit_max = xl_tqmin / (pwm_const->pwms_min + pwm_const->pwml_min);
+	int pwm_per_bit;
+	u32 pwm_tqmin;
+
+	/* For 5 MB/s databitrate or greater, xl_ns < CAN_PWM_NS_MAX
+	 * giving us a pwm_per_bit of 1 and the loop immediately breaks
+	 */
+	for (pwm_per_bit = DIV_ROUND_UP(xl_ns, CAN_PWM_NS_MAX);
+	     pwm_per_bit <= pwm_per_bit_max; pwm_per_bit++)
+		if (xl_tqmin % pwm_per_bit == 0)
+			break;
+
+	if (pwm_per_bit > pwm_per_bit_max) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "Can not divide the XL data phase's bit time: %u tqmin into multiple PWM symbols",
+				   xl_tqmin);
+		return -EINVAL;
+	}
+
+	pwm_tqmin = xl_tqmin / pwm_per_bit;
+	pwm->pwms = DIV_ROUND_UP_POW2(pwm_tqmin, 4);
+	pwm->pwml = pwm_tqmin - pwm->pwms;
+	pwm->pwmo = nom_tqmin % pwm_tqmin;
+
+	return 0;
+}
diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c
index 681643ab3780..091f30e94c61 100644
--- a/drivers/net/can/dev/dev.c
+++ b/drivers/net/can/dev/dev.c
@@ -4,17 +4,17 @@
  * Copyright (C) 2008-2009 Wolfgang Grandegger <wg@grandegger.com>
  */
 
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/netdevice.h>
-#include <linux/if_arp.h>
-#include <linux/workqueue.h>
 #include <linux/can.h>
 #include <linux/can/can-ml.h>
 #include <linux/can/dev.h>
 #include <linux/can/skb.h>
 #include <linux/gpio/consumer.h>
+#include <linux/if_arp.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
 #include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
 
 static void can_update_state_error_stats(struct net_device *dev,
 					 enum can_state new_state)
@@ -85,11 +85,52 @@ const char *can_get_state_str(const enum can_state state)
 	default:
 		return "<unknown>";
 	}
-
-	return "<unknown>";
 }
 EXPORT_SYMBOL_GPL(can_get_state_str);
 
+const char *can_get_ctrlmode_str(u32 ctrlmode)
+{
+	switch (ctrlmode & ~(ctrlmode - 1)) {
+	case 0:
+		return "(none)";
+	case CAN_CTRLMODE_LOOPBACK:
+		return "LOOPBACK";
+	case CAN_CTRLMODE_LISTENONLY:
+		return "LISTEN-ONLY";
+	case CAN_CTRLMODE_3_SAMPLES:
+		return "TRIPLE-SAMPLING";
+	case CAN_CTRLMODE_ONE_SHOT:
+		return "ONE-SHOT";
+	case CAN_CTRLMODE_BERR_REPORTING:
+		return "BERR-REPORTING";
+	case CAN_CTRLMODE_FD:
+		return "FD";
+	case CAN_CTRLMODE_PRESUME_ACK:
+		return "PRESUME-ACK";
+	case CAN_CTRLMODE_FD_NON_ISO:
+		return "FD-NON-ISO";
+	case CAN_CTRLMODE_CC_LEN8_DLC:
+		return "CC-LEN8-DLC";
+	case CAN_CTRLMODE_TDC_AUTO:
+		return "TDC-AUTO";
+	case CAN_CTRLMODE_TDC_MANUAL:
+		return "TDC-MANUAL";
+	case CAN_CTRLMODE_RESTRICTED:
+		return "RESTRICTED";
+	case CAN_CTRLMODE_XL:
+		return "XL";
+	case CAN_CTRLMODE_XL_TDC_AUTO:
+		return "XL-TDC-AUTO";
+	case CAN_CTRLMODE_XL_TDC_MANUAL:
+		return "XL-TDC-MANUAL";
+	case CAN_CTRLMODE_XL_TMS:
+		return "TMS";
+	default:
+		return "<unknown>";
+	}
+}
+EXPORT_SYMBOL_GPL(can_get_ctrlmode_str);
+
 static enum can_state can_state_err_to_state(u16 err)
 {
 	if (err < CAN_ERROR_WARNING_THRESHOLD)
@@ -147,13 +188,16 @@ void can_change_state(struct net_device *dev, struct can_frame *cf,
 EXPORT_SYMBOL_GPL(can_change_state);
 
 /* CAN device restart for bus-off recovery */
-static void can_restart(struct net_device *dev)
+static int can_restart(struct net_device *dev)
 {
 	struct can_priv *priv = netdev_priv(dev);
 	struct sk_buff *skb;
 	struct can_frame *cf;
 	int err;
 
+	if (!priv->do_set_mode)
+		return -EOPNOTSUPP;
+
 	if (netif_carrier_ok(dev))
 		netdev_err(dev, "Attempt to restart for bus-off recovery, but carrier is OK?\n");
 
@@ -175,10 +219,14 @@ static void can_restart(struct net_device *dev)
 	if (err) {
 		netdev_err(dev, "Restart failed, error %pe\n", ERR_PTR(err));
 		netif_carrier_off(dev);
+
+		return err;
 	} else {
 		netdev_dbg(dev, "Restarted\n");
 		priv->can_stats.restarts++;
 	}
+
+	return 0;
 }
 
 static void can_restart_work(struct work_struct *work)
@@ -203,9 +251,8 @@ int can_restart_now(struct net_device *dev)
 		return -EBUSY;
 
 	cancel_delayed_work_sync(&priv->restart_work);
-	can_restart(dev);
 
-	return 0;
+	return can_restart(dev);
 }
 
 /* CAN bus-off
@@ -236,6 +283,8 @@ void can_setup(struct net_device *dev)
 {
 	dev->type = ARPHRD_CAN;
 	dev->mtu = CAN_MTU;
+	dev->min_mtu = CAN_MTU;
+	dev->max_mtu = CAN_MTU;
 	dev->hard_header_len = 0;
 	dev->addr_len = 0;
 	dev->tx_queue_len = 10;
@@ -305,72 +354,74 @@ void free_candev(struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(free_candev);
 
-/* changing MTU and control mode for CAN/CANFD devices */
-int can_change_mtu(struct net_device *dev, int new_mtu)
+void can_set_default_mtu(struct net_device *dev)
 {
 	struct can_priv *priv = netdev_priv(dev);
-	u32 ctrlmode_static = can_get_static_ctrlmode(priv);
 
-	/* Do not allow changing the MTU while running */
-	if (dev->flags & IFF_UP)
-		return -EBUSY;
+	if (priv->ctrlmode & CAN_CTRLMODE_XL) {
+		if (can_is_canxl_dev_mtu(dev->mtu))
+			return;
+		dev->mtu = CANXL_MTU;
+		dev->min_mtu = CANXL_MIN_MTU;
+		dev->max_mtu = CANXL_MAX_MTU;
+	} else if (priv->ctrlmode & CAN_CTRLMODE_FD) {
+		dev->mtu = CANFD_MTU;
+		dev->min_mtu = CANFD_MTU;
+		dev->max_mtu = CANFD_MTU;
+	} else {
+		dev->mtu = CAN_MTU;
+		dev->min_mtu = CAN_MTU;
+		dev->max_mtu = CAN_MTU;
+	}
+}
 
-	/* allow change of MTU according to the CANFD ability of the device */
-	switch (new_mtu) {
-	case CAN_MTU:
-		/* 'CANFD-only' controllers can not switch to CAN_MTU */
-		if (ctrlmode_static & CAN_CTRLMODE_FD)
-			return -EINVAL;
+/* helper to define static CAN controller features at device creation time */
+int can_set_static_ctrlmode(struct net_device *dev, u32 static_mode)
+{
+	struct can_priv *priv = netdev_priv(dev);
 
-		priv->ctrlmode &= ~CAN_CTRLMODE_FD;
-		break;
+	/* alloc_candev() succeeded => netdev_priv() is valid at this point */
+	if (priv->ctrlmode_supported & static_mode) {
+		netdev_warn(dev,
+			    "Controller features can not be supported and static at the same time\n");
+		return -EINVAL;
+	}
+	priv->ctrlmode = static_mode;
 
-	case CANFD_MTU:
-		/* check for potential CANFD ability */
-		if (!(priv->ctrlmode_supported & CAN_CTRLMODE_FD) &&
-		    !(ctrlmode_static & CAN_CTRLMODE_FD))
-			return -EINVAL;
+	/* override MTU which was set by default in can_setup()? */
+	can_set_default_mtu(dev);
 
-		priv->ctrlmode |= CAN_CTRLMODE_FD;
-		break;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(can_set_static_ctrlmode);
 
-	default:
-		return -EINVAL;
-	}
+/* generic implementation of netdev_ops::ndo_hwtstamp_get for CAN devices
+ * supporting hardware timestamps
+ */
+int can_hwtstamp_get(struct net_device *netdev,
+		     struct kernel_hwtstamp_config *cfg)
+{
+	cfg->tx_type = HWTSTAMP_TX_ON;
+	cfg->rx_filter = HWTSTAMP_FILTER_ALL;
 
-	WRITE_ONCE(dev->mtu, new_mtu);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(can_change_mtu);
+EXPORT_SYMBOL(can_hwtstamp_get);
 
-/* generic implementation of netdev_ops::ndo_eth_ioctl for CAN devices
+/* generic implementation of netdev_ops::ndo_hwtstamp_set for CAN devices
  * supporting hardware timestamps
  */
-int can_eth_ioctl_hwts(struct net_device *netdev, struct ifreq *ifr, int cmd)
+int can_hwtstamp_set(struct net_device *netdev,
+		     struct kernel_hwtstamp_config *cfg,
+		     struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config hwts_cfg = { 0 };
-
-	switch (cmd) {
-	case SIOCSHWTSTAMP: /* set */
-		if (copy_from_user(&hwts_cfg, ifr->ifr_data, sizeof(hwts_cfg)))
-			return -EFAULT;
-		if (hwts_cfg.tx_type == HWTSTAMP_TX_ON &&
-		    hwts_cfg.rx_filter == HWTSTAMP_FILTER_ALL)
-			return 0;
-		return -ERANGE;
-
-	case SIOCGHWTSTAMP: /* get */
-		hwts_cfg.tx_type = HWTSTAMP_TX_ON;
-		hwts_cfg.rx_filter = HWTSTAMP_FILTER_ALL;
-		if (copy_to_user(ifr->ifr_data, &hwts_cfg, sizeof(hwts_cfg)))
-			return -EFAULT;
+	if (cfg->tx_type == HWTSTAMP_TX_ON &&
+	    cfg->rx_filter == HWTSTAMP_FILTER_ALL)
 		return 0;
-
-	default:
-		return -EOPNOTSUPP;
-	}
+	NL_SET_ERR_MSG_MOD(extack, "Only TX on and RX all packets filter supported");
+	return -ERANGE;
 }
-EXPORT_SYMBOL(can_eth_ioctl_hwts);
+EXPORT_SYMBOL(can_hwtstamp_set);
 
 /* generic implementation of ethtool_ops::get_ts_info for CAN devices
  * supporting hardware timestamps
@@ -406,8 +457,8 @@ int open_candev(struct net_device *dev)
 
 	/* For CAN FD the data bitrate has to be >= the arbitration bitrate */
 	if ((priv->ctrlmode & CAN_CTRLMODE_FD) &&
-	    (!priv->data_bittiming.bitrate ||
-	     priv->data_bittiming.bitrate < priv->bittiming.bitrate)) {
+	    (!priv->fd.data_bittiming.bitrate ||
+	     priv->fd.data_bittiming.bitrate < priv->bittiming.bitrate)) {
 		netdev_err(dev, "incorrect/missing data bit-timing\n");
 		return -EINVAL;
 	}
@@ -545,16 +596,16 @@ int register_candev(struct net_device *dev)
 	if (!priv->bitrate_const != !priv->bitrate_const_cnt)
 		return -EINVAL;
 
-	if (!priv->data_bitrate_const != !priv->data_bitrate_const_cnt)
+	if (!priv->fd.data_bitrate_const != !priv->fd.data_bitrate_const_cnt)
 		return -EINVAL;
 
 	/* We only support either fixed bit rates or bit timing const. */
-	if ((priv->bitrate_const || priv->data_bitrate_const) &&
-	    (priv->bittiming_const || priv->data_bittiming_const))
+	if ((priv->bitrate_const || priv->fd.data_bitrate_const) &&
+	    (priv->bittiming_const || priv->fd.data_bittiming_const))
 		return -EINVAL;
 
 	if (!can_bittiming_const_valid(priv->bittiming_const) ||
-	    !can_bittiming_const_valid(priv->data_bittiming_const))
+	    !can_bittiming_const_valid(priv->fd.data_bittiming_const))
 		return -EINVAL;
 
 	if (!priv->termination_const) {
diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index 01aacdcda260..d6b0e686fb11 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -2,7 +2,7 @@
 /* Copyright (C) 2005 Marc Kleine-Budde, Pengutronix
  * Copyright (C) 2006 Andrey Volkov, Varma Electronics
  * Copyright (C) 2008-2009 Wolfgang Grandegger <wg@grandegger.com>
- * Copyright (C) 2021 Vincent Mailhol <mailhol.vincent@wanadoo.fr>
+ * Copyright (C) 2021-2025 Vincent Mailhol <mailhol@kernel.org>
  */
 
 #include <linux/can/dev.h>
@@ -18,10 +18,14 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = {
 	[IFLA_CAN_CLOCK] = { .len = sizeof(struct can_clock) },
 	[IFLA_CAN_BERR_COUNTER] = { .len = sizeof(struct can_berr_counter) },
 	[IFLA_CAN_DATA_BITTIMING] = { .len = sizeof(struct can_bittiming) },
-	[IFLA_CAN_DATA_BITTIMING_CONST]	= { .len = sizeof(struct can_bittiming_const) },
+	[IFLA_CAN_DATA_BITTIMING_CONST] = { .len = sizeof(struct can_bittiming_const) },
 	[IFLA_CAN_TERMINATION] = { .type = NLA_U16 },
 	[IFLA_CAN_TDC] = { .type = NLA_NESTED },
 	[IFLA_CAN_CTRLMODE_EXT] = { .type = NLA_NESTED },
+	[IFLA_CAN_XL_DATA_BITTIMING] = { .len = sizeof(struct can_bittiming) },
+	[IFLA_CAN_XL_DATA_BITTIMING_CONST] = { .len = sizeof(struct can_bittiming_const) },
+	[IFLA_CAN_XL_TDC] = { .type = NLA_NESTED },
+	[IFLA_CAN_XL_PWM] = { .type = NLA_NESTED },
 };
 
 static const struct nla_policy can_tdc_policy[IFLA_CAN_TDC_MAX + 1] = {
@@ -36,116 +40,360 @@ static const struct nla_policy can_tdc_policy[IFLA_CAN_TDC_MAX + 1] = {
 	[IFLA_CAN_TDC_TDCF] = { .type = NLA_U32 },
 };
 
-static int can_validate_bittiming(const struct can_bittiming *bt,
-				  struct netlink_ext_ack *extack)
+static const struct nla_policy can_pwm_policy[IFLA_CAN_PWM_MAX + 1] = {
+	[IFLA_CAN_PWM_PWMS_MIN] = { .type = NLA_U32 },
+	[IFLA_CAN_PWM_PWMS_MAX] = { .type = NLA_U32 },
+	[IFLA_CAN_PWM_PWML_MIN] = { .type = NLA_U32 },
+	[IFLA_CAN_PWM_PWML_MAX] = { .type = NLA_U32 },
+	[IFLA_CAN_PWM_PWMO_MIN] = { .type = NLA_U32 },
+	[IFLA_CAN_PWM_PWMO_MAX] = { .type = NLA_U32 },
+	[IFLA_CAN_PWM_PWMS] = { .type = NLA_U32 },
+	[IFLA_CAN_PWM_PWML] = { .type = NLA_U32 },
+	[IFLA_CAN_PWM_PWMO] = { .type = NLA_U32 },
+};
+
+static int can_validate_bittiming(struct nlattr *data[],
+				  struct netlink_ext_ack *extack,
+				  int ifla_can_bittiming)
 {
+	struct can_bittiming *bt;
+
+	if (!data[ifla_can_bittiming])
+		return 0;
+
+	static_assert(__alignof__(*bt) <= NLA_ALIGNTO);
+	bt = nla_data(data[ifla_can_bittiming]);
+
 	/* sample point is in one-tenth of a percent */
 	if (bt->sample_point >= 1000) {
 		NL_SET_ERR_MSG(extack, "sample point must be between 0 and 100%");
-
 		return -EINVAL;
 	}
 
 	return 0;
 }
 
-static int can_validate(struct nlattr *tb[], struct nlattr *data[],
-			struct netlink_ext_ack *extack)
+static int can_validate_tdc(struct nlattr *data_tdc,
+			    struct netlink_ext_ack *extack, u32 tdc_flags)
 {
-	bool is_can_fd = false;
+	bool tdc_manual = tdc_flags & CAN_CTRLMODE_TDC_MANUAL_MASK;
+	bool tdc_auto = tdc_flags & CAN_CTRLMODE_TDC_AUTO_MASK;
 	int err;
 
-	/* Make sure that valid CAN FD configurations always consist of
-	 * - nominal/arbitration bittiming
-	 * - data bittiming
-	 * - control mode with CAN_CTRLMODE_FD set
-	 * - TDC parameters are coherent (details below)
+	if (tdc_auto && tdc_manual) {
+		NL_SET_ERR_MSG(extack,
+			       "TDC manual and auto modes are mutually exclusive");
+		return -EOPNOTSUPP;
+	}
+
+	/* If one of the CAN_CTRLMODE_{,XL}_TDC_* flags is set then TDC
+	 * must be set and vice-versa
 	 */
+	if ((tdc_auto || tdc_manual) && !data_tdc) {
+		NL_SET_ERR_MSG(extack, "TDC parameters are missing");
+		return -EOPNOTSUPP;
+	}
+	if (!(tdc_auto || tdc_manual) && data_tdc) {
+		NL_SET_ERR_MSG(extack, "TDC mode (auto or manual) is missing");
+		return -EOPNOTSUPP;
+	}
 
-	if (!data)
+	/* If providing TDC parameters, at least TDCO is needed. TDCV is
+	 * needed if and only if CAN_CTRLMODE_{,XL}_TDC_MANUAL is set
+	 */
+	if (data_tdc) {
+		struct nlattr *tb_tdc[IFLA_CAN_TDC_MAX + 1];
+
+		err = nla_parse_nested(tb_tdc, IFLA_CAN_TDC_MAX,
+				       data_tdc, can_tdc_policy, extack);
+		if (err)
+			return err;
+
+		if (tb_tdc[IFLA_CAN_TDC_TDCV]) {
+			if (tdc_auto) {
+				NL_SET_ERR_MSG(extack,
+					       "TDCV is incompatible with TDC auto mode");
+				return -EOPNOTSUPP;
+			}
+		} else {
+			if (tdc_manual) {
+				NL_SET_ERR_MSG(extack,
+					       "TDC manual mode requires TDCV");
+				return -EOPNOTSUPP;
+			}
+		}
+
+		if (!tb_tdc[IFLA_CAN_TDC_TDCO]) {
+			NL_SET_ERR_MSG(extack, "TDCO is missing");
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static int can_validate_pwm(struct nlattr *data[],
+			    struct netlink_ext_ack *extack, u32 flags)
+{
+	struct nlattr *tb_pwm[IFLA_CAN_PWM_MAX + 1];
+	int err;
+
+	if (!data[IFLA_CAN_XL_PWM])
 		return 0;
 
-	if (data[IFLA_CAN_CTRLMODE]) {
-		struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]);
-		u32 tdc_flags = cm->flags & CAN_CTRLMODE_TDC_MASK;
+	if (!(flags & CAN_CTRLMODE_XL_TMS)) {
+		NL_SET_ERR_MSG(extack, "PWM requires TMS");
+		return -EOPNOTSUPP;
+	}
+
+	err = nla_parse_nested(tb_pwm, IFLA_CAN_PWM_MAX, data[IFLA_CAN_XL_PWM],
+			       can_pwm_policy, extack);
+	if (err)
+		return err;
+
+	if (!tb_pwm[IFLA_CAN_PWM_PWMS] != !tb_pwm[IFLA_CAN_PWM_PWML]) {
+		NL_SET_ERR_MSG(extack,
+			       "Provide either both PWMS and PWML, or none for automatic calculation");
+		return -EOPNOTSUPP;
+	}
+
+	if (tb_pwm[IFLA_CAN_PWM_PWMO] &&
+	    (!tb_pwm[IFLA_CAN_PWM_PWMS] || !tb_pwm[IFLA_CAN_PWM_PWML])) {
+		NL_SET_ERR_MSG(extack, "PWMO requires both PWMS and PWML");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int can_validate_databittiming(struct nlattr *data[],
+				      struct netlink_ext_ack *extack,
+				      int ifla_can_data_bittiming, u32 flags)
+{
+	struct nlattr *data_tdc;
+	const char *type;
+	u32 tdc_flags;
+	bool is_on;
+	int err;
 
-		is_can_fd = cm->flags & cm->mask & CAN_CTRLMODE_FD;
+	/* Make sure that valid CAN FD/XL configurations always consist of
+	 * - nominal/arbitration bittiming
+	 * - data bittiming
+	 * - control mode with CAN_CTRLMODE_{FD,XL} set
+	 * - TDC parameters are coherent (details in can_validate_tdc())
+	 */
+
+	if (ifla_can_data_bittiming == IFLA_CAN_DATA_BITTIMING) {
+		data_tdc = data[IFLA_CAN_TDC];
+		tdc_flags = flags & CAN_CTRLMODE_FD_TDC_MASK;
+		is_on = flags & CAN_CTRLMODE_FD;
+		type = "FD";
+	} else {
+		data_tdc = data[IFLA_CAN_XL_TDC];
+		tdc_flags = flags & CAN_CTRLMODE_XL_TDC_MASK;
+		is_on = flags & CAN_CTRLMODE_XL;
+		type = "XL";
+	}
 
-		/* CAN_CTRLMODE_TDC_{AUTO,MANUAL} are mutually exclusive */
-		if (tdc_flags == CAN_CTRLMODE_TDC_MASK)
+	if (is_on) {
+		if (!data[IFLA_CAN_BITTIMING] || !data[ifla_can_data_bittiming]) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "Provide both nominal and %s data bittiming",
+					   type);
 			return -EOPNOTSUPP;
-		/* If one of the CAN_CTRLMODE_TDC_* flag is set then
-		 * TDC must be set and vice-versa
-		 */
-		if (!!tdc_flags != !!data[IFLA_CAN_TDC])
+		}
+	} else {
+		if (data[ifla_can_data_bittiming]) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "%s data bittiming requires CAN %s",
+					   type, type);
 			return -EOPNOTSUPP;
-		/* If providing TDC parameters, at least TDCO is
-		 * needed. TDCV is needed if and only if
-		 * CAN_CTRLMODE_TDC_MANUAL is set
-		 */
-		if (data[IFLA_CAN_TDC]) {
-			struct nlattr *tb_tdc[IFLA_CAN_TDC_MAX + 1];
+		}
+		if (data_tdc) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "%s TDC requires CAN %s",
+					   type, type);
+			return -EOPNOTSUPP;
+		}
+	}
 
-			err = nla_parse_nested(tb_tdc, IFLA_CAN_TDC_MAX,
-					       data[IFLA_CAN_TDC],
-					       can_tdc_policy, extack);
-			if (err)
-				return err;
+	err = can_validate_bittiming(data, extack, ifla_can_data_bittiming);
+	if (err)
+		return err;
 
-			if (tb_tdc[IFLA_CAN_TDC_TDCV]) {
-				if (tdc_flags & CAN_CTRLMODE_TDC_AUTO)
-					return -EOPNOTSUPP;
-			} else {
-				if (tdc_flags & CAN_CTRLMODE_TDC_MANUAL)
-					return -EOPNOTSUPP;
-			}
+	err = can_validate_tdc(data_tdc, extack, tdc_flags);
+	if (err)
+		return err;
+
+	return 0;
+}
 
-			if (!tb_tdc[IFLA_CAN_TDC_TDCO])
+static int can_validate_xl_flags(struct netlink_ext_ack *extack,
+				 u32 masked_flags, u32 mask)
+{
+	if (masked_flags & CAN_CTRLMODE_XL) {
+		if (masked_flags & CAN_CTRLMODE_XL_TMS) {
+			const u32 tms_conflicts_mask = CAN_CTRLMODE_FD |
+				CAN_CTRLMODE_XL_TDC_MASK;
+			u32 tms_conflicts = masked_flags & tms_conflicts_mask;
+
+			if (tms_conflicts) {
+				NL_SET_ERR_MSG_FMT(extack,
+						   "TMS and %s are mutually exclusive",
+						   can_get_ctrlmode_str(tms_conflicts));
 				return -EOPNOTSUPP;
+			}
+		}
+	} else {
+		if (mask & CAN_CTRLMODE_XL_TMS) {
+			NL_SET_ERR_MSG(extack, "TMS requires CAN XL");
+			return -EOPNOTSUPP;
 		}
 	}
 
-	if (data[IFLA_CAN_BITTIMING]) {
-		struct can_bittiming bt;
+	return 0;
+}
 
-		memcpy(&bt, nla_data(data[IFLA_CAN_BITTIMING]), sizeof(bt));
-		err = can_validate_bittiming(&bt, extack);
+static int can_validate(struct nlattr *tb[], struct nlattr *data[],
+			struct netlink_ext_ack *extack)
+{
+	u32 flags = 0;
+	int err;
+
+	if (!data)
+		return 0;
+
+	if (data[IFLA_CAN_CTRLMODE]) {
+		struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]);
+
+		flags = cm->flags & cm->mask;
+
+		if ((flags & CAN_CTRLMODE_LISTENONLY) &&
+		    (flags & CAN_CTRLMODE_RESTRICTED)) {
+			NL_SET_ERR_MSG(extack,
+				       "LISTEN-ONLY and RESTRICTED modes are mutually exclusive");
+			return -EOPNOTSUPP;
+		}
+
+		err = can_validate_xl_flags(extack, flags, cm->mask);
 		if (err)
 			return err;
 	}
 
-	if (is_can_fd) {
-		if (!data[IFLA_CAN_BITTIMING] || !data[IFLA_CAN_DATA_BITTIMING])
-			return -EOPNOTSUPP;
+	err = can_validate_bittiming(data, extack, IFLA_CAN_BITTIMING);
+	if (err)
+		return err;
+
+	err = can_validate_databittiming(data, extack,
+					 IFLA_CAN_DATA_BITTIMING, flags);
+	if (err)
+		return err;
+
+	err = can_validate_databittiming(data, extack,
+					 IFLA_CAN_XL_DATA_BITTIMING, flags);
+	if (err)
+		return err;
+
+	err = can_validate_pwm(data, extack, flags);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int can_ctrlmode_changelink(struct net_device *dev,
+				   struct nlattr *data[],
+				   struct netlink_ext_ack *extack)
+{
+	struct can_priv *priv = netdev_priv(dev);
+	struct can_ctrlmode *cm;
+	u32 ctrlstatic, maskedflags, deactivated, notsupp, ctrlstatic_missing;
+
+	if (!data[IFLA_CAN_CTRLMODE])
+		return 0;
+
+	/* Do not allow changing controller mode while running */
+	if (dev->flags & IFF_UP)
+		return -EBUSY;
+
+	cm = nla_data(data[IFLA_CAN_CTRLMODE]);
+	ctrlstatic = can_get_static_ctrlmode(priv);
+	maskedflags = cm->flags & cm->mask;
+	deactivated = ~cm->flags & cm->mask;
+	notsupp = maskedflags & ~(priv->ctrlmode_supported | ctrlstatic);
+	ctrlstatic_missing = (maskedflags & ctrlstatic) ^ ctrlstatic;
+
+	if (notsupp) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "requested control mode %s not supported",
+				   can_get_ctrlmode_str(notsupp));
+		return -EOPNOTSUPP;
 	}
 
-	if (data[IFLA_CAN_DATA_BITTIMING] || data[IFLA_CAN_TDC]) {
-		if (!is_can_fd)
-			return -EOPNOTSUPP;
+	/* do not check for static fd-non-iso if 'fd' is disabled */
+	if (!(maskedflags & CAN_CTRLMODE_FD))
+		ctrlstatic &= ~CAN_CTRLMODE_FD_NON_ISO;
+
+	if (ctrlstatic_missing) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "missing required %s static control mode",
+				   can_get_ctrlmode_str(ctrlstatic_missing));
+		return -EOPNOTSUPP;
 	}
 
-	if (data[IFLA_CAN_DATA_BITTIMING]) {
-		struct can_bittiming bt;
+	/* If FD was active and is not turned off, check for XL conflicts */
+	if (priv->ctrlmode & CAN_CTRLMODE_FD & ~deactivated) {
+		if (maskedflags & CAN_CTRLMODE_XL_TMS) {
+			NL_SET_ERR_MSG(extack,
+				       "TMS can not be activated while CAN FD is on");
+			return -EOPNOTSUPP;
+		}
+	}
 
-		memcpy(&bt, nla_data(data[IFLA_CAN_DATA_BITTIMING]), sizeof(bt));
-		err = can_validate_bittiming(&bt, extack);
-		if (err)
-			return err;
+	/* If a top dependency flag is provided, reset all its dependencies */
+	if (cm->mask & CAN_CTRLMODE_FD)
+		priv->ctrlmode &= ~CAN_CTRLMODE_FD_TDC_MASK;
+	if (cm->mask & CAN_CTRLMODE_XL)
+		priv->ctrlmode &= ~(CAN_CTRLMODE_XL_TDC_MASK |
+				    CAN_CTRLMODE_XL_TMS);
+
+	/* clear bits to be modified and copy the flag values */
+	priv->ctrlmode &= ~cm->mask;
+	priv->ctrlmode |= maskedflags;
+
+	/* Wipe potential leftovers from previous CAN FD/XL config */
+	if (!(priv->ctrlmode & CAN_CTRLMODE_FD)) {
+		memset(&priv->fd.data_bittiming, 0,
+		       sizeof(priv->fd.data_bittiming));
+		priv->ctrlmode &= ~CAN_CTRLMODE_FD_TDC_MASK;
+		memset(&priv->fd.tdc, 0, sizeof(priv->fd.tdc));
 	}
+	if (!(priv->ctrlmode & CAN_CTRLMODE_XL)) {
+		memset(&priv->xl.data_bittiming, 0,
+		       sizeof(priv->fd.data_bittiming));
+		priv->ctrlmode &= ~CAN_CTRLMODE_XL_TDC_MASK;
+		memset(&priv->xl.tdc, 0, sizeof(priv->xl.tdc));
+		memset(&priv->xl.pwm, 0, sizeof(priv->xl.pwm));
+	}
+
+	can_set_default_mtu(dev);
 
 	return 0;
 }
 
-static int can_tdc_changelink(struct can_priv *priv, const struct nlattr *nla,
+static int can_tdc_changelink(struct data_bittiming_params *dbt_params,
+			      const struct nlattr *nla,
 			      struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb_tdc[IFLA_CAN_TDC_MAX + 1];
 	struct can_tdc tdc = { 0 };
-	const struct can_tdc_const *tdc_const = priv->tdc_const;
+	const struct can_tdc_const *tdc_const = dbt_params->tdc_const;
 	int err;
 
-	if (!tdc_const || !can_tdc_is_enabled(priv))
+	if (!tdc_const) {
+		NL_SET_ERR_MSG(extack, "The device does not support TDC");
 		return -EOPNOTSUPP;
+	}
 
 	err = nla_parse_nested(tb_tdc, IFLA_CAN_TDC_MAX, nla,
 			       can_tdc_policy, extack);
@@ -179,69 +427,181 @@ static int can_tdc_changelink(struct can_priv *priv, const struct nlattr *nla,
 		tdc.tdcf = tdcf;
 	}
 
-	priv->tdc = tdc;
+	dbt_params->tdc = tdc;
 
 	return 0;
 }
 
-static int can_changelink(struct net_device *dev, struct nlattr *tb[],
-			  struct nlattr *data[],
-			  struct netlink_ext_ack *extack)
+static int can_dbt_changelink(struct net_device *dev, struct nlattr *data[],
+			      bool fd, struct netlink_ext_ack *extack)
 {
+	struct nlattr *data_bittiming, *data_tdc;
 	struct can_priv *priv = netdev_priv(dev);
-	u32 tdc_mask = 0;
+	struct data_bittiming_params *dbt_params;
+	struct can_bittiming dbt;
+	bool need_tdc_calc = false;
+	u32 tdc_mask;
 	int err;
 
-	/* We need synchronization with dev->stop() */
-	ASSERT_RTNL();
+	if (fd) {
+		data_bittiming = data[IFLA_CAN_DATA_BITTIMING];
+		data_tdc = data[IFLA_CAN_TDC];
+		dbt_params = &priv->fd;
+		tdc_mask = CAN_CTRLMODE_FD_TDC_MASK;
+	} else {
+		data_bittiming = data[IFLA_CAN_XL_DATA_BITTIMING];
+		data_tdc = data[IFLA_CAN_XL_TDC];
+		dbt_params = &priv->xl;
+		tdc_mask = CAN_CTRLMODE_XL_TDC_MASK;
+	}
+
+	if (!data_bittiming)
+		return 0;
+
+	/* Do not allow changing bittiming while running */
+	if (dev->flags & IFF_UP)
+		return -EBUSY;
+
+	/* Calculate bittiming parameters based on data_bittiming_const
+	 * if set, otherwise pass bitrate directly via do_set_bitrate().
+	 * Bail out if neither is given.
+	 */
+	if (!dbt_params->data_bittiming_const && !dbt_params->do_set_data_bittiming &&
+	    !dbt_params->data_bitrate_const)
+		return -EOPNOTSUPP;
+
+	memcpy(&dbt, nla_data(data_bittiming), sizeof(dbt));
+	err = can_get_bittiming(dev, &dbt, dbt_params->data_bittiming_const,
+				dbt_params->data_bitrate_const,
+				dbt_params->data_bitrate_const_cnt, extack);
+	if (err)
+		return err;
+
+	if (priv->bitrate_max && dbt.bitrate > priv->bitrate_max) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "CAN data bitrate %u bps surpasses transceiver capabilities of %u bps",
+				   dbt.bitrate, priv->bitrate_max);
+		return -EINVAL;
+	}
 
+	memset(&dbt_params->tdc, 0, sizeof(dbt_params->tdc));
 	if (data[IFLA_CAN_CTRLMODE]) {
-		struct can_ctrlmode *cm;
-		u32 ctrlstatic;
-		u32 maskedflags;
+		struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]);
 
-		/* Do not allow changing controller mode while running */
-		if (dev->flags & IFF_UP)
-			return -EBUSY;
-		cm = nla_data(data[IFLA_CAN_CTRLMODE]);
-		ctrlstatic = can_get_static_ctrlmode(priv);
-		maskedflags = cm->flags & cm->mask;
+		if (fd || !(priv->ctrlmode & CAN_CTRLMODE_XL_TMS))
+			need_tdc_calc = !(cm->mask & tdc_mask);
+	}
+	if (data_tdc) {
+		/* TDC parameters are provided: use them */
+		err = can_tdc_changelink(dbt_params, data_tdc, extack);
+		if (err) {
+			priv->ctrlmode &= ~tdc_mask;
+			return err;
+		}
+	} else if (need_tdc_calc) {
+		/* Neither of TDC parameters nor TDC flags are provided:
+		 * do calculation
+		 */
+		can_calc_tdco(&dbt_params->tdc, dbt_params->tdc_const, &dbt,
+			      tdc_mask, &priv->ctrlmode, priv->ctrlmode_supported);
+	} /* else: both CAN_CTRLMODE_{,XL}_TDC_{AUTO,MANUAL} are explicitly
+	   * turned off. TDC is disabled: do nothing
+	   */
 
-		/* check whether provided bits are allowed to be passed */
-		if (maskedflags & ~(priv->ctrlmode_supported | ctrlstatic))
-			return -EOPNOTSUPP;
+	memcpy(&dbt_params->data_bittiming, &dbt, sizeof(dbt));
 
-		/* do not check for static fd-non-iso if 'fd' is disabled */
-		if (!(maskedflags & CAN_CTRLMODE_FD))
-			ctrlstatic &= ~CAN_CTRLMODE_FD_NON_ISO;
+	if (dbt_params->do_set_data_bittiming) {
+		/* Finally, set the bit-timing registers */
+		err = dbt_params->do_set_data_bittiming(dev);
+		if (err)
+			return err;
+	}
 
-		/* make sure static options are provided by configuration */
-		if ((maskedflags & ctrlstatic) != ctrlstatic)
-			return -EOPNOTSUPP;
+	return 0;
+}
 
-		/* clear bits to be modified and copy the flag values */
-		priv->ctrlmode &= ~cm->mask;
-		priv->ctrlmode |= maskedflags;
+static int can_pwm_changelink(struct net_device *dev,
+			      const struct nlattr *pwm_nla,
+			      struct netlink_ext_ack *extack)
+{
+	struct can_priv *priv = netdev_priv(dev);
+	const struct can_pwm_const *pwm_const = priv->xl.pwm_const;
+	struct nlattr *tb_pwm[IFLA_CAN_PWM_MAX + 1];
+	struct can_pwm pwm = { 0 };
+	int err;
 
-		/* CAN_CTRLMODE_FD can only be set when driver supports FD */
-		if (priv->ctrlmode & CAN_CTRLMODE_FD) {
-			dev->mtu = CANFD_MTU;
-		} else {
-			dev->mtu = CAN_MTU;
-			memset(&priv->data_bittiming, 0,
-			       sizeof(priv->data_bittiming));
-			priv->ctrlmode &= ~CAN_CTRLMODE_TDC_MASK;
-			memset(&priv->tdc, 0, sizeof(priv->tdc));
+	if (!(priv->ctrlmode & CAN_CTRLMODE_XL_TMS))
+		return 0;
+
+	if (!pwm_const) {
+		NL_SET_ERR_MSG(extack, "The device does not support PWM");
+		return -EOPNOTSUPP;
+	}
+
+	if (!pwm_nla)
+		return can_calc_pwm(dev, extack);
+
+	err = nla_parse_nested(tb_pwm, IFLA_CAN_PWM_MAX, pwm_nla,
+			       can_pwm_policy, extack);
+	if (err)
+		return err;
+
+	if (tb_pwm[IFLA_CAN_PWM_PWMS]) {
+		pwm.pwms = nla_get_u32(tb_pwm[IFLA_CAN_PWM_PWMS]);
+		if (pwm.pwms < pwm_const->pwms_min ||
+		    pwm.pwms > pwm_const->pwms_max) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "PWMS: %u tqmin is out of range: %u...%u",
+					   pwm.pwms, pwm_const->pwms_min,
+					   pwm_const->pwms_max);
+			return -EINVAL;
 		}
+	}
 
-		tdc_mask = cm->mask & CAN_CTRLMODE_TDC_MASK;
-		/* CAN_CTRLMODE_TDC_{AUTO,MANUAL} are mutually
-		 * exclusive: make sure to turn the other one off
-		 */
-		if (tdc_mask)
-			priv->ctrlmode &= cm->flags | ~CAN_CTRLMODE_TDC_MASK;
+	if (tb_pwm[IFLA_CAN_PWM_PWML]) {
+		pwm.pwml = nla_get_u32(tb_pwm[IFLA_CAN_PWM_PWML]);
+		if (pwm.pwml < pwm_const->pwml_min ||
+		    pwm.pwml > pwm_const->pwml_max) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "PWML: %u tqmin is out of range: %u...%u",
+					   pwm.pwml, pwm_const->pwml_min,
+					   pwm_const->pwml_max);
+			return -EINVAL;
+		}
+	}
+
+	if (tb_pwm[IFLA_CAN_PWM_PWMO]) {
+		pwm.pwmo = nla_get_u32(tb_pwm[IFLA_CAN_PWM_PWMO]);
+		if (pwm.pwmo < pwm_const->pwmo_min ||
+		    pwm.pwmo > pwm_const->pwmo_max) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "PWMO: %u tqmin is out of range: %u...%u",
+					   pwm.pwmo, pwm_const->pwmo_min,
+					   pwm_const->pwmo_max);
+			return -EINVAL;
+		}
 	}
 
+	err = can_validate_pwm_bittiming(dev, &pwm, extack);
+	if (err)
+		return err;
+
+	priv->xl.pwm = pwm;
+	return 0;
+}
+
+static int can_changelink(struct net_device *dev, struct nlattr *tb[],
+			  struct nlattr *data[],
+			  struct netlink_ext_ack *extack)
+{
+	struct can_priv *priv = netdev_priv(dev);
+	int err;
+
+	/* We need synchronization with dev->stop() */
+	ASSERT_RTNL();
+
+	can_ctrlmode_changelink(dev, data, extack);
+
 	if (data[IFLA_CAN_BITTIMING]) {
 		struct can_bittiming bt;
 
@@ -285,13 +645,27 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 	}
 
 	if (data[IFLA_CAN_RESTART_MS]) {
+		unsigned int restart_ms = nla_get_u32(data[IFLA_CAN_RESTART_MS]);
+
+		if (restart_ms != 0 && !priv->do_set_mode) {
+			NL_SET_ERR_MSG(extack,
+				       "Device doesn't support restart from Bus Off");
+			return -EOPNOTSUPP;
+		}
+
 		/* Do not allow changing restart delay while running */
 		if (dev->flags & IFF_UP)
 			return -EBUSY;
-		priv->restart_ms = nla_get_u32(data[IFLA_CAN_RESTART_MS]);
+		priv->restart_ms = restart_ms;
 	}
 
 	if (data[IFLA_CAN_RESTART]) {
+		if (!priv->do_set_mode) {
+			NL_SET_ERR_MSG(extack,
+				       "Device doesn't support restart from Bus Off");
+			return -EOPNOTSUPP;
+		}
+
 		/* Do not allow a restart while not running */
 		if (!(dev->flags & IFF_UP))
 			return -EINVAL;
@@ -300,75 +674,29 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 			return err;
 	}
 
-	if (data[IFLA_CAN_DATA_BITTIMING]) {
-		struct can_bittiming dbt;
-
-		/* Do not allow changing bittiming while running */
-		if (dev->flags & IFF_UP)
-			return -EBUSY;
-
-		/* Calculate bittiming parameters based on
-		 * data_bittiming_const if set, otherwise pass bitrate
-		 * directly via do_set_bitrate(). Bail out if neither
-		 * is given.
-		 */
-		if (!priv->data_bittiming_const && !priv->do_set_data_bittiming &&
-		    !priv->data_bitrate_const)
-			return -EOPNOTSUPP;
-
-		memcpy(&dbt, nla_data(data[IFLA_CAN_DATA_BITTIMING]),
-		       sizeof(dbt));
-		err = can_get_bittiming(dev, &dbt,
-					priv->data_bittiming_const,
-					priv->data_bitrate_const,
-					priv->data_bitrate_const_cnt,
-					extack);
-		if (err)
-			return err;
-
-		if (priv->bitrate_max && dbt.bitrate > priv->bitrate_max) {
-			NL_SET_ERR_MSG_FMT(extack,
-					   "CANFD data bitrate %u bps surpasses transceiver capabilities of %u bps",
-					   dbt.bitrate, priv->bitrate_max);
-			return -EINVAL;
-		}
+	/* CAN FD */
+	err = can_dbt_changelink(dev, data, true, extack);
+	if (err)
+		return err;
 
-		memset(&priv->tdc, 0, sizeof(priv->tdc));
-		if (data[IFLA_CAN_TDC]) {
-			/* TDC parameters are provided: use them */
-			err = can_tdc_changelink(priv, data[IFLA_CAN_TDC],
-						 extack);
-			if (err) {
-				priv->ctrlmode &= ~CAN_CTRLMODE_TDC_MASK;
-				return err;
-			}
-		} else if (!tdc_mask) {
-			/* Neither of TDC parameters nor TDC flags are
-			 * provided: do calculation
-			 */
-			can_calc_tdco(&priv->tdc, priv->tdc_const, &dbt,
-				      &priv->ctrlmode, priv->ctrlmode_supported);
-		} /* else: both CAN_CTRLMODE_TDC_{AUTO,MANUAL} are explicitly
-		   * turned off. TDC is disabled: do nothing
-		   */
-
-		memcpy(&priv->data_bittiming, &dbt, sizeof(dbt));
-
-		if (priv->do_set_data_bittiming) {
-			/* Finally, set the bit-timing registers */
-			err = priv->do_set_data_bittiming(dev);
-			if (err)
-				return err;
-		}
-	}
+	/* CAN XL */
+	err = can_dbt_changelink(dev, data, false, extack);
+	if (err)
+		return err;
+	err = can_pwm_changelink(dev, data[IFLA_CAN_XL_PWM], extack);
+	if (err)
+		return err;
 
 	if (data[IFLA_CAN_TERMINATION]) {
 		const u16 termval = nla_get_u16(data[IFLA_CAN_TERMINATION]);
 		const unsigned int num_term = priv->termination_const_cnt;
 		unsigned int i;
 
-		if (!priv->do_set_termination)
+		if (!priv->do_set_termination) {
+			NL_SET_ERR_MSG(extack,
+				       "Termination is not configurable on this device");
 			return -EOPNOTSUPP;
+		}
 
 		/* check whether given value is supported by the interface */
 		for (i = 0; i < num_term; i++) {
@@ -389,44 +717,85 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 	return 0;
 }
 
-static size_t can_tdc_get_size(const struct net_device *dev)
+static size_t can_tdc_get_size(struct data_bittiming_params *dbt_params,
+			       u32 tdc_flags)
 {
-	struct can_priv *priv = netdev_priv(dev);
+	bool tdc_manual = tdc_flags & CAN_CTRLMODE_TDC_MANUAL_MASK;
 	size_t size;
 
-	if (!priv->tdc_const)
+	if (!dbt_params->tdc_const)
 		return 0;
 
 	size = nla_total_size(0);			/* nest IFLA_CAN_TDC */
-	if (priv->ctrlmode_supported & CAN_CTRLMODE_TDC_MANUAL) {
+	if (tdc_manual) {
 		size += nla_total_size(sizeof(u32));	/* IFLA_CAN_TDCV_MIN */
 		size += nla_total_size(sizeof(u32));	/* IFLA_CAN_TDCV_MAX */
 	}
 	size += nla_total_size(sizeof(u32));		/* IFLA_CAN_TDCO_MIN */
 	size += nla_total_size(sizeof(u32));		/* IFLA_CAN_TDCO_MAX */
-	if (priv->tdc_const->tdcf_max) {
+	if (dbt_params->tdc_const->tdcf_max) {
 		size += nla_total_size(sizeof(u32));	/* IFLA_CAN_TDCF_MIN */
 		size += nla_total_size(sizeof(u32));	/* IFLA_CAN_TDCF_MAX */
 	}
 
-	if (can_tdc_is_enabled(priv)) {
-		if (priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL ||
-		    priv->do_get_auto_tdcv)
+	if (tdc_flags) {
+		if (tdc_manual || dbt_params->do_get_auto_tdcv)
 			size += nla_total_size(sizeof(u32));	/* IFLA_CAN_TDCV */
 		size += nla_total_size(sizeof(u32));		/* IFLA_CAN_TDCO */
-		if (priv->tdc_const->tdcf_max)
+		if (dbt_params->tdc_const->tdcf_max)
 			size += nla_total_size(sizeof(u32));	/* IFLA_CAN_TDCF */
 	}
 
 	return size;
 }
 
+static size_t can_data_bittiming_get_size(struct data_bittiming_params *dbt_params,
+					  u32 tdc_flags)
+{
+	size_t size = 0;
+
+	if (dbt_params->data_bittiming.bitrate)		/* IFLA_CAN_{,XL}_DATA_BITTIMING */
+		size += nla_total_size(sizeof(dbt_params->data_bittiming));
+	if (dbt_params->data_bittiming_const)		/* IFLA_CAN_{,XL}_DATA_BITTIMING_CONST */
+		size += nla_total_size(sizeof(*dbt_params->data_bittiming_const));
+	if (dbt_params->data_bitrate_const)		/* IFLA_CAN_{,XL}_DATA_BITRATE_CONST */
+		size += nla_total_size(sizeof(*dbt_params->data_bitrate_const) *
+				       dbt_params->data_bitrate_const_cnt);
+	size += can_tdc_get_size(dbt_params, tdc_flags);/* IFLA_CAN_{,XL}_TDC */
+
+	return size;
+}
+
 static size_t can_ctrlmode_ext_get_size(void)
 {
 	return nla_total_size(0) +		/* nest IFLA_CAN_CTRLMODE_EXT */
 		nla_total_size(sizeof(u32));	/* IFLA_CAN_CTRLMODE_SUPPORTED */
 }
 
+static size_t can_pwm_get_size(const struct can_pwm_const *pwm_const,
+			       bool pwm_on)
+{
+	size_t size;
+
+	if (!pwm_const || !pwm_on)
+		return 0;
+
+	size = nla_total_size(0);			/* nest IFLA_CAN_PWM */
+
+	size += nla_total_size(sizeof(u32));		/* IFLA_CAN_PWM_PWMS_MIN */
+	size += nla_total_size(sizeof(u32));		/* IFLA_CAN_PWM_PWMS_MAX */
+	size += nla_total_size(sizeof(u32));		/* IFLA_CAN_PWM_PWML_MIN */
+	size += nla_total_size(sizeof(u32));		/* IFLA_CAN_PWM_PWML_MAX */
+	size += nla_total_size(sizeof(u32));		/* IFLA_CAN_PWM_PWMO_MIN */
+	size += nla_total_size(sizeof(u32));		/* IFLA_CAN_PWM_PWMO_MAX */
+
+	size += nla_total_size(sizeof(u32));		/* IFLA_CAN_PWM_PWMS */
+	size += nla_total_size(sizeof(u32));		/* IFLA_CAN_PWM_PWML */
+	size += nla_total_size(sizeof(u32));		/* IFLA_CAN_PWM_PWMO */
+
+	return size;
+}
+
 static size_t can_get_size(const struct net_device *dev)
 {
 	struct can_priv *priv = netdev_priv(dev);
@@ -442,10 +811,6 @@ static size_t can_get_size(const struct net_device *dev)
 	size += nla_total_size(sizeof(u32));			/* IFLA_CAN_RESTART_MS */
 	if (priv->do_get_berr_counter)				/* IFLA_CAN_BERR_COUNTER */
 		size += nla_total_size(sizeof(struct can_berr_counter));
-	if (priv->data_bittiming.bitrate)			/* IFLA_CAN_DATA_BITTIMING */
-		size += nla_total_size(sizeof(struct can_bittiming));
-	if (priv->data_bittiming_const)				/* IFLA_CAN_DATA_BITTIMING_CONST */
-		size += nla_total_size(sizeof(struct can_bittiming_const));
 	if (priv->termination_const) {
 		size += nla_total_size(sizeof(priv->termination));		/* IFLA_CAN_TERMINATION */
 		size += nla_total_size(sizeof(*priv->termination_const) *	/* IFLA_CAN_TERMINATION_CONST */
@@ -454,31 +819,76 @@ static size_t can_get_size(const struct net_device *dev)
 	if (priv->bitrate_const)				/* IFLA_CAN_BITRATE_CONST */
 		size += nla_total_size(sizeof(*priv->bitrate_const) *
 				       priv->bitrate_const_cnt);
-	if (priv->data_bitrate_const)				/* IFLA_CAN_DATA_BITRATE_CONST */
-		size += nla_total_size(sizeof(*priv->data_bitrate_const) *
-				       priv->data_bitrate_const_cnt);
 	size += sizeof(priv->bitrate_max);			/* IFLA_CAN_BITRATE_MAX */
-	size += can_tdc_get_size(dev);				/* IFLA_CAN_TDC */
 	size += can_ctrlmode_ext_get_size();			/* IFLA_CAN_CTRLMODE_EXT */
 
+	size += can_data_bittiming_get_size(&priv->fd,
+					    priv->ctrlmode & CAN_CTRLMODE_FD_TDC_MASK);
+
+	size += can_data_bittiming_get_size(&priv->xl,
+					    priv->ctrlmode & CAN_CTRLMODE_XL_TDC_MASK);
+	size += can_pwm_get_size(priv->xl.pwm_const,		/* IFLA_CAN_XL_PWM */
+				 priv->ctrlmode & CAN_CTRLMODE_XL_TMS);
+
 	return size;
 }
 
-static int can_tdc_fill_info(struct sk_buff *skb, const struct net_device *dev)
+static int can_bittiming_fill_info(struct sk_buff *skb, int ifla_can_bittiming,
+				   struct can_bittiming *bittiming)
+{
+	return bittiming->bitrate != CAN_BITRATE_UNSET &&
+		bittiming->bitrate != CAN_BITRATE_UNKNOWN &&
+		nla_put(skb, ifla_can_bittiming, sizeof(*bittiming), bittiming);
+}
+
+static int can_bittiming_const_fill_info(struct sk_buff *skb,
+					 int ifla_can_bittiming_const,
+					 const struct can_bittiming_const *bittiming_const)
+{
+	return bittiming_const &&
+		nla_put(skb, ifla_can_bittiming_const,
+			sizeof(*bittiming_const), bittiming_const);
+}
+
+static int can_bitrate_const_fill_info(struct sk_buff *skb,
+				       int ifla_can_bitrate_const,
+				       const u32 *bitrate_const, unsigned int cnt)
+{
+	return bitrate_const &&
+		nla_put(skb, ifla_can_bitrate_const,
+			sizeof(*bitrate_const) * cnt, bitrate_const);
+}
+
+static int can_tdc_fill_info(struct sk_buff *skb, const struct net_device *dev,
+			     int ifla_can_tdc)
 {
-	struct nlattr *nest;
 	struct can_priv *priv = netdev_priv(dev);
-	struct can_tdc *tdc = &priv->tdc;
-	const struct can_tdc_const *tdc_const = priv->tdc_const;
+	struct data_bittiming_params *dbt_params;
+	const struct can_tdc_const *tdc_const;
+	struct can_tdc *tdc;
+	struct nlattr *nest;
+	bool tdc_is_enabled, tdc_manual;
+
+	if (ifla_can_tdc == IFLA_CAN_TDC) {
+		dbt_params = &priv->fd;
+		tdc_is_enabled = can_fd_tdc_is_enabled(priv);
+		tdc_manual = priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL;
+	} else {
+		dbt_params = &priv->xl;
+		tdc_is_enabled = can_xl_tdc_is_enabled(priv);
+		tdc_manual = priv->ctrlmode & CAN_CTRLMODE_XL_TDC_MANUAL;
+	}
+	tdc_const = dbt_params->tdc_const;
+	tdc = &dbt_params->tdc;
 
 	if (!tdc_const)
 		return 0;
 
-	nest = nla_nest_start(skb, IFLA_CAN_TDC);
+	nest = nla_nest_start(skb, ifla_can_tdc);
 	if (!nest)
 		return -EMSGSIZE;
 
-	if (priv->ctrlmode_supported & CAN_CTRLMODE_TDC_MANUAL &&
+	if (tdc_manual &&
 	    (nla_put_u32(skb, IFLA_CAN_TDC_TDCV_MIN, tdc_const->tdcv_min) ||
 	     nla_put_u32(skb, IFLA_CAN_TDC_TDCV_MAX, tdc_const->tdcv_max)))
 		goto err_cancel;
@@ -490,15 +900,15 @@ static int can_tdc_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	     nla_put_u32(skb, IFLA_CAN_TDC_TDCF_MAX, tdc_const->tdcf_max)))
 		goto err_cancel;
 
-	if (can_tdc_is_enabled(priv)) {
+	if (tdc_is_enabled) {
 		u32 tdcv;
 		int err = -EINVAL;
 
-		if (priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL) {
+		if (tdc_manual) {
 			tdcv = tdc->tdcv;
 			err = 0;
-		} else if (priv->do_get_auto_tdcv) {
-			err = priv->do_get_auto_tdcv(dev, &tdcv);
+		} else if (dbt_params->do_get_auto_tdcv) {
+			err = dbt_params->do_get_auto_tdcv(dev, &tdcv);
 		}
 		if (!err && nla_put_u32(skb, IFLA_CAN_TDC_TDCV, tdcv))
 			goto err_cancel;
@@ -517,6 +927,42 @@ err_cancel:
 	return -EMSGSIZE;
 }
 
+static int can_pwm_fill_info(struct sk_buff *skb, const struct can_priv *priv)
+{
+	const struct can_pwm_const *pwm_const = priv->xl.pwm_const;
+	const struct can_pwm *pwm = &priv->xl.pwm;
+	struct nlattr *nest;
+
+	if (!pwm_const)
+		return 0;
+
+	nest = nla_nest_start(skb, IFLA_CAN_XL_PWM);
+	if (!nest)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, IFLA_CAN_PWM_PWMS_MIN, pwm_const->pwms_min) ||
+	    nla_put_u32(skb, IFLA_CAN_PWM_PWMS_MAX, pwm_const->pwms_max) ||
+	    nla_put_u32(skb, IFLA_CAN_PWM_PWML_MIN, pwm_const->pwml_min) ||
+	    nla_put_u32(skb, IFLA_CAN_PWM_PWML_MAX, pwm_const->pwml_max) ||
+	    nla_put_u32(skb, IFLA_CAN_PWM_PWMO_MIN, pwm_const->pwmo_min) ||
+	    nla_put_u32(skb, IFLA_CAN_PWM_PWMO_MAX, pwm_const->pwmo_max))
+		goto err_cancel;
+
+	if (priv->ctrlmode & CAN_CTRLMODE_XL_TMS) {
+		if (nla_put_u32(skb, IFLA_CAN_PWM_PWMS, pwm->pwms) ||
+		    nla_put_u32(skb, IFLA_CAN_PWM_PWML, pwm->pwml) ||
+		    nla_put_u32(skb, IFLA_CAN_PWM_PWMO, pwm->pwmo))
+			goto err_cancel;
+	}
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+err_cancel:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
 static int can_ctrlmode_ext_fill_info(struct sk_buff *skb,
 				      const struct can_priv *priv)
 {
@@ -546,14 +992,11 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	if (priv->do_get_state)
 		priv->do_get_state(dev, &state);
 
-	if ((priv->bittiming.bitrate != CAN_BITRATE_UNSET &&
-	     priv->bittiming.bitrate != CAN_BITRATE_UNKNOWN &&
-	     nla_put(skb, IFLA_CAN_BITTIMING,
-		     sizeof(priv->bittiming), &priv->bittiming)) ||
+	if (can_bittiming_fill_info(skb, IFLA_CAN_BITTIMING,
+				    &priv->bittiming) ||
 
-	    (priv->bittiming_const &&
-	     nla_put(skb, IFLA_CAN_BITTIMING_CONST,
-		     sizeof(*priv->bittiming_const), priv->bittiming_const)) ||
+	    can_bittiming_const_fill_info(skb, IFLA_CAN_BITTIMING_CONST,
+					  priv->bittiming_const) ||
 
 	    nla_put(skb, IFLA_CAN_CLOCK, sizeof(priv->clock), &priv->clock) ||
 	    nla_put_u32(skb, IFLA_CAN_STATE, state) ||
@@ -564,14 +1007,11 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	     !priv->do_get_berr_counter(dev, &bec) &&
 	     nla_put(skb, IFLA_CAN_BERR_COUNTER, sizeof(bec), &bec)) ||
 
-	    (priv->data_bittiming.bitrate &&
-	     nla_put(skb, IFLA_CAN_DATA_BITTIMING,
-		     sizeof(priv->data_bittiming), &priv->data_bittiming)) ||
+	    can_bittiming_fill_info(skb, IFLA_CAN_DATA_BITTIMING,
+				    &priv->fd.data_bittiming) ||
 
-	    (priv->data_bittiming_const &&
-	     nla_put(skb, IFLA_CAN_DATA_BITTIMING_CONST,
-		     sizeof(*priv->data_bittiming_const),
-		     priv->data_bittiming_const)) ||
+	    can_bittiming_const_fill_info(skb, IFLA_CAN_DATA_BITTIMING_CONST,
+					  priv->fd.data_bittiming_const) ||
 
 	    (priv->termination_const &&
 	     (nla_put_u16(skb, IFLA_CAN_TERMINATION, priv->termination) ||
@@ -580,27 +1020,36 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		      priv->termination_const_cnt,
 		      priv->termination_const))) ||
 
-	    (priv->bitrate_const &&
-	     nla_put(skb, IFLA_CAN_BITRATE_CONST,
-		     sizeof(*priv->bitrate_const) *
-		     priv->bitrate_const_cnt,
-		     priv->bitrate_const)) ||
+	    can_bitrate_const_fill_info(skb, IFLA_CAN_BITRATE_CONST,
+					priv->bitrate_const,
+					priv->bitrate_const_cnt) ||
 
-	    (priv->data_bitrate_const &&
-	     nla_put(skb, IFLA_CAN_DATA_BITRATE_CONST,
-		     sizeof(*priv->data_bitrate_const) *
-		     priv->data_bitrate_const_cnt,
-		     priv->data_bitrate_const)) ||
+	    can_bitrate_const_fill_info(skb, IFLA_CAN_DATA_BITRATE_CONST,
+					priv->fd.data_bitrate_const,
+					priv->fd.data_bitrate_const_cnt) ||
 
 	    (nla_put(skb, IFLA_CAN_BITRATE_MAX,
 		     sizeof(priv->bitrate_max),
 		     &priv->bitrate_max)) ||
 
-	    can_tdc_fill_info(skb, dev) ||
+	    can_tdc_fill_info(skb, dev, IFLA_CAN_TDC) ||
 
-	    can_ctrlmode_ext_fill_info(skb, priv)
-	    )
+	    can_ctrlmode_ext_fill_info(skb, priv) ||
 
+	    can_bittiming_fill_info(skb, IFLA_CAN_XL_DATA_BITTIMING,
+				    &priv->xl.data_bittiming) ||
+
+	    can_bittiming_const_fill_info(skb, IFLA_CAN_XL_DATA_BITTIMING_CONST,
+					  priv->xl.data_bittiming_const) ||
+
+	    can_bitrate_const_fill_info(skb, IFLA_CAN_XL_DATA_BITRATE_CONST,
+					priv->xl.data_bitrate_const,
+					priv->xl.data_bitrate_const_cnt) ||
+
+	    can_tdc_fill_info(skb, dev, IFLA_CAN_XL_TDC) ||
+
+	    can_pwm_fill_info(skb, priv)
+	    )
 		return -EMSGSIZE;
 
 	return 0;
@@ -624,8 +1073,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int can_newlink(struct net *src_net, struct net_device *dev,
-		       struct nlattr *tb[], struct nlattr *data[],
+static int can_newlink(struct net_device *dev,
+		       struct rtnl_newlink_params *params,
 		       struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
diff --git a/drivers/net/can/dummy_can.c b/drivers/net/can/dummy_can.c
new file mode 100644
index 000000000000..41953655e3d3
--- /dev/null
+++ b/drivers/net/can/dummy_can.c
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Copyright (c) 2025 Vincent Mailhol <mailhol@kernel.org> */
+
+#include <linux/array_size.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/units.h>
+#include <linux/string_choices.h>
+
+#include <linux/can.h>
+#include <linux/can/bittiming.h>
+#include <linux/can/dev.h>
+#include <linux/can/skb.h>
+
+struct dummy_can {
+	struct can_priv can;
+	struct net_device *dev;
+};
+
+static struct dummy_can *dummy_can;
+
+static const struct can_bittiming_const dummy_can_bittiming_const = {
+	.name = "dummy_can CC",
+	.tseg1_min = 2,
+	.tseg1_max = 256,
+	.tseg2_min = 2,
+	.tseg2_max = 128,
+	.sjw_max = 128,
+	.brp_min = 1,
+	.brp_max = 512,
+	.brp_inc = 1
+};
+
+static const struct can_bittiming_const dummy_can_fd_databittiming_const = {
+	.name = "dummy_can FD",
+	.tseg1_min = 2,
+	.tseg1_max = 256,
+	.tseg2_min = 2,
+	.tseg2_max = 128,
+	.sjw_max = 128,
+	.brp_min = 1,
+	.brp_max = 512,
+	.brp_inc = 1
+};
+
+static const struct can_tdc_const dummy_can_fd_tdc_const = {
+	.tdcv_min = 0,
+	.tdcv_max = 0, /* Manual mode not supported. */
+	.tdco_min = 0,
+	.tdco_max = 127,
+	.tdcf_min = 0,
+	.tdcf_max = 127
+};
+
+static const struct can_bittiming_const dummy_can_xl_databittiming_const = {
+	.name = "dummy_can XL",
+	.tseg1_min = 2,
+	.tseg1_max = 256,
+	.tseg2_min = 2,
+	.tseg2_max = 128,
+	.sjw_max = 128,
+	.brp_min = 1,
+	.brp_max = 512,
+	.brp_inc = 1
+};
+
+static const struct can_tdc_const dummy_can_xl_tdc_const = {
+	.tdcv_min = 0,
+	.tdcv_max = 0, /* Manual mode not supported. */
+	.tdco_min = 0,
+	.tdco_max = 127,
+	.tdcf_min = 0,
+	.tdcf_max = 127
+};
+
+static const struct can_pwm_const dummy_can_pwm_const = {
+	.pwms_min = 1,
+	.pwms_max = 8,
+	.pwml_min = 2,
+	.pwml_max = 24,
+	.pwmo_min = 0,
+	.pwmo_max = 16,
+};
+
+static void dummy_can_print_bittiming(struct net_device *dev,
+				      struct can_bittiming *bt)
+{
+	netdev_dbg(dev, "\tbitrate: %u\n", bt->bitrate);
+	netdev_dbg(dev, "\tsample_point: %u\n", bt->sample_point);
+	netdev_dbg(dev, "\ttq: %u\n", bt->tq);
+	netdev_dbg(dev, "\tprop_seg: %u\n", bt->prop_seg);
+	netdev_dbg(dev, "\tphase_seg1: %u\n", bt->phase_seg1);
+	netdev_dbg(dev, "\tphase_seg2: %u\n", bt->phase_seg2);
+	netdev_dbg(dev, "\tsjw: %u\n", bt->sjw);
+	netdev_dbg(dev, "\tbrp: %u\n", bt->brp);
+}
+
+static void dummy_can_print_tdc(struct net_device *dev, struct can_tdc *tdc)
+{
+	netdev_dbg(dev, "\t\ttdcv: %u\n", tdc->tdcv);
+	netdev_dbg(dev, "\t\ttdco: %u\n", tdc->tdco);
+	netdev_dbg(dev, "\t\ttdcf: %u\n", tdc->tdcf);
+}
+
+static void dummy_can_print_pwm(struct net_device *dev, struct can_pwm *pwm,
+				struct can_bittiming *dbt)
+{
+	netdev_dbg(dev, "\t\tpwms: %u\n", pwm->pwms);
+	netdev_dbg(dev, "\t\tpwml: %u\n", pwm->pwml);
+	netdev_dbg(dev, "\t\tpwmo: %u\n", pwm->pwmo);
+}
+
+static void dummy_can_print_ctrlmode(struct net_device *dev)
+{
+	struct dummy_can *priv = netdev_priv(dev);
+	struct can_priv *can_priv = &priv->can;
+	unsigned long supported = can_priv->ctrlmode_supported;
+	u32 enabled = can_priv->ctrlmode;
+
+	netdev_dbg(dev, "Control modes:\n");
+	netdev_dbg(dev, "\tsupported: 0x%08x\n", (u32)supported);
+	netdev_dbg(dev, "\tenabled: 0x%08x\n", enabled);
+
+	if (supported) {
+		int idx;
+
+		netdev_dbg(dev, "\tlist:");
+		for_each_set_bit(idx, &supported, BITS_PER_TYPE(u32))
+			netdev_dbg(dev, "\t\t%s: %s\n",
+				   can_get_ctrlmode_str(BIT(idx)),
+				   enabled & BIT(idx) ? "on" : "off");
+	}
+}
+
+static void dummy_can_print_bittiming_info(struct net_device *dev)
+{
+	struct dummy_can *priv = netdev_priv(dev);
+	struct can_priv *can_priv = &priv->can;
+
+	netdev_dbg(dev, "Clock frequency: %u\n", can_priv->clock.freq);
+	netdev_dbg(dev, "Maximum bitrate: %u\n", can_priv->bitrate_max);
+	netdev_dbg(dev, "MTU: %u\n", dev->mtu);
+	netdev_dbg(dev, "\n");
+
+	dummy_can_print_ctrlmode(dev);
+	netdev_dbg(dev, "\n");
+
+	netdev_dbg(dev, "Classical CAN nominal bittiming:\n");
+	dummy_can_print_bittiming(dev, &can_priv->bittiming);
+	netdev_dbg(dev, "\n");
+
+	if (can_priv->ctrlmode & CAN_CTRLMODE_FD) {
+		netdev_dbg(dev, "CAN FD databittiming:\n");
+		dummy_can_print_bittiming(dev, &can_priv->fd.data_bittiming);
+		if (can_fd_tdc_is_enabled(can_priv)) {
+			netdev_dbg(dev, "\tCAN FD TDC:\n");
+			dummy_can_print_tdc(dev, &can_priv->fd.tdc);
+		}
+	}
+	netdev_dbg(dev, "\n");
+
+	if (can_priv->ctrlmode & CAN_CTRLMODE_XL) {
+		netdev_dbg(dev, "CAN XL databittiming:\n");
+		dummy_can_print_bittiming(dev, &can_priv->xl.data_bittiming);
+		if (can_xl_tdc_is_enabled(can_priv)) {
+			netdev_dbg(dev, "\tCAN XL TDC:\n");
+			dummy_can_print_tdc(dev, &can_priv->xl.tdc);
+		}
+		if (can_priv->ctrlmode & CAN_CTRLMODE_XL_TMS) {
+			netdev_dbg(dev, "\tCAN XL PWM:\n");
+			dummy_can_print_pwm(dev, &can_priv->xl.pwm,
+					    &can_priv->xl.data_bittiming);
+		}
+	}
+	netdev_dbg(dev, "\n");
+}
+
+static int dummy_can_netdev_open(struct net_device *dev)
+{
+	int ret;
+	struct can_priv *priv = netdev_priv(dev);
+
+	dummy_can_print_bittiming_info(dev);
+	netdev_dbg(dev, "error-signalling is %s\n",
+		   str_enabled_disabled(!can_dev_in_xl_only_mode(priv)));
+
+	ret = open_candev(dev);
+	if (ret)
+		return ret;
+	netif_start_queue(dev);
+	netdev_dbg(dev, "dummy-can is up\n");
+
+	return 0;
+}
+
+static int dummy_can_netdev_close(struct net_device *dev)
+{
+	netif_stop_queue(dev);
+	close_candev(dev);
+	netdev_dbg(dev, "dummy-can is down\n");
+
+	return 0;
+}
+
+static netdev_tx_t dummy_can_start_xmit(struct sk_buff *skb,
+					struct net_device *dev)
+{
+	if (can_dev_dropped_skb(dev, skb))
+		return NETDEV_TX_OK;
+
+	can_put_echo_skb(skb, dev, 0, 0);
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += can_get_echo_skb(dev, 0, NULL);
+
+	return NETDEV_TX_OK;
+}
+
+static const struct net_device_ops dummy_can_netdev_ops = {
+	.ndo_open = dummy_can_netdev_open,
+	.ndo_stop = dummy_can_netdev_close,
+	.ndo_start_xmit = dummy_can_start_xmit,
+};
+
+static const struct ethtool_ops dummy_can_ethtool_ops = {
+	.get_ts_info = ethtool_op_get_ts_info,
+};
+
+static int __init dummy_can_init(void)
+{
+	struct net_device *dev;
+	struct dummy_can *priv;
+	int ret;
+
+	dev = alloc_candev(sizeof(*priv), 1);
+	if (!dev)
+		return -ENOMEM;
+
+	dev->netdev_ops = &dummy_can_netdev_ops;
+	dev->ethtool_ops = &dummy_can_ethtool_ops;
+	priv = netdev_priv(dev);
+	priv->can.bittiming_const = &dummy_can_bittiming_const;
+	priv->can.bitrate_max = 20 * MEGA /* BPS */;
+	priv->can.clock.freq = 160 * MEGA /* Hz */;
+	priv->can.fd.data_bittiming_const = &dummy_can_fd_databittiming_const;
+	priv->can.fd.tdc_const = &dummy_can_fd_tdc_const;
+	priv->can.xl.data_bittiming_const = &dummy_can_xl_databittiming_const;
+	priv->can.xl.tdc_const = &dummy_can_xl_tdc_const;
+	priv->can.xl.pwm_const = &dummy_can_pwm_const;
+	priv->can.ctrlmode_supported = CAN_CTRLMODE_LISTENONLY |
+		CAN_CTRLMODE_FD | CAN_CTRLMODE_TDC_AUTO |
+		CAN_CTRLMODE_RESTRICTED | CAN_CTRLMODE_XL |
+		CAN_CTRLMODE_XL_TDC_AUTO | CAN_CTRLMODE_XL_TMS;
+	priv->dev = dev;
+
+	ret = register_candev(priv->dev);
+	if (ret) {
+		free_candev(priv->dev);
+		return ret;
+	}
+
+	dummy_can = priv;
+	netdev_dbg(dev, "dummy-can ready\n");
+
+	return 0;
+}
+
+static void __exit dummy_can_exit(void)
+{
+	struct net_device *dev = dummy_can->dev;
+
+	netdev_dbg(dev, "dummy-can bye bye\n");
+	unregister_candev(dev);
+	free_candev(dev);
+}
+
+module_init(dummy_can_init);
+module_exit(dummy_can_exit);
+
+MODULE_DESCRIPTION("A dummy CAN driver, mainly to test the netlink interface");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Vincent Mailhol <mailhol@kernel.org>");
diff --git a/drivers/net/can/esd/esd_402_pci-core.c b/drivers/net/can/esd/esd_402_pci-core.c
index 5d6d2828cd04..c826f00c551b 100644
--- a/drivers/net/can/esd/esd_402_pci-core.c
+++ b/drivers/net/can/esd/esd_402_pci-core.c
@@ -86,8 +86,8 @@ static const struct net_device_ops pci402_acc_netdev_ops = {
 	.ndo_open = acc_open,
 	.ndo_stop = acc_close,
 	.ndo_start_xmit = acc_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
-	.ndo_eth_ioctl = can_eth_ioctl_hwts,
+	.ndo_hwtstamp_get = can_hwtstamp_get,
+	.ndo_hwtstamp_set = can_hwtstamp_set,
 };
 
 static const struct ethtool_ops pci402_acc_ethtool_ops = {
diff --git a/drivers/net/can/esd/esdacc.c b/drivers/net/can/esd/esdacc.c
index c80032bc1a52..73e66f9a3781 100644
--- a/drivers/net/can/esd/esdacc.c
+++ b/drivers/net/can/esd/esdacc.c
@@ -254,7 +254,7 @@ netdev_tx_t acc_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	u32 acc_id;
 	u32 acc_dlc;
 
-	if (can_dropped_invalid_skb(netdev, skb))
+	if (can_dev_dropped_skb(netdev, skb))
 		return NETDEV_TX_OK;
 
 	/* Access core->tx_fifo_tail only once because it may be changed
diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index ac1a860986df..f5d22c61503f 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -26,6 +26,7 @@
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/can/platform/flexcan.h>
+#include <linux/phy/phy.h>
 #include <linux/pm_runtime.h>
 #include <linux/property.h>
 #include <linux/regmap.h>
@@ -386,6 +387,16 @@ static const struct flexcan_devtype_data fsl_lx2160a_r1_devtype_data = {
 		FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR,
 };
 
+static const struct flexcan_devtype_data nxp_s32g2_devtype_data = {
+	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
+		FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE |
+		FLEXCAN_QUIRK_USE_RX_MAILBOX | FLEXCAN_QUIRK_SUPPORT_FD |
+		FLEXCAN_QUIRK_SUPPORT_ECC | FLEXCAN_QUIRK_NR_IRQ_3 |
+		FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX |
+		FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR |
+		FLEXCAN_QUIRK_SECONDARY_MB_IRQ,
+};
+
 static const struct can_bittiming_const flexcan_bittiming_const = {
 	.name = DRV_NAME,
 	.tseg1_min = 4,
@@ -634,18 +645,22 @@ static void flexcan_clks_disable(const struct flexcan_priv *priv)
 
 static inline int flexcan_transceiver_enable(const struct flexcan_priv *priv)
 {
-	if (!priv->reg_xceiver)
-		return 0;
+	if (priv->reg_xceiver)
+		return regulator_enable(priv->reg_xceiver);
+	else if (priv->transceiver)
+		return phy_power_on(priv->transceiver);
 
-	return regulator_enable(priv->reg_xceiver);
+	return 0;
 }
 
 static inline int flexcan_transceiver_disable(const struct flexcan_priv *priv)
 {
-	if (!priv->reg_xceiver)
-		return 0;
+	if (priv->reg_xceiver)
+		return regulator_disable(priv->reg_xceiver);
+	else if (priv->transceiver)
+		return phy_power_off(priv->transceiver);
 
-	return regulator_disable(priv->reg_xceiver);
+	return 0;
 }
 
 static int flexcan_chip_enable(struct flexcan_priv *priv)
@@ -1211,7 +1226,7 @@ static void flexcan_set_bittiming_cbt(const struct net_device *dev)
 {
 	struct flexcan_priv *priv = netdev_priv(dev);
 	struct can_bittiming *bt = &priv->can.bittiming;
-	struct can_bittiming *dbt = &priv->can.data_bittiming;
+	struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	struct flexcan_regs __iomem *regs = priv->regs;
 	u32 reg_cbt, reg_fdctrl;
 
@@ -1762,14 +1777,25 @@ static int flexcan_open(struct net_device *dev)
 			goto out_free_irq_boff;
 	}
 
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SECONDARY_MB_IRQ) {
+		err = request_irq(priv->irq_secondary_mb,
+				  flexcan_irq, IRQF_SHARED, dev->name, dev);
+		if (err)
+			goto out_free_irq_err;
+	}
+
 	flexcan_chip_interrupts_enable(dev);
 
 	netif_start_queue(dev);
 
 	return 0;
 
+ out_free_irq_err:
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3)
+		free_irq(priv->irq_err, dev);
  out_free_irq_boff:
-	free_irq(priv->irq_boff, dev);
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3)
+		free_irq(priv->irq_boff, dev);
  out_free_irq:
 	free_irq(dev->irq, dev);
  out_can_rx_offload_disable:
@@ -1794,6 +1820,9 @@ static int flexcan_close(struct net_device *dev)
 	netif_stop_queue(dev);
 	flexcan_chip_interrupts_disable(dev);
 
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SECONDARY_MB_IRQ)
+		free_irq(priv->irq_secondary_mb, dev);
+
 	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3) {
 		free_irq(priv->irq_err, dev);
 		free_irq(priv->irq_boff, dev);
@@ -1838,7 +1867,6 @@ static const struct net_device_ops flexcan_netdev_ops = {
 	.ndo_open	= flexcan_open,
 	.ndo_stop	= flexcan_close,
 	.ndo_start_xmit	= flexcan_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static int register_flexcandev(struct net_device *dev)
@@ -2041,6 +2069,7 @@ static const struct of_device_id flexcan_of_match[] = {
 	{ .compatible = "fsl,vf610-flexcan", .data = &fsl_vf610_devtype_data, },
 	{ .compatible = "fsl,ls1021ar2-flexcan", .data = &fsl_ls1021a_r2_devtype_data, },
 	{ .compatible = "fsl,lx2160ar1-flexcan", .data = &fsl_lx2160a_r1_devtype_data, },
+	{ .compatible = "nxp,s32g2-flexcan", .data = &nxp_s32g2_devtype_data, },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, flexcan_of_match);
@@ -2061,6 +2090,7 @@ static int flexcan_probe(struct platform_device *pdev)
 	struct net_device *dev;
 	struct flexcan_priv *priv;
 	struct regulator *reg_xceiver;
+	struct phy *transceiver;
 	struct clk *clk_ipg = NULL, *clk_per = NULL;
 	struct flexcan_regs __iomem *regs;
 	struct flexcan_platform_data *pdata;
@@ -2076,6 +2106,11 @@ static int flexcan_probe(struct platform_device *pdev)
 	else if (IS_ERR(reg_xceiver))
 		return PTR_ERR(reg_xceiver);
 
+	transceiver = devm_phy_optional_get(&pdev->dev, NULL);
+	if (IS_ERR(transceiver))
+		return dev_err_probe(&pdev->dev, PTR_ERR(transceiver),
+				     "failed to get phy\n");
+
 	if (pdev->dev.of_node) {
 		of_property_read_u32(pdev->dev.of_node,
 				     "clock-frequency", &clock_freq);
@@ -2173,6 +2208,10 @@ static int flexcan_probe(struct platform_device *pdev)
 	priv->clk_per = clk_per;
 	priv->clk_src = clk_src;
 	priv->reg_xceiver = reg_xceiver;
+	priv->transceiver = transceiver;
+
+	if (transceiver)
+		priv->can.bitrate_max = transceiver->attrs.max_link_rate;
 
 	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3) {
 		priv->irq_boff = platform_get_irq(pdev, 1);
@@ -2187,11 +2226,19 @@ static int flexcan_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SECONDARY_MB_IRQ) {
+		priv->irq_secondary_mb = platform_get_irq_byname(pdev, "mb-1");
+		if (priv->irq_secondary_mb < 0) {
+			err = priv->irq_secondary_mb;
+			goto failed_platform_get_irq;
+		}
+	}
+
 	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SUPPORT_FD) {
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD |
 			CAN_CTRLMODE_FD_NON_ISO;
 		priv->can.bittiming_const = &flexcan_fd_bittiming_const;
-		priv->can.data_bittiming_const =
+		priv->can.fd.data_bittiming_const =
 			&flexcan_fd_data_bittiming_const;
 	} else {
 		priv->can.bittiming_const = &flexcan_bittiming_const;
@@ -2260,14 +2307,19 @@ static int __maybe_unused flexcan_suspend(struct device *device)
 
 			flexcan_chip_interrupts_disable(dev);
 
+			err = flexcan_transceiver_disable(priv);
+			if (err)
+				return err;
+
 			err = pinctrl_pm_select_sleep_state(device);
 			if (err)
 				return err;
 		}
 		netif_stop_queue(dev);
 		netif_device_detach(dev);
+
+		priv->can.state = CAN_STATE_SLEEPING;
 	}
-	priv->can.state = CAN_STATE_SLEEPING;
 
 	return 0;
 }
@@ -2278,7 +2330,6 @@ static int __maybe_unused flexcan_resume(struct device *device)
 	struct flexcan_priv *priv = netdev_priv(dev);
 	int err;
 
-	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 	if (netif_running(dev)) {
 		netif_device_attach(dev);
 		netif_start_queue(dev);
@@ -2292,12 +2343,20 @@ static int __maybe_unused flexcan_resume(struct device *device)
 			if (err)
 				return err;
 
-			err = flexcan_chip_start(dev);
+			err = flexcan_transceiver_enable(priv);
 			if (err)
 				return err;
 
+			err = flexcan_chip_start(dev);
+			if (err) {
+				flexcan_transceiver_disable(priv);
+				return err;
+			}
+
 			flexcan_chip_interrupts_enable(dev);
 		}
+
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
 	}
 
 	return 0;
diff --git a/drivers/net/can/flexcan/flexcan.h b/drivers/net/can/flexcan/flexcan.h
index 4933d8c7439e..16692a2502eb 100644
--- a/drivers/net/can/flexcan/flexcan.h
+++ b/drivers/net/can/flexcan/flexcan.h
@@ -70,6 +70,10 @@
 #define FLEXCAN_QUIRK_SUPPORT_RX_FIFO BIT(16)
 /* Setup stop mode with ATF SCMI protocol to support wakeup */
 #define FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI BIT(17)
+/* Device has two separate interrupt lines for two mailbox ranges, which
+ * both need to have an interrupt handler registered.
+ */
+#define FLEXCAN_QUIRK_SECONDARY_MB_IRQ	BIT(18)
 
 struct flexcan_devtype_data {
 	u32 quirks;		/* quirks needed for different IP cores */
@@ -103,10 +107,12 @@ struct flexcan_priv {
 	struct clk *clk_per;
 	struct flexcan_devtype_data devtype_data;
 	struct regulator *reg_xceiver;
+	struct phy *transceiver;
 	struct flexcan_stop_mode stm;
 
 	int irq_boff;
 	int irq_err;
+	int irq_secondary_mb;
 
 	/* IPC handle when setup stop mode by System Controller firmware(scfw) */
 	struct imx_sc_ipc *sc_ipc_handle;
diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c
index cdf0ec9fa7f3..3b1b09943436 100644
--- a/drivers/net/can/grcan.c
+++ b/drivers/net/can/grcan.c
@@ -778,7 +778,7 @@ static irqreturn_t grcan_interrupt(int irq, void *dev_id)
 	 */
 	if (priv->need_txbug_workaround &&
 	    (sources & (GRCAN_IRQ_TX | GRCAN_IRQ_TXLOSS))) {
-		del_timer(&priv->hang_timer);
+		timer_delete(&priv->hang_timer);
 	}
 
 	/* Frame(s) received or transmitted */
@@ -806,7 +806,7 @@ static irqreturn_t grcan_interrupt(int irq, void *dev_id)
  */
 static void grcan_running_reset(struct timer_list *t)
 {
-	struct grcan_priv *priv = from_timer(priv, t, rr_timer);
+	struct grcan_priv *priv = timer_container_of(priv, t, rr_timer);
 	struct net_device *dev = priv->dev;
 	struct grcan_registers __iomem *regs = priv->regs;
 	unsigned long flags;
@@ -817,8 +817,8 @@ static void grcan_running_reset(struct timer_list *t)
 	spin_lock_irqsave(&priv->lock, flags);
 
 	priv->resetting = false;
-	del_timer(&priv->hang_timer);
-	del_timer(&priv->rr_timer);
+	timer_delete(&priv->hang_timer);
+	timer_delete(&priv->rr_timer);
 
 	if (!priv->closing) {
 		/* Save and reset - config register preserved by grcan_reset */
@@ -897,7 +897,7 @@ static inline void grcan_reset_timer(struct timer_list *timer, __u32 bitrate)
 /* Disable channels and schedule a running reset */
 static void grcan_initiate_running_reset(struct timer_list *t)
 {
-	struct grcan_priv *priv = from_timer(priv, t, hang_timer);
+	struct grcan_priv *priv = timer_container_of(priv, t, hang_timer);
 	struct net_device *dev = priv->dev;
 	struct grcan_registers __iomem *regs = priv->regs;
 	unsigned long flags;
@@ -1073,9 +1073,10 @@ static int grcan_open(struct net_device *dev)
 	if (err)
 		goto exit_close_candev;
 
+	napi_enable(&priv->napi);
+
 	spin_lock_irqsave(&priv->lock, flags);
 
-	napi_enable(&priv->napi);
 	grcan_start(dev);
 	if (!(priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY))
 		netif_start_queue(dev);
@@ -1107,8 +1108,8 @@ static int grcan_close(struct net_device *dev)
 	priv->closing = true;
 	if (priv->need_txbug_workaround) {
 		spin_unlock_irqrestore(&priv->lock, flags);
-		del_timer_sync(&priv->hang_timer);
-		del_timer_sync(&priv->rr_timer);
+		timer_delete_sync(&priv->hang_timer);
+		timer_delete_sync(&priv->rr_timer);
 		spin_lock_irqsave(&priv->lock, flags);
 	}
 	netif_stop_queue(dev);
@@ -1146,7 +1147,7 @@ static void grcan_transmit_catch_up(struct net_device *dev)
 		 * so prevent a running reset while catching up
 		 */
 		if (priv->need_txbug_workaround)
-			del_timer(&priv->hang_timer);
+			timer_delete(&priv->hang_timer);
 	}
 
 	spin_unlock_irqrestore(&priv->lock, flags);
@@ -1560,7 +1561,6 @@ static const struct net_device_ops grcan_netdev_ops = {
 	.ndo_open	= grcan_open,
 	.ndo_stop	= grcan_close,
 	.ndo_start_xmit	= grcan_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops grcan_ethtool_ops = {
diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c
index c86b57d47085..0f83335e4d07 100644
--- a/drivers/net/can/ifi_canfd/ifi_canfd.c
+++ b/drivers/net/can/ifi_canfd/ifi_canfd.c
@@ -669,7 +669,7 @@ static void ifi_canfd_set_bittiming(struct net_device *ndev)
 {
 	struct ifi_canfd_priv *priv = netdev_priv(ndev);
 	const struct can_bittiming *bt = &priv->can.bittiming;
-	const struct can_bittiming *dbt = &priv->can.data_bittiming;
+	const struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	u16 brp, sjw, tseg1, tseg2, tdc;
 
 	/* Configure bit timing */
@@ -944,7 +944,6 @@ static const struct net_device_ops ifi_canfd_netdev_ops = {
 	.ndo_open	= ifi_canfd_open,
 	.ndo_stop	= ifi_canfd_close,
 	.ndo_start_xmit	= ifi_canfd_start_xmit,
-	.ndo_change_mtu	= can_change_mtu,
 };
 
 static const struct ethtool_ops ifi_canfd_ethtool_ops = {
@@ -1000,10 +999,10 @@ static int ifi_canfd_plat_probe(struct platform_device *pdev)
 
 	priv->can.clock.freq = readl(addr + IFI_CANFD_CANCLOCK);
 
-	priv->can.bittiming_const	= &ifi_canfd_bittiming_const;
-	priv->can.data_bittiming_const	= &ifi_canfd_bittiming_const;
-	priv->can.do_set_mode		= ifi_canfd_set_mode;
-	priv->can.do_get_berr_counter	= ifi_canfd_get_berr_counter;
+	priv->can.bittiming_const = &ifi_canfd_bittiming_const;
+	priv->can.fd.data_bittiming_const = &ifi_canfd_bittiming_const;
+	priv->can.do_set_mode = ifi_canfd_set_mode;
+	priv->can.do_get_berr_counter = ifi_canfd_get_berr_counter;
 
 	/* IFI CANFD can do both Bosch FD and ISO FD */
 	priv->can.ctrlmode = CAN_CTRLMODE_FD;
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index 60c7b83b4539..1efdd1fd8caa 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -1752,7 +1752,6 @@ static const struct net_device_ops ican3_netdev_ops = {
 	.ndo_open	= ican3_open,
 	.ndo_stop	= ican3_stop,
 	.ndo_start_xmit	= ican3_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops ican3_ethtool_ops = {
@@ -1867,7 +1866,7 @@ static ssize_t fwinfo_show(struct device *dev,
 {
 	struct ican3_dev *mod = netdev_priv(to_net_dev(dev));
 
-	return scnprintf(buf, PAGE_SIZE, "%s\n", mod->fwinfo);
+	return sysfs_emit(buf, "%s\n", mod->fwinfo);
 }
 
 static DEVICE_ATTR_RW(termination);
diff --git a/drivers/net/can/kvaser_pciefd/Makefile b/drivers/net/can/kvaser_pciefd/Makefile
new file mode 100644
index 000000000000..8c5b8cdc6b5f
--- /dev/null
+++ b/drivers/net/can/kvaser_pciefd/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_CAN_KVASER_PCIEFD) += kvaser_pciefd.o
+kvaser_pciefd-y = kvaser_pciefd_core.o kvaser_pciefd_devlink.o
diff --git a/drivers/net/can/kvaser_pciefd/kvaser_pciefd.h b/drivers/net/can/kvaser_pciefd/kvaser_pciefd.h
new file mode 100644
index 000000000000..08c9ddc1ee85
--- /dev/null
+++ b/drivers/net/can/kvaser_pciefd/kvaser_pciefd.h
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */
+/* kvaser_pciefd common definitions and declarations
+ *
+ * Copyright (C) 2025 KVASER AB, Sweden. All rights reserved.
+ */
+
+#ifndef _KVASER_PCIEFD_H
+#define _KVASER_PCIEFD_H
+
+#include <linux/can/dev.h>
+#include <linux/completion.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include <linux/timer.h>
+#include <linux/types.h>
+#include <net/devlink.h>
+
+#define KVASER_PCIEFD_MAX_CAN_CHANNELS 8UL
+#define KVASER_PCIEFD_DMA_COUNT 2U
+#define KVASER_PCIEFD_DMA_SIZE (4U * 1024U)
+#define KVASER_PCIEFD_CAN_TX_MAX_COUNT 17U
+
+struct kvaser_pciefd;
+
+struct kvaser_pciefd_address_offset {
+	u32 serdes;
+	u32 pci_ien;
+	u32 pci_irq;
+	u32 sysid;
+	u32 loopback;
+	u32 kcan_srb_fifo;
+	u32 kcan_srb;
+	u32 kcan_ch0;
+	u32 kcan_ch1;
+};
+
+struct kvaser_pciefd_irq_mask {
+	u32 kcan_rx0;
+	u32 kcan_tx[KVASER_PCIEFD_MAX_CAN_CHANNELS];
+	u32 all;
+};
+
+struct kvaser_pciefd_dev_ops {
+	void (*kvaser_pciefd_write_dma_map)(struct kvaser_pciefd *pcie,
+					    dma_addr_t addr, int index);
+};
+
+struct kvaser_pciefd_driver_data {
+	const struct kvaser_pciefd_address_offset *address_offset;
+	const struct kvaser_pciefd_irq_mask *irq_mask;
+	const struct kvaser_pciefd_dev_ops *ops;
+};
+
+struct kvaser_pciefd_fw_version {
+	u8 major;
+	u8 minor;
+	u16 build;
+};
+
+struct kvaser_pciefd_can {
+	struct can_priv can;
+	struct devlink_port devlink_port;
+	struct kvaser_pciefd *kv_pcie;
+	void __iomem *reg_base;
+	struct can_berr_counter bec;
+	u32 ioc;
+	u8 cmd_seq;
+	u8 tx_max_count;
+	u8 tx_idx;
+	u8 ack_idx;
+	int err_rep_cnt;
+	unsigned int completed_tx_pkts;
+	unsigned int completed_tx_bytes;
+	spinlock_t lock; /* Locks sensitive registers (e.g. MODE) */
+	struct timer_list bec_poll_timer;
+	struct completion start_comp, flush_comp;
+};
+
+struct kvaser_pciefd {
+	struct pci_dev *pci;
+	void __iomem *reg_base;
+	struct kvaser_pciefd_can *can[KVASER_PCIEFD_MAX_CAN_CHANNELS];
+	const struct kvaser_pciefd_driver_data *driver_data;
+	void *dma_data[KVASER_PCIEFD_DMA_COUNT];
+	u8 nr_channels;
+	u32 bus_freq;
+	u32 freq;
+	u32 freq_to_ticks_div;
+	struct kvaser_pciefd_fw_version fw_version;
+};
+
+extern const struct devlink_ops kvaser_pciefd_devlink_ops;
+
+int kvaser_pciefd_devlink_port_register(struct kvaser_pciefd_can *can);
+void kvaser_pciefd_devlink_port_unregister(struct kvaser_pciefd_can *can);
+#endif /* _KVASER_PCIEFD_H */
diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd/kvaser_pciefd_core.c
index fee012b57f33..d8c9bfb20230 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd/kvaser_pciefd_core.c
@@ -5,6 +5,8 @@
  *  - PEAK linux canfd driver
  */
 
+#include "kvaser_pciefd.h"
+
 #include <linux/bitfield.h>
 #include <linux/can/dev.h>
 #include <linux/device.h>
@@ -16,6 +18,7 @@
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include <linux/timer.h>
+#include <net/netdev_queues.h>
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Kvaser AB <support@kvaser.com>");
@@ -26,10 +29,6 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices");
 #define KVASER_PCIEFD_WAIT_TIMEOUT msecs_to_jiffies(1000)
 #define KVASER_PCIEFD_BEC_POLL_FREQ (jiffies + msecs_to_jiffies(200))
 #define KVASER_PCIEFD_MAX_ERR_REP 256U
-#define KVASER_PCIEFD_CAN_TX_MAX_COUNT 17U
-#define KVASER_PCIEFD_MAX_CAN_CHANNELS 8UL
-#define KVASER_PCIEFD_DMA_COUNT 2U
-#define KVASER_PCIEFD_DMA_SIZE (4U * 1024U)
 
 #define KVASER_PCIEFD_VENDOR 0x1a07
 
@@ -65,6 +64,7 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices");
 #define KVASER_PCIEFD_KCAN_FIFO_LAST_REG 0x180
 #define KVASER_PCIEFD_KCAN_CTRL_REG 0x2c0
 #define KVASER_PCIEFD_KCAN_CMD_REG 0x400
+#define KVASER_PCIEFD_KCAN_IOC_REG 0x404
 #define KVASER_PCIEFD_KCAN_IEN_REG 0x408
 #define KVASER_PCIEFD_KCAN_IRQ_REG 0x410
 #define KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG 0x414
@@ -135,6 +135,9 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices");
 /* Request status packet */
 #define KVASER_PCIEFD_KCAN_CMD_SRQ BIT(0)
 
+/* Control CAN LED, active low */
+#define KVASER_PCIEFD_KCAN_IOC_LED BIT(0)
+
 /* Transmitter unaligned */
 #define KVASER_PCIEFD_KCAN_IRQ_TAL BIT(17)
 /* Tx FIFO empty */
@@ -291,35 +294,6 @@ static void kvaser_pciefd_write_dma_map_sf2(struct kvaser_pciefd *pcie,
 static void kvaser_pciefd_write_dma_map_xilinx(struct kvaser_pciefd *pcie,
 					       dma_addr_t addr, int index);
 
-struct kvaser_pciefd_address_offset {
-	u32 serdes;
-	u32 pci_ien;
-	u32 pci_irq;
-	u32 sysid;
-	u32 loopback;
-	u32 kcan_srb_fifo;
-	u32 kcan_srb;
-	u32 kcan_ch0;
-	u32 kcan_ch1;
-};
-
-struct kvaser_pciefd_dev_ops {
-	void (*kvaser_pciefd_write_dma_map)(struct kvaser_pciefd *pcie,
-					    dma_addr_t addr, int index);
-};
-
-struct kvaser_pciefd_irq_mask {
-	u32 kcan_rx0;
-	u32 kcan_tx[KVASER_PCIEFD_MAX_CAN_CHANNELS];
-	u32 all;
-};
-
-struct kvaser_pciefd_driver_data {
-	const struct kvaser_pciefd_address_offset *address_offset;
-	const struct kvaser_pciefd_irq_mask *irq_mask;
-	const struct kvaser_pciefd_dev_ops *ops;
-};
-
 static const struct kvaser_pciefd_address_offset kvaser_pciefd_altera_address_offset = {
 	.serdes = 0x1000,
 	.pci_ien = 0x50,
@@ -404,32 +378,6 @@ static const struct kvaser_pciefd_driver_data kvaser_pciefd_xilinx_driver_data =
 	.ops = &kvaser_pciefd_xilinx_dev_ops,
 };
 
-struct kvaser_pciefd_can {
-	struct can_priv can;
-	struct kvaser_pciefd *kv_pcie;
-	void __iomem *reg_base;
-	struct can_berr_counter bec;
-	u8 cmd_seq;
-	int err_rep_cnt;
-	int echo_idx;
-	spinlock_t lock; /* Locks sensitive registers (e.g. MODE) */
-	spinlock_t echo_lock; /* Locks the message echo buffer */
-	struct timer_list bec_poll_timer;
-	struct completion start_comp, flush_comp;
-};
-
-struct kvaser_pciefd {
-	struct pci_dev *pci;
-	void __iomem *reg_base;
-	struct kvaser_pciefd_can *can[KVASER_PCIEFD_MAX_CAN_CHANNELS];
-	const struct kvaser_pciefd_driver_data *driver_data;
-	void *dma_data[KVASER_PCIEFD_DMA_COUNT];
-	u8 nr_channels;
-	u32 bus_freq;
-	u32 freq;
-	u32 freq_to_ticks_div;
-};
-
 struct kvaser_pciefd_rx_packet {
 	u32 header[2];
 	u64 timestamp;
@@ -524,6 +472,16 @@ static inline void kvaser_pciefd_abort_flush_reset(struct kvaser_pciefd_can *can
 	kvaser_pciefd_send_kcan_cmd(can, KVASER_PCIEFD_KCAN_CMD_AT);
 }
 
+static inline void kvaser_pciefd_set_led(struct kvaser_pciefd_can *can, bool on)
+{
+	if (on)
+		can->ioc &= ~KVASER_PCIEFD_KCAN_IOC_LED;
+	else
+		can->ioc |= KVASER_PCIEFD_KCAN_IOC_LED;
+
+	iowrite32(can->ioc, can->reg_base + KVASER_PCIEFD_KCAN_IOC_REG);
+}
+
 static void kvaser_pciefd_enable_err_gen(struct kvaser_pciefd_can *can)
 {
 	u32 mode;
@@ -631,7 +589,7 @@ static int kvaser_pciefd_bus_on(struct kvaser_pciefd_can *can)
 	u32 mode;
 	unsigned long irq;
 
-	del_timer(&can->bec_poll_timer);
+	timer_delete(&can->bec_poll_timer);
 	if (!completion_done(&can->flush_comp))
 		kvaser_pciefd_start_controller_flush(can);
 
@@ -714,6 +672,9 @@ static int kvaser_pciefd_open(struct net_device *netdev)
 	int ret;
 	struct kvaser_pciefd_can *can = netdev_priv(netdev);
 
+	can->tx_idx = 0;
+	can->ack_idx = 0;
+
 	ret = open_candev(netdev);
 	if (ret)
 		return ret;
@@ -742,24 +703,29 @@ static int kvaser_pciefd_stop(struct net_device *netdev)
 		ret = -ETIMEDOUT;
 	} else {
 		iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG);
-		del_timer(&can->bec_poll_timer);
+		timer_delete(&can->bec_poll_timer);
 	}
 	can->can.state = CAN_STATE_STOPPED;
+	netdev_reset_queue(netdev);
 	close_candev(netdev);
 
 	return ret;
 }
 
+static unsigned int kvaser_pciefd_tx_avail(const struct kvaser_pciefd_can *can)
+{
+	return can->tx_max_count - (READ_ONCE(can->tx_idx) - READ_ONCE(can->ack_idx));
+}
+
 static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p,
-					   struct kvaser_pciefd_can *can,
+					   struct can_priv *can, u8 seq,
 					   struct sk_buff *skb)
 {
 	struct canfd_frame *cf = (struct canfd_frame *)skb->data;
 	int packet_size;
-	int seq = can->echo_idx;
 
 	memset(p, 0, sizeof(*p));
-	if (can->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT)
+	if (can->ctrlmode & CAN_CTRLMODE_ONE_SHOT)
 		p->header[1] |= KVASER_PCIEFD_TPACKET_SMS;
 
 	if (cf->can_id & CAN_RTR_FLAG)
@@ -782,7 +748,7 @@ static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p,
 	} else {
 		p->header[1] |=
 			FIELD_PREP(KVASER_PCIEFD_RPACKET_DLC_MASK,
-				   can_get_cc_dlc((struct can_frame *)cf, can->can.ctrlmode));
+				   can_get_cc_dlc((struct can_frame *)cf, can->ctrlmode));
 	}
 
 	p->header[1] |= FIELD_PREP(KVASER_PCIEFD_PACKET_SEQ_MASK, seq);
@@ -797,22 +763,24 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb,
 					    struct net_device *netdev)
 {
 	struct kvaser_pciefd_can *can = netdev_priv(netdev);
-	unsigned long irq_flags;
 	struct kvaser_pciefd_tx_packet packet;
+	unsigned int seq = can->tx_idx & (can->can.echo_skb_max - 1);
+	unsigned int frame_len;
 	int nr_words;
-	u8 count;
 
 	if (can_dev_dropped_skb(netdev, skb))
 		return NETDEV_TX_OK;
+	if (!netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1))
+		return NETDEV_TX_BUSY;
 
-	nr_words = kvaser_pciefd_prepare_tx_packet(&packet, can, skb);
+	nr_words = kvaser_pciefd_prepare_tx_packet(&packet, &can->can, seq, skb);
 
-	spin_lock_irqsave(&can->echo_lock, irq_flags);
 	/* Prepare and save echo skb in internal slot */
-	can_put_echo_skb(skb, netdev, can->echo_idx, 0);
-
-	/* Move echo index to the next slot */
-	can->echo_idx = (can->echo_idx + 1) % can->can.echo_skb_max;
+	WRITE_ONCE(can->can.echo_skb[seq], NULL);
+	frame_len = can_skb_get_frame_len(skb);
+	can_put_echo_skb(skb, netdev, seq, frame_len);
+	netdev_sent_queue(netdev, frame_len);
+	WRITE_ONCE(can->tx_idx, can->tx_idx + 1);
 
 	/* Write header to fifo */
 	iowrite32(packet.header[0],
@@ -836,14 +804,7 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb,
 			     KVASER_PCIEFD_KCAN_FIFO_LAST_REG);
 	}
 
-	count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK,
-			  ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
-	/* No room for a new message, stop the queue until at least one
-	 * successful transmit
-	 */
-	if (count >= can->can.echo_skb_max || can->can.echo_skb[can->echo_idx])
-		netif_stop_queue(netdev);
-	spin_unlock_irqrestore(&can->echo_lock, irq_flags);
+	netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1);
 
 	return NETDEV_TX_OK;
 }
@@ -856,7 +817,7 @@ static int kvaser_pciefd_set_bittiming(struct kvaser_pciefd_can *can, bool data)
 	struct can_bittiming *bt;
 
 	if (data)
-		bt = &can->can.data_bittiming;
+		bt = &can->can.fd.data_bittiming;
 	else
 		bt = &can->can.bittiming;
 
@@ -930,7 +891,8 @@ static int kvaser_pciefd_get_berr_counter(const struct net_device *ndev,
 
 static void kvaser_pciefd_bec_poll_timer(struct timer_list *data)
 {
-	struct kvaser_pciefd_can *can = from_timer(can, data, bec_poll_timer);
+	struct kvaser_pciefd_can *can = timer_container_of(can, data,
+							   bec_poll_timer);
 
 	kvaser_pciefd_enable_err_gen(can);
 	kvaser_pciefd_request_status(can);
@@ -940,13 +902,37 @@ static void kvaser_pciefd_bec_poll_timer(struct timer_list *data)
 static const struct net_device_ops kvaser_pciefd_netdev_ops = {
 	.ndo_open = kvaser_pciefd_open,
 	.ndo_stop = kvaser_pciefd_stop,
-	.ndo_eth_ioctl = can_eth_ioctl_hwts,
 	.ndo_start_xmit = kvaser_pciefd_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
+	.ndo_hwtstamp_get = can_hwtstamp_get,
+	.ndo_hwtstamp_set = can_hwtstamp_set,
 };
 
+static int kvaser_pciefd_set_phys_id(struct net_device *netdev,
+				     enum ethtool_phys_id_state state)
+{
+	struct kvaser_pciefd_can *can = netdev_priv(netdev);
+
+	switch (state) {
+	case ETHTOOL_ID_ACTIVE:
+		return 3; /* 3 On/Off cycles per second */
+
+	case ETHTOOL_ID_ON:
+		kvaser_pciefd_set_led(can, true);
+		return 0;
+
+	case ETHTOOL_ID_OFF:
+	case ETHTOOL_ID_INACTIVE:
+		kvaser_pciefd_set_led(can, false);
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct ethtool_ops kvaser_pciefd_ethtool_ops = {
 	.get_ts_info = can_ethtool_op_get_ts_info_hwts,
+	.set_phys_id = kvaser_pciefd_set_phys_id,
 };
 
 static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
@@ -957,9 +943,10 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		struct net_device *netdev;
 		struct kvaser_pciefd_can *can;
 		u32 status, tx_nr_packets_max;
+		int ret;
 
 		netdev = alloc_candev(sizeof(struct kvaser_pciefd_can),
-				      KVASER_PCIEFD_CAN_TX_MAX_COUNT);
+				      roundup_pow_of_two(KVASER_PCIEFD_CAN_TX_MAX_COUNT));
 		if (!netdev)
 			return -ENOMEM;
 
@@ -970,8 +957,11 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		can->kv_pcie = pcie;
 		can->cmd_seq = 0;
 		can->err_rep_cnt = 0;
+		can->completed_tx_pkts = 0;
+		can->completed_tx_bytes = 0;
 		can->bec.txerr = 0;
 		can->bec.rxerr = 0;
+		can->can.dev->dev_port = i;
 
 		init_completion(&can->start_comp);
 		init_completion(&can->flush_comp);
@@ -980,26 +970,28 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		/* Disable Bus load reporting */
 		iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_BUS_LOAD_REG);
 
+		can->ioc = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_IOC_REG);
+		kvaser_pciefd_set_led(can, false);
+
 		tx_nr_packets_max =
 			FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_MAX_MASK,
 				  ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
+		can->tx_max_count = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1);
 
 		can->can.clock.freq = pcie->freq;
-		can->can.echo_skb_max = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1);
-		can->echo_idx = 0;
-		spin_lock_init(&can->echo_lock);
 		spin_lock_init(&can->lock);
 
 		can->can.bittiming_const = &kvaser_pciefd_bittiming_const;
-		can->can.data_bittiming_const = &kvaser_pciefd_bittiming_const;
+		can->can.fd.data_bittiming_const = &kvaser_pciefd_bittiming_const;
 		can->can.do_set_bittiming = kvaser_pciefd_set_nominal_bittiming;
-		can->can.do_set_data_bittiming = kvaser_pciefd_set_data_bittiming;
+		can->can.fd.do_set_data_bittiming = kvaser_pciefd_set_data_bittiming;
 		can->can.do_set_mode = kvaser_pciefd_set_mode;
 		can->can.do_get_berr_counter = kvaser_pciefd_get_berr_counter;
 		can->can.ctrlmode_supported = CAN_CTRLMODE_LISTENONLY |
 					      CAN_CTRLMODE_FD |
 					      CAN_CTRLMODE_FD_NON_ISO |
-					      CAN_CTRLMODE_CC_LEN8_DLC;
+					      CAN_CTRLMODE_CC_LEN8_DLC |
+					      CAN_CTRLMODE_BERR_REPORTING;
 
 		status = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_STAT_REG);
 		if (!(status & KVASER_PCIEFD_KCAN_STAT_FD)) {
@@ -1022,6 +1014,11 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 
 		pcie->can[i] = can;
 		kvaser_pciefd_pwm_start(can);
+		ret = kvaser_pciefd_devlink_port_register(can);
+		if (ret) {
+			dev_err(&pcie->pci->dev, "Failed to register devlink port\n");
+			return ret;
+		}
 	}
 
 	return 0;
@@ -1154,14 +1151,12 @@ static int kvaser_pciefd_setup_board(struct kvaser_pciefd *pcie)
 	u32 version, srb_status, build;
 
 	version = ioread32(KVASER_PCIEFD_SYSID_ADDR(pcie) + KVASER_PCIEFD_SYSID_VERSION_REG);
+	build = ioread32(KVASER_PCIEFD_SYSID_ADDR(pcie) + KVASER_PCIEFD_SYSID_BUILD_REG);
 	pcie->nr_channels = min(KVASER_PCIEFD_MAX_CAN_CHANNELS,
 				FIELD_GET(KVASER_PCIEFD_SYSID_VERSION_NR_CHAN_MASK, version));
-
-	build = ioread32(KVASER_PCIEFD_SYSID_ADDR(pcie) + KVASER_PCIEFD_SYSID_BUILD_REG);
-	dev_dbg(&pcie->pci->dev, "Version %lu.%lu.%lu\n",
-		FIELD_GET(KVASER_PCIEFD_SYSID_VERSION_MAJOR_MASK, version),
-		FIELD_GET(KVASER_PCIEFD_SYSID_VERSION_MINOR_MASK, version),
-		FIELD_GET(KVASER_PCIEFD_SYSID_BUILD_SEQ_MASK, build));
+	pcie->fw_version.major = FIELD_GET(KVASER_PCIEFD_SYSID_VERSION_MAJOR_MASK, version);
+	pcie->fw_version.minor = FIELD_GET(KVASER_PCIEFD_SYSID_VERSION_MINOR_MASK, version);
+	pcie->fw_version.build = FIELD_GET(KVASER_PCIEFD_SYSID_BUILD_SEQ_MASK, build);
 
 	srb_status = ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_STAT_REG);
 	if (!(srb_status & KVASER_PCIEFD_SRB_STAT_DMA)) {
@@ -1200,7 +1195,7 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
 		skb = alloc_canfd_skb(priv->dev, &cf);
 		if (!skb) {
 			priv->dev->stats.rx_dropped++;
-			return -ENOMEM;
+			return 0;
 		}
 
 		cf->len = can_fd_dlc2len(dlc);
@@ -1212,7 +1207,7 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
 		skb = alloc_can_skb(priv->dev, (struct can_frame **)&cf);
 		if (!skb) {
 			priv->dev->stats.rx_dropped++;
-			return -ENOMEM;
+			return 0;
 		}
 		can_frame_set_cc_len((struct can_frame *)cf, dlc, priv->ctrlmode);
 	}
@@ -1230,15 +1225,21 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
 	priv->dev->stats.rx_packets++;
 	kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
 
-	return netif_rx(skb);
+	netif_rx(skb);
+
+	return 0;
 }
 
 static void kvaser_pciefd_change_state(struct kvaser_pciefd_can *can,
+				       const struct can_berr_counter *bec,
 				       struct can_frame *cf,
 				       enum can_state new_state,
 				       enum can_state tx_state,
 				       enum can_state rx_state)
 {
+	enum can_state old_state;
+
+	old_state = can->can.state;
 	can_change_state(can->can.dev, cf, tx_state, rx_state);
 
 	if (new_state == CAN_STATE_BUS_OFF) {
@@ -1254,6 +1255,18 @@ static void kvaser_pciefd_change_state(struct kvaser_pciefd_can *can,
 			can_bus_off(ndev);
 		}
 	}
+	if (old_state == CAN_STATE_BUS_OFF &&
+	    new_state == CAN_STATE_ERROR_ACTIVE &&
+	    can->can.restart_ms) {
+		can->can.can_stats.restarts++;
+		if (cf)
+			cf->can_id |= CAN_ERR_RESTARTED;
+	}
+	if (cf && new_state != CAN_STATE_BUS_OFF) {
+		cf->can_id |= CAN_ERR_CNT;
+		cf->data[6] = bec->txerr;
+		cf->data[7] = bec->rxerr;
+	}
 }
 
 static void kvaser_pciefd_packet_to_state(struct kvaser_pciefd_rx_packet *p,
@@ -1288,7 +1301,7 @@ static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can,
 	struct can_berr_counter bec;
 	enum can_state old_state, new_state, tx_state, rx_state;
 	struct net_device *ndev = can->can.dev;
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	struct can_frame *cf = NULL;
 
 	old_state = can->can.state;
@@ -1297,16 +1310,10 @@ static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can,
 	bec.rxerr = FIELD_GET(KVASER_PCIEFD_SPACK_RXERR_MASK, p->header[0]);
 
 	kvaser_pciefd_packet_to_state(p, &bec, &new_state, &tx_state, &rx_state);
-	skb = alloc_can_err_skb(ndev, &cf);
+	if (can->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)
+		skb = alloc_can_err_skb(ndev, &cf);
 	if (new_state != old_state) {
-		kvaser_pciefd_change_state(can, cf, new_state, tx_state, rx_state);
-		if (old_state == CAN_STATE_BUS_OFF &&
-		    new_state == CAN_STATE_ERROR_ACTIVE &&
-		    can->can.restart_ms) {
-			can->can.can_stats.restarts++;
-			if (skb)
-				cf->can_id |= CAN_ERR_RESTARTED;
-		}
+		kvaser_pciefd_change_state(can, &bec, cf, new_state, tx_state, rx_state);
 	}
 
 	can->err_rep_cnt++;
@@ -1319,18 +1326,19 @@ static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can,
 	can->bec.txerr = bec.txerr;
 	can->bec.rxerr = bec.rxerr;
 
-	if (!skb) {
-		ndev->stats.rx_dropped++;
-		return -ENOMEM;
+	if (can->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) {
+		if (!skb) {
+			netdev_warn(ndev, "No memory left for err_skb\n");
+			ndev->stats.rx_dropped++;
+			return -ENOMEM;
+		}
+		kvaser_pciefd_set_skb_timestamp(can->kv_pcie, skb, p->timestamp);
+		cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_CNT;
+		cf->data[6] = bec.txerr;
+		cf->data[7] = bec.rxerr;
+		netif_rx(skb);
 	}
 
-	kvaser_pciefd_set_skb_timestamp(can->kv_pcie, skb, p->timestamp);
-	cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_CNT;
-	cf->data[6] = bec.txerr;
-	cf->data[7] = bec.rxerr;
-
-	netif_rx(skb);
-
 	return 0;
 }
 
@@ -1359,6 +1367,7 @@ static int kvaser_pciefd_handle_status_resp(struct kvaser_pciefd_can *can,
 {
 	struct can_berr_counter bec;
 	enum can_state old_state, new_state, tx_state, rx_state;
+	int ret = 0;
 
 	old_state = can->can.state;
 
@@ -1372,25 +1381,15 @@ static int kvaser_pciefd_handle_status_resp(struct kvaser_pciefd_can *can,
 		struct can_frame *cf;
 
 		skb = alloc_can_err_skb(ndev, &cf);
-		if (!skb) {
+		kvaser_pciefd_change_state(can, &bec, cf, new_state, tx_state, rx_state);
+		if (skb) {
+			kvaser_pciefd_set_skb_timestamp(can->kv_pcie, skb, p->timestamp);
+			netif_rx(skb);
+		} else {
 			ndev->stats.rx_dropped++;
-			return -ENOMEM;
+			netdev_warn(ndev, "No memory left for err_skb\n");
+			ret = -ENOMEM;
 		}
-
-		kvaser_pciefd_change_state(can, cf, new_state, tx_state, rx_state);
-		if (old_state == CAN_STATE_BUS_OFF &&
-		    new_state == CAN_STATE_ERROR_ACTIVE &&
-		    can->can.restart_ms) {
-			can->can.can_stats.restarts++;
-			cf->can_id |= CAN_ERR_RESTARTED;
-		}
-
-		kvaser_pciefd_set_skb_timestamp(can->kv_pcie, skb, p->timestamp);
-
-		cf->data[6] = bec.txerr;
-		cf->data[7] = bec.rxerr;
-
-		netif_rx(skb);
 	}
 	can->bec.txerr = bec.txerr;
 	can->bec.rxerr = bec.rxerr;
@@ -1398,7 +1397,7 @@ static int kvaser_pciefd_handle_status_resp(struct kvaser_pciefd_can *can,
 	if (bec.txerr || bec.rxerr)
 		mod_timer(&can->bec_poll_timer, KVASER_PCIEFD_BEC_POLL_FREQ);
 
-	return 0;
+	return ret;
 }
 
 static int kvaser_pciefd_handle_status_packet(struct kvaser_pciefd *pcie,
@@ -1507,19 +1506,21 @@ static int kvaser_pciefd_handle_ack_packet(struct kvaser_pciefd *pcie,
 		netdev_dbg(can->can.dev, "Packet was flushed\n");
 	} else {
 		int echo_idx = FIELD_GET(KVASER_PCIEFD_PACKET_SEQ_MASK, p->header[0]);
-		int len;
-		u8 count;
+		unsigned int len, frame_len = 0;
 		struct sk_buff *skb;
 
+		if (echo_idx != (can->ack_idx & (can->can.echo_skb_max - 1)))
+			return 0;
 		skb = can->can.echo_skb[echo_idx];
-		if (skb)
-			kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
-		len = can_get_echo_skb(can->can.dev, echo_idx, NULL);
-		count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK,
-				  ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
+		if (!skb)
+			return 0;
+		kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
+		len = can_get_echo_skb(can->can.dev, echo_idx, &frame_len);
 
-		if (count < can->can.echo_skb_max && netif_queue_stopped(can->can.dev))
-			netif_wake_queue(can->can.dev);
+		/* Pairs with barrier in kvaser_pciefd_start_xmit() */
+		smp_store_release(&can->ack_idx, can->ack_idx + 1);
+		can->completed_tx_pkts++;
+		can->completed_tx_bytes += frame_len;
 
 		if (!one_shot_fail) {
 			can->can.dev->stats.tx_bytes += len;
@@ -1635,32 +1636,51 @@ static int kvaser_pciefd_read_buffer(struct kvaser_pciefd *pcie, int dma_buf)
 {
 	int pos = 0;
 	int res = 0;
+	unsigned int i;
 
 	do {
 		res = kvaser_pciefd_read_packet(pcie, &pos, dma_buf);
 	} while (!res && pos > 0 && pos < KVASER_PCIEFD_DMA_SIZE);
 
+	/* Report ACKs in this buffer to BQL en masse for correct periods */
+	for (i = 0; i < pcie->nr_channels; ++i) {
+		struct kvaser_pciefd_can *can = pcie->can[i];
+
+		if (!can->completed_tx_pkts)
+			continue;
+		netif_subqueue_completed_wake(can->can.dev, 0,
+					      can->completed_tx_pkts,
+					      can->completed_tx_bytes,
+					      kvaser_pciefd_tx_avail(can), 1);
+		can->completed_tx_pkts = 0;
+		can->completed_tx_bytes = 0;
+	}
+
 	return res;
 }
 
-static u32 kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
+static void kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
 {
+	void __iomem *srb_cmd_reg = KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG;
 	u32 irq = ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
 
-	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0)
+	iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
+
+	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) {
 		kvaser_pciefd_read_buffer(pcie, 0);
+		iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0, srb_cmd_reg); /* Rearm buffer */
+	}
 
-	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1)
+	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) {
 		kvaser_pciefd_read_buffer(pcie, 1);
+		iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, srb_cmd_reg); /* Rearm buffer */
+	}
 
 	if (unlikely(irq & KVASER_PCIEFD_SRB_IRQ_DOF0 ||
 		     irq & KVASER_PCIEFD_SRB_IRQ_DOF1 ||
 		     irq & KVASER_PCIEFD_SRB_IRQ_DUF0 ||
 		     irq & KVASER_PCIEFD_SRB_IRQ_DUF1))
 		dev_err(&pcie->pci->dev, "DMA IRQ error 0x%08X\n", irq);
-
-	iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
-	return irq;
 }
 
 static void kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can)
@@ -1688,29 +1708,22 @@ static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *dev)
 	struct kvaser_pciefd *pcie = (struct kvaser_pciefd *)dev;
 	const struct kvaser_pciefd_irq_mask *irq_mask = pcie->driver_data->irq_mask;
 	u32 pci_irq = ioread32(KVASER_PCIEFD_PCI_IRQ_ADDR(pcie));
-	u32 srb_irq = 0;
-	u32 srb_release = 0;
 	int i;
 
 	if (!(pci_irq & irq_mask->all))
 		return IRQ_NONE;
 
+	iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
+
 	if (pci_irq & irq_mask->kcan_rx0)
-		srb_irq = kvaser_pciefd_receive_irq(pcie);
+		kvaser_pciefd_receive_irq(pcie);
 
 	for (i = 0; i < pcie->nr_channels; i++) {
 		if (pci_irq & irq_mask->kcan_tx[i])
 			kvaser_pciefd_transmit_irq(pcie->can[i]);
 	}
 
-	if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD0)
-		srb_release |= KVASER_PCIEFD_SRB_CMD_RDB0;
-
-	if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD1)
-		srb_release |= KVASER_PCIEFD_SRB_CMD_RDB1;
-
-	if (srb_release)
-		iowrite32(srb_release, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
+	iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
 
 	return IRQ_HANDLED;
 }
@@ -1725,23 +1738,36 @@ static void kvaser_pciefd_teardown_can_ctrls(struct kvaser_pciefd *pcie)
 		if (can) {
 			iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG);
 			kvaser_pciefd_pwm_stop(can);
+			kvaser_pciefd_devlink_port_unregister(can);
 			free_candev(can->can.dev);
 		}
 	}
 }
 
+static void kvaser_pciefd_disable_irq_srcs(struct kvaser_pciefd *pcie)
+{
+	unsigned int i;
+
+	/* Masking PCI_IRQ is insufficient as running ISR will unmask it */
+	iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG);
+	for (i = 0; i < pcie->nr_channels; ++i)
+		iowrite32(0, pcie->can[i]->reg_base + KVASER_PCIEFD_KCAN_IEN_REG);
+}
+
 static int kvaser_pciefd_probe(struct pci_dev *pdev,
 			       const struct pci_device_id *id)
 {
 	int ret;
+	struct devlink *devlink;
+	struct device *dev = &pdev->dev;
 	struct kvaser_pciefd *pcie;
 	const struct kvaser_pciefd_irq_mask *irq_mask;
-	void __iomem *irq_en_base;
 
-	pcie = devm_kzalloc(&pdev->dev, sizeof(*pcie), GFP_KERNEL);
-	if (!pcie)
+	devlink = devlink_alloc(&kvaser_pciefd_devlink_ops, sizeof(*pcie), dev);
+	if (!devlink)
 		return -ENOMEM;
 
+	pcie = devlink_priv(devlink);
 	pci_set_drvdata(pdev, pcie);
 	pcie->pci = pdev;
 	pcie->driver_data = (const struct kvaser_pciefd_driver_data *)id->driver_data;
@@ -1749,7 +1775,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 
 	ret = pci_enable_device(pdev);
 	if (ret)
-		return ret;
+		goto err_free_devlink;
 
 	ret = pci_request_regions(pdev, KVASER_PCIEFD_DRV_NAME);
 	if (ret)
@@ -1777,7 +1803,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 
 	ret = pci_alloc_irq_vectors(pcie->pci, 1, 1, PCI_IRQ_INTX | PCI_IRQ_MSI);
 	if (ret < 0) {
-		dev_err(&pcie->pci->dev, "Failed to allocate IRQ vectors.\n");
+		dev_err(dev, "Failed to allocate IRQ vectors.\n");
 		goto err_teardown_can_ctrls;
 	}
 
@@ -1790,7 +1816,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 	ret = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler,
 			  IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie);
 	if (ret) {
-		dev_err(&pcie->pci->dev, "Failed to request IRQ %d\n", pcie->pci->irq);
+		dev_err(dev, "Failed to request IRQ %d\n", pcie->pci->irq);
 		goto err_pci_free_irq_vectors;
 	}
 	iowrite32(KVASER_PCIEFD_SRB_IRQ_DPD0 | KVASER_PCIEFD_SRB_IRQ_DPD1,
@@ -1802,8 +1828,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG);
 
 	/* Enable PCI interrupts */
-	irq_en_base = KVASER_PCIEFD_PCI_IEN_ADDR(pcie);
-	iowrite32(irq_mask->all, irq_en_base);
+	iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
 	/* Ready the DMA buffers */
 	iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0,
 		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
@@ -1814,11 +1839,12 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 	if (ret)
 		goto err_free_irq;
 
+	devlink_register(devlink);
+
 	return 0;
 
 err_free_irq:
-	/* Disable PCI interrupts */
-	iowrite32(0, irq_en_base);
+	kvaser_pciefd_disable_irq_srcs(pcie);
 	free_irq(pcie->pci->irq, pcie);
 
 err_pci_free_irq_vectors:
@@ -1838,41 +1864,38 @@ err_release_regions:
 err_disable_pci:
 	pci_disable_device(pdev);
 
-	return ret;
-}
-
-static void kvaser_pciefd_remove_all_ctrls(struct kvaser_pciefd *pcie)
-{
-	int i;
+err_free_devlink:
+	devlink_free(devlink);
 
-	for (i = 0; i < pcie->nr_channels; i++) {
-		struct kvaser_pciefd_can *can = pcie->can[i];
-
-		if (can) {
-			iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG);
-			unregister_candev(can->can.dev);
-			del_timer(&can->bec_poll_timer);
-			kvaser_pciefd_pwm_stop(can);
-			free_candev(can->can.dev);
-		}
-	}
+	return ret;
 }
 
 static void kvaser_pciefd_remove(struct pci_dev *pdev)
 {
 	struct kvaser_pciefd *pcie = pci_get_drvdata(pdev);
+	unsigned int i;
 
-	kvaser_pciefd_remove_all_ctrls(pcie);
+	for (i = 0; i < pcie->nr_channels; ++i) {
+		struct kvaser_pciefd_can *can = pcie->can[i];
 
-	/* Disable interrupts */
-	iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CTRL_REG);
-	iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
+		unregister_candev(can->can.dev);
+		timer_delete(&can->bec_poll_timer);
+		kvaser_pciefd_pwm_stop(can);
+		kvaser_pciefd_devlink_port_unregister(can);
+	}
 
+	kvaser_pciefd_disable_irq_srcs(pcie);
 	free_irq(pcie->pci->irq, pcie);
 	pci_free_irq_vectors(pcie->pci);
+
+	for (i = 0; i < pcie->nr_channels; ++i)
+		free_candev(pcie->can[i]->can.dev);
+
+	devlink_unregister(priv_to_devlink(pcie));
 	pci_iounmap(pdev, pcie->reg_base);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
+	devlink_free(priv_to_devlink(pcie));
 }
 
 static struct pci_driver kvaser_pciefd = {
diff --git a/drivers/net/can/kvaser_pciefd/kvaser_pciefd_devlink.c b/drivers/net/can/kvaser_pciefd/kvaser_pciefd_devlink.c
new file mode 100644
index 000000000000..1d61a8b0eeba
--- /dev/null
+++ b/drivers/net/can/kvaser_pciefd/kvaser_pciefd_devlink.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause
+/* kvaser_pciefd devlink functions
+ *
+ * Copyright (C) 2025 KVASER AB, Sweden. All rights reserved.
+ */
+#include "kvaser_pciefd.h"
+
+#include <linux/netdevice.h>
+#include <net/devlink.h>
+
+static int kvaser_pciefd_devlink_info_get(struct devlink *devlink,
+					  struct devlink_info_req *req,
+					  struct netlink_ext_ack *extack)
+{
+	struct kvaser_pciefd *pcie = devlink_priv(devlink);
+	char buf[] = "xxx.xxx.xxxxx";
+	int ret;
+
+	if (pcie->fw_version.major) {
+		snprintf(buf, sizeof(buf), "%u.%u.%u",
+			 pcie->fw_version.major,
+			 pcie->fw_version.minor,
+			 pcie->fw_version.build);
+		ret = devlink_info_version_running_put(req,
+						       DEVLINK_INFO_VERSION_GENERIC_FW,
+						       buf);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+const struct devlink_ops kvaser_pciefd_devlink_ops = {
+	.info_get = kvaser_pciefd_devlink_info_get,
+};
+
+int kvaser_pciefd_devlink_port_register(struct kvaser_pciefd_can *can)
+{
+	int ret;
+	struct devlink_port_attrs attrs = {
+		.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL,
+		.phys.port_number = can->can.dev->dev_port,
+	};
+	devlink_port_attrs_set(&can->devlink_port, &attrs);
+
+	ret = devlink_port_register(priv_to_devlink(can->kv_pcie),
+				    &can->devlink_port, can->can.dev->dev_port);
+	if (ret)
+		return ret;
+
+	SET_NETDEV_DEVLINK_PORT(can->can.dev, &can->devlink_port);
+
+	return 0;
+}
+
+void kvaser_pciefd_devlink_port_unregister(struct kvaser_pciefd_can *can)
+{
+	devlink_port_unregister(&can->devlink_port);
+}
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 97cd8bbf2e32..eb856547ae7d 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // CAN bus driver for Bosch M_CAN controller
 // Copyright (C) 2014 Freescale Semiconductor, Inc.
-//      Dong Aisheng <b29396@freescale.com>
+//      Dong Aisheng <aisheng.dong@nxp.com>
 // Copyright (C) 2018-19 Texas Instruments Incorporated - http://www.ti.com/
 
 /* Bosch M_CAN user manual can be obtained from:
@@ -23,6 +23,7 @@
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/reset.h>
 
 #include "m_can.h"
 
@@ -386,8 +387,8 @@ static int m_can_cccr_update_bits(struct m_can_classdev *cdev, u32 mask, u32 val
 	size_t tries = 10;
 
 	if (!(mask & CCCR_INIT) && !(val_before & CCCR_INIT)) {
-		dev_err(cdev->dev,
-			"refusing to configure device when in normal mode\n");
+		netdev_err(cdev->net,
+			   "refusing to configure device when in normal mode\n");
 		return -EBUSY;
 	}
 
@@ -451,7 +452,7 @@ static void m_can_interrupt_enable(struct m_can_classdev *cdev, u32 interrupts)
 {
 	if (cdev->active_interrupts == interrupts)
 		return;
-	cdev->ops->write_reg(cdev, M_CAN_IE, interrupts);
+	m_can_write(cdev, M_CAN_IE, interrupts);
 	cdev->active_interrupts = interrupts;
 }
 
@@ -469,7 +470,7 @@ static void m_can_coalescing_disable(struct m_can_classdev *cdev)
 static inline void m_can_enable_all_interrupts(struct m_can_classdev *cdev)
 {
 	if (!cdev->net->irq) {
-		dev_dbg(cdev->dev, "Start hrtimer\n");
+		netdev_dbg(cdev->net, "Start hrtimer\n");
 		hrtimer_start(&cdev->hrtimer,
 			      ms_to_ktime(HRTIMER_POLL_INTERVAL_MS),
 			      HRTIMER_MODE_REL_PINNED);
@@ -485,7 +486,7 @@ static inline void m_can_disable_all_interrupts(struct m_can_classdev *cdev)
 	m_can_write(cdev, M_CAN_ILE, 0x0);
 
 	if (!cdev->net->irq) {
-		dev_dbg(cdev->dev, "Stop hrtimer\n");
+		netdev_dbg(cdev->net, "Stop hrtimer\n");
 		hrtimer_try_to_cancel(&cdev->hrtimer);
 	}
 }
@@ -665,7 +666,7 @@ static int m_can_handle_lost_msg(struct net_device *dev)
 	struct can_frame *frame;
 	u32 timestamp = 0;
 
-	netdev_err(dev, "msg lost in rxf0\n");
+	netdev_dbg(dev, "msg lost in rxf0\n");
 
 	stats->rx_errors++;
 	stats->rx_over_errors++;
@@ -790,6 +791,10 @@ static int m_can_get_berr_counter(const struct net_device *dev,
 	struct m_can_classdev *cdev = netdev_priv(dev);
 	int err;
 
+	/* Avoid waking up the controller if the interface is down */
+	if (!(dev->flags & IFF_UP))
+		return 0;
+
 	err = m_can_clk_start(cdev);
 	if (err)
 		return err;
@@ -812,6 +817,9 @@ static int m_can_handle_state_change(struct net_device *dev,
 	u32 timestamp = 0;
 
 	switch (new_state) {
+	case CAN_STATE_ERROR_ACTIVE:
+		cdev->can.state = CAN_STATE_ERROR_ACTIVE;
+		break;
 	case CAN_STATE_ERROR_WARNING:
 		/* error warning state */
 		cdev->can.can_stats.error_warning++;
@@ -841,6 +849,12 @@ static int m_can_handle_state_change(struct net_device *dev,
 	__m_can_get_berr_counter(dev, &bec);
 
 	switch (new_state) {
+	case CAN_STATE_ERROR_ACTIVE:
+		cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT;
+		cf->data[1] = CAN_ERR_CRTL_ACTIVE;
+		cf->data[6] = bec.txerr;
+		cf->data[7] = bec.rxerr;
+		break;
 	case CAN_STATE_ERROR_WARNING:
 		/* error warning state */
 		cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT;
@@ -877,30 +891,33 @@ static int m_can_handle_state_change(struct net_device *dev,
 	return 1;
 }
 
-static int m_can_handle_state_errors(struct net_device *dev, u32 psr)
+static enum can_state
+m_can_state_get_by_psr(struct m_can_classdev *cdev)
 {
-	struct m_can_classdev *cdev = netdev_priv(dev);
-	int work_done = 0;
+	u32 reg_psr;
 
-	if (psr & PSR_EW && cdev->can.state != CAN_STATE_ERROR_WARNING) {
-		netdev_dbg(dev, "entered error warning state\n");
-		work_done += m_can_handle_state_change(dev,
-						       CAN_STATE_ERROR_WARNING);
-	}
+	reg_psr = m_can_read(cdev, M_CAN_PSR);
 
-	if (psr & PSR_EP && cdev->can.state != CAN_STATE_ERROR_PASSIVE) {
-		netdev_dbg(dev, "entered error passive state\n");
-		work_done += m_can_handle_state_change(dev,
-						       CAN_STATE_ERROR_PASSIVE);
-	}
+	if (reg_psr & PSR_BO)
+		return CAN_STATE_BUS_OFF;
+	if (reg_psr & PSR_EP)
+		return CAN_STATE_ERROR_PASSIVE;
+	if (reg_psr & PSR_EW)
+		return CAN_STATE_ERROR_WARNING;
 
-	if (psr & PSR_BO && cdev->can.state != CAN_STATE_BUS_OFF) {
-		netdev_dbg(dev, "entered error bus off state\n");
-		work_done += m_can_handle_state_change(dev,
-						       CAN_STATE_BUS_OFF);
-	}
+	return CAN_STATE_ERROR_ACTIVE;
+}
 
-	return work_done;
+static int m_can_handle_state_errors(struct net_device *dev)
+{
+	struct m_can_classdev *cdev = netdev_priv(dev);
+	enum can_state new_state;
+
+	new_state = m_can_state_get_by_psr(cdev);
+	if (new_state == cdev->can.state)
+		return 0;
+
+	return m_can_handle_state_change(dev, new_state);
 }
 
 static void m_can_handle_other_err(struct net_device *dev, u32 irqstatus)
@@ -1031,8 +1048,7 @@ static int m_can_rx_handler(struct net_device *dev, int quota, u32 irqstatus)
 	}
 
 	if (irqstatus & IR_ERR_STATE)
-		work_done += m_can_handle_state_errors(dev,
-						       m_can_read(cdev, M_CAN_PSR));
+		work_done += m_can_handle_state_errors(dev);
 
 	if (irqstatus & IR_ERR_BUS_30X)
 		work_done += m_can_handle_bus_errors(dev, irqstatus,
@@ -1368,11 +1384,32 @@ static const struct can_bittiming_const m_can_data_bittiming_const_31X = {
 	.brp_inc = 1,
 };
 
+static int m_can_init_ram(struct m_can_classdev *cdev)
+{
+	int end, i, start;
+	int err = 0;
+
+	/* initialize the entire Message RAM in use to avoid possible
+	 * ECC/parity checksum errors when reading an uninitialized buffer
+	 */
+	start = cdev->mcfg[MRAM_SIDF].off;
+	end = cdev->mcfg[MRAM_TXB].off +
+		cdev->mcfg[MRAM_TXB].num * TXB_ELEMENT_SIZE;
+
+	for (i = start; i < end; i += 4) {
+		err = m_can_fifo_write_no_off(cdev, i, 0x0);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
 static int m_can_set_bittiming(struct net_device *dev)
 {
 	struct m_can_classdev *cdev = netdev_priv(dev);
 	const struct can_bittiming *bt = &cdev->can.bittiming;
-	const struct can_bittiming *dbt = &cdev->can.data_bittiming;
+	const struct can_bittiming *dbt = &cdev->can.fd.data_bittiming;
 	u16 brp, sjw, tseg1, tseg2;
 	u32 reg_btp;
 
@@ -1453,7 +1490,7 @@ static int m_can_chip_config(struct net_device *dev)
 
 	err = m_can_init_ram(cdev);
 	if (err) {
-		dev_err(cdev->dev, "Message RAM configuration failed\n");
+		netdev_err(dev, "Message RAM configuration failed\n");
 		return err;
 	}
 
@@ -1606,7 +1643,7 @@ static int m_can_start(struct net_device *dev)
 	netdev_queue_set_dql_min_limit(netdev_get_tx_queue(cdev->net, 0),
 				       cdev->tx_max_coalesced_frames);
 
-	cdev->can.state = CAN_STATE_ERROR_ACTIVE;
+	cdev->can.state = m_can_state_get_by_psr(cdev);
 
 	m_can_enable_all_interrupts(cdev);
 
@@ -1683,7 +1720,7 @@ static int m_can_niso_supported(struct m_can_classdev *cdev)
 	/* Then clear the it again. */
 	ret = m_can_cccr_update_bits(cdev, CCCR_NISO, 0);
 	if (ret) {
-		dev_err(cdev->dev, "failed to revert the NON-ISO bit in CCCR\n");
+		netdev_err(cdev->net, "failed to revert the NON-ISO bit in CCCR\n");
 		return ret;
 	}
 
@@ -1702,8 +1739,8 @@ static int m_can_dev_setup(struct m_can_classdev *cdev)
 	m_can_version = m_can_check_core_release(cdev);
 	/* return if unsupported version */
 	if (!m_can_version) {
-		dev_err(cdev->dev, "Unsupported version number: %2d",
-			m_can_version);
+		netdev_err(cdev->net, "Unsupported version number: %2d",
+			   m_can_version);
 		return -EINVAL;
 	}
 
@@ -1738,7 +1775,7 @@ static int m_can_dev_setup(struct m_can_classdev *cdev)
 		if (err)
 			return err;
 		cdev->can.bittiming_const = &m_can_bittiming_const_30X;
-		cdev->can.data_bittiming_const = &m_can_data_bittiming_const_30X;
+		cdev->can.fd.data_bittiming_const = &m_can_data_bittiming_const_30X;
 		break;
 	case 31:
 		/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.1.x */
@@ -1746,13 +1783,13 @@ static int m_can_dev_setup(struct m_can_classdev *cdev)
 		if (err)
 			return err;
 		cdev->can.bittiming_const = &m_can_bittiming_const_31X;
-		cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X;
+		cdev->can.fd.data_bittiming_const = &m_can_data_bittiming_const_31X;
 		break;
 	case 32:
 	case 33:
 		/* Support both MCAN version v3.2.x and v3.3.0 */
 		cdev->can.bittiming_const = &m_can_bittiming_const_31X;
-		cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X;
+		cdev->can.fd.data_bittiming_const = &m_can_data_bittiming_const_31X;
 
 		niso = m_can_niso_supported(cdev);
 		if (niso < 0)
@@ -1761,8 +1798,8 @@ static int m_can_dev_setup(struct m_can_classdev *cdev)
 			cdev->can.ctrlmode_supported |= CAN_CTRLMODE_FD_NON_ISO;
 		break;
 	default:
-		dev_err(cdev->dev, "Unsupported version number: %2d",
-			cdev->version);
+		netdev_err(cdev->net, "Unsupported version number: %2d",
+			   cdev->version);
 		return -EINVAL;
 	}
 
@@ -1785,6 +1822,13 @@ static void m_can_stop(struct net_device *dev)
 
 	/* set the state as STOPPED */
 	cdev->can.state = CAN_STATE_STOPPED;
+
+	if (cdev->ops->deinit) {
+		ret = cdev->ops->deinit(cdev);
+		if (ret)
+			netdev_err(dev, "failed to deinitialize: %pe\n",
+				   ERR_PTR(ret));
+	}
 }
 
 static int m_can_close(struct net_device *dev)
@@ -1809,6 +1853,7 @@ static int m_can_close(struct net_device *dev)
 
 	close_candev(dev);
 
+	reset_control_assert(cdev->rst);
 	m_can_clk_stop(cdev);
 	phy_power_off(cdev->transceiver);
 
@@ -1932,11 +1977,6 @@ out_fail:
 
 static void m_can_tx_submit(struct m_can_classdev *cdev)
 {
-	if (cdev->version == 30)
-		return;
-	if (!cdev->is_peripheral)
-		return;
-
 	m_can_write(cdev, M_CAN_TXBAR, cdev->tx_peripheral_submit);
 	cdev->tx_peripheral_submit = 0;
 }
@@ -2017,7 +2057,7 @@ static netdev_tx_t m_can_start_xmit(struct sk_buff *skb,
 	return ret;
 }
 
-static enum hrtimer_restart hrtimer_callback(struct hrtimer *timer)
+static enum hrtimer_restart m_can_polling_timer(struct hrtimer *timer)
 {
 	struct m_can_classdev *cdev = container_of(timer, struct
 						   m_can_classdev, hrtimer);
@@ -2051,11 +2091,15 @@ static int m_can_open(struct net_device *dev)
 	if (err)
 		goto out_phy_power_off;
 
+	err = reset_control_deassert(cdev->rst);
+	if (err)
+		goto exit_disable_clks;
+
 	/* open the can device */
 	err = open_candev(dev);
 	if (err) {
 		netdev_err(dev, "failed to open can device\n");
-		goto exit_disable_clks;
+		goto out_reset_control_assert;
 	}
 
 	if (cdev->is_peripheral)
@@ -2111,6 +2155,8 @@ out_wq_fail:
 	else
 		napi_disable(&cdev->napi);
 	close_candev(dev);
+out_reset_control_assert:
+	reset_control_assert(cdev->rst);
 exit_disable_clks:
 	m_can_clk_stop(cdev);
 out_phy_power_off:
@@ -2122,7 +2168,6 @@ static const struct net_device_ops m_can_netdev_ops = {
 	.ndo_open = m_can_open,
 	.ndo_stop = m_can_close,
 	.ndo_start_xmit = m_can_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static int m_can_get_coalesce(struct net_device *dev,
@@ -2206,13 +2251,60 @@ static int m_can_set_coalesce(struct net_device *dev,
 	cdev->tx_coalesce_usecs_irq = ec->tx_coalesce_usecs_irq;
 
 	if (cdev->rx_coalesce_usecs_irq)
-		cdev->irq_timer_wait =
-			ns_to_ktime(cdev->rx_coalesce_usecs_irq * NSEC_PER_USEC);
+		cdev->irq_timer_wait = us_to_ktime(cdev->rx_coalesce_usecs_irq);
 	else
-		cdev->irq_timer_wait =
-			ns_to_ktime(cdev->tx_coalesce_usecs_irq * NSEC_PER_USEC);
+		cdev->irq_timer_wait = us_to_ktime(cdev->tx_coalesce_usecs_irq);
+
+	return 0;
+}
+
+static void m_can_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+	struct m_can_classdev *cdev = netdev_priv(dev);
+
+	wol->supported = device_can_wakeup(cdev->dev) ? WAKE_PHY : 0;
+	wol->wolopts = device_may_wakeup(cdev->dev) ? WAKE_PHY : 0;
+}
+
+static int m_can_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+	struct m_can_classdev *cdev = netdev_priv(dev);
+	bool wol_enable = !!(wol->wolopts & WAKE_PHY);
+	int ret;
+
+	if (wol->wolopts & ~WAKE_PHY)
+		return -EINVAL;
+
+	if (wol_enable == device_may_wakeup(cdev->dev))
+		return 0;
+
+	ret = device_set_wakeup_enable(cdev->dev, wol_enable);
+	if (ret) {
+		netdev_err(cdev->net, "Failed to set wakeup enable %pE\n",
+			   ERR_PTR(ret));
+		return ret;
+	}
+
+	if (!IS_ERR_OR_NULL(cdev->pinctrl_state_wakeup)) {
+		if (wol_enable)
+			ret = pinctrl_select_state(cdev->pinctrl, cdev->pinctrl_state_wakeup);
+		else
+			ret = pinctrl_pm_select_default_state(cdev->dev);
+
+		if (ret) {
+			netdev_err(cdev->net, "Failed to select pinctrl state %pE\n",
+				   ERR_PTR(ret));
+			goto err_wakeup_enable;
+		}
+	}
 
 	return 0;
+
+err_wakeup_enable:
+	/* Revert wakeup enable */
+	device_set_wakeup_enable(cdev->dev, !wol_enable);
+
+	return ret;
 }
 
 static const struct ethtool_ops m_can_ethtool_ops_coalescing = {
@@ -2224,10 +2316,14 @@ static const struct ethtool_ops m_can_ethtool_ops_coalescing = {
 	.get_ts_info = ethtool_op_get_ts_info,
 	.get_coalesce = m_can_get_coalesce,
 	.set_coalesce = m_can_set_coalesce,
+	.get_wol = m_can_get_wol,
+	.set_wol = m_can_set_wol,
 };
 
 static const struct ethtool_ops m_can_ethtool_ops = {
 	.get_ts_info = ethtool_op_get_ts_info,
+	.get_wol = m_can_get_wol,
+	.set_wol = m_can_set_wol,
 };
 
 static int register_m_can_dev(struct m_can_classdev *cdev)
@@ -2251,8 +2347,8 @@ int m_can_check_mram_cfg(struct m_can_classdev *cdev, u32 mram_max_size)
 	total_size = cdev->mcfg[MRAM_TXB].off - cdev->mcfg[MRAM_SIDF].off +
 			cdev->mcfg[MRAM_TXB].num * TXB_ELEMENT_SIZE;
 	if (total_size > mram_max_size) {
-		dev_err(cdev->dev, "Total size of mram config(%u) exceeds mram(%u)\n",
-			total_size, mram_max_size);
+		netdev_err(cdev->net, "Total size of mram config(%u) exceeds mram(%u)\n",
+			   total_size, mram_max_size);
 		return -EINVAL;
 	}
 
@@ -2287,38 +2383,16 @@ static void m_can_of_parse_mram(struct m_can_classdev *cdev,
 	cdev->mcfg[MRAM_TXB].num = mram_config_vals[7] &
 		FIELD_MAX(TXBC_NDTB_MASK);
 
-	dev_dbg(cdev->dev,
-		"sidf 0x%x %d xidf 0x%x %d rxf0 0x%x %d rxf1 0x%x %d rxb 0x%x %d txe 0x%x %d txb 0x%x %d\n",
-		cdev->mcfg[MRAM_SIDF].off, cdev->mcfg[MRAM_SIDF].num,
-		cdev->mcfg[MRAM_XIDF].off, cdev->mcfg[MRAM_XIDF].num,
-		cdev->mcfg[MRAM_RXF0].off, cdev->mcfg[MRAM_RXF0].num,
-		cdev->mcfg[MRAM_RXF1].off, cdev->mcfg[MRAM_RXF1].num,
-		cdev->mcfg[MRAM_RXB].off, cdev->mcfg[MRAM_RXB].num,
-		cdev->mcfg[MRAM_TXE].off, cdev->mcfg[MRAM_TXE].num,
-		cdev->mcfg[MRAM_TXB].off, cdev->mcfg[MRAM_TXB].num);
-}
-
-int m_can_init_ram(struct m_can_classdev *cdev)
-{
-	int end, i, start;
-	int err = 0;
-
-	/* initialize the entire Message RAM in use to avoid possible
-	 * ECC/parity checksum errors when reading an uninitialized buffer
-	 */
-	start = cdev->mcfg[MRAM_SIDF].off;
-	end = cdev->mcfg[MRAM_TXB].off +
-		cdev->mcfg[MRAM_TXB].num * TXB_ELEMENT_SIZE;
-
-	for (i = start; i < end; i += 4) {
-		err = m_can_fifo_write_no_off(cdev, i, 0x0);
-		if (err)
-			break;
-	}
-
-	return err;
+	netdev_dbg(cdev->net,
+		   "sidf 0x%x %d xidf 0x%x %d rxf0 0x%x %d rxf1 0x%x %d rxb 0x%x %d txe 0x%x %d txb 0x%x %d\n",
+		   cdev->mcfg[MRAM_SIDF].off, cdev->mcfg[MRAM_SIDF].num,
+		   cdev->mcfg[MRAM_XIDF].off, cdev->mcfg[MRAM_XIDF].num,
+		   cdev->mcfg[MRAM_RXF0].off, cdev->mcfg[MRAM_RXF0].num,
+		   cdev->mcfg[MRAM_RXF1].off, cdev->mcfg[MRAM_RXF1].num,
+		   cdev->mcfg[MRAM_RXB].off, cdev->mcfg[MRAM_RXB].num,
+		   cdev->mcfg[MRAM_TXE].off, cdev->mcfg[MRAM_TXE].num,
+		   cdev->mcfg[MRAM_TXB].off, cdev->mcfg[MRAM_TXB].num);
 }
-EXPORT_SYMBOL_GPL(m_can_init_ram);
 
 int m_can_class_get_clocks(struct m_can_classdev *cdev)
 {
@@ -2328,7 +2402,7 @@ int m_can_class_get_clocks(struct m_can_classdev *cdev)
 	cdev->cclk = devm_clk_get(cdev->dev, "cclk");
 
 	if (IS_ERR(cdev->hclk) || IS_ERR(cdev->cclk)) {
-		dev_err(cdev->dev, "no clock found\n");
+		netdev_err(cdev->net, "no clock found\n");
 		ret = -ENODEV;
 	}
 
@@ -2336,6 +2410,42 @@ int m_can_class_get_clocks(struct m_can_classdev *cdev)
 }
 EXPORT_SYMBOL_GPL(m_can_class_get_clocks);
 
+static bool m_can_class_wakeup_pinctrl_enabled(struct m_can_classdev *class_dev)
+{
+	return device_may_wakeup(class_dev->dev) && class_dev->pinctrl_state_wakeup;
+}
+
+static int m_can_class_parse_pinctrl(struct m_can_classdev *class_dev)
+{
+	struct device *dev = class_dev->dev;
+	int ret;
+
+	class_dev->pinctrl = devm_pinctrl_get(dev);
+	if (IS_ERR(class_dev->pinctrl)) {
+		ret = PTR_ERR(class_dev->pinctrl);
+		class_dev->pinctrl = NULL;
+
+		if (ret == -ENODEV)
+			return 0;
+
+		return dev_err_probe(dev, ret, "Failed to get pinctrl\n");
+	}
+
+	class_dev->pinctrl_state_wakeup =
+		pinctrl_lookup_state(class_dev->pinctrl, "wakeup");
+	if (IS_ERR(class_dev->pinctrl_state_wakeup)) {
+		ret = PTR_ERR(class_dev->pinctrl_state_wakeup);
+		class_dev->pinctrl_state_wakeup = NULL;
+
+		if (ret == -ENODEV)
+			return 0;
+
+		return dev_err_probe(dev, ret, "Failed to lookup pinctrl wakeup state\n");
+	}
+
+	return 0;
+}
+
 struct m_can_classdev *m_can_class_allocate_dev(struct device *dev,
 						int sizeof_priv)
 {
@@ -2351,9 +2461,12 @@ struct m_can_classdev *m_can_class_allocate_dev(struct device *dev,
 					     sizeof(mram_config_vals) / 4);
 	if (ret) {
 		dev_err(dev, "Could not get Message RAM configuration.");
-		goto out;
+		return ERR_PTR(ret);
 	}
 
+	if (dev->of_node && of_property_read_bool(dev->of_node, "wakeup-source"))
+		device_set_wakeup_capable(dev, true);
+
 	/* Get TX FIFO size
 	 * Defines the total amount of echo buffers for loopback
 	 */
@@ -2363,7 +2476,7 @@ struct m_can_classdev *m_can_class_allocate_dev(struct device *dev,
 	net_dev = alloc_candev(sizeof_priv, tx_fifo_size);
 	if (!net_dev) {
 		dev_err(dev, "Failed to allocate CAN device");
-		goto out;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	class_dev = netdev_priv(net_dev);
@@ -2372,8 +2485,17 @@ struct m_can_classdev *m_can_class_allocate_dev(struct device *dev,
 	SET_NETDEV_DEV(net_dev, dev);
 
 	m_can_of_parse_mram(class_dev, mram_config_vals);
-out:
+	spin_lock_init(&class_dev->tx_handling_spinlock);
+
+	ret = m_can_class_parse_pinctrl(class_dev);
+	if (ret)
+		goto err_free_candev;
+
 	return class_dev;
+
+err_free_candev:
+	free_candev(net_dev);
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(m_can_class_allocate_dev);
 
@@ -2394,31 +2516,37 @@ int m_can_class_register(struct m_can_classdev *cdev)
 			devm_kzalloc(cdev->dev,
 				     cdev->tx_fifo_size * sizeof(*cdev->tx_ops),
 				     GFP_KERNEL);
-		if (!cdev->tx_ops) {
-			dev_err(cdev->dev, "Failed to allocate tx_ops for workqueue\n");
+		if (!cdev->tx_ops)
 			return -ENOMEM;
-		}
 	}
 
+	cdev->rst = devm_reset_control_get_optional_shared(cdev->dev, NULL);
+	if (IS_ERR(cdev->rst))
+		return dev_err_probe(cdev->dev, PTR_ERR(cdev->rst),
+				     "Failed to get reset line\n");
+
 	ret = m_can_clk_start(cdev);
 	if (ret)
 		return ret;
 
+	ret = reset_control_deassert(cdev->rst);
+	if (ret)
+		goto clk_disable;
+
 	if (cdev->is_peripheral) {
 		ret = can_rx_offload_add_manual(cdev->net, &cdev->offload,
 						NAPI_POLL_WEIGHT);
 		if (ret)
-			goto clk_disable;
+			goto out_reset_control_assert;
 	}
 
 	if (!cdev->net->irq) {
-		dev_dbg(cdev->dev, "Polling enabled, initialize hrtimer");
-		hrtimer_init(&cdev->hrtimer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL_PINNED);
-		cdev->hrtimer.function = &hrtimer_callback;
+		netdev_dbg(cdev->net, "Polling enabled, initialize hrtimer");
+		hrtimer_setup(&cdev->hrtimer, m_can_polling_timer, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL_PINNED);
 	} else {
-		hrtimer_init(&cdev->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		cdev->hrtimer.function = m_can_coalescing_timer;
+		hrtimer_setup(&cdev->hrtimer, m_can_coalescing_timer, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 	}
 
 	ret = m_can_dev_setup(cdev);
@@ -2427,19 +2555,21 @@ int m_can_class_register(struct m_can_classdev *cdev)
 
 	ret = register_m_can_dev(cdev);
 	if (ret) {
-		dev_err(cdev->dev, "registering %s failed (err=%d)\n",
-			cdev->net->name, ret);
+		netdev_err(cdev->net, "registering %s failed (err=%d)\n",
+			   cdev->net->name, ret);
 		goto rx_offload_del;
 	}
 
 	of_can_transceiver(cdev->net);
 
-	dev_info(cdev->dev, "%s device registered (irq=%d, version=%d)\n",
-		 KBUILD_MODNAME, cdev->net->irq, cdev->version);
+	netdev_info(cdev->net, "device registered (irq=%d, version=%d)\n",
+		    cdev->net->irq, cdev->version);
 
 	/* Probe finished
-	 * Stop clocks. They will be reactivated once the M_CAN device is opened
+	 * Assert reset and stop clocks.
+	 * They will be reactivated once the M_CAN device is opened
 	 */
+	reset_control_assert(cdev->rst);
 	m_can_clk_stop(cdev);
 
 	return 0;
@@ -2447,6 +2577,8 @@ int m_can_class_register(struct m_can_classdev *cdev)
 rx_offload_del:
 	if (cdev->is_peripheral)
 		can_rx_offload_del(&cdev->offload);
+out_reset_control_assert:
+	reset_control_assert(cdev->rst);
 clk_disable:
 	m_can_clk_stop(cdev);
 
@@ -2456,9 +2588,9 @@ EXPORT_SYMBOL_GPL(m_can_class_register);
 
 void m_can_class_unregister(struct m_can_classdev *cdev)
 {
+	unregister_candev(cdev->net);
 	if (cdev->is_peripheral)
 		can_rx_offload_del(&cdev->offload);
-	unregister_candev(cdev->net);
 }
 EXPORT_SYMBOL_GPL(m_can_class_unregister);
 
@@ -2466,6 +2598,7 @@ int m_can_class_suspend(struct device *dev)
 {
 	struct m_can_classdev *cdev = dev_get_drvdata(dev);
 	struct net_device *ndev = cdev->net;
+	int ret = 0;
 
 	if (netif_running(ndev)) {
 		netif_stop_queue(ndev);
@@ -2478,18 +2611,21 @@ int m_can_class_suspend(struct device *dev)
 		if (cdev->pm_wake_source) {
 			hrtimer_cancel(&cdev->hrtimer);
 			m_can_write(cdev, M_CAN_IE, IR_RF0N);
+
+			if (cdev->ops->deinit)
+				ret = cdev->ops->deinit(cdev);
 		} else {
 			m_can_stop(ndev);
 		}
 
 		m_can_clk_stop(cdev);
+		cdev->can.state = CAN_STATE_SLEEPING;
 	}
 
-	pinctrl_pm_select_sleep_state(dev);
+	if (!m_can_class_wakeup_pinctrl_enabled(cdev))
+		pinctrl_pm_select_sleep_state(dev);
 
-	cdev->can.state = CAN_STATE_SLEEPING;
-
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(m_can_class_suspend);
 
@@ -2497,14 +2633,12 @@ int m_can_class_resume(struct device *dev)
 {
 	struct m_can_classdev *cdev = dev_get_drvdata(dev);
 	struct net_device *ndev = cdev->net;
+	int ret = 0;
 
-	pinctrl_pm_select_default_state(dev);
-
-	cdev->can.state = CAN_STATE_ERROR_ACTIVE;
+	if (!m_can_class_wakeup_pinctrl_enabled(cdev))
+		pinctrl_pm_select_default_state(dev);
 
 	if (netif_running(ndev)) {
-		int ret;
-
 		ret = m_can_clk_start(cdev);
 		if (ret)
 			return ret;
@@ -2517,6 +2651,12 @@ int m_can_class_resume(struct device *dev)
 			 * again.
 			 */
 			cdev->active_interrupts |= IR_RF0N | IR_TEFN;
+
+			if (cdev->ops->init)
+				ret = cdev->ops->init(cdev);
+
+			cdev->can.state = m_can_state_get_by_psr(cdev);
+
 			m_can_write(cdev, M_CAN_IE, cdev->active_interrupts);
 		} else {
 			ret  = m_can_start(ndev);
@@ -2530,11 +2670,11 @@ int m_can_class_resume(struct device *dev)
 		netif_start_queue(ndev);
 	}
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(m_can_class_resume);
 
-MODULE_AUTHOR("Dong Aisheng <b29396@freescale.com>");
+MODULE_AUTHOR("Dong Aisheng <aisheng.dong@nxp.com>");
 MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com>");
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("CAN bus driver for Bosch M_CAN controller");
diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h
index ef39e8e527ab..4743342b2fba 100644
--- a/drivers/net/can/m_can/m_can.h
+++ b/drivers/net/can/m_can/m_can.h
@@ -68,6 +68,7 @@ struct m_can_ops {
 	int (*write_fifo)(struct m_can_classdev *cdev, int addr_offset,
 			  const void *val, size_t val_count);
 	int (*init)(struct m_can_classdev *cdev);
+	int (*deinit)(struct m_can_classdev *cdev);
 };
 
 struct m_can_tx_op {
@@ -85,6 +86,7 @@ struct m_can_classdev {
 	struct device *dev;
 	struct clk *hclk;
 	struct clk *cclk;
+	struct reset_control *rst;
 
 	struct workqueue_struct *tx_wq;
 	struct phy *transceiver;
@@ -127,6 +129,9 @@ struct m_can_classdev {
 	struct mram_cfg mcfg[MRAM_CFG_NUM];
 
 	struct hrtimer hrtimer;
+
+	struct pinctrl *pinctrl;
+	struct pinctrl_state *pinctrl_state_wakeup;
 };
 
 struct m_can_classdev *m_can_class_allocate_dev(struct device *dev, int sizeof_priv);
@@ -134,7 +139,6 @@ void m_can_class_free_dev(struct net_device *net);
 int m_can_class_register(struct m_can_classdev *cdev);
 void m_can_class_unregister(struct m_can_classdev *cdev);
 int m_can_class_get_clocks(struct m_can_classdev *cdev);
-int m_can_init_ram(struct m_can_classdev *priv);
 int m_can_check_mram_cfg(struct m_can_classdev *cdev, u32 mram_max_size);
 
 int m_can_class_suspend(struct device *dev);
diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c
index 9ad7419f88f8..eb31ed1f9644 100644
--- a/drivers/net/can/m_can/m_can_pci.c
+++ b/drivers/net/can/m_can/m_can_pci.c
@@ -111,8 +111,8 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
 
 	mcan_class = m_can_class_allocate_dev(&pci->dev,
 					      sizeof(struct m_can_pci_priv));
-	if (!mcan_class)
-		return -ENOMEM;
+	if (IS_ERR(mcan_class))
+		return PTR_ERR(mcan_class);
 
 	priv = cdev_to_priv(mcan_class);
 
diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c
index b832566efda0..56da411878af 100644
--- a/drivers/net/can/m_can/m_can_platform.c
+++ b/drivers/net/can/m_can/m_can_platform.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // IOMapped CAN bus driver for Bosch M_CAN controller
 // Copyright (C) 2014 Freescale Semiconductor, Inc.
-//	Dong Aisheng <b29396@freescale.com>
+//	Dong Aisheng <aisheng.dong@nxp.com>
 //
 // Copyright (C) 2018-19 Texas Instruments Incorporated - http://www.ti.com/
 
@@ -87,8 +87,8 @@ static int m_can_plat_probe(struct platform_device *pdev)
 
 	mcan_class = m_can_class_allocate_dev(&pdev->dev,
 					      sizeof(struct m_can_plat_priv));
-	if (!mcan_class)
-		return -ENOMEM;
+	if (IS_ERR(mcan_class))
+		return PTR_ERR(mcan_class);
 
 	priv = cdev_to_priv(mcan_class);
 
@@ -180,7 +180,7 @@ static void m_can_plat_remove(struct platform_device *pdev)
 	struct m_can_classdev *mcan_class = &priv->cdev;
 
 	m_can_class_unregister(mcan_class);
-
+	pm_runtime_disable(mcan_class->dev);
 	m_can_class_free_dev(mcan_class->net);
 }
 
@@ -236,7 +236,7 @@ static struct platform_driver m_can_plat_driver = {
 
 module_platform_driver(m_can_plat_driver);
 
-MODULE_AUTHOR("Dong Aisheng <b29396@freescale.com>");
+MODULE_AUTHOR("Dong Aisheng <aisheng.dong@nxp.com>");
 MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com>");
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("M_CAN driver for IO Mapped Bosch controllers");
diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c
index 2f73bf3abad8..31cc9d0abd45 100644
--- a/drivers/net/can/m_can/tcan4x5x-core.c
+++ b/drivers/net/can/m_can/tcan4x5x-core.c
@@ -92,6 +92,8 @@
 #define TCAN4X5X_MODE_STANDBY BIT(6)
 #define TCAN4X5X_MODE_NORMAL BIT(7)
 
+#define TCAN4X5X_NWKRQ_VOLTAGE_VIO BIT(19)
+
 #define TCAN4X5X_DISABLE_WAKE_MSK	(BIT(31) | BIT(30))
 #define TCAN4X5X_DISABLE_INH_MSK	BIT(9)
 
@@ -267,9 +269,24 @@ static int tcan4x5x_init(struct m_can_classdev *cdev)
 	if (ret)
 		return ret;
 
+	if (tcan4x5x->nwkrq_voltage_vio) {
+		ret = regmap_set_bits(tcan4x5x->regmap, TCAN4X5X_CONFIG,
+				      TCAN4X5X_NWKRQ_VOLTAGE_VIO);
+		if (ret)
+			return ret;
+	}
+
 	return ret;
 }
 
+static int tcan4x5x_deinit(struct m_can_classdev *cdev)
+{
+	struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev);
+
+	return regmap_update_bits(tcan4x5x->regmap, TCAN4X5X_CONFIG,
+				  TCAN4X5X_MODE_SEL_MASK, TCAN4X5X_MODE_STANDBY);
+};
+
 static int tcan4x5x_disable_wake(struct m_can_classdev *cdev)
 {
 	struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev);
@@ -318,21 +335,27 @@ static const struct tcan4x5x_version_info
 	return &tcan4x5x_versions[TCAN4X5X];
 }
 
-static int tcan4x5x_get_gpios(struct m_can_classdev *cdev,
-			      const struct tcan4x5x_version_info *version_info)
+static void tcan4x5x_get_dt_data(struct m_can_classdev *cdev)
+{
+	struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev);
+
+	tcan4x5x->nwkrq_voltage_vio =
+		of_property_read_bool(cdev->dev->of_node, "ti,nwkrq-voltage-vio");
+}
+
+static int tcan4x5x_get_gpios(struct m_can_classdev *cdev)
 {
 	struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev);
 	int ret;
 
-	if (version_info->has_wake_pin) {
-		tcan4x5x->device_wake_gpio = devm_gpiod_get(cdev->dev, "device-wake",
-							    GPIOD_OUT_HIGH);
-		if (IS_ERR(tcan4x5x->device_wake_gpio)) {
-			if (PTR_ERR(tcan4x5x->device_wake_gpio) == -EPROBE_DEFER)
-				return -EPROBE_DEFER;
+	tcan4x5x->device_wake_gpio = devm_gpiod_get_optional(cdev->dev,
+							     "device-wake",
+							     GPIOD_OUT_HIGH);
+	if (IS_ERR(tcan4x5x->device_wake_gpio)) {
+		if (PTR_ERR(tcan4x5x->device_wake_gpio) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
 
-			tcan4x5x_disable_wake(cdev);
-		}
+		tcan4x5x->device_wake_gpio = NULL;
 	}
 
 	tcan4x5x->reset_gpio = devm_gpiod_get_optional(cdev->dev, "reset",
@@ -344,14 +367,31 @@ static int tcan4x5x_get_gpios(struct m_can_classdev *cdev,
 	if (ret)
 		return ret;
 
-	if (version_info->has_state_pin) {
-		tcan4x5x->device_state_gpio = devm_gpiod_get_optional(cdev->dev,
-								      "device-state",
-								      GPIOD_IN);
-		if (IS_ERR(tcan4x5x->device_state_gpio)) {
-			tcan4x5x->device_state_gpio = NULL;
-			tcan4x5x_disable_state(cdev);
-		}
+	tcan4x5x->device_state_gpio = devm_gpiod_get_optional(cdev->dev,
+							      "device-state",
+							      GPIOD_IN);
+	if (IS_ERR(tcan4x5x->device_state_gpio))
+		tcan4x5x->device_state_gpio = NULL;
+
+	return 0;
+}
+
+static int tcan4x5x_check_gpios(struct m_can_classdev *cdev,
+				const struct tcan4x5x_version_info *version_info)
+{
+	struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev);
+	int ret;
+
+	if (version_info->has_wake_pin && !tcan4x5x->device_wake_gpio) {
+		ret = tcan4x5x_disable_wake(cdev);
+		if (ret)
+			return ret;
+	}
+
+	if (version_info->has_state_pin && !tcan4x5x->device_state_gpio) {
+		ret = tcan4x5x_disable_state(cdev);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -359,6 +399,7 @@ static int tcan4x5x_get_gpios(struct m_can_classdev *cdev,
 
 static const struct m_can_ops tcan4x5x_ops = {
 	.init = tcan4x5x_init,
+	.deinit = tcan4x5x_deinit,
 	.read_reg = tcan4x5x_read_reg,
 	.write_reg = tcan4x5x_write_reg,
 	.write_fifo = tcan4x5x_write_fifo,
@@ -375,8 +416,8 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
 
 	mcan_class = m_can_class_allocate_dev(&spi->dev,
 					      sizeof(struct tcan4x5x_priv));
-	if (!mcan_class)
-		return -ENOMEM;
+	if (IS_ERR(mcan_class))
+		return PTR_ERR(mcan_class);
 
 	ret = m_can_check_mram_cfg(mcan_class, TCAN4X5X_MRAM_SIZE);
 	if (ret)
@@ -385,14 +426,15 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
 	priv = cdev_to_priv(mcan_class);
 
 	priv->power = devm_regulator_get_optional(&spi->dev, "vsup");
-	if (PTR_ERR(priv->power) == -EPROBE_DEFER) {
-		ret = -EPROBE_DEFER;
-		goto out_m_can_class_free_dev;
-	} else {
+	if (IS_ERR(priv->power)) {
+		if (PTR_ERR(priv->power) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto out_m_can_class_free_dev;
+		}
 		priv->power = NULL;
 	}
 
-	m_can_class_get_clocks(mcan_class);
+	mcan_class->cclk = devm_clk_get(mcan_class->dev, "cclk");
 	if (IS_ERR(mcan_class->cclk)) {
 		dev_err(&spi->dev, "no CAN clock source defined\n");
 		freq = TCAN4X5X_EXT_CLK_DEF;
@@ -441,18 +483,26 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
 		goto out_m_can_class_free_dev;
 	}
 
+	ret = tcan4x5x_get_gpios(mcan_class);
+	if (ret) {
+		dev_err(&spi->dev, "Getting gpios failed %pe\n", ERR_PTR(ret));
+		goto out_power;
+	}
+
 	version_info = tcan4x5x_find_version(priv);
 	if (IS_ERR(version_info)) {
 		ret = PTR_ERR(version_info);
 		goto out_power;
 	}
 
-	ret = tcan4x5x_get_gpios(mcan_class, version_info);
+	ret = tcan4x5x_check_gpios(mcan_class, version_info);
 	if (ret) {
-		dev_err(&spi->dev, "Getting gpios failed %pe\n", ERR_PTR(ret));
+		dev_err(&spi->dev, "Checking gpios failed %pe\n", ERR_PTR(ret));
 		goto out_power;
 	}
 
+	tcan4x5x_get_dt_data(mcan_class);
+
 	tcan4x5x_check_wake(priv);
 
 	ret = tcan4x5x_write_tcan_reg(mcan_class, TCAN4X5X_INT_EN, 0);
diff --git a/drivers/net/can/m_can/tcan4x5x.h b/drivers/net/can/m_can/tcan4x5x.h
index e62c030d3e1e..203399d5e8cc 100644
--- a/drivers/net/can/m_can/tcan4x5x.h
+++ b/drivers/net/can/m_can/tcan4x5x.h
@@ -42,6 +42,8 @@ struct tcan4x5x_priv {
 
 	struct tcan4x5x_map_buf map_buf_rx;
 	struct tcan4x5x_map_buf map_buf_tx;
+
+	bool nwkrq_voltage_vio;
 };
 
 static inline void
diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c
index 8c2a7bc64d3d..39c7aa2a0b2f 100644
--- a/drivers/net/can/mscan/mscan.c
+++ b/drivers/net/can/mscan/mscan.c
@@ -607,7 +607,6 @@ static const struct net_device_ops mscan_netdev_ops = {
 	.ndo_open	= mscan_open,
 	.ndo_stop	= mscan_close,
 	.ndo_start_xmit	= mscan_start_xmit,
-	.ndo_change_mtu	= can_change_mtu,
 };
 
 static const struct ethtool_ops mscan_ethtool_ops = {
diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c
index 28f3fd805273..06cb2629f66a 100644
--- a/drivers/net/can/peak_canfd/peak_canfd.c
+++ b/drivers/net/can/peak_canfd/peak_canfd.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (C) 2007, 2011 Wolfgang Grandegger <wg@grandegger.com>
- * Copyright (C) 2012 Stephane Grosjean <s.grosjean@peak-system.com>
  *
- * Copyright (C) 2016  PEAK System-Technik GmbH
+ * Copyright (C) 2016-2025 PEAK System-Technik GmbH
+ * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
  */
 
 #include <linux/can.h>
@@ -624,7 +624,7 @@ static int peak_canfd_set_data_bittiming(struct net_device *ndev)
 {
 	struct peak_canfd_priv *priv = netdev_priv(ndev);
 
-	return pucan_set_timing_fast(priv, &priv->can.data_bittiming);
+	return pucan_set_timing_fast(priv, &priv->can.fd.data_bittiming);
 }
 
 static int peak_canfd_close(struct net_device *ndev)
@@ -743,37 +743,33 @@ static netdev_tx_t peak_canfd_start_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
-static int peak_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+static int peak_eth_hwtstamp_get(struct net_device *netdev,
+				 struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config hwts_cfg = { 0 };
+	config->tx_type = HWTSTAMP_TX_OFF;
+	config->rx_filter = HWTSTAMP_FILTER_ALL;
 
-	switch (cmd) {
-	case SIOCSHWTSTAMP: /* set */
-		if (copy_from_user(&hwts_cfg, ifr->ifr_data, sizeof(hwts_cfg)))
-			return -EFAULT;
-		if (hwts_cfg.tx_type == HWTSTAMP_TX_OFF &&
-		    hwts_cfg.rx_filter == HWTSTAMP_FILTER_ALL)
-			return 0;
-		return -ERANGE;
+	return 0;
+}
 
-	case SIOCGHWTSTAMP: /* get */
-		hwts_cfg.tx_type = HWTSTAMP_TX_OFF;
-		hwts_cfg.rx_filter = HWTSTAMP_FILTER_ALL;
-		if (copy_to_user(ifr->ifr_data, &hwts_cfg, sizeof(hwts_cfg)))
-			return -EFAULT;
+static int peak_eth_hwtstamp_set(struct net_device *netdev,
+				 struct kernel_hwtstamp_config *config,
+				 struct netlink_ext_ack *extack)
+{
+	if (config->tx_type == HWTSTAMP_TX_OFF &&
+	    config->rx_filter == HWTSTAMP_FILTER_ALL)
 		return 0;
 
-	default:
-		return -EOPNOTSUPP;
-	}
+	NL_SET_ERR_MSG_MOD(extack, "Only RX HWTSTAMP_FILTER_ALL is supported");
+	return -ERANGE;
 }
 
 static const struct net_device_ops peak_canfd_netdev_ops = {
 	.ndo_open = peak_canfd_open,
 	.ndo_stop = peak_canfd_close,
-	.ndo_eth_ioctl = peak_eth_ioctl,
 	.ndo_start_xmit = peak_canfd_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
+	.ndo_hwtstamp_get = peak_eth_hwtstamp_get,
+	.ndo_hwtstamp_set = peak_eth_hwtstamp_set,
 };
 
 static int peak_get_ts_info(struct net_device *dev,
@@ -813,12 +809,12 @@ struct net_device *alloc_peak_canfd_dev(int sizeof_priv, int index,
 	/* complete now socket-can initialization side */
 	priv->can.state = CAN_STATE_STOPPED;
 	priv->can.bittiming_const = &peak_canfd_nominal_const;
-	priv->can.data_bittiming_const = &peak_canfd_data_const;
+	priv->can.fd.data_bittiming_const = &peak_canfd_data_const;
 
 	priv->can.do_set_mode = peak_canfd_set_mode;
 	priv->can.do_get_berr_counter = peak_canfd_get_berr_counter;
 	priv->can.do_set_bittiming = peak_canfd_set_bittiming;
-	priv->can.do_set_data_bittiming = peak_canfd_set_data_bittiming;
+	priv->can.fd.do_set_data_bittiming = peak_canfd_set_data_bittiming;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 				       CAN_CTRLMODE_LISTENONLY |
 				       CAN_CTRLMODE_3_SAMPLES |
diff --git a/drivers/net/can/peak_canfd/peak_canfd_user.h b/drivers/net/can/peak_canfd/peak_canfd_user.h
index a72719dc3b74..60c6542028cf 100644
--- a/drivers/net/can/peak_canfd/peak_canfd_user.h
+++ b/drivers/net/can/peak_canfd/peak_canfd_user.h
@@ -1,8 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /* CAN driver for PEAK System micro-CAN based adapters
  *
- * Copyright (C) 2003-2011 PEAK System-Technik GmbH
- * Copyright (C) 2011-2013 Stephane Grosjean <s.grosjean@peak-system.com>
+ * Copyright (C) 2003-2025 PEAK System-Technik GmbH
+ * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
  */
 #ifndef PEAK_CANFD_USER_H
 #define PEAK_CANFD_USER_H
diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c
index 1df3c4b54f03..93558e33bc02 100644
--- a/drivers/net/can/peak_canfd/peak_pciefd_main.c
+++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c
@@ -1,10 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (C) 2007, 2011 Wolfgang Grandegger <wg@grandegger.com>
- * Copyright (C) 2012 Stephane Grosjean <s.grosjean@peak-system.com>
  *
  * Derived from the PCAN project file driver/src/pcan_pci.c:
  *
- * Copyright (C) 2001-2006  PEAK System-Technik GmbH
+ * Copyright (C) 2001-2025 PEAK System-Technik GmbH
+ * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
  */
 
 #include <linux/kernel.h>
@@ -19,7 +19,7 @@
 
 #include "peak_canfd_user.h"
 
-MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>");
+MODULE_AUTHOR("Stéphane Grosjean <stephane.grosjean@hms-networks.com>");
 MODULE_DESCRIPTION("Socket-CAN driver for PEAK PCAN PCIe/M.2 FD family cards");
 MODULE_LICENSE("GPL v2");
 
diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
index 2b7dd359f27b..fc3df328e877 100644
--- a/drivers/net/can/rcar/rcar_can.c
+++ b/drivers/net/can/rcar/rcar_can.c
@@ -5,6 +5,8 @@
  * Copyright (C) 2013 Renesas Solutions Corp.
  */
 
+#include <linux/bitfield.h>
+#include <linux/bits.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -16,6 +18,7 @@
 #include <linux/can/dev.h>
 #include <linux/clk.h>
 #include <linux/of.h>
+#include <linux/pm_runtime.h>
 
 #define RCAR_CAN_DRV_NAME	"rcar_can"
 
@@ -92,7 +95,6 @@ struct rcar_can_priv {
 	struct net_device *ndev;
 	struct napi_struct napi;
 	struct rcar_can_regs __iomem *regs;
-	struct clk *clk;
 	struct clk *can_clk;
 	u32 tx_head;
 	u32 tx_tail;
@@ -113,100 +115,102 @@ static const struct can_bittiming_const rcar_can_bittiming_const = {
 };
 
 /* Control Register bits */
-#define RCAR_CAN_CTLR_BOM	(3 << 11) /* Bus-Off Recovery Mode Bits */
-#define RCAR_CAN_CTLR_BOM_ENT	(1 << 11) /* Entry to halt mode */
-					/* at bus-off entry */
-#define RCAR_CAN_CTLR_SLPM	(1 << 10)
-#define RCAR_CAN_CTLR_CANM	(3 << 8) /* Operating Mode Select Bit */
-#define RCAR_CAN_CTLR_CANM_HALT	(1 << 9)
-#define RCAR_CAN_CTLR_CANM_RESET (1 << 8)
-#define RCAR_CAN_CTLR_CANM_FORCE_RESET (3 << 8)
-#define RCAR_CAN_CTLR_MLM	(1 << 3) /* Message Lost Mode Select */
-#define RCAR_CAN_CTLR_IDFM	(3 << 1) /* ID Format Mode Select Bits */
-#define RCAR_CAN_CTLR_IDFM_MIXED (1 << 2) /* Mixed ID mode */
-#define RCAR_CAN_CTLR_MBM	(1 << 0) /* Mailbox Mode select */
+#define RCAR_CAN_CTLR_BOM	GENMASK(12, 11)	/* Bus-Off Recovery Mode Bits */
+#define RCAR_CAN_CTLR_BOM_ENT		1	/* Entry to halt mode */
+						/* at bus-off entry */
+#define RCAR_CAN_CTLR_SLPM	BIT(10)		/* Sleep Mode */
+#define RCAR_CAN_CTLR_CANM	GENMASK(9, 8)	/* Operating Mode Select Bit */
+#define RCAR_CAN_CTLR_CANM_OPER		0	/* Operation Mode */
+#define RCAR_CAN_CTLR_CANM_RESET	1	/* Reset Mode */
+#define RCAR_CAN_CTLR_CANM_HALT		2	/* Halt Mode */
+#define RCAR_CAN_CTLR_CANM_FORCE_RESET	3	/* Reset Mode (forcible) */
+#define RCAR_CAN_CTLR_MLM	BIT(3)		/* Message Lost Mode Select */
+#define RCAR_CAN_CTLR_IDFM	GENMASK(2, 1)	/* ID Format Mode Select Bits */
+#define RCAR_CAN_CTLR_IDFM_STD		0	/* Standard ID mode */
+#define RCAR_CAN_CTLR_IDFM_EXT		1	/* Extended ID mode */
+#define RCAR_CAN_CTLR_IDFM_MIXED	2	/* Mixed ID mode */
+#define RCAR_CAN_CTLR_MBM	BIT(0)		/* Mailbox Mode select */
 
 /* Status Register bits */
-#define RCAR_CAN_STR_RSTST	(1 << 8) /* Reset Status Bit */
+#define RCAR_CAN_STR_RSTST	BIT(8)		/* Reset Status Bit */
 
 /* FIFO Received ID Compare Registers 0 and 1 bits */
-#define RCAR_CAN_FIDCR_IDE	(1 << 31) /* ID Extension Bit */
-#define RCAR_CAN_FIDCR_RTR	(1 << 30) /* Remote Transmission Request Bit */
+#define RCAR_CAN_FIDCR_IDE	BIT(31)		/* ID Extension Bit */
+#define RCAR_CAN_FIDCR_RTR	BIT(30)		/* Remote Transmission Request Bit */
 
 /* Receive FIFO Control Register bits */
-#define RCAR_CAN_RFCR_RFEST	(1 << 7) /* Receive FIFO Empty Status Flag */
-#define RCAR_CAN_RFCR_RFE	(1 << 0) /* Receive FIFO Enable */
+#define RCAR_CAN_RFCR_RFEST	BIT(7)		/* Receive FIFO Empty Status Flag */
+#define RCAR_CAN_RFCR_RFE	BIT(0)		/* Receive FIFO Enable */
 
 /* Transmit FIFO Control Register bits */
-#define RCAR_CAN_TFCR_TFUST	(7 << 1) /* Transmit FIFO Unsent Message */
-					/* Number Status Bits */
-#define RCAR_CAN_TFCR_TFUST_SHIFT 1	/* Offset of Transmit FIFO Unsent */
-					/* Message Number Status Bits */
-#define RCAR_CAN_TFCR_TFE	(1 << 0) /* Transmit FIFO Enable */
-
-#define RCAR_CAN_N_RX_MKREGS1	2	/* Number of mask registers */
-					/* for Rx mailboxes 0-31 */
+#define RCAR_CAN_TFCR_TFUST	GENMASK(3, 1)	/* Transmit FIFO Unsent Message */
+						/* Number Status Bits */
+#define RCAR_CAN_TFCR_TFE	BIT(0)		/* Transmit FIFO Enable */
+
+#define RCAR_CAN_N_RX_MKREGS1	2		/* Number of mask registers */
+						/* for Rx mailboxes 0-31 */
 #define RCAR_CAN_N_RX_MKREGS2	8
 
 /* Bit Configuration Register settings */
-#define RCAR_CAN_BCR_TSEG1(x)	(((x) & 0x0f) << 20)
-#define RCAR_CAN_BCR_BPR(x)	(((x) & 0x3ff) << 8)
-#define RCAR_CAN_BCR_SJW(x)	(((x) & 0x3) << 4)
-#define RCAR_CAN_BCR_TSEG2(x)	((x) & 0x07)
+#define RCAR_CAN_BCR_TSEG1	GENMASK(23, 20)
+#define RCAR_CAN_BCR_BRP	GENMASK(17, 8)
+#define RCAR_CAN_BCR_SJW	GENMASK(5, 4)
+#define RCAR_CAN_BCR_TSEG2	GENMASK(2, 0)
 
 /* Mailbox and Mask Registers bits */
-#define RCAR_CAN_IDE		(1 << 31)
-#define RCAR_CAN_RTR		(1 << 30)
-#define RCAR_CAN_SID_SHIFT	18
+#define RCAR_CAN_IDE		BIT(31)		/* ID Extension */
+#define RCAR_CAN_RTR		BIT(30)		/* Remote Transmission Request */
+#define RCAR_CAN_SID		GENMASK(28, 18)	/* Standard ID */
+#define RCAR_CAN_EID		GENMASK(28, 0)	/* Extended ID */
 
 /* Mailbox Interrupt Enable Register 1 bits */
-#define RCAR_CAN_MIER1_RXFIE	(1 << 28) /* Receive  FIFO Interrupt Enable */
-#define RCAR_CAN_MIER1_TXFIE	(1 << 24) /* Transmit FIFO Interrupt Enable */
+#define RCAR_CAN_MIER1_RXFIE	BIT(28)		/* Receive  FIFO Interrupt Enable */
+#define RCAR_CAN_MIER1_TXFIE	BIT(24)		/* Transmit FIFO Interrupt Enable */
 
 /* Interrupt Enable Register bits */
-#define RCAR_CAN_IER_ERSIE	(1 << 5) /* Error (ERS) Interrupt Enable Bit */
-#define RCAR_CAN_IER_RXFIE	(1 << 4) /* Reception FIFO Interrupt */
-					/* Enable Bit */
-#define RCAR_CAN_IER_TXFIE	(1 << 3) /* Transmission FIFO Interrupt */
-					/* Enable Bit */
+#define RCAR_CAN_IER_ERSIE	BIT(5)		/* Error (ERS) Interrupt Enable Bit */
+#define RCAR_CAN_IER_RXFIE	BIT(4)		/* Reception FIFO Interrupt */
+						/* Enable Bit */
+#define RCAR_CAN_IER_TXFIE	BIT(3)		/* Transmission FIFO Interrupt */
+						/* Enable Bit */
 /* Interrupt Status Register bits */
-#define RCAR_CAN_ISR_ERSF	(1 << 5) /* Error (ERS) Interrupt Status Bit */
-#define RCAR_CAN_ISR_RXFF	(1 << 4) /* Reception FIFO Interrupt */
-					/* Status Bit */
-#define RCAR_CAN_ISR_TXFF	(1 << 3) /* Transmission FIFO Interrupt */
-					/* Status Bit */
+#define RCAR_CAN_ISR_ERSF	BIT(5)		/* Error (ERS) Interrupt Status Bit */
+#define RCAR_CAN_ISR_RXFF	BIT(4)		/* Reception FIFO Interrupt */
+						/* Status Bit */
+#define RCAR_CAN_ISR_TXFF	BIT(3)		/* Transmission FIFO Interrupt */
+						/* Status Bit */
 
 /* Error Interrupt Enable Register bits */
-#define RCAR_CAN_EIER_BLIE	(1 << 7) /* Bus Lock Interrupt Enable */
-#define RCAR_CAN_EIER_OLIE	(1 << 6) /* Overload Frame Transmit */
-					/* Interrupt Enable */
-#define RCAR_CAN_EIER_ORIE	(1 << 5) /* Receive Overrun  Interrupt Enable */
-#define RCAR_CAN_EIER_BORIE	(1 << 4) /* Bus-Off Recovery Interrupt Enable */
-#define RCAR_CAN_EIER_BOEIE	(1 << 3) /* Bus-Off Entry Interrupt Enable */
-#define RCAR_CAN_EIER_EPIE	(1 << 2) /* Error Passive Interrupt Enable */
-#define RCAR_CAN_EIER_EWIE	(1 << 1) /* Error Warning Interrupt Enable */
-#define RCAR_CAN_EIER_BEIE	(1 << 0) /* Bus Error Interrupt Enable */
+#define RCAR_CAN_EIER_BLIE	BIT(7)		/* Bus Lock Interrupt Enable */
+#define RCAR_CAN_EIER_OLIE	BIT(6)		/* Overload Frame Transmit */
+						/* Interrupt Enable */
+#define RCAR_CAN_EIER_ORIE	BIT(5)		/* Receive Overrun  Interrupt Enable */
+#define RCAR_CAN_EIER_BORIE	BIT(4)		/* Bus-Off Recovery Interrupt Enable */
+#define RCAR_CAN_EIER_BOEIE	BIT(3)		/* Bus-Off Entry Interrupt Enable */
+#define RCAR_CAN_EIER_EPIE	BIT(2)		/* Error Passive Interrupt Enable */
+#define RCAR_CAN_EIER_EWIE	BIT(1)		/* Error Warning Interrupt Enable */
+#define RCAR_CAN_EIER_BEIE	BIT(0)		/* Bus Error Interrupt Enable */
 
 /* Error Interrupt Factor Judge Register bits */
-#define RCAR_CAN_EIFR_BLIF	(1 << 7) /* Bus Lock Detect Flag */
-#define RCAR_CAN_EIFR_OLIF	(1 << 6) /* Overload Frame Transmission */
-					 /* Detect Flag */
-#define RCAR_CAN_EIFR_ORIF	(1 << 5) /* Receive Overrun Detect Flag */
-#define RCAR_CAN_EIFR_BORIF	(1 << 4) /* Bus-Off Recovery Detect Flag */
-#define RCAR_CAN_EIFR_BOEIF	(1 << 3) /* Bus-Off Entry Detect Flag */
-#define RCAR_CAN_EIFR_EPIF	(1 << 2) /* Error Passive Detect Flag */
-#define RCAR_CAN_EIFR_EWIF	(1 << 1) /* Error Warning Detect Flag */
-#define RCAR_CAN_EIFR_BEIF	(1 << 0) /* Bus Error Detect Flag */
+#define RCAR_CAN_EIFR_BLIF	BIT(7)		/* Bus Lock Detect Flag */
+#define RCAR_CAN_EIFR_OLIF	BIT(6)		/* Overload Frame Transmission */
+						/* Detect Flag */
+#define RCAR_CAN_EIFR_ORIF	BIT(5)		/* Receive Overrun Detect Flag */
+#define RCAR_CAN_EIFR_BORIF	BIT(4)		/* Bus-Off Recovery Detect Flag */
+#define RCAR_CAN_EIFR_BOEIF	BIT(3)		/* Bus-Off Entry Detect Flag */
+#define RCAR_CAN_EIFR_EPIF	BIT(2)		/* Error Passive Detect Flag */
+#define RCAR_CAN_EIFR_EWIF	BIT(1)		/* Error Warning Detect Flag */
+#define RCAR_CAN_EIFR_BEIF	BIT(0)		/* Bus Error Detect Flag */
 
 /* Error Code Store Register bits */
-#define RCAR_CAN_ECSR_EDPM	(1 << 7) /* Error Display Mode Select Bit */
-#define RCAR_CAN_ECSR_ADEF	(1 << 6) /* ACK Delimiter Error Flag */
-#define RCAR_CAN_ECSR_BE0F	(1 << 5) /* Bit Error (dominant) Flag */
-#define RCAR_CAN_ECSR_BE1F	(1 << 4) /* Bit Error (recessive) Flag */
-#define RCAR_CAN_ECSR_CEF	(1 << 3) /* CRC Error Flag */
-#define RCAR_CAN_ECSR_AEF	(1 << 2) /* ACK Error Flag */
-#define RCAR_CAN_ECSR_FEF	(1 << 1) /* Form Error Flag */
-#define RCAR_CAN_ECSR_SEF	(1 << 0) /* Stuff Error Flag */
+#define RCAR_CAN_ECSR_EDPM	BIT(7)		/* Error Display Mode Select Bit */
+#define RCAR_CAN_ECSR_ADEF	BIT(6)		/* ACK Delimiter Error Flag */
+#define RCAR_CAN_ECSR_BE0F	BIT(5)		/* Bit Error (dominant) Flag */
+#define RCAR_CAN_ECSR_BE1F	BIT(4)		/* Bit Error (recessive) Flag */
+#define RCAR_CAN_ECSR_CEF	BIT(3)		/* CRC Error Flag */
+#define RCAR_CAN_ECSR_AEF	BIT(2)		/* ACK Error Flag */
+#define RCAR_CAN_ECSR_FEF	BIT(1)		/* Form Error Flag */
+#define RCAR_CAN_ECSR_SEF	BIT(0)		/* Stuff Error Flag */
 
 #define RCAR_CAN_NAPI_WEIGHT	4
 #define MAX_STR_READS		0x100
@@ -248,35 +252,35 @@ static void rcar_can_error(struct net_device *ndev)
 		if (ecsr & RCAR_CAN_ECSR_ADEF) {
 			netdev_dbg(priv->ndev, "ACK Delimiter Error\n");
 			tx_errors++;
-			writeb(~RCAR_CAN_ECSR_ADEF, &priv->regs->ecsr);
+			writeb((u8)~RCAR_CAN_ECSR_ADEF, &priv->regs->ecsr);
 			if (skb)
 				cf->data[3] = CAN_ERR_PROT_LOC_ACK_DEL;
 		}
 		if (ecsr & RCAR_CAN_ECSR_BE0F) {
 			netdev_dbg(priv->ndev, "Bit Error (dominant)\n");
 			tx_errors++;
-			writeb(~RCAR_CAN_ECSR_BE0F, &priv->regs->ecsr);
+			writeb((u8)~RCAR_CAN_ECSR_BE0F, &priv->regs->ecsr);
 			if (skb)
 				cf->data[2] |= CAN_ERR_PROT_BIT0;
 		}
 		if (ecsr & RCAR_CAN_ECSR_BE1F) {
 			netdev_dbg(priv->ndev, "Bit Error (recessive)\n");
 			tx_errors++;
-			writeb(~RCAR_CAN_ECSR_BE1F, &priv->regs->ecsr);
+			writeb((u8)~RCAR_CAN_ECSR_BE1F, &priv->regs->ecsr);
 			if (skb)
 				cf->data[2] |= CAN_ERR_PROT_BIT1;
 		}
 		if (ecsr & RCAR_CAN_ECSR_CEF) {
 			netdev_dbg(priv->ndev, "CRC Error\n");
 			rx_errors++;
-			writeb(~RCAR_CAN_ECSR_CEF, &priv->regs->ecsr);
+			writeb((u8)~RCAR_CAN_ECSR_CEF, &priv->regs->ecsr);
 			if (skb)
 				cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
 		}
 		if (ecsr & RCAR_CAN_ECSR_AEF) {
 			netdev_dbg(priv->ndev, "ACK Error\n");
 			tx_errors++;
-			writeb(~RCAR_CAN_ECSR_AEF, &priv->regs->ecsr);
+			writeb((u8)~RCAR_CAN_ECSR_AEF, &priv->regs->ecsr);
 			if (skb) {
 				cf->can_id |= CAN_ERR_ACK;
 				cf->data[3] = CAN_ERR_PROT_LOC_ACK;
@@ -285,14 +289,14 @@ static void rcar_can_error(struct net_device *ndev)
 		if (ecsr & RCAR_CAN_ECSR_FEF) {
 			netdev_dbg(priv->ndev, "Form Error\n");
 			rx_errors++;
-			writeb(~RCAR_CAN_ECSR_FEF, &priv->regs->ecsr);
+			writeb((u8)~RCAR_CAN_ECSR_FEF, &priv->regs->ecsr);
 			if (skb)
 				cf->data[2] |= CAN_ERR_PROT_FORM;
 		}
 		if (ecsr & RCAR_CAN_ECSR_SEF) {
 			netdev_dbg(priv->ndev, "Stuff Error\n");
 			rx_errors++;
-			writeb(~RCAR_CAN_ECSR_SEF, &priv->regs->ecsr);
+			writeb((u8)~RCAR_CAN_ECSR_SEF, &priv->regs->ecsr);
 			if (skb)
 				cf->data[2] |= CAN_ERR_PROT_STUFF;
 		}
@@ -300,14 +304,14 @@ static void rcar_can_error(struct net_device *ndev)
 		priv->can.can_stats.bus_error++;
 		ndev->stats.rx_errors += rx_errors;
 		ndev->stats.tx_errors += tx_errors;
-		writeb(~RCAR_CAN_EIFR_BEIF, &priv->regs->eifr);
+		writeb((u8)~RCAR_CAN_EIFR_BEIF, &priv->regs->eifr);
 	}
 	if (eifr & RCAR_CAN_EIFR_EWIF) {
 		netdev_dbg(priv->ndev, "Error warning interrupt\n");
 		priv->can.state = CAN_STATE_ERROR_WARNING;
 		priv->can.can_stats.error_warning++;
 		/* Clear interrupt condition */
-		writeb(~RCAR_CAN_EIFR_EWIF, &priv->regs->eifr);
+		writeb((u8)~RCAR_CAN_EIFR_EWIF, &priv->regs->eifr);
 		if (skb)
 			cf->data[1] = txerr > rxerr ? CAN_ERR_CRTL_TX_WARNING :
 					      CAN_ERR_CRTL_RX_WARNING;
@@ -317,7 +321,7 @@ static void rcar_can_error(struct net_device *ndev)
 		priv->can.state = CAN_STATE_ERROR_PASSIVE;
 		priv->can.can_stats.error_passive++;
 		/* Clear interrupt condition */
-		writeb(~RCAR_CAN_EIFR_EPIF, &priv->regs->eifr);
+		writeb((u8)~RCAR_CAN_EIFR_EPIF, &priv->regs->eifr);
 		if (skb)
 			cf->data[1] = txerr > rxerr ? CAN_ERR_CRTL_TX_PASSIVE :
 					      CAN_ERR_CRTL_RX_PASSIVE;
@@ -329,7 +333,7 @@ static void rcar_can_error(struct net_device *ndev)
 		writeb(priv->ier, &priv->regs->ier);
 		priv->can.state = CAN_STATE_BUS_OFF;
 		/* Clear interrupt condition */
-		writeb(~RCAR_CAN_EIFR_BOEIF, &priv->regs->eifr);
+		writeb((u8)~RCAR_CAN_EIFR_BOEIF, &priv->regs->eifr);
 		priv->can.can_stats.bus_off++;
 		can_bus_off(ndev);
 		if (skb)
@@ -343,7 +347,7 @@ static void rcar_can_error(struct net_device *ndev)
 		netdev_dbg(priv->ndev, "Receive overrun error interrupt\n");
 		ndev->stats.rx_over_errors++;
 		ndev->stats.rx_errors++;
-		writeb(~RCAR_CAN_EIFR_ORIF, &priv->regs->eifr);
+		writeb((u8)~RCAR_CAN_EIFR_ORIF, &priv->regs->eifr);
 		if (skb) {
 			cf->can_id |= CAN_ERR_CRTL;
 			cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
@@ -354,7 +358,7 @@ static void rcar_can_error(struct net_device *ndev)
 			   "Overload Frame Transmission error interrupt\n");
 		ndev->stats.rx_over_errors++;
 		ndev->stats.rx_errors++;
-		writeb(~RCAR_CAN_EIFR_OLIF, &priv->regs->eifr);
+		writeb((u8)~RCAR_CAN_EIFR_OLIF, &priv->regs->eifr);
 		if (skb) {
 			cf->can_id |= CAN_ERR_PROT;
 			cf->data[2] |= CAN_ERR_PROT_OVERLOAD;
@@ -372,10 +376,9 @@ static void rcar_can_tx_done(struct net_device *ndev)
 	u8 isr;
 
 	while (1) {
-		u8 unsent = readb(&priv->regs->tfcr);
+		u8 unsent = FIELD_GET(RCAR_CAN_TFCR_TFUST,
+			    readb(&priv->regs->tfcr));
 
-		unsent = (unsent & RCAR_CAN_TFCR_TFUST) >>
-			  RCAR_CAN_TFCR_TFUST_SHIFT;
 		if (priv->tx_head - priv->tx_tail <= unsent)
 			break;
 		stats->tx_packets++;
@@ -420,15 +423,16 @@ static irqreturn_t rcar_can_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static void rcar_can_set_bittiming(struct net_device *dev)
+static void rcar_can_set_bittiming(struct net_device *ndev)
 {
-	struct rcar_can_priv *priv = netdev_priv(dev);
+	struct rcar_can_priv *priv = netdev_priv(ndev);
 	struct can_bittiming *bt = &priv->can.bittiming;
 	u32 bcr;
 
-	bcr = RCAR_CAN_BCR_TSEG1(bt->phase_seg1 + bt->prop_seg - 1) |
-	      RCAR_CAN_BCR_BPR(bt->brp - 1) | RCAR_CAN_BCR_SJW(bt->sjw - 1) |
-	      RCAR_CAN_BCR_TSEG2(bt->phase_seg2 - 1);
+	bcr = FIELD_PREP(RCAR_CAN_BCR_TSEG1, bt->phase_seg1 + bt->prop_seg - 1) |
+	      FIELD_PREP(RCAR_CAN_BCR_BRP, bt->brp - 1) |
+	      FIELD_PREP(RCAR_CAN_BCR_SJW, bt->sjw - 1) |
+	      FIELD_PREP(RCAR_CAN_BCR_TSEG2, bt->phase_seg2 - 1);
 	/* Don't overwrite CLKR with 32-bit BCR access; CLKR has 8-bit access.
 	 * All the registers are big-endian but they get byte-swapped on 32-bit
 	 * read/write (but not on 8-bit, contrary to the manuals)...
@@ -452,16 +456,17 @@ static void rcar_can_start(struct net_device *ndev)
 	ctlr &= ~RCAR_CAN_CTLR_SLPM;
 	writew(ctlr, &priv->regs->ctlr);
 	/* Go to reset mode */
-	ctlr |= RCAR_CAN_CTLR_CANM_FORCE_RESET;
+	ctlr |= FIELD_PREP(RCAR_CAN_CTLR_CANM, RCAR_CAN_CTLR_CANM_FORCE_RESET);
 	writew(ctlr, &priv->regs->ctlr);
 	for (i = 0; i < MAX_STR_READS; i++) {
 		if (readw(&priv->regs->str) & RCAR_CAN_STR_RSTST)
 			break;
 	}
 	rcar_can_set_bittiming(ndev);
-	ctlr |= RCAR_CAN_CTLR_IDFM_MIXED; /* Select mixed ID mode */
-	ctlr |= RCAR_CAN_CTLR_BOM_ENT;	/* Entry to halt mode automatically */
-					/* at bus-off */
+	/* Select mixed ID mode */
+	ctlr |= FIELD_PREP(RCAR_CAN_CTLR_IDFM, RCAR_CAN_CTLR_IDFM_MIXED);
+	/* Entry to halt mode automatically at bus-off */
+	ctlr |= FIELD_PREP(RCAR_CAN_CTLR_BOM, RCAR_CAN_CTLR_BOM_ENT);
 	ctlr |= RCAR_CAN_CTLR_MBM;	/* Select FIFO mailbox mode */
 	ctlr |= RCAR_CAN_CTLR_MLM;	/* Overrun mode */
 	writew(ctlr, &priv->regs->ctlr);
@@ -491,7 +496,9 @@ static void rcar_can_start(struct net_device *ndev)
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 
 	/* Go to operation mode */
-	writew(ctlr & ~RCAR_CAN_CTLR_CANM, &priv->regs->ctlr);
+	ctlr &= ~RCAR_CAN_CTLR_CANM;
+	ctlr |= FIELD_PREP(RCAR_CAN_CTLR_CANM, RCAR_CAN_CTLR_CANM_OPER);
+	writew(ctlr, &priv->regs->ctlr);
 	for (i = 0; i < MAX_STR_READS; i++) {
 		if (!(readw(&priv->regs->str) & RCAR_CAN_STR_RSTST))
 			break;
@@ -506,29 +513,28 @@ static int rcar_can_open(struct net_device *ndev)
 	struct rcar_can_priv *priv = netdev_priv(ndev);
 	int err;
 
-	err = clk_prepare_enable(priv->clk);
+	err = pm_runtime_resume_and_get(ndev->dev.parent);
 	if (err) {
-		netdev_err(ndev,
-			   "failed to enable peripheral clock, error %d\n",
-			   err);
+		netdev_err(ndev, "pm_runtime_resume_and_get() failed %pe\n",
+			   ERR_PTR(err));
 		goto out;
 	}
 	err = clk_prepare_enable(priv->can_clk);
 	if (err) {
-		netdev_err(ndev, "failed to enable CAN clock, error %d\n",
-			   err);
-		goto out_clock;
+		netdev_err(ndev, "failed to enable CAN clock: %pe\n",
+			   ERR_PTR(err));
+		goto out_rpm;
 	}
 	err = open_candev(ndev);
 	if (err) {
-		netdev_err(ndev, "open_candev() failed, error %d\n", err);
+		netdev_err(ndev, "open_candev() failed %pe\n", ERR_PTR(err));
 		goto out_can_clock;
 	}
 	napi_enable(&priv->napi);
 	err = request_irq(ndev->irq, rcar_can_interrupt, 0, ndev->name, ndev);
 	if (err) {
-		netdev_err(ndev, "request_irq(%d) failed, error %d\n",
-			   ndev->irq, err);
+		netdev_err(ndev, "request_irq(%d) failed %pe\n", ndev->irq,
+			   ERR_PTR(err));
 		goto out_close;
 	}
 	rcar_can_start(ndev);
@@ -539,8 +545,8 @@ out_close:
 	close_candev(ndev);
 out_can_clock:
 	clk_disable_unprepare(priv->can_clk);
-out_clock:
-	clk_disable_unprepare(priv->clk);
+out_rpm:
+	pm_runtime_put(ndev->dev.parent);
 out:
 	return err;
 }
@@ -553,7 +559,7 @@ static void rcar_can_stop(struct net_device *ndev)
 
 	/* Go to (force) reset mode */
 	ctlr = readw(&priv->regs->ctlr);
-	ctlr |= RCAR_CAN_CTLR_CANM_FORCE_RESET;
+	ctlr |= FIELD_PREP(RCAR_CAN_CTLR_CANM, RCAR_CAN_CTLR_CANM_FORCE_RESET);
 	writew(ctlr, &priv->regs->ctlr);
 	for (i = 0; i < MAX_STR_READS; i++) {
 		if (readw(&priv->regs->str) & RCAR_CAN_STR_RSTST)
@@ -578,7 +584,7 @@ static int rcar_can_close(struct net_device *ndev)
 	free_irq(ndev->irq, ndev);
 	napi_disable(&priv->napi);
 	clk_disable_unprepare(priv->can_clk);
-	clk_disable_unprepare(priv->clk);
+	pm_runtime_put(ndev->dev.parent);
 	close_candev(ndev);
 	return 0;
 }
@@ -594,9 +600,10 @@ static netdev_tx_t rcar_can_start_xmit(struct sk_buff *skb,
 		return NETDEV_TX_OK;
 
 	if (cf->can_id & CAN_EFF_FLAG)	/* Extended frame format */
-		data = (cf->can_id & CAN_EFF_MASK) | RCAR_CAN_IDE;
+		data = FIELD_PREP(RCAR_CAN_EID, cf->can_id & CAN_EFF_MASK) |
+		       RCAR_CAN_IDE;
 	else				/* Standard frame format */
-		data = (cf->can_id & CAN_SFF_MASK) << RCAR_CAN_SID_SHIFT;
+		data = FIELD_PREP(RCAR_CAN_SID, cf->can_id & CAN_SFF_MASK);
 
 	if (cf->can_id & CAN_RTR_FLAG) { /* Remote transmission request */
 		data |= RCAR_CAN_RTR;
@@ -628,7 +635,6 @@ static const struct net_device_ops rcar_can_netdev_ops = {
 	.ndo_open = rcar_can_open,
 	.ndo_stop = rcar_can_close,
 	.ndo_start_xmit = rcar_can_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops rcar_can_ethtool_ops = {
@@ -651,9 +657,9 @@ static void rcar_can_rx_pkt(struct rcar_can_priv *priv)
 
 	data = readl(&priv->regs->mb[RCAR_CAN_RX_FIFO_MBX].id);
 	if (data & RCAR_CAN_IDE)
-		cf->can_id = (data & CAN_EFF_MASK) | CAN_EFF_FLAG;
+		cf->can_id = FIELD_GET(RCAR_CAN_EID, data) | CAN_EFF_FLAG;
 	else
-		cf->can_id = (data >> RCAR_CAN_SID_SHIFT) & CAN_SFF_MASK;
+		cf->can_id = FIELD_GET(RCAR_CAN_SID, data);
 
 	dlc = readb(&priv->regs->mb[RCAR_CAN_RX_FIFO_MBX].dlc);
 	cf->len = can_cc_dlc2len(dlc);
@@ -715,18 +721,21 @@ static int rcar_can_do_set_mode(struct net_device *ndev, enum can_mode mode)
 	}
 }
 
-static int rcar_can_get_berr_counter(const struct net_device *dev,
+static int rcar_can_get_berr_counter(const struct net_device *ndev,
 				     struct can_berr_counter *bec)
 {
-	struct rcar_can_priv *priv = netdev_priv(dev);
+	struct rcar_can_priv *priv = netdev_priv(ndev);
 	int err;
 
-	err = clk_prepare_enable(priv->clk);
+	err = pm_runtime_resume_and_get(ndev->dev.parent);
 	if (err)
 		return err;
+
 	bec->txerr = readb(&priv->regs->tecr);
 	bec->rxerr = readb(&priv->regs->recr);
-	clk_disable_unprepare(priv->clk);
+
+	pm_runtime_put(ndev->dev.parent);
+
 	return 0;
 }
 
@@ -738,6 +747,7 @@ static const char * const clock_names[] = {
 
 static int rcar_can_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	struct rcar_can_priv *priv;
 	struct net_device *ndev;
 	void __iomem *addr;
@@ -745,7 +755,7 @@ static int rcar_can_probe(struct platform_device *pdev)
 	int err = -ENODEV;
 	int irq;
 
-	of_property_read_u32(pdev->dev.of_node, "renesas,can-clock-select",
+	of_property_read_u32(dev->of_node, "renesas,can-clock-select",
 			     &clock_select);
 
 	irq = platform_get_irq(pdev, 0);
@@ -762,30 +772,21 @@ static int rcar_can_probe(struct platform_device *pdev)
 
 	ndev = alloc_candev(sizeof(struct rcar_can_priv), RCAR_CAN_FIFO_DEPTH);
 	if (!ndev) {
-		dev_err(&pdev->dev, "alloc_candev() failed\n");
 		err = -ENOMEM;
 		goto fail;
 	}
 
 	priv = netdev_priv(ndev);
 
-	priv->clk = devm_clk_get(&pdev->dev, "clkp1");
-	if (IS_ERR(priv->clk)) {
-		err = PTR_ERR(priv->clk);
-		dev_err(&pdev->dev, "cannot get peripheral clock, error %d\n",
-			err);
-		goto fail_clk;
-	}
-
 	if (!(BIT(clock_select) & RCAR_SUPPORTED_CLOCKS)) {
 		err = -EINVAL;
-		dev_err(&pdev->dev, "invalid CAN clock selected\n");
+		dev_err(dev, "invalid CAN clock selected\n");
 		goto fail_clk;
 	}
-	priv->can_clk = devm_clk_get(&pdev->dev, clock_names[clock_select]);
+	priv->can_clk = devm_clk_get(dev, clock_names[clock_select]);
 	if (IS_ERR(priv->can_clk)) {
+		dev_err(dev, "cannot get CAN clock: %pe\n", priv->can_clk);
 		err = PTR_ERR(priv->can_clk);
-		dev_err(&pdev->dev, "cannot get CAN clock, error %d\n", err);
 		goto fail_clk;
 	}
 
@@ -802,21 +803,24 @@ static int rcar_can_probe(struct platform_device *pdev)
 	priv->can.do_get_berr_counter = rcar_can_get_berr_counter;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_BERR_REPORTING;
 	platform_set_drvdata(pdev, ndev);
-	SET_NETDEV_DEV(ndev, &pdev->dev);
+	SET_NETDEV_DEV(ndev, dev);
 
 	netif_napi_add_weight(ndev, &priv->napi, rcar_can_rx_poll,
 			      RCAR_CAN_NAPI_WEIGHT);
+
+	pm_runtime_enable(dev);
+
 	err = register_candev(ndev);
 	if (err) {
-		dev_err(&pdev->dev, "register_candev() failed, error %d\n",
-			err);
-		goto fail_candev;
+		dev_err(dev, "register_candev() failed %pe\n", ERR_PTR(err));
+		goto fail_rpm;
 	}
 
-	dev_info(&pdev->dev, "device registered (IRQ%d)\n", ndev->irq);
+	dev_info(dev, "device registered (IRQ%d)\n", ndev->irq);
 
 	return 0;
-fail_candev:
+fail_rpm:
+	pm_runtime_disable(dev);
 	netif_napi_del(&priv->napi);
 fail_clk:
 	free_candev(ndev);
@@ -830,11 +834,12 @@ static void rcar_can_remove(struct platform_device *pdev)
 	struct rcar_can_priv *priv = netdev_priv(ndev);
 
 	unregister_candev(ndev);
+	pm_runtime_disable(&pdev->dev);
 	netif_napi_del(&priv->napi);
 	free_candev(ndev);
 }
 
-static int __maybe_unused rcar_can_suspend(struct device *dev)
+static int rcar_can_suspend(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct rcar_can_priv *priv = netdev_priv(ndev);
@@ -847,38 +852,32 @@ static int __maybe_unused rcar_can_suspend(struct device *dev)
 	netif_device_detach(ndev);
 
 	ctlr = readw(&priv->regs->ctlr);
-	ctlr |= RCAR_CAN_CTLR_CANM_HALT;
+	ctlr |= FIELD_PREP(RCAR_CAN_CTLR_CANM, RCAR_CAN_CTLR_CANM_HALT);
 	writew(ctlr, &priv->regs->ctlr);
 	ctlr |= RCAR_CAN_CTLR_SLPM;
 	writew(ctlr, &priv->regs->ctlr);
 	priv->can.state = CAN_STATE_SLEEPING;
 
-	clk_disable(priv->clk);
+	pm_runtime_put(dev);
 	return 0;
 }
 
-static int __maybe_unused rcar_can_resume(struct device *dev)
+static int rcar_can_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
-	struct rcar_can_priv *priv = netdev_priv(ndev);
-	u16 ctlr;
 	int err;
 
 	if (!netif_running(ndev))
 		return 0;
 
-	err = clk_enable(priv->clk);
+	err = pm_runtime_resume_and_get(dev);
 	if (err) {
-		netdev_err(ndev, "clk_enable() failed, error %d\n", err);
+		netdev_err(ndev, "pm_runtime_resume_and_get() failed %pe\n",
+			   ERR_PTR(err));
 		return err;
 	}
 
-	ctlr = readw(&priv->regs->ctlr);
-	ctlr &= ~RCAR_CAN_CTLR_SLPM;
-	writew(ctlr, &priv->regs->ctlr);
-	ctlr &= ~RCAR_CAN_CTLR_CANM;
-	writew(ctlr, &priv->regs->ctlr);
-	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+	rcar_can_start(ndev);
 
 	netif_device_attach(ndev);
 	netif_start_queue(ndev);
@@ -886,7 +885,8 @@ static int __maybe_unused rcar_can_resume(struct device *dev)
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(rcar_can_pm_ops, rcar_can_suspend, rcar_can_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(rcar_can_pm_ops, rcar_can_suspend,
+				rcar_can_resume);
 
 static const struct of_device_id rcar_can_of_table[] __maybe_unused = {
 	{ .compatible = "renesas,can-r8a7778" },
@@ -904,7 +904,7 @@ static struct platform_driver rcar_can_driver = {
 	.driver = {
 		.name = RCAR_CAN_DRV_NAME,
 		.of_match_table = of_match_ptr(rcar_can_of_table),
-		.pm = &rcar_can_pm_ops,
+		.pm = pm_sleep_ptr(&rcar_can_pm_ops),
 	},
 	.probe = rcar_can_probe,
 	.remove = rcar_can_remove,
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index df1a5d0b37b2..7895e1fdea1c 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -21,6 +21,7 @@
  * wherever it is modified to a readable name.
  */
 
+#include <linux/bitfield.h>
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
 #include <linux/can/dev.h>
@@ -74,33 +75,24 @@
 #define RCANFD_GSTS_GNOPM		(BIT(0) | BIT(1) | BIT(2) | BIT(3))
 
 /* RSCFDnCFDGERFL / RSCFDnGERFL */
-#define RCANFD_GERFL_EEF0_7		GENMASK(23, 16)
-#define RCANFD_GERFL_EEF(ch)		BIT(16 + (ch))
+#define RCANFD_GERFL_EEF		GENMASK(23, 16)
 #define RCANFD_GERFL_CMPOF		BIT(3)	/* CAN FD only */
 #define RCANFD_GERFL_THLES		BIT(2)
 #define RCANFD_GERFL_MES		BIT(1)
 #define RCANFD_GERFL_DEF		BIT(0)
 
 #define RCANFD_GERFL_ERR(gpriv, x) \
-	((x) & (reg_gen4(gpriv, RCANFD_GERFL_EEF0_7, \
-			 RCANFD_GERFL_EEF(0) | RCANFD_GERFL_EEF(1)) | \
-		RCANFD_GERFL_MES | \
-		((gpriv)->fdmode ? RCANFD_GERFL_CMPOF : 0)))
+({\
+	typeof(gpriv) (_gpriv) = (gpriv); \
+	((x) & ((FIELD_PREP(RCANFD_GERFL_EEF, (_gpriv)->channels_mask)) | \
+		RCANFD_GERFL_MES | ((_gpriv)->fdmode ? RCANFD_GERFL_CMPOF : 0))); \
+})
 
 /* AFL Rx rules registers */
 
-/* RSCFDnCFDGAFLCFG0 / RSCFDnGAFLCFG0 */
-#define RCANFD_GAFLCFG_SETRNC(gpriv, n, x) \
-	(((x) & reg_gen4(gpriv, 0x1ff, 0xff)) << \
-	 (reg_gen4(gpriv, 16, 24) - ((n) & 1) * reg_gen4(gpriv, 16, 8)))
-
-#define RCANFD_GAFLCFG_GETRNC(gpriv, n, x) \
-	(((x) >> (reg_gen4(gpriv, 16, 24) - ((n) & 1) * reg_gen4(gpriv, 16, 8))) & \
-	 reg_gen4(gpriv, 0x1ff, 0xff))
-
 /* RSCFDnCFDGAFLECTR / RSCFDnGAFLECTR */
 #define RCANFD_GAFLECTR_AFLDAE		BIT(8)
-#define RCANFD_GAFLECTR_AFLPN(gpriv, x)	((x) & reg_gen4(gpriv, 0x7f, 0x1f))
+#define RCANFD_GAFLECTR_AFLPN(gpriv, page_num)	((page_num) & (gpriv)->info->max_aflpn)
 
 /* RSCFDnCFDGAFLIDj / RSCFDnGAFLIDj */
 #define RCANFD_GAFLID_GAFLLB		BIT(29)
@@ -111,22 +103,13 @@
 /* Channel register bits */
 
 /* RSCFDnCmCFG - Classical CAN only */
-#define RCANFD_CFG_SJW(x)		(((x) & 0x3) << 24)
-#define RCANFD_CFG_TSEG2(x)		(((x) & 0x7) << 20)
-#define RCANFD_CFG_TSEG1(x)		(((x) & 0xf) << 16)
-#define RCANFD_CFG_BRP(x)		(((x) & 0x3ff) << 0)
+#define RCANFD_CFG_SJW		GENMASK(25, 24)
+#define RCANFD_CFG_TSEG2	GENMASK(22, 20)
+#define RCANFD_CFG_TSEG1	GENMASK(19, 16)
+#define RCANFD_CFG_BRP		GENMASK(9, 0)
 
 /* RSCFDnCFDCmNCFG - CAN FD only */
-#define RCANFD_NCFG_NTSEG2(gpriv, x) \
-	(((x) & reg_gen4(gpriv, 0x7f, 0x1f)) << reg_gen4(gpriv, 25, 24))
-
-#define RCANFD_NCFG_NTSEG1(gpriv, x) \
-	(((x) & reg_gen4(gpriv, 0xff, 0x7f)) << reg_gen4(gpriv, 17, 16))
-
-#define RCANFD_NCFG_NSJW(gpriv, x) \
-	(((x) & reg_gen4(gpriv, 0x7f, 0x1f)) << reg_gen4(gpriv, 10, 11))
-
-#define RCANFD_NCFG_NBRP(x)		(((x) & 0x3ff) << 0)
+#define RCANFD_NCFG_NBRP	GENMASK(9, 0)
 
 /* RSCFDnCFDCmCTR / RSCFDnCmCTR */
 #define RCANFD_CCTR_CTME		BIT(24)
@@ -186,22 +169,24 @@
 #define RCANFD_CERFL_ERR(x)		((x) & (0x7fff)) /* above bits 14:0 */
 
 /* RSCFDnCFDCmDCFG */
-#define RCANFD_DCFG_DSJW(gpriv, x)	(((x) & reg_gen4(gpriv, 0xf, 0x7)) << 24)
-
-#define RCANFD_DCFG_DTSEG2(gpriv, x) \
-	(((x) & reg_gen4(gpriv, 0x0f, 0x7)) << reg_gen4(gpriv, 16, 20))
-
-#define RCANFD_DCFG_DTSEG1(gpriv, x) \
-	(((x) & reg_gen4(gpriv, 0x1f, 0xf)) << reg_gen4(gpriv, 8, 16))
-
-#define RCANFD_DCFG_DBRP(x)		(((x) & 0xff) << 0)
+#define RCANFD_DCFG_DBRP		GENMASK(7, 0)
 
 /* RSCFDnCFDCmFDCFG */
 #define RCANFD_GEN4_FDCFG_CLOE		BIT(30)
 #define RCANFD_GEN4_FDCFG_FDOE		BIT(28)
+#define RCANFD_FDCFG_TDCO		GENMASK(23, 16)
 #define RCANFD_FDCFG_TDCE		BIT(9)
 #define RCANFD_FDCFG_TDCOC		BIT(8)
-#define RCANFD_FDCFG_TDCO(x)		(((x) & 0x7f) >> 16)
+
+/* RSCFDnCFDCmFDSTS */
+#define RCANFD_FDSTS_SOC		GENMASK(31, 24)
+#define RCANFD_FDSTS_EOC		GENMASK(23, 16)
+#define RCANFD_GEN4_FDSTS_TDCVF		BIT(15)
+#define RCANFD_GEN4_FDSTS_PNSTS		GENMASK(13, 12)
+#define RCANFD_FDSTS_SOCO		BIT(9)
+#define RCANFD_FDSTS_EOCO		BIT(8)
+#define RCANFD_FDSTS_TDCVF		BIT(7)
+#define RCANFD_FDSTS_TDCR		GENMASK(7, 0)
 
 /* RSCFDnCFDRFCCx */
 #define RCANFD_RFCC_RFIM		BIT(12)
@@ -222,8 +207,6 @@
 
 /* RSCFDnCFDRFPTRx */
 #define RCANFD_RFPTR_RFDLC(x)		(((x) >> 28) & 0xf)
-#define RCANFD_RFPTR_RFPTR(x)		(((x) >> 16) & 0xfff)
-#define RCANFD_RFPTR_RFTS(x)		(((x) >> 0) & 0xffff)
 
 /* RSCFDnCFDRFFDSTSx */
 #define RCANFD_RFFDSTS_RFFDF		BIT(2)
@@ -233,11 +216,14 @@
 /* Common FIFO bits */
 
 /* RSCFDnCFDCFCCk */
-#define RCANFD_CFCC_CFTML(gpriv, x)	\
-	(((x) & reg_gen4(gpriv, 0x1f, 0xf)) << reg_gen4(gpriv, 16, 20))
-#define RCANFD_CFCC_CFM(gpriv, x)	(((x) & 0x3) << reg_gen4(gpriv,  8, 16))
+#define RCANFD_CFCC_CFTML(gpriv, cftml) \
+({\
+	typeof(gpriv) (_gpriv) = (gpriv); \
+	(((cftml) & (_gpriv)->info->max_cftml) << (_gpriv)->info->sh->cftml); \
+})
+#define RCANFD_CFCC_CFM(gpriv, x)	(((x) & 0x3) << (gpriv)->info->sh->cfm)
 #define RCANFD_CFCC_CFIM		BIT(12)
-#define RCANFD_CFCC_CFDC(gpriv, x)	(((x) & 0x7) << reg_gen4(gpriv, 21,  8))
+#define RCANFD_CFCC_CFDC(gpriv, x)	(((x) & 0x7) << (gpriv)->info->sh->cfdc)
 #define RCANFD_CFCC_CFPLS(x)		(((x) & 0x7) << 4)
 #define RCANFD_CFCC_CFTXIE		BIT(2)
 #define RCANFD_CFCC_CFE			BIT(0)
@@ -252,12 +238,9 @@
 /* RSCFDnCFDCFIDk */
 #define RCANFD_CFID_CFIDE		BIT(31)
 #define RCANFD_CFID_CFRTR		BIT(30)
-#define RCANFD_CFID_CFID_MASK(x)	((x) & 0x1fffffff)
 
 /* RSCFDnCFDCFPTRk */
 #define RCANFD_CFPTR_CFDLC(x)		(((x) & 0xf) << 28)
-#define RCANFD_CFPTR_CFPTR(x)		(((x) & 0xfff) << 16)
-#define RCANFD_CFPTR_CFTS(x)		(((x) & 0xff) << 0)
 
 /* RSCFDnCFDCFFDCSTSk */
 #define RCANFD_CFFDCSTS_CFFDF		BIT(2)
@@ -298,14 +281,14 @@
 /* RSCFDnCFDGAFLECTR / RSCFDnGAFLECTR */
 #define RCANFD_GAFLECTR			(0x0098)
 /* RSCFDnCFDGAFLCFG / RSCFDnGAFLCFG */
-#define RCANFD_GAFLCFG(ch)		(0x009c + (0x04 * ((ch) / 2)))
+#define RCANFD_GAFLCFG(w)		(0x009c + (0x04 * (w)))
 /* RSCFDnCFDRMNB / RSCFDnRMNB */
 #define RCANFD_RMNB			(0x00a4)
 /* RSCFDnCFDRMND / RSCFDnRMND */
 #define RCANFD_RMND(y)			(0x00a8 + (0x04 * (y)))
 
 /* RSCFDnCFDRFCCx / RSCFDnRFCCx */
-#define RCANFD_RFCC(gpriv, x)		(reg_gen4(gpriv, 0x00c0, 0x00b8) + (0x04 * (x)))
+#define RCANFD_RFCC(gpriv, x)		((gpriv)->info->regs->rfcc + (0x04 * (x)))
 /* RSCFDnCFDRFSTSx / RSCFDnRFSTSx */
 #define RCANFD_RFSTS(gpriv, x)		(RCANFD_RFCC(gpriv, x) + 0x20)
 /* RSCFDnCFDRFPCTRx / RSCFDnRFPCTRx */
@@ -315,67 +298,14 @@
 
 /* RSCFDnCFDCFCCx / RSCFDnCFCCx */
 #define RCANFD_CFCC(gpriv, ch, idx) \
-	(reg_gen4(gpriv, 0x0120, 0x0118) + (0x0c * (ch)) + (0x04 * (idx)))
+	((gpriv)->info->regs->cfcc + (0x0c * (ch)) + (0x04 * (idx)))
 /* RSCFDnCFDCFSTSx / RSCFDnCFSTSx */
 #define RCANFD_CFSTS(gpriv, ch, idx) \
-	(reg_gen4(gpriv, 0x01e0, 0x0178) + (0x0c * (ch)) + (0x04 * (idx)))
+	((gpriv)->info->regs->cfsts + (0x0c * (ch)) + (0x04 * (idx)))
 /* RSCFDnCFDCFPCTRx / RSCFDnCFPCTRx */
 #define RCANFD_CFPCTR(gpriv, ch, idx) \
-	(reg_gen4(gpriv, 0x0240, 0x01d8) + (0x0c * (ch)) + (0x04 * (idx)))
-
-/* RSCFDnCFDFESTS / RSCFDnFESTS */
-#define RCANFD_FESTS			(0x0238)
-/* RSCFDnCFDFFSTS / RSCFDnFFSTS */
-#define RCANFD_FFSTS			(0x023c)
-/* RSCFDnCFDFMSTS / RSCFDnFMSTS */
-#define RCANFD_FMSTS			(0x0240)
-/* RSCFDnCFDRFISTS / RSCFDnRFISTS */
-#define RCANFD_RFISTS			(0x0244)
-/* RSCFDnCFDCFRISTS / RSCFDnCFRISTS */
-#define RCANFD_CFRISTS			(0x0248)
-/* RSCFDnCFDCFTISTS / RSCFDnCFTISTS */
-#define RCANFD_CFTISTS			(0x024c)
-
-/* RSCFDnCFDTMCp / RSCFDnTMCp */
-#define RCANFD_TMC(p)			(0x0250 + (0x01 * (p)))
-/* RSCFDnCFDTMSTSp / RSCFDnTMSTSp */
-#define RCANFD_TMSTS(p)			(0x02d0 + (0x01 * (p)))
-
-/* RSCFDnCFDTMTRSTSp / RSCFDnTMTRSTSp */
-#define RCANFD_TMTRSTS(y)		(0x0350 + (0x04 * (y)))
-/* RSCFDnCFDTMTARSTSp / RSCFDnTMTARSTSp */
-#define RCANFD_TMTARSTS(y)		(0x0360 + (0x04 * (y)))
-/* RSCFDnCFDTMTCSTSp / RSCFDnTMTCSTSp */
-#define RCANFD_TMTCSTS(y)		(0x0370 + (0x04 * (y)))
-/* RSCFDnCFDTMTASTSp / RSCFDnTMTASTSp */
-#define RCANFD_TMTASTS(y)		(0x0380 + (0x04 * (y)))
-/* RSCFDnCFDTMIECy / RSCFDnTMIECy */
-#define RCANFD_TMIEC(y)			(0x0390 + (0x04 * (y)))
-
-/* RSCFDnCFDTXQCCm / RSCFDnTXQCCm */
-#define RCANFD_TXQCC(m)			(0x03a0 + (0x04 * (m)))
-/* RSCFDnCFDTXQSTSm / RSCFDnTXQSTSm */
-#define RCANFD_TXQSTS(m)		(0x03c0 + (0x04 * (m)))
-/* RSCFDnCFDTXQPCTRm / RSCFDnTXQPCTRm */
-#define RCANFD_TXQPCTR(m)		(0x03e0 + (0x04 * (m)))
-
-/* RSCFDnCFDTHLCCm / RSCFDnTHLCCm */
-#define RCANFD_THLCC(m)			(0x0400 + (0x04 * (m)))
-/* RSCFDnCFDTHLSTSm / RSCFDnTHLSTSm */
-#define RCANFD_THLSTS(m)		(0x0420 + (0x04 * (m)))
-/* RSCFDnCFDTHLPCTRm / RSCFDnTHLPCTRm */
-#define RCANFD_THLPCTR(m)		(0x0440 + (0x04 * (m)))
-
-/* RSCFDnCFDGTINTSTS0 / RSCFDnGTINTSTS0 */
-#define RCANFD_GTINTSTS0		(0x0460)
-/* RSCFDnCFDGTINTSTS1 / RSCFDnGTINTSTS1 */
-#define RCANFD_GTINTSTS1		(0x0464)
-/* RSCFDnCFDGTSTCFG / RSCFDnGTSTCFG */
-#define RCANFD_GTSTCFG			(0x0468)
-/* RSCFDnCFDGTSTCTR / RSCFDnGTSTCTR */
-#define RCANFD_GTSTCTR			(0x046c)
-/* RSCFDnCFDGLOCKK / RSCFDnGLOCKK */
-#define RCANFD_GLOCKK			(0x047c)
+	((gpriv)->info->regs->cfpctr + (0x0c * (ch)) + (0x04 * (idx)))
+
 /* RSCFDnCFDGRMCFG */
 #define RCANFD_GRMCFG			(0x04fc)
 
@@ -393,12 +323,6 @@
 /* RSCFDnGAFLXXXj offset */
 #define RCANFD_C_GAFL_OFFSET		(0x0500)
 
-/* RSCFDnRMXXXq -> RCANFD_C_RMXXX(q) */
-#define RCANFD_C_RMID(q)		(0x0600 + (0x10 * (q)))
-#define RCANFD_C_RMPTR(q)		(0x0604 + (0x10 * (q)))
-#define RCANFD_C_RMDF0(q)		(0x0608 + (0x10 * (q)))
-#define RCANFD_C_RMDF1(q)		(0x060c + (0x10 * (q)))
-
 /* RSCFDnRFXXx -> RCANFD_C_RFXX(x) */
 #define RCANFD_C_RFOFFSET	(0x0e00)
 #define RCANFD_C_RFID(x)	(RCANFD_C_RFOFFSET + (0x10 * (x)))
@@ -418,42 +342,26 @@
 #define RCANFD_C_CFDF(ch, idx, df) \
 	(RCANFD_C_CFOFFSET + 0x08 + (0x30 * (ch)) + (0x10 * (idx)) + (0x04 * (df)))
 
-/* RSCFDnTMXXp -> RCANFD_C_TMXX(p) */
-#define RCANFD_C_TMID(p)		(0x1000 + (0x10 * (p)))
-#define RCANFD_C_TMPTR(p)		(0x1004 + (0x10 * (p)))
-#define RCANFD_C_TMDF0(p)		(0x1008 + (0x10 * (p)))
-#define RCANFD_C_TMDF1(p)		(0x100c + (0x10 * (p)))
-
-/* RSCFDnTHLACCm */
-#define RCANFD_C_THLACC(m)		(0x1800 + (0x04 * (m)))
-/* RSCFDnRPGACCr */
-#define RCANFD_C_RPGACC(r)		(0x1900 + (0x04 * (r)))
-
 /* R-Car Gen4 Classical and CAN FD mode specific register map */
-#define RCANFD_GEN4_FDCFG(m)		(0x1404 + (0x20 * (m)))
-
 #define RCANFD_GEN4_GAFL_OFFSET		(0x1800)
 
 /* CAN FD mode specific register map */
 
-/* RSCFDnCFDCmXXX -> RCANFD_F_XXX(m) */
-#define RCANFD_F_DCFG(gpriv, m)		(reg_gen4(gpriv, 0x1400, 0x0500) + (0x20 * (m)))
-#define RCANFD_F_CFDCFG(m)		(0x0504 + (0x20 * (m)))
-#define RCANFD_F_CFDCTR(m)		(0x0508 + (0x20 * (m)))
-#define RCANFD_F_CFDSTS(m)		(0x050c + (0x20 * (m)))
-#define RCANFD_F_CFDCRC(m)		(0x0510 + (0x20 * (m)))
+/* RSCFDnCFDCmXXX -> gpriv->fcbase[m].xxx */
+struct rcar_canfd_f_c {
+	u32 dcfg;
+	u32 cfdcfg;
+	u32 cfdctr;
+	u32 cfdsts;
+	u32 cfdcrc;
+	u32 pad[3];
+};
 
 /* RSCFDnCFDGAFLXXXj offset */
 #define RCANFD_F_GAFL_OFFSET		(0x1000)
 
-/* RSCFDnCFDRMXXXq -> RCANFD_F_RMXXX(q) */
-#define RCANFD_F_RMID(q)		(0x2000 + (0x20 * (q)))
-#define RCANFD_F_RMPTR(q)		(0x2004 + (0x20 * (q)))
-#define RCANFD_F_RMFDSTS(q)		(0x2008 + (0x20 * (q)))
-#define RCANFD_F_RMDF(q, b)		(0x200c + (0x04 * (b)) + (0x20 * (q)))
-
 /* RSCFDnCFDRFXXx -> RCANFD_F_RFXX(x) */
-#define RCANFD_F_RFOFFSET(gpriv)	reg_gen4(gpriv, 0x6000, 0x3000)
+#define RCANFD_F_RFOFFSET(gpriv)	((gpriv)->info->regs->rfoffset)
 #define RCANFD_F_RFID(gpriv, x)		(RCANFD_F_RFOFFSET(gpriv) + (0x80 * (x)))
 #define RCANFD_F_RFPTR(gpriv, x)	(RCANFD_F_RFOFFSET(gpriv) + 0x04 + (0x80 * (x)))
 #define RCANFD_F_RFFDSTS(gpriv, x)	(RCANFD_F_RFOFFSET(gpriv) + 0x08 + (0x80 * (x)))
@@ -461,7 +369,7 @@
 	(RCANFD_F_RFOFFSET(gpriv) + 0x0c + (0x80 * (x)) + (0x04 * (df)))
 
 /* RSCFDnCFDCFXXk -> RCANFD_F_CFXX(ch, k) */
-#define RCANFD_F_CFOFFSET(gpriv)	reg_gen4(gpriv, 0x6400, 0x3400)
+#define RCANFD_F_CFOFFSET(gpriv)	((gpriv)->info->regs->cfoffset)
 
 #define RCANFD_F_CFID(gpriv, ch, idx) \
 	(RCANFD_F_CFOFFSET(gpriv) + (0x180 * (ch)) + (0x80 * (idx)))
@@ -476,23 +384,11 @@
 	(RCANFD_F_CFOFFSET(gpriv) + 0x0c + (0x180 * (ch)) + (0x80 * (idx)) + \
 	 (0x04 * (df)))
 
-/* RSCFDnCFDTMXXp -> RCANFD_F_TMXX(p) */
-#define RCANFD_F_TMID(p)		(0x4000 + (0x20 * (p)))
-#define RCANFD_F_TMPTR(p)		(0x4004 + (0x20 * (p)))
-#define RCANFD_F_TMFDCTR(p)		(0x4008 + (0x20 * (p)))
-#define RCANFD_F_TMDF(p, b)		(0x400c + (0x20 * (p)) + (0x04 * (b)))
-
-/* RSCFDnCFDTHLACCm */
-#define RCANFD_F_THLACC(m)		(0x6000 + (0x04 * (m)))
-/* RSCFDnCFDRPGACCr */
-#define RCANFD_F_RPGACC(r)		(0x6400 + (0x04 * (r)))
-
 /* Constants */
 #define RCANFD_FIFO_DEPTH		8	/* Tx FIFO depth */
 #define RCANFD_NAPI_WEIGHT		8	/* Rx poll quota */
 
 #define RCANFD_NUM_CHANNELS		8	/* Eight channels max */
-#define RCANFD_CHANNELS_MASK		BIT((RCANFD_NUM_CHANNELS) - 1)
 
 #define RCANFD_GAFL_PAGENUM(entry)	((entry) / 16)
 #define RCANFD_CHANNEL_NUMRULES		1	/* only one rule per channel */
@@ -510,12 +406,44 @@
 
 struct rcar_canfd_global;
 
+struct rcar_canfd_regs {
+	u16 rfcc;	/* RX FIFO Configuration/Control Register */
+	u16 cfcc;	/* Common FIFO Configuration/Control Register */
+	u16 cfsts;	/* Common FIFO Status Register */
+	u16 cfpctr;	/* Common FIFO Pointer Control Register */
+	u16 coffset;	/* Channel Data Bitrate Configuration Register */
+	u16 rfoffset;	/* Receive FIFO buffer access ID register */
+	u16 cfoffset;	/* Transmit/receive FIFO buffer access ID register */
+};
+
+struct rcar_canfd_shift_data {
+	u8 ntseg2;	/* Nominal Bit Rate Time Segment 2 Control */
+	u8 ntseg1;	/* Nominal Bit Rate Time Segment 1 Control */
+	u8 nsjw;	/* Nominal Bit Rate Resynchronization Jump Width Control */
+	u8 dtseg2;	/* Data Bit Rate Time Segment 2 Control */
+	u8 dtseg1;	/* Data Bit Rate Time Segment 1 Control */
+	u8 cftml;	/* Common FIFO TX Message Buffer Link */
+	u8 cfm;		/* Common FIFO Mode */
+	u8 cfdc;	/* Common FIFO Depth Configuration */
+};
+
 struct rcar_canfd_hw_info {
+	const struct can_bittiming_const *nom_bittiming;
+	const struct can_bittiming_const *data_bittiming;
+	const struct can_tdc_const *tdc_const;
+	const struct rcar_canfd_regs *regs;
+	const struct rcar_canfd_shift_data *sh;
+	u8 rnc_field_width;
+	u8 max_aflpn;
+	u8 max_cftml;
 	u8 max_channels;
 	u8 postdiv;
 	/* hardware features */
 	unsigned shared_global_irqs:1;	/* Has shared global irqs */
 	unsigned multi_channel_irqs:1;	/* Has multiple channel irqs */
+	unsigned ch_interface_mode:1;	/* Has channel interface mode */
+	unsigned shared_can_regs:1;	/* Has shared classical can registers */
+	unsigned external_clk:1;	/* Has external clock */
 };
 
 /* Channel priv data */
@@ -536,9 +464,11 @@ struct rcar_canfd_channel {
 struct rcar_canfd_global {
 	struct rcar_canfd_channel *ch[RCANFD_NUM_CHANNELS];
 	void __iomem *base;		/* Register base address */
+	struct rcar_canfd_f_c __iomem *fcbase;
 	struct platform_device *pdev;	/* Respective platform device */
 	struct clk *clkp;		/* Peripheral clock */
 	struct clk *can_clk;		/* fCAN clock */
+	struct clk *clk_ram;		/* Clock RAM */
 	unsigned long channels_mask;	/* Enabled channels mask */
 	bool extclk;			/* CANFD or Ext clock */
 	bool fdmode;			/* CAN FD or Classical CAN only mode */
@@ -548,7 +478,7 @@ struct rcar_canfd_global {
 };
 
 /* CAN FD mode nominal rate constants */
-static const struct can_bittiming_const rcar_canfd_nom_bittiming_const = {
+static const struct can_bittiming_const rcar_canfd_gen3_nom_bittiming_const = {
 	.name = RCANFD_DRV_NAME,
 	.tseg1_min = 2,
 	.tseg1_max = 128,
@@ -560,8 +490,20 @@ static const struct can_bittiming_const rcar_canfd_nom_bittiming_const = {
 	.brp_inc = 1,
 };
 
+static const struct can_bittiming_const rcar_canfd_gen4_nom_bittiming_const = {
+	.name = RCANFD_DRV_NAME,
+	.tseg1_min = 2,
+	.tseg1_max = 256,
+	.tseg2_min = 2,
+	.tseg2_max = 128,
+	.sjw_max = 128,
+	.brp_min = 1,
+	.brp_max = 1024,
+	.brp_inc = 1,
+};
+
 /* CAN FD mode data rate constants */
-static const struct can_bittiming_const rcar_canfd_data_bittiming_const = {
+static const struct can_bittiming_const rcar_canfd_gen3_data_bittiming_const = {
 	.name = RCANFD_DRV_NAME,
 	.tseg1_min = 2,
 	.tseg1_max = 16,
@@ -573,6 +515,18 @@ static const struct can_bittiming_const rcar_canfd_data_bittiming_const = {
 	.brp_inc = 1,
 };
 
+static const struct can_bittiming_const rcar_canfd_gen4_data_bittiming_const = {
+	.name = RCANFD_DRV_NAME,
+	.tseg1_min = 2,
+	.tseg1_max = 32,
+	.tseg2_min = 2,
+	.tseg2_max = 16,
+	.sjw_max = 16,
+	.brp_min = 1,
+	.brp_max = 256,
+	.brp_inc = 1,
+};
+
 /* Classical CAN mode bitrate constants */
 static const struct can_bittiming_const rcar_canfd_bittiming_const = {
 	.name = RCANFD_DRV_NAME,
@@ -586,36 +540,136 @@ static const struct can_bittiming_const rcar_canfd_bittiming_const = {
 	.brp_inc = 1,
 };
 
+/* CAN FD Transmission Delay Compensation constants */
+static const struct can_tdc_const rcar_canfd_gen3_tdc_const = {
+	.tdcv_min = 1,
+	.tdcv_max = 128,
+	.tdco_min = 1,
+	.tdco_max = 128,
+	.tdcf_min = 0,	/* Filter window not supported */
+	.tdcf_max = 0,
+};
+
+static const struct can_tdc_const rcar_canfd_gen4_tdc_const = {
+	.tdcv_min = 1,
+	.tdcv_max = 256,
+	.tdco_min = 1,
+	.tdco_max = 256,
+	.tdcf_min = 0,	/* Filter window not supported */
+	.tdcf_max = 0,
+};
+
+static const struct rcar_canfd_regs rcar_gen3_regs = {
+	.rfcc = 0x00b8,
+	.cfcc = 0x0118,
+	.cfsts = 0x0178,
+	.cfpctr = 0x01d8,
+	.coffset = 0x0500,
+	.rfoffset = 0x3000,
+	.cfoffset = 0x3400,
+};
+
+static const struct rcar_canfd_regs rcar_gen4_regs = {
+	.rfcc = 0x00c0,
+	.cfcc = 0x0120,
+	.cfsts = 0x01e0,
+	.cfpctr = 0x0240,
+	.coffset = 0x1400,
+	.rfoffset = 0x6000,
+	.cfoffset = 0x6400,
+};
+
+static const struct rcar_canfd_shift_data rcar_gen3_shift_data = {
+	.ntseg2 = 24,
+	.ntseg1 = 16,
+	.nsjw = 11,
+	.dtseg2 = 20,
+	.dtseg1 = 16,
+	.cftml = 20,
+	.cfm = 16,
+	.cfdc = 8,
+};
+
+static const struct rcar_canfd_shift_data rcar_gen4_shift_data = {
+	.ntseg2 = 25,
+	.ntseg1 = 17,
+	.nsjw = 10,
+	.dtseg2 = 16,
+	.dtseg1 = 8,
+	.cftml = 16,
+	.cfm = 8,
+	.cfdc = 21,
+};
+
 static const struct rcar_canfd_hw_info rcar_gen3_hw_info = {
+	.nom_bittiming = &rcar_canfd_gen3_nom_bittiming_const,
+	.data_bittiming = &rcar_canfd_gen3_data_bittiming_const,
+	.tdc_const = &rcar_canfd_gen3_tdc_const,
+	.regs = &rcar_gen3_regs,
+	.sh = &rcar_gen3_shift_data,
+	.rnc_field_width = 8,
+	.max_aflpn = 31,
+	.max_cftml = 15,
 	.max_channels = 2,
 	.postdiv = 2,
 	.shared_global_irqs = 1,
+	.ch_interface_mode = 0,
+	.shared_can_regs = 0,
+	.external_clk = 1,
 };
 
 static const struct rcar_canfd_hw_info rcar_gen4_hw_info = {
+	.nom_bittiming = &rcar_canfd_gen4_nom_bittiming_const,
+	.data_bittiming = &rcar_canfd_gen4_data_bittiming_const,
+	.tdc_const = &rcar_canfd_gen4_tdc_const,
+	.regs = &rcar_gen4_regs,
+	.sh = &rcar_gen4_shift_data,
+	.rnc_field_width = 16,
+	.max_aflpn = 127,
+	.max_cftml = 31,
 	.max_channels = 8,
 	.postdiv = 2,
 	.shared_global_irqs = 1,
+	.ch_interface_mode = 1,
+	.shared_can_regs = 1,
+	.external_clk = 1,
 };
 
 static const struct rcar_canfd_hw_info rzg2l_hw_info = {
+	.nom_bittiming = &rcar_canfd_gen3_nom_bittiming_const,
+	.data_bittiming = &rcar_canfd_gen3_data_bittiming_const,
+	.tdc_const = &rcar_canfd_gen3_tdc_const,
+	.regs = &rcar_gen3_regs,
+	.sh = &rcar_gen3_shift_data,
+	.rnc_field_width = 8,
+	.max_aflpn = 31,
+	.max_cftml = 15,
 	.max_channels = 2,
 	.postdiv = 1,
 	.multi_channel_irqs = 1,
+	.ch_interface_mode = 0,
+	.shared_can_regs = 0,
+	.external_clk = 1,
 };
 
-/* Helper functions */
-static inline bool is_gen4(struct rcar_canfd_global *gpriv)
-{
-	return gpriv->info == &rcar_gen4_hw_info;
-}
-
-static inline u32 reg_gen4(struct rcar_canfd_global *gpriv,
-			   u32 gen4, u32 not_gen4)
-{
-	return is_gen4(gpriv) ? gen4 : not_gen4;
-}
+static const struct rcar_canfd_hw_info r9a09g047_hw_info = {
+	.nom_bittiming = &rcar_canfd_gen4_nom_bittiming_const,
+	.data_bittiming = &rcar_canfd_gen4_data_bittiming_const,
+	.tdc_const = &rcar_canfd_gen4_tdc_const,
+	.regs = &rcar_gen4_regs,
+	.sh = &rcar_gen4_shift_data,
+	.rnc_field_width = 16,
+	.max_aflpn = 63,
+	.max_cftml = 31,
+	.max_channels = 6,
+	.postdiv = 1,
+	.multi_channel_irqs = 1,
+	.ch_interface_mode = 1,
+	.shared_can_regs = 1,
+	.external_clk = 0,
+};
 
+/* Helper functions */
 static inline void rcar_canfd_update(u32 mask, u32 val, u32 __iomem *reg)
 {
 	u32 data = readl(reg);
@@ -651,26 +705,41 @@ static void rcar_canfd_update_bit(void __iomem *base, u32 reg,
 	rcar_canfd_update(mask, val, base + reg);
 }
 
+static void rcar_canfd_set_bit_reg(void __iomem *addr, u32 val)
+{
+	rcar_canfd_update(val, val, addr);
+}
+
+static void rcar_canfd_clear_bit_reg(void __iomem *addr, u32 val)
+{
+	rcar_canfd_update(val, 0, addr);
+}
+
+static void rcar_canfd_update_bit_reg(void __iomem *addr, u32 mask, u32 val)
+{
+	rcar_canfd_update(mask, val, addr);
+}
+
 static void rcar_canfd_get_data(struct rcar_canfd_channel *priv,
 				struct canfd_frame *cf, u32 off)
 {
+	u32 *data = (u32 *)cf->data;
 	u32 i, lwords;
 
 	lwords = DIV_ROUND_UP(cf->len, sizeof(u32));
 	for (i = 0; i < lwords; i++)
-		*((u32 *)cf->data + i) =
-			rcar_canfd_read(priv->base, off + i * sizeof(u32));
+		data[i] = rcar_canfd_read(priv->base, off + i * sizeof(u32));
 }
 
 static void rcar_canfd_put_data(struct rcar_canfd_channel *priv,
 				struct canfd_frame *cf, u32 off)
 {
+	const u32 *data = (u32 *)cf->data;
 	u32 i, lwords;
 
 	lwords = DIV_ROUND_UP(cf->len, sizeof(u32));
 	for (i = 0; i < lwords; i++)
-		rcar_canfd_write(priv->base, off + i * sizeof(u32),
-				 *((u32 *)cf->data + i));
+		rcar_canfd_write(priv->base, off + i * sizeof(u32), data[i]);
 }
 
 static void rcar_canfd_tx_failure_cleanup(struct net_device *ndev)
@@ -681,28 +750,20 @@ static void rcar_canfd_tx_failure_cleanup(struct net_device *ndev)
 		can_free_echo_skb(ndev, i, NULL);
 }
 
-static void rcar_canfd_set_mode(struct rcar_canfd_global *gpriv)
+static void rcar_canfd_set_rnc(struct rcar_canfd_global *gpriv, unsigned int ch,
+			       unsigned int num_rules)
 {
-	if (is_gen4(gpriv)) {
-		u32 ch, val = gpriv->fdmode ? RCANFD_GEN4_FDCFG_FDOE
-					    : RCANFD_GEN4_FDCFG_CLOE;
-
-		for_each_set_bit(ch, &gpriv->channels_mask,
-				 gpriv->info->max_channels)
-			rcar_canfd_set_bit(gpriv->base, RCANFD_GEN4_FDCFG(ch),
-					   val);
-	} else {
-		if (gpriv->fdmode)
-			rcar_canfd_set_bit(gpriv->base, RCANFD_GRMCFG,
-					   RCANFD_GRMCFG_RCMC);
-		else
-			rcar_canfd_clear_bit(gpriv->base, RCANFD_GRMCFG,
-					     RCANFD_GRMCFG_RCMC);
-	}
+	unsigned int rnc_stride = 32 / gpriv->info->rnc_field_width;
+	unsigned int shift = 32 - (ch % rnc_stride + 1) * gpriv->info->rnc_field_width;
+	unsigned int w = ch / rnc_stride;
+	u32 rnc = num_rules << shift;
+
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLCFG(w), rnc);
 }
 
 static int rcar_canfd_reset_controller(struct rcar_canfd_global *gpriv)
 {
+	struct device *dev = &gpriv->pdev->dev;
 	u32 sts, ch;
 	int err;
 
@@ -712,7 +773,7 @@ static int rcar_canfd_reset_controller(struct rcar_canfd_global *gpriv)
 	err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts,
 				 !(sts & RCANFD_GSTS_GRAMINIT), 2, 500000);
 	if (err) {
-		dev_dbg(&gpriv->pdev->dev, "global raminit failed\n");
+		dev_dbg(dev, "global raminit failed\n");
 		return err;
 	}
 
@@ -725,7 +786,7 @@ static int rcar_canfd_reset_controller(struct rcar_canfd_global *gpriv)
 	err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts,
 				 (sts & RCANFD_GSTS_GRSTSTS), 2, 500000);
 	if (err) {
-		dev_dbg(&gpriv->pdev->dev, "global reset failed\n");
+		dev_dbg(dev, "global reset failed\n");
 		return err;
 	}
 
@@ -733,7 +794,14 @@ static int rcar_canfd_reset_controller(struct rcar_canfd_global *gpriv)
 	rcar_canfd_write(gpriv->base, RCANFD_GERFL, 0x0);
 
 	/* Set the controller into appropriate mode */
-	rcar_canfd_set_mode(gpriv);
+	if (!gpriv->info->ch_interface_mode) {
+		if (gpriv->fdmode)
+			rcar_canfd_set_bit(gpriv->base, RCANFD_GRMCFG,
+					   RCANFD_GRMCFG_RCMC);
+		else
+			rcar_canfd_clear_bit(gpriv->base, RCANFD_GRMCFG,
+					     RCANFD_GRMCFG_RCMC);
+	}
 
 	/* Transition all Channels to reset mode */
 	for_each_set_bit(ch, &gpriv->channels_mask, gpriv->info->max_channels) {
@@ -749,11 +817,27 @@ static int rcar_canfd_reset_controller(struct rcar_canfd_global *gpriv)
 					 (sts & RCANFD_CSTS_CRSTSTS),
 					 2, 500000);
 		if (err) {
-			dev_dbg(&gpriv->pdev->dev,
-				"channel %u reset failed\n", ch);
+			dev_dbg(dev, "channel %u reset failed\n", ch);
 			return err;
 		}
+
+		/* Set the controller into appropriate mode */
+		if (gpriv->info->ch_interface_mode) {
+			/* Do not set CLOE and FDOE simultaneously */
+			if (!gpriv->fdmode) {
+				rcar_canfd_clear_bit_reg(&gpriv->fcbase[ch].cfdcfg,
+							 RCANFD_GEN4_FDCFG_FDOE);
+				rcar_canfd_set_bit_reg(&gpriv->fcbase[ch].cfdcfg,
+						       RCANFD_GEN4_FDCFG_CLOE);
+			} else {
+				rcar_canfd_clear_bit_reg(&gpriv->fcbase[ch].cfdcfg,
+							 RCANFD_GEN4_FDCFG_FDOE);
+				rcar_canfd_clear_bit_reg(&gpriv->fcbase[ch].cfdcfg,
+							 RCANFD_GEN4_FDCFG_CLOE);
+			}
+		}
 	}
+
 	return 0;
 }
 
@@ -787,30 +871,21 @@ static void rcar_canfd_configure_controller(struct rcar_canfd_global *gpriv)
 }
 
 static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv,
-					   u32 ch)
+					   u32 ch, u32 rule_entry)
 {
-	u32 cfg;
-	int offset, start, page, num_rules = RCANFD_CHANNEL_NUMRULES;
+	unsigned int offset, page, num_rules = RCANFD_CHANNEL_NUMRULES;
+	u32 rule_entry_index = rule_entry % 16;
 	u32 ridx = ch + RCANFD_RFFIFO_IDX;
 
-	if (ch == 0) {
-		start = 0; /* Channel 0 always starts from 0th rule */
-	} else {
-		/* Get number of Channel 0 rules and adjust */
-		cfg = rcar_canfd_read(gpriv->base, RCANFD_GAFLCFG(ch));
-		start = RCANFD_GAFLCFG_GETRNC(gpriv, 0, cfg);
-	}
-
 	/* Enable write access to entry */
-	page = RCANFD_GAFL_PAGENUM(start);
+	page = RCANFD_GAFL_PAGENUM(rule_entry);
 	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLECTR,
 			   (RCANFD_GAFLECTR_AFLPN(gpriv, page) |
 			    RCANFD_GAFLECTR_AFLDAE));
 
 	/* Write number of rules for channel */
-	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLCFG(ch),
-			   RCANFD_GAFLCFG_SETRNC(gpriv, ch, num_rules));
-	if (is_gen4(gpriv))
+	rcar_canfd_set_rnc(gpriv, ch, num_rules);
+	if (gpriv->info->shared_can_regs)
 		offset = RCANFD_GEN4_GAFL_OFFSET;
 	else if (gpriv->fdmode)
 		offset = RCANFD_F_GAFL_OFFSET;
@@ -818,13 +893,13 @@ static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv,
 		offset = RCANFD_C_GAFL_OFFSET;
 
 	/* Accept all IDs */
-	rcar_canfd_write(gpriv->base, RCANFD_GAFLID(offset, start), 0);
+	rcar_canfd_write(gpriv->base, RCANFD_GAFLID(offset, rule_entry_index), 0);
 	/* IDE or RTR is not considered for matching */
-	rcar_canfd_write(gpriv->base, RCANFD_GAFLM(offset, start), 0);
+	rcar_canfd_write(gpriv->base, RCANFD_GAFLM(offset, rule_entry_index), 0);
 	/* Any data length accepted */
-	rcar_canfd_write(gpriv->base, RCANFD_GAFLP0(offset, start), 0);
+	rcar_canfd_write(gpriv->base, RCANFD_GAFLP0(offset, rule_entry_index), 0);
 	/* Place the msg in corresponding Rx FIFO entry */
-	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLP1(offset, start),
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLP1(offset, rule_entry_index),
 			   RCANFD_GAFLP1_GAFLFDP(ridx));
 
 	/* Disable write access to page */
@@ -950,7 +1025,7 @@ static void rcar_canfd_global_error(struct net_device *ndev)
 	u32 ridx = ch + RCANFD_RFFIFO_IDX;
 
 	gerfl = rcar_canfd_read(priv->base, RCANFD_GERFL);
-	if (gerfl & RCANFD_GERFL_EEF(ch)) {
+	if (gerfl & FIELD_PREP(RCANFD_GERFL_EEF, BIT(ch))) {
 		netdev_dbg(ndev, "Ch%u: ECC Error flag\n", ch);
 		stats->tx_dropped++;
 	}
@@ -1307,14 +1382,52 @@ static irqreturn_t rcar_canfd_channel_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static void rcar_canfd_set_bittiming(struct net_device *dev)
+static inline u32 rcar_canfd_compute_nominal_bit_rate_cfg(struct rcar_canfd_channel *priv,
+							  u16 tseg1, u16 tseg2, u16 sjw, u16 brp)
+{
+	struct rcar_canfd_global *gpriv = priv->gpriv;
+	const struct rcar_canfd_hw_info *info = gpriv->info;
+	u32 ntseg1, ntseg2, nsjw, nbrp;
+
+	if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || gpriv->info->shared_can_regs) {
+		ntseg1 = (tseg1 & (info->nom_bittiming->tseg1_max - 1)) << info->sh->ntseg1;
+		ntseg2 = (tseg2 & (info->nom_bittiming->tseg2_max - 1)) << info->sh->ntseg2;
+		nsjw = (sjw & (info->nom_bittiming->sjw_max - 1)) << info->sh->nsjw;
+		nbrp = FIELD_PREP(RCANFD_NCFG_NBRP, brp);
+	} else {
+		ntseg1 = FIELD_PREP(RCANFD_CFG_TSEG1, tseg1);
+		ntseg2 = FIELD_PREP(RCANFD_CFG_TSEG2, tseg2);
+		nsjw = FIELD_PREP(RCANFD_CFG_SJW, sjw);
+		nbrp = FIELD_PREP(RCANFD_CFG_BRP, brp);
+	}
+
+	return (ntseg1 | ntseg2 | nsjw | nbrp);
+}
+
+static inline u32 rcar_canfd_compute_data_bit_rate_cfg(const struct rcar_canfd_hw_info *info,
+						       u16 tseg1, u16 tseg2, u16 sjw, u16 brp)
 {
-	struct rcar_canfd_channel *priv = netdev_priv(dev);
+	u32 dtseg1, dtseg2, dsjw, dbrp;
+
+	dtseg1 = (tseg1 & (info->data_bittiming->tseg1_max - 1)) << info->sh->dtseg1;
+	dtseg2 = (tseg2 & (info->data_bittiming->tseg2_max - 1)) << info->sh->dtseg2;
+	dsjw = (sjw & (info->data_bittiming->sjw_max - 1)) << 24;
+	dbrp = FIELD_PREP(RCANFD_DCFG_DBRP, brp);
+
+	return (dtseg1 | dtseg2 | dsjw | dbrp);
+}
+
+static void rcar_canfd_set_bittiming(struct net_device *ndev)
+{
+	u32 mask = RCANFD_FDCFG_TDCO | RCANFD_FDCFG_TDCE | RCANFD_FDCFG_TDCOC;
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
 	struct rcar_canfd_global *gpriv = priv->gpriv;
 	const struct can_bittiming *bt = &priv->can.bittiming;
-	const struct can_bittiming *dbt = &priv->can.data_bittiming;
+	const struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
+	const struct can_tdc_const *tdc_const = priv->can.fd.tdc_const;
+	const struct can_tdc *tdc = &priv->can.fd.tdc;
+	u32 cfg, tdcmode = 0, tdco = 0;
 	u16 brp, sjw, tseg1, tseg2;
-	u32 cfg;
 	u32 ch = priv->channel;
 
 	/* Nominal bit timing settings */
@@ -1322,47 +1435,33 @@ static void rcar_canfd_set_bittiming(struct net_device *dev)
 	sjw = bt->sjw - 1;
 	tseg1 = bt->prop_seg + bt->phase_seg1 - 1;
 	tseg2 = bt->phase_seg2 - 1;
+	cfg = rcar_canfd_compute_nominal_bit_rate_cfg(priv, tseg1, tseg2, sjw, brp);
+	rcar_canfd_write(priv->base, RCANFD_CCFG(ch), cfg);
 
-	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
-		/* CAN FD only mode */
-		cfg = (RCANFD_NCFG_NTSEG1(gpriv, tseg1) | RCANFD_NCFG_NBRP(brp) |
-		       RCANFD_NCFG_NSJW(gpriv, sjw) | RCANFD_NCFG_NTSEG2(gpriv, tseg2));
-
-		rcar_canfd_write(priv->base, RCANFD_CCFG(ch), cfg);
-		netdev_dbg(priv->ndev, "nrate: brp %u, sjw %u, tseg1 %u, tseg2 %u\n",
-			   brp, sjw, tseg1, tseg2);
-
-		/* Data bit timing settings */
-		brp = dbt->brp - 1;
-		sjw = dbt->sjw - 1;
-		tseg1 = dbt->prop_seg + dbt->phase_seg1 - 1;
-		tseg2 = dbt->phase_seg2 - 1;
-
-		cfg = (RCANFD_DCFG_DTSEG1(gpriv, tseg1) | RCANFD_DCFG_DBRP(brp) |
-		       RCANFD_DCFG_DSJW(gpriv, sjw) | RCANFD_DCFG_DTSEG2(gpriv, tseg2));
-
-		rcar_canfd_write(priv->base, RCANFD_F_DCFG(gpriv, ch), cfg);
-		netdev_dbg(priv->ndev, "drate: brp %u, sjw %u, tseg1 %u, tseg2 %u\n",
-			   brp, sjw, tseg1, tseg2);
-	} else {
-		/* Classical CAN only mode */
-		if (is_gen4(gpriv)) {
-			cfg = (RCANFD_NCFG_NTSEG1(gpriv, tseg1) |
-			       RCANFD_NCFG_NBRP(brp) |
-			       RCANFD_NCFG_NSJW(gpriv, sjw) |
-			       RCANFD_NCFG_NTSEG2(gpriv, tseg2));
-		} else {
-			cfg = (RCANFD_CFG_TSEG1(tseg1) |
-			       RCANFD_CFG_BRP(brp) |
-			       RCANFD_CFG_SJW(sjw) |
-			       RCANFD_CFG_TSEG2(tseg2));
-		}
+	if (!(priv->can.ctrlmode & CAN_CTRLMODE_FD))
+		return;
 
-		rcar_canfd_write(priv->base, RCANFD_CCFG(ch), cfg);
-		netdev_dbg(priv->ndev,
-			   "rate: brp %u, sjw %u, tseg1 %u, tseg2 %u\n",
-			   brp, sjw, tseg1, tseg2);
+	/* Data bit timing settings */
+	brp = dbt->brp - 1;
+	sjw = dbt->sjw - 1;
+	tseg1 = dbt->prop_seg + dbt->phase_seg1 - 1;
+	tseg2 = dbt->phase_seg2 - 1;
+	cfg = rcar_canfd_compute_data_bit_rate_cfg(gpriv->info, tseg1, tseg2, sjw, brp);
+	writel(cfg, &gpriv->fcbase[ch].dcfg);
+
+	/* Transceiver Delay Compensation */
+	if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_AUTO) {
+		/* TDC enabled, measured + offset */
+		tdcmode = RCANFD_FDCFG_TDCE;
+		tdco = tdc->tdco - 1;
+	} else if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_MANUAL) {
+		/* TDC enabled, offset only */
+		tdcmode = RCANFD_FDCFG_TDCE | RCANFD_FDCFG_TDCOC;
+		tdco = min(tdc->tdcv + tdc->tdco, tdc_const->tdco_max) - 1;
 	}
+
+	rcar_canfd_update_bit_reg(&gpriv->fcbase[ch].cfdcfg, mask,
+				  tdcmode | FIELD_PREP(RCANFD_FDCFG_TDCO, tdco));
 }
 
 static int rcar_canfd_start(struct net_device *ndev)
@@ -1480,8 +1579,8 @@ static int rcar_canfd_close(struct net_device *ndev)
 	netif_stop_queue(ndev);
 	rcar_canfd_stop(ndev);
 	napi_disable(&priv->napi);
-	clk_disable_unprepare(gpriv->can_clk);
 	close_candev(ndev);
+	clk_disable_unprepare(gpriv->can_clk);
 	phy_power_off(priv->transceiver);
 	return 0;
 }
@@ -1511,7 +1610,7 @@ static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb,
 
 	dlc = RCANFD_CFPTR_CFDLC(can_fd_len2dlc(cf->len));
 
-	if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_gen4(gpriv)) {
+	if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || gpriv->info->shared_can_regs) {
 		rcar_canfd_write(priv->base,
 				 RCANFD_F_CFID(gpriv, ch, RCANFD_CFFIFO_IDX), id);
 		rcar_canfd_write(priv->base,
@@ -1562,7 +1661,8 @@ static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb,
 
 static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv)
 {
-	struct net_device_stats *stats = &priv->ndev->stats;
+	struct net_device *ndev = priv->ndev;
+	struct net_device_stats *stats = &ndev->stats;
 	struct rcar_canfd_global *gpriv = priv->gpriv;
 	struct canfd_frame *cf;
 	struct sk_buff *skb;
@@ -1570,7 +1670,7 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv)
 	u32 ch = priv->channel;
 	u32 ridx = ch + RCANFD_RFFIFO_IDX;
 
-	if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_gen4(gpriv)) {
+	if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || gpriv->info->shared_can_regs) {
 		id = rcar_canfd_read(priv->base, RCANFD_F_RFID(gpriv, ridx));
 		dlc = rcar_canfd_read(priv->base, RCANFD_F_RFPTR(gpriv, ridx));
 
@@ -1578,14 +1678,13 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv)
 
 		if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) &&
 		    sts & RCANFD_RFFDSTS_RFFDF)
-			skb = alloc_canfd_skb(priv->ndev, &cf);
+			skb = alloc_canfd_skb(ndev, &cf);
 		else
-			skb = alloc_can_skb(priv->ndev,
-					    (struct can_frame **)&cf);
+			skb = alloc_can_skb(ndev, (struct can_frame **)&cf);
 	} else {
 		id = rcar_canfd_read(priv->base, RCANFD_C_RFID(ridx));
 		dlc = rcar_canfd_read(priv->base, RCANFD_C_RFPTR(ridx));
-		skb = alloc_can_skb(priv->ndev, (struct can_frame **)&cf);
+		skb = alloc_can_skb(ndev, (struct can_frame **)&cf);
 	}
 
 	if (!skb) {
@@ -1606,7 +1705,7 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv)
 
 		if (sts & RCANFD_RFFDSTS_RFESI) {
 			cf->flags |= CANFD_ESI;
-			netdev_dbg(priv->ndev, "ESI Error\n");
+			netdev_dbg(ndev, "ESI Error\n");
 		}
 
 		if (!(sts & RCANFD_RFFDSTS_RFFDF) && (id & RCANFD_RFID_RFRTR)) {
@@ -1621,7 +1720,7 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv)
 		cf->len = can_cc_dlc2len(RCANFD_RFPTR_RFDLC(dlc));
 		if (id & RCANFD_RFID_RFRTR)
 			cf->can_id |= CAN_RTR_FLAG;
-		else if (is_gen4(gpriv))
+		else if (gpriv->info->shared_can_regs)
 			rcar_canfd_get_data(priv, cf, RCANFD_F_RFDF(gpriv, ridx, 0));
 		else
 			rcar_canfd_get_data(priv, cf, RCANFD_C_RFDF(ridx, 0));
@@ -1673,6 +1772,29 @@ static int rcar_canfd_rx_poll(struct napi_struct *napi, int quota)
 	return num_pkts;
 }
 
+static unsigned int rcar_canfd_get_tdcr(struct rcar_canfd_global *gpriv,
+					unsigned int ch)
+{
+	u32 sts = readl(&gpriv->fcbase[ch].cfdsts);
+	u32 tdcr = FIELD_GET(RCANFD_FDSTS_TDCR, sts);
+
+	return tdcr & (gpriv->info->tdc_const->tdcv_max - 1);
+}
+
+static int rcar_canfd_get_auto_tdcv(const struct net_device *ndev, u32 *tdcv)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	u32 tdco = priv->can.fd.tdc.tdco;
+	u32 tdcr;
+
+	/* Transceiver Delay Compensation Result */
+	tdcr = rcar_canfd_get_tdcr(priv->gpriv, priv->channel) + 1;
+
+	*tdcv = tdcr < tdco ? 0 : tdcr - tdco;
+
+	return 0;
+}
+
 static int rcar_canfd_do_set_mode(struct net_device *ndev, enum can_mode mode)
 {
 	int err;
@@ -1689,10 +1811,10 @@ static int rcar_canfd_do_set_mode(struct net_device *ndev, enum can_mode mode)
 	}
 }
 
-static int rcar_canfd_get_berr_counter(const struct net_device *dev,
+static int rcar_canfd_get_berr_counter(const struct net_device *ndev,
 				       struct can_berr_counter *bec)
 {
-	struct rcar_canfd_channel *priv = netdev_priv(dev);
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
 	u32 val, ch = priv->channel;
 
 	/* Peripheral clock is already enabled in probe */
@@ -1706,7 +1828,6 @@ static const struct net_device_ops rcar_canfd_netdev_ops = {
 	.ndo_open = rcar_canfd_open,
 	.ndo_stop = rcar_canfd_close,
 	.ndo_start_xmit = rcar_canfd_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops rcar_canfd_ethtool_ops = {
@@ -1744,16 +1865,19 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
 
 	if (info->multi_channel_irqs) {
 		char *irq_name;
+		char name[10];
 		int err_irq;
 		int tx_irq;
 
-		err_irq = platform_get_irq_byname(pdev, ch == 0 ? "ch0_err" : "ch1_err");
+		scnprintf(name, sizeof(name), "ch%u_err", ch);
+		err_irq = platform_get_irq_byname(pdev, name);
 		if (err_irq < 0) {
 			err = err_irq;
 			goto fail;
 		}
 
-		tx_irq = platform_get_irq_byname(pdev, ch == 0 ? "ch0_trx" : "ch1_trx");
+		scnprintf(name, sizeof(name), "ch%u_trx", ch);
+		tx_irq = platform_get_irq_byname(pdev, name);
 		if (tx_irq < 0) {
 			err = tx_irq;
 			goto fail;
@@ -1790,18 +1914,25 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
 	}
 
 	if (gpriv->fdmode) {
-		priv->can.bittiming_const = &rcar_canfd_nom_bittiming_const;
-		priv->can.data_bittiming_const =
-			&rcar_canfd_data_bittiming_const;
+		priv->can.bittiming_const = gpriv->info->nom_bittiming;
+		priv->can.fd.data_bittiming_const = gpriv->info->data_bittiming;
+		priv->can.fd.tdc_const = gpriv->info->tdc_const;
 
 		/* Controller starts in CAN FD only mode */
 		err = can_set_static_ctrlmode(ndev, CAN_CTRLMODE_FD);
 		if (err)
 			goto fail;
-		priv->can.ctrlmode_supported = CAN_CTRLMODE_BERR_REPORTING;
+
+		priv->can.ctrlmode_supported = CAN_CTRLMODE_BERR_REPORTING |
+					       CAN_CTRLMODE_TDC_AUTO |
+					       CAN_CTRLMODE_TDC_MANUAL;
+		priv->can.fd.do_get_auto_tdcv = rcar_canfd_get_auto_tdcv;
 	} else {
 		/* Controller starts in Classical CAN only mode */
-		priv->can.bittiming_const = &rcar_canfd_bittiming_const;
+		if (gpriv->info->shared_can_regs)
+			priv->can.bittiming_const = gpriv->info->nom_bittiming;
+		else
+			priv->can.bittiming_const = &rcar_canfd_bittiming_const;
 		priv->can.ctrlmode_supported = CAN_CTRLMODE_BERR_REPORTING;
 	}
 
@@ -1839,13 +1970,112 @@ static void rcar_canfd_channel_remove(struct rcar_canfd_global *gpriv, u32 ch)
 	}
 }
 
+static int rcar_canfd_global_init(struct rcar_canfd_global *gpriv)
+{
+	struct device *dev = &gpriv->pdev->dev;
+	u32 rule_entry = 0;
+	u32 ch, sts;
+	int err;
+
+	err = reset_control_reset(gpriv->rstc1);
+	if (err)
+		return err;
+
+	err = reset_control_reset(gpriv->rstc2);
+	if (err)
+		goto fail_reset1;
+
+	/* Enable peripheral clock for register access */
+	err = clk_prepare_enable(gpriv->clkp);
+	if (err) {
+		dev_err(dev, "failed to enable peripheral clock: %pe\n",
+			ERR_PTR(err));
+		goto fail_reset2;
+	}
+
+	/* Enable RAM clock */
+	err = clk_prepare_enable(gpriv->clk_ram);
+	if (err) {
+		dev_err(dev,
+			"failed to enable RAM clock, error %d\n", err);
+		goto fail_clk;
+	}
+
+	err = rcar_canfd_reset_controller(gpriv);
+	if (err) {
+		dev_err(dev, "reset controller failed: %pe\n", ERR_PTR(err));
+		goto fail_ram_clk;
+	}
+
+	/* Controller in Global reset & Channel reset mode */
+	rcar_canfd_configure_controller(gpriv);
+
+	/* Configure per channel attributes */
+	for_each_set_bit(ch, &gpriv->channels_mask, gpriv->info->max_channels) {
+		/* Configure Channel's Rx fifo */
+		rcar_canfd_configure_rx(gpriv, ch);
+
+		/* Configure Channel's Tx (Common) fifo */
+		rcar_canfd_configure_tx(gpriv, ch);
+
+		/* Configure receive rules */
+		rcar_canfd_configure_afl_rules(gpriv, ch, rule_entry);
+		rule_entry += RCANFD_CHANNEL_NUMRULES;
+	}
+
+	/* Configure common interrupts */
+	rcar_canfd_enable_global_interrupts(gpriv);
+
+	/* Start Global operation mode */
+	rcar_canfd_update_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GMDC_MASK,
+			      RCANFD_GCTR_GMDC_GOPM);
+
+	/* Verify mode change */
+	err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts,
+				 !(sts & RCANFD_GSTS_GNOPM), 2, 500000);
+	if (err) {
+		dev_err(dev, "global operational mode failed\n");
+		goto fail_mode;
+	}
+
+	return 0;
+
+fail_mode:
+	rcar_canfd_disable_global_interrupts(gpriv);
+fail_ram_clk:
+	clk_disable_unprepare(gpriv->clk_ram);
+fail_clk:
+	clk_disable_unprepare(gpriv->clkp);
+fail_reset2:
+	reset_control_assert(gpriv->rstc2);
+fail_reset1:
+	reset_control_assert(gpriv->rstc1);
+	return err;
+}
+
+static void rcar_canfd_global_deinit(struct rcar_canfd_global *gpriv, bool full)
+{
+	rcar_canfd_disable_global_interrupts(gpriv);
+
+	if (full) {
+		rcar_canfd_reset_controller(gpriv);
+
+		/* Enter global sleep mode */
+		rcar_canfd_set_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GSLPR);
+	}
+
+	clk_disable_unprepare(gpriv->clk_ram);
+	clk_disable_unprepare(gpriv->clkp);
+	reset_control_assert(gpriv->rstc2);
+	reset_control_assert(gpriv->rstc1);
+}
+
 static int rcar_canfd_probe(struct platform_device *pdev)
 {
 	struct phy *transceivers[RCANFD_NUM_CHANNELS] = { NULL, };
 	const struct rcar_canfd_hw_info *info;
 	struct device *dev = &pdev->dev;
 	void __iomem *addr;
-	u32 sts, ch, fcan_freq;
 	struct rcar_canfd_global *gpriv;
 	struct device_node *of_child;
 	unsigned long channels_mask = 0;
@@ -1853,6 +2083,7 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 	int g_err_irq, g_recc_irq;
 	bool fdmode = true;			/* CAN FD only mode - default */
 	char name[9] = "channelX";
+	u32 ch, fcan_freq;
 	int i;
 
 	info = of_device_get_match_data(dev);
@@ -1862,13 +2093,13 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 
 	for (i = 0; i < info->max_channels; ++i) {
 		name[7] = '0' + i;
-		of_child = of_get_child_by_name(dev->of_node, name);
-		if (of_child && of_device_is_available(of_child)) {
+		of_child = of_get_available_child_by_name(dev->of_node, name);
+		if (of_child) {
 			channels_mask |= BIT(i);
 			transceivers[i] = devm_of_phy_optional_get(dev,
 							of_child, NULL);
+			of_node_put(of_child);
 		}
-		of_node_put(of_child);
 		if (IS_ERR(transceivers[i]))
 			return PTR_ERR(transceivers[i]);
 	}
@@ -1939,15 +2170,21 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 		fcan_freq = clk_get_rate(gpriv->can_clk) / info->postdiv;
 	} else {
 		fcan_freq = clk_get_rate(gpriv->can_clk);
-		gpriv->extclk = true;
+		gpriv->extclk = gpriv->info->external_clk;
 	}
 
+	gpriv->clk_ram = devm_clk_get_optional(dev, "ram_clk");
+	if (IS_ERR(gpriv->clk_ram))
+		return dev_err_probe(dev, PTR_ERR(gpriv->clk_ram),
+				     "cannot get ram clock\n");
+
 	addr = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(addr)) {
 		err = PTR_ERR(addr);
 		goto fail_dev;
 	}
 	gpriv->base = addr;
+	gpriv->fcbase = addr + gpriv->info->regs->coffset;
 
 	/* Request IRQ that's common for both channels */
 	if (info->shared_global_irqs) {
@@ -1988,58 +2225,9 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 		}
 	}
 
-	err = reset_control_reset(gpriv->rstc1);
+	err = rcar_canfd_global_init(gpriv);
 	if (err)
-		goto fail_dev;
-	err = reset_control_reset(gpriv->rstc2);
-	if (err) {
-		reset_control_assert(gpriv->rstc1);
-		goto fail_dev;
-	}
-
-	/* Enable peripheral clock for register access */
-	err = clk_prepare_enable(gpriv->clkp);
-	if (err) {
-		dev_err(dev, "failed to enable peripheral clock: %pe\n",
-			ERR_PTR(err));
-		goto fail_reset;
-	}
-
-	err = rcar_canfd_reset_controller(gpriv);
-	if (err) {
-		dev_err(dev, "reset controller failed: %pe\n", ERR_PTR(err));
-		goto fail_clk;
-	}
-
-	/* Controller in Global reset & Channel reset mode */
-	rcar_canfd_configure_controller(gpriv);
-
-	/* Configure per channel attributes */
-	for_each_set_bit(ch, &gpriv->channels_mask, info->max_channels) {
-		/* Configure Channel's Rx fifo */
-		rcar_canfd_configure_rx(gpriv, ch);
-
-		/* Configure Channel's Tx (Common) fifo */
-		rcar_canfd_configure_tx(gpriv, ch);
-
-		/* Configure receive rules */
-		rcar_canfd_configure_afl_rules(gpriv, ch);
-	}
-
-	/* Configure common interrupts */
-	rcar_canfd_enable_global_interrupts(gpriv);
-
-	/* Start Global operation mode */
-	rcar_canfd_update_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GMDC_MASK,
-			      RCANFD_GCTR_GMDC_GOPM);
-
-	/* Verify mode change */
-	err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts,
-				 !(sts & RCANFD_GSTS_GNOPM), 2, 500000);
-	if (err) {
-		dev_err(dev, "global operational mode failed\n");
 		goto fail_mode;
-	}
 
 	for_each_set_bit(ch, &gpriv->channels_mask, info->max_channels) {
 		err = rcar_canfd_channel_probe(gpriv, ch, fcan_freq,
@@ -2058,12 +2246,7 @@ fail_channel:
 	for_each_set_bit(ch, &gpriv->channels_mask, info->max_channels)
 		rcar_canfd_channel_remove(gpriv, ch);
 fail_mode:
-	rcar_canfd_disable_global_interrupts(gpriv);
-fail_clk:
-	clk_disable_unprepare(gpriv->clkp);
-fail_reset:
-	reset_control_assert(gpriv->rstc1);
-	reset_control_assert(gpriv->rstc2);
+	rcar_canfd_global_deinit(gpriv, false);
 fail_dev:
 	return err;
 }
@@ -2073,36 +2256,83 @@ static void rcar_canfd_remove(struct platform_device *pdev)
 	struct rcar_canfd_global *gpriv = platform_get_drvdata(pdev);
 	u32 ch;
 
-	rcar_canfd_reset_controller(gpriv);
-	rcar_canfd_disable_global_interrupts(gpriv);
-
 	for_each_set_bit(ch, &gpriv->channels_mask, gpriv->info->max_channels) {
 		rcar_canfd_disable_channel_interrupts(gpriv->ch[ch]);
 		rcar_canfd_channel_remove(gpriv, ch);
 	}
 
-	/* Enter global sleep mode */
-	rcar_canfd_set_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GSLPR);
-	clk_disable_unprepare(gpriv->clkp);
-	reset_control_assert(gpriv->rstc1);
-	reset_control_assert(gpriv->rstc2);
+	rcar_canfd_global_deinit(gpriv, true);
 }
 
-static int __maybe_unused rcar_canfd_suspend(struct device *dev)
+static int rcar_canfd_suspend(struct device *dev)
 {
+	struct rcar_canfd_global *gpriv = dev_get_drvdata(dev);
+	int err;
+	u32 ch;
+
+	for_each_set_bit(ch, &gpriv->channels_mask, gpriv->info->max_channels) {
+		struct rcar_canfd_channel *priv = gpriv->ch[ch];
+		struct net_device *ndev = priv->ndev;
+
+		if (!netif_running(ndev))
+			continue;
+
+		netif_device_detach(ndev);
+
+		err = rcar_canfd_close(ndev);
+		if (err) {
+			netdev_err(ndev, "rcar_canfd_close() failed %pe\n",
+				   ERR_PTR(err));
+			return err;
+		}
+
+		priv->can.state = CAN_STATE_SLEEPING;
+	}
+
+	/* TODO Skip if wake-up (which is not yet supported) is enabled */
+	rcar_canfd_global_deinit(gpriv, false);
+
 	return 0;
 }
 
-static int __maybe_unused rcar_canfd_resume(struct device *dev)
+static int rcar_canfd_resume(struct device *dev)
 {
+	struct rcar_canfd_global *gpriv = dev_get_drvdata(dev);
+	int err;
+	u32 ch;
+
+	err = rcar_canfd_global_init(gpriv);
+	if (err) {
+		dev_err(dev, "rcar_canfd_global_init() failed %pe\n", ERR_PTR(err));
+		return err;
+	}
+
+	for_each_set_bit(ch, &gpriv->channels_mask, gpriv->info->max_channels) {
+		struct rcar_canfd_channel *priv = gpriv->ch[ch];
+		struct net_device *ndev = priv->ndev;
+
+		if (!netif_running(ndev))
+			continue;
+
+		err = rcar_canfd_open(ndev);
+		if (err) {
+			netdev_err(ndev, "rcar_canfd_open() failed %pe\n",
+				   ERR_PTR(err));
+			return err;
+		}
+
+		netif_device_attach(ndev);
+	}
+
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(rcar_canfd_pm_ops, rcar_canfd_suspend,
-			 rcar_canfd_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(rcar_canfd_pm_ops, rcar_canfd_suspend,
+				rcar_canfd_resume);
 
 static const __maybe_unused struct of_device_id rcar_canfd_of_table[] = {
 	{ .compatible = "renesas,r8a779a0-canfd", .data = &rcar_gen4_hw_info },
+	{ .compatible = "renesas,r9a09g047-canfd", .data = &r9a09g047_hw_info },
 	{ .compatible = "renesas,rcar-gen3-canfd", .data = &rcar_gen3_hw_info },
 	{ .compatible = "renesas,rcar-gen4-canfd", .data = &rcar_gen4_hw_info },
 	{ .compatible = "renesas,rzg2l-canfd", .data = &rzg2l_hw_info },
@@ -2115,7 +2345,7 @@ static struct platform_driver rcar_canfd_driver = {
 	.driver = {
 		.name = RCANFD_DRV_NAME,
 		.of_match_table = of_match_ptr(rcar_canfd_of_table),
-		.pm = &rcar_canfd_pm_ops,
+		.pm = pm_sleep_ptr(&rcar_canfd_pm_ops),
 	},
 	.probe = rcar_canfd_probe,
 	.remove = rcar_canfd_remove,
diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index df18c85fc078..29de0c01e4ed 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -118,7 +118,7 @@ static void rkcanfd_chip_set_work_mode(const struct rkcanfd_priv *priv)
 
 static int rkcanfd_set_bittiming(struct rkcanfd_priv *priv)
 {
-	const struct can_bittiming *dbt = &priv->can.data_bittiming;
+	const struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	const struct can_bittiming *bt = &priv->can.bittiming;
 	u32 reg_nbt, reg_dbt, reg_tdc;
 	u32 tdco;
@@ -236,11 +236,6 @@ static void rkcanfd_chip_fifo_setup(struct rkcanfd_priv *priv)
 {
 	u32 reg;
 
-	/* TXE FIFO */
-	reg = rkcanfd_read(priv, RKCANFD_REG_RX_FIFO_CTRL);
-	reg |= RKCANFD_REG_RX_FIFO_CTRL_RX_FIFO_ENABLE;
-	rkcanfd_write(priv, RKCANFD_REG_RX_FIFO_CTRL, reg);
-
 	/* RX FIFO */
 	reg = rkcanfd_read(priv, RKCANFD_REG_RX_FIFO_CTRL);
 	reg |= RKCANFD_REG_RX_FIFO_CTRL_RX_FIFO_ENABLE;
@@ -622,7 +617,7 @@ rkcanfd_handle_rx_fifo_overflow_int(struct rkcanfd_priv *priv)
 	netdev_dbg(priv->ndev, "RX-FIFO overflow\n");
 
 	skb = rkcanfd_alloc_can_err_skb(priv, &cf, &timestamp);
-	if (skb)
+	if (!skb)
 		return 0;
 
 	rkcanfd_get_berr_counter_corrected(priv, &bec);
@@ -766,7 +761,6 @@ static const struct net_device_ops rkcanfd_netdev_ops = {
 	.ndo_open = rkcanfd_open,
 	.ndo_stop = rkcanfd_stop,
 	.ndo_start_xmit = rkcanfd_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static int __maybe_unused rkcanfd_runtime_suspend(struct device *dev)
@@ -904,18 +898,19 @@ static int rkcanfd_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, priv);
 	priv->can.clock.freq = clk_get_rate(priv->clks[0].clk);
 	priv->can.bittiming_const = &rkcanfd_bittiming_const;
-	priv->can.data_bittiming_const = &rkcanfd_data_bittiming_const;
+	priv->can.fd.data_bittiming_const = &rkcanfd_data_bittiming_const;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 		CAN_CTRLMODE_BERR_REPORTING;
-	if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_CANFD_BROKEN))
-		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
 	priv->can.do_set_mode = rkcanfd_set_mode;
 	priv->can.do_get_berr_counter = rkcanfd_get_berr_counter;
 	priv->ndev = ndev;
 
 	match = device_get_match_data(&pdev->dev);
-	if (match)
+	if (match) {
 		priv->devtype_data = *(struct rkcanfd_devtype_data *)match;
+		if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_CANFD_BROKEN))
+			priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
+	}
 
 	err = can_rx_offload_add_manual(ndev, &priv->offload,
 					RKCANFD_NAPI_WEIGHT);
@@ -941,8 +936,8 @@ static void rkcanfd_remove(struct platform_device *pdev)
 	struct rkcanfd_priv *priv = platform_get_drvdata(pdev);
 	struct net_device *ndev = priv->ndev;
 
-	can_rx_offload_del(&priv->offload);
 	rkcanfd_unregister(priv);
+	can_rx_offload_del(&priv->offload);
 	free_candev(ndev);
 }
 
diff --git a/drivers/net/can/rockchip/rockchip_canfd-timestamp.c b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
index 43d4b5721812..72774cd2f94b 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
@@ -8,7 +8,7 @@
 
 #include "rockchip_canfd.h"
 
-static u64 rkcanfd_timestamp_read(const struct cyclecounter *cc)
+static u64 rkcanfd_timestamp_read(struct cyclecounter *cc)
 {
 	const struct rkcanfd_priv *priv = container_of(cc, struct rkcanfd_priv, cc);
 
@@ -39,7 +39,7 @@ static void rkcanfd_timestamp_work(struct work_struct *work)
 
 void rkcanfd_timestamp_init(struct rkcanfd_priv *priv)
 {
-	const struct can_bittiming *dbt = &priv->can.data_bittiming;
+	const struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	const struct can_bittiming *bt = &priv->can.bittiming;
 	struct cyclecounter *cc = &priv->cc;
 	u32 bitrate, div, reg, rate;
diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index 865a15e033a9..12200dcfd338 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -72,7 +72,7 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	int err;
 	u8 i;
 
-	if (can_dropped_invalid_skb(ndev, skb))
+	if (can_dev_dropped_skb(ndev, skb))
 		return NETDEV_TX_OK;
 
 	if (!netif_subqueue_maybe_stop(priv->ndev, 0,
diff --git a/drivers/net/can/sja1000/Kconfig b/drivers/net/can/sja1000/Kconfig
index 2f516cc6d22c..e061e35769bf 100644
--- a/drivers/net/can/sja1000/Kconfig
+++ b/drivers/net/can/sja1000/Kconfig
@@ -105,7 +105,7 @@ config CAN_SJA1000_PLATFORM
 
 config CAN_TSCAN1
 	tristate "TS-CAN1 PC104 boards"
-	depends on ISA
+	depends on (ISA && PC104) || (COMPILE_TEST && HAS_IOPORT)
 	help
 	  This driver is for Technologic Systems' TSCAN-1 PC104 boards.
 	  https://www.embeddedts.com/products/TS-CAN1
diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index da396d641e24..10d88cbda465 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2007, 2011 Wolfgang Grandegger <wg@grandegger.com>
- * Copyright (C) 2012 Stephane Grosjean <s.grosjean@peak-system.com>
  *
  * Derived from the PCAN project file driver/src/pcan_pci.c:
  *
- * Copyright (C) 2001-2006  PEAK System-Technik GmbH
+ * Copyright (C) 2001-2025 PEAK System-Technik GmbH
+ * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
  */
 
 #include <linux/kernel.h>
@@ -22,7 +22,7 @@
 
 #include "sja1000.h"
 
-MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>");
+MODULE_AUTHOR("Stéphane Grosjean <stephane.grosjean@hms-networks.com>");
 MODULE_DESCRIPTION("Socket-CAN driver for PEAK PCAN PCI family cards");
 MODULE_LICENSE("GPL v2");
 
diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c
index ebd5941c3f53..e1610b527d13 100644
--- a/drivers/net/can/sja1000/peak_pcmcia.c
+++ b/drivers/net/can/sja1000/peak_pcmcia.c
@@ -1,10 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2010-2012 Stephane Grosjean <s.grosjean@peak-system.com>
- *
  * CAN driver for PEAK-System PCAN-PC Card
  * Derived from the PCAN project file driver/src/pcan_pccard.c
- * Copyright (C) 2006-2010 PEAK System-Technik GmbH
+ *
+ * Copyright (C) 2006-2025 PEAK System-Technik GmbH
+ * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -19,7 +19,7 @@
 #include <linux/can/dev.h>
 #include "sja1000.h"
 
-MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>");
+MODULE_AUTHOR("Stéphane Grosjean <stephane.grosjean@hms-networks.com>");
 MODULE_DESCRIPTION("CAN driver for PEAK-System PCAN-PC Cards");
 MODULE_LICENSE("GPL v2");
 
@@ -167,7 +167,7 @@ static void pcan_start_led_timer(struct pcan_pccard *card)
  */
 static void pcan_stop_led_timer(struct pcan_pccard *card)
 {
-	del_timer_sync(&card->led_timer);
+	timer_delete_sync(&card->led_timer);
 }
 
 /*
@@ -374,7 +374,7 @@ static inline void pcan_set_can_power(struct pcan_pccard *card, int onoff)
  */
 static void pcan_led_timer(struct timer_list *t)
 {
-	struct pcan_pccard *card = from_timer(card, t, led_timer);
+	struct pcan_pccard *card = timer_container_of(card, t, led_timer);
 	struct net_device *netdev;
 	int i, up_count = 0;
 	u8 ccr;
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 4d245857ef1c..a8fa0d6516b9 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -548,8 +548,8 @@ irqreturn_t sja1000_interrupt(int irq, void *dev_id)
 	if (priv->read_reg(priv, SJA1000_IER) == IRQ_OFF)
 		goto out;
 
-	while ((isrc = priv->read_reg(priv, SJA1000_IR)) &&
-	       (n < SJA1000_MAX_IRQ)) {
+	while ((n < SJA1000_MAX_IRQ) &&
+	       (isrc = priv->read_reg(priv, SJA1000_IR))) {
 
 		status = priv->read_reg(priv, SJA1000_SR);
 		/* check for absent controller due to hw unplug */
@@ -697,7 +697,6 @@ static const struct net_device_ops sja1000_netdev_ops = {
 	.ndo_open	= sja1000_open,
 	.ndo_stop	= sja1000_close,
 	.ndo_start_xmit	= sja1000_start_xmit,
-	.ndo_change_mtu	= can_change_mtu,
 };
 
 static const struct ethtool_ops sja1000_ethtool_ops = {
diff --git a/drivers/net/can/slcan/slcan-core.c b/drivers/net/can/slcan/slcan-core.c
index 24c6622d36bd..cd789e178d34 100644
--- a/drivers/net/can/slcan/slcan-core.c
+++ b/drivers/net/can/slcan/slcan-core.c
@@ -71,12 +71,21 @@ MODULE_AUTHOR("Dario Binacchi <dario.binacchi@amarulasolutions.com>");
 #define SLCAN_CMD_LEN 1
 #define SLCAN_SFF_ID_LEN 3
 #define SLCAN_EFF_ID_LEN 8
+#define SLCAN_DATA_LENGTH_LEN 1
+#define SLCAN_ERROR_LEN 1
 #define SLCAN_STATE_LEN 1
 #define SLCAN_STATE_BE_RXCNT_LEN 3
 #define SLCAN_STATE_BE_TXCNT_LEN 3
-#define SLCAN_STATE_FRAME_LEN       (1 + SLCAN_CMD_LEN + \
-				     SLCAN_STATE_BE_RXCNT_LEN + \
-				     SLCAN_STATE_BE_TXCNT_LEN)
+#define SLCAN_STATE_MSG_LEN     (SLCAN_CMD_LEN +		\
+                                 SLCAN_STATE_LEN +		\
+                                 SLCAN_STATE_BE_RXCNT_LEN +	\
+                                 SLCAN_STATE_BE_TXCNT_LEN)
+#define SLCAN_ERROR_MSG_LEN_MIN (SLCAN_CMD_LEN +	\
+                                 SLCAN_ERROR_LEN +	\
+                                 SLCAN_DATA_LENGTH_LEN)
+#define SLCAN_FRAME_MSG_LEN_MIN (SLCAN_CMD_LEN +	\
+                                 SLCAN_SFF_ID_LEN +	\
+                                 SLCAN_DATA_LENGTH_LEN)
 struct slcan {
 	struct can_priv         can;
 
@@ -176,6 +185,9 @@ static void slcan_bump_frame(struct slcan *sl)
 	u32 tmpid;
 	char *cmd = sl->rbuff;
 
+	if (sl->rcount < SLCAN_FRAME_MSG_LEN_MIN)
+		return;
+
 	skb = alloc_can_skb(sl->dev, &cf);
 	if (unlikely(!skb)) {
 		sl->dev->stats.rx_dropped++;
@@ -281,7 +293,7 @@ static void slcan_bump_state(struct slcan *sl)
 		return;
 	}
 
-	if (state == sl->can.state || sl->rcount < SLCAN_STATE_FRAME_LEN)
+	if (state == sl->can.state || sl->rcount != SLCAN_STATE_MSG_LEN)
 		return;
 
 	cmd += SLCAN_STATE_BE_RXCNT_LEN + SLCAN_CMD_LEN + 1;
@@ -328,6 +340,9 @@ static void slcan_bump_err(struct slcan *sl)
 	bool rx_errors = false, tx_errors = false, rx_over_errors = false;
 	int i, len;
 
+	if (sl->rcount < SLCAN_ERROR_MSG_LEN_MIN)
+		return;
+
 	/* get len from sanitized ASCII value */
 	len = cmd[1];
 	if (len >= '0' && len < '9')
@@ -456,8 +471,7 @@ static void slcan_bump(struct slcan *sl)
 static void slcan_unesc(struct slcan *sl, unsigned char s)
 {
 	if ((s == '\r') || (s == '\a')) { /* CR or BEL ends the pdu */
-		if (!test_and_clear_bit(SLF_ERROR, &sl->flags) &&
-		    sl->rcount > 4)
+		if (!test_and_clear_bit(SLF_ERROR, &sl->flags))
 			slcan_bump(sl);
 
 		sl->rcount = 0;
@@ -760,7 +774,6 @@ static const struct net_device_ops slcan_netdev_ops = {
 	.ndo_open               = slcan_netdev_open,
 	.ndo_stop               = slcan_netdev_close,
 	.ndo_start_xmit         = slcan_netdev_xmit,
-	.ndo_change_mtu         = can_change_mtu,
 };
 
 /******************************************
diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c
index 278ee8722770..79bc64395ac4 100644
--- a/drivers/net/can/softing/softing_main.c
+++ b/drivers/net/can/softing/softing_main.c
@@ -609,7 +609,6 @@ static const struct net_device_ops softing_netdev_ops = {
 	.ndo_open = softing_netdev_open,
 	.ndo_stop = softing_netdev_stop,
 	.ndo_start_xmit	= softing_netdev_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops softing_ethtool_ops = {
diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
index 09ae218315d7..e00d3dbc4cf4 100644
--- a/drivers/net/can/spi/hi311x.c
+++ b/drivers/net/can/spi/hi311x.c
@@ -545,8 +545,6 @@ static int hi3110_stop(struct net_device *net)
 
 	priv->force_quit = 1;
 	free_irq(spi->irq, priv);
-	destroy_workqueue(priv->wq);
-	priv->wq = NULL;
 
 	mutex_lock(&priv->hi3110_lock);
 
@@ -770,34 +768,23 @@ static int hi3110_open(struct net_device *net)
 		goto out_close;
 	}
 
-	priv->wq = alloc_workqueue("hi3110_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM,
-				   0);
-	if (!priv->wq) {
-		ret = -ENOMEM;
-		goto out_free_irq;
-	}
-	INIT_WORK(&priv->tx_work, hi3110_tx_work_handler);
-	INIT_WORK(&priv->restart_work, hi3110_restart_work_handler);
-
 	ret = hi3110_hw_reset(spi);
 	if (ret)
-		goto out_free_wq;
+		goto out_free_irq;
 
 	ret = hi3110_setup(net);
 	if (ret)
-		goto out_free_wq;
+		goto out_free_irq;
 
 	ret = hi3110_set_normal_mode(spi);
 	if (ret)
-		goto out_free_wq;
+		goto out_free_irq;
 
 	netif_wake_queue(net);
 	mutex_unlock(&priv->hi3110_lock);
 
 	return 0;
 
- out_free_wq:
-	destroy_workqueue(priv->wq);
  out_free_irq:
 	free_irq(spi->irq, priv);
 	hi3110_hw_sleep(spi);
@@ -908,6 +895,16 @@ static int hi3110_can_probe(struct spi_device *spi)
 	if (ret)
 		goto out_clk;
 
+	priv->wq = alloc_workqueue("hi3110_wq",
+				   WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU,
+				   0);
+	if (!priv->wq) {
+		ret = -ENOMEM;
+		goto out_clk;
+	}
+	INIT_WORK(&priv->tx_work, hi3110_tx_work_handler);
+	INIT_WORK(&priv->restart_work, hi3110_restart_work_handler);
+
 	priv->spi = spi;
 	mutex_init(&priv->hi3110_lock);
 
@@ -943,6 +940,8 @@ static int hi3110_can_probe(struct spi_device *spi)
 	return 0;
 
  error_probe:
+	destroy_workqueue(priv->wq);
+	priv->wq = NULL;
 	hi3110_power_enable(priv->power, 0);
 
  out_clk:
@@ -963,6 +962,9 @@ static void hi3110_can_remove(struct spi_device *spi)
 
 	hi3110_power_enable(priv->power, 0);
 
+	destroy_workqueue(priv->wq);
+	priv->wq = NULL;
+
 	clk_disable_unprepare(priv->clk);
 
 	free_candev(net);
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index ec5c64006a16..fa97adf25b73 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -388,8 +388,8 @@ static void mcp251x_write_2regs(struct spi_device *spi, u8 reg, u8 v1, u8 v2)
 	mcp251x_spi_write(spi, 4);
 }
 
-static void mcp251x_write_bits(struct spi_device *spi, u8 reg,
-			       u8 mask, u8 val)
+static int mcp251x_write_bits(struct spi_device *spi, u8 reg,
+			      u8 mask, u8 val)
 {
 	struct mcp251x_priv *priv = spi_get_drvdata(spi);
 
@@ -398,7 +398,7 @@ static void mcp251x_write_bits(struct spi_device *spi, u8 reg,
 	priv->spi_tx_buf[2] = mask;
 	priv->spi_tx_buf[3] = val;
 
-	mcp251x_spi_write(spi, 4);
+	return mcp251x_spi_write(spi, 4);
 }
 
 static u8 mcp251x_read_stat(struct spi_device *spi)
@@ -441,6 +441,7 @@ static int mcp251x_gpio_request(struct gpio_chip *chip,
 				unsigned int offset)
 {
 	struct mcp251x_priv *priv = gpiochip_get_data(chip);
+	int ret;
 	u8 val;
 
 	/* nothing to be done for inputs */
@@ -450,8 +451,10 @@ static int mcp251x_gpio_request(struct gpio_chip *chip,
 	val = BFPCTRL_BFE(offset - MCP251X_GPIO_RX0BF);
 
 	mutex_lock(&priv->mcp_lock);
-	mcp251x_write_bits(priv->spi, BFPCTRL, val, val);
+	ret = mcp251x_write_bits(priv->spi, BFPCTRL, val, val);
 	mutex_unlock(&priv->mcp_lock);
+	if (ret)
+		return ret;
 
 	priv->reg_bfpctrl |= val;
 
@@ -530,29 +533,35 @@ static int mcp251x_gpio_get_multiple(struct gpio_chip *chip,
 	return 0;
 }
 
-static void mcp251x_gpio_set(struct gpio_chip *chip, unsigned int offset,
-			     int value)
+static int mcp251x_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			    int value)
 {
 	struct mcp251x_priv *priv = gpiochip_get_data(chip);
 	u8 mask, val;
+	int ret;
 
 	mask = BFPCTRL_BFS(offset - MCP251X_GPIO_RX0BF);
 	val = value ? mask : 0;
 
 	mutex_lock(&priv->mcp_lock);
-	mcp251x_write_bits(priv->spi, BFPCTRL, mask, val);
+	ret = mcp251x_write_bits(priv->spi, BFPCTRL, mask, val);
 	mutex_unlock(&priv->mcp_lock);
+	if (ret)
+		return ret;
 
 	priv->reg_bfpctrl &= ~mask;
 	priv->reg_bfpctrl |= val;
+
+	return 0;
 }
 
-static void
+static int
 mcp251x_gpio_set_multiple(struct gpio_chip *chip,
 			  unsigned long *maskp, unsigned long *bitsp)
 {
 	struct mcp251x_priv *priv = gpiochip_get_data(chip);
 	u8 mask, val;
+	int ret;
 
 	mask = FIELD_GET(MCP251X_GPIO_OUTPUT_MASK, maskp[0]);
 	mask = FIELD_PREP(BFPCTRL_BFS_MASK, mask);
@@ -561,14 +570,18 @@ mcp251x_gpio_set_multiple(struct gpio_chip *chip,
 	val = FIELD_PREP(BFPCTRL_BFS_MASK, val);
 
 	if (!mask)
-		return;
+		return 0;
 
 	mutex_lock(&priv->mcp_lock);
-	mcp251x_write_bits(priv->spi, BFPCTRL, mask, val);
+	ret = mcp251x_write_bits(priv->spi, BFPCTRL, mask, val);
 	mutex_unlock(&priv->mcp_lock);
+	if (ret)
+		return ret;
 
 	priv->reg_bfpctrl &= ~mask;
 	priv->reg_bfpctrl |= val;
+
+	return 0;
 }
 
 static void mcp251x_gpio_restore(struct spi_device *spi)
@@ -1257,7 +1270,6 @@ static const struct net_device_ops mcp251x_netdev_ops = {
 	.ndo_open = mcp251x_open,
 	.ndo_stop = mcp251x_stop,
 	.ndo_start_xmit = mcp251x_hard_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops mcp251x_ethtool_ops = {
@@ -1308,7 +1320,7 @@ static int mcp251x_can_probe(struct spi_device *spi)
 
 	clk = devm_clk_get_optional(&spi->dev, NULL);
 	if (IS_ERR(clk))
-		return PTR_ERR(clk);
+		return dev_err_probe(&spi->dev, PTR_ERR(clk), "Cannot get clock\n");
 
 	freq = clk_get_rate(clk);
 	if (freq == 0)
@@ -1316,7 +1328,7 @@ static int mcp251x_can_probe(struct spi_device *spi)
 
 	/* Sanity check */
 	if (freq < 1000000 || freq > 25000000)
-		return -ERANGE;
+		return dev_err_probe(&spi->dev, -ERANGE, "clock frequency out of range\n");
 
 	/* Allocate can/net device */
 	net = alloc_candev(sizeof(struct mcp251x_priv), TX_ECHO_SKB_MAX);
@@ -1324,8 +1336,10 @@ static int mcp251x_can_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	ret = clk_prepare_enable(clk);
-	if (ret)
+	if (ret) {
+		dev_err_probe(&spi->dev, ret, "Cannot enable clock\n");
 		goto out_free;
+	}
 
 	net->netdev_ops = &mcp251x_netdev_ops;
 	net->ethtool_ops = &mcp251x_ethtool_ops;
@@ -1350,22 +1364,28 @@ static int mcp251x_can_probe(struct spi_device *spi)
 	else
 		spi->max_speed_hz = spi->max_speed_hz ? : 10 * 1000 * 1000;
 	ret = spi_setup(spi);
-	if (ret)
+	if (ret) {
+		dev_err_probe(&spi->dev, ret, "Cannot set up spi\n");
 		goto out_clk;
+	}
 
 	priv->power = devm_regulator_get_optional(&spi->dev, "vdd");
 	priv->transceiver = devm_regulator_get_optional(&spi->dev, "xceiver");
 	if ((PTR_ERR(priv->power) == -EPROBE_DEFER) ||
 	    (PTR_ERR(priv->transceiver) == -EPROBE_DEFER)) {
 		ret = -EPROBE_DEFER;
+		dev_err_probe(&spi->dev, ret, "supply deferred\n");
 		goto out_clk;
 	}
 
 	ret = mcp251x_power_enable(priv->power, 1);
-	if (ret)
+	if (ret) {
+		dev_err_probe(&spi->dev, ret, "Cannot enable power\n");
 		goto out_clk;
+	}
 
-	priv->wq = alloc_workqueue("mcp251x_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM,
+	priv->wq = alloc_workqueue("mcp251x_wq",
+				   WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU,
 				   0);
 	if (!priv->wq) {
 		ret = -ENOMEM;
@@ -1396,21 +1416,24 @@ static int mcp251x_can_probe(struct spi_device *spi)
 	/* Here is OK to not lock the MCP, no one knows about it yet */
 	ret = mcp251x_hw_probe(spi);
 	if (ret) {
-		if (ret == -ENODEV)
-			dev_err(&spi->dev, "Cannot initialize MCP%x. Wrong wiring?\n",
-				priv->model);
+		dev_err_probe(&spi->dev, ret, "Cannot initialize MCP%x. Wrong wiring?\n",
+			      priv->model);
 		goto error_probe;
 	}
 
 	mcp251x_hw_sleep(spi);
 
 	ret = register_candev(net);
-	if (ret)
+	if (ret) {
+		dev_err_probe(&spi->dev, ret, "Cannot register CAN device\n");
 		goto error_probe;
+	}
 
 	ret = mcp251x_gpio_setup(priv);
-	if (ret)
+	if (ret) {
+		dev_err_probe(&spi->dev, ret, "Cannot set up gpios\n");
 		goto out_unregister_candev;
+	}
 
 	netdev_info(net, "MCP%x successfully initialized.\n", priv->model);
 	return 0;
@@ -1429,7 +1452,6 @@ out_clk:
 out_free:
 	free_candev(net);
 
-	dev_err(&spi->dev, "Probe failed, err=%d\n", -ret);
 	return ret;
 }
 
diff --git a/drivers/net/can/spi/mcp251xfd/Kconfig b/drivers/net/can/spi/mcp251xfd/Kconfig
index 877e4356010d..7c29846e6051 100644
--- a/drivers/net/can/spi/mcp251xfd/Kconfig
+++ b/drivers/net/can/spi/mcp251xfd/Kconfig
@@ -5,6 +5,7 @@ config CAN_MCP251XFD
 	select CAN_RX_OFFLOAD
 	select REGMAP
 	select WANT_DEV_COREDUMP
+	select GPIOLIB
 	help
 	  Driver for the Microchip MCP251XFD SPI FD-CAN controller
 	  family.
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 3bc56517fe7a..5134ebb85880 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -75,6 +75,24 @@ static const struct can_bittiming_const mcp251xfd_data_bittiming_const = {
 	.brp_inc = 1,
 };
 
+/* The datasheet of the mcp2518fd (DS20006027B) specifies a range of
+ * [-64,63] for TDCO, indicating a relative TDCO.
+ *
+ * Manual tests have shown, that using a relative TDCO configuration
+ * results in bus off, while an absolute configuration works.
+ *
+ * For TDCO use the max value (63) from the data sheet, but 0 as the
+ * minimum.
+ */
+static const struct can_tdc_const mcp251xfd_tdc_const = {
+	.tdcv_min = 0,
+	.tdcv_max = 63,
+	.tdco_min = 0,
+	.tdco_max = 63,
+	.tdcf_min = 0,
+	.tdcf_max = 0,
+};
+
 static const char *__mcp251xfd_get_model_str(enum mcp251xfd_model model)
 {
 	switch (model) {
@@ -509,9 +527,8 @@ static int mcp251xfd_chip_timestamp_init(const struct mcp251xfd_priv *priv)
 static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv)
 {
 	const struct can_bittiming *bt = &priv->can.bittiming;
-	const struct can_bittiming *dbt = &priv->can.data_bittiming;
-	u32 val = 0;
-	s8 tdco;
+	const struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
+	u32 tdcmod, val = 0;
 	int err;
 
 	/* CAN Control Register
@@ -575,34 +592,37 @@ static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv)
 		return err;
 
 	/* Transmitter Delay Compensation */
-	tdco = clamp_t(int, dbt->brp * (dbt->prop_seg + dbt->phase_seg1),
-		       -64, 63);
-	val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK,
-			 MCP251XFD_REG_TDC_TDCMOD_AUTO) |
-		FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, tdco);
+	if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_AUTO)
+		tdcmod = MCP251XFD_REG_TDC_TDCMOD_AUTO;
+	else if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_MANUAL)
+		tdcmod = MCP251XFD_REG_TDC_TDCMOD_MANUAL;
+	else
+		tdcmod = MCP251XFD_REG_TDC_TDCMOD_DISABLED;
+
+	val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK, tdcmod) |
+	      FIELD_PREP(MCP251XFD_REG_TDC_TDCV_MASK, priv->can.fd.tdc.tdcv) |
+	      FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, priv->can.fd.tdc.tdco);
 
 	return regmap_write(priv->map_reg, MCP251XFD_REG_TDC, val);
 }
 
 static int mcp251xfd_chip_rx_int_enable(const struct mcp251xfd_priv *priv)
 {
-	u32 val;
+	u32 val, mask;
 
 	if (!priv->rx_int)
 		return 0;
 
-	/* Configure GPIOs:
-	 * - PIN0: GPIO Input
-	 * - PIN1: GPIO Input/RX Interrupt
+	/* Configure PIN1 as RX Interrupt:
 	 *
 	 * PIN1 must be Input, otherwise there is a glitch on the
 	 * rx-INT line. It happens between setting the PIN as output
 	 * (in the first byte of the SPI transfer) and configuring the
 	 * PIN as interrupt (in the last byte of the SPI transfer).
 	 */
-	val = MCP251XFD_REG_IOCON_PM0 | MCP251XFD_REG_IOCON_TRIS1 |
-		MCP251XFD_REG_IOCON_TRIS0;
-	return regmap_write(priv->map_reg, MCP251XFD_REG_IOCON, val);
+	val = MCP251XFD_REG_IOCON_TRIS(1);
+	mask = MCP251XFD_REG_IOCON_TRIS(1) | MCP251XFD_REG_IOCON_PM(1);
+	return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON, mask, val);
 }
 
 static int mcp251xfd_chip_rx_int_disable(const struct mcp251xfd_priv *priv)
@@ -612,13 +632,9 @@ static int mcp251xfd_chip_rx_int_disable(const struct mcp251xfd_priv *priv)
 	if (!priv->rx_int)
 		return 0;
 
-	/* Configure GPIOs:
-	 * - PIN0: GPIO Input
-	 * - PIN1: GPIO Input
-	 */
-	val = MCP251XFD_REG_IOCON_PM1 | MCP251XFD_REG_IOCON_PM0 |
-		MCP251XFD_REG_IOCON_TRIS1 | MCP251XFD_REG_IOCON_TRIS0;
-	return regmap_write(priv->map_reg, MCP251XFD_REG_IOCON, val);
+	/* Configure PIN1 as GPIO Input */
+	val = MCP251XFD_REG_IOCON_PM(1) | MCP251XFD_REG_IOCON_TRIS(1);
+	return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON, val, val);
 }
 
 static int mcp251xfd_chip_ecc_init(struct mcp251xfd_priv *priv)
@@ -745,21 +761,13 @@ static void mcp251xfd_chip_stop(struct mcp251xfd_priv *priv,
 	mcp251xfd_chip_interrupts_disable(priv);
 	mcp251xfd_chip_rx_int_disable(priv);
 	mcp251xfd_timestamp_stop(priv);
-	mcp251xfd_chip_sleep(priv);
+	mcp251xfd_chip_set_mode(priv, MCP251XFD_REG_CON_MODE_CONFIG);
 }
 
 static int mcp251xfd_chip_start(struct mcp251xfd_priv *priv)
 {
 	int err;
 
-	err = mcp251xfd_chip_softreset(priv);
-	if (err)
-		goto out_chip_stop;
-
-	err = mcp251xfd_chip_clock_init(priv);
-	if (err)
-		goto out_chip_stop;
-
 	err = mcp251xfd_chip_timestamp_init(priv);
 	if (err)
 		goto out_chip_stop;
@@ -1603,8 +1611,11 @@ static int mcp251xfd_open(struct net_device *ndev)
 		return err;
 
 	err = pm_runtime_resume_and_get(ndev->dev.parent);
-	if (err)
+	if (err) {
+		if (err == -ETIMEDOUT || err == -ENODEV)
+			pm_runtime_set_suspended(ndev->dev.parent);
 		goto out_close_candev;
+	}
 
 	err = mcp251xfd_ring_alloc(priv);
 	if (err)
@@ -1692,8 +1703,8 @@ static const struct net_device_ops mcp251xfd_netdev_ops = {
 	.ndo_open = mcp251xfd_open,
 	.ndo_stop = mcp251xfd_stop,
 	.ndo_start_xmit	= mcp251xfd_start_xmit,
-	.ndo_eth_ioctl = can_eth_ioctl_hwts,
-	.ndo_change_mtu = can_change_mtu,
+	.ndo_hwtstamp_get = can_hwtstamp_get,
+	.ndo_hwtstamp_set = can_hwtstamp_set,
 };
 
 static void
@@ -1786,6 +1797,160 @@ static int mcp251xfd_register_check_rx_int(struct mcp251xfd_priv *priv)
 	return 0;
 }
 
+static const char * const mcp251xfd_gpio_names[] = { "GPIO0", "GPIO1" };
+
+static int mcp251xfd_gpio_request(struct gpio_chip *chip, unsigned int offset)
+{
+	struct mcp251xfd_priv *priv = gpiochip_get_data(chip);
+	u32 pin_mask = MCP251XFD_REG_IOCON_PM(offset);
+	int ret;
+
+	if (priv->rx_int && offset == 1) {
+		netdev_err(priv->ndev, "Can't use GPIO 1 with RX-INT!\n");
+		return -EINVAL;
+	}
+
+	ret = pm_runtime_resume_and_get(priv->ndev->dev.parent);
+	if (ret)
+		return ret;
+
+	return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON, pin_mask, pin_mask);
+}
+
+static void mcp251xfd_gpio_free(struct gpio_chip *chip, unsigned int offset)
+{
+	struct mcp251xfd_priv *priv = gpiochip_get_data(chip);
+
+	pm_runtime_put(priv->ndev->dev.parent);
+}
+
+static int mcp251xfd_gpio_get_direction(struct gpio_chip *chip,
+					unsigned int offset)
+{
+	struct mcp251xfd_priv *priv = gpiochip_get_data(chip);
+	u32 mask = MCP251XFD_REG_IOCON_TRIS(offset);
+	u32 val;
+	int ret;
+
+	ret = regmap_read(priv->map_reg, MCP251XFD_REG_IOCON, &val);
+	if (ret)
+		return ret;
+
+	if (mask & val)
+		return GPIO_LINE_DIRECTION_IN;
+
+	return GPIO_LINE_DIRECTION_OUT;
+}
+
+static int mcp251xfd_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+	struct mcp251xfd_priv *priv = gpiochip_get_data(chip);
+	u32 mask = MCP251XFD_REG_IOCON_GPIO(offset);
+	u32 val;
+	int ret;
+
+	ret = regmap_read(priv->map_reg, MCP251XFD_REG_IOCON, &val);
+	if (ret)
+		return ret;
+
+	return !!(mask & val);
+}
+
+static int mcp251xfd_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask,
+				       unsigned long *bit)
+{
+	struct mcp251xfd_priv *priv = gpiochip_get_data(chip);
+	u32 val;
+	int ret;
+
+	ret = regmap_read(priv->map_reg, MCP251XFD_REG_IOCON, &val);
+	if (ret)
+		return ret;
+
+	*bit = FIELD_GET(MCP251XFD_REG_IOCON_GPIO_MASK, val) & *mask;
+
+	return 0;
+}
+
+static int mcp251xfd_gpio_direction_output(struct gpio_chip *chip,
+					   unsigned int offset, int value)
+{
+	struct mcp251xfd_priv *priv = gpiochip_get_data(chip);
+	u32 dir_mask = MCP251XFD_REG_IOCON_TRIS(offset);
+	u32 val_mask = MCP251XFD_REG_IOCON_LAT(offset);
+	u32 val;
+
+	if (value)
+		val = val_mask;
+	else
+		val = 0;
+
+	return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON,
+				  dir_mask | val_mask, val);
+}
+
+static int mcp251xfd_gpio_direction_input(struct gpio_chip *chip,
+					  unsigned int offset)
+{
+	struct mcp251xfd_priv *priv = gpiochip_get_data(chip);
+	u32 dir_mask = MCP251XFD_REG_IOCON_TRIS(offset);
+
+	return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON, dir_mask, dir_mask);
+}
+
+static int mcp251xfd_gpio_set(struct gpio_chip *chip, unsigned int offset, int value)
+{
+	struct mcp251xfd_priv *priv = gpiochip_get_data(chip);
+	u32 val_mask = MCP251XFD_REG_IOCON_LAT(offset);
+	u32 val;
+
+	if (value)
+		val = val_mask;
+	else
+		val = 0;
+
+	return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON, val_mask, val);
+}
+
+static int mcp251xfd_gpio_set_multiple(struct gpio_chip *chip, unsigned long *mask,
+				       unsigned long *bits)
+{
+	struct mcp251xfd_priv *priv = gpiochip_get_data(chip);
+	u32 val;
+
+	val = FIELD_PREP(MCP251XFD_REG_IOCON_LAT_MASK, *bits);
+
+	return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON,
+				  MCP251XFD_REG_IOCON_LAT_MASK, val);
+}
+
+static int mcp251fdx_gpio_setup(struct mcp251xfd_priv *priv)
+{
+	struct gpio_chip *gc = &priv->gc;
+
+	if (!device_property_present(&priv->spi->dev, "gpio-controller"))
+		return 0;
+
+	gc->label = dev_name(&priv->spi->dev);
+	gc->parent = &priv->spi->dev;
+	gc->owner = THIS_MODULE;
+	gc->request = mcp251xfd_gpio_request;
+	gc->free = mcp251xfd_gpio_free;
+	gc->get_direction = mcp251xfd_gpio_get_direction;
+	gc->direction_output = mcp251xfd_gpio_direction_output;
+	gc->direction_input = mcp251xfd_gpio_direction_input;
+	gc->get = mcp251xfd_gpio_get;
+	gc->get_multiple = mcp251xfd_gpio_get_multiple;
+	gc->set = mcp251xfd_gpio_set;
+	gc->set_multiple = mcp251xfd_gpio_set_multiple;
+	gc->base = -1;
+	gc->can_sleep = true;
+	gc->ngpio = ARRAY_SIZE(mcp251xfd_gpio_names);
+	gc->names = mcp251xfd_gpio_names;
+
+	return devm_gpiochip_add_data(&priv->spi->dev, gc, priv);
+}
+
 static int
 mcp251xfd_register_get_dev_id(const struct mcp251xfd_priv *priv, u32 *dev_id,
 			      u32 *effective_speed_hz_slow,
@@ -1885,53 +2050,59 @@ static int mcp251xfd_register(struct mcp251xfd_priv *priv)
 	struct net_device *ndev = priv->ndev;
 	int err;
 
+	mcp251xfd_register_quirks(priv);
+
 	err = mcp251xfd_clks_and_vdd_enable(priv);
 	if (err)
 		return err;
 
-	pm_runtime_get_noresume(ndev->dev.parent);
-	err = pm_runtime_set_active(ndev->dev.parent);
-	if (err)
-		goto out_runtime_put_noidle;
-	pm_runtime_enable(ndev->dev.parent);
-
-	mcp251xfd_register_quirks(priv);
-
 	err = mcp251xfd_chip_softreset(priv);
 	if (err == -ENODEV)
-		goto out_runtime_disable;
+		goto out_clks_and_vdd_disable;
 	if (err)
 		goto out_chip_sleep;
 
 	err = mcp251xfd_chip_clock_init(priv);
 	if (err == -ENODEV)
-		goto out_runtime_disable;
+		goto out_clks_and_vdd_disable;
 	if (err)
 		goto out_chip_sleep;
 
+	pm_runtime_get_noresume(ndev->dev.parent);
+	err = pm_runtime_set_active(ndev->dev.parent);
+	if (err)
+		goto out_runtime_put_noidle;
+	pm_runtime_enable(ndev->dev.parent);
+
 	err = mcp251xfd_register_chip_detect(priv);
 	if (err)
-		goto out_chip_sleep;
+		goto out_runtime_disable;
 
 	err = mcp251xfd_register_check_rx_int(priv);
 	if (err)
-		goto out_chip_sleep;
+		goto out_runtime_disable;
 
 	mcp251xfd_ethtool_init(priv);
 
+	err = mcp251fdx_gpio_setup(priv);
+	if (err) {
+		dev_err_probe(&priv->spi->dev, err, "Failed to register gpio-controller.\n");
+		goto out_runtime_disable;
+	}
+
 	err = register_candev(ndev);
 	if (err)
-		goto out_chip_sleep;
+		goto out_runtime_disable;
 
 	err = mcp251xfd_register_done(priv);
 	if (err)
 		goto out_unregister_candev;
 
-	/* Put controller into sleep mode and let pm_runtime_put()
-	 * disable the clocks and vdd. If CONFIG_PM is not enabled,
-	 * the clocks and vdd will stay powered.
+	/* Put controller into Config mode and let pm_runtime_put()
+	 * put in sleep mode, disable the clocks and vdd. If CONFIG_PM
+	 * is not enabled, the clocks and vdd will stay powered.
 	 */
-	err = mcp251xfd_chip_sleep(priv);
+	err = mcp251xfd_chip_set_mode(priv, MCP251XFD_REG_CON_MODE_CONFIG);
 	if (err)
 		goto out_unregister_candev;
 
@@ -1941,12 +2112,13 @@ static int mcp251xfd_register(struct mcp251xfd_priv *priv)
 
 out_unregister_candev:
 	unregister_candev(ndev);
-out_chip_sleep:
-	mcp251xfd_chip_sleep(priv);
 out_runtime_disable:
 	pm_runtime_disable(ndev->dev.parent);
 out_runtime_put_noidle:
 	pm_runtime_put_noidle(ndev->dev.parent);
+out_chip_sleep:
+	mcp251xfd_chip_sleep(priv);
+out_clks_and_vdd_disable:
 	mcp251xfd_clks_and_vdd_disable(priv);
 
 	return err;
@@ -1958,10 +2130,12 @@ static inline void mcp251xfd_unregister(struct mcp251xfd_priv *priv)
 
 	unregister_candev(ndev);
 
-	if (pm_runtime_enabled(ndev->dev.parent))
+	if (pm_runtime_enabled(ndev->dev.parent)) {
 		pm_runtime_disable(ndev->dev.parent);
-	else
+	} else {
+		mcp251xfd_chip_sleep(priv);
 		mcp251xfd_clks_and_vdd_disable(priv);
+	}
 }
 
 static const struct of_device_id mcp251xfd_of_match[] = {
@@ -2082,11 +2256,13 @@ static int mcp251xfd_probe(struct spi_device *spi)
 	priv->can.do_set_mode = mcp251xfd_set_mode;
 	priv->can.do_get_berr_counter = mcp251xfd_get_berr_counter;
 	priv->can.bittiming_const = &mcp251xfd_bittiming_const;
-	priv->can.data_bittiming_const = &mcp251xfd_data_bittiming_const;
+	priv->can.fd.data_bittiming_const = &mcp251xfd_data_bittiming_const;
+	priv->can.fd.tdc_const = &mcp251xfd_tdc_const;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 		CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING |
 		CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO |
-		CAN_CTRLMODE_CC_LEN8_DLC;
+		CAN_CTRLMODE_CC_LEN8_DLC | CAN_CTRLMODE_TDC_AUTO |
+		CAN_CTRLMODE_TDC_MANUAL;
 	set_bit(MCP251XFD_FLAGS_DOWN, priv->flags);
 	priv->ndev = ndev;
 	priv->spi = spi;
@@ -2174,24 +2350,49 @@ static void mcp251xfd_remove(struct spi_device *spi)
 	struct mcp251xfd_priv *priv = spi_get_drvdata(spi);
 	struct net_device *ndev = priv->ndev;
 
-	can_rx_offload_del(&priv->offload);
 	mcp251xfd_unregister(priv);
+	can_rx_offload_del(&priv->offload);
 	spi->max_speed_hz = priv->spi_max_speed_hz_orig;
 	free_candev(ndev);
 }
 
 static int __maybe_unused mcp251xfd_runtime_suspend(struct device *device)
 {
-	const struct mcp251xfd_priv *priv = dev_get_drvdata(device);
+	struct mcp251xfd_priv *priv = dev_get_drvdata(device);
 
+	mcp251xfd_chip_sleep(priv);
 	return mcp251xfd_clks_and_vdd_disable(priv);
 }
 
 static int __maybe_unused mcp251xfd_runtime_resume(struct device *device)
 {
-	const struct mcp251xfd_priv *priv = dev_get_drvdata(device);
+	struct mcp251xfd_priv *priv = dev_get_drvdata(device);
+	int err;
+
+	err = mcp251xfd_clks_and_vdd_enable(priv);
+	if (err)
+		return err;
+
+	err = mcp251xfd_chip_softreset(priv);
+	if (err == -ENODEV)
+		goto out_clks_and_vdd_disable;
+	if (err)
+		goto out_chip_sleep;
+
+	err = mcp251xfd_chip_clock_init(priv);
+	if (err == -ENODEV)
+		goto out_clks_and_vdd_disable;
+	if (err)
+		goto out_chip_sleep;
 
-	return mcp251xfd_clks_and_vdd_enable(priv);
+	return 0;
+
+out_chip_sleep:
+	mcp251xfd_chip_sleep(priv);
+out_clks_and_vdd_disable:
+	mcp251xfd_clks_and_vdd_disable(priv);
+
+	return err;
 }
 
 static const struct dev_pm_ops mcp251xfd_pm_ops = {
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
index 8c5be8d1c519..70d5ff0ae7ac 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
@@ -13,17 +13,9 @@
 static const struct regmap_config mcp251xfd_regmap_crc;
 
 static int
-mcp251xfd_regmap_nocrc_write(void *context, const void *data, size_t count)
-{
-	struct spi_device *spi = context;
-
-	return spi_write(spi, data, count);
-}
-
-static int
-mcp251xfd_regmap_nocrc_gather_write(void *context,
-				    const void *reg, size_t reg_len,
-				    const void *val, size_t val_len)
+_mcp251xfd_regmap_nocrc_gather_write(void *context,
+				     const void *reg, size_t reg_len,
+				     const void *val, size_t val_len)
 {
 	struct spi_device *spi = context;
 	struct mcp251xfd_priv *priv = spi_get_drvdata(spi);
@@ -47,6 +39,54 @@ mcp251xfd_regmap_nocrc_gather_write(void *context,
 	return spi_sync_transfer(spi, xfer, ARRAY_SIZE(xfer));
 }
 
+static int
+mcp251xfd_regmap_nocrc_gather_write(void *context,
+				    const void *reg_p, size_t reg_len,
+				    const void *val, size_t val_len)
+{
+	const u16 byte_exclude = MCP251XFD_REG_IOCON +
+				 mcp251xfd_first_byte_set(MCP251XFD_REG_IOCON_GPIO_MASK);
+	u16 reg = be16_to_cpu(*(__be16 *)reg_p) & MCP251XFD_SPI_ADDRESS_MASK;
+	int ret;
+
+	/* Never write to bits 16..23 of IOCON register to avoid clearing of LAT0/LAT1
+	 *
+	 * According to MCP2518FD Errata DS80000789E 5 writing IOCON register using one
+	 * SPI write command clears LAT0/LAT1.
+	 *
+	 * Errata Fix/Work Around suggests to write registers with single byte
+	 * write instructions. However, it seems that the byte at 0xe06(IOCON[23:16])
+	 * is for read-only access and writing to it causes the clearing of LAT0/LAT1.
+	 */
+	if (reg <= byte_exclude && reg + val_len > byte_exclude) {
+		size_t len = byte_exclude - reg;
+
+		/* Write up to 0xe05 */
+		ret = _mcp251xfd_regmap_nocrc_gather_write(context, reg_p, reg_len, val, len);
+		if (ret)
+			return ret;
+
+		/* Write from 0xe07 on */
+		reg += len + 1;
+		reg = (__force unsigned short)cpu_to_be16(MCP251XFD_SPI_INSTRUCTION_WRITE | reg);
+		return _mcp251xfd_regmap_nocrc_gather_write(context, &reg, reg_len,
+							    val + len + 1,
+							    val_len - len - 1);
+	}
+
+	return _mcp251xfd_regmap_nocrc_gather_write(context, reg_p, reg_len,
+						  val, val_len);
+}
+
+static int
+mcp251xfd_regmap_nocrc_write(void *context, const void *data, size_t count)
+{
+	const size_t data_offset = sizeof(__be16);
+
+	return mcp251xfd_regmap_nocrc_gather_write(context, data, data_offset,
+						   data + data_offset, count - data_offset);
+}
+
 static inline bool
 mcp251xfd_update_bits_read_reg(const struct mcp251xfd_priv *priv,
 			       unsigned int reg)
@@ -64,6 +104,7 @@ mcp251xfd_update_bits_read_reg(const struct mcp251xfd_priv *priv,
 	case MCP251XFD_REG_CON:
 	case MCP251XFD_REG_OSC:
 	case MCP251XFD_REG_ECCCON:
+	case MCP251XFD_REG_IOCON:
 		return true;
 	default:
 		mcp251xfd_for_each_rx_ring(priv, ring, n) {
@@ -139,10 +180,9 @@ mcp251xfd_regmap_nocrc_update_bits(void *context, unsigned int reg,
 	tmp_le32 = orig_le32 & ~mask_le32;
 	tmp_le32 |= val_le32 & mask_le32;
 
-	mcp251xfd_spi_cmd_write_nocrc(&buf_tx->cmd, reg + first_byte);
-	memcpy(buf_tx->data, &tmp_le32, len);
-
-	return spi_write(spi, buf_tx, sizeof(buf_tx->cmd) + len);
+	reg += first_byte;
+	mcp251xfd_spi_cmd_write_nocrc(&buf_tx->cmd, reg);
+	return mcp251xfd_regmap_nocrc_gather_write(context, &buf_tx->cmd, 2, &tmp_le32, len);
 }
 
 static int
@@ -196,9 +236,9 @@ mcp251xfd_regmap_nocrc_read(void *context,
 }
 
 static int
-mcp251xfd_regmap_crc_gather_write(void *context,
-				  const void *reg_p, size_t reg_len,
-				  const void *val, size_t val_len)
+_mcp251xfd_regmap_crc_gather_write(void *context,
+				   const void *reg_p, size_t reg_len,
+				   const void *val, size_t val_len)
 {
 	struct spi_device *spi = context;
 	struct mcp251xfd_priv *priv = spi_get_drvdata(spi);
@@ -230,6 +270,44 @@ mcp251xfd_regmap_crc_gather_write(void *context,
 }
 
 static int
+mcp251xfd_regmap_crc_gather_write(void *context,
+				  const void *reg_p, size_t reg_len,
+				  const void *val, size_t val_len)
+{
+	const u16 byte_exclude = MCP251XFD_REG_IOCON +
+				 mcp251xfd_first_byte_set(MCP251XFD_REG_IOCON_GPIO_MASK);
+	u16 reg = *(u16 *)reg_p;
+	int ret;
+
+	/* Never write to bits 16..23 of IOCON register to avoid clearing of LAT0/LAT1
+	 *
+	 * According to MCP2518FD Errata DS80000789E 5 writing IOCON register using one
+	 * SPI write command clears LAT0/LAT1.
+	 *
+	 * Errata Fix/Work Around suggests to write registers with single byte
+	 * write instructions. However, it seems that the byte at 0xe06(IOCON[23:16])
+	 * is for read-only access and writing to it causes the clearing of LAT0/LAT1.
+	 */
+	if (reg <= byte_exclude  && reg + val_len > byte_exclude) {
+		size_t len = byte_exclude - reg;
+
+		/* Write up to 0xe05 */
+		ret = _mcp251xfd_regmap_crc_gather_write(context, &reg, reg_len, val, len);
+		if (ret)
+			return ret;
+
+		/* Write from 0xe07 on */
+		reg += len + 1;
+		return _mcp251xfd_regmap_crc_gather_write(context, &reg, reg_len,
+							  val + len + 1,
+							  val_len - len - 1);
+	}
+
+	return _mcp251xfd_regmap_crc_gather_write(context, reg_p, reg_len,
+						  val, val_len);
+}
+
+static int
 mcp251xfd_regmap_crc_write(void *context,
 			   const void *data, size_t count)
 {
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
index 7209a831f0f2..c34f2067a989 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
@@ -541,11 +541,11 @@ int mcp251xfd_ring_alloc(struct mcp251xfd_priv *priv)
 	}
 	priv->rx_ring_num = i;
 
-	hrtimer_init(&priv->rx_irq_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	priv->rx_irq_timer.function = mcp251xfd_rx_irq_timer;
+	hrtimer_setup(&priv->rx_irq_timer, mcp251xfd_rx_irq_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
-	hrtimer_init(&priv->tx_irq_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	priv->tx_irq_timer.function = mcp251xfd_tx_irq_timer;
+	hrtimer_setup(&priv->tx_irq_timer, mcp251xfd_tx_irq_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	return 0;
 }
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
index 202ca0d24d03..413a5cb75c13 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
@@ -11,7 +11,7 @@
 
 #include "mcp251xfd.h"
 
-static u64 mcp251xfd_timestamp_raw_read(const struct cyclecounter *cc)
+static u64 mcp251xfd_timestamp_raw_read(struct cyclecounter *cc)
 {
 	const struct mcp251xfd_priv *priv;
 	u32 ts_raw = 0;
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
index dcbbd2b2fae8..085d7101e595 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
@@ -15,6 +15,7 @@
 #include <linux/can/dev.h>
 #include <linux/can/rx-offload.h>
 #include <linux/gpio/consumer.h>
+#include <linux/gpio/driver.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
 #include <linux/regmap.h>
@@ -335,13 +336,19 @@
 #define MCP251XFD_REG_IOCON_TXCANOD BIT(28)
 #define MCP251XFD_REG_IOCON_PM1 BIT(25)
 #define MCP251XFD_REG_IOCON_PM0 BIT(24)
+#define MCP251XFD_REG_IOCON_PM(n) (MCP251XFD_REG_IOCON_PM0 << (n))
 #define MCP251XFD_REG_IOCON_GPIO1 BIT(17)
 #define MCP251XFD_REG_IOCON_GPIO0 BIT(16)
+#define MCP251XFD_REG_IOCON_GPIO(n) (MCP251XFD_REG_IOCON_GPIO0 << (n))
+#define MCP251XFD_REG_IOCON_GPIO_MASK GENMASK(17, 16)
 #define MCP251XFD_REG_IOCON_LAT1 BIT(9)
 #define MCP251XFD_REG_IOCON_LAT0 BIT(8)
+#define MCP251XFD_REG_IOCON_LAT(n) (MCP251XFD_REG_IOCON_LAT0 << (n))
+#define MCP251XFD_REG_IOCON_LAT_MASK GENMASK(9, 8)
 #define MCP251XFD_REG_IOCON_XSTBYEN BIT(6)
 #define MCP251XFD_REG_IOCON_TRIS1 BIT(1)
 #define MCP251XFD_REG_IOCON_TRIS0 BIT(0)
+#define MCP251XFD_REG_IOCON_TRIS(n) (MCP251XFD_REG_IOCON_TRIS0 << (n))
 
 #define MCP251XFD_REG_CRC 0xe08
 #define MCP251XFD_REG_CRC_FERRIE BIT(25)
@@ -670,6 +677,7 @@ struct mcp251xfd_priv {
 
 	struct mcp251xfd_devtype_data devtype_data;
 	struct can_berr_counter bec;
+	struct gpio_chip gc;
 };
 
 #define MCP251XFD_IS(_model) \
diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index 4311c1f0eafd..af52285d5a4e 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -570,7 +570,7 @@ static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status)
 		else
 			state = CAN_STATE_ERROR_ACTIVE;
 	}
-	if (skb && state != CAN_STATE_BUS_OFF) {
+	if (likely(skb) && state != CAN_STATE_BUS_OFF) {
 		cf->can_id |= CAN_ERR_CNT;
 		cf->data[6] = txerr;
 		cf->data[7] = rxerr;
@@ -657,8 +657,8 @@ static irqreturn_t sun4i_can_interrupt(int irq, void *dev_id)
 	u8 isrc, status;
 	int n = 0;
 
-	while ((isrc = readl(priv->base + SUN4I_REG_INT_ADDR)) &&
-	       (n < SUN4I_CAN_MAX_IRQ)) {
+	while ((n < SUN4I_CAN_MAX_IRQ) &&
+	       (isrc = readl(priv->base + SUN4I_REG_INT_ADDR))) {
 		n++;
 		status = readl(priv->base + SUN4I_REG_STA_ADDR);
 
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 644e8b8eb91e..1d3dbf28b105 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -383,7 +383,7 @@ static void ti_hecc_start(struct net_device *ndev)
 	 * overflows instead of the hardware silently dropping the
 	 * messages.
 	 */
-	mbx_mask = ~BIT(HECC_RX_LAST_MBOX);
+	mbx_mask = ~BIT_U32(HECC_RX_LAST_MBOX);
 	hecc_write(priv, HECC_CANOPC, mbx_mask);
 
 	/* Enable interrupts */
@@ -829,7 +829,6 @@ static const struct net_device_ops ti_hecc_netdev_ops = {
 	.ndo_open		= ti_hecc_open,
 	.ndo_stop		= ti_hecc_close,
 	.ndo_start_xmit		= ti_hecc_xmit,
-	.ndo_change_mtu		= can_change_mtu,
 };
 
 static const struct ethtool_ops ti_hecc_ethtool_ops = {
diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index 9dae0c71a2e1..cf65a90816b9 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -66,6 +66,7 @@ config CAN_GS_USB
 
 config CAN_KVASER_USB
 	tristate "Kvaser CAN/USB interface"
+	select NET_DEVLINK
 	help
 	  This driver adds support for Kvaser CAN/USB devices like Kvaser
 	  Leaf Light, Kvaser USBcan II and Kvaser Memorator Pro 5xHS.
@@ -133,6 +134,17 @@ config CAN_MCBA_USB
 	  This driver supports the CAN BUS Analyzer interface
 	  from Microchip (http://www.microchip.com/development-tools/).
 
+config CAN_NCT6694
+	tristate "Nuvoton NCT6694 Socket CANfd support"
+	depends on MFD_NCT6694
+	select CAN_RX_OFFLOAD
+	help
+	  If you say yes to this option, support will be included for Nuvoton
+	  NCT6694, a USB device to socket CANfd controller.
+
+	  This driver can also be built as a module. If so, the module will
+	  be called nct6694_canfd.
+
 config CAN_PEAK_USB
 	tristate "PEAK PCAN-USB/USB Pro interfaces for CAN 2.0b/CAN-FD"
 	help
diff --git a/drivers/net/can/usb/Makefile b/drivers/net/can/usb/Makefile
index 8b11088e9a59..fcafb1ac262e 100644
--- a/drivers/net/can/usb/Makefile
+++ b/drivers/net/can/usb/Makefile
@@ -11,5 +11,6 @@ obj-$(CONFIG_CAN_F81604) += f81604.o
 obj-$(CONFIG_CAN_GS_USB) += gs_usb.o
 obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb/
 obj-$(CONFIG_CAN_MCBA_USB) += mcba_usb.o
+obj-$(CONFIG_CAN_NCT6694) += nct6694_canfd.o
 obj-$(CONFIG_CAN_PEAK_USB) += peak_usb/
 obj-$(CONFIG_CAN_UCAN) += ucan.o
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 5355bac4dccb..de8e212a1366 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -885,7 +885,6 @@ static const struct net_device_ops ems_usb_netdev_ops = {
 	.ndo_open = ems_usb_open,
 	.ndo_stop = ems_usb_close,
 	.ndo_start_xmit = ems_usb_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops ems_usb_ethtool_ops = {
diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c
index 03ad10b01867..08da507faef4 100644
--- a/drivers/net/can/usb/esd_usb.c
+++ b/drivers/net/can/usb/esd_usb.c
@@ -9,6 +9,7 @@
 #include <linux/can.h>
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
+#include <linux/err.h>
 #include <linux/ethtool.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
@@ -274,6 +275,7 @@ struct esd_usb {
 	int net_count;
 	u32 version;
 	int rxinitdone;
+	int in_usb_disconnect;
 	void *rxbuf[ESD_USB_MAX_RX_URBS];
 	dma_addr_t rxbuf_dma[ESD_USB_MAX_RX_URBS];
 };
@@ -480,7 +482,7 @@ static void esd_usb_tx_done_msg(struct esd_usb_net_priv *priv,
 static void esd_usb_read_bulk_callback(struct urb *urb)
 {
 	struct esd_usb *dev = urb->context;
-	int retval;
+	int err;
 	int pos = 0;
 	int i;
 
@@ -496,7 +498,7 @@ static void esd_usb_read_bulk_callback(struct urb *urb)
 
 	default:
 		dev_info(dev->udev->dev.parent,
-			 "Rx URB aborted (%d)\n", urb->status);
+			 "Rx URB aborted (%pe)\n", ERR_PTR(urb->status));
 		goto resubmit_urb;
 	}
 
@@ -539,15 +541,15 @@ resubmit_urb:
 			  urb->transfer_buffer, ESD_USB_RX_BUFFER_SIZE,
 			  esd_usb_read_bulk_callback, dev);
 
-	retval = usb_submit_urb(urb, GFP_ATOMIC);
-	if (retval == -ENODEV) {
+	err = usb_submit_urb(urb, GFP_ATOMIC);
+	if (err == -ENODEV) {
 		for (i = 0; i < dev->net_count; i++) {
 			if (dev->nets[i])
 				netif_device_detach(dev->nets[i]->netdev);
 		}
-	} else if (retval) {
+	} else if (err) {
 		dev_err(dev->udev->dev.parent,
-			"failed resubmitting read bulk urb: %d\n", retval);
+			"failed resubmitting read bulk urb: %pe\n", ERR_PTR(err));
 	}
 }
 
@@ -572,7 +574,7 @@ static void esd_usb_write_bulk_callback(struct urb *urb)
 		return;
 
 	if (urb->status)
-		netdev_info(netdev, "Tx URB aborted (%d)\n", urb->status);
+		netdev_info(netdev, "Tx URB aborted (%pe)\n", ERR_PTR(urb->status));
 
 	netif_trans_update(netdev);
 }
@@ -758,7 +760,7 @@ out:
 	if (err == -ENODEV)
 		netif_device_detach(netdev);
 	if (err)
-		netdev_err(netdev, "couldn't start device: %d\n", err);
+		netdev_err(netdev, "couldn't start device: %pe\n", ERR_PTR(err));
 
 	kfree(msg);
 	return err;
@@ -800,7 +802,6 @@ static int esd_usb_open(struct net_device *netdev)
 	/* finally start device */
 	err = esd_usb_start(priv);
 	if (err) {
-		netdev_warn(netdev, "couldn't start device: %d\n", err);
 		close_candev(netdev);
 		return err;
 	}
@@ -923,7 +924,7 @@ static netdev_tx_t esd_usb_start_xmit(struct sk_buff *skb,
 		if (err == -ENODEV)
 			netif_device_detach(netdev);
 		else
-			netdev_warn(netdev, "failed tx_urb %d\n", err);
+			netdev_warn(netdev, "failed tx_urb %pe\n", ERR_PTR(err));
 
 		goto releasebuf;
 	}
@@ -947,10 +948,11 @@ nourbmem:
 	return ret;
 }
 
-static int esd_usb_close(struct net_device *netdev)
+/* Stop interface */
+static int esd_usb_stop(struct esd_usb_net_priv *priv)
 {
-	struct esd_usb_net_priv *priv = netdev_priv(netdev);
 	union esd_usb_msg *msg;
+	int err;
 	int i;
 
 	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
@@ -964,8 +966,11 @@ static int esd_usb_close(struct net_device *netdev)
 	msg->filter.option = ESD_USB_ID_ENABLE; /* start with segment 0 */
 	for (i = 0; i <= ESD_USB_MAX_ID_SEGMENT; i++)
 		msg->filter.mask[i] = 0;
-	if (esd_usb_send_msg(priv->usb, msg) < 0)
-		netdev_err(netdev, "sending idadd message failed\n");
+	err = esd_usb_send_msg(priv->usb, msg);
+	if (err < 0) {
+		netdev_err(priv->netdev, "sending idadd message failed: %pe\n", ERR_PTR(err));
+		goto bail;
+	}
 
 	/* set CAN controller to reset mode */
 	msg->hdr.len = sizeof(struct esd_usb_set_baudrate_msg) / sizeof(u32); /* # of 32bit words */
@@ -973,8 +978,25 @@ static int esd_usb_close(struct net_device *netdev)
 	msg->setbaud.net = priv->index;
 	msg->setbaud.rsvd = 0;
 	msg->setbaud.baud = cpu_to_le32(ESD_USB_NO_BAUDRATE);
-	if (esd_usb_send_msg(priv->usb, msg) < 0)
-		netdev_err(netdev, "sending setbaud message failed\n");
+	err = esd_usb_send_msg(priv->usb, msg);
+	if (err < 0)
+		netdev_err(priv->netdev, "sending setbaud message failed: %pe\n", ERR_PTR(err));
+
+bail:
+	kfree(msg);
+
+	return err;
+}
+
+static int esd_usb_close(struct net_device *netdev)
+{
+	struct esd_usb_net_priv *priv = netdev_priv(netdev);
+	int err = 0;
+
+	if (!priv->usb->in_usb_disconnect) {
+		/* It's moot to try this in usb_disconnect()! */
+		err = esd_usb_stop(priv);
+	}
 
 	priv->can.state = CAN_STATE_STOPPED;
 
@@ -982,16 +1004,13 @@ static int esd_usb_close(struct net_device *netdev)
 
 	close_candev(netdev);
 
-	kfree(msg);
-
-	return 0;
+	return err;
 }
 
 static const struct net_device_ops esd_usb_netdev_ops = {
 	.ndo_open = esd_usb_open,
 	.ndo_stop = esd_usb_close,
 	.ndo_start_xmit = esd_usb_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops esd_usb_ethtool_ops = {
@@ -1098,7 +1117,7 @@ static int esd_usb_3_set_bittiming(struct net_device *netdev)
 	const struct can_bittiming_const *data_btc = &esd_usb_3_data_bittiming_const;
 	struct esd_usb_net_priv *priv = netdev_priv(netdev);
 	struct can_bittiming *nom_bt = &priv->can.bittiming;
-	struct can_bittiming *data_bt = &priv->can.data_bittiming;
+	struct can_bittiming *data_bt = &priv->can.fd.data_bittiming;
 	struct esd_usb_3_set_baudrate_msg_x *baud_x;
 	union esd_usb_msg *msg;
 	u16 flags = 0;
@@ -1218,9 +1237,9 @@ static int esd_usb_probe_one_net(struct usb_interface *intf, int index)
 		priv->can.clock.freq = ESD_USB_3_CAN_CLOCK;
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
 		priv->can.bittiming_const = &esd_usb_3_nom_bittiming_const;
-		priv->can.data_bittiming_const = &esd_usb_3_data_bittiming_const;
+		priv->can.fd.data_bittiming_const = &esd_usb_3_data_bittiming_const;
 		priv->can.do_set_bittiming = esd_usb_3_set_bittiming;
-		priv->can.do_set_data_bittiming = esd_usb_3_set_bittiming;
+		priv->can.fd.do_set_data_bittiming = esd_usb_3_set_bittiming;
 		break;
 
 	case ESD_USB_CANUSBM_PRODUCT_ID:
@@ -1251,14 +1270,14 @@ static int esd_usb_probe_one_net(struct usb_interface *intf, int index)
 
 	err = register_candev(netdev);
 	if (err) {
-		dev_err(&intf->dev, "couldn't register CAN device: %d\n", err);
+		dev_err(&intf->dev, "couldn't register CAN device: %pe\n", ERR_PTR(err));
 		free_candev(netdev);
 		err = -ENOMEM;
 		goto done;
 	}
 
 	dev->nets[index] = priv;
-	netdev_info(netdev, "device %s registered\n", netdev->name);
+	netdev_info(netdev, "registered\n");
 
 done:
 	return err;
@@ -1354,9 +1373,11 @@ static void esd_usb_disconnect(struct usb_interface *intf)
 	usb_set_intfdata(intf, NULL);
 
 	if (dev) {
+		dev->in_usb_disconnect = 1;
 		for (i = 0; i < dev->net_count; i++) {
 			if (dev->nets[i]) {
 				netdev = dev->nets[i]->netdev;
+				netdev_info(netdev, "unregister\n");
 				unregister_netdev(netdev);
 				free_candev(netdev);
 			}
diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c
index 71f24dc0a927..f799233c2b72 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_core.c
+++ b/drivers/net/can/usb/etas_es58x/es58x_core.c
@@ -7,7 +7,7 @@
  *
  * Copyright (c) 2019 Robert Bosch Engineering and Business Solutions. All rights reserved.
  * Copyright (c) 2020 ETAS K.K.. All rights reserved.
- * Copyright (c) 2020-2022 Vincent Mailhol <mailhol.vincent@wanadoo.fr>
+ * Copyright (c) 2020-2025 Vincent Mailhol <mailhol@kernel.org>
  */
 
 #include <linux/unaligned.h>
@@ -1976,7 +1976,8 @@ static const struct net_device_ops es58x_netdev_ops = {
 	.ndo_open = es58x_open,
 	.ndo_stop = es58x_stop,
 	.ndo_start_xmit = es58x_start_xmit,
-	.ndo_eth_ioctl = can_eth_ioctl_hwts,
+	.ndo_hwtstamp_get = can_hwtstamp_get,
+	.ndo_hwtstamp_set = can_hwtstamp_set,
 };
 
 static const struct ethtool_ops es58x_ethtool_ops = {
@@ -2059,8 +2060,8 @@ static int es58x_init_priv(struct es58x_device *es58x_dev,
 
 	can->bittiming_const = param->bittiming_const;
 	if (param->ctrlmode_supported & CAN_CTRLMODE_FD) {
-		can->data_bittiming_const = param->data_bittiming_const;
-		can->tdc_const = param->tdc_const;
+		can->fd.data_bittiming_const = param->data_bittiming_const;
+		can->fd.tdc_const = param->tdc_const;
 	}
 	can->bitrate_max = param->bitrate_max;
 	can->clock = param->clock;
diff --git a/drivers/net/can/usb/etas_es58x/es58x_devlink.c b/drivers/net/can/usb/etas_es58x/es58x_devlink.c
index eee20839d96f..0d155eb1b9e9 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_devlink.c
+++ b/drivers/net/can/usb/etas_es58x/es58x_devlink.c
@@ -248,7 +248,11 @@ static int es58x_devlink_info_get(struct devlink *devlink,
 			return ret;
 	}
 
-	return devlink_info_serial_number_put(req, es58x_dev->udev->serial);
+	if (es58x_dev->udev->serial)
+		ret = devlink_info_serial_number_put(req,
+						     es58x_dev->udev->serial);
+
+	return ret;
 }
 
 const struct devlink_ops es58x_dl_ops = {
diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.c b/drivers/net/can/usb/etas_es58x/es58x_fd.c
index 84ffa1839bac..6476add1c105 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_fd.c
+++ b/drivers/net/can/usb/etas_es58x/es58x_fd.c
@@ -427,12 +427,12 @@ static int es58x_fd_enable_channel(struct es58x_priv *priv)
 
 	if (tx_conf_msg.canfd_enabled) {
 		es58x_fd_convert_bittiming(&tx_conf_msg.data_bittiming,
-					   &priv->can.data_bittiming);
+					   &priv->can.fd.data_bittiming);
 
-		if (can_tdc_is_enabled(&priv->can)) {
+		if (can_fd_tdc_is_enabled(&priv->can)) {
 			tx_conf_msg.tdc_enabled = 1;
-			tx_conf_msg.tdco = cpu_to_le16(priv->can.tdc.tdco);
-			tx_conf_msg.tdcf = cpu_to_le16(priv->can.tdc.tdcf);
+			tx_conf_msg.tdco = cpu_to_le16(priv->can.fd.tdc.tdco);
+			tx_conf_msg.tdcf = cpu_to_le16(priv->can.fd.tdc.tdcf);
 		}
 
 		conf_len = ES58X_FD_CANFD_CONF_LEN;
diff --git a/drivers/net/can/usb/f81604.c b/drivers/net/can/usb/f81604.c
index e0cfa1460b0b..efe61ece79ea 100644
--- a/drivers/net/can/usb/f81604.c
+++ b/drivers/net/can/usb/f81604.c
@@ -1052,7 +1052,6 @@ static const struct net_device_ops f81604_netdev_ops = {
 	.ndo_open = f81604_open,
 	.ndo_stop = f81604_close,
 	.ndo_start_xmit = f81604_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct can_bittiming_const f81604_bittiming_const = {
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index b6f4de375df7..e29e85b67fd4 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -43,6 +43,9 @@
 #define USB_XYLANTA_SAINT3_VENDOR_ID 0x16d0
 #define USB_XYLANTA_SAINT3_PRODUCT_ID 0x0f30
 
+#define USB_CANNECTIVITY_VENDOR_ID 0x1209
+#define USB_CANNECTIVITY_PRODUCT_ID 0xca01
+
 /* Timestamp 32 bit timer runs at 1 MHz (1 µs tick). Worker accounts
  * for timer overflow (will be after ~71 minutes)
  */
@@ -258,14 +261,21 @@ struct canfd_quirk {
 	u8 quirk;
 } __packed;
 
+/* struct gs_host_frame::echo_id == GS_HOST_FRAME_ECHO_ID_RX indicates
+ * a regular RX'ed CAN frame
+ */
+#define GS_HOST_FRAME_ECHO_ID_RX 0xffffffff
+
 struct gs_host_frame {
-	u32 echo_id;
-	__le32 can_id;
+	struct_group(header,
+		u32 echo_id;
+		__le32 can_id;
 
-	u8 can_dlc;
-	u8 channel;
-	u8 flags;
-	u8 reserved;
+		u8 can_dlc;
+		u8 channel;
+		u8 flags;
+		u8 reserved;
+	);
 
 	union {
 		DECLARE_FLEX_ARRAY(struct classic_can, classic_can);
@@ -286,11 +296,6 @@ struct gs_host_frame {
 #define GS_MAX_RX_URBS 30
 #define GS_NAPI_WEIGHT 32
 
-/* Maximum number of interfaces the driver supports per device.
- * Current hardware only supports 3 interfaces. The future may vary.
- */
-#define GS_MAX_INTF 3
-
 struct gs_tx_context {
 	struct gs_can *dev;
 	unsigned int echo_id;
@@ -321,7 +326,6 @@ struct gs_can {
 
 /* usb interface struct */
 struct gs_usb {
-	struct gs_can *canch[GS_MAX_INTF];
 	struct usb_anchor rx_submitted;
 	struct usb_device *udev;
 
@@ -333,9 +337,11 @@ struct gs_usb {
 
 	unsigned int hf_size_rx;
 	u8 active_channels;
+	u8 channel_cnt;
 
 	unsigned int pipe_in;
 	unsigned int pipe_out;
+	struct gs_can *canch[] __counted_by(channel_cnt);
 };
 
 /* 'allocate' a tx context.
@@ -417,7 +423,7 @@ static inline int gs_usb_get_timestamp(const struct gs_usb *parent,
 	return 0;
 }
 
-static u64 gs_usb_timestamp_read(const struct cyclecounter *cc) __must_hold(&dev->tc_lock)
+static u64 gs_usb_timestamp_read(struct cyclecounter *cc) __must_hold(&dev->tc_lock)
 {
 	struct gs_usb *parent = container_of(cc, struct gs_usb, cc);
 	u32 timestamp = 0;
@@ -569,6 +575,37 @@ gs_usb_get_echo_skb(struct gs_can *dev, struct sk_buff *skb,
 	return len;
 }
 
+static unsigned int
+gs_usb_get_minimum_rx_length(const struct gs_can *dev, const struct gs_host_frame *hf,
+			     unsigned int *data_length_p)
+{
+	unsigned int minimum_length, data_length = 0;
+
+	if (hf->flags & GS_CAN_FLAG_FD) {
+		if (hf->echo_id == GS_HOST_FRAME_ECHO_ID_RX)
+			data_length = can_fd_dlc2len(hf->can_dlc);
+
+		if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
+			/* timestamp follows data field of max size */
+			minimum_length = struct_size(hf, canfd_ts, 1);
+		else
+			minimum_length = sizeof(hf->header) + data_length;
+	} else {
+		if (hf->echo_id == GS_HOST_FRAME_ECHO_ID_RX &&
+		    !(hf->can_id & cpu_to_le32(CAN_RTR_FLAG)))
+			data_length = can_cc_dlc2len(hf->can_dlc);
+
+		if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
+			/* timestamp follows data field of max size */
+			minimum_length = struct_size(hf, classic_can_ts, 1);
+		else
+			minimum_length = sizeof(hf->header) + data_length;
+	}
+
+	*data_length_p = data_length;
+	return minimum_length;
+}
+
 static void gs_usb_receive_bulk_callback(struct urb *urb)
 {
 	struct gs_usb *parent = urb->context;
@@ -577,6 +614,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 	int rc;
 	struct net_device_stats *stats;
 	struct gs_host_frame *hf = urb->transfer_buffer;
+	unsigned int minimum_length, data_length;
 	struct gs_tx_context *txc;
 	struct can_frame *cf;
 	struct canfd_frame *cfd;
@@ -595,8 +633,17 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 		return;
 	}
 
+	minimum_length = sizeof(hf->header);
+	if (urb->actual_length < minimum_length) {
+		dev_err_ratelimited(&parent->udev->dev,
+				    "short read (actual_length=%u, minimum_length=%u)\n",
+				    urb->actual_length, minimum_length);
+
+		goto resubmit_urb;
+	}
+
 	/* device reports out of range channel id */
-	if (hf->channel >= GS_MAX_INTF)
+	if (hf->channel >= parent->channel_cnt)
 		goto device_detach;
 
 	dev = parent->canch[hf->channel];
@@ -610,20 +657,33 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 	if (!netif_running(netdev))
 		goto resubmit_urb;
 
-	if (hf->echo_id == -1) { /* normal rx */
+	minimum_length = gs_usb_get_minimum_rx_length(dev, hf, &data_length);
+	if (urb->actual_length < minimum_length) {
+		stats->rx_errors++;
+		stats->rx_length_errors++;
+
+		if (net_ratelimit())
+			netdev_err(netdev,
+				   "short read (actual_length=%u, minimum_length=%u)\n",
+				   urb->actual_length, minimum_length);
+
+		goto resubmit_urb;
+	}
+
+	if (hf->echo_id == GS_HOST_FRAME_ECHO_ID_RX) { /* normal rx */
 		if (hf->flags & GS_CAN_FLAG_FD) {
 			skb = alloc_canfd_skb(netdev, &cfd);
 			if (!skb)
 				return;
 
 			cfd->can_id = le32_to_cpu(hf->can_id);
-			cfd->len = can_fd_dlc2len(hf->can_dlc);
+			cfd->len = data_length;
 			if (hf->flags & GS_CAN_FLAG_BRS)
 				cfd->flags |= CANFD_BRS;
 			if (hf->flags & GS_CAN_FLAG_ESI)
 				cfd->flags |= CANFD_ESI;
 
-			memcpy(cfd->data, hf->canfd->data, cfd->len);
+			memcpy(cfd->data, hf->canfd->data, data_length);
 		} else {
 			skb = alloc_can_skb(netdev, &cf);
 			if (!skb)
@@ -632,7 +692,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 			cf->can_id = le32_to_cpu(hf->can_id);
 			can_frame_set_cc_len(cf, hf->can_dlc, dev->can.ctrlmode);
 
-			memcpy(cf->data, hf->classic_can->data, 8);
+			memcpy(cf->data, hf->classic_can->data, data_length);
 
 			/* ERROR frames tell us information about the controller */
 			if (le32_to_cpu(hf->can_id) & CAN_ERR_FLAG)
@@ -688,7 +748,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 resubmit_urb:
 	usb_fill_bulk_urb(urb, parent->udev,
 			  parent->pipe_in,
-			  hf, dev->parent->hf_size_rx,
+			  hf, parent->hf_size_rx,
 			  gs_usb_receive_bulk_callback, parent);
 
 	rc = usb_submit_urb(urb, GFP_ATOMIC);
@@ -696,7 +756,7 @@ resubmit_urb:
 	/* USB failure take down all interfaces */
 	if (rc == -ENODEV) {
 device_detach:
-		for (rc = 0; rc < GS_MAX_INTF; rc++) {
+		for (rc = 0; rc < parent->channel_cnt; rc++) {
 			if (parent->canch[rc])
 				netif_device_detach(parent->canch[rc]->netdev);
 		}
@@ -725,7 +785,7 @@ static int gs_usb_set_bittiming(struct net_device *netdev)
 static int gs_usb_set_data_bittiming(struct net_device *netdev)
 {
 	struct gs_can *dev = netdev_priv(netdev);
-	struct can_bittiming *bt = &dev->can.data_bittiming;
+	struct can_bittiming *bt = &dev->can.fd.data_bittiming;
 	struct gs_device_bittiming dbt = {
 		.prop_seg = cpu_to_le32(bt->prop_seg),
 		.phase_seg1 = cpu_to_le32(bt->phase_seg1),
@@ -751,8 +811,21 @@ static void gs_usb_xmit_callback(struct urb *urb)
 	struct gs_can *dev = txc->dev;
 	struct net_device *netdev = dev->netdev;
 
-	if (urb->status)
-		netdev_info(netdev, "usb xmit fail %u\n", txc->echo_id);
+	if (!urb->status)
+		return;
+
+	if (urb->status != -ESHUTDOWN && net_ratelimit())
+		netdev_info(netdev, "failed to xmit URB %u: %pe\n",
+			    txc->echo_id, ERR_PTR(urb->status));
+
+	netdev->stats.tx_dropped++;
+	netdev->stats.tx_errors++;
+
+	can_free_echo_skb(netdev, txc->echo_id, NULL);
+	gs_free_tx_context(txc);
+	atomic_dec(&dev->active_tx_urbs);
+
+	netif_wake_queue(netdev);
 }
 
 static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb,
@@ -1088,12 +1161,25 @@ static int gs_can_close(struct net_device *netdev)
 	return 0;
 }
 
-static int gs_can_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+static int gs_can_hwtstamp_get(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *cfg)
 {
 	const struct gs_can *dev = netdev_priv(netdev);
 
 	if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
-		return can_eth_ioctl_hwts(netdev, ifr, cmd);
+		return can_hwtstamp_get(netdev, cfg);
+
+	return -EOPNOTSUPP;
+}
+
+static int gs_can_hwtstamp_set(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *cfg,
+			       struct netlink_ext_ack *extack)
+{
+	const struct gs_can *dev = netdev_priv(netdev);
+
+	if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
+		return can_hwtstamp_set(netdev, cfg, extack);
 
 	return -EOPNOTSUPP;
 }
@@ -1102,8 +1188,8 @@ static const struct net_device_ops gs_usb_netdev_ops = {
 	.ndo_open = gs_can_open,
 	.ndo_stop = gs_can_close,
 	.ndo_start_xmit = gs_can_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
-	.ndo_eth_ioctl = gs_can_eth_ioctl,
+	.ndo_hwtstamp_get = gs_can_hwtstamp_get,
+	.ndo_hwtstamp_set = gs_can_hwtstamp_set,
 };
 
 static int gs_usb_set_identify(struct net_device *netdev, bool do_identify)
@@ -1246,6 +1332,7 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 
 	netdev->flags |= IFF_ECHO; /* we support full roundtrip echo */
 	netdev->dev_id = channel;
+	netdev->dev_port = channel;
 
 	/* dev setup */
 	strcpy(dev->bt_const.name, KBUILD_MODNAME);
@@ -1297,8 +1384,8 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 		/* The data bit timing will be overwritten, if
 		 * GS_CAN_FEATURE_BT_CONST_EXT is set.
 		 */
-		dev->can.data_bittiming_const = &dev->bt_const;
-		dev->can.do_set_data_bittiming = gs_usb_set_data_bittiming;
+		dev->can.fd.data_bittiming_const = &dev->bt_const;
+		dev->can.fd.do_set_data_bittiming = gs_usb_set_data_bittiming;
 	}
 
 	if (feature & GS_CAN_FEATURE_TERMINATION) {
@@ -1378,7 +1465,7 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 		dev->data_bt_const.brp_max = le32_to_cpu(bt_const_extended.dbrp_max);
 		dev->data_bt_const.brp_inc = le32_to_cpu(bt_const_extended.dbrp_inc);
 
-		dev->can.data_bittiming_const = &dev->data_bt_const;
+		dev->can.fd.data_bittiming_const = &dev->data_bt_const;
 	}
 
 	can_rx_offload_add_manual(netdev, &dev->offload, GS_NAPI_WEIGHT);
@@ -1457,17 +1544,19 @@ static int gs_usb_probe(struct usb_interface *intf,
 	icount = dconf.icount + 1;
 	dev_info(&intf->dev, "Configuring for %u interfaces\n", icount);
 
-	if (icount > GS_MAX_INTF) {
+	if (icount > type_max(parent->channel_cnt)) {
 		dev_err(&intf->dev,
 			"Driver cannot handle more that %u CAN interfaces\n",
-			GS_MAX_INTF);
+			type_max(parent->channel_cnt));
 		return -EINVAL;
 	}
 
-	parent = kzalloc(sizeof(*parent), GFP_KERNEL);
+	parent = kzalloc(struct_size(parent, canch, icount), GFP_KERNEL);
 	if (!parent)
 		return -ENOMEM;
 
+	parent->channel_cnt = icount;
+
 	init_usb_anchor(&parent->rx_submitted);
 
 	usb_set_intfdata(intf, parent);
@@ -1528,7 +1617,7 @@ static void gs_usb_disconnect(struct usb_interface *intf)
 		return;
 	}
 
-	for (i = 0; i < GS_MAX_INTF; i++)
+	for (i = 0; i < parent->channel_cnt; i++)
 		if (parent->canch[i])
 			gs_destroy_candev(parent->canch[i]);
 
@@ -1546,6 +1635,8 @@ static const struct usb_device_id gs_usb_table[] = {
 				      USB_ABE_CANDEBUGGER_FD_PRODUCT_ID, 0) },
 	{ USB_DEVICE_INTERFACE_NUMBER(USB_XYLANTA_SAINT3_VENDOR_ID,
 				      USB_XYLANTA_SAINT3_PRODUCT_ID, 0) },
+	{ USB_DEVICE_INTERFACE_NUMBER(USB_CANNECTIVITY_VENDOR_ID,
+				      USB_CANNECTIVITY_PRODUCT_ID, 0) },
 	{} /* Terminating entry */
 };
 
diff --git a/drivers/net/can/usb/kvaser_usb/Makefile b/drivers/net/can/usb/kvaser_usb/Makefile
index cf260044f0b9..41b4a11555aa 100644
--- a/drivers/net/can/usb/kvaser_usb/Makefile
+++ b/drivers/net/can/usb/kvaser_usb/Makefile
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb.o
-kvaser_usb-y = kvaser_usb_core.o kvaser_usb_leaf.o kvaser_usb_hydra.o
+kvaser_usb-y = kvaser_usb_core.o kvaser_usb_devlink.o kvaser_usb_leaf.o kvaser_usb_hydra.o
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
index 078496d9b7ba..46a1b6907a50 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
@@ -27,6 +27,7 @@
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/usb.h>
+#include <net/devlink.h>
 
 #include <linux/can.h>
 #include <linux/can/dev.h>
@@ -47,6 +48,10 @@
 #define KVASER_USB_CAP_EXT_CAP			0x02
 #define KVASER_USB_HYDRA_CAP_EXT_CMD		0x04
 
+#define KVASER_USB_SW_VERSION_MAJOR_MASK GENMASK(31, 24)
+#define KVASER_USB_SW_VERSION_MINOR_MASK GENMASK(23, 16)
+#define KVASER_USB_SW_VERSION_BUILD_MASK GENMASK(15, 0)
+
 struct kvaser_usb_dev_cfg;
 
 enum kvaser_usb_leaf_family {
@@ -54,6 +59,11 @@ enum kvaser_usb_leaf_family {
 	KVASER_USBCAN,
 };
 
+enum kvaser_usb_led_state {
+	KVASER_USB_LED_ON = 0,
+	KVASER_USB_LED_OFF = 1,
+};
+
 #define KVASER_USB_HYDRA_MAX_CMD_LEN		128
 struct kvaser_usb_dev_card_data_hydra {
 	u8 channel_to_he[KVASER_USB_MAX_NET_DEVICES];
@@ -78,6 +88,12 @@ struct kvaser_usb_tx_urb_context {
 	u32 echo_index;
 };
 
+struct kvaser_usb_fw_version {
+	u8 major;
+	u8 minor;
+	u16 build;
+};
+
 struct kvaser_usb_busparams {
 	__le32 bitrate;
 	u8 tseg1;
@@ -96,12 +112,15 @@ struct kvaser_usb {
 	struct usb_endpoint_descriptor *bulk_in, *bulk_out;
 	struct usb_anchor rx_submitted;
 
+	u32 ean[2];
+	u32 serial_number;
+	struct kvaser_usb_fw_version fw_version;
+	u8 hw_revision;
+	unsigned int nchannels;
 	/* @max_tx_urbs: Firmware-reported maximum number of outstanding,
 	 * not yet ACKed, transmissions on this device. This value is
 	 * also used as a sentinel for marking free tx contexts.
 	 */
-	u32 fw_version;
-	unsigned int nchannels;
 	unsigned int max_tx_urbs;
 	struct kvaser_usb_dev_card_data card_data;
 
@@ -112,6 +131,7 @@ struct kvaser_usb {
 
 struct kvaser_usb_net_priv {
 	struct can_priv can;
+	struct devlink_port devlink_port;
 	struct can_berr_counter bec;
 
 	/* subdriver-specific data */
@@ -137,7 +157,7 @@ struct kvaser_usb_net_priv {
  * @dev_set_mode:		used for can.do_set_mode
  * @dev_set_bittiming:		used for can.do_set_bittiming
  * @dev_get_busparams:		readback arbitration busparams
- * @dev_set_data_bittiming:	used for can.do_set_data_bittiming
+ * @dev_set_data_bittiming:	used for can.fd.do_set_data_bittiming
  * @dev_get_data_busparams:	readback data busparams
  * @dev_get_berr_counter:	used for can.do_get_berr_counter
  *
@@ -149,6 +169,7 @@ struct kvaser_usb_net_priv {
  * @dev_get_software_details:	get software details
  * @dev_get_card_info:		get card info
  * @dev_get_capabilities:	discover device capabilities
+ * @dev_set_led:		turn on/off device LED
  *
  * @dev_set_opt_mode:		set ctrlmod
  * @dev_start_chip:		start the CAN controller
@@ -176,6 +197,9 @@ struct kvaser_usb_dev_ops {
 	int (*dev_get_software_details)(struct kvaser_usb *dev);
 	int (*dev_get_card_info)(struct kvaser_usb *dev);
 	int (*dev_get_capabilities)(struct kvaser_usb *dev);
+	int (*dev_set_led)(struct kvaser_usb_net_priv *priv,
+			   enum kvaser_usb_led_state state,
+			   u16 duration_ms);
 	int (*dev_set_opt_mode)(const struct kvaser_usb_net_priv *priv);
 	int (*dev_start_chip)(struct kvaser_usb_net_priv *priv);
 	int (*dev_stop_chip)(struct kvaser_usb_net_priv *priv);
@@ -204,6 +228,11 @@ struct kvaser_usb_dev_cfg {
 extern const struct kvaser_usb_dev_ops kvaser_usb_hydra_dev_ops;
 extern const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops;
 
+extern const struct devlink_ops kvaser_usb_devlink_ops;
+
+int kvaser_usb_devlink_port_register(struct kvaser_usb_net_priv *priv);
+void kvaser_usb_devlink_port_unregister(struct kvaser_usb_net_priv *priv);
+
 void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv);
 
 int kvaser_usb_recv_cmd(const struct kvaser_usb *dev, void *cmd, int len,
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index 7d12776ab63e..62701ec34272 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -364,10 +364,13 @@ resubmit_urb:
 	err = usb_submit_urb(urb, GFP_ATOMIC);
 	if (err == -ENODEV) {
 		for (i = 0; i < dev->nchannels; i++) {
-			if (!dev->nets[i])
+			struct kvaser_usb_net_priv *priv;
+
+			priv = dev->nets[i];
+			if (!priv)
 				continue;
 
-			netif_device_detach(dev->nets[i]->netdev);
+			netif_device_detach(priv->netdev);
 		}
 	} else if (err) {
 		dev_err(&dev->intf->dev,
@@ -592,7 +595,7 @@ static int kvaser_usb_set_data_bittiming(struct net_device *netdev)
 	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
 	struct kvaser_usb *dev = priv->dev;
 	const struct kvaser_usb_dev_ops *ops = dev->driver_info->ops;
-	struct can_bittiming *dbt = &priv->can.data_bittiming;
+	struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	struct kvaser_usb_busparams busparams;
 	int tseg1 = dbt->prop_seg + dbt->phase_seg1;
 	int tseg2 = dbt->phase_seg2;
@@ -753,40 +756,70 @@ freeurb:
 	return ret;
 }
 
+static int kvaser_usb_set_phys_id(struct net_device *netdev,
+				  enum ethtool_phys_id_state state)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	const struct kvaser_usb_dev_ops *ops = priv->dev->driver_info->ops;
+
+	switch (state) {
+	case ETHTOOL_ID_ACTIVE:
+		return 3; /* 3 On/Off cycles per second */
+
+	case ETHTOOL_ID_ON:
+		return ops->dev_set_led(priv, KVASER_USB_LED_ON, 1000);
+
+	case ETHTOOL_ID_OFF:
+		return ops->dev_set_led(priv, KVASER_USB_LED_OFF, 1000);
+
+	case ETHTOOL_ID_INACTIVE:
+		/* Turn LED off and restore standard function after 1ms */
+		return ops->dev_set_led(priv, KVASER_USB_LED_OFF, 1);
+
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops kvaser_usb_netdev_ops = {
 	.ndo_open = kvaser_usb_open,
 	.ndo_stop = kvaser_usb_close,
-	.ndo_eth_ioctl = can_eth_ioctl_hwts,
 	.ndo_start_xmit = kvaser_usb_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
+	.ndo_hwtstamp_get = can_hwtstamp_get,
+	.ndo_hwtstamp_set = can_hwtstamp_set,
 };
 
 static const struct ethtool_ops kvaser_usb_ethtool_ops = {
 	.get_ts_info = can_ethtool_op_get_ts_info_hwts,
+	.set_phys_id = kvaser_usb_set_phys_id,
 };
 
 static void kvaser_usb_remove_interfaces(struct kvaser_usb *dev)
 {
 	const struct kvaser_usb_dev_ops *ops = dev->driver_info->ops;
 	int i;
+	struct kvaser_usb_net_priv *priv;
 
 	for (i = 0; i < dev->nchannels; i++) {
-		if (!dev->nets[i])
+		priv = dev->nets[i];
+		if (!priv)
 			continue;
 
-		unregister_candev(dev->nets[i]->netdev);
+		unregister_candev(priv->netdev);
 	}
 
 	kvaser_usb_unlink_all_urbs(dev);
 
 	for (i = 0; i < dev->nchannels; i++) {
-		if (!dev->nets[i])
+		priv = dev->nets[i];
+		if (!priv)
 			continue;
 
 		if (ops->dev_remove_channel)
-			ops->dev_remove_channel(dev->nets[i]);
+			ops->dev_remove_channel(priv);
 
-		free_candev(dev->nets[i]->netdev);
+		kvaser_usb_devlink_port_unregister(priv);
+		free_candev(priv->netdev);
 	}
 }
 
@@ -818,7 +851,8 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel)
 	init_completion(&priv->stop_comp);
 	init_completion(&priv->flush_comp);
 	init_completion(&priv->get_busparams_comp);
-	priv->can.ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC;
+	priv->can.ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC |
+				       CAN_CTRLMODE_BERR_REPORTING;
 
 	priv->dev = dev;
 	priv->netdev = netdev;
@@ -841,8 +875,8 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel)
 	priv->can.ctrlmode_supported |= dev->card_data.ctrlmode_supported;
 
 	if (priv->can.ctrlmode_supported & CAN_CTRLMODE_FD) {
-		priv->can.data_bittiming_const = dev->cfg->data_bittiming_const;
-		priv->can.do_set_data_bittiming = kvaser_usb_set_data_bittiming;
+		priv->can.fd.data_bittiming_const = dev->cfg->data_bittiming_const;
+		priv->can.fd.do_set_data_bittiming = kvaser_usb_set_data_bittiming;
 	}
 
 	netdev->flags |= IFF_ECHO;
@@ -851,26 +885,35 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel)
 	netdev->ethtool_ops = &kvaser_usb_ethtool_ops;
 	SET_NETDEV_DEV(netdev, &dev->intf->dev);
 	netdev->dev_id = channel;
+	netdev->dev_port = channel;
 
 	dev->nets[channel] = priv;
 
 	if (ops->dev_init_channel) {
 		err = ops->dev_init_channel(priv);
 		if (err)
-			goto err;
+			goto candev_free;
+	}
+
+	err = kvaser_usb_devlink_port_register(priv);
+	if (err) {
+		dev_err(&dev->intf->dev, "Failed to register devlink port\n");
+		goto candev_free;
 	}
 
 	err = register_candev(netdev);
 	if (err) {
 		dev_err(&dev->intf->dev, "Failed to register CAN device\n");
-		goto err;
+		goto unregister_devlink_port;
 	}
 
 	netdev_dbg(netdev, "device registered\n");
 
 	return 0;
 
-err:
+unregister_devlink_port:
+	kvaser_usb_devlink_port_unregister(priv);
+candev_free:
 	free_candev(netdev);
 	dev->nets[channel] = NULL;
 	return err;
@@ -880,6 +923,7 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 			    const struct usb_device_id *id)
 {
 	struct kvaser_usb *dev;
+	struct devlink *devlink;
 	int err;
 	int i;
 	const struct kvaser_usb_driver_info *driver_info;
@@ -889,17 +933,20 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 	if (!driver_info)
 		return -ENODEV;
 
-	dev = devm_kzalloc(&intf->dev, sizeof(*dev), GFP_KERNEL);
-	if (!dev)
+	devlink = devlink_alloc(&kvaser_usb_devlink_ops, sizeof(*dev), &intf->dev);
+	if (!devlink)
 		return -ENOMEM;
 
+	dev = devlink_priv(devlink);
 	dev->intf = intf;
 	dev->driver_info = driver_info;
 	ops = driver_info->ops;
 
 	err = ops->dev_setup_endpoints(dev);
-	if (err)
-		return dev_err_probe(&intf->dev, err, "Cannot get usb endpoint(s)");
+	if (err) {
+		dev_err_probe(&intf->dev, err, "Cannot get usb endpoint(s)");
+		goto free_devlink;
+	}
 
 	dev->udev = interface_to_usbdev(intf);
 
@@ -910,55 +957,66 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 	dev->card_data.ctrlmode_supported = 0;
 	dev->card_data.capabilities = 0;
 	err = ops->dev_init_card(dev);
-	if (err)
-		return dev_err_probe(&intf->dev, err,
-				     "Failed to initialize card\n");
+	if (err) {
+		dev_err_probe(&intf->dev, err,
+			      "Failed to initialize card\n");
+		goto free_devlink;
+	}
 
 	err = ops->dev_get_software_info(dev);
-	if (err)
-		return dev_err_probe(&intf->dev, err,
-				     "Cannot get software info\n");
+	if (err) {
+		dev_err_probe(&intf->dev, err,
+			      "Cannot get software info\n");
+		goto free_devlink;
+	}
 
 	if (ops->dev_get_software_details) {
 		err = ops->dev_get_software_details(dev);
-		if (err)
-			return dev_err_probe(&intf->dev, err,
-					     "Cannot get software details\n");
+		if (err) {
+			dev_err_probe(&intf->dev, err,
+				      "Cannot get software details\n");
+			goto free_devlink;
+		}
 	}
 
-	if (WARN_ON(!dev->cfg))
-		return -ENODEV;
-
-	dev_dbg(&intf->dev, "Firmware version: %d.%d.%d\n",
-		((dev->fw_version >> 24) & 0xff),
-		((dev->fw_version >> 16) & 0xff),
-		(dev->fw_version & 0xffff));
+	if (WARN_ON(!dev->cfg)) {
+		err = -ENODEV;
+		goto free_devlink;
+	}
 
 	dev_dbg(&intf->dev, "Max outstanding tx = %d URBs\n", dev->max_tx_urbs);
 
 	err = ops->dev_get_card_info(dev);
-	if (err)
-		return dev_err_probe(&intf->dev, err,
-				     "Cannot get card info\n");
+	if (err) {
+		dev_err_probe(&intf->dev, err,
+			      "Cannot get card info\n");
+		goto free_devlink;
+	}
 
 	if (ops->dev_get_capabilities) {
 		err = ops->dev_get_capabilities(dev);
 		if (err) {
-			kvaser_usb_remove_interfaces(dev);
-			return dev_err_probe(&intf->dev, err,
-					     "Cannot get capabilities\n");
+			dev_err_probe(&intf->dev, err,
+				      "Cannot get capabilities\n");
+			goto remove_interfaces;
 		}
 	}
 
 	for (i = 0; i < dev->nchannels; i++) {
 		err = kvaser_usb_init_one(dev, i);
-		if (err) {
-			kvaser_usb_remove_interfaces(dev);
-			return err;
-		}
+		if (err)
+			goto remove_interfaces;
 	}
+	devlink_register(devlink);
 
 	return 0;
+
+remove_interfaces:
+	kvaser_usb_remove_interfaces(dev);
+free_devlink:
+	devlink_free(devlink);
+
+	return err;
 }
 
 static void kvaser_usb_disconnect(struct usb_interface *intf)
@@ -971,6 +1029,8 @@ static void kvaser_usb_disconnect(struct usb_interface *intf)
 		return;
 
 	kvaser_usb_remove_interfaces(dev);
+	devlink_unregister(priv_to_devlink(dev));
+	devlink_free(priv_to_devlink(dev));
 }
 
 static struct usb_driver kvaser_usb_driver = {
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_devlink.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_devlink.c
new file mode 100644
index 000000000000..e838b82298ae
--- /dev/null
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_devlink.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/* kvaser_usb devlink functions
+ *
+ * Copyright (C) 2025 KVASER AB, Sweden. All rights reserved.
+ */
+#include "kvaser_usb.h"
+
+#include <linux/netdevice.h>
+#include <net/devlink.h>
+
+#define KVASER_USB_EAN_MSB 0x00073301
+
+static int kvaser_usb_devlink_info_get(struct devlink *devlink,
+				       struct devlink_info_req *req,
+				       struct netlink_ext_ack *extack)
+{
+	struct kvaser_usb *dev = devlink_priv(devlink);
+	char buf[] = "73301XXXXXXXXXX";
+	int ret;
+
+	if (dev->serial_number) {
+		snprintf(buf, sizeof(buf), "%u", dev->serial_number);
+		ret = devlink_info_serial_number_put(req, buf);
+		if (ret)
+			return ret;
+	}
+
+	if (dev->fw_version.major) {
+		snprintf(buf, sizeof(buf), "%u.%u.%u",
+			 dev->fw_version.major,
+			 dev->fw_version.minor,
+			 dev->fw_version.build);
+		ret = devlink_info_version_running_put(req,
+						       DEVLINK_INFO_VERSION_GENERIC_FW,
+						       buf);
+		if (ret)
+			return ret;
+	}
+
+	if (dev->hw_revision) {
+		snprintf(buf, sizeof(buf), "%u", dev->hw_revision);
+		ret = devlink_info_version_fixed_put(req,
+						     DEVLINK_INFO_VERSION_GENERIC_BOARD_REV,
+						     buf);
+		if (ret)
+			return ret;
+	}
+
+	if (dev->ean[1] == KVASER_USB_EAN_MSB) {
+		snprintf(buf, sizeof(buf), "%x%08x", dev->ean[1], dev->ean[0]);
+		ret = devlink_info_version_fixed_put(req,
+						     DEVLINK_INFO_VERSION_GENERIC_BOARD_ID,
+						     buf);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+const struct devlink_ops kvaser_usb_devlink_ops = {
+	.info_get = kvaser_usb_devlink_info_get,
+};
+
+int kvaser_usb_devlink_port_register(struct kvaser_usb_net_priv *priv)
+{
+	int ret;
+	struct devlink_port_attrs attrs = {
+		.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL,
+		.phys.port_number = priv->channel,
+	};
+	devlink_port_attrs_set(&priv->devlink_port, &attrs);
+
+	ret = devlink_port_register(priv_to_devlink(priv->dev),
+				    &priv->devlink_port, priv->channel);
+	if (ret)
+		return ret;
+
+	SET_NETDEV_DEVLINK_PORT(priv->netdev, &priv->devlink_port);
+
+	return 0;
+}
+
+void kvaser_usb_devlink_port_unregister(struct kvaser_usb_net_priv *priv)
+{
+	devlink_port_unregister(&priv->devlink_port);
+}
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index 3764b263add3..a59f20dad692 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -12,6 +12,7 @@
  *    distinguish between ERROR_WARNING and ERROR_ACTIVE.
  */
 
+#include <linux/bitfield.h>
 #include <linux/completion.h>
 #include <linux/device.h>
 #include <linux/gfp.h>
@@ -67,6 +68,8 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_rt;
 #define CMD_SET_BUSPARAMS_RESP			85
 #define CMD_GET_CAPABILITIES_REQ		95
 #define CMD_GET_CAPABILITIES_RESP		96
+#define CMD_LED_ACTION_REQ			101
+#define CMD_LED_ACTION_RESP			102
 #define CMD_RX_MESSAGE				106
 #define CMD_MAP_CHANNEL_REQ			200
 #define CMD_MAP_CHANNEL_RESP			201
@@ -111,7 +114,7 @@ struct kvaser_cmd_card_info {
 	__le32 clock_res;
 	__le32 mfg_date;
 	__le32 ean[2];
-	u8 hw_version;
+	u8 hw_revision;
 	u8 usb_mode;
 	u8 hw_type;
 	u8 reserved0;
@@ -217,6 +220,22 @@ struct kvaser_cmd_get_busparams_res {
 	u8 reserved[20];
 } __packed;
 
+/* The device has two LEDs per CAN channel
+ * The LSB of action field controls the state:
+ *   0 = ON
+ *   1 = OFF
+ * The remaining bits of action field is the LED index
+ */
+#define KVASER_USB_HYDRA_LED_IDX_MASK GENMASK(31, 1)
+#define KVASER_USB_HYDRA_LED_YELLOW_CH0_IDX 3
+#define KVASER_USB_HYDRA_LEDS_PER_CHANNEL 2
+struct kvaser_cmd_led_action_req {
+	u8 action;
+	u8 padding;
+	__le16 duration_ms;
+	u8 reserved[24];
+} __packed;
+
 /* Ctrl modes */
 #define KVASER_USB_HYDRA_CTRLMODE_NORMAL	0x01
 #define KVASER_USB_HYDRA_CTRLMODE_LISTEN	0x02
@@ -299,6 +318,8 @@ struct kvaser_cmd {
 		struct kvaser_cmd_get_busparams_req get_busparams_req;
 		struct kvaser_cmd_get_busparams_res get_busparams_res;
 
+		struct kvaser_cmd_led_action_req led_action_req;
+
 		struct kvaser_cmd_chip_state_event chip_state_event;
 
 		struct kvaser_cmd_set_ctrlmode set_ctrlmode;
@@ -926,6 +947,42 @@ kvaser_usb_hydra_bus_status_to_can_state(const struct kvaser_usb_net_priv *priv,
 	}
 }
 
+static void kvaser_usb_hydra_change_state(struct kvaser_usb_net_priv *priv,
+					  const struct can_berr_counter *bec,
+					  struct can_frame *cf,
+					  enum can_state new_state)
+{
+	struct net_device *netdev = priv->netdev;
+	enum can_state old_state = priv->can.state;
+	enum can_state tx_state, rx_state;
+
+	tx_state = (bec->txerr >= bec->rxerr) ?
+				new_state : CAN_STATE_ERROR_ACTIVE;
+	rx_state = (bec->txerr <= bec->rxerr) ?
+				new_state : CAN_STATE_ERROR_ACTIVE;
+	can_change_state(netdev, cf, tx_state, rx_state);
+
+	if (new_state == CAN_STATE_BUS_OFF && old_state < CAN_STATE_BUS_OFF) {
+		if (priv->can.restart_ms == 0)
+			kvaser_usb_hydra_send_simple_cmd_async(priv, CMD_STOP_CHIP_REQ);
+
+		can_bus_off(netdev);
+	}
+
+	if (priv->can.restart_ms &&
+	    old_state >= CAN_STATE_BUS_OFF &&
+	    new_state < CAN_STATE_BUS_OFF) {
+		priv->can.can_stats.restarts++;
+		if (cf)
+			cf->can_id |= CAN_ERR_RESTARTED;
+	}
+	if (cf && new_state != CAN_STATE_BUS_OFF) {
+		cf->can_id |= CAN_ERR_CNT;
+		cf->data[6] = bec->txerr;
+		cf->data[7] = bec->rxerr;
+	}
+}
+
 static void kvaser_usb_hydra_update_state(struct kvaser_usb_net_priv *priv,
 					  u8 bus_status,
 					  const struct can_berr_counter *bec)
@@ -951,41 +1008,11 @@ static void kvaser_usb_hydra_update_state(struct kvaser_usb_net_priv *priv,
 		return;
 
 	skb = alloc_can_err_skb(netdev, &cf);
-	if (skb) {
-		enum can_state tx_state, rx_state;
-
-		tx_state = (bec->txerr >= bec->rxerr) ?
-					new_state : CAN_STATE_ERROR_ACTIVE;
-		rx_state = (bec->txerr <= bec->rxerr) ?
-					new_state : CAN_STATE_ERROR_ACTIVE;
-		can_change_state(netdev, cf, tx_state, rx_state);
-	}
-
-	if (new_state == CAN_STATE_BUS_OFF && old_state < CAN_STATE_BUS_OFF) {
-		if (!priv->can.restart_ms)
-			kvaser_usb_hydra_send_simple_cmd_async
-						(priv, CMD_STOP_CHIP_REQ);
-
-		can_bus_off(netdev);
-	}
-
-	if (!skb) {
+	kvaser_usb_hydra_change_state(priv, bec, cf, new_state);
+	if (skb)
+		netif_rx(skb);
+	else
 		netdev_warn(netdev, "No memory left for err_skb\n");
-		return;
-	}
-
-	if (priv->can.restart_ms &&
-	    old_state >= CAN_STATE_BUS_OFF &&
-	    new_state < CAN_STATE_BUS_OFF)
-		priv->can.can_stats.restarts++;
-
-	if (new_state != CAN_STATE_BUS_OFF) {
-		cf->can_id |= CAN_ERR_CNT;
-		cf->data[6] = bec->txerr;
-		cf->data[7] = bec->rxerr;
-	}
-
-	netif_rx(skb);
 }
 
 static void kvaser_usb_hydra_state_event(const struct kvaser_usb *dev,
@@ -1078,9 +1105,8 @@ kvaser_usb_hydra_error_frame(struct kvaser_usb_net_priv *priv,
 {
 	struct net_device *netdev = priv->netdev;
 	struct net_device_stats *stats = &netdev->stats;
-	struct can_frame *cf;
-	struct sk_buff *skb;
-	struct skb_shared_hwtstamps *shhwtstamps;
+	struct can_frame *cf = NULL;
+	struct sk_buff *skb = NULL;
 	struct can_berr_counter bec;
 	enum can_state new_state, old_state;
 	u8 bus_status;
@@ -1096,52 +1122,26 @@ kvaser_usb_hydra_error_frame(struct kvaser_usb_net_priv *priv,
 	kvaser_usb_hydra_bus_status_to_can_state(priv, bus_status, &bec,
 						 &new_state);
 
-	skb = alloc_can_err_skb(netdev, &cf);
+	if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)
+		skb = alloc_can_err_skb(netdev, &cf);
+	if (new_state != old_state)
+		kvaser_usb_hydra_change_state(priv, &bec, cf, new_state);
 
-	if (new_state != old_state) {
+	if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) {
 		if (skb) {
-			enum can_state tx_state, rx_state;
-
-			tx_state = (bec.txerr >= bec.rxerr) ?
-					new_state : CAN_STATE_ERROR_ACTIVE;
-			rx_state = (bec.txerr <= bec.rxerr) ?
-					new_state : CAN_STATE_ERROR_ACTIVE;
-
-			can_change_state(netdev, cf, tx_state, rx_state);
-
-			if (priv->can.restart_ms &&
-			    old_state >= CAN_STATE_BUS_OFF &&
-			    new_state < CAN_STATE_BUS_OFF)
-				cf->can_id |= CAN_ERR_RESTARTED;
-		}
-
-		if (new_state == CAN_STATE_BUS_OFF) {
-			if (!priv->can.restart_ms)
-				kvaser_usb_hydra_send_simple_cmd_async
-						(priv, CMD_STOP_CHIP_REQ);
+			struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
 
-			can_bus_off(netdev);
+			shhwtstamps->hwtstamp = hwtstamp;
+			cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_CNT;
+			cf->data[6] = bec.txerr;
+			cf->data[7] = bec.rxerr;
+			netif_rx(skb);
+		} else {
+			stats->rx_dropped++;
+			netdev_warn(netdev, "No memory left for err_skb\n");
 		}
 	}
 
-	if (!skb) {
-		stats->rx_dropped++;
-		netdev_warn(netdev, "No memory left for err_skb\n");
-		return;
-	}
-
-	shhwtstamps = skb_hwtstamps(skb);
-	shhwtstamps->hwtstamp = hwtstamp;
-
-	cf->can_id |= CAN_ERR_BUSERROR;
-	if (new_state != CAN_STATE_BUS_OFF) {
-		cf->can_id |= CAN_ERR_CNT;
-		cf->data[6] = bec.txerr;
-		cf->data[7] = bec.rxerr;
-	}
-
-	netif_rx(skb);
-
 	priv->bec.txerr = bec.txerr;
 	priv->bec.rxerr = bec.rxerr;
 }
@@ -1411,6 +1411,7 @@ static void kvaser_usb_hydra_handle_cmd_std(const struct kvaser_usb *dev,
 	/* Ignored commands */
 	case CMD_SET_BUSPARAMS_RESP:
 	case CMD_SET_BUSPARAMS_FD_RESP:
+	case CMD_LED_ACTION_RESP:
 		break;
 
 	default:
@@ -1838,6 +1839,7 @@ static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev)
 	size_t cmd_len;
 	int err;
 	u32 flags;
+	u32 fw_version;
 	struct kvaser_usb_dev_card_data *card_data = &dev->card_data;
 
 	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
@@ -1862,7 +1864,10 @@ static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev)
 	if (err)
 		goto end;
 
-	dev->fw_version = le32_to_cpu(cmd->sw_detail_res.sw_version);
+	fw_version = le32_to_cpu(cmd->sw_detail_res.sw_version);
+	dev->fw_version.major = FIELD_GET(KVASER_USB_SW_VERSION_MAJOR_MASK, fw_version);
+	dev->fw_version.minor = FIELD_GET(KVASER_USB_SW_VERSION_MINOR_MASK, fw_version);
+	dev->fw_version.build = FIELD_GET(KVASER_USB_SW_VERSION_BUILD_MASK, fw_version);
 	flags = le32_to_cpu(cmd->sw_detail_res.sw_flags);
 
 	if (flags & KVASER_USB_HYDRA_SW_FLAG_FW_BAD) {
@@ -1913,6 +1918,10 @@ static int kvaser_usb_hydra_get_card_info(struct kvaser_usb *dev)
 	err = kvaser_usb_hydra_wait_cmd(dev, CMD_GET_CARD_INFO_RESP, &cmd);
 	if (err)
 		return err;
+	dev->ean[1] = le32_to_cpu(cmd.card_info.ean[1]);
+	dev->ean[0] = le32_to_cpu(cmd.card_info.ean[0]);
+	dev->serial_number = le32_to_cpu(cmd.card_info.serial_number);
+	dev->hw_revision = cmd.card_info.hw_revision;
 
 	dev->nchannels = cmd.card_info.nchannels;
 	if (dev->nchannels > KVASER_USB_MAX_NET_DEVICES)
@@ -1967,6 +1976,36 @@ static int kvaser_usb_hydra_get_capabilities(struct kvaser_usb *dev)
 	return 0;
 }
 
+static int kvaser_usb_hydra_set_led(struct kvaser_usb_net_priv *priv,
+				    enum kvaser_usb_led_state state,
+				    u16 duration_ms)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct kvaser_cmd *cmd;
+	size_t cmd_len;
+	int ret;
+
+	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = CMD_LED_ACTION_REQ;
+	cmd_len = kvaser_usb_hydra_cmd_size(cmd);
+	kvaser_usb_hydra_set_cmd_dest_he(cmd, dev->card_data.hydra.sysdbg_he);
+	kvaser_usb_hydra_set_cmd_transid(cmd, kvaser_usb_hydra_get_next_transid(dev));
+
+	cmd->led_action_req.duration_ms = cpu_to_le16(duration_ms);
+	cmd->led_action_req.action = state |
+				     FIELD_PREP(KVASER_USB_HYDRA_LED_IDX_MASK,
+						KVASER_USB_HYDRA_LED_YELLOW_CH0_IDX +
+						KVASER_USB_HYDRA_LEDS_PER_CHANNEL * priv->channel);
+
+	ret = kvaser_usb_send_cmd(dev, cmd, cmd_len);
+	kfree(cmd);
+
+	return ret;
+}
+
 static int kvaser_usb_hydra_set_opt_mode(const struct kvaser_usb_net_priv *priv)
 {
 	struct kvaser_usb *dev = priv->dev;
@@ -2170,6 +2209,7 @@ const struct kvaser_usb_dev_ops kvaser_usb_hydra_dev_ops = {
 	.dev_get_software_details = kvaser_usb_hydra_get_software_details,
 	.dev_get_card_info = kvaser_usb_hydra_get_card_info,
 	.dev_get_capabilities = kvaser_usb_hydra_get_capabilities,
+	.dev_set_led = kvaser_usb_hydra_set_led,
 	.dev_set_opt_mode = kvaser_usb_hydra_set_opt_mode,
 	.dev_start_chip = kvaser_usb_hydra_start_chip,
 	.dev_stop_chip = kvaser_usb_hydra_stop_chip,
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 6b9122ab1464..1167d38344f1 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -10,6 +10,7 @@
  * Copyright (C) 2015 Valeo S.A.
  */
 
+#include <linux/bitfield.h>
 #include <linux/completion.h>
 #include <linux/device.h>
 #include <linux/gfp.h>
@@ -81,6 +82,8 @@
 #define CMD_FLUSH_QUEUE_REPLY		68
 #define CMD_GET_CAPABILITIES_REQ	95
 #define CMD_GET_CAPABILITIES_RESP	96
+#define CMD_LED_ACTION_REQ		101
+#define CMD_LED_ACTION_RESP		102
 
 #define CMD_LEAF_LOG_MESSAGE		106
 
@@ -135,7 +138,7 @@ struct kvaser_cmd_cardinfo {
 	__le32 padding0;
 	__le32 clock_resolution;
 	__le32 mfgdate;
-	u8 ean[8];
+	__le32 ean[2];
 	u8 hw_revision;
 	union {
 		struct {
@@ -173,6 +176,21 @@ struct kvaser_cmd_busparams {
 	struct kvaser_usb_busparams busparams;
 } __packed;
 
+/* The device has one LED per CAN channel
+ * The LSB of action field controls the state:
+ *   0 = ON
+ *   1 = OFF
+ * The remaining bits of action field is the LED index
+ */
+#define KVASER_USB_LEAF_LED_IDX_MASK GENMASK(31, 1)
+#define KVASER_USB_LEAF_LED_YELLOW_CH0_IDX 2
+struct kvaser_cmd_led_action_req {
+	u8 tid;
+	u8 action;
+	__le16 duration_ms;
+	u8 padding[24];
+} __packed;
+
 struct kvaser_cmd_tx_can {
 	u8 channel;
 	u8 tid;
@@ -359,6 +377,8 @@ struct kvaser_cmd {
 		struct kvaser_cmd_cardinfo cardinfo;
 		struct kvaser_cmd_busparams busparams;
 
+		struct kvaser_cmd_led_action_req led_action_req;
+
 		struct kvaser_cmd_rx_can_header rx_can_header;
 		struct kvaser_cmd_tx_acknowledge_header tx_acknowledge_header;
 
@@ -409,6 +429,7 @@ static const u8 kvaser_usb_leaf_cmd_sizes_leaf[] = {
 	[CMD_ERROR_EVENT]		= kvaser_fsize(u.leaf.error_event),
 	/* ignored events: */
 	[CMD_FLUSH_QUEUE_REPLY]		= CMD_SIZE_ANY,
+	[CMD_LED_ACTION_RESP]		= CMD_SIZE_ANY,
 };
 
 static const u8 kvaser_usb_leaf_cmd_sizes_usbcan[] = {
@@ -423,6 +444,8 @@ static const u8 kvaser_usb_leaf_cmd_sizes_usbcan[] = {
 	[CMD_CAN_ERROR_EVENT]		= kvaser_fsize(u.usbcan.can_error_event),
 	[CMD_ERROR_EVENT]		= kvaser_fsize(u.usbcan.error_event),
 	[CMD_USBCAN_CLOCK_OVERFLOW_EVENT] = kvaser_fsize(u.usbcan.clk_overflow_event),
+	/* ignored events: */
+	[CMD_LED_ACTION_RESP]		= CMD_SIZE_ANY,
 };
 
 /* Summary of a kvaser error event, for a unified Leaf/Usbcan error
@@ -662,7 +685,7 @@ static int kvaser_usb_leaf_wait_cmd(const struct kvaser_usb *dev, u8 id,
 			 * for further details.
 			 */
 			if (tmp->len == 0) {
-				pos = round_up(pos,
+				pos = round_up(pos + 1,
 					       le16_to_cpu
 						(dev->bulk_in->wMaxPacketSize));
 				continue;
@@ -718,9 +741,13 @@ static int kvaser_usb_leaf_send_simple_cmd(const struct kvaser_usb *dev,
 static void kvaser_usb_leaf_get_software_info_leaf(struct kvaser_usb *dev,
 						   const struct leaf_cmd_softinfo *softinfo)
 {
+	u32 fw_version;
 	u32 sw_options = le32_to_cpu(softinfo->sw_options);
 
-	dev->fw_version = le32_to_cpu(softinfo->fw_version);
+	fw_version = le32_to_cpu(softinfo->fw_version);
+	dev->fw_version.major = FIELD_GET(KVASER_USB_SW_VERSION_MAJOR_MASK, fw_version);
+	dev->fw_version.minor = FIELD_GET(KVASER_USB_SW_VERSION_MINOR_MASK, fw_version);
+	dev->fw_version.build = FIELD_GET(KVASER_USB_SW_VERSION_BUILD_MASK, fw_version);
 	dev->max_tx_urbs = le16_to_cpu(softinfo->max_outstanding_tx);
 
 	if (sw_options & KVASER_USB_LEAF_SWOPTION_EXT_CAP)
@@ -761,6 +788,7 @@ static int kvaser_usb_leaf_get_software_info_inner(struct kvaser_usb *dev)
 {
 	struct kvaser_cmd cmd;
 	int err;
+	u32 fw_version;
 
 	err = kvaser_usb_leaf_send_simple_cmd(dev, CMD_GET_SOFTWARE_INFO, 0);
 	if (err)
@@ -775,7 +803,13 @@ static int kvaser_usb_leaf_get_software_info_inner(struct kvaser_usb *dev)
 		kvaser_usb_leaf_get_software_info_leaf(dev, &cmd.u.leaf.softinfo);
 		break;
 	case KVASER_USBCAN:
-		dev->fw_version = le32_to_cpu(cmd.u.usbcan.softinfo.fw_version);
+		fw_version = le32_to_cpu(cmd.u.usbcan.softinfo.fw_version);
+		dev->fw_version.major = FIELD_GET(KVASER_USB_SW_VERSION_MAJOR_MASK,
+						  fw_version);
+		dev->fw_version.minor = FIELD_GET(KVASER_USB_SW_VERSION_MINOR_MASK,
+						  fw_version);
+		dev->fw_version.build = FIELD_GET(KVASER_USB_SW_VERSION_BUILD_MASK,
+						  fw_version);
 		dev->max_tx_urbs =
 			le16_to_cpu(cmd.u.usbcan.softinfo.max_outstanding_tx);
 		dev->cfg = &kvaser_usb_leaf_usbcan_dev_cfg;
@@ -820,6 +854,10 @@ static int kvaser_usb_leaf_get_card_info(struct kvaser_usb *dev)
 	    (dev->driver_info->family == KVASER_USBCAN &&
 	     dev->nchannels > MAX_USBCAN_NET_DEVICES))
 		return -EINVAL;
+	dev->ean[1] = le32_to_cpu(cmd.u.cardinfo.ean[1]);
+	dev->ean[0] = le32_to_cpu(cmd.u.cardinfo.ean[0]);
+	dev->serial_number = le32_to_cpu(cmd.u.cardinfo.serial_number);
+	dev->hw_revision = cmd.u.cardinfo.hw_revision;
 
 	return 0;
 }
@@ -924,6 +962,34 @@ static int kvaser_usb_leaf_get_capabilities_leaf(struct kvaser_usb *dev)
 	return 0;
 }
 
+static int kvaser_usb_leaf_set_led(struct kvaser_usb_net_priv *priv,
+				   enum kvaser_usb_led_state state,
+				   u16 duration_ms)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct kvaser_cmd *cmd;
+	int ret;
+
+	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->id = CMD_LED_ACTION_REQ;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_led_action_req);
+	cmd->u.led_action_req.tid = 0xff;
+
+	cmd->u.led_action_req.duration_ms = cpu_to_le16(duration_ms);
+	cmd->u.led_action_req.action = state |
+				       FIELD_PREP(KVASER_USB_LEAF_LED_IDX_MASK,
+						  KVASER_USB_LEAF_LED_YELLOW_CH0_IDX +
+						  priv->channel);
+
+	ret = kvaser_usb_send_cmd(dev, cmd, cmd->len);
+	kfree(cmd);
+
+	return ret;
+}
+
 static int kvaser_usb_leaf_get_capabilities(struct kvaser_usb *dev)
 {
 	int err = 0;
@@ -1120,10 +1186,8 @@ kvaser_usb_leaf_rx_error_update_can_state(struct kvaser_usb_net_priv *priv,
 static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev,
 				     const struct kvaser_usb_err_summary *es)
 {
-	struct can_frame *cf;
-	struct can_frame tmp_cf = { .can_id = CAN_ERR_FLAG,
-				    .len = CAN_ERR_DLC };
-	struct sk_buff *skb;
+	struct can_frame *cf = NULL;
+	struct sk_buff *skb = NULL;
 	struct net_device_stats *stats;
 	struct kvaser_usb_net_priv *priv;
 	struct kvaser_usb_net_leaf_priv *leaf;
@@ -1143,18 +1207,10 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev,
 	if (!netif_running(priv->netdev))
 		return;
 
-	/* Update all of the CAN interface's state and error counters before
-	 * trying any memory allocation that can actually fail with -ENOMEM.
-	 *
-	 * We send a temporary stack-allocated error CAN frame to
-	 * can_change_state() for the very same reason.
-	 *
-	 * TODO: Split can_change_state() responsibility between updating the
-	 * CAN interface's state and counters, and the setting up of CAN error
-	 * frame ID and data to userspace. Remove stack allocation afterwards.
-	 */
 	old_state = priv->can.state;
-	kvaser_usb_leaf_rx_error_update_can_state(priv, es, &tmp_cf);
+	if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)
+		skb = alloc_can_err_skb(priv->netdev, &cf);
+	kvaser_usb_leaf_rx_error_update_can_state(priv, es, cf);
 	new_state = priv->can.state;
 
 	/* If there are errors, request status updates periodically as we do
@@ -1168,13 +1224,6 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev,
 		schedule_delayed_work(&leaf->chip_state_req_work,
 				      msecs_to_jiffies(500));
 
-	skb = alloc_can_err_skb(priv->netdev, &cf);
-	if (!skb) {
-		stats->rx_dropped++;
-		return;
-	}
-	memcpy(cf, &tmp_cf, sizeof(*cf));
-
 	if (new_state != old_state) {
 		if (es->status &
 		    (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) {
@@ -1187,11 +1236,20 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev,
 		if (priv->can.restart_ms &&
 		    old_state == CAN_STATE_BUS_OFF &&
 		    new_state < CAN_STATE_BUS_OFF) {
-			cf->can_id |= CAN_ERR_RESTARTED;
+			if (cf)
+				cf->can_id |= CAN_ERR_RESTARTED;
 			netif_carrier_on(priv->netdev);
 		}
 	}
 
+	if (!skb) {
+		if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) {
+			stats->rx_dropped++;
+			netdev_warn(priv->netdev, "No memory left for err_skb\n");
+		}
+		return;
+	}
+
 	switch (dev->driver_info->family) {
 	case KVASER_LEAF:
 		if (es->leaf.error_factor) {
@@ -1646,6 +1704,8 @@ static void kvaser_usb_leaf_handle_command(struct kvaser_usb *dev,
 		if (dev->driver_info->family != KVASER_LEAF)
 			goto warn;
 		break;
+	case CMD_LED_ACTION_RESP:
+		break;
 
 	default:
 warn:		dev_warn(&dev->intf->dev, "Unhandled command (%d)\n", cmd->id);
@@ -1672,7 +1732,7 @@ static void kvaser_usb_leaf_read_bulk_callback(struct kvaser_usb *dev,
 		 * number of events in case of a heavy rx load on the bus.
 		 */
 		if (cmd->len == 0) {
-			pos = round_up(pos, le16_to_cpu
+			pos = round_up(pos + 1, le16_to_cpu
 						(dev->bulk_in->wMaxPacketSize));
 			continue;
 		}
@@ -1935,6 +1995,7 @@ const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops = {
 	.dev_get_software_details = NULL,
 	.dev_get_card_info = kvaser_usb_leaf_get_card_info,
 	.dev_get_capabilities = kvaser_usb_leaf_get_capabilities,
+	.dev_set_led = kvaser_usb_leaf_set_led,
 	.dev_set_opt_mode = kvaser_usb_leaf_set_opt_mode,
 	.dev_start_chip = kvaser_usb_leaf_start_chip,
 	.dev_stop_chip = kvaser_usb_leaf_stop_chip,
diff --git a/drivers/net/can/usb/nct6694_canfd.c b/drivers/net/can/usb/nct6694_canfd.c
new file mode 100644
index 000000000000..dd6df2ec3742
--- /dev/null
+++ b/drivers/net/can/usb/nct6694_canfd.c
@@ -0,0 +1,831 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Nuvoton NCT6694 Socket CANfd driver based on USB interface.
+ *
+ * Copyright (C) 2025 Nuvoton Technology Corp.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/can/dev.h>
+#include <linux/can/rx-offload.h>
+#include <linux/ethtool.h>
+#include <linux/idr.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/mfd/nct6694.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/platform_device.h>
+
+#define DEVICE_NAME "nct6694-canfd"
+
+/* USB command module type for NCT6694 CANfd controller.
+ * This defines the module type used for communication with the NCT6694
+ * CANfd controller over the USB interface.
+ */
+#define NCT6694_CANFD_MOD			0x05
+
+/* Command 00h - CAN Setting and Initialization */
+#define NCT6694_CANFD_SETTING			0x00
+#define NCT6694_CANFD_SETTING_ACTIVE_CTRL1	BIT(0)
+#define NCT6694_CANFD_SETTING_ACTIVE_CTRL2	BIT(1)
+#define NCT6694_CANFD_SETTING_ACTIVE_NBTP_DBTP	BIT(2)
+#define NCT6694_CANFD_SETTING_CTRL1_MON		BIT(0)
+#define NCT6694_CANFD_SETTING_CTRL1_NISO	BIT(1)
+#define NCT6694_CANFD_SETTING_CTRL1_LBCK	BIT(2)
+#define NCT6694_CANFD_SETTING_NBTP_NTSEG2	GENMASK(6, 0)
+#define NCT6694_CANFD_SETTING_NBTP_NTSEG1	GENMASK(15, 8)
+#define NCT6694_CANFD_SETTING_NBTP_NBRP		GENMASK(24, 16)
+#define NCT6694_CANFD_SETTING_NBTP_NSJW		GENMASK(31, 25)
+#define NCT6694_CANFD_SETTING_DBTP_DSJW		GENMASK(3, 0)
+#define NCT6694_CANFD_SETTING_DBTP_DTSEG2	GENMASK(7, 4)
+#define NCT6694_CANFD_SETTING_DBTP_DTSEG1	GENMASK(12, 8)
+#define NCT6694_CANFD_SETTING_DBTP_DBRP		GENMASK(20, 16)
+#define NCT6694_CANFD_SETTING_DBTP_TDC		BIT(23)
+
+/* Command 01h - CAN Information */
+#define NCT6694_CANFD_INFORMATION		0x01
+#define NCT6694_CANFD_INFORMATION_SEL		0x00
+
+/* Command 02h - CAN Event */
+#define NCT6694_CANFD_EVENT			0x02
+#define NCT6694_CANFD_EVENT_SEL(idx, mask)	\
+	((idx ? 0x80 : 0x00) | ((mask) & 0x7F))
+
+#define NCT6694_CANFD_EVENT_MASK		GENMASK(5, 0)
+#define NCT6694_CANFD_EVT_TX_FIFO_EMPTY		BIT(7)	/* Read-clear */
+#define NCT6694_CANFD_EVT_RX_DATA_LOST		BIT(5)	/* Read-clear */
+#define NCT6694_CANFD_EVT_RX_DATA_IN		BIT(7)	/* Read-clear */
+
+/* Command 10h - CAN Deliver */
+#define NCT6694_CANFD_DELIVER			0x10
+#define NCT6694_CANFD_DELIVER_SEL(buf_cnt)	\
+	((buf_cnt) & 0xFF)
+
+/* Command 11h - CAN Receive */
+#define NCT6694_CANFD_RECEIVE			0x11
+#define NCT6694_CANFD_RECEIVE_SEL(idx, buf_cnt)	\
+	((idx ? 0x80 : 0x00) | ((buf_cnt) & 0x7F))
+
+#define NCT6694_CANFD_FRAME_TAG(idx)		(0xC0 | (idx))
+#define NCT6694_CANFD_FRAME_FLAG_EFF		BIT(0)
+#define NCT6694_CANFD_FRAME_FLAG_RTR		BIT(1)
+#define NCT6694_CANFD_FRAME_FLAG_FD		BIT(2)
+#define NCT6694_CANFD_FRAME_FLAG_BRS		BIT(3)
+#define NCT6694_CANFD_FRAME_FLAG_ERR		BIT(4)
+
+#define NCT6694_NAPI_WEIGHT			32
+
+enum nct6694_event_err {
+	NCT6694_CANFD_EVT_ERR_NO_ERROR = 0,
+	NCT6694_CANFD_EVT_ERR_CRC_ERROR,
+	NCT6694_CANFD_EVT_ERR_STUFF_ERROR,
+	NCT6694_CANFD_EVT_ERR_ACK_ERROR,
+	NCT6694_CANFD_EVT_ERR_FORM_ERROR,
+	NCT6694_CANFD_EVT_ERR_BIT_ERROR,
+	NCT6694_CANFD_EVT_ERR_TIMEOUT_ERROR,
+	NCT6694_CANFD_EVT_ERR_UNKNOWN_ERROR,
+};
+
+enum nct6694_event_status {
+	NCT6694_CANFD_EVT_STS_ERROR_ACTIVE = 0,
+	NCT6694_CANFD_EVT_STS_ERROR_PASSIVE,
+	NCT6694_CANFD_EVT_STS_BUS_OFF,
+	NCT6694_CANFD_EVT_STS_WARNING,
+};
+
+struct __packed nct6694_canfd_setting {
+	__le32 nbr;
+	__le32 dbr;
+	u8 active;
+	u8 reserved[3];
+	__le16 ctrl1;
+	__le16 ctrl2;
+	__le32 nbtp;
+	__le32 dbtp;
+};
+
+struct __packed nct6694_canfd_information {
+	u8 tx_fifo_cnt;
+	u8 rx_fifo_cnt;
+	u8 reserved[2];
+	__le32 can_clk;
+};
+
+struct __packed nct6694_canfd_event {
+	u8 err;
+	u8 status;
+	u8 tx_evt;
+	u8 rx_evt;
+	u8 rec;
+	u8 tec;
+	u8 reserved[2];
+};
+
+struct __packed nct6694_canfd_frame {
+	u8 tag;
+	u8 flag;
+	u8 reserved;
+	u8 length;
+	__le32 id;
+	u8 data[CANFD_MAX_DLEN];
+};
+
+struct nct6694_canfd_priv {
+	struct can_priv can;	/* must be the first member */
+	struct can_rx_offload offload;
+	struct net_device *ndev;
+	struct nct6694 *nct6694;
+	struct workqueue_struct *wq;
+	struct work_struct tx_work;
+	struct nct6694_canfd_frame tx;
+	struct nct6694_canfd_frame rx;
+	struct nct6694_canfd_event event[2];
+	struct can_berr_counter bec;
+};
+
+static inline struct nct6694_canfd_priv *rx_offload_to_priv(struct can_rx_offload *offload)
+{
+	return container_of(offload, struct nct6694_canfd_priv, offload);
+}
+
+static const struct can_bittiming_const nct6694_canfd_bittiming_nominal_const = {
+	.name = DEVICE_NAME,
+	.tseg1_min = 1,
+	.tseg1_max = 256,
+	.tseg2_min = 1,
+	.tseg2_max = 128,
+	.sjw_max = 128,
+	.brp_min = 1,
+	.brp_max = 512,
+	.brp_inc = 1,
+};
+
+static const struct can_bittiming_const nct6694_canfd_bittiming_data_const = {
+	.name = DEVICE_NAME,
+	.tseg1_min = 1,
+	.tseg1_max = 32,
+	.tseg2_min = 1,
+	.tseg2_max = 16,
+	.sjw_max = 16,
+	.brp_min = 1,
+	.brp_max = 32,
+	.brp_inc = 1,
+};
+
+static void nct6694_canfd_rx_offload(struct can_rx_offload *offload,
+				     struct sk_buff *skb)
+{
+	struct nct6694_canfd_priv *priv = rx_offload_to_priv(offload);
+	int ret;
+
+	ret = can_rx_offload_queue_tail(offload, skb);
+	if (ret)
+		priv->ndev->stats.rx_fifo_errors++;
+}
+
+static void nct6694_canfd_handle_lost_msg(struct net_device *ndev)
+{
+	struct nct6694_canfd_priv *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+
+	netdev_dbg(ndev, "RX FIFO overflow, message(s) lost.\n");
+
+	stats->rx_errors++;
+	stats->rx_over_errors++;
+
+	skb = alloc_can_err_skb(ndev, &cf);
+	if (!skb)
+		return;
+
+	cf->can_id |= CAN_ERR_CRTL;
+	cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
+
+	nct6694_canfd_rx_offload(&priv->offload, skb);
+}
+
+static void nct6694_canfd_handle_rx(struct net_device *ndev, u8 rx_evt)
+{
+	struct net_device_stats *stats = &ndev->stats;
+	struct nct6694_canfd_priv *priv = netdev_priv(ndev);
+	struct nct6694_canfd_frame *frame = &priv->rx;
+	const struct nct6694_cmd_header cmd_hd = {
+		.mod = NCT6694_CANFD_MOD,
+		.cmd = NCT6694_CANFD_RECEIVE,
+		.sel = NCT6694_CANFD_RECEIVE_SEL(ndev->dev_port, 1),
+		.len = cpu_to_le16(sizeof(*frame))
+	};
+	struct sk_buff *skb;
+	int ret;
+
+	ret = nct6694_read_msg(priv->nct6694, &cmd_hd, frame);
+	if (ret)
+		return;
+
+	if (frame->flag & NCT6694_CANFD_FRAME_FLAG_FD) {
+		struct canfd_frame *cfd;
+
+		skb = alloc_canfd_skb(priv->ndev, &cfd);
+		if (!skb) {
+			stats->rx_dropped++;
+			return;
+		}
+
+		cfd->can_id = le32_to_cpu(frame->id);
+		cfd->len = canfd_sanitize_len(frame->length);
+		if (frame->flag & NCT6694_CANFD_FRAME_FLAG_EFF)
+			cfd->can_id |= CAN_EFF_FLAG;
+		if (frame->flag & NCT6694_CANFD_FRAME_FLAG_BRS)
+			cfd->flags |= CANFD_BRS;
+		if (frame->flag & NCT6694_CANFD_FRAME_FLAG_ERR)
+			cfd->flags |= CANFD_ESI;
+
+		memcpy(cfd->data, frame->data, cfd->len);
+	} else {
+		struct can_frame *cf;
+
+		skb = alloc_can_skb(priv->ndev, &cf);
+		if (!skb) {
+			stats->rx_dropped++;
+			return;
+		}
+
+		cf->can_id = le32_to_cpu(frame->id);
+		cf->len = can_cc_dlc2len(frame->length);
+		if (frame->flag & NCT6694_CANFD_FRAME_FLAG_EFF)
+			cf->can_id |= CAN_EFF_FLAG;
+
+		if (frame->flag & NCT6694_CANFD_FRAME_FLAG_RTR)
+			cf->can_id |= CAN_RTR_FLAG;
+		else
+			memcpy(cf->data, frame->data, cf->len);
+	}
+
+	nct6694_canfd_rx_offload(&priv->offload, skb);
+}
+
+static int nct6694_canfd_get_berr_counter(const struct net_device *ndev,
+					  struct can_berr_counter *bec)
+{
+	struct nct6694_canfd_priv *priv = netdev_priv(ndev);
+
+	*bec = priv->bec;
+
+	return 0;
+}
+
+static void nct6694_canfd_handle_state_change(struct net_device *ndev, u8 status)
+{
+	struct nct6694_canfd_priv *priv = netdev_priv(ndev);
+	enum can_state new_state, rx_state, tx_state;
+	struct can_berr_counter bec;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+
+	nct6694_canfd_get_berr_counter(ndev, &bec);
+	can_state_get_by_berr_counter(ndev, &bec, &tx_state, &rx_state);
+
+	new_state = max(tx_state, rx_state);
+
+	/* state hasn't changed */
+	if (new_state == priv->can.state)
+		return;
+
+	skb = alloc_can_err_skb(ndev, &cf);
+
+	can_change_state(ndev, cf, tx_state, rx_state);
+
+	if (new_state == CAN_STATE_BUS_OFF) {
+		can_bus_off(ndev);
+	} else if (cf) {
+		cf->can_id |= CAN_ERR_CNT;
+		cf->data[6] = bec.txerr;
+		cf->data[7] = bec.rxerr;
+	}
+
+	if (skb)
+		nct6694_canfd_rx_offload(&priv->offload, skb);
+}
+
+static void nct6694_canfd_handle_bus_err(struct net_device *ndev, u8 bus_err)
+{
+	struct nct6694_canfd_priv *priv = netdev_priv(ndev);
+	struct can_frame *cf;
+	struct sk_buff *skb;
+
+	priv->can.can_stats.bus_error++;
+
+	skb = alloc_can_err_skb(ndev, &cf);
+	if (cf)
+		cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR;
+
+	switch (bus_err) {
+	case NCT6694_CANFD_EVT_ERR_CRC_ERROR:
+		netdev_dbg(ndev, "CRC error\n");
+		ndev->stats.rx_errors++;
+		if (cf)
+			cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+		break;
+
+	case NCT6694_CANFD_EVT_ERR_STUFF_ERROR:
+		netdev_dbg(ndev, "Stuff error\n");
+		ndev->stats.rx_errors++;
+		if (cf)
+			cf->data[2] |= CAN_ERR_PROT_STUFF;
+		break;
+
+	case NCT6694_CANFD_EVT_ERR_ACK_ERROR:
+		netdev_dbg(ndev, "Ack error\n");
+		ndev->stats.tx_errors++;
+		if (cf) {
+			cf->can_id |= CAN_ERR_ACK;
+			cf->data[2] |= CAN_ERR_PROT_TX;
+		}
+		break;
+
+	case NCT6694_CANFD_EVT_ERR_FORM_ERROR:
+		netdev_dbg(ndev, "Form error\n");
+		ndev->stats.rx_errors++;
+		if (cf)
+			cf->data[2] |= CAN_ERR_PROT_FORM;
+		break;
+
+	case NCT6694_CANFD_EVT_ERR_BIT_ERROR:
+		netdev_dbg(ndev, "Bit error\n");
+		ndev->stats.tx_errors++;
+		if (cf)
+			cf->data[2] |= CAN_ERR_PROT_TX | CAN_ERR_PROT_BIT;
+		break;
+
+	default:
+		break;
+	}
+
+	if (skb)
+		nct6694_canfd_rx_offload(&priv->offload, skb);
+}
+
+static void nct6694_canfd_handle_tx(struct net_device *ndev)
+{
+	struct nct6694_canfd_priv *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+
+	stats->tx_bytes += can_rx_offload_get_echo_skb_queue_tail(&priv->offload,
+								  0, NULL);
+	stats->tx_packets++;
+	netif_wake_queue(ndev);
+}
+
+static irqreturn_t nct6694_canfd_irq(int irq, void *data)
+{
+	struct net_device *ndev = data;
+	struct nct6694_canfd_priv *priv = netdev_priv(ndev);
+	struct nct6694_canfd_event *event = &priv->event[ndev->dev_port];
+	const struct nct6694_cmd_header cmd_hd = {
+		.mod = NCT6694_CANFD_MOD,
+		.cmd = NCT6694_CANFD_EVENT,
+		.sel = NCT6694_CANFD_EVENT_SEL(ndev->dev_port, NCT6694_CANFD_EVENT_MASK),
+		.len = cpu_to_le16(sizeof(priv->event))
+	};
+	irqreturn_t handled = IRQ_NONE;
+	int ret;
+
+	ret = nct6694_read_msg(priv->nct6694, &cmd_hd, priv->event);
+	if (ret < 0)
+		return handled;
+
+	if (event->rx_evt & NCT6694_CANFD_EVT_RX_DATA_IN) {
+		nct6694_canfd_handle_rx(ndev, event->rx_evt);
+		handled = IRQ_HANDLED;
+	}
+
+	if (event->rx_evt & NCT6694_CANFD_EVT_RX_DATA_LOST) {
+		nct6694_canfd_handle_lost_msg(ndev);
+		handled = IRQ_HANDLED;
+	}
+
+	if (event->status) {
+		nct6694_canfd_handle_state_change(ndev, event->status);
+		handled = IRQ_HANDLED;
+	}
+
+	if (event->err != NCT6694_CANFD_EVT_ERR_NO_ERROR) {
+		if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)
+			nct6694_canfd_handle_bus_err(ndev, event->err);
+		handled = IRQ_HANDLED;
+	}
+
+	if (event->tx_evt & NCT6694_CANFD_EVT_TX_FIFO_EMPTY) {
+		nct6694_canfd_handle_tx(ndev);
+		handled = IRQ_HANDLED;
+	}
+
+	if (handled)
+		can_rx_offload_threaded_irq_finish(&priv->offload);
+
+	priv->bec.rxerr = event->rec;
+	priv->bec.txerr = event->tec;
+
+	return handled;
+}
+
+static void nct6694_canfd_tx_work(struct work_struct *work)
+{
+	struct nct6694_canfd_priv *priv = container_of(work,
+						       struct nct6694_canfd_priv,
+						       tx_work);
+	struct nct6694_canfd_frame *frame = &priv->tx;
+	struct net_device *ndev = priv->ndev;
+	struct net_device_stats *stats = &ndev->stats;
+	struct sk_buff *skb = priv->can.echo_skb[0];
+	static const struct nct6694_cmd_header cmd_hd = {
+		.mod = NCT6694_CANFD_MOD,
+		.cmd = NCT6694_CANFD_DELIVER,
+		.sel = NCT6694_CANFD_DELIVER_SEL(1),
+		.len = cpu_to_le16(sizeof(*frame))
+	};
+	u32 txid;
+	int err;
+
+	memset(frame, 0, sizeof(*frame));
+
+	frame->tag = NCT6694_CANFD_FRAME_TAG(ndev->dev_port);
+
+	if (can_is_canfd_skb(skb)) {
+		struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
+
+		if (cfd->flags & CANFD_BRS)
+			frame->flag |= NCT6694_CANFD_FRAME_FLAG_BRS;
+
+		if (cfd->can_id & CAN_EFF_FLAG) {
+			txid = cfd->can_id & CAN_EFF_MASK;
+			frame->flag |= NCT6694_CANFD_FRAME_FLAG_EFF;
+		} else {
+			txid = cfd->can_id & CAN_SFF_MASK;
+		}
+		frame->flag |= NCT6694_CANFD_FRAME_FLAG_FD;
+		frame->id = cpu_to_le32(txid);
+		frame->length = canfd_sanitize_len(cfd->len);
+
+		memcpy(frame->data, cfd->data, frame->length);
+	} else {
+		struct can_frame *cf = (struct can_frame *)skb->data;
+
+		if (cf->can_id & CAN_EFF_FLAG) {
+			txid = cf->can_id & CAN_EFF_MASK;
+			frame->flag |= NCT6694_CANFD_FRAME_FLAG_EFF;
+		} else {
+			txid = cf->can_id & CAN_SFF_MASK;
+		}
+
+		if (cf->can_id & CAN_RTR_FLAG)
+			frame->flag |= NCT6694_CANFD_FRAME_FLAG_RTR;
+		else
+			memcpy(frame->data, cf->data, cf->len);
+
+		frame->id = cpu_to_le32(txid);
+		frame->length = cf->len;
+	}
+
+	err = nct6694_write_msg(priv->nct6694, &cmd_hd, frame);
+	if (err) {
+		can_free_echo_skb(ndev, 0, NULL);
+		stats->tx_dropped++;
+		stats->tx_errors++;
+		netif_wake_queue(ndev);
+	}
+}
+
+static netdev_tx_t nct6694_canfd_start_xmit(struct sk_buff *skb,
+					    struct net_device *ndev)
+{
+	struct nct6694_canfd_priv *priv = netdev_priv(ndev);
+
+	if (can_dev_dropped_skb(ndev, skb))
+		return NETDEV_TX_OK;
+
+	netif_stop_queue(ndev);
+	can_put_echo_skb(skb, ndev, 0, 0);
+	queue_work(priv->wq, &priv->tx_work);
+
+	return NETDEV_TX_OK;
+}
+
+static int nct6694_canfd_start(struct net_device *ndev)
+{
+	struct nct6694_canfd_priv *priv = netdev_priv(ndev);
+	const struct can_bittiming *n_bt = &priv->can.bittiming;
+	const struct can_bittiming *d_bt = &priv->can.fd.data_bittiming;
+	struct nct6694_canfd_setting *setting __free(kfree) = NULL;
+	const struct nct6694_cmd_header cmd_hd = {
+		.mod = NCT6694_CANFD_MOD,
+		.cmd = NCT6694_CANFD_SETTING,
+		.sel = ndev->dev_port,
+		.len = cpu_to_le16(sizeof(*setting))
+	};
+	u32 en_tdc;
+	int ret;
+
+	setting = kzalloc(sizeof(*setting), GFP_KERNEL);
+	if (!setting)
+		return -ENOMEM;
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		setting->ctrl1 |= cpu_to_le16(NCT6694_CANFD_SETTING_CTRL1_MON);
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO)
+		setting->ctrl1 |= cpu_to_le16(NCT6694_CANFD_SETTING_CTRL1_NISO);
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
+		setting->ctrl1 |= cpu_to_le16(NCT6694_CANFD_SETTING_CTRL1_LBCK);
+
+	/* Disable clock divider */
+	setting->ctrl2 = 0;
+
+	setting->nbtp = cpu_to_le32(FIELD_PREP(NCT6694_CANFD_SETTING_NBTP_NSJW,
+					       n_bt->sjw - 1) |
+				    FIELD_PREP(NCT6694_CANFD_SETTING_NBTP_NBRP,
+					       n_bt->brp - 1) |
+				    FIELD_PREP(NCT6694_CANFD_SETTING_NBTP_NTSEG2,
+					       n_bt->phase_seg2 - 1) |
+				    FIELD_PREP(NCT6694_CANFD_SETTING_NBTP_NTSEG1,
+					       n_bt->prop_seg + n_bt->phase_seg1 - 1));
+
+	if (d_bt->brp <= 2)
+		en_tdc = NCT6694_CANFD_SETTING_DBTP_TDC;
+	else
+		en_tdc = 0;
+
+	setting->dbtp = cpu_to_le32(FIELD_PREP(NCT6694_CANFD_SETTING_DBTP_DSJW,
+					       d_bt->sjw - 1) |
+				    FIELD_PREP(NCT6694_CANFD_SETTING_DBTP_DBRP,
+					       d_bt->brp - 1) |
+				    FIELD_PREP(NCT6694_CANFD_SETTING_DBTP_DTSEG2,
+					       d_bt->phase_seg2 - 1) |
+				    FIELD_PREP(NCT6694_CANFD_SETTING_DBTP_DTSEG1,
+					       d_bt->prop_seg + d_bt->phase_seg1 - 1) |
+				    en_tdc);
+
+	setting->active = NCT6694_CANFD_SETTING_ACTIVE_CTRL1 |
+			  NCT6694_CANFD_SETTING_ACTIVE_CTRL2 |
+			  NCT6694_CANFD_SETTING_ACTIVE_NBTP_DBTP;
+
+	ret = nct6694_write_msg(priv->nct6694, &cmd_hd, setting);
+	if (ret)
+		return ret;
+
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+
+	return 0;
+}
+
+static void nct6694_canfd_stop(struct net_device *ndev)
+{
+	struct nct6694_canfd_priv *priv = netdev_priv(ndev);
+	struct nct6694_canfd_setting *setting __free(kfree) = NULL;
+	const struct nct6694_cmd_header cmd_hd = {
+		.mod = NCT6694_CANFD_MOD,
+		.cmd = NCT6694_CANFD_SETTING,
+		.sel = ndev->dev_port,
+		.len = cpu_to_le16(sizeof(*setting))
+	};
+
+	/* The NCT6694 cannot be stopped. To ensure safe operation and avoid
+	 * interference, the control mode is set to Listen-Only mode. This
+	 * mode allows the device to monitor bus activity without actively
+	 * participating in communication.
+	 */
+	setting = kzalloc(sizeof(*setting), GFP_KERNEL);
+	if (!setting)
+		return;
+
+	nct6694_read_msg(priv->nct6694, &cmd_hd, setting);
+	setting->ctrl1 = cpu_to_le16(NCT6694_CANFD_SETTING_CTRL1_MON);
+	setting->active = NCT6694_CANFD_SETTING_ACTIVE_CTRL1;
+	nct6694_write_msg(priv->nct6694, &cmd_hd, setting);
+
+	priv->can.state = CAN_STATE_STOPPED;
+}
+
+static int nct6694_canfd_close(struct net_device *ndev)
+{
+	struct nct6694_canfd_priv *priv = netdev_priv(ndev);
+
+	netif_stop_queue(ndev);
+	nct6694_canfd_stop(ndev);
+	destroy_workqueue(priv->wq);
+	free_irq(ndev->irq, ndev);
+	can_rx_offload_disable(&priv->offload);
+	close_candev(ndev);
+	return 0;
+}
+
+static int nct6694_canfd_set_mode(struct net_device *ndev, enum can_mode mode)
+{
+	int ret;
+
+	switch (mode) {
+	case CAN_MODE_START:
+		ret = nct6694_canfd_start(ndev);
+		if (ret)
+			return ret;
+
+		netif_wake_queue(ndev);
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+static int nct6694_canfd_open(struct net_device *ndev)
+{
+	struct nct6694_canfd_priv *priv = netdev_priv(ndev);
+	int ret;
+
+	ret = open_candev(ndev);
+	if (ret)
+		return ret;
+
+	can_rx_offload_enable(&priv->offload);
+
+	ret = request_threaded_irq(ndev->irq, NULL,
+				   nct6694_canfd_irq, IRQF_ONESHOT,
+				   "nct6694_canfd", ndev);
+	if (ret) {
+		netdev_err(ndev, "Failed to request IRQ\n");
+		goto can_rx_offload_disable;
+	}
+
+	priv->wq = alloc_ordered_workqueue("%s-nct6694_wq",
+					   WQ_FREEZABLE | WQ_MEM_RECLAIM,
+					   ndev->name);
+	if (!priv->wq) {
+		ret = -ENOMEM;
+		goto free_irq;
+	}
+
+	ret = nct6694_canfd_start(ndev);
+	if (ret)
+		goto destroy_wq;
+
+	netif_start_queue(ndev);
+
+	return 0;
+
+destroy_wq:
+	destroy_workqueue(priv->wq);
+free_irq:
+	free_irq(ndev->irq, ndev);
+can_rx_offload_disable:
+	can_rx_offload_disable(&priv->offload);
+	close_candev(ndev);
+	return ret;
+}
+
+static const struct net_device_ops nct6694_canfd_netdev_ops = {
+	.ndo_open = nct6694_canfd_open,
+	.ndo_stop = nct6694_canfd_close,
+	.ndo_start_xmit = nct6694_canfd_start_xmit,
+};
+
+static const struct ethtool_ops nct6694_canfd_ethtool_ops = {
+	.get_ts_info = ethtool_op_get_ts_info,
+};
+
+static int nct6694_canfd_get_clock(struct nct6694_canfd_priv *priv)
+{
+	struct nct6694_canfd_information *info __free(kfree) = NULL;
+	static const struct nct6694_cmd_header cmd_hd = {
+		.mod = NCT6694_CANFD_MOD,
+		.cmd = NCT6694_CANFD_INFORMATION,
+		.sel = NCT6694_CANFD_INFORMATION_SEL,
+		.len = cpu_to_le16(sizeof(*info))
+	};
+	int ret;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	ret = nct6694_read_msg(priv->nct6694, &cmd_hd, info);
+	if (ret)
+		return ret;
+
+	return le32_to_cpu(info->can_clk);
+}
+
+static int nct6694_canfd_probe(struct platform_device *pdev)
+{
+	struct nct6694 *nct6694 = dev_get_drvdata(pdev->dev.parent);
+	struct nct6694_canfd_priv *priv;
+	struct net_device *ndev;
+	int port, irq, ret, can_clk;
+
+	port = ida_alloc(&nct6694->canfd_ida, GFP_KERNEL);
+	if (port < 0)
+		return port;
+
+	irq = irq_create_mapping(nct6694->domain,
+				 NCT6694_IRQ_CAN0 + port);
+	if (!irq) {
+		ret = -EINVAL;
+		goto free_ida;
+	}
+
+	ndev = alloc_candev(sizeof(struct nct6694_canfd_priv), 1);
+	if (!ndev) {
+		ret = -ENOMEM;
+		goto dispose_irq;
+	}
+
+	ndev->irq = irq;
+	ndev->flags |= IFF_ECHO;
+	ndev->dev_port = port;
+	ndev->netdev_ops = &nct6694_canfd_netdev_ops;
+	ndev->ethtool_ops = &nct6694_canfd_ethtool_ops;
+
+	priv = netdev_priv(ndev);
+	priv->nct6694 = nct6694;
+	priv->ndev = ndev;
+
+	can_clk = nct6694_canfd_get_clock(priv);
+	if (can_clk < 0) {
+		ret = dev_err_probe(&pdev->dev, can_clk,
+				    "Failed to get clock\n");
+		goto free_candev;
+	}
+
+	INIT_WORK(&priv->tx_work, nct6694_canfd_tx_work);
+
+	priv->can.clock.freq = can_clk;
+	priv->can.bittiming_const = &nct6694_canfd_bittiming_nominal_const;
+	priv->can.fd.data_bittiming_const = &nct6694_canfd_bittiming_data_const;
+	priv->can.do_set_mode = nct6694_canfd_set_mode;
+	priv->can.do_get_berr_counter = nct6694_canfd_get_berr_counter;
+	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
+		CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING |
+		CAN_CTRLMODE_FD_NON_ISO;
+
+	ret = can_set_static_ctrlmode(ndev, CAN_CTRLMODE_FD);
+	if (ret)
+		goto free_candev;
+
+	ret = can_rx_offload_add_manual(ndev, &priv->offload,
+					NCT6694_NAPI_WEIGHT);
+	if (ret) {
+		dev_err_probe(&pdev->dev, ret, "Failed to add rx_offload\n");
+		goto free_candev;
+	}
+
+	platform_set_drvdata(pdev, priv);
+	SET_NETDEV_DEV(priv->ndev, &pdev->dev);
+
+	ret = register_candev(priv->ndev);
+	if (ret)
+		goto rx_offload_del;
+
+	return 0;
+
+rx_offload_del:
+	can_rx_offload_del(&priv->offload);
+free_candev:
+	free_candev(ndev);
+dispose_irq:
+	irq_dispose_mapping(irq);
+free_ida:
+	ida_free(&nct6694->canfd_ida, port);
+	return ret;
+}
+
+static void nct6694_canfd_remove(struct platform_device *pdev)
+{
+	struct nct6694_canfd_priv *priv = platform_get_drvdata(pdev);
+	struct nct6694 *nct6694 = priv->nct6694;
+	struct net_device *ndev = priv->ndev;
+	int port = ndev->dev_port;
+	int irq = ndev->irq;
+
+	unregister_candev(ndev);
+	can_rx_offload_del(&priv->offload);
+	free_candev(ndev);
+	irq_dispose_mapping(irq);
+	ida_free(&nct6694->canfd_ida, port);
+}
+
+static struct platform_driver nct6694_canfd_driver = {
+	.driver = {
+		.name	= DEVICE_NAME,
+	},
+	.probe		= nct6694_canfd_probe,
+	.remove		= nct6694_canfd_remove,
+};
+
+module_platform_driver(nct6694_canfd_driver);
+
+MODULE_DESCRIPTION("USB-CAN FD driver for NCT6694");
+MODULE_AUTHOR("Ming Yu <tmyu0@nuvoton.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index c75df1755b3b..9278a1522aae 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -3,8 +3,8 @@
  * CAN driver for PEAK System PCAN-USB adapter
  * Derived from the PCAN project file driver/src/pcan_usb.c
  *
- * Copyright (C) 2003-2010 PEAK System-Technik GmbH
- * Copyright (C) 2011-2012 Stephane Grosjean <s.grosjean@peak-system.com>
+ * Copyright (C) 2003-2025 PEAK System-Technik GmbH
+ * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
  *
  * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de>
  */
@@ -319,7 +319,7 @@ static int pcan_usb_write_mode(struct peak_usb_device *dev, u8 onoff)
  */
 static void pcan_usb_restart(struct timer_list *t)
 {
-	struct pcan_usb *pdev = from_timer(pdev, t, restart_timer);
+	struct pcan_usb *pdev = timer_container_of(pdev, t, restart_timer);
 	struct peak_usb_device *dev = &pdev->dev;
 
 	/* notify candev and netdev */
@@ -919,7 +919,7 @@ static int pcan_usb_init(struct peak_usb_device *dev)
 					    CAN_CTRLMODE_LOOPBACK;
 	} else {
 		dev_info(dev->netdev->dev.parent,
-			 "Firmware update available. Please contact support@peak-system.com\n");
+			 "Firmware update available. Please contact support.peak@hms-networks.com\n");
 	}
 
 	return 0;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 59f7cd8ceb39..cf48bb26d46d 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -3,8 +3,8 @@
  * CAN driver for PEAK System USB adapters
  * Derived from the PCAN project file driver/src/pcan_usb_core.c
  *
- * Copyright (C) 2003-2010 PEAK System-Technik GmbH
- * Copyright (C) 2010-2012 Stephane Grosjean <s.grosjean@peak-system.com>
+ * Copyright (C) 2003-2025 PEAK System-Technik GmbH
+ * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
  *
  * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de>
  */
@@ -24,7 +24,7 @@
 
 #include "pcan_usb_core.h"
 
-MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>");
+MODULE_AUTHOR("Stéphane Grosjean <stephane.grosjean@hms-networks.com>");
 MODULE_DESCRIPTION("CAN driver for PEAK-System USB adapters");
 MODULE_LICENSE("GPL v2");
 
@@ -111,7 +111,7 @@ void peak_usb_update_ts_now(struct peak_time_ref *time_ref, u32 ts_now)
 		u32 delta_ts = time_ref->ts_dev_2 - time_ref->ts_dev_1;
 
 		if (time_ref->ts_dev_2 < time_ref->ts_dev_1)
-			delta_ts &= (1 << time_ref->adapter->ts_used_bits) - 1;
+			delta_ts &= (1ULL << time_ref->adapter->ts_used_bits) - 1;
 
 		time_ref->ts_total += delta_ts;
 	}
@@ -770,7 +770,7 @@ static int peak_usb_set_data_bittiming(struct net_device *netdev)
 	const struct peak_usb_adapter *pa = dev->adapter;
 
 	if (pa->dev_set_data_bittiming) {
-		struct can_bittiming *bt = &dev->can.data_bittiming;
+		struct can_bittiming *bt = &dev->can.fd.data_bittiming;
 		int err = pa->dev_set_data_bittiming(dev, bt);
 
 		if (err)
@@ -784,37 +784,33 @@ static int peak_usb_set_data_bittiming(struct net_device *netdev)
 	return 0;
 }
 
-static int peak_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+static int peak_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config hwts_cfg = { 0 };
-
-	switch (cmd) {
-	case SIOCSHWTSTAMP: /* set */
-		if (copy_from_user(&hwts_cfg, ifr->ifr_data, sizeof(hwts_cfg)))
-			return -EFAULT;
-		if (hwts_cfg.tx_type == HWTSTAMP_TX_OFF &&
-		    hwts_cfg.rx_filter == HWTSTAMP_FILTER_ALL)
-			return 0;
-		return -ERANGE;
-
-	case SIOCGHWTSTAMP: /* get */
-		hwts_cfg.tx_type = HWTSTAMP_TX_OFF;
-		hwts_cfg.rx_filter = HWTSTAMP_FILTER_ALL;
-		if (copy_to_user(ifr->ifr_data, &hwts_cfg, sizeof(hwts_cfg)))
-			return -EFAULT;
+	config->tx_type = HWTSTAMP_TX_OFF;
+	config->rx_filter = HWTSTAMP_FILTER_ALL;
+
+	return 0;
+}
+
+static int peak_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
+{
+	if (config->tx_type == HWTSTAMP_TX_OFF &&
+	    config->rx_filter == HWTSTAMP_FILTER_ALL)
 		return 0;
 
-	default:
-		return -EOPNOTSUPP;
-	}
+	NL_SET_ERR_MSG_MOD(extack, "Only RX HWTSTAMP_FILTER_ALL is supported");
+	return -ERANGE;
 }
 
 static const struct net_device_ops peak_usb_netdev_ops = {
 	.ndo_open = peak_usb_ndo_open,
 	.ndo_stop = peak_usb_ndo_stop,
-	.ndo_eth_ioctl = peak_eth_ioctl,
 	.ndo_start_xmit = peak_usb_ndo_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
+	.ndo_hwtstamp_get = peak_hwtstamp_get,
+	.ndo_hwtstamp_set = peak_hwtstamp_set,
 };
 
 /* CAN-USB devices generally handle 32-bit CAN channel IDs.
@@ -954,8 +950,8 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter,
 	dev->can.clock = peak_usb_adapter->clock;
 	dev->can.bittiming_const = peak_usb_adapter->bittiming_const;
 	dev->can.do_set_bittiming = peak_usb_set_bittiming;
-	dev->can.data_bittiming_const = peak_usb_adapter->data_bittiming_const;
-	dev->can.do_set_data_bittiming = peak_usb_set_data_bittiming;
+	dev->can.fd.data_bittiming_const = peak_usb_adapter->data_bittiming_const;
+	dev->can.fd.do_set_data_bittiming = peak_usb_set_data_bittiming;
 	dev->can.do_set_mode = peak_usb_set_mode;
 	dev->can.do_get_berr_counter = peak_usb_adapter->do_get_berr_counter;
 	dev->can.ctrlmode_supported = peak_usb_adapter->ctrlmode_supported;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h
index abab00930b9d..d1c1897d47b9 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h
@@ -3,8 +3,8 @@
  * CAN driver for PEAK System USB adapters
  * Derived from the PCAN project file driver/src/pcan_usb_core.c
  *
- * Copyright (C) 2003-2010 PEAK System-Technik GmbH
- * Copyright (C) 2010-2012 Stephane Grosjean <s.grosjean@peak-system.com>
+ * Copyright (C) 2003-2025 PEAK System-Technik GmbH
+ * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
  *
  * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de>
  */
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index 4d85b29a17b7..be84191cde56 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -2,7 +2,8 @@
 /*
  * CAN driver for PEAK System PCAN-USB FD / PCAN-USB Pro FD adapter
  *
- * Copyright (C) 2013-2014 Stephane Grosjean <s.grosjean@peak-system.com>
+ * Copyright (C) 2013-2025 PEAK System-Technik GmbH
+ * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
  */
 #include <linux/ethtool.h>
 #include <linux/module.h>
@@ -49,7 +50,7 @@ struct __packed pcan_ufd_fw_info {
 	__le32	ser_no;		/* S/N */
 	__le32	flags;		/* special functions */
 
-	/* extended data when type == PCAN_USBFD_TYPE_EXT */
+	/* extended data when type >= PCAN_USBFD_TYPE_EXT */
 	u8	cmd_out_ep;	/* ep for cmd */
 	u8	cmd_in_ep;	/* ep for replies */
 	u8	data_out_ep[2];	/* ep for CANx TX */
@@ -982,10 +983,11 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev)
 			dev->can.ctrlmode |= CAN_CTRLMODE_FD_NON_ISO;
 		}
 
-		/* if vendor rsp is of type 2, then it contains EP numbers to
-		 * use for cmds pipes. If not, then default EP should be used.
+		/* if vendor rsp type is greater than or equal to 2, then it
+		 * contains EP numbers to use for cmds pipes. If not, then
+		 * default EP should be used.
 		 */
-		if (fw_info->type != cpu_to_le16(PCAN_USBFD_TYPE_EXT)) {
+		if (le16_to_cpu(fw_info->type) < PCAN_USBFD_TYPE_EXT) {
 			fw_info->cmd_out_ep = PCAN_USBPRO_EP_CMDOUT;
 			fw_info->cmd_in_ep = PCAN_USBPRO_EP_CMDIN;
 		}
@@ -1018,11 +1020,11 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev)
 	dev->can_channel_id =
 		le32_to_cpu(pdev->usb_if->fw_info.dev_id[dev->ctrl_idx]);
 
-	/* if vendor rsp is of type 2, then it contains EP numbers to
-	 * use for data pipes. If not, then statically defined EP are used
-	 * (see peak_usb_create_dev()).
+	/* if vendor rsp type is greater than or equal to 2, then it contains EP
+	 * numbers to use for data pipes. If not, then statically defined EP are
+	 * used (see peak_usb_create_dev()).
 	 */
-	if (fw_info->type == cpu_to_le16(PCAN_USBFD_TYPE_EXT)) {
+	if (le16_to_cpu(fw_info->type) >= PCAN_USBFD_TYPE_EXT) {
 		dev->ep_msg_in = fw_info->data_in_ep;
 		dev->ep_msg_out = fw_info->data_out_ep[dev->ctrl_idx];
 	}
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index f736196383ac..7be286293b1a 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -3,8 +3,8 @@
  * CAN driver for PEAK System PCAN-USB Pro adapter
  * Derived from the PCAN project file driver/src/pcan_usbpro.c
  *
- * Copyright (C) 2003-2011 PEAK System-Technik GmbH
- * Copyright (C) 2011-2012 Stephane Grosjean <s.grosjean@peak-system.com>
+ * Copyright (C) 2003-2025 PEAK System-Technik GmbH
+ * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
  */
 #include <linux/ethtool.h>
 #include <linux/module.h>
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.h b/drivers/net/can/usb/peak_usb/pcan_usb_pro.h
index 28e740af905d..162c7546d3a8 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.h
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.h
@@ -3,8 +3,8 @@
  * CAN driver for PEAK System PCAN-USB Pro adapter
  * Derived from the PCAN project file driver/src/pcan_usbpro_fw.h
  *
- * Copyright (C) 2003-2011 PEAK System-Technik GmbH
- * Copyright (C) 2011-2012 Stephane Grosjean <s.grosjean@peak-system.com>
+ * Copyright (C) 2003-2025 PEAK System-Technik GmbH
+ * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
  */
 #ifndef PCAN_USB_PRO_H
 #define PCAN_USB_PRO_H
diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c
index 39a63b7313a4..de61d9da99e3 100644
--- a/drivers/net/can/usb/ucan.c
+++ b/drivers/net/can/usb/ucan.c
@@ -186,7 +186,7 @@ union ucan_ctl_payload {
 	 */
 	struct ucan_ctl_cmd_get_protocol_version cmd_get_protocol_version;
 
-	u8 raw[128];
+	u8 fw_str[128];
 } __packed;
 
 enum {
@@ -424,18 +424,20 @@ static int ucan_ctrl_command_out(struct ucan_priv *up,
 			       UCAN_USB_CTL_PIPE_TIMEOUT);
 }
 
-static int ucan_device_request_in(struct ucan_priv *up,
-				  u8 cmd, u16 subcmd, u16 datalen)
+static void ucan_get_fw_str(struct ucan_priv *up, char *fw_str, size_t size)
 {
-	return usb_control_msg(up->udev,
-			       usb_rcvctrlpipe(up->udev, 0),
-			       cmd,
-			       USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-			       subcmd,
-			       0,
-			       up->ctl_msg_buffer,
-			       datalen,
-			       UCAN_USB_CTL_PIPE_TIMEOUT);
+	int ret;
+
+	ret = usb_control_msg(up->udev, usb_rcvctrlpipe(up->udev, 0),
+			      UCAN_DEVICE_GET_FW_STRING,
+			      USB_DIR_IN | USB_TYPE_VENDOR |
+			      USB_RECIP_DEVICE,
+			      0, 0, fw_str, size - 1,
+			      UCAN_USB_CTL_PIPE_TIMEOUT);
+	if (ret > 0)
+		fw_str[ret] = '\0';
+	else
+		strscpy(fw_str, "unknown", size);
 }
 
 /* Parse the device information structure reported by the device and
@@ -1231,7 +1233,6 @@ static const struct net_device_ops ucan_netdev_ops = {
 	.ndo_open = ucan_open,
 	.ndo_stop = ucan_close,
 	.ndo_start_xmit = ucan_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops ucan_ethtool_ops = {
@@ -1314,7 +1315,6 @@ static int ucan_probe(struct usb_interface *intf,
 	u8 in_ep_addr;
 	u8 out_ep_addr;
 	union ucan_ctl_payload *ctl_msg_buffer;
-	char firmware_str[sizeof(union ucan_ctl_payload) + 1];
 
 	udev = interface_to_usbdev(intf);
 
@@ -1527,17 +1527,6 @@ static int ucan_probe(struct usb_interface *intf,
 	 */
 	ucan_parse_device_info(up, &ctl_msg_buffer->cmd_get_device_info);
 
-	/* just print some device information - if available */
-	ret = ucan_device_request_in(up, UCAN_DEVICE_GET_FW_STRING, 0,
-				     sizeof(union ucan_ctl_payload));
-	if (ret > 0) {
-		/* copy string while ensuring zero termination */
-		strscpy(firmware_str, up->ctl_msg_buffer->raw,
-			sizeof(union ucan_ctl_payload) + 1);
-	} else {
-		strcpy(firmware_str, "unknown");
-	}
-
 	/* device is compatible, reset it */
 	ret = ucan_ctrl_command_out(up, UCAN_COMMAND_RESET, 0, 0);
 	if (ret < 0)
@@ -1555,7 +1544,10 @@ static int ucan_probe(struct usb_interface *intf,
 
 	/* initialisation complete, log device info */
 	netdev_info(up->netdev, "registered device\n");
-	netdev_info(up->netdev, "firmware string: %s\n", firmware_str);
+	ucan_get_fw_str(up, up->ctl_msg_buffer->fw_str,
+			sizeof(up->ctl_msg_buffer->fw_str));
+	netdev_info(up->netdev, "firmware string: %s\n",
+		    up->ctl_msg_buffer->fw_str);
 
 	/* success */
 	return 0;
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index 8a5596ce4e46..7449328f7cd7 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -868,7 +868,6 @@ static const struct net_device_ops usb_8dev_netdev_ops = {
 	.ndo_open = usb_8dev_open,
 	.ndo_stop = usb_8dev_close,
 	.ndo_start_xmit = usb_8dev_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
 };
 
 static const struct ethtool_ops usb_8dev_ethtool_ops = {
diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c
index f67e85807100..fdc662aea279 100644
--- a/drivers/net/can/vcan.c
+++ b/drivers/net/can/vcan.c
@@ -156,7 +156,7 @@ static const struct ethtool_ops vcan_ethtool_ops = {
 static void vcan_setup(struct net_device *dev)
 {
 	dev->type		= ARPHRD_CAN;
-	dev->mtu		= CANFD_MTU;
+	dev->mtu		= CANXL_MTU;
 	dev->hard_header_len	= 0;
 	dev->addr_len		= 0;
 	dev->tx_queue_len	= 0;
diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c
index ca8811941085..b2c19f8c5f8e 100644
--- a/drivers/net/can/vxcan.c
+++ b/drivers/net/can/vxcan.c
@@ -156,7 +156,7 @@ static void vxcan_setup(struct net_device *dev)
 	struct can_ml_priv *can_ml;
 
 	dev->type		= ARPHRD_CAN;
-	dev->mtu		= CANFD_MTU;
+	dev->mtu		= CANXL_MTU;
 	dev->hard_header_len	= 0;
 	dev->addr_len		= 0;
 	dev->tx_queue_len	= 0;
@@ -172,10 +172,13 @@ static void vxcan_setup(struct net_device *dev)
 /* forward declaration for rtnl_create_link() */
 static struct rtnl_link_ops vxcan_link_ops;
 
-static int vxcan_newlink(struct net *peer_net, struct net_device *dev,
-			 struct nlattr *tb[], struct nlattr *data[],
+static int vxcan_newlink(struct net_device *dev,
+			 struct rtnl_newlink_params *params,
 			 struct netlink_ext_ack *extack)
 {
+	struct net *peer_net = rtnl_newlink_peer_net(params);
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	struct vxcan_priv *priv;
 	struct net_device *peer;
 
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 436c0e4b0344..43d7f22820b8 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -481,7 +481,7 @@ static int xcan_set_bittiming(struct net_device *ndev)
 {
 	struct xcan_priv *priv = netdev_priv(ndev);
 	struct can_bittiming *bt = &priv->can.bittiming;
-	struct can_bittiming *dbt = &priv->can.data_bittiming;
+	struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	u32 btr0, btr1;
 	u32 is_config_mode;
 
@@ -515,12 +515,12 @@ static int xcan_set_bittiming(struct net_device *ndev)
 	    priv->devtype.cantype == XAXI_CANFD_2_0) {
 		/* Setting Baud Rate prescaler value in F_BRPR Register */
 		btr0 = dbt->brp - 1;
-		if (can_tdc_is_enabled(&priv->can)) {
+		if (can_fd_tdc_is_enabled(&priv->can)) {
 			if (priv->devtype.cantype == XAXI_CANFD)
-				btr0 |= FIELD_PREP(XCAN_BRPR_TDCO_MASK, priv->can.tdc.tdco) |
+				btr0 |= FIELD_PREP(XCAN_BRPR_TDCO_MASK, priv->can.fd.tdc.tdco) |
 					XCAN_BRPR_TDC_ENABLE;
 			else
-				btr0 |= FIELD_PREP(XCAN_2_BRPR_TDCO_MASK, priv->can.tdc.tdco) |
+				btr0 |= FIELD_PREP(XCAN_2_BRPR_TDCO_MASK, priv->can.fd.tdc.tdco) |
 					XCAN_BRPR_TDC_ENABLE;
 		}
 
@@ -690,14 +690,6 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb,
 		dlc |= XCAN_DLCR_EDL_MASK;
 	}
 
-	if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) &&
-	    (priv->devtype.flags & XCAN_FLAG_TXFEMP))
-		can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0);
-	else
-		can_put_echo_skb(skb, ndev, 0, 0);
-
-	priv->tx_head++;
-
 	priv->write_reg(priv, XCAN_FRAME_ID_OFFSET(frame_offset), id);
 	/* If the CAN frame is RTR frame this write triggers transmission
 	 * (not on CAN FD)
@@ -730,6 +722,14 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb,
 					data[1]);
 		}
 	}
+
+	if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) &&
+	    (priv->devtype.flags & XCAN_FLAG_TXFEMP))
+		can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0);
+	else
+		can_put_echo_skb(skb, ndev, 0, 0);
+
+	priv->tx_head++;
 }
 
 /**
@@ -1702,7 +1702,6 @@ static const struct net_device_ops xcan_netdev_ops = {
 	.ndo_open	= xcan_open,
 	.ndo_stop	= xcan_close,
 	.ndo_start_xmit	= xcan_start_xmit,
-	.ndo_change_mtu	= can_change_mtu,
 };
 
 static const struct ethtool_ops xcan_ethtool_ops = {
@@ -1967,22 +1966,22 @@ static int xcan_probe(struct platform_device *pdev)
 		goto err_free;
 
 	if (devtype->cantype == XAXI_CANFD) {
-		priv->can.data_bittiming_const =
+		priv->can.fd.data_bittiming_const =
 			&xcan_data_bittiming_const_canfd;
-		priv->can.tdc_const = &xcan_tdc_const_canfd;
+		priv->can.fd.tdc_const = &xcan_tdc_const_canfd;
 	}
 
 	if (devtype->cantype == XAXI_CANFD_2_0) {
-		priv->can.data_bittiming_const =
+		priv->can.fd.data_bittiming_const =
 			&xcan_data_bittiming_const_canfd2;
-		priv->can.tdc_const = &xcan_tdc_const_canfd2;
+		priv->can.fd.tdc_const = &xcan_tdc_const_canfd2;
 	}
 
 	if (devtype->cantype == XAXI_CANFD ||
 	    devtype->cantype == XAXI_CANFD_2_0) {
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD |
 						CAN_CTRLMODE_TDC_AUTO;
-		priv->can.do_get_auto_tdcv = xcan_get_auto_tdcv;
+		priv->can.fd.do_get_auto_tdcv = xcan_get_auto_tdcv;
 	}
 
 	priv->reg_base = addr;
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 2d10b4d6cfbb..7eb301fd987d 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -26,17 +26,12 @@ config NET_DSA_LOOP
 
 source "drivers/net/dsa/hirschmann/Kconfig"
 
-config NET_DSA_LANTIQ_GSWIP
-	tristate "Lantiq / Intel GSWIP"
-	depends on HAS_IOMEM
-	select NET_DSA_TAG_GSWIP
-	help
-	  This enables support for the Lantiq / Intel GSWIP 2.1 found in
-	  the xrx200 / VR9 SoC.
+source "drivers/net/dsa/lantiq/Kconfig"
 
 config NET_DSA_MT7530
 	tristate "MediaTek MT7530 and MT7531 Ethernet switch support"
 	select NET_DSA_TAG_MTK
+	select REGMAP_IRQ
 	imply NET_DSA_MT7530_MDIO
 	imply NET_DSA_MT7530_MMIO
 	help
@@ -91,13 +86,21 @@ source "drivers/net/dsa/realtek/Kconfig"
 
 config NET_DSA_RZN1_A5PSW
 	tristate "Renesas RZ/N1 A5PSW Ethernet switch support"
-	depends on OF && ARCH_RZN1
+	depends on OF && (ARCH_RZN1 || COMPILE_TEST)
 	select NET_DSA_TAG_RZN1_A5PSW
 	select PCS_RZN1_MIIC
 	help
 	  This driver supports the A5PSW switch, which is embedded in Renesas
 	  RZ/N1 SoC.
 
+config NET_DSA_KS8995
+	tristate "Micrel KS8995 family 5-ports 10/100 Ethernet switches"
+	depends on SPI
+	select NET_DSA_TAG_NONE
+	help
+	  This driver supports the Micrel KS8995 family of 10/100 Mbit ethernet
+	  switches, managed over SPI.
+
 config NET_DSA_SMSC_LAN9303
 	tristate
 	select NET_DSA_TAG_LAN9303
@@ -151,4 +154,11 @@ config NET_DSA_VITESSE_VSC73XX_PLATFORM
 	  This enables support for the Vitesse VSC7385, VSC7388, VSC7395
 	  and VSC7398 SparX integrated ethernet switches, connected over
 	  a CPU-attached address bus and work in memory-mapped I/O mode.
+
+config NET_DSA_YT921X
+	tristate "Motorcomm YT9215 ethernet switch chip support"
+	select NET_DSA_TAG_YT921X
+	help
+	  This enables support for the Motorcomm YT9215 ethernet switch
+	  chip.
 endmenu
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
index cb9a97340e58..16de4ba3fa38 100644
--- a/drivers/net/dsa/Makefile
+++ b/drivers/net/dsa/Makefile
@@ -2,10 +2,7 @@
 obj-$(CONFIG_NET_DSA_BCM_SF2)	+= bcm-sf2.o
 bcm-sf2-objs			:= bcm_sf2.o bcm_sf2_cfp.o
 obj-$(CONFIG_NET_DSA_LOOP)	+= dsa_loop.o
-ifdef CONFIG_NET_DSA_LOOP
-obj-$(CONFIG_FIXED_PHY)		+= dsa_loop_bdinfo.o
-endif
-obj-$(CONFIG_NET_DSA_LANTIQ_GSWIP) += lantiq_gswip.o
+obj-$(CONFIG_NET_DSA_KS8995) 	+= ks8995.o
 obj-$(CONFIG_NET_DSA_MT7530)	+= mt7530.o
 obj-$(CONFIG_NET_DSA_MT7530_MDIO) += mt7530-mdio.o
 obj-$(CONFIG_NET_DSA_MT7530_MMIO) += mt7530-mmio.o
@@ -17,8 +14,10 @@ obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o
 obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX) += vitesse-vsc73xx-core.o
 obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX_PLATFORM) += vitesse-vsc73xx-platform.o
 obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX_SPI) += vitesse-vsc73xx-spi.o
+obj-$(CONFIG_NET_DSA_YT921X) += yt921x.o
 obj-y				+= b53/
 obj-y				+= hirschmann/
+obj-y				+= lantiq/
 obj-y				+= microchip/
 obj-y				+= mv88e6xxx/
 obj-y				+= ocelot/
diff --git a/drivers/net/dsa/b53/Kconfig b/drivers/net/dsa/b53/Kconfig
index ebaa4a80d544..915008e8eff5 100644
--- a/drivers/net/dsa/b53/Kconfig
+++ b/drivers/net/dsa/b53/Kconfig
@@ -5,6 +5,7 @@ menuconfig B53
 	select NET_DSA_TAG_NONE
 	select NET_DSA_TAG_BRCM
 	select NET_DSA_TAG_BRCM_LEGACY
+	select NET_DSA_TAG_BRCM_LEGACY_FCS
 	select NET_DSA_TAG_BRCM_PREPEND
 	help
 	  This driver adds support for Broadcom managed switch chips. It supports
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 0561b60f668f..a1a177713d99 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -21,6 +21,8 @@
 #include <linux/export.h>
 #include <linux/gpio.h>
 #include <linux/kernel.h>
+#include <linux/math.h>
+#include <linux/minmax.h>
 #include <linux/module.h>
 #include <linux/platform_data/b53.h>
 #include <linux/phy.h>
@@ -326,6 +328,26 @@ static void b53_get_vlan_entry(struct b53_device *dev, u16 vid,
 	}
 }
 
+static void b53_set_eap_mode(struct b53_device *dev, int port, int mode)
+{
+	u64 eap_conf;
+
+	if (is5325(dev) || is5365(dev) || dev->chip_id == BCM5389_DEVICE_ID)
+		return;
+
+	b53_read64(dev, B53_EAP_PAGE, B53_PORT_EAP_CONF(port), &eap_conf);
+
+	if (is63xx(dev)) {
+		eap_conf &= ~EAP_MODE_MASK_63XX;
+		eap_conf |= (u64)mode << EAP_MODE_SHIFT_63XX;
+	} else {
+		eap_conf &= ~EAP_MODE_MASK;
+		eap_conf |= (u64)mode << EAP_MODE_SHIFT;
+	}
+
+	b53_write64(dev, B53_EAP_PAGE, B53_PORT_EAP_CONF(port), eap_conf);
+}
+
 static void b53_set_forwarding(struct b53_device *dev, int enable)
 {
 	u8 mgmt;
@@ -339,18 +361,23 @@ static void b53_set_forwarding(struct b53_device *dev, int enable)
 
 	b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt);
 
-	/* Include IMP port in dumb forwarding mode
-	 */
-	b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, &mgmt);
-	mgmt |= B53_MII_DUMB_FWDG_EN;
-	b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt);
+	if (!is5325(dev)) {
+		/* Include IMP port in dumb forwarding mode */
+		b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, &mgmt);
+		mgmt |= B53_MII_DUMB_FWDG_EN;
+		b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt);
 
-	/* Look at B53_UC_FWD_EN and B53_MC_FWD_EN to decide whether
-	 * frames should be flooded or not.
-	 */
-	b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt);
-	mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IPMC_FWD_EN;
-	b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt);
+		/* Look at B53_UC_FWD_EN and B53_MC_FWD_EN to decide whether
+		 * frames should be flooded or not.
+		 */
+		b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt);
+		mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IP_MC;
+		b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt);
+	} else {
+		b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt);
+		mgmt |= B53_IP_MC;
+		b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt);
+	}
 }
 
 static void b53_enable_vlan(struct b53_device *dev, int port, bool enable,
@@ -373,15 +400,17 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable,
 		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5, &vc5);
 	}
 
+	vc1 &= ~VC1_RX_MCST_FWD_EN;
+
 	if (enable) {
 		vc0 |= VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID;
-		vc1 |= VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN;
+		vc1 |= VC1_RX_MCST_UNTAG_EN;
 		vc4 &= ~VC4_ING_VID_CHECK_MASK;
 		if (enable_filtering) {
 			vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S;
 			vc5 |= VC5_DROP_VTABLE_MISS;
 		} else {
-			vc4 |= VC4_ING_VID_VIO_FWD << VC4_ING_VID_CHECK_S;
+			vc4 |= VC4_NO_ING_VID_CHK << VC4_ING_VID_CHECK_S;
 			vc5 &= ~VC5_DROP_VTABLE_MISS;
 		}
 
@@ -393,7 +422,7 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable,
 
 	} else {
 		vc0 &= ~(VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID);
-		vc1 &= ~(VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN);
+		vc1 &= ~VC1_RX_MCST_UNTAG_EN;
 		vc4 &= ~VC4_ING_VID_CHECK_MASK;
 		vc5 &= ~VC5_DROP_VTABLE_MISS;
 
@@ -463,6 +492,9 @@ static int b53_flush_arl(struct b53_device *dev, u8 mask)
 {
 	unsigned int i;
 
+	if (is5325(dev))
+		return 0;
+
 	b53_write8(dev, B53_CTRL_PAGE, B53_FAST_AGE_CTRL,
 		   FAST_AGE_DONE | FAST_AGE_DYNAMIC | mask);
 
@@ -487,6 +519,9 @@ out:
 
 static int b53_fast_age_port(struct b53_device *dev, int port)
 {
+	if (is5325(dev))
+		return 0;
+
 	b53_write8(dev, B53_CTRL_PAGE, B53_FAST_AGE_PORT_CTRL, port);
 
 	return b53_flush_arl(dev, FAST_AGE_PORT);
@@ -494,6 +529,9 @@ static int b53_fast_age_port(struct b53_device *dev, int port)
 
 static int b53_fast_age_vlan(struct b53_device *dev, u16 vid)
 {
+	if (is5325(dev))
+		return 0;
+
 	b53_write16(dev, B53_CTRL_PAGE, B53_FAST_AGE_VID_CTRL, vid);
 
 	return b53_flush_arl(dev, FAST_AGE_VLAN);
@@ -505,6 +543,10 @@ void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port)
 	unsigned int i;
 	u16 pvlan;
 
+	/* BCM5325 CPU port is at 8 */
+	if ((is5325(dev) || is5365(dev)) && cpu_port == B53_CPU_PORT_25)
+		cpu_port = B53_CPU_PORT;
+
 	/* Enable the IMP port to be in the same VLAN as the other ports
 	 * on a per-port basis such that we only have Port i and IMP in
 	 * the same VLAN.
@@ -522,12 +564,24 @@ static void b53_port_set_ucast_flood(struct b53_device *dev, int port,
 {
 	u16 uc;
 
-	b53_read16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, &uc);
-	if (unicast)
-		uc |= BIT(port);
-	else
-		uc &= ~BIT(port);
-	b53_write16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, uc);
+	if (is5325(dev)) {
+		if (port == B53_CPU_PORT_25)
+			port = B53_CPU_PORT;
+
+		b53_read16(dev, B53_IEEE_PAGE, B53_IEEE_UCAST_DLF, &uc);
+		if (unicast)
+			uc |= BIT(port) | B53_IEEE_UCAST_DROP_EN;
+		else
+			uc &= ~BIT(port);
+		b53_write16(dev, B53_IEEE_PAGE, B53_IEEE_UCAST_DLF, uc);
+	} else {
+		b53_read16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, &uc);
+		if (unicast)
+			uc |= BIT(port);
+		else
+			uc &= ~BIT(port);
+		b53_write16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, uc);
+	}
 }
 
 static void b53_port_set_mcast_flood(struct b53_device *dev, int port,
@@ -535,19 +589,31 @@ static void b53_port_set_mcast_flood(struct b53_device *dev, int port,
 {
 	u16 mc;
 
-	b53_read16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, &mc);
-	if (multicast)
-		mc |= BIT(port);
-	else
-		mc &= ~BIT(port);
-	b53_write16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, mc);
+	if (is5325(dev)) {
+		if (port == B53_CPU_PORT_25)
+			port = B53_CPU_PORT;
 
-	b53_read16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, &mc);
-	if (multicast)
-		mc |= BIT(port);
-	else
-		mc &= ~BIT(port);
-	b53_write16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, mc);
+		b53_read16(dev, B53_IEEE_PAGE, B53_IEEE_MCAST_DLF, &mc);
+		if (multicast)
+			mc |= BIT(port) | B53_IEEE_MCAST_DROP_EN;
+		else
+			mc &= ~BIT(port);
+		b53_write16(dev, B53_IEEE_PAGE, B53_IEEE_MCAST_DLF, mc);
+	} else {
+		b53_read16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, &mc);
+		if (multicast)
+			mc |= BIT(port);
+		else
+			mc &= ~BIT(port);
+		b53_write16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, mc);
+
+		b53_read16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, &mc);
+		if (multicast)
+			mc |= BIT(port);
+		else
+			mc &= ~BIT(port);
+		b53_write16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, mc);
+	}
 }
 
 static void b53_port_set_learning(struct b53_device *dev, int port,
@@ -555,6 +621,9 @@ static void b53_port_set_learning(struct b53_device *dev, int port,
 {
 	u16 reg;
 
+	if (is5325(dev))
+		return;
+
 	b53_read16(dev, B53_CTRL_PAGE, B53_DIS_LEARNING, &reg);
 	if (learning)
 		reg &= ~BIT(port);
@@ -563,6 +632,25 @@ static void b53_port_set_learning(struct b53_device *dev, int port,
 	b53_write16(dev, B53_CTRL_PAGE, B53_DIS_LEARNING, reg);
 }
 
+static void b53_port_set_isolated(struct b53_device *dev, int port,
+				  bool isolated)
+{
+	u8 offset;
+	u16 reg;
+
+	if (is5325(dev))
+		offset = B53_PROTECTED_PORT_SEL_25;
+	else
+		offset = B53_PROTECTED_PORT_SEL;
+
+	b53_read16(dev, B53_CTRL_PAGE, offset, &reg);
+	if (isolated)
+		reg |= BIT(port);
+	else
+		reg &= ~BIT(port);
+	b53_write16(dev, B53_CTRL_PAGE, offset, reg);
+}
+
 static void b53_eee_enable_set(struct dsa_switch *ds, int port, bool enable)
 {
 	struct b53_device *dev = ds->priv;
@@ -576,6 +664,39 @@ static void b53_eee_enable_set(struct dsa_switch *ds, int port, bool enable)
 	b53_write16(dev, B53_EEE_PAGE, B53_EEE_EN_CTRL, reg);
 }
 
+int b53_setup_port(struct dsa_switch *ds, int port)
+{
+	struct b53_device *dev = ds->priv;
+
+	b53_port_set_ucast_flood(dev, port, true);
+	b53_port_set_mcast_flood(dev, port, true);
+	b53_port_set_learning(dev, port, false);
+	b53_port_set_isolated(dev, port, false);
+
+	/* Force all traffic to go to the CPU port to prevent the ASIC from
+	 * trying to forward to bridged ports on matching FDB entries, then
+	 * dropping frames because it isn't allowed to forward there.
+	 */
+	if (dsa_is_user_port(ds, port))
+		b53_set_eap_mode(dev, port, EAP_MODE_SIMPLIFIED);
+
+	if (is5325(dev) &&
+	    in_range(port, 1, 4)) {
+		u8 reg;
+
+		b53_read8(dev, B53_CTRL_PAGE, B53_PD_MODE_CTRL_25, &reg);
+		reg &= ~PD_MODE_POWER_DOWN_PORT(0);
+		if (dsa_is_unused_port(ds, port))
+			reg |= PD_MODE_POWER_DOWN_PORT(port);
+		else
+			reg &= ~PD_MODE_POWER_DOWN_PORT(port);
+		b53_write8(dev, B53_CTRL_PAGE, B53_PD_MODE_CTRL_25, reg);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(b53_setup_port);
+
 int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 {
 	struct b53_device *dev = ds->priv;
@@ -588,9 +709,8 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 
 	cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
 
-	b53_port_set_ucast_flood(dev, port, true);
-	b53_port_set_mcast_flood(dev, port, true);
-	b53_port_set_learning(dev, port, false);
+	if (dev->ops->phy_enable)
+		dev->ops->phy_enable(dev, port);
 
 	if (dev->ops->irq_enable)
 		ret = dev->ops->irq_enable(dev, port);
@@ -630,6 +750,9 @@ void b53_disable_port(struct dsa_switch *ds, int port)
 	reg |= PORT_CTRL_RX_DISABLE | PORT_CTRL_TX_DISABLE;
 	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), reg);
 
+	if (dev->ops->phy_disable)
+		dev->ops->phy_disable(dev, port);
+
 	if (dev->ops->irq_disable)
 		dev->ops->irq_disable(dev, port);
 }
@@ -674,6 +797,11 @@ void b53_brcm_hdr_setup(struct dsa_switch *ds, int port)
 		hdr_ctl |= GC_FRM_MGMT_PORT_M;
 	b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, hdr_ctl);
 
+	/* B53_BRCM_HDR not present on devices with legacy tags */
+	if (dev->tag_protocol == DSA_TAG_PROTO_BRCM_LEGACY ||
+	    dev->tag_protocol == DSA_TAG_PROTO_BRCM_LEGACY_FCS)
+		return;
+
 	/* Enable Broadcom tags for IMP port */
 	b53_read8(dev, B53_MGMT_PAGE, B53_BRCM_HDR, &hdr_ctl);
 	if (tag_en)
@@ -722,10 +850,6 @@ static void b53_enable_cpu_port(struct b53_device *dev, int port)
 	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), port_ctrl);
 
 	b53_brcm_hdr_setup(dev->ds, port);
-
-	b53_port_set_ucast_flood(dev, port, true);
-	b53_port_set_mcast_flood(dev, port, true);
-	b53_port_set_learning(dev, port, false);
 }
 
 static void b53_enable_mib(struct b53_device *dev)
@@ -737,12 +861,18 @@ static void b53_enable_mib(struct b53_device *dev)
 	b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc);
 }
 
+static void b53_enable_stp(struct b53_device *dev)
+{
+	u8 gc;
+
+	b53_read8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, &gc);
+	gc |= GC_RX_BPDU_EN;
+	b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc);
+}
+
 static u16 b53_default_pvid(struct b53_device *dev)
 {
-	if (is5325(dev) || is5365(dev))
-		return 1;
-	else
-		return 0;
+	return 0;
 }
 
 static bool b53_vlan_port_needs_forced_tagged(struct dsa_switch *ds, int port)
@@ -752,6 +882,22 @@ static bool b53_vlan_port_needs_forced_tagged(struct dsa_switch *ds, int port)
 	return dev->tag_protocol == DSA_TAG_PROTO_NONE && dsa_is_cpu_port(ds, port);
 }
 
+static bool b53_vlan_port_may_join_untagged(struct dsa_switch *ds, int port)
+{
+	struct b53_device *dev = ds->priv;
+	struct dsa_port *dp;
+
+	if (!dev->vlan_filtering)
+		return true;
+
+	dp = dsa_to_port(ds, port);
+
+	if (dsa_port_is_cpu(dp))
+		return true;
+
+	return dp->bridge == NULL;
+}
+
 int b53_configure_vlan(struct dsa_switch *ds)
 {
 	struct b53_device *dev = ds->priv;
@@ -770,7 +916,7 @@ int b53_configure_vlan(struct dsa_switch *ds)
 		b53_do_vlan_op(dev, VTA_CMD_CLEAR);
 	}
 
-	b53_enable_vlan(dev, -1, dev->vlan_enabled, ds->vlan_filtering);
+	b53_enable_vlan(dev, -1, dev->vlan_enabled, dev->vlan_filtering);
 
 	/* Create an untagged VLAN entry for the default PVID in case
 	 * CONFIG_VLAN_8021Q is disabled and there are no calls to
@@ -778,26 +924,39 @@ int b53_configure_vlan(struct dsa_switch *ds)
 	 * entry. Do this only when the tagging protocol is not
 	 * DSA_TAG_PROTO_NONE
 	 */
+	v = &dev->vlans[def_vid];
 	b53_for_each_port(dev, i) {
-		v = &dev->vlans[def_vid];
-		v->members |= BIT(i);
+		if (!b53_vlan_port_may_join_untagged(ds, i))
+			continue;
+
+		vl.members |= BIT(i);
 		if (!b53_vlan_port_needs_forced_tagged(ds, i))
-			v->untag = v->members;
-		b53_write16(dev, B53_VLAN_PAGE,
-			    B53_VLAN_PORT_DEF_TAG(i), def_vid);
+			vl.untag = vl.members;
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(i),
+			    def_vid);
 	}
+	b53_set_vlan_entry(dev, def_vid, &vl);
 
-	/* Upon initial call we have not set-up any VLANs, but upon
-	 * system resume, we need to restore all VLAN entries.
-	 */
-	for (vid = def_vid; vid < dev->num_vlans; vid++) {
-		v = &dev->vlans[vid];
+	if (dev->vlan_filtering) {
+		/* Upon initial call we have not set-up any VLANs, but upon
+		 * system resume, we need to restore all VLAN entries.
+		 */
+		for (vid = def_vid + 1; vid < dev->num_vlans; vid++) {
+			v = &dev->vlans[vid];
 
-		if (!v->members)
-			continue;
+			if (!v->members)
+				continue;
+
+			b53_set_vlan_entry(dev, vid, v);
+			b53_fast_age_vlan(dev, vid);
+		}
 
-		b53_set_vlan_entry(dev, vid, v);
-		b53_fast_age_vlan(dev, vid);
+		b53_for_each_port(dev, i) {
+			if (!dsa_is_cpu_port(ds, i))
+				b53_write16(dev, B53_VLAN_PAGE,
+					    B53_VLAN_PORT_DEF_TAG(i),
+					    dev->ports[i].pvid);
+		}
 	}
 
 	return 0;
@@ -876,6 +1035,7 @@ static int b53_switch_reset(struct b53_device *dev)
 	}
 
 	b53_enable_mib(dev);
+	b53_enable_stp(dev);
 
 	return b53_flush_arl(dev, FAST_AGE_STATIC);
 }
@@ -1115,7 +1275,9 @@ EXPORT_SYMBOL(b53_setup_devlink_resources);
 static int b53_setup(struct dsa_switch *ds)
 {
 	struct b53_device *dev = ds->priv;
+	struct b53_vlan *vl;
 	unsigned int port;
+	u16 pvid;
 	int ret;
 
 	/* Request bridge PVID untagged when DSA_TAG_PROTO_NONE is set
@@ -1123,12 +1285,36 @@ static int b53_setup(struct dsa_switch *ds)
 	 */
 	ds->untag_bridge_pvid = dev->tag_protocol == DSA_TAG_PROTO_NONE;
 
+	/* The switch does not tell us the original VLAN for untagged
+	 * packets, so keep the CPU port always tagged.
+	 */
+	ds->untag_vlan_aware_bridge_pvid = true;
+
+	if (dev->chip_id == BCM53101_DEVICE_ID) {
+		/* BCM53101 uses 0.5 second increments */
+		ds->ageing_time_min = 1 * 500;
+		ds->ageing_time_max = AGE_TIME_MAX * 500;
+	} else {
+		/* Everything else uses 1 second increments */
+		ds->ageing_time_min = 1 * 1000;
+		ds->ageing_time_max = AGE_TIME_MAX * 1000;
+	}
+
 	ret = b53_reset_switch(dev);
 	if (ret) {
 		dev_err(ds->dev, "failed to reset switch\n");
 		return ret;
 	}
 
+	/* setup default vlan for filtering mode */
+	pvid = b53_default_pvid(dev);
+	vl = &dev->vlans[pvid];
+	b53_for_each_port(dev, port) {
+		vl->members |= BIT(port);
+		if (!b53_vlan_port_needs_forced_tagged(ds, port))
+			vl->untag |= BIT(port);
+	}
+
 	b53_reset_mib(dev);
 
 	ret = b53_apply_config(dev);
@@ -1163,6 +1349,8 @@ static void b53_force_link(struct b53_device *dev, int port, int link)
 	if (port == dev->imp_port) {
 		off = B53_PORT_OVERRIDE_CTRL;
 		val = PORT_OVERRIDE_EN;
+	} else if (is5325(dev)) {
+		return;
 	} else {
 		off = B53_GMII_PORT_OVERRIDE_CTRL(port);
 		val = GMII_PO_EN;
@@ -1187,6 +1375,8 @@ static void b53_force_port_config(struct b53_device *dev, int port,
 	if (port == dev->imp_port) {
 		off = B53_PORT_OVERRIDE_CTRL;
 		val = PORT_OVERRIDE_EN;
+	} else if (is5325(dev)) {
+		return;
 	} else {
 		off = B53_GMII_PORT_OVERRIDE_CTRL(port);
 		val = GMII_PO_EN;
@@ -1199,6 +1389,10 @@ static void b53_force_port_config(struct b53_device *dev, int port,
 	else
 		reg &= ~PORT_OVERRIDE_FULL_DUPLEX;
 
+	reg &= ~(0x3 << GMII_PO_SPEED_S);
+	if (is5301x(dev) || is58xx(dev))
+		reg &= ~PORT_OVERRIDE_SPEED_2000M;
+
 	switch (speed) {
 	case 2000:
 		reg |= PORT_OVERRIDE_SPEED_2000M;
@@ -1217,10 +1411,24 @@ static void b53_force_port_config(struct b53_device *dev, int port,
 		return;
 	}
 
-	if (rx_pause)
-		reg |= PORT_OVERRIDE_RX_FLOW;
-	if (tx_pause)
-		reg |= PORT_OVERRIDE_TX_FLOW;
+	if (is5325(dev))
+		reg &= ~PORT_OVERRIDE_LP_FLOW_25;
+	else
+		reg &= ~(PORT_OVERRIDE_RX_FLOW | PORT_OVERRIDE_TX_FLOW);
+
+	if (rx_pause) {
+		if (is5325(dev))
+			reg |= PORT_OVERRIDE_LP_FLOW_25;
+		else
+			reg |= PORT_OVERRIDE_RX_FLOW;
+	}
+
+	if (tx_pause) {
+		if (is5325(dev))
+			reg |= PORT_OVERRIDE_LP_FLOW_25;
+		else
+			reg |= PORT_OVERRIDE_TX_FLOW;
+	}
 
 	b53_write8(dev, B53_CTRL_PAGE, off, reg);
 }
@@ -1229,41 +1437,17 @@ static void b53_adjust_63xx_rgmii(struct dsa_switch *ds, int port,
 				  phy_interface_t interface)
 {
 	struct b53_device *dev = ds->priv;
-	u8 rgmii_ctrl = 0, off;
+	u8 rgmii_ctrl = 0;
 
-	if (port == dev->imp_port)
-		off = B53_RGMII_CTRL_IMP;
-	else
-		off = B53_RGMII_CTRL_P(port);
+	b53_read8(dev, B53_CTRL_PAGE, B53_RGMII_CTRL_P(port), &rgmii_ctrl);
+	rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC);
 
-	b53_read8(dev, B53_CTRL_PAGE, off, &rgmii_ctrl);
+	if (is6318_268(dev))
+		rgmii_ctrl |= RGMII_CTRL_MII_OVERRIDE;
 
-	switch (interface) {
-	case PHY_INTERFACE_MODE_RGMII_ID:
-		rgmii_ctrl |= (RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC);
-		break;
-	case PHY_INTERFACE_MODE_RGMII_RXID:
-		rgmii_ctrl &= ~(RGMII_CTRL_DLL_TXC);
-		rgmii_ctrl |= RGMII_CTRL_DLL_RXC;
-		break;
-	case PHY_INTERFACE_MODE_RGMII_TXID:
-		rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC);
-		rgmii_ctrl |= RGMII_CTRL_DLL_TXC;
-		break;
-	case PHY_INTERFACE_MODE_RGMII:
-	default:
-		rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC);
-		break;
-	}
-
-	if (port != dev->imp_port) {
-		if (is63268(dev))
-			rgmii_ctrl |= RGMII_CTRL_MII_OVERRIDE;
+	rgmii_ctrl |= RGMII_CTRL_ENABLE_GMII;
 
-		rgmii_ctrl |= RGMII_CTRL_ENABLE_GMII;
-	}
-
-	b53_write8(dev, B53_CTRL_PAGE, off, rgmii_ctrl);
+	b53_write8(dev, B53_CTRL_PAGE, B53_RGMII_CTRL_P(port), rgmii_ctrl);
 
 	dev_dbg(ds->dev, "Configured port %d for %s\n", port,
 		phy_modes(interface));
@@ -1284,8 +1468,7 @@ static void b53_adjust_531x5_rgmii(struct dsa_switch *ds, int port,
 	 * tx_clk aligned timing (restoring to reset defaults)
 	 */
 	b53_read8(dev, B53_CTRL_PAGE, off, &rgmii_ctrl);
-	rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC |
-			RGMII_CTRL_TIMING_SEL);
+	rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC);
 
 	/* PHY_INTERFACE_MODE_RGMII_TXID means TX internal delay, make
 	 * sure that we enable the port TX clock internal delay to
@@ -1305,7 +1488,10 @@ static void b53_adjust_531x5_rgmii(struct dsa_switch *ds, int port,
 		rgmii_ctrl |= RGMII_CTRL_DLL_TXC;
 	if (interface == PHY_INTERFACE_MODE_RGMII)
 		rgmii_ctrl |= RGMII_CTRL_DLL_TXC | RGMII_CTRL_DLL_RXC;
-	rgmii_ctrl |= RGMII_CTRL_TIMING_SEL;
+
+	if (dev->chip_id != BCM53115_DEVICE_ID)
+		rgmii_ctrl |= RGMII_CTRL_TIMING_SEL;
+
 	b53_write8(dev, B53_CTRL_PAGE, off, rgmii_ctrl);
 
 	dev_info(ds->dev, "Configured port %d for %s\n", port,
@@ -1369,6 +1555,10 @@ static void b53_phylink_get_caps(struct dsa_switch *ds, int port,
 	__set_bit(PHY_INTERFACE_MODE_MII, config->supported_interfaces);
 	__set_bit(PHY_INTERFACE_MODE_REVMII, config->supported_interfaces);
 
+	/* BCM63xx RGMII ports support RGMII */
+	if (is63xx(dev) && in_range(port, B53_63XX_RGMII0, 4))
+		phy_interface_set_rgmii(config->supported_interfaces);
+
 	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 		MAC_10 | MAC_100;
 
@@ -1408,7 +1598,7 @@ static void b53_phylink_mac_config(struct phylink_config *config,
 	struct b53_device *dev = ds->priv;
 	int port = dp->index;
 
-	if (is63xx(dev) && port >= B53_63XX_RGMII0)
+	if (is63xx(dev) && in_range(port, B53_63XX_RGMII0, 4))
 		b53_adjust_63xx_rgmii(ds, port, interface);
 
 	if (mode == MLO_AN_FIXED) {
@@ -1429,8 +1619,11 @@ static void b53_phylink_mac_link_down(struct phylink_config *config,
 	struct b53_device *dev = dp->ds->priv;
 	int port = dp->index;
 
-	if (mode == MLO_AN_PHY)
+	if (mode == MLO_AN_PHY) {
+		if (is63xx(dev) && in_range(port, B53_63XX_RGMII0, 4))
+			b53_force_link(dev, port, false);
 		return;
+	}
 
 	if (mode == MLO_AN_FIXED) {
 		b53_force_link(dev, port, false);
@@ -1458,6 +1651,13 @@ static void b53_phylink_mac_link_up(struct phylink_config *config,
 	if (mode == MLO_AN_PHY) {
 		/* Re-negotiate EEE if it was enabled already */
 		p->eee_enabled = b53_eee_init(ds, port, phydev);
+
+		if (is63xx(dev) && in_range(port, B53_63XX_RGMII0, 4)) {
+			b53_force_port_config(dev, port, speed, duplex,
+					      tx_pause, rx_pause);
+			b53_force_link(dev, port, true);
+		}
+
 		return;
 	}
 
@@ -1482,7 +1682,10 @@ int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering,
 {
 	struct b53_device *dev = ds->priv;
 
-	b53_enable_vlan(dev, port, dev->vlan_enabled, vlan_filtering);
+	if (dev->vlan_filtering != vlan_filtering) {
+		dev->vlan_filtering = vlan_filtering;
+		b53_apply_config(dev);
+	}
 
 	return 0;
 }
@@ -1493,9 +1696,6 @@ static int b53_vlan_prepare(struct dsa_switch *ds, int port,
 {
 	struct b53_device *dev = ds->priv;
 
-	if ((is5325(dev) || is5365(dev)) && vlan->vid == 0)
-		return -EOPNOTSUPP;
-
 	/* Port 7 on 7278 connects to the ASP's UniMAC which is not capable of
 	 * receiving VLAN tagged frames at all, we can still allow the port to
 	 * be configured for egress untagged.
@@ -1507,7 +1707,7 @@ static int b53_vlan_prepare(struct dsa_switch *ds, int port,
 	if (vlan->vid >= dev->num_vlans)
 		return -ERANGE;
 
-	b53_enable_vlan(dev, port, true, ds->vlan_filtering);
+	b53_enable_vlan(dev, port, true, dev->vlan_filtering);
 
 	return 0;
 }
@@ -1520,18 +1720,29 @@ int b53_vlan_add(struct dsa_switch *ds, int port,
 	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
 	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
 	struct b53_vlan *vl;
+	u16 old_pvid, new_pvid;
 	int err;
 
 	err = b53_vlan_prepare(ds, port, vlan);
 	if (err)
 		return err;
 
-	vl = &dev->vlans[vlan->vid];
+	if (vlan->vid == 0)
+		return 0;
 
-	b53_get_vlan_entry(dev, vlan->vid, vl);
+	old_pvid = dev->ports[port].pvid;
+	if (pvid)
+		new_pvid = vlan->vid;
+	else if (!pvid && vlan->vid == old_pvid)
+		new_pvid = b53_default_pvid(dev);
+	else
+		new_pvid = old_pvid;
+	dev->ports[port].pvid = new_pvid;
+
+	vl = &dev->vlans[vlan->vid];
 
-	if (vlan->vid == 0 && vlan->vid == b53_default_pvid(dev))
-		untagged = true;
+	if (dsa_is_cpu_port(ds, port))
+		untagged = false;
 
 	vl->members |= BIT(port);
 	if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port))
@@ -1539,13 +1750,16 @@ int b53_vlan_add(struct dsa_switch *ds, int port,
 	else
 		vl->untag &= ~BIT(port);
 
+	if (!dev->vlan_filtering)
+		return 0;
+
 	b53_set_vlan_entry(dev, vlan->vid, vl);
 	b53_fast_age_vlan(dev, vlan->vid);
 
-	if (pvid && !dsa_is_cpu_port(ds, port)) {
+	if (!dsa_is_cpu_port(ds, port) && new_pvid != old_pvid) {
 		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port),
-			    vlan->vid);
-		b53_fast_age_vlan(dev, vlan->vid);
+			    new_pvid);
+		b53_fast_age_vlan(dev, old_pvid);
 	}
 
 	return 0;
@@ -1560,20 +1774,25 @@ int b53_vlan_del(struct dsa_switch *ds, int port,
 	struct b53_vlan *vl;
 	u16 pvid;
 
-	b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid);
+	if (vlan->vid == 0)
+		return 0;
 
-	vl = &dev->vlans[vlan->vid];
+	pvid = dev->ports[port].pvid;
 
-	b53_get_vlan_entry(dev, vlan->vid, vl);
+	vl = &dev->vlans[vlan->vid];
 
 	vl->members &= ~BIT(port);
 
 	if (pvid == vlan->vid)
 		pvid = b53_default_pvid(dev);
+	dev->ports[port].pvid = pvid;
 
 	if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port))
 		vl->untag &= ~(BIT(port));
 
+	if (!dev->vlan_filtering)
+		return 0;
+
 	b53_set_vlan_entry(dev, vlan->vid, vl);
 	b53_fast_age_vlan(dev, vlan->vid);
 
@@ -1625,7 +1844,82 @@ static int b53_arl_rw_op(struct b53_device *dev, unsigned int op)
 	return b53_arl_op_wait(dev);
 }
 
-static int b53_arl_read(struct b53_device *dev, u64 mac,
+static void b53_arl_read_entry_25(struct b53_device *dev,
+				  struct b53_arl_entry *ent, u8 idx)
+{
+	u8 vid_entry;
+	u64 mac_vid;
+
+	b53_read8(dev, B53_ARLIO_PAGE, B53_ARLTBL_VID_ENTRY_25(idx),
+		  &vid_entry);
+	b53_read64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx),
+		   &mac_vid);
+	b53_arl_to_entry_25(ent, mac_vid, vid_entry);
+}
+
+static void b53_arl_write_entry_25(struct b53_device *dev,
+				   const struct b53_arl_entry *ent, u8 idx)
+{
+	u8 vid_entry;
+	u64 mac_vid;
+
+	b53_arl_from_entry_25(&mac_vid, &vid_entry, ent);
+	b53_write8(dev, B53_ARLIO_PAGE, B53_ARLTBL_VID_ENTRY_25(idx), vid_entry);
+	b53_write64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx),
+		    mac_vid);
+}
+
+static void b53_arl_read_entry_89(struct b53_device *dev,
+				  struct b53_arl_entry *ent, u8 idx)
+{
+	u64 mac_vid;
+	u16 fwd_entry;
+
+	b53_read64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx),
+		   &mac_vid);
+	b53_read16(dev, B53_ARLIO_PAGE, B53_ARLTBL_DATA_ENTRY(idx), &fwd_entry);
+	b53_arl_to_entry_89(ent, mac_vid, fwd_entry);
+}
+
+static void b53_arl_write_entry_89(struct b53_device *dev,
+				   const struct b53_arl_entry *ent, u8 idx)
+{
+	u32 fwd_entry;
+	u64 mac_vid;
+
+	b53_arl_from_entry_89(&mac_vid, &fwd_entry, ent);
+	b53_write64(dev, B53_ARLIO_PAGE,
+		    B53_ARLTBL_MAC_VID_ENTRY(idx), mac_vid);
+	b53_write16(dev, B53_ARLIO_PAGE,
+		    B53_ARLTBL_DATA_ENTRY(idx), fwd_entry);
+}
+
+static void b53_arl_read_entry_95(struct b53_device *dev,
+				  struct b53_arl_entry *ent, u8 idx)
+{
+	u32 fwd_entry;
+	u64 mac_vid;
+
+	b53_read64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx),
+		   &mac_vid);
+	b53_read32(dev, B53_ARLIO_PAGE, B53_ARLTBL_DATA_ENTRY(idx), &fwd_entry);
+	b53_arl_to_entry(ent, mac_vid, fwd_entry);
+}
+
+static void b53_arl_write_entry_95(struct b53_device *dev,
+				   const struct b53_arl_entry *ent, u8 idx)
+{
+	u32 fwd_entry;
+	u64 mac_vid;
+
+	b53_arl_from_entry(&mac_vid, &fwd_entry, ent);
+	b53_write64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx),
+		    mac_vid);
+	b53_write32(dev, B53_ARLIO_PAGE, B53_ARLTBL_DATA_ENTRY(idx),
+		    fwd_entry);
+}
+
+static int b53_arl_read(struct b53_device *dev, const u8 *mac,
 			u16 vid, struct b53_arl_entry *ent, u8 *idx)
 {
 	DECLARE_BITMAP(free_bins, B53_ARLTBL_MAX_BIN_ENTRIES);
@@ -1640,23 +1934,15 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 
 	/* Read the bins */
 	for (i = 0; i < dev->num_arl_bins; i++) {
-		u64 mac_vid;
-		u32 fwd_entry;
-
-		b53_read64(dev, B53_ARLIO_PAGE,
-			   B53_ARLTBL_MAC_VID_ENTRY(i), &mac_vid);
-		b53_read32(dev, B53_ARLIO_PAGE,
-			   B53_ARLTBL_DATA_ENTRY(i), &fwd_entry);
-		b53_arl_to_entry(ent, mac_vid, fwd_entry);
+		b53_arl_read_entry(dev, ent, i);
 
-		if (!(fwd_entry & ARLTBL_VALID)) {
+		if (!ent->is_valid) {
 			set_bit(i, free_bins);
 			continue;
 		}
-		if ((mac_vid & ARLTBL_MAC_MASK) != mac)
+		if (!ether_addr_equal(ent->mac, mac))
 			continue;
-		if (dev->vlan_enabled &&
-		    ((mac_vid >> ARLTBL_VID_S) & ARLTBL_VID_MASK) != vid)
+		if (dev->vlan_enabled && ent->vid != vid)
 			continue;
 		*idx = i;
 		return 0;
@@ -1670,9 +1956,8 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 		      const unsigned char *addr, u16 vid, bool is_valid)
 {
 	struct b53_arl_entry ent;
-	u32 fwd_entry;
-	u64 mac, mac_vid = 0;
 	u8 idx = 0;
+	u64 mac;
 	int ret;
 
 	/* Convert the array into a 64-bit MAC */
@@ -1680,14 +1965,19 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 
 	/* Perform a read for the given MAC and VID */
 	b53_write48(dev, B53_ARLIO_PAGE, B53_MAC_ADDR_IDX, mac);
-	b53_write16(dev, B53_ARLIO_PAGE, B53_VLAN_ID_IDX, vid);
+	if (!is5325m(dev)) {
+		if (is5325(dev) || is5365(dev))
+			b53_write8(dev, B53_ARLIO_PAGE, B53_VLAN_ID_IDX, vid);
+		else
+			b53_write16(dev, B53_ARLIO_PAGE, B53_VLAN_ID_IDX, vid);
+	}
 
 	/* Issue a read operation for this MAC */
 	ret = b53_arl_rw_op(dev, 1);
 	if (ret)
 		return ret;
 
-	ret = b53_arl_read(dev, mac, vid, &ent, &idx);
+	ret = b53_arl_read(dev, addr, vid, &ent, &idx);
 
 	/* If this is a read, just finish now */
 	if (op)
@@ -1704,7 +1994,6 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 		/* We could not find a matching MAC, so reset to a new entry */
 		dev_dbg(dev->dev, "{%pM,%.4d} not found, using idx: %d\n",
 			addr, vid, idx);
-		fwd_entry = 0;
 		break;
 	default:
 		dev_dbg(dev->dev, "{%pM,%.4d} found, using idx: %d\n",
@@ -1731,12 +2020,7 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 	ent.is_static = true;
 	ent.is_age = false;
 	memcpy(ent.mac, addr, ETH_ALEN);
-	b53_arl_from_entry(&mac_vid, &fwd_entry, &ent);
-
-	b53_write64(dev, B53_ARLIO_PAGE,
-		    B53_ARLTBL_MAC_VID_ENTRY(idx), mac_vid);
-	b53_write32(dev, B53_ARLIO_PAGE,
-		    B53_ARLTBL_DATA_ENTRY(idx), fwd_entry);
+	b53_arl_write_entry(dev, &ent, idx);
 
 	return b53_arl_rw_op(dev, 0);
 }
@@ -1748,12 +2032,6 @@ int b53_fdb_add(struct dsa_switch *ds, int port,
 	struct b53_device *priv = ds->priv;
 	int ret;
 
-	/* 5325 and 5365 require some more massaging, but could
-	 * be supported eventually
-	 */
-	if (is5325(priv) || is5365(priv))
-		return -EOPNOTSUPP;
-
 	mutex_lock(&priv->arl_mutex);
 	ret = b53_arl_op(priv, 0, port, addr, vid, true);
 	mutex_unlock(&priv->arl_mutex);
@@ -1777,15 +2055,55 @@ int b53_fdb_del(struct dsa_switch *ds, int port,
 }
 EXPORT_SYMBOL(b53_fdb_del);
 
+static void b53_read_arl_srch_ctl(struct b53_device *dev, u8 *val)
+{
+	u8 offset;
+
+	if (is5325(dev) || is5365(dev))
+		offset = B53_ARL_SRCH_CTL_25;
+	else if (dev->chip_id == BCM5389_DEVICE_ID || is5397_98(dev) ||
+		 is63xx(dev))
+		offset = B53_ARL_SRCH_CTL_89;
+	else
+		offset = B53_ARL_SRCH_CTL;
+
+	if (is63xx(dev)) {
+		u16 val16;
+
+		b53_read16(dev, B53_ARLIO_PAGE, offset, &val16);
+		*val = val16 & 0xff;
+	} else {
+		b53_read8(dev, B53_ARLIO_PAGE, offset, val);
+	}
+}
+
+static void b53_write_arl_srch_ctl(struct b53_device *dev, u8 val)
+{
+	u8 offset;
+
+	if (is5325(dev) || is5365(dev))
+		offset = B53_ARL_SRCH_CTL_25;
+	else if (dev->chip_id == BCM5389_DEVICE_ID || is5397_98(dev) ||
+		 is63xx(dev))
+		offset = B53_ARL_SRCH_CTL_89;
+	else
+		offset = B53_ARL_SRCH_CTL;
+
+	if (is63xx(dev))
+		b53_write16(dev, B53_ARLIO_PAGE, offset, val);
+	else
+		b53_write8(dev, B53_ARLIO_PAGE, offset, val);
+}
+
 static int b53_arl_search_wait(struct b53_device *dev)
 {
 	unsigned int timeout = 1000;
 	u8 reg;
 
 	do {
-		b53_read8(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_CTL, &reg);
+		b53_read_arl_srch_ctl(dev, &reg);
 		if (!(reg & ARL_SRCH_STDN))
-			return 0;
+			return -ENOENT;
 
 		if (reg & ARL_SRCH_VLID)
 			return 0;
@@ -1796,16 +2114,52 @@ static int b53_arl_search_wait(struct b53_device *dev)
 	return -ETIMEDOUT;
 }
 
-static void b53_arl_search_rd(struct b53_device *dev, u8 idx,
-			      struct b53_arl_entry *ent)
+static void b53_arl_search_read_25(struct b53_device *dev, u8 idx,
+				   struct b53_arl_entry *ent)
 {
 	u64 mac_vid;
+	u8 ext;
+
+	b53_read8(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_EXT_25, &ext);
+	b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_0_MACVID_25,
+		   &mac_vid);
+	b53_arl_search_to_entry_25(ent, mac_vid, ext);
+}
+
+static void b53_arl_search_read_89(struct b53_device *dev, u8 idx,
+				   struct b53_arl_entry *ent)
+{
+	u16 fwd_entry;
+	u64 mac_vid;
+
+	b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_MACVID_89,
+		   &mac_vid);
+	b53_read16(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_89, &fwd_entry);
+	b53_arl_to_entry_89(ent, mac_vid, fwd_entry);
+}
+
+static void b53_arl_search_read_63xx(struct b53_device *dev, u8 idx,
+				     struct b53_arl_entry *ent)
+{
+	u16 fwd_entry;
+	u64 mac_vid;
+
+	b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_MACVID_63XX,
+		   &mac_vid);
+	b53_read16(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_63XX, &fwd_entry);
+	b53_arl_search_to_entry_63xx(ent, mac_vid, fwd_entry);
+}
+
+static void b53_arl_search_read_95(struct b53_device *dev, u8 idx,
+				   struct b53_arl_entry *ent)
+{
 	u32 fwd_entry;
+	u64 mac_vid;
 
-	b53_read64(dev, B53_ARLIO_PAGE,
-		   B53_ARL_SRCH_RSTL_MACVID(idx), &mac_vid);
-	b53_read32(dev, B53_ARLIO_PAGE,
-		   B53_ARL_SRCH_RSTL(idx), &fwd_entry);
+	b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_MACVID(idx),
+		   &mac_vid);
+	b53_read32(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL(idx),
+		   &fwd_entry);
 	b53_arl_to_entry(ent, mac_vid, fwd_entry);
 }
 
@@ -1824,30 +2178,31 @@ static int b53_fdb_copy(int port, const struct b53_arl_entry *ent,
 int b53_fdb_dump(struct dsa_switch *ds, int port,
 		 dsa_fdb_dump_cb_t *cb, void *data)
 {
+	unsigned int count = 0, results_per_hit = 1;
 	struct b53_device *priv = ds->priv;
 	struct b53_arl_entry results[2];
-	unsigned int count = 0;
 	int ret;
-	u8 reg;
+
+	if (priv->num_arl_bins > 2)
+		results_per_hit = 2;
 
 	mutex_lock(&priv->arl_mutex);
 
 	/* Start search operation */
-	reg = ARL_SRCH_STDN;
-	b53_write8(priv, B53_ARLIO_PAGE, B53_ARL_SRCH_CTL, reg);
+	b53_write_arl_srch_ctl(priv, ARL_SRCH_STDN);
 
 	do {
 		ret = b53_arl_search_wait(priv);
 		if (ret)
 			break;
 
-		b53_arl_search_rd(priv, 0, &results[0]);
+		b53_arl_search_read(priv, 0, &results[0]);
 		ret = b53_fdb_copy(port, &results[0], cb, data);
 		if (ret)
 			break;
 
-		if (priv->num_arl_bins > 2) {
-			b53_arl_search_rd(priv, 1, &results[1]);
+		if (results_per_hit == 2) {
+			b53_arl_search_read(priv, 1, &results[1]);
 			ret = b53_fdb_copy(port, &results[1], cb, data);
 			if (ret)
 				break;
@@ -1856,7 +2211,7 @@ int b53_fdb_dump(struct dsa_switch *ds, int port,
 				break;
 		}
 
-	} while (count++ < b53_max_arl_entries(priv) / 2);
+	} while (count++ < b53_max_arl_entries(priv) / results_per_hit);
 
 	mutex_unlock(&priv->arl_mutex);
 
@@ -1906,8 +2261,9 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
 		bool *tx_fwd_offload, struct netlink_ext_ack *extack)
 {
 	struct b53_device *dev = ds->priv;
+	struct b53_vlan *vl;
 	s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
-	u16 pvlan, reg;
+	u16 pvlan, reg, pvid;
 	unsigned int i;
 
 	/* On 7278, port 7 which connects to the ASP should only receive
@@ -1916,15 +2272,26 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
 	if (dev->chip_id == BCM7278_DEVICE_ID && port == 7)
 		return -EINVAL;
 
-	/* Make this port leave the all VLANs join since we will have proper
-	 * VLAN entries from now on
-	 */
-	if (is58xx(dev)) {
-		b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, &reg);
-		reg &= ~BIT(port);
-		if ((reg & BIT(cpu_port)) == BIT(cpu_port))
-			reg &= ~BIT(cpu_port);
-		b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
+	pvid = b53_default_pvid(dev);
+	vl = &dev->vlans[pvid];
+
+	if (dev->vlan_filtering) {
+		/* Make this port leave the all VLANs join since we will have
+		 * proper VLAN entries from now on
+		 */
+		if (is58xx(dev)) {
+			b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN,
+				   &reg);
+			reg &= ~BIT(port);
+			if ((reg & BIT(cpu_port)) == BIT(cpu_port))
+				reg &= ~BIT(cpu_port);
+			b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN,
+				    reg);
+		}
+
+		b53_get_vlan_entry(dev, pvid, vl);
+		vl->members &= ~BIT(port);
+		b53_set_vlan_entry(dev, pvid, vl);
 	}
 
 	b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan);
@@ -1944,6 +2311,9 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
 		pvlan |= BIT(i);
 	}
 
+	/* Disable redirection of unknown SA to the CPU port */
+	b53_set_eap_mode(dev, port, EAP_MODE_BASIC);
+
 	/* Configure the local port VLAN control membership to include
 	 * remote ports and update the local port bitmask
 	 */
@@ -1957,7 +2327,7 @@ EXPORT_SYMBOL(b53_br_join);
 void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge)
 {
 	struct b53_device *dev = ds->priv;
-	struct b53_vlan *vl = &dev->vlans[0];
+	struct b53_vlan *vl;
 	s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
 	unsigned int i;
 	u16 pvlan, reg, pvid;
@@ -1979,22 +2349,27 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge)
 			pvlan &= ~BIT(i);
 	}
 
+	/* Enable redirection of unknown SA to the CPU port */
+	b53_set_eap_mode(dev, port, EAP_MODE_SIMPLIFIED);
+
 	b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan);
 	dev->ports[port].vlan_ctl_mask = pvlan;
 
 	pvid = b53_default_pvid(dev);
+	vl = &dev->vlans[pvid];
+
+	if (dev->vlan_filtering) {
+		/* Make this port join all VLANs without VLAN entries */
+		if (is58xx(dev)) {
+			b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, &reg);
+			reg |= BIT(port);
+			if (!(reg & BIT(cpu_port)))
+				reg |= BIT(cpu_port);
+			b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
+		}
 
-	/* Make this port join all VLANs without VLAN entries */
-	if (is58xx(dev)) {
-		b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, &reg);
-		reg |= BIT(port);
-		if (!(reg & BIT(cpu_port)))
-			reg |= BIT(cpu_port);
-		b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
-	} else {
 		b53_get_vlan_entry(dev, pvid, vl);
-		vl->members |= BIT(port) | BIT(cpu_port);
-		vl->untag |= BIT(port) | BIT(cpu_port);
+		vl->members |= BIT(port);
 		b53_set_vlan_entry(dev, pvid, vl);
 	}
 }
@@ -2047,7 +2422,13 @@ int b53_br_flags_pre(struct dsa_switch *ds, int port,
 		     struct switchdev_brport_flags flags,
 		     struct netlink_ext_ack *extack)
 {
-	if (flags.mask & ~(BR_FLOOD | BR_MCAST_FLOOD | BR_LEARNING))
+	struct b53_device *dev = ds->priv;
+	unsigned long mask = (BR_FLOOD | BR_MCAST_FLOOD | BR_ISOLATED);
+
+	if (!is5325(dev))
+		mask |= BR_LEARNING;
+
+	if (flags.mask & ~mask)
 		return -EINVAL;
 
 	return 0;
@@ -2067,6 +2448,9 @@ int b53_br_flags(struct dsa_switch *ds, int port,
 	if (flags.mask & BR_LEARNING)
 		b53_port_set_learning(ds->priv, port,
 				      !!(flags.val & BR_LEARNING));
+	if (flags.mask & BR_ISOLATED)
+		b53_port_set_isolated(ds->priv, port,
+				      !!(flags.val & BR_ISOLATED));
 
 	return 0;
 }
@@ -2123,8 +2507,11 @@ enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port,
 		goto out;
 	}
 
-	/* Older models require a different 6 byte tag */
-	if (is5325(dev) || is5365(dev) || is63xx(dev)) {
+	/* Older models require different 6 byte tags */
+	if (is5325(dev) || is5365(dev)) {
+		dev->tag_protocol = DSA_TAG_PROTO_BRCM_LEGACY_FCS;
+		goto out;
+	} else if (is63xx(dev)) {
 		dev->tag_protocol = DSA_TAG_PROTO_BRCM_LEGACY;
 		goto out;
 	}
@@ -2214,6 +2601,9 @@ int b53_eee_init(struct dsa_switch *ds, int port, struct phy_device *phy)
 {
 	int ret;
 
+	if (!b53_support_eee(ds, port))
+		return 0;
+
 	ret = phy_init_eee(phy, false);
 	if (ret)
 		return 0;
@@ -2228,16 +2618,10 @@ bool b53_support_eee(struct dsa_switch *ds, int port)
 {
 	struct b53_device *dev = ds->priv;
 
-	return !is5325(dev) && !is5365(dev);
+	return !is5325(dev) && !is5365(dev) && !is63xx(dev);
 }
 EXPORT_SYMBOL(b53_support_eee);
 
-int b53_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e)
-{
-	return 0;
-}
-EXPORT_SYMBOL(b53_get_mac_eee);
-
 int b53_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e)
 {
 	struct b53_device *dev = ds->priv;
@@ -2278,6 +2662,31 @@ static int b53_get_max_mtu(struct dsa_switch *ds, int port)
 	return B53_MAX_MTU;
 }
 
+int b53_set_ageing_time(struct dsa_switch *ds, unsigned int msecs)
+{
+	struct b53_device *dev = ds->priv;
+	u32 atc;
+	int reg;
+
+	if (is63xx(dev))
+		reg = B53_AGING_TIME_CONTROL_63XX;
+	else
+		reg = B53_AGING_TIME_CONTROL;
+
+	if (dev->chip_id == BCM53101_DEVICE_ID)
+		atc = DIV_ROUND_CLOSEST(msecs, 500);
+	else
+		atc = DIV_ROUND_CLOSEST(msecs, 1000);
+
+	if (!is5325(dev) && !is5365(dev))
+		atc |= AGE_CHANGE;
+
+	b53_write32(dev, B53_MGMT_PAGE, reg, atc);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(b53_set_ageing_time);
+
 static const struct phylink_mac_ops b53_phylink_mac_ops = {
 	.mac_select_pcs	= b53_phylink_mac_select_pcs,
 	.mac_config	= b53_phylink_mac_config,
@@ -2296,11 +2705,12 @@ static const struct dsa_switch_ops b53_switch_ops = {
 	.phy_read		= b53_phy_read16,
 	.phy_write		= b53_phy_write16,
 	.phylink_get_caps	= b53_phylink_get_caps,
+	.port_setup		= b53_setup_port,
 	.port_enable		= b53_enable_port,
 	.port_disable		= b53_disable_port,
 	.support_eee		= b53_support_eee,
-	.get_mac_eee		= b53_get_mac_eee,
 	.set_mac_eee		= b53_set_mac_eee,
+	.set_ageing_time	= b53_set_ageing_time,
 	.port_bridge_join	= b53_br_join,
 	.port_bridge_leave	= b53_br_leave,
 	.port_pre_bridge_flags	= b53_br_flags_pre,
@@ -2321,6 +2731,30 @@ static const struct dsa_switch_ops b53_switch_ops = {
 	.port_change_mtu	= b53_change_mtu,
 };
 
+static const struct b53_arl_ops b53_arl_ops_25 = {
+	.arl_read_entry = b53_arl_read_entry_25,
+	.arl_write_entry = b53_arl_write_entry_25,
+	.arl_search_read = b53_arl_search_read_25,
+};
+
+static const struct b53_arl_ops b53_arl_ops_89 = {
+	.arl_read_entry = b53_arl_read_entry_89,
+	.arl_write_entry = b53_arl_write_entry_89,
+	.arl_search_read = b53_arl_search_read_89,
+};
+
+static const struct b53_arl_ops b53_arl_ops_63xx = {
+	.arl_read_entry = b53_arl_read_entry_89,
+	.arl_write_entry = b53_arl_write_entry_89,
+	.arl_search_read = b53_arl_search_read_63xx,
+};
+
+static const struct b53_arl_ops b53_arl_ops_95 = {
+	.arl_read_entry = b53_arl_read_entry_95,
+	.arl_write_entry = b53_arl_write_entry_95,
+	.arl_search_read = b53_arl_search_read_95,
+};
+
 struct b53_chip_data {
 	u32 chip_id;
 	const char *dev_name;
@@ -2334,6 +2768,7 @@ struct b53_chip_data {
 	u8 duplex_reg;
 	u8 jumbo_pm_reg;
 	u8 jumbo_size_reg;
+	const struct b53_arl_ops *arl_ops;
 };
 
 #define B53_VTA_REGS	\
@@ -2353,6 +2788,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.arl_buckets = 1024,
 		.imp_port = 5,
 		.duplex_reg = B53_DUPLEX_STAT_FE,
+		.arl_ops = &b53_arl_ops_25,
 	},
 	{
 		.chip_id = BCM5365_DEVICE_ID,
@@ -2363,6 +2799,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.arl_buckets = 1024,
 		.imp_port = 5,
 		.duplex_reg = B53_DUPLEX_STAT_FE,
+		.arl_ops = &b53_arl_ops_25,
 	},
 	{
 		.chip_id = BCM5389_DEVICE_ID,
@@ -2376,6 +2813,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_89,
 	},
 	{
 		.chip_id = BCM5395_DEVICE_ID,
@@ -2389,6 +2827,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM5397_DEVICE_ID,
@@ -2402,6 +2841,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_89,
 	},
 	{
 		.chip_id = BCM5398_DEVICE_ID,
@@ -2415,6 +2855,21 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_89,
+	},
+	{
+		.chip_id = BCM53101_DEVICE_ID,
+		.dev_name = "BCM53101",
+		.vlans = 4096,
+		.enabled_ports = 0x11f,
+		.arl_bins = 4,
+		.arl_buckets = 512,
+		.vta_regs = B53_VTA_REGS,
+		.imp_port = 8,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM53115_DEVICE_ID,
@@ -2428,6 +2883,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM53125_DEVICE_ID,
@@ -2441,6 +2897,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM53128_DEVICE_ID,
@@ -2454,32 +2911,21 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM63XX_DEVICE_ID,
 		.dev_name = "BCM63xx",
 		.vlans = 4096,
 		.enabled_ports = 0, /* pdata must provide them */
-		.arl_bins = 4,
-		.arl_buckets = 1024,
-		.imp_port = 8,
-		.vta_regs = B53_VTA_REGS_63XX,
-		.duplex_reg = B53_DUPLEX_STAT_63XX,
-		.jumbo_pm_reg = B53_JUMBO_PORT_MASK_63XX,
-		.jumbo_size_reg = B53_JUMBO_MAX_SIZE_63XX,
-	},
-	{
-		.chip_id = BCM63268_DEVICE_ID,
-		.dev_name = "BCM63268",
-		.vlans = 4096,
-		.enabled_ports = 0, /* pdata must provide them */
-		.arl_bins = 4,
-		.arl_buckets = 1024,
+		.arl_bins = 1,
+		.arl_buckets = 4096,
 		.imp_port = 8,
 		.vta_regs = B53_VTA_REGS_63XX,
 		.duplex_reg = B53_DUPLEX_STAT_63XX,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK_63XX,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE_63XX,
+		.arl_ops = &b53_arl_ops_63xx,
 	},
 	{
 		.chip_id = BCM53010_DEVICE_ID,
@@ -2493,6 +2939,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM53011_DEVICE_ID,
@@ -2506,6 +2953,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM53012_DEVICE_ID,
@@ -2519,6 +2967,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM53018_DEVICE_ID,
@@ -2532,6 +2981,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM53019_DEVICE_ID,
@@ -2545,6 +2995,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM58XX_DEVICE_ID,
@@ -2558,6 +3009,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM583XX_DEVICE_ID,
@@ -2571,6 +3023,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	/* Starfighter 2 */
 	{
@@ -2585,6 +3038,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM7445_DEVICE_ID,
@@ -2598,6 +3052,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM7278_DEVICE_ID,
@@ -2611,6 +3066,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 	{
 		.chip_id = BCM53134_DEVICE_ID,
@@ -2625,18 +3081,23 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_GE,
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+		.arl_ops = &b53_arl_ops_95,
 	},
 };
 
 static int b53_switch_init(struct b53_device *dev)
 {
+	u32 chip_id = dev->chip_id;
 	unsigned int i;
 	int ret;
 
+	if (is63xx(dev))
+		chip_id = BCM63XX_DEVICE_ID;
+
 	for (i = 0; i < ARRAY_SIZE(b53_switch_chips); i++) {
 		const struct b53_chip_data *chip = &b53_switch_chips[i];
 
-		if (chip->chip_id == dev->chip_id) {
+		if (chip->chip_id == chip_id) {
 			if (!dev->enabled_ports)
 				dev->enabled_ports = chip->enabled_ports;
 			dev->name = chip->dev_name;
@@ -2649,6 +3110,7 @@ static int b53_switch_init(struct b53_device *dev)
 			dev->num_vlans = chip->vlans;
 			dev->num_arl_bins = chip->arl_bins;
 			dev->num_arl_buckets = chip->arl_buckets;
+			dev->arl_ops = chip->arl_ops;
 			break;
 		}
 	}
@@ -2679,6 +3141,9 @@ static int b53_switch_init(struct b53_device *dev)
 		}
 	}
 
+	if (is5325e(dev))
+		dev->num_arl_buckets = 512;
+
 	dev->num_ports = fls(dev->enabled_ports);
 
 	dev->ds->num_ports = min_t(unsigned int, dev->num_ports, DSA_MAX_PORTS);
@@ -2741,6 +3206,7 @@ struct b53_device *b53_switch_alloc(struct device *base,
 	ds->ops = &b53_switch_ops;
 	ds->phylink_mac_ops = &b53_phylink_mac_ops;
 	dev->vlan_enabled = true;
+	dev->vlan_filtering = false;
 	/* Let DSA handle the case were multiple bridges span the same switch
 	 * device and different VLAN awareness settings are requested, which
 	 * would be breaking filtering semantics for any of the other bridge
@@ -2779,10 +3245,24 @@ int b53_switch_detect(struct b53_device *dev)
 		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_25, 0xf);
 		b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_25, &tmp);
 
-		if (tmp == 0xf)
+		if (tmp == 0xf) {
+			u32 phy_id;
+			int val;
+
 			dev->chip_id = BCM5325_DEVICE_ID;
-		else
+
+			val = b53_phy_read16(dev->ds, 0, MII_PHYSID1);
+			phy_id = (val & 0xffff) << 16;
+			val = b53_phy_read16(dev->ds, 0, MII_PHYSID2);
+			phy_id |= (val & 0xfff0);
+
+			if (phy_id == 0x00406330)
+				dev->variant_id = B53_VARIANT_5325M;
+			else if (phy_id == 0x0143bc30)
+				dev->variant_id = B53_VARIANT_5325E;
+		} else {
 			dev->chip_id = BCM5365_DEVICE_ID;
+		}
 		break;
 	case BCM5389_DEVICE_ID:
 	case BCM5395_DEVICE_ID:
@@ -2796,6 +3276,7 @@ int b53_switch_detect(struct b53_device *dev)
 			return ret;
 
 		switch (id32) {
+		case BCM53101_DEVICE_ID:
 		case BCM53115_DEVICE_ID:
 		case BCM53125_DEVICE_ID:
 		case BCM53128_DEVICE_ID:
diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c
index 31d070bf161a..43a3b37b731b 100644
--- a/drivers/net/dsa/b53/b53_mdio.c
+++ b/drivers/net/dsa/b53/b53_mdio.c
@@ -374,6 +374,7 @@ static void b53_mdio_shutdown(struct mdio_device *mdiodev)
 
 static const struct of_device_id b53_of_match[] = {
 	{ .compatible = "brcm,bcm5325" },
+	{ .compatible = "brcm,bcm53101" },
 	{ .compatible = "brcm,bcm53115" },
 	{ .compatible = "brcm,bcm53125" },
 	{ .compatible = "brcm,bcm53128" },
diff --git a/drivers/net/dsa/b53/b53_mmap.c b/drivers/net/dsa/b53/b53_mmap.c
index c687360a5b7f..f4a59d8fbdd6 100644
--- a/drivers/net/dsa/b53/b53_mmap.c
+++ b/drivers/net/dsa/b53/b53_mmap.c
@@ -21,13 +21,60 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/io.h>
+#include <linux/mfd/syscon.h>
 #include <linux/platform_device.h>
 #include <linux/platform_data/b53.h>
+#include <linux/regmap.h>
 
 #include "b53_priv.h"
 
+#define BCM63XX_EPHY_REG 0x3C
+#define BCM63268_GPHY_REG 0x54
+
+#define GPHY_CTRL_LOW_PWR	BIT(3)
+#define GPHY_CTRL_IDDQ_BIAS	BIT(0)
+
+struct b53_phy_info {
+	u32 gphy_port_mask;
+	u32 ephy_enable_mask;
+	u32 ephy_port_mask;
+	u32 ephy_bias_bit;
+	const u32 *ephy_offset;
+};
+
 struct b53_mmap_priv {
 	void __iomem *regs;
+	struct regmap *gpio_ctrl;
+	const struct b53_phy_info *phy_info;
+	u32 phys_enabled;
+};
+
+static const u32 bcm6318_ephy_offsets[] = {4, 5, 6, 7};
+
+static const struct b53_phy_info bcm6318_ephy_info = {
+	.ephy_enable_mask = BIT(0) | BIT(4) | BIT(8) | BIT(12) | BIT(16),
+	.ephy_port_mask = GENMASK((ARRAY_SIZE(bcm6318_ephy_offsets) - 1), 0),
+	.ephy_bias_bit = 24,
+	.ephy_offset = bcm6318_ephy_offsets,
+};
+
+static const u32 bcm6368_ephy_offsets[] = {2, 3, 4, 5};
+
+static const struct b53_phy_info bcm6368_ephy_info = {
+	.ephy_enable_mask = BIT(0),
+	.ephy_port_mask = GENMASK((ARRAY_SIZE(bcm6368_ephy_offsets) - 1), 0),
+	.ephy_bias_bit = 0,
+	.ephy_offset = bcm6368_ephy_offsets,
+};
+
+static const u32 bcm63268_ephy_offsets[] = {4, 9, 14};
+
+static const struct b53_phy_info bcm63268_ephy_info = {
+	.gphy_port_mask = BIT(3),
+	.ephy_enable_mask = GENMASK(4, 0),
+	.ephy_port_mask = GENMASK((ARRAY_SIZE(bcm63268_ephy_offsets) - 1), 0),
+	.ephy_bias_bit = 24,
+	.ephy_offset = bcm63268_ephy_offsets,
 };
 
 static int b53_mmap_read8(struct b53_device *dev, u8 page, u8 reg, u8 *val)
@@ -229,6 +276,71 @@ static int b53_mmap_phy_write16(struct b53_device *dev, int addr, int reg,
 	return -EIO;
 }
 
+static int bcm63xx_ephy_set(struct b53_device *dev, int port, bool enable)
+{
+	struct b53_mmap_priv *priv = dev->priv;
+	const struct b53_phy_info *info = priv->phy_info;
+	struct regmap *gpio_ctrl = priv->gpio_ctrl;
+	u32 mask, val;
+
+	if (enable) {
+		mask = (info->ephy_enable_mask << info->ephy_offset[port])
+				| BIT(info->ephy_bias_bit);
+		val = 0;
+	} else {
+		mask = (info->ephy_enable_mask << info->ephy_offset[port]);
+		if (!((priv->phys_enabled & ~BIT(port)) & info->ephy_port_mask))
+			mask |= BIT(info->ephy_bias_bit);
+		val = mask;
+	}
+	return regmap_update_bits(gpio_ctrl, BCM63XX_EPHY_REG, mask, val);
+}
+
+static int bcm63268_gphy_set(struct b53_device *dev, bool enable)
+{
+	struct b53_mmap_priv *priv = dev->priv;
+	struct regmap *gpio_ctrl = priv->gpio_ctrl;
+	u32 mask = GPHY_CTRL_IDDQ_BIAS | GPHY_CTRL_LOW_PWR;
+	u32 val = 0;
+
+	if (!enable)
+		val = mask;
+
+	return regmap_update_bits(gpio_ctrl, BCM63268_GPHY_REG, mask, val);
+}
+
+static void b53_mmap_phy_enable(struct b53_device *dev, int port)
+{
+	struct b53_mmap_priv *priv = dev->priv;
+	int ret = 0;
+
+	if (priv->phy_info) {
+		if (BIT(port) & priv->phy_info->ephy_port_mask)
+			ret = bcm63xx_ephy_set(dev, port, true);
+		else if (BIT(port) & priv->phy_info->gphy_port_mask)
+			ret = bcm63268_gphy_set(dev, true);
+	}
+
+	if (!ret)
+		priv->phys_enabled |= BIT(port);
+}
+
+static void b53_mmap_phy_disable(struct b53_device *dev, int port)
+{
+	struct b53_mmap_priv *priv = dev->priv;
+	int ret = 0;
+
+	if (priv->phy_info) {
+		if (BIT(port) & priv->phy_info->ephy_port_mask)
+			ret = bcm63xx_ephy_set(dev, port, false);
+		else if (BIT(port) & priv->phy_info->gphy_port_mask)
+			ret = bcm63268_gphy_set(dev, false);
+	}
+
+	if (!ret)
+		priv->phys_enabled &= ~BIT(port);
+}
+
 static const struct b53_io_ops b53_mmap_ops = {
 	.read8 = b53_mmap_read8,
 	.read16 = b53_mmap_read16,
@@ -242,6 +354,8 @@ static const struct b53_io_ops b53_mmap_ops = {
 	.write64 = b53_mmap_write64,
 	.phy_read16 = b53_mmap_phy_read16,
 	.phy_write16 = b53_mmap_phy_write16,
+	.phy_enable = b53_mmap_phy_enable,
+	.phy_disable = b53_mmap_phy_disable,
 };
 
 static int b53_mmap_probe_of(struct platform_device *pdev,
@@ -313,6 +427,18 @@ static int b53_mmap_probe(struct platform_device *pdev)
 
 	priv->regs = pdata->regs;
 
+	priv->gpio_ctrl = syscon_regmap_lookup_by_phandle(np, "brcm,gpio-ctrl");
+	if (!IS_ERR(priv->gpio_ctrl)) {
+		if (pdata->chip_id == BCM6318_DEVICE_ID ||
+		    pdata->chip_id == BCM6328_DEVICE_ID ||
+		    pdata->chip_id == BCM6362_DEVICE_ID)
+			priv->phy_info = &bcm6318_ephy_info;
+		else if (pdata->chip_id == BCM6368_DEVICE_ID)
+			priv->phy_info = &bcm6368_ephy_info;
+		else if (pdata->chip_id == BCM63268_DEVICE_ID)
+			priv->phy_info = &bcm63268_ephy_info;
+	}
+
 	dev = b53_switch_alloc(&pdev->dev, &b53_mmap_ops, priv);
 	if (!dev)
 		return -ENOMEM;
@@ -348,16 +474,16 @@ static const struct of_device_id b53_mmap_of_table[] = {
 		.data = (void *)BCM63XX_DEVICE_ID,
 	}, {
 		.compatible = "brcm,bcm6318-switch",
-		.data = (void *)BCM63268_DEVICE_ID,
+		.data = (void *)BCM6318_DEVICE_ID,
 	}, {
 		.compatible = "brcm,bcm6328-switch",
-		.data = (void *)BCM63XX_DEVICE_ID,
+		.data = (void *)BCM6328_DEVICE_ID,
 	}, {
 		.compatible = "brcm,bcm6362-switch",
-		.data = (void *)BCM63XX_DEVICE_ID,
+		.data = (void *)BCM6362_DEVICE_ID,
 	}, {
 		.compatible = "brcm,bcm6368-switch",
-		.data = (void *)BCM63XX_DEVICE_ID,
+		.data = (void *)BCM6368_DEVICE_ID,
 	}, {
 		.compatible = "brcm,bcm63268-switch",
 		.data = (void *)BCM63268_DEVICE_ID,
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 99e5cfc98ae8..bd6849e5bb93 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -45,6 +45,8 @@ struct b53_io_ops {
 	int (*phy_write16)(struct b53_device *dev, int addr, int reg, u16 value);
 	int (*irq_enable)(struct b53_device *dev, int port);
 	void (*irq_disable)(struct b53_device *dev, int port);
+	void (*phy_enable)(struct b53_device *dev, int port);
+	void (*phy_disable)(struct b53_device *dev, int port);
 	void (*phylink_get_caps)(struct b53_device *dev, int port,
 				 struct phylink_config *config);
 	struct phylink_pcs *(*phylink_mac_select_pcs)(struct b53_device *dev,
@@ -56,6 +58,17 @@ struct b53_io_ops {
 				bool link_up);
 };
 
+struct b53_arl_entry;
+
+struct b53_arl_ops {
+	void (*arl_read_entry)(struct b53_device *dev,
+			       struct b53_arl_entry *ent, u8 idx);
+	void (*arl_write_entry)(struct b53_device *dev,
+				const struct b53_arl_entry *ent, u8 idx);
+	void (*arl_search_read)(struct b53_device *dev, u8 idx,
+				struct b53_arl_entry *ent);
+};
+
 #define B53_INVALID_LANE	0xff
 
 enum {
@@ -66,10 +79,15 @@ enum {
 	BCM5395_DEVICE_ID = 0x95,
 	BCM5397_DEVICE_ID = 0x97,
 	BCM5398_DEVICE_ID = 0x98,
+	BCM53101_DEVICE_ID = 0x53101,
 	BCM53115_DEVICE_ID = 0x53115,
 	BCM53125_DEVICE_ID = 0x53125,
 	BCM53128_DEVICE_ID = 0x53128,
 	BCM63XX_DEVICE_ID = 0x6300,
+	BCM6318_DEVICE_ID = 0x6318,
+	BCM6328_DEVICE_ID = 0x6328,
+	BCM6362_DEVICE_ID = 0x6362,
+	BCM6368_DEVICE_ID = 0x6368,
 	BCM63268_DEVICE_ID = 0x63268,
 	BCM53010_DEVICE_ID = 0x53010,
 	BCM53011_DEVICE_ID = 0x53011,
@@ -83,6 +101,12 @@ enum {
 	BCM53134_DEVICE_ID = 0x5075,
 };
 
+enum b53_variant_id {
+	B53_VARIANT_NONE = 0,
+	B53_VARIANT_5325E,
+	B53_VARIANT_5325M,
+};
+
 struct b53_pcs {
 	struct phylink_pcs pcs;
 	struct b53_device *dev;
@@ -95,6 +119,7 @@ struct b53_pcs {
 
 struct b53_port {
 	u16		vlan_ctl_mask;
+	u16		pvid;
 	struct ethtool_keee eee;
 };
 
@@ -113,9 +138,11 @@ struct b53_device {
 	struct mutex stats_mutex;
 	struct mutex arl_mutex;
 	const struct b53_io_ops *ops;
+	const struct b53_arl_ops *arl_ops;
 
 	/* chip specific data */
 	u32 chip_id;
+	enum b53_variant_id variant_id;
 	u8 core_rev;
 	u8 vta_regs[3];
 	u8 duplex_reg;
@@ -146,6 +173,7 @@ struct b53_device {
 	unsigned int num_vlans;
 	struct b53_vlan *vlans;
 	bool vlan_enabled;
+	bool vlan_filtering;
 	unsigned int num_ports;
 	struct b53_port *ports;
 
@@ -162,6 +190,18 @@ static inline int is5325(struct b53_device *dev)
 	return dev->chip_id == BCM5325_DEVICE_ID;
 }
 
+static inline int is5325e(struct b53_device *dev)
+{
+	return is5325(dev) &&
+		dev->variant_id == B53_VARIANT_5325E;
+}
+
+static inline int is5325m(struct b53_device *dev)
+{
+	return is5325(dev) &&
+		dev->variant_id == B53_VARIANT_5325M;
+}
+
 static inline int is5365(struct b53_device *dev)
 {
 #ifdef CONFIG_BCM47XX
@@ -188,6 +228,7 @@ static inline int is531x5(struct b53_device *dev)
 {
 	return dev->chip_id == BCM53115_DEVICE_ID ||
 		dev->chip_id == BCM53125_DEVICE_ID ||
+		dev->chip_id == BCM53101_DEVICE_ID ||
 		dev->chip_id == BCM53128_DEVICE_ID ||
 		dev->chip_id == BCM53134_DEVICE_ID;
 }
@@ -195,12 +236,17 @@ static inline int is531x5(struct b53_device *dev)
 static inline int is63xx(struct b53_device *dev)
 {
 	return dev->chip_id == BCM63XX_DEVICE_ID ||
+		dev->chip_id == BCM6318_DEVICE_ID ||
+		dev->chip_id == BCM6328_DEVICE_ID ||
+		dev->chip_id == BCM6362_DEVICE_ID ||
+		dev->chip_id == BCM6368_DEVICE_ID ||
 		dev->chip_id == BCM63268_DEVICE_ID;
 }
 
-static inline int is63268(struct b53_device *dev)
+static inline int is6318_268(struct b53_device *dev)
 {
-	return dev->chip_id == BCM63268_DEVICE_ID;
+	return dev->chip_id == BCM6318_DEVICE_ID ||
+		dev->chip_id == BCM63268_DEVICE_ID;
 }
 
 static inline int is5301x(struct b53_device *dev)
@@ -294,6 +340,33 @@ static inline void b53_arl_to_entry(struct b53_arl_entry *ent,
 	ent->vid = mac_vid >> ARLTBL_VID_S;
 }
 
+static inline void b53_arl_to_entry_25(struct b53_arl_entry *ent,
+				       u64 mac_vid, u8 vid_entry)
+{
+	memset(ent, 0, sizeof(*ent));
+	ent->is_valid = !!(mac_vid & ARLTBL_VALID_25);
+	ent->is_age = !!(mac_vid & ARLTBL_AGE_25);
+	ent->is_static = !!(mac_vid & ARLTBL_STATIC_25);
+	u64_to_ether_addr(mac_vid, ent->mac);
+	ent->port = (mac_vid & ARLTBL_DATA_PORT_ID_MASK_25) >>
+		     ARLTBL_DATA_PORT_ID_S_25;
+	if (is_unicast_ether_addr(ent->mac) && ent->port == B53_CPU_PORT)
+		ent->port = B53_CPU_PORT_25;
+	ent->vid = vid_entry;
+}
+
+static inline void b53_arl_to_entry_89(struct b53_arl_entry *ent,
+				       u64 mac_vid, u16 fwd_entry)
+{
+	memset(ent, 0, sizeof(*ent));
+	ent->port = fwd_entry & ARLTBL_DATA_PORT_ID_MASK_89;
+	ent->is_valid = !!(fwd_entry & ARLTBL_VALID_89);
+	ent->is_age = !!(fwd_entry & ARLTBL_AGE_89);
+	ent->is_static = !!(fwd_entry & ARLTBL_STATIC_89);
+	u64_to_ether_addr(mac_vid, ent->mac);
+	ent->vid = mac_vid >> ARLTBL_VID_S;
+}
+
 static inline void b53_arl_from_entry(u64 *mac_vid, u32 *fwd_entry,
 				      const struct b53_arl_entry *ent)
 {
@@ -308,6 +381,89 @@ static inline void b53_arl_from_entry(u64 *mac_vid, u32 *fwd_entry,
 		*fwd_entry |= ARLTBL_AGE;
 }
 
+static inline void b53_arl_from_entry_25(u64 *mac_vid, u8 *vid_entry,
+					 const struct b53_arl_entry *ent)
+{
+	*mac_vid = ether_addr_to_u64(ent->mac);
+	if (is_unicast_ether_addr(ent->mac) && ent->port == B53_CPU_PORT_25)
+		*mac_vid |= (u64)B53_CPU_PORT << ARLTBL_DATA_PORT_ID_S_25;
+	else
+		*mac_vid |= ((u64)ent->port << ARLTBL_DATA_PORT_ID_S_25) &
+			    ARLTBL_DATA_PORT_ID_MASK_25;
+	if (ent->is_valid)
+		*mac_vid |= ARLTBL_VALID_25;
+	if (ent->is_static)
+		*mac_vid |= ARLTBL_STATIC_25;
+	if (ent->is_age)
+		*mac_vid |= ARLTBL_AGE_25;
+	*vid_entry = ent->vid;
+}
+
+static inline void b53_arl_from_entry_89(u64 *mac_vid, u32 *fwd_entry,
+					 const struct b53_arl_entry *ent)
+{
+	*mac_vid = ether_addr_to_u64(ent->mac);
+	*mac_vid |= (u64)(ent->vid & ARLTBL_VID_MASK) << ARLTBL_VID_S;
+	*fwd_entry = ent->port & ARLTBL_DATA_PORT_ID_MASK_89;
+	if (ent->is_valid)
+		*fwd_entry |= ARLTBL_VALID_89;
+	if (ent->is_static)
+		*fwd_entry |= ARLTBL_STATIC_89;
+	if (ent->is_age)
+		*fwd_entry |= ARLTBL_AGE_89;
+}
+
+static inline void b53_arl_search_to_entry_25(struct b53_arl_entry *ent,
+					      u64 mac_vid, u8 ext)
+{
+	memset(ent, 0, sizeof(*ent));
+	ent->is_valid = !!(mac_vid & ARLTBL_VALID_25);
+	ent->is_age = !!(mac_vid & ARLTBL_AGE_25);
+	ent->is_static = !!(mac_vid & ARLTBL_STATIC_25);
+	u64_to_ether_addr(mac_vid, ent->mac);
+	ent->vid = (mac_vid & ARL_SRCH_RSLT_VID_MASK_25) >>
+		   ARL_SRCH_RSLT_VID_S_25;
+	ent->port = (mac_vid & ARL_SRCH_RSLT_PORT_ID_MASK_25) >>
+		    ARL_SRCH_RSLT_PORT_ID_S_25;
+	if (is_multicast_ether_addr(ent->mac) && (ext & ARL_SRCH_RSLT_EXT_MC_MII))
+		ent->port |= BIT(B53_CPU_PORT_25);
+	else if (!is_multicast_ether_addr(ent->mac) && ent->port == B53_CPU_PORT)
+		ent->port = B53_CPU_PORT_25;
+}
+
+static inline void b53_arl_search_to_entry_63xx(struct b53_arl_entry *ent,
+						u64 mac_vid, u16 fwd_entry)
+{
+	memset(ent, 0, sizeof(*ent));
+	u64_to_ether_addr(mac_vid, ent->mac);
+	ent->vid = mac_vid >> ARLTBL_VID_S;
+
+	ent->port = fwd_entry & ARL_SRST_PORT_ID_MASK_63XX;
+	ent->port >>= 1;
+
+	ent->is_age = !!(fwd_entry & ARL_SRST_AGE_63XX);
+	ent->is_static = !!(fwd_entry & ARL_SRST_STATIC_63XX);
+	ent->is_valid = 1;
+}
+
+static inline void b53_arl_read_entry(struct b53_device *dev,
+				      struct b53_arl_entry *ent, u8 idx)
+{
+	dev->arl_ops->arl_read_entry(dev, ent, idx);
+}
+
+static inline void b53_arl_write_entry(struct b53_device *dev,
+				       const struct b53_arl_entry *ent, u8 idx)
+{
+	dev->arl_ops->arl_write_entry(dev, ent, idx);
+}
+
+static inline void b53_arl_search_read(struct b53_device *dev, u8 idx,
+				       struct b53_arl_entry *ent)
+{
+	dev->arl_ops->arl_search_read(dev, idx, ent);
+}
+
 #ifdef CONFIG_BCM47XX
 
 #include <linux/bcm47xx_nvram.h>
@@ -339,6 +495,7 @@ void b53_get_strings(struct dsa_switch *ds, int port, u32 stringset,
 void b53_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data);
 int b53_get_sset_count(struct dsa_switch *ds, int port, int sset);
 void b53_get_ethtool_phy_stats(struct dsa_switch *ds, int port, uint64_t *data);
+int b53_set_ageing_time(struct dsa_switch *ds, unsigned int msecs);
 int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
 		bool *tx_fwd_offload, struct netlink_ext_ack *extack);
 void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge);
@@ -380,12 +537,12 @@ enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port,
 					   enum dsa_tag_protocol mprot);
 void b53_mirror_del(struct dsa_switch *ds, int port,
 		    struct dsa_mall_mirror_tc_entry *mirror);
+int b53_setup_port(struct dsa_switch *ds, int port);
 int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy);
 void b53_disable_port(struct dsa_switch *ds, int port);
 void b53_brcm_hdr_setup(struct dsa_switch *ds, int port);
 int b53_eee_init(struct dsa_switch *ds, int port, struct phy_device *phy);
 bool b53_support_eee(struct dsa_switch *ds, int port);
-int b53_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e);
 int b53_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e);
 
 #endif
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index bfbcb66bef66..54a278db67c9 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -29,6 +29,7 @@
 #define B53_ARLIO_PAGE			0x05 /* ARL Access */
 #define B53_FRAMEBUF_PAGE		0x06 /* Management frame access */
 #define B53_MEM_ACCESS_PAGE		0x08 /* Memory access */
+#define B53_IEEE_PAGE			0x0a /* IEEE 802.1X */
 
 /* PHY Registers */
 #define B53_PORT_MII_PAGE(i)		(0x10 + (i)) /* Port i MII Registers */
@@ -50,6 +51,9 @@
 /* Jumbo Frame Registers */
 #define B53_JUMBO_PAGE			0x40
 
+/* EAP Registers */
+#define B53_EAP_PAGE			0x42
+
 /* EEE Control Registers Page */
 #define B53_EEE_PAGE			0x92
 
@@ -92,18 +96,22 @@
 #define   PORT_OVERRIDE_SPEED_10M	(0 << PORT_OVERRIDE_SPEED_S)
 #define   PORT_OVERRIDE_SPEED_100M	(1 << PORT_OVERRIDE_SPEED_S)
 #define   PORT_OVERRIDE_SPEED_1000M	(2 << PORT_OVERRIDE_SPEED_S)
+#define   PORT_OVERRIDE_LP_FLOW_25	BIT(3) /* BCM5325 only */
 #define   PORT_OVERRIDE_RV_MII_25	BIT(4) /* BCM5325 only */
 #define   PORT_OVERRIDE_RX_FLOW		BIT(4)
 #define   PORT_OVERRIDE_TX_FLOW		BIT(5)
 #define   PORT_OVERRIDE_SPEED_2000M	BIT(6) /* BCM5301X only, requires setting 1000M */
 #define   PORT_OVERRIDE_EN		BIT(7) /* Use the register contents */
 
-/* Power-down mode control */
+/* Power-down mode control (8 bit) */
 #define B53_PD_MODE_CTRL_25		0x0f
+#define  PD_MODE_PORT_MASK		0x1f
+/* Bit 0 also powers down the switch. */
+#define  PD_MODE_POWER_DOWN_PORT(i)	BIT(i)
 
 /* IP Multicast control (8 bit) */
 #define B53_IP_MULTICAST_CTRL		0x21
-#define  B53_IPMC_FWD_EN		BIT(1)
+#define  B53_IP_MC			BIT(0)
 #define  B53_UC_FWD_EN			BIT(6)
 #define  B53_MC_FWD_EN			BIT(7)
 
@@ -111,6 +119,10 @@
 #define B53_SWITCH_CTRL			0x22
 #define  B53_MII_DUMB_FWDG_EN		BIT(6)
 
+/* Protected Port Selection (16 bit) */
+#define B53_PROTECTED_PORT_SEL		0x24
+#define B53_PROTECTED_PORT_SEL_25	0x26
+
 /* (16 bit) */
 #define B53_UC_FLOOD_MASK		0x32
 #define B53_MC_FLOOD_MASK		0x34
@@ -217,6 +229,13 @@
 #define   BRCM_HDR_P5_EN		BIT(1) /* Enable tagging on port 5 */
 #define   BRCM_HDR_P7_EN		BIT(2) /* Enable tagging on port 7 */
 
+/* Aging Time control register (32 bit) */
+#define B53_AGING_TIME_CONTROL		0x06
+#define B53_AGING_TIME_CONTROL_63XX	0x08
+#define  AGE_CHANGE			BIT(20)
+#define  AGE_TIME_MASK			0x7ffff
+#define  AGE_TIME_MAX			1048575
+
 /* Mirror capture control register (16 bit) */
 #define B53_MIR_CAP_CTL			0x10
 #define  CAP_PORT_MASK			0xf
@@ -310,13 +329,12 @@
 #define B53_ARLTBL_MAC_VID_ENTRY(n)	((0x10 * (n)) + 0x10)
 #define   ARLTBL_MAC_MASK		0xffffffffffffULL
 #define   ARLTBL_VID_S			48
-#define   ARLTBL_VID_MASK_25		0xff
 #define   ARLTBL_VID_MASK		0xfff
 #define   ARLTBL_DATA_PORT_ID_S_25	48
-#define   ARLTBL_DATA_PORT_ID_MASK_25	0xf
-#define   ARLTBL_AGE_25			BIT(61)
-#define   ARLTBL_STATIC_25		BIT(62)
-#define   ARLTBL_VALID_25		BIT(63)
+#define   ARLTBL_DATA_PORT_ID_MASK_25	GENMASK_ULL(53, 48)
+#define   ARLTBL_AGE_25			BIT_ULL(61)
+#define   ARLTBL_STATIC_25		BIT_ULL(62)
+#define   ARLTBL_VALID_25		BIT_ULL(63)
 
 /* ARL Table Data Entry N Registers (32 bit) */
 #define B53_ARLTBL_DATA_ENTRY(n)	((0x10 * (n)) + 0x18)
@@ -326,12 +344,23 @@
 #define   ARLTBL_STATIC			BIT(15)
 #define   ARLTBL_VALID			BIT(16)
 
+/* BCM5389 ARL Table Data Entry N Register format (16 bit) */
+#define   ARLTBL_DATA_PORT_ID_MASK_89	GENMASK(8, 0)
+#define   ARLTBL_TC_MASK_89		GENMASK(12, 10)
+#define   ARLTBL_AGE_89			BIT(13)
+#define   ARLTBL_STATIC_89		BIT(14)
+#define   ARLTBL_VALID_89		BIT(15)
+
+/* BCM5325/BCM565 ARL Table VID Entry N Registers (8 bit) */
+#define B53_ARLTBL_VID_ENTRY_25(n)	((0x2 * (n)) + 0x30)
+
 /* Maximum number of bin entries in the ARL for all switches */
 #define B53_ARLTBL_MAX_BIN_ENTRIES	4
 
 /* ARL Search Control Register (8 bit) */
 #define B53_ARL_SRCH_CTL		0x50
 #define B53_ARL_SRCH_CTL_25		0x20
+#define B53_ARL_SRCH_CTL_89		0x30
 #define   ARL_SRCH_VLID			BIT(0)
 #define   ARL_SRCH_STDN			BIT(7)
 
@@ -339,22 +368,54 @@
 #define B53_ARL_SRCH_ADDR		0x51
 #define B53_ARL_SRCH_ADDR_25		0x22
 #define B53_ARL_SRCH_ADDR_65		0x24
+#define B53_ARL_SRCH_ADDR_89		0x31
+#define B53_ARL_SRCH_ADDR_63XX		0x32
 #define  ARL_ADDR_MASK			GENMASK(14, 0)
 
 /* ARL Search MAC/VID Result (64 bit) */
 #define B53_ARL_SRCH_RSTL_0_MACVID	0x60
+#define B53_ARL_SRCH_RSLT_MACVID_89	0x33
+#define B53_ARL_SRCH_RSLT_MACVID_63XX	0x34
 
-/* Single register search result on 5325 */
+/* Single register search result on 5325/5365 */
 #define B53_ARL_SRCH_RSTL_0_MACVID_25	0x24
-/* Single register search result on 5365 */
-#define B53_ARL_SRCH_RSTL_0_MACVID_65	0x30
+#define   ARL_SRCH_RSLT_PORT_ID_S_25	48
+#define   ARL_SRCH_RSLT_PORT_ID_MASK_25	GENMASK_ULL(52, 48)
+#define   ARL_SRCH_RSLT_VID_S_25	53
+#define   ARL_SRCH_RSLT_VID_MASK_25	GENMASK_ULL(60, 53)
+
+/* BCM5325/5365 Search result extend register (8 bit) */
+#define B53_ARL_SRCH_RSLT_EXT_25	0x2c
+#define   ARL_SRCH_RSLT_EXT_MC_MII	BIT(2)
 
 /* ARL Search Data Result (32 bit) */
 #define B53_ARL_SRCH_RSTL_0		0x68
 
+/* BCM5389 ARL Search Data Result (16 bit) */
+#define B53_ARL_SRCH_RSLT_89		0x3b
+
 #define B53_ARL_SRCH_RSTL_MACVID(x)	(B53_ARL_SRCH_RSTL_0_MACVID + ((x) * 0x10))
 #define B53_ARL_SRCH_RSTL(x)		(B53_ARL_SRCH_RSTL_0 + ((x) * 0x10))
 
+/* 63XX ARL Search Data Result (16 bit) */
+#define B53_ARL_SRCH_RSLT_63XX		0x3c
+#define   ARL_SRST_PORT_ID_MASK_63XX	GENMASK(9, 1)
+#define   ARL_SRST_TC_MASK_63XX		GENMASK(13, 11)
+#define   ARL_SRST_AGE_63XX		BIT(14)
+#define   ARL_SRST_STATIC_63XX		BIT(15)
+
+/*************************************************************************
+ * IEEE 802.1X Registers
+ *************************************************************************/
+
+/* Multicast DLF Drop Control register (16 bit) */
+#define B53_IEEE_MCAST_DLF		0x94
+#define B53_IEEE_MCAST_DROP_EN		BIT(11)
+
+/* Unicast DLF Drop Control register (16 bit) */
+#define B53_IEEE_UCAST_DLF		0x96
+#define B53_IEEE_UCAST_DROP_EN		BIT(11)
+
 /*************************************************************************
  * Port VLAN Registers
  *************************************************************************/
@@ -481,6 +542,17 @@
 #define   JMS_MAX_SIZE			9724
 
 /*************************************************************************
+ * EAP Page Registers
+ *************************************************************************/
+#define B53_PORT_EAP_CONF(i)		(0x20 + 8 * (i))
+#define  EAP_MODE_SHIFT			51
+#define  EAP_MODE_SHIFT_63XX		50
+#define  EAP_MODE_MASK			(0x3ull << EAP_MODE_SHIFT)
+#define  EAP_MODE_MASK_63XX		(0x3ull << EAP_MODE_SHIFT_63XX)
+#define  EAP_MODE_BASIC			0
+#define  EAP_MODE_SIMPLIFIED		3
+
+/*************************************************************************
  * EEE Configuration Page Registers
  *************************************************************************/
 
diff --git a/drivers/net/dsa/b53/b53_serdes.c b/drivers/net/dsa/b53/b53_serdes.c
index 3f8a491ce885..7460122f6abc 100644
--- a/drivers/net/dsa/b53/b53_serdes.c
+++ b/drivers/net/dsa/b53/b53_serdes.c
@@ -99,8 +99,8 @@ static void b53_serdes_an_restart(struct phylink_pcs *pcs)
 			 SERDES_MII_BLK, reg);
 }
 
-static void b53_serdes_get_state(struct phylink_pcs *pcs,
-				  struct phylink_link_state *state)
+static void b53_serdes_get_state(struct phylink_pcs *pcs, unsigned int neg_mode,
+				 struct phylink_link_state *state)
 {
 	struct b53_device *dev = pcs_to_b53_pcs(pcs)->dev;
 	u8 lane = pcs_to_b53_pcs(pcs)->lane;
@@ -239,7 +239,6 @@ int b53_serdes_init(struct b53_device *dev, int port)
 	pcs->dev = dev;
 	pcs->lane = lane;
 	pcs->pcs.ops = &b53_pcs_ops;
-	pcs->pcs.neg_mode = true;
 
 	return 0;
 }
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index a53fb6191e6b..960685596093 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1230,11 +1230,12 @@ static const struct dsa_switch_ops bcm_sf2_ops = {
 	.resume			= bcm_sf2_sw_resume,
 	.get_wol		= bcm_sf2_sw_get_wol,
 	.set_wol		= bcm_sf2_sw_set_wol,
+	.port_setup		= b53_setup_port,
 	.port_enable		= bcm_sf2_port_setup,
 	.port_disable		= bcm_sf2_port_disable,
 	.support_eee		= b53_support_eee,
-	.get_mac_eee		= b53_get_mac_eee,
 	.set_mac_eee		= b53_set_mac_eee,
+	.set_ageing_time	= b53_set_ageing_time,
 	.port_bridge_join	= b53_br_join,
 	.port_bridge_leave	= b53_br_leave,
 	.port_pre_bridge_flags	= b53_br_flags_pre,
diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index adbab544c60f..4a416f2717ba 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -17,7 +17,19 @@
 #include <linux/dsa/loop.h>
 #include <net/dsa.h>
 
-#include "dsa_loop.h"
+#define DSA_LOOP_NUM_PORTS	6
+#define DSA_LOOP_CPU_PORT	(DSA_LOOP_NUM_PORTS - 1)
+#define NUM_FIXED_PHYS		(DSA_LOOP_NUM_PORTS - 2)
+
+struct dsa_loop_pdata {
+	/* Must be first, such that dsa_register_switch() can access this
+	 * without gory pointer manipulations
+	 */
+	struct dsa_chip_data cd;
+	const char *name;
+	unsigned int enabled_ports;
+	const char *netdev;
+};
 
 static struct dsa_loop_mib_entry dsa_loop_mibs[] = {
 	[DSA_LOOP_PHY_READ_OK]	= { "phy_read_ok", },
@@ -27,6 +39,7 @@ static struct dsa_loop_mib_entry dsa_loop_mibs[] = {
 };
 
 static struct phy_device *phydevs[PHY_MAX_ADDR];
+static struct mdio_device *switch_mdiodev;
 
 enum dsa_loop_devlink_resource_id {
 	DSA_LOOP_DEVLINK_PARAM_ID_VTU,
@@ -382,34 +395,68 @@ static struct mdio_driver dsa_loop_drv = {
 	.shutdown = dsa_loop_drv_shutdown,
 };
 
-#define NUM_FIXED_PHYS	(DSA_LOOP_NUM_PORTS - 2)
-
 static void dsa_loop_phydevs_unregister(void)
 {
-	unsigned int i;
-
-	for (i = 0; i < NUM_FIXED_PHYS; i++)
-		if (!IS_ERR(phydevs[i])) {
+	for (int i = 0; i < NUM_FIXED_PHYS; i++) {
+		if (!IS_ERR(phydevs[i]))
 			fixed_phy_unregister(phydevs[i]);
-			phy_device_free(phydevs[i]);
-		}
+	}
 }
 
-static int __init dsa_loop_init(void)
+static int __init dsa_loop_create_switch_mdiodev(void)
 {
-	struct fixed_phy_status status = {
-		.link = 1,
-		.speed = SPEED_100,
-		.duplex = DUPLEX_FULL,
+	static struct dsa_loop_pdata dsa_loop_pdata = {
+		.cd = {
+			.port_names[0] = "lan1",
+			.port_names[1] = "lan2",
+			.port_names[2] = "lan3",
+			.port_names[3] = "lan4",
+			.port_names[DSA_LOOP_CPU_PORT] = "cpu",
+		},
+		.name = "DSA mockup driver",
+		.enabled_ports = 0x1f,
+		.netdev = "eth0",
 	};
-	unsigned int i, ret;
+	struct mii_bus *bus;
+	int ret = -ENODEV;
+
+	bus = mdio_find_bus("fixed-0");
+	if (WARN_ON(!bus))
+		return ret;
+
+	switch_mdiodev = mdio_device_create(bus, 31);
+	if (IS_ERR(switch_mdiodev))
+		goto out;
+
+	strscpy(switch_mdiodev->modalias, "dsa-loop");
+	switch_mdiodev->dev.platform_data = &dsa_loop_pdata;
+
+	ret = mdio_device_register(switch_mdiodev);
+	if (ret)
+		mdio_device_free(switch_mdiodev);
+out:
+	put_device(&bus->dev);
+	return ret;
+}
+
+static int __init dsa_loop_init(void)
+{
+	unsigned int i;
+	int ret;
+
+	ret = dsa_loop_create_switch_mdiodev();
+	if (ret)
+		return ret;
 
 	for (i = 0; i < NUM_FIXED_PHYS; i++)
-		phydevs[i] = fixed_phy_register(PHY_POLL, &status, NULL);
+		phydevs[i] = fixed_phy_register_100fd();
 
 	ret = mdio_driver_register(&dsa_loop_drv);
-	if (ret)
+	if (ret) {
 		dsa_loop_phydevs_unregister();
+		mdio_device_remove(switch_mdiodev);
+		mdio_device_free(switch_mdiodev);
+	}
 
 	return ret;
 }
@@ -419,10 +466,11 @@ static void __exit dsa_loop_exit(void)
 {
 	mdio_driver_unregister(&dsa_loop_drv);
 	dsa_loop_phydevs_unregister();
+	mdio_device_remove(switch_mdiodev);
+	mdio_device_free(switch_mdiodev);
 }
 module_exit(dsa_loop_exit);
 
-MODULE_SOFTDEP("pre: dsa_loop_bdinfo");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Florian Fainelli");
 MODULE_DESCRIPTION("DSA loopback driver");
diff --git a/drivers/net/dsa/dsa_loop.h b/drivers/net/dsa/dsa_loop.h
deleted file mode 100644
index 93e5c15d0efd..000000000000
--- a/drivers/net/dsa/dsa_loop.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __DSA_LOOP_H
-#define __DSA_LOOP_H
-
-struct dsa_chip_data;
-
-struct dsa_loop_pdata {
-	/* Must be first, such that dsa_register_switch() can access this
-	 * without gory pointer manipulations
-	 */
-	struct dsa_chip_data cd;
-	const char *name;
-	unsigned int enabled_ports;
-	const char *netdev;
-};
-
-#define DSA_LOOP_NUM_PORTS	6
-#define DSA_LOOP_CPU_PORT	(DSA_LOOP_NUM_PORTS - 1)
-
-#endif /* __DSA_LOOP_H */
diff --git a/drivers/net/dsa/dsa_loop_bdinfo.c b/drivers/net/dsa/dsa_loop_bdinfo.c
deleted file mode 100644
index 14ca42491512..000000000000
--- a/drivers/net/dsa/dsa_loop_bdinfo.c
+++ /dev/null
@@ -1,36 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/phy.h>
-#include <net/dsa.h>
-
-#include "dsa_loop.h"
-
-static struct dsa_loop_pdata dsa_loop_pdata = {
-	.cd = {
-		.port_names[0] = "lan1",
-		.port_names[1] = "lan2",
-		.port_names[2] = "lan3",
-		.port_names[3] = "lan4",
-		.port_names[DSA_LOOP_CPU_PORT] = "cpu",
-	},
-	.name = "DSA mockup driver",
-	.enabled_ports = 0x1f,
-	.netdev = "eth0",
-};
-
-static const struct mdio_board_info bdinfo = {
-	.bus_id	= "fixed-0",
-	.modalias = "dsa-loop",
-	.mdio_addr = 31,
-	.platform_data = &dsa_loop_pdata,
-};
-
-static int __init dsa_loop_bdinfo_init(void)
-{
-	return mdiobus_register_board_info(&bdinfo, 1);
-}
-arch_initcall(dsa_loop_bdinfo_init)
-
-MODULE_DESCRIPTION("DSA mock-up switch driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c
index 283ec5a6e23c..dd5f263ab984 100644
--- a/drivers/net/dsa/hirschmann/hellcreek.c
+++ b/drivers/net/dsa/hirschmann/hellcreek.c
@@ -1061,7 +1061,7 @@ static void hellcreek_setup_tc_identity_mapping(struct hellcreek *hellcreek)
 
 static int hellcreek_setup_fdb(struct hellcreek *hellcreek)
 {
-	static struct hellcreek_fdb_entry l2_ptp = {
+	static const struct hellcreek_fdb_entry l2_ptp = {
 		/* MAC: 01-1B-19-00-00-00 */
 		.mac	      = { 0x01, 0x1b, 0x19, 0x00, 0x00, 0x00 },
 		.portmask     = 0x03,	/* Management ports */
@@ -1072,7 +1072,7 @@ static int hellcreek_setup_fdb(struct hellcreek *hellcreek)
 		.reprio_tc    = 6,	/* TC: 6 as per IEEE 802.1AS */
 		.reprio_en    = 1,
 	};
-	static struct hellcreek_fdb_entry udp4_ptp = {
+	static const struct hellcreek_fdb_entry udp4_ptp = {
 		/* MAC: 01-00-5E-00-01-81 */
 		.mac	      = { 0x01, 0x00, 0x5e, 0x00, 0x01, 0x81 },
 		.portmask     = 0x03,	/* Management ports */
@@ -1083,7 +1083,7 @@ static int hellcreek_setup_fdb(struct hellcreek *hellcreek)
 		.reprio_tc    = 6,
 		.reprio_en    = 1,
 	};
-	static struct hellcreek_fdb_entry udp6_ptp = {
+	static const struct hellcreek_fdb_entry udp6_ptp = {
 		/* MAC: 33-33-00-00-01-81 */
 		.mac	      = { 0x33, 0x33, 0x00, 0x00, 0x01, 0x81 },
 		.portmask     = 0x03,	/* Management ports */
@@ -1094,7 +1094,7 @@ static int hellcreek_setup_fdb(struct hellcreek *hellcreek)
 		.reprio_tc    = 6,
 		.reprio_en    = 1,
 	};
-	static struct hellcreek_fdb_entry l2_p2p = {
+	static const struct hellcreek_fdb_entry l2_p2p = {
 		/* MAC: 01-80-C2-00-00-0E */
 		.mac	      = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x0e },
 		.portmask     = 0x03,	/* Management ports */
@@ -1105,7 +1105,7 @@ static int hellcreek_setup_fdb(struct hellcreek *hellcreek)
 		.reprio_tc    = 6,	/* TC: 6 as per IEEE 802.1AS */
 		.reprio_en    = 1,
 	};
-	static struct hellcreek_fdb_entry udp4_p2p = {
+	static const struct hellcreek_fdb_entry udp4_p2p = {
 		/* MAC: 01-00-5E-00-00-6B */
 		.mac	      = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x6b },
 		.portmask     = 0x03,	/* Management ports */
@@ -1116,7 +1116,7 @@ static int hellcreek_setup_fdb(struct hellcreek *hellcreek)
 		.reprio_tc    = 6,
 		.reprio_en    = 1,
 	};
-	static struct hellcreek_fdb_entry udp6_p2p = {
+	static const struct hellcreek_fdb_entry udp6_p2p = {
 		/* MAC: 33-33-00-00-00-6B */
 		.mac	      = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x6b },
 		.portmask     = 0x03,	/* Management ports */
@@ -1127,7 +1127,7 @@ static int hellcreek_setup_fdb(struct hellcreek *hellcreek)
 		.reprio_tc    = 6,
 		.reprio_en    = 1,
 	};
-	static struct hellcreek_fdb_entry stp = {
+	static const struct hellcreek_fdb_entry stp = {
 		/* MAC: 01-80-C2-00-00-00 */
 		.mac	      = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 },
 		.portmask     = 0x03,	/* Management ports */
@@ -1320,13 +1320,13 @@ static int hellcreek_devlink_region_fdb_snapshot(struct devlink *dl,
 	return 0;
 }
 
-static struct devlink_region_ops hellcreek_region_vlan_ops = {
+static const struct devlink_region_ops hellcreek_region_vlan_ops = {
 	.name	    = "vlan",
 	.snapshot   = hellcreek_devlink_region_vlan_snapshot,
 	.destructor = kfree,
 };
 
-static struct devlink_region_ops hellcreek_region_fdb_ops = {
+static const struct devlink_region_ops hellcreek_region_fdb_ops = {
 	.name	    = "fdb",
 	.snapshot   = hellcreek_devlink_region_fdb_snapshot,
 	.destructor = kfree,
@@ -1335,7 +1335,7 @@ static struct devlink_region_ops hellcreek_region_fdb_ops = {
 static int hellcreek_setup_devlink_regions(struct dsa_switch *ds)
 {
 	struct hellcreek *hellcreek = ds->priv;
-	struct devlink_region_ops *ops;
+	const struct devlink_region_ops *ops;
 	struct devlink_region *region;
 	u64 size;
 	int ret;
@@ -1926,6 +1926,8 @@ static const struct dsa_switch_ops hellcreek_ds_ops = {
 	.port_vlan_filtering   = hellcreek_vlan_filtering,
 	.setup		       = hellcreek_setup,
 	.teardown	       = hellcreek_teardown,
+	.port_hsr_join	       = dsa_port_simple_hsr_join,
+	.port_hsr_leave	       = dsa_port_simple_hsr_leave,
 };
 
 static int hellcreek_probe(struct platform_device *pdev)
diff --git a/drivers/net/dsa/hirschmann/hellcreek.h b/drivers/net/dsa/hirschmann/hellcreek.h
index 9c2ed2ba79da..bebf0d3ff330 100644
--- a/drivers/net/dsa/hirschmann/hellcreek.h
+++ b/drivers/net/dsa/hirschmann/hellcreek.h
@@ -244,7 +244,7 @@ struct hellcreek_port_hwtstamp {
 	struct sk_buff *tx_skb;
 
 	/* Current timestamp configuration */
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 };
 
 struct hellcreek_port {
diff --git a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c
index ca2500aba96f..99941ff1ebf9 100644
--- a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c
+++ b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c
@@ -40,7 +40,7 @@ int hellcreek_get_ts_info(struct dsa_switch *ds, int port,
  * the user requested what is actually available or not
  */
 static int hellcreek_set_hwtstamp_config(struct hellcreek *hellcreek, int port,
-					 struct hwtstamp_config *config)
+					 struct kernel_hwtstamp_config *config)
 {
 	struct hellcreek_port_hwtstamp *ps =
 		&hellcreek->ports[port].port_hwtstamp;
@@ -110,41 +110,35 @@ static int hellcreek_set_hwtstamp_config(struct hellcreek *hellcreek, int port,
 }
 
 int hellcreek_port_hwtstamp_set(struct dsa_switch *ds, int port,
-				struct ifreq *ifr)
+				struct kernel_hwtstamp_config *config,
+				struct netlink_ext_ack *extack)
 {
 	struct hellcreek *hellcreek = ds->priv;
 	struct hellcreek_port_hwtstamp *ps;
-	struct hwtstamp_config config;
 	int err;
 
 	ps = &hellcreek->ports[port].port_hwtstamp;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	err = hellcreek_set_hwtstamp_config(hellcreek, port, &config);
+	err = hellcreek_set_hwtstamp_config(hellcreek, port, config);
 	if (err)
 		return err;
 
 	/* Save the chosen configuration to be returned later */
-	memcpy(&ps->tstamp_config, &config, sizeof(config));
+	ps->tstamp_config = *config;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 int hellcreek_port_hwtstamp_get(struct dsa_switch *ds, int port,
-				struct ifreq *ifr)
+				struct kernel_hwtstamp_config *config)
 {
 	struct hellcreek *hellcreek = ds->priv;
 	struct hellcreek_port_hwtstamp *ps;
-	struct hwtstamp_config *config;
 
 	ps = &hellcreek->ports[port].port_hwtstamp;
-	config = &ps->tstamp_config;
+	*config = ps->tstamp_config;
 
-	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 /* Returns a pointer to the PTP header if the caller should time stamp, or NULL
diff --git a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.h b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.h
index 7d88da2134f2..388821c4aa10 100644
--- a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.h
+++ b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.h
@@ -38,9 +38,10 @@
 #define TX_TSTAMP_TIMEOUT	msecs_to_jiffies(40)
 
 int hellcreek_port_hwtstamp_set(struct dsa_switch *ds, int port,
-				struct ifreq *ifr);
+				struct kernel_hwtstamp_config *config,
+				struct netlink_ext_ack *extack);
 int hellcreek_port_hwtstamp_get(struct dsa_switch *ds, int port,
-				struct ifreq *ifr);
+				struct kernel_hwtstamp_config *config);
 
 bool hellcreek_port_rxtstamp(struct dsa_switch *ds, int port,
 			     struct sk_buff *clone, unsigned int type);
diff --git a/drivers/net/dsa/hirschmann/hellcreek_ptp.c b/drivers/net/dsa/hirschmann/hellcreek_ptp.c
index bfe21f9f7dcd..cb23bea9c21b 100644
--- a/drivers/net/dsa/hirschmann/hellcreek_ptp.c
+++ b/drivers/net/dsa/hirschmann/hellcreek_ptp.c
@@ -376,8 +376,18 @@ static int hellcreek_led_setup(struct hellcreek *hellcreek)
 		hellcreek_set_brightness(hellcreek, STATUS_OUT_IS_GM, 1);
 
 	/* Register both leds */
-	led_classdev_register(hellcreek->dev, &hellcreek->led_sync_good);
-	led_classdev_register(hellcreek->dev, &hellcreek->led_is_gm);
+	ret = led_classdev_register(hellcreek->dev, &hellcreek->led_sync_good);
+	if (ret) {
+		dev_err(hellcreek->dev, "Failed to register sync_good LED\n");
+		goto out;
+	}
+
+	ret = led_classdev_register(hellcreek->dev, &hellcreek->led_is_gm);
+	if (ret) {
+		dev_err(hellcreek->dev, "Failed to register is_gm LED\n");
+		led_classdev_unregister(&hellcreek->led_sync_good);
+		goto out;
+	}
 
 	ret = 0;
 
diff --git a/drivers/net/dsa/ks8995.c b/drivers/net/dsa/ks8995.c
new file mode 100644
index 000000000000..77d8b842693c
--- /dev/null
+++ b/drivers/net/dsa/ks8995.c
@@ -0,0 +1,857 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SPI driver for Micrel/Kendin KS8995M and KSZ8864RMN ethernet switches
+ *
+ * Copyright (C) 2008 Gabor Juhos <juhosg at openwrt.org>
+ * Copyright (C) 2025 Linus Walleij <linus.walleij@linaro.org>
+ *
+ * This file was based on: drivers/spi/at25.c
+ *     Copyright (C) 2006 David Brownell
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/bits.h>
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/gpio/consumer.h>
+#include <linux/of.h>
+#include <linux/spi/spi.h>
+#include <net/dsa.h>
+
+#define DRV_VERSION		"0.1.1"
+#define DRV_DESC		"Micrel KS8995 Ethernet switch SPI driver"
+
+/* ------------------------------------------------------------------------ */
+
+#define KS8995_REG_ID0		0x00    /* Chip ID0 */
+#define KS8995_REG_ID1		0x01    /* Chip ID1 */
+
+#define KS8995_REG_GC0		0x02    /* Global Control 0 */
+
+#define KS8995_GC0_P5_PHY	BIT(3)	/* Port 5 PHY enabled */
+
+#define KS8995_REG_GC1		0x03    /* Global Control 1 */
+#define KS8995_REG_GC2		0x04    /* Global Control 2 */
+
+#define KS8995_GC2_HUGE		BIT(2)	/* Huge packet support */
+#define KS8995_GC2_LEGAL	BIT(1)	/* Legal size override */
+
+#define KS8995_REG_GC3		0x05    /* Global Control 3 */
+#define KS8995_REG_GC4		0x06    /* Global Control 4 */
+
+#define KS8995_GC4_10BT		BIT(4)	/* Force switch to 10Mbit */
+#define KS8995_GC4_MII_FLOW	BIT(5)	/* MII full-duplex flow control enable */
+#define KS8995_GC4_MII_HD	BIT(6)	/* MII half-duplex mode enable */
+
+#define KS8995_REG_GC5		0x07    /* Global Control 5 */
+#define KS8995_REG_GC6		0x08    /* Global Control 6 */
+#define KS8995_REG_GC7		0x09    /* Global Control 7 */
+#define KS8995_REG_GC8		0x0a    /* Global Control 8 */
+#define KS8995_REG_GC9		0x0b    /* Global Control 9 */
+
+#define KS8995_GC9_SPECIAL	BIT(0)	/* Special tagging mode (DSA) */
+
+/* In DSA the ports 1-4 are numbered 0-3 and the CPU port is port 4 */
+#define KS8995_REG_PC(p, r)	(0x10 + (0x10 * (p)) + (r)) /* Port Control */
+#define KS8995_REG_PS(p, r)	(0x1e + (0x10 * (p)) + (r)) /* Port Status */
+
+#define KS8995_REG_PC0		0x00    /* Port Control 0 */
+#define KS8995_REG_PC1		0x01    /* Port Control 1 */
+#define KS8995_REG_PC2		0x02    /* Port Control 2 */
+#define KS8995_REG_PC3		0x03    /* Port Control 3 */
+#define KS8995_REG_PC4		0x04    /* Port Control 4 */
+#define KS8995_REG_PC5		0x05    /* Port Control 5 */
+#define KS8995_REG_PC6		0x06    /* Port Control 6 */
+#define KS8995_REG_PC7		0x07    /* Port Control 7 */
+#define KS8995_REG_PC8		0x08    /* Port Control 8 */
+#define KS8995_REG_PC9		0x09    /* Port Control 9 */
+#define KS8995_REG_PC10		0x0a    /* Port Control 10 */
+#define KS8995_REG_PC11		0x0b    /* Port Control 11 */
+#define KS8995_REG_PC12		0x0c    /* Port Control 12 */
+#define KS8995_REG_PC13		0x0d    /* Port Control 13 */
+
+#define KS8995_PC0_TAG_INS	BIT(2)	/* Enable tag insertion on port */
+#define KS8995_PC0_TAG_REM	BIT(1)	/* Enable tag removal on port */
+#define KS8995_PC0_PRIO_EN	BIT(0)	/* Enable priority handling */
+
+#define KS8995_PC2_TXEN		BIT(2)	/* Enable TX on port */
+#define KS8995_PC2_RXEN		BIT(1)	/* Enable RX on port */
+#define KS8995_PC2_LEARN_DIS	BIT(0)	/* Disable learning on port */
+
+#define KS8995_PC13_TXDIS	BIT(6)	/* Disable transmitter */
+#define KS8995_PC13_PWDN	BIT(3)	/* Power down */
+
+#define KS8995_REG_TPC0		0x60    /* TOS Priority Control 0 */
+#define KS8995_REG_TPC1		0x61    /* TOS Priority Control 1 */
+#define KS8995_REG_TPC2		0x62    /* TOS Priority Control 2 */
+#define KS8995_REG_TPC3		0x63    /* TOS Priority Control 3 */
+#define KS8995_REG_TPC4		0x64    /* TOS Priority Control 4 */
+#define KS8995_REG_TPC5		0x65    /* TOS Priority Control 5 */
+#define KS8995_REG_TPC6		0x66    /* TOS Priority Control 6 */
+#define KS8995_REG_TPC7		0x67    /* TOS Priority Control 7 */
+
+#define KS8995_REG_MAC0		0x68    /* MAC address 0 */
+#define KS8995_REG_MAC1		0x69    /* MAC address 1 */
+#define KS8995_REG_MAC2		0x6a    /* MAC address 2 */
+#define KS8995_REG_MAC3		0x6b    /* MAC address 3 */
+#define KS8995_REG_MAC4		0x6c    /* MAC address 4 */
+#define KS8995_REG_MAC5		0x6d    /* MAC address 5 */
+
+#define KS8995_REG_IAC0		0x6e    /* Indirect Access Control 0 */
+#define KS8995_REG_IAC1		0x6f    /* Indirect Access Control 0 */
+#define KS8995_REG_IAD7		0x70    /* Indirect Access Data 7 */
+#define KS8995_REG_IAD6		0x71    /* Indirect Access Data 6 */
+#define KS8995_REG_IAD5		0x72    /* Indirect Access Data 5 */
+#define KS8995_REG_IAD4		0x73    /* Indirect Access Data 4 */
+#define KS8995_REG_IAD3		0x74    /* Indirect Access Data 3 */
+#define KS8995_REG_IAD2		0x75    /* Indirect Access Data 2 */
+#define KS8995_REG_IAD1		0x76    /* Indirect Access Data 1 */
+#define KS8995_REG_IAD0		0x77    /* Indirect Access Data 0 */
+
+#define KSZ8864_REG_ID1		0xfe	/* Chip ID in bit 7 */
+
+#define KS8995_REGS_SIZE	0x80
+#define KSZ8864_REGS_SIZE	0x100
+#define KSZ8795_REGS_SIZE	0x100
+
+#define ID1_CHIPID_M		0xf
+#define ID1_CHIPID_S		4
+#define ID1_REVISION_M		0x7
+#define ID1_REVISION_S		1
+#define ID1_START_SW		1	/* start the switch */
+
+#define FAMILY_KS8995		0x95
+#define FAMILY_KSZ8795		0x87
+#define CHIPID_M		0
+#define KS8995_CHIP_ID		0x00
+#define KSZ8864_CHIP_ID		0x01
+#define KSZ8795_CHIP_ID		0x09
+
+#define KS8995_CMD_WRITE	0x02U
+#define KS8995_CMD_READ		0x03U
+
+#define KS8995_CPU_PORT		4
+#define KS8995_NUM_PORTS	5 /* 5 ports including the CPU port */
+#define KS8995_RESET_DELAY	10 /* usec */
+
+enum ks8995_chip_variant {
+	ks8995,
+	ksz8864,
+	ksz8795,
+	max_variant
+};
+
+struct ks8995_chip_params {
+	char *name;
+	int family_id;
+	int chip_id;
+	int regs_size;
+	int addr_width;
+	int addr_shift;
+};
+
+static const struct ks8995_chip_params ks8995_chip[] = {
+	[ks8995] = {
+		.name = "KS8995MA",
+		.family_id = FAMILY_KS8995,
+		.chip_id = KS8995_CHIP_ID,
+		.regs_size = KS8995_REGS_SIZE,
+		.addr_width = 8,
+		.addr_shift = 0,
+	},
+	[ksz8864] = {
+		.name = "KSZ8864RMN",
+		.family_id = FAMILY_KS8995,
+		.chip_id = KSZ8864_CHIP_ID,
+		.regs_size = KSZ8864_REGS_SIZE,
+		.addr_width = 8,
+		.addr_shift = 0,
+	},
+	[ksz8795] = {
+		.name = "KSZ8795CLX",
+		.family_id = FAMILY_KSZ8795,
+		.chip_id = KSZ8795_CHIP_ID,
+		.regs_size = KSZ8795_REGS_SIZE,
+		.addr_width = 12,
+		.addr_shift = 1,
+	},
+};
+
+struct ks8995_switch {
+	struct spi_device	*spi;
+	struct device		*dev;
+	struct dsa_switch	*ds;
+	struct mutex		lock;
+	struct gpio_desc	*reset_gpio;
+	struct bin_attribute	regs_attr;
+	const struct ks8995_chip_params	*chip;
+	int			revision_id;
+	unsigned int max_mtu[KS8995_NUM_PORTS];
+};
+
+static const struct spi_device_id ks8995_id[] = {
+	{"ks8995", ks8995},
+	{"ksz8864", ksz8864},
+	{"ksz8795", ksz8795},
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, ks8995_id);
+
+static const struct of_device_id ks8995_spi_of_match[] = {
+	{ .compatible = "micrel,ks8995" },
+	{ .compatible = "micrel,ksz8864" },
+	{ .compatible = "micrel,ksz8795" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ks8995_spi_of_match);
+
+static inline u8 get_chip_id(u8 val)
+{
+	return (val >> ID1_CHIPID_S) & ID1_CHIPID_M;
+}
+
+static inline u8 get_chip_rev(u8 val)
+{
+	return (val >> ID1_REVISION_S) & ID1_REVISION_M;
+}
+
+/* create_spi_cmd - create a chip specific SPI command header
+ * @ks: pointer to switch instance
+ * @cmd: SPI command for switch
+ * @address: register address for command
+ *
+ * Different chip families use different bit pattern to address the switches
+ * registers:
+ *
+ * KS8995: 8bit command + 8bit address
+ * KSZ8795: 3bit command + 12bit address + 1bit TR (?)
+ */
+static inline __be16 create_spi_cmd(struct ks8995_switch *ks, int cmd,
+				    unsigned address)
+{
+	u16 result = cmd;
+
+	/* make room for address (incl. address shift) */
+	result <<= ks->chip->addr_width + ks->chip->addr_shift;
+	/* add address */
+	result |= address << ks->chip->addr_shift;
+	/* SPI protocol needs big endian */
+	return cpu_to_be16(result);
+}
+/* ------------------------------------------------------------------------ */
+static int ks8995_read(struct ks8995_switch *ks, char *buf,
+		 unsigned offset, size_t count)
+{
+	__be16 cmd;
+	struct spi_transfer t[2];
+	struct spi_message m;
+	int err;
+
+	cmd = create_spi_cmd(ks, KS8995_CMD_READ, offset);
+	spi_message_init(&m);
+
+	memset(&t, 0, sizeof(t));
+
+	t[0].tx_buf = &cmd;
+	t[0].len = sizeof(cmd);
+	spi_message_add_tail(&t[0], &m);
+
+	t[1].rx_buf = buf;
+	t[1].len = count;
+	spi_message_add_tail(&t[1], &m);
+
+	mutex_lock(&ks->lock);
+	err = spi_sync(ks->spi, &m);
+	mutex_unlock(&ks->lock);
+
+	return err ? err : count;
+}
+
+static int ks8995_write(struct ks8995_switch *ks, char *buf,
+		 unsigned offset, size_t count)
+{
+	__be16 cmd;
+	struct spi_transfer t[2];
+	struct spi_message m;
+	int err;
+
+	cmd = create_spi_cmd(ks, KS8995_CMD_WRITE, offset);
+	spi_message_init(&m);
+
+	memset(&t, 0, sizeof(t));
+
+	t[0].tx_buf = &cmd;
+	t[0].len = sizeof(cmd);
+	spi_message_add_tail(&t[0], &m);
+
+	t[1].tx_buf = buf;
+	t[1].len = count;
+	spi_message_add_tail(&t[1], &m);
+
+	mutex_lock(&ks->lock);
+	err = spi_sync(ks->spi, &m);
+	mutex_unlock(&ks->lock);
+
+	return err ? err : count;
+}
+
+static inline int ks8995_read_reg(struct ks8995_switch *ks, u8 addr, u8 *buf)
+{
+	return ks8995_read(ks, buf, addr, 1) != 1;
+}
+
+static inline int ks8995_write_reg(struct ks8995_switch *ks, u8 addr, u8 val)
+{
+	char buf = val;
+
+	return ks8995_write(ks, &buf, addr, 1) != 1;
+}
+
+/* ------------------------------------------------------------------------ */
+
+static int ks8995_stop(struct ks8995_switch *ks)
+{
+	return ks8995_write_reg(ks, KS8995_REG_ID1, 0);
+}
+
+static int ks8995_start(struct ks8995_switch *ks)
+{
+	return ks8995_write_reg(ks, KS8995_REG_ID1, 1);
+}
+
+static int ks8995_reset(struct ks8995_switch *ks)
+{
+	int err;
+
+	err = ks8995_stop(ks);
+	if (err)
+		return err;
+
+	udelay(KS8995_RESET_DELAY);
+
+	return ks8995_start(ks);
+}
+
+/* ks8995_get_revision - get chip revision
+ * @ks: pointer to switch instance
+ *
+ * Verify chip family and id and get chip revision.
+ */
+static int ks8995_get_revision(struct ks8995_switch *ks)
+{
+	int err;
+	u8 id0, id1, ksz8864_id;
+
+	/* read family id */
+	err = ks8995_read_reg(ks, KS8995_REG_ID0, &id0);
+	if (err) {
+		err = -EIO;
+		goto err_out;
+	}
+
+	/* verify family id */
+	if (id0 != ks->chip->family_id) {
+		dev_err(&ks->spi->dev, "chip family id mismatch: expected 0x%02x but 0x%02x read\n",
+			ks->chip->family_id, id0);
+		err = -ENODEV;
+		goto err_out;
+	}
+
+	switch (ks->chip->family_id) {
+	case FAMILY_KS8995:
+		/* try reading chip id at CHIP ID1 */
+		err = ks8995_read_reg(ks, KS8995_REG_ID1, &id1);
+		if (err) {
+			err = -EIO;
+			goto err_out;
+		}
+
+		/* verify chip id */
+		if ((get_chip_id(id1) == CHIPID_M) &&
+		    (get_chip_id(id1) == ks->chip->chip_id)) {
+			/* KS8995MA */
+			ks->revision_id = get_chip_rev(id1);
+		} else if (get_chip_id(id1) != CHIPID_M) {
+			/* KSZ8864RMN */
+			err = ks8995_read_reg(ks, KS8995_REG_ID1, &ksz8864_id);
+			if (err) {
+				err = -EIO;
+				goto err_out;
+			}
+
+			if ((ksz8864_id & 0x80) &&
+			    (ks->chip->chip_id == KSZ8864_CHIP_ID)) {
+				ks->revision_id = get_chip_rev(id1);
+			}
+
+		} else {
+			dev_err(&ks->spi->dev, "unsupported chip id for KS8995 family: 0x%02x\n",
+				id1);
+			err = -ENODEV;
+		}
+		break;
+	case FAMILY_KSZ8795:
+		/* try reading chip id at CHIP ID1 */
+		err = ks8995_read_reg(ks, KS8995_REG_ID1, &id1);
+		if (err) {
+			err = -EIO;
+			goto err_out;
+		}
+
+		if (get_chip_id(id1) == ks->chip->chip_id) {
+			ks->revision_id = get_chip_rev(id1);
+		} else {
+			dev_err(&ks->spi->dev, "unsupported chip id for KSZ8795 family: 0x%02x\n",
+				id1);
+			err = -ENODEV;
+		}
+		break;
+	default:
+		dev_err(&ks->spi->dev, "unsupported family id: 0x%02x\n", id0);
+		err = -ENODEV;
+		break;
+	}
+err_out:
+	return err;
+}
+
+static int ks8995_check_config(struct ks8995_switch *ks)
+{
+	int ret;
+	u8 val;
+
+	ret = ks8995_read_reg(ks, KS8995_REG_GC0, &val);
+	if (ret) {
+		dev_err(ks->dev, "failed to read KS8995_REG_GC0\n");
+		return ret;
+	}
+
+	dev_dbg(ks->dev, "port 5 PHY %senabled\n",
+		(val & KS8995_GC0_P5_PHY) ? "" : "not ");
+
+	val |= KS8995_GC0_P5_PHY;
+	ret = ks8995_write_reg(ks, KS8995_REG_GC0, val);
+	if (ret)
+		dev_err(ks->dev, "failed to set KS8995_REG_GC0\n");
+
+	dev_dbg(ks->dev, "set KS8995_REG_GC0 to 0x%02x\n", val);
+
+	return 0;
+}
+
+static void
+ks8995_mac_config(struct phylink_config *config, unsigned int mode,
+		  const struct phylink_link_state *state)
+{
+}
+
+static void
+ks8995_mac_link_up(struct phylink_config *config, struct phy_device *phydev,
+		   unsigned int mode, phy_interface_t interface,
+		   int speed, int duplex, bool tx_pause, bool rx_pause)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct ks8995_switch *ks = dp->ds->priv;
+	int port = dp->index;
+	int ret;
+	u8 val;
+
+	/* Allow forcing the mode on the fixed CPU port, no autonegotiation.
+	 * We assume autonegotiation works on the PHY-facing ports.
+	 */
+	if (port != KS8995_CPU_PORT)
+		return;
+
+	dev_dbg(ks->dev, "MAC link up on CPU port (%d)\n", port);
+
+	ret = ks8995_read_reg(ks, KS8995_REG_GC4, &val);
+	if (ret) {
+		dev_err(ks->dev, "failed to read KS8995_REG_GC4\n");
+		return;
+	}
+
+	/* Conjure port config */
+	switch (speed) {
+	case SPEED_10:
+		dev_dbg(ks->dev, "set switch MII to 100Mbit mode\n");
+		val |= KS8995_GC4_10BT;
+		break;
+	case SPEED_100:
+	default:
+		dev_dbg(ks->dev, "set switch MII to 100Mbit mode\n");
+		val &= ~KS8995_GC4_10BT;
+		break;
+	}
+
+	if (duplex == DUPLEX_HALF) {
+		dev_dbg(ks->dev, "set switch MII to half duplex\n");
+		val |= KS8995_GC4_MII_HD;
+	} else {
+		dev_dbg(ks->dev, "set switch MII to full duplex\n");
+		val &= ~KS8995_GC4_MII_HD;
+	}
+
+	dev_dbg(ks->dev, "set KS8995_REG_GC4 to %02x\n", val);
+
+	/* Enable the CPU port */
+	ret = ks8995_write_reg(ks, KS8995_REG_GC4, val);
+	if (ret)
+		dev_err(ks->dev, "failed to set KS8995_REG_GC4\n");
+}
+
+static void
+ks8995_mac_link_down(struct phylink_config *config, unsigned int mode,
+		     phy_interface_t interface)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct ks8995_switch *ks = dp->ds->priv;
+	int port = dp->index;
+
+	if (port != KS8995_CPU_PORT)
+		return;
+
+	dev_dbg(ks->dev, "MAC link down on CPU port (%d)\n", port);
+
+	/* Disable the CPU port */
+}
+
+static const struct phylink_mac_ops ks8995_phylink_mac_ops = {
+	.mac_config = ks8995_mac_config,
+	.mac_link_up = ks8995_mac_link_up,
+	.mac_link_down = ks8995_mac_link_down,
+};
+
+static enum
+dsa_tag_protocol ks8995_get_tag_protocol(struct dsa_switch *ds,
+					 int port,
+					 enum dsa_tag_protocol mp)
+{
+	/* This switch actually uses the 6 byte KS8995 protocol */
+	return DSA_TAG_PROTO_NONE;
+}
+
+static int ks8995_setup(struct dsa_switch *ds)
+{
+	return 0;
+}
+
+static int ks8995_port_enable(struct dsa_switch *ds, int port,
+			      struct phy_device *phy)
+{
+	struct ks8995_switch *ks = ds->priv;
+
+	dev_dbg(ks->dev, "enable port %d\n", port);
+
+	return 0;
+}
+
+static void ks8995_port_disable(struct dsa_switch *ds, int port)
+{
+	struct ks8995_switch *ks = ds->priv;
+
+	dev_dbg(ks->dev, "disable port %d\n", port);
+}
+
+static int ks8995_port_pre_bridge_flags(struct dsa_switch *ds, int port,
+					struct switchdev_brport_flags flags,
+					struct netlink_ext_ack *extack)
+{
+	/* We support enabling/disabling learning */
+	if (flags.mask & ~(BR_LEARNING))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int ks8995_port_bridge_flags(struct dsa_switch *ds, int port,
+				    struct switchdev_brport_flags flags,
+				    struct netlink_ext_ack *extack)
+{
+	struct ks8995_switch *ks = ds->priv;
+	int ret;
+	u8 val;
+
+	if (flags.mask & BR_LEARNING) {
+		ret = ks8995_read_reg(ks, KS8995_REG_PC(port, KS8995_REG_PC2), &val);
+		if (ret) {
+			dev_err(ks->dev, "failed to read KS8995_REG_PC2 on port %d\n", port);
+			return ret;
+		}
+
+		if (flags.val & BR_LEARNING)
+			val &= ~KS8995_PC2_LEARN_DIS;
+		else
+			val |= KS8995_PC2_LEARN_DIS;
+
+		ret = ks8995_write_reg(ks, KS8995_REG_PC(port, KS8995_REG_PC2), val);
+		if (ret) {
+			dev_err(ks->dev, "failed to write KS8995_REG_PC2 on port %d\n", port);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void ks8995_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
+{
+	struct ks8995_switch *ks = ds->priv;
+	int ret;
+	u8 val;
+
+	ret = ks8995_read_reg(ks, KS8995_REG_PC(port, KS8995_REG_PC2), &val);
+	if (ret) {
+		dev_err(ks->dev, "failed to read KS8995_REG_PC2 on port %d\n", port);
+		return;
+	}
+
+	/* Set the bits for the different STP states in accordance with
+	 * the datasheet, pages 36-37 "Spanning tree support".
+	 */
+	switch (state) {
+	case BR_STATE_DISABLED:
+	case BR_STATE_BLOCKING:
+	case BR_STATE_LISTENING:
+		val &= ~KS8995_PC2_TXEN;
+		val &= ~KS8995_PC2_RXEN;
+		val |= KS8995_PC2_LEARN_DIS;
+		break;
+	case BR_STATE_LEARNING:
+		val &= ~KS8995_PC2_TXEN;
+		val &= ~KS8995_PC2_RXEN;
+		val &= ~KS8995_PC2_LEARN_DIS;
+		break;
+	case BR_STATE_FORWARDING:
+		val |= KS8995_PC2_TXEN;
+		val |= KS8995_PC2_RXEN;
+		val &= ~KS8995_PC2_LEARN_DIS;
+		break;
+	default:
+		dev_err(ks->dev, "unknown bridge state requested\n");
+		return;
+	}
+
+	ret = ks8995_write_reg(ks, KS8995_REG_PC(port, KS8995_REG_PC2), val);
+	if (ret) {
+		dev_err(ks->dev, "failed to write KS8995_REG_PC2 on port %d\n", port);
+		return;
+	}
+
+	dev_dbg(ks->dev, "set KS8995_REG_PC2 for port %d to %02x\n", port, val);
+}
+
+static void ks8995_phylink_get_caps(struct dsa_switch *dsa, int port,
+				    struct phylink_config *config)
+{
+	unsigned long *interfaces = config->supported_interfaces;
+
+	if (port == KS8995_CPU_PORT)
+		__set_bit(PHY_INTERFACE_MODE_MII, interfaces);
+
+	if (port <= 3) {
+		/* Internal PHYs */
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL, interfaces);
+		/* phylib default */
+		__set_bit(PHY_INTERFACE_MODE_MII, interfaces);
+	}
+
+	config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100;
+}
+
+/* Huge packet support up to 1916 byte packages "inclusive"
+ * which means that tags are included. If the bit is not set
+ * it is 1536 bytes "inclusive". We present the length without
+ * tags or ethernet headers. The setting affects all ports.
+ */
+static int ks8995_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
+{
+	struct ks8995_switch *ks = ds->priv;
+	unsigned int max_mtu;
+	int ret;
+	u8 val;
+	int i;
+
+	ks->max_mtu[port] = new_mtu;
+
+	/* Roof out the MTU for the entire switch to the greatest
+	 * common denominator: the biggest set for any one port will
+	 * be the biggest MTU for the switch.
+	 */
+	max_mtu = ETH_DATA_LEN;
+	for (i = 0; i < KS8995_NUM_PORTS; i++) {
+		if (ks->max_mtu[i] > max_mtu)
+			max_mtu = ks->max_mtu[i];
+	}
+
+	/* Translate to layer 2 size.
+	 * Add ethernet and (possible) VLAN headers, and checksum to the size.
+	 * For ETH_DATA_LEN (1500 bytes) this will add up to 1522 bytes.
+	 */
+	max_mtu += VLAN_ETH_HLEN;
+	max_mtu += ETH_FCS_LEN;
+
+	ret = ks8995_read_reg(ks, KS8995_REG_GC2, &val);
+	if (ret) {
+		dev_err(ks->dev, "failed to read KS8995_REG_GC2\n");
+		return ret;
+	}
+
+	if (max_mtu <= 1522) {
+		val &= ~KS8995_GC2_HUGE;
+		val &= ~KS8995_GC2_LEGAL;
+	} else if (max_mtu > 1522 && max_mtu <= 1536) {
+		/* This accepts packets up to 1536 bytes */
+		val &= ~KS8995_GC2_HUGE;
+		val |= KS8995_GC2_LEGAL;
+	} else {
+		/* This accepts packets up to 1916 bytes */
+		val |= KS8995_GC2_HUGE;
+		val |= KS8995_GC2_LEGAL;
+	}
+
+	dev_dbg(ks->dev, "new max MTU %d bytes (inclusive)\n", max_mtu);
+
+	ret = ks8995_write_reg(ks, KS8995_REG_GC2, val);
+	if (ret)
+		dev_err(ks->dev, "failed to set KS8995_REG_GC2\n");
+
+	return ret;
+}
+
+static int ks8995_get_max_mtu(struct dsa_switch *ds, int port)
+{
+	return 1916 - ETH_HLEN - ETH_FCS_LEN;
+}
+
+static const struct dsa_switch_ops ks8995_ds_ops = {
+	.get_tag_protocol = ks8995_get_tag_protocol,
+	.setup = ks8995_setup,
+	.port_pre_bridge_flags = ks8995_port_pre_bridge_flags,
+	.port_bridge_flags = ks8995_port_bridge_flags,
+	.port_enable = ks8995_port_enable,
+	.port_disable = ks8995_port_disable,
+	.port_stp_state_set = ks8995_port_stp_state_set,
+	.port_change_mtu = ks8995_change_mtu,
+	.port_max_mtu = ks8995_get_max_mtu,
+	.phylink_get_caps = ks8995_phylink_get_caps,
+};
+
+/* ------------------------------------------------------------------------ */
+static int ks8995_probe(struct spi_device *spi)
+{
+	struct ks8995_switch *ks;
+	int err;
+	int variant = spi_get_device_id(spi)->driver_data;
+
+	if (variant >= max_variant) {
+		dev_err(&spi->dev, "bad chip variant %d\n", variant);
+		return -ENODEV;
+	}
+
+	ks = devm_kzalloc(&spi->dev, sizeof(*ks), GFP_KERNEL);
+	if (!ks)
+		return -ENOMEM;
+
+	mutex_init(&ks->lock);
+	ks->spi = spi;
+	ks->dev = &spi->dev;
+	ks->chip = &ks8995_chip[variant];
+
+	ks->reset_gpio = devm_gpiod_get_optional(&spi->dev, "reset",
+						 GPIOD_OUT_HIGH);
+	err = PTR_ERR_OR_ZERO(ks->reset_gpio);
+	if (err) {
+		dev_err(&spi->dev,
+			"failed to get reset gpio: %d\n", err);
+		return err;
+	}
+
+	err = gpiod_set_consumer_name(ks->reset_gpio, "switch-reset");
+	if (err)
+		return err;
+
+	if (ks->reset_gpio) {
+		/*
+		 * If a reset line was obtained, wait for 100us after
+		 * de-asserting RESET before accessing any registers, see
+		 * the KS8995MA datasheet, page 44.
+		 */
+		gpiod_set_value_cansleep(ks->reset_gpio, 0);
+		udelay(100);
+	}
+
+	spi_set_drvdata(spi, ks);
+
+	spi->mode = SPI_MODE_0;
+	spi->bits_per_word = 8;
+	err = spi_setup(spi);
+	if (err) {
+		dev_err(&spi->dev, "spi_setup failed, err=%d\n", err);
+		return err;
+	}
+
+	err = ks8995_get_revision(ks);
+	if (err)
+		return err;
+
+	err = ks8995_reset(ks);
+	if (err)
+		return err;
+
+	dev_info(&spi->dev, "%s device found, Chip ID:%x, Revision:%x\n",
+		 ks->chip->name, ks->chip->chip_id, ks->revision_id);
+
+	err = ks8995_check_config(ks);
+	if (err)
+		return err;
+
+	ks->ds = devm_kzalloc(&spi->dev, sizeof(*ks->ds), GFP_KERNEL);
+	if (!ks->ds)
+		return -ENOMEM;
+
+	ks->ds->dev = &spi->dev;
+	ks->ds->num_ports = KS8995_NUM_PORTS;
+	ks->ds->ops = &ks8995_ds_ops;
+	ks->ds->phylink_mac_ops = &ks8995_phylink_mac_ops;
+	ks->ds->priv = ks;
+
+	err = dsa_register_switch(ks->ds);
+	if (err)
+		return dev_err_probe(&spi->dev, err,
+				     "unable to register DSA switch\n");
+
+	return 0;
+}
+
+static void ks8995_remove(struct spi_device *spi)
+{
+	struct ks8995_switch *ks = spi_get_drvdata(spi);
+
+	dsa_unregister_switch(ks->ds);
+	/* assert reset */
+	gpiod_set_value_cansleep(ks->reset_gpio, 1);
+}
+
+/* ------------------------------------------------------------------------ */
+static struct spi_driver ks8995_driver = {
+	.driver = {
+		.name	    = "spi-ks8995",
+		.of_match_table = ks8995_spi_of_match,
+	},
+	.probe	  = ks8995_probe,
+	.remove	  = ks8995_remove,
+	.id_table = ks8995_id,
+};
+
+module_spi_driver(ks8995_driver);
+
+MODULE_DESCRIPTION(DRV_DESC);
+MODULE_VERSION(DRV_VERSION);
+MODULE_AUTHOR("Gabor Juhos <juhosg at openwrt.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/dsa/lantiq/Kconfig b/drivers/net/dsa/lantiq/Kconfig
new file mode 100644
index 000000000000..4a9771be5d58
--- /dev/null
+++ b/drivers/net/dsa/lantiq/Kconfig
@@ -0,0 +1,24 @@
+config NET_DSA_LANTIQ_COMMON
+	tristate
+	select REGMAP
+
+config NET_DSA_LANTIQ_GSWIP
+	tristate "Lantiq / Intel GSWIP"
+	depends on HAS_IOMEM
+	select NET_DSA_TAG_GSWIP
+	select NET_DSA_LANTIQ_COMMON
+	help
+	  This enables support for the Lantiq / Intel GSWIP 2.1 found in
+	  the xrx200 / VR9 SoC.
+
+config NET_DSA_MXL_GSW1XX
+	tristate "MaxLinear GSW1xx Ethernet switch support"
+	select NET_DSA_TAG_MXL_GSW1XX
+	select NET_DSA_LANTIQ_COMMON
+	help
+	  This enables support for the MaxLinear GSW1xx family of 1GE switches
+	    GSW120 4 port, 2 PHYs, RGMII & SGMII/2500Base-X
+	    GSW125 4 port, 2 PHYs, RGMII & SGMII/2500Base-X, industrial temperature
+	    GSW140 6 port, 4 PHYs, RGMII & SGMII/2500Base-X
+	    GSW141 6 port, 4 PHYs, RGMII & SGMII
+	    GSW145 6 port, 4 PHYs, RGMII & SGMII/2500Base-X, industrial temperature
diff --git a/drivers/net/dsa/lantiq/Makefile b/drivers/net/dsa/lantiq/Makefile
new file mode 100644
index 000000000000..85fce605310b
--- /dev/null
+++ b/drivers/net/dsa/lantiq/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_NET_DSA_LANTIQ_GSWIP) += lantiq_gswip.o
+obj-$(CONFIG_NET_DSA_LANTIQ_COMMON) += lantiq_gswip_common.o
+obj-$(CONFIG_NET_DSA_MXL_GSW1XX) += mxl-gsw1xx.o
diff --git a/drivers/net/dsa/lantiq/lantiq_gswip.c b/drivers/net/dsa/lantiq/lantiq_gswip.c
new file mode 100644
index 000000000000..57dd063c0740
--- /dev/null
+++ b/drivers/net/dsa/lantiq/lantiq_gswip.c
@@ -0,0 +1,518 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Lantiq / Intel GSWIP switch driver for VRX200, xRX300 and xRX330 SoCs
+ *
+ * Copyright (C) 2025 Daniel Golle <daniel@makrotopia.org>
+ * Copyright (C) 2017 - 2019 Hauke Mehrtens <hauke@hauke-m.de>
+ * Copyright (C) 2012 John Crispin <john@phrozen.org>
+ * Copyright (C) 2010 Lantiq Deutschland
+ */
+
+#include "lantiq_gswip.h"
+#include "lantiq_pce.h"
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/firmware.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/reset.h>
+#include <dt-bindings/mips/lantiq_rcu_gphy.h>
+
+#include <net/dsa.h>
+
+struct xway_gphy_match_data {
+	char *fe_firmware_name;
+	char *ge_firmware_name;
+};
+
+static void gswip_xrx200_phylink_get_caps(struct dsa_switch *ds, int port,
+					  struct phylink_config *config)
+{
+	switch (port) {
+	case 0:
+	case 1:
+		phy_interface_set_rgmii(config->supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_MII,
+			  config->supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_REVMII,
+			  config->supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_RMII,
+			  config->supported_interfaces);
+		break;
+
+	case 2:
+	case 3:
+	case 4:
+	case 6:
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  config->supported_interfaces);
+		break;
+
+	case 5:
+		phy_interface_set_rgmii(config->supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  config->supported_interfaces);
+		break;
+	}
+
+	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+		MAC_10 | MAC_100 | MAC_1000;
+}
+
+static void gswip_xrx300_phylink_get_caps(struct dsa_switch *ds, int port,
+					  struct phylink_config *config)
+{
+	switch (port) {
+	case 0:
+		phy_interface_set_rgmii(config->supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_GMII,
+			  config->supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_RMII,
+			  config->supported_interfaces);
+		break;
+
+	case 1:
+	case 2:
+	case 3:
+	case 4:
+	case 6:
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  config->supported_interfaces);
+		break;
+
+	case 5:
+		phy_interface_set_rgmii(config->supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  config->supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_RMII,
+			  config->supported_interfaces);
+		break;
+	}
+
+	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+		MAC_10 | MAC_100 | MAC_1000;
+}
+
+static const struct xway_gphy_match_data xrx200a1x_gphy_data = {
+	.fe_firmware_name = "lantiq/xrx200_phy22f_a14.bin",
+	.ge_firmware_name = "lantiq/xrx200_phy11g_a14.bin",
+};
+
+static const struct xway_gphy_match_data xrx200a2x_gphy_data = {
+	.fe_firmware_name = "lantiq/xrx200_phy22f_a22.bin",
+	.ge_firmware_name = "lantiq/xrx200_phy11g_a22.bin",
+};
+
+static const struct xway_gphy_match_data xrx300_gphy_data = {
+	.fe_firmware_name = "lantiq/xrx300_phy22f_a21.bin",
+	.ge_firmware_name = "lantiq/xrx300_phy11g_a21.bin",
+};
+
+static const struct of_device_id xway_gphy_match[] __maybe_unused = {
+	{ .compatible = "lantiq,xrx200-gphy-fw", .data = NULL },
+	{ .compatible = "lantiq,xrx200a1x-gphy-fw", .data = &xrx200a1x_gphy_data },
+	{ .compatible = "lantiq,xrx200a2x-gphy-fw", .data = &xrx200a2x_gphy_data },
+	{ .compatible = "lantiq,xrx300-gphy-fw", .data = &xrx300_gphy_data },
+	{ .compatible = "lantiq,xrx330-gphy-fw", .data = &xrx300_gphy_data },
+	{},
+};
+
+static int gswip_gphy_fw_load(struct gswip_priv *priv, struct gswip_gphy_fw *gphy_fw)
+{
+	struct device *dev = priv->dev;
+	const struct firmware *fw;
+	void *fw_addr;
+	dma_addr_t dma_addr;
+	dma_addr_t dev_addr;
+	size_t size;
+	int ret;
+
+	ret = clk_prepare_enable(gphy_fw->clk_gate);
+	if (ret)
+		return ret;
+
+	reset_control_assert(gphy_fw->reset);
+
+	/* The vendor BSP uses a 200ms delay after asserting the reset line.
+	 * Without this some users are observing that the PHY is not coming up
+	 * on the MDIO bus.
+	 */
+	msleep(200);
+
+	ret = request_firmware(&fw, gphy_fw->fw_name, dev);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to load firmware: %s\n",
+				     gphy_fw->fw_name);
+
+	/* GPHY cores need the firmware code in a persistent and contiguous
+	 * memory area with a 16 kB boundary aligned start address.
+	 */
+	size = fw->size + XRX200_GPHY_FW_ALIGN;
+
+	fw_addr = dmam_alloc_coherent(dev, size, &dma_addr, GFP_KERNEL);
+	if (fw_addr) {
+		fw_addr = PTR_ALIGN(fw_addr, XRX200_GPHY_FW_ALIGN);
+		dev_addr = ALIGN(dma_addr, XRX200_GPHY_FW_ALIGN);
+		memcpy(fw_addr, fw->data, fw->size);
+	} else {
+		release_firmware(fw);
+		return -ENOMEM;
+	}
+
+	release_firmware(fw);
+
+	ret = regmap_write(priv->rcu_regmap, gphy_fw->fw_addr_offset, dev_addr);
+	if (ret)
+		return ret;
+
+	reset_control_deassert(gphy_fw->reset);
+
+	return ret;
+}
+
+static int gswip_gphy_fw_probe(struct gswip_priv *priv,
+			       struct gswip_gphy_fw *gphy_fw,
+			       struct device_node *gphy_fw_np, int i)
+{
+	struct device *dev = priv->dev;
+	u32 gphy_mode;
+	int ret;
+	char gphyname[10];
+
+	snprintf(gphyname, sizeof(gphyname), "gphy%d", i);
+
+	gphy_fw->clk_gate = devm_clk_get(dev, gphyname);
+	if (IS_ERR(gphy_fw->clk_gate)) {
+		return dev_err_probe(dev, PTR_ERR(gphy_fw->clk_gate),
+				     "Failed to lookup gate clock\n");
+	}
+
+	ret = of_property_read_u32(gphy_fw_np, "reg", &gphy_fw->fw_addr_offset);
+	if (ret)
+		return ret;
+
+	ret = of_property_read_u32(gphy_fw_np, "lantiq,gphy-mode", &gphy_mode);
+	/* Default to GE mode */
+	if (ret)
+		gphy_mode = GPHY_MODE_GE;
+
+	switch (gphy_mode) {
+	case GPHY_MODE_FE:
+		gphy_fw->fw_name = priv->gphy_fw_name_cfg->fe_firmware_name;
+		break;
+	case GPHY_MODE_GE:
+		gphy_fw->fw_name = priv->gphy_fw_name_cfg->ge_firmware_name;
+		break;
+	default:
+		return dev_err_probe(dev, -EINVAL, "Unknown GPHY mode %d\n",
+				     gphy_mode);
+	}
+
+	gphy_fw->reset = of_reset_control_array_get_exclusive(gphy_fw_np);
+	if (IS_ERR(gphy_fw->reset))
+		return dev_err_probe(dev, PTR_ERR(gphy_fw->reset),
+				     "Failed to lookup gphy reset\n");
+
+	return gswip_gphy_fw_load(priv, gphy_fw);
+}
+
+static void gswip_gphy_fw_remove(struct gswip_priv *priv,
+				 struct gswip_gphy_fw *gphy_fw)
+{
+	int ret;
+
+	/* check if the device was fully probed */
+	if (!gphy_fw->fw_name)
+		return;
+
+	ret = regmap_write(priv->rcu_regmap, gphy_fw->fw_addr_offset, 0);
+	if (ret)
+		dev_err(priv->dev, "can not reset GPHY FW pointer\n");
+
+	clk_disable_unprepare(gphy_fw->clk_gate);
+
+	reset_control_put(gphy_fw->reset);
+}
+
+static int gswip_gphy_fw_list(struct gswip_priv *priv,
+			      struct device_node *gphy_fw_list_np, u32 version)
+{
+	struct device *dev = priv->dev;
+	struct device_node *gphy_fw_np;
+	const struct of_device_id *match;
+	int err;
+	int i = 0;
+
+	/* The VRX200 rev 1.1 uses the GSWIP 2.0 and needs the older
+	 * GPHY firmware. The VRX200 rev 1.2 uses the GSWIP 2.1 and also
+	 * needs a different GPHY firmware.
+	 */
+	if (of_device_is_compatible(gphy_fw_list_np, "lantiq,xrx200-gphy-fw")) {
+		switch (version) {
+		case GSWIP_VERSION_2_0:
+			priv->gphy_fw_name_cfg = &xrx200a1x_gphy_data;
+			break;
+		case GSWIP_VERSION_2_1:
+			priv->gphy_fw_name_cfg = &xrx200a2x_gphy_data;
+			break;
+		default:
+			return dev_err_probe(dev, -ENOENT,
+					     "unknown GSWIP version: 0x%x\n",
+					     version);
+		}
+	}
+
+	match = of_match_node(xway_gphy_match, gphy_fw_list_np);
+	if (match && match->data)
+		priv->gphy_fw_name_cfg = match->data;
+
+	if (!priv->gphy_fw_name_cfg)
+		return dev_err_probe(dev, -ENOENT,
+				     "GPHY compatible type not supported\n");
+
+	priv->num_gphy_fw = of_get_available_child_count(gphy_fw_list_np);
+	if (!priv->num_gphy_fw)
+		return -ENOENT;
+
+	priv->rcu_regmap = syscon_regmap_lookup_by_phandle(gphy_fw_list_np,
+							   "lantiq,rcu");
+	if (IS_ERR(priv->rcu_regmap))
+		return PTR_ERR(priv->rcu_regmap);
+
+	priv->gphy_fw = devm_kmalloc_array(dev, priv->num_gphy_fw,
+					   sizeof(*priv->gphy_fw),
+					   GFP_KERNEL | __GFP_ZERO);
+	if (!priv->gphy_fw)
+		return -ENOMEM;
+
+	for_each_available_child_of_node(gphy_fw_list_np, gphy_fw_np) {
+		err = gswip_gphy_fw_probe(priv, &priv->gphy_fw[i],
+					  gphy_fw_np, i);
+		if (err) {
+			of_node_put(gphy_fw_np);
+			goto remove_gphy;
+		}
+		i++;
+	}
+
+	/* The standalone PHY11G requires 300ms to be fully
+	 * initialized and ready for any MDIO communication after being
+	 * taken out of reset. For the SoC-internal GPHY variant there
+	 * is no (known) documentation for the minimum time after a
+	 * reset. Use the same value as for the standalone variant as
+	 * some users have reported internal PHYs not being detected
+	 * without any delay.
+	 */
+	msleep(300);
+
+	return 0;
+
+remove_gphy:
+	for (i = 0; i < priv->num_gphy_fw; i++)
+		gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]);
+	return err;
+}
+
+static const struct regmap_config sw_regmap_config = {
+	.name = "switch",
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_shift = REGMAP_UPSHIFT(2),
+	.val_format_endian = REGMAP_ENDIAN_NATIVE,
+	.max_register = GSWIP_SDMA_PCTRLp(6),
+};
+
+static const struct regmap_config mdio_regmap_config = {
+	.name = "mdio",
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_shift = REGMAP_UPSHIFT(2),
+	.val_format_endian = REGMAP_ENDIAN_NATIVE,
+	.max_register = GSWIP_MDIO_PHYp(0),
+};
+
+static const struct regmap_config mii_regmap_config = {
+	.name = "mii",
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_shift = REGMAP_UPSHIFT(2),
+	.val_format_endian = REGMAP_ENDIAN_NATIVE,
+	.max_register = GSWIP_MII_CFGp(6),
+};
+
+static int gswip_probe(struct platform_device *pdev)
+{
+	struct device_node *np, *gphy_fw_np;
+	__iomem void *gswip, *mdio, *mii;
+	struct device *dev = &pdev->dev;
+	struct gswip_priv *priv;
+	int err;
+	int i;
+	u32 version;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	gswip = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(gswip))
+		return PTR_ERR(gswip);
+
+	mdio = devm_platform_ioremap_resource(pdev, 1);
+	if (IS_ERR(mdio))
+		return PTR_ERR(mdio);
+
+	mii = devm_platform_ioremap_resource(pdev, 2);
+	if (IS_ERR(mii))
+		return PTR_ERR(mii);
+
+	priv->gswip = devm_regmap_init_mmio(dev, gswip, &sw_regmap_config);
+	if (IS_ERR(priv->gswip))
+		return PTR_ERR(priv->gswip);
+
+	priv->mdio = devm_regmap_init_mmio(dev, mdio, &mdio_regmap_config);
+	if (IS_ERR(priv->mdio))
+		return PTR_ERR(priv->mdio);
+
+	priv->mii = devm_regmap_init_mmio(dev, mii, &mii_regmap_config);
+	if (IS_ERR(priv->mii))
+		return PTR_ERR(priv->mii);
+
+	priv->hw_info = of_device_get_match_data(dev);
+	if (!priv->hw_info)
+		return -EINVAL;
+
+	priv->ds = devm_kzalloc(dev, sizeof(*priv->ds), GFP_KERNEL);
+	if (!priv->ds)
+		return -ENOMEM;
+
+	priv->dev = dev;
+
+	regmap_read(priv->gswip, GSWIP_VERSION, &version);
+
+	np = dev->of_node;
+	switch (version) {
+	case GSWIP_VERSION_2_0:
+	case GSWIP_VERSION_2_1:
+		if (!of_device_is_compatible(np, "lantiq,xrx200-gswip"))
+			return -EINVAL;
+		break;
+	case GSWIP_VERSION_2_2:
+	case GSWIP_VERSION_2_2_ETC:
+		if (!of_device_is_compatible(np, "lantiq,xrx300-gswip") &&
+		    !of_device_is_compatible(np, "lantiq,xrx330-gswip"))
+			return -EINVAL;
+		break;
+	default:
+		return dev_err_probe(dev, -ENOENT,
+				     "unknown GSWIP version: 0x%x\n", version);
+	}
+
+	/* bring up the mdio bus */
+	gphy_fw_np = of_get_compatible_child(dev->of_node, "lantiq,gphy-fw");
+	if (gphy_fw_np) {
+		err = gswip_gphy_fw_list(priv, gphy_fw_np, version);
+		of_node_put(gphy_fw_np);
+		if (err)
+			return dev_err_probe(dev, err,
+					     "gphy fw probe failed\n");
+	}
+
+	err = gswip_probe_common(priv, version);
+	if (err)
+		goto gphy_fw_remove;
+
+	platform_set_drvdata(pdev, priv);
+
+	return 0;
+
+gphy_fw_remove:
+	for (i = 0; i < priv->num_gphy_fw; i++)
+		gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]);
+	return err;
+}
+
+static void gswip_remove(struct platform_device *pdev)
+{
+	struct gswip_priv *priv = platform_get_drvdata(pdev);
+	int i;
+
+	if (!priv)
+		return;
+
+	/* disable the switch */
+	gswip_disable_switch(priv);
+
+	dsa_unregister_switch(priv->ds);
+
+	for (i = 0; i < priv->num_gphy_fw; i++)
+		gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]);
+}
+
+static void gswip_shutdown(struct platform_device *pdev)
+{
+	struct gswip_priv *priv = platform_get_drvdata(pdev);
+
+	if (!priv)
+		return;
+
+	dsa_switch_shutdown(priv->ds);
+
+	platform_set_drvdata(pdev, NULL);
+}
+
+static const struct gswip_hw_info gswip_xrx200 = {
+	.max_ports = 7,
+	.allowed_cpu_ports = BIT(6),
+	.mii_ports = BIT(0) | BIT(1) | BIT(5),
+	.mii_port_reg_offset = 0,
+	.phylink_get_caps = gswip_xrx200_phylink_get_caps,
+	.pce_microcode = &gswip_pce_microcode,
+	.pce_microcode_size = ARRAY_SIZE(gswip_pce_microcode),
+	.tag_protocol = DSA_TAG_PROTO_GSWIP,
+};
+
+static const struct gswip_hw_info gswip_xrx300 = {
+	.max_ports = 7,
+	.allowed_cpu_ports = BIT(6),
+	.mii_ports = BIT(0) | BIT(5),
+	.mii_port_reg_offset = 0,
+	.phylink_get_caps = gswip_xrx300_phylink_get_caps,
+	.pce_microcode = &gswip_pce_microcode,
+	.pce_microcode_size = ARRAY_SIZE(gswip_pce_microcode),
+	.tag_protocol = DSA_TAG_PROTO_GSWIP,
+};
+
+static const struct of_device_id gswip_of_match[] = {
+	{ .compatible = "lantiq,xrx200-gswip", .data = &gswip_xrx200 },
+	{ .compatible = "lantiq,xrx300-gswip", .data = &gswip_xrx300 },
+	{ .compatible = "lantiq,xrx330-gswip", .data = &gswip_xrx300 },
+	{},
+};
+MODULE_DEVICE_TABLE(of, gswip_of_match);
+
+static struct platform_driver gswip_driver = {
+	.probe = gswip_probe,
+	.remove = gswip_remove,
+	.shutdown = gswip_shutdown,
+	.driver = {
+		.name = "gswip",
+		.of_match_table = gswip_of_match,
+	},
+};
+
+module_platform_driver(gswip_driver);
+
+MODULE_FIRMWARE("lantiq/xrx300_phy11g_a21.bin");
+MODULE_FIRMWARE("lantiq/xrx300_phy22f_a21.bin");
+MODULE_FIRMWARE("lantiq/xrx200_phy11g_a14.bin");
+MODULE_FIRMWARE("lantiq/xrx200_phy11g_a22.bin");
+MODULE_FIRMWARE("lantiq/xrx200_phy22f_a14.bin");
+MODULE_FIRMWARE("lantiq/xrx200_phy22f_a22.bin");
+MODULE_AUTHOR("Hauke Mehrtens <hauke@hauke-m.de>");
+MODULE_DESCRIPTION("Lantiq / Intel GSWIP driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/dsa/lantiq/lantiq_gswip.h b/drivers/net/dsa/lantiq/lantiq_gswip.h
new file mode 100644
index 000000000000..9c38e51a75e8
--- /dev/null
+++ b/drivers/net/dsa/lantiq/lantiq_gswip.h
@@ -0,0 +1,301 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __LANTIQ_GSWIP_H
+#define __LANTIQ_GSWIP_H
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/mutex.h>
+#include <linux/phylink.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/reset.h>
+#include <linux/swab.h>
+#include <net/dsa.h>
+
+/* GSWIP MDIO Registers */
+#define GSWIP_MDIO_GLOB			0x00
+#define  GSWIP_MDIO_GLOB_ENABLE		BIT(15)
+#define GSWIP_MDIO_CTRL			0x08
+#define  GSWIP_MDIO_CTRL_BUSY		BIT(12)
+#define  GSWIP_MDIO_CTRL_RD		BIT(11)
+#define  GSWIP_MDIO_CTRL_WR		BIT(10)
+#define  GSWIP_MDIO_CTRL_PHYAD_MASK	0x1f
+#define  GSWIP_MDIO_CTRL_PHYAD_SHIFT	5
+#define  GSWIP_MDIO_CTRL_REGAD_MASK	0x1f
+#define GSWIP_MDIO_READ			0x09
+#define GSWIP_MDIO_WRITE		0x0A
+#define GSWIP_MDIO_MDC_CFG0		0x0B
+#define GSWIP_MDIO_MDC_CFG1		0x0C
+#define GSWIP_MDIO_PHYp(p)		(0x15 - (p))
+#define  GSWIP_MDIO_PHY_LINK_MASK	0x6000
+#define  GSWIP_MDIO_PHY_LINK_AUTO	0x0000
+#define  GSWIP_MDIO_PHY_LINK_DOWN	0x4000
+#define  GSWIP_MDIO_PHY_LINK_UP		0x2000
+#define  GSWIP_MDIO_PHY_SPEED_MASK	0x1800
+#define  GSWIP_MDIO_PHY_SPEED_AUTO	0x1800
+#define  GSWIP_MDIO_PHY_SPEED_M10	0x0000
+#define  GSWIP_MDIO_PHY_SPEED_M100	0x0800
+#define  GSWIP_MDIO_PHY_SPEED_G1	0x1000
+#define  GSWIP_MDIO_PHY_FDUP_MASK	0x0600
+#define  GSWIP_MDIO_PHY_FDUP_AUTO	0x0000
+#define  GSWIP_MDIO_PHY_FDUP_EN		0x0200
+#define  GSWIP_MDIO_PHY_FDUP_DIS	0x0600
+#define  GSWIP_MDIO_PHY_FCONTX_MASK	0x0180
+#define  GSWIP_MDIO_PHY_FCONTX_AUTO	0x0000
+#define  GSWIP_MDIO_PHY_FCONTX_EN	0x0100
+#define  GSWIP_MDIO_PHY_FCONTX_DIS	0x0180
+#define  GSWIP_MDIO_PHY_FCONRX_MASK	0x0060
+#define  GSWIP_MDIO_PHY_FCONRX_AUTO	0x0000
+#define  GSWIP_MDIO_PHY_FCONRX_EN	0x0020
+#define  GSWIP_MDIO_PHY_FCONRX_DIS	0x0060
+#define  GSWIP_MDIO_PHY_ADDR_MASK	0x001f
+#define  GSWIP_MDIO_PHY_MASK		(GSWIP_MDIO_PHY_ADDR_MASK | \
+					 GSWIP_MDIO_PHY_FCONRX_MASK | \
+					 GSWIP_MDIO_PHY_FCONTX_MASK | \
+					 GSWIP_MDIO_PHY_LINK_MASK | \
+					 GSWIP_MDIO_PHY_SPEED_MASK | \
+					 GSWIP_MDIO_PHY_FDUP_MASK)
+
+/* GSWIP MII Registers */
+#define GSWIP_MII_CFGp(p)		(0x2 * (p))
+#define  GSWIP_MII_CFG_RESET		BIT(15)
+#define  GSWIP_MII_CFG_EN		BIT(14)
+#define  GSWIP_MII_CFG_ISOLATE		BIT(13)
+#define  GSWIP_MII_CFG_LDCLKDIS		BIT(12)
+#define  GSWIP_MII_CFG_RGMII_IBS	BIT(8)
+#define  GSWIP_MII_CFG_RMII_CLK		BIT(7)
+#define  GSWIP_MII_CFG_MODE_MIIP	0x0
+#define  GSWIP_MII_CFG_MODE_MIIM	0x1
+#define  GSWIP_MII_CFG_MODE_RMIIP	0x2
+#define  GSWIP_MII_CFG_MODE_RMIIM	0x3
+#define  GSWIP_MII_CFG_MODE_RGMII	0x4
+#define  GSWIP_MII_CFG_MODE_GMII	0x9
+#define  GSWIP_MII_CFG_MODE_MASK	0xf
+#define  GSWIP_MII_CFG_RATE_M2P5	0x00
+#define  GSWIP_MII_CFG_RATE_M25	0x10
+#define  GSWIP_MII_CFG_RATE_M125	0x20
+#define  GSWIP_MII_CFG_RATE_M50	0x30
+#define  GSWIP_MII_CFG_RATE_AUTO	0x40
+#define  GSWIP_MII_CFG_RATE_MASK	0x70
+#define GSWIP_MII_PCDU0			0x01
+#define GSWIP_MII_PCDU1			0x03
+#define GSWIP_MII_PCDU5			0x05
+#define  GSWIP_MII_PCDU_TXDLY_MASK	GENMASK(2, 0)
+#define  GSWIP_MII_PCDU_RXDLY_MASK	GENMASK(9, 7)
+#define  GSWIP_MII_PCDU_TXDLY(x)	u16_encode_bits(((x) / 500), GSWIP_MII_PCDU_TXDLY_MASK)
+#define  GSWIP_MII_PCDU_RXDLY(x)	u16_encode_bits(((x) / 500), GSWIP_MII_PCDU_RXDLY_MASK)
+#define GSWIP_MII_PCDU_RXDLY_DEFAULT	2000 /* picoseconds */
+#define GSWIP_MII_PCDU_TXDLY_DEFAULT	2000 /* picoseconds */
+
+/* GSWIP Core Registers */
+#define GSWIP_SWRES			0x000
+#define  GSWIP_SWRES_R1			BIT(1)	/* GSWIP Software reset */
+#define  GSWIP_SWRES_R0			BIT(0)	/* GSWIP Hardware reset */
+#define GSWIP_VERSION			0x013
+#define  GSWIP_VERSION_REV_MASK		GENMASK(7, 0)
+#define  GSWIP_VERSION_MOD_MASK		GENMASK(15, 8)
+#define  GSWIP_VERSION_REV(v)		FIELD_GET(GSWIP_VERSION_REV_MASK, v)
+#define  GSWIP_VERSION_MOD(v)		FIELD_GET(GSWIP_VERSION_MOD_MASK, v)
+#define   GSWIP_VERSION_2_0		0x100
+#define   GSWIP_VERSION_2_1		0x021
+#define   GSWIP_VERSION_2_2		0x122
+#define   GSWIP_VERSION_2_2_ETC		0x022
+/* The hardware has the 'major/minor' version bytes in the wrong order
+ * preventing numerical comparisons. Swap the bytes of the 16-bit value
+ * to end up with REV being the most significant byte and MOD being the
+ * least significant byte, which then allows comparing it with the
+ * value stored in struct gswip_priv.
+ */
+#define GSWIP_VERSION_GE(priv, ver)	((priv)->version >= swab16(ver))
+
+#define GSWIP_BM_RAM_VAL(x)		(0x043 - (x))
+#define GSWIP_BM_RAM_ADDR		0x044
+#define GSWIP_BM_RAM_CTRL		0x045
+#define  GSWIP_BM_RAM_CTRL_BAS		BIT(15)
+#define  GSWIP_BM_RAM_CTRL_OPMOD	BIT(5)
+#define  GSWIP_BM_RAM_CTRL_ADDR_MASK	GENMASK(4, 0)
+#define GSWIP_BM_QUEUE_GCTRL		0x04A
+#define  GSWIP_BM_QUEUE_GCTRL_GL_MOD	BIT(10)
+/* buffer management Port Configuration Register */
+#define GSWIP_BM_PCFGp(p)		(0x080 + ((p) * 2))
+#define  GSWIP_BM_PCFG_CNTEN		BIT(0)	/* RMON Counter Enable */
+#define  GSWIP_BM_PCFG_IGCNT		BIT(1)	/* Ingres Special Tag RMON count */
+/* buffer management Port Control Register */
+#define GSWIP_BM_RMON_CTRLp(p)		(0x81 + ((p) * 2))
+#define  GSWIP_BM_CTRL_RMON_RAM1_RES	BIT(0)	/* Software Reset for RMON RAM 1 */
+#define  GSWIP_BM_CTRL_RMON_RAM2_RES	BIT(1)	/* Software Reset for RMON RAM 2 */
+
+/* PCE */
+#define GSWIP_PCE_TBL_KEY(x)		(0x447 - (x))
+#define GSWIP_PCE_TBL_MASK		0x448
+#define GSWIP_PCE_TBL_VAL(x)		(0x44D - (x))
+#define GSWIP_PCE_TBL_ADDR		0x44E
+#define GSWIP_PCE_TBL_CTRL		0x44F
+#define  GSWIP_PCE_TBL_CTRL_BAS		BIT(15)
+#define  GSWIP_PCE_TBL_CTRL_TYPE	BIT(13)
+#define  GSWIP_PCE_TBL_CTRL_VLD		BIT(12)
+#define  GSWIP_PCE_TBL_CTRL_KEYFORM	BIT(11)
+#define  GSWIP_PCE_TBL_CTRL_GMAP_MASK	GENMASK(10, 7)
+#define  GSWIP_PCE_TBL_CTRL_OPMOD_MASK	GENMASK(6, 5)
+#define  GSWIP_PCE_TBL_CTRL_OPMOD_ADRD	0x00
+#define  GSWIP_PCE_TBL_CTRL_OPMOD_ADWR	0x20
+#define  GSWIP_PCE_TBL_CTRL_OPMOD_KSRD	0x40
+#define  GSWIP_PCE_TBL_CTRL_OPMOD_KSWR	0x60
+#define  GSWIP_PCE_TBL_CTRL_ADDR_MASK	GENMASK(4, 0)
+#define GSWIP_PCE_PMAP1			0x453	/* Monitoring port map */
+#define GSWIP_PCE_PMAP2			0x454	/* Default Multicast port map */
+#define GSWIP_PCE_PMAP3			0x455	/* Default Unknown Unicast port map */
+#define GSWIP_PCE_GCTRL_0		0x456
+#define  GSWIP_PCE_GCTRL_0_MTFL		BIT(0)  /* MAC Table Flushing */
+#define  GSWIP_PCE_GCTRL_0_MC_VALID	BIT(3)
+#define  GSWIP_PCE_GCTRL_0_VLAN		BIT(14) /* VLAN aware Switching */
+#define GSWIP_PCE_GCTRL_1		0x457
+#define  GSWIP_PCE_GCTRL_1_MAC_GLOCK	BIT(2)	/* MAC Address table lock */
+#define  GSWIP_PCE_GCTRL_1_MAC_GLOCK_MOD	BIT(3) /* Mac address table lock forwarding mode */
+#define GSWIP_PCE_PCTRL_0p(p)		(0x480 + ((p) * 0xA))
+#define  GSWIP_PCE_PCTRL_0_TVM		BIT(5)	/* Transparent VLAN mode */
+#define  GSWIP_PCE_PCTRL_0_VREP		BIT(6)	/* VLAN Replace Mode */
+#define  GSWIP_PCE_PCTRL_0_INGRESS	BIT(11)	/* Accept special tag in ingress */
+#define  GSWIP_PCE_PCTRL_0_PSTATE_LISTEN	0x0
+#define  GSWIP_PCE_PCTRL_0_PSTATE_RX		0x1
+#define  GSWIP_PCE_PCTRL_0_PSTATE_TX		0x2
+#define  GSWIP_PCE_PCTRL_0_PSTATE_LEARNING	0x3
+#define  GSWIP_PCE_PCTRL_0_PSTATE_FORWARDING	0x7
+#define  GSWIP_PCE_PCTRL_0_PSTATE_MASK	GENMASK(2, 0)
+/* Ethernet Switch PCE Port Control Register 3 */
+#define GSWIP_PCE_PCTRL_3p(p)		(0x483 + ((p) * 0xA))
+#define  GSWIP_PCE_PCTRL_3_LNDIS	BIT(15)  /* Learning Disable */
+#define GSWIP_PCE_VCTRL(p)		(0x485 + ((p) * 0xA))
+#define  GSWIP_PCE_VCTRL_UVR		BIT(0)	/* Unknown VLAN Rule */
+#define  GSWIP_PCE_VCTRL_VINR		GENMASK(2, 1) /* VLAN Ingress Tag Rule */
+#define  GSWIP_PCE_VCTRL_VINR_ALL	0 /* Admit tagged and untagged packets */
+#define  GSWIP_PCE_VCTRL_VINR_TAGGED	1 /* Admit only tagged packets */
+#define  GSWIP_PCE_VCTRL_VINR_UNTAGGED	2 /* Admit only untagged packets */
+#define  GSWIP_PCE_VCTRL_VIMR		BIT(3)	/* VLAN Ingress Member violation rule */
+#define  GSWIP_PCE_VCTRL_VEMR		BIT(4)	/* VLAN Egress Member violation rule */
+#define  GSWIP_PCE_VCTRL_VSR		BIT(5)	/* VLAN Security */
+#define  GSWIP_PCE_VCTRL_VID0		BIT(6)	/* Priority Tagged Rule */
+#define GSWIP_PCE_DEFPVID(p)		(0x486 + ((p) * 0xA))
+
+#define GSWIP_MAC_FLEN			0x8C5
+#define GSWIP_MAC_CTRL_0p(p)		(0x903 + ((p) * 0xC))
+#define  GSWIP_MAC_CTRL_0_PADEN		BIT(8)
+#define  GSWIP_MAC_CTRL_0_FCS_EN	BIT(7)
+#define  GSWIP_MAC_CTRL_0_FCON_MASK	0x0070
+#define  GSWIP_MAC_CTRL_0_FCON_AUTO	0x0000
+#define  GSWIP_MAC_CTRL_0_FCON_RX	0x0010
+#define  GSWIP_MAC_CTRL_0_FCON_TX	0x0020
+#define  GSWIP_MAC_CTRL_0_FCON_RXTX	0x0030
+#define  GSWIP_MAC_CTRL_0_FCON_NONE	0x0040
+#define  GSWIP_MAC_CTRL_0_FDUP_MASK	0x000C
+#define  GSWIP_MAC_CTRL_0_FDUP_AUTO	0x0000
+#define  GSWIP_MAC_CTRL_0_FDUP_EN	0x0004
+#define  GSWIP_MAC_CTRL_0_FDUP_DIS	0x000C
+#define  GSWIP_MAC_CTRL_0_GMII_MASK	0x0003
+#define  GSWIP_MAC_CTRL_0_GMII_AUTO	0x0000
+#define  GSWIP_MAC_CTRL_0_GMII_MII	0x0001
+#define  GSWIP_MAC_CTRL_0_GMII_RGMII	0x0002
+#define GSWIP_MAC_CTRL_2p(p)		(0x905 + ((p) * 0xC))
+#define GSWIP_MAC_CTRL_2_LCHKL		BIT(2) /* Frame Length Check Long Enable */
+#define GSWIP_MAC_CTRL_2_MLEN		BIT(3) /* Maximum Untagged Frame Lnegth */
+#define GSWIP_MAC_CTRL_4p(p)		(0x907 + ((p) * 0xC))
+#define  GSWIP_MAC_CTRL_4_LPIEN		BIT(7) /* LPI Mode Enable */
+#define  GSWIP_MAC_CTRL_4_GWAIT_MASK	GENMASK(14, 8) /* LPI Wait Time 1G */
+#define  GSWIP_MAC_CTRL_4_GWAIT(t)	u16_encode_bits((t), GSWIP_MAC_CTRL_4_GWAIT_MASK)
+#define  GSWIP_MAC_CTRL_4_WAIT_MASK	GENMASK(6, 0) /* LPI Wait Time 100M */
+#define  GSWIP_MAC_CTRL_4_WAIT(t)	u16_encode_bits((t), GSWIP_MAC_CTRL_4_WAIT_MASK)
+
+/* Ethernet Switch Fetch DMA Port Control Register */
+#define GSWIP_FDMA_PCTRLp(p)		(0xA80 + ((p) * 0x6))
+#define  GSWIP_FDMA_PCTRL_EN		BIT(0)	/* FDMA Port Enable */
+#define  GSWIP_FDMA_PCTRL_STEN		BIT(1)	/* Special Tag Insertion Enable */
+#define  GSWIP_FDMA_PCTRL_VLANMOD_MASK	GENMASK(4, 3)	/* VLAN Modification Control */
+#define  GSWIP_FDMA_PCTRL_VLANMOD_SHIFT	3	/* VLAN Modification Control */
+#define  GSWIP_FDMA_PCTRL_VLANMOD_DIS	(0x0 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT)
+#define  GSWIP_FDMA_PCTRL_VLANMOD_PRIO	(0x1 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT)
+#define  GSWIP_FDMA_PCTRL_VLANMOD_ID	(0x2 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT)
+#define  GSWIP_FDMA_PCTRL_VLANMOD_BOTH	(0x3 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT)
+
+/* Ethernet Switch Store DMA Port Control Register */
+#define GSWIP_SDMA_PCTRLp(p)		(0xBC0 + ((p) * 0x6))
+#define  GSWIP_SDMA_PCTRL_EN		BIT(0)	/* SDMA Port Enable */
+#define  GSWIP_SDMA_PCTRL_FCEN		BIT(1)	/* Flow Control Enable */
+#define  GSWIP_SDMA_PCTRL_PAUFWD	BIT(3)	/* Pause Frame Forwarding */
+
+#define GSWIP_TABLE_ACTIVE_VLAN		0x01
+#define GSWIP_TABLE_VLAN_MAPPING	0x02
+#define GSWIP_TABLE_MAC_BRIDGE		0x0b
+#define  GSWIP_TABLE_MAC_BRIDGE_KEY3_FID	GENMASK(5, 0)	/* Filtering identifier */
+#define  GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT	GENMASK(7, 4)	/* Port on learned entries */
+#define  GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC	BIT(0)		/* Static, non-aging entry */
+#define  GSWIP_TABLE_MAC_BRIDGE_VAL1_VALID	BIT(1)		/* Valid bit */
+
+#define XRX200_GPHY_FW_ALIGN	(16 * 1024)
+
+/* Maximum packet size supported by the switch. In theory this should be 10240,
+ * but long packets currently cause lock-ups with an MTU of over 2526. Medium
+ * packets are sometimes dropped (e.g. TCP over 2477, UDP over 2516-2519, ICMP
+ * over 2526), hence an MTU value of 2400 seems safe. This issue only affects
+ * packet reception. This is probably caused by the PPA engine, which is on the
+ * RX part of the device. Packet transmission works properly up to 10240.
+ */
+#define GSWIP_MAX_PACKET_LENGTH	2400
+
+#define GSWIP_VLAN_UNAWARE_PVID	0
+
+struct gswip_pce_microcode {
+	u16 val_3;
+	u16 val_2;
+	u16 val_1;
+	u16 val_0;
+};
+
+struct gswip_hw_info {
+	int max_ports;
+	unsigned int allowed_cpu_ports;
+	unsigned int mii_ports;
+	int mii_port_reg_offset;
+	bool supports_2500m;
+	const struct gswip_pce_microcode (*pce_microcode)[];
+	size_t pce_microcode_size;
+	enum dsa_tag_protocol tag_protocol;
+	void (*phylink_get_caps)(struct dsa_switch *ds, int port,
+				 struct phylink_config *config);
+	struct phylink_pcs *(*mac_select_pcs)(struct phylink_config *config,
+					      phy_interface_t interface);
+};
+
+struct gswip_gphy_fw {
+	struct clk *clk_gate;
+	struct reset_control *reset;
+	u32 fw_addr_offset;
+	char *fw_name;
+};
+
+struct gswip_vlan {
+	struct net_device *bridge;
+	u16 vid;
+	u8 fid;
+};
+
+struct gswip_priv {
+	struct regmap *gswip;
+	struct regmap *mdio;
+	struct regmap *mii;
+	const struct gswip_hw_info *hw_info;
+	const struct xway_gphy_match_data *gphy_fw_name_cfg;
+	struct dsa_switch *ds;
+	struct device *dev;
+	struct regmap *rcu_regmap;
+	struct gswip_vlan vlans[64];
+	int num_gphy_fw;
+	struct gswip_gphy_fw *gphy_fw;
+	struct mutex pce_table_lock;
+	u16 version;
+};
+
+void gswip_disable_switch(struct gswip_priv *priv);
+
+int gswip_probe_common(struct gswip_priv *priv, u32 version);
+
+#endif /* __LANTIQ_GSWIP_H */
diff --git a/drivers/net/dsa/lantiq/lantiq_gswip_common.c b/drivers/net/dsa/lantiq/lantiq_gswip_common.c
new file mode 100644
index 000000000000..9da39edf8f57
--- /dev/null
+++ b/drivers/net/dsa/lantiq/lantiq_gswip_common.c
@@ -0,0 +1,1739 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Lantiq / Intel / MaxLinear GSWIP common function library
+ *
+ * Copyright (C) 2025 Daniel Golle <daniel@makrotopia.org>
+ * Copyright (C) 2023 - 2024 MaxLinear Inc.
+ * Copyright (C) 2022 Snap One, LLC.  All rights reserved.
+ * Copyright (C) 2017 - 2019 Hauke Mehrtens <hauke@hauke-m.de>
+ * Copyright (C) 2012 John Crispin <john@phrozen.org>
+ * Copyright (C) 2010 Lantiq Deutschland
+ *
+ * The VLAN and bridge model the GSWIP hardware uses does not directly
+ * matches the model DSA uses.
+ *
+ * The hardware has 64 possible table entries for bridges with one VLAN
+ * ID, one flow id and a list of ports for each bridge. All entries which
+ * match the same flow ID are combined in the mac learning table, they
+ * act as one global bridge.
+ * The hardware does not support VLAN filter on the port, but on the
+ * bridge, this driver converts the DSA model to the hardware.
+ *
+ * The CPU gets all the exception frames which do not match any forwarding
+ * rule and the CPU port is also added to all bridges. This makes it possible
+ * to handle all the special cases easily in software.
+ * At the initialization the driver allocates one bridge table entry for
+ * each switch port which is used when the port is used without an
+ * explicit bridge. This prevents the frames from being forwarded
+ * between all LAN ports by default.
+ */
+
+#include "lantiq_gswip.h"
+
+#include <linux/delay.h>
+#include <linux/etherdevice.h>
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/phy.h>
+#include <linux/phylink.h>
+#include <linux/regmap.h>
+#include <net/dsa.h>
+
+struct gswip_pce_table_entry {
+	u16 index;      // PCE_TBL_ADDR.ADDR = pData->table_index
+	u16 table;      // PCE_TBL_CTRL.ADDR = pData->table
+	u16 key[8];
+	u16 val[5];
+	u16 mask;
+	u8 gmap;
+	bool type;
+	bool valid;
+	bool key_mode;
+};
+
+struct gswip_rmon_cnt_desc {
+	unsigned int size;
+	unsigned int offset;
+	const char *name;
+};
+
+#define MIB_DESC(_size, _offset, _name) {.size = _size, .offset = _offset, .name = _name}
+
+static const struct gswip_rmon_cnt_desc gswip_rmon_cnt[] = {
+	/** Receive Packet Count (only packets that are accepted and not discarded). */
+	MIB_DESC(1, 0x1F, "RxGoodPkts"),
+	MIB_DESC(1, 0x23, "RxUnicastPkts"),
+	MIB_DESC(1, 0x22, "RxMulticastPkts"),
+	MIB_DESC(1, 0x21, "RxFCSErrorPkts"),
+	MIB_DESC(1, 0x1D, "RxUnderSizeGoodPkts"),
+	MIB_DESC(1, 0x1E, "RxUnderSizeErrorPkts"),
+	MIB_DESC(1, 0x1B, "RxOversizeGoodPkts"),
+	MIB_DESC(1, 0x1C, "RxOversizeErrorPkts"),
+	MIB_DESC(1, 0x20, "RxGoodPausePkts"),
+	MIB_DESC(1, 0x1A, "RxAlignErrorPkts"),
+	MIB_DESC(1, 0x12, "Rx64BytePkts"),
+	MIB_DESC(1, 0x13, "Rx127BytePkts"),
+	MIB_DESC(1, 0x14, "Rx255BytePkts"),
+	MIB_DESC(1, 0x15, "Rx511BytePkts"),
+	MIB_DESC(1, 0x16, "Rx1023BytePkts"),
+	/** Receive Size 1024-1522 (or more, if configured) Packet Count. */
+	MIB_DESC(1, 0x17, "RxMaxBytePkts"),
+	MIB_DESC(1, 0x18, "RxDroppedPkts"),
+	MIB_DESC(1, 0x19, "RxFilteredPkts"),
+	MIB_DESC(2, 0x24, "RxGoodBytes"),
+	MIB_DESC(2, 0x26, "RxBadBytes"),
+	MIB_DESC(1, 0x11, "TxAcmDroppedPkts"),
+	MIB_DESC(1, 0x0C, "TxGoodPkts"),
+	MIB_DESC(1, 0x06, "TxUnicastPkts"),
+	MIB_DESC(1, 0x07, "TxMulticastPkts"),
+	MIB_DESC(1, 0x00, "Tx64BytePkts"),
+	MIB_DESC(1, 0x01, "Tx127BytePkts"),
+	MIB_DESC(1, 0x02, "Tx255BytePkts"),
+	MIB_DESC(1, 0x03, "Tx511BytePkts"),
+	MIB_DESC(1, 0x04, "Tx1023BytePkts"),
+	/** Transmit Size 1024-1522 (or more, if configured) Packet Count. */
+	MIB_DESC(1, 0x05, "TxMaxBytePkts"),
+	MIB_DESC(1, 0x08, "TxSingleCollCount"),
+	MIB_DESC(1, 0x09, "TxMultCollCount"),
+	MIB_DESC(1, 0x0A, "TxLateCollCount"),
+	MIB_DESC(1, 0x0B, "TxExcessCollCount"),
+	MIB_DESC(1, 0x0D, "TxPauseCount"),
+	MIB_DESC(1, 0x10, "TxDroppedPkts"),
+	MIB_DESC(2, 0x0E, "TxGoodBytes"),
+};
+
+static u32 gswip_switch_r_timeout(struct gswip_priv *priv, u32 offset,
+				  u32 cleared)
+{
+	u32 val;
+
+	return regmap_read_poll_timeout(priv->gswip, offset, val,
+					!(val & cleared), 20, 50000);
+}
+
+static void gswip_mii_mask_cfg(struct gswip_priv *priv, u32 mask, u32 set,
+			       int port)
+{
+	int reg_port;
+
+	/* MII_CFG register only exists for MII ports */
+	if (!(priv->hw_info->mii_ports & BIT(port)))
+		return;
+
+	reg_port = port + priv->hw_info->mii_port_reg_offset;
+
+	regmap_write_bits(priv->mii, GSWIP_MII_CFGp(reg_port), mask,
+			  set);
+}
+
+static int gswip_mdio_poll(struct gswip_priv *priv)
+{
+	u32 ctrl;
+
+	return regmap_read_poll_timeout(priv->mdio, GSWIP_MDIO_CTRL, ctrl,
+					!(ctrl & GSWIP_MDIO_CTRL_BUSY), 40, 4000);
+}
+
+static int gswip_mdio_wr(struct mii_bus *bus, int addr, int reg, u16 val)
+{
+	struct gswip_priv *priv = bus->priv;
+	int err;
+
+	err = gswip_mdio_poll(priv);
+	if (err) {
+		dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n");
+		return err;
+	}
+
+	regmap_write(priv->mdio, GSWIP_MDIO_WRITE, val);
+	regmap_write(priv->mdio, GSWIP_MDIO_CTRL,
+		     GSWIP_MDIO_CTRL_BUSY | GSWIP_MDIO_CTRL_WR |
+		     ((addr & GSWIP_MDIO_CTRL_PHYAD_MASK) << GSWIP_MDIO_CTRL_PHYAD_SHIFT) |
+		     (reg & GSWIP_MDIO_CTRL_REGAD_MASK));
+
+	return 0;
+}
+
+static int gswip_mdio_rd(struct mii_bus *bus, int addr, int reg)
+{
+	struct gswip_priv *priv = bus->priv;
+	u32 val;
+	int err;
+
+	err = gswip_mdio_poll(priv);
+	if (err) {
+		dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n");
+		return err;
+	}
+
+	regmap_write(priv->mdio, GSWIP_MDIO_CTRL,
+		     GSWIP_MDIO_CTRL_BUSY | GSWIP_MDIO_CTRL_RD |
+		     ((addr & GSWIP_MDIO_CTRL_PHYAD_MASK) << GSWIP_MDIO_CTRL_PHYAD_SHIFT) |
+		     (reg & GSWIP_MDIO_CTRL_REGAD_MASK));
+
+	err = gswip_mdio_poll(priv);
+	if (err) {
+		dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n");
+		return err;
+	}
+
+	err = regmap_read(priv->mdio, GSWIP_MDIO_READ, &val);
+	if (err)
+		return err;
+
+	return val;
+}
+
+static int gswip_mdio(struct gswip_priv *priv)
+{
+	struct device_node *mdio_np, *switch_np = priv->dev->of_node;
+	struct device *dev = priv->dev;
+	struct mii_bus *bus;
+	int err = 0;
+
+	mdio_np = of_get_compatible_child(switch_np, "lantiq,xrx200-mdio");
+	if (!mdio_np)
+		mdio_np = of_get_child_by_name(switch_np, "mdio");
+
+	if (!of_device_is_available(mdio_np))
+		goto out_put_node;
+
+	bus = devm_mdiobus_alloc(dev);
+	if (!bus) {
+		err = -ENOMEM;
+		goto out_put_node;
+	}
+
+	bus->priv = priv;
+	bus->read = gswip_mdio_rd;
+	bus->write = gswip_mdio_wr;
+	bus->name = "lantiq,xrx200-mdio";
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(priv->dev));
+	bus->parent = priv->dev;
+
+	err = devm_of_mdiobus_register(dev, bus, mdio_np);
+
+out_put_node:
+	of_node_put(mdio_np);
+
+	return err;
+}
+
+static int gswip_pce_table_entry_read(struct gswip_priv *priv,
+				      struct gswip_pce_table_entry *tbl)
+{
+	int i;
+	int err;
+	u32 crtl;
+	u32 tmp;
+	u16 addr_mode = tbl->key_mode ? GSWIP_PCE_TBL_CTRL_OPMOD_KSRD :
+					GSWIP_PCE_TBL_CTRL_OPMOD_ADRD;
+
+	mutex_lock(&priv->pce_table_lock);
+
+	err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL,
+				     GSWIP_PCE_TBL_CTRL_BAS);
+	if (err)
+		goto out_unlock;
+
+	regmap_write(priv->gswip, GSWIP_PCE_TBL_ADDR, tbl->index);
+	regmap_write_bits(priv->gswip, GSWIP_PCE_TBL_CTRL,
+			  GSWIP_PCE_TBL_CTRL_ADDR_MASK |
+			  GSWIP_PCE_TBL_CTRL_OPMOD_MASK |
+			  GSWIP_PCE_TBL_CTRL_BAS,
+			  tbl->table | addr_mode | GSWIP_PCE_TBL_CTRL_BAS);
+
+	err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL,
+				     GSWIP_PCE_TBL_CTRL_BAS);
+	if (err)
+		goto out_unlock;
+
+	for (i = 0; i < ARRAY_SIZE(tbl->key); i++) {
+		err = regmap_read(priv->gswip, GSWIP_PCE_TBL_KEY(i), &tmp);
+		if (err)
+			goto out_unlock;
+		tbl->key[i] = tmp;
+	}
+	for (i = 0; i < ARRAY_SIZE(tbl->val); i++) {
+		err = regmap_read(priv->gswip, GSWIP_PCE_TBL_VAL(i), &tmp);
+		if (err)
+			goto out_unlock;
+		tbl->val[i] = tmp;
+	}
+
+	err = regmap_read(priv->gswip, GSWIP_PCE_TBL_MASK, &tmp);
+	if (err)
+		goto out_unlock;
+
+	tbl->mask = tmp;
+	err = regmap_read(priv->gswip, GSWIP_PCE_TBL_CTRL, &crtl);
+	if (err)
+		goto out_unlock;
+
+	tbl->type = !!(crtl & GSWIP_PCE_TBL_CTRL_TYPE);
+	tbl->valid = !!(crtl & GSWIP_PCE_TBL_CTRL_VLD);
+	tbl->gmap = (crtl & GSWIP_PCE_TBL_CTRL_GMAP_MASK) >> 7;
+
+out_unlock:
+	mutex_unlock(&priv->pce_table_lock);
+
+	return err;
+}
+
+static int gswip_pce_table_entry_write(struct gswip_priv *priv,
+				       struct gswip_pce_table_entry *tbl)
+{
+	int i;
+	int err;
+	u32 crtl;
+	u16 addr_mode = tbl->key_mode ? GSWIP_PCE_TBL_CTRL_OPMOD_KSWR :
+					GSWIP_PCE_TBL_CTRL_OPMOD_ADWR;
+
+	mutex_lock(&priv->pce_table_lock);
+
+	err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL,
+				     GSWIP_PCE_TBL_CTRL_BAS);
+	if (err) {
+		mutex_unlock(&priv->pce_table_lock);
+		return err;
+	}
+
+	regmap_write(priv->gswip, GSWIP_PCE_TBL_ADDR, tbl->index);
+	regmap_write_bits(priv->gswip, GSWIP_PCE_TBL_CTRL,
+			  GSWIP_PCE_TBL_CTRL_ADDR_MASK |
+			  GSWIP_PCE_TBL_CTRL_OPMOD_MASK,
+			  tbl->table | addr_mode);
+
+	for (i = 0; i < ARRAY_SIZE(tbl->key); i++)
+		regmap_write(priv->gswip, GSWIP_PCE_TBL_KEY(i), tbl->key[i]);
+
+	for (i = 0; i < ARRAY_SIZE(tbl->val); i++)
+		regmap_write(priv->gswip, GSWIP_PCE_TBL_VAL(i), tbl->val[i]);
+
+	regmap_write_bits(priv->gswip, GSWIP_PCE_TBL_CTRL,
+			  GSWIP_PCE_TBL_CTRL_ADDR_MASK |
+			  GSWIP_PCE_TBL_CTRL_OPMOD_MASK,
+			  tbl->table | addr_mode);
+
+	regmap_write(priv->gswip, GSWIP_PCE_TBL_MASK, tbl->mask);
+
+	regmap_read(priv->gswip, GSWIP_PCE_TBL_CTRL, &crtl);
+	crtl &= ~(GSWIP_PCE_TBL_CTRL_TYPE | GSWIP_PCE_TBL_CTRL_VLD |
+		  GSWIP_PCE_TBL_CTRL_GMAP_MASK);
+	if (tbl->type)
+		crtl |= GSWIP_PCE_TBL_CTRL_TYPE;
+	if (tbl->valid)
+		crtl |= GSWIP_PCE_TBL_CTRL_VLD;
+	crtl |= (tbl->gmap << 7) & GSWIP_PCE_TBL_CTRL_GMAP_MASK;
+	crtl |= GSWIP_PCE_TBL_CTRL_BAS;
+	regmap_write(priv->gswip, GSWIP_PCE_TBL_CTRL, crtl);
+
+	err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL,
+				     GSWIP_PCE_TBL_CTRL_BAS);
+
+	mutex_unlock(&priv->pce_table_lock);
+
+	return err;
+}
+
+/* Add the LAN port into a bridge with the CPU port by
+ * default. This prevents automatic forwarding of
+ * packages between the LAN ports when no explicit
+ * bridge is configured.
+ */
+static int gswip_add_single_port_br(struct gswip_priv *priv, int port, bool add)
+{
+	struct gswip_pce_table_entry vlan_active = {0,};
+	struct gswip_pce_table_entry vlan_mapping = {0,};
+	int err;
+
+	vlan_active.index = port + 1;
+	vlan_active.table = GSWIP_TABLE_ACTIVE_VLAN;
+	vlan_active.key[0] = GSWIP_VLAN_UNAWARE_PVID;
+	vlan_active.val[0] = port + 1 /* fid */;
+	vlan_active.valid = add;
+	err = gswip_pce_table_entry_write(priv, &vlan_active);
+	if (err) {
+		dev_err(priv->dev, "failed to write active VLAN: %d\n", err);
+		return err;
+	}
+
+	if (!add)
+		return 0;
+
+	vlan_mapping.index = port + 1;
+	vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING;
+	vlan_mapping.val[0] = GSWIP_VLAN_UNAWARE_PVID;
+	vlan_mapping.val[1] = BIT(port) | dsa_cpu_ports(priv->ds);
+	vlan_mapping.val[2] = 0;
+	err = gswip_pce_table_entry_write(priv, &vlan_mapping);
+	if (err) {
+		dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static int gswip_port_set_learning(struct gswip_priv *priv, int port,
+				   bool enable)
+{
+	if (!GSWIP_VERSION_GE(priv, GSWIP_VERSION_2_2))
+		return -EOPNOTSUPP;
+
+	/* learning disable bit */
+	return regmap_update_bits(priv->gswip, GSWIP_PCE_PCTRL_3p(port),
+				  GSWIP_PCE_PCTRL_3_LNDIS,
+				  enable ? 0 : GSWIP_PCE_PCTRL_3_LNDIS);
+}
+
+static int gswip_port_pre_bridge_flags(struct dsa_switch *ds, int port,
+				       struct switchdev_brport_flags flags,
+				       struct netlink_ext_ack *extack)
+{
+	struct gswip_priv *priv = ds->priv;
+	unsigned long supported = 0;
+
+	if (GSWIP_VERSION_GE(priv, GSWIP_VERSION_2_2))
+		supported |= BR_LEARNING;
+
+	if (flags.mask & ~supported)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int gswip_port_bridge_flags(struct dsa_switch *ds, int port,
+				   struct switchdev_brport_flags flags,
+				   struct netlink_ext_ack *extack)
+{
+	struct gswip_priv *priv = ds->priv;
+
+	if (flags.mask & BR_LEARNING)
+		return gswip_port_set_learning(priv, port,
+					       !!(flags.val & BR_LEARNING));
+
+	return 0;
+}
+
+static int gswip_port_setup(struct dsa_switch *ds, int port)
+{
+	struct gswip_priv *priv = ds->priv;
+	int err;
+
+	if (!dsa_is_cpu_port(ds, port)) {
+		err = gswip_add_single_port_br(priv, port, true);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int gswip_port_enable(struct dsa_switch *ds, int port,
+			     struct phy_device *phydev)
+{
+	struct gswip_priv *priv = ds->priv;
+
+	if (!dsa_is_cpu_port(ds, port)) {
+		u32 mdio_phy = 0;
+
+		if (phydev)
+			mdio_phy = phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK;
+
+		regmap_write_bits(priv->mdio, GSWIP_MDIO_PHYp(port),
+				  GSWIP_MDIO_PHY_ADDR_MASK,
+				  mdio_phy);
+	}
+
+	/* RMON Counter Enable for port */
+	regmap_write(priv->gswip, GSWIP_BM_PCFGp(port), GSWIP_BM_PCFG_CNTEN);
+
+	/* enable port fetch/store dma & VLAN Modification */
+	regmap_set_bits(priv->gswip, GSWIP_FDMA_PCTRLp(port),
+			GSWIP_FDMA_PCTRL_EN | GSWIP_FDMA_PCTRL_VLANMOD_BOTH);
+	regmap_set_bits(priv->gswip, GSWIP_SDMA_PCTRLp(port),
+			GSWIP_SDMA_PCTRL_EN);
+
+	return 0;
+}
+
+static void gswip_port_disable(struct dsa_switch *ds, int port)
+{
+	struct gswip_priv *priv = ds->priv;
+
+	regmap_clear_bits(priv->gswip, GSWIP_FDMA_PCTRLp(port),
+			  GSWIP_FDMA_PCTRL_EN);
+	regmap_clear_bits(priv->gswip, GSWIP_SDMA_PCTRLp(port),
+			  GSWIP_SDMA_PCTRL_EN);
+}
+
+static int gswip_pce_load_microcode(struct gswip_priv *priv)
+{
+	int i;
+	int err;
+
+	regmap_write_bits(priv->gswip, GSWIP_PCE_TBL_CTRL,
+			  GSWIP_PCE_TBL_CTRL_ADDR_MASK |
+			  GSWIP_PCE_TBL_CTRL_OPMOD_MASK |
+			  GSWIP_PCE_TBL_CTRL_OPMOD_ADWR,
+			  GSWIP_PCE_TBL_CTRL_OPMOD_ADWR);
+	regmap_write(priv->gswip, GSWIP_PCE_TBL_MASK, 0);
+
+	for (i = 0; i < priv->hw_info->pce_microcode_size; i++) {
+		regmap_write(priv->gswip, GSWIP_PCE_TBL_ADDR, i);
+		regmap_write(priv->gswip, GSWIP_PCE_TBL_VAL(0),
+			     (*priv->hw_info->pce_microcode)[i].val_0);
+		regmap_write(priv->gswip, GSWIP_PCE_TBL_VAL(1),
+			     (*priv->hw_info->pce_microcode)[i].val_1);
+		regmap_write(priv->gswip, GSWIP_PCE_TBL_VAL(2),
+			     (*priv->hw_info->pce_microcode)[i].val_2);
+		regmap_write(priv->gswip, GSWIP_PCE_TBL_VAL(3),
+			     (*priv->hw_info->pce_microcode)[i].val_3);
+
+		/* start the table access: */
+		regmap_set_bits(priv->gswip, GSWIP_PCE_TBL_CTRL,
+				GSWIP_PCE_TBL_CTRL_BAS);
+		err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL,
+					     GSWIP_PCE_TBL_CTRL_BAS);
+		if (err)
+			return err;
+	}
+
+	/* tell the switch that the microcode is loaded */
+	regmap_set_bits(priv->gswip, GSWIP_PCE_GCTRL_0,
+			GSWIP_PCE_GCTRL_0_MC_VALID);
+
+	return 0;
+}
+
+static void gswip_port_commit_pvid(struct gswip_priv *priv, int port)
+{
+	struct dsa_port *dp = dsa_to_port(priv->ds, port);
+	struct net_device *br = dsa_port_bridge_dev_get(dp);
+	u32 vinr;
+	int idx;
+
+	if (!dsa_port_is_user(dp))
+		return;
+
+	if (br) {
+		u16 pvid = GSWIP_VLAN_UNAWARE_PVID;
+
+		if (br_vlan_enabled(br))
+			br_vlan_get_pvid(br, &pvid);
+
+		/* VLAN-aware bridge ports with no PVID will use Active VLAN
+		 * index 0. The expectation is that this drops all untagged and
+		 * VID-0 tagged ingress traffic.
+		 */
+		idx = 0;
+		for (int i = priv->hw_info->max_ports;
+		     i < ARRAY_SIZE(priv->vlans); i++) {
+			if (priv->vlans[i].bridge == br &&
+			    priv->vlans[i].vid == pvid) {
+				idx = i;
+				break;
+			}
+		}
+	} else {
+		/* The Active VLAN table index as configured by
+		 * gswip_add_single_port_br()
+		 */
+		idx = port + 1;
+	}
+
+	vinr = idx ? GSWIP_PCE_VCTRL_VINR_ALL : GSWIP_PCE_VCTRL_VINR_TAGGED;
+	regmap_write_bits(priv->gswip, GSWIP_PCE_VCTRL(port),
+			  GSWIP_PCE_VCTRL_VINR,
+			  FIELD_PREP(GSWIP_PCE_VCTRL_VINR, vinr));
+
+	/* Note that in GSWIP 2.2 VLAN mode the VID needs to be programmed
+	 * directly instead of referencing the index in the Active VLAN Tablet.
+	 * However, without the VLANMD bit (9) in PCE_GCTRL_1 (0x457) even
+	 * GSWIP 2.2 and newer hardware maintain the GSWIP 2.1 behavior.
+	 */
+	regmap_write(priv->gswip, GSWIP_PCE_DEFPVID(port), idx);
+}
+
+static int gswip_port_vlan_filtering(struct dsa_switch *ds, int port,
+				     bool vlan_filtering,
+				     struct netlink_ext_ack *extack)
+{
+	struct gswip_priv *priv = ds->priv;
+
+	if (vlan_filtering) {
+		/* Use tag based VLAN */
+		regmap_write_bits(priv->gswip, GSWIP_PCE_VCTRL(port),
+				  GSWIP_PCE_VCTRL_VSR |
+				  GSWIP_PCE_VCTRL_UVR |
+				  GSWIP_PCE_VCTRL_VIMR |
+				  GSWIP_PCE_VCTRL_VEMR |
+				  GSWIP_PCE_VCTRL_VID0,
+				  GSWIP_PCE_VCTRL_UVR |
+				  GSWIP_PCE_VCTRL_VIMR |
+				  GSWIP_PCE_VCTRL_VEMR |
+				  GSWIP_PCE_VCTRL_VID0);
+		regmap_clear_bits(priv->gswip, GSWIP_PCE_PCTRL_0p(port),
+				  GSWIP_PCE_PCTRL_0_TVM);
+	} else {
+		/* Use port based VLAN */
+		regmap_write_bits(priv->gswip, GSWIP_PCE_VCTRL(port),
+				  GSWIP_PCE_VCTRL_UVR |
+				  GSWIP_PCE_VCTRL_VIMR |
+				  GSWIP_PCE_VCTRL_VEMR |
+				  GSWIP_PCE_VCTRL_VID0 |
+				  GSWIP_PCE_VCTRL_VSR,
+				  GSWIP_PCE_VCTRL_VSR);
+		regmap_set_bits(priv->gswip, GSWIP_PCE_PCTRL_0p(port),
+				GSWIP_PCE_PCTRL_0_TVM);
+	}
+
+	gswip_port_commit_pvid(priv, port);
+
+	return 0;
+}
+
+static void gswip_mii_delay_setup(struct gswip_priv *priv, struct dsa_port *dp,
+				  phy_interface_t interface)
+{
+	u32 tx_delay = GSWIP_MII_PCDU_TXDLY_DEFAULT;
+	u32 rx_delay = GSWIP_MII_PCDU_RXDLY_DEFAULT;
+	struct device_node *port_dn = dp->dn;
+	u16 mii_pcdu_reg;
+
+	/* As MII_PCDU registers only exist for MII ports, silently return
+	 * unless the port is an MII port
+	 */
+	if (!(priv->hw_info->mii_ports & BIT(dp->index)))
+		return;
+
+	switch (dp->index + priv->hw_info->mii_port_reg_offset) {
+	case 0:
+		mii_pcdu_reg = GSWIP_MII_PCDU0;
+		break;
+	case 1:
+		mii_pcdu_reg = GSWIP_MII_PCDU1;
+		break;
+	case 5:
+		mii_pcdu_reg = GSWIP_MII_PCDU5;
+		break;
+	default:
+		return;
+	}
+
+	/* legacy code to set default delays according to the interface mode */
+	switch (interface) {
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		tx_delay = 0;
+		rx_delay = 0;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		rx_delay = 0;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		tx_delay = 0;
+		break;
+	default:
+		break;
+	}
+
+	/* allow settings delays using device tree properties */
+	of_property_read_u32(port_dn, "rx-internal-delay-ps", &rx_delay);
+	of_property_read_u32(port_dn, "tx-internal-delay-ps", &tx_delay);
+
+	regmap_write_bits(priv->mii, mii_pcdu_reg,
+			  GSWIP_MII_PCDU_TXDLY_MASK |
+			  GSWIP_MII_PCDU_RXDLY_MASK,
+			  GSWIP_MII_PCDU_TXDLY(tx_delay) |
+			  GSWIP_MII_PCDU_RXDLY(rx_delay));
+}
+
+static int gswip_setup(struct dsa_switch *ds)
+{
+	unsigned int cpu_ports = dsa_cpu_ports(ds);
+	struct gswip_priv *priv = ds->priv;
+	struct dsa_port *cpu_dp;
+	int err, i;
+
+	regmap_write(priv->gswip, GSWIP_SWRES, GSWIP_SWRES_R0);
+	usleep_range(5000, 10000);
+	regmap_write(priv->gswip, GSWIP_SWRES, 0);
+
+	/* disable port fetch/store dma on all ports */
+	for (i = 0; i < priv->hw_info->max_ports; i++) {
+		gswip_port_disable(ds, i);
+		gswip_port_vlan_filtering(ds, i, false, NULL);
+	}
+
+	/* enable Switch */
+	regmap_set_bits(priv->mdio, GSWIP_MDIO_GLOB, GSWIP_MDIO_GLOB_ENABLE);
+
+	err = gswip_pce_load_microcode(priv);
+	if (err) {
+		dev_err(priv->dev, "writing PCE microcode failed, %i\n", err);
+		return err;
+	}
+
+	/* Default unknown Broadcast/Multicast/Unicast port maps */
+	regmap_write(priv->gswip, GSWIP_PCE_PMAP1, cpu_ports);
+	regmap_write(priv->gswip, GSWIP_PCE_PMAP2, cpu_ports);
+	regmap_write(priv->gswip, GSWIP_PCE_PMAP3, cpu_ports);
+
+	/* Deactivate MDIO PHY auto polling. Some PHYs as the AR8030 have an
+	 * interoperability problem with this auto polling mechanism because
+	 * their status registers think that the link is in a different state
+	 * than it actually is. For the AR8030 it has the BMSR_ESTATEN bit set
+	 * as well as ESTATUS_1000_TFULL and ESTATUS_1000_XFULL. This makes the
+	 * auto polling state machine consider the link being negotiated with
+	 * 1Gbit/s. Since the PHY itself is a Fast Ethernet RMII PHY this leads
+	 * to the switch port being completely dead (RX and TX are both not
+	 * working).
+	 * Also with various other PHY / port combinations (PHY11G GPHY, PHY22F
+	 * GPHY, external RGMII PEF7071/7072) any traffic would stop. Sometimes
+	 * it would work fine for a few minutes to hours and then stop, on
+	 * other device it would no traffic could be sent or received at all.
+	 * Testing shows that when PHY auto polling is disabled these problems
+	 * go away.
+	 */
+	regmap_write(priv->mdio, GSWIP_MDIO_MDC_CFG0, 0x0);
+
+	/* Configure the MDIO Clock 2.5 MHz */
+	regmap_write_bits(priv->mdio, GSWIP_MDIO_MDC_CFG1, 0xff, 0x09);
+
+	/* bring up the mdio bus */
+	err = gswip_mdio(priv);
+	if (err) {
+		dev_err(priv->dev, "mdio bus setup failed\n");
+		return err;
+	}
+
+	/* Disable the xMII interface and clear it's isolation bit */
+	for (i = 0; i < priv->hw_info->max_ports; i++)
+		gswip_mii_mask_cfg(priv,
+				   GSWIP_MII_CFG_EN | GSWIP_MII_CFG_ISOLATE,
+				   0, i);
+
+	dsa_switch_for_each_cpu_port(cpu_dp, ds) {
+		/* enable special tag insertion on cpu port */
+		regmap_set_bits(priv->gswip, GSWIP_FDMA_PCTRLp(cpu_dp->index),
+				GSWIP_FDMA_PCTRL_STEN);
+
+		/* accept special tag in ingress direction */
+		regmap_set_bits(priv->gswip,
+				GSWIP_PCE_PCTRL_0p(cpu_dp->index),
+				GSWIP_PCE_PCTRL_0_INGRESS);
+	}
+
+	regmap_set_bits(priv->gswip, GSWIP_BM_QUEUE_GCTRL,
+			GSWIP_BM_QUEUE_GCTRL_GL_MOD);
+
+	/* VLAN aware Switching */
+	regmap_set_bits(priv->gswip, GSWIP_PCE_GCTRL_0,
+			GSWIP_PCE_GCTRL_0_VLAN);
+
+	/* Flush MAC Table */
+	regmap_set_bits(priv->gswip, GSWIP_PCE_GCTRL_0,
+			GSWIP_PCE_GCTRL_0_MTFL);
+
+	err = gswip_switch_r_timeout(priv, GSWIP_PCE_GCTRL_0,
+				     GSWIP_PCE_GCTRL_0_MTFL);
+	if (err) {
+		dev_err(priv->dev, "MAC flushing didn't finish\n");
+		return err;
+	}
+
+	ds->mtu_enforcement_ingress = true;
+
+	return 0;
+}
+
+static enum dsa_tag_protocol gswip_get_tag_protocol(struct dsa_switch *ds,
+						    int port,
+						    enum dsa_tag_protocol mp)
+{
+	struct gswip_priv *priv = ds->priv;
+
+	return priv->hw_info->tag_protocol;
+}
+
+static int gswip_vlan_active_create(struct gswip_priv *priv,
+				    struct net_device *bridge,
+				    int fid, u16 vid)
+{
+	struct gswip_pce_table_entry vlan_active = {0,};
+	unsigned int max_ports = priv->hw_info->max_ports;
+	int idx = -1;
+	int err;
+	int i;
+
+	/* Look for a free slot */
+	for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) {
+		if (!priv->vlans[i].bridge) {
+			idx = i;
+			break;
+		}
+	}
+
+	if (idx == -1)
+		return -ENOSPC;
+
+	if (fid == -1)
+		fid = idx;
+
+	vlan_active.index = idx;
+	vlan_active.table = GSWIP_TABLE_ACTIVE_VLAN;
+	vlan_active.key[0] = vid;
+	vlan_active.val[0] = fid;
+	vlan_active.valid = true;
+
+	err = gswip_pce_table_entry_write(priv, &vlan_active);
+	if (err) {
+		dev_err(priv->dev, "failed to write active VLAN: %d\n",	err);
+		return err;
+	}
+
+	priv->vlans[idx].bridge = bridge;
+	priv->vlans[idx].vid = vid;
+	priv->vlans[idx].fid = fid;
+
+	return idx;
+}
+
+static int gswip_vlan_active_remove(struct gswip_priv *priv, int idx)
+{
+	struct gswip_pce_table_entry vlan_active = {0,};
+	int err;
+
+	vlan_active.index = idx;
+	vlan_active.table = GSWIP_TABLE_ACTIVE_VLAN;
+	vlan_active.valid = false;
+	err = gswip_pce_table_entry_write(priv, &vlan_active);
+	if (err)
+		dev_err(priv->dev, "failed to delete active VLAN: %d\n", err);
+	priv->vlans[idx].bridge = NULL;
+
+	return err;
+}
+
+static int gswip_vlan_add(struct gswip_priv *priv, struct net_device *bridge,
+			  int port, u16 vid, bool untagged, bool pvid,
+			  bool vlan_aware)
+{
+	struct gswip_pce_table_entry vlan_mapping = {0,};
+	unsigned int max_ports = priv->hw_info->max_ports;
+	unsigned int cpu_ports = dsa_cpu_ports(priv->ds);
+	bool active_vlan_created = false;
+	int fid = -1, idx = -1;
+	int i, err;
+
+	/* Check if there is already a page for this bridge */
+	for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) {
+		if (priv->vlans[i].bridge == bridge) {
+			if (vlan_aware) {
+				if (fid != -1 && fid != priv->vlans[i].fid)
+					dev_err(priv->dev, "one bridge with multiple flow ids\n");
+				fid = priv->vlans[i].fid;
+			}
+			if (priv->vlans[i].vid == vid) {
+				idx = i;
+				break;
+			}
+		}
+	}
+
+	/* If this bridge is not programmed yet, add a Active VLAN table
+	 * entry in a free slot and prepare the VLAN mapping table entry.
+	 */
+	if (idx == -1) {
+		idx = gswip_vlan_active_create(priv, bridge, fid, vid);
+		if (idx < 0)
+			return idx;
+		active_vlan_created = true;
+
+		vlan_mapping.index = idx;
+		vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING;
+	} else {
+		/* Read the existing VLAN mapping entry from the switch */
+		vlan_mapping.index = idx;
+		vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING;
+		err = gswip_pce_table_entry_read(priv, &vlan_mapping);
+		if (err) {
+			dev_err(priv->dev, "failed to read VLAN mapping: %d\n",
+				err);
+			return err;
+		}
+	}
+
+	/* VLAN ID byte, maps to the VLAN ID of vlan active table */
+	vlan_mapping.val[0] = vid;
+	/* Update the VLAN mapping entry and write it to the switch */
+	vlan_mapping.val[1] |= cpu_ports;
+	vlan_mapping.val[1] |= BIT(port);
+	if (vlan_aware)
+		vlan_mapping.val[2] |= cpu_ports;
+	if (untagged)
+		vlan_mapping.val[2] &= ~BIT(port);
+	else
+		vlan_mapping.val[2] |= BIT(port);
+	err = gswip_pce_table_entry_write(priv, &vlan_mapping);
+	if (err) {
+		dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err);
+		/* In case an Active VLAN was creaetd delete it again */
+		if (active_vlan_created)
+			gswip_vlan_active_remove(priv, idx);
+		return err;
+	}
+
+	gswip_port_commit_pvid(priv, port);
+
+	return 0;
+}
+
+static int gswip_vlan_remove(struct gswip_priv *priv,
+			     struct net_device *bridge, int port,
+			     u16 vid)
+{
+	struct gswip_pce_table_entry vlan_mapping = {0,};
+	unsigned int max_ports = priv->hw_info->max_ports;
+	int idx = -1;
+	int i;
+	int err;
+
+	/* Check if there is already a page for this bridge */
+	for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) {
+		if (priv->vlans[i].bridge == bridge &&
+		    priv->vlans[i].vid == vid) {
+			idx = i;
+			break;
+		}
+	}
+
+	if (idx == -1) {
+		dev_err(priv->dev, "Port %d cannot find VID %u of bridge %s\n",
+			port, vid, bridge ? bridge->name : "(null)");
+		return -ENOENT;
+	}
+
+	vlan_mapping.index = idx;
+	vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING;
+	err = gswip_pce_table_entry_read(priv, &vlan_mapping);
+	if (err) {
+		dev_err(priv->dev, "failed to read VLAN mapping: %d\n",	err);
+		return err;
+	}
+
+	vlan_mapping.val[1] &= ~BIT(port);
+	vlan_mapping.val[2] &= ~BIT(port);
+	err = gswip_pce_table_entry_write(priv, &vlan_mapping);
+	if (err) {
+		dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err);
+		return err;
+	}
+
+	/* In case all ports are removed from the bridge, remove the VLAN */
+	if (!(vlan_mapping.val[1] & ~dsa_cpu_ports(priv->ds))) {
+		err = gswip_vlan_active_remove(priv, idx);
+		if (err) {
+			dev_err(priv->dev, "failed to write active VLAN: %d\n",
+				err);
+			return err;
+		}
+	}
+
+	gswip_port_commit_pvid(priv, port);
+
+	return 0;
+}
+
+static int gswip_port_bridge_join(struct dsa_switch *ds, int port,
+				  struct dsa_bridge bridge,
+				  bool *tx_fwd_offload,
+				  struct netlink_ext_ack *extack)
+{
+	struct net_device *br = bridge.dev;
+	struct gswip_priv *priv = ds->priv;
+	int err;
+
+	/* Set up the VLAN for VLAN-unaware bridging for this port, and remove
+	 * it from the "single-port bridge" through which it was operating as
+	 * standalone.
+	 */
+	err = gswip_vlan_add(priv, br, port, GSWIP_VLAN_UNAWARE_PVID,
+			     true, true, false);
+	if (err)
+		return err;
+
+	return gswip_add_single_port_br(priv, port, false);
+}
+
+static void gswip_port_bridge_leave(struct dsa_switch *ds, int port,
+				    struct dsa_bridge bridge)
+{
+	struct net_device *br = bridge.dev;
+	struct gswip_priv *priv = ds->priv;
+
+	/* Add the port back to the "single-port bridge", and remove it from
+	 * the VLAN-unaware PVID created for this bridge.
+	 */
+	gswip_add_single_port_br(priv, port, true);
+	gswip_vlan_remove(priv, br, port, GSWIP_VLAN_UNAWARE_PVID);
+}
+
+static int gswip_port_vlan_prepare(struct dsa_switch *ds, int port,
+				   const struct switchdev_obj_port_vlan *vlan,
+				   struct netlink_ext_ack *extack)
+{
+	struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port));
+	struct gswip_priv *priv = ds->priv;
+	unsigned int max_ports = priv->hw_info->max_ports;
+	int pos = max_ports;
+	int i, idx = -1;
+
+	/* We only support VLAN filtering on bridges */
+	if (!dsa_is_cpu_port(ds, port) && !bridge)
+		return -EOPNOTSUPP;
+
+	/* Check if there is already a page for this VLAN */
+	for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) {
+		if (priv->vlans[i].bridge == bridge &&
+		    priv->vlans[i].vid == vlan->vid) {
+			idx = i;
+			break;
+		}
+	}
+
+	/* If this VLAN is not programmed yet, we have to reserve
+	 * one entry in the VLAN table. Make sure we start at the
+	 * next position round.
+	 */
+	if (idx == -1) {
+		/* Look for a free slot */
+		for (; pos < ARRAY_SIZE(priv->vlans); pos++) {
+			if (!priv->vlans[pos].bridge) {
+				idx = pos;
+				pos++;
+				break;
+			}
+		}
+
+		if (idx == -1) {
+			NL_SET_ERR_MSG_MOD(extack, "No slot in VLAN table");
+			return -ENOSPC;
+		}
+	}
+
+	return 0;
+}
+
+static int gswip_port_vlan_add(struct dsa_switch *ds, int port,
+			       const struct switchdev_obj_port_vlan *vlan,
+			       struct netlink_ext_ack *extack)
+{
+	struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port));
+	struct gswip_priv *priv = ds->priv;
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+	int err;
+
+	if (vlan->vid == GSWIP_VLAN_UNAWARE_PVID)
+		return 0;
+
+	err = gswip_port_vlan_prepare(ds, port, vlan, extack);
+	if (err)
+		return err;
+
+	/* We have to receive all packets on the CPU port and should not
+	 * do any VLAN filtering here. This is also called with bridge
+	 * NULL and then we do not know for which bridge to configure
+	 * this.
+	 */
+	if (dsa_is_cpu_port(ds, port))
+		return 0;
+
+	return gswip_vlan_add(priv, bridge, port, vlan->vid, untagged, pvid,
+			      true);
+}
+
+static int gswip_port_vlan_del(struct dsa_switch *ds, int port,
+			       const struct switchdev_obj_port_vlan *vlan)
+{
+	struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port));
+	struct gswip_priv *priv = ds->priv;
+
+	if (vlan->vid == GSWIP_VLAN_UNAWARE_PVID)
+		return 0;
+
+	/* We have to receive all packets on the CPU port and should not
+	 * do any VLAN filtering here. This is also called with bridge
+	 * NULL and then we do not know for which bridge to configure
+	 * this.
+	 */
+	if (dsa_is_cpu_port(ds, port))
+		return 0;
+
+	return gswip_vlan_remove(priv, bridge, port, vlan->vid);
+}
+
+static void gswip_port_fast_age(struct dsa_switch *ds, int port)
+{
+	struct gswip_priv *priv = ds->priv;
+	struct gswip_pce_table_entry mac_bridge = {0,};
+	int i;
+	int err;
+
+	for (i = 0; i < 2048; i++) {
+		mac_bridge.table = GSWIP_TABLE_MAC_BRIDGE;
+		mac_bridge.index = i;
+
+		err = gswip_pce_table_entry_read(priv, &mac_bridge);
+		if (err) {
+			dev_err(priv->dev, "failed to read mac bridge: %d\n",
+				err);
+			return;
+		}
+
+		if (!mac_bridge.valid)
+			continue;
+
+		if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC)
+			continue;
+
+		if (port != FIELD_GET(GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT,
+				      mac_bridge.val[0]))
+			continue;
+
+		mac_bridge.valid = false;
+		err = gswip_pce_table_entry_write(priv, &mac_bridge);
+		if (err) {
+			dev_err(priv->dev, "failed to write mac bridge: %d\n",
+				err);
+			return;
+		}
+	}
+}
+
+static void gswip_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
+{
+	struct gswip_priv *priv = ds->priv;
+	u32 stp_state;
+
+	switch (state) {
+	case BR_STATE_DISABLED:
+		regmap_clear_bits(priv->gswip, GSWIP_SDMA_PCTRLp(port),
+				  GSWIP_SDMA_PCTRL_EN);
+		return;
+	case BR_STATE_BLOCKING:
+	case BR_STATE_LISTENING:
+		stp_state = GSWIP_PCE_PCTRL_0_PSTATE_LISTEN;
+		break;
+	case BR_STATE_LEARNING:
+		stp_state = GSWIP_PCE_PCTRL_0_PSTATE_LEARNING;
+		break;
+	case BR_STATE_FORWARDING:
+		stp_state = GSWIP_PCE_PCTRL_0_PSTATE_FORWARDING;
+		break;
+	default:
+		dev_err(priv->dev, "invalid STP state: %d\n", state);
+		return;
+	}
+
+	regmap_set_bits(priv->gswip, GSWIP_SDMA_PCTRLp(port),
+			GSWIP_SDMA_PCTRL_EN);
+	regmap_write_bits(priv->gswip, GSWIP_PCE_PCTRL_0p(port),
+			  GSWIP_PCE_PCTRL_0_PSTATE_MASK,
+			  stp_state);
+}
+
+static int gswip_port_fdb(struct dsa_switch *ds, int port,
+			  struct net_device *bridge, const unsigned char *addr,
+			  u16 vid, bool add)
+{
+	struct gswip_priv *priv = ds->priv;
+	struct gswip_pce_table_entry mac_bridge = {0,};
+	unsigned int max_ports = priv->hw_info->max_ports;
+	int fid = -1;
+	int i;
+	int err;
+
+	for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) {
+		if (priv->vlans[i].bridge == bridge) {
+			fid = priv->vlans[i].fid;
+			break;
+		}
+	}
+
+	if (fid == -1) {
+		dev_err(priv->dev, "no FID found for bridge %s\n",
+			bridge->name);
+		return -EINVAL;
+	}
+
+	mac_bridge.table = GSWIP_TABLE_MAC_BRIDGE;
+	mac_bridge.key_mode = true;
+	mac_bridge.key[0] = addr[5] | (addr[4] << 8);
+	mac_bridge.key[1] = addr[3] | (addr[2] << 8);
+	mac_bridge.key[2] = addr[1] | (addr[0] << 8);
+	mac_bridge.key[3] = FIELD_PREP(GSWIP_TABLE_MAC_BRIDGE_KEY3_FID, fid);
+	mac_bridge.val[0] = add ? BIT(port) : 0; /* port map */
+	if (GSWIP_VERSION_GE(priv, GSWIP_VERSION_2_2_ETC))
+		mac_bridge.val[1] = add ? (GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC |
+					   GSWIP_TABLE_MAC_BRIDGE_VAL1_VALID) : 0;
+	else
+		mac_bridge.val[1] = GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC;
+
+	mac_bridge.valid = add;
+
+	err = gswip_pce_table_entry_write(priv, &mac_bridge);
+	if (err)
+		dev_err(priv->dev, "failed to write mac bridge: %d\n", err);
+
+	return err;
+}
+
+static int gswip_port_fdb_add(struct dsa_switch *ds, int port,
+			      const unsigned char *addr, u16 vid,
+			      struct dsa_db db)
+{
+	if (db.type != DSA_DB_BRIDGE)
+		return -EOPNOTSUPP;
+
+	return gswip_port_fdb(ds, port, db.bridge.dev, addr, vid, true);
+}
+
+static int gswip_port_fdb_del(struct dsa_switch *ds, int port,
+			      const unsigned char *addr, u16 vid,
+			      struct dsa_db db)
+{
+	if (db.type != DSA_DB_BRIDGE)
+		return -EOPNOTSUPP;
+
+	return gswip_port_fdb(ds, port, db.bridge.dev, addr, vid, false);
+}
+
+static int gswip_port_fdb_dump(struct dsa_switch *ds, int port,
+			       dsa_fdb_dump_cb_t *cb, void *data)
+{
+	struct gswip_priv *priv = ds->priv;
+	struct gswip_pce_table_entry mac_bridge = {0,};
+	unsigned char addr[ETH_ALEN];
+	int i;
+	int err;
+
+	for (i = 0; i < 2048; i++) {
+		mac_bridge.table = GSWIP_TABLE_MAC_BRIDGE;
+		mac_bridge.index = i;
+
+		err = gswip_pce_table_entry_read(priv, &mac_bridge);
+		if (err) {
+			dev_err(priv->dev,
+				"failed to read mac bridge entry %d: %d\n",
+				i, err);
+			return err;
+		}
+
+		if (!mac_bridge.valid)
+			continue;
+
+		addr[5] = mac_bridge.key[0] & 0xff;
+		addr[4] = (mac_bridge.key[0] >> 8) & 0xff;
+		addr[3] = mac_bridge.key[1] & 0xff;
+		addr[2] = (mac_bridge.key[1] >> 8) & 0xff;
+		addr[1] = mac_bridge.key[2] & 0xff;
+		addr[0] = (mac_bridge.key[2] >> 8) & 0xff;
+		if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC) {
+			if (mac_bridge.val[0] & BIT(port)) {
+				err = cb(addr, 0, true, data);
+				if (err)
+					return err;
+			}
+		} else {
+			if (port == FIELD_GET(GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT,
+					      mac_bridge.val[0])) {
+				err = cb(addr, 0, false, data);
+				if (err)
+					return err;
+			}
+		}
+	}
+	return 0;
+}
+
+static int gswip_port_max_mtu(struct dsa_switch *ds, int port)
+{
+	/* Includes 8 bytes for special header. */
+	return GSWIP_MAX_PACKET_LENGTH - VLAN_ETH_HLEN - ETH_FCS_LEN;
+}
+
+static int gswip_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
+{
+	struct gswip_priv *priv = ds->priv;
+
+	/* CPU port always has maximum mtu of user ports, so use it to set
+	 * switch frame size, including 8 byte special header.
+	 */
+	if (dsa_is_cpu_port(ds, port)) {
+		new_mtu += 8;
+		regmap_write(priv->gswip, GSWIP_MAC_FLEN,
+			     VLAN_ETH_HLEN + new_mtu + ETH_FCS_LEN);
+	}
+
+	/* Enable MLEN for ports with non-standard MTUs, including the special
+	 * header on the CPU port added above.
+	 */
+	if (new_mtu != ETH_DATA_LEN)
+		regmap_set_bits(priv->gswip, GSWIP_MAC_CTRL_2p(port),
+				GSWIP_MAC_CTRL_2_MLEN);
+	else
+		regmap_clear_bits(priv->gswip, GSWIP_MAC_CTRL_2p(port),
+				  GSWIP_MAC_CTRL_2_MLEN);
+
+	return 0;
+}
+
+static void gswip_phylink_get_caps(struct dsa_switch *ds, int port,
+				   struct phylink_config *config)
+{
+	struct gswip_priv *priv = ds->priv;
+
+	priv->hw_info->phylink_get_caps(ds, port, config);
+}
+
+static void gswip_port_set_link(struct gswip_priv *priv, int port, bool link)
+{
+	u32 mdio_phy;
+
+	if (link)
+		mdio_phy = GSWIP_MDIO_PHY_LINK_UP;
+	else
+		mdio_phy = GSWIP_MDIO_PHY_LINK_DOWN;
+
+	regmap_write_bits(priv->mdio, GSWIP_MDIO_PHYp(port),
+			  GSWIP_MDIO_PHY_LINK_MASK, mdio_phy);
+}
+
+static void gswip_port_set_speed(struct gswip_priv *priv, int port, int speed,
+				 phy_interface_t interface)
+{
+	u32 mdio_phy = 0, mii_cfg = 0, mac_ctrl_0 = 0;
+
+	switch (speed) {
+	case SPEED_10:
+		mdio_phy = GSWIP_MDIO_PHY_SPEED_M10;
+
+		if (interface == PHY_INTERFACE_MODE_RMII)
+			mii_cfg = GSWIP_MII_CFG_RATE_M50;
+		else
+			mii_cfg = GSWIP_MII_CFG_RATE_M2P5;
+
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII;
+		break;
+
+	case SPEED_100:
+		mdio_phy = GSWIP_MDIO_PHY_SPEED_M100;
+
+		if (interface == PHY_INTERFACE_MODE_RMII)
+			mii_cfg = GSWIP_MII_CFG_RATE_M50;
+		else
+			mii_cfg = GSWIP_MII_CFG_RATE_M25;
+
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII;
+		break;
+
+	case SPEED_1000:
+		mdio_phy = GSWIP_MDIO_PHY_SPEED_G1;
+
+		mii_cfg = GSWIP_MII_CFG_RATE_M125;
+
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_RGMII;
+		break;
+	}
+
+	regmap_write_bits(priv->mdio, GSWIP_MDIO_PHYp(port),
+			  GSWIP_MDIO_PHY_SPEED_MASK, mdio_phy);
+	gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_RATE_MASK, mii_cfg, port);
+	regmap_write_bits(priv->gswip, GSWIP_MAC_CTRL_0p(port),
+			  GSWIP_MAC_CTRL_0_GMII_MASK, mac_ctrl_0);
+}
+
+static void gswip_port_set_duplex(struct gswip_priv *priv, int port, int duplex)
+{
+	u32 mac_ctrl_0, mdio_phy;
+
+	if (duplex == DUPLEX_FULL) {
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_EN;
+		mdio_phy = GSWIP_MDIO_PHY_FDUP_EN;
+	} else {
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_DIS;
+		mdio_phy = GSWIP_MDIO_PHY_FDUP_DIS;
+	}
+
+	regmap_write_bits(priv->gswip, GSWIP_MAC_CTRL_0p(port),
+			  GSWIP_MAC_CTRL_0_FDUP_MASK, mac_ctrl_0);
+	regmap_write_bits(priv->mdio, GSWIP_MDIO_PHYp(port),
+			  GSWIP_MDIO_PHY_FDUP_MASK, mdio_phy);
+}
+
+static void gswip_port_set_pause(struct gswip_priv *priv, int port,
+				 bool tx_pause, bool rx_pause)
+{
+	u32 mac_ctrl_0, mdio_phy;
+
+	if (tx_pause && rx_pause) {
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RXTX;
+		mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN |
+			   GSWIP_MDIO_PHY_FCONRX_EN;
+	} else if (tx_pause) {
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_TX;
+		mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN |
+			   GSWIP_MDIO_PHY_FCONRX_DIS;
+	} else if (rx_pause) {
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RX;
+		mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS |
+			   GSWIP_MDIO_PHY_FCONRX_EN;
+	} else {
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_NONE;
+		mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS |
+			   GSWIP_MDIO_PHY_FCONRX_DIS;
+	}
+
+	regmap_write_bits(priv->gswip, GSWIP_MAC_CTRL_0p(port),
+			  GSWIP_MAC_CTRL_0_FCON_MASK, mac_ctrl_0);
+	regmap_write_bits(priv->mdio, GSWIP_MDIO_PHYp(port),
+			  GSWIP_MDIO_PHY_FCONTX_MASK | GSWIP_MDIO_PHY_FCONRX_MASK,
+			  mdio_phy);
+}
+
+static void gswip_phylink_mac_config(struct phylink_config *config,
+				     unsigned int mode,
+				     const struct phylink_link_state *state)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct gswip_priv *priv = dp->ds->priv;
+	int port = dp->index;
+	u32 miicfg = 0;
+
+	miicfg |= GSWIP_MII_CFG_LDCLKDIS;
+
+	switch (state->interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_1000BASEX:
+	case PHY_INTERFACE_MODE_2500BASEX:
+		return;
+	case PHY_INTERFACE_MODE_MII:
+	case PHY_INTERFACE_MODE_INTERNAL:
+		miicfg |= GSWIP_MII_CFG_MODE_MIIM;
+		break;
+	case PHY_INTERFACE_MODE_REVMII:
+		miicfg |= GSWIP_MII_CFG_MODE_MIIP;
+		break;
+	case PHY_INTERFACE_MODE_RMII:
+		miicfg |= GSWIP_MII_CFG_MODE_RMIIM;
+		if (of_property_read_bool(dp->dn, "maxlinear,rmii-refclk-out"))
+			miicfg |= GSWIP_MII_CFG_RMII_CLK;
+		break;
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		miicfg |= GSWIP_MII_CFG_MODE_RGMII;
+		break;
+	case PHY_INTERFACE_MODE_GMII:
+		miicfg |= GSWIP_MII_CFG_MODE_GMII;
+		break;
+	default:
+		dev_err(dp->ds->dev,
+			"Unsupported interface: %d\n", state->interface);
+		return;
+	}
+
+	gswip_mii_mask_cfg(priv,
+			   GSWIP_MII_CFG_MODE_MASK | GSWIP_MII_CFG_RMII_CLK |
+			   GSWIP_MII_CFG_RGMII_IBS | GSWIP_MII_CFG_LDCLKDIS,
+			   miicfg, port);
+
+	gswip_mii_delay_setup(priv, dp, state->interface);
+}
+
+static void gswip_phylink_mac_link_down(struct phylink_config *config,
+					unsigned int mode,
+					phy_interface_t interface)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct gswip_priv *priv = dp->ds->priv;
+	int port = dp->index;
+
+	gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, port);
+
+	if (!dsa_port_is_cpu(dp))
+		gswip_port_set_link(priv, port, false);
+}
+
+static void gswip_phylink_mac_link_up(struct phylink_config *config,
+				      struct phy_device *phydev,
+				      unsigned int mode,
+				      phy_interface_t interface,
+				      int speed, int duplex,
+				      bool tx_pause, bool rx_pause)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct gswip_priv *priv = dp->ds->priv;
+	int port = dp->index;
+
+	if (!dsa_port_is_cpu(dp) || interface != PHY_INTERFACE_MODE_INTERNAL) {
+		gswip_port_set_link(priv, port, true);
+		gswip_port_set_speed(priv, port, speed, interface);
+		gswip_port_set_duplex(priv, port, duplex);
+		gswip_port_set_pause(priv, port, tx_pause, rx_pause);
+	}
+
+	gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, GSWIP_MII_CFG_EN, port);
+}
+
+static void gswip_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+			      uint8_t *data)
+{
+	int i;
+
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(gswip_rmon_cnt); i++)
+		ethtool_puts(&data, gswip_rmon_cnt[i].name);
+}
+
+static u32 gswip_bcm_ram_entry_read(struct gswip_priv *priv, u32 table,
+				    u32 index)
+{
+	u32 result, val;
+	int err;
+
+	regmap_write(priv->gswip, GSWIP_BM_RAM_ADDR, index);
+	regmap_write_bits(priv->gswip, GSWIP_BM_RAM_CTRL,
+			  GSWIP_BM_RAM_CTRL_ADDR_MASK | GSWIP_BM_RAM_CTRL_OPMOD |
+			  GSWIP_BM_RAM_CTRL_BAS,
+			  table | GSWIP_BM_RAM_CTRL_BAS);
+
+	err = gswip_switch_r_timeout(priv, GSWIP_BM_RAM_CTRL,
+				     GSWIP_BM_RAM_CTRL_BAS);
+	if (err) {
+		dev_err(priv->dev, "timeout while reading table: %u, index: %u\n",
+			table, index);
+		return 0;
+	}
+
+	regmap_read(priv->gswip, GSWIP_BM_RAM_VAL(0), &result);
+	regmap_read(priv->gswip, GSWIP_BM_RAM_VAL(1), &val);
+	result |= val << 16;
+
+	return result;
+}
+
+static void gswip_get_ethtool_stats(struct dsa_switch *ds, int port,
+				    uint64_t *data)
+{
+	struct gswip_priv *priv = ds->priv;
+	const struct gswip_rmon_cnt_desc *rmon_cnt;
+	int i;
+	u64 high;
+
+	for (i = 0; i < ARRAY_SIZE(gswip_rmon_cnt); i++) {
+		rmon_cnt = &gswip_rmon_cnt[i];
+
+		data[i] = gswip_bcm_ram_entry_read(priv, port,
+						   rmon_cnt->offset);
+		if (rmon_cnt->size == 2) {
+			high = gswip_bcm_ram_entry_read(priv, port,
+							rmon_cnt->offset + 1);
+			data[i] |= high << 32;
+		}
+	}
+}
+
+static int gswip_get_sset_count(struct dsa_switch *ds, int port, int sset)
+{
+	if (sset != ETH_SS_STATS)
+		return 0;
+
+	return ARRAY_SIZE(gswip_rmon_cnt);
+}
+
+static int gswip_set_mac_eee(struct dsa_switch *ds, int port,
+			     struct ethtool_keee *e)
+{
+	if (e->tx_lpi_timer > 0x7f)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void gswip_phylink_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct gswip_priv *priv = dp->ds->priv;
+
+	regmap_clear_bits(priv->gswip, GSWIP_MAC_CTRL_4p(dp->index),
+			  GSWIP_MAC_CTRL_4_LPIEN);
+}
+
+static int gswip_phylink_mac_enable_tx_lpi(struct phylink_config *config,
+					   u32 timer, bool tx_clock_stop)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct gswip_priv *priv = dp->ds->priv;
+
+	return regmap_update_bits(priv->gswip, GSWIP_MAC_CTRL_4p(dp->index),
+				  GSWIP_MAC_CTRL_4_LPIEN |
+				  GSWIP_MAC_CTRL_4_GWAIT_MASK |
+				  GSWIP_MAC_CTRL_4_WAIT_MASK,
+				  GSWIP_MAC_CTRL_4_LPIEN |
+				  GSWIP_MAC_CTRL_4_GWAIT(timer) |
+				  GSWIP_MAC_CTRL_4_WAIT(timer));
+}
+
+static bool gswip_support_eee(struct dsa_switch *ds, int port)
+{
+	struct gswip_priv *priv = ds->priv;
+
+	if (GSWIP_VERSION_GE(priv, GSWIP_VERSION_2_2))
+		return true;
+
+	return false;
+}
+
+static struct phylink_pcs *gswip_phylink_mac_select_pcs(struct phylink_config *config,
+							phy_interface_t interface)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct gswip_priv *priv = dp->ds->priv;
+
+	if (priv->hw_info->mac_select_pcs)
+		return priv->hw_info->mac_select_pcs(config, interface);
+
+	return NULL;
+}
+
+static const struct phylink_mac_ops gswip_phylink_mac_ops = {
+	.mac_config		= gswip_phylink_mac_config,
+	.mac_link_down		= gswip_phylink_mac_link_down,
+	.mac_link_up		= gswip_phylink_mac_link_up,
+	.mac_disable_tx_lpi	= gswip_phylink_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi	= gswip_phylink_mac_enable_tx_lpi,
+	.mac_select_pcs		= gswip_phylink_mac_select_pcs,
+};
+
+static const struct dsa_switch_ops gswip_switch_ops = {
+	.get_tag_protocol	= gswip_get_tag_protocol,
+	.setup			= gswip_setup,
+	.port_setup		= gswip_port_setup,
+	.port_enable		= gswip_port_enable,
+	.port_disable		= gswip_port_disable,
+	.port_pre_bridge_flags	= gswip_port_pre_bridge_flags,
+	.port_bridge_flags	= gswip_port_bridge_flags,
+	.port_bridge_join	= gswip_port_bridge_join,
+	.port_bridge_leave	= gswip_port_bridge_leave,
+	.port_fast_age		= gswip_port_fast_age,
+	.port_vlan_filtering	= gswip_port_vlan_filtering,
+	.port_vlan_add		= gswip_port_vlan_add,
+	.port_vlan_del		= gswip_port_vlan_del,
+	.port_stp_state_set	= gswip_port_stp_state_set,
+	.port_fdb_add		= gswip_port_fdb_add,
+	.port_fdb_del		= gswip_port_fdb_del,
+	.port_fdb_dump		= gswip_port_fdb_dump,
+	.port_change_mtu	= gswip_port_change_mtu,
+	.port_max_mtu		= gswip_port_max_mtu,
+	.phylink_get_caps	= gswip_phylink_get_caps,
+	.get_strings		= gswip_get_strings,
+	.get_ethtool_stats	= gswip_get_ethtool_stats,
+	.get_sset_count		= gswip_get_sset_count,
+	.set_mac_eee		= gswip_set_mac_eee,
+	.support_eee		= gswip_support_eee,
+	.port_hsr_join		= dsa_port_simple_hsr_join,
+	.port_hsr_leave		= dsa_port_simple_hsr_leave,
+};
+
+void gswip_disable_switch(struct gswip_priv *priv)
+{
+	regmap_clear_bits(priv->mdio, GSWIP_MDIO_GLOB, GSWIP_MDIO_GLOB_ENABLE);
+}
+EXPORT_SYMBOL_GPL(gswip_disable_switch);
+
+static int gswip_validate_cpu_port(struct dsa_switch *ds)
+{
+	struct gswip_priv *priv = ds->priv;
+	struct dsa_port *cpu_dp;
+	int cpu_port = -1;
+
+	dsa_switch_for_each_cpu_port(cpu_dp, ds) {
+		if (cpu_port != -1)
+			return dev_err_probe(ds->dev, -EINVAL,
+					     "only a single CPU port is supported\n");
+
+		cpu_port = cpu_dp->index;
+	}
+
+	if (cpu_port == -1)
+		return dev_err_probe(ds->dev, -EINVAL, "no CPU port defined\n");
+
+	if (BIT(cpu_port) & ~priv->hw_info->allowed_cpu_ports)
+		return dev_err_probe(ds->dev, -EINVAL,
+				     "unsupported CPU port defined\n");
+
+	return 0;
+}
+
+int gswip_probe_common(struct gswip_priv *priv, u32 version)
+{
+	int err;
+
+	mutex_init(&priv->pce_table_lock);
+
+	priv->ds = devm_kzalloc(priv->dev, sizeof(*priv->ds), GFP_KERNEL);
+	if (!priv->ds)
+		return -ENOMEM;
+
+	priv->ds->dev = priv->dev;
+	priv->ds->num_ports = priv->hw_info->max_ports;
+	priv->ds->ops = &gswip_switch_ops;
+	priv->ds->phylink_mac_ops = &gswip_phylink_mac_ops;
+	priv->ds->priv = priv;
+
+	/* The hardware has the 'major/minor' version bytes in the wrong order
+	 * preventing numerical comparisons. Construct a 16-bit unsigned integer
+	 * having the REV field as most significant byte and the MOD field as
+	 * least significant byte. This is effectively swapping the two bytes of
+	 * the version variable, but other than using swab16 it doesn't affect
+	 * the source variable.
+	 */
+	priv->version = GSWIP_VERSION_REV(version) << 8 |
+			GSWIP_VERSION_MOD(version);
+
+	err = dsa_register_switch(priv->ds);
+	if (err)
+		return dev_err_probe(priv->dev, err, "dsa switch registration failed\n");
+
+	err = gswip_validate_cpu_port(priv->ds);
+	if (err)
+		goto disable_switch;
+
+	dev_info(priv->dev, "probed GSWIP version %lx mod %lx\n",
+		 GSWIP_VERSION_REV(version), GSWIP_VERSION_MOD(version));
+
+	return 0;
+
+disable_switch:
+	gswip_disable_switch(priv);
+	dsa_unregister_switch(priv->ds);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(gswip_probe_common);
+
+MODULE_AUTHOR("Hauke Mehrtens <hauke@hauke-m.de>");
+MODULE_AUTHOR("Daniel Golle <daniel@makrotopia.org>");
+MODULE_DESCRIPTION("Lantiq / Intel / MaxLinear GSWIP common functions");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/lantiq_pce.h b/drivers/net/dsa/lantiq/lantiq_pce.h
index e2be31f3672a..659f9a0638d9 100644
--- a/drivers/net/dsa/lantiq_pce.h
+++ b/drivers/net/dsa/lantiq/lantiq_pce.h
@@ -7,6 +7,8 @@
  * Copyright (C) 2017 - 2018 Hauke Mehrtens <hauke@hauke-m.de>
  */
 
+#include "lantiq_gswip.h"
+
 enum {
 	OUT_MAC0 = 0,
 	OUT_MAC1,
@@ -74,13 +76,6 @@ enum {
 	FLAG_NO,	/*13*/
 };
 
-struct gswip_pce_microcode {
-	u16 val_3;
-	u16 val_2;
-	u16 val_1;
-	u16 val_0;
-};
-
 #define MC_ENTRY(val, msk, ns, out, len, type, flags, ipv4_len) \
 	{ val, msk, ((ns) << 10 | (out) << 4 | (len) >> 1),\
 		((len) & 1) << 15 | (type) << 13 | (flags) << 9 | (ipv4_len) << 8 }
diff --git a/drivers/net/dsa/lantiq/mxl-gsw1xx.c b/drivers/net/dsa/lantiq/mxl-gsw1xx.c
new file mode 100644
index 000000000000..0816c61a47f1
--- /dev/null
+++ b/drivers/net/dsa/lantiq/mxl-gsw1xx.c
@@ -0,0 +1,733 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* DSA Driver for MaxLinear GSW1xx switch devices
+ *
+ * Copyright (C) 2025 Daniel Golle <daniel@makrotopia.org>
+ * Copyright (C) 2023 - 2024 MaxLinear Inc.
+ * Copyright (C) 2022 Snap One, LLC.  All rights reserved.
+ * Copyright (C) 2017 - 2019 Hauke Mehrtens <hauke@hauke-m.de>
+ * Copyright (C) 2012 John Crispin <john@phrozen.org>
+ * Copyright (C) 2010 Lantiq Deutschland
+ */
+
+#include <linux/bits.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/regmap.h>
+#include <net/dsa.h>
+
+#include "lantiq_gswip.h"
+#include "mxl-gsw1xx.h"
+#include "mxl-gsw1xx_pce.h"
+
+struct gsw1xx_priv {
+	struct mdio_device	*mdio_dev;
+	int			smdio_badr;
+	struct			regmap *sgmii;
+	struct			regmap *gpio;
+	struct			regmap *clk;
+	struct			regmap *shell;
+	struct			phylink_pcs pcs;
+	phy_interface_t		tbi_interface;
+	struct gswip_priv	gswip;
+};
+
+static int gsw1xx_config_smdio_badr(struct gsw1xx_priv *priv,
+				    unsigned int reg)
+{
+	struct mii_bus *bus = priv->mdio_dev->bus;
+	int sw_addr = priv->mdio_dev->addr;
+	int smdio_badr = priv->smdio_badr;
+	int res;
+
+	if (smdio_badr == GSW1XX_SMDIO_BADR_UNKNOWN ||
+	    reg - smdio_badr >= GSW1XX_SMDIO_BADR ||
+	    smdio_badr > reg) {
+		/* Configure the Switch Base Address */
+		smdio_badr = reg & ~GENMASK(3, 0);
+		res = __mdiobus_write(bus, sw_addr, GSW1XX_SMDIO_BADR, smdio_badr);
+		if (res < 0) {
+			dev_err(&priv->mdio_dev->dev,
+				"%s: Error %d, configuring switch base\n",
+				__func__, res);
+			return res;
+		}
+		priv->smdio_badr = smdio_badr;
+	}
+
+	return smdio_badr;
+}
+
+static int gsw1xx_regmap_read(void *context, unsigned int reg,
+			      unsigned int *val)
+{
+	struct gsw1xx_priv *priv = context;
+	struct mii_bus *bus = priv->mdio_dev->bus;
+	int sw_addr = priv->mdio_dev->addr;
+	int smdio_badr;
+	int res;
+
+	smdio_badr = gsw1xx_config_smdio_badr(priv, reg);
+	if (smdio_badr < 0)
+		return smdio_badr;
+
+	res = __mdiobus_read(bus, sw_addr, reg - smdio_badr);
+	if (res < 0) {
+		dev_err(&priv->mdio_dev->dev, "%s: Error %d reading 0x%x\n",
+			__func__, res, reg);
+		return res;
+	}
+
+	*val = res;
+
+	return 0;
+}
+
+static int gsw1xx_regmap_write(void *context, unsigned int reg,
+			       unsigned int val)
+{
+	struct gsw1xx_priv *priv = context;
+	struct mii_bus *bus = priv->mdio_dev->bus;
+	int sw_addr = priv->mdio_dev->addr;
+	int smdio_badr;
+	int res;
+
+	smdio_badr = gsw1xx_config_smdio_badr(priv, reg);
+	if (smdio_badr < 0)
+		return smdio_badr;
+
+	res = __mdiobus_write(bus, sw_addr, reg - smdio_badr, val);
+	if (res < 0)
+		dev_err(&priv->mdio_dev->dev,
+			"%s: Error %d, writing 0x%x:0x%x\n", __func__, res, reg,
+			val);
+
+	return res;
+}
+
+static const struct regmap_bus gsw1xx_regmap_bus = {
+	.reg_write = gsw1xx_regmap_write,
+	.reg_read = gsw1xx_regmap_read,
+};
+
+static void gsw1xx_mdio_regmap_lock(void *mdio_lock)
+{
+	mutex_lock_nested(mdio_lock, MDIO_MUTEX_NESTED);
+}
+
+static void gsw1xx_mdio_regmap_unlock(void *mdio_lock)
+{
+	mutex_unlock(mdio_lock);
+}
+
+static unsigned int gsw1xx_pcs_inband_caps(struct phylink_pcs *pcs,
+					   phy_interface_t interface)
+{
+	return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE;
+}
+
+static struct gsw1xx_priv *pcs_to_gsw1xx(struct phylink_pcs *pcs)
+{
+	return container_of(pcs, struct gsw1xx_priv, pcs);
+}
+
+static int gsw1xx_pcs_enable(struct phylink_pcs *pcs)
+{
+	struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs);
+
+	/* Deassert SGMII shell reset */
+	return regmap_clear_bits(priv->shell, GSW1XX_SHELL_RST_REQ,
+				 GSW1XX_RST_REQ_SGMII_SHELL);
+}
+
+static void gsw1xx_pcs_disable(struct phylink_pcs *pcs)
+{
+	struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs);
+
+	/* Assert SGMII shell reset */
+	regmap_set_bits(priv->shell, GSW1XX_SHELL_RST_REQ,
+			GSW1XX_RST_REQ_SGMII_SHELL);
+
+	priv->tbi_interface = PHY_INTERFACE_MODE_NA;
+}
+
+static void gsw1xx_pcs_get_state(struct phylink_pcs *pcs,
+				 unsigned int neg_mode,
+				 struct phylink_link_state *state)
+{
+	struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs);
+	int ret;
+	u32 val;
+
+	ret = regmap_read(priv->sgmii, GSW1XX_SGMII_TBI_TBISTAT, &val);
+	if (ret < 0)
+		return;
+
+	state->link = !!(val & GSW1XX_SGMII_TBI_TBISTAT_LINK);
+	state->an_complete = !!(val & GSW1XX_SGMII_TBI_TBISTAT_AN_COMPLETE);
+
+	ret = regmap_read(priv->sgmii, GSW1XX_SGMII_TBI_LPSTAT, &val);
+	if (ret < 0)
+		return;
+
+	state->duplex = (val & GSW1XX_SGMII_TBI_LPSTAT_DUPLEX) ?
+			 DUPLEX_FULL : DUPLEX_HALF;
+	if (val & GSW1XX_SGMII_TBI_LPSTAT_PAUSE_RX)
+		state->pause |= MLO_PAUSE_RX;
+
+	if (val & GSW1XX_SGMII_TBI_LPSTAT_PAUSE_TX)
+		state->pause |= MLO_PAUSE_TX;
+
+	switch (FIELD_GET(GSW1XX_SGMII_TBI_LPSTAT_SPEED, val)) {
+	case GSW1XX_SGMII_TBI_LPSTAT_SPEED_10:
+		state->speed = SPEED_10;
+		break;
+	case GSW1XX_SGMII_TBI_LPSTAT_SPEED_100:
+		state->speed = SPEED_100;
+		break;
+	case GSW1XX_SGMII_TBI_LPSTAT_SPEED_1000:
+		state->speed = SPEED_1000;
+		break;
+	case GSW1XX_SGMII_TBI_LPSTAT_SPEED_NOSGMII:
+		if (state->interface == PHY_INTERFACE_MODE_1000BASEX)
+			state->speed = SPEED_1000;
+		else if (state->interface == PHY_INTERFACE_MODE_2500BASEX)
+			state->speed = SPEED_2500;
+		else
+			state->speed = SPEED_UNKNOWN;
+		break;
+	}
+}
+
+static int gsw1xx_pcs_phy_xaui_write(struct gsw1xx_priv *priv, u16 addr,
+				     u16 data)
+{
+	int ret, val;
+
+	ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_D, data);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_A, addr);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_C,
+			   GSW1XX_SGMII_PHY_WRITE |
+			   GSW1XX_SGMII_PHY_RESET_N);
+	if (ret < 0)
+		return ret;
+
+	return regmap_read_poll_timeout(priv->sgmii, GSW1XX_SGMII_PHY_C,
+					val, val & GSW1XX_SGMII_PHY_STATUS,
+					1000, 100000);
+}
+
+static int gsw1xx_pcs_reset(struct gsw1xx_priv *priv)
+{
+	int ret;
+	u16 val;
+
+	/* Assert and deassert SGMII shell reset */
+	ret = regmap_set_bits(priv->shell, GSW1XX_SHELL_RST_REQ,
+			      GSW1XX_RST_REQ_SGMII_SHELL);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_clear_bits(priv->shell, GSW1XX_SHELL_RST_REQ,
+				GSW1XX_RST_REQ_SGMII_SHELL);
+	if (ret < 0)
+		return ret;
+
+	/* Hardware Bringup FSM Enable  */
+	ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_HWBU_CTRL,
+			   GSW1XX_SGMII_PHY_HWBU_CTRL_EN_HWBU_FSM |
+			   GSW1XX_SGMII_PHY_HWBU_CTRL_HW_FSM_EN);
+	if (ret < 0)
+		return ret;
+
+	/* Configure SGMII PHY Receiver */
+	val = FIELD_PREP(GSW1XX_SGMII_PHY_RX0_CFG2_EQ,
+			 GSW1XX_SGMII_PHY_RX0_CFG2_EQ_DEF) |
+	      GSW1XX_SGMII_PHY_RX0_CFG2_LOS_EN |
+	      GSW1XX_SGMII_PHY_RX0_CFG2_TERM_EN |
+	      FIELD_PREP(GSW1XX_SGMII_PHY_RX0_CFG2_FILT_CNT,
+			 GSW1XX_SGMII_PHY_RX0_CFG2_FILT_CNT_DEF);
+
+	/* TODO: Take care of inverted RX pair once generic property is
+	 *       available
+	 */
+
+	ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_RX0_CFG2, val);
+	if (ret < 0)
+		return ret;
+
+	val = FIELD_PREP(GSW1XX_SGMII_PHY_TX0_CFG3_VBOOST_LEVEL,
+			 GSW1XX_SGMII_PHY_TX0_CFG3_VBOOST_LEVEL_DEF);
+
+	/* TODO: Take care of inverted TX pair once generic property is
+	 *       available
+	 */
+
+	ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_TX0_CFG3, val);
+	if (ret < 0)
+		return ret;
+
+	/* Reset and Release TBI */
+	val = GSW1XX_SGMII_TBI_TBICTL_INITTBI | GSW1XX_SGMII_TBI_TBICTL_ENTBI |
+	      GSW1XX_SGMII_TBI_TBICTL_CRSTRR | GSW1XX_SGMII_TBI_TBICTL_CRSOFF;
+	ret = regmap_write(priv->sgmii, GSW1XX_SGMII_TBI_TBICTL, val);
+	if (ret < 0)
+		return ret;
+	val &= ~GSW1XX_SGMII_TBI_TBICTL_INITTBI;
+	ret = regmap_write(priv->sgmii, GSW1XX_SGMII_TBI_TBICTL, val);
+	if (ret < 0)
+		return ret;
+
+	/* Release Tx Data Buffers */
+	ret = regmap_set_bits(priv->sgmii, GSW1XX_SGMII_PCS_TXB_CTL,
+			      GSW1XX_SGMII_PCS_TXB_CTL_INIT_TX_TXB);
+	if (ret < 0)
+		return ret;
+	ret = regmap_clear_bits(priv->sgmii, GSW1XX_SGMII_PCS_TXB_CTL,
+				GSW1XX_SGMII_PCS_TXB_CTL_INIT_TX_TXB);
+	if (ret < 0)
+		return ret;
+
+	/* Release Rx Data Buffers */
+	ret = regmap_set_bits(priv->sgmii, GSW1XX_SGMII_PCS_RXB_CTL,
+			      GSW1XX_SGMII_PCS_RXB_CTL_INIT_RX_RXB);
+	if (ret < 0)
+		return ret;
+	return regmap_clear_bits(priv->sgmii, GSW1XX_SGMII_PCS_RXB_CTL,
+				 GSW1XX_SGMII_PCS_RXB_CTL_INIT_RX_RXB);
+}
+
+static int gsw1xx_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode,
+			     phy_interface_t interface,
+			     const unsigned long *advertising,
+			     bool permit_pause_to_mac)
+{
+	struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs);
+	u16 txaneg, anegctl, nco_ctrl;
+	bool reconf = false;
+	int ret = 0;
+
+	/* do not unnecessarily disrupt link and skip resetting the hardware in
+	 * case the PCS has previously been successfully configured for this
+	 * interface mode
+	 */
+	if (priv->tbi_interface == interface)
+		reconf = true;
+
+	/* mark PCS configuration as incomplete */
+	priv->tbi_interface = PHY_INTERFACE_MODE_NA;
+
+	if (!reconf)
+		ret = gsw1xx_pcs_reset(priv);
+
+	if (ret)
+		return ret;
+
+	/* override bootstrap pin settings
+	 * OVRANEG sets ANEG Mode, Enable ANEG and restart ANEG to be
+	 * taken from bits ANMODE, ANEGEN, RANEG of the ANEGCTL register.
+	 * OVERABL sets ability bits in tx_config_reg to be taken from
+	 * the TXANEGH and TXANEGL registers.
+	 */
+	anegctl = GSW1XX_SGMII_TBI_ANEGCTL_OVRANEG |
+		  GSW1XX_SGMII_TBI_ANEGCTL_OVRABL;
+
+	switch (phylink_get_link_timer_ns(interface)) {
+	case 10000:
+		anegctl |= FIELD_PREP(GSW1XX_SGMII_TBI_ANEGCTL_LT,
+				      GSW1XX_SGMII_TBI_ANEGCTL_LT_10US);
+		break;
+	case 1600000:
+		anegctl |= FIELD_PREP(GSW1XX_SGMII_TBI_ANEGCTL_LT,
+				      GSW1XX_SGMII_TBI_ANEGCTL_LT_1_6MS);
+		break;
+	case 5000000:
+		anegctl |= FIELD_PREP(GSW1XX_SGMII_TBI_ANEGCTL_LT,
+				      GSW1XX_SGMII_TBI_ANEGCTL_LT_5MS);
+		break;
+	case 10000000:
+		anegctl |= FIELD_PREP(GSW1XX_SGMII_TBI_ANEGCTL_LT,
+				      GSW1XX_SGMII_TBI_ANEGCTL_LT_10MS);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (neg_mode & PHYLINK_PCS_NEG_INBAND)
+		anegctl |= GSW1XX_SGMII_TBI_ANEGCTL_ANEGEN;
+
+	txaneg = phylink_mii_c22_pcs_encode_advertisement(interface, advertising);
+
+	if (interface == PHY_INTERFACE_MODE_SGMII) {
+		/* lacking a defined reverse-SGMII interface mode this
+		 * driver only supports SGMII (MAC side) for now
+		 */
+		anegctl |= FIELD_PREP(GSW1XX_SGMII_TBI_ANEGCTL_ANMODE,
+				      GSW1XX_SGMII_TBI_ANEGCTL_ANMODE_SGMII_MAC);
+		txaneg |= ADVERTISE_LPACK;
+	} else if (interface == PHY_INTERFACE_MODE_1000BASEX ||
+		   interface == PHY_INTERFACE_MODE_2500BASEX) {
+		anegctl |= FIELD_PREP(GSW1XX_SGMII_TBI_ANEGCTL_ANMODE,
+				      GSW1XX_SGMII_TBI_ANEGCTL_ANMODE_1000BASEX);
+	} else {
+		dev_err(priv->gswip.dev, "%s: wrong interface mode %s\n",
+			__func__, phy_modes(interface));
+		return -EINVAL;
+	}
+
+	ret = regmap_write(priv->sgmii, GSW1XX_SGMII_TBI_TXANEGH,
+			   FIELD_GET(GENMASK(15, 8), txaneg));
+	if (ret < 0)
+		return ret;
+	ret = regmap_write(priv->sgmii, GSW1XX_SGMII_TBI_TXANEGL,
+			   FIELD_GET(GENMASK(7, 0), txaneg));
+	if (ret < 0)
+		return ret;
+	ret = regmap_write(priv->sgmii, GSW1XX_SGMII_TBI_ANEGCTL, anegctl);
+	if (ret < 0)
+		return ret;
+
+	if (!reconf) {
+		/* setup SerDes clock speed */
+		if (interface == PHY_INTERFACE_MODE_2500BASEX)
+			nco_ctrl = GSW1XX_SGMII_2G5 | GSW1XX_SGMII_2G5_NCO2;
+		else
+			nco_ctrl = GSW1XX_SGMII_1G | GSW1XX_SGMII_1G_NCO1;
+
+		ret = regmap_update_bits(priv->clk, GSW1XX_CLK_NCO_CTRL,
+					 GSW1XX_SGMII_HSP_MASK |
+					 GSW1XX_SGMII_SEL,
+					 nco_ctrl);
+		if (ret)
+			return ret;
+
+		ret = gsw1xx_pcs_phy_xaui_write(priv, 0x30, 0x80);
+		if (ret)
+			return ret;
+	}
+
+	/* PCS configuration has now been completed, store mode to prevent
+	 * disrupting the link in case of future calls of this function for the
+	 * same interface mode.
+	 */
+	priv->tbi_interface = interface;
+
+	return 0;
+}
+
+static void gsw1xx_pcs_an_restart(struct phylink_pcs *pcs)
+{
+	struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs);
+
+	regmap_set_bits(priv->sgmii, GSW1XX_SGMII_TBI_ANEGCTL,
+			GSW1XX_SGMII_TBI_ANEGCTL_RANEG);
+}
+
+static void gsw1xx_pcs_link_up(struct phylink_pcs *pcs,
+			       unsigned int neg_mode,
+			       phy_interface_t interface, int speed,
+			       int duplex)
+{
+	struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs);
+	u16 lpstat;
+
+	/* When in-band AN is enabled hardware will set lpstat */
+	if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED)
+		return;
+
+	/* Force speed and duplex settings */
+	if (interface == PHY_INTERFACE_MODE_SGMII) {
+		if (speed == SPEED_10)
+			lpstat = FIELD_PREP(GSW1XX_SGMII_TBI_LPSTAT_SPEED,
+					    GSW1XX_SGMII_TBI_LPSTAT_SPEED_10);
+		else if (speed == SPEED_100)
+			lpstat = FIELD_PREP(GSW1XX_SGMII_TBI_LPSTAT_SPEED,
+					    GSW1XX_SGMII_TBI_LPSTAT_SPEED_100);
+		else
+			lpstat = FIELD_PREP(GSW1XX_SGMII_TBI_LPSTAT_SPEED,
+					    GSW1XX_SGMII_TBI_LPSTAT_SPEED_1000);
+	} else {
+		lpstat = FIELD_PREP(GSW1XX_SGMII_TBI_LPSTAT_SPEED,
+				    GSW1XX_SGMII_TBI_LPSTAT_SPEED_NOSGMII);
+	}
+
+	if (duplex == DUPLEX_FULL)
+		lpstat |= GSW1XX_SGMII_TBI_LPSTAT_DUPLEX;
+
+	regmap_write(priv->sgmii, GSW1XX_SGMII_TBI_LPSTAT, lpstat);
+}
+
+static const struct phylink_pcs_ops gsw1xx_pcs_ops = {
+	.pcs_inband_caps = gsw1xx_pcs_inband_caps,
+	.pcs_enable = gsw1xx_pcs_enable,
+	.pcs_disable = gsw1xx_pcs_disable,
+	.pcs_get_state = gsw1xx_pcs_get_state,
+	.pcs_config = gsw1xx_pcs_config,
+	.pcs_an_restart = gsw1xx_pcs_an_restart,
+	.pcs_link_up = gsw1xx_pcs_link_up,
+};
+
+static void gsw1xx_phylink_get_caps(struct dsa_switch *ds, int port,
+				    struct phylink_config *config)
+{
+	struct gswip_priv *priv = ds->priv;
+
+	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+				   MAC_10 | MAC_100 | MAC_1000;
+
+	switch (port) {
+	case 0:
+	case 1:
+	case 2:
+	case 3:
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  config->supported_interfaces);
+		break;
+	case 4: /* port 4: SGMII */
+		__set_bit(PHY_INTERFACE_MODE_SGMII,
+			  config->supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_1000BASEX,
+			  config->supported_interfaces);
+		if (priv->hw_info->supports_2500m) {
+			__set_bit(PHY_INTERFACE_MODE_2500BASEX,
+				  config->supported_interfaces);
+			config->mac_capabilities |= MAC_2500FD;
+		}
+		return; /* no support for EEE on SGMII port */
+	case 5: /* port 5: RGMII or RMII */
+		__set_bit(PHY_INTERFACE_MODE_RMII,
+			  config->supported_interfaces);
+		phy_interface_set_rgmii(config->supported_interfaces);
+		break;
+	}
+
+	config->lpi_capabilities = MAC_100FD | MAC_1000FD;
+	config->lpi_timer_default = 20;
+	memcpy(config->lpi_interfaces, config->supported_interfaces,
+	       sizeof(config->lpi_interfaces));
+}
+
+static struct phylink_pcs *gsw1xx_phylink_mac_select_pcs(struct phylink_config *config,
+							 phy_interface_t interface)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct gswip_priv *gswip_priv = dp->ds->priv;
+	struct gsw1xx_priv *gsw1xx_priv = container_of(gswip_priv,
+						       struct gsw1xx_priv,
+						       gswip);
+
+	switch (dp->index) {
+	case GSW1XX_SGMII_PORT:
+		return &gsw1xx_priv->pcs;
+	default:
+		return NULL;
+	}
+}
+
+static struct regmap *gsw1xx_regmap_init(struct gsw1xx_priv *priv,
+					 const char *name,
+					 unsigned int reg_base,
+					 unsigned int max_register)
+{
+	const struct regmap_config config = {
+		.name = name,
+		.reg_bits = 16,
+		.val_bits = 16,
+		.reg_base = reg_base,
+		.max_register = max_register,
+		.lock = gsw1xx_mdio_regmap_lock,
+		.unlock = gsw1xx_mdio_regmap_unlock,
+		.lock_arg = &priv->mdio_dev->bus->mdio_lock,
+	};
+
+	return devm_regmap_init(&priv->mdio_dev->dev, &gsw1xx_regmap_bus,
+				priv, &config);
+}
+
+static int gsw1xx_probe(struct mdio_device *mdiodev)
+{
+	struct device *dev = &mdiodev->dev;
+	struct gsw1xx_priv *priv;
+	u32 version;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->mdio_dev = mdiodev;
+	priv->smdio_badr = GSW1XX_SMDIO_BADR_UNKNOWN;
+
+	priv->gswip.dev = dev;
+	priv->gswip.hw_info = of_device_get_match_data(dev);
+	if (!priv->gswip.hw_info)
+		return -EINVAL;
+
+	priv->gswip.gswip = gsw1xx_regmap_init(priv, "switch",
+					       GSW1XX_SWITCH_BASE, 0xfff);
+	if (IS_ERR(priv->gswip.gswip))
+		return PTR_ERR(priv->gswip.gswip);
+
+	priv->gswip.mdio = gsw1xx_regmap_init(priv, "mdio", GSW1XX_MMDIO_BASE,
+					      0xff);
+	if (IS_ERR(priv->gswip.mdio))
+		return PTR_ERR(priv->gswip.mdio);
+
+	priv->gswip.mii = gsw1xx_regmap_init(priv, "mii", GSW1XX_RGMII_BASE,
+					     0xff);
+	if (IS_ERR(priv->gswip.mii))
+		return PTR_ERR(priv->gswip.mii);
+
+	priv->sgmii = gsw1xx_regmap_init(priv, "sgmii", GSW1XX_SGMII_BASE,
+					 0xfff);
+	if (IS_ERR(priv->sgmii))
+		return PTR_ERR(priv->sgmii);
+
+	priv->gpio = gsw1xx_regmap_init(priv, "gpio", GSW1XX_GPIO_BASE, 0xff);
+	if (IS_ERR(priv->gpio))
+		return PTR_ERR(priv->gpio);
+
+	priv->clk = gsw1xx_regmap_init(priv, "clk", GSW1XX_CLK_BASE, 0xff);
+	if (IS_ERR(priv->clk))
+		return PTR_ERR(priv->clk);
+
+	priv->shell = gsw1xx_regmap_init(priv, "shell", GSW1XX_SHELL_BASE,
+					 0xff);
+	if (IS_ERR(priv->shell))
+		return PTR_ERR(priv->shell);
+
+	priv->pcs.ops = &gsw1xx_pcs_ops;
+	priv->pcs.poll = true;
+	__set_bit(PHY_INTERFACE_MODE_SGMII,
+		  priv->pcs.supported_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_1000BASEX,
+		  priv->pcs.supported_interfaces);
+	if (priv->gswip.hw_info->supports_2500m)
+		__set_bit(PHY_INTERFACE_MODE_2500BASEX,
+			  priv->pcs.supported_interfaces);
+	priv->tbi_interface = PHY_INTERFACE_MODE_NA;
+
+	/* assert SGMII reset to power down SGMII unit */
+	ret = regmap_set_bits(priv->shell, GSW1XX_SHELL_RST_REQ,
+			      GSW1XX_RST_REQ_SGMII_SHELL);
+	if (ret < 0)
+		return ret;
+
+	/* configure GPIO pin-mux for MMDIO in case of external PHY connected to
+	 * SGMII or RGMII as slave interface
+	 */
+	regmap_set_bits(priv->gpio, GPIO_ALTSEL0, 3);
+	regmap_set_bits(priv->gpio, GPIO_ALTSEL1, 3);
+
+	ret = regmap_read(priv->gswip.gswip, GSWIP_VERSION, &version);
+	if (ret)
+		return ret;
+
+	ret = gswip_probe_common(&priv->gswip, version);
+	if (ret)
+		return ret;
+
+	dev_set_drvdata(dev, &priv->gswip);
+
+	return 0;
+}
+
+static void gsw1xx_remove(struct mdio_device *mdiodev)
+{
+	struct gswip_priv *priv = dev_get_drvdata(&mdiodev->dev);
+
+	if (!priv)
+		return;
+
+	gswip_disable_switch(priv);
+
+	dsa_unregister_switch(priv->ds);
+}
+
+static void gsw1xx_shutdown(struct mdio_device *mdiodev)
+{
+	struct gswip_priv *priv = dev_get_drvdata(&mdiodev->dev);
+
+	if (!priv)
+		return;
+
+	dev_set_drvdata(&mdiodev->dev, NULL);
+
+	gswip_disable_switch(priv);
+}
+
+static const struct gswip_hw_info gsw12x_data = {
+	.max_ports		= GSW1XX_PORTS,
+	.allowed_cpu_ports	= BIT(GSW1XX_MII_PORT) | BIT(GSW1XX_SGMII_PORT),
+	.mii_ports		= BIT(GSW1XX_MII_PORT),
+	.mii_port_reg_offset	= -GSW1XX_MII_PORT,
+	.mac_select_pcs		= gsw1xx_phylink_mac_select_pcs,
+	.phylink_get_caps	= &gsw1xx_phylink_get_caps,
+	.supports_2500m		= true,
+	.pce_microcode		= &gsw1xx_pce_microcode,
+	.pce_microcode_size	= ARRAY_SIZE(gsw1xx_pce_microcode),
+	.tag_protocol		= DSA_TAG_PROTO_MXL_GSW1XX,
+};
+
+static const struct gswip_hw_info gsw140_data = {
+	.max_ports		= GSW1XX_PORTS,
+	.allowed_cpu_ports	= BIT(GSW1XX_MII_PORT) | BIT(GSW1XX_SGMII_PORT),
+	.mii_ports		= BIT(GSW1XX_MII_PORT),
+	.mii_port_reg_offset	= -GSW1XX_MII_PORT,
+	.mac_select_pcs		= gsw1xx_phylink_mac_select_pcs,
+	.phylink_get_caps	= &gsw1xx_phylink_get_caps,
+	.supports_2500m		= true,
+	.pce_microcode		= &gsw1xx_pce_microcode,
+	.pce_microcode_size	= ARRAY_SIZE(gsw1xx_pce_microcode),
+	.tag_protocol		= DSA_TAG_PROTO_MXL_GSW1XX,
+};
+
+static const struct gswip_hw_info gsw141_data = {
+	.max_ports		= GSW1XX_PORTS,
+	.allowed_cpu_ports	= BIT(GSW1XX_MII_PORT) | BIT(GSW1XX_SGMII_PORT),
+	.mii_ports		= BIT(GSW1XX_MII_PORT),
+	.mii_port_reg_offset	= -GSW1XX_MII_PORT,
+	.mac_select_pcs		= gsw1xx_phylink_mac_select_pcs,
+	.phylink_get_caps	= gsw1xx_phylink_get_caps,
+	.pce_microcode		= &gsw1xx_pce_microcode,
+	.pce_microcode_size	= ARRAY_SIZE(gsw1xx_pce_microcode),
+	.tag_protocol		= DSA_TAG_PROTO_MXL_GSW1XX,
+};
+
+/*
+ * GSW125 is the industrial temperature version of GSW120.
+ * GSW145 is the industrial temperature version of GSW140.
+ */
+static const struct of_device_id gsw1xx_of_match[] = {
+	{ .compatible = "maxlinear,gsw120", .data = &gsw12x_data },
+	{ .compatible = "maxlinear,gsw125", .data = &gsw12x_data },
+	{ .compatible = "maxlinear,gsw140", .data = &gsw140_data },
+	{ .compatible = "maxlinear,gsw141", .data = &gsw141_data },
+	{ .compatible = "maxlinear,gsw145", .data = &gsw140_data },
+	{ /* sentinel */ },
+};
+
+MODULE_DEVICE_TABLE(of, gsw1xx_of_match);
+
+static struct mdio_driver gsw1xx_driver = {
+	.probe		= gsw1xx_probe,
+	.remove		= gsw1xx_remove,
+	.shutdown	= gsw1xx_shutdown,
+	.mdiodrv.driver	= {
+		.name = "mxl-gsw1xx",
+		.of_match_table = gsw1xx_of_match,
+	},
+};
+
+mdio_module_driver(gsw1xx_driver);
+
+MODULE_AUTHOR("Daniel Golle <daniel@makrotopia.org>");
+MODULE_DESCRIPTION("Driver for MaxLinear GSW1xx ethernet switch");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/lantiq/mxl-gsw1xx.h b/drivers/net/dsa/lantiq/mxl-gsw1xx.h
new file mode 100644
index 000000000000..38e03c048a26
--- /dev/null
+++ b/drivers/net/dsa/lantiq/mxl-gsw1xx.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Register definitions for MaxLinear GSW1xx series switches
+ *
+ * Copyright (C) 2025 Daniel Golle <daniel@makrotopia.org>
+ * Copyright (C) 2023 - 2024 MaxLinear Inc.
+ */
+#ifndef __MXL_GSW1XX_H
+#define __MXL_GSW1XX_H
+
+#include <linux/bitfield.h>
+
+#define GSW1XX_PORTS				6
+/* Port used for RGMII or optional RMII */
+#define GSW1XX_MII_PORT				5
+/* Port used for SGMII */
+#define GSW1XX_SGMII_PORT			4
+
+#define GSW1XX_SYS_CLK_FREQ			340000000
+
+/* SMDIO switch register base address */
+#define GSW1XX_SMDIO_BADR			0x1f
+#define  GSW1XX_SMDIO_BADR_UNKNOWN		-1
+
+/* GSW1XX SGMII PCS */
+#define GSW1XX_SGMII_BASE			0xd000
+#define GSW1XX_SGMII_PHY_HWBU_CTRL		0x009
+#define  GSW1XX_SGMII_PHY_HWBU_CTRL_EN_HWBU_FSM	BIT(0)
+#define  GSW1XX_SGMII_PHY_HWBU_CTRL_HW_FSM_EN	BIT(3)
+#define GSW1XX_SGMII_TBI_TXANEGH		0x300
+#define GSW1XX_SGMII_TBI_TXANEGL		0x301
+#define GSW1XX_SGMII_TBI_ANEGCTL		0x304
+#define  GSW1XX_SGMII_TBI_ANEGCTL_LT		GENMASK(1, 0)
+#define   GSW1XX_SGMII_TBI_ANEGCTL_LT_10US	0
+#define   GSW1XX_SGMII_TBI_ANEGCTL_LT_1_6MS	1
+#define   GSW1XX_SGMII_TBI_ANEGCTL_LT_5MS	2
+#define   GSW1XX_SGMII_TBI_ANEGCTL_LT_10MS	3
+#define  GSW1XX_SGMII_TBI_ANEGCTL_ANEGEN	BIT(2)
+#define  GSW1XX_SGMII_TBI_ANEGCTL_RANEG		BIT(3)
+#define  GSW1XX_SGMII_TBI_ANEGCTL_OVRABL	BIT(4)
+#define  GSW1XX_SGMII_TBI_ANEGCTL_OVRANEG	BIT(5)
+#define  GSW1XX_SGMII_TBI_ANEGCTL_ANMODE	GENMASK(7, 6)
+#define   GSW1XX_SGMII_TBI_ANEGCTL_ANMODE_1000BASEX	1
+#define   GSW1XX_SGMII_TBI_ANEGCTL_ANMODE_SGMII_PHY	2
+#define   GSW1XX_SGMII_TBI_ANEGCTL_ANMODE_SGMII_MAC	3
+#define  GSW1XX_SGMII_TBI_ANEGCTL_BCOMP		BIT(15)
+
+#define GSW1XX_SGMII_TBI_TBICTL			0x305
+#define  GSW1XX_SGMII_TBI_TBICTL_INITTBI	BIT(0)
+#define  GSW1XX_SGMII_TBI_TBICTL_ENTBI		BIT(1)
+#define  GSW1XX_SGMII_TBI_TBICTL_CRSTRR		BIT(4)
+#define  GSW1XX_SGMII_TBI_TBICTL_CRSOFF		BIT(5)
+#define GSW1XX_SGMII_TBI_TBISTAT		0x309
+#define  GSW1XX_SGMII_TBI_TBISTAT_LINK		BIT(0)
+#define  GSW1XX_SGMII_TBI_TBISTAT_AN_COMPLETE	BIT(1)
+#define GSW1XX_SGMII_TBI_LPSTAT			0x30a
+#define  GSW1XX_SGMII_TBI_LPSTAT_DUPLEX		BIT(0)
+#define  GSW1XX_SGMII_TBI_LPSTAT_PAUSE_RX	BIT(1)
+#define  GSW1XX_SGMII_TBI_LPSTAT_PAUSE_TX	BIT(2)
+#define  GSW1XX_SGMII_TBI_LPSTAT_SPEED		GENMASK(6, 5)
+#define   GSW1XX_SGMII_TBI_LPSTAT_SPEED_10	0
+#define   GSW1XX_SGMII_TBI_LPSTAT_SPEED_100	1
+#define   GSW1XX_SGMII_TBI_LPSTAT_SPEED_1000	2
+#define   GSW1XX_SGMII_TBI_LPSTAT_SPEED_NOSGMII	3
+#define GSW1XX_SGMII_PHY_D			0x100
+#define GSW1XX_SGMII_PHY_A			0x101
+#define GSW1XX_SGMII_PHY_C			0x102
+#define  GSW1XX_SGMII_PHY_STATUS		BIT(0)
+#define  GSW1XX_SGMII_PHY_READ			BIT(4)
+#define  GSW1XX_SGMII_PHY_WRITE			BIT(8)
+#define  GSW1XX_SGMII_PHY_RESET_N		BIT(12)
+#define GSW1XX_SGMII_PCS_RXB_CTL		0x401
+#define  GSW1XX_SGMII_PCS_RXB_CTL_INIT_RX_RXB	BIT(1)
+#define GSW1XX_SGMII_PCS_TXB_CTL		0x404
+#define  GSW1XX_SGMII_PCS_TXB_CTL_INIT_TX_TXB	BIT(1)
+
+#define GSW1XX_SGMII_PHY_RX0_CFG2		0x004
+#define  GSW1XX_SGMII_PHY_RX0_CFG2_EQ		GENMASK(2, 0)
+#define   GSW1XX_SGMII_PHY_RX0_CFG2_EQ_DEF	2
+#define  GSW1XX_SGMII_PHY_RX0_CFG2_INVERT	BIT(3)
+#define  GSW1XX_SGMII_PHY_RX0_CFG2_LOS_EN	BIT(4)
+#define  GSW1XX_SGMII_PHY_RX0_CFG2_TERM_EN	BIT(5)
+#define  GSW1XX_SGMII_PHY_RX0_CFG2_FILT_CNT	GENMASK(12, 6)
+#define   GSW1XX_SGMII_PHY_RX0_CFG2_FILT_CNT_DEF	20
+
+#define GSW1XX_SGMII_PHY_TX0_CFG3		0x007
+#define  GSW1XX_SGMII_PHY_TX0_CFG3_VBOOST_EN	BIT(12)
+#define  GSW1XX_SGMII_PHY_TX0_CFG3_VBOOST_LEVEL	GENMASK(11, 9)
+#define   GSW1XX_SGMII_PHY_TX0_CFG3_VBOOST_LEVEL_DEF	4
+#define  GSW1XX_SGMII_PHY_TX0_CFG3_INVERT	BIT(8)
+
+/* GSW1XX PDI Registers */
+#define GSW1XX_SWITCH_BASE			0xe000
+
+/* GSW1XX MII Registers */
+#define GSW1XX_RGMII_BASE			0xf100
+
+/* GSW1XX GPIO Registers */
+#define GSW1XX_GPIO_BASE			0xf300
+#define GPIO_ALTSEL0				0x83
+#define GPIO_ALTSEL0_EXTPHY_MUX_VAL		0x03c3
+#define GPIO_ALTSEL1				0x84
+#define GPIO_ALTSEL1_EXTPHY_MUX_VAL		0x003f
+
+/* MDIO bus controller */
+#define GSW1XX_MMDIO_BASE			0xf400
+
+/* generic IC registers */
+#define GSW1XX_SHELL_BASE			0xfa00
+#define  GSW1XX_SHELL_RST_REQ			0x01
+#define   GSW1XX_RST_REQ_SGMII_SHELL		BIT(5)
+/* RGMII PAD Slew Control Register */
+#define  GSW1XX_SHELL_RGMII_SLEW_CFG		0x78
+#define   RGMII_SLEW_CFG_RX_2_5_V		BIT(4)
+#define   RGMII_SLEW_CFG_TX_2_5_V		BIT(5)
+
+/* SGMII clock related settings */
+#define GSW1XX_CLK_BASE				0xf900
+#define  GSW1XX_CLK_NCO_CTRL			0x68
+#define   GSW1XX_SGMII_HSP_MASK			GENMASK(3, 2)
+#define   GSW1XX_SGMII_SEL			BIT(1)
+#define   GSW1XX_SGMII_1G			0x0
+#define   GSW1XX_SGMII_2G5			0xc
+#define   GSW1XX_SGMII_1G_NCO1			0x0
+#define   GSW1XX_SGMII_2G5_NCO2			0x2
+
+#endif /* __MXL_GSW1XX_H */
diff --git a/drivers/net/dsa/lantiq/mxl-gsw1xx_pce.h b/drivers/net/dsa/lantiq/mxl-gsw1xx_pce.h
new file mode 100644
index 000000000000..eefcd411a340
--- /dev/null
+++ b/drivers/net/dsa/lantiq/mxl-gsw1xx_pce.h
@@ -0,0 +1,154 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PCE microcode code update for driver for MaxLinear GSW1xx switch chips
+ *
+ * Copyright (C) 2023 - 2024 MaxLinear Inc.
+ * Copyright (C) 2022 Snap One, LLC.  All rights reserved.
+ * Copyright (C) 2017 - 2019 Hauke Mehrtens <hauke@hauke-m.de>
+ * Copyright (C) 2012 John Crispin <john@phrozen.org>
+ * Copyright (C) 2010 Lantiq Deutschland
+ */
+
+#include "lantiq_gswip.h"
+
+#define INSTR 0
+#define IPV6 1
+#define LENACCU 2
+
+/* GSWIP_2.X */
+enum {
+	OUT_MAC0 = 0,
+	OUT_MAC1,
+	OUT_MAC2,
+	OUT_MAC3,
+	OUT_MAC4,
+	OUT_MAC5,
+	OUT_ETHTYP,
+	OUT_VTAG0,
+	OUT_VTAG1,
+	OUT_ITAG0,
+	OUT_ITAG1,	/* 10 */
+	OUT_ITAG2,
+	OUT_ITAG3,
+	OUT_IP0,
+	OUT_IP1,
+	OUT_IP2,
+	OUT_IP3,
+	OUT_SIP0,
+	OUT_SIP1,
+	OUT_SIP2,
+	OUT_SIP3,	/* 20 */
+	OUT_SIP4,
+	OUT_SIP5,
+	OUT_SIP6,
+	OUT_SIP7,
+	OUT_DIP0,
+	OUT_DIP1,
+	OUT_DIP2,
+	OUT_DIP3,
+	OUT_DIP4,
+	OUT_DIP5,	/* 30 */
+	OUT_DIP6,
+	OUT_DIP7,
+	OUT_SESID,
+	OUT_PROT,
+	OUT_APP0,
+	OUT_APP1,
+	OUT_IGMP0,
+	OUT_IGMP1,
+	OUT_STAG0 = 61,
+	OUT_STAG1 = 62,
+	OUT_NONE = 63,
+};
+
+/* parser's microcode flag type */
+enum {
+	FLAG_ITAG = 0,
+	FLAG_VLAN,
+	FLAG_SNAP,
+	FLAG_PPPOE,
+	FLAG_IPV6,
+	FLAG_IPV6FL,
+	FLAG_IPV4,
+	FLAG_IGMP,
+	FLAG_TU,
+	FLAG_HOP,
+	FLAG_NN1,	/* 10 */
+	FLAG_NN2,
+	FLAG_END,
+	FLAG_NO,	/* 13 */
+	FLAG_SVLAN,	/* 14 */
+};
+
+#define PCE_MC_M(val, msk, ns, out, len, type, flags, ipv4_len) \
+	{ (val), (msk), ((ns) << 10 | (out) << 4 | (len) >> 1),\
+	 ((len) & 1) << 15 | (type) << 13 | (flags) << 9 | (ipv4_len) << 8 }
+
+/* V22_2X (IPv6 issue fixed) */
+static const struct gswip_pce_microcode gsw1xx_pce_microcode[] = {
+	/*       value   mask    ns  fields      L  type     flags       ipv4_len */
+	PCE_MC_M(0x88c3, 0xFFFF, 1,  OUT_ITAG0,  4, INSTR,   FLAG_ITAG,  0),
+	PCE_MC_M(0x8100, 0xFFFF, 4,  OUT_STAG0,  2, INSTR,   FLAG_SVLAN, 0),
+	PCE_MC_M(0x88A8, 0xFFFF, 4,  OUT_STAG0,  2, INSTR,   FLAG_SVLAN, 0),
+	PCE_MC_M(0x9100, 0xFFFF, 4,  OUT_STAG0,  2, INSTR,   FLAG_SVLAN, 0),
+	PCE_MC_M(0x8100, 0xFFFF, 5,  OUT_VTAG0,  2, INSTR,   FLAG_VLAN,  0),
+	PCE_MC_M(0x88A8, 0xFFFF, 6,  OUT_VTAG0,  2, INSTR,   FLAG_VLAN,  0),
+	PCE_MC_M(0x9100, 0xFFFF, 4,  OUT_VTAG0,  2, INSTR,   FLAG_VLAN,  0),
+	PCE_MC_M(0x8864, 0xFFFF, 20, OUT_ETHTYP, 1, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0800, 0xFFFF, 24, OUT_ETHTYP, 1, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x86DD, 0xFFFF, 25, OUT_ETHTYP, 1, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x8863, 0xFFFF, 19, OUT_ETHTYP, 1, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0xF800, 13, OUT_NONE,   0, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x0000, 44, OUT_ETHTYP, 1, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0600, 0x0600, 44, OUT_ETHTYP, 1, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x0000, 15, OUT_NONE,   1, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0xAAAA, 0xFFFF, 17, OUT_NONE,   1, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0300, 0xFF00, 45, OUT_NONE,   0, INSTR,   FLAG_SNAP,  0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_DIP7,   3, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x0000, 21, OUT_DIP7,   3, INSTR,   FLAG_PPPOE, 0),
+	PCE_MC_M(0x0021, 0xFFFF, 24, OUT_NONE,   1, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0057, 0xFFFF, 25, OUT_NONE,   1, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x0000, 44, OUT_NONE,   0, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x4000, 0xF000, 27, OUT_IP0,    4, INSTR,   FLAG_IPV4,  1),
+	PCE_MC_M(0x6000, 0xF000, 30, OUT_IP0,    3, INSTR,   FLAG_IPV6,  0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x0000, 28, OUT_IP3,    2, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x0000, 29, OUT_SIP0,   4, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x0000, 44, OUT_NONE,   0, LENACCU, FLAG_NO,    0),
+	PCE_MC_M(0x1100, 0xFF00, 43, OUT_PROT,   1, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0600, 0xFF00, 43, OUT_PROT,   1, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0xFF00, 36, OUT_IP3,   17, INSTR,   FLAG_HOP,   0),
+	PCE_MC_M(0x2B00, 0xFF00, 36, OUT_IP3,   17, INSTR,   FLAG_NN1,   0),
+	PCE_MC_M(0x3C00, 0xFF00, 36, OUT_IP3,   17, INSTR,   FLAG_NN2,   0),
+	PCE_MC_M(0x0000, 0x0000, 43, OUT_PROT,   1, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x00F0, 38, OUT_NONE,   0, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x0000, 44, OUT_NONE,   0, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0xFF00, 36, OUT_NONE,   0, IPV6,    FLAG_HOP,   0),
+	PCE_MC_M(0x2B00, 0xFF00, 36, OUT_NONE,   0, IPV6,    FLAG_NN1,   0),
+	PCE_MC_M(0x3C00, 0xFF00, 36, OUT_NONE,   0, IPV6,    FLAG_NN2,   0),
+	PCE_MC_M(0x0000, 0x00FC, 44, OUT_PROT,   0, IPV6,    FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x0000, 44, OUT_NONE,   0, IPV6,    FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x0000, 44, OUT_SIP0,  16, INSTR,   FLAG_NO,    0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_APP0,   4, INSTR,   FLAG_IGMP,  0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+	PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE,   0, INSTR,   FLAG_END,   0),
+};
diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c
deleted file mode 100644
index 6eb3140d4044..000000000000
--- a/drivers/net/dsa/lantiq_gswip.c
+++ /dev/null
@@ -1,2270 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Lantiq / Intel GSWIP switch driver for VRX200, xRX300 and xRX330 SoCs
- *
- * Copyright (C) 2010 Lantiq Deutschland
- * Copyright (C) 2012 John Crispin <john@phrozen.org>
- * Copyright (C) 2017 - 2019 Hauke Mehrtens <hauke@hauke-m.de>
- *
- * The VLAN and bridge model the GSWIP hardware uses does not directly
- * matches the model DSA uses.
- *
- * The hardware has 64 possible table entries for bridges with one VLAN
- * ID, one flow id and a list of ports for each bridge. All entries which
- * match the same flow ID are combined in the mac learning table, they
- * act as one global bridge.
- * The hardware does not support VLAN filter on the port, but on the
- * bridge, this driver converts the DSA model to the hardware.
- *
- * The CPU gets all the exception frames which do not match any forwarding
- * rule and the CPU port is also added to all bridges. This makes it possible
- * to handle all the special cases easily in software.
- * At the initialization the driver allocates one bridge table entry for
- * each switch port which is used when the port is used without an
- * explicit bridge. This prevents the frames from being forwarded
- * between all LAN ports by default.
- */
-
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/etherdevice.h>
-#include <linux/firmware.h>
-#include <linux/if_bridge.h>
-#include <linux/if_vlan.h>
-#include <linux/iopoll.h>
-#include <linux/mfd/syscon.h>
-#include <linux/module.h>
-#include <linux/of_mdio.h>
-#include <linux/of_net.h>
-#include <linux/of_platform.h>
-#include <linux/phy.h>
-#include <linux/phylink.h>
-#include <linux/platform_device.h>
-#include <linux/regmap.h>
-#include <linux/reset.h>
-#include <net/dsa.h>
-#include <dt-bindings/mips/lantiq_rcu_gphy.h>
-
-#include "lantiq_pce.h"
-
-/* GSWIP MDIO Registers */
-#define GSWIP_MDIO_GLOB			0x00
-#define  GSWIP_MDIO_GLOB_ENABLE		BIT(15)
-#define GSWIP_MDIO_CTRL			0x08
-#define  GSWIP_MDIO_CTRL_BUSY		BIT(12)
-#define  GSWIP_MDIO_CTRL_RD		BIT(11)
-#define  GSWIP_MDIO_CTRL_WR		BIT(10)
-#define  GSWIP_MDIO_CTRL_PHYAD_MASK	0x1f
-#define  GSWIP_MDIO_CTRL_PHYAD_SHIFT	5
-#define  GSWIP_MDIO_CTRL_REGAD_MASK	0x1f
-#define GSWIP_MDIO_READ			0x09
-#define GSWIP_MDIO_WRITE		0x0A
-#define GSWIP_MDIO_MDC_CFG0		0x0B
-#define GSWIP_MDIO_MDC_CFG1		0x0C
-#define GSWIP_MDIO_PHYp(p)		(0x15 - (p))
-#define  GSWIP_MDIO_PHY_LINK_MASK	0x6000
-#define  GSWIP_MDIO_PHY_LINK_AUTO	0x0000
-#define  GSWIP_MDIO_PHY_LINK_DOWN	0x4000
-#define  GSWIP_MDIO_PHY_LINK_UP		0x2000
-#define  GSWIP_MDIO_PHY_SPEED_MASK	0x1800
-#define  GSWIP_MDIO_PHY_SPEED_AUTO	0x1800
-#define  GSWIP_MDIO_PHY_SPEED_M10	0x0000
-#define  GSWIP_MDIO_PHY_SPEED_M100	0x0800
-#define  GSWIP_MDIO_PHY_SPEED_G1	0x1000
-#define  GSWIP_MDIO_PHY_FDUP_MASK	0x0600
-#define  GSWIP_MDIO_PHY_FDUP_AUTO	0x0000
-#define  GSWIP_MDIO_PHY_FDUP_EN		0x0200
-#define  GSWIP_MDIO_PHY_FDUP_DIS	0x0600
-#define  GSWIP_MDIO_PHY_FCONTX_MASK	0x0180
-#define  GSWIP_MDIO_PHY_FCONTX_AUTO	0x0000
-#define  GSWIP_MDIO_PHY_FCONTX_EN	0x0100
-#define  GSWIP_MDIO_PHY_FCONTX_DIS	0x0180
-#define  GSWIP_MDIO_PHY_FCONRX_MASK	0x0060
-#define  GSWIP_MDIO_PHY_FCONRX_AUTO	0x0000
-#define  GSWIP_MDIO_PHY_FCONRX_EN	0x0020
-#define  GSWIP_MDIO_PHY_FCONRX_DIS	0x0060
-#define  GSWIP_MDIO_PHY_ADDR_MASK	0x001f
-#define  GSWIP_MDIO_PHY_MASK		(GSWIP_MDIO_PHY_ADDR_MASK | \
-					 GSWIP_MDIO_PHY_FCONRX_MASK | \
-					 GSWIP_MDIO_PHY_FCONTX_MASK | \
-					 GSWIP_MDIO_PHY_LINK_MASK | \
-					 GSWIP_MDIO_PHY_SPEED_MASK | \
-					 GSWIP_MDIO_PHY_FDUP_MASK)
-
-/* GSWIP MII Registers */
-#define GSWIP_MII_CFGp(p)		(0x2 * (p))
-#define  GSWIP_MII_CFG_RESET		BIT(15)
-#define  GSWIP_MII_CFG_EN		BIT(14)
-#define  GSWIP_MII_CFG_ISOLATE		BIT(13)
-#define  GSWIP_MII_CFG_LDCLKDIS		BIT(12)
-#define  GSWIP_MII_CFG_RGMII_IBS	BIT(8)
-#define  GSWIP_MII_CFG_RMII_CLK		BIT(7)
-#define  GSWIP_MII_CFG_MODE_MIIP	0x0
-#define  GSWIP_MII_CFG_MODE_MIIM	0x1
-#define  GSWIP_MII_CFG_MODE_RMIIP	0x2
-#define  GSWIP_MII_CFG_MODE_RMIIM	0x3
-#define  GSWIP_MII_CFG_MODE_RGMII	0x4
-#define  GSWIP_MII_CFG_MODE_GMII	0x9
-#define  GSWIP_MII_CFG_MODE_MASK	0xf
-#define  GSWIP_MII_CFG_RATE_M2P5	0x00
-#define  GSWIP_MII_CFG_RATE_M25	0x10
-#define  GSWIP_MII_CFG_RATE_M125	0x20
-#define  GSWIP_MII_CFG_RATE_M50	0x30
-#define  GSWIP_MII_CFG_RATE_AUTO	0x40
-#define  GSWIP_MII_CFG_RATE_MASK	0x70
-#define GSWIP_MII_PCDU0			0x01
-#define GSWIP_MII_PCDU1			0x03
-#define GSWIP_MII_PCDU5			0x05
-#define  GSWIP_MII_PCDU_TXDLY_MASK	GENMASK(2, 0)
-#define  GSWIP_MII_PCDU_RXDLY_MASK	GENMASK(9, 7)
-
-/* GSWIP Core Registers */
-#define GSWIP_SWRES			0x000
-#define  GSWIP_SWRES_R1			BIT(1)	/* GSWIP Software reset */
-#define  GSWIP_SWRES_R0			BIT(0)	/* GSWIP Hardware reset */
-#define GSWIP_VERSION			0x013
-#define  GSWIP_VERSION_REV_SHIFT	0
-#define  GSWIP_VERSION_REV_MASK		GENMASK(7, 0)
-#define  GSWIP_VERSION_MOD_SHIFT	8
-#define  GSWIP_VERSION_MOD_MASK		GENMASK(15, 8)
-#define   GSWIP_VERSION_2_0		0x100
-#define   GSWIP_VERSION_2_1		0x021
-#define   GSWIP_VERSION_2_2		0x122
-#define   GSWIP_VERSION_2_2_ETC		0x022
-
-#define GSWIP_BM_RAM_VAL(x)		(0x043 - (x))
-#define GSWIP_BM_RAM_ADDR		0x044
-#define GSWIP_BM_RAM_CTRL		0x045
-#define  GSWIP_BM_RAM_CTRL_BAS		BIT(15)
-#define  GSWIP_BM_RAM_CTRL_OPMOD	BIT(5)
-#define  GSWIP_BM_RAM_CTRL_ADDR_MASK	GENMASK(4, 0)
-#define GSWIP_BM_QUEUE_GCTRL		0x04A
-#define  GSWIP_BM_QUEUE_GCTRL_GL_MOD	BIT(10)
-/* buffer management Port Configuration Register */
-#define GSWIP_BM_PCFGp(p)		(0x080 + ((p) * 2))
-#define  GSWIP_BM_PCFG_CNTEN		BIT(0)	/* RMON Counter Enable */
-#define  GSWIP_BM_PCFG_IGCNT		BIT(1)	/* Ingres Special Tag RMON count */
-/* buffer management Port Control Register */
-#define GSWIP_BM_RMON_CTRLp(p)		(0x81 + ((p) * 2))
-#define  GSWIP_BM_CTRL_RMON_RAM1_RES	BIT(0)	/* Software Reset for RMON RAM 1 */
-#define  GSWIP_BM_CTRL_RMON_RAM2_RES	BIT(1)	/* Software Reset for RMON RAM 2 */
-
-/* PCE */
-#define GSWIP_PCE_TBL_KEY(x)		(0x447 - (x))
-#define GSWIP_PCE_TBL_MASK		0x448
-#define GSWIP_PCE_TBL_VAL(x)		(0x44D - (x))
-#define GSWIP_PCE_TBL_ADDR		0x44E
-#define GSWIP_PCE_TBL_CTRL		0x44F
-#define  GSWIP_PCE_TBL_CTRL_BAS		BIT(15)
-#define  GSWIP_PCE_TBL_CTRL_TYPE	BIT(13)
-#define  GSWIP_PCE_TBL_CTRL_VLD		BIT(12)
-#define  GSWIP_PCE_TBL_CTRL_KEYFORM	BIT(11)
-#define  GSWIP_PCE_TBL_CTRL_GMAP_MASK	GENMASK(10, 7)
-#define  GSWIP_PCE_TBL_CTRL_OPMOD_MASK	GENMASK(6, 5)
-#define  GSWIP_PCE_TBL_CTRL_OPMOD_ADRD	0x00
-#define  GSWIP_PCE_TBL_CTRL_OPMOD_ADWR	0x20
-#define  GSWIP_PCE_TBL_CTRL_OPMOD_KSRD	0x40
-#define  GSWIP_PCE_TBL_CTRL_OPMOD_KSWR	0x60
-#define  GSWIP_PCE_TBL_CTRL_ADDR_MASK	GENMASK(4, 0)
-#define GSWIP_PCE_PMAP1			0x453	/* Monitoring port map */
-#define GSWIP_PCE_PMAP2			0x454	/* Default Multicast port map */
-#define GSWIP_PCE_PMAP3			0x455	/* Default Unknown Unicast port map */
-#define GSWIP_PCE_GCTRL_0		0x456
-#define  GSWIP_PCE_GCTRL_0_MTFL		BIT(0)  /* MAC Table Flushing */
-#define  GSWIP_PCE_GCTRL_0_MC_VALID	BIT(3)
-#define  GSWIP_PCE_GCTRL_0_VLAN		BIT(14) /* VLAN aware Switching */
-#define GSWIP_PCE_GCTRL_1		0x457
-#define  GSWIP_PCE_GCTRL_1_MAC_GLOCK	BIT(2)	/* MAC Address table lock */
-#define  GSWIP_PCE_GCTRL_1_MAC_GLOCK_MOD	BIT(3) /* Mac address table lock forwarding mode */
-#define GSWIP_PCE_PCTRL_0p(p)		(0x480 + ((p) * 0xA))
-#define  GSWIP_PCE_PCTRL_0_TVM		BIT(5)	/* Transparent VLAN mode */
-#define  GSWIP_PCE_PCTRL_0_VREP		BIT(6)	/* VLAN Replace Mode */
-#define  GSWIP_PCE_PCTRL_0_INGRESS	BIT(11)	/* Accept special tag in ingress */
-#define  GSWIP_PCE_PCTRL_0_PSTATE_LISTEN	0x0
-#define  GSWIP_PCE_PCTRL_0_PSTATE_RX		0x1
-#define  GSWIP_PCE_PCTRL_0_PSTATE_TX		0x2
-#define  GSWIP_PCE_PCTRL_0_PSTATE_LEARNING	0x3
-#define  GSWIP_PCE_PCTRL_0_PSTATE_FORWARDING	0x7
-#define  GSWIP_PCE_PCTRL_0_PSTATE_MASK	GENMASK(2, 0)
-#define GSWIP_PCE_VCTRL(p)		(0x485 + ((p) * 0xA))
-#define  GSWIP_PCE_VCTRL_UVR		BIT(0)	/* Unknown VLAN Rule */
-#define  GSWIP_PCE_VCTRL_VIMR		BIT(3)	/* VLAN Ingress Member violation rule */
-#define  GSWIP_PCE_VCTRL_VEMR		BIT(4)	/* VLAN Egress Member violation rule */
-#define  GSWIP_PCE_VCTRL_VSR		BIT(5)	/* VLAN Security */
-#define  GSWIP_PCE_VCTRL_VID0		BIT(6)	/* Priority Tagged Rule */
-#define GSWIP_PCE_DEFPVID(p)		(0x486 + ((p) * 0xA))
-
-#define GSWIP_MAC_FLEN			0x8C5
-#define GSWIP_MAC_CTRL_0p(p)		(0x903 + ((p) * 0xC))
-#define  GSWIP_MAC_CTRL_0_PADEN		BIT(8)
-#define  GSWIP_MAC_CTRL_0_FCS_EN	BIT(7)
-#define  GSWIP_MAC_CTRL_0_FCON_MASK	0x0070
-#define  GSWIP_MAC_CTRL_0_FCON_AUTO	0x0000
-#define  GSWIP_MAC_CTRL_0_FCON_RX	0x0010
-#define  GSWIP_MAC_CTRL_0_FCON_TX	0x0020
-#define  GSWIP_MAC_CTRL_0_FCON_RXTX	0x0030
-#define  GSWIP_MAC_CTRL_0_FCON_NONE	0x0040
-#define  GSWIP_MAC_CTRL_0_FDUP_MASK	0x000C
-#define  GSWIP_MAC_CTRL_0_FDUP_AUTO	0x0000
-#define  GSWIP_MAC_CTRL_0_FDUP_EN	0x0004
-#define  GSWIP_MAC_CTRL_0_FDUP_DIS	0x000C
-#define  GSWIP_MAC_CTRL_0_GMII_MASK	0x0003
-#define  GSWIP_MAC_CTRL_0_GMII_AUTO	0x0000
-#define  GSWIP_MAC_CTRL_0_GMII_MII	0x0001
-#define  GSWIP_MAC_CTRL_0_GMII_RGMII	0x0002
-#define GSWIP_MAC_CTRL_2p(p)		(0x905 + ((p) * 0xC))
-#define GSWIP_MAC_CTRL_2_LCHKL		BIT(2) /* Frame Length Check Long Enable */
-#define GSWIP_MAC_CTRL_2_MLEN		BIT(3) /* Maximum Untagged Frame Lnegth */
-
-/* Ethernet Switch Fetch DMA Port Control Register */
-#define GSWIP_FDMA_PCTRLp(p)		(0xA80 + ((p) * 0x6))
-#define  GSWIP_FDMA_PCTRL_EN		BIT(0)	/* FDMA Port Enable */
-#define  GSWIP_FDMA_PCTRL_STEN		BIT(1)	/* Special Tag Insertion Enable */
-#define  GSWIP_FDMA_PCTRL_VLANMOD_MASK	GENMASK(4, 3)	/* VLAN Modification Control */
-#define  GSWIP_FDMA_PCTRL_VLANMOD_SHIFT	3	/* VLAN Modification Control */
-#define  GSWIP_FDMA_PCTRL_VLANMOD_DIS	(0x0 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT)
-#define  GSWIP_FDMA_PCTRL_VLANMOD_PRIO	(0x1 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT)
-#define  GSWIP_FDMA_PCTRL_VLANMOD_ID	(0x2 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT)
-#define  GSWIP_FDMA_PCTRL_VLANMOD_BOTH	(0x3 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT)
-
-/* Ethernet Switch Store DMA Port Control Register */
-#define GSWIP_SDMA_PCTRLp(p)		(0xBC0 + ((p) * 0x6))
-#define  GSWIP_SDMA_PCTRL_EN		BIT(0)	/* SDMA Port Enable */
-#define  GSWIP_SDMA_PCTRL_FCEN		BIT(1)	/* Flow Control Enable */
-#define  GSWIP_SDMA_PCTRL_PAUFWD	BIT(3)	/* Pause Frame Forwarding */
-
-#define GSWIP_TABLE_ACTIVE_VLAN		0x01
-#define GSWIP_TABLE_VLAN_MAPPING	0x02
-#define GSWIP_TABLE_MAC_BRIDGE		0x0b
-#define  GSWIP_TABLE_MAC_BRIDGE_KEY3_FID	GENMASK(5, 0)	/* Filtering identifier */
-#define  GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT	GENMASK(7, 4)	/* Port on learned entries */
-#define  GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC	BIT(0)		/* Static, non-aging entry */
-
-#define XRX200_GPHY_FW_ALIGN	(16 * 1024)
-
-/* Maximum packet size supported by the switch. In theory this should be 10240,
- * but long packets currently cause lock-ups with an MTU of over 2526. Medium
- * packets are sometimes dropped (e.g. TCP over 2477, UDP over 2516-2519, ICMP
- * over 2526), hence an MTU value of 2400 seems safe. This issue only affects
- * packet reception. This is probably caused by the PPA engine, which is on the
- * RX part of the device. Packet transmission works properly up to 10240.
- */
-#define GSWIP_MAX_PACKET_LENGTH	2400
-
-struct gswip_hw_info {
-	int max_ports;
-	int cpu_port;
-	const struct dsa_switch_ops *ops;
-};
-
-struct xway_gphy_match_data {
-	char *fe_firmware_name;
-	char *ge_firmware_name;
-};
-
-struct gswip_gphy_fw {
-	struct clk *clk_gate;
-	struct reset_control *reset;
-	u32 fw_addr_offset;
-	char *fw_name;
-};
-
-struct gswip_vlan {
-	struct net_device *bridge;
-	u16 vid;
-	u8 fid;
-};
-
-struct gswip_priv {
-	__iomem void *gswip;
-	__iomem void *mdio;
-	__iomem void *mii;
-	const struct gswip_hw_info *hw_info;
-	const struct xway_gphy_match_data *gphy_fw_name_cfg;
-	struct dsa_switch *ds;
-	struct device *dev;
-	struct regmap *rcu_regmap;
-	struct gswip_vlan vlans[64];
-	int num_gphy_fw;
-	struct gswip_gphy_fw *gphy_fw;
-	u32 port_vlan_filter;
-	struct mutex pce_table_lock;
-};
-
-struct gswip_pce_table_entry {
-	u16 index;      // PCE_TBL_ADDR.ADDR = pData->table_index
-	u16 table;      // PCE_TBL_CTRL.ADDR = pData->table
-	u16 key[8];
-	u16 val[5];
-	u16 mask;
-	u8 gmap;
-	bool type;
-	bool valid;
-	bool key_mode;
-};
-
-struct gswip_rmon_cnt_desc {
-	unsigned int size;
-	unsigned int offset;
-	const char *name;
-};
-
-#define MIB_DESC(_size, _offset, _name) {.size = _size, .offset = _offset, .name = _name}
-
-static const struct gswip_rmon_cnt_desc gswip_rmon_cnt[] = {
-	/** Receive Packet Count (only packets that are accepted and not discarded). */
-	MIB_DESC(1, 0x1F, "RxGoodPkts"),
-	MIB_DESC(1, 0x23, "RxUnicastPkts"),
-	MIB_DESC(1, 0x22, "RxMulticastPkts"),
-	MIB_DESC(1, 0x21, "RxFCSErrorPkts"),
-	MIB_DESC(1, 0x1D, "RxUnderSizeGoodPkts"),
-	MIB_DESC(1, 0x1E, "RxUnderSizeErrorPkts"),
-	MIB_DESC(1, 0x1B, "RxOversizeGoodPkts"),
-	MIB_DESC(1, 0x1C, "RxOversizeErrorPkts"),
-	MIB_DESC(1, 0x20, "RxGoodPausePkts"),
-	MIB_DESC(1, 0x1A, "RxAlignErrorPkts"),
-	MIB_DESC(1, 0x12, "Rx64BytePkts"),
-	MIB_DESC(1, 0x13, "Rx127BytePkts"),
-	MIB_DESC(1, 0x14, "Rx255BytePkts"),
-	MIB_DESC(1, 0x15, "Rx511BytePkts"),
-	MIB_DESC(1, 0x16, "Rx1023BytePkts"),
-	/** Receive Size 1024-1522 (or more, if configured) Packet Count. */
-	MIB_DESC(1, 0x17, "RxMaxBytePkts"),
-	MIB_DESC(1, 0x18, "RxDroppedPkts"),
-	MIB_DESC(1, 0x19, "RxFilteredPkts"),
-	MIB_DESC(2, 0x24, "RxGoodBytes"),
-	MIB_DESC(2, 0x26, "RxBadBytes"),
-	MIB_DESC(1, 0x11, "TxAcmDroppedPkts"),
-	MIB_DESC(1, 0x0C, "TxGoodPkts"),
-	MIB_DESC(1, 0x06, "TxUnicastPkts"),
-	MIB_DESC(1, 0x07, "TxMulticastPkts"),
-	MIB_DESC(1, 0x00, "Tx64BytePkts"),
-	MIB_DESC(1, 0x01, "Tx127BytePkts"),
-	MIB_DESC(1, 0x02, "Tx255BytePkts"),
-	MIB_DESC(1, 0x03, "Tx511BytePkts"),
-	MIB_DESC(1, 0x04, "Tx1023BytePkts"),
-	/** Transmit Size 1024-1522 (or more, if configured) Packet Count. */
-	MIB_DESC(1, 0x05, "TxMaxBytePkts"),
-	MIB_DESC(1, 0x08, "TxSingleCollCount"),
-	MIB_DESC(1, 0x09, "TxMultCollCount"),
-	MIB_DESC(1, 0x0A, "TxLateCollCount"),
-	MIB_DESC(1, 0x0B, "TxExcessCollCount"),
-	MIB_DESC(1, 0x0D, "TxPauseCount"),
-	MIB_DESC(1, 0x10, "TxDroppedPkts"),
-	MIB_DESC(2, 0x0E, "TxGoodBytes"),
-};
-
-static u32 gswip_switch_r(struct gswip_priv *priv, u32 offset)
-{
-	return __raw_readl(priv->gswip + (offset * 4));
-}
-
-static void gswip_switch_w(struct gswip_priv *priv, u32 val, u32 offset)
-{
-	__raw_writel(val, priv->gswip + (offset * 4));
-}
-
-static void gswip_switch_mask(struct gswip_priv *priv, u32 clear, u32 set,
-			      u32 offset)
-{
-	u32 val = gswip_switch_r(priv, offset);
-
-	val &= ~(clear);
-	val |= set;
-	gswip_switch_w(priv, val, offset);
-}
-
-static u32 gswip_switch_r_timeout(struct gswip_priv *priv, u32 offset,
-				  u32 cleared)
-{
-	u32 val;
-
-	return readx_poll_timeout(__raw_readl, priv->gswip + (offset * 4), val,
-				  (val & cleared) == 0, 20, 50000);
-}
-
-static u32 gswip_mdio_r(struct gswip_priv *priv, u32 offset)
-{
-	return __raw_readl(priv->mdio + (offset * 4));
-}
-
-static void gswip_mdio_w(struct gswip_priv *priv, u32 val, u32 offset)
-{
-	__raw_writel(val, priv->mdio + (offset * 4));
-}
-
-static void gswip_mdio_mask(struct gswip_priv *priv, u32 clear, u32 set,
-			    u32 offset)
-{
-	u32 val = gswip_mdio_r(priv, offset);
-
-	val &= ~(clear);
-	val |= set;
-	gswip_mdio_w(priv, val, offset);
-}
-
-static u32 gswip_mii_r(struct gswip_priv *priv, u32 offset)
-{
-	return __raw_readl(priv->mii + (offset * 4));
-}
-
-static void gswip_mii_w(struct gswip_priv *priv, u32 val, u32 offset)
-{
-	__raw_writel(val, priv->mii + (offset * 4));
-}
-
-static void gswip_mii_mask(struct gswip_priv *priv, u32 clear, u32 set,
-			   u32 offset)
-{
-	u32 val = gswip_mii_r(priv, offset);
-
-	val &= ~(clear);
-	val |= set;
-	gswip_mii_w(priv, val, offset);
-}
-
-static void gswip_mii_mask_cfg(struct gswip_priv *priv, u32 clear, u32 set,
-			       int port)
-{
-	/* There's no MII_CFG register for the CPU port */
-	if (!dsa_is_cpu_port(priv->ds, port))
-		gswip_mii_mask(priv, clear, set, GSWIP_MII_CFGp(port));
-}
-
-static void gswip_mii_mask_pcdu(struct gswip_priv *priv, u32 clear, u32 set,
-				int port)
-{
-	switch (port) {
-	case 0:
-		gswip_mii_mask(priv, clear, set, GSWIP_MII_PCDU0);
-		break;
-	case 1:
-		gswip_mii_mask(priv, clear, set, GSWIP_MII_PCDU1);
-		break;
-	case 5:
-		gswip_mii_mask(priv, clear, set, GSWIP_MII_PCDU5);
-		break;
-	}
-}
-
-static int gswip_mdio_poll(struct gswip_priv *priv)
-{
-	int cnt = 100;
-
-	while (likely(cnt--)) {
-		u32 ctrl = gswip_mdio_r(priv, GSWIP_MDIO_CTRL);
-
-		if ((ctrl & GSWIP_MDIO_CTRL_BUSY) == 0)
-			return 0;
-		usleep_range(20, 40);
-	}
-
-	return -ETIMEDOUT;
-}
-
-static int gswip_mdio_wr(struct mii_bus *bus, int addr, int reg, u16 val)
-{
-	struct gswip_priv *priv = bus->priv;
-	int err;
-
-	err = gswip_mdio_poll(priv);
-	if (err) {
-		dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n");
-		return err;
-	}
-
-	gswip_mdio_w(priv, val, GSWIP_MDIO_WRITE);
-	gswip_mdio_w(priv, GSWIP_MDIO_CTRL_BUSY | GSWIP_MDIO_CTRL_WR |
-		((addr & GSWIP_MDIO_CTRL_PHYAD_MASK) << GSWIP_MDIO_CTRL_PHYAD_SHIFT) |
-		(reg & GSWIP_MDIO_CTRL_REGAD_MASK),
-		GSWIP_MDIO_CTRL);
-
-	return 0;
-}
-
-static int gswip_mdio_rd(struct mii_bus *bus, int addr, int reg)
-{
-	struct gswip_priv *priv = bus->priv;
-	int err;
-
-	err = gswip_mdio_poll(priv);
-	if (err) {
-		dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n");
-		return err;
-	}
-
-	gswip_mdio_w(priv, GSWIP_MDIO_CTRL_BUSY | GSWIP_MDIO_CTRL_RD |
-		((addr & GSWIP_MDIO_CTRL_PHYAD_MASK) << GSWIP_MDIO_CTRL_PHYAD_SHIFT) |
-		(reg & GSWIP_MDIO_CTRL_REGAD_MASK),
-		GSWIP_MDIO_CTRL);
-
-	err = gswip_mdio_poll(priv);
-	if (err) {
-		dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n");
-		return err;
-	}
-
-	return gswip_mdio_r(priv, GSWIP_MDIO_READ);
-}
-
-static int gswip_mdio(struct gswip_priv *priv)
-{
-	struct device_node *mdio_np, *switch_np = priv->dev->of_node;
-	struct device *dev = priv->dev;
-	struct mii_bus *bus;
-	int err = 0;
-
-	mdio_np = of_get_compatible_child(switch_np, "lantiq,xrx200-mdio");
-	if (!of_device_is_available(mdio_np))
-		goto out_put_node;
-
-	bus = devm_mdiobus_alloc(dev);
-	if (!bus) {
-		err = -ENOMEM;
-		goto out_put_node;
-	}
-
-	bus->priv = priv;
-	bus->read = gswip_mdio_rd;
-	bus->write = gswip_mdio_wr;
-	bus->name = "lantiq,xrx200-mdio";
-	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(priv->dev));
-	bus->parent = priv->dev;
-
-	err = devm_of_mdiobus_register(dev, bus, mdio_np);
-
-out_put_node:
-	of_node_put(mdio_np);
-
-	return err;
-}
-
-static int gswip_pce_table_entry_read(struct gswip_priv *priv,
-				      struct gswip_pce_table_entry *tbl)
-{
-	int i;
-	int err;
-	u16 crtl;
-	u16 addr_mode = tbl->key_mode ? GSWIP_PCE_TBL_CTRL_OPMOD_KSRD :
-					GSWIP_PCE_TBL_CTRL_OPMOD_ADRD;
-
-	mutex_lock(&priv->pce_table_lock);
-
-	err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL,
-				     GSWIP_PCE_TBL_CTRL_BAS);
-	if (err) {
-		mutex_unlock(&priv->pce_table_lock);
-		return err;
-	}
-
-	gswip_switch_w(priv, tbl->index, GSWIP_PCE_TBL_ADDR);
-	gswip_switch_mask(priv, GSWIP_PCE_TBL_CTRL_ADDR_MASK |
-				GSWIP_PCE_TBL_CTRL_OPMOD_MASK,
-			  tbl->table | addr_mode | GSWIP_PCE_TBL_CTRL_BAS,
-			  GSWIP_PCE_TBL_CTRL);
-
-	err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL,
-				     GSWIP_PCE_TBL_CTRL_BAS);
-	if (err) {
-		mutex_unlock(&priv->pce_table_lock);
-		return err;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(tbl->key); i++)
-		tbl->key[i] = gswip_switch_r(priv, GSWIP_PCE_TBL_KEY(i));
-
-	for (i = 0; i < ARRAY_SIZE(tbl->val); i++)
-		tbl->val[i] = gswip_switch_r(priv, GSWIP_PCE_TBL_VAL(i));
-
-	tbl->mask = gswip_switch_r(priv, GSWIP_PCE_TBL_MASK);
-
-	crtl = gswip_switch_r(priv, GSWIP_PCE_TBL_CTRL);
-
-	tbl->type = !!(crtl & GSWIP_PCE_TBL_CTRL_TYPE);
-	tbl->valid = !!(crtl & GSWIP_PCE_TBL_CTRL_VLD);
-	tbl->gmap = (crtl & GSWIP_PCE_TBL_CTRL_GMAP_MASK) >> 7;
-
-	mutex_unlock(&priv->pce_table_lock);
-
-	return 0;
-}
-
-static int gswip_pce_table_entry_write(struct gswip_priv *priv,
-				       struct gswip_pce_table_entry *tbl)
-{
-	int i;
-	int err;
-	u16 crtl;
-	u16 addr_mode = tbl->key_mode ? GSWIP_PCE_TBL_CTRL_OPMOD_KSWR :
-					GSWIP_PCE_TBL_CTRL_OPMOD_ADWR;
-
-	mutex_lock(&priv->pce_table_lock);
-
-	err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL,
-				     GSWIP_PCE_TBL_CTRL_BAS);
-	if (err) {
-		mutex_unlock(&priv->pce_table_lock);
-		return err;
-	}
-
-	gswip_switch_w(priv, tbl->index, GSWIP_PCE_TBL_ADDR);
-	gswip_switch_mask(priv, GSWIP_PCE_TBL_CTRL_ADDR_MASK |
-				GSWIP_PCE_TBL_CTRL_OPMOD_MASK,
-			  tbl->table | addr_mode,
-			  GSWIP_PCE_TBL_CTRL);
-
-	for (i = 0; i < ARRAY_SIZE(tbl->key); i++)
-		gswip_switch_w(priv, tbl->key[i], GSWIP_PCE_TBL_KEY(i));
-
-	for (i = 0; i < ARRAY_SIZE(tbl->val); i++)
-		gswip_switch_w(priv, tbl->val[i], GSWIP_PCE_TBL_VAL(i));
-
-	gswip_switch_mask(priv, GSWIP_PCE_TBL_CTRL_ADDR_MASK |
-				GSWIP_PCE_TBL_CTRL_OPMOD_MASK,
-			  tbl->table | addr_mode,
-			  GSWIP_PCE_TBL_CTRL);
-
-	gswip_switch_w(priv, tbl->mask, GSWIP_PCE_TBL_MASK);
-
-	crtl = gswip_switch_r(priv, GSWIP_PCE_TBL_CTRL);
-	crtl &= ~(GSWIP_PCE_TBL_CTRL_TYPE | GSWIP_PCE_TBL_CTRL_VLD |
-		  GSWIP_PCE_TBL_CTRL_GMAP_MASK);
-	if (tbl->type)
-		crtl |= GSWIP_PCE_TBL_CTRL_TYPE;
-	if (tbl->valid)
-		crtl |= GSWIP_PCE_TBL_CTRL_VLD;
-	crtl |= (tbl->gmap << 7) & GSWIP_PCE_TBL_CTRL_GMAP_MASK;
-	crtl |= GSWIP_PCE_TBL_CTRL_BAS;
-	gswip_switch_w(priv, crtl, GSWIP_PCE_TBL_CTRL);
-
-	err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL,
-				     GSWIP_PCE_TBL_CTRL_BAS);
-
-	mutex_unlock(&priv->pce_table_lock);
-
-	return err;
-}
-
-/* Add the LAN port into a bridge with the CPU port by
- * default. This prevents automatic forwarding of
- * packages between the LAN ports when no explicit
- * bridge is configured.
- */
-static int gswip_add_single_port_br(struct gswip_priv *priv, int port, bool add)
-{
-	struct gswip_pce_table_entry vlan_active = {0,};
-	struct gswip_pce_table_entry vlan_mapping = {0,};
-	unsigned int cpu_port = priv->hw_info->cpu_port;
-	int err;
-
-	vlan_active.index = port + 1;
-	vlan_active.table = GSWIP_TABLE_ACTIVE_VLAN;
-	vlan_active.key[0] = 0; /* vid */
-	vlan_active.val[0] = port + 1 /* fid */;
-	vlan_active.valid = add;
-	err = gswip_pce_table_entry_write(priv, &vlan_active);
-	if (err) {
-		dev_err(priv->dev, "failed to write active VLAN: %d\n", err);
-		return err;
-	}
-
-	if (!add)
-		return 0;
-
-	vlan_mapping.index = port + 1;
-	vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING;
-	vlan_mapping.val[0] = 0 /* vid */;
-	vlan_mapping.val[1] = BIT(port) | BIT(cpu_port);
-	vlan_mapping.val[2] = 0;
-	err = gswip_pce_table_entry_write(priv, &vlan_mapping);
-	if (err) {
-		dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err);
-		return err;
-	}
-
-	return 0;
-}
-
-static int gswip_port_enable(struct dsa_switch *ds, int port,
-			     struct phy_device *phydev)
-{
-	struct gswip_priv *priv = ds->priv;
-	int err;
-
-	if (!dsa_is_cpu_port(ds, port)) {
-		u32 mdio_phy = 0;
-
-		err = gswip_add_single_port_br(priv, port, true);
-		if (err)
-			return err;
-
-		if (phydev)
-			mdio_phy = phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK;
-
-		gswip_mdio_mask(priv, GSWIP_MDIO_PHY_ADDR_MASK, mdio_phy,
-				GSWIP_MDIO_PHYp(port));
-	}
-
-	/* RMON Counter Enable for port */
-	gswip_switch_w(priv, GSWIP_BM_PCFG_CNTEN, GSWIP_BM_PCFGp(port));
-
-	/* enable port fetch/store dma & VLAN Modification */
-	gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_EN |
-				   GSWIP_FDMA_PCTRL_VLANMOD_BOTH,
-			 GSWIP_FDMA_PCTRLp(port));
-	gswip_switch_mask(priv, 0, GSWIP_SDMA_PCTRL_EN,
-			  GSWIP_SDMA_PCTRLp(port));
-
-	return 0;
-}
-
-static void gswip_port_disable(struct dsa_switch *ds, int port)
-{
-	struct gswip_priv *priv = ds->priv;
-
-	gswip_switch_mask(priv, GSWIP_FDMA_PCTRL_EN, 0,
-			  GSWIP_FDMA_PCTRLp(port));
-	gswip_switch_mask(priv, GSWIP_SDMA_PCTRL_EN, 0,
-			  GSWIP_SDMA_PCTRLp(port));
-}
-
-static int gswip_pce_load_microcode(struct gswip_priv *priv)
-{
-	int i;
-	int err;
-
-	gswip_switch_mask(priv, GSWIP_PCE_TBL_CTRL_ADDR_MASK |
-				GSWIP_PCE_TBL_CTRL_OPMOD_MASK,
-			  GSWIP_PCE_TBL_CTRL_OPMOD_ADWR, GSWIP_PCE_TBL_CTRL);
-	gswip_switch_w(priv, 0, GSWIP_PCE_TBL_MASK);
-
-	for (i = 0; i < ARRAY_SIZE(gswip_pce_microcode); i++) {
-		gswip_switch_w(priv, i, GSWIP_PCE_TBL_ADDR);
-		gswip_switch_w(priv, gswip_pce_microcode[i].val_0,
-			       GSWIP_PCE_TBL_VAL(0));
-		gswip_switch_w(priv, gswip_pce_microcode[i].val_1,
-			       GSWIP_PCE_TBL_VAL(1));
-		gswip_switch_w(priv, gswip_pce_microcode[i].val_2,
-			       GSWIP_PCE_TBL_VAL(2));
-		gswip_switch_w(priv, gswip_pce_microcode[i].val_3,
-			       GSWIP_PCE_TBL_VAL(3));
-
-		/* start the table access: */
-		gswip_switch_mask(priv, 0, GSWIP_PCE_TBL_CTRL_BAS,
-				  GSWIP_PCE_TBL_CTRL);
-		err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL,
-					     GSWIP_PCE_TBL_CTRL_BAS);
-		if (err)
-			return err;
-	}
-
-	/* tell the switch that the microcode is loaded */
-	gswip_switch_mask(priv, 0, GSWIP_PCE_GCTRL_0_MC_VALID,
-			  GSWIP_PCE_GCTRL_0);
-
-	return 0;
-}
-
-static int gswip_port_vlan_filtering(struct dsa_switch *ds, int port,
-				     bool vlan_filtering,
-				     struct netlink_ext_ack *extack)
-{
-	struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port));
-	struct gswip_priv *priv = ds->priv;
-
-	/* Do not allow changing the VLAN filtering options while in bridge */
-	if (bridge && !!(priv->port_vlan_filter & BIT(port)) != vlan_filtering) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "Dynamic toggling of vlan_filtering not supported");
-		return -EIO;
-	}
-
-	if (vlan_filtering) {
-		/* Use tag based VLAN */
-		gswip_switch_mask(priv,
-				  GSWIP_PCE_VCTRL_VSR,
-				  GSWIP_PCE_VCTRL_UVR | GSWIP_PCE_VCTRL_VIMR |
-				  GSWIP_PCE_VCTRL_VEMR,
-				  GSWIP_PCE_VCTRL(port));
-		gswip_switch_mask(priv, GSWIP_PCE_PCTRL_0_TVM, 0,
-				  GSWIP_PCE_PCTRL_0p(port));
-	} else {
-		/* Use port based VLAN */
-		gswip_switch_mask(priv,
-				  GSWIP_PCE_VCTRL_UVR | GSWIP_PCE_VCTRL_VIMR |
-				  GSWIP_PCE_VCTRL_VEMR,
-				  GSWIP_PCE_VCTRL_VSR,
-				  GSWIP_PCE_VCTRL(port));
-		gswip_switch_mask(priv, 0, GSWIP_PCE_PCTRL_0_TVM,
-				  GSWIP_PCE_PCTRL_0p(port));
-	}
-
-	return 0;
-}
-
-static int gswip_setup(struct dsa_switch *ds)
-{
-	struct gswip_priv *priv = ds->priv;
-	unsigned int cpu_port = priv->hw_info->cpu_port;
-	int i;
-	int err;
-
-	gswip_switch_w(priv, GSWIP_SWRES_R0, GSWIP_SWRES);
-	usleep_range(5000, 10000);
-	gswip_switch_w(priv, 0, GSWIP_SWRES);
-
-	/* disable port fetch/store dma on all ports */
-	for (i = 0; i < priv->hw_info->max_ports; i++) {
-		gswip_port_disable(ds, i);
-		gswip_port_vlan_filtering(ds, i, false, NULL);
-	}
-
-	/* enable Switch */
-	gswip_mdio_mask(priv, 0, GSWIP_MDIO_GLOB_ENABLE, GSWIP_MDIO_GLOB);
-
-	err = gswip_pce_load_microcode(priv);
-	if (err) {
-		dev_err(priv->dev, "writing PCE microcode failed, %i\n", err);
-		return err;
-	}
-
-	/* Default unknown Broadcast/Multicast/Unicast port maps */
-	gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP1);
-	gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP2);
-	gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP3);
-
-	/* Deactivate MDIO PHY auto polling. Some PHYs as the AR8030 have an
-	 * interoperability problem with this auto polling mechanism because
-	 * their status registers think that the link is in a different state
-	 * than it actually is. For the AR8030 it has the BMSR_ESTATEN bit set
-	 * as well as ESTATUS_1000_TFULL and ESTATUS_1000_XFULL. This makes the
-	 * auto polling state machine consider the link being negotiated with
-	 * 1Gbit/s. Since the PHY itself is a Fast Ethernet RMII PHY this leads
-	 * to the switch port being completely dead (RX and TX are both not
-	 * working).
-	 * Also with various other PHY / port combinations (PHY11G GPHY, PHY22F
-	 * GPHY, external RGMII PEF7071/7072) any traffic would stop. Sometimes
-	 * it would work fine for a few minutes to hours and then stop, on
-	 * other device it would no traffic could be sent or received at all.
-	 * Testing shows that when PHY auto polling is disabled these problems
-	 * go away.
-	 */
-	gswip_mdio_w(priv, 0x0, GSWIP_MDIO_MDC_CFG0);
-
-	/* Configure the MDIO Clock 2.5 MHz */
-	gswip_mdio_mask(priv, 0xff, 0x09, GSWIP_MDIO_MDC_CFG1);
-
-	/* Disable the xMII interface and clear it's isolation bit */
-	for (i = 0; i < priv->hw_info->max_ports; i++)
-		gswip_mii_mask_cfg(priv,
-				   GSWIP_MII_CFG_EN | GSWIP_MII_CFG_ISOLATE,
-				   0, i);
-
-	/* enable special tag insertion on cpu port */
-	gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_STEN,
-			  GSWIP_FDMA_PCTRLp(cpu_port));
-
-	/* accept special tag in ingress direction */
-	gswip_switch_mask(priv, 0, GSWIP_PCE_PCTRL_0_INGRESS,
-			  GSWIP_PCE_PCTRL_0p(cpu_port));
-
-	gswip_switch_mask(priv, 0, GSWIP_BM_QUEUE_GCTRL_GL_MOD,
-			  GSWIP_BM_QUEUE_GCTRL);
-
-	/* VLAN aware Switching */
-	gswip_switch_mask(priv, 0, GSWIP_PCE_GCTRL_0_VLAN, GSWIP_PCE_GCTRL_0);
-
-	/* Flush MAC Table */
-	gswip_switch_mask(priv, 0, GSWIP_PCE_GCTRL_0_MTFL, GSWIP_PCE_GCTRL_0);
-
-	err = gswip_switch_r_timeout(priv, GSWIP_PCE_GCTRL_0,
-				     GSWIP_PCE_GCTRL_0_MTFL);
-	if (err) {
-		dev_err(priv->dev, "MAC flushing didn't finish\n");
-		return err;
-	}
-
-	ds->mtu_enforcement_ingress = true;
-
-	ds->configure_vlan_while_not_filtering = false;
-
-	return 0;
-}
-
-static enum dsa_tag_protocol gswip_get_tag_protocol(struct dsa_switch *ds,
-						    int port,
-						    enum dsa_tag_protocol mp)
-{
-	return DSA_TAG_PROTO_GSWIP;
-}
-
-static int gswip_vlan_active_create(struct gswip_priv *priv,
-				    struct net_device *bridge,
-				    int fid, u16 vid)
-{
-	struct gswip_pce_table_entry vlan_active = {0,};
-	unsigned int max_ports = priv->hw_info->max_ports;
-	int idx = -1;
-	int err;
-	int i;
-
-	/* Look for a free slot */
-	for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) {
-		if (!priv->vlans[i].bridge) {
-			idx = i;
-			break;
-		}
-	}
-
-	if (idx == -1)
-		return -ENOSPC;
-
-	if (fid == -1)
-		fid = idx;
-
-	vlan_active.index = idx;
-	vlan_active.table = GSWIP_TABLE_ACTIVE_VLAN;
-	vlan_active.key[0] = vid;
-	vlan_active.val[0] = fid;
-	vlan_active.valid = true;
-
-	err = gswip_pce_table_entry_write(priv, &vlan_active);
-	if (err) {
-		dev_err(priv->dev, "failed to write active VLAN: %d\n",	err);
-		return err;
-	}
-
-	priv->vlans[idx].bridge = bridge;
-	priv->vlans[idx].vid = vid;
-	priv->vlans[idx].fid = fid;
-
-	return idx;
-}
-
-static int gswip_vlan_active_remove(struct gswip_priv *priv, int idx)
-{
-	struct gswip_pce_table_entry vlan_active = {0,};
-	int err;
-
-	vlan_active.index = idx;
-	vlan_active.table = GSWIP_TABLE_ACTIVE_VLAN;
-	vlan_active.valid = false;
-	err = gswip_pce_table_entry_write(priv, &vlan_active);
-	if (err)
-		dev_err(priv->dev, "failed to delete active VLAN: %d\n", err);
-	priv->vlans[idx].bridge = NULL;
-
-	return err;
-}
-
-static int gswip_vlan_add_unaware(struct gswip_priv *priv,
-				  struct net_device *bridge, int port)
-{
-	struct gswip_pce_table_entry vlan_mapping = {0,};
-	unsigned int max_ports = priv->hw_info->max_ports;
-	unsigned int cpu_port = priv->hw_info->cpu_port;
-	bool active_vlan_created = false;
-	int idx = -1;
-	int i;
-	int err;
-
-	/* Check if there is already a page for this bridge */
-	for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) {
-		if (priv->vlans[i].bridge == bridge) {
-			idx = i;
-			break;
-		}
-	}
-
-	/* If this bridge is not programmed yet, add a Active VLAN table
-	 * entry in a free slot and prepare the VLAN mapping table entry.
-	 */
-	if (idx == -1) {
-		idx = gswip_vlan_active_create(priv, bridge, -1, 0);
-		if (idx < 0)
-			return idx;
-		active_vlan_created = true;
-
-		vlan_mapping.index = idx;
-		vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING;
-		/* VLAN ID byte, maps to the VLAN ID of vlan active table */
-		vlan_mapping.val[0] = 0;
-	} else {
-		/* Read the existing VLAN mapping entry from the switch */
-		vlan_mapping.index = idx;
-		vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING;
-		err = gswip_pce_table_entry_read(priv, &vlan_mapping);
-		if (err) {
-			dev_err(priv->dev, "failed to read VLAN mapping: %d\n",
-				err);
-			return err;
-		}
-	}
-
-	/* Update the VLAN mapping entry and write it to the switch */
-	vlan_mapping.val[1] |= BIT(cpu_port);
-	vlan_mapping.val[1] |= BIT(port);
-	err = gswip_pce_table_entry_write(priv, &vlan_mapping);
-	if (err) {
-		dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err);
-		/* In case an Active VLAN was creaetd delete it again */
-		if (active_vlan_created)
-			gswip_vlan_active_remove(priv, idx);
-		return err;
-	}
-
-	gswip_switch_w(priv, 0, GSWIP_PCE_DEFPVID(port));
-	return 0;
-}
-
-static int gswip_vlan_add_aware(struct gswip_priv *priv,
-				struct net_device *bridge, int port,
-				u16 vid, bool untagged,
-				bool pvid)
-{
-	struct gswip_pce_table_entry vlan_mapping = {0,};
-	unsigned int max_ports = priv->hw_info->max_ports;
-	unsigned int cpu_port = priv->hw_info->cpu_port;
-	bool active_vlan_created = false;
-	int idx = -1;
-	int fid = -1;
-	int i;
-	int err;
-
-	/* Check if there is already a page for this bridge */
-	for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) {
-		if (priv->vlans[i].bridge == bridge) {
-			if (fid != -1 && fid != priv->vlans[i].fid)
-				dev_err(priv->dev, "one bridge with multiple flow ids\n");
-			fid = priv->vlans[i].fid;
-			if (priv->vlans[i].vid == vid) {
-				idx = i;
-				break;
-			}
-		}
-	}
-
-	/* If this bridge is not programmed yet, add a Active VLAN table
-	 * entry in a free slot and prepare the VLAN mapping table entry.
-	 */
-	if (idx == -1) {
-		idx = gswip_vlan_active_create(priv, bridge, fid, vid);
-		if (idx < 0)
-			return idx;
-		active_vlan_created = true;
-
-		vlan_mapping.index = idx;
-		vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING;
-		/* VLAN ID byte, maps to the VLAN ID of vlan active table */
-		vlan_mapping.val[0] = vid;
-	} else {
-		/* Read the existing VLAN mapping entry from the switch */
-		vlan_mapping.index = idx;
-		vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING;
-		err = gswip_pce_table_entry_read(priv, &vlan_mapping);
-		if (err) {
-			dev_err(priv->dev, "failed to read VLAN mapping: %d\n",
-				err);
-			return err;
-		}
-	}
-
-	vlan_mapping.val[0] = vid;
-	/* Update the VLAN mapping entry and write it to the switch */
-	vlan_mapping.val[1] |= BIT(cpu_port);
-	vlan_mapping.val[2] |= BIT(cpu_port);
-	vlan_mapping.val[1] |= BIT(port);
-	if (untagged)
-		vlan_mapping.val[2] &= ~BIT(port);
-	else
-		vlan_mapping.val[2] |= BIT(port);
-	err = gswip_pce_table_entry_write(priv, &vlan_mapping);
-	if (err) {
-		dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err);
-		/* In case an Active VLAN was creaetd delete it again */
-		if (active_vlan_created)
-			gswip_vlan_active_remove(priv, idx);
-		return err;
-	}
-
-	if (pvid)
-		gswip_switch_w(priv, idx, GSWIP_PCE_DEFPVID(port));
-
-	return 0;
-}
-
-static int gswip_vlan_remove(struct gswip_priv *priv,
-			     struct net_device *bridge, int port,
-			     u16 vid, bool pvid, bool vlan_aware)
-{
-	struct gswip_pce_table_entry vlan_mapping = {0,};
-	unsigned int max_ports = priv->hw_info->max_ports;
-	unsigned int cpu_port = priv->hw_info->cpu_port;
-	int idx = -1;
-	int i;
-	int err;
-
-	/* Check if there is already a page for this bridge */
-	for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) {
-		if (priv->vlans[i].bridge == bridge &&
-		    (!vlan_aware || priv->vlans[i].vid == vid)) {
-			idx = i;
-			break;
-		}
-	}
-
-	if (idx == -1) {
-		dev_err(priv->dev, "bridge to leave does not exists\n");
-		return -ENOENT;
-	}
-
-	vlan_mapping.index = idx;
-	vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING;
-	err = gswip_pce_table_entry_read(priv, &vlan_mapping);
-	if (err) {
-		dev_err(priv->dev, "failed to read VLAN mapping: %d\n",	err);
-		return err;
-	}
-
-	vlan_mapping.val[1] &= ~BIT(port);
-	vlan_mapping.val[2] &= ~BIT(port);
-	err = gswip_pce_table_entry_write(priv, &vlan_mapping);
-	if (err) {
-		dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err);
-		return err;
-	}
-
-	/* In case all ports are removed from the bridge, remove the VLAN */
-	if ((vlan_mapping.val[1] & ~BIT(cpu_port)) == 0) {
-		err = gswip_vlan_active_remove(priv, idx);
-		if (err) {
-			dev_err(priv->dev, "failed to write active VLAN: %d\n",
-				err);
-			return err;
-		}
-	}
-
-	/* GSWIP 2.2 (GRX300) and later program here the VID directly. */
-	if (pvid)
-		gswip_switch_w(priv, 0, GSWIP_PCE_DEFPVID(port));
-
-	return 0;
-}
-
-static int gswip_port_bridge_join(struct dsa_switch *ds, int port,
-				  struct dsa_bridge bridge,
-				  bool *tx_fwd_offload,
-				  struct netlink_ext_ack *extack)
-{
-	struct net_device *br = bridge.dev;
-	struct gswip_priv *priv = ds->priv;
-	int err;
-
-	/* When the bridge uses VLAN filtering we have to configure VLAN
-	 * specific bridges. No bridge is configured here.
-	 */
-	if (!br_vlan_enabled(br)) {
-		err = gswip_vlan_add_unaware(priv, br, port);
-		if (err)
-			return err;
-		priv->port_vlan_filter &= ~BIT(port);
-	} else {
-		priv->port_vlan_filter |= BIT(port);
-	}
-	return gswip_add_single_port_br(priv, port, false);
-}
-
-static void gswip_port_bridge_leave(struct dsa_switch *ds, int port,
-				    struct dsa_bridge bridge)
-{
-	struct net_device *br = bridge.dev;
-	struct gswip_priv *priv = ds->priv;
-
-	gswip_add_single_port_br(priv, port, true);
-
-	/* When the bridge uses VLAN filtering we have to configure VLAN
-	 * specific bridges. No bridge is configured here.
-	 */
-	if (!br_vlan_enabled(br))
-		gswip_vlan_remove(priv, br, port, 0, true, false);
-}
-
-static int gswip_port_vlan_prepare(struct dsa_switch *ds, int port,
-				   const struct switchdev_obj_port_vlan *vlan,
-				   struct netlink_ext_ack *extack)
-{
-	struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port));
-	struct gswip_priv *priv = ds->priv;
-	unsigned int max_ports = priv->hw_info->max_ports;
-	int pos = max_ports;
-	int i, idx = -1;
-
-	/* We only support VLAN filtering on bridges */
-	if (!dsa_is_cpu_port(ds, port) && !bridge)
-		return -EOPNOTSUPP;
-
-	/* Check if there is already a page for this VLAN */
-	for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) {
-		if (priv->vlans[i].bridge == bridge &&
-		    priv->vlans[i].vid == vlan->vid) {
-			idx = i;
-			break;
-		}
-	}
-
-	/* If this VLAN is not programmed yet, we have to reserve
-	 * one entry in the VLAN table. Make sure we start at the
-	 * next position round.
-	 */
-	if (idx == -1) {
-		/* Look for a free slot */
-		for (; pos < ARRAY_SIZE(priv->vlans); pos++) {
-			if (!priv->vlans[pos].bridge) {
-				idx = pos;
-				pos++;
-				break;
-			}
-		}
-
-		if (idx == -1) {
-			NL_SET_ERR_MSG_MOD(extack, "No slot in VLAN table");
-			return -ENOSPC;
-		}
-	}
-
-	return 0;
-}
-
-static int gswip_port_vlan_add(struct dsa_switch *ds, int port,
-			       const struct switchdev_obj_port_vlan *vlan,
-			       struct netlink_ext_ack *extack)
-{
-	struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port));
-	struct gswip_priv *priv = ds->priv;
-	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
-	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
-	int err;
-
-	err = gswip_port_vlan_prepare(ds, port, vlan, extack);
-	if (err)
-		return err;
-
-	/* We have to receive all packets on the CPU port and should not
-	 * do any VLAN filtering here. This is also called with bridge
-	 * NULL and then we do not know for which bridge to configure
-	 * this.
-	 */
-	if (dsa_is_cpu_port(ds, port))
-		return 0;
-
-	return gswip_vlan_add_aware(priv, bridge, port, vlan->vid,
-				    untagged, pvid);
-}
-
-static int gswip_port_vlan_del(struct dsa_switch *ds, int port,
-			       const struct switchdev_obj_port_vlan *vlan)
-{
-	struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port));
-	struct gswip_priv *priv = ds->priv;
-	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
-
-	/* We have to receive all packets on the CPU port and should not
-	 * do any VLAN filtering here. This is also called with bridge
-	 * NULL and then we do not know for which bridge to configure
-	 * this.
-	 */
-	if (dsa_is_cpu_port(ds, port))
-		return 0;
-
-	return gswip_vlan_remove(priv, bridge, port, vlan->vid, pvid, true);
-}
-
-static void gswip_port_fast_age(struct dsa_switch *ds, int port)
-{
-	struct gswip_priv *priv = ds->priv;
-	struct gswip_pce_table_entry mac_bridge = {0,};
-	int i;
-	int err;
-
-	for (i = 0; i < 2048; i++) {
-		mac_bridge.table = GSWIP_TABLE_MAC_BRIDGE;
-		mac_bridge.index = i;
-
-		err = gswip_pce_table_entry_read(priv, &mac_bridge);
-		if (err) {
-			dev_err(priv->dev, "failed to read mac bridge: %d\n",
-				err);
-			return;
-		}
-
-		if (!mac_bridge.valid)
-			continue;
-
-		if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC)
-			continue;
-
-		if (port != FIELD_GET(GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT,
-				      mac_bridge.val[0]))
-			continue;
-
-		mac_bridge.valid = false;
-		err = gswip_pce_table_entry_write(priv, &mac_bridge);
-		if (err) {
-			dev_err(priv->dev, "failed to write mac bridge: %d\n",
-				err);
-			return;
-		}
-	}
-}
-
-static void gswip_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
-{
-	struct gswip_priv *priv = ds->priv;
-	u32 stp_state;
-
-	switch (state) {
-	case BR_STATE_DISABLED:
-		gswip_switch_mask(priv, GSWIP_SDMA_PCTRL_EN, 0,
-				  GSWIP_SDMA_PCTRLp(port));
-		return;
-	case BR_STATE_BLOCKING:
-	case BR_STATE_LISTENING:
-		stp_state = GSWIP_PCE_PCTRL_0_PSTATE_LISTEN;
-		break;
-	case BR_STATE_LEARNING:
-		stp_state = GSWIP_PCE_PCTRL_0_PSTATE_LEARNING;
-		break;
-	case BR_STATE_FORWARDING:
-		stp_state = GSWIP_PCE_PCTRL_0_PSTATE_FORWARDING;
-		break;
-	default:
-		dev_err(priv->dev, "invalid STP state: %d\n", state);
-		return;
-	}
-
-	gswip_switch_mask(priv, 0, GSWIP_SDMA_PCTRL_EN,
-			  GSWIP_SDMA_PCTRLp(port));
-	gswip_switch_mask(priv, GSWIP_PCE_PCTRL_0_PSTATE_MASK, stp_state,
-			  GSWIP_PCE_PCTRL_0p(port));
-}
-
-static int gswip_port_fdb(struct dsa_switch *ds, int port,
-			  const unsigned char *addr, u16 vid, bool add)
-{
-	struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port));
-	struct gswip_priv *priv = ds->priv;
-	struct gswip_pce_table_entry mac_bridge = {0,};
-	unsigned int max_ports = priv->hw_info->max_ports;
-	int fid = -1;
-	int i;
-	int err;
-
-	if (!bridge)
-		return -EINVAL;
-
-	for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) {
-		if (priv->vlans[i].bridge == bridge) {
-			fid = priv->vlans[i].fid;
-			break;
-		}
-	}
-
-	if (fid == -1) {
-		dev_err(priv->dev, "no FID found for bridge %s\n",
-			bridge->name);
-		return -EINVAL;
-	}
-
-	mac_bridge.table = GSWIP_TABLE_MAC_BRIDGE;
-	mac_bridge.key_mode = true;
-	mac_bridge.key[0] = addr[5] | (addr[4] << 8);
-	mac_bridge.key[1] = addr[3] | (addr[2] << 8);
-	mac_bridge.key[2] = addr[1] | (addr[0] << 8);
-	mac_bridge.key[3] = FIELD_PREP(GSWIP_TABLE_MAC_BRIDGE_KEY3_FID, fid);
-	mac_bridge.val[0] = add ? BIT(port) : 0; /* port map */
-	mac_bridge.val[1] = GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC;
-	mac_bridge.valid = add;
-
-	err = gswip_pce_table_entry_write(priv, &mac_bridge);
-	if (err)
-		dev_err(priv->dev, "failed to write mac bridge: %d\n", err);
-
-	return err;
-}
-
-static int gswip_port_fdb_add(struct dsa_switch *ds, int port,
-			      const unsigned char *addr, u16 vid,
-			      struct dsa_db db)
-{
-	return gswip_port_fdb(ds, port, addr, vid, true);
-}
-
-static int gswip_port_fdb_del(struct dsa_switch *ds, int port,
-			      const unsigned char *addr, u16 vid,
-			      struct dsa_db db)
-{
-	return gswip_port_fdb(ds, port, addr, vid, false);
-}
-
-static int gswip_port_fdb_dump(struct dsa_switch *ds, int port,
-			       dsa_fdb_dump_cb_t *cb, void *data)
-{
-	struct gswip_priv *priv = ds->priv;
-	struct gswip_pce_table_entry mac_bridge = {0,};
-	unsigned char addr[ETH_ALEN];
-	int i;
-	int err;
-
-	for (i = 0; i < 2048; i++) {
-		mac_bridge.table = GSWIP_TABLE_MAC_BRIDGE;
-		mac_bridge.index = i;
-
-		err = gswip_pce_table_entry_read(priv, &mac_bridge);
-		if (err) {
-			dev_err(priv->dev,
-				"failed to read mac bridge entry %d: %d\n",
-				i, err);
-			return err;
-		}
-
-		if (!mac_bridge.valid)
-			continue;
-
-		addr[5] = mac_bridge.key[0] & 0xff;
-		addr[4] = (mac_bridge.key[0] >> 8) & 0xff;
-		addr[3] = mac_bridge.key[1] & 0xff;
-		addr[2] = (mac_bridge.key[1] >> 8) & 0xff;
-		addr[1] = mac_bridge.key[2] & 0xff;
-		addr[0] = (mac_bridge.key[2] >> 8) & 0xff;
-		if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC) {
-			if (mac_bridge.val[0] & BIT(port)) {
-				err = cb(addr, 0, true, data);
-				if (err)
-					return err;
-			}
-		} else {
-			if (port == FIELD_GET(GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT,
-					      mac_bridge.val[0])) {
-				err = cb(addr, 0, false, data);
-				if (err)
-					return err;
-			}
-		}
-	}
-	return 0;
-}
-
-static int gswip_port_max_mtu(struct dsa_switch *ds, int port)
-{
-	/* Includes 8 bytes for special header. */
-	return GSWIP_MAX_PACKET_LENGTH - VLAN_ETH_HLEN - ETH_FCS_LEN;
-}
-
-static int gswip_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
-{
-	struct gswip_priv *priv = ds->priv;
-
-	/* CPU port always has maximum mtu of user ports, so use it to set
-	 * switch frame size, including 8 byte special header.
-	 */
-	if (dsa_is_cpu_port(ds, port)) {
-		new_mtu += 8;
-		gswip_switch_w(priv, VLAN_ETH_HLEN + new_mtu + ETH_FCS_LEN,
-			       GSWIP_MAC_FLEN);
-	}
-
-	/* Enable MLEN for ports with non-standard MTUs, including the special
-	 * header on the CPU port added above.
-	 */
-	if (new_mtu != ETH_DATA_LEN)
-		gswip_switch_mask(priv, 0, GSWIP_MAC_CTRL_2_MLEN,
-				  GSWIP_MAC_CTRL_2p(port));
-	else
-		gswip_switch_mask(priv, GSWIP_MAC_CTRL_2_MLEN, 0,
-				  GSWIP_MAC_CTRL_2p(port));
-
-	return 0;
-}
-
-static void gswip_xrx200_phylink_get_caps(struct dsa_switch *ds, int port,
-					  struct phylink_config *config)
-{
-	switch (port) {
-	case 0:
-	case 1:
-		phy_interface_set_rgmii(config->supported_interfaces);
-		__set_bit(PHY_INTERFACE_MODE_MII,
-			  config->supported_interfaces);
-		__set_bit(PHY_INTERFACE_MODE_REVMII,
-			  config->supported_interfaces);
-		__set_bit(PHY_INTERFACE_MODE_RMII,
-			  config->supported_interfaces);
-		break;
-
-	case 2:
-	case 3:
-	case 4:
-	case 6:
-		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
-			  config->supported_interfaces);
-		break;
-
-	case 5:
-		phy_interface_set_rgmii(config->supported_interfaces);
-		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
-			  config->supported_interfaces);
-		break;
-	}
-
-	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
-		MAC_10 | MAC_100 | MAC_1000;
-}
-
-static void gswip_xrx300_phylink_get_caps(struct dsa_switch *ds, int port,
-					  struct phylink_config *config)
-{
-	switch (port) {
-	case 0:
-		phy_interface_set_rgmii(config->supported_interfaces);
-		__set_bit(PHY_INTERFACE_MODE_GMII,
-			  config->supported_interfaces);
-		__set_bit(PHY_INTERFACE_MODE_RMII,
-			  config->supported_interfaces);
-		break;
-
-	case 1:
-	case 2:
-	case 3:
-	case 4:
-	case 6:
-		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
-			  config->supported_interfaces);
-		break;
-
-	case 5:
-		phy_interface_set_rgmii(config->supported_interfaces);
-		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
-			  config->supported_interfaces);
-		__set_bit(PHY_INTERFACE_MODE_RMII,
-			  config->supported_interfaces);
-		break;
-	}
-
-	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
-		MAC_10 | MAC_100 | MAC_1000;
-}
-
-static void gswip_port_set_link(struct gswip_priv *priv, int port, bool link)
-{
-	u32 mdio_phy;
-
-	if (link)
-		mdio_phy = GSWIP_MDIO_PHY_LINK_UP;
-	else
-		mdio_phy = GSWIP_MDIO_PHY_LINK_DOWN;
-
-	gswip_mdio_mask(priv, GSWIP_MDIO_PHY_LINK_MASK, mdio_phy,
-			GSWIP_MDIO_PHYp(port));
-}
-
-static void gswip_port_set_speed(struct gswip_priv *priv, int port, int speed,
-				 phy_interface_t interface)
-{
-	u32 mdio_phy = 0, mii_cfg = 0, mac_ctrl_0 = 0;
-
-	switch (speed) {
-	case SPEED_10:
-		mdio_phy = GSWIP_MDIO_PHY_SPEED_M10;
-
-		if (interface == PHY_INTERFACE_MODE_RMII)
-			mii_cfg = GSWIP_MII_CFG_RATE_M50;
-		else
-			mii_cfg = GSWIP_MII_CFG_RATE_M2P5;
-
-		mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII;
-		break;
-
-	case SPEED_100:
-		mdio_phy = GSWIP_MDIO_PHY_SPEED_M100;
-
-		if (interface == PHY_INTERFACE_MODE_RMII)
-			mii_cfg = GSWIP_MII_CFG_RATE_M50;
-		else
-			mii_cfg = GSWIP_MII_CFG_RATE_M25;
-
-		mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII;
-		break;
-
-	case SPEED_1000:
-		mdio_phy = GSWIP_MDIO_PHY_SPEED_G1;
-
-		mii_cfg = GSWIP_MII_CFG_RATE_M125;
-
-		mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_RGMII;
-		break;
-	}
-
-	gswip_mdio_mask(priv, GSWIP_MDIO_PHY_SPEED_MASK, mdio_phy,
-			GSWIP_MDIO_PHYp(port));
-	gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_RATE_MASK, mii_cfg, port);
-	gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_GMII_MASK, mac_ctrl_0,
-			  GSWIP_MAC_CTRL_0p(port));
-}
-
-static void gswip_port_set_duplex(struct gswip_priv *priv, int port, int duplex)
-{
-	u32 mac_ctrl_0, mdio_phy;
-
-	if (duplex == DUPLEX_FULL) {
-		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_EN;
-		mdio_phy = GSWIP_MDIO_PHY_FDUP_EN;
-	} else {
-		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_DIS;
-		mdio_phy = GSWIP_MDIO_PHY_FDUP_DIS;
-	}
-
-	gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_FDUP_MASK, mac_ctrl_0,
-			  GSWIP_MAC_CTRL_0p(port));
-	gswip_mdio_mask(priv, GSWIP_MDIO_PHY_FDUP_MASK, mdio_phy,
-			GSWIP_MDIO_PHYp(port));
-}
-
-static void gswip_port_set_pause(struct gswip_priv *priv, int port,
-				 bool tx_pause, bool rx_pause)
-{
-	u32 mac_ctrl_0, mdio_phy;
-
-	if (tx_pause && rx_pause) {
-		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RXTX;
-		mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN |
-			   GSWIP_MDIO_PHY_FCONRX_EN;
-	} else if (tx_pause) {
-		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_TX;
-		mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN |
-			   GSWIP_MDIO_PHY_FCONRX_DIS;
-	} else if (rx_pause) {
-		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RX;
-		mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS |
-			   GSWIP_MDIO_PHY_FCONRX_EN;
-	} else {
-		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_NONE;
-		mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS |
-			   GSWIP_MDIO_PHY_FCONRX_DIS;
-	}
-
-	gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_FCON_MASK,
-			  mac_ctrl_0, GSWIP_MAC_CTRL_0p(port));
-	gswip_mdio_mask(priv,
-			GSWIP_MDIO_PHY_FCONTX_MASK |
-			GSWIP_MDIO_PHY_FCONRX_MASK,
-			mdio_phy, GSWIP_MDIO_PHYp(port));
-}
-
-static void gswip_phylink_mac_config(struct phylink_config *config,
-				     unsigned int mode,
-				     const struct phylink_link_state *state)
-{
-	struct dsa_port *dp = dsa_phylink_to_port(config);
-	struct gswip_priv *priv = dp->ds->priv;
-	int port = dp->index;
-	u32 miicfg = 0;
-
-	miicfg |= GSWIP_MII_CFG_LDCLKDIS;
-
-	switch (state->interface) {
-	case PHY_INTERFACE_MODE_MII:
-	case PHY_INTERFACE_MODE_INTERNAL:
-		miicfg |= GSWIP_MII_CFG_MODE_MIIM;
-		break;
-	case PHY_INTERFACE_MODE_REVMII:
-		miicfg |= GSWIP_MII_CFG_MODE_MIIP;
-		break;
-	case PHY_INTERFACE_MODE_RMII:
-		miicfg |= GSWIP_MII_CFG_MODE_RMIIM;
-		break;
-	case PHY_INTERFACE_MODE_RGMII:
-	case PHY_INTERFACE_MODE_RGMII_ID:
-	case PHY_INTERFACE_MODE_RGMII_RXID:
-	case PHY_INTERFACE_MODE_RGMII_TXID:
-		miicfg |= GSWIP_MII_CFG_MODE_RGMII;
-		break;
-	case PHY_INTERFACE_MODE_GMII:
-		miicfg |= GSWIP_MII_CFG_MODE_GMII;
-		break;
-	default:
-		dev_err(dp->ds->dev,
-			"Unsupported interface: %d\n", state->interface);
-		return;
-	}
-
-	gswip_mii_mask_cfg(priv,
-			   GSWIP_MII_CFG_MODE_MASK | GSWIP_MII_CFG_RMII_CLK |
-			   GSWIP_MII_CFG_RGMII_IBS | GSWIP_MII_CFG_LDCLKDIS,
-			   miicfg, port);
-
-	switch (state->interface) {
-	case PHY_INTERFACE_MODE_RGMII_ID:
-		gswip_mii_mask_pcdu(priv, GSWIP_MII_PCDU_TXDLY_MASK |
-					  GSWIP_MII_PCDU_RXDLY_MASK, 0, port);
-		break;
-	case PHY_INTERFACE_MODE_RGMII_RXID:
-		gswip_mii_mask_pcdu(priv, GSWIP_MII_PCDU_RXDLY_MASK, 0, port);
-		break;
-	case PHY_INTERFACE_MODE_RGMII_TXID:
-		gswip_mii_mask_pcdu(priv, GSWIP_MII_PCDU_TXDLY_MASK, 0, port);
-		break;
-	default:
-		break;
-	}
-}
-
-static void gswip_phylink_mac_link_down(struct phylink_config *config,
-					unsigned int mode,
-					phy_interface_t interface)
-{
-	struct dsa_port *dp = dsa_phylink_to_port(config);
-	struct gswip_priv *priv = dp->ds->priv;
-	int port = dp->index;
-
-	gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, port);
-
-	if (!dsa_port_is_cpu(dp))
-		gswip_port_set_link(priv, port, false);
-}
-
-static void gswip_phylink_mac_link_up(struct phylink_config *config,
-				      struct phy_device *phydev,
-				      unsigned int mode,
-				      phy_interface_t interface,
-				      int speed, int duplex,
-				      bool tx_pause, bool rx_pause)
-{
-	struct dsa_port *dp = dsa_phylink_to_port(config);
-	struct gswip_priv *priv = dp->ds->priv;
-	int port = dp->index;
-
-	if (!dsa_port_is_cpu(dp)) {
-		gswip_port_set_link(priv, port, true);
-		gswip_port_set_speed(priv, port, speed, interface);
-		gswip_port_set_duplex(priv, port, duplex);
-		gswip_port_set_pause(priv, port, tx_pause, rx_pause);
-	}
-
-	gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port);
-}
-
-static void gswip_get_strings(struct dsa_switch *ds, int port, u32 stringset,
-			      uint8_t *data)
-{
-	int i;
-
-	if (stringset != ETH_SS_STATS)
-		return;
-
-	for (i = 0; i < ARRAY_SIZE(gswip_rmon_cnt); i++)
-		ethtool_puts(&data, gswip_rmon_cnt[i].name);
-}
-
-static u32 gswip_bcm_ram_entry_read(struct gswip_priv *priv, u32 table,
-				    u32 index)
-{
-	u32 result;
-	int err;
-
-	gswip_switch_w(priv, index, GSWIP_BM_RAM_ADDR);
-	gswip_switch_mask(priv, GSWIP_BM_RAM_CTRL_ADDR_MASK |
-				GSWIP_BM_RAM_CTRL_OPMOD,
-			      table | GSWIP_BM_RAM_CTRL_BAS,
-			      GSWIP_BM_RAM_CTRL);
-
-	err = gswip_switch_r_timeout(priv, GSWIP_BM_RAM_CTRL,
-				     GSWIP_BM_RAM_CTRL_BAS);
-	if (err) {
-		dev_err(priv->dev, "timeout while reading table: %u, index: %u\n",
-			table, index);
-		return 0;
-	}
-
-	result = gswip_switch_r(priv, GSWIP_BM_RAM_VAL(0));
-	result |= gswip_switch_r(priv, GSWIP_BM_RAM_VAL(1)) << 16;
-
-	return result;
-}
-
-static void gswip_get_ethtool_stats(struct dsa_switch *ds, int port,
-				    uint64_t *data)
-{
-	struct gswip_priv *priv = ds->priv;
-	const struct gswip_rmon_cnt_desc *rmon_cnt;
-	int i;
-	u64 high;
-
-	for (i = 0; i < ARRAY_SIZE(gswip_rmon_cnt); i++) {
-		rmon_cnt = &gswip_rmon_cnt[i];
-
-		data[i] = gswip_bcm_ram_entry_read(priv, port,
-						   rmon_cnt->offset);
-		if (rmon_cnt->size == 2) {
-			high = gswip_bcm_ram_entry_read(priv, port,
-							rmon_cnt->offset + 1);
-			data[i] |= high << 32;
-		}
-	}
-}
-
-static int gswip_get_sset_count(struct dsa_switch *ds, int port, int sset)
-{
-	if (sset != ETH_SS_STATS)
-		return 0;
-
-	return ARRAY_SIZE(gswip_rmon_cnt);
-}
-
-static const struct phylink_mac_ops gswip_phylink_mac_ops = {
-	.mac_config	= gswip_phylink_mac_config,
-	.mac_link_down	= gswip_phylink_mac_link_down,
-	.mac_link_up	= gswip_phylink_mac_link_up,
-};
-
-static const struct dsa_switch_ops gswip_xrx200_switch_ops = {
-	.get_tag_protocol	= gswip_get_tag_protocol,
-	.setup			= gswip_setup,
-	.port_enable		= gswip_port_enable,
-	.port_disable		= gswip_port_disable,
-	.port_bridge_join	= gswip_port_bridge_join,
-	.port_bridge_leave	= gswip_port_bridge_leave,
-	.port_fast_age		= gswip_port_fast_age,
-	.port_vlan_filtering	= gswip_port_vlan_filtering,
-	.port_vlan_add		= gswip_port_vlan_add,
-	.port_vlan_del		= gswip_port_vlan_del,
-	.port_stp_state_set	= gswip_port_stp_state_set,
-	.port_fdb_add		= gswip_port_fdb_add,
-	.port_fdb_del		= gswip_port_fdb_del,
-	.port_fdb_dump		= gswip_port_fdb_dump,
-	.port_change_mtu	= gswip_port_change_mtu,
-	.port_max_mtu		= gswip_port_max_mtu,
-	.phylink_get_caps	= gswip_xrx200_phylink_get_caps,
-	.get_strings		= gswip_get_strings,
-	.get_ethtool_stats	= gswip_get_ethtool_stats,
-	.get_sset_count		= gswip_get_sset_count,
-};
-
-static const struct dsa_switch_ops gswip_xrx300_switch_ops = {
-	.get_tag_protocol	= gswip_get_tag_protocol,
-	.setup			= gswip_setup,
-	.port_enable		= gswip_port_enable,
-	.port_disable		= gswip_port_disable,
-	.port_bridge_join	= gswip_port_bridge_join,
-	.port_bridge_leave	= gswip_port_bridge_leave,
-	.port_fast_age		= gswip_port_fast_age,
-	.port_vlan_filtering	= gswip_port_vlan_filtering,
-	.port_vlan_add		= gswip_port_vlan_add,
-	.port_vlan_del		= gswip_port_vlan_del,
-	.port_stp_state_set	= gswip_port_stp_state_set,
-	.port_fdb_add		= gswip_port_fdb_add,
-	.port_fdb_del		= gswip_port_fdb_del,
-	.port_fdb_dump		= gswip_port_fdb_dump,
-	.port_change_mtu	= gswip_port_change_mtu,
-	.port_max_mtu		= gswip_port_max_mtu,
-	.phylink_get_caps	= gswip_xrx300_phylink_get_caps,
-	.get_strings		= gswip_get_strings,
-	.get_ethtool_stats	= gswip_get_ethtool_stats,
-	.get_sset_count		= gswip_get_sset_count,
-};
-
-static const struct xway_gphy_match_data xrx200a1x_gphy_data = {
-	.fe_firmware_name = "lantiq/xrx200_phy22f_a14.bin",
-	.ge_firmware_name = "lantiq/xrx200_phy11g_a14.bin",
-};
-
-static const struct xway_gphy_match_data xrx200a2x_gphy_data = {
-	.fe_firmware_name = "lantiq/xrx200_phy22f_a22.bin",
-	.ge_firmware_name = "lantiq/xrx200_phy11g_a22.bin",
-};
-
-static const struct xway_gphy_match_data xrx300_gphy_data = {
-	.fe_firmware_name = "lantiq/xrx300_phy22f_a21.bin",
-	.ge_firmware_name = "lantiq/xrx300_phy11g_a21.bin",
-};
-
-static const struct of_device_id xway_gphy_match[] __maybe_unused = {
-	{ .compatible = "lantiq,xrx200-gphy-fw", .data = NULL },
-	{ .compatible = "lantiq,xrx200a1x-gphy-fw", .data = &xrx200a1x_gphy_data },
-	{ .compatible = "lantiq,xrx200a2x-gphy-fw", .data = &xrx200a2x_gphy_data },
-	{ .compatible = "lantiq,xrx300-gphy-fw", .data = &xrx300_gphy_data },
-	{ .compatible = "lantiq,xrx330-gphy-fw", .data = &xrx300_gphy_data },
-	{},
-};
-
-static int gswip_gphy_fw_load(struct gswip_priv *priv, struct gswip_gphy_fw *gphy_fw)
-{
-	struct device *dev = priv->dev;
-	const struct firmware *fw;
-	void *fw_addr;
-	dma_addr_t dma_addr;
-	dma_addr_t dev_addr;
-	size_t size;
-	int ret;
-
-	ret = clk_prepare_enable(gphy_fw->clk_gate);
-	if (ret)
-		return ret;
-
-	reset_control_assert(gphy_fw->reset);
-
-	/* The vendor BSP uses a 200ms delay after asserting the reset line.
-	 * Without this some users are observing that the PHY is not coming up
-	 * on the MDIO bus.
-	 */
-	msleep(200);
-
-	ret = request_firmware(&fw, gphy_fw->fw_name, dev);
-	if (ret)
-		return dev_err_probe(dev, ret, "failed to load firmware: %s\n",
-				     gphy_fw->fw_name);
-
-	/* GPHY cores need the firmware code in a persistent and contiguous
-	 * memory area with a 16 kB boundary aligned start address.
-	 */
-	size = fw->size + XRX200_GPHY_FW_ALIGN;
-
-	fw_addr = dmam_alloc_coherent(dev, size, &dma_addr, GFP_KERNEL);
-	if (fw_addr) {
-		fw_addr = PTR_ALIGN(fw_addr, XRX200_GPHY_FW_ALIGN);
-		dev_addr = ALIGN(dma_addr, XRX200_GPHY_FW_ALIGN);
-		memcpy(fw_addr, fw->data, fw->size);
-	} else {
-		release_firmware(fw);
-		return dev_err_probe(dev, -ENOMEM,
-				     "failed to alloc firmware memory\n");
-	}
-
-	release_firmware(fw);
-
-	ret = regmap_write(priv->rcu_regmap, gphy_fw->fw_addr_offset, dev_addr);
-	if (ret)
-		return ret;
-
-	reset_control_deassert(gphy_fw->reset);
-
-	return ret;
-}
-
-static int gswip_gphy_fw_probe(struct gswip_priv *priv,
-			       struct gswip_gphy_fw *gphy_fw,
-			       struct device_node *gphy_fw_np, int i)
-{
-	struct device *dev = priv->dev;
-	u32 gphy_mode;
-	int ret;
-	char gphyname[10];
-
-	snprintf(gphyname, sizeof(gphyname), "gphy%d", i);
-
-	gphy_fw->clk_gate = devm_clk_get(dev, gphyname);
-	if (IS_ERR(gphy_fw->clk_gate)) {
-		return dev_err_probe(dev, PTR_ERR(gphy_fw->clk_gate),
-				     "Failed to lookup gate clock\n");
-	}
-
-	ret = of_property_read_u32(gphy_fw_np, "reg", &gphy_fw->fw_addr_offset);
-	if (ret)
-		return ret;
-
-	ret = of_property_read_u32(gphy_fw_np, "lantiq,gphy-mode", &gphy_mode);
-	/* Default to GE mode */
-	if (ret)
-		gphy_mode = GPHY_MODE_GE;
-
-	switch (gphy_mode) {
-	case GPHY_MODE_FE:
-		gphy_fw->fw_name = priv->gphy_fw_name_cfg->fe_firmware_name;
-		break;
-	case GPHY_MODE_GE:
-		gphy_fw->fw_name = priv->gphy_fw_name_cfg->ge_firmware_name;
-		break;
-	default:
-		return dev_err_probe(dev, -EINVAL, "Unknown GPHY mode %d\n",
-				     gphy_mode);
-	}
-
-	gphy_fw->reset = of_reset_control_array_get_exclusive(gphy_fw_np);
-	if (IS_ERR(gphy_fw->reset))
-		return dev_err_probe(dev, PTR_ERR(gphy_fw->reset),
-				     "Failed to lookup gphy reset\n");
-
-	return gswip_gphy_fw_load(priv, gphy_fw);
-}
-
-static void gswip_gphy_fw_remove(struct gswip_priv *priv,
-				 struct gswip_gphy_fw *gphy_fw)
-{
-	int ret;
-
-	/* check if the device was fully probed */
-	if (!gphy_fw->fw_name)
-		return;
-
-	ret = regmap_write(priv->rcu_regmap, gphy_fw->fw_addr_offset, 0);
-	if (ret)
-		dev_err(priv->dev, "can not reset GPHY FW pointer\n");
-
-	clk_disable_unprepare(gphy_fw->clk_gate);
-
-	reset_control_put(gphy_fw->reset);
-}
-
-static int gswip_gphy_fw_list(struct gswip_priv *priv,
-			      struct device_node *gphy_fw_list_np, u32 version)
-{
-	struct device *dev = priv->dev;
-	struct device_node *gphy_fw_np;
-	const struct of_device_id *match;
-	int err;
-	int i = 0;
-
-	/* The VRX200 rev 1.1 uses the GSWIP 2.0 and needs the older
-	 * GPHY firmware. The VRX200 rev 1.2 uses the GSWIP 2.1 and also
-	 * needs a different GPHY firmware.
-	 */
-	if (of_device_is_compatible(gphy_fw_list_np, "lantiq,xrx200-gphy-fw")) {
-		switch (version) {
-		case GSWIP_VERSION_2_0:
-			priv->gphy_fw_name_cfg = &xrx200a1x_gphy_data;
-			break;
-		case GSWIP_VERSION_2_1:
-			priv->gphy_fw_name_cfg = &xrx200a2x_gphy_data;
-			break;
-		default:
-			return dev_err_probe(dev, -ENOENT,
-					     "unknown GSWIP version: 0x%x\n",
-					     version);
-		}
-	}
-
-	match = of_match_node(xway_gphy_match, gphy_fw_list_np);
-	if (match && match->data)
-		priv->gphy_fw_name_cfg = match->data;
-
-	if (!priv->gphy_fw_name_cfg)
-		return dev_err_probe(dev, -ENOENT,
-				     "GPHY compatible type not supported\n");
-
-	priv->num_gphy_fw = of_get_available_child_count(gphy_fw_list_np);
-	if (!priv->num_gphy_fw)
-		return -ENOENT;
-
-	priv->rcu_regmap = syscon_regmap_lookup_by_phandle(gphy_fw_list_np,
-							   "lantiq,rcu");
-	if (IS_ERR(priv->rcu_regmap))
-		return PTR_ERR(priv->rcu_regmap);
-
-	priv->gphy_fw = devm_kmalloc_array(dev, priv->num_gphy_fw,
-					   sizeof(*priv->gphy_fw),
-					   GFP_KERNEL | __GFP_ZERO);
-	if (!priv->gphy_fw)
-		return -ENOMEM;
-
-	for_each_available_child_of_node(gphy_fw_list_np, gphy_fw_np) {
-		err = gswip_gphy_fw_probe(priv, &priv->gphy_fw[i],
-					  gphy_fw_np, i);
-		if (err) {
-			of_node_put(gphy_fw_np);
-			goto remove_gphy;
-		}
-		i++;
-	}
-
-	/* The standalone PHY11G requires 300ms to be fully
-	 * initialized and ready for any MDIO communication after being
-	 * taken out of reset. For the SoC-internal GPHY variant there
-	 * is no (known) documentation for the minimum time after a
-	 * reset. Use the same value as for the standalone variant as
-	 * some users have reported internal PHYs not being detected
-	 * without any delay.
-	 */
-	msleep(300);
-
-	return 0;
-
-remove_gphy:
-	for (i = 0; i < priv->num_gphy_fw; i++)
-		gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]);
-	return err;
-}
-
-static int gswip_probe(struct platform_device *pdev)
-{
-	struct device_node *np, *gphy_fw_np;
-	struct device *dev = &pdev->dev;
-	struct gswip_priv *priv;
-	int err;
-	int i;
-	u32 version;
-
-	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return -ENOMEM;
-
-	priv->gswip = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(priv->gswip))
-		return PTR_ERR(priv->gswip);
-
-	priv->mdio = devm_platform_ioremap_resource(pdev, 1);
-	if (IS_ERR(priv->mdio))
-		return PTR_ERR(priv->mdio);
-
-	priv->mii = devm_platform_ioremap_resource(pdev, 2);
-	if (IS_ERR(priv->mii))
-		return PTR_ERR(priv->mii);
-
-	priv->hw_info = of_device_get_match_data(dev);
-	if (!priv->hw_info)
-		return -EINVAL;
-
-	priv->ds = devm_kzalloc(dev, sizeof(*priv->ds), GFP_KERNEL);
-	if (!priv->ds)
-		return -ENOMEM;
-
-	priv->ds->dev = dev;
-	priv->ds->num_ports = priv->hw_info->max_ports;
-	priv->ds->priv = priv;
-	priv->ds->ops = priv->hw_info->ops;
-	priv->ds->phylink_mac_ops = &gswip_phylink_mac_ops;
-	priv->dev = dev;
-	mutex_init(&priv->pce_table_lock);
-	version = gswip_switch_r(priv, GSWIP_VERSION);
-
-	np = dev->of_node;
-	switch (version) {
-	case GSWIP_VERSION_2_0:
-	case GSWIP_VERSION_2_1:
-		if (!of_device_is_compatible(np, "lantiq,xrx200-gswip"))
-			return -EINVAL;
-		break;
-	case GSWIP_VERSION_2_2:
-	case GSWIP_VERSION_2_2_ETC:
-		if (!of_device_is_compatible(np, "lantiq,xrx300-gswip") &&
-		    !of_device_is_compatible(np, "lantiq,xrx330-gswip"))
-			return -EINVAL;
-		break;
-	default:
-		return dev_err_probe(dev, -ENOENT,
-				     "unknown GSWIP version: 0x%x\n", version);
-	}
-
-	/* bring up the mdio bus */
-	gphy_fw_np = of_get_compatible_child(dev->of_node, "lantiq,gphy-fw");
-	if (gphy_fw_np) {
-		err = gswip_gphy_fw_list(priv, gphy_fw_np, version);
-		of_node_put(gphy_fw_np);
-		if (err)
-			return dev_err_probe(dev, err,
-					     "gphy fw probe failed\n");
-	}
-
-	/* bring up the mdio bus */
-	err = gswip_mdio(priv);
-	if (err) {
-		dev_err_probe(dev, err, "mdio probe failed\n");
-		goto gphy_fw_remove;
-	}
-
-	err = dsa_register_switch(priv->ds);
-	if (err) {
-		dev_err_probe(dev, err, "dsa switch registration failed\n");
-		goto gphy_fw_remove;
-	}
-	if (!dsa_is_cpu_port(priv->ds, priv->hw_info->cpu_port)) {
-		err = dev_err_probe(dev, -EINVAL,
-				    "wrong CPU port defined, HW only supports port: %i\n",
-				    priv->hw_info->cpu_port);
-		goto disable_switch;
-	}
-
-	platform_set_drvdata(pdev, priv);
-
-	dev_info(dev, "probed GSWIP version %lx mod %lx\n",
-		 (version & GSWIP_VERSION_REV_MASK) >> GSWIP_VERSION_REV_SHIFT,
-		 (version & GSWIP_VERSION_MOD_MASK) >> GSWIP_VERSION_MOD_SHIFT);
-	return 0;
-
-disable_switch:
-	gswip_mdio_mask(priv, GSWIP_MDIO_GLOB_ENABLE, 0, GSWIP_MDIO_GLOB);
-	dsa_unregister_switch(priv->ds);
-gphy_fw_remove:
-	for (i = 0; i < priv->num_gphy_fw; i++)
-		gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]);
-	return err;
-}
-
-static void gswip_remove(struct platform_device *pdev)
-{
-	struct gswip_priv *priv = platform_get_drvdata(pdev);
-	int i;
-
-	if (!priv)
-		return;
-
-	/* disable the switch */
-	gswip_mdio_mask(priv, GSWIP_MDIO_GLOB_ENABLE, 0, GSWIP_MDIO_GLOB);
-
-	dsa_unregister_switch(priv->ds);
-
-	for (i = 0; i < priv->num_gphy_fw; i++)
-		gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]);
-}
-
-static void gswip_shutdown(struct platform_device *pdev)
-{
-	struct gswip_priv *priv = platform_get_drvdata(pdev);
-
-	if (!priv)
-		return;
-
-	dsa_switch_shutdown(priv->ds);
-
-	platform_set_drvdata(pdev, NULL);
-}
-
-static const struct gswip_hw_info gswip_xrx200 = {
-	.max_ports = 7,
-	.cpu_port = 6,
-	.ops = &gswip_xrx200_switch_ops,
-};
-
-static const struct gswip_hw_info gswip_xrx300 = {
-	.max_ports = 7,
-	.cpu_port = 6,
-	.ops = &gswip_xrx300_switch_ops,
-};
-
-static const struct of_device_id gswip_of_match[] = {
-	{ .compatible = "lantiq,xrx200-gswip", .data = &gswip_xrx200 },
-	{ .compatible = "lantiq,xrx300-gswip", .data = &gswip_xrx300 },
-	{ .compatible = "lantiq,xrx330-gswip", .data = &gswip_xrx300 },
-	{},
-};
-MODULE_DEVICE_TABLE(of, gswip_of_match);
-
-static struct platform_driver gswip_driver = {
-	.probe = gswip_probe,
-	.remove = gswip_remove,
-	.shutdown = gswip_shutdown,
-	.driver = {
-		.name = "gswip",
-		.of_match_table = gswip_of_match,
-	},
-};
-
-module_platform_driver(gswip_driver);
-
-MODULE_FIRMWARE("lantiq/xrx300_phy11g_a21.bin");
-MODULE_FIRMWARE("lantiq/xrx300_phy22f_a21.bin");
-MODULE_FIRMWARE("lantiq/xrx200_phy11g_a14.bin");
-MODULE_FIRMWARE("lantiq/xrx200_phy11g_a22.bin");
-MODULE_FIRMWARE("lantiq/xrx200_phy22f_a14.bin");
-MODULE_FIRMWARE("lantiq/xrx200_phy22f_a22.bin");
-MODULE_AUTHOR("Hauke Mehrtens <hauke@hauke-m.de>");
-MODULE_DESCRIPTION("Lantiq / Intel GSWIP driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/dsa/microchip/Kconfig b/drivers/net/dsa/microchip/Kconfig
index 12a86585a77f..c71d3fd5dfeb 100644
--- a/drivers/net/dsa/microchip/Kconfig
+++ b/drivers/net/dsa/microchip/Kconfig
@@ -6,6 +6,7 @@ menuconfig NET_DSA_MICROCHIP_KSZ_COMMON
 	select NET_DSA_TAG_NONE
 	select NET_IEEE8021Q_HELPERS
 	select DCB
+	select PCS_XPCS
 	help
 	  This driver adds support for Microchip KSZ8, KSZ9 and
 	  LAN937X series switch chips, being KSZ8863/8873,
diff --git a/drivers/net/dsa/microchip/ksz8.c b/drivers/net/dsa/microchip/ksz8.c
index da7110d67558..c354abdafc1b 100644
--- a/drivers/net/dsa/microchip/ksz8.c
+++ b/drivers/net/dsa/microchip/ksz8.c
@@ -3,6 +3,7 @@
  * Microchip KSZ8XXX series switch driver
  *
  * It supports the following switches:
+ * - KSZ8463
  * - KSZ8863, KSZ8873 aka KSZ88X3
  * - KSZ8895, KSZ8864 aka KSZ8895 family
  * - KSZ8794, KSZ8795, KSZ8765 aka KSZ87XX
@@ -35,14 +36,14 @@
 
 static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set)
 {
-	regmap_update_bits(ksz_regmap_8(dev), addr, bits, set ? bits : 0);
+	ksz_rmw8(dev, addr, bits, set ? bits : 0);
 }
 
 static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits,
 			 bool set)
 {
-	regmap_update_bits(ksz_regmap_8(dev), PORT_CTRL_ADDR(port, offset),
-			   bits, set ? bits : 0);
+	ksz_rmw8(dev, dev->dev_ops->get_port_addr(port, offset), bits,
+		 set ? bits : 0);
 }
 
 /**
@@ -140,6 +141,11 @@ int ksz8_reset_switch(struct ksz_device *dev)
 			KSZ8863_GLOBAL_SOFTWARE_RESET | KSZ8863_PCS_RESET, true);
 		ksz_cfg(dev, KSZ8863_REG_SW_RESET,
 			KSZ8863_GLOBAL_SOFTWARE_RESET | KSZ8863_PCS_RESET, false);
+	} else if (ksz_is_ksz8463(dev)) {
+		ksz_cfg(dev, KSZ8463_REG_SW_RESET,
+			KSZ8463_GLOBAL_SOFTWARE_RESET, true);
+		ksz_cfg(dev, KSZ8463_REG_SW_RESET,
+			KSZ8463_GLOBAL_SOFTWARE_RESET, false);
 	} else {
 		/* reset switch */
 		ksz_write8(dev, REG_POWER_MANAGEMENT_1,
@@ -194,6 +200,7 @@ int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu)
 	case KSZ8794_CHIP_ID:
 	case KSZ8765_CHIP_ID:
 		return ksz8795_change_mtu(dev, frame_size);
+	case KSZ8463_CHIP_ID:
 	case KSZ88X3_CHIP_ID:
 	case KSZ8864_CHIP_ID:
 	case KSZ8895_CHIP_ID:
@@ -227,6 +234,11 @@ static int ksz8_port_queue_split(struct ksz_device *dev, int port, int queues)
 			       WEIGHTED_FAIR_QUEUE_ENABLE);
 		if (ret)
 			return ret;
+	} else if (ksz_is_ksz8463(dev)) {
+		mask_4q = KSZ8873_PORT_4QUEUE_SPLIT_EN;
+		mask_2q = KSZ8873_PORT_2QUEUE_SPLIT_EN;
+		reg_4q = P1CR1;
+		reg_2q = P1CR1 + 1;
 	} else {
 		mask_4q = KSZ8795_PORT_4QUEUE_SPLIT_EN;
 		mask_2q = KSZ8795_PORT_2QUEUE_SPLIT_EN;
@@ -371,6 +383,9 @@ static void ksz8863_r_mib_pkt(struct ksz_device *dev, int port, u16 addr,
 	addr -= dev->info->reg_mib_cnt;
 	ctrl_addr = addr ? KSZ8863_MIB_PACKET_DROPPED_TX_0 :
 			   KSZ8863_MIB_PACKET_DROPPED_RX_0;
+	if (ksz_is_8895_family(dev) &&
+	    ctrl_addr == KSZ8863_MIB_PACKET_DROPPED_RX_0)
+		ctrl_addr = KSZ8895_MIB_PACKET_DROPPED_RX_0;
 	ctrl_addr += port;
 	ctrl_addr |= IND_ACC_TABLE(TABLE_MIB | TABLE_READ);
 
@@ -1265,12 +1280,15 @@ int ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val)
 
 void ksz8_cfg_port_member(struct ksz_device *dev, int port, u8 member)
 {
+	int offset = P_MIRROR_CTRL;
 	u8 data;
 
-	ksz_pread8(dev, port, P_MIRROR_CTRL, &data);
-	data &= ~PORT_VLAN_MEMBERSHIP;
+	if (ksz_is_ksz8463(dev))
+		offset = P1CR2;
+	ksz_pread8(dev, port, offset, &data);
+	data &= ~dev->port_mask;
 	data |= (member & dev->port_mask);
-	ksz_pwrite8(dev, port, P_MIRROR_CTRL, data);
+	ksz_pwrite8(dev, port, offset, data);
 }
 
 void ksz8_flush_dyn_mac_table(struct ksz_device *dev, int port)
@@ -1278,6 +1296,8 @@ void ksz8_flush_dyn_mac_table(struct ksz_device *dev, int port)
 	u8 learn[DSA_MAX_PORTS];
 	int first, index, cnt;
 	const u16 *regs;
+	int reg = S_FLUSH_TABLE_CTRL;
+	int mask = SW_FLUSH_DYN_MAC_TABLE;
 
 	regs = dev->info->regs;
 
@@ -1295,7 +1315,11 @@ void ksz8_flush_dyn_mac_table(struct ksz_device *dev, int port)
 			ksz_pwrite8(dev, index, regs[P_STP_CTRL],
 				    learn[index] | PORT_LEARN_DISABLE);
 	}
-	ksz_cfg(dev, S_FLUSH_TABLE_CTRL, SW_FLUSH_DYN_MAC_TABLE, true);
+	if (ksz_is_ksz8463(dev)) {
+		reg = KSZ8463_FLUSH_TABLE_CTRL;
+		mask = KSZ8463_FLUSH_DYN_MAC_TABLE;
+	}
+	ksz_cfg(dev, reg, mask, true);
 	for (index = first; index < cnt; index++) {
 		if (!(learn[index] & PORT_LEARN_DISABLE))
 			ksz_pwrite8(dev, index, regs[P_STP_CTRL], learn[index]);
@@ -1434,7 +1458,7 @@ int ksz8_fdb_del(struct ksz_device *dev, int port, const unsigned char *addr,
 int ksz8_port_vlan_filtering(struct ksz_device *dev, int port, bool flag,
 			     struct netlink_ext_ack *extack)
 {
-	if (ksz_is_ksz88x3(dev))
+	if (ksz_is_ksz88x3(dev) || ksz_is_ksz8463(dev))
 		return -ENOTSUPP;
 
 	/* Discard packets with VID not enabled on the switch */
@@ -1450,9 +1474,12 @@ int ksz8_port_vlan_filtering(struct ksz_device *dev, int port, bool flag,
 
 static void ksz8_port_enable_pvid(struct ksz_device *dev, int port, bool state)
 {
-	if (ksz_is_ksz88x3(dev)) {
-		ksz_cfg(dev, REG_SW_INSERT_SRC_PVID,
-			0x03 << (4 - 2 * port), state);
+	if (ksz_is_ksz88x3(dev) || ksz_is_ksz8463(dev)) {
+		int reg = REG_SW_INSERT_SRC_PVID;
+
+		if (ksz_is_ksz8463(dev))
+			reg = KSZ8463_REG_SW_CTRL_9;
+		ksz_cfg(dev, reg, 0x03 << (4 - 2 * port), state);
 	} else {
 		ksz_pwrite8(dev, port, REG_PORT_CTRL_12, state ? 0x0f : 0x00);
 	}
@@ -1467,7 +1494,7 @@ int ksz8_port_vlan_add(struct ksz_device *dev, int port,
 	u16 data, new_pvid = 0;
 	u8 fid, member, valid;
 
-	if (ksz_is_ksz88x3(dev))
+	if (ksz_is_ksz88x3(dev) || ksz_is_ksz8463(dev))
 		return -ENOTSUPP;
 
 	/* If a VLAN is added with untagged flag different from the
@@ -1536,7 +1563,7 @@ int ksz8_port_vlan_del(struct ksz_device *dev, int port,
 	u16 data, pvid;
 	u8 fid, member, valid;
 
-	if (ksz_is_ksz88x3(dev))
+	if (ksz_is_ksz88x3(dev) || ksz_is_ksz8463(dev))
 		return -ENOTSUPP;
 
 	ksz_pread16(dev, port, REG_PORT_CTRL_VID, &pvid);
@@ -1566,19 +1593,23 @@ int ksz8_port_mirror_add(struct ksz_device *dev, int port,
 			 struct dsa_mall_mirror_tc_entry *mirror,
 			 bool ingress, struct netlink_ext_ack *extack)
 {
+	int offset = P_MIRROR_CTRL;
+
+	if (ksz_is_ksz8463(dev))
+		offset = P1CR2;
 	if (ingress) {
-		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, true);
+		ksz_port_cfg(dev, port, offset, PORT_MIRROR_RX, true);
 		dev->mirror_rx |= BIT(port);
 	} else {
-		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, true);
+		ksz_port_cfg(dev, port, offset, PORT_MIRROR_TX, true);
 		dev->mirror_tx |= BIT(port);
 	}
 
-	ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_SNIFFER, false);
+	ksz_port_cfg(dev, port, offset, PORT_MIRROR_SNIFFER, false);
 
 	/* configure mirror port */
 	if (dev->mirror_rx || dev->mirror_tx)
-		ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL,
+		ksz_port_cfg(dev, mirror->to_local_port, offset,
 			     PORT_MIRROR_SNIFFER, true);
 
 	return 0;
@@ -1587,20 +1618,23 @@ int ksz8_port_mirror_add(struct ksz_device *dev, int port,
 void ksz8_port_mirror_del(struct ksz_device *dev, int port,
 			  struct dsa_mall_mirror_tc_entry *mirror)
 {
+	int offset = P_MIRROR_CTRL;
 	u8 data;
 
+	if (ksz_is_ksz8463(dev))
+		offset = P1CR2;
 	if (mirror->ingress) {
-		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, false);
+		ksz_port_cfg(dev, port, offset, PORT_MIRROR_RX, false);
 		dev->mirror_rx &= ~BIT(port);
 	} else {
-		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, false);
+		ksz_port_cfg(dev, port, offset, PORT_MIRROR_TX, false);
 		dev->mirror_tx &= ~BIT(port);
 	}
 
-	ksz_pread8(dev, port, P_MIRROR_CTRL, &data);
+	ksz_pread8(dev, port, offset, &data);
 
 	if (!dev->mirror_rx && !dev->mirror_tx)
-		ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL,
+		ksz_port_cfg(dev, mirror->to_local_port, offset,
 			     PORT_MIRROR_SNIFFER, false);
 }
 
@@ -1625,26 +1659,24 @@ void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 	const u16 *regs = dev->info->regs;
 	struct dsa_switch *ds = dev->ds;
 	const u32 *masks;
-	int queues;
+	int offset;
 	u8 member;
 
 	masks = dev->info->masks;
 
 	/* enable broadcast storm limit */
-	ksz_port_cfg(dev, port, P_BCAST_STORM_CTRL, PORT_BROADCAST_STORM, true);
-
-	/* For KSZ88x3 enable only one queue by default, otherwise we won't
-	 * be able to get rid of PCP prios on Port 2.
-	 */
-	if (ksz_is_ksz88x3(dev))
-		queues = 1;
-	else
-		queues = dev->info->num_tx_queues;
+	offset = P_BCAST_STORM_CTRL;
+	if (ksz_is_ksz8463(dev))
+		offset = P1CR1;
+	ksz_port_cfg(dev, port, offset, PORT_BROADCAST_STORM, true);
 
-	ksz8_port_queue_split(dev, port, queues);
+	ksz8_port_queue_split(dev, port, dev->info->num_tx_queues);
 
 	/* replace priority */
-	ksz_port_cfg(dev, port, P_802_1P_CTRL,
+	offset = P_802_1P_CTRL;
+	if (ksz_is_ksz8463(dev))
+		offset = P1CR2;
+	ksz_port_cfg(dev, port, offset,
 		     masks[PORT_802_1P_REMAPPING], false);
 
 	if (cpu_port)
@@ -1684,6 +1716,7 @@ void ksz8_config_cpu_port(struct dsa_switch *ds)
 	const u32 *masks;
 	const u16 *regs;
 	u8 remote;
+	u8 fiber_ports = 0;
 	int i;
 
 	masks = dev->info->masks;
@@ -1714,6 +1747,32 @@ void ksz8_config_cpu_port(struct dsa_switch *ds)
 		else
 			ksz_port_cfg(dev, i, regs[P_STP_CTRL],
 				     PORT_FORCE_FLOW_CTRL, false);
+		if (p->fiber)
+			fiber_ports |= (1 << i);
+	}
+	if (ksz_is_ksz8463(dev)) {
+		/* Setup fiber ports. */
+		if (fiber_ports) {
+			fiber_ports &= 3;
+			regmap_update_bits(ksz_regmap_16(dev),
+					   KSZ8463_REG_CFG_CTRL,
+					   fiber_ports << PORT_COPPER_MODE_S,
+					   0);
+			regmap_update_bits(ksz_regmap_16(dev),
+					   KSZ8463_REG_DSP_CTRL_6,
+					   COPPER_RECEIVE_ADJUSTMENT, 0);
+		}
+
+		/* Turn off PTP function as the switch's proprietary way of
+		 * handling timestamp is not supported in current Linux PTP
+		 * stack implementation.
+		 */
+		regmap_update_bits(ksz_regmap_16(dev),
+				   KSZ8463_PTP_MSG_CONF1,
+				   PTP_ENABLE, 0);
+		regmap_update_bits(ksz_regmap_16(dev),
+				   KSZ8463_PTP_CLK_CTRL,
+				   PTP_CLK_ENABLE, 0);
 	}
 }
 
@@ -1895,22 +1954,25 @@ int ksz8_setup(struct dsa_switch *ds)
 	ksz_cfg(dev, S_LINK_AGING_CTRL, SW_LINK_AUTO_AGING, true);
 
 	/* Enable aggressive back off algorithm in half duplex mode. */
-	regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_1,
-			   SW_AGGR_BACKOFF, SW_AGGR_BACKOFF);
+	ret = ksz_rmw8(dev, REG_SW_CTRL_1, SW_AGGR_BACKOFF, SW_AGGR_BACKOFF);
+	if (ret)
+		return ret;
 
 	/*
 	 * Make sure unicast VLAN boundary is set as default and
 	 * enable no excessive collision drop.
 	 */
-	regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_2,
-			   UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP,
-			   UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP);
+	ret = ksz_rmw8(dev, REG_SW_CTRL_2,
+		       UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP,
+		       UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP);
+	if (ret)
+		return ret;
 
 	ksz_cfg(dev, S_REPLACE_VID_CTRL, SW_REPLACE_VID, false);
 
 	ksz_cfg(dev, S_MIRROR_CTRL, SW_MIRROR_RX_TX, false);
 
-	if (!ksz_is_ksz88x3(dev))
+	if (!ksz_is_ksz88x3(dev) && !ksz_is_ksz8463(dev))
 		ksz_cfg(dev, REG_SW_CTRL_19, SW_INS_TAG_ENABLE, true);
 
 	for (i = 0; i < (dev->info->num_vlans / 4); i++)
@@ -1956,6 +2018,84 @@ u32 ksz8_get_port_addr(int port, int offset)
 	return PORT_CTRL_ADDR(port, offset);
 }
 
+u32 ksz8463_get_port_addr(int port, int offset)
+{
+	return offset + 0x18 * port;
+}
+
+static u16 ksz8463_get_phy_addr(u16 phy, u16 reg, u16 offset)
+{
+	return offset + reg * 2 + phy * (P2MBCR - P1MBCR);
+}
+
+int ksz8463_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val)
+{
+	u16 sw_reg = 0;
+	u16 data = 0;
+	int ret;
+
+	if (phy > 1)
+		return -ENOSPC;
+	switch (reg) {
+	case MII_PHYSID1:
+		sw_reg = ksz8463_get_phy_addr(phy, 0, PHY1IHR);
+		break;
+	case MII_PHYSID2:
+		sw_reg = ksz8463_get_phy_addr(phy, 0, PHY1ILR);
+		break;
+	case MII_BMCR:
+	case MII_BMSR:
+	case MII_ADVERTISE:
+	case MII_LPA:
+		sw_reg = ksz8463_get_phy_addr(phy, reg, P1MBCR);
+		break;
+	case MII_TPISTATUS:
+		/* This register holds the PHY interrupt status for simulated
+		 * Micrel KSZ PHY.
+		 */
+		data = 0x0505;
+		break;
+	default:
+		break;
+	}
+	if (sw_reg) {
+		ret = ksz_read16(dev, sw_reg, &data);
+		if (ret)
+			return ret;
+	}
+	*val = data;
+
+	return 0;
+}
+
+int ksz8463_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val)
+{
+	u16 sw_reg = 0;
+	int ret;
+
+	if (phy > 1)
+		return -ENOSPC;
+
+	/* No write to fiber port. */
+	if (dev->ports[phy].fiber)
+		return 0;
+	switch (reg) {
+	case MII_BMCR:
+	case MII_ADVERTISE:
+		sw_reg = ksz8463_get_phy_addr(phy, reg, P1MBCR);
+		break;
+	default:
+		break;
+	}
+	if (sw_reg) {
+		ret = ksz_write16(dev, sw_reg, val);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 int ksz8_switch_init(struct ksz_device *dev)
 {
 	dev->cpu_port = fls(dev->info->cpu_ports) - 1;
diff --git a/drivers/net/dsa/microchip/ksz8.h b/drivers/net/dsa/microchip/ksz8.h
index e1c79ff97123..0f2cd1474b44 100644
--- a/drivers/net/dsa/microchip/ksz8.h
+++ b/drivers/net/dsa/microchip/ksz8.h
@@ -63,4 +63,8 @@ void ksz8_phylink_mac_link_up(struct phylink_config *config,
 			      bool tx_pause, bool rx_pause);
 int ksz8_all_queues_split(struct ksz_device *dev, int queues);
 
+u32 ksz8463_get_port_addr(int port, int offset);
+int ksz8463_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val);
+int ksz8463_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val);
+
 #endif
diff --git a/drivers/net/dsa/microchip/ksz8_reg.h b/drivers/net/dsa/microchip/ksz8_reg.h
index 329688603a58..332408567b47 100644
--- a/drivers/net/dsa/microchip/ksz8_reg.h
+++ b/drivers/net/dsa/microchip/ksz8_reg.h
@@ -729,6 +729,55 @@
 #define PHY_POWER_SAVING_ENABLE		BIT(2)
 #define PHY_REMOTE_LOOPBACK		BIT(1)
 
+/* KSZ8463 specific registers. */
+#define P1MBCR				0x4C
+#define P1MBSR				0x4E
+#define PHY1ILR				0x50
+#define PHY1IHR				0x52
+#define P1ANAR				0x54
+#define P1ANLPR				0x56
+#define P2MBCR				0x58
+#define P2MBSR				0x5A
+#define PHY2ILR				0x5C
+#define PHY2IHR				0x5E
+#define P2ANAR				0x60
+#define P2ANLPR				0x62
+
+#define P1CR1				0x6C
+#define P1CR2				0x6E
+#define P1CR3				0x72
+#define P1CR4				0x7E
+#define P1SR				0x80
+
+#define KSZ8463_FLUSH_TABLE_CTRL	0xAD
+
+#define KSZ8463_FLUSH_DYN_MAC_TABLE	BIT(2)
+#define KSZ8463_FLUSH_STA_MAC_TABLE	BIT(1)
+
+#define KSZ8463_REG_SW_CTRL_9		0xAE
+
+#define KSZ8463_REG_CFG_CTRL		0xD8
+
+#define PORT_2_COPPER_MODE		BIT(7)
+#define PORT_1_COPPER_MODE		BIT(6)
+#define PORT_COPPER_MODE_S		6
+
+#define KSZ8463_REG_SW_RESET		0x126
+
+#define KSZ8463_GLOBAL_SOFTWARE_RESET	BIT(0)
+
+#define KSZ8463_PTP_CLK_CTRL		0x600
+
+#define PTP_CLK_ENABLE			BIT(1)
+
+#define KSZ8463_PTP_MSG_CONF1		0x620
+
+#define PTP_ENABLE			BIT(6)
+
+#define KSZ8463_REG_DSP_CTRL_6		0x734
+
+#define COPPER_RECEIVE_ADJUSTMENT	BIT(13)
+
 /* Chip resource */
 
 #define PRIO_QUEUES			4
@@ -784,7 +833,9 @@
 #define KSZ8795_MIB_TOTAL_TX_1		0x105
 
 #define KSZ8863_MIB_PACKET_DROPPED_TX_0 0x100
-#define KSZ8863_MIB_PACKET_DROPPED_RX_0 0x105
+#define KSZ8863_MIB_PACKET_DROPPED_RX_0 0x103
+
+#define KSZ8895_MIB_PACKET_DROPPED_RX_0 0x105
 
 #define MIB_PACKET_DROPPED		0x0000FFFF
 
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index d16817e0476f..5facffbb9c9a 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -2,7 +2,7 @@
 /*
  * Microchip KSZ9477 switch driver main logic
  *
- * Copyright (C) 2017-2019 Microchip Technology Inc.
+ * Copyright (C) 2017-2025 Microchip Technology Inc.
  */
 
 #include <linux/kernel.h>
@@ -161,6 +161,190 @@ static int ksz9477_wait_alu_sta_ready(struct ksz_device *dev)
 					10, 1000);
 }
 
+static void port_sgmii_s(struct ksz_device *dev, uint port, u16 devid, u16 reg)
+{
+	u32 data;
+
+	data = (devid & MII_MMD_CTRL_DEVAD_MASK) << 16;
+	data |= reg;
+	ksz_pwrite32(dev, port, REG_PORT_SGMII_ADDR__4, data);
+}
+
+static void port_sgmii_r(struct ksz_device *dev, uint port, u16 devid, u16 reg,
+			 u16 *buf)
+{
+	port_sgmii_s(dev, port, devid, reg);
+	ksz_pread16(dev, port, REG_PORT_SGMII_DATA__4 + 2, buf);
+}
+
+static void port_sgmii_w(struct ksz_device *dev, uint port, u16 devid, u16 reg,
+			 u16 buf)
+{
+	port_sgmii_s(dev, port, devid, reg);
+	ksz_pwrite32(dev, port, REG_PORT_SGMII_DATA__4, buf);
+}
+
+static int ksz9477_pcs_read(struct mii_bus *bus, int phy, int mmd, int reg)
+{
+	struct ksz_device *dev = bus->priv;
+	int port = ksz_get_sgmii_port(dev);
+	u16 val;
+
+	port_sgmii_r(dev, port, mmd, reg, &val);
+
+	/* Simulate a value to activate special code in the XPCS driver if
+	 * supported.
+	 */
+	if (mmd == MDIO_MMD_PMAPMD) {
+		if (reg == MDIO_DEVID1)
+			val = 0x9477;
+		else if (reg == MDIO_DEVID2)
+			val = 0x22 << 10;
+	} else if (mmd == MDIO_MMD_VEND2) {
+		struct ksz_port *p = &dev->ports[port];
+
+		/* Need to update MII_BMCR register with the exact speed and
+		 * duplex mode when running in SGMII mode and this register is
+		 * used to detect connected speed in that mode.
+		 */
+		if (reg == MMD_SR_MII_AUTO_NEG_STATUS) {
+			int duplex, speed;
+
+			if (val & SR_MII_STAT_LINK_UP) {
+				speed = (val >> SR_MII_STAT_S) & SR_MII_STAT_M;
+				if (speed == SR_MII_STAT_1000_MBPS)
+					speed = SPEED_1000;
+				else if (speed == SR_MII_STAT_100_MBPS)
+					speed = SPEED_100;
+				else
+					speed = SPEED_10;
+
+				if (val & SR_MII_STAT_FULL_DUPLEX)
+					duplex = DUPLEX_FULL;
+				else
+					duplex = DUPLEX_HALF;
+
+				if (!p->phydev.link ||
+				    p->phydev.speed != speed ||
+				    p->phydev.duplex != duplex) {
+					u16 ctrl;
+
+					p->phydev.link = 1;
+					p->phydev.speed = speed;
+					p->phydev.duplex = duplex;
+					port_sgmii_r(dev, port, mmd, MII_BMCR,
+						     &ctrl);
+					ctrl &= BMCR_ANENABLE;
+					ctrl |= mii_bmcr_encode_fixed(speed,
+								      duplex);
+					port_sgmii_w(dev, port, mmd, MII_BMCR,
+						     ctrl);
+				}
+			} else {
+				p->phydev.link = 0;
+			}
+		} else if (reg == MII_BMSR) {
+			p->phydev.link = !!(val & BMSR_LSTATUS);
+		}
+	}
+
+	return val;
+}
+
+static int ksz9477_pcs_write(struct mii_bus *bus, int phy, int mmd, int reg,
+			     u16 val)
+{
+	struct ksz_device *dev = bus->priv;
+	int port = ksz_get_sgmii_port(dev);
+
+	if (mmd == MDIO_MMD_VEND2) {
+		struct ksz_port *p = &dev->ports[port];
+
+		if (reg == MMD_SR_MII_AUTO_NEG_CTRL) {
+			u16 sgmii_mode = SR_MII_PCS_SGMII << SR_MII_PCS_MODE_S;
+
+			/* Need these bits for 1000BASE-X mode to work with
+			 * AN on.
+			 */
+			if (!(val & sgmii_mode))
+				val |= SR_MII_SGMII_LINK_UP |
+				       SR_MII_TX_CFG_PHY_MASTER;
+
+			/* SGMII interrupt in the port cannot be masked, so
+			 * make sure interrupt is not enabled as it is not
+			 * handled.
+			 */
+			val &= ~SR_MII_AUTO_NEG_COMPLETE_INTR;
+		} else if (reg == MII_BMCR) {
+			/* The MII_ADVERTISE register needs to write once
+			 * before doing auto-negotiation for the correct
+			 * config_word to be sent out after reset.
+			 */
+			if ((val & BMCR_ANENABLE) && !p->sgmii_adv_write) {
+				u16 adv;
+
+				/* The SGMII port cannot disable flow control
+				 * so it is better to just advertise symmetric
+				 * pause.
+				 */
+				port_sgmii_r(dev, port, mmd, MII_ADVERTISE,
+					     &adv);
+				adv |= ADVERTISE_1000XPAUSE;
+				adv &= ~ADVERTISE_1000XPSE_ASYM;
+				port_sgmii_w(dev, port, mmd, MII_ADVERTISE,
+					     adv);
+				p->sgmii_adv_write = 1;
+			} else if (val & BMCR_RESET) {
+				p->sgmii_adv_write = 0;
+			}
+		} else if (reg == MII_ADVERTISE) {
+			/* XPCS driver writes to this register so there is no
+			 * need to update it for the errata.
+			 */
+			p->sgmii_adv_write = 1;
+		}
+	}
+	port_sgmii_w(dev, port, mmd, reg, val);
+
+	return 0;
+}
+
+int ksz9477_pcs_create(struct ksz_device *dev)
+{
+	/* This chip has a SGMII port. */
+	if (ksz_has_sgmii_port(dev)) {
+		int port = ksz_get_sgmii_port(dev);
+		struct ksz_port *p = &dev->ports[port];
+		struct phylink_pcs *pcs;
+		struct mii_bus *bus;
+		int ret;
+
+		bus = devm_mdiobus_alloc(dev->dev);
+		if (!bus)
+			return -ENOMEM;
+
+		bus->name = "ksz_pcs_mdio_bus";
+		snprintf(bus->id, MII_BUS_ID_SIZE, "%s-pcs",
+			 dev_name(dev->dev));
+		bus->read_c45 = &ksz9477_pcs_read;
+		bus->write_c45 = &ksz9477_pcs_write;
+		bus->parent = dev->dev;
+		bus->phy_mask = ~0;
+		bus->priv = dev;
+
+		ret = devm_mdiobus_register(dev->dev, bus);
+		if (ret)
+			return ret;
+
+		pcs = xpcs_create_pcs_mdiodev(bus, 0);
+		if (IS_ERR(pcs))
+			return PTR_ERR(pcs);
+		p->pcs = pcs;
+	}
+
+	return 0;
+}
+
 int ksz9477_reset_switch(struct ksz_device *dev)
 {
 	u8 data8;
@@ -978,31 +1162,64 @@ void ksz9477_get_caps(struct ksz_device *dev, int port,
 
 	if (dev->info->gbit_capable[port])
 		config->mac_capabilities |= MAC_1000FD;
+
+	if (ksz_is_sgmii_port(dev, port)) {
+		struct ksz_port *p = &dev->ports[port];
+
+		phy_interface_or(config->supported_interfaces,
+				 config->supported_interfaces,
+				 p->pcs->supported_interfaces);
+	}
 }
 
 int ksz9477_set_ageing_time(struct ksz_device *dev, unsigned int msecs)
 {
 	u32 secs = msecs / 1000;
-	u8 value;
-	u8 data;
+	u8 data, mult, value;
+	u32 max_val;
 	int ret;
 
-	value = FIELD_GET(SW_AGE_PERIOD_7_0_M, secs);
+#define MAX_TIMER_VAL	((1 << 8) - 1)
 
-	ret = ksz_write8(dev, REG_SW_LUE_CTRL_3, value);
-	if (ret < 0)
-		return ret;
+	/* The aging timer comprises a 3-bit multiplier and an 8-bit second
+	 * value.  Either of them cannot be zero.  The maximum timer is then
+	 * 7 * 255 = 1785 seconds.
+	 */
+	if (!secs)
+		secs = 1;
 
-	data = FIELD_GET(SW_AGE_PERIOD_10_8_M, secs);
+	/* Return error if too large. */
+	else if (secs > 7 * MAX_TIMER_VAL)
+		return -EINVAL;
 
 	ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &value);
 	if (ret < 0)
 		return ret;
 
-	value &= ~SW_AGE_CNT_M;
-	value |= FIELD_PREP(SW_AGE_CNT_M, data);
+	/* Check whether there is need to update the multiplier. */
+	mult = FIELD_GET(SW_AGE_CNT_M, value);
+	max_val = MAX_TIMER_VAL;
+	if (mult > 0) {
+		/* Try to use the same multiplier already in the register as
+		 * the hardware default uses multiplier 4 and 75 seconds for
+		 * 300 seconds.
+		 */
+		max_val = DIV_ROUND_UP(secs, mult);
+		if (max_val > MAX_TIMER_VAL || max_val * mult != secs)
+			max_val = MAX_TIMER_VAL;
+	}
+
+	data = DIV_ROUND_UP(secs, max_val);
+	if (mult != data) {
+		value &= ~SW_AGE_CNT_M;
+		value |= FIELD_PREP(SW_AGE_CNT_M, data);
+		ret = ksz_write8(dev, REG_SW_LUE_CTRL_0, value);
+		if (ret < 0)
+			return ret;
+	}
 
-	return ksz_write8(dev, REG_SW_LUE_CTRL_0, value);
+	value = DIV_ROUND_UP(secs, data);
+	return ksz_write8(dev, REG_SW_LUE_CTRL_3, value);
 }
 
 void ksz9477_port_queue_split(struct ksz_device *dev, int port)
@@ -1138,9 +1355,15 @@ void ksz9477_config_cpu_port(struct dsa_switch *ds)
 	}
 }
 
+#define RESV_MCAST_CNT	8
+
+static u8 reserved_mcast_map[RESV_MCAST_CNT] = { 0, 1, 3, 16, 32, 33, 2, 17 };
+
 int ksz9477_enable_stp_addr(struct ksz_device *dev)
 {
+	u8 i, ports, update;
 	const u32 *masks;
+	bool override;
 	u32 data;
 	int ret;
 
@@ -1149,23 +1372,87 @@ int ksz9477_enable_stp_addr(struct ksz_device *dev)
 	/* Enable Reserved multicast table */
 	ksz_cfg(dev, REG_SW_LUE_CTRL_0, SW_RESV_MCAST_ENABLE, true);
 
-	/* Set the Override bit for forwarding BPDU packet to CPU */
-	ret = ksz_write32(dev, REG_SW_ALU_VAL_B,
-			  ALU_V_OVERRIDE | BIT(dev->cpu_port));
-	if (ret < 0)
-		return ret;
+	/* The reserved multicast address table has 8 entries.  Each entry has
+	 * a default value of which port to forward.  It is assumed the host
+	 * port is the last port in most of the switches, but that is not the
+	 * case for KSZ9477 or maybe KSZ9897.  For LAN937X family the default
+	 * port is port 5, the first RGMII port.  It is okay for LAN9370, a
+	 * 5-port switch, but may not be correct for the other 8-port
+	 * versions.  It is necessary to update the whole table to forward to
+	 * the right ports.
+	 * Furthermore PTP messages can use a reserved multicast address and
+	 * the host will not receive them if this table is not correct.
+	 */
+	for (i = 0; i < RESV_MCAST_CNT; i++) {
+		data = reserved_mcast_map[i] <<
+			dev->info->shifts[ALU_STAT_INDEX];
+		data |= ALU_STAT_START |
+			masks[ALU_STAT_DIRECT] |
+			masks[ALU_RESV_MCAST_ADDR] |
+			masks[ALU_STAT_READ];
+		ret = ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data);
+		if (ret < 0)
+			return ret;
 
-	data = ALU_STAT_START | ALU_RESV_MCAST_ADDR | masks[ALU_STAT_WRITE];
+		/* wait to be finished */
+		ret = ksz9477_wait_alu_sta_ready(dev);
+		if (ret < 0)
+			return ret;
 
-	ret = ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data);
-	if (ret < 0)
-		return ret;
+		ret = ksz_read32(dev, REG_SW_ALU_VAL_B, &data);
+		if (ret < 0)
+			return ret;
 
-	/* wait to be finished */
-	ret = ksz9477_wait_alu_sta_ready(dev);
-	if (ret < 0) {
-		dev_err(dev->dev, "Failed to update Reserved Multicast table\n");
-		return ret;
+		override = false;
+		ports = data & dev->port_mask;
+		switch (i) {
+		case 0:
+		case 6:
+			/* Change the host port. */
+			update = BIT(dev->cpu_port);
+			override = true;
+			break;
+		case 2:
+			/* Change the host port. */
+			update = BIT(dev->cpu_port);
+			break;
+		case 4:
+		case 5:
+		case 7:
+			/* Skip the host port. */
+			update = dev->port_mask & ~BIT(dev->cpu_port);
+			break;
+		default:
+			update = ports;
+			break;
+		}
+		if (update != ports || override) {
+			data &= ~dev->port_mask;
+			data |= update;
+			/* Set Override bit to receive frame even when port is
+			 * closed.
+			 */
+			if (override)
+				data |= ALU_V_OVERRIDE;
+			ret = ksz_write32(dev, REG_SW_ALU_VAL_B, data);
+			if (ret < 0)
+				return ret;
+
+			data = reserved_mcast_map[i] <<
+			       dev->info->shifts[ALU_STAT_INDEX];
+			data |= ALU_STAT_START |
+				masks[ALU_STAT_DIRECT] |
+				masks[ALU_RESV_MCAST_ADDR] |
+				masks[ALU_STAT_WRITE];
+			ret = ksz_write32(dev, REG_SW_ALU_STAT_CTRL__4, data);
+			if (ret < 0)
+				return ret;
+
+			/* wait to be finished */
+			ret = ksz9477_wait_alu_sta_ready(dev);
+			if (ret < 0)
+				return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/net/dsa/microchip/ksz9477.h b/drivers/net/dsa/microchip/ksz9477.h
index d2166b0d881e..0d1a6dfda23e 100644
--- a/drivers/net/dsa/microchip/ksz9477.h
+++ b/drivers/net/dsa/microchip/ksz9477.h
@@ -2,7 +2,7 @@
 /*
  * Microchip KSZ9477 series Header file
  *
- * Copyright (C) 2017-2022 Microchip Technology Inc.
+ * Copyright (C) 2017-2025 Microchip Technology Inc.
  */
 
 #ifndef __KSZ9477_H
@@ -97,4 +97,6 @@ void ksz9477_acl_match_process_l2(struct ksz_device *dev, int port,
 				  u16 ethtype, u8 *src_mac, u8 *dst_mac,
 				  unsigned long cookie, u32 prio);
 
+int ksz9477_pcs_create(struct ksz_device *dev);
+
 #endif
diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h
index 04235c22bf40..61ea11e3338e 100644
--- a/drivers/net/dsa/microchip/ksz9477_reg.h
+++ b/drivers/net/dsa/microchip/ksz9477_reg.h
@@ -2,7 +2,7 @@
 /*
  * Microchip KSZ9477 register definitions
  *
- * Copyright (C) 2017-2018 Microchip Technology Inc.
+ * Copyright (C) 2017-2025 Microchip Technology Inc.
  */
 
 #ifndef __KSZ9477_REGS_H
@@ -165,8 +165,6 @@
 #define SW_VLAN_ENABLE			BIT(7)
 #define SW_DROP_INVALID_VID		BIT(6)
 #define SW_AGE_CNT_M			GENMASK(5, 3)
-#define SW_AGE_CNT_S			3
-#define SW_AGE_PERIOD_10_8_M		GENMASK(10, 8)
 #define SW_RESV_MCAST_ENABLE		BIT(2)
 #define SW_HASH_OPTION_M		0x03
 #define SW_HASH_OPTION_CRC		1
@@ -399,7 +397,6 @@
 
 #define ALU_RESV_MCAST_INDEX_M		(BIT(6) - 1)
 #define ALU_STAT_START			BIT(7)
-#define ALU_RESV_MCAST_ADDR		BIT(1)
 
 #define REG_SW_ALU_VAL_A		0x0420
 
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index e3512e324572..0c10351fe5eb 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -2,7 +2,7 @@
 /*
  * Microchip switch driver main logic
  *
- * Copyright (C) 2017-2024 Microchip Technology Inc.
+ * Copyright (C) 2017-2025 Microchip Technology Inc.
  */
 
 #include <linux/delay.h>
@@ -23,6 +23,7 @@
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/micrel_phy.h>
+#include <linux/pinctrl/consumer.h>
 #include <net/dsa.h>
 #include <net/ieee8021q.h>
 #include <net/pkt_cls.h>
@@ -265,16 +266,102 @@ static void ksz_phylink_mac_link_down(struct phylink_config *config,
 				      unsigned int mode,
 				      phy_interface_t interface);
 
+/**
+ * ksz_phylink_mac_disable_tx_lpi() - Callback to signal LPI support (Dummy)
+ * @config: phylink config structure
+ *
+ * This function is a dummy handler. See ksz_phylink_mac_enable_tx_lpi() for
+ * a detailed explanation of EEE/LPI handling in KSZ switches.
+ */
+static void ksz_phylink_mac_disable_tx_lpi(struct phylink_config *config)
+{
+}
+
+/**
+ * ksz_phylink_mac_enable_tx_lpi() - Callback to signal LPI support (Dummy)
+ * @config: phylink config structure
+ * @timer: timer value before entering LPI (unused)
+ * @tx_clock_stop: whether to stop the TX clock in LPI mode (unused)
+ *
+ * This function signals to phylink that the driver architecture supports
+ * LPI management, enabling phylink to control EEE advertisement during
+ * negotiation according to IEEE Std 802.3 (Clause 78).
+ *
+ * Hardware Management of EEE/LPI State:
+ * For KSZ switch ports with integrated PHYs (e.g., KSZ9893R ports 1-2),
+ * observation and testing suggest that the actual EEE / Low Power Idle (LPI)
+ * state transitions are managed autonomously by the hardware based on
+ * the auto-negotiation results. (Note: While the datasheet describes EEE
+ * operation based on negotiation, it doesn't explicitly detail the internal
+ * MAC/PHY interaction, so autonomous hardware management of the MAC state
+ * for LPI is inferred from observed behavior).
+ * This hardware control, consistent with the switch's ability to operate
+ * autonomously via strapping, means MAC-level software intervention is not
+ * required or exposed for managing the LPI state once EEE is negotiated.
+ * (Ref: KSZ9893R Data Sheet DS00002420D, primarily Section 4.7.5 explaining
+ * EEE, also Sections 4.1.7 on Auto-Negotiation and 3.2.1 on Configuration
+ * Straps).
+ *
+ * Additionally, ports configured as MAC interfaces (e.g., KSZ9893R port 3)
+ * lack documented MAC-level LPI control.
+ *
+ * Therefore, this callback performs no action and serves primarily to inform
+ * phylink of LPI awareness and to document the inferred hardware behavior.
+ *
+ * Returns: 0 (Always success)
+ */
+static int ksz_phylink_mac_enable_tx_lpi(struct phylink_config *config,
+					 u32 timer, bool tx_clock_stop)
+{
+	return 0;
+}
+
 static const struct phylink_mac_ops ksz88x3_phylink_mac_ops = {
 	.mac_config	= ksz88x3_phylink_mac_config,
 	.mac_link_down	= ksz_phylink_mac_link_down,
 	.mac_link_up	= ksz8_phylink_mac_link_up,
+	.mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi,
 };
 
 static const struct phylink_mac_ops ksz8_phylink_mac_ops = {
 	.mac_config	= ksz_phylink_mac_config,
 	.mac_link_down	= ksz_phylink_mac_link_down,
 	.mac_link_up	= ksz8_phylink_mac_link_up,
+	.mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi,
+};
+
+static const struct ksz_dev_ops ksz8463_dev_ops = {
+	.setup = ksz8_setup,
+	.get_port_addr = ksz8463_get_port_addr,
+	.cfg_port_member = ksz8_cfg_port_member,
+	.flush_dyn_mac_table = ksz8_flush_dyn_mac_table,
+	.port_setup = ksz8_port_setup,
+	.r_phy = ksz8463_r_phy,
+	.w_phy = ksz8463_w_phy,
+	.r_mib_cnt = ksz8_r_mib_cnt,
+	.r_mib_pkt = ksz8_r_mib_pkt,
+	.r_mib_stat64 = ksz88xx_r_mib_stats64,
+	.freeze_mib = ksz8_freeze_mib,
+	.port_init_cnt = ksz8_port_init_cnt,
+	.fdb_dump = ksz8_fdb_dump,
+	.fdb_add = ksz8_fdb_add,
+	.fdb_del = ksz8_fdb_del,
+	.mdb_add = ksz8_mdb_add,
+	.mdb_del = ksz8_mdb_del,
+	.vlan_filtering = ksz8_port_vlan_filtering,
+	.vlan_add = ksz8_port_vlan_add,
+	.vlan_del = ksz8_port_vlan_del,
+	.mirror_add = ksz8_port_mirror_add,
+	.mirror_del = ksz8_port_mirror_del,
+	.get_caps = ksz8_get_caps,
+	.config_cpu_port = ksz8_config_cpu_port,
+	.enable_stp_addr = ksz8_enable_stp_addr,
+	.reset = ksz8_reset_switch,
+	.init = ksz8_switch_init,
+	.exit = ksz8_switch_exit,
+	.change_mtu = ksz8_change_mtu,
 };
 
 static const struct ksz_dev_ops ksz88xx_dev_ops = {
@@ -354,10 +441,29 @@ static void ksz9477_phylink_mac_link_up(struct phylink_config *config,
 					int speed, int duplex, bool tx_pause,
 					bool rx_pause);
 
+static struct phylink_pcs *
+ksz_phylink_mac_select_pcs(struct phylink_config *config,
+			   phy_interface_t interface)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct ksz_device *dev = dp->ds->priv;
+	struct ksz_port *p = &dev->ports[dp->index];
+
+	if (ksz_is_sgmii_port(dev, dp->index) &&
+	    (interface == PHY_INTERFACE_MODE_SGMII ||
+	    interface == PHY_INTERFACE_MODE_1000BASEX))
+		return p->pcs;
+
+	return NULL;
+}
+
 static const struct phylink_mac_ops ksz9477_phylink_mac_ops = {
 	.mac_config	= ksz_phylink_mac_config,
 	.mac_link_down	= ksz_phylink_mac_link_down,
 	.mac_link_up	= ksz9477_phylink_mac_link_up,
+	.mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi,
+	.mac_select_pcs	= ksz_phylink_mac_select_pcs,
 };
 
 static const struct ksz_dev_ops ksz9477_dev_ops = {
@@ -395,12 +501,15 @@ static const struct ksz_dev_ops ksz9477_dev_ops = {
 	.reset = ksz9477_reset_switch,
 	.init = ksz9477_switch_init,
 	.exit = ksz9477_switch_exit,
+	.pcs_create = ksz9477_pcs_create,
 };
 
 static const struct phylink_mac_ops lan937x_phylink_mac_ops = {
 	.mac_config	= ksz_phylink_mac_config,
 	.mac_link_down	= ksz_phylink_mac_link_down,
 	.mac_link_up	= ksz9477_phylink_mac_link_up,
+	.mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi,
 };
 
 static const struct ksz_dev_ops lan937x_dev_ops = {
@@ -441,6 +550,60 @@ static const struct ksz_dev_ops lan937x_dev_ops = {
 	.exit = lan937x_switch_exit,
 };
 
+static const u16 ksz8463_regs[] = {
+	[REG_SW_MAC_ADDR]		= 0x10,
+	[REG_IND_CTRL_0]		= 0x30,
+	[REG_IND_DATA_8]		= 0x26,
+	[REG_IND_DATA_CHECK]		= 0x26,
+	[REG_IND_DATA_HI]		= 0x28,
+	[REG_IND_DATA_LO]		= 0x2C,
+	[REG_IND_MIB_CHECK]		= 0x2F,
+	[P_FORCE_CTRL]			= 0x0C,
+	[P_LINK_STATUS]			= 0x0E,
+	[P_LOCAL_CTRL]			= 0x0C,
+	[P_NEG_RESTART_CTRL]		= 0x0D,
+	[P_REMOTE_STATUS]		= 0x0E,
+	[P_SPEED_STATUS]		= 0x0F,
+	[S_TAIL_TAG_CTRL]		= 0xAD,
+	[P_STP_CTRL]			= 0x6F,
+	[S_START_CTRL]			= 0x01,
+	[S_BROADCAST_CTRL]		= 0x06,
+	[S_MULTICAST_CTRL]		= 0x04,
+};
+
+static const u32 ksz8463_masks[] = {
+	[PORT_802_1P_REMAPPING]		= BIT(3),
+	[SW_TAIL_TAG_ENABLE]		= BIT(0),
+	[MIB_COUNTER_OVERFLOW]		= BIT(7),
+	[MIB_COUNTER_VALID]		= BIT(6),
+	[VLAN_TABLE_FID]		= GENMASK(15, 12),
+	[VLAN_TABLE_MEMBERSHIP]		= GENMASK(18, 16),
+	[VLAN_TABLE_VALID]		= BIT(19),
+	[STATIC_MAC_TABLE_VALID]	= BIT(19),
+	[STATIC_MAC_TABLE_USE_FID]	= BIT(21),
+	[STATIC_MAC_TABLE_FID]		= GENMASK(25, 22),
+	[STATIC_MAC_TABLE_OVERRIDE]	= BIT(20),
+	[STATIC_MAC_TABLE_FWD_PORTS]	= GENMASK(18, 16),
+	[DYNAMIC_MAC_TABLE_ENTRIES_H]	= GENMASK(1, 0),
+	[DYNAMIC_MAC_TABLE_MAC_EMPTY]	= BIT(2),
+	[DYNAMIC_MAC_TABLE_NOT_READY]	= BIT(7),
+	[DYNAMIC_MAC_TABLE_ENTRIES]	= GENMASK(31, 24),
+	[DYNAMIC_MAC_TABLE_FID]		= GENMASK(19, 16),
+	[DYNAMIC_MAC_TABLE_SRC_PORT]	= GENMASK(21, 20),
+	[DYNAMIC_MAC_TABLE_TIMESTAMP]	= GENMASK(23, 22),
+};
+
+static u8 ksz8463_shifts[] = {
+	[VLAN_TABLE_MEMBERSHIP_S]	= 16,
+	[STATIC_MAC_FWD_PORTS]		= 16,
+	[STATIC_MAC_FID]		= 22,
+	[DYNAMIC_MAC_ENTRIES_H]		= 8,
+	[DYNAMIC_MAC_ENTRIES]		= 24,
+	[DYNAMIC_MAC_FID]		= 16,
+	[DYNAMIC_MAC_TIMESTAMP]		= 22,
+	[DYNAMIC_MAC_SRC_PORT]		= 20,
+};
+
 static const u16 ksz8795_regs[] = {
 	[REG_SW_MAC_ADDR]		= 0x68,
 	[REG_IND_CTRL_0]		= 0x6E,
@@ -645,6 +808,8 @@ static const u16 ksz9477_regs[] = {
 static const u32 ksz9477_masks[] = {
 	[ALU_STAT_WRITE]		= 0,
 	[ALU_STAT_READ]			= 1,
+	[ALU_STAT_DIRECT]		= 0,
+	[ALU_RESV_MCAST_ADDR]		= BIT(1),
 	[P_MII_TX_FLOW_CTRL]		= BIT(5),
 	[P_MII_RX_FLOW_CTRL]		= BIT(3),
 };
@@ -672,6 +837,8 @@ static const u8 ksz9477_xmii_ctrl1[] = {
 static const u32 lan937x_masks[] = {
 	[ALU_STAT_WRITE]		= 1,
 	[ALU_STAT_READ]			= 2,
+	[ALU_STAT_DIRECT]		= BIT(3),
+	[ALU_RESV_MCAST_ADDR]		= BIT(2),
 	[P_MII_TX_FLOW_CTRL]		= BIT(5),
 	[P_MII_RX_FLOW_CTRL]		= BIT(3),
 };
@@ -1035,8 +1202,7 @@ static const struct regmap_range ksz9477_valid_regs[] = {
 	regmap_reg_range(0x701b, 0x701b),
 	regmap_reg_range(0x701f, 0x7020),
 	regmap_reg_range(0x7030, 0x7030),
-	regmap_reg_range(0x7200, 0x7203),
-	regmap_reg_range(0x7206, 0x7207),
+	regmap_reg_range(0x7200, 0x7207),
 	regmap_reg_range(0x7300, 0x7301),
 	regmap_reg_range(0x7400, 0x7401),
 	regmap_reg_range(0x7403, 0x7403),
@@ -1286,6 +1452,7 @@ static const struct regmap_range ksz8873_valid_regs[] = {
 	regmap_reg_range(0x3f, 0x3f),
 
 	/* advanced control registers */
+	regmap_reg_range(0x43, 0x43),
 	regmap_reg_range(0x60, 0x6f),
 	regmap_reg_range(0x70, 0x75),
 	regmap_reg_range(0x76, 0x78),
@@ -1312,6 +1479,29 @@ static const struct regmap_access_table ksz8873_register_set = {
 };
 
 const struct ksz_chip_data ksz_switch_chips[] = {
+	[KSZ8463] = {
+		.chip_id = KSZ8463_CHIP_ID,
+		.dev_name = "KSZ8463",
+		.num_vlans = 16,
+		.num_alus = 0,
+		.num_statics = 8,
+		.cpu_ports = 0x4,	/* can be configured as cpu port */
+		.port_cnt = 3,
+		.num_tx_queues = 4,
+		.num_ipms = 4,
+		.ops = &ksz8463_dev_ops,
+		.phylink_mac_ops = &ksz88x3_phylink_mac_ops,
+		.mib_names = ksz88xx_mib_names,
+		.mib_cnt = ARRAY_SIZE(ksz88xx_mib_names),
+		.reg_mib_cnt = MIB_COUNTER_NUM,
+		.regs = ksz8463_regs,
+		.masks = ksz8463_masks,
+		.shifts = ksz8463_shifts,
+		.supports_mii = {false, false, true},
+		.supports_rmii = {false, false, true},
+		.internal_phy = {true, true, false},
+	},
+
 	[KSZ8563] = {
 		.chip_id = KSZ8563_CHIP_ID,
 		.dev_name = "KSZ8563",
@@ -1552,6 +1742,7 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 				   true, false, false},
 		.gbit_capable	= {true, true, true, true, true, true, true},
 		.ptp_capable = true,
+		.sgmii_port = 7,
 		.wr_table = &ksz9477_register_set,
 		.rd_table = &ksz9477_register_set,
 	},
@@ -1944,6 +2135,7 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 		.internal_phy	= {true, true, true, true,
 				   true, false, false},
 		.gbit_capable	= {true, true, true, true, true, true, true},
+		.sgmii_port = 7,
 		.wr_table = &ksz9477_register_set,
 		.rd_table = &ksz9477_register_set,
 	},
@@ -2016,6 +2208,18 @@ static void ksz_phylink_get_caps(struct dsa_switch *ds, int port,
 
 	if (dev->dev_ops->get_caps)
 		dev->dev_ops->get_caps(dev, port, config);
+
+	if (ds->ops->support_eee && ds->ops->support_eee(ds, port)) {
+		memcpy(config->lpi_interfaces, config->supported_interfaces,
+		       sizeof(config->lpi_interfaces));
+
+		config->lpi_capabilities = MAC_100FD;
+		if (dev->info->gbit_capable[port])
+			config->lpi_capabilities |= MAC_1000FD;
+
+		/* EEE is fully operational */
+		config->eee_enabled_default = true;
+	}
 }
 
 void ksz_r_mib_stats64(struct ksz_device *dev, int port)
@@ -2067,7 +2271,7 @@ void ksz_r_mib_stats64(struct ksz_device *dev, int port)
 
 	spin_unlock(&mib->stats64_lock);
 
-	if (dev->info->phy_errata_9477) {
+	if (dev->info->phy_errata_9477 && !ksz_is_sgmii_port(dev, port)) {
 		ret = ksz9477_errata_monitor(dev, port, raw->tx_late_col);
 		if (ret)
 			dev_err(dev->dev, "Failed to monitor transmission halt\n");
@@ -2258,6 +2462,12 @@ static void ksz_update_port_member(struct ksz_device *dev, int port)
 		dev->dev_ops->cfg_port_member(dev, i, val | cpu_port);
 	}
 
+	/* HSR ports are setup once so need to use the assigned membership
+	 * when the port is enabled.
+	 */
+	if (!port_member && p->stp_state == BR_STATE_FORWARDING &&
+	    (dev->hsr_ports & BIT(port)))
+		port_member = dev->hsr_ports;
 	dev->dev_ops->cfg_port_member(dev, port, port_member | cpu_port);
 }
 
@@ -2377,8 +2587,8 @@ static int ksz_irq_phy_setup(struct ksz_device *dev)
 
 			irq = irq_find_mapping(dev->ports[port].pirq.domain,
 					       PORT_SRC_PHY_INT);
-			if (irq < 0) {
-				ret = irq;
+			if (!irq) {
+				ret = -EINVAL;
 				goto out;
 			}
 			ds->user_mii_bus->irq[phy] = irq;
@@ -2697,8 +2907,8 @@ static int ksz_irq_common_setup(struct ksz_device *dev, struct ksz_irq *kirq)
 	kirq->dev = dev;
 	kirq->masked = ~0;
 
-	kirq->domain = irq_domain_add_simple(dev->dev->of_node, kirq->nirqs, 0,
-					     &ksz_irq_domain_ops, kirq);
+	kirq->domain = irq_domain_create_simple(dev_fwnode(dev->dev), kirq->nirqs, 0,
+						&ksz_irq_domain_ops, kirq);
 	if (!kirq->domain)
 		return -ENOMEM;
 
@@ -2742,8 +2952,8 @@ static int ksz_pirq_setup(struct ksz_device *dev, u8 p)
 	snprintf(pirq->name, sizeof(pirq->name), "port_irq-%d", p);
 
 	pirq->irq_num = irq_find_mapping(dev->girq.domain, p);
-	if (pirq->irq_num < 0)
-		return pirq->irq_num;
+	if (!pirq->irq_num)
+		return -EINVAL;
 
 	return ksz_irq_common_setup(dev, pirq);
 }
@@ -2753,6 +2963,7 @@ static int ksz_parse_drive_strength(struct ksz_device *dev);
 static int ksz_setup(struct dsa_switch *ds)
 {
 	struct ksz_device *dev = ds->priv;
+	u16 storm_mask, storm_rate;
 	struct dsa_port *dp;
 	struct ksz_port *p;
 	const u16 *regs;
@@ -2775,11 +2986,21 @@ static int ksz_setup(struct dsa_switch *ds)
 	if (ret)
 		return ret;
 
+	if (ksz_has_sgmii_port(dev) && dev->dev_ops->pcs_create) {
+		ret = dev->dev_ops->pcs_create(dev);
+		if (ret)
+			return ret;
+	}
+
 	/* set broadcast storm protection 10% rate */
+	storm_mask = BROADCAST_STORM_RATE;
+	storm_rate = (BROADCAST_STORM_VALUE * BROADCAST_STORM_PROT_RATE) / 100;
+	if (ksz_is_ksz8463(dev)) {
+		storm_mask = swab16(storm_mask);
+		storm_rate = swab16(storm_rate);
+	}
 	regmap_update_bits(ksz_regmap_16(dev), regs[S_BROADCAST_CTRL],
-			   BROADCAST_STORM_RATE,
-			   (BROADCAST_STORM_VALUE *
-			   BROADCAST_STORM_PROT_RATE) / 100);
+			   storm_mask, storm_rate);
 
 	dev->dev_ops->config_cpu_port(ds);
 
@@ -2817,12 +3038,12 @@ static int ksz_setup(struct dsa_switch *ds)
 		dsa_switch_for_each_user_port(dp, dev->ds) {
 			ret = ksz_pirq_setup(dev, dp->index);
 			if (ret)
-				goto out_girq;
+				goto port_release;
 
 			if (dev->info->ptp_capable) {
 				ret = ksz_ptp_irq_setup(ds, dp->index);
 				if (ret)
-					goto out_pirq;
+					goto pirq_release;
 			}
 		}
 	}
@@ -2832,7 +3053,7 @@ static int ksz_setup(struct dsa_switch *ds)
 		if (ret) {
 			dev_err(dev->dev, "Failed to register PTP clock: %d\n",
 				ret);
-			goto out_ptpirq;
+			goto port_release;
 		}
 	}
 
@@ -2855,17 +3076,16 @@ static int ksz_setup(struct dsa_switch *ds)
 out_ptp_clock_unregister:
 	if (dev->info->ptp_capable)
 		ksz_ptp_clock_unregister(ds);
-out_ptpirq:
-	if (dev->irq > 0 && dev->info->ptp_capable)
-		dsa_switch_for_each_user_port(dp, dev->ds)
-			ksz_ptp_irq_free(ds, dp->index);
-out_pirq:
-	if (dev->irq > 0)
-		dsa_switch_for_each_user_port(dp, dev->ds)
+port_release:
+	if (dev->irq > 0) {
+		dsa_switch_for_each_user_port_continue_reverse(dp, dev->ds) {
+			if (dev->info->ptp_capable)
+				ksz_ptp_irq_free(ds, dp->index);
+pirq_release:
 			ksz_irq_free(&dev->ports[dp->index].pirq);
-out_girq:
-	if (dev->irq > 0)
+		}
 		ksz_irq_free(&dev->girq);
+	}
 
 	return ret;
 }
@@ -3008,31 +3228,6 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port)
 		if (!port)
 			return MICREL_KSZ8_P1_ERRATA;
 		break;
-	case KSZ8567_CHIP_ID:
-		/* KSZ8567R Errata DS80000752C Module 4 */
-	case KSZ8765_CHIP_ID:
-	case KSZ8794_CHIP_ID:
-	case KSZ8795_CHIP_ID:
-		/* KSZ879x/KSZ877x/KSZ876x Errata DS80000687C Module 2 */
-	case KSZ9477_CHIP_ID:
-		/* KSZ9477S Errata DS80000754A Module 4 */
-	case KSZ9567_CHIP_ID:
-		/* KSZ9567S Errata DS80000756A Module 4 */
-	case KSZ9896_CHIP_ID:
-		/* KSZ9896C Errata DS80000757A Module 3 */
-	case KSZ9897_CHIP_ID:
-	case LAN9646_CHIP_ID:
-		/* KSZ9897R Errata DS80000758C Module 4 */
-		/* Energy Efficient Ethernet (EEE) feature select must be manually disabled
-		 *   The EEE feature is enabled by default, but it is not fully
-		 *   operational. It must be manually disabled through register
-		 *   controls. If not disabled, the PHY ports can auto-negotiate
-		 *   to enable EEE, and this feature can cause link drops when
-		 *   linked to another device supporting EEE.
-		 *
-		 * The same item appears in the errata for all switches above.
-		 */
-		return MICREL_NO_EEE;
 	}
 
 	return 0;
@@ -3330,6 +3525,7 @@ static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds,
 		proto = DSA_TAG_PROTO_KSZ8795;
 
 	if (dev->chip_id == KSZ88X3_CHIP_ID ||
+	    dev->chip_id == KSZ8463_CHIP_ID ||
 	    dev->chip_id == KSZ8563_CHIP_ID ||
 	    dev->chip_id == KSZ9893_CHIP_ID ||
 	    dev->chip_id == KSZ9563_CHIP_ID)
@@ -3442,6 +3638,7 @@ static int ksz_max_mtu(struct dsa_switch *ds, int port)
 	case KSZ8794_CHIP_ID:
 	case KSZ8765_CHIP_ID:
 		return KSZ8795_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN;
+	case KSZ8463_CHIP_ID:
 	case KSZ88X3_CHIP_ID:
 	case KSZ8864_CHIP_ID:
 	case KSZ8895_CHIP_ID:
@@ -3466,6 +3663,20 @@ static int ksz_max_mtu(struct dsa_switch *ds, int port)
 	return -EOPNOTSUPP;
 }
 
+/**
+ * ksz_support_eee - Determine Energy Efficient Ethernet (EEE) support for a
+ *                   port
+ * @ds: Pointer to the DSA switch structure
+ * @port: Port number to check
+ *
+ * This function also documents devices where EEE was initially advertised but
+ * later withdrawn due to reliability issues, as described in official errata
+ * documents. These devices are explicitly listed to record known limitations,
+ * even if there is no technical necessity for runtime checks.
+ *
+ * Returns: true if the internal PHY on the given port supports fully
+ * operational EEE, false otherwise.
+ */
 static bool ksz_support_eee(struct dsa_switch *ds, int port)
 {
 	struct ksz_device *dev = ds->priv;
@@ -3475,34 +3686,40 @@ static bool ksz_support_eee(struct dsa_switch *ds, int port)
 
 	switch (dev->chip_id) {
 	case KSZ8563_CHIP_ID:
+	case KSZ9563_CHIP_ID:
+	case KSZ9893_CHIP_ID:
+		return true;
 	case KSZ8567_CHIP_ID:
+		/* KSZ8567R Errata DS80000752C Module 4 */
+	case KSZ8765_CHIP_ID:
+	case KSZ8794_CHIP_ID:
+	case KSZ8795_CHIP_ID:
+		/* KSZ879x/KSZ877x/KSZ876x Errata DS80000687C Module 2 */
 	case KSZ9477_CHIP_ID:
-	case KSZ9563_CHIP_ID:
+		/* KSZ9477S Errata DS80000754A Module 4 */
 	case KSZ9567_CHIP_ID:
-	case KSZ9893_CHIP_ID:
+		/* KSZ9567S Errata DS80000756A Module 4 */
 	case KSZ9896_CHIP_ID:
+		/* KSZ9896C Errata DS80000757A Module 3 */
 	case KSZ9897_CHIP_ID:
 	case LAN9646_CHIP_ID:
-		return true;
+		/* KSZ9897R Errata DS80000758C Module 4 */
+		/* Energy Efficient Ethernet (EEE) feature select must be
+		 * manually disabled
+		 *   The EEE feature is enabled by default, but it is not fully
+		 *   operational. It must be manually disabled through register
+		 *   controls. If not disabled, the PHY ports can auto-negotiate
+		 *   to enable EEE, and this feature can cause link drops when
+		 *   linked to another device supporting EEE.
+		 *
+		 * The same item appears in the errata for all switches above.
+		 */
+		break;
 	}
 
 	return false;
 }
 
-static int ksz_get_mac_eee(struct dsa_switch *ds, int port,
-			   struct ethtool_keee *e)
-{
-	/* There is no documented control of Tx LPI configuration. */
-	e->tx_lpi_enabled = true;
-
-	/* There is no documented control of Tx LPI timer. According to tests
-	 * Tx LPI timer seems to be set by default to minimal value.
-	 */
-	e->tx_lpi_timer = 0;
-
-	return 0;
-}
-
 static int ksz_set_mac_eee(struct dsa_switch *ds, int port,
 			   struct ethtool_keee *e)
 {
@@ -3627,6 +3844,10 @@ static void ksz_phylink_mac_config(struct phylink_config *config,
 	if (dev->info->internal_phy[port])
 		return;
 
+	/* No need to configure XMII control register when using SGMII. */
+	if (ksz_is_sgmii_port(dev, port))
+		return;
+
 	if (phylink_autoneg_inband(mode)) {
 		dev_err(dev->dev, "In-band AN not supported!\n");
 		return;
@@ -3772,6 +3993,9 @@ static int ksz_switch_detect(struct ksz_device *dev)
 	id2 = FIELD_GET(SW_CHIP_ID_M, id16);
 
 	switch (id1) {
+	case KSZ84_FAMILY_ID:
+		dev->chip_id = KSZ8463_CHIP_ID;
+		break;
 	case KSZ87_FAMILY_ID:
 		if (id2 == KSZ87_CHIP_ID_95) {
 			u8 val;
@@ -4013,6 +4237,104 @@ static int ksz_ets_band_to_queue(struct tc_ets_qopt_offload_replace_params *p,
 	return p->bands - 1 - band;
 }
 
+static u8 ksz8463_tc_ctrl(int port, int queue)
+{
+	u8 reg;
+
+	reg = 0xC8 + port * 4;
+	reg += ((3 - queue) / 2) * 2;
+	reg++;
+	reg -= (queue & 1);
+	return reg;
+}
+
+/**
+ * ksz88x3_tc_ets_add - Configure ETS (Enhanced Transmission Selection)
+ *                      for a port on KSZ88x3 switch
+ * @dev: Pointer to the KSZ switch device structure
+ * @port: Port number to configure
+ * @p: Pointer to offload replace parameters describing ETS bands and mapping
+ *
+ * The KSZ88x3 supports two scheduling modes: Strict Priority and
+ * Weighted Fair Queuing (WFQ). Both modes have fixed behavior:
+ *   - No configurable queue-to-priority mapping
+ *   - No weight adjustment in WFQ mode
+ *
+ * This function configures the switch to use strict priority mode by
+ * clearing the WFQ enable bit for all queues associated with ETS bands.
+ * If strict priority is not explicitly requested, the switch will default
+ * to WFQ mode.
+ *
+ * Return: 0 on success, or a negative error code on failure
+ */
+static int ksz88x3_tc_ets_add(struct ksz_device *dev, int port,
+			      struct tc_ets_qopt_offload_replace_params *p)
+{
+	int ret, band;
+
+	/* Only strict priority mode is supported for now.
+	 * WFQ is implicitly enabled when strict mode is disabled.
+	 */
+	for (band = 0; band < p->bands; band++) {
+		int queue = ksz_ets_band_to_queue(p, band);
+		u8 reg;
+
+		/* Calculate TXQ Split Control register address for this
+		 * port/queue
+		 */
+		reg = KSZ8873_TXQ_SPLIT_CTRL_REG(port, queue);
+		if (ksz_is_ksz8463(dev))
+			reg = ksz8463_tc_ctrl(port, queue);
+
+		/* Clear WFQ enable bit to select strict priority scheduling */
+		ret = ksz_rmw8(dev, reg, KSZ8873_TXQ_WFQ_ENABLE, 0);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * ksz88x3_tc_ets_del - Reset ETS (Enhanced Transmission Selection) config
+ *                      for a port on KSZ88x3 switch
+ * @dev: Pointer to the KSZ switch device structure
+ * @port: Port number to reset
+ *
+ * The KSZ88x3 supports only fixed scheduling modes: Strict Priority or
+ * Weighted Fair Queuing (WFQ), with no reconfiguration of weights or
+ * queue mapping. This function resets the port’s scheduling mode to
+ * the default, which is WFQ, by enabling the WFQ bit for all queues.
+ *
+ * Return: 0 on success, or a negative error code on failure
+ */
+static int ksz88x3_tc_ets_del(struct ksz_device *dev, int port)
+{
+	int ret, queue;
+
+	/* Iterate over all transmit queues for this port */
+	for (queue = 0; queue < dev->info->num_tx_queues; queue++) {
+		u8 reg;
+
+		/* Calculate TXQ Split Control register address for this
+		 * port/queue
+		 */
+		reg = KSZ8873_TXQ_SPLIT_CTRL_REG(port, queue);
+		if (ksz_is_ksz8463(dev))
+			reg = ksz8463_tc_ctrl(port, queue);
+
+		/* Set WFQ enable bit to revert back to default scheduling
+		 * mode
+		 */
+		ret = ksz_rmw8(dev, reg, KSZ8873_TXQ_WFQ_ENABLE,
+			       KSZ8873_TXQ_WFQ_ENABLE);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int ksz_queue_set_strict(struct ksz_device *dev, int port, int queue)
 {
 	int ret;
@@ -4094,6 +4416,7 @@ static int ksz_tc_ets_del(struct ksz_device *dev, int port)
 	for (queue = 0; queue < dev->info->num_tx_queues; queue++) {
 		ret = ksz_queue_set_wrr(dev, port, queue,
 					KSZ9477_DEFAULT_WRR_WEIGHT);
+
 		if (ret)
 			return ret;
 	}
@@ -4146,7 +4469,7 @@ static int ksz_tc_setup_qdisc_ets(struct dsa_switch *ds, int port,
 	struct ksz_device *dev = ds->priv;
 	int ret;
 
-	if (is_ksz8(dev))
+	if (is_ksz8(dev) && !(ksz_is_ksz88x3(dev) || ksz_is_ksz8463(dev)))
 		return -EOPNOTSUPP;
 
 	if (qopt->parent != TC_H_ROOT) {
@@ -4160,9 +4483,16 @@ static int ksz_tc_setup_qdisc_ets(struct dsa_switch *ds, int port,
 		if (ret)
 			return ret;
 
-		return ksz_tc_ets_add(dev, port, &qopt->replace_params);
+		if (ksz_is_ksz88x3(dev) || ksz_is_ksz8463(dev))
+			return ksz88x3_tc_ets_add(dev, port,
+						  &qopt->replace_params);
+		else
+			return ksz_tc_ets_add(dev, port, &qopt->replace_params);
 	case TC_ETS_DESTROY:
-		return ksz_tc_ets_del(dev, port);
+		if (ksz_is_ksz88x3(dev) || ksz_is_ksz8463(dev))
+			return ksz88x3_tc_ets_del(dev, port);
+		else
+			return ksz_tc_ets_del(dev, port);
 	case TC_ETS_STATS:
 	case TC_ETS_GRAFT:
 		return -EOPNOTSUPP;
@@ -4502,7 +4832,16 @@ int ksz_switch_macaddr_get(struct dsa_switch *ds, int port,
 
 	/* Program the switch MAC address to hardware */
 	for (i = 0; i < ETH_ALEN; i++) {
-		ret = ksz_write8(dev, regs[REG_SW_MAC_ADDR] + i, addr[i]);
+		if (ksz_is_ksz8463(dev)) {
+			u16 addr16 = ((u16)addr[i] << 8) | addr[i + 1];
+
+			ret = ksz_write16(dev, regs[REG_SW_MAC_ADDR] + i,
+					  addr16);
+			i++;
+		} else {
+			ret = ksz_write8(dev, regs[REG_SW_MAC_ADDR] + i,
+					 addr[i]);
+		}
 		if (ret)
 			goto macaddr_drop;
 	}
@@ -4672,7 +5011,6 @@ static const struct dsa_switch_ops ksz_switch_ops = {
 	.cls_flower_del		= ksz_cls_flower_del,
 	.port_setup_tc		= ksz_setup_tc,
 	.support_eee		= ksz_support_eee,
-	.get_mac_eee		= ksz_get_mac_eee,
 	.set_mac_eee		= ksz_set_mac_eee,
 	.port_get_default_prio	= ksz_port_get_default_prio,
 	.port_set_default_prio	= ksz_port_set_default_prio,
@@ -5011,6 +5349,38 @@ static int ksz_parse_drive_strength(struct ksz_device *dev)
 	return 0;
 }
 
+static int ksz8463_configure_straps_spi(struct ksz_device *dev)
+{
+	struct pinctrl *pinctrl;
+	struct gpio_desc *rxd0;
+	struct gpio_desc *rxd1;
+
+	rxd0 = devm_gpiod_get_index_optional(dev->dev, "straps-rxd", 0, GPIOD_OUT_LOW);
+	if (IS_ERR(rxd0))
+		return PTR_ERR(rxd0);
+
+	rxd1 = devm_gpiod_get_index_optional(dev->dev, "straps-rxd", 1, GPIOD_OUT_HIGH);
+	if (IS_ERR(rxd1))
+		return PTR_ERR(rxd1);
+
+	if (!rxd0 && !rxd1)
+		return 0;
+
+	if ((rxd0 && !rxd1) || (rxd1 && !rxd0))
+		return -EINVAL;
+
+	pinctrl = devm_pinctrl_get_select(dev->dev, "reset");
+	if (IS_ERR(pinctrl))
+		return PTR_ERR(pinctrl);
+
+	return 0;
+}
+
+static int ksz8463_release_straps_spi(struct ksz_device *dev)
+{
+	return pinctrl_select_default_state(dev->dev);
+}
+
 int ksz_switch_register(struct ksz_device *dev)
 {
 	const struct ksz_chip_data *info;
@@ -5026,10 +5396,22 @@ int ksz_switch_register(struct ksz_device *dev)
 		return PTR_ERR(dev->reset_gpio);
 
 	if (dev->reset_gpio) {
+		if (of_device_is_compatible(dev->dev->of_node, "microchip,ksz8463")) {
+			ret = ksz8463_configure_straps_spi(dev);
+			if (ret)
+				return ret;
+		}
+
 		gpiod_set_value_cansleep(dev->reset_gpio, 1);
 		usleep_range(10000, 12000);
 		gpiod_set_value_cansleep(dev->reset_gpio, 0);
 		msleep(100);
+
+		if (of_device_is_compatible(dev->dev->of_node, "microchip,ksz8463")) {
+			ret = ksz8463_release_straps_spi(dev);
+			if (ret)
+				return ret;
+		}
 	}
 
 	mutex_init(&dev->dev_mutex);
@@ -5112,6 +5494,9 @@ int ksz_switch_register(struct ksz_device *dev)
 						&dev->ports[port_num].interface);
 
 				ksz_parse_rgmii_delay(dev, port_num, port);
+				dev->ports[port_num].fiber =
+					of_property_read_bool(port,
+							      "micrel,fiber-mode");
 			}
 			of_node_put(ports);
 		}
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index af17a9c030d4..c65188cd3c0a 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Microchip switch driver common header
  *
- * Copyright (C) 2017-2024 Microchip Technology Inc.
+ * Copyright (C) 2017-2025 Microchip Technology Inc.
  */
 
 #ifndef __KSZ_COMMON_H
@@ -10,6 +10,7 @@
 #include <linux/etherdevice.h>
 #include <linux/kernel.h>
 #include <linux/mutex.h>
+#include <linux/pcs/pcs-xpcs.h>
 #include <linux/phy.h>
 #include <linux/regmap.h>
 #include <net/dsa.h>
@@ -93,6 +94,7 @@ struct ksz_chip_data {
 	bool internal_phy[KSZ_MAX_NUM_PORTS];
 	bool gbit_capable[KSZ_MAX_NUM_PORTS];
 	bool ptp_capable;
+	u8 sgmii_port;
 	const struct regmap_access_table *wr_table;
 	const struct regmap_access_table *rd_table;
 };
@@ -132,6 +134,7 @@ struct ksz_port {
 	u32 force:1;
 	u32 read:1;			/* read MIB counters in background */
 	u32 freeze:1;			/* MIB counter freeze is enabled */
+	u32 sgmii_adv_write:1;
 
 	struct ksz_port_mib mib;
 	phy_interface_t interface;
@@ -141,8 +144,9 @@ struct ksz_port {
 	void *acl_priv;
 	struct ksz_irq pirq;
 	u8 num;
+	struct phylink_pcs *pcs;
 #if IS_ENABLED(CONFIG_NET_DSA_MICROCHIP_KSZ_PTP)
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 	bool hwts_tx_en;
 	bool hwts_rx_en;
 	struct ksz_irq ptpirq;
@@ -218,6 +222,7 @@ struct ksz_device {
 
 /* List of supported models */
 enum ksz_model {
+	KSZ8463,
 	KSZ8563,
 	KSZ8567,
 	KSZ8795,
@@ -289,6 +294,8 @@ enum ksz_masks {
 	DYNAMIC_MAC_TABLE_TIMESTAMP,
 	ALU_STAT_WRITE,
 	ALU_STAT_READ,
+	ALU_STAT_DIRECT,
+	ALU_RESV_MCAST_ADDR,
 	P_MII_TX_FLOW_CTRL,
 	P_MII_RX_FLOW_CTRL,
 };
@@ -440,6 +447,8 @@ struct ksz_dev_ops {
 	int (*reset)(struct ksz_device *dev);
 	int (*init)(struct ksz_device *dev);
 	void (*exit)(struct ksz_device *dev);
+
+	int (*pcs_create)(struct ksz_device *dev);
 };
 
 struct ksz_device *ksz_switch_alloc(struct device *base, void *priv);
@@ -478,6 +487,11 @@ static inline struct regmap *ksz_regmap_32(struct ksz_device *dev)
 	return dev->regmap[KSZ_REGMAP_32];
 }
 
+static inline bool ksz_is_ksz8463(struct ksz_device *dev)
+{
+	return dev->chip_id == KSZ8463_CHIP_ID;
+}
+
 static inline int ksz_read8(struct ksz_device *dev, u32 reg, u8 *val)
 {
 	unsigned int value;
@@ -703,12 +717,13 @@ static inline bool ksz_is_8895_family(struct ksz_device *dev)
 static inline bool is_ksz8(struct ksz_device *dev)
 {
 	return ksz_is_ksz87xx(dev) || ksz_is_ksz88x3(dev) ||
-	       ksz_is_8895_family(dev);
+	       ksz_is_8895_family(dev) || ksz_is_ksz8463(dev);
 }
 
 static inline bool is_ksz88xx(struct ksz_device *dev)
 {
-	return ksz_is_ksz88x3(dev) || ksz_is_8895_family(dev);
+	return ksz_is_ksz88x3(dev) || ksz_is_8895_family(dev) ||
+	       ksz_is_ksz8463(dev);
 }
 
 static inline bool is_ksz9477(struct ksz_device *dev)
@@ -731,6 +746,21 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port)
 		dev->chip_id == LAN9372_CHIP_ID) && port == KSZ_PORT_4;
 }
 
+static inline int ksz_get_sgmii_port(struct ksz_device *dev)
+{
+	return dev->info->sgmii_port - 1;
+}
+
+static inline bool ksz_has_sgmii_port(struct ksz_device *dev)
+{
+	return dev->info->sgmii_port > 0;
+}
+
+static inline bool ksz_is_sgmii_port(struct ksz_device *dev, int port)
+{
+	return dev->info->sgmii_port == port + 1;
+}
+
 /* STP State Defines */
 #define PORT_TX_ENABLE			BIT(2)
 #define PORT_RX_ENABLE			BIT(1)
@@ -740,6 +770,7 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port)
 #define REG_CHIP_ID0			0x00
 
 #define SW_FAMILY_ID_M			GENMASK(15, 8)
+#define KSZ84_FAMILY_ID			0x84
 #define KSZ87_FAMILY_ID			0x87
 #define KSZ88_FAMILY_ID			0x88
 #define KSZ8895_FAMILY_ID		0x95
@@ -836,6 +867,25 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port)
 #define SW_HI_SPEED_DRIVE_STRENGTH_S	4
 #define SW_LO_SPEED_DRIVE_STRENGTH_S	0
 
+/* TXQ Split Control Register for per-port, per-queue configuration.
+ * Register 0xAF is TXQ Split for Q3 on Port 1.
+ * Register offset formula: 0xAF + (port * 4) + (3 - queue)
+ *   where: port = 0..2, queue = 0..3
+ */
+#define KSZ8873_TXQ_SPLIT_CTRL_REG(port, queue) \
+	(0xAF + ((port) * 4) + (3 - (queue)))
+
+/* Bit 7 selects between:
+ *   0 = Strict priority mode (highest-priority queue first)
+ *   1 = Weighted Fair Queuing (WFQ) mode:
+ *       Queue weights: Q3:Q2:Q1:Q0 = 8:4:2:1
+ *       If any queues are empty, weight is redistributed.
+ *
+ * Note: This is referred to as "Weighted Fair Queuing" (WFQ) in KSZ8863/8873
+ * documentation, and as "Weighted Round Robin" (WRR) in KSZ9477 family docs.
+ */
+#define KSZ8873_TXQ_WFQ_ENABLE		BIT(7)
+
 #define KSZ9477_REG_PORT_OUT_RATE_0	0x0420
 #define KSZ9477_OUT_RATE_NO_LIMIT	0
 
@@ -899,4 +949,29 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port)
 		[KSZ_REGMAP_32] = KSZ_REGMAP_ENTRY(32, swp, (regbits), (regpad), (regalign)), \
 	}
 
+#define KSZ8463_REGMAP_ENTRY(width, regbits, regpad, regalign)		\
+	{								\
+		.name = #width,						\
+		.val_bits = (width),					\
+		.reg_stride = (width / 8),				\
+		.reg_bits = (regbits) + (regalign),			\
+		.pad_bits = (regpad),					\
+		.read = ksz8463_spi_read,				\
+		.write = ksz8463_spi_write,				\
+		.max_register = BIT(regbits) - 1,			\
+		.cache_type = REGCACHE_NONE,				\
+		.zero_flag_mask = 1,					\
+		.use_single_read = 1,					\
+		.use_single_write = 1,					\
+		.lock = ksz_regmap_lock,				\
+		.unlock = ksz_regmap_unlock,				\
+	}
+
+#define KSZ8463_REGMAP_TABLE(ksz, regbits, regpad, regalign)		\
+	static const struct regmap_config ksz##_regmap_config[] = {	\
+		[KSZ_REGMAP_8] = KSZ8463_REGMAP_ENTRY(8, (regbits), (regpad), (regalign)), \
+		[KSZ_REGMAP_16] = KSZ8463_REGMAP_ENTRY(16, (regbits), (regpad), (regalign)), \
+		[KSZ_REGMAP_32] = KSZ8463_REGMAP_ENTRY(32, (regbits), (regpad), (regalign)), \
+	}
+
 #endif
diff --git a/drivers/net/dsa/microchip/ksz_dcb.c b/drivers/net/dsa/microchip/ksz_dcb.c
index 30b4a6186e38..7131c5caac54 100644
--- a/drivers/net/dsa/microchip/ksz_dcb.c
+++ b/drivers/net/dsa/microchip/ksz_dcb.c
@@ -10,11 +10,18 @@
 #include "ksz_dcb.h"
 #include "ksz8.h"
 
-#define KSZ8_REG_PORT_1_CTRL_0			0x10
+/* Port X Control 0 register.
+ * The datasheet specifies: Port 1 - 0x10, Port 2 - 0x20, Port 3 - 0x30.
+ * However, the driver uses get_port_addr(), which maps Port 1 to offset 0.
+ * Therefore, we define the base offset as 0x00 here to align with that logic.
+ */
+#define KSZ8_REG_PORT_1_CTRL_0			0x00
+#define KSZ8463_REG_PORT_1_CTRL_0		0x6C
 #define KSZ8_PORT_DIFFSERV_ENABLE		BIT(6)
 #define KSZ8_PORT_802_1P_ENABLE			BIT(5)
 #define KSZ8_PORT_BASED_PRIO_M			GENMASK(4, 3)
 
+#define KSZ8463_REG_TOS_DSCP_CTRL		0x16
 #define KSZ88X3_REG_TOS_DSCP_CTRL		0x60
 #define KSZ8765_REG_TOS_DSCP_CTRL		0x90
 
@@ -93,6 +100,8 @@ static void ksz_get_default_port_prio_reg(struct ksz_device *dev, int *reg,
 		*reg = KSZ8_REG_PORT_1_CTRL_0;
 		*mask = KSZ8_PORT_BASED_PRIO_M;
 		*shift = __bf_shf(KSZ8_PORT_BASED_PRIO_M);
+		if (ksz_is_ksz8463(dev))
+			*reg = KSZ8463_REG_PORT_1_CTRL_0;
 	} else {
 		*reg = KSZ9477_REG_PORT_MRI_MAC_CTRL;
 		*mask = KSZ9477_PORT_BASED_PRIO_M;
@@ -117,10 +126,12 @@ static void ksz_get_dscp_prio_reg(struct ksz_device *dev, int *reg,
 		*reg = KSZ8765_REG_TOS_DSCP_CTRL;
 		*per_reg = 4;
 		*mask = GENMASK(1, 0);
-	} else if (ksz_is_ksz88x3(dev)) {
+	} else if (ksz_is_ksz88x3(dev) || ksz_is_ksz8463(dev)) {
 		*reg = KSZ88X3_REG_TOS_DSCP_CTRL;
 		*per_reg = 4;
 		*mask = GENMASK(1, 0);
+		if (ksz_is_ksz8463(dev))
+			*reg = KSZ8463_REG_TOS_DSCP_CTRL;
 	} else {
 		*reg = KSZ9477_REG_DIFFSERV_PRIO_MAP;
 		*per_reg = 2;
@@ -146,6 +157,8 @@ static void ksz_get_apptrust_map_and_reg(struct ksz_device *dev,
 		*map = ksz8_apptrust_map_to_bit;
 		*reg = KSZ8_REG_PORT_1_CTRL_0;
 		*mask = KSZ8_PORT_DIFFSERV_ENABLE | KSZ8_PORT_802_1P_ENABLE;
+		if (ksz_is_ksz8463(dev))
+			*reg = KSZ8463_REG_PORT_1_CTRL_0;
 	} else {
 		*map = ksz9477_apptrust_map_to_bit;
 		*reg = KSZ9477_REG_PORT_MRI_PRIO_CTRL;
@@ -182,49 +195,6 @@ int ksz_port_get_default_prio(struct dsa_switch *ds, int port)
 }
 
 /**
- * ksz88x3_port_set_default_prio_quirks - Quirks for default priority
- * @dev: Pointer to the KSZ switch device structure
- * @port: Port number for which to set the default priority
- * @prio: Priority value to set
- *
- * This function implements quirks for setting the default priority on KSZ88x3
- * devices. On Port 2, no other priority providers are working
- * except of PCP. So, configuring default priority on Port 2 is not possible.
- * On Port 1, it is not possible to configure port priority if PCP
- * apptrust on Port 2 is disabled. Since we disable multiple queues on the
- * switch to disable PCP on Port 2, we need to ensure that the default priority
- * configuration on Port 1 is in agreement with the configuration on Port 2.
- *
- * Return: 0 on success, or a negative error code on failure
- */
-static int ksz88x3_port_set_default_prio_quirks(struct ksz_device *dev, int port,
-						u8 prio)
-{
-	if (!prio)
-		return 0;
-
-	if (port == KSZ_PORT_2) {
-		dev_err(dev->dev, "Port priority configuration is not working on Port 2\n");
-		return -EINVAL;
-	} else if (port == KSZ_PORT_1) {
-		u8 port2_data;
-		int ret;
-
-		ret = ksz_pread8(dev, KSZ_PORT_2, KSZ8_REG_PORT_1_CTRL_0,
-				 &port2_data);
-		if (ret)
-			return ret;
-
-		if (!(port2_data & KSZ8_PORT_802_1P_ENABLE)) {
-			dev_err(dev->dev, "Not possible to configure port priority on Port 1 if PCP apptrust on Port 2 is disabled\n");
-			return -EINVAL;
-		}
-	}
-
-	return 0;
-}
-
-/**
  * ksz_port_set_default_prio - Sets the default priority for a port on a KSZ
  *			       switch
  * @ds: Pointer to the DSA switch structure
@@ -239,18 +209,12 @@ static int ksz88x3_port_set_default_prio_quirks(struct ksz_device *dev, int port
 int ksz_port_set_default_prio(struct dsa_switch *ds, int port, u8 prio)
 {
 	struct ksz_device *dev = ds->priv;
-	int reg, shift, ret;
+	int reg, shift;
 	u8 mask;
 
 	if (prio >= dev->info->num_ipms)
 		return -EINVAL;
 
-	if (ksz_is_ksz88x3(dev)) {
-		ret = ksz88x3_port_set_default_prio_quirks(dev, port, prio);
-		if (ret)
-			return ret;
-	}
-
 	ksz_get_default_port_prio_reg(dev, &reg, &mask, &shift);
 
 	return ksz_prmw8(dev, port, reg, mask, (prio << shift) & mask);
@@ -519,155 +483,6 @@ err_sel_not_vaild:
 }
 
 /**
- * ksz88x3_port1_apptrust_quirk - Quirk for apptrust configuration on Port 1
- *				  of KSZ88x3 devices
- * @dev: Pointer to the KSZ switch device structure
- * @port: Port number for which to set the apptrust selectors
- * @reg: Register address for the apptrust configuration
- * @port1_data: Data to set for the apptrust configuration
- *
- * This function implements a quirk for apptrust configuration on Port 1 of
- * KSZ88x3 devices. It ensures that apptrust configuration on Port 1 is not
- * possible if PCP apptrust on Port 2 is disabled. This is because the Port 2
- * seems to be permanently hardwired to PCP classification, so we need to
- * do Port 1 configuration always in agreement with Port 2 configuration.
- *
- * Return: 0 on success, or a negative error code on failure
- */
-static int ksz88x3_port1_apptrust_quirk(struct ksz_device *dev, int port,
-					int reg, u8 port1_data)
-{
-	u8 port2_data;
-	int ret;
-
-	/* If no apptrust is requested for Port 1, no need to care about Port 2
-	 * configuration.
-	 */
-	if (!(port1_data & (KSZ8_PORT_802_1P_ENABLE | KSZ8_PORT_DIFFSERV_ENABLE)))
-		return 0;
-
-	/* We got request to enable any apptrust on Port 1. To make it possible,
-	 * we need to enable multiple queues on the switch. If we enable
-	 * multiqueue support, PCP classification on Port 2 will be
-	 * automatically activated by HW.
-	 */
-	ret = ksz_pread8(dev, KSZ_PORT_2, reg, &port2_data);
-	if (ret)
-		return ret;
-
-	/* If KSZ8_PORT_802_1P_ENABLE bit is set on Port 2, the driver showed
-	 * the interest in PCP classification on Port 2. In this case,
-	 * multiqueue support is enabled and we can enable any apptrust on
-	 * Port 1.
-	 * If KSZ8_PORT_802_1P_ENABLE bit is not set on Port 2, the PCP
-	 * classification on Port 2 is still active, but the driver disabled
-	 * multiqueue support and made frame prioritization inactive for
-	 * all ports. In this case, we can't enable any apptrust on Port 1.
-	 */
-	if (!(port2_data & KSZ8_PORT_802_1P_ENABLE)) {
-		dev_err(dev->dev, "Not possible to enable any apptrust on Port 1 if PCP apptrust on Port 2 is disabled\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-/**
- * ksz88x3_port2_apptrust_quirk - Quirk for apptrust configuration on Port 2
- *				  of KSZ88x3 devices
- * @dev: Pointer to the KSZ switch device structure
- * @port: Port number for which to set the apptrust selectors
- * @reg: Register address for the apptrust configuration
- * @port2_data: Data to set for the apptrust configuration
- *
- * This function implements a quirk for apptrust configuration on Port 2 of
- * KSZ88x3 devices. It ensures that DSCP apptrust is not working on Port 2 and
- * that it is not possible to disable PCP on Port 2. The only way to disable PCP
- * on Port 2 is to disable multiple queues on the switch.
- *
- * Return: 0 on success, or a negative error code on failure
- */
-static int ksz88x3_port2_apptrust_quirk(struct ksz_device *dev, int port,
-					int reg, u8 port2_data)
-{
-	struct dsa_switch *ds = dev->ds;
-	u8 port1_data;
-	int ret;
-
-	/* First validate Port 2 configuration. DiffServ/DSCP is not working
-	 * on this port.
-	 */
-	if (port2_data & KSZ8_PORT_DIFFSERV_ENABLE) {
-		dev_err(dev->dev, "DSCP apptrust is not working on Port 2\n");
-		return -EINVAL;
-	}
-
-	/* If PCP support is requested, we need to enable all queues on the
-	 * switch to make PCP priority working on Port 2.
-	 */
-	if (port2_data & KSZ8_PORT_802_1P_ENABLE)
-		return ksz8_all_queues_split(dev, dev->info->num_tx_queues);
-
-	/* We got request to disable PCP priority on Port 2.
-	 * Now, we need to compare Port 2 configuration with Port 1
-	 * configuration.
-	 */
-	ret = ksz_pread8(dev, KSZ_PORT_1, reg, &port1_data);
-	if (ret)
-		return ret;
-
-	/* If Port 1 has any apptrust enabled, we can't disable multiple queues
-	 * on the switch, so we can't disable PCP on Port 2.
-	 */
-	if (port1_data & (KSZ8_PORT_802_1P_ENABLE | KSZ8_PORT_DIFFSERV_ENABLE)) {
-		dev_err(dev->dev, "Not possible to disable PCP on Port 2 if any apptrust is enabled on Port 1\n");
-		return -EINVAL;
-	}
-
-	/* Now we need to ensure that default priority on Port 1 is set to 0
-	 * otherwise we can't disable multiqueue support on the switch.
-	 */
-	ret = ksz_port_get_default_prio(ds, KSZ_PORT_1);
-	if (ret < 0) {
-		return ret;
-	} else if (ret) {
-		dev_err(dev->dev, "Not possible to disable PCP on Port 2 if non zero default priority is set on Port 1\n");
-		return -EINVAL;
-	}
-
-	/* Port 1 has no apptrust or default priority set and we got request to
-	 * disable PCP on Port 2. We can disable multiqueue support to disable
-	 * PCP on Port 2.
-	 */
-	return ksz8_all_queues_split(dev, 1);
-}
-
-/**
- * ksz88x3_port_apptrust_quirk - Quirk for apptrust configuration on KSZ88x3
- *			       devices
- * @dev: Pointer to the KSZ switch device structure
- * @port: Port number for which to set the apptrust selectors
- * @reg: Register address for the apptrust configuration
- * @data: Data to set for the apptrust configuration
- *
- * This function implements a quirk for apptrust configuration on KSZ88x3
- * devices. It ensures that apptrust configuration on Port 1 and
- * Port 2 is done in agreement with each other.
- *
- * Return: 0 on success, or a negative error code on failure
- */
-static int ksz88x3_port_apptrust_quirk(struct ksz_device *dev, int port,
-				       int reg, u8 data)
-{
-	if (port == KSZ_PORT_1)
-		return ksz88x3_port1_apptrust_quirk(dev, port, reg, data);
-	else if (port == KSZ_PORT_2)
-		return ksz88x3_port2_apptrust_quirk(dev, port, reg, data);
-
-	return 0;
-}
-
-/**
  * ksz_port_set_apptrust - Sets the apptrust selectors for a port on a KSZ
  *			   switch
  * @ds: Pointer to the DSA switch structure
@@ -707,12 +522,6 @@ int ksz_port_set_apptrust(struct dsa_switch *ds, int port,
 		}
 	}
 
-	if (ksz_is_ksz88x3(dev)) {
-		ret = ksz88x3_port_apptrust_quirk(dev, port, reg, data);
-		if (ret)
-			return ret;
-	}
-
 	return ksz_prmw8(dev, port, reg, mask, data);
 }
 
@@ -799,21 +608,5 @@ int ksz_dcb_init_port(struct ksz_device *dev, int port)
  */
 int ksz_dcb_init(struct ksz_device *dev)
 {
-	int ret;
-
-	ret = ksz_init_global_dscp_map(dev);
-	if (ret)
-		return ret;
-
-	/* Enable 802.1p priority control on Port 2 during switch initialization.
-	 * This setup is critical for the apptrust functionality on Port 1, which
-	 * relies on the priority settings of Port 2. Note: Port 1 is naturally
-	 * configured before Port 2, necessitating this configuration order.
-	 */
-	if (ksz_is_ksz88x3(dev))
-		return ksz_prmw8(dev, KSZ_PORT_2, KSZ8_REG_PORT_1_CTRL_0,
-				 KSZ8_PORT_802_1P_ENABLE,
-				 KSZ8_PORT_802_1P_ENABLE);
-
-	return 0;
+	return ksz_init_global_dscp_map(dev);
 }
diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c
index 22fb9ef4645c..997e4a76d0a6 100644
--- a/drivers/net/dsa/microchip/ksz_ptp.c
+++ b/drivers/net/dsa/microchip/ksz_ptp.c
@@ -319,22 +319,21 @@ int ksz_get_ts_info(struct dsa_switch *ds, int port, struct kernel_ethtool_ts_in
 	return 0;
 }
 
-int ksz_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr)
+int ksz_hwtstamp_get(struct dsa_switch *ds, int port,
+		     struct kernel_hwtstamp_config *config)
 {
 	struct ksz_device *dev = ds->priv;
-	struct hwtstamp_config *config;
 	struct ksz_port *prt;
 
 	prt = &dev->ports[port];
-	config = &prt->tstamp_config;
+	*config = prt->tstamp_config;
 
-	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 static int ksz_set_hwtstamp_config(struct ksz_device *dev,
 				   struct ksz_port *prt,
-				   struct hwtstamp_config *config)
+				   struct kernel_hwtstamp_config *config)
 {
 	int ret;
 
@@ -404,26 +403,21 @@ static int ksz_set_hwtstamp_config(struct ksz_device *dev,
 	return ksz_ptp_enable_mode(dev);
 }
 
-int ksz_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr)
+int ksz_hwtstamp_set(struct dsa_switch *ds, int port,
+		     struct kernel_hwtstamp_config *config,
+		     struct netlink_ext_ack *extack)
 {
 	struct ksz_device *dev = ds->priv;
-	struct hwtstamp_config config;
 	struct ksz_port *prt;
 	int ret;
 
 	prt = &dev->ports[port];
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	ret = ksz_set_hwtstamp_config(dev, prt, &config);
+	ret = ksz_set_hwtstamp_config(dev, prt, config);
 	if (ret)
 		return ret;
 
-	memcpy(&prt->tstamp_config, &config, sizeof(config));
-
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	prt->tstamp_config = *config;
 
 	return 0;
 }
@@ -1099,19 +1093,19 @@ static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n)
 	static const char * const name[] = {"pdresp-msg", "xdreq-msg",
 					    "sync-msg"};
 	const struct ksz_dev_ops *ops = port->ksz_dev->dev_ops;
+	struct ksz_irq *ptpirq = &port->ptpirq;
 	struct ksz_ptp_irq *ptpmsg_irq;
 
 	ptpmsg_irq = &port->ptpmsg_irq[n];
+	ptpmsg_irq->num = irq_create_mapping(ptpirq->domain, n);
+	if (!ptpmsg_irq->num)
+		return -EINVAL;
 
 	ptpmsg_irq->port = port;
 	ptpmsg_irq->ts_reg = ops->get_port_addr(port->num, ts_reg[n]);
 
 	strscpy(ptpmsg_irq->name, name[n]);
 
-	ptpmsg_irq->num = irq_find_mapping(port->ptpirq.domain, n);
-	if (ptpmsg_irq->num < 0)
-		return ptpmsg_irq->num;
-
 	return request_threaded_irq(ptpmsg_irq->num, NULL,
 				    ksz_ptp_msg_thread_fn, IRQF_ONESHOT,
 				    ptpmsg_irq->name, ptpmsg_irq);
@@ -1136,17 +1130,14 @@ int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p)
 
 	init_completion(&port->tstamp_msg_comp);
 
-	ptpirq->domain = irq_domain_add_linear(dev->dev->of_node, ptpirq->nirqs,
-					       &ksz_ptp_irq_domain_ops, ptpirq);
+	ptpirq->domain = irq_domain_create_linear(dev_fwnode(dev->dev), ptpirq->nirqs,
+						  &ksz_ptp_irq_domain_ops, ptpirq);
 	if (!ptpirq->domain)
 		return -ENOMEM;
 
-	for (irq = 0; irq < ptpirq->nirqs; irq++)
-		irq_create_mapping(ptpirq->domain, irq);
-
 	ptpirq->irq_num = irq_find_mapping(port->pirq.domain, PORT_SRC_PTP_INT);
-	if (ptpirq->irq_num < 0) {
-		ret = ptpirq->irq_num;
+	if (!ptpirq->irq_num) {
+		ret = -EINVAL;
 		goto out;
 	}
 
@@ -1165,12 +1156,11 @@ int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p)
 
 out_ptp_msg:
 	free_irq(ptpirq->irq_num, ptpirq);
-	while (irq--)
+	while (irq--) {
 		free_irq(port->ptpmsg_irq[irq].num, &port->ptpmsg_irq[irq]);
-out:
-	for (irq = 0; irq < ptpirq->nirqs; irq++)
 		irq_dispose_mapping(port->ptpmsg_irq[irq].num);
-
+	}
+out:
 	irq_domain_remove(ptpirq->domain);
 
 	return ret;
diff --git a/drivers/net/dsa/microchip/ksz_ptp.h b/drivers/net/dsa/microchip/ksz_ptp.h
index 2f1783c0d723..3086e519b1b6 100644
--- a/drivers/net/dsa/microchip/ksz_ptp.h
+++ b/drivers/net/dsa/microchip/ksz_ptp.h
@@ -39,8 +39,11 @@ void ksz_ptp_clock_unregister(struct dsa_switch *ds);
 
 int ksz_get_ts_info(struct dsa_switch *ds, int port,
 		    struct kernel_ethtool_ts_info *ts);
-int ksz_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr);
-int ksz_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr);
+int ksz_hwtstamp_get(struct dsa_switch *ds, int port,
+		     struct kernel_hwtstamp_config *config);
+int ksz_hwtstamp_set(struct dsa_switch *ds, int port,
+		     struct kernel_hwtstamp_config *config,
+		     struct netlink_ext_ack *extack);
 void ksz_port_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb);
 void ksz_port_deferred_xmit(struct kthread_work *work);
 bool ksz_port_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb,
diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c
index b633d263098c..d8001734b057 100644
--- a/drivers/net/dsa/microchip/ksz_spi.c
+++ b/drivers/net/dsa/microchip/ksz_spi.c
@@ -16,6 +16,10 @@
 
 #include "ksz_common.h"
 
+#define KSZ8463_SPI_ADDR_SHIFT			13
+#define KSZ8463_SPI_ADDR_ALIGN			3
+#define KSZ8463_SPI_TURNAROUND_SHIFT		2
+
 #define KSZ8795_SPI_ADDR_SHIFT			12
 #define KSZ8795_SPI_ADDR_ALIGN			3
 #define KSZ8795_SPI_TURNAROUND_SHIFT		1
@@ -37,6 +41,99 @@ KSZ_REGMAP_TABLE(ksz8863, 16, KSZ8863_SPI_ADDR_SHIFT,
 KSZ_REGMAP_TABLE(ksz9477, 32, KSZ9477_SPI_ADDR_SHIFT,
 		 KSZ9477_SPI_TURNAROUND_SHIFT, KSZ9477_SPI_ADDR_ALIGN);
 
+static u16 ksz8463_reg(u16 reg, size_t size)
+{
+	switch (size) {
+	case 1:
+		reg = ((reg >> 2) << 4) | (1 << (reg & 3));
+		break;
+	case 2:
+		reg = ((reg >> 2) << 4) | (reg & 2 ? 0x0c : 0x03);
+		break;
+	default:
+		reg = ((reg >> 2) << 4) | 0xf;
+		break;
+	}
+	reg <<= KSZ8463_SPI_TURNAROUND_SHIFT;
+	return reg;
+}
+
+static int ksz8463_spi_read(void *context,
+			    const void *reg, size_t reg_size,
+			    void *val, size_t val_size)
+{
+	struct device *dev = context;
+	struct spi_device *spi = to_spi_device(dev);
+	u8 bytes[2];
+	u16 cmd;
+	int rc;
+
+	if (reg_size > 2 || val_size > 4)
+		return -EINVAL;
+	memcpy(&cmd, reg, sizeof(u16));
+	cmd = ksz8463_reg(cmd, val_size);
+	/* SPI command uses big-endian format. */
+	put_unaligned_be16(cmd, bytes);
+	rc = spi_write_then_read(spi, bytes, reg_size, val, val_size);
+#if defined(__BIG_ENDIAN)
+	/* Register value uses little-endian format so need to convert when
+	 * running in big-endian system.
+	 */
+	if (!rc && val_size > 1) {
+		if (val_size == 2) {
+			u16 v = get_unaligned_le16(val);
+
+			memcpy(val, &v, sizeof(v));
+		} else if (val_size == 4) {
+			u32 v = get_unaligned_le32(val);
+
+			memcpy(val, &v, sizeof(v));
+		}
+	}
+#endif
+	return rc;
+}
+
+static int ksz8463_spi_write(void *context, const void *data, size_t count)
+{
+	struct device *dev = context;
+	struct spi_device *spi = to_spi_device(dev);
+	size_t val_size = count - 2;
+	u8 bytes[6];
+	u16 cmd;
+
+	if (count <= 2 || count > 6)
+		return -EINVAL;
+	memcpy(bytes, data, count);
+	memcpy(&cmd, data, sizeof(u16));
+	cmd = ksz8463_reg(cmd, val_size);
+	cmd |= (1 << (KSZ8463_SPI_ADDR_SHIFT + KSZ8463_SPI_TURNAROUND_SHIFT));
+	/* SPI command uses big-endian format. */
+	put_unaligned_be16(cmd, bytes);
+#if defined(__BIG_ENDIAN)
+	/* Register value uses little-endian format so need to convert when
+	 * running in big-endian system.
+	 */
+	if (val_size == 2) {
+		u8 *val = &bytes[2];
+		u16 v;
+
+		memcpy(&v, val, sizeof(v));
+		put_unaligned_le16(v, val);
+	} else if (val_size == 4) {
+		u8 *val = &bytes[2];
+		u32 v;
+
+		memcpy(&v, val, sizeof(v));
+		put_unaligned_le32(v, val);
+	}
+#endif
+	return spi_write(spi, bytes, count);
+}
+
+KSZ8463_REGMAP_TABLE(ksz8463, KSZ8463_SPI_ADDR_SHIFT, 0,
+		     KSZ8463_SPI_ADDR_ALIGN);
+
 static int ksz_spi_probe(struct spi_device *spi)
 {
 	const struct regmap_config *regmap_config;
@@ -58,6 +155,8 @@ static int ksz_spi_probe(struct spi_device *spi)
 	dev->chip_id = chip->chip_id;
 	if (chip->chip_id == KSZ88X3_CHIP_ID)
 		regmap_config = ksz8863_regmap_config;
+	else if (chip->chip_id == KSZ8463_CHIP_ID)
+		regmap_config = ksz8463_regmap_config;
 	else if (chip->chip_id == KSZ8795_CHIP_ID ||
 		 chip->chip_id == KSZ8794_CHIP_ID ||
 		 chip->chip_id == KSZ8765_CHIP_ID)
@@ -126,6 +225,10 @@ static void ksz_spi_shutdown(struct spi_device *spi)
 
 static const struct of_device_id ksz_dt_ids[] = {
 	{
+		.compatible = "microchip,ksz8463",
+		.data = &ksz_switch_chips[KSZ8463]
+	},
+	{
 		.compatible = "microchip,ksz8765",
 		.data = &ksz_switch_chips[KSZ8765]
 	},
@@ -214,6 +317,7 @@ static const struct of_device_id ksz_dt_ids[] = {
 MODULE_DEVICE_TABLE(of, ksz_dt_ids);
 
 static const struct spi_device_id ksz_spi_ids[] = {
+	{ "ksz8463" },
 	{ "ksz8765" },
 	{ "ksz8794" },
 	{ "ksz8795" },
diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c
index b7652efd632e..5a1496fff445 100644
--- a/drivers/net/dsa/microchip/lan937x_main.c
+++ b/drivers/net/dsa/microchip/lan937x_main.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Microchip LAN937X switch driver main logic
- * Copyright (C) 2019-2022 Microchip Technology Inc.
+ * Copyright (C) 2019-2024 Microchip Technology Inc.
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -461,10 +461,66 @@ int lan937x_change_mtu(struct ksz_device *dev, int port, int new_mtu)
 
 int lan937x_set_ageing_time(struct ksz_device *dev, unsigned int msecs)
 {
-	u32 secs = msecs / 1000;
-	u32 value;
+	u8 data, mult, value8;
+	bool in_msec = false;
+	u32 max_val, value;
+	u32 secs = msecs;
 	int ret;
 
+#define MAX_TIMER_VAL	((1 << 20) - 1)
+
+	/* The aging timer comprises a 3-bit multiplier and a 20-bit second
+	 * value.  Either of them cannot be zero.  The maximum timer is then
+	 * 7 * 1048575 = 7340025 seconds.  As this value is too large for
+	 * practical use it can be interpreted as microseconds, making the
+	 * maximum timer 7340 seconds with finer control.  This allows for
+	 * maximum 122 minutes compared to 29 minutes in KSZ9477 switch.
+	 */
+	if (msecs % 1000)
+		in_msec = true;
+	else
+		secs /= 1000;
+	if (!secs)
+		secs = 1;
+
+	/* Return error if too large. */
+	else if (secs > 7 * MAX_TIMER_VAL)
+		return -EINVAL;
+
+	/* Configure how to interpret the number value. */
+	ret = ksz_rmw8(dev, REG_SW_LUE_CTRL_2, SW_AGE_CNT_IN_MICROSEC,
+		       in_msec ? SW_AGE_CNT_IN_MICROSEC : 0);
+	if (ret < 0)
+		return ret;
+
+	ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &value8);
+	if (ret < 0)
+		return ret;
+
+	/* Check whether there is need to update the multiplier. */
+	mult = FIELD_GET(SW_AGE_CNT_M, value8);
+	max_val = MAX_TIMER_VAL;
+	if (mult > 0) {
+		/* Try to use the same multiplier already in the register as
+		 * the hardware default uses multiplier 4 and 75 seconds for
+		 * 300 seconds.
+		 */
+		max_val = DIV_ROUND_UP(secs, mult);
+		if (max_val > MAX_TIMER_VAL || max_val * mult != secs)
+			max_val = MAX_TIMER_VAL;
+	}
+
+	data = DIV_ROUND_UP(secs, max_val);
+	if (mult != data) {
+		value8 &= ~SW_AGE_CNT_M;
+		value8 |= FIELD_PREP(SW_AGE_CNT_M, data);
+		ret = ksz_write8(dev, REG_SW_LUE_CTRL_0, value8);
+		if (ret < 0)
+			return ret;
+	}
+
+	secs = DIV_ROUND_UP(secs, data);
+
 	value = FIELD_GET(SW_AGE_PERIOD_7_0_M, secs);
 
 	ret = ksz_write8(dev, REG_SW_AGE_PERIOD__1, value);
@@ -484,6 +540,7 @@ static void lan937x_set_tune_adj(struct ksz_device *dev, int port,
 	ksz_pread16(dev, port, reg, &data16);
 
 	/* Update tune Adjust */
+	data16 &= ~PORT_TUNE_ADJ;
 	data16 |= FIELD_PREP(PORT_TUNE_ADJ, val);
 	ksz_pwrite16(dev, port, reg, data16);
 
diff --git a/drivers/net/dsa/microchip/lan937x_reg.h b/drivers/net/dsa/microchip/lan937x_reg.h
index 4ec93e421da4..72042fd64e5b 100644
--- a/drivers/net/dsa/microchip/lan937x_reg.h
+++ b/drivers/net/dsa/microchip/lan937x_reg.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Microchip LAN937X switch register definitions
- * Copyright (C) 2019-2021 Microchip Technology Inc.
+ * Copyright (C) 2019-2024 Microchip Technology Inc.
  */
 #ifndef __LAN937X_REG_H
 #define __LAN937X_REG_H
@@ -56,8 +56,7 @@
 
 #define SW_VLAN_ENABLE			BIT(7)
 #define SW_DROP_INVALID_VID		BIT(6)
-#define SW_AGE_CNT_M			0x7
-#define SW_AGE_CNT_S			3
+#define SW_AGE_CNT_M			GENMASK(5, 3)
 #define SW_RESV_MCAST_ENABLE		BIT(2)
 
 #define REG_SW_LUE_CTRL_1		0x0311
@@ -70,6 +69,10 @@
 #define SW_FAST_AGING			BIT(1)
 #define SW_LINK_AUTO_AGING		BIT(0)
 
+#define REG_SW_LUE_CTRL_2		0x0312
+
+#define SW_AGE_CNT_IN_MICROSEC		BIT(7)
+
 #define REG_SW_AGE_PERIOD__1		0x0313
 #define SW_AGE_PERIOD_7_0_M		GENMASK(7, 0)
 
diff --git a/drivers/net/dsa/mt7530-mdio.c b/drivers/net/dsa/mt7530-mdio.c
index 51df42ccdbe6..0286a6cecb6f 100644
--- a/drivers/net/dsa/mt7530-mdio.c
+++ b/drivers/net/dsa/mt7530-mdio.c
@@ -136,10 +136,17 @@ static const struct of_device_id mt7530_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, mt7530_of_match);
 
+static const struct regmap_config regmap_config = {
+	.reg_bits = 16,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = MT7530_CREV,
+	.disable_locking = true,
+};
+
 static int
 mt7530_probe(struct mdio_device *mdiodev)
 {
-	static struct regmap_config *regmap_config;
 	struct mt7530_priv *priv;
 	struct device_node *dn;
 	int ret;
@@ -193,18 +200,8 @@ mt7530_probe(struct mdio_device *mdiodev)
 			return PTR_ERR(priv->io_pwr);
 	}
 
-	regmap_config = devm_kzalloc(&mdiodev->dev, sizeof(*regmap_config),
-				     GFP_KERNEL);
-	if (!regmap_config)
-		return -ENOMEM;
-
-	regmap_config->reg_bits = 16;
-	regmap_config->val_bits = 32;
-	regmap_config->reg_stride = 4;
-	regmap_config->max_register = MT7530_CREV;
-	regmap_config->disable_locking = true;
 	priv->regmap = devm_regmap_init(priv->dev, &mt7530_regmap_bus, priv,
-					regmap_config);
+					&regmap_config);
 	if (IS_ERR(priv->regmap))
 		return PTR_ERR(priv->regmap);
 
diff --git a/drivers/net/dsa/mt7530-mmio.c b/drivers/net/dsa/mt7530-mmio.c
index 5f2db4317dd3..1dc8b93fb51a 100644
--- a/drivers/net/dsa/mt7530-mmio.c
+++ b/drivers/net/dsa/mt7530-mmio.c
@@ -11,16 +11,24 @@
 #include "mt7530.h"
 
 static const struct of_device_id mt7988_of_match[] = {
+	{ .compatible = "airoha,an7583-switch", .data = &mt753x_table[ID_AN7583], },
 	{ .compatible = "airoha,en7581-switch", .data = &mt753x_table[ID_EN7581], },
 	{ .compatible = "mediatek,mt7988-switch", .data = &mt753x_table[ID_MT7988], },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, mt7988_of_match);
 
+static const struct regmap_config sw_regmap_config = {
+	.name = "switch",
+	.reg_bits = 16,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = MT7530_CREV,
+};
+
 static int
 mt7988_probe(struct platform_device *pdev)
 {
-	static struct regmap_config *sw_regmap_config;
 	struct mt7530_priv *priv;
 	void __iomem *base_addr;
 	int ret;
@@ -48,16 +56,8 @@ mt7988_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	sw_regmap_config = devm_kzalloc(&pdev->dev, sizeof(*sw_regmap_config), GFP_KERNEL);
-	if (!sw_regmap_config)
-		return -ENOMEM;
-
-	sw_regmap_config->name = "switch";
-	sw_regmap_config->reg_bits = 16;
-	sw_regmap_config->val_bits = 32;
-	sw_regmap_config->reg_stride = 4;
-	sw_regmap_config->max_register = MT7530_CREV;
-	priv->regmap = devm_regmap_init_mmio(&pdev->dev, base_addr, sw_regmap_config);
+	priv->regmap = devm_regmap_init_mmio(&pdev->dev, base_addr,
+					     &sw_regmap_config);
 	if (IS_ERR(priv->regmap))
 		return PTR_ERR(priv->regmap);
 
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 9605febd3573..b9423389c2ef 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -32,47 +32,15 @@ static struct mt753x_pcs *pcs_to_mt753x_pcs(struct phylink_pcs *pcs)
 
 /* String, offset, and register size in bytes if different from 4 bytes */
 static const struct mt7530_mib_desc mt7530_mib[] = {
-	MIB_DESC(1, 0x00, "TxDrop"),
-	MIB_DESC(1, 0x04, "TxCrcErr"),
-	MIB_DESC(1, 0x08, "TxUnicast"),
-	MIB_DESC(1, 0x0c, "TxMulticast"),
-	MIB_DESC(1, 0x10, "TxBroadcast"),
-	MIB_DESC(1, 0x14, "TxCollision"),
-	MIB_DESC(1, 0x18, "TxSingleCollision"),
-	MIB_DESC(1, 0x1c, "TxMultipleCollision"),
-	MIB_DESC(1, 0x20, "TxDeferred"),
-	MIB_DESC(1, 0x24, "TxLateCollision"),
-	MIB_DESC(1, 0x28, "TxExcessiveCollistion"),
-	MIB_DESC(1, 0x2c, "TxPause"),
-	MIB_DESC(1, 0x30, "TxPktSz64"),
-	MIB_DESC(1, 0x34, "TxPktSz65To127"),
-	MIB_DESC(1, 0x38, "TxPktSz128To255"),
-	MIB_DESC(1, 0x3c, "TxPktSz256To511"),
-	MIB_DESC(1, 0x40, "TxPktSz512To1023"),
-	MIB_DESC(1, 0x44, "Tx1024ToMax"),
-	MIB_DESC(2, 0x48, "TxBytes"),
-	MIB_DESC(1, 0x60, "RxDrop"),
-	MIB_DESC(1, 0x64, "RxFiltering"),
-	MIB_DESC(1, 0x68, "RxUnicast"),
-	MIB_DESC(1, 0x6c, "RxMulticast"),
-	MIB_DESC(1, 0x70, "RxBroadcast"),
-	MIB_DESC(1, 0x74, "RxAlignErr"),
-	MIB_DESC(1, 0x78, "RxCrcErr"),
-	MIB_DESC(1, 0x7c, "RxUnderSizeErr"),
-	MIB_DESC(1, 0x80, "RxFragErr"),
-	MIB_DESC(1, 0x84, "RxOverSzErr"),
-	MIB_DESC(1, 0x88, "RxJabberErr"),
-	MIB_DESC(1, 0x8c, "RxPause"),
-	MIB_DESC(1, 0x90, "RxPktSz64"),
-	MIB_DESC(1, 0x94, "RxPktSz65To127"),
-	MIB_DESC(1, 0x98, "RxPktSz128To255"),
-	MIB_DESC(1, 0x9c, "RxPktSz256To511"),
-	MIB_DESC(1, 0xa0, "RxPktSz512To1023"),
-	MIB_DESC(1, 0xa4, "RxPktSz1024ToMax"),
-	MIB_DESC(2, 0xa8, "RxBytes"),
-	MIB_DESC(1, 0xb0, "RxCtrlDrop"),
-	MIB_DESC(1, 0xb4, "RxIngressDrop"),
-	MIB_DESC(1, 0xb8, "RxArlDrop"),
+	MIB_DESC(1, MT7530_PORT_MIB_TX_DROP, "TxDrop"),
+	MIB_DESC(1, MT7530_PORT_MIB_TX_CRC_ERR, "TxCrcErr"),
+	MIB_DESC(1, MT7530_PORT_MIB_TX_COLLISION, "TxCollision"),
+	MIB_DESC(1, MT7530_PORT_MIB_RX_DROP, "RxDrop"),
+	MIB_DESC(1, MT7530_PORT_MIB_RX_FILTERING, "RxFiltering"),
+	MIB_DESC(1, MT7530_PORT_MIB_RX_CRC_ERR, "RxCrcErr"),
+	MIB_DESC(1, MT7530_PORT_MIB_RX_CTRL_DROP, "RxCtrlDrop"),
+	MIB_DESC(1, MT7530_PORT_MIB_RX_INGRESS_DROP, "RxIngressDrop"),
+	MIB_DESC(1, MT7530_PORT_MIB_RX_ARL_DROP, "RxArlDrop"),
 };
 
 static void
@@ -790,23 +758,33 @@ mt7530_get_strings(struct dsa_switch *ds, int port, u32 stringset,
 }
 
 static void
+mt7530_read_port_stats(struct mt7530_priv *priv, int port,
+		       u32 offset, u8 size, uint64_t *data)
+{
+	u32 val, reg = MT7530_PORT_MIB_COUNTER(port) + offset;
+
+	val = mt7530_read(priv, reg);
+	*data = val;
+
+	if (size == 2) {
+		val = mt7530_read(priv, reg + 4);
+		*data |= (u64)val << 32;
+	}
+}
+
+static void
 mt7530_get_ethtool_stats(struct dsa_switch *ds, int port,
 			 uint64_t *data)
 {
 	struct mt7530_priv *priv = ds->priv;
 	const struct mt7530_mib_desc *mib;
-	u32 reg, i;
-	u64 hi;
+	int i;
 
 	for (i = 0; i < ARRAY_SIZE(mt7530_mib); i++) {
 		mib = &mt7530_mib[i];
-		reg = MT7530_PORT_MIB_COUNTER(port) + mib->offset;
 
-		data[i] = mt7530_read(priv, reg);
-		if (mib->size == 2) {
-			hi = mt7530_read(priv, reg + 4);
-			data[i] |= hi << 32;
-		}
+		mt7530_read_port_stats(priv, port, mib->offset, mib->size,
+				       data + i);
 	}
 }
 
@@ -819,6 +797,172 @@ mt7530_get_sset_count(struct dsa_switch *ds, int port, int sset)
 	return ARRAY_SIZE(mt7530_mib);
 }
 
+static void mt7530_get_eth_mac_stats(struct dsa_switch *ds, int port,
+				     struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	/* MIB counter doesn't provide a FramesTransmittedOK but instead
+	 * provide stats for Unicast, Broadcast and Multicast frames separately.
+	 * To simulate a global frame counter, read Unicast and addition Multicast
+	 * and Broadcast later
+	 */
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_UNICAST, 1,
+			       &mac_stats->FramesTransmittedOK);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_SINGLE_COLLISION, 1,
+			       &mac_stats->SingleCollisionFrames);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_MULTIPLE_COLLISION, 1,
+			       &mac_stats->MultipleCollisionFrames);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_UNICAST, 1,
+			       &mac_stats->FramesReceivedOK);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_BYTES, 2,
+			       &mac_stats->OctetsTransmittedOK);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_ALIGN_ERR, 1,
+			       &mac_stats->AlignmentErrors);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_DEFERRED, 1,
+			       &mac_stats->FramesWithDeferredXmissions);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_LATE_COLLISION, 1,
+			       &mac_stats->LateCollisions);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_EXCESSIVE_COLLISION, 1,
+			       &mac_stats->FramesAbortedDueToXSColls);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_BYTES, 2,
+			       &mac_stats->OctetsReceivedOK);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_MULTICAST, 1,
+			       &mac_stats->MulticastFramesXmittedOK);
+	mac_stats->FramesTransmittedOK += mac_stats->MulticastFramesXmittedOK;
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_BROADCAST, 1,
+			       &mac_stats->BroadcastFramesXmittedOK);
+	mac_stats->FramesTransmittedOK += mac_stats->BroadcastFramesXmittedOK;
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_MULTICAST, 1,
+			       &mac_stats->MulticastFramesReceivedOK);
+	mac_stats->FramesReceivedOK += mac_stats->MulticastFramesReceivedOK;
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_BROADCAST, 1,
+			       &mac_stats->BroadcastFramesReceivedOK);
+	mac_stats->FramesReceivedOK += mac_stats->BroadcastFramesReceivedOK;
+}
+
+static const struct ethtool_rmon_hist_range mt7530_rmon_ranges[] = {
+	{ 0, 64 },
+	{ 65, 127 },
+	{ 128, 255 },
+	{ 256, 511 },
+	{ 512, 1023 },
+	{ 1024, MT7530_MAX_MTU },
+	{}
+};
+
+static void mt7530_get_rmon_stats(struct dsa_switch *ds, int port,
+				  struct ethtool_rmon_stats *rmon_stats,
+				  const struct ethtool_rmon_hist_range **ranges)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_UNDER_SIZE_ERR, 1,
+			       &rmon_stats->undersize_pkts);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_OVER_SZ_ERR, 1,
+			       &rmon_stats->oversize_pkts);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_FRAG_ERR, 1,
+			       &rmon_stats->fragments);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_JABBER_ERR, 1,
+			       &rmon_stats->jabbers);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PKT_SZ_64, 1,
+			       &rmon_stats->hist[0]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PKT_SZ_65_TO_127, 1,
+			       &rmon_stats->hist[1]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PKT_SZ_128_TO_255, 1,
+			       &rmon_stats->hist[2]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PKT_SZ_256_TO_511, 1,
+			       &rmon_stats->hist[3]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PKT_SZ_512_TO_1023, 1,
+			       &rmon_stats->hist[4]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PKT_SZ_1024_TO_MAX, 1,
+			       &rmon_stats->hist[5]);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PKT_SZ_64, 1,
+			       &rmon_stats->hist_tx[0]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PKT_SZ_65_TO_127, 1,
+			       &rmon_stats->hist_tx[1]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PKT_SZ_128_TO_255, 1,
+			       &rmon_stats->hist_tx[2]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PKT_SZ_256_TO_511, 1,
+			       &rmon_stats->hist_tx[3]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PKT_SZ_512_TO_1023, 1,
+			       &rmon_stats->hist_tx[4]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PKT_SZ_1024_TO_MAX, 1,
+			       &rmon_stats->hist_tx[5]);
+
+	*ranges = mt7530_rmon_ranges;
+}
+
+static void mt7530_get_stats64(struct dsa_switch *ds, int port,
+			       struct rtnl_link_stats64 *storage)
+{
+	struct mt7530_priv *priv = ds->priv;
+	uint64_t data;
+
+	/* MIB counter doesn't provide a FramesTransmittedOK but instead
+	 * provide stats for Unicast, Broadcast and Multicast frames separately.
+	 * To simulate a global frame counter, read Unicast and addition Multicast
+	 * and Broadcast later
+	 */
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_UNICAST, 1,
+			       &storage->rx_packets);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_MULTICAST, 1,
+			       &storage->multicast);
+	storage->rx_packets += storage->multicast;
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_BROADCAST, 1,
+			       &data);
+	storage->rx_packets += data;
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_UNICAST, 1,
+			       &storage->tx_packets);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_MULTICAST, 1,
+			       &data);
+	storage->tx_packets += data;
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_BROADCAST, 1,
+			       &data);
+	storage->tx_packets += data;
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_BYTES, 2,
+			       &storage->rx_bytes);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_BYTES, 2,
+			       &storage->tx_bytes);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_DROP, 1,
+			       &storage->rx_dropped);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_DROP, 1,
+			       &storage->tx_dropped);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_CRC_ERR, 1,
+			       &storage->rx_crc_errors);
+}
+
+static void mt7530_get_eth_ctrl_stats(struct dsa_switch *ds, int port,
+				      struct ethtool_eth_ctrl_stats *ctrl_stats)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PAUSE, 1,
+			       &ctrl_stats->MACControlFramesTransmitted);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PAUSE, 1,
+			       &ctrl_stats->MACControlFramesReceived);
+}
+
 static int
 mt7530_set_ageing_time(struct dsa_switch *ds, unsigned int msecs)
 {
@@ -1154,7 +1298,7 @@ mt753x_cpu_port_enable(struct dsa_switch *ds, int port)
 	 * is affine to the inbound user port.
 	 */
 	if (priv->id == ID_MT7531 || priv->id == ID_MT7988 ||
-	    priv->id == ID_EN7581)
+	    priv->id == ID_EN7581 || priv->id == ID_AN7583)
 		mt7530_set(priv, MT7531_CFC, MT7531_CPU_PMAP(BIT(port)));
 
 	/* CPU port gets connected to all user ports of
@@ -1968,7 +2112,7 @@ mt7530_gpio_get(struct gpio_chip *gc, unsigned int offset)
 	return !!(mt7530_read(priv, MT7530_LED_GPIO_DATA) & bit);
 }
 
-static void
+static int
 mt7530_gpio_set(struct gpio_chip *gc, unsigned int offset, int value)
 {
 	struct mt7530_priv *priv = gpiochip_get_data(gc);
@@ -1978,6 +2122,8 @@ mt7530_gpio_set(struct gpio_chip *gc, unsigned int offset, int value)
 		mt7530_set(priv, MT7530_LED_GPIO_DATA, bit);
 	else
 		mt7530_clear(priv, MT7530_LED_GPIO_DATA, bit);
+
+	return 0;
 }
 
 static int
@@ -2050,131 +2196,6 @@ mt7530_setup_gpio(struct mt7530_priv *priv)
 }
 #endif /* CONFIG_GPIOLIB */
 
-static irqreturn_t
-mt7530_irq_thread_fn(int irq, void *dev_id)
-{
-	struct mt7530_priv *priv = dev_id;
-	bool handled = false;
-	u32 val;
-	int p;
-
-	mt7530_mutex_lock(priv);
-	val = mt7530_mii_read(priv, MT7530_SYS_INT_STS);
-	mt7530_mii_write(priv, MT7530_SYS_INT_STS, val);
-	mt7530_mutex_unlock(priv);
-
-	for (p = 0; p < MT7530_NUM_PHYS; p++) {
-		if (BIT(p) & val) {
-			unsigned int irq;
-
-			irq = irq_find_mapping(priv->irq_domain, p);
-			handle_nested_irq(irq);
-			handled = true;
-		}
-	}
-
-	return IRQ_RETVAL(handled);
-}
-
-static void
-mt7530_irq_mask(struct irq_data *d)
-{
-	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
-
-	priv->irq_enable &= ~BIT(d->hwirq);
-}
-
-static void
-mt7530_irq_unmask(struct irq_data *d)
-{
-	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
-
-	priv->irq_enable |= BIT(d->hwirq);
-}
-
-static void
-mt7530_irq_bus_lock(struct irq_data *d)
-{
-	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
-
-	mt7530_mutex_lock(priv);
-}
-
-static void
-mt7530_irq_bus_sync_unlock(struct irq_data *d)
-{
-	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
-
-	mt7530_mii_write(priv, MT7530_SYS_INT_EN, priv->irq_enable);
-	mt7530_mutex_unlock(priv);
-}
-
-static struct irq_chip mt7530_irq_chip = {
-	.name = KBUILD_MODNAME,
-	.irq_mask = mt7530_irq_mask,
-	.irq_unmask = mt7530_irq_unmask,
-	.irq_bus_lock = mt7530_irq_bus_lock,
-	.irq_bus_sync_unlock = mt7530_irq_bus_sync_unlock,
-};
-
-static int
-mt7530_irq_map(struct irq_domain *domain, unsigned int irq,
-	       irq_hw_number_t hwirq)
-{
-	irq_set_chip_data(irq, domain->host_data);
-	irq_set_chip_and_handler(irq, &mt7530_irq_chip, handle_simple_irq);
-	irq_set_nested_thread(irq, true);
-	irq_set_noprobe(irq);
-
-	return 0;
-}
-
-static const struct irq_domain_ops mt7530_irq_domain_ops = {
-	.map = mt7530_irq_map,
-	.xlate = irq_domain_xlate_onecell,
-};
-
-static void
-mt7988_irq_mask(struct irq_data *d)
-{
-	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
-
-	priv->irq_enable &= ~BIT(d->hwirq);
-	mt7530_mii_write(priv, MT7530_SYS_INT_EN, priv->irq_enable);
-}
-
-static void
-mt7988_irq_unmask(struct irq_data *d)
-{
-	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
-
-	priv->irq_enable |= BIT(d->hwirq);
-	mt7530_mii_write(priv, MT7530_SYS_INT_EN, priv->irq_enable);
-}
-
-static struct irq_chip mt7988_irq_chip = {
-	.name = KBUILD_MODNAME,
-	.irq_mask = mt7988_irq_mask,
-	.irq_unmask = mt7988_irq_unmask,
-};
-
-static int
-mt7988_irq_map(struct irq_domain *domain, unsigned int irq,
-	       irq_hw_number_t hwirq)
-{
-	irq_set_chip_data(irq, domain->host_data);
-	irq_set_chip_and_handler(irq, &mt7988_irq_chip, handle_simple_irq);
-	irq_set_nested_thread(irq, true);
-	irq_set_noprobe(irq);
-
-	return 0;
-}
-
-static const struct irq_domain_ops mt7988_irq_domain_ops = {
-	.map = mt7988_irq_map,
-	.xlate = irq_domain_xlate_onecell,
-};
-
 static void
 mt7530_setup_mdio_irq(struct mt7530_priv *priv)
 {
@@ -2191,49 +2212,72 @@ mt7530_setup_mdio_irq(struct mt7530_priv *priv)
 	}
 }
 
+static const struct regmap_irq mt7530_irqs[] = {
+	REGMAP_IRQ_REG_LINE(0, 32),  /* PHY0_LC */
+	REGMAP_IRQ_REG_LINE(1, 32),  /* PHY1_LC */
+	REGMAP_IRQ_REG_LINE(2, 32),  /* PHY2_LC */
+	REGMAP_IRQ_REG_LINE(3, 32),  /* PHY3_LC */
+	REGMAP_IRQ_REG_LINE(4, 32),  /* PHY4_LC */
+	REGMAP_IRQ_REG_LINE(5, 32),  /* PHY5_LC */
+	REGMAP_IRQ_REG_LINE(6, 32),  /* PHY6_LC */
+	REGMAP_IRQ_REG_LINE(16, 32), /* MAC_PC */
+	REGMAP_IRQ_REG_LINE(17, 32), /* BMU */
+	REGMAP_IRQ_REG_LINE(18, 32), /* MIB */
+	REGMAP_IRQ_REG_LINE(22, 32), /* ARL_COL_FULL_COL */
+	REGMAP_IRQ_REG_LINE(23, 32), /* ARL_COL_FULL */
+	REGMAP_IRQ_REG_LINE(24, 32), /* ARL_TBL_ERR */
+	REGMAP_IRQ_REG_LINE(25, 32), /* ARL_PKT_QERR */
+	REGMAP_IRQ_REG_LINE(26, 32), /* ARL_EQ_ERR */
+	REGMAP_IRQ_REG_LINE(27, 32), /* ARL_PKT_BC */
+	REGMAP_IRQ_REG_LINE(28, 32), /* ARL_SEC_IG1X */
+	REGMAP_IRQ_REG_LINE(29, 32), /* ARL_SEC_VLAN */
+	REGMAP_IRQ_REG_LINE(30, 32), /* ARL_SEC_TAG */
+	REGMAP_IRQ_REG_LINE(31, 32), /* ACL */
+};
+
+static const struct regmap_irq_chip mt7530_regmap_irq_chip = {
+	.name = KBUILD_MODNAME,
+	.status_base = MT7530_SYS_INT_STS,
+	.unmask_base = MT7530_SYS_INT_EN,
+	.ack_base = MT7530_SYS_INT_STS,
+	.init_ack_masked = true,
+	.irqs = mt7530_irqs,
+	.num_irqs = ARRAY_SIZE(mt7530_irqs),
+	.num_regs = 1,
+};
+
 static int
 mt7530_setup_irq(struct mt7530_priv *priv)
 {
+	struct regmap_irq_chip_data *irq_data;
 	struct device *dev = priv->dev;
 	struct device_node *np = dev->of_node;
-	int ret;
+	int irq, ret;
 
 	if (!of_property_read_bool(np, "interrupt-controller")) {
 		dev_info(dev, "no interrupt support\n");
 		return 0;
 	}
 
-	priv->irq = of_irq_get(np, 0);
-	if (priv->irq <= 0) {
-		dev_err(dev, "failed to get parent IRQ: %d\n", priv->irq);
-		return priv->irq ? : -EINVAL;
-	}
-
-	if (priv->id == ID_MT7988 || priv->id == ID_EN7581)
-		priv->irq_domain = irq_domain_add_linear(np, MT7530_NUM_PHYS,
-							 &mt7988_irq_domain_ops,
-							 priv);
-	else
-		priv->irq_domain = irq_domain_add_linear(np, MT7530_NUM_PHYS,
-							 &mt7530_irq_domain_ops,
-							 priv);
-
-	if (!priv->irq_domain) {
-		dev_err(dev, "failed to create IRQ domain\n");
-		return -ENOMEM;
+	irq = of_irq_get(np, 0);
+	if (irq <= 0) {
+		dev_err(dev, "failed to get parent IRQ: %d\n", irq);
+		return irq ? : -EINVAL;
 	}
 
 	/* This register must be set for MT7530 to properly fire interrupts */
 	if (priv->id == ID_MT7530 || priv->id == ID_MT7621)
 		mt7530_set(priv, MT7530_TOP_SIG_CTRL, TOP_SIG_CTRL_NORMAL);
 
-	ret = request_threaded_irq(priv->irq, NULL, mt7530_irq_thread_fn,
-				   IRQF_ONESHOT, KBUILD_MODNAME, priv);
-	if (ret) {
-		irq_domain_remove(priv->irq_domain);
-		dev_err(dev, "failed to request IRQ: %d\n", ret);
+	ret = devm_regmap_add_irq_chip_fwnode(dev, dev_fwnode(dev),
+					      priv->regmap, irq,
+					      IRQF_ONESHOT,
+					      0, &mt7530_regmap_irq_chip,
+					      &irq_data);
+	if (ret)
 		return ret;
-	}
+
+	priv->irq_domain = regmap_irq_get_domain(irq_data);
 
 	return 0;
 }
@@ -2253,26 +2297,6 @@ mt7530_free_mdio_irq(struct mt7530_priv *priv)
 	}
 }
 
-static void
-mt7530_free_irq_common(struct mt7530_priv *priv)
-{
-	free_irq(priv->irq, priv);
-	irq_domain_remove(priv->irq_domain);
-}
-
-static void
-mt7530_free_irq(struct mt7530_priv *priv)
-{
-	struct device_node *mnp, *np = priv->dev->of_node;
-
-	mnp = of_get_child_by_name(np, "mdio");
-	if (!mnp)
-		mt7530_free_mdio_irq(priv);
-	of_node_put(mnp);
-
-	mt7530_free_irq_common(priv);
-}
-
 static int
 mt7530_setup_mdio(struct mt7530_priv *priv)
 {
@@ -2307,13 +2331,13 @@ mt7530_setup_mdio(struct mt7530_priv *priv)
 	bus->parent = dev;
 	bus->phy_mask = ~ds->phys_mii_mask;
 
-	if (priv->irq && !mnp)
+	if (priv->irq_domain && !mnp)
 		mt7530_setup_mdio_irq(priv);
 
 	ret = devm_of_mdiobus_register(dev, bus, mnp);
 	if (ret) {
 		dev_err(dev, "failed to register MDIO bus: %d\n", ret);
-		if (priv->irq && !mnp)
+		if (priv->irq_domain && !mnp)
 			mt7530_free_mdio_irq(priv);
 	}
 
@@ -2541,6 +2565,9 @@ mt7531_setup_common(struct dsa_switch *ds)
 	struct mt7530_priv *priv = ds->priv;
 	int ret, i;
 
+	ds->assisted_learning_on_cpu_port = true;
+	ds->mtu_enforcement_ingress = true;
+
 	mt753x_trap_frames(priv);
 
 	/* Enable and reset MIB counters */
@@ -2586,12 +2613,18 @@ mt7531_setup_common(struct dsa_switch *ds)
 	/* Allow mirroring frames received on the local port (monitor port). */
 	mt7530_set(priv, MT753X_AGC, LOCAL_EN);
 
+	/* Enable Special Tag for rx frames */
+	if (priv->id == ID_EN7581 || priv->id == ID_AN7583)
+		mt7530_write(priv, MT753X_CPORT_SPTAG_CFG,
+			     CPORT_SW2FE_STAG_EN | CPORT_FE2SW_STAG_EN);
+
 	/* Flush the FDB table */
 	ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, NULL);
 	if (ret < 0)
 		return ret;
 
-	return 0;
+	/* Setup VLAN ID 0 for VLAN-unaware bridges */
+	return mt7530_setup_vlan0(priv);
 }
 
 static int
@@ -2687,14 +2720,6 @@ mt7531_setup(struct dsa_switch *ds)
 	if (ret)
 		return ret;
 
-	/* Setup VLAN ID 0 for VLAN-unaware bridges */
-	ret = mt7530_setup_vlan0(priv);
-	if (ret)
-		return ret;
-
-	ds->assisted_learning_on_cpu_port = true;
-	ds->mtu_enforcement_ingress = true;
-
 	return 0;
 }
 
@@ -2957,28 +2982,61 @@ static void mt753x_phylink_mac_link_up(struct phylink_config *config,
 			mcr |= PMCR_FORCE_RX_FC_EN;
 	}
 
-	if (mode == MLO_AN_PHY && phydev && phy_init_eee(phydev, false) >= 0) {
-		switch (speed) {
-		case SPEED_1000:
-		case SPEED_2500:
-			mcr |= PMCR_FORCE_EEE1G;
-			break;
-		case SPEED_100:
-			mcr |= PMCR_FORCE_EEE100;
-			break;
-		}
-	}
-
 	mt7530_set(priv, MT753X_PMCR_P(dp->index), mcr);
 }
 
+static void mt753x_phylink_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct mt7530_priv *priv = dp->ds->priv;
+
+	mt7530_clear(priv, MT753X_PMCR_P(dp->index),
+		     PMCR_FORCE_EEE1G | PMCR_FORCE_EEE100);
+}
+
+static int mt753x_phylink_mac_enable_tx_lpi(struct phylink_config *config,
+					    u32 timer, bool tx_clock_stop)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct mt7530_priv *priv = dp->ds->priv;
+	u32 val;
+
+	/* If the timer is zero, then set LPI_MODE_EN, which allows the
+	 * system to enter LPI mode immediately rather than waiting for
+	 * the LPI threshold.
+	 */
+	if (!timer)
+		val = LPI_MODE_EN;
+	else if (FIELD_FIT(LPI_THRESH_MASK, timer))
+		val = FIELD_PREP(LPI_THRESH_MASK, timer);
+	else
+		val = LPI_THRESH_MASK;
+
+	mt7530_rmw(priv, MT753X_PMEEECR_P(dp->index),
+		   LPI_THRESH_MASK | LPI_MODE_EN, val);
+
+	mt7530_set(priv, MT753X_PMCR_P(dp->index),
+		   PMCR_FORCE_EEE1G | PMCR_FORCE_EEE100);
+
+	return 0;
+}
+
 static void mt753x_phylink_get_caps(struct dsa_switch *ds, int port,
 				    struct phylink_config *config)
 {
 	struct mt7530_priv *priv = ds->priv;
+	u32 eeecr;
 
 	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE;
 
+	config->lpi_capabilities = MAC_100FD | MAC_1000FD | MAC_2500FD;
+
+	eeecr = mt7530_read(priv, MT753X_PMEEECR_P(port));
+	/* tx_lpi_timer should be in microseconds. The time units for
+	 * LPI threshold are unspecified.
+	 */
+	config->lpi_timer_default = FIELD_GET(LPI_THRESH_MASK, eeecr);
+
 	priv->info->mac_port_get_caps(ds, port, config);
 }
 
@@ -2994,7 +3052,7 @@ static int mt753x_pcs_validate(struct phylink_pcs *pcs,
 	return 0;
 }
 
-static void mt7530_pcs_get_state(struct phylink_pcs *pcs,
+static void mt7530_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode,
 				 struct phylink_link_state *state)
 {
 	struct mt7530_priv *priv = pcs_to_mt753x_pcs(pcs)->priv;
@@ -3063,55 +3121,31 @@ mt753x_setup(struct dsa_switch *ds)
 		return ret;
 
 	ret = mt7530_setup_mdio(priv);
-	if (ret && priv->irq)
-		mt7530_free_irq_common(priv);
 	if (ret)
 		return ret;
 
 	/* Initialise the PCS devices */
 	for (i = 0; i < priv->ds->num_ports; i++) {
 		priv->pcs[i].pcs.ops = priv->info->pcs_ops;
-		priv->pcs[i].pcs.neg_mode = true;
 		priv->pcs[i].priv = priv;
 		priv->pcs[i].port = i;
 	}
 
-	if (priv->create_sgmii) {
+	if (priv->create_sgmii)
 		ret = priv->create_sgmii(priv);
-		if (ret && priv->irq)
-			mt7530_free_irq(priv);
-	}
-
-	return ret;
-}
 
-static int mt753x_get_mac_eee(struct dsa_switch *ds, int port,
-			      struct ethtool_keee *e)
-{
-	struct mt7530_priv *priv = ds->priv;
-	u32 eeecr = mt7530_read(priv, MT753X_PMEEECR_P(port));
-
-	e->tx_lpi_enabled = !(eeecr & LPI_MODE_EN);
-	e->tx_lpi_timer = LPI_THRESH_GET(eeecr);
+	if (ret && priv->irq_domain)
+		mt7530_free_mdio_irq(priv);
 
-	return 0;
+	return ret;
 }
 
 static int mt753x_set_mac_eee(struct dsa_switch *ds, int port,
 			      struct ethtool_keee *e)
 {
-	struct mt7530_priv *priv = ds->priv;
-	u32 set, mask = LPI_THRESH_MASK | LPI_MODE_EN;
-
 	if (e->tx_lpi_timer > 0xFFF)
 		return -EINVAL;
 
-	set = LPI_THRESH_SET(e->tx_lpi_timer);
-	if (!e->tx_lpi_enabled)
-		/* Force LPI Mode without a delay */
-		set |= LPI_MODE_EN;
-	mt7530_rmw(priv, MT753X_PMEEECR_P(port), mask, set);
-
 	return 0;
 }
 
@@ -3204,19 +3238,33 @@ static int mt7988_setup(struct dsa_switch *ds)
 	reset_control_deassert(priv->rstc);
 	usleep_range(20, 50);
 
+	/* AN7583 require additional tweak to CONN_CFG */
+	if (priv->id == ID_AN7583)
+		mt7530_rmw(priv, AN7583_GEPHY_CONN_CFG,
+			   AN7583_CSR_DPHY_CKIN_SEL |
+			   AN7583_CSR_PHY_CORE_REG_CLK_SEL |
+			   AN7583_CSR_ETHER_AFE_PWD,
+			   AN7583_CSR_DPHY_CKIN_SEL |
+			   AN7583_CSR_PHY_CORE_REG_CLK_SEL |
+			   FIELD_PREP(AN7583_CSR_ETHER_AFE_PWD, 0));
+
 	/* Reset the switch PHYs */
 	mt7530_write(priv, MT7530_SYS_CTRL, SYS_CTRL_PHY_RST);
 
 	return mt7531_setup_common(ds);
 }
 
-const struct dsa_switch_ops mt7530_switch_ops = {
+static const struct dsa_switch_ops mt7530_switch_ops = {
 	.get_tag_protocol	= mtk_get_tag_protocol,
 	.setup			= mt753x_setup,
 	.preferred_default_local_cpu_port = mt753x_preferred_default_local_cpu_port,
 	.get_strings		= mt7530_get_strings,
 	.get_ethtool_stats	= mt7530_get_ethtool_stats,
 	.get_sset_count		= mt7530_get_sset_count,
+	.get_eth_mac_stats	= mt7530_get_eth_mac_stats,
+	.get_rmon_stats		= mt7530_get_rmon_stats,
+	.get_eth_ctrl_stats	= mt7530_get_eth_ctrl_stats,
+	.get_stats64		= mt7530_get_stats64,
 	.set_ageing_time	= mt7530_set_ageing_time,
 	.port_enable		= mt7530_port_enable,
 	.port_disable		= mt7530_port_disable,
@@ -3239,18 +3287,20 @@ const struct dsa_switch_ops mt7530_switch_ops = {
 	.port_mirror_del	= mt753x_port_mirror_del,
 	.phylink_get_caps	= mt753x_phylink_get_caps,
 	.support_eee		= dsa_supports_eee,
-	.get_mac_eee		= mt753x_get_mac_eee,
 	.set_mac_eee		= mt753x_set_mac_eee,
 	.conduit_state_change	= mt753x_conduit_state_change,
 	.port_setup_tc		= mt753x_setup_tc,
+	.port_hsr_join		= dsa_port_simple_hsr_join,
+	.port_hsr_leave		= dsa_port_simple_hsr_leave,
 };
-EXPORT_SYMBOL_GPL(mt7530_switch_ops);
 
 static const struct phylink_mac_ops mt753x_phylink_mac_ops = {
 	.mac_select_pcs	= mt753x_phylink_mac_select_pcs,
 	.mac_config	= mt753x_phylink_mac_config,
 	.mac_link_down	= mt753x_phylink_mac_link_down,
 	.mac_link_up	= mt753x_phylink_mac_link_up,
+	.mac_disable_tx_lpi = mt753x_phylink_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = mt753x_phylink_mac_enable_tx_lpi,
 };
 
 const struct mt753x_info mt753x_table[] = {
@@ -3307,6 +3357,16 @@ const struct mt753x_info mt753x_table[] = {
 		.phy_write_c45 = mt7531_ind_c45_phy_write,
 		.mac_port_get_caps = en7581_mac_port_get_caps,
 	},
+	[ID_AN7583] = {
+		.id = ID_AN7583,
+		.pcs_ops = &mt7530_pcs_ops,
+		.sw_setup = mt7988_setup,
+		.phy_read_c22 = mt7531_ind_c22_phy_read,
+		.phy_write_c22 = mt7531_ind_c22_phy_write,
+		.phy_read_c45 = mt7531_ind_c45_phy_read,
+		.phy_write_c45 = mt7531_ind_c45_phy_write,
+		.mac_port_get_caps = en7581_mac_port_get_caps,
+	},
 };
 EXPORT_SYMBOL_GPL(mt753x_table);
 
@@ -3344,8 +3404,8 @@ EXPORT_SYMBOL_GPL(mt7530_probe_common);
 void
 mt7530_remove_common(struct mt7530_priv *priv)
 {
-	if (priv->irq)
-		mt7530_free_irq(priv);
+	if (priv->irq_domain)
+		mt7530_free_mdio_irq(priv);
 
 	dsa_unregister_switch(priv->ds);
 
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index 448200689f49..3e0090bed298 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -20,6 +20,7 @@ enum mt753x_id {
 	ID_MT7531 = 2,
 	ID_MT7988 = 3,
 	ID_EN7581 = 4,
+	ID_AN7583 = 5,
 };
 
 #define	NUM_TRGMII_CTRL			5
@@ -66,7 +67,8 @@ enum mt753x_id {
 
 #define MT753X_MIRROR_REG(id)		((id == ID_MT7531 || \
 					  id == ID_MT7988 || \
-					  id == ID_EN7581) ? \
+					  id == ID_EN7581 || \
+					  id == ID_AN7583) ? \
 					 MT7531_CFC : MT753X_MFC)
 
 #define MT753X_MIRROR_EN(id)		((id == ID_MT7531 || \
@@ -76,19 +78,22 @@ enum mt753x_id {
 
 #define MT753X_MIRROR_PORT_MASK(id)	((id == ID_MT7531 || \
 					  id == ID_MT7988 || \
-					  id == ID_EN7581) ? \
+					  id == ID_EN7581 || \
+					  id == ID_AN7583) ? \
 					 MT7531_MIRROR_PORT_MASK : \
 					 MT7530_MIRROR_PORT_MASK)
 
 #define MT753X_MIRROR_PORT_GET(id, val)	((id == ID_MT7531 || \
 					  id == ID_MT7988 || \
-					  id == ID_EN7581) ? \
+					  id == ID_EN7581 || \
+					  id == ID_AN7583) ? \
 					 MT7531_MIRROR_PORT_GET(val) : \
 					 MT7530_MIRROR_PORT_GET(val))
 
 #define MT753X_MIRROR_PORT_SET(id, val)	((id == ID_MT7531 || \
 					  id == ID_MT7988 || \
-					  id == ID_EN7581) ? \
+					  id == ID_EN7581 || \
+					  id == ID_AN7583) ? \
 					 MT7531_MIRROR_PORT_SET(val) : \
 					 MT7530_MIRROR_PORT_SET(val))
 
@@ -423,6 +428,48 @@ enum mt7530_vlan_port_acc_frm {
 
 /* Register for MIB */
 #define MT7530_PORT_MIB_COUNTER(x)	(0x4000 + (x) * 0x100)
+/* Each define is an offset of MT7530_PORT_MIB_COUNTER */
+#define   MT7530_PORT_MIB_TX_DROP	0x00
+#define   MT7530_PORT_MIB_TX_CRC_ERR	0x04
+#define   MT7530_PORT_MIB_TX_UNICAST	0x08
+#define   MT7530_PORT_MIB_TX_MULTICAST	0x0c
+#define   MT7530_PORT_MIB_TX_BROADCAST	0x10
+#define   MT7530_PORT_MIB_TX_COLLISION	0x14
+#define   MT7530_PORT_MIB_TX_SINGLE_COLLISION 0x18
+#define   MT7530_PORT_MIB_TX_MULTIPLE_COLLISION 0x1c
+#define   MT7530_PORT_MIB_TX_DEFERRED	0x20
+#define   MT7530_PORT_MIB_TX_LATE_COLLISION 0x24
+#define   MT7530_PORT_MIB_TX_EXCESSIVE_COLLISION 0x28
+#define   MT7530_PORT_MIB_TX_PAUSE	0x2c
+#define   MT7530_PORT_MIB_TX_PKT_SZ_64	0x30
+#define   MT7530_PORT_MIB_TX_PKT_SZ_65_TO_127 0x34
+#define   MT7530_PORT_MIB_TX_PKT_SZ_128_TO_255 0x38
+#define   MT7530_PORT_MIB_TX_PKT_SZ_256_TO_511 0x3c
+#define   MT7530_PORT_MIB_TX_PKT_SZ_512_TO_1023 0x40
+#define   MT7530_PORT_MIB_TX_PKT_SZ_1024_TO_MAX 0x44
+#define   MT7530_PORT_MIB_TX_BYTES	0x48 /* 64 bytes */
+#define   MT7530_PORT_MIB_RX_DROP	0x60
+#define   MT7530_PORT_MIB_RX_FILTERING	0x64
+#define   MT7530_PORT_MIB_RX_UNICAST	0x68
+#define   MT7530_PORT_MIB_RX_MULTICAST	0x6c
+#define   MT7530_PORT_MIB_RX_BROADCAST	0x70
+#define   MT7530_PORT_MIB_RX_ALIGN_ERR	0x74
+#define   MT7530_PORT_MIB_RX_CRC_ERR	0x78
+#define   MT7530_PORT_MIB_RX_UNDER_SIZE_ERR 0x7c
+#define   MT7530_PORT_MIB_RX_FRAG_ERR	0x80
+#define   MT7530_PORT_MIB_RX_OVER_SZ_ERR 0x84
+#define   MT7530_PORT_MIB_RX_JABBER_ERR	0x88
+#define   MT7530_PORT_MIB_RX_PAUSE	0x8c
+#define   MT7530_PORT_MIB_RX_PKT_SZ_64	0x90
+#define   MT7530_PORT_MIB_RX_PKT_SZ_65_TO_127 0x94
+#define   MT7530_PORT_MIB_RX_PKT_SZ_128_TO_255 0x98
+#define   MT7530_PORT_MIB_RX_PKT_SZ_256_TO_511 0x9c
+#define   MT7530_PORT_MIB_RX_PKT_SZ_512_TO_1023 0xa0
+#define   MT7530_PORT_MIB_RX_PKT_SZ_1024_TO_MAX 0xa4
+#define   MT7530_PORT_MIB_RX_BYTES	0xa8 /* 64 bytes */
+#define   MT7530_PORT_MIB_RX_CTRL_DROP	0xb0
+#define   MT7530_PORT_MIB_RX_INGRESS_DROP 0xb4
+#define   MT7530_PORT_MIB_RX_ARL_DROP	0xb8
 #define MT7530_MIB_CCR			0x4fe0
 #define  CCR_MIB_ENABLE			BIT(31)
 #define  CCR_RX_OCT_CNT_GOOD		BIT(7)
@@ -627,6 +674,15 @@ enum mt7531_xtal_fsel {
 #define  MT7531_GPIO12_RG_RXD3_MASK	GENMASK(19, 16)
 #define  MT7531_EXT_P_MDIO_12		(2 << 16)
 
+#define MT753X_CPORT_SPTAG_CFG		0x7c10
+#define  CPORT_SW2FE_STAG_EN		BIT(1)
+#define  CPORT_FE2SW_STAG_EN		BIT(0)
+
+#define AN7583_GEPHY_CONN_CFG		0x7c14
+#define  AN7583_CSR_DPHY_CKIN_SEL	BIT(31)
+#define  AN7583_CSR_PHY_CORE_REG_CLK_SEL BIT(30)
+#define  AN7583_CSR_ETHER_AFE_PWD	GENMASK(28, 24)
+
 /* Registers for LED GPIO control (MT7530 only)
  * All registers follow this pattern:
  * [ 2: 0]  port 0
@@ -815,9 +871,7 @@ struct mt753x_info {
  * @p5_mode:		Holding the current mode of port 5 of the MT7530 switch
  * @p5_sgmii:		Flag for distinguishing if port 5 of the MT7531 switch
  *			has got SGMII
- * @irq:		IRQ number of the switch
  * @irq_domain:		IRQ domain of the switch irq_chip
- * @irq_enable:		IRQ enable bits, synced to SYS_INT_EN
  * @create_sgmii:	Pointer to function creating SGMII PCS instance(s)
  * @active_cpu_ports:	Holding the active CPU ports
  * @mdiodev:		The pointer to the MDIO device structure
@@ -842,9 +896,7 @@ struct mt7530_priv {
 	struct mt753x_pcs	pcs[MT7530_NUM_PORTS];
 	/* protect among processes for registers access*/
 	struct mutex reg_mutex;
-	int irq;
 	struct irq_domain *irq_domain;
-	u32 irq_enable;
 	int (*create_sgmii)(struct mt7530_priv *priv);
 	u8 active_cpu_ports;
 	struct mdio_device *mdiodev;
@@ -887,7 +939,6 @@ static inline void INIT_MT7530_DUMMY_POLL(struct mt7530_dummy_poll *p,
 int mt7530_probe_common(struct mt7530_priv *priv);
 void mt7530_remove_common(struct mt7530_priv *priv);
 
-extern const struct dsa_switch_ops mt7530_switch_ops;
 extern const struct mt753x_info mt753x_table[];
 
 #endif /* __MT7530_H */
diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c
index 294312b58e4f..9c8ac14cd4f5 100644
--- a/drivers/net/dsa/mv88e6060.c
+++ b/drivers/net/dsa/mv88e6060.c
@@ -297,6 +297,8 @@ static const struct dsa_switch_ops mv88e6060_switch_ops = {
 	.phy_read	= mv88e6060_phy_read,
 	.phy_write	= mv88e6060_phy_write,
 	.phylink_get_caps = mv88e6060_phylink_get_caps,
+	.port_hsr_join	= dsa_port_simple_hsr_join,
+	.port_hsr_leave	= dsa_port_simple_hsr_leave,
 };
 
 static int mv88e6060_probe(struct mdio_device *mdiodev)
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 570c8642d387..b4d48997bf46 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -297,7 +297,7 @@ static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip)
 	u16 reg, mask;
 
 	chip->g1_irq.nirqs = chip->info->g1_irqs;
-	chip->g1_irq.domain = irq_domain_add_simple(
+	chip->g1_irq.domain = irq_domain_create_simple(
 		NULL, chip->g1_irq.nirqs, 0,
 		&mv88e6xxx_g1_irq_domain_ops, chip);
 	if (!chip->g1_irq.domain)
@@ -394,7 +394,7 @@ static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip)
 	kthread_init_delayed_work(&chip->irq_poll_work,
 				  mv88e6xxx_irq_poll);
 
-	chip->kworker = kthread_create_worker(0, "%s", dev_name(chip->dev));
+	chip->kworker = kthread_run_worker(0, "%s", dev_name(chip->dev));
 	if (IS_ERR(chip->kworker))
 		return PTR_ERR(chip->kworker);
 
@@ -1513,13 +1513,6 @@ static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port,
 	mv88e6xxx_reg_unlock(chip);
 }
 
-static int mv88e6xxx_get_mac_eee(struct dsa_switch *ds, int port,
-				 struct ethtool_keee *e)
-{
-	/* Nothing to do on the port's MAC */
-	return 0;
-}
-
 static int mv88e6xxx_set_mac_eee(struct dsa_switch *ds, int port,
 				 struct ethtool_keee *e)
 {
@@ -1859,6 +1852,8 @@ static int mv88e6xxx_vtu_get(struct mv88e6xxx_chip *chip, u16 vid,
 	if (!chip->info->ops->vtu_getnext)
 		return -EOPNOTSUPP;
 
+	memset(entry, 0, sizeof(*entry));
+
 	entry->vid = vid ? vid - 1 : mv88e6xxx_max_vid(chip);
 	entry->valid = false;
 
@@ -1967,7 +1962,16 @@ static int mv88e6xxx_mst_put(struct mv88e6xxx_chip *chip, u8 sid)
 	struct mv88e6xxx_mst *mst, *tmp;
 	int err;
 
-	if (!sid)
+	/* If the SID is zero, it is for a VLAN mapped to the default MSTI,
+	 * and mv88e6xxx_stu_setup() made sure it is always present, and thus,
+	 * should not be removed here.
+	 *
+	 * If the chip lacks STU support, numerically the "sid" variable will
+	 * happen to also be zero, but we don't want to rely on that fact, so
+	 * we explicitly test that first. In that case, there is also nothing
+	 * to do here.
+	 */
+	if (!mv88e6xxx_has_stu(chip) || !sid)
 		return 0;
 
 	list_for_each_entry_safe(mst, tmp, &chip->msts, node) {
@@ -2215,13 +2219,11 @@ mv88e6xxx_port_vlan_prepare(struct dsa_switch *ds, int port,
 	return err;
 }
 
-static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
-					const unsigned char *addr, u16 vid,
-					u8 state)
+static int mv88e6xxx_port_db_get(struct mv88e6xxx_chip *chip,
+				 const unsigned char *addr, u16 vid,
+				 u16 *fid, struct mv88e6xxx_atu_entry *entry)
 {
-	struct mv88e6xxx_atu_entry entry;
 	struct mv88e6xxx_vtu_entry vlan;
-	u16 fid;
 	int err;
 
 	/* Ports have two private address databases: one for when the port is
@@ -2232,7 +2234,7 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
 	 * VLAN ID into the port's database used for VLAN-unaware bridging.
 	 */
 	if (vid == 0) {
-		fid = MV88E6XXX_FID_BRIDGED;
+		*fid = MV88E6XXX_FID_BRIDGED;
 	} else {
 		err = mv88e6xxx_vtu_get(chip, vid, &vlan);
 		if (err)
@@ -2242,14 +2244,39 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
 		if (!vlan.valid)
 			return -EOPNOTSUPP;
 
-		fid = vlan.fid;
+		*fid = vlan.fid;
 	}
 
-	entry.state = 0;
-	ether_addr_copy(entry.mac, addr);
-	eth_addr_dec(entry.mac);
+	entry->state = 0;
+	ether_addr_copy(entry->mac, addr);
+	eth_addr_dec(entry->mac);
+
+	return mv88e6xxx_g1_atu_getnext(chip, *fid, entry);
+}
+
+static bool mv88e6xxx_port_db_find(struct mv88e6xxx_chip *chip,
+				   const unsigned char *addr, u16 vid)
+{
+	struct mv88e6xxx_atu_entry entry;
+	u16 fid;
+	int err;
+
+	err = mv88e6xxx_port_db_get(chip, addr, vid, &fid, &entry);
+	if (err)
+		return false;
+
+	return entry.state && ether_addr_equal(entry.mac, addr);
+}
+
+static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
+					const unsigned char *addr, u16 vid,
+					u8 state)
+{
+	struct mv88e6xxx_atu_entry entry;
+	u16 fid;
+	int err;
 
-	err = mv88e6xxx_g1_atu_getnext(chip, fid, &entry);
+	err = mv88e6xxx_port_db_get(chip, addr, vid, &fid, &entry);
 	if (err)
 		return err;
 
@@ -2853,6 +2880,13 @@ static int mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port,
 	mv88e6xxx_reg_lock(chip);
 	err = mv88e6xxx_port_db_load_purge(chip, port, addr, vid,
 					   MV88E6XXX_G1_ATU_DATA_STATE_UC_STATIC);
+	if (err)
+		goto out;
+
+	if (!mv88e6xxx_port_db_find(chip, addr, vid))
+		err = -ENOSPC;
+
+out:
 	mv88e6xxx_reg_unlock(chip);
 
 	return err;
@@ -3651,6 +3685,21 @@ static int mv88e6xxx_stats_setup(struct mv88e6xxx_chip *chip)
 	return mv88e6xxx_g1_stats_clear(chip);
 }
 
+static int mv88e6320_setup_errata(struct mv88e6xxx_chip *chip)
+{
+	u16 dummy;
+	int err;
+
+	/* Workaround for erratum
+	 *   3.3 RGMII timing may be out of spec when transmit delay is enabled
+	 */
+	err = mv88e6xxx_port_hidden_write(chip, 0, 0xf, 0x7, 0xe000);
+	if (err)
+		return err;
+
+	return mv88e6xxx_port_hidden_read(chip, 0, 0xf, 0x7, &dummy);
+}
+
 /* Check if the errata has already been applied. */
 static bool mv88e6390_setup_errata_applied(struct mv88e6xxx_chip *chip)
 {
@@ -3916,6 +3965,8 @@ static void mv88e6xxx_teardown(struct dsa_switch *ds)
 	mv88e6xxx_teardown_devlink_params(ds);
 	dsa_devlink_resources_unregister(ds);
 	mv88e6xxx_teardown_devlink_regions_global(ds);
+	mv88e6xxx_hwtstamp_free(chip);
+	mv88e6xxx_ptp_free(chip);
 	mv88e6xxx_mdios_unregister(chip);
 }
 
@@ -4056,7 +4107,7 @@ unlock:
 	mv88e6xxx_reg_unlock(chip);
 
 	if (err)
-		goto out_mdios;
+		goto out_hwtstamp;
 
 	/* Have to be called without holding the register lock, since
 	 * they take the devlink lock, and we later take the locks in
@@ -4065,7 +4116,7 @@ unlock:
 	 */
 	err = mv88e6xxx_setup_devlink_resources(ds);
 	if (err)
-		goto out_mdios;
+		goto out_hwtstamp;
 
 	err = mv88e6xxx_setup_devlink_params(ds);
 	if (err)
@@ -4081,7 +4132,9 @@ out_params:
 	mv88e6xxx_teardown_devlink_params(ds);
 out_resources:
 	dsa_devlink_resources_unregister(ds);
-out_mdios:
+out_hwtstamp:
+	mv88e6xxx_hwtstamp_free(chip);
+	mv88e6xxx_ptp_free(chip);
 	mv88e6xxx_mdios_unregister(chip);
 
 	return err;
@@ -5039,7 +5092,7 @@ static const struct mv88e6xxx_ops mv88e6250_ops = {
 	.vtu_getnext = mv88e6185_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
 	.avb_ops = &mv88e6352_avb_ops,
-	.ptp_ops = &mv88e6250_ptp_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
 	.phylink_get_caps = mv88e6250_phylink_get_caps,
 	.set_max_frame_size = mv88e6185_g1_set_max_frame_size,
 };
@@ -5107,6 +5160,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 
 static const struct mv88e6xxx_ops mv88e6320_ops = {
 	/* MV88E6XXX_FAMILY_6320 */
+	.setup_errata = mv88e6320_setup_errata,
 	.ieee_pri_map = mv88e6085_g1_ieee_pri_map,
 	.ip_pri_map = mv88e6085_g1_ip_pri_map,
 	.irl_init_all = mv88e6352_g2_irl_init_all,
@@ -5122,6 +5176,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.port_set_rgmii_delay = mv88e6320_port_set_rgmii_delay,
 	.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
 	.port_tag_remap = mv88e6095_port_tag_remap,
+	.port_set_policy = mv88e6352_port_set_policy,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_ucast_flood = mv88e6352_port_set_ucast_flood,
 	.port_set_mcast_flood = mv88e6352_port_set_mcast_flood,
@@ -5146,8 +5201,10 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.hardware_reset_pre = mv88e6xxx_g2_eeprom_wait,
 	.hardware_reset_post = mv88e6xxx_g2_eeprom_wait,
 	.reset = mv88e6352_g1_reset,
-	.vtu_getnext = mv88e6185_g1_vtu_getnext,
-	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.stu_getnext = mv88e6352_g1_stu_getnext,
+	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
@@ -5156,6 +5213,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 
 static const struct mv88e6xxx_ops mv88e6321_ops = {
 	/* MV88E6XXX_FAMILY_6320 */
+	.setup_errata = mv88e6320_setup_errata,
 	.ieee_pri_map = mv88e6085_g1_ieee_pri_map,
 	.ip_pri_map = mv88e6085_g1_ip_pri_map,
 	.irl_init_all = mv88e6352_g2_irl_init_all,
@@ -5171,6 +5229,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.port_set_rgmii_delay = mv88e6320_port_set_rgmii_delay,
 	.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
 	.port_tag_remap = mv88e6095_port_tag_remap,
+	.port_set_policy = mv88e6352_port_set_policy,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_ucast_flood = mv88e6352_port_set_ucast_flood,
 	.port_set_mcast_flood = mv88e6352_port_set_mcast_flood,
@@ -5194,8 +5253,10 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.hardware_reset_pre = mv88e6xxx_g2_eeprom_wait,
 	.hardware_reset_post = mv88e6xxx_g2_eeprom_wait,
 	.reset = mv88e6352_g1_reset,
-	.vtu_getnext = mv88e6185_g1_vtu_getnext,
-	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.stu_getnext = mv88e6352_g1_stu_getnext,
+	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
@@ -5795,7 +5856,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 3750,
-		.atu_move_port_mask = 0x1f,
+		.atu_move_port_mask = 0xf,
 		.g1_irqs = 9,
 		.g2_irqs = 10,
 		.stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1,
@@ -6213,9 +6274,11 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_databases = 4096,
 		.num_macs = 8192,
 		.num_ports = 7,
-		.num_internal_phys = 5,
+		.num_internal_phys = 2,
+		.internal_phys_offset = 3,
 		.num_gpio = 15,
 		.max_vid = 4095,
+		.max_sid = 63,
 		.port_base_addr = 0x10,
 		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
@@ -6239,9 +6302,11 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_databases = 4096,
 		.num_macs = 8192,
 		.num_ports = 7,
-		.num_internal_phys = 5,
+		.num_internal_phys = 2,
+		.internal_phys_offset = 3,
 		.num_gpio = 15,
 		.max_vid = 4095,
+		.max_sid = 63,
 		.port_base_addr = 0x10,
 		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
@@ -6251,6 +6316,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.g2_irqs = 10,
 		.stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1,
 		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.multi_chip = true,
 		.edsa_support = MV88E6XXX_EDSA_SUPPORTED,
 		.ptp_support = true,
@@ -6273,7 +6339,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 3750,
-		.atu_move_port_mask = 0x1f,
+		.atu_move_port_mask = 0xf,
 		.g1_irqs = 9,
 		.g2_irqs = 10,
 		.stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1,
@@ -6621,6 +6687,13 @@ static int mv88e6xxx_port_mdb_add(struct dsa_switch *ds, int port,
 	mv88e6xxx_reg_lock(chip);
 	err = mv88e6xxx_port_db_load_purge(chip, port, mdb->addr, mdb->vid,
 					   MV88E6XXX_G1_ATU_DATA_STATE_MC_STATIC);
+	if (err)
+		goto out;
+
+	if (!mv88e6xxx_port_db_find(chip, mdb->addr, mdb->vid))
+		err = -ENOSPC;
+
+out:
 	mv88e6xxx_reg_unlock(chip);
 
 	return err;
@@ -7100,7 +7173,6 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = {
 	.port_max_mtu		= mv88e6xxx_get_max_mtu,
 	.port_change_mtu	= mv88e6xxx_change_mtu,
 	.support_eee		= dsa_supports_eee,
-	.get_mac_eee		= mv88e6xxx_get_mac_eee,
 	.set_mac_eee		= mv88e6xxx_set_mac_eee,
 	.get_eeprom_len		= mv88e6xxx_get_eeprom_len,
 	.get_eeprom		= mv88e6xxx_get_eeprom,
@@ -7293,13 +7365,13 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 	err = mv88e6xxx_switch_reset(chip);
 	mv88e6xxx_reg_unlock(chip);
 	if (err)
-		goto out;
+		goto out_phy;
 
 	if (np) {
 		chip->irq = of_irq_get(np, 0);
 		if (chip->irq == -EPROBE_DEFER) {
 			err = chip->irq;
-			goto out;
+			goto out_phy;
 		}
 	}
 
@@ -7318,7 +7390,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 	mv88e6xxx_reg_unlock(chip);
 
 	if (err)
-		goto out;
+		goto out_phy;
 
 	if (chip->info->g2_irqs > 0) {
 		err = mv88e6xxx_g2_irq_setup(chip);
@@ -7352,6 +7424,8 @@ out_g1_irq:
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
+out_phy:
+	mv88e6xxx_phy_destroy(chip);
 out:
 	if (pdata)
 		dev_put(pdata->netdev);
@@ -7369,12 +7443,6 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 
 	chip = ds->priv;
 
-	if (chip->info->ptp_support) {
-		mv88e6xxx_hwtstamp_free(chip);
-		mv88e6xxx_ptp_free(chip);
-	}
-
-	mv88e6xxx_phy_destroy(chip);
 	mv88e6xxx_unregister_switch(chip);
 
 	mv88e6xxx_g1_vtu_prob_irq_free(chip);
@@ -7387,6 +7455,8 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
+
+	mv88e6xxx_phy_destroy(chip);
 }
 
 static void mv88e6xxx_shutdown(struct mdio_device *mdiodev)
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 86bf113c9bfa..2f211e55cb47 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -241,7 +241,7 @@ struct mv88e6xxx_port_hwtstamp {
 	u16 tx_seq_id;
 
 	/* Current timestamp configuration */
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 };
 
 enum mv88e6xxx_policy_mapping {
@@ -424,8 +424,6 @@ struct mv88e6xxx_chip {
 	struct ptp_clock_info	ptp_clock_info;
 	struct delayed_work	tai_event_work;
 	struct ptp_pin_desc	pin_config[MV88E6XXX_MAX_GPIO];
-	u16 trig_config;
-	u16 evcap_config;
 	u16 enable_count;
 
 	/* Current ingress and egress monitor ports */
@@ -732,7 +730,7 @@ struct mv88e6xxx_avb_ops {
 };
 
 struct mv88e6xxx_ptp_ops {
-	u64 (*clock_read)(const struct cyclecounter *cc);
+	u64 (*clock_read)(struct cyclecounter *cc);
 	int (*ptp_enable)(struct ptp_clock_info *ptp,
 			  struct ptp_clock_request *rq, int on);
 	int (*ptp_verify)(struct ptp_clock_info *ptp, unsigned int pin,
diff --git a/drivers/net/dsa/mv88e6xxx/devlink.c b/drivers/net/dsa/mv88e6xxx/devlink.c
index 795c8df7b6a7..da69e0b85879 100644
--- a/drivers/net/dsa/mv88e6xxx/devlink.c
+++ b/drivers/net/dsa/mv88e6xxx/devlink.c
@@ -376,19 +376,14 @@ static int mv88e6xxx_region_atu_snapshot(struct devlink *dl,
 	struct dsa_switch *ds = dsa_devlink_to_ds(dl);
 	struct mv88e6xxx_devlink_atu_entry *table;
 	struct mv88e6xxx_chip *chip = ds->priv;
-	int fid = -1, err = 0, count;
+	int fid = -1, err = 0, count = 0;
 
-	table = kmalloc_array(mv88e6xxx_num_databases(chip),
-			      sizeof(struct mv88e6xxx_devlink_atu_entry),
-			      GFP_KERNEL);
+	table = kcalloc(mv88e6xxx_num_databases(chip),
+			sizeof(struct mv88e6xxx_devlink_atu_entry),
+			GFP_KERNEL);
 	if (!table)
 		return -ENOMEM;
 
-	memset(table, 0, mv88e6xxx_num_databases(chip) *
-	       sizeof(struct mv88e6xxx_devlink_atu_entry));
-
-	count = 0;
-
 	mv88e6xxx_reg_lock(chip);
 
 	while (1) {
@@ -647,7 +642,7 @@ static struct mv88e6xxx_region_priv mv88e6xxx_region_global1_priv = {
 	.id = MV88E6XXX_REGION_GLOBAL1,
 };
 
-static struct devlink_region_ops mv88e6xxx_region_global1_ops = {
+static const struct devlink_region_ops mv88e6xxx_region_global1_ops = {
 	.name = "global1",
 	.snapshot = mv88e6xxx_region_global_snapshot,
 	.destructor = kfree,
@@ -658,32 +653,32 @@ static struct mv88e6xxx_region_priv mv88e6xxx_region_global2_priv = {
 	.id = MV88E6XXX_REGION_GLOBAL2,
 };
 
-static struct devlink_region_ops mv88e6xxx_region_global2_ops = {
+static const struct devlink_region_ops mv88e6xxx_region_global2_ops = {
 	.name = "global2",
 	.snapshot = mv88e6xxx_region_global_snapshot,
 	.destructor = kfree,
 	.priv = &mv88e6xxx_region_global2_priv,
 };
 
-static struct devlink_region_ops mv88e6xxx_region_atu_ops = {
+static const struct devlink_region_ops mv88e6xxx_region_atu_ops = {
 	.name = "atu",
 	.snapshot = mv88e6xxx_region_atu_snapshot,
 	.destructor = kfree,
 };
 
-static struct devlink_region_ops mv88e6xxx_region_vtu_ops = {
+static const struct devlink_region_ops mv88e6xxx_region_vtu_ops = {
 	.name = "vtu",
 	.snapshot = mv88e6xxx_region_vtu_snapshot,
 	.destructor = kfree,
 };
 
-static struct devlink_region_ops mv88e6xxx_region_stu_ops = {
+static const struct devlink_region_ops mv88e6xxx_region_stu_ops = {
 	.name = "stu",
 	.snapshot = mv88e6xxx_region_stu_snapshot,
 	.destructor = kfree,
 };
 
-static struct devlink_region_ops mv88e6xxx_region_pvt_ops = {
+static const struct devlink_region_ops mv88e6xxx_region_pvt_ops = {
 	.name = "pvt",
 	.snapshot = mv88e6xxx_region_pvt_snapshot,
 	.destructor = kfree,
@@ -696,13 +691,13 @@ static const struct devlink_port_region_ops mv88e6xxx_region_port_ops = {
 };
 
 struct mv88e6xxx_region {
-	struct devlink_region_ops *ops;
+	const struct devlink_region_ops *ops;
 	u64 size;
 
 	bool (*cond)(struct mv88e6xxx_chip *chip);
 };
 
-static struct mv88e6xxx_region mv88e6xxx_regions[] = {
+static const struct mv88e6xxx_region mv88e6xxx_regions[] = {
 	[MV88E6XXX_REGION_GLOBAL1] = {
 		.ops = &mv88e6xxx_region_global1_ops,
 		.size = 32 * sizeof(u16)
@@ -736,7 +731,8 @@ void mv88e6xxx_teardown_devlink_regions_global(struct dsa_switch *ds)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(mv88e6xxx_regions); i++)
-		dsa_devlink_region_destroy(chip->regions[i]);
+		if (chip->regions[i])
+			dsa_devlink_region_destroy(chip->regions[i]);
 }
 
 void mv88e6xxx_teardown_devlink_regions_port(struct dsa_switch *ds, int port)
@@ -767,7 +763,7 @@ int mv88e6xxx_setup_devlink_regions_global(struct dsa_switch *ds)
 {
 	bool (*cond)(struct mv88e6xxx_chip *chip);
 	struct mv88e6xxx_chip *chip = ds->priv;
-	struct devlink_region_ops *ops;
+	const struct devlink_region_ops *ops;
 	struct devlink_region *region;
 	u64 size;
 	int i, j;
diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c
index b2b5f6ba438f..30a6ffa7817b 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.c
+++ b/drivers/net/dsa/mv88e6xxx/global2.c
@@ -1154,8 +1154,8 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip)
 	if (err)
 		return err;
 
-	chip->g2_irq.domain = irq_domain_add_simple(
-		chip->dev->of_node, 16, 0, &mv88e6xxx_g2_irq_domain_ops, chip);
+	chip->g2_irq.domain = irq_domain_create_simple(dev_fwnode(chip->dev), 16, 0,
+						       &mv88e6xxx_g2_irq_domain_ops, chip);
 	if (!chip->g2_irq.domain)
 		return -ENOMEM;
 
diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
index 49e6e1355142..6e6472a3b75a 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
@@ -89,7 +89,7 @@ int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port,
 }
 
 static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port,
-					 struct hwtstamp_config *config)
+					 struct kernel_hwtstamp_config *config)
 {
 	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port];
@@ -169,42 +169,38 @@ static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port,
 }
 
 int mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds, int port,
-				struct ifreq *ifr)
+				struct kernel_hwtstamp_config *config,
+				struct netlink_ext_ack *extack)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
 	struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port];
-	struct hwtstamp_config config;
 	int err;
 
 	if (!chip->info->ptp_support)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	err = mv88e6xxx_set_hwtstamp_config(chip, port, &config);
+	err = mv88e6xxx_set_hwtstamp_config(chip, port, config);
 	if (err)
 		return err;
 
 	/* Save the chosen configuration to be returned later. */
-	memcpy(&ps->tstamp_config, &config, sizeof(config));
+	ps->tstamp_config = *config;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, int port,
-				struct ifreq *ifr)
+				struct kernel_hwtstamp_config *config)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
 	struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port];
-	struct hwtstamp_config *config = &ps->tstamp_config;
 
 	if (!chip->info->ptp_support)
 		return -EOPNOTSUPP;
 
-	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
-		-EFAULT : 0;
+	*config = ps->tstamp_config;
+
+	return 0;
 }
 
 /* Returns a pointer to the PTP header if the caller should time stamp,
@@ -574,7 +570,7 @@ int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip)
 	}
 
 	/* Set the ethertype of L2 PTP messages */
-	err = mv88e6xxx_ptp_write(chip, MV88E6XXX_PTP_GC_ETYPE, ETH_P_1588);
+	err = mv88e6xxx_ptp_write(chip, MV88E6XXX_PTP_ETHERTYPE, ETH_P_1588);
 	if (err)
 		return err;
 
diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.h b/drivers/net/dsa/mv88e6xxx/hwtstamp.h
index 85acc758e3eb..c359821d5a6e 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.h
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.h
@@ -111,9 +111,10 @@
 #ifdef CONFIG_NET_DSA_MV88E6XXX_PTP
 
 int mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds, int port,
-				struct ifreq *ifr);
+				struct kernel_hwtstamp_config *cfg,
+				struct netlink_ext_ack *extack);
 int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, int port,
-				struct ifreq *ifr);
+				struct kernel_hwtstamp_config *cfg);
 
 bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port,
 			     struct sk_buff *clone, unsigned int type);
@@ -123,6 +124,7 @@ void mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port,
 int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port,
 			  struct kernel_ethtool_ts_info *info);
 
+long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp);
 int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip);
 void mv88e6xxx_hwtstamp_free(struct mv88e6xxx_chip *chip);
 int mv88e6352_hwtstamp_port_enable(struct mv88e6xxx_chip *chip, int port);
@@ -132,14 +134,17 @@ int mv88e6165_global_disable(struct mv88e6xxx_chip *chip);
 
 #else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */
 
-static inline int mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds,
-					      int port, struct ifreq *ifr)
+static inline int
+mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds, int port,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
 
-static inline int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds,
-					      int port, struct ifreq *ifr)
+static inline int
+mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, int port,
+			    struct kernel_hwtstamp_config *config)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/dsa/mv88e6xxx/leds.c b/drivers/net/dsa/mv88e6xxx/leds.c
index 1c88bfaea46b..ab3bc645da56 100644
--- a/drivers/net/dsa/mv88e6xxx/leds.c
+++ b/drivers/net/dsa/mv88e6xxx/leds.c
@@ -779,7 +779,8 @@ int mv88e6xxx_port_setup_leds(struct mv88e6xxx_chip *chip, int port)
 			continue;
 		if (led_num > 1) {
 			dev_err(dev, "invalid LED specified port %d\n", port);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err_put_led;
 		}
 
 		if (led_num == 0)
@@ -823,17 +824,25 @@ int mv88e6xxx_port_setup_leds(struct mv88e6xxx_chip *chip, int port)
 		init_data.devname_mandatory = true;
 		init_data.devicename = kasprintf(GFP_KERNEL, "%s:0%d:0%d", chip->info->name,
 						 port, led_num);
-		if (!init_data.devicename)
-			return -ENOMEM;
+		if (!init_data.devicename) {
+			ret = -ENOMEM;
+			goto err_put_led;
+		}
 
 		ret = devm_led_classdev_register_ext(dev, l, &init_data);
 		kfree(init_data.devicename);
 
 		if (ret) {
 			dev_err(dev, "Failed to init LED %d for port %d", led_num, port);
-			return ret;
+			goto err_put_led;
 		}
 	}
 
+	fwnode_handle_put(leds);
 	return 0;
+
+err_put_led:
+	fwnode_handle_put(led);
+	fwnode_handle_put(leds);
+	return ret;
 }
diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6185.c b/drivers/net/dsa/mv88e6xxx/pcs-6185.c
index 5a27d047a38e..af7e06d265f7 100644
--- a/drivers/net/dsa/mv88e6xxx/pcs-6185.c
+++ b/drivers/net/dsa/mv88e6xxx/pcs-6185.c
@@ -55,6 +55,7 @@ static irqreturn_t mv88e6185_pcs_handle_irq(int irq, void *dev_id)
 }
 
 static void mv88e6185_pcs_get_state(struct phylink_pcs *pcs,
+				    unsigned int neg_mode,
 				    struct phylink_link_state *state)
 {
 	struct mv88e6185_pcs *mpcs = pcs_to_mv88e6185_pcs(pcs);
@@ -137,7 +138,6 @@ static int mv88e6185_pcs_init(struct mv88e6xxx_chip *chip, int port)
 	mpcs->chip = chip;
 	mpcs->port = port;
 	mpcs->phylink_pcs.ops = &mv88e6185_phylink_pcs_ops;
-	mpcs->phylink_pcs.neg_mode = true;
 
 	irq = mv88e6xxx_serdes_irq_mapping(chip, port);
 	if (irq) {
diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6352.c b/drivers/net/dsa/mv88e6xxx/pcs-6352.c
index 88f624b65470..36993400837e 100644
--- a/drivers/net/dsa/mv88e6xxx/pcs-6352.c
+++ b/drivers/net/dsa/mv88e6xxx/pcs-6352.c
@@ -158,6 +158,7 @@ static void marvell_c22_pcs_disable(struct phylink_pcs *pcs)
 }
 
 static void marvell_c22_pcs_get_state(struct phylink_pcs *pcs,
+				      unsigned int neg_mode,
 				      struct phylink_link_state *state)
 {
 	struct marvell_c22_pcs *mpcs = pcs_to_marvell_c22_pcs(pcs);
@@ -274,7 +275,6 @@ static struct marvell_c22_pcs *marvell_c22_pcs_alloc(struct device *dev,
 	mpcs->mdio.bus = bus;
 	mpcs->mdio.addr = addr;
 	mpcs->phylink_pcs.ops = &marvell_c22_pcs_ops;
-	mpcs->phylink_pcs.neg_mode = true;
 
 	return mpcs;
 }
diff --git a/drivers/net/dsa/mv88e6xxx/pcs-639x.c b/drivers/net/dsa/mv88e6xxx/pcs-639x.c
index d758a6c1b226..5db17c0b77f5 100644
--- a/drivers/net/dsa/mv88e6xxx/pcs-639x.c
+++ b/drivers/net/dsa/mv88e6xxx/pcs-639x.c
@@ -9,6 +9,7 @@
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include <linux/mii.h>
+#include <linux/string_choices.h>
 
 #include "chip.h"
 #include "global2.h"
@@ -257,6 +258,7 @@ static int mv88e639x_sgmii_pcs_post_config(struct phylink_pcs *pcs,
 }
 
 static void mv88e639x_sgmii_pcs_get_state(struct phylink_pcs *pcs,
+					  unsigned int neg_mode,
 					  struct phylink_link_state *state)
 {
 	struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs);
@@ -395,6 +397,7 @@ static void mv88e639x_xg_pcs_disable(struct mv88e639x_pcs *mpcs)
 }
 
 static void mv88e639x_xg_pcs_get_state(struct phylink_pcs *pcs,
+				       unsigned int neg_mode,
 				       struct phylink_link_state *state)
 {
 	struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs);
@@ -562,9 +565,7 @@ static int mv88e6390_pcs_init(struct mv88e6xxx_chip *chip, int port)
 		return -ENOMEM;
 
 	mpcs->sgmii_pcs.ops = &mv88e639x_sgmii_pcs_ops;
-	mpcs->sgmii_pcs.neg_mode = true;
 	mpcs->xg_pcs.ops = &mv88e6390_xg_pcs_ops;
-	mpcs->xg_pcs.neg_mode = true;
 
 	if (chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6190X ||
 	    chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6390X)
@@ -748,7 +749,7 @@ static int mv88e6393x_sgmii_apply_2500basex_an(struct mv88e639x_pcs *mpcs,
 	if (err)
 		dev_err(mpcs->mdio.dev.parent,
 			"failed to %s 2500basex fix: %pe\n",
-			enable ? "enable" : "disable", ERR_PTR(err));
+			str_enable_disable(enable), ERR_PTR(err));
 
 	return err;
 }
@@ -889,6 +890,7 @@ static int mv88e6393x_xg_pcs_post_config(struct phylink_pcs *pcs,
 }
 
 static void mv88e6393x_xg_pcs_get_state(struct phylink_pcs *pcs,
+					unsigned int neg_mode,
 					struct phylink_link_state *state)
 {
 	struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs);
@@ -896,7 +898,7 @@ static void mv88e6393x_xg_pcs_get_state(struct phylink_pcs *pcs,
 	int err;
 
 	if (state->interface != PHY_INTERFACE_MODE_USXGMII)
-		return mv88e639x_xg_pcs_get_state(pcs, state);
+		return mv88e639x_xg_pcs_get_state(pcs, neg_mode, state);
 
 	state->link = false;
 
@@ -941,9 +943,7 @@ static int mv88e6393x_pcs_init(struct mv88e6xxx_chip *chip, int port)
 		return -ENOMEM;
 
 	mpcs->sgmii_pcs.ops = &mv88e6393x_sgmii_pcs_ops;
-	mpcs->sgmii_pcs.neg_mode = true;
 	mpcs->xg_pcs.ops = &mv88e6393x_xg_pcs_ops;
-	mpcs->xg_pcs.neg_mode = true;
 	mpcs->supports_5g = true;
 
 	err = mv88e6393x_erratum_4_6(mpcs);
diff --git a/drivers/net/dsa/mv88e6xxx/phy.c b/drivers/net/dsa/mv88e6xxx/phy.c
index 8bb88b3d900d..4e7827ee684a 100644
--- a/drivers/net/dsa/mv88e6xxx/phy.c
+++ b/drivers/net/dsa/mv88e6xxx/phy.c
@@ -182,7 +182,7 @@ static void mv88e6xxx_phy_ppu_reenable_work(struct work_struct *ugly)
 
 static void mv88e6xxx_phy_ppu_reenable_timer(struct timer_list *t)
 {
-	struct mv88e6xxx_chip *chip = from_timer(chip, t, ppu_timer);
+	struct mv88e6xxx_chip *chip = timer_container_of(chip, t, ppu_timer);
 
 	schedule_work(&chip->ppu_work);
 }
@@ -206,7 +206,7 @@ static int mv88e6xxx_phy_ppu_access_get(struct mv88e6xxx_chip *chip)
 		}
 		chip->ppu_disabled = 1;
 	} else {
-		del_timer(&chip->ppu_timer);
+		timer_delete(&chip->ppu_timer);
 		ret = 0;
 	}
 
@@ -229,7 +229,10 @@ static void mv88e6xxx_phy_ppu_state_init(struct mv88e6xxx_chip *chip)
 
 static void mv88e6xxx_phy_ppu_state_destroy(struct mv88e6xxx_chip *chip)
 {
-	del_timer_sync(&chip->ppu_timer);
+	mutex_lock(&chip->ppu_mutex);
+	timer_delete_sync(&chip->ppu_timer);
+	cancel_work_sync(&chip->ppu_work);
+	mutex_unlock(&chip->ppu_mutex);
 }
 
 int mv88e6185_phy_ppu_read(struct mv88e6xxx_chip *chip, struct mii_bus *bus,
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index dc777ddce1f3..66b1b7277281 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -13,6 +13,7 @@
 #include <linux/phy.h>
 #include <linux/phylink.h>
 #include <linux/property.h>
+#include <linux/string_choices.h>
 
 #include "chip.h"
 #include "global2.h"
@@ -176,7 +177,7 @@ int mv88e6xxx_port_set_link(struct mv88e6xxx_chip *chip, int port, int link)
 
 	dev_dbg(chip->dev, "p%d: %s link %s\n", port,
 		reg & MV88E6XXX_PORT_MAC_CTL_FORCE_LINK ? "Force" : "Unforce",
-		reg & MV88E6XXX_PORT_MAC_CTL_LINK_UP ? "up" : "down");
+		str_up_down(reg & MV88E6XXX_PORT_MAC_CTL_LINK_UP));
 
 	return 0;
 }
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c
index aed4a4b07f34..f7603573d3a9 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.c
+++ b/drivers/net/dsa/mv88e6xxx/ptp.c
@@ -138,13 +138,13 @@ mv88e6xxx_cc_coeff_get(struct mv88e6xxx_chip *chip)
 	}
 }
 
-static u64 mv88e6352_ptp_clock_read(const struct cyclecounter *cc)
+static u64 mv88e6352_ptp_clock_read(struct cyclecounter *cc)
 {
 	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
 	u16 phc_time[2];
 	int err;
 
-	err = mv88e6xxx_tai_read(chip, MV88E6XXX_TAI_TIME_LO, phc_time,
+	err = mv88e6xxx_tai_read(chip, MV88E6352_TAI_TIME_LO, phc_time,
 				 ARRAY_SIZE(phc_time));
 	if (err)
 		return 0;
@@ -152,13 +152,13 @@ static u64 mv88e6352_ptp_clock_read(const struct cyclecounter *cc)
 		return ((u32)phc_time[1] << 16) | phc_time[0];
 }
 
-static u64 mv88e6165_ptp_clock_read(const struct cyclecounter *cc)
+static u64 mv88e6165_ptp_clock_read(struct cyclecounter *cc)
 {
 	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
 	u16 phc_time[2];
 	int err;
 
-	err = mv88e6xxx_tai_read(chip, MV88E6XXX_PTP_GC_TIME_LO, phc_time,
+	err = mv88e6xxx_tai_read(chip, MV88E6165_PTP_GC_TIME_LO, phc_time,
 				 ARRAY_SIZE(phc_time));
 	if (err)
 		return 0;
@@ -167,42 +167,26 @@ static u64 mv88e6165_ptp_clock_read(const struct cyclecounter *cc)
 }
 
 /* mv88e6352_config_eventcap - configure TAI event capture
- * @event: PTP_CLOCK_PPS (internal) or PTP_CLOCK_EXTTS (external)
  * @rising: zero for falling-edge trigger, else rising-edge trigger
  *
  * This will also reset the capture sequence counter.
  */
-static int mv88e6352_config_eventcap(struct mv88e6xxx_chip *chip, int event,
-				     int rising)
+static int mv88e6352_config_eventcap(struct mv88e6xxx_chip *chip, int rising)
 {
-	u16 global_config;
-	u16 cap_config;
+	u16 evcap_config;
 	int err;
 
-	chip->evcap_config = MV88E6XXX_TAI_CFG_CAP_OVERWRITE |
-			     MV88E6XXX_TAI_CFG_CAP_CTR_START;
+	evcap_config = MV88E6352_TAI_CFG_CAP_OVERWRITE |
+		       MV88E6352_TAI_CFG_CAP_CTR_START;
 	if (!rising)
-		chip->evcap_config |= MV88E6XXX_TAI_CFG_EVREQ_FALLING;
+		evcap_config |= MV88E6352_TAI_CFG_EVREQ_FALLING;
 
-	global_config = (chip->evcap_config | chip->trig_config);
-	err = mv88e6xxx_tai_write(chip, MV88E6XXX_TAI_CFG, global_config);
+	err = mv88e6xxx_tai_write(chip, MV88E6352_TAI_CFG, evcap_config);
 	if (err)
 		return err;
 
-	if (event == PTP_CLOCK_PPS) {
-		cap_config = MV88E6XXX_TAI_EVENT_STATUS_CAP_TRIG;
-	} else if (event == PTP_CLOCK_EXTTS) {
-		/* if STATUS_CAP_TRIG is unset we capture PTP_EVREQ events */
-		cap_config = 0;
-	} else {
-		return -EINVAL;
-	}
-
 	/* Write the capture config; this also clears the capture counter */
-	err = mv88e6xxx_tai_write(chip, MV88E6XXX_TAI_EVENT_STATUS,
-				  cap_config);
-
-	return err;
+	return mv88e6xxx_tai_write(chip, MV88E6352_TAI_EVENT_STATUS, 0);
 }
 
 static void mv88e6352_tai_event_work(struct work_struct *ugly)
@@ -215,7 +199,7 @@ static void mv88e6352_tai_event_work(struct work_struct *ugly)
 	int err;
 
 	mv88e6xxx_reg_lock(chip);
-	err = mv88e6xxx_tai_read(chip, MV88E6XXX_TAI_EVENT_STATUS,
+	err = mv88e6xxx_tai_read(chip, MV88E6352_TAI_EVENT_STATUS,
 				 status, ARRAY_SIZE(status));
 	mv88e6xxx_reg_unlock(chip);
 
@@ -223,19 +207,19 @@ static void mv88e6352_tai_event_work(struct work_struct *ugly)
 		dev_err(chip->dev, "failed to read TAI status register\n");
 		return;
 	}
-	if (status[0] & MV88E6XXX_TAI_EVENT_STATUS_ERROR) {
+	if (status[0] & MV88E6352_TAI_EVENT_STATUS_ERROR) {
 		dev_warn(chip->dev, "missed event capture\n");
 		return;
 	}
-	if (!(status[0] & MV88E6XXX_TAI_EVENT_STATUS_VALID))
+	if (!(status[0] & MV88E6352_TAI_EVENT_STATUS_VALID))
 		goto out;
 
 	raw_ts = ((u32)status[2] << 16) | status[1];
 
 	/* Clear the valid bit so the next timestamp can come in */
-	status[0] &= ~MV88E6XXX_TAI_EVENT_STATUS_VALID;
+	status[0] &= ~MV88E6352_TAI_EVENT_STATUS_VALID;
 	mv88e6xxx_reg_lock(chip);
-	err = mv88e6xxx_tai_write(chip, MV88E6XXX_TAI_EVENT_STATUS, status[0]);
+	err = mv88e6xxx_tai_write(chip, MV88E6352_TAI_EVENT_STATUS, status[0]);
 	mv88e6xxx_reg_unlock(chip);
 	if (err) {
 		dev_err(chip->dev, "failed to write TAI status register\n");
@@ -332,13 +316,6 @@ static int mv88e6352_ptp_enable_extts(struct mv88e6xxx_chip *chip,
 	int pin;
 	int err;
 
-	/* Reject requests with unsupported flags */
-	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-				PTP_RISING_EDGE |
-				PTP_FALLING_EDGE |
-				PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	/* Reject requests to enable time stamping on both edges. */
 	if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
 	    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
@@ -362,7 +339,7 @@ static int mv88e6352_ptp_enable_extts(struct mv88e6xxx_chip *chip,
 		schedule_delayed_work(&chip->tai_event_work,
 				      TAI_EVENT_WORK_INTERVAL);
 
-		err = mv88e6352_config_eventcap(chip, PTP_CLOCK_EXTTS, rising);
+		err = mv88e6352_config_eventcap(chip, rising);
 	} else {
 		func = MV88E6352_G2_SCRATCH_GPIO_PCTL_GPIO;
 
@@ -420,29 +397,6 @@ const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = {
 		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
 };
 
-const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops = {
-	.clock_read = mv88e6352_ptp_clock_read,
-	.ptp_enable = mv88e6352_ptp_enable,
-	.ptp_verify = mv88e6352_ptp_verify,
-	.event_work = mv88e6352_tai_event_work,
-	.port_enable = mv88e6352_hwtstamp_port_enable,
-	.port_disable = mv88e6352_hwtstamp_port_disable,
-	.n_ext_ts = 1,
-	.arr0_sts_reg = MV88E6XXX_PORT_PTP_ARR0_STS,
-	.arr1_sts_reg = MV88E6XXX_PORT_PTP_ARR1_STS,
-	.dep_sts_reg = MV88E6XXX_PORT_PTP_DEP_STS,
-	.rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
-};
-
 const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {
 	.clock_read = mv88e6352_ptp_clock_read,
 	.ptp_enable = mv88e6352_ptp_enable,
@@ -490,7 +444,7 @@ const struct mv88e6xxx_ptp_ops mv88e6390_ptp_ops = {
 		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
 };
 
-static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
+static u64 mv88e6xxx_ptp_clock_read(struct cyclecounter *cc)
 {
 	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
 
@@ -566,6 +520,10 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip)
 	chip->ptp_clock_info.verify	= ptp_ops->ptp_verify;
 	chip->ptp_clock_info.do_aux_work = mv88e6xxx_hwtstamp_work;
 
+	chip->ptp_clock_info.supported_extts_flags = PTP_RISING_EDGE |
+						     PTP_FALLING_EDGE |
+						     PTP_STRICT_FLAGS;
+
 	if (ptp_ops->set_ptp_cpu_port) {
 		struct dsa_port *dp;
 		int upstream = 0;
@@ -593,6 +551,7 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip)
 	return 0;
 }
 
+/* This must never be called holding the register lock */
 void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip)
 {
 	if (chip->ptp_clock) {
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.h b/drivers/net/dsa/mv88e6xxx/ptp.h
index 6c4d09adc93c..95bdddb0bf39 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.h
+++ b/drivers/net/dsa/mv88e6xxx/ptp.h
@@ -16,132 +16,56 @@
 #include "chip.h"
 
 /* Offset 0x00: TAI Global Config */
-#define MV88E6XXX_TAI_CFG			0x00
-#define MV88E6XXX_TAI_CFG_CAP_OVERWRITE		0x8000
-#define MV88E6XXX_TAI_CFG_CAP_CTR_START		0x4000
-#define MV88E6XXX_TAI_CFG_EVREQ_FALLING		0x2000
-#define MV88E6XXX_TAI_CFG_TRIG_ACTIVE_LO	0x1000
-#define MV88E6XXX_TAI_CFG_IRL_ENABLE		0x0400
-#define MV88E6XXX_TAI_CFG_TRIG_IRQ_EN		0x0200
-#define MV88E6XXX_TAI_CFG_EVREQ_IRQ_EN		0x0100
-#define MV88E6XXX_TAI_CFG_TRIG_LOCK		0x0080
-#define MV88E6XXX_TAI_CFG_BLOCK_UPDATE		0x0008
-#define MV88E6XXX_TAI_CFG_MULTI_PTP		0x0004
-#define MV88E6XXX_TAI_CFG_TRIG_MODE_ONESHOT	0x0002
-#define MV88E6XXX_TAI_CFG_TRIG_ENABLE		0x0001
+#define MV88E6352_TAI_CFG			0x00
+#define MV88E6352_TAI_CFG_CAP_OVERWRITE		0x8000
+#define MV88E6352_TAI_CFG_CAP_CTR_START		0x4000
+#define MV88E6352_TAI_CFG_EVREQ_FALLING		0x2000
+#define MV88E6352_TAI_CFG_TRIG_ACTIVE_LO	0x1000
+#define MV88E6352_TAI_CFG_IRL_ENABLE		0x0400
+#define MV88E6352_TAI_CFG_TRIG_IRQ_EN		0x0200
+#define MV88E6352_TAI_CFG_EVREQ_IRQ_EN		0x0100
+#define MV88E6352_TAI_CFG_TRIG_LOCK		0x0080
+#define MV88E6352_TAI_CFG_BLOCK_UPDATE		0x0008
+#define MV88E6352_TAI_CFG_MULTI_PTP		0x0004
+#define MV88E6352_TAI_CFG_TRIG_MODE_ONESHOT	0x0002
+#define MV88E6352_TAI_CFG_TRIG_ENABLE		0x0001
 
 /* Offset 0x01: Timestamp Clock Period (ps) */
 #define MV88E6XXX_TAI_CLOCK_PERIOD		0x01
 
-/* Offset 0x02/0x03: Trigger Generation Amount */
-#define MV88E6XXX_TAI_TRIG_GEN_AMOUNT_LO	0x02
-#define MV88E6XXX_TAI_TRIG_GEN_AMOUNT_HI	0x03
-
-/* Offset 0x04: Clock Compensation */
-#define MV88E6XXX_TAI_TRIG_CLOCK_COMP		0x04
-
-/* Offset 0x05: Trigger Configuration */
-#define MV88E6XXX_TAI_TRIG_CFG			0x05
-
-/* Offset 0x06: Ingress Rate Limiter Clock Generation Amount */
-#define MV88E6XXX_TAI_IRL_AMOUNT		0x06
-
-/* Offset 0x07: Ingress Rate Limiter Compensation */
-#define MV88E6XXX_TAI_IRL_COMP			0x07
-
-/* Offset 0x08: Ingress Rate Limiter Compensation */
-#define MV88E6XXX_TAI_IRL_COMP_PS		0x08
-
 /* Offset 0x09: Event Status */
-#define MV88E6XXX_TAI_EVENT_STATUS		0x09
-#define MV88E6XXX_TAI_EVENT_STATUS_CAP_TRIG	0x4000
-#define MV88E6XXX_TAI_EVENT_STATUS_ERROR	0x0200
-#define MV88E6XXX_TAI_EVENT_STATUS_VALID	0x0100
-#define MV88E6XXX_TAI_EVENT_STATUS_CTR_MASK	0x00ff
-
-/* Offset 0x0A/0x0B: Event Time */
-#define MV88E6XXX_TAI_EVENT_TIME_LO		0x0a
-#define MV88E6XXX_TAI_EVENT_TYPE_HI		0x0b
+#define MV88E6352_TAI_EVENT_STATUS		0x09
+#define MV88E6352_TAI_EVENT_STATUS_ERROR	0x0200
+#define MV88E6352_TAI_EVENT_STATUS_VALID	0x0100
+#define MV88E6352_TAI_EVENT_STATUS_CTR_MASK	0x00ff
+/* Offset 0x0A/0x0B: Event Time Lo/Hi. Always read with Event Status. */
 
 /* Offset 0x0E/0x0F: PTP Global Time */
-#define MV88E6XXX_TAI_TIME_LO			0x0e
-#define MV88E6XXX_TAI_TIME_HI			0x0f
-
-/* Offset 0x10/0x11: Trig Generation Time */
-#define MV88E6XXX_TAI_TRIG_TIME_LO		0x10
-#define MV88E6XXX_TAI_TRIG_TIME_HI		0x11
-
-/* Offset 0x12: Lock Status */
-#define MV88E6XXX_TAI_LOCK_STATUS		0x12
-
-/* Offset 0x00: Ether Type */
-#define MV88E6XXX_PTP_GC_ETYPE			0x00
+#define MV88E6352_TAI_TIME_LO			0x0e
+#define MV88E6352_TAI_TIME_HI			0x0f
 
 /* 6165 Global Control Registers */
-/* Offset 0x00: Ether Type */
-#define MV88E6XXX_PTP_GC_ETYPE			0x00
-
-/* Offset 0x01: Message ID */
-#define MV88E6XXX_PTP_GC_MESSAGE_ID		0x01
-
-/* Offset 0x02: Time Stamp Arrive Time */
-#define MV88E6XXX_PTP_GC_TS_ARR_PTR		0x02
-
-/* Offset 0x03: Port Arrival Interrupt Enable */
-#define MV88E6XXX_PTP_GC_PORT_ARR_INT_EN	0x03
-
-/* Offset 0x04: Port Departure Interrupt Enable */
-#define MV88E6XXX_PTP_GC_PORT_DEP_INT_EN	0x04
-
-/* Offset 0x05: Configuration */
-#define MV88E6XXX_PTP_GC_CONFIG			0x05
-#define MV88E6XXX_PTP_GC_CONFIG_DIS_OVERWRITE	BIT(1)
-#define MV88E6XXX_PTP_GC_CONFIG_DIS_TS		BIT(0)
-
-/* Offset 0x8: Interrupt Status */
-#define MV88E6XXX_PTP_GC_INT_STATUS		0x08
-
 /* Offset 0x9/0xa: Global Time */
-#define MV88E6XXX_PTP_GC_TIME_LO		0x09
-#define MV88E6XXX_PTP_GC_TIME_HI		0x0A
+#define MV88E6165_PTP_GC_TIME_LO		0x09
+#define MV88E6165_PTP_GC_TIME_HI		0x0A
 
-/* 6165 Per Port Registers */
+/* 6165 Per Port Registers. The arrival and departure registers are a
+ * common block consisting of status, two time registers and the sequence ID
+ */
 /* Offset 0: Arrival Time 0 Status */
 #define MV88E6165_PORT_PTP_ARR0_STS	0x00
 
-/* Offset 0x01/0x02: PTP Arrival 0 Time */
-#define MV88E6165_PORT_PTP_ARR0_TIME_LO	0x01
-#define MV88E6165_PORT_PTP_ARR0_TIME_HI	0x02
-
-/* Offset 0x03: PTP Arrival 0 Sequence ID */
-#define MV88E6165_PORT_PTP_ARR0_SEQID	0x03
-
 /* Offset 0x04: PTP Arrival 1 Status */
 #define MV88E6165_PORT_PTP_ARR1_STS	0x04
 
-/* Offset 0x05/0x6E: PTP Arrival 1 Time */
-#define MV88E6165_PORT_PTP_ARR1_TIME_LO	0x05
-#define MV88E6165_PORT_PTP_ARR1_TIME_HI	0x06
-
-/* Offset 0x07: PTP Arrival 1 Sequence ID */
-#define MV88E6165_PORT_PTP_ARR1_SEQID	0x07
-
 /* Offset 0x08: PTP Departure Status */
 #define MV88E6165_PORT_PTP_DEP_STS	0x08
 
-/* Offset 0x09/0x0a: PTP Deperture Time */
-#define MV88E6165_PORT_PTP_DEP_TIME_LO	0x09
-#define MV88E6165_PORT_PTP_DEP_TIME_HI	0x0a
-
-/* Offset 0x0b: PTP Departure Sequence ID */
-#define MV88E6165_PORT_PTP_DEP_SEQID	0x0b
-
 /* Offset 0x0d: Port Status */
 #define MV88E6164_PORT_STATUS		0x0d
 
 #ifdef CONFIG_NET_DSA_MV88E6XXX_PTP
 
-long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp);
 int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip);
 void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip);
 
@@ -149,17 +73,11 @@ void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip);
 				      ptp_clock_info)
 
 extern const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops;
-extern const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops;
 extern const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops;
 extern const struct mv88e6xxx_ptp_ops mv88e6390_ptp_ops;
 
 #else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */
 
-static inline long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp)
-{
-	return -1;
-}
-
 static inline int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip)
 {
 	return 0;
@@ -170,7 +88,6 @@ static inline void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip)
 }
 
 static const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = {};
-static const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops = {};
 static const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {};
 static const struct mv88e6xxx_ptp_ops mv88e6390_ptp_ops = {};
 
diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 3aa9c997018a..9e5ede932b42 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -1153,6 +1153,9 @@ static void felix_phylink_get_caps(struct dsa_switch *ds, int port,
 
 	__set_bit(ocelot->ports[port]->phy_mode,
 		  config->supported_interfaces);
+	if (ocelot->ports[port]->phy_mode == PHY_INTERFACE_MODE_USXGMII)
+		__set_bit(PHY_INTERFACE_MODE_10G_QXGMII,
+			  config->supported_interfaces);
 }
 
 static void felix_phylink_mac_config(struct phylink_config *config,
@@ -1230,6 +1233,7 @@ static int felix_port_enable(struct dsa_switch *ds, int port,
 {
 	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct ocelot *ocelot = ds->priv;
+	struct felix *felix = ocelot_to_felix(ocelot);
 
 	if (!dsa_port_is_user(dp))
 		return 0;
@@ -1243,7 +1247,25 @@ static int felix_port_enable(struct dsa_switch *ds, int port,
 		}
 	}
 
-	return 0;
+	if (!dp->hsr_dev || felix->tag_proto == DSA_TAG_PROTO_OCELOT_8021Q)
+		return 0;
+
+	return dsa_port_simple_hsr_join(ds, port, dp->hsr_dev, NULL);
+}
+
+static void felix_port_disable(struct dsa_switch *ds, int port)
+{
+	struct dsa_port *dp = dsa_to_port(ds, port);
+	struct ocelot *ocelot = ds->priv;
+	struct felix *felix = ocelot_to_felix(ocelot);
+
+	if (!dsa_port_is_user(dp))
+		return;
+
+	if (!dp->hsr_dev || felix->tag_proto == DSA_TAG_PROTO_OCELOT_8021Q)
+		return;
+
+	dsa_port_simple_hsr_leave(ds, port, dp->hsr_dev);
 }
 
 static void felix_port_qos_map_init(struct ocelot *ocelot, int port)
@@ -1316,6 +1338,14 @@ static void felix_get_eth_phy_stats(struct dsa_switch *ds, int port,
 	ocelot_port_get_eth_phy_stats(ocelot, port, phy_stats);
 }
 
+static void felix_get_ts_stats(struct dsa_switch *ds, int port,
+			       struct ethtool_ts_stats *ts_stats)
+{
+	struct ocelot *ocelot = ds->priv;
+
+	ocelot_port_get_ts_stats(ocelot, port, ts_stats);
+}
+
 static void felix_get_strings(struct dsa_switch *ds, int port,
 			      u32 stringset, u8 *data)
 {
@@ -1351,6 +1381,7 @@ static const u32 felix_phy_match_table[PHY_INTERFACE_MODE_MAX] = {
 	[PHY_INTERFACE_MODE_SGMII] = OCELOT_PORT_MODE_SGMII,
 	[PHY_INTERFACE_MODE_QSGMII] = OCELOT_PORT_MODE_QSGMII,
 	[PHY_INTERFACE_MODE_USXGMII] = OCELOT_PORT_MODE_USXGMII,
+	[PHY_INTERFACE_MODE_10G_QXGMII] = OCELOT_PORT_MODE_10G_QXGMII,
 	[PHY_INTERFACE_MODE_1000BASEX] = OCELOT_PORT_MODE_1000BASEX,
 	[PHY_INTERFACE_MODE_2500BASEX] = OCELOT_PORT_MODE_2500BASEX,
 };
@@ -1766,22 +1797,25 @@ static void felix_teardown(struct dsa_switch *ds)
 }
 
 static int felix_hwtstamp_get(struct dsa_switch *ds, int port,
-			      struct ifreq *ifr)
+			      struct kernel_hwtstamp_config *config)
 {
 	struct ocelot *ocelot = ds->priv;
 
-	return ocelot_hwstamp_get(ocelot, port, ifr);
+	ocelot_hwstamp_get(ocelot, port, config);
+
+	return 0;
 }
 
 static int felix_hwtstamp_set(struct dsa_switch *ds, int port,
-			      struct ifreq *ifr)
+			      struct kernel_hwtstamp_config *config,
+			      struct netlink_ext_ack *extack)
 {
 	struct ocelot *ocelot = ds->priv;
 	struct felix *felix = ocelot_to_felix(ocelot);
 	bool using_tag_8021q;
 	int err;
 
-	err = ocelot_hwstamp_set(ocelot, port, ifr);
+	err = ocelot_hwstamp_set(ocelot, port, config, extack);
 	if (err)
 		return err;
 
@@ -2217,6 +2251,52 @@ static void felix_get_mm_stats(struct dsa_switch *ds, int port,
 	ocelot_port_get_mm_stats(ocelot, port, stats);
 }
 
+/* Depending on port type, we may be able to support the offload later (with
+ * the "ocelot"/"seville" tagging protocols), or never.
+ * If we return 0, the dp->hsr_dev reference is kept for later; if we return
+ * -EOPNOTSUPP, it is cleared (which helps to not bother
+ * dsa_port_simple_hsr_leave() with an offload that didn't pass validation).
+ */
+static int felix_port_hsr_join(struct dsa_switch *ds, int port,
+			       struct net_device *hsr,
+			       struct netlink_ext_ack *extack)
+{
+	struct ocelot *ocelot = ds->priv;
+	struct felix *felix = ocelot_to_felix(ocelot);
+
+	if (felix->tag_proto == DSA_TAG_PROTO_OCELOT_8021Q) {
+		int err;
+
+		err = dsa_port_simple_hsr_validate(ds, port, hsr, extack);
+		if (err)
+			return err;
+
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Offloading not supported with \"ocelot-8021q\"");
+		return 0;
+	}
+
+	if (!(dsa_to_port(ds, port)->user->flags & IFF_UP))
+		return 0;
+
+	return dsa_port_simple_hsr_join(ds, port, hsr, extack);
+}
+
+static int felix_port_hsr_leave(struct dsa_switch *ds, int port,
+				struct net_device *hsr)
+{
+	struct ocelot *ocelot = ds->priv;
+	struct felix *felix = ocelot_to_felix(ocelot);
+
+	if (felix->tag_proto == DSA_TAG_PROTO_OCELOT_8021Q)
+		return 0;
+
+	if (!(dsa_to_port(ds, port)->user->flags & IFF_UP))
+		return 0;
+
+	return dsa_port_simple_hsr_leave(ds, port, hsr);
+}
+
 static const struct phylink_mac_ops felix_phylink_mac_ops = {
 	.mac_select_pcs		= felix_phylink_mac_select_pcs,
 	.mac_config		= felix_phylink_mac_config,
@@ -2237,6 +2317,7 @@ static const struct dsa_switch_ops felix_switch_ops = {
 	.get_stats64			= felix_get_stats64,
 	.get_pause_stats		= felix_get_pause_stats,
 	.get_rmon_stats			= felix_get_rmon_stats,
+	.get_ts_stats			= felix_get_ts_stats,
 	.get_eth_ctrl_stats		= felix_get_eth_ctrl_stats,
 	.get_eth_mac_stats		= felix_get_eth_mac_stats,
 	.get_eth_phy_stats		= felix_get_eth_phy_stats,
@@ -2246,6 +2327,7 @@ static const struct dsa_switch_ops felix_switch_ops = {
 	.get_ts_info			= felix_get_ts_info,
 	.phylink_get_caps		= felix_phylink_get_caps,
 	.port_enable			= felix_port_enable,
+	.port_disable			= felix_port_disable,
 	.port_fast_age			= felix_port_fast_age,
 	.port_fdb_dump			= felix_fdb_dump,
 	.port_fdb_add			= felix_fdb_add,
@@ -2302,6 +2384,8 @@ static const struct dsa_switch_ops felix_switch_ops = {
 	.port_del_dscp_prio		= felix_port_del_dscp_prio,
 	.port_set_host_flood		= felix_port_set_host_flood,
 	.port_change_conduit		= felix_port_change_conduit,
+	.port_hsr_join			= felix_port_hsr_join,
+	.port_hsr_leave			= felix_port_hsr_leave,
 };
 
 int felix_register_switch(struct device *dev, resource_size_t switch_base,
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index 211991f494e3..a657b190c5d7 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -12,8 +12,9 @@
 #define OCELOT_PORT_MODE_SGMII		BIT(1)
 #define OCELOT_PORT_MODE_QSGMII		BIT(2)
 #define OCELOT_PORT_MODE_2500BASEX	BIT(3)
-#define OCELOT_PORT_MODE_USXGMII	BIT(4)
+#define OCELOT_PORT_MODE_USXGMII	BIT(4) /* compatibility */
 #define OCELOT_PORT_MODE_1000BASEX	BIT(5)
+#define OCELOT_PORT_MODE_10G_QXGMII	BIT(6)
 
 struct device_node;
 
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 940f1b71226d..8cf4c8986587 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -34,7 +34,8 @@
 					 OCELOT_PORT_MODE_QSGMII | \
 					 OCELOT_PORT_MODE_1000BASEX | \
 					 OCELOT_PORT_MODE_2500BASEX | \
-					 OCELOT_PORT_MODE_USXGMII)
+					 OCELOT_PORT_MODE_USXGMII | \
+					 OCELOT_PORT_MODE_10G_QXGMII)
 
 static const u32 vsc9959_port_modes[VSC9959_NUM_PORTS] = {
 	VSC9959_PORT_MODE_SERDES,
@@ -1543,7 +1544,7 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
 	struct tc_taprio_qopt_offload *taprio;
 	struct ocelot_port *ocelot_port;
 	struct timespec64 base_ts;
-	int port;
+	int i, port;
 	u32 val;
 
 	mutex_lock(&ocelot->fwd_domain_lock);
@@ -1575,6 +1576,9 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
 			   QSYS_PARAM_CFG_REG_3_BASE_TIME_SEC_MSB_M,
 			   QSYS_PARAM_CFG_REG_3);
 
+		for (i = 0; i < taprio->num_entries; i++)
+			vsc9959_tas_gcl_set(ocelot, i, &taprio->entries[i]);
+
 		ocelot_rmw(ocelot, QSYS_TAS_PARAM_CFG_CTRL_CONFIG_CHANGE,
 			   QSYS_TAS_PARAM_CFG_CTRL_CONFIG_CHANGE,
 			   QSYS_TAS_PARAM_CFG_CTRL);
diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c
index e9f2c67bc15f..0526aa96146e 100644
--- a/drivers/net/dsa/qca/ar9331.c
+++ b/drivers/net/dsa/qca/ar9331.c
@@ -821,8 +821,8 @@ static int ar9331_sw_irq_init(struct ar9331_sw_priv *priv)
 		return ret;
 	}
 
-	priv->irqdomain = irq_domain_add_linear(np, 1, &ar9331_sw_irqdomain_ops,
-						priv);
+	priv->irqdomain = irq_domain_create_linear(dev_fwnode(dev), 1, &ar9331_sw_irqdomain_ops,
+						   priv);
 	if (!priv->irqdomain) {
 		dev_err(dev, "failed to create IRQ domain\n");
 		return -EINVAL;
diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index 90e24bc00b99..a36b8b07030e 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -1019,7 +1019,7 @@ qca8k_setup_mdio_bus(struct qca8k_priv *priv)
 
 		of_get_phy_mode(port, &mode);
 
-		if (of_property_read_bool(port, "phy-handle") &&
+		if (of_property_present(port, "phy-handle") &&
 		    mode != PHY_INTERFACE_MODE_INTERNAL)
 			external_mdio_mask |= BIT(reg);
 		else
@@ -1491,7 +1491,7 @@ static struct qca8k_pcs *pcs_to_qca8k_pcs(struct phylink_pcs *pcs)
 	return container_of(pcs, struct qca8k_pcs, pcs);
 }
 
-static void qca8k_pcs_get_state(struct phylink_pcs *pcs,
+static void qca8k_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode,
 				struct phylink_link_state *state)
 {
 	struct qca8k_priv *priv = pcs_to_qca8k_pcs(pcs)->priv;
@@ -1634,7 +1634,6 @@ static void qca8k_setup_pcs(struct qca8k_priv *priv, struct qca8k_pcs *qpcs,
 			    int port)
 {
 	qpcs->pcs.ops = &qca8k_pcs_ops;
-	qpcs->pcs.neg_mode = true;
 
 	/* We don't have interrupts for link changes, so we need to poll */
 	qpcs->pcs.poll = true;
@@ -2017,7 +2016,6 @@ static const struct dsa_switch_ops qca8k_switch_ops = {
 	.get_sset_count		= qca8k_get_sset_count,
 	.set_ageing_time	= qca8k_set_ageing_time,
 	.support_eee		= dsa_supports_eee,
-	.get_mac_eee		= qca8k_get_mac_eee,
 	.set_mac_eee		= qca8k_set_mac_eee,
 	.port_enable		= qca8k_port_enable,
 	.port_disable		= qca8k_port_disable,
diff --git a/drivers/net/dsa/qca/qca8k-common.c b/drivers/net/dsa/qca/qca8k-common.c
index 560c74c4ac3d..13005f10edb7 100644
--- a/drivers/net/dsa/qca/qca8k-common.c
+++ b/drivers/net/dsa/qca/qca8k-common.c
@@ -557,13 +557,6 @@ exit:
 	return ret;
 }
 
-int qca8k_get_mac_eee(struct dsa_switch *ds, int port,
-		      struct ethtool_keee *e)
-{
-	/* Nothing to do on the port's MAC */
-	return 0;
-}
-
 static int qca8k_port_configure_learning(struct dsa_switch *ds, int port,
 					 bool learning)
 {
diff --git a/drivers/net/dsa/qca/qca8k.h b/drivers/net/dsa/qca/qca8k.h
index 24962a395754..d046679265fa 100644
--- a/drivers/net/dsa/qca/qca8k.h
+++ b/drivers/net/dsa/qca/qca8k.h
@@ -520,7 +520,6 @@ int qca8k_get_sset_count(struct dsa_switch *ds, int port, int sset);
 
 /* Common eee function */
 int qca8k_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *eee);
-int qca8k_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e);
 
 /* Common bridge function */
 void qca8k_port_stp_state_set(struct dsa_switch *ds, int port, u8 state);
diff --git a/drivers/net/dsa/realtek/Kconfig b/drivers/net/dsa/realtek/Kconfig
index 6989972eebc3..d6eb6713e5f6 100644
--- a/drivers/net/dsa/realtek/Kconfig
+++ b/drivers/net/dsa/realtek/Kconfig
@@ -43,4 +43,10 @@ config NET_DSA_REALTEK_RTL8366RB
 	help
 	  Select to enable support for Realtek RTL8366RB.
 
+config NET_DSA_REALTEK_RTL8366RB_LEDS
+	bool
+	depends on (LEDS_CLASS=y || LEDS_CLASS=NET_DSA_REALTEK_RTL8366RB)
+	depends on NET_DSA_REALTEK_RTL8366RB
+	default NET_DSA_REALTEK_RTL8366RB
+
 endif
diff --git a/drivers/net/dsa/realtek/Makefile b/drivers/net/dsa/realtek/Makefile
index 35491dc20d6d..17367bcba496 100644
--- a/drivers/net/dsa/realtek/Makefile
+++ b/drivers/net/dsa/realtek/Makefile
@@ -12,4 +12,7 @@ endif
 
 obj-$(CONFIG_NET_DSA_REALTEK_RTL8366RB) += rtl8366.o
 rtl8366-objs 				:= rtl8366-core.o rtl8366rb.o
+ifdef CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS
+rtl8366-objs 				+= rtl8366rb-leds.o
+endif
 obj-$(CONFIG_NET_DSA_REALTEK_RTL8365MB) += rtl8365mb.o
diff --git a/drivers/net/dsa/realtek/realtek.h b/drivers/net/dsa/realtek/realtek.h
index a1b2e0b529d5..c03485a80d93 100644
--- a/drivers/net/dsa/realtek/realtek.h
+++ b/drivers/net/dsa/realtek/realtek.h
@@ -19,9 +19,6 @@
 
 struct phylink_mac_ops;
 struct realtek_ops;
-struct dentry;
-struct inode;
-struct file;
 
 struct rtl8366_mib_counter {
 	unsigned int	base;
diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c
index 7e96355c28bd..c575e164368c 100644
--- a/drivers/net/dsa/realtek/rtl8365mb.c
+++ b/drivers/net/dsa/realtek/rtl8365mb.c
@@ -1719,8 +1719,8 @@ static int rtl8365mb_irq_setup(struct realtek_priv *priv)
 		goto out_put_node;
 	}
 
-	priv->irqdomain = irq_domain_add_linear(intc, priv->num_ports,
-						&rtl8365mb_irqdomain_ops, priv);
+	priv->irqdomain = irq_domain_create_linear(of_fwnode_handle(intc), priv->num_ports,
+						   &rtl8365mb_irqdomain_ops, priv);
 	if (!priv->irqdomain) {
 		dev_err(priv->dev, "failed to add irq domain\n");
 		ret = -ENOMEM;
@@ -2134,6 +2134,8 @@ static const struct dsa_switch_ops rtl8365mb_switch_ops = {
 	.get_stats64 = rtl8365mb_get_stats64,
 	.port_change_mtu = rtl8365mb_port_change_mtu,
 	.port_max_mtu = rtl8365mb_port_max_mtu,
+	.port_hsr_join = dsa_port_simple_hsr_join,
+	.port_hsr_leave = dsa_port_simple_hsr_leave,
 };
 
 static const struct realtek_ops rtl8365mb_ops = {
diff --git a/drivers/net/dsa/realtek/rtl8366rb-leds.c b/drivers/net/dsa/realtek/rtl8366rb-leds.c
new file mode 100644
index 000000000000..99c890681ae6
--- /dev/null
+++ b/drivers/net/dsa/realtek/rtl8366rb-leds.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bitops.h>
+#include <linux/regmap.h>
+#include <net/dsa.h>
+#include "rtl83xx.h"
+#include "rtl8366rb.h"
+
+static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port)
+{
+	switch (led_group) {
+	case 0:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	case 1:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	case 2:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	case 3:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	default:
+		return 0;
+	}
+}
+
+static int rb8366rb_get_port_led(struct rtl8366rb_led *led)
+{
+	struct realtek_priv *priv = led->priv;
+	u8 led_group = led->led_group;
+	u8 port_num = led->port_num;
+	int ret;
+	u32 val;
+
+	ret = regmap_read(priv->map, RTL8366RB_LED_X_X_CTRL_REG(led_group),
+			  &val);
+	if (ret) {
+		dev_err(priv->dev, "error reading LED on port %d group %d\n",
+			led_group, port_num);
+		return ret;
+	}
+
+	return !!(val & rtl8366rb_led_group_port_mask(led_group, port_num));
+}
+
+static int rb8366rb_set_port_led(struct rtl8366rb_led *led, bool enable)
+{
+	struct realtek_priv *priv = led->priv;
+	u8 led_group = led->led_group;
+	u8 port_num = led->port_num;
+	int ret;
+
+	ret = regmap_update_bits(priv->map,
+				 RTL8366RB_LED_X_X_CTRL_REG(led_group),
+				 rtl8366rb_led_group_port_mask(led_group,
+							       port_num),
+				 enable ? 0xffff : 0);
+	if (ret) {
+		dev_err(priv->dev, "error updating LED on port %d group %d\n",
+			led_group, port_num);
+		return ret;
+	}
+
+	/* Change the LED group to manual controlled LEDs if required */
+	ret = rb8366rb_set_ledgroup_mode(priv, led_group,
+					 RTL8366RB_LEDGROUP_FORCE);
+
+	if (ret) {
+		dev_err(priv->dev, "error updating LED GROUP group %d\n",
+			led_group);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int
+rtl8366rb_cled_brightness_set_blocking(struct led_classdev *ldev,
+				       enum led_brightness brightness)
+{
+	struct rtl8366rb_led *led = container_of(ldev, struct rtl8366rb_led,
+						 cdev);
+
+	return rb8366rb_set_port_led(led, brightness == LED_ON);
+}
+
+static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp,
+			       struct fwnode_handle *led_fwnode)
+{
+	struct rtl8366rb *rb = priv->chip_data;
+	struct led_init_data init_data = { };
+	enum led_default_state state;
+	struct rtl8366rb_led *led;
+	u32 led_group;
+	int ret;
+
+	ret = fwnode_property_read_u32(led_fwnode, "reg", &led_group);
+	if (ret)
+		return ret;
+
+	if (led_group >= RTL8366RB_NUM_LEDGROUPS) {
+		dev_warn(priv->dev, "Invalid LED reg %d defined for port %d",
+			 led_group, dp->index);
+		return -EINVAL;
+	}
+
+	led = &rb->leds[dp->index][led_group];
+	led->port_num = dp->index;
+	led->led_group = led_group;
+	led->priv = priv;
+
+	state = led_init_default_state_get(led_fwnode);
+	switch (state) {
+	case LEDS_DEFSTATE_ON:
+		led->cdev.brightness = 1;
+		rb8366rb_set_port_led(led, 1);
+		break;
+	case LEDS_DEFSTATE_KEEP:
+		led->cdev.brightness =
+			rb8366rb_get_port_led(led);
+		break;
+	case LEDS_DEFSTATE_OFF:
+	default:
+		led->cdev.brightness = 0;
+		rb8366rb_set_port_led(led, 0);
+	}
+
+	led->cdev.max_brightness = 1;
+	led->cdev.brightness_set_blocking =
+		rtl8366rb_cled_brightness_set_blocking;
+	init_data.fwnode = led_fwnode;
+	init_data.devname_mandatory = true;
+
+	init_data.devicename = kasprintf(GFP_KERNEL, "Realtek-%d:0%d:%d",
+					 dp->ds->index, dp->index, led_group);
+	if (!init_data.devicename)
+		return -ENOMEM;
+
+	ret = devm_led_classdev_register_ext(priv->dev, &led->cdev, &init_data);
+	if (ret) {
+		dev_warn(priv->dev, "Failed to init LED %d for port %d",
+			 led_group, dp->index);
+		return ret;
+	}
+
+	return 0;
+}
+
+int rtl8366rb_setup_leds(struct realtek_priv *priv)
+{
+	struct dsa_switch *ds = &priv->ds;
+	struct device_node *leds_np;
+	struct dsa_port *dp;
+	int ret = 0;
+
+	dsa_switch_for_each_port(dp, ds) {
+		if (!dp->dn)
+			continue;
+
+		leds_np = of_get_child_by_name(dp->dn, "leds");
+		if (!leds_np) {
+			dev_dbg(priv->dev, "No leds defined for port %d",
+				dp->index);
+			continue;
+		}
+
+		for_each_child_of_node_scoped(leds_np, led_np) {
+			ret = rtl8366rb_setup_led(priv, dp,
+						  of_fwnode_handle(led_np));
+			if (ret)
+				break;
+		}
+
+		of_node_put(leds_np);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c
index 23374178a176..d96ae72b0a5c 100644
--- a/drivers/net/dsa/realtek/rtl8366rb.c
+++ b/drivers/net/dsa/realtek/rtl8366rb.c
@@ -21,16 +21,13 @@
 #include <linux/irqchip/chained_irq.h>
 #include <linux/of_irq.h>
 #include <linux/regmap.h>
+#include <linux/string_choices.h>
 
 #include "realtek.h"
 #include "realtek-smi.h"
 #include "realtek-mdio.h"
 #include "rtl83xx.h"
-
-#define RTL8366RB_PORT_NUM_CPU		5
-#define RTL8366RB_NUM_PORTS		6
-#define RTL8366RB_PHY_NO_MAX		4
-#define RTL8366RB_PHY_ADDR_MAX		31
+#include "rtl8366rb.h"
 
 /* Switch Global Configuration register */
 #define RTL8366RB_SGCR				0x0000
@@ -175,39 +172,6 @@
  */
 #define RTL8366RB_VLAN_INGRESS_CTRL2_REG	0x037f
 
-/* LED control registers */
-/* The LED blink rate is global; it is used by all triggers in all groups. */
-#define RTL8366RB_LED_BLINKRATE_REG		0x0430
-#define RTL8366RB_LED_BLINKRATE_MASK		0x0007
-#define RTL8366RB_LED_BLINKRATE_28MS		0x0000
-#define RTL8366RB_LED_BLINKRATE_56MS		0x0001
-#define RTL8366RB_LED_BLINKRATE_84MS		0x0002
-#define RTL8366RB_LED_BLINKRATE_111MS		0x0003
-#define RTL8366RB_LED_BLINKRATE_222MS		0x0004
-#define RTL8366RB_LED_BLINKRATE_446MS		0x0005
-
-/* LED trigger event for each group */
-#define RTL8366RB_LED_CTRL_REG			0x0431
-#define RTL8366RB_LED_CTRL_OFFSET(led_group)	\
-	(4 * (led_group))
-#define RTL8366RB_LED_CTRL_MASK(led_group)	\
-	(0xf << RTL8366RB_LED_CTRL_OFFSET(led_group))
-
-/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only
- * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is
- * RTL8366RB_LEDGROUP_FORCE. Otherwise, it is ignored.
- */
-#define RTL8366RB_LED_0_1_CTRL_REG		0x0432
-#define RTL8366RB_LED_2_3_CTRL_REG		0x0433
-#define RTL8366RB_LED_X_X_CTRL_REG(led_group)	\
-	((led_group) <= 1 ? \
-		RTL8366RB_LED_0_1_CTRL_REG : \
-		RTL8366RB_LED_2_3_CTRL_REG)
-#define RTL8366RB_LED_0_X_CTRL_MASK		GENMASK(5, 0)
-#define RTL8366RB_LED_X_1_CTRL_MASK		GENMASK(11, 6)
-#define RTL8366RB_LED_2_X_CTRL_MASK		GENMASK(5, 0)
-#define RTL8366RB_LED_X_3_CTRL_MASK		GENMASK(11, 6)
-
 #define RTL8366RB_MIB_COUNT			33
 #define RTL8366RB_GLOBAL_MIB_COUNT		1
 #define RTL8366RB_MIB_COUNTER_PORT_OFFSET	0x0050
@@ -243,7 +207,6 @@
 #define RTL8366RB_PORT_STATUS_AN_MASK		0x0080
 
 #define RTL8366RB_NUM_VLANS		16
-#define RTL8366RB_NUM_LEDGROUPS		4
 #define RTL8366RB_NUM_VIDS		4096
 #define RTL8366RB_PRIORITYMAX		7
 #define RTL8366RB_NUM_FIDS		8
@@ -350,46 +313,6 @@
 #define RTL8366RB_GREEN_FEATURE_TX	BIT(0)
 #define RTL8366RB_GREEN_FEATURE_RX	BIT(2)
 
-enum rtl8366_ledgroup_mode {
-	RTL8366RB_LEDGROUP_OFF			= 0x0,
-	RTL8366RB_LEDGROUP_DUP_COL		= 0x1,
-	RTL8366RB_LEDGROUP_LINK_ACT		= 0x2,
-	RTL8366RB_LEDGROUP_SPD1000		= 0x3,
-	RTL8366RB_LEDGROUP_SPD100		= 0x4,
-	RTL8366RB_LEDGROUP_SPD10		= 0x5,
-	RTL8366RB_LEDGROUP_SPD1000_ACT		= 0x6,
-	RTL8366RB_LEDGROUP_SPD100_ACT		= 0x7,
-	RTL8366RB_LEDGROUP_SPD10_ACT		= 0x8,
-	RTL8366RB_LEDGROUP_SPD100_10_ACT	= 0x9,
-	RTL8366RB_LEDGROUP_FIBER		= 0xa,
-	RTL8366RB_LEDGROUP_AN_FAULT		= 0xb,
-	RTL8366RB_LEDGROUP_LINK_RX		= 0xc,
-	RTL8366RB_LEDGROUP_LINK_TX		= 0xd,
-	RTL8366RB_LEDGROUP_MASTER		= 0xe,
-	RTL8366RB_LEDGROUP_FORCE		= 0xf,
-
-	__RTL8366RB_LEDGROUP_MODE_MAX
-};
-
-struct rtl8366rb_led {
-	u8 port_num;
-	u8 led_group;
-	struct realtek_priv *priv;
-	struct led_classdev cdev;
-};
-
-/**
- * struct rtl8366rb - RTL8366RB-specific data
- * @max_mtu: per-port max MTU setting
- * @pvid_enabled: if PVID is set for respective port
- * @leds: per-port and per-ledgroup led info
- */
-struct rtl8366rb {
-	unsigned int max_mtu[RTL8366RB_NUM_PORTS];
-	bool pvid_enabled[RTL8366RB_NUM_PORTS];
-	struct rtl8366rb_led leds[RTL8366RB_NUM_PORTS][RTL8366RB_NUM_LEDGROUPS];
-};
-
 static struct rtl8366_mib_counter rtl8366rb_mib_counters[] = {
 	{ 0,  0, 4, "IfInOctets"				},
 	{ 0,  4, 4, "EtherStatsOctets"				},
@@ -627,10 +550,8 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_priv *priv)
 		dev_err(priv->dev, "unable to request irq: %d\n", ret);
 		goto out_put_node;
 	}
-	priv->irqdomain = irq_domain_add_linear(intc,
-						RTL8366RB_NUM_INTERRUPT,
-						&rtl8366rb_irqdomain_ops,
-						priv);
+	priv->irqdomain = irq_domain_create_linear(of_fwnode_handle(intc), RTL8366RB_NUM_INTERRUPT,
+						   &rtl8366rb_irqdomain_ops, priv);
 	if (!priv->irqdomain) {
 		dev_err(priv->dev, "failed to create IRQ domain\n");
 		ret = -EINVAL;
@@ -830,9 +751,10 @@ static int rtl8366rb_jam_table(const struct rtl8366rb_jam_tbl_entry *jam_table,
 	return 0;
 }
 
-static int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
-				      u8 led_group,
-				      enum rtl8366_ledgroup_mode mode)
+/* This code is used also with LEDs disabled */
+int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
+			       u8 led_group,
+			       enum rtl8366_ledgroup_mode mode)
 {
 	int ret;
 	u32 val;
@@ -849,144 +771,7 @@ static int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
 	return 0;
 }
 
-static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port)
-{
-	switch (led_group) {
-	case 0:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	case 1:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	case 2:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	case 3:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	default:
-		return 0;
-	}
-}
-
-static int rb8366rb_get_port_led(struct rtl8366rb_led *led)
-{
-	struct realtek_priv *priv = led->priv;
-	u8 led_group = led->led_group;
-	u8 port_num = led->port_num;
-	int ret;
-	u32 val;
-
-	ret = regmap_read(priv->map, RTL8366RB_LED_X_X_CTRL_REG(led_group),
-			  &val);
-	if (ret) {
-		dev_err(priv->dev, "error reading LED on port %d group %d\n",
-			led_group, port_num);
-		return ret;
-	}
-
-	return !!(val & rtl8366rb_led_group_port_mask(led_group, port_num));
-}
-
-static int rb8366rb_set_port_led(struct rtl8366rb_led *led, bool enable)
-{
-	struct realtek_priv *priv = led->priv;
-	u8 led_group = led->led_group;
-	u8 port_num = led->port_num;
-	int ret;
-
-	ret = regmap_update_bits(priv->map,
-				 RTL8366RB_LED_X_X_CTRL_REG(led_group),
-				 rtl8366rb_led_group_port_mask(led_group,
-							       port_num),
-				 enable ? 0xffff : 0);
-	if (ret) {
-		dev_err(priv->dev, "error updating LED on port %d group %d\n",
-			led_group, port_num);
-		return ret;
-	}
-
-	/* Change the LED group to manual controlled LEDs if required */
-	ret = rb8366rb_set_ledgroup_mode(priv, led_group,
-					 RTL8366RB_LEDGROUP_FORCE);
-
-	if (ret) {
-		dev_err(priv->dev, "error updating LED GROUP group %d\n",
-			led_group);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int
-rtl8366rb_cled_brightness_set_blocking(struct led_classdev *ldev,
-				       enum led_brightness brightness)
-{
-	struct rtl8366rb_led *led = container_of(ldev, struct rtl8366rb_led,
-						 cdev);
-
-	return rb8366rb_set_port_led(led, brightness == LED_ON);
-}
-
-static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp,
-			       struct fwnode_handle *led_fwnode)
-{
-	struct rtl8366rb *rb = priv->chip_data;
-	struct led_init_data init_data = { };
-	enum led_default_state state;
-	struct rtl8366rb_led *led;
-	u32 led_group;
-	int ret;
-
-	ret = fwnode_property_read_u32(led_fwnode, "reg", &led_group);
-	if (ret)
-		return ret;
-
-	if (led_group >= RTL8366RB_NUM_LEDGROUPS) {
-		dev_warn(priv->dev, "Invalid LED reg %d defined for port %d",
-			 led_group, dp->index);
-		return -EINVAL;
-	}
-
-	led = &rb->leds[dp->index][led_group];
-	led->port_num = dp->index;
-	led->led_group = led_group;
-	led->priv = priv;
-
-	state = led_init_default_state_get(led_fwnode);
-	switch (state) {
-	case LEDS_DEFSTATE_ON:
-		led->cdev.brightness = 1;
-		rb8366rb_set_port_led(led, 1);
-		break;
-	case LEDS_DEFSTATE_KEEP:
-		led->cdev.brightness =
-			rb8366rb_get_port_led(led);
-		break;
-	case LEDS_DEFSTATE_OFF:
-	default:
-		led->cdev.brightness = 0;
-		rb8366rb_set_port_led(led, 0);
-	}
-
-	led->cdev.max_brightness = 1;
-	led->cdev.brightness_set_blocking =
-		rtl8366rb_cled_brightness_set_blocking;
-	init_data.fwnode = led_fwnode;
-	init_data.devname_mandatory = true;
-
-	init_data.devicename = kasprintf(GFP_KERNEL, "Realtek-%d:0%d:%d",
-					 dp->ds->index, dp->index, led_group);
-	if (!init_data.devicename)
-		return -ENOMEM;
-
-	ret = devm_led_classdev_register_ext(priv->dev, &led->cdev, &init_data);
-	if (ret) {
-		dev_warn(priv->dev, "Failed to init LED %d for port %d",
-			 led_group, dp->index);
-		return ret;
-	}
-
-	return 0;
-}
-
+/* This code is used also with LEDs disabled */
 static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv)
 {
 	int ret = 0;
@@ -1007,38 +792,6 @@ static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv)
 	return ret;
 }
 
-static int rtl8366rb_setup_leds(struct realtek_priv *priv)
-{
-	struct dsa_switch *ds = &priv->ds;
-	struct device_node *leds_np;
-	struct dsa_port *dp;
-	int ret = 0;
-
-	dsa_switch_for_each_port(dp, ds) {
-		if (!dp->dn)
-			continue;
-
-		leds_np = of_get_child_by_name(dp->dn, "leds");
-		if (!leds_np) {
-			dev_dbg(priv->dev, "No leds defined for port %d",
-				dp->index);
-			continue;
-		}
-
-		for_each_child_of_node_scoped(leds_np, led_np) {
-			ret = rtl8366rb_setup_led(priv, dp,
-						  of_fwnode_handle(led_np));
-			if (ret)
-				break;
-		}
-
-		of_node_put(leds_np);
-		if (ret)
-			return ret;
-	}
-	return 0;
-}
-
 static int rtl8366rb_setup(struct dsa_switch *ds)
 {
 	struct realtek_priv *priv = ds->priv;
@@ -1522,7 +1275,7 @@ static int rtl8366rb_vlan_filtering(struct dsa_switch *ds, int port,
 	rb = priv->chip_data;
 
 	dev_dbg(priv->dev, "port %d: %s VLAN filtering\n", port,
-		vlan_filtering ? "enable" : "disable");
+		str_enable_disable(vlan_filtering));
 
 	/* If the port is not in the member set, the frame will be dropped */
 	ret = regmap_update_bits(priv->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG,
@@ -1884,7 +1637,7 @@ static bool rtl8366rb_is_vlan_valid(struct realtek_priv *priv, unsigned int vlan
 
 static int rtl8366rb_enable_vlan(struct realtek_priv *priv, bool enable)
 {
-	dev_dbg(priv->dev, "%s VLAN\n", enable ? "enable" : "disable");
+	dev_dbg(priv->dev, "%s VLAN\n", str_enable_disable(enable));
 	return regmap_update_bits(priv->map,
 				  RTL8366RB_SGCR, RTL8366RB_SGCR_EN_VLAN,
 				  enable ? RTL8366RB_SGCR_EN_VLAN : 0);
@@ -1892,7 +1645,7 @@ static int rtl8366rb_enable_vlan(struct realtek_priv *priv, bool enable)
 
 static int rtl8366rb_enable_vlan4k(struct realtek_priv *priv, bool enable)
 {
-	dev_dbg(priv->dev, "%s VLAN 4k\n", enable ? "enable" : "disable");
+	dev_dbg(priv->dev, "%s VLAN 4k\n", str_enable_disable(enable));
 	return regmap_update_bits(priv->map, RTL8366RB_SGCR,
 				  RTL8366RB_SGCR_EN_VLAN_4KTB,
 				  enable ? RTL8366RB_SGCR_EN_VLAN_4KTB : 0);
@@ -2062,6 +1815,8 @@ static const struct dsa_switch_ops rtl8366rb_switch_ops = {
 	.port_fast_age = rtl8366rb_port_fast_age,
 	.port_change_mtu = rtl8366rb_change_mtu,
 	.port_max_mtu = rtl8366rb_max_mtu,
+	.port_hsr_join = dsa_port_simple_hsr_join,
+	.port_hsr_leave = dsa_port_simple_hsr_leave,
 };
 
 static const struct realtek_ops rtl8366rb_ops = {
diff --git a/drivers/net/dsa/realtek/rtl8366rb.h b/drivers/net/dsa/realtek/rtl8366rb.h
new file mode 100644
index 000000000000..685ff3275faa
--- /dev/null
+++ b/drivers/net/dsa/realtek/rtl8366rb.h
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _RTL8366RB_H
+#define _RTL8366RB_H
+
+#include "realtek.h"
+
+#define RTL8366RB_PORT_NUM_CPU		5
+#define RTL8366RB_NUM_PORTS		6
+#define RTL8366RB_PHY_NO_MAX		4
+#define RTL8366RB_NUM_LEDGROUPS		4
+#define RTL8366RB_PHY_ADDR_MAX		31
+
+/* LED control registers */
+/* The LED blink rate is global; it is used by all triggers in all groups. */
+#define RTL8366RB_LED_BLINKRATE_REG		0x0430
+#define RTL8366RB_LED_BLINKRATE_MASK		0x0007
+#define RTL8366RB_LED_BLINKRATE_28MS		0x0000
+#define RTL8366RB_LED_BLINKRATE_56MS		0x0001
+#define RTL8366RB_LED_BLINKRATE_84MS		0x0002
+#define RTL8366RB_LED_BLINKRATE_111MS		0x0003
+#define RTL8366RB_LED_BLINKRATE_222MS		0x0004
+#define RTL8366RB_LED_BLINKRATE_446MS		0x0005
+
+/* LED trigger event for each group */
+#define RTL8366RB_LED_CTRL_REG			0x0431
+#define RTL8366RB_LED_CTRL_OFFSET(led_group)	\
+	(4 * (led_group))
+#define RTL8366RB_LED_CTRL_MASK(led_group)	\
+	(0xf << RTL8366RB_LED_CTRL_OFFSET(led_group))
+
+/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only
+ * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is
+ * RTL8366RB_LEDGROUP_FORCE. Otherwise, it is ignored.
+ */
+#define RTL8366RB_LED_0_1_CTRL_REG		0x0432
+#define RTL8366RB_LED_2_3_CTRL_REG		0x0433
+#define RTL8366RB_LED_X_X_CTRL_REG(led_group)	\
+	((led_group) <= 1 ? \
+		RTL8366RB_LED_0_1_CTRL_REG : \
+		RTL8366RB_LED_2_3_CTRL_REG)
+#define RTL8366RB_LED_0_X_CTRL_MASK		GENMASK(5, 0)
+#define RTL8366RB_LED_X_1_CTRL_MASK		GENMASK(11, 6)
+#define RTL8366RB_LED_2_X_CTRL_MASK		GENMASK(5, 0)
+#define RTL8366RB_LED_X_3_CTRL_MASK		GENMASK(11, 6)
+
+enum rtl8366_ledgroup_mode {
+	RTL8366RB_LEDGROUP_OFF			= 0x0,
+	RTL8366RB_LEDGROUP_DUP_COL		= 0x1,
+	RTL8366RB_LEDGROUP_LINK_ACT		= 0x2,
+	RTL8366RB_LEDGROUP_SPD1000		= 0x3,
+	RTL8366RB_LEDGROUP_SPD100		= 0x4,
+	RTL8366RB_LEDGROUP_SPD10		= 0x5,
+	RTL8366RB_LEDGROUP_SPD1000_ACT		= 0x6,
+	RTL8366RB_LEDGROUP_SPD100_ACT		= 0x7,
+	RTL8366RB_LEDGROUP_SPD10_ACT		= 0x8,
+	RTL8366RB_LEDGROUP_SPD100_10_ACT	= 0x9,
+	RTL8366RB_LEDGROUP_FIBER		= 0xa,
+	RTL8366RB_LEDGROUP_AN_FAULT		= 0xb,
+	RTL8366RB_LEDGROUP_LINK_RX		= 0xc,
+	RTL8366RB_LEDGROUP_LINK_TX		= 0xd,
+	RTL8366RB_LEDGROUP_MASTER		= 0xe,
+	RTL8366RB_LEDGROUP_FORCE		= 0xf,
+
+	__RTL8366RB_LEDGROUP_MODE_MAX
+};
+
+#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS)
+
+struct rtl8366rb_led {
+	u8 port_num;
+	u8 led_group;
+	struct realtek_priv *priv;
+	struct led_classdev cdev;
+};
+
+int rtl8366rb_setup_leds(struct realtek_priv *priv);
+
+#else
+
+static inline int rtl8366rb_setup_leds(struct realtek_priv *priv)
+{
+	return 0;
+}
+
+#endif /* IS_ENABLED(CONFIG_LEDS_CLASS) */
+
+/**
+ * struct rtl8366rb - RTL8366RB-specific data
+ * @max_mtu: per-port max MTU setting
+ * @pvid_enabled: if PVID is set for respective port
+ * @leds: per-port and per-ledgroup led info
+ */
+struct rtl8366rb {
+	unsigned int max_mtu[RTL8366RB_NUM_PORTS];
+	bool pvid_enabled[RTL8366RB_NUM_PORTS];
+#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS)
+	struct rtl8366rb_led leds[RTL8366RB_NUM_PORTS][RTL8366RB_NUM_LEDGROUPS];
+#endif
+};
+
+/* This code is used also with LEDs disabled */
+int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
+			       u8 led_group,
+			       enum rtl8366_ledgroup_mode mode);
+
+#endif /* _RTL8366RB_H */
diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c
index 66974379334a..4d857e3be10b 100644
--- a/drivers/net/dsa/rzn1_a5psw.c
+++ b/drivers/net/dsa/rzn1_a5psw.c
@@ -337,8 +337,9 @@ static void a5psw_port_rx_block_set(struct a5psw *a5psw, int port, bool block)
 static void a5psw_flooding_set_resolution(struct a5psw *a5psw, int port,
 					  bool set)
 {
-	u8 offsets[] = {A5PSW_UCAST_DEF_MASK, A5PSW_BCAST_DEF_MASK,
-			A5PSW_MCAST_DEF_MASK};
+	static const u8 offsets[] = {
+		A5PSW_UCAST_DEF_MASK, A5PSW_BCAST_DEF_MASK, A5PSW_MCAST_DEF_MASK
+	};
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(offsets); i++)
@@ -1034,6 +1035,8 @@ static const struct dsa_switch_ops a5psw_switch_ops = {
 	.port_fdb_add = a5psw_port_fdb_add,
 	.port_fdb_del = a5psw_port_fdb_del,
 	.port_fdb_dump = a5psw_port_fdb_dump,
+	.port_hsr_join = dsa_port_simple_hsr_join,
+	.port_hsr_leave = dsa_port_simple_hsr_leave,
 };
 
 static int a5psw_mdio_wait_busy(struct a5psw *a5psw)
@@ -1226,40 +1229,30 @@ static int a5psw_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	a5psw->hclk = devm_clk_get(dev, "hclk");
+	a5psw->hclk = devm_clk_get_enabled(dev, "hclk");
 	if (IS_ERR(a5psw->hclk)) {
 		dev_err(dev, "failed get hclk clock\n");
 		ret = PTR_ERR(a5psw->hclk);
 		goto free_pcs;
 	}
 
-	a5psw->clk = devm_clk_get(dev, "clk");
+	a5psw->clk = devm_clk_get_enabled(dev, "clk");
 	if (IS_ERR(a5psw->clk)) {
 		dev_err(dev, "failed get clk_switch clock\n");
 		ret = PTR_ERR(a5psw->clk);
 		goto free_pcs;
 	}
 
-	ret = clk_prepare_enable(a5psw->clk);
-	if (ret)
-		goto free_pcs;
-
-	ret = clk_prepare_enable(a5psw->hclk);
-	if (ret)
-		goto clk_disable;
-
-	mdio = of_get_child_by_name(dev->of_node, "mdio");
-	if (of_device_is_available(mdio)) {
+	mdio = of_get_available_child_by_name(dev->of_node, "mdio");
+	if (mdio) {
 		ret = a5psw_probe_mdio(a5psw, mdio);
+		of_node_put(mdio);
 		if (ret) {
-			of_node_put(mdio);
 			dev_err(dev, "Failed to register MDIO: %d\n", ret);
-			goto hclk_disable;
+			goto free_pcs;
 		}
 	}
 
-	of_node_put(mdio);
-
 	ds = &a5psw->ds;
 	ds->dev = dev;
 	ds->num_ports = A5PSW_PORTS_NUM;
@@ -1270,15 +1263,11 @@ static int a5psw_probe(struct platform_device *pdev)
 	ret = dsa_register_switch(ds);
 	if (ret) {
 		dev_err(dev, "Failed to register DSA switch: %d\n", ret);
-		goto hclk_disable;
+		goto free_pcs;
 	}
 
 	return 0;
 
-hclk_disable:
-	clk_disable_unprepare(a5psw->hclk);
-clk_disable:
-	clk_disable_unprepare(a5psw->clk);
 free_pcs:
 	a5psw_pcs_free(a5psw);
 
@@ -1294,8 +1283,6 @@ static void a5psw_remove(struct platform_device *pdev)
 
 	dsa_unregister_switch(&a5psw->ds);
 	a5psw_pcs_free(a5psw);
-	clk_disable_unprepare(a5psw->hclk);
-	clk_disable_unprepare(a5psw->clk);
 }
 
 static void a5psw_shutdown(struct platform_device *pdev)
diff --git a/drivers/net/dsa/sja1105/sja1105_ethtool.c b/drivers/net/dsa/sja1105/sja1105_ethtool.c
index 2ea64b1d026d..84d7d3f66bd0 100644
--- a/drivers/net/dsa/sja1105/sja1105_ethtool.c
+++ b/drivers/net/dsa/sja1105/sja1105_ethtool.c
@@ -571,6 +571,9 @@ void sja1105_get_ethtool_stats(struct dsa_switch *ds, int port, u64 *data)
 		max_ctr = __MAX_SJA1105PQRS_PORT_COUNTER;
 
 	for (i = 0; i < max_ctr; i++) {
+		if (!strlen(sja1105_port_counters[i].name))
+			continue;
+
 		rc = sja1105_port_counter_read(priv, port, i, &data[k++]);
 		if (rc) {
 			dev_err(ds->dev,
@@ -596,8 +599,12 @@ void sja1105_get_strings(struct dsa_switch *ds, int port,
 	else
 		max_ctr = __MAX_SJA1105PQRS_PORT_COUNTER;
 
-	for (i = 0; i < max_ctr; i++)
+	for (i = 0; i < max_ctr; i++) {
+		if (!strlen(sja1105_port_counters[i].name))
+			continue;
+
 		ethtool_puts(&data, sja1105_port_counters[i].name);
+	}
 }
 
 int sja1105_get_sset_count(struct dsa_switch *ds, int port, int sset)
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index f8454f3b6f9c..aa2145cf29a6 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1302,14 +1302,7 @@ static int sja1105_set_port_speed(struct sja1105_private *priv, int port,
 	 * table, since this will be used for the clocking setup, and we no
 	 * longer need to store it in the static config (already told hardware
 	 * we want auto during upload phase).
-	 * Actually for the SGMII port, the MAC is fixed at 1 Gbps and
-	 * we need to configure the PCS only (if even that).
 	 */
-	if (priv->phy_mode[port] == PHY_INTERFACE_MODE_SGMII)
-		speed = priv->info->port_speed[SJA1105_SPEED_1000MBPS];
-	else if (priv->phy_mode[port] == PHY_INTERFACE_MODE_2500BASEX)
-		speed = priv->info->port_speed[SJA1105_SPEED_2500MBPS];
-
 	mac[port].speed = speed;
 
 	return 0;
@@ -2081,6 +2074,7 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port,
 	switch (state) {
 	case BR_STATE_DISABLED:
 	case BR_STATE_BLOCKING:
+	case BR_STATE_LISTENING:
 		/* From UM10944 description of DRPDTAG (why put this there?):
 		 * "Management traffic flows to the port regardless of the state
 		 * of the INGRESS flag". So BPDUs are still be allowed to pass.
@@ -2090,11 +2084,6 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port,
 		mac[port].egress    = false;
 		mac[port].dyn_learn = false;
 		break;
-	case BR_STATE_LISTENING:
-		mac[port].ingress   = true;
-		mac[port].egress    = false;
-		mac[port].dyn_learn = false;
-		break;
 	case BR_STATE_LEARNING:
 		mac[port].ingress   = true;
 		mac[port].egress    = false;
diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c
index 84b7169f2974..8d535c033cef 100644
--- a/drivers/net/dsa/sja1105/sja1105_mdio.c
+++ b/drivers/net/dsa/sja1105/sja1105_mdio.c
@@ -468,13 +468,10 @@ int sja1105_mdiobus_register(struct dsa_switch *ds)
 	if (rc)
 		return rc;
 
-	mdio_node = of_get_child_by_name(switch_node, "mdios");
+	mdio_node = of_get_available_child_by_name(switch_node, "mdios");
 	if (!mdio_node)
 		return 0;
 
-	if (!of_device_is_available(mdio_node))
-		goto out_put_mdio_node;
-
 	if (regs->mdio_100base_tx != SJA1105_RSV_ADDR) {
 		rc = sja1105_mdiobus_base_tx_register(priv, mdio_node);
 		if (rc)
@@ -487,7 +484,6 @@ int sja1105_mdiobus_register(struct dsa_switch *ds)
 			goto err_free_base_tx_mdiobus;
 	}
 
-out_put_mdio_node:
 	of_node_put(mdio_node);
 
 	return 0;
diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c
index a1f4ca6ad888..fefe46e2a5e6 100644
--- a/drivers/net/dsa/sja1105/sja1105_ptp.c
+++ b/drivers/net/dsa/sja1105/sja1105_ptp.c
@@ -58,56 +58,60 @@ enum sja1105_ptp_clk_mode {
 #define ptp_data_to_sja1105(d) \
 		container_of((d), struct sja1105_private, ptp_data)
 
-int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr)
+int sja1105_hwtstamp_set(struct dsa_switch *ds, int port,
+			 struct kernel_hwtstamp_config *config,
+			 struct netlink_ext_ack *extack)
 {
 	struct sja1105_private *priv = ds->priv;
-	struct hwtstamp_config config;
+	unsigned long hwts_tx_en, hwts_rx_en;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	hwts_tx_en = priv->hwts_tx_en;
+	hwts_rx_en = priv->hwts_rx_en;
 
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
-		priv->hwts_tx_en &= ~BIT(port);
+		hwts_tx_en &= ~BIT(port);
 		break;
 	case HWTSTAMP_TX_ON:
-		priv->hwts_tx_en |= BIT(port);
+		hwts_tx_en |= BIT(port);
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
-		priv->hwts_rx_en &= ~BIT(port);
+		hwts_rx_en &= ~BIT(port);
 		break;
-	default:
-		priv->hwts_rx_en |= BIT(port);
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+		hwts_rx_en |= BIT(port);
 		break;
+	default:
+		return -ERANGE;
 	}
 
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	priv->hwts_tx_en = hwts_tx_en;
+	priv->hwts_rx_en = hwts_rx_en;
+
 	return 0;
 }
 
-int sja1105_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr)
+int sja1105_hwtstamp_get(struct dsa_switch *ds, int port,
+			 struct kernel_hwtstamp_config *config)
 {
 	struct sja1105_private *priv = ds->priv;
-	struct hwtstamp_config config;
 
-	config.flags = 0;
+	config->flags = 0;
 	if (priv->hwts_tx_en & BIT(port))
-		config.tx_type = HWTSTAMP_TX_ON;
+		config->tx_type = HWTSTAMP_TX_ON;
 	else
-		config.tx_type = HWTSTAMP_TX_OFF;
+		config->tx_type = HWTSTAMP_TX_OFF;
 	if (priv->hwts_rx_en & BIT(port))
-		config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 	else
-		config.rx_filter = HWTSTAMP_FILTER_NONE;
+		config->rx_filter = HWTSTAMP_FILTER_NONE;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 int sja1105_get_ts_info(struct dsa_switch *ds, int port,
@@ -727,10 +731,6 @@ static int sja1105_per_out_enable(struct sja1105_private *priv,
 	if (perout->index != 0)
 		return -EOPNOTSUPP;
 
-	/* Reject requests with unsupported flags */
-	if (perout->flags)
-		return -EOPNOTSUPP;
-
 	mutex_lock(&ptp_data->lock);
 
 	rc = sja1105_change_ptp_clk_pin_func(priv, PTP_PF_PEROUT);
@@ -810,13 +810,6 @@ static int sja1105_extts_enable(struct sja1105_private *priv,
 	if (extts->index != 0)
 		return -EOPNOTSUPP;
 
-	/* Reject requests with unsupported flags */
-	if (extts->flags & ~(PTP_ENABLE_FEATURE |
-			     PTP_RISING_EDGE |
-			     PTP_FALLING_EDGE |
-			     PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	/* We can only enable time stamping on both edges, sadly. */
 	if ((extts->flags & PTP_STRICT_FLAGS) &&
 	    (extts->flags & PTP_ENABLE_FEATURE) &&
@@ -832,7 +825,7 @@ static int sja1105_extts_enable(struct sja1105_private *priv,
 	if (on)
 		sja1105_ptp_extts_setup_timer(&priv->ptp_data);
 	else
-		del_timer_sync(&priv->ptp_data.extts_timer);
+		timer_delete_sync(&priv->ptp_data.extts_timer);
 
 	return 0;
 }
@@ -902,6 +895,9 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds)
 		.n_pins		= 1,
 		.n_ext_ts	= 1,
 		.n_per_out	= 1,
+		.supported_extts_flags = PTP_RISING_EDGE |
+					 PTP_FALLING_EDGE |
+					 PTP_STRICT_FLAGS,
 	};
 
 	/* Only used on SJA1105 */
@@ -929,7 +925,7 @@ void sja1105_ptp_clock_unregister(struct dsa_switch *ds)
 	if (IS_ERR_OR_NULL(ptp_data->clock))
 		return;
 
-	del_timer_sync(&ptp_data->extts_timer);
+	timer_delete_sync(&ptp_data->extts_timer);
 	ptp_cancel_worker_sync(ptp_data->clock);
 	skb_queue_purge(&ptp_data->skb_txtstamp_queue);
 	skb_queue_purge(&ptp_data->skb_rxtstamp_queue);
diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h
index 8add2bd5f728..325e3777ea07 100644
--- a/drivers/net/dsa/sja1105/sja1105_ptp.h
+++ b/drivers/net/dsa/sja1105/sja1105_ptp.h
@@ -112,9 +112,12 @@ bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port,
 void sja1105_port_txtstamp(struct dsa_switch *ds, int port,
 			   struct sk_buff *skb);
 
-int sja1105_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr);
+int sja1105_hwtstamp_get(struct dsa_switch *ds, int port,
+			 struct kernel_hwtstamp_config *config);
 
-int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr);
+int sja1105_hwtstamp_set(struct dsa_switch *ds, int port,
+			 struct kernel_hwtstamp_config *config,
+			 struct netlink_ext_ack *extack);
 
 int __sja1105_ptp_gettimex(struct dsa_switch *ds, u64 *ns,
 			   struct ptp_system_timestamp *sts);
diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c
index 3d790f8c6f4d..ffece8a400a6 100644
--- a/drivers/net/dsa/sja1105/sja1105_static_config.c
+++ b/drivers/net/dsa/sja1105/sja1105_static_config.c
@@ -1917,8 +1917,10 @@ int sja1105_table_delete_entry(struct sja1105_table *table, int i)
 	if (i > table->entry_count)
 		return -ERANGE;
 
-	memmove(entries + i * entry_size, entries + (i + 1) * entry_size,
-		(table->entry_count - i) * entry_size);
+	if (i + 1 < table->entry_count) {
+		memmove(entries + i * entry_size, entries + (i + 1) * entry_size,
+			(table->entry_count - i - 1) * entry_size);
+	}
 
 	table->entry_count--;
 
diff --git a/drivers/net/dsa/sja1105/sja1105_tas.c b/drivers/net/dsa/sja1105/sja1105_tas.c
index d7818710bc02..d5949d2c3e71 100644
--- a/drivers/net/dsa/sja1105/sja1105_tas.c
+++ b/drivers/net/dsa/sja1105/sja1105_tas.c
@@ -775,9 +775,8 @@ static void sja1105_tas_state_machine(struct work_struct *work)
 		base_time_ts = ns_to_timespec64(base_time);
 		now_ts = ns_to_timespec64(now);
 
-		dev_dbg(ds->dev, "OPER base time %lld.%09ld (now %lld.%09ld)\n",
-			base_time_ts.tv_sec, base_time_ts.tv_nsec,
-			now_ts.tv_sec, now_ts.tv_nsec);
+		dev_dbg(ds->dev, "OPER base time %ptSp (now %ptSp)\n",
+			&base_time_ts, &now_ts);
 
 		break;
 
@@ -798,8 +797,7 @@ static void sja1105_tas_state_machine(struct work_struct *work)
 		if (now < tas_data->oper_base_time) {
 			/* TAS has not started yet */
 			diff = ns_to_timespec64(tas_data->oper_base_time - now);
-			dev_dbg(ds->dev, "time to start: [%lld.%09ld]",
-				diff.tv_sec, diff.tv_nsec);
+			dev_dbg(ds->dev, "time to start: [%ptSp]", &diff);
 			break;
 		}
 
diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
index f18aa321053d..9d31b8258268 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -2258,14 +2258,14 @@ static int vsc73xx_gpio_get(struct gpio_chip *chip, unsigned int offset)
 	return !!(val & BIT(offset));
 }
 
-static void vsc73xx_gpio_set(struct gpio_chip *chip, unsigned int offset,
-			     int val)
+static int vsc73xx_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			    int val)
 {
 	struct vsc73xx *vsc = gpiochip_get_data(chip);
 	u32 tmp = val ? BIT(offset) : 0;
 
-	vsc73xx_update_bits(vsc, VSC73XX_BLOCK_SYSTEM, 0,
-			    VSC73XX_GPIO, BIT(offset), tmp);
+	return vsc73xx_update_bits(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+				   VSC73XX_GPIO, BIT(offset), tmp);
 }
 
 static int vsc73xx_gpio_direction_output(struct gpio_chip *chip,
diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c
index 4dbcc49a9e52..0a05f4156ef4 100644
--- a/drivers/net/dsa/xrs700x/xrs700x.c
+++ b/drivers/net/dsa/xrs700x/xrs700x.c
@@ -566,6 +566,7 @@ static int xrs700x_hsr_join(struct dsa_switch *ds, int port,
 	struct xrs700x *priv = ds->priv;
 	struct net_device *user;
 	int ret, i, hsr_pair[2];
+	enum hsr_port_type type;
 	enum hsr_version ver;
 	bool fwd = false;
 
@@ -589,6 +590,16 @@ static int xrs700x_hsr_join(struct dsa_switch *ds, int port,
 		return -EOPNOTSUPP;
 	}
 
+	ret = hsr_get_port_type(hsr, dsa_to_port(ds, port)->user, &type);
+	if (ret)
+		return ret;
+
+	if (type != HSR_PT_SLAVE_A && type != HSR_PT_SLAVE_B) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Only HSR slave ports can be offloaded");
+		return -EOPNOTSUPP;
+	}
+
 	dsa_hsr_foreach_port(dp, ds, hsr) {
 		if (dp->index != port) {
 			partner = dp;
diff --git a/drivers/net/dsa/yt921x.c b/drivers/net/dsa/yt921x.c
new file mode 100644
index 000000000000..1c511f5dc6ab
--- /dev/null
+++ b/drivers/net/dsa/yt921x.c
@@ -0,0 +1,3006 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Driver for Motorcomm YT921x Switch
+ *
+ * Should work on YT9213/YT9214/YT9215/YT9218, but only tested on YT9215+SGMII,
+ * be sure to do your own checks before porting to another chip.
+ *
+ * Copyright (c) 2025 David Yang
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/if_bridge.h>
+#include <linux/if_hsr.h>
+#include <linux/if_vlan.h>
+#include <linux/iopoll.h>
+#include <linux/mdio.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+
+#include <net/dsa.h>
+
+#include "yt921x.h"
+
+struct yt921x_mib_desc {
+	unsigned int size;
+	unsigned int offset;
+	const char *name;
+};
+
+#define MIB_DESC(_size, _offset, _name) \
+	{_size, _offset, _name}
+
+/* Must agree with yt921x_mib
+ *
+ * Unstructured fields (name != NULL) will appear in get_ethtool_stats(),
+ * structured go to their *_stats() methods, but we need their sizes and offsets
+ * to perform 32bit MIB overflow wraparound.
+ */
+static const struct yt921x_mib_desc yt921x_mib_descs[] = {
+	MIB_DESC(1, YT921X_MIB_DATA_RX_BROADCAST, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_RX_PAUSE, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_RX_MULTICAST, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_RX_CRC_ERR, NULL),
+
+	MIB_DESC(1, YT921X_MIB_DATA_RX_ALIGN_ERR, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_RX_UNDERSIZE_ERR, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_RX_FRAG_ERR, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_64, NULL),
+
+	MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_65_TO_127, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_128_TO_255, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_256_TO_511, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_512_TO_1023, NULL),
+
+	MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_1024_TO_1518, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_1519_TO_MAX, NULL),
+	MIB_DESC(2, YT921X_MIB_DATA_RX_GOOD_BYTES, NULL),
+
+	MIB_DESC(2, YT921X_MIB_DATA_RX_BAD_BYTES, "RxBadBytes"),
+	MIB_DESC(1, YT921X_MIB_DATA_RX_OVERSIZE_ERR, NULL),
+
+	MIB_DESC(1, YT921X_MIB_DATA_RX_DROPPED, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_BROADCAST, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_PAUSE, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_MULTICAST, NULL),
+
+	MIB_DESC(1, YT921X_MIB_DATA_TX_UNDERSIZE_ERR, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_64, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_65_TO_127, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_128_TO_255, NULL),
+
+	MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_256_TO_511, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_512_TO_1023, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_1024_TO_1518, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_1519_TO_MAX, NULL),
+
+	MIB_DESC(2, YT921X_MIB_DATA_TX_GOOD_BYTES, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_COLLISION, NULL),
+
+	MIB_DESC(1, YT921X_MIB_DATA_TX_EXCESSIVE_COLLISION, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_MULTIPLE_COLLISION, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_SINGLE_COLLISION, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_PKT, NULL),
+
+	MIB_DESC(1, YT921X_MIB_DATA_TX_DEFERRED, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_LATE_COLLISION, NULL),
+	MIB_DESC(1, YT921X_MIB_DATA_RX_OAM, "RxOAM"),
+	MIB_DESC(1, YT921X_MIB_DATA_TX_OAM, "TxOAM"),
+};
+
+struct yt921x_info {
+	const char *name;
+	u16 major;
+	/* Unknown, seems to be plain enumeration */
+	u8 mode;
+	u8 extmode;
+	/* Ports with integral GbE PHYs, not including MCU Port 10 */
+	u16 internal_mask;
+	/* TODO: see comments in yt921x_dsa_phylink_get_caps() */
+	u16 external_mask;
+};
+
+#define YT921X_PORT_MASK_INTn(port)	BIT(port)
+#define YT921X_PORT_MASK_INT0_n(n)	GENMASK((n) - 1, 0)
+#define YT921X_PORT_MASK_EXT0		BIT(8)
+#define YT921X_PORT_MASK_EXT1		BIT(9)
+
+static const struct yt921x_info yt921x_infos[] = {
+	{
+		"YT9215SC", YT9215_MAJOR, 1, 0,
+		YT921X_PORT_MASK_INT0_n(5),
+		YT921X_PORT_MASK_EXT0 | YT921X_PORT_MASK_EXT1,
+	},
+	{
+		"YT9215S", YT9215_MAJOR, 2, 0,
+		YT921X_PORT_MASK_INT0_n(5),
+		YT921X_PORT_MASK_EXT0 | YT921X_PORT_MASK_EXT1,
+	},
+	{
+		"YT9215RB", YT9215_MAJOR, 3, 0,
+		YT921X_PORT_MASK_INT0_n(5),
+		YT921X_PORT_MASK_EXT0 | YT921X_PORT_MASK_EXT1,
+	},
+	{
+		"YT9214NB", YT9215_MAJOR, 3, 2,
+		YT921X_PORT_MASK_INTn(1) | YT921X_PORT_MASK_INTn(3),
+		YT921X_PORT_MASK_EXT0 | YT921X_PORT_MASK_EXT1,
+	},
+	{
+		"YT9213NB", YT9215_MAJOR, 3, 3,
+		YT921X_PORT_MASK_INTn(1) | YT921X_PORT_MASK_INTn(3),
+		YT921X_PORT_MASK_EXT1,
+	},
+	{
+		"YT9218N", YT9218_MAJOR, 0, 0,
+		YT921X_PORT_MASK_INT0_n(8),
+		0,
+	},
+	{
+		"YT9218MB", YT9218_MAJOR, 1, 0,
+		YT921X_PORT_MASK_INT0_n(8),
+		YT921X_PORT_MASK_EXT0 | YT921X_PORT_MASK_EXT1,
+	},
+	{}
+};
+
+#define YT921X_NAME	"yt921x"
+
+#define YT921X_VID_UNWARE	4095
+
+#define YT921X_POLL_SLEEP_US	10000
+#define YT921X_POLL_TIMEOUT_US	100000
+
+/* The interval should be small enough to avoid overflow of 32bit MIBs.
+ *
+ * Until we can read MIBs from stats64 call directly (i.e. sleep
+ * there), we have to poll stats more frequently then it is actually needed.
+ * For overflow protection, normally, 100 sec interval should have been OK.
+ */
+#define YT921X_STATS_INTERVAL_JIFFIES	(3 * HZ)
+
+struct yt921x_reg_mdio {
+	struct mii_bus *bus;
+	int addr;
+	/* SWITCH_ID_1 / SWITCH_ID_0 of the device
+	 *
+	 * This is a way to multiplex multiple devices on the same MII phyaddr
+	 * and should be configurable in DT. However, MDIO core simply doesn't
+	 * allow multiple devices over one reg addr, so this is a fixed value
+	 * for now until a solution is found.
+	 *
+	 * Keep this because we need switchid to form MII regaddrs anyway.
+	 */
+	unsigned char switchid;
+};
+
+/* TODO: SPI/I2C */
+
+#define to_yt921x_priv(_ds) container_of_const(_ds, struct yt921x_priv, ds)
+#define to_device(priv) ((priv)->ds.dev)
+
+static int yt921x_reg_read(struct yt921x_priv *priv, u32 reg, u32 *valp)
+{
+	WARN_ON(!mutex_is_locked(&priv->reg_lock));
+
+	return priv->reg_ops->read(priv->reg_ctx, reg, valp);
+}
+
+static int yt921x_reg_write(struct yt921x_priv *priv, u32 reg, u32 val)
+{
+	WARN_ON(!mutex_is_locked(&priv->reg_lock));
+
+	return priv->reg_ops->write(priv->reg_ctx, reg, val);
+}
+
+static int
+yt921x_reg_wait(struct yt921x_priv *priv, u32 reg, u32 mask, u32 *valp)
+{
+	u32 val;
+	int res;
+	int ret;
+
+	ret = read_poll_timeout(yt921x_reg_read, res,
+				res || (val & mask) == *valp,
+				YT921X_POLL_SLEEP_US, YT921X_POLL_TIMEOUT_US,
+				false, priv, reg, &val);
+	if (ret)
+		return ret;
+	if (res)
+		return res;
+
+	*valp = val;
+	return 0;
+}
+
+static int
+yt921x_reg_update_bits(struct yt921x_priv *priv, u32 reg, u32 mask, u32 val)
+{
+	int res;
+	u32 v;
+	u32 u;
+
+	res = yt921x_reg_read(priv, reg, &v);
+	if (res)
+		return res;
+
+	u = v;
+	u &= ~mask;
+	u |= val;
+	if (u == v)
+		return 0;
+
+	return yt921x_reg_write(priv, reg, u);
+}
+
+static int yt921x_reg_set_bits(struct yt921x_priv *priv, u32 reg, u32 mask)
+{
+	return yt921x_reg_update_bits(priv, reg, 0, mask);
+}
+
+static int yt921x_reg_clear_bits(struct yt921x_priv *priv, u32 reg, u32 mask)
+{
+	return yt921x_reg_update_bits(priv, reg, mask, 0);
+}
+
+static int
+yt921x_reg_toggle_bits(struct yt921x_priv *priv, u32 reg, u32 mask, bool set)
+{
+	return yt921x_reg_update_bits(priv, reg, mask, !set ? 0 : mask);
+}
+
+/* Some registers, like VLANn_CTRL, should always be written in 64-bit, even if
+ * you are to write only the lower / upper 32 bits.
+ *
+ * There is no such restriction for reading, but we still provide 64-bit read
+ * wrappers so that we always handle u64 values.
+ */
+
+static int yt921x_reg64_read(struct yt921x_priv *priv, u32 reg, u64 *valp)
+{
+	u32 lo;
+	u32 hi;
+	int res;
+
+	res = yt921x_reg_read(priv, reg, &lo);
+	if (res)
+		return res;
+	res = yt921x_reg_read(priv, reg + 4, &hi);
+	if (res)
+		return res;
+
+	*valp = ((u64)hi << 32) | lo;
+	return 0;
+}
+
+static int yt921x_reg64_write(struct yt921x_priv *priv, u32 reg, u64 val)
+{
+	int res;
+
+	res = yt921x_reg_write(priv, reg, (u32)val);
+	if (res)
+		return res;
+	return yt921x_reg_write(priv, reg + 4, (u32)(val >> 32));
+}
+
+static int
+yt921x_reg64_update_bits(struct yt921x_priv *priv, u32 reg, u64 mask, u64 val)
+{
+	int res;
+	u64 v;
+	u64 u;
+
+	res = yt921x_reg64_read(priv, reg, &v);
+	if (res)
+		return res;
+
+	u = v;
+	u &= ~mask;
+	u |= val;
+	if (u == v)
+		return 0;
+
+	return yt921x_reg64_write(priv, reg, u);
+}
+
+static int yt921x_reg64_clear_bits(struct yt921x_priv *priv, u32 reg, u64 mask)
+{
+	return yt921x_reg64_update_bits(priv, reg, mask, 0);
+}
+
+static int yt921x_reg_mdio_read(void *context, u32 reg, u32 *valp)
+{
+	struct yt921x_reg_mdio *mdio = context;
+	struct mii_bus *bus = mdio->bus;
+	int addr = mdio->addr;
+	u32 reg_addr;
+	u32 reg_data;
+	u32 val;
+	int res;
+
+	/* Hold the mdio bus lock to avoid (un)locking for 4 times */
+	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+	reg_addr = YT921X_SMI_SWITCHID(mdio->switchid) | YT921X_SMI_ADDR |
+		   YT921X_SMI_READ;
+	res = __mdiobus_write(bus, addr, reg_addr, (u16)(reg >> 16));
+	if (res)
+		goto end;
+	res = __mdiobus_write(bus, addr, reg_addr, (u16)reg);
+	if (res)
+		goto end;
+
+	reg_data = YT921X_SMI_SWITCHID(mdio->switchid) | YT921X_SMI_DATA |
+		   YT921X_SMI_READ;
+	res = __mdiobus_read(bus, addr, reg_data);
+	if (res < 0)
+		goto end;
+	val = (u16)res;
+	res = __mdiobus_read(bus, addr, reg_data);
+	if (res < 0)
+		goto end;
+	val = (val << 16) | (u16)res;
+
+	*valp = val;
+	res = 0;
+
+end:
+	mutex_unlock(&bus->mdio_lock);
+	return res;
+}
+
+static int yt921x_reg_mdio_write(void *context, u32 reg, u32 val)
+{
+	struct yt921x_reg_mdio *mdio = context;
+	struct mii_bus *bus = mdio->bus;
+	int addr = mdio->addr;
+	u32 reg_addr;
+	u32 reg_data;
+	int res;
+
+	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+	reg_addr = YT921X_SMI_SWITCHID(mdio->switchid) | YT921X_SMI_ADDR |
+		   YT921X_SMI_WRITE;
+	res = __mdiobus_write(bus, addr, reg_addr, (u16)(reg >> 16));
+	if (res)
+		goto end;
+	res = __mdiobus_write(bus, addr, reg_addr, (u16)reg);
+	if (res)
+		goto end;
+
+	reg_data = YT921X_SMI_SWITCHID(mdio->switchid) | YT921X_SMI_DATA |
+		   YT921X_SMI_WRITE;
+	res = __mdiobus_write(bus, addr, reg_data, (u16)(val >> 16));
+	if (res)
+		goto end;
+	res = __mdiobus_write(bus, addr, reg_data, (u16)val);
+	if (res)
+		goto end;
+
+	res = 0;
+
+end:
+	mutex_unlock(&bus->mdio_lock);
+	return res;
+}
+
+static const struct yt921x_reg_ops yt921x_reg_ops_mdio = {
+	.read = yt921x_reg_mdio_read,
+	.write = yt921x_reg_mdio_write,
+};
+
+/* TODO: SPI/I2C */
+
+static int yt921x_intif_wait(struct yt921x_priv *priv)
+{
+	u32 val = 0;
+
+	return yt921x_reg_wait(priv, YT921X_INT_MBUS_OP, YT921X_MBUS_OP_START,
+			       &val);
+}
+
+static int
+yt921x_intif_read(struct yt921x_priv *priv, int port, int reg, u16 *valp)
+{
+	struct device *dev = to_device(priv);
+	u32 mask;
+	u32 ctrl;
+	u32 val;
+	int res;
+
+	res = yt921x_intif_wait(priv);
+	if (res)
+		return res;
+
+	mask = YT921X_MBUS_CTRL_PORT_M | YT921X_MBUS_CTRL_REG_M |
+	       YT921X_MBUS_CTRL_OP_M;
+	ctrl = YT921X_MBUS_CTRL_PORT(port) | YT921X_MBUS_CTRL_REG(reg) |
+	       YT921X_MBUS_CTRL_READ;
+	res = yt921x_reg_update_bits(priv, YT921X_INT_MBUS_CTRL, mask, ctrl);
+	if (res)
+		return res;
+	res = yt921x_reg_write(priv, YT921X_INT_MBUS_OP, YT921X_MBUS_OP_START);
+	if (res)
+		return res;
+
+	res = yt921x_intif_wait(priv);
+	if (res)
+		return res;
+	res = yt921x_reg_read(priv, YT921X_INT_MBUS_DIN, &val);
+	if (res)
+		return res;
+
+	if ((u16)val != val)
+		dev_info(dev,
+			 "%s: port %d, reg 0x%x: Expected u16, got 0x%08x\n",
+			 __func__, port, reg, val);
+	*valp = (u16)val;
+	return 0;
+}
+
+static int
+yt921x_intif_write(struct yt921x_priv *priv, int port, int reg, u16 val)
+{
+	u32 mask;
+	u32 ctrl;
+	int res;
+
+	res = yt921x_intif_wait(priv);
+	if (res)
+		return res;
+
+	mask = YT921X_MBUS_CTRL_PORT_M | YT921X_MBUS_CTRL_REG_M |
+	       YT921X_MBUS_CTRL_OP_M;
+	ctrl = YT921X_MBUS_CTRL_PORT(port) | YT921X_MBUS_CTRL_REG(reg) |
+	       YT921X_MBUS_CTRL_WRITE;
+	res = yt921x_reg_update_bits(priv, YT921X_INT_MBUS_CTRL, mask, ctrl);
+	if (res)
+		return res;
+	res = yt921x_reg_write(priv, YT921X_INT_MBUS_DOUT, val);
+	if (res)
+		return res;
+	res = yt921x_reg_write(priv, YT921X_INT_MBUS_OP, YT921X_MBUS_OP_START);
+	if (res)
+		return res;
+
+	return yt921x_intif_wait(priv);
+}
+
+static int yt921x_mbus_int_read(struct mii_bus *mbus, int port, int reg)
+{
+	struct yt921x_priv *priv = mbus->priv;
+	u16 val;
+	int res;
+
+	if (port >= YT921X_PORT_NUM)
+		return U16_MAX;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_intif_read(priv, port, reg, &val);
+	mutex_unlock(&priv->reg_lock);
+
+	if (res)
+		return res;
+	return val;
+}
+
+static int
+yt921x_mbus_int_write(struct mii_bus *mbus, int port, int reg, u16 data)
+{
+	struct yt921x_priv *priv = mbus->priv;
+	int res;
+
+	if (port >= YT921X_PORT_NUM)
+		return -ENODEV;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_intif_write(priv, port, reg, data);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int
+yt921x_mbus_int_init(struct yt921x_priv *priv, struct device_node *mnp)
+{
+	struct device *dev = to_device(priv);
+	struct mii_bus *mbus;
+	int res;
+
+	mbus = devm_mdiobus_alloc(dev);
+	if (!mbus)
+		return -ENOMEM;
+
+	mbus->name = "YT921x internal MDIO bus";
+	snprintf(mbus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev));
+	mbus->priv = priv;
+	mbus->read = yt921x_mbus_int_read;
+	mbus->write = yt921x_mbus_int_write;
+	mbus->parent = dev;
+	mbus->phy_mask = (u32)~GENMASK(YT921X_PORT_NUM - 1, 0);
+
+	res = devm_of_mdiobus_register(dev, mbus, mnp);
+	if (res)
+		return res;
+
+	priv->mbus_int = mbus;
+
+	return 0;
+}
+
+static int yt921x_extif_wait(struct yt921x_priv *priv)
+{
+	u32 val = 0;
+
+	return yt921x_reg_wait(priv, YT921X_EXT_MBUS_OP, YT921X_MBUS_OP_START,
+			       &val);
+}
+
+static int
+yt921x_extif_read(struct yt921x_priv *priv, int port, int reg, u16 *valp)
+{
+	struct device *dev = to_device(priv);
+	u32 mask;
+	u32 ctrl;
+	u32 val;
+	int res;
+
+	res = yt921x_extif_wait(priv);
+	if (res)
+		return res;
+
+	mask = YT921X_MBUS_CTRL_PORT_M | YT921X_MBUS_CTRL_REG_M |
+	       YT921X_MBUS_CTRL_TYPE_M | YT921X_MBUS_CTRL_OP_M;
+	ctrl = YT921X_MBUS_CTRL_PORT(port) | YT921X_MBUS_CTRL_REG(reg) |
+	       YT921X_MBUS_CTRL_TYPE_C22 | YT921X_MBUS_CTRL_READ;
+	res = yt921x_reg_update_bits(priv, YT921X_EXT_MBUS_CTRL, mask, ctrl);
+	if (res)
+		return res;
+	res = yt921x_reg_write(priv, YT921X_EXT_MBUS_OP, YT921X_MBUS_OP_START);
+	if (res)
+		return res;
+
+	res = yt921x_extif_wait(priv);
+	if (res)
+		return res;
+	res = yt921x_reg_read(priv, YT921X_EXT_MBUS_DIN, &val);
+	if (res)
+		return res;
+
+	if ((u16)val != val)
+		dev_info(dev,
+			 "%s: port %d, reg 0x%x: Expected u16, got 0x%08x\n",
+			 __func__, port, reg, val);
+	*valp = (u16)val;
+	return 0;
+}
+
+static int
+yt921x_extif_write(struct yt921x_priv *priv, int port, int reg, u16 val)
+{
+	u32 mask;
+	u32 ctrl;
+	int res;
+
+	res = yt921x_extif_wait(priv);
+	if (res)
+		return res;
+
+	mask = YT921X_MBUS_CTRL_PORT_M | YT921X_MBUS_CTRL_REG_M |
+	       YT921X_MBUS_CTRL_TYPE_M | YT921X_MBUS_CTRL_OP_M;
+	ctrl = YT921X_MBUS_CTRL_PORT(port) | YT921X_MBUS_CTRL_REG(reg) |
+	       YT921X_MBUS_CTRL_TYPE_C22 | YT921X_MBUS_CTRL_WRITE;
+	res = yt921x_reg_update_bits(priv, YT921X_EXT_MBUS_CTRL, mask, ctrl);
+	if (res)
+		return res;
+	res = yt921x_reg_write(priv, YT921X_EXT_MBUS_DOUT, val);
+	if (res)
+		return res;
+	res = yt921x_reg_write(priv, YT921X_EXT_MBUS_OP, YT921X_MBUS_OP_START);
+	if (res)
+		return res;
+
+	return yt921x_extif_wait(priv);
+}
+
+static int yt921x_mbus_ext_read(struct mii_bus *mbus, int port, int reg)
+{
+	struct yt921x_priv *priv = mbus->priv;
+	u16 val;
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_extif_read(priv, port, reg, &val);
+	mutex_unlock(&priv->reg_lock);
+
+	if (res)
+		return res;
+	return val;
+}
+
+static int
+yt921x_mbus_ext_write(struct mii_bus *mbus, int port, int reg, u16 data)
+{
+	struct yt921x_priv *priv = mbus->priv;
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_extif_write(priv, port, reg, data);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int
+yt921x_mbus_ext_init(struct yt921x_priv *priv, struct device_node *mnp)
+{
+	struct device *dev = to_device(priv);
+	struct mii_bus *mbus;
+	int res;
+
+	mbus = devm_mdiobus_alloc(dev);
+	if (!mbus)
+		return -ENOMEM;
+
+	mbus->name = "YT921x external MDIO bus";
+	snprintf(mbus->id, MII_BUS_ID_SIZE, "%s@ext", dev_name(dev));
+	mbus->priv = priv;
+	/* TODO: c45? */
+	mbus->read = yt921x_mbus_ext_read;
+	mbus->write = yt921x_mbus_ext_write;
+	mbus->parent = dev;
+
+	res = devm_of_mdiobus_register(dev, mbus, mnp);
+	if (res)
+		return res;
+
+	priv->mbus_ext = mbus;
+
+	return 0;
+}
+
+/* Read and handle overflow of 32bit MIBs. MIB buffer must be zeroed before. */
+static int yt921x_read_mib(struct yt921x_priv *priv, int port)
+{
+	struct yt921x_port *pp = &priv->ports[port];
+	struct device *dev = to_device(priv);
+	struct yt921x_mib *mib = &pp->mib;
+	int res = 0;
+
+	/* Reading of yt921x_port::mib is not protected by a lock and it's vain
+	 * to keep its consistency, since we have to read registers one by one
+	 * and there is no way to make a snapshot of MIB stats.
+	 *
+	 * Writing (by this function only) is and should be protected by
+	 * reg_lock.
+	 */
+
+	for (size_t i = 0; i < ARRAY_SIZE(yt921x_mib_descs); i++) {
+		const struct yt921x_mib_desc *desc = &yt921x_mib_descs[i];
+		u32 reg = YT921X_MIBn_DATA0(port) + desc->offset;
+		u64 *valp = &((u64 *)mib)[i];
+		u64 val = *valp;
+		u32 val0;
+		u32 val1;
+
+		res = yt921x_reg_read(priv, reg, &val0);
+		if (res)
+			break;
+
+		if (desc->size <= 1) {
+			if (val < (u32)val)
+				/* overflow */
+				val += (u64)U32_MAX + 1;
+			val &= ~U32_MAX;
+			val |= val0;
+		} else {
+			res = yt921x_reg_read(priv, reg + 4, &val1);
+			if (res)
+				break;
+			val = ((u64)val1 << 32) | val0;
+		}
+
+		WRITE_ONCE(*valp, val);
+	}
+
+	pp->rx_frames = mib->rx_64byte + mib->rx_65_127byte +
+			mib->rx_128_255byte + mib->rx_256_511byte +
+			mib->rx_512_1023byte + mib->rx_1024_1518byte +
+			mib->rx_jumbo;
+	pp->tx_frames = mib->tx_64byte + mib->tx_65_127byte +
+			mib->tx_128_255byte + mib->tx_256_511byte +
+			mib->tx_512_1023byte + mib->tx_1024_1518byte +
+			mib->tx_jumbo;
+
+	if (res)
+		dev_err(dev, "Failed to %s port %d: %i\n", "read stats for",
+			port, res);
+	return res;
+}
+
+static void yt921x_poll_mib(struct work_struct *work)
+{
+	struct yt921x_port *pp = container_of_const(work, struct yt921x_port,
+						    mib_read.work);
+	struct yt921x_priv *priv = (void *)(pp - pp->index) -
+				   offsetof(struct yt921x_priv, ports);
+	unsigned long delay = YT921X_STATS_INTERVAL_JIFFIES;
+	int port = pp->index;
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_read_mib(priv, port);
+	mutex_unlock(&priv->reg_lock);
+	if (res)
+		delay *= 4;
+
+	schedule_delayed_work(&pp->mib_read, delay);
+}
+
+static void
+yt921x_dsa_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+		       uint8_t *data)
+{
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	for (size_t i = 0; i < ARRAY_SIZE(yt921x_mib_descs); i++) {
+		const struct yt921x_mib_desc *desc = &yt921x_mib_descs[i];
+
+		if (desc->name)
+			ethtool_puts(&data, desc->name);
+	}
+}
+
+static void
+yt921x_dsa_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	struct yt921x_port *pp = &priv->ports[port];
+	struct yt921x_mib *mib = &pp->mib;
+	size_t j;
+
+	mutex_lock(&priv->reg_lock);
+	yt921x_read_mib(priv, port);
+	mutex_unlock(&priv->reg_lock);
+
+	j = 0;
+	for (size_t i = 0; i < ARRAY_SIZE(yt921x_mib_descs); i++) {
+		const struct yt921x_mib_desc *desc = &yt921x_mib_descs[i];
+
+		if (!desc->name)
+			continue;
+
+		data[j] = ((u64 *)mib)[i];
+		j++;
+	}
+}
+
+static int yt921x_dsa_get_sset_count(struct dsa_switch *ds, int port, int sset)
+{
+	int cnt = 0;
+
+	if (sset != ETH_SS_STATS)
+		return 0;
+
+	for (size_t i = 0; i < ARRAY_SIZE(yt921x_mib_descs); i++) {
+		const struct yt921x_mib_desc *desc = &yt921x_mib_descs[i];
+
+		if (desc->name)
+			cnt++;
+	}
+
+	return cnt;
+}
+
+static void
+yt921x_dsa_get_eth_mac_stats(struct dsa_switch *ds, int port,
+			     struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	struct yt921x_port *pp = &priv->ports[port];
+	struct yt921x_mib *mib = &pp->mib;
+
+	mutex_lock(&priv->reg_lock);
+	yt921x_read_mib(priv, port);
+	mutex_unlock(&priv->reg_lock);
+
+	mac_stats->FramesTransmittedOK = pp->tx_frames;
+	mac_stats->SingleCollisionFrames = mib->tx_single_collisions;
+	mac_stats->MultipleCollisionFrames = mib->tx_multiple_collisions;
+	mac_stats->FramesReceivedOK = pp->rx_frames;
+	mac_stats->FrameCheckSequenceErrors = mib->rx_crc_errors;
+	mac_stats->AlignmentErrors = mib->rx_alignment_errors;
+	mac_stats->OctetsTransmittedOK = mib->tx_good_bytes;
+	mac_stats->FramesWithDeferredXmissions = mib->tx_deferred;
+	mac_stats->LateCollisions = mib->tx_late_collisions;
+	mac_stats->FramesAbortedDueToXSColls = mib->tx_aborted_errors;
+	/* mac_stats->FramesLostDueToIntMACXmitError */
+	/* mac_stats->CarrierSenseErrors */
+	mac_stats->OctetsReceivedOK = mib->rx_good_bytes;
+	/* mac_stats->FramesLostDueToIntMACRcvError */
+	mac_stats->MulticastFramesXmittedOK = mib->tx_multicast;
+	mac_stats->BroadcastFramesXmittedOK = mib->tx_broadcast;
+	/* mac_stats->FramesWithExcessiveDeferral */
+	mac_stats->MulticastFramesReceivedOK = mib->rx_multicast;
+	mac_stats->BroadcastFramesReceivedOK = mib->rx_broadcast;
+	/* mac_stats->InRangeLengthErrors */
+	/* mac_stats->OutOfRangeLengthField */
+	mac_stats->FrameTooLongErrors = mib->rx_oversize_errors;
+}
+
+static void
+yt921x_dsa_get_eth_ctrl_stats(struct dsa_switch *ds, int port,
+			      struct ethtool_eth_ctrl_stats *ctrl_stats)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	struct yt921x_port *pp = &priv->ports[port];
+	struct yt921x_mib *mib = &pp->mib;
+
+	mutex_lock(&priv->reg_lock);
+	yt921x_read_mib(priv, port);
+	mutex_unlock(&priv->reg_lock);
+
+	ctrl_stats->MACControlFramesTransmitted = mib->tx_pause;
+	ctrl_stats->MACControlFramesReceived = mib->rx_pause;
+	/* ctrl_stats->UnsupportedOpcodesReceived */
+}
+
+static const struct ethtool_rmon_hist_range yt921x_rmon_ranges[] = {
+	{ 0, 64 },
+	{ 65, 127 },
+	{ 128, 255 },
+	{ 256, 511 },
+	{ 512, 1023 },
+	{ 1024, 1518 },
+	{ 1519, YT921X_FRAME_SIZE_MAX },
+	{}
+};
+
+static void
+yt921x_dsa_get_rmon_stats(struct dsa_switch *ds, int port,
+			  struct ethtool_rmon_stats *rmon_stats,
+			  const struct ethtool_rmon_hist_range **ranges)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	struct yt921x_port *pp = &priv->ports[port];
+	struct yt921x_mib *mib = &pp->mib;
+
+	mutex_lock(&priv->reg_lock);
+	yt921x_read_mib(priv, port);
+	mutex_unlock(&priv->reg_lock);
+
+	*ranges = yt921x_rmon_ranges;
+
+	rmon_stats->undersize_pkts = mib->rx_undersize_errors;
+	rmon_stats->oversize_pkts = mib->rx_oversize_errors;
+	rmon_stats->fragments = mib->rx_alignment_errors;
+	/* rmon_stats->jabbers */
+
+	rmon_stats->hist[0] = mib->rx_64byte;
+	rmon_stats->hist[1] = mib->rx_65_127byte;
+	rmon_stats->hist[2] = mib->rx_128_255byte;
+	rmon_stats->hist[3] = mib->rx_256_511byte;
+	rmon_stats->hist[4] = mib->rx_512_1023byte;
+	rmon_stats->hist[5] = mib->rx_1024_1518byte;
+	rmon_stats->hist[6] = mib->rx_jumbo;
+
+	rmon_stats->hist_tx[0] = mib->tx_64byte;
+	rmon_stats->hist_tx[1] = mib->tx_65_127byte;
+	rmon_stats->hist_tx[2] = mib->tx_128_255byte;
+	rmon_stats->hist_tx[3] = mib->tx_256_511byte;
+	rmon_stats->hist_tx[4] = mib->tx_512_1023byte;
+	rmon_stats->hist_tx[5] = mib->tx_1024_1518byte;
+	rmon_stats->hist_tx[6] = mib->tx_jumbo;
+}
+
+static void
+yt921x_dsa_get_stats64(struct dsa_switch *ds, int port,
+		       struct rtnl_link_stats64 *stats)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	struct yt921x_port *pp = &priv->ports[port];
+	struct yt921x_mib *mib = &pp->mib;
+
+	stats->rx_length_errors = mib->rx_undersize_errors +
+				  mib->rx_fragment_errors;
+	stats->rx_over_errors = mib->rx_oversize_errors;
+	stats->rx_crc_errors = mib->rx_crc_errors;
+	stats->rx_frame_errors = mib->rx_alignment_errors;
+	/* stats->rx_fifo_errors */
+	/* stats->rx_missed_errors */
+
+	stats->tx_aborted_errors = mib->tx_aborted_errors;
+	/* stats->tx_carrier_errors */
+	stats->tx_fifo_errors = mib->tx_undersize_errors;
+	/* stats->tx_heartbeat_errors */
+	stats->tx_window_errors = mib->tx_late_collisions;
+
+	stats->rx_packets = pp->rx_frames;
+	stats->tx_packets = pp->tx_frames;
+	stats->rx_bytes = mib->rx_good_bytes - ETH_FCS_LEN * stats->rx_packets;
+	stats->tx_bytes = mib->tx_good_bytes - ETH_FCS_LEN * stats->tx_packets;
+	stats->rx_errors = stats->rx_length_errors + stats->rx_over_errors +
+			   stats->rx_crc_errors + stats->rx_frame_errors;
+	stats->tx_errors = stats->tx_aborted_errors + stats->tx_fifo_errors +
+			   stats->tx_window_errors;
+	stats->rx_dropped = mib->rx_dropped;
+	/* stats->tx_dropped */
+	stats->multicast = mib->rx_multicast;
+	stats->collisions = mib->tx_collisions;
+}
+
+static void
+yt921x_dsa_get_pause_stats(struct dsa_switch *ds, int port,
+			   struct ethtool_pause_stats *pause_stats)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	struct yt921x_port *pp = &priv->ports[port];
+	struct yt921x_mib *mib = &pp->mib;
+
+	mutex_lock(&priv->reg_lock);
+	yt921x_read_mib(priv, port);
+	mutex_unlock(&priv->reg_lock);
+
+	pause_stats->tx_pause_frames = mib->tx_pause;
+	pause_stats->rx_pause_frames = mib->rx_pause;
+}
+
+static int
+yt921x_set_eee(struct yt921x_priv *priv, int port, struct ethtool_keee *e)
+{
+	/* Poor datasheet for EEE operations; don't ask if you are confused */
+
+	bool enable = e->eee_enabled;
+	u16 new_mask;
+	int res;
+
+	/* Enable / disable global EEE */
+	new_mask = priv->eee_ports_mask;
+	new_mask &= ~BIT(port);
+	new_mask |= !enable ? 0 : BIT(port);
+
+	if (!!new_mask != !!priv->eee_ports_mask) {
+		res = yt921x_reg_toggle_bits(priv, YT921X_PON_STRAP_FUNC,
+					     YT921X_PON_STRAP_EEE, !!new_mask);
+		if (res)
+			return res;
+		res = yt921x_reg_toggle_bits(priv, YT921X_PON_STRAP_VAL,
+					     YT921X_PON_STRAP_EEE, !!new_mask);
+		if (res)
+			return res;
+	}
+
+	priv->eee_ports_mask = new_mask;
+
+	/* Enable / disable port EEE */
+	res = yt921x_reg_toggle_bits(priv, YT921X_EEE_CTRL,
+				     YT921X_EEE_CTRL_ENn(port), enable);
+	if (res)
+		return res;
+	res = yt921x_reg_toggle_bits(priv, YT921X_EEEn_VAL(port),
+				     YT921X_EEE_VAL_DATA, enable);
+	if (res)
+		return res;
+
+	return 0;
+}
+
+static int
+yt921x_dsa_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_set_eee(priv, port, e);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int
+yt921x_dsa_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
+{
+	/* Only serves as packet filter, since the frame size is always set to
+	 * maximum after reset
+	 */
+
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	struct dsa_port *dp = dsa_to_port(ds, port);
+	int frame_size;
+	int res;
+
+	frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN;
+	if (dsa_port_is_cpu(dp))
+		frame_size += YT921X_TAG_LEN;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_reg_update_bits(priv, YT921X_MACn_FRAME(port),
+				     YT921X_MAC_FRAME_SIZE_M,
+				     YT921X_MAC_FRAME_SIZE(frame_size));
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int yt921x_dsa_port_max_mtu(struct dsa_switch *ds, int port)
+{
+	/* Only called for user ports, exclude tag len here */
+	return YT921X_FRAME_SIZE_MAX - ETH_HLEN - ETH_FCS_LEN - YT921X_TAG_LEN;
+}
+
+static int
+yt921x_mirror_del(struct yt921x_priv *priv, int port, bool ingress)
+{
+	u32 mask;
+
+	if (ingress)
+		mask = YT921X_MIRROR_IGR_PORTn(port);
+	else
+		mask = YT921X_MIRROR_EGR_PORTn(port);
+	return yt921x_reg_clear_bits(priv, YT921X_MIRROR, mask);
+}
+
+static int
+yt921x_mirror_add(struct yt921x_priv *priv, int port, bool ingress,
+		  int to_local_port, struct netlink_ext_ack *extack)
+{
+	u32 srcs;
+	u32 ctrl;
+	u32 val;
+	u32 dst;
+	int res;
+
+	if (ingress)
+		srcs = YT921X_MIRROR_IGR_PORTn(port);
+	else
+		srcs = YT921X_MIRROR_EGR_PORTn(port);
+	dst = YT921X_MIRROR_PORT(to_local_port);
+
+	res = yt921x_reg_read(priv, YT921X_MIRROR, &val);
+	if (res)
+		return res;
+
+	/* other mirror tasks & different dst port -> conflict */
+	if ((val & ~srcs & (YT921X_MIRROR_EGR_PORTS_M |
+			    YT921X_MIRROR_IGR_PORTS_M)) &&
+	    (val & YT921X_MIRROR_PORT_M) != dst) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Sniffer port is already configured, delete existing rules & retry");
+		return -EBUSY;
+	}
+
+	ctrl = val & ~YT921X_MIRROR_PORT_M;
+	ctrl |= srcs;
+	ctrl |= dst;
+
+	if (ctrl == val)
+		return 0;
+
+	return yt921x_reg_write(priv, YT921X_MIRROR, ctrl);
+}
+
+static void
+yt921x_dsa_port_mirror_del(struct dsa_switch *ds, int port,
+			   struct dsa_mall_mirror_tc_entry *mirror)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	struct device *dev = to_device(priv);
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_mirror_del(priv, port, mirror->ingress);
+	mutex_unlock(&priv->reg_lock);
+
+	if (res)
+		dev_err(dev, "Failed to %s port %d: %i\n", "unmirror",
+			port, res);
+}
+
+static int
+yt921x_dsa_port_mirror_add(struct dsa_switch *ds, int port,
+			   struct dsa_mall_mirror_tc_entry *mirror,
+			   bool ingress, struct netlink_ext_ack *extack)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_mirror_add(priv, port, ingress,
+				mirror->to_local_port, extack);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int yt921x_fdb_wait(struct yt921x_priv *priv, u32 *valp)
+{
+	struct device *dev = to_device(priv);
+	u32 val = YT921X_FDB_RESULT_DONE;
+	int res;
+
+	res = yt921x_reg_wait(priv, YT921X_FDB_RESULT, YT921X_FDB_RESULT_DONE,
+			      &val);
+	if (res) {
+		dev_err(dev, "FDB probably stuck\n");
+		return res;
+	}
+
+	*valp = val;
+	return 0;
+}
+
+static int
+yt921x_fdb_in01(struct yt921x_priv *priv, const unsigned char *addr,
+		u16 vid, u32 ctrl1)
+{
+	u32 ctrl;
+	int res;
+
+	ctrl = (addr[0] << 24) | (addr[1] << 16) | (addr[2] << 8) | addr[3];
+	res = yt921x_reg_write(priv, YT921X_FDB_IN0, ctrl);
+	if (res)
+		return res;
+
+	ctrl = ctrl1 | YT921X_FDB_IO1_FID(vid) | (addr[4] << 8) | addr[5];
+	return yt921x_reg_write(priv, YT921X_FDB_IN1, ctrl);
+}
+
+static int
+yt921x_fdb_has(struct yt921x_priv *priv, const unsigned char *addr, u16 vid,
+	       u16 *indexp)
+{
+	u32 ctrl;
+	u32 val;
+	int res;
+
+	res = yt921x_fdb_in01(priv, addr, vid, 0);
+	if (res)
+		return res;
+
+	ctrl = 0;
+	res = yt921x_reg_write(priv, YT921X_FDB_IN2, ctrl);
+	if (res)
+		return res;
+
+	ctrl = YT921X_FDB_OP_OP_GET_ONE | YT921X_FDB_OP_START;
+	res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl);
+	if (res)
+		return res;
+
+	res = yt921x_fdb_wait(priv, &val);
+	if (res)
+		return res;
+	if (val & YT921X_FDB_RESULT_NOTFOUND) {
+		*indexp = YT921X_FDB_NUM;
+		return 0;
+	}
+
+	*indexp = FIELD_GET(YT921X_FDB_RESULT_INDEX_M, val);
+	return 0;
+}
+
+static int
+yt921x_fdb_read(struct yt921x_priv *priv, unsigned char *addr, u16 *vidp,
+		u16 *ports_maskp, u16 *indexp, u8 *statusp)
+{
+	struct device *dev = to_device(priv);
+	u16 index;
+	u32 data0;
+	u32 data1;
+	u32 data2;
+	u32 val;
+	int res;
+
+	res = yt921x_fdb_wait(priv, &val);
+	if (res)
+		return res;
+	if (val & YT921X_FDB_RESULT_NOTFOUND) {
+		*ports_maskp = 0;
+		return 0;
+	}
+	index = FIELD_GET(YT921X_FDB_RESULT_INDEX_M, val);
+
+	res = yt921x_reg_read(priv, YT921X_FDB_OUT1, &data1);
+	if (res)
+		return res;
+	if ((data1 & YT921X_FDB_IO1_STATUS_M) ==
+	    YT921X_FDB_IO1_STATUS_INVALID) {
+		*ports_maskp = 0;
+		return 0;
+	}
+
+	res = yt921x_reg_read(priv, YT921X_FDB_OUT0, &data0);
+	if (res)
+		return res;
+	res = yt921x_reg_read(priv, YT921X_FDB_OUT2, &data2);
+	if (res)
+		return res;
+
+	addr[0] = data0 >> 24;
+	addr[1] = data0 >> 16;
+	addr[2] = data0 >> 8;
+	addr[3] = data0;
+	addr[4] = data1 >> 8;
+	addr[5] = data1;
+	*vidp = FIELD_GET(YT921X_FDB_IO1_FID_M, data1);
+	*indexp = index;
+	*ports_maskp = FIELD_GET(YT921X_FDB_IO2_EGR_PORTS_M, data2);
+	*statusp = FIELD_GET(YT921X_FDB_IO1_STATUS_M, data1);
+
+	dev_dbg(dev,
+		"%s: index 0x%x, mac %02x:%02x:%02x:%02x:%02x:%02x, vid %d, ports 0x%x, status %d\n",
+		__func__, *indexp, addr[0], addr[1], addr[2], addr[3],
+		addr[4], addr[5], *vidp, *ports_maskp, *statusp);
+	return 0;
+}
+
+static int
+yt921x_fdb_dump(struct yt921x_priv *priv, u16 ports_mask,
+		dsa_fdb_dump_cb_t *cb, void *data)
+{
+	unsigned char addr[ETH_ALEN];
+	u8 status;
+	u16 pmask;
+	u16 index;
+	u32 ctrl;
+	u16 vid;
+	int res;
+
+	ctrl = YT921X_FDB_OP_INDEX(0) | YT921X_FDB_OP_MODE_INDEX |
+	       YT921X_FDB_OP_OP_GET_ONE | YT921X_FDB_OP_START;
+	res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl);
+	if (res)
+		return res;
+	res = yt921x_fdb_read(priv, addr, &vid, &pmask, &index, &status);
+	if (res)
+		return res;
+	if ((pmask & ports_mask) && !is_multicast_ether_addr(addr)) {
+		res = cb(addr, vid,
+			 status == YT921X_FDB_ENTRY_STATUS_STATIC, data);
+		if (res)
+			return res;
+	}
+
+	ctrl = YT921X_FDB_IO2_EGR_PORTS(ports_mask);
+	res = yt921x_reg_write(priv, YT921X_FDB_IN2, ctrl);
+	if (res)
+		return res;
+
+	index = 0;
+	do {
+		ctrl = YT921X_FDB_OP_INDEX(index) | YT921X_FDB_OP_MODE_INDEX |
+		       YT921X_FDB_OP_NEXT_TYPE_UCAST_PORT |
+		       YT921X_FDB_OP_OP_GET_NEXT | YT921X_FDB_OP_START;
+		res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl);
+		if (res)
+			return res;
+
+		res = yt921x_fdb_read(priv, addr, &vid, &pmask, &index,
+				      &status);
+		if (res)
+			return res;
+		if (!pmask)
+			break;
+
+		if ((pmask & ports_mask) && !is_multicast_ether_addr(addr)) {
+			res = cb(addr, vid,
+				 status == YT921X_FDB_ENTRY_STATUS_STATIC,
+				 data);
+			if (res)
+				return res;
+		}
+
+		/* Never call GET_NEXT with 4095, otherwise it will hang
+		 * forever until a reset!
+		 */
+	} while (index < YT921X_FDB_NUM - 1);
+
+	return 0;
+}
+
+static int
+yt921x_fdb_flush_raw(struct yt921x_priv *priv, u16 ports_mask, u16 vid,
+		     bool flush_static)
+{
+	u32 ctrl;
+	u32 val;
+	int res;
+
+	if (vid < 4096) {
+		ctrl = YT921X_FDB_IO1_FID(vid);
+		res = yt921x_reg_write(priv, YT921X_FDB_IN1, ctrl);
+		if (res)
+			return res;
+	}
+
+	ctrl = YT921X_FDB_IO2_EGR_PORTS(ports_mask);
+	res = yt921x_reg_write(priv, YT921X_FDB_IN2, ctrl);
+	if (res)
+		return res;
+
+	ctrl = YT921X_FDB_OP_OP_FLUSH | YT921X_FDB_OP_START;
+	if (vid >= 4096)
+		ctrl |= YT921X_FDB_OP_FLUSH_PORT;
+	else
+		ctrl |= YT921X_FDB_OP_FLUSH_PORT_VID;
+	if (flush_static)
+		ctrl |= YT921X_FDB_OP_FLUSH_STATIC;
+	res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl);
+	if (res)
+		return res;
+
+	res = yt921x_fdb_wait(priv, &val);
+	if (res)
+		return res;
+
+	return 0;
+}
+
+static int
+yt921x_fdb_flush_port(struct yt921x_priv *priv, int port, bool flush_static)
+{
+	return yt921x_fdb_flush_raw(priv, BIT(port), 4096, flush_static);
+}
+
+static int
+yt921x_fdb_add_index_in12(struct yt921x_priv *priv, u16 index, u16 ctrl1,
+			  u16 ctrl2)
+{
+	u32 ctrl;
+	u32 val;
+	int res;
+
+	res = yt921x_reg_write(priv, YT921X_FDB_IN1, ctrl1);
+	if (res)
+		return res;
+	res = yt921x_reg_write(priv, YT921X_FDB_IN2, ctrl2);
+	if (res)
+		return res;
+
+	ctrl = YT921X_FDB_OP_INDEX(index) | YT921X_FDB_OP_MODE_INDEX |
+	       YT921X_FDB_OP_OP_ADD | YT921X_FDB_OP_START;
+	res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl);
+	if (res)
+		return res;
+
+	return yt921x_fdb_wait(priv, &val);
+}
+
+static int
+yt921x_fdb_add(struct yt921x_priv *priv, const unsigned char *addr, u16 vid,
+	       u16 ports_mask)
+{
+	u32 ctrl;
+	u32 val;
+	int res;
+
+	ctrl = YT921X_FDB_IO1_STATUS_STATIC;
+	res = yt921x_fdb_in01(priv, addr, vid, ctrl);
+	if (res)
+		return res;
+
+	ctrl = YT921X_FDB_IO2_EGR_PORTS(ports_mask);
+	res = yt921x_reg_write(priv, YT921X_FDB_IN2, ctrl);
+	if (res)
+		return res;
+
+	ctrl = YT921X_FDB_OP_OP_ADD | YT921X_FDB_OP_START;
+	res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl);
+	if (res)
+		return res;
+
+	return yt921x_fdb_wait(priv, &val);
+}
+
+static int
+yt921x_fdb_leave(struct yt921x_priv *priv, const unsigned char *addr,
+		 u16 vid, u16 ports_mask)
+{
+	u16 index;
+	u32 ctrl1;
+	u32 ctrl2;
+	u32 ctrl;
+	u32 val2;
+	u32 val;
+	int res;
+
+	/* Check for presence */
+	res = yt921x_fdb_has(priv, addr, vid, &index);
+	if (res)
+		return res;
+	if (index >= YT921X_FDB_NUM)
+		return 0;
+
+	/* Check if action required */
+	res = yt921x_reg_read(priv, YT921X_FDB_OUT2, &val2);
+	if (res)
+		return res;
+
+	ctrl2 = val2 & ~YT921X_FDB_IO2_EGR_PORTS(ports_mask);
+	if (ctrl2 == val2)
+		return 0;
+	if (!(ctrl2 & YT921X_FDB_IO2_EGR_PORTS_M)) {
+		ctrl = YT921X_FDB_OP_OP_DEL | YT921X_FDB_OP_START;
+		res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl);
+		if (res)
+			return res;
+
+		return yt921x_fdb_wait(priv, &val);
+	}
+
+	res = yt921x_reg_read(priv, YT921X_FDB_OUT1, &ctrl1);
+	if (res)
+		return res;
+
+	return yt921x_fdb_add_index_in12(priv, index, ctrl1, ctrl2);
+}
+
+static int
+yt921x_fdb_join(struct yt921x_priv *priv, const unsigned char *addr, u16 vid,
+		u16 ports_mask)
+{
+	u16 index;
+	u32 ctrl1;
+	u32 ctrl2;
+	u32 val1;
+	u32 val2;
+	int res;
+
+	/* Check for presence */
+	res = yt921x_fdb_has(priv, addr, vid, &index);
+	if (res)
+		return res;
+	if (index >= YT921X_FDB_NUM)
+		return yt921x_fdb_add(priv, addr, vid, ports_mask);
+
+	/* Check if action required */
+	res = yt921x_reg_read(priv, YT921X_FDB_OUT1, &val1);
+	if (res)
+		return res;
+	res = yt921x_reg_read(priv, YT921X_FDB_OUT2, &val2);
+	if (res)
+		return res;
+
+	ctrl1 = val1 & ~YT921X_FDB_IO1_STATUS_M;
+	ctrl1 |= YT921X_FDB_IO1_STATUS_STATIC;
+	ctrl2 = val2 | YT921X_FDB_IO2_EGR_PORTS(ports_mask);
+	if (ctrl1 == val1 && ctrl2 == val2)
+		return 0;
+
+	return yt921x_fdb_add_index_in12(priv, index, ctrl1, ctrl2);
+}
+
+static int
+yt921x_dsa_port_fdb_dump(struct dsa_switch *ds, int port,
+			 dsa_fdb_dump_cb_t *cb, void *data)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	/* Hardware FDB is shared for fdb and mdb, "bridge fdb show"
+	 * only wants to see unicast
+	 */
+	res = yt921x_fdb_dump(priv, BIT(port), cb, data);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static void yt921x_dsa_port_fast_age(struct dsa_switch *ds, int port)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	struct device *dev = to_device(priv);
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_fdb_flush_port(priv, port, false);
+	mutex_unlock(&priv->reg_lock);
+
+	if (res)
+		dev_err(dev, "Failed to %s port %d: %i\n", "clear FDB for",
+			port, res);
+}
+
+static int
+yt921x_dsa_set_ageing_time(struct dsa_switch *ds, unsigned int msecs)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	u32 ctrl;
+	int res;
+
+	/* AGEING reg is set in 5s step */
+	ctrl = clamp(msecs / 5000, 1, U16_MAX);
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_reg_write(priv, YT921X_AGEING, ctrl);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int
+yt921x_dsa_port_fdb_del(struct dsa_switch *ds, int port,
+			const unsigned char *addr, u16 vid, struct dsa_db db)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_fdb_leave(priv, addr, vid, BIT(port));
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int
+yt921x_dsa_port_fdb_add(struct dsa_switch *ds, int port,
+			const unsigned char *addr, u16 vid, struct dsa_db db)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_fdb_join(priv, addr, vid, BIT(port));
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int
+yt921x_dsa_port_mdb_del(struct dsa_switch *ds, int port,
+			const struct switchdev_obj_port_mdb *mdb,
+			struct dsa_db db)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	const unsigned char *addr = mdb->addr;
+	u16 vid = mdb->vid;
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_fdb_leave(priv, addr, vid, BIT(port));
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int
+yt921x_dsa_port_mdb_add(struct dsa_switch *ds, int port,
+			const struct switchdev_obj_port_mdb *mdb,
+			struct dsa_db db)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	const unsigned char *addr = mdb->addr;
+	u16 vid = mdb->vid;
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_fdb_join(priv, addr, vid, BIT(port));
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int
+yt921x_port_set_pvid(struct yt921x_priv *priv, int port, u16 vid)
+{
+	u32 mask;
+	u32 ctrl;
+
+	mask = YT921X_PORT_VLAN_CTRL_CVID_M;
+	ctrl = YT921X_PORT_VLAN_CTRL_CVID(vid);
+	return yt921x_reg_update_bits(priv, YT921X_PORTn_VLAN_CTRL(port),
+				      mask, ctrl);
+}
+
+static int
+yt921x_vlan_filtering(struct yt921x_priv *priv, int port, bool vlan_filtering)
+{
+	struct dsa_port *dp = dsa_to_port(&priv->ds, port);
+	struct net_device *bdev;
+	u16 pvid;
+	u32 mask;
+	u32 ctrl;
+	int res;
+
+	bdev = dsa_port_bridge_dev_get(dp);
+
+	if (!bdev || !vlan_filtering)
+		pvid = YT921X_VID_UNWARE;
+	else
+		br_vlan_get_pvid(bdev, &pvid);
+	res = yt921x_port_set_pvid(priv, port, pvid);
+	if (res)
+		return res;
+
+	mask = YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_TAGGED |
+	       YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_UNTAGGED;
+	ctrl = 0;
+	/* Do not drop tagged frames here; let VLAN_IGR_FILTER do it */
+	if (vlan_filtering && !pvid)
+		ctrl |= YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_UNTAGGED;
+	res = yt921x_reg_update_bits(priv, YT921X_PORTn_VLAN_CTRL1(port),
+				     mask, ctrl);
+	if (res)
+		return res;
+
+	res = yt921x_reg_toggle_bits(priv, YT921X_VLAN_IGR_FILTER,
+				     YT921X_VLAN_IGR_FILTER_PORTn(port),
+				     vlan_filtering);
+	if (res)
+		return res;
+
+	/* Turn on / off VLAN awareness */
+	mask = YT921X_PORT_IGR_TPIDn_CTAG_M;
+	if (!vlan_filtering)
+		ctrl = 0;
+	else
+		ctrl = YT921X_PORT_IGR_TPIDn_CTAG(0);
+	res = yt921x_reg_update_bits(priv, YT921X_PORTn_IGR_TPID(port),
+				     mask, ctrl);
+	if (res)
+		return res;
+
+	return 0;
+}
+
+static int
+yt921x_vlan_del(struct yt921x_priv *priv, int port, u16 vid)
+{
+	u64 mask64;
+
+	mask64 = YT921X_VLAN_CTRL_PORTS(port) |
+		 YT921X_VLAN_CTRL_UNTAG_PORTn(port);
+
+	return yt921x_reg64_clear_bits(priv, YT921X_VLANn_CTRL(vid), mask64);
+}
+
+static int
+yt921x_vlan_add(struct yt921x_priv *priv, int port, u16 vid, bool untagged)
+{
+	u64 mask64;
+	u64 ctrl64;
+
+	mask64 = YT921X_VLAN_CTRL_PORTn(port) |
+		 YT921X_VLAN_CTRL_PORTS(priv->cpu_ports_mask);
+	ctrl64 = mask64;
+
+	mask64 |= YT921X_VLAN_CTRL_UNTAG_PORTn(port);
+	if (untagged)
+		ctrl64 |= YT921X_VLAN_CTRL_UNTAG_PORTn(port);
+
+	return yt921x_reg64_update_bits(priv, YT921X_VLANn_CTRL(vid),
+					mask64, ctrl64);
+}
+
+static int
+yt921x_pvid_clear(struct yt921x_priv *priv, int port)
+{
+	struct dsa_port *dp = dsa_to_port(&priv->ds, port);
+	bool vlan_filtering;
+	u32 mask;
+	int res;
+
+	vlan_filtering = dsa_port_is_vlan_filtering(dp);
+
+	res = yt921x_port_set_pvid(priv, port,
+				   vlan_filtering ? 0 : YT921X_VID_UNWARE);
+	if (res)
+		return res;
+
+	if (vlan_filtering) {
+		mask = YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_UNTAGGED;
+		res = yt921x_reg_set_bits(priv, YT921X_PORTn_VLAN_CTRL1(port),
+					  mask);
+		if (res)
+			return res;
+	}
+
+	return 0;
+}
+
+static int
+yt921x_pvid_set(struct yt921x_priv *priv, int port, u16 vid)
+{
+	struct dsa_port *dp = dsa_to_port(&priv->ds, port);
+	bool vlan_filtering;
+	u32 mask;
+	int res;
+
+	vlan_filtering = dsa_port_is_vlan_filtering(dp);
+
+	if (vlan_filtering) {
+		res = yt921x_port_set_pvid(priv, port, vid);
+		if (res)
+			return res;
+	}
+
+	mask = YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_UNTAGGED;
+	res = yt921x_reg_clear_bits(priv, YT921X_PORTn_VLAN_CTRL1(port), mask);
+	if (res)
+		return res;
+
+	return 0;
+}
+
+static int
+yt921x_dsa_port_vlan_filtering(struct dsa_switch *ds, int port,
+			       bool vlan_filtering,
+			       struct netlink_ext_ack *extack)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	int res;
+
+	if (dsa_is_cpu_port(ds, port))
+		return 0;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_vlan_filtering(priv, port, vlan_filtering);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int
+yt921x_dsa_port_vlan_del(struct dsa_switch *ds, int port,
+			 const struct switchdev_obj_port_vlan *vlan)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	u16 vid = vlan->vid;
+	u16 pvid;
+	int res;
+
+	if (dsa_is_cpu_port(ds, port))
+		return 0;
+
+	mutex_lock(&priv->reg_lock);
+	do {
+		struct dsa_port *dp = dsa_to_port(ds, port);
+		struct net_device *bdev;
+
+		res = yt921x_vlan_del(priv, port, vid);
+		if (res)
+			break;
+
+		bdev = dsa_port_bridge_dev_get(dp);
+		if (bdev) {
+			br_vlan_get_pvid(bdev, &pvid);
+			if (pvid == vid)
+				res = yt921x_pvid_clear(priv, port);
+		}
+	} while (0);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int
+yt921x_dsa_port_vlan_add(struct dsa_switch *ds, int port,
+			 const struct switchdev_obj_port_vlan *vlan,
+			 struct netlink_ext_ack *extack)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	u16 vid = vlan->vid;
+	u16 pvid;
+	int res;
+
+	/* CPU port is supposed to be a member of every VLAN; see
+	 * yt921x_vlan_add() and yt921x_port_setup()
+	 */
+	if (dsa_is_cpu_port(ds, port))
+		return 0;
+
+	mutex_lock(&priv->reg_lock);
+	do {
+		struct dsa_port *dp = dsa_to_port(ds, port);
+		struct net_device *bdev;
+
+		res = yt921x_vlan_add(priv, port, vid,
+				      vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED);
+		if (res)
+			break;
+
+		bdev = dsa_port_bridge_dev_get(dp);
+		if (bdev) {
+			if (vlan->flags & BRIDGE_VLAN_INFO_PVID) {
+				res = yt921x_pvid_set(priv, port, vid);
+			} else {
+				br_vlan_get_pvid(bdev, &pvid);
+				if (pvid == vid)
+					res = yt921x_pvid_clear(priv, port);
+			}
+		}
+	} while (0);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int yt921x_userport_standalone(struct yt921x_priv *priv, int port)
+{
+	u32 mask;
+	u32 ctrl;
+	int res;
+
+	ctrl = ~priv->cpu_ports_mask;
+	res = yt921x_reg_write(priv, YT921X_PORTn_ISOLATION(port), ctrl);
+	if (res)
+		return res;
+
+	/* Turn off FDB learning to prevent FDB pollution */
+	mask = YT921X_PORT_LEARN_DIS;
+	res = yt921x_reg_set_bits(priv, YT921X_PORTn_LEARN(port), mask);
+	if (res)
+		return res;
+
+	/* Turn off VLAN awareness */
+	mask = YT921X_PORT_IGR_TPIDn_CTAG_M;
+	res = yt921x_reg_clear_bits(priv, YT921X_PORTn_IGR_TPID(port), mask);
+	if (res)
+		return res;
+
+	/* Unrelated since learning is off and all packets are trapped;
+	 * set it anyway
+	 */
+	res = yt921x_port_set_pvid(priv, port, YT921X_VID_UNWARE);
+	if (res)
+		return res;
+
+	return 0;
+}
+
+static int yt921x_userport_bridge(struct yt921x_priv *priv, int port)
+{
+	u32 mask;
+	int res;
+
+	mask = YT921X_PORT_LEARN_DIS;
+	res = yt921x_reg_clear_bits(priv, YT921X_PORTn_LEARN(port), mask);
+	if (res)
+		return res;
+
+	return 0;
+}
+
+static int yt921x_isolate(struct yt921x_priv *priv, int port)
+{
+	u32 mask;
+	int res;
+
+	mask = BIT(port);
+	for (int i = 0; i < YT921X_PORT_NUM; i++) {
+		if ((BIT(i) & priv->cpu_ports_mask) || i == port)
+			continue;
+
+		res = yt921x_reg_set_bits(priv, YT921X_PORTn_ISOLATION(i),
+					  mask);
+		if (res)
+			return res;
+	}
+
+	return 0;
+}
+
+/* Make sure to include the CPU port in ports_mask, or your bridge will
+ * not have it.
+ */
+static int yt921x_bridge(struct yt921x_priv *priv, u16 ports_mask)
+{
+	unsigned long targets_mask = ports_mask & ~priv->cpu_ports_mask;
+	u32 isolated_mask;
+	u32 ctrl;
+	int port;
+	int res;
+
+	isolated_mask = 0;
+	for_each_set_bit(port, &targets_mask, YT921X_PORT_NUM) {
+		struct yt921x_port *pp = &priv->ports[port];
+
+		if (pp->isolated)
+			isolated_mask |= BIT(port);
+	}
+
+	/* Block from non-cpu bridge ports ... */
+	for_each_set_bit(port, &targets_mask, YT921X_PORT_NUM) {
+		struct yt921x_port *pp = &priv->ports[port];
+
+		/* to non-bridge ports */
+		ctrl = ~ports_mask;
+		/* to isolated ports when isolated */
+		if (pp->isolated)
+			ctrl |= isolated_mask;
+		/* to itself when non-hairpin */
+		if (!pp->hairpin)
+			ctrl |= BIT(port);
+		else
+			ctrl &= ~BIT(port);
+
+		res = yt921x_reg_write(priv, YT921X_PORTn_ISOLATION(port),
+				       ctrl);
+		if (res)
+			return res;
+	}
+
+	return 0;
+}
+
+static int yt921x_bridge_leave(struct yt921x_priv *priv, int port)
+{
+	int res;
+
+	res = yt921x_userport_standalone(priv, port);
+	if (res)
+		return res;
+
+	res = yt921x_isolate(priv, port);
+	if (res)
+		return res;
+
+	return 0;
+}
+
+static int
+yt921x_bridge_join(struct yt921x_priv *priv, int port, u16 ports_mask)
+{
+	int res;
+
+	res = yt921x_userport_bridge(priv, port);
+	if (res)
+		return res;
+
+	res = yt921x_bridge(priv, ports_mask);
+	if (res)
+		return res;
+
+	return 0;
+}
+
+static u32
+dsa_bridge_ports(struct dsa_switch *ds, const struct net_device *bdev)
+{
+	struct dsa_port *dp;
+	u32 mask = 0;
+
+	dsa_switch_for_each_user_port(dp, ds)
+		if (dsa_port_offloads_bridge_dev(dp, bdev))
+			mask |= BIT(dp->index);
+
+	return mask;
+}
+
+static int
+yt921x_bridge_flags(struct yt921x_priv *priv, int port,
+		    struct switchdev_brport_flags flags)
+{
+	struct yt921x_port *pp = &priv->ports[port];
+	bool do_flush;
+	u32 mask;
+	int res;
+
+	if (flags.mask & BR_LEARNING) {
+		bool learning = flags.val & BR_LEARNING;
+
+		mask = YT921X_PORT_LEARN_DIS;
+		res = yt921x_reg_toggle_bits(priv, YT921X_PORTn_LEARN(port),
+					     mask, !learning);
+		if (res)
+			return res;
+	}
+
+	/* BR_FLOOD, BR_MCAST_FLOOD: see the comment where ACT_UNK_ACTn_TRAP
+	 * is set
+	 */
+
+	/* BR_BCAST_FLOOD: we can filter bcast, but cannot trap them */
+
+	do_flush = false;
+	if (flags.mask & BR_HAIRPIN_MODE) {
+		pp->hairpin = flags.val & BR_HAIRPIN_MODE;
+		do_flush = true;
+	}
+	if (flags.mask & BR_ISOLATED) {
+		pp->isolated = flags.val & BR_ISOLATED;
+		do_flush = true;
+	}
+	if (do_flush) {
+		struct dsa_switch *ds = &priv->ds;
+		struct dsa_port *dp = dsa_to_port(ds, port);
+		struct net_device *bdev;
+
+		bdev = dsa_port_bridge_dev_get(dp);
+		if (bdev) {
+			u32 ports_mask;
+
+			ports_mask = dsa_bridge_ports(ds, bdev);
+			ports_mask |= priv->cpu_ports_mask;
+			res = yt921x_bridge(priv, ports_mask);
+			if (res)
+				return res;
+		}
+	}
+
+	return 0;
+}
+
+static int
+yt921x_dsa_port_pre_bridge_flags(struct dsa_switch *ds, int port,
+				 struct switchdev_brport_flags flags,
+				 struct netlink_ext_ack *extack)
+{
+	if (flags.mask & ~(BR_HAIRPIN_MODE | BR_LEARNING | BR_FLOOD |
+			   BR_MCAST_FLOOD | BR_ISOLATED))
+		return -EINVAL;
+	return 0;
+}
+
+static int
+yt921x_dsa_port_bridge_flags(struct dsa_switch *ds, int port,
+			     struct switchdev_brport_flags flags,
+			     struct netlink_ext_ack *extack)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	int res;
+
+	if (dsa_is_cpu_port(ds, port))
+		return 0;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_bridge_flags(priv, port, flags);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static void
+yt921x_dsa_port_bridge_leave(struct dsa_switch *ds, int port,
+			     struct dsa_bridge bridge)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	struct device *dev = to_device(priv);
+	int res;
+
+	if (dsa_is_cpu_port(ds, port))
+		return;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_bridge_leave(priv, port);
+	mutex_unlock(&priv->reg_lock);
+
+	if (res)
+		dev_err(dev, "Failed to %s port %d: %i\n", "unbridge",
+			port, res);
+}
+
+static int
+yt921x_dsa_port_bridge_join(struct dsa_switch *ds, int port,
+			    struct dsa_bridge bridge, bool *tx_fwd_offload,
+			    struct netlink_ext_ack *extack)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	u16 ports_mask;
+	int res;
+
+	if (dsa_is_cpu_port(ds, port))
+		return 0;
+
+	ports_mask = dsa_bridge_ports(ds, bridge.dev);
+	ports_mask |= priv->cpu_ports_mask;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_bridge_join(priv, port, ports_mask);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int
+yt921x_dsa_port_mst_state_set(struct dsa_switch *ds, int port,
+			      const struct switchdev_mst_state *st)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	u32 mask;
+	u32 ctrl;
+	int res;
+
+	mask = YT921X_STP_PORTn_M(port);
+	switch (st->state) {
+	case BR_STATE_DISABLED:
+		ctrl = YT921X_STP_PORTn_DISABLED(port);
+		break;
+	case BR_STATE_LISTENING:
+	case BR_STATE_LEARNING:
+		ctrl = YT921X_STP_PORTn_LEARNING(port);
+		break;
+	case BR_STATE_FORWARDING:
+	default:
+		ctrl = YT921X_STP_PORTn_FORWARD(port);
+		break;
+	case BR_STATE_BLOCKING:
+		ctrl = YT921X_STP_PORTn_BLOCKING(port);
+		break;
+	}
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_reg_update_bits(priv, YT921X_STPn(st->msti), mask, ctrl);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int
+yt921x_dsa_vlan_msti_set(struct dsa_switch *ds, struct dsa_bridge bridge,
+			 const struct switchdev_vlan_msti *msti)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	u64 mask64;
+	u64 ctrl64;
+	int res;
+
+	if (!msti->vid)
+		return -EINVAL;
+	if (!msti->msti || msti->msti >= YT921X_MSTI_NUM)
+		return -EINVAL;
+
+	mask64 = YT921X_VLAN_CTRL_STP_ID_M;
+	ctrl64 = YT921X_VLAN_CTRL_STP_ID(msti->msti);
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_reg64_update_bits(priv, YT921X_VLANn_CTRL(msti->vid),
+				       mask64, ctrl64);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static void
+yt921x_dsa_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	struct dsa_port *dp = dsa_to_port(ds, port);
+	struct device *dev = to_device(priv);
+	bool learning;
+	u32 mask;
+	u32 ctrl;
+	int res;
+
+	mask = YT921X_STP_PORTn_M(port);
+	learning = false;
+	switch (state) {
+	case BR_STATE_DISABLED:
+		ctrl = YT921X_STP_PORTn_DISABLED(port);
+		break;
+	case BR_STATE_LISTENING:
+		ctrl = YT921X_STP_PORTn_LEARNING(port);
+		break;
+	case BR_STATE_LEARNING:
+		ctrl = YT921X_STP_PORTn_LEARNING(port);
+		learning = dp->learning;
+		break;
+	case BR_STATE_FORWARDING:
+	default:
+		ctrl = YT921X_STP_PORTn_FORWARD(port);
+		learning = dp->learning;
+		break;
+	case BR_STATE_BLOCKING:
+		ctrl = YT921X_STP_PORTn_BLOCKING(port);
+		break;
+	}
+
+	mutex_lock(&priv->reg_lock);
+	do {
+		res = yt921x_reg_update_bits(priv, YT921X_STPn(0), mask, ctrl);
+		if (res)
+			break;
+
+		mask = YT921X_PORT_LEARN_DIS;
+		ctrl = !learning ? YT921X_PORT_LEARN_DIS : 0;
+		res = yt921x_reg_update_bits(priv, YT921X_PORTn_LEARN(port),
+					     mask, ctrl);
+	} while (0);
+	mutex_unlock(&priv->reg_lock);
+
+	if (res)
+		dev_err(dev, "Failed to %s port %d: %i\n", "set STP state for",
+			port, res);
+}
+
+static int yt921x_port_down(struct yt921x_priv *priv, int port)
+{
+	u32 mask;
+	int res;
+
+	mask = YT921X_PORT_LINK | YT921X_PORT_RX_MAC_EN | YT921X_PORT_TX_MAC_EN;
+	res = yt921x_reg_clear_bits(priv, YT921X_PORTn_CTRL(port), mask);
+	if (res)
+		return res;
+
+	if (yt921x_port_is_external(port)) {
+		mask = YT921X_SERDES_LINK;
+		res = yt921x_reg_clear_bits(priv, YT921X_SERDESn(port), mask);
+		if (res)
+			return res;
+
+		mask = YT921X_XMII_LINK;
+		res = yt921x_reg_clear_bits(priv, YT921X_XMIIn(port), mask);
+		if (res)
+			return res;
+	}
+
+	return 0;
+}
+
+static int
+yt921x_port_up(struct yt921x_priv *priv, int port, unsigned int mode,
+	       phy_interface_t interface, int speed, int duplex,
+	       bool tx_pause, bool rx_pause)
+{
+	u32 mask;
+	u32 ctrl;
+	int res;
+
+	switch (speed) {
+	case SPEED_10:
+		ctrl = YT921X_PORT_SPEED_10;
+		break;
+	case SPEED_100:
+		ctrl = YT921X_PORT_SPEED_100;
+		break;
+	case SPEED_1000:
+		ctrl = YT921X_PORT_SPEED_1000;
+		break;
+	case SPEED_2500:
+		ctrl = YT921X_PORT_SPEED_2500;
+		break;
+	case SPEED_10000:
+		ctrl = YT921X_PORT_SPEED_10000;
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (duplex == DUPLEX_FULL)
+		ctrl |= YT921X_PORT_DUPLEX_FULL;
+	if (tx_pause)
+		ctrl |= YT921X_PORT_TX_PAUSE;
+	if (rx_pause)
+		ctrl |= YT921X_PORT_RX_PAUSE;
+	ctrl |= YT921X_PORT_RX_MAC_EN | YT921X_PORT_TX_MAC_EN;
+	res = yt921x_reg_write(priv, YT921X_PORTn_CTRL(port), ctrl);
+	if (res)
+		return res;
+
+	if (yt921x_port_is_external(port)) {
+		mask = YT921X_SERDES_SPEED_M;
+		switch (speed) {
+		case SPEED_10:
+			ctrl = YT921X_SERDES_SPEED_10;
+			break;
+		case SPEED_100:
+			ctrl = YT921X_SERDES_SPEED_100;
+			break;
+		case SPEED_1000:
+			ctrl = YT921X_SERDES_SPEED_1000;
+			break;
+		case SPEED_2500:
+			ctrl = YT921X_SERDES_SPEED_2500;
+			break;
+		case SPEED_10000:
+			ctrl = YT921X_SERDES_SPEED_10000;
+			break;
+		default:
+			return -EINVAL;
+		}
+		mask |= YT921X_SERDES_DUPLEX_FULL;
+		if (duplex == DUPLEX_FULL)
+			ctrl |= YT921X_SERDES_DUPLEX_FULL;
+		mask |= YT921X_SERDES_TX_PAUSE;
+		if (tx_pause)
+			ctrl |= YT921X_SERDES_TX_PAUSE;
+		mask |= YT921X_SERDES_RX_PAUSE;
+		if (rx_pause)
+			ctrl |= YT921X_SERDES_RX_PAUSE;
+		mask |= YT921X_SERDES_LINK;
+		ctrl |= YT921X_SERDES_LINK;
+		res = yt921x_reg_update_bits(priv, YT921X_SERDESn(port),
+					     mask, ctrl);
+		if (res)
+			return res;
+
+		mask = YT921X_XMII_LINK;
+		res = yt921x_reg_set_bits(priv, YT921X_XMIIn(port), mask);
+		if (res)
+			return res;
+
+		switch (speed) {
+		case SPEED_10:
+			ctrl = YT921X_MDIO_POLLING_SPEED_10;
+			break;
+		case SPEED_100:
+			ctrl = YT921X_MDIO_POLLING_SPEED_100;
+			break;
+		case SPEED_1000:
+			ctrl = YT921X_MDIO_POLLING_SPEED_1000;
+			break;
+		case SPEED_2500:
+			ctrl = YT921X_MDIO_POLLING_SPEED_2500;
+			break;
+		case SPEED_10000:
+			ctrl = YT921X_MDIO_POLLING_SPEED_10000;
+			break;
+		default:
+			return -EINVAL;
+		}
+		if (duplex == DUPLEX_FULL)
+			ctrl |= YT921X_MDIO_POLLING_DUPLEX_FULL;
+		ctrl |= YT921X_MDIO_POLLING_LINK;
+		res = yt921x_reg_write(priv, YT921X_MDIO_POLLINGn(port), ctrl);
+		if (res)
+			return res;
+	}
+
+	return 0;
+}
+
+static int
+yt921x_port_config(struct yt921x_priv *priv, int port, unsigned int mode,
+		   phy_interface_t interface)
+{
+	struct device *dev = to_device(priv);
+	u32 mask;
+	u32 ctrl;
+	int res;
+
+	if (!yt921x_port_is_external(port)) {
+		if (interface != PHY_INTERFACE_MODE_INTERNAL) {
+			dev_err(dev, "Wrong mode %d on port %d\n",
+				interface, port);
+			return -EINVAL;
+		}
+		return 0;
+	}
+
+	switch (interface) {
+	/* SERDES */
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_100BASEX:
+	case PHY_INTERFACE_MODE_1000BASEX:
+	case PHY_INTERFACE_MODE_2500BASEX:
+		mask = YT921X_SERDES_CTRL_PORTn(port);
+		res = yt921x_reg_set_bits(priv, YT921X_SERDES_CTRL, mask);
+		if (res)
+			return res;
+
+		mask = YT921X_XMII_CTRL_PORTn(port);
+		res = yt921x_reg_clear_bits(priv, YT921X_XMII_CTRL, mask);
+		if (res)
+			return res;
+
+		mask = YT921X_SERDES_MODE_M;
+		switch (interface) {
+		case PHY_INTERFACE_MODE_SGMII:
+			ctrl = YT921X_SERDES_MODE_SGMII;
+			break;
+		case PHY_INTERFACE_MODE_100BASEX:
+			ctrl = YT921X_SERDES_MODE_100BASEX;
+			break;
+		case PHY_INTERFACE_MODE_1000BASEX:
+			ctrl = YT921X_SERDES_MODE_1000BASEX;
+			break;
+		case PHY_INTERFACE_MODE_2500BASEX:
+			ctrl = YT921X_SERDES_MODE_2500BASEX;
+			break;
+		default:
+			return -EINVAL;
+		}
+		res = yt921x_reg_update_bits(priv, YT921X_SERDESn(port),
+					     mask, ctrl);
+		if (res)
+			return res;
+
+		break;
+	/* add XMII support here */
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void
+yt921x_phylink_mac_link_down(struct phylink_config *config, unsigned int mode,
+			     phy_interface_t interface)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct yt921x_priv *priv = to_yt921x_priv(dp->ds);
+	int port = dp->index;
+	int res;
+
+	/* No need to sync; port control block is hold until device remove */
+	cancel_delayed_work(&priv->ports[port].mib_read);
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_port_down(priv, port);
+	mutex_unlock(&priv->reg_lock);
+
+	if (res)
+		dev_err(dp->ds->dev, "Failed to %s port %d: %i\n", "bring down",
+			port, res);
+}
+
+static void
+yt921x_phylink_mac_link_up(struct phylink_config *config,
+			   struct phy_device *phydev, unsigned int mode,
+			   phy_interface_t interface, int speed, int duplex,
+			   bool tx_pause, bool rx_pause)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct yt921x_priv *priv = to_yt921x_priv(dp->ds);
+	int port = dp->index;
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_port_up(priv, port, mode, interface, speed, duplex,
+			     tx_pause, rx_pause);
+	mutex_unlock(&priv->reg_lock);
+
+	if (res)
+		dev_err(dp->ds->dev, "Failed to %s port %d: %i\n", "bring up",
+			port, res);
+
+	schedule_delayed_work(&priv->ports[port].mib_read, 0);
+}
+
+static void
+yt921x_phylink_mac_config(struct phylink_config *config, unsigned int mode,
+			  const struct phylink_link_state *state)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct yt921x_priv *priv = to_yt921x_priv(dp->ds);
+	int port = dp->index;
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_port_config(priv, port, mode, state->interface);
+	mutex_unlock(&priv->reg_lock);
+
+	if (res)
+		dev_err(dp->ds->dev, "Failed to %s port %d: %i\n", "config",
+			port, res);
+}
+
+static void
+yt921x_dsa_phylink_get_caps(struct dsa_switch *ds, int port,
+			    struct phylink_config *config)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	const struct yt921x_info *info = priv->info;
+
+	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+				   MAC_10 | MAC_100 | MAC_1000;
+
+	if (info->internal_mask & BIT(port)) {
+		/* Port 10 for MCU should probably go here too. But since that
+		 * is untested yet, turn it down for the moment by letting it
+		 * fall to the default branch.
+		 */
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  config->supported_interfaces);
+	} else if (info->external_mask & BIT(port)) {
+		/* TODO: external ports may support SERDES only, XMII only, or
+		 * SERDES + XMII depending on the chip. However, we can't get
+		 * the accurate config table due to lack of document, thus
+		 * we simply declare SERDES + XMII and rely on the correctness
+		 * of devicetree for now.
+		 */
+
+		/* SERDES */
+		__set_bit(PHY_INTERFACE_MODE_SGMII,
+			  config->supported_interfaces);
+		/* REVSGMII (SGMII in PHY role) should go here, once
+		 * PHY_INTERFACE_MODE_REVSGMII is introduced.
+		 */
+		__set_bit(PHY_INTERFACE_MODE_100BASEX,
+			  config->supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_1000BASEX,
+			  config->supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_2500BASEX,
+			  config->supported_interfaces);
+		config->mac_capabilities |= MAC_2500FD;
+
+		/* XMII */
+
+		/* Not tested. To add support for XMII:
+		 *   - Add proper interface modes below
+		 *   - Handle them in yt921x_port_config()
+		 */
+	}
+	/* no such port: empty supported_interfaces causes phylink to turn it
+	 * down
+	 */
+}
+
+static int yt921x_port_setup(struct yt921x_priv *priv, int port)
+{
+	struct dsa_switch *ds = &priv->ds;
+	u32 ctrl;
+	int res;
+
+	res = yt921x_userport_standalone(priv, port);
+	if (res)
+		return res;
+
+	if (dsa_is_cpu_port(ds, port)) {
+		/* Egress of CPU port is supposed to be completely controlled
+		 * via tagging, so set to oneway isolated (drop all packets
+		 * without tag).
+		 */
+		ctrl = ~(u32)0;
+		res = yt921x_reg_write(priv, YT921X_PORTn_ISOLATION(port),
+				       ctrl);
+		if (res)
+			return res;
+
+		/* To simplify FDB "isolation" simulation, we also disable
+		 * learning on the CPU port, and let software identify packets
+		 * towarding CPU (either trapped or a static FDB entry is
+		 * matched, no matter which bridge that entry is for), which is
+		 * already done by yt921x_userport_standalone(). As a result,
+		 * VLAN-awareness becomes unrelated on the CPU port (set to
+		 * VLAN-unaware by the way).
+		 */
+	}
+
+	return 0;
+}
+
+static enum dsa_tag_protocol
+yt921x_dsa_get_tag_protocol(struct dsa_switch *ds, int port,
+			    enum dsa_tag_protocol m)
+{
+	return DSA_TAG_PROTO_YT921X;
+}
+
+static int yt921x_dsa_port_setup(struct dsa_switch *ds, int port)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_port_setup(priv, port);
+	mutex_unlock(&priv->reg_lock);
+
+	return res;
+}
+
+static int yt921x_edata_wait(struct yt921x_priv *priv, u32 *valp)
+{
+	u32 val = YT921X_EDATA_DATA_IDLE;
+	int res;
+
+	res = yt921x_reg_wait(priv, YT921X_EDATA_DATA,
+			      YT921X_EDATA_DATA_STATUS_M, &val);
+	if (res)
+		return res;
+
+	*valp = val;
+	return 0;
+}
+
+static int
+yt921x_edata_read_cont(struct yt921x_priv *priv, u8 addr, u8 *valp)
+{
+	u32 ctrl;
+	u32 val;
+	int res;
+
+	ctrl = YT921X_EDATA_CTRL_ADDR(addr) | YT921X_EDATA_CTRL_READ;
+	res = yt921x_reg_write(priv, YT921X_EDATA_CTRL, ctrl);
+	if (res)
+		return res;
+	res = yt921x_edata_wait(priv, &val);
+	if (res)
+		return res;
+
+	*valp = FIELD_GET(YT921X_EDATA_DATA_DATA_M, val);
+	return 0;
+}
+
+static int yt921x_edata_read(struct yt921x_priv *priv, u8 addr, u8 *valp)
+{
+	u32 val;
+	int res;
+
+	res = yt921x_edata_wait(priv, &val);
+	if (res)
+		return res;
+	return yt921x_edata_read_cont(priv, addr, valp);
+}
+
+static int yt921x_chip_detect(struct yt921x_priv *priv)
+{
+	struct device *dev = to_device(priv);
+	const struct yt921x_info *info;
+	u8 extmode;
+	u32 chipid;
+	u32 major;
+	u32 mode;
+	int res;
+
+	res = yt921x_reg_read(priv, YT921X_CHIP_ID, &chipid);
+	if (res)
+		return res;
+
+	major = FIELD_GET(YT921X_CHIP_ID_MAJOR, chipid);
+
+	for (info = yt921x_infos; info->name; info++)
+		if (info->major == major)
+			break;
+	if (!info->name) {
+		dev_err(dev, "Unexpected chipid 0x%x\n", chipid);
+		return -ENODEV;
+	}
+
+	res = yt921x_reg_read(priv, YT921X_CHIP_MODE, &mode);
+	if (res)
+		return res;
+	res = yt921x_edata_read(priv, YT921X_EDATA_EXTMODE, &extmode);
+	if (res)
+		return res;
+
+	for (; info->name; info++)
+		if (info->major == major && info->mode == mode &&
+		    info->extmode == extmode)
+			break;
+	if (!info->name) {
+		dev_err(dev,
+			"Unsupported chipid 0x%x with chipmode 0x%x 0x%x\n",
+			chipid, mode, extmode);
+		return -ENODEV;
+	}
+
+	/* Print chipid here since we are interested in lower 16 bits */
+	dev_info(dev,
+		 "Motorcomm %s ethernet switch, chipid: 0x%x, chipmode: 0x%x 0x%x\n",
+		 info->name, chipid, mode, extmode);
+
+	priv->info = info;
+	return 0;
+}
+
+static int yt921x_chip_reset(struct yt921x_priv *priv)
+{
+	struct device *dev = to_device(priv);
+	u16 eth_p_tag;
+	u32 val;
+	int res;
+
+	res = yt921x_chip_detect(priv);
+	if (res)
+		return res;
+
+	/* Reset */
+	res = yt921x_reg_write(priv, YT921X_RST, YT921X_RST_HW);
+	if (res)
+		return res;
+
+	/* RST_HW is almost same as GPIO hard reset, so we need this delay. */
+	fsleep(YT921X_RST_DELAY_US);
+
+	val = 0;
+	res = yt921x_reg_wait(priv, YT921X_RST, ~0, &val);
+	if (res)
+		return res;
+
+	/* Check for tag EtherType; do it after reset in case you messed it up
+	 * before.
+	 */
+	res = yt921x_reg_read(priv, YT921X_CPU_TAG_TPID, &val);
+	if (res)
+		return res;
+	eth_p_tag = FIELD_GET(YT921X_CPU_TAG_TPID_TPID_M, val);
+	if (eth_p_tag != ETH_P_YT921X) {
+		dev_err(dev, "Tag type 0x%x != 0x%x\n", eth_p_tag,
+			ETH_P_YT921X);
+		/* Despite being possible, we choose not to set CPU_TAG_TPID,
+		 * since there is no way it can be different unless you have the
+		 * wrong chip.
+		 */
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int yt921x_chip_setup(struct yt921x_priv *priv)
+{
+	struct dsa_switch *ds = &priv->ds;
+	unsigned long cpu_ports_mask;
+	u64 ctrl64;
+	u32 ctrl;
+	int port;
+	int res;
+
+	/* Enable DSA */
+	priv->cpu_ports_mask = dsa_cpu_ports(ds);
+
+	ctrl = YT921X_EXT_CPU_PORT_TAG_EN | YT921X_EXT_CPU_PORT_PORT_EN |
+	       YT921X_EXT_CPU_PORT_PORT(__ffs(priv->cpu_ports_mask));
+	res = yt921x_reg_write(priv, YT921X_EXT_CPU_PORT, ctrl);
+	if (res)
+		return res;
+
+	/* Enable and clear MIB */
+	res = yt921x_reg_set_bits(priv, YT921X_FUNC, YT921X_FUNC_MIB);
+	if (res)
+		return res;
+
+	ctrl = YT921X_MIB_CTRL_CLEAN | YT921X_MIB_CTRL_ALL_PORT;
+	res = yt921x_reg_write(priv, YT921X_MIB_CTRL, ctrl);
+	if (res)
+		return res;
+
+	/* Setup software switch */
+	ctrl = YT921X_CPU_COPY_TO_EXT_CPU;
+	res = yt921x_reg_write(priv, YT921X_CPU_COPY, ctrl);
+	if (res)
+		return res;
+
+	ctrl = GENMASK(10, 0);
+	res = yt921x_reg_write(priv, YT921X_FILTER_UNK_UCAST, ctrl);
+	if (res)
+		return res;
+	res = yt921x_reg_write(priv, YT921X_FILTER_UNK_MCAST, ctrl);
+	if (res)
+		return res;
+
+	/* YT921x does not support native DSA port bridging, so we use port
+	 * isolation to emulate it. However, be especially careful that port
+	 * isolation takes _after_ FDB lookups, i.e. if an FDB entry (from
+	 * another bridge) is matched and the destination port (in another
+	 * bridge) is blocked, the packet will be dropped instead of flooding to
+	 * the "bridged" ports, thus we need to trap and handle those packets by
+	 * software.
+	 *
+	 * If there is no more than one bridge, we might be able to drop them
+	 * directly given some conditions are met, but we trap them in all cases
+	 * for now.
+	 */
+	ctrl = 0;
+	for (int i = 0; i < YT921X_PORT_NUM; i++)
+		ctrl |= YT921X_ACT_UNK_ACTn_TRAP(i);
+	/* Except for CPU ports, if any packets are sent via CPU ports without
+	 * tag, they should be dropped.
+	 */
+	cpu_ports_mask = priv->cpu_ports_mask;
+	for_each_set_bit(port, &cpu_ports_mask, YT921X_PORT_NUM) {
+		ctrl &= ~YT921X_ACT_UNK_ACTn_M(port);
+		ctrl |= YT921X_ACT_UNK_ACTn_DROP(port);
+	}
+	res = yt921x_reg_write(priv, YT921X_ACT_UNK_UCAST, ctrl);
+	if (res)
+		return res;
+	res = yt921x_reg_write(priv, YT921X_ACT_UNK_MCAST, ctrl);
+	if (res)
+		return res;
+
+	/* Tagged VID 0 should be treated as untagged, which confuses the
+	 * hardware a lot
+	 */
+	ctrl64 = YT921X_VLAN_CTRL_LEARN_DIS | YT921X_VLAN_CTRL_PORTS_M;
+	res = yt921x_reg64_write(priv, YT921X_VLANn_CTRL(0), ctrl64);
+	if (res)
+		return res;
+
+	/* Miscellaneous */
+	res = yt921x_reg_set_bits(priv, YT921X_SENSOR, YT921X_SENSOR_TEMP);
+	if (res)
+		return res;
+
+	return 0;
+}
+
+static int yt921x_dsa_setup(struct dsa_switch *ds)
+{
+	struct yt921x_priv *priv = to_yt921x_priv(ds);
+	struct device *dev = to_device(priv);
+	struct device_node *np = dev->of_node;
+	struct device_node *child;
+	int res;
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_chip_reset(priv);
+	mutex_unlock(&priv->reg_lock);
+
+	if (res)
+		return res;
+
+	/* Register the internal mdio bus. Nodes for internal ports should have
+	 * proper phy-handle pointing to their PHYs. Not enabling the internal
+	 * bus is possible, though pretty wired, if internal ports are not used.
+	 */
+	child = of_get_child_by_name(np, "mdio");
+	if (child) {
+		res = yt921x_mbus_int_init(priv, child);
+		of_node_put(child);
+		if (res)
+			return res;
+	}
+
+	/* External mdio bus is optional */
+	child = of_get_child_by_name(np, "mdio-external");
+	if (child) {
+		res = yt921x_mbus_ext_init(priv, child);
+		of_node_put(child);
+		if (res)
+			return res;
+
+		dev_err(dev, "Untested external mdio bus\n");
+		return -ENODEV;
+	}
+
+	mutex_lock(&priv->reg_lock);
+	res = yt921x_chip_setup(priv);
+	mutex_unlock(&priv->reg_lock);
+
+	if (res)
+		return res;
+
+	return 0;
+}
+
+static const struct phylink_mac_ops yt921x_phylink_mac_ops = {
+	.mac_link_down	= yt921x_phylink_mac_link_down,
+	.mac_link_up	= yt921x_phylink_mac_link_up,
+	.mac_config	= yt921x_phylink_mac_config,
+};
+
+static const struct dsa_switch_ops yt921x_dsa_switch_ops = {
+	/* mib */
+	.get_strings		= yt921x_dsa_get_strings,
+	.get_ethtool_stats	= yt921x_dsa_get_ethtool_stats,
+	.get_sset_count		= yt921x_dsa_get_sset_count,
+	.get_eth_mac_stats	= yt921x_dsa_get_eth_mac_stats,
+	.get_eth_ctrl_stats	= yt921x_dsa_get_eth_ctrl_stats,
+	.get_rmon_stats		= yt921x_dsa_get_rmon_stats,
+	.get_stats64		= yt921x_dsa_get_stats64,
+	.get_pause_stats	= yt921x_dsa_get_pause_stats,
+	/* eee */
+	.support_eee		= dsa_supports_eee,
+	.set_mac_eee		= yt921x_dsa_set_mac_eee,
+	/* mtu */
+	.port_change_mtu	= yt921x_dsa_port_change_mtu,
+	.port_max_mtu		= yt921x_dsa_port_max_mtu,
+	/* hsr */
+	.port_hsr_leave		= dsa_port_simple_hsr_leave,
+	.port_hsr_join		= dsa_port_simple_hsr_join,
+	/* mirror */
+	.port_mirror_del	= yt921x_dsa_port_mirror_del,
+	.port_mirror_add	= yt921x_dsa_port_mirror_add,
+	/* fdb */
+	.port_fdb_dump		= yt921x_dsa_port_fdb_dump,
+	.port_fast_age		= yt921x_dsa_port_fast_age,
+	.set_ageing_time	= yt921x_dsa_set_ageing_time,
+	.port_fdb_del		= yt921x_dsa_port_fdb_del,
+	.port_fdb_add		= yt921x_dsa_port_fdb_add,
+	.port_mdb_del		= yt921x_dsa_port_mdb_del,
+	.port_mdb_add		= yt921x_dsa_port_mdb_add,
+	/* vlan */
+	.port_vlan_filtering	= yt921x_dsa_port_vlan_filtering,
+	.port_vlan_del		= yt921x_dsa_port_vlan_del,
+	.port_vlan_add		= yt921x_dsa_port_vlan_add,
+	/* bridge */
+	.port_pre_bridge_flags	= yt921x_dsa_port_pre_bridge_flags,
+	.port_bridge_flags	= yt921x_dsa_port_bridge_flags,
+	.port_bridge_leave	= yt921x_dsa_port_bridge_leave,
+	.port_bridge_join	= yt921x_dsa_port_bridge_join,
+	/* mst */
+	.port_mst_state_set	= yt921x_dsa_port_mst_state_set,
+	.vlan_msti_set		= yt921x_dsa_vlan_msti_set,
+	.port_stp_state_set	= yt921x_dsa_port_stp_state_set,
+	/* port */
+	.get_tag_protocol	= yt921x_dsa_get_tag_protocol,
+	.phylink_get_caps	= yt921x_dsa_phylink_get_caps,
+	.port_setup		= yt921x_dsa_port_setup,
+	/* chip */
+	.setup			= yt921x_dsa_setup,
+};
+
+static void yt921x_mdio_shutdown(struct mdio_device *mdiodev)
+{
+	struct yt921x_priv *priv = mdiodev_get_drvdata(mdiodev);
+
+	if (!priv)
+		return;
+
+	dsa_switch_shutdown(&priv->ds);
+}
+
+static void yt921x_mdio_remove(struct mdio_device *mdiodev)
+{
+	struct yt921x_priv *priv = mdiodev_get_drvdata(mdiodev);
+
+	if (!priv)
+		return;
+
+	for (size_t i = ARRAY_SIZE(priv->ports); i-- > 0; ) {
+		struct yt921x_port *pp = &priv->ports[i];
+
+		disable_delayed_work_sync(&pp->mib_read);
+	}
+
+	dsa_unregister_switch(&priv->ds);
+
+	mutex_destroy(&priv->reg_lock);
+}
+
+static int yt921x_mdio_probe(struct mdio_device *mdiodev)
+{
+	struct device *dev = &mdiodev->dev;
+	struct yt921x_reg_mdio *mdio;
+	struct yt921x_priv *priv;
+	struct dsa_switch *ds;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	mdio = devm_kzalloc(dev, sizeof(*mdio), GFP_KERNEL);
+	if (!mdio)
+		return -ENOMEM;
+
+	mdio->bus = mdiodev->bus;
+	mdio->addr = mdiodev->addr;
+	mdio->switchid = 0;
+
+	mutex_init(&priv->reg_lock);
+
+	priv->reg_ops = &yt921x_reg_ops_mdio;
+	priv->reg_ctx = mdio;
+
+	for (size_t i = 0; i < ARRAY_SIZE(priv->ports); i++) {
+		struct yt921x_port *pp = &priv->ports[i];
+
+		pp->index = i;
+		INIT_DELAYED_WORK(&pp->mib_read, yt921x_poll_mib);
+	}
+
+	ds = &priv->ds;
+	ds->dev = dev;
+	ds->assisted_learning_on_cpu_port = true;
+	ds->priv = priv;
+	ds->ops = &yt921x_dsa_switch_ops;
+	ds->ageing_time_min = 1 * 5000;
+	ds->ageing_time_max = U16_MAX * 5000;
+	ds->phylink_mac_ops = &yt921x_phylink_mac_ops;
+	ds->num_ports = YT921X_PORT_NUM;
+
+	mdiodev_set_drvdata(mdiodev, priv);
+
+	return dsa_register_switch(ds);
+}
+
+static const struct of_device_id yt921x_of_match[] = {
+	{ .compatible = "motorcomm,yt9215" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, yt921x_of_match);
+
+static struct mdio_driver yt921x_mdio_driver = {
+	.probe = yt921x_mdio_probe,
+	.remove = yt921x_mdio_remove,
+	.shutdown = yt921x_mdio_shutdown,
+	.mdiodrv.driver = {
+		.name = YT921X_NAME,
+		.of_match_table = yt921x_of_match,
+	},
+};
+
+mdio_module_driver(yt921x_mdio_driver);
+
+MODULE_AUTHOR("David Yang <mmyangfl@gmail.com>");
+MODULE_DESCRIPTION("Driver for Motorcomm YT921x Switch");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/yt921x.h b/drivers/net/dsa/yt921x.h
new file mode 100644
index 000000000000..61bb0ab3b09a
--- /dev/null
+++ b/drivers/net/dsa/yt921x.h
@@ -0,0 +1,567 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2025 David Yang
+ */
+
+#ifndef __YT921X_H
+#define __YT921X_H
+
+#include <net/dsa.h>
+
+#define YT921X_SMI_SWITCHID_M		GENMASK(3, 2)
+#define  YT921X_SMI_SWITCHID(x)			FIELD_PREP(YT921X_SMI_SWITCHID_M, (x))
+#define YT921X_SMI_AD			BIT(1)
+#define  YT921X_SMI_ADDR			0
+#define  YT921X_SMI_DATA			YT921X_SMI_AD
+#define YT921X_SMI_RW			BIT(0)
+#define  YT921X_SMI_WRITE			0
+#define  YT921X_SMI_READ			YT921X_SMI_RW
+
+#define YT921X_SWITCHID_NUM		4
+
+#define YT921X_RST			0x80000
+#define  YT921X_RST_HW				BIT(31)
+#define  YT921X_RST_SW				BIT(1)
+#define YT921X_FUNC			0x80004
+#define  YT921X_FUNC_MIB			BIT(1)
+#define YT921X_CHIP_ID			0x80008
+#define  YT921X_CHIP_ID_MAJOR			GENMASK(31, 16)
+#define YT921X_EXT_CPU_PORT		0x8000c
+#define  YT921X_EXT_CPU_PORT_TAG_EN		BIT(15)
+#define  YT921X_EXT_CPU_PORT_PORT_EN		BIT(14)
+#define  YT921X_EXT_CPU_PORT_PORT_M		GENMASK(3, 0)
+#define   YT921X_EXT_CPU_PORT_PORT(x)			FIELD_PREP(YT921X_EXT_CPU_PORT_PORT_M, (x))
+#define YT921X_CPU_TAG_TPID		0x80010
+#define  YT921X_CPU_TAG_TPID_TPID_M		GENMASK(15, 0)
+/* Same as ETH_P_YT921X, but this represents the true HW default, while the
+ * former is a local convention chosen by us.
+ */
+#define   YT921X_CPU_TAG_TPID_TPID_DEFAULT		0x9988
+#define YT921X_PVID_SEL			0x80014
+#define  YT921X_PVID_SEL_SVID_PORTn(port)	BIT(port)
+#define YT921X_SERDES_CTRL		0x80028
+#define  YT921X_SERDES_CTRL_PORTn_TEST(port)	BIT((port) - 3)
+#define  YT921X_SERDES_CTRL_PORTn(port)		BIT((port) - 8)
+#define YT921X_IO_LEVEL			0x80030
+#define  YT9215_IO_LEVEL_NORMAL_M		GENMASK(5, 4)
+#define   YT9215_IO_LEVEL_NORMAL(x)			FIELD_PREP(YT9215_IO_LEVEL_NORMAL_M, (x))
+#define   YT9215_IO_LEVEL_NORMAL_3V3			YT9215_IO_LEVEL_NORMAL(0)
+#define   YT9215_IO_LEVEL_NORMAL_1V8			YT9215_IO_LEVEL_NORMAL(3)
+#define  YT9215_IO_LEVEL_RGMII1_M		GENMASK(3, 2)
+#define   YT9215_IO_LEVEL_RGMII1(x)			FIELD_PREP(YT9215_IO_LEVEL_RGMII1_M, (x))
+#define   YT9215_IO_LEVEL_RGMII1_3V3			YT9215_IO_LEVEL_RGMII1(0)
+#define   YT9215_IO_LEVEL_RGMII1_2V5			YT9215_IO_LEVEL_RGMII1(1)
+#define   YT9215_IO_LEVEL_RGMII1_1V8			YT9215_IO_LEVEL_RGMII1(2)
+#define  YT9215_IO_LEVEL_RGMII0_M		GENMASK(1, 0)
+#define   YT9215_IO_LEVEL_RGMII0(x)			FIELD_PREP(YT9215_IO_LEVEL_RGMII0_M, (x))
+#define   YT9215_IO_LEVEL_RGMII0_3V3			YT9215_IO_LEVEL_RGMII0(0)
+#define   YT9215_IO_LEVEL_RGMII0_2V5			YT9215_IO_LEVEL_RGMII0(1)
+#define   YT9215_IO_LEVEL_RGMII0_1V8			YT9215_IO_LEVEL_RGMII0(2)
+#define  YT9218_IO_LEVEL_RGMII1_M		GENMASK(5, 4)
+#define   YT9218_IO_LEVEL_RGMII1(x)			FIELD_PREP(YT9218_IO_LEVEL_RGMII1_M, (x))
+#define   YT9218_IO_LEVEL_RGMII1_3V3			YT9218_IO_LEVEL_RGMII1(0)
+#define   YT9218_IO_LEVEL_RGMII1_2V5			YT9218_IO_LEVEL_RGMII1(1)
+#define   YT9218_IO_LEVEL_RGMII1_1V8			YT9218_IO_LEVEL_RGMII1(2)
+#define  YT9218_IO_LEVEL_RGMII0_M		GENMASK(3, 2)
+#define   YT9218_IO_LEVEL_RGMII0(x)			FIELD_PREP(YT9218_IO_LEVEL_RGMII0_M, (x))
+#define   YT9218_IO_LEVEL_RGMII0_3V3			YT9218_IO_LEVEL_RGMII0(0)
+#define   YT9218_IO_LEVEL_RGMII0_2V5			YT9218_IO_LEVEL_RGMII0(1)
+#define   YT9218_IO_LEVEL_RGMII0_1V8			YT9218_IO_LEVEL_RGMII0(2)
+#define  YT9218_IO_LEVEL_NORMAL_M		GENMASK(1, 0)
+#define   YT9218_IO_LEVEL_NORMAL(x)			FIELD_PREP(YT9218_IO_LEVEL_NORMAL_M, (x))
+#define   YT9218_IO_LEVEL_NORMAL_3V3			YT9218_IO_LEVEL_NORMAL(0)
+#define   YT9218_IO_LEVEL_NORMAL_1V8			YT9218_IO_LEVEL_NORMAL(3)
+#define YT921X_MAC_ADDR_HI2		0x80080
+#define YT921X_MAC_ADDR_LO4		0x80084
+#define YT921X_SERDESn(port)		(0x8008c + 4 * ((port) - 8))
+#define  YT921X_SERDES_MODE_M			GENMASK(9, 7)
+#define   YT921X_SERDES_MODE(x)				FIELD_PREP(YT921X_SERDES_MODE_M, (x))
+#define   YT921X_SERDES_MODE_SGMII			YT921X_SERDES_MODE(0)
+#define   YT921X_SERDES_MODE_REVSGMII			YT921X_SERDES_MODE(1)
+#define   YT921X_SERDES_MODE_1000BASEX			YT921X_SERDES_MODE(2)
+#define   YT921X_SERDES_MODE_100BASEX			YT921X_SERDES_MODE(3)
+#define   YT921X_SERDES_MODE_2500BASEX			YT921X_SERDES_MODE(4)
+#define  YT921X_SERDES_RX_PAUSE			BIT(6)
+#define  YT921X_SERDES_TX_PAUSE			BIT(5)
+#define  YT921X_SERDES_LINK			BIT(4)  /* force link */
+#define  YT921X_SERDES_DUPLEX_FULL		BIT(3)
+#define  YT921X_SERDES_SPEED_M			GENMASK(2, 0)
+#define   YT921X_SERDES_SPEED(x)			FIELD_PREP(YT921X_SERDES_SPEED_M, (x))
+#define   YT921X_SERDES_SPEED_10			YT921X_SERDES_SPEED(0)
+#define   YT921X_SERDES_SPEED_100			YT921X_SERDES_SPEED(1)
+#define   YT921X_SERDES_SPEED_1000			YT921X_SERDES_SPEED(2)
+#define   YT921X_SERDES_SPEED_10000			YT921X_SERDES_SPEED(3)
+#define   YT921X_SERDES_SPEED_2500			YT921X_SERDES_SPEED(4)
+#define YT921X_PORTn_CTRL(port)		(0x80100 + 4 * (port))
+#define  YT921X_PORT_CTRL_PAUSE_AN		BIT(10)
+#define YT921X_PORTn_STATUS(port)	(0x80200 + 4 * (port))
+#define  YT921X_PORT_LINK			BIT(9)  /* CTRL: auto negotiation */
+#define  YT921X_PORT_HALF_PAUSE			BIT(8)  /* Half-duplex back pressure mode */
+#define  YT921X_PORT_DUPLEX_FULL		BIT(7)
+#define  YT921X_PORT_RX_PAUSE			BIT(6)
+#define  YT921X_PORT_TX_PAUSE			BIT(5)
+#define  YT921X_PORT_RX_MAC_EN			BIT(4)
+#define  YT921X_PORT_TX_MAC_EN			BIT(3)
+#define  YT921X_PORT_SPEED_M			GENMASK(2, 0)
+#define   YT921X_PORT_SPEED(x)				FIELD_PREP(YT921X_PORT_SPEED_M, (x))
+#define   YT921X_PORT_SPEED_10				YT921X_PORT_SPEED(0)
+#define   YT921X_PORT_SPEED_100				YT921X_PORT_SPEED(1)
+#define   YT921X_PORT_SPEED_1000			YT921X_PORT_SPEED(2)
+#define   YT921X_PORT_SPEED_10000			YT921X_PORT_SPEED(3)
+#define   YT921X_PORT_SPEED_2500			YT921X_PORT_SPEED(4)
+#define YT921X_PON_STRAP_FUNC		0x80320
+#define YT921X_PON_STRAP_VAL		0x80324
+#define YT921X_PON_STRAP_CAP		0x80328
+#define  YT921X_PON_STRAP_EEE			BIT(16)
+#define  YT921X_PON_STRAP_LOOP_DETECT		BIT(7)
+#define YT921X_MDIO_POLLINGn(port)	(0x80364 + 4 * ((port) - 8))
+#define  YT921X_MDIO_POLLING_DUPLEX_FULL	BIT(4)
+#define  YT921X_MDIO_POLLING_LINK		BIT(3)
+#define  YT921X_MDIO_POLLING_SPEED_M		GENMASK(2, 0)
+#define   YT921X_MDIO_POLLING_SPEED(x)			FIELD_PREP(YT921X_MDIO_POLLING_SPEED_M, (x))
+#define   YT921X_MDIO_POLLING_SPEED_10			YT921X_MDIO_POLLING_SPEED(0)
+#define   YT921X_MDIO_POLLING_SPEED_100			YT921X_MDIO_POLLING_SPEED(1)
+#define   YT921X_MDIO_POLLING_SPEED_1000		YT921X_MDIO_POLLING_SPEED(2)
+#define   YT921X_MDIO_POLLING_SPEED_10000		YT921X_MDIO_POLLING_SPEED(3)
+#define   YT921X_MDIO_POLLING_SPEED_2500		YT921X_MDIO_POLLING_SPEED(4)
+#define YT921X_SENSOR			0x8036c
+#define  YT921X_SENSOR_TEMP			BIT(18)
+#define YT921X_TEMP			0x80374
+#define YT921X_CHIP_MODE		0x80388
+#define  YT921X_CHIP_MODE_MODE			GENMASK(1, 0)
+#define YT921X_XMII_CTRL		0x80394
+#define  YT921X_XMII_CTRL_PORTn(port)		BIT(9 - (port))  /* Yes, it's reversed */
+#define YT921X_XMIIn(port)		(0x80400 + 8 * ((port) - 8))
+#define  YT921X_XMII_MODE_M			GENMASK(31, 29)
+#define   YT921X_XMII_MODE(x)				FIELD_PREP(YT921X_XMII_MODE_M, (x))
+#define   YT921X_XMII_MODE_MII				YT921X_XMII_MODE(0)
+#define   YT921X_XMII_MODE_REVMII			YT921X_XMII_MODE(1)
+#define   YT921X_XMII_MODE_RMII				YT921X_XMII_MODE(2)
+#define   YT921X_XMII_MODE_REVRMII			YT921X_XMII_MODE(3)
+#define   YT921X_XMII_MODE_RGMII			YT921X_XMII_MODE(4)
+#define   YT921X_XMII_MODE_DISABLE			YT921X_XMII_MODE(5)
+#define  YT921X_XMII_LINK			BIT(19)  /* force link */
+#define  YT921X_XMII_EN				BIT(18)
+#define  YT921X_XMII_SOFT_RST			BIT(17)
+#define  YT921X_XMII_RGMII_TX_DELAY_150PS_M	GENMASK(16, 13)
+#define   YT921X_XMII_RGMII_TX_DELAY_150PS(x)		FIELD_PREP(YT921X_XMII_RGMII_TX_DELAY_150PS_M, (x))
+#define  YT921X_XMII_TX_CLK_IN			BIT(11)
+#define  YT921X_XMII_RX_CLK_IN			BIT(10)
+#define  YT921X_XMII_RGMII_TX_DELAY_2NS		BIT(8)
+#define  YT921X_XMII_RGMII_TX_CLK_OUT		BIT(7)
+#define  YT921X_XMII_RGMII_RX_DELAY_150PS_M	GENMASK(6, 3)
+#define   YT921X_XMII_RGMII_RX_DELAY_150PS(x)		FIELD_PREP(YT921X_XMII_RGMII_RX_DELAY_150PS_M, (x))
+#define  YT921X_XMII_RMII_PHY_TX_CLK_OUT	BIT(2)
+#define  YT921X_XMII_REVMII_TX_CLK_OUT		BIT(1)
+#define  YT921X_XMII_REVMII_RX_CLK_OUT		BIT(0)
+
+#define YT921X_MACn_FRAME(port)		(0x81008 + 0x1000 * (port))
+#define  YT921X_MAC_FRAME_SIZE_M		GENMASK(21, 8)
+#define   YT921X_MAC_FRAME_SIZE(x)			FIELD_PREP(YT921X_MAC_FRAME_SIZE_M, (x))
+
+#define YT921X_EEEn_VAL(port)		(0xa0000 + 0x40 * (port))
+#define  YT921X_EEE_VAL_DATA			BIT(1)
+
+#define YT921X_EEE_CTRL			0xb0000
+#define  YT921X_EEE_CTRL_ENn(port)		BIT(port)
+
+#define YT921X_MIB_CTRL			0xc0004
+#define  YT921X_MIB_CTRL_CLEAN			BIT(30)
+#define  YT921X_MIB_CTRL_PORT_M			GENMASK(6, 3)
+#define   YT921X_MIB_CTRL_PORT(x)			FIELD_PREP(YT921X_MIB_CTRL_PORT_M, (x))
+#define  YT921X_MIB_CTRL_ONE_PORT		BIT(1)
+#define  YT921X_MIB_CTRL_ALL_PORT		BIT(0)
+#define YT921X_MIBn_DATA0(port)		(0xc0100 + 0x100 * (port))
+#define YT921X_MIBn_DATAm(port, x)	(YT921X_MIBn_DATA0(port) + 4 * (x))
+#define  YT921X_MIB_DATA_RX_BROADCAST		0x00
+#define  YT921X_MIB_DATA_RX_PAUSE		0x04
+#define  YT921X_MIB_DATA_RX_MULTICAST		0x08
+#define  YT921X_MIB_DATA_RX_CRC_ERR		0x0c
+
+#define  YT921X_MIB_DATA_RX_ALIGN_ERR		0x10
+#define  YT921X_MIB_DATA_RX_UNDERSIZE_ERR	0x14
+#define  YT921X_MIB_DATA_RX_FRAG_ERR		0x18
+#define  YT921X_MIB_DATA_RX_PKT_SZ_64		0x1c
+
+#define  YT921X_MIB_DATA_RX_PKT_SZ_65_TO_127	0x20
+#define  YT921X_MIB_DATA_RX_PKT_SZ_128_TO_255	0x24
+#define  YT921X_MIB_DATA_RX_PKT_SZ_256_TO_511	0x28
+#define  YT921X_MIB_DATA_RX_PKT_SZ_512_TO_1023	0x2c
+
+#define  YT921X_MIB_DATA_RX_PKT_SZ_1024_TO_1518	0x30
+#define  YT921X_MIB_DATA_RX_PKT_SZ_1519_TO_MAX	0x34
+/* 0x38: unused */
+#define  YT921X_MIB_DATA_RX_GOOD_BYTES		0x3c
+
+/* 0x40: 64 bytes */
+#define  YT921X_MIB_DATA_RX_BAD_BYTES		0x44
+/* 0x48: 64 bytes */
+#define  YT921X_MIB_DATA_RX_OVERSIZE_ERR	0x4c
+
+#define  YT921X_MIB_DATA_RX_DROPPED		0x50
+#define  YT921X_MIB_DATA_TX_BROADCAST		0x54
+#define  YT921X_MIB_DATA_TX_PAUSE		0x58
+#define  YT921X_MIB_DATA_TX_MULTICAST		0x5c
+
+#define  YT921X_MIB_DATA_TX_UNDERSIZE_ERR	0x60
+#define  YT921X_MIB_DATA_TX_PKT_SZ_64		0x64
+#define  YT921X_MIB_DATA_TX_PKT_SZ_65_TO_127	0x68
+#define  YT921X_MIB_DATA_TX_PKT_SZ_128_TO_255	0x6c
+
+#define  YT921X_MIB_DATA_TX_PKT_SZ_256_TO_511	0x70
+#define  YT921X_MIB_DATA_TX_PKT_SZ_512_TO_1023	0x74
+#define  YT921X_MIB_DATA_TX_PKT_SZ_1024_TO_1518	0x78
+#define  YT921X_MIB_DATA_TX_PKT_SZ_1519_TO_MAX	0x7c
+
+/* 0x80: unused */
+#define  YT921X_MIB_DATA_TX_GOOD_BYTES		0x84
+/* 0x88: 64 bytes */
+#define  YT921X_MIB_DATA_TX_COLLISION		0x8c
+
+#define  YT921X_MIB_DATA_TX_EXCESSIVE_COLLISION	0x90
+#define  YT921X_MIB_DATA_TX_MULTIPLE_COLLISION	0x94
+#define  YT921X_MIB_DATA_TX_SINGLE_COLLISION	0x98
+#define  YT921X_MIB_DATA_TX_PKT			0x9c
+
+#define  YT921X_MIB_DATA_TX_DEFERRED		0xa0
+#define  YT921X_MIB_DATA_TX_LATE_COLLISION	0xa4
+#define  YT921X_MIB_DATA_RX_OAM			0xa8
+#define  YT921X_MIB_DATA_TX_OAM			0xac
+
+#define YT921X_EDATA_CTRL		0xe0000
+#define  YT921X_EDATA_CTRL_ADDR_M		GENMASK(15, 8)
+#define   YT921X_EDATA_CTRL_ADDR(x)			FIELD_PREP(YT921X_EDATA_CTRL_ADDR_M, (x))
+#define  YT921X_EDATA_CTRL_OP_M			GENMASK(3, 0)
+#define   YT921X_EDATA_CTRL_OP(x)			FIELD_PREP(YT921X_EDATA_CTRL_OP_M, (x))
+#define   YT921X_EDATA_CTRL_READ			YT921X_EDATA_CTRL_OP(5)
+#define YT921X_EDATA_DATA		0xe0004
+#define  YT921X_EDATA_DATA_DATA_M			GENMASK(31, 24)
+#define  YT921X_EDATA_DATA_STATUS_M		GENMASK(3, 0)
+#define   YT921X_EDATA_DATA_STATUS(x)			FIELD_PREP(YT921X_EDATA_DATA_STATUS_M, (x))
+#define   YT921X_EDATA_DATA_IDLE			YT921X_EDATA_DATA_STATUS(3)
+
+#define YT921X_EXT_MBUS_OP		0x6a000
+#define YT921X_INT_MBUS_OP		0xf0000
+#define  YT921X_MBUS_OP_START			BIT(0)
+#define YT921X_EXT_MBUS_CTRL		0x6a004
+#define YT921X_INT_MBUS_CTRL		0xf0004
+#define  YT921X_MBUS_CTRL_PORT_M		GENMASK(25, 21)
+#define   YT921X_MBUS_CTRL_PORT(x)			FIELD_PREP(YT921X_MBUS_CTRL_PORT_M, (x))
+#define  YT921X_MBUS_CTRL_REG_M			GENMASK(20, 16)
+#define   YT921X_MBUS_CTRL_REG(x)			FIELD_PREP(YT921X_MBUS_CTRL_REG_M, (x))
+#define  YT921X_MBUS_CTRL_TYPE_M		GENMASK(11, 8)  /* wild guess */
+#define   YT921X_MBUS_CTRL_TYPE(x)			FIELD_PREP(YT921X_MBUS_CTRL_TYPE_M, (x))
+#define   YT921X_MBUS_CTRL_TYPE_C22			YT921X_MBUS_CTRL_TYPE(4)
+#define  YT921X_MBUS_CTRL_OP_M			GENMASK(3, 2)  /* wild guess */
+#define   YT921X_MBUS_CTRL_OP(x)			FIELD_PREP(YT921X_MBUS_CTRL_OP_M, (x))
+#define   YT921X_MBUS_CTRL_WRITE			YT921X_MBUS_CTRL_OP(1)
+#define   YT921X_MBUS_CTRL_READ				YT921X_MBUS_CTRL_OP(2)
+#define YT921X_EXT_MBUS_DOUT		0x6a008
+#define YT921X_INT_MBUS_DOUT		0xf0008
+#define YT921X_EXT_MBUS_DIN		0x6a00c
+#define YT921X_INT_MBUS_DIN		0xf000c
+
+#define YT921X_PORTn_EGR(port)		(0x100000 + 4 * (port))
+#define  YT921X_PORT_EGR_TPID_CTAG_M		GENMASK(5, 4)
+#define   YT921X_PORT_EGR_TPID_CTAG(x)			FIELD_PREP(YT921X_PORT_EGR_TPID_CTAG_M, (x))
+#define  YT921X_PORT_EGR_TPID_STAG_M		GENMASK(3, 2)
+#define   YT921X_PORT_EGR_TPID_STAG(x)			FIELD_PREP(YT921X_PORT_EGR_TPID_STAG_M, (x))
+#define YT921X_TPID_EGRn(x)		(0x100300 + 4 * (x))	/* [0, 3] */
+#define  YT921X_TPID_EGR_TPID_M			GENMASK(15, 0)
+
+#define YT921X_VLAN_IGR_FILTER		0x180280
+#define  YT921X_VLAN_IGR_FILTER_PORTn_BYPASS_IGMP(port)	BIT((port) + 11)
+#define  YT921X_VLAN_IGR_FILTER_PORTn(port)	BIT(port)
+#define YT921X_PORTn_ISOLATION(port)	(0x180294 + 4 * (port))
+#define  YT921X_PORT_ISOLATION_BLOCKn(port)	BIT(port)
+#define YT921X_STPn(n)			(0x18038c + 4 * (n))
+#define  YT921X_STP_PORTn_M(port)		GENMASK(2 * (port) + 1, 2 * (port))
+#define   YT921X_STP_PORTn(port, x)			((x) << (2 * (port)))
+#define   YT921X_STP_PORTn_DISABLED(port)		YT921X_STP_PORTn(port, 0)
+#define   YT921X_STP_PORTn_LEARNING(port)		YT921X_STP_PORTn(port, 1)
+#define   YT921X_STP_PORTn_BLOCKING(port)		YT921X_STP_PORTn(port, 2)
+#define   YT921X_STP_PORTn_FORWARD(port)		YT921X_STP_PORTn(port, 3)
+#define YT921X_PORTn_LEARN(port)	(0x1803d0 + 4 * (port))
+#define  YT921X_PORT_LEARN_VID_LEARN_MULTI_EN	BIT(22)
+#define  YT921X_PORT_LEARN_VID_LEARN_MODE	BIT(21)
+#define  YT921X_PORT_LEARN_VID_LEARN_EN		BIT(20)
+#define  YT921X_PORT_LEARN_SUSPEND_COPY_EN	BIT(19)
+#define  YT921X_PORT_LEARN_SUSPEND_DROP_EN	BIT(18)
+#define  YT921X_PORT_LEARN_DIS			BIT(17)
+#define  YT921X_PORT_LEARN_LIMIT_EN		BIT(16)
+#define  YT921X_PORT_LEARN_LIMIT_M		GENMASK(15, 8)
+#define   YT921X_PORT_LEARN_LIMIT(x)			FIELD_PREP(YT921X_PORT_LEARN_LIMIT_M, (x))
+#define  YT921X_PORT_LEARN_DROP_ON_EXCEEDED	BIT(2)
+#define  YT921X_PORT_LEARN_MODE_M		GENMASK(1, 0)
+#define   YT921X_PORT_LEARN_MODE(x)			FIELD_PREP(YT921X_PORT_LEARN_MODE_M, (x))
+#define   YT921X_PORT_LEARN_MODE_AUTO			YT921X_PORT_LEARN_MODE(0)
+#define   YT921X_PORT_LEARN_MODE_AUTO_AND_COPY		YT921X_PORT_LEARN_MODE(1)
+#define   YT921X_PORT_LEARN_MODE_CPU_CONTROL		YT921X_PORT_LEARN_MODE(2)
+#define YT921X_AGEING			0x180440
+#define  YT921X_AGEING_INTERVAL_M		GENMASK(15, 0)
+#define YT921X_FDB_IN0			0x180454
+#define YT921X_FDB_IN1			0x180458
+#define YT921X_FDB_IN2			0x18045c
+#define YT921X_FDB_OP			0x180460
+#define  YT921X_FDB_OP_INDEX_M			GENMASK(22, 11)
+#define   YT921X_FDB_OP_INDEX(x)			FIELD_PREP(YT921X_FDB_OP_INDEX_M, (x))
+#define  YT921X_FDB_OP_MODE_INDEX		BIT(10)  /* mac+fid / index */
+#define  YT921X_FDB_OP_FLUSH_MCAST		BIT(9)  /* ucast / mcast */
+#define  YT921X_FDB_OP_FLUSH_M			GENMASK(8, 7)
+#define   YT921X_FDB_OP_FLUSH(x)			FIELD_PREP(YT921X_FDB_OP_FLUSH_M, (x))
+#define   YT921X_FDB_OP_FLUSH_ALL			YT921X_FDB_OP_FLUSH(0)
+#define   YT921X_FDB_OP_FLUSH_PORT			YT921X_FDB_OP_FLUSH(1)
+#define   YT921X_FDB_OP_FLUSH_PORT_VID			YT921X_FDB_OP_FLUSH(2)
+#define   YT921X_FDB_OP_FLUSH_VID			YT921X_FDB_OP_FLUSH(3)
+#define  YT921X_FDB_OP_FLUSH_STATIC		BIT(6)
+#define  YT921X_FDB_OP_NEXT_TYPE_M		GENMASK(5, 4)
+#define   YT921X_FDB_OP_NEXT_TYPE(x)			FIELD_PREP(YT921X_FDB_OP_NEXT_TYPE_M, (x))
+#define   YT921X_FDB_OP_NEXT_TYPE_UCAST_PORT		YT921X_FDB_OP_NEXT_TYPE(0)
+#define   YT921X_FDB_OP_NEXT_TYPE_UCAST_VID		YT921X_FDB_OP_NEXT_TYPE(1)
+#define   YT921X_FDB_OP_NEXT_TYPE_UCAST			YT921X_FDB_OP_NEXT_TYPE(2)
+#define   YT921X_FDB_OP_NEXT_TYPE_MCAST			YT921X_FDB_OP_NEXT_TYPE(3)
+#define  YT921X_FDB_OP_OP_M			GENMASK(3, 1)
+#define   YT921X_FDB_OP_OP(x)				FIELD_PREP(YT921X_FDB_OP_OP_M, (x))
+#define   YT921X_FDB_OP_OP_ADD				YT921X_FDB_OP_OP(0)
+#define   YT921X_FDB_OP_OP_DEL				YT921X_FDB_OP_OP(1)
+#define   YT921X_FDB_OP_OP_GET_ONE			YT921X_FDB_OP_OP(2)
+#define   YT921X_FDB_OP_OP_GET_NEXT			YT921X_FDB_OP_OP(3)
+#define   YT921X_FDB_OP_OP_FLUSH			YT921X_FDB_OP_OP(4)
+#define  YT921X_FDB_OP_START			BIT(0)
+#define YT921X_FDB_RESULT		0x180464
+#define  YT921X_FDB_RESULT_DONE			BIT(15)
+#define  YT921X_FDB_RESULT_NOTFOUND		BIT(14)
+#define  YT921X_FDB_RESULT_OVERWRITED		BIT(13)
+#define  YT921X_FDB_RESULT_INDEX_M		GENMASK(11, 0)
+#define   YT921X_FDB_RESULT_INDEX(x)			FIELD_PREP(YT921X_FDB_RESULT_INDEX_M, (x))
+#define YT921X_FDB_OUT0			0x1804b0
+#define  YT921X_FDB_IO0_ADDR_HI4_M		GENMASK(31, 0)
+#define YT921X_FDB_OUT1			0x1804b4
+#define  YT921X_FDB_IO1_EGR_INT_PRI_EN		BIT(31)
+#define  YT921X_FDB_IO1_STATUS_M		GENMASK(30, 28)
+#define   YT921X_FDB_IO1_STATUS(x)			FIELD_PREP(YT921X_FDB_IO1_STATUS_M, (x))
+#define   YT921X_FDB_IO1_STATUS_INVALID			YT921X_FDB_IO1_STATUS(0)
+#define   YT921X_FDB_IO1_STATUS_MIN_TIME		YT921X_FDB_IO1_STATUS(1)
+#define   YT921X_FDB_IO1_STATUS_MOVE_AGING_MAX_TIME	YT921X_FDB_IO1_STATUS(3)
+#define   YT921X_FDB_IO1_STATUS_MAX_TIME		YT921X_FDB_IO1_STATUS(5)
+#define   YT921X_FDB_IO1_STATUS_PENDING			YT921X_FDB_IO1_STATUS(6)
+#define   YT921X_FDB_IO1_STATUS_STATIC			YT921X_FDB_IO1_STATUS(7)
+#define  YT921X_FDB_IO1_FID_M			GENMASK(27, 16)  /* filtering ID (VID) */
+#define   YT921X_FDB_IO1_FID(x)				FIELD_PREP(YT921X_FDB_IO1_FID_M, (x))
+#define  YT921X_FDB_IO1_ADDR_LO2_M		GENMASK(15, 0)
+#define YT921X_FDB_OUT2			0x1804b8
+#define  YT921X_FDB_IO2_MOVE_AGING_STATUS_M	GENMASK(31, 30)
+#define  YT921X_FDB_IO2_IGR_DROP		BIT(29)
+#define  YT921X_FDB_IO2_EGR_PORTS_M		GENMASK(28, 18)
+#define   YT921X_FDB_IO2_EGR_PORTS(x)			FIELD_PREP(YT921X_FDB_IO2_EGR_PORTS_M, (x))
+#define  YT921X_FDB_IO2_EGR_DROP		BIT(17)
+#define  YT921X_FDB_IO2_COPY_TO_CPU		BIT(16)
+#define  YT921X_FDB_IO2_IGR_INT_PRI_EN		BIT(15)
+#define  YT921X_FDB_IO2_INT_PRI_M		GENMASK(14, 12)
+#define   YT921X_FDB_IO2_INT_PRI(x)			FIELD_PREP(YT921X_FDB_IO2_INT_PRI_M, (x))
+#define  YT921X_FDB_IO2_NEW_VID_M		GENMASK(11, 0)
+#define   YT921X_FDB_IO2_NEW_VID(x)			FIELD_PREP(YT921X_FDB_IO2_NEW_VID_M, (x))
+#define YT921X_FILTER_UNK_UCAST		0x180508
+#define YT921X_FILTER_UNK_MCAST		0x18050c
+#define YT921X_FILTER_MCAST		0x180510
+#define YT921X_FILTER_BCAST		0x180514
+#define  YT921X_FILTER_PORTS_M			GENMASK(10, 0)
+#define   YT921X_FILTER_PORTS(x)			FIELD_PREP(YT921X_FILTER_PORTS_M, (x))
+#define  YT921X_FILTER_PORTn(port)		BIT(port)
+#define YT921X_VLAN_EGR_FILTER		0x180598
+#define  YT921X_VLAN_EGR_FILTER_PORTn(port)	BIT(port)
+#define YT921X_CPU_COPY			0x180690
+#define  YT921X_CPU_COPY_FORCE_INT_PORT		BIT(2)
+#define  YT921X_CPU_COPY_TO_INT_CPU		BIT(1)
+#define  YT921X_CPU_COPY_TO_EXT_CPU		BIT(0)
+#define YT921X_ACT_UNK_UCAST		0x180734
+#define YT921X_ACT_UNK_MCAST		0x180738
+#define  YT921X_ACT_UNK_MCAST_BYPASS_DROP_RMA	BIT(23)
+#define  YT921X_ACT_UNK_MCAST_BYPASS_DROP_IGMP	BIT(22)
+#define  YT921X_ACT_UNK_ACTn_M(port)		GENMASK(2 * (port) + 1, 2 * (port))
+#define   YT921X_ACT_UNK_ACTn(port, x)			((x) << (2 * (port)))
+#define   YT921X_ACT_UNK_ACTn_FORWARD(port)		YT921X_ACT_UNK_ACTn(port, 0)  /* flood */
+#define   YT921X_ACT_UNK_ACTn_TRAP(port)		YT921X_ACT_UNK_ACTn(port, 1)  /* steer to CPU */
+#define   YT921X_ACT_UNK_ACTn_DROP(port)		YT921X_ACT_UNK_ACTn(port, 2)  /* discard */
+/* NEVER use this action; see comments in the tag driver */
+#define   YT921X_ACT_UNK_ACTn_COPY(port)		YT921X_ACT_UNK_ACTn(port, 3)  /* flood and copy */
+#define YT921X_FDB_HW_FLUSH		0x180958
+#define  YT921X_FDB_HW_FLUSH_ON_LINKDOWN	BIT(0)
+
+#define YT921X_VLANn_CTRL(vlan)		(0x188000 + 8 * (vlan))
+#define  YT921X_VLAN_CTRL_UNTAG_PORTS_M		GENMASK_ULL(50, 40)
+#define   YT921X_VLAN_CTRL_UNTAG_PORTS(x)		FIELD_PREP(YT921X_VLAN_CTRL_UNTAG_PORTS_M, (x))
+#define  YT921X_VLAN_CTRL_UNTAG_PORTn(port)	BIT_ULL((port) + 40)
+#define  YT921X_VLAN_CTRL_STP_ID_M		GENMASK_ULL(39, 36)
+#define   YT921X_VLAN_CTRL_STP_ID(x)			FIELD_PREP(YT921X_VLAN_CTRL_STP_ID_M, (x))
+#define  YT921X_VLAN_CTRL_SVLAN_EN		BIT_ULL(35)
+#define  YT921X_VLAN_CTRL_FID_M			GENMASK_ULL(34, 23)
+#define   YT921X_VLAN_CTRL_FID(x)			FIELD_PREP(YT921X_VLAN_CTRL_FID_M, (x))
+#define  YT921X_VLAN_CTRL_LEARN_DIS		BIT_ULL(22)
+#define  YT921X_VLAN_CTRL_INT_PRI_EN		BIT_ULL(21)
+#define  YT921X_VLAN_CTRL_INT_PRI_M		GENMASK_ULL(20, 18)
+#define  YT921X_VLAN_CTRL_PORTS_M		GENMASK_ULL(17, 7)
+#define   YT921X_VLAN_CTRL_PORTS(x)			FIELD_PREP(YT921X_VLAN_CTRL_PORTS_M, (x))
+#define  YT921X_VLAN_CTRL_PORTn(port)		BIT_ULL((port) + 7)
+#define  YT921X_VLAN_CTRL_BYPASS_1X_AC		BIT_ULL(6)
+#define  YT921X_VLAN_CTRL_METER_EN		BIT_ULL(5)
+#define  YT921X_VLAN_CTRL_METER_ID_M		GENMASK_ULL(4, 0)
+
+#define YT921X_TPID_IGRn(x)		(0x210000 + 4 * (x))	/* [0, 3] */
+#define  YT921X_TPID_IGR_TPID_M			GENMASK(15, 0)
+#define YT921X_PORTn_IGR_TPID(port)	(0x210010 + 4 * (port))
+#define  YT921X_PORT_IGR_TPIDn_STAG_M		GENMASK(7, 4)
+#define  YT921X_PORT_IGR_TPIDn_STAG(x)		BIT((x) + 4)
+#define  YT921X_PORT_IGR_TPIDn_CTAG_M		GENMASK(3, 0)
+#define  YT921X_PORT_IGR_TPIDn_CTAG(x)		BIT(x)
+
+#define YT921X_PORTn_VLAN_CTRL(port)	(0x230010 + 4 * (port))
+#define  YT921X_PORT_VLAN_CTRL_SVLAN_PRI_EN	BIT(31)
+#define  YT921X_PORT_VLAN_CTRL_CVLAN_PRI_EN	BIT(30)
+#define  YT921X_PORT_VLAN_CTRL_SVID_M		GENMASK(29, 18)
+#define   YT921X_PORT_VLAN_CTRL_SVID(x)			FIELD_PREP(YT921X_PORT_VLAN_CTRL_SVID_M, (x))
+#define  YT921X_PORT_VLAN_CTRL_CVID_M		GENMASK(17, 6)
+#define   YT921X_PORT_VLAN_CTRL_CVID(x)			FIELD_PREP(YT921X_PORT_VLAN_CTRL_CVID_M, (x))
+#define  YT921X_PORT_VLAN_CTRL_SVLAN_PRI_M	GENMASK(5, 3)
+#define  YT921X_PORT_VLAN_CTRL_CVLAN_PRI_M	GENMASK(2, 0)
+#define YT921X_PORTn_VLAN_CTRL1(port)	(0x230080 + 4 * (port))
+#define  YT921X_PORT_VLAN_CTRL1_VLAN_RANGE_EN	BIT(8)
+#define  YT921X_PORT_VLAN_CTRL1_VLAN_RANGE_PROFILE_ID_M	GENMASK(7, 4)
+#define  YT921X_PORT_VLAN_CTRL1_SVLAN_DROP_TAGGED	BIT(3)
+#define  YT921X_PORT_VLAN_CTRL1_SVLAN_DROP_UNTAGGED	BIT(2)
+#define  YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_TAGGED	BIT(1)
+#define  YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_UNTAGGED	BIT(0)
+
+#define YT921X_MIRROR			0x300300
+#define  YT921X_MIRROR_IGR_PORTS_M		GENMASK(26, 16)
+#define   YT921X_MIRROR_IGR_PORTS(x)			FIELD_PREP(YT921X_MIRROR_IGR_PORTS_M, (x))
+#define  YT921X_MIRROR_IGR_PORTn(port)		BIT((port) + 16)
+#define  YT921X_MIRROR_EGR_PORTS_M		GENMASK(14, 4)
+#define   YT921X_MIRROR_EGR_PORTS(x)			FIELD_PREP(YT921X_MIRROR_EGR_PORTS_M, (x))
+#define  YT921X_MIRROR_EGR_PORTn(port)		BIT((port) + 4)
+#define  YT921X_MIRROR_PORT_M			GENMASK(3, 0)
+#define   YT921X_MIRROR_PORT(x)				FIELD_PREP(YT921X_MIRROR_PORT_M, (x))
+
+#define YT921X_EDATA_EXTMODE	0xfb
+#define YT921X_EDATA_LEN	0x100
+
+#define YT921X_FDB_NUM	4096
+
+enum yt921x_fdb_entry_status {
+	YT921X_FDB_ENTRY_STATUS_INVALID = 0,
+	YT921X_FDB_ENTRY_STATUS_MIN_TIME = 1,
+	YT921X_FDB_ENTRY_STATUS_MOVE_AGING_MAX_TIME = 3,
+	YT921X_FDB_ENTRY_STATUS_MAX_TIME = 5,
+	YT921X_FDB_ENTRY_STATUS_PENDING = 6,
+	YT921X_FDB_ENTRY_STATUS_STATIC = 7,
+};
+
+#define YT921X_MSTI_NUM		16
+
+#define YT9215_MAJOR	0x9002
+#define YT9218_MAJOR	0x9001
+
+/* required for a hard reset */
+#define YT921X_RST_DELAY_US	10000
+
+#define YT921X_FRAME_SIZE_MAX	0x2400  /* 9216 */
+
+#define YT921X_TAG_LEN	8
+
+/* 8 internal + 2 external + 1 mcu */
+#define YT921X_PORT_NUM			11
+
+#define yt921x_port_is_internal(port) ((port) < 8)
+#define yt921x_port_is_external(port) (8 <= (port) && (port) < 9)
+
+struct yt921x_mib {
+	u64 rx_broadcast;
+	u64 rx_pause;
+	u64 rx_multicast;
+	u64 rx_crc_errors;
+
+	u64 rx_alignment_errors;
+	u64 rx_undersize_errors;
+	u64 rx_fragment_errors;
+	u64 rx_64byte;
+
+	u64 rx_65_127byte;
+	u64 rx_128_255byte;
+	u64 rx_256_511byte;
+	u64 rx_512_1023byte;
+
+	u64 rx_1024_1518byte;
+	u64 rx_jumbo;
+	u64 rx_good_bytes;
+
+	u64 rx_bad_bytes;
+	u64 rx_oversize_errors;
+
+	u64 rx_dropped;
+	u64 tx_broadcast;
+	u64 tx_pause;
+	u64 tx_multicast;
+
+	u64 tx_undersize_errors;
+	u64 tx_64byte;
+	u64 tx_65_127byte;
+	u64 tx_128_255byte;
+
+	u64 tx_256_511byte;
+	u64 tx_512_1023byte;
+	u64 tx_1024_1518byte;
+	u64 tx_jumbo;
+
+	u64 tx_good_bytes;
+	u64 tx_collisions;
+
+	u64 tx_aborted_errors;
+	u64 tx_multiple_collisions;
+	u64 tx_single_collisions;
+	u64 tx_good;
+
+	u64 tx_deferred;
+	u64 tx_late_collisions;
+	u64 rx_oam;
+	u64 tx_oam;
+};
+
+struct yt921x_port {
+	unsigned char index;
+
+	bool hairpin;
+	bool isolated;
+
+	struct delayed_work mib_read;
+	struct yt921x_mib mib;
+	u64 rx_frames;
+	u64 tx_frames;
+};
+
+struct yt921x_reg_ops {
+	int (*read)(void *context, u32 reg, u32 *valp);
+	int (*write)(void *context, u32 reg, u32 val);
+};
+
+struct yt921x_priv {
+	struct dsa_switch ds;
+
+	const struct yt921x_info *info;
+	/* cache of dsa_cpu_ports(ds) */
+	u16 cpu_ports_mask;
+
+	/* protect the access to the switch registers */
+	struct mutex reg_lock;
+	const struct yt921x_reg_ops *reg_ops;
+	void *reg_ctx;
+
+	/* mdio master bus */
+	struct mii_bus *mbus_int;
+	struct mii_bus *mbus_ext;
+
+	struct yt921x_port ports[YT921X_PORT_NUM];
+
+	u16 eee_ports_mask;
+};
+
+#endif
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 005d79975f3b..d6bdad4baadd 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -38,6 +38,7 @@
 #include <linux/moduleparam.h>
 #include <linux/rtnetlink.h>
 #include <linux/net_tstamp.h>
+#include <net/netdev_lock.h>
 #include <net/rtnetlink.h>
 #include <linux/u64_stats_sync.h>
 
@@ -104,6 +105,7 @@ static void dummy_setup(struct net_device *dev)
 	dev->netdev_ops = &dummy_netdev_ops;
 	dev->ethtool_ops = &dummy_ethtool_ops;
 	dev->needs_free_netdev = true;
+	dev->request_ops_lock = true;
 
 	/* Fill in device structure with ethernet-generic values. */
 	dev->flags |= IFF_NOARP;
diff --git a/drivers/net/eql.c b/drivers/net/eql.c
index 3c2efda916f1..9ba10efd3794 100644
--- a/drivers/net/eql.c
+++ b/drivers/net/eql.c
@@ -143,7 +143,7 @@ static void eql_kill_one_slave(slave_queue_t *queue, slave_t *slave);
 
 static void eql_timer(struct timer_list *t)
 {
-	equalizer_t *eql = from_timer(eql, t, timer);
+	equalizer_t *eql = timer_container_of(eql, t, timer);
 	struct list_head *this, *tmp, *head;
 
 	spin_lock(&eql->queue.lock);
@@ -254,7 +254,7 @@ static int eql_close(struct net_device *dev)
 	 *	at the data structure it scans every so often...
 	 */
 
-	del_timer_sync(&eql->timer);
+	timer_delete_sync(&eql->timer);
 
 	eql_kill_slave_queue(&eql->queue);
 
diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c
index 4725a8cfd695..2227c83a4862 100644
--- a/drivers/net/ethernet/3com/3c515.c
+++ b/drivers/net/ethernet/3com/3c515.c
@@ -859,7 +859,7 @@ static int corkscrew_open(struct net_device *dev)
 static void corkscrew_timer(struct timer_list *t)
 {
 #ifdef AUTOMEDIA
-	struct corkscrew_private *vp = from_timer(vp, t, timer);
+	struct corkscrew_private *vp = timer_container_of(vp, t, timer);
 	struct net_device *dev = vp->our_dev;
 	int ioaddr = dev->base_addr;
 	unsigned long flags;
@@ -1414,7 +1414,7 @@ static int corkscrew_close(struct net_device *dev)
 			dev->name, rx_nocopy, rx_copy, queued_packet);
 	}
 
-	del_timer_sync(&vp->timer);
+	timer_delete_sync(&vp->timer);
 
 	/* Turn off statistics ASAP.  We update lp->stats below. */
 	outw(StatsDisable, ioaddr + EL3_CMD);
@@ -1547,9 +1547,8 @@ static const struct ethtool_ops netdev_ethtool_ops = {
 	.set_msglevel		= netdev_set_msglevel,
 };
 
-
 #ifdef MODULE
-void cleanup_module(void)
+static void __exit corkscrew_exit_module(void)
 {
 	while (!list_empty(&root_corkscrew_dev)) {
 		struct net_device *dev;
@@ -1563,4 +1562,5 @@ void cleanup_module(void)
 		free_netdev(dev);
 	}
 }
+module_exit(corkscrew_exit_module);
 #endif				/* MODULE */
diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c
index dc3b7c960611..1f2070497a75 100644
--- a/drivers/net/ethernet/3com/3c574_cs.c
+++ b/drivers/net/ethernet/3com/3c574_cs.c
@@ -858,7 +858,7 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id)
 */
 static void media_check(struct timer_list *t)
 {
-	struct el3_private *lp = from_timer(lp, t, media);
+	struct el3_private *lp = timer_container_of(lp, t, media);
 	struct net_device *dev = lp->p_dev->priv;
 	unsigned int ioaddr = dev->base_addr;
 	unsigned long flags;
@@ -1140,7 +1140,7 @@ static int el3_close(struct net_device *dev)
 
 	link->open--;
 	netif_stop_queue(dev);
-	del_timer_sync(&lp->media);
+	timer_delete_sync(&lp->media);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c
index be58dac0502a..ea49be43b8c3 100644
--- a/drivers/net/ethernet/3com/3c589_cs.c
+++ b/drivers/net/ethernet/3com/3c589_cs.c
@@ -685,7 +685,7 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id)
 
 static void media_check(struct timer_list *t)
 {
-	struct el3_private *lp = from_timer(lp, t, media);
+	struct el3_private *lp = timer_container_of(lp, t, media);
 	struct net_device *dev = lp->p_dev->priv;
 	unsigned int ioaddr = dev->base_addr;
 	u16 media, errs;
@@ -946,7 +946,7 @@ static int el3_close(struct net_device *dev)
 
 	link->open--;
 	netif_stop_queue(dev);
-	del_timer_sync(&lp->media);
+	timer_delete_sync(&lp->media);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 790270912913..8c9cc97efd4e 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -1783,7 +1783,7 @@ out:
 static void
 vortex_timer(struct timer_list *t)
 {
-	struct vortex_private *vp = from_timer(vp, t, timer);
+	struct vortex_private *vp = timer_container_of(vp, t, timer);
 	struct net_device *dev = vp->mii.dev;
 	void __iomem *ioaddr = vp->ioaddr;
 	int next_tick = 60*HZ;
@@ -2691,7 +2691,7 @@ vortex_down(struct net_device *dev, int final_down)
 	netdev_reset_queue(dev);
 	netif_stop_queue(dev);
 
-	del_timer_sync(&vp->timer);
+	timer_delete_sync(&vp->timer);
 
 	/* Turn off statistics ASAP.  We update dev->stats below. */
 	iowrite16(StatsDisable, ioaddr + EL3_CMD);
diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c
index fea489af72fb..7c8213011b5c 100644
--- a/drivers/net/ethernet/8390/axnet_cs.c
+++ b/drivers/net/ethernet/8390/axnet_cs.c
@@ -504,7 +504,7 @@ static int axnet_close(struct net_device *dev)
     
     link->open--;
     netif_stop_queue(dev);
-    del_timer_sync(&info->watchdog);
+    timer_delete_sync(&info->watchdog);
 
     return 0;
 } /* axnet_close */
@@ -550,7 +550,7 @@ static irqreturn_t ei_irq_wrapper(int irq, void *dev_id)
 
 static void ei_watchdog(struct timer_list *t)
 {
-    struct axnet_dev *info = from_timer(info, t, watchdog);
+    struct axnet_dev *info = timer_container_of(info, t, watchdog);
     struct net_device *dev = info->p_dev->priv;
     unsigned int nic_base = dev->base_addr;
     unsigned int mii_addr = nic_base + AXNET_MII_EEP;
diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c
index 780fb4afb6af..19f9c5db3f3b 100644
--- a/drivers/net/ethernet/8390/pcnet_cs.c
+++ b/drivers/net/ethernet/8390/pcnet_cs.c
@@ -947,7 +947,7 @@ static int pcnet_close(struct net_device *dev)
 
     link->open--;
     netif_stop_queue(dev);
-    del_timer_sync(&info->watchdog);
+    timer_delete_sync(&info->watchdog);
 
     return 0;
 } /* pcnet_close */
@@ -1018,7 +1018,7 @@ static irqreturn_t ei_irq_wrapper(int irq, void *dev_id)
 
 static void ei_watchdog(struct timer_list *t)
 {
-    struct pcnet_dev *info = from_timer(info, t, watchdog);
+    struct pcnet_dev *info = timer_container_of(info, t, watchdog);
     struct net_device *dev = info->p_dev->priv;
     unsigned int nic_base = dev->base_addr;
     unsigned int mii_addr = nic_base + DLINK_GPIO;
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 977b42bc1e8c..4a1b368ca7e6 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -20,6 +20,7 @@ source "drivers/net/ethernet/actions/Kconfig"
 source "drivers/net/ethernet/adaptec/Kconfig"
 source "drivers/net/ethernet/aeroflex/Kconfig"
 source "drivers/net/ethernet/agere/Kconfig"
+source "drivers/net/ethernet/airoha/Kconfig"
 source "drivers/net/ethernet/alacritech/Kconfig"
 source "drivers/net/ethernet/allwinner/Kconfig"
 source "drivers/net/ethernet/alteon/Kconfig"
@@ -128,6 +129,7 @@ source "drivers/net/ethernet/microchip/Kconfig"
 source "drivers/net/ethernet/mscc/Kconfig"
 source "drivers/net/ethernet/microsoft/Kconfig"
 source "drivers/net/ethernet/moxa/Kconfig"
+source "drivers/net/ethernet/mucse/Kconfig"
 source "drivers/net/ethernet/myricom/Kconfig"
 
 config FEALNX
@@ -187,6 +189,7 @@ source "drivers/net/ethernet/sis/Kconfig"
 source "drivers/net/ethernet/sfc/Kconfig"
 source "drivers/net/ethernet/smsc/Kconfig"
 source "drivers/net/ethernet/socionext/Kconfig"
+source "drivers/net/ethernet/spacemit/Kconfig"
 source "drivers/net/ethernet/stmicro/Kconfig"
 source "drivers/net/ethernet/sun/Kconfig"
 source "drivers/net/ethernet/sunplus/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 99fa180dedb8..2e18df8ca8ec 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_NET_VENDOR_ADAPTEC) += adaptec/
 obj-$(CONFIG_GRETH) += aeroflex/
 obj-$(CONFIG_NET_VENDOR_ADI) += adi/
 obj-$(CONFIG_NET_VENDOR_AGERE) += agere/
+obj-$(CONFIG_NET_VENDOR_AIROHA) += airoha/
 obj-$(CONFIG_NET_VENDOR_ALACRITECH) += alacritech/
 obj-$(CONFIG_NET_VENDOR_ALLWINNER) += allwinner/
 obj-$(CONFIG_NET_VENDOR_ALTEON) += alteon/
@@ -64,6 +65,7 @@ obj-$(CONFIG_NET_VENDOR_MICREL) += micrel/
 obj-$(CONFIG_NET_VENDOR_MICROCHIP) += microchip/
 obj-$(CONFIG_NET_VENDOR_MICROSEMI) += mscc/
 obj-$(CONFIG_NET_VENDOR_MOXART) += moxa/
+obj-$(CONFIG_NET_VENDOR_MUCSE) += mucse/
 obj-$(CONFIG_NET_VENDOR_MYRI) += myricom/
 obj-$(CONFIG_FEALNX) += fealnx.o
 obj-$(CONFIG_NET_VENDOR_NATSEMI) += natsemi/
@@ -90,6 +92,7 @@ obj-$(CONFIG_NET_VENDOR_SOLARFLARE) += sfc/
 obj-$(CONFIG_NET_VENDOR_SGI) += sgi/
 obj-$(CONFIG_NET_VENDOR_SMSC) += smsc/
 obj-$(CONFIG_NET_VENDOR_SOCIONEXT) += socionext/
+obj-$(CONFIG_NET_VENDOR_SPACEMIT) += spacemit/
 obj-$(CONFIG_NET_VENDOR_STMICRO) += stmicro/
 obj-$(CONFIG_NET_VENDOR_SUN) += sun/
 obj-$(CONFIG_NET_VENDOR_SUNPLUS) += sunplus/
diff --git a/drivers/net/ethernet/actions/owl-emac.c b/drivers/net/ethernet/actions/owl-emac.c
index 115f48b3342c..0a08da799255 100644
--- a/drivers/net/ethernet/actions/owl-emac.c
+++ b/drivers/net/ethernet/actions/owl-emac.c
@@ -1325,15 +1325,10 @@ static int owl_emac_mdio_init(struct net_device *netdev)
 	struct device_node *mdio_node;
 	int ret;
 
-	mdio_node = of_get_child_by_name(dev->of_node, "mdio");
+	mdio_node = of_get_available_child_by_name(dev->of_node, "mdio");
 	if (!mdio_node)
 		return -ENODEV;
 
-	if (!of_device_is_available(mdio_node)) {
-		ret = -ENODEV;
-		goto err_put_node;
-	}
-
 	priv->mii = devm_mdiobus_alloc(dev);
 	if (!priv->mii) {
 		ret = -ENOMEM;
diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c
index 68fad5575fd4..30f9d271e595 100644
--- a/drivers/net/ethernet/adi/adin1110.c
+++ b/drivers/net/ethernet/adi/adin1110.c
@@ -1599,7 +1599,7 @@ static int adin1110_probe_netdevs(struct adin1110_priv *priv)
 		netdev->netdev_ops = &adin1110_netdev_ops;
 		netdev->ethtool_ops = &adin1110_ethtool_ops;
 		netdev->priv_flags |= IFF_UNICAST_FLT;
-		netdev->netns_local = true;
+		netdev->netns_immutable = true;
 
 		port_priv->phydev = get_phy_device(priv->mii_bus, i + 1, false);
 		if (IS_ERR(port_priv->phydev)) {
diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index b325e0cef120..5c8217638dda 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -2459,6 +2459,10 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 							  skb->data,
 							  skb_headlen(skb),
 							  DMA_TO_DEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      dma_addr))
+					return -ENOMEM;
+
 				desc[frag].addr_lo = lower_32_bits(dma_addr);
 				desc[frag].addr_hi = upper_32_bits(dma_addr);
 				frag++;
@@ -2468,6 +2472,10 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 							  skb->data,
 							  skb_headlen(skb) / 2,
 							  DMA_TO_DEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      dma_addr))
+					return -ENOMEM;
+
 				desc[frag].addr_lo = lower_32_bits(dma_addr);
 				desc[frag].addr_hi = upper_32_bits(dma_addr);
 				frag++;
@@ -2478,6 +2486,10 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 							  skb_headlen(skb) / 2,
 							  skb_headlen(skb) / 2,
 							  DMA_TO_DEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      dma_addr))
+					goto unmap_first_out;
+
 				desc[frag].addr_lo = lower_32_bits(dma_addr);
 				desc[frag].addr_hi = upper_32_bits(dma_addr);
 				frag++;
@@ -2489,6 +2501,9 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 						    0,
 						    desc[frag].len_vlan,
 						    DMA_TO_DEVICE);
+			if (dma_mapping_error(&adapter->pdev->dev, dma_addr))
+				goto unmap_out;
+
 			desc[frag].addr_lo = lower_32_bits(dma_addr);
 			desc[frag].addr_hi = upper_32_bits(dma_addr);
 			frag++;
@@ -2578,6 +2593,27 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 		       &adapter->regs->global.watchdog_timer);
 	}
 	return 0;
+
+unmap_out:
+	// Unmap the body of the packet with map_page
+	while (--i) {
+		frag--;
+		dma_addr = desc[frag].addr_lo;
+		dma_addr |= (u64)desc[frag].addr_hi << 32;
+		dma_unmap_page(&adapter->pdev->dev, dma_addr,
+			       desc[frag].len_vlan, DMA_TO_DEVICE);
+	}
+
+unmap_first_out:
+	// Unmap the header with map_single
+	while (frag--) {
+		dma_addr = desc[frag].addr_lo;
+		dma_addr |= (u64)desc[frag].addr_hi << 32;
+		dma_unmap_single(&adapter->pdev->dev, dma_addr,
+				 desc[frag].len_vlan, DMA_TO_DEVICE);
+	}
+
+	return -ENOMEM;
 }
 
 static int send_packet(struct sk_buff *skb, struct et131x_adapter *adapter)
@@ -3076,7 +3112,8 @@ err_out:
  */
 static void et131x_error_timer_handler(struct timer_list *t)
 {
-	struct et131x_adapter *adapter = from_timer(adapter, t, error_timer);
+	struct et131x_adapter *adapter = timer_container_of(adapter, t,
+							    error_timer);
 	struct phy_device *phydev = adapter->netdev->phydev;
 
 	if (et1310_in_phy_coma(adapter)) {
@@ -3639,7 +3676,7 @@ static int et131x_close(struct net_device *netdev)
 	free_irq(adapter->pdev->irq, netdev);
 
 	/* Stop the error timer */
-	return del_timer_sync(&adapter->error_timer);
+	return timer_delete_sync(&adapter->error_timer);
 }
 
 /* et131x_set_packet_filter - Configures the Rx Packet filtering */
diff --git a/drivers/net/ethernet/airoha/Kconfig b/drivers/net/ethernet/airoha/Kconfig
new file mode 100644
index 000000000000..ad3ce501e7a5
--- /dev/null
+++ b/drivers/net/ethernet/airoha/Kconfig
@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config NET_VENDOR_AIROHA
+	bool "Airoha devices"
+	depends on ARCH_AIROHA || COMPILE_TEST
+	help
+	  If you have a Airoha SoC with ethernet, say Y.
+
+if NET_VENDOR_AIROHA
+
+config NET_AIROHA_NPU
+	tristate "Airoha NPU support"
+	select WANT_DEV_COREDUMP
+	select REGMAP_MMIO
+	help
+	  This driver supports Airoha Network Processor (NPU) available
+	  on the Airoha Soc family.
+
+config NET_AIROHA
+	tristate "Airoha SoC Gigabit Ethernet support"
+	depends on NET_DSA || !NET_DSA
+	select NET_AIROHA_NPU
+	select PAGE_POOL
+	help
+	  This driver supports the gigabit ethernet MACs in the
+	  Airoha SoC family.
+
+config NET_AIROHA_FLOW_STATS
+	default y
+	bool "Airoha flow stats"
+	depends on NET_AIROHA && NET_AIROHA_NPU
+	help
+	  Enable Aiorha flowtable statistic counters.
+
+endif #NET_VENDOR_AIROHA
diff --git a/drivers/net/ethernet/airoha/Makefile b/drivers/net/ethernet/airoha/Makefile
new file mode 100644
index 000000000000..94468053e34b
--- /dev/null
+++ b/drivers/net/ethernet/airoha/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Airoha for the Mediatek SoCs built-in ethernet macs
+#
+
+obj-$(CONFIG_NET_AIROHA) += airoha-eth.o
+airoha-eth-y := airoha_eth.o airoha_ppe.o
+airoha-eth-$(CONFIG_DEBUG_FS) += airoha_ppe_debugfs.o
+obj-$(CONFIG_NET_AIROHA_NPU) += airoha_npu.o
diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index d8bfc21a5b19..75893c90a0a1 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -3,841 +3,31 @@
  * Copyright (c) 2024 AIROHA Inc
  * Author: Lorenzo Bianconi <lorenzo@kernel.org>
  */
-#include <linux/etherdevice.h>
-#include <linux/iopoll.h>
-#include <linux/kernel.h>
-#include <linux/netdevice.h>
 #include <linux/of.h>
 #include <linux/of_net.h>
+#include <linux/of_reserved_mem.h>
 #include <linux/platform_device.h>
-#include <linux/reset.h>
 #include <linux/tcp.h>
 #include <linux/u64_stats_sync.h>
-#include <net/dsa.h>
+#include <net/dst_metadata.h>
 #include <net/page_pool/helpers.h>
+#include <net/pkt_cls.h>
 #include <uapi/linux/ppp_defs.h>
 
-#define AIROHA_MAX_NUM_GDM_PORTS	1
-#define AIROHA_MAX_NUM_QDMA		2
-#define AIROHA_MAX_NUM_RSTS		3
-#define AIROHA_MAX_NUM_XSI_RSTS		5
-#define AIROHA_MAX_MTU			2000
-#define AIROHA_MAX_PACKET_SIZE		2048
-#define AIROHA_NUM_TX_RING		32
-#define AIROHA_NUM_RX_RING		32
-#define AIROHA_FE_MC_MAX_VLAN_TABLE	64
-#define AIROHA_FE_MC_MAX_VLAN_PORT	16
-#define AIROHA_NUM_TX_IRQ		2
-#define HW_DSCP_NUM			2048
-#define IRQ_QUEUE_LEN(_n)		((_n) ? 1024 : 2048)
-#define TX_DSCP_NUM			1024
-#define RX_DSCP_NUM(_n)			\
-	((_n) ==  2 ? 128 :		\
-	 (_n) == 11 ? 128 :		\
-	 (_n) == 15 ? 128 :		\
-	 (_n) ==  0 ? 1024 : 16)
-
-#define PSE_RSV_PAGES			128
-#define PSE_QUEUE_RSV_PAGES		64
-
-/* FE */
-#define PSE_BASE			0x0100
-#define CSR_IFC_BASE			0x0200
-#define CDM1_BASE			0x0400
-#define GDM1_BASE			0x0500
-#define PPE1_BASE			0x0c00
-
-#define CDM2_BASE			0x1400
-#define GDM2_BASE			0x1500
-
-#define GDM3_BASE			0x1100
-#define GDM4_BASE			0x2500
-
-#define GDM_BASE(_n)			\
-	((_n) == 4 ? GDM4_BASE :	\
-	 (_n) == 3 ? GDM3_BASE :	\
-	 (_n) == 2 ? GDM2_BASE : GDM1_BASE)
-
-#define REG_FE_DMA_GLO_CFG		0x0000
-#define FE_DMA_GLO_L2_SPACE_MASK	GENMASK(7, 4)
-#define FE_DMA_GLO_PG_SZ_MASK		BIT(3)
-
-#define REG_FE_RST_GLO_CFG		0x0004
-#define FE_RST_GDM4_MBI_ARB_MASK	BIT(3)
-#define FE_RST_GDM3_MBI_ARB_MASK	BIT(2)
-#define FE_RST_CORE_MASK		BIT(0)
-
-#define REG_FE_WAN_MAC_H		0x0030
-#define REG_FE_LAN_MAC_H		0x0040
-
-#define REG_FE_MAC_LMIN(_n)		((_n) + 0x04)
-#define REG_FE_MAC_LMAX(_n)		((_n) + 0x08)
-
-#define REG_FE_CDM1_OQ_MAP0		0x0050
-#define REG_FE_CDM1_OQ_MAP1		0x0054
-#define REG_FE_CDM1_OQ_MAP2		0x0058
-#define REG_FE_CDM1_OQ_MAP3		0x005c
-
-#define REG_FE_PCE_CFG			0x0070
-#define PCE_DPI_EN_MASK			BIT(2)
-#define PCE_KA_EN_MASK			BIT(1)
-#define PCE_MC_EN_MASK			BIT(0)
-
-#define REG_FE_PSE_QUEUE_CFG_WR		0x0080
-#define PSE_CFG_PORT_ID_MASK		GENMASK(27, 24)
-#define PSE_CFG_QUEUE_ID_MASK		GENMASK(20, 16)
-#define PSE_CFG_WR_EN_MASK		BIT(8)
-#define PSE_CFG_OQRSV_SEL_MASK		BIT(0)
-
-#define REG_FE_PSE_QUEUE_CFG_VAL	0x0084
-#define PSE_CFG_OQ_RSV_MASK		GENMASK(13, 0)
-
-#define PSE_FQ_CFG			0x008c
-#define PSE_FQ_LIMIT_MASK		GENMASK(14, 0)
-
-#define REG_FE_PSE_BUF_SET		0x0090
-#define PSE_SHARE_USED_LTHD_MASK	GENMASK(31, 16)
-#define PSE_ALLRSV_MASK			GENMASK(14, 0)
-
-#define REG_PSE_SHARE_USED_THD		0x0094
-#define PSE_SHARE_USED_MTHD_MASK	GENMASK(31, 16)
-#define PSE_SHARE_USED_HTHD_MASK	GENMASK(15, 0)
-
-#define REG_GDM_MISC_CFG		0x0148
-#define GDM2_RDM_ACK_WAIT_PREF_MASK	BIT(9)
-#define GDM2_CHN_VLD_MODE_MASK		BIT(5)
-
-#define REG_FE_CSR_IFC_CFG		CSR_IFC_BASE
-#define FE_IFC_EN_MASK			BIT(0)
-
-#define REG_FE_VIP_PORT_EN		0x01f0
-#define REG_FE_IFC_PORT_EN		0x01f4
-
-#define REG_PSE_IQ_REV1			(PSE_BASE + 0x08)
-#define PSE_IQ_RES1_P2_MASK		GENMASK(23, 16)
-
-#define REG_PSE_IQ_REV2			(PSE_BASE + 0x0c)
-#define PSE_IQ_RES2_P5_MASK		GENMASK(15, 8)
-#define PSE_IQ_RES2_P4_MASK		GENMASK(7, 0)
-
-#define REG_FE_VIP_EN(_n)		(0x0300 + ((_n) << 3))
-#define PATN_FCPU_EN_MASK		BIT(7)
-#define PATN_SWP_EN_MASK		BIT(6)
-#define PATN_DP_EN_MASK			BIT(5)
-#define PATN_SP_EN_MASK			BIT(4)
-#define PATN_TYPE_MASK			GENMASK(3, 1)
-#define PATN_EN_MASK			BIT(0)
-
-#define REG_FE_VIP_PATN(_n)		(0x0304 + ((_n) << 3))
-#define PATN_DP_MASK			GENMASK(31, 16)
-#define PATN_SP_MASK			GENMASK(15, 0)
-
-#define REG_CDM1_VLAN_CTRL		CDM1_BASE
-#define CDM1_VLAN_MASK			GENMASK(31, 16)
-
-#define REG_CDM1_FWD_CFG		(CDM1_BASE + 0x08)
-#define CDM1_VIP_QSEL_MASK		GENMASK(24, 20)
-
-#define REG_CDM1_CRSN_QSEL(_n)		(CDM1_BASE + 0x10 + ((_n) << 2))
-#define CDM1_CRSN_QSEL_REASON_MASK(_n)	\
-	GENMASK(4 + (((_n) % 4) << 3),	(((_n) % 4) << 3))
-
-#define REG_CDM2_FWD_CFG		(CDM2_BASE + 0x08)
-#define CDM2_OAM_QSEL_MASK		GENMASK(31, 27)
-#define CDM2_VIP_QSEL_MASK		GENMASK(24, 20)
-
-#define REG_CDM2_CRSN_QSEL(_n)		(CDM2_BASE + 0x10 + ((_n) << 2))
-#define CDM2_CRSN_QSEL_REASON_MASK(_n)	\
-	GENMASK(4 + (((_n) % 4) << 3),	(((_n) % 4) << 3))
-
-#define REG_GDM_FWD_CFG(_n)		GDM_BASE(_n)
-#define GDM_DROP_CRC_ERR		BIT(23)
-#define GDM_IP4_CKSUM			BIT(22)
-#define GDM_TCP_CKSUM			BIT(21)
-#define GDM_UDP_CKSUM			BIT(20)
-#define GDM_UCFQ_MASK			GENMASK(15, 12)
-#define GDM_BCFQ_MASK			GENMASK(11, 8)
-#define GDM_MCFQ_MASK			GENMASK(7, 4)
-#define GDM_OCFQ_MASK			GENMASK(3, 0)
-
-#define REG_GDM_INGRESS_CFG(_n)		(GDM_BASE(_n) + 0x10)
-#define GDM_INGRESS_FC_EN_MASK		BIT(1)
-#define GDM_STAG_EN_MASK		BIT(0)
-
-#define REG_GDM_LEN_CFG(_n)		(GDM_BASE(_n) + 0x14)
-#define GDM_SHORT_LEN_MASK		GENMASK(13, 0)
-#define GDM_LONG_LEN_MASK		GENMASK(29, 16)
-
-#define REG_FE_CPORT_CFG		(GDM1_BASE + 0x40)
-#define FE_CPORT_PAD			BIT(26)
-#define FE_CPORT_PORT_XFC_MASK		BIT(25)
-#define FE_CPORT_QUEUE_XFC_MASK		BIT(24)
-
-#define REG_FE_GDM_MIB_CLEAR(_n)	(GDM_BASE(_n) + 0xf0)
-#define FE_GDM_MIB_RX_CLEAR_MASK	BIT(1)
-#define FE_GDM_MIB_TX_CLEAR_MASK	BIT(0)
-
-#define REG_FE_GDM1_MIB_CFG		(GDM1_BASE + 0xf4)
-#define FE_STRICT_RFC2819_MODE_MASK	BIT(31)
-#define FE_GDM1_TX_MIB_SPLIT_EN_MASK	BIT(17)
-#define FE_GDM1_RX_MIB_SPLIT_EN_MASK	BIT(16)
-#define FE_TX_MIB_ID_MASK		GENMASK(15, 8)
-#define FE_RX_MIB_ID_MASK		GENMASK(7, 0)
-
-#define REG_FE_GDM_TX_OK_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x104)
-#define REG_FE_GDM_TX_OK_BYTE_CNT_L(_n)		(GDM_BASE(_n) + 0x10c)
-#define REG_FE_GDM_TX_ETH_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x110)
-#define REG_FE_GDM_TX_ETH_BYTE_CNT_L(_n)	(GDM_BASE(_n) + 0x114)
-#define REG_FE_GDM_TX_ETH_DROP_CNT(_n)		(GDM_BASE(_n) + 0x118)
-#define REG_FE_GDM_TX_ETH_BC_CNT(_n)		(GDM_BASE(_n) + 0x11c)
-#define REG_FE_GDM_TX_ETH_MC_CNT(_n)		(GDM_BASE(_n) + 0x120)
-#define REG_FE_GDM_TX_ETH_RUNT_CNT(_n)		(GDM_BASE(_n) + 0x124)
-#define REG_FE_GDM_TX_ETH_LONG_CNT(_n)		(GDM_BASE(_n) + 0x128)
-#define REG_FE_GDM_TX_ETH_E64_CNT_L(_n)		(GDM_BASE(_n) + 0x12c)
-#define REG_FE_GDM_TX_ETH_L64_CNT_L(_n)		(GDM_BASE(_n) + 0x130)
-#define REG_FE_GDM_TX_ETH_L127_CNT_L(_n)	(GDM_BASE(_n) + 0x134)
-#define REG_FE_GDM_TX_ETH_L255_CNT_L(_n)	(GDM_BASE(_n) + 0x138)
-#define REG_FE_GDM_TX_ETH_L511_CNT_L(_n)	(GDM_BASE(_n) + 0x13c)
-#define REG_FE_GDM_TX_ETH_L1023_CNT_L(_n)	(GDM_BASE(_n) + 0x140)
-
-#define REG_FE_GDM_RX_OK_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x148)
-#define REG_FE_GDM_RX_FC_DROP_CNT(_n)		(GDM_BASE(_n) + 0x14c)
-#define REG_FE_GDM_RX_RC_DROP_CNT(_n)		(GDM_BASE(_n) + 0x150)
-#define REG_FE_GDM_RX_OVERFLOW_DROP_CNT(_n)	(GDM_BASE(_n) + 0x154)
-#define REG_FE_GDM_RX_ERROR_DROP_CNT(_n)	(GDM_BASE(_n) + 0x158)
-#define REG_FE_GDM_RX_OK_BYTE_CNT_L(_n)		(GDM_BASE(_n) + 0x15c)
-#define REG_FE_GDM_RX_ETH_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x160)
-#define REG_FE_GDM_RX_ETH_BYTE_CNT_L(_n)	(GDM_BASE(_n) + 0x164)
-#define REG_FE_GDM_RX_ETH_DROP_CNT(_n)		(GDM_BASE(_n) + 0x168)
-#define REG_FE_GDM_RX_ETH_BC_CNT(_n)		(GDM_BASE(_n) + 0x16c)
-#define REG_FE_GDM_RX_ETH_MC_CNT(_n)		(GDM_BASE(_n) + 0x170)
-#define REG_FE_GDM_RX_ETH_CRC_ERR_CNT(_n)	(GDM_BASE(_n) + 0x174)
-#define REG_FE_GDM_RX_ETH_FRAG_CNT(_n)		(GDM_BASE(_n) + 0x178)
-#define REG_FE_GDM_RX_ETH_JABBER_CNT(_n)	(GDM_BASE(_n) + 0x17c)
-#define REG_FE_GDM_RX_ETH_RUNT_CNT(_n)		(GDM_BASE(_n) + 0x180)
-#define REG_FE_GDM_RX_ETH_LONG_CNT(_n)		(GDM_BASE(_n) + 0x184)
-#define REG_FE_GDM_RX_ETH_E64_CNT_L(_n)		(GDM_BASE(_n) + 0x188)
-#define REG_FE_GDM_RX_ETH_L64_CNT_L(_n)		(GDM_BASE(_n) + 0x18c)
-#define REG_FE_GDM_RX_ETH_L127_CNT_L(_n)	(GDM_BASE(_n) + 0x190)
-#define REG_FE_GDM_RX_ETH_L255_CNT_L(_n)	(GDM_BASE(_n) + 0x194)
-#define REG_FE_GDM_RX_ETH_L511_CNT_L(_n)	(GDM_BASE(_n) + 0x198)
-#define REG_FE_GDM_RX_ETH_L1023_CNT_L(_n)	(GDM_BASE(_n) + 0x19c)
-
-#define REG_PPE1_TB_HASH_CFG		(PPE1_BASE + 0x250)
-#define PPE1_SRAM_TABLE_EN_MASK		BIT(0)
-#define PPE1_SRAM_HASH1_EN_MASK		BIT(8)
-#define PPE1_DRAM_TABLE_EN_MASK		BIT(16)
-#define PPE1_DRAM_HASH1_EN_MASK		BIT(24)
-
-#define REG_FE_GDM_TX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x280)
-#define REG_FE_GDM_TX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x284)
-#define REG_FE_GDM_TX_ETH_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x288)
-#define REG_FE_GDM_TX_ETH_BYTE_CNT_H(_n)	(GDM_BASE(_n) + 0x28c)
-
-#define REG_FE_GDM_RX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x290)
-#define REG_FE_GDM_RX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x294)
-#define REG_FE_GDM_RX_ETH_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x298)
-#define REG_FE_GDM_RX_ETH_BYTE_CNT_H(_n)	(GDM_BASE(_n) + 0x29c)
-#define REG_FE_GDM_TX_ETH_E64_CNT_H(_n)		(GDM_BASE(_n) + 0x2b8)
-#define REG_FE_GDM_TX_ETH_L64_CNT_H(_n)		(GDM_BASE(_n) + 0x2bc)
-#define REG_FE_GDM_TX_ETH_L127_CNT_H(_n)	(GDM_BASE(_n) + 0x2c0)
-#define REG_FE_GDM_TX_ETH_L255_CNT_H(_n)	(GDM_BASE(_n) + 0x2c4)
-#define REG_FE_GDM_TX_ETH_L511_CNT_H(_n)	(GDM_BASE(_n) + 0x2c8)
-#define REG_FE_GDM_TX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2cc)
-#define REG_FE_GDM_RX_ETH_E64_CNT_H(_n)		(GDM_BASE(_n) + 0x2e8)
-#define REG_FE_GDM_RX_ETH_L64_CNT_H(_n)		(GDM_BASE(_n) + 0x2ec)
-#define REG_FE_GDM_RX_ETH_L127_CNT_H(_n)	(GDM_BASE(_n) + 0x2f0)
-#define REG_FE_GDM_RX_ETH_L255_CNT_H(_n)	(GDM_BASE(_n) + 0x2f4)
-#define REG_FE_GDM_RX_ETH_L511_CNT_H(_n)	(GDM_BASE(_n) + 0x2f8)
-#define REG_FE_GDM_RX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2fc)
-
-#define REG_GDM2_CHN_RLS		(GDM2_BASE + 0x20)
-#define MBI_RX_AGE_SEL_MASK		GENMASK(26, 25)
-#define MBI_TX_AGE_SEL_MASK		GENMASK(18, 17)
-
-#define REG_GDM3_FWD_CFG		GDM3_BASE
-#define GDM3_PAD_EN_MASK		BIT(28)
-
-#define REG_GDM4_FWD_CFG		(GDM4_BASE + 0x100)
-#define GDM4_PAD_EN_MASK		BIT(28)
-#define GDM4_SPORT_OFFSET0_MASK		GENMASK(11, 8)
-
-#define REG_GDM4_SRC_PORT_SET		(GDM4_BASE + 0x33c)
-#define GDM4_SPORT_OFF2_MASK		GENMASK(19, 16)
-#define GDM4_SPORT_OFF1_MASK		GENMASK(15, 12)
-#define GDM4_SPORT_OFF0_MASK		GENMASK(11, 8)
-
-#define REG_IP_FRAG_FP			0x2010
-#define IP_ASSEMBLE_PORT_MASK		GENMASK(24, 21)
-#define IP_ASSEMBLE_NBQ_MASK		GENMASK(20, 16)
-#define IP_FRAGMENT_PORT_MASK		GENMASK(8, 5)
-#define IP_FRAGMENT_NBQ_MASK		GENMASK(4, 0)
-
-#define REG_MC_VLAN_EN			0x2100
-#define MC_VLAN_EN_MASK			BIT(0)
-
-#define REG_MC_VLAN_CFG			0x2104
-#define MC_VLAN_CFG_CMD_DONE_MASK	BIT(31)
-#define MC_VLAN_CFG_TABLE_ID_MASK	GENMASK(21, 16)
-#define MC_VLAN_CFG_PORT_ID_MASK	GENMASK(11, 8)
-#define MC_VLAN_CFG_TABLE_SEL_MASK	BIT(4)
-#define MC_VLAN_CFG_RW_MASK		BIT(0)
-
-#define REG_MC_VLAN_DATA		0x2108
-
-#define REG_CDM5_RX_OQ1_DROP_CNT	0x29d4
-
-/* QDMA */
-#define REG_QDMA_GLOBAL_CFG			0x0004
-#define GLOBAL_CFG_RX_2B_OFFSET_MASK		BIT(31)
-#define GLOBAL_CFG_DMA_PREFERENCE_MASK		GENMASK(30, 29)
-#define GLOBAL_CFG_CPU_TXR_RR_MASK		BIT(28)
-#define GLOBAL_CFG_DSCP_BYTE_SWAP_MASK		BIT(27)
-#define GLOBAL_CFG_PAYLOAD_BYTE_SWAP_MASK	BIT(26)
-#define GLOBAL_CFG_MULTICAST_MODIFY_FP_MASK	BIT(25)
-#define GLOBAL_CFG_OAM_MODIFY_MASK		BIT(24)
-#define GLOBAL_CFG_RESET_MASK			BIT(23)
-#define GLOBAL_CFG_RESET_DONE_MASK		BIT(22)
-#define GLOBAL_CFG_MULTICAST_EN_MASK		BIT(21)
-#define GLOBAL_CFG_IRQ1_EN_MASK			BIT(20)
-#define GLOBAL_CFG_IRQ0_EN_MASK			BIT(19)
-#define GLOBAL_CFG_LOOPCNT_EN_MASK		BIT(18)
-#define GLOBAL_CFG_RD_BYPASS_WR_MASK		BIT(17)
-#define GLOBAL_CFG_QDMA_LOOPBACK_MASK		BIT(16)
-#define GLOBAL_CFG_LPBK_RXQ_SEL_MASK		GENMASK(13, 8)
-#define GLOBAL_CFG_CHECK_DONE_MASK		BIT(7)
-#define GLOBAL_CFG_TX_WB_DONE_MASK		BIT(6)
-#define GLOBAL_CFG_MAX_ISSUE_NUM_MASK		GENMASK(5, 4)
-#define GLOBAL_CFG_RX_DMA_BUSY_MASK		BIT(3)
-#define GLOBAL_CFG_RX_DMA_EN_MASK		BIT(2)
-#define GLOBAL_CFG_TX_DMA_BUSY_MASK		BIT(1)
-#define GLOBAL_CFG_TX_DMA_EN_MASK		BIT(0)
-
-#define REG_FWD_DSCP_BASE			0x0010
-#define REG_FWD_BUF_BASE			0x0014
-
-#define REG_HW_FWD_DSCP_CFG			0x0018
-#define HW_FWD_DSCP_PAYLOAD_SIZE_MASK		GENMASK(29, 28)
-#define HW_FWD_DSCP_SCATTER_LEN_MASK		GENMASK(17, 16)
-#define HW_FWD_DSCP_MIN_SCATTER_LEN_MASK	GENMASK(15, 0)
-
-#define REG_INT_STATUS(_n)		\
-	(((_n) == 4) ? 0x0730 :		\
-	 ((_n) == 3) ? 0x0724 :		\
-	 ((_n) == 2) ? 0x0720 :		\
-	 ((_n) == 1) ? 0x0024 : 0x0020)
-
-#define REG_INT_ENABLE(_n)		\
-	(((_n) == 4) ? 0x0750 :		\
-	 ((_n) == 3) ? 0x0744 :		\
-	 ((_n) == 2) ? 0x0740 :		\
-	 ((_n) == 1) ? 0x002c : 0x0028)
-
-/* QDMA_CSR_INT_ENABLE1 */
-#define RX15_COHERENT_INT_MASK		BIT(31)
-#define RX14_COHERENT_INT_MASK		BIT(30)
-#define RX13_COHERENT_INT_MASK		BIT(29)
-#define RX12_COHERENT_INT_MASK		BIT(28)
-#define RX11_COHERENT_INT_MASK		BIT(27)
-#define RX10_COHERENT_INT_MASK		BIT(26)
-#define RX9_COHERENT_INT_MASK		BIT(25)
-#define RX8_COHERENT_INT_MASK		BIT(24)
-#define RX7_COHERENT_INT_MASK		BIT(23)
-#define RX6_COHERENT_INT_MASK		BIT(22)
-#define RX5_COHERENT_INT_MASK		BIT(21)
-#define RX4_COHERENT_INT_MASK		BIT(20)
-#define RX3_COHERENT_INT_MASK		BIT(19)
-#define RX2_COHERENT_INT_MASK		BIT(18)
-#define RX1_COHERENT_INT_MASK		BIT(17)
-#define RX0_COHERENT_INT_MASK		BIT(16)
-#define TX7_COHERENT_INT_MASK		BIT(15)
-#define TX6_COHERENT_INT_MASK		BIT(14)
-#define TX5_COHERENT_INT_MASK		BIT(13)
-#define TX4_COHERENT_INT_MASK		BIT(12)
-#define TX3_COHERENT_INT_MASK		BIT(11)
-#define TX2_COHERENT_INT_MASK		BIT(10)
-#define TX1_COHERENT_INT_MASK		BIT(9)
-#define TX0_COHERENT_INT_MASK		BIT(8)
-#define CNT_OVER_FLOW_INT_MASK		BIT(7)
-#define IRQ1_FULL_INT_MASK		BIT(5)
-#define IRQ1_INT_MASK			BIT(4)
-#define HWFWD_DSCP_LOW_INT_MASK		BIT(3)
-#define HWFWD_DSCP_EMPTY_INT_MASK	BIT(2)
-#define IRQ0_FULL_INT_MASK		BIT(1)
-#define IRQ0_INT_MASK			BIT(0)
-
-#define TX_DONE_INT_MASK(_n)					\
-	((_n) ? IRQ1_INT_MASK | IRQ1_FULL_INT_MASK		\
-	      : IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
-
-#define INT_TX_MASK						\
-	(IRQ1_INT_MASK | IRQ1_FULL_INT_MASK |			\
-	 IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
-
-#define INT_IDX0_MASK						\
-	(TX0_COHERENT_INT_MASK | TX1_COHERENT_INT_MASK |	\
-	 TX2_COHERENT_INT_MASK | TX3_COHERENT_INT_MASK |	\
-	 TX4_COHERENT_INT_MASK | TX5_COHERENT_INT_MASK |	\
-	 TX6_COHERENT_INT_MASK | TX7_COHERENT_INT_MASK |	\
-	 RX0_COHERENT_INT_MASK | RX1_COHERENT_INT_MASK |	\
-	 RX2_COHERENT_INT_MASK | RX3_COHERENT_INT_MASK |	\
-	 RX4_COHERENT_INT_MASK | RX7_COHERENT_INT_MASK |	\
-	 RX8_COHERENT_INT_MASK | RX9_COHERENT_INT_MASK |	\
-	 RX15_COHERENT_INT_MASK | INT_TX_MASK)
-
-/* QDMA_CSR_INT_ENABLE2 */
-#define RX15_NO_CPU_DSCP_INT_MASK	BIT(31)
-#define RX14_NO_CPU_DSCP_INT_MASK	BIT(30)
-#define RX13_NO_CPU_DSCP_INT_MASK	BIT(29)
-#define RX12_NO_CPU_DSCP_INT_MASK	BIT(28)
-#define RX11_NO_CPU_DSCP_INT_MASK	BIT(27)
-#define RX10_NO_CPU_DSCP_INT_MASK	BIT(26)
-#define RX9_NO_CPU_DSCP_INT_MASK	BIT(25)
-#define RX8_NO_CPU_DSCP_INT_MASK	BIT(24)
-#define RX7_NO_CPU_DSCP_INT_MASK	BIT(23)
-#define RX6_NO_CPU_DSCP_INT_MASK	BIT(22)
-#define RX5_NO_CPU_DSCP_INT_MASK	BIT(21)
-#define RX4_NO_CPU_DSCP_INT_MASK	BIT(20)
-#define RX3_NO_CPU_DSCP_INT_MASK	BIT(19)
-#define RX2_NO_CPU_DSCP_INT_MASK	BIT(18)
-#define RX1_NO_CPU_DSCP_INT_MASK	BIT(17)
-#define RX0_NO_CPU_DSCP_INT_MASK	BIT(16)
-#define RX15_DONE_INT_MASK		BIT(15)
-#define RX14_DONE_INT_MASK		BIT(14)
-#define RX13_DONE_INT_MASK		BIT(13)
-#define RX12_DONE_INT_MASK		BIT(12)
-#define RX11_DONE_INT_MASK		BIT(11)
-#define RX10_DONE_INT_MASK		BIT(10)
-#define RX9_DONE_INT_MASK		BIT(9)
-#define RX8_DONE_INT_MASK		BIT(8)
-#define RX7_DONE_INT_MASK		BIT(7)
-#define RX6_DONE_INT_MASK		BIT(6)
-#define RX5_DONE_INT_MASK		BIT(5)
-#define RX4_DONE_INT_MASK		BIT(4)
-#define RX3_DONE_INT_MASK		BIT(3)
-#define RX2_DONE_INT_MASK		BIT(2)
-#define RX1_DONE_INT_MASK		BIT(1)
-#define RX0_DONE_INT_MASK		BIT(0)
-
-#define RX_DONE_INT_MASK					\
-	(RX0_DONE_INT_MASK | RX1_DONE_INT_MASK |		\
-	 RX2_DONE_INT_MASK | RX3_DONE_INT_MASK |		\
-	 RX4_DONE_INT_MASK | RX7_DONE_INT_MASK |		\
-	 RX8_DONE_INT_MASK | RX9_DONE_INT_MASK |		\
-	 RX15_DONE_INT_MASK)
-#define INT_IDX1_MASK						\
-	(RX_DONE_INT_MASK |					\
-	 RX0_NO_CPU_DSCP_INT_MASK | RX1_NO_CPU_DSCP_INT_MASK |	\
-	 RX2_NO_CPU_DSCP_INT_MASK | RX3_NO_CPU_DSCP_INT_MASK |	\
-	 RX4_NO_CPU_DSCP_INT_MASK | RX7_NO_CPU_DSCP_INT_MASK |	\
-	 RX8_NO_CPU_DSCP_INT_MASK | RX9_NO_CPU_DSCP_INT_MASK |	\
-	 RX15_NO_CPU_DSCP_INT_MASK)
-
-/* QDMA_CSR_INT_ENABLE5 */
-#define TX31_COHERENT_INT_MASK		BIT(31)
-#define TX30_COHERENT_INT_MASK		BIT(30)
-#define TX29_COHERENT_INT_MASK		BIT(29)
-#define TX28_COHERENT_INT_MASK		BIT(28)
-#define TX27_COHERENT_INT_MASK		BIT(27)
-#define TX26_COHERENT_INT_MASK		BIT(26)
-#define TX25_COHERENT_INT_MASK		BIT(25)
-#define TX24_COHERENT_INT_MASK		BIT(24)
-#define TX23_COHERENT_INT_MASK		BIT(23)
-#define TX22_COHERENT_INT_MASK		BIT(22)
-#define TX21_COHERENT_INT_MASK		BIT(21)
-#define TX20_COHERENT_INT_MASK		BIT(20)
-#define TX19_COHERENT_INT_MASK		BIT(19)
-#define TX18_COHERENT_INT_MASK		BIT(18)
-#define TX17_COHERENT_INT_MASK		BIT(17)
-#define TX16_COHERENT_INT_MASK		BIT(16)
-#define TX15_COHERENT_INT_MASK		BIT(15)
-#define TX14_COHERENT_INT_MASK		BIT(14)
-#define TX13_COHERENT_INT_MASK		BIT(13)
-#define TX12_COHERENT_INT_MASK		BIT(12)
-#define TX11_COHERENT_INT_MASK		BIT(11)
-#define TX10_COHERENT_INT_MASK		BIT(10)
-#define TX9_COHERENT_INT_MASK		BIT(9)
-#define TX8_COHERENT_INT_MASK		BIT(8)
-
-#define INT_IDX4_MASK						\
-	(TX8_COHERENT_INT_MASK | TX9_COHERENT_INT_MASK |	\
-	 TX10_COHERENT_INT_MASK | TX11_COHERENT_INT_MASK |	\
-	 TX12_COHERENT_INT_MASK | TX13_COHERENT_INT_MASK |	\
-	 TX14_COHERENT_INT_MASK | TX15_COHERENT_INT_MASK |	\
-	 TX16_COHERENT_INT_MASK | TX17_COHERENT_INT_MASK |	\
-	 TX18_COHERENT_INT_MASK | TX19_COHERENT_INT_MASK |	\
-	 TX20_COHERENT_INT_MASK | TX21_COHERENT_INT_MASK |	\
-	 TX22_COHERENT_INT_MASK | TX23_COHERENT_INT_MASK |	\
-	 TX24_COHERENT_INT_MASK | TX25_COHERENT_INT_MASK |	\
-	 TX26_COHERENT_INT_MASK | TX27_COHERENT_INT_MASK |	\
-	 TX28_COHERENT_INT_MASK | TX29_COHERENT_INT_MASK |	\
-	 TX30_COHERENT_INT_MASK | TX31_COHERENT_INT_MASK)
-
-#define REG_TX_IRQ_BASE(_n)		((_n) ? 0x0048 : 0x0050)
-
-#define REG_TX_IRQ_CFG(_n)		((_n) ? 0x004c : 0x0054)
-#define TX_IRQ_THR_MASK			GENMASK(27, 16)
-#define TX_IRQ_DEPTH_MASK		GENMASK(11, 0)
-
-#define REG_IRQ_CLEAR_LEN(_n)		((_n) ? 0x0064 : 0x0058)
-#define IRQ_CLEAR_LEN_MASK		GENMASK(7, 0)
-
-#define REG_IRQ_STATUS(_n)		((_n) ? 0x0068 : 0x005c)
-#define IRQ_ENTRY_LEN_MASK		GENMASK(27, 16)
-#define IRQ_HEAD_IDX_MASK		GENMASK(11, 0)
-
-#define REG_TX_RING_BASE(_n)	\
-	(((_n) < 8) ? 0x0100 + ((_n) << 5) : 0x0b00 + (((_n) - 8) << 5))
-
-#define REG_TX_RING_BLOCKING(_n)	\
-	(((_n) < 8) ? 0x0104 + ((_n) << 5) : 0x0b04 + (((_n) - 8) << 5))
-
-#define TX_RING_IRQ_BLOCKING_MAP_MASK			BIT(6)
-#define TX_RING_IRQ_BLOCKING_CFG_MASK			BIT(4)
-#define TX_RING_IRQ_BLOCKING_TX_DROP_EN_MASK		BIT(2)
-#define TX_RING_IRQ_BLOCKING_MAX_TH_TXRING_EN_MASK	BIT(1)
-#define TX_RING_IRQ_BLOCKING_MIN_TH_TXRING_EN_MASK	BIT(0)
-
-#define REG_TX_CPU_IDX(_n)	\
-	(((_n) < 8) ? 0x0108 + ((_n) << 5) : 0x0b08 + (((_n) - 8) << 5))
-
-#define TX_RING_CPU_IDX_MASK		GENMASK(15, 0)
-
-#define REG_TX_DMA_IDX(_n)	\
-	(((_n) < 8) ? 0x010c + ((_n) << 5) : 0x0b0c + (((_n) - 8) << 5))
-
-#define TX_RING_DMA_IDX_MASK		GENMASK(15, 0)
-
-#define IRQ_RING_IDX_MASK		GENMASK(20, 16)
-#define IRQ_DESC_IDX_MASK		GENMASK(15, 0)
-
-#define REG_RX_RING_BASE(_n)	\
-	(((_n) < 16) ? 0x0200 + ((_n) << 5) : 0x0e00 + (((_n) - 16) << 5))
-
-#define REG_RX_RING_SIZE(_n)	\
-	(((_n) < 16) ? 0x0204 + ((_n) << 5) : 0x0e04 + (((_n) - 16) << 5))
-
-#define RX_RING_THR_MASK		GENMASK(31, 16)
-#define RX_RING_SIZE_MASK		GENMASK(15, 0)
-
-#define REG_RX_CPU_IDX(_n)	\
-	(((_n) < 16) ? 0x0208 + ((_n) << 5) : 0x0e08 + (((_n) - 16) << 5))
-
-#define RX_RING_CPU_IDX_MASK		GENMASK(15, 0)
-
-#define REG_RX_DMA_IDX(_n)	\
-	(((_n) < 16) ? 0x020c + ((_n) << 5) : 0x0e0c + (((_n) - 16) << 5))
-
-#define REG_RX_DELAY_INT_IDX(_n)	\
-	(((_n) < 16) ? 0x0210 + ((_n) << 5) : 0x0e10 + (((_n) - 16) << 5))
-
-#define RX_DELAY_INT_MASK		GENMASK(15, 0)
-
-#define RX_RING_DMA_IDX_MASK		GENMASK(15, 0)
-
-#define REG_INGRESS_TRTCM_CFG		0x0070
-#define INGRESS_TRTCM_EN_MASK		BIT(31)
-#define INGRESS_TRTCM_MODE_MASK		BIT(30)
-#define INGRESS_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
-#define INGRESS_FAST_TICK_MASK		GENMASK(15, 0)
-
-#define REG_TXQ_DIS_CFG_BASE(_n)	((_n) ? 0x20a0 : 0x00a0)
-#define REG_TXQ_DIS_CFG(_n, _m)		(REG_TXQ_DIS_CFG_BASE((_n)) + (_m) << 2)
-
-#define REG_LMGR_INIT_CFG		0x1000
-#define LMGR_INIT_START			BIT(31)
-#define LMGR_SRAM_MODE_MASK		BIT(30)
-#define HW_FWD_PKTSIZE_OVERHEAD_MASK	GENMASK(27, 20)
-#define HW_FWD_DESC_NUM_MASK		GENMASK(16, 0)
-
-#define REG_FWD_DSCP_LOW_THR		0x1004
-#define FWD_DSCP_LOW_THR_MASK		GENMASK(17, 0)
-
-#define REG_EGRESS_RATE_METER_CFG		0x100c
-#define EGRESS_RATE_METER_EN_MASK		BIT(31)
-#define EGRESS_RATE_METER_EQ_RATE_EN_MASK	BIT(17)
-#define EGRESS_RATE_METER_WINDOW_SZ_MASK	GENMASK(16, 12)
-#define EGRESS_RATE_METER_TIMESLICE_MASK	GENMASK(10, 0)
-
-#define REG_EGRESS_TRTCM_CFG		0x1010
-#define EGRESS_TRTCM_EN_MASK		BIT(31)
-#define EGRESS_TRTCM_MODE_MASK		BIT(30)
-#define EGRESS_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
-#define EGRESS_FAST_TICK_MASK		GENMASK(15, 0)
-
-#define REG_TXWRR_MODE_CFG		0x1020
-#define TWRR_WEIGHT_SCALE_MASK		BIT(31)
-#define TWRR_WEIGHT_BASE_MASK		BIT(3)
-
-#define REG_PSE_BUF_USAGE_CFG		0x1028
-#define PSE_BUF_ESTIMATE_EN_MASK	BIT(29)
-
-#define REG_GLB_TRTCM_CFG		0x1080
-#define GLB_TRTCM_EN_MASK		BIT(31)
-#define GLB_TRTCM_MODE_MASK		BIT(30)
-#define GLB_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
-#define GLB_FAST_TICK_MASK		GENMASK(15, 0)
-
-#define REG_TXQ_CNGST_CFG		0x10a0
-#define TXQ_CNGST_DROP_EN		BIT(31)
-#define TXQ_CNGST_DEI_DROP_EN		BIT(30)
-
-#define REG_SLA_TRTCM_CFG		0x1150
-#define SLA_TRTCM_EN_MASK		BIT(31)
-#define SLA_TRTCM_MODE_MASK		BIT(30)
-#define SLA_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
-#define SLA_FAST_TICK_MASK		GENMASK(15, 0)
-
-/* CTRL */
-#define QDMA_DESC_DONE_MASK		BIT(31)
-#define QDMA_DESC_DROP_MASK		BIT(30) /* tx: drop - rx: overflow */
-#define QDMA_DESC_MORE_MASK		BIT(29) /* more SG elements */
-#define QDMA_DESC_DEI_MASK		BIT(25)
-#define QDMA_DESC_NO_DROP_MASK		BIT(24)
-#define QDMA_DESC_LEN_MASK		GENMASK(15, 0)
-/* DATA */
-#define QDMA_DESC_NEXT_ID_MASK		GENMASK(15, 0)
-/* TX MSG0 */
-#define QDMA_ETH_TXMSG_MIC_IDX_MASK	BIT(30)
-#define QDMA_ETH_TXMSG_SP_TAG_MASK	GENMASK(29, 14)
-#define QDMA_ETH_TXMSG_ICO_MASK		BIT(13)
-#define QDMA_ETH_TXMSG_UCO_MASK		BIT(12)
-#define QDMA_ETH_TXMSG_TCO_MASK		BIT(11)
-#define QDMA_ETH_TXMSG_TSO_MASK		BIT(10)
-#define QDMA_ETH_TXMSG_FAST_MASK	BIT(9)
-#define QDMA_ETH_TXMSG_OAM_MASK		BIT(8)
-#define QDMA_ETH_TXMSG_CHAN_MASK	GENMASK(7, 3)
-#define QDMA_ETH_TXMSG_QUEUE_MASK	GENMASK(2, 0)
-/* TX MSG1 */
-#define QDMA_ETH_TXMSG_NO_DROP		BIT(31)
-#define QDMA_ETH_TXMSG_METER_MASK	GENMASK(30, 24)	/* 0x7f no meters */
-#define QDMA_ETH_TXMSG_FPORT_MASK	GENMASK(23, 20)
-#define QDMA_ETH_TXMSG_NBOQ_MASK	GENMASK(19, 15)
-#define QDMA_ETH_TXMSG_HWF_MASK		BIT(14)
-#define QDMA_ETH_TXMSG_HOP_MASK		BIT(13)
-#define QDMA_ETH_TXMSG_PTP_MASK		BIT(12)
-#define QDMA_ETH_TXMSG_ACNT_G1_MASK	GENMASK(10, 6)	/* 0x1f do not count */
-#define QDMA_ETH_TXMSG_ACNT_G0_MASK	GENMASK(5, 0)	/* 0x3f do not count */
-
-/* RX MSG1 */
-#define QDMA_ETH_RXMSG_DEI_MASK		BIT(31)
-#define QDMA_ETH_RXMSG_IP6_MASK		BIT(30)
-#define QDMA_ETH_RXMSG_IP4_MASK		BIT(29)
-#define QDMA_ETH_RXMSG_IP4F_MASK	BIT(28)
-#define QDMA_ETH_RXMSG_L4_VALID_MASK	BIT(27)
-#define QDMA_ETH_RXMSG_L4F_MASK		BIT(26)
-#define QDMA_ETH_RXMSG_SPORT_MASK	GENMASK(25, 21)
-#define QDMA_ETH_RXMSG_CRSN_MASK	GENMASK(20, 16)
-#define QDMA_ETH_RXMSG_PPE_ENTRY_MASK	GENMASK(15, 0)
-
-struct airoha_qdma_desc {
-	__le32 rsv;
-	__le32 ctrl;
-	__le32 addr;
-	__le32 data;
-	__le32 msg0;
-	__le32 msg1;
-	__le32 msg2;
-	__le32 msg3;
-};
-
-/* CTRL0 */
-#define QDMA_FWD_DESC_CTX_MASK		BIT(31)
-#define QDMA_FWD_DESC_RING_MASK		GENMASK(30, 28)
-#define QDMA_FWD_DESC_IDX_MASK		GENMASK(27, 16)
-#define QDMA_FWD_DESC_LEN_MASK		GENMASK(15, 0)
-/* CTRL1 */
-#define QDMA_FWD_DESC_FIRST_IDX_MASK	GENMASK(15, 0)
-/* CTRL2 */
-#define QDMA_FWD_DESC_MORE_PKT_NUM_MASK	GENMASK(2, 0)
-
-struct airoha_qdma_fwd_desc {
-	__le32 addr;
-	__le32 ctrl0;
-	__le32 ctrl1;
-	__le32 ctrl2;
-	__le32 msg0;
-	__le32 msg1;
-	__le32 rsv0;
-	__le32 rsv1;
-};
-
-enum {
-	QDMA_INT_REG_IDX0,
-	QDMA_INT_REG_IDX1,
-	QDMA_INT_REG_IDX2,
-	QDMA_INT_REG_IDX3,
-	QDMA_INT_REG_IDX4,
-	QDMA_INT_REG_MAX
-};
-
-enum {
-	XSI_PCIE0_PORT,
-	XSI_PCIE1_PORT,
-	XSI_USB_PORT,
-	XSI_AE_PORT,
-	XSI_ETH_PORT,
-};
-
-enum {
-	XSI_PCIE0_VIP_PORT_MASK	= BIT(22),
-	XSI_PCIE1_VIP_PORT_MASK	= BIT(23),
-	XSI_USB_VIP_PORT_MASK	= BIT(25),
-	XSI_ETH_VIP_PORT_MASK	= BIT(24),
-};
-
-enum {
-	DEV_STATE_INITIALIZED,
-};
-
-enum {
-	CDM_CRSN_QSEL_Q1 = 1,
-	CDM_CRSN_QSEL_Q5 = 5,
-	CDM_CRSN_QSEL_Q6 = 6,
-	CDM_CRSN_QSEL_Q15 = 15,
-};
-
-enum {
-	CRSN_08 = 0x8,
-	CRSN_21 = 0x15, /* KA */
-	CRSN_22 = 0x16, /* hit bind and force route to CPU */
-	CRSN_24 = 0x18,
-	CRSN_25 = 0x19,
-};
-
-enum {
-	FE_PSE_PORT_CDM1,
-	FE_PSE_PORT_GDM1,
-	FE_PSE_PORT_GDM2,
-	FE_PSE_PORT_GDM3,
-	FE_PSE_PORT_PPE1,
-	FE_PSE_PORT_CDM2,
-	FE_PSE_PORT_CDM3,
-	FE_PSE_PORT_CDM4,
-	FE_PSE_PORT_PPE2,
-	FE_PSE_PORT_GDM4,
-	FE_PSE_PORT_CDM5,
-	FE_PSE_PORT_DROP = 0xf,
-};
-
-struct airoha_queue_entry {
-	union {
-		void *buf;
-		struct sk_buff *skb;
-	};
-	dma_addr_t dma_addr;
-	u16 dma_len;
-};
-
-struct airoha_queue {
-	struct airoha_qdma *qdma;
-
-	/* protect concurrent queue accesses */
-	spinlock_t lock;
-	struct airoha_queue_entry *entry;
-	struct airoha_qdma_desc *desc;
-	u16 head;
-	u16 tail;
-
-	int queued;
-	int ndesc;
-	int free_thr;
-	int buf_size;
-
-	struct napi_struct napi;
-	struct page_pool *page_pool;
-};
-
-struct airoha_tx_irq_queue {
-	struct airoha_qdma *qdma;
-
-	struct napi_struct napi;
-
-	int size;
-	u32 *q;
-};
-
-struct airoha_hw_stats {
-	/* protect concurrent hw_stats accesses */
-	spinlock_t lock;
-	struct u64_stats_sync syncp;
-
-	/* get_stats64 */
-	u64 rx_ok_pkts;
-	u64 tx_ok_pkts;
-	u64 rx_ok_bytes;
-	u64 tx_ok_bytes;
-	u64 rx_multicast;
-	u64 rx_errors;
-	u64 rx_drops;
-	u64 tx_drops;
-	u64 rx_crc_error;
-	u64 rx_over_errors;
-	/* ethtool stats */
-	u64 tx_broadcast;
-	u64 tx_multicast;
-	u64 tx_len[7];
-	u64 rx_broadcast;
-	u64 rx_fragment;
-	u64 rx_jabber;
-	u64 rx_len[7];
-};
-
-struct airoha_qdma {
-	struct airoha_eth *eth;
-	void __iomem *regs;
+#include "airoha_regs.h"
+#include "airoha_eth.h"
 
-	/* protect concurrent irqmask accesses */
-	spinlock_t irq_lock;
-	u32 irqmask[QDMA_INT_REG_MAX];
-	int irq;
-
-	struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ];
-
-	struct airoha_queue q_tx[AIROHA_NUM_TX_RING];
-	struct airoha_queue q_rx[AIROHA_NUM_RX_RING];
-
-	/* descriptor and packet buffers for qdma hw forward */
-	struct {
-		void *desc;
-		void *q;
-	} hfwd;
-};
-
-struct airoha_gdm_port {
-	struct airoha_qdma *qdma;
-	struct net_device *dev;
-	int id;
-
-	struct airoha_hw_stats stats;
-};
-
-struct airoha_eth {
-	struct device *dev;
-
-	unsigned long state;
-	void __iomem *fe_regs;
-
-	struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS];
-	struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS];
-
-	struct net_device *napi_dev;
-
-	struct airoha_qdma qdma[AIROHA_MAX_NUM_QDMA];
-	struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS];
-};
-
-static u32 airoha_rr(void __iomem *base, u32 offset)
+u32 airoha_rr(void __iomem *base, u32 offset)
 {
 	return readl(base + offset);
 }
 
-static void airoha_wr(void __iomem *base, u32 offset, u32 val)
+void airoha_wr(void __iomem *base, u32 offset, u32 val)
 {
 	writel(val, base + offset);
 }
 
-static u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val)
+u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val)
 {
 	val |= (airoha_rr(base, offset) & ~mask);
 	airoha_wr(base, offset, val);
@@ -845,68 +35,40 @@ static u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val)
 	return val;
 }
 
-#define airoha_fe_rr(eth, offset)				\
-	airoha_rr((eth)->fe_regs, (offset))
-#define airoha_fe_wr(eth, offset, val)				\
-	airoha_wr((eth)->fe_regs, (offset), (val))
-#define airoha_fe_rmw(eth, offset, mask, val)			\
-	airoha_rmw((eth)->fe_regs, (offset), (mask), (val))
-#define airoha_fe_set(eth, offset, val)				\
-	airoha_rmw((eth)->fe_regs, (offset), 0, (val))
-#define airoha_fe_clear(eth, offset, val)			\
-	airoha_rmw((eth)->fe_regs, (offset), (val), 0)
-
-#define airoha_qdma_rr(qdma, offset)				\
-	airoha_rr((qdma)->regs, (offset))
-#define airoha_qdma_wr(qdma, offset, val)			\
-	airoha_wr((qdma)->regs, (offset), (val))
-#define airoha_qdma_rmw(qdma, offset, mask, val)		\
-	airoha_rmw((qdma)->regs, (offset), (mask), (val))
-#define airoha_qdma_set(qdma, offset, val)			\
-	airoha_rmw((qdma)->regs, (offset), 0, (val))
-#define airoha_qdma_clear(qdma, offset, val)			\
-	airoha_rmw((qdma)->regs, (offset), (val), 0)
-
-static void airoha_qdma_set_irqmask(struct airoha_qdma *qdma, int index,
-				    u32 clear, u32 set)
+static void airoha_qdma_set_irqmask(struct airoha_irq_bank *irq_bank,
+				    int index, u32 clear, u32 set)
 {
+	struct airoha_qdma *qdma = irq_bank->qdma;
+	int bank = irq_bank - &qdma->irq_banks[0];
 	unsigned long flags;
 
-	if (WARN_ON_ONCE(index >= ARRAY_SIZE(qdma->irqmask)))
+	if (WARN_ON_ONCE(index >= ARRAY_SIZE(irq_bank->irqmask)))
 		return;
 
-	spin_lock_irqsave(&qdma->irq_lock, flags);
+	spin_lock_irqsave(&irq_bank->irq_lock, flags);
 
-	qdma->irqmask[index] &= ~clear;
-	qdma->irqmask[index] |= set;
-	airoha_qdma_wr(qdma, REG_INT_ENABLE(index), qdma->irqmask[index]);
+	irq_bank->irqmask[index] &= ~clear;
+	irq_bank->irqmask[index] |= set;
+	airoha_qdma_wr(qdma, REG_INT_ENABLE(bank, index),
+		       irq_bank->irqmask[index]);
 	/* Read irq_enable register in order to guarantee the update above
 	 * completes in the spinlock critical section.
 	 */
-	airoha_qdma_rr(qdma, REG_INT_ENABLE(index));
+	airoha_qdma_rr(qdma, REG_INT_ENABLE(bank, index));
 
-	spin_unlock_irqrestore(&qdma->irq_lock, flags);
+	spin_unlock_irqrestore(&irq_bank->irq_lock, flags);
 }
 
-static void airoha_qdma_irq_enable(struct airoha_qdma *qdma, int index,
-				   u32 mask)
+static void airoha_qdma_irq_enable(struct airoha_irq_bank *irq_bank,
+				   int index, u32 mask)
 {
-	airoha_qdma_set_irqmask(qdma, index, 0, mask);
+	airoha_qdma_set_irqmask(irq_bank, index, 0, mask);
 }
 
-static void airoha_qdma_irq_disable(struct airoha_qdma *qdma, int index,
-				    u32 mask)
+static void airoha_qdma_irq_disable(struct airoha_irq_bank *irq_bank,
+				    int index, u32 mask)
 {
-	airoha_qdma_set_irqmask(qdma, index, mask, 0);
-}
-
-static bool airhoa_is_lan_gdm_port(struct airoha_gdm_port *port)
-{
-	/* GDM1 port on EN7581 SoC is connected to the lan dsa switch.
-	 * GDM{2,3,4} can be used as wan port connected to an external
-	 * phy module.
-	 */
-	return port->id == 1;
+	airoha_qdma_set_irqmask(irq_bank, index, mask, 0);
 }
 
 static void airoha_set_macaddr(struct airoha_gdm_port *port, const u8 *addr)
@@ -922,6 +84,8 @@ static void airoha_set_macaddr(struct airoha_gdm_port *port, const u8 *addr)
 	val = (addr[3] << 16) | (addr[4] << 8) | addr[5];
 	airoha_fe_wr(eth, REG_FE_MAC_LMIN(reg), val);
 	airoha_fe_wr(eth, REG_FE_MAC_LMAX(reg), val);
+
+	airoha_ppe_init_upd_mem(port);
 }
 
 static void airoha_set_gdm_port_fwd_cfg(struct airoha_eth *eth, u32 addr,
@@ -937,30 +101,23 @@ static void airoha_set_gdm_port_fwd_cfg(struct airoha_eth *eth, u32 addr,
 		      FIELD_PREP(GDM_UCFQ_MASK, val));
 }
 
-static int airoha_set_gdm_port(struct airoha_eth *eth, int port, bool enable)
+static int airoha_set_vip_for_gdm_port(struct airoha_gdm_port *port,
+				       bool enable)
 {
-	u32 val = enable ? FE_PSE_PORT_PPE1 : FE_PSE_PORT_DROP;
-	u32 vip_port, cfg_addr;
+	struct airoha_eth *eth = port->qdma->eth;
+	u32 vip_port;
 
-	switch (port) {
-	case XSI_PCIE0_PORT:
+	switch (port->id) {
+	case 3:
+		/* FIXME: handle XSI_PCIE1_PORT */
 		vip_port = XSI_PCIE0_VIP_PORT_MASK;
-		cfg_addr = REG_GDM_FWD_CFG(3);
-		break;
-	case XSI_PCIE1_PORT:
-		vip_port = XSI_PCIE1_VIP_PORT_MASK;
-		cfg_addr = REG_GDM_FWD_CFG(3);
-		break;
-	case XSI_USB_PORT:
-		vip_port = XSI_USB_VIP_PORT_MASK;
-		cfg_addr = REG_GDM_FWD_CFG(4);
 		break;
-	case XSI_ETH_PORT:
+	case 4:
+		/* FIXME: handle XSI_USB_PORT */
 		vip_port = XSI_ETH_VIP_PORT_MASK;
-		cfg_addr = REG_GDM_FWD_CFG(4);
 		break;
 	default:
-		return -EINVAL;
+		return 0;
 	}
 
 	if (enable) {
@@ -971,54 +128,20 @@ static int airoha_set_gdm_port(struct airoha_eth *eth, int port, bool enable)
 		airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, vip_port);
 	}
 
-	airoha_set_gdm_port_fwd_cfg(eth, cfg_addr, val);
-
-	return 0;
-}
-
-static int airoha_set_gdm_ports(struct airoha_eth *eth, bool enable)
-{
-	const int port_list[] = {
-		XSI_PCIE0_PORT,
-		XSI_PCIE1_PORT,
-		XSI_USB_PORT,
-		XSI_ETH_PORT
-	};
-	int i, err;
-
-	for (i = 0; i < ARRAY_SIZE(port_list); i++) {
-		err = airoha_set_gdm_port(eth, port_list[i], enable);
-		if (err)
-			goto error;
-	}
-
 	return 0;
-
-error:
-	for (i--; i >= 0; i--)
-		airoha_set_gdm_port(eth, port_list[i], false);
-
-	return err;
 }
 
 static void airoha_fe_maccr_init(struct airoha_eth *eth)
 {
 	int p;
 
-	for (p = 1; p <= ARRAY_SIZE(eth->ports); p++) {
+	for (p = 1; p <= ARRAY_SIZE(eth->ports); p++)
 		airoha_fe_set(eth, REG_GDM_FWD_CFG(p),
-			      GDM_TCP_CKSUM | GDM_UDP_CKSUM | GDM_IP4_CKSUM |
-			      GDM_DROP_CRC_ERR);
-		airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(p),
-					    FE_PSE_PORT_CDM1);
-		airoha_fe_rmw(eth, REG_GDM_LEN_CFG(p),
-			      GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK,
-			      FIELD_PREP(GDM_SHORT_LEN_MASK, 60) |
-			      FIELD_PREP(GDM_LONG_LEN_MASK, 4004));
-	}
+			      GDM_TCP_CKSUM_MASK | GDM_UDP_CKSUM_MASK |
+			      GDM_IP4_CKSUM_MASK | GDM_DROP_CRC_ERR_MASK);
 
-	airoha_fe_rmw(eth, REG_CDM1_VLAN_CTRL, CDM1_VLAN_MASK,
-		      FIELD_PREP(CDM1_VLAN_MASK, 0x8100));
+	airoha_fe_rmw(eth, REG_CDM_VLAN_CTRL(1), CDM_VLAN_MASK,
+		      FIELD_PREP(CDM_VLAN_MASK, 0x8100));
 
 	airoha_fe_set(eth, REG_FE_CPORT_CFG, FE_CPORT_PAD);
 }
@@ -1174,8 +297,11 @@ static void airoha_fe_pse_ports_init(struct airoha_eth *eth)
 	int q;
 
 	all_rsv = airoha_fe_get_pse_all_rsv(eth);
-	/* hw misses PPE2 oq rsv */
-	all_rsv += PSE_RSV_PAGES * pse_port_num_queues[FE_PSE_PORT_PPE2];
+	if (airoha_ppe_is_enabled(eth, 1)) {
+		/* hw misses PPE2 oq rsv */
+		all_rsv += PSE_RSV_PAGES *
+			   pse_port_num_queues[FE_PSE_PORT_PPE2];
+	}
 	airoha_fe_set(eth, REG_FE_PSE_BUF_SET, all_rsv);
 
 	/* CMD1 */
@@ -1212,13 +338,17 @@ static void airoha_fe_pse_ports_init(struct airoha_eth *eth)
 	for (q = 4; q < pse_port_num_queues[FE_PSE_PORT_CDM4]; q++)
 		airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_CDM4, q,
 					 PSE_QUEUE_RSV_PAGES);
-	/* PPE2 */
-	for (q = 0; q < pse_port_num_queues[FE_PSE_PORT_PPE2]; q++) {
-		if (q < pse_port_num_queues[FE_PSE_PORT_PPE2] / 2)
-			airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_PPE2, q,
-						 PSE_QUEUE_RSV_PAGES);
-		else
-			airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_PPE2, q, 0);
+	if (airoha_ppe_is_enabled(eth, 1)) {
+		/* PPE2 */
+		for (q = 0; q < pse_port_num_queues[FE_PSE_PORT_PPE2]; q++) {
+			if (q < pse_port_num_queues[FE_PSE_PORT_PPE2] / 2)
+				airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_PPE2,
+							 q,
+							 PSE_QUEUE_RSV_PAGES);
+			else
+				airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_PPE2,
+							 q, 0);
+		}
 	}
 	/* GMD4 */
 	for (q = 0; q < pse_port_num_queues[FE_PSE_PORT_GDM4]; q++)
@@ -1273,46 +403,46 @@ static int airoha_fe_mc_vlan_clear(struct airoha_eth *eth)
 static void airoha_fe_crsn_qsel_init(struct airoha_eth *eth)
 {
 	/* CDM1_CRSN_QSEL */
-	airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_22 >> 2),
-		      CDM1_CRSN_QSEL_REASON_MASK(CRSN_22),
-		      FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_22),
+	airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_22 >> 2),
+		      CDM_CRSN_QSEL_REASON_MASK(CRSN_22),
+		      FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_22),
 				 CDM_CRSN_QSEL_Q1));
-	airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_08 >> 2),
-		      CDM1_CRSN_QSEL_REASON_MASK(CRSN_08),
-		      FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_08),
+	airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_08 >> 2),
+		      CDM_CRSN_QSEL_REASON_MASK(CRSN_08),
+		      FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_08),
 				 CDM_CRSN_QSEL_Q1));
-	airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_21 >> 2),
-		      CDM1_CRSN_QSEL_REASON_MASK(CRSN_21),
-		      FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_21),
+	airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_21 >> 2),
+		      CDM_CRSN_QSEL_REASON_MASK(CRSN_21),
+		      FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_21),
 				 CDM_CRSN_QSEL_Q1));
-	airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_24 >> 2),
-		      CDM1_CRSN_QSEL_REASON_MASK(CRSN_24),
-		      FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_24),
+	airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_24 >> 2),
+		      CDM_CRSN_QSEL_REASON_MASK(CRSN_24),
+		      FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_24),
 				 CDM_CRSN_QSEL_Q6));
-	airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_25 >> 2),
-		      CDM1_CRSN_QSEL_REASON_MASK(CRSN_25),
-		      FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_25),
+	airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_25 >> 2),
+		      CDM_CRSN_QSEL_REASON_MASK(CRSN_25),
+		      FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_25),
 				 CDM_CRSN_QSEL_Q1));
 	/* CDM2_CRSN_QSEL */
-	airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_08 >> 2),
-		      CDM2_CRSN_QSEL_REASON_MASK(CRSN_08),
-		      FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_08),
+	airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_08 >> 2),
+		      CDM_CRSN_QSEL_REASON_MASK(CRSN_08),
+		      FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_08),
 				 CDM_CRSN_QSEL_Q1));
-	airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_21 >> 2),
-		      CDM2_CRSN_QSEL_REASON_MASK(CRSN_21),
-		      FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_21),
+	airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_21 >> 2),
+		      CDM_CRSN_QSEL_REASON_MASK(CRSN_21),
+		      FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_21),
 				 CDM_CRSN_QSEL_Q1));
-	airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_22 >> 2),
-		      CDM2_CRSN_QSEL_REASON_MASK(CRSN_22),
-		      FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_22),
+	airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_22 >> 2),
+		      CDM_CRSN_QSEL_REASON_MASK(CRSN_22),
+		      FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_22),
 				 CDM_CRSN_QSEL_Q1));
-	airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_24 >> 2),
-		      CDM2_CRSN_QSEL_REASON_MASK(CRSN_24),
-		      FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_24),
+	airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_24 >> 2),
+		      CDM_CRSN_QSEL_REASON_MASK(CRSN_24),
+		      FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_24),
 				 CDM_CRSN_QSEL_Q6));
-	airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_25 >> 2),
-		      CDM2_CRSN_QSEL_REASON_MASK(CRSN_25),
-		      FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_25),
+	airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_25 >> 2),
+		      CDM_CRSN_QSEL_REASON_MASK(CRSN_25),
+		      FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_25),
 				 CDM_CRSN_QSEL_Q1));
 }
 
@@ -1332,18 +462,18 @@ static int airoha_fe_init(struct airoha_eth *eth)
 	airoha_fe_wr(eth, REG_FE_PCE_CFG,
 		     PCE_DPI_EN_MASK | PCE_KA_EN_MASK | PCE_MC_EN_MASK);
 	/* set vip queue selection to ring 1 */
-	airoha_fe_rmw(eth, REG_CDM1_FWD_CFG, CDM1_VIP_QSEL_MASK,
-		      FIELD_PREP(CDM1_VIP_QSEL_MASK, 0x4));
-	airoha_fe_rmw(eth, REG_CDM2_FWD_CFG, CDM2_VIP_QSEL_MASK,
-		      FIELD_PREP(CDM2_VIP_QSEL_MASK, 0x4));
+	airoha_fe_rmw(eth, REG_CDM_FWD_CFG(1), CDM_VIP_QSEL_MASK,
+		      FIELD_PREP(CDM_VIP_QSEL_MASK, 0x4));
+	airoha_fe_rmw(eth, REG_CDM_FWD_CFG(2), CDM_VIP_QSEL_MASK,
+		      FIELD_PREP(CDM_VIP_QSEL_MASK, 0x4));
 	/* set GDM4 source interface offset to 8 */
-	airoha_fe_rmw(eth, REG_GDM4_SRC_PORT_SET,
-		      GDM4_SPORT_OFF2_MASK |
-		      GDM4_SPORT_OFF1_MASK |
-		      GDM4_SPORT_OFF0_MASK,
-		      FIELD_PREP(GDM4_SPORT_OFF2_MASK, 8) |
-		      FIELD_PREP(GDM4_SPORT_OFF1_MASK, 8) |
-		      FIELD_PREP(GDM4_SPORT_OFF0_MASK, 8));
+	airoha_fe_rmw(eth, REG_GDM_SRC_PORT_SET(4),
+		      GDM_SPORT_OFF2_MASK |
+		      GDM_SPORT_OFF1_MASK |
+		      GDM_SPORT_OFF0_MASK,
+		      FIELD_PREP(GDM_SPORT_OFF2_MASK, 8) |
+		      FIELD_PREP(GDM_SPORT_OFF1_MASK, 8) |
+		      FIELD_PREP(GDM_SPORT_OFF0_MASK, 8));
 
 	/* set PSE Page as 128B */
 	airoha_fe_rmw(eth, REG_FE_DMA_GLO_CFG,
@@ -1369,8 +499,8 @@ static int airoha_fe_init(struct airoha_eth *eth)
 	airoha_fe_set(eth, REG_GDM_MISC_CFG,
 		      GDM2_RDM_ACK_WAIT_PREF_MASK |
 		      GDM2_CHN_VLD_MODE_MASK);
-	airoha_fe_rmw(eth, REG_CDM2_FWD_CFG, CDM2_OAM_QSEL_MASK,
-		      FIELD_PREP(CDM2_OAM_QSEL_MASK, 15));
+	airoha_fe_rmw(eth, REG_CDM_FWD_CFG(2), CDM_OAM_QSEL_MASK,
+		      FIELD_PREP(CDM_OAM_QSEL_MASK, 15));
 
 	/* init fragment and assemble Force Port */
 	/* NPU Core-3, NPU Bridge Channel-3 */
@@ -1384,8 +514,8 @@ static int airoha_fe_init(struct airoha_eth *eth)
 		      FIELD_PREP(IP_ASSEMBLE_PORT_MASK, 0) |
 		      FIELD_PREP(IP_ASSEMBLE_NBQ_MASK, 22));
 
-	airoha_fe_set(eth, REG_GDM3_FWD_CFG, GDM3_PAD_EN_MASK);
-	airoha_fe_set(eth, REG_GDM4_FWD_CFG, GDM4_PAD_EN_MASK);
+	airoha_fe_set(eth, REG_GDM_FWD_CFG(3), GDM_PAD_EN_MASK);
+	airoha_fe_set(eth, REG_GDM_FWD_CFG(4), GDM_PAD_EN_MASK);
 
 	airoha_fe_crsn_qsel_init(eth);
 
@@ -1393,7 +523,7 @@ static int airoha_fe_init(struct airoha_eth *eth)
 	airoha_fe_set(eth, REG_FE_CPORT_CFG, FE_CPORT_PORT_XFC_MASK);
 
 	/* default aging mode for mbi unlock issue */
-	airoha_fe_rmw(eth, REG_GDM2_CHN_RLS,
+	airoha_fe_rmw(eth, REG_GDM_CHN_RLS(2),
 		      MBI_RX_AGE_SEL_MASK | MBI_TX_AGE_SEL_MASK,
 		      FIELD_PREP(MBI_RX_AGE_SEL_MASK, 3) |
 		      FIELD_PREP(MBI_TX_AGE_SEL_MASK, 3));
@@ -1409,9 +539,7 @@ static int airoha_fe_init(struct airoha_eth *eth)
 
 static int airoha_qdma_fill_rx_queue(struct airoha_queue *q)
 {
-	enum dma_data_direction dir = page_pool_get_dma_dir(q->page_pool);
 	struct airoha_qdma *qdma = q->qdma;
-	struct airoha_eth *eth = qdma->eth;
 	int qid = q - &qdma->q_rx[0];
 	int nframes = 0;
 
@@ -1435,9 +563,6 @@ static int airoha_qdma_fill_rx_queue(struct airoha_queue *q)
 		e->dma_addr = page_pool_get_dma_addr(page) + offset;
 		e->dma_len = SKB_WITH_OVERHEAD(q->buf_size);
 
-		dma_sync_single_for_device(eth->dev, e->dma_addr, e->dma_len,
-					   dir);
-
 		val = FIELD_PREP(QDMA_DESC_LEN_MASK, e->dma_len);
 		WRITE_ONCE(desc->ctrl, cpu_to_le32(val));
 		WRITE_ONCE(desc->addr, cpu_to_le32(e->dma_addr));
@@ -1463,7 +588,7 @@ static int airoha_qdma_get_gdm_port(struct airoha_eth *eth,
 
 	sport = FIELD_GET(QDMA_ETH_RXMSG_SPORT_MASK, msg1);
 	switch (sport) {
-	case 0x10 ... 0x13:
+	case 0x10 ... 0x14:
 		port = 0;
 		break;
 	case 0x2 ... 0x4:
@@ -1487,53 +612,94 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 	while (done < budget) {
 		struct airoha_queue_entry *e = &q->entry[q->tail];
 		struct airoha_qdma_desc *desc = &q->desc[q->tail];
-		dma_addr_t dma_addr = le32_to_cpu(desc->addr);
+		u32 hash, reason, msg1 = le32_to_cpu(desc->msg1);
+		struct page *page = virt_to_head_page(e->buf);
 		u32 desc_ctrl = le32_to_cpu(desc->ctrl);
-		struct sk_buff *skb;
-		int len, p;
+		struct airoha_gdm_port *port;
+		int data_len, len, p;
 
 		if (!(desc_ctrl & QDMA_DESC_DONE_MASK))
 			break;
 
-		if (!dma_addr)
-			break;
-
-		len = FIELD_GET(QDMA_DESC_LEN_MASK, desc_ctrl);
-		if (!len)
-			break;
-
 		q->tail = (q->tail + 1) % q->ndesc;
 		q->queued--;
 
-		dma_sync_single_for_cpu(eth->dev, dma_addr,
+		dma_sync_single_for_cpu(eth->dev, e->dma_addr,
 					SKB_WITH_OVERHEAD(q->buf_size), dir);
 
+		len = FIELD_GET(QDMA_DESC_LEN_MASK, desc_ctrl);
+		data_len = q->skb ? q->buf_size
+				  : SKB_WITH_OVERHEAD(q->buf_size);
+		if (!len || data_len < len)
+			goto free_frag;
+
 		p = airoha_qdma_get_gdm_port(eth, desc);
-		if (p < 0 || !eth->ports[p]) {
-			page_pool_put_full_page(q->page_pool,
-						virt_to_head_page(e->buf),
-						true);
-			continue;
+		if (p < 0 || !eth->ports[p])
+			goto free_frag;
+
+		port = eth->ports[p];
+		if (!q->skb) { /* first buffer */
+			q->skb = napi_build_skb(e->buf, q->buf_size);
+			if (!q->skb)
+				goto free_frag;
+
+			__skb_put(q->skb, len);
+			skb_mark_for_recycle(q->skb);
+			q->skb->dev = port->dev;
+			q->skb->protocol = eth_type_trans(q->skb, port->dev);
+			q->skb->ip_summed = CHECKSUM_UNNECESSARY;
+			skb_record_rx_queue(q->skb, qid);
+		} else { /* scattered frame */
+			struct skb_shared_info *shinfo = skb_shinfo(q->skb);
+			int nr_frags = shinfo->nr_frags;
+
+			if (nr_frags >= ARRAY_SIZE(shinfo->frags))
+				goto free_frag;
+
+			skb_add_rx_frag(q->skb, nr_frags, page,
+					e->buf - page_address(page), len,
+					q->buf_size);
 		}
 
-		skb = napi_build_skb(e->buf, q->buf_size);
-		if (!skb) {
-			page_pool_put_full_page(q->page_pool,
-						virt_to_head_page(e->buf),
-						true);
-			break;
+		if (FIELD_GET(QDMA_DESC_MORE_MASK, desc_ctrl))
+			continue;
+
+		if (netdev_uses_dsa(port->dev)) {
+			/* PPE module requires untagged packets to work
+			 * properly and it provides DSA port index via the
+			 * DMA descriptor. Report DSA tag to the DSA stack
+			 * via skb dst info.
+			 */
+			u32 sptag = FIELD_GET(QDMA_ETH_RXMSG_SPTAG,
+					      le32_to_cpu(desc->msg0));
+
+			if (sptag < ARRAY_SIZE(port->dsa_meta) &&
+			    port->dsa_meta[sptag])
+				skb_dst_set_noref(q->skb,
+						  &port->dsa_meta[sptag]->dst);
 		}
 
-		skb_reserve(skb, 2);
-		__skb_put(skb, len);
-		skb_mark_for_recycle(skb);
-		skb->dev = eth->ports[p]->dev;
-		skb->protocol = eth_type_trans(skb, skb->dev);
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		skb_record_rx_queue(skb, qid);
-		napi_gro_receive(&q->napi, skb);
+		hash = FIELD_GET(AIROHA_RXD4_FOE_ENTRY, msg1);
+		if (hash != AIROHA_RXD4_FOE_ENTRY)
+			skb_set_hash(q->skb, jhash_1word(hash, 0),
+				     PKT_HASH_TYPE_L4);
+
+		reason = FIELD_GET(AIROHA_RXD4_PPE_CPU_REASON, msg1);
+		if (reason == PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED)
+			airoha_ppe_check_skb(&eth->ppe->dev, q->skb, hash,
+					     false);
 
 		done++;
+		napi_gro_receive(&q->napi, q->skb);
+		q->skb = NULL;
+		continue;
+free_frag:
+		if (q->skb) {
+			dev_kfree_skb(q->skb);
+			q->skb = NULL;
+		} else {
+			page_pool_put_full_page(q->page_pool, page, true);
+		}
 	}
 	airoha_qdma_fill_rx_queue(q);
 
@@ -1550,9 +716,20 @@ static int airoha_qdma_rx_napi_poll(struct napi_struct *napi, int budget)
 		done += cur;
 	} while (cur && done < budget);
 
-	if (done < budget && napi_complete(napi))
-		airoha_qdma_irq_enable(q->qdma, QDMA_INT_REG_IDX1,
-				       RX_DONE_INT_MASK);
+	if (done < budget && napi_complete(napi)) {
+		struct airoha_qdma *qdma = q->qdma;
+		int i, qid = q - &qdma->q_rx[0];
+		int intr_reg = qid < RX_DONE_HIGH_OFFSET ? QDMA_INT_REG_IDX1
+							 : QDMA_INT_REG_IDX2;
+
+		for (i = 0; i < ARRAY_SIZE(qdma->irq_banks); i++) {
+			if (!(BIT(qid) & RX_IRQ_BANK_PIN_MASK(i)))
+				continue;
+
+			airoha_qdma_irq_enable(&qdma->irq_banks[i], intr_reg,
+					       BIT(qid % RX_DONE_HIGH_OFFSET));
+		}
+	}
 
 	return done;
 }
@@ -1608,6 +785,7 @@ static int airoha_qdma_init_rx_queue(struct airoha_queue *q,
 			FIELD_PREP(RX_RING_THR_MASK, thr));
 	airoha_qdma_rmw(qdma, REG_RX_DMA_IDX(qid), RX_RING_DMA_IDX_MASK,
 			FIELD_PREP(RX_RING_DMA_IDX_MASK, q->head));
+	airoha_qdma_set(qdma, REG_RX_SCATTER_CFG(qid), RX_RING_SG_EN_MASK);
 
 	airoha_qdma_fill_rx_queue(q);
 
@@ -1714,19 +892,13 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget)
 
 		dma_unmap_single(eth->dev, e->dma_addr, e->dma_len,
 				 DMA_TO_DEVICE);
-		memset(e, 0, sizeof(*e));
+		e->dma_addr = 0;
+		list_add_tail(&e->list, &q->tx_list);
+
 		WRITE_ONCE(desc->msg0, 0);
 		WRITE_ONCE(desc->msg1, 0);
 		q->queued--;
 
-		/* completion ring can report out-of-order indexes if hw QoS
-		 * is enabled and packets with different priority are queued
-		 * to same DMA ring. Take into account possible out-of-order
-		 * reports incrementing DMA ring tail pointer
-		 */
-		while (q->tail != q->head && !q->entry[q->tail].dma_addr)
-			q->tail = (q->tail + 1) % q->ndesc;
-
 		if (skb) {
 			u16 queue = skb_get_queue_mapping(skb);
 			struct netdev_queue *txq;
@@ -1754,7 +926,7 @@ unlock:
 	}
 
 	if (done < budget && napi_complete(napi))
-		airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX0,
+		airoha_qdma_irq_enable(&qdma->irq_banks[0], QDMA_INT_REG_IDX0,
 				       TX_DONE_INT_MASK(id));
 
 	return done;
@@ -1771,6 +943,7 @@ static int airoha_qdma_init_tx_queue(struct airoha_queue *q,
 	q->ndesc = size;
 	q->qdma = qdma;
 	q->free_thr = 1 + MAX_SKB_FRAGS;
+	INIT_LIST_HEAD(&q->tx_list);
 
 	q->entry = devm_kzalloc(eth->dev, q->ndesc * sizeof(*q->entry),
 				GFP_KERNEL);
@@ -1783,17 +956,21 @@ static int airoha_qdma_init_tx_queue(struct airoha_queue *q,
 		return -ENOMEM;
 
 	for (i = 0; i < q->ndesc; i++) {
-		u32 val;
+		u32 val = FIELD_PREP(QDMA_DESC_DONE_MASK, 1);
 
-		val = FIELD_PREP(QDMA_DESC_DONE_MASK, 1);
+		list_add_tail(&q->entry[i].list, &q->tx_list);
 		WRITE_ONCE(q->desc[i].ctrl, cpu_to_le32(val));
 	}
 
+	/* xmit ring drop default setting */
+	airoha_qdma_set(qdma, REG_TX_RING_BLOCKING(qid),
+			TX_RING_IRQ_BLOCKING_TX_DROP_EN_MASK);
+
 	airoha_qdma_wr(qdma, REG_TX_RING_BASE(qid), dma_addr);
 	airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK,
-			FIELD_PREP(TX_RING_CPU_IDX_MASK, q->head));
+			FIELD_PREP(TX_RING_CPU_IDX_MASK, 0));
 	airoha_qdma_rmw(qdma, REG_TX_DMA_IDX(qid), TX_RING_DMA_IDX_MASK,
-			FIELD_PREP(TX_RING_DMA_IDX_MASK, q->head));
+			FIELD_PREP(TX_RING_DMA_IDX_MASK, 0));
 
 	return 0;
 }
@@ -1849,17 +1026,21 @@ static int airoha_qdma_init_tx(struct airoha_qdma *qdma)
 static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q)
 {
 	struct airoha_eth *eth = q->qdma->eth;
+	int i;
 
 	spin_lock_bh(&q->lock);
-	while (q->queued) {
-		struct airoha_queue_entry *e = &q->entry[q->tail];
+	for (i = 0; i < q->ndesc; i++) {
+		struct airoha_queue_entry *e = &q->entry[i];
+
+		if (!e->dma_addr)
+			continue;
 
 		dma_unmap_single(eth->dev, e->dma_addr, e->dma_len,
 				 DMA_TO_DEVICE);
 		dev_kfree_skb_any(e->skb);
+		e->dma_addr = 0;
 		e->skb = NULL;
-
-		q->tail = (q->tail + 1) % q->ndesc;
+		list_add_tail(&e->list, &q->tx_list);
 		q->queued--;
 	}
 	spin_unlock_bh(&q->lock);
@@ -1867,37 +1048,64 @@ static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q)
 
 static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
 {
+	int size, index, num_desc = HW_DSCP_NUM;
 	struct airoha_eth *eth = qdma->eth;
+	int id = qdma - &eth->qdma[0];
+	u32 status, buf_size;
 	dma_addr_t dma_addr;
-	u32 status;
-	int size;
+	const char *name;
 
-	size = HW_DSCP_NUM * sizeof(struct airoha_qdma_fwd_desc);
-	qdma->hfwd.desc = dmam_alloc_coherent(eth->dev, size, &dma_addr,
-					      GFP_KERNEL);
-	if (!qdma->hfwd.desc)
+	name = devm_kasprintf(eth->dev, GFP_KERNEL, "qdma%d-buf", id);
+	if (!name)
 		return -ENOMEM;
 
-	airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
+	buf_size = id ? AIROHA_MAX_PACKET_SIZE / 2 : AIROHA_MAX_PACKET_SIZE;
+	index = of_property_match_string(eth->dev->of_node,
+					 "memory-region-names", name);
+	if (index >= 0) {
+		struct reserved_mem *rmem;
+		struct device_node *np;
 
-	size = AIROHA_MAX_PACKET_SIZE * HW_DSCP_NUM;
-	qdma->hfwd.q = dmam_alloc_coherent(eth->dev, size, &dma_addr,
-					   GFP_KERNEL);
-	if (!qdma->hfwd.q)
-		return -ENOMEM;
+		/* Consume reserved memory for hw forwarding buffers queue if
+		 * available in the DTS
+		 */
+		np = of_parse_phandle(eth->dev->of_node, "memory-region",
+				      index);
+		if (!np)
+			return -ENODEV;
+
+		rmem = of_reserved_mem_lookup(np);
+		of_node_put(np);
+		dma_addr = rmem->base;
+		/* Compute the number of hw descriptors according to the
+		 * reserved memory size and the payload buffer size
+		 */
+		num_desc = div_u64(rmem->size, buf_size);
+	} else {
+		size = buf_size * num_desc;
+		if (!dmam_alloc_coherent(eth->dev, size, &dma_addr,
+					 GFP_KERNEL))
+			return -ENOMEM;
+	}
 
 	airoha_qdma_wr(qdma, REG_FWD_BUF_BASE, dma_addr);
 
+	size = num_desc * sizeof(struct airoha_qdma_fwd_desc);
+	if (!dmam_alloc_coherent(eth->dev, size, &dma_addr, GFP_KERNEL))
+		return -ENOMEM;
+
+	airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
+	/* QDMA0: 2KB. QDMA1: 1KB */
 	airoha_qdma_rmw(qdma, REG_HW_FWD_DSCP_CFG,
 			HW_FWD_DSCP_PAYLOAD_SIZE_MASK,
-			FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, 0));
+			FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, !!id));
 	airoha_qdma_rmw(qdma, REG_FWD_DSCP_LOW_THR, FWD_DSCP_LOW_THR_MASK,
 			FIELD_PREP(FWD_DSCP_LOW_THR_MASK, 128));
 	airoha_qdma_rmw(qdma, REG_LMGR_INIT_CFG,
 			LMGR_INIT_START | LMGR_SRAM_MODE_MASK |
 			HW_FWD_DESC_NUM_MASK,
-			FIELD_PREP(HW_FWD_DESC_NUM_MASK, HW_DSCP_NUM) |
-			LMGR_INIT_START);
+			FIELD_PREP(HW_FWD_DESC_NUM_MASK, num_desc) |
+			LMGR_INIT_START | LMGR_SRAM_MODE_MASK);
 
 	return read_poll_timeout(airoha_qdma_rr, status,
 				 !(status & LMGR_INIT_START), USEC_PER_MSEC,
@@ -1955,18 +1163,49 @@ static void airoha_qdma_init_qos(struct airoha_qdma *qdma)
 			FIELD_PREP(SLA_SLOW_TICK_RATIO_MASK, 40));
 }
 
+static void airoha_qdma_init_qos_stats(struct airoha_qdma *qdma)
+{
+	int i;
+
+	for (i = 0; i < AIROHA_NUM_QOS_CHANNELS; i++) {
+		/* Tx-cpu transferred count */
+		airoha_qdma_wr(qdma, REG_CNTR_VAL(i << 1), 0);
+		airoha_qdma_wr(qdma, REG_CNTR_CFG(i << 1),
+			       CNTR_EN_MASK | CNTR_ALL_QUEUE_EN_MASK |
+			       CNTR_ALL_DSCP_RING_EN_MASK |
+			       FIELD_PREP(CNTR_CHAN_MASK, i));
+		/* Tx-fwd transferred count */
+		airoha_qdma_wr(qdma, REG_CNTR_VAL((i << 1) + 1), 0);
+		airoha_qdma_wr(qdma, REG_CNTR_CFG(i << 1),
+			       CNTR_EN_MASK | CNTR_ALL_QUEUE_EN_MASK |
+			       CNTR_ALL_DSCP_RING_EN_MASK |
+			       FIELD_PREP(CNTR_SRC_MASK, 1) |
+			       FIELD_PREP(CNTR_CHAN_MASK, i));
+	}
+}
+
 static int airoha_qdma_hw_init(struct airoha_qdma *qdma)
 {
 	int i;
 
-	/* clear pending irqs */
-	for (i = 0; i < ARRAY_SIZE(qdma->irqmask); i++)
+	for (i = 0; i < ARRAY_SIZE(qdma->irq_banks); i++) {
+		/* clear pending irqs */
 		airoha_qdma_wr(qdma, REG_INT_STATUS(i), 0xffffffff);
-
-	/* setup irqs */
-	airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX0, INT_IDX0_MASK);
-	airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX1, INT_IDX1_MASK);
-	airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX4, INT_IDX4_MASK);
+		/* setup rx irqs */
+		airoha_qdma_irq_enable(&qdma->irq_banks[i], QDMA_INT_REG_IDX0,
+				       INT_RX0_MASK(RX_IRQ_BANK_PIN_MASK(i)));
+		airoha_qdma_irq_enable(&qdma->irq_banks[i], QDMA_INT_REG_IDX1,
+				       INT_RX1_MASK(RX_IRQ_BANK_PIN_MASK(i)));
+		airoha_qdma_irq_enable(&qdma->irq_banks[i], QDMA_INT_REG_IDX2,
+				       INT_RX2_MASK(RX_IRQ_BANK_PIN_MASK(i)));
+		airoha_qdma_irq_enable(&qdma->irq_banks[i], QDMA_INT_REG_IDX3,
+				       INT_RX3_MASK(RX_IRQ_BANK_PIN_MASK(i)));
+	}
+	/* setup tx irqs */
+	airoha_qdma_irq_enable(&qdma->irq_banks[0], QDMA_INT_REG_IDX0,
+			       TX_COHERENT_LOW_INT_MASK | INT_TX_MASK);
+	airoha_qdma_irq_enable(&qdma->irq_banks[0], QDMA_INT_REG_IDX4,
+			       TX_COHERENT_HIGH_INT_MASK);
 
 	/* setup irq binding */
 	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
@@ -1982,7 +1221,6 @@ static int airoha_qdma_hw_init(struct airoha_qdma *qdma)
 	}
 
 	airoha_qdma_wr(qdma, REG_QDMA_GLOBAL_CFG,
-		       GLOBAL_CFG_RX_2B_OFFSET_MASK |
 		       FIELD_PREP(GLOBAL_CFG_DMA_PREFERENCE_MASK, 3) |
 		       GLOBAL_CFG_CPU_TXR_RR_MASK |
 		       GLOBAL_CFG_PAYLOAD_BYTE_SWAP_MASK |
@@ -2005,36 +1243,46 @@ static int airoha_qdma_hw_init(struct airoha_qdma *qdma)
 
 	airoha_qdma_set(qdma, REG_TXQ_CNGST_CFG,
 			TXQ_CNGST_DROP_EN | TXQ_CNGST_DEI_DROP_EN);
+	airoha_qdma_init_qos_stats(qdma);
 
 	return 0;
 }
 
 static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 {
-	struct airoha_qdma *qdma = dev_instance;
-	u32 intr[ARRAY_SIZE(qdma->irqmask)];
+	struct airoha_irq_bank *irq_bank = dev_instance;
+	struct airoha_qdma *qdma = irq_bank->qdma;
+	u32 rx_intr_mask = 0, rx_intr1, rx_intr2;
+	u32 intr[ARRAY_SIZE(irq_bank->irqmask)];
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(qdma->irqmask); i++) {
+	for (i = 0; i < ARRAY_SIZE(intr); i++) {
 		intr[i] = airoha_qdma_rr(qdma, REG_INT_STATUS(i));
-		intr[i] &= qdma->irqmask[i];
+		intr[i] &= irq_bank->irqmask[i];
 		airoha_qdma_wr(qdma, REG_INT_STATUS(i), intr[i]);
 	}
 
 	if (!test_bit(DEV_STATE_INITIALIZED, &qdma->eth->state))
 		return IRQ_NONE;
 
-	if (intr[1] & RX_DONE_INT_MASK) {
-		airoha_qdma_irq_disable(qdma, QDMA_INT_REG_IDX1,
-					RX_DONE_INT_MASK);
+	rx_intr1 = intr[1] & RX_DONE_LOW_INT_MASK;
+	if (rx_intr1) {
+		airoha_qdma_irq_disable(irq_bank, QDMA_INT_REG_IDX1, rx_intr1);
+		rx_intr_mask |= rx_intr1;
+	}
 
-		for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
-			if (!qdma->q_rx[i].ndesc)
-				continue;
+	rx_intr2 = intr[2] & RX_DONE_HIGH_INT_MASK;
+	if (rx_intr2) {
+		airoha_qdma_irq_disable(irq_bank, QDMA_INT_REG_IDX2, rx_intr2);
+		rx_intr_mask |= (rx_intr2 << 16);
+	}
 
-			if (intr[1] & BIT(i))
-				napi_schedule(&qdma->q_rx[i].napi);
-		}
+	for (i = 0; rx_intr_mask && i < ARRAY_SIZE(qdma->q_rx); i++) {
+		if (!qdma->q_rx[i].ndesc)
+			continue;
+
+		if (rx_intr_mask & BIT(i))
+			napi_schedule(&qdma->q_rx[i].napi);
 	}
 
 	if (intr[0] & INT_TX_MASK) {
@@ -2042,7 +1290,7 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 			if (!(intr[0] & TX_DONE_INT_MASK(i)))
 				continue;
 
-			airoha_qdma_irq_disable(qdma, QDMA_INT_REG_IDX0,
+			airoha_qdma_irq_disable(irq_bank, QDMA_INT_REG_IDX0,
 						TX_DONE_INT_MASK(i));
 			napi_schedule(&qdma->q_tx_irq[i].napi);
 		}
@@ -2051,6 +1299,39 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 	return IRQ_HANDLED;
 }
 
+static int airoha_qdma_init_irq_banks(struct platform_device *pdev,
+				      struct airoha_qdma *qdma)
+{
+	struct airoha_eth *eth = qdma->eth;
+	int i, id = qdma - &eth->qdma[0];
+
+	for (i = 0; i < ARRAY_SIZE(qdma->irq_banks); i++) {
+		struct airoha_irq_bank *irq_bank = &qdma->irq_banks[i];
+		int err, irq_index = 4 * id + i;
+		const char *name;
+
+		spin_lock_init(&irq_bank->irq_lock);
+		irq_bank->qdma = qdma;
+
+		irq_bank->irq = platform_get_irq(pdev, irq_index);
+		if (irq_bank->irq < 0)
+			return irq_bank->irq;
+
+		name = devm_kasprintf(eth->dev, GFP_KERNEL,
+				      KBUILD_MODNAME ".%d", irq_index);
+		if (!name)
+			return -ENOMEM;
+
+		err = devm_request_irq(eth->dev, irq_bank->irq,
+				       airoha_irq_handler, IRQF_SHARED, name,
+				       irq_bank);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int airoha_qdma_init(struct platform_device *pdev,
 			    struct airoha_eth *eth,
 			    struct airoha_qdma *qdma)
@@ -2058,9 +1339,7 @@ static int airoha_qdma_init(struct platform_device *pdev,
 	int err, id = qdma - &eth->qdma[0];
 	const char *res;
 
-	spin_lock_init(&qdma->irq_lock);
 	qdma->eth = eth;
-
 	res = devm_kasprintf(eth->dev, GFP_KERNEL, "qdma%d", id);
 	if (!res)
 		return -ENOMEM;
@@ -2070,12 +1349,7 @@ static int airoha_qdma_init(struct platform_device *pdev,
 		return dev_err_probe(eth->dev, PTR_ERR(qdma->regs),
 				     "failed to iomap qdma%d regs\n", id);
 
-	qdma->irq = platform_get_irq(pdev, 4 * id);
-	if (qdma->irq < 0)
-		return qdma->irq;
-
-	err = devm_request_irq(eth->dev, qdma->irq, airoha_irq_handler,
-			       IRQF_SHARED, KBUILD_MODNAME, qdma);
+	err = airoha_qdma_init_irq_banks(pdev, qdma);
 	if (err)
 		return err;
 
@@ -2100,8 +1374,7 @@ static int airoha_hw_init(struct platform_device *pdev,
 	int err, i;
 
 	/* disable xsi */
-	err = reset_control_bulk_assert(ARRAY_SIZE(eth->xsi_rsts),
-					eth->xsi_rsts);
+	err = reset_control_bulk_assert(eth->soc->num_xsi_rsts, eth->xsi_rsts);
 	if (err)
 		return err;
 
@@ -2125,6 +1398,10 @@ static int airoha_hw_init(struct platform_device *pdev,
 			return err;
 	}
 
+	err = airoha_ppe_init(eth);
+	if (err)
+		return err;
+
 	set_bit(DEV_STATE_INITIALIZED, &eth->state);
 
 	return 0;
@@ -2331,12 +1608,12 @@ static void airoha_update_hw_stats(struct airoha_gdm_port *port)
 
 static int airoha_dev_open(struct net_device *dev)
 {
+	int err, len = ETH_HLEN + dev->mtu + ETH_FCS_LEN;
 	struct airoha_gdm_port *port = netdev_priv(dev);
 	struct airoha_qdma *qdma = port->qdma;
-	int err;
 
 	netif_tx_start_all_queues(dev);
-	err = airoha_set_gdm_ports(qdma->eth, true);
+	err = airoha_set_vip_for_gdm_port(port, true);
 	if (err)
 		return err;
 
@@ -2347,9 +1624,15 @@ static int airoha_dev_open(struct net_device *dev)
 		airoha_fe_clear(qdma->eth, REG_GDM_INGRESS_CFG(port->id),
 				GDM_STAG_EN_MASK);
 
+	airoha_fe_rmw(qdma->eth, REG_GDM_LEN_CFG(port->id),
+		      GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK,
+		      FIELD_PREP(GDM_SHORT_LEN_MASK, 60) |
+		      FIELD_PREP(GDM_LONG_LEN_MASK, len));
+
 	airoha_qdma_set(qdma, REG_QDMA_GLOBAL_CFG,
 			GLOBAL_CFG_TX_DMA_EN_MASK |
 			GLOBAL_CFG_RX_DMA_EN_MASK);
+	atomic_inc(&qdma->users);
 
 	return 0;
 }
@@ -2361,20 +1644,24 @@ static int airoha_dev_stop(struct net_device *dev)
 	int i, err;
 
 	netif_tx_disable(dev);
-	err = airoha_set_gdm_ports(qdma->eth, false);
+	err = airoha_set_vip_for_gdm_port(port, false);
 	if (err)
 		return err;
 
-	airoha_qdma_clear(qdma, REG_QDMA_GLOBAL_CFG,
-			  GLOBAL_CFG_TX_DMA_EN_MASK |
-			  GLOBAL_CFG_RX_DMA_EN_MASK);
+	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++)
+		netdev_tx_reset_subqueue(dev, i);
 
-	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
-		if (!qdma->q_tx[i].ndesc)
-			continue;
+	if (atomic_dec_and_test(&qdma->users)) {
+		airoha_qdma_clear(qdma, REG_QDMA_GLOBAL_CFG,
+				  GLOBAL_CFG_TX_DMA_EN_MASK |
+				  GLOBAL_CFG_RX_DMA_EN_MASK);
 
-		airoha_qdma_cleanup_tx_queue(&qdma->q_tx[i]);
-		netdev_tx_reset_subqueue(dev, i);
+		for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
+			if (!qdma->q_tx[i].ndesc)
+				continue;
+
+			airoha_qdma_cleanup_tx_queue(&qdma->q_tx[i]);
+		}
 	}
 
 	return 0;
@@ -2394,12 +1681,106 @@ static int airoha_dev_set_macaddr(struct net_device *dev, void *p)
 	return 0;
 }
 
+static int airhoha_set_gdm2_loopback(struct airoha_gdm_port *port)
+{
+	struct airoha_eth *eth = port->qdma->eth;
+	u32 val, pse_port, chan, nbq;
+	int src_port;
+
+	/* Forward the traffic to the proper GDM port */
+	pse_port = port->id == AIROHA_GDM3_IDX ? FE_PSE_PORT_GDM3
+					       : FE_PSE_PORT_GDM4;
+	airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(2), pse_port);
+	airoha_fe_clear(eth, REG_GDM_FWD_CFG(2), GDM_STRIP_CRC_MASK);
+
+	/* Enable GDM2 loopback */
+	airoha_fe_wr(eth, REG_GDM_TXCHN_EN(2), 0xffffffff);
+	airoha_fe_wr(eth, REG_GDM_RXCHN_EN(2), 0xffff);
+
+	chan = port->id == AIROHA_GDM3_IDX ? airoha_is_7581(eth) ? 4 : 3 : 0;
+	airoha_fe_rmw(eth, REG_GDM_LPBK_CFG(2),
+		      LPBK_CHAN_MASK | LPBK_MODE_MASK | LPBK_EN_MASK,
+		      FIELD_PREP(LPBK_CHAN_MASK, chan) |
+		      LBK_GAP_MODE_MASK | LBK_LEN_MODE_MASK |
+		      LBK_CHAN_MODE_MASK | LPBK_EN_MASK);
+	airoha_fe_rmw(eth, REG_GDM_LEN_CFG(2),
+		      GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK,
+		      FIELD_PREP(GDM_SHORT_LEN_MASK, 60) |
+		      FIELD_PREP(GDM_LONG_LEN_MASK, AIROHA_MAX_MTU));
+
+	/* Disable VIP and IFC for GDM2 */
+	airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(2));
+	airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, BIT(2));
+
+	/* XXX: handle XSI_USB_PORT and XSI_PCE1_PORT */
+	nbq = port->id == AIROHA_GDM3_IDX && airoha_is_7581(eth) ? 4 : 0;
+	src_port = eth->soc->ops.get_src_port_id(port, nbq);
+	if (src_port < 0)
+		return src_port;
+
+	airoha_fe_rmw(eth, REG_FE_WAN_PORT,
+		      WAN1_EN_MASK | WAN1_MASK | WAN0_MASK,
+		      FIELD_PREP(WAN0_MASK, src_port));
+	val = src_port & SP_CPORT_DFT_MASK;
+	airoha_fe_rmw(eth,
+		      REG_SP_DFT_CPORT(src_port >> fls(SP_CPORT_DFT_MASK)),
+		      SP_CPORT_MASK(val),
+		      FE_PSE_PORT_CDM2 << __ffs(SP_CPORT_MASK(val)));
+
+	if (port->id != AIROHA_GDM3_IDX && airoha_is_7581(eth))
+		airoha_fe_rmw(eth, REG_SRC_PORT_FC_MAP6,
+			      FC_ID_OF_SRC_PORT24_MASK,
+			      FIELD_PREP(FC_ID_OF_SRC_PORT24_MASK, 2));
+
+	return 0;
+}
+
 static int airoha_dev_init(struct net_device *dev)
 {
 	struct airoha_gdm_port *port = netdev_priv(dev);
+	struct airoha_qdma *qdma = port->qdma;
+	struct airoha_eth *eth = qdma->eth;
+	u32 pse_port, fe_cpu_port;
+	u8 ppe_id;
 
 	airoha_set_macaddr(port, dev->dev_addr);
 
+	switch (port->id) {
+	case 3:
+	case 4:
+		/* If GDM2 is active we can't enable loopback */
+		if (!eth->ports[1]) {
+			int err;
+
+			err = airhoha_set_gdm2_loopback(port);
+			if (err)
+				return err;
+		}
+		fallthrough;
+	case 2:
+		if (airoha_ppe_is_enabled(eth, 1)) {
+			/* For PPE2 always use secondary cpu port. */
+			fe_cpu_port = FE_PSE_PORT_CDM2;
+			pse_port = FE_PSE_PORT_PPE2;
+			break;
+		}
+		fallthrough;
+	default: {
+		u8 qdma_id = qdma - &eth->qdma[0];
+
+		/* For PPE1 select cpu port according to the running QDMA. */
+		fe_cpu_port = qdma_id ? FE_PSE_PORT_CDM2 : FE_PSE_PORT_CDM1;
+		pse_port = FE_PSE_PORT_PPE1;
+		break;
+	}
+	}
+
+	airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(port->id), pse_port);
+	ppe_id = pse_port == FE_PSE_PORT_PPE2 ? 1 : 0;
+	airoha_fe_rmw(eth, REG_PPE_DFT_CPORT0(ppe_id),
+		      DFT_CPORT_MASK(port->id),
+		      fe_cpu_port << __ffs(DFT_CPORT_MASK(port->id)));
+
 	return 0;
 }
 
@@ -2425,21 +1806,121 @@ static void airoha_dev_get_stats64(struct net_device *dev,
 	} while (u64_stats_fetch_retry(&port->stats.syncp, start));
 }
 
+static int airoha_dev_change_mtu(struct net_device *dev, int mtu)
+{
+	struct airoha_gdm_port *port = netdev_priv(dev);
+	struct airoha_eth *eth = port->qdma->eth;
+	u32 len = ETH_HLEN + mtu + ETH_FCS_LEN;
+
+	airoha_fe_rmw(eth, REG_GDM_LEN_CFG(port->id),
+		      GDM_LONG_LEN_MASK,
+		      FIELD_PREP(GDM_LONG_LEN_MASK, len));
+	WRITE_ONCE(dev->mtu, mtu);
+
+	return 0;
+}
+
+static u16 airoha_dev_select_queue(struct net_device *dev, struct sk_buff *skb,
+				   struct net_device *sb_dev)
+{
+	struct airoha_gdm_port *port = netdev_priv(dev);
+	int queue, channel;
+
+	/* For dsa device select QoS channel according to the dsa user port
+	 * index, rely on port id otherwise. Select QoS queue based on the
+	 * skb priority.
+	 */
+	channel = netdev_uses_dsa(dev) ? skb_get_queue_mapping(skb) : port->id;
+	channel = channel % AIROHA_NUM_QOS_CHANNELS;
+	queue = (skb->priority - 1) % AIROHA_NUM_QOS_QUEUES; /* QoS queue */
+	queue = channel * AIROHA_NUM_QOS_QUEUES + queue;
+
+	return queue < dev->num_tx_queues ? queue : 0;
+}
+
+static u32 airoha_get_dsa_tag(struct sk_buff *skb, struct net_device *dev)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+	struct ethhdr *ehdr;
+	u8 xmit_tpid;
+	u16 tag;
+
+	if (!netdev_uses_dsa(dev))
+		return 0;
+
+	if (dev->dsa_ptr->tag_ops->proto != DSA_TAG_PROTO_MTK)
+		return 0;
+
+	if (skb_cow_head(skb, 0))
+		return 0;
+
+	ehdr = (struct ethhdr *)skb->data;
+	tag = be16_to_cpu(ehdr->h_proto);
+	xmit_tpid = tag >> 8;
+
+	switch (xmit_tpid) {
+	case MTK_HDR_XMIT_TAGGED_TPID_8100:
+		ehdr->h_proto = cpu_to_be16(ETH_P_8021Q);
+		tag &= ~(MTK_HDR_XMIT_TAGGED_TPID_8100 << 8);
+		break;
+	case MTK_HDR_XMIT_TAGGED_TPID_88A8:
+		ehdr->h_proto = cpu_to_be16(ETH_P_8021AD);
+		tag &= ~(MTK_HDR_XMIT_TAGGED_TPID_88A8 << 8);
+		break;
+	default:
+		/* PPE module requires untagged DSA packets to work properly,
+		 * so move DSA tag to DMA descriptor.
+		 */
+		memmove(skb->data + MTK_HDR_LEN, skb->data, 2 * ETH_ALEN);
+		__skb_pull(skb, MTK_HDR_LEN);
+		break;
+	}
+
+	return tag;
+#else
+	return 0;
+#endif
+}
+
+static int airoha_get_fe_port(struct airoha_gdm_port *port)
+{
+	struct airoha_qdma *qdma = port->qdma;
+	struct airoha_eth *eth = qdma->eth;
+
+	switch (eth->soc->version) {
+	case 0x7583:
+		return port->id == AIROHA_GDM3_IDX ? FE_PSE_PORT_GDM3
+						   : port->id;
+	case 0x7581:
+	default:
+		return port->id == AIROHA_GDM4_IDX ? FE_PSE_PORT_GDM4
+						   : port->id;
+	}
+}
+
 static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 				   struct net_device *dev)
 {
-	struct skb_shared_info *sinfo = skb_shinfo(skb);
 	struct airoha_gdm_port *port = netdev_priv(dev);
-	u32 msg0 = 0, msg1, len = skb_headlen(skb);
-	int i, qid = skb_get_queue_mapping(skb);
 	struct airoha_qdma *qdma = port->qdma;
-	u32 nr_frags = 1 + sinfo->nr_frags;
+	u32 nr_frags, tag, msg0, msg1, len;
+	struct airoha_queue_entry *e;
 	struct netdev_queue *txq;
 	struct airoha_queue *q;
-	void *data = skb->data;
+	LIST_HEAD(tx_list);
+	void *data;
+	int i, qid;
 	u16 index;
 	u8 fport;
 
+	qid = skb_get_queue_mapping(skb) % ARRAY_SIZE(qdma->q_tx);
+	tag = airoha_get_dsa_tag(skb, dev);
+
+	msg0 = FIELD_PREP(QDMA_ETH_TXMSG_CHAN_MASK,
+			  qid / AIROHA_NUM_QOS_QUEUES) |
+	       FIELD_PREP(QDMA_ETH_TXMSG_QUEUE_MASK,
+			  qid % AIROHA_NUM_QOS_QUEUES) |
+	       FIELD_PREP(QDMA_ETH_TXMSG_SP_TAG_MASK, tag);
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		msg0 |= FIELD_PREP(QDMA_ETH_TXMSG_TCO_MASK, 1) |
 			FIELD_PREP(QDMA_ETH_TXMSG_UCO_MASK, 1) |
@@ -2450,15 +1931,16 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 		if (skb_cow_head(skb, 0))
 			goto error;
 
-		if (sinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
-			__be16 csum = cpu_to_be16(sinfo->gso_size);
+		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 |
+						 SKB_GSO_TCPV6)) {
+			__be16 csum = cpu_to_be16(skb_shinfo(skb)->gso_size);
 
 			tcp_hdr(skb)->check = (__force __sum16)csum;
 			msg0 |= FIELD_PREP(QDMA_ETH_TXMSG_TSO_MASK, 1);
 		}
 	}
 
-	fport = port->id == 4 ? FE_PSE_PORT_GDM4 : port->id;
+	fport = airoha_get_fe_port(port);
 	msg1 = FIELD_PREP(QDMA_ETH_TXMSG_FPORT_MASK, fport) |
 	       FIELD_PREP(QDMA_ETH_TXMSG_METER_MASK, 0x7f);
 
@@ -2469,18 +1951,25 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 	spin_lock_bh(&q->lock);
 
 	txq = netdev_get_tx_queue(dev, qid);
-	if (q->queued + nr_frags > q->ndesc) {
+	nr_frags = 1 + skb_shinfo(skb)->nr_frags;
+
+	if (q->queued + nr_frags >= q->ndesc) {
 		/* not enough space in the queue */
 		netif_tx_stop_queue(txq);
 		spin_unlock_bh(&q->lock);
 		return NETDEV_TX_BUSY;
 	}
 
-	index = q->head;
+	len = skb_headlen(skb);
+	data = skb->data;
+
+	e = list_first_entry(&q->tx_list, struct airoha_queue_entry,
+			     list);
+	index = e - q->entry;
+
 	for (i = 0; i < nr_frags; i++) {
 		struct airoha_qdma_desc *desc = &q->desc[index];
-		struct airoha_queue_entry *e = &q->entry[index];
-		skb_frag_t *frag = &sinfo->frags[i];
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 		dma_addr_t addr;
 		u32 val;
 
@@ -2489,7 +1978,14 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 		if (unlikely(dma_mapping_error(dev->dev.parent, addr)))
 			goto error_unmap;
 
-		index = (index + 1) % q->ndesc;
+		list_move_tail(&e->list, &tx_list);
+		e->skb = i ? NULL : skb;
+		e->dma_addr = addr;
+		e->dma_len = len;
+
+		e = list_first_entry(&q->tx_list, struct airoha_queue_entry,
+				     list);
+		index = e - q->entry;
 
 		val = FIELD_PREP(QDMA_DESC_LEN_MASK, len);
 		if (i < nr_frags - 1)
@@ -2502,15 +1998,9 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 		WRITE_ONCE(desc->msg1, cpu_to_le32(msg1));
 		WRITE_ONCE(desc->msg2, cpu_to_le32(0xffff));
 
-		e->skb = i ? NULL : skb;
-		e->dma_addr = addr;
-		e->dma_len = len;
-
 		data = skb_frag_address(frag);
 		len = skb_frag_size(frag);
 	}
-
-	q->head = index;
 	q->queued += i;
 
 	skb_tx_timestamp(skb);
@@ -2519,7 +2009,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 	if (netif_xmit_stopped(txq) || !netdev_xmit_more())
 		airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid),
 				TX_RING_CPU_IDX_MASK,
-				FIELD_PREP(TX_RING_CPU_IDX_MASK, q->head));
+				FIELD_PREP(TX_RING_CPU_IDX_MASK, index));
 
 	if (q->ndesc - q->queued < q->free_thr)
 		netif_tx_stop_queue(txq);
@@ -2529,10 +2019,13 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 
 error_unmap:
-	for (i--; i >= 0; i--) {
-		index = (q->head + i) % q->ndesc;
-		dma_unmap_single(dev->dev.parent, q->entry[index].dma_addr,
-				 q->entry[index].dma_len, DMA_TO_DEVICE);
+	while (!list_empty(&tx_list)) {
+		e = list_first_entry(&tx_list, struct airoha_queue_entry,
+				     list);
+		dma_unmap_single(dev->dev.parent, e->dma_addr, e->dma_len,
+				 DMA_TO_DEVICE);
+		e->dma_addr = 0;
+		list_move_tail(&e->list, &q->tx_list);
 	}
 
 	spin_unlock_bh(&q->lock);
@@ -2562,8 +2055,12 @@ static void airoha_ethtool_get_mac_stats(struct net_device *dev,
 	airoha_update_hw_stats(port);
 	do {
 		start = u64_stats_fetch_begin(&port->stats.syncp);
+		stats->FramesTransmittedOK = port->stats.tx_ok_pkts;
+		stats->OctetsTransmittedOK = port->stats.tx_ok_bytes;
 		stats->MulticastFramesXmittedOK = port->stats.tx_multicast;
 		stats->BroadcastFramesXmittedOK = port->stats.tx_broadcast;
+		stats->FramesReceivedOK = port->stats.rx_ok_pkts;
+		stats->OctetsReceivedOK = port->stats.rx_ok_bytes;
 		stats->BroadcastFramesReceivedOK = port->stats.rx_broadcast;
 	} while (u64_stats_fetch_retry(&port->stats.syncp, start));
 }
@@ -2609,28 +2106,758 @@ airoha_ethtool_get_rmon_stats(struct net_device *dev,
 	} while (u64_stats_fetch_retry(&port->stats.syncp, start));
 }
 
+static int airoha_qdma_set_chan_tx_sched(struct airoha_gdm_port *port,
+					 int channel, enum tx_sched_mode mode,
+					 const u16 *weights, u8 n_weights)
+{
+	int i;
+
+	for (i = 0; i < AIROHA_NUM_TX_RING; i++)
+		airoha_qdma_clear(port->qdma, REG_QUEUE_CLOSE_CFG(channel),
+				  TXQ_DISABLE_CHAN_QUEUE_MASK(channel, i));
+
+	for (i = 0; i < n_weights; i++) {
+		u32 status;
+		int err;
+
+		airoha_qdma_wr(port->qdma, REG_TXWRR_WEIGHT_CFG,
+			       TWRR_RW_CMD_MASK |
+			       FIELD_PREP(TWRR_CHAN_IDX_MASK, channel) |
+			       FIELD_PREP(TWRR_QUEUE_IDX_MASK, i) |
+			       FIELD_PREP(TWRR_VALUE_MASK, weights[i]));
+		err = read_poll_timeout(airoha_qdma_rr, status,
+					status & TWRR_RW_CMD_DONE,
+					USEC_PER_MSEC, 10 * USEC_PER_MSEC,
+					true, port->qdma,
+					REG_TXWRR_WEIGHT_CFG);
+		if (err)
+			return err;
+	}
+
+	airoha_qdma_rmw(port->qdma, REG_CHAN_QOS_MODE(channel >> 3),
+			CHAN_QOS_MODE_MASK(channel),
+			mode << __ffs(CHAN_QOS_MODE_MASK(channel)));
+
+	return 0;
+}
+
+static int airoha_qdma_set_tx_prio_sched(struct airoha_gdm_port *port,
+					 int channel)
+{
+	static const u16 w[AIROHA_NUM_QOS_QUEUES] = {};
+
+	return airoha_qdma_set_chan_tx_sched(port, channel, TC_SCH_SP, w,
+					     ARRAY_SIZE(w));
+}
+
+static int airoha_qdma_set_tx_ets_sched(struct airoha_gdm_port *port,
+					int channel,
+					struct tc_ets_qopt_offload *opt)
+{
+	struct tc_ets_qopt_offload_replace_params *p = &opt->replace_params;
+	enum tx_sched_mode mode = TC_SCH_SP;
+	u16 w[AIROHA_NUM_QOS_QUEUES] = {};
+	int i, nstrict = 0;
+
+	if (p->bands > AIROHA_NUM_QOS_QUEUES)
+		return -EINVAL;
+
+	for (i = 0; i < p->bands; i++) {
+		if (!p->quanta[i])
+			nstrict++;
+	}
+
+	/* this configuration is not supported by the hw */
+	if (nstrict == AIROHA_NUM_QOS_QUEUES - 1)
+		return -EINVAL;
+
+	/* EN7581 SoC supports fixed QoS band priority where WRR queues have
+	 * lowest priorities with respect to SP ones.
+	 * e.g: WRR0, WRR1, .., WRRm, SP0, SP1, .., SPn
+	 */
+	for (i = 0; i < nstrict; i++) {
+		if (p->priomap[p->bands - i - 1] != i)
+			return -EINVAL;
+	}
+
+	for (i = 0; i < p->bands - nstrict; i++) {
+		if (p->priomap[i] != nstrict + i)
+			return -EINVAL;
+
+		w[i] = p->weights[nstrict + i];
+	}
+
+	if (!nstrict)
+		mode = TC_SCH_WRR8;
+	else if (nstrict < AIROHA_NUM_QOS_QUEUES - 1)
+		mode = nstrict + 1;
+
+	return airoha_qdma_set_chan_tx_sched(port, channel, mode, w,
+					     ARRAY_SIZE(w));
+}
+
+static int airoha_qdma_get_tx_ets_stats(struct airoha_gdm_port *port,
+					int channel,
+					struct tc_ets_qopt_offload *opt)
+{
+	u64 cpu_tx_packets = airoha_qdma_rr(port->qdma,
+					    REG_CNTR_VAL(channel << 1));
+	u64 fwd_tx_packets = airoha_qdma_rr(port->qdma,
+					    REG_CNTR_VAL((channel << 1) + 1));
+	u64 tx_packets = (cpu_tx_packets - port->cpu_tx_packets) +
+			 (fwd_tx_packets - port->fwd_tx_packets);
+	_bstats_update(opt->stats.bstats, 0, tx_packets);
+
+	port->cpu_tx_packets = cpu_tx_packets;
+	port->fwd_tx_packets = fwd_tx_packets;
+
+	return 0;
+}
+
+static int airoha_tc_setup_qdisc_ets(struct airoha_gdm_port *port,
+				     struct tc_ets_qopt_offload *opt)
+{
+	int channel;
+
+	if (opt->parent == TC_H_ROOT)
+		return -EINVAL;
+
+	channel = TC_H_MAJ(opt->handle) >> 16;
+	channel = channel % AIROHA_NUM_QOS_CHANNELS;
+
+	switch (opt->command) {
+	case TC_ETS_REPLACE:
+		return airoha_qdma_set_tx_ets_sched(port, channel, opt);
+	case TC_ETS_DESTROY:
+		/* PRIO is default qdisc scheduler */
+		return airoha_qdma_set_tx_prio_sched(port, channel);
+	case TC_ETS_STATS:
+		return airoha_qdma_get_tx_ets_stats(port, channel, opt);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int airoha_qdma_get_rl_param(struct airoha_qdma *qdma, int queue_id,
+				    u32 addr, enum trtcm_param_type param,
+				    u32 *val_low, u32 *val_high)
+{
+	u32 idx = QDMA_METER_IDX(queue_id), group = QDMA_METER_GROUP(queue_id);
+	u32 val, config = FIELD_PREP(RATE_LIMIT_PARAM_TYPE_MASK, param) |
+			  FIELD_PREP(RATE_LIMIT_METER_GROUP_MASK, group) |
+			  FIELD_PREP(RATE_LIMIT_PARAM_INDEX_MASK, idx);
+
+	airoha_qdma_wr(qdma, REG_TRTCM_CFG_PARAM(addr), config);
+	if (read_poll_timeout(airoha_qdma_rr, val,
+			      val & RATE_LIMIT_PARAM_RW_DONE_MASK,
+			      USEC_PER_MSEC, 10 * USEC_PER_MSEC, true, qdma,
+			      REG_TRTCM_CFG_PARAM(addr)))
+		return -ETIMEDOUT;
+
+	*val_low = airoha_qdma_rr(qdma, REG_TRTCM_DATA_LOW(addr));
+	if (val_high)
+		*val_high = airoha_qdma_rr(qdma, REG_TRTCM_DATA_HIGH(addr));
+
+	return 0;
+}
+
+static int airoha_qdma_set_rl_param(struct airoha_qdma *qdma, int queue_id,
+				    u32 addr, enum trtcm_param_type param,
+				    u32 val)
+{
+	u32 idx = QDMA_METER_IDX(queue_id), group = QDMA_METER_GROUP(queue_id);
+	u32 config = RATE_LIMIT_PARAM_RW_MASK |
+		     FIELD_PREP(RATE_LIMIT_PARAM_TYPE_MASK, param) |
+		     FIELD_PREP(RATE_LIMIT_METER_GROUP_MASK, group) |
+		     FIELD_PREP(RATE_LIMIT_PARAM_INDEX_MASK, idx);
+
+	airoha_qdma_wr(qdma, REG_TRTCM_DATA_LOW(addr), val);
+	airoha_qdma_wr(qdma, REG_TRTCM_CFG_PARAM(addr), config);
+
+	return read_poll_timeout(airoha_qdma_rr, val,
+				 val & RATE_LIMIT_PARAM_RW_DONE_MASK,
+				 USEC_PER_MSEC, 10 * USEC_PER_MSEC, true,
+				 qdma, REG_TRTCM_CFG_PARAM(addr));
+}
+
+static int airoha_qdma_set_rl_config(struct airoha_qdma *qdma, int queue_id,
+				     u32 addr, bool enable, u32 enable_mask)
+{
+	u32 val;
+	int err;
+
+	err = airoha_qdma_get_rl_param(qdma, queue_id, addr, TRTCM_MISC_MODE,
+				       &val, NULL);
+	if (err)
+		return err;
+
+	val = enable ? val | enable_mask : val & ~enable_mask;
+
+	return airoha_qdma_set_rl_param(qdma, queue_id, addr, TRTCM_MISC_MODE,
+					val);
+}
+
+static int airoha_qdma_set_rl_token_bucket(struct airoha_qdma *qdma,
+					   int queue_id, u32 rate_val,
+					   u32 bucket_size)
+{
+	u32 val, config, tick, unit, rate, rate_frac;
+	int err;
+
+	err = airoha_qdma_get_rl_param(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+				       TRTCM_MISC_MODE, &config, NULL);
+	if (err)
+		return err;
+
+	val = airoha_qdma_rr(qdma, REG_INGRESS_TRTCM_CFG);
+	tick = FIELD_GET(INGRESS_FAST_TICK_MASK, val);
+	if (config & TRTCM_TICK_SEL)
+		tick *= FIELD_GET(INGRESS_SLOW_TICK_RATIO_MASK, val);
+	if (!tick)
+		return -EINVAL;
+
+	unit = (config & TRTCM_PKT_MODE) ? 1000000 / tick : 8000 / tick;
+	if (!unit)
+		return -EINVAL;
+
+	rate = rate_val / unit;
+	rate_frac = rate_val % unit;
+	rate_frac = FIELD_PREP(TRTCM_TOKEN_RATE_MASK, rate_frac) / unit;
+	rate = FIELD_PREP(TRTCM_TOKEN_RATE_MASK, rate) |
+	       FIELD_PREP(TRTCM_TOKEN_RATE_FRACTION_MASK, rate_frac);
+
+	err = airoha_qdma_set_rl_param(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+				       TRTCM_TOKEN_RATE_MODE, rate);
+	if (err)
+		return err;
+
+	val = bucket_size;
+	if (!(config & TRTCM_PKT_MODE))
+		val = max_t(u32, val, MIN_TOKEN_SIZE);
+	val = min_t(u32, __fls(val), MAX_TOKEN_SIZE_OFFSET);
+
+	return airoha_qdma_set_rl_param(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+					TRTCM_BUCKETSIZE_SHIFT_MODE, val);
+}
+
+static int airoha_qdma_init_rl_config(struct airoha_qdma *qdma, int queue_id,
+				      bool enable, enum trtcm_unit_type unit)
+{
+	bool tick_sel = queue_id == 0 || queue_id == 2 || queue_id == 8;
+	enum trtcm_param mode = TRTCM_METER_MODE;
+	int err;
+
+	mode |= unit == TRTCM_PACKET_UNIT ? TRTCM_PKT_MODE : 0;
+	err = airoha_qdma_set_rl_config(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+					enable, mode);
+	if (err)
+		return err;
+
+	return airoha_qdma_set_rl_config(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+					 tick_sel, TRTCM_TICK_SEL);
+}
+
+static int airoha_qdma_get_trtcm_param(struct airoha_qdma *qdma, int channel,
+				       u32 addr, enum trtcm_param_type param,
+				       enum trtcm_mode_type mode,
+				       u32 *val_low, u32 *val_high)
+{
+	u32 idx = QDMA_METER_IDX(channel), group = QDMA_METER_GROUP(channel);
+	u32 val, config = FIELD_PREP(TRTCM_PARAM_TYPE_MASK, param) |
+			  FIELD_PREP(TRTCM_METER_GROUP_MASK, group) |
+			  FIELD_PREP(TRTCM_PARAM_INDEX_MASK, idx) |
+			  FIELD_PREP(TRTCM_PARAM_RATE_TYPE_MASK, mode);
+
+	airoha_qdma_wr(qdma, REG_TRTCM_CFG_PARAM(addr), config);
+	if (read_poll_timeout(airoha_qdma_rr, val,
+			      val & TRTCM_PARAM_RW_DONE_MASK,
+			      USEC_PER_MSEC, 10 * USEC_PER_MSEC, true,
+			      qdma, REG_TRTCM_CFG_PARAM(addr)))
+		return -ETIMEDOUT;
+
+	*val_low = airoha_qdma_rr(qdma, REG_TRTCM_DATA_LOW(addr));
+	if (val_high)
+		*val_high = airoha_qdma_rr(qdma, REG_TRTCM_DATA_HIGH(addr));
+
+	return 0;
+}
+
+static int airoha_qdma_set_trtcm_param(struct airoha_qdma *qdma, int channel,
+				       u32 addr, enum trtcm_param_type param,
+				       enum trtcm_mode_type mode, u32 val)
+{
+	u32 idx = QDMA_METER_IDX(channel), group = QDMA_METER_GROUP(channel);
+	u32 config = TRTCM_PARAM_RW_MASK |
+		     FIELD_PREP(TRTCM_PARAM_TYPE_MASK, param) |
+		     FIELD_PREP(TRTCM_METER_GROUP_MASK, group) |
+		     FIELD_PREP(TRTCM_PARAM_INDEX_MASK, idx) |
+		     FIELD_PREP(TRTCM_PARAM_RATE_TYPE_MASK, mode);
+
+	airoha_qdma_wr(qdma, REG_TRTCM_DATA_LOW(addr), val);
+	airoha_qdma_wr(qdma, REG_TRTCM_CFG_PARAM(addr), config);
+
+	return read_poll_timeout(airoha_qdma_rr, val,
+				 val & TRTCM_PARAM_RW_DONE_MASK,
+				 USEC_PER_MSEC, 10 * USEC_PER_MSEC, true,
+				 qdma, REG_TRTCM_CFG_PARAM(addr));
+}
+
+static int airoha_qdma_set_trtcm_config(struct airoha_qdma *qdma, int channel,
+					u32 addr, enum trtcm_mode_type mode,
+					bool enable, u32 enable_mask)
+{
+	u32 val;
+
+	if (airoha_qdma_get_trtcm_param(qdma, channel, addr, TRTCM_MISC_MODE,
+					mode, &val, NULL))
+		return -EINVAL;
+
+	val = enable ? val | enable_mask : val & ~enable_mask;
+
+	return airoha_qdma_set_trtcm_param(qdma, channel, addr, TRTCM_MISC_MODE,
+					   mode, val);
+}
+
+static int airoha_qdma_set_trtcm_token_bucket(struct airoha_qdma *qdma,
+					      int channel, u32 addr,
+					      enum trtcm_mode_type mode,
+					      u32 rate_val, u32 bucket_size)
+{
+	u32 val, config, tick, unit, rate, rate_frac;
+	int err;
+
+	if (airoha_qdma_get_trtcm_param(qdma, channel, addr, TRTCM_MISC_MODE,
+					mode, &config, NULL))
+		return -EINVAL;
+
+	val = airoha_qdma_rr(qdma, addr);
+	tick = FIELD_GET(INGRESS_FAST_TICK_MASK, val);
+	if (config & TRTCM_TICK_SEL)
+		tick *= FIELD_GET(INGRESS_SLOW_TICK_RATIO_MASK, val);
+	if (!tick)
+		return -EINVAL;
+
+	unit = (config & TRTCM_PKT_MODE) ? 1000000 / tick : 8000 / tick;
+	if (!unit)
+		return -EINVAL;
+
+	rate = rate_val / unit;
+	rate_frac = rate_val % unit;
+	rate_frac = FIELD_PREP(TRTCM_TOKEN_RATE_MASK, rate_frac) / unit;
+	rate = FIELD_PREP(TRTCM_TOKEN_RATE_MASK, rate) |
+	       FIELD_PREP(TRTCM_TOKEN_RATE_FRACTION_MASK, rate_frac);
+
+	err = airoha_qdma_set_trtcm_param(qdma, channel, addr,
+					  TRTCM_TOKEN_RATE_MODE, mode, rate);
+	if (err)
+		return err;
+
+	val = max_t(u32, bucket_size, MIN_TOKEN_SIZE);
+	val = min_t(u32, __fls(val), MAX_TOKEN_SIZE_OFFSET);
+
+	return airoha_qdma_set_trtcm_param(qdma, channel, addr,
+					   TRTCM_BUCKETSIZE_SHIFT_MODE,
+					   mode, val);
+}
+
+static int airoha_qdma_set_tx_rate_limit(struct airoha_gdm_port *port,
+					 int channel, u32 rate,
+					 u32 bucket_size)
+{
+	int i, err;
+
+	for (i = 0; i <= TRTCM_PEAK_MODE; i++) {
+		err = airoha_qdma_set_trtcm_config(port->qdma, channel,
+						   REG_EGRESS_TRTCM_CFG, i,
+						   !!rate, TRTCM_METER_MODE);
+		if (err)
+			return err;
+
+		err = airoha_qdma_set_trtcm_token_bucket(port->qdma, channel,
+							 REG_EGRESS_TRTCM_CFG,
+							 i, rate, bucket_size);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int airoha_tc_htb_alloc_leaf_queue(struct airoha_gdm_port *port,
+					  struct tc_htb_qopt_offload *opt)
+{
+	u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
+	u32 rate = div_u64(opt->rate, 1000) << 3; /* kbps */
+	struct net_device *dev = port->dev;
+	int num_tx_queues = dev->real_num_tx_queues;
+	int err;
+
+	if (opt->parent_classid != TC_HTB_CLASSID_ROOT) {
+		NL_SET_ERR_MSG_MOD(opt->extack, "invalid parent classid");
+		return -EINVAL;
+	}
+
+	err = airoha_qdma_set_tx_rate_limit(port, channel, rate, opt->quantum);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(opt->extack,
+				   "failed configuring htb offload");
+		return err;
+	}
+
+	if (opt->command == TC_HTB_NODE_MODIFY)
+		return 0;
+
+	err = netif_set_real_num_tx_queues(dev, num_tx_queues + 1);
+	if (err) {
+		airoha_qdma_set_tx_rate_limit(port, channel, 0, opt->quantum);
+		NL_SET_ERR_MSG_MOD(opt->extack,
+				   "failed setting real_num_tx_queues");
+		return err;
+	}
+
+	set_bit(channel, port->qos_sq_bmap);
+	opt->qid = AIROHA_NUM_TX_RING + channel;
+
+	return 0;
+}
+
+static int airoha_qdma_set_rx_meter(struct airoha_gdm_port *port,
+				    u32 rate, u32 bucket_size,
+				    enum trtcm_unit_type unit_type)
+{
+	struct airoha_qdma *qdma = port->qdma;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
+		int err;
+
+		if (!qdma->q_rx[i].ndesc)
+			continue;
+
+		err = airoha_qdma_init_rl_config(qdma, i, !!rate, unit_type);
+		if (err)
+			return err;
+
+		err = airoha_qdma_set_rl_token_bucket(qdma, i, rate,
+						      bucket_size);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int airoha_tc_matchall_act_validate(struct tc_cls_matchall_offload *f)
+{
+	const struct flow_action *actions = &f->rule->action;
+	const struct flow_action_entry *act;
+
+	if (!flow_action_has_entries(actions)) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "filter run with no actions");
+		return -EINVAL;
+	}
+
+	if (!flow_offload_has_one_action(actions)) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "only once action per filter is supported");
+		return -EOPNOTSUPP;
+	}
+
+	act = &actions->entries[0];
+	if (act->id != FLOW_ACTION_POLICE) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "unsupported action");
+		return -EOPNOTSUPP;
+	}
+
+	if (act->police.exceed.act_id != FLOW_ACTION_DROP) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "invalid exceed action id");
+		return -EOPNOTSUPP;
+	}
+
+	if (act->police.notexceed.act_id != FLOW_ACTION_ACCEPT) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "invalid notexceed action id");
+		return -EOPNOTSUPP;
+	}
+
+	if (act->police.notexceed.act_id == FLOW_ACTION_ACCEPT &&
+	    !flow_action_is_last_entry(actions, act)) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "action accept must be last");
+		return -EOPNOTSUPP;
+	}
+
+	if (act->police.peakrate_bytes_ps || act->police.avrate ||
+	    act->police.overhead || act->police.mtu) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "peakrate/avrate/overhead/mtu unsupported");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int airoha_dev_tc_matchall(struct net_device *dev,
+				  struct tc_cls_matchall_offload *f)
+{
+	enum trtcm_unit_type unit_type = TRTCM_BYTE_UNIT;
+	struct airoha_gdm_port *port = netdev_priv(dev);
+	u32 rate = 0, bucket_size = 0;
+
+	switch (f->command) {
+	case TC_CLSMATCHALL_REPLACE: {
+		const struct flow_action_entry *act;
+		int err;
+
+		err = airoha_tc_matchall_act_validate(f);
+		if (err)
+			return err;
+
+		act = &f->rule->action.entries[0];
+		if (act->police.rate_pkt_ps) {
+			rate = act->police.rate_pkt_ps;
+			bucket_size = act->police.burst_pkt;
+			unit_type = TRTCM_PACKET_UNIT;
+		} else {
+			rate = div_u64(act->police.rate_bytes_ps, 1000);
+			rate = rate << 3; /* Kbps */
+			bucket_size = act->police.burst;
+		}
+		fallthrough;
+	}
+	case TC_CLSMATCHALL_DESTROY:
+		return airoha_qdma_set_rx_meter(port, rate, bucket_size,
+						unit_type);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int airoha_dev_setup_tc_block_cb(enum tc_setup_type type,
+					void *type_data, void *cb_priv)
+{
+	struct net_device *dev = cb_priv;
+	struct airoha_gdm_port *port = netdev_priv(dev);
+	struct airoha_eth *eth = port->qdma->eth;
+
+	if (!tc_can_offload(dev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return airoha_ppe_setup_tc_block_cb(&eth->ppe->dev, type_data);
+	case TC_SETUP_CLSMATCHALL:
+		return airoha_dev_tc_matchall(dev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int airoha_dev_setup_tc_block(struct airoha_gdm_port *port,
+				     struct flow_block_offload *f)
+{
+	flow_setup_cb_t *cb = airoha_dev_setup_tc_block_cb;
+	static LIST_HEAD(block_cb_list);
+	struct flow_block_cb *block_cb;
+
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	f->driver_block_list = &block_cb_list;
+	switch (f->command) {
+	case FLOW_BLOCK_BIND:
+		block_cb = flow_block_cb_lookup(f->block, cb, port->dev);
+		if (block_cb) {
+			flow_block_cb_incref(block_cb);
+			return 0;
+		}
+		block_cb = flow_block_cb_alloc(cb, port->dev, port->dev, NULL);
+		if (IS_ERR(block_cb))
+			return PTR_ERR(block_cb);
+
+		flow_block_cb_incref(block_cb);
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &block_cb_list);
+		return 0;
+	case FLOW_BLOCK_UNBIND:
+		block_cb = flow_block_cb_lookup(f->block, cb, port->dev);
+		if (!block_cb)
+			return -ENOENT;
+
+		if (!flow_block_cb_decref(block_cb)) {
+			flow_block_cb_remove(block_cb, f);
+			list_del(&block_cb->driver_list);
+		}
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void airoha_tc_remove_htb_queue(struct airoha_gdm_port *port, int queue)
+{
+	struct net_device *dev = port->dev;
+
+	netif_set_real_num_tx_queues(dev, dev->real_num_tx_queues - 1);
+	airoha_qdma_set_tx_rate_limit(port, queue + 1, 0, 0);
+	clear_bit(queue, port->qos_sq_bmap);
+}
+
+static int airoha_tc_htb_delete_leaf_queue(struct airoha_gdm_port *port,
+					   struct tc_htb_qopt_offload *opt)
+{
+	u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
+
+	if (!test_bit(channel, port->qos_sq_bmap)) {
+		NL_SET_ERR_MSG_MOD(opt->extack, "invalid queue id");
+		return -EINVAL;
+	}
+
+	airoha_tc_remove_htb_queue(port, channel);
+
+	return 0;
+}
+
+static int airoha_tc_htb_destroy(struct airoha_gdm_port *port)
+{
+	int q;
+
+	for_each_set_bit(q, port->qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS)
+		airoha_tc_remove_htb_queue(port, q);
+
+	return 0;
+}
+
+static int airoha_tc_get_htb_get_leaf_queue(struct airoha_gdm_port *port,
+					    struct tc_htb_qopt_offload *opt)
+{
+	u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
+
+	if (!test_bit(channel, port->qos_sq_bmap)) {
+		NL_SET_ERR_MSG_MOD(opt->extack, "invalid queue id");
+		return -EINVAL;
+	}
+
+	opt->qid = AIROHA_NUM_TX_RING + channel;
+
+	return 0;
+}
+
+static int airoha_tc_setup_qdisc_htb(struct airoha_gdm_port *port,
+				     struct tc_htb_qopt_offload *opt)
+{
+	switch (opt->command) {
+	case TC_HTB_CREATE:
+		break;
+	case TC_HTB_DESTROY:
+		return airoha_tc_htb_destroy(port);
+	case TC_HTB_NODE_MODIFY:
+	case TC_HTB_LEAF_ALLOC_QUEUE:
+		return airoha_tc_htb_alloc_leaf_queue(port, opt);
+	case TC_HTB_LEAF_DEL:
+	case TC_HTB_LEAF_DEL_LAST:
+	case TC_HTB_LEAF_DEL_LAST_FORCE:
+		return airoha_tc_htb_delete_leaf_queue(port, opt);
+	case TC_HTB_LEAF_QUERY_QUEUE:
+		return airoha_tc_get_htb_get_leaf_queue(port, opt);
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int airoha_dev_tc_setup(struct net_device *dev, enum tc_setup_type type,
+			       void *type_data)
+{
+	struct airoha_gdm_port *port = netdev_priv(dev);
+
+	switch (type) {
+	case TC_SETUP_QDISC_ETS:
+		return airoha_tc_setup_qdisc_ets(port, type_data);
+	case TC_SETUP_QDISC_HTB:
+		return airoha_tc_setup_qdisc_htb(port, type_data);
+	case TC_SETUP_BLOCK:
+	case TC_SETUP_FT:
+		return airoha_dev_setup_tc_block(port, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct net_device_ops airoha_netdev_ops = {
 	.ndo_init		= airoha_dev_init,
 	.ndo_open		= airoha_dev_open,
 	.ndo_stop		= airoha_dev_stop,
+	.ndo_change_mtu		= airoha_dev_change_mtu,
+	.ndo_select_queue	= airoha_dev_select_queue,
 	.ndo_start_xmit		= airoha_dev_xmit,
 	.ndo_get_stats64        = airoha_dev_get_stats64,
 	.ndo_set_mac_address	= airoha_dev_set_macaddr,
+	.ndo_setup_tc		= airoha_dev_tc_setup,
 };
 
 static const struct ethtool_ops airoha_ethtool_ops = {
 	.get_drvinfo		= airoha_ethtool_get_drvinfo,
 	.get_eth_mac_stats      = airoha_ethtool_get_mac_stats,
 	.get_rmon_stats		= airoha_ethtool_get_rmon_stats,
+	.get_link		= ethtool_op_get_link,
 };
 
-static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
+static int airoha_metadata_dst_alloc(struct airoha_gdm_port *port)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(port->dsa_meta); i++) {
+		struct metadata_dst *md_dst;
+
+		md_dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
+					    GFP_KERNEL);
+		if (!md_dst)
+			return -ENOMEM;
+
+		md_dst->u.port_info.port_id = i;
+		port->dsa_meta[i] = md_dst;
+	}
+
+	return 0;
+}
+
+static void airoha_metadata_dst_free(struct airoha_gdm_port *port)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(port->dsa_meta); i++) {
+		if (!port->dsa_meta[i])
+			continue;
+
+		metadata_dst_free(port->dsa_meta[i]);
+	}
+}
+
+bool airoha_is_valid_gdm_port(struct airoha_eth *eth,
+			      struct airoha_gdm_port *port)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
+		if (eth->ports[i] == port)
+			return true;
+	}
+
+	return false;
+}
+
+static int airoha_alloc_gdm_port(struct airoha_eth *eth,
+				 struct device_node *np, int index)
 {
 	const __be32 *id_ptr = of_get_property(np, "reg", NULL);
 	struct airoha_gdm_port *port;
 	struct airoha_qdma *qdma;
 	struct net_device *dev;
-	int err, index;
+	int err, p;
 	u32 id;
 
 	if (!id_ptr) {
@@ -2639,20 +2866,21 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 	}
 
 	id = be32_to_cpup(id_ptr);
-	index = id - 1;
+	p = id - 1;
 
 	if (!id || id > ARRAY_SIZE(eth->ports)) {
 		dev_err(eth->dev, "invalid gdm port id: %d\n", id);
 		return -EINVAL;
 	}
 
-	if (eth->ports[index]) {
+	if (eth->ports[p]) {
 		dev_err(eth->dev, "duplicate gdm port id: %d\n", id);
 		return -EINVAL;
 	}
 
 	dev = devm_alloc_etherdev_mqs(eth->dev, sizeof(*port),
-				      AIROHA_NUM_TX_RING, AIROHA_NUM_RX_RING);
+				      AIROHA_NUM_NETDEV_TX_RINGS,
+				      AIROHA_NUM_RX_RING);
 	if (!dev) {
 		dev_err(eth->dev, "alloc_etherdev failed\n");
 		return -ENOMEM;
@@ -2665,12 +2893,19 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 	dev->watchdog_timeo = 5 * HZ;
 	dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 			   NETIF_F_TSO6 | NETIF_F_IPV6_CSUM |
-			   NETIF_F_SG | NETIF_F_TSO;
+			   NETIF_F_SG | NETIF_F_TSO |
+			   NETIF_F_HW_TC;
 	dev->features |= dev->hw_features;
+	dev->vlan_features = dev->hw_features;
 	dev->dev.of_node = np;
-	dev->irq = qdma->irq;
+	dev->irq = qdma->irq_banks[0].irq;
 	SET_NETDEV_DEV(dev, eth->dev);
 
+	/* reserve hw queues for HTB offloading */
+	err = netif_set_real_num_tx_queues(dev, AIROHA_NUM_TX_RING);
+	if (err)
+		return err;
+
 	err = of_get_ethdev_address(np, dev);
 	if (err) {
 		if (err == -EPROBE_DEFER)
@@ -2687,13 +2922,26 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 	port->qdma = qdma;
 	port->dev = dev;
 	port->id = id;
-	eth->ports[index] = port;
+	eth->ports[p] = port;
 
-	return register_netdev(dev);
+	err = airoha_metadata_dst_alloc(port);
+	if (err)
+		return err;
+
+	err = register_netdev(dev);
+	if (err)
+		goto free_metadata_dst;
+
+	return 0;
+
+free_metadata_dst:
+	airoha_metadata_dst_free(port);
+	return err;
 }
 
 static int airoha_probe(struct platform_device *pdev)
 {
+	struct reset_control_bulk_data *xsi_rsts;
 	struct device_node *np;
 	struct airoha_eth *eth;
 	int i, err;
@@ -2702,6 +2950,10 @@ static int airoha_probe(struct platform_device *pdev)
 	if (!eth)
 		return -ENOMEM;
 
+	eth->soc = of_device_get_match_data(&pdev->dev);
+	if (!eth->soc)
+		return -EINVAL;
+
 	eth->dev = &pdev->dev;
 
 	err = dma_set_mask_and_coherent(eth->dev, DMA_BIT_MASK(32));
@@ -2726,13 +2978,18 @@ static int airoha_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	eth->xsi_rsts[0].id = "xsi-mac";
-	eth->xsi_rsts[1].id = "hsi0-mac";
-	eth->xsi_rsts[2].id = "hsi1-mac";
-	eth->xsi_rsts[3].id = "hsi-mac";
-	eth->xsi_rsts[4].id = "xfp-mac";
+	xsi_rsts = devm_kcalloc(eth->dev,
+				eth->soc->num_xsi_rsts, sizeof(*xsi_rsts),
+				GFP_KERNEL);
+	if (!xsi_rsts)
+		return -ENOMEM;
+
+	eth->xsi_rsts = xsi_rsts;
+	for (i = 0; i < eth->soc->num_xsi_rsts; i++)
+		eth->xsi_rsts[i].id = eth->soc->xsi_rsts_names[i];
+
 	err = devm_reset_control_bulk_get_exclusive(eth->dev,
-						    ARRAY_SIZE(eth->xsi_rsts),
+						    eth->soc->num_xsi_rsts,
 						    eth->xsi_rsts);
 	if (err) {
 		dev_err(eth->dev, "failed to get bulk xsi reset lines\n");
@@ -2755,6 +3012,7 @@ static int airoha_probe(struct platform_device *pdev)
 	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
 		airoha_qdma_start_napi(&eth->qdma[i]);
 
+	i = 0;
 	for_each_child_of_node(pdev->dev.of_node, np) {
 		if (!of_device_is_compatible(np, "airoha,eth-mac"))
 			continue;
@@ -2762,7 +3020,7 @@ static int airoha_probe(struct platform_device *pdev)
 		if (!of_device_is_available(np))
 			continue;
 
-		err = airoha_alloc_gdm_port(eth, np);
+		err = airoha_alloc_gdm_port(eth, np, i++);
 		if (err) {
 			of_node_put(np);
 			goto error_napi_stop;
@@ -2774,6 +3032,7 @@ static int airoha_probe(struct platform_device *pdev)
 error_napi_stop:
 	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
 		airoha_qdma_stop_napi(&eth->qdma[i]);
+	airoha_ppe_deinit(eth);
 error_hw_cleanup:
 	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
 		airoha_hw_cleanup(&eth->qdma[i]);
@@ -2781,8 +3040,10 @@ error_hw_cleanup:
 	for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
 		struct airoha_gdm_port *port = eth->ports[i];
 
-		if (port && port->dev->reg_state == NETREG_REGISTERED)
+		if (port && port->dev->reg_state == NETREG_REGISTERED) {
 			unregister_netdev(port->dev);
+			airoha_metadata_dst_free(port);
+		}
 	}
 	free_netdev(eth->napi_dev);
 	platform_set_drvdata(pdev, NULL);
@@ -2808,14 +3069,98 @@ static void airoha_remove(struct platform_device *pdev)
 
 		airoha_dev_stop(port->dev);
 		unregister_netdev(port->dev);
+		airoha_metadata_dst_free(port);
 	}
 	free_netdev(eth->napi_dev);
 
+	airoha_ppe_deinit(eth);
 	platform_set_drvdata(pdev, NULL);
 }
 
+static const char * const en7581_xsi_rsts_names[] = {
+	"xsi-mac",
+	"hsi0-mac",
+	"hsi1-mac",
+	"hsi-mac",
+	"xfp-mac",
+};
+
+static int airoha_en7581_get_src_port_id(struct airoha_gdm_port *port, int nbq)
+{
+	switch (port->id) {
+	case 3:
+		/* 7581 SoC supports PCIe serdes on GDM3 port */
+		if (nbq == 4)
+			return HSGMII_LAN_7581_PCIE0_SRCPORT;
+		if (nbq == 5)
+			return HSGMII_LAN_7581_PCIE1_SRCPORT;
+		break;
+	case 4:
+		/* 7581 SoC supports eth and usb serdes on GDM4 port */
+		if (!nbq)
+			return HSGMII_LAN_7581_ETH_SRCPORT;
+		if (nbq == 1)
+			return HSGMII_LAN_7581_USB_SRCPORT;
+		break;
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const char * const an7583_xsi_rsts_names[] = {
+	"xsi-mac",
+	"hsi0-mac",
+	"hsi1-mac",
+	"xfp-mac",
+};
+
+static int airoha_an7583_get_src_port_id(struct airoha_gdm_port *port, int nbq)
+{
+	switch (port->id) {
+	case 3:
+		/* 7583 SoC supports eth serdes on GDM3 port */
+		if (!nbq)
+			return HSGMII_LAN_7583_ETH_SRCPORT;
+		break;
+	case 4:
+		/* 7583 SoC supports PCIe and USB serdes on GDM4 port */
+		if (!nbq)
+			return HSGMII_LAN_7583_PCIE_SRCPORT;
+		if (nbq == 1)
+			return HSGMII_LAN_7583_USB_SRCPORT;
+		break;
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const struct airoha_eth_soc_data en7581_soc_data = {
+	.version = 0x7581,
+	.xsi_rsts_names = en7581_xsi_rsts_names,
+	.num_xsi_rsts = ARRAY_SIZE(en7581_xsi_rsts_names),
+	.num_ppe = 2,
+	.ops = {
+		.get_src_port_id = airoha_en7581_get_src_port_id,
+	},
+};
+
+static const struct airoha_eth_soc_data an7583_soc_data = {
+	.version = 0x7583,
+	.xsi_rsts_names = an7583_xsi_rsts_names,
+	.num_xsi_rsts = ARRAY_SIZE(an7583_xsi_rsts_names),
+	.num_ppe = 1,
+	.ops = {
+		.get_src_port_id = airoha_an7583_get_src_port_id,
+	},
+};
+
 static const struct of_device_id of_airoha_match[] = {
-	{ .compatible = "airoha,en7581-eth" },
+	{ .compatible = "airoha,en7581-eth", .data = &en7581_soc_data },
+	{ .compatible = "airoha,an7583-eth", .data = &an7583_soc_data },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, of_airoha_match);
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
new file mode 100644
index 000000000000..fbbc58133364
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -0,0 +1,673 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#ifndef AIROHA_ETH_H
+#define AIROHA_ETH_H
+
+#include <linux/debugfs.h>
+#include <linux/etherdevice.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/reset.h>
+#include <linux/soc/airoha/airoha_offload.h>
+#include <net/dsa.h>
+
+#define AIROHA_MAX_NUM_GDM_PORTS	4
+#define AIROHA_MAX_NUM_QDMA		2
+#define AIROHA_MAX_NUM_IRQ_BANKS	4
+#define AIROHA_MAX_DSA_PORTS		7
+#define AIROHA_MAX_NUM_RSTS		3
+#define AIROHA_MAX_MTU			9216
+#define AIROHA_MAX_PACKET_SIZE		2048
+#define AIROHA_NUM_QOS_CHANNELS		4
+#define AIROHA_NUM_QOS_QUEUES		8
+#define AIROHA_NUM_TX_RING		32
+#define AIROHA_NUM_RX_RING		32
+#define AIROHA_NUM_NETDEV_TX_RINGS	(AIROHA_NUM_TX_RING + \
+					 AIROHA_NUM_QOS_CHANNELS)
+#define AIROHA_FE_MC_MAX_VLAN_TABLE	64
+#define AIROHA_FE_MC_MAX_VLAN_PORT	16
+#define AIROHA_NUM_TX_IRQ		2
+#define HW_DSCP_NUM			2048
+#define IRQ_QUEUE_LEN(_n)		((_n) ? 1024 : 2048)
+#define TX_DSCP_NUM			1024
+#define RX_DSCP_NUM(_n)			\
+	((_n) ==  2 ? 128 :		\
+	 (_n) == 11 ? 128 :		\
+	 (_n) == 15 ? 128 :		\
+	 (_n) ==  0 ? 1024 : 16)
+
+#define PSE_RSV_PAGES			128
+#define PSE_QUEUE_RSV_PAGES		64
+
+#define QDMA_METER_IDX(_n)		((_n) & 0xff)
+#define QDMA_METER_GROUP(_n)		(((_n) >> 8) & 0x3)
+
+#define PPE_SRAM_NUM_ENTRIES		(8 * 1024)
+#define PPE_STATS_NUM_ENTRIES		(4 * 1024)
+#define PPE_DRAM_NUM_ENTRIES		(16 * 1024)
+#define PPE_ENTRY_SIZE			80
+#define PPE_RAM_NUM_ENTRIES_SHIFT(_n)	(__ffs((_n) >> 10))
+
+#define MTK_HDR_LEN			4
+#define MTK_HDR_XMIT_TAGGED_TPID_8100	1
+#define MTK_HDR_XMIT_TAGGED_TPID_88A8	2
+
+enum {
+	QDMA_INT_REG_IDX0,
+	QDMA_INT_REG_IDX1,
+	QDMA_INT_REG_IDX2,
+	QDMA_INT_REG_IDX3,
+	QDMA_INT_REG_IDX4,
+	QDMA_INT_REG_MAX
+};
+
+enum {
+	HSGMII_LAN_7581_PCIE0_SRCPORT	= 0x16,
+	HSGMII_LAN_7581_PCIE1_SRCPORT,
+	HSGMII_LAN_7581_ETH_SRCPORT,
+	HSGMII_LAN_7581_USB_SRCPORT,
+};
+
+enum {
+	HSGMII_LAN_7583_ETH_SRCPORT	= 0x16,
+	HSGMII_LAN_7583_PCIE_SRCPORT	= 0x18,
+	HSGMII_LAN_7583_USB_SRCPORT,
+};
+
+enum {
+	XSI_PCIE0_VIP_PORT_MASK	= BIT(22),
+	XSI_PCIE1_VIP_PORT_MASK	= BIT(23),
+	XSI_USB_VIP_PORT_MASK	= BIT(25),
+	XSI_ETH_VIP_PORT_MASK	= BIT(24),
+};
+
+enum {
+	DEV_STATE_INITIALIZED,
+};
+
+enum {
+	CDM_CRSN_QSEL_Q1 = 1,
+	CDM_CRSN_QSEL_Q5 = 5,
+	CDM_CRSN_QSEL_Q6 = 6,
+	CDM_CRSN_QSEL_Q15 = 15,
+};
+
+enum {
+	CRSN_08 = 0x8,
+	CRSN_21 = 0x15, /* KA */
+	CRSN_22 = 0x16, /* hit bind and force route to CPU */
+	CRSN_24 = 0x18,
+	CRSN_25 = 0x19,
+};
+
+enum airoha_gdm_index {
+	AIROHA_GDM1_IDX = 1,
+	AIROHA_GDM2_IDX = 2,
+	AIROHA_GDM3_IDX = 3,
+	AIROHA_GDM4_IDX = 4,
+};
+
+enum {
+	FE_PSE_PORT_CDM1,
+	FE_PSE_PORT_GDM1,
+	FE_PSE_PORT_GDM2,
+	FE_PSE_PORT_GDM3,
+	FE_PSE_PORT_PPE1,
+	FE_PSE_PORT_CDM2,
+	FE_PSE_PORT_CDM3,
+	FE_PSE_PORT_CDM4,
+	FE_PSE_PORT_PPE2,
+	FE_PSE_PORT_GDM4,
+	FE_PSE_PORT_CDM5,
+	FE_PSE_PORT_DROP = 0xf,
+};
+
+enum tx_sched_mode {
+	TC_SCH_WRR8,
+	TC_SCH_SP,
+	TC_SCH_WRR7,
+	TC_SCH_WRR6,
+	TC_SCH_WRR5,
+	TC_SCH_WRR4,
+	TC_SCH_WRR3,
+	TC_SCH_WRR2,
+};
+
+enum trtcm_unit_type {
+	TRTCM_BYTE_UNIT,
+	TRTCM_PACKET_UNIT,
+};
+
+enum trtcm_param_type {
+	TRTCM_MISC_MODE, /* meter_en, pps_mode, tick_sel */
+	TRTCM_TOKEN_RATE_MODE,
+	TRTCM_BUCKETSIZE_SHIFT_MODE,
+	TRTCM_BUCKET_COUNTER_MODE,
+};
+
+enum trtcm_mode_type {
+	TRTCM_COMMIT_MODE,
+	TRTCM_PEAK_MODE,
+};
+
+enum trtcm_param {
+	TRTCM_TICK_SEL = BIT(0),
+	TRTCM_PKT_MODE = BIT(1),
+	TRTCM_METER_MODE = BIT(2),
+};
+
+#define MIN_TOKEN_SIZE				4096
+#define MAX_TOKEN_SIZE_OFFSET			17
+#define TRTCM_TOKEN_RATE_MASK			GENMASK(23, 6)
+#define TRTCM_TOKEN_RATE_FRACTION_MASK		GENMASK(5, 0)
+
+struct airoha_queue_entry {
+	union {
+		void *buf;
+		struct {
+			struct list_head list;
+			struct sk_buff *skb;
+		};
+	};
+	dma_addr_t dma_addr;
+	u16 dma_len;
+};
+
+struct airoha_queue {
+	struct airoha_qdma *qdma;
+
+	/* protect concurrent queue accesses */
+	spinlock_t lock;
+	struct airoha_queue_entry *entry;
+	struct airoha_qdma_desc *desc;
+	u16 head;
+	u16 tail;
+
+	int queued;
+	int ndesc;
+	int free_thr;
+	int buf_size;
+
+	struct napi_struct napi;
+	struct page_pool *page_pool;
+	struct sk_buff *skb;
+
+	struct list_head tx_list;
+};
+
+struct airoha_tx_irq_queue {
+	struct airoha_qdma *qdma;
+
+	struct napi_struct napi;
+
+	int size;
+	u32 *q;
+};
+
+struct airoha_hw_stats {
+	/* protect concurrent hw_stats accesses */
+	spinlock_t lock;
+	struct u64_stats_sync syncp;
+
+	/* get_stats64 */
+	u64 rx_ok_pkts;
+	u64 tx_ok_pkts;
+	u64 rx_ok_bytes;
+	u64 tx_ok_bytes;
+	u64 rx_multicast;
+	u64 rx_errors;
+	u64 rx_drops;
+	u64 tx_drops;
+	u64 rx_crc_error;
+	u64 rx_over_errors;
+	/* ethtool stats */
+	u64 tx_broadcast;
+	u64 tx_multicast;
+	u64 tx_len[7];
+	u64 rx_broadcast;
+	u64 rx_fragment;
+	u64 rx_jabber;
+	u64 rx_len[7];
+};
+
+enum {
+	AIROHA_FOE_STATE_INVALID,
+	AIROHA_FOE_STATE_UNBIND,
+	AIROHA_FOE_STATE_BIND,
+	AIROHA_FOE_STATE_FIN
+};
+
+enum {
+	PPE_PKT_TYPE_IPV4_HNAPT = 0,
+	PPE_PKT_TYPE_IPV4_ROUTE = 1,
+	PPE_PKT_TYPE_BRIDGE = 2,
+	PPE_PKT_TYPE_IPV4_DSLITE = 3,
+	PPE_PKT_TYPE_IPV6_ROUTE_3T = 4,
+	PPE_PKT_TYPE_IPV6_ROUTE_5T = 5,
+	PPE_PKT_TYPE_IPV6_6RD = 7,
+};
+
+#define AIROHA_FOE_MAC_SMAC_ID		GENMASK(20, 16)
+#define AIROHA_FOE_MAC_PPPOE_ID		GENMASK(15, 0)
+
+#define AIROHA_FOE_MAC_WDMA_QOS		GENMASK(15, 12)
+#define AIROHA_FOE_MAC_WDMA_BAND	BIT(11)
+#define AIROHA_FOE_MAC_WDMA_WCID	GENMASK(10, 0)
+
+struct airoha_foe_mac_info_common {
+	u16 vlan1;
+	u16 etype;
+
+	u32 dest_mac_hi;
+
+	u16 vlan2;
+	u16 dest_mac_lo;
+
+	u32 src_mac_hi;
+};
+
+struct airoha_foe_mac_info {
+	struct airoha_foe_mac_info_common common;
+
+	u16 pppoe_id;
+	u16 src_mac_lo;
+
+	u32 meter;
+};
+
+#define AIROHA_FOE_IB1_UNBIND_PREBIND		BIT(24)
+#define AIROHA_FOE_IB1_UNBIND_PACKETS		GENMASK(23, 8)
+#define AIROHA_FOE_IB1_UNBIND_TIMESTAMP		GENMASK(7, 0)
+
+#define AIROHA_FOE_IB1_BIND_STATIC		BIT(31)
+#define AIROHA_FOE_IB1_BIND_UDP			BIT(30)
+#define AIROHA_FOE_IB1_BIND_STATE		GENMASK(29, 28)
+#define AIROHA_FOE_IB1_BIND_PACKET_TYPE		GENMASK(27, 25)
+#define AIROHA_FOE_IB1_BIND_TTL			BIT(24)
+#define AIROHA_FOE_IB1_BIND_TUNNEL_DECAP	BIT(23)
+#define AIROHA_FOE_IB1_BIND_PPPOE		BIT(22)
+#define AIROHA_FOE_IB1_BIND_VPM			GENMASK(21, 20)
+#define AIROHA_FOE_IB1_BIND_VLAN_LAYER		GENMASK(19, 16)
+#define AIROHA_FOE_IB1_BIND_KEEPALIVE		BIT(15)
+#define AIROHA_FOE_IB1_BIND_TIMESTAMP		GENMASK(14, 0)
+
+#define AIROHA_FOE_IB2_DSCP			GENMASK(31, 24)
+#define AIROHA_FOE_IB2_PORT_AG			GENMASK(23, 13)
+#define AIROHA_FOE_IB2_PCP			BIT(12)
+#define AIROHA_FOE_IB2_MULTICAST		BIT(11)
+#define AIROHA_FOE_IB2_FAST_PATH		BIT(10)
+#define AIROHA_FOE_IB2_PSE_QOS			BIT(9)
+#define AIROHA_FOE_IB2_PSE_PORT			GENMASK(8, 5)
+#define AIROHA_FOE_IB2_NBQ			GENMASK(4, 0)
+
+#define AIROHA_FOE_ACTDP			GENMASK(31, 24)
+#define AIROHA_FOE_SHAPER_ID			GENMASK(23, 16)
+#define AIROHA_FOE_CHANNEL			GENMASK(15, 11)
+#define AIROHA_FOE_QID				GENMASK(10, 8)
+#define AIROHA_FOE_DPI				BIT(7)
+#define AIROHA_FOE_TUNNEL			BIT(6)
+#define AIROHA_FOE_TUNNEL_ID			GENMASK(5, 0)
+
+#define AIROHA_FOE_TUNNEL_MTU			GENMASK(31, 16)
+#define AIROHA_FOE_ACNT_GRP3			GENMASK(15, 9)
+#define AIROHA_FOE_METER_GRP3			GENMASK(8, 5)
+#define AIROHA_FOE_METER_GRP2			GENMASK(4, 0)
+
+struct airoha_foe_bridge {
+	u32 dest_mac_hi;
+
+	u16 src_mac_hi;
+	u16 dest_mac_lo;
+
+	u32 src_mac_lo;
+
+	u32 ib2;
+
+	u32 rsv[5];
+
+	u32 data;
+
+	struct airoha_foe_mac_info l2;
+};
+
+struct airoha_foe_ipv4_tuple {
+	u32 src_ip;
+	u32 dest_ip;
+	union {
+		struct {
+			u16 dest_port;
+			u16 src_port;
+		};
+		struct {
+			u8 protocol;
+			u8 _pad[3]; /* fill with 0xa5a5a5 */
+		};
+		u32 ports;
+	};
+};
+
+struct airoha_foe_ipv4 {
+	struct airoha_foe_ipv4_tuple orig_tuple;
+
+	u32 ib2;
+
+	struct airoha_foe_ipv4_tuple new_tuple;
+
+	u32 rsv[2];
+
+	u32 data;
+
+	struct airoha_foe_mac_info l2;
+};
+
+struct airoha_foe_ipv4_dslite {
+	struct airoha_foe_ipv4_tuple ip4;
+
+	u32 ib2;
+
+	u8 flow_label[3];
+	u8 priority;
+
+	u32 rsv[4];
+
+	u32 data;
+
+	struct airoha_foe_mac_info l2;
+};
+
+struct airoha_foe_ipv6 {
+	u32 src_ip[4];
+	u32 dest_ip[4];
+
+	union {
+		struct {
+			u16 dest_port;
+			u16 src_port;
+		};
+		struct {
+			u8 protocol;
+			u8 pad[3];
+		};
+		u32 ports;
+	};
+
+	u32 data;
+
+	u32 ib2;
+
+	struct airoha_foe_mac_info_common l2;
+
+	u32 meter;
+};
+
+struct airoha_foe_entry {
+	union {
+		struct {
+			u32 ib1;
+			union {
+				struct airoha_foe_bridge bridge;
+				struct airoha_foe_ipv4 ipv4;
+				struct airoha_foe_ipv4_dslite dslite;
+				struct airoha_foe_ipv6 ipv6;
+				DECLARE_FLEX_ARRAY(u32, d);
+			};
+		};
+		u8 data[PPE_ENTRY_SIZE];
+	};
+};
+
+struct airoha_foe_stats {
+	u32 bytes;
+	u32 packets;
+};
+
+struct airoha_foe_stats64 {
+	u64 bytes;
+	u64 packets;
+};
+
+struct airoha_flow_data {
+	struct ethhdr eth;
+
+	union {
+		struct {
+			__be32 src_addr;
+			__be32 dst_addr;
+		} v4;
+
+		struct {
+			struct in6_addr src_addr;
+			struct in6_addr dst_addr;
+		} v6;
+	};
+
+	__be16 src_port;
+	__be16 dst_port;
+
+	struct {
+		struct {
+			u16 id;
+			__be16 proto;
+		} hdr[2];
+		u8 num;
+	} vlan;
+	struct {
+		u16 sid;
+		u8 num;
+	} pppoe;
+};
+
+enum airoha_flow_entry_type {
+	FLOW_TYPE_L4,
+	FLOW_TYPE_L2,
+	FLOW_TYPE_L2_SUBFLOW,
+};
+
+struct airoha_flow_table_entry {
+	union {
+		struct hlist_node list; /* PPE L3 flow entry */
+		struct {
+			struct rhash_head l2_node;  /* L2 flow entry */
+			struct hlist_head l2_flows; /* PPE L2 subflows list */
+		};
+	};
+
+	struct hlist_node l2_subflow_node; /* PPE L2 subflow entry */
+	u32 hash;
+
+	struct airoha_foe_stats64 stats;
+	enum airoha_flow_entry_type type;
+
+	struct rhash_head node;
+	unsigned long cookie;
+
+	/* Must be last --ends in a flexible-array member. */
+	struct airoha_foe_entry data;
+};
+
+struct airoha_wdma_info {
+	u8 idx;
+	u8 queue;
+	u16 wcid;
+	u8 bss;
+};
+
+/* RX queue to IRQ mapping: BIT(q) in IRQ(n) */
+#define RX_IRQ0_BANK_PIN_MASK			0x839f
+#define RX_IRQ1_BANK_PIN_MASK			0x7fe00000
+#define RX_IRQ2_BANK_PIN_MASK			0x20
+#define RX_IRQ3_BANK_PIN_MASK			0x40
+#define RX_IRQ_BANK_PIN_MASK(_n)		\
+	(((_n) == 3) ? RX_IRQ3_BANK_PIN_MASK :	\
+	 ((_n) == 2) ? RX_IRQ2_BANK_PIN_MASK :	\
+	 ((_n) == 1) ? RX_IRQ1_BANK_PIN_MASK :	\
+	 RX_IRQ0_BANK_PIN_MASK)
+
+struct airoha_irq_bank {
+	struct airoha_qdma *qdma;
+
+	/* protect concurrent irqmask accesses */
+	spinlock_t irq_lock;
+	u32 irqmask[QDMA_INT_REG_MAX];
+	int irq;
+};
+
+struct airoha_qdma {
+	struct airoha_eth *eth;
+	void __iomem *regs;
+
+	atomic_t users;
+
+	struct airoha_irq_bank irq_banks[AIROHA_MAX_NUM_IRQ_BANKS];
+
+	struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ];
+
+	struct airoha_queue q_tx[AIROHA_NUM_TX_RING];
+	struct airoha_queue q_rx[AIROHA_NUM_RX_RING];
+};
+
+struct airoha_gdm_port {
+	struct airoha_qdma *qdma;
+	struct net_device *dev;
+	int id;
+
+	struct airoha_hw_stats stats;
+
+	DECLARE_BITMAP(qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS);
+
+	/* qos stats counters */
+	u64 cpu_tx_packets;
+	u64 fwd_tx_packets;
+
+	struct metadata_dst *dsa_meta[AIROHA_MAX_DSA_PORTS];
+};
+
+#define AIROHA_RXD4_PPE_CPU_REASON	GENMASK(20, 16)
+#define AIROHA_RXD4_FOE_ENTRY		GENMASK(15, 0)
+
+struct airoha_ppe {
+	struct airoha_ppe_dev dev;
+	struct airoha_eth *eth;
+
+	void *foe;
+	dma_addr_t foe_dma;
+
+	struct rhashtable l2_flows;
+
+	struct hlist_head *foe_flow;
+	u16 *foe_check_time;
+
+	struct airoha_foe_stats *foe_stats;
+	dma_addr_t foe_stats_dma;
+
+	struct dentry *debugfs_dir;
+};
+
+struct airoha_eth_soc_data {
+	u16 version;
+	const char * const *xsi_rsts_names;
+	int num_xsi_rsts;
+	int num_ppe;
+	struct {
+		int (*get_src_port_id)(struct airoha_gdm_port *port, int nbq);
+	} ops;
+};
+
+struct airoha_eth {
+	struct device *dev;
+
+	const struct airoha_eth_soc_data *soc;
+
+	unsigned long state;
+	void __iomem *fe_regs;
+
+	struct airoha_npu __rcu *npu;
+
+	struct airoha_ppe *ppe;
+	struct rhashtable flow_table;
+
+	struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS];
+	struct reset_control_bulk_data *xsi_rsts;
+
+	struct net_device *napi_dev;
+
+	struct airoha_qdma qdma[AIROHA_MAX_NUM_QDMA];
+	struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS];
+};
+
+u32 airoha_rr(void __iomem *base, u32 offset);
+void airoha_wr(void __iomem *base, u32 offset, u32 val);
+u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val);
+
+#define airoha_fe_rr(eth, offset)				\
+	airoha_rr((eth)->fe_regs, (offset))
+#define airoha_fe_wr(eth, offset, val)				\
+	airoha_wr((eth)->fe_regs, (offset), (val))
+#define airoha_fe_rmw(eth, offset, mask, val)			\
+	airoha_rmw((eth)->fe_regs, (offset), (mask), (val))
+#define airoha_fe_set(eth, offset, val)				\
+	airoha_rmw((eth)->fe_regs, (offset), 0, (val))
+#define airoha_fe_clear(eth, offset, val)			\
+	airoha_rmw((eth)->fe_regs, (offset), (val), 0)
+
+#define airoha_qdma_rr(qdma, offset)				\
+	airoha_rr((qdma)->regs, (offset))
+#define airoha_qdma_wr(qdma, offset, val)			\
+	airoha_wr((qdma)->regs, (offset), (val))
+#define airoha_qdma_rmw(qdma, offset, mask, val)		\
+	airoha_rmw((qdma)->regs, (offset), (mask), (val))
+#define airoha_qdma_set(qdma, offset, val)			\
+	airoha_rmw((qdma)->regs, (offset), 0, (val))
+#define airoha_qdma_clear(qdma, offset, val)			\
+	airoha_rmw((qdma)->regs, (offset), (val), 0)
+
+static inline bool airhoa_is_lan_gdm_port(struct airoha_gdm_port *port)
+{
+	/* GDM1 port on EN7581 SoC is connected to the lan dsa switch.
+	 * GDM{2,3,4} can be used as wan port connected to an external
+	 * phy module.
+	 */
+	return port->id == 1;
+}
+
+static inline bool airoha_is_7581(struct airoha_eth *eth)
+{
+	return eth->soc->version == 0x7581;
+}
+
+static inline bool airoha_is_7583(struct airoha_eth *eth)
+{
+	return eth->soc->version == 0x7583;
+}
+
+bool airoha_is_valid_gdm_port(struct airoha_eth *eth,
+			      struct airoha_gdm_port *port);
+
+bool airoha_ppe_is_enabled(struct airoha_eth *eth, int index);
+void airoha_ppe_check_skb(struct airoha_ppe_dev *dev, struct sk_buff *skb,
+			  u16 hash, bool rx_wlan);
+int airoha_ppe_setup_tc_block_cb(struct airoha_ppe_dev *dev, void *type_data);
+int airoha_ppe_init(struct airoha_eth *eth);
+void airoha_ppe_deinit(struct airoha_eth *eth);
+void airoha_ppe_init_upd_mem(struct airoha_gdm_port *port);
+u32 airoha_ppe_get_total_num_entries(struct airoha_ppe *ppe);
+struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe,
+						  u32 hash);
+void airoha_ppe_foe_entry_get_stats(struct airoha_ppe *ppe, u32 hash,
+				    struct airoha_foe_stats64 *stats);
+
+#ifdef CONFIG_DEBUG_FS
+int airoha_ppe_debugfs_init(struct airoha_ppe *ppe);
+#else
+static inline int airoha_ppe_debugfs_init(struct airoha_ppe *ppe)
+{
+	return 0;
+}
+#endif
+
+#endif /* AIROHA_ETH_H */
diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c
new file mode 100644
index 000000000000..68b7f9684dc7
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_npu.c
@@ -0,0 +1,783 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2025 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#include <linux/devcoredump.h>
+#include <linux/firmware.h>
+#include <linux/platform_device.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/regmap.h>
+
+#include "airoha_eth.h"
+
+#define NPU_EN7581_FIRMWARE_DATA		"airoha/en7581_npu_data.bin"
+#define NPU_EN7581_FIRMWARE_RV32		"airoha/en7581_npu_rv32.bin"
+#define NPU_AN7583_FIRMWARE_DATA		"airoha/an7583_npu_data.bin"
+#define NPU_AN7583_FIRMWARE_RV32		"airoha/an7583_npu_rv32.bin"
+#define NPU_EN7581_FIRMWARE_RV32_MAX_SIZE	0x200000
+#define NPU_EN7581_FIRMWARE_DATA_MAX_SIZE	0x10000
+#define NPU_DUMP_SIZE				512
+
+#define REG_NPU_LOCAL_SRAM		0x0
+
+#define NPU_PC_BASE_ADDR		0x305000
+#define REG_PC_DBG(_n)			(0x305000 + ((_n) * 0x100))
+
+#define NPU_CLUSTER_BASE_ADDR		0x306000
+
+#define REG_CR_BOOT_TRIGGER		(NPU_CLUSTER_BASE_ADDR + 0x000)
+#define REG_CR_BOOT_CONFIG		(NPU_CLUSTER_BASE_ADDR + 0x004)
+#define REG_CR_BOOT_BASE(_n)		(NPU_CLUSTER_BASE_ADDR + 0x020 + ((_n) << 2))
+
+#define NPU_MBOX_BASE_ADDR		0x30c000
+
+#define REG_CR_MBOX_INT_STATUS		(NPU_MBOX_BASE_ADDR + 0x000)
+#define MBOX_INT_STATUS_MASK		BIT(8)
+
+#define REG_CR_MBOX_INT_MASK(_n)	(NPU_MBOX_BASE_ADDR + 0x004 + ((_n) << 2))
+#define REG_CR_MBQ0_CTRL(_n)		(NPU_MBOX_BASE_ADDR + 0x030 + ((_n) << 2))
+#define REG_CR_MBQ8_CTRL(_n)		(NPU_MBOX_BASE_ADDR + 0x0b0 + ((_n) << 2))
+#define REG_CR_NPU_MIB(_n)		(NPU_MBOX_BASE_ADDR + 0x140 + ((_n) << 2))
+
+#define NPU_WLAN_BASE_ADDR		0x30d000
+
+#define REG_IRQ_STATUS			(NPU_WLAN_BASE_ADDR + 0x030)
+#define REG_IRQ_RXDONE(_n)		(NPU_WLAN_BASE_ADDR + ((_n) << 2) + 0x034)
+#define NPU_IRQ_RX_MASK(_n)		((_n) == 1 ? BIT(17) : BIT(16))
+
+#define REG_TX_BASE(_n)			(NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x080)
+#define REG_TX_DSCP_NUM(_n)		(NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x084)
+#define REG_TX_CPU_IDX(_n)		(NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x088)
+#define REG_TX_DMA_IDX(_n)		(NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x08c)
+
+#define REG_RX_BASE(_n)			(NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x180)
+#define REG_RX_DSCP_NUM(_n)		(NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x184)
+#define REG_RX_CPU_IDX(_n)		(NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x188)
+#define REG_RX_DMA_IDX(_n)		(NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x18c)
+
+#define NPU_TIMER_BASE_ADDR		0x310100
+#define REG_WDT_TIMER_CTRL(_n)		(NPU_TIMER_BASE_ADDR + ((_n) * 0x100))
+#define WDT_EN_MASK			BIT(25)
+#define WDT_INTR_MASK			BIT(21)
+
+enum {
+	NPU_OP_SET = 1,
+	NPU_OP_SET_NO_WAIT,
+	NPU_OP_GET,
+	NPU_OP_GET_NO_WAIT,
+};
+
+enum {
+	NPU_FUNC_WIFI,
+	NPU_FUNC_TUNNEL,
+	NPU_FUNC_NOTIFY,
+	NPU_FUNC_DBA,
+	NPU_FUNC_TR471,
+	NPU_FUNC_PPE,
+};
+
+enum {
+	NPU_MBOX_ERROR,
+	NPU_MBOX_SUCCESS,
+};
+
+enum {
+	PPE_FUNC_SET_WAIT,
+	PPE_FUNC_SET_WAIT_HWNAT_INIT,
+	PPE_FUNC_SET_WAIT_HWNAT_DEINIT,
+	PPE_FUNC_SET_WAIT_API,
+	PPE_FUNC_SET_WAIT_FLOW_STATS_SETUP,
+};
+
+enum {
+	PPE2_SRAM_SET_ENTRY,
+	PPE_SRAM_SET_ENTRY,
+	PPE_SRAM_SET_VAL,
+	PPE_SRAM_RESET_VAL,
+};
+
+enum {
+	QDMA_WAN_ETHER = 1,
+	QDMA_WAN_PON_XDSL,
+};
+
+struct airoha_npu_fw {
+	const char *name;
+	int max_size;
+};
+
+struct airoha_npu_soc_data {
+	struct airoha_npu_fw fw_rv32;
+	struct airoha_npu_fw fw_data;
+};
+
+#define MBOX_MSG_FUNC_ID	GENMASK(14, 11)
+#define MBOX_MSG_STATIC_BUF	BIT(5)
+#define MBOX_MSG_STATUS		GENMASK(4, 2)
+#define MBOX_MSG_DONE		BIT(1)
+#define MBOX_MSG_WAIT_RSP	BIT(0)
+
+#define PPE_TYPE_L2B_IPV4	2
+#define PPE_TYPE_L2B_IPV4_IPV6	3
+
+struct ppe_mbox_data {
+	u32 func_type;
+	u32 func_id;
+	union {
+		struct {
+			u8 cds;
+			u8 xpon_hal_api;
+			u8 wan_xsi;
+			u8 ct_joyme4;
+			u8 max_packet;
+			u8 rsv[3];
+			u32 ppe_type;
+			u32 wan_mode;
+			u32 wan_sel;
+		} init_info;
+		struct {
+			u32 func_id;
+			u32 size;
+			u32 data;
+		} set_info;
+		struct {
+			u32 npu_stats_addr;
+			u32 foe_stats_addr;
+		} stats_info;
+	};
+};
+
+struct wlan_mbox_data {
+	u32 ifindex:4;
+	u32 func_type:4;
+	u32 func_id;
+	DECLARE_FLEX_ARRAY(u8, d);
+};
+
+static int airoha_npu_send_msg(struct airoha_npu *npu, int func_id,
+			       void *p, int size)
+{
+	u16 core = 0; /* FIXME */
+	u32 val, offset = core << 4;
+	dma_addr_t dma_addr;
+	int ret;
+
+	dma_addr = dma_map_single(npu->dev, p, size, DMA_TO_DEVICE);
+	ret = dma_mapping_error(npu->dev, dma_addr);
+	if (ret)
+		return ret;
+
+	spin_lock_bh(&npu->cores[core].lock);
+
+	regmap_write(npu->regmap, REG_CR_MBQ0_CTRL(0) + offset, dma_addr);
+	regmap_write(npu->regmap, REG_CR_MBQ0_CTRL(1) + offset, size);
+	regmap_read(npu->regmap, REG_CR_MBQ0_CTRL(2) + offset, &val);
+	regmap_write(npu->regmap, REG_CR_MBQ0_CTRL(2) + offset, val + 1);
+	val = FIELD_PREP(MBOX_MSG_FUNC_ID, func_id) | MBOX_MSG_WAIT_RSP;
+	regmap_write(npu->regmap, REG_CR_MBQ0_CTRL(3) + offset, val);
+
+	ret = regmap_read_poll_timeout_atomic(npu->regmap,
+					      REG_CR_MBQ0_CTRL(3) + offset,
+					      val, (val & MBOX_MSG_DONE),
+					      100, 100 * MSEC_PER_SEC);
+	if (!ret && FIELD_GET(MBOX_MSG_STATUS, val) != NPU_MBOX_SUCCESS)
+		ret = -EINVAL;
+
+	spin_unlock_bh(&npu->cores[core].lock);
+
+	dma_unmap_single(npu->dev, dma_addr, size, DMA_TO_DEVICE);
+
+	return ret;
+}
+
+static int airoha_npu_load_firmware(struct device *dev, void __iomem *addr,
+				    const struct airoha_npu_fw *fw_info)
+{
+	const struct firmware *fw;
+	int ret;
+
+	ret = request_firmware(&fw, fw_info->name, dev);
+	if (ret)
+		return ret == -ENOENT ? -EPROBE_DEFER : ret;
+
+	if (fw->size > fw_info->max_size) {
+		dev_err(dev, "%s: fw size too overlimit (%zu)\n",
+			fw_info->name, fw->size);
+		ret = -E2BIG;
+		goto out;
+	}
+
+	memcpy_toio(addr, fw->data, fw->size);
+out:
+	release_firmware(fw);
+
+	return ret;
+}
+
+static int airoha_npu_run_firmware(struct device *dev, void __iomem *base,
+				   struct resource *res)
+{
+	const struct airoha_npu_soc_data *soc;
+	void __iomem *addr;
+	int ret;
+
+	soc = of_device_get_match_data(dev);
+	if (!soc)
+		return -EINVAL;
+
+	addr = devm_ioremap_resource(dev, res);
+	if (IS_ERR(addr))
+		return PTR_ERR(addr);
+
+	/* Load rv32 npu firmware */
+	ret = airoha_npu_load_firmware(dev, addr, &soc->fw_rv32);
+	if (ret)
+		return ret;
+
+	/* Load data npu firmware */
+	return airoha_npu_load_firmware(dev, base + REG_NPU_LOCAL_SRAM,
+					&soc->fw_data);
+}
+
+static irqreturn_t airoha_npu_mbox_handler(int irq, void *npu_instance)
+{
+	struct airoha_npu *npu = npu_instance;
+
+	/* clear mbox interrupt status */
+	regmap_write(npu->regmap, REG_CR_MBOX_INT_STATUS,
+		     MBOX_INT_STATUS_MASK);
+
+	/* acknowledge npu */
+	regmap_update_bits(npu->regmap, REG_CR_MBQ8_CTRL(3),
+			   MBOX_MSG_STATUS | MBOX_MSG_DONE, MBOX_MSG_DONE);
+
+	return IRQ_HANDLED;
+}
+
+static void airoha_npu_wdt_work(struct work_struct *work)
+{
+	struct airoha_npu_core *core;
+	struct airoha_npu *npu;
+	void *dump;
+	u32 val[3];
+	int c;
+
+	core = container_of(work, struct airoha_npu_core, wdt_work);
+	npu = core->npu;
+
+	dump = vzalloc(NPU_DUMP_SIZE);
+	if (!dump)
+		return;
+
+	c = core - &npu->cores[0];
+	regmap_bulk_read(npu->regmap, REG_PC_DBG(c), val, ARRAY_SIZE(val));
+	snprintf(dump, NPU_DUMP_SIZE, "PC: %08x SP: %08x LR: %08x\n",
+		 val[0], val[1], val[2]);
+
+	dev_coredumpv(npu->dev, dump, NPU_DUMP_SIZE, GFP_KERNEL);
+}
+
+static irqreturn_t airoha_npu_wdt_handler(int irq, void *core_instance)
+{
+	struct airoha_npu_core *core = core_instance;
+	struct airoha_npu *npu = core->npu;
+	int c = core - &npu->cores[0];
+	u32 val;
+
+	regmap_set_bits(npu->regmap, REG_WDT_TIMER_CTRL(c), WDT_INTR_MASK);
+	if (!regmap_read(npu->regmap, REG_WDT_TIMER_CTRL(c), &val) &&
+	    FIELD_GET(WDT_EN_MASK, val))
+		schedule_work(&core->wdt_work);
+
+	return IRQ_HANDLED;
+}
+
+static int airoha_npu_ppe_init(struct airoha_npu *npu)
+{
+	struct ppe_mbox_data *ppe_data;
+	int err;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_KERNEL);
+	if (!ppe_data)
+		return -ENOMEM;
+
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_HWNAT_INIT;
+	ppe_data->init_info.ppe_type = PPE_TYPE_L2B_IPV4_IPV6;
+	ppe_data->init_info.wan_mode = QDMA_WAN_ETHER;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	kfree(ppe_data);
+
+	return err;
+}
+
+static int airoha_npu_ppe_deinit(struct airoha_npu *npu)
+{
+	struct ppe_mbox_data *ppe_data;
+	int err;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_KERNEL);
+	if (!ppe_data)
+		return -ENOMEM;
+
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_HWNAT_DEINIT;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	kfree(ppe_data);
+
+	return err;
+}
+
+static int airoha_npu_ppe_flush_sram_entries(struct airoha_npu *npu,
+					     dma_addr_t foe_addr,
+					     int sram_num_entries)
+{
+	struct ppe_mbox_data *ppe_data;
+	int err;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_KERNEL);
+	if (!ppe_data)
+		return -ENOMEM;
+
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_API;
+	ppe_data->set_info.func_id = PPE_SRAM_RESET_VAL;
+	ppe_data->set_info.data = foe_addr;
+	ppe_data->set_info.size = sram_num_entries;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	kfree(ppe_data);
+
+	return err;
+}
+
+static int airoha_npu_foe_commit_entry(struct airoha_npu *npu,
+				       dma_addr_t foe_addr,
+				       u32 entry_size, u32 hash, bool ppe2)
+{
+	struct ppe_mbox_data *ppe_data;
+	int err;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_ATOMIC);
+	if (!ppe_data)
+		return -ENOMEM;
+
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_API;
+	ppe_data->set_info.data = foe_addr;
+	ppe_data->set_info.size = entry_size;
+	ppe_data->set_info.func_id = ppe2 ? PPE2_SRAM_SET_ENTRY
+					  : PPE_SRAM_SET_ENTRY;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	if (err)
+		goto out;
+
+	ppe_data->set_info.func_id = PPE_SRAM_SET_VAL;
+	ppe_data->set_info.data = hash;
+	ppe_data->set_info.size = sizeof(u32);
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+out:
+	kfree(ppe_data);
+
+	return err;
+}
+
+static int airoha_npu_ppe_stats_setup(struct airoha_npu *npu,
+				      dma_addr_t foe_stats_addr,
+				      u32 num_stats_entries)
+{
+	int err, size = num_stats_entries * sizeof(*npu->stats);
+	struct ppe_mbox_data *ppe_data;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_ATOMIC);
+	if (!ppe_data)
+		return -ENOMEM;
+
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_FLOW_STATS_SETUP;
+	ppe_data->stats_info.foe_stats_addr = foe_stats_addr;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	if (err)
+		goto out;
+
+	npu->stats = devm_ioremap(npu->dev,
+				  ppe_data->stats_info.npu_stats_addr,
+				  size);
+	if (!npu->stats)
+		err = -ENOMEM;
+out:
+	kfree(ppe_data);
+
+	return err;
+}
+
+static int airoha_npu_wlan_msg_send(struct airoha_npu *npu, int ifindex,
+				    enum airoha_npu_wlan_set_cmd func_id,
+				    void *data, int data_len, gfp_t gfp)
+{
+	struct wlan_mbox_data *wlan_data;
+	int err, len;
+
+	len = sizeof(*wlan_data) + data_len;
+	wlan_data = kzalloc(len, gfp);
+	if (!wlan_data)
+		return -ENOMEM;
+
+	wlan_data->ifindex = ifindex;
+	wlan_data->func_type = NPU_OP_SET;
+	wlan_data->func_id = func_id;
+	memcpy(wlan_data->d, data, data_len);
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_WIFI, wlan_data, len);
+	kfree(wlan_data);
+
+	return err;
+}
+
+static int airoha_npu_wlan_msg_get(struct airoha_npu *npu, int ifindex,
+				   enum airoha_npu_wlan_get_cmd func_id,
+				   void *data, int data_len, gfp_t gfp)
+{
+	struct wlan_mbox_data *wlan_data;
+	int err, len;
+
+	len = sizeof(*wlan_data) + data_len;
+	wlan_data = kzalloc(len, gfp);
+	if (!wlan_data)
+		return -ENOMEM;
+
+	wlan_data->ifindex = ifindex;
+	wlan_data->func_type = NPU_OP_GET;
+	wlan_data->func_id = func_id;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_WIFI, wlan_data, len);
+	if (!err)
+		memcpy(data, wlan_data->d, data_len);
+	kfree(wlan_data);
+
+	return err;
+}
+
+static int
+airoha_npu_wlan_set_reserved_memory(struct airoha_npu *npu,
+				    int ifindex, const char *name,
+				    enum airoha_npu_wlan_set_cmd func_id)
+{
+	struct device *dev = npu->dev;
+	struct resource res;
+	int err;
+	u32 val;
+
+	err = of_reserved_mem_region_to_resource_byname(dev->of_node, name,
+							&res);
+	if (err)
+		return err;
+
+	val = res.start;
+	return airoha_npu_wlan_msg_send(npu, ifindex, func_id, &val,
+					sizeof(val), GFP_KERNEL);
+}
+
+static int airoha_npu_wlan_init_memory(struct airoha_npu *npu)
+{
+	enum airoha_npu_wlan_set_cmd cmd = WLAN_FUNC_SET_WAIT_NPU_BAND0_ONCPU;
+	u32 val = 0;
+	int err;
+
+	err = airoha_npu_wlan_msg_send(npu, 1, cmd, &val, sizeof(val),
+				       GFP_KERNEL);
+	if (err)
+		return err;
+
+	cmd = WLAN_FUNC_SET_WAIT_TX_BUF_CHECK_ADDR;
+	err = airoha_npu_wlan_set_reserved_memory(npu, 0, "tx-bufid", cmd);
+	if (err)
+		return err;
+
+	cmd = WLAN_FUNC_SET_WAIT_PKT_BUF_ADDR;
+	err = airoha_npu_wlan_set_reserved_memory(npu, 0, "pkt", cmd);
+	if (err)
+		return err;
+
+	cmd = WLAN_FUNC_SET_WAIT_TX_PKT_BUF_ADDR;
+	err = airoha_npu_wlan_set_reserved_memory(npu, 0, "tx-pkt", cmd);
+	if (err)
+		return err;
+
+	cmd = WLAN_FUNC_SET_WAIT_IS_FORCE_TO_CPU;
+	return airoha_npu_wlan_msg_send(npu, 0, cmd, &val, sizeof(val),
+					GFP_KERNEL);
+}
+
+static u32 airoha_npu_wlan_queue_addr_get(struct airoha_npu *npu, int qid,
+					  bool xmit)
+{
+	if (xmit)
+		return REG_TX_BASE(qid + 2);
+
+	return REG_RX_BASE(qid);
+}
+
+static void airoha_npu_wlan_irq_status_set(struct airoha_npu *npu, u32 val)
+{
+	regmap_write(npu->regmap, REG_IRQ_STATUS, val);
+}
+
+static u32 airoha_npu_wlan_irq_status_get(struct airoha_npu *npu, int q)
+{
+	u32 val;
+
+	regmap_read(npu->regmap, REG_IRQ_STATUS, &val);
+	return val;
+}
+
+static void airoha_npu_wlan_irq_enable(struct airoha_npu *npu, int q)
+{
+	regmap_set_bits(npu->regmap, REG_IRQ_RXDONE(q), NPU_IRQ_RX_MASK(q));
+}
+
+static void airoha_npu_wlan_irq_disable(struct airoha_npu *npu, int q)
+{
+	regmap_clear_bits(npu->regmap, REG_IRQ_RXDONE(q), NPU_IRQ_RX_MASK(q));
+}
+
+struct airoha_npu *airoha_npu_get(struct device *dev)
+{
+	struct platform_device *pdev;
+	struct device_node *np;
+	struct airoha_npu *npu;
+
+	np = of_parse_phandle(dev->of_node, "airoha,npu", 0);
+	if (!np)
+		return ERR_PTR(-ENODEV);
+
+	pdev = of_find_device_by_node(np);
+
+	if (!pdev) {
+		dev_err(dev, "cannot find device node %s\n", np->name);
+		of_node_put(np);
+		return ERR_PTR(-ENODEV);
+	}
+	of_node_put(np);
+
+	if (!try_module_get(THIS_MODULE)) {
+		dev_err(dev, "failed to get the device driver module\n");
+		npu = ERR_PTR(-ENODEV);
+		goto error_pdev_put;
+	}
+
+	npu = platform_get_drvdata(pdev);
+	if (!npu) {
+		npu = ERR_PTR(-ENODEV);
+		goto error_module_put;
+	}
+
+	if (!device_link_add(dev, &pdev->dev, DL_FLAG_AUTOREMOVE_SUPPLIER)) {
+		dev_err(&pdev->dev,
+			"failed to create device link to consumer %s\n",
+			dev_name(dev));
+		npu = ERR_PTR(-EINVAL);
+		goto error_module_put;
+	}
+
+	return npu;
+
+error_module_put:
+	module_put(THIS_MODULE);
+error_pdev_put:
+	platform_device_put(pdev);
+
+	return npu;
+}
+EXPORT_SYMBOL_GPL(airoha_npu_get);
+
+void airoha_npu_put(struct airoha_npu *npu)
+{
+	module_put(THIS_MODULE);
+	put_device(npu->dev);
+}
+EXPORT_SYMBOL_GPL(airoha_npu_put);
+
+static const struct airoha_npu_soc_data en7581_npu_soc_data = {
+	.fw_rv32 = {
+		.name = NPU_EN7581_FIRMWARE_RV32,
+		.max_size = NPU_EN7581_FIRMWARE_RV32_MAX_SIZE,
+	},
+	.fw_data = {
+		.name = NPU_EN7581_FIRMWARE_DATA,
+		.max_size = NPU_EN7581_FIRMWARE_DATA_MAX_SIZE,
+	},
+};
+
+static const struct airoha_npu_soc_data an7583_npu_soc_data = {
+	.fw_rv32 = {
+		.name = NPU_AN7583_FIRMWARE_RV32,
+		.max_size = NPU_EN7581_FIRMWARE_RV32_MAX_SIZE,
+	},
+	.fw_data = {
+		.name = NPU_AN7583_FIRMWARE_DATA,
+		.max_size = NPU_EN7581_FIRMWARE_DATA_MAX_SIZE,
+	},
+};
+
+static const struct of_device_id of_airoha_npu_match[] = {
+	{ .compatible = "airoha,en7581-npu", .data = &en7581_npu_soc_data },
+	{ .compatible = "airoha,an7583-npu", .data = &an7583_npu_soc_data },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, of_airoha_npu_match);
+
+static const struct regmap_config regmap_config = {
+	.name			= "npu",
+	.reg_bits		= 32,
+	.val_bits		= 32,
+	.reg_stride		= 4,
+	.disable_locking	= true,
+};
+
+static int airoha_npu_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct airoha_npu *npu;
+	struct resource res;
+	void __iomem *base;
+	int i, irq, err;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	npu = devm_kzalloc(dev, sizeof(*npu), GFP_KERNEL);
+	if (!npu)
+		return -ENOMEM;
+
+	npu->dev = dev;
+	npu->ops.ppe_init = airoha_npu_ppe_init;
+	npu->ops.ppe_deinit = airoha_npu_ppe_deinit;
+	npu->ops.ppe_init_stats = airoha_npu_ppe_stats_setup;
+	npu->ops.ppe_flush_sram_entries = airoha_npu_ppe_flush_sram_entries;
+	npu->ops.ppe_foe_commit_entry = airoha_npu_foe_commit_entry;
+	npu->ops.wlan_init_reserved_memory = airoha_npu_wlan_init_memory;
+	npu->ops.wlan_send_msg = airoha_npu_wlan_msg_send;
+	npu->ops.wlan_get_msg = airoha_npu_wlan_msg_get;
+	npu->ops.wlan_get_queue_addr = airoha_npu_wlan_queue_addr_get;
+	npu->ops.wlan_set_irq_status = airoha_npu_wlan_irq_status_set;
+	npu->ops.wlan_get_irq_status = airoha_npu_wlan_irq_status_get;
+	npu->ops.wlan_enable_irq = airoha_npu_wlan_irq_enable;
+	npu->ops.wlan_disable_irq = airoha_npu_wlan_irq_disable;
+
+	npu->regmap = devm_regmap_init_mmio(dev, base, &regmap_config);
+	if (IS_ERR(npu->regmap))
+		return PTR_ERR(npu->regmap);
+
+	err = of_reserved_mem_region_to_resource(dev->of_node, 0, &res);
+	if (err)
+		return err;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	err = devm_request_irq(dev, irq, airoha_npu_mbox_handler,
+			       IRQF_SHARED, "airoha-npu-mbox", npu);
+	if (err)
+		return err;
+
+	for (i = 0; i < ARRAY_SIZE(npu->cores); i++) {
+		struct airoha_npu_core *core = &npu->cores[i];
+
+		spin_lock_init(&core->lock);
+		core->npu = npu;
+
+		irq = platform_get_irq(pdev, i + 1);
+		if (irq < 0)
+			return irq;
+
+		err = devm_request_irq(dev, irq, airoha_npu_wdt_handler,
+				       IRQF_SHARED, "airoha-npu-wdt", core);
+		if (err)
+			return err;
+
+		INIT_WORK(&core->wdt_work, airoha_npu_wdt_work);
+	}
+
+	/* wlan IRQ lines */
+	for (i = 0; i < ARRAY_SIZE(npu->irqs); i++) {
+		irq = platform_get_irq(pdev, i + ARRAY_SIZE(npu->cores) + 1);
+		if (irq < 0)
+			return irq;
+
+		npu->irqs[i] = irq;
+	}
+
+	err = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
+	if (err)
+		return err;
+
+	err = airoha_npu_run_firmware(dev, base, &res);
+	if (err)
+		return dev_err_probe(dev, err, "failed to run npu firmware\n");
+
+	regmap_write(npu->regmap, REG_CR_NPU_MIB(10),
+		     res.start + NPU_EN7581_FIRMWARE_RV32_MAX_SIZE);
+	regmap_write(npu->regmap, REG_CR_NPU_MIB(11), 0x40000); /* SRAM 256K */
+	regmap_write(npu->regmap, REG_CR_NPU_MIB(12), 0);
+	regmap_write(npu->regmap, REG_CR_NPU_MIB(21), 1);
+	msleep(100);
+
+	/* setting booting address */
+	for (i = 0; i < NPU_NUM_CORES; i++)
+		regmap_write(npu->regmap, REG_CR_BOOT_BASE(i), res.start);
+	usleep_range(1000, 2000);
+
+	/* enable NPU cores */
+	regmap_write(npu->regmap, REG_CR_BOOT_CONFIG, 0xff);
+	regmap_write(npu->regmap, REG_CR_BOOT_TRIGGER, 0x1);
+	msleep(100);
+
+	platform_set_drvdata(pdev, npu);
+
+	return 0;
+}
+
+static void airoha_npu_remove(struct platform_device *pdev)
+{
+	struct airoha_npu *npu = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(npu->cores); i++)
+		cancel_work_sync(&npu->cores[i].wdt_work);
+}
+
+static struct platform_driver airoha_npu_driver = {
+	.probe = airoha_npu_probe,
+	.remove = airoha_npu_remove,
+	.driver = {
+		.name = "airoha-npu",
+		.of_match_table = of_airoha_npu_match,
+	},
+};
+module_platform_driver(airoha_npu_driver);
+
+MODULE_FIRMWARE(NPU_EN7581_FIRMWARE_DATA);
+MODULE_FIRMWARE(NPU_EN7581_FIRMWARE_RV32);
+MODULE_FIRMWARE(NPU_AN7583_FIRMWARE_DATA);
+MODULE_FIRMWARE(NPU_AN7583_FIRMWARE_RV32);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("Airoha Network Processor Unit driver");
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
new file mode 100644
index 000000000000..0caabb0c3aa0
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -0,0 +1,1561 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2025 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/rhashtable.h>
+#include <net/ipv6.h>
+#include <net/pkt_cls.h>
+
+#include "airoha_regs.h"
+#include "airoha_eth.h"
+
+static DEFINE_MUTEX(flow_offload_mutex);
+static DEFINE_SPINLOCK(ppe_lock);
+
+static const struct rhashtable_params airoha_flow_table_params = {
+	.head_offset = offsetof(struct airoha_flow_table_entry, node),
+	.key_offset = offsetof(struct airoha_flow_table_entry, cookie),
+	.key_len = sizeof(unsigned long),
+	.automatic_shrinking = true,
+};
+
+static const struct rhashtable_params airoha_l2_flow_table_params = {
+	.head_offset = offsetof(struct airoha_flow_table_entry, l2_node),
+	.key_offset = offsetof(struct airoha_flow_table_entry, data.bridge),
+	.key_len = 2 * ETH_ALEN,
+	.automatic_shrinking = true,
+};
+
+static int airoha_ppe_get_num_stats_entries(struct airoha_ppe *ppe)
+{
+	if (!IS_ENABLED(CONFIG_NET_AIROHA_FLOW_STATS))
+		return -EOPNOTSUPP;
+
+	if (airoha_is_7583(ppe->eth))
+		return -EOPNOTSUPP;
+
+	return PPE_STATS_NUM_ENTRIES;
+}
+
+static int airoha_ppe_get_total_num_stats_entries(struct airoha_ppe *ppe)
+{
+	int num_stats = airoha_ppe_get_num_stats_entries(ppe);
+
+	if (num_stats > 0) {
+		struct airoha_eth *eth = ppe->eth;
+
+		num_stats = num_stats * eth->soc->num_ppe;
+	}
+
+	return num_stats;
+}
+
+static u32 airoha_ppe_get_total_sram_num_entries(struct airoha_ppe *ppe)
+{
+	struct airoha_eth *eth = ppe->eth;
+
+	return PPE_SRAM_NUM_ENTRIES * eth->soc->num_ppe;
+}
+
+u32 airoha_ppe_get_total_num_entries(struct airoha_ppe *ppe)
+{
+	u32 sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe);
+
+	return sram_num_entries + PPE_DRAM_NUM_ENTRIES;
+}
+
+bool airoha_ppe_is_enabled(struct airoha_eth *eth, int index)
+{
+	if (index >= eth->soc->num_ppe)
+		return false;
+
+	return airoha_fe_rr(eth, REG_PPE_GLO_CFG(index)) & PPE_GLO_CFG_EN_MASK;
+}
+
+static u32 airoha_ppe_get_timestamp(struct airoha_ppe *ppe)
+{
+	u16 timestamp = airoha_fe_rr(ppe->eth, REG_FE_FOE_TS);
+
+	return FIELD_GET(AIROHA_FOE_IB1_BIND_TIMESTAMP, timestamp);
+}
+
+static void airoha_ppe_hw_init(struct airoha_ppe *ppe)
+{
+	u32 sram_ppe_num_data_entries = PPE_SRAM_NUM_ENTRIES, sram_num_entries;
+	u32 sram_tb_size, dram_num_entries;
+	struct airoha_eth *eth = ppe->eth;
+	int i, sram_num_stats_entries;
+
+	sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe);
+	sram_tb_size = sram_num_entries * sizeof(struct airoha_foe_entry);
+	dram_num_entries = PPE_RAM_NUM_ENTRIES_SHIFT(PPE_DRAM_NUM_ENTRIES);
+
+	sram_num_stats_entries = airoha_ppe_get_num_stats_entries(ppe);
+	if (sram_num_stats_entries > 0)
+		sram_ppe_num_data_entries -= sram_num_stats_entries;
+	sram_ppe_num_data_entries =
+		PPE_RAM_NUM_ENTRIES_SHIFT(sram_ppe_num_data_entries);
+
+	for (i = 0; i < eth->soc->num_ppe; i++) {
+		int p;
+
+		airoha_fe_wr(eth, REG_PPE_TB_BASE(i),
+			     ppe->foe_dma + sram_tb_size);
+
+		airoha_fe_rmw(eth, REG_PPE_BND_AGE0(i),
+			      PPE_BIND_AGE0_DELTA_NON_L4 |
+			      PPE_BIND_AGE0_DELTA_UDP,
+			      FIELD_PREP(PPE_BIND_AGE0_DELTA_NON_L4, 1) |
+			      FIELD_PREP(PPE_BIND_AGE0_DELTA_UDP, 12));
+		airoha_fe_rmw(eth, REG_PPE_BND_AGE1(i),
+			      PPE_BIND_AGE1_DELTA_TCP_FIN |
+			      PPE_BIND_AGE1_DELTA_TCP,
+			      FIELD_PREP(PPE_BIND_AGE1_DELTA_TCP_FIN, 1) |
+			      FIELD_PREP(PPE_BIND_AGE1_DELTA_TCP, 7));
+
+		airoha_fe_rmw(eth, REG_PPE_TB_HASH_CFG(i),
+			      PPE_SRAM_TABLE_EN_MASK |
+			      PPE_SRAM_HASH1_EN_MASK |
+			      PPE_DRAM_TABLE_EN_MASK |
+			      PPE_SRAM_HASH0_MODE_MASK |
+			      PPE_SRAM_HASH1_MODE_MASK |
+			      PPE_DRAM_HASH0_MODE_MASK |
+			      PPE_DRAM_HASH1_MODE_MASK,
+			      FIELD_PREP(PPE_SRAM_TABLE_EN_MASK, 1) |
+			      FIELD_PREP(PPE_SRAM_HASH1_EN_MASK, 1) |
+			      FIELD_PREP(PPE_SRAM_HASH1_MODE_MASK, 1) |
+			      FIELD_PREP(PPE_DRAM_HASH1_MODE_MASK, 3));
+
+		airoha_fe_rmw(eth, REG_PPE_TB_CFG(i),
+			      PPE_TB_CFG_SEARCH_MISS_MASK |
+			      PPE_SRAM_TB_NUM_ENTRY_MASK |
+			      PPE_DRAM_TB_NUM_ENTRY_MASK |
+			      PPE_TB_CFG_KEEPALIVE_MASK |
+			      PPE_TB_ENTRY_SIZE_MASK,
+			      FIELD_PREP(PPE_TB_CFG_SEARCH_MISS_MASK, 3) |
+			      FIELD_PREP(PPE_TB_ENTRY_SIZE_MASK, 0) |
+			      FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK,
+					 sram_ppe_num_data_entries) |
+			      FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK,
+					 dram_num_entries));
+
+		airoha_fe_wr(eth, REG_PPE_HASH_SEED(i), PPE_HASH_SEED);
+
+		for (p = 0; p < ARRAY_SIZE(eth->ports); p++)
+			airoha_fe_rmw(eth, REG_PPE_MTU(i, p),
+				      FP0_EGRESS_MTU_MASK |
+				      FP1_EGRESS_MTU_MASK,
+				      FIELD_PREP(FP0_EGRESS_MTU_MASK,
+						 AIROHA_MAX_MTU) |
+				      FIELD_PREP(FP1_EGRESS_MTU_MASK,
+						 AIROHA_MAX_MTU));
+	}
+}
+
+static void airoha_ppe_flow_mangle_eth(const struct flow_action_entry *act, void *eth)
+{
+	void *dest = eth + act->mangle.offset;
+	const void *src = &act->mangle.val;
+
+	if (act->mangle.offset > 8)
+		return;
+
+	if (act->mangle.mask == 0xffff) {
+		src += 2;
+		dest += 2;
+	}
+
+	memcpy(dest, src, act->mangle.mask ? 2 : 4);
+}
+
+static int airoha_ppe_flow_mangle_ports(const struct flow_action_entry *act,
+					struct airoha_flow_data *data)
+{
+	u32 val = be32_to_cpu((__force __be32)act->mangle.val);
+
+	switch (act->mangle.offset) {
+	case 0:
+		if ((__force __be32)act->mangle.mask == ~cpu_to_be32(0xffff))
+			data->dst_port = cpu_to_be16(val);
+		else
+			data->src_port = cpu_to_be16(val >> 16);
+		break;
+	case 2:
+		data->dst_port = cpu_to_be16(val);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_flow_mangle_ipv4(const struct flow_action_entry *act,
+				       struct airoha_flow_data *data)
+{
+	__be32 *dest;
+
+	switch (act->mangle.offset) {
+	case offsetof(struct iphdr, saddr):
+		dest = &data->v4.src_addr;
+		break;
+	case offsetof(struct iphdr, daddr):
+		dest = &data->v4.dst_addr;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	memcpy(dest, &act->mangle.val, sizeof(u32));
+
+	return 0;
+}
+
+static int airoha_ppe_get_wdma_info(struct net_device *dev, const u8 *addr,
+				    struct airoha_wdma_info *info)
+{
+	struct net_device_path_stack stack;
+	struct net_device_path *path;
+	int err;
+
+	if (!dev)
+		return -ENODEV;
+
+	err = dev_fill_forward_path(dev, addr, &stack);
+	if (err)
+		return err;
+
+	path = &stack.path[stack.num_paths - 1];
+	if (path->type != DEV_PATH_MTK_WDMA)
+		return -1;
+
+	info->idx = path->mtk_wdma.wdma_idx;
+	info->bss = path->mtk_wdma.bss;
+	info->wcid = path->mtk_wdma.wcid;
+
+	return 0;
+}
+
+static int airoha_get_dsa_port(struct net_device **dev)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+	struct dsa_port *dp = dsa_port_from_netdev(*dev);
+
+	if (IS_ERR(dp))
+		return -ENODEV;
+
+	*dev = dsa_port_to_conduit(dp);
+	return dp->index;
+#else
+	return -ENODEV;
+#endif
+}
+
+static void airoha_ppe_foe_set_bridge_addrs(struct airoha_foe_bridge *br,
+					    struct ethhdr *eh)
+{
+	br->dest_mac_hi = get_unaligned_be32(eh->h_dest);
+	br->dest_mac_lo = get_unaligned_be16(eh->h_dest + 4);
+	br->src_mac_hi = get_unaligned_be16(eh->h_source);
+	br->src_mac_lo = get_unaligned_be32(eh->h_source + 2);
+}
+
+static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
+					struct airoha_foe_entry *hwe,
+					struct net_device *dev, int type,
+					struct airoha_flow_data *data,
+					int l4proto)
+{
+	u32 qdata = FIELD_PREP(AIROHA_FOE_SHAPER_ID, 0x7f), ports_pad, val;
+	int wlan_etype = -EINVAL, dsa_port = airoha_get_dsa_port(&dev);
+	struct airoha_foe_mac_info_common *l2;
+	u8 smac_id = 0xf;
+
+	memset(hwe, 0, sizeof(*hwe));
+
+	val = FIELD_PREP(AIROHA_FOE_IB1_BIND_STATE, AIROHA_FOE_STATE_BIND) |
+	      FIELD_PREP(AIROHA_FOE_IB1_BIND_PACKET_TYPE, type) |
+	      FIELD_PREP(AIROHA_FOE_IB1_BIND_UDP, l4proto == IPPROTO_UDP) |
+	      FIELD_PREP(AIROHA_FOE_IB1_BIND_VLAN_LAYER, data->vlan.num) |
+	      FIELD_PREP(AIROHA_FOE_IB1_BIND_VPM, data->vlan.num) |
+	      FIELD_PREP(AIROHA_FOE_IB1_BIND_PPPOE, data->pppoe.num) |
+	      AIROHA_FOE_IB1_BIND_TTL;
+	hwe->ib1 = val;
+
+	val = FIELD_PREP(AIROHA_FOE_IB2_PORT_AG, 0x1f);
+	if (dev) {
+		struct airoha_wdma_info info = {};
+
+		if (!airoha_ppe_get_wdma_info(dev, data->eth.h_dest, &info)) {
+			val |= FIELD_PREP(AIROHA_FOE_IB2_NBQ, info.idx) |
+			       FIELD_PREP(AIROHA_FOE_IB2_PSE_PORT,
+					  FE_PSE_PORT_CDM4);
+			qdata |= FIELD_PREP(AIROHA_FOE_ACTDP, info.bss);
+			wlan_etype = FIELD_PREP(AIROHA_FOE_MAC_WDMA_BAND,
+						info.idx) |
+				     FIELD_PREP(AIROHA_FOE_MAC_WDMA_WCID,
+						info.wcid);
+		} else {
+			struct airoha_gdm_port *port = netdev_priv(dev);
+			u8 pse_port;
+
+			if (!airoha_is_valid_gdm_port(eth, port))
+				return -EINVAL;
+
+			if (dsa_port >= 0 || eth->ports[1])
+				pse_port = port->id == 4 ? FE_PSE_PORT_GDM4
+							 : port->id;
+			else
+				pse_port = 2; /* uplink relies on GDM2
+					       * loopback
+					       */
+
+			val |= FIELD_PREP(AIROHA_FOE_IB2_PSE_PORT, pse_port) |
+			       AIROHA_FOE_IB2_PSE_QOS;
+			/* For downlink traffic consume SRAM memory for hw
+			 * forwarding descriptors queue.
+			 */
+			if (airhoa_is_lan_gdm_port(port))
+				val |= AIROHA_FOE_IB2_FAST_PATH;
+			if (dsa_port >= 0)
+				val |= FIELD_PREP(AIROHA_FOE_IB2_NBQ,
+						  dsa_port);
+
+			smac_id = port->id;
+		}
+	}
+
+	if (is_multicast_ether_addr(data->eth.h_dest))
+		val |= AIROHA_FOE_IB2_MULTICAST;
+
+	ports_pad = 0xa5a5a500 | (l4proto & 0xff);
+	if (type == PPE_PKT_TYPE_IPV4_ROUTE)
+		hwe->ipv4.orig_tuple.ports = ports_pad;
+	if (type == PPE_PKT_TYPE_IPV6_ROUTE_3T)
+		hwe->ipv6.ports = ports_pad;
+
+	if (type == PPE_PKT_TYPE_BRIDGE) {
+		airoha_ppe_foe_set_bridge_addrs(&hwe->bridge, &data->eth);
+		hwe->bridge.data = qdata;
+		hwe->bridge.ib2 = val;
+		l2 = &hwe->bridge.l2.common;
+	} else if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+		hwe->ipv6.data = qdata;
+		hwe->ipv6.ib2 = val;
+		l2 = &hwe->ipv6.l2;
+		l2->etype = ETH_P_IPV6;
+	} else {
+		hwe->ipv4.data = qdata;
+		hwe->ipv4.ib2 = val;
+		l2 = &hwe->ipv4.l2.common;
+		l2->etype = ETH_P_IP;
+	}
+
+	l2->dest_mac_hi = get_unaligned_be32(data->eth.h_dest);
+	l2->dest_mac_lo = get_unaligned_be16(data->eth.h_dest + 4);
+	if (type <= PPE_PKT_TYPE_IPV4_DSLITE) {
+		struct airoha_foe_mac_info *mac_info;
+
+		l2->src_mac_hi = get_unaligned_be32(data->eth.h_source);
+		hwe->ipv4.l2.src_mac_lo =
+			get_unaligned_be16(data->eth.h_source + 4);
+
+		mac_info = (struct airoha_foe_mac_info *)l2;
+		mac_info->pppoe_id = data->pppoe.sid;
+	} else {
+		l2->src_mac_hi = FIELD_PREP(AIROHA_FOE_MAC_SMAC_ID, smac_id) |
+				 FIELD_PREP(AIROHA_FOE_MAC_PPPOE_ID,
+					    data->pppoe.sid);
+	}
+
+	if (data->vlan.num) {
+		l2->vlan1 = data->vlan.hdr[0].id;
+		if (data->vlan.num == 2)
+			l2->vlan2 = data->vlan.hdr[1].id;
+	}
+
+	if (wlan_etype >= 0) {
+		l2->etype = wlan_etype;
+	} else if (dsa_port >= 0) {
+		l2->etype = BIT(dsa_port);
+		l2->etype |= !data->vlan.num ? BIT(15) : 0;
+	} else if (data->pppoe.num) {
+		l2->etype = ETH_P_PPP_SES;
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_foe_entry_set_ipv4_tuple(struct airoha_foe_entry *hwe,
+					       struct airoha_flow_data *data,
+					       bool egress)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+	struct airoha_foe_ipv4_tuple *t;
+
+	switch (type) {
+	case PPE_PKT_TYPE_IPV4_HNAPT:
+		if (egress) {
+			t = &hwe->ipv4.new_tuple;
+			break;
+		}
+		fallthrough;
+	case PPE_PKT_TYPE_IPV4_DSLITE:
+	case PPE_PKT_TYPE_IPV4_ROUTE:
+		t = &hwe->ipv4.orig_tuple;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	t->src_ip = be32_to_cpu(data->v4.src_addr);
+	t->dest_ip = be32_to_cpu(data->v4.dst_addr);
+
+	if (type != PPE_PKT_TYPE_IPV4_ROUTE) {
+		t->src_port = be16_to_cpu(data->src_port);
+		t->dest_port = be16_to_cpu(data->dst_port);
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_foe_entry_set_ipv6_tuple(struct airoha_foe_entry *hwe,
+					       struct airoha_flow_data *data)
+
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+	u32 *src, *dest;
+
+	switch (type) {
+	case PPE_PKT_TYPE_IPV6_ROUTE_5T:
+	case PPE_PKT_TYPE_IPV6_6RD:
+		hwe->ipv6.src_port = be16_to_cpu(data->src_port);
+		hwe->ipv6.dest_port = be16_to_cpu(data->dst_port);
+		fallthrough;
+	case PPE_PKT_TYPE_IPV6_ROUTE_3T:
+		src = hwe->ipv6.src_ip;
+		dest = hwe->ipv6.dest_ip;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	ipv6_addr_be32_to_cpu(src, data->v6.src_addr.s6_addr32);
+	ipv6_addr_be32_to_cpu(dest, data->v6.dst_addr.s6_addr32);
+
+	return 0;
+}
+
+static u32 airoha_ppe_foe_get_entry_hash(struct airoha_ppe *ppe,
+					 struct airoha_foe_entry *hwe)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+	u32 ppe_hash_mask = airoha_ppe_get_total_num_entries(ppe) - 1;
+	u32 hash, hv1, hv2, hv3;
+
+	switch (type) {
+	case PPE_PKT_TYPE_IPV4_ROUTE:
+	case PPE_PKT_TYPE_IPV4_HNAPT:
+		hv1 = hwe->ipv4.orig_tuple.ports;
+		hv2 = hwe->ipv4.orig_tuple.dest_ip;
+		hv3 = hwe->ipv4.orig_tuple.src_ip;
+		break;
+	case PPE_PKT_TYPE_IPV6_ROUTE_3T:
+	case PPE_PKT_TYPE_IPV6_ROUTE_5T:
+		hv1 = hwe->ipv6.src_ip[3] ^ hwe->ipv6.dest_ip[3];
+		hv1 ^= hwe->ipv6.ports;
+
+		hv2 = hwe->ipv6.src_ip[2] ^ hwe->ipv6.dest_ip[2];
+		hv2 ^= hwe->ipv6.dest_ip[0];
+
+		hv3 = hwe->ipv6.src_ip[1] ^ hwe->ipv6.dest_ip[1];
+		hv3 ^= hwe->ipv6.src_ip[0];
+		break;
+	case PPE_PKT_TYPE_BRIDGE: {
+		struct airoha_foe_mac_info *l2 = &hwe->bridge.l2;
+
+		hv1 = l2->common.src_mac_hi & 0xffff;
+		hv1 = hv1 << 16 | l2->src_mac_lo;
+
+		hv2 = l2->common.dest_mac_lo;
+		hv2 = hv2 << 16;
+		hv2 = hv2 | ((l2->common.src_mac_hi & 0xffff0000) >> 16);
+
+		hv3 = l2->common.dest_mac_hi;
+		break;
+	}
+	case PPE_PKT_TYPE_IPV4_DSLITE:
+	case PPE_PKT_TYPE_IPV6_6RD:
+	default:
+		WARN_ON_ONCE(1);
+		return ppe_hash_mask;
+	}
+
+	hash = (hv1 & hv2) | ((~hv1) & hv3);
+	hash = (hash >> 24) | ((hash & 0xffffff) << 8);
+	hash ^= hv1 ^ hv2 ^ hv3;
+	hash ^= hash >> 16;
+	hash &= ppe_hash_mask;
+
+	return hash;
+}
+
+static int airoha_ppe_foe_get_flow_stats_index(struct airoha_ppe *ppe,
+					       u32 hash, u32 *index)
+{
+	int ppe_num_stats_entries;
+
+	ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe);
+	if (ppe_num_stats_entries < 0)
+		return ppe_num_stats_entries;
+
+	*index = hash >= ppe_num_stats_entries ? hash - PPE_STATS_NUM_ENTRIES
+					       : hash;
+
+	return 0;
+}
+
+static void airoha_ppe_foe_flow_stat_entry_reset(struct airoha_ppe *ppe,
+						 struct airoha_npu *npu,
+						 int index)
+{
+	memset_io(&npu->stats[index], 0, sizeof(*npu->stats));
+	memset(&ppe->foe_stats[index], 0, sizeof(*ppe->foe_stats));
+}
+
+static void airoha_ppe_foe_flow_stats_reset(struct airoha_ppe *ppe,
+					    struct airoha_npu *npu)
+{
+	int i, ppe_num_stats_entries;
+
+	ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe);
+	if (ppe_num_stats_entries < 0)
+		return;
+
+	for (i = 0; i < ppe_num_stats_entries; i++)
+		airoha_ppe_foe_flow_stat_entry_reset(ppe, npu, i);
+}
+
+static void airoha_ppe_foe_flow_stats_update(struct airoha_ppe *ppe,
+					     struct airoha_npu *npu,
+					     struct airoha_foe_entry *hwe,
+					     u32 hash)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+	u32 index, pse_port, val, *data, *ib2, *meter;
+	int ppe_num_stats_entries;
+	u8 nbq;
+
+	ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe);
+	if (ppe_num_stats_entries < 0)
+		return;
+
+	if (airoha_ppe_foe_get_flow_stats_index(ppe, hash, &index))
+		return;
+
+	if (index >= ppe_num_stats_entries)
+		return;
+
+	if (type == PPE_PKT_TYPE_BRIDGE) {
+		data = &hwe->bridge.data;
+		ib2 = &hwe->bridge.ib2;
+		meter = &hwe->bridge.l2.meter;
+	} else if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+		data = &hwe->ipv6.data;
+		ib2 = &hwe->ipv6.ib2;
+		meter = &hwe->ipv6.meter;
+	} else {
+		data = &hwe->ipv4.data;
+		ib2 = &hwe->ipv4.ib2;
+		meter = &hwe->ipv4.l2.meter;
+	}
+
+	pse_port = FIELD_GET(AIROHA_FOE_IB2_PSE_PORT, *ib2);
+	if (pse_port == FE_PSE_PORT_CDM4)
+		return;
+
+	airoha_ppe_foe_flow_stat_entry_reset(ppe, npu, index);
+
+	val = FIELD_GET(AIROHA_FOE_CHANNEL | AIROHA_FOE_QID, *data);
+	*data = (*data & ~AIROHA_FOE_ACTDP) |
+		FIELD_PREP(AIROHA_FOE_ACTDP, val);
+
+	val = *ib2 & (AIROHA_FOE_IB2_NBQ | AIROHA_FOE_IB2_PSE_PORT |
+		      AIROHA_FOE_IB2_PSE_QOS | AIROHA_FOE_IB2_FAST_PATH);
+	*meter |= FIELD_PREP(AIROHA_FOE_TUNNEL_MTU, val);
+
+	nbq = pse_port == 1 ? 6 : 5;
+	*ib2 &= ~(AIROHA_FOE_IB2_NBQ | AIROHA_FOE_IB2_PSE_PORT |
+		  AIROHA_FOE_IB2_PSE_QOS);
+	*ib2 |= FIELD_PREP(AIROHA_FOE_IB2_PSE_PORT, 6) |
+		FIELD_PREP(AIROHA_FOE_IB2_NBQ, nbq);
+}
+
+static struct airoha_foe_entry *
+airoha_ppe_foe_get_entry_locked(struct airoha_ppe *ppe, u32 hash)
+{
+	u32 sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe);
+
+	lockdep_assert_held(&ppe_lock);
+
+	if (hash < sram_num_entries) {
+		u32 *hwe = ppe->foe + hash * sizeof(struct airoha_foe_entry);
+		bool ppe2 = hash >= PPE_SRAM_NUM_ENTRIES;
+		struct airoha_eth *eth = ppe->eth;
+		u32 val;
+		int i;
+
+		airoha_fe_wr(ppe->eth, REG_PPE_RAM_CTRL(ppe2),
+			     FIELD_PREP(PPE_SRAM_CTRL_ENTRY_MASK, hash) |
+			     PPE_SRAM_CTRL_REQ_MASK);
+		if (read_poll_timeout_atomic(airoha_fe_rr, val,
+					     val & PPE_SRAM_CTRL_ACK_MASK,
+					     10, 100, false, eth,
+					     REG_PPE_RAM_CTRL(ppe2)))
+			return NULL;
+
+		for (i = 0; i < sizeof(struct airoha_foe_entry) / sizeof(*hwe);
+		     i++)
+			hwe[i] = airoha_fe_rr(eth,
+					      REG_PPE_RAM_ENTRY(ppe2, i));
+	}
+
+	return ppe->foe + hash * sizeof(struct airoha_foe_entry);
+}
+
+struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe,
+						  u32 hash)
+{
+	struct airoha_foe_entry *hwe;
+
+	spin_lock_bh(&ppe_lock);
+	hwe = airoha_ppe_foe_get_entry_locked(ppe, hash);
+	spin_unlock_bh(&ppe_lock);
+
+	return hwe;
+}
+
+static bool airoha_ppe_foe_compare_entry(struct airoha_flow_table_entry *e,
+					 struct airoha_foe_entry *hwe)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, e->data.ib1);
+	int len;
+
+	if ((hwe->ib1 ^ e->data.ib1) & AIROHA_FOE_IB1_BIND_UDP)
+		return false;
+
+	if (type > PPE_PKT_TYPE_IPV4_DSLITE)
+		len = offsetof(struct airoha_foe_entry, ipv6.data);
+	else
+		len = offsetof(struct airoha_foe_entry, ipv4.ib2);
+
+	return !memcmp(&e->data.d, &hwe->d, len - sizeof(hwe->ib1));
+}
+
+static int airoha_ppe_foe_commit_sram_entry(struct airoha_ppe *ppe, u32 hash)
+{
+	struct airoha_foe_entry *hwe = ppe->foe + hash * sizeof(*hwe);
+	bool ppe2 = hash >= PPE_SRAM_NUM_ENTRIES;
+	u32 *ptr = (u32 *)hwe, val;
+	int i;
+
+	for (i = 0; i < sizeof(*hwe) / sizeof(*ptr); i++)
+		airoha_fe_wr(ppe->eth, REG_PPE_RAM_ENTRY(ppe2, i), ptr[i]);
+
+	wmb();
+	airoha_fe_wr(ppe->eth, REG_PPE_RAM_CTRL(ppe2),
+		     FIELD_PREP(PPE_SRAM_CTRL_ENTRY_MASK, hash) |
+		     PPE_SRAM_CTRL_WR_MASK | PPE_SRAM_CTRL_REQ_MASK);
+
+	return read_poll_timeout_atomic(airoha_fe_rr, val,
+					val & PPE_SRAM_CTRL_ACK_MASK,
+					10, 100, false, ppe->eth,
+					REG_PPE_RAM_CTRL(ppe2));
+}
+
+static int airoha_ppe_foe_commit_entry(struct airoha_ppe *ppe,
+				       struct airoha_foe_entry *e,
+				       u32 hash, bool rx_wlan)
+{
+	u32 sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe);
+	struct airoha_foe_entry *hwe = ppe->foe + hash * sizeof(*hwe);
+	u32 ts = airoha_ppe_get_timestamp(ppe);
+	struct airoha_eth *eth = ppe->eth;
+	struct airoha_npu *npu;
+	int err = 0;
+
+	memcpy(&hwe->d, &e->d, sizeof(*hwe) - sizeof(hwe->ib1));
+	wmb();
+
+	e->ib1 &= ~AIROHA_FOE_IB1_BIND_TIMESTAMP;
+	e->ib1 |= FIELD_PREP(AIROHA_FOE_IB1_BIND_TIMESTAMP, ts);
+	hwe->ib1 = e->ib1;
+
+	rcu_read_lock();
+
+	npu = rcu_dereference(eth->npu);
+	if (!npu) {
+		err = -ENODEV;
+		goto unlock;
+	}
+
+	if (!rx_wlan)
+		airoha_ppe_foe_flow_stats_update(ppe, npu, hwe, hash);
+
+	if (hash < sram_num_entries)
+		err = airoha_ppe_foe_commit_sram_entry(ppe, hash);
+unlock:
+	rcu_read_unlock();
+
+	return err;
+}
+
+static void airoha_ppe_foe_remove_flow(struct airoha_ppe *ppe,
+				       struct airoha_flow_table_entry *e)
+{
+	lockdep_assert_held(&ppe_lock);
+
+	hlist_del_init(&e->list);
+	if (e->hash != 0xffff) {
+		e->data.ib1 &= ~AIROHA_FOE_IB1_BIND_STATE;
+		e->data.ib1 |= FIELD_PREP(AIROHA_FOE_IB1_BIND_STATE,
+					  AIROHA_FOE_STATE_INVALID);
+		airoha_ppe_foe_commit_entry(ppe, &e->data, e->hash, false);
+		e->hash = 0xffff;
+	}
+	if (e->type == FLOW_TYPE_L2_SUBFLOW) {
+		hlist_del_init(&e->l2_subflow_node);
+		kfree(e);
+	}
+}
+
+static void airoha_ppe_foe_remove_l2_flow(struct airoha_ppe *ppe,
+					  struct airoha_flow_table_entry *e)
+{
+	struct hlist_head *head = &e->l2_flows;
+	struct hlist_node *n;
+
+	lockdep_assert_held(&ppe_lock);
+
+	rhashtable_remove_fast(&ppe->l2_flows, &e->l2_node,
+			       airoha_l2_flow_table_params);
+	hlist_for_each_entry_safe(e, n, head, l2_subflow_node)
+		airoha_ppe_foe_remove_flow(ppe, e);
+}
+
+static void airoha_ppe_foe_flow_remove_entry(struct airoha_ppe *ppe,
+					     struct airoha_flow_table_entry *e)
+{
+	spin_lock_bh(&ppe_lock);
+
+	if (e->type == FLOW_TYPE_L2)
+		airoha_ppe_foe_remove_l2_flow(ppe, e);
+	else
+		airoha_ppe_foe_remove_flow(ppe, e);
+
+	spin_unlock_bh(&ppe_lock);
+}
+
+static int
+airoha_ppe_foe_commit_subflow_entry(struct airoha_ppe *ppe,
+				    struct airoha_flow_table_entry *e,
+				    u32 hash, bool rx_wlan)
+{
+	u32 mask = AIROHA_FOE_IB1_BIND_PACKET_TYPE | AIROHA_FOE_IB1_BIND_UDP;
+	struct airoha_foe_entry *hwe_p, hwe;
+	struct airoha_flow_table_entry *f;
+	int type;
+
+	hwe_p = airoha_ppe_foe_get_entry_locked(ppe, hash);
+	if (!hwe_p)
+		return -EINVAL;
+
+	f = kzalloc(sizeof(*f), GFP_ATOMIC);
+	if (!f)
+		return -ENOMEM;
+
+	hlist_add_head(&f->l2_subflow_node, &e->l2_flows);
+	f->type = FLOW_TYPE_L2_SUBFLOW;
+	f->hash = hash;
+
+	memcpy(&hwe, hwe_p, sizeof(*hwe_p));
+	hwe.ib1 = (hwe.ib1 & mask) | (e->data.ib1 & ~mask);
+
+	type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe.ib1);
+	if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+		memcpy(&hwe.ipv6.l2, &e->data.bridge.l2, sizeof(hwe.ipv6.l2));
+		hwe.ipv6.ib2 = e->data.bridge.ib2;
+		/* setting smac_id to 0xf instruct the hw to keep original
+		 * source mac address
+		 */
+		hwe.ipv6.l2.src_mac_hi = FIELD_PREP(AIROHA_FOE_MAC_SMAC_ID,
+						    0xf);
+	} else {
+		memcpy(&hwe.bridge.l2, &e->data.bridge.l2,
+		       sizeof(hwe.bridge.l2));
+		hwe.bridge.ib2 = e->data.bridge.ib2;
+		if (type == PPE_PKT_TYPE_IPV4_HNAPT)
+			memcpy(&hwe.ipv4.new_tuple, &hwe.ipv4.orig_tuple,
+			       sizeof(hwe.ipv4.new_tuple));
+	}
+
+	hwe.bridge.data = e->data.bridge.data;
+	airoha_ppe_foe_commit_entry(ppe, &hwe, hash, rx_wlan);
+
+	return 0;
+}
+
+static void airoha_ppe_foe_insert_entry(struct airoha_ppe *ppe,
+					struct sk_buff *skb,
+					u32 hash, bool rx_wlan)
+{
+	struct airoha_flow_table_entry *e;
+	struct airoha_foe_bridge br = {};
+	struct airoha_foe_entry *hwe;
+	bool commit_done = false;
+	struct hlist_node *n;
+	u32 index, state;
+
+	spin_lock_bh(&ppe_lock);
+
+	hwe = airoha_ppe_foe_get_entry_locked(ppe, hash);
+	if (!hwe)
+		goto unlock;
+
+	state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, hwe->ib1);
+	if (state == AIROHA_FOE_STATE_BIND)
+		goto unlock;
+
+	index = airoha_ppe_foe_get_entry_hash(ppe, hwe);
+	hlist_for_each_entry_safe(e, n, &ppe->foe_flow[index], list) {
+		if (e->type == FLOW_TYPE_L2_SUBFLOW) {
+			state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, hwe->ib1);
+			if (state != AIROHA_FOE_STATE_BIND) {
+				e->hash = 0xffff;
+				airoha_ppe_foe_remove_flow(ppe, e);
+			}
+			continue;
+		}
+
+		if (!airoha_ppe_foe_compare_entry(e, hwe))
+			continue;
+
+		airoha_ppe_foe_commit_entry(ppe, &e->data, hash, rx_wlan);
+		commit_done = true;
+		e->hash = hash;
+	}
+
+	if (commit_done)
+		goto unlock;
+
+	airoha_ppe_foe_set_bridge_addrs(&br, eth_hdr(skb));
+	e = rhashtable_lookup_fast(&ppe->l2_flows, &br,
+				   airoha_l2_flow_table_params);
+	if (e)
+		airoha_ppe_foe_commit_subflow_entry(ppe, e, hash, rx_wlan);
+unlock:
+	spin_unlock_bh(&ppe_lock);
+}
+
+static int
+airoha_ppe_foe_l2_flow_commit_entry(struct airoha_ppe *ppe,
+				    struct airoha_flow_table_entry *e)
+{
+	struct airoha_flow_table_entry *prev;
+
+	e->type = FLOW_TYPE_L2;
+	prev = rhashtable_lookup_get_insert_fast(&ppe->l2_flows, &e->l2_node,
+						 airoha_l2_flow_table_params);
+	if (!prev)
+		return 0;
+
+	if (IS_ERR(prev))
+		return PTR_ERR(prev);
+
+	return rhashtable_replace_fast(&ppe->l2_flows, &prev->l2_node,
+				       &e->l2_node,
+				       airoha_l2_flow_table_params);
+}
+
+static int airoha_ppe_foe_flow_commit_entry(struct airoha_ppe *ppe,
+					    struct airoha_flow_table_entry *e)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, e->data.ib1);
+	u32 hash;
+
+	if (type == PPE_PKT_TYPE_BRIDGE)
+		return airoha_ppe_foe_l2_flow_commit_entry(ppe, e);
+
+	hash = airoha_ppe_foe_get_entry_hash(ppe, &e->data);
+	e->type = FLOW_TYPE_L4;
+	e->hash = 0xffff;
+
+	spin_lock_bh(&ppe_lock);
+	hlist_add_head(&e->list, &ppe->foe_flow[hash]);
+	spin_unlock_bh(&ppe_lock);
+
+	return 0;
+}
+
+static int airoha_ppe_get_entry_idle_time(struct airoha_ppe *ppe, u32 ib1)
+{
+	u32 state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, ib1);
+	u32 ts, ts_mask, now = airoha_ppe_get_timestamp(ppe);
+	int idle;
+
+	if (state == AIROHA_FOE_STATE_BIND) {
+		ts = FIELD_GET(AIROHA_FOE_IB1_BIND_TIMESTAMP, ib1);
+		ts_mask = AIROHA_FOE_IB1_BIND_TIMESTAMP;
+	} else {
+		ts = FIELD_GET(AIROHA_FOE_IB1_UNBIND_TIMESTAMP, ib1);
+		now = FIELD_GET(AIROHA_FOE_IB1_UNBIND_TIMESTAMP, now);
+		ts_mask = AIROHA_FOE_IB1_UNBIND_TIMESTAMP;
+	}
+	idle = now - ts;
+
+	return idle < 0 ? idle + ts_mask + 1 : idle;
+}
+
+static void
+airoha_ppe_foe_flow_l2_entry_update(struct airoha_ppe *ppe,
+				    struct airoha_flow_table_entry *e)
+{
+	int min_idle = airoha_ppe_get_entry_idle_time(ppe, e->data.ib1);
+	struct airoha_flow_table_entry *iter;
+	struct hlist_node *n;
+
+	lockdep_assert_held(&ppe_lock);
+
+	hlist_for_each_entry_safe(iter, n, &e->l2_flows, l2_subflow_node) {
+		struct airoha_foe_entry *hwe;
+		u32 ib1, state;
+		int idle;
+
+		hwe = airoha_ppe_foe_get_entry_locked(ppe, iter->hash);
+		if (!hwe)
+			continue;
+
+		ib1 = READ_ONCE(hwe->ib1);
+		state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, ib1);
+		if (state != AIROHA_FOE_STATE_BIND) {
+			iter->hash = 0xffff;
+			airoha_ppe_foe_remove_flow(ppe, iter);
+			continue;
+		}
+
+		idle = airoha_ppe_get_entry_idle_time(ppe, ib1);
+		if (idle >= min_idle)
+			continue;
+
+		min_idle = idle;
+		e->data.ib1 &= ~AIROHA_FOE_IB1_BIND_TIMESTAMP;
+		e->data.ib1 |= ib1 & AIROHA_FOE_IB1_BIND_TIMESTAMP;
+	}
+}
+
+static void airoha_ppe_foe_flow_entry_update(struct airoha_ppe *ppe,
+					     struct airoha_flow_table_entry *e)
+{
+	struct airoha_foe_entry *hwe_p, hwe = {};
+
+	spin_lock_bh(&ppe_lock);
+
+	if (e->type == FLOW_TYPE_L2) {
+		airoha_ppe_foe_flow_l2_entry_update(ppe, e);
+		goto unlock;
+	}
+
+	if (e->hash == 0xffff)
+		goto unlock;
+
+	hwe_p = airoha_ppe_foe_get_entry_locked(ppe, e->hash);
+	if (!hwe_p)
+		goto unlock;
+
+	memcpy(&hwe, hwe_p, sizeof(*hwe_p));
+	if (!airoha_ppe_foe_compare_entry(e, &hwe)) {
+		e->hash = 0xffff;
+		goto unlock;
+	}
+
+	e->data.ib1 = hwe.ib1;
+unlock:
+	spin_unlock_bh(&ppe_lock);
+}
+
+static int airoha_ppe_entry_idle_time(struct airoha_ppe *ppe,
+				      struct airoha_flow_table_entry *e)
+{
+	airoha_ppe_foe_flow_entry_update(ppe, e);
+
+	return airoha_ppe_get_entry_idle_time(ppe, e->data.ib1);
+}
+
+static int airoha_ppe_flow_offload_replace(struct airoha_eth *eth,
+					   struct flow_cls_offload *f)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct airoha_flow_table_entry *e;
+	struct airoha_flow_data data = {};
+	struct net_device *odev = NULL;
+	struct flow_action_entry *act;
+	struct airoha_foe_entry hwe;
+	int err, i, offload_type;
+	u16 addr_type = 0;
+	u8 l4proto = 0;
+
+	if (rhashtable_lookup(&eth->flow_table, &f->cookie,
+			      airoha_flow_table_params))
+		return -EEXIST;
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META))
+		return -EOPNOTSUPP;
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
+
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
+		if (flow_rule_has_control_flags(match.mask->flags,
+						f->common.extack))
+			return -EOPNOTSUPP;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
+		l4proto = match.key->ip_proto;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	switch (addr_type) {
+	case 0:
+		offload_type = PPE_PKT_TYPE_BRIDGE;
+		if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+			struct flow_match_eth_addrs match;
+
+			flow_rule_match_eth_addrs(rule, &match);
+			memcpy(data.eth.h_dest, match.key->dst, ETH_ALEN);
+			memcpy(data.eth.h_source, match.key->src, ETH_ALEN);
+		} else {
+			return -EOPNOTSUPP;
+		}
+		break;
+	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+		offload_type = PPE_PKT_TYPE_IPV4_HNAPT;
+		break;
+	case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+		offload_type = PPE_PKT_TYPE_IPV6_ROUTE_5T;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	flow_action_for_each(i, act, &rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_MANGLE:
+			if (offload_type == PPE_PKT_TYPE_BRIDGE)
+				return -EOPNOTSUPP;
+
+			if (act->mangle.htype == FLOW_ACT_MANGLE_HDR_TYPE_ETH)
+				airoha_ppe_flow_mangle_eth(act, &data.eth);
+			break;
+		case FLOW_ACTION_REDIRECT:
+			odev = act->dev;
+			break;
+		case FLOW_ACTION_CSUM:
+			break;
+		case FLOW_ACTION_VLAN_PUSH:
+			if (data.vlan.num == 2 ||
+			    act->vlan.proto != htons(ETH_P_8021Q))
+				return -EOPNOTSUPP;
+
+			data.vlan.hdr[data.vlan.num].id = act->vlan.vid;
+			data.vlan.hdr[data.vlan.num].proto = act->vlan.proto;
+			data.vlan.num++;
+			break;
+		case FLOW_ACTION_VLAN_POP:
+			break;
+		case FLOW_ACTION_PPPOE_PUSH:
+			if (data.pppoe.num == 1 || data.vlan.num == 2)
+				return -EOPNOTSUPP;
+
+			data.pppoe.sid = act->pppoe.sid;
+			data.pppoe.num++;
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
+
+	if (!is_valid_ether_addr(data.eth.h_source) ||
+	    !is_valid_ether_addr(data.eth.h_dest))
+		return -EINVAL;
+
+	err = airoha_ppe_foe_entry_prepare(eth, &hwe, odev, offload_type,
+					   &data, l4proto);
+	if (err)
+		return err;
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports ports;
+
+		if (offload_type == PPE_PKT_TYPE_BRIDGE)
+			return -EOPNOTSUPP;
+
+		flow_rule_match_ports(rule, &ports);
+		data.src_port = ports.key->src;
+		data.dst_port = ports.key->dst;
+	} else if (offload_type != PPE_PKT_TYPE_BRIDGE) {
+		return -EOPNOTSUPP;
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		struct flow_match_ipv4_addrs addrs;
+
+		flow_rule_match_ipv4_addrs(rule, &addrs);
+		data.v4.src_addr = addrs.key->src;
+		data.v4.dst_addr = addrs.key->dst;
+		airoha_ppe_foe_entry_set_ipv4_tuple(&hwe, &data, false);
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+		struct flow_match_ipv6_addrs addrs;
+
+		flow_rule_match_ipv6_addrs(rule, &addrs);
+
+		data.v6.src_addr = addrs.key->src;
+		data.v6.dst_addr = addrs.key->dst;
+		airoha_ppe_foe_entry_set_ipv6_tuple(&hwe, &data);
+	}
+
+	flow_action_for_each(i, act, &rule->action) {
+		if (act->id != FLOW_ACTION_MANGLE)
+			continue;
+
+		if (offload_type == PPE_PKT_TYPE_BRIDGE)
+			return -EOPNOTSUPP;
+
+		switch (act->mangle.htype) {
+		case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
+		case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
+			err = airoha_ppe_flow_mangle_ports(act, &data);
+			break;
+		case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
+			err = airoha_ppe_flow_mangle_ipv4(act, &data);
+			break;
+		case FLOW_ACT_MANGLE_HDR_TYPE_ETH:
+			/* handled earlier */
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+
+		if (err)
+			return err;
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		err = airoha_ppe_foe_entry_set_ipv4_tuple(&hwe, &data, true);
+		if (err)
+			return err;
+	}
+
+	e = kzalloc(sizeof(*e), GFP_KERNEL);
+	if (!e)
+		return -ENOMEM;
+
+	e->cookie = f->cookie;
+	memcpy(&e->data, &hwe, sizeof(e->data));
+
+	err = airoha_ppe_foe_flow_commit_entry(eth->ppe, e);
+	if (err)
+		goto free_entry;
+
+	err = rhashtable_insert_fast(&eth->flow_table, &e->node,
+				     airoha_flow_table_params);
+	if (err < 0)
+		goto remove_foe_entry;
+
+	return 0;
+
+remove_foe_entry:
+	airoha_ppe_foe_flow_remove_entry(eth->ppe, e);
+free_entry:
+	kfree(e);
+
+	return err;
+}
+
+static int airoha_ppe_flow_offload_destroy(struct airoha_eth *eth,
+					   struct flow_cls_offload *f)
+{
+	struct airoha_flow_table_entry *e;
+
+	e = rhashtable_lookup(&eth->flow_table, &f->cookie,
+			      airoha_flow_table_params);
+	if (!e)
+		return -ENOENT;
+
+	airoha_ppe_foe_flow_remove_entry(eth->ppe, e);
+	rhashtable_remove_fast(&eth->flow_table, &e->node,
+			       airoha_flow_table_params);
+	kfree(e);
+
+	return 0;
+}
+
+void airoha_ppe_foe_entry_get_stats(struct airoha_ppe *ppe, u32 hash,
+				    struct airoha_foe_stats64 *stats)
+{
+	struct airoha_eth *eth = ppe->eth;
+	int ppe_num_stats_entries;
+	struct airoha_npu *npu;
+	u32 index;
+
+	ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe);
+	if (ppe_num_stats_entries < 0)
+		return;
+
+	if (airoha_ppe_foe_get_flow_stats_index(ppe, hash, &index))
+		return;
+
+	if (index >= ppe_num_stats_entries)
+		return;
+
+	rcu_read_lock();
+
+	npu = rcu_dereference(eth->npu);
+	if (npu) {
+		u64 packets = ppe->foe_stats[index].packets;
+		u64 bytes = ppe->foe_stats[index].bytes;
+		struct airoha_foe_stats npu_stats;
+
+		memcpy_fromio(&npu_stats, &npu->stats[index],
+			      sizeof(*npu->stats));
+		stats->packets = packets << 32 | npu_stats.packets;
+		stats->bytes = bytes << 32 | npu_stats.bytes;
+	}
+
+	rcu_read_unlock();
+}
+
+static int airoha_ppe_flow_offload_stats(struct airoha_eth *eth,
+					 struct flow_cls_offload *f)
+{
+	struct airoha_flow_table_entry *e;
+	u32 idle;
+
+	e = rhashtable_lookup(&eth->flow_table, &f->cookie,
+			      airoha_flow_table_params);
+	if (!e)
+		return -ENOENT;
+
+	idle = airoha_ppe_entry_idle_time(eth->ppe, e);
+	f->stats.lastused = jiffies - idle * HZ;
+
+	if (e->hash != 0xffff) {
+		struct airoha_foe_stats64 stats = {};
+
+		airoha_ppe_foe_entry_get_stats(eth->ppe, e->hash, &stats);
+		f->stats.pkts += (stats.packets - e->stats.packets);
+		f->stats.bytes += (stats.bytes - e->stats.bytes);
+		e->stats = stats;
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_flow_offload_cmd(struct airoha_eth *eth,
+				       struct flow_cls_offload *f)
+{
+	switch (f->command) {
+	case FLOW_CLS_REPLACE:
+		return airoha_ppe_flow_offload_replace(eth, f);
+	case FLOW_CLS_DESTROY:
+		return airoha_ppe_flow_offload_destroy(eth, f);
+	case FLOW_CLS_STATS:
+		return airoha_ppe_flow_offload_stats(eth, f);
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int airoha_ppe_flush_sram_entries(struct airoha_ppe *ppe)
+{
+	u32 sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe);
+	struct airoha_foe_entry *hwe = ppe->foe;
+	int i, err = 0;
+
+	for (i = 0; i < sram_num_entries; i++) {
+		int err;
+
+		memset(&hwe[i], 0, sizeof(*hwe));
+		err = airoha_ppe_foe_commit_sram_entry(ppe, i);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+static struct airoha_npu *airoha_ppe_npu_get(struct airoha_eth *eth)
+{
+	struct airoha_npu *npu = airoha_npu_get(eth->dev);
+
+	if (IS_ERR(npu)) {
+		request_module("airoha-npu");
+		npu = airoha_npu_get(eth->dev);
+	}
+
+	return npu;
+}
+
+static int airoha_ppe_offload_setup(struct airoha_eth *eth)
+{
+	struct airoha_npu *npu = airoha_ppe_npu_get(eth);
+	struct airoha_ppe *ppe = eth->ppe;
+	int err, ppe_num_stats_entries;
+
+	if (IS_ERR(npu))
+		return PTR_ERR(npu);
+
+	err = npu->ops.ppe_init(npu);
+	if (err)
+		goto error_npu_put;
+
+	ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe);
+	if (ppe_num_stats_entries > 0) {
+		err = npu->ops.ppe_init_stats(npu, ppe->foe_stats_dma,
+					      ppe_num_stats_entries);
+		if (err)
+			goto error_npu_put;
+	}
+
+	airoha_ppe_hw_init(ppe);
+	airoha_ppe_foe_flow_stats_reset(ppe, npu);
+
+	rcu_assign_pointer(eth->npu, npu);
+	synchronize_rcu();
+
+	return 0;
+
+error_npu_put:
+	airoha_npu_put(npu);
+
+	return err;
+}
+
+int airoha_ppe_setup_tc_block_cb(struct airoha_ppe_dev *dev, void *type_data)
+{
+	struct airoha_ppe *ppe = dev->priv;
+	struct airoha_eth *eth = ppe->eth;
+	int err = 0;
+
+	mutex_lock(&flow_offload_mutex);
+
+	if (!eth->npu)
+		err = airoha_ppe_offload_setup(eth);
+	if (!err)
+		err = airoha_ppe_flow_offload_cmd(eth, type_data);
+
+	mutex_unlock(&flow_offload_mutex);
+
+	return err;
+}
+
+void airoha_ppe_check_skb(struct airoha_ppe_dev *dev, struct sk_buff *skb,
+			  u16 hash, bool rx_wlan)
+{
+	struct airoha_ppe *ppe = dev->priv;
+	u32 ppe_hash_mask = airoha_ppe_get_total_num_entries(ppe) - 1;
+	u16 now, diff;
+
+	if (hash > ppe_hash_mask)
+		return;
+
+	now = (u16)jiffies;
+	diff = now - ppe->foe_check_time[hash];
+	if (diff < HZ / 10)
+		return;
+
+	ppe->foe_check_time[hash] = now;
+	airoha_ppe_foe_insert_entry(ppe, skb, hash, rx_wlan);
+}
+
+void airoha_ppe_init_upd_mem(struct airoha_gdm_port *port)
+{
+	struct airoha_eth *eth = port->qdma->eth;
+	struct net_device *dev = port->dev;
+	const u8 *addr = dev->dev_addr;
+	u32 val;
+
+	val = (addr[2] << 24) | (addr[3] << 16) | (addr[4] << 8) | addr[5];
+	airoha_fe_wr(eth, REG_UPDMEM_DATA(0), val);
+	airoha_fe_wr(eth, REG_UPDMEM_CTRL(0),
+		     FIELD_PREP(PPE_UPDMEM_ADDR_MASK, port->id) |
+		     PPE_UPDMEM_WR_MASK | PPE_UPDMEM_REQ_MASK);
+
+	val = (addr[0] << 8) | addr[1];
+	airoha_fe_wr(eth, REG_UPDMEM_DATA(0), val);
+	airoha_fe_wr(eth, REG_UPDMEM_CTRL(0),
+		     FIELD_PREP(PPE_UPDMEM_ADDR_MASK, port->id) |
+		     FIELD_PREP(PPE_UPDMEM_OFFSET_MASK, 1) |
+		     PPE_UPDMEM_WR_MASK | PPE_UPDMEM_REQ_MASK);
+}
+
+struct airoha_ppe_dev *airoha_ppe_get_dev(struct device *dev)
+{
+	struct platform_device *pdev;
+	struct device_node *np;
+	struct airoha_eth *eth;
+
+	np = of_parse_phandle(dev->of_node, "airoha,eth", 0);
+	if (!np)
+		return ERR_PTR(-ENODEV);
+
+	pdev = of_find_device_by_node(np);
+	if (!pdev) {
+		dev_err(dev, "cannot find device node %s\n", np->name);
+		of_node_put(np);
+		return ERR_PTR(-ENODEV);
+	}
+	of_node_put(np);
+
+	if (!try_module_get(THIS_MODULE)) {
+		dev_err(dev, "failed to get the device driver module\n");
+		goto error_pdev_put;
+	}
+
+	eth = platform_get_drvdata(pdev);
+	if (!eth)
+		goto error_module_put;
+
+	if (!device_link_add(dev, &pdev->dev, DL_FLAG_AUTOREMOVE_SUPPLIER)) {
+		dev_err(&pdev->dev,
+			"failed to create device link to consumer %s\n",
+			dev_name(dev));
+		goto error_module_put;
+	}
+
+	return &eth->ppe->dev;
+
+error_module_put:
+	module_put(THIS_MODULE);
+error_pdev_put:
+	platform_device_put(pdev);
+
+	return ERR_PTR(-ENODEV);
+}
+EXPORT_SYMBOL_GPL(airoha_ppe_get_dev);
+
+void airoha_ppe_put_dev(struct airoha_ppe_dev *dev)
+{
+	struct airoha_ppe *ppe = dev->priv;
+	struct airoha_eth *eth = ppe->eth;
+
+	module_put(THIS_MODULE);
+	put_device(eth->dev);
+}
+EXPORT_SYMBOL_GPL(airoha_ppe_put_dev);
+
+int airoha_ppe_init(struct airoha_eth *eth)
+{
+	int foe_size, err, ppe_num_stats_entries;
+	u32 ppe_num_entries;
+	struct airoha_ppe *ppe;
+
+	ppe = devm_kzalloc(eth->dev, sizeof(*ppe), GFP_KERNEL);
+	if (!ppe)
+		return -ENOMEM;
+
+	ppe->dev.ops.setup_tc_block_cb = airoha_ppe_setup_tc_block_cb;
+	ppe->dev.ops.check_skb = airoha_ppe_check_skb;
+	ppe->dev.priv = ppe;
+	ppe->eth = eth;
+	eth->ppe = ppe;
+
+	ppe_num_entries = airoha_ppe_get_total_num_entries(ppe);
+	foe_size = ppe_num_entries * sizeof(struct airoha_foe_entry);
+	ppe->foe = dmam_alloc_coherent(eth->dev, foe_size, &ppe->foe_dma,
+				       GFP_KERNEL);
+	if (!ppe->foe)
+		return -ENOMEM;
+
+	ppe->foe_flow = devm_kzalloc(eth->dev,
+				     ppe_num_entries * sizeof(*ppe->foe_flow),
+				     GFP_KERNEL);
+	if (!ppe->foe_flow)
+		return -ENOMEM;
+
+	ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe);
+	if (ppe_num_stats_entries > 0) {
+		foe_size = ppe_num_stats_entries * sizeof(*ppe->foe_stats);
+		ppe->foe_stats = dmam_alloc_coherent(eth->dev, foe_size,
+						     &ppe->foe_stats_dma,
+						     GFP_KERNEL);
+		if (!ppe->foe_stats)
+			return -ENOMEM;
+	}
+
+	ppe->foe_check_time = devm_kzalloc(eth->dev, ppe_num_entries,
+					   GFP_KERNEL);
+	if (!ppe->foe_check_time)
+		return -ENOMEM;
+
+	err = airoha_ppe_flush_sram_entries(ppe);
+	if (err)
+		return err;
+
+	err = rhashtable_init(&eth->flow_table, &airoha_flow_table_params);
+	if (err)
+		return err;
+
+	err = rhashtable_init(&ppe->l2_flows, &airoha_l2_flow_table_params);
+	if (err)
+		goto error_flow_table_destroy;
+
+	err = airoha_ppe_debugfs_init(ppe);
+	if (err)
+		goto error_l2_flow_table_destroy;
+
+	return 0;
+
+error_l2_flow_table_destroy:
+	rhashtable_destroy(&ppe->l2_flows);
+error_flow_table_destroy:
+	rhashtable_destroy(&eth->flow_table);
+
+	return err;
+}
+
+void airoha_ppe_deinit(struct airoha_eth *eth)
+{
+	struct airoha_npu *npu;
+
+	rcu_read_lock();
+	npu = rcu_dereference(eth->npu);
+	if (npu) {
+		npu->ops.ppe_deinit(npu);
+		airoha_npu_put(npu);
+	}
+	rcu_read_unlock();
+
+	rhashtable_destroy(&eth->ppe->l2_flows);
+	rhashtable_destroy(&eth->flow_table);
+	debugfs_remove(eth->ppe->debugfs_dir);
+}
diff --git a/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c b/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c
new file mode 100644
index 000000000000..0112c41150bb
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2025 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#include "airoha_eth.h"
+
+static void airoha_debugfs_ppe_print_tuple(struct seq_file *m,
+					   void *src_addr, void *dest_addr,
+					   u16 *src_port, u16 *dest_port,
+					   bool ipv6)
+{
+	__be32 n_addr[IPV6_ADDR_WORDS];
+
+	if (ipv6) {
+		ipv6_addr_cpu_to_be32(n_addr, src_addr);
+		seq_printf(m, "%pI6", n_addr);
+	} else {
+		seq_printf(m, "%pI4h", src_addr);
+	}
+	if (src_port)
+		seq_printf(m, ":%d", *src_port);
+
+	seq_puts(m, "->");
+
+	if (ipv6) {
+		ipv6_addr_cpu_to_be32(n_addr, dest_addr);
+		seq_printf(m, "%pI6", n_addr);
+	} else {
+		seq_printf(m, "%pI4h", dest_addr);
+	}
+	if (dest_port)
+		seq_printf(m, ":%d", *dest_port);
+}
+
+static int airoha_ppe_debugfs_foe_show(struct seq_file *m, void *private,
+				       bool bind)
+{
+	static const char *const ppe_type_str[] = {
+		[PPE_PKT_TYPE_IPV4_HNAPT] = "IPv4 5T",
+		[PPE_PKT_TYPE_IPV4_ROUTE] = "IPv4 3T",
+		[PPE_PKT_TYPE_BRIDGE] = "L2B",
+		[PPE_PKT_TYPE_IPV4_DSLITE] = "DS-LITE",
+		[PPE_PKT_TYPE_IPV6_ROUTE_3T] = "IPv6 3T",
+		[PPE_PKT_TYPE_IPV6_ROUTE_5T] = "IPv6 5T",
+		[PPE_PKT_TYPE_IPV6_6RD] = "6RD",
+	};
+	static const char *const ppe_state_str[] = {
+		[AIROHA_FOE_STATE_INVALID] = "INV",
+		[AIROHA_FOE_STATE_UNBIND] = "UNB",
+		[AIROHA_FOE_STATE_BIND] = "BND",
+		[AIROHA_FOE_STATE_FIN] = "FIN",
+	};
+	struct airoha_ppe *ppe = m->private;
+	u32 ppe_num_entries = airoha_ppe_get_total_num_entries(ppe);
+	int i;
+
+	for (i = 0; i < ppe_num_entries; i++) {
+		const char *state_str, *type_str = "UNKNOWN";
+		void *src_addr = NULL, *dest_addr = NULL;
+		u16 *src_port = NULL, *dest_port = NULL;
+		struct airoha_foe_mac_info_common *l2;
+		unsigned char h_source[ETH_ALEN] = {};
+		struct airoha_foe_stats64 stats = {};
+		unsigned char h_dest[ETH_ALEN];
+		struct airoha_foe_entry *hwe;
+		u32 type, state, ib2, data;
+		bool ipv6 = false;
+
+		hwe = airoha_ppe_foe_get_entry(ppe, i);
+		if (!hwe)
+			continue;
+
+		state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, hwe->ib1);
+		if (!state)
+			continue;
+
+		if (bind && state != AIROHA_FOE_STATE_BIND)
+			continue;
+
+		state_str = ppe_state_str[state % ARRAY_SIZE(ppe_state_str)];
+		type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+		if (type < ARRAY_SIZE(ppe_type_str) && ppe_type_str[type])
+			type_str = ppe_type_str[type];
+
+		seq_printf(m, "%05x %s %7s", i, state_str, type_str);
+
+		switch (type) {
+		case PPE_PKT_TYPE_IPV4_HNAPT:
+		case PPE_PKT_TYPE_IPV4_DSLITE:
+			src_port = &hwe->ipv4.orig_tuple.src_port;
+			dest_port = &hwe->ipv4.orig_tuple.dest_port;
+			fallthrough;
+		case PPE_PKT_TYPE_IPV4_ROUTE:
+			src_addr = &hwe->ipv4.orig_tuple.src_ip;
+			dest_addr = &hwe->ipv4.orig_tuple.dest_ip;
+			break;
+		case PPE_PKT_TYPE_IPV6_ROUTE_5T:
+			src_port = &hwe->ipv6.src_port;
+			dest_port = &hwe->ipv6.dest_port;
+			fallthrough;
+		case PPE_PKT_TYPE_IPV6_ROUTE_3T:
+		case PPE_PKT_TYPE_IPV6_6RD:
+			src_addr = &hwe->ipv6.src_ip;
+			dest_addr = &hwe->ipv6.dest_ip;
+			ipv6 = true;
+			break;
+		default:
+			break;
+		}
+
+		if (src_addr && dest_addr) {
+			seq_puts(m, " orig=");
+			airoha_debugfs_ppe_print_tuple(m, src_addr, dest_addr,
+						       src_port, dest_port, ipv6);
+		}
+
+		switch (type) {
+		case PPE_PKT_TYPE_IPV4_HNAPT:
+		case PPE_PKT_TYPE_IPV4_DSLITE:
+			src_port = &hwe->ipv4.new_tuple.src_port;
+			dest_port = &hwe->ipv4.new_tuple.dest_port;
+			fallthrough;
+		case PPE_PKT_TYPE_IPV4_ROUTE:
+			src_addr = &hwe->ipv4.new_tuple.src_ip;
+			dest_addr = &hwe->ipv4.new_tuple.dest_ip;
+			seq_puts(m, " new=");
+			airoha_debugfs_ppe_print_tuple(m, src_addr, dest_addr,
+						       src_port, dest_port,
+						       ipv6);
+			break;
+		default:
+			break;
+		}
+
+		if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+			data = hwe->ipv6.data;
+			ib2 = hwe->ipv6.ib2;
+			l2 = &hwe->ipv6.l2;
+		} else {
+			data = hwe->ipv4.data;
+			ib2 = hwe->ipv4.ib2;
+			l2 = &hwe->ipv4.l2.common;
+			*((__be16 *)&h_source[4]) =
+				cpu_to_be16(hwe->ipv4.l2.src_mac_lo);
+		}
+
+		airoha_ppe_foe_entry_get_stats(ppe, i, &stats);
+
+		*((__be32 *)h_dest) = cpu_to_be32(l2->dest_mac_hi);
+		*((__be16 *)&h_dest[4]) = cpu_to_be16(l2->dest_mac_lo);
+		*((__be32 *)h_source) = cpu_to_be32(l2->src_mac_hi);
+
+		seq_printf(m, " eth=%pM->%pM etype=%04x data=%08x"
+			      " vlan=%d,%d ib1=%08x ib2=%08x"
+			      " packets=%llu bytes=%llu\n",
+			   h_source, h_dest, l2->etype, data,
+			   l2->vlan1, l2->vlan2, hwe->ib1, ib2,
+			   stats.packets, stats.bytes);
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_debugfs_foe_all_show(struct seq_file *m, void *private)
+{
+	return airoha_ppe_debugfs_foe_show(m, private, false);
+}
+DEFINE_SHOW_ATTRIBUTE(airoha_ppe_debugfs_foe_all);
+
+static int airoha_ppe_debugfs_foe_bind_show(struct seq_file *m, void *private)
+{
+	return airoha_ppe_debugfs_foe_show(m, private, true);
+}
+DEFINE_SHOW_ATTRIBUTE(airoha_ppe_debugfs_foe_bind);
+
+int airoha_ppe_debugfs_init(struct airoha_ppe *ppe)
+{
+	ppe->debugfs_dir = debugfs_create_dir("ppe", NULL);
+	debugfs_create_file("entries", 0444, ppe->debugfs_dir, ppe,
+			    &airoha_ppe_debugfs_foe_all_fops);
+	debugfs_create_file("bind", 0444, ppe->debugfs_dir, ppe,
+			    &airoha_ppe_debugfs_foe_bind_fops);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h
new file mode 100644
index 000000000000..ed4e3407f4a0
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_regs.h
@@ -0,0 +1,923 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#ifndef AIROHA_REGS_H
+#define AIROHA_REGS_H
+
+#include <linux/types.h>
+
+/* FE */
+#define PSE_BASE			0x0100
+#define CSR_IFC_BASE			0x0200
+#define CDM1_BASE			0x0400
+#define GDM1_BASE			0x0500
+#define PPE1_BASE			0x0c00
+#define PPE2_BASE			0x1c00
+
+#define CDM2_BASE			0x1400
+#define GDM2_BASE			0x1500
+
+#define GDM3_BASE			0x1100
+#define GDM4_BASE			0x2500
+
+#define CDM_BASE(_n)			\
+	((_n) == 2 ? CDM2_BASE : CDM1_BASE)
+#define GDM_BASE(_n)			\
+	((_n) == 4 ? GDM4_BASE :	\
+	 (_n) == 3 ? GDM3_BASE :	\
+	 (_n) == 2 ? GDM2_BASE : GDM1_BASE)
+
+#define REG_FE_DMA_GLO_CFG		0x0000
+#define FE_DMA_GLO_L2_SPACE_MASK	GENMASK(7, 4)
+#define FE_DMA_GLO_PG_SZ_MASK		BIT(3)
+
+#define REG_FE_RST_GLO_CFG		0x0004
+#define FE_RST_GDM4_MBI_ARB_MASK	BIT(3)
+#define FE_RST_GDM3_MBI_ARB_MASK	BIT(2)
+#define FE_RST_CORE_MASK		BIT(0)
+
+#define REG_FE_FOE_TS			0x0010
+
+#define REG_FE_WAN_PORT			0x0024
+#define WAN1_EN_MASK			BIT(16)
+#define WAN1_MASK			GENMASK(12, 8)
+#define WAN0_MASK			GENMASK(4, 0)
+
+#define REG_FE_WAN_MAC_H		0x0030
+#define REG_FE_LAN_MAC_H		0x0040
+
+#define REG_FE_MAC_LMIN(_n)		((_n) + 0x04)
+#define REG_FE_MAC_LMAX(_n)		((_n) + 0x08)
+
+#define REG_FE_CDM1_OQ_MAP0		0x0050
+#define REG_FE_CDM1_OQ_MAP1		0x0054
+#define REG_FE_CDM1_OQ_MAP2		0x0058
+#define REG_FE_CDM1_OQ_MAP3		0x005c
+
+#define REG_FE_PCE_CFG			0x0070
+#define PCE_DPI_EN_MASK			BIT(2)
+#define PCE_KA_EN_MASK			BIT(1)
+#define PCE_MC_EN_MASK			BIT(0)
+
+#define REG_FE_PSE_QUEUE_CFG_WR		0x0080
+#define PSE_CFG_PORT_ID_MASK		GENMASK(27, 24)
+#define PSE_CFG_QUEUE_ID_MASK		GENMASK(20, 16)
+#define PSE_CFG_WR_EN_MASK		BIT(8)
+#define PSE_CFG_OQRSV_SEL_MASK		BIT(0)
+
+#define REG_FE_PSE_QUEUE_CFG_VAL	0x0084
+#define PSE_CFG_OQ_RSV_MASK		GENMASK(13, 0)
+
+#define PSE_FQ_CFG			0x008c
+#define PSE_FQ_LIMIT_MASK		GENMASK(14, 0)
+
+#define REG_FE_PSE_BUF_SET		0x0090
+#define PSE_SHARE_USED_LTHD_MASK	GENMASK(31, 16)
+#define PSE_ALLRSV_MASK			GENMASK(14, 0)
+
+#define REG_PSE_SHARE_USED_THD		0x0094
+#define PSE_SHARE_USED_MTHD_MASK	GENMASK(31, 16)
+#define PSE_SHARE_USED_HTHD_MASK	GENMASK(15, 0)
+
+#define REG_GDM_MISC_CFG		0x0148
+#define GDM2_RDM_ACK_WAIT_PREF_MASK	BIT(9)
+#define GDM2_CHN_VLD_MODE_MASK		BIT(5)
+
+#define REG_FE_CSR_IFC_CFG		CSR_IFC_BASE
+#define FE_IFC_EN_MASK			BIT(0)
+
+#define REG_FE_VIP_PORT_EN		0x01f0
+#define REG_FE_IFC_PORT_EN		0x01f4
+
+#define REG_PSE_IQ_REV1			(PSE_BASE + 0x08)
+#define PSE_IQ_RES1_P2_MASK		GENMASK(23, 16)
+
+#define REG_PSE_IQ_REV2			(PSE_BASE + 0x0c)
+#define PSE_IQ_RES2_P5_MASK		GENMASK(15, 8)
+#define PSE_IQ_RES2_P4_MASK		GENMASK(7, 0)
+
+#define REG_FE_VIP_EN(_n)		(0x0300 + ((_n) << 3))
+#define PATN_FCPU_EN_MASK		BIT(7)
+#define PATN_SWP_EN_MASK		BIT(6)
+#define PATN_DP_EN_MASK			BIT(5)
+#define PATN_SP_EN_MASK			BIT(4)
+#define PATN_TYPE_MASK			GENMASK(3, 1)
+#define PATN_EN_MASK			BIT(0)
+
+#define REG_FE_VIP_PATN(_n)		(0x0304 + ((_n) << 3))
+#define PATN_DP_MASK			GENMASK(31, 16)
+#define PATN_SP_MASK			GENMASK(15, 0)
+
+#define REG_CDM_VLAN_CTRL(_n)		CDM_BASE(_n)
+#define CDM_VLAN_MASK			GENMASK(31, 16)
+
+#define REG_CDM_FWD_CFG(_n)		(CDM_BASE(_n) + 0x08)
+#define CDM_OAM_QSEL_MASK		GENMASK(31, 27)
+#define CDM_VIP_QSEL_MASK		GENMASK(24, 20)
+
+#define REG_CDM_CRSN_QSEL(_n, _m)	(CDM_BASE(_n) + 0x10 + ((_m) << 2))
+#define CDM_CRSN_QSEL_REASON_MASK(_n)	\
+	GENMASK(4 + (((_n) % 4) << 3),	(((_n) % 4) << 3))
+
+#define REG_GDM_FWD_CFG(_n)		GDM_BASE(_n)
+#define GDM_PAD_EN_MASK			BIT(28)
+#define GDM_DROP_CRC_ERR_MASK		BIT(23)
+#define GDM_IP4_CKSUM_MASK		BIT(22)
+#define GDM_TCP_CKSUM_MASK		BIT(21)
+#define GDM_UDP_CKSUM_MASK		BIT(20)
+#define GDM_STRIP_CRC_MASK		BIT(16)
+#define GDM_UCFQ_MASK			GENMASK(15, 12)
+#define GDM_BCFQ_MASK			GENMASK(11, 8)
+#define GDM_MCFQ_MASK			GENMASK(7, 4)
+#define GDM_OCFQ_MASK			GENMASK(3, 0)
+
+#define REG_GDM_INGRESS_CFG(_n)		(GDM_BASE(_n) + 0x10)
+#define GDM_INGRESS_FC_EN_MASK		BIT(1)
+#define GDM_STAG_EN_MASK		BIT(0)
+
+#define REG_GDM_LEN_CFG(_n)		(GDM_BASE(_n) + 0x14)
+#define GDM_SHORT_LEN_MASK		GENMASK(13, 0)
+#define GDM_LONG_LEN_MASK		GENMASK(29, 16)
+
+#define REG_GDM_LPBK_CFG(_n)		(GDM_BASE(_n) + 0x1c)
+#define LPBK_GAP_MASK			GENMASK(31, 24)
+#define LPBK_LEN_MASK			GENMASK(23, 10)
+#define LPBK_CHAN_MASK			GENMASK(8, 4)
+#define LPBK_MODE_MASK			GENMASK(3, 1)
+#define LBK_GAP_MODE_MASK		BIT(3)
+#define LBK_LEN_MODE_MASK		BIT(2)
+#define LBK_CHAN_MODE_MASK		BIT(1)
+#define LPBK_EN_MASK			BIT(0)
+
+#define REG_GDM_CHN_RLS(_n)		(GDM_BASE(_n) + 0x20)
+#define MBI_RX_AGE_SEL_MASK		GENMASK(26, 25)
+#define MBI_TX_AGE_SEL_MASK		GENMASK(18, 17)
+
+#define REG_GDM_TXCHN_EN(_n)		(GDM_BASE(_n) + 0x24)
+#define REG_GDM_RXCHN_EN(_n)		(GDM_BASE(_n) + 0x28)
+
+#define REG_FE_CPORT_CFG		(GDM1_BASE + 0x40)
+#define FE_CPORT_PAD			BIT(26)
+#define FE_CPORT_PORT_XFC_MASK		BIT(25)
+#define FE_CPORT_QUEUE_XFC_MASK		BIT(24)
+
+#define REG_FE_GDM_MIB_CLEAR(_n)	(GDM_BASE(_n) + 0xf0)
+#define FE_GDM_MIB_RX_CLEAR_MASK	BIT(1)
+#define FE_GDM_MIB_TX_CLEAR_MASK	BIT(0)
+
+#define REG_FE_GDM_MIB_CFG(_n)		(GDM_BASE(_n) + 0xf4)
+#define FE_STRICT_RFC2819_MODE_MASK	BIT(31)
+#define FE_GDM_TX_MIB_SPLIT_EN_MASK	BIT(17)
+#define FE_GDM_RX_MIB_SPLIT_EN_MASK	BIT(16)
+#define FE_TX_MIB_ID_MASK		GENMASK(15, 8)
+#define FE_RX_MIB_ID_MASK		GENMASK(7, 0)
+
+#define REG_FE_GDM_TX_OK_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x104)
+#define REG_FE_GDM_TX_OK_BYTE_CNT_L(_n)		(GDM_BASE(_n) + 0x10c)
+#define REG_FE_GDM_TX_ETH_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x110)
+#define REG_FE_GDM_TX_ETH_BYTE_CNT_L(_n)	(GDM_BASE(_n) + 0x114)
+#define REG_FE_GDM_TX_ETH_DROP_CNT(_n)		(GDM_BASE(_n) + 0x118)
+#define REG_FE_GDM_TX_ETH_BC_CNT(_n)		(GDM_BASE(_n) + 0x11c)
+#define REG_FE_GDM_TX_ETH_MC_CNT(_n)		(GDM_BASE(_n) + 0x120)
+#define REG_FE_GDM_TX_ETH_RUNT_CNT(_n)		(GDM_BASE(_n) + 0x124)
+#define REG_FE_GDM_TX_ETH_LONG_CNT(_n)		(GDM_BASE(_n) + 0x128)
+#define REG_FE_GDM_TX_ETH_E64_CNT_L(_n)		(GDM_BASE(_n) + 0x12c)
+#define REG_FE_GDM_TX_ETH_L64_CNT_L(_n)		(GDM_BASE(_n) + 0x130)
+#define REG_FE_GDM_TX_ETH_L127_CNT_L(_n)	(GDM_BASE(_n) + 0x134)
+#define REG_FE_GDM_TX_ETH_L255_CNT_L(_n)	(GDM_BASE(_n) + 0x138)
+#define REG_FE_GDM_TX_ETH_L511_CNT_L(_n)	(GDM_BASE(_n) + 0x13c)
+#define REG_FE_GDM_TX_ETH_L1023_CNT_L(_n)	(GDM_BASE(_n) + 0x140)
+
+#define REG_FE_GDM_RX_OK_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x148)
+#define REG_FE_GDM_RX_FC_DROP_CNT(_n)		(GDM_BASE(_n) + 0x14c)
+#define REG_FE_GDM_RX_RC_DROP_CNT(_n)		(GDM_BASE(_n) + 0x150)
+#define REG_FE_GDM_RX_OVERFLOW_DROP_CNT(_n)	(GDM_BASE(_n) + 0x154)
+#define REG_FE_GDM_RX_ERROR_DROP_CNT(_n)	(GDM_BASE(_n) + 0x158)
+#define REG_FE_GDM_RX_OK_BYTE_CNT_L(_n)		(GDM_BASE(_n) + 0x15c)
+#define REG_FE_GDM_RX_ETH_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x160)
+#define REG_FE_GDM_RX_ETH_BYTE_CNT_L(_n)	(GDM_BASE(_n) + 0x164)
+#define REG_FE_GDM_RX_ETH_DROP_CNT(_n)		(GDM_BASE(_n) + 0x168)
+#define REG_FE_GDM_RX_ETH_BC_CNT(_n)		(GDM_BASE(_n) + 0x16c)
+#define REG_FE_GDM_RX_ETH_MC_CNT(_n)		(GDM_BASE(_n) + 0x170)
+#define REG_FE_GDM_RX_ETH_CRC_ERR_CNT(_n)	(GDM_BASE(_n) + 0x174)
+#define REG_FE_GDM_RX_ETH_FRAG_CNT(_n)		(GDM_BASE(_n) + 0x178)
+#define REG_FE_GDM_RX_ETH_JABBER_CNT(_n)	(GDM_BASE(_n) + 0x17c)
+#define REG_FE_GDM_RX_ETH_RUNT_CNT(_n)		(GDM_BASE(_n) + 0x180)
+#define REG_FE_GDM_RX_ETH_LONG_CNT(_n)		(GDM_BASE(_n) + 0x184)
+#define REG_FE_GDM_RX_ETH_E64_CNT_L(_n)		(GDM_BASE(_n) + 0x188)
+#define REG_FE_GDM_RX_ETH_L64_CNT_L(_n)		(GDM_BASE(_n) + 0x18c)
+#define REG_FE_GDM_RX_ETH_L127_CNT_L(_n)	(GDM_BASE(_n) + 0x190)
+#define REG_FE_GDM_RX_ETH_L255_CNT_L(_n)	(GDM_BASE(_n) + 0x194)
+#define REG_FE_GDM_RX_ETH_L511_CNT_L(_n)	(GDM_BASE(_n) + 0x198)
+#define REG_FE_GDM_RX_ETH_L1023_CNT_L(_n)	(GDM_BASE(_n) + 0x19c)
+
+#define REG_GDM_SRC_PORT_SET(_n)		(GDM_BASE(_n) + 0x23c)
+#define GDM_SPORT_OFF2_MASK			GENMASK(19, 16)
+#define GDM_SPORT_OFF1_MASK			GENMASK(15, 12)
+#define GDM_SPORT_OFF0_MASK			GENMASK(11, 8)
+
+#define REG_FE_GDM_TX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x280)
+#define REG_FE_GDM_TX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x284)
+#define REG_FE_GDM_TX_ETH_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x288)
+#define REG_FE_GDM_TX_ETH_BYTE_CNT_H(_n)	(GDM_BASE(_n) + 0x28c)
+
+#define REG_FE_GDM_RX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x290)
+#define REG_FE_GDM_RX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x294)
+#define REG_FE_GDM_RX_ETH_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x298)
+#define REG_FE_GDM_RX_ETH_BYTE_CNT_H(_n)	(GDM_BASE(_n) + 0x29c)
+#define REG_FE_GDM_TX_ETH_E64_CNT_H(_n)		(GDM_BASE(_n) + 0x2b8)
+#define REG_FE_GDM_TX_ETH_L64_CNT_H(_n)		(GDM_BASE(_n) + 0x2bc)
+#define REG_FE_GDM_TX_ETH_L127_CNT_H(_n)	(GDM_BASE(_n) + 0x2c0)
+#define REG_FE_GDM_TX_ETH_L255_CNT_H(_n)	(GDM_BASE(_n) + 0x2c4)
+#define REG_FE_GDM_TX_ETH_L511_CNT_H(_n)	(GDM_BASE(_n) + 0x2c8)
+#define REG_FE_GDM_TX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2cc)
+#define REG_FE_GDM_RX_ETH_E64_CNT_H(_n)		(GDM_BASE(_n) + 0x2e8)
+#define REG_FE_GDM_RX_ETH_L64_CNT_H(_n)		(GDM_BASE(_n) + 0x2ec)
+#define REG_FE_GDM_RX_ETH_L127_CNT_H(_n)	(GDM_BASE(_n) + 0x2f0)
+#define REG_FE_GDM_RX_ETH_L255_CNT_H(_n)	(GDM_BASE(_n) + 0x2f4)
+#define REG_FE_GDM_RX_ETH_L511_CNT_H(_n)	(GDM_BASE(_n) + 0x2f8)
+#define REG_FE_GDM_RX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2fc)
+
+#define REG_PPE_GLO_CFG(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x200)
+#define PPE_GLO_CFG_BUSY_MASK			BIT(31)
+#define PPE_GLO_CFG_FLOW_DROP_UPDATE_MASK	BIT(9)
+#define PPE_GLO_CFG_PSE_HASH_OFS_MASK		BIT(6)
+#define PPE_GLO_CFG_PPE_BSWAP_MASK		BIT(5)
+#define PPE_GLO_CFG_TTL_DROP_MASK		BIT(4)
+#define PPE_GLO_CFG_IP4_CS_DROP_MASK		BIT(3)
+#define PPE_GLO_CFG_IP4_L4_CS_DROP_MASK		BIT(2)
+#define PPE_GLO_CFG_EN_MASK			BIT(0)
+
+#define REG_PPE_PPE_FLOW_CFG(_n)		(((_n) ? PPE2_BASE : PPE1_BASE) + 0x204)
+#define PPE_FLOW_CFG_IP6_HASH_GRE_KEY_MASK	BIT(20)
+#define PPE_FLOW_CFG_IP4_HASH_GRE_KEY_MASK	BIT(19)
+#define PPE_FLOW_CFG_IP4_HASH_FLOW_LABEL_MASK	BIT(18)
+#define PPE_FLOW_CFG_IP4_NAT_FRAG_MASK		BIT(17)
+#define PPE_FLOW_CFG_IP_PROTO_BLACKLIST_MASK	BIT(16)
+#define PPE_FLOW_CFG_IP4_DSLITE_MASK		BIT(14)
+#define PPE_FLOW_CFG_IP4_NAPT_MASK		BIT(13)
+#define PPE_FLOW_CFG_IP4_NAT_MASK		BIT(12)
+#define PPE_FLOW_CFG_IP6_6RD_MASK		BIT(10)
+#define PPE_FLOW_CFG_IP6_5T_ROUTE_MASK		BIT(9)
+#define PPE_FLOW_CFG_IP6_3T_ROUTE_MASK		BIT(8)
+#define PPE_FLOW_CFG_IP4_UDP_FRAG_MASK		BIT(7)
+#define PPE_FLOW_CFG_IP4_TCP_FRAG_MASK		BIT(6)
+
+#define REG_PPE_IP_PROTO_CHK(_n)		(((_n) ? PPE2_BASE : PPE1_BASE) + 0x208)
+#define PPE_IP_PROTO_CHK_IPV4_MASK		GENMASK(31, 16)
+#define PPE_IP_PROTO_CHK_IPV6_MASK		GENMASK(15, 0)
+
+#define REG_PPE_TB_CFG(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x21c)
+#define PPE_SRAM_TB_NUM_ENTRY_MASK		GENMASK(26, 24)
+#define PPE_TB_CFG_KEEPALIVE_MASK		GENMASK(13, 12)
+#define PPE_TB_CFG_AGE_TCP_FIN_MASK		BIT(11)
+#define PPE_TB_CFG_AGE_UDP_MASK			BIT(10)
+#define PPE_TB_CFG_AGE_TCP_MASK			BIT(9)
+#define PPE_TB_CFG_AGE_UNBIND_MASK		BIT(8)
+#define PPE_TB_CFG_AGE_NON_L4_MASK		BIT(7)
+#define PPE_TB_CFG_AGE_PREBIND_MASK		BIT(6)
+#define PPE_TB_CFG_SEARCH_MISS_MASK		GENMASK(5, 4)
+#define PPE_TB_ENTRY_SIZE_MASK			BIT(3)
+#define PPE_DRAM_TB_NUM_ENTRY_MASK		GENMASK(2, 0)
+
+#define REG_PPE_TB_BASE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x220)
+
+#define REG_PPE_BIND_RATE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x228)
+#define PPE_BIND_RATE_L2B_BIND_MASK		GENMASK(31, 16)
+#define PPE_BIND_RATE_BIND_MASK			GENMASK(15, 0)
+
+#define REG_PPE_BIND_LIMIT0(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x22c)
+#define PPE_BIND_LIMIT0_HALF_MASK		GENMASK(29, 16)
+#define PPE_BIND_LIMIT0_QUARTER_MASK		GENMASK(13, 0)
+
+#define REG_PPE_BIND_LIMIT1(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x230)
+#define PPE_BIND_LIMIT1_NON_L4_MASK		GENMASK(23, 16)
+#define PPE_BIND_LIMIT1_FULL_MASK		GENMASK(13, 0)
+
+#define REG_PPE_BND_AGE0(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x23c)
+#define PPE_BIND_AGE0_DELTA_NON_L4		GENMASK(30, 16)
+#define PPE_BIND_AGE0_DELTA_UDP			GENMASK(14, 0)
+
+#define REG_PPE_UNBIND_AGE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x238)
+#define PPE_UNBIND_AGE_MIN_PACKETS_MASK		GENMASK(31, 16)
+#define PPE_UNBIND_AGE_DELTA_MASK		GENMASK(7, 0)
+
+#define REG_PPE_BND_AGE1(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x240)
+#define PPE_BIND_AGE1_DELTA_TCP_FIN		GENMASK(30, 16)
+#define PPE_BIND_AGE1_DELTA_TCP			GENMASK(14, 0)
+
+#define REG_PPE_HASH_SEED(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x244)
+#define PPE_HASH_SEED				0x12345678
+
+#define REG_PPE_DFT_CPORT0(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x248)
+#define DFT_CPORT_MASK(_n)			GENMASK(3 + ((_n) << 2), ((_n) << 2))
+
+#define REG_PPE_DFT_CPORT1(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x24c)
+
+#define REG_PPE_TB_HASH_CFG(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x250)
+#define PPE_DRAM_HASH1_MODE_MASK		GENMASK(31, 28)
+#define PPE_DRAM_HASH1_EN_MASK			BIT(24)
+#define PPE_DRAM_HASH0_MODE_MASK		GENMASK(23, 20)
+#define PPE_DRAM_TABLE_EN_MASK			BIT(16)
+#define PPE_SRAM_HASH1_MODE_MASK		GENMASK(15, 12)
+#define PPE_SRAM_HASH1_EN_MASK			BIT(8)
+#define PPE_SRAM_HASH0_MODE_MASK		GENMASK(7, 4)
+#define PPE_SRAM_TABLE_EN_MASK			BIT(0)
+
+#define REG_PPE_MTU_BASE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x304)
+#define REG_PPE_MTU(_m, _n)			(REG_PPE_MTU_BASE(_m) + ((_n) << 2))
+#define FP1_EGRESS_MTU_MASK			GENMASK(29, 16)
+#define FP0_EGRESS_MTU_MASK			GENMASK(13, 0)
+
+#define REG_PPE_RAM_CTRL(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x31c)
+#define PPE_SRAM_CTRL_ACK_MASK			BIT(31)
+#define PPE_SRAM_CTRL_DUAL_SUCESS_MASK		BIT(30)
+#define PPE_SRAM_CTRL_ENTRY_MASK		GENMASK(23, 8)
+#define PPE_SRAM_WR_DUAL_DIRECTION_MASK		BIT(2)
+#define PPE_SRAM_CTRL_WR_MASK			BIT(1)
+#define PPE_SRAM_CTRL_REQ_MASK			BIT(0)
+
+#define REG_PPE_RAM_BASE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x320)
+#define REG_PPE_RAM_ENTRY(_m, _n)		(REG_PPE_RAM_BASE(_m) + ((_n) << 2))
+
+#define REG_UPDMEM_CTRL(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x370)
+#define PPE_UPDMEM_ACK_MASK			BIT(31)
+#define PPE_UPDMEM_ADDR_MASK			GENMASK(11, 8)
+#define PPE_UPDMEM_OFFSET_MASK			GENMASK(7, 4)
+#define PPE_UPDMEM_SEL_MASK			GENMASK(3, 2)
+#define PPE_UPDMEM_WR_MASK			BIT(1)
+#define PPE_UPDMEM_REQ_MASK			BIT(0)
+
+#define REG_UPDMEM_DATA(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x374)
+
+#define REG_IP_FRAG_FP			0x2010
+#define IP_ASSEMBLE_PORT_MASK		GENMASK(24, 21)
+#define IP_ASSEMBLE_NBQ_MASK		GENMASK(20, 16)
+#define IP_FRAGMENT_PORT_MASK		GENMASK(8, 5)
+#define IP_FRAGMENT_NBQ_MASK		GENMASK(4, 0)
+
+#define REG_MC_VLAN_EN			0x2100
+#define MC_VLAN_EN_MASK			BIT(0)
+
+#define REG_MC_VLAN_CFG			0x2104
+#define MC_VLAN_CFG_CMD_DONE_MASK	BIT(31)
+#define MC_VLAN_CFG_TABLE_ID_MASK	GENMASK(21, 16)
+#define MC_VLAN_CFG_PORT_ID_MASK	GENMASK(11, 8)
+#define MC_VLAN_CFG_TABLE_SEL_MASK	BIT(4)
+#define MC_VLAN_CFG_RW_MASK		BIT(0)
+
+#define REG_MC_VLAN_DATA		0x2108
+
+#define REG_SP_DFT_CPORT(_n)		(0x20e0 + ((_n) << 2))
+#define SP_CPORT_DFT_MASK		GENMASK(2, 0)
+#define SP_CPORT_MASK(_n)		GENMASK(3 + ((_n) << 2), ((_n) << 2))
+
+#define REG_SRC_PORT_FC_MAP6		0x2298
+#define FC_ID_OF_SRC_PORT27_MASK	GENMASK(28, 24)
+#define FC_ID_OF_SRC_PORT26_MASK	GENMASK(20, 16)
+#define FC_ID_OF_SRC_PORT25_MASK	GENMASK(12, 8)
+#define FC_ID_OF_SRC_PORT24_MASK	GENMASK(4, 0)
+
+#define REG_CDM5_RX_OQ1_DROP_CNT	0x29d4
+
+/* QDMA */
+#define REG_QDMA_GLOBAL_CFG			0x0004
+#define GLOBAL_CFG_RX_2B_OFFSET_MASK		BIT(31)
+#define GLOBAL_CFG_DMA_PREFERENCE_MASK		GENMASK(30, 29)
+#define GLOBAL_CFG_CPU_TXR_RR_MASK		BIT(28)
+#define GLOBAL_CFG_DSCP_BYTE_SWAP_MASK		BIT(27)
+#define GLOBAL_CFG_PAYLOAD_BYTE_SWAP_MASK	BIT(26)
+#define GLOBAL_CFG_MULTICAST_MODIFY_FP_MASK	BIT(25)
+#define GLOBAL_CFG_OAM_MODIFY_MASK		BIT(24)
+#define GLOBAL_CFG_RESET_MASK			BIT(23)
+#define GLOBAL_CFG_RESET_DONE_MASK		BIT(22)
+#define GLOBAL_CFG_MULTICAST_EN_MASK		BIT(21)
+#define GLOBAL_CFG_IRQ1_EN_MASK			BIT(20)
+#define GLOBAL_CFG_IRQ0_EN_MASK			BIT(19)
+#define GLOBAL_CFG_LOOPCNT_EN_MASK		BIT(18)
+#define GLOBAL_CFG_RD_BYPASS_WR_MASK		BIT(17)
+#define GLOBAL_CFG_QDMA_LOOPBACK_MASK		BIT(16)
+#define GLOBAL_CFG_LPBK_RXQ_SEL_MASK		GENMASK(13, 8)
+#define GLOBAL_CFG_CHECK_DONE_MASK		BIT(7)
+#define GLOBAL_CFG_TX_WB_DONE_MASK		BIT(6)
+#define GLOBAL_CFG_MAX_ISSUE_NUM_MASK		GENMASK(5, 4)
+#define GLOBAL_CFG_RX_DMA_BUSY_MASK		BIT(3)
+#define GLOBAL_CFG_RX_DMA_EN_MASK		BIT(2)
+#define GLOBAL_CFG_TX_DMA_BUSY_MASK		BIT(1)
+#define GLOBAL_CFG_TX_DMA_EN_MASK		BIT(0)
+
+#define REG_FWD_DSCP_BASE			0x0010
+#define REG_FWD_BUF_BASE			0x0014
+
+#define REG_HW_FWD_DSCP_CFG			0x0018
+#define HW_FWD_DSCP_PAYLOAD_SIZE_MASK		GENMASK(29, 28)
+#define HW_FWD_DSCP_SCATTER_LEN_MASK		GENMASK(17, 16)
+#define HW_FWD_DSCP_MIN_SCATTER_LEN_MASK	GENMASK(15, 0)
+
+#define REG_INT_STATUS(_n)		\
+	(((_n) == 4) ? 0x0730 :		\
+	 ((_n) == 3) ? 0x0724 :		\
+	 ((_n) == 2) ? 0x0720 :		\
+	 ((_n) == 1) ? 0x0024 : 0x0020)
+
+#define REG_INT_ENABLE(_b, _n)		\
+	(((_n) == 4) ? 0x0750 + ((_b) << 5) :	\
+	 ((_n) == 3) ? 0x0744 + ((_b) << 5) :	\
+	 ((_n) == 2) ? 0x0740 + ((_b) << 5) :	\
+	 ((_n) == 1) ? 0x002c + ((_b) << 3) :	\
+		       0x0028 + ((_b) << 3))
+
+/* QDMA_CSR_INT_ENABLE1 */
+#define RX15_COHERENT_INT_MASK		BIT(31)
+#define RX14_COHERENT_INT_MASK		BIT(30)
+#define RX13_COHERENT_INT_MASK		BIT(29)
+#define RX12_COHERENT_INT_MASK		BIT(28)
+#define RX11_COHERENT_INT_MASK		BIT(27)
+#define RX10_COHERENT_INT_MASK		BIT(26)
+#define RX9_COHERENT_INT_MASK		BIT(25)
+#define RX8_COHERENT_INT_MASK		BIT(24)
+#define RX7_COHERENT_INT_MASK		BIT(23)
+#define RX6_COHERENT_INT_MASK		BIT(22)
+#define RX5_COHERENT_INT_MASK		BIT(21)
+#define RX4_COHERENT_INT_MASK		BIT(20)
+#define RX3_COHERENT_INT_MASK		BIT(19)
+#define RX2_COHERENT_INT_MASK		BIT(18)
+#define RX1_COHERENT_INT_MASK		BIT(17)
+#define RX0_COHERENT_INT_MASK		BIT(16)
+#define TX7_COHERENT_INT_MASK		BIT(15)
+#define TX6_COHERENT_INT_MASK		BIT(14)
+#define TX5_COHERENT_INT_MASK		BIT(13)
+#define TX4_COHERENT_INT_MASK		BIT(12)
+#define TX3_COHERENT_INT_MASK		BIT(11)
+#define TX2_COHERENT_INT_MASK		BIT(10)
+#define TX1_COHERENT_INT_MASK		BIT(9)
+#define TX0_COHERENT_INT_MASK		BIT(8)
+#define CNT_OVER_FLOW_INT_MASK		BIT(7)
+#define IRQ1_FULL_INT_MASK		BIT(5)
+#define IRQ1_INT_MASK			BIT(4)
+#define HWFWD_DSCP_LOW_INT_MASK		BIT(3)
+#define HWFWD_DSCP_EMPTY_INT_MASK	BIT(2)
+#define IRQ0_FULL_INT_MASK		BIT(1)
+#define IRQ0_INT_MASK			BIT(0)
+
+#define RX_COHERENT_LOW_INT_MASK				\
+	(RX15_COHERENT_INT_MASK | RX14_COHERENT_INT_MASK |	\
+	 RX13_COHERENT_INT_MASK | RX12_COHERENT_INT_MASK |	\
+	 RX11_COHERENT_INT_MASK | RX10_COHERENT_INT_MASK |	\
+	 RX9_COHERENT_INT_MASK | RX8_COHERENT_INT_MASK |	\
+	 RX7_COHERENT_INT_MASK | RX6_COHERENT_INT_MASK |	\
+	 RX5_COHERENT_INT_MASK | RX4_COHERENT_INT_MASK |	\
+	 RX3_COHERENT_INT_MASK | RX2_COHERENT_INT_MASK |	\
+	 RX1_COHERENT_INT_MASK | RX0_COHERENT_INT_MASK)
+
+#define RX_COHERENT_LOW_OFFSET	__ffs(RX_COHERENT_LOW_INT_MASK)
+#define INT_RX0_MASK(_n)					\
+	(((_n) << RX_COHERENT_LOW_OFFSET) & RX_COHERENT_LOW_INT_MASK)
+
+#define TX_COHERENT_LOW_INT_MASK				\
+	(TX7_COHERENT_INT_MASK | TX6_COHERENT_INT_MASK |	\
+	 TX5_COHERENT_INT_MASK | TX4_COHERENT_INT_MASK |	\
+	 TX3_COHERENT_INT_MASK | TX2_COHERENT_INT_MASK |	\
+	 TX1_COHERENT_INT_MASK | TX0_COHERENT_INT_MASK)
+
+#define TX_DONE_INT_MASK(_n)					\
+	((_n) ? IRQ1_INT_MASK | IRQ1_FULL_INT_MASK		\
+	      : IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
+
+#define INT_TX_MASK						\
+	(IRQ1_INT_MASK | IRQ1_FULL_INT_MASK |			\
+	 IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
+
+/* QDMA_CSR_INT_ENABLE2 */
+#define RX15_NO_CPU_DSCP_INT_MASK	BIT(31)
+#define RX14_NO_CPU_DSCP_INT_MASK	BIT(30)
+#define RX13_NO_CPU_DSCP_INT_MASK	BIT(29)
+#define RX12_NO_CPU_DSCP_INT_MASK	BIT(28)
+#define RX11_NO_CPU_DSCP_INT_MASK	BIT(27)
+#define RX10_NO_CPU_DSCP_INT_MASK	BIT(26)
+#define RX9_NO_CPU_DSCP_INT_MASK	BIT(25)
+#define RX8_NO_CPU_DSCP_INT_MASK	BIT(24)
+#define RX7_NO_CPU_DSCP_INT_MASK	BIT(23)
+#define RX6_NO_CPU_DSCP_INT_MASK	BIT(22)
+#define RX5_NO_CPU_DSCP_INT_MASK	BIT(21)
+#define RX4_NO_CPU_DSCP_INT_MASK	BIT(20)
+#define RX3_NO_CPU_DSCP_INT_MASK	BIT(19)
+#define RX2_NO_CPU_DSCP_INT_MASK	BIT(18)
+#define RX1_NO_CPU_DSCP_INT_MASK	BIT(17)
+#define RX0_NO_CPU_DSCP_INT_MASK	BIT(16)
+#define RX15_DONE_INT_MASK		BIT(15)
+#define RX14_DONE_INT_MASK		BIT(14)
+#define RX13_DONE_INT_MASK		BIT(13)
+#define RX12_DONE_INT_MASK		BIT(12)
+#define RX11_DONE_INT_MASK		BIT(11)
+#define RX10_DONE_INT_MASK		BIT(10)
+#define RX9_DONE_INT_MASK		BIT(9)
+#define RX8_DONE_INT_MASK		BIT(8)
+#define RX7_DONE_INT_MASK		BIT(7)
+#define RX6_DONE_INT_MASK		BIT(6)
+#define RX5_DONE_INT_MASK		BIT(5)
+#define RX4_DONE_INT_MASK		BIT(4)
+#define RX3_DONE_INT_MASK		BIT(3)
+#define RX2_DONE_INT_MASK		BIT(2)
+#define RX1_DONE_INT_MASK		BIT(1)
+#define RX0_DONE_INT_MASK		BIT(0)
+
+#define RX_NO_CPU_DSCP_LOW_INT_MASK					\
+	(RX15_NO_CPU_DSCP_INT_MASK | RX14_NO_CPU_DSCP_INT_MASK |	\
+	 RX13_NO_CPU_DSCP_INT_MASK | RX12_NO_CPU_DSCP_INT_MASK |	\
+	 RX11_NO_CPU_DSCP_INT_MASK | RX10_NO_CPU_DSCP_INT_MASK |	\
+	 RX9_NO_CPU_DSCP_INT_MASK | RX8_NO_CPU_DSCP_INT_MASK |		\
+	 RX7_NO_CPU_DSCP_INT_MASK | RX6_NO_CPU_DSCP_INT_MASK |		\
+	 RX5_NO_CPU_DSCP_INT_MASK | RX4_NO_CPU_DSCP_INT_MASK |		\
+	 RX3_NO_CPU_DSCP_INT_MASK | RX2_NO_CPU_DSCP_INT_MASK |		\
+	 RX1_NO_CPU_DSCP_INT_MASK | RX0_NO_CPU_DSCP_INT_MASK)
+
+#define RX_DONE_LOW_INT_MASK				\
+	(RX15_DONE_INT_MASK | RX14_DONE_INT_MASK |	\
+	 RX13_DONE_INT_MASK | RX12_DONE_INT_MASK |	\
+	 RX11_DONE_INT_MASK | RX10_DONE_INT_MASK |	\
+	 RX9_DONE_INT_MASK | RX8_DONE_INT_MASK |	\
+	 RX7_DONE_INT_MASK | RX6_DONE_INT_MASK |	\
+	 RX5_DONE_INT_MASK | RX4_DONE_INT_MASK |	\
+	 RX3_DONE_INT_MASK | RX2_DONE_INT_MASK |	\
+	 RX1_DONE_INT_MASK | RX0_DONE_INT_MASK)
+
+#define RX_NO_CPU_DSCP_LOW_OFFSET	__ffs(RX_NO_CPU_DSCP_LOW_INT_MASK)
+#define INT_RX1_MASK(_n)							\
+	((((_n) << RX_NO_CPU_DSCP_LOW_OFFSET) & RX_NO_CPU_DSCP_LOW_INT_MASK) |	\
+	 (RX_DONE_LOW_INT_MASK & (_n)))
+
+/* QDMA_CSR_INT_ENABLE3 */
+#define RX31_NO_CPU_DSCP_INT_MASK	BIT(31)
+#define RX30_NO_CPU_DSCP_INT_MASK	BIT(30)
+#define RX29_NO_CPU_DSCP_INT_MASK	BIT(29)
+#define RX28_NO_CPU_DSCP_INT_MASK	BIT(28)
+#define RX27_NO_CPU_DSCP_INT_MASK	BIT(27)
+#define RX26_NO_CPU_DSCP_INT_MASK	BIT(26)
+#define RX25_NO_CPU_DSCP_INT_MASK	BIT(25)
+#define RX24_NO_CPU_DSCP_INT_MASK	BIT(24)
+#define RX23_NO_CPU_DSCP_INT_MASK	BIT(23)
+#define RX22_NO_CPU_DSCP_INT_MASK	BIT(22)
+#define RX21_NO_CPU_DSCP_INT_MASK	BIT(21)
+#define RX20_NO_CPU_DSCP_INT_MASK	BIT(20)
+#define RX19_NO_CPU_DSCP_INT_MASK	BIT(19)
+#define RX18_NO_CPU_DSCP_INT_MASK	BIT(18)
+#define RX17_NO_CPU_DSCP_INT_MASK	BIT(17)
+#define RX16_NO_CPU_DSCP_INT_MASK	BIT(16)
+#define RX31_DONE_INT_MASK		BIT(15)
+#define RX30_DONE_INT_MASK		BIT(14)
+#define RX29_DONE_INT_MASK		BIT(13)
+#define RX28_DONE_INT_MASK		BIT(12)
+#define RX27_DONE_INT_MASK		BIT(11)
+#define RX26_DONE_INT_MASK		BIT(10)
+#define RX25_DONE_INT_MASK		BIT(9)
+#define RX24_DONE_INT_MASK		BIT(8)
+#define RX23_DONE_INT_MASK		BIT(7)
+#define RX22_DONE_INT_MASK		BIT(6)
+#define RX21_DONE_INT_MASK		BIT(5)
+#define RX20_DONE_INT_MASK		BIT(4)
+#define RX19_DONE_INT_MASK		BIT(3)
+#define RX18_DONE_INT_MASK		BIT(2)
+#define RX17_DONE_INT_MASK		BIT(1)
+#define RX16_DONE_INT_MASK		BIT(0)
+
+#define RX_NO_CPU_DSCP_HIGH_INT_MASK					\
+	(RX31_NO_CPU_DSCP_INT_MASK | RX30_NO_CPU_DSCP_INT_MASK |	\
+	 RX29_NO_CPU_DSCP_INT_MASK | RX28_NO_CPU_DSCP_INT_MASK |	\
+	 RX27_NO_CPU_DSCP_INT_MASK | RX26_NO_CPU_DSCP_INT_MASK |	\
+	 RX25_NO_CPU_DSCP_INT_MASK | RX24_NO_CPU_DSCP_INT_MASK |	\
+	 RX23_NO_CPU_DSCP_INT_MASK | RX22_NO_CPU_DSCP_INT_MASK |	\
+	 RX21_NO_CPU_DSCP_INT_MASK | RX20_NO_CPU_DSCP_INT_MASK |	\
+	 RX19_NO_CPU_DSCP_INT_MASK | RX18_NO_CPU_DSCP_INT_MASK |	\
+	 RX17_NO_CPU_DSCP_INT_MASK | RX16_NO_CPU_DSCP_INT_MASK)
+
+#define RX_DONE_HIGH_INT_MASK				\
+	(RX31_DONE_INT_MASK | RX30_DONE_INT_MASK |	\
+	 RX29_DONE_INT_MASK | RX28_DONE_INT_MASK |	\
+	 RX27_DONE_INT_MASK | RX26_DONE_INT_MASK |	\
+	 RX25_DONE_INT_MASK | RX24_DONE_INT_MASK |	\
+	 RX23_DONE_INT_MASK | RX22_DONE_INT_MASK |	\
+	 RX21_DONE_INT_MASK | RX20_DONE_INT_MASK |	\
+	 RX19_DONE_INT_MASK | RX18_DONE_INT_MASK |	\
+	 RX17_DONE_INT_MASK | RX16_DONE_INT_MASK)
+
+#define RX_DONE_HIGH_OFFSET	fls(RX_DONE_HIGH_INT_MASK)
+#define RX_DONE_INT_MASK	\
+	((RX_DONE_HIGH_INT_MASK << RX_DONE_HIGH_OFFSET) | RX_DONE_LOW_INT_MASK)
+
+#define INT_RX2_MASK(_n)				\
+	((RX_NO_CPU_DSCP_HIGH_INT_MASK & (_n)) |	\
+	 (((_n) >> RX_DONE_HIGH_OFFSET) & RX_DONE_HIGH_INT_MASK))
+
+/* QDMA_CSR_INT_ENABLE4 */
+#define RX31_COHERENT_INT_MASK		BIT(31)
+#define RX30_COHERENT_INT_MASK		BIT(30)
+#define RX29_COHERENT_INT_MASK		BIT(29)
+#define RX28_COHERENT_INT_MASK		BIT(28)
+#define RX27_COHERENT_INT_MASK		BIT(27)
+#define RX26_COHERENT_INT_MASK		BIT(26)
+#define RX25_COHERENT_INT_MASK		BIT(25)
+#define RX24_COHERENT_INT_MASK		BIT(24)
+#define RX23_COHERENT_INT_MASK		BIT(23)
+#define RX22_COHERENT_INT_MASK		BIT(22)
+#define RX21_COHERENT_INT_MASK		BIT(21)
+#define RX20_COHERENT_INT_MASK		BIT(20)
+#define RX19_COHERENT_INT_MASK		BIT(19)
+#define RX18_COHERENT_INT_MASK		BIT(18)
+#define RX17_COHERENT_INT_MASK		BIT(17)
+#define RX16_COHERENT_INT_MASK		BIT(16)
+
+#define RX_COHERENT_HIGH_INT_MASK				\
+	(RX31_COHERENT_INT_MASK | RX30_COHERENT_INT_MASK |	\
+	 RX29_COHERENT_INT_MASK | RX28_COHERENT_INT_MASK |	\
+	 RX27_COHERENT_INT_MASK | RX26_COHERENT_INT_MASK |	\
+	 RX25_COHERENT_INT_MASK | RX24_COHERENT_INT_MASK |	\
+	 RX23_COHERENT_INT_MASK | RX22_COHERENT_INT_MASK |	\
+	 RX21_COHERENT_INT_MASK | RX20_COHERENT_INT_MASK |	\
+	 RX19_COHERENT_INT_MASK | RX18_COHERENT_INT_MASK |	\
+	 RX17_COHERENT_INT_MASK | RX16_COHERENT_INT_MASK)
+
+#define INT_RX3_MASK(_n)	(RX_COHERENT_HIGH_INT_MASK & (_n))
+
+/* QDMA_CSR_INT_ENABLE5 */
+#define TX31_COHERENT_INT_MASK		BIT(31)
+#define TX30_COHERENT_INT_MASK		BIT(30)
+#define TX29_COHERENT_INT_MASK		BIT(29)
+#define TX28_COHERENT_INT_MASK		BIT(28)
+#define TX27_COHERENT_INT_MASK		BIT(27)
+#define TX26_COHERENT_INT_MASK		BIT(26)
+#define TX25_COHERENT_INT_MASK		BIT(25)
+#define TX24_COHERENT_INT_MASK		BIT(24)
+#define TX23_COHERENT_INT_MASK		BIT(23)
+#define TX22_COHERENT_INT_MASK		BIT(22)
+#define TX21_COHERENT_INT_MASK		BIT(21)
+#define TX20_COHERENT_INT_MASK		BIT(20)
+#define TX19_COHERENT_INT_MASK		BIT(19)
+#define TX18_COHERENT_INT_MASK		BIT(18)
+#define TX17_COHERENT_INT_MASK		BIT(17)
+#define TX16_COHERENT_INT_MASK		BIT(16)
+#define TX15_COHERENT_INT_MASK		BIT(15)
+#define TX14_COHERENT_INT_MASK		BIT(14)
+#define TX13_COHERENT_INT_MASK		BIT(13)
+#define TX12_COHERENT_INT_MASK		BIT(12)
+#define TX11_COHERENT_INT_MASK		BIT(11)
+#define TX10_COHERENT_INT_MASK		BIT(10)
+#define TX9_COHERENT_INT_MASK		BIT(9)
+#define TX8_COHERENT_INT_MASK		BIT(8)
+
+#define TX_COHERENT_HIGH_INT_MASK				\
+	(TX31_COHERENT_INT_MASK | TX30_COHERENT_INT_MASK |	\
+	 TX29_COHERENT_INT_MASK | TX28_COHERENT_INT_MASK |	\
+	 TX27_COHERENT_INT_MASK | TX26_COHERENT_INT_MASK |	\
+	 TX25_COHERENT_INT_MASK | TX24_COHERENT_INT_MASK |	\
+	 TX23_COHERENT_INT_MASK | TX22_COHERENT_INT_MASK |	\
+	 TX21_COHERENT_INT_MASK | TX20_COHERENT_INT_MASK |	\
+	 TX19_COHERENT_INT_MASK | TX18_COHERENT_INT_MASK |	\
+	 TX17_COHERENT_INT_MASK | TX16_COHERENT_INT_MASK |	\
+	 TX15_COHERENT_INT_MASK | TX14_COHERENT_INT_MASK |	\
+	 TX13_COHERENT_INT_MASK | TX12_COHERENT_INT_MASK |	\
+	 TX11_COHERENT_INT_MASK | TX10_COHERENT_INT_MASK |	\
+	 TX9_COHERENT_INT_MASK | TX8_COHERENT_INT_MASK)
+
+#define REG_TX_IRQ_BASE(_n)		((_n) ? 0x0048 : 0x0050)
+
+#define REG_TX_IRQ_CFG(_n)		((_n) ? 0x004c : 0x0054)
+#define TX_IRQ_THR_MASK			GENMASK(27, 16)
+#define TX_IRQ_DEPTH_MASK		GENMASK(11, 0)
+
+#define REG_IRQ_CLEAR_LEN(_n)		((_n) ? 0x0064 : 0x0058)
+#define IRQ_CLEAR_LEN_MASK		GENMASK(7, 0)
+
+#define REG_IRQ_STATUS(_n)		((_n) ? 0x0068 : 0x005c)
+#define IRQ_ENTRY_LEN_MASK		GENMASK(27, 16)
+#define IRQ_HEAD_IDX_MASK		GENMASK(11, 0)
+
+#define REG_TX_RING_BASE(_n)	\
+	(((_n) < 8) ? 0x0100 + ((_n) << 5) : 0x0b00 + (((_n) - 8) << 5))
+
+#define REG_TX_RING_BLOCKING(_n)	\
+	(((_n) < 8) ? 0x0104 + ((_n) << 5) : 0x0b04 + (((_n) - 8) << 5))
+
+#define TX_RING_IRQ_BLOCKING_MAP_MASK			BIT(6)
+#define TX_RING_IRQ_BLOCKING_CFG_MASK			BIT(4)
+#define TX_RING_IRQ_BLOCKING_TX_DROP_EN_MASK		BIT(2)
+#define TX_RING_IRQ_BLOCKING_MAX_TH_TXRING_EN_MASK	BIT(1)
+#define TX_RING_IRQ_BLOCKING_MIN_TH_TXRING_EN_MASK	BIT(0)
+
+#define REG_TX_CPU_IDX(_n)	\
+	(((_n) < 8) ? 0x0108 + ((_n) << 5) : 0x0b08 + (((_n) - 8) << 5))
+
+#define TX_RING_CPU_IDX_MASK		GENMASK(15, 0)
+
+#define REG_TX_DMA_IDX(_n)	\
+	(((_n) < 8) ? 0x010c + ((_n) << 5) : 0x0b0c + (((_n) - 8) << 5))
+
+#define TX_RING_DMA_IDX_MASK		GENMASK(15, 0)
+
+#define IRQ_RING_IDX_MASK		GENMASK(20, 16)
+#define IRQ_DESC_IDX_MASK		GENMASK(15, 0)
+
+#define REG_RX_RING_BASE(_n)	\
+	(((_n) < 16) ? 0x0200 + ((_n) << 5) : 0x0e00 + (((_n) - 16) << 5))
+
+#define REG_RX_RING_SIZE(_n)	\
+	(((_n) < 16) ? 0x0204 + ((_n) << 5) : 0x0e04 + (((_n) - 16) << 5))
+
+#define RX_RING_THR_MASK		GENMASK(31, 16)
+#define RX_RING_SIZE_MASK		GENMASK(15, 0)
+
+#define REG_RX_CPU_IDX(_n)	\
+	(((_n) < 16) ? 0x0208 + ((_n) << 5) : 0x0e08 + (((_n) - 16) << 5))
+
+#define RX_RING_CPU_IDX_MASK		GENMASK(15, 0)
+
+#define REG_RX_DMA_IDX(_n)	\
+	(((_n) < 16) ? 0x020c + ((_n) << 5) : 0x0e0c + (((_n) - 16) << 5))
+
+#define REG_RX_DELAY_INT_IDX(_n)	\
+	(((_n) < 16) ? 0x0210 + ((_n) << 5) : 0x0e10 + (((_n) - 16) << 5))
+
+#define REG_RX_SCATTER_CFG(_n)	\
+	(((_n) < 16) ? 0x0214 + ((_n) << 5) : 0x0e14 + (((_n) - 16) << 5))
+
+#define RX_DELAY_INT_MASK		GENMASK(15, 0)
+
+#define RX_RING_DMA_IDX_MASK		GENMASK(15, 0)
+
+#define RX_RING_SG_EN_MASK		BIT(0)
+
+#define REG_INGRESS_TRTCM_CFG		0x0070
+#define INGRESS_TRTCM_EN_MASK		BIT(31)
+#define INGRESS_TRTCM_MODE_MASK		BIT(30)
+#define INGRESS_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
+#define INGRESS_FAST_TICK_MASK		GENMASK(15, 0)
+
+#define REG_QUEUE_CLOSE_CFG(_n)		(0x00a0 + ((_n) & 0xfc))
+#define TXQ_DISABLE_CHAN_QUEUE_MASK(_n, _m)	BIT((_m) + (((_n) & 0x3) << 3))
+
+#define REG_TXQ_DIS_CFG_BASE(_n)	((_n) ? 0x20a0 : 0x00a0)
+#define REG_TXQ_DIS_CFG(_n, _m)		(REG_TXQ_DIS_CFG_BASE((_n)) + (_m) << 2)
+
+#define REG_CNTR_CFG(_n)		(0x0400 + ((_n) << 3))
+#define CNTR_EN_MASK			BIT(31)
+#define CNTR_ALL_CHAN_EN_MASK		BIT(30)
+#define CNTR_ALL_QUEUE_EN_MASK		BIT(29)
+#define CNTR_ALL_DSCP_RING_EN_MASK	BIT(28)
+#define CNTR_SRC_MASK			GENMASK(27, 24)
+#define CNTR_DSCP_RING_MASK		GENMASK(20, 16)
+#define CNTR_CHAN_MASK			GENMASK(7, 3)
+#define CNTR_QUEUE_MASK			GENMASK(2, 0)
+
+#define REG_CNTR_VAL(_n)		(0x0404 + ((_n) << 3))
+
+#define REG_LMGR_INIT_CFG		0x1000
+#define LMGR_INIT_START			BIT(31)
+#define LMGR_SRAM_MODE_MASK		BIT(30)
+#define HW_FWD_PKTSIZE_OVERHEAD_MASK	GENMASK(27, 20)
+#define HW_FWD_DESC_NUM_MASK		GENMASK(16, 0)
+
+#define REG_FWD_DSCP_LOW_THR		0x1004
+#define FWD_DSCP_LOW_THR_MASK		GENMASK(17, 0)
+
+#define REG_EGRESS_RATE_METER_CFG		0x100c
+#define EGRESS_RATE_METER_EN_MASK		BIT(31)
+#define EGRESS_RATE_METER_EQ_RATE_EN_MASK	BIT(17)
+#define EGRESS_RATE_METER_WINDOW_SZ_MASK	GENMASK(16, 12)
+#define EGRESS_RATE_METER_TIMESLICE_MASK	GENMASK(10, 0)
+
+#define REG_EGRESS_TRTCM_CFG		0x1010
+#define EGRESS_TRTCM_EN_MASK		BIT(31)
+#define EGRESS_TRTCM_MODE_MASK		BIT(30)
+#define EGRESS_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
+#define EGRESS_FAST_TICK_MASK		GENMASK(15, 0)
+
+#define TRTCM_PARAM_RW_MASK		BIT(31)
+#define TRTCM_PARAM_RW_DONE_MASK	BIT(30)
+#define TRTCM_PARAM_TYPE_MASK		GENMASK(29, 28)
+#define TRTCM_METER_GROUP_MASK		GENMASK(27, 26)
+#define TRTCM_PARAM_INDEX_MASK		GENMASK(23, 17)
+#define TRTCM_PARAM_RATE_TYPE_MASK	BIT(16)
+
+#define REG_TRTCM_CFG_PARAM(_n)		((_n) + 0x4)
+#define REG_TRTCM_DATA_LOW(_n)		((_n) + 0x8)
+#define REG_TRTCM_DATA_HIGH(_n)		((_n) + 0xc)
+
+#define RATE_LIMIT_PARAM_RW_MASK	BIT(31)
+#define RATE_LIMIT_PARAM_RW_DONE_MASK	BIT(30)
+#define RATE_LIMIT_PARAM_TYPE_MASK	GENMASK(29, 28)
+#define RATE_LIMIT_METER_GROUP_MASK	GENMASK(27, 26)
+#define RATE_LIMIT_PARAM_INDEX_MASK	GENMASK(23, 16)
+
+#define REG_TXWRR_MODE_CFG		0x1020
+#define TWRR_WEIGHT_SCALE_MASK		BIT(31)
+#define TWRR_WEIGHT_BASE_MASK		BIT(3)
+
+#define REG_TXWRR_WEIGHT_CFG		0x1024
+#define TWRR_RW_CMD_MASK		BIT(31)
+#define TWRR_RW_CMD_DONE		BIT(30)
+#define TWRR_CHAN_IDX_MASK		GENMASK(23, 19)
+#define TWRR_QUEUE_IDX_MASK		GENMASK(18, 16)
+#define TWRR_VALUE_MASK			GENMASK(15, 0)
+
+#define REG_PSE_BUF_USAGE_CFG		0x1028
+#define PSE_BUF_ESTIMATE_EN_MASK	BIT(29)
+
+#define REG_CHAN_QOS_MODE(_n)		(0x1040 + ((_n) << 2))
+#define CHAN_QOS_MODE_MASK(_n)		GENMASK(2 + ((_n) << 2), (_n) << 2)
+
+#define REG_GLB_TRTCM_CFG		0x1080
+#define GLB_TRTCM_EN_MASK		BIT(31)
+#define GLB_TRTCM_MODE_MASK		BIT(30)
+#define GLB_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
+#define GLB_FAST_TICK_MASK		GENMASK(15, 0)
+
+#define REG_TXQ_CNGST_CFG		0x10a0
+#define TXQ_CNGST_DROP_EN		BIT(31)
+#define TXQ_CNGST_DEI_DROP_EN		BIT(30)
+
+#define REG_SLA_TRTCM_CFG		0x1150
+#define SLA_TRTCM_EN_MASK		BIT(31)
+#define SLA_TRTCM_MODE_MASK		BIT(30)
+#define SLA_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
+#define SLA_FAST_TICK_MASK		GENMASK(15, 0)
+
+/* CTRL */
+#define QDMA_DESC_DONE_MASK		BIT(31)
+#define QDMA_DESC_DROP_MASK		BIT(30) /* tx: drop - rx: overflow */
+#define QDMA_DESC_MORE_MASK		BIT(29) /* more SG elements */
+#define QDMA_DESC_DEI_MASK		BIT(25)
+#define QDMA_DESC_NO_DROP_MASK		BIT(24)
+#define QDMA_DESC_LEN_MASK		GENMASK(15, 0)
+/* DATA */
+#define QDMA_DESC_NEXT_ID_MASK		GENMASK(15, 0)
+/* TX MSG0 */
+#define QDMA_ETH_TXMSG_MIC_IDX_MASK	BIT(30)
+#define QDMA_ETH_TXMSG_SP_TAG_MASK	GENMASK(29, 14)
+#define QDMA_ETH_TXMSG_ICO_MASK		BIT(13)
+#define QDMA_ETH_TXMSG_UCO_MASK		BIT(12)
+#define QDMA_ETH_TXMSG_TCO_MASK		BIT(11)
+#define QDMA_ETH_TXMSG_TSO_MASK		BIT(10)
+#define QDMA_ETH_TXMSG_FAST_MASK	BIT(9)
+#define QDMA_ETH_TXMSG_OAM_MASK		BIT(8)
+#define QDMA_ETH_TXMSG_CHAN_MASK	GENMASK(7, 3)
+#define QDMA_ETH_TXMSG_QUEUE_MASK	GENMASK(2, 0)
+/* TX MSG1 */
+#define QDMA_ETH_TXMSG_NO_DROP		BIT(31)
+#define QDMA_ETH_TXMSG_METER_MASK	GENMASK(30, 24)	/* 0x7f no meters */
+#define QDMA_ETH_TXMSG_FPORT_MASK	GENMASK(23, 20)
+#define QDMA_ETH_TXMSG_NBOQ_MASK	GENMASK(19, 15)
+#define QDMA_ETH_TXMSG_HWF_MASK		BIT(14)
+#define QDMA_ETH_TXMSG_HOP_MASK		BIT(13)
+#define QDMA_ETH_TXMSG_PTP_MASK		BIT(12)
+#define QDMA_ETH_TXMSG_ACNT_G1_MASK	GENMASK(10, 6)	/* 0x1f do not count */
+#define QDMA_ETH_TXMSG_ACNT_G0_MASK	GENMASK(5, 0)	/* 0x3f do not count */
+
+/* RX MSG0 */
+#define QDMA_ETH_RXMSG_SPTAG		GENMASK(21, 14)
+/* RX MSG1 */
+#define QDMA_ETH_RXMSG_DEI_MASK		BIT(31)
+#define QDMA_ETH_RXMSG_IP6_MASK		BIT(30)
+#define QDMA_ETH_RXMSG_IP4_MASK		BIT(29)
+#define QDMA_ETH_RXMSG_IP4F_MASK	BIT(28)
+#define QDMA_ETH_RXMSG_L4_VALID_MASK	BIT(27)
+#define QDMA_ETH_RXMSG_L4F_MASK		BIT(26)
+#define QDMA_ETH_RXMSG_SPORT_MASK	GENMASK(25, 21)
+#define QDMA_ETH_RXMSG_CRSN_MASK	GENMASK(20, 16)
+#define QDMA_ETH_RXMSG_PPE_ENTRY_MASK	GENMASK(15, 0)
+
+struct airoha_qdma_desc {
+	__le32 rsv;
+	__le32 ctrl;
+	__le32 addr;
+	__le32 data;
+	__le32 msg0;
+	__le32 msg1;
+	__le32 msg2;
+	__le32 msg3;
+};
+
+/* CTRL0 */
+#define QDMA_FWD_DESC_CTX_MASK		BIT(31)
+#define QDMA_FWD_DESC_RING_MASK		GENMASK(30, 28)
+#define QDMA_FWD_DESC_IDX_MASK		GENMASK(27, 16)
+#define QDMA_FWD_DESC_LEN_MASK		GENMASK(15, 0)
+/* CTRL1 */
+#define QDMA_FWD_DESC_FIRST_IDX_MASK	GENMASK(15, 0)
+/* CTRL2 */
+#define QDMA_FWD_DESC_MORE_PKT_NUM_MASK	GENMASK(2, 0)
+
+struct airoha_qdma_fwd_desc {
+	__le32 addr;
+	__le32 ctrl0;
+	__le32 ctrl1;
+	__le32 ctrl2;
+	__le32 msg0;
+	__le32 msg1;
+	__le32 rsv0;
+	__le32 rsv1;
+};
+
+#endif /* AIROHA_REGS_H */
diff --git a/drivers/net/ethernet/altera/altera_tse.h b/drivers/net/ethernet/altera/altera_tse.h
index 82f2363a45cd..e5a56bb989da 100644
--- a/drivers/net/ethernet/altera/altera_tse.h
+++ b/drivers/net/ethernet/altera/altera_tse.h
@@ -401,9 +401,6 @@ struct altera_tse_private {
 	/* MAC address space */
 	struct altera_tse_mac __iomem *mac_dev;
 
-	/* TSE Revision */
-	u32	revision;
-
 	/* mSGDMA Rx Dispatcher address space */
 	void __iomem *rx_dma_csr;
 	void __iomem *rx_dma_desc;
diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index 3f6204de9e6b..ca55c5fd11df 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -892,9 +892,6 @@ static int tse_open(struct net_device *dev)
 		netdev_warn(dev, "device MAC address %pM\n",
 			    dev->dev_addr);
 
-	if ((priv->revision < 0xd00) || (priv->revision > 0xe00))
-		netdev_warn(dev, "TSE revision %x\n", priv->revision);
-
 	spin_lock(&priv->mac_cfg_lock);
 
 	ret = reset_mac(priv);
@@ -1142,6 +1139,7 @@ static int altera_tse_probe(struct platform_device *pdev)
 	struct net_device *ndev;
 	void __iomem *descmap;
 	int ret = -ENODEV;
+	u32 revision;
 
 	ndev = alloc_etherdev(sizeof(struct altera_tse_private));
 	if (!ndev) {
@@ -1150,6 +1148,7 @@ static int altera_tse_probe(struct platform_device *pdev)
 	}
 
 	SET_NETDEV_DEV(ndev, &pdev->dev);
+	platform_set_drvdata(pdev, ndev);
 
 	priv = netdev_priv(ndev);
 	priv->device = &pdev->dev;
@@ -1387,25 +1386,7 @@ static int altera_tse_probe(struct platform_device *pdev)
 	spin_lock_init(&priv->tx_lock);
 	spin_lock_init(&priv->rxdma_irq_lock);
 
-	netif_carrier_off(ndev);
-	ret = register_netdev(ndev);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to register TSE net device\n");
-		goto err_register_netdev;
-	}
-
-	platform_set_drvdata(pdev, ndev);
-
-	priv->revision = ioread32(&priv->mac_dev->megacore_revision);
-
-	if (netif_msg_probe(priv))
-		dev_info(&pdev->dev, "Altera TSE MAC version %d.%d at 0x%08lx irq %d/%d\n",
-			 (priv->revision >> 8) & 0xff,
-			 priv->revision & 0xff,
-			 (unsigned long) control_port->start, priv->rx_irq,
-			 priv->tx_irq);
-
-	snprintf(mrc.name, MII_BUS_ID_SIZE, "%s-pcs-mii", ndev->name);
+	snprintf(mrc.name, MII_BUS_ID_SIZE, "%s-pcs-mii", dev_name(&pdev->dev));
 	pcs_bus = devm_mdio_regmap_register(&pdev->dev, &mrc);
 	if (IS_ERR(pcs_bus)) {
 		ret = PTR_ERR(pcs_bus);
@@ -1442,12 +1423,30 @@ static int altera_tse_probe(struct platform_device *pdev)
 		goto err_init_phylink;
 	}
 
+	ret = register_netdev(ndev);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register TSE net device\n");
+		goto err_register_netdev;
+	}
+
+	revision = ioread32(&priv->mac_dev->megacore_revision);
+
+	if (revision < 0xd00 || revision > 0xe00)
+		netdev_warn(ndev, "TSE revision %x\n", revision);
+
+	if (netif_msg_probe(priv))
+		dev_info(&pdev->dev, "Altera TSE MAC version %d.%d at 0x%08lx irq %d/%d\n",
+			 (revision >> 8) & 0xff, revision & 0xff,
+			 (unsigned long)control_port->start, priv->rx_irq,
+			 priv->tx_irq);
+
 	return 0;
+
+err_register_netdev:
+	phylink_destroy(priv->phylink);
 err_init_phylink:
 	lynx_pcs_destroy(priv->pcs);
 err_init_pcs:
-	unregister_netdev(ndev);
-err_register_netdev:
 	netif_napi_del(&priv->napi);
 	altera_tse_mdio_destroy(ndev);
 err_free_netdev:
diff --git a/drivers/net/ethernet/amazon/Kconfig b/drivers/net/ethernet/amazon/Kconfig
index c37fa393b99e..95dcc3969f0c 100644
--- a/drivers/net/ethernet/amazon/Kconfig
+++ b/drivers/net/ethernet/amazon/Kconfig
@@ -19,7 +19,9 @@ if NET_VENDOR_AMAZON
 config ENA_ETHERNET
 	tristate "Elastic Network Adapter (ENA) support"
 	depends on PCI_MSI && !CPU_BIG_ENDIAN
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select DIMLIB
+	select NET_DEVLINK
 	help
 	  This driver supports Elastic Network Adapter (ENA)"
 
diff --git a/drivers/net/ethernet/amazon/ena/Makefile b/drivers/net/ethernet/amazon/ena/Makefile
index 6ab615365172..6d8036bc1823 100644
--- a/drivers/net/ethernet/amazon/ena/Makefile
+++ b/drivers/net/ethernet/amazon/ena/Makefile
@@ -5,4 +5,4 @@
 
 obj-$(CONFIG_ENA_ETHERNET) += ena.o
 
-ena-y := ena_netdev.o ena_com.o ena_eth_com.o ena_ethtool.o ena_xdp.o
+ena-y := ena_netdev.o ena_com.o ena_eth_com.o ena_ethtool.o ena_xdp.o ena_phc.o ena_devlink.o ena_debugfs.o
diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
index 9d9fa6559354..898ecd96b96a 100644
--- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
@@ -60,6 +60,7 @@ enum ena_admin_aq_feature_id {
 	ENA_ADMIN_AENQ_CONFIG                       = 26,
 	ENA_ADMIN_LINK_CONFIG                       = 27,
 	ENA_ADMIN_HOST_ATTR_CONFIG                  = 28,
+	ENA_ADMIN_PHC_CONFIG                        = 29,
 	ENA_ADMIN_FEATURES_OPCODE_NUM               = 32,
 };
 
@@ -127,6 +128,14 @@ enum ena_admin_get_stats_scope {
 	ENA_ADMIN_ETH_TRAFFIC                       = 1,
 };
 
+enum ena_admin_phc_type {
+	ENA_ADMIN_PHC_TYPE_READLESS                 = 0,
+};
+
+enum ena_admin_phc_error_flags {
+	ENA_ADMIN_PHC_ERROR_FLAG_TIMESTAMP   = BIT(0),
+};
+
 /* ENA SRD configuration for ENI */
 enum ena_admin_ena_srd_flags {
 	/* Feature enabled */
@@ -943,7 +952,9 @@ struct ena_admin_host_info {
 	 * 4 : rss_configurable_function_key
 	 * 5 : reserved
 	 * 6 : rx_page_reuse
-	 * 31:7 : reserved
+	 * 7 : reserved
+	 * 8 : phc
+	 * 31:9 : reserved
 	 */
 	u32 driver_supported_features;
 };
@@ -975,7 +986,7 @@ struct ena_admin_feature_rss_ind_table {
 	struct ena_admin_rss_ind_table_entry inline_entry;
 };
 
-/* When hint value is 0, driver should use it's own predefined value */
+/* When hint value is 0, driver should use its own predefined value */
 struct ena_admin_ena_hw_hints {
 	/* value in ms */
 	u16 mmio_read_timeout;
@@ -1023,6 +1034,43 @@ struct ena_admin_queue_ext_feature_desc {
 	};
 };
 
+struct ena_admin_feature_phc_desc {
+	/* PHC type as defined in enum ena_admin_get_phc_type,
+	 * used only for GET command.
+	 */
+	u8 type;
+
+	/* Reserved - MBZ */
+	u8 reserved1[3];
+
+	/* PHC doorbell address as an offset to PCIe MMIO REG BAR,
+	 * used only for GET command.
+	 */
+	u32 doorbell_offset;
+
+	/* Max time for valid PHC retrieval, passing this threshold will
+	 * fail the get-time request and block PHC requests for
+	 * block_timeout_usec, used only for GET command.
+	 */
+	u32 expire_timeout_usec;
+
+	/* PHC requests block period, blocking starts if PHC request expired
+	 * in order to prevent floods on busy device,
+	 * used only for GET command.
+	 */
+	u32 block_timeout_usec;
+
+	/* Shared PHC physical address (ena_admin_phc_resp),
+	 * used only for SET command.
+	 */
+	struct ena_common_mem_addr output_address;
+
+	/* Shared PHC Size (ena_admin_phc_resp),
+	 * used only for SET command.
+	 */
+	u32 output_length;
+};
+
 struct ena_admin_get_feat_resp {
 	struct ena_admin_acq_common_desc acq_common_desc;
 
@@ -1052,6 +1100,8 @@ struct ena_admin_get_feat_resp {
 		struct ena_admin_feature_intr_moder_desc intr_moderation;
 
 		struct ena_admin_ena_hw_hints hw_hints;
+
+		struct ena_admin_feature_phc_desc phc;
 	} u;
 };
 
@@ -1085,6 +1135,9 @@ struct ena_admin_set_feat_cmd {
 
 		/* LLQ configuration */
 		struct ena_admin_feature_llq_desc llq;
+
+		/* PHC configuration */
+		struct ena_admin_feature_phc_desc phc;
 	} u;
 };
 
@@ -1162,6 +1215,23 @@ struct ena_admin_ena_mmio_req_read_less_resp {
 	u32 reg_val;
 };
 
+struct ena_admin_phc_resp {
+	/* Request Id, received from DB register */
+	u16 req_id;
+
+	u8 reserved1[6];
+
+	/* PHC timestamp (nsec) */
+	u64 timestamp;
+
+	u8 reserved2[12];
+
+	/* Bit field of enum ena_admin_phc_error_flags */
+	u32 error_flags;
+
+	u8 reserved3[32];
+};
+
 /* aq_common_desc */
 #define ENA_ADMIN_AQ_COMMON_DESC_COMMAND_ID_MASK            GENMASK(11, 0)
 #define ENA_ADMIN_AQ_COMMON_DESC_PHASE_MASK                 BIT(0)
@@ -1260,6 +1330,8 @@ struct ena_admin_ena_mmio_req_read_less_resp {
 #define ENA_ADMIN_HOST_INFO_RSS_CONFIGURABLE_FUNCTION_KEY_MASK BIT(4)
 #define ENA_ADMIN_HOST_INFO_RX_PAGE_REUSE_SHIFT             6
 #define ENA_ADMIN_HOST_INFO_RX_PAGE_REUSE_MASK              BIT(6)
+#define ENA_ADMIN_HOST_INFO_PHC_SHIFT                       8
+#define ENA_ADMIN_HOST_INFO_PHC_MASK                        BIT(8)
 
 /* aenq_common_desc */
 #define ENA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK               BIT(0)
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 66445617fbfb..e67b592e5697 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -41,6 +41,12 @@
 
 #define ENA_MAX_ADMIN_POLL_US 5000
 
+/* PHC definitions */
+#define ENA_PHC_DEFAULT_EXPIRE_TIMEOUT_USEC 10
+#define ENA_PHC_DEFAULT_BLOCK_TIMEOUT_USEC 1000
+#define ENA_PHC_REQ_ID_OFFSET 0xDEAD
+#define ENA_PHC_ERROR_FLAGS (ENA_ADMIN_PHC_ERROR_FLAG_TIMESTAMP)
+
 /*****************************************************************************/
 /*****************************************************************************/
 /*****************************************************************************/
@@ -1641,6 +1647,267 @@ void ena_com_set_admin_polling_mode(struct ena_com_dev *ena_dev, bool polling)
 	ena_dev->admin_queue.polling = polling;
 }
 
+bool ena_com_phc_supported(struct ena_com_dev *ena_dev)
+{
+	return ena_com_check_supported_feature_id(ena_dev, ENA_ADMIN_PHC_CONFIG);
+}
+
+int ena_com_phc_init(struct ena_com_dev *ena_dev)
+{
+	struct ena_com_phc_info *phc = &ena_dev->phc;
+
+	memset(phc, 0x0, sizeof(*phc));
+
+	/* Allocate shared mem used PHC timestamp retrieved from device */
+	phc->virt_addr = dma_alloc_coherent(ena_dev->dmadev,
+					    sizeof(*phc->virt_addr),
+					    &phc->phys_addr,
+					    GFP_KERNEL);
+	if (unlikely(!phc->virt_addr))
+		return -ENOMEM;
+
+	spin_lock_init(&phc->lock);
+
+	phc->virt_addr->req_id = 0;
+	phc->virt_addr->timestamp = 0;
+
+	return 0;
+}
+
+int ena_com_phc_config(struct ena_com_dev *ena_dev)
+{
+	struct ena_com_phc_info *phc = &ena_dev->phc;
+	struct ena_admin_get_feat_resp get_feat_resp;
+	struct ena_admin_set_feat_resp set_feat_resp;
+	struct ena_admin_set_feat_cmd set_feat_cmd;
+	int ret = 0;
+
+	/* Get device PHC default configuration */
+	ret = ena_com_get_feature(ena_dev,
+				  &get_feat_resp,
+				  ENA_ADMIN_PHC_CONFIG,
+				  0);
+	if (unlikely(ret)) {
+		netdev_err(ena_dev->net_device,
+			   "Failed to get PHC feature configuration, error: %d\n",
+			   ret);
+		return ret;
+	}
+
+	/* Supporting only readless PHC retrieval */
+	if (get_feat_resp.u.phc.type != ENA_ADMIN_PHC_TYPE_READLESS) {
+		netdev_err(ena_dev->net_device,
+			   "Unsupported PHC type, error: %d\n",
+			   -EOPNOTSUPP);
+		return -EOPNOTSUPP;
+	}
+
+	/* Update PHC doorbell offset according to device value,
+	 * used to write req_id to PHC bar
+	 */
+	phc->doorbell_offset = get_feat_resp.u.phc.doorbell_offset;
+
+	/* Update PHC expire timeout according to device
+	 * or default driver value
+	 */
+	phc->expire_timeout_usec = (get_feat_resp.u.phc.expire_timeout_usec) ?
+				    get_feat_resp.u.phc.expire_timeout_usec :
+				    ENA_PHC_DEFAULT_EXPIRE_TIMEOUT_USEC;
+
+	/* Update PHC block timeout according to device
+	 * or default driver value
+	 */
+	phc->block_timeout_usec = (get_feat_resp.u.phc.block_timeout_usec) ?
+				   get_feat_resp.u.phc.block_timeout_usec :
+				   ENA_PHC_DEFAULT_BLOCK_TIMEOUT_USEC;
+
+	/* Sanity check - expire timeout must not exceed block timeout */
+	if (phc->expire_timeout_usec > phc->block_timeout_usec)
+		phc->expire_timeout_usec = phc->block_timeout_usec;
+
+	/* Prepare PHC feature command */
+	memset(&set_feat_cmd, 0x0, sizeof(set_feat_cmd));
+	set_feat_cmd.aq_common_descriptor.opcode = ENA_ADMIN_SET_FEATURE;
+	set_feat_cmd.feat_common.feature_id = ENA_ADMIN_PHC_CONFIG;
+	set_feat_cmd.u.phc.output_length = sizeof(*phc->virt_addr);
+	ret = ena_com_mem_addr_set(ena_dev,
+				   &set_feat_cmd.u.phc.output_address,
+				   phc->phys_addr);
+	if (unlikely(ret)) {
+		netdev_err(ena_dev->net_device,
+			   "Failed setting PHC output address, error: %d\n",
+			   ret);
+		return ret;
+	}
+
+	/* Send PHC feature command to the device */
+	ret = ena_com_execute_admin_command(&ena_dev->admin_queue,
+					    (struct ena_admin_aq_entry *)&set_feat_cmd,
+					    sizeof(set_feat_cmd),
+					    (struct ena_admin_acq_entry *)&set_feat_resp,
+					    sizeof(set_feat_resp));
+
+	if (unlikely(ret)) {
+		netdev_err(ena_dev->net_device,
+			   "Failed to enable PHC, error: %d\n",
+			   ret);
+		return ret;
+	}
+
+	phc->active = true;
+	netdev_dbg(ena_dev->net_device, "PHC is active in the device\n");
+
+	return ret;
+}
+
+void ena_com_phc_destroy(struct ena_com_dev *ena_dev)
+{
+	struct ena_com_phc_info *phc = &ena_dev->phc;
+	unsigned long flags = 0;
+
+	/* In case PHC is not supported by the device, silently exiting */
+	if (!phc->virt_addr)
+		return;
+
+	spin_lock_irqsave(&phc->lock, flags);
+	phc->active = false;
+	spin_unlock_irqrestore(&phc->lock, flags);
+
+	dma_free_coherent(ena_dev->dmadev,
+			  sizeof(*phc->virt_addr),
+			  phc->virt_addr,
+			  phc->phys_addr);
+	phc->virt_addr = NULL;
+}
+
+int ena_com_phc_get_timestamp(struct ena_com_dev *ena_dev, u64 *timestamp)
+{
+	volatile struct ena_admin_phc_resp *resp = ena_dev->phc.virt_addr;
+	const ktime_t zero_system_time = ktime_set(0, 0);
+	struct ena_com_phc_info *phc = &ena_dev->phc;
+	ktime_t expire_time;
+	ktime_t block_time;
+	unsigned long flags = 0;
+	int ret = 0;
+
+	if (!phc->active) {
+		netdev_err(ena_dev->net_device, "PHC feature is not active in the device\n");
+		return -EOPNOTSUPP;
+	}
+
+	spin_lock_irqsave(&phc->lock, flags);
+
+	/* Check if PHC is in blocked state */
+	if (unlikely(ktime_compare(phc->system_time, zero_system_time))) {
+		/* Check if blocking time expired */
+		block_time = ktime_add_us(phc->system_time, phc->block_timeout_usec);
+		if (!ktime_after(ktime_get(), block_time)) {
+			/* PHC is still in blocked state, skip PHC request */
+			phc->stats.phc_skp++;
+			ret = -EBUSY;
+			goto skip;
+		}
+
+		/* PHC is in active state, update statistics according
+		 * to req_id and error_flags
+		 */
+		if (READ_ONCE(resp->req_id) != phc->req_id) {
+			/* Device didn't update req_id during blocking time,
+			 * this indicates on a device error
+			 */
+			netdev_err(ena_dev->net_device,
+				   "PHC get time request 0x%x failed (device error)\n",
+				   phc->req_id);
+			phc->stats.phc_err_dv++;
+		} else if (resp->error_flags & ENA_PHC_ERROR_FLAGS) {
+			/* Device updated req_id during blocking time but got
+			 * a PHC error, this occurs if device:
+			 * - exceeded the get time request limit
+			 * - received an invalid timestamp
+			 */
+			netdev_err(ena_dev->net_device,
+				   "PHC get time request 0x%x failed (error 0x%x)\n",
+				   phc->req_id,
+				   resp->error_flags);
+			phc->stats.phc_err_ts += !!(resp->error_flags &
+				ENA_ADMIN_PHC_ERROR_FLAG_TIMESTAMP);
+		} else {
+			/* Device updated req_id during blocking time
+			 * with valid timestamp
+			 */
+			phc->stats.phc_exp++;
+		}
+	}
+
+	/* Setting relative timeouts */
+	phc->system_time = ktime_get();
+	block_time = ktime_add_us(phc->system_time, phc->block_timeout_usec);
+	expire_time = ktime_add_us(phc->system_time, phc->expire_timeout_usec);
+
+	/* We expect the device to return this req_id once
+	 * the new PHC timestamp is updated
+	 */
+	phc->req_id++;
+
+	/* Initialize PHC shared memory with different req_id value
+	 * to be able to identify once the device changes it to req_id
+	 */
+	resp->req_id = phc->req_id + ENA_PHC_REQ_ID_OFFSET;
+
+	/* Writing req_id to PHC bar */
+	writel(phc->req_id, ena_dev->reg_bar + phc->doorbell_offset);
+
+	/* Stalling until the device updates req_id */
+	while (1) {
+		if (unlikely(ktime_after(ktime_get(), expire_time))) {
+			/* Gave up waiting for updated req_id, PHC enters into
+			 * blocked state until passing blocking time,
+			 * during this time any get PHC timestamp will fail with
+			 * device busy error
+			 */
+			ret = -EBUSY;
+			break;
+		}
+
+		/* Check if req_id was updated by the device */
+		if (READ_ONCE(resp->req_id) != phc->req_id) {
+			/* req_id was not updated by the device yet,
+			 * check again on next loop
+			 */
+			continue;
+		}
+
+		/* req_id was updated by the device which indicates that
+		 * PHC timestamp and error_flags are updated too,
+		 * checking errors before retrieving timestamp
+		 */
+		if (unlikely(resp->error_flags & ENA_PHC_ERROR_FLAGS)) {
+			/* Retrieved invalid PHC timestamp, PHC enters into
+			 * blocked state until passing blocking time,
+			 * during this time any get PHC timestamp requests
+			 * will fail with device busy error
+			 */
+			ret = -EBUSY;
+			break;
+		}
+
+		/* PHC timestamp value is returned to the caller */
+		*timestamp = resp->timestamp;
+
+		/* Update statistic on valid PHC timestamp retrieval */
+		phc->stats.phc_cnt++;
+
+		/* This indicates PHC state is active */
+		phc->system_time = zero_system_time;
+		break;
+	}
+
+skip:
+	spin_unlock_irqrestore(&phc->lock, flags);
+
+	return ret;
+}
+
 int ena_com_mmio_reg_read_request_init(struct ena_com_dev *ena_dev)
 {
 	struct ena_com_mmio_read *mmio_read = &ena_dev->mmio_read;
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index 9414e93d107b..64df2c48c9a6 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -210,6 +210,14 @@ struct ena_com_stats_admin {
 	u64 no_completion;
 };
 
+struct ena_com_stats_phc {
+	u64 phc_cnt;
+	u64 phc_exp;
+	u64 phc_skp;
+	u64 phc_err_dv;
+	u64 phc_err_ts;
+};
+
 struct ena_com_admin_queue {
 	void *q_dmadev;
 	struct ena_com_dev *ena_dev;
@@ -258,6 +266,47 @@ struct ena_com_mmio_read {
 	spinlock_t lock;
 };
 
+/* PTP hardware clock (PHC) MMIO read data info */
+struct ena_com_phc_info {
+	/* Internal PHC statistics */
+	struct ena_com_stats_phc stats;
+
+	/* PHC shared memory - virtual address */
+	struct ena_admin_phc_resp *virt_addr;
+
+	/* System time of last PHC request */
+	ktime_t system_time;
+
+	/* Spin lock to ensure a single outstanding PHC read */
+	spinlock_t lock;
+
+	/* PHC doorbell address as an offset to PCIe MMIO REG BAR */
+	u32 doorbell_offset;
+
+	/* Shared memory read expire timeout (usec)
+	 * Max time for valid PHC retrieval, passing this threshold will fail
+	 * the get time request and block new PHC requests for block_timeout_usec
+	 * in order to prevent floods on busy device
+	 */
+	u32 expire_timeout_usec;
+
+	/* Shared memory read abort timeout (usec)
+	 * PHC requests block period, blocking starts once PHC request expired
+	 * in order to prevent floods on busy device,
+	 * any PHC requests during block period will be skipped
+	 */
+	u32 block_timeout_usec;
+
+	/* PHC shared memory - physical address */
+	dma_addr_t phys_addr;
+
+	/* Request id sent to the device */
+	u16 req_id;
+
+	/* True if PHC is active in the device */
+	bool active;
+};
+
 struct ena_rss {
 	/* Indirect table */
 	u16 *host_rss_ind_tbl;
@@ -317,6 +366,7 @@ struct ena_com_dev {
 	u32 ena_min_poll_delay_us;
 
 	struct ena_com_mmio_read mmio_read;
+	struct ena_com_phc_info phc;
 
 	struct ena_rss rss;
 	u32 supported_features;
@@ -382,6 +432,40 @@ struct ena_aenq_handlers {
  */
 int ena_com_mmio_reg_read_request_init(struct ena_com_dev *ena_dev);
 
+/* ena_com_phc_init - Allocate and initialize PHC feature
+ * @ena_dev: ENA communication layer struct
+ * @note: This method assumes PHC is supported by the device
+ * @return - 0 on success, negative value on failure
+ */
+int ena_com_phc_init(struct ena_com_dev *ena_dev);
+
+/* ena_com_phc_supported - Return if PHC feature is supported by the device
+ * @ena_dev: ENA communication layer struct
+ * @note: This method must be called after getting supported features
+ * @return - supported or not
+ */
+bool ena_com_phc_supported(struct ena_com_dev *ena_dev);
+
+/* ena_com_phc_config - Configure PHC feature
+ * @ena_dev: ENA communication layer struct
+ * Configure PHC feature in driver and device
+ * @note: This method assumes PHC is supported by the device
+ * @return - 0 on success, negative value on failure
+ */
+int ena_com_phc_config(struct ena_com_dev *ena_dev);
+
+/* ena_com_phc_destroy - Destroy PHC feature
+ * @ena_dev: ENA communication layer struct
+ */
+void ena_com_phc_destroy(struct ena_com_dev *ena_dev);
+
+/* ena_com_phc_get_timestamp - Retrieve PHC timestamp
+ * @ena_dev: ENA communication layer struct
+ * @timestamp: Retrieved PHC timestamp
+ * @return - 0 on success, negative value on failure
+ */
+int ena_com_phc_get_timestamp(struct ena_com_dev *ena_dev, u64 *timestamp);
+
 /* ena_com_set_mmio_read_mode - Enable/disable the indirect mmio reg read mechanism
  * @ena_dev: ENA communication layer struct
  * @readless_supported: readless mode (enable/disable)
diff --git a/drivers/net/ethernet/amazon/ena/ena_debugfs.c b/drivers/net/ethernet/amazon/ena/ena_debugfs.c
new file mode 100644
index 000000000000..46ed80986724
--- /dev/null
+++ b/drivers/net/ethernet/amazon/ena/ena_debugfs.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) Amazon.com, Inc. or its affiliates.
+ * All rights reserved.
+ */
+
+#ifdef CONFIG_DEBUG_FS
+
+#include <linux/seq_file.h>
+#include <linux/pci.h>
+#include "ena_debugfs.h"
+#include "ena_phc.h"
+
+static int phc_stats_show(struct seq_file *file, void *priv)
+{
+	struct ena_adapter *adapter = file->private;
+
+	if (!ena_phc_is_active(adapter))
+		return 0;
+
+	seq_printf(file,
+		   "phc_cnt: %llu\n",
+		   adapter->ena_dev->phc.stats.phc_cnt);
+	seq_printf(file,
+		   "phc_exp: %llu\n",
+		   adapter->ena_dev->phc.stats.phc_exp);
+	seq_printf(file,
+		   "phc_skp: %llu\n",
+		   adapter->ena_dev->phc.stats.phc_skp);
+	seq_printf(file,
+		   "phc_err_dv: %llu\n",
+		   adapter->ena_dev->phc.stats.phc_err_dv);
+	seq_printf(file,
+		   "phc_err_ts: %llu\n",
+		   adapter->ena_dev->phc.stats.phc_err_ts);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(phc_stats);
+
+void ena_debugfs_init(struct net_device *dev)
+{
+	struct ena_adapter *adapter = netdev_priv(dev);
+
+	adapter->debugfs_base =
+		debugfs_create_dir(dev_name(&adapter->pdev->dev), NULL);
+
+	debugfs_create_file("phc_stats",
+			    0400,
+			    adapter->debugfs_base,
+			    adapter,
+			    &phc_stats_fops);
+}
+
+void ena_debugfs_terminate(struct net_device *dev)
+{
+	struct ena_adapter *adapter = netdev_priv(dev);
+
+	debugfs_remove_recursive(adapter->debugfs_base);
+}
+
+#endif /* CONFIG_DEBUG_FS */
diff --git a/drivers/net/ethernet/amazon/ena/ena_debugfs.h b/drivers/net/ethernet/amazon/ena/ena_debugfs.h
new file mode 100644
index 000000000000..dc61dd998867
--- /dev/null
+++ b/drivers/net/ethernet/amazon/ena/ena_debugfs.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) Amazon.com, Inc. or its affiliates.
+ * All rights reserved.
+ */
+
+#ifndef __ENA_DEBUGFS_H__
+#define __ENA_DEBUGFS_H__
+
+#include <linux/debugfs.h>
+#include <linux/netdevice.h>
+#include "ena_netdev.h"
+
+#ifdef CONFIG_DEBUG_FS
+
+void ena_debugfs_init(struct net_device *dev);
+
+void ena_debugfs_terminate(struct net_device *dev);
+
+#else /* CONFIG_DEBUG_FS */
+
+static inline void ena_debugfs_init(struct net_device *dev) {}
+
+static inline void ena_debugfs_terminate(struct net_device *dev) {}
+
+#endif /* CONFIG_DEBUG_FS */
+
+#endif /* __ENA_DEBUGFS_H__ */
diff --git a/drivers/net/ethernet/amazon/ena/ena_devlink.c b/drivers/net/ethernet/amazon/ena/ena_devlink.c
new file mode 100644
index 000000000000..ac81c24016dd
--- /dev/null
+++ b/drivers/net/ethernet/amazon/ena/ena_devlink.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) Amazon.com, Inc. or its affiliates.
+ * All rights reserved.
+ */
+
+#include "linux/pci.h"
+#include "ena_devlink.h"
+#include "ena_phc.h"
+
+static int ena_devlink_enable_phc_validate(struct devlink *devlink, u32 id,
+					   union devlink_param_value val,
+					   struct netlink_ext_ack *extack)
+{
+	struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink);
+
+	if (!val.vbool)
+		return 0;
+
+	if (!ena_com_phc_supported(adapter->ena_dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support PHC");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static const struct devlink_param ena_devlink_params[] = {
+	DEVLINK_PARAM_GENERIC(ENABLE_PHC,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL,
+			      NULL,
+			      ena_devlink_enable_phc_validate),
+};
+
+void ena_devlink_params_get(struct devlink *devlink)
+{
+	struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink);
+	union devlink_param_value val;
+	int err;
+
+	err = devl_param_driverinit_value_get(devlink,
+					      DEVLINK_PARAM_GENERIC_ID_ENABLE_PHC,
+					      &val);
+	if (err) {
+		netdev_err(adapter->netdev, "Failed to query PHC param\n");
+		return;
+	}
+
+	ena_phc_enable(adapter, val.vbool);
+}
+
+void ena_devlink_disable_phc_param(struct devlink *devlink)
+{
+	union devlink_param_value value;
+
+	value.vbool = false;
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_ENABLE_PHC,
+					value);
+}
+
+static void ena_devlink_port_register(struct devlink *devlink)
+{
+	struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink);
+	struct devlink_port_attrs attrs = {};
+
+	attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
+	devlink_port_attrs_set(&adapter->devlink_port, &attrs);
+	devl_port_register(devlink, &adapter->devlink_port, 0);
+}
+
+static void ena_devlink_port_unregister(struct devlink *devlink)
+{
+	struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink);
+
+	devl_port_unregister(&adapter->devlink_port);
+}
+
+static int ena_devlink_reload_down(struct devlink *devlink,
+				   bool netns_change,
+				   enum devlink_reload_action action,
+				   enum devlink_reload_limit limit,
+				   struct netlink_ext_ack *extack)
+{
+	struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink);
+
+	if (netns_change) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Namespace change is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	ena_devlink_port_unregister(devlink);
+
+	rtnl_lock();
+	ena_destroy_device(adapter, false);
+	rtnl_unlock();
+
+	return 0;
+}
+
+static int ena_devlink_reload_up(struct devlink *devlink,
+				 enum devlink_reload_action action,
+				 enum devlink_reload_limit limit,
+				 u32 *actions_performed,
+				 struct netlink_ext_ack *extack)
+{
+	struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink);
+	int err = 0;
+
+	rtnl_lock();
+	/* Check that no other routine initialized the device (e.g.
+	 * ena_fw_reset_device()). Also we're under devlink_mutex here,
+	 * so devlink isn't freed under our feet.
+	 */
+	if (!test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags))
+		err = ena_restore_device(adapter);
+
+	rtnl_unlock();
+
+	ena_devlink_port_register(devlink);
+
+	if (!err)
+		*actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
+
+	return err;
+}
+
+static const struct devlink_ops ena_devlink_ops = {
+	.reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT),
+	.reload_down	= ena_devlink_reload_down,
+	.reload_up	= ena_devlink_reload_up,
+};
+
+static int ena_devlink_configure_params(struct devlink *devlink)
+{
+	struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink);
+	union devlink_param_value value;
+	int rc;
+
+	rc = devlink_params_register(devlink, ena_devlink_params,
+				     ARRAY_SIZE(ena_devlink_params));
+	if (rc) {
+		netdev_err(adapter->netdev, "Failed to register devlink params\n");
+		return rc;
+	}
+
+	value.vbool = ena_phc_is_enabled(adapter);
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_ENABLE_PHC,
+					value);
+
+	return 0;
+}
+
+struct devlink *ena_devlink_alloc(struct ena_adapter *adapter)
+{
+	struct device *dev = &adapter->pdev->dev;
+	struct devlink *devlink;
+
+	devlink = devlink_alloc(&ena_devlink_ops,
+				sizeof(struct ena_adapter *),
+				dev);
+	if (!devlink) {
+		netdev_err(adapter->netdev,
+			   "Failed to allocate devlink struct\n");
+		return NULL;
+	}
+
+	ENA_DEVLINK_PRIV(devlink) = adapter;
+	adapter->devlink = devlink;
+
+	if (ena_devlink_configure_params(devlink))
+		goto free_devlink;
+
+	return devlink;
+
+free_devlink:
+	devlink_free(devlink);
+	return NULL;
+}
+
+static void ena_devlink_configure_params_clean(struct devlink *devlink)
+{
+	devlink_params_unregister(devlink, ena_devlink_params,
+				  ARRAY_SIZE(ena_devlink_params));
+}
+
+void ena_devlink_free(struct devlink *devlink)
+{
+	ena_devlink_configure_params_clean(devlink);
+
+	devlink_free(devlink);
+}
+
+void ena_devlink_register(struct devlink *devlink, struct device *dev)
+{
+	devl_lock(devlink);
+	ena_devlink_port_register(devlink);
+	devl_register(devlink);
+	devl_unlock(devlink);
+}
+
+void ena_devlink_unregister(struct devlink *devlink)
+{
+	devl_lock(devlink);
+	ena_devlink_port_unregister(devlink);
+	devl_unregister(devlink);
+	devl_unlock(devlink);
+}
diff --git a/drivers/net/ethernet/amazon/ena/ena_devlink.h b/drivers/net/ethernet/amazon/ena/ena_devlink.h
new file mode 100644
index 000000000000..7a19ce4830d9
--- /dev/null
+++ b/drivers/net/ethernet/amazon/ena/ena_devlink.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) Amazon.com, Inc. or its affiliates.
+ * All rights reserved.
+ */
+#ifndef DEVLINK_H
+#define DEVLINK_H
+
+#include "ena_netdev.h"
+#include <net/devlink.h>
+
+#define ENA_DEVLINK_PRIV(devlink) \
+	(*(struct ena_adapter **)devlink_priv(devlink))
+
+struct devlink *ena_devlink_alloc(struct ena_adapter *adapter);
+void ena_devlink_free(struct devlink *devlink);
+void ena_devlink_register(struct devlink *devlink, struct device *dev);
+void ena_devlink_unregister(struct devlink *devlink);
+void ena_devlink_params_get(struct devlink *devlink);
+void ena_devlink_disable_phc_param(struct devlink *devlink);
+
+#endif /* DEVLINK_H */
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index a3c934c3de71..fe3479b84a1f 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -5,9 +5,11 @@
 
 #include <linux/ethtool.h>
 #include <linux/pci.h>
+#include <linux/net_tstamp.h>
 
 #include "ena_netdev.h"
 #include "ena_xdp.h"
+#include "ena_phc.h"
 
 struct ena_stats {
 	char name[ETH_GSTRING_LEN];
@@ -298,6 +300,18 @@ static void ena_get_ethtool_stats(struct net_device *netdev,
 	ena_get_stats(adapter, data, true);
 }
 
+static int ena_get_ts_info(struct net_device *netdev,
+			   struct kernel_ethtool_ts_info *info)
+{
+	struct ena_adapter *adapter = netdev_priv(netdev);
+
+	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE;
+
+	info->phc_index = ena_phc_get_index(adapter);
+
+	return 0;
+}
+
 static int ena_get_sw_stats_count(struct ena_adapter *adapter)
 {
 	return adapter->num_io_queues * (ENA_STATS_ARRAY_TX + ENA_STATS_ARRAY_RX)
@@ -721,9 +735,11 @@ static u16 ena_flow_data_to_flow_hash(u32 hash_fields)
 	return data;
 }
 
-static int ena_get_rss_hash(struct ena_com_dev *ena_dev,
-			    struct ethtool_rxnfc *cmd)
+static int ena_get_rxfh_fields(struct net_device *netdev,
+			       struct ethtool_rxfh_fields *cmd)
 {
+	struct ena_adapter *adapter = netdev_priv(netdev);
+	struct ena_com_dev *ena_dev = adapter->ena_dev;
 	enum ena_admin_flow_hash_proto proto;
 	u16 hash_fields;
 	int rc;
@@ -772,9 +788,12 @@ static int ena_get_rss_hash(struct ena_com_dev *ena_dev,
 	return 0;
 }
 
-static int ena_set_rss_hash(struct ena_com_dev *ena_dev,
-			    struct ethtool_rxnfc *cmd)
+static int ena_set_rxfh_fields(struct net_device *netdev,
+			       const struct ethtool_rxfh_fields *cmd,
+			       struct netlink_ext_ack *extack)
 {
+	struct ena_adapter *adapter = netdev_priv(netdev);
+	struct ena_com_dev *ena_dev = adapter->ena_dev;
 	enum ena_admin_flow_hash_proto proto;
 	u16 hash_fields;
 
@@ -816,26 +835,6 @@ static int ena_set_rss_hash(struct ena_com_dev *ena_dev,
 	return ena_com_fill_hash_ctrl(ena_dev, proto, hash_fields);
 }
 
-static int ena_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info)
-{
-	struct ena_adapter *adapter = netdev_priv(netdev);
-	int rc = 0;
-
-	switch (info->cmd) {
-	case ETHTOOL_SRXFH:
-		rc = ena_set_rss_hash(adapter->ena_dev, info);
-		break;
-	case ETHTOOL_SRXCLSRLDEL:
-	case ETHTOOL_SRXCLSRLINS:
-	default:
-		netif_err(adapter, drv, netdev,
-			  "Command parameter %d is not supported\n", info->cmd);
-		rc = -EOPNOTSUPP;
-	}
-
-	return rc;
-}
-
 static int ena_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info,
 			 u32 *rules)
 {
@@ -847,9 +846,6 @@ static int ena_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info,
 		info->data = adapter->num_io_queues;
 		rc = 0;
 		break;
-	case ETHTOOL_GRXFH:
-		rc = ena_get_rss_hash(adapter->ena_dev, info);
-		break;
 	case ETHTOOL_GRXCLSRLCNT:
 	case ETHTOOL_GRXCLSRULE:
 	case ETHTOOL_GRXCLSRLALL:
@@ -869,7 +865,10 @@ static u32 ena_get_rxfh_indir_size(struct net_device *netdev)
 
 static u32 ena_get_rxfh_key_size(struct net_device *netdev)
 {
-	return ENA_HASH_KEY_SIZE;
+	struct ena_adapter *adapter = netdev_priv(netdev);
+	struct ena_rss *rss = &adapter->ena_dev->rss;
+
+	return rss->hash_key ? ENA_HASH_KEY_SIZE : 0;
 }
 
 static int ena_indirection_table_set(struct ena_adapter *adapter,
@@ -1098,16 +1097,17 @@ static const struct ethtool_ops ena_ethtool_ops = {
 	.get_strings		= ena_get_ethtool_strings,
 	.get_ethtool_stats      = ena_get_ethtool_stats,
 	.get_rxnfc		= ena_get_rxnfc,
-	.set_rxnfc		= ena_set_rxnfc,
 	.get_rxfh_indir_size    = ena_get_rxfh_indir_size,
 	.get_rxfh_key_size	= ena_get_rxfh_key_size,
 	.get_rxfh		= ena_get_rxfh,
 	.set_rxfh		= ena_set_rxfh,
+	.get_rxfh_fields	= ena_get_rxfh_fields,
+	.set_rxfh_fields	= ena_set_rxfh_fields,
 	.get_channels		= ena_get_channels,
 	.set_channels		= ena_set_channels,
 	.get_tunable		= ena_get_tunable,
 	.set_tunable		= ena_set_tunable,
-	.get_ts_info            = ethtool_op_get_ts_info,
+	.get_ts_info		= ena_get_ts_info,
 };
 
 void ena_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index c1295dfad0d0..92d149d4f091 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -5,9 +5,6 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#ifdef CONFIG_RFS_ACCEL
-#include <linux/cpu_rmap.h>
-#endif /* CONFIG_RFS_ACCEL */
 #include <linux/ethtool.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -22,6 +19,12 @@
 #include "ena_pci_id_tbl.h"
 #include "ena_xdp.h"
 
+#include "ena_phc.h"
+
+#include "ena_devlink.h"
+
+#include "ena_debugfs.h"
+
 MODULE_AUTHOR("Amazon.com, Inc. or its affiliates");
 MODULE_DESCRIPTION(DEVICE_NAME);
 MODULE_LICENSE("GPL");
@@ -42,8 +45,6 @@ MODULE_DEVICE_TABLE(pci, ena_pci_tbl);
 
 static int ena_rss_init_default(struct ena_adapter *adapter);
 static void check_for_admin_com_state(struct ena_adapter *adapter);
-static int ena_destroy_device(struct ena_adapter *adapter, bool graceful);
-static int ena_restore_device(struct ena_adapter *adapter);
 
 static void ena_tx_timeout(struct net_device *dev, unsigned int txqueue)
 {
@@ -162,30 +163,6 @@ int ena_xmit_common(struct ena_adapter *adapter,
 	return 0;
 }
 
-static int ena_init_rx_cpu_rmap(struct ena_adapter *adapter)
-{
-#ifdef CONFIG_RFS_ACCEL
-	u32 i;
-	int rc;
-
-	adapter->netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(adapter->num_io_queues);
-	if (!adapter->netdev->rx_cpu_rmap)
-		return -ENOMEM;
-	for (i = 0; i < adapter->num_io_queues; i++) {
-		int irq_idx = ENA_IO_IRQ_IDX(i);
-
-		rc = irq_cpu_rmap_add(adapter->netdev->rx_cpu_rmap,
-				      pci_irq_vector(adapter->pdev, irq_idx));
-		if (rc) {
-			free_irq_cpu_rmap(adapter->netdev->rx_cpu_rmap);
-			adapter->netdev->rx_cpu_rmap = NULL;
-			return rc;
-		}
-	}
-#endif /* CONFIG_RFS_ACCEL */
-	return 0;
-}
-
 static void ena_init_io_rings_common(struct ena_adapter *adapter,
 				     struct ena_ring *ring, u16 qid)
 {
@@ -1596,7 +1573,7 @@ static int ena_enable_msix(struct ena_adapter *adapter)
 		adapter->num_io_queues = irq_cnt - ENA_ADMIN_MSIX_VEC;
 	}
 
-	if (ena_init_rx_cpu_rmap(adapter))
+	if (netif_enable_cpu_rmap(adapter->netdev, adapter->num_io_queues))
 		netif_warn(adapter, probe, adapter->netdev,
 			   "Failed to map IRQs to CPUs\n");
 
@@ -1742,16 +1719,13 @@ static void ena_free_io_irq(struct ena_adapter *adapter)
 	struct ena_irq *irq;
 	int i;
 
-#ifdef CONFIG_RFS_ACCEL
-	if (adapter->msix_vecs >= 1) {
-		free_irq_cpu_rmap(adapter->netdev->rx_cpu_rmap);
-		adapter->netdev->rx_cpu_rmap = NULL;
-	}
-#endif /* CONFIG_RFS_ACCEL */
-
 	for (i = ENA_IO_IRQ_FIRST_IDX; i < ENA_MAX_MSIX_VEC(io_queue_count); i++) {
+		struct ena_napi *ena_napi;
+
 		irq = &adapter->irq_tbl[i];
 		irq_set_affinity_hint(irq->vector, NULL);
+		ena_napi = irq->data;
+		netif_napi_set_irq(&ena_napi->napi, -1);
 		free_irq(irq->vector, irq->data);
 	}
 }
@@ -1807,7 +1781,7 @@ static void ena_init_napi_in_range(struct ena_adapter *adapter,
 		if (ENA_IS_XDP_INDEX(adapter, i))
 			napi_handler = ena_xdp_io_poll;
 
-		netif_napi_add(adapter->netdev, &napi->napi, napi_handler);
+		netif_napi_add_config(adapter->netdev, &napi->napi, napi_handler, i);
 
 		if (!ENA_IS_XDP_INDEX(adapter, i))
 			napi->rx_ring = rx_ring;
@@ -2773,7 +2747,8 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev, struct pci_dev *pd
 		ENA_ADMIN_HOST_INFO_INTERRUPT_MODERATION_MASK |
 		ENA_ADMIN_HOST_INFO_RX_BUF_MIRRORING_MASK |
 		ENA_ADMIN_HOST_INFO_RSS_CONFIGURABLE_FUNCTION_KEY_MASK |
-		ENA_ADMIN_HOST_INFO_RX_PAGE_REUSE_MASK;
+		ENA_ADMIN_HOST_INFO_RX_PAGE_REUSE_MASK |
+		ENA_ADMIN_HOST_INFO_PHC_MASK;
 
 	rc = ena_com_set_host_attributes(ena_dev);
 	if (rc) {
@@ -3165,6 +3140,8 @@ static int ena_device_init(struct ena_adapter *adapter, struct pci_dev *pdev,
 		goto err_mmio_read_less;
 	}
 
+	ena_devlink_params_get(adapter->devlink);
+
 	/* ENA admin level init */
 	rc = ena_com_admin_init(ena_dev, &aenq_handlers);
 	if (rc) {
@@ -3218,6 +3195,10 @@ static int ena_device_init(struct ena_adapter *adapter, struct pci_dev *pdev,
 	if (unlikely(rc))
 		goto err_admin_init;
 
+	rc = ena_phc_init(adapter);
+	if (unlikely(rc && (rc != -EOPNOTSUPP)))
+		netdev_err(netdev, "Failed initializing PHC, error: %d\n", rc);
+
 	return 0;
 
 err_admin_init:
@@ -3263,7 +3244,7 @@ err_disable_msix:
 	return rc;
 }
 
-static int ena_destroy_device(struct ena_adapter *adapter, bool graceful)
+int ena_destroy_device(struct ena_adapter *adapter, bool graceful)
 {
 	struct net_device *netdev = adapter->netdev;
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
@@ -3275,7 +3256,7 @@ static int ena_destroy_device(struct ena_adapter *adapter, bool graceful)
 
 	netif_carrier_off(netdev);
 
-	del_timer_sync(&adapter->timer_service);
+	timer_delete_sync(&adapter->timer_service);
 
 	dev_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags);
 	adapter->dev_up_before_reset = dev_up;
@@ -3301,6 +3282,8 @@ static int ena_destroy_device(struct ena_adapter *adapter, bool graceful)
 
 	ena_com_admin_destroy(ena_dev);
 
+	ena_phc_destroy(adapter);
+
 	ena_com_mmio_reg_read_request_destroy(ena_dev);
 
 	/* return reset reason to default value */
@@ -3312,7 +3295,7 @@ static int ena_destroy_device(struct ena_adapter *adapter, bool graceful)
 	return rc;
 }
 
-static int ena_restore_device(struct ena_adapter *adapter)
+int ena_restore_device(struct ena_adapter *adapter)
 {
 	struct ena_com_dev_get_features_ctx get_feat_ctx;
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
@@ -3374,6 +3357,7 @@ err_device_destroy:
 	ena_com_wait_for_abort_completion(ena_dev);
 	ena_com_admin_destroy(ena_dev);
 	ena_com_dev_reset(ena_dev, ENA_REGS_RESET_DRIVER_INVALID_STATE);
+	ena_phc_destroy(adapter);
 	ena_com_mmio_reg_read_request_destroy(ena_dev);
 err:
 	clear_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags);
@@ -3697,7 +3681,8 @@ static void ena_update_host_info(struct ena_admin_host_info *host_info,
 
 static void ena_timer_service(struct timer_list *t)
 {
-	struct ena_adapter *adapter = from_timer(adapter, t, timer_service);
+	struct ena_adapter *adapter = timer_container_of(adapter, t,
+							 timer_service);
 	u8 *debug_area = adapter->ena_dev->host_attr.debug_area_virt_addr;
 	struct ena_admin_host_info *host_info =
 		adapter->ena_dev->host_attr.host_info;
@@ -3896,6 +3881,7 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct ena_adapter *adapter;
 	struct net_device *netdev;
 	static int adapters_found;
+	struct devlink *devlink;
 	u32 max_num_io_queues;
 	bool wd_state;
 	int bars, rc;
@@ -3961,10 +3947,16 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_drvdata(pdev, adapter);
 
+	rc = ena_phc_alloc(adapter);
+	if (rc) {
+		netdev_err(netdev, "ena_phc_alloc failed\n");
+		goto err_netdev_destroy;
+	}
+
 	rc = ena_com_allocate_customer_metrics_buffer(ena_dev);
 	if (rc) {
 		netdev_err(netdev, "ena_com_allocate_customer_metrics_buffer failed\n");
-		goto err_netdev_destroy;
+		goto err_free_phc;
 	}
 
 	rc = ena_map_llq_mem_bar(pdev, ena_dev, bars);
@@ -3973,12 +3965,20 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_metrics_destroy;
 	}
 
+	/* Need to do this before ena_device_init */
+	devlink = ena_devlink_alloc(adapter);
+	if (!devlink) {
+		netdev_err(netdev, "ena_devlink_alloc failed\n");
+		rc = -ENOMEM;
+		goto err_metrics_destroy;
+	}
+
 	rc = ena_device_init(adapter, pdev, &get_feat_ctx, &wd_state);
 	if (rc) {
 		dev_err(&pdev->dev, "ENA device init failed\n");
 		if (rc == -ETIME)
 			rc = -EPROBE_DEFER;
-		goto err_metrics_destroy;
+		goto ena_devlink_destroy;
 	}
 
 	/* Initial TX and RX interrupt delay. Assumes 1 usec granularity.
@@ -4062,6 +4062,8 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_rss;
 	}
 
+	ena_debugfs_init(netdev);
+
 	INIT_WORK(&adapter->reset_task, ena_fw_reset_device);
 
 	adapter->last_keep_alive_jiffies = jiffies;
@@ -4083,6 +4085,12 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	adapters_found++;
 
+	/* From this point, the devlink device is visible to users.
+	 * Perform the registration last to ensure that all the resources
+	 * are available and that the netdevice is registered.
+	 */
+	ena_devlink_register(devlink, &pdev->dev);
+
 	return 0;
 
 err_rss:
@@ -4095,12 +4103,16 @@ err_free_msix:
 	ena_free_mgmnt_irq(adapter);
 	ena_disable_msix(adapter);
 err_worker_destroy:
-	del_timer(&adapter->timer_service);
+	timer_delete(&adapter->timer_service);
 err_device_destroy:
 	ena_com_delete_host_info(ena_dev);
 	ena_com_admin_destroy(ena_dev);
+ena_devlink_destroy:
+	ena_devlink_free(devlink);
 err_metrics_destroy:
 	ena_com_delete_customer_metrics_buffer(ena_dev);
+err_free_phc:
+	ena_phc_free(adapter);
 err_netdev_destroy:
 	free_netdev(netdev);
 err_free_region:
@@ -4131,23 +4143,23 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown)
 	ena_dev = adapter->ena_dev;
 	netdev = adapter->netdev;
 
-#ifdef CONFIG_RFS_ACCEL
-	if ((adapter->msix_vecs >= 1) && (netdev->rx_cpu_rmap)) {
-		free_irq_cpu_rmap(netdev->rx_cpu_rmap);
-		netdev->rx_cpu_rmap = NULL;
-	}
+	ena_debugfs_terminate(netdev);
 
-#endif /* CONFIG_RFS_ACCEL */
 	/* Make sure timer and reset routine won't be called after
 	 * freeing device resources.
 	 */
-	del_timer_sync(&adapter->timer_service);
+	timer_delete_sync(&adapter->timer_service);
 	cancel_work_sync(&adapter->reset_task);
 
 	rtnl_lock(); /* lock released inside the below if-else block */
 	adapter->reset_reason = ENA_REGS_RESET_SHUTDOWN;
 	ena_destroy_device(adapter, true);
 
+	ena_phc_free(adapter);
+
+	ena_devlink_unregister(adapter->devlink);
+	ena_devlink_free(adapter->devlink);
+
 	if (shutdown) {
 		netif_device_detach(netdev);
 		dev_close(netdev);
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 6e12ae3b12e5..006f9a3acea6 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -16,6 +16,7 @@
 #include <linux/skbuff.h>
 #include <net/xdp.h>
 #include <uapi/linux/bpf.h>
+#include <net/devlink.h>
 
 #include "ena_com.h"
 #include "ena_eth_com.h"
@@ -110,6 +111,8 @@
 
 #define ENA_MMIO_DISABLE_REG_READ	BIT(0)
 
+struct ena_phc_info;
+
 struct ena_irq {
 	irq_handler_t handler;
 	void *data;
@@ -348,6 +351,8 @@ struct ena_adapter {
 
 	char name[ENA_NAME_MAX_LEN];
 
+	struct ena_phc_info *phc_info;
+
 	unsigned long flags;
 	/* TX */
 	struct ena_ring tx_ring[ENA_MAX_NUM_IO_QUEUES]
@@ -383,6 +388,13 @@ struct ena_adapter {
 	struct bpf_prog *xdp_bpf_prog;
 	u32 xdp_first_ring;
 	u32 xdp_num_queues;
+
+	struct devlink *devlink;
+	struct devlink_port devlink_port;
+#ifdef CONFIG_DEBUG_FS
+
+	struct dentry *debugfs_base;
+#endif /* CONFIG_DEBUG_FS */
 };
 
 void ena_set_ethtool_ops(struct net_device *netdev);
@@ -412,6 +424,8 @@ static inline void ena_reset_device(struct ena_adapter *adapter,
 	set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
 }
 
+int ena_destroy_device(struct ena_adapter *adapter, bool graceful);
+int ena_restore_device(struct ena_adapter *adapter);
 int handle_invalid_req_id(struct ena_ring *ring, u16 req_id,
 			  struct ena_tx_buffer *tx_info, bool is_xdp);
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_phc.c b/drivers/net/ethernet/amazon/ena/ena_phc.c
new file mode 100644
index 000000000000..7867e893fd15
--- /dev/null
+++ b/drivers/net/ethernet/amazon/ena/ena_phc.c
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright 2015-2022 Amazon.com, Inc. or its affiliates. All rights reserved.
+ */
+
+#include <linux/pci.h>
+#include "ena_netdev.h"
+#include "ena_phc.h"
+#include "ena_devlink.h"
+
+static int ena_phc_adjtime(struct ptp_clock_info *clock_info, s64 delta)
+{
+	return -EOPNOTSUPP;
+}
+
+static int ena_phc_adjfine(struct ptp_clock_info *clock_info, long scaled_ppm)
+{
+	return -EOPNOTSUPP;
+}
+
+static int ena_phc_feature_enable(struct ptp_clock_info *clock_info,
+				  struct ptp_clock_request *rq,
+				  int on)
+{
+	return -EOPNOTSUPP;
+}
+
+static int ena_phc_gettimex64(struct ptp_clock_info *clock_info,
+			      struct timespec64 *ts,
+			      struct ptp_system_timestamp *sts)
+{
+	struct ena_phc_info *phc_info =
+		container_of(clock_info, struct ena_phc_info, clock_info);
+	unsigned long flags;
+	u64 timestamp_nsec;
+	int rc;
+
+	spin_lock_irqsave(&phc_info->lock, flags);
+
+	ptp_read_system_prets(sts);
+
+	rc = ena_com_phc_get_timestamp(phc_info->adapter->ena_dev,
+				       &timestamp_nsec);
+
+	ptp_read_system_postts(sts);
+
+	spin_unlock_irqrestore(&phc_info->lock, flags);
+
+	*ts = ns_to_timespec64(timestamp_nsec);
+
+	return rc;
+}
+
+static int ena_phc_settime64(struct ptp_clock_info *clock_info,
+			     const struct timespec64 *ts)
+{
+	return -EOPNOTSUPP;
+}
+
+static struct ptp_clock_info ena_ptp_clock_info = {
+	.owner		= THIS_MODULE,
+	.n_alarm	= 0,
+	.n_ext_ts	= 0,
+	.n_per_out	= 0,
+	.pps		= 0,
+	.adjtime	= ena_phc_adjtime,
+	.adjfine	= ena_phc_adjfine,
+	.gettimex64	= ena_phc_gettimex64,
+	.settime64	= ena_phc_settime64,
+	.enable		= ena_phc_feature_enable,
+};
+
+/* Enable/Disable PHC by the kernel, affects on the next init flow */
+void ena_phc_enable(struct ena_adapter *adapter, bool enable)
+{
+	struct ena_phc_info *phc_info = adapter->phc_info;
+
+	if (!phc_info) {
+		netdev_err(adapter->netdev, "phc_info is not allocated\n");
+		return;
+	}
+
+	phc_info->enabled = enable;
+}
+
+/* Check if PHC is enabled by the kernel */
+bool ena_phc_is_enabled(struct ena_adapter *adapter)
+{
+	struct ena_phc_info *phc_info = adapter->phc_info;
+
+	return (phc_info && phc_info->enabled);
+}
+
+/* PHC is activated if ptp clock is registered in the kernel */
+bool ena_phc_is_active(struct ena_adapter *adapter)
+{
+	struct ena_phc_info *phc_info = adapter->phc_info;
+
+	return (phc_info && phc_info->clock);
+}
+
+static int ena_phc_register(struct ena_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct ptp_clock_info *clock_info;
+	struct ena_phc_info *phc_info;
+	int rc = 0;
+
+	phc_info = adapter->phc_info;
+	clock_info = &phc_info->clock_info;
+
+	/* PHC may already be registered in case of a reset */
+	if (ena_phc_is_active(adapter))
+		return 0;
+
+	phc_info->adapter = adapter;
+
+	spin_lock_init(&phc_info->lock);
+
+	/* Fill the ptp_clock_info struct and register PTP clock */
+	*clock_info = ena_ptp_clock_info;
+	snprintf(clock_info->name,
+		 sizeof(clock_info->name),
+		 "ena-ptp-%02x",
+		 PCI_SLOT(pdev->devfn));
+
+	phc_info->clock = ptp_clock_register(clock_info, &pdev->dev);
+	if (IS_ERR(phc_info->clock)) {
+		rc = PTR_ERR(phc_info->clock);
+		netdev_err(adapter->netdev, "Failed registering ptp clock, error: %d\n",
+			   rc);
+		phc_info->clock = NULL;
+	}
+
+	return rc;
+}
+
+static void ena_phc_unregister(struct ena_adapter *adapter)
+{
+	struct ena_phc_info *phc_info = adapter->phc_info;
+
+	/* During reset flow, PHC must stay registered
+	 * to keep kernel's PHC index
+	 */
+	if (ena_phc_is_active(adapter) &&
+	    !test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags)) {
+		ptp_clock_unregister(phc_info->clock);
+		phc_info->clock = NULL;
+	}
+}
+
+int ena_phc_alloc(struct ena_adapter *adapter)
+{
+	/* Allocate driver specific PHC info */
+	adapter->phc_info = vzalloc(sizeof(*adapter->phc_info));
+	if (unlikely(!adapter->phc_info)) {
+		netdev_err(adapter->netdev, "Failed to alloc phc_info\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void ena_phc_free(struct ena_adapter *adapter)
+{
+	if (adapter->phc_info) {
+		vfree(adapter->phc_info);
+		adapter->phc_info = NULL;
+	}
+}
+
+int ena_phc_init(struct ena_adapter *adapter)
+{
+	struct ena_com_dev *ena_dev = adapter->ena_dev;
+	struct net_device *netdev = adapter->netdev;
+	int rc = -EOPNOTSUPP;
+
+	/* Validate PHC feature is supported in the device */
+	if (!ena_com_phc_supported(ena_dev)) {
+		netdev_dbg(netdev, "PHC feature is not supported by the device\n");
+		goto err_ena_com_phc_init;
+	}
+
+	/* Validate PHC feature is enabled by the kernel */
+	if (!ena_phc_is_enabled(adapter)) {
+		netdev_dbg(netdev, "PHC feature is not enabled by the kernel\n");
+		goto err_ena_com_phc_init;
+	}
+
+	/* Initialize device specific PHC info */
+	rc = ena_com_phc_init(ena_dev);
+	if (unlikely(rc)) {
+		netdev_err(netdev, "Failed to init phc, error: %d\n", rc);
+		goto err_ena_com_phc_init;
+	}
+
+	/* Configure PHC feature in driver and device */
+	rc = ena_com_phc_config(ena_dev);
+	if (unlikely(rc)) {
+		netdev_err(netdev, "Failed to config phc, error: %d\n", rc);
+		goto err_ena_com_phc_config;
+	}
+
+	/* Register to PTP class driver */
+	rc = ena_phc_register(adapter);
+	if (unlikely(rc)) {
+		netdev_err(netdev, "Failed to register phc, error: %d\n", rc);
+		goto err_ena_com_phc_config;
+	}
+
+	return 0;
+
+err_ena_com_phc_config:
+	ena_com_phc_destroy(ena_dev);
+err_ena_com_phc_init:
+	ena_phc_enable(adapter, false);
+	ena_devlink_disable_phc_param(adapter->devlink);
+	return rc;
+}
+
+void ena_phc_destroy(struct ena_adapter *adapter)
+{
+	ena_phc_unregister(adapter);
+	ena_com_phc_destroy(adapter->ena_dev);
+}
+
+int ena_phc_get_index(struct ena_adapter *adapter)
+{
+	if (ena_phc_is_active(adapter))
+		return ptp_clock_index(adapter->phc_info->clock);
+
+	return -1;
+}
diff --git a/drivers/net/ethernet/amazon/ena/ena_phc.h b/drivers/net/ethernet/amazon/ena/ena_phc.h
new file mode 100644
index 000000000000..7364fe714e44
--- /dev/null
+++ b/drivers/net/ethernet/amazon/ena/ena_phc.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * Copyright 2015-2022 Amazon.com, Inc. or its affiliates. All rights reserved.
+ */
+
+#ifndef ENA_PHC_H
+#define ENA_PHC_H
+
+#include <linux/ptp_clock_kernel.h>
+
+struct ena_phc_info {
+	/* PTP hardware capabilities */
+	struct ptp_clock_info clock_info;
+
+	/* Registered PTP clock device */
+	struct ptp_clock *clock;
+
+	/* Adapter specific private data structure */
+	struct ena_adapter *adapter;
+
+	/* PHC lock */
+	spinlock_t lock;
+
+	/* Enabled by kernel */
+	bool enabled;
+};
+
+void ena_phc_enable(struct ena_adapter *adapter, bool enable);
+bool ena_phc_is_enabled(struct ena_adapter *adapter);
+bool ena_phc_is_active(struct ena_adapter *adapter);
+int ena_phc_get_index(struct ena_adapter *adapter);
+int ena_phc_init(struct ena_adapter *adapter);
+void ena_phc_destroy(struct ena_adapter *adapter);
+int ena_phc_alloc(struct ena_adapter *adapter);
+void ena_phc_free(struct ena_adapter *adapter);
+
+#endif /* ENA_PHC_H */
diff --git a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
index a2efebafd686..51068dc1cc2a 100644
--- a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
@@ -53,6 +53,11 @@ enum ena_regs_reset_reason_types {
 #define ENA_REGS_MMIO_RESP_HI_OFF                           0x64
 #define ENA_REGS_RSS_IND_ENTRY_UPDATE_OFF                   0x68
 
+/* phc_registers offsets */
+
+/* 100 base */
+#define ENA_REGS_PHC_DB_OFF                                 0x100
+
 /* version register */
 #define ENA_REGS_VERSION_MINOR_VERSION_MASK                 0xff
 #define ENA_REGS_VERSION_MAJOR_VERSION_SHIFT                8
@@ -129,4 +134,7 @@ enum ena_regs_reset_reason_types {
 #define ENA_REGS_RSS_IND_ENTRY_UPDATE_CQ_IDX_SHIFT          16
 #define ENA_REGS_RSS_IND_ENTRY_UPDATE_CQ_IDX_MASK           0xffff0000
 
+/* phc_db_req_id register */
+#define ENA_REGS_PHC_DB_REQ_ID_MASK                         0xffff
+
 #endif /* _ENA_REGS_H_ */
diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig
index b39c6f3e1eda..d54dca3074eb 100644
--- a/drivers/net/ethernet/amd/Kconfig
+++ b/drivers/net/ethernet/amd/Kconfig
@@ -165,6 +165,7 @@ config AMD_XGBE
 	select CRC32
 	select PHYLIB
 	select AMD_XGBE_HAVE_ECC if X86
+	select NET_SELFTESTS
 	help
 	  This driver supports the AMD 10GbE Ethernet device found on an
 	  AMD SoC.
diff --git a/drivers/net/ethernet/amd/a2065.c b/drivers/net/ethernet/amd/a2065.c
index 1ca26a8c40eb..ce9445425045 100644
--- a/drivers/net/ethernet/amd/a2065.c
+++ b/drivers/net/ethernet/amd/a2065.c
@@ -486,7 +486,7 @@ static int lance_close(struct net_device *dev)
 	volatile struct lance_regs *ll = lp->ll;
 
 	netif_stop_queue(dev);
-	del_timer_sync(&lp->multicast_timer);
+	timer_delete_sync(&lp->multicast_timer);
 
 	/* Stop the card */
 	ll->rap = LE_CSR0;
@@ -636,7 +636,7 @@ static void lance_set_multicast(struct net_device *dev)
 
 static void lance_set_multicast_retry(struct timer_list *t)
 {
-	struct lance_private *lp = from_timer(lp, t, multicast_timer);
+	struct lance_private *lp = timer_container_of(lp, t, multicast_timer);
 
 	lance_set_multicast(lp->dev);
 }
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index f64f96fa17cf..76e8c13d5985 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -1173,7 +1173,7 @@ static int amd8111e_close(struct net_device *dev)
 
 	/* Delete ipg timer */
 	if (lp->options & OPTION_DYN_IPG_ENABLE)
-		del_timer_sync(&lp->ipg_data.ipg_timer);
+		timer_delete_sync(&lp->ipg_data.ipg_timer);
 
 	spin_unlock_irq(&lp->lock);
 	free_irq(dev->irq, dev);
@@ -1598,7 +1598,7 @@ static int __maybe_unused amd8111e_suspend(struct device *dev_d)
 	/* stop chip */
 	spin_lock_irq(&lp->lock);
 	if (lp->options & OPTION_DYN_IPG_ENABLE)
-		del_timer_sync(&lp->ipg_data.ipg_timer);
+		timer_delete_sync(&lp->ipg_data.ipg_timer);
 	amd8111e_stop_chip(lp);
 	spin_unlock_irq(&lp->lock);
 
@@ -1641,7 +1641,8 @@ static int __maybe_unused amd8111e_resume(struct device *dev_d)
 
 static void amd8111e_config_ipg(struct timer_list *t)
 {
-	struct amd8111e_priv *lp = from_timer(lp, t, ipg_data.ipg_timer);
+	struct amd8111e_priv *lp = timer_container_of(lp, t,
+						      ipg_data.ipg_timer);
 	struct ipg_info *ipg_data = &lp->ipg_data;
 	void __iomem *mmio = lp->mmio;
 	unsigned int prev_col_cnt = ipg_data->col_cnt;
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index 0671a066913b..9d35ac348ebe 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -571,7 +571,7 @@ static struct db_dest *au1000_GetFreeDB(struct au1000_private *aup)
 	return pDB;
 }
 
-void au1000_ReleaseDB(struct au1000_private *aup, struct db_dest *pDB)
+static void au1000_ReleaseDB(struct au1000_private *aup, struct db_dest *pDB)
 {
 	struct db_dest *pDBfree = aup->pDBfree;
 	if (pDBfree)
diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c
index ec8df05e7bf6..8d05a0c5f2d5 100644
--- a/drivers/net/ethernet/amd/declance.c
+++ b/drivers/net/ethernet/amd/declance.c
@@ -842,7 +842,7 @@ static int lance_close(struct net_device *dev)
 	volatile struct lance_regs *ll = lp->ll;
 
 	netif_stop_queue(dev);
-	del_timer_sync(&lp->multicast_timer);
+	timer_delete_sync(&lp->multicast_timer);
 
 	/* Stop the card */
 	writereg(&ll->rap, LE_CSR0);
@@ -1004,7 +1004,7 @@ static void lance_set_multicast(struct net_device *dev)
 
 static void lance_set_multicast_retry(struct timer_list *t)
 {
-	struct lance_private *lp = from_timer(lp, t, multicast_timer);
+	struct lance_private *lp = timer_container_of(lp, t, multicast_timer);
 	struct net_device *dev = lp->dev;
 
 	lance_set_multicast(dev);
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index 72db9f9e7bee..9eaefa0f5e80 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -462,7 +462,7 @@ static void pcnet32_netif_start(struct net_device *dev)
 	val = lp->a->read_csr(ioaddr, CSR3);
 	val &= 0x00ff;
 	lp->a->write_csr(ioaddr, CSR3, val);
-	napi_enable(&lp->napi);
+	napi_enable_locked(&lp->napi);
 }
 
 /*
@@ -889,6 +889,7 @@ static int pcnet32_set_ringparam(struct net_device *dev,
 	if (netif_running(dev))
 		pcnet32_netif_stop(dev);
 
+	netdev_lock(dev);
 	spin_lock_irqsave(&lp->lock, flags);
 	lp->a->write_csr(ioaddr, CSR0, CSR0_STOP);	/* stop the chip */
 
@@ -920,6 +921,7 @@ static int pcnet32_set_ringparam(struct net_device *dev,
 	}
 
 	spin_unlock_irqrestore(&lp->lock, flags);
+	netdev_unlock(dev);
 
 	netif_info(lp, drv, dev, "Ring Param Settings: RX: %d, TX: %d\n",
 		   lp->rx_ring_size, lp->tx_ring_size);
@@ -985,6 +987,7 @@ static int pcnet32_loopback_test(struct net_device *dev, uint64_t * data1)
 	if (netif_running(dev))
 		pcnet32_netif_stop(dev);
 
+	netdev_lock(dev);
 	spin_lock_irqsave(&lp->lock, flags);
 	lp->a->write_csr(ioaddr, CSR0, CSR0_STOP);	/* stop the chip */
 
@@ -1122,6 +1125,7 @@ clean_up:
 		lp->a->write_bcr(ioaddr, 20, 4);	/* return to 16bit mode */
 	}
 	spin_unlock_irqrestore(&lp->lock, flags);
+	netdev_unlock(dev);
 
 	return rc;
 }				/* end pcnet32_loopback_test  */
@@ -2101,6 +2105,7 @@ static int pcnet32_open(struct net_device *dev)
 		return -EAGAIN;
 	}
 
+	netdev_lock(dev);
 	spin_lock_irqsave(&lp->lock, flags);
 	/* Check for a valid station address */
 	if (!is_valid_ether_addr(dev->dev_addr)) {
@@ -2266,7 +2271,7 @@ static int pcnet32_open(struct net_device *dev)
 		goto err_free_ring;
 	}
 
-	napi_enable(&lp->napi);
+	napi_enable_locked(&lp->napi);
 
 	/* Re-initialize the PCNET32, and start it when done. */
 	lp->a->write_csr(ioaddr, 1, (lp->init_dma_addr & 0xffff));
@@ -2300,6 +2305,7 @@ static int pcnet32_open(struct net_device *dev)
 		     lp->a->read_csr(ioaddr, CSR0));
 
 	spin_unlock_irqrestore(&lp->lock, flags);
+	netdev_unlock(dev);
 
 	return 0;		/* Always succeed */
 
@@ -2315,6 +2321,7 @@ err_free_ring:
 
 err_free_irq:
 	spin_unlock_irqrestore(&lp->lock, flags);
+	netdev_unlock(dev);
 	free_irq(dev->irq, dev);
 	return rc;
 }
@@ -2623,7 +2630,7 @@ static int pcnet32_close(struct net_device *dev)
 	struct pcnet32_private *lp = netdev_priv(dev);
 	unsigned long flags;
 
-	del_timer_sync(&lp->watchdog_timer);
+	timer_delete_sync(&lp->watchdog_timer);
 
 	netif_stop_queue(dev);
 	napi_disable(&lp->napi);
@@ -2898,7 +2905,7 @@ static void pcnet32_check_media(struct net_device *dev, int verbose)
 
 static void pcnet32_watchdog(struct timer_list *t)
 {
-	struct pcnet32_private *lp = from_timer(lp, t, watchdog_timer);
+	struct pcnet32_private *lp = timer_container_of(lp, t, watchdog_timer);
 	struct net_device *dev = lp->dev;
 	unsigned long flags;
 
diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index c83a0a80d533..097bb092bdb8 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -5,11 +5,6 @@
 
 #include "core.h"
 
-struct pdsc_wait_context {
-	struct pdsc_qcq *qcq;
-	struct completion wait_completion;
-};
-
 static int pdsc_process_notifyq(struct pdsc_qcq *qcq)
 {
 	union pds_core_notifyq_comp *comp;
@@ -109,10 +104,10 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq)
 		q_info = &q->info[q->tail_idx];
 		q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1);
 
-		/* Copy out the completion data */
-		memcpy(q_info->dest, comp, sizeof(*comp));
-
-		complete_all(&q_info->wc->wait_completion);
+		if (!completion_done(&q_info->completion)) {
+			memcpy(q_info->dest, comp, sizeof(*comp));
+			complete(&q_info->completion);
+		}
 
 		if (cq->tail_idx == cq->num_descs - 1)
 			cq->done_color = !cq->done_color;
@@ -162,8 +157,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
 static int __pdsc_adminq_post(struct pdsc *pdsc,
 			      struct pdsc_qcq *qcq,
 			      union pds_core_adminq_cmd *cmd,
-			      union pds_core_adminq_comp *comp,
-			      struct pdsc_wait_context *wc)
+			      union pds_core_adminq_comp *comp)
 {
 	struct pdsc_queue *q = &qcq->q;
 	struct pdsc_q_info *q_info;
@@ -205,9 +199,9 @@ static int __pdsc_adminq_post(struct pdsc *pdsc,
 	/* Post the request */
 	index = q->head_idx;
 	q_info = &q->info[index];
-	q_info->wc = wc;
 	q_info->dest = comp;
 	memcpy(q_info->desc, cmd, sizeof(*cmd));
+	reinit_completion(&q_info->completion);
 
 	dev_dbg(pdsc->dev, "head_idx %d tail_idx %d\n",
 		q->head_idx, q->tail_idx);
@@ -231,16 +225,13 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 		     union pds_core_adminq_comp *comp,
 		     bool fast_poll)
 {
-	struct pdsc_wait_context wc = {
-		.wait_completion =
-			COMPLETION_INITIALIZER_ONSTACK(wc.wait_completion),
-	};
-	unsigned long poll_interval = 1;
+	unsigned long poll_interval = 200;
 	unsigned long poll_jiffies;
 	unsigned long time_limit;
 	unsigned long time_start;
 	unsigned long time_done;
 	unsigned long remaining;
+	struct completion *wc;
 	int err = 0;
 	int index;
 
@@ -250,20 +241,19 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 		return -ENXIO;
 	}
 
-	wc.qcq = &pdsc->adminqcq;
-	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc);
+	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp);
 	if (index < 0) {
 		err = index;
 		goto err_out;
 	}
 
+	wc = &pdsc->adminqcq.q.info[index].completion;
 	time_start = jiffies;
 	time_limit = time_start + HZ * pdsc->devcmd_timeout;
 	do {
 		/* Timeslice the actual wait to catch IO errors etc early */
-		poll_jiffies = msecs_to_jiffies(poll_interval);
-		remaining = wait_for_completion_timeout(&wc.wait_completion,
-							poll_jiffies);
+		poll_jiffies = usecs_to_jiffies(poll_interval);
+		remaining = wait_for_completion_timeout(wc, poll_jiffies);
 		if (remaining)
 			break;
 
@@ -292,9 +282,11 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 	dev_dbg(pdsc->dev, "%s: elapsed %d msecs\n",
 		__func__, jiffies_to_msecs(time_done - time_start));
 
-	/* Check the results */
-	if (time_after_eq(time_done, time_limit))
+	/* Check the results and clear an un-completed timeout */
+	if (time_after_eq(time_done, time_limit) && !completion_done(wc)) {
 		err = -ETIMEDOUT;
+		complete(wc);
+	}
 
 	dev_dbg(pdsc->dev, "read admin queue completion idx %d:\n", index);
 	dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1,
diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c
index 2babea110991..92f359f2b449 100644
--- a/drivers/net/ethernet/amd/pds_core/auxbus.c
+++ b/drivers/net/ethernet/amd/pds_core/auxbus.c
@@ -107,9 +107,6 @@ int pds_client_adminq_cmd(struct pds_auxiliary_dev *padev,
 	dev_dbg(pf->dev, "%s: %s opcode %d\n",
 		__func__, dev_name(&padev->aux_dev.dev), req->opcode);
 
-	if (pf->state)
-		return -ENXIO;
-
 	/* Wrap the client's request */
 	cmd.client_request.opcode = PDS_AQ_CMD_CLIENT_CMD;
 	cmd.client_request.client_id = cpu_to_le16(padev->client_id);
@@ -175,34 +172,31 @@ static struct pds_auxiliary_dev *pdsc_auxbus_dev_register(struct pdsc *cf,
 	return padev;
 }
 
-int pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf)
+void pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf,
+			 struct pds_auxiliary_dev **pd_ptr)
 {
 	struct pds_auxiliary_dev *padev;
-	int err = 0;
 
-	if (!cf)
-		return -ENODEV;
+	if (!*pd_ptr)
+		return;
 
 	mutex_lock(&pf->config_lock);
 
-	padev = pf->vfs[cf->vf_id].padev;
-	if (padev) {
-		pds_client_unregister(pf, padev->client_id);
-		auxiliary_device_delete(&padev->aux_dev);
-		auxiliary_device_uninit(&padev->aux_dev);
-		padev->client_id = 0;
-	}
-	pf->vfs[cf->vf_id].padev = NULL;
+	padev = *pd_ptr;
+	pds_client_unregister(pf, padev->client_id);
+	auxiliary_device_delete(&padev->aux_dev);
+	auxiliary_device_uninit(&padev->aux_dev);
+	*pd_ptr = NULL;
 
 	mutex_unlock(&pf->config_lock);
-	return err;
 }
 
-int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf)
+int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf,
+			enum pds_core_vif_types vt,
+			struct pds_auxiliary_dev **pd_ptr)
 {
 	struct pds_auxiliary_dev *padev;
 	char devname[PDS_DEVNAME_LEN];
-	enum pds_core_vif_types vt;
 	unsigned long mask;
 	u16 vt_support;
 	int client_id;
@@ -211,6 +205,9 @@ int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf)
 	if (!cf)
 		return -ENODEV;
 
+	if (vt >= PDS_DEV_TYPE_MAX)
+		return -EINVAL;
+
 	mutex_lock(&pf->config_lock);
 
 	mask = BIT_ULL(PDSC_S_FW_DEAD) |
@@ -222,17 +219,10 @@ int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf)
 		goto out_unlock;
 	}
 
-	/* We only support vDPA so far, so it is the only one to
-	 * be verified that it is available in the Core device and
-	 * enabled in the devlink param.  In the future this might
-	 * become a loop for several VIF types.
-	 */
-
 	/* Verify that the type is supported and enabled.  It is not
-	 * an error if there is no auxbus device support for this
-	 * VF, it just means something else needs to happen with it.
+	 * an error if the firmware doesn't support the feature, the
+	 * driver just won't set up an auxiliary_device for it.
 	 */
-	vt = PDS_DEV_TYPE_VDPA;
 	vt_support = !!le16_to_cpu(pf->dev_ident.vif_types[vt]);
 	if (!(vt_support &&
 	      pf->viftype_status[vt].supported &&
@@ -258,7 +248,7 @@ int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf)
 		err = PTR_ERR(padev);
 		goto out_unlock;
 	}
-	pf->vfs[cf->vf_id].padev = padev;
+	*pd_ptr = padev;
 
 out_unlock:
 	mutex_unlock(&pf->config_lock);
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 536635e57727..076dfe2910c7 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -167,8 +167,10 @@ static void pdsc_q_map(struct pdsc_queue *q, void *base, dma_addr_t base_pa)
 	q->base = base;
 	q->base_pa = base_pa;
 
-	for (i = 0, cur = q->info; i < q->num_descs; i++, cur++)
+	for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) {
 		cur->desc = base + (i * q->desc_size);
+		init_completion(&cur->completion);
+	}
 }
 
 static void pdsc_cq_map(struct pdsc_cq *cq, void *base, dma_addr_t base_pa)
@@ -325,10 +327,7 @@ static int pdsc_core_init(struct pdsc *pdsc)
 	size_t sz;
 	int err;
 
-	/* Scale the descriptor ring length based on number of CPUs and VFs */
-	numdescs = max_t(int, PDSC_ADMINQ_MIN_LENGTH, num_online_cpus());
-	numdescs += 2 * pci_sriov_get_totalvfs(pdsc->pdev);
-	numdescs = roundup_pow_of_two(numdescs);
+	numdescs = PDSC_ADMINQ_MAX_LENGTH;
 	err = pdsc_qcq_alloc(pdsc, PDS_CORE_QTYPE_ADMINQ, 0, "adminq",
 			     PDS_CORE_QCQ_F_CORE | PDS_CORE_QCQ_F_INTR,
 			     numdescs,
@@ -402,6 +401,10 @@ err_out_uninit:
 }
 
 static struct pdsc_viftype pdsc_viftype_defaults[] = {
+	[PDS_DEV_TYPE_FWCTL] = { .name = PDS_DEV_TYPE_FWCTL_STR,
+				 .enabled = true,
+				 .vif_id = PDS_DEV_TYPE_FWCTL,
+				 .dl_id = -1 },
 	[PDS_DEV_TYPE_VDPA] = { .name = PDS_DEV_TYPE_VDPA_STR,
 				.vif_id = PDS_DEV_TYPE_VDPA,
 				.dl_id = DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET },
@@ -412,7 +415,8 @@ static int pdsc_viftypes_init(struct pdsc *pdsc)
 {
 	enum pds_core_vif_types vt;
 
-	pdsc->viftype_status = kzalloc(sizeof(pdsc_viftype_defaults),
+	pdsc->viftype_status = kcalloc(ARRAY_SIZE(pdsc_viftype_defaults),
+				       sizeof(*pdsc->viftype_status),
 				       GFP_KERNEL);
 	if (!pdsc->viftype_status)
 		return -ENOMEM;
@@ -428,6 +432,7 @@ static int pdsc_viftypes_init(struct pdsc *pdsc)
 
 		/* See what the Core device has for support */
 		vt_support = !!le16_to_cpu(pdsc->dev_ident.vif_types[vt]);
+
 		dev_dbg(pdsc->dev, "VIF %s is %ssupported\n",
 			pdsc->viftype_status[vt].name,
 			vt_support ? "" : "not ");
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index 14522d6d5f86..4a6b35c84dab 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -16,7 +16,7 @@
 
 #define PDSC_WATCHDOG_SECS	5
 #define PDSC_QUEUE_NAME_MAX_SZ  16
-#define PDSC_ADMINQ_MIN_LENGTH	16	/* must be a power of two */
+#define PDSC_ADMINQ_MAX_LENGTH	16	/* must be a power of two */
 #define PDSC_NOTIFYQ_LENGTH	64	/* must be a power of two */
 #define PDSC_TEARDOWN_RECOVERY	false
 #define PDSC_TEARDOWN_REMOVING	true
@@ -96,7 +96,7 @@ struct pdsc_q_info {
 	unsigned int bytes;
 	unsigned int nbufs;
 	struct pdsc_buf_info bufs[PDS_CORE_MAX_FRAGS];
-	struct pdsc_wait_context *wc;
+	struct completion completion;
 	void *dest;
 };
 
@@ -156,6 +156,7 @@ struct pdsc {
 	struct dentry *dentry;
 	struct device *dev;
 	struct pdsc_dev_bar bars[PDS_CORE_BARS_MAX];
+	struct pds_auxiliary_dev *padev;
 	struct pdsc_vf *vfs;
 	int num_vfs;
 	int vf_id;
@@ -254,7 +255,8 @@ int pdsc_dl_flash_update(struct devlink *dl,
 			 struct devlink_flash_update_params *params,
 			 struct netlink_ext_ack *extack);
 int pdsc_dl_enable_get(struct devlink *dl, u32 id,
-		       struct devlink_param_gset_ctx *ctx);
+		       struct devlink_param_gset_ctx *ctx,
+		       struct netlink_ext_ack *extack);
 int pdsc_dl_enable_set(struct devlink *dl, u32 id,
 		       struct devlink_param_gset_ctx *ctx,
 		       struct netlink_ext_ack *extack);
@@ -303,8 +305,11 @@ void pdsc_health_thread(struct work_struct *work);
 int pdsc_register_notify(struct notifier_block *nb);
 void pdsc_unregister_notify(struct notifier_block *nb);
 void pdsc_notify(unsigned long event, void *data);
-int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf);
-int pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf);
+int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf,
+			enum pds_core_vif_types vt,
+			struct pds_auxiliary_dev **pd_ptr);
+void pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf,
+			 struct pds_auxiliary_dev **pd_ptr);
 
 void pdsc_process_adminq(struct pdsc_qcq *qcq);
 void pdsc_work_thread(struct work_struct *work);
diff --git a/drivers/net/ethernet/amd/pds_core/debugfs.c b/drivers/net/ethernet/amd/pds_core/debugfs.c
index ac37a4e738ae..04c5e3abd8d7 100644
--- a/drivers/net/ethernet/amd/pds_core/debugfs.c
+++ b/drivers/net/ethernet/amd/pds_core/debugfs.c
@@ -154,8 +154,9 @@ void pdsc_debugfs_add_qcq(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 		debugfs_create_u32("index", 0400, intr_dentry, &intr->index);
 		debugfs_create_u32("vector", 0400, intr_dentry, &intr->vector);
 
-		intr_ctrl_regset = kzalloc(sizeof(*intr_ctrl_regset),
-					   GFP_KERNEL);
+		intr_ctrl_regset = devm_kzalloc(pdsc->dev,
+						sizeof(*intr_ctrl_regset),
+						GFP_KERNEL);
 		if (!intr_ctrl_regset)
 			return;
 		intr_ctrl_regset->regs = intr_ctrl_regs;
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index 2681889162a2..b576be626a29 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -22,7 +22,8 @@ pdsc_viftype *pdsc_dl_find_viftype_by_id(struct pdsc *pdsc,
 }
 
 int pdsc_dl_enable_get(struct devlink *dl, u32 id,
-		       struct devlink_param_gset_ctx *ctx)
+		       struct devlink_param_gset_ctx *ctx,
+		       struct netlink_ext_ack *extack)
 {
 	struct pdsc *pdsc = devlink_priv(dl);
 	struct pdsc_viftype *vt_entry;
@@ -56,8 +57,11 @@ int pdsc_dl_enable_set(struct devlink *dl, u32 id,
 	for (vf_id = 0; vf_id < pdsc->num_vfs; vf_id++) {
 		struct pdsc *vf = pdsc->vfs[vf_id].vf;
 
-		err = ctx->val.vbool ? pdsc_auxbus_dev_add(vf, pdsc) :
-				       pdsc_auxbus_dev_del(vf, pdsc);
+		if (ctx->val.vbool)
+			err = pdsc_auxbus_dev_add(vf, pdsc, vt_entry->vif_id,
+						  &pdsc->vfs[vf_id].padev);
+		else
+			pdsc_auxbus_dev_del(vf, pdsc, &pdsc->vfs[vf_id].padev);
 	}
 
 	return err;
@@ -102,7 +106,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 		.fw_control.opcode = PDS_CORE_CMD_FW_CONTROL,
 		.fw_control.oper = PDS_CORE_FW_GET_LIST,
 	};
-	struct pds_core_fw_list_info fw_list;
+	struct pds_core_fw_list_info fw_list = {};
 	struct pdsc *pdsc = devlink_priv(dl);
 	union pds_core_dev_comp comp;
 	char buf[32];
@@ -115,10 +119,8 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 	if (!err)
 		memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
 	mutex_unlock(&pdsc->devcmd_lock);
-	if (err && err != -EIO)
-		return err;
 
-	listlen = fw_list.num_fw_slots;
+	listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names));
 	for (i = 0; i < listlen; i++) {
 		if (i < ARRAY_SIZE(fw_slotnames))
 			strscpy(buf, fw_slotnames[i], sizeof(buf));
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index 660268ff9562..c7a2eff57632 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -23,7 +23,7 @@ MODULE_DEVICE_TABLE(pci, pdsc_id_table);
 
 static void pdsc_wdtimer_cb(struct timer_list *t)
 {
-	struct pdsc *pdsc = from_timer(pdsc, t, wdtimer);
+	struct pdsc *pdsc = timer_container_of(pdsc, t, wdtimer);
 
 	dev_dbg(pdsc->dev, "%s: jiffies %ld\n", __func__, jiffies);
 	mod_timer(&pdsc->wdtimer,
@@ -190,7 +190,8 @@ static int pdsc_init_vf(struct pdsc *vf)
 	devl_unlock(dl);
 
 	pf->vfs[vf->vf_id].vf = vf;
-	err = pdsc_auxbus_dev_add(vf, pf);
+	err = pdsc_auxbus_dev_add(vf, pf, PDS_DEV_TYPE_VDPA,
+				  &pf->vfs[vf->vf_id].padev);
 	if (err) {
 		devl_lock(dl);
 		devl_unregister(dl);
@@ -264,6 +265,10 @@ static int pdsc_init_pf(struct pdsc *pdsc)
 
 	mutex_unlock(&pdsc->config_lock);
 
+	err = pdsc_auxbus_dev_add(pdsc, pdsc, PDS_DEV_TYPE_FWCTL, &pdsc->padev);
+	if (err)
+		goto err_out_stop;
+
 	dl = priv_to_devlink(pdsc);
 	devl_lock(dl);
 	err = devl_params_register(dl, pdsc_dl_params,
@@ -272,10 +277,10 @@ static int pdsc_init_pf(struct pdsc *pdsc)
 		devl_unlock(dl);
 		dev_warn(pdsc->dev, "Failed to register devlink params: %pe\n",
 			 ERR_PTR(err));
-		goto err_out_stop;
+		goto err_out_del_dev;
 	}
 
-	hr = devl_health_reporter_create(dl, &pdsc_fw_reporter_ops, 0, pdsc);
+	hr = devl_health_reporter_create(dl, &pdsc_fw_reporter_ops, pdsc);
 	if (IS_ERR(hr)) {
 		devl_unlock(dl);
 		dev_warn(pdsc->dev, "Failed to create fw reporter: %pe\n", hr);
@@ -295,6 +300,8 @@ static int pdsc_init_pf(struct pdsc *pdsc)
 err_out_unreg_params:
 	devlink_params_unregister(dl, pdsc_dl_params,
 				  ARRAY_SIZE(pdsc_dl_params));
+err_out_del_dev:
+	pdsc_auxbus_dev_del(pdsc, pdsc, &pdsc->padev);
 err_out_stop:
 	pdsc_stop(pdsc);
 err_out_teardown:
@@ -417,7 +424,7 @@ static void pdsc_remove(struct pci_dev *pdev)
 
 		pf = pdsc_get_pf_struct(pdsc->pdev);
 		if (!IS_ERR(pf)) {
-			pdsc_auxbus_dev_del(pdsc, pf);
+			pdsc_auxbus_dev_del(pdsc, pf, &pf->vfs[pdsc->vf_id].padev);
 			pf->vfs[pdsc->vf_id].vf = NULL;
 		}
 	} else {
@@ -426,6 +433,7 @@ static void pdsc_remove(struct pci_dev *pdev)
 		 * shut themselves down.
 		 */
 		pdsc_sriov_configure(pdev, 0);
+		pdsc_auxbus_dev_del(pdsc, pdsc, &pdsc->padev);
 
 		timer_shutdown_sync(&pdsc->wdtimer);
 		if (pdsc->wq)
@@ -482,7 +490,10 @@ static void pdsc_reset_prepare(struct pci_dev *pdev)
 
 		pf = pdsc_get_pf_struct(pdsc->pdev);
 		if (!IS_ERR(pf))
-			pdsc_auxbus_dev_del(pdsc, pf);
+			pdsc_auxbus_dev_del(pdsc, pf,
+					    &pf->vfs[pdsc->vf_id].padev);
+	} else {
+		pdsc_auxbus_dev_del(pdsc, pdsc, &pdsc->padev);
 	}
 
 	pdsc_unmap_bars(pdsc);
@@ -527,7 +538,11 @@ static void pdsc_reset_done(struct pci_dev *pdev)
 
 		pf = pdsc_get_pf_struct(pdsc->pdev);
 		if (!IS_ERR(pf))
-			pdsc_auxbus_dev_add(pdsc, pf);
+			pdsc_auxbus_dev_add(pdsc, pf, PDS_DEV_TYPE_VDPA,
+					    &pf->vfs[pdsc->vf_id].padev);
+	} else {
+		pdsc_auxbus_dev_add(pdsc, pdsc, PDS_DEV_TYPE_FWCTL,
+				    &pdsc->padev);
 	}
 }
 
diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c
index 0f98b92408ed..0b273327f5a6 100644
--- a/drivers/net/ethernet/amd/sunlance.c
+++ b/drivers/net/ethernet/amd/sunlance.c
@@ -963,7 +963,7 @@ static int lance_close(struct net_device *dev)
 	struct lance_private *lp = netdev_priv(dev);
 
 	netif_stop_queue(dev);
-	del_timer_sync(&lp->multicast_timer);
+	timer_delete_sync(&lp->multicast_timer);
 
 	STOP_LANCE(lp);
 
@@ -1246,7 +1246,7 @@ static void lance_set_multicast(struct net_device *dev)
 
 static void lance_set_multicast_retry(struct timer_list *t)
 {
-	struct lance_private *lp = from_timer(lp, t, multicast_timer);
+	struct lance_private *lp = timer_container_of(lp, t, multicast_timer);
 	struct net_device *dev = lp->dev;
 
 	lance_set_multicast(dev);
diff --git a/drivers/net/ethernet/amd/xgbe/Makefile b/drivers/net/ethernet/amd/xgbe/Makefile
index 620785ffbd51..5992f7fd4d9b 100644
--- a/drivers/net/ethernet/amd/xgbe/Makefile
+++ b/drivers/net/ethernet/amd/xgbe/Makefile
@@ -3,9 +3,9 @@ obj-$(CONFIG_AMD_XGBE) += amd-xgbe.o
 
 amd-xgbe-objs := xgbe-main.o xgbe-drv.o xgbe-dev.o \
 		 xgbe-desc.o xgbe-ethtool.o xgbe-mdio.o \
-		 xgbe-ptp.o \
+		 xgbe-hwtstamp.o xgbe-ptp.o xgbe-pps.o \
 		 xgbe-i2c.o xgbe-phy-v1.o xgbe-phy-v2.o \
-		 xgbe-platform.o
+		 xgbe-platform.o xgbe-selftest.o
 
 amd-xgbe-$(CONFIG_PCI) += xgbe-pci.o
 amd-xgbe-$(CONFIG_AMD_XGBE_DCB) += xgbe-dcb.o
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 3b70f6737633..62b01de93db4 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #ifndef __XGBE_COMMON_H__
@@ -332,7 +223,15 @@
 #define MAC_TSSR			0x0d20
 #define MAC_TXSNR			0x0d30
 #define MAC_TXSSR			0x0d34
-
+#define MAC_TICNR                       0x0d58
+#define MAC_TICSNR                      0x0d5C
+#define MAC_TECNR                       0x0d60
+#define MAC_TECSNR                      0x0d64
+#define MAC_PPSCR			0x0d70
+#define MAC_PPS0_TTSR			0x0d80
+#define MAC_PPS0_TTNSR			0x0d84
+#define MAC_PPS0_INTERVAL		0x0d88
+#define MAC_PPS0_WIDTH			0x0d8C
 #define MAC_QTFCR_INC			4
 #define MAC_MACA_INC			4
 #define MAC_HTR_INC			4
@@ -340,6 +239,18 @@
 #define MAC_RQC2_INC			4
 #define MAC_RQC2_Q_PER_REG		4
 
+/* PPS helpers */
+#define PPSEN0				BIT(4)
+#define MAC_PPSx_TTSR(x)		((MAC_PPS0_TTSR) + ((x) * 0x10))
+#define MAC_PPSx_TTNSR(x)		((MAC_PPS0_TTNSR) + ((x) * 0x10))
+#define MAC_PPSx_INTERVAL(x)		((MAC_PPS0_INTERVAL) + ((x) * 0x10))
+#define MAC_PPSx_WIDTH(x)		((MAC_PPS0_WIDTH) + ((x) * 0x10))
+#define PPS_MAXIDX(x)			((((x) + 1) * 8) - 1)
+#define PPS_MINIDX(x)			((x) * 8)
+#define XGBE_PPSCMD_STOP		0x5
+#define XGBE_PPSCMD_START		0x2
+#define XGBE_PPSTARGET_PULSE		0x2
+
 /* MAC register entry bit positions and sizes */
 #define MAC_HWF0R_ADDMACADRSEL_INDEX	18
 #define MAC_HWF0R_ADDMACADRSEL_WIDTH	5
@@ -473,6 +384,10 @@
 #define MAC_RCR_CST_WIDTH		1
 #define MAC_RCR_DCRCC_INDEX		3
 #define MAC_RCR_DCRCC_WIDTH		1
+#define MAC_RCR_GPSLCE_INDEX		6
+#define MAC_RCR_GPSLCE_WIDTH		1
+#define MAC_RCR_WD_INDEX		7
+#define MAC_RCR_WD_WIDTH		1
 #define MAC_RCR_HDSMS_INDEX		12
 #define MAC_RCR_HDSMS_WIDTH		3
 #define MAC_RCR_IPC_INDEX		9
@@ -483,6 +398,8 @@
 #define MAC_RCR_LM_WIDTH		1
 #define MAC_RCR_RE_INDEX		0
 #define MAC_RCR_RE_WIDTH		1
+#define MAC_RCR_GPSL_INDEX		16
+#define MAC_RCR_GPSL_WIDTH		14
 #define MAC_RFCR_PFCE_INDEX		8
 #define MAC_RFCR_PFCE_WIDTH		1
 #define MAC_RFCR_RFE_INDEX		0
@@ -521,6 +438,8 @@
 #define MAC_TCR_VNE_WIDTH		1
 #define MAC_TCR_VNM_INDEX		25
 #define MAC_TCR_VNM_WIDTH		1
+#define MAC_TCR_JD_INDEX		16
+#define MAC_TCR_JD_WIDTH		1
 #define MAC_TIR_TNID_INDEX		0
 #define MAC_TIR_TNID_WIDTH		16
 #define MAC_TSCR_AV8021ASMEN_INDEX	28
@@ -529,6 +448,8 @@
 #define MAC_TSCR_SNAPTYPSEL_WIDTH	2
 #define MAC_TSCR_TSADDREG_INDEX		5
 #define MAC_TSCR_TSADDREG_WIDTH		1
+#define MAC_TSCR_TSUPDT_INDEX		3
+#define MAC_TSCR_TSUPDT_WIDTH		1
 #define MAC_TSCR_TSCFUPDT_INDEX		1
 #define MAC_TSCR_TSCFUPDT_WIDTH		1
 #define MAC_TSCR_TSCTRLSSR_INDEX	9
@@ -557,6 +478,10 @@
 #define MAC_TSSR_TXTSC_WIDTH		1
 #define MAC_TXSNR_TXTSSTSMIS_INDEX	31
 #define MAC_TXSNR_TXTSSTSMIS_WIDTH	1
+#define MAC_TICSNR_TSICSNS_INDEX	8
+#define MAC_TICSNR_TSICSNS_WIDTH	8
+#define MAC_TECSNR_TSECSNS_INDEX	8
+#define MAC_TECSNR_TSECSNS_WIDTH	8
 #define MAC_VLANHTR_VLHT_INDEX		0
 #define MAC_VLANHTR_VLHT_WIDTH		16
 #define MAC_VLANIR_VLTI_INDEX		20
@@ -587,8 +512,10 @@
 #define MAC_VR_SNPSVER_WIDTH		8
 #define MAC_VR_USERVER_INDEX		16
 #define MAC_VR_USERVER_WIDTH		8
+#define MAC_PPSx_TTNSR_TRGTBUSY0_INDEX	31
+#define MAC_PPSx_TTNSR_TRGTBUSY0_WIDTH	1
 
-/* MMC register offsets */
+ /* MMC register offsets */
 #define MMC_CR				0x0800
 #define MMC_RISR			0x0804
 #define MMC_TISR			0x0808
@@ -900,6 +827,11 @@
 #define PCS_V2_RV_WINDOW_SELECT		0x1064
 #define PCS_V2_YC_WINDOW_DEF		0x18060
 #define PCS_V2_YC_WINDOW_SELECT		0x18064
+#define PCS_V3_RN_WINDOW_DEF		0xf8078
+#define PCS_V3_RN_WINDOW_SELECT		0xf807c
+
+#define PCS_RN_SMN_BASE_ADDR		0x11e00000
+#define PCS_RN_PORT_ADDR_SIZE		0x100000
 
 /* PCS register entry bit positions and sizes */
 #define PCS_V2_WINDOW_DEF_OFFSET_INDEX	6
@@ -1373,6 +1305,8 @@
 #define MDIO_VEND2_CTRL1_SS13		BIT(13)
 #endif
 
+#define XGBE_VEND2_MAC_AUTO_SW		BIT(9)
+
 /* MDIO mask values */
 #define XGBE_AN_CL73_INT_CMPLT		BIT(0)
 #define XGBE_AN_CL73_INC_LINK		BIT(1)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c b/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c
index c68ace804e37..1474df5544fa 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
index b0a6c96b6ef4..d9157c4acde9 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/debugfs.h>
@@ -505,21 +396,6 @@ void xgbe_debugfs_exit(struct xgbe_prv_data *pdata)
 
 void xgbe_debugfs_rename(struct xgbe_prv_data *pdata)
 {
-	char *buf;
-
-	if (!pdata->xgbe_debugfs)
-		return;
-
-	buf = kasprintf(GFP_KERNEL, "amd-xgbe-%s", pdata->netdev->name);
-	if (!buf)
-		return;
-
-	if (!strcmp(pdata->xgbe_debugfs->d_name.name, buf))
-		goto out;
-
-	debugfs_rename(pdata->xgbe_debugfs->d_parent, pdata->xgbe_debugfs,
-		       pdata->xgbe_debugfs->d_parent, buf);
-
-out:
-	kfree(buf);
+	debugfs_change_name(pdata->xgbe_debugfs,
+			    "amd-xgbe-%s", pdata->netdev->name);
 }
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index 230726d7b74f..7c8a19988a52 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include "xgbe.h"
@@ -373,8 +264,13 @@ static int xgbe_map_rx_buffer(struct xgbe_prv_data *pdata,
 	}
 
 	/* Set up the header page info */
-	xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
-			     XGBE_SKB_ALLOC_SIZE);
+	if (pdata->netdev->features & NETIF_F_RXCSUM) {
+		xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
+				     XGBE_SKB_ALLOC_SIZE);
+	} else {
+		xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
+				     pdata->rx_buf_size);
+	}
 
 	/* Set up the buffer page info */
 	xgbe_set_buffer_data(&rdata->rx.buf, &ring->rx_buf_pa,
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index f393228d41c7..b646ae575e6a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/phy.h>
@@ -120,9 +11,11 @@
 #include <linux/bitrev.h>
 #include <linux/crc32.h>
 #include <linux/crc32poly.h>
+#include <linux/pci.h>
 
 #include "xgbe.h"
 #include "xgbe-common.h"
+#include "xgbe-smn.h"
 
 static inline unsigned int xgbe_get_max_frame(struct xgbe_prv_data *pdata)
 {
@@ -318,6 +211,20 @@ static void xgbe_config_sph_mode(struct xgbe_prv_data *pdata)
 	}
 
 	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, HDSMS, XGBE_SPH_HDSMS_SIZE);
+	pdata->sph = true;
+}
+
+static void xgbe_disable_sph_mode(struct xgbe_prv_data *pdata)
+{
+	unsigned int i;
+
+	for (i = 0; i < pdata->channel_count; i++) {
+		if (!pdata->channel[i]->rx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(pdata->channel[i], DMA_CH_CR, SPH, 0);
+	}
+	pdata->sph = false;
 }
 
 static int xgbe_write_rss_reg(struct xgbe_prv_data *pdata, unsigned int type,
@@ -1150,18 +1057,19 @@ static int xgbe_set_gpio(struct xgbe_prv_data *pdata, unsigned int gpio)
 	return 0;
 }
 
-static int xgbe_read_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
-				 int mmd_reg)
+static unsigned int xgbe_get_mmd_address(struct xgbe_prv_data *pdata,
+					 int mmd_reg)
 {
-	unsigned long flags;
-	unsigned int mmd_address, index, offset;
-	int mmd_data;
-
-	if (mmd_reg & XGBE_ADDR_C45)
-		mmd_address = mmd_reg & ~XGBE_ADDR_C45;
-	else
-		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+	return (mmd_reg & XGBE_ADDR_C45) ?
+		mmd_reg & ~XGBE_ADDR_C45 :
+		(pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+}
 
+static void xgbe_get_pcs_index_and_offset(struct xgbe_prv_data *pdata,
+					  unsigned int mmd_address,
+					  unsigned int *index,
+					  unsigned int *offset)
+{
 	/* The PCS registers are accessed using mmio. The underlying
 	 * management interface uses indirect addressing to access the MMD
 	 * register sets. This requires accessing of the PCS register in two
@@ -1172,8 +1080,98 @@ static int xgbe_read_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
 	 * offset 1 bit and reading 16 bits of data.
 	 */
 	mmd_address <<= 1;
-	index = mmd_address & ~pdata->xpcs_window_mask;
-	offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
+	*index = mmd_address & ~pdata->xpcs_window_mask;
+	*offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
+}
+
+static int xgbe_read_mmd_regs_v3(struct xgbe_prv_data *pdata, int prtad,
+				 int mmd_reg)
+{
+	unsigned int mmd_address, index, offset;
+	u32 smn_address;
+	int mmd_data;
+	int ret;
+
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
+
+	xgbe_get_pcs_index_and_offset(pdata, mmd_address, &index, &offset);
+
+	smn_address = pdata->smn_base + pdata->xpcs_window_sel_reg;
+	ret = amd_smn_write(0, smn_address, index);
+	if (ret)
+		return ret;
+
+	ret = amd_smn_read(0, pdata->smn_base + offset, &mmd_data);
+	if (ret)
+		return ret;
+
+	mmd_data = (offset % 4) ? FIELD_GET(XGBE_GEN_HI_MASK, mmd_data) :
+				  FIELD_GET(XGBE_GEN_LO_MASK, mmd_data);
+
+	return mmd_data;
+}
+
+static void xgbe_write_mmd_regs_v3(struct xgbe_prv_data *pdata, int prtad,
+				   int mmd_reg, int mmd_data)
+{
+	unsigned int pci_mmd_data, hi_mask, lo_mask;
+	unsigned int mmd_address, index, offset;
+	struct pci_dev *dev;
+	u32 smn_address;
+	int ret;
+
+	dev = pdata->pcidev;
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
+
+	xgbe_get_pcs_index_and_offset(pdata, mmd_address, &index, &offset);
+
+	smn_address = pdata->smn_base + pdata->xpcs_window_sel_reg;
+	ret = amd_smn_write(0, smn_address, index);
+	if (ret) {
+		pci_err(dev, "Failed to write data 0x%x\n", index);
+		return;
+	}
+
+	ret = amd_smn_read(0, pdata->smn_base + offset, &pci_mmd_data);
+	if (ret) {
+		pci_err(dev, "Failed to read data\n");
+		return;
+	}
+
+	if (offset % 4) {
+		hi_mask = FIELD_PREP(XGBE_GEN_HI_MASK, mmd_data);
+		lo_mask = FIELD_GET(XGBE_GEN_LO_MASK, pci_mmd_data);
+	} else {
+		hi_mask = FIELD_PREP(XGBE_GEN_HI_MASK,
+				     FIELD_GET(XGBE_GEN_HI_MASK, pci_mmd_data));
+		lo_mask = FIELD_GET(XGBE_GEN_LO_MASK, mmd_data);
+	}
+
+	pci_mmd_data = hi_mask | lo_mask;
+
+	ret = amd_smn_write(0, smn_address, index);
+	if (ret) {
+		pci_err(dev, "Failed to write data 0x%x\n", index);
+		return;
+	}
+
+	ret = amd_smn_write(0, (pdata->smn_base + offset), pci_mmd_data);
+	if (ret) {
+		pci_err(dev, "Failed to write data 0x%x\n", pci_mmd_data);
+		return;
+	}
+}
+
+static int xgbe_read_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
+				 int mmd_reg)
+{
+	unsigned int mmd_address, index, offset;
+	unsigned long flags;
+	int mmd_data;
+
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
+
+	xgbe_get_pcs_index_and_offset(pdata, mmd_address, &index, &offset);
 
 	spin_lock_irqsave(&pdata->xpcs_lock, flags);
 	XPCS32_IOWRITE(pdata, pdata->xpcs_window_sel_reg, index);
@@ -1189,23 +1187,9 @@ static void xgbe_write_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
 	unsigned long flags;
 	unsigned int mmd_address, index, offset;
 
-	if (mmd_reg & XGBE_ADDR_C45)
-		mmd_address = mmd_reg & ~XGBE_ADDR_C45;
-	else
-		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
 
-	/* The PCS registers are accessed using mmio. The underlying
-	 * management interface uses indirect addressing to access the MMD
-	 * register sets. This requires accessing of the PCS register in two
-	 * phases, an address phase and a data phase.
-	 *
-	 * The mmio interface is based on 16-bit offsets and values. All
-	 * register offsets must therefore be adjusted by left shifting the
-	 * offset 1 bit and writing 16 bits of data.
-	 */
-	mmd_address <<= 1;
-	index = mmd_address & ~pdata->xpcs_window_mask;
-	offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
+	xgbe_get_pcs_index_and_offset(pdata, mmd_address, &index, &offset);
 
 	spin_lock_irqsave(&pdata->xpcs_lock, flags);
 	XPCS32_IOWRITE(pdata, pdata->xpcs_window_sel_reg, index);
@@ -1220,10 +1204,7 @@ static int xgbe_read_mmd_regs_v1(struct xgbe_prv_data *pdata, int prtad,
 	unsigned int mmd_address;
 	int mmd_data;
 
-	if (mmd_reg & XGBE_ADDR_C45)
-		mmd_address = mmd_reg & ~XGBE_ADDR_C45;
-	else
-		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
 
 	/* The PCS registers are accessed using mmio. The underlying APB3
 	 * management interface uses indirect addressing to access the MMD
@@ -1248,10 +1229,7 @@ static void xgbe_write_mmd_regs_v1(struct xgbe_prv_data *pdata, int prtad,
 	unsigned int mmd_address;
 	unsigned long flags;
 
-	if (mmd_reg & XGBE_ADDR_C45)
-		mmd_address = mmd_reg & ~XGBE_ADDR_C45;
-	else
-		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
 
 	/* The PCS registers are accessed using mmio. The underlying APB3
 	 * management interface uses indirect addressing to access the MMD
@@ -1278,6 +1256,9 @@ static int xgbe_read_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
 	case XGBE_XPCS_ACCESS_V2:
 	default:
 		return xgbe_read_mmd_regs_v2(pdata, prtad, mmd_reg);
+
+	case XGBE_XPCS_ACCESS_V3:
+		return xgbe_read_mmd_regs_v3(pdata, prtad, mmd_reg);
 	}
 }
 
@@ -1288,6 +1269,9 @@ static void xgbe_write_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
 	case XGBE_XPCS_ACCESS_V1:
 		return xgbe_write_mmd_regs_v1(pdata, prtad, mmd_reg, mmd_data);
 
+	case XGBE_XPCS_ACCESS_V3:
+		return xgbe_write_mmd_regs_v3(pdata, prtad, mmd_reg, mmd_data);
+
 	case XGBE_XPCS_ACCESS_V2:
 	default:
 		return xgbe_write_mmd_regs_v2(pdata, prtad, mmd_reg, mmd_data);
@@ -1576,125 +1560,6 @@ static void xgbe_rx_desc_init(struct xgbe_channel *channel)
 	DBGPR("<--rx_desc_init\n");
 }
 
-static void xgbe_update_tstamp_addend(struct xgbe_prv_data *pdata,
-				      unsigned int addend)
-{
-	unsigned int count = 10000;
-
-	/* Set the addend register value and tell the device */
-	XGMAC_IOWRITE(pdata, MAC_TSAR, addend);
-	XGMAC_IOWRITE_BITS(pdata, MAC_TSCR, TSADDREG, 1);
-
-	/* Wait for addend update to complete */
-	while (--count && XGMAC_IOREAD_BITS(pdata, MAC_TSCR, TSADDREG))
-		udelay(5);
-
-	if (!count)
-		netdev_err(pdata->netdev,
-			   "timed out updating timestamp addend register\n");
-}
-
-static void xgbe_set_tstamp_time(struct xgbe_prv_data *pdata, unsigned int sec,
-				 unsigned int nsec)
-{
-	unsigned int count = 10000;
-
-	/* Set the time values and tell the device */
-	XGMAC_IOWRITE(pdata, MAC_STSUR, sec);
-	XGMAC_IOWRITE(pdata, MAC_STNUR, nsec);
-	XGMAC_IOWRITE_BITS(pdata, MAC_TSCR, TSINIT, 1);
-
-	/* Wait for time update to complete */
-	while (--count && XGMAC_IOREAD_BITS(pdata, MAC_TSCR, TSINIT))
-		udelay(5);
-
-	if (!count)
-		netdev_err(pdata->netdev, "timed out initializing timestamp\n");
-}
-
-static u64 xgbe_get_tstamp_time(struct xgbe_prv_data *pdata)
-{
-	u64 nsec;
-
-	nsec = XGMAC_IOREAD(pdata, MAC_STSR);
-	nsec *= NSEC_PER_SEC;
-	nsec += XGMAC_IOREAD(pdata, MAC_STNR);
-
-	return nsec;
-}
-
-static u64 xgbe_get_tx_tstamp(struct xgbe_prv_data *pdata)
-{
-	unsigned int tx_snr, tx_ssr;
-	u64 nsec;
-
-	if (pdata->vdata->tx_tstamp_workaround) {
-		tx_snr = XGMAC_IOREAD(pdata, MAC_TXSNR);
-		tx_ssr = XGMAC_IOREAD(pdata, MAC_TXSSR);
-	} else {
-		tx_ssr = XGMAC_IOREAD(pdata, MAC_TXSSR);
-		tx_snr = XGMAC_IOREAD(pdata, MAC_TXSNR);
-	}
-
-	if (XGMAC_GET_BITS(tx_snr, MAC_TXSNR, TXTSSTSMIS))
-		return 0;
-
-	nsec = tx_ssr;
-	nsec *= NSEC_PER_SEC;
-	nsec += tx_snr;
-
-	return nsec;
-}
-
-static void xgbe_get_rx_tstamp(struct xgbe_packet_data *packet,
-			       struct xgbe_ring_desc *rdesc)
-{
-	u64 nsec;
-
-	if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_CONTEXT_DESC3, TSA) &&
-	    !XGMAC_GET_BITS_LE(rdesc->desc3, RX_CONTEXT_DESC3, TSD)) {
-		nsec = le32_to_cpu(rdesc->desc1);
-		nsec <<= 32;
-		nsec |= le32_to_cpu(rdesc->desc0);
-		if (nsec != 0xffffffffffffffffULL) {
-			packet->rx_tstamp = nsec;
-			XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
-				       RX_TSTAMP, 1);
-		}
-	}
-}
-
-static int xgbe_config_tstamp(struct xgbe_prv_data *pdata,
-			      unsigned int mac_tscr)
-{
-	/* Set one nano-second accuracy */
-	XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSCTRLSSR, 1);
-
-	/* Set fine timestamp update */
-	XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSCFUPDT, 1);
-
-	/* Overwrite earlier timestamps */
-	XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TXTSSTSM, 1);
-
-	XGMAC_IOWRITE(pdata, MAC_TSCR, mac_tscr);
-
-	/* Exit if timestamping is not enabled */
-	if (!XGMAC_GET_BITS(mac_tscr, MAC_TSCR, TSENA))
-		return 0;
-
-	/* Initialize time registers */
-	XGMAC_IOWRITE_BITS(pdata, MAC_SSIR, SSINC, XGBE_TSTAMP_SSINC);
-	XGMAC_IOWRITE_BITS(pdata, MAC_SSIR, SNSINC, XGBE_TSTAMP_SNSINC);
-	xgbe_update_tstamp_addend(pdata, pdata->tstamp_addend);
-	xgbe_set_tstamp_time(pdata, 0, 0);
-
-	/* Initialize the timecounter */
-	timecounter_init(&pdata->tstamp_tc, &pdata->tstamp_cc,
-			 ktime_to_ns(ktime_get_real()));
-
-	return 0;
-}
-
 static void xgbe_tx_start_xmit(struct xgbe_channel *channel,
 			       struct xgbe_ring *ring)
 {
@@ -2868,9 +2733,19 @@ static void xgbe_config_jumbo_enable(struct xgbe_prv_data *pdata)
 {
 	unsigned int val;
 
-	val = (pdata->netdev->mtu > XGMAC_STD_PACKET_MTU) ? 1 : 0;
-
-	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, JE, val);
+	if (pdata->netdev->mtu > XGMAC_JUMBO_PACKET_MTU) {
+		XGMAC_IOWRITE_BITS(pdata, MAC_RCR, GPSL,
+				   XGMAC_GIANT_PACKET_MTU);
+		XGMAC_IOWRITE_BITS(pdata, MAC_RCR, WD, 1);
+		XGMAC_IOWRITE_BITS(pdata, MAC_TCR, JD, 1);
+		XGMAC_IOWRITE_BITS(pdata, MAC_RCR, GPSLCE, 1);
+	} else {
+		val = pdata->netdev->mtu > XGMAC_STD_PACKET_MTU ? 1 : 0;
+		XGMAC_IOWRITE_BITS(pdata, MAC_RCR, GPSLCE, 0);
+		XGMAC_IOWRITE_BITS(pdata, MAC_RCR, WD, 0);
+		XGMAC_IOWRITE_BITS(pdata, MAC_TCR, JD, 0);
+		XGMAC_IOWRITE_BITS(pdata, MAC_RCR, JE, val);
+	}
 }
 
 static void xgbe_config_mac_speed(struct xgbe_prv_data *pdata)
@@ -3545,8 +3420,12 @@ static int xgbe_init(struct xgbe_prv_data *pdata)
 	xgbe_config_tx_coalesce(pdata);
 	xgbe_config_rx_buffer_size(pdata);
 	xgbe_config_tso_mode(pdata);
-	xgbe_config_sph_mode(pdata);
-	xgbe_config_rss(pdata);
+
+	if (pdata->netdev->features & NETIF_F_RXCSUM) {
+		xgbe_config_sph_mode(pdata);
+		xgbe_config_rss(pdata);
+	}
+
 	desc_if->wrapper_tx_desc_init(pdata);
 	desc_if->wrapper_rx_desc_init(pdata);
 	xgbe_enable_dma_interrupts(pdata);
@@ -3675,13 +3554,6 @@ void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if)
 	hw_if->rx_mmc_int = xgbe_rx_mmc_int;
 	hw_if->read_mmc_stats = xgbe_read_mmc_stats;
 
-	/* For PTP config */
-	hw_if->config_tstamp = xgbe_config_tstamp;
-	hw_if->update_tstamp_addend = xgbe_update_tstamp_addend;
-	hw_if->set_tstamp_time = xgbe_set_tstamp_time;
-	hw_if->get_tstamp_time = xgbe_get_tstamp_time;
-	hw_if->get_tx_tstamp = xgbe_get_tx_tstamp;
-
 	/* For Data Center Bridging config */
 	hw_if->config_tc = xgbe_config_tc;
 	hw_if->config_dcb_tc = xgbe_config_dcb_tc;
@@ -3702,5 +3574,26 @@ void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if)
 	hw_if->disable_vxlan = xgbe_disable_vxlan;
 	hw_if->set_vxlan_id = xgbe_set_vxlan_id;
 
+	/* For Split Header*/
+	hw_if->enable_sph = xgbe_config_sph_mode;
+	hw_if->disable_sph = xgbe_disable_sph_mode;
+
 	DBGPR("<--xgbe_init_function_ptrs\n");
 }
+
+int xgbe_enable_mac_loopback(struct xgbe_prv_data *pdata)
+{
+	/* Enable MAC loopback mode */
+	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, LM, 1);
+
+	/* Wait for loopback to stabilize */
+	usleep_range(10, 15);
+
+	return 0;
+}
+
+void xgbe_disable_mac_loopback(struct xgbe_prv_data *pdata)
+{
+	/* Disable MAC loopback mode */
+	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, LM, 0);
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 5475867708f4..3ddd896d6987 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
@@ -476,10 +367,11 @@ static irqreturn_t xgbe_ecc_isr(int irq, void *data)
 static void xgbe_isr_bh_work(struct work_struct *work)
 {
 	struct xgbe_prv_data *pdata = from_work(pdata, work, dev_bh_work);
+	unsigned int mac_isr, mac_tssr, mac_mdioisr;
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
-	struct xgbe_channel *channel;
+	bool per_ch_irq, ti, ri, rbu, fbe;
 	unsigned int dma_isr, dma_ch_isr;
-	unsigned int mac_isr, mac_tssr, mac_mdioisr;
+	struct xgbe_channel *channel;
 	unsigned int i;
 
 	/* The DMA interrupt status register also reports MAC and MTL
@@ -493,43 +385,73 @@ static void xgbe_isr_bh_work(struct work_struct *work)
 	netif_dbg(pdata, intr, pdata->netdev, "DMA_ISR=%#010x\n", dma_isr);
 
 	for (i = 0; i < pdata->channel_count; i++) {
+		bool schedule_napi = false;
+		struct napi_struct *napi;
+
 		if (!(dma_isr & (1 << i)))
 			continue;
 
 		channel = pdata->channel[i];
 
 		dma_ch_isr = XGMAC_DMA_IOREAD(channel, DMA_CH_SR);
+
+		/* Precompute flags once */
+		ti  = !!XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, TI);
+		ri  = !!XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, RI);
+		rbu = !!XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, RBU);
+		fbe = !!XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, FBE);
+
 		netif_dbg(pdata, intr, pdata->netdev, "DMA_CH%u_ISR=%#010x\n",
 			  i, dma_ch_isr);
 
-		/* The TI or RI interrupt bits may still be set even if using
-		 * per channel DMA interrupts. Check to be sure those are not
-		 * enabled before using the private data napi structure.
+		per_ch_irq = pdata->per_channel_irq;
+
+		/*
+		 * Decide which NAPI to use and whether to schedule:
+		 * - When not using per-channel IRQs: schedule on global NAPI
+		 *   if TI or RI are set.
+		 * - RBU should also trigger NAPI (either per-channel or global)
+		 *   to allow refill.
 		 */
-		if (!pdata->per_channel_irq &&
-		    (XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, TI) ||
-		     XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, RI))) {
-			if (napi_schedule_prep(&pdata->napi)) {
-				/* Disable Tx and Rx interrupts */
-				xgbe_disable_rx_tx_ints(pdata);
+		if (!per_ch_irq && (ti || ri))
+			schedule_napi = true;
+
+		if (rbu) {
+			schedule_napi = true;
+			pdata->ext_stats.rx_buffer_unavailable++;
+		}
 
-				/* Turn on polling */
-				__napi_schedule(&pdata->napi);
+		napi = per_ch_irq ? &channel->napi : &pdata->napi;
+
+		if (schedule_napi && napi_schedule_prep(napi)) {
+			/* Disable interrupts appropriately before polling */
+			if (per_ch_irq) {
+				if (pdata->channel_irq_mode)
+					xgbe_disable_rx_tx_int(pdata, channel);
+				else
+					disable_irq_nosync(channel->dma_irq);
+			} else {
+				xgbe_disable_rx_tx_ints(pdata);
 			}
+
+			/* Turn on polling */
+			__napi_schedule(napi);
 		} else {
-			/* Don't clear Rx/Tx status if doing per channel DMA
-			 * interrupts, these will be cleared by the ISR for
-			 * per channel DMA interrupts.
+			/*
+			 * Don't clear Rx/Tx status if doing per-channel DMA
+			 * interrupts; those bits will be serviced/cleared by
+			 * the per-channel ISR/NAPI. In non-per-channel mode
+			 * when we're not scheduling NAPI here, ensure we don't
+			 * accidentally clear TI/RI in HW: zero them in the
+			 * local copy so that the eventual write-back does not
+			 * clear TI/RI.
 			 */
 			XGMAC_SET_BITS(dma_ch_isr, DMA_CH_SR, TI, 0);
 			XGMAC_SET_BITS(dma_ch_isr, DMA_CH_SR, RI, 0);
 		}
 
-		if (XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, RBU))
-			pdata->ext_stats.rx_buffer_unavailable++;
-
 		/* Restart the device on a Fatal Bus Error */
-		if (XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, FBE))
+		if (fbe)
 			schedule_work(&pdata->restart_work);
 
 		/* Clear interrupt signals */
@@ -557,7 +479,7 @@ static void xgbe_isr_bh_work(struct work_struct *work)
 			if (XGMAC_GET_BITS(mac_tssr, MAC_TSSR, TXTSC)) {
 				/* Read Tx Timestamp to clear interrupt */
 				pdata->tx_tstamp =
-					hw_if->get_tx_tstamp(pdata);
+					xgbe_get_tx_tstamp(pdata);
 				queue_work(pdata->dev_workqueue,
 					   &pdata->tx_tstamp_work);
 			}
@@ -643,7 +565,8 @@ static irqreturn_t xgbe_dma_isr(int irq, void *data)
 
 static void xgbe_tx_timer(struct timer_list *t)
 {
-	struct xgbe_channel *channel = from_timer(channel, t, tx_timer);
+	struct xgbe_channel *channel = timer_container_of(channel, t,
+							  tx_timer);
 	struct xgbe_prv_data *pdata = channel->pdata;
 	struct napi_struct *napi;
 
@@ -681,7 +604,8 @@ static void xgbe_service(struct work_struct *work)
 
 static void xgbe_service_timer(struct timer_list *t)
 {
-	struct xgbe_prv_data *pdata = from_timer(pdata, t, service_timer);
+	struct xgbe_prv_data *pdata = timer_container_of(pdata, t,
+							 service_timer);
 	struct xgbe_channel *channel;
 	unsigned int i;
 
@@ -728,7 +652,7 @@ static void xgbe_stop_timers(struct xgbe_prv_data *pdata)
 	struct xgbe_channel *channel;
 	unsigned int i;
 
-	del_timer_sync(&pdata->service_timer);
+	timer_delete_sync(&pdata->service_timer);
 
 	for (i = 0; i < pdata->channel_count; i++) {
 		channel = pdata->channel[i];
@@ -736,7 +660,7 @@ static void xgbe_stop_timers(struct xgbe_prv_data *pdata)
 			break;
 
 		/* Deactivate the Tx timer */
-		del_timer_sync(&channel->tx_timer);
+		timer_delete_sync(&channel->tx_timer);
 		channel->tx_timer_active = 0;
 	}
 }
@@ -798,6 +722,21 @@ void xgbe_get_all_hw_features(struct xgbe_prv_data *pdata)
 	hw_feat->pps_out_num  = XGMAC_GET_BITS(mac_hfr2, MAC_HWF2R, PPSOUTNUM);
 	hw_feat->aux_snap_num = XGMAC_GET_BITS(mac_hfr2, MAC_HWF2R, AUXSNAPNUM);
 
+	/* Sanity check and warn if hardware reports more than supported */
+	if (hw_feat->pps_out_num > XGBE_MAX_PPS_OUT) {
+		dev_warn(pdata->dev,
+			 "Hardware reports %u PPS outputs, limiting to %u\n",
+			 hw_feat->pps_out_num, XGBE_MAX_PPS_OUT);
+		hw_feat->pps_out_num = XGBE_MAX_PPS_OUT;
+	}
+
+	if (hw_feat->aux_snap_num > XGBE_MAX_AUX_SNAP) {
+		dev_warn(pdata->dev,
+			 "Hardware reports %u aux snapshot inputs, limiting to %u\n",
+			 hw_feat->aux_snap_num, XGBE_MAX_AUX_SNAP);
+		hw_feat->aux_snap_num = XGBE_MAX_AUX_SNAP;
+	}
+
 	/* Translate the Hash Table size into actual number */
 	switch (hw_feat->hash_table_size) {
 	case 0:
@@ -1172,7 +1111,6 @@ static void xgbe_free_rx_data(struct xgbe_prv_data *pdata)
 
 static int xgbe_phy_reset(struct xgbe_prv_data *pdata)
 {
-	pdata->phy_link = -1;
 	pdata->phy_speed = SPEED_UNKNOWN;
 
 	return pdata->phy_if.phy_reset(pdata);
@@ -1352,6 +1290,11 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 
 	udp_tunnel_nic_reset_ntf(netdev);
 
+	/* Reset the phy settings */
+	ret = xgbe_phy_reset(pdata);
+	if (ret)
+		goto err_txrx;
+
 	netif_tx_start_all_queues(netdev);
 
 	xgbe_start_timers(pdata);
@@ -1361,6 +1304,10 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 
 	return 0;
 
+err_txrx:
+	hw_if->disable_rx(pdata);
+	hw_if->disable_tx(pdata);
+
 err_irqs:
 	xgbe_free_irqs(pdata);
 
@@ -1478,199 +1425,6 @@ static void xgbe_restart(struct work_struct *work)
 	rtnl_unlock();
 }
 
-static void xgbe_tx_tstamp(struct work_struct *work)
-{
-	struct xgbe_prv_data *pdata = container_of(work,
-						   struct xgbe_prv_data,
-						   tx_tstamp_work);
-	struct skb_shared_hwtstamps hwtstamps;
-	u64 nsec;
-	unsigned long flags;
-
-	spin_lock_irqsave(&pdata->tstamp_lock, flags);
-	if (!pdata->tx_tstamp_skb)
-		goto unlock;
-
-	if (pdata->tx_tstamp) {
-		nsec = timecounter_cyc2time(&pdata->tstamp_tc,
-					    pdata->tx_tstamp);
-
-		memset(&hwtstamps, 0, sizeof(hwtstamps));
-		hwtstamps.hwtstamp = ns_to_ktime(nsec);
-		skb_tstamp_tx(pdata->tx_tstamp_skb, &hwtstamps);
-	}
-
-	dev_kfree_skb_any(pdata->tx_tstamp_skb);
-
-	pdata->tx_tstamp_skb = NULL;
-
-unlock:
-	spin_unlock_irqrestore(&pdata->tstamp_lock, flags);
-}
-
-static int xgbe_get_hwtstamp_settings(struct xgbe_prv_data *pdata,
-				      struct ifreq *ifreq)
-{
-	if (copy_to_user(ifreq->ifr_data, &pdata->tstamp_config,
-			 sizeof(pdata->tstamp_config)))
-		return -EFAULT;
-
-	return 0;
-}
-
-static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata,
-				      struct ifreq *ifreq)
-{
-	struct hwtstamp_config config;
-	unsigned int mac_tscr;
-
-	if (copy_from_user(&config, ifreq->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	mac_tscr = 0;
-
-	switch (config.tx_type) {
-	case HWTSTAMP_TX_OFF:
-		break;
-
-	case HWTSTAMP_TX_ON:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
-		break;
-
-	default:
-		return -ERANGE;
-	}
-
-	switch (config.rx_filter) {
-	case HWTSTAMP_FILTER_NONE:
-		break;
-
-	case HWTSTAMP_FILTER_NTP_ALL:
-	case HWTSTAMP_FILTER_ALL:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENALL, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
-		break;
-
-	/* PTP v2, UDP, any kind of event packet */
-	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
-		fallthrough;	/* to PTP v1, UDP, any kind of event packet */
-	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, SNAPTYPSEL, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
-		break;
-
-	/* PTP v2, UDP, Sync packet */
-	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
-		fallthrough;	/* to PTP v1, UDP, Sync packet */
-	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
-		break;
-
-	/* PTP v2, UDP, Delay_req packet */
-	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
-		fallthrough;	/* to PTP v1, UDP, Delay_req packet */
-	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSMSTRENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
-		break;
-
-	/* 802.AS1, Ethernet, any kind of event packet */
-	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, AV8021ASMEN, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, SNAPTYPSEL, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
-		break;
-
-	/* 802.AS1, Ethernet, Sync packet */
-	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, AV8021ASMEN, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
-		break;
-
-	/* 802.AS1, Ethernet, Delay_req packet */
-	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, AV8021ASMEN, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSMSTRENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
-		break;
-
-	/* PTP v2/802.AS1, any layer, any kind of event packet */
-	case HWTSTAMP_FILTER_PTP_V2_EVENT:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, SNAPTYPSEL, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
-		break;
-
-	/* PTP v2/802.AS1, any layer, Sync packet */
-	case HWTSTAMP_FILTER_PTP_V2_SYNC:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
-		break;
-
-	/* PTP v2/802.AS1, any layer, Delay_req packet */
-	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSMSTRENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1);
-		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
-		break;
-
-	default:
-		return -ERANGE;
-	}
-
-	pdata->hw_if.config_tstamp(pdata, mac_tscr);
-
-	memcpy(&pdata->tstamp_config, &config, sizeof(config));
-
-	return 0;
-}
-
-static void xgbe_prep_tx_tstamp(struct xgbe_prv_data *pdata,
-				struct sk_buff *skb,
-				struct xgbe_packet_data *packet)
-{
-	unsigned long flags;
-
-	if (XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES, PTP)) {
-		spin_lock_irqsave(&pdata->tstamp_lock, flags);
-		if (pdata->tx_tstamp_skb) {
-			/* Another timestamp in progress, ignore this one */
-			XGMAC_SET_BITS(packet->attributes,
-				       TX_PACKET_ATTRIBUTES, PTP, 0);
-		} else {
-			pdata->tx_tstamp_skb = skb_get(skb);
-			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-		}
-		spin_unlock_irqrestore(&pdata->tstamp_lock, flags);
-	}
-
-	skb_tx_timestamp(skb);
-}
-
 static void xgbe_prep_vlan(struct sk_buff *skb, struct xgbe_packet_data *packet)
 {
 	if (skb_vlan_tag_present(skb))
@@ -1860,11 +1614,6 @@ static int xgbe_open(struct net_device *netdev)
 		goto err_dev_wq;
 	}
 
-	/* Reset the phy settings */
-	ret = xgbe_phy_reset(pdata);
-	if (ret)
-		goto err_an_wq;
-
 	/* Enable the clocks */
 	ret = clk_prepare_enable(pdata->sysclk);
 	if (ret) {
@@ -1883,6 +1632,9 @@ static int xgbe_open(struct net_device *netdev)
 	INIT_WORK(&pdata->stopdev_work, xgbe_stopdev);
 	INIT_WORK(&pdata->tx_tstamp_work, xgbe_tx_tstamp);
 
+	/* Initialize PTP timestamping and clock. */
+	xgbe_init_ptp(pdata);
+
 	ret = xgbe_alloc_memory(pdata);
 	if (ret)
 		goto err_ptpclk;
@@ -2037,27 +1789,6 @@ static int xgbe_set_mac_address(struct net_device *netdev, void *addr)
 	return 0;
 }
 
-static int xgbe_ioctl(struct net_device *netdev, struct ifreq *ifreq, int cmd)
-{
-	struct xgbe_prv_data *pdata = netdev_priv(netdev);
-	int ret;
-
-	switch (cmd) {
-	case SIOCGHWTSTAMP:
-		ret = xgbe_get_hwtstamp_settings(pdata, ifreq);
-		break;
-
-	case SIOCSHWTSTAMP:
-		ret = xgbe_set_hwtstamp_settings(pdata, ifreq);
-		break;
-
-	default:
-		ret = -EOPNOTSUPP;
-	}
-
-	return ret;
-}
-
 static int xgbe_change_mtu(struct net_device *netdev, int mtu)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
@@ -2257,10 +1988,17 @@ static int xgbe_set_features(struct net_device *netdev,
 	if (ret)
 		return ret;
 
-	if ((features & NETIF_F_RXCSUM) && !rxcsum)
+	if ((features & NETIF_F_RXCSUM) && !rxcsum) {
+		hw_if->enable_sph(pdata);
+		hw_if->enable_vxlan(pdata);
 		hw_if->enable_rx_csum(pdata);
-	else if (!(features & NETIF_F_RXCSUM) && rxcsum)
+		schedule_work(&pdata->restart_work);
+	} else if (!(features & NETIF_F_RXCSUM) && rxcsum) {
+		hw_if->disable_sph(pdata);
+		hw_if->disable_vxlan(pdata);
 		hw_if->disable_rx_csum(pdata);
+		schedule_work(&pdata->restart_work);
+	}
 
 	if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !rxvlan)
 		hw_if->enable_rx_vlan_stripping(pdata);
@@ -2296,7 +2034,6 @@ static const struct net_device_ops xgbe_netdev_ops = {
 	.ndo_set_rx_mode	= xgbe_set_rx_mode,
 	.ndo_set_mac_address	= xgbe_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_eth_ioctl		= xgbe_ioctl,
 	.ndo_change_mtu		= xgbe_change_mtu,
 	.ndo_tx_timeout		= xgbe_tx_timeout,
 	.ndo_get_stats64	= xgbe_get_stats64,
@@ -2309,6 +2046,8 @@ static const struct net_device_ops xgbe_netdev_ops = {
 	.ndo_fix_features	= xgbe_fix_features,
 	.ndo_set_features	= xgbe_set_features,
 	.ndo_features_check	= xgbe_features_check,
+	.ndo_hwtstamp_get	= xgbe_get_hwtstamp_settings,
+	.ndo_hwtstamp_set	= xgbe_set_hwtstamp_settings,
 };
 
 const struct net_device_ops *xgbe_get_netdev_ops(void)
@@ -2646,12 +2385,8 @@ skip_data:
 
 		if (XGMAC_GET_BITS(packet->attributes,
 				   RX_PACKET_ATTRIBUTES, RX_TSTAMP)) {
-			u64 nsec;
-
-			nsec = timecounter_cyc2time(&pdata->tstamp_tc,
-						    packet->rx_tstamp);
 			hwtstamps = skb_hwtstamps(skb);
-			hwtstamps->hwtstamp = ns_to_ktime(nsec);
+			hwtstamps->hwtstamp = ns_to_ktime(packet->rx_tstamp);
 		}
 
 		if (XGMAC_GET_BITS(packet->attributes,
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
index 4431ab1c18b3..0d19b09497a0 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/spinlock.h>
@@ -194,6 +85,9 @@ static void xgbe_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 	int i;
 
 	switch (stringset) {
+	case ETH_SS_TEST:
+		xgbe_selftest_get_strings(pdata, data);
+		break;
 	case ETH_SS_STATS:
 		for (i = 0; i < XGBE_STATS_COUNT; i++)
 			ethtool_puts(&data, xgbe_gstring_stats[i].stat_string);
@@ -240,6 +134,9 @@ static int xgbe_get_sset_count(struct net_device *netdev, int stringset)
 	int ret;
 
 	switch (stringset) {
+	case ETH_SS_TEST:
+		ret = xgbe_selftest_get_count(pdata);
+		break;
 	case ETH_SS_STATS:
 		ret = XGBE_STATS_COUNT +
 		      (pdata->tx_ring_count * 2) +
@@ -438,6 +335,7 @@ static int xgbe_get_coalesce(struct net_device *netdev,
 	ec->rx_coalesce_usecs = pdata->rx_usecs;
 	ec->rx_max_coalesced_frames = pdata->rx_frames;
 
+	ec->tx_coalesce_usecs = pdata->tx_usecs;
 	ec->tx_max_coalesced_frames = pdata->tx_frames;
 
 	return 0;
@@ -451,7 +349,8 @@ static int xgbe_set_coalesce(struct net_device *netdev,
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
 	unsigned int rx_frames, rx_riwt, rx_usecs;
-	unsigned int tx_frames;
+	unsigned int tx_frames, tx_usecs;
+	unsigned int jiffy_us = jiffies_to_usecs(1);
 
 	rx_riwt = hw_if->usec_to_riwt(pdata, ec->rx_coalesce_usecs);
 	rx_usecs = ec->rx_coalesce_usecs;
@@ -473,20 +372,42 @@ static int xgbe_set_coalesce(struct net_device *netdev,
 		return -EINVAL;
 	}
 
+	tx_usecs = ec->tx_coalesce_usecs;
 	tx_frames = ec->tx_max_coalesced_frames;
 
 	/* Check the bounds of values for Tx */
+	if (!tx_usecs) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "tx-usecs must not be 0");
+		return -EINVAL;
+	}
+	if (tx_usecs > XGMAC_MAX_COAL_TX_TICK) {
+		NL_SET_ERR_MSG_FMT_MOD(extack, "tx-usecs is limited to %d usec",
+				       XGMAC_MAX_COAL_TX_TICK);
+		return -EINVAL;
+	}
 	if (tx_frames > pdata->tx_desc_count) {
 		netdev_err(netdev, "tx-frames is limited to %d frames\n",
 			   pdata->tx_desc_count);
 		return -EINVAL;
 	}
 
+	/* Round tx-usecs to nearest multiple of jiffy granularity */
+	if (tx_usecs % jiffy_us) {
+		tx_usecs = rounddown(tx_usecs, jiffy_us);
+		if (!tx_usecs)
+			tx_usecs = jiffy_us;
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "tx-usecs rounded to %u usec due to jiffy granularity (%u usec)",
+				       tx_usecs, jiffy_us);
+	}
+
 	pdata->rx_riwt = rx_riwt;
 	pdata->rx_usecs = rx_usecs;
 	pdata->rx_frames = rx_frames;
 	hw_if->config_rx_coalesce(pdata);
 
+	pdata->tx_usecs = tx_usecs;
 	pdata->tx_frames = tx_frames;
 	hw_if->config_tx_coalesce(pdata);
 
@@ -549,7 +470,7 @@ static int xgbe_set_rxfh(struct net_device *netdev,
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
-	unsigned int ret;
+	int ret;
 
 	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
 	    rxfh->hfunc != ETH_RSS_HASH_TOP) {
@@ -818,7 +739,7 @@ out:
 }
 
 static const struct ethtool_ops xgbe_ethtool_ops = {
-	.supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS |
+	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES,
 	.get_drvinfo = xgbe_get_drvinfo,
 	.get_msglevel = xgbe_get_msglevel,
@@ -845,6 +766,7 @@ static const struct ethtool_ops xgbe_ethtool_ops = {
 	.set_ringparam = xgbe_set_ringparam,
 	.get_channels = xgbe_get_channels,
 	.set_channels = xgbe_set_channels,
+	.self_test = xgbe_selftest_run,
 };
 
 const struct ethtool_ops *xgbe_get_ethtool_ops(void)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-hwtstamp.c b/drivers/net/ethernet/amd/xgbe/xgbe-hwtstamp.c
new file mode 100644
index 000000000000..0127988e10be
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-hwtstamp.c
@@ -0,0 +1,399 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
+/*
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
+ *
+ * Author: Raju Rangoju <Raju.Rangoju@amd.com>
+ */
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+void xgbe_update_tstamp_time(struct xgbe_prv_data *pdata,
+			     unsigned int sec, unsigned int nsec)
+{
+	int count;
+
+	/* Set the time values and tell the device */
+	XGMAC_IOWRITE(pdata, MAC_STSUR, sec);
+	XGMAC_IOWRITE(pdata, MAC_STNUR, nsec);
+
+	/* issue command to update the system time value */
+	XGMAC_IOWRITE(pdata, MAC_TSCR,
+		      XGMAC_IOREAD(pdata, MAC_TSCR) |
+		      (1 << MAC_TSCR_TSUPDT_INDEX));
+
+	/* Wait for the time adjust/update to complete */
+	count = 10000;
+	while (--count && XGMAC_IOREAD_BITS(pdata, MAC_TSCR, TSUPDT))
+		udelay(5);
+
+	if (count < 0)
+		netdev_err(pdata->netdev,
+			   "timed out updating system timestamp\n");
+}
+
+void xgbe_update_tstamp_addend(struct xgbe_prv_data *pdata,
+			       unsigned int addend)
+{
+	unsigned int count = 10000;
+
+	/* Set the addend register value and tell the device */
+	XGMAC_IOWRITE(pdata, MAC_TSAR, addend);
+	XGMAC_IOWRITE_BITS(pdata, MAC_TSCR, TSADDREG, 1);
+
+	/* Wait for addend update to complete */
+	while (--count && XGMAC_IOREAD_BITS(pdata, MAC_TSCR, TSADDREG))
+		udelay(5);
+
+	if (!count)
+		netdev_err(pdata->netdev,
+			   "timed out updating timestamp addend register\n");
+}
+
+void xgbe_set_tstamp_time(struct xgbe_prv_data *pdata, unsigned int sec,
+			  unsigned int nsec)
+{
+	unsigned int count = 10000;
+
+	/* Set the time values and tell the device */
+	XGMAC_IOWRITE(pdata, MAC_STSUR, sec);
+	XGMAC_IOWRITE(pdata, MAC_STNUR, nsec);
+	XGMAC_IOWRITE_BITS(pdata, MAC_TSCR, TSINIT, 1);
+
+	/* Wait for time update to complete */
+	while (--count && XGMAC_IOREAD_BITS(pdata, MAC_TSCR, TSINIT))
+		udelay(5);
+
+	if (!count)
+		netdev_err(pdata->netdev, "timed out initializing timestamp\n");
+}
+
+u64 xgbe_get_tstamp_time(struct xgbe_prv_data *pdata)
+{
+	u64 nsec;
+
+	nsec = XGMAC_IOREAD(pdata, MAC_STSR);
+	nsec *= NSEC_PER_SEC;
+	nsec += XGMAC_IOREAD(pdata, MAC_STNR);
+
+	return nsec;
+}
+
+u64 xgbe_get_tx_tstamp(struct xgbe_prv_data *pdata)
+{
+	unsigned int tx_snr, tx_ssr;
+	u64 nsec;
+
+	if (pdata->vdata->tx_tstamp_workaround) {
+		tx_snr = XGMAC_IOREAD(pdata, MAC_TXSNR);
+		tx_ssr = XGMAC_IOREAD(pdata, MAC_TXSSR);
+	} else {
+		tx_ssr = XGMAC_IOREAD(pdata, MAC_TXSSR);
+		tx_snr = XGMAC_IOREAD(pdata, MAC_TXSNR);
+	}
+
+	if (XGMAC_GET_BITS(tx_snr, MAC_TXSNR, TXTSSTSMIS))
+		return 0;
+
+	nsec = tx_ssr;
+	nsec *= NSEC_PER_SEC;
+	nsec += tx_snr;
+
+	return nsec;
+}
+
+void xgbe_get_rx_tstamp(struct xgbe_packet_data *packet,
+			struct xgbe_ring_desc *rdesc)
+{
+	u64 nsec;
+
+	if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_CONTEXT_DESC3, TSA) &&
+	    !XGMAC_GET_BITS_LE(rdesc->desc3, RX_CONTEXT_DESC3, TSD)) {
+		nsec = le32_to_cpu(rdesc->desc1);
+		nsec *= NSEC_PER_SEC;
+		nsec += le32_to_cpu(rdesc->desc0);
+		if (nsec != 0xffffffffffffffffULL) {
+			packet->rx_tstamp = nsec;
+			XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+				       RX_TSTAMP, 1);
+		}
+	}
+}
+
+void xgbe_config_tstamp(struct xgbe_prv_data *pdata, unsigned int mac_tscr)
+{
+	unsigned int value = 0;
+
+	value = XGMAC_IOREAD(pdata, MAC_TSCR);
+	value |= mac_tscr;
+	XGMAC_IOWRITE(pdata, MAC_TSCR, value);
+}
+
+void xgbe_tx_tstamp(struct work_struct *work)
+{
+	struct xgbe_prv_data *pdata = container_of(work,
+						   struct xgbe_prv_data,
+						   tx_tstamp_work);
+	struct skb_shared_hwtstamps hwtstamps;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pdata->tstamp_lock, flags);
+	if (!pdata->tx_tstamp_skb)
+		goto unlock;
+
+	if (pdata->tx_tstamp) {
+		memset(&hwtstamps, 0, sizeof(hwtstamps));
+		hwtstamps.hwtstamp = ns_to_ktime(pdata->tx_tstamp);
+		skb_tstamp_tx(pdata->tx_tstamp_skb, &hwtstamps);
+	}
+
+	dev_kfree_skb_any(pdata->tx_tstamp_skb);
+
+	pdata->tx_tstamp_skb = NULL;
+
+unlock:
+	spin_unlock_irqrestore(&pdata->tstamp_lock, flags);
+}
+
+int xgbe_get_hwtstamp_settings(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *config)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+
+	*config = pdata->tstamp_config;
+
+	return 0;
+}
+
+int xgbe_set_hwtstamp_settings(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	unsigned int mac_tscr = 0;
+
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+		break;
+
+	case HWTSTAMP_TX_ON:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
+		break;
+
+	default:
+		return -ERANGE;
+	}
+
+	switch (config->rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		break;
+
+	case HWTSTAMP_FILTER_NTP_ALL:
+	case HWTSTAMP_FILTER_ALL:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENALL, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
+		break;
+
+		/* PTP v2, UDP, any kind of event packet */
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
+		fallthrough;    /* to PTP v1, UDP, any kind of event packet */
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, SNAPTYPSEL, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
+		break;
+		/* PTP v2, UDP, Sync packet */
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
+		fallthrough;    /* to PTP v1, UDP, Sync packet */
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
+		break;
+
+		/* PTP v2, UDP, Delay_req packet */
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
+		fallthrough;    /* to PTP v1, UDP, Delay_req packet */
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSMSTRENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
+		break;
+
+		/* 802.AS1, Ethernet, any kind of event packet */
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, AV8021ASMEN, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, SNAPTYPSEL, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
+		break;
+
+		/* 802.AS1, Ethernet, Sync packet */
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, AV8021ASMEN, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
+		break;
+
+		/* 802.AS1, Ethernet, Delay_req packet */
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, AV8021ASMEN, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSMSTRENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
+		break;
+
+		/* PTP v2/802.AS1, any layer, any kind of event packet */
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, SNAPTYPSEL, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
+		break;
+
+		/* PTP v2/802.AS1, any layer, Sync packet */
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
+		break;
+
+		/* PTP v2/802.AS1, any layer, Delay_req packet */
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSMSTRENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1);
+		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
+		break;
+
+	default:
+		return -ERANGE;
+	}
+
+	xgbe_config_tstamp(pdata, mac_tscr);
+
+	pdata->tstamp_config = *config;
+
+	return 0;
+}
+
+void xgbe_prep_tx_tstamp(struct xgbe_prv_data *pdata,
+			 struct sk_buff *skb,
+			 struct xgbe_packet_data *packet)
+{
+	unsigned long flags;
+
+	if (XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES, PTP)) {
+		spin_lock_irqsave(&pdata->tstamp_lock, flags);
+		if (pdata->tx_tstamp_skb) {
+			/* Another timestamp in progress, ignore this one */
+			XGMAC_SET_BITS(packet->attributes,
+				       TX_PACKET_ATTRIBUTES, PTP, 0);
+		} else {
+			pdata->tx_tstamp_skb = skb_get(skb);
+			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+		}
+		spin_unlock_irqrestore(&pdata->tstamp_lock, flags);
+	}
+
+	skb_tx_timestamp(skb);
+}
+
+int xgbe_init_ptp(struct xgbe_prv_data *pdata)
+{
+	unsigned int mac_tscr = 0;
+	struct timespec64 now;
+	u64 dividend;
+
+	/* Register Settings to be done based on the link speed. */
+	switch (pdata->phy.speed) {
+	case SPEED_1000:
+		XGMAC_IOWRITE(pdata, MAC_TICNR, MAC_TICNR_1G_INITVAL);
+		XGMAC_IOWRITE(pdata, MAC_TECNR, MAC_TECNR_1G_INITVAL);
+		break;
+	case SPEED_2500:
+	case SPEED_10000:
+		XGMAC_IOWRITE_BITS(pdata, MAC_TICSNR, TSICSNS,
+				   MAC_TICSNR_10G_INITVAL);
+		XGMAC_IOWRITE(pdata, MAC_TECNR, MAC_TECNR_10G_INITVAL);
+		XGMAC_IOWRITE_BITS(pdata, MAC_TECSNR, TSECSNS,
+				   MAC_TECSNR_10G_INITVAL);
+		break;
+	case SPEED_UNKNOWN:
+	default:
+		break;
+	}
+
+	/* Enable IEEE1588 PTP clock. */
+	XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
+
+	/* Overwrite earlier timestamps */
+	XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TXTSSTSM, 1);
+
+	/* Set one nano-second accuracy */
+	XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSCTRLSSR, 1);
+
+	/* Set fine timestamp update */
+	XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSCFUPDT, 1);
+
+	xgbe_config_tstamp(pdata, mac_tscr);
+
+	/* Exit if timestamping is not enabled */
+	if (!XGMAC_GET_BITS(mac_tscr, MAC_TSCR, TSENA))
+		return -EOPNOTSUPP;
+
+	if (pdata->vdata->tstamp_ptp_clock_freq) {
+		/* Initialize time registers based on
+		 * 125MHz PTP Clock Frequency
+		 */
+		XGMAC_IOWRITE_BITS(pdata, MAC_SSIR, SSINC,
+				   XGBE_V2_TSTAMP_SSINC);
+		XGMAC_IOWRITE_BITS(pdata, MAC_SSIR, SNSINC,
+				   XGBE_V2_TSTAMP_SNSINC);
+	} else {
+		/* Initialize time registers based on
+		 * 50MHz PTP Clock Frequency
+		 */
+		XGMAC_IOWRITE_BITS(pdata, MAC_SSIR, SSINC, XGBE_TSTAMP_SSINC);
+		XGMAC_IOWRITE_BITS(pdata, MAC_SSIR, SNSINC, XGBE_TSTAMP_SNSINC);
+	}
+
+	/* Calculate the addend:
+	 *   addend = 2^32 / (PTP ref clock / (PTP clock based on SSINC))
+	 *          = (2^32 * (PTP clock based on SSINC)) / PTP ref clock
+	 */
+	if (pdata->vdata->tstamp_ptp_clock_freq)
+		dividend = XGBE_V2_PTP_ACT_CLK_FREQ;
+	else
+		dividend = XGBE_PTP_ACT_CLK_FREQ;
+
+	dividend = (u64)(dividend << 32);
+	pdata->tstamp_addend = div_u64(dividend, pdata->ptpclk_rate);
+
+	xgbe_update_tstamp_addend(pdata, pdata->tstamp_addend);
+
+	dma_wmb();
+	/* initialize system time */
+	ktime_get_real_ts64(&now);
+
+	/* lower 32 bits of tv_sec are safe until y2106 */
+	xgbe_set_tstamp_time(pdata, (u32)now.tv_sec, now.tv_nsec);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
index 7a833894f52a..65eb7b577b65 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
@@ -179,7 +70,7 @@ static int xgbe_i2c_set_enable(struct xgbe_prv_data *pdata, bool enable)
 
 static int xgbe_i2c_disable(struct xgbe_prv_data *pdata)
 {
-	unsigned int ret;
+	int ret;
 
 	ret = xgbe_i2c_set_enable(pdata, false);
 	if (ret) {
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
index 0e8698928e4d..d1f0419edb23 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
@@ -384,7 +275,7 @@ int xgbe_config_netdev(struct xgbe_prv_data *pdata)
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 	netdev->min_mtu = 0;
-	netdev->max_mtu = XGMAC_JUMBO_PACKET_MTU;
+	netdev->max_mtu = XGMAC_GIANT_PACKET_MTU - XGBE_ETH_FRAME_HDR;
 
 	/* Use default watchdog timeout */
 	netdev->watchdog_timeo = 0;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 07f4f3418d01..7675bb98f029 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/interrupt.h>
@@ -375,6 +266,10 @@ static void xgbe_an37_set(struct xgbe_prv_data *pdata, bool enable,
 		reg |= MDIO_VEND2_CTRL1_AN_RESTART;
 
 	XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_CTRL1, reg);
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL);
+	reg |= XGBE_VEND2_MAC_AUTO_SW;
+	XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL, reg);
 }
 
 static void xgbe_an37_restart(struct xgbe_prv_data *pdata)
@@ -1003,6 +898,11 @@ static void xgbe_an37_init(struct xgbe_prv_data *pdata)
 
 	netif_dbg(pdata, link, pdata->netdev, "CL37 AN (%s) initialized\n",
 		  (pdata->an_mode == XGBE_AN_MODE_CL37) ? "BaseX" : "SGMII");
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_CTRL1);
+	reg &= ~MDIO_AN_CTRL1_ENABLE;
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_CTRL1, reg);
+
 }
 
 static void xgbe_an73_init(struct xgbe_prv_data *pdata)
@@ -1404,6 +1304,10 @@ static void xgbe_phy_status(struct xgbe_prv_data *pdata)
 
 	pdata->phy.link = pdata->phy_if.phy_impl.link_status(pdata,
 							     &an_restart);
+	/* bail out if the link status register read fails */
+	if (pdata->phy.link < 0)
+		return;
+
 	if (an_restart) {
 		xgbe_phy_config_aneg(pdata);
 		goto adjust_link;
@@ -1651,6 +1555,7 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata)
 		pdata->phy.duplex = DUPLEX_FULL;
 	}
 
+	pdata->phy_link = 0;
 	pdata->phy.link = 0;
 
 	pdata->phy.pause_autoneg = pdata->pause_autoneg;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index c636999a6a84..e3e1dca9856a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -1,123 +1,15 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/pci.h>
 #include <linux/log2.h>
+#include "xgbe-smn.h"
 
 #include "xgbe.h"
 #include "xgbe-common.h"
@@ -207,14 +99,14 @@ out:
 
 static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
-	struct xgbe_prv_data *pdata;
-	struct device *dev = &pdev->dev;
 	void __iomem * const *iomap_table;
-	struct pci_dev *rdev;
+	unsigned int port_addr_size, reg;
+	struct device *dev = &pdev->dev;
+	struct xgbe_prv_data *pdata;
 	unsigned int ma_lo, ma_hi;
-	unsigned int reg;
-	int bar_mask;
-	int ret;
+	struct pci_dev *rdev;
+	int bar_mask, ret;
+	u32 address;
 
 	pdata = xgbe_alloc_pdata(dev);
 	if (IS_ERR(pdata)) {
@@ -274,20 +166,31 @@ static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	/* Set the PCS indirect addressing definition registers */
 	rdev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0, 0));
-	if (rdev &&
-	    (rdev->vendor == PCI_VENDOR_ID_AMD) && (rdev->device == 0x15d0)) {
-		pdata->xpcs_window_def_reg = PCS_V2_RV_WINDOW_DEF;
-		pdata->xpcs_window_sel_reg = PCS_V2_RV_WINDOW_SELECT;
-	} else if (rdev && (rdev->vendor == PCI_VENDOR_ID_AMD) &&
-		   (rdev->device == 0x14b5)) {
-		pdata->xpcs_window_def_reg = PCS_V2_YC_WINDOW_DEF;
-		pdata->xpcs_window_sel_reg = PCS_V2_YC_WINDOW_SELECT;
-
-		/* Yellow Carp devices do not need cdr workaround */
-		pdata->vdata->an_cdr_workaround = 0;
-
-		/* Yellow Carp devices do not need rrc */
-		pdata->vdata->enable_rrc = 0;
+	if (rdev && rdev->vendor == PCI_VENDOR_ID_AMD) {
+		switch (rdev->device) {
+		case XGBE_RV_PCI_DEVICE_ID:
+			pdata->xpcs_window_def_reg = PCS_V2_RV_WINDOW_DEF;
+			pdata->xpcs_window_sel_reg = PCS_V2_RV_WINDOW_SELECT;
+			break;
+		case XGBE_YC_PCI_DEVICE_ID:
+			pdata->xpcs_window_def_reg = PCS_V2_YC_WINDOW_DEF;
+			pdata->xpcs_window_sel_reg = PCS_V2_YC_WINDOW_SELECT;
+
+			/* Yellow Carp devices do not need cdr workaround */
+			pdata->vdata->an_cdr_workaround = 0;
+
+			/* Yellow Carp devices do not need rrc */
+			pdata->vdata->enable_rrc = 0;
+			break;
+		case XGBE_RN_PCI_DEVICE_ID:
+			pdata->xpcs_window_def_reg = PCS_V3_RN_WINDOW_DEF;
+			pdata->xpcs_window_sel_reg = PCS_V3_RN_WINDOW_SELECT;
+			break;
+		default:
+			pdata->xpcs_window_def_reg = PCS_V2_WINDOW_DEF;
+			pdata->xpcs_window_sel_reg = PCS_V2_WINDOW_SELECT;
+			break;
+		}
 	} else {
 		pdata->xpcs_window_def_reg = PCS_V2_WINDOW_DEF;
 		pdata->xpcs_window_sel_reg = PCS_V2_WINDOW_SELECT;
@@ -295,7 +198,22 @@ static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	pci_dev_put(rdev);
 
 	/* Configure the PCS indirect addressing support */
-	reg = XPCS32_IOREAD(pdata, pdata->xpcs_window_def_reg);
+	if (pdata->vdata->xpcs_access == XGBE_XPCS_ACCESS_V3) {
+		reg = XP_IOREAD(pdata, XP_PROP_0);
+		port_addr_size = PCS_RN_PORT_ADDR_SIZE *
+				 XP_GET_BITS(reg, XP_PROP_0, PORT_ID);
+		pdata->smn_base = PCS_RN_SMN_BASE_ADDR + port_addr_size;
+
+		address = pdata->smn_base + (pdata->xpcs_window_def_reg);
+		ret = amd_smn_read(0, address, &reg);
+		if (ret) {
+			pci_err(pdata->pcidev, "Failed to read data\n");
+			goto err_pci_enable;
+		}
+	} else {
+		reg = XPCS32_IOREAD(pdata, pdata->xpcs_window_def_reg);
+	}
+
 	pdata->xpcs_window = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, OFFSET);
 	pdata->xpcs_window <<= 6;
 	pdata->xpcs_window_size = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, SIZE);
@@ -473,6 +391,22 @@ static int __maybe_unused xgbe_pci_resume(struct device *dev)
 	return ret;
 }
 
+static struct xgbe_version_data xgbe_v3 = {
+	.init_function_ptrs_phy_impl	= xgbe_init_function_ptrs_phy_v2,
+	.xpcs_access			= XGBE_XPCS_ACCESS_V3,
+	.mmc_64bit			= 1,
+	.tx_max_fifo_size		= 65536,
+	.rx_max_fifo_size		= 65536,
+	.tx_tstamp_workaround		= 1,
+	.ecc_support			= 1,
+	.i2c_support			= 1,
+	.irq_reissue_support		= 1,
+	.tx_desc_prefetch		= 5,
+	.rx_desc_prefetch		= 5,
+	.an_cdr_workaround		= 0,
+	.enable_rrc			= 0,
+};
+
 static struct xgbe_version_data xgbe_v2a = {
 	.init_function_ptrs_phy_impl	= xgbe_init_function_ptrs_phy_v2,
 	.xpcs_access			= XGBE_XPCS_ACCESS_V2,
@@ -480,6 +414,7 @@ static struct xgbe_version_data xgbe_v2a = {
 	.tx_max_fifo_size		= 229376,
 	.rx_max_fifo_size		= 229376,
 	.tx_tstamp_workaround		= 1,
+	.tstamp_ptp_clock_freq		= 1,
 	.ecc_support			= 1,
 	.i2c_support			= 1,
 	.irq_reissue_support		= 1,
@@ -496,6 +431,7 @@ static struct xgbe_version_data xgbe_v2b = {
 	.tx_max_fifo_size		= 65536,
 	.rx_max_fifo_size		= 65536,
 	.tx_tstamp_workaround		= 1,
+	.tstamp_ptp_clock_freq		= 1,
 	.ecc_support			= 1,
 	.i2c_support			= 1,
 	.irq_reissue_support		= 1,
@@ -510,6 +446,8 @@ static const struct pci_device_id xgbe_pci_table[] = {
 	  .driver_data = (kernel_ulong_t)&xgbe_v2a },
 	{ PCI_VDEVICE(AMD, 0x1459),
 	  .driver_data = (kernel_ulong_t)&xgbe_v2b },
+	{ PCI_VDEVICE(AMD, 0x1641),
+	  .driver_data = (kernel_ulong_t)&xgbe_v3 },
 	/* Last entry must be zero */
 	{ 0, }
 };
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c
index d16eae415f72..2e6b8ffe785c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 6a716337f48b..a68757e8fd22 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
@@ -777,7 +668,7 @@ static int xgbe_phy_mii_read_c45(struct mii_bus *mii, int addr, int devad,
 	else if (phy_data->conn_type & XGBE_CONN_TYPE_MDIO)
 		ret = xgbe_phy_mdio_mii_read_c45(pdata, addr, devad, reg);
 	else
-		ret = -ENOTSUPP;
+		ret = -EOPNOTSUPP;
 
 	xgbe_phy_put_comm_ownership(pdata);
 
@@ -923,7 +814,6 @@ static void xgbe_phy_free_phy_device(struct xgbe_prv_data *pdata)
 
 static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
 	unsigned int phy_id = phy_data->phydev->phy_id;
 
@@ -945,14 +835,7 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 	phy_write(phy_data->phydev, 0x04, 0x0d01);
 	phy_write(phy_data->phydev, 0x00, 0x9140);
 
-	linkmode_set_bit_array(phy_10_100_features_array,
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       supported);
-	linkmode_set_bit_array(phy_gbit_features_array,
-			       ARRAY_SIZE(phy_gbit_features_array),
-			       supported);
-
-	linkmode_copy(phy_data->phydev->supported, supported);
+	linkmode_copy(phy_data->phydev->supported, PHY_GBIT_FEATURES);
 
 	phy_support_asym_pause(phy_data->phydev);
 
@@ -964,7 +847,6 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 
 static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
 	struct xgbe_sfp_eeprom *sfp_eeprom = &phy_data->sfp_eeprom;
 	unsigned int phy_id = phy_data->phydev->phy_id;
@@ -1028,13 +910,7 @@ static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata)
 	reg = phy_read(phy_data->phydev, 0x00);
 	phy_write(phy_data->phydev, 0x00, reg & ~0x00800);
 
-	linkmode_set_bit_array(phy_10_100_features_array,
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       supported);
-	linkmode_set_bit_array(phy_gbit_features_array,
-			       ARRAY_SIZE(phy_gbit_features_array),
-			       supported);
-	linkmode_copy(phy_data->phydev->supported, supported);
+	linkmode_copy(phy_data->phydev->supported, PHY_GBIT_FEATURES);
 	phy_support_asym_pause(phy_data->phydev);
 
 	netif_dbg(pdata, drv, pdata->netdev,
@@ -1113,6 +989,7 @@ static int xgbe_phy_find_phy_device(struct xgbe_prv_data *pdata)
 		return ret;
 	}
 	phy_data->phydev = phydev;
+	phy_data->phydev->mac_managed_pm = true;
 
 	xgbe_phy_external_phy_quirks(pdata);
 
@@ -2870,8 +2747,7 @@ static bool xgbe_phy_valid_speed(struct xgbe_prv_data *pdata, int speed)
 static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
-	unsigned int reg;
-	int ret;
+	int reg, ret;
 
 	*an_restart = 0;
 
@@ -2905,11 +2781,20 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 			return 0;
 	}
 
-	/* Link status is latched low, so read once to clear
-	 * and then read again to get current state
-	 */
-	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
 	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+	if (reg < 0)
+		return reg;
+
+	/* Link status is latched low so that momentary link drops
+	 * can be detected. If link was already down read again
+	 * to get the latest state.
+	 */
+
+	if (!pdata->phy.link && !(reg & MDIO_STAT1_LSTATUS)) {
+		reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+		if (reg < 0)
+			return reg;
+	}
 
 	if (pdata->en_rx_adap) {
 		/* if the link is available and adaptation is done,
@@ -2928,9 +2813,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 			xgbe_phy_set_mode(pdata, phy_data->cur_mode);
 		}
 
-		/* check again for the link and adaptation status */
-		reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
-		if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done)
+		if (pdata->rx_adapt_done)
 			return 1;
 	} else if (reg & MDIO_STAT1_LSTATUS)
 		return 1;
@@ -3020,7 +2903,7 @@ static void xgbe_phy_sfp_setup(struct xgbe_prv_data *pdata)
 static int xgbe_phy_int_mdio_reset(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
-	unsigned int ret;
+	int ret;
 
 	ret = pdata->hw_if.set_gpio(pdata, phy_data->mdio_reset_gpio);
 	if (ret)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-platform.c b/drivers/net/ethernet/amd/xgbe/xgbe-platform.c
index 4365bd62942c..47d53e59ccf6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-platform.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-platform.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pps.c b/drivers/net/ethernet/amd/xgbe/xgbe-pps.c
new file mode 100644
index 000000000000..6d03ae7ab36f
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pps.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
+/*
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
+ *
+ * Author: Raju Rangoju <Raju.Rangoju@amd.com>
+ */
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+static u32 get_pps_mask(unsigned int x)
+{
+	return GENMASK(PPS_MAXIDX(x), PPS_MINIDX(x));
+}
+
+static u32 get_pps_cmd(unsigned int x, u32 val)
+{
+	return (val & GENMASK(3, 0)) << PPS_MINIDX(x);
+}
+
+static u32 get_target_mode_sel(unsigned int x, u32 val)
+{
+	return (val & GENMASK(1, 0)) << (PPS_MAXIDX(x) - 2);
+}
+
+int xgbe_pps_config(struct xgbe_prv_data *pdata,
+		    struct xgbe_pps_config *cfg, int index, bool on)
+{
+	unsigned int ppscr = 0;
+	unsigned int tnsec;
+	u64 period;
+
+	/* Check if target time register is busy */
+	tnsec = XGMAC_IOREAD(pdata, MAC_PPSx_TTNSR(index));
+	if (XGMAC_GET_BITS(tnsec, MAC_PPSx_TTNSR, TRGTBUSY0))
+		return -EBUSY;
+
+	ppscr = XGMAC_IOREAD(pdata, MAC_PPSCR);
+	ppscr &= ~get_pps_mask(index);
+
+	if (!on) {
+		/* Disable PPS output */
+		ppscr |= get_pps_cmd(index, XGBE_PPSCMD_STOP);
+		ppscr |= PPSEN0;
+		XGMAC_IOWRITE(pdata, MAC_PPSCR, ppscr);
+
+		return 0;
+	}
+
+	/* Configure start time */
+	XGMAC_IOWRITE(pdata, MAC_PPSx_TTSR(index), cfg->start.tv_sec);
+	XGMAC_IOWRITE(pdata, MAC_PPSx_TTNSR(index), cfg->start.tv_nsec);
+
+	period = cfg->period.tv_sec * NSEC_PER_SEC + cfg->period.tv_nsec;
+	period = div_u64(period, XGBE_V2_TSTAMP_SSINC);
+
+	if (period < 4)
+		return -EINVAL;
+
+	/* Configure interval and pulse width (50% duty cycle) */
+	XGMAC_IOWRITE(pdata, MAC_PPSx_INTERVAL(index), period - 1);
+	XGMAC_IOWRITE(pdata, MAC_PPSx_WIDTH(index), (period >> 1) - 1);
+
+	/* Enable PPS with pulse train mode */
+	ppscr |= get_pps_cmd(index, XGBE_PPSCMD_START);
+	ppscr |= get_target_mode_sel(index, XGBE_PPSTARGET_PULSE);
+	ppscr |= PPSEN0;
+
+	XGMAC_IOWRITE(pdata, MAC_PPSCR, ppscr);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c
index 7051bd7cf6dc..0e0b8ec3b504 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/clk.h>
@@ -122,18 +13,6 @@
 #include "xgbe.h"
 #include "xgbe-common.h"
 
-static u64 xgbe_cc_read(const struct cyclecounter *cc)
-{
-	struct xgbe_prv_data *pdata = container_of(cc,
-						   struct xgbe_prv_data,
-						   tstamp_cc);
-	u64 nsec;
-
-	nsec = pdata->hw_if.get_tstamp_time(pdata);
-
-	return nsec;
-}
-
 static int xgbe_adjfine(struct ptp_clock_info *info, long scaled_ppm)
 {
 	struct xgbe_prv_data *pdata = container_of(info,
@@ -146,7 +25,7 @@ static int xgbe_adjfine(struct ptp_clock_info *info, long scaled_ppm)
 
 	spin_lock_irqsave(&pdata->tstamp_lock, flags);
 
-	pdata->hw_if.update_tstamp_addend(pdata, addend);
+	xgbe_update_tstamp_addend(pdata, addend);
 
 	spin_unlock_irqrestore(&pdata->tstamp_lock, flags);
 
@@ -158,16 +37,39 @@ static int xgbe_adjtime(struct ptp_clock_info *info, s64 delta)
 	struct xgbe_prv_data *pdata = container_of(info,
 						   struct xgbe_prv_data,
 						   ptp_clock_info);
+	unsigned int neg_adjust = 0;
+	unsigned int sec, nsec;
+	u32 quotient, reminder;
 	unsigned long flags;
 
+	if (delta < 0) {
+		neg_adjust = 1;
+		delta = -delta;
+	}
+
+	quotient = div_u64_rem(delta, 1000000000ULL, &reminder);
+	sec = quotient;
+	nsec = reminder;
+
+	/* Negative adjustment for Hw timer register. */
+	if (neg_adjust) {
+		sec = -sec;
+		if (XGMAC_IOREAD_BITS(pdata, MAC_TSCR, TSCTRLSSR))
+			nsec = (1000000000UL - nsec);
+		else
+			nsec = (0x80000000UL - nsec);
+	}
+	nsec = (neg_adjust << 31) | nsec;
+
 	spin_lock_irqsave(&pdata->tstamp_lock, flags);
-	timecounter_adjtime(&pdata->tstamp_tc, delta);
+	xgbe_update_tstamp_time(pdata, sec, nsec);
 	spin_unlock_irqrestore(&pdata->tstamp_lock, flags);
 
 	return 0;
 }
 
-static int xgbe_gettime(struct ptp_clock_info *info, struct timespec64 *ts)
+static int xgbe_gettimex(struct ptp_clock_info *info, struct timespec64 *ts,
+			 struct ptp_system_timestamp *sts)
 {
 	struct xgbe_prv_data *pdata = container_of(info,
 						   struct xgbe_prv_data,
@@ -176,9 +78,9 @@ static int xgbe_gettime(struct ptp_clock_info *info, struct timespec64 *ts)
 	u64 nsec;
 
 	spin_lock_irqsave(&pdata->tstamp_lock, flags);
-
-	nsec = timecounter_read(&pdata->tstamp_tc);
-
+	ptp_read_system_prets(sts);
+	nsec = xgbe_get_tstamp_time(pdata);
+	ptp_read_system_postts(sts);
 	spin_unlock_irqrestore(&pdata->tstamp_lock, flags);
 
 	*ts = ns_to_timespec64(nsec);
@@ -193,14 +95,9 @@ static int xgbe_settime(struct ptp_clock_info *info,
 						   struct xgbe_prv_data,
 						   ptp_clock_info);
 	unsigned long flags;
-	u64 nsec;
-
-	nsec = timespec64_to_ns(ts);
 
 	spin_lock_irqsave(&pdata->tstamp_lock, flags);
-
-	timecounter_init(&pdata->tstamp_tc, &pdata->tstamp_cc, nsec);
-
+	xgbe_set_tstamp_time(pdata, ts->tv_sec, ts->tv_nsec);
 	spin_unlock_irqrestore(&pdata->tstamp_lock, flags);
 
 	return 0;
@@ -209,15 +106,35 @@ static int xgbe_settime(struct ptp_clock_info *info,
 static int xgbe_enable(struct ptp_clock_info *info,
 		       struct ptp_clock_request *request, int on)
 {
-	return -EOPNOTSUPP;
+	struct xgbe_prv_data *pdata = container_of(info, struct xgbe_prv_data,
+						   ptp_clock_info);
+	struct xgbe_pps_config *pps_cfg;
+	unsigned long flags;
+	int ret;
+
+	dev_dbg(pdata->dev, "rq->type %d on %d\n", request->type, on);
+
+	if (request->type != PTP_CLK_REQ_PEROUT)
+		return -EOPNOTSUPP;
+
+	pps_cfg = &pdata->pps[request->perout.index];
+
+	pps_cfg->start.tv_sec = request->perout.start.sec;
+	pps_cfg->start.tv_nsec = request->perout.start.nsec;
+	pps_cfg->period.tv_sec = request->perout.period.sec;
+	pps_cfg->period.tv_nsec = request->perout.period.nsec;
+
+	spin_lock_irqsave(&pdata->tstamp_lock, flags);
+	ret = xgbe_pps_config(pdata, pps_cfg, request->perout.index, on);
+	spin_unlock_irqrestore(&pdata->tstamp_lock, flags);
+
+	return ret;
 }
 
 void xgbe_ptp_register(struct xgbe_prv_data *pdata)
 {
 	struct ptp_clock_info *info = &pdata->ptp_clock_info;
 	struct ptp_clock *clock;
-	struct cyclecounter *cc = &pdata->tstamp_cc;
-	u64 dividend;
 
 	snprintf(info->name, sizeof(info->name), "%s",
 		 netdev_name(pdata->netdev));
@@ -225,8 +142,10 @@ void xgbe_ptp_register(struct xgbe_prv_data *pdata)
 	info->max_adj = pdata->ptpclk_rate;
 	info->adjfine = xgbe_adjfine;
 	info->adjtime = xgbe_adjtime;
-	info->gettime64 = xgbe_gettime;
+	info->gettimex64 = xgbe_gettimex;
 	info->settime64 = xgbe_settime;
+	info->n_per_out = pdata->hw_feat.pps_out_num;
+	info->n_ext_ts = pdata->hw_feat.aux_snap_num;
 	info->enable = xgbe_enable;
 
 	clock = ptp_clock_register(info, pdata->dev);
@@ -237,23 +156,6 @@ void xgbe_ptp_register(struct xgbe_prv_data *pdata)
 
 	pdata->ptp_clock = clock;
 
-	/* Calculate the addend:
-	 *   addend = 2^32 / (PTP ref clock / 50Mhz)
-	 *          = (2^32 * 50Mhz) / PTP ref clock
-	 */
-	dividend = 50000000;
-	dividend <<= 32;
-	pdata->tstamp_addend = div_u64(dividend, pdata->ptpclk_rate);
-
-	/* Setup the timecounter */
-	cc->read = xgbe_cc_read;
-	cc->mask = CLOCKSOURCE_MASK(64);
-	cc->mult = 1;
-	cc->shift = 0;
-
-	timecounter_init(&pdata->tstamp_tc, &pdata->tstamp_cc,
-			 ktime_to_ns(ktime_get_real()));
-
 	/* Disable all timestamping to start */
 	XGMAC_IOWRITE(pdata, MAC_TSCR, 0);
 	pdata->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-selftest.c b/drivers/net/ethernet/amd/xgbe/xgbe-selftest.c
new file mode 100644
index 000000000000..55e5e467facd
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-selftest.c
@@ -0,0 +1,346 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
+/*
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
+ *
+ * Author: Raju Rangoju <Raju.Rangoju@amd.com>
+ */
+#include <linux/crc32.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <net/tcp.h>
+#include <net/udp.h>
+#include <net/checksum.h>
+#include <net/selftests.h>
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+#define XGBE_LOOPBACK_NONE	0
+#define XGBE_LOOPBACK_MAC	1
+#define XGBE_LOOPBACK_PHY	2
+
+struct xgbe_test {
+	char name[ETH_GSTRING_LEN];
+	int lb;
+	int (*fn)(struct xgbe_prv_data *pdata);
+};
+
+static u8 xgbe_test_id;
+
+static int xgbe_test_loopback_validate(struct sk_buff *skb,
+				       struct net_device *ndev,
+				       struct packet_type *pt,
+				       struct net_device *orig_ndev)
+{
+	struct net_test_priv *tdata = pt->af_packet_priv;
+	const unsigned char *dst = tdata->packet->dst;
+	const unsigned char *src = tdata->packet->src;
+	struct netsfhdr *hdr;
+	struct ethhdr *eh;
+	struct tcphdr *th;
+	struct udphdr *uh;
+	struct iphdr *ih;
+	int eat;
+
+	skb = skb_unshare(skb, GFP_ATOMIC);
+	if (!skb)
+		goto out;
+
+	eat = (skb->tail + skb->data_len) - skb->end;
+	if (eat > 0 && skb_shared(skb)) {
+		skb = skb_share_check(skb, GFP_ATOMIC);
+		if (!skb)
+			goto out;
+	}
+
+	if (skb_linearize(skb))
+		goto out;
+
+	if (skb_headlen(skb) < (NET_TEST_PKT_SIZE - ETH_HLEN))
+		goto out;
+
+	eh = (struct ethhdr *)skb_mac_header(skb);
+	if (dst) {
+		if (!ether_addr_equal_unaligned(eh->h_dest, dst))
+			goto out;
+	}
+	if (src) {
+		if (!ether_addr_equal_unaligned(eh->h_source, src))
+			goto out;
+	}
+
+	ih = ip_hdr(skb);
+
+	if (tdata->packet->tcp) {
+		if (ih->protocol != IPPROTO_TCP)
+			goto out;
+
+		th = (struct tcphdr *)((u8 *)ih + 4 * ih->ihl);
+		if (th->dest != htons(tdata->packet->dport))
+			goto out;
+
+		hdr = (struct netsfhdr *)((u8 *)th + sizeof(*th));
+	} else {
+		if (ih->protocol != IPPROTO_UDP)
+			goto out;
+
+		uh = (struct udphdr *)((u8 *)ih + 4 * ih->ihl);
+		if (uh->dest != htons(tdata->packet->dport))
+			goto out;
+
+		hdr = (struct netsfhdr *)((u8 *)uh + sizeof(*uh));
+	}
+
+	if (hdr->magic != cpu_to_be64(NET_TEST_PKT_MAGIC))
+		goto out;
+	if (tdata->packet->id != hdr->id)
+		goto out;
+
+	tdata->ok = true;
+	complete(&tdata->comp);
+out:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int __xgbe_test_loopback(struct xgbe_prv_data *pdata,
+				struct net_packet_attrs *attr)
+{
+	struct net_test_priv *tdata;
+	struct sk_buff *skb = NULL;
+	int ret = 0;
+
+	tdata = kzalloc(sizeof(*tdata), GFP_KERNEL);
+	if (!tdata)
+		return -ENOMEM;
+
+	tdata->ok = false;
+	init_completion(&tdata->comp);
+
+	tdata->pt.type = htons(ETH_P_IP);
+	tdata->pt.func = xgbe_test_loopback_validate;
+	tdata->pt.dev = pdata->netdev;
+	tdata->pt.af_packet_priv = tdata;
+	tdata->packet = attr;
+
+	dev_add_pack(&tdata->pt);
+
+	skb = net_test_get_skb(pdata->netdev, xgbe_test_id, attr);
+	if (!skb) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	xgbe_test_id++;
+	ret = dev_direct_xmit(skb, attr->queue_mapping);
+	if (ret)
+		goto cleanup;
+
+	if (!attr->timeout)
+		attr->timeout = NET_LB_TIMEOUT;
+
+	wait_for_completion_timeout(&tdata->comp, attr->timeout);
+	ret = tdata->ok ? 0 : -ETIMEDOUT;
+
+	if (ret)
+		netdev_err(pdata->netdev, "Response timedout: ret %d\n", ret);
+cleanup:
+	dev_remove_pack(&tdata->pt);
+	kfree(tdata);
+	return ret;
+}
+
+static int xgbe_test_mac_loopback(struct xgbe_prv_data *pdata)
+{
+	struct net_packet_attrs attr = {};
+
+	attr.dst = pdata->netdev->dev_addr;
+	return __xgbe_test_loopback(pdata, &attr);
+}
+
+static int xgbe_test_phy_loopback(struct xgbe_prv_data *pdata)
+{
+	struct net_packet_attrs attr = {};
+	int ret;
+
+	if (!pdata->netdev->phydev) {
+		netdev_err(pdata->netdev, "phydev not found: cannot start PHY loopback test\n");
+		return -EOPNOTSUPP;
+	}
+
+	ret = phy_loopback(pdata->netdev->phydev, true, 0);
+	if (ret)
+		return ret;
+
+	attr.dst = pdata->netdev->dev_addr;
+	ret = __xgbe_test_loopback(pdata, &attr);
+
+	phy_loopback(pdata->netdev->phydev, false, 0);
+	return ret;
+}
+
+static int xgbe_test_sph(struct xgbe_prv_data *pdata)
+{
+	struct net_packet_attrs attr = {};
+	unsigned long cnt_end, cnt_start;
+	int ret;
+
+	cnt_start = pdata->ext_stats.rx_split_header_packets;
+
+	if (!pdata->sph) {
+		netdev_err(pdata->netdev, "Split Header not enabled\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* UDP test */
+	attr.dst = pdata->netdev->dev_addr;
+	attr.tcp = false;
+
+	ret = __xgbe_test_loopback(pdata, &attr);
+	if (ret)
+		return ret;
+
+	cnt_end = pdata->ext_stats.rx_split_header_packets;
+	if (cnt_end <= cnt_start)
+		return -EINVAL;
+
+	/* TCP test */
+	cnt_start = cnt_end;
+
+	attr.dst = pdata->netdev->dev_addr;
+	attr.tcp = true;
+
+	ret = __xgbe_test_loopback(pdata, &attr);
+	if (ret)
+		return ret;
+
+	cnt_end = pdata->ext_stats.rx_split_header_packets;
+	if (cnt_end <= cnt_start)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int xgbe_test_jumbo(struct xgbe_prv_data *pdata)
+{
+	struct net_packet_attrs attr = {};
+	int size = pdata->rx_buf_size;
+
+	attr.dst = pdata->netdev->dev_addr;
+	attr.max_size = size - ETH_FCS_LEN;
+
+	return __xgbe_test_loopback(pdata, &attr);
+}
+
+static const struct xgbe_test xgbe_selftests[] = {
+	{
+		.name = "MAC Loopback   ",
+		.lb = XGBE_LOOPBACK_MAC,
+		.fn = xgbe_test_mac_loopback,
+	}, {
+		.name = "PHY Loopback   ",
+		.lb = XGBE_LOOPBACK_NONE,
+		.fn = xgbe_test_phy_loopback,
+	}, {
+		.name = "Split Header   ",
+		.lb = XGBE_LOOPBACK_PHY,
+		.fn = xgbe_test_sph,
+	}, {
+		.name = "Jumbo Frame    ",
+		.lb = XGBE_LOOPBACK_PHY,
+		.fn = xgbe_test_jumbo,
+	},
+};
+
+void xgbe_selftest_run(struct net_device *dev,
+		       struct ethtool_test *etest, u64 *buf)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(dev);
+	int count = xgbe_selftest_get_count(pdata);
+	int i, ret;
+
+	memset(buf, 0, sizeof(*buf) * count);
+	xgbe_test_id = 0;
+
+	if (etest->flags != ETH_TEST_FL_OFFLINE) {
+		netdev_err(pdata->netdev, "Only offline tests are supported\n");
+		etest->flags |= ETH_TEST_FL_FAILED;
+		return;
+	} else if (!netif_carrier_ok(dev)) {
+		netdev_err(pdata->netdev,
+			   "Invalid link, cannot execute tests\n");
+		etest->flags |= ETH_TEST_FL_FAILED;
+		return;
+	}
+
+	/* Wait for queues drain */
+	msleep(200);
+
+	for (i = 0; i < count; i++) {
+		ret = 0;
+
+		switch (xgbe_selftests[i].lb) {
+		case XGBE_LOOPBACK_PHY:
+			ret = -EOPNOTSUPP;
+			if (dev->phydev)
+				ret = phy_loopback(dev->phydev, true, 0);
+			if (!ret)
+				break;
+			fallthrough;
+		case XGBE_LOOPBACK_MAC:
+			ret = xgbe_enable_mac_loopback(pdata);
+			break;
+		case XGBE_LOOPBACK_NONE:
+			break;
+		default:
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
+		/*
+		 * First tests will always be MAC / PHY loopback.
+		 * If any of them is not supported we abort earlier.
+		 */
+		if (ret) {
+			netdev_err(pdata->netdev, "Loopback not supported\n");
+			etest->flags |= ETH_TEST_FL_FAILED;
+			break;
+		}
+
+		ret = xgbe_selftests[i].fn(pdata);
+		if (ret && (ret != -EOPNOTSUPP))
+			etest->flags |= ETH_TEST_FL_FAILED;
+		buf[i] = ret;
+
+		switch (xgbe_selftests[i].lb) {
+		case XGBE_LOOPBACK_PHY:
+			ret = -EOPNOTSUPP;
+			if (dev->phydev)
+				ret = phy_loopback(dev->phydev, false, 0);
+			if (!ret)
+				break;
+			fallthrough;
+		case XGBE_LOOPBACK_MAC:
+			xgbe_disable_mac_loopback(pdata);
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+void xgbe_selftest_get_strings(struct xgbe_prv_data *pdata, u8 *data)
+{
+	u8 *p = data;
+	int i;
+
+	for (i = 0; i < xgbe_selftest_get_count(pdata); i++)
+		ethtool_puts(&p, xgbe_selftests[i].name);
+}
+
+int xgbe_selftest_get_count(struct xgbe_prv_data *pdata)
+{
+	return ARRAY_SIZE(xgbe_selftests);
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-smn.h b/drivers/net/ethernet/amd/xgbe/xgbe-smn.h
new file mode 100644
index 000000000000..c6ae127ced03
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-smn.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause) */
+/*
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
+ *
+ * Author: Raju Rangoju <Raju.Rangoju@amd.com>
+ */
+
+#ifndef __SMN_H__
+#define __SMN_H__
+
+#ifdef CONFIG_AMD_NB
+
+#include <asm/amd/nb.h>
+
+#else
+
+static inline int amd_smn_write(u16 node, u32 address, u32 value)
+{
+	return -ENODEV;
+}
+
+static inline int amd_smn_read(u16 node, u32 address, u32 *value)
+{
+	return -ENODEV;
+}
+
+#endif
+#endif
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index d85386cac8d1..03ef0f548483 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #ifndef __XGBE_H__
@@ -189,11 +80,13 @@
 #define XGBE_IRQ_MODE_EDGE	0
 #define XGBE_IRQ_MODE_LEVEL	1
 
+#define XGBE_ETH_FRAME_HDR	(ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN)
 #define XGMAC_MIN_PACKET	60
 #define XGMAC_STD_PACKET_MTU	1500
 #define XGMAC_MAX_STD_PACKET	1518
 #define XGMAC_JUMBO_PACKET_MTU	9000
 #define XGMAC_MAX_JUMBO_PACKET	9018
+#define XGMAC_GIANT_PACKET_MTU	16368
 #define XGMAC_ETH_PREAMBLE	(12 + 8)	/* Inter-frame gap + preamble */
 
 #define XGMAC_PFC_DATA_LEN	46
@@ -226,6 +119,14 @@
 #define XGBE_MSI_BASE_COUNT	4
 #define XGBE_MSI_MIN_COUNT	(XGBE_MSI_BASE_COUNT + 1)
 
+/* Initial PTP register values based on Link Speed. */
+#define MAC_TICNR_1G_INITVAL	0x10
+#define MAC_TECNR_1G_INITVAL	0x28
+
+#define MAC_TICSNR_10G_INITVAL	0x33
+#define MAC_TECNR_10G_INITVAL	0x14
+#define MAC_TECSNR_10G_INITVAL	0xCC
+
 /* PCI clock frequencies */
 #define XGBE_V2_DMA_CLOCK_FREQ	500000000	/* 500 MHz */
 #define XGBE_V2_PTP_CLOCK_FREQ	125000000	/* 125 MHz */
@@ -235,6 +136,15 @@
  */
 #define XGBE_TSTAMP_SSINC	20
 #define XGBE_TSTAMP_SNSINC	0
+#define XGBE_PTP_ACT_CLK_FREQ	500000000
+
+#define XGBE_V2_TSTAMP_SSINC	0xA
+#define XGBE_V2_TSTAMP_SNSINC	0
+#define XGBE_V2_PTP_ACT_CLK_FREQ	1000000000
+
+/* Define maximum supported values */
+#define XGBE_MAX_PPS_OUT	4
+#define XGBE_MAX_AUX_SNAP	4
 
 /* Driver PMT macros */
 #define XGMAC_DRIVER_CONTEXT	1
@@ -262,6 +172,7 @@
 /* Default coalescing parameters */
 #define XGMAC_INIT_DMA_TX_USECS		1000
 #define XGMAC_INIT_DMA_TX_FRAMES	25
+#define XGMAC_MAX_COAL_TX_TICK		100000
 
 #define XGMAC_MAX_DMA_RIWT		0xff
 #define XGMAC_INIT_DMA_RX_USECS		30
@@ -292,12 +203,12 @@
 #define XGBE_LINK_TIMEOUT		5
 #define XGBE_KR_TRAINING_WAIT_ITER	50
 
-#define XGBE_SGMII_AN_LINK_STATUS	BIT(1)
+#define XGBE_SGMII_AN_LINK_DUPLEX	BIT(1)
 #define XGBE_SGMII_AN_LINK_SPEED	(BIT(2) | BIT(3))
 #define XGBE_SGMII_AN_LINK_SPEED_10	0x00
 #define XGBE_SGMII_AN_LINK_SPEED_100	0x04
 #define XGBE_SGMII_AN_LINK_SPEED_1000	0x08
-#define XGBE_SGMII_AN_LINK_DUPLEX	BIT(4)
+#define XGBE_SGMII_AN_LINK_STATUS	BIT(4)
 
 /* ECC correctable error notification window (seconds) */
 #define XGBE_ECC_LIMIT			60
@@ -347,6 +258,15 @@
 		    (_src)->link_modes._sname,		\
 		    __ETHTOOL_LINK_MODE_MASK_NBITS)
 
+/* XGBE PCI device id */
+#define XGBE_RV_PCI_DEVICE_ID	0x15d0
+#define XGBE_YC_PCI_DEVICE_ID	0x14b5
+#define XGBE_RN_PCI_DEVICE_ID	0x1630
+
+ /* Generic low and high masks */
+#define XGBE_GEN_HI_MASK	GENMASK(31, 16)
+#define XGBE_GEN_LO_MASK	GENMASK(15, 0)
+
 struct xgbe_prv_data;
 
 struct xgbe_packet_data {
@@ -565,6 +485,7 @@ enum xgbe_speed {
 enum xgbe_xpcs_access {
 	XGBE_XPCS_ACCESS_V1 = 0,
 	XGBE_XPCS_ACCESS_V2,
+	XGBE_XPCS_ACCESS_V3,
 };
 
 enum xgbe_an_mode {
@@ -756,6 +677,11 @@ struct xgbe_ext_stats {
 	u64 rx_vxlan_csum_errors;
 };
 
+struct xgbe_pps_config {
+	struct timespec64 start;
+	struct timespec64 period;
+};
+
 struct xgbe_hw_if {
 	int (*tx_complete)(struct xgbe_ring_desc *);
 
@@ -838,14 +764,6 @@ struct xgbe_hw_if {
 	void (*tx_mmc_int)(struct xgbe_prv_data *);
 	void (*read_mmc_stats)(struct xgbe_prv_data *);
 
-	/* For Timestamp config */
-	int (*config_tstamp)(struct xgbe_prv_data *, unsigned int);
-	void (*update_tstamp_addend)(struct xgbe_prv_data *, unsigned int);
-	void (*set_tstamp_time)(struct xgbe_prv_data *, unsigned int sec,
-				unsigned int nsec);
-	u64 (*get_tstamp_time)(struct xgbe_prv_data *);
-	u64 (*get_tx_tstamp)(struct xgbe_prv_data *);
-
 	/* For Data Center Bridging config */
 	void (*config_tc)(struct xgbe_prv_data *);
 	void (*config_dcb_tc)(struct xgbe_prv_data *);
@@ -865,6 +783,10 @@ struct xgbe_hw_if {
 	void (*enable_vxlan)(struct xgbe_prv_data *);
 	void (*disable_vxlan)(struct xgbe_prv_data *);
 	void (*set_vxlan_id)(struct xgbe_prv_data *);
+
+	/* For Split Header */
+	void (*enable_sph)(struct xgbe_prv_data *pdata);
+	void (*disable_sph)(struct xgbe_prv_data *pdata);
 };
 
 /* This structure represents implementation specific routines for an
@@ -1039,6 +961,7 @@ struct xgbe_version_data {
 	unsigned int tx_max_fifo_size;
 	unsigned int rx_max_fifo_size;
 	unsigned int tx_tstamp_workaround;
+	unsigned int tstamp_ptp_clock_freq;
 	unsigned int ecc_support;
 	unsigned int i2c_support;
 	unsigned int irq_reissue_support;
@@ -1056,6 +979,7 @@ struct xgbe_prv_data {
 	struct device *dev;
 	struct platform_device *phy_platdev;
 	struct device *phy_dev;
+	unsigned int smn_base;
 
 	/* Version related data */
 	struct xgbe_version_data *vdata;
@@ -1222,14 +1146,15 @@ struct xgbe_prv_data {
 	spinlock_t tstamp_lock;
 	struct ptp_clock_info ptp_clock_info;
 	struct ptp_clock *ptp_clock;
-	struct hwtstamp_config tstamp_config;
-	struct cyclecounter tstamp_cc;
-	struct timecounter tstamp_tc;
+	struct kernel_hwtstamp_config tstamp_config;
 	unsigned int tstamp_addend;
 	struct work_struct tx_tstamp_work;
 	struct sk_buff *tx_tstamp_skb;
 	u64 tx_tstamp;
 
+	/* Pulse Per Second output */
+	struct xgbe_pps_config pps[XGBE_MAX_PPS_OUT];
+
 	/* DCB support */
 	struct ieee_ets *ets;
 	struct ieee_pfc *pfc;
@@ -1321,6 +1246,7 @@ struct xgbe_prv_data {
 	int rx_adapt_retries;
 	bool rx_adapt_done;
 	bool mode_set;
+	bool sph;
 };
 
 /* Function prototypes*/
@@ -1369,6 +1295,44 @@ void xgbe_init_tx_coalesce(struct xgbe_prv_data *);
 void xgbe_restart_dev(struct xgbe_prv_data *pdata);
 void xgbe_full_restart_dev(struct xgbe_prv_data *pdata);
 
+/* For Timestamp config */
+void xgbe_config_tstamp(struct xgbe_prv_data *pdata, unsigned int mac_tscr);
+u64 xgbe_get_tstamp_time(struct xgbe_prv_data *pdata);
+u64 xgbe_get_tx_tstamp(struct xgbe_prv_data *pdata);
+void xgbe_get_rx_tstamp(struct xgbe_packet_data *packet,
+			struct xgbe_ring_desc *rdesc);
+void xgbe_get_rx_tstamp(struct xgbe_packet_data *packet,
+			struct xgbe_ring_desc *rdesc);
+void xgbe_update_tstamp_addend(struct xgbe_prv_data *pdata,
+			       unsigned int addend);
+void xgbe_set_tstamp_time(struct xgbe_prv_data *pdata, unsigned int sec,
+			  unsigned int nsec);
+void xgbe_tx_tstamp(struct work_struct *work);
+int xgbe_get_hwtstamp_settings(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *config);
+int xgbe_set_hwtstamp_settings(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack);
+void xgbe_prep_tx_tstamp(struct xgbe_prv_data *pdata,
+			 struct sk_buff *skb,
+			 struct xgbe_packet_data *packet);
+int xgbe_init_ptp(struct xgbe_prv_data *pdata);
+void xgbe_update_tstamp_time(struct xgbe_prv_data *pdata, unsigned int sec,
+			     unsigned int nsec);
+
+int xgbe_pps_config(struct xgbe_prv_data *pdata, struct xgbe_pps_config *cfg,
+		    int index, bool on);
+
+/* Selftest functions */
+void xgbe_selftest_run(struct net_device *dev,
+		       struct ethtool_test *etest, u64 *buf);
+void xgbe_selftest_get_strings(struct xgbe_prv_data *pdata, u8 *data);
+int xgbe_selftest_get_count(struct xgbe_prv_data *pdata);
+
+/* Loopback control */
+int xgbe_enable_mac_loopback(struct xgbe_prv_data *pdata);
+void xgbe_disable_mac_loopback(struct xgbe_prv_data *pdata);
+
 #ifdef CONFIG_DEBUG_FS
 void xgbe_debugfs_init(struct xgbe_prv_data *);
 void xgbe_debugfs_exit(struct xgbe_prv_data *);
diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c
index 2a91c84aebdb..d7ca847d44c7 100644
--- a/drivers/net/ethernet/apm/xgene-v2/main.c
+++ b/drivers/net/ethernet/apm/xgene-v2/main.c
@@ -9,8 +9,6 @@
 
 #include "main.h"
 
-static const struct acpi_device_id xge_acpi_match[];
-
 static int xge_get_resources(struct xge_pdata *pdata)
 {
 	struct platform_device *pdev;
@@ -731,7 +729,7 @@ MODULE_DEVICE_TABLE(acpi, xge_acpi_match);
 static struct platform_driver xge_driver = {
 	.driver = {
 		   .name = "xgene-enet-v2",
-		   .acpi_match_table = ACPI_PTR(xge_acpi_match),
+		   .acpi_match_table = xge_acpi_match,
 	},
 	.probe = xge_probe,
 	.remove = xge_remove,
diff --git a/drivers/net/ethernet/apm/xgene-v2/mdio.c b/drivers/net/ethernet/apm/xgene-v2/mdio.c
index eba06831aec2..6a17045a5f62 100644
--- a/drivers/net/ethernet/apm/xgene-v2/mdio.c
+++ b/drivers/net/ethernet/apm/xgene-v2/mdio.c
@@ -97,7 +97,6 @@ void xge_mdio_remove(struct net_device *ndev)
 
 int xge_mdio_config(struct net_device *ndev)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct xge_pdata *pdata = netdev_priv(ndev);
 	struct device *dev = &pdata->pdev->dev;
 	struct mii_bus *mdio_bus;
@@ -137,17 +136,12 @@ int xge_mdio_config(struct net_device *ndev)
 		goto err;
 	}
 
-	linkmode_set_bit_array(phy_10_100_features_array,
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_AUI_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_BNC_BIT, mask);
-
-	linkmode_andnot(phydev->supported, phydev->supported, mask);
-	linkmode_copy(phydev->advertising, phydev->supported);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Full_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Full_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
+
 	pdata->phy_speed = SPEED_UNKNOWN;
 
 	return 0;
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
index 86607b79c09f..cc3b1631c905 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
@@ -6,8 +6,14 @@
  *	    Keyur Chudgar <kchudgar@apm.com>
  */
 
-#include <linux/of_gpio.h>
-#include <linux/gpio.h>
+#include <linux/acpi.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/io.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
 #include "xgene_enet_main.h"
 #include "xgene_enet_hw.h"
 #include "xgene_enet_xgmac.h"
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index 785f4b4ff758..b3bf8d6f88e8 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -20,7 +20,6 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/crc32.h>
-#include <linux/crc32poly.h>
 #include <linux/bitrev.h>
 #include <linux/ethtool.h>
 #include <linux/slab.h>
@@ -461,7 +460,7 @@ static int bmac_suspend(struct macio_dev *mdev, pm_message_t state)
 	/* prolly should wait for dma to finish & turn off the chip */
 	spin_lock_irqsave(&bp->lock, flags);
 	if (bp->timeout_active) {
-		del_timer(&bp->tx_timeout);
+		timer_delete(&bp->tx_timeout);
 		bp->timeout_active = 0;
 	}
 	disable_irq(dev->irq);
@@ -546,7 +545,7 @@ static inline void bmac_set_timeout(struct net_device *dev)
 
 	spin_lock_irqsave(&bp->lock, flags);
 	if (bp->timeout_active)
-		del_timer(&bp->tx_timeout);
+		timer_delete(&bp->tx_timeout);
 	bp->tx_timeout.expires = jiffies + TX_TIMEOUT;
 	add_timer(&bp->tx_timeout);
 	bp->timeout_active = 1;
@@ -755,7 +754,7 @@ static irqreturn_t bmac_txdma_intr(int irq, void *dev_id)
 		XXDEBUG(("bmac_txdma_intr\n"));
 	}
 
-	/*     del_timer(&bp->tx_timeout); */
+	/*     timer_delete(&bp->tx_timeout); */
 	/*     bp->timeout_active = 0; */
 
 	while (1) {
@@ -796,59 +795,6 @@ static irqreturn_t bmac_txdma_intr(int irq, void *dev_id)
 }
 
 #ifndef SUNHME_MULTICAST
-/* Real fast bit-reversal algorithm, 6-bit values */
-static int reverse6[64] = {
-	0x0,0x20,0x10,0x30,0x8,0x28,0x18,0x38,
-	0x4,0x24,0x14,0x34,0xc,0x2c,0x1c,0x3c,
-	0x2,0x22,0x12,0x32,0xa,0x2a,0x1a,0x3a,
-	0x6,0x26,0x16,0x36,0xe,0x2e,0x1e,0x3e,
-	0x1,0x21,0x11,0x31,0x9,0x29,0x19,0x39,
-	0x5,0x25,0x15,0x35,0xd,0x2d,0x1d,0x3d,
-	0x3,0x23,0x13,0x33,0xb,0x2b,0x1b,0x3b,
-	0x7,0x27,0x17,0x37,0xf,0x2f,0x1f,0x3f
-};
-
-static unsigned int
-crc416(unsigned int curval, unsigned short nxtval)
-{
-	unsigned int counter, cur = curval, next = nxtval;
-	int high_crc_set, low_data_set;
-
-	/* Swap bytes */
-	next = ((next & 0x00FF) << 8) | (next >> 8);
-
-	/* Compute bit-by-bit */
-	for (counter = 0; counter < 16; ++counter) {
-		/* is high CRC bit set? */
-		if ((cur & 0x80000000) == 0) high_crc_set = 0;
-		else high_crc_set = 1;
-
-		cur = cur << 1;
-
-		if ((next & 0x0001) == 0) low_data_set = 0;
-		else low_data_set = 1;
-
-		next = next >> 1;
-
-		/* do the XOR */
-		if (high_crc_set ^ low_data_set) cur = cur ^ CRC32_POLY_BE;
-	}
-	return cur;
-}
-
-static unsigned int
-bmac_crc(unsigned short *address)
-{
-	unsigned int newcrc;
-
-	XXDEBUG(("bmac_crc: addr=%#04x, %#04x, %#04x\n", *address, address[1], address[2]));
-	newcrc = crc416(0xffffffff, *address);	/* address bits 47 - 32 */
-	newcrc = crc416(newcrc, address[1]);	/* address bits 31 - 16 */
-	newcrc = crc416(newcrc, address[2]);	/* address bits 15 - 0  */
-
-	return(newcrc);
-}
-
 /*
  * Add requested mcast addr to BMac's hash table filter.
  *
@@ -861,8 +807,7 @@ bmac_addhash(struct bmac_data *bp, unsigned char *addr)
 	unsigned short	 mask;
 
 	if (!(*addr)) return;
-	crc = bmac_crc((unsigned short *)addr) & 0x3f; /* Big-endian alert! */
-	crc = reverse6[crc];	/* Hyperfast bit-reversing algorithm */
+	crc = crc32(~0, addr, ETH_ALEN) >> 26;
 	if (bp->hash_use_count[crc]++) return; /* This bit is already set */
 	mask = crc % 16;
 	mask = (unsigned char)1 << mask;
@@ -876,8 +821,7 @@ bmac_removehash(struct bmac_data *bp, unsigned char *addr)
 	unsigned char mask;
 
 	/* Now, delete the address from the filter copy, as indicated */
-	crc = bmac_crc((unsigned short *)addr) & 0x3f; /* Big-endian alert! */
-	crc = reverse6[crc];	/* Hyperfast bit-reversing algorithm */
+	crc = crc32(~0, addr, ETH_ALEN) >> 26;
 	if (bp->hash_use_count[crc] == 0) return; /* That bit wasn't in use! */
 	if (--bp->hash_use_count[crc]) return; /* That bit is still in use */
 	mask = crc % 16;
@@ -1466,7 +1410,7 @@ bmac_output(struct sk_buff *skb, struct net_device *dev)
 
 static void bmac_tx_timeout(struct timer_list *t)
 {
-	struct bmac_data *bp = from_timer(bp, t, tx_timeout);
+	struct bmac_data *bp = timer_container_of(bp, t, tx_timeout);
 	struct net_device *dev = macio_get_drvdata(bp->mdev);
 	volatile struct dbdma_regs __iomem *td = bp->tx_dma;
 	volatile struct dbdma_regs __iomem *rd = bp->rx_dma;
diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c
index e6350971c707..af26905e44e3 100644
--- a/drivers/net/ethernet/apple/mace.c
+++ b/drivers/net/ethernet/apple/mace.c
@@ -523,7 +523,7 @@ static inline void mace_set_timeout(struct net_device *dev)
     struct mace_data *mp = netdev_priv(dev);
 
     if (mp->timeout_active)
-	del_timer(&mp->tx_timeout);
+	timer_delete(&mp->tx_timeout);
     mp->tx_timeout.expires = jiffies + TX_TIMEOUT;
     add_timer(&mp->tx_timeout);
     mp->timeout_active = 1;
@@ -676,7 +676,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id)
 
     i = mp->tx_empty;
     while (in_8(&mb->pr) & XMTSV) {
-	del_timer(&mp->tx_timeout);
+	timer_delete(&mp->tx_timeout);
 	mp->timeout_active = 0;
 	/*
 	 * Clear any interrupt indication associated with this status
@@ -805,7 +805,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id)
 
 static void mace_tx_timeout(struct timer_list *t)
 {
-    struct mace_data *mp = from_timer(mp, t, tx_timeout);
+    struct mace_data *mp = timer_container_of(mp, t, tx_timeout);
     struct net_device *dev = macio_get_drvdata(mp->mdev);
     volatile struct mace __iomem *mb = mp->mace;
     volatile struct dbdma_regs __iomem *td = mp->tx_dma;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c b/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c
index 414b2e448d59..787ea91802e7 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c
@@ -113,19 +113,9 @@ static const struct hwmon_ops aq_hwmon_ops = {
 	.read_string = aq_hwmon_read_string,
 };
 
-static u32 aq_hwmon_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_LABEL,
-	HWMON_T_INPUT | HWMON_T_LABEL,
-	0,
-};
-
-static const struct hwmon_channel_info aq_hwmon_temp = {
-	.type = hwmon_temp,
-	.config = aq_hwmon_temp_config,
-};
-
 static const struct hwmon_channel_info * const aq_hwmon_info[] = {
-	&aq_hwmon_temp,
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_LABEL),
 	NULL,
 };
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index 42c0efc1b455..4e66fd9b2ab1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -113,6 +113,8 @@ struct aq_stats_s {
 #define AQ_HW_POWER_STATE_D0   0U
 #define AQ_HW_POWER_STATE_D3   3U
 
+#define	AQ_FW_WAKE_ON_LINK_RTPM BIT(10)
+
 #define AQ_HW_FLAG_STARTED     0x00000004U
 #define AQ_HW_FLAG_STOPPING    0x00000008U
 #define AQ_HW_FLAG_RESETTING   0x00000010U
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c
index 1921741f7311..18b08277d2e1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c
@@ -15,6 +15,7 @@
 
 #include "aq_hw.h"
 #include "aq_nic.h"
+#include "hw_atl/hw_atl_llh.h"
 
 void aq_hw_write_reg_bit(struct aq_hw_s *aq_hw, u32 addr, u32 msk,
 			 u32 shift, u32 val)
@@ -81,6 +82,27 @@ void aq_hw_write_reg64(struct aq_hw_s *hw, u32 reg, u64 value)
 		lo_hi_writeq(value, hw->mmio + reg);
 }
 
+int aq_hw_invalidate_descriptor_cache(struct aq_hw_s *hw)
+{
+	int err;
+	u32 val;
+
+	/* Invalidate Descriptor Cache to prevent writing to the cached
+	 * descriptors and to the data pointer of those descriptors
+	 */
+	hw_atl_rdm_rx_dma_desc_cache_init_tgl(hw);
+
+	err = aq_hw_err_from_flags(hw);
+	if (err)
+		goto err_exit;
+
+	readx_poll_timeout_atomic(hw_atl_rdm_rx_dma_desc_cache_init_done_get,
+				  hw, val, val == 1, 1000U, 10000U);
+
+err_exit:
+	return err;
+}
+
 int aq_hw_err_from_flags(struct aq_hw_s *hw)
 {
 	int err = 0;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h
index ffa6e4067c21..d89c63d88e4a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h
@@ -35,6 +35,7 @@ u32 aq_hw_read_reg(struct aq_hw_s *hw, u32 reg);
 void aq_hw_write_reg(struct aq_hw_s *hw, u32 reg, u32 value);
 u64 aq_hw_read_reg64(struct aq_hw_s *hw, u32 reg);
 void aq_hw_write_reg64(struct aq_hw_s *hw, u32 reg, u64 value);
+int aq_hw_invalidate_descriptor_cache(struct aq_hw_s *hw);
 int aq_hw_err_from_flags(struct aq_hw_s *hw);
 int aq_hw_num_tcs(struct aq_hw_s *hw);
 int aq_hw_q_per_tc(struct aq_hw_s *hw);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index c1d1673c5749..4ef4fe64b8ac 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -123,7 +123,6 @@ static netdev_tx_t aq_ndev_start_xmit(struct sk_buff *skb, struct net_device *nd
 	}
 #endif
 
-	skb_tx_timestamp(skb);
 	return aq_nic_xmit(aq_nic, skb);
 }
 
@@ -259,10 +258,15 @@ static void aq_ndev_set_multicast_settings(struct net_device *ndev)
 	(void)aq_nic_set_multicast_list(aq_nic, ndev);
 }
 
-#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK)
-static int aq_ndev_config_hwtstamp(struct aq_nic_s *aq_nic,
-				   struct hwtstamp_config *config)
+static int aq_ndev_hwtstamp_set(struct net_device *netdev,
+				struct kernel_hwtstamp_config *config,
+				struct netlink_ext_ack *extack)
 {
+	struct aq_nic_s *aq_nic = netdev_priv(netdev);
+
+	if (!IS_REACHABLE(CONFIG_PTP_1588_CLOCK) || !aq_nic->aq_ptp)
+		return -EOPNOTSUPP;
+
 	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 	case HWTSTAMP_TX_ON:
@@ -291,59 +295,17 @@ static int aq_ndev_config_hwtstamp(struct aq_nic_s *aq_nic,
 
 	return aq_ptp_hwtstamp_config_set(aq_nic->aq_ptp, config);
 }
-#endif
-
-static int aq_ndev_hwtstamp_set(struct aq_nic_s *aq_nic, struct ifreq *ifr)
-{
-	struct hwtstamp_config config;
-#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK)
-	int ret_val;
-#endif
-
-	if (!aq_nic->aq_ptp)
-		return -EOPNOTSUPP;
-
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK)
-	ret_val = aq_ndev_config_hwtstamp(aq_nic, &config);
-	if (ret_val)
-		return ret_val;
-#endif
-
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-	       -EFAULT : 0;
-}
 
-#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK)
-static int aq_ndev_hwtstamp_get(struct aq_nic_s *aq_nic, struct ifreq *ifr)
+static int aq_ndev_hwtstamp_get(struct net_device *netdev,
+				struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config config;
+	struct aq_nic_s *aq_nic = netdev_priv(netdev);
 
 	if (!aq_nic->aq_ptp)
 		return -EOPNOTSUPP;
 
-	aq_ptp_hwtstamp_config_get(aq_nic->aq_ptp, &config);
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-	       -EFAULT : 0;
-}
-#endif
-
-static int aq_ndev_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
-{
-	struct aq_nic_s *aq_nic = netdev_priv(netdev);
-
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return aq_ndev_hwtstamp_set(aq_nic, ifr);
-
-#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK)
-	case SIOCGHWTSTAMP:
-		return aq_ndev_hwtstamp_get(aq_nic, ifr);
-#endif
-	}
-
-	return -EOPNOTSUPP;
+	aq_ptp_hwtstamp_config_get(aq_nic->aq_ptp, config);
+	return 0;
 }
 
 static int aq_ndo_vlan_rx_add_vid(struct net_device *ndev, __be16 proto,
@@ -501,12 +463,13 @@ static const struct net_device_ops aq_ndev_ops = {
 	.ndo_set_mac_address = aq_ndev_set_mac_address,
 	.ndo_set_features = aq_ndev_set_features,
 	.ndo_fix_features = aq_ndev_fix_features,
-	.ndo_eth_ioctl = aq_ndev_ioctl,
 	.ndo_vlan_rx_add_vid = aq_ndo_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid = aq_ndo_vlan_rx_kill_vid,
 	.ndo_setup_tc = aq_ndo_setup_tc,
 	.ndo_bpf = aq_xdp,
 	.ndo_xdp_xmit = aq_xdp_xmit,
+	.ndo_hwtstamp_get = aq_ndev_hwtstamp_get,
+	.ndo_hwtstamp_set = aq_ndev_hwtstamp_set,
 };
 
 static int __init aq_ndev_init_module(void)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index fe0e3e2a8117..b24eaa5283fa 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -254,7 +254,7 @@ static void aq_nic_service_task(struct work_struct *work)
 
 static void aq_nic_service_timer_cb(struct timer_list *t)
 {
-	struct aq_nic_s *self = from_timer(self, t, service_timer);
+	struct aq_nic_s *self = timer_container_of(self, t, service_timer);
 
 	mod_timer(&self->service_timer,
 		  jiffies + AQ_CFG_SERVICE_TIMER_INTERVAL);
@@ -264,7 +264,7 @@ static void aq_nic_service_timer_cb(struct timer_list *t)
 
 static void aq_nic_polling_timer_cb(struct timer_list *t)
 {
-	struct aq_nic_s *self = from_timer(self, t, polling_timer);
+	struct aq_nic_s *self = timer_container_of(self, t, polling_timer);
 	unsigned int i = 0U;
 
 	for (i = 0U; self->aq_vecs > i; ++i)
@@ -898,6 +898,8 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 
 	frags = aq_nic_map_skb(self, skb, ring);
 
+	skb_tx_timestamp(skb);
+
 	if (likely(frags)) {
 		err = self->aq_hw_ops->hw_ring_tx_xmit(self->aq_hw,
 						       ring, frags);
@@ -1389,13 +1391,13 @@ int aq_nic_stop(struct aq_nic_s *self)
 	netif_tx_disable(self->ndev);
 	netif_carrier_off(self->ndev);
 
-	del_timer_sync(&self->service_timer);
+	timer_delete_sync(&self->service_timer);
 	cancel_work_sync(&self->service_task);
 
 	self->aq_hw_ops->hw_irq_disable(self->aq_hw, AQ_CFG_IRQ_MASK);
 
 	if (self->aq_nic_cfg.is_polling)
-		del_timer_sync(&self->polling_timer);
+		timer_delete_sync(&self->polling_timer);
 	else
 		aq_pci_func_free_irqs(self);
 
@@ -1441,7 +1443,9 @@ void aq_nic_deinit(struct aq_nic_s *self, bool link_down)
 	aq_ptp_ring_free(self);
 	aq_ptp_free(self);
 
-	if (likely(self->aq_fw_ops->deinit) && link_down) {
+	/* May be invoked during hot unplug. */
+	if (pci_device_is_present(self->pdev) &&
+	    likely(self->aq_fw_ops->deinit) && link_down) {
 		mutex_lock(&self->fwreq_mutex);
 		self->aq_fw_ops->deinit(self->aq_hw);
 		mutex_unlock(&self->fwreq_mutex);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index 08630ee94251..ed5231dece3f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -463,7 +463,7 @@ static const struct dev_pm_ops aq_pm_ops = {
 };
 #endif
 
-static struct pci_driver aq_pci_ops = {
+static struct pci_driver aq_pci_driver = {
 	.name = AQ_CFG_DRV_NAME,
 	.id_table = aq_pci_tbl,
 	.probe = aq_pci_probe,
@@ -476,11 +476,11 @@ static struct pci_driver aq_pci_ops = {
 
 int aq_pci_func_register_driver(void)
 {
-	return pci_register_driver(&aq_pci_ops);
+	return pci_register_driver(&aq_pci_driver);
 }
 
 void aq_pci_func_unregister_driver(void)
 {
-	pci_unregister_driver(&aq_pci_ops);
+	pci_unregister_driver(&aq_pci_driver);
 }
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
index 5acb3e16b567..0fa0f891c0e0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
@@ -51,7 +51,7 @@ struct ptp_tx_timeout {
 
 struct aq_ptp_s {
 	struct aq_nic_s *aq_nic;
-	struct hwtstamp_config hwtstamp_config;
+	struct kernel_hwtstamp_config hwtstamp_config;
 	spinlock_t ptp_lock;
 	spinlock_t ptp_ring_lock;
 	struct ptp_clock *ptp_clock;
@@ -567,7 +567,7 @@ static void aq_ptp_rx_hwtstamp(struct aq_ptp_s *aq_ptp, struct skb_shared_hwtsta
 }
 
 void aq_ptp_hwtstamp_config_get(struct aq_ptp_s *aq_ptp,
-				struct hwtstamp_config *config)
+				struct kernel_hwtstamp_config *config)
 {
 	*config = aq_ptp->hwtstamp_config;
 }
@@ -588,7 +588,7 @@ static void aq_ptp_prepare_filters(struct aq_ptp_s *aq_ptp)
 }
 
 int aq_ptp_hwtstamp_config_set(struct aq_ptp_s *aq_ptp,
-			       struct hwtstamp_config *config)
+			       struct kernel_hwtstamp_config *config)
 {
 	struct aq_nic_s *aq_nic = aq_ptp->aq_nic;
 	const struct aq_hw_ops *hw_ops;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h
index 210b723f2207..5e643ec7cc06 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h
@@ -60,9 +60,9 @@ void aq_ptp_tx_hwtstamp(struct aq_nic_s *aq_nic, u64 timestamp);
 
 /* Must be to check available of PTP before call */
 void aq_ptp_hwtstamp_config_get(struct aq_ptp_s *aq_ptp,
-				struct hwtstamp_config *config);
+				struct kernel_hwtstamp_config *config);
 int aq_ptp_hwtstamp_config_set(struct aq_ptp_s *aq_ptp,
-			       struct hwtstamp_config *config);
+			       struct kernel_hwtstamp_config *config);
 
 /* Return either ring is belong to PTP or not*/
 bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring);
@@ -130,9 +130,9 @@ static inline int aq_ptp_xmit(struct aq_nic_s *aq_nic, struct sk_buff *skb)
 
 static inline void aq_ptp_tx_hwtstamp(struct aq_nic_s *aq_nic, u64 timestamp) {}
 static inline void aq_ptp_hwtstamp_config_get(struct aq_ptp_s *aq_ptp,
-					      struct hwtstamp_config *config) {}
+					      struct kernel_hwtstamp_config *config) {}
 static inline int aq_ptp_hwtstamp_config_set(struct aq_ptp_s *aq_ptp,
-					     struct hwtstamp_config *config)
+					     struct kernel_hwtstamp_config *config)
 {
 	return 0;
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index f21de0c21e52..d23d23bed39f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -547,6 +547,11 @@ static int __aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi,
 
 		if (!buff->is_eop) {
 			unsigned int frag_cnt = 0U;
+
+			/* There will be an extra fragment */
+			if (buff->len > AQ_CFG_RX_HDR_SIZE)
+				frag_cnt++;
+
 			buff_ = buff;
 			do {
 				bool is_rsc_completed = true;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 493432d036b9..c7895bfb2ecf 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -1198,26 +1198,9 @@ static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self)
 
 static int hw_atl_b0_hw_stop(struct aq_hw_s *self)
 {
-	int err;
-	u32 val;
-
 	hw_atl_b0_hw_irq_disable(self, HW_ATL_B0_INT_MASK);
 
-	/* Invalidate Descriptor Cache to prevent writing to the cached
-	 * descriptors and to the data pointer of those descriptors
-	 */
-	hw_atl_rdm_rx_dma_desc_cache_init_tgl(self);
-
-	err = aq_hw_err_from_flags(self);
-
-	if (err)
-		goto err_exit;
-
-	readx_poll_timeout_atomic(hw_atl_rdm_rx_dma_desc_cache_init_done_get,
-				  self, val, val == 1, 1000U, 10000U);
-
-err_exit:
-	return err;
+	return aq_hw_invalidate_descriptor_cache(self);
 }
 
 int hw_atl_b0_hw_ring_tx_stop(struct aq_hw_s *self, struct aq_ring_s *ring)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index f5901f8e3907..f6b990b7f5b4 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -226,7 +226,6 @@ struct __packed offload_info {
 	struct offload_port_info ports;
 	struct offload_ka_info kas;
 	struct offload_rr_info rrs;
-	u8 buf[];
 };
 
 struct __packed hw_atl_utils_fw_rpc {
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index b0ed572e88c6..0ce9caae8799 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -759,7 +759,7 @@ static int hw_atl2_hw_stop(struct aq_hw_s *self)
 {
 	hw_atl_b0_hw_irq_disable(self, HW_ATL2_INT_MASK);
 
-	return 0;
+	return aq_hw_invalidate_descriptor_cache(self);
 }
 
 static struct aq_stats_s *hw_atl2_utils_get_hw_stats(struct aq_hw_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
index 52e2070a4a2f..7370e3f76b62 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
@@ -462,6 +462,44 @@ static int aq_a2_fw_get_mac_temp(struct aq_hw_s *self, int *temp)
 	return aq_a2_fw_get_phy_temp(self, temp);
 }
 
+static int aq_a2_fw_set_wol_params(struct aq_hw_s *self, const u8 *mac, u32 wol)
+{
+	struct mac_address_aligned_s mac_address;
+	struct link_control_s link_control;
+	struct wake_on_lan_s wake_on_lan;
+
+	memcpy(mac_address.aligned.mac_address, mac, ETH_ALEN);
+	hw_atl2_shared_buffer_write(self, mac_address, mac_address);
+
+	memset(&wake_on_lan, 0, sizeof(wake_on_lan));
+
+	if (wol & WAKE_MAGIC)
+		wake_on_lan.wake_on_magic_packet = 1U;
+
+	if (wol & (WAKE_PHY | AQ_FW_WAKE_ON_LINK_RTPM))
+		wake_on_lan.wake_on_link_up = 1U;
+
+	hw_atl2_shared_buffer_write(self, sleep_proxy, wake_on_lan);
+
+	hw_atl2_shared_buffer_get(self, link_control, link_control);
+	link_control.mode = AQ_HOST_MODE_SLEEP_PROXY;
+	hw_atl2_shared_buffer_write(self, link_control, link_control);
+
+	return hw_atl2_shared_buffer_finish_ack(self);
+}
+
+static int aq_a2_fw_set_power(struct aq_hw_s *self, unsigned int power_state,
+			      const u8 *mac)
+{
+	u32 wol = self->aq_nic_cfg->wol;
+	int err = 0;
+
+	if (wol)
+		err = aq_a2_fw_set_wol_params(self, mac, wol);
+
+	return err;
+}
+
 static int aq_a2_fw_set_eee_rate(struct aq_hw_s *self, u32 speed)
 {
 	struct link_options_s link_options;
@@ -605,6 +643,7 @@ const struct aq_fw_ops aq_a2_fw_ops = {
 	.set_state          = aq_a2_fw_set_state,
 	.update_link_status = aq_a2_fw_update_link_status,
 	.update_stats       = aq_a2_fw_update_stats,
+	.set_power          = aq_a2_fw_set_power,
 	.get_mac_temp       = aq_a2_fw_get_mac_temp,
 	.get_phy_temp       = aq_a2_fw_get_phy_temp,
 	.set_eee_rate       = aq_a2_fw_set_eee_rate,
diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 3d4c3d8698e2..cbc730c7cff2 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1213,6 +1213,11 @@ static bool ag71xx_fill_rx_buf(struct ag71xx *ag, struct ag71xx_buf *buf,
 	buf->rx.rx_buf = data;
 	buf->rx.dma_addr = dma_map_single(&ag->pdev->dev, data, ag->rx_buf_size,
 					  DMA_FROM_DEVICE);
+	if (dma_mapping_error(&ag->pdev->dev, buf->rx.dma_addr)) {
+		skb_free_frag(data);
+		buf->rx.rx_buf = NULL;
+		return false;
+	}
 	desc->data = (u32)buf->rx.dma_addr + offset;
 	return true;
 }
@@ -1391,7 +1396,7 @@ static void ag71xx_hw_disable(struct ag71xx *ag)
 	ag71xx_dma_reset(ag);
 
 	napi_disable(&ag->napi);
-	del_timer_sync(&ag->oom_timer);
+	timer_delete_sync(&ag->oom_timer);
 
 	ag71xx_rings_cleanup(ag);
 }
@@ -1511,6 +1516,10 @@ static netdev_tx_t ag71xx_hard_start_xmit(struct sk_buff *skb,
 
 	dma_addr = dma_map_single(&ag->pdev->dev, skb->data, skb->len,
 				  DMA_TO_DEVICE);
+	if (dma_mapping_error(&ag->pdev->dev, dma_addr)) {
+		netif_dbg(ag, tx_err, ndev, "DMA mapping error\n");
+		goto err_drop;
+	}
 
 	i = ring->curr & ring_mask;
 	desc = ag71xx_ring_desc(ring, i);
@@ -1563,7 +1572,7 @@ err_drop:
 
 static void ag71xx_oom_timer_handler(struct timer_list *t)
 {
-	struct ag71xx *ag = from_timer(ag, t, oom_timer);
+	struct ag71xx *ag = timer_container_of(ag, t, oom_timer);
 
 	napi_schedule(&ag->napi);
 }
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index c571614b1d50..7efa3fc257b3 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -231,8 +231,8 @@ static u32 atl1c_wait_until_idle(struct atl1c_hw *hw, u32 modu_ctrl)
  */
 static void atl1c_phy_config(struct timer_list *t)
 {
-	struct atl1c_adapter *adapter = from_timer(adapter, t,
-						   phy_config_timer);
+	struct atl1c_adapter *adapter = timer_container_of(adapter, t,
+							   phy_config_timer);
 	struct atl1c_hw *hw = &adapter->hw;
 	unsigned long flags;
 
@@ -357,7 +357,7 @@ static void atl1c_common_task(struct work_struct *work)
 
 static void atl1c_del_timer(struct atl1c_adapter *adapter)
 {
-	del_timer_sync(&adapter->phy_config_timer);
+	timer_delete_sync(&adapter->phy_config_timer);
 }
 
 
@@ -2688,7 +2688,7 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	adapter->mii.mdio_write = atl1c_mdio_write;
 	adapter->mii.phy_id_mask = 0x1f;
 	adapter->mii.reg_num_mask = MDIO_CTRL_REG_MASK;
-	dev_set_threaded(netdev, true);
+	netif_threaded_enable(netdev);
 	for (i = 0; i < adapter->rx_queue_count; ++i)
 		netif_napi_add(netdev, &adapter->rrd_ring[i].napi,
 			       atl1c_clean_rx);
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 9b778b34b67e..40290028580b 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -115,8 +115,8 @@ static inline void atl1e_irq_reset(struct atl1e_adapter *adapter)
  */
 static void atl1e_phy_config(struct timer_list *t)
 {
-	struct atl1e_adapter *adapter = from_timer(adapter, t,
-						   phy_config_timer);
+	struct atl1e_adapter *adapter = timer_container_of(adapter, t,
+							   phy_config_timer);
 	struct atl1e_hw *hw = &adapter->hw;
 	unsigned long flags;
 
@@ -232,7 +232,7 @@ static void atl1e_link_chg_event(struct atl1e_adapter *adapter)
 
 static void atl1e_del_timer(struct atl1e_adapter *adapter)
 {
-	del_timer_sync(&adapter->phy_config_timer);
+	timer_delete_sync(&adapter->phy_config_timer);
 }
 
 static void atl1e_cancel_work(struct atl1e_adapter *adapter)
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 3afd3627ce48..98a4d089270e 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -1861,14 +1861,21 @@ static u16 atl1_alloc_rx_buffers(struct atl1_adapter *adapter)
 			break;
 		}
 
-		buffer_info->alloced = 1;
-		buffer_info->skb = skb;
-		buffer_info->length = (u16) adapter->rx_buffer_len;
 		page = virt_to_page(skb->data);
 		offset = offset_in_page(skb->data);
 		buffer_info->dma = dma_map_page(&pdev->dev, page, offset,
 						adapter->rx_buffer_len,
 						DMA_FROM_DEVICE);
+		if (dma_mapping_error(&pdev->dev, buffer_info->dma)) {
+			kfree_skb(skb);
+			adapter->soft_stats.rx_dropped++;
+			break;
+		}
+
+		buffer_info->alloced = 1;
+		buffer_info->skb = skb;
+		buffer_info->length = (u16)adapter->rx_buffer_len;
+
 		rfd_desc->buffer_addr = cpu_to_le64(buffer_info->dma);
 		rfd_desc->buf_len = cpu_to_le16(adapter->rx_buffer_len);
 		rfd_desc->coalese = 0;
@@ -2183,8 +2190,8 @@ static int atl1_tx_csum(struct atl1_adapter *adapter, struct sk_buff *skb,
 	return 0;
 }
 
-static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
-	struct tx_packet_desc *ptpd)
+static bool atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
+			struct tx_packet_desc *ptpd)
 {
 	struct atl1_tpd_ring *tpd_ring = &adapter->tpd_ring;
 	struct atl1_buffer *buffer_info;
@@ -2194,6 +2201,7 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 	unsigned int nr_frags;
 	unsigned int f;
 	int retval;
+	u16 first_mapped;
 	u16 next_to_use;
 	u16 data_len;
 	u8 hdr_len;
@@ -2201,6 +2209,7 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 	buf_len -= skb->data_len;
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	next_to_use = atomic_read(&tpd_ring->next_to_use);
+	first_mapped = next_to_use;
 	buffer_info = &tpd_ring->buffer_info[next_to_use];
 	BUG_ON(buffer_info->skb);
 	/* put skb in last TPD */
@@ -2216,6 +2225,8 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 		buffer_info->dma = dma_map_page(&adapter->pdev->dev, page,
 						offset, hdr_len,
 						DMA_TO_DEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))
+			goto dma_err;
 
 		if (++next_to_use == tpd_ring->count)
 			next_to_use = 0;
@@ -2242,6 +2253,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 								page, offset,
 								buffer_info->length,
 								DMA_TO_DEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      buffer_info->dma))
+					goto dma_err;
 				if (++next_to_use == tpd_ring->count)
 					next_to_use = 0;
 			}
@@ -2254,6 +2268,8 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 		buffer_info->dma = dma_map_page(&adapter->pdev->dev, page,
 						offset, buf_len,
 						DMA_TO_DEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))
+			goto dma_err;
 		if (++next_to_use == tpd_ring->count)
 			next_to_use = 0;
 	}
@@ -2277,6 +2293,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 			buffer_info->dma = skb_frag_dma_map(&adapter->pdev->dev,
 				frag, i * ATL1_MAX_TX_BUF_LEN,
 				buffer_info->length, DMA_TO_DEVICE);
+			if (dma_mapping_error(&adapter->pdev->dev,
+					      buffer_info->dma))
+				goto dma_err;
 
 			if (++next_to_use == tpd_ring->count)
 				next_to_use = 0;
@@ -2285,6 +2304,22 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 
 	/* last tpd's buffer-info */
 	buffer_info->skb = skb;
+
+	return true;
+
+ dma_err:
+	while (first_mapped != next_to_use) {
+		buffer_info = &tpd_ring->buffer_info[first_mapped];
+		dma_unmap_page(&adapter->pdev->dev,
+			       buffer_info->dma,
+			       buffer_info->length,
+			       DMA_TO_DEVICE);
+		buffer_info->dma = 0;
+
+		if (++first_mapped == tpd_ring->count)
+			first_mapped = 0;
+	}
+	return false;
 }
 
 static void atl1_tx_queue(struct atl1_adapter *adapter, u16 count,
@@ -2355,10 +2390,8 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 
 	len = skb_headlen(skb);
 
-	if (unlikely(skb->len <= 0)) {
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
+	if (unlikely(skb->len <= 0))
+		goto drop_packet;
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	for (f = 0; f < nr_frags; f++) {
@@ -2371,10 +2404,9 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 	if (mss) {
 		if (skb->protocol == htons(ETH_P_IP)) {
 			proto_hdr_len = skb_tcp_all_headers(skb);
-			if (unlikely(proto_hdr_len > len)) {
-				dev_kfree_skb_any(skb);
-				return NETDEV_TX_OK;
-			}
+			if (unlikely(proto_hdr_len > len))
+				goto drop_packet;
+
 			/* need additional TPD ? */
 			if (proto_hdr_len != len)
 				count += (len - proto_hdr_len +
@@ -2406,23 +2438,26 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 	}
 
 	tso = atl1_tso(adapter, skb, ptpd);
-	if (tso < 0) {
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
+	if (tso < 0)
+		goto drop_packet;
 
 	if (!tso) {
 		ret_val = atl1_tx_csum(adapter, skb, ptpd);
-		if (ret_val < 0) {
-			dev_kfree_skb_any(skb);
-			return NETDEV_TX_OK;
-		}
+		if (ret_val < 0)
+			goto drop_packet;
 	}
 
-	atl1_tx_map(adapter, skb, ptpd);
+	if (!atl1_tx_map(adapter, skb, ptpd))
+		goto drop_packet;
+
 	atl1_tx_queue(adapter, count, ptpd);
 	atl1_update_mailbox(adapter);
 	return NETDEV_TX_OK;
+
+drop_packet:
+	adapter->soft_stats.tx_errors++;
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
 }
 
 static int atl1_rings_clean(struct napi_struct *napi, int budget)
@@ -2556,8 +2591,8 @@ static irqreturn_t atl1_intr(int irq, void *data)
  */
 static void atl1_phy_config(struct timer_list *t)
 {
-	struct atl1_adapter *adapter = from_timer(adapter, t,
-						  phy_config_timer);
+	struct atl1_adapter *adapter = timer_container_of(adapter, t,
+							  phy_config_timer);
 	struct atl1_hw *hw = &adapter->hw;
 	unsigned long flags;
 
@@ -2641,7 +2676,7 @@ static void atl1_down(struct atl1_adapter *adapter)
 
 	napi_disable(&adapter->napi);
 	netif_stop_queue(netdev);
-	del_timer_sync(&adapter->phy_config_timer);
+	timer_delete_sync(&adapter->phy_config_timer);
 	adapter->phy_timer_pending = false;
 
 	atlx_irq_disable(adapter);
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index fa9a4919f25d..280e2f5f4aa5 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -752,8 +752,8 @@ static void atl2_down(struct atl2_adapter *adapter)
 
 	atl2_irq_disable(adapter);
 
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_config_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_config_timer);
 	clear_bit(0, &adapter->cfg_phy);
 
 	netif_carrier_off(netdev);
@@ -1010,7 +1010,8 @@ static void atl2_tx_timeout(struct net_device *netdev, unsigned int txqueue)
  */
 static void atl2_watchdog(struct timer_list *t)
 {
-	struct atl2_adapter *adapter = from_timer(adapter, t, watchdog_timer);
+	struct atl2_adapter *adapter = timer_container_of(adapter, t,
+							  watchdog_timer);
 
 	if (!test_bit(__ATL2_DOWN, &adapter->flags)) {
 		u32 drop_rxd, drop_rxs;
@@ -1035,8 +1036,8 @@ static void atl2_watchdog(struct timer_list *t)
  */
 static void atl2_phy_config(struct timer_list *t)
 {
-	struct atl2_adapter *adapter = from_timer(adapter, t,
-						  phy_config_timer);
+	struct atl2_adapter *adapter = timer_container_of(adapter, t,
+							  phy_config_timer);
 	struct atl2_hw *hw = &adapter->hw;
 	unsigned long flags;
 
@@ -1468,8 +1469,8 @@ static void atl2_remove(struct pci_dev *pdev)
 	 * explicitly disable watchdog tasks from being rescheduled  */
 	set_bit(__ATL2_DOWN, &adapter->flags);
 
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_config_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_config_timer);
 	cancel_work_sync(&adapter->reset_task);
 	cancel_work_sync(&adapter->link_chg_task);
 
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index eeec8bf17cf4..666522d64775 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -25,6 +25,7 @@ config B44
 	select SSB
 	select MII
 	select PHYLIB
+	select FIXED_PHY if BCM47XX
 	help
 	  If you have a network (Ethernet) controller of this type, say Y
 	  or M here.
@@ -96,7 +97,6 @@ config BNX2
 config CNIC
 	tristate "QLogic CNIC support"
 	depends on PCI && (IPV6 || IPV6=n)
-	depends on MMU
 	select BNX2
 	select UIO
 	help
@@ -123,6 +123,7 @@ config TIGON3
 	tristate "Broadcom Tigon3 support"
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
+	select CRC32
 	select PHYLIB
 	help
 	  This driver supports Broadcom Tigon3 based gigabit Ethernet cards.
@@ -143,7 +144,7 @@ config BNX2X
 	depends on PTP_1588_CLOCK_OPTIONAL
 	select FW_LOADER
 	select ZLIB_INFLATE
-	select LIBCRC32C
+	select CRC32
 	select MDIO
 	help
 	  This driver supports Broadcom NetXtremeII 10 gigabit Ethernet cards.
@@ -207,7 +208,7 @@ config BNXT
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
 	select FW_LOADER
-	select LIBCRC32C
+	select CRC32
 	select NET_DEVLINK
 	select PAGE_POOL
 	select DIMLIB
@@ -253,6 +254,16 @@ config BNXT_HWMON
 	  Say Y if you want to expose the thermal sensor data on NetXtreme-C/E
 	  devices, via the hwmon sysfs interface.
 
+config BNGE
+	tristate "Broadcom Ethernet device support"
+	depends on PCI
+	select NET_DEVLINK
+	select PAGE_POOL
+	help
+	  This driver supports Broadcom 50/100/200/400/800 gigabit Ethernet cards.
+	  The module will be called bng_en. To compile this driver as a module,
+	  choose M here.
+
 config BCMASP
 	tristate "Broadcom ASP 2.0 Ethernet support"
 	depends on ARCH_BRCMSTB || COMPILE_TEST
diff --git a/drivers/net/ethernet/broadcom/Makefile b/drivers/net/ethernet/broadcom/Makefile
index bac5cb6ad0cd..10cc1c92ecfc 100644
--- a/drivers/net/ethernet/broadcom/Makefile
+++ b/drivers/net/ethernet/broadcom/Makefile
@@ -18,3 +18,4 @@ obj-$(CONFIG_BGMAC_PLATFORM) += bgmac-platform.o
 obj-$(CONFIG_SYSTEMPORT) += bcmsysport.o
 obj-$(CONFIG_BNXT) += bnxt/
 obj-$(CONFIG_BCMASP) += asp2/
+obj-$(CONFIG_BNGE) += bnge/
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index a68fab1b05f0..fd35f4b4dc50 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -141,7 +141,7 @@ void bcmasp_flush_rx_port(struct bcmasp_intf *intf)
 		return;
 	}
 
-	rx_ctrl_core_wl(priv, mask, priv->hw_info->rx_ctrl_flush);
+	rx_ctrl_core_wl(priv, mask, ASP_RX_CTRL_FLUSH);
 }
 
 static void bcmasp_netfilt_hw_en_wake(struct bcmasp_priv *priv,
@@ -518,7 +518,7 @@ void bcmasp_netfilt_suspend(struct bcmasp_intf *intf)
 	int ret, i;
 
 	/* Write all filters to HW */
-	for (i = 0; i < NUM_NET_FILTERS; i++) {
+	for (i = 0; i < priv->num_net_filters; i++) {
 		/* If the filter does not match the port, skip programming. */
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
@@ -551,7 +551,7 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
 	struct bcmasp_priv *priv = intf->parent;
 	int j = 0, i;
 
-	for (i = 0; i < NUM_NET_FILTERS; i++) {
+	for (i = 0; i < priv->num_net_filters; i++) {
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
 			continue;
@@ -577,7 +577,7 @@ int bcmasp_netfilt_get_active(struct bcmasp_intf *intf)
 	struct bcmasp_priv *priv = intf->parent;
 	int cnt = 0, i;
 
-	for (i = 0; i < NUM_NET_FILTERS; i++) {
+	for (i = 0; i < priv->num_net_filters; i++) {
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
 			continue;
@@ -602,7 +602,7 @@ bool bcmasp_netfilt_check_dup(struct bcmasp_intf *intf,
 	size_t fs_size = 0;
 	int i;
 
-	for (i = 0; i < NUM_NET_FILTERS; i++) {
+	for (i = 0; i < priv->num_net_filters; i++) {
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
 			continue;
@@ -670,7 +670,7 @@ struct bcmasp_net_filter *bcmasp_netfilt_get_init(struct bcmasp_intf *intf,
 	int i, open_index = -1;
 
 	/* Check whether we exceed the filter table capacity */
-	if (loc != RX_CLS_LOC_ANY && loc >= NUM_NET_FILTERS)
+	if (loc != RX_CLS_LOC_ANY && loc >= priv->num_net_filters)
 		return ERR_PTR(-EINVAL);
 
 	/* If the filter location is busy (already claimed) and we are initializing
@@ -686,7 +686,7 @@ struct bcmasp_net_filter *bcmasp_netfilt_get_init(struct bcmasp_intf *intf,
 	/* Initialize the loop index based on the desired location or from 0 */
 	i = loc == RX_CLS_LOC_ANY ? 0 : loc;
 
-	for ( ; i < NUM_NET_FILTERS; i++) {
+	for ( ; i < priv->num_net_filters; i++) {
 		/* Found matching network filter */
 		if (!init &&
 		    priv->net_filters[i].claimed &&
@@ -779,7 +779,7 @@ static void bcmasp_en_mda_filter(struct bcmasp_intf *intf, bool en,
 	priv->mda_filters[i].en = en;
 	priv->mda_filters[i].port = intf->port;
 
-	rx_filter_core_wl(priv, ((intf->channel + 8) |
+	rx_filter_core_wl(priv, ((intf->channel + priv->tx_chan_offset) |
 			  (en << ASP_RX_FILTER_MDA_CFG_EN_SHIFT) |
 			  ASP_RX_FILTER_MDA_CFG_UMC_SEL(intf->port)),
 			  ASP_RX_FILTER_MDA_CFG(i));
@@ -865,7 +865,7 @@ void bcmasp_disable_all_filters(struct bcmasp_intf *intf)
 	res_count = bcmasp_total_res_mda_cnt(intf->parent);
 
 	/* Disable all filters held by this port */
-	for (i = res_count; i < NUM_MDA_FILTERS; i++) {
+	for (i = res_count; i < priv->num_mda_filters; i++) {
 		if (priv->mda_filters[i].en &&
 		    priv->mda_filters[i].port == intf->port)
 			bcmasp_en_mda_filter(intf, 0, i);
@@ -909,7 +909,7 @@ int bcmasp_set_en_mda_filter(struct bcmasp_intf *intf, unsigned char *addr,
 
 	res_count = bcmasp_total_res_mda_cnt(intf->parent);
 
-	for (i = res_count; i < NUM_MDA_FILTERS; i++) {
+	for (i = res_count; i < priv->num_mda_filters; i++) {
 		/* If filter not enabled or belongs to another port skip */
 		if (!priv->mda_filters[i].en ||
 		    priv->mda_filters[i].port != intf->port)
@@ -924,7 +924,7 @@ int bcmasp_set_en_mda_filter(struct bcmasp_intf *intf, unsigned char *addr,
 	}
 
 	/* Create new filter if possible */
-	for (i = res_count; i < NUM_MDA_FILTERS; i++) {
+	for (i = res_count; i < priv->num_mda_filters; i++) {
 		if (priv->mda_filters[i].en)
 			continue;
 
@@ -944,12 +944,12 @@ static void bcmasp_core_init_filters(struct bcmasp_priv *priv)
 	/* Disable all filters and reset software view since the HW
 	 * can lose context while in deep sleep suspend states
 	 */
-	for (i = 0; i < NUM_MDA_FILTERS; i++) {
+	for (i = 0; i < priv->num_mda_filters; i++) {
 		rx_filter_core_wl(priv, 0x0, ASP_RX_FILTER_MDA_CFG(i));
 		priv->mda_filters[i].en = 0;
 	}
 
-	for (i = 0; i < NUM_NET_FILTERS; i++)
+	for (i = 0; i < priv->num_net_filters; i++)
 		rx_filter_core_wl(priv, 0x0, ASP_RX_FILTER_NET_CFG(i));
 
 	/* Top level filter enable bit should be enabled at all times, set
@@ -966,18 +966,8 @@ static void bcmasp_core_init_filters(struct bcmasp_priv *priv)
 /* ASP core initialization */
 static void bcmasp_core_init(struct bcmasp_priv *priv)
 {
-	tx_analytics_core_wl(priv, 0x0, ASP_TX_ANALYTICS_CTRL);
-	rx_analytics_core_wl(priv, 0x4, ASP_RX_ANALYTICS_CTRL);
-
-	rx_edpkt_core_wl(priv, (ASP_EDPKT_HDR_SZ_128 << ASP_EDPKT_HDR_SZ_SHIFT),
-			 ASP_EDPKT_HDR_CFG);
-	rx_edpkt_core_wl(priv,
-			 (ASP_EDPKT_ENDI_BT_SWP_WD << ASP_EDPKT_ENDI_DESC_SHIFT),
-			 ASP_EDPKT_ENDI);
-
 	rx_edpkt_core_wl(priv, 0x1b, ASP_EDPKT_BURST_BUF_PSCAL_TOUT);
 	rx_edpkt_core_wl(priv, 0x3e8, ASP_EDPKT_BURST_BUF_WRITE_TOUT);
-	rx_edpkt_core_wl(priv, 0x3e8, ASP_EDPKT_BURST_BUF_READ_TOUT);
 
 	rx_edpkt_core_wl(priv, ASP_EDPKT_ENABLE_EN, ASP_EDPKT_ENABLE);
 
@@ -1020,6 +1010,18 @@ static void bcmasp_core_clock_select_one(struct bcmasp_priv *priv, bool slow)
 	ctrl_core_wl(priv, reg, ASP_CTRL_CORE_CLOCK_SELECT);
 }
 
+static void bcmasp_core_clock_select_one_ctrl2(struct bcmasp_priv *priv, bool slow)
+{
+	u32 reg;
+
+	reg = ctrl2_core_rl(priv, ASP_CTRL2_CORE_CLOCK_SELECT);
+	if (slow)
+		reg &= ~ASP_CTRL2_CORE_CLOCK_SELECT_MAIN;
+	else
+		reg |= ASP_CTRL2_CORE_CLOCK_SELECT_MAIN;
+	ctrl2_core_wl(priv, reg, ASP_CTRL2_CORE_CLOCK_SELECT);
+}
+
 static void bcmasp_core_clock_set_ll(struct bcmasp_priv *priv, u32 clr, u32 set)
 {
 	u32 reg;
@@ -1108,7 +1110,7 @@ static int bcmasp_get_and_request_irq(struct bcmasp_priv *priv, int i)
 	return irq;
 }
 
-static void bcmasp_init_wol_shared(struct bcmasp_priv *priv)
+static void bcmasp_init_wol(struct bcmasp_priv *priv)
 {
 	struct platform_device *pdev = priv->pdev;
 	struct device *dev = &pdev->dev;
@@ -1125,7 +1127,7 @@ static void bcmasp_init_wol_shared(struct bcmasp_priv *priv)
 	device_set_wakeup_capable(&pdev->dev, 1);
 }
 
-static void bcmasp_enable_wol_shared(struct bcmasp_intf *intf, bool en)
+void bcmasp_enable_wol(struct bcmasp_intf *intf, bool en)
 {
 	struct bcmasp_priv *priv = intf->parent;
 	struct device *dev = &priv->pdev->dev;
@@ -1154,54 +1156,12 @@ static void bcmasp_enable_wol_shared(struct bcmasp_intf *intf, bool en)
 	}
 }
 
-static void bcmasp_wol_irq_destroy_shared(struct bcmasp_priv *priv)
+static void bcmasp_wol_irq_destroy(struct bcmasp_priv *priv)
 {
 	if (priv->wol_irq > 0)
 		free_irq(priv->wol_irq, priv);
 }
 
-static void bcmasp_init_wol_per_intf(struct bcmasp_priv *priv)
-{
-	struct platform_device *pdev = priv->pdev;
-	struct device *dev = &pdev->dev;
-	struct bcmasp_intf *intf;
-	int irq;
-
-	list_for_each_entry(intf, &priv->intfs, list) {
-		irq = bcmasp_get_and_request_irq(priv, intf->port + 1);
-		if (irq < 0) {
-			dev_warn(dev, "Failed to init WoL irq(port %d): %d\n",
-				 intf->port, irq);
-			continue;
-		}
-
-		intf->wol_irq = irq;
-		intf->wol_irq_enabled = false;
-		device_set_wakeup_capable(&pdev->dev, 1);
-	}
-}
-
-static void bcmasp_enable_wol_per_intf(struct bcmasp_intf *intf, bool en)
-{
-	struct device *dev = &intf->parent->pdev->dev;
-
-	if (en ^ intf->wol_irq_enabled)
-		irq_set_irq_wake(intf->wol_irq, en);
-
-	intf->wol_irq_enabled = en;
-	device_set_wakeup_enable(dev, en);
-}
-
-static void bcmasp_wol_irq_destroy_per_intf(struct bcmasp_priv *priv)
-{
-	struct bcmasp_intf *intf;
-
-	list_for_each_entry(intf, &priv->intfs, list) {
-		if (intf->wol_irq > 0)
-			free_irq(intf->wol_irq, priv);
-	}
-}
-
 static void bcmasp_eee_fixup(struct bcmasp_intf *intf, bool en)
 {
 	u32 reg, phy_lpi_overwrite;
@@ -1220,70 +1180,53 @@ static void bcmasp_eee_fixup(struct bcmasp_intf *intf, bool en)
 	usleep_range(50, 100);
 }
 
-static struct bcmasp_hw_info v20_hw_info = {
-	.rx_ctrl_flush = ASP_RX_CTRL_FLUSH,
-	.umac2fb = UMAC2FB_OFFSET,
-	.rx_ctrl_fb_out_frame_count = ASP_RX_CTRL_FB_OUT_FRAME_COUNT,
-	.rx_ctrl_fb_filt_out_frame_count = ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT,
-	.rx_ctrl_fb_rx_fifo_depth = ASP_RX_CTRL_FB_RX_FIFO_DEPTH,
-};
-
-static const struct bcmasp_plat_data v20_plat_data = {
-	.init_wol = bcmasp_init_wol_per_intf,
-	.enable_wol = bcmasp_enable_wol_per_intf,
-	.destroy_wol = bcmasp_wol_irq_destroy_per_intf,
-	.core_clock_select = bcmasp_core_clock_select_one,
-	.hw_info = &v20_hw_info,
-};
-
-static struct bcmasp_hw_info v21_hw_info = {
-	.rx_ctrl_flush = ASP_RX_CTRL_FLUSH_2_1,
-	.umac2fb = UMAC2FB_OFFSET_2_1,
-	.rx_ctrl_fb_out_frame_count = ASP_RX_CTRL_FB_OUT_FRAME_COUNT_2_1,
-	.rx_ctrl_fb_filt_out_frame_count =
-		ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT_2_1,
-	.rx_ctrl_fb_rx_fifo_depth = ASP_RX_CTRL_FB_RX_FIFO_DEPTH_2_1,
-};
-
 static const struct bcmasp_plat_data v21_plat_data = {
-	.init_wol = bcmasp_init_wol_shared,
-	.enable_wol = bcmasp_enable_wol_shared,
-	.destroy_wol = bcmasp_wol_irq_destroy_shared,
 	.core_clock_select = bcmasp_core_clock_select_one,
-	.hw_info = &v21_hw_info,
+	.num_mda_filters = 32,
+	.num_net_filters = 32,
+	.tx_chan_offset = 8,
+	.rx_ctrl_offset = 0x0,
 };
 
 static const struct bcmasp_plat_data v22_plat_data = {
-	.init_wol = bcmasp_init_wol_shared,
-	.enable_wol = bcmasp_enable_wol_shared,
-	.destroy_wol = bcmasp_wol_irq_destroy_shared,
 	.core_clock_select = bcmasp_core_clock_select_many,
-	.hw_info = &v21_hw_info,
 	.eee_fixup = bcmasp_eee_fixup,
+	.num_mda_filters = 32,
+	.num_net_filters = 32,
+	.tx_chan_offset = 8,
+	.rx_ctrl_offset = 0x0,
+};
+
+static const struct bcmasp_plat_data v30_plat_data = {
+	.core_clock_select = bcmasp_core_clock_select_one_ctrl2,
+	.num_mda_filters = 20,
+	.num_net_filters = 16,
+	.tx_chan_offset = 0,
+	.rx_ctrl_offset = 0x10000,
 };
 
 static void bcmasp_set_pdata(struct bcmasp_priv *priv, const struct bcmasp_plat_data *pdata)
 {
-	priv->init_wol = pdata->init_wol;
-	priv->enable_wol = pdata->enable_wol;
-	priv->destroy_wol = pdata->destroy_wol;
 	priv->core_clock_select = pdata->core_clock_select;
 	priv->eee_fixup = pdata->eee_fixup;
-	priv->hw_info = pdata->hw_info;
+	priv->num_mda_filters = pdata->num_mda_filters;
+	priv->num_net_filters = pdata->num_net_filters;
+	priv->tx_chan_offset = pdata->tx_chan_offset;
+	priv->rx_ctrl_offset = pdata->rx_ctrl_offset;
 }
 
 static const struct of_device_id bcmasp_of_match[] = {
-	{ .compatible = "brcm,asp-v2.0", .data = &v20_plat_data },
 	{ .compatible = "brcm,asp-v2.1", .data = &v21_plat_data },
 	{ .compatible = "brcm,asp-v2.2", .data = &v22_plat_data },
+	{ .compatible = "brcm,asp-v3.0", .data = &v30_plat_data },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, bcmasp_of_match);
 
 static const struct of_device_id bcmasp_mdio_of_match[] = {
-	{ .compatible = "brcm,asp-v2.2-mdio", },
 	{ .compatible = "brcm,asp-v2.1-mdio", },
-	{ .compatible = "brcm,asp-v2.0-mdio", },
+	{ .compatible = "brcm,asp-v2.2-mdio", },
+	{ .compatible = "brcm,asp-v3.0-mdio", },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, bcmasp_mdio_of_match);
@@ -1365,6 +1308,17 @@ static int bcmasp_probe(struct platform_device *pdev)
 	 * how many interfaces come up.
 	 */
 	bcmasp_core_init(priv);
+
+	priv->mda_filters = devm_kcalloc(dev, priv->num_mda_filters,
+					 sizeof(*priv->mda_filters), GFP_KERNEL);
+	if (!priv->mda_filters)
+		return -ENOMEM;
+
+	priv->net_filters = devm_kcalloc(dev, priv->num_net_filters,
+					 sizeof(*priv->net_filters), GFP_KERNEL);
+	if (!priv->net_filters)
+		return -ENOMEM;
+
 	bcmasp_core_init_filters(priv);
 
 	ports_node = of_find_node_by_name(dev->of_node, "ethernet-ports");
@@ -1387,7 +1341,7 @@ static int bcmasp_probe(struct platform_device *pdev)
 	}
 
 	/* Check and enable WoL */
-	priv->init_wol(priv);
+	bcmasp_init_wol(priv);
 
 	/* Drop the clock reference count now and let ndo_open()/ndo_close()
 	 * manage it for us from now on.
@@ -1404,7 +1358,7 @@ static int bcmasp_probe(struct platform_device *pdev)
 		if (ret) {
 			netdev_err(intf->ndev,
 				   "failed to register net_device: %d\n", ret);
-			priv->destroy_wol(priv);
+			bcmasp_wol_irq_destroy(priv);
 			bcmasp_remove_intfs(priv);
 			goto of_put_exit;
 		}
@@ -1425,7 +1379,7 @@ static void bcmasp_remove(struct platform_device *pdev)
 	if (!priv)
 		return;
 
-	priv->destroy_wol(priv);
+	bcmasp_wol_irq_destroy(priv);
 	bcmasp_remove_intfs(priv);
 }
 
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
index f93cb3da44b0..74adfdb50e11 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
@@ -53,22 +53,15 @@
 #define ASP_RX_CTRL_FB_0_FRAME_COUNT		0x14
 #define ASP_RX_CTRL_FB_1_FRAME_COUNT		0x18
 #define ASP_RX_CTRL_FB_8_FRAME_COUNT		0x1c
-/* asp2.1 diverges offsets here */
-/* ASP2.0 */
-#define ASP_RX_CTRL_FB_OUT_FRAME_COUNT		0x20
-#define ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT	0x24
-#define ASP_RX_CTRL_FLUSH			0x28
-#define  ASP_CTRL_UMAC0_FLUSH_MASK		(BIT(0) | BIT(12))
-#define  ASP_CTRL_UMAC1_FLUSH_MASK		(BIT(1) | BIT(13))
-#define  ASP_CTRL_SPB_FLUSH_MASK		(BIT(8) | BIT(20))
-#define ASP_RX_CTRL_FB_RX_FIFO_DEPTH		0x30
-/* ASP2.1 */
-#define ASP_RX_CTRL_FB_9_FRAME_COUNT_2_1	0x20
-#define ASP_RX_CTRL_FB_10_FRAME_COUNT_2_1	0x24
-#define ASP_RX_CTRL_FB_OUT_FRAME_COUNT_2_1	0x28
-#define ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT_2_1	0x2c
-#define ASP_RX_CTRL_FLUSH_2_1			0x30
-#define ASP_RX_CTRL_FB_RX_FIFO_DEPTH_2_1	0x38
+#define ASP_RX_CTRL_FB_9_FRAME_COUNT		0x20
+#define ASP_RX_CTRL_FB_10_FRAME_COUNT		0x24
+#define ASP_RX_CTRL_FB_OUT_FRAME_COUNT		0x28
+#define ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT	0x2c
+#define ASP_RX_CTRL_FLUSH			0x30
+#define  ASP_CTRL_UMAC0_FLUSH_MASK             (BIT(0) | BIT(12))
+#define  ASP_CTRL_UMAC1_FLUSH_MASK             (BIT(1) | BIT(13))
+#define  ASP_CTRL_SPB_FLUSH_MASK               (BIT(8) | BIT(20))
+#define ASP_RX_CTRL_FB_RX_FIFO_DEPTH		0x38
 
 #define ASP_RX_FILTER_OFFSET			0x80000
 #define  ASP_RX_FILTER_BLK_CTRL			0x0
@@ -345,11 +338,6 @@ struct bcmasp_intf {
 
 	u32				wolopts;
 	u8				sopass[SOPASS_MAX];
-	/* Used if per intf wol irq */
-	int				wol_irq;
-	unsigned int			wol_irq_enabled:1;
-
-	struct ethtool_keee		eee;
 };
 
 #define NUM_NET_FILTERS				32
@@ -372,21 +360,13 @@ struct bcmasp_mda_filter {
 	u8		mask[ETH_ALEN];
 };
 
-struct bcmasp_hw_info {
-	u32		rx_ctrl_flush;
-	u32		umac2fb;
-	u32		rx_ctrl_fb_out_frame_count;
-	u32		rx_ctrl_fb_filt_out_frame_count;
-	u32		rx_ctrl_fb_rx_fifo_depth;
-};
-
 struct bcmasp_plat_data {
-	void (*init_wol)(struct bcmasp_priv *priv);
-	void (*enable_wol)(struct bcmasp_intf *intf, bool en);
-	void (*destroy_wol)(struct bcmasp_priv *priv);
 	void (*core_clock_select)(struct bcmasp_priv *priv, bool slow);
 	void (*eee_fixup)(struct bcmasp_intf *priv, bool en);
-	struct bcmasp_hw_info		*hw_info;
+	unsigned int num_mda_filters;
+	unsigned int num_net_filters;
+	unsigned int tx_chan_offset;
+	unsigned int rx_ctrl_offset;
 };
 
 struct bcmasp_priv {
@@ -401,18 +381,18 @@ struct bcmasp_priv {
 	int				wol_irq;
 	unsigned long			wol_irq_enabled_mask;
 
-	void (*init_wol)(struct bcmasp_priv *priv);
-	void (*enable_wol)(struct bcmasp_intf *intf, bool en);
-	void (*destroy_wol)(struct bcmasp_priv *priv);
 	void (*core_clock_select)(struct bcmasp_priv *priv, bool slow);
 	void (*eee_fixup)(struct bcmasp_intf *intf, bool en);
+	unsigned int			num_mda_filters;
+	unsigned int			num_net_filters;
+	unsigned int			tx_chan_offset;
+	unsigned int			rx_ctrl_offset;
 
 	void __iomem			*base;
-	struct	bcmasp_hw_info		*hw_info;
 
 	struct list_head		intfs;
 
-	struct bcmasp_mda_filter	mda_filters[NUM_MDA_FILTERS];
+	struct bcmasp_mda_filter	*mda_filters;
 
 	/* MAC destination address filters lock */
 	spinlock_t			mda_lock;
@@ -420,7 +400,7 @@ struct bcmasp_priv {
 	/* Protects accesses to ASP_CTRL_CLOCK_CTRL */
 	spinlock_t			clk_lock;
 
-	struct bcmasp_net_filter	net_filters[NUM_NET_FILTERS];
+	struct bcmasp_net_filter	*net_filters;
 
 	/* Network filter lock */
 	struct mutex			net_lock;
@@ -510,8 +490,8 @@ BCMASP_FP_IO_MACRO_Q(rx_edpkt_cfg);
 #define  PKT_OFFLOAD_EPKT_IP(x)		((x) << 21)
 #define  PKT_OFFLOAD_EPKT_TP(x)		((x) << 19)
 #define  PKT_OFFLOAD_EPKT_LEN(x)	((x) << 16)
-#define  PKT_OFFLOAD_EPKT_CSUM_L3	BIT(15)
-#define  PKT_OFFLOAD_EPKT_CSUM_L2	BIT(14)
+#define  PKT_OFFLOAD_EPKT_CSUM_L4	BIT(15)
+#define  PKT_OFFLOAD_EPKT_CSUM_L3	BIT(14)
 #define  PKT_OFFLOAD_EPKT_ID(x)		((x) << 12)
 #define  PKT_OFFLOAD_EPKT_SEQ(x)	((x) << 10)
 #define  PKT_OFFLOAD_EPKT_TS(x)		((x) << 8)
@@ -543,12 +523,27 @@ BCMASP_CORE_IO_MACRO(intr2, ASP_INTR2_OFFSET);
 BCMASP_CORE_IO_MACRO(wakeup_intr2, ASP_WAKEUP_INTR2_OFFSET);
 BCMASP_CORE_IO_MACRO(tx_analytics, ASP_TX_ANALYTICS_OFFSET);
 BCMASP_CORE_IO_MACRO(rx_analytics, ASP_RX_ANALYTICS_OFFSET);
-BCMASP_CORE_IO_MACRO(rx_ctrl, ASP_RX_CTRL_OFFSET);
 BCMASP_CORE_IO_MACRO(rx_filter, ASP_RX_FILTER_OFFSET);
 BCMASP_CORE_IO_MACRO(rx_edpkt, ASP_EDPKT_OFFSET);
 BCMASP_CORE_IO_MACRO(ctrl, ASP_CTRL_OFFSET);
 BCMASP_CORE_IO_MACRO(ctrl2, ASP_CTRL2_OFFSET);
 
+#define BCMASP_CORE_IO_MACRO_OFFSET(name, offset)			\
+static inline u32 name##_core_rl(struct bcmasp_priv *priv,		\
+				 u32 off)				\
+{									\
+	u32 reg = readl_relaxed(priv->base + priv->name##_offset +	\
+				(offset) + off);			\
+	return reg;							\
+}									\
+static inline void name##_core_wl(struct bcmasp_priv *priv,		\
+				  u32 val, u32 off)			\
+{									\
+	writel_relaxed(val, priv->base + priv->name##_offset +		\
+		       (offset) + off);					\
+}
+BCMASP_CORE_IO_MACRO_OFFSET(rx_ctrl, ASP_RX_CTRL_OFFSET);
+
 struct bcmasp_intf *bcmasp_interface_create(struct bcmasp_priv *priv,
 					    struct device_node *ndev_dn, int i);
 
@@ -601,5 +596,5 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
 
 void bcmasp_netfilt_suspend(struct bcmasp_intf *intf);
 
-void bcmasp_eee_enable_set(struct bcmasp_intf *intf, bool enable);
+void bcmasp_enable_wol(struct bcmasp_intf *intf, bool en);
 #endif
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
index 9da5ae29a105..dd80ccfca19d 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
@@ -10,7 +10,6 @@
 #include "bcmasp_intf_defs.h"
 
 enum bcmasp_stat_type {
-	BCMASP_STAT_RX_EDPKT,
 	BCMASP_STAT_RX_CTRL,
 	BCMASP_STAT_RX_CTRL_PER_INTF,
 	BCMASP_STAT_SOFT,
@@ -33,8 +32,6 @@ struct bcmasp_stats {
 	.reg_offset = offset, \
 }
 
-#define STAT_BCMASP_RX_EDPKT(str, offset) \
-	STAT_BCMASP_OFFSET(str, BCMASP_STAT_RX_EDPKT, offset)
 #define STAT_BCMASP_RX_CTRL(str, offset) \
 	STAT_BCMASP_OFFSET(str, BCMASP_STAT_RX_CTRL, offset)
 #define STAT_BCMASP_RX_CTRL_PER_INTF(str, offset) \
@@ -42,11 +39,6 @@ struct bcmasp_stats {
 
 /* Must match the order of struct bcmasp_mib_counters */
 static const struct bcmasp_stats bcmasp_gstrings_stats[] = {
-	/* EDPKT counters */
-	STAT_BCMASP_RX_EDPKT("RX Time Stamp", ASP_EDPKT_RX_TS_COUNTER),
-	STAT_BCMASP_RX_EDPKT("RX PKT Count", ASP_EDPKT_RX_PKT_CNT),
-	STAT_BCMASP_RX_EDPKT("RX PKT Buffered", ASP_EDPKT_HDR_EXTR_CNT),
-	STAT_BCMASP_RX_EDPKT("RX PKT Pushed to DRAM", ASP_EDPKT_HDR_OUT_CNT),
 	/* ASP RX control */
 	STAT_BCMASP_RX_CTRL_PER_INTF("Frames From Unimac",
 				     ASP_RX_CTRL_UMAC_0_FRAME_COUNT),
@@ -71,23 +63,6 @@ static const struct bcmasp_stats bcmasp_gstrings_stats[] = {
 
 #define BCMASP_STATS_LEN	ARRAY_SIZE(bcmasp_gstrings_stats)
 
-static u16 bcmasp_stat_fixup_offset(struct bcmasp_intf *intf,
-				    const struct bcmasp_stats *s)
-{
-	struct bcmasp_priv *priv = intf->parent;
-
-	if (!strcmp("Frames Out(Buffer)", s->stat_string))
-		return priv->hw_info->rx_ctrl_fb_out_frame_count;
-
-	if (!strcmp("Frames Out(Filters)", s->stat_string))
-		return priv->hw_info->rx_ctrl_fb_filt_out_frame_count;
-
-	if (!strcmp("RX Buffer FIFO Depth", s->stat_string))
-		return priv->hw_info->rx_ctrl_fb_rx_fifo_depth;
-
-	return s->reg_offset;
-}
-
 static int bcmasp_get_sset_count(struct net_device *dev, int string_set)
 {
 	switch (string_set) {
@@ -126,13 +101,10 @@ static void bcmasp_update_mib_counters(struct bcmasp_intf *intf)
 		char *p;
 
 		s = &bcmasp_gstrings_stats[i];
-		offset = bcmasp_stat_fixup_offset(intf, s);
+		offset = s->reg_offset;
 		switch (s->type) {
 		case BCMASP_STAT_SOFT:
 			continue;
-		case BCMASP_STAT_RX_EDPKT:
-			val = rx_edpkt_core_rl(intf->parent, offset);
-			break;
 		case BCMASP_STAT_RX_CTRL:
 			val = rx_ctrl_core_rl(intf->parent, offset);
 			break;
@@ -191,11 +163,30 @@ static void bcmasp_set_msglevel(struct net_device *dev, u32 level)
 static void bcmasp_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct bcmasp_intf *intf = netdev_priv(dev);
+	struct bcmasp_priv *priv = intf->parent;
+	struct device *kdev = &priv->pdev->dev;
+	u32 phy_wolopts = 0;
+
+	if (dev->phydev) {
+		phy_ethtool_get_wol(dev->phydev, wol);
+		phy_wolopts = wol->wolopts;
+	}
+
+	/* MAC is not wake-up capable, return what the PHY does */
+	if (!device_can_wakeup(kdev))
+		return;
+
+	/* Overlay MAC capabilities with that of the PHY queried before */
+	wol->supported |= BCMASP_SUPPORTED_WAKE;
+	wol->wolopts |= intf->wolopts;
+
+	/* Return the PHY configured magic password */
+	if (phy_wolopts & WAKE_MAGICSECURE)
+		return;
 
-	wol->supported = BCMASP_SUPPORTED_WAKE;
-	wol->wolopts = intf->wolopts;
 	memset(wol->sopass, 0, sizeof(wol->sopass));
 
+	/* Otherwise the MAC one */
 	if (wol->wolopts & WAKE_MAGICSECURE)
 		memcpy(wol->sopass, intf->sopass, sizeof(intf->sopass));
 }
@@ -205,17 +196,28 @@ static int bcmasp_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	struct bcmasp_intf *intf = netdev_priv(dev);
 	struct bcmasp_priv *priv = intf->parent;
 	struct device *kdev = &priv->pdev->dev;
+	int ret = 0;
+
+	/* Try Wake-on-LAN from the PHY first */
+	if (dev->phydev) {
+		ret = phy_ethtool_set_wol(dev->phydev, wol);
+		if (ret != -EOPNOTSUPP && wol->wolopts)
+			return ret;
+	}
 
 	if (!device_can_wakeup(kdev))
 		return -EOPNOTSUPP;
 
+	if (wol->wolopts & ~BCMASP_SUPPORTED_WAKE)
+		return -EINVAL;
+
 	/* Interface Specific */
 	intf->wolopts = wol->wolopts;
 	if (intf->wolopts & WAKE_MAGICSECURE)
 		memcpy(intf->sopass, wol->sopass, sizeof(wol->sopass));
 
 	mutex_lock(&priv->wol_lock);
-	priv->enable_wol(intf, !!intf->wolopts);
+	bcmasp_enable_wol(intf, !!intf->wolopts);
 	mutex_unlock(&priv->wol_lock);
 
 	return 0;
@@ -289,7 +291,7 @@ static int bcmasp_flow_get(struct bcmasp_intf *intf, struct ethtool_rxnfc *cmd)
 
 	memcpy(&cmd->fs, &nfilter->fs, sizeof(nfilter->fs));
 
-	cmd->data = NUM_NET_FILTERS;
+	cmd->data = intf->parent->num_net_filters;
 
 	return 0;
 }
@@ -336,7 +338,7 @@ static int bcmasp_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 		break;
 	case ETHTOOL_GRXCLSRLALL:
 		err = bcmasp_netfilt_get_all_active(intf, rule_locs, &cmd->rule_cnt);
-		cmd->data = NUM_NET_FILTERS;
+		cmd->data = intf->parent->num_net_filters;
 		break;
 	default:
 		err = -EOPNOTSUPP;
@@ -348,58 +350,19 @@ static int bcmasp_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	return err;
 }
 
-void bcmasp_eee_enable_set(struct bcmasp_intf *intf, bool enable)
-{
-	u32 reg;
-
-	reg = umac_rl(intf, UMC_EEE_CTRL);
-	if (enable)
-		reg |= EEE_EN;
-	else
-		reg &= ~EEE_EN;
-	umac_wl(intf, reg, UMC_EEE_CTRL);
-
-	intf->eee.eee_enabled = enable;
-}
-
 static int bcmasp_get_eee(struct net_device *dev, struct ethtool_keee *e)
 {
-	struct bcmasp_intf *intf = netdev_priv(dev);
-	struct ethtool_keee *p = &intf->eee;
-
 	if (!dev->phydev)
 		return -ENODEV;
 
-	e->tx_lpi_enabled = p->tx_lpi_enabled;
-	e->tx_lpi_timer = umac_rl(intf, UMC_EEE_LPI_TIMER);
-
 	return phy_ethtool_get_eee(dev->phydev, e);
 }
 
 static int bcmasp_set_eee(struct net_device *dev, struct ethtool_keee *e)
 {
-	struct bcmasp_intf *intf = netdev_priv(dev);
-	struct ethtool_keee *p = &intf->eee;
-	int ret;
-
 	if (!dev->phydev)
 		return -ENODEV;
 
-	if (!p->eee_enabled) {
-		bcmasp_eee_enable_set(intf, false);
-	} else {
-		ret = phy_init_eee(dev->phydev, 0);
-		if (ret) {
-			netif_err(intf, hw, dev,
-				  "EEE initialization failed: %d\n", ret);
-			return ret;
-		}
-
-		umac_wl(intf, e->tx_lpi_timer, UMC_EEE_LPI_TIMER);
-		intf->eee.tx_lpi_enabled = e->tx_lpi_enabled;
-		bcmasp_eee_enable_set(intf, true);
-	}
-
 	return phy_ethtool_set_eee(dev->phydev, e);
 }
 
@@ -497,4 +460,5 @@ const struct ethtool_ops bcmasp_ethtool_ops = {
 	.get_ethtool_stats	= bcmasp_get_ethtool_stats,
 	.get_sset_count		= bcmasp_get_sset_count,
 	.get_ts_info		= ethtool_op_get_ts_info,
+	.nway_reset		= phy_ethtool_nway_reset,
 };
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
index cfd50efbdbc0..b9973956c480 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -180,14 +180,14 @@ static struct sk_buff *bcmasp_csum_offload(struct net_device *dev,
 	case htons(ETH_P_IP):
 		header |= PKT_OFFLOAD_HDR_SIZE_2((ip_hdrlen(skb) >> 8) & 0xf);
 		header2 |= PKT_OFFLOAD_HDR2_SIZE_2(ip_hdrlen(skb) & 0xff);
-		epkt |= PKT_OFFLOAD_EPKT_IP(0) | PKT_OFFLOAD_EPKT_CSUM_L2;
+		epkt |= PKT_OFFLOAD_EPKT_IP(0);
 		ip_proto = ip_hdr(skb)->protocol;
 		header_cnt += 2;
 		break;
 	case htons(ETH_P_IPV6):
 		header |= PKT_OFFLOAD_HDR_SIZE_2((IP6_HLEN >> 8) & 0xf);
 		header2 |= PKT_OFFLOAD_HDR2_SIZE_2(IP6_HLEN & 0xff);
-		epkt |= PKT_OFFLOAD_EPKT_IP(1) | PKT_OFFLOAD_EPKT_CSUM_L2;
+		epkt |= PKT_OFFLOAD_EPKT_IP(1);
 		ip_proto = ipv6_hdr(skb)->nexthdr;
 		header_cnt += 2;
 		break;
@@ -198,12 +198,12 @@ static struct sk_buff *bcmasp_csum_offload(struct net_device *dev,
 	switch (ip_proto) {
 	case IPPROTO_TCP:
 		header2 |= PKT_OFFLOAD_HDR2_SIZE_3(tcp_hdrlen(skb));
-		epkt |= PKT_OFFLOAD_EPKT_TP(0) | PKT_OFFLOAD_EPKT_CSUM_L3;
+		epkt |= PKT_OFFLOAD_EPKT_TP(0) | PKT_OFFLOAD_EPKT_CSUM_L4;
 		header_cnt++;
 		break;
 	case IPPROTO_UDP:
 		header2 |= PKT_OFFLOAD_HDR2_SIZE_3(UDP_HLEN);
-		epkt |= PKT_OFFLOAD_EPKT_TP(1) | PKT_OFFLOAD_EPKT_CSUM_L3;
+		epkt |= PKT_OFFLOAD_EPKT_TP(1) | PKT_OFFLOAD_EPKT_CSUM_L4;
 		header_cnt++;
 		break;
 	default:
@@ -605,10 +605,8 @@ next:
 
 	bcmasp_intf_rx_desc_write(intf, intf->rx_edpkt_dma_read);
 
-	if (processed < budget) {
-		napi_complete_done(&intf->rx_napi, processed);
+	if (processed < budget && napi_complete_done(&intf->rx_napi, processed))
 		bcmasp_enable_rx_irq(intf, 1);
-	}
 
 	return processed;
 }
@@ -619,7 +617,6 @@ static void bcmasp_adj_link(struct net_device *dev)
 	struct phy_device *phydev = dev->phydev;
 	u32 cmd_bits = 0, reg;
 	int changed = 0;
-	bool active;
 
 	if (intf->old_link != phydev->link) {
 		changed = 1;
@@ -677,8 +674,13 @@ static void bcmasp_adj_link(struct net_device *dev)
 		}
 		umac_wl(intf, reg, UMC_CMD);
 
-		active = phy_init_eee(phydev, 0) >= 0;
-		bcmasp_eee_enable_set(intf, active);
+		umac_wl(intf, phydev->eee_cfg.tx_lpi_timer, UMC_EEE_LPI_TIMER);
+		reg = umac_rl(intf, UMC_EEE_CTRL);
+		if (phydev->enable_tx_lpi)
+			reg |= EEE_EN;
+		else
+			reg &= ~EEE_EN;
+		umac_wl(intf, reg, UMC_EEE_CTRL);
 	}
 
 	reg = rgmii_rl(intf, RGMII_OOB_CNTRL);
@@ -814,9 +816,10 @@ static void bcmasp_init_tx(struct bcmasp_intf *intf)
 	/* Tx SPB */
 	tx_spb_ctrl_wl(intf, ((intf->channel + 8) << TX_SPB_CTRL_XF_BID_SHIFT),
 		       TX_SPB_CTRL_XF_CTRL2);
-	tx_pause_ctrl_wl(intf, (1 << (intf->channel + 8)), TX_PAUSE_MAP_VECTOR);
+
+	if (intf->parent->tx_chan_offset)
+		tx_pause_ctrl_wl(intf, (1 << (intf->channel + 8)), TX_PAUSE_MAP_VECTOR);
 	tx_spb_top_wl(intf, 0x1e, TX_SPB_TOP_BLKOUT);
-	tx_spb_top_wl(intf, 0x0, TX_SPB_TOP_SPRE_BW_CTRL);
 
 	tx_spb_dma_wq(intf, intf->tx_spb_dma_addr, TX_SPB_DMA_READ);
 	tx_spb_dma_wq(intf, intf->tx_spb_dma_addr, TX_SPB_DMA_BASE);
@@ -1055,6 +1058,9 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
 
 		/* Indicate that the MAC is responsible for PHY PM */
 		phydev->mac_managed_pm = true;
+
+		/* Set phylib's copy of the LPI timer */
+		phydev->eee_cfg.tx_lpi_timer = umac_rl(intf, UMC_EEE_LPI_TIMER);
 	}
 
 	umac_reset(intf);
@@ -1178,7 +1184,7 @@ static void bcmasp_map_res(struct bcmasp_priv *priv, struct bcmasp_intf *intf)
 {
 	/* Per port */
 	intf->res.umac = priv->base + UMC_OFFSET(intf);
-	intf->res.umac2fb = priv->base + (priv->hw_info->umac2fb +
+	intf->res.umac2fb = priv->base + (UMAC2FB_OFFSET + priv->rx_ctrl_offset +
 					  (intf->port * 0x4));
 	intf->res.rgmii = priv->base + RGMII_OFFSET(intf);
 
@@ -1193,7 +1199,6 @@ static void bcmasp_map_res(struct bcmasp_priv *priv, struct bcmasp_intf *intf)
 	intf->rx_edpkt_cfg = priv->base + RX_EDPKT_CFG_OFFSET(intf);
 }
 
-#define MAX_IRQ_STR_LEN		64
 struct bcmasp_intf *bcmasp_interface_create(struct bcmasp_priv *priv,
 					    struct device_node *ndev_dn, int i)
 {
@@ -1277,6 +1282,8 @@ struct bcmasp_intf *bcmasp_interface_create(struct bcmasp_priv *priv,
 	ndev->hw_features |= ndev->features;
 	ndev->needed_headroom += sizeof(struct bcmasp_pkt_offload);
 
+	netdev_sw_irq_coalesce_default_on(ndev);
+
 	return intf;
 
 err_free_netdev:
@@ -1331,7 +1338,8 @@ static void bcmasp_suspend_to_wol(struct bcmasp_intf *intf)
 				     ASP_WAKEUP_INTR2_MASK_CLEAR);
 	}
 
-	if (intf->eee.eee_enabled && intf->parent->eee_fixup)
+	if (ndev->phydev && ndev->phydev->eee_cfg.eee_enabled &&
+	    intf->parent->eee_fixup)
 		intf->parent->eee_fixup(intf, true);
 
 	netif_dbg(intf, wol, ndev, "entered WOL mode\n");
@@ -1373,7 +1381,8 @@ static void bcmasp_resume_from_wol(struct bcmasp_intf *intf)
 {
 	u32 reg;
 
-	if (intf->eee.eee_enabled && intf->parent->eee_fixup)
+	if (intf->ndev->phydev && intf->ndev->phydev->eee_cfg.eee_enabled &&
+	    intf->parent->eee_fixup)
 		intf->parent->eee_fixup(intf, false);
 
 	reg = umac_rl(intf, UMC_MPD_CTRL);
@@ -1404,9 +1413,6 @@ int bcmasp_interface_resume(struct bcmasp_intf *intf)
 
 	bcmasp_resume_from_wol(intf);
 
-	if (intf->eee.eee_enabled)
-		bcmasp_eee_enable_set(intf, true);
-
 	netif_device_attach(dev);
 
 	return 0;
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
index ad742612895f..af7418348e81 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
@@ -118,8 +118,7 @@
 #define  UMC_PSW_MS			0x624
 #define  UMC_PSW_LS			0x628
 
-#define UMAC2FB_OFFSET_2_1		0x9f044
-#define UMAC2FB_OFFSET			0x9f03c
+#define UMAC2FB_OFFSET			0x9f044
 #define  UMAC2FB_CFG			0x0
 #define   UMAC2FB_CFG_OPUT_EN		BIT(0)
 #define   UMAC2FB_CFG_VLAN_EN		BIT(1)
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index e5809ad5eb82..888f28f11406 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -31,6 +31,7 @@
 #include <linux/ssb/ssb.h>
 #include <linux/slab.h>
 #include <linux/phy.h>
+#include <linux/phy_fixed.h>
 
 #include <linux/uaccess.h>
 #include <asm/io.h>
@@ -575,7 +576,7 @@ static void b44_check_phy(struct b44 *bp)
 
 static void b44_timer(struct timer_list *t)
 {
-	struct b44 *bp = from_timer(bp, t, timer);
+	struct b44 *bp = timer_container_of(bp, t, timer);
 
 	spin_lock_irq(&bp->lock);
 
@@ -1628,7 +1629,7 @@ static int b44_close(struct net_device *dev)
 
 	napi_disable(&bp->napi);
 
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 
 	spin_lock_irq(&bp->lock);
 
@@ -2233,7 +2234,6 @@ static int b44_register_phy_one(struct b44 *bp)
 	struct mii_bus *mii_bus;
 	struct ssb_device *sdev = bp->sdev;
 	struct phy_device *phydev;
-	char bus_id[MII_BUS_ID_SIZE + 3];
 	struct ssb_sprom *sprom = &sdev->bus->sprom;
 	int err;
 
@@ -2260,27 +2260,26 @@ static int b44_register_phy_one(struct b44 *bp)
 		goto err_out_mdiobus;
 	}
 
-	if (!mdiobus_is_registered_device(bp->mii_bus, bp->phy_addr) &&
-	    (sprom->boardflags_lo & (B44_BOARDFLAG_ROBO | B44_BOARDFLAG_ADM))) {
-
+	phydev = mdiobus_get_phy(bp->mii_bus, bp->phy_addr);
+	if (!phydev &&
+	    sprom->boardflags_lo & (B44_BOARDFLAG_ROBO | B44_BOARDFLAG_ADM)) {
 		dev_info(sdev->dev,
 			 "could not find PHY at %i, use fixed one\n",
 			 bp->phy_addr);
 
-		bp->phy_addr = 0;
-		snprintf(bus_id, sizeof(bus_id), PHY_ID_FMT, "fixed-0",
-			 bp->phy_addr);
-	} else {
-		snprintf(bus_id, sizeof(bus_id), PHY_ID_FMT, mii_bus->id,
-			 bp->phy_addr);
+		phydev = fixed_phy_register_100fd();
+		if (!IS_ERR(phydev))
+			bp->phy_addr = phydev->mdio.addr;
 	}
 
-	phydev = phy_connect(bp->dev, bus_id, &b44_adjust_link,
-			     PHY_INTERFACE_MODE_MII);
-	if (IS_ERR(phydev)) {
+	if (IS_ERR_OR_NULL(phydev))
+		err = -ENODEV;
+	else
+		err = phy_connect_direct(bp->dev, phydev, &b44_adjust_link,
+					 PHY_INTERFACE_MODE_MII);
+	if (err) {
 		dev_err(sdev->dev, "could not attach PHY at %i\n",
 			bp->phy_addr);
-		err = PTR_ERR(phydev);
 		goto err_out_mdiobus_unregister;
 	}
 
@@ -2293,7 +2292,6 @@ static int b44_register_phy_one(struct b44 *bp)
 	linkmode_copy(phydev->advertising, phydev->supported);
 
 	bp->old_link = 0;
-	bp->phy_addr = phydev->mdio.addr;
 
 	phy_attached_info(phydev);
 
@@ -2311,10 +2309,15 @@ err_out:
 
 static void b44_unregister_phy_one(struct b44 *bp)
 {
-	struct net_device *dev = bp->dev;
 	struct mii_bus *mii_bus = bp->mii_bus;
+	struct net_device *dev = bp->dev;
+	struct phy_device *phydev;
+
+	phydev = dev->phydev;
 
-	phy_disconnect(dev->phydev);
+	phy_disconnect(phydev);
+	if (phy_is_pseudo_fixed_link(phydev))
+		fixed_phy_unregister(phydev);
 	mdiobus_unregister(mii_bus);
 	mdiobus_free(mii_bus);
 }
@@ -2473,7 +2476,7 @@ static int b44_suspend(struct ssb_device *sdev, pm_message_t state)
 	if (!netif_running(dev))
 		return 0;
 
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 
 	spin_lock_irq(&bp->lock);
 
@@ -2570,7 +2573,7 @@ static int __init b44_init(void)
 	unsigned int dma_desc_align_size = dma_get_cache_alignment();
 	int err;
 
-	/* Setup paramaters for syncing RX/TX DMA descriptors */
+	/* Setup parameters for syncing RX/TX DMA descriptors */
 	dma_desc_sync_size = max_t(unsigned int, dma_desc_align_size, sizeof(struct dma_desc));
 
 	err = b44_pci_init();
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 65e3a0656a4c..92204fea1f08 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -286,7 +286,7 @@ static int bcm_enet_refill_rx(struct net_device *dev, bool napi_mode)
  */
 static void bcm_enet_refill_rx_timer(struct timer_list *t)
 {
-	struct bcm_enet_priv *priv = from_timer(priv, t, rx_timeout);
+	struct bcm_enet_priv *priv = timer_container_of(priv, t, rx_timeout);
 	struct net_device *dev = priv->net_dev;
 
 	spin_lock(&priv->rx_lock);
@@ -1195,7 +1195,7 @@ static int bcm_enet_stop(struct net_device *dev)
 	napi_disable(&priv->napi);
 	if (priv->has_phy)
 		phy_stop(dev->phydev);
-	del_timer_sync(&priv->rx_timeout);
+	timer_delete_sync(&priv->rx_timeout);
 
 	/* mask all interrupts */
 	enet_writel(priv, 0, ENET_IRMASK_REG);
@@ -2001,7 +2001,7 @@ static inline int bcm_enet_port_is_rgmii(int portid)
  */
 static void swphy_poll_timer(struct timer_list *t)
 {
-	struct bcm_enet_priv *priv = from_timer(priv, t, swphy_poll);
+	struct bcm_enet_priv *priv = timer_container_of(priv, t, swphy_poll);
 	unsigned int i;
 
 	for (i = 0; i < priv->num_ports; i++) {
@@ -2346,10 +2346,10 @@ static int bcm_enetsw_stop(struct net_device *dev)
 	priv = netdev_priv(dev);
 	kdev = &priv->pdev->dev;
 
-	del_timer_sync(&priv->swphy_poll);
+	timer_delete_sync(&priv->swphy_poll);
 	netif_stop_queue(dev);
 	napi_disable(&priv->napi);
-	del_timer_sync(&priv->rx_timeout);
+	timer_delete_sync(&priv->rx_timeout);
 
 	/* mask all interrupts */
 	enet_dmac_writel(priv, 0, ENETDMAC_IRMASK, priv->rx_chan);
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 42672c63f108..bc4e1f3b3752 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1933,7 +1933,11 @@ static int bcm_sysport_open(struct net_device *dev)
 	unsigned int i;
 	int ret;
 
-	clk_prepare_enable(priv->clk);
+	ret = clk_prepare_enable(priv->clk);
+	if (ret) {
+		netdev_err(dev, "could not enable priv clock\n");
+		return ret;
+	}
 
 	/* Reset UniMAC */
 	umac_reset(priv);
@@ -2591,7 +2595,11 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 		goto err_deregister_notifier;
 	}
 
-	clk_prepare_enable(priv->clk);
+	ret = clk_prepare_enable(priv->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "could not enable priv clock\n");
+		goto err_deregister_netdev;
+	}
 
 	priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK;
 	dev_info(&pdev->dev,
@@ -2605,6 +2613,8 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_deregister_netdev:
+	unregister_netdev(dev);
 err_deregister_notifier:
 	unregister_netdevice_notifier(&priv->netdev_notifier);
 err_deregister_fixed_link:
@@ -2774,7 +2784,12 @@ static int __maybe_unused bcm_sysport_resume(struct device *d)
 	if (!netif_running(dev))
 		return 0;
 
-	clk_prepare_enable(priv->clk);
+	ret = clk_prepare_enable(priv->clk);
+	if (ret) {
+		netdev_err(dev, "could not enable priv clock\n");
+		return ret;
+	}
+
 	if (priv->wolopts)
 		clk_disable_unprepare(priv->wol_clk);
 
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index a461ec612e95..3e9c57196a39 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1446,7 +1446,7 @@ int bgmac_phy_connect_direct(struct bgmac *bgmac)
 	struct phy_device *phy_dev;
 	int err;
 
-	phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
+	phy_dev = fixed_phy_register(&fphy_status, NULL);
 	if (IS_ERR(phy_dev)) {
 		dev_err(bgmac->dev, "Failed to register fixed PHY device\n");
 		return PTR_ERR(phy_dev);
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index d73ef262991d..6fee9a41839c 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -328,8 +328,7 @@
 #define BGMAC_RX_FRAME_OFFSET			30		/* There are 2 unused bytes between header and real data */
 #define BGMAC_RX_BUF_OFFSET			(NET_SKB_PAD + NET_IP_ALIGN - \
 						 BGMAC_RX_FRAME_OFFSET)
-/* Jumbo frame size with FCS */
-#define BGMAC_RX_MAX_FRAME_SIZE			9724
+#define BGMAC_RX_MAX_FRAME_SIZE			1536
 #define BGMAC_RX_BUF_SIZE			(BGMAC_RX_FRAME_OFFSET + BGMAC_RX_MAX_FRAME_SIZE)
 #define BGMAC_RX_ALLOC_SIZE			(SKB_DATA_ALIGN(BGMAC_RX_BUF_SIZE + BGMAC_RX_BUF_OFFSET) + \
 						 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
diff --git a/drivers/net/ethernet/broadcom/bnge/Makefile b/drivers/net/ethernet/broadcom/bnge/Makefile
new file mode 100644
index 000000000000..ea6596854e5c
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/Makefile
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_BNGE) += bng_en.o
+
+bng_en-y := bnge_core.o \
+	    bnge_devlink.o \
+	    bnge_hwrm.o \
+	    bnge_hwrm_lib.o \
+	    bnge_rmem.o \
+	    bnge_resc.o \
+	    bnge_netdev.o \
+	    bnge_ethtool.o \
+	    bnge_auxr.o
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge.h b/drivers/net/ethernet/broadcom/bnge/bnge.h
new file mode 100644
index 000000000000..411744894349
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge.h
@@ -0,0 +1,255 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Broadcom */
+
+#ifndef _BNGE_H_
+#define _BNGE_H_
+
+#define DRV_NAME	"bng_en"
+#define DRV_SUMMARY	"Broadcom 800G Ethernet Linux Driver"
+
+#include <linux/etherdevice.h>
+#include <linux/bnxt/hsi.h>
+#include "bnge_rmem.h"
+#include "bnge_resc.h"
+#include "bnge_auxr.h"
+
+#define DRV_VER_MAJ	1
+#define DRV_VER_MIN	15
+#define DRV_VER_UPD	1
+
+extern char bnge_driver_name[];
+
+enum board_idx {
+	BCM57708,
+};
+
+struct bnge_auxr_priv {
+	struct auxiliary_device aux_dev;
+	struct bnge_auxr_dev *auxr_dev;
+	int id;
+};
+
+struct bnge_pf_info {
+	u16	fw_fid;
+	u16	port_id;
+	u8	mac_addr[ETH_ALEN];
+};
+
+#define INVALID_HW_RING_ID      ((u16)-1)
+
+enum {
+	BNGE_FW_CAP_SHORT_CMD				= BIT_ULL(0),
+	BNGE_FW_CAP_LLDP_AGENT				= BIT_ULL(1),
+	BNGE_FW_CAP_DCBX_AGENT				= BIT_ULL(2),
+	BNGE_FW_CAP_IF_CHANGE				= BIT_ULL(3),
+	BNGE_FW_CAP_KONG_MB_CHNL			= BIT_ULL(4),
+	BNGE_FW_CAP_ERROR_RECOVERY			= BIT_ULL(5),
+	BNGE_FW_CAP_PKG_VER				= BIT_ULL(6),
+	BNGE_FW_CAP_CFA_ADV_FLOW			= BIT_ULL(7),
+	BNGE_FW_CAP_CFA_RFS_RING_TBL_IDX_V2		= BIT_ULL(8),
+	BNGE_FW_CAP_PCIE_STATS_SUPPORTED		= BIT_ULL(9),
+	BNGE_FW_CAP_EXT_STATS_SUPPORTED			= BIT_ULL(10),
+	BNGE_FW_CAP_ERR_RECOVER_RELOAD			= BIT_ULL(11),
+	BNGE_FW_CAP_HOT_RESET				= BIT_ULL(12),
+	BNGE_FW_CAP_RX_ALL_PKT_TS			= BIT_ULL(13),
+	BNGE_FW_CAP_VLAN_RX_STRIP			= BIT_ULL(14),
+	BNGE_FW_CAP_VLAN_TX_INSERT			= BIT_ULL(15),
+	BNGE_FW_CAP_EXT_HW_STATS_SUPPORTED		= BIT_ULL(16),
+	BNGE_FW_CAP_LIVEPATCH				= BIT_ULL(17),
+	BNGE_FW_CAP_HOT_RESET_IF			= BIT_ULL(18),
+	BNGE_FW_CAP_RING_MONITOR			= BIT_ULL(19),
+	BNGE_FW_CAP_DBG_QCAPS				= BIT_ULL(20),
+	BNGE_FW_CAP_THRESHOLD_TEMP_SUPPORTED		= BIT_ULL(21),
+	BNGE_FW_CAP_DFLT_VLAN_TPID_PCP			= BIT_ULL(22),
+	BNGE_FW_CAP_VNIC_TUNNEL_TPA			= BIT_ULL(23),
+	BNGE_FW_CAP_CFA_NTUPLE_RX_EXT_IP_PROTO		= BIT_ULL(24),
+	BNGE_FW_CAP_CFA_RFS_RING_TBL_IDX_V3		= BIT_ULL(25),
+	BNGE_FW_CAP_VNIC_RE_FLUSH			= BIT_ULL(26),
+};
+
+enum {
+	BNGE_EN_ROCE_V1					= BIT_ULL(0),
+	BNGE_EN_ROCE_V2					= BIT_ULL(1),
+	BNGE_EN_STRIP_VLAN				= BIT_ULL(2),
+	BNGE_EN_SHARED_CHNL				= BIT_ULL(3),
+	BNGE_EN_UDP_GSO_SUPP				= BIT_ULL(4),
+};
+
+#define BNGE_EN_ROCE		(BNGE_EN_ROCE_V1 | BNGE_EN_ROCE_V2)
+
+enum {
+	BNGE_RSS_CAP_RSS_HASH_TYPE_DELTA		= BIT(0),
+	BNGE_RSS_CAP_UDP_RSS_CAP			= BIT(1),
+	BNGE_RSS_CAP_NEW_RSS_CAP			= BIT(2),
+	BNGE_RSS_CAP_RSS_TCAM				= BIT(3),
+	BNGE_RSS_CAP_AH_V4_RSS_CAP			= BIT(4),
+	BNGE_RSS_CAP_AH_V6_RSS_CAP			= BIT(5),
+	BNGE_RSS_CAP_ESP_V4_RSS_CAP			= BIT(6),
+	BNGE_RSS_CAP_ESP_V6_RSS_CAP			= BIT(7),
+};
+
+#define BNGE_MAX_QUEUE		8
+struct bnge_queue_info {
+	u8      queue_id;
+	u8      queue_profile;
+};
+
+struct bnge_dev {
+	struct device	*dev;
+	struct pci_dev	*pdev;
+	struct net_device	*netdev;
+	u64	dsn;
+#define BNGE_VPD_FLD_LEN	32
+	char		board_partno[BNGE_VPD_FLD_LEN];
+	char		board_serialno[BNGE_VPD_FLD_LEN];
+
+	void __iomem	*bar0;
+	void __iomem	*bar1;
+
+	u16		chip_num;
+	u8		chip_rev;
+
+#if BITS_PER_LONG == 32
+	/* ensure atomic 64-bit doorbell writes on 32-bit systems. */
+	spinlock_t	db_lock;
+#endif
+	int		db_offset; /* db_offset within db_size */
+	int		db_size;
+
+	/* HWRM members */
+	u16			hwrm_cmd_seq;
+	u16			hwrm_cmd_kong_seq;
+	struct dma_pool		*hwrm_dma_pool;
+	struct hlist_head	hwrm_pending_list;
+	u16			hwrm_max_req_len;
+	u16			hwrm_max_ext_req_len;
+	unsigned int		hwrm_cmd_timeout;
+	unsigned int		hwrm_cmd_max_timeout;
+	struct mutex		hwrm_cmd_lock;	/* serialize hwrm messages */
+
+	struct hwrm_ver_get_output	ver_resp;
+#define FW_VER_STR_LEN		32
+	char			fw_ver_str[FW_VER_STR_LEN];
+	char			hwrm_ver_supp[FW_VER_STR_LEN];
+	char			nvm_cfg_ver[FW_VER_STR_LEN];
+	u64			fw_ver_code;
+#define BNGE_FW_VER_CODE(maj, min, bld, rsv)			\
+	((u64)(maj) << 48 | (u64)(min) << 32 | (u64)(bld) << 16 | (rsv))
+
+	struct bnge_pf_info	pf;
+
+	unsigned long           state;
+#define BNGE_STATE_DRV_REGISTERED      0
+#define BNGE_STATE_OPEN			1
+
+	u64			fw_cap;
+
+	/* Backing stores */
+	struct bnge_ctx_mem_info	*ctx;
+
+	u64			flags;
+
+	struct bnge_hw_resc	hw_resc;
+
+	u16			tso_max_segs;
+
+	int			max_fltr;
+#define BNGE_L2_FLTR_MAX_FLTR	1024
+
+	u32			*rss_indir_tbl;
+#define BNGE_RSS_TABLE_ENTRIES	64
+#define BNGE_RSS_TABLE_SIZE		(BNGE_RSS_TABLE_ENTRIES * 4)
+#define BNGE_RSS_TABLE_MAX_TBL	8
+#define BNGE_MAX_RSS_TABLE_SIZE				\
+	(BNGE_RSS_TABLE_SIZE * BNGE_RSS_TABLE_MAX_TBL)
+#define BNGE_MAX_RSS_TABLE_ENTRIES				\
+	(BNGE_RSS_TABLE_ENTRIES * BNGE_RSS_TABLE_MAX_TBL)
+	u16			rss_indir_tbl_entries;
+
+	u32			rss_cap;
+	u32			rss_hash_cfg;
+
+	u16			rx_nr_rings;
+	u16			tx_nr_rings;
+	u16			tx_nr_rings_per_tc;
+	/* Number of NQs */
+	u16			nq_nr_rings;
+
+	/* Aux device resources */
+	u16			aux_num_msix;
+	u16			aux_num_stat_ctxs;
+
+	u16			max_mtu;
+#define BNGE_MAX_MTU		9500
+
+	u16			hw_ring_stats_size;
+#define BNGE_NUM_RX_RING_STATS			8
+#define BNGE_NUM_TX_RING_STATS			8
+#define BNGE_NUM_TPA_RING_STATS			6
+#define BNGE_RING_STATS_SIZE					\
+	((BNGE_NUM_RX_RING_STATS + BNGE_NUM_TX_RING_STATS +	\
+	  BNGE_NUM_TPA_RING_STATS) * 8)
+
+	u16			max_tpa_v2;
+#define BNGE_SUPPORTS_TPA(bd)	((bd)->max_tpa_v2)
+
+	u8                      num_tc;
+	u8			max_tc;
+	u8			max_lltc;	/* lossless TCs */
+	struct bnge_queue_info	q_info[BNGE_MAX_QUEUE];
+	u8			tc_to_qidx[BNGE_MAX_QUEUE];
+	u8			q_ids[BNGE_MAX_QUEUE];
+	u8			max_q;
+	u8			port_count;
+
+	struct bnge_irq		*irq_tbl;
+	u16			irqs_acquired;
+
+	struct bnge_auxr_priv	*aux_priv;
+	struct bnge_auxr_dev	*auxr_dev;
+};
+
+static inline bool bnge_is_roce_en(struct bnge_dev *bd)
+{
+	return bd->flags & BNGE_EN_ROCE;
+}
+
+static inline bool bnge_is_agg_reqd(struct bnge_dev *bd)
+{
+	if (bd->netdev) {
+		struct bnge_net *bn = netdev_priv(bd->netdev);
+
+		if (bn->priv_flags & BNGE_NET_EN_TPA ||
+		    bn->priv_flags & BNGE_NET_EN_JUMBO)
+			return true;
+		else
+			return false;
+	}
+
+	return true;
+}
+
+static inline void bnge_writeq(struct bnge_dev *bd, u64 val,
+			       void __iomem *addr)
+{
+#if BITS_PER_LONG == 32
+	spin_lock(&bd->db_lock);
+	lo_hi_writeq(val, addr);
+	spin_unlock(&bd->db_lock);
+#else
+	writeq(val, addr);
+#endif
+}
+
+/* For TX and RX ring doorbells */
+static inline void bnge_db_write(struct bnge_dev *bd, struct bnge_db_info *db,
+				 u32 idx)
+{
+	bnge_writeq(bd, db->db_key64 | DB_RING_IDX(db, idx),
+		    db->doorbell);
+}
+
+bool bnge_aux_registered(struct bnge_dev *bd);
+u16 bnge_aux_get_msix(struct bnge_dev *bd);
+
+#endif /* _BNGE_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c b/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c
new file mode 100644
index 000000000000..d64592b64e17
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c
@@ -0,0 +1,258 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2025 Broadcom.
+
+#include <linux/module.h>
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/bitops.h>
+#include <linux/irq.h>
+#include <asm/byteorder.h>
+#include <linux/bitmap.h>
+#include <linux/auxiliary_bus.h>
+#include <linux/bnxt/hsi.h>
+
+#include "bnge.h"
+#include "bnge_hwrm.h"
+#include "bnge_auxr.h"
+
+static DEFINE_IDA(bnge_aux_dev_ids);
+
+static void bnge_fill_msix_vecs(struct bnge_dev *bd,
+				struct bnge_msix_info *info)
+{
+	struct bnge_auxr_dev *auxr_dev = bd->auxr_dev;
+	int num_msix, i;
+
+	if (!auxr_dev->auxr_info->msix_requested) {
+		dev_warn(bd->dev, "Requested MSI-X vectors not allocated\n");
+		return;
+	}
+	num_msix = auxr_dev->auxr_info->msix_requested;
+	for (i = 0; i < num_msix; i++) {
+		info[i].vector = bd->irq_tbl[i].vector;
+		info[i].db_offset = bd->db_offset;
+		info[i].ring_idx = i;
+	}
+}
+
+int bnge_register_dev(struct bnge_auxr_dev *auxr_dev,
+		      void *handle)
+{
+	struct bnge_dev *bd = pci_get_drvdata(auxr_dev->pdev);
+	struct bnge_auxr_info *auxr_info;
+	int rc = 0;
+
+	netdev_lock(bd->netdev);
+	mutex_lock(&auxr_dev->auxr_dev_lock);
+	if (!bd->irq_tbl) {
+		rc = -ENODEV;
+		goto exit;
+	}
+
+	if (!bnge_aux_has_enough_resources(bd)) {
+		rc = -ENOMEM;
+		goto exit;
+	}
+
+	auxr_info = auxr_dev->auxr_info;
+	auxr_info->handle = handle;
+
+	auxr_info->msix_requested = bd->aux_num_msix;
+
+	bnge_fill_msix_vecs(bd, bd->auxr_dev->msix_info);
+	auxr_dev->flags |= BNGE_ARDEV_MSIX_ALLOC;
+
+exit:
+	mutex_unlock(&auxr_dev->auxr_dev_lock);
+	netdev_unlock(bd->netdev);
+	return rc;
+}
+EXPORT_SYMBOL(bnge_register_dev);
+
+void bnge_unregister_dev(struct bnge_auxr_dev *auxr_dev)
+{
+	struct bnge_dev *bd = pci_get_drvdata(auxr_dev->pdev);
+	struct bnge_auxr_info *auxr_info;
+
+	auxr_info = auxr_dev->auxr_info;
+	netdev_lock(bd->netdev);
+	mutex_lock(&auxr_dev->auxr_dev_lock);
+	if (auxr_info->msix_requested)
+		auxr_dev->flags &= ~BNGE_ARDEV_MSIX_ALLOC;
+	auxr_info->msix_requested = 0;
+
+	mutex_unlock(&auxr_dev->auxr_dev_lock);
+	netdev_unlock(bd->netdev);
+}
+EXPORT_SYMBOL(bnge_unregister_dev);
+
+int bnge_send_msg(struct bnge_auxr_dev *auxr_dev, struct bnge_fw_msg *fw_msg)
+{
+	struct bnge_dev *bd = pci_get_drvdata(auxr_dev->pdev);
+	struct output *resp;
+	struct input *req;
+	u32 resp_len;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, 0 /* don't care */);
+	if (rc)
+		return rc;
+
+	rc = bnge_hwrm_req_replace(bd, req, fw_msg->msg, fw_msg->msg_len);
+	if (rc)
+		goto drop_req;
+
+	bnge_hwrm_req_timeout(bd, req, fw_msg->timeout);
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	resp_len = le16_to_cpu(resp->resp_len);
+	if (resp_len) {
+		if (fw_msg->resp_max_len < resp_len)
+			resp_len = fw_msg->resp_max_len;
+
+		memcpy(fw_msg->resp, resp, resp_len);
+	}
+drop_req:
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+EXPORT_SYMBOL(bnge_send_msg);
+
+void bnge_rdma_aux_device_uninit(struct bnge_dev *bd)
+{
+	struct bnge_auxr_priv *aux_priv;
+	struct auxiliary_device *adev;
+
+	/* Skip if no auxiliary device init was done. */
+	if (!bd->aux_priv)
+		return;
+
+	aux_priv = bd->aux_priv;
+	adev = &aux_priv->aux_dev;
+	auxiliary_device_uninit(adev);
+}
+
+static void bnge_aux_dev_release(struct device *dev)
+{
+	struct bnge_auxr_priv *aux_priv =
+			container_of(dev, struct bnge_auxr_priv, aux_dev.dev);
+	struct bnge_dev *bd = pci_get_drvdata(aux_priv->auxr_dev->pdev);
+
+	ida_free(&bnge_aux_dev_ids, aux_priv->id);
+	kfree(aux_priv->auxr_dev->auxr_info);
+	bd->auxr_dev = NULL;
+	kfree(aux_priv->auxr_dev);
+	kfree(aux_priv);
+	bd->aux_priv = NULL;
+}
+
+void bnge_rdma_aux_device_del(struct bnge_dev *bd)
+{
+	if (!bd->auxr_dev)
+		return;
+
+	auxiliary_device_delete(&bd->aux_priv->aux_dev);
+}
+
+static void bnge_set_auxr_dev_info(struct bnge_auxr_dev *auxr_dev,
+				   struct bnge_dev *bd)
+{
+	auxr_dev->pdev = bd->pdev;
+	auxr_dev->l2_db_size = bd->db_size;
+	auxr_dev->l2_db_size_nc = bd->db_size;
+	auxr_dev->l2_db_offset = bd->db_offset;
+	mutex_init(&auxr_dev->auxr_dev_lock);
+
+	if (bd->flags & BNGE_EN_ROCE_V1)
+		auxr_dev->flags |= BNGE_ARDEV_ROCEV1_SUPP;
+	if (bd->flags & BNGE_EN_ROCE_V2)
+		auxr_dev->flags |= BNGE_ARDEV_ROCEV2_SUPP;
+
+	auxr_dev->chip_num = bd->chip_num;
+	auxr_dev->hw_ring_stats_size = bd->hw_ring_stats_size;
+	auxr_dev->pf_port_id = bd->pf.port_id;
+	auxr_dev->en_state = bd->state;
+	auxr_dev->bar0 = bd->bar0;
+}
+
+void bnge_rdma_aux_device_add(struct bnge_dev *bd)
+{
+	struct auxiliary_device *aux_dev;
+	int rc;
+
+	if (!bd->auxr_dev)
+		return;
+
+	aux_dev = &bd->aux_priv->aux_dev;
+	rc = auxiliary_device_add(aux_dev);
+	if (rc) {
+		dev_warn(bd->dev, "Failed to add auxiliary device for ROCE\n");
+		auxiliary_device_uninit(aux_dev);
+		bd->flags &= ~BNGE_EN_ROCE;
+	}
+
+	bd->auxr_dev->net = bd->netdev;
+}
+
+void bnge_rdma_aux_device_init(struct bnge_dev *bd)
+{
+	struct auxiliary_device *aux_dev;
+	struct bnge_auxr_info *auxr_info;
+	struct bnge_auxr_priv *aux_priv;
+	struct bnge_auxr_dev *auxr_dev;
+	int rc;
+
+	if (!bnge_is_roce_en(bd))
+		return;
+
+	aux_priv = kzalloc(sizeof(*aux_priv), GFP_KERNEL);
+	if (!aux_priv)
+		goto exit;
+
+	aux_priv->id = ida_alloc(&bnge_aux_dev_ids, GFP_KERNEL);
+	if (aux_priv->id < 0) {
+		dev_warn(bd->dev, "ida alloc failed for aux device\n");
+		kfree(aux_priv);
+		goto exit;
+	}
+
+	aux_dev = &aux_priv->aux_dev;
+	aux_dev->id = aux_priv->id;
+	aux_dev->name = "rdma";
+	aux_dev->dev.parent = &bd->pdev->dev;
+	aux_dev->dev.release = bnge_aux_dev_release;
+
+	rc = auxiliary_device_init(aux_dev);
+	if (rc) {
+		ida_free(&bnge_aux_dev_ids, aux_priv->id);
+		kfree(aux_priv);
+		goto exit;
+	}
+	bd->aux_priv = aux_priv;
+
+	auxr_dev = kzalloc(sizeof(*auxr_dev), GFP_KERNEL);
+	if (!auxr_dev)
+		goto aux_dev_uninit;
+
+	aux_priv->auxr_dev = auxr_dev;
+
+	auxr_info = kzalloc(sizeof(*auxr_info), GFP_KERNEL);
+	if (!auxr_info)
+		goto aux_dev_uninit;
+
+	auxr_dev->auxr_info = auxr_info;
+	bd->auxr_dev = auxr_dev;
+	bnge_set_auxr_dev_info(auxr_dev, bd);
+
+	return;
+
+aux_dev_uninit:
+	auxiliary_device_uninit(aux_dev);
+exit:
+	bd->flags &= ~BNGE_EN_ROCE;
+}
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_auxr.h b/drivers/net/ethernet/broadcom/bnge/bnge_auxr.h
new file mode 100644
index 000000000000..6c5c15ef2b0a
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_auxr.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Broadcom */
+
+#ifndef _BNGE_AUXR_H_
+#define _BNGE_AUXR_H_
+
+#include <linux/auxiliary_bus.h>
+
+#define BNGE_MIN_ROCE_CP_RINGS	2
+#define BNGE_MIN_ROCE_STAT_CTXS	1
+
+#define BNGE_MAX_ROCE_MSIX	64
+
+struct hwrm_async_event_cmpl;
+struct bnge;
+
+struct bnge_msix_info {
+	u32	vector;
+	u32	ring_idx;
+	u32	db_offset;
+};
+
+struct bnge_fw_msg {
+	void	*msg;
+	int	msg_len;
+	void	*resp;
+	int	resp_max_len;
+	int	timeout;
+};
+
+struct bnge_auxr_info {
+	void		*handle;
+	u16		msix_requested;
+};
+
+enum {
+	BNGE_ARDEV_ROCEV1_SUPP		= BIT(0),
+	BNGE_ARDEV_ROCEV2_SUPP		= BIT(1),
+	BNGE_ARDEV_MSIX_ALLOC		= BIT(2),
+};
+
+#define BNGE_ARDEV_ROCE_SUPP	(BNGE_ARDEV_ROCEV1_SUPP | \
+				 BNGE_ARDEV_ROCEV2_SUPP)
+
+struct bnge_auxr_dev {
+	struct net_device	*net;
+	struct pci_dev		*pdev;
+	void __iomem		*bar0;
+
+	struct bnge_msix_info	msix_info[BNGE_MAX_ROCE_MSIX];
+
+	u32 flags;
+
+	struct bnge_auxr_info	*auxr_info;
+
+	/* Doorbell BAR size in bytes mapped by L2 driver. */
+	int	l2_db_size;
+	/* Doorbell BAR size in bytes mapped as non-cacheable. */
+	int	l2_db_size_nc;
+	/* Doorbell offset in bytes within l2_db_size_nc. */
+	int	l2_db_offset;
+
+	u16		chip_num;
+	u16		hw_ring_stats_size;
+	u16		pf_port_id;
+	unsigned long	en_state;
+
+	u16	auxr_num_msix_vec;
+	u16	auxr_num_ctxs;
+
+	/* serialize auxr operations */
+	struct mutex	auxr_dev_lock;
+};
+
+void bnge_rdma_aux_device_uninit(struct bnge_dev *bdev);
+void bnge_rdma_aux_device_del(struct bnge_dev *bdev);
+void bnge_rdma_aux_device_add(struct bnge_dev *bdev);
+void bnge_rdma_aux_device_init(struct bnge_dev *bdev);
+int bnge_register_dev(struct bnge_auxr_dev *adev,
+		      void *handle);
+void bnge_unregister_dev(struct bnge_auxr_dev *adev);
+int bnge_send_msg(struct bnge_auxr_dev *adev, struct bnge_fw_msg *fw_msg);
+
+#endif /* _BNGE_AUXR_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_core.c b/drivers/net/ethernet/broadcom/bnge/bnge_core.c
new file mode 100644
index 000000000000..c94e132bebc8
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_core.c
@@ -0,0 +1,420 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2025 Broadcom.
+
+#include <linux/init.h>
+#include <linux/crash_dump.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include "bnge.h"
+#include "bnge_devlink.h"
+#include "bnge_hwrm.h"
+#include "bnge_hwrm_lib.h"
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION(DRV_SUMMARY);
+
+char bnge_driver_name[] = DRV_NAME;
+
+static const struct {
+	char *name;
+} board_info[] = {
+	[BCM57708] = { "Broadcom BCM57708 50Gb/100Gb/200Gb/400Gb/800Gb Ethernet" },
+};
+
+static const struct pci_device_id bnge_pci_tbl[] = {
+	{ PCI_VDEVICE(BROADCOM, 0x1780), .driver_data = BCM57708 },
+	/* Required last entry */
+	{0, }
+};
+MODULE_DEVICE_TABLE(pci, bnge_pci_tbl);
+
+static void bnge_print_device_info(struct pci_dev *pdev, enum board_idx idx)
+{
+	struct device *dev = &pdev->dev;
+
+	dev_info(dev, "%s found at mem %lx\n", board_info[idx].name,
+		 (long)pci_resource_start(pdev, 0));
+
+	pcie_print_link_status(pdev);
+}
+
+bool bnge_aux_registered(struct bnge_dev *bd)
+{
+	struct bnge_auxr_dev *ba_dev = bd->auxr_dev;
+
+	if (ba_dev && ba_dev->auxr_info->msix_requested)
+		return true;
+
+	return false;
+}
+
+static void bnge_nvm_cfg_ver_get(struct bnge_dev *bd)
+{
+	struct hwrm_nvm_get_dev_info_output nvm_info;
+
+	if (!bnge_hwrm_nvm_dev_info(bd, &nvm_info))
+		snprintf(bd->nvm_cfg_ver, FW_VER_STR_LEN, "%d.%d.%d",
+			 nvm_info.nvm_cfg_ver_maj, nvm_info.nvm_cfg_ver_min,
+			 nvm_info.nvm_cfg_ver_upd);
+}
+
+static int bnge_func_qcaps(struct bnge_dev *bd)
+{
+	int rc;
+
+	rc = bnge_hwrm_func_qcaps(bd);
+	if (rc)
+		return rc;
+
+	rc = bnge_hwrm_queue_qportcfg(bd);
+	if (rc) {
+		dev_err(bd->dev, "query qportcfg failure rc: %d\n", rc);
+		return rc;
+	}
+
+	rc = bnge_hwrm_func_resc_qcaps(bd);
+	if (rc) {
+		dev_err(bd->dev, "query resc caps failure rc: %d\n", rc);
+		return rc;
+	}
+
+	rc = bnge_hwrm_func_qcfg(bd);
+	if (rc) {
+		dev_err(bd->dev, "query config failure rc: %d\n", rc);
+		return rc;
+	}
+
+	rc = bnge_hwrm_vnic_qcaps(bd);
+	if (rc) {
+		dev_err(bd->dev, "vnic caps failure rc: %d\n", rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+static void bnge_fw_unregister_dev(struct bnge_dev *bd)
+{
+	/* ctx mem free after unrgtr only */
+	bnge_hwrm_func_drv_unrgtr(bd);
+	bnge_free_ctx_mem(bd);
+}
+
+static void bnge_set_dflt_rss_hash_type(struct bnge_dev *bd)
+{
+	bd->rss_hash_cfg = VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 |
+			   VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 |
+			   VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 |
+			   VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6 |
+			   VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 |
+			   VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
+}
+
+static int bnge_fw_register_dev(struct bnge_dev *bd)
+{
+	int rc;
+
+	bd->fw_cap = 0;
+	rc = bnge_hwrm_ver_get(bd);
+	if (rc) {
+		dev_err(bd->dev, "Get Version command failed rc: %d\n", rc);
+		return rc;
+	}
+
+	bnge_nvm_cfg_ver_get(bd);
+
+	rc = bnge_hwrm_func_reset(bd);
+	if (rc) {
+		dev_err(bd->dev, "Failed to reset function rc: %d\n", rc);
+		return rc;
+	}
+
+	bnge_hwrm_fw_set_time(bd);
+
+	rc =  bnge_hwrm_func_drv_rgtr(bd);
+	if (rc) {
+		dev_err(bd->dev, "Failed to rgtr with firmware rc: %d\n", rc);
+		return rc;
+	}
+
+	rc = bnge_alloc_ctx_mem(bd);
+	if (rc) {
+		dev_err(bd->dev, "Failed to allocate ctx mem rc: %d\n", rc);
+		goto err_func_unrgtr;
+	}
+
+	/* Get the resources and configuration from firmware */
+	rc = bnge_func_qcaps(bd);
+	if (rc) {
+		dev_err(bd->dev, "Failed initial configuration rc: %d\n", rc);
+		rc = -ENODEV;
+		goto err_func_unrgtr;
+	}
+
+	bnge_set_dflt_rss_hash_type(bd);
+
+	return 0;
+
+err_func_unrgtr:
+	bnge_fw_unregister_dev(bd);
+	return rc;
+}
+
+static void bnge_pci_disable(struct pci_dev *pdev)
+{
+	pci_release_regions(pdev);
+	if (pci_is_enabled(pdev))
+		pci_disable_device(pdev);
+}
+
+static int bnge_pci_enable(struct pci_dev *pdev)
+{
+	int rc;
+
+	rc = pci_enable_device(pdev);
+	if (rc) {
+		dev_err(&pdev->dev, "Cannot enable PCI device, aborting\n");
+		return rc;
+	}
+
+	if (!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
+		dev_err(&pdev->dev,
+			"Cannot find PCI device base address, aborting\n");
+		rc = -ENODEV;
+		goto err_pci_disable;
+	}
+
+	rc = pci_request_regions(pdev, bnge_driver_name);
+	if (rc) {
+		dev_err(&pdev->dev, "Cannot obtain PCI resources, aborting\n");
+		goto err_pci_disable;
+	}
+
+	dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+
+	pci_set_master(pdev);
+
+	return 0;
+
+err_pci_disable:
+	pci_disable_device(pdev);
+	return rc;
+}
+
+static void bnge_unmap_bars(struct pci_dev *pdev)
+{
+	struct bnge_dev *bd = pci_get_drvdata(pdev);
+
+	if (bd->bar1) {
+		pci_iounmap(pdev, bd->bar1);
+		bd->bar1 = NULL;
+	}
+
+	if (bd->bar0) {
+		pci_iounmap(pdev, bd->bar0);
+		bd->bar0 = NULL;
+	}
+}
+
+static void bnge_set_max_func_irqs(struct bnge_dev *bd,
+				   unsigned int max_irqs)
+{
+	bd->hw_resc.max_irqs = max_irqs;
+}
+
+static int bnge_get_max_irq(struct pci_dev *pdev)
+{
+	u16 ctrl;
+
+	pci_read_config_word(pdev, pdev->msix_cap + PCI_MSIX_FLAGS, &ctrl);
+	return (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1;
+}
+
+static int bnge_map_db_bar(struct bnge_dev *bd)
+{
+	if (!bd->db_size)
+		return -ENODEV;
+
+	bd->bar1 = pci_iomap(bd->pdev, 2, bd->db_size);
+	if (!bd->bar1)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int bnge_probe_one(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	unsigned int max_irqs;
+	struct bnge_dev *bd;
+	int rc;
+
+	if (pci_is_bridge(pdev))
+		return -ENODEV;
+
+	if (!pdev->msix_cap) {
+		dev_err(&pdev->dev, "MSIX capability missing, aborting\n");
+		return -ENODEV;
+	}
+
+	if (is_kdump_kernel()) {
+		pci_clear_master(pdev);
+		pcie_flr(pdev);
+	}
+
+	rc = bnge_pci_enable(pdev);
+	if (rc)
+		return rc;
+
+	bnge_print_device_info(pdev, ent->driver_data);
+
+	bd = bnge_devlink_alloc(pdev);
+	if (!bd) {
+		dev_err(&pdev->dev, "Devlink allocation failed\n");
+		rc = -ENOMEM;
+		goto err_pci_disable;
+	}
+
+	bd->bar0 = pci_ioremap_bar(pdev, 0);
+	if (!bd->bar0) {
+		dev_err(&pdev->dev, "Failed mapping BAR-0, aborting\n");
+		rc = -ENOMEM;
+		goto err_devl_free;
+	}
+
+	rc = bnge_init_hwrm_resources(bd);
+	if (rc)
+		goto err_bar_unmap;
+
+	rc = bnge_fw_register_dev(bd);
+	if (rc) {
+		dev_err(&pdev->dev, "Failed to register with firmware rc = %d\n", rc);
+		goto err_hwrm_cleanup;
+	}
+
+	bnge_devlink_register(bd);
+
+	max_irqs = bnge_get_max_irq(pdev);
+	bnge_set_max_func_irqs(bd, max_irqs);
+
+	bnge_aux_init_dflt_config(bd);
+
+	rc = bnge_net_init_dflt_config(bd);
+	if (rc) {
+		dev_err(&pdev->dev, "Error setting up default cfg to netdev rc = %d\n",
+			rc);
+		goto err_fw_reg;
+	}
+
+	rc = bnge_map_db_bar(bd);
+	if (rc) {
+		dev_err(&pdev->dev, "Failed mapping doorbell BAR rc = %d, aborting\n",
+			rc);
+		goto err_config_uninit;
+	}
+
+#if BITS_PER_LONG == 32
+	spin_lock_init(&bd->db_lock);
+#endif
+
+	bnge_rdma_aux_device_init(bd);
+
+	rc = bnge_alloc_irqs(bd);
+	if (rc) {
+		dev_err(&pdev->dev, "Error IRQ allocation rc = %d\n", rc);
+		goto err_uninit_auxr;
+	}
+
+	rc = bnge_netdev_alloc(bd, max_irqs);
+	if (rc)
+		goto err_free_irq;
+
+	bnge_rdma_aux_device_add(bd);
+
+	pci_save_state(pdev);
+
+	return 0;
+
+err_free_irq:
+	bnge_free_irqs(bd);
+
+err_uninit_auxr:
+	bnge_rdma_aux_device_uninit(bd);
+
+err_config_uninit:
+	bnge_net_uninit_dflt_config(bd);
+
+err_fw_reg:
+	bnge_devlink_unregister(bd);
+	bnge_fw_unregister_dev(bd);
+
+err_hwrm_cleanup:
+	bnge_cleanup_hwrm_resources(bd);
+
+err_bar_unmap:
+	bnge_unmap_bars(pdev);
+
+err_devl_free:
+	bnge_devlink_free(bd);
+
+err_pci_disable:
+	bnge_pci_disable(pdev);
+	return rc;
+}
+
+static void bnge_remove_one(struct pci_dev *pdev)
+{
+	struct bnge_dev *bd = pci_get_drvdata(pdev);
+
+	bnge_rdma_aux_device_del(bd);
+
+	bnge_netdev_free(bd);
+
+	bnge_free_irqs(bd);
+
+	bnge_rdma_aux_device_uninit(bd);
+
+	bnge_net_uninit_dflt_config(bd);
+
+	bnge_devlink_unregister(bd);
+
+	bnge_fw_unregister_dev(bd);
+
+	bnge_cleanup_hwrm_resources(bd);
+
+	bnge_unmap_bars(pdev);
+
+	bnge_devlink_free(bd);
+
+	bnge_pci_disable(pdev);
+}
+
+static void bnge_shutdown(struct pci_dev *pdev)
+{
+	pci_disable_device(pdev);
+
+	if (system_state == SYSTEM_POWER_OFF) {
+		pci_wake_from_d3(pdev, 0);
+		pci_set_power_state(pdev, PCI_D3hot);
+	}
+}
+
+static struct pci_driver bnge_driver = {
+	.name		= bnge_driver_name,
+	.id_table	= bnge_pci_tbl,
+	.probe		= bnge_probe_one,
+	.remove		= bnge_remove_one,
+	.shutdown	= bnge_shutdown,
+};
+
+static int __init bnge_init_module(void)
+{
+	return pci_register_driver(&bnge_driver);
+}
+module_init(bnge_init_module);
+
+static void __exit bnge_exit_module(void)
+{
+	pci_unregister_driver(&bnge_driver);
+}
+module_exit(bnge_exit_module);
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_db.h b/drivers/net/ethernet/broadcom/bnge/bnge_db.h
new file mode 100644
index 000000000000..950ed582f1d8
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_db.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Broadcom */
+
+#ifndef _BNGE_DB_H_
+#define _BNGE_DB_H_
+
+/* 64-bit doorbell */
+#define DBR_EPOCH_SFT					24
+#define DBR_TOGGLE_SFT					25
+#define DBR_XID_SFT					32
+#define DBR_PATH_L2					(0x1ULL << 56)
+#define DBR_VALID					(0x1ULL << 58)
+#define DBR_TYPE_SQ					(0x0ULL << 60)
+#define DBR_TYPE_SRQ					(0x2ULL << 60)
+#define DBR_TYPE_CQ					(0x4ULL << 60)
+#define DBR_TYPE_CQ_ARMALL				(0x6ULL << 60)
+#define DBR_TYPE_NQ					(0xaULL << 60)
+#define DBR_TYPE_NQ_ARM					(0xbULL << 60)
+#define DBR_TYPE_NQ_MASK				(0xeULL << 60)
+
+struct bnge_db_info {
+	void __iomem		*doorbell;
+	u64			db_key64;
+	u32			db_ring_mask;
+	u32			db_epoch_mask;
+	u8			db_epoch_shift;
+};
+
+#define DB_EPOCH(db, idx)	(((idx) & (db)->db_epoch_mask) <<	\
+				 ((db)->db_epoch_shift))
+#define DB_RING_IDX(db, idx)	(((idx) & (db)->db_ring_mask) |		\
+				 DB_EPOCH(db, idx))
+
+#endif /* _BNGE_DB_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_devlink.c b/drivers/net/ethernet/broadcom/bnge/bnge_devlink.c
new file mode 100644
index 000000000000..a987afebd64d
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_devlink.c
@@ -0,0 +1,306 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2025 Broadcom.
+
+#include <linux/unaligned.h>
+#include <linux/pci.h>
+#include <linux/types.h>
+#include <net/devlink.h>
+
+#include "bnge.h"
+#include "bnge_devlink.h"
+#include "bnge_hwrm_lib.h"
+
+static int bnge_dl_info_put(struct bnge_dev *bd, struct devlink_info_req *req,
+			    enum bnge_dl_version_type type, const char *key,
+			    char *buf)
+{
+	if (!strlen(buf))
+		return 0;
+
+	if (!strcmp(key, DEVLINK_INFO_VERSION_GENERIC_FW_NCSI) ||
+	    !strcmp(key, DEVLINK_INFO_VERSION_GENERIC_FW_ROCE))
+		return 0;
+
+	switch (type) {
+	case BNGE_VERSION_FIXED:
+		return devlink_info_version_fixed_put(req, key, buf);
+	case BNGE_VERSION_RUNNING:
+		return devlink_info_version_running_put(req, key, buf);
+	case BNGE_VERSION_STORED:
+		return devlink_info_version_stored_put(req, key, buf);
+	}
+
+	return 0;
+}
+
+static void bnge_vpd_read_info(struct bnge_dev *bd)
+{
+	struct pci_dev *pdev = bd->pdev;
+	unsigned int vpd_size, kw_len;
+	int pos, size;
+	u8 *vpd_data;
+
+	vpd_data = pci_vpd_alloc(pdev, &vpd_size);
+	if (IS_ERR(vpd_data)) {
+		pci_warn(pdev, "Unable to read VPD\n");
+		return;
+	}
+
+	pos = pci_vpd_find_ro_info_keyword(vpd_data, vpd_size,
+					   PCI_VPD_RO_KEYWORD_PARTNO, &kw_len);
+	if (pos < 0)
+		goto read_sn;
+
+	size = min_t(int, kw_len, BNGE_VPD_FLD_LEN - 1);
+	memcpy(bd->board_partno, &vpd_data[pos], size);
+
+read_sn:
+	pos = pci_vpd_find_ro_info_keyword(vpd_data, vpd_size,
+					   PCI_VPD_RO_KEYWORD_SERIALNO,
+					   &kw_len);
+	if (pos < 0)
+		goto exit;
+
+	size = min_t(int, kw_len, BNGE_VPD_FLD_LEN - 1);
+	memcpy(bd->board_serialno, &vpd_data[pos], size);
+
+exit:
+	kfree(vpd_data);
+}
+
+#define HWRM_FW_VER_STR_LEN	16
+
+static int bnge_devlink_info_get(struct devlink *devlink,
+				 struct devlink_info_req *req,
+				 struct netlink_ext_ack *extack)
+{
+	struct hwrm_nvm_get_dev_info_output nvm_dev_info;
+	struct bnge_dev *bd = devlink_priv(devlink);
+	struct hwrm_ver_get_output *ver_resp;
+	char mgmt_ver[FW_VER_STR_LEN];
+	char roce_ver[FW_VER_STR_LEN];
+	char ncsi_ver[FW_VER_STR_LEN];
+	char buf[32];
+
+	int rc;
+
+	if (bd->dsn) {
+		char buf[32];
+		u8 dsn[8];
+		int rc;
+
+		put_unaligned_le64(bd->dsn, dsn);
+		sprintf(buf, "%02X-%02X-%02X-%02X-%02X-%02X-%02X-%02X",
+			dsn[7], dsn[6], dsn[5], dsn[4],
+			dsn[3], dsn[2], dsn[1], dsn[0]);
+		rc = devlink_info_serial_number_put(req, buf);
+		if (rc) {
+			NL_SET_ERR_MSG_MOD(extack, "Failed to set dsn");
+			return rc;
+		}
+	}
+
+	if (strlen(bd->board_serialno)) {
+		rc = devlink_info_board_serial_number_put(req,
+							  bd->board_serialno);
+		if (rc) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to set board serial number");
+			return rc;
+		}
+	}
+
+	rc = bnge_dl_info_put(bd, req, BNGE_VERSION_FIXED,
+			      DEVLINK_INFO_VERSION_GENERIC_BOARD_ID,
+			      bd->board_partno);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to set board part number");
+		return rc;
+	}
+
+	/* More information from HWRM ver get command */
+	sprintf(buf, "%X", bd->chip_num);
+	rc = bnge_dl_info_put(bd, req, BNGE_VERSION_FIXED,
+			      DEVLINK_INFO_VERSION_GENERIC_ASIC_ID, buf);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to set asic id");
+		return rc;
+	}
+
+	ver_resp = &bd->ver_resp;
+	sprintf(buf, "%c%d", 'A' + ver_resp->chip_rev, ver_resp->chip_metal);
+	rc = bnge_dl_info_put(bd, req, BNGE_VERSION_FIXED,
+			      DEVLINK_INFO_VERSION_GENERIC_ASIC_REV, buf);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to set asic info");
+		return rc;
+	}
+
+	rc = bnge_dl_info_put(bd, req, BNGE_VERSION_RUNNING,
+			      DEVLINK_INFO_VERSION_GENERIC_FW_PSID,
+			      bd->nvm_cfg_ver);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to set firmware version");
+		return rc;
+	}
+
+	buf[0] = 0;
+	strncat(buf, ver_resp->active_pkg_name, HWRM_FW_VER_STR_LEN);
+	rc = bnge_dl_info_put(bd, req, BNGE_VERSION_RUNNING,
+			      DEVLINK_INFO_VERSION_GENERIC_FW, buf);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to set firmware generic version");
+		return rc;
+	}
+
+	if (ver_resp->flags & VER_GET_RESP_FLAGS_EXT_VER_AVAIL) {
+		snprintf(mgmt_ver, FW_VER_STR_LEN, "%d.%d.%d.%d",
+			 ver_resp->hwrm_fw_major, ver_resp->hwrm_fw_minor,
+			 ver_resp->hwrm_fw_build, ver_resp->hwrm_fw_patch);
+
+		snprintf(ncsi_ver, FW_VER_STR_LEN, "%d.%d.%d.%d",
+			 ver_resp->mgmt_fw_major, ver_resp->mgmt_fw_minor,
+			 ver_resp->mgmt_fw_build, ver_resp->mgmt_fw_patch);
+
+		snprintf(roce_ver, FW_VER_STR_LEN, "%d.%d.%d.%d",
+			 ver_resp->roce_fw_major, ver_resp->roce_fw_minor,
+			 ver_resp->roce_fw_build, ver_resp->roce_fw_patch);
+	} else {
+		snprintf(mgmt_ver, FW_VER_STR_LEN, "%d.%d.%d.%d",
+			 ver_resp->hwrm_fw_maj_8b, ver_resp->hwrm_fw_min_8b,
+			 ver_resp->hwrm_fw_bld_8b, ver_resp->hwrm_fw_rsvd_8b);
+
+		snprintf(ncsi_ver, FW_VER_STR_LEN, "%d.%d.%d.%d",
+			 ver_resp->mgmt_fw_maj_8b, ver_resp->mgmt_fw_min_8b,
+			 ver_resp->mgmt_fw_bld_8b, ver_resp->mgmt_fw_rsvd_8b);
+
+		snprintf(roce_ver, FW_VER_STR_LEN, "%d.%d.%d.%d",
+			 ver_resp->roce_fw_maj_8b, ver_resp->roce_fw_min_8b,
+			 ver_resp->roce_fw_bld_8b, ver_resp->roce_fw_rsvd_8b);
+	}
+	rc = bnge_dl_info_put(bd, req, BNGE_VERSION_RUNNING,
+			      DEVLINK_INFO_VERSION_GENERIC_FW_MGMT, mgmt_ver);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to set firmware mgmt version");
+		return rc;
+	}
+
+	rc = bnge_dl_info_put(bd, req, BNGE_VERSION_RUNNING,
+			      DEVLINK_INFO_VERSION_GENERIC_FW_MGMT_API,
+			      bd->hwrm_ver_supp);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to set firmware mgmt api version");
+		return rc;
+	}
+
+	rc = bnge_dl_info_put(bd, req, BNGE_VERSION_RUNNING,
+			      DEVLINK_INFO_VERSION_GENERIC_FW_NCSI, ncsi_ver);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to set ncsi firmware version");
+		return rc;
+	}
+
+	rc = bnge_dl_info_put(bd, req, BNGE_VERSION_RUNNING,
+			      DEVLINK_INFO_VERSION_GENERIC_FW_ROCE, roce_ver);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to set roce firmware version");
+		return rc;
+	}
+
+	rc = bnge_hwrm_nvm_dev_info(bd, &nvm_dev_info);
+	if (!(nvm_dev_info.flags & NVM_GET_DEV_INFO_RESP_FLAGS_FW_VER_VALID))
+		return 0;
+
+	buf[0] = 0;
+	strncat(buf, nvm_dev_info.pkg_name, HWRM_FW_VER_STR_LEN);
+	rc = bnge_dl_info_put(bd, req, BNGE_VERSION_STORED,
+			      DEVLINK_INFO_VERSION_GENERIC_FW, buf);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to set roce firmware version");
+		return rc;
+	}
+
+	snprintf(mgmt_ver, FW_VER_STR_LEN, "%d.%d.%d.%d",
+		 nvm_dev_info.hwrm_fw_major, nvm_dev_info.hwrm_fw_minor,
+		 nvm_dev_info.hwrm_fw_build, nvm_dev_info.hwrm_fw_patch);
+	rc = bnge_dl_info_put(bd, req, BNGE_VERSION_STORED,
+			      DEVLINK_INFO_VERSION_GENERIC_FW_MGMT, mgmt_ver);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to set stored firmware version");
+		return rc;
+	}
+
+	snprintf(ncsi_ver, FW_VER_STR_LEN, "%d.%d.%d.%d",
+		 nvm_dev_info.mgmt_fw_major, nvm_dev_info.mgmt_fw_minor,
+		 nvm_dev_info.mgmt_fw_build, nvm_dev_info.mgmt_fw_patch);
+	rc = bnge_dl_info_put(bd, req, BNGE_VERSION_STORED,
+			      DEVLINK_INFO_VERSION_GENERIC_FW_NCSI, ncsi_ver);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to set stored ncsi firmware version");
+		return rc;
+	}
+
+	snprintf(roce_ver, FW_VER_STR_LEN, "%d.%d.%d.%d",
+		 nvm_dev_info.roce_fw_major, nvm_dev_info.roce_fw_minor,
+		 nvm_dev_info.roce_fw_build, nvm_dev_info.roce_fw_patch);
+	rc = bnge_dl_info_put(bd, req, BNGE_VERSION_STORED,
+			      DEVLINK_INFO_VERSION_GENERIC_FW_ROCE, roce_ver);
+	if (rc)
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to set stored roce firmware version");
+
+	return rc;
+}
+
+static const struct devlink_ops bnge_devlink_ops = {
+	.info_get = bnge_devlink_info_get,
+};
+
+void bnge_devlink_free(struct bnge_dev *bd)
+{
+	struct devlink *devlink = priv_to_devlink(bd);
+
+	devlink_free(devlink);
+}
+
+struct bnge_dev *bnge_devlink_alloc(struct pci_dev *pdev)
+{
+	struct devlink *devlink;
+	struct bnge_dev *bd;
+
+	devlink = devlink_alloc(&bnge_devlink_ops, sizeof(*bd), &pdev->dev);
+	if (!devlink)
+		return NULL;
+
+	bd = devlink_priv(devlink);
+	pci_set_drvdata(pdev, bd);
+	bd->dev = &pdev->dev;
+	bd->pdev = pdev;
+
+	bd->dsn = pci_get_dsn(pdev);
+	if (!bd->dsn)
+		pci_warn(pdev, "Failed to get DSN\n");
+
+	bnge_vpd_read_info(bd);
+
+	return bd;
+}
+
+void bnge_devlink_register(struct bnge_dev *bd)
+{
+	struct devlink *devlink = priv_to_devlink(bd);
+	devlink_register(devlink);
+}
+
+void bnge_devlink_unregister(struct bnge_dev *bd)
+{
+	struct devlink *devlink = priv_to_devlink(bd);
+	devlink_unregister(devlink);
+}
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_devlink.h b/drivers/net/ethernet/broadcom/bnge/bnge_devlink.h
new file mode 100644
index 000000000000..c6575255e650
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_devlink.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Broadcom */
+
+#ifndef _BNGE_DEVLINK_H_
+#define _BNGE_DEVLINK_H_
+
+enum bnge_dl_version_type {
+	BNGE_VERSION_FIXED,
+	BNGE_VERSION_RUNNING,
+	BNGE_VERSION_STORED,
+};
+
+void bnge_devlink_free(struct bnge_dev *bd);
+struct bnge_dev *bnge_devlink_alloc(struct pci_dev *pdev);
+void bnge_devlink_register(struct bnge_dev *bd);
+void bnge_devlink_unregister(struct bnge_dev *bd);
+
+#endif /* _BNGE_DEVLINK_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c b/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c
new file mode 100644
index 000000000000..569371c1b4f2
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2025 Broadcom.
+
+#include <linux/unaligned.h>
+#include <linux/pci.h>
+#include <linux/types.h>
+#include <net/devlink.h>
+#include <linux/ethtool.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool_netlink.h>
+
+#include "bnge.h"
+#include "bnge_ethtool.h"
+
+static void bnge_get_drvinfo(struct net_device *dev,
+			     struct ethtool_drvinfo *info)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+	struct bnge_dev *bd = bn->bd;
+
+	strscpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strscpy(info->fw_version, bd->fw_ver_str, sizeof(info->fw_version));
+	strscpy(info->bus_info, pci_name(bd->pdev), sizeof(info->bus_info));
+}
+
+static const struct ethtool_ops bnge_ethtool_ops = {
+	.get_drvinfo		= bnge_get_drvinfo,
+};
+
+void bnge_set_ethtool_ops(struct net_device *dev)
+{
+	dev->ethtool_ops = &bnge_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.h b/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.h
new file mode 100644
index 000000000000..21e96a0976d5
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Broadcom */
+
+#ifndef _BNGE_ETHTOOL_H_
+#define _BNGE_ETHTOOL_H_
+
+void bnge_set_ethtool_ops(struct net_device *dev);
+
+#endif /* _BNGE_ETHTOOL_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm.c b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm.c
new file mode 100644
index 000000000000..c3087e5cd875
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm.c
@@ -0,0 +1,548 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2025 Broadcom.
+
+#include <asm/byteorder.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+
+#include "bnge.h"
+#include "bnge_hwrm.h"
+
+static u64 bnge_cal_sentinel(struct bnge_hwrm_ctx *ctx, u16 req_type)
+{
+	return (((uintptr_t)ctx) + req_type) ^ BNGE_HWRM_SENTINEL;
+}
+
+int bnge_hwrm_req_create(struct bnge_dev *bd, void **req, u16 req_type,
+			 u32 req_len)
+{
+	struct bnge_hwrm_ctx *ctx;
+	dma_addr_t dma_handle;
+	u8 *req_addr;
+
+	if (req_len > BNGE_HWRM_CTX_OFFSET)
+		return -E2BIG;
+
+	req_addr = dma_pool_alloc(bd->hwrm_dma_pool, GFP_KERNEL | __GFP_ZERO,
+				  &dma_handle);
+	if (!req_addr)
+		return -ENOMEM;
+
+	ctx = (struct bnge_hwrm_ctx *)(req_addr + BNGE_HWRM_CTX_OFFSET);
+	/* safety first, sentinel used to check for invalid requests */
+	ctx->sentinel = bnge_cal_sentinel(ctx, req_type);
+	ctx->req_len = req_len;
+	ctx->req = (struct input *)req_addr;
+	ctx->resp = (struct output *)(req_addr + BNGE_HWRM_RESP_OFFSET);
+	ctx->dma_handle = dma_handle;
+	ctx->flags = 0; /* __GFP_ZERO, but be explicit regarding ownership */
+	ctx->timeout = bd->hwrm_cmd_timeout ?: BNGE_DFLT_HWRM_CMD_TIMEOUT;
+	ctx->allocated = BNGE_HWRM_DMA_SIZE - BNGE_HWRM_CTX_OFFSET;
+	ctx->gfp = GFP_KERNEL;
+	ctx->slice_addr = NULL;
+
+	/* initialize common request fields */
+	ctx->req->req_type = cpu_to_le16(req_type);
+	ctx->req->resp_addr = cpu_to_le64(dma_handle + BNGE_HWRM_RESP_OFFSET);
+	ctx->req->cmpl_ring = cpu_to_le16(BNGE_HWRM_NO_CMPL_RING);
+	ctx->req->target_id = cpu_to_le16(BNGE_HWRM_TARGET);
+	*req = ctx->req;
+
+	return 0;
+}
+
+static struct bnge_hwrm_ctx *__hwrm_ctx_get(struct bnge_dev *bd, u8 *req_addr)
+{
+	void *ctx_addr = req_addr + BNGE_HWRM_CTX_OFFSET;
+	struct input *req = (struct input *)req_addr;
+	struct bnge_hwrm_ctx *ctx = ctx_addr;
+	u64 sentinel;
+
+	if (!req) {
+		dev_err(bd->dev, "null HWRM request");
+		dump_stack();
+		return NULL;
+	}
+
+	/* HWRM API has no type safety, verify sentinel to validate address */
+	sentinel = bnge_cal_sentinel(ctx, le16_to_cpu(req->req_type));
+	if (ctx->sentinel != sentinel) {
+		dev_err(bd->dev, "HWRM sentinel mismatch, req_type = %u\n",
+			(u32)le16_to_cpu(req->req_type));
+		dump_stack();
+		return NULL;
+	}
+
+	return ctx;
+}
+
+void bnge_hwrm_req_timeout(struct bnge_dev *bd,
+			   void *req, unsigned int timeout)
+{
+	struct bnge_hwrm_ctx *ctx = __hwrm_ctx_get(bd, req);
+
+	if (ctx)
+		ctx->timeout = timeout;
+}
+
+void bnge_hwrm_req_alloc_flags(struct bnge_dev *bd, void *req, gfp_t gfp)
+{
+	struct bnge_hwrm_ctx *ctx = __hwrm_ctx_get(bd, req);
+
+	if (ctx)
+		ctx->gfp = gfp;
+}
+
+int bnge_hwrm_req_replace(struct bnge_dev *bd, void *req, void *new_req,
+			  u32 len)
+{
+	struct bnge_hwrm_ctx *ctx = __hwrm_ctx_get(bd, req);
+	struct input *internal_req = req;
+	u16 req_type;
+
+	if (!ctx)
+		return -EINVAL;
+
+	if (len > BNGE_HWRM_CTX_OFFSET)
+		return -E2BIG;
+
+	/* free any existing slices */
+	ctx->allocated = BNGE_HWRM_DMA_SIZE - BNGE_HWRM_CTX_OFFSET;
+	if (ctx->slice_addr) {
+		dma_free_coherent(bd->dev, ctx->slice_size,
+				  ctx->slice_addr, ctx->slice_handle);
+		ctx->slice_addr = NULL;
+	}
+	ctx->gfp = GFP_KERNEL;
+
+	if ((bd->fw_cap & BNGE_FW_CAP_SHORT_CMD) || len > BNGE_HWRM_MAX_REQ_LEN) {
+		memcpy(internal_req, new_req, len);
+	} else {
+		internal_req->req_type = ((struct input *)new_req)->req_type;
+		ctx->req = new_req;
+	}
+
+	ctx->req_len = len;
+	ctx->req->resp_addr = cpu_to_le64(ctx->dma_handle +
+					  BNGE_HWRM_RESP_OFFSET);
+
+	/* update sentinel for potentially new request type */
+	req_type = le16_to_cpu(internal_req->req_type);
+	ctx->sentinel = bnge_cal_sentinel(ctx, req_type);
+
+	return 0;
+}
+
+void bnge_hwrm_req_flags(struct bnge_dev *bd, void *req,
+			 enum bnge_hwrm_ctx_flags flags)
+{
+	struct bnge_hwrm_ctx *ctx = __hwrm_ctx_get(bd, req);
+
+	if (ctx)
+		ctx->flags |= (flags & BNGE_HWRM_API_FLAGS);
+}
+
+void *bnge_hwrm_req_hold(struct bnge_dev *bd, void *req)
+{
+	struct bnge_hwrm_ctx *ctx = __hwrm_ctx_get(bd, req);
+	struct input *input = (struct input *)req;
+
+	if (!ctx)
+		return NULL;
+
+	if (ctx->flags & BNGE_HWRM_INTERNAL_CTX_OWNED) {
+		dev_err(bd->dev, "HWRM context already owned, req_type = %u\n",
+			(u32)le16_to_cpu(input->req_type));
+		dump_stack();
+		return NULL;
+	}
+
+	ctx->flags |= BNGE_HWRM_INTERNAL_CTX_OWNED;
+	return ((u8 *)req) + BNGE_HWRM_RESP_OFFSET;
+}
+
+static void __hwrm_ctx_invalidate(struct bnge_dev *bd,
+				  struct bnge_hwrm_ctx *ctx)
+{
+	void *addr = ((u8 *)ctx) - BNGE_HWRM_CTX_OFFSET;
+	dma_addr_t dma_handle = ctx->dma_handle; /* save before invalidate */
+
+	/* unmap any auxiliary DMA slice */
+	if (ctx->slice_addr)
+		dma_free_coherent(bd->dev, ctx->slice_size,
+				  ctx->slice_addr, ctx->slice_handle);
+
+	/* invalidate, ensure ownership, sentinel and dma_handle are cleared */
+	memset(ctx, 0, sizeof(struct bnge_hwrm_ctx));
+
+	/* return the buffer to the DMA pool */
+	if (dma_handle)
+		dma_pool_free(bd->hwrm_dma_pool, addr, dma_handle);
+}
+
+void bnge_hwrm_req_drop(struct bnge_dev *bd, void *req)
+{
+	struct bnge_hwrm_ctx *ctx = __hwrm_ctx_get(bd, req);
+
+	if (ctx)
+		__hwrm_ctx_invalidate(bd, ctx);
+}
+
+static int bnge_map_hwrm_error(u32 hwrm_err)
+{
+	switch (hwrm_err) {
+	case HWRM_ERR_CODE_SUCCESS:
+		return 0;
+	case HWRM_ERR_CODE_RESOURCE_LOCKED:
+		return -EROFS;
+	case HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED:
+		return -EACCES;
+	case HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR:
+		return -ENOSPC;
+	case HWRM_ERR_CODE_INVALID_PARAMS:
+	case HWRM_ERR_CODE_INVALID_FLAGS:
+	case HWRM_ERR_CODE_INVALID_ENABLES:
+	case HWRM_ERR_CODE_UNSUPPORTED_TLV:
+	case HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR:
+		return -EINVAL;
+	case HWRM_ERR_CODE_NO_BUFFER:
+		return -ENOMEM;
+	case HWRM_ERR_CODE_HOT_RESET_PROGRESS:
+	case HWRM_ERR_CODE_BUSY:
+		return -EAGAIN;
+	case HWRM_ERR_CODE_CMD_NOT_SUPPORTED:
+		return -EOPNOTSUPP;
+	case HWRM_ERR_CODE_PF_UNAVAILABLE:
+		return -ENODEV;
+	default:
+		return -EIO;
+	}
+}
+
+static struct bnge_hwrm_wait_token *
+bnge_hwrm_create_token(struct bnge_dev *bd, enum bnge_hwrm_chnl dst)
+{
+	struct bnge_hwrm_wait_token *token;
+
+	token = kzalloc(sizeof(*token), GFP_KERNEL);
+	if (!token)
+		return NULL;
+
+	mutex_lock(&bd->hwrm_cmd_lock);
+
+	token->dst = dst;
+	token->state = BNGE_HWRM_PENDING;
+	if (dst == BNGE_HWRM_CHNL_CHIMP) {
+		token->seq_id = bd->hwrm_cmd_seq++;
+		hlist_add_head_rcu(&token->node, &bd->hwrm_pending_list);
+	} else {
+		token->seq_id = bd->hwrm_cmd_kong_seq++;
+	}
+
+	return token;
+}
+
+static void
+bnge_hwrm_destroy_token(struct bnge_dev *bd, struct bnge_hwrm_wait_token *token)
+{
+	if (token->dst == BNGE_HWRM_CHNL_CHIMP) {
+		hlist_del_rcu(&token->node);
+		kfree_rcu(token, rcu);
+	} else {
+		kfree(token);
+	}
+	mutex_unlock(&bd->hwrm_cmd_lock);
+}
+
+static void bnge_hwrm_req_dbg(struct bnge_dev *bd, struct input *req)
+{
+	u32 ring = le16_to_cpu(req->cmpl_ring);
+	u32 type = le16_to_cpu(req->req_type);
+	u32 tgt = le16_to_cpu(req->target_id);
+	u32 seq = le16_to_cpu(req->seq_id);
+	char opt[32] = "\n";
+
+	if (unlikely(ring != (u16)BNGE_HWRM_NO_CMPL_RING))
+		snprintf(opt, 16, " ring %d\n", ring);
+
+	if (unlikely(tgt != BNGE_HWRM_TARGET))
+		snprintf(opt + strlen(opt) - 1, 16, " tgt 0x%x\n", tgt);
+
+	dev_dbg(bd->dev, "sent hwrm req_type 0x%x seq id 0x%x%s",
+		type, seq, opt);
+}
+
+#define bnge_hwrm_err(bd, ctx, fmt, ...)		\
+	do {							       \
+		if ((ctx)->flags & BNGE_HWRM_CTX_SILENT)	       \
+			dev_dbg((bd)->dev, fmt, __VA_ARGS__);       \
+		else						       \
+			dev_err((bd)->dev, fmt, __VA_ARGS__);       \
+	} while (0)
+
+static int __hwrm_send_ctx(struct bnge_dev *bd, struct bnge_hwrm_ctx *ctx)
+{
+	u32 doorbell_offset = BNGE_GRCPF_REG_CHIMP_COMM_TRIGGER;
+	enum bnge_hwrm_chnl dst = BNGE_HWRM_CHNL_CHIMP;
+	u32 bar_offset = BNGE_GRCPF_REG_CHIMP_COMM;
+	struct bnge_hwrm_wait_token *token = NULL;
+	u16 max_req_len = BNGE_HWRM_MAX_REQ_LEN;
+	unsigned int i, timeout, tmo_count;
+	u32 *data = (u32 *)ctx->req;
+	u32 msg_len = ctx->req_len;
+	int rc = -EBUSY;
+	u32 req_type;
+	u16 len = 0;
+	u8 *valid;
+
+	if (ctx->flags & BNGE_HWRM_INTERNAL_RESP_DIRTY)
+		memset(ctx->resp, 0, PAGE_SIZE);
+
+	req_type = le16_to_cpu(ctx->req->req_type);
+
+	if (msg_len > BNGE_HWRM_MAX_REQ_LEN &&
+	    msg_len > bd->hwrm_max_ext_req_len) {
+		dev_warn(bd->dev, "oversized hwrm request, req_type 0x%x",
+			 req_type);
+		rc = -E2BIG;
+		goto exit;
+	}
+
+	token = bnge_hwrm_create_token(bd, dst);
+	if (!token) {
+		rc = -ENOMEM;
+		goto exit;
+	}
+	ctx->req->seq_id = cpu_to_le16(token->seq_id);
+
+	/* Ensure any associated DMA buffers are written before doorbell */
+	wmb();
+
+	/* Write request msg to hwrm channel */
+	__iowrite32_copy(bd->bar0 + bar_offset, data, msg_len / 4);
+
+	for (i = msg_len; i < max_req_len; i += 4)
+		writel(0, bd->bar0 + bar_offset + i);
+
+	/* Ring channel doorbell */
+	writel(1, bd->bar0 + doorbell_offset);
+
+	bnge_hwrm_req_dbg(bd, ctx->req);
+
+	/* Limit timeout to an upper limit */
+	timeout = min(ctx->timeout,
+		      bd->hwrm_cmd_max_timeout ?: BNGE_HWRM_CMD_MAX_TIMEOUT);
+	/* convert timeout to usec */
+	timeout *= 1000;
+
+	i = 0;
+	/* Short timeout for the first few iterations:
+	 * number of loops = number of loops for short timeout +
+	 * number of loops for standard timeout.
+	 */
+	tmo_count = BNGE_HWRM_SHORT_TIMEOUT_COUNTER;
+	timeout = timeout - BNGE_HWRM_SHORT_MIN_TIMEOUT *
+			BNGE_HWRM_SHORT_TIMEOUT_COUNTER;
+	tmo_count += DIV_ROUND_UP(timeout, BNGE_HWRM_MIN_TIMEOUT);
+
+	if (le16_to_cpu(ctx->req->cmpl_ring) != INVALID_HW_RING_ID) {
+		/* Wait until hwrm response cmpl interrupt is processed */
+		while (READ_ONCE(token->state) < BNGE_HWRM_COMPLETE &&
+		       i++ < tmo_count) {
+			/* on first few passes, just barely sleep */
+			if (i < BNGE_HWRM_SHORT_TIMEOUT_COUNTER) {
+				usleep_range(BNGE_HWRM_SHORT_MIN_TIMEOUT,
+					     BNGE_HWRM_SHORT_MAX_TIMEOUT);
+			} else {
+				usleep_range(BNGE_HWRM_MIN_TIMEOUT,
+					     BNGE_HWRM_MAX_TIMEOUT);
+			}
+		}
+
+		if (READ_ONCE(token->state) != BNGE_HWRM_COMPLETE) {
+			bnge_hwrm_err(bd, ctx, "No hwrm cmpl received: 0x%x\n",
+				      req_type);
+			goto exit;
+		}
+		len = le16_to_cpu(READ_ONCE(ctx->resp->resp_len));
+		valid = ((u8 *)ctx->resp) + len - 1;
+	} else {
+		__le16 seen_out_of_seq = ctx->req->seq_id; /* will never see */
+		int j;
+
+		/* Check if response len is updated */
+		for (i = 0; i < tmo_count; i++) {
+			if (token &&
+			    READ_ONCE(token->state) == BNGE_HWRM_DEFERRED) {
+				bnge_hwrm_destroy_token(bd, token);
+				token = NULL;
+			}
+
+			len = le16_to_cpu(READ_ONCE(ctx->resp->resp_len));
+			if (len) {
+				__le16 resp_seq = READ_ONCE(ctx->resp->seq_id);
+
+				if (resp_seq == ctx->req->seq_id)
+					break;
+				if (resp_seq != seen_out_of_seq) {
+					dev_warn(bd->dev, "Discarding out of seq response: 0x%x for msg {0x%x 0x%x}\n",
+						 le16_to_cpu(resp_seq), req_type, le16_to_cpu(ctx->req->seq_id));
+					seen_out_of_seq = resp_seq;
+				}
+			}
+
+			/* on first few passes, just barely sleep */
+			if (i < BNGE_HWRM_SHORT_TIMEOUT_COUNTER) {
+				usleep_range(BNGE_HWRM_SHORT_MIN_TIMEOUT,
+					     BNGE_HWRM_SHORT_MAX_TIMEOUT);
+			} else {
+				usleep_range(BNGE_HWRM_MIN_TIMEOUT,
+					     BNGE_HWRM_MAX_TIMEOUT);
+			}
+		}
+
+		if (i >= tmo_count) {
+			bnge_hwrm_err(bd, ctx,
+				      "Error (timeout: %u) msg {0x%x 0x%x} len:%d\n",
+				      bnge_hwrm_timeout(i), req_type,
+				      le16_to_cpu(ctx->req->seq_id), len);
+			goto exit;
+		}
+
+		/* Last byte of resp contains valid bit */
+		valid = ((u8 *)ctx->resp) + len - 1;
+		for (j = 0; j < BNGE_HWRM_FIN_WAIT_USEC; ) {
+			/* make sure we read from updated DMA memory */
+			dma_rmb();
+			if (*valid)
+				break;
+			if (j < 10) {
+				udelay(1);
+				j++;
+			} else {
+				usleep_range(20, 30);
+				j += 20;
+			}
+		}
+
+		if (j >= BNGE_HWRM_FIN_WAIT_USEC) {
+			bnge_hwrm_err(bd, ctx, "Error (timeout: %u) msg {0x%x 0x%x} len:%d v:%d\n",
+				      bnge_hwrm_timeout(i) + j, req_type,
+				      le16_to_cpu(ctx->req->seq_id), len, *valid);
+			goto exit;
+		}
+	}
+
+	/* Zero valid bit for compatibility.  Valid bit in an older spec
+	 * may become a new field in a newer spec.  We must make sure that
+	 * a new field not implemented by old spec will read zero.
+	 */
+	*valid = 0;
+	rc = le16_to_cpu(ctx->resp->error_code);
+	if (rc == HWRM_ERR_CODE_BUSY && !(ctx->flags & BNGE_HWRM_CTX_SILENT))
+		dev_warn(bd->dev, "FW returned busy, hwrm req_type 0x%x\n",
+			 req_type);
+	else if (rc && rc != HWRM_ERR_CODE_PF_UNAVAILABLE)
+		bnge_hwrm_err(bd, ctx, "hwrm req_type 0x%x seq id 0x%x error %d\n",
+			      req_type, le16_to_cpu(ctx->req->seq_id), rc);
+	rc = bnge_map_hwrm_error(rc);
+
+exit:
+	if (token)
+		bnge_hwrm_destroy_token(bd, token);
+	if (ctx->flags & BNGE_HWRM_INTERNAL_CTX_OWNED)
+		ctx->flags |= BNGE_HWRM_INTERNAL_RESP_DIRTY;
+	else
+		__hwrm_ctx_invalidate(bd, ctx);
+	return rc;
+}
+
+int bnge_hwrm_req_send(struct bnge_dev *bd, void *req)
+{
+	struct bnge_hwrm_ctx *ctx = __hwrm_ctx_get(bd, req);
+
+	if (!ctx)
+		return -EINVAL;
+
+	return __hwrm_send_ctx(bd, ctx);
+}
+
+int bnge_hwrm_req_send_silent(struct bnge_dev *bd, void *req)
+{
+	bnge_hwrm_req_flags(bd, req, BNGE_HWRM_CTX_SILENT);
+	return bnge_hwrm_req_send(bd, req);
+}
+
+void *
+bnge_hwrm_req_dma_slice(struct bnge_dev *bd, void *req, u32 size,
+			dma_addr_t *dma_handle)
+{
+	struct bnge_hwrm_ctx *ctx = __hwrm_ctx_get(bd, req);
+	u8 *end = ((u8 *)req) + BNGE_HWRM_DMA_SIZE;
+	struct input *input = req;
+	u8 *addr, *req_addr = req;
+	u32 max_offset, offset;
+
+	if (!ctx)
+		return NULL;
+
+	max_offset = BNGE_HWRM_DMA_SIZE - ctx->allocated;
+	offset = max_offset - size;
+	offset = ALIGN_DOWN(offset, BNGE_HWRM_DMA_ALIGN);
+	addr = req_addr + offset;
+
+	if (addr < req_addr + max_offset && req_addr + ctx->req_len <= addr) {
+		ctx->allocated = end - addr;
+		*dma_handle = ctx->dma_handle + offset;
+		return addr;
+	}
+
+	if (ctx->slice_addr) {
+		dev_err(bd->dev, "HWRM refusing to reallocate DMA slice, req_type = %u\n",
+			(u32)le16_to_cpu(input->req_type));
+		dump_stack();
+		return NULL;
+	}
+
+	addr = dma_alloc_coherent(bd->dev, size, dma_handle, ctx->gfp);
+	if (!addr)
+		return NULL;
+
+	ctx->slice_addr = addr;
+	ctx->slice_size = size;
+	ctx->slice_handle = *dma_handle;
+
+	return addr;
+}
+
+void bnge_cleanup_hwrm_resources(struct bnge_dev *bd)
+{
+	struct bnge_hwrm_wait_token *token;
+
+	dma_pool_destroy(bd->hwrm_dma_pool);
+	bd->hwrm_dma_pool = NULL;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(token, &bd->hwrm_pending_list, node)
+		WRITE_ONCE(token->state, BNGE_HWRM_CANCELLED);
+	rcu_read_unlock();
+}
+
+int bnge_init_hwrm_resources(struct bnge_dev *bd)
+{
+	bd->hwrm_dma_pool = dma_pool_create("bnge_hwrm", bd->dev,
+					    BNGE_HWRM_DMA_SIZE,
+					    BNGE_HWRM_DMA_ALIGN, 0);
+	if (!bd->hwrm_dma_pool)
+		return -ENOMEM;
+
+	INIT_HLIST_HEAD(&bd->hwrm_pending_list);
+	mutex_init(&bd->hwrm_cmd_lock);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm.h b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm.h
new file mode 100644
index 000000000000..6df629761d95
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm.h
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Broadcom */
+
+#ifndef _BNGE_HWRM_H_
+#define _BNGE_HWRM_H_
+
+#include <linux/bnxt/hsi.h>
+
+enum bnge_hwrm_ctx_flags {
+	BNGE_HWRM_INTERNAL_CTX_OWNED	= BIT(0),
+	BNGE_HWRM_INTERNAL_RESP_DIRTY	= BIT(1),
+	BNGE_HWRM_CTX_SILENT		= BIT(2),
+	BNGE_HWRM_FULL_WAIT		= BIT(3),
+};
+
+#define BNGE_HWRM_API_FLAGS (BNGE_HWRM_CTX_SILENT | BNGE_HWRM_FULL_WAIT)
+
+struct bnge_hwrm_ctx {
+	u64 sentinel;
+	dma_addr_t dma_handle;
+	struct output *resp;
+	struct input *req;
+	dma_addr_t slice_handle;
+	void *slice_addr;
+	u32 slice_size;
+	u32 req_len;
+	enum bnge_hwrm_ctx_flags flags;
+	unsigned int timeout;
+	u32 allocated;
+	gfp_t gfp;
+};
+
+enum bnge_hwrm_wait_state {
+	BNGE_HWRM_PENDING,
+	BNGE_HWRM_DEFERRED,
+	BNGE_HWRM_COMPLETE,
+	BNGE_HWRM_CANCELLED,
+};
+
+enum bnge_hwrm_chnl { BNGE_HWRM_CHNL_CHIMP, BNGE_HWRM_CHNL_KONG };
+
+struct bnge_hwrm_wait_token {
+	struct rcu_head rcu;
+	struct hlist_node node;
+	enum bnge_hwrm_wait_state state;
+	enum bnge_hwrm_chnl dst;
+	u16 seq_id;
+};
+
+#define BNGE_DFLT_HWRM_CMD_TIMEOUT		500
+
+#define BNGE_GRCPF_REG_CHIMP_COMM		0x0
+#define BNGE_GRCPF_REG_CHIMP_COMM_TRIGGER	0x100
+
+#define BNGE_HWRM_MAX_REQ_LEN		(bd->hwrm_max_req_len)
+#define BNGE_HWRM_SHORT_REQ_LEN		sizeof(struct hwrm_short_input)
+#define BNGE_HWRM_CMD_MAX_TIMEOUT	40000U
+#define BNGE_SHORT_HWRM_CMD_TIMEOUT	20
+#define BNGE_HWRM_CMD_TIMEOUT		(bd->hwrm_cmd_timeout)
+#define BNGE_HWRM_RESET_TIMEOUT		((BNGE_HWRM_CMD_TIMEOUT) * 4)
+#define BNGE_HWRM_TARGET		0xffff
+#define BNGE_HWRM_NO_CMPL_RING		-1
+#define BNGE_HWRM_REQ_MAX_SIZE		128
+#define BNGE_HWRM_DMA_SIZE		(2 * PAGE_SIZE) /* space for req+resp */
+#define BNGE_HWRM_RESP_RESERVED		PAGE_SIZE
+#define BNGE_HWRM_RESP_OFFSET		(BNGE_HWRM_DMA_SIZE -		\
+					 BNGE_HWRM_RESP_RESERVED)
+#define BNGE_HWRM_CTX_OFFSET		(BNGE_HWRM_RESP_OFFSET -	\
+					 sizeof(struct bnge_hwrm_ctx))
+#define BNGE_HWRM_DMA_ALIGN		16
+#define BNGE_HWRM_SENTINEL		0xb6e1f68a12e9a7eb /* arbitrary value */
+#define BNGE_HWRM_SHORT_MIN_TIMEOUT		3
+#define BNGE_HWRM_SHORT_MAX_TIMEOUT		10
+#define BNGE_HWRM_SHORT_TIMEOUT_COUNTER		5
+
+#define BNGE_HWRM_MIN_TIMEOUT		25
+#define BNGE_HWRM_MAX_TIMEOUT		40
+
+static inline unsigned int bnge_hwrm_timeout(unsigned int n)
+{
+	return n <= BNGE_HWRM_SHORT_TIMEOUT_COUNTER ?
+		n * BNGE_HWRM_SHORT_MIN_TIMEOUT :
+		BNGE_HWRM_SHORT_TIMEOUT_COUNTER *
+			BNGE_HWRM_SHORT_MIN_TIMEOUT +
+			(n - BNGE_HWRM_SHORT_TIMEOUT_COUNTER) *
+				BNGE_HWRM_MIN_TIMEOUT;
+}
+
+#define BNGE_HWRM_FIN_WAIT_USEC	50000
+
+void bnge_cleanup_hwrm_resources(struct bnge_dev *bd);
+int bnge_init_hwrm_resources(struct bnge_dev *bd);
+
+int bnge_hwrm_req_create(struct bnge_dev *bd, void **req, u16 req_type,
+			 u32 req_len);
+#define bnge_hwrm_req_init(bd, req, req_type) \
+	bnge_hwrm_req_create((bd), (void **)&(req), (req_type),	\
+			     sizeof(*(req)))
+void *bnge_hwrm_req_hold(struct bnge_dev *bd, void *req);
+void bnge_hwrm_req_drop(struct bnge_dev *bd, void *req);
+void bnge_hwrm_req_flags(struct bnge_dev *bd, void *req,
+			 enum bnge_hwrm_ctx_flags flags);
+void bnge_hwrm_req_timeout(struct bnge_dev *bd, void *req,
+			   unsigned int timeout);
+int bnge_hwrm_req_send(struct bnge_dev *bd, void *req);
+int bnge_hwrm_req_send_silent(struct bnge_dev *bd, void *req);
+void bnge_hwrm_req_alloc_flags(struct bnge_dev *bd, void *req, gfp_t flags);
+void *bnge_hwrm_req_dma_slice(struct bnge_dev *bd, void *req, u32 size,
+			      dma_addr_t *dma);
+int bnge_hwrm_req_replace(struct bnge_dev *bd, void *req, void *new_req,
+			  u32 len);
+#endif /* _BNGE_HWRM_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c
new file mode 100644
index 000000000000..198f49b40dbf
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c
@@ -0,0 +1,1185 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2025 Broadcom.
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/pci.h>
+#include <linux/bnxt/hsi.h>
+#include <linux/if_vlan.h>
+#include <net/netdev_queues.h>
+
+#include "bnge.h"
+#include "bnge_hwrm.h"
+#include "bnge_hwrm_lib.h"
+#include "bnge_rmem.h"
+#include "bnge_resc.h"
+
+int bnge_hwrm_ver_get(struct bnge_dev *bd)
+{
+	u32 dev_caps_cfg, hwrm_ver, hwrm_spec_code;
+	u16 fw_maj, fw_min, fw_bld, fw_rsv;
+	struct hwrm_ver_get_output *resp;
+	struct hwrm_ver_get_input *req;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_VER_GET);
+	if (rc)
+		return rc;
+
+	bnge_hwrm_req_flags(bd, req, BNGE_HWRM_FULL_WAIT);
+	bd->hwrm_max_req_len = HWRM_MAX_REQ_LEN;
+	req->hwrm_intf_maj = HWRM_VERSION_MAJOR;
+	req->hwrm_intf_min = HWRM_VERSION_MINOR;
+	req->hwrm_intf_upd = HWRM_VERSION_UPDATE;
+
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	if (rc)
+		goto hwrm_ver_get_exit;
+
+	memcpy(&bd->ver_resp, resp, sizeof(struct hwrm_ver_get_output));
+
+	hwrm_spec_code = resp->hwrm_intf_maj_8b << 16 |
+			 resp->hwrm_intf_min_8b << 8 |
+			 resp->hwrm_intf_upd_8b;
+	hwrm_ver = HWRM_VERSION_MAJOR << 16 | HWRM_VERSION_MINOR << 8 |
+			HWRM_VERSION_UPDATE;
+
+	if (hwrm_spec_code > hwrm_ver)
+		snprintf(bd->hwrm_ver_supp, FW_VER_STR_LEN, "%d.%d.%d",
+			 HWRM_VERSION_MAJOR, HWRM_VERSION_MINOR,
+			 HWRM_VERSION_UPDATE);
+	else
+		snprintf(bd->hwrm_ver_supp, FW_VER_STR_LEN, "%d.%d.%d",
+			 resp->hwrm_intf_maj_8b, resp->hwrm_intf_min_8b,
+			 resp->hwrm_intf_upd_8b);
+
+	fw_maj = le16_to_cpu(resp->hwrm_fw_major);
+	fw_min = le16_to_cpu(resp->hwrm_fw_minor);
+	fw_bld = le16_to_cpu(resp->hwrm_fw_build);
+	fw_rsv = le16_to_cpu(resp->hwrm_fw_patch);
+
+	bd->fw_ver_code = BNGE_FW_VER_CODE(fw_maj, fw_min, fw_bld, fw_rsv);
+	snprintf(bd->fw_ver_str, FW_VER_STR_LEN, "%d.%d.%d.%d",
+		 fw_maj, fw_min, fw_bld, fw_rsv);
+
+	if (strlen(resp->active_pkg_name)) {
+		int fw_ver_len = strlen(bd->fw_ver_str);
+
+		snprintf(bd->fw_ver_str + fw_ver_len,
+			 FW_VER_STR_LEN - fw_ver_len - 1, "/pkg %s",
+			 resp->active_pkg_name);
+		bd->fw_cap |= BNGE_FW_CAP_PKG_VER;
+	}
+
+	bd->hwrm_cmd_timeout = le16_to_cpu(resp->def_req_timeout);
+	if (!bd->hwrm_cmd_timeout)
+		bd->hwrm_cmd_timeout = BNGE_DFLT_HWRM_CMD_TIMEOUT;
+	bd->hwrm_cmd_max_timeout = le16_to_cpu(resp->max_req_timeout) * 1000;
+	if (!bd->hwrm_cmd_max_timeout)
+		bd->hwrm_cmd_max_timeout = BNGE_HWRM_CMD_MAX_TIMEOUT;
+	else if (bd->hwrm_cmd_max_timeout > BNGE_HWRM_CMD_MAX_TIMEOUT)
+		dev_warn(bd->dev, "Default HWRM commands max timeout increased to %d seconds\n",
+			 bd->hwrm_cmd_max_timeout / 1000);
+
+	bd->hwrm_max_req_len = le16_to_cpu(resp->max_req_win_len);
+	bd->hwrm_max_ext_req_len = le16_to_cpu(resp->max_ext_req_len);
+
+	if (bd->hwrm_max_ext_req_len < HWRM_MAX_REQ_LEN)
+		bd->hwrm_max_ext_req_len = HWRM_MAX_REQ_LEN;
+
+	bd->chip_num = le16_to_cpu(resp->chip_num);
+	bd->chip_rev = resp->chip_rev;
+
+	dev_caps_cfg = le32_to_cpu(resp->dev_caps_cfg);
+	if ((dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_SUPPORTED) &&
+	    (dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_REQUIRED))
+		bd->fw_cap |= BNGE_FW_CAP_SHORT_CMD;
+
+	if (dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_KONG_MB_CHNL_SUPPORTED)
+		bd->fw_cap |= BNGE_FW_CAP_KONG_MB_CHNL;
+
+	if (dev_caps_cfg &
+	    VER_GET_RESP_DEV_CAPS_CFG_CFA_ADV_FLOW_MGNT_SUPPORTED)
+		bd->fw_cap |= BNGE_FW_CAP_CFA_ADV_FLOW;
+
+hwrm_ver_get_exit:
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+
+int
+bnge_hwrm_nvm_dev_info(struct bnge_dev *bd,
+		       struct hwrm_nvm_get_dev_info_output *nvm_info)
+{
+	struct hwrm_nvm_get_dev_info_output *resp;
+	struct hwrm_nvm_get_dev_info_input *req;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_NVM_GET_DEV_INFO);
+	if (rc)
+		return rc;
+
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	if (!rc)
+		memcpy(nvm_info, resp, sizeof(*resp));
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+
+int bnge_hwrm_func_reset(struct bnge_dev *bd)
+{
+	struct hwrm_func_reset_input *req;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_FUNC_RESET);
+	if (rc)
+		return rc;
+
+	req->enables = 0;
+	bnge_hwrm_req_timeout(bd, req, BNGE_HWRM_RESET_TIMEOUT);
+	return bnge_hwrm_req_send(bd, req);
+}
+
+int bnge_hwrm_fw_set_time(struct bnge_dev *bd)
+{
+	struct hwrm_fw_set_time_input *req;
+	struct tm tm;
+	int rc;
+
+	time64_to_tm(ktime_get_real_seconds(), 0, &tm);
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_FW_SET_TIME);
+	if (rc)
+		return rc;
+
+	req->year = cpu_to_le16(1900 + tm.tm_year);
+	req->month = 1 + tm.tm_mon;
+	req->day = tm.tm_mday;
+	req->hour = tm.tm_hour;
+	req->minute = tm.tm_min;
+	req->second = tm.tm_sec;
+	return bnge_hwrm_req_send(bd, req);
+}
+
+int bnge_hwrm_func_drv_rgtr(struct bnge_dev *bd)
+{
+	struct hwrm_func_drv_rgtr_output *resp;
+	struct hwrm_func_drv_rgtr_input *req;
+	u32 flags;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_FUNC_DRV_RGTR);
+	if (rc)
+		return rc;
+
+	req->enables = cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE |
+				   FUNC_DRV_RGTR_REQ_ENABLES_VER |
+				   FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD);
+
+	req->os_type = cpu_to_le16(FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX);
+	flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE;
+
+	req->flags = cpu_to_le32(flags);
+	req->ver_maj_8b = DRV_VER_MAJ;
+	req->ver_min_8b = DRV_VER_MIN;
+	req->ver_upd_8b = DRV_VER_UPD;
+	req->ver_maj = cpu_to_le16(DRV_VER_MAJ);
+	req->ver_min = cpu_to_le16(DRV_VER_MIN);
+	req->ver_upd = cpu_to_le16(DRV_VER_UPD);
+
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	if (!rc) {
+		set_bit(BNGE_STATE_DRV_REGISTERED, &bd->state);
+		if (resp->flags &
+		    cpu_to_le32(FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED))
+			bd->fw_cap |= BNGE_FW_CAP_IF_CHANGE;
+	}
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+
+int bnge_hwrm_func_drv_unrgtr(struct bnge_dev *bd)
+{
+	struct hwrm_func_drv_unrgtr_input *req;
+	int rc;
+
+	if (!test_and_clear_bit(BNGE_STATE_DRV_REGISTERED, &bd->state))
+		return 0;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_FUNC_DRV_UNRGTR);
+	if (rc)
+		return rc;
+	return bnge_hwrm_req_send(bd, req);
+}
+
+static void bnge_init_ctx_initializer(struct bnge_ctx_mem_type *ctxm,
+				      u8 init_val, u8 init_offset,
+				      bool init_mask_set)
+{
+	ctxm->init_value = init_val;
+	ctxm->init_offset = BNGE_CTX_INIT_INVALID_OFFSET;
+	if (init_mask_set)
+		ctxm->init_offset = init_offset * 4;
+	else
+		ctxm->init_value = 0;
+}
+
+static int bnge_alloc_all_ctx_pg_info(struct bnge_dev *bd, int ctx_max)
+{
+	struct bnge_ctx_mem_info *ctx = bd->ctx;
+	u16 type;
+
+	for (type = 0; type < ctx_max; type++) {
+		struct bnge_ctx_mem_type *ctxm = &ctx->ctx_arr[type];
+		int n = 1;
+
+		if (!ctxm->max_entries)
+			continue;
+
+		if (ctxm->instance_bmap)
+			n = hweight32(ctxm->instance_bmap);
+		ctxm->pg_info = kcalloc(n, sizeof(*ctxm->pg_info), GFP_KERNEL);
+		if (!ctxm->pg_info)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+#define BNGE_CTX_INIT_VALID(flags)	\
+	(!!((flags) &			\
+	    FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT))
+
+int bnge_hwrm_func_backing_store_qcaps(struct bnge_dev *bd)
+{
+	struct hwrm_func_backing_store_qcaps_v2_output *resp;
+	struct hwrm_func_backing_store_qcaps_v2_input *req;
+	struct bnge_ctx_mem_info *ctx;
+	u16 type;
+	int rc;
+
+	if (bd->ctx)
+		return 0;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_FUNC_BACKING_STORE_QCAPS_V2);
+	if (rc)
+		return rc;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	bd->ctx = ctx;
+
+	resp = bnge_hwrm_req_hold(bd, req);
+
+	for (type = 0; type < BNGE_CTX_V2_MAX; ) {
+		struct bnge_ctx_mem_type *ctxm = &ctx->ctx_arr[type];
+		u8 init_val, init_off, i;
+		__le32 *p;
+		u32 flags;
+
+		req->type = cpu_to_le16(type);
+		rc = bnge_hwrm_req_send(bd, req);
+		if (rc)
+			goto ctx_done;
+		flags = le32_to_cpu(resp->flags);
+		type = le16_to_cpu(resp->next_valid_type);
+		if (!(flags &
+		      FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID))
+			continue;
+
+		ctxm->type = le16_to_cpu(resp->type);
+		ctxm->entry_size = le16_to_cpu(resp->entry_size);
+		ctxm->flags = flags;
+		ctxm->instance_bmap = le32_to_cpu(resp->instance_bit_map);
+		ctxm->entry_multiple = resp->entry_multiple;
+		ctxm->max_entries = le32_to_cpu(resp->max_num_entries);
+		ctxm->min_entries = le32_to_cpu(resp->min_num_entries);
+		init_val = resp->ctx_init_value;
+		init_off = resp->ctx_init_offset;
+		bnge_init_ctx_initializer(ctxm, init_val, init_off,
+					  BNGE_CTX_INIT_VALID(flags));
+		ctxm->split_entry_cnt = min_t(u8, resp->subtype_valid_cnt,
+					      BNGE_MAX_SPLIT_ENTRY);
+		for (i = 0, p = &resp->split_entry_0; i < ctxm->split_entry_cnt;
+		     i++, p++)
+			ctxm->split[i] = le32_to_cpu(*p);
+	}
+	rc = bnge_alloc_all_ctx_pg_info(bd, BNGE_CTX_V2_MAX);
+
+ctx_done:
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+
+static void bnge_hwrm_set_pg_attr(struct bnge_ring_mem_info *rmem, u8 *pg_attr,
+				  __le64 *pg_dir)
+{
+	if (!rmem->nr_pages)
+		return;
+
+	BNGE_SET_CTX_PAGE_ATTR(*pg_attr);
+	if (rmem->depth >= 1) {
+		if (rmem->depth == 2)
+			*pg_attr |= 2;
+		else
+			*pg_attr |= 1;
+		*pg_dir = cpu_to_le64(rmem->dma_pg_tbl);
+	} else {
+		*pg_dir = cpu_to_le64(rmem->dma_arr[0]);
+	}
+}
+
+int bnge_hwrm_func_backing_store(struct bnge_dev *bd,
+				 struct bnge_ctx_mem_type *ctxm,
+				 bool last)
+{
+	struct hwrm_func_backing_store_cfg_v2_input *req;
+	u32 instance_bmap = ctxm->instance_bmap;
+	int i, j, rc = 0, n = 1;
+	__le32 *p;
+
+	if (!(ctxm->flags & BNGE_CTX_MEM_TYPE_VALID) || !ctxm->pg_info)
+		return 0;
+
+	if (instance_bmap)
+		n = hweight32(ctxm->instance_bmap);
+	else
+		instance_bmap = 1;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_FUNC_BACKING_STORE_CFG_V2);
+	if (rc)
+		return rc;
+	bnge_hwrm_req_hold(bd, req);
+	req->type = cpu_to_le16(ctxm->type);
+	req->entry_size = cpu_to_le16(ctxm->entry_size);
+	req->subtype_valid_cnt = ctxm->split_entry_cnt;
+	for (i = 0, p = &req->split_entry_0; i < ctxm->split_entry_cnt; i++)
+		p[i] = cpu_to_le32(ctxm->split[i]);
+	for (i = 0, j = 0; j < n && !rc; i++) {
+		struct bnge_ctx_pg_info *ctx_pg;
+
+		if (!(instance_bmap & (1 << i)))
+			continue;
+		req->instance = cpu_to_le16(i);
+		ctx_pg = &ctxm->pg_info[j++];
+		if (!ctx_pg->entries)
+			continue;
+		req->num_entries = cpu_to_le32(ctx_pg->entries);
+		bnge_hwrm_set_pg_attr(&ctx_pg->ring_mem,
+				      &req->page_size_pbl_level,
+				      &req->page_dir);
+		if (last && j == n)
+			req->flags =
+				cpu_to_le32(BNGE_BS_CFG_ALL_DONE);
+		rc = bnge_hwrm_req_send(bd, req);
+	}
+	bnge_hwrm_req_drop(bd, req);
+
+	return rc;
+}
+
+static int bnge_hwrm_get_rings(struct bnge_dev *bd)
+{
+	struct bnge_hw_resc *hw_resc = &bd->hw_resc;
+	struct hwrm_func_qcfg_output *resp;
+	struct hwrm_func_qcfg_input *req;
+	u16 cp, stats;
+	u16 rx, tx;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_FUNC_QCFG);
+	if (rc)
+		return rc;
+
+	req->fid = cpu_to_le16(0xffff);
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	if (rc) {
+		bnge_hwrm_req_drop(bd, req);
+		return rc;
+	}
+
+	hw_resc->resv_tx_rings = le16_to_cpu(resp->alloc_tx_rings);
+	hw_resc->resv_rx_rings = le16_to_cpu(resp->alloc_rx_rings);
+	hw_resc->resv_hw_ring_grps =
+		le32_to_cpu(resp->alloc_hw_ring_grps);
+	hw_resc->resv_vnics = le16_to_cpu(resp->alloc_vnics);
+	hw_resc->resv_rsscos_ctxs = le16_to_cpu(resp->alloc_rsscos_ctx);
+	cp = le16_to_cpu(resp->alloc_cmpl_rings);
+	stats = le16_to_cpu(resp->alloc_stat_ctx);
+	hw_resc->resv_irqs = cp;
+	rx = hw_resc->resv_rx_rings;
+	tx = hw_resc->resv_tx_rings;
+	if (bnge_is_agg_reqd(bd))
+		rx >>= 1;
+	if (cp < (rx + tx)) {
+		rc = bnge_fix_rings_count(&rx, &tx, cp, false);
+		if (rc)
+			goto get_rings_exit;
+		if (bnge_is_agg_reqd(bd))
+			rx <<= 1;
+		hw_resc->resv_rx_rings = rx;
+		hw_resc->resv_tx_rings = tx;
+	}
+	hw_resc->resv_irqs = le16_to_cpu(resp->alloc_msix);
+	hw_resc->resv_hw_ring_grps = rx;
+	hw_resc->resv_cp_rings = cp;
+	hw_resc->resv_stat_ctxs = stats;
+
+get_rings_exit:
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+
+static struct hwrm_func_cfg_input *
+__bnge_hwrm_reserve_pf_rings(struct bnge_dev *bd, struct bnge_hw_rings *hwr)
+{
+	struct hwrm_func_cfg_input *req;
+	u32 enables = 0;
+
+	if (bnge_hwrm_req_init(bd, req, HWRM_FUNC_QCFG))
+		return NULL;
+
+	req->fid = cpu_to_le16(0xffff);
+	enables |= hwr->tx ? FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS : 0;
+	req->num_tx_rings = cpu_to_le16(hwr->tx);
+
+	enables |= hwr->rx ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0;
+	enables |= hwr->stat ? FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+	enables |= hwr->nq ? FUNC_CFG_REQ_ENABLES_NUM_MSIX : 0;
+	enables |= hwr->cmpl ? FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
+	enables |= hwr->vnic ? FUNC_CFG_REQ_ENABLES_NUM_VNICS : 0;
+	enables |= hwr->rss_ctx ? FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
+
+	req->num_rx_rings = cpu_to_le16(hwr->rx);
+	req->num_rsscos_ctxs = cpu_to_le16(hwr->rss_ctx);
+	req->num_cmpl_rings = cpu_to_le16(hwr->cmpl);
+	req->num_msix = cpu_to_le16(hwr->nq);
+	req->num_stat_ctxs = cpu_to_le16(hwr->stat);
+	req->num_vnics = cpu_to_le16(hwr->vnic);
+	req->enables = cpu_to_le32(enables);
+
+	return req;
+}
+
+static int
+bnge_hwrm_reserve_pf_rings(struct bnge_dev *bd, struct bnge_hw_rings *hwr)
+{
+	struct hwrm_func_cfg_input *req;
+	int rc;
+
+	req = __bnge_hwrm_reserve_pf_rings(bd, hwr);
+	if (!req)
+		return -ENOMEM;
+
+	if (!req->enables) {
+		bnge_hwrm_req_drop(bd, req);
+		return 0;
+	}
+
+	rc = bnge_hwrm_req_send(bd, req);
+	if (rc)
+		return rc;
+
+	return bnge_hwrm_get_rings(bd);
+}
+
+int bnge_hwrm_reserve_rings(struct bnge_dev *bd, struct bnge_hw_rings *hwr)
+{
+	return bnge_hwrm_reserve_pf_rings(bd, hwr);
+}
+
+int bnge_hwrm_func_qcfg(struct bnge_dev *bd)
+{
+	struct hwrm_func_qcfg_output *resp;
+	struct hwrm_func_qcfg_input *req;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_FUNC_QCFG);
+	if (rc)
+		return rc;
+
+	req->fid = cpu_to_le16(0xffff);
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	if (rc)
+		goto func_qcfg_exit;
+
+	bd->max_mtu = le16_to_cpu(resp->max_mtu_configured);
+	if (!bd->max_mtu)
+		bd->max_mtu = BNGE_MAX_MTU;
+
+	if (bd->db_size)
+		goto func_qcfg_exit;
+
+	bd->db_offset = le16_to_cpu(resp->legacy_l2_db_size_kb) * 1024;
+	bd->db_size = PAGE_ALIGN(le16_to_cpu(resp->l2_doorbell_bar_size_kb) *
+			1024);
+	if (!bd->db_size || bd->db_size > pci_resource_len(bd->pdev, 2) ||
+	    bd->db_size <= bd->db_offset)
+		bd->db_size = pci_resource_len(bd->pdev, 2);
+
+func_qcfg_exit:
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+
+int bnge_hwrm_func_resc_qcaps(struct bnge_dev *bd)
+{
+	struct hwrm_func_resource_qcaps_output *resp;
+	struct bnge_hw_resc *hw_resc = &bd->hw_resc;
+	struct hwrm_func_resource_qcaps_input *req;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_FUNC_RESOURCE_QCAPS);
+	if (rc)
+		return rc;
+
+	req->fid = cpu_to_le16(0xffff);
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send_silent(bd, req);
+	if (rc)
+		goto hwrm_func_resc_qcaps_exit;
+
+	hw_resc->max_tx_sch_inputs = le16_to_cpu(resp->max_tx_scheduler_inputs);
+	hw_resc->min_rsscos_ctxs = le16_to_cpu(resp->min_rsscos_ctx);
+	hw_resc->max_rsscos_ctxs = le16_to_cpu(resp->max_rsscos_ctx);
+	hw_resc->min_cp_rings = le16_to_cpu(resp->min_cmpl_rings);
+	hw_resc->max_cp_rings = le16_to_cpu(resp->max_cmpl_rings);
+	hw_resc->min_tx_rings = le16_to_cpu(resp->min_tx_rings);
+	hw_resc->max_tx_rings = le16_to_cpu(resp->max_tx_rings);
+	hw_resc->min_rx_rings = le16_to_cpu(resp->min_rx_rings);
+	hw_resc->max_rx_rings = le16_to_cpu(resp->max_rx_rings);
+	hw_resc->min_hw_ring_grps = le16_to_cpu(resp->min_hw_ring_grps);
+	hw_resc->max_hw_ring_grps = le16_to_cpu(resp->max_hw_ring_grps);
+	hw_resc->min_l2_ctxs = le16_to_cpu(resp->min_l2_ctxs);
+	hw_resc->max_l2_ctxs = le16_to_cpu(resp->max_l2_ctxs);
+	hw_resc->min_vnics = le16_to_cpu(resp->min_vnics);
+	hw_resc->max_vnics = le16_to_cpu(resp->max_vnics);
+	hw_resc->min_stat_ctxs = le16_to_cpu(resp->min_stat_ctx);
+	hw_resc->max_stat_ctxs = le16_to_cpu(resp->max_stat_ctx);
+
+	hw_resc->max_nqs = le16_to_cpu(resp->max_msix);
+	hw_resc->max_hw_ring_grps = hw_resc->max_rx_rings;
+
+hwrm_func_resc_qcaps_exit:
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+
+int bnge_hwrm_func_qcaps(struct bnge_dev *bd)
+{
+	struct hwrm_func_qcaps_output *resp;
+	struct hwrm_func_qcaps_input *req;
+	struct bnge_pf_info *pf = &bd->pf;
+	u32 flags;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_FUNC_QCAPS);
+	if (rc)
+		return rc;
+
+	req->fid = cpu_to_le16(0xffff);
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	if (rc)
+		goto hwrm_func_qcaps_exit;
+
+	flags = le32_to_cpu(resp->flags);
+	if (flags & FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED)
+		bd->flags |= BNGE_EN_ROCE_V1;
+	if (flags & FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED)
+		bd->flags |= BNGE_EN_ROCE_V2;
+
+	pf->fw_fid = le16_to_cpu(resp->fid);
+	pf->port_id = le16_to_cpu(resp->port_id);
+	memcpy(pf->mac_addr, resp->mac_address, ETH_ALEN);
+
+	bd->tso_max_segs = le16_to_cpu(resp->max_tso_segs);
+
+hwrm_func_qcaps_exit:
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+
+int bnge_hwrm_vnic_qcaps(struct bnge_dev *bd)
+{
+	struct hwrm_vnic_qcaps_output *resp;
+	struct hwrm_vnic_qcaps_input *req;
+	int rc;
+
+	bd->hw_ring_stats_size = sizeof(struct ctx_hw_stats);
+	bd->rss_cap &= ~BNGE_RSS_CAP_NEW_RSS_CAP;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_VNIC_QCAPS);
+	if (rc)
+		return rc;
+
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	if (!rc) {
+		u32 flags = le32_to_cpu(resp->flags);
+
+		if (flags & VNIC_QCAPS_RESP_FLAGS_VLAN_STRIP_CAP)
+			bd->fw_cap |= BNGE_FW_CAP_VLAN_RX_STRIP;
+		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_HASH_TYPE_DELTA_CAP)
+			bd->rss_cap |= BNGE_RSS_CAP_RSS_HASH_TYPE_DELTA;
+		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_PROF_TCAM_MODE_ENABLED)
+			bd->rss_cap |= BNGE_RSS_CAP_RSS_TCAM;
+		bd->max_tpa_v2 = le16_to_cpu(resp->max_aggs_supported);
+		if (bd->max_tpa_v2)
+			bd->hw_ring_stats_size = BNGE_RING_STATS_SIZE;
+		if (flags & VNIC_QCAPS_RESP_FLAGS_HW_TUNNEL_TPA_CAP)
+			bd->fw_cap |= BNGE_FW_CAP_VNIC_TUNNEL_TPA;
+		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_AH_SPI_IPV4_CAP)
+			bd->rss_cap |= BNGE_RSS_CAP_AH_V4_RSS_CAP;
+		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_AH_SPI_IPV6_CAP)
+			bd->rss_cap |= BNGE_RSS_CAP_AH_V6_RSS_CAP;
+		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV4_CAP)
+			bd->rss_cap |= BNGE_RSS_CAP_ESP_V4_RSS_CAP;
+		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV6_CAP)
+			bd->rss_cap |= BNGE_RSS_CAP_ESP_V6_RSS_CAP;
+	}
+	bnge_hwrm_req_drop(bd, req);
+
+	return rc;
+}
+
+#define BNGE_CNPQ(q_profile)	\
+		((q_profile) ==	\
+		 QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY_ROCE_CNP)
+
+int bnge_hwrm_queue_qportcfg(struct bnge_dev *bd)
+{
+	struct hwrm_queue_qportcfg_output *resp;
+	struct hwrm_queue_qportcfg_input *req;
+	u8 i, j, *qptr;
+	bool no_rdma;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_QUEUE_QPORTCFG);
+	if (rc)
+		return rc;
+
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	if (rc)
+		goto qportcfg_exit;
+
+	if (!resp->max_configurable_queues) {
+		rc = -EINVAL;
+		goto qportcfg_exit;
+	}
+	bd->max_tc = resp->max_configurable_queues;
+	bd->max_lltc = resp->max_configurable_lossless_queues;
+	if (bd->max_tc > BNGE_MAX_QUEUE)
+		bd->max_tc = BNGE_MAX_QUEUE;
+
+	no_rdma = !bnge_is_roce_en(bd);
+	qptr = &resp->queue_id0;
+	for (i = 0, j = 0; i < bd->max_tc; i++) {
+		bd->q_info[j].queue_id = *qptr;
+		bd->q_ids[i] = *qptr++;
+		bd->q_info[j].queue_profile = *qptr++;
+		bd->tc_to_qidx[j] = j;
+		if (!BNGE_CNPQ(bd->q_info[j].queue_profile) || no_rdma)
+			j++;
+	}
+	bd->max_q = bd->max_tc;
+	bd->max_tc = max_t(u8, j, 1);
+
+	if (resp->queue_cfg_info & QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG)
+		bd->max_tc = 1;
+
+	if (bd->max_lltc > bd->max_tc)
+		bd->max_lltc = bd->max_tc;
+
+qportcfg_exit:
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+
+int bnge_hwrm_vnic_set_hds(struct bnge_net *bn, struct bnge_vnic_info *vnic)
+{
+	u16 hds_thresh = (u16)bn->netdev->cfg_pending->hds_thresh;
+	struct hwrm_vnic_plcmodes_cfg_input *req;
+	struct bnge_dev *bd = bn->bd;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_VNIC_PLCMODES_CFG);
+	if (rc)
+		return rc;
+
+	req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT);
+	req->enables = cpu_to_le32(BNGE_PLC_EN_JUMBO_THRES_VALID);
+	req->jumbo_thresh = cpu_to_le16(bn->rx_buf_use_size);
+
+	if (bnge_is_agg_reqd(bd)) {
+		req->flags |= cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 |
+					  VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6);
+		req->enables |=
+			cpu_to_le32(BNGE_PLC_EN_HDS_THRES_VALID);
+		req->hds_threshold = cpu_to_le16(hds_thresh);
+	}
+	req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
+	return bnge_hwrm_req_send(bd, req);
+}
+
+int bnge_hwrm_vnic_ctx_alloc(struct bnge_dev *bd,
+			     struct bnge_vnic_info *vnic, u16 ctx_idx)
+{
+	struct hwrm_vnic_rss_cos_lb_ctx_alloc_output *resp;
+	struct hwrm_vnic_rss_cos_lb_ctx_alloc_input *req;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_VNIC_RSS_COS_LB_CTX_ALLOC);
+	if (rc)
+		return rc;
+
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	if (!rc)
+		vnic->fw_rss_cos_lb_ctx[ctx_idx] =
+			le16_to_cpu(resp->rss_cos_lb_ctx_id);
+	bnge_hwrm_req_drop(bd, req);
+
+	return rc;
+}
+
+static void
+__bnge_hwrm_vnic_set_rss(struct bnge_net *bn,
+			 struct hwrm_vnic_rss_cfg_input *req,
+			 struct bnge_vnic_info *vnic)
+{
+	struct bnge_dev *bd = bn->bd;
+
+	bnge_fill_hw_rss_tbl(bn, vnic);
+	req->flags |= VNIC_RSS_CFG_REQ_FLAGS_IPSEC_HASH_TYPE_CFG_SUPPORT;
+
+	req->hash_type = cpu_to_le32(bd->rss_hash_cfg);
+	req->hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT;
+	req->ring_grp_tbl_addr = cpu_to_le64(vnic->rss_table_dma_addr);
+	req->hash_key_tbl_addr = cpu_to_le64(vnic->rss_hash_key_dma_addr);
+}
+
+int bnge_hwrm_vnic_set_rss(struct bnge_net *bn,
+			   struct bnge_vnic_info *vnic, bool set_rss)
+{
+	struct hwrm_vnic_rss_cfg_input *req;
+	struct bnge_dev *bd = bn->bd;
+	dma_addr_t ring_tbl_map;
+	u32 i, nr_ctxs;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_VNIC_RSS_CFG);
+	if (rc)
+		return rc;
+
+	req->vnic_id = cpu_to_le16(vnic->fw_vnic_id);
+	if (!set_rss)
+		return bnge_hwrm_req_send(bd, req);
+
+	__bnge_hwrm_vnic_set_rss(bn, req, vnic);
+	ring_tbl_map = vnic->rss_table_dma_addr;
+	nr_ctxs = bnge_cal_nr_rss_ctxs(bd->rx_nr_rings);
+
+	bnge_hwrm_req_hold(bd, req);
+	for (i = 0; i < nr_ctxs; ring_tbl_map += BNGE_RSS_TABLE_SIZE, i++) {
+		req->ring_grp_tbl_addr = cpu_to_le64(ring_tbl_map);
+		req->ring_table_pair_index = i;
+		req->rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[i]);
+		rc = bnge_hwrm_req_send(bd, req);
+		if (rc)
+			goto exit;
+	}
+
+exit:
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+
+int bnge_hwrm_vnic_cfg(struct bnge_net *bn, struct bnge_vnic_info *vnic)
+{
+	struct bnge_rx_ring_info *rxr = &bn->rx_ring[0];
+	struct hwrm_vnic_cfg_input *req;
+	struct bnge_dev *bd = bn->bd;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_VNIC_CFG);
+	if (rc)
+		return rc;
+
+	req->default_rx_ring_id =
+		cpu_to_le16(rxr->rx_ring_struct.fw_ring_id);
+	req->default_cmpl_ring_id =
+		cpu_to_le16(bnge_cp_ring_for_rx(rxr));
+	req->enables =
+		cpu_to_le32(VNIC_CFG_REQ_ENABLES_DEFAULT_RX_RING_ID |
+			    VNIC_CFG_REQ_ENABLES_DEFAULT_CMPL_RING_ID);
+	vnic->mru = bd->netdev->mtu + ETH_HLEN + VLAN_HLEN;
+	req->mru = cpu_to_le16(vnic->mru);
+
+	req->vnic_id = cpu_to_le16(vnic->fw_vnic_id);
+
+	if (bd->flags & BNGE_EN_STRIP_VLAN)
+		req->flags |= cpu_to_le32(VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE);
+	if (vnic->vnic_id == BNGE_VNIC_DEFAULT && bnge_aux_registered(bd))
+		req->flags |= cpu_to_le32(BNGE_VNIC_CFG_ROCE_DUAL_MODE);
+
+	return bnge_hwrm_req_send(bd, req);
+}
+
+void bnge_hwrm_update_rss_hash_cfg(struct bnge_net *bn)
+{
+	struct bnge_vnic_info *vnic = &bn->vnic_info[BNGE_VNIC_DEFAULT];
+	struct hwrm_vnic_rss_qcfg_output *resp;
+	struct hwrm_vnic_rss_qcfg_input *req;
+	struct bnge_dev *bd = bn->bd;
+
+	if (bnge_hwrm_req_init(bd, req, HWRM_VNIC_RSS_QCFG))
+		return;
+
+	req->vnic_id = cpu_to_le16(vnic->fw_vnic_id);
+	/* all contexts configured to same hash_type, zero always exists */
+	req->rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[0]);
+	resp = bnge_hwrm_req_hold(bd, req);
+	if (!bnge_hwrm_req_send(bd, req))
+		bd->rss_hash_cfg =
+			le32_to_cpu(resp->hash_type) ?: bd->rss_hash_cfg;
+	bnge_hwrm_req_drop(bd, req);
+}
+
+int bnge_hwrm_l2_filter_free(struct bnge_dev *bd, struct bnge_l2_filter *fltr)
+{
+	struct hwrm_cfa_l2_filter_free_input *req;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_CFA_L2_FILTER_FREE);
+	if (rc)
+		return rc;
+
+	req->l2_filter_id = fltr->base.filter_id;
+	return bnge_hwrm_req_send(bd, req);
+}
+
+int bnge_hwrm_l2_filter_alloc(struct bnge_dev *bd, struct bnge_l2_filter *fltr)
+{
+	struct hwrm_cfa_l2_filter_alloc_output *resp;
+	struct hwrm_cfa_l2_filter_alloc_input *req;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_CFA_L2_FILTER_ALLOC);
+	if (rc)
+		return rc;
+
+	req->flags = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX);
+
+	req->flags |= cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST);
+	req->dst_id = cpu_to_le16(fltr->base.fw_vnic_id);
+	req->enables =
+		cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR |
+			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID |
+			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK);
+	ether_addr_copy(req->l2_addr, fltr->l2_key.dst_mac_addr);
+	eth_broadcast_addr(req->l2_addr_mask);
+
+	if (fltr->l2_key.vlan) {
+		req->enables |=
+			cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN |
+				CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN_MASK |
+				CFA_L2_FILTER_ALLOC_REQ_ENABLES_NUM_VLANS);
+		req->num_vlans = 1;
+		req->l2_ivlan = cpu_to_le16(fltr->l2_key.vlan);
+		req->l2_ivlan_mask = cpu_to_le16(0xfff);
+	}
+
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	if (!rc)
+		fltr->base.filter_id = resp->l2_filter_id;
+
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+
+int bnge_hwrm_cfa_l2_set_rx_mask(struct bnge_dev *bd,
+				 struct bnge_vnic_info *vnic)
+{
+	struct hwrm_cfa_l2_set_rx_mask_input *req;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_CFA_L2_SET_RX_MASK);
+	if (rc)
+		return rc;
+
+	req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
+	if (vnic->rx_mask & CFA_L2_SET_RX_MASK_REQ_MASK_MCAST) {
+		req->num_mc_entries = cpu_to_le32(vnic->mc_list_count);
+		req->mc_tbl_addr = cpu_to_le64(vnic->mc_list_mapping);
+	}
+	req->mask = cpu_to_le32(vnic->rx_mask);
+	return bnge_hwrm_req_send_silent(bd, req);
+}
+
+int bnge_hwrm_vnic_alloc(struct bnge_dev *bd, struct bnge_vnic_info *vnic,
+			 unsigned int nr_rings)
+{
+	struct hwrm_vnic_alloc_output *resp;
+	struct hwrm_vnic_alloc_input *req;
+	unsigned int i;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_VNIC_ALLOC);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < BNGE_MAX_CTX_PER_VNIC; i++)
+		vnic->fw_rss_cos_lb_ctx[i] = INVALID_HW_RING_ID;
+	if (vnic->vnic_id == BNGE_VNIC_DEFAULT)
+		req->flags = cpu_to_le32(VNIC_ALLOC_REQ_FLAGS_DEFAULT);
+
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	if (!rc)
+		vnic->fw_vnic_id = le32_to_cpu(resp->vnic_id);
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+
+void bnge_hwrm_vnic_free_one(struct bnge_dev *bd, struct bnge_vnic_info *vnic)
+{
+	if (vnic->fw_vnic_id != INVALID_HW_RING_ID) {
+		struct hwrm_vnic_free_input *req;
+
+		if (bnge_hwrm_req_init(bd, req, HWRM_VNIC_FREE))
+			return;
+
+		req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
+
+		bnge_hwrm_req_send(bd, req);
+		vnic->fw_vnic_id = INVALID_HW_RING_ID;
+	}
+}
+
+void bnge_hwrm_vnic_ctx_free_one(struct bnge_dev *bd,
+				 struct bnge_vnic_info *vnic, u16 ctx_idx)
+{
+	struct hwrm_vnic_rss_cos_lb_ctx_free_input *req;
+
+	if (bnge_hwrm_req_init(bd, req, HWRM_VNIC_RSS_COS_LB_CTX_FREE))
+		return;
+
+	req->rss_cos_lb_ctx_id =
+		cpu_to_le16(vnic->fw_rss_cos_lb_ctx[ctx_idx]);
+
+	bnge_hwrm_req_send(bd, req);
+	vnic->fw_rss_cos_lb_ctx[ctx_idx] = INVALID_HW_RING_ID;
+}
+
+void bnge_hwrm_stat_ctx_free(struct bnge_net *bn)
+{
+	struct hwrm_stat_ctx_free_input *req;
+	struct bnge_dev *bd = bn->bd;
+	int i;
+
+	if (bnge_hwrm_req_init(bd, req, HWRM_STAT_CTX_FREE))
+		return;
+
+	bnge_hwrm_req_hold(bd, req);
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		struct bnge_napi *bnapi = bn->bnapi[i];
+		struct bnge_nq_ring_info *nqr = &bnapi->nq_ring;
+
+		if (nqr->hw_stats_ctx_id != INVALID_STATS_CTX_ID) {
+			req->stat_ctx_id = cpu_to_le32(nqr->hw_stats_ctx_id);
+			bnge_hwrm_req_send(bd, req);
+
+			nqr->hw_stats_ctx_id = INVALID_STATS_CTX_ID;
+		}
+	}
+	bnge_hwrm_req_drop(bd, req);
+}
+
+int bnge_hwrm_stat_ctx_alloc(struct bnge_net *bn)
+{
+	struct hwrm_stat_ctx_alloc_output *resp;
+	struct hwrm_stat_ctx_alloc_input *req;
+	struct bnge_dev *bd = bn->bd;
+	int rc, i;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_STAT_CTX_ALLOC);
+	if (rc)
+		return rc;
+
+	req->stats_dma_length = cpu_to_le16(bd->hw_ring_stats_size);
+	req->update_period_ms = cpu_to_le32(bn->stats_coal_ticks / 1000);
+
+	resp = bnge_hwrm_req_hold(bd, req);
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		struct bnge_napi *bnapi = bn->bnapi[i];
+		struct bnge_nq_ring_info *nqr = &bnapi->nq_ring;
+
+		req->stats_dma_addr = cpu_to_le64(nqr->stats.hw_stats_map);
+
+		rc = bnge_hwrm_req_send(bd, req);
+		if (rc)
+			break;
+
+		nqr->hw_stats_ctx_id = le32_to_cpu(resp->stat_ctx_id);
+		bn->grp_info[i].fw_stats_ctx = nqr->hw_stats_ctx_id;
+	}
+	bnge_hwrm_req_drop(bd, req);
+	return rc;
+}
+
+int hwrm_ring_free_send_msg(struct bnge_net *bn,
+			    struct bnge_ring_struct *ring,
+			    u32 ring_type, int cmpl_ring_id)
+{
+	struct hwrm_ring_free_input *req;
+	struct bnge_dev *bd = bn->bd;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_RING_FREE);
+	if (rc)
+		goto exit;
+
+	req->cmpl_ring = cpu_to_le16(cmpl_ring_id);
+	req->ring_type = ring_type;
+	req->ring_id = cpu_to_le16(ring->fw_ring_id);
+
+	bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	bnge_hwrm_req_drop(bd, req);
+exit:
+	if (rc) {
+		netdev_err(bd->netdev, "hwrm_ring_free type %d failed. rc:%d\n", ring_type, rc);
+		return -EIO;
+	}
+	return 0;
+}
+
+int hwrm_ring_alloc_send_msg(struct bnge_net *bn,
+			     struct bnge_ring_struct *ring,
+			     u32 ring_type, u32 map_index)
+{
+	struct bnge_ring_mem_info *rmem = &ring->ring_mem;
+	struct bnge_ring_grp_info *grp_info;
+	struct hwrm_ring_alloc_output *resp;
+	struct hwrm_ring_alloc_input *req;
+	struct bnge_dev *bd = bn->bd;
+	u16 ring_id, flags = 0;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_RING_ALLOC);
+	if (rc)
+		goto exit;
+
+	req->enables = 0;
+	if (rmem->nr_pages > 1) {
+		req->page_tbl_addr = cpu_to_le64(rmem->dma_pg_tbl);
+		/* Page size is in log2 units */
+		req->page_size = BNGE_PAGE_SHIFT;
+		req->page_tbl_depth = 1;
+	} else {
+		req->page_tbl_addr =  cpu_to_le64(rmem->dma_arr[0]);
+	}
+	req->fbo = 0;
+	/* Association of ring index with doorbell index and MSIX number */
+	req->logical_id = cpu_to_le16(map_index);
+
+	switch (ring_type) {
+	case HWRM_RING_ALLOC_TX: {
+		struct bnge_tx_ring_info *txr;
+
+		txr = container_of(ring, struct bnge_tx_ring_info,
+				   tx_ring_struct);
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_TX;
+		/* Association of transmit ring with completion ring */
+		grp_info = &bn->grp_info[ring->grp_idx];
+		req->cmpl_ring_id = cpu_to_le16(bnge_cp_ring_for_tx(txr));
+		req->length = cpu_to_le32(bn->tx_ring_mask + 1);
+		req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
+		req->queue_id = cpu_to_le16(ring->queue_id);
+		req->flags = cpu_to_le16(flags);
+		break;
+	}
+	case HWRM_RING_ALLOC_RX:
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX;
+		req->length = cpu_to_le32(bn->rx_ring_mask + 1);
+
+		/* Association of rx ring with stats context */
+		grp_info = &bn->grp_info[ring->grp_idx];
+		req->rx_buf_size = cpu_to_le16(bn->rx_buf_use_size);
+		req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
+		req->enables |=
+			cpu_to_le32(RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID);
+		if (NET_IP_ALIGN == 2)
+			flags = RING_ALLOC_REQ_FLAGS_RX_SOP_PAD;
+		req->flags = cpu_to_le16(flags);
+		break;
+	case HWRM_RING_ALLOC_AGG:
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG;
+		/* Association of agg ring with rx ring */
+		grp_info = &bn->grp_info[ring->grp_idx];
+		req->rx_ring_id = cpu_to_le16(grp_info->rx_fw_ring_id);
+		req->rx_buf_size = cpu_to_le16(BNGE_RX_PAGE_SIZE);
+		req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
+		req->enables |=
+			cpu_to_le32(RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID |
+				    RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID);
+		req->length = cpu_to_le32(bn->rx_agg_ring_mask + 1);
+		break;
+	case HWRM_RING_ALLOC_CMPL:
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL;
+		req->length = cpu_to_le32(bn->cp_ring_mask + 1);
+		/* Association of cp ring with nq */
+		grp_info = &bn->grp_info[map_index];
+		req->nq_ring_id = cpu_to_le16(grp_info->nq_fw_ring_id);
+		req->cq_handle = cpu_to_le64(ring->handle);
+		req->enables |=
+			cpu_to_le32(RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID);
+		break;
+	case HWRM_RING_ALLOC_NQ:
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_NQ;
+		req->length = cpu_to_le32(bn->cp_ring_mask + 1);
+		req->int_mode = RING_ALLOC_REQ_INT_MODE_MSIX;
+		break;
+	default:
+		netdev_err(bn->netdev, "hwrm alloc invalid ring type %d\n", ring_type);
+		return -EINVAL;
+	}
+
+	resp = bnge_hwrm_req_hold(bd, req);
+	rc = bnge_hwrm_req_send(bd, req);
+	ring_id = le16_to_cpu(resp->ring_id);
+	bnge_hwrm_req_drop(bd, req);
+
+exit:
+	if (rc) {
+		netdev_err(bd->netdev, "hwrm_ring_alloc type %d failed. rc:%d\n", ring_type, rc);
+		return -EIO;
+	}
+	ring->fw_ring_id = ring_id;
+	return rc;
+}
+
+int bnge_hwrm_set_async_event_cr(struct bnge_dev *bd, int idx)
+{
+	struct hwrm_func_cfg_input *req;
+	int rc;
+
+	rc = bnge_hwrm_req_init(bd, req, HWRM_FUNC_CFG);
+	if (rc)
+		return rc;
+
+	req->fid = cpu_to_le16(0xffff);
+	req->enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_ASYNC_EVENT_CR);
+	req->async_event_cr = cpu_to_le16(idx);
+	return bnge_hwrm_req_send(bd, req);
+}
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.h b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.h
new file mode 100644
index 000000000000..042f28e84a05
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Broadcom */
+
+#ifndef _BNGE_HWRM_LIB_H_
+#define _BNGE_HWRM_LIB_H_
+
+#define BNGE_PLC_EN_JUMBO_THRES_VALID		\
+	VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID
+#define BNGE_PLC_EN_HDS_THRES_VALID		\
+	VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID
+#define BNGE_VNIC_CFG_ROCE_DUAL_MODE		\
+	VNIC_CFG_REQ_FLAGS_ROCE_DUAL_VNIC_MODE
+
+int bnge_hwrm_ver_get(struct bnge_dev *bd);
+int bnge_hwrm_func_reset(struct bnge_dev *bd);
+int bnge_hwrm_fw_set_time(struct bnge_dev *bd);
+int bnge_hwrm_func_drv_rgtr(struct bnge_dev *bd);
+int bnge_hwrm_func_drv_unrgtr(struct bnge_dev *bd);
+int bnge_hwrm_vnic_qcaps(struct bnge_dev *bd);
+int bnge_hwrm_nvm_dev_info(struct bnge_dev *bd,
+			   struct hwrm_nvm_get_dev_info_output *nvm_dev_info);
+int bnge_hwrm_func_backing_store(struct bnge_dev *bd,
+				 struct bnge_ctx_mem_type *ctxm,
+				 bool last);
+int bnge_hwrm_func_backing_store_qcaps(struct bnge_dev *bd);
+int bnge_hwrm_reserve_rings(struct bnge_dev *bd,
+			    struct bnge_hw_rings *hwr);
+int bnge_hwrm_func_qcaps(struct bnge_dev *bd);
+int bnge_hwrm_vnic_qcaps(struct bnge_dev *bd);
+int bnge_hwrm_func_qcfg(struct bnge_dev *bd);
+int bnge_hwrm_func_resc_qcaps(struct bnge_dev *bd);
+int bnge_hwrm_queue_qportcfg(struct bnge_dev *bd);
+
+int bnge_hwrm_vnic_set_hds(struct bnge_net *bn, struct bnge_vnic_info *vnic);
+int bnge_hwrm_vnic_ctx_alloc(struct bnge_dev *bd,
+			     struct bnge_vnic_info *vnic, u16 ctx_idx);
+int bnge_hwrm_vnic_set_rss(struct bnge_net *bn,
+			   struct bnge_vnic_info *vnic, bool set_rss);
+int bnge_hwrm_vnic_cfg(struct bnge_net *bn, struct bnge_vnic_info *vnic);
+void bnge_hwrm_update_rss_hash_cfg(struct bnge_net *bn);
+int bnge_hwrm_vnic_alloc(struct bnge_dev *bd, struct bnge_vnic_info *vnic,
+			 unsigned int nr_rings);
+void bnge_hwrm_vnic_free_one(struct bnge_dev *bd, struct bnge_vnic_info *vnic);
+void bnge_hwrm_vnic_ctx_free_one(struct bnge_dev *bd,
+				 struct bnge_vnic_info *vnic, u16 ctx_idx);
+int bnge_hwrm_l2_filter_free(struct bnge_dev *bd, struct bnge_l2_filter *fltr);
+int bnge_hwrm_l2_filter_alloc(struct bnge_dev *bd, struct bnge_l2_filter *fltr);
+int bnge_hwrm_cfa_l2_set_rx_mask(struct bnge_dev *bd,
+				 struct bnge_vnic_info *vnic);
+void bnge_hwrm_stat_ctx_free(struct bnge_net *bn);
+int bnge_hwrm_stat_ctx_alloc(struct bnge_net *bn);
+int hwrm_ring_free_send_msg(struct bnge_net *bn, struct bnge_ring_struct *ring,
+			    u32 ring_type, int cmpl_ring_id);
+int hwrm_ring_alloc_send_msg(struct bnge_net *bn,
+			     struct bnge_ring_struct *ring,
+			     u32 ring_type, u32 map_index);
+int bnge_hwrm_set_async_event_cr(struct bnge_dev *bd, int idx);
+#endif /* _BNGE_HWRM_LIB_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
new file mode 100644
index 000000000000..832eeb960bd2
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
@@ -0,0 +1,2485 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2025 Broadcom.
+
+#include <asm/byteorder.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/if.h>
+#include <net/ip.h>
+#include <linux/skbuff.h>
+#include <net/page_pool/helpers.h>
+
+#include "bnge.h"
+#include "bnge_hwrm_lib.h"
+#include "bnge_ethtool.h"
+#include "bnge_rmem.h"
+
+#define BNGE_RING_TO_TC_OFF(bd, tx)	\
+	((tx) % (bd)->tx_nr_rings_per_tc)
+
+#define BNGE_RING_TO_TC(bd, tx)		\
+	((tx) / (bd)->tx_nr_rings_per_tc)
+
+#define BNGE_TC_TO_RING_BASE(bd, tc)	\
+	((tc) * (bd)->tx_nr_rings_per_tc)
+
+static void bnge_free_stats_mem(struct bnge_net *bn,
+				struct bnge_stats_mem *stats)
+{
+	struct bnge_dev *bd = bn->bd;
+
+	if (stats->hw_stats) {
+		dma_free_coherent(bd->dev, stats->len, stats->hw_stats,
+				  stats->hw_stats_map);
+		stats->hw_stats = NULL;
+	}
+}
+
+static int bnge_alloc_stats_mem(struct bnge_net *bn,
+				struct bnge_stats_mem *stats)
+{
+	struct bnge_dev *bd = bn->bd;
+
+	stats->hw_stats = dma_alloc_coherent(bd->dev, stats->len,
+					     &stats->hw_stats_map, GFP_KERNEL);
+	if (!stats->hw_stats)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void bnge_free_ring_stats(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i;
+
+	if (!bn->bnapi)
+		return;
+
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		struct bnge_napi *bnapi = bn->bnapi[i];
+		struct bnge_nq_ring_info *nqr = &bnapi->nq_ring;
+
+		bnge_free_stats_mem(bn, &nqr->stats);
+	}
+}
+
+static int bnge_alloc_ring_stats(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	u32 size, i;
+	int rc;
+
+	size = bd->hw_ring_stats_size;
+
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		struct bnge_napi *bnapi = bn->bnapi[i];
+		struct bnge_nq_ring_info *nqr = &bnapi->nq_ring;
+
+		nqr->stats.len = size;
+		rc = bnge_alloc_stats_mem(bn, &nqr->stats);
+		if (rc)
+			goto err_free_ring_stats;
+
+		nqr->hw_stats_ctx_id = INVALID_STATS_CTX_ID;
+	}
+	return 0;
+
+err_free_ring_stats:
+	bnge_free_ring_stats(bn);
+	return rc;
+}
+
+static void bnge_free_nq_desc_arr(struct bnge_nq_ring_info *nqr)
+{
+	struct bnge_ring_struct *ring = &nqr->ring_struct;
+
+	kfree(nqr->desc_ring);
+	nqr->desc_ring = NULL;
+	ring->ring_mem.pg_arr = NULL;
+	kfree(nqr->desc_mapping);
+	nqr->desc_mapping = NULL;
+	ring->ring_mem.dma_arr = NULL;
+}
+
+static void bnge_free_cp_desc_arr(struct bnge_cp_ring_info *cpr)
+{
+	struct bnge_ring_struct *ring = &cpr->ring_struct;
+
+	kfree(cpr->desc_ring);
+	cpr->desc_ring = NULL;
+	ring->ring_mem.pg_arr = NULL;
+	kfree(cpr->desc_mapping);
+	cpr->desc_mapping = NULL;
+	ring->ring_mem.dma_arr = NULL;
+}
+
+static int bnge_alloc_nq_desc_arr(struct bnge_nq_ring_info *nqr, int n)
+{
+	nqr->desc_ring = kcalloc(n, sizeof(*nqr->desc_ring), GFP_KERNEL);
+	if (!nqr->desc_ring)
+		return -ENOMEM;
+
+	nqr->desc_mapping = kcalloc(n, sizeof(*nqr->desc_mapping), GFP_KERNEL);
+	if (!nqr->desc_mapping)
+		goto err_free_desc_ring;
+	return 0;
+
+err_free_desc_ring:
+	kfree(nqr->desc_ring);
+	nqr->desc_ring = NULL;
+	return -ENOMEM;
+}
+
+static int bnge_alloc_cp_desc_arr(struct bnge_cp_ring_info *cpr, int n)
+{
+	cpr->desc_ring = kcalloc(n, sizeof(*cpr->desc_ring), GFP_KERNEL);
+	if (!cpr->desc_ring)
+		return -ENOMEM;
+
+	cpr->desc_mapping = kcalloc(n, sizeof(*cpr->desc_mapping), GFP_KERNEL);
+	if (!cpr->desc_mapping)
+		goto err_free_desc_ring;
+	return 0;
+
+err_free_desc_ring:
+	kfree(cpr->desc_ring);
+	cpr->desc_ring = NULL;
+	return -ENOMEM;
+}
+
+static void bnge_free_nq_arrays(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i;
+
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		struct bnge_napi *bnapi = bn->bnapi[i];
+
+		bnge_free_nq_desc_arr(&bnapi->nq_ring);
+	}
+}
+
+static int bnge_alloc_nq_arrays(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i, rc;
+
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		struct bnge_napi *bnapi = bn->bnapi[i];
+
+		rc = bnge_alloc_nq_desc_arr(&bnapi->nq_ring, bn->cp_nr_pages);
+		if (rc)
+			goto err_free_nq_arrays;
+	}
+	return 0;
+
+err_free_nq_arrays:
+	bnge_free_nq_arrays(bn);
+	return rc;
+}
+
+static void bnge_free_nq_tree(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i;
+
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		struct bnge_napi *bnapi = bn->bnapi[i];
+		struct bnge_nq_ring_info *nqr;
+		struct bnge_ring_struct *ring;
+		int j;
+
+		nqr = &bnapi->nq_ring;
+		ring = &nqr->ring_struct;
+
+		bnge_free_ring(bd, &ring->ring_mem);
+
+		if (!nqr->cp_ring_arr)
+			continue;
+
+		for (j = 0; j < nqr->cp_ring_count; j++) {
+			struct bnge_cp_ring_info *cpr = &nqr->cp_ring_arr[j];
+
+			ring = &cpr->ring_struct;
+			bnge_free_ring(bd, &ring->ring_mem);
+			bnge_free_cp_desc_arr(cpr);
+		}
+		kfree(nqr->cp_ring_arr);
+		nqr->cp_ring_arr = NULL;
+		nqr->cp_ring_count = 0;
+	}
+}
+
+static int alloc_one_cp_ring(struct bnge_net *bn,
+			     struct bnge_cp_ring_info *cpr)
+{
+	struct bnge_ring_mem_info *rmem;
+	struct bnge_ring_struct *ring;
+	struct bnge_dev *bd = bn->bd;
+	int rc;
+
+	rc = bnge_alloc_cp_desc_arr(cpr, bn->cp_nr_pages);
+	if (rc)
+		return -ENOMEM;
+	ring = &cpr->ring_struct;
+	rmem = &ring->ring_mem;
+	rmem->nr_pages = bn->cp_nr_pages;
+	rmem->page_size = HW_CMPD_RING_SIZE;
+	rmem->pg_arr = (void **)cpr->desc_ring;
+	rmem->dma_arr = cpr->desc_mapping;
+	rmem->flags = BNGE_RMEM_RING_PTE_FLAG;
+	rc = bnge_alloc_ring(bd, rmem);
+	if (rc)
+		goto err_free_cp_desc_arr;
+	return rc;
+
+err_free_cp_desc_arr:
+	bnge_free_cp_desc_arr(cpr);
+	return rc;
+}
+
+static int bnge_alloc_nq_tree(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i, j, ulp_msix, rc;
+	int tcs = 1;
+
+	ulp_msix = bnge_aux_get_msix(bd);
+	for (i = 0, j = 0; i < bd->nq_nr_rings; i++) {
+		bool sh = !!(bd->flags & BNGE_EN_SHARED_CHNL);
+		struct bnge_napi *bnapi = bn->bnapi[i];
+		struct bnge_nq_ring_info *nqr;
+		struct bnge_cp_ring_info *cpr;
+		struct bnge_ring_struct *ring;
+		int cp_count = 0, k;
+		int rx = 0, tx = 0;
+
+		nqr = &bnapi->nq_ring;
+		nqr->bnapi = bnapi;
+		ring = &nqr->ring_struct;
+
+		rc = bnge_alloc_ring(bd, &ring->ring_mem);
+		if (rc)
+			goto err_free_nq_tree;
+
+		ring->map_idx = ulp_msix + i;
+
+		if (i < bd->rx_nr_rings) {
+			cp_count++;
+			rx = 1;
+		}
+
+		if ((sh && i < bd->tx_nr_rings) ||
+		    (!sh && i >= bd->rx_nr_rings)) {
+			cp_count += tcs;
+			tx = 1;
+		}
+
+		nqr->cp_ring_arr = kcalloc(cp_count, sizeof(*cpr),
+					   GFP_KERNEL);
+		if (!nqr->cp_ring_arr) {
+			rc = -ENOMEM;
+			goto err_free_nq_tree;
+		}
+
+		nqr->cp_ring_count = cp_count;
+
+		for (k = 0; k < cp_count; k++) {
+			cpr = &nqr->cp_ring_arr[k];
+			rc = alloc_one_cp_ring(bn, cpr);
+			if (rc)
+				goto err_free_nq_tree;
+
+			cpr->bnapi = bnapi;
+			cpr->cp_idx = k;
+			if (!k && rx) {
+				bn->rx_ring[i].rx_cpr = cpr;
+				cpr->cp_ring_type = BNGE_NQ_HDL_TYPE_RX;
+			} else {
+				int n, tc = k - rx;
+
+				n = BNGE_TC_TO_RING_BASE(bd, tc) + j;
+				bn->tx_ring[n].tx_cpr = cpr;
+				cpr->cp_ring_type = BNGE_NQ_HDL_TYPE_TX;
+			}
+		}
+		if (tx)
+			j++;
+	}
+	return 0;
+
+err_free_nq_tree:
+	bnge_free_nq_tree(bn);
+	return rc;
+}
+
+static bool bnge_separate_head_pool(struct bnge_rx_ring_info *rxr)
+{
+	return rxr->need_head_pool || PAGE_SIZE > BNGE_RX_PAGE_SIZE;
+}
+
+static void bnge_free_one_rx_ring_bufs(struct bnge_net *bn,
+				       struct bnge_rx_ring_info *rxr)
+{
+	int i, max_idx;
+
+	if (!rxr->rx_buf_ring)
+		return;
+
+	max_idx = bn->rx_nr_pages * RX_DESC_CNT;
+
+	for (i = 0; i < max_idx; i++) {
+		struct bnge_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[i];
+		void *data = rx_buf->data;
+
+		if (!data)
+			continue;
+
+		rx_buf->data = NULL;
+		page_pool_free_va(rxr->head_pool, data, true);
+	}
+}
+
+static void bnge_free_one_agg_ring_bufs(struct bnge_net *bn,
+					struct bnge_rx_ring_info *rxr)
+{
+	int i, max_idx;
+
+	if (!rxr->rx_agg_buf_ring)
+		return;
+
+	max_idx = bn->rx_agg_nr_pages * RX_DESC_CNT;
+
+	for (i = 0; i < max_idx; i++) {
+		struct bnge_sw_rx_agg_bd *rx_agg_buf = &rxr->rx_agg_buf_ring[i];
+		netmem_ref netmem = rx_agg_buf->netmem;
+
+		if (!netmem)
+			continue;
+
+		rx_agg_buf->netmem = 0;
+		__clear_bit(i, rxr->rx_agg_bmap);
+
+		page_pool_recycle_direct_netmem(rxr->page_pool, netmem);
+	}
+}
+
+static void bnge_free_one_rx_ring_pair_bufs(struct bnge_net *bn,
+					    struct bnge_rx_ring_info *rxr)
+{
+	bnge_free_one_rx_ring_bufs(bn, rxr);
+	bnge_free_one_agg_ring_bufs(bn, rxr);
+}
+
+static void bnge_free_rx_ring_pair_bufs(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i;
+
+	if (!bn->rx_ring)
+		return;
+
+	for (i = 0; i < bd->rx_nr_rings; i++)
+		bnge_free_one_rx_ring_pair_bufs(bn, &bn->rx_ring[i]);
+}
+
+static void bnge_free_all_rings_bufs(struct bnge_net *bn)
+{
+	bnge_free_rx_ring_pair_bufs(bn);
+}
+
+static void bnge_free_rx_rings(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i;
+
+	for (i = 0; i < bd->rx_nr_rings; i++) {
+		struct bnge_rx_ring_info *rxr = &bn->rx_ring[i];
+		struct bnge_ring_struct *ring;
+
+		page_pool_destroy(rxr->page_pool);
+		page_pool_destroy(rxr->head_pool);
+		rxr->page_pool = rxr->head_pool = NULL;
+
+		kfree(rxr->rx_agg_bmap);
+		rxr->rx_agg_bmap = NULL;
+
+		ring = &rxr->rx_ring_struct;
+		bnge_free_ring(bd, &ring->ring_mem);
+
+		ring = &rxr->rx_agg_ring_struct;
+		bnge_free_ring(bd, &ring->ring_mem);
+	}
+}
+
+static int bnge_alloc_rx_page_pool(struct bnge_net *bn,
+				   struct bnge_rx_ring_info *rxr,
+				   int numa_node)
+{
+	const unsigned int agg_size_fac = PAGE_SIZE / BNGE_RX_PAGE_SIZE;
+	const unsigned int rx_size_fac = PAGE_SIZE / SZ_4K;
+	struct page_pool_params pp = { 0 };
+	struct bnge_dev *bd = bn->bd;
+	struct page_pool *pool;
+
+	pp.pool_size = bn->rx_agg_ring_size / agg_size_fac;
+	pp.nid = numa_node;
+	pp.netdev = bn->netdev;
+	pp.dev = bd->dev;
+	pp.dma_dir = bn->rx_dir;
+	pp.max_len = PAGE_SIZE;
+	pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV |
+		   PP_FLAG_ALLOW_UNREADABLE_NETMEM;
+	pp.queue_idx = rxr->bnapi->index;
+
+	pool = page_pool_create(&pp);
+	if (IS_ERR(pool))
+		return PTR_ERR(pool);
+	rxr->page_pool = pool;
+
+	rxr->need_head_pool = page_pool_is_unreadable(pool);
+	if (bnge_separate_head_pool(rxr)) {
+		pp.pool_size = min(bn->rx_ring_size / rx_size_fac, 1024);
+		pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+		pool = page_pool_create(&pp);
+		if (IS_ERR(pool))
+			goto err_destroy_pp;
+	} else {
+		page_pool_get(pool);
+	}
+	rxr->head_pool = pool;
+	return 0;
+
+err_destroy_pp:
+	page_pool_destroy(rxr->page_pool);
+	rxr->page_pool = NULL;
+	return PTR_ERR(pool);
+}
+
+static void bnge_enable_rx_page_pool(struct bnge_rx_ring_info *rxr)
+{
+	page_pool_enable_direct_recycling(rxr->head_pool, &rxr->bnapi->napi);
+	page_pool_enable_direct_recycling(rxr->page_pool, &rxr->bnapi->napi);
+}
+
+static int bnge_alloc_rx_agg_bmap(struct bnge_net *bn,
+				  struct bnge_rx_ring_info *rxr)
+{
+	u16 mem_size;
+
+	rxr->rx_agg_bmap_size = bn->rx_agg_ring_mask + 1;
+	mem_size = rxr->rx_agg_bmap_size / 8;
+	rxr->rx_agg_bmap = kzalloc(mem_size, GFP_KERNEL);
+	if (!rxr->rx_agg_bmap)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int bnge_alloc_rx_rings(struct bnge_net *bn)
+{
+	int i, rc = 0, agg_rings = 0, cpu;
+	struct bnge_dev *bd = bn->bd;
+
+	if (bnge_is_agg_reqd(bd))
+		agg_rings = 1;
+
+	for (i = 0; i < bd->rx_nr_rings; i++) {
+		struct bnge_rx_ring_info *rxr = &bn->rx_ring[i];
+		struct bnge_ring_struct *ring;
+		int cpu_node;
+
+		ring = &rxr->rx_ring_struct;
+
+		cpu = cpumask_local_spread(i, dev_to_node(bd->dev));
+		cpu_node = cpu_to_node(cpu);
+		netdev_dbg(bn->netdev, "Allocating page pool for rx_ring[%d] on numa_node: %d\n",
+			   i, cpu_node);
+		rc = bnge_alloc_rx_page_pool(bn, rxr, cpu_node);
+		if (rc)
+			goto err_free_rx_rings;
+		bnge_enable_rx_page_pool(rxr);
+
+		rc = bnge_alloc_ring(bd, &ring->ring_mem);
+		if (rc)
+			goto err_free_rx_rings;
+
+		ring->grp_idx = i;
+		if (agg_rings) {
+			ring = &rxr->rx_agg_ring_struct;
+			rc = bnge_alloc_ring(bd, &ring->ring_mem);
+			if (rc)
+				goto err_free_rx_rings;
+
+			ring->grp_idx = i;
+			rc = bnge_alloc_rx_agg_bmap(bn, rxr);
+			if (rc)
+				goto err_free_rx_rings;
+		}
+	}
+	return rc;
+
+err_free_rx_rings:
+	bnge_free_rx_rings(bn);
+	return rc;
+}
+
+static void bnge_free_tx_rings(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i;
+
+	for (i = 0; i < bd->tx_nr_rings; i++) {
+		struct bnge_tx_ring_info *txr = &bn->tx_ring[i];
+		struct bnge_ring_struct *ring;
+
+		ring = &txr->tx_ring_struct;
+
+		bnge_free_ring(bd, &ring->ring_mem);
+	}
+}
+
+static int bnge_alloc_tx_rings(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i, j, rc;
+
+	for (i = 0, j = 0; i < bd->tx_nr_rings; i++) {
+		struct bnge_tx_ring_info *txr = &bn->tx_ring[i];
+		struct bnge_ring_struct *ring;
+		u8 qidx;
+
+		ring = &txr->tx_ring_struct;
+
+		rc = bnge_alloc_ring(bd, &ring->ring_mem);
+		if (rc)
+			goto err_free_tx_rings;
+
+		ring->grp_idx = txr->bnapi->index;
+		qidx = bd->tc_to_qidx[j];
+		ring->queue_id = bd->q_info[qidx].queue_id;
+		if (BNGE_RING_TO_TC_OFF(bd, i) == (bd->tx_nr_rings_per_tc - 1))
+			j++;
+	}
+	return 0;
+
+err_free_tx_rings:
+	bnge_free_tx_rings(bn);
+	return rc;
+}
+
+static void bnge_free_vnic_attributes(struct bnge_net *bn)
+{
+	struct pci_dev *pdev = bn->bd->pdev;
+	struct bnge_vnic_info *vnic;
+	int i;
+
+	if (!bn->vnic_info)
+		return;
+
+	for (i = 0; i < bn->nr_vnics; i++) {
+		vnic = &bn->vnic_info[i];
+
+		kfree(vnic->uc_list);
+		vnic->uc_list = NULL;
+
+		if (vnic->mc_list) {
+			dma_free_coherent(&pdev->dev, vnic->mc_list_size,
+					  vnic->mc_list, vnic->mc_list_mapping);
+			vnic->mc_list = NULL;
+		}
+
+		if (vnic->rss_table) {
+			dma_free_coherent(&pdev->dev, vnic->rss_table_size,
+					  vnic->rss_table,
+					  vnic->rss_table_dma_addr);
+			vnic->rss_table = NULL;
+		}
+
+		vnic->rss_hash_key = NULL;
+		vnic->flags = 0;
+	}
+}
+
+static int bnge_alloc_vnic_attributes(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	struct bnge_vnic_info *vnic;
+	int i, size;
+
+	for (i = 0; i < bn->nr_vnics; i++) {
+		vnic = &bn->vnic_info[i];
+
+		if (vnic->flags & BNGE_VNIC_UCAST_FLAG) {
+			int mem_size = (BNGE_MAX_UC_ADDRS - 1) * ETH_ALEN;
+
+			vnic->uc_list = kmalloc(mem_size, GFP_KERNEL);
+			if (!vnic->uc_list)
+				goto err_free_vnic_attributes;
+		}
+
+		if (vnic->flags & BNGE_VNIC_MCAST_FLAG) {
+			vnic->mc_list_size = BNGE_MAX_MC_ADDRS * ETH_ALEN;
+			vnic->mc_list =
+				dma_alloc_coherent(bd->dev,
+						   vnic->mc_list_size,
+						   &vnic->mc_list_mapping,
+						   GFP_KERNEL);
+			if (!vnic->mc_list)
+				goto err_free_vnic_attributes;
+		}
+
+		/* Allocate rss table and hash key */
+		size = L1_CACHE_ALIGN(BNGE_MAX_RSS_TABLE_SIZE);
+
+		vnic->rss_table_size = size + HW_HASH_KEY_SIZE;
+		vnic->rss_table = dma_alloc_coherent(bd->dev,
+						     vnic->rss_table_size,
+						     &vnic->rss_table_dma_addr,
+						     GFP_KERNEL);
+		if (!vnic->rss_table)
+			goto err_free_vnic_attributes;
+
+		vnic->rss_hash_key = ((void *)vnic->rss_table) + size;
+		vnic->rss_hash_key_dma_addr = vnic->rss_table_dma_addr + size;
+	}
+	return 0;
+
+err_free_vnic_attributes:
+	bnge_free_vnic_attributes(bn);
+	return -ENOMEM;
+}
+
+static int bnge_alloc_vnics(struct bnge_net *bn)
+{
+	int num_vnics;
+
+	/* Allocate only 1 VNIC for now
+	 * Additional VNICs will be added based on RFS/NTUPLE in future patches
+	 */
+	num_vnics = 1;
+
+	bn->vnic_info = kcalloc(num_vnics, sizeof(struct bnge_vnic_info),
+				GFP_KERNEL);
+	if (!bn->vnic_info)
+		return -ENOMEM;
+
+	bn->nr_vnics = num_vnics;
+
+	return 0;
+}
+
+static void bnge_free_vnics(struct bnge_net *bn)
+{
+	kfree(bn->vnic_info);
+	bn->vnic_info = NULL;
+	bn->nr_vnics = 0;
+}
+
+static void bnge_free_ring_grps(struct bnge_net *bn)
+{
+	kfree(bn->grp_info);
+	bn->grp_info = NULL;
+}
+
+static int bnge_init_ring_grps(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i;
+
+	bn->grp_info = kcalloc(bd->nq_nr_rings,
+			       sizeof(struct bnge_ring_grp_info),
+			       GFP_KERNEL);
+	if (!bn->grp_info)
+		return -ENOMEM;
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		bn->grp_info[i].fw_stats_ctx = INVALID_HW_RING_ID;
+		bn->grp_info[i].fw_grp_id = INVALID_HW_RING_ID;
+		bn->grp_info[i].rx_fw_ring_id = INVALID_HW_RING_ID;
+		bn->grp_info[i].agg_fw_ring_id = INVALID_HW_RING_ID;
+		bn->grp_info[i].nq_fw_ring_id = INVALID_HW_RING_ID;
+	}
+
+	return 0;
+}
+
+static void bnge_free_core(struct bnge_net *bn)
+{
+	bnge_free_vnic_attributes(bn);
+	bnge_free_tx_rings(bn);
+	bnge_free_rx_rings(bn);
+	bnge_free_nq_tree(bn);
+	bnge_free_nq_arrays(bn);
+	bnge_free_ring_stats(bn);
+	bnge_free_ring_grps(bn);
+	bnge_free_vnics(bn);
+	kfree(bn->tx_ring_map);
+	bn->tx_ring_map = NULL;
+	kfree(bn->tx_ring);
+	bn->tx_ring = NULL;
+	kfree(bn->rx_ring);
+	bn->rx_ring = NULL;
+	kfree(bn->bnapi);
+	bn->bnapi = NULL;
+}
+
+static int bnge_alloc_core(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i, j, size, arr_size;
+	int rc = -ENOMEM;
+	void *bnapi;
+
+	arr_size = L1_CACHE_ALIGN(sizeof(struct bnge_napi *) *
+			bd->nq_nr_rings);
+	size = L1_CACHE_ALIGN(sizeof(struct bnge_napi));
+	bnapi = kzalloc(arr_size + size * bd->nq_nr_rings, GFP_KERNEL);
+	if (!bnapi)
+		return rc;
+
+	bn->bnapi = bnapi;
+	bnapi += arr_size;
+	for (i = 0; i < bd->nq_nr_rings; i++, bnapi += size) {
+		struct bnge_nq_ring_info *nqr;
+
+		bn->bnapi[i] = bnapi;
+		bn->bnapi[i]->index = i;
+		bn->bnapi[i]->bn = bn;
+		nqr = &bn->bnapi[i]->nq_ring;
+		nqr->ring_struct.ring_mem.flags = BNGE_RMEM_RING_PTE_FLAG;
+	}
+
+	bn->rx_ring = kcalloc(bd->rx_nr_rings,
+			      sizeof(struct bnge_rx_ring_info),
+			      GFP_KERNEL);
+	if (!bn->rx_ring)
+		goto err_free_core;
+
+	for (i = 0; i < bd->rx_nr_rings; i++) {
+		struct bnge_rx_ring_info *rxr = &bn->rx_ring[i];
+
+		rxr->rx_ring_struct.ring_mem.flags =
+			BNGE_RMEM_RING_PTE_FLAG;
+		rxr->rx_agg_ring_struct.ring_mem.flags =
+			BNGE_RMEM_RING_PTE_FLAG;
+		rxr->bnapi = bn->bnapi[i];
+		bn->bnapi[i]->rx_ring = &bn->rx_ring[i];
+	}
+
+	bn->tx_ring = kcalloc(bd->tx_nr_rings,
+			      sizeof(struct bnge_tx_ring_info),
+			      GFP_KERNEL);
+	if (!bn->tx_ring)
+		goto err_free_core;
+
+	bn->tx_ring_map = kcalloc(bd->tx_nr_rings, sizeof(u16),
+				  GFP_KERNEL);
+	if (!bn->tx_ring_map)
+		goto err_free_core;
+
+	if (bd->flags & BNGE_EN_SHARED_CHNL)
+		j = 0;
+	else
+		j = bd->rx_nr_rings;
+
+	for (i = 0; i < bd->tx_nr_rings; i++) {
+		struct bnge_tx_ring_info *txr = &bn->tx_ring[i];
+		struct bnge_napi *bnapi2;
+		int k;
+
+		txr->tx_ring_struct.ring_mem.flags = BNGE_RMEM_RING_PTE_FLAG;
+		bn->tx_ring_map[i] = i;
+		k = j + BNGE_RING_TO_TC_OFF(bd, i);
+
+		bnapi2 = bn->bnapi[k];
+		txr->txq_index = i;
+		txr->tx_napi_idx =
+			BNGE_RING_TO_TC(bd, txr->txq_index);
+		bnapi2->tx_ring[txr->tx_napi_idx] = txr;
+		txr->bnapi = bnapi2;
+	}
+
+	rc = bnge_alloc_ring_stats(bn);
+	if (rc)
+		goto err_free_core;
+
+	rc = bnge_alloc_vnics(bn);
+	if (rc)
+		goto err_free_core;
+
+	rc = bnge_alloc_nq_arrays(bn);
+	if (rc)
+		goto err_free_core;
+
+	bnge_init_ring_struct(bn);
+
+	rc = bnge_alloc_rx_rings(bn);
+	if (rc)
+		goto err_free_core;
+
+	rc = bnge_alloc_tx_rings(bn);
+	if (rc)
+		goto err_free_core;
+
+	rc = bnge_alloc_nq_tree(bn);
+	if (rc)
+		goto err_free_core;
+
+	bn->vnic_info[BNGE_VNIC_DEFAULT].flags |= BNGE_VNIC_RSS_FLAG |
+						  BNGE_VNIC_MCAST_FLAG |
+						  BNGE_VNIC_UCAST_FLAG;
+	rc = bnge_alloc_vnic_attributes(bn);
+	if (rc)
+		goto err_free_core;
+	return 0;
+
+err_free_core:
+	bnge_free_core(bn);
+	return rc;
+}
+
+u16 bnge_cp_ring_for_rx(struct bnge_rx_ring_info *rxr)
+{
+	return rxr->rx_cpr->ring_struct.fw_ring_id;
+}
+
+u16 bnge_cp_ring_for_tx(struct bnge_tx_ring_info *txr)
+{
+	return txr->tx_cpr->ring_struct.fw_ring_id;
+}
+
+static void bnge_db_nq(struct bnge_net *bn, struct bnge_db_info *db, u32 idx)
+{
+	bnge_writeq(bn->bd, db->db_key64 | DBR_TYPE_NQ_MASK |
+		    DB_RING_IDX(db, idx), db->doorbell);
+}
+
+static void bnge_db_cq(struct bnge_net *bn, struct bnge_db_info *db, u32 idx)
+{
+	bnge_writeq(bn->bd, db->db_key64 | DBR_TYPE_CQ_ARMALL |
+		    DB_RING_IDX(db, idx), db->doorbell);
+}
+
+static int bnge_cp_num_to_irq_num(struct bnge_net *bn, int n)
+{
+	struct bnge_napi *bnapi = bn->bnapi[n];
+	struct bnge_nq_ring_info *nqr;
+
+	nqr = &bnapi->nq_ring;
+
+	return nqr->ring_struct.map_idx;
+}
+
+static irqreturn_t bnge_msix(int irq, void *dev_instance)
+{
+	/* NAPI scheduling to be added in a future patch */
+	return IRQ_HANDLED;
+}
+
+static void bnge_init_nq_tree(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i, j;
+
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		struct bnge_nq_ring_info *nqr = &bn->bnapi[i]->nq_ring;
+		struct bnge_ring_struct *ring = &nqr->ring_struct;
+
+		ring->fw_ring_id = INVALID_HW_RING_ID;
+		for (j = 0; j < nqr->cp_ring_count; j++) {
+			struct bnge_cp_ring_info *cpr = &nqr->cp_ring_arr[j];
+
+			ring = &cpr->ring_struct;
+			ring->fw_ring_id = INVALID_HW_RING_ID;
+		}
+	}
+}
+
+static netmem_ref __bnge_alloc_rx_netmem(struct bnge_net *bn,
+					 dma_addr_t *mapping,
+					 struct bnge_rx_ring_info *rxr,
+					 unsigned int *offset,
+					 gfp_t gfp)
+{
+	netmem_ref netmem;
+
+	if (PAGE_SIZE > BNGE_RX_PAGE_SIZE) {
+		netmem = page_pool_alloc_frag_netmem(rxr->page_pool, offset,
+						     BNGE_RX_PAGE_SIZE, gfp);
+	} else {
+		netmem = page_pool_alloc_netmems(rxr->page_pool, gfp);
+		*offset = 0;
+	}
+	if (!netmem)
+		return 0;
+
+	*mapping = page_pool_get_dma_addr_netmem(netmem) + *offset;
+	return netmem;
+}
+
+static u8 *__bnge_alloc_rx_frag(struct bnge_net *bn, dma_addr_t *mapping,
+				struct bnge_rx_ring_info *rxr,
+				gfp_t gfp)
+{
+	unsigned int offset;
+	struct page *page;
+
+	page = page_pool_alloc_frag(rxr->head_pool, &offset,
+				    bn->rx_buf_size, gfp);
+	if (!page)
+		return NULL;
+
+	*mapping = page_pool_get_dma_addr(page) + bn->rx_dma_offset + offset;
+	return page_address(page) + offset;
+}
+
+static int bnge_alloc_rx_data(struct bnge_net *bn,
+			      struct bnge_rx_ring_info *rxr,
+			      u16 prod, gfp_t gfp)
+{
+	struct bnge_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[RING_RX(bn, prod)];
+	struct rx_bd *rxbd;
+	dma_addr_t mapping;
+	u8 *data;
+
+	rxbd = &rxr->rx_desc_ring[RX_RING(bn, prod)][RX_IDX(prod)];
+	data = __bnge_alloc_rx_frag(bn, &mapping, rxr, gfp);
+	if (!data)
+		return -ENOMEM;
+
+	rx_buf->data = data;
+	rx_buf->data_ptr = data + bn->rx_offset;
+	rx_buf->mapping = mapping;
+
+	rxbd->rx_bd_haddr = cpu_to_le64(mapping);
+
+	return 0;
+}
+
+static int bnge_alloc_one_rx_ring_bufs(struct bnge_net *bn,
+				       struct bnge_rx_ring_info *rxr,
+				       int ring_nr)
+{
+	u32 prod = rxr->rx_prod;
+	int i, rc = 0;
+
+	for (i = 0; i < bn->rx_ring_size; i++) {
+		rc = bnge_alloc_rx_data(bn, rxr, prod, GFP_KERNEL);
+		if (rc)
+			break;
+		prod = NEXT_RX(prod);
+	}
+
+	/* Abort if not a single buffer can be allocated */
+	if (rc && !i) {
+		netdev_err(bn->netdev,
+			   "RX ring %d: allocated %d/%d buffers, abort\n",
+			   ring_nr, i, bn->rx_ring_size);
+		return rc;
+	}
+
+	rxr->rx_prod = prod;
+
+	if (i < bn->rx_ring_size)
+		netdev_warn(bn->netdev,
+			    "RX ring %d: allocated %d/%d buffers, continuing\n",
+			    ring_nr, i, bn->rx_ring_size);
+	return 0;
+}
+
+static u16 bnge_find_next_agg_idx(struct bnge_rx_ring_info *rxr, u16 idx)
+{
+	u16 next, max = rxr->rx_agg_bmap_size;
+
+	next = find_next_zero_bit(rxr->rx_agg_bmap, max, idx);
+	if (next >= max)
+		next = find_first_zero_bit(rxr->rx_agg_bmap, max);
+	return next;
+}
+
+static int bnge_alloc_rx_netmem(struct bnge_net *bn,
+				struct bnge_rx_ring_info *rxr,
+				u16 prod, gfp_t gfp)
+{
+	struct bnge_sw_rx_agg_bd *rx_agg_buf;
+	u16 sw_prod = rxr->rx_sw_agg_prod;
+	unsigned int offset = 0;
+	struct rx_bd *rxbd;
+	dma_addr_t mapping;
+	netmem_ref netmem;
+
+	rxbd = &rxr->rx_agg_desc_ring[RX_AGG_RING(bn, prod)][RX_IDX(prod)];
+	netmem = __bnge_alloc_rx_netmem(bn, &mapping, rxr, &offset, gfp);
+	if (!netmem)
+		return -ENOMEM;
+
+	if (unlikely(test_bit(sw_prod, rxr->rx_agg_bmap)))
+		sw_prod = bnge_find_next_agg_idx(rxr, sw_prod);
+
+	__set_bit(sw_prod, rxr->rx_agg_bmap);
+	rx_agg_buf = &rxr->rx_agg_buf_ring[sw_prod];
+	rxr->rx_sw_agg_prod = RING_RX_AGG(bn, NEXT_RX_AGG(sw_prod));
+
+	rx_agg_buf->netmem = netmem;
+	rx_agg_buf->offset = offset;
+	rx_agg_buf->mapping = mapping;
+	rxbd->rx_bd_haddr = cpu_to_le64(mapping);
+	rxbd->rx_bd_opaque = sw_prod;
+	return 0;
+}
+
+static int bnge_alloc_one_agg_ring_bufs(struct bnge_net *bn,
+					struct bnge_rx_ring_info *rxr,
+					int ring_nr)
+{
+	u32 prod = rxr->rx_agg_prod;
+	int i, rc = 0;
+
+	for (i = 0; i < bn->rx_agg_ring_size; i++) {
+		rc = bnge_alloc_rx_netmem(bn, rxr, prod, GFP_KERNEL);
+		if (rc)
+			break;
+		prod = NEXT_RX_AGG(prod);
+	}
+
+	if (rc && i < MAX_SKB_FRAGS) {
+		netdev_err(bn->netdev,
+			   "Agg ring %d: allocated %d/%d buffers (min %d), abort\n",
+			   ring_nr, i, bn->rx_agg_ring_size, MAX_SKB_FRAGS);
+		goto err_free_one_agg_ring_bufs;
+	}
+
+	rxr->rx_agg_prod = prod;
+
+	if (i < bn->rx_agg_ring_size)
+		netdev_warn(bn->netdev,
+			    "Agg ring %d: allocated %d/%d buffers, continuing\n",
+			    ring_nr, i, bn->rx_agg_ring_size);
+	return 0;
+
+err_free_one_agg_ring_bufs:
+	bnge_free_one_agg_ring_bufs(bn, rxr);
+	return -ENOMEM;
+}
+
+static int bnge_alloc_one_rx_ring_pair_bufs(struct bnge_net *bn, int ring_nr)
+{
+	struct bnge_rx_ring_info *rxr = &bn->rx_ring[ring_nr];
+	int rc;
+
+	rc = bnge_alloc_one_rx_ring_bufs(bn, rxr, ring_nr);
+	if (rc)
+		return rc;
+
+	if (bnge_is_agg_reqd(bn->bd)) {
+		rc = bnge_alloc_one_agg_ring_bufs(bn, rxr, ring_nr);
+		if (rc)
+			goto err_free_one_rx_ring_bufs;
+	}
+	return 0;
+
+err_free_one_rx_ring_bufs:
+	bnge_free_one_rx_ring_bufs(bn, rxr);
+	return rc;
+}
+
+static void bnge_init_rxbd_pages(struct bnge_ring_struct *ring, u32 type)
+{
+	struct rx_bd **rx_desc_ring;
+	u32 prod;
+	int i;
+
+	rx_desc_ring = (struct rx_bd **)ring->ring_mem.pg_arr;
+	for (i = 0, prod = 0; i < ring->ring_mem.nr_pages; i++) {
+		struct rx_bd *rxbd = rx_desc_ring[i];
+		int j;
+
+		for (j = 0; j < RX_DESC_CNT; j++, rxbd++, prod++) {
+			rxbd->rx_bd_len_flags_type = cpu_to_le32(type);
+			rxbd->rx_bd_opaque = prod;
+		}
+	}
+}
+
+static void bnge_init_one_rx_ring_rxbd(struct bnge_net *bn,
+				       struct bnge_rx_ring_info *rxr)
+{
+	struct bnge_ring_struct *ring;
+	u32 type;
+
+	type = (bn->rx_buf_use_size << RX_BD_LEN_SHIFT) |
+		RX_BD_TYPE_RX_PACKET_BD | RX_BD_FLAGS_EOP;
+
+	if (NET_IP_ALIGN == 2)
+		type |= RX_BD_FLAGS_SOP;
+
+	ring = &rxr->rx_ring_struct;
+	bnge_init_rxbd_pages(ring, type);
+	ring->fw_ring_id = INVALID_HW_RING_ID;
+}
+
+static void bnge_init_one_agg_ring_rxbd(struct bnge_net *bn,
+					struct bnge_rx_ring_info *rxr)
+{
+	struct bnge_ring_struct *ring;
+	u32 type;
+
+	ring = &rxr->rx_agg_ring_struct;
+	ring->fw_ring_id = INVALID_HW_RING_ID;
+	if (bnge_is_agg_reqd(bn->bd)) {
+		type = ((u32)BNGE_RX_PAGE_SIZE << RX_BD_LEN_SHIFT) |
+			RX_BD_TYPE_RX_AGG_BD | RX_BD_FLAGS_SOP;
+
+		bnge_init_rxbd_pages(ring, type);
+	}
+}
+
+static void bnge_init_one_rx_ring_pair(struct bnge_net *bn, int ring_nr)
+{
+	struct bnge_rx_ring_info *rxr;
+
+	rxr = &bn->rx_ring[ring_nr];
+	bnge_init_one_rx_ring_rxbd(bn, rxr);
+
+	netif_queue_set_napi(bn->netdev, ring_nr, NETDEV_QUEUE_TYPE_RX,
+			     &rxr->bnapi->napi);
+
+	bnge_init_one_agg_ring_rxbd(bn, rxr);
+}
+
+static int bnge_alloc_rx_ring_pair_bufs(struct bnge_net *bn)
+{
+	int i, rc;
+
+	for (i = 0; i < bn->bd->rx_nr_rings; i++) {
+		rc = bnge_alloc_one_rx_ring_pair_bufs(bn, i);
+		if (rc)
+			goto err_free_rx_ring_pair_bufs;
+	}
+	return 0;
+
+err_free_rx_ring_pair_bufs:
+	bnge_free_rx_ring_pair_bufs(bn);
+	return rc;
+}
+
+static void bnge_init_rx_rings(struct bnge_net *bn)
+{
+	int i;
+
+#define BNGE_RX_OFFSET (NET_SKB_PAD + NET_IP_ALIGN)
+#define BNGE_RX_DMA_OFFSET NET_SKB_PAD
+	bn->rx_offset = BNGE_RX_OFFSET;
+	bn->rx_dma_offset = BNGE_RX_DMA_OFFSET;
+
+	for (i = 0; i < bn->bd->rx_nr_rings; i++)
+		bnge_init_one_rx_ring_pair(bn, i);
+}
+
+static void bnge_init_tx_rings(struct bnge_net *bn)
+{
+	int i;
+
+	bn->tx_wake_thresh = max(bn->tx_ring_size / 2, BNGE_MIN_TX_DESC_CNT);
+
+	for (i = 0; i < bn->bd->tx_nr_rings; i++) {
+		struct bnge_tx_ring_info *txr = &bn->tx_ring[i];
+		struct bnge_ring_struct *ring = &txr->tx_ring_struct;
+
+		ring->fw_ring_id = INVALID_HW_RING_ID;
+
+		netif_queue_set_napi(bn->netdev, i, NETDEV_QUEUE_TYPE_TX,
+				     &txr->bnapi->napi);
+	}
+}
+
+static void bnge_init_vnics(struct bnge_net *bn)
+{
+	struct bnge_vnic_info *vnic0 = &bn->vnic_info[BNGE_VNIC_DEFAULT];
+	int i;
+
+	for (i = 0; i < bn->nr_vnics; i++) {
+		struct bnge_vnic_info *vnic = &bn->vnic_info[i];
+		int j;
+
+		vnic->fw_vnic_id = INVALID_HW_RING_ID;
+		vnic->vnic_id = i;
+		for (j = 0; j < BNGE_MAX_CTX_PER_VNIC; j++)
+			vnic->fw_rss_cos_lb_ctx[j] = INVALID_HW_RING_ID;
+
+		if (bn->vnic_info[i].rss_hash_key) {
+			if (i == BNGE_VNIC_DEFAULT) {
+				u8 *key = (void *)vnic->rss_hash_key;
+				int k;
+
+				if (!bn->rss_hash_key_valid &&
+				    !bn->rss_hash_key_updated) {
+					get_random_bytes(bn->rss_hash_key,
+							 HW_HASH_KEY_SIZE);
+					bn->rss_hash_key_updated = true;
+				}
+
+				memcpy(vnic->rss_hash_key, bn->rss_hash_key,
+				       HW_HASH_KEY_SIZE);
+
+				if (!bn->rss_hash_key_updated)
+					continue;
+
+				bn->rss_hash_key_updated = false;
+				bn->rss_hash_key_valid = true;
+
+				bn->toeplitz_prefix = 0;
+				for (k = 0; k < 8; k++) {
+					bn->toeplitz_prefix <<= 8;
+					bn->toeplitz_prefix |= key[k];
+				}
+			} else {
+				memcpy(vnic->rss_hash_key, vnic0->rss_hash_key,
+				       HW_HASH_KEY_SIZE);
+			}
+		}
+	}
+}
+
+static void bnge_set_db_mask(struct bnge_net *bn, struct bnge_db_info *db,
+			     u32 ring_type)
+{
+	switch (ring_type) {
+	case HWRM_RING_ALLOC_TX:
+		db->db_ring_mask = bn->tx_ring_mask;
+		break;
+	case HWRM_RING_ALLOC_RX:
+		db->db_ring_mask = bn->rx_ring_mask;
+		break;
+	case HWRM_RING_ALLOC_AGG:
+		db->db_ring_mask = bn->rx_agg_ring_mask;
+		break;
+	case HWRM_RING_ALLOC_CMPL:
+	case HWRM_RING_ALLOC_NQ:
+		db->db_ring_mask = bn->cp_ring_mask;
+		break;
+	}
+	db->db_epoch_mask = db->db_ring_mask + 1;
+	db->db_epoch_shift = DBR_EPOCH_SFT - ilog2(db->db_epoch_mask);
+}
+
+static void bnge_set_db(struct bnge_net *bn, struct bnge_db_info *db,
+			u32 ring_type, u32 map_idx, u32 xid)
+{
+	struct bnge_dev *bd = bn->bd;
+
+	switch (ring_type) {
+	case HWRM_RING_ALLOC_TX:
+		db->db_key64 = DBR_PATH_L2 | DBR_TYPE_SQ;
+		break;
+	case HWRM_RING_ALLOC_RX:
+	case HWRM_RING_ALLOC_AGG:
+		db->db_key64 = DBR_PATH_L2 | DBR_TYPE_SRQ;
+		break;
+	case HWRM_RING_ALLOC_CMPL:
+		db->db_key64 = DBR_PATH_L2;
+		break;
+	case HWRM_RING_ALLOC_NQ:
+		db->db_key64 = DBR_PATH_L2;
+		break;
+	}
+	db->db_key64 |= ((u64)xid << DBR_XID_SFT) | DBR_VALID;
+
+	db->doorbell = bd->bar1 + bd->db_offset;
+	bnge_set_db_mask(bn, db, ring_type);
+}
+
+static int bnge_hwrm_cp_ring_alloc(struct bnge_net *bn,
+				   struct bnge_cp_ring_info *cpr)
+{
+	const u32 type = HWRM_RING_ALLOC_CMPL;
+	struct bnge_napi *bnapi = cpr->bnapi;
+	struct bnge_ring_struct *ring;
+	u32 map_idx = bnapi->index;
+	int rc;
+
+	ring = &cpr->ring_struct;
+	ring->handle = BNGE_SET_NQ_HDL(cpr);
+	rc = hwrm_ring_alloc_send_msg(bn, ring, type, map_idx);
+	if (rc)
+		return rc;
+
+	bnge_set_db(bn, &cpr->cp_db, type, map_idx, ring->fw_ring_id);
+	bnge_db_cq(bn, &cpr->cp_db, cpr->cp_raw_cons);
+
+	return 0;
+}
+
+static int bnge_hwrm_tx_ring_alloc(struct bnge_net *bn,
+				   struct bnge_tx_ring_info *txr, u32 tx_idx)
+{
+	struct bnge_ring_struct *ring = &txr->tx_ring_struct;
+	const u32 type = HWRM_RING_ALLOC_TX;
+	int rc;
+
+	rc = hwrm_ring_alloc_send_msg(bn, ring, type, tx_idx);
+	if (rc)
+		return rc;
+
+	bnge_set_db(bn, &txr->tx_db, type, tx_idx, ring->fw_ring_id);
+
+	return 0;
+}
+
+static int bnge_hwrm_rx_agg_ring_alloc(struct bnge_net *bn,
+				       struct bnge_rx_ring_info *rxr)
+{
+	struct bnge_ring_struct *ring = &rxr->rx_agg_ring_struct;
+	u32 type = HWRM_RING_ALLOC_AGG;
+	struct bnge_dev *bd = bn->bd;
+	u32 grp_idx = ring->grp_idx;
+	u32 map_idx;
+	int rc;
+
+	map_idx = grp_idx + bd->rx_nr_rings;
+	rc = hwrm_ring_alloc_send_msg(bn, ring, type, map_idx);
+	if (rc)
+		return rc;
+
+	bnge_set_db(bn, &rxr->rx_agg_db, type, map_idx,
+		    ring->fw_ring_id);
+	bnge_db_write(bn->bd, &rxr->rx_agg_db, rxr->rx_agg_prod);
+	bnge_db_write(bn->bd, &rxr->rx_db, rxr->rx_prod);
+	bn->grp_info[grp_idx].agg_fw_ring_id = ring->fw_ring_id;
+
+	return 0;
+}
+
+static int bnge_hwrm_rx_ring_alloc(struct bnge_net *bn,
+				   struct bnge_rx_ring_info *rxr)
+{
+	struct bnge_ring_struct *ring = &rxr->rx_ring_struct;
+	struct bnge_napi *bnapi = rxr->bnapi;
+	u32 type = HWRM_RING_ALLOC_RX;
+	u32 map_idx = bnapi->index;
+	int rc;
+
+	rc = hwrm_ring_alloc_send_msg(bn, ring, type, map_idx);
+	if (rc)
+		return rc;
+
+	bnge_set_db(bn, &rxr->rx_db, type, map_idx, ring->fw_ring_id);
+	bn->grp_info[map_idx].rx_fw_ring_id = ring->fw_ring_id;
+
+	return 0;
+}
+
+static int bnge_hwrm_ring_alloc(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	bool agg_rings;
+	int i, rc = 0;
+
+	agg_rings = !!(bnge_is_agg_reqd(bd));
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		struct bnge_napi *bnapi = bn->bnapi[i];
+		struct bnge_nq_ring_info *nqr = &bnapi->nq_ring;
+		struct bnge_ring_struct *ring = &nqr->ring_struct;
+		u32 type = HWRM_RING_ALLOC_NQ;
+		u32 map_idx = ring->map_idx;
+		unsigned int vector;
+
+		vector = bd->irq_tbl[map_idx].vector;
+		disable_irq_nosync(vector);
+		rc = hwrm_ring_alloc_send_msg(bn, ring, type, map_idx);
+		if (rc) {
+			enable_irq(vector);
+			goto err_out;
+		}
+		bnge_set_db(bn, &nqr->nq_db, type, map_idx, ring->fw_ring_id);
+		bnge_db_nq(bn, &nqr->nq_db, nqr->nq_raw_cons);
+		enable_irq(vector);
+		bn->grp_info[i].nq_fw_ring_id = ring->fw_ring_id;
+
+		if (!i) {
+			rc = bnge_hwrm_set_async_event_cr(bd, ring->fw_ring_id);
+			if (rc)
+				netdev_warn(bn->netdev, "Failed to set async event completion ring.\n");
+		}
+	}
+
+	for (i = 0; i < bd->tx_nr_rings; i++) {
+		struct bnge_tx_ring_info *txr = &bn->tx_ring[i];
+
+		rc = bnge_hwrm_cp_ring_alloc(bn, txr->tx_cpr);
+		if (rc)
+			goto err_out;
+		rc = bnge_hwrm_tx_ring_alloc(bn, txr, i);
+		if (rc)
+			goto err_out;
+	}
+
+	for (i = 0; i < bd->rx_nr_rings; i++) {
+		struct bnge_rx_ring_info *rxr = &bn->rx_ring[i];
+		struct bnge_cp_ring_info *cpr;
+		struct bnge_ring_struct *ring;
+		struct bnge_napi *bnapi;
+		u32 map_idx, type;
+
+		rc = bnge_hwrm_rx_ring_alloc(bn, rxr);
+		if (rc)
+			goto err_out;
+		/* If we have agg rings, post agg buffers first. */
+		if (!agg_rings)
+			bnge_db_write(bn->bd, &rxr->rx_db, rxr->rx_prod);
+
+		cpr = rxr->rx_cpr;
+		bnapi = rxr->bnapi;
+		type = HWRM_RING_ALLOC_CMPL;
+		map_idx = bnapi->index;
+
+		ring = &cpr->ring_struct;
+		ring->handle = BNGE_SET_NQ_HDL(cpr);
+		rc = hwrm_ring_alloc_send_msg(bn, ring, type, map_idx);
+		if (rc)
+			goto err_out;
+		bnge_set_db(bn, &cpr->cp_db, type, map_idx,
+			    ring->fw_ring_id);
+		bnge_db_cq(bn, &cpr->cp_db, cpr->cp_raw_cons);
+	}
+
+	if (agg_rings) {
+		for (i = 0; i < bd->rx_nr_rings; i++) {
+			rc = bnge_hwrm_rx_agg_ring_alloc(bn, &bn->rx_ring[i]);
+			if (rc)
+				goto err_out;
+		}
+	}
+err_out:
+	return rc;
+}
+
+void bnge_fill_hw_rss_tbl(struct bnge_net *bn, struct bnge_vnic_info *vnic)
+{
+	__le16 *ring_tbl = vnic->rss_table;
+	struct bnge_rx_ring_info *rxr;
+	struct bnge_dev *bd = bn->bd;
+	u16 tbl_size, i;
+
+	tbl_size = bnge_get_rxfh_indir_size(bd);
+
+	for (i = 0; i < tbl_size; i++) {
+		u16 ring_id, j;
+
+		j = bd->rss_indir_tbl[i];
+		rxr = &bn->rx_ring[j];
+
+		ring_id = rxr->rx_ring_struct.fw_ring_id;
+		*ring_tbl++ = cpu_to_le16(ring_id);
+		ring_id = bnge_cp_ring_for_rx(rxr);
+		*ring_tbl++ = cpu_to_le16(ring_id);
+	}
+}
+
+static int bnge_hwrm_vnic_rss_cfg(struct bnge_net *bn,
+				  struct bnge_vnic_info *vnic)
+{
+	int rc;
+
+	rc = bnge_hwrm_vnic_set_rss(bn, vnic, true);
+	if (rc) {
+		netdev_err(bn->netdev, "hwrm vnic %d set rss failure rc: %d\n",
+			   vnic->vnic_id, rc);
+		return rc;
+	}
+	rc = bnge_hwrm_vnic_cfg(bn, vnic);
+	if (rc)
+		netdev_err(bn->netdev, "hwrm vnic %d cfg failure rc: %d\n",
+			   vnic->vnic_id, rc);
+	return rc;
+}
+
+static int bnge_setup_vnic(struct bnge_net *bn, struct bnge_vnic_info *vnic)
+{
+	struct bnge_dev *bd = bn->bd;
+	int rc, i, nr_ctxs;
+
+	nr_ctxs = bnge_cal_nr_rss_ctxs(bd->rx_nr_rings);
+	for (i = 0; i < nr_ctxs; i++) {
+		rc = bnge_hwrm_vnic_ctx_alloc(bd, vnic, i);
+		if (rc) {
+			netdev_err(bn->netdev, "hwrm vnic %d ctx %d alloc failure rc: %d\n",
+				   vnic->vnic_id, i, rc);
+			return -ENOMEM;
+		}
+		bn->rsscos_nr_ctxs++;
+	}
+
+	rc = bnge_hwrm_vnic_rss_cfg(bn, vnic);
+	if (rc)
+		return rc;
+
+	if (bnge_is_agg_reqd(bd)) {
+		rc = bnge_hwrm_vnic_set_hds(bn, vnic);
+		if (rc)
+			netdev_err(bn->netdev, "hwrm vnic %d set hds failure rc: %d\n",
+				   vnic->vnic_id, rc);
+	}
+	return rc;
+}
+
+static void bnge_del_l2_filter(struct bnge_net *bn, struct bnge_l2_filter *fltr)
+{
+	if (!refcount_dec_and_test(&fltr->refcnt))
+		return;
+	hlist_del_rcu(&fltr->base.hash);
+	kfree_rcu(fltr, base.rcu);
+}
+
+static void bnge_init_l2_filter(struct bnge_net *bn,
+				struct bnge_l2_filter *fltr,
+				struct bnge_l2_key *key, u32 idx)
+{
+	struct hlist_head *head;
+
+	ether_addr_copy(fltr->l2_key.dst_mac_addr, key->dst_mac_addr);
+	fltr->l2_key.vlan = key->vlan;
+	fltr->base.type = BNGE_FLTR_TYPE_L2;
+
+	head = &bn->l2_fltr_hash_tbl[idx];
+	hlist_add_head_rcu(&fltr->base.hash, head);
+	refcount_set(&fltr->refcnt, 1);
+}
+
+static struct bnge_l2_filter *__bnge_lookup_l2_filter(struct bnge_net *bn,
+						      struct bnge_l2_key *key,
+						      u32 idx)
+{
+	struct bnge_l2_filter *fltr;
+	struct hlist_head *head;
+
+	head = &bn->l2_fltr_hash_tbl[idx];
+	hlist_for_each_entry_rcu(fltr, head, base.hash) {
+		struct bnge_l2_key *l2_key = &fltr->l2_key;
+
+		if (ether_addr_equal(l2_key->dst_mac_addr, key->dst_mac_addr) &&
+		    l2_key->vlan == key->vlan)
+			return fltr;
+	}
+	return NULL;
+}
+
+static struct bnge_l2_filter *bnge_lookup_l2_filter(struct bnge_net *bn,
+						    struct bnge_l2_key *key,
+						    u32 idx)
+{
+	struct bnge_l2_filter *fltr;
+
+	rcu_read_lock();
+	fltr = __bnge_lookup_l2_filter(bn, key, idx);
+	if (fltr)
+		refcount_inc(&fltr->refcnt);
+	rcu_read_unlock();
+	return fltr;
+}
+
+static struct bnge_l2_filter *bnge_alloc_l2_filter(struct bnge_net *bn,
+						   struct bnge_l2_key *key,
+						   gfp_t gfp)
+{
+	struct bnge_l2_filter *fltr;
+	u32 idx;
+
+	idx = jhash2(&key->filter_key, BNGE_L2_KEY_SIZE, bn->hash_seed) &
+	      BNGE_L2_FLTR_HASH_MASK;
+	fltr = bnge_lookup_l2_filter(bn, key, idx);
+	if (fltr)
+		return fltr;
+
+	fltr = kzalloc(sizeof(*fltr), gfp);
+	if (!fltr)
+		return ERR_PTR(-ENOMEM);
+
+	bnge_init_l2_filter(bn, fltr, key, idx);
+	return fltr;
+}
+
+static int bnge_hwrm_set_vnic_filter(struct bnge_net *bn, u16 vnic_id, u16 idx,
+				     const u8 *mac_addr)
+{
+	struct bnge_l2_filter *fltr;
+	struct bnge_l2_key key;
+	int rc;
+
+	ether_addr_copy(key.dst_mac_addr, mac_addr);
+	key.vlan = 0;
+	fltr = bnge_alloc_l2_filter(bn, &key, GFP_KERNEL);
+	if (IS_ERR(fltr))
+		return PTR_ERR(fltr);
+
+	fltr->base.fw_vnic_id = bn->vnic_info[vnic_id].fw_vnic_id;
+	rc = bnge_hwrm_l2_filter_alloc(bn->bd, fltr);
+	if (rc)
+		goto err_del_l2_filter;
+	bn->vnic_info[vnic_id].l2_filters[idx] = fltr;
+	return rc;
+
+err_del_l2_filter:
+	bnge_del_l2_filter(bn, fltr);
+	return rc;
+}
+
+static bool bnge_mc_list_updated(struct bnge_net *bn, u32 *rx_mask)
+{
+	struct bnge_vnic_info *vnic = &bn->vnic_info[BNGE_VNIC_DEFAULT];
+	struct net_device *dev = bn->netdev;
+	struct netdev_hw_addr *ha;
+	int mc_count = 0, off = 0;
+	bool update = false;
+	u8 *haddr;
+
+	netdev_for_each_mc_addr(ha, dev) {
+		if (mc_count >= BNGE_MAX_MC_ADDRS) {
+			*rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST;
+			vnic->mc_list_count = 0;
+			return false;
+		}
+		haddr = ha->addr;
+		if (!ether_addr_equal(haddr, vnic->mc_list + off)) {
+			memcpy(vnic->mc_list + off, haddr, ETH_ALEN);
+			update = true;
+		}
+		off += ETH_ALEN;
+		mc_count++;
+	}
+	if (mc_count)
+		*rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_MCAST;
+
+	if (mc_count != vnic->mc_list_count) {
+		vnic->mc_list_count = mc_count;
+		update = true;
+	}
+	return update;
+}
+
+static bool bnge_uc_list_updated(struct bnge_net *bn)
+{
+	struct bnge_vnic_info *vnic = &bn->vnic_info[BNGE_VNIC_DEFAULT];
+	struct net_device *dev = bn->netdev;
+	struct netdev_hw_addr *ha;
+	int off = 0;
+
+	if (netdev_uc_count(dev) != (vnic->uc_filter_count - 1))
+		return true;
+
+	netdev_for_each_uc_addr(ha, dev) {
+		if (!ether_addr_equal(ha->addr, vnic->uc_list + off))
+			return true;
+
+		off += ETH_ALEN;
+	}
+	return false;
+}
+
+static bool bnge_promisc_ok(struct bnge_net *bn)
+{
+	return true;
+}
+
+static int bnge_cfg_def_vnic(struct bnge_net *bn)
+{
+	struct bnge_vnic_info *vnic = &bn->vnic_info[BNGE_VNIC_DEFAULT];
+	struct net_device *dev = bn->netdev;
+	struct bnge_dev *bd = bn->bd;
+	struct netdev_hw_addr *ha;
+	int i, off = 0, rc;
+	bool uc_update;
+
+	netif_addr_lock_bh(dev);
+	uc_update = bnge_uc_list_updated(bn);
+	netif_addr_unlock_bh(dev);
+
+	if (!uc_update)
+		goto skip_uc;
+
+	for (i = 1; i < vnic->uc_filter_count; i++) {
+		struct bnge_l2_filter *fltr = vnic->l2_filters[i];
+
+		bnge_hwrm_l2_filter_free(bd, fltr);
+		bnge_del_l2_filter(bn, fltr);
+	}
+
+	vnic->uc_filter_count = 1;
+
+	netif_addr_lock_bh(dev);
+	if (netdev_uc_count(dev) > (BNGE_MAX_UC_ADDRS - 1)) {
+		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS;
+	} else {
+		netdev_for_each_uc_addr(ha, dev) {
+			memcpy(vnic->uc_list + off, ha->addr, ETH_ALEN);
+			off += ETH_ALEN;
+			vnic->uc_filter_count++;
+		}
+	}
+	netif_addr_unlock_bh(dev);
+
+	for (i = 1, off = 0; i < vnic->uc_filter_count; i++, off += ETH_ALEN) {
+		rc = bnge_hwrm_set_vnic_filter(bn, 0, i, vnic->uc_list + off);
+		if (rc) {
+			netdev_err(dev, "HWRM vnic filter failure rc: %d\n", rc);
+			vnic->uc_filter_count = i;
+			return rc;
+		}
+	}
+
+skip_uc:
+	if ((vnic->rx_mask & CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS) &&
+	    !bnge_promisc_ok(bn))
+		vnic->rx_mask &= ~CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS;
+	rc = bnge_hwrm_cfa_l2_set_rx_mask(bd, vnic);
+	if (rc && (vnic->rx_mask & CFA_L2_SET_RX_MASK_REQ_MASK_MCAST)) {
+		netdev_info(dev, "Failed setting MC filters rc: %d, turning on ALL_MCAST mode\n",
+			    rc);
+		vnic->rx_mask &= ~CFA_L2_SET_RX_MASK_REQ_MASK_MCAST;
+		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST;
+		vnic->mc_list_count = 0;
+		rc = bnge_hwrm_cfa_l2_set_rx_mask(bd, vnic);
+	}
+	if (rc)
+		netdev_err(dev, "HWRM cfa l2 rx mask failure rc: %d\n",
+			   rc);
+
+	return rc;
+}
+
+static void bnge_hwrm_vnic_free(struct bnge_net *bn)
+{
+	int i;
+
+	for (i = 0; i < bn->nr_vnics; i++)
+		bnge_hwrm_vnic_free_one(bn->bd, &bn->vnic_info[i]);
+}
+
+static void bnge_hwrm_vnic_ctx_free(struct bnge_net *bn)
+{
+	int i, j;
+
+	for (i = 0; i < bn->nr_vnics; i++) {
+		struct bnge_vnic_info *vnic = &bn->vnic_info[i];
+
+		for (j = 0; j < BNGE_MAX_CTX_PER_VNIC; j++) {
+			if (vnic->fw_rss_cos_lb_ctx[j] != INVALID_HW_RING_ID)
+				bnge_hwrm_vnic_ctx_free_one(bn->bd, vnic, j);
+		}
+	}
+	bn->rsscos_nr_ctxs = 0;
+}
+
+static void bnge_hwrm_clear_vnic_filter(struct bnge_net *bn)
+{
+	struct bnge_vnic_info *vnic = &bn->vnic_info[BNGE_VNIC_DEFAULT];
+	int i;
+
+	for (i = 0; i < vnic->uc_filter_count; i++) {
+		struct bnge_l2_filter *fltr = vnic->l2_filters[i];
+
+		bnge_hwrm_l2_filter_free(bn->bd, fltr);
+		bnge_del_l2_filter(bn, fltr);
+	}
+
+	vnic->uc_filter_count = 0;
+}
+
+static void bnge_clear_vnic(struct bnge_net *bn)
+{
+	bnge_hwrm_clear_vnic_filter(bn);
+	bnge_hwrm_vnic_free(bn);
+	bnge_hwrm_vnic_ctx_free(bn);
+}
+
+static void bnge_hwrm_rx_ring_free(struct bnge_net *bn,
+				   struct bnge_rx_ring_info *rxr,
+				   bool close_path)
+{
+	struct bnge_ring_struct *ring = &rxr->rx_ring_struct;
+	u32 grp_idx = rxr->bnapi->index;
+	u32 cmpl_ring_id;
+
+	if (ring->fw_ring_id == INVALID_HW_RING_ID)
+		return;
+
+	cmpl_ring_id = bnge_cp_ring_for_rx(rxr);
+	hwrm_ring_free_send_msg(bn, ring,
+				RING_FREE_REQ_RING_TYPE_RX,
+				close_path ? cmpl_ring_id :
+				INVALID_HW_RING_ID);
+	ring->fw_ring_id = INVALID_HW_RING_ID;
+	bn->grp_info[grp_idx].rx_fw_ring_id = INVALID_HW_RING_ID;
+}
+
+static void bnge_hwrm_rx_agg_ring_free(struct bnge_net *bn,
+				       struct bnge_rx_ring_info *rxr,
+				       bool close_path)
+{
+	struct bnge_ring_struct *ring = &rxr->rx_agg_ring_struct;
+	u32 grp_idx = rxr->bnapi->index;
+	u32 cmpl_ring_id;
+
+	if (ring->fw_ring_id == INVALID_HW_RING_ID)
+		return;
+
+	cmpl_ring_id = bnge_cp_ring_for_rx(rxr);
+	hwrm_ring_free_send_msg(bn, ring, RING_FREE_REQ_RING_TYPE_RX_AGG,
+				close_path ? cmpl_ring_id :
+				INVALID_HW_RING_ID);
+	ring->fw_ring_id = INVALID_HW_RING_ID;
+	bn->grp_info[grp_idx].agg_fw_ring_id = INVALID_HW_RING_ID;
+}
+
+static void bnge_hwrm_tx_ring_free(struct bnge_net *bn,
+				   struct bnge_tx_ring_info *txr,
+				   bool close_path)
+{
+	struct bnge_ring_struct *ring = &txr->tx_ring_struct;
+	u32 cmpl_ring_id;
+
+	if (ring->fw_ring_id == INVALID_HW_RING_ID)
+		return;
+
+	cmpl_ring_id = close_path ? bnge_cp_ring_for_tx(txr) :
+		       INVALID_HW_RING_ID;
+	hwrm_ring_free_send_msg(bn, ring, RING_FREE_REQ_RING_TYPE_TX,
+				cmpl_ring_id);
+	ring->fw_ring_id = INVALID_HW_RING_ID;
+}
+
+static void bnge_hwrm_cp_ring_free(struct bnge_net *bn,
+				   struct bnge_cp_ring_info *cpr)
+{
+	struct bnge_ring_struct *ring;
+
+	ring = &cpr->ring_struct;
+	if (ring->fw_ring_id == INVALID_HW_RING_ID)
+		return;
+
+	hwrm_ring_free_send_msg(bn, ring, RING_FREE_REQ_RING_TYPE_L2_CMPL,
+				INVALID_HW_RING_ID);
+	ring->fw_ring_id = INVALID_HW_RING_ID;
+}
+
+static void bnge_hwrm_ring_free(struct bnge_net *bn, bool close_path)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i;
+
+	if (!bn->bnapi)
+		return;
+
+	for (i = 0; i < bd->tx_nr_rings; i++)
+		bnge_hwrm_tx_ring_free(bn, &bn->tx_ring[i], close_path);
+
+	for (i = 0; i < bd->rx_nr_rings; i++) {
+		bnge_hwrm_rx_ring_free(bn, &bn->rx_ring[i], close_path);
+		bnge_hwrm_rx_agg_ring_free(bn, &bn->rx_ring[i], close_path);
+	}
+
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		struct bnge_napi *bnapi = bn->bnapi[i];
+		struct bnge_nq_ring_info *nqr;
+		struct bnge_ring_struct *ring;
+		int j;
+
+		nqr = &bnapi->nq_ring;
+		for (j = 0; j < nqr->cp_ring_count && nqr->cp_ring_arr; j++)
+			bnge_hwrm_cp_ring_free(bn, &nqr->cp_ring_arr[j]);
+
+		ring = &nqr->ring_struct;
+		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			hwrm_ring_free_send_msg(bn, ring,
+						RING_FREE_REQ_RING_TYPE_NQ,
+						INVALID_HW_RING_ID);
+			ring->fw_ring_id = INVALID_HW_RING_ID;
+			bn->grp_info[i].nq_fw_ring_id = INVALID_HW_RING_ID;
+		}
+	}
+}
+
+static void bnge_setup_msix(struct bnge_net *bn)
+{
+	struct net_device *dev = bn->netdev;
+	struct bnge_dev *bd = bn->bd;
+	int len, i;
+
+	len = sizeof(bd->irq_tbl[0].name);
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		int map_idx = bnge_cp_num_to_irq_num(bn, i);
+		char *attr;
+
+		if (bd->flags & BNGE_EN_SHARED_CHNL)
+			attr = "TxRx";
+		else if (i < bd->rx_nr_rings)
+			attr = "rx";
+		else
+			attr = "tx";
+
+		snprintf(bd->irq_tbl[map_idx].name, len, "%s-%s-%d", dev->name,
+			 attr, i);
+		bd->irq_tbl[map_idx].handler = bnge_msix;
+	}
+}
+
+static int bnge_setup_interrupts(struct bnge_net *bn)
+{
+	struct net_device *dev = bn->netdev;
+	struct bnge_dev *bd = bn->bd;
+
+	bnge_setup_msix(bn);
+
+	return netif_set_real_num_queues(dev, bd->tx_nr_rings, bd->rx_nr_rings);
+}
+
+static void bnge_hwrm_resource_free(struct bnge_net *bn, bool close_path)
+{
+	bnge_clear_vnic(bn);
+	bnge_hwrm_ring_free(bn, close_path);
+	bnge_hwrm_stat_ctx_free(bn);
+}
+
+static void bnge_free_irq(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	struct bnge_irq *irq;
+	int i;
+
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		int map_idx = bnge_cp_num_to_irq_num(bn, i);
+
+		irq = &bd->irq_tbl[map_idx];
+		if (irq->requested) {
+			if (irq->have_cpumask) {
+				irq_set_affinity_hint(irq->vector, NULL);
+				free_cpumask_var(irq->cpu_mask);
+				irq->have_cpumask = 0;
+			}
+			free_irq(irq->vector, bn->bnapi[i]);
+		}
+
+		irq->requested = 0;
+	}
+}
+
+static int bnge_request_irq(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i, rc;
+
+	rc = bnge_setup_interrupts(bn);
+	if (rc) {
+		netdev_err(bn->netdev, "bnge_setup_interrupts err: %d\n", rc);
+		return rc;
+	}
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		int map_idx = bnge_cp_num_to_irq_num(bn, i);
+		struct bnge_irq *irq = &bd->irq_tbl[map_idx];
+
+		rc = request_irq(irq->vector, irq->handler, 0, irq->name,
+				 bn->bnapi[i]);
+		if (rc)
+			goto err_free_irq;
+
+		netif_napi_set_irq_locked(&bn->bnapi[i]->napi, irq->vector);
+		irq->requested = 1;
+
+		if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) {
+			int numa_node = dev_to_node(&bd->pdev->dev);
+
+			irq->have_cpumask = 1;
+			cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+					irq->cpu_mask);
+			rc = irq_set_affinity_hint(irq->vector, irq->cpu_mask);
+			if (rc) {
+				netdev_warn(bn->netdev,
+					    "Set affinity failed, IRQ = %d\n",
+					    irq->vector);
+				goto err_free_irq;
+			}
+		}
+	}
+	return 0;
+
+err_free_irq:
+	bnge_free_irq(bn);
+	return rc;
+}
+
+static int bnge_init_chip(struct bnge_net *bn)
+{
+	struct bnge_vnic_info *vnic = &bn->vnic_info[BNGE_VNIC_DEFAULT];
+	struct bnge_dev *bd = bn->bd;
+	int rc;
+
+#define BNGE_DEF_STATS_COAL_TICKS	 1000000
+	bn->stats_coal_ticks = BNGE_DEF_STATS_COAL_TICKS;
+
+	rc = bnge_hwrm_stat_ctx_alloc(bn);
+	if (rc) {
+		netdev_err(bn->netdev, "hwrm stat ctx alloc failure rc: %d\n", rc);
+		goto err_out;
+	}
+
+	rc = bnge_hwrm_ring_alloc(bn);
+	if (rc) {
+		netdev_err(bn->netdev, "hwrm ring alloc failure rc: %d\n", rc);
+		goto err_out;
+	}
+
+	rc = bnge_hwrm_vnic_alloc(bd, vnic, bd->rx_nr_rings);
+	if (rc) {
+		netdev_err(bn->netdev, "hwrm vnic alloc failure rc: %d\n", rc);
+		goto err_out;
+	}
+
+	rc = bnge_setup_vnic(bn, vnic);
+	if (rc)
+		goto err_out;
+
+	if (bd->rss_cap & BNGE_RSS_CAP_RSS_HASH_TYPE_DELTA)
+		bnge_hwrm_update_rss_hash_cfg(bn);
+
+	/* Filter for default vnic 0 */
+	rc = bnge_hwrm_set_vnic_filter(bn, 0, 0, bn->netdev->dev_addr);
+	if (rc) {
+		netdev_err(bn->netdev, "HWRM vnic filter failure rc: %d\n", rc);
+		goto err_out;
+	}
+	vnic->uc_filter_count = 1;
+
+	vnic->rx_mask = 0;
+
+	if (bn->netdev->flags & IFF_BROADCAST)
+		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_BCAST;
+
+	if (bn->netdev->flags & IFF_PROMISC)
+		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS;
+
+	if (bn->netdev->flags & IFF_ALLMULTI) {
+		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST;
+		vnic->mc_list_count = 0;
+	} else if (bn->netdev->flags & IFF_MULTICAST) {
+		u32 mask = 0;
+
+		bnge_mc_list_updated(bn, &mask);
+		vnic->rx_mask |= mask;
+	}
+
+	rc = bnge_cfg_def_vnic(bn);
+	if (rc)
+		goto err_out;
+	return 0;
+
+err_out:
+	bnge_hwrm_resource_free(bn, 0);
+	return rc;
+}
+
+static int bnge_napi_poll(struct napi_struct *napi, int budget)
+{
+	int work_done = 0;
+
+	/* defer NAPI implementation to next patch series */
+	napi_complete_done(napi, work_done);
+
+	return work_done;
+}
+
+static void bnge_init_napi(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	struct bnge_napi *bnapi;
+	int i;
+
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		bnapi = bn->bnapi[i];
+		netif_napi_add_config_locked(bn->netdev, &bnapi->napi,
+					     bnge_napi_poll, bnapi->index);
+	}
+}
+
+static void bnge_del_napi(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i;
+
+	for (i = 0; i < bd->rx_nr_rings; i++)
+		netif_queue_set_napi(bn->netdev, i, NETDEV_QUEUE_TYPE_RX, NULL);
+	for (i = 0; i < bd->tx_nr_rings; i++)
+		netif_queue_set_napi(bn->netdev, i, NETDEV_QUEUE_TYPE_TX, NULL);
+
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		struct bnge_napi *bnapi = bn->bnapi[i];
+
+		__netif_napi_del_locked(&bnapi->napi);
+	}
+
+	/* Wait for RCU grace period after removing NAPI instances */
+	synchronize_net();
+}
+
+static int bnge_init_nic(struct bnge_net *bn)
+{
+	int rc;
+
+	bnge_init_nq_tree(bn);
+
+	bnge_init_rx_rings(bn);
+	rc = bnge_alloc_rx_ring_pair_bufs(bn);
+	if (rc)
+		return rc;
+
+	bnge_init_tx_rings(bn);
+
+	rc = bnge_init_ring_grps(bn);
+	if (rc)
+		goto err_free_rx_ring_pair_bufs;
+
+	bnge_init_vnics(bn);
+
+	rc = bnge_init_chip(bn);
+	if (rc)
+		goto err_free_ring_grps;
+	return rc;
+
+err_free_ring_grps:
+	bnge_free_ring_grps(bn);
+	return rc;
+
+err_free_rx_ring_pair_bufs:
+	bnge_free_rx_ring_pair_bufs(bn);
+	return rc;
+}
+
+static int bnge_open_core(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int rc;
+
+	netif_carrier_off(bn->netdev);
+
+	rc = bnge_reserve_rings(bd);
+	if (rc) {
+		netdev_err(bn->netdev, "bnge_reserve_rings err: %d\n", rc);
+		return rc;
+	}
+
+	rc = bnge_alloc_core(bn);
+	if (rc) {
+		netdev_err(bn->netdev, "bnge_alloc_core err: %d\n", rc);
+		return rc;
+	}
+
+	bnge_init_napi(bn);
+	rc = bnge_request_irq(bn);
+	if (rc) {
+		netdev_err(bn->netdev, "bnge_request_irq err: %d\n", rc);
+		goto err_del_napi;
+	}
+
+	rc = bnge_init_nic(bn);
+	if (rc) {
+		netdev_err(bn->netdev, "bnge_init_nic err: %d\n", rc);
+		goto err_free_irq;
+	}
+	set_bit(BNGE_STATE_OPEN, &bd->state);
+	return 0;
+
+err_free_irq:
+	bnge_free_irq(bn);
+err_del_napi:
+	bnge_del_napi(bn);
+	bnge_free_core(bn);
+	return rc;
+}
+
+static netdev_tx_t bnge_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	dev_kfree_skb_any(skb);
+
+	return NETDEV_TX_OK;
+}
+
+static int bnge_open(struct net_device *dev)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+	int rc;
+
+	rc = bnge_open_core(bn);
+	if (rc)
+		netdev_err(dev, "bnge_open_core err: %d\n", rc);
+
+	return rc;
+}
+
+static int bnge_shutdown_nic(struct bnge_net *bn)
+{
+	/* TODO: close_path = 0 until we make NAPI functional */
+	bnge_hwrm_resource_free(bn, 0);
+	return 0;
+}
+
+static void bnge_close_core(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+
+	clear_bit(BNGE_STATE_OPEN, &bd->state);
+	bnge_shutdown_nic(bn);
+	bnge_free_all_rings_bufs(bn);
+	bnge_free_irq(bn);
+	bnge_del_napi(bn);
+
+	bnge_free_core(bn);
+}
+
+static int bnge_close(struct net_device *dev)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+
+	bnge_close_core(bn);
+
+	return 0;
+}
+
+static const struct net_device_ops bnge_netdev_ops = {
+	.ndo_open		= bnge_open,
+	.ndo_stop		= bnge_close,
+	.ndo_start_xmit		= bnge_start_xmit,
+};
+
+static void bnge_init_mac_addr(struct bnge_dev *bd)
+{
+	eth_hw_addr_set(bd->netdev, bd->pf.mac_addr);
+}
+
+static void bnge_set_tpa_flags(struct bnge_dev *bd)
+{
+	struct bnge_net *bn = netdev_priv(bd->netdev);
+
+	bn->priv_flags &= ~BNGE_NET_EN_TPA;
+
+	if (bd->netdev->features & NETIF_F_LRO)
+		bn->priv_flags |= BNGE_NET_EN_LRO;
+	else if (bd->netdev->features & NETIF_F_GRO_HW)
+		bn->priv_flags |= BNGE_NET_EN_GRO;
+}
+
+static void bnge_init_l2_fltr_tbl(struct bnge_net *bn)
+{
+	int i;
+
+	for (i = 0; i < BNGE_L2_FLTR_HASH_SIZE; i++)
+		INIT_HLIST_HEAD(&bn->l2_fltr_hash_tbl[i]);
+	get_random_bytes(&bn->hash_seed, sizeof(bn->hash_seed));
+}
+
+void bnge_set_ring_params(struct bnge_dev *bd)
+{
+	struct bnge_net *bn = netdev_priv(bd->netdev);
+	u32 ring_size, rx_size, rx_space, max_rx_cmpl;
+	u32 agg_factor = 0, agg_ring_size = 0;
+
+	/* 8 for CRC and VLAN */
+	rx_size = SKB_DATA_ALIGN(bn->netdev->mtu + ETH_HLEN + NET_IP_ALIGN + 8);
+
+	rx_space = rx_size + ALIGN(NET_SKB_PAD, 8) +
+		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+	bn->rx_copy_thresh = BNGE_RX_COPY_THRESH;
+	ring_size = bn->rx_ring_size;
+	bn->rx_agg_ring_size = 0;
+	bn->rx_agg_nr_pages = 0;
+
+	if (bn->priv_flags & BNGE_NET_EN_TPA)
+		agg_factor = min_t(u32, 4, 65536 / BNGE_RX_PAGE_SIZE);
+
+	bn->priv_flags &= ~BNGE_NET_EN_JUMBO;
+	if (rx_space > PAGE_SIZE) {
+		u32 jumbo_factor;
+
+		bn->priv_flags |= BNGE_NET_EN_JUMBO;
+		jumbo_factor = PAGE_ALIGN(bn->netdev->mtu - 40) >> PAGE_SHIFT;
+		if (jumbo_factor > agg_factor)
+			agg_factor = jumbo_factor;
+	}
+	if (agg_factor) {
+		if (ring_size > BNGE_MAX_RX_DESC_CNT_JUM_ENA) {
+			ring_size = BNGE_MAX_RX_DESC_CNT_JUM_ENA;
+			netdev_warn(bn->netdev, "RX ring size reduced from %d to %d due to jumbo ring\n",
+				    bn->rx_ring_size, ring_size);
+			bn->rx_ring_size = ring_size;
+		}
+		agg_ring_size = ring_size * agg_factor;
+
+		bn->rx_agg_nr_pages = bnge_adjust_pow_two(agg_ring_size,
+							  RX_DESC_CNT);
+		if (bn->rx_agg_nr_pages > MAX_RX_AGG_PAGES) {
+			u32 tmp = agg_ring_size;
+
+			bn->rx_agg_nr_pages = MAX_RX_AGG_PAGES;
+			agg_ring_size = MAX_RX_AGG_PAGES * RX_DESC_CNT - 1;
+			netdev_warn(bn->netdev, "RX agg ring size %d reduced to %d.\n",
+				    tmp, agg_ring_size);
+		}
+		bn->rx_agg_ring_size = agg_ring_size;
+		bn->rx_agg_ring_mask = (bn->rx_agg_nr_pages * RX_DESC_CNT) - 1;
+
+		rx_size = SKB_DATA_ALIGN(BNGE_RX_COPY_THRESH + NET_IP_ALIGN);
+		rx_space = rx_size + NET_SKB_PAD +
+			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	}
+
+	bn->rx_buf_use_size = rx_size;
+	bn->rx_buf_size = rx_space;
+
+	bn->rx_nr_pages = bnge_adjust_pow_two(ring_size, RX_DESC_CNT);
+	bn->rx_ring_mask = (bn->rx_nr_pages * RX_DESC_CNT) - 1;
+
+	ring_size = bn->tx_ring_size;
+	bn->tx_nr_pages = bnge_adjust_pow_two(ring_size, TX_DESC_CNT);
+	bn->tx_ring_mask = (bn->tx_nr_pages * TX_DESC_CNT) - 1;
+
+	max_rx_cmpl = bn->rx_ring_size;
+
+	if (bn->priv_flags & BNGE_NET_EN_TPA)
+		max_rx_cmpl += bd->max_tpa_v2;
+	ring_size = max_rx_cmpl * 2 + agg_ring_size + bn->tx_ring_size;
+	bn->cp_ring_size = ring_size;
+
+	bn->cp_nr_pages = bnge_adjust_pow_two(ring_size, CP_DESC_CNT);
+	if (bn->cp_nr_pages > MAX_CP_PAGES) {
+		bn->cp_nr_pages = MAX_CP_PAGES;
+		bn->cp_ring_size = MAX_CP_PAGES * CP_DESC_CNT - 1;
+		netdev_warn(bn->netdev, "completion ring size %d reduced to %d.\n",
+			    ring_size, bn->cp_ring_size);
+	}
+	bn->cp_bit = bn->cp_nr_pages * CP_DESC_CNT;
+	bn->cp_ring_mask = bn->cp_bit - 1;
+}
+
+int bnge_netdev_alloc(struct bnge_dev *bd, int max_irqs)
+{
+	struct net_device *netdev;
+	struct bnge_net *bn;
+	int rc;
+
+	netdev = alloc_etherdev_mqs(sizeof(*bn), max_irqs * BNGE_MAX_QUEUE,
+				    max_irqs);
+	if (!netdev)
+		return -ENOMEM;
+
+	SET_NETDEV_DEV(netdev, bd->dev);
+	bd->netdev = netdev;
+
+	netdev->netdev_ops = &bnge_netdev_ops;
+
+	bnge_set_ethtool_ops(netdev);
+
+	bn = netdev_priv(netdev);
+	bn->netdev = netdev;
+	bn->bd = bd;
+
+	netdev->min_mtu = ETH_ZLEN;
+	netdev->max_mtu = bd->max_mtu;
+
+	netdev->hw_features = NETIF_F_IP_CSUM |
+			      NETIF_F_IPV6_CSUM |
+			      NETIF_F_SG |
+			      NETIF_F_TSO |
+			      NETIF_F_TSO6 |
+			      NETIF_F_GSO_UDP_TUNNEL |
+			      NETIF_F_GSO_GRE |
+			      NETIF_F_GSO_IPXIP4 |
+			      NETIF_F_GSO_UDP_TUNNEL_CSUM |
+			      NETIF_F_GSO_GRE_CSUM |
+			      NETIF_F_GSO_PARTIAL |
+			      NETIF_F_RXHASH |
+			      NETIF_F_RXCSUM |
+			      NETIF_F_GRO;
+
+	if (bd->flags & BNGE_EN_UDP_GSO_SUPP)
+		netdev->hw_features |= NETIF_F_GSO_UDP_L4;
+
+	if (BNGE_SUPPORTS_TPA(bd))
+		netdev->hw_features |= NETIF_F_LRO;
+
+	netdev->hw_enc_features = NETIF_F_IP_CSUM |
+				  NETIF_F_IPV6_CSUM |
+				  NETIF_F_SG |
+				  NETIF_F_TSO |
+				  NETIF_F_TSO6 |
+				  NETIF_F_GSO_UDP_TUNNEL |
+				  NETIF_F_GSO_GRE |
+				  NETIF_F_GSO_UDP_TUNNEL_CSUM |
+				  NETIF_F_GSO_GRE_CSUM |
+				  NETIF_F_GSO_IPXIP4 |
+				  NETIF_F_GSO_PARTIAL;
+
+	if (bd->flags & BNGE_EN_UDP_GSO_SUPP)
+		netdev->hw_enc_features |= NETIF_F_GSO_UDP_L4;
+
+	netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM |
+				       NETIF_F_GSO_GRE_CSUM;
+
+	netdev->vlan_features = netdev->hw_features | NETIF_F_HIGHDMA;
+	if (bd->fw_cap & BNGE_FW_CAP_VLAN_RX_STRIP)
+		netdev->hw_features |= BNGE_HW_FEATURE_VLAN_ALL_RX;
+	if (bd->fw_cap & BNGE_FW_CAP_VLAN_TX_INSERT)
+		netdev->hw_features |= BNGE_HW_FEATURE_VLAN_ALL_TX;
+
+	if (BNGE_SUPPORTS_TPA(bd))
+		netdev->hw_features |= NETIF_F_GRO_HW;
+
+	netdev->features |= netdev->hw_features | NETIF_F_HIGHDMA;
+
+	if (netdev->features & NETIF_F_GRO_HW)
+		netdev->features &= ~NETIF_F_LRO;
+
+	netdev->priv_flags |= IFF_UNICAST_FLT;
+
+	netif_set_tso_max_size(netdev, GSO_MAX_SIZE);
+	if (bd->tso_max_segs)
+		netif_set_tso_max_segs(netdev, bd->tso_max_segs);
+
+	bn->rx_ring_size = BNGE_DEFAULT_RX_RING_SIZE;
+	bn->tx_ring_size = BNGE_DEFAULT_TX_RING_SIZE;
+	bn->rx_dir = DMA_FROM_DEVICE;
+
+	bnge_set_tpa_flags(bd);
+	bnge_set_ring_params(bd);
+
+	bnge_init_l2_fltr_tbl(bn);
+	bnge_init_mac_addr(bd);
+
+	netdev->request_ops_lock = true;
+	rc = register_netdev(netdev);
+	if (rc) {
+		dev_err(bd->dev, "Register netdev failed rc: %d\n", rc);
+		goto err_netdev;
+	}
+
+	return 0;
+
+err_netdev:
+	free_netdev(netdev);
+	return rc;
+}
+
+void bnge_netdev_free(struct bnge_dev *bd)
+{
+	struct net_device *netdev = bd->netdev;
+
+	unregister_netdev(netdev);
+	free_netdev(netdev);
+	bd->netdev = NULL;
+}
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h
new file mode 100644
index 000000000000..fb3b961536ba
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h
@@ -0,0 +1,454 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Broadcom */
+
+#ifndef _BNGE_NETDEV_H_
+#define _BNGE_NETDEV_H_
+
+#include <linux/bnxt/hsi.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/refcount.h>
+#include "bnge_db.h"
+
+struct tx_bd {
+	__le32 tx_bd_len_flags_type;
+	#define TX_BD_TYPE					(0x3f << 0)
+	#define TX_BD_TYPE_SHORT_TX_BD				(0x00 << 0)
+	#define TX_BD_TYPE_LONG_TX_BD				(0x10 << 0)
+	#define TX_BD_FLAGS_PACKET_END				(1 << 6)
+	#define TX_BD_FLAGS_NO_CMPL				(1 << 7)
+	#define TX_BD_FLAGS_BD_CNT				(0x1f << 8)
+	#define TX_BD_FLAGS_BD_CNT_SHIFT			8
+	#define TX_BD_FLAGS_LHINT				(3 << 13)
+	#define TX_BD_FLAGS_LHINT_SHIFT				13
+	#define TX_BD_FLAGS_LHINT_512_AND_SMALLER		(0 << 13)
+	#define TX_BD_FLAGS_LHINT_512_TO_1023			(1 << 13)
+	#define TX_BD_FLAGS_LHINT_1024_TO_2047			(2 << 13)
+	#define TX_BD_FLAGS_LHINT_2048_AND_LARGER		(3 << 13)
+	#define TX_BD_FLAGS_COAL_NOW				(1 << 15)
+	#define TX_BD_LEN					(0xffff << 16)
+	#define TX_BD_LEN_SHIFT					16
+	u32 tx_bd_opaque;
+	__le64 tx_bd_haddr;
+} __packed;
+
+struct rx_bd {
+	__le32 rx_bd_len_flags_type;
+	#define RX_BD_TYPE					(0x3f << 0)
+	#define RX_BD_TYPE_RX_PACKET_BD				0x4
+	#define RX_BD_TYPE_RX_BUFFER_BD				0x5
+	#define RX_BD_TYPE_RX_AGG_BD				0x6
+	#define RX_BD_TYPE_16B_BD_SIZE				(0 << 4)
+	#define RX_BD_TYPE_32B_BD_SIZE				(1 << 4)
+	#define RX_BD_TYPE_48B_BD_SIZE				(2 << 4)
+	#define RX_BD_TYPE_64B_BD_SIZE				(3 << 4)
+	#define RX_BD_FLAGS_SOP					(1 << 6)
+	#define RX_BD_FLAGS_EOP					(1 << 7)
+	#define RX_BD_FLAGS_BUFFERS				(3 << 8)
+	#define RX_BD_FLAGS_1_BUFFER_PACKET			(0 << 8)
+	#define RX_BD_FLAGS_2_BUFFER_PACKET			(1 << 8)
+	#define RX_BD_FLAGS_3_BUFFER_PACKET			(2 << 8)
+	#define RX_BD_FLAGS_4_BUFFER_PACKET			(3 << 8)
+	#define RX_BD_LEN					(0xffff << 16)
+	#define RX_BD_LEN_SHIFT					16
+	u32 rx_bd_opaque;
+	__le64 rx_bd_haddr;
+};
+
+struct tx_cmp {
+	__le32 tx_cmp_flags_type;
+	#define CMP_TYPE					(0x3f << 0)
+	#define CMP_TYPE_TX_L2_CMP				0
+	#define CMP_TYPE_TX_L2_COAL_CMP				2
+	#define CMP_TYPE_TX_L2_PKT_TS_CMP			4
+	#define CMP_TYPE_RX_L2_CMP				17
+	#define CMP_TYPE_RX_AGG_CMP				18
+	#define CMP_TYPE_RX_L2_TPA_START_CMP			19
+	#define CMP_TYPE_RX_L2_TPA_END_CMP			21
+	#define CMP_TYPE_RX_TPA_AGG_CMP				22
+	#define CMP_TYPE_RX_L2_V3_CMP				23
+	#define CMP_TYPE_RX_L2_TPA_START_V3_CMP			25
+	#define CMP_TYPE_STATUS_CMP				32
+	#define CMP_TYPE_REMOTE_DRIVER_REQ			34
+	#define CMP_TYPE_REMOTE_DRIVER_RESP			36
+	#define CMP_TYPE_ERROR_STATUS				48
+	#define CMPL_BASE_TYPE_STAT_EJECT			0x1aUL
+	#define CMPL_BASE_TYPE_HWRM_DONE			0x20UL
+	#define CMPL_BASE_TYPE_HWRM_FWD_REQ			0x22UL
+	#define CMPL_BASE_TYPE_HWRM_FWD_RESP			0x24UL
+	#define CMPL_BASE_TYPE_HWRM_ASYNC_EVENT			0x2eUL
+	#define TX_CMP_FLAGS_ERROR				(1 << 6)
+	#define TX_CMP_FLAGS_PUSH				(1 << 7)
+	u32 tx_cmp_opaque;
+	__le32 tx_cmp_errors_v;
+	#define TX_CMP_V					(1 << 0)
+	#define TX_CMP_ERRORS_BUFFER_ERROR			(7 << 1)
+	#define TX_CMP_ERRORS_BUFFER_ERROR_NO_ERROR		0
+	#define TX_CMP_ERRORS_BUFFER_ERROR_BAD_FORMAT		2
+	#define TX_CMP_ERRORS_BUFFER_ERROR_INVALID_STAG		4
+	#define TX_CMP_ERRORS_BUFFER_ERROR_STAG_BOUNDS		5
+	#define TX_CMP_ERRORS_ZERO_LENGTH_PKT			(1 << 4)
+	#define TX_CMP_ERRORS_EXCESSIVE_BD_LEN			(1 << 5)
+	#define TX_CMP_ERRORS_DMA_ERROR				(1 << 6)
+	#define TX_CMP_ERRORS_HINT_TOO_SHORT			(1 << 7)
+	__le32 sq_cons_idx;
+	#define TX_CMP_SQ_CONS_IDX_MASK				0x00ffffff
+};
+
+struct bnge_sw_tx_bd {
+	struct sk_buff		*skb;
+	DEFINE_DMA_UNMAP_ADDR(mapping);
+	DEFINE_DMA_UNMAP_LEN(len);
+	struct page		*page;
+	u8			is_ts_pkt;
+	u8			is_push;
+	u8			action;
+	unsigned short		nr_frags;
+	union {
+		u16		rx_prod;
+		u16		txts_prod;
+	};
+};
+
+struct bnge_sw_rx_bd {
+	void			*data;
+	u8			*data_ptr;
+	dma_addr_t		mapping;
+};
+
+struct bnge_sw_rx_agg_bd {
+	netmem_ref		netmem;
+	unsigned int		offset;
+	dma_addr_t		mapping;
+};
+
+#define HWRM_RING_ALLOC_TX	0x1
+#define HWRM_RING_ALLOC_RX	0x2
+#define HWRM_RING_ALLOC_AGG	0x4
+#define HWRM_RING_ALLOC_CMPL	0x8
+#define HWRM_RING_ALLOC_NQ	0x10
+
+struct bnge_ring_grp_info {
+	u16	fw_stats_ctx;
+	u16	fw_grp_id;
+	u16	rx_fw_ring_id;
+	u16	agg_fw_ring_id;
+	u16	nq_fw_ring_id;
+};
+
+#define BNGE_RX_COPY_THRESH     256
+
+#define BNGE_HW_FEATURE_VLAN_ALL_RX	\
+		(NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)
+#define BNGE_HW_FEATURE_VLAN_ALL_TX	\
+		(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX)
+
+enum {
+	BNGE_NET_EN_GRO		= BIT(0),
+	BNGE_NET_EN_LRO		= BIT(1),
+	BNGE_NET_EN_JUMBO	= BIT(2),
+};
+
+#define BNGE_NET_EN_TPA		(BNGE_NET_EN_GRO | BNGE_NET_EN_LRO)
+
+/* Minimum TX BDs for a TX packet with MAX_SKB_FRAGS + 1. We need one extra
+ * BD because the first TX BD is always a long BD.
+ */
+#define BNGE_MIN_TX_DESC_CNT	(MAX_SKB_FRAGS + 2)
+
+#define RX_RING(bn, x)	(((x) & (bn)->rx_ring_mask) >> (BNGE_PAGE_SHIFT - 4))
+#define RX_AGG_RING(bn, x)	(((x) & (bn)->rx_agg_ring_mask) >>	\
+				 (BNGE_PAGE_SHIFT - 4))
+#define RX_IDX(x)	((x) & (RX_DESC_CNT - 1))
+
+#define TX_RING(bn, x)	(((x) & (bn)->tx_ring_mask) >> (BNGE_PAGE_SHIFT - 4))
+#define TX_IDX(x)	((x) & (TX_DESC_CNT - 1))
+
+#define CP_RING(x)	(((x) & ~(CP_DESC_CNT - 1)) >> (BNGE_PAGE_SHIFT - 4))
+#define CP_IDX(x)	((x) & (CP_DESC_CNT - 1))
+
+#define RING_RX(bn, idx)	((idx) & (bn)->rx_ring_mask)
+#define NEXT_RX(idx)		((idx) + 1)
+
+#define RING_RX_AGG(bn, idx)	((idx) & (bn)->rx_agg_ring_mask)
+#define NEXT_RX_AGG(idx)	((idx) + 1)
+
+#define BNGE_NQ_HDL_TYPE_SHIFT	24
+#define BNGE_NQ_HDL_TYPE_RX	0x00
+#define BNGE_NQ_HDL_TYPE_TX	0x01
+
+struct bnge_net {
+	struct bnge_dev		*bd;
+	struct net_device	*netdev;
+
+	u32			priv_flags;
+
+	u32			rx_ring_size;
+	u32			rx_buf_size;
+	u32			rx_buf_use_size; /* usable size */
+	u32			rx_agg_ring_size;
+	u32			rx_copy_thresh;
+	u32			rx_ring_mask;
+	u32			rx_agg_ring_mask;
+	u16			rx_nr_pages;
+	u16			rx_agg_nr_pages;
+
+	u32			tx_ring_size;
+	u32			tx_ring_mask;
+	u16			tx_nr_pages;
+
+	/* NQs and Completion rings */
+	u32			cp_ring_size;
+	u32			cp_ring_mask;
+	u32			cp_bit;
+	u16			cp_nr_pages;
+
+#define BNGE_L2_FLTR_HASH_SIZE	32
+#define BNGE_L2_FLTR_HASH_MASK	(BNGE_L2_FLTR_HASH_SIZE - 1)
+	struct hlist_head	l2_fltr_hash_tbl[BNGE_L2_FLTR_HASH_SIZE];
+	u32			hash_seed;
+	u64			toeplitz_prefix;
+
+	struct bnge_napi		**bnapi;
+
+	struct bnge_rx_ring_info	*rx_ring;
+	struct bnge_tx_ring_info	*tx_ring;
+
+	u16				*tx_ring_map;
+	enum dma_data_direction		rx_dir;
+
+	/* grp_info indexed by napi/nq index */
+	struct bnge_ring_grp_info	*grp_info;
+	struct bnge_vnic_info		*vnic_info;
+	int				nr_vnics;
+	int				total_irqs;
+
+	u32			tx_wake_thresh;
+	u16			rx_offset;
+	u16			rx_dma_offset;
+
+	u8			rss_hash_key[HW_HASH_KEY_SIZE];
+	u8			rss_hash_key_valid:1;
+	u8			rss_hash_key_updated:1;
+	int			rsscos_nr_ctxs;
+	u32			stats_coal_ticks;
+};
+
+#define BNGE_DEFAULT_RX_RING_SIZE	511
+#define BNGE_DEFAULT_TX_RING_SIZE	511
+
+int bnge_netdev_alloc(struct bnge_dev *bd, int max_irqs);
+void bnge_netdev_free(struct bnge_dev *bd);
+void bnge_set_ring_params(struct bnge_dev *bd);
+
+#if (BNGE_PAGE_SHIFT == 16)
+#define MAX_RX_PAGES_AGG_ENA	1
+#define MAX_RX_PAGES		4
+#define MAX_RX_AGG_PAGES	4
+#define MAX_TX_PAGES		1
+#define MAX_CP_PAGES		16
+#else
+#define MAX_RX_PAGES_AGG_ENA	8
+#define MAX_RX_PAGES		32
+#define MAX_RX_AGG_PAGES	32
+#define MAX_TX_PAGES		8
+#define MAX_CP_PAGES		128
+#endif
+
+#define BNGE_RX_PAGE_SIZE		(1 << BNGE_RX_PAGE_SHIFT)
+
+#define RX_DESC_CNT			(BNGE_PAGE_SIZE / sizeof(struct rx_bd))
+#define TX_DESC_CNT			(BNGE_PAGE_SIZE / sizeof(struct tx_bd))
+#define CP_DESC_CNT			(BNGE_PAGE_SIZE / sizeof(struct tx_cmp))
+#define SW_RXBD_RING_SIZE		(sizeof(struct bnge_sw_rx_bd) * RX_DESC_CNT)
+#define HW_RXBD_RING_SIZE		(sizeof(struct rx_bd) * RX_DESC_CNT)
+#define SW_RXBD_AGG_RING_SIZE		(sizeof(struct bnge_sw_rx_agg_bd) * RX_DESC_CNT)
+#define SW_TXBD_RING_SIZE		(sizeof(struct bnge_sw_tx_bd) * TX_DESC_CNT)
+#define HW_TXBD_RING_SIZE		(sizeof(struct tx_bd) * TX_DESC_CNT)
+#define HW_CMPD_RING_SIZE		(sizeof(struct tx_cmp) * CP_DESC_CNT)
+#define BNGE_MAX_RX_DESC_CNT		(RX_DESC_CNT * MAX_RX_PAGES - 1)
+#define BNGE_MAX_RX_DESC_CNT_JUM_ENA	(RX_DESC_CNT * MAX_RX_PAGES_AGG_ENA - 1)
+#define BNGE_MAX_RX_JUM_DESC_CNT	(RX_DESC_CNT * MAX_RX_AGG_PAGES - 1)
+#define BNGE_MAX_TX_DESC_CNT		(TX_DESC_CNT * MAX_TX_PAGES - 1)
+
+#define BNGE_MAX_TXR_PER_NAPI	8
+
+#define bnge_for_each_napi_tx(iter, bnapi, txr)		\
+	for (iter = 0, txr = (bnapi)->tx_ring[0]; txr;	\
+	     txr = (iter < BNGE_MAX_TXR_PER_NAPI - 1) ?	\
+	     (bnapi)->tx_ring[++iter] : NULL)
+
+#define BNGE_SET_NQ_HDL(cpr)						\
+	(((cpr)->cp_ring_type << BNGE_NQ_HDL_TYPE_SHIFT) | (cpr)->cp_idx)
+
+struct bnge_stats_mem {
+	u64		*sw_stats;
+	u64		*hw_masks;
+	void		*hw_stats;
+	dma_addr_t	hw_stats_map;
+	int		len;
+};
+
+struct bnge_cp_ring_info {
+	struct bnge_napi	*bnapi;
+	dma_addr_t		*desc_mapping;
+	struct tx_cmp		**desc_ring;
+	struct bnge_ring_struct	ring_struct;
+	u8			cp_ring_type;
+	u8			cp_idx;
+	u32			cp_raw_cons;
+	struct bnge_db_info	cp_db;
+};
+
+struct bnge_nq_ring_info {
+	struct bnge_napi	*bnapi;
+	dma_addr_t		*desc_mapping;
+	struct nqe_cn		**desc_ring;
+	struct bnge_ring_struct	ring_struct;
+	u32			nq_raw_cons;
+	struct bnge_db_info	nq_db;
+
+	struct bnge_stats_mem	stats;
+	u32			hw_stats_ctx_id;
+
+	int				cp_ring_count;
+	struct bnge_cp_ring_info	*cp_ring_arr;
+};
+
+struct bnge_rx_ring_info {
+	struct bnge_napi	*bnapi;
+	struct bnge_cp_ring_info	*rx_cpr;
+	u16			rx_prod;
+	u16			rx_agg_prod;
+	u16			rx_sw_agg_prod;
+	u16			rx_next_cons;
+	struct bnge_db_info	rx_db;
+	struct bnge_db_info	rx_agg_db;
+
+	struct rx_bd		*rx_desc_ring[MAX_RX_PAGES];
+	struct bnge_sw_rx_bd	*rx_buf_ring;
+
+	struct rx_bd			*rx_agg_desc_ring[MAX_RX_AGG_PAGES];
+	struct bnge_sw_rx_agg_bd	*rx_agg_buf_ring;
+
+	unsigned long		*rx_agg_bmap;
+	u16			rx_agg_bmap_size;
+
+	dma_addr_t		rx_desc_mapping[MAX_RX_PAGES];
+	dma_addr_t		rx_agg_desc_mapping[MAX_RX_AGG_PAGES];
+
+	struct bnge_ring_struct	rx_ring_struct;
+	struct bnge_ring_struct	rx_agg_ring_struct;
+	struct page_pool	*page_pool;
+	struct page_pool	*head_pool;
+	bool			need_head_pool;
+};
+
+struct bnge_tx_ring_info {
+	struct bnge_napi	*bnapi;
+	struct bnge_cp_ring_info	*tx_cpr;
+	u16			tx_prod;
+	u16			tx_cons;
+	u16			tx_hw_cons;
+	u16			txq_index;
+	u8			tx_napi_idx;
+	u8			kick_pending;
+	struct bnge_db_info	tx_db;
+
+	struct tx_bd		*tx_desc_ring[MAX_TX_PAGES];
+	struct bnge_sw_tx_bd	*tx_buf_ring;
+
+	dma_addr_t		tx_desc_mapping[MAX_TX_PAGES];
+
+	u32			dev_state;
+#define BNGE_DEV_STATE_CLOSING	0x1
+
+	struct bnge_ring_struct	tx_ring_struct;
+};
+
+struct bnge_napi {
+	struct napi_struct		napi;
+	struct bnge_net			*bn;
+	int				index;
+
+	struct bnge_nq_ring_info	nq_ring;
+	struct bnge_rx_ring_info	*rx_ring;
+	struct bnge_tx_ring_info	*tx_ring[BNGE_MAX_TXR_PER_NAPI];
+};
+
+#define INVALID_STATS_CTX_ID	-1
+#define BNGE_VNIC_DEFAULT	0
+#define BNGE_MAX_UC_ADDRS	4
+
+struct bnge_vnic_info {
+	u16		fw_vnic_id;
+#define BNGE_MAX_CTX_PER_VNIC	8
+	u16		fw_rss_cos_lb_ctx[BNGE_MAX_CTX_PER_VNIC];
+	u16		mru;
+	/* index 0 always dev_addr */
+	struct bnge_l2_filter *l2_filters[BNGE_MAX_UC_ADDRS];
+	u16		uc_filter_count;
+	u8		*uc_list;
+	dma_addr_t	rss_table_dma_addr;
+	__le16		*rss_table;
+	dma_addr_t	rss_hash_key_dma_addr;
+	u64		*rss_hash_key;
+	int		rss_table_size;
+#define BNGE_RSS_TABLE_ENTRIES		64
+#define BNGE_RSS_TABLE_SIZE		(BNGE_RSS_TABLE_ENTRIES * 4)
+#define BNGE_RSS_TABLE_MAX_TBL		8
+#define BNGE_MAX_RSS_TABLE_SIZE			\
+	(BNGE_RSS_TABLE_SIZE * BNGE_RSS_TABLE_MAX_TBL)
+	u32		rx_mask;
+
+	u8		*mc_list;
+	int		mc_list_size;
+	int		mc_list_count;
+	dma_addr_t	mc_list_mapping;
+#define BNGE_MAX_MC_ADDRS	16
+
+	u32		flags;
+#define BNGE_VNIC_RSS_FLAG	1
+#define BNGE_VNIC_MCAST_FLAG	4
+#define BNGE_VNIC_UCAST_FLAG	8
+	u32		vnic_id;
+};
+
+struct bnge_filter_base {
+	struct hlist_node	hash;
+	struct list_head	list;
+	__le64			filter_id;
+	u8			type;
+#define BNGE_FLTR_TYPE_L2	2
+	u8			flags;
+	u16			rxq;
+	u16			fw_vnic_id;
+	u16			vf_idx;
+	unsigned long		state;
+#define BNGE_FLTR_VALID		0
+#define BNGE_FLTR_FW_DELETED	2
+
+	struct rcu_head         rcu;
+};
+
+struct bnge_l2_key {
+	union {
+		struct {
+			u8	dst_mac_addr[ETH_ALEN];
+			u16	vlan;
+		};
+		u32	filter_key;
+	};
+};
+
+#define BNGE_L2_KEY_SIZE	(sizeof(struct bnge_l2_key) / 4)
+struct bnge_l2_filter {
+	/* base filter must be the first member */
+	struct bnge_filter_base	base;
+	struct bnge_l2_key	l2_key;
+	refcount_t		refcnt;
+};
+
+u16 bnge_cp_ring_for_rx(struct bnge_rx_ring_info *rxr);
+u16 bnge_cp_ring_for_tx(struct bnge_tx_ring_info *txr);
+void bnge_fill_hw_rss_tbl(struct bnge_net *bn, struct bnge_vnic_info *vnic);
+#endif /* _BNGE_NETDEV_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_resc.c b/drivers/net/ethernet/broadcom/bnge/bnge_resc.c
new file mode 100644
index 000000000000..943df5f60f01
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_resc.c
@@ -0,0 +1,617 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2025 Broadcom.
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/ethtool.h>
+#include <linux/netdevice.h>
+
+#include "bnge.h"
+#include "bnge_hwrm.h"
+#include "bnge_hwrm_lib.h"
+#include "bnge_resc.h"
+
+static u16 bnge_num_tx_to_cp(struct bnge_dev *bd, u16 tx)
+{
+	u16 tcs = bd->num_tc;
+
+	if (!tcs)
+		tcs = 1;
+
+	return tx / tcs;
+}
+
+static u16 bnge_get_max_func_irqs(struct bnge_dev *bd)
+{
+	struct bnge_hw_resc *hw_resc = &bd->hw_resc;
+
+	return min_t(u16, hw_resc->max_irqs, hw_resc->max_nqs);
+}
+
+static unsigned int bnge_get_max_func_stat_ctxs(struct bnge_dev *bd)
+{
+	return bd->hw_resc.max_stat_ctxs;
+}
+
+bool bnge_aux_has_enough_resources(struct bnge_dev *bd)
+{
+	unsigned int max_stat_ctxs;
+
+	max_stat_ctxs = bnge_get_max_func_stat_ctxs(bd);
+	if (max_stat_ctxs <= BNGE_MIN_ROCE_STAT_CTXS ||
+	    bd->nq_nr_rings == max_stat_ctxs)
+		return false;
+
+	return true;
+}
+
+static unsigned int bnge_get_max_func_cp_rings(struct bnge_dev *bd)
+{
+	return bd->hw_resc.max_cp_rings;
+}
+
+static int bnge_aux_get_dflt_msix(struct bnge_dev *bd)
+{
+	int roce_msix = BNGE_MAX_ROCE_MSIX;
+
+	return min_t(int, roce_msix, num_online_cpus() + 1);
+}
+
+u16 bnge_aux_get_msix(struct bnge_dev *bd)
+{
+	if (bnge_is_roce_en(bd))
+		return bd->aux_num_msix;
+
+	return 0;
+}
+
+static void bnge_aux_set_msix_num(struct bnge_dev *bd, u16 num)
+{
+	if (bnge_is_roce_en(bd))
+		bd->aux_num_msix = num;
+}
+
+static u16 bnge_aux_get_stat_ctxs(struct bnge_dev *bd)
+{
+	if (bnge_is_roce_en(bd))
+		return bd->aux_num_stat_ctxs;
+
+	return 0;
+}
+
+static void bnge_aux_set_stat_ctxs(struct bnge_dev *bd, u16 num_aux_ctx)
+{
+	if (bnge_is_roce_en(bd))
+		bd->aux_num_stat_ctxs = num_aux_ctx;
+}
+
+static u16 bnge_func_stat_ctxs_demand(struct bnge_dev *bd)
+{
+	return bd->nq_nr_rings + bnge_aux_get_stat_ctxs(bd);
+}
+
+static int bnge_get_dflt_aux_stat_ctxs(struct bnge_dev *bd)
+{
+	int stat_ctx = 0;
+
+	if (bnge_is_roce_en(bd)) {
+		stat_ctx = BNGE_MIN_ROCE_STAT_CTXS;
+
+		if (!bd->pf.port_id && bd->port_count > 1)
+			stat_ctx++;
+	}
+
+	return stat_ctx;
+}
+
+static u16 bnge_nqs_demand(struct bnge_dev *bd)
+{
+	return bd->nq_nr_rings + bnge_aux_get_msix(bd);
+}
+
+static u16 bnge_cprs_demand(struct bnge_dev *bd)
+{
+	return bd->tx_nr_rings + bd->rx_nr_rings;
+}
+
+static u16 bnge_get_avail_msix(struct bnge_dev *bd, int num)
+{
+	u16 max_irq = bnge_get_max_func_irqs(bd);
+	u16 total_demand = bd->nq_nr_rings + num;
+
+	if (max_irq < total_demand) {
+		num = max_irq - bd->nq_nr_rings;
+		if (num <= 0)
+			return 0;
+	}
+
+	return num;
+}
+
+static u16 bnge_num_cp_to_tx(struct bnge_dev *bd, u16 tx_chunks)
+{
+	return tx_chunks * bd->num_tc;
+}
+
+int bnge_fix_rings_count(u16 *rx, u16 *tx, u16 max, bool shared)
+{
+	u16 _rx = *rx, _tx = *tx;
+
+	if (shared) {
+		*rx = min_t(u16, _rx, max);
+		*tx = min_t(u16, _tx, max);
+	} else {
+		if (max < 2)
+			return -ENOMEM;
+		while (_rx + _tx > max) {
+			if (_rx > _tx && _rx > 1)
+				_rx--;
+			else if (_tx > 1)
+				_tx--;
+		}
+		*rx = _rx;
+		*tx = _tx;
+	}
+
+	return 0;
+}
+
+static int bnge_adjust_rings(struct bnge_dev *bd, u16 *rx,
+			     u16 *tx, u16 max_nq, bool sh)
+{
+	u16 tx_chunks = bnge_num_tx_to_cp(bd, *tx);
+
+	if (tx_chunks != *tx) {
+		u16 tx_saved = tx_chunks, rc;
+
+		rc = bnge_fix_rings_count(rx, &tx_chunks, max_nq, sh);
+		if (rc)
+			return rc;
+		if (tx_chunks != tx_saved)
+			*tx = bnge_num_cp_to_tx(bd, tx_chunks);
+		return 0;
+	}
+
+	return bnge_fix_rings_count(rx, tx, max_nq, sh);
+}
+
+int bnge_cal_nr_rss_ctxs(u16 rx_rings)
+{
+	if (!rx_rings)
+		return 0;
+
+	return bnge_adjust_pow_two(rx_rings - 1,
+				   BNGE_RSS_TABLE_ENTRIES);
+}
+
+static u16 bnge_rss_ctxs_in_use(struct bnge_dev *bd,
+				struct bnge_hw_rings *hwr)
+{
+	return bnge_cal_nr_rss_ctxs(hwr->grp);
+}
+
+static u16 bnge_get_total_vnics(struct bnge_dev *bd, u16 rx_rings)
+{
+	return 1;
+}
+
+u32 bnge_get_rxfh_indir_size(struct bnge_dev *bd)
+{
+	return bnge_cal_nr_rss_ctxs(bd->rx_nr_rings) *
+	       BNGE_RSS_TABLE_ENTRIES;
+}
+
+static void bnge_set_dflt_rss_indir_tbl(struct bnge_dev *bd)
+{
+	u16 max_entries, pad;
+	u32 *rss_indir_tbl;
+	int i;
+
+	max_entries = bnge_get_rxfh_indir_size(bd);
+	rss_indir_tbl = &bd->rss_indir_tbl[0];
+
+	for (i = 0; i < max_entries; i++)
+		rss_indir_tbl[i] = ethtool_rxfh_indir_default(i,
+							      bd->rx_nr_rings);
+
+	pad = bd->rss_indir_tbl_entries - max_entries;
+	if (pad)
+		memset(&rss_indir_tbl[i], 0, pad * sizeof(*rss_indir_tbl));
+}
+
+static void bnge_copy_reserved_rings(struct bnge_dev *bd,
+				     struct bnge_hw_rings *hwr)
+{
+	struct bnge_hw_resc *hw_resc = &bd->hw_resc;
+
+	hwr->tx = hw_resc->resv_tx_rings;
+	hwr->rx = hw_resc->resv_rx_rings;
+	hwr->nq = hw_resc->resv_irqs;
+	hwr->cmpl = hw_resc->resv_cp_rings;
+	hwr->grp = hw_resc->resv_hw_ring_grps;
+	hwr->vnic = hw_resc->resv_vnics;
+	hwr->stat = hw_resc->resv_stat_ctxs;
+	hwr->rss_ctx = hw_resc->resv_rsscos_ctxs;
+}
+
+static bool bnge_rings_ok(struct bnge_hw_rings *hwr)
+{
+	return hwr->tx && hwr->rx && hwr->nq && hwr->grp && hwr->vnic &&
+	       hwr->stat && hwr->cmpl;
+}
+
+static bool bnge_need_reserve_rings(struct bnge_dev *bd)
+{
+	struct bnge_hw_resc *hw_resc = &bd->hw_resc;
+	u16 cprs = bnge_cprs_demand(bd);
+	u16 rx = bd->rx_nr_rings, stat;
+	u16 nqs = bnge_nqs_demand(bd);
+	u16 vnic;
+
+	if (hw_resc->resv_tx_rings != bd->tx_nr_rings)
+		return true;
+
+	vnic = bnge_get_total_vnics(bd, rx);
+
+	if (bnge_is_agg_reqd(bd))
+		rx <<= 1;
+	stat = bnge_func_stat_ctxs_demand(bd);
+	if (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cprs ||
+	    hw_resc->resv_vnics != vnic || hw_resc->resv_stat_ctxs != stat)
+		return true;
+	if (hw_resc->resv_irqs != nqs)
+		return true;
+
+	return false;
+}
+
+int bnge_reserve_rings(struct bnge_dev *bd)
+{
+	u16 aux_dflt_msix = bnge_aux_get_dflt_msix(bd);
+	struct bnge_hw_rings hwr = {0};
+	u16 rx_rings, old_rx_rings;
+	u16 nq = bd->nq_nr_rings;
+	u16 aux_msix = 0;
+	bool sh = false;
+	u16 tx_cp;
+	int rc;
+
+	if (!bnge_need_reserve_rings(bd))
+		return 0;
+
+	if (!bnge_aux_registered(bd)) {
+		aux_msix = bnge_get_avail_msix(bd, aux_dflt_msix);
+		if (!aux_msix)
+			bnge_aux_set_stat_ctxs(bd, 0);
+
+		if (aux_msix > aux_dflt_msix)
+			aux_msix = aux_dflt_msix;
+		hwr.nq = nq + aux_msix;
+	} else {
+		hwr.nq = bnge_nqs_demand(bd);
+	}
+
+	hwr.tx = bd->tx_nr_rings;
+	hwr.rx = bd->rx_nr_rings;
+	if (bd->flags & BNGE_EN_SHARED_CHNL)
+		sh = true;
+	hwr.cmpl = hwr.rx + hwr.tx;
+
+	hwr.vnic = bnge_get_total_vnics(bd, hwr.rx);
+
+	if (bnge_is_agg_reqd(bd))
+		hwr.rx <<= 1;
+	hwr.grp = bd->rx_nr_rings;
+	hwr.rss_ctx = bnge_rss_ctxs_in_use(bd, &hwr);
+	hwr.stat = bnge_func_stat_ctxs_demand(bd);
+	old_rx_rings = bd->hw_resc.resv_rx_rings;
+
+	rc = bnge_hwrm_reserve_rings(bd, &hwr);
+	if (rc)
+		return rc;
+
+	bnge_copy_reserved_rings(bd, &hwr);
+
+	rx_rings = hwr.rx;
+	if (bnge_is_agg_reqd(bd)) {
+		if (hwr.rx >= 2)
+			rx_rings = hwr.rx >> 1;
+		else
+			return -ENOMEM;
+	}
+
+	rx_rings = min_t(u16, rx_rings, hwr.grp);
+	hwr.nq = min_t(u16, hwr.nq, bd->nq_nr_rings);
+	if (hwr.stat > bnge_aux_get_stat_ctxs(bd))
+		hwr.stat -= bnge_aux_get_stat_ctxs(bd);
+	hwr.nq = min_t(u16, hwr.nq, hwr.stat);
+
+	/* Adjust the rings */
+	rc = bnge_adjust_rings(bd, &rx_rings, &hwr.tx, hwr.nq, sh);
+	if (bnge_is_agg_reqd(bd))
+		hwr.rx = rx_rings << 1;
+	tx_cp = hwr.tx;
+	hwr.nq = sh ? max_t(u16, tx_cp, rx_rings) : tx_cp + rx_rings;
+	bd->tx_nr_rings = hwr.tx;
+
+	if (rx_rings != bd->rx_nr_rings)
+		dev_warn(bd->dev, "RX rings resv reduced to %d than earlier %d requested\n",
+			 rx_rings, bd->rx_nr_rings);
+
+	bd->rx_nr_rings = rx_rings;
+	bd->nq_nr_rings = hwr.nq;
+
+	if (!bnge_rings_ok(&hwr))
+		return -ENOMEM;
+
+	if (old_rx_rings != bd->hw_resc.resv_rx_rings)
+		bnge_set_dflt_rss_indir_tbl(bd);
+
+	if (!bnge_aux_registered(bd)) {
+		u16 resv_msix, resv_ctx, aux_ctxs;
+		struct bnge_hw_resc *hw_resc;
+
+		hw_resc = &bd->hw_resc;
+		resv_msix = hw_resc->resv_irqs - bd->nq_nr_rings;
+		aux_msix = min_t(u16, resv_msix, aux_msix);
+		bnge_aux_set_msix_num(bd, aux_msix);
+		resv_ctx = hw_resc->resv_stat_ctxs  - bd->nq_nr_rings;
+		aux_ctxs = min(resv_ctx, bnge_aux_get_stat_ctxs(bd));
+		bnge_aux_set_stat_ctxs(bd, aux_ctxs);
+	}
+
+	return rc;
+}
+
+int bnge_alloc_irqs(struct bnge_dev *bd)
+{
+	u16 aux_msix, tx_cp, num_entries;
+	int i, irqs_demand, rc;
+	u16 max, min = 1;
+
+	irqs_demand = bnge_nqs_demand(bd);
+	max = bnge_get_max_func_irqs(bd);
+	if (irqs_demand > max)
+		irqs_demand = max;
+
+	if (!(bd->flags & BNGE_EN_SHARED_CHNL))
+		min = 2;
+
+	irqs_demand = pci_alloc_irq_vectors(bd->pdev, min, irqs_demand,
+					    PCI_IRQ_MSIX);
+	aux_msix = bnge_aux_get_msix(bd);
+	if (irqs_demand < 0 || irqs_demand < aux_msix) {
+		rc = -ENODEV;
+		goto err_free_irqs;
+	}
+
+	num_entries = irqs_demand;
+	if (pci_msix_can_alloc_dyn(bd->pdev))
+		num_entries = max;
+	bd->irq_tbl = kcalloc(num_entries, sizeof(*bd->irq_tbl), GFP_KERNEL);
+	if (!bd->irq_tbl) {
+		rc = -ENOMEM;
+		goto err_free_irqs;
+	}
+
+	for (i = 0; i < irqs_demand; i++)
+		bd->irq_tbl[i].vector = pci_irq_vector(bd->pdev, i);
+
+	bd->irqs_acquired = irqs_demand;
+	/* Reduce rings based upon num of vectors allocated.
+	 * We dont need to consider NQs as they have been calculated
+	 * and must be more than irqs_demand.
+	 */
+	rc = bnge_adjust_rings(bd, &bd->rx_nr_rings,
+			       &bd->tx_nr_rings,
+			       irqs_demand - aux_msix, min == 1);
+	if (rc)
+		goto err_free_irqs;
+
+	tx_cp = bnge_num_tx_to_cp(bd, bd->tx_nr_rings);
+	bd->nq_nr_rings = (min == 1) ?
+		max_t(u16, tx_cp, bd->rx_nr_rings) :
+		tx_cp + bd->rx_nr_rings;
+
+	/* Readjust tx_nr_rings_per_tc */
+	if (!bd->num_tc)
+		bd->tx_nr_rings_per_tc = bd->tx_nr_rings;
+
+	return 0;
+
+err_free_irqs:
+	dev_err(bd->dev, "Failed to allocate IRQs err = %d\n", rc);
+	bnge_free_irqs(bd);
+	return rc;
+}
+
+void bnge_free_irqs(struct bnge_dev *bd)
+{
+	pci_free_irq_vectors(bd->pdev);
+	kfree(bd->irq_tbl);
+	bd->irq_tbl = NULL;
+}
+
+static void _bnge_get_max_rings(struct bnge_dev *bd, u16 *max_rx,
+				u16 *max_tx, u16 *max_nq)
+{
+	struct bnge_hw_resc *hw_resc = &bd->hw_resc;
+	u16 max_ring_grps = 0, max_cp;
+	int rc;
+
+	*max_tx = hw_resc->max_tx_rings;
+	*max_rx = hw_resc->max_rx_rings;
+	*max_nq = min_t(int, bnge_get_max_func_irqs(bd),
+			hw_resc->max_stat_ctxs);
+	max_ring_grps = hw_resc->max_hw_ring_grps;
+	if (bnge_is_agg_reqd(bd))
+		*max_rx >>= 1;
+
+	max_cp = bnge_get_max_func_cp_rings(bd);
+
+	/* Fix RX and TX rings according to number of CPs available */
+	rc = bnge_fix_rings_count(max_rx, max_tx, max_cp, false);
+	if (rc) {
+		*max_rx = 0;
+		*max_tx = 0;
+	}
+
+	*max_rx = min_t(int, *max_rx, max_ring_grps);
+}
+
+static int bnge_get_max_rings(struct bnge_dev *bd, u16 *max_rx,
+			      u16 *max_tx, bool shared)
+{
+	u16 rx, tx, nq;
+
+	_bnge_get_max_rings(bd, &rx, &tx, &nq);
+	*max_rx = rx;
+	*max_tx = tx;
+	if (!rx || !tx || !nq)
+		return -ENOMEM;
+
+	return bnge_fix_rings_count(max_rx, max_tx, nq, shared);
+}
+
+static int bnge_get_dflt_rings(struct bnge_dev *bd, u16 *max_rx, u16 *max_tx,
+			       bool shared)
+{
+	int rc;
+
+	rc = bnge_get_max_rings(bd, max_rx, max_tx, shared);
+	if (rc) {
+		dev_info(bd->dev, "Not enough rings available\n");
+		return rc;
+	}
+
+	if (bnge_is_roce_en(bd)) {
+		int max_cp, max_stat, max_irq;
+
+		/* Reserve minimum resources for RoCE */
+		max_cp = bnge_get_max_func_cp_rings(bd);
+		max_stat = bnge_get_max_func_stat_ctxs(bd);
+		max_irq = bnge_get_max_func_irqs(bd);
+		if (max_cp <= BNGE_MIN_ROCE_CP_RINGS ||
+		    max_irq <= BNGE_MIN_ROCE_CP_RINGS ||
+		    max_stat <= BNGE_MIN_ROCE_STAT_CTXS)
+			return 0;
+
+		max_cp -= BNGE_MIN_ROCE_CP_RINGS;
+		max_irq -= BNGE_MIN_ROCE_CP_RINGS;
+		max_stat -= BNGE_MIN_ROCE_STAT_CTXS;
+		max_cp = min_t(u16, max_cp, max_irq);
+		max_cp = min_t(u16, max_cp, max_stat);
+		rc = bnge_adjust_rings(bd, max_rx, max_tx, max_cp, shared);
+		if (rc)
+			rc = 0;
+	}
+
+	return rc;
+}
+
+/* In initial default shared ring setting, each shared ring must have a
+ * RX/TX ring pair.
+ */
+static void bnge_trim_dflt_sh_rings(struct bnge_dev *bd)
+{
+	bd->nq_nr_rings = min_t(u16, bd->tx_nr_rings_per_tc, bd->rx_nr_rings);
+	bd->rx_nr_rings = bd->nq_nr_rings;
+	bd->tx_nr_rings_per_tc = bd->nq_nr_rings;
+	bd->tx_nr_rings = bd->tx_nr_rings_per_tc;
+}
+
+static int bnge_net_init_dflt_rings(struct bnge_dev *bd, bool sh)
+{
+	u16 dflt_rings, max_rx_rings, max_tx_rings;
+	int rc;
+
+	if (sh)
+		bd->flags |= BNGE_EN_SHARED_CHNL;
+
+	dflt_rings = netif_get_num_default_rss_queues();
+
+	rc = bnge_get_dflt_rings(bd, &max_rx_rings, &max_tx_rings, sh);
+	if (rc)
+		return rc;
+	bd->rx_nr_rings = min_t(u16, dflt_rings, max_rx_rings);
+	bd->tx_nr_rings_per_tc = min_t(u16, dflt_rings, max_tx_rings);
+	if (sh)
+		bnge_trim_dflt_sh_rings(bd);
+	else
+		bd->nq_nr_rings = bd->tx_nr_rings_per_tc + bd->rx_nr_rings;
+	bd->tx_nr_rings = bd->tx_nr_rings_per_tc;
+
+	rc = bnge_reserve_rings(bd);
+	if (rc && rc != -ENODEV)
+		dev_warn(bd->dev, "Unable to reserve tx rings\n");
+	bd->tx_nr_rings_per_tc = bd->tx_nr_rings;
+	if (sh)
+		bnge_trim_dflt_sh_rings(bd);
+
+	/* Rings may have been reduced, re-reserve them again */
+	if (bnge_need_reserve_rings(bd)) {
+		rc = bnge_reserve_rings(bd);
+		if (rc && rc != -ENODEV)
+			dev_warn(bd->dev, "Fewer rings reservation failed\n");
+		bd->tx_nr_rings_per_tc = bd->tx_nr_rings;
+	}
+	if (rc) {
+		bd->tx_nr_rings = 0;
+		bd->rx_nr_rings = 0;
+	}
+
+	return rc;
+}
+
+static int bnge_alloc_rss_indir_tbl(struct bnge_dev *bd)
+{
+	u16 entries;
+
+	entries = BNGE_MAX_RSS_TABLE_ENTRIES;
+
+	bd->rss_indir_tbl_entries = entries;
+	bd->rss_indir_tbl =
+		kmalloc_array(entries, sizeof(*bd->rss_indir_tbl), GFP_KERNEL);
+	if (!bd->rss_indir_tbl)
+		return -ENOMEM;
+
+	return 0;
+}
+
+int bnge_net_init_dflt_config(struct bnge_dev *bd)
+{
+	struct bnge_hw_resc *hw_resc;
+	int rc;
+
+	rc = bnge_alloc_rss_indir_tbl(bd);
+	if (rc)
+		return rc;
+
+	rc = bnge_net_init_dflt_rings(bd, true);
+	if (rc)
+		goto err_free_tbl;
+
+	hw_resc = &bd->hw_resc;
+	bd->max_fltr = hw_resc->max_rx_em_flows + hw_resc->max_rx_wm_flows +
+		       BNGE_L2_FLTR_MAX_FLTR;
+
+	return 0;
+
+err_free_tbl:
+	kfree(bd->rss_indir_tbl);
+	bd->rss_indir_tbl = NULL;
+	return rc;
+}
+
+void bnge_net_uninit_dflt_config(struct bnge_dev *bd)
+{
+	kfree(bd->rss_indir_tbl);
+	bd->rss_indir_tbl = NULL;
+}
+
+void bnge_aux_init_dflt_config(struct bnge_dev *bd)
+{
+	bd->aux_num_msix = bnge_aux_get_dflt_msix(bd);
+	bd->aux_num_stat_ctxs = bnge_get_dflt_aux_stat_ctxs(bd);
+}
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_resc.h b/drivers/net/ethernet/broadcom/bnge/bnge_resc.h
new file mode 100644
index 000000000000..b62a634669f6
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_resc.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Broadcom */
+
+#ifndef _BNGE_RESC_H_
+#define _BNGE_RESC_H_
+
+#include "bnge_netdev.h"
+#include "bnge_rmem.h"
+
+struct bnge_hw_resc {
+	u16	min_rsscos_ctxs;
+	u16	max_rsscos_ctxs;
+	u16	resv_rsscos_ctxs;
+	u16	min_cp_rings;
+	u16	max_cp_rings;
+	u16	resv_cp_rings;
+	u16	min_tx_rings;
+	u16	max_tx_rings;
+	u16	resv_tx_rings;
+	u16	max_tx_sch_inputs;
+	u16	min_rx_rings;
+	u16	max_rx_rings;
+	u16	resv_rx_rings;
+	u16	min_hw_ring_grps;
+	u16	max_hw_ring_grps;
+	u16	resv_hw_ring_grps;
+	u16	min_l2_ctxs;
+	u16	max_l2_ctxs;
+	u16	min_vnics;
+	u16	max_vnics;
+	u16	resv_vnics;
+	u16	min_stat_ctxs;
+	u16	max_stat_ctxs;
+	u16	resv_stat_ctxs;
+	u16	max_nqs;
+	u16	max_irqs;
+	u16	resv_irqs;
+	u32	max_encap_records;
+	u32	max_decap_records;
+	u32	max_tx_em_flows;
+	u32	max_tx_wm_flows;
+	u32	max_rx_em_flows;
+	u32	max_rx_wm_flows;
+};
+
+struct bnge_hw_rings {
+	u16 tx;
+	u16 rx;
+	u16 grp;
+	u16 nq;
+	u16 cmpl;
+	u16 stat;
+	u16 vnic;
+	u16 rss_ctx;
+};
+
+/* "TXRX", 2 hypens, plus maximum integer */
+#define BNGE_IRQ_NAME_EXTRA	17
+struct bnge_irq {
+	irq_handler_t	handler;
+	unsigned int	vector;
+	u8		requested:1;
+	u8		have_cpumask:1;
+	char		name[IFNAMSIZ + BNGE_IRQ_NAME_EXTRA];
+	cpumask_var_t	cpu_mask;
+};
+
+int bnge_reserve_rings(struct bnge_dev *bd);
+int bnge_fix_rings_count(u16 *rx, u16 *tx, u16 max, bool shared);
+int bnge_alloc_irqs(struct bnge_dev *bd);
+void bnge_free_irqs(struct bnge_dev *bd);
+int bnge_net_init_dflt_config(struct bnge_dev *bd);
+void bnge_net_uninit_dflt_config(struct bnge_dev *bd);
+void bnge_aux_init_dflt_config(struct bnge_dev *bd);
+u32 bnge_get_rxfh_indir_size(struct bnge_dev *bd);
+int bnge_cal_nr_rss_ctxs(u16 rx_rings);
+bool bnge_aux_has_enough_resources(struct bnge_dev *bd);
+
+static inline u32
+bnge_adjust_pow_two(u32 total_ent, u16 ent_per_blk)
+{
+	u32 blks = total_ent / ent_per_blk;
+
+	if (blks == 0 || blks == 1)
+		return ++blks;
+
+	if (!is_power_of_2(blks))
+		blks = roundup_pow_of_two(blks);
+
+	return blks;
+}
+
+#define BNGE_MAX_ROCE_MSIX		64
+#define BNGE_MIN_ROCE_CP_RINGS		2
+#define BNGE_MIN_ROCE_STAT_CTXS		1
+
+#endif /* _BNGE_RESC_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_rmem.c b/drivers/net/ethernet/broadcom/bnge/bnge_rmem.c
new file mode 100644
index 000000000000..79f5ce2e5d08
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_rmem.c
@@ -0,0 +1,499 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2025 Broadcom.
+
+#include <linux/etherdevice.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/mm.h>
+#include <linux/dma-mapping.h>
+#include <linux/vmalloc.h>
+#include <linux/crash_dump.h>
+#include <linux/bnxt/hsi.h>
+
+#include "bnge.h"
+#include "bnge_hwrm_lib.h"
+#include "bnge_rmem.h"
+
+static void bnge_init_ctx_mem(struct bnge_ctx_mem_type *ctxm,
+			      void *p, int len)
+{
+	u8 init_val = ctxm->init_value;
+	u16 offset = ctxm->init_offset;
+	u8 *p2 = p;
+	int i;
+
+	if (!init_val)
+		return;
+	if (offset == BNGE_CTX_INIT_INVALID_OFFSET) {
+		memset(p, init_val, len);
+		return;
+	}
+	for (i = 0; i < len; i += ctxm->entry_size)
+		*(p2 + i + offset) = init_val;
+}
+
+void bnge_free_ring(struct bnge_dev *bd, struct bnge_ring_mem_info *rmem)
+{
+	struct pci_dev *pdev = bd->pdev;
+	int i;
+
+	if (!rmem->pg_arr)
+		goto skip_pages;
+
+	for (i = 0; i < rmem->nr_pages; i++) {
+		if (!rmem->pg_arr[i])
+			continue;
+
+		dma_free_coherent(&pdev->dev, rmem->page_size,
+				  rmem->pg_arr[i], rmem->dma_arr[i]);
+
+		rmem->pg_arr[i] = NULL;
+	}
+skip_pages:
+	if (rmem->pg_tbl) {
+		size_t pg_tbl_size = rmem->nr_pages * 8;
+
+		if (rmem->flags & BNGE_RMEM_USE_FULL_PAGE_FLAG)
+			pg_tbl_size = rmem->page_size;
+		dma_free_coherent(&pdev->dev, pg_tbl_size,
+				  rmem->pg_tbl, rmem->dma_pg_tbl);
+		rmem->pg_tbl = NULL;
+	}
+	if (rmem->vmem_size && *rmem->vmem) {
+		vfree(*rmem->vmem);
+		*rmem->vmem = NULL;
+	}
+}
+
+int bnge_alloc_ring(struct bnge_dev *bd, struct bnge_ring_mem_info *rmem)
+{
+	struct pci_dev *pdev = bd->pdev;
+	u64 valid_bit = 0;
+	int i;
+
+	if (rmem->flags & (BNGE_RMEM_VALID_PTE_FLAG | BNGE_RMEM_RING_PTE_FLAG))
+		valid_bit = PTU_PTE_VALID;
+
+	if ((rmem->nr_pages > 1 || rmem->depth > 0) && !rmem->pg_tbl) {
+		size_t pg_tbl_size = rmem->nr_pages * 8;
+
+		if (rmem->flags & BNGE_RMEM_USE_FULL_PAGE_FLAG)
+			pg_tbl_size = rmem->page_size;
+		rmem->pg_tbl = dma_alloc_coherent(&pdev->dev, pg_tbl_size,
+						  &rmem->dma_pg_tbl,
+						  GFP_KERNEL);
+		if (!rmem->pg_tbl)
+			return -ENOMEM;
+	}
+
+	for (i = 0; i < rmem->nr_pages; i++) {
+		u64 extra_bits = valid_bit;
+
+		rmem->pg_arr[i] = dma_alloc_coherent(&pdev->dev,
+						     rmem->page_size,
+						     &rmem->dma_arr[i],
+						     GFP_KERNEL);
+		if (!rmem->pg_arr[i])
+			goto err_free_ring;
+
+		if (rmem->ctx_mem)
+			bnge_init_ctx_mem(rmem->ctx_mem, rmem->pg_arr[i],
+					  rmem->page_size);
+
+		if (rmem->nr_pages > 1 || rmem->depth > 0) {
+			if (i == rmem->nr_pages - 2 &&
+			    (rmem->flags & BNGE_RMEM_RING_PTE_FLAG))
+				extra_bits |= PTU_PTE_NEXT_TO_LAST;
+			else if (i == rmem->nr_pages - 1 &&
+				 (rmem->flags & BNGE_RMEM_RING_PTE_FLAG))
+				extra_bits |= PTU_PTE_LAST;
+			rmem->pg_tbl[i] =
+				cpu_to_le64(rmem->dma_arr[i] | extra_bits);
+		}
+	}
+
+	if (rmem->vmem_size) {
+		*rmem->vmem = vzalloc(rmem->vmem_size);
+		if (!(*rmem->vmem))
+			goto err_free_ring;
+	}
+	return 0;
+
+err_free_ring:
+	bnge_free_ring(bd, rmem);
+	return -ENOMEM;
+}
+
+static int bnge_alloc_ctx_one_lvl(struct bnge_dev *bd,
+				  struct bnge_ctx_pg_info *ctx_pg)
+{
+	struct bnge_ring_mem_info *rmem = &ctx_pg->ring_mem;
+
+	rmem->page_size = BNGE_PAGE_SIZE;
+	rmem->pg_arr = ctx_pg->ctx_pg_arr;
+	rmem->dma_arr = ctx_pg->ctx_dma_arr;
+	rmem->flags = BNGE_RMEM_VALID_PTE_FLAG;
+	if (rmem->depth >= 1)
+		rmem->flags |= BNGE_RMEM_USE_FULL_PAGE_FLAG;
+	return bnge_alloc_ring(bd, rmem);
+}
+
+static int bnge_alloc_ctx_pg_tbls(struct bnge_dev *bd,
+				  struct bnge_ctx_pg_info *ctx_pg, u32 mem_size,
+				  u8 depth, struct bnge_ctx_mem_type *ctxm)
+{
+	struct bnge_ring_mem_info *rmem = &ctx_pg->ring_mem;
+	int rc;
+
+	if (!mem_size)
+		return -EINVAL;
+
+	ctx_pg->nr_pages = DIV_ROUND_UP(mem_size, BNGE_PAGE_SIZE);
+	if (ctx_pg->nr_pages > MAX_CTX_TOTAL_PAGES) {
+		ctx_pg->nr_pages = 0;
+		return -EINVAL;
+	}
+	if (ctx_pg->nr_pages > MAX_CTX_PAGES || depth > 1) {
+		int nr_tbls, i;
+
+		rmem->depth = 2;
+		ctx_pg->ctx_pg_tbl = kcalloc(MAX_CTX_PAGES, sizeof(ctx_pg),
+					     GFP_KERNEL);
+		if (!ctx_pg->ctx_pg_tbl)
+			return -ENOMEM;
+		nr_tbls = DIV_ROUND_UP(ctx_pg->nr_pages, MAX_CTX_PAGES);
+		rmem->nr_pages = nr_tbls;
+		rc = bnge_alloc_ctx_one_lvl(bd, ctx_pg);
+		if (rc)
+			return rc;
+		for (i = 0; i < nr_tbls; i++) {
+			struct bnge_ctx_pg_info *pg_tbl;
+
+			pg_tbl = kzalloc(sizeof(*pg_tbl), GFP_KERNEL);
+			if (!pg_tbl)
+				return -ENOMEM;
+			ctx_pg->ctx_pg_tbl[i] = pg_tbl;
+			rmem = &pg_tbl->ring_mem;
+			rmem->pg_tbl = ctx_pg->ctx_pg_arr[i];
+			rmem->dma_pg_tbl = ctx_pg->ctx_dma_arr[i];
+			rmem->depth = 1;
+			rmem->nr_pages = MAX_CTX_PAGES;
+			rmem->ctx_mem = ctxm;
+			if (i == (nr_tbls - 1)) {
+				int rem = ctx_pg->nr_pages % MAX_CTX_PAGES;
+
+				if (rem)
+					rmem->nr_pages = rem;
+			}
+			rc = bnge_alloc_ctx_one_lvl(bd, pg_tbl);
+			if (rc)
+				break;
+		}
+	} else {
+		rmem->nr_pages = DIV_ROUND_UP(mem_size, BNGE_PAGE_SIZE);
+		if (rmem->nr_pages > 1 || depth)
+			rmem->depth = 1;
+		rmem->ctx_mem = ctxm;
+		rc = bnge_alloc_ctx_one_lvl(bd, ctx_pg);
+	}
+
+	return rc;
+}
+
+static void bnge_free_ctx_pg_tbls(struct bnge_dev *bd,
+				  struct bnge_ctx_pg_info *ctx_pg)
+{
+	struct bnge_ring_mem_info *rmem = &ctx_pg->ring_mem;
+
+	if (rmem->depth > 1 || ctx_pg->nr_pages > MAX_CTX_PAGES ||
+	    ctx_pg->ctx_pg_tbl) {
+		int i, nr_tbls = rmem->nr_pages;
+
+		for (i = 0; i < nr_tbls; i++) {
+			struct bnge_ctx_pg_info *pg_tbl;
+			struct bnge_ring_mem_info *rmem2;
+
+			pg_tbl = ctx_pg->ctx_pg_tbl[i];
+			if (!pg_tbl)
+				continue;
+			rmem2 = &pg_tbl->ring_mem;
+			bnge_free_ring(bd, rmem2);
+			ctx_pg->ctx_pg_arr[i] = NULL;
+			kfree(pg_tbl);
+			ctx_pg->ctx_pg_tbl[i] = NULL;
+		}
+		kfree(ctx_pg->ctx_pg_tbl);
+		ctx_pg->ctx_pg_tbl = NULL;
+	}
+	bnge_free_ring(bd, rmem);
+	ctx_pg->nr_pages = 0;
+}
+
+static int bnge_setup_ctxm_pg_tbls(struct bnge_dev *bd,
+				   struct bnge_ctx_mem_type *ctxm, u32 entries,
+				   u8 pg_lvl)
+{
+	struct bnge_ctx_pg_info *ctx_pg = ctxm->pg_info;
+	int i, rc = 0, n = 1;
+	u32 mem_size;
+
+	if (!ctxm->entry_size || !ctx_pg)
+		return -EINVAL;
+	if (ctxm->instance_bmap)
+		n = hweight32(ctxm->instance_bmap);
+	if (ctxm->entry_multiple)
+		entries = roundup(entries, ctxm->entry_multiple);
+	entries = clamp_t(u32, entries, ctxm->min_entries, ctxm->max_entries);
+	mem_size = entries * ctxm->entry_size;
+	for (i = 0; i < n && !rc; i++) {
+		ctx_pg[i].entries = entries;
+		rc = bnge_alloc_ctx_pg_tbls(bd, &ctx_pg[i], mem_size, pg_lvl,
+					    ctxm->init_value ? ctxm : NULL);
+	}
+
+	return rc;
+}
+
+static int bnge_backing_store_cfg(struct bnge_dev *bd, u32 ena)
+{
+	struct bnge_ctx_mem_info *ctx = bd->ctx;
+	struct bnge_ctx_mem_type *ctxm;
+	u16 last_type;
+	int rc = 0;
+	u16 type;
+
+	if (!ena)
+		return 0;
+	else if (ena & FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM)
+		last_type = BNGE_CTX_MAX - 1;
+	else
+		last_type = BNGE_CTX_L2_MAX - 1;
+	ctx->ctx_arr[last_type].last = 1;
+
+	for (type = 0 ; type < BNGE_CTX_V2_MAX; type++) {
+		ctxm = &ctx->ctx_arr[type];
+
+		rc = bnge_hwrm_func_backing_store(bd, ctxm, ctxm->last);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+void bnge_free_ctx_mem(struct bnge_dev *bd)
+{
+	struct bnge_ctx_mem_info *ctx = bd->ctx;
+	u16 type;
+
+	if (!ctx)
+		return;
+
+	for (type = 0; type < BNGE_CTX_V2_MAX; type++) {
+		struct bnge_ctx_mem_type *ctxm = &ctx->ctx_arr[type];
+		struct bnge_ctx_pg_info *ctx_pg = ctxm->pg_info;
+		int i, n = 1;
+
+		if (!ctx_pg)
+			continue;
+		if (ctxm->instance_bmap)
+			n = hweight32(ctxm->instance_bmap);
+		for (i = 0; i < n; i++)
+			bnge_free_ctx_pg_tbls(bd, &ctx_pg[i]);
+
+		kfree(ctx_pg);
+		ctxm->pg_info = NULL;
+	}
+
+	ctx->flags &= ~BNGE_CTX_FLAG_INITED;
+	kfree(ctx);
+	bd->ctx = NULL;
+}
+
+#define FUNC_BACKING_STORE_CFG_REQ_DFLT_ENABLES			\
+	(FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP |		\
+	 FUNC_BACKING_STORE_CFG_REQ_ENABLES_SRQ |		\
+	 FUNC_BACKING_STORE_CFG_REQ_ENABLES_CQ |		\
+	 FUNC_BACKING_STORE_CFG_REQ_ENABLES_VNIC |		\
+	 FUNC_BACKING_STORE_CFG_REQ_ENABLES_STAT)
+
+int bnge_alloc_ctx_mem(struct bnge_dev *bd)
+{
+	struct bnge_ctx_mem_type *ctxm;
+	struct bnge_ctx_mem_info *ctx;
+	u32 l2_qps, qp1_qps, max_qps;
+	u32 ena, entries_sp, entries;
+	u32 srqs, max_srqs, min;
+	u32 num_mr, num_ah;
+	u32 extra_srqs = 0;
+	u32 extra_qps = 0;
+	u32 fast_qpmd_qps;
+	u8 pg_lvl = 1;
+	int i, rc;
+
+	rc = bnge_hwrm_func_backing_store_qcaps(bd);
+	if (rc) {
+		dev_err(bd->dev, "Failed querying ctx mem caps, rc: %d\n", rc);
+		return rc;
+	}
+
+	ctx = bd->ctx;
+	if (!ctx || (ctx->flags & BNGE_CTX_FLAG_INITED))
+		return 0;
+
+	ctxm = &ctx->ctx_arr[BNGE_CTX_QP];
+	l2_qps = ctxm->qp_l2_entries;
+	qp1_qps = ctxm->qp_qp1_entries;
+	fast_qpmd_qps = ctxm->qp_fast_qpmd_entries;
+	max_qps = ctxm->max_entries;
+	ctxm = &ctx->ctx_arr[BNGE_CTX_SRQ];
+	srqs = ctxm->srq_l2_entries;
+	max_srqs = ctxm->max_entries;
+	ena = 0;
+	if (bnge_is_roce_en(bd) && !is_kdump_kernel()) {
+		pg_lvl = 2;
+		extra_qps = min_t(u32, 65536, max_qps - l2_qps - qp1_qps);
+		/* allocate extra qps if fast qp destroy feature enabled */
+		extra_qps += fast_qpmd_qps;
+		extra_srqs = min_t(u32, 8192, max_srqs - srqs);
+		if (fast_qpmd_qps)
+			ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP_FAST_QPMD;
+	}
+
+	ctxm = &ctx->ctx_arr[BNGE_CTX_QP];
+	rc = bnge_setup_ctxm_pg_tbls(bd, ctxm, l2_qps + qp1_qps + extra_qps,
+				     pg_lvl);
+	if (rc)
+		return rc;
+
+	ctxm = &ctx->ctx_arr[BNGE_CTX_SRQ];
+	rc = bnge_setup_ctxm_pg_tbls(bd, ctxm, srqs + extra_srqs, pg_lvl);
+	if (rc)
+		return rc;
+
+	ctxm = &ctx->ctx_arr[BNGE_CTX_CQ];
+	rc = bnge_setup_ctxm_pg_tbls(bd, ctxm, ctxm->cq_l2_entries +
+				     extra_qps * 2, pg_lvl);
+	if (rc)
+		return rc;
+
+	ctxm = &ctx->ctx_arr[BNGE_CTX_VNIC];
+	rc = bnge_setup_ctxm_pg_tbls(bd, ctxm, ctxm->max_entries, 1);
+	if (rc)
+		return rc;
+
+	ctxm = &ctx->ctx_arr[BNGE_CTX_STAT];
+	rc = bnge_setup_ctxm_pg_tbls(bd, ctxm, ctxm->max_entries, 1);
+	if (rc)
+		return rc;
+
+	if (!bnge_is_roce_en(bd))
+		goto skip_rdma;
+
+	ctxm = &ctx->ctx_arr[BNGE_CTX_MRAV];
+	/* 128K extra is needed to accommodate static AH context
+	 * allocation by f/w.
+	 */
+	num_mr = min_t(u32, ctxm->max_entries / 2, 1024 * 256);
+	num_ah = min_t(u32, num_mr, 1024 * 128);
+	ctxm->split_entry_cnt = BNGE_CTX_MRAV_AV_SPLIT_ENTRY + 1;
+	if (!ctxm->mrav_av_entries || ctxm->mrav_av_entries > num_ah)
+		ctxm->mrav_av_entries = num_ah;
+
+	rc = bnge_setup_ctxm_pg_tbls(bd, ctxm, num_mr + num_ah, 2);
+	if (rc)
+		return rc;
+	ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV;
+
+	ctxm = &ctx->ctx_arr[BNGE_CTX_TIM];
+	rc = bnge_setup_ctxm_pg_tbls(bd, ctxm, l2_qps + qp1_qps + extra_qps, 1);
+	if (rc)
+		return rc;
+	ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM;
+
+skip_rdma:
+	ctxm = &ctx->ctx_arr[BNGE_CTX_STQM];
+	min = ctxm->min_entries;
+	entries_sp = ctx->ctx_arr[BNGE_CTX_VNIC].vnic_entries + l2_qps +
+		     2 * (extra_qps + qp1_qps) + min;
+	rc = bnge_setup_ctxm_pg_tbls(bd, ctxm, entries_sp, 2);
+	if (rc)
+		return rc;
+
+	ctxm = &ctx->ctx_arr[BNGE_CTX_FTQM];
+	entries = l2_qps + 2 * (extra_qps + qp1_qps);
+	rc = bnge_setup_ctxm_pg_tbls(bd, ctxm, entries, 2);
+	if (rc)
+		return rc;
+	for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++)
+		ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP << i;
+	ena |= FUNC_BACKING_STORE_CFG_REQ_DFLT_ENABLES;
+
+	rc = bnge_backing_store_cfg(bd, ena);
+	if (rc) {
+		dev_err(bd->dev, "Failed configuring ctx mem, rc: %d\n", rc);
+		return rc;
+	}
+	ctx->flags |= BNGE_CTX_FLAG_INITED;
+
+	return 0;
+}
+
+void bnge_init_ring_struct(struct bnge_net *bn)
+{
+	struct bnge_dev *bd = bn->bd;
+	int i, j;
+
+	for (i = 0; i < bd->nq_nr_rings; i++) {
+		struct bnge_napi *bnapi = bn->bnapi[i];
+		struct bnge_ring_mem_info *rmem;
+		struct bnge_nq_ring_info *nqr;
+		struct bnge_rx_ring_info *rxr;
+		struct bnge_tx_ring_info *txr;
+		struct bnge_ring_struct *ring;
+
+		nqr = &bnapi->nq_ring;
+		ring = &nqr->ring_struct;
+		rmem = &ring->ring_mem;
+		rmem->nr_pages = bn->cp_nr_pages;
+		rmem->page_size = HW_CMPD_RING_SIZE;
+		rmem->pg_arr = (void **)nqr->desc_ring;
+		rmem->dma_arr = nqr->desc_mapping;
+		rmem->vmem_size = 0;
+
+		rxr = bnapi->rx_ring;
+		if (!rxr)
+			goto skip_rx;
+
+		ring = &rxr->rx_ring_struct;
+		rmem = &ring->ring_mem;
+		rmem->nr_pages = bn->rx_nr_pages;
+		rmem->page_size = HW_RXBD_RING_SIZE;
+		rmem->pg_arr = (void **)rxr->rx_desc_ring;
+		rmem->dma_arr = rxr->rx_desc_mapping;
+		rmem->vmem_size = SW_RXBD_RING_SIZE * bn->rx_nr_pages;
+		rmem->vmem = (void **)&rxr->rx_buf_ring;
+
+		ring = &rxr->rx_agg_ring_struct;
+		rmem = &ring->ring_mem;
+		rmem->nr_pages = bn->rx_agg_nr_pages;
+		rmem->page_size = HW_RXBD_RING_SIZE;
+		rmem->pg_arr = (void **)rxr->rx_agg_desc_ring;
+		rmem->dma_arr = rxr->rx_agg_desc_mapping;
+		rmem->vmem_size = SW_RXBD_AGG_RING_SIZE * bn->rx_agg_nr_pages;
+		rmem->vmem = (void **)&rxr->rx_agg_buf_ring;
+
+skip_rx:
+		bnge_for_each_napi_tx(j, bnapi, txr) {
+			ring = &txr->tx_ring_struct;
+			rmem = &ring->ring_mem;
+			rmem->nr_pages = bn->tx_nr_pages;
+			rmem->page_size = HW_TXBD_RING_SIZE;
+			rmem->pg_arr = (void **)txr->tx_desc_ring;
+			rmem->dma_arr = txr->tx_desc_mapping;
+			rmem->vmem_size = SW_TXBD_RING_SIZE * bn->tx_nr_pages;
+			rmem->vmem = (void **)&txr->tx_buf_ring;
+		}
+	}
+}
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_rmem.h b/drivers/net/ethernet/broadcom/bnge/bnge_rmem.h
new file mode 100644
index 000000000000..341c7f81ed09
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_rmem.h
@@ -0,0 +1,202 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Broadcom */
+
+#ifndef _BNGE_RMEM_H_
+#define _BNGE_RMEM_H_
+
+struct bnge_ctx_mem_type;
+struct bnge_dev;
+struct bnge_net;
+
+#define PTU_PTE_VALID             0x1UL
+#define PTU_PTE_LAST              0x2UL
+#define PTU_PTE_NEXT_TO_LAST      0x4UL
+
+struct bnge_ring_mem_info {
+	/* Number of pages to next level */
+	int			nr_pages;
+	int			page_size;
+	u16			flags;
+#define BNGE_RMEM_VALID_PTE_FLAG	1
+#define BNGE_RMEM_RING_PTE_FLAG		2
+#define BNGE_RMEM_USE_FULL_PAGE_FLAG	4
+
+	u16			depth;
+
+	void			**pg_arr;
+	dma_addr_t		*dma_arr;
+
+	__le64			*pg_tbl;
+	dma_addr_t		dma_pg_tbl;
+
+	int			vmem_size;
+	void			**vmem;
+
+	struct bnge_ctx_mem_type	*ctx_mem;
+};
+
+/* The hardware supports certain page sizes.
+ * Use the supported page sizes to allocate the rings.
+ */
+#if (PAGE_SHIFT < 12)
+#define BNGE_PAGE_SHIFT	12
+#elif (PAGE_SHIFT <= 13)
+#define BNGE_PAGE_SHIFT	PAGE_SHIFT
+#elif (PAGE_SHIFT < 16)
+#define BNGE_PAGE_SHIFT	13
+#else
+#define BNGE_PAGE_SHIFT	16
+#endif
+#define BNGE_PAGE_SIZE	(1 << BNGE_PAGE_SHIFT)
+/* The RXBD length is 16-bit so we can only support page sizes < 64K */
+#if (PAGE_SHIFT > 15)
+#define BNGE_RX_PAGE_SHIFT 15
+#else
+#define BNGE_RX_PAGE_SHIFT PAGE_SHIFT
+#endif
+#define MAX_CTX_PAGES	(BNGE_PAGE_SIZE / 8)
+#define MAX_CTX_TOTAL_PAGES	(MAX_CTX_PAGES * MAX_CTX_PAGES)
+
+struct bnge_ctx_pg_info {
+	u32		entries;
+	u32		nr_pages;
+	void		*ctx_pg_arr[MAX_CTX_PAGES];
+	dma_addr_t	ctx_dma_arr[MAX_CTX_PAGES];
+	struct bnge_ring_mem_info ring_mem;
+	struct bnge_ctx_pg_info **ctx_pg_tbl;
+};
+
+#define BNGE_MAX_TQM_SP_RINGS		1
+#define BNGE_MAX_TQM_FP_RINGS		8
+#define BNGE_MAX_TQM_RINGS		\
+	(BNGE_MAX_TQM_SP_RINGS + BNGE_MAX_TQM_FP_RINGS)
+#define BNGE_BACKING_STORE_CFG_LEGACY_LEN	256
+#define BNGE_SET_CTX_PAGE_ATTR(attr)					\
+do {									\
+	if (BNGE_PAGE_SIZE == 0x2000)					\
+		attr = FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8K;	\
+	else if (BNGE_PAGE_SIZE == 0x10000)				\
+		attr = FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_64K;	\
+	else								\
+		attr = FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_4K;	\
+} while (0)
+
+#define BNGE_CTX_MRAV_AV_SPLIT_ENTRY	0
+
+#define BNGE_CTX_QP	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP
+#define BNGE_CTX_SRQ	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ
+#define BNGE_CTX_CQ	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ
+#define BNGE_CTX_VNIC	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC
+#define BNGE_CTX_STAT	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT
+#define BNGE_CTX_STQM	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING
+#define BNGE_CTX_FTQM	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING
+#define BNGE_CTX_MRAV	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV
+#define BNGE_CTX_TIM	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM
+#define BNGE_CTX_TCK	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TX_CK
+#define BNGE_CTX_RCK	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RX_CK
+#define BNGE_CTX_MTQM	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING
+#define BNGE_CTX_SQDBS	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW
+#define BNGE_CTX_RQDBS	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW
+#define BNGE_CTX_SRQDBS	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW
+#define BNGE_CTX_CQDBS	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW
+#define BNGE_CTX_SRT_TRACE	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE
+#define BNGE_CTX_SRT2_TRACE	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE
+#define BNGE_CTX_CRT_TRACE	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE
+#define BNGE_CTX_CRT2_TRACE	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT2_TRACE
+#define BNGE_CTX_RIGP0_TRACE	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP0_TRACE
+#define BNGE_CTX_L2_HWRM_TRACE	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_L2_HWRM_TRACE
+#define BNGE_CTX_ROCE_HWRM_TRACE	\
+	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ROCE_HWRM_TRACE
+
+#define BNGE_CTX_MAX		(BNGE_CTX_TIM + 1)
+#define BNGE_CTX_L2_MAX		(BNGE_CTX_FTQM + 1)
+#define BNGE_CTX_INV		((u16)-1)
+
+#define BNGE_CTX_V2_MAX	\
+	(FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ROCE_HWRM_TRACE + 1)
+
+#define BNGE_BS_CFG_ALL_DONE	\
+	FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_BS_CFG_ALL_DONE
+
+struct bnge_ctx_mem_type {
+	u16	type;
+	u16	entry_size;
+	u32	flags;
+#define BNGE_CTX_MEM_TYPE_VALID	\
+	FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID
+	u32	instance_bmap;
+	u8	init_value;
+	u8	entry_multiple;
+	u16	init_offset;
+#define	BNGE_CTX_INIT_INVALID_OFFSET	0xffff
+	u32	max_entries;
+	u32	min_entries;
+	u8	last:1;
+	u8	split_entry_cnt;
+#define BNGE_MAX_SPLIT_ENTRY	4
+	union {
+		struct {
+			u32	qp_l2_entries;
+			u32	qp_qp1_entries;
+			u32	qp_fast_qpmd_entries;
+		};
+		u32	srq_l2_entries;
+		u32	cq_l2_entries;
+		u32	vnic_entries;
+		struct {
+			u32	mrav_av_entries;
+			u32	mrav_num_entries_units;
+		};
+		u32	split[BNGE_MAX_SPLIT_ENTRY];
+	};
+	struct bnge_ctx_pg_info	*pg_info;
+};
+
+struct bnge_ctx_mem_info {
+	u8	tqm_fp_rings_count;
+	u32	flags;
+#define BNGE_CTX_FLAG_INITED	0x01
+	struct bnge_ctx_mem_type	ctx_arr[BNGE_CTX_V2_MAX];
+};
+
+struct bnge_ring_struct {
+	struct bnge_ring_mem_info	ring_mem;
+
+	u16			fw_ring_id;
+	union {
+		u16		grp_idx;
+		u16		map_idx; /* Used by NQs */
+	};
+	u32			handle;
+	u8			queue_id;
+};
+
+int bnge_alloc_ring(struct bnge_dev *bd, struct bnge_ring_mem_info *rmem);
+void bnge_free_ring(struct bnge_dev *bd, struct bnge_ring_mem_info *rmem);
+int bnge_alloc_ctx_mem(struct bnge_dev *bd);
+void bnge_free_ctx_mem(struct bnge_dev *bd);
+void bnge_init_ring_struct(struct bnge_net *bn);
+
+#endif /* _BNGE_RMEM_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index 6ec773e61182..805daae9dd36 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -6163,7 +6163,7 @@ bnx2_5708_serdes_timer(struct bnx2 *bp)
 static void
 bnx2_timer(struct timer_list *t)
 {
-	struct bnx2 *bp = from_timer(bp, t, timer);
+	struct bnx2 *bp = timer_container_of(bp, t, timer);
 
 	if (!netif_running(bp->dev))
 		return;
@@ -6400,7 +6400,7 @@ bnx2_open(struct net_device *dev)
 				rc = bnx2_request_irq(bp);
 
 			if (rc) {
-				del_timer_sync(&bp->timer);
+				timer_delete_sync(&bp->timer);
 				goto open_err;
 			}
 			bnx2_enable_int(bp);
@@ -6444,7 +6444,6 @@ bnx2_reset_task(struct work_struct *work)
 	if (!(pcicmd & PCI_COMMAND_MEMORY)) {
 		/* in case PCI block has reset */
 		pci_restore_state(bp->pdev);
-		pci_save_state(bp->pdev);
 	}
 	rc = bnx2_init_nic(bp, 1);
 	if (rc) {
@@ -6752,7 +6751,7 @@ bnx2_close(struct net_device *dev)
 	bnx2_disable_int_sync(bp);
 	bnx2_napi_disable(bp);
 	netif_tx_disable(dev);
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 	bnx2_shutdown_chip(bp);
 	bnx2_free_irq(bp);
 	bnx2_free_skbs(bp);
@@ -8602,7 +8601,7 @@ bnx2_remove_one(struct pci_dev *pdev)
 
 	unregister_netdev(dev);
 
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 	cancel_work_sync(&bp->reset_task);
 
 	pci_iounmap(bp->pdev, bp->regview);
@@ -8629,7 +8628,7 @@ bnx2_suspend(struct device *device)
 		cancel_work_sync(&bp->reset_task);
 		bnx2_netif_stop(bp, true);
 		netif_device_detach(dev);
-		del_timer_sync(&bp->timer);
+		timer_delete_sync(&bp->timer);
 		bnx2_shutdown_chip(bp);
 		__bnx2_free_irq(bp);
 		bnx2_free_skbs(bp);
@@ -8687,7 +8686,7 @@ static pci_ers_result_t bnx2_io_error_detected(struct pci_dev *pdev,
 
 	if (netif_running(dev)) {
 		bnx2_netif_stop(bp, true);
-		del_timer_sync(&bp->timer);
+		timer_delete_sync(&bp->timer);
 		bnx2_reset_nic(bp, BNX2_DRV_MSG_CODE_RESET);
 	}
 
@@ -8718,7 +8717,6 @@ static pci_ers_result_t bnx2_io_slot_reset(struct pci_dev *pdev)
 	} else {
 		pci_set_master(pdev);
 		pci_restore_state(pdev);
-		pci_save_state(pdev);
 
 		if (netif_running(dev))
 			err = bnx2_init_nic(bp, 1);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index a8e07e51418f..e59530357e2c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3059,7 +3059,7 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link)
 
 	bp->rx_mode = BNX2X_RX_MODE_NONE;
 
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 
 	if (IS_PF(bp) && !BP_NOMCP(bp)) {
 		/* Set ALWAYS_ALIVE bit in shmem */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
index 17ae6df90723..9af81630c8a4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
@@ -344,7 +344,7 @@ static void  bnx2x_dcbx_get_pfc_feature(struct bnx2x *bp,
 	}
 }
 
-/* maps unmapped priorities to to the same COS as L2 */
+/* maps unmapped priorities to the same COS as L2 */
 static void bnx2x_dcbx_map_nw(struct bnx2x *bp)
 {
 	int i;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 44199855ebfb..3d853eeb976f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -1243,9 +1243,9 @@ static int bnx2x_get_eeprom_len(struct net_device *dev)
  * pf B succeeds in taking the same lock since they are from the same port.
  * pf A takes the per pf misc lock. Performs eeprom access.
  * pf A finishes. Unlocks the per pf misc lock.
- * Pf B takes the lock and proceeds to perform it's own access.
+ * Pf B takes the lock and proceeds to perform its own access.
  * pf A unlocks the per port lock, while pf B is still working (!).
- * mcp takes the per port lock and corrupts pf B's access (and/or has it's own
+ * mcp takes the per port lock and corrupts pf B's access (and/or has its own
  * access corrupted by pf B)
  */
 static int bnx2x_acquire_nvram_lock(struct bnx2x *bp)
@@ -3318,8 +3318,11 @@ static int bnx2x_set_phys_id(struct net_device *dev,
 	return 0;
 }
 
-static int bnx2x_get_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info)
+static int bnx2x_get_rxfh_fields(struct net_device *dev,
+				 struct ethtool_rxfh_fields *info)
 {
+	struct bnx2x *bp = netdev_priv(dev);
+
 	switch (info->flow_type) {
 	case TCP_V4_FLOW:
 	case TCP_V6_FLOW:
@@ -3352,29 +3355,22 @@ static int bnx2x_get_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info)
 	return 0;
 }
 
-static int bnx2x_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
-			   u32 *rules __always_unused)
+static u32 bnx2x_get_rx_ring_count(struct net_device *dev)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
-	switch (info->cmd) {
-	case ETHTOOL_GRXRINGS:
-		info->data = BNX2X_NUM_ETH_QUEUES(bp);
-		return 0;
-	case ETHTOOL_GRXFH:
-		return bnx2x_get_rss_flags(bp, info);
-	default:
-		DP(BNX2X_MSG_ETHTOOL, "Command parameters not supported\n");
-		return -EOPNOTSUPP;
-	}
+	return BNX2X_NUM_ETH_QUEUES(bp);
 }
 
-static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info)
+static int bnx2x_set_rxfh_fields(struct net_device *dev,
+				 const struct ethtool_rxfh_fields *info,
+				 struct netlink_ext_ack *extack)
 {
+	struct bnx2x *bp = netdev_priv(dev);
 	int udp_rss_requested;
 
 	DP(BNX2X_MSG_ETHTOOL,
-	   "Set rss flags command parameters: flow type = %d, data = %llu\n",
+	   "Set rss flags command parameters: flow type = %d, data = %u\n",
 	   info->flow_type, info->data);
 
 	switch (info->flow_type) {
@@ -3460,19 +3456,6 @@ static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info)
 	}
 }
 
-static int bnx2x_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info)
-{
-	struct bnx2x *bp = netdev_priv(dev);
-
-	switch (info->cmd) {
-	case ETHTOOL_SRXFH:
-		return bnx2x_set_rss_flags(bp, info);
-	default:
-		DP(BNX2X_MSG_ETHTOOL, "Command parameters not supported\n");
-		return -EOPNOTSUPP;
-	}
-}
-
 static u32 bnx2x_get_rxfh_indir_size(struct net_device *dev)
 {
 	return T_ETH_INDIRECTION_TABLE_SIZE;
@@ -3683,11 +3666,12 @@ static const struct ethtool_ops bnx2x_ethtool_ops = {
 	.get_strings		= bnx2x_get_strings,
 	.set_phys_id		= bnx2x_set_phys_id,
 	.get_ethtool_stats	= bnx2x_get_ethtool_stats,
-	.get_rxnfc		= bnx2x_get_rxnfc,
-	.set_rxnfc		= bnx2x_set_rxnfc,
+	.get_rx_ring_count	= bnx2x_get_rx_ring_count,
 	.get_rxfh_indir_size	= bnx2x_get_rxfh_indir_size,
 	.get_rxfh		= bnx2x_get_rxfh,
 	.set_rxfh		= bnx2x_set_rxfh,
+	.get_rxfh_fields	= bnx2x_get_rxfh_fields,
+	.set_rxfh_fields	= bnx2x_set_rxfh_fields,
 	.get_channels		= bnx2x_get_channels,
 	.set_channels		= bnx2x_set_channels,
 	.get_module_info	= bnx2x_get_module_info,
@@ -3710,11 +3694,12 @@ static const struct ethtool_ops bnx2x_vf_ethtool_ops = {
 	.get_sset_count		= bnx2x_get_sset_count,
 	.get_strings		= bnx2x_get_strings,
 	.get_ethtool_stats	= bnx2x_get_ethtool_stats,
-	.get_rxnfc		= bnx2x_get_rxnfc,
-	.set_rxnfc		= bnx2x_set_rxnfc,
+	.get_rx_ring_count	= bnx2x_get_rx_ring_count,
 	.get_rxfh_indir_size	= bnx2x_get_rxfh_indir_size,
 	.get_rxfh		= bnx2x_get_rxfh,
 	.set_rxfh		= bnx2x_set_rxfh,
+	.get_rxfh_fields	= bnx2x_get_rxfh_fields,
+	.set_rxfh_fields	= bnx2x_set_rxfh_fields,
 	.get_channels		= bnx2x_get_channels,
 	.set_channels		= bnx2x_set_channels,
 	.get_link_ksettings	= bnx2x_get_vf_link_ksettings,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
index a84d015da5df..9221942290a8 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
@@ -332,7 +332,7 @@
 #define TOE_STATE (TOE_CONNECTION_TYPE << PROTOCOL_STATE_BIT_OFFSET)
 #define RDMA_STATE (RDMA_CONNECTION_TYPE << PROTOCOL_STATE_BIT_OFFSET)
 
-/* microcode fixed page page size 4K (chains and ring segments) */
+/* microcode fixed page size 4K (chains and ring segments) */
 #define MC_PAGE_SIZE 4096
 
 /* Number of indices per slow-path SB */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 678829646cec..6a1cc2032bf3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -308,8 +308,11 @@ static int bnx2x_set_storm_rx_mode(struct bnx2x *bp);
 /****************************************************************************
 * General service functions
 ****************************************************************************/
-
-static int bnx2x_hwtstamp_ioctl(struct bnx2x *bp, struct ifreq *ifr);
+static int bnx2x_hwtstamp_set(struct net_device *dev,
+			      struct kernel_hwtstamp_config *config,
+			      struct netlink_ext_ack *extack);
+static int bnx2x_hwtstamp_get(struct net_device *dev,
+			      struct kernel_hwtstamp_config *config);
 
 static void __storm_memset_dma_mapping(struct bnx2x *bp,
 				       u32 addr, dma_addr_t mapping)
@@ -1768,7 +1771,7 @@ static bool bnx2x_trylock_hw_lock(struct bnx2x *bp, u32 resource)
  * @bp:	driver handle
  *
  * Returns the recovery leader resource id according to the engine this function
- * belongs to. Currently only only 2 engines is supported.
+ * belongs to. Currently only 2 engines is supported.
  */
 static int bnx2x_get_leader_lock_resource(struct bnx2x *bp)
 {
@@ -5783,7 +5786,7 @@ void bnx2x_drv_pulse(struct bnx2x *bp)
 
 static void bnx2x_timer(struct timer_list *t)
 {
-	struct bnx2x *bp = from_timer(bp, t, timer);
+	struct bnx2x *bp = timer_container_of(bp, t, timer);
 
 	if (!netif_running(bp->dev))
 		return;
@@ -10219,8 +10222,7 @@ static int bnx2x_udp_tunnel_sync(struct net_device *netdev, unsigned int table)
 
 static const struct udp_tunnel_nic_info bnx2x_udp_tunnels = {
 	.sync_table	= bnx2x_udp_tunnel_sync,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-			  UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.flags		= UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
@@ -12814,14 +12816,9 @@ static int bnx2x_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	if (!netif_running(dev))
 		return -EAGAIN;
 
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return bnx2x_hwtstamp_ioctl(bp, ifr);
-	default:
-		DP(NETIF_MSG_LINK, "ioctl: phy id 0x%x, reg 0x%x, val_in 0x%x\n",
-		   mdio->phy_id, mdio->reg_num, mdio->val_in);
-		return mdio_mii_ioctl(&bp->mdio, mdio, cmd);
-	}
+	DP(NETIF_MSG_LINK, "ioctl: phy id 0x%x, reg 0x%x, val_in 0x%x\n",
+	   mdio->phy_id, mdio->reg_num, mdio->val_in);
+	return mdio_mii_ioctl(&bp->mdio, mdio, cmd);
 }
 
 static int bnx2x_validate_addr(struct net_device *dev)
@@ -13037,6 +13034,8 @@ static const struct net_device_ops bnx2x_netdev_ops = {
 	.ndo_get_phys_port_id	= bnx2x_get_phys_port_id,
 	.ndo_set_vf_link_state	= bnx2x_set_vf_link_state,
 	.ndo_features_check	= bnx2x_features_check,
+	.ndo_hwtstamp_get	= bnx2x_hwtstamp_get,
+	.ndo_hwtstamp_set	= bnx2x_hwtstamp_set,
 };
 
 static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev,
@@ -14140,7 +14139,7 @@ static int bnx2x_eeh_nic_unload(struct bnx2x *bp)
 	bnx2x_tx_disable(bp);
 	netdev_reset_tc(bp->dev);
 
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 	cancel_delayed_work_sync(&bp->sp_task);
 	cancel_delayed_work_sync(&bp->period_task);
 
@@ -14217,7 +14216,6 @@ static pci_ers_result_t bnx2x_io_slot_reset(struct pci_dev *pdev)
 
 	pci_set_master(pdev);
 	pci_restore_state(pdev);
-	pci_save_state(pdev);
 
 	if (netif_running(dev))
 		bnx2x_set_power_state(bp, PCI_D0);
@@ -15176,7 +15174,7 @@ void bnx2x_set_rx_ts(struct bnx2x *bp, struct sk_buff *skb)
 }
 
 /* Read the PHC */
-static u64 bnx2x_cyclecounter_read(const struct cyclecounter *cc)
+static u64 bnx2x_cyclecounter_read(struct cyclecounter *cc)
 {
 	struct bnx2x *bp = container_of(cc, struct bnx2x, cyclecounter);
 	int port = BP_PORT(bp);
@@ -15351,31 +15349,57 @@ int bnx2x_configure_ptp_filters(struct bnx2x *bp)
 	return 0;
 }
 
-static int bnx2x_hwtstamp_ioctl(struct bnx2x *bp, struct ifreq *ifr)
+static int bnx2x_hwtstamp_set(struct net_device *dev,
+			      struct kernel_hwtstamp_config *config,
+			      struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
+	struct bnx2x *bp = netdev_priv(dev);
 	int rc;
 
-	DP(BNX2X_MSG_PTP, "HWTSTAMP IOCTL called\n");
+	DP(BNX2X_MSG_PTP, "HWTSTAMP SET called\n");
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	if (!netif_running(dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Device is down");
+		return -EAGAIN;
+	}
 
 	DP(BNX2X_MSG_PTP, "Requested tx_type: %d, requested rx_filters = %d\n",
-	   config.tx_type, config.rx_filter);
+	   config->tx_type, config->rx_filter);
+
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_ON:
+	case HWTSTAMP_TX_OFF:
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "One-step timestamping is not supported");
+		return -ERANGE;
+	}
 
 	bp->hwtstamp_ioctl_called = true;
-	bp->tx_type = config.tx_type;
-	bp->rx_filter = config.rx_filter;
+	bp->tx_type = config->tx_type;
+	bp->rx_filter = config->rx_filter;
 
 	rc = bnx2x_configure_ptp_filters(bp);
-	if (rc)
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "HW configuration failure");
 		return rc;
+	}
+
+	config->rx_filter = bp->rx_filter;
+
+	return 0;
+}
+
+static int bnx2x_hwtstamp_get(struct net_device *dev,
+			      struct kernel_hwtstamp_config *config)
+{
+	struct bnx2x *bp = netdev_priv(dev);
 
-	config.rx_filter = bp->rx_filter;
+	config->rx_filter = bp->rx_filter;
+	config->tx_type = bp->tx_type;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 /* Configures HW for PTP */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 8e04552d2216..02c8213915a5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -2593,7 +2593,7 @@ void bnx2x_init_rx_mode_obj(struct bnx2x *bp,
 /********************* Multicast verbs: SET, CLEAR ****************************/
 static inline u8 bnx2x_mcast_bin_from_mac(u8 *mac)
 {
-	return (crc32c_le(0, mac, ETH_ALEN) >> 24) & 0xff;
+	return (crc32c(0, mac, ETH_ALEN) >> 24) & 0xff;
 }
 
 struct bnx2x_mcast_mac_elem {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
index bacc8552bce1..00ca861c80dd 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
@@ -379,7 +379,7 @@ struct bnx2x_vlan_mac_obj {
 	/**
 	*  Delete all configured elements having the given
 	*  vlan_mac_flags specification. Assumes no pending for
-	*  execution commands. Will schedule all all currently
+	*  execution commands. Will schedule all currently
 	*  configured MACs/VLANs/VLAN-MACs matching the vlan_mac_flags
 	*  specification for deletion and will use the given
 	*  ramrod_flags for the last DEL operation.
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 46edea75e062..d17d0ea89c36 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -54,9 +54,12 @@
 #include <net/pkt_cls.h>
 #include <net/page_pool/helpers.h>
 #include <linux/align.h>
+#include <net/netdev_lock.h>
 #include <net/netdev_queues.h>
+#include <net/netdev_rx_queue.h>
+#include <linux/pci-tph.h>
+#include <linux/bnxt/hsi.h>
 
-#include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ulp.h"
@@ -76,12 +79,12 @@
 #define BNXT_DEF_MSG_ENABLE	(NETIF_MSG_DRV | NETIF_MSG_HW | \
 				 NETIF_MSG_TX_ERR)
 
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Broadcom NetXtreme network driver");
 
 #define BNXT_RX_OFFSET (NET_SKB_PAD + NET_IP_ALIGN)
 #define BNXT_RX_DMA_OFFSET NET_SKB_PAD
-#define BNXT_RX_COPY_THRESH 256
 
 #define BNXT_TX_PUSH_THRESH 164
 
@@ -139,6 +142,7 @@ static const struct {
 	[NETXTREME_E_P5_VF] = { "Broadcom BCM5750X NetXtreme-E Ethernet Virtual Function" },
 	[NETXTREME_E_P5_VF_HV] = { "Broadcom BCM5750X NetXtreme-E Virtual Function for Hyper-V" },
 	[NETXTREME_E_P7_VF] = { "Broadcom BCM5760X Virtual Function" },
+	[NETXTREME_E_P7_VF_HV] = { "Broadcom BCM5760X Virtual Function for Hyper-V" },
 };
 
 static const struct pci_device_id bnxt_pci_tbl[] = {
@@ -214,6 +218,7 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x1808), .driver_data = NETXTREME_E_P5_VF_HV },
 	{ PCI_VDEVICE(BROADCOM, 0x1809), .driver_data = NETXTREME_E_P5_VF_HV },
 	{ PCI_VDEVICE(BROADCOM, 0x1819), .driver_data = NETXTREME_E_P7_VF },
+	{ PCI_VDEVICE(BROADCOM, 0x181b), .driver_data = NETXTREME_E_P7_VF_HV },
 	{ PCI_VDEVICE(BROADCOM, 0xd800), .driver_data = NETXTREME_S_VF },
 #endif
 	{ 0 }
@@ -260,6 +265,8 @@ const u16 bnxt_bstore_to_trace[] = {
 	[BNXT_CTX_CA1]		= DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA1_TRACE,
 	[BNXT_CTX_CA2]		= DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA2_TRACE,
 	[BNXT_CTX_RIGP1]	= DBG_LOG_BUFFER_FLUSH_REQ_TYPE_RIGP1_TRACE,
+	[BNXT_CTX_KONG]		= DBG_LOG_BUFFER_FLUSH_REQ_TYPE_AFM_KONG_HWRM_TRACE,
+	[BNXT_CTX_QPC]		= DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ERR_QPC_TRACE,
 };
 
 static struct workqueue_struct *bnxt_pf_wq;
@@ -312,7 +319,8 @@ static bool bnxt_vf_pciid(enum board_idx idx)
 	return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF ||
 		idx == NETXTREME_S_VF || idx == NETXTREME_C_VF_HV ||
 		idx == NETXTREME_E_VF_HV || idx == NETXTREME_E_P5_VF ||
-		idx == NETXTREME_E_P5_VF_HV || idx == NETXTREME_E_P7_VF);
+		idx == NETXTREME_E_P5_VF_HV || idx == NETXTREME_E_P7_VF ||
+		idx == NETXTREME_E_P7_VF_HV);
 }
 
 #define DB_CP_REARM_FLAGS	(DB_KEY_CP | DB_IDX_VALID)
@@ -474,6 +482,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct bnxt_tx_ring_info *txr;
 	struct bnxt_sw_tx_bd *tx_buf;
 	__le32 lflags = 0;
+	skb_frag_t *frag;
 
 	i = skb_get_queue_mapping(skb);
 	if (unlikely(i >= bp->tx_nr_rings)) {
@@ -486,6 +495,17 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	txr = &bp->tx_ring[bp->tx_ring_map[i]];
 	prod = txr->tx_prod;
 
+#if (MAX_SKB_FRAGS > TX_MAX_FRAGS)
+	if (skb_shinfo(skb)->nr_frags > TX_MAX_FRAGS) {
+		netdev_warn_once(dev, "SKB has too many (%d) fragments, max supported is %d.  SKB will be linearized.\n",
+				 skb_shinfo(skb)->nr_frags, TX_MAX_FRAGS);
+		if (skb_linearize(skb)) {
+			dev_kfree_skb_any(skb);
+			dev_core_stats_tx_dropped_inc(dev);
+			return NETDEV_TX_OK;
+		}
+	}
+#endif
 	free_size = bnxt_tx_avail(bp, txr);
 	if (unlikely(free_size < skb_shinfo(skb)->nr_frags + 2)) {
 		/* We must have raced with NAPI cleanup */
@@ -549,7 +569,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		lflags |= cpu_to_le32(TX_BD_FLAGS_NO_CRC);
 
 	if (free_size == bp->tx_ring_size && length <= bp->tx_push_thresh &&
-	    !lflags) {
+	    skb_frags_readable(skb) && !lflags) {
 		struct tx_push_buffer *tx_push_buf = txr->tx_push;
 		struct tx_push_bd *tx_push = &tx_push_buf->push_bd;
 		struct tx_bd_ext *tx_push1 = &tx_push->txbd2;
@@ -565,7 +585,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 					TX_BD_FLAGS_LHINT_512_AND_SMALLER |
 					TX_BD_FLAGS_COAL_NOW |
 					TX_BD_FLAGS_PACKET_END |
-					(2 << TX_BD_FLAGS_BD_CNT_SHIFT));
+					TX_BD_CNT(2));
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			tx_push1->tx_bd_hsize_lflags =
@@ -584,9 +604,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		skb_copy_from_linear_data(skb, pdata, len);
 		pdata += len;
 		for (j = 0; j < last_frag; j++) {
-			skb_frag_t *frag = &skb_shinfo(skb)->frags[j];
 			void *fptr;
 
+			frag = &skb_shinfo(skb)->frags[j];
 			fptr = skb_frag_address_safe(frag);
 			if (!fptr)
 				goto normal_tx;
@@ -640,7 +660,7 @@ normal_tx:
 
 	dma_unmap_addr_set(tx_buf, mapping, mapping);
 	flags = (len << TX_BD_LEN_SHIFT) | TX_BD_TYPE_LONG_TX_BD |
-		((last_frag + 2) << TX_BD_FLAGS_BD_CNT_SHIFT);
+		TX_BD_CNT(last_frag + 2);
 
 	txbd->tx_bd_haddr = cpu_to_le64(mapping);
 	txbd->tx_bd_opaque = SET_TX_OPAQUE(bp, txr, prod, 2 + last_frag);
@@ -694,8 +714,7 @@ normal_tx:
 			cpu_to_le32(cfa_action << TX_BD_CFA_ACTION_SHIFT);
 	txbd0 = txbd;
 	for (i = 0; i < last_frag; i++) {
-		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
+		frag = &skb_shinfo(skb)->frags[i];
 		prod = NEXT_TX(prod);
 		txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 
@@ -707,7 +726,8 @@ normal_tx:
 			goto tx_dma_error;
 
 		tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
-		dma_unmap_addr_set(tx_buf, mapping, mapping);
+		netmem_dma_unmap_addr_set(skb_frag_netmem(frag), tx_buf,
+					  mapping, mapping);
 
 		txbd->tx_bd_haddr = cpu_to_le64(mapping);
 
@@ -764,16 +784,18 @@ tx_dma_error:
 	for (i = 0; i < last_frag; i++) {
 		prod = NEXT_TX(prod);
 		tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
-		dma_unmap_page(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
-			       skb_frag_size(&skb_shinfo(skb)->frags[i]),
-			       DMA_TO_DEVICE);
+		frag = &skb_shinfo(skb)->frags[i];
+		netmem_dma_unmap_page_attrs(&pdev->dev,
+					    dma_unmap_addr(tx_buf, mapping),
+					    skb_frag_size(frag),
+					    DMA_TO_DEVICE, 0);
 	}
 
 tx_free:
 	dev_kfree_skb_any(skb);
 tx_kick_pending:
 	if (BNXT_TX_PTP_IS_SET(lflags)) {
-		txr->tx_buf_ring[txr->tx_prod].is_ts_pkt = 0;
+		txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].is_ts_pkt = 0;
 		atomic64_inc(&bp->ptp_cfg->stats.ts_err);
 		if (!(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
 			/* set SKB to err so PTP worker will clean up */
@@ -781,7 +803,7 @@ tx_kick_pending:
 	}
 	if (txr->kick_pending)
 		bnxt_txr_db_kick(bp, txr, txr->tx_prod);
-	txr->tx_buf_ring[txr->tx_prod].skb = NULL;
+	txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].skb = NULL;
 	dev_core_stats_tx_dropped_inc(dev);
 	return NETDEV_TX_OK;
 }
@@ -795,6 +817,7 @@ static bool __bnxt_tx_int(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 	u16 hw_cons = txr->tx_hw_cons;
 	unsigned int tx_bytes = 0;
 	u16 cons = txr->tx_cons;
+	skb_frag_t *frag;
 	int tx_pkts = 0;
 	bool rc = false;
 
@@ -834,13 +857,14 @@ static bool __bnxt_tx_int(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 		last = tx_buf->nr_frags;
 
 		for (j = 0; j < last; j++) {
+			frag = &skb_shinfo(skb)->frags[j];
 			cons = NEXT_TX(cons);
 			tx_buf = &txr->tx_buf_ring[RING_TX(bp, cons)];
-			dma_unmap_page(
-				&pdev->dev,
-				dma_unmap_addr(tx_buf, mapping),
-				skb_frag_size(&skb_shinfo(skb)->frags[j]),
-				DMA_TO_DEVICE);
+			netmem_dma_unmap_page_attrs(&pdev->dev,
+						    dma_unmap_addr(tx_buf,
+								   mapping),
+						    skb_frag_size(frag),
+						    DMA_TO_DEVICE, 0);
 		}
 		if (unlikely(is_ts_pkt)) {
 			if (BNXT_CHIP_P5(bp)) {
@@ -853,7 +877,7 @@ static bool __bnxt_tx_int(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 next_tx_int:
 		cons = NEXT_TX(cons);
 
-		dev_consume_skb_any(skb);
+		napi_consume_skb(skb, budget);
 	}
 
 	WRITE_ONCE(txr->tx_cons, cons);
@@ -879,9 +903,9 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 		bnapi->events &= ~BNXT_TX_CMP_EVENT;
 }
 
-static bool bnxt_separate_head_pool(void)
+static bool bnxt_separate_head_pool(struct bnxt_rx_ring_info *rxr)
 {
-	return PAGE_SIZE > BNXT_RX_PAGE_SIZE;
+	return rxr->need_head_pool || PAGE_SIZE > BNXT_RX_PAGE_SIZE;
 }
 
 static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
@@ -905,6 +929,26 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 	return page;
 }
 
+static netmem_ref __bnxt_alloc_rx_netmem(struct bnxt *bp, dma_addr_t *mapping,
+					 struct bnxt_rx_ring_info *rxr,
+					 unsigned int *offset,
+					 gfp_t gfp)
+{
+	netmem_ref netmem;
+
+	if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) {
+		netmem = page_pool_alloc_frag_netmem(rxr->page_pool, offset, BNXT_RX_PAGE_SIZE, gfp);
+	} else {
+		netmem = page_pool_alloc_netmems(rxr->page_pool, gfp);
+		*offset = 0;
+	}
+	if (!netmem)
+		return 0;
+
+	*mapping = page_pool_get_dma_addr_netmem(netmem) + *offset;
+	return netmem;
+}
+
 static inline u8 *__bnxt_alloc_rx_frag(struct bnxt *bp, dma_addr_t *mapping,
 				       struct bnxt_rx_ring_info *rxr,
 				       gfp_t gfp)
@@ -985,21 +1029,19 @@ static inline u16 bnxt_find_next_agg_idx(struct bnxt_rx_ring_info *rxr, u16 idx)
 	return next;
 }
 
-static inline int bnxt_alloc_rx_page(struct bnxt *bp,
-				     struct bnxt_rx_ring_info *rxr,
-				     u16 prod, gfp_t gfp)
+static int bnxt_alloc_rx_netmem(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
+				u16 prod, gfp_t gfp)
 {
 	struct rx_bd *rxbd =
 		&rxr->rx_agg_desc_ring[RX_AGG_RING(bp, prod)][RX_IDX(prod)];
 	struct bnxt_sw_rx_agg_bd *rx_agg_buf;
-	struct page *page;
-	dma_addr_t mapping;
 	u16 sw_prod = rxr->rx_sw_agg_prod;
 	unsigned int offset = 0;
+	dma_addr_t mapping;
+	netmem_ref netmem;
 
-	page = __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp);
-
-	if (!page)
+	netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, &offset, gfp);
+	if (!netmem)
 		return -ENOMEM;
 
 	if (unlikely(test_bit(sw_prod, rxr->rx_agg_bmap)))
@@ -1009,7 +1051,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
 	rx_agg_buf = &rxr->rx_agg_ring[sw_prod];
 	rxr->rx_sw_agg_prod = RING_RX_AGG(bp, NEXT_RX_AGG(sw_prod));
 
-	rx_agg_buf->page = page;
+	rx_agg_buf->netmem = netmem;
 	rx_agg_buf->offset = offset;
 	rx_agg_buf->mapping = mapping;
 	rxbd->rx_bd_haddr = cpu_to_le64(mapping);
@@ -1053,11 +1095,11 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
 		p5_tpa = true;
 
 	for (i = 0; i < agg_bufs; i++) {
-		u16 cons;
-		struct rx_agg_cmp *agg;
 		struct bnxt_sw_rx_agg_bd *cons_rx_buf, *prod_rx_buf;
+		struct rx_agg_cmp *agg;
 		struct rx_bd *prod_bd;
-		struct page *page;
+		netmem_ref netmem;
+		u16 cons;
 
 		if (p5_tpa)
 			agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, start + i);
@@ -1074,11 +1116,11 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
 		cons_rx_buf = &rxr->rx_agg_ring[cons];
 
 		/* It is possible for sw_prod to be equal to cons, so
-		 * set cons_rx_buf->page to NULL first.
+		 * set cons_rx_buf->netmem to 0 first.
 		 */
-		page = cons_rx_buf->page;
-		cons_rx_buf->page = NULL;
-		prod_rx_buf->page = page;
+		netmem = cons_rx_buf->netmem;
+		cons_rx_buf->netmem = 0;
+		prod_rx_buf->netmem = netmem;
 		prod_rx_buf->offset = cons_rx_buf->offset;
 
 		prod_rx_buf->mapping = cons_rx_buf->mapping;
@@ -1204,29 +1246,35 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp,
 	return skb;
 }
 
-static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
-			       struct bnxt_cp_ring_info *cpr,
-			       struct skb_shared_info *shinfo,
-			       u16 idx, u32 agg_bufs, bool tpa,
-			       struct xdp_buff *xdp)
+static u32 __bnxt_rx_agg_netmems(struct bnxt *bp,
+				 struct bnxt_cp_ring_info *cpr,
+				 u16 idx, u32 agg_bufs, bool tpa,
+				 struct sk_buff *skb,
+				 struct xdp_buff *xdp)
 {
 	struct bnxt_napi *bnapi = cpr->bnapi;
-	struct pci_dev *pdev = bp->pdev;
-	struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
-	u16 prod = rxr->rx_agg_prod;
+	struct skb_shared_info *shinfo;
+	struct bnxt_rx_ring_info *rxr;
 	u32 i, total_frag_len = 0;
 	bool p5_tpa = false;
+	u16 prod;
+
+	rxr = bnapi->rx_ring;
+	prod = rxr->rx_agg_prod;
 
 	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) && tpa)
 		p5_tpa = true;
 
+	if (skb)
+		shinfo = skb_shinfo(skb);
+	else
+		shinfo = xdp_get_shared_info_from_buff(xdp);
+
 	for (i = 0; i < agg_bufs; i++) {
-		skb_frag_t *frag = &shinfo->frags[i];
-		u16 cons, frag_len;
-		struct rx_agg_cmp *agg;
 		struct bnxt_sw_rx_agg_bd *cons_rx_buf;
-		struct page *page;
-		dma_addr_t mapping;
+		struct rx_agg_cmp *agg;
+		u16 cons, frag_len;
+		netmem_ref netmem;
 
 		if (p5_tpa)
 			agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, i);
@@ -1237,27 +1285,41 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
 			    RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT;
 
 		cons_rx_buf = &rxr->rx_agg_ring[cons];
-		skb_frag_fill_page_desc(frag, cons_rx_buf->page,
-					cons_rx_buf->offset, frag_len);
-		shinfo->nr_frags = i + 1;
+		if (skb) {
+			skb_add_rx_frag_netmem(skb, i, cons_rx_buf->netmem,
+					       cons_rx_buf->offset,
+					       frag_len, BNXT_RX_PAGE_SIZE);
+		} else {
+			skb_frag_t *frag = &shinfo->frags[i];
+
+			skb_frag_fill_netmem_desc(frag, cons_rx_buf->netmem,
+						  cons_rx_buf->offset,
+						  frag_len);
+			shinfo->nr_frags = i + 1;
+		}
 		__clear_bit(cons, rxr->rx_agg_bmap);
 
-		/* It is possible for bnxt_alloc_rx_page() to allocate
+		/* It is possible for bnxt_alloc_rx_netmem() to allocate
 		 * a sw_prod index that equals the cons index, so we
 		 * need to clear the cons entry now.
 		 */
-		mapping = cons_rx_buf->mapping;
-		page = cons_rx_buf->page;
-		cons_rx_buf->page = NULL;
+		netmem = cons_rx_buf->netmem;
+		cons_rx_buf->netmem = 0;
 
-		if (xdp && page_is_pfmemalloc(page))
+		if (xdp && netmem_is_pfmemalloc(netmem))
 			xdp_buff_set_frag_pfmemalloc(xdp);
 
-		if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_ATOMIC) != 0) {
+		if (bnxt_alloc_rx_netmem(bp, rxr, prod, GFP_ATOMIC) != 0) {
+			if (skb) {
+				skb->len -= frag_len;
+				skb->data_len -= frag_len;
+				skb->truesize -= BNXT_RX_PAGE_SIZE;
+			}
+
 			--shinfo->nr_frags;
-			cons_rx_buf->page = page;
+			cons_rx_buf->netmem = netmem;
 
-			/* Update prod since possibly some pages have been
+			/* Update prod since possibly some netmems have been
 			 * allocated already.
 			 */
 			rxr->rx_agg_prod = prod;
@@ -1265,8 +1327,8 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
 			return 0;
 		}
 
-		dma_sync_single_for_cpu(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE,
-					bp->rx_dir);
+		page_pool_dma_sync_netmem_for_cpu(rxr->page_pool, netmem, 0,
+						  BNXT_RX_PAGE_SIZE);
 
 		total_frag_len += frag_len;
 		prod = NEXT_RX_AGG(prod);
@@ -1275,32 +1337,28 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
 	return total_frag_len;
 }
 
-static struct sk_buff *bnxt_rx_agg_pages_skb(struct bnxt *bp,
-					     struct bnxt_cp_ring_info *cpr,
-					     struct sk_buff *skb, u16 idx,
-					     u32 agg_bufs, bool tpa)
+static struct sk_buff *bnxt_rx_agg_netmems_skb(struct bnxt *bp,
+					       struct bnxt_cp_ring_info *cpr,
+					       struct sk_buff *skb, u16 idx,
+					       u32 agg_bufs, bool tpa)
 {
-	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	u32 total_frag_len = 0;
 
-	total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo, idx,
-					     agg_bufs, tpa, NULL);
+	total_frag_len = __bnxt_rx_agg_netmems(bp, cpr, idx, agg_bufs, tpa,
+					       skb, NULL);
 	if (!total_frag_len) {
 		skb_mark_for_recycle(skb);
 		dev_kfree_skb(skb);
 		return NULL;
 	}
 
-	skb->data_len += total_frag_len;
-	skb->len += total_frag_len;
-	skb->truesize += BNXT_RX_PAGE_SIZE * agg_bufs;
 	return skb;
 }
 
-static u32 bnxt_rx_agg_pages_xdp(struct bnxt *bp,
-				 struct bnxt_cp_ring_info *cpr,
-				 struct xdp_buff *xdp, u16 idx,
-				 u32 agg_bufs, bool tpa)
+static u32 bnxt_rx_agg_netmems_xdp(struct bnxt *bp,
+				   struct bnxt_cp_ring_info *cpr,
+				   struct xdp_buff *xdp, u16 idx,
+				   u32 agg_bufs, bool tpa)
 {
 	struct skb_shared_info *shinfo = xdp_get_shared_info_from_buff(xdp);
 	u32 total_frag_len = 0;
@@ -1308,8 +1366,8 @@ static u32 bnxt_rx_agg_pages_xdp(struct bnxt *bp,
 	if (!xdp_buff_has_frags(xdp))
 		shinfo->nr_frags = 0;
 
-	total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo,
-					     idx, agg_bufs, tpa, xdp);
+	total_frag_len = __bnxt_rx_agg_netmems(bp, cpr, idx, agg_bufs, tpa,
+					       NULL, xdp);
 	if (total_frag_len) {
 		xdp_buff_set_frags_flag(xdp);
 		shinfo->nr_frags = agg_bufs;
@@ -1343,13 +1401,13 @@ static struct sk_buff *bnxt_copy_data(struct bnxt_napi *bnapi, u8 *data,
 	if (!skb)
 		return NULL;
 
-	dma_sync_single_for_cpu(&pdev->dev, mapping, bp->rx_copy_thresh,
+	dma_sync_single_for_cpu(&pdev->dev, mapping, bp->rx_copybreak,
 				bp->rx_dir);
 
 	memcpy(skb->data - NET_IP_ALIGN, data - NET_IP_ALIGN,
 	       len + NET_IP_ALIGN);
 
-	dma_sync_single_for_device(&pdev->dev, mapping, bp->rx_copy_thresh,
+	dma_sync_single_for_device(&pdev->dev, mapping, bp->rx_copybreak,
 				   bp->rx_dir);
 
 	skb_put(skb, len);
@@ -1768,7 +1826,7 @@ static struct net_device *bnxt_get_pkt_dev(struct bnxt *bp, u16 cfa_code)
 {
 	struct net_device *dev = bnxt_get_vf_rep(bp, cfa_code);
 
-	/* if vf-rep dev is NULL, the must belongs to the PF */
+	/* if vf-rep dev is NULL, it must belong to the PF */
 	return dev ? dev : bp->dev;
 }
 
@@ -1842,7 +1900,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		return NULL;
 	}
 
-	if (len <= bp->rx_copy_thresh) {
+	if (len <= bp->rx_copybreak) {
 		skb = bnxt_copy_skb(bnapi, data_ptr, len, mapping);
 		if (!skb) {
 			bnxt_abort_tpa(cpr, idx, agg_bufs);
@@ -1881,7 +1939,8 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 	}
 
 	if (agg_bufs) {
-		skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, idx, agg_bufs, true);
+		skb = bnxt_rx_agg_netmems_skb(bp, cpr, skb, idx, agg_bufs,
+					      true);
 		if (!skb) {
 			/* Page reuse already handled by bnxt_rx_pages(). */
 			cpr->sw_stats->rx.rx_oom_discards += 1;
@@ -2001,6 +2060,7 @@ static struct sk_buff *bnxt_rx_vlan(struct sk_buff *skb, u8 cmp_type,
 	}
 	return skb;
 vlan_err:
+	skb_mark_for_recycle(skb);
 	dev_kfree_skb(skb);
 	return NULL;
 }
@@ -2039,6 +2099,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	struct rx_cmp_ext *rxcmp1;
 	u32 tmp_raw_cons = *raw_cons;
 	u16 cons, prod, cp_cons = RING_CMP(tmp_raw_cons);
+	struct skb_shared_info *sinfo;
 	struct bnxt_sw_rx_bd *rx_buf;
 	unsigned int len;
 	u8 *data_ptr, agg_bufs, cmp_type;
@@ -2160,11 +2221,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	if (bnxt_xdp_attached(bp, rxr)) {
 		bnxt_xdp_buff_init(bp, rxr, cons, data_ptr, len, &xdp);
 		if (agg_bufs) {
-			u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp,
-							     cp_cons, agg_bufs,
-							     false);
+			u32 frag_len = bnxt_rx_agg_netmems_xdp(bp, cpr, &xdp,
+							       cp_cons,
+							       agg_bufs,
+							       false);
 			if (!frag_len)
 				goto oom_next_rx;
+
 		}
 		xdp_active = true;
 	}
@@ -2174,9 +2237,15 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			rc = 1;
 			goto next_rx;
 		}
+		if (xdp_buff_has_frags(&xdp)) {
+			sinfo = xdp_get_shared_info_from_buff(&xdp);
+			agg_bufs = sinfo->nr_frags;
+		} else {
+			agg_bufs = 0;
+		}
 	}
 
-	if (len <= bp->rx_copy_thresh) {
+	if (len <= bp->rx_copybreak) {
 		if (!xdp_active)
 			skb = bnxt_copy_skb(bnapi, data_ptr, len, dma_addr);
 		else
@@ -2207,11 +2276,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 
 	if (agg_bufs) {
 		if (!xdp_active) {
-			skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, cp_cons, agg_bufs, false);
+			skb = bnxt_rx_agg_netmems_skb(bp, cpr, skb, cp_cons,
+						      agg_bufs, false);
 			if (!skb)
 				goto oom_next_rx;
 		} else {
-			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs, rxr->page_pool, &xdp, rxcmp1);
+			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs,
+						 rxr->page_pool, &xdp);
 			if (!skb) {
 				/* we should be able to free the old skb here */
 				bnxt_xdp_buff_frags_free(rxr, &xdp);
@@ -2855,6 +2926,7 @@ static int bnxt_async_event_process(struct bnxt *bp,
 	}
 	__bnxt_queue_sp_work(bp);
 async_event_process_exit:
+	bnxt_ulp_async_events(bp, cmpl);
 	return 0;
 }
 
@@ -2897,6 +2969,13 @@ static int bnxt_hwrm_handler(struct bnxt *bp, struct tx_cmp *txcmp)
 	return 0;
 }
 
+static bool bnxt_vnic_is_active(struct bnxt *bp)
+{
+	struct bnxt_vnic_info *vnic = &bp->vnic_info[0];
+
+	return vnic->fw_vnic_id != INVALID_HW_RING_ID && vnic->mru > 0;
+}
+
 static irqreturn_t bnxt_msix(int irq, void *dev_instance)
 {
 	struct bnxt_napi *bnapi = dev_instance;
@@ -2926,6 +3005,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 {
 	struct bnxt_napi *bnapi = cpr->bnapi;
 	u32 raw_cons = cpr->cp_raw_cons;
+	bool flush_xdp = false;
 	u32 cons;
 	int rx_pkts = 0;
 	u8 event = 0;
@@ -2979,6 +3059,8 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			else
 				rc = bnxt_force_rx_discard(bp, cpr, &raw_cons,
 							   &event);
+			if (event & BNXT_REDIRECT_EVENT)
+				flush_xdp = true;
 			if (likely(rc >= 0))
 				rx_pkts += rc;
 			/* Increment rx_pkts when rc is -ENOMEM to count towards
@@ -3003,7 +3085,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		}
 	}
 
-	if (event & BNXT_REDIRECT_EVENT) {
+	if (flush_xdp) {
 		xdp_do_flush();
 		event &= ~BNXT_REDIRECT_EVENT;
 	}
@@ -3164,7 +3246,7 @@ static int bnxt_poll(struct napi_struct *napi, int budget)
 			break;
 		}
 	}
-	if (bp->flags & BNXT_FLAG_DIM) {
+	if ((bp->flags & BNXT_FLAG_DIM) && bnxt_vnic_is_active(bp)) {
 		struct dim_sample dim_sample = {};
 
 		dim_update_sample(cpr->event_ctr,
@@ -3295,7 +3377,7 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget)
 poll_done:
 	cpr_rx = &cpr->cp_ring_arr[0];
 	if (cpr_rx->cp_ring_type == BNXT_NQ_HDL_TYPE_RX &&
-	    (bp->flags & BNXT_FLAG_DIM)) {
+	    (bp->flags & BNXT_FLAG_DIM) && bnxt_vnic_is_active(bp)) {
 		struct dim_sample dim_sample = {};
 
 		dim_update_sample(cpr->event_ctr,
@@ -3307,75 +3389,87 @@ poll_done:
 	return work_done;
 }
 
-static void bnxt_free_tx_skbs(struct bnxt *bp)
+static void bnxt_free_one_tx_ring_skbs(struct bnxt *bp,
+				       struct bnxt_tx_ring_info *txr, int idx)
 {
 	int i, max_idx;
 	struct pci_dev *pdev = bp->pdev;
 
-	if (!bp->tx_ring)
-		return;
-
 	max_idx = bp->tx_nr_pages * TX_DESC_CNT;
-	for (i = 0; i < bp->tx_nr_rings; i++) {
-		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
-		int j;
 
-		if (!txr->tx_buf_ring)
+	for (i = 0; i < max_idx;) {
+		struct bnxt_sw_tx_bd *tx_buf = &txr->tx_buf_ring[i];
+		struct sk_buff *skb;
+		int j, last;
+
+		if (idx  < bp->tx_nr_rings_xdp &&
+		    tx_buf->action == XDP_REDIRECT) {
+			dma_unmap_single(&pdev->dev,
+					 dma_unmap_addr(tx_buf, mapping),
+					 dma_unmap_len(tx_buf, len),
+					 DMA_TO_DEVICE);
+			xdp_return_frame(tx_buf->xdpf);
+			tx_buf->action = 0;
+			tx_buf->xdpf = NULL;
+			i++;
 			continue;
+		}
 
-		for (j = 0; j < max_idx;) {
-			struct bnxt_sw_tx_bd *tx_buf = &txr->tx_buf_ring[j];
-			struct sk_buff *skb;
-			int k, last;
-
-			if (i < bp->tx_nr_rings_xdp &&
-			    tx_buf->action == XDP_REDIRECT) {
-				dma_unmap_single(&pdev->dev,
-					dma_unmap_addr(tx_buf, mapping),
-					dma_unmap_len(tx_buf, len),
-					DMA_TO_DEVICE);
-				xdp_return_frame(tx_buf->xdpf);
-				tx_buf->action = 0;
-				tx_buf->xdpf = NULL;
-				j++;
-				continue;
-			}
+		skb = tx_buf->skb;
+		if (!skb) {
+			i++;
+			continue;
+		}
 
-			skb = tx_buf->skb;
-			if (!skb) {
-				j++;
-				continue;
-			}
+		tx_buf->skb = NULL;
 
-			tx_buf->skb = NULL;
+		if (tx_buf->is_push) {
+			dev_kfree_skb(skb);
+			i += 2;
+			continue;
+		}
 
-			if (tx_buf->is_push) {
-				dev_kfree_skb(skb);
-				j += 2;
-				continue;
-			}
+		dma_unmap_single(&pdev->dev,
+				 dma_unmap_addr(tx_buf, mapping),
+				 skb_headlen(skb),
+				 DMA_TO_DEVICE);
 
-			dma_unmap_single(&pdev->dev,
-					 dma_unmap_addr(tx_buf, mapping),
-					 skb_headlen(skb),
-					 DMA_TO_DEVICE);
+		last = tx_buf->nr_frags;
+		i += 2;
+		for (j = 0; j < last; j++, i++) {
+			int ring_idx = i & bp->tx_ring_mask;
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[j];
 
-			last = tx_buf->nr_frags;
-			j += 2;
-			for (k = 0; k < last; k++, j++) {
-				int ring_idx = j & bp->tx_ring_mask;
-				skb_frag_t *frag = &skb_shinfo(skb)->frags[k];
-
-				tx_buf = &txr->tx_buf_ring[ring_idx];
-				dma_unmap_page(
-					&pdev->dev,
-					dma_unmap_addr(tx_buf, mapping),
-					skb_frag_size(frag), DMA_TO_DEVICE);
-			}
-			dev_kfree_skb(skb);
+			tx_buf = &txr->tx_buf_ring[ring_idx];
+			netmem_dma_unmap_page_attrs(&pdev->dev,
+						    dma_unmap_addr(tx_buf,
+								   mapping),
+						    skb_frag_size(frag),
+						    DMA_TO_DEVICE, 0);
 		}
-		netdev_tx_reset_queue(netdev_get_tx_queue(bp->dev, i));
+		dev_kfree_skb(skb);
+	}
+	netdev_tx_reset_queue(netdev_get_tx_queue(bp->dev, idx));
+}
+
+static void bnxt_free_tx_skbs(struct bnxt *bp)
+{
+	int i;
+
+	if (!bp->tx_ring)
+		return;
+
+	for (i = 0; i < bp->tx_nr_rings; i++) {
+		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
+
+		if (!txr->tx_buf_ring)
+			continue;
+
+		bnxt_free_one_tx_ring_skbs(bp, txr, i);
 	}
+
+	if (bp->ptp_cfg && !(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
+		bnxt_ptp_free_txts_skbs(bp->ptp_cfg);
 }
 
 static void bnxt_free_one_rx_ring(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
@@ -3407,15 +3501,15 @@ static void bnxt_free_one_rx_agg_ring(struct bnxt *bp, struct bnxt_rx_ring_info
 
 	for (i = 0; i < max_idx; i++) {
 		struct bnxt_sw_rx_agg_bd *rx_agg_buf = &rxr->rx_agg_ring[i];
-		struct page *page = rx_agg_buf->page;
+		netmem_ref netmem = rx_agg_buf->netmem;
 
-		if (!page)
+		if (!netmem)
 			continue;
 
-		rx_agg_buf->page = NULL;
+		rx_agg_buf->netmem = 0;
 		__clear_bit(i, rxr->rx_agg_bmap);
 
-		page_pool_recycle_direct(rxr->page_pool, page);
+		page_pool_recycle_direct_netmem(rxr->page_pool, netmem);
 	}
 }
 
@@ -3708,8 +3802,7 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
 			xdp_rxq_info_unreg(&rxr->xdp_rxq);
 
 		page_pool_destroy(rxr->page_pool);
-		if (bnxt_separate_head_pool())
-			page_pool_destroy(rxr->head_pool);
+		page_pool_destroy(rxr->head_pool);
 		rxr->page_pool = rxr->head_pool = NULL;
 
 		kfree(rxr->rx_agg_bmap);
@@ -3727,30 +3820,37 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 				   struct bnxt_rx_ring_info *rxr,
 				   int numa_node)
 {
+	const unsigned int agg_size_fac = PAGE_SIZE / BNXT_RX_PAGE_SIZE;
+	const unsigned int rx_size_fac = PAGE_SIZE / SZ_4K;
 	struct page_pool_params pp = { 0 };
 	struct page_pool *pool;
 
-	pp.pool_size = bp->rx_agg_ring_size;
+	pp.pool_size = bp->rx_agg_ring_size / agg_size_fac;
 	if (BNXT_RX_PAGE_MODE(bp))
-		pp.pool_size += bp->rx_ring_size;
+		pp.pool_size += bp->rx_ring_size / rx_size_fac;
 	pp.nid = numa_node;
-	pp.napi = &rxr->bnapi->napi;
 	pp.netdev = bp->dev;
 	pp.dev = &bp->pdev->dev;
 	pp.dma_dir = bp->rx_dir;
 	pp.max_len = PAGE_SIZE;
-	pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+	pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV |
+		   PP_FLAG_ALLOW_UNREADABLE_NETMEM;
+	pp.queue_idx = rxr->bnapi->index;
 
 	pool = page_pool_create(&pp);
 	if (IS_ERR(pool))
 		return PTR_ERR(pool);
 	rxr->page_pool = pool;
 
-	if (bnxt_separate_head_pool()) {
-		pp.pool_size = max(bp->rx_ring_size, 1024);
+	rxr->need_head_pool = page_pool_is_unreadable(pool);
+	if (bnxt_separate_head_pool(rxr)) {
+		pp.pool_size = min(bp->rx_ring_size / rx_size_fac, 1024);
+		pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
 		pool = page_pool_create(&pp);
 		if (IS_ERR(pool))
 			goto err_destroy_pp;
+	} else {
+		page_pool_get(pool);
 	}
 	rxr->head_pool = pool;
 
@@ -3762,6 +3862,12 @@ err_destroy_pp:
 	return PTR_ERR(pool);
 }
 
+static void bnxt_enable_rx_page_pool(struct bnxt_rx_ring_info *rxr)
+{
+	page_pool_enable_direct_recycling(rxr->head_pool, &rxr->bnapi->napi);
+	page_pool_enable_direct_recycling(rxr->page_pool, &rxr->bnapi->napi);
+}
+
 static int bnxt_alloc_rx_agg_bmap(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 {
 	u16 mem_size;
@@ -3800,6 +3906,7 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp)
 		rc = bnxt_alloc_rx_page_pool(bp, rxr, cpu_node);
 		if (rc)
 			return rc;
+		bnxt_enable_rx_page_pool(rxr);
 
 		rc = xdp_rxq_info_reg(&rxr->xdp_rxq, bp->dev, i, 0);
 		if (rc < 0)
@@ -4159,6 +4266,8 @@ static void bnxt_reset_rx_ring_struct(struct bnxt *bp,
 
 	rxr->page_pool->p.napi = NULL;
 	rxr->page_pool = NULL;
+	rxr->head_pool->p.napi = NULL;
+	rxr->head_pool = NULL;
 	memset(&rxr->xdp_rxq, 0, sizeof(struct xdp_rxq_info));
 
 	ring = &rxr->rx_ring_struct;
@@ -4283,18 +4392,18 @@ static void bnxt_alloc_one_rx_ring_skb(struct bnxt *bp,
 	rxr->rx_prod = prod;
 }
 
-static void bnxt_alloc_one_rx_ring_page(struct bnxt *bp,
-					struct bnxt_rx_ring_info *rxr,
-					int ring_nr)
+static void bnxt_alloc_one_rx_ring_netmem(struct bnxt *bp,
+					  struct bnxt_rx_ring_info *rxr,
+					  int ring_nr)
 {
 	u32 prod;
 	int i;
 
 	prod = rxr->rx_agg_prod;
 	for (i = 0; i < bp->rx_agg_ring_size; i++) {
-		if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_KERNEL)) {
+		if (bnxt_alloc_rx_netmem(bp, rxr, prod, GFP_KERNEL)) {
 			netdev_warn(bp->dev, "init'ed rx ring %d with %d/%d pages only\n",
-				    ring_nr, i, bp->rx_ring_size);
+				    ring_nr, i, bp->rx_agg_ring_size);
 			break;
 		}
 		prod = NEXT_RX_AGG(prod);
@@ -4333,7 +4442,7 @@ static int bnxt_alloc_one_rx_ring(struct bnxt *bp, int ring_nr)
 	if (!(bp->flags & BNXT_FLAG_AGG_RINGS))
 		return 0;
 
-	bnxt_alloc_one_rx_ring_page(bp, rxr, ring_nr);
+	bnxt_alloc_one_rx_ring_netmem(bp, rxr, ring_nr);
 
 	if (rxr->rx_tpa) {
 		rc = bnxt_alloc_one_tpa_info_data(bp, rxr);
@@ -4370,7 +4479,14 @@ static void bnxt_init_one_rx_agg_ring_rxbd(struct bnxt *bp,
 	ring->fw_ring_id = INVALID_HW_RING_ID;
 	if ((bp->flags & BNXT_FLAG_AGG_RINGS)) {
 		type = ((u32)BNXT_RX_PAGE_SIZE << RX_BD_LEN_SHIFT) |
-			RX_BD_TYPE_RX_AGG_BD | RX_BD_FLAGS_SOP;
+			RX_BD_TYPE_RX_AGG_BD;
+
+		/* On P7, setting EOP will cause the chip to disable
+		 * Relaxed Ordering (RO) for TPA data.  Disable EOP for
+		 * potentially higher performance with RO.
+		 */
+		if (BNXT_CHIP_P5_AND_MINUS(bp) || !(bp->flags & BNXT_FLAG_TPA))
+			type |= RX_BD_FLAGS_AGG_EOP;
 
 		bnxt_init_rxbd_pages(ring, type);
 	}
@@ -4601,6 +4717,17 @@ void bnxt_set_tpa_flags(struct bnxt *bp)
 		bp->flags |= BNXT_FLAG_GRO;
 }
 
+static void bnxt_init_ring_params(struct bnxt *bp)
+{
+	unsigned int rx_size;
+
+	bp->rx_copybreak = BNXT_DEFAULT_RX_COPYBREAK;
+	/* Try to fit 4 chunks into a 4k page */
+	rx_size = SZ_1K -
+		NET_SKB_PAD - SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	bp->dev->cfg->hds_thresh = max(BNXT_DEFAULT_RX_COPYBREAK, rx_size);
+}
+
 /* bp->rx_ring_size, bp->tx_ring_size, dev->mtu, BNXT_FLAG_{G|L}RO flags must
  * be set on entry.
  */
@@ -4615,12 +4742,11 @@ void bnxt_set_ring_params(struct bnxt *bp)
 	rx_space = rx_size + ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) +
 		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
-	bp->rx_copy_thresh = BNXT_RX_COPY_THRESH;
 	ring_size = bp->rx_ring_size;
 	bp->rx_agg_ring_size = 0;
 	bp->rx_agg_nr_pages = 0;
 
-	if (bp->flags & BNXT_FLAG_TPA)
+	if (bp->flags & BNXT_FLAG_TPA || bp->flags & BNXT_FLAG_HDS)
 		agg_factor = min_t(u32, 4, 65536 / BNXT_RX_PAGE_SIZE);
 
 	bp->flags &= ~BNXT_FLAG_JUMBO;
@@ -4660,7 +4786,10 @@ void bnxt_set_ring_params(struct bnxt *bp)
 				  ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) -
 				  SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 		} else {
-			rx_size = SKB_DATA_ALIGN(BNXT_RX_COPY_THRESH + NET_IP_ALIGN);
+			rx_size = max3(BNXT_DEFAULT_RX_COPYBREAK,
+				       bp->rx_copybreak,
+				       bp->dev->cfg_pending->hds_thresh);
+			rx_size = SKB_DATA_ALIGN(rx_size + NET_IP_ALIGN);
 			rx_space = rx_size + NET_SKB_PAD +
 				SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 		}
@@ -4701,7 +4830,7 @@ void bnxt_set_ring_params(struct bnxt *bp)
 /* Changing allocation mode of RX rings.
  * TODO: Update when extending xdp_rxq_info to support allocation modes.
  */
-int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
+static void __bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
 {
 	struct net_device *dev = bp->dev;
 
@@ -4722,15 +4851,30 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
 			bp->rx_skb_func = bnxt_rx_page_skb;
 		}
 		bp->rx_dir = DMA_BIDIRECTIONAL;
-		/* Disable LRO or GRO_HW */
-		netdev_update_features(dev);
 	} else {
 		dev->max_mtu = bp->max_mtu;
 		bp->flags &= ~BNXT_FLAG_RX_PAGE_MODE;
 		bp->rx_dir = DMA_FROM_DEVICE;
 		bp->rx_skb_func = bnxt_rx_skb;
 	}
-	return 0;
+}
+
+void bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
+{
+	__bnxt_set_rx_skb_mode(bp, page_mode);
+
+	if (!page_mode) {
+		int rx, tx;
+
+		bnxt_get_max_rings(bp, &rx, &tx, true);
+		if (rx > 1) {
+			bp->flags &= ~BNXT_FLAG_NO_AGG_RINGS;
+			bp->dev->hw_features |= NETIF_F_LRO;
+		}
+	}
+
+	/* Update LRO and GRO_HW availability */
+	netdev_update_features(bp->dev);
 }
 
 static void bnxt_free_vnic_attributes(struct bnxt *bp)
@@ -5201,8 +5345,10 @@ static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool all)
 {
 	int i;
 
-	/* Under rtnl_lock and all our NAPIs have been disabled.  It's
-	 * safe to delete the hash table.
+	netdev_assert_locked_or_invisible(bp->dev);
+
+	/* Under netdev instance lock and all our NAPIs have been disabled.
+	 * It's safe to delete the hash table.
 	 */
 	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++) {
 		struct hlist_head *head;
@@ -5530,6 +5676,8 @@ int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size,
 	if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)
 		flags |= FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT |
 			 FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT;
+	if (bp->fw_cap & BNXT_FW_CAP_NPAR_1_2)
+		flags |= FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT;
 	req->flags = cpu_to_le32(flags);
 	req->ver_maj_8b = DRV_VER_MAJ;
 	req->ver_min_8b = DRV_VER_MIN;
@@ -5547,6 +5695,10 @@ int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size,
 			u16 cmd = bnxt_vf_req_snif[i];
 			unsigned int bit, idx;
 
+			if ((bp->fw_cap & BNXT_FW_CAP_LINK_ADMIN) &&
+			    cmd == HWRM_PORT_PHY_QCFG)
+				continue;
+
 			idx = cmd / 32;
 			bit = cmd % 32;
 			data[idx] |= 1 << bit;
@@ -6557,6 +6709,7 @@ static void bnxt_hwrm_update_rss_hash_cfg(struct bnxt *bp)
 
 static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
+	u16 hds_thresh = (u16)bp->dev->cfg_pending->hds_thresh;
 	struct hwrm_vnic_plcmodes_cfg_input *req;
 	int rc;
 
@@ -6566,16 +6719,14 @@ static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 
 	req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT);
 	req->enables = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID);
+	req->jumbo_thresh = cpu_to_le16(bp->rx_buf_use_size);
 
-	if (BNXT_RX_PAGE_MODE(bp)) {
-		req->jumbo_thresh = cpu_to_le16(bp->rx_buf_use_size);
-	} else {
+	if (!BNXT_RX_PAGE_MODE(bp) && (bp->flags & BNXT_FLAG_AGG_RINGS)) {
 		req->flags |= cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 |
 					  VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6);
 		req->enables |=
 			cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID);
-		req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh);
-		req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh);
+		req->hds_threshold = cpu_to_le16(hds_thresh);
 	}
 	req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
 	return hwrm_req_send(bp, req);
@@ -6698,7 +6849,7 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 	req->dflt_ring_grp = cpu_to_le16(bp->grp_info[grp_idx].fw_grp_id);
 	req->lb_rule = cpu_to_le16(0xffff);
 vnic_mru:
-	vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
+	vnic->mru = bp->dev->mtu + VLAN_ETH_HLEN;
 	req->mru = cpu_to_le16(vnic->mru);
 
 	req->vnic_id = cpu_to_le16(vnic->fw_vnic_id);
@@ -6835,6 +6986,8 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 			bp->rss_cap |= BNXT_RSS_CAP_ESP_V4_RSS_CAP;
 		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV6_CAP)
 			bp->rss_cap |= BNXT_RSS_CAP_ESP_V6_RSS_CAP;
+		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_IPV6_FLOW_LABEL_CAP)
+			bp->rss_cap |= BNXT_RSS_CAP_IPV6_FLOW_LABEL_RSS_CAP;
 		if (flags & VNIC_QCAPS_RESP_FLAGS_RE_FLUSH_CAP)
 			bp->fw_cap |= BNXT_FW_CAP_VNIC_RE_FLUSH;
 	}
@@ -6901,6 +7054,30 @@ static void bnxt_hwrm_ring_grp_free(struct bnxt *bp)
 	hwrm_req_drop(bp, req);
 }
 
+static void bnxt_set_rx_ring_params_p5(struct bnxt *bp, u32 ring_type,
+				       struct hwrm_ring_alloc_input *req,
+				       struct bnxt_ring_struct *ring)
+{
+	struct bnxt_ring_grp_info *grp_info = &bp->grp_info[ring->grp_idx];
+	u32 enables = RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID |
+		      RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID;
+
+	if (ring_type == HWRM_RING_ALLOC_AGG) {
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG;
+		req->rx_ring_id = cpu_to_le16(grp_info->rx_fw_ring_id);
+		req->rx_buf_size = cpu_to_le16(BNXT_RX_PAGE_SIZE);
+		enables |= RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID;
+	} else {
+		req->rx_buf_size = cpu_to_le16(bp->rx_buf_use_size);
+		if (NET_IP_ALIGN == 2)
+			req->flags =
+				cpu_to_le16(RING_ALLOC_REQ_FLAGS_RX_SOP_PAD);
+	}
+	req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
+	req->nq_ring_id = cpu_to_le16(grp_info->cp_fw_ring_id);
+	req->enables |= cpu_to_le32(enables);
+}
+
 static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 				    struct bnxt_ring_struct *ring,
 				    u32 ring_type, u32 map_index)
@@ -6952,37 +7129,13 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 		break;
 	}
 	case HWRM_RING_ALLOC_RX:
-		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX;
-		req->length = cpu_to_le32(bp->rx_ring_mask + 1);
-		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-			u16 flags = 0;
-
-			/* Association of rx ring with stats context */
-			grp_info = &bp->grp_info[ring->grp_idx];
-			req->rx_buf_size = cpu_to_le16(bp->rx_buf_use_size);
-			req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
-			req->enables |= cpu_to_le32(
-				RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID);
-			if (NET_IP_ALIGN == 2)
-				flags = RING_ALLOC_REQ_FLAGS_RX_SOP_PAD;
-			req->flags = cpu_to_le16(flags);
-		}
-		break;
 	case HWRM_RING_ALLOC_AGG:
-		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-			req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG;
-			/* Association of agg ring with rx ring */
-			grp_info = &bp->grp_info[ring->grp_idx];
-			req->rx_ring_id = cpu_to_le16(grp_info->rx_fw_ring_id);
-			req->rx_buf_size = cpu_to_le16(BNXT_RX_PAGE_SIZE);
-			req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
-			req->enables |= cpu_to_le32(
-				RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID |
-				RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID);
-		} else {
-			req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX;
-		}
-		req->length = cpu_to_le32(bp->rx_agg_ring_mask + 1);
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX;
+		req->length = (ring_type == HWRM_RING_ALLOC_RX) ?
+			      cpu_to_le32(bp->rx_ring_mask + 1) :
+			      cpu_to_le32(bp->rx_agg_ring_mask + 1);
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+			bnxt_set_rx_ring_params_p5(bp, ring_type, req, ring);
 		break;
 	case HWRM_RING_ALLOC_CMPL:
 		req->ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL;
@@ -7006,7 +7159,7 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 	default:
 		netdev_err(bp->dev, "hwrm alloc invalid ring type %d\n",
 			   ring_type);
-		return -1;
+		return -EINVAL;
 	}
 
 	resp = hwrm_req_hold(bp, req);
@@ -7163,6 +7316,39 @@ static int bnxt_hwrm_rx_agg_ring_alloc(struct bnxt *bp,
 	return 0;
 }
 
+static int bnxt_hwrm_cp_ring_alloc_p5(struct bnxt *bp,
+				      struct bnxt_cp_ring_info *cpr)
+{
+	const u32 type = HWRM_RING_ALLOC_CMPL;
+	struct bnxt_napi *bnapi = cpr->bnapi;
+	struct bnxt_ring_struct *ring;
+	u32 map_idx = bnapi->index;
+	int rc;
+
+	ring = &cpr->cp_ring_struct;
+	ring->handle = BNXT_SET_NQ_HDL(cpr);
+	rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx);
+	if (rc)
+		return rc;
+	bnxt_set_db(bp, &cpr->cp_db, type, map_idx, ring->fw_ring_id);
+	bnxt_db_cq(bp, &cpr->cp_db, cpr->cp_raw_cons);
+	return 0;
+}
+
+static int bnxt_hwrm_tx_ring_alloc(struct bnxt *bp,
+				   struct bnxt_tx_ring_info *txr, u32 tx_idx)
+{
+	struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
+	const u32 type = HWRM_RING_ALLOC_TX;
+	int rc;
+
+	rc = hwrm_ring_alloc_send_msg(bp, ring, type, tx_idx);
+	if (rc)
+		return rc;
+	bnxt_set_db(bp, &txr->tx_db, type, tx_idx, ring->fw_ring_id);
+	return 0;
+}
+
 static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 {
 	bool agg_rings = !!(bp->flags & BNXT_FLAG_AGG_RINGS);
@@ -7199,33 +7385,17 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		}
 	}
 
-	type = HWRM_RING_ALLOC_TX;
 	for (i = 0; i < bp->tx_nr_rings; i++) {
 		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
-		struct bnxt_ring_struct *ring;
-		u32 map_idx;
 
 		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-			struct bnxt_cp_ring_info *cpr2 = txr->tx_cpr;
-			struct bnxt_napi *bnapi = txr->bnapi;
-			u32 type2 = HWRM_RING_ALLOC_CMPL;
-
-			ring = &cpr2->cp_ring_struct;
-			ring->handle = BNXT_SET_NQ_HDL(cpr2);
-			map_idx = bnapi->index;
-			rc = hwrm_ring_alloc_send_msg(bp, ring, type2, map_idx);
+			rc = bnxt_hwrm_cp_ring_alloc_p5(bp, txr->tx_cpr);
 			if (rc)
 				goto err_out;
-			bnxt_set_db(bp, &cpr2->cp_db, type2, map_idx,
-				    ring->fw_ring_id);
-			bnxt_db_cq(bp, &cpr2->cp_db, cpr2->cp_raw_cons);
 		}
-		ring = &txr->tx_ring_struct;
-		map_idx = i;
-		rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx);
+		rc = bnxt_hwrm_tx_ring_alloc(bp, txr, i);
 		if (rc)
 			goto err_out;
-		bnxt_set_db(bp, &txr->tx_db, type, map_idx, ring->fw_ring_id);
 	}
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {
@@ -7238,20 +7408,9 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		if (!agg_rings)
 			bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-			struct bnxt_cp_ring_info *cpr2 = rxr->rx_cpr;
-			struct bnxt_napi *bnapi = rxr->bnapi;
-			u32 type2 = HWRM_RING_ALLOC_CMPL;
-			struct bnxt_ring_struct *ring;
-			u32 map_idx = bnapi->index;
-
-			ring = &cpr2->cp_ring_struct;
-			ring->handle = BNXT_SET_NQ_HDL(cpr2);
-			rc = hwrm_ring_alloc_send_msg(bp, ring, type2, map_idx);
+			rc = bnxt_hwrm_cp_ring_alloc_p5(bp, rxr->rx_cpr);
 			if (rc)
 				goto err_out;
-			bnxt_set_db(bp, &cpr2->cp_db, type2, map_idx,
-				    ring->fw_ring_id);
-			bnxt_db_cq(bp, &cpr2->cp_db, cpr2->cp_raw_cons);
 		}
 	}
 
@@ -7266,6 +7425,26 @@ err_out:
 	return rc;
 }
 
+static void bnxt_cancel_dim(struct bnxt *bp)
+{
+	int i;
+
+	/* DIM work is initialized in bnxt_enable_napi().  Proceed only
+	 * if NAPI is enabled.
+	 */
+	if (!bp->bnapi || test_bit(BNXT_STATE_NAPI_DISABLED, &bp->state))
+		return;
+
+	/* Make sure NAPI sees that the VNIC is disabled */
+	synchronize_net();
+	for (i = 0; i < bp->rx_nr_rings; i++) {
+		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
+		struct bnxt_napi *bnapi = rxr->bnapi;
+
+		cancel_work_sync(&bnapi->cp_ring.dim.work);
+	}
+}
+
 static int hwrm_ring_free_send_msg(struct bnxt *bp,
 				   struct bnxt_ring_struct *ring,
 				   u32 ring_type, int cmpl_ring_id)
@@ -7299,6 +7478,23 @@ exit:
 	return 0;
 }
 
+static void bnxt_hwrm_tx_ring_free(struct bnxt *bp,
+				   struct bnxt_tx_ring_info *txr,
+				   bool close_path)
+{
+	struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
+	u32 cmpl_ring_id;
+
+	if (ring->fw_ring_id == INVALID_HW_RING_ID)
+		return;
+
+	cmpl_ring_id = close_path ? bnxt_cp_ring_for_tx(bp, txr) :
+		       INVALID_HW_RING_ID;
+	hwrm_ring_free_send_msg(bp, ring, RING_FREE_REQ_RING_TYPE_TX,
+				cmpl_ring_id);
+	ring->fw_ring_id = INVALID_HW_RING_ID;
+}
+
 static void bnxt_hwrm_rx_ring_free(struct bnxt *bp,
 				   struct bnxt_rx_ring_info *rxr,
 				   bool close_path)
@@ -7343,6 +7539,33 @@ static void bnxt_hwrm_rx_agg_ring_free(struct bnxt *bp,
 	bp->grp_info[grp_idx].agg_fw_ring_id = INVALID_HW_RING_ID;
 }
 
+static void bnxt_hwrm_cp_ring_free(struct bnxt *bp,
+				   struct bnxt_cp_ring_info *cpr)
+{
+	struct bnxt_ring_struct *ring;
+
+	ring = &cpr->cp_ring_struct;
+	if (ring->fw_ring_id == INVALID_HW_RING_ID)
+		return;
+
+	hwrm_ring_free_send_msg(bp, ring, RING_FREE_REQ_RING_TYPE_L2_CMPL,
+				INVALID_HW_RING_ID);
+	ring->fw_ring_id = INVALID_HW_RING_ID;
+}
+
+static void bnxt_clear_one_cp_ring(struct bnxt *bp, struct bnxt_cp_ring_info *cpr)
+{
+	struct bnxt_ring_struct *ring = &cpr->cp_ring_struct;
+	int i, size = ring->ring_mem.page_size;
+
+	cpr->cp_raw_cons = 0;
+	cpr->toggle = 0;
+
+	for (i = 0; i < bp->cp_nr_pages; i++)
+		if (cpr->cp_desc_ring[i])
+			memset(cpr->cp_desc_ring[i], 0, size);
+}
+
 static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 {
 	u32 type;
@@ -7351,21 +7574,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 	if (!bp->bnapi)
 		return;
 
-	for (i = 0; i < bp->tx_nr_rings; i++) {
-		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
-		struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
-
-		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
-			u32 cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
-
-			hwrm_ring_free_send_msg(bp, ring,
-						RING_FREE_REQ_RING_TYPE_TX,
-						close_path ? cmpl_ring_id :
-						INVALID_HW_RING_ID);
-			ring->fw_ring_id = INVALID_HW_RING_ID;
-		}
-	}
+	for (i = 0; i < bp->tx_nr_rings; i++)
+		bnxt_hwrm_tx_ring_free(bp, &bp->tx_ring[i], close_path);
 
+	bnxt_cancel_dim(bp);
 	for (i = 0; i < bp->rx_nr_rings; i++) {
 		bnxt_hwrm_rx_ring_free(bp, &bp->rx_ring[i], close_path);
 		bnxt_hwrm_rx_agg_ring_free(bp, &bp->rx_ring[i], close_path);
@@ -7387,17 +7599,9 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_ring_struct *ring;
 		int j;
 
-		for (j = 0; j < cpr->cp_ring_count && cpr->cp_ring_arr; j++) {
-			struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[j];
+		for (j = 0; j < cpr->cp_ring_count && cpr->cp_ring_arr; j++)
+			bnxt_hwrm_cp_ring_free(bp, &cpr->cp_ring_arr[j]);
 
-			ring = &cpr2->cp_ring_struct;
-			if (ring->fw_ring_id == INVALID_HW_RING_ID)
-				continue;
-			hwrm_ring_free_send_msg(bp, ring,
-						RING_FREE_REQ_RING_TYPE_L2_CMPL,
-						INVALID_HW_RING_ID);
-			ring->fw_ring_id = INVALID_HW_RING_ID;
-		}
 		ring = &cpr->cp_ring_struct;
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
 			hwrm_ring_free_send_msg(bp, ring, type,
@@ -7831,7 +8035,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	}
 	rx_rings = min_t(int, rx_rings, hwr.grp);
 	hwr.cp = min_t(int, hwr.cp, bp->cp_nr_rings);
-	if (hwr.stat > bnxt_get_ulp_stat_ctxs(bp))
+	if (bnxt_ulp_registered(bp->edev) &&
+	    hwr.stat > bnxt_get_ulp_stat_ctxs(bp))
 		hwr.stat -= bnxt_get_ulp_stat_ctxs(bp);
 	hwr.cp = min_t(int, hwr.cp, hwr.stat);
 	rc = bnxt_trim_rings(bp, &rx_rings, &hwr.tx, hwr.cp, sh);
@@ -7839,6 +8044,11 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		hwr.rx = rx_rings << 1;
 	tx_cp = bnxt_num_tx_to_cp(bp, hwr.tx);
 	hwr.cp = sh ? max_t(int, tx_cp, rx_rings) : tx_cp + rx_rings;
+	if (hwr.tx != bp->tx_nr_rings) {
+		netdev_warn(bp->dev,
+			    "Able to reserve only %d out of %d requested TX rings\n",
+			    hwr.tx, bp->tx_nr_rings);
+	}
 	bp->tx_nr_rings = hwr.tx;
 
 	/* If we cannot reserve all the RX rings, reset the RSS map only
@@ -8307,9 +8517,15 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 
 	if (flags & FUNC_QCFG_RESP_FLAGS_ENABLE_RDMA_SRIOV)
 		bp->fw_cap |= BNXT_FW_CAP_ENABLE_RDMA_SRIOV;
+	if (resp->roce_bidi_opt_mode &
+	    FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_DEDICATED)
+		bp->cos0_cos1_shared = 1;
+	else
+		bp->cos0_cos1_shared = 0;
 
 	switch (resp->port_partition_type) {
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0:
+	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_2:
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5:
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0:
 		bp->port_partition_type = resp->port_partition_type;
@@ -8952,7 +9168,7 @@ static int bnxt_hwrm_func_backing_store_cfg_v2(struct bnxt *bp,
 	return rc;
 }
 
-static int bnxt_backing_store_cfg_v2(struct bnxt *bp, u32 ena)
+static int bnxt_backing_store_cfg_v2(struct bnxt *bp)
 {
 	struct bnxt_ctx_mem_info *ctx = bp->ctx;
 	struct bnxt_ctx_mem_type *ctxm;
@@ -8960,7 +9176,7 @@ static int bnxt_backing_store_cfg_v2(struct bnxt *bp, u32 ena)
 	int rc = 0;
 	u16 type;
 
-	for (type = BNXT_CTX_SRT; type <= BNXT_CTX_RIGP1; type++) {
+	for (type = BNXT_CTX_SRT; type <= BNXT_CTX_QPC; type++) {
 		ctxm = &ctx->ctx_arr[type];
 		if (!bnxt_bs_trace_avail(bp, type))
 			continue;
@@ -8978,12 +9194,13 @@ static int bnxt_backing_store_cfg_v2(struct bnxt *bp, u32 ena)
 	}
 
 	if (last_type == BNXT_CTX_INV) {
-		if (!ena)
+		for (type = 0; type < BNXT_CTX_MAX; type++) {
+			ctxm = &ctx->ctx_arr[type];
+			if (ctxm->mem_valid)
+				last_type = type;
+		}
+		if (last_type == BNXT_CTX_INV)
 			return 0;
-		else if (ena & FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM)
-			last_type = BNXT_CTX_MAX - 1;
-		else
-			last_type = BNXT_CTX_L2_MAX - 1;
 	}
 	ctx->ctx_arr[last_type].last = 1;
 
@@ -9110,6 +9327,10 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	if (!ctx || (ctx->flags & BNXT_CTX_FLAG_INITED))
 		return 0;
 
+	ena = 0;
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
+		goto skip_legacy;
+
 	ctxm = &ctx->ctx_arr[BNXT_CTX_QP];
 	l2_qps = ctxm->qp_l2_entries;
 	qp1_qps = ctxm->qp_qp1_entries;
@@ -9118,7 +9339,6 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	ctxm = &ctx->ctx_arr[BNXT_CTX_SRQ];
 	srqs = ctxm->srq_l2_entries;
 	max_srqs = ctxm->max_entries;
-	ena = 0;
 	if ((bp->flags & BNXT_FLAG_ROCE_CAP) && !is_kdump_kernel()) {
 		pg_lvl = 2;
 		if (BNXT_SW_RES_LMT(bp)) {
@@ -9212,8 +9432,9 @@ skip_rdma:
 		ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP << i;
 	ena |= FUNC_BACKING_STORE_CFG_REQ_DFLT_ENABLES;
 
+skip_legacy:
 	if (bp->fw_cap & BNXT_FW_CAP_BACKING_STORE_V2)
-		rc = bnxt_backing_store_cfg_v2(bp, ena);
+		rc = bnxt_backing_store_cfg_v2(bp);
 	else
 		rc = bnxt_hwrm_func_backing_store_cfg(bp, ena);
 	if (rc) {
@@ -9427,10 +9648,10 @@ no_ptp:
 
 static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 {
+	u32 flags, flags_ext, flags_ext2, flags_ext3;
+	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 	struct hwrm_func_qcaps_output *resp;
 	struct hwrm_func_qcaps_input *req;
-	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
-	u32 flags, flags_ext, flags_ext2;
 	int rc;
 
 	rc = hwrm_req_init(bp, req, HWRM_FUNC_QCAPS);
@@ -9448,6 +9669,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->flags |= BNXT_FLAG_ROCEV1_CAP;
 	if (flags & FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED)
 		bp->flags |= BNXT_FLAG_ROCEV2_CAP;
+	if (flags & FUNC_QCAPS_RESP_FLAGS_LINK_ADMIN_STATUS_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_LINK_ADMIN;
 	if (flags & FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED)
 		bp->fw_cap |= BNXT_FW_CAP_PCIE_STATS_SUPPORTED;
 	if (flags & FUNC_QCAPS_RESP_FLAGS_HOT_RESET_CAPABLE)
@@ -9474,6 +9697,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->fw_cap |= BNXT_FW_CAP_HOT_RESET_IF;
 	if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED))
 		bp->fw_cap |= BNXT_FW_CAP_LIVEPATCH;
+	if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_NPAR_1_2_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_NPAR_1_2;
 	if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_DFLT_VLAN_TPID_PCP_SUPPORTED))
 		bp->fw_cap |= BNXT_FW_CAP_DFLT_VLAN_TPID_PCP;
 	if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED)
@@ -9495,6 +9720,12 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 	    (flags_ext2 & FUNC_QCAPS_RESP_FLAGS_EXT2_ROCE_VF_RESOURCE_MGMT_SUPPORTED))
 		bp->fw_cap |= BNXT_FW_CAP_ROCE_VF_RESC_MGMT_SUPPORTED;
 
+	flags_ext3 = le32_to_cpu(resp->flags_ext3);
+	if (flags_ext3 & FUNC_QCAPS_RESP_FLAGS_EXT3_ROCE_VF_DYN_ALLOC_SUPPORT)
+		bp->fw_cap |= BNXT_FW_CAP_ROCE_VF_DYN_ALLOC_SUPPORT;
+	if (flags_ext3 & FUNC_QCAPS_RESP_FLAGS_EXT3_MIRROR_ON_ROCE_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_MIRROR_ON_ROCE;
+
 	bp->tx_push_thresh = 0;
 	if ((flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED) &&
 	    BNXT_FW_MAJ(bp) > 217)
@@ -9950,7 +10181,7 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	struct hwrm_ver_get_input *req;
 	u16 fw_maj, fw_min, fw_bld, fw_rsv;
 	u32 dev_caps_cfg, hwrm_ver;
-	int rc, len;
+	int rc, len, max_tmo_secs;
 
 	rc = hwrm_req_init(bp, req, HWRM_VER_GET);
 	if (rc)
@@ -10023,9 +10254,14 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	bp->hwrm_cmd_max_timeout = le16_to_cpu(resp->max_req_timeout) * 1000;
 	if (!bp->hwrm_cmd_max_timeout)
 		bp->hwrm_cmd_max_timeout = HWRM_CMD_MAX_TIMEOUT;
-	else if (bp->hwrm_cmd_max_timeout > HWRM_CMD_MAX_TIMEOUT)
-		netdev_warn(bp->dev, "Device requests max timeout of %d seconds, may trigger hung task watchdog\n",
-			    bp->hwrm_cmd_max_timeout / 1000);
+	max_tmo_secs = bp->hwrm_cmd_max_timeout / 1000;
+#ifdef CONFIG_DETECT_HUNG_TASK
+	if (bp->hwrm_cmd_max_timeout > HWRM_CMD_MAX_TIMEOUT ||
+	    max_tmo_secs > CONFIG_DEFAULT_HUNG_TASK_TIMEOUT) {
+		netdev_warn(bp->dev, "Device requests max timeout of %d seconds, may trigger hung task watchdog (kernel default %ds)\n",
+			    max_tmo_secs, CONFIG_DEFAULT_HUNG_TASK_TIMEOUT);
+	}
+#endif
 
 	if (resp->hwrm_intf_maj_8b >= 1) {
 		bp->hwrm_max_req_len = le16_to_cpu(resp->max_req_win_len);
@@ -10611,6 +10847,72 @@ void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
 	bp->num_rss_ctx--;
 }
 
+static bool bnxt_vnic_has_rx_ring(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				  int rxr_id)
+{
+	u16 tbl_size = bnxt_get_rxfh_indir_size(bp->dev);
+	int i, vnic_rx;
+
+	/* Ntuple VNIC always has all the rx rings. Any change of ring id
+	 * must be updated because a future filter may use it.
+	 */
+	if (vnic->flags & BNXT_VNIC_NTUPLE_FLAG)
+		return true;
+
+	for (i = 0; i < tbl_size; i++) {
+		if (vnic->flags & BNXT_VNIC_RSSCTX_FLAG)
+			vnic_rx = ethtool_rxfh_context_indir(vnic->rss_ctx)[i];
+		else
+			vnic_rx = bp->rss_indir_tbl[i];
+
+		if (rxr_id == vnic_rx)
+			return true;
+	}
+
+	return false;
+}
+
+static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				u16 mru, int rxr_id)
+{
+	int rc;
+
+	if (!bnxt_vnic_has_rx_ring(bp, vnic, rxr_id))
+		return 0;
+
+	if (mru) {
+		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
+		if (rc) {
+			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
+				   vnic->vnic_id, rc);
+			return rc;
+		}
+	}
+	vnic->mru = mru;
+	bnxt_hwrm_vnic_update(bp, vnic,
+			      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+
+	return 0;
+}
+
+static int bnxt_set_rss_ctx_vnic_mru(struct bnxt *bp, u16 mru, int rxr_id)
+{
+	struct ethtool_rxfh_context *ctx;
+	unsigned long context;
+	int rc;
+
+	xa_for_each(&bp->dev->ethtool->rss_ctx, context, ctx) {
+		struct bnxt_rss_ctx *rss_ctx = ethtool_rxfh_context_priv(ctx);
+		struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+
+		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, rxr_id);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
 static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp)
 {
 	bool set_tpa = !!(bp->flags & BNXT_FLAG_TPA);
@@ -11182,6 +11484,155 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 	return 0;
 }
 
+static void bnxt_tx_queue_stop(struct bnxt *bp, int idx)
+{
+	struct bnxt_tx_ring_info *txr;
+	struct netdev_queue *txq;
+	struct bnxt_napi *bnapi;
+	int i;
+
+	bnapi = bp->bnapi[idx];
+	bnxt_for_each_napi_tx(i, bnapi, txr) {
+		WRITE_ONCE(txr->dev_state, BNXT_DEV_STATE_CLOSING);
+		synchronize_net();
+
+		if (!(bnapi->flags & BNXT_NAPI_FLAG_XDP)) {
+			txq = netdev_get_tx_queue(bp->dev, txr->txq_index);
+			if (txq) {
+				__netif_tx_lock_bh(txq);
+				netif_tx_stop_queue(txq);
+				__netif_tx_unlock_bh(txq);
+			}
+		}
+
+		if (!bp->tph_mode)
+			continue;
+
+		bnxt_hwrm_tx_ring_free(bp, txr, true);
+		bnxt_hwrm_cp_ring_free(bp, txr->tx_cpr);
+		bnxt_free_one_tx_ring_skbs(bp, txr, txr->txq_index);
+		bnxt_clear_one_cp_ring(bp, txr->tx_cpr);
+	}
+}
+
+static int bnxt_tx_queue_start(struct bnxt *bp, int idx)
+{
+	struct bnxt_tx_ring_info *txr;
+	struct netdev_queue *txq;
+	struct bnxt_napi *bnapi;
+	int rc, i;
+
+	bnapi = bp->bnapi[idx];
+	/* All rings have been reserved and previously allocated.
+	 * Reallocating with the same parameters should never fail.
+	 */
+	bnxt_for_each_napi_tx(i, bnapi, txr) {
+		if (!bp->tph_mode)
+			goto start_tx;
+
+		rc = bnxt_hwrm_cp_ring_alloc_p5(bp, txr->tx_cpr);
+		if (rc)
+			return rc;
+
+		rc = bnxt_hwrm_tx_ring_alloc(bp, txr, false);
+		if (rc)
+			return rc;
+
+		txr->tx_prod = 0;
+		txr->tx_cons = 0;
+		txr->tx_hw_cons = 0;
+start_tx:
+		WRITE_ONCE(txr->dev_state, 0);
+		synchronize_net();
+
+		if (bnapi->flags & BNXT_NAPI_FLAG_XDP)
+			continue;
+
+		txq = netdev_get_tx_queue(bp->dev, txr->txq_index);
+		if (txq)
+			netif_tx_start_queue(txq);
+	}
+
+	return 0;
+}
+
+static void bnxt_irq_affinity_notify(struct irq_affinity_notify *notify,
+				     const cpumask_t *mask)
+{
+	struct bnxt_irq *irq;
+	u16 tag;
+	int err;
+
+	irq = container_of(notify, struct bnxt_irq, affinity_notify);
+
+	if (!irq->bp->tph_mode)
+		return;
+
+	cpumask_copy(irq->cpu_mask, mask);
+
+	if (irq->ring_nr >= irq->bp->rx_nr_rings)
+		return;
+
+	if (pcie_tph_get_cpu_st(irq->bp->pdev, TPH_MEM_TYPE_VM,
+				cpumask_first(irq->cpu_mask), &tag))
+		return;
+
+	if (pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, tag))
+		return;
+
+	netdev_lock(irq->bp->dev);
+	if (netif_running(irq->bp->dev)) {
+		err = netdev_rx_queue_restart(irq->bp->dev, irq->ring_nr);
+		if (err)
+			netdev_err(irq->bp->dev,
+				   "RX queue restart failed: err=%d\n", err);
+	}
+	netdev_unlock(irq->bp->dev);
+}
+
+static void bnxt_irq_affinity_release(struct kref *ref)
+{
+	struct irq_affinity_notify *notify =
+		container_of(ref, struct irq_affinity_notify, kref);
+	struct bnxt_irq *irq;
+
+	irq = container_of(notify, struct bnxt_irq, affinity_notify);
+
+	if (!irq->bp->tph_mode)
+		return;
+
+	if (pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, 0)) {
+		netdev_err(irq->bp->dev,
+			   "Setting ST=0 for MSIX entry %d failed\n",
+			   irq->msix_nr);
+		return;
+	}
+}
+
+static void bnxt_release_irq_notifier(struct bnxt_irq *irq)
+{
+	irq_set_affinity_notifier(irq->vector, NULL);
+}
+
+static void bnxt_register_irq_notifier(struct bnxt *bp, struct bnxt_irq *irq)
+{
+	struct irq_affinity_notify *notify;
+
+	irq->bp = bp;
+
+	/* Nothing to do if TPH is not enabled */
+	if (!bp->tph_mode)
+		return;
+
+	/* Register IRQ affinity notifier */
+	notify = &irq->affinity_notify;
+	notify->irq = irq->vector;
+	notify->notify = bnxt_irq_affinity_notify;
+	notify->release = bnxt_irq_affinity_release;
+
+	irq_set_affinity_notifier(irq->vector, notify);
+}
+
 static void bnxt_free_irq(struct bnxt *bp)
 {
 	struct bnxt_irq *irq;
@@ -11204,20 +11655,25 @@ static void bnxt_free_irq(struct bnxt *bp)
 				free_cpumask_var(irq->cpu_mask);
 				irq->have_cpumask = 0;
 			}
+
+			bnxt_release_irq_notifier(irq);
+
 			free_irq(irq->vector, bp->bnapi[i]);
 		}
 
 		irq->requested = 0;
 	}
+
+	/* Disable TPH support */
+	pcie_disable_tph(bp->pdev);
+	bp->tph_mode = 0;
 }
 
 static int bnxt_request_irq(struct bnxt *bp)
 {
+	struct cpu_rmap *rmap = NULL;
 	int i, j, rc = 0;
 	unsigned long flags = 0;
-#ifdef CONFIG_RFS_ACCEL
-	struct cpu_rmap *rmap;
-#endif
 
 	rc = bnxt_setup_int_mode(bp);
 	if (rc) {
@@ -11228,31 +11684,40 @@ static int bnxt_request_irq(struct bnxt *bp)
 #ifdef CONFIG_RFS_ACCEL
 	rmap = bp->dev->rx_cpu_rmap;
 #endif
+
+	/* Enable TPH support as part of IRQ request */
+	rc = pcie_enable_tph(bp->pdev, PCI_TPH_ST_IV_MODE);
+	if (!rc)
+		bp->tph_mode = PCI_TPH_ST_IV_MODE;
+
 	for (i = 0, j = 0; i < bp->cp_nr_rings; i++) {
 		int map_idx = bnxt_cp_num_to_irq_num(bp, i);
 		struct bnxt_irq *irq = &bp->irq_tbl[map_idx];
 
-#ifdef CONFIG_RFS_ACCEL
-		if (rmap && bp->bnapi[i]->rx_ring) {
+		if (IS_ENABLED(CONFIG_RFS_ACCEL) &&
+		    rmap && bp->bnapi[i]->rx_ring) {
 			rc = irq_cpu_rmap_add(rmap, irq->vector);
 			if (rc)
 				netdev_warn(bp->dev, "failed adding irq rmap for ring %d\n",
 					    j);
 			j++;
 		}
-#endif
+
 		rc = request_irq(irq->vector, irq->handler, flags, irq->name,
 				 bp->bnapi[i]);
 		if (rc)
 			break;
 
-		netif_napi_set_irq(&bp->bnapi[i]->napi, irq->vector);
+		netif_napi_set_irq_locked(&bp->bnapi[i]->napi, irq->vector);
 		irq->requested = 1;
 
 		if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) {
 			int numa_node = dev_to_node(&bp->pdev->dev);
+			u16 tag;
 
 			irq->have_cpumask = 1;
+			irq->msix_nr = map_idx;
+			irq->ring_nr = i;
 			cpumask_set_cpu(cpumask_local_spread(i, numa_node),
 					irq->cpu_mask);
 			rc = irq_update_affinity_hint(irq->vector, irq->cpu_mask);
@@ -11262,6 +11727,16 @@ static int bnxt_request_irq(struct bnxt *bp)
 					    irq->vector);
 				break;
 			}
+
+			bnxt_register_irq_notifier(bp, irq);
+
+			/* Init ST table entry */
+			if (pcie_tph_get_cpu_st(irq->bp->pdev, TPH_MEM_TYPE_VM,
+						cpumask_first(irq->cpu_mask),
+						&tag))
+				continue;
+
+			pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, tag);
 		}
 	}
 	return rc;
@@ -11282,9 +11757,9 @@ static void bnxt_del_napi(struct bnxt *bp)
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 
-		__netif_napi_del(&bnapi->napi);
+		__netif_napi_del_locked(&bnapi->napi);
 	}
-	/* We called __netif_napi_del(), we need
+	/* We called __netif_napi_del_locked(), we need
 	 * to respect an RCU grace period before freeing napi structures.
 	 */
 	synchronize_net();
@@ -11301,14 +11776,17 @@ static void bnxt_init_napi(struct bnxt *bp)
 		poll_fn = bnxt_poll_p5;
 	else if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 		cp_nr_rings--;
+
+	set_bit(BNXT_STATE_NAPI_DISABLED, &bp->state);
+
 	for (i = 0; i < cp_nr_rings; i++) {
 		bnapi = bp->bnapi[i];
-		netif_napi_add_config(bp->dev, &bnapi->napi, poll_fn,
-				      bnapi->index);
+		netif_napi_add_config_locked(bp->dev, &bnapi->napi, poll_fn,
+					     bnapi->index);
 	}
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
 		bnapi = bp->bnapi[cp_nr_rings];
-		netif_napi_add(bp->dev, &bnapi->napi, bnxt_poll_nitroa0);
+		netif_napi_add_locked(bp->dev, &bnapi->napi, bnxt_poll_nitroa0);
 	}
 }
 
@@ -11329,9 +11807,7 @@ static void bnxt_disable_napi(struct bnxt *bp)
 			cpr->sw_stats->tx.tx_resets++;
 		if (bnapi->in_reset)
 			cpr->sw_stats->rx.rx_resets++;
-		napi_disable(&bnapi->napi);
-		if (bnapi->rx_ring)
-			cancel_work_sync(&cpr->dim.work);
+		napi_disable_locked(&bnapi->napi);
 	}
 }
 
@@ -11353,7 +11829,7 @@ static void bnxt_enable_napi(struct bnxt *bp)
 			INIT_WORK(&cpr->dim.work, bnxt_dim_work);
 			cpr->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 		}
-		napi_enable(&bnapi->napi);
+		napi_enable_locked(&bnapi->napi);
 	}
 }
 
@@ -11981,7 +12457,7 @@ static int bnxt_try_recover_fw(struct bnxt *bp)
 	return -ENODEV;
 }
 
-static void bnxt_clear_reservations(struct bnxt *bp, bool fw_reset)
+void bnxt_clear_reservations(struct bnxt *bp, bool fw_reset)
 {
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 
@@ -12022,11 +12498,15 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 {
 	struct hwrm_func_drv_if_change_output *resp;
 	struct hwrm_func_drv_if_change_input *req;
-	bool fw_reset = !bp->irq_tbl;
 	bool resc_reinit = false;
+	bool caps_change = false;
 	int rc, retry = 0;
+	bool fw_reset;
 	u32 flags = 0;
 
+	fw_reset = (bp->fw_reset_state == BNXT_FW_RESET_STATE_ABORT);
+	bp->fw_reset_state = 0;
+
 	if (!(bp->fw_cap & BNXT_FW_CAP_IF_CHANGE))
 		return 0;
 
@@ -12079,8 +12559,11 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 		set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
 		return -ENODEV;
 	}
-	if (resc_reinit || fw_reset) {
-		if (fw_reset) {
+	if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_CAPS_CHANGE)
+		caps_change = true;
+
+	if (resc_reinit || fw_reset || caps_change) {
+		if (fw_reset || caps_change) {
 			set_bit(BNXT_STATE_FW_RESET_DET, &bp->state);
 			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 				bnxt_ulp_irq_stop(bp);
@@ -12092,13 +12575,8 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 				set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
 				return rc;
 			}
+			/* IRQ will be initialized later in bnxt_request_irq()*/
 			bnxt_clear_int_mode(bp);
-			rc = bnxt_init_int_mode(bp);
-			if (rc) {
-				clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state);
-				netdev_err(bp->dev, "init int mode failed\n");
-				return rc;
-			}
 		}
 		rc = bnxt_cancel_reservations(bp, fw_reset);
 	}
@@ -12416,6 +12894,17 @@ static int bnxt_set_xps_mapping(struct bnxt *bp)
 	return rc;
 }
 
+static int bnxt_tx_nr_rings(struct bnxt *bp)
+{
+	return bp->num_tc ? bp->tx_nr_rings_per_tc * bp->num_tc :
+			    bp->tx_nr_rings_per_tc;
+}
+
+static int bnxt_tx_nr_rings_per_tc(struct bnxt *bp)
+{
+	return bp->num_tc ? bp->tx_nr_rings / bp->num_tc : bp->tx_nr_rings;
+}
+
 static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
 	int rc = 0;
@@ -12433,6 +12922,13 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	if (rc)
 		return rc;
 
+	/* Make adjustments if reserved TX rings are less than requested */
+	bp->tx_nr_rings -= bp->tx_nr_rings_xdp;
+	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
+	if (bp->tx_nr_rings_xdp) {
+		bp->tx_nr_rings_xdp = bp->tx_nr_rings_per_tc;
+		bp->tx_nr_rings += bp->tx_nr_rings_xdp;
+	}
 	rc = bnxt_alloc_mem(bp, irq_re_init);
 	if (rc) {
 		netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
@@ -12497,8 +12993,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	/* VF-reps may need to be re-opened after the PF is re-opened */
 	if (BNXT_PF(bp))
 		bnxt_vf_reps_open(bp);
-	if (bp->ptp_cfg && !(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
-		WRITE_ONCE(bp->ptp_cfg->tx_avail, BNXT_MAX_TX_TS);
 	bnxt_ptp_init_rtc(bp, true);
 	bnxt_ptp_cfg_tstamp_filters(bp);
 	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
@@ -12516,7 +13010,6 @@ open_err_free_mem:
 	return rc;
 }
 
-/* rtnl_lock held */
 int bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
 	int rc = 0;
@@ -12527,14 +13020,14 @@ int bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		rc = __bnxt_open_nic(bp, irq_re_init, link_re_init);
 	if (rc) {
 		netdev_err(bp->dev, "nic open fail (rc: %x)\n", rc);
-		dev_close(bp->dev);
+		netif_close(bp->dev);
 	}
 	return rc;
 }
 
-/* rtnl_lock held, open the NIC half way by allocating all resources, but
- * NAPI, IRQ, and TX are not enabled.  This is mainly used for offline
- * self tests.
+/* netdev instance lock held, open the NIC half way by allocating all
+ * resources, but NAPI, IRQ, and TX are not enabled.  This is mainly used
+ * for offline self tests.
  */
 int bnxt_half_open_nic(struct bnxt *bp)
 {
@@ -12565,12 +13058,12 @@ int bnxt_half_open_nic(struct bnxt *bp)
 half_open_err:
 	bnxt_free_skbs(bp);
 	bnxt_free_mem(bp, true);
-	dev_close(bp->dev);
+	netif_close(bp->dev);
 	return rc;
 }
 
-/* rtnl_lock held, this call can only be made after a previous successful
- * call to bnxt_half_open_nic().
+/* netdev instance lock held, this call can only be made after a previous
+ * successful call to bnxt_half_open_nic().
  */
 void bnxt_half_close_nic(struct bnxt *bp)
 {
@@ -12659,7 +13152,7 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 
 	bnxt_debug_dev_exit(bp);
 	bnxt_disable_napi(bp);
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 	bnxt_free_skbs(bp);
 
 	/* Save ring stats before shutdown */
@@ -12679,10 +13172,11 @@ void bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		/* If we get here, it means firmware reset is in progress
 		 * while we are trying to close.  We can safely proceed with
-		 * the close because we are holding rtnl_lock().  Some firmware
-		 * messages may fail as we proceed to close.  We set the
-		 * ABORT_ERR flag here so that the FW reset thread will later
-		 * abort when it gets the rtnl_lock() and sees the flag.
+		 * the close because we are holding netdev instance lock.
+		 * Some firmware messages may fail as we proceed to close.
+		 * We set the ABORT_ERR flag here so that the FW reset thread
+		 * will later abort when it gets the netdev instance lock
+		 * and sees the flag.
 		 */
 		netdev_warn(bp->dev, "FW reset in progress during close, FW reset will be aborted\n");
 		set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
@@ -12773,7 +13267,7 @@ static int bnxt_hwrm_port_phy_write(struct bnxt *bp, u16 phy_addr, u16 reg,
 	return hwrm_req_send(bp, req);
 }
 
-/* rtnl_lock held */
+/* netdev instance lock held */
 static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct mii_ioctl_data *mdio = if_mii(ifr);
@@ -12804,12 +13298,6 @@ static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		return bnxt_hwrm_port_phy_write(bp, mdio->phy_id, mdio->reg_num,
 						mdio->val_in);
 
-	case SIOCSHWTSTAMP:
-		return bnxt_hwtstamp_set(dev, ifr);
-
-	case SIOCGHWTSTAMP:
-		return bnxt_hwtstamp_get(dev, ifr);
-
 	default:
 		/* do nothing */
 		break;
@@ -13550,11 +14038,19 @@ static void bnxt_dump_rx_sw_state(struct bnxt_napi *bnapi)
 
 static void bnxt_dump_cp_sw_state(struct bnxt_napi *bnapi)
 {
-	struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
-	int i = bnapi->index;
+	struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring, *cpr2;
+	int i = bnapi->index, j;
 
 	netdev_info(bnapi->bp->dev, "[%d]: cp{fw_ring: %d raw_cons: %x}\n",
 		    i, cpr->cp_ring_struct.fw_ring_id, cpr->cp_raw_cons);
+	for (j = 0; j < cpr->cp_ring_count; j++) {
+		cpr2 = &cpr->cp_ring_arr[j];
+		if (!cpr2->bnapi)
+			continue;
+		netdev_info(bnapi->bp->dev, "[%d.%d]: cp{fw_ring: %d raw_cons: %x}\n",
+			    i, j, cpr2->cp_ring_struct.fw_ring_id,
+			    cpr2->cp_raw_cons);
+	}
 }
 
 static void bnxt_dbg_dump_states(struct bnxt *bp)
@@ -13650,7 +14146,7 @@ fw_reset:
 
 static void bnxt_timer(struct timer_list *t)
 {
-	struct bnxt *bp = from_timer(bp, t, timer);
+	struct bnxt *bp = timer_container_of(bp, t, timer);
 	struct net_device *dev = bp->dev;
 
 	if (!netif_running(dev) || !test_bit(BNXT_STATE_OPEN, &bp->state))
@@ -13692,30 +14188,31 @@ bnxt_restart_timer:
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 }
 
-static void bnxt_rtnl_lock_sp(struct bnxt *bp)
+static void bnxt_lock_sp(struct bnxt *bp)
 {
 	/* We are called from bnxt_sp_task which has BNXT_STATE_IN_SP_TASK
 	 * set.  If the device is being closed, bnxt_close() may be holding
-	 * rtnl() and waiting for BNXT_STATE_IN_SP_TASK to clear.  So we
-	 * must clear BNXT_STATE_IN_SP_TASK before holding rtnl().
+	 * netdev instance lock and waiting for BNXT_STATE_IN_SP_TASK to clear.
+	 * So we must clear BNXT_STATE_IN_SP_TASK before holding netdev
+	 * instance lock.
 	 */
 	clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
-	rtnl_lock();
+	netdev_lock(bp->dev);
 }
 
-static void bnxt_rtnl_unlock_sp(struct bnxt *bp)
+static void bnxt_unlock_sp(struct bnxt *bp)
 {
 	set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
-	rtnl_unlock();
+	netdev_unlock(bp->dev);
 }
 
 /* Only called from bnxt_sp_task() */
 static void bnxt_reset(struct bnxt *bp, bool silent)
 {
-	bnxt_rtnl_lock_sp(bp);
+	bnxt_lock_sp(bp);
 	if (test_bit(BNXT_STATE_OPEN, &bp->state))
 		bnxt_reset_task(bp, silent);
-	bnxt_rtnl_unlock_sp(bp);
+	bnxt_unlock_sp(bp);
 }
 
 /* Only called from bnxt_sp_task() */
@@ -13723,9 +14220,9 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
 {
 	int i;
 
-	bnxt_rtnl_lock_sp(bp);
+	bnxt_lock_sp(bp);
 	if (!test_bit(BNXT_STATE_OPEN, &bp->state)) {
-		bnxt_rtnl_unlock_sp(bp);
+		bnxt_unlock_sp(bp);
 		return;
 	}
 	/* Disable and flush TPA before resetting the RX ring */
@@ -13764,7 +14261,7 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
 	}
 	if (bp->flags & BNXT_FLAG_TPA)
 		bnxt_set_tpa(bp, true);
-	bnxt_rtnl_unlock_sp(bp);
+	bnxt_unlock_sp(bp);
 }
 
 static void bnxt_fw_fatal_close(struct bnxt *bp)
@@ -13820,7 +14317,7 @@ static bool is_bnxt_fw_ok(struct bnxt *bp)
 	return false;
 }
 
-/* rtnl_lock is acquired before calling this function */
+/* netdev instance lock is acquired before calling this function */
 static void bnxt_force_fw_reset(struct bnxt *bp)
 {
 	struct bnxt_fw_health *fw_health = bp->fw_health;
@@ -13863,9 +14360,9 @@ void bnxt_fw_exception(struct bnxt *bp)
 	netdev_warn(bp->dev, "Detected firmware fatal condition, initiating reset\n");
 	set_bit(BNXT_STATE_FW_FATAL_COND, &bp->state);
 	bnxt_ulp_stop(bp);
-	bnxt_rtnl_lock_sp(bp);
+	bnxt_lock_sp(bp);
 	bnxt_force_fw_reset(bp);
-	bnxt_rtnl_unlock_sp(bp);
+	bnxt_unlock_sp(bp);
 }
 
 /* Returns the number of registered VFs, or 1 if VF configuration is pending, or
@@ -13895,7 +14392,7 @@ static int bnxt_get_registered_vfs(struct bnxt *bp)
 void bnxt_fw_reset(struct bnxt *bp)
 {
 	bnxt_ulp_stop(bp);
-	bnxt_rtnl_lock_sp(bp);
+	bnxt_lock_sp(bp);
 	if (test_bit(BNXT_STATE_OPEN, &bp->state) &&
 	    !test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
@@ -13918,7 +14415,7 @@ void bnxt_fw_reset(struct bnxt *bp)
 			netdev_err(bp->dev, "Firmware reset aborted, rc = %d\n",
 				   n);
 			clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-			dev_close(bp->dev);
+			netif_close(bp->dev);
 			goto fw_reset_exit;
 		} else if (n > 0) {
 			u16 vf_tmo_dsecs = n * 10;
@@ -13941,7 +14438,7 @@ void bnxt_fw_reset(struct bnxt *bp)
 		bnxt_queue_fw_reset_work(bp, tmo);
 	}
 fw_reset_exit:
-	bnxt_rtnl_unlock_sp(bp);
+	bnxt_unlock_sp(bp);
 }
 
 static void bnxt_chk_missed_irq(struct bnxt *bp)
@@ -14140,7 +14637,7 @@ static void bnxt_sp_task(struct work_struct *work)
 static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 				int *max_cp);
 
-/* Under rtnl_lock */
+/* Under netdev instance lock */
 int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 		     int tx_xdp)
 {
@@ -14273,6 +14770,23 @@ static bool bnxt_fw_pre_resv_vnics(struct bnxt *bp)
 	return false;
 }
 
+static void bnxt_hwrm_pfcwd_qcaps(struct bnxt *bp)
+{
+	struct hwrm_queue_pfcwd_timeout_qcaps_output *resp;
+	struct hwrm_queue_pfcwd_timeout_qcaps_input *req;
+	int rc;
+
+	bp->max_pfcwd_tmo_ms = 0;
+	rc = hwrm_req_init(bp, req, HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS);
+	if (rc)
+		return;
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send_silent(bp, req);
+	if (!rc)
+		bp->max_pfcwd_tmo_ms = le16_to_cpu(resp->max_pfcwd_timeout);
+	hwrm_req_drop(bp, req);
+}
+
 static int bnxt_fw_init_one_p1(struct bnxt *bp)
 {
 	int rc;
@@ -14350,6 +14864,7 @@ static int bnxt_fw_init_one_p2(struct bnxt *bp)
 	if (bnxt_fw_pre_resv_vnics(bp))
 		bp->fw_cap |= BNXT_FW_CAP_PRE_RESV_VNICS;
 
+	bnxt_hwrm_pfcwd_qcaps(bp);
 	bnxt_hwrm_func_qcfg(bp);
 	bnxt_hwrm_vnic_qcaps(bp);
 	bnxt_hwrm_port_led_qcaps(bp);
@@ -14532,8 +15047,8 @@ static void bnxt_fw_reset_abort(struct bnxt *bp, int rc)
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF)
 		bnxt_dl_health_fw_status_update(bp, false);
-	bp->fw_reset_state = 0;
-	dev_close(bp->dev);
+	bp->fw_reset_state = BNXT_FW_RESET_STATE_ABORT;
+	netif_close(bp->dev);
 }
 
 static void bnxt_fw_reset_task(struct work_struct *work)
@@ -14568,10 +15083,10 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			return;
 		}
 		bp->fw_reset_timestamp = jiffies;
-		rtnl_lock();
+		netdev_lock(bp->dev);
 		if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) {
 			bnxt_fw_reset_abort(bp, rc);
-			rtnl_unlock();
+			netdev_unlock(bp->dev);
 			goto ulp_start;
 		}
 		bnxt_fw_reset_close(bp);
@@ -14582,7 +15097,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV;
 			tmo = bp->fw_reset_min_dsecs * HZ / 10;
 		}
-		rtnl_unlock();
+		netdev_unlock(bp->dev);
 		bnxt_queue_fw_reset_work(bp, tmo);
 		return;
 	}
@@ -14656,7 +15171,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		bp->fw_reset_state = BNXT_FW_RESET_STATE_OPENING;
 		fallthrough;
 	case BNXT_FW_RESET_STATE_OPENING:
-		while (!rtnl_trylock()) {
+		while (!netdev_trylock(bp->dev)) {
 			bnxt_queue_fw_reset_work(bp, HZ / 10);
 			return;
 		}
@@ -14664,7 +15179,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		if (rc) {
 			netdev_err(bp->dev, "bnxt_open() failed during FW reset\n");
 			bnxt_fw_reset_abort(bp, rc);
-			rtnl_unlock();
+			netdev_unlock(bp->dev);
 			goto ulp_start;
 		}
 
@@ -14683,13 +15198,13 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			bnxt_dl_health_fw_recovery_done(bp);
 			bnxt_dl_health_fw_status_update(bp, true);
 		}
-		rtnl_unlock();
+		netdev_unlock(bp->dev);
 		bnxt_ulp_start(bp, 0);
 		bnxt_reenable_sriov(bp);
-		rtnl_lock();
+		netdev_lock(bp->dev);
 		bnxt_vf_reps_alloc(bp);
 		bnxt_vf_reps_open(bp);
-		rtnl_unlock();
+		netdev_unlock(bp->dev);
 		break;
 	}
 	return;
@@ -14702,9 +15217,9 @@ fw_reset_abort_status:
 		netdev_err(bp->dev, "fw_health_status 0x%x\n", sts);
 	}
 fw_reset_abort:
-	rtnl_lock();
+	netdev_lock(bp->dev);
 	bnxt_fw_reset_abort(bp, rc);
-	rtnl_unlock();
+	netdev_unlock(bp->dev);
 ulp_start:
 	bnxt_ulp_start(bp, rc);
 }
@@ -14796,13 +15311,14 @@ init_err:
 	return rc;
 }
 
-/* rtnl_lock held */
 static int bnxt_change_mac_addr(struct net_device *dev, void *p)
 {
 	struct sockaddr *addr = p;
 	struct bnxt *bp = netdev_priv(dev);
 	int rc = 0;
 
+	netdev_assert_locked(dev);
+
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
@@ -14823,11 +15339,12 @@ static int bnxt_change_mac_addr(struct net_device *dev, void *p)
 	return rc;
 }
 
-/* rtnl_lock held */
 static int bnxt_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
+	netdev_assert_locked(dev);
+
 	if (netif_running(dev))
 		bnxt_close_nic(bp, true, false);
 
@@ -15207,8 +15724,7 @@ static int bnxt_udp_tunnel_unset_port(struct net_device *netdev, unsigned int ta
 static const struct udp_tunnel_nic_info bnxt_udp_tunnels = {
 	.set_port	= bnxt_udp_tunnel_set_port,
 	.unset_port	= bnxt_udp_tunnel_unset_port,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-			  UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.flags		= UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
@@ -15216,8 +15732,7 @@ static const struct udp_tunnel_nic_info bnxt_udp_tunnels = {
 }, bnxt_udp_tunnels_p7 = {
 	.set_port	= bnxt_udp_tunnel_set_port,
 	.unset_port	= bnxt_udp_tunnel_unset_port,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-			  UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.flags		= UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
@@ -15313,6 +15828,8 @@ static const struct net_device_ops bnxt_netdev_ops = {
 	.ndo_xdp_xmit		= bnxt_xdp_xmit,
 	.ndo_bridge_getlink	= bnxt_bridge_getlink,
 	.ndo_bridge_setlink	= bnxt_bridge_setlink,
+	.ndo_hwtstamp_get	= bnxt_hwtstamp_get,
+	.ndo_hwtstamp_set	= bnxt_hwtstamp_set,
 };
 
 static void bnxt_get_queue_stats_rx(struct net_device *dev, int i,
@@ -15322,6 +15839,9 @@ static void bnxt_get_queue_stats_rx(struct net_device *dev, int i,
 	struct bnxt_cp_ring_info *cpr;
 	u64 *sw;
 
+	if (!bp->bnapi)
+		return;
+
 	cpr = &bp->bnapi[i]->cp_ring;
 	sw = cpr->stats.sw_stats;
 
@@ -15345,6 +15865,9 @@ static void bnxt_get_queue_stats_tx(struct net_device *dev, int i,
 	struct bnxt_napi *bnapi;
 	u64 *sw;
 
+	if (!bp->tx_ring)
+		return;
+
 	bnapi = bp->tx_ring[bp->tx_ring_map[i]].bnapi;
 	sw = bnapi->cp_ring.stats.sw_stats;
 
@@ -15386,6 +15909,9 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 	struct bnxt_ring_struct *ring;
 	int rc;
 
+	if (!bp->rx_ring)
+		return -ENETDOWN;
+
 	rxr = &bp->rx_ring[idx];
 	clone = qmem;
 	memcpy(clone, rxr, sizeof(*rxr));
@@ -15396,6 +15922,7 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 	clone->rx_agg_prod = 0;
 	clone->rx_sw_agg_prod = 0;
 	clone->rx_next_cons = 0;
+	clone->need_head_pool = false;
 
 	rc = bnxt_alloc_rx_page_pool(bp, clone, rxr->page_pool->p.nid);
 	if (rc)
@@ -15438,7 +15965,7 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 
 	bnxt_alloc_one_rx_ring_skb(bp, clone, idx);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
-		bnxt_alloc_one_rx_ring_page(bp, clone, idx);
+		bnxt_alloc_one_rx_ring_netmem(bp, clone, idx);
 	if (bp->flags & BNXT_FLAG_TPA)
 		bnxt_alloc_one_tpa_info_data(bp, clone);
 
@@ -15454,8 +15981,7 @@ err_rxq_info_unreg:
 	xdp_rxq_info_unreg(&clone->xdp_rxq);
 err_page_pool_destroy:
 	page_pool_destroy(clone->page_pool);
-	if (bnxt_separate_head_pool())
-		page_pool_destroy(clone->head_pool);
+	page_pool_destroy(clone->head_pool);
 	clone->page_pool = NULL;
 	clone->head_pool = NULL;
 	return rc;
@@ -15468,12 +15994,12 @@ static void bnxt_queue_mem_free(struct net_device *dev, void *qmem)
 	struct bnxt_ring_struct *ring;
 
 	bnxt_free_one_rx_ring_skbs(bp, rxr);
+	bnxt_free_one_tpa_info(bp, rxr);
 
 	xdp_rxq_info_unreg(&rxr->xdp_rxq);
 
 	page_pool_destroy(rxr->page_pool);
-	if (bnxt_separate_head_pool())
-		page_pool_destroy(rxr->head_pool);
+	page_pool_destroy(rxr->head_pool);
 	rxr->page_pool = NULL;
 	rxr->head_pool = NULL;
 
@@ -15548,7 +16074,9 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	struct bnxt_rx_ring_info *rxr, *clone;
 	struct bnxt_cp_ring_info *cpr;
 	struct bnxt_vnic_info *vnic;
+	struct bnxt_napi *bnapi;
 	int i, rc;
+	u16 mru;
 
 	rxr = &bp->rx_ring[idx];
 	clone = qmem;
@@ -15562,41 +16090,60 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	rxr->page_pool = clone->page_pool;
 	rxr->head_pool = clone->head_pool;
 	rxr->xdp_rxq = clone->xdp_rxq;
+	rxr->need_head_pool = clone->need_head_pool;
 
 	bnxt_copy_rx_ring(bp, rxr, clone);
 
+	bnapi = rxr->bnapi;
+	cpr = &bnapi->cp_ring;
+
+	/* All rings have been reserved and previously allocated.
+	 * Reallocating with the same parameters should never fail.
+	 */
 	rc = bnxt_hwrm_rx_ring_alloc(bp, rxr);
 	if (rc)
-		return rc;
+		goto err_reset;
+
+	if (bp->tph_mode) {
+		rc = bnxt_hwrm_cp_ring_alloc_p5(bp, rxr->rx_cpr);
+		if (rc)
+			goto err_reset;
+	}
+
 	rc = bnxt_hwrm_rx_agg_ring_alloc(bp, rxr);
 	if (rc)
-		goto err_free_hwrm_rx_ring;
+		goto err_reset;
 
 	bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
 
-	cpr = &rxr->bnapi->cp_ring;
-	cpr->sw_stats->rx.rx_resets++;
+	if (bp->flags & BNXT_FLAG_SHARED_RINGS) {
+		rc = bnxt_tx_queue_start(bp, idx);
+		if (rc)
+			goto err_reset;
+	}
+
+	bnxt_enable_rx_page_pool(rxr);
+	napi_enable_locked(&bnapi->napi);
+	bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
 
-	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
+	mru = bp->dev->mtu + VLAN_ETH_HLEN;
+	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
 
-		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
-		if (rc) {
-			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
-				   vnic->vnic_id, rc);
+		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, idx);
+		if (rc)
 			return rc;
-		}
-		vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
-		bnxt_hwrm_vnic_update(bp, vnic,
-				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
 	}
+	return bnxt_set_rss_ctx_vnic_mru(bp, mru, idx);
 
-	return 0;
-
-err_free_hwrm_rx_ring:
-	bnxt_hwrm_rx_ring_free(bp, rxr, false);
+err_reset:
+	netdev_err(bp->dev, "Unexpected HWRM error during queue start rc: %d\n",
+		   rc);
+	napi_enable_locked(&bnapi->napi);
+	bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
+	bnxt_reset_task(bp, true);
 	return rc;
 }
 
@@ -15604,24 +16151,44 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_rx_ring_info *rxr;
+	struct bnxt_cp_ring_info *cpr;
 	struct bnxt_vnic_info *vnic;
+	struct bnxt_napi *bnapi;
 	int i;
 
-	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
+	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
-		vnic->mru = 0;
-		bnxt_hwrm_vnic_update(bp, vnic,
-				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
-	}
 
+		bnxt_set_vnic_mru_p5(bp, vnic, 0, idx);
+	}
+	bnxt_set_rss_ctx_vnic_mru(bp, 0, idx);
+	/* Make sure NAPI sees that the VNIC is disabled */
+	synchronize_net();
 	rxr = &bp->rx_ring[idx];
+	bnapi = rxr->bnapi;
+	cpr = &bnapi->cp_ring;
+	cancel_work_sync(&cpr->dim.work);
 	bnxt_hwrm_rx_ring_free(bp, rxr, false);
 	bnxt_hwrm_rx_agg_ring_free(bp, rxr, false);
-	rxr->rx_next_cons = 0;
 	page_pool_disable_direct_recycling(rxr->page_pool);
-	if (bnxt_separate_head_pool())
+	if (bnxt_separate_head_pool(rxr))
 		page_pool_disable_direct_recycling(rxr->head_pool);
 
+	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
+		bnxt_tx_queue_stop(bp, idx);
+
+	/* Disable NAPI now after freeing the rings because HWRM_RING_FREE
+	 * completion is handled in NAPI to guarantee no more DMA on that ring
+	 * after seeing the completion.
+	 */
+	napi_disable_locked(&bnapi->napi);
+
+	if (bp->tph_mode) {
+		bnxt_hwrm_cp_ring_free(bp, rxr->rx_cpr);
+		bnxt_clear_one_cp_ring(bp, rxr->rx_cpr);
+	}
+	bnxt_db_nq(bp, &cpr->cp_db, cpr->cp_raw_cons);
+
 	memcpy(qmem, rxr, sizeof(*rxr));
 	bnxt_init_rx_ring_struct(bp, qmem);
 
@@ -15642,12 +16209,12 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	struct bnxt *bp = netdev_priv(dev);
 
 	if (BNXT_PF(bp))
-		bnxt_sriov_disable(bp);
+		__bnxt_sriov_disable(bp);
 
 	bnxt_rdma_aux_device_del(bp);
 
-	bnxt_ptp_clear(bp);
 	unregister_netdev(dev);
+	bnxt_ptp_clear(bp);
 
 	bnxt_rdma_aux_device_uninit(bp);
 
@@ -15839,7 +16406,7 @@ static void bnxt_trim_dflt_sh_rings(struct bnxt *bp)
 	bp->cp_nr_rings = min_t(int, bp->tx_nr_rings_per_tc, bp->rx_nr_rings);
 	bp->rx_nr_rings = bp->cp_nr_rings;
 	bp->tx_nr_rings_per_tc = bp->cp_nr_rings;
-	bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
+	bp->tx_nr_rings = bnxt_tx_nr_rings(bp);
 }
 
 static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
@@ -15871,7 +16438,7 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 		bnxt_trim_dflt_sh_rings(bp);
 	else
 		bp->cp_nr_rings = bp->tx_nr_rings_per_tc + bp->rx_nr_rings;
-	bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
+	bp->tx_nr_rings = bnxt_tx_nr_rings(bp);
 
 	avail_msix = bnxt_get_max_func_irqs(bp) - bp->cp_nr_rings;
 	if (avail_msix >= BNXT_MIN_ROCE_CP_RINGS) {
@@ -15884,7 +16451,7 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 	rc = __bnxt_reserve_rings(bp);
 	if (rc && rc != -ENODEV)
 		netdev_warn(bp->dev, "Unable to reserve tx rings\n");
-	bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
+	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
 	if (sh)
 		bnxt_trim_dflt_sh_rings(bp);
 
@@ -15893,7 +16460,7 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 		rc = __bnxt_reserve_rings(bp);
 		if (rc && rc != -ENODEV)
 			netdev_warn(bp->dev, "2nd rings reservation failed.\n");
-		bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
+		bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
 	}
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
 		bp->rx_nr_rings++;
@@ -15927,7 +16494,7 @@ static int bnxt_init_dflt_ring_mode(struct bnxt *bp)
 	if (rc)
 		goto init_dflt_ring_err;
 
-	bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
+	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
 
 	bnxt_set_dflt_rfs(bp);
 
@@ -15940,7 +16507,7 @@ int bnxt_restore_pf_fw_resources(struct bnxt *bp)
 {
 	int rc;
 
-	ASSERT_RTNL();
+	netdev_ops_assert_locked(bp->dev);
 	bnxt_hwrm_func_qcaps(bp);
 
 	if (netif_running(bp->dev))
@@ -15953,7 +16520,7 @@ int bnxt_restore_pf_fw_resources(struct bnxt *bp)
 
 	if (netif_running(bp->dev)) {
 		if (rc)
-			dev_close(bp->dev);
+			netif_close(bp->dev);
 		else
 			rc = bnxt_open_nic(bp, true, false);
 	}
@@ -16231,8 +16798,9 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (bp->max_fltr < BNXT_MAX_FLTR)
 		bp->max_fltr = BNXT_MAX_FLTR;
 	bnxt_init_l2_fltr_tbl(bp);
-	bnxt_set_rx_skb_mode(bp, false);
+	__bnxt_set_rx_skb_mode(bp, false);
 	bnxt_set_tpa_flags(bp);
+	bnxt_init_ring_params(bp);
 	bnxt_set_ring_params(bp);
 	bnxt_rdma_aux_device_init(bp);
 	rc = bnxt_set_dflt_rings(bp, true);
@@ -16289,6 +16857,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		bp->rss_cap |= BNXT_RSS_CAP_MULTI_RSS_CTX;
 	if (BNXT_SUPPORTS_QUEUE_API(bp))
 		dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops;
+	dev->request_ops_lock = true;
+	dev->netmem_tx = true;
 
 	rc = register_netdev(dev);
 	if (rc)
@@ -16340,13 +16910,18 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 		return;
 
 	rtnl_lock();
+	netdev_lock(dev);
 	bp = netdev_priv(dev);
 	if (!bp)
 		goto shutdown_exit;
 
 	if (netif_running(dev))
-		dev_close(dev);
+		netif_close(dev);
 
+	if (bnxt_hwrm_func_drv_unrgtr(bp)) {
+		pcie_flr(pdev);
+		goto shutdown_exit;
+	}
 	bnxt_ptp_clear(bp);
 	bnxt_clear_int_mode(bp);
 	pci_disable_device(pdev);
@@ -16357,6 +16932,7 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 	}
 
 shutdown_exit:
+	netdev_unlock(dev);
 	rtnl_unlock();
 }
 
@@ -16369,7 +16945,7 @@ static int bnxt_suspend(struct device *device)
 
 	bnxt_ulp_stop(bp);
 
-	rtnl_lock();
+	netdev_lock(dev);
 	if (netif_running(dev)) {
 		netif_device_detach(dev);
 		rc = bnxt_close(dev);
@@ -16378,7 +16954,7 @@ static int bnxt_suspend(struct device *device)
 	bnxt_ptp_clear(bp);
 	pci_disable_device(bp->pdev);
 	bnxt_free_ctx_mem(bp, false);
-	rtnl_unlock();
+	netdev_unlock(dev);
 	return rc;
 }
 
@@ -16388,7 +16964,7 @@ static int bnxt_resume(struct device *device)
 	struct bnxt *bp = netdev_priv(dev);
 	int rc = 0;
 
-	rtnl_lock();
+	netdev_lock(dev);
 	rc = pci_enable_device(bp->pdev);
 	if (rc) {
 		netdev_err(dev, "Cannot re-enable PCI device during resume, err = %d\n",
@@ -16431,7 +17007,7 @@ static int bnxt_resume(struct device *device)
 	}
 
 resume_exit:
-	rtnl_unlock();
+	netdev_unlock(bp->dev);
 	bnxt_ulp_start(bp, rc);
 	if (!rc)
 		bnxt_reenable_sriov(bp);
@@ -16466,7 +17042,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 
 	bnxt_ulp_stop(bp);
 
-	rtnl_lock();
+	netdev_lock(netdev);
 	netif_device_detach(netdev);
 
 	if (test_and_set_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
@@ -16475,7 +17051,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 	}
 
 	if (abort || state == pci_channel_io_perm_failure) {
-		rtnl_unlock();
+		netdev_unlock(netdev);
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
@@ -16494,9 +17070,9 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 	if (pci_is_enabled(pdev))
 		pci_disable_device(pdev);
 	bnxt_free_ctx_mem(bp, false);
-	rtnl_unlock();
+	netdev_unlock(netdev);
 
-	/* Request a slot slot reset. */
+	/* Request a slot reset. */
 	return PCI_ERS_RESULT_NEED_RESET;
 }
 
@@ -16524,7 +17100,7 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 	    test_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state))
 		msleep(900);
 
-	rtnl_lock();
+	netdev_lock(netdev);
 
 	if (pci_enable_device(pdev)) {
 		dev_err(&pdev->dev,
@@ -16570,16 +17146,15 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 		if (!err)
 			result = PCI_ERS_RESULT_RECOVERED;
 
+		/* IRQ will be initialized later in bnxt_io_resume */
 		bnxt_ulp_irq_stop(bp);
 		bnxt_clear_int_mode(bp);
-		err = bnxt_init_int_mode(bp);
-		bnxt_ulp_irq_restart(bp, err);
 	}
 
 reset_exit:
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	bnxt_clear_reservations(bp, true);
-	rtnl_unlock();
+	netdev_unlock(netdev);
 
 	return result;
 }
@@ -16598,20 +17173,23 @@ static void bnxt_io_resume(struct pci_dev *pdev)
 	int err;
 
 	netdev_info(bp->dev, "PCI Slot Resume\n");
-	rtnl_lock();
+	netdev_lock(netdev);
 
 	err = bnxt_hwrm_func_qcaps(bp);
 	if (!err) {
-		if (netif_running(netdev))
+		if (netif_running(netdev)) {
 			err = bnxt_open(netdev);
-		else
+		} else {
 			err = bnxt_reserve_rings(bp, true);
+			if (!err)
+				err = bnxt_init_int_mode(bp);
+		}
 	}
 
 	if (!err)
 		netif_device_attach(netdev);
 
-	rtnl_unlock();
+	netdev_unlock(netdev);
 	bnxt_ulp_start(bp, err);
 	if (!err)
 		bnxt_reenable_sriov(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 094c9e95b463..f5f07a7e6b29 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -34,6 +34,9 @@
 #include <linux/firmware/broadcom/tee_bnxt_fw.h>
 #endif
 
+#define BNXT_DEFAULT_RX_COPYBREAK 256
+#define BNXT_MAX_RX_COPYBREAK 1024
+
 extern struct list_head bnxt_block_cb_list;
 
 struct page_pool;
@@ -79,6 +82,12 @@ struct tx_bd {
 #define TX_OPAQUE_PROD(bp, opq)	((TX_OPAQUE_IDX(opq) + TX_OPAQUE_BDS(opq)) &\
 				 (bp)->tx_ring_mask)
 
+#define TX_BD_CNT(n)	(((n) << TX_BD_FLAGS_BD_CNT_SHIFT) & TX_BD_FLAGS_BD_CNT)
+
+#define TX_MAX_BD_CNT	32
+
+#define TX_MAX_FRAGS		(TX_MAX_BD_CNT - 2)
+
 struct tx_bd_ext {
 	__le32 tx_bd_hsize_lflags;
 	#define TX_BD_FLAGS_TCP_UDP_CHKSUM			(1 << 0)
@@ -122,6 +131,7 @@ struct rx_bd {
 	 #define RX_BD_TYPE_48B_BD_SIZE				 (2 << 4)
 	 #define RX_BD_TYPE_64B_BD_SIZE				 (3 << 4)
 	#define RX_BD_FLAGS_SOP					(1 << 6)
+	#define RX_BD_FLAGS_AGG_EOP				(1 << 6)
 	#define RX_BD_FLAGS_EOP					(1 << 7)
 	#define RX_BD_FLAGS_BUFFERS				(3 << 8)
 	 #define RX_BD_FLAGS_1_BUFFER_PACKET			 (0 << 8)
@@ -894,7 +904,7 @@ struct bnxt_sw_rx_bd {
 };
 
 struct bnxt_sw_rx_agg_bd {
-	struct page		*page;
+	netmem_ref		netmem;
 	unsigned int		offset;
 	dma_addr_t		mapping;
 };
@@ -1097,6 +1107,7 @@ struct bnxt_rx_ring_info {
 
 	unsigned long		*rx_agg_bmap;
 	u16			rx_agg_bmap_size;
+	bool                    need_head_pool;
 
 	dma_addr_t		rx_desc_mapping[MAX_RX_PAGES];
 	dma_addr_t		rx_agg_desc_mapping[MAX_RX_AGG_PAGES];
@@ -1231,6 +1242,11 @@ struct bnxt_irq {
 	u8		have_cpumask:1;
 	char		name[IFNAMSIZ + BNXT_IRQ_NAME_EXTRA];
 	cpumask_var_t	cpu_mask;
+
+	struct bnxt	*bp;
+	int		msix_nr;
+	int		ring_nr;
+	struct irq_affinity_notify affinity_notify;
 };
 
 #define HWRM_RING_ALLOC_TX	0x1
@@ -1953,10 +1969,12 @@ struct bnxt_ctx_mem_type {
 #define BNXT_CTX_CA1	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA1_TRACE
 #define BNXT_CTX_CA2	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA2_TRACE
 #define BNXT_CTX_RIGP1	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP1_TRACE
+#define BNXT_CTX_KONG	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE
+#define BNXT_CTX_QPC	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ERR_QPC_TRACE
 
 #define BNXT_CTX_MAX	(BNXT_CTX_TIM + 1)
 #define BNXT_CTX_L2_MAX	(BNXT_CTX_FTQM + 1)
-#define BNXT_CTX_V2_MAX	(BNXT_CTX_RIGP1 + 1)
+#define BNXT_CTX_V2_MAX (BNXT_CTX_QPC + 1)
 #define BNXT_CTX_INV	((u16)-1)
 
 struct bnxt_ctx_mem_info {
@@ -2115,6 +2133,7 @@ enum board_idx {
 	NETXTREME_E_P5_VF,
 	NETXTREME_E_P5_VF_HV,
 	NETXTREME_E_P7_VF,
+	NETXTREME_E_P7_VF_HV,
 };
 
 #define BNXT_TRACE_BUF_MAGIC_BYTE ((u8)0xbc)
@@ -2131,7 +2150,7 @@ struct bnxt_bs_trace_info {
 static inline void bnxt_bs_trace_check_wrap(struct bnxt_bs_trace_info *bs_trace,
 					    u32 offset)
 {
-	if (!bs_trace->wrapped &&
+	if (!bs_trace->wrapped && bs_trace->magic_byte &&
 	    *bs_trace->magic_byte != BNXT_TRACE_BUF_MAGIC_BYTE)
 		bs_trace->wrapped = 1;
 	bs_trace->last_offset = offset;
@@ -2241,8 +2260,6 @@ struct bnxt {
 	#define BNXT_FLAG_TPA		(BNXT_FLAG_LRO | BNXT_FLAG_GRO)
 	#define BNXT_FLAG_JUMBO		0x10
 	#define BNXT_FLAG_STRIP_VLAN	0x20
-	#define BNXT_FLAG_AGG_RINGS	(BNXT_FLAG_JUMBO | BNXT_FLAG_GRO | \
-					 BNXT_FLAG_LRO)
 	#define BNXT_FLAG_RFS		0x100
 	#define BNXT_FLAG_SHARED_RINGS	0x200
 	#define BNXT_FLAG_PORT_STATS	0x400
@@ -2263,6 +2280,9 @@ struct bnxt {
 	#define BNXT_FLAG_ROCE_MIRROR_CAP	0x4000000
 	#define BNXT_FLAG_TX_COAL_CMPL	0x8000000
 	#define BNXT_FLAG_PORT_STATS_EXT	0x10000000
+	#define BNXT_FLAG_HDS		0x20000000
+	#define BNXT_FLAG_AGG_RINGS	(BNXT_FLAG_JUMBO | BNXT_FLAG_GRO | \
+					 BNXT_FLAG_LRO | BNXT_FLAG_HDS)
 
 	#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA |		\
 					    BNXT_FLAG_RFS |		\
@@ -2347,7 +2367,7 @@ struct bnxt {
 	enum dma_data_direction	rx_dir;
 	u32			rx_ring_size;
 	u32			rx_agg_ring_size;
-	u32			rx_copy_thresh;
+	u32			rx_copybreak;
 	u32			rx_ring_mask;
 	u32			rx_agg_ring_mask;
 	int			rx_nr_pages;
@@ -2391,6 +2411,7 @@ struct bnxt {
 #define BNXT_RSS_CAP_ESP_V4_RSS_CAP		BIT(6)
 #define BNXT_RSS_CAP_ESP_V6_RSS_CAP		BIT(7)
 #define BNXT_RSS_CAP_MULTI_RSS_CTX		BIT(8)
+#define BNXT_RSS_CAP_IPV6_FLOW_LABEL_RSS_CAP	BIT(9)
 
 	u8			rss_hash_key[HW_HASH_KEY_SIZE];
 	u8			rss_hash_key_valid:1;
@@ -2404,8 +2425,13 @@ struct bnxt {
 	u8			tc_to_qidx[BNXT_MAX_QUEUE];
 	u8			q_ids[BNXT_MAX_QUEUE];
 	u8			max_q;
+	u8			cos0_cos1_shared;
 	u8			num_tc;
 
+	u16			max_pfcwd_tmo_ms;
+
+	u8			tph_mode;
+
 	unsigned int		current_interval;
 #define BNXT_TIMER_INTERVAL	HZ
 
@@ -2457,6 +2483,8 @@ struct bnxt {
 	#define BNXT_FW_CAP_ENABLE_RDMA_SRIOV           BIT_ULL(5)
 	#define BNXT_FW_CAP_ROCE_VF_RESC_MGMT_SUPPORTED	BIT_ULL(6)
 	#define BNXT_FW_CAP_KONG_MB_CHNL		BIT_ULL(7)
+	#define BNXT_FW_CAP_ROCE_VF_DYN_ALLOC_SUPPORT	BIT_ULL(8)
+	#define BNXT_FW_CAP_LINK_ADMIN			BIT_ULL(9)
 	#define BNXT_FW_CAP_OVS_64BIT_HANDLE		BIT_ULL(10)
 	#define BNXT_FW_CAP_TRUSTED_VF			BIT_ULL(11)
 	#define BNXT_FW_CAP_ERROR_RECOVERY		BIT_ULL(13)
@@ -2488,6 +2516,8 @@ struct bnxt {
 	#define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V3	BIT_ULL(39)
 	#define BNXT_FW_CAP_VNIC_RE_FLUSH		BIT_ULL(40)
 	#define BNXT_FW_CAP_SW_MAX_RESOURCE_LIMITS	BIT_ULL(41)
+	#define BNXT_FW_CAP_NPAR_1_2			BIT_ULL(42)
+	#define BNXT_FW_CAP_MIRROR_ON_ROCE		BIT_ULL(43)
 
 	u32			fw_dbg_cap;
 
@@ -2500,6 +2530,8 @@ struct bnxt {
 #define BNXT_SUPPORTS_MULTI_RSS_CTX(bp)				\
 	(BNXT_PF(bp) && BNXT_SUPPORTS_NTUPLE_VNIC(bp) &&	\
 	 ((bp)->rss_cap & BNXT_RSS_CAP_MULTI_RSS_CTX))
+#define BNXT_ROCE_VF_DYN_ALLOC_CAP(bp)				\
+	((bp)->fw_cap & BNXT_FW_CAP_ROCE_VF_DYN_ALLOC_SUPPORT)
 #define BNXT_SUPPORTS_QUEUE_API(bp)				\
 	(BNXT_PF(bp) && BNXT_SUPPORTS_NTUPLE_VNIC(bp) &&	\
 	 ((bp)->fw_cap & BNXT_FW_CAP_VNIC_RE_FLUSH))
@@ -2509,6 +2541,8 @@ struct bnxt {
 	((bp)->fw_cap & BNXT_FW_CAP_ROCE_VF_RESC_MGMT_SUPPORTED)
 #define BNXT_SW_RES_LMT(bp)		\
 	((bp)->fw_cap & BNXT_FW_CAP_SW_MAX_RESOURCE_LIMITS)
+#define BNXT_MIRROR_ON_ROCE_CAP(bp)	\
+	((bp)->fw_cap & BNXT_FW_CAP_MIRROR_ON_ROCE)
 
 	u32			hwrm_spec_code;
 	u16			hwrm_cmd_seq;
@@ -2523,6 +2557,7 @@ struct bnxt {
 	u16			fw_rx_stats_ext_size;
 	u16			fw_tx_stats_ext_size;
 	u16			hw_ring_stats_size;
+	u16			pcie_stat_len;
 	u8			pri2cos_idx[8];
 	u8			pri2cos_valid;
 
@@ -2596,6 +2631,7 @@ struct bnxt {
 #define BNXT_FW_RESET_STATE_POLL_FW	4
 #define BNXT_FW_RESET_STATE_OPENING	5
 #define BNXT_FW_RESET_STATE_POLL_FW_DOWN	6
+#define BNXT_FW_RESET_STATE_ABORT	7
 
 	u16			fw_reset_min_dsecs;
 #define BNXT_DFLT_FW_RST_MIN_DSECS	20
@@ -2685,6 +2721,7 @@ struct bnxt {
 #define BNXT_DUMP_LIVE		0
 #define BNXT_DUMP_CRASH		1
 #define BNXT_DUMP_DRIVER	2
+#define BNXT_DUMP_LIVE_WITH_CTX_L1_CACHE	3
 
 	struct bpf_prog		*xdp_prog;
 
@@ -2775,6 +2812,8 @@ struct bnxt {
 #define SFF_MODULE_ID_QSFP28			0x11
 #define BNXT_MAX_PHY_I2C_RESP_SIZE		64
 
+#define BNXT_HDS_THRESHOLD_MAX			1023
+
 static inline u32 bnxt_tx_avail(struct bnxt *bp,
 				const struct bnxt_tx_ring_info *txr)
 {
@@ -2859,7 +2898,7 @@ u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx);
 bool bnxt_bs_trace_avail(struct bnxt *bp, u16 type);
 void bnxt_set_tpa_flags(struct bnxt *bp);
 void bnxt_set_ring_params(struct bnxt *);
-int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
+void bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
 void bnxt_insert_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr);
 void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr);
 int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap,
@@ -2905,6 +2944,7 @@ void bnxt_report_link(struct bnxt *bp);
 int bnxt_update_link(struct bnxt *bp, bool chng_link_state);
 int bnxt_hwrm_set_pause(struct bnxt *);
 int bnxt_hwrm_set_link_setting(struct bnxt *, bool, bool);
+void bnxt_clear_reservations(struct bnxt *bp, bool fw_reset);
 int bnxt_cancel_reservations(struct bnxt *bp, bool fw_reset);
 int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp);
 int bnxt_hwrm_free_wol_fltr(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
index 7236d8e548ab..ccb8b509662d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
@@ -10,7 +10,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/pci.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_coredump.h"
@@ -36,6 +36,8 @@ static const u16 bnxt_bstore_to_seg_id[] = {
 	[BNXT_CTX_CA1]			= BNXT_CTX_MEM_SEG_CA1,
 	[BNXT_CTX_CA2]			= BNXT_CTX_MEM_SEG_CA2,
 	[BNXT_CTX_RIGP1]		= BNXT_CTX_MEM_SEG_RIGP1,
+	[BNXT_CTX_KONG]			= BNXT_CTX_MEM_SEG_KONG,
+	[BNXT_CTX_QPC]			= BNXT_CTX_MEM_SEG_QPC,
 };
 
 static int bnxt_dbg_hwrm_log_buffer_flush(struct bnxt *bp, u16 type, u32 flags,
@@ -110,20 +112,30 @@ static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg,
 			}
 		}
 
+		if (cmn_req->req_type ==
+				cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
+			info->dest_buf_size += len;
+
 		if (info->dest_buf) {
 			if ((info->seg_start + off + len) <=
 			    BNXT_COREDUMP_BUF_LEN(info->buf_len)) {
-				memcpy(info->dest_buf + off, dma_buf, len);
+				u16 copylen = min_t(u16, len,
+						    info->dest_buf_size - off);
+
+				memcpy(info->dest_buf + off, dma_buf, copylen);
+				if (copylen < len)
+					break;
 			} else {
 				rc = -ENOBUFS;
+				if (cmn_req->req_type ==
+				    cpu_to_le16(HWRM_DBG_COREDUMP_LIST)) {
+					kfree(info->dest_buf);
+					info->dest_buf = NULL;
+				}
 				break;
 			}
 		}
 
-		if (cmn_req->req_type ==
-				cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
-			info->dest_buf_size += len;
-
 		if (!(cmn_resp->flags & HWRM_DBG_CMN_FLAGS_MORE))
 			break;
 
@@ -159,8 +171,8 @@ static int bnxt_hwrm_dbg_coredump_list(struct bnxt *bp,
 	return rc;
 }
 
-static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id,
-					   u16 segment_id)
+static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 dump_type,
+					   u16 component_id, u16 segment_id)
 {
 	struct hwrm_dbg_coredump_initiate_input *req;
 	int rc;
@@ -172,6 +184,8 @@ static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id,
 	hwrm_req_timeout(bp, req, bp->hwrm_cmd_max_timeout);
 	req->component_id = cpu_to_le16(component_id);
 	req->segment_id = cpu_to_le16(segment_id);
+	if (dump_type == BNXT_DUMP_LIVE_WITH_CTX_L1_CACHE)
+		req->seg_flags = DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_COLLECT_CTX_L1_CACHE;
 
 	return hwrm_req_send(bp, req);
 }
@@ -319,13 +333,14 @@ static void bnxt_fill_drv_seg_record(struct bnxt *bp,
 	u32 offset = 0;
 	int rc = 0;
 
+	record->max_entries = cpu_to_le32(ctxm->max_entries);
+	record->entry_size = cpu_to_le32(ctxm->entry_size);
+
 	rc = bnxt_dbg_hwrm_log_buffer_flush(bp, type, 0, &offset);
 	if (rc)
 		return;
 
 	bnxt_bs_trace_check_wrap(bs_trace, offset);
-	record->max_entries = cpu_to_le32(ctxm->max_entries);
-	record->entry_size = cpu_to_le32(ctxm->entry_size);
 	record->offset = cpu_to_le32(bs_trace->last_offset);
 	record->wrapped = bs_trace->wrapped;
 }
@@ -347,7 +362,7 @@ static u32 bnxt_get_ctx_coredump(struct bnxt *bp, void *buf, u32 offset,
 
 	if (buf)
 		buf += offset;
-	for (type = 0 ; type <= BNXT_CTX_RIGP1; type++) {
+	for (type = 0; type < BNXT_CTX_V2_MAX; type++) {
 		struct bnxt_ctx_mem_type *ctxm = &ctx->ctx_arr[type];
 		bool trace = bnxt_bs_trace_avail(bp, type);
 		u32 seg_id = bnxt_bstore_to_seg_id[type];
@@ -356,23 +371,27 @@ static u32 bnxt_get_ctx_coredump(struct bnxt *bp, void *buf, u32 offset,
 		if (!ctxm->mem_valid || !seg_id)
 			continue;
 
-		if (trace)
+		if (trace) {
 			extra_hlen = BNXT_SEG_RCD_LEN;
+			if (buf) {
+				u16 trace_type = bnxt_bstore_to_trace[type];
+
+				bnxt_fill_drv_seg_record(bp, &record, ctxm,
+							 trace_type);
+			}
+		}
+
 		if (buf)
 			data = buf + BNXT_SEG_HDR_LEN + extra_hlen;
+
 		seg_len = bnxt_copy_ctx_mem(bp, ctxm, data, 0) + extra_hlen;
 		if (buf) {
 			bnxt_fill_coredump_seg_hdr(bp, &seg_hdr, NULL, seg_len,
 						   0, 0, 0, comp_id, seg_id);
 			memcpy(buf, &seg_hdr, BNXT_SEG_HDR_LEN);
 			buf += BNXT_SEG_HDR_LEN;
-			if (trace) {
-				u16 trace_type = bnxt_bstore_to_trace[type];
-
-				bnxt_fill_drv_seg_record(bp, &record, ctxm,
-							 trace_type);
+			if (trace)
 				memcpy(buf, &record, BNXT_SEG_RCD_LEN);
-			}
 			buf += seg_len;
 		}
 		len += BNXT_SEG_HDR_LEN + seg_len;
@@ -450,7 +469,8 @@ static int __bnxt_get_coredump(struct bnxt *bp, u16 dump_type, void *buf,
 
 		start = jiffies;
 
-		rc = bnxt_hwrm_dbg_coredump_initiate(bp, comp_id, seg_id);
+		rc = bnxt_hwrm_dbg_coredump_initiate(bp, dump_type, comp_id,
+						     seg_id);
 		if (rc) {
 			netdev_err(bp->dev,
 				   "Failed to initiate coredump for seg = %d\n",
@@ -493,9 +513,16 @@ err:
 					  start_utc, coredump.total_segs + 1,
 					  rc);
 	kfree(coredump.data);
-	*dump_len += sizeof(struct bnxt_coredump_record);
-	if (rc == -ENOBUFS)
+	if (!rc) {
+		*dump_len += sizeof(struct bnxt_coredump_record);
+		/* The actual coredump length can be smaller than the FW
+		 * reported length earlier.  Use the ethtool provided length.
+		 */
+		if (buf_len)
+			*dump_len = buf_len;
+	} else if (rc == -ENOBUFS) {
 		netdev_err(bp->dev, "Firmware returned large coredump buffer\n");
+	}
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h
index d1cd6387f3ab..c087df88154a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h
@@ -102,6 +102,8 @@ struct bnxt_driver_segment_record {
 #define BNXT_CTX_MEM_SEG_CA1	0x9
 #define BNXT_CTX_MEM_SEG_CA2	0xa
 #define BNXT_CTX_MEM_SEG_RIGP1	0xb
+#define BNXT_CTX_MEM_SEG_QPC	0xc
+#define BNXT_CTX_MEM_SEG_KONG	0xd
 
 #define BNXT_CRASH_DUMP_LEN	(8 << 20)
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 0dbb880a7aa0..a00b67334f9b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -16,7 +16,7 @@
 #include <linux/pci.h>
 #include <linux/etherdevice.h>
 #include <rdma/ib_verbs.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_dcb.h"
@@ -487,7 +487,9 @@ static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
 
 		if ((ets->tc_tx_bw[i] || ets->tc_tsa[i]) && i > bp->max_tc)
 			return -EINVAL;
+	}
 
+	for (i = 0; i < max_tc; i++) {
 		switch (ets->tc_tsa[i]) {
 		case IEEE_8021QAZ_TSA_STRICT:
 			break;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c
index 127b7015f676..3324afbb3bec 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c
@@ -10,7 +10,7 @@
 #include <linux/debugfs.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include <linux/dim.h>
 #include "bnxt.h"
 #include "bnxt_debugfs.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.h
index d0bb4887acd0..a0a8d687dd99 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.h
@@ -7,7 +7,7 @@
  * the Free Software Foundation.
  */
 
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index ef8288fd68f4..15de802bbac4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -11,7 +11,8 @@
 #include <linux/netdevice.h>
 #include <linux/vmalloc.h>
 #include <net/devlink.h>
-#include "bnxt_hsi.h"
+#include <net/netdev_lock.h>
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_vfr.h"
@@ -39,12 +40,6 @@ bnxt_dl_flash_update(struct devlink *dl,
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
 	int rc;
 
-	if (!BNXT_PF(bp)) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "flash update not supported from a VF");
-		return -EPERM;
-	}
-
 	devlink_flash_update_status_notify(dl, "Preparing to flash", NULL, 0, 0);
 	rc = bnxt_flash_package_from_fw_obj(bp->dev, params->fw, 0, extack);
 	if (!rc)
@@ -219,7 +214,7 @@ __bnxt_dl_reporter_create(struct bnxt *bp,
 {
 	struct devlink_health_reporter *reporter;
 
-	reporter = devlink_health_reporter_create(bp->dl, ops, 0, bp);
+	reporter = devlink_health_reporter_create(bp->dl, ops, bp);
 	if (IS_ERR(reporter)) {
 		netdev_warn(bp->dev, "Failed to create %s health reporter, rc = %ld\n",
 			    ops->name, PTR_ERR(reporter));
@@ -439,14 +434,17 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: {
 		bnxt_ulp_stop(bp);
 		rtnl_lock();
+		netdev_lock(bp->dev);
 		if (bnxt_sriov_cfg(bp)) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "reload is unsupported while VFs are allocated or being configured");
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			bnxt_ulp_start(bp, 0);
 			return -EOPNOTSUPP;
 		}
 		if (bp->dev->reg_state == NETREG_UNREGISTERED) {
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			bnxt_ulp_start(bp, 0);
 			return -ENODEV;
@@ -458,11 +456,12 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 		if (rc) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to deregister");
 			if (netif_running(bp->dev))
-				dev_close(bp->dev);
+				netif_close(bp->dev);
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			break;
 		}
-		bnxt_cancel_reservations(bp, false);
+		bnxt_clear_reservations(bp, false);
 		bnxt_free_ctx_mem(bp, false);
 		break;
 	}
@@ -479,7 +478,9 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 			return -EPERM;
 		}
 		rtnl_lock();
+		netdev_lock(bp->dev);
 		if (bp->dev->reg_state == NETREG_UNREGISTERED) {
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			return -ENODEV;
 		}
@@ -493,6 +494,7 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 		if (rc) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to activate firmware");
 			clear_bit(BNXT_STATE_FW_ACTIVATE, &bp->state);
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 		}
 		break;
@@ -511,6 +513,8 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
 	int rc = 0;
 
+	netdev_assert_locked(bp->dev);
+
 	*actions_performed = 0;
 	switch (action) {
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: {
@@ -535,6 +539,7 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 		if (!netif_running(bp->dev))
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Device is closed, not waiting for reset notice that will never come");
+		netdev_unlock(bp->dev);
 		rtnl_unlock();
 		while (test_bit(BNXT_STATE_FW_ACTIVATE, &bp->state)) {
 			if (time_after(jiffies, timeout)) {
@@ -550,6 +555,7 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 			msleep(50);
 		}
 		rtnl_lock();
+		netdev_lock(bp->dev);
 		if (!rc)
 			*actions_performed |= BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
 		clear_bit(BNXT_STATE_FW_ACTIVATE, &bp->state);
@@ -568,8 +574,9 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 		}
 		*actions_performed |= BIT(action);
 	} else if (netif_running(bp->dev)) {
-		dev_close(bp->dev);
+		netif_close(bp->dev);
 	}
+	netdev_unlock(bp->dev);
 	rtnl_unlock();
 	if (action == DEVLINK_RELOAD_ACTION_DRIVER_REINIT)
 		bnxt_ulp_start(bp, rc);
@@ -666,6 +673,8 @@ static const struct bnxt_dl_nvm_param nvm_params[] = {
 	 NVM_OFF_MSIX_VEC_PER_PF_MAX, BNXT_NVM_SHARED_CFG, 10, 4},
 	{DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
 	 NVM_OFF_MSIX_VEC_PER_PF_MIN, BNXT_NVM_SHARED_CFG, 7, 4},
+	{DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, NVM_OFF_SUPPORT_RDMA,
+	 BNXT_NVM_FUNC_CFG, 1, 1},
 	{BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, NVM_OFF_DIS_GRE_VER_CHECK,
 	 BNXT_NVM_SHARED_CFG, 1, 1},
 };
@@ -1010,37 +1019,19 @@ static int bnxt_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 
 }
 
-static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
-			     union devlink_param_value *val)
+static int __bnxt_hwrm_nvm_req(struct bnxt *bp,
+			       const struct bnxt_dl_nvm_param *nvm, void *msg,
+			       union devlink_param_value *val)
 {
 	struct hwrm_nvm_get_variable_input *req = msg;
-	struct bnxt_dl_nvm_param nvm_param;
 	struct hwrm_err_output *resp;
 	union bnxt_nvm_data *data;
 	dma_addr_t data_dma_addr;
-	int idx = 0, rc, i;
+	int idx = 0, rc;
 
-	/* Get/Set NVM CFG parameter is supported only on PFs */
-	if (BNXT_VF(bp)) {
-		hwrm_req_drop(bp, req);
-		return -EPERM;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(nvm_params); i++) {
-		if (nvm_params[i].id == param_id) {
-			nvm_param = nvm_params[i];
-			break;
-		}
-	}
-
-	if (i == ARRAY_SIZE(nvm_params)) {
-		hwrm_req_drop(bp, req);
-		return -EOPNOTSUPP;
-	}
-
-	if (nvm_param.dir_type == BNXT_NVM_PORT_CFG)
+	if (nvm->dir_type == BNXT_NVM_PORT_CFG)
 		idx = bp->pf.port_id;
-	else if (nvm_param.dir_type == BNXT_NVM_FUNC_CFG)
+	else if (nvm->dir_type == BNXT_NVM_FUNC_CFG)
 		idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID;
 
 	data = hwrm_req_dma_slice(bp, req, sizeof(*data), &data_dma_addr);
@@ -1051,23 +1042,23 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 	}
 
 	req->dest_data_addr = cpu_to_le64(data_dma_addr);
-	req->data_len = cpu_to_le16(nvm_param.nvm_num_bits);
-	req->option_num = cpu_to_le16(nvm_param.offset);
+	req->data_len = cpu_to_le16(nvm->nvm_num_bits);
+	req->option_num = cpu_to_le16(nvm->offset);
 	req->index_0 = cpu_to_le16(idx);
 	if (idx)
 		req->dimensions = cpu_to_le16(1);
 
 	resp = hwrm_req_hold(bp, req);
 	if (req->req_type == cpu_to_le16(HWRM_NVM_SET_VARIABLE)) {
-		bnxt_copy_to_nvm_data(data, val, nvm_param.nvm_num_bits,
-				      nvm_param.dl_num_bytes);
+		bnxt_copy_to_nvm_data(data, val, nvm->nvm_num_bits,
+				      nvm->dl_num_bytes);
 		rc = hwrm_req_send(bp, msg);
 	} else {
 		rc = hwrm_req_send_silent(bp, msg);
 		if (!rc) {
 			bnxt_copy_from_nvm_data(val, data,
-						nvm_param.nvm_num_bits,
-						nvm_param.dl_num_bytes);
+						nvm->nvm_num_bits,
+						nvm->dl_num_bytes);
 		} else {
 			if (resp->cmd_err ==
 				NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST)
@@ -1080,8 +1071,23 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 	return rc;
 }
 
+static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
+			     union devlink_param_value *val)
+{
+	const struct bnxt_dl_nvm_param *nvm_param;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nvm_params); i++) {
+		nvm_param = &nvm_params[i];
+		if (nvm_param->id == param_id)
+			return __bnxt_hwrm_nvm_req(bp, nvm_param, msg, val);
+	}
+	return -EOPNOTSUPP;
+}
+
 static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id,
-				 struct devlink_param_gset_ctx *ctx)
+				 struct devlink_param_gset_ctx *ctx,
+				 struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
 	struct hwrm_nvm_get_variable_input *req;
@@ -1116,6 +1122,32 @@ static int bnxt_dl_nvm_param_set(struct devlink *dl, u32 id,
 	return bnxt_hwrm_nvm_req(bp, id, req, &ctx->val);
 }
 
+static int bnxt_dl_roce_validate(struct devlink *dl, u32 id,
+				 union devlink_param_value val,
+				 struct netlink_ext_ack *extack)
+{
+	const struct bnxt_dl_nvm_param nvm_roce_cap = {0, NVM_OFF_RDMA_CAPABLE,
+		BNXT_NVM_SHARED_CFG, 1, 1};
+	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
+	struct hwrm_nvm_get_variable_input *req;
+	union devlink_param_value roce_cap;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_NVM_GET_VARIABLE);
+	if (rc)
+		return rc;
+
+	if (__bnxt_hwrm_nvm_req(bp, &nvm_roce_cap, req, &roce_cap)) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to verify if device is RDMA Capable");
+		return -EINVAL;
+	}
+	if (!roce_cap.vbool) {
+		NL_SET_ERR_MSG_MOD(extack, "Device does not support RDMA");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int bnxt_dl_msix_validate(struct devlink *dl, u32 id,
 				 union devlink_param_value val,
 				 struct netlink_ext_ack *extack)
@@ -1137,7 +1169,8 @@ static int bnxt_dl_msix_validate(struct devlink *dl, u32 id,
 }
 
 static int bnxt_remote_dev_reset_get(struct devlink *dl, u32 id,
-				     struct devlink_param_gset_ctx *ctx)
+				     struct devlink_param_gset_ctx *ctx,
+				     struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
 
@@ -1180,6 +1213,10 @@ static const struct devlink_param bnxt_dl_params[] = {
 			      BIT(DEVLINK_PARAM_CMODE_PERMANENT),
 			      bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set,
 			      bnxt_dl_msix_validate),
+	DEVLINK_PARAM_GENERIC(ENABLE_ROCE,
+			      BIT(DEVLINK_PARAM_CMODE_PERMANENT),
+			      bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set,
+			      bnxt_dl_roce_validate),
 	DEVLINK_PARAM_DRIVER(BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK,
 			     "gre_ver_check", DEVLINK_PARAM_TYPE_BOOL,
 			     BIT(DEVLINK_PARAM_CMODE_PERMANENT),
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index b8105065367b..7f45dcd7b287 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -41,8 +41,10 @@ static inline void bnxt_dl_set_remote_reset(struct devlink *dl, bool value)
 #define NVM_OFF_MSIX_VEC_PER_PF_MAX	108
 #define NVM_OFF_MSIX_VEC_PER_PF_MIN	114
 #define NVM_OFF_IGNORE_ARI		164
+#define NVM_OFF_RDMA_CAPABLE		161
 #define NVM_OFF_DIS_GRE_VER_CHECK	171
 #define NVM_OFF_ENABLE_SRIOV		401
+#define NVM_OFF_SUPPORT_RDMA		506
 #define NVM_OFF_NVM_CFG_VER		602
 
 #define BNXT_NVM_CFG_VER_BITS		8
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c
index 6f6576dc417a..53a3bcb0efe0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c
@@ -8,7 +8,7 @@
  */
 
 #include <linux/dim.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 
 void bnxt_dim_work(struct work_struct *work)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 75a59dd72bce..068e191ede19 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -24,8 +24,9 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/net_tstamp.h>
 #include <linux/timecounter.h>
+#include <net/netdev_queues.h>
 #include <net/netlink.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ulp.h"
@@ -687,16 +688,22 @@ skip_ring_stats:
 				buf[j] = *(rx_port_stats_ext + n);
 			}
 			for (i = 0; i < 8; i++, j++) {
-				long n = bnxt_tx_bytes_pri_arr[i].base_off +
-					 bp->pri2cos_idx[i];
+				u8 cos_idx = bp->pri2cos_idx[i];
+				long n;
 
+				n = bnxt_tx_bytes_pri_arr[i].base_off + cos_idx;
 				buf[j] = *(tx_port_stats_ext + n);
+				if (bp->cos0_cos1_shared && !cos_idx)
+					buf[j] += *(tx_port_stats_ext + n + 1);
 			}
 			for (i = 0; i < 8; i++, j++) {
-				long n = bnxt_tx_pkts_pri_arr[i].base_off +
-					 bp->pri2cos_idx[i];
+				u8 cos_idx = bp->pri2cos_idx[i];
+				long n;
 
+				n = bnxt_tx_pkts_pri_arr[i].base_off + cos_idx;
 				buf[j] = *(tx_port_stats_ext + n);
+				if (bp->cos0_cos1_shared && !cos_idx)
+					buf[j] += *(tx_port_stats_ext + n + 1);
 			}
 		}
 	}
@@ -833,6 +840,8 @@ static void bnxt_get_ringparam(struct net_device *dev,
 	ering->rx_pending = bp->rx_ring_size;
 	ering->rx_jumbo_pending = bp->rx_agg_ring_size;
 	ering->tx_pending = bp->tx_ring_size;
+
+	kernel_ering->hds_thresh_max = BNXT_HDS_THRESHOLD_MAX;
 }
 
 static int bnxt_set_ringparam(struct net_device *dev,
@@ -840,16 +849,35 @@ static int bnxt_set_ringparam(struct net_device *dev,
 			      struct kernel_ethtool_ringparam *kernel_ering,
 			      struct netlink_ext_ack *extack)
 {
+	u8 tcp_data_split = kernel_ering->tcp_data_split;
 	struct bnxt *bp = netdev_priv(dev);
+	u8 hds_config_mod;
 
 	if ((ering->rx_pending > BNXT_MAX_RX_DESC_CNT) ||
 	    (ering->tx_pending > BNXT_MAX_TX_DESC_CNT) ||
 	    (ering->tx_pending < BNXT_MIN_TX_DESC_CNT))
 		return -EINVAL;
 
+	hds_config_mod = tcp_data_split != dev->cfg->hds_config;
+	if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_DISABLED && hds_config_mod)
+		return -EINVAL;
+
+	if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED &&
+	    hds_config_mod && BNXT_RX_PAGE_MODE(bp)) {
+		NL_SET_ERR_MSG_MOD(extack, "tcp-data-split is disallowed when XDP is attached");
+		return -EINVAL;
+	}
+
 	if (netif_running(dev))
 		bnxt_close_nic(bp, false, false);
 
+	if (hds_config_mod) {
+		if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED)
+			bp->flags |= BNXT_FLAG_HDS;
+		else if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN)
+			bp->flags &= ~BNXT_FLAG_HDS;
+	}
+
 	bp->rx_ring_size = ering->rx_pending;
 	bp->tx_ring_size = ering->tx_pending;
 	bnxt_set_ring_params(bp);
@@ -1562,11 +1590,16 @@ static u64 get_ethtool_ipv6_rss(struct bnxt *bp)
 {
 	if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6)
 		return RXH_IP_SRC | RXH_IP_DST;
+	if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL)
+		return RXH_IP_SRC | RXH_IP_DST | RXH_IP6_FL;
 	return 0;
 }
 
-static int bnxt_grxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
+static int bnxt_get_rxfh_fields(struct net_device *dev,
+				struct ethtool_rxfh_fields *cmd)
 {
+	struct bnxt *bp = netdev_priv(dev);
+
 	cmd->data = 0;
 	switch (cmd->flow_type) {
 	case TCP_V4_FLOW:
@@ -1625,20 +1658,30 @@ static int bnxt_grxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 #define RXH_4TUPLE (RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3)
 #define RXH_2TUPLE (RXH_IP_SRC | RXH_IP_DST)
 
-static int bnxt_srxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
+static int bnxt_set_rxfh_fields(struct net_device *dev,
+				const struct ethtool_rxfh_fields *cmd,
+				struct netlink_ext_ack *extack)
 {
-	u32 rss_hash_cfg = bp->rss_hash_cfg;
+	struct bnxt *bp = netdev_priv(dev);
 	int tuple, rc = 0;
+	u32 rss_hash_cfg;
+
+	rss_hash_cfg = bp->rss_hash_cfg;
 
 	if (cmd->data == RXH_4TUPLE)
 		tuple = 4;
-	else if (cmd->data == RXH_2TUPLE)
+	else if (cmd->data == RXH_2TUPLE ||
+		 cmd->data == (RXH_2TUPLE | RXH_IP6_FL))
 		tuple = 2;
 	else if (!cmd->data)
 		tuple = 0;
 	else
 		return -EINVAL;
 
+	if (cmd->data & RXH_IP6_FL &&
+	    !(bp->rss_cap & BNXT_RSS_CAP_IPV6_FLOW_LABEL_RSS_CAP))
+		return -EINVAL;
+
 	if (cmd->flow_type == TCP_V4_FLOW) {
 		rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4;
 		if (tuple == 4)
@@ -1702,10 +1745,15 @@ static int bnxt_srxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 	case AH_V6_FLOW:
 	case ESP_V6_FLOW:
 	case IPV6_FLOW:
-		if (tuple == 2)
+		rss_hash_cfg &= ~(VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 |
+				  VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL);
+		if (!tuple)
+			break;
+		if (cmd->data & RXH_IP6_FL)
+			rss_hash_cfg |=
+				VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL;
+		else if (tuple == 2)
 			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6;
-		else if (!tuple)
-			rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6;
 		break;
 	}
 
@@ -1722,6 +1770,13 @@ static int bnxt_srxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 	return rc;
 }
 
+static u32 bnxt_get_rx_ring_count(struct net_device *dev)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	return bp->rx_nr_rings;
+}
+
 static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 			  u32 *rule_locs)
 {
@@ -1729,10 +1784,6 @@ static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	int rc = 0;
 
 	switch (cmd->cmd) {
-	case ETHTOOL_GRXRINGS:
-		cmd->data = bp->rx_nr_rings;
-		break;
-
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = bp->ntp_fltr_count;
 		cmd->data = bp->max_fltr | RX_CLS_LOC_SPECIAL;
@@ -1746,10 +1797,6 @@ static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 		rc = bnxt_grxclsrule(bp, cmd);
 		break;
 
-	case ETHTOOL_GRXFH:
-		rc = bnxt_grxfh(bp, cmd);
-		break;
-
 	default:
 		rc = -EOPNOTSUPP;
 		break;
@@ -1764,10 +1811,6 @@ static int bnxt_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	int rc;
 
 	switch (cmd->cmd) {
-	case ETHTOOL_SRXFH:
-		rc = bnxt_srxfh(bp, cmd);
-		break;
-
 	case ETHTOOL_SRXCLSRLINS:
 		rc = bnxt_srxclsrlins(bp, cmd);
 		break;
@@ -2027,27 +2070,52 @@ static void bnxt_get_drvinfo(struct net_device *dev,
 static int bnxt_get_regs_len(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	int reg_len;
 
 	if (!BNXT_PF(bp))
 		return -EOPNOTSUPP;
 
-	reg_len = BNXT_PXP_REG_LEN;
+	return BNXT_PXP_REG_LEN + bp->pcie_stat_len;
+}
+
+static void *
+__bnxt_hwrm_pcie_qstats(struct bnxt *bp, struct hwrm_pcie_qstats_input *req)
+{
+	struct pcie_ctx_hw_stats_v2 *hw_pcie_stats;
+	dma_addr_t hw_pcie_stats_addr;
+	int rc;
+
+	hw_pcie_stats = hwrm_req_dma_slice(bp, req, sizeof(*hw_pcie_stats),
+					   &hw_pcie_stats_addr);
+	if (!hw_pcie_stats)
+		return NULL;
 
-	if (bp->fw_cap & BNXT_FW_CAP_PCIE_STATS_SUPPORTED)
-		reg_len += sizeof(struct pcie_ctx_hw_stats);
+	req->pcie_stat_size = cpu_to_le16(sizeof(*hw_pcie_stats));
+	req->pcie_stat_host_addr = cpu_to_le64(hw_pcie_stats_addr);
+	rc = hwrm_req_send(bp, req);
 
-	return reg_len;
+	return rc ? NULL : hw_pcie_stats;
 }
 
+#define BNXT_PCIE_32B_ENTRY(start, end)			\
+	 { offsetof(struct pcie_ctx_hw_stats_v2, start),\
+	   offsetof(struct pcie_ctx_hw_stats_v2, end) }
+
+static const struct {
+	u16 start;
+	u16 end;
+} bnxt_pcie_32b_entries[] = {
+	BNXT_PCIE_32B_ENTRY(pcie_ltssm_histogram[0], pcie_ltssm_histogram[3]),
+	BNXT_PCIE_32B_ENTRY(pcie_tl_credit_nph_histogram[0], unused_1),
+	BNXT_PCIE_32B_ENTRY(pcie_rd_latency_histogram[0], unused_2),
+};
+
 static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 			  void *_p)
 {
-	struct pcie_ctx_hw_stats *hw_pcie_stats;
+	struct hwrm_pcie_qstats_output *resp;
 	struct hwrm_pcie_qstats_input *req;
 	struct bnxt *bp = netdev_priv(dev);
-	dma_addr_t hw_pcie_stats_addr;
-	int rc;
+	u8 *src;
 
 	regs->version = 0;
 	if (!(bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_REG_ACCESS_RESTRICTED))
@@ -2059,25 +2127,37 @@ static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	if (hwrm_req_init(bp, req, HWRM_PCIE_QSTATS))
 		return;
 
-	hw_pcie_stats = hwrm_req_dma_slice(bp, req, sizeof(*hw_pcie_stats),
-					   &hw_pcie_stats_addr);
-	if (!hw_pcie_stats) {
-		hwrm_req_drop(bp, req);
-		return;
-	}
-
-	regs->version = 1;
-	hwrm_req_hold(bp, req); /* hold on to slice */
-	req->pcie_stat_size = cpu_to_le16(sizeof(*hw_pcie_stats));
-	req->pcie_stat_host_addr = cpu_to_le64(hw_pcie_stats_addr);
-	rc = hwrm_req_send(bp, req);
-	if (!rc) {
-		__le64 *src = (__le64 *)hw_pcie_stats;
-		u64 *dst = (u64 *)(_p + BNXT_PXP_REG_LEN);
-		int i;
-
-		for (i = 0; i < sizeof(*hw_pcie_stats) / sizeof(__le64); i++)
-			dst[i] = le64_to_cpu(src[i]);
+	resp = hwrm_req_hold(bp, req);
+	src = __bnxt_hwrm_pcie_qstats(bp, req);
+	if (src) {
+		u8 *dst = (u8 *)(_p + BNXT_PXP_REG_LEN);
+		int i, j, len;
+
+		len = min(bp->pcie_stat_len, le16_to_cpu(resp->pcie_stat_size));
+		if (len <= sizeof(struct pcie_ctx_hw_stats))
+			regs->version = 1;
+		else if (len < sizeof(struct pcie_ctx_hw_stats_v2))
+			regs->version = 2;
+		else
+			regs->version = 3;
+
+		for (i = 0, j = 0; i < len; ) {
+			if (i >= bnxt_pcie_32b_entries[j].start &&
+			    i <= bnxt_pcie_32b_entries[j].end) {
+				u32 *dst32 = (u32 *)(dst + i);
+
+				*dst32 = le32_to_cpu(*(__le32 *)(src + i));
+				i += 4;
+				if (i > bnxt_pcie_32b_entries[j].end &&
+				    j < ARRAY_SIZE(bnxt_pcie_32b_entries) - 1)
+					j++;
+			} else {
+				u64 *dst64 = (u64 *)(dst + i);
+
+				*dst64 = le64_to_cpu(*(__le64 *)(src + i));
+				i += 8;
+			}
+		}
 	}
 	hwrm_req_drop(bp, req);
 }
@@ -3137,7 +3217,8 @@ static int bnxt_get_fecparam(struct net_device *dev,
 }
 
 static void bnxt_get_fec_stats(struct net_device *dev,
-			       struct ethtool_fec_stats *fec_stats)
+			       struct ethtool_fec_stats *fec_stats,
+			       struct ethtool_fec_hist *hist)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	u64 *rx;
@@ -4162,7 +4243,7 @@ err:
 static void bnxt_get_pkgver(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	char buf[FW_VER_STR_LEN];
+	char buf[FW_VER_STR_LEN - 5];
 	int len;
 
 	if (!bnxt_get_pkginfo(dev, buf, sizeof(buf))) {
@@ -4328,6 +4409,88 @@ static int bnxt_get_eee(struct net_device *dev, struct ethtool_keee *edata)
 	return 0;
 }
 
+static int bnxt_hwrm_pfcwd_qcfg(struct bnxt *bp, u16 *val)
+{
+	struct hwrm_queue_pfcwd_timeout_qcfg_output *resp;
+	struct hwrm_queue_pfcwd_timeout_qcfg_input *req;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_QUEUE_PFCWD_TIMEOUT_QCFG);
+	if (rc)
+		return rc;
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
+	if (!rc)
+		*val = le16_to_cpu(resp->pfcwd_timeout_value);
+	hwrm_req_drop(bp, req);
+	return rc;
+}
+
+static int bnxt_hwrm_pfcwd_cfg(struct bnxt *bp, u16 val)
+{
+	struct hwrm_queue_pfcwd_timeout_cfg_input *req;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_QUEUE_PFCWD_TIMEOUT_CFG);
+	if (rc)
+		return rc;
+	req->pfcwd_timeout_value = cpu_to_le16(val);
+	rc = hwrm_req_send(bp, req);
+	return rc;
+}
+
+static int bnxt_set_tunable(struct net_device *dev,
+			    const struct ethtool_tunable *tuna,
+			    const void *data)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	u32 rx_copybreak, val;
+
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		rx_copybreak = *(u32 *)data;
+		if (rx_copybreak > BNXT_MAX_RX_COPYBREAK)
+			return -ERANGE;
+		if (rx_copybreak != bp->rx_copybreak) {
+			if (netif_running(dev))
+				return -EBUSY;
+			bp->rx_copybreak = rx_copybreak;
+		}
+		return 0;
+	case ETHTOOL_PFC_PREVENTION_TOUT:
+		if (BNXT_VF(bp) || !bp->max_pfcwd_tmo_ms)
+			return -EOPNOTSUPP;
+
+		val = *(u16 *)data;
+		if (val > bp->max_pfcwd_tmo_ms &&
+		    val != PFC_STORM_PREVENTION_AUTO)
+			return -EINVAL;
+		return bnxt_hwrm_pfcwd_cfg(bp, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int bnxt_get_tunable(struct net_device *dev,
+			    const struct ethtool_tunable *tuna, void *data)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		*(u32 *)data = bp->rx_copybreak;
+		break;
+	case ETHTOOL_PFC_PREVENTION_TOUT:
+		if (!bp->max_pfcwd_tmo_ms)
+			return -EOPNOTSUPP;
+		return bnxt_hwrm_pfcwd_qcfg(bp, data);
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static int bnxt_read_sfp_module_eeprom_info(struct bnxt *bp, u16 i2c_addr,
 					    u16 page_number, u8 bank,
 					    u16 start_addr, u16 data_length,
@@ -4463,6 +4626,11 @@ static int bnxt_get_module_status(struct bnxt *bp, struct netlink_ext_ack *extac
 	    PORT_PHY_QCFG_RESP_MODULE_STATUS_WARNINGMSG)
 		return 0;
 
+	if (bp->link_info.phy_type == PORT_PHY_QCFG_RESP_PHY_TYPE_BASET ||
+	    bp->link_info.phy_type == PORT_PHY_QCFG_RESP_PHY_TYPE_BASETE){
+		NL_SET_ERR_MSG_MOD(extack, "Operation not supported as PHY type is Base-T");
+		return -EOPNOTSUPP;
+	}
 	switch (bp->link_info.module_status) {
 	case PORT_PHY_QCFG_RESP_MODULE_STATUS_PWRDOWN:
 		NL_SET_ERR_MSG_MOD(extack, "Transceiver module is powering down");
@@ -4480,16 +4648,16 @@ static int bnxt_get_module_status(struct bnxt *bp, struct netlink_ext_ack *extac
 	return -EINVAL;
 }
 
-static int bnxt_get_module_eeprom_by_page(struct net_device *dev,
-					  const struct ethtool_module_eeprom *page_data,
-					  struct netlink_ext_ack *extack)
+static int
+bnxt_mod_eeprom_by_page_precheck(struct bnxt *bp,
+				 const struct ethtool_module_eeprom *page_data,
+				 struct netlink_ext_ack *extack)
 {
-	struct bnxt *bp = netdev_priv(dev);
 	int rc;
 
 	if (BNXT_VF(bp) && !BNXT_VF_IS_TRUSTED(bp)) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "Module read not permitted on untrusted VF");
+				   "Module read/write not permitted on untrusted VF");
 		return -EPERM;
 	}
 
@@ -4506,6 +4674,19 @@ static int bnxt_get_module_eeprom_by_page(struct net_device *dev,
 		NL_SET_ERR_MSG_MOD(extack, "Firmware not capable for bank selection");
 		return -EINVAL;
 	}
+	return 0;
+}
+
+static int bnxt_get_module_eeprom_by_page(struct net_device *dev,
+					  const struct ethtool_module_eeprom *page_data,
+					  struct netlink_ext_ack *extack)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	int rc;
+
+	rc = bnxt_mod_eeprom_by_page_precheck(bp, page_data, extack);
+	if (rc)
+		return rc;
 
 	rc = bnxt_read_sfp_module_eeprom_info(bp, page_data->i2c_address << 1,
 					      page_data->page, page_data->bank,
@@ -4519,6 +4700,62 @@ static int bnxt_get_module_eeprom_by_page(struct net_device *dev,
 	return page_data->length;
 }
 
+static int bnxt_write_sfp_module_eeprom_info(struct bnxt *bp,
+					     const struct ethtool_module_eeprom *page)
+{
+	struct hwrm_port_phy_i2c_write_input *req;
+	int bytes_written = 0;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_I2C_WRITE);
+	if (rc)
+		return rc;
+
+	hwrm_req_hold(bp, req);
+	req->i2c_slave_addr = page->i2c_address << 1;
+	req->page_number = cpu_to_le16(page->page);
+	req->bank_number = page->bank;
+	req->port_id = cpu_to_le16(bp->pf.port_id);
+	req->enables = cpu_to_le32(PORT_PHY_I2C_WRITE_REQ_ENABLES_PAGE_OFFSET |
+				   PORT_PHY_I2C_WRITE_REQ_ENABLES_BANK_NUMBER);
+
+	while (bytes_written < page->length) {
+		u16 xfer_size;
+
+		xfer_size = min_t(u16, page->length - bytes_written,
+				  BNXT_MAX_PHY_I2C_RESP_SIZE);
+		req->page_offset = cpu_to_le16(page->offset + bytes_written);
+		req->data_length = xfer_size;
+		memcpy(req->data, page->data + bytes_written, xfer_size);
+		rc = hwrm_req_send(bp, req);
+		if (rc)
+			break;
+		bytes_written += xfer_size;
+	}
+
+	hwrm_req_drop(bp, req);
+	return rc;
+}
+
+static int bnxt_set_module_eeprom_by_page(struct net_device *dev,
+					  const struct ethtool_module_eeprom *page_data,
+					  struct netlink_ext_ack *extack)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	int rc;
+
+	rc = bnxt_mod_eeprom_by_page_precheck(bp, page_data, extack);
+	if (rc)
+		return rc;
+
+	rc = bnxt_write_sfp_module_eeprom_info(bp, page_data);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Module`s eeprom write failed");
+		return rc;
+	}
+	return page_data->length;
+}
+
 static int bnxt_nway_reset(struct net_device *dev)
 {
 	int rc = 0;
@@ -4790,7 +5027,8 @@ static int bnxt_run_loopback(struct bnxt *bp)
 	cpr = &rxr->bnapi->cp_ring;
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		cpr = rxr->rx_cpr;
-	pkt_size = min(bp->dev->mtu + ETH_HLEN, bp->rx_copy_thresh);
+	pkt_size = min(bp->dev->mtu + ETH_HLEN, max(BNXT_DEFAULT_RX_COPYBREAK,
+						    bp->rx_copybreak));
 	skb = netdev_alloc_skb(bp->dev, pkt_size);
 	if (!skb)
 		return -ENOMEM;
@@ -4860,6 +5098,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 	if (!bp->num_tests || !BNXT_PF(bp))
 		return;
 
+	memset(buf, 0, sizeof(u64) * bp->num_tests);
 	if (etest->flags & ETH_TEST_FL_OFFLINE &&
 	    bnxt_ulp_registered(bp->edev)) {
 		etest->flags |= ETH_TEST_FL_FAILED;
@@ -4867,7 +5106,6 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 		return;
 	}
 
-	memset(buf, 0, sizeof(u64) * bp->num_tests);
 	if (!netif_running(dev)) {
 		etest->flags |= ETH_TEST_FL_FAILED;
 		return;
@@ -5015,8 +5253,9 @@ static int bnxt_set_dump(struct net_device *dev, struct ethtool_dump *dump)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (dump->flag > BNXT_DUMP_DRIVER) {
-		netdev_info(dev, "Supports only Live(0), Crash(1), Driver(2) dumps.\n");
+	if (dump->flag > BNXT_DUMP_LIVE_WITH_CTX_L1_CACHE) {
+		netdev_info(dev,
+			    "Supports only Live(0), Crash(1), Driver(2), Live with cached context(3) dumps.\n");
 		return -EINVAL;
 	}
 
@@ -5096,6 +5335,26 @@ static int bnxt_get_ts_info(struct net_device *dev,
 	return 0;
 }
 
+static void bnxt_hwrm_pcie_qstats(struct bnxt *bp)
+{
+	struct hwrm_pcie_qstats_output *resp;
+	struct hwrm_pcie_qstats_input *req;
+
+	bp->pcie_stat_len = 0;
+	if (!(bp->fw_cap & BNXT_FW_CAP_PCIE_STATS_SUPPORTED))
+		return;
+
+	if (hwrm_req_init(bp, req, HWRM_PCIE_QSTATS))
+		return;
+
+	resp = hwrm_req_hold(bp, req);
+	if (__bnxt_hwrm_pcie_qstats(bp, req))
+		bp->pcie_stat_len = min_t(u16,
+					  le16_to_cpu(resp->pcie_stat_size),
+					  sizeof(struct pcie_ctx_hw_stats_v2));
+	hwrm_req_drop(bp, req);
+}
+
 void bnxt_ethtool_init(struct bnxt *bp)
 {
 	struct hwrm_selftest_qlist_output *resp;
@@ -5104,6 +5363,7 @@ void bnxt_ethtool_init(struct bnxt *bp)
 	struct net_device *dev = bp->dev;
 	int i, rc;
 
+	bnxt_hwrm_pcie_qstats(bp);
 	if (!(bp->fw_cap & BNXT_FW_CAP_PKG_VER))
 		bnxt_get_pkgver(dev);
 
@@ -5331,6 +5591,8 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 				     ETHTOOL_COALESCE_STATS_BLOCK_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX |
 				     ETHTOOL_COALESCE_USE_CQE,
+	.supported_ring_params	= ETHTOOL_RING_USE_TCP_DATA_SPLIT |
+				  ETHTOOL_RING_USE_HDS_THRS,
 	.get_link_ksettings	= bnxt_get_link_ksettings,
 	.set_link_ksettings	= bnxt_set_link_ksettings,
 	.get_fec_stats		= bnxt_get_fec_stats,
@@ -5357,10 +5619,13 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 	.set_channels		= bnxt_set_channels,
 	.get_rxnfc		= bnxt_get_rxnfc,
 	.set_rxnfc		= bnxt_set_rxnfc,
+	.get_rx_ring_count	= bnxt_get_rx_ring_count,
 	.get_rxfh_indir_size    = bnxt_get_rxfh_indir_size,
 	.get_rxfh_key_size      = bnxt_get_rxfh_key_size,
 	.get_rxfh               = bnxt_get_rxfh,
 	.set_rxfh		= bnxt_set_rxfh,
+	.get_rxfh_fields        = bnxt_get_rxfh_fields,
+	.set_rxfh_fields        = bnxt_set_rxfh_fields,
 	.create_rxfh_context	= bnxt_create_rxfh_context,
 	.modify_rxfh_context	= bnxt_modify_rxfh_context,
 	.remove_rxfh_context	= bnxt_remove_rxfh_context,
@@ -5372,9 +5637,12 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 	.get_link_ext_stats	= bnxt_get_link_ext_stats,
 	.get_eee		= bnxt_get_eee,
 	.set_eee		= bnxt_set_eee,
+	.get_tunable		= bnxt_get_tunable,
+	.set_tunable		= bnxt_set_tunable,
 	.get_module_info	= bnxt_get_module_info,
 	.get_module_eeprom	= bnxt_get_module_eeprom,
 	.get_module_eeprom_by_page = bnxt_get_module_eeprom_by_page,
+	.set_module_eeprom_by_page = bnxt_set_module_eeprom_by_page,
 	.nway_reset		= bnxt_nway_reset,
 	.set_phys_id		= bnxt_set_phys_id,
 	.self_test		= bnxt_self_test,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
deleted file mode 100644
index 5f8de1634378..000000000000
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ /dev/null
@@ -1,10819 +0,0 @@
-/* Broadcom NetXtreme-C/E network driver.
- *
- * Copyright (c) 2014-2016 Broadcom Corporation
- * Copyright (c) 2014-2018 Broadcom Limited
- * Copyright (c) 2018-2024 Broadcom Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation.
- *
- * DO NOT MODIFY!!! This file is automatically generated.
- */
-
-#ifndef _BNXT_HSI_H_
-#define _BNXT_HSI_H_
-
-/* hwrm_cmd_hdr (size:128b/16B) */
-struct hwrm_cmd_hdr {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_resp_hdr (size:64b/8B) */
-struct hwrm_resp_hdr {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-};
-
-#define CMD_DISCR_TLV_ENCAP 0x8000UL
-#define CMD_DISCR_LAST     CMD_DISCR_TLV_ENCAP
-
-
-#define TLV_TYPE_HWRM_REQUEST                    0x1UL
-#define TLV_TYPE_HWRM_RESPONSE                   0x2UL
-#define TLV_TYPE_ROCE_SP_COMMAND                 0x3UL
-#define TLV_TYPE_QUERY_ROCE_CC_GEN1              0x4UL
-#define TLV_TYPE_MODIFY_ROCE_CC_GEN1             0x5UL
-#define TLV_TYPE_QUERY_ROCE_CC_GEN2              0x6UL
-#define TLV_TYPE_MODIFY_ROCE_CC_GEN2             0x7UL
-#define TLV_TYPE_QUERY_ROCE_CC_GEN1_EXT          0x8UL
-#define TLV_TYPE_MODIFY_ROCE_CC_GEN1_EXT         0x9UL
-#define TLV_TYPE_QUERY_ROCE_CC_GEN2_EXT          0xaUL
-#define TLV_TYPE_MODIFY_ROCE_CC_GEN2_EXT         0xbUL
-#define TLV_TYPE_ENGINE_CKV_ALIAS_ECC_PUBLIC_KEY 0x8001UL
-#define TLV_TYPE_ENGINE_CKV_IV                   0x8003UL
-#define TLV_TYPE_ENGINE_CKV_AUTH_TAG             0x8004UL
-#define TLV_TYPE_ENGINE_CKV_CIPHERTEXT           0x8005UL
-#define TLV_TYPE_ENGINE_CKV_HOST_ALGORITHMS      0x8006UL
-#define TLV_TYPE_ENGINE_CKV_HOST_ECC_PUBLIC_KEY  0x8007UL
-#define TLV_TYPE_ENGINE_CKV_ECDSA_SIGNATURE      0x8008UL
-#define TLV_TYPE_ENGINE_CKV_FW_ECC_PUBLIC_KEY    0x8009UL
-#define TLV_TYPE_ENGINE_CKV_FW_ALGORITHMS        0x800aUL
-#define TLV_TYPE_LAST                           TLV_TYPE_ENGINE_CKV_FW_ALGORITHMS
-
-
-/* tlv (size:64b/8B) */
-struct tlv {
-	__le16	cmd_discr;
-	u8	reserved_8b;
-	u8	flags;
-	#define TLV_FLAGS_MORE         0x1UL
-	#define TLV_FLAGS_MORE_LAST      0x0UL
-	#define TLV_FLAGS_MORE_NOT_LAST  0x1UL
-	#define TLV_FLAGS_REQUIRED     0x2UL
-	#define TLV_FLAGS_REQUIRED_NO    (0x0UL << 1)
-	#define TLV_FLAGS_REQUIRED_YES   (0x1UL << 1)
-	#define TLV_FLAGS_REQUIRED_LAST TLV_FLAGS_REQUIRED_YES
-	__le16	tlv_type;
-	__le16	length;
-};
-
-/* input (size:128b/16B) */
-struct input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* output (size:64b/8B) */
-struct output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-};
-
-/* hwrm_short_input (size:128b/16B) */
-struct hwrm_short_input {
-	__le16	req_type;
-	__le16	signature;
-	#define SHORT_REQ_SIGNATURE_SHORT_CMD 0x4321UL
-	#define SHORT_REQ_SIGNATURE_LAST     SHORT_REQ_SIGNATURE_SHORT_CMD
-	__le16	target_id;
-	#define SHORT_REQ_TARGET_ID_DEFAULT 0x0UL
-	#define SHORT_REQ_TARGET_ID_TOOLS   0xfffdUL
-	#define SHORT_REQ_TARGET_ID_LAST   SHORT_REQ_TARGET_ID_TOOLS
-	__le16	size;
-	__le64	req_addr;
-};
-
-/* cmd_nums (size:64b/8B) */
-struct cmd_nums {
-	__le16	req_type;
-	#define HWRM_VER_GET                              0x0UL
-	#define HWRM_FUNC_ECHO_RESPONSE                   0xbUL
-	#define HWRM_ERROR_RECOVERY_QCFG                  0xcUL
-	#define HWRM_FUNC_DRV_IF_CHANGE                   0xdUL
-	#define HWRM_FUNC_BUF_UNRGTR                      0xeUL
-	#define HWRM_FUNC_VF_CFG                          0xfUL
-	#define HWRM_RESERVED1                            0x10UL
-	#define HWRM_FUNC_RESET                           0x11UL
-	#define HWRM_FUNC_GETFID                          0x12UL
-	#define HWRM_FUNC_VF_ALLOC                        0x13UL
-	#define HWRM_FUNC_VF_FREE                         0x14UL
-	#define HWRM_FUNC_QCAPS                           0x15UL
-	#define HWRM_FUNC_QCFG                            0x16UL
-	#define HWRM_FUNC_CFG                             0x17UL
-	#define HWRM_FUNC_QSTATS                          0x18UL
-	#define HWRM_FUNC_CLR_STATS                       0x19UL
-	#define HWRM_FUNC_DRV_UNRGTR                      0x1aUL
-	#define HWRM_FUNC_VF_RESC_FREE                    0x1bUL
-	#define HWRM_FUNC_VF_VNIC_IDS_QUERY               0x1cUL
-	#define HWRM_FUNC_DRV_RGTR                        0x1dUL
-	#define HWRM_FUNC_DRV_QVER                        0x1eUL
-	#define HWRM_FUNC_BUF_RGTR                        0x1fUL
-	#define HWRM_PORT_PHY_CFG                         0x20UL
-	#define HWRM_PORT_MAC_CFG                         0x21UL
-	#define HWRM_PORT_TS_QUERY                        0x22UL
-	#define HWRM_PORT_QSTATS                          0x23UL
-	#define HWRM_PORT_LPBK_QSTATS                     0x24UL
-	#define HWRM_PORT_CLR_STATS                       0x25UL
-	#define HWRM_PORT_LPBK_CLR_STATS                  0x26UL
-	#define HWRM_PORT_PHY_QCFG                        0x27UL
-	#define HWRM_PORT_MAC_QCFG                        0x28UL
-	#define HWRM_PORT_MAC_PTP_QCFG                    0x29UL
-	#define HWRM_PORT_PHY_QCAPS                       0x2aUL
-	#define HWRM_PORT_PHY_I2C_WRITE                   0x2bUL
-	#define HWRM_PORT_PHY_I2C_READ                    0x2cUL
-	#define HWRM_PORT_LED_CFG                         0x2dUL
-	#define HWRM_PORT_LED_QCFG                        0x2eUL
-	#define HWRM_PORT_LED_QCAPS                       0x2fUL
-	#define HWRM_QUEUE_QPORTCFG                       0x30UL
-	#define HWRM_QUEUE_QCFG                           0x31UL
-	#define HWRM_QUEUE_CFG                            0x32UL
-	#define HWRM_FUNC_VLAN_CFG                        0x33UL
-	#define HWRM_FUNC_VLAN_QCFG                       0x34UL
-	#define HWRM_QUEUE_PFCENABLE_QCFG                 0x35UL
-	#define HWRM_QUEUE_PFCENABLE_CFG                  0x36UL
-	#define HWRM_QUEUE_PRI2COS_QCFG                   0x37UL
-	#define HWRM_QUEUE_PRI2COS_CFG                    0x38UL
-	#define HWRM_QUEUE_COS2BW_QCFG                    0x39UL
-	#define HWRM_QUEUE_COS2BW_CFG                     0x3aUL
-	#define HWRM_QUEUE_DSCP_QCAPS                     0x3bUL
-	#define HWRM_QUEUE_DSCP2PRI_QCFG                  0x3cUL
-	#define HWRM_QUEUE_DSCP2PRI_CFG                   0x3dUL
-	#define HWRM_VNIC_ALLOC                           0x40UL
-	#define HWRM_VNIC_FREE                            0x41UL
-	#define HWRM_VNIC_CFG                             0x42UL
-	#define HWRM_VNIC_QCFG                            0x43UL
-	#define HWRM_VNIC_TPA_CFG                         0x44UL
-	#define HWRM_VNIC_TPA_QCFG                        0x45UL
-	#define HWRM_VNIC_RSS_CFG                         0x46UL
-	#define HWRM_VNIC_RSS_QCFG                        0x47UL
-	#define HWRM_VNIC_PLCMODES_CFG                    0x48UL
-	#define HWRM_VNIC_PLCMODES_QCFG                   0x49UL
-	#define HWRM_VNIC_QCAPS                           0x4aUL
-	#define HWRM_VNIC_UPDATE                          0x4bUL
-	#define HWRM_RING_ALLOC                           0x50UL
-	#define HWRM_RING_FREE                            0x51UL
-	#define HWRM_RING_CMPL_RING_QAGGINT_PARAMS        0x52UL
-	#define HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS     0x53UL
-	#define HWRM_RING_AGGINT_QCAPS                    0x54UL
-	#define HWRM_RING_SCHQ_ALLOC                      0x55UL
-	#define HWRM_RING_SCHQ_CFG                        0x56UL
-	#define HWRM_RING_SCHQ_FREE                       0x57UL
-	#define HWRM_RING_RESET                           0x5eUL
-	#define HWRM_RING_GRP_ALLOC                       0x60UL
-	#define HWRM_RING_GRP_FREE                        0x61UL
-	#define HWRM_RING_CFG                             0x62UL
-	#define HWRM_RING_QCFG                            0x63UL
-	#define HWRM_RESERVED5                            0x64UL
-	#define HWRM_RESERVED6                            0x65UL
-	#define HWRM_VNIC_RSS_COS_LB_CTX_ALLOC            0x70UL
-	#define HWRM_VNIC_RSS_COS_LB_CTX_FREE             0x71UL
-	#define HWRM_QUEUE_MPLS_QCAPS                     0x80UL
-	#define HWRM_QUEUE_MPLSTC2PRI_QCFG                0x81UL
-	#define HWRM_QUEUE_MPLSTC2PRI_CFG                 0x82UL
-	#define HWRM_QUEUE_VLANPRI_QCAPS                  0x83UL
-	#define HWRM_QUEUE_VLANPRI2PRI_QCFG               0x84UL
-	#define HWRM_QUEUE_VLANPRI2PRI_CFG                0x85UL
-	#define HWRM_QUEUE_GLOBAL_CFG                     0x86UL
-	#define HWRM_QUEUE_GLOBAL_QCFG                    0x87UL
-	#define HWRM_QUEUE_ADPTV_QOS_RX_FEATURE_QCFG      0x88UL
-	#define HWRM_QUEUE_ADPTV_QOS_RX_FEATURE_CFG       0x89UL
-	#define HWRM_QUEUE_ADPTV_QOS_TX_FEATURE_QCFG      0x8aUL
-	#define HWRM_QUEUE_ADPTV_QOS_TX_FEATURE_CFG       0x8bUL
-	#define HWRM_QUEUE_QCAPS                          0x8cUL
-	#define HWRM_QUEUE_ADPTV_QOS_RX_TUNING_QCFG       0x8dUL
-	#define HWRM_QUEUE_ADPTV_QOS_RX_TUNING_CFG        0x8eUL
-	#define HWRM_QUEUE_ADPTV_QOS_TX_TUNING_QCFG       0x8fUL
-	#define HWRM_CFA_L2_FILTER_ALLOC                  0x90UL
-	#define HWRM_CFA_L2_FILTER_FREE                   0x91UL
-	#define HWRM_CFA_L2_FILTER_CFG                    0x92UL
-	#define HWRM_CFA_L2_SET_RX_MASK                   0x93UL
-	#define HWRM_CFA_VLAN_ANTISPOOF_CFG               0x94UL
-	#define HWRM_CFA_TUNNEL_FILTER_ALLOC              0x95UL
-	#define HWRM_CFA_TUNNEL_FILTER_FREE               0x96UL
-	#define HWRM_CFA_ENCAP_RECORD_ALLOC               0x97UL
-	#define HWRM_CFA_ENCAP_RECORD_FREE                0x98UL
-	#define HWRM_CFA_NTUPLE_FILTER_ALLOC              0x99UL
-	#define HWRM_CFA_NTUPLE_FILTER_FREE               0x9aUL
-	#define HWRM_CFA_NTUPLE_FILTER_CFG                0x9bUL
-	#define HWRM_CFA_EM_FLOW_ALLOC                    0x9cUL
-	#define HWRM_CFA_EM_FLOW_FREE                     0x9dUL
-	#define HWRM_CFA_EM_FLOW_CFG                      0x9eUL
-	#define HWRM_TUNNEL_DST_PORT_QUERY                0xa0UL
-	#define HWRM_TUNNEL_DST_PORT_ALLOC                0xa1UL
-	#define HWRM_TUNNEL_DST_PORT_FREE                 0xa2UL
-	#define HWRM_QUEUE_ADPTV_QOS_TX_TUNING_CFG        0xa3UL
-	#define HWRM_STAT_CTX_ENG_QUERY                   0xafUL
-	#define HWRM_STAT_CTX_ALLOC                       0xb0UL
-	#define HWRM_STAT_CTX_FREE                        0xb1UL
-	#define HWRM_STAT_CTX_QUERY                       0xb2UL
-	#define HWRM_STAT_CTX_CLR_STATS                   0xb3UL
-	#define HWRM_PORT_QSTATS_EXT                      0xb4UL
-	#define HWRM_PORT_PHY_MDIO_WRITE                  0xb5UL
-	#define HWRM_PORT_PHY_MDIO_READ                   0xb6UL
-	#define HWRM_PORT_PHY_MDIO_BUS_ACQUIRE            0xb7UL
-	#define HWRM_PORT_PHY_MDIO_BUS_RELEASE            0xb8UL
-	#define HWRM_PORT_QSTATS_EXT_PFC_WD               0xb9UL
-	#define HWRM_RESERVED7                            0xbaUL
-	#define HWRM_PORT_TX_FIR_CFG                      0xbbUL
-	#define HWRM_PORT_TX_FIR_QCFG                     0xbcUL
-	#define HWRM_PORT_ECN_QSTATS                      0xbdUL
-	#define HWRM_FW_LIVEPATCH_QUERY                   0xbeUL
-	#define HWRM_FW_LIVEPATCH                         0xbfUL
-	#define HWRM_FW_RESET                             0xc0UL
-	#define HWRM_FW_QSTATUS                           0xc1UL
-	#define HWRM_FW_HEALTH_CHECK                      0xc2UL
-	#define HWRM_FW_SYNC                              0xc3UL
-	#define HWRM_FW_STATE_QCAPS                       0xc4UL
-	#define HWRM_FW_STATE_QUIESCE                     0xc5UL
-	#define HWRM_FW_STATE_BACKUP                      0xc6UL
-	#define HWRM_FW_STATE_RESTORE                     0xc7UL
-	#define HWRM_FW_SET_TIME                          0xc8UL
-	#define HWRM_FW_GET_TIME                          0xc9UL
-	#define HWRM_FW_SET_STRUCTURED_DATA               0xcaUL
-	#define HWRM_FW_GET_STRUCTURED_DATA               0xcbUL
-	#define HWRM_FW_IPC_MAILBOX                       0xccUL
-	#define HWRM_FW_ECN_CFG                           0xcdUL
-	#define HWRM_FW_ECN_QCFG                          0xceUL
-	#define HWRM_FW_SECURE_CFG                        0xcfUL
-	#define HWRM_EXEC_FWD_RESP                        0xd0UL
-	#define HWRM_REJECT_FWD_RESP                      0xd1UL
-	#define HWRM_FWD_RESP                             0xd2UL
-	#define HWRM_FWD_ASYNC_EVENT_CMPL                 0xd3UL
-	#define HWRM_OEM_CMD                              0xd4UL
-	#define HWRM_PORT_PRBS_TEST                       0xd5UL
-	#define HWRM_PORT_SFP_SIDEBAND_CFG                0xd6UL
-	#define HWRM_PORT_SFP_SIDEBAND_QCFG               0xd7UL
-	#define HWRM_FW_STATE_UNQUIESCE                   0xd8UL
-	#define HWRM_PORT_DSC_DUMP                        0xd9UL
-	#define HWRM_PORT_EP_TX_QCFG                      0xdaUL
-	#define HWRM_PORT_EP_TX_CFG                       0xdbUL
-	#define HWRM_PORT_CFG                             0xdcUL
-	#define HWRM_PORT_QCFG                            0xddUL
-	#define HWRM_PORT_MAC_QCAPS                       0xdfUL
-	#define HWRM_TEMP_MONITOR_QUERY                   0xe0UL
-	#define HWRM_REG_POWER_QUERY                      0xe1UL
-	#define HWRM_CORE_FREQUENCY_QUERY                 0xe2UL
-	#define HWRM_REG_POWER_HISTOGRAM                  0xe3UL
-	#define HWRM_WOL_FILTER_ALLOC                     0xf0UL
-	#define HWRM_WOL_FILTER_FREE                      0xf1UL
-	#define HWRM_WOL_FILTER_QCFG                      0xf2UL
-	#define HWRM_WOL_REASON_QCFG                      0xf3UL
-	#define HWRM_CFA_METER_QCAPS                      0xf4UL
-	#define HWRM_CFA_METER_PROFILE_ALLOC              0xf5UL
-	#define HWRM_CFA_METER_PROFILE_FREE               0xf6UL
-	#define HWRM_CFA_METER_PROFILE_CFG                0xf7UL
-	#define HWRM_CFA_METER_INSTANCE_ALLOC             0xf8UL
-	#define HWRM_CFA_METER_INSTANCE_FREE              0xf9UL
-	#define HWRM_CFA_METER_INSTANCE_CFG               0xfaUL
-	#define HWRM_CFA_VFR_ALLOC                        0xfdUL
-	#define HWRM_CFA_VFR_FREE                         0xfeUL
-	#define HWRM_CFA_VF_PAIR_ALLOC                    0x100UL
-	#define HWRM_CFA_VF_PAIR_FREE                     0x101UL
-	#define HWRM_CFA_VF_PAIR_INFO                     0x102UL
-	#define HWRM_CFA_FLOW_ALLOC                       0x103UL
-	#define HWRM_CFA_FLOW_FREE                        0x104UL
-	#define HWRM_CFA_FLOW_FLUSH                       0x105UL
-	#define HWRM_CFA_FLOW_STATS                       0x106UL
-	#define HWRM_CFA_FLOW_INFO                        0x107UL
-	#define HWRM_CFA_DECAP_FILTER_ALLOC               0x108UL
-	#define HWRM_CFA_DECAP_FILTER_FREE                0x109UL
-	#define HWRM_CFA_VLAN_ANTISPOOF_QCFG              0x10aUL
-	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_ALLOC       0x10bUL
-	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_FREE        0x10cUL
-	#define HWRM_CFA_PAIR_ALLOC                       0x10dUL
-	#define HWRM_CFA_PAIR_FREE                        0x10eUL
-	#define HWRM_CFA_PAIR_INFO                        0x10fUL
-	#define HWRM_FW_IPC_MSG                           0x110UL
-	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_INFO        0x111UL
-	#define HWRM_CFA_REDIRECT_QUERY_TUNNEL_TYPE       0x112UL
-	#define HWRM_CFA_FLOW_AGING_TIMER_RESET           0x113UL
-	#define HWRM_CFA_FLOW_AGING_CFG                   0x114UL
-	#define HWRM_CFA_FLOW_AGING_QCFG                  0x115UL
-	#define HWRM_CFA_FLOW_AGING_QCAPS                 0x116UL
-	#define HWRM_CFA_CTX_MEM_RGTR                     0x117UL
-	#define HWRM_CFA_CTX_MEM_UNRGTR                   0x118UL
-	#define HWRM_CFA_CTX_MEM_QCTX                     0x119UL
-	#define HWRM_CFA_CTX_MEM_QCAPS                    0x11aUL
-	#define HWRM_CFA_COUNTER_QCAPS                    0x11bUL
-	#define HWRM_CFA_COUNTER_CFG                      0x11cUL
-	#define HWRM_CFA_COUNTER_QCFG                     0x11dUL
-	#define HWRM_CFA_COUNTER_QSTATS                   0x11eUL
-	#define HWRM_CFA_TCP_FLAG_PROCESS_QCFG            0x11fUL
-	#define HWRM_CFA_EEM_QCAPS                        0x120UL
-	#define HWRM_CFA_EEM_CFG                          0x121UL
-	#define HWRM_CFA_EEM_QCFG                         0x122UL
-	#define HWRM_CFA_EEM_OP                           0x123UL
-	#define HWRM_CFA_ADV_FLOW_MGNT_QCAPS              0x124UL
-	#define HWRM_CFA_TFLIB                            0x125UL
-	#define HWRM_CFA_LAG_GROUP_MEMBER_RGTR            0x126UL
-	#define HWRM_CFA_LAG_GROUP_MEMBER_UNRGTR          0x127UL
-	#define HWRM_CFA_TLS_FILTER_ALLOC                 0x128UL
-	#define HWRM_CFA_TLS_FILTER_FREE                  0x129UL
-	#define HWRM_CFA_RELEASE_AFM_FUNC                 0x12aUL
-	#define HWRM_ENGINE_CKV_STATUS                    0x12eUL
-	#define HWRM_ENGINE_CKV_CKEK_ADD                  0x12fUL
-	#define HWRM_ENGINE_CKV_CKEK_DELETE               0x130UL
-	#define HWRM_ENGINE_CKV_KEY_ADD                   0x131UL
-	#define HWRM_ENGINE_CKV_KEY_DELETE                0x132UL
-	#define HWRM_ENGINE_CKV_FLUSH                     0x133UL
-	#define HWRM_ENGINE_CKV_RNG_GET                   0x134UL
-	#define HWRM_ENGINE_CKV_KEY_GEN                   0x135UL
-	#define HWRM_ENGINE_CKV_KEY_LABEL_CFG             0x136UL
-	#define HWRM_ENGINE_CKV_KEY_LABEL_QCFG            0x137UL
-	#define HWRM_ENGINE_QG_CONFIG_QUERY               0x13cUL
-	#define HWRM_ENGINE_QG_QUERY                      0x13dUL
-	#define HWRM_ENGINE_QG_METER_PROFILE_CONFIG_QUERY 0x13eUL
-	#define HWRM_ENGINE_QG_METER_PROFILE_QUERY        0x13fUL
-	#define HWRM_ENGINE_QG_METER_PROFILE_ALLOC        0x140UL
-	#define HWRM_ENGINE_QG_METER_PROFILE_FREE         0x141UL
-	#define HWRM_ENGINE_QG_METER_QUERY                0x142UL
-	#define HWRM_ENGINE_QG_METER_BIND                 0x143UL
-	#define HWRM_ENGINE_QG_METER_UNBIND               0x144UL
-	#define HWRM_ENGINE_QG_FUNC_BIND                  0x145UL
-	#define HWRM_ENGINE_SG_CONFIG_QUERY               0x146UL
-	#define HWRM_ENGINE_SG_QUERY                      0x147UL
-	#define HWRM_ENGINE_SG_METER_QUERY                0x148UL
-	#define HWRM_ENGINE_SG_METER_CONFIG               0x149UL
-	#define HWRM_ENGINE_SG_QG_BIND                    0x14aUL
-	#define HWRM_ENGINE_QG_SG_UNBIND                  0x14bUL
-	#define HWRM_ENGINE_CONFIG_QUERY                  0x154UL
-	#define HWRM_ENGINE_STATS_CONFIG                  0x155UL
-	#define HWRM_ENGINE_STATS_CLEAR                   0x156UL
-	#define HWRM_ENGINE_STATS_QUERY                   0x157UL
-	#define HWRM_ENGINE_STATS_QUERY_CONTINUOUS_ERROR  0x158UL
-	#define HWRM_ENGINE_RQ_ALLOC                      0x15eUL
-	#define HWRM_ENGINE_RQ_FREE                       0x15fUL
-	#define HWRM_ENGINE_CQ_ALLOC                      0x160UL
-	#define HWRM_ENGINE_CQ_FREE                       0x161UL
-	#define HWRM_ENGINE_NQ_ALLOC                      0x162UL
-	#define HWRM_ENGINE_NQ_FREE                       0x163UL
-	#define HWRM_ENGINE_ON_DIE_RQE_CREDITS            0x164UL
-	#define HWRM_ENGINE_FUNC_QCFG                     0x165UL
-	#define HWRM_FUNC_RESOURCE_QCAPS                  0x190UL
-	#define HWRM_FUNC_VF_RESOURCE_CFG                 0x191UL
-	#define HWRM_FUNC_BACKING_STORE_QCAPS             0x192UL
-	#define HWRM_FUNC_BACKING_STORE_CFG               0x193UL
-	#define HWRM_FUNC_BACKING_STORE_QCFG              0x194UL
-	#define HWRM_FUNC_VF_BW_CFG                       0x195UL
-	#define HWRM_FUNC_VF_BW_QCFG                      0x196UL
-	#define HWRM_FUNC_HOST_PF_IDS_QUERY               0x197UL
-	#define HWRM_FUNC_QSTATS_EXT                      0x198UL
-	#define HWRM_STAT_EXT_CTX_QUERY                   0x199UL
-	#define HWRM_FUNC_SPD_CFG                         0x19aUL
-	#define HWRM_FUNC_SPD_QCFG                        0x19bUL
-	#define HWRM_FUNC_PTP_PIN_QCFG                    0x19cUL
-	#define HWRM_FUNC_PTP_PIN_CFG                     0x19dUL
-	#define HWRM_FUNC_PTP_CFG                         0x19eUL
-	#define HWRM_FUNC_PTP_TS_QUERY                    0x19fUL
-	#define HWRM_FUNC_PTP_EXT_CFG                     0x1a0UL
-	#define HWRM_FUNC_PTP_EXT_QCFG                    0x1a1UL
-	#define HWRM_FUNC_KEY_CTX_ALLOC                   0x1a2UL
-	#define HWRM_FUNC_BACKING_STORE_CFG_V2            0x1a3UL
-	#define HWRM_FUNC_BACKING_STORE_QCFG_V2           0x1a4UL
-	#define HWRM_FUNC_DBR_PACING_CFG                  0x1a5UL
-	#define HWRM_FUNC_DBR_PACING_QCFG                 0x1a6UL
-	#define HWRM_FUNC_DBR_PACING_BROADCAST_EVENT      0x1a7UL
-	#define HWRM_FUNC_BACKING_STORE_QCAPS_V2          0x1a8UL
-	#define HWRM_FUNC_DBR_PACING_NQLIST_QUERY         0x1a9UL
-	#define HWRM_FUNC_DBR_RECOVERY_COMPLETED          0x1aaUL
-	#define HWRM_FUNC_SYNCE_CFG                       0x1abUL
-	#define HWRM_FUNC_SYNCE_QCFG                      0x1acUL
-	#define HWRM_FUNC_KEY_CTX_FREE                    0x1adUL
-	#define HWRM_FUNC_LAG_MODE_CFG                    0x1aeUL
-	#define HWRM_FUNC_LAG_MODE_QCFG                   0x1afUL
-	#define HWRM_FUNC_LAG_CREATE                      0x1b0UL
-	#define HWRM_FUNC_LAG_UPDATE                      0x1b1UL
-	#define HWRM_FUNC_LAG_FREE                        0x1b2UL
-	#define HWRM_FUNC_LAG_QCFG                        0x1b3UL
-	#define HWRM_FUNC_TIMEDTX_PACING_RATE_ADD         0x1c2UL
-	#define HWRM_FUNC_TIMEDTX_PACING_RATE_DELETE      0x1c3UL
-	#define HWRM_FUNC_TIMEDTX_PACING_RATE_QUERY       0x1c4UL
-	#define HWRM_SELFTEST_QLIST                       0x200UL
-	#define HWRM_SELFTEST_EXEC                        0x201UL
-	#define HWRM_SELFTEST_IRQ                         0x202UL
-	#define HWRM_SELFTEST_RETRIEVE_SERDES_DATA        0x203UL
-	#define HWRM_PCIE_QSTATS                          0x204UL
-	#define HWRM_MFG_FRU_WRITE_CONTROL                0x205UL
-	#define HWRM_MFG_TIMERS_QUERY                     0x206UL
-	#define HWRM_MFG_OTP_CFG                          0x207UL
-	#define HWRM_MFG_OTP_QCFG                         0x208UL
-	#define HWRM_MFG_HDMA_TEST                        0x209UL
-	#define HWRM_MFG_FRU_EEPROM_WRITE                 0x20aUL
-	#define HWRM_MFG_FRU_EEPROM_READ                  0x20bUL
-	#define HWRM_MFG_SOC_IMAGE                        0x20cUL
-	#define HWRM_MFG_SOC_QSTATUS                      0x20dUL
-	#define HWRM_MFG_PARAM_CRITICAL_DATA_FINALIZE     0x20eUL
-	#define HWRM_MFG_PARAM_CRITICAL_DATA_READ         0x20fUL
-	#define HWRM_MFG_PARAM_CRITICAL_DATA_HEALTH       0x210UL
-	#define HWRM_MFG_PRVSN_EXPORT_CSR                 0x211UL
-	#define HWRM_MFG_PRVSN_IMPORT_CERT                0x212UL
-	#define HWRM_MFG_PRVSN_GET_STATE                  0x213UL
-	#define HWRM_MFG_GET_NVM_MEASUREMENT              0x214UL
-	#define HWRM_MFG_PSOC_QSTATUS                     0x215UL
-	#define HWRM_MFG_SELFTEST_QLIST                   0x216UL
-	#define HWRM_MFG_SELFTEST_EXEC                    0x217UL
-	#define HWRM_STAT_GENERIC_QSTATS                  0x218UL
-	#define HWRM_MFG_PRVSN_EXPORT_CERT                0x219UL
-	#define HWRM_STAT_DB_ERROR_QSTATS                 0x21aUL
-	#define HWRM_MFG_TESTS                            0x21bUL
-	#define HWRM_PORT_POE_CFG                         0x230UL
-	#define HWRM_PORT_POE_QCFG                        0x231UL
-	#define HWRM_UDCC_QCAPS                           0x258UL
-	#define HWRM_UDCC_CFG                             0x259UL
-	#define HWRM_UDCC_QCFG                            0x25aUL
-	#define HWRM_UDCC_SESSION_CFG                     0x25bUL
-	#define HWRM_UDCC_SESSION_QCFG                    0x25cUL
-	#define HWRM_UDCC_SESSION_QUERY                   0x25dUL
-	#define HWRM_UDCC_COMP_CFG                        0x25eUL
-	#define HWRM_UDCC_COMP_QCFG                       0x25fUL
-	#define HWRM_UDCC_COMP_QUERY                      0x260UL
-	#define HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS            0x261UL
-	#define HWRM_QUEUE_PFCWD_TIMEOUT_CFG              0x262UL
-	#define HWRM_QUEUE_PFCWD_TIMEOUT_QCFG             0x263UL
-	#define HWRM_TF                                   0x2bcUL
-	#define HWRM_TF_VERSION_GET                       0x2bdUL
-	#define HWRM_TF_SESSION_OPEN                      0x2c6UL
-	#define HWRM_TF_SESSION_REGISTER                  0x2c8UL
-	#define HWRM_TF_SESSION_UNREGISTER                0x2c9UL
-	#define HWRM_TF_SESSION_CLOSE                     0x2caUL
-	#define HWRM_TF_SESSION_QCFG                      0x2cbUL
-	#define HWRM_TF_SESSION_RESC_QCAPS                0x2ccUL
-	#define HWRM_TF_SESSION_RESC_ALLOC                0x2cdUL
-	#define HWRM_TF_SESSION_RESC_FREE                 0x2ceUL
-	#define HWRM_TF_SESSION_RESC_FLUSH                0x2cfUL
-	#define HWRM_TF_SESSION_RESC_INFO                 0x2d0UL
-	#define HWRM_TF_SESSION_HOTUP_STATE_SET           0x2d1UL
-	#define HWRM_TF_SESSION_HOTUP_STATE_GET           0x2d2UL
-	#define HWRM_TF_TBL_TYPE_GET                      0x2daUL
-	#define HWRM_TF_TBL_TYPE_SET                      0x2dbUL
-	#define HWRM_TF_TBL_TYPE_BULK_GET                 0x2dcUL
-	#define HWRM_TF_EM_INSERT                         0x2eaUL
-	#define HWRM_TF_EM_DELETE                         0x2ebUL
-	#define HWRM_TF_EM_HASH_INSERT                    0x2ecUL
-	#define HWRM_TF_EM_MOVE                           0x2edUL
-	#define HWRM_TF_TCAM_SET                          0x2f8UL
-	#define HWRM_TF_TCAM_GET                          0x2f9UL
-	#define HWRM_TF_TCAM_MOVE                         0x2faUL
-	#define HWRM_TF_TCAM_FREE                         0x2fbUL
-	#define HWRM_TF_GLOBAL_CFG_SET                    0x2fcUL
-	#define HWRM_TF_GLOBAL_CFG_GET                    0x2fdUL
-	#define HWRM_TF_IF_TBL_SET                        0x2feUL
-	#define HWRM_TF_IF_TBL_GET                        0x2ffUL
-	#define HWRM_TF_RESC_USAGE_SET                    0x300UL
-	#define HWRM_TF_RESC_USAGE_QUERY                  0x301UL
-	#define HWRM_TF_TBL_TYPE_ALLOC                    0x302UL
-	#define HWRM_TF_TBL_TYPE_FREE                     0x303UL
-	#define HWRM_TFC_TBL_SCOPE_QCAPS                  0x380UL
-	#define HWRM_TFC_TBL_SCOPE_ID_ALLOC               0x381UL
-	#define HWRM_TFC_TBL_SCOPE_CONFIG                 0x382UL
-	#define HWRM_TFC_TBL_SCOPE_DECONFIG               0x383UL
-	#define HWRM_TFC_TBL_SCOPE_FID_ADD                0x384UL
-	#define HWRM_TFC_TBL_SCOPE_FID_REM                0x385UL
-	#define HWRM_TFC_TBL_SCOPE_POOL_ALLOC             0x386UL
-	#define HWRM_TFC_TBL_SCOPE_POOL_FREE              0x387UL
-	#define HWRM_TFC_SESSION_ID_ALLOC                 0x388UL
-	#define HWRM_TFC_SESSION_FID_ADD                  0x389UL
-	#define HWRM_TFC_SESSION_FID_REM                  0x38aUL
-	#define HWRM_TFC_IDENT_ALLOC                      0x38bUL
-	#define HWRM_TFC_IDENT_FREE                       0x38cUL
-	#define HWRM_TFC_IDX_TBL_ALLOC                    0x38dUL
-	#define HWRM_TFC_IDX_TBL_ALLOC_SET                0x38eUL
-	#define HWRM_TFC_IDX_TBL_SET                      0x38fUL
-	#define HWRM_TFC_IDX_TBL_GET                      0x390UL
-	#define HWRM_TFC_IDX_TBL_FREE                     0x391UL
-	#define HWRM_TFC_GLOBAL_ID_ALLOC                  0x392UL
-	#define HWRM_TFC_TCAM_SET                         0x393UL
-	#define HWRM_TFC_TCAM_GET                         0x394UL
-	#define HWRM_TFC_TCAM_ALLOC                       0x395UL
-	#define HWRM_TFC_TCAM_ALLOC_SET                   0x396UL
-	#define HWRM_TFC_TCAM_FREE                        0x397UL
-	#define HWRM_TFC_IF_TBL_SET                       0x398UL
-	#define HWRM_TFC_IF_TBL_GET                       0x399UL
-	#define HWRM_TFC_TBL_SCOPE_CONFIG_GET             0x39aUL
-	#define HWRM_TFC_RESC_USAGE_QUERY                 0x39bUL
-	#define HWRM_TFC_GLOBAL_ID_FREE                   0x39cUL
-	#define HWRM_SV                                   0x400UL
-	#define HWRM_DBG_SERDES_TEST                      0xff0eUL
-	#define HWRM_DBG_LOG_BUFFER_FLUSH                 0xff0fUL
-	#define HWRM_DBG_READ_DIRECT                      0xff10UL
-	#define HWRM_DBG_READ_INDIRECT                    0xff11UL
-	#define HWRM_DBG_WRITE_DIRECT                     0xff12UL
-	#define HWRM_DBG_WRITE_INDIRECT                   0xff13UL
-	#define HWRM_DBG_DUMP                             0xff14UL
-	#define HWRM_DBG_ERASE_NVM                        0xff15UL
-	#define HWRM_DBG_CFG                              0xff16UL
-	#define HWRM_DBG_COREDUMP_LIST                    0xff17UL
-	#define HWRM_DBG_COREDUMP_INITIATE                0xff18UL
-	#define HWRM_DBG_COREDUMP_RETRIEVE                0xff19UL
-	#define HWRM_DBG_FW_CLI                           0xff1aUL
-	#define HWRM_DBG_I2C_CMD                          0xff1bUL
-	#define HWRM_DBG_RING_INFO_GET                    0xff1cUL
-	#define HWRM_DBG_CRASHDUMP_HEADER                 0xff1dUL
-	#define HWRM_DBG_CRASHDUMP_ERASE                  0xff1eUL
-	#define HWRM_DBG_DRV_TRACE                        0xff1fUL
-	#define HWRM_DBG_QCAPS                            0xff20UL
-	#define HWRM_DBG_QCFG                             0xff21UL
-	#define HWRM_DBG_CRASHDUMP_MEDIUM_CFG             0xff22UL
-	#define HWRM_DBG_USEQ_ALLOC                       0xff23UL
-	#define HWRM_DBG_USEQ_FREE                        0xff24UL
-	#define HWRM_DBG_USEQ_FLUSH                       0xff25UL
-	#define HWRM_DBG_USEQ_QCAPS                       0xff26UL
-	#define HWRM_DBG_USEQ_CW_CFG                      0xff27UL
-	#define HWRM_DBG_USEQ_SCHED_CFG                   0xff28UL
-	#define HWRM_DBG_USEQ_RUN                         0xff29UL
-	#define HWRM_DBG_USEQ_DELIVERY_REQ                0xff2aUL
-	#define HWRM_DBG_USEQ_RESP_HDR                    0xff2bUL
-	#define HWRM_DBG_COREDUMP_CAPTURE                 0xff2cUL
-	#define HWRM_DBG_PTRACE                           0xff2dUL
-	#define HWRM_DBG_SIM_CABLE_STATE                  0xff2eUL
-	#define HWRM_NVM_GET_VPD_FIELD_INFO               0xffeaUL
-	#define HWRM_NVM_SET_VPD_FIELD_INFO               0xffebUL
-	#define HWRM_NVM_DEFRAG                           0xffecUL
-	#define HWRM_NVM_REQ_ARBITRATION                  0xffedUL
-	#define HWRM_NVM_FACTORY_DEFAULTS                 0xffeeUL
-	#define HWRM_NVM_VALIDATE_OPTION                  0xffefUL
-	#define HWRM_NVM_FLUSH                            0xfff0UL
-	#define HWRM_NVM_GET_VARIABLE                     0xfff1UL
-	#define HWRM_NVM_SET_VARIABLE                     0xfff2UL
-	#define HWRM_NVM_INSTALL_UPDATE                   0xfff3UL
-	#define HWRM_NVM_MODIFY                           0xfff4UL
-	#define HWRM_NVM_VERIFY_UPDATE                    0xfff5UL
-	#define HWRM_NVM_GET_DEV_INFO                     0xfff6UL
-	#define HWRM_NVM_ERASE_DIR_ENTRY                  0xfff7UL
-	#define HWRM_NVM_MOD_DIR_ENTRY                    0xfff8UL
-	#define HWRM_NVM_FIND_DIR_ENTRY                   0xfff9UL
-	#define HWRM_NVM_GET_DIR_ENTRIES                  0xfffaUL
-	#define HWRM_NVM_GET_DIR_INFO                     0xfffbUL
-	#define HWRM_NVM_RAW_DUMP                         0xfffcUL
-	#define HWRM_NVM_READ                             0xfffdUL
-	#define HWRM_NVM_WRITE                            0xfffeUL
-	#define HWRM_NVM_RAW_WRITE_BLK                    0xffffUL
-	#define HWRM_LAST                                HWRM_NVM_RAW_WRITE_BLK
-	__le16	unused_0[3];
-};
-
-/* ret_codes (size:64b/8B) */
-struct ret_codes {
-	__le16	error_code;
-	#define HWRM_ERR_CODE_SUCCESS                      0x0UL
-	#define HWRM_ERR_CODE_FAIL                         0x1UL
-	#define HWRM_ERR_CODE_INVALID_PARAMS               0x2UL
-	#define HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED       0x3UL
-	#define HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR         0x4UL
-	#define HWRM_ERR_CODE_INVALID_FLAGS                0x5UL
-	#define HWRM_ERR_CODE_INVALID_ENABLES              0x6UL
-	#define HWRM_ERR_CODE_UNSUPPORTED_TLV              0x7UL
-	#define HWRM_ERR_CODE_NO_BUFFER                    0x8UL
-	#define HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR       0x9UL
-	#define HWRM_ERR_CODE_HOT_RESET_PROGRESS           0xaUL
-	#define HWRM_ERR_CODE_HOT_RESET_FAIL               0xbUL
-	#define HWRM_ERR_CODE_NO_FLOW_COUNTER_DURING_ALLOC 0xcUL
-	#define HWRM_ERR_CODE_KEY_HASH_COLLISION           0xdUL
-	#define HWRM_ERR_CODE_KEY_ALREADY_EXISTS           0xeUL
-	#define HWRM_ERR_CODE_HWRM_ERROR                   0xfUL
-	#define HWRM_ERR_CODE_BUSY                         0x10UL
-	#define HWRM_ERR_CODE_RESOURCE_LOCKED              0x11UL
-	#define HWRM_ERR_CODE_PF_UNAVAILABLE               0x12UL
-	#define HWRM_ERR_CODE_ENTITY_NOT_PRESENT           0x13UL
-	#define HWRM_ERR_CODE_SECURE_SOC_ERROR             0x14UL
-	#define HWRM_ERR_CODE_TLV_ENCAPSULATED_RESPONSE    0x8000UL
-	#define HWRM_ERR_CODE_UNKNOWN_ERR                  0xfffeUL
-	#define HWRM_ERR_CODE_CMD_NOT_SUPPORTED            0xffffUL
-	#define HWRM_ERR_CODE_LAST                        HWRM_ERR_CODE_CMD_NOT_SUPPORTED
-	__le16	unused_0[3];
-};
-
-/* hwrm_err_output (size:128b/16B) */
-struct hwrm_err_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	opaque_0;
-	__le16	opaque_1;
-	u8	cmd_err;
-	u8	valid;
-};
-#define HWRM_NA_SIGNATURE ((__le32)(-1))
-#define HWRM_MAX_REQ_LEN 128
-#define HWRM_MAX_RESP_LEN 704
-#define HW_HASH_INDEX_SIZE 0x80
-#define HW_HASH_KEY_SIZE 40
-#define HWRM_RESP_VALID_KEY 1
-#define HWRM_TARGET_ID_BONO 0xFFF8
-#define HWRM_TARGET_ID_KONG 0xFFF9
-#define HWRM_TARGET_ID_APE 0xFFFA
-#define HWRM_TARGET_ID_TOOLS 0xFFFD
-#define HWRM_VERSION_MAJOR 1
-#define HWRM_VERSION_MINOR 10
-#define HWRM_VERSION_UPDATE 3
-#define HWRM_VERSION_RSVD 85
-#define HWRM_VERSION_STR "1.10.3.85"
-
-/* hwrm_ver_get_input (size:192b/24B) */
-struct hwrm_ver_get_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	hwrm_intf_maj;
-	u8	hwrm_intf_min;
-	u8	hwrm_intf_upd;
-	u8	unused_0[5];
-};
-
-/* hwrm_ver_get_output (size:1408b/176B) */
-struct hwrm_ver_get_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	hwrm_intf_maj_8b;
-	u8	hwrm_intf_min_8b;
-	u8	hwrm_intf_upd_8b;
-	u8	hwrm_intf_rsvd_8b;
-	u8	hwrm_fw_maj_8b;
-	u8	hwrm_fw_min_8b;
-	u8	hwrm_fw_bld_8b;
-	u8	hwrm_fw_rsvd_8b;
-	u8	mgmt_fw_maj_8b;
-	u8	mgmt_fw_min_8b;
-	u8	mgmt_fw_bld_8b;
-	u8	mgmt_fw_rsvd_8b;
-	u8	netctrl_fw_maj_8b;
-	u8	netctrl_fw_min_8b;
-	u8	netctrl_fw_bld_8b;
-	u8	netctrl_fw_rsvd_8b;
-	__le32	dev_caps_cfg;
-	#define VER_GET_RESP_DEV_CAPS_CFG_SECURE_FW_UPD_SUPPORTED                  0x1UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_FW_DCBX_AGENT_SUPPORTED                  0x2UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_SUPPORTED                      0x4UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_REQUIRED                       0x8UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_KONG_MB_CHNL_SUPPORTED                   0x10UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_FLOW_HANDLE_64BIT_SUPPORTED              0x20UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_L2_FILTER_TYPES_ROCE_OR_L2_SUPPORTED     0x40UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_VIRTIO_VSWITCH_OFFLOAD_SUPPORTED         0x80UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_TRUSTED_VF_SUPPORTED                     0x100UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_FLOW_AGING_SUPPORTED                     0x200UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_ADV_FLOW_COUNTERS_SUPPORTED              0x400UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_EEM_SUPPORTED                        0x800UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_ADV_FLOW_MGNT_SUPPORTED              0x1000UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_TFLIB_SUPPORTED                      0x2000UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_TRUFLOW_SUPPORTED                    0x4000UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_SECURE_BOOT_CAPABLE                      0x8000UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_SECURE_SOC_CAPABLE                       0x10000UL
-	u8	roce_fw_maj_8b;
-	u8	roce_fw_min_8b;
-	u8	roce_fw_bld_8b;
-	u8	roce_fw_rsvd_8b;
-	char	hwrm_fw_name[16];
-	char	mgmt_fw_name[16];
-	char	netctrl_fw_name[16];
-	char	active_pkg_name[16];
-	char	roce_fw_name[16];
-	__le16	chip_num;
-	u8	chip_rev;
-	u8	chip_metal;
-	u8	chip_bond_id;
-	u8	chip_platform_type;
-	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_ASIC      0x0UL
-	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_FPGA      0x1UL
-	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_PALLADIUM 0x2UL
-	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_LAST     VER_GET_RESP_CHIP_PLATFORM_TYPE_PALLADIUM
-	__le16	max_req_win_len;
-	__le16	max_resp_len;
-	__le16	def_req_timeout;
-	u8	flags;
-	#define VER_GET_RESP_FLAGS_DEV_NOT_RDY                   0x1UL
-	#define VER_GET_RESP_FLAGS_EXT_VER_AVAIL                 0x2UL
-	#define VER_GET_RESP_FLAGS_DEV_NOT_RDY_BACKING_STORE     0x4UL
-	u8	unused_0[2];
-	u8	always_1;
-	__le16	hwrm_intf_major;
-	__le16	hwrm_intf_minor;
-	__le16	hwrm_intf_build;
-	__le16	hwrm_intf_patch;
-	__le16	hwrm_fw_major;
-	__le16	hwrm_fw_minor;
-	__le16	hwrm_fw_build;
-	__le16	hwrm_fw_patch;
-	__le16	mgmt_fw_major;
-	__le16	mgmt_fw_minor;
-	__le16	mgmt_fw_build;
-	__le16	mgmt_fw_patch;
-	__le16	netctrl_fw_major;
-	__le16	netctrl_fw_minor;
-	__le16	netctrl_fw_build;
-	__le16	netctrl_fw_patch;
-	__le16	roce_fw_major;
-	__le16	roce_fw_minor;
-	__le16	roce_fw_build;
-	__le16	roce_fw_patch;
-	__le16	max_ext_req_len;
-	__le16	max_req_timeout;
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* eject_cmpl (size:128b/16B) */
-struct eject_cmpl {
-	__le16	type;
-	#define EJECT_CMPL_TYPE_MASK       0x3fUL
-	#define EJECT_CMPL_TYPE_SFT        0
-	#define EJECT_CMPL_TYPE_STAT_EJECT   0x1aUL
-	#define EJECT_CMPL_TYPE_LAST        EJECT_CMPL_TYPE_STAT_EJECT
-	#define EJECT_CMPL_FLAGS_MASK      0xffc0UL
-	#define EJECT_CMPL_FLAGS_SFT       6
-	#define EJECT_CMPL_FLAGS_ERROR      0x40UL
-	__le16	len;
-	__le32	opaque;
-	__le16	v;
-	#define EJECT_CMPL_V                              0x1UL
-	#define EJECT_CMPL_ERRORS_MASK                    0xfffeUL
-	#define EJECT_CMPL_ERRORS_SFT                     1
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_MASK        0xeUL
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_SFT         1
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_NO_BUFFER     (0x0UL << 1)
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_DID_NOT_FIT   (0x1UL << 1)
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_BAD_FORMAT    (0x3UL << 1)
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_FLUSH         (0x5UL << 1)
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_LAST         EJECT_CMPL_ERRORS_BUFFER_ERROR_FLUSH
-	__le16	reserved16;
-	__le32	unused_2;
-};
-
-/* hwrm_cmpl (size:128b/16B) */
-struct hwrm_cmpl {
-	__le16	type;
-	#define CMPL_TYPE_MASK     0x3fUL
-	#define CMPL_TYPE_SFT      0
-	#define CMPL_TYPE_HWRM_DONE  0x20UL
-	#define CMPL_TYPE_LAST      CMPL_TYPE_HWRM_DONE
-	__le16	sequence_id;
-	__le32	unused_1;
-	__le32	v;
-	#define CMPL_V     0x1UL
-	__le32	unused_3;
-};
-
-/* hwrm_fwd_req_cmpl (size:128b/16B) */
-struct hwrm_fwd_req_cmpl {
-	__le16	req_len_type;
-	#define FWD_REQ_CMPL_TYPE_MASK        0x3fUL
-	#define FWD_REQ_CMPL_TYPE_SFT         0
-	#define FWD_REQ_CMPL_TYPE_HWRM_FWD_REQ  0x22UL
-	#define FWD_REQ_CMPL_TYPE_LAST         FWD_REQ_CMPL_TYPE_HWRM_FWD_REQ
-	#define FWD_REQ_CMPL_REQ_LEN_MASK     0xffc0UL
-	#define FWD_REQ_CMPL_REQ_LEN_SFT      6
-	__le16	source_id;
-	__le32	unused0;
-	__le32	req_buf_addr_v[2];
-	#define FWD_REQ_CMPL_V                0x1UL
-	#define FWD_REQ_CMPL_REQ_BUF_ADDR_MASK 0xfffffffeUL
-	#define FWD_REQ_CMPL_REQ_BUF_ADDR_SFT 1
-};
-
-/* hwrm_fwd_resp_cmpl (size:128b/16B) */
-struct hwrm_fwd_resp_cmpl {
-	__le16	type;
-	#define FWD_RESP_CMPL_TYPE_MASK         0x3fUL
-	#define FWD_RESP_CMPL_TYPE_SFT          0
-	#define FWD_RESP_CMPL_TYPE_HWRM_FWD_RESP  0x24UL
-	#define FWD_RESP_CMPL_TYPE_LAST          FWD_RESP_CMPL_TYPE_HWRM_FWD_RESP
-	__le16	source_id;
-	__le16	resp_len;
-	__le16	unused_1;
-	__le32	resp_buf_addr_v[2];
-	#define FWD_RESP_CMPL_V                 0x1UL
-	#define FWD_RESP_CMPL_RESP_BUF_ADDR_MASK 0xfffffffeUL
-	#define FWD_RESP_CMPL_RESP_BUF_ADDR_SFT 1
-};
-
-/* hwrm_async_event_cmpl (size:128b/16B) */
-struct hwrm_async_event_cmpl {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_TYPE_LAST             ASYNC_EVENT_CMPL_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE              0x0UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_MTU_CHANGE                 0x1UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CHANGE               0x2UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DCB_CONFIG_CHANGE               0x3UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PORT_CONN_NOT_ALLOWED           0x4UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_NOT_ALLOWED      0x5UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE           0x6UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PORT_PHY_CFG_CHANGE             0x7UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY                    0x8UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY                  0x9UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_RING_MONITOR_MSG                0xaUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_UNLOAD                0x10UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_LOAD                  0x11UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_FLR_PROC_CMPLT             0x12UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_UNLOAD                  0x20UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_LOAD                    0x21UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_FLR                          0x30UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_MAC_ADDR_CHANGE              0x31UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_VF_COMM_STATUS_CHANGE        0x32UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE                   0x33UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LLFC_PFC_CHANGE                 0x34UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DEFAULT_VNIC_CHANGE             0x35UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_HW_FLOW_AGED                    0x36UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DEBUG_NOTIFICATION              0x37UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_REQ             0x38UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_DONE            0x39UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_TCP_FLAG_ACTION_CHANGE          0x3aUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_FLOW_ACTIVE                 0x3bUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CFG_CHANGE                  0x3cUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_TFLIB_DEFAULT_VNIC_CHANGE       0x3dUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_TFLIB_LINK_STATUS_CHANGE        0x3eUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_QUIESCE_DONE                    0x3fUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE               0x40UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PFC_WATCHDOG_CFG_CHANGE         0x41UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST                    0x42UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE                      0x43UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP                   0x44UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT                    0x45UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DOORBELL_PACING_THRESHOLD       0x46UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_RSS_CHANGE                      0x47UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DOORBELL_PACING_NQ_UPDATE       0x48UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_HW_DOORBELL_RECOVERY_READ_ERROR 0x49UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_CTX_ERROR                       0x4aUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_UDCC_SESSION_CHANGE             0x4bUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER                0x4cUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PEER_MMAP_CHANGE                0x4dUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_REPRESENTOR_PAIR_CHANGE         0x4eUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_STAT_CHANGE                  0x4fUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_HOST_COREDUMP                   0x50UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID               0x51UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG                    0xfeUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR                      0xffUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LAST                           ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_V          0x1UL
-	#define ASYNC_EVENT_CMPL_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-};
-
-/* hwrm_async_event_cmpl_link_status_change (size:128b/16B) */
-struct hwrm_async_event_cmpl_link_status_change {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_ID_LINK_STATUS_CHANGE 0x0UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_ID_LAST              ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_ID_LINK_STATUS_CHANGE
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE     0x1UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_DOWN  0x0UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_UP    0x1UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_LAST ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_UP
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_MASK       0xeUL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_SFT        1
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_MASK    0xffff0UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_SFT     4
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_MASK      0xff00000UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_SFT       20
-};
-
-/* hwrm_async_event_cmpl_port_conn_not_allowed (size:128b/16B) */
-struct hwrm_async_event_cmpl_port_conn_not_allowed {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_LAST             ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_ID_PORT_CONN_NOT_ALLOWED 0x4UL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_ID_LAST                 ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_ID_PORT_CONN_NOT_ALLOWED
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_V          0x1UL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_MASK                 0xffffUL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_SFT                  0
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_MASK      0xff0000UL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_SFT       16
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_NONE        (0x0UL << 16)
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_DISABLETX   (0x1UL << 16)
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_WARNINGMSG  (0x2UL << 16)
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_PWRDOWN     (0x3UL << 16)
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_LAST       ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_PWRDOWN
-};
-
-/* hwrm_async_event_cmpl_link_speed_cfg_change (size:128b/16B) */
-struct hwrm_async_event_cmpl_link_speed_cfg_change {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_ID_LINK_SPEED_CFG_CHANGE 0x6UL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_ID_LAST                 ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_ID_LINK_SPEED_CFG_CHANGE
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_PORT_ID_MASK                     0xffffUL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_PORT_ID_SFT                      0
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_SUPPORTED_LINK_SPEEDS_CHANGE     0x10000UL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_ILLEGAL_LINK_SPEED_CFG           0x20000UL
-};
-
-/* hwrm_async_event_cmpl_reset_notify (size:128b/16B) */
-struct hwrm_async_event_cmpl_reset_notify {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_LAST             ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_RESET_NOTIFY 0x8UL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_LAST        ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_RESET_NOTIFY
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA2_FW_STATUS_CODE_MASK 0xffffUL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA2_FW_STATUS_CODE_SFT 0
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_V          0x1UL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_MASK                  0xffUL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_SFT                   0
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_STOP_TX_QUEUE    0x1UL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_IFDOWN           0x2UL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_LAST                   ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_IFDOWN
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MASK                    0xff00UL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_SFT                     8
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MANAGEMENT_RESET_REQUEST  (0x1UL << 8)
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL        (0x2UL << 8)
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_NON_FATAL    (0x3UL << 8)
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FAST_RESET                (0x4UL << 8)
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION             (0x5UL << 8)
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_LAST                     ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_MASK           0xffff0000UL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_SFT            16
-};
-
-/* hwrm_async_event_cmpl_error_recovery (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_recovery {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY 0x9UL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_LAST          ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASK                 0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_SFT                  0
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASTER_FUNC           0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_RECOVERY_ENABLED      0x2UL
-};
-
-/* hwrm_async_event_cmpl_ring_monitor_msg (size:128b/16B) */
-struct hwrm_async_event_cmpl_ring_monitor_msg {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_LAST             ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_RING_MONITOR_MSG 0xaUL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_LAST            ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_RING_MONITOR_MSG
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_MASK 0xffUL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_SFT 0
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_TX    0x0UL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_RX    0x1UL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_CMPL  0x2UL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_LAST ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_CMPL
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_V          0x1UL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-};
-
-/* hwrm_async_event_cmpl_vf_cfg_change (size:128b/16B) */
-struct hwrm_async_event_cmpl_vf_cfg_change {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_VF_CFG_CHANGE 0x33UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_LAST         ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_VF_CFG_CHANGE
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA2_VF_ID_MASK 0xffffUL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA2_VF_ID_SFT 0
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_MTU_CHANGE                0x1UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_MRU_CHANGE                0x2UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_DFLT_MAC_ADDR_CHANGE      0x4UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_DFLT_VLAN_CHANGE          0x8UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_TRUSTED_VF_CFG_CHANGE     0x10UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_TF_OWNERSHIP_RELEASE      0x20UL
-};
-
-/* hwrm_async_event_cmpl_default_vnic_change (size:128b/16B) */
-struct hwrm_async_event_cmpl_default_vnic_change {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_HWRM_ASYNC_EVENT
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_UNUSED1_MASK         0xffc0UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_UNUSED1_SFT          6
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_ALLOC_FREE_NOTIFICATION 0x35UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_LAST                   ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_ALLOC_FREE_NOTIFICATION
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_MASK          0x3UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_SFT           0
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_ALLOC  0x1UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_FREE   0x2UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_LAST           ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_FREE
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_PF_ID_MASK                   0x3fcUL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_PF_ID_SFT                    2
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_VF_ID_MASK                   0x3fffc00UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_VF_ID_SFT                    10
-};
-
-/* hwrm_async_event_cmpl_hw_flow_aged (size:128b/16B) */
-struct hwrm_async_event_cmpl_hw_flow_aged {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_LAST             ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_HW_FLOW_AGED 0x36UL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_LAST        ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_HW_FLOW_AGED
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_V          0x1UL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_ID_MASK       0x7fffffffUL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_ID_SFT        0
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION     0x80000000UL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_RX    (0x0UL << 31)
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_TX    (0x1UL << 31)
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_LAST ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_TX
-};
-
-/* hwrm_async_event_cmpl_eem_cache_flush_req (size:128b/16B) */
-struct hwrm_async_event_cmpl_eem_cache_flush_req {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_LAST             ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_EEM_CACHE_FLUSH_REQ 0x38UL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_LAST               ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_EEM_CACHE_FLUSH_REQ
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_V          0x1UL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-};
-
-/* hwrm_async_event_cmpl_eem_cache_flush_done (size:128b/16B) */
-struct hwrm_async_event_cmpl_eem_cache_flush_done {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_LAST             ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_EEM_CACHE_FLUSH_DONE 0x39UL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_LAST                ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_EEM_CACHE_FLUSH_DONE
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_DATA1_FID_MASK 0xffffUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_DATA1_FID_SFT 0
-};
-
-/* hwrm_async_event_cmpl_deferred_response (size:128b/16B) */
-struct hwrm_async_event_cmpl_deferred_response {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_LAST             ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_DEFERRED_RESPONSE 0x40UL
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_LAST             ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_DEFERRED_RESPONSE
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_DATA2_SEQ_ID_MASK 0xffffUL
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_DATA2_SEQ_ID_SFT 0
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-};
-
-/* hwrm_async_event_cmpl_echo_request (size:128b/16B) */
-struct hwrm_async_event_cmpl_echo_request {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_LAST             ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_EVENT_ID_ECHO_REQUEST 0x42UL
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ECHO_REQUEST_EVENT_ID_ECHO_REQUEST
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-};
-
-/* hwrm_async_event_cmpl_phc_update (size:128b/16B) */
-struct hwrm_async_event_cmpl_phc_update {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_LAST             ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE 0x43UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_LAST      ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_MASK 0xffffUL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_SFT 0
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_MASK   0xffff0000UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_SFT    16
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_MASK          0xfUL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_SFT           0
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_MASTER      0x1UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_SECONDARY   0x2UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_FAILOVER    0x3UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE  0x4UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_LAST           ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_MASK   0xffff0UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_SFT    4
-};
-
-/* hwrm_async_event_cmpl_pps_timestamp (size:128b/16B) */
-struct hwrm_async_event_cmpl_pps_timestamp {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_LAST             ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_PPS_TIMESTAMP 0x44UL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_LAST         ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_PPS_TIMESTAMP
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE              0x1UL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_INTERNAL       0x0UL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_EXTERNAL       0x1UL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_LAST          ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_EXTERNAL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PIN_NUMBER_MASK         0xeUL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PIN_NUMBER_SFT          1
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PPS_TIMESTAMP_UPPER_MASK 0xffff0UL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PPS_TIMESTAMP_UPPER_SFT 4
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_V          0x1UL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA1_PPS_TIMESTAMP_LOWER_MASK 0xffffffffUL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA1_PPS_TIMESTAMP_LOWER_SFT 0
-};
-
-/* hwrm_async_event_cmpl_error_report (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_DATA1_ERROR_TYPE_SFT 0
-};
-
-/* hwrm_async_event_cmpl_dbg_buf_producer (size:128b/16B) */
-struct hwrm_async_event_cmpl_dbg_buf_producer {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_LAST             ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_ID_DBG_BUF_PRODUCER 0x4cUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_ID_LAST            ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_ID_DBG_BUF_PRODUCER
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA2_CURR_OFF_MASK 0xffffffffUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA2_CURR_OFF_SFT 0
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_V          0x1UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_MASK               0xffffUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_SFT                0
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_SRT_TRACE            0x0UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_SRT2_TRACE           0x1UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CRT_TRACE            0x2UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CRT2_TRACE           0x3UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_RIGP0_TRACE          0x4UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_L2_HWRM_TRACE        0x5UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_ROCE_HWRM_TRACE      0x6UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CA0_TRACE            0x7UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CA1_TRACE            0x8UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CA2_TRACE            0x9UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_RIGP1_TRACE          0xaUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_AFM_KONG_HWRM_TRACE  0xbUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_LAST                ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_AFM_KONG_HWRM_TRACE
-};
-
-/* hwrm_async_event_cmpl_hwrm_error (size:128b/16B) */
-struct hwrm_async_event_cmpl_hwrm_error {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_LAST             ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_HWRM_ERROR 0xffUL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_LAST      ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_HWRM_ERROR
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_MASK    0xffUL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_SFT     0
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_WARNING   0x0UL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_NONFATAL  0x1UL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_FATAL     0x2UL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_LAST     ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_FATAL
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_V          0x1UL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA1_TIMESTAMP     0x1UL
-};
-
-/* hwrm_async_event_cmpl_error_report_base (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_base {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK                        0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT                         0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_RESERVED                      0x0UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM                   0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL                0x2UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM                           0x3UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD       0x4UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_THERMAL_THRESHOLD             0x5UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED  0x6UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST                         ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED
-};
-
-/* hwrm_async_event_cmpl_error_report_pause_storm (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_pause_storm {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_MASK       0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_SFT        0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM  0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM
-};
-
-/* hwrm_async_event_cmpl_error_report_invalid_signal (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_invalid_signal {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_MASK 0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_SFT 0
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_MASK          0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_SFT           0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL  0x2UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_LAST           ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL
-};
-
-/* hwrm_async_event_cmpl_error_report_nvm (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_nvm {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA2_ERR_ADDR_MASK 0xffffffffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA2_ERR_ADDR_SFT 0
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_MASK     0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_SFT      0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_NVM_ERROR  0x3UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_LAST      ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_NVM_ERROR
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_MASK   0xff00UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_SFT    8
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_WRITE    (0x1UL << 8)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE    (0x2UL << 8)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_LAST    ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE
-};
-
-/* hwrm_async_event_cmpl_error_report_doorbell_drop_threshold (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_doorbell_drop_threshold {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_MASK                   0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_SFT                    0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD  0x4UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_LAST                    ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_EPOCH_MASK                        0xffffff00UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_EPOCH_SFT                         8
-};
-
-/* hwrm_async_event_cmpl_error_report_thermal (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_thermal {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_CURRENT_TEMP_MASK  0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_CURRENT_TEMP_SFT   0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_THRESHOLD_TEMP_MASK 0xff00UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_THRESHOLD_TEMP_SFT 8
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_MASK          0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_SFT           0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_THERMAL_EVENT   0x5UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_LAST           ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_THERMAL_EVENT
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_MASK      0x700UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_SFT       8
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_WARN        (0x0UL << 8)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_CRITICAL    (0x1UL << 8)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_FATAL       (0x2UL << 8)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_SHUTDOWN    (0x3UL << 8)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_LAST       ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_SHUTDOWN
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR           0x800UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_DECREASING  (0x0UL << 11)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_INCREASING  (0x1UL << 11)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_LAST       ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_INCREASING
-};
-
-/* hwrm_async_event_cmpl_error_report_dual_data_rate_not_supported (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_dual_data_rate_not_supported {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_MASK                        0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_SFT                         0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED  0x6UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_LAST                         ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED
-};
-
-/* hwrm_func_reset_input (size:192b/24B) */
-struct hwrm_func_reset_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_RESET_REQ_ENABLES_VF_ID_VALID     0x1UL
-	__le16	vf_id;
-	u8	func_reset_level;
-	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETALL      0x0UL
-	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETME       0x1UL
-	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETCHILDREN 0x2UL
-	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETVF       0x3UL
-	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_LAST         FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETVF
-	u8	unused_0;
-};
-
-/* hwrm_func_reset_output (size:128b/16B) */
-struct hwrm_func_reset_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_getfid_input (size:192b/24B) */
-struct hwrm_func_getfid_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_GETFID_REQ_ENABLES_PCI_ID     0x1UL
-	__le16	pci_id;
-	u8	unused_0[2];
-};
-
-/* hwrm_func_getfid_output (size:128b/16B) */
-struct hwrm_func_getfid_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	fid;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_func_vf_alloc_input (size:192b/24B) */
-struct hwrm_func_vf_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_VF_ALLOC_REQ_ENABLES_FIRST_VF_ID     0x1UL
-	__le16	first_vf_id;
-	__le16	num_vfs;
-};
-
-/* hwrm_func_vf_alloc_output (size:128b/16B) */
-struct hwrm_func_vf_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	first_vf_id;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_func_vf_free_input (size:192b/24B) */
-struct hwrm_func_vf_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_VF_FREE_REQ_ENABLES_FIRST_VF_ID     0x1UL
-	__le16	first_vf_id;
-	__le16	num_vfs;
-};
-
-/* hwrm_func_vf_free_output (size:128b/16B) */
-struct hwrm_func_vf_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_vf_cfg_input (size:576b/72B) */
-struct hwrm_func_vf_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_VF_CFG_REQ_ENABLES_MTU                      0x1UL
-	#define FUNC_VF_CFG_REQ_ENABLES_GUEST_VLAN               0x2UL
-	#define FUNC_VF_CFG_REQ_ENABLES_ASYNC_EVENT_CR           0x4UL
-	#define FUNC_VF_CFG_REQ_ENABLES_DFLT_MAC_ADDR            0x8UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS          0x10UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS           0x20UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS             0x40UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS             0x80UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_L2_CTXS              0x100UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_VNICS                0x200UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS            0x400UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS         0x800UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_KTLS_TX_KEY_CTXS     0x1000UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_KTLS_RX_KEY_CTXS     0x2000UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_QUIC_TX_KEY_CTXS     0x4000UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_QUIC_RX_KEY_CTXS     0x8000UL
-	__le16	mtu;
-	__le16	guest_vlan;
-	__le16	async_event_cr;
-	u8	dflt_mac_addr[6];
-	__le32	flags;
-	#define FUNC_VF_CFG_REQ_FLAGS_TX_ASSETS_TEST             0x1UL
-	#define FUNC_VF_CFG_REQ_FLAGS_RX_ASSETS_TEST             0x2UL
-	#define FUNC_VF_CFG_REQ_FLAGS_CMPL_ASSETS_TEST           0x4UL
-	#define FUNC_VF_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST     0x8UL
-	#define FUNC_VF_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST       0x10UL
-	#define FUNC_VF_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST       0x20UL
-	#define FUNC_VF_CFG_REQ_FLAGS_VNIC_ASSETS_TEST           0x40UL
-	#define FUNC_VF_CFG_REQ_FLAGS_L2_CTX_ASSETS_TEST         0x80UL
-	#define FUNC_VF_CFG_REQ_FLAGS_PPP_PUSH_MODE_ENABLE       0x100UL
-	#define FUNC_VF_CFG_REQ_FLAGS_PPP_PUSH_MODE_DISABLE      0x200UL
-	__le16	num_rsscos_ctxs;
-	__le16	num_cmpl_rings;
-	__le16	num_tx_rings;
-	__le16	num_rx_rings;
-	__le16	num_l2_ctxs;
-	__le16	num_vnics;
-	__le16	num_stat_ctxs;
-	__le16	num_hw_ring_grps;
-	__le32	num_ktls_tx_key_ctxs;
-	__le32	num_ktls_rx_key_ctxs;
-	__le16	num_msix;
-	u8	unused[2];
-	__le32	num_quic_tx_key_ctxs;
-	__le32	num_quic_rx_key_ctxs;
-};
-
-/* hwrm_func_vf_cfg_output (size:128b/16B) */
-struct hwrm_func_vf_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_qcaps_input (size:192b/24B) */
-struct hwrm_func_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	unused_0[6];
-};
-
-/* hwrm_func_qcaps_output (size:1152b/144B) */
-struct hwrm_func_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	fid;
-	__le16	port_id;
-	__le32	flags;
-	#define FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED                   0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_GLOBAL_MSIX_AUTOMASKING               0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED                         0x4UL
-	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED                     0x8UL
-	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED                     0x10UL
-	#define FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED                0x20UL
-	#define FUNC_QCAPS_RESP_FLAGS_WOL_BMP_SUPPORTED                     0x40UL
-	#define FUNC_QCAPS_RESP_FLAGS_TX_RING_RL_SUPPORTED                  0x80UL
-	#define FUNC_QCAPS_RESP_FLAGS_TX_BW_CFG_SUPPORTED                   0x100UL
-	#define FUNC_QCAPS_RESP_FLAGS_VF_TX_RING_RL_SUPPORTED               0x200UL
-	#define FUNC_QCAPS_RESP_FLAGS_VF_BW_CFG_SUPPORTED                   0x400UL
-	#define FUNC_QCAPS_RESP_FLAGS_STD_TX_RING_MODE_SUPPORTED            0x800UL
-	#define FUNC_QCAPS_RESP_FLAGS_GENEVE_TUN_FLAGS_SUPPORTED            0x1000UL
-	#define FUNC_QCAPS_RESP_FLAGS_NVGRE_TUN_FLAGS_SUPPORTED             0x2000UL
-	#define FUNC_QCAPS_RESP_FLAGS_GRE_TUN_FLAGS_SUPPORTED               0x4000UL
-	#define FUNC_QCAPS_RESP_FLAGS_MPLS_TUN_FLAGS_SUPPORTED              0x8000UL
-	#define FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED                  0x10000UL
-	#define FUNC_QCAPS_RESP_FLAGS_ADOPTED_PF_SUPPORTED                  0x20000UL
-	#define FUNC_QCAPS_RESP_FLAGS_ADMIN_PF_SUPPORTED                    0x40000UL
-	#define FUNC_QCAPS_RESP_FLAGS_LINK_ADMIN_STATUS_SUPPORTED           0x80000UL
-	#define FUNC_QCAPS_RESP_FLAGS_WCB_PUSH_MODE                         0x100000UL
-	#define FUNC_QCAPS_RESP_FLAGS_DYNAMIC_TX_RING_ALLOC                 0x200000UL
-	#define FUNC_QCAPS_RESP_FLAGS_HOT_RESET_CAPABLE                     0x400000UL
-	#define FUNC_QCAPS_RESP_FLAGS_ERROR_RECOVERY_CAPABLE                0x800000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_STATS_SUPPORTED                   0x1000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_ERR_RECOVER_RELOAD                    0x2000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_NOTIFY_VF_DEF_VNIC_CHNG_SUPPORTED     0x4000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_VLAN_ACCELERATION_TX_DISABLED         0x8000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_COREDUMP_CMD_SUPPORTED                0x10000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_CRASHDUMP_CMD_SUPPORTED               0x20000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_PFC_WD_STATS_SUPPORTED                0x40000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_DBG_QCAPS_CMD_SUPPORTED               0x80000000UL
-	u8	mac_address[6];
-	__le16	max_rsscos_ctx;
-	__le16	max_cmpl_rings;
-	__le16	max_tx_rings;
-	__le16	max_rx_rings;
-	__le16	max_l2_ctxs;
-	__le16	max_vnics;
-	__le16	first_vf_id;
-	__le16	max_vfs;
-	__le16	max_stat_ctx;
-	__le32	max_encap_records;
-	__le32	max_decap_records;
-	__le32	max_tx_em_flows;
-	__le32	max_tx_wm_flows;
-	__le32	max_rx_em_flows;
-	__le32	max_rx_wm_flows;
-	__le32	max_mcast_filters;
-	__le32	max_flow_id;
-	__le32	max_hw_ring_grps;
-	__le16	max_sp_tx_rings;
-	__le16	max_msix_vfs;
-	__le32	flags_ext;
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_MARK_SUPPORTED                          0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_STATS_SUPPORTED                         0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_EXT_HW_STATS_SUPPORTED                      0x4UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_HOT_RESET_IF_SUPPORT                        0x8UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_PROXY_MODE_SUPPORT                          0x10UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_TX_PROXY_SRC_INTF_OVERRIDE_SUPPORT          0x20UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_SCHQ_SUPPORTED                              0x40UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_PPP_PUSH_MODE_SUPPORTED                     0x80UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_EVB_MODE_CFG_NOT_SUPPORTED                  0x100UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_SOC_SPD_SUPPORTED                           0x200UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED                      0x400UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_FAST_RESET_CAPABLE                          0x800UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_TX_METADATA_CFG_CAPABLE                     0x1000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_NVM_OPTION_ACTION_SUPPORTED                 0x2000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_BD_METADATA_SUPPORTED                       0x4000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECHO_REQUEST_SUPPORTED                      0x8000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_NPAR_1_2_SUPPORTED                          0x10000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PTM_SUPPORTED                           0x20000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PPS_SUPPORTED                           0x40000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_VF_CFG_ASYNC_FOR_PF_SUPPORTED               0x80000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_PARTITION_BW_SUPPORTED                      0x100000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_DFLT_VLAN_TPID_PCP_SUPPORTED                0x200000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_KTLS_SUPPORTED                              0x400000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_EP_RATE_CONTROL                             0x800000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_MIN_BW_SUPPORTED                            0x1000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_TX_COAL_CMPL_CAP                            0x2000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED                             0x4000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_REQUIRED                              0x8000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_64BIT_RTC_SUPPORTED                     0x10000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_DBR_PACING_SUPPORTED                        0x20000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_HW_DBR_DROP_RECOV_SUPPORTED                 0x40000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_DISABLE_CQ_OVERFLOW_DETECTION_SUPPORTED     0x80000000UL
-	u8	max_schqs;
-	u8	mpc_chnls_cap;
-	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TCE         0x1UL
-	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_RCE         0x2UL
-	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TE_CFA      0x4UL
-	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_RE_CFA      0x8UL
-	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_PRIMATE     0x10UL
-	__le16	max_key_ctxs_alloc;
-	__le32	flags_ext2;
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_RX_ALL_PKTS_TIMESTAMPS_SUPPORTED      0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_QUIC_SUPPORTED                        0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KDNET_SUPPORTED                       0x4UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_EXT_SUPPORTED              0x8UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_DBR_DROP_RECOVERY_SUPPORTED        0x10UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_GENERIC_STATS_SUPPORTED               0x20UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDP_GSO_SUPPORTED                     0x40UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SYNCE_SUPPORTED                       0x80UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_V0_SUPPORTED               0x100UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TX_PKT_TS_CMPL_SUPPORTED              0x200UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_HW_LAG_SUPPORTED                      0x400UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ON_CHIP_CTX_SUPPORTED                 0x800UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_STEERING_TAG_SUPPORTED                0x1000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ENHANCED_VF_SCALE_SUPPORTED           0x2000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KEY_XID_PARTITION_SUPPORTED           0x4000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_CONCURRENT_KTLS_QUIC_SUPPORTED        0x8000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_CROSS_TC_CAP_SUPPORTED           0x10000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_PER_TC_CAP_SUPPORTED             0x20000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_PER_TC_RESERVATION_SUPPORTED     0x40000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DB_ERROR_STATS_SUPPORTED              0x80000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ROCE_VF_RESOURCE_MGMT_SUPPORTED       0x100000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDCC_SUPPORTED                        0x200000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TIMED_TX_SO_TXTIME_SUPPORTED          0x400000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_MAX_RESOURCE_LIMITS_SUPPORTED      0x800000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_INGRESS_NIC_FLOW_SUPPORTED         0x1000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_LPBK_STATS_SUPPORTED                  0x2000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_EGRESS_NIC_FLOW_SUPPORTED          0x4000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_MULTI_LOSSLESS_QUEUES_SUPPORTED       0x8000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_PEER_MMAP_SUPPORTED                   0x10000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TIMED_TX_PACING_SUPPORTED             0x20000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_VF_STAT_EJECTION_SUPPORTED            0x40000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_HOST_COREDUMP_SUPPORTED               0x80000000UL
-	__le16	tunnel_disable_flag;
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_VXLAN      0x1UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NGE        0x2UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NVGRE      0x4UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_L2GRE      0x8UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_GRE        0x10UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_IPINIP     0x20UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_MPLS       0x40UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_PPPOE      0x80UL
-	__le16	xid_partition_cap;
-	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_TX_CK     0x1UL
-	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_RX_CK     0x2UL
-	u8	device_serial_number[8];
-	__le16	ctxs_per_partition;
-	__le16	max_tso_segs;
-	__le32	roce_vf_max_av;
-	__le32	roce_vf_max_cq;
-	__le32	roce_vf_max_mrw;
-	__le32	roce_vf_max_qp;
-	__le32	roce_vf_max_srq;
-	__le32	roce_vf_max_gid;
-	__le32	flags_ext3;
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RM_RSV_WHILE_ALLOC_CAP     0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_REQUIRE_L2_FILTER          0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MAX_ROCE_VFS_SUPPORTED     0x4UL
-	__le16	max_roce_vfs;
-	u8	unused_3[5];
-	u8	valid;
-};
-
-/* hwrm_func_qcfg_input (size:192b/24B) */
-struct hwrm_func_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	unused_0[6];
-};
-
-/* hwrm_func_qcfg_output (size:1280b/160B) */
-struct hwrm_func_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	fid;
-	__le16	port_id;
-	__le16	vlan;
-	__le16	flags;
-	#define FUNC_QCFG_RESP_FLAGS_OOB_WOL_MAGICPKT_ENABLED     0x1UL
-	#define FUNC_QCFG_RESP_FLAGS_OOB_WOL_BMP_ENABLED          0x2UL
-	#define FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED        0x4UL
-	#define FUNC_QCFG_RESP_FLAGS_STD_TX_RING_MODE_ENABLED     0x8UL
-	#define FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED        0x10UL
-	#define FUNC_QCFG_RESP_FLAGS_MULTI_HOST                   0x20UL
-	#define FUNC_QCFG_RESP_FLAGS_TRUSTED_VF                   0x40UL
-	#define FUNC_QCFG_RESP_FLAGS_SECURE_MODE_ENABLED          0x80UL
-	#define FUNC_QCFG_RESP_FLAGS_PREBOOT_LEGACY_L2_RINGS      0x100UL
-	#define FUNC_QCFG_RESP_FLAGS_HOT_RESET_ALLOWED            0x200UL
-	#define FUNC_QCFG_RESP_FLAGS_PPP_PUSH_MODE_ENABLED        0x400UL
-	#define FUNC_QCFG_RESP_FLAGS_RING_MONITOR_ENABLED         0x800UL
-	#define FUNC_QCFG_RESP_FLAGS_FAST_RESET_ALLOWED           0x1000UL
-	#define FUNC_QCFG_RESP_FLAGS_MULTI_ROOT                   0x2000UL
-	#define FUNC_QCFG_RESP_FLAGS_ENABLE_RDMA_SRIOV            0x4000UL
-	#define FUNC_QCFG_RESP_FLAGS_ROCE_VNIC_ID_VALID           0x8000UL
-	u8	mac_address[6];
-	__le16	pci_id;
-	__le16	alloc_rsscos_ctx;
-	__le16	alloc_cmpl_rings;
-	__le16	alloc_tx_rings;
-	__le16	alloc_rx_rings;
-	__le16	alloc_l2_ctx;
-	__le16	alloc_vnics;
-	__le16	admin_mtu;
-	__le16	mru;
-	__le16	stat_ctx_id;
-	u8	port_partition_type;
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_SPF     0x0UL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_MPFS    0x1UL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0 0x2UL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5 0x3UL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0 0x4UL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_2 0x5UL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN 0xffUL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_LAST   FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN
-	u8	port_pf_cnt;
-	#define FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL 0x0UL
-	#define FUNC_QCFG_RESP_PORT_PF_CNT_LAST   FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL
-	__le16	dflt_vnic_id;
-	__le16	max_mtu_configured;
-	__le32	min_bw;
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_SFT              0
-	#define FUNC_QCFG_RESP_MIN_BW_SCALE                     0x10000000UL
-	#define FUNC_QCFG_RESP_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_QCFG_RESP_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_QCFG_RESP_MIN_BW_SCALE_LAST                 FUNC_QCFG_RESP_MIN_BW_SCALE_BYTES
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	max_bw;
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_SFT              0
-	#define FUNC_QCFG_RESP_MAX_BW_SCALE                     0x10000000UL
-	#define FUNC_QCFG_RESP_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_QCFG_RESP_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_QCFG_RESP_MAX_BW_SCALE_LAST                 FUNC_QCFG_RESP_MAX_BW_SCALE_BYTES
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	evb_mode;
-	#define FUNC_QCFG_RESP_EVB_MODE_NO_EVB 0x0UL
-	#define FUNC_QCFG_RESP_EVB_MODE_VEB    0x1UL
-	#define FUNC_QCFG_RESP_EVB_MODE_VEPA   0x2UL
-	#define FUNC_QCFG_RESP_EVB_MODE_LAST  FUNC_QCFG_RESP_EVB_MODE_VEPA
-	u8	options;
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_MASK         0x3UL
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SFT          0
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_64        0x0UL
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128       0x1UL
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_LAST          FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128
-	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_MASK       0xcUL
-	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_SFT        2
-	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN  (0x0UL << 2)
-	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_UP    (0x1UL << 2)
-	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO         (0x2UL << 2)
-	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_LAST        FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO
-	#define FUNC_QCFG_RESP_OPTIONS_RSVD_MASK                   0xf0UL
-	#define FUNC_QCFG_RESP_OPTIONS_RSVD_SFT                    4
-	__le16	alloc_vfs;
-	__le32	alloc_mcast_filters;
-	__le32	alloc_hw_ring_grps;
-	__le16	alloc_sp_tx_rings;
-	__le16	alloc_stat_ctx;
-	__le16	alloc_msix;
-	__le16	registered_vfs;
-	__le16	l2_doorbell_bar_size_kb;
-	u8	active_endpoints;
-	u8	always_1;
-	__le32	reset_addr_poll;
-	__le16	legacy_l2_db_size_kb;
-	__le16	svif_info;
-	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_MASK      0x7fffUL
-	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_SFT       0
-	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_VALID     0x8000UL
-	u8	mpc_chnls;
-	#define FUNC_QCFG_RESP_MPC_CHNLS_TCE_ENABLED         0x1UL
-	#define FUNC_QCFG_RESP_MPC_CHNLS_RCE_ENABLED         0x2UL
-	#define FUNC_QCFG_RESP_MPC_CHNLS_TE_CFA_ENABLED      0x4UL
-	#define FUNC_QCFG_RESP_MPC_CHNLS_RE_CFA_ENABLED      0x8UL
-	#define FUNC_QCFG_RESP_MPC_CHNLS_PRIMATE_ENABLED     0x10UL
-	u8	db_page_size;
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_4KB   0x0UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_8KB   0x1UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_16KB  0x2UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_32KB  0x3UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_64KB  0x4UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_128KB 0x5UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_256KB 0x6UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_512KB 0x7UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_1MB   0x8UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_2MB   0x9UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_4MB   0xaUL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_LAST FUNC_QCFG_RESP_DB_PAGE_SIZE_4MB
-	__le16	roce_vnic_id;
-	__le32	partition_min_bw;
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_SFT              0
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE                     0x10000000UL
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_LAST                 FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BYTES
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100
-	__le32	partition_max_bw;
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_SFT              0
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE                     0x10000000UL
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_LAST                 FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BYTES
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100
-	__le16	host_mtu;
-	__le16	flags2;
-	#define FUNC_QCFG_RESP_FLAGS2_SRIOV_DSCP_INSERT_ENABLED     0x1UL
-	u8	unused_4[2];
-	u8	port_kdnet_mode;
-	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_DISABLED 0x0UL
-	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_ENABLED  0x1UL
-	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_LAST    FUNC_QCFG_RESP_PORT_KDNET_MODE_ENABLED
-	u8	kdnet_pcie_function;
-	__le16	port_kdnet_fid;
-	u8	unused_5[2];
-	__le32	num_ktls_tx_key_ctxs;
-	__le32	num_ktls_rx_key_ctxs;
-	u8	lag_id;
-	u8	parif;
-	u8	fw_lag_id;
-	u8	unused_6;
-	__le32	num_quic_tx_key_ctxs;
-	__le32	num_quic_rx_key_ctxs;
-	__le32	roce_max_av_per_vf;
-	__le32	roce_max_cq_per_vf;
-	__le32	roce_max_mrw_per_vf;
-	__le32	roce_max_qp_per_vf;
-	__le32	roce_max_srq_per_vf;
-	__le32	roce_max_gid_per_vf;
-	__le16	xid_partition_cfg;
-	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_TX_CK     0x1UL
-	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_RX_CK     0x2UL
-	u8	unused_7;
-	u8	valid;
-};
-
-/* hwrm_func_cfg_input (size:1280b/160B) */
-struct hwrm_func_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	__le16	num_msix;
-	__le32	flags;
-	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE     0x1UL
-	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE      0x2UL
-	#define FUNC_CFG_REQ_FLAGS_RSVD_MASK                      0x1fcUL
-	#define FUNC_CFG_REQ_FLAGS_RSVD_SFT                       2
-	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_ENABLE        0x200UL
-	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_DISABLE       0x400UL
-	#define FUNC_CFG_REQ_FLAGS_VIRT_MAC_PERSIST               0x800UL
-	#define FUNC_CFG_REQ_FLAGS_NO_AUTOCLEAR_STATISTIC         0x1000UL
-	#define FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST                 0x2000UL
-	#define FUNC_CFG_REQ_FLAGS_RX_ASSETS_TEST                 0x4000UL
-	#define FUNC_CFG_REQ_FLAGS_CMPL_ASSETS_TEST               0x8000UL
-	#define FUNC_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST         0x10000UL
-	#define FUNC_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST           0x20000UL
-	#define FUNC_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST           0x40000UL
-	#define FUNC_CFG_REQ_FLAGS_VNIC_ASSETS_TEST               0x80000UL
-	#define FUNC_CFG_REQ_FLAGS_L2_CTX_ASSETS_TEST             0x100000UL
-	#define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE              0x200000UL
-	#define FUNC_CFG_REQ_FLAGS_DYNAMIC_TX_RING_ALLOC          0x400000UL
-	#define FUNC_CFG_REQ_FLAGS_NQ_ASSETS_TEST                 0x800000UL
-	#define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE             0x1000000UL
-	#define FUNC_CFG_REQ_FLAGS_PREBOOT_LEGACY_L2_RINGS        0x2000000UL
-	#define FUNC_CFG_REQ_FLAGS_HOT_RESET_IF_EN_DIS            0x4000000UL
-	#define FUNC_CFG_REQ_FLAGS_PPP_PUSH_MODE_ENABLE           0x8000000UL
-	#define FUNC_CFG_REQ_FLAGS_PPP_PUSH_MODE_DISABLE          0x10000000UL
-	#define FUNC_CFG_REQ_FLAGS_BD_METADATA_ENABLE             0x20000000UL
-	#define FUNC_CFG_REQ_FLAGS_BD_METADATA_DISABLE            0x40000000UL
-	__le32	enables;
-	#define FUNC_CFG_REQ_ENABLES_ADMIN_MTU                0x1UL
-	#define FUNC_CFG_REQ_ENABLES_MRU                      0x2UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS          0x4UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS           0x8UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS             0x10UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS             0x20UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_L2_CTXS              0x40UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_VNICS                0x80UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS            0x100UL
-	#define FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR            0x200UL
-	#define FUNC_CFG_REQ_ENABLES_DFLT_VLAN                0x400UL
-	#define FUNC_CFG_REQ_ENABLES_DFLT_IP_ADDR             0x800UL
-	#define FUNC_CFG_REQ_ENABLES_MIN_BW                   0x1000UL
-	#define FUNC_CFG_REQ_ENABLES_MAX_BW                   0x2000UL
-	#define FUNC_CFG_REQ_ENABLES_ASYNC_EVENT_CR           0x4000UL
-	#define FUNC_CFG_REQ_ENABLES_VLAN_ANTISPOOF_MODE      0x8000UL
-	#define FUNC_CFG_REQ_ENABLES_ALLOWED_VLAN_PRIS        0x10000UL
-	#define FUNC_CFG_REQ_ENABLES_EVB_MODE                 0x20000UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_MCAST_FILTERS        0x40000UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS         0x80000UL
-	#define FUNC_CFG_REQ_ENABLES_CACHE_LINESIZE           0x100000UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_MSIX                 0x200000UL
-	#define FUNC_CFG_REQ_ENABLES_ADMIN_LINK_STATE         0x400000UL
-	#define FUNC_CFG_REQ_ENABLES_HOT_RESET_IF_SUPPORT     0x800000UL
-	#define FUNC_CFG_REQ_ENABLES_SCHQ_ID                  0x1000000UL
-	#define FUNC_CFG_REQ_ENABLES_MPC_CHNLS                0x2000000UL
-	#define FUNC_CFG_REQ_ENABLES_PARTITION_MIN_BW         0x4000000UL
-	#define FUNC_CFG_REQ_ENABLES_PARTITION_MAX_BW         0x8000000UL
-	#define FUNC_CFG_REQ_ENABLES_TPID                     0x10000000UL
-	#define FUNC_CFG_REQ_ENABLES_HOST_MTU                 0x20000000UL
-	#define FUNC_CFG_REQ_ENABLES_KTLS_TX_KEY_CTXS         0x40000000UL
-	#define FUNC_CFG_REQ_ENABLES_KTLS_RX_KEY_CTXS         0x80000000UL
-	__le16	admin_mtu;
-	__le16	mru;
-	__le16	num_rsscos_ctxs;
-	__le16	num_cmpl_rings;
-	__le16	num_tx_rings;
-	__le16	num_rx_rings;
-	__le16	num_l2_ctxs;
-	__le16	num_vnics;
-	__le16	num_stat_ctxs;
-	__le16	num_hw_ring_grps;
-	u8	dflt_mac_addr[6];
-	__le16	dflt_vlan;
-	__be32	dflt_ip_addr[4];
-	__le32	min_bw;
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_SFT              0
-	#define FUNC_CFG_REQ_MIN_BW_SCALE                     0x10000000UL
-	#define FUNC_CFG_REQ_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_CFG_REQ_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_CFG_REQ_MIN_BW_SCALE_LAST                 FUNC_CFG_REQ_MIN_BW_SCALE_BYTES
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	max_bw;
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_SFT              0
-	#define FUNC_CFG_REQ_MAX_BW_SCALE                     0x10000000UL
-	#define FUNC_CFG_REQ_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_CFG_REQ_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_CFG_REQ_MAX_BW_SCALE_LAST                 FUNC_CFG_REQ_MAX_BW_SCALE_BYTES
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_INVALID
-	__le16	async_event_cr;
-	u8	vlan_antispoof_mode;
-	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_NOCHECK                 0x0UL
-	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_VALIDATE_VLAN           0x1UL
-	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_IF_VLANDNE       0x2UL
-	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_OR_OVERRIDE_VLAN 0x3UL
-	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_LAST                   FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_OR_OVERRIDE_VLAN
-	u8	allowed_vlan_pris;
-	u8	evb_mode;
-	#define FUNC_CFG_REQ_EVB_MODE_NO_EVB 0x0UL
-	#define FUNC_CFG_REQ_EVB_MODE_VEB    0x1UL
-	#define FUNC_CFG_REQ_EVB_MODE_VEPA   0x2UL
-	#define FUNC_CFG_REQ_EVB_MODE_LAST  FUNC_CFG_REQ_EVB_MODE_VEPA
-	u8	options;
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_MASK         0x3UL
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SFT          0
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_64        0x0UL
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128       0x1UL
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_LAST          FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128
-	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_MASK       0xcUL
-	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_SFT        2
-	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN  (0x0UL << 2)
-	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_UP    (0x1UL << 2)
-	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO         (0x2UL << 2)
-	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_LAST        FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO
-	#define FUNC_CFG_REQ_OPTIONS_RSVD_MASK                   0xf0UL
-	#define FUNC_CFG_REQ_OPTIONS_RSVD_SFT                    4
-	__le16	num_mcast_filters;
-	__le16	schq_id;
-	__le16	mpc_chnls;
-	#define FUNC_CFG_REQ_MPC_CHNLS_TCE_ENABLE          0x1UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_TCE_DISABLE         0x2UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_RCE_ENABLE          0x4UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_RCE_DISABLE         0x8UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_TE_CFA_ENABLE       0x10UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_TE_CFA_DISABLE      0x20UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_RE_CFA_ENABLE       0x40UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_RE_CFA_DISABLE      0x80UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_PRIMATE_ENABLE      0x100UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_PRIMATE_DISABLE     0x200UL
-	__le32	partition_min_bw;
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_SFT              0
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE                     0x10000000UL
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_LAST                 FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BYTES
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100
-	__le32	partition_max_bw;
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_SFT              0
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE                     0x10000000UL
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_LAST                 FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BYTES
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100
-	__be16	tpid;
-	__le16	host_mtu;
-	__le32	flags2;
-	#define FUNC_CFG_REQ_FLAGS2_KTLS_KEY_CTX_ASSETS_TEST     0x1UL
-	#define FUNC_CFG_REQ_FLAGS2_QUIC_KEY_CTX_ASSETS_TEST     0x2UL
-	__le32	enables2;
-	#define FUNC_CFG_REQ_ENABLES2_KDNET                    0x1UL
-	#define FUNC_CFG_REQ_ENABLES2_DB_PAGE_SIZE             0x2UL
-	#define FUNC_CFG_REQ_ENABLES2_QUIC_TX_KEY_CTXS         0x4UL
-	#define FUNC_CFG_REQ_ENABLES2_QUIC_RX_KEY_CTXS         0x8UL
-	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_AV_PER_VF       0x10UL
-	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_CQ_PER_VF       0x20UL
-	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_MRW_PER_VF      0x40UL
-	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_QP_PER_VF       0x80UL
-	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_SRQ_PER_VF      0x100UL
-	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_GID_PER_VF      0x200UL
-	#define FUNC_CFG_REQ_ENABLES2_XID_PARTITION_CFG        0x400UL
-	#define FUNC_CFG_REQ_ENABLES2_PHYSICAL_SLOT_NUMBER     0x800UL
-	u8	port_kdnet_mode;
-	#define FUNC_CFG_REQ_PORT_KDNET_MODE_DISABLED 0x0UL
-	#define FUNC_CFG_REQ_PORT_KDNET_MODE_ENABLED  0x1UL
-	#define FUNC_CFG_REQ_PORT_KDNET_MODE_LAST    FUNC_CFG_REQ_PORT_KDNET_MODE_ENABLED
-	u8	db_page_size;
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_4KB   0x0UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_8KB   0x1UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_16KB  0x2UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_32KB  0x3UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_64KB  0x4UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_128KB 0x5UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_256KB 0x6UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_512KB 0x7UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_1MB   0x8UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_2MB   0x9UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_4MB   0xaUL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_LAST FUNC_CFG_REQ_DB_PAGE_SIZE_4MB
-	__le16	physical_slot_number;
-	__le32	num_ktls_tx_key_ctxs;
-	__le32	num_ktls_rx_key_ctxs;
-	__le32	num_quic_tx_key_ctxs;
-	__le32	num_quic_rx_key_ctxs;
-	__le32	roce_max_av_per_vf;
-	__le32	roce_max_cq_per_vf;
-	__le32	roce_max_mrw_per_vf;
-	__le32	roce_max_qp_per_vf;
-	__le32	roce_max_srq_per_vf;
-	__le32	roce_max_gid_per_vf;
-	__le16	xid_partition_cfg;
-	#define FUNC_CFG_REQ_XID_PARTITION_CFG_TX_CK     0x1UL
-	#define FUNC_CFG_REQ_XID_PARTITION_CFG_RX_CK     0x2UL
-	__le16	unused_2;
-};
-
-/* hwrm_func_cfg_output (size:128b/16B) */
-struct hwrm_func_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_cfg_cmd_err (size:64b/8B) */
-struct hwrm_func_cfg_cmd_err {
-	u8	code;
-	#define FUNC_CFG_CMD_ERR_CODE_UNKNOWN                      0x0UL
-	#define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_BW_RANGE       0x1UL
-	#define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_MORE_THAN_MAX  0x2UL
-	#define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_BW_UNSUPPORTED 0x3UL
-	#define FUNC_CFG_CMD_ERR_CODE_PARTITION_BW_PERCENT         0x4UL
-	#define FUNC_CFG_CMD_ERR_CODE_LAST                        FUNC_CFG_CMD_ERR_CODE_PARTITION_BW_PERCENT
-	u8	unused_0[7];
-};
-
-/* hwrm_func_qstats_input (size:192b/24B) */
-struct hwrm_func_qstats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	flags;
-	#define FUNC_QSTATS_REQ_FLAGS_ROCE_ONLY        0x1UL
-	#define FUNC_QSTATS_REQ_FLAGS_COUNTER_MASK     0x2UL
-	#define FUNC_QSTATS_REQ_FLAGS_L2_ONLY          0x4UL
-	u8	unused_0[5];
-};
-
-/* hwrm_func_qstats_output (size:1408b/176B) */
-struct hwrm_func_qstats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	tx_ucast_pkts;
-	__le64	tx_mcast_pkts;
-	__le64	tx_bcast_pkts;
-	__le64	tx_discard_pkts;
-	__le64	tx_drop_pkts;
-	__le64	tx_ucast_bytes;
-	__le64	tx_mcast_bytes;
-	__le64	tx_bcast_bytes;
-	__le64	rx_ucast_pkts;
-	__le64	rx_mcast_pkts;
-	__le64	rx_bcast_pkts;
-	__le64	rx_discard_pkts;
-	__le64	rx_drop_pkts;
-	__le64	rx_ucast_bytes;
-	__le64	rx_mcast_bytes;
-	__le64	rx_bcast_bytes;
-	__le64	rx_agg_pkts;
-	__le64	rx_agg_bytes;
-	__le64	rx_agg_events;
-	__le64	rx_agg_aborts;
-	u8	clear_seq;
-	u8	unused_0[6];
-	u8	valid;
-};
-
-/* hwrm_func_qstats_ext_input (size:256b/32B) */
-struct hwrm_func_qstats_ext_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	flags;
-	#define FUNC_QSTATS_EXT_REQ_FLAGS_ROCE_ONLY        0x1UL
-	#define FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK     0x2UL
-	u8	unused_0[1];
-	__le32	enables;
-	#define FUNC_QSTATS_EXT_REQ_ENABLES_SCHQ_ID     0x1UL
-	__le16	schq_id;
-	__le16	traffic_class;
-	u8	unused_1[4];
-};
-
-/* hwrm_func_qstats_ext_output (size:1536b/192B) */
-struct hwrm_func_qstats_ext_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	rx_ucast_pkts;
-	__le64	rx_mcast_pkts;
-	__le64	rx_bcast_pkts;
-	__le64	rx_discard_pkts;
-	__le64	rx_error_pkts;
-	__le64	rx_ucast_bytes;
-	__le64	rx_mcast_bytes;
-	__le64	rx_bcast_bytes;
-	__le64	tx_ucast_pkts;
-	__le64	tx_mcast_pkts;
-	__le64	tx_bcast_pkts;
-	__le64	tx_error_pkts;
-	__le64	tx_discard_pkts;
-	__le64	tx_ucast_bytes;
-	__le64	tx_mcast_bytes;
-	__le64	tx_bcast_bytes;
-	__le64	rx_tpa_eligible_pkt;
-	__le64	rx_tpa_eligible_bytes;
-	__le64	rx_tpa_pkt;
-	__le64	rx_tpa_bytes;
-	__le64	rx_tpa_errors;
-	__le64	rx_tpa_events;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_clr_stats_input (size:192b/24B) */
-struct hwrm_func_clr_stats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	unused_0[6];
-};
-
-/* hwrm_func_clr_stats_output (size:128b/16B) */
-struct hwrm_func_clr_stats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_vf_resc_free_input (size:192b/24B) */
-struct hwrm_func_vf_resc_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	vf_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_func_vf_resc_free_output (size:128b/16B) */
-struct hwrm_func_vf_resc_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_drv_rgtr_input (size:896b/112B) */
-struct hwrm_func_drv_rgtr_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define FUNC_DRV_RGTR_REQ_FLAGS_FWD_ALL_MODE                     0x1UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_FWD_NONE_MODE                    0x2UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE                   0x4UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_FLOW_HANDLE_64BIT_MODE           0x8UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT                0x10UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT           0x20UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT                   0x40UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_FAST_RESET_SUPPORT               0x80UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_RSS_STRICT_HASH_TYPE_SUPPORT     0x100UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT                 0x200UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_ASYM_QUEUE_CFG_SUPPORT           0x400UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_TF_INGRESS_NIC_FLOW_MODE         0x800UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_TF_EGRESS_NIC_FLOW_MODE          0x1000UL
-	__le32	enables;
-	#define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE             0x1UL
-	#define FUNC_DRV_RGTR_REQ_ENABLES_VER                 0x2UL
-	#define FUNC_DRV_RGTR_REQ_ENABLES_TIMESTAMP           0x4UL
-	#define FUNC_DRV_RGTR_REQ_ENABLES_VF_REQ_FWD          0x8UL
-	#define FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD     0x10UL
-	__le16	os_type;
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_UNKNOWN   0x0UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_OTHER     0x1UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_MSDOS     0xeUL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_WINDOWS   0x12UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_SOLARIS   0x1dUL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX     0x24UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_FREEBSD   0x2aUL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_ESXI      0x68UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_WIN864    0x73UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_WIN2012R2 0x74UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_UEFI      0x8000UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_LAST     FUNC_DRV_RGTR_REQ_OS_TYPE_UEFI
-	u8	ver_maj_8b;
-	u8	ver_min_8b;
-	u8	ver_upd_8b;
-	u8	unused_0[3];
-	__le32	timestamp;
-	u8	unused_1[4];
-	__le32	vf_req_fwd[8];
-	__le32	async_event_fwd[8];
-	__le16	ver_maj;
-	__le16	ver_min;
-	__le16	ver_upd;
-	__le16	ver_patch;
-};
-
-/* hwrm_func_drv_rgtr_output (size:128b/16B) */
-struct hwrm_func_drv_rgtr_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED     0x1UL
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_func_drv_unrgtr_input (size:192b/24B) */
-struct hwrm_func_drv_unrgtr_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define FUNC_DRV_UNRGTR_REQ_FLAGS_PREPARE_FOR_SHUTDOWN     0x1UL
-	u8	unused_0[4];
-};
-
-/* hwrm_func_drv_unrgtr_output (size:128b/16B) */
-struct hwrm_func_drv_unrgtr_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_buf_rgtr_input (size:1024b/128B) */
-struct hwrm_func_buf_rgtr_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_BUF_RGTR_REQ_ENABLES_VF_ID            0x1UL
-	#define FUNC_BUF_RGTR_REQ_ENABLES_ERR_BUF_ADDR     0x2UL
-	__le16	vf_id;
-	__le16	req_buf_num_pages;
-	__le16	req_buf_page_size;
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_16B 0x4UL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_4K  0xcUL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_8K  0xdUL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_64K 0x10UL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_2M  0x15UL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_4M  0x16UL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_1G  0x1eUL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_LAST FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_1G
-	__le16	req_buf_len;
-	__le16	resp_buf_len;
-	u8	unused_0[2];
-	__le64	req_buf_page_addr0;
-	__le64	req_buf_page_addr1;
-	__le64	req_buf_page_addr2;
-	__le64	req_buf_page_addr3;
-	__le64	req_buf_page_addr4;
-	__le64	req_buf_page_addr5;
-	__le64	req_buf_page_addr6;
-	__le64	req_buf_page_addr7;
-	__le64	req_buf_page_addr8;
-	__le64	req_buf_page_addr9;
-	__le64	error_buf_addr;
-	__le64	resp_buf_addr;
-};
-
-/* hwrm_func_buf_rgtr_output (size:128b/16B) */
-struct hwrm_func_buf_rgtr_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_drv_qver_input (size:192b/24B) */
-struct hwrm_func_drv_qver_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	reserved;
-	__le16	fid;
-	u8	driver_type;
-	#define FUNC_DRV_QVER_REQ_DRIVER_TYPE_L2   0x0UL
-	#define FUNC_DRV_QVER_REQ_DRIVER_TYPE_ROCE 0x1UL
-	#define FUNC_DRV_QVER_REQ_DRIVER_TYPE_LAST FUNC_DRV_QVER_REQ_DRIVER_TYPE_ROCE
-	u8	unused_0;
-};
-
-/* hwrm_func_drv_qver_output (size:256b/32B) */
-struct hwrm_func_drv_qver_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	os_type;
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_UNKNOWN   0x0UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_OTHER     0x1UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_MSDOS     0xeUL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_WINDOWS   0x12UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_SOLARIS   0x1dUL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_LINUX     0x24UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_FREEBSD   0x2aUL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_ESXI      0x68UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_WIN864    0x73UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_WIN2012R2 0x74UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_UEFI      0x8000UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_LAST     FUNC_DRV_QVER_RESP_OS_TYPE_UEFI
-	u8	ver_maj_8b;
-	u8	ver_min_8b;
-	u8	ver_upd_8b;
-	u8	unused_0[3];
-	__le16	ver_maj;
-	__le16	ver_min;
-	__le16	ver_upd;
-	__le16	ver_patch;
-	u8	unused_1[7];
-	u8	valid;
-};
-
-/* hwrm_func_resource_qcaps_input (size:192b/24B) */
-struct hwrm_func_resource_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	unused_0[6];
-};
-
-/* hwrm_func_resource_qcaps_output (size:704b/88B) */
-struct hwrm_func_resource_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	max_vfs;
-	__le16	max_msix;
-	__le16	vf_reservation_strategy;
-	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MAXIMAL        0x0UL
-	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MINIMAL        0x1UL
-	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MINIMAL_STATIC 0x2UL
-	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_LAST          FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MINIMAL_STATIC
-	__le16	min_rsscos_ctx;
-	__le16	max_rsscos_ctx;
-	__le16	min_cmpl_rings;
-	__le16	max_cmpl_rings;
-	__le16	min_tx_rings;
-	__le16	max_tx_rings;
-	__le16	min_rx_rings;
-	__le16	max_rx_rings;
-	__le16	min_l2_ctxs;
-	__le16	max_l2_ctxs;
-	__le16	min_vnics;
-	__le16	max_vnics;
-	__le16	min_stat_ctx;
-	__le16	max_stat_ctx;
-	__le16	min_hw_ring_grps;
-	__le16	max_hw_ring_grps;
-	__le16	max_tx_scheduler_inputs;
-	__le16	flags;
-	#define FUNC_RESOURCE_QCAPS_RESP_FLAGS_MIN_GUARANTEED     0x1UL
-	__le16	min_msix;
-	__le32	min_ktls_tx_key_ctxs;
-	__le32	max_ktls_tx_key_ctxs;
-	__le32	min_ktls_rx_key_ctxs;
-	__le32	max_ktls_rx_key_ctxs;
-	__le32	min_quic_tx_key_ctxs;
-	__le32	max_quic_tx_key_ctxs;
-	__le32	min_quic_rx_key_ctxs;
-	__le32	max_quic_rx_key_ctxs;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_func_vf_resource_cfg_input (size:704b/88B) */
-struct hwrm_func_vf_resource_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	vf_id;
-	__le16	max_msix;
-	__le16	min_rsscos_ctx;
-	__le16	max_rsscos_ctx;
-	__le16	min_cmpl_rings;
-	__le16	max_cmpl_rings;
-	__le16	min_tx_rings;
-	__le16	max_tx_rings;
-	__le16	min_rx_rings;
-	__le16	max_rx_rings;
-	__le16	min_l2_ctxs;
-	__le16	max_l2_ctxs;
-	__le16	min_vnics;
-	__le16	max_vnics;
-	__le16	min_stat_ctx;
-	__le16	max_stat_ctx;
-	__le16	min_hw_ring_grps;
-	__le16	max_hw_ring_grps;
-	__le16	flags;
-	#define FUNC_VF_RESOURCE_CFG_REQ_FLAGS_MIN_GUARANTEED     0x1UL
-	__le16	min_msix;
-	__le32	min_ktls_tx_key_ctxs;
-	__le32	max_ktls_tx_key_ctxs;
-	__le32	min_ktls_rx_key_ctxs;
-	__le32	max_ktls_rx_key_ctxs;
-	__le32	min_quic_tx_key_ctxs;
-	__le32	max_quic_tx_key_ctxs;
-	__le32	min_quic_rx_key_ctxs;
-	__le32	max_quic_rx_key_ctxs;
-};
-
-/* hwrm_func_vf_resource_cfg_output (size:384b/48B) */
-struct hwrm_func_vf_resource_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	reserved_rsscos_ctx;
-	__le16	reserved_cmpl_rings;
-	__le16	reserved_tx_rings;
-	__le16	reserved_rx_rings;
-	__le16	reserved_l2_ctxs;
-	__le16	reserved_vnics;
-	__le16	reserved_stat_ctx;
-	__le16	reserved_hw_ring_grps;
-	__le32	reserved_ktls_tx_key_ctxs;
-	__le32	reserved_ktls_rx_key_ctxs;
-	__le32	reserved_quic_tx_key_ctxs;
-	__le32	reserved_quic_rx_key_ctxs;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_backing_store_qcaps_input (size:128b/16B) */
-struct hwrm_func_backing_store_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_func_backing_store_qcaps_output (size:832b/104B) */
-struct hwrm_func_backing_store_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	qp_max_entries;
-	__le16	qp_min_qp1_entries;
-	__le16	qp_max_l2_entries;
-	__le16	qp_entry_size;
-	__le16	srq_max_l2_entries;
-	__le32	srq_max_entries;
-	__le16	srq_entry_size;
-	__le16	cq_max_l2_entries;
-	__le32	cq_max_entries;
-	__le16	cq_entry_size;
-	__le16	vnic_max_vnic_entries;
-	__le16	vnic_max_ring_table_entries;
-	__le16	vnic_entry_size;
-	__le32	stat_max_entries;
-	__le16	stat_entry_size;
-	__le16	tqm_entry_size;
-	__le32	tqm_min_entries_per_ring;
-	__le32	tqm_max_entries_per_ring;
-	__le32	mrav_max_entries;
-	__le16	mrav_entry_size;
-	__le16	tim_entry_size;
-	__le32	tim_max_entries;
-	__le16	mrav_num_entries_units;
-	u8	tqm_entries_multiple;
-	u8	ctx_kind_initializer;
-	__le16	ctx_init_mask;
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_QP       0x1UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_SRQ      0x2UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_CQ       0x4UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_VNIC     0x8UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_STAT     0x10UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_MRAV     0x20UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_TKC      0x40UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_RKC      0x80UL
-	u8	qp_init_offset;
-	u8	srq_init_offset;
-	u8	cq_init_offset;
-	u8	vnic_init_offset;
-	u8	tqm_fp_rings_count;
-	u8	stat_init_offset;
-	u8	mrav_init_offset;
-	u8	tqm_fp_rings_count_ext;
-	u8	tkc_init_offset;
-	u8	rkc_init_offset;
-	__le16	tkc_entry_size;
-	__le16	rkc_entry_size;
-	__le32	tkc_max_entries;
-	__le32	rkc_max_entries;
-	__le16	fast_qpmd_qp_num_entries;
-	u8	rsvd1[5];
-	u8	valid;
-};
-
-/* tqm_fp_ring_cfg (size:128b/16B) */
-struct tqm_fp_ring_cfg {
-	u8	tqm_ring_pg_size_tqm_ring_lvl;
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_MASK      0xfUL
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_SFT       0
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_0       0x0UL
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_1       0x1UL
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_2       0x2UL
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LAST       TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_2
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_MASK  0xf0UL
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_SFT   4
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_LAST   TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_1G
-	u8	unused[3];
-	__le32	tqm_ring_num_entries;
-	__le64	tqm_ring_page_dir;
-};
-
-/* hwrm_func_backing_store_cfg_input (size:2688b/336B) */
-struct hwrm_func_backing_store_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define FUNC_BACKING_STORE_CFG_REQ_FLAGS_PREBOOT_MODE               0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_FLAGS_MRAV_RESERVATION_SPLIT     0x2UL
-	__le32	enables;
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP               0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_SRQ              0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_CQ               0x4UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_VNIC             0x8UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_STAT             0x10UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP           0x20UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING0        0x40UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING1        0x80UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING2        0x100UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING3        0x200UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING4        0x400UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING5        0x800UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING6        0x1000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING7        0x2000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV             0x4000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM              0x8000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING8        0x10000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING9        0x20000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING10       0x40000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TKC              0x80000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_RKC              0x100000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP_FAST_QPMD     0x200000UL
-	u8	qpc_pg_size_qpc_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G
-	u8	srq_pg_size_srq_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G
-	u8	cq_pg_size_cq_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G
-	u8	vnic_pg_size_vnic_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G
-	u8	stat_pg_size_stat_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G
-	u8	tqm_sp_pg_size_tqm_sp_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G
-	u8	tqm_ring0_pg_size_tqm_ring0_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G
-	u8	tqm_ring1_pg_size_tqm_ring1_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G
-	u8	tqm_ring2_pg_size_tqm_ring2_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G
-	u8	tqm_ring3_pg_size_tqm_ring3_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G
-	u8	tqm_ring4_pg_size_tqm_ring4_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G
-	u8	tqm_ring5_pg_size_tqm_ring5_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G
-	u8	tqm_ring6_pg_size_tqm_ring6_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G
-	u8	tqm_ring7_pg_size_tqm_ring7_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G
-	u8	mrav_pg_size_mrav_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G
-	u8	tim_pg_size_tim_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G
-	__le64	qpc_page_dir;
-	__le64	srq_page_dir;
-	__le64	cq_page_dir;
-	__le64	vnic_page_dir;
-	__le64	stat_page_dir;
-	__le64	tqm_sp_page_dir;
-	__le64	tqm_ring0_page_dir;
-	__le64	tqm_ring1_page_dir;
-	__le64	tqm_ring2_page_dir;
-	__le64	tqm_ring3_page_dir;
-	__le64	tqm_ring4_page_dir;
-	__le64	tqm_ring5_page_dir;
-	__le64	tqm_ring6_page_dir;
-	__le64	tqm_ring7_page_dir;
-	__le64	mrav_page_dir;
-	__le64	tim_page_dir;
-	__le32	qp_num_entries;
-	__le32	srq_num_entries;
-	__le32	cq_num_entries;
-	__le32	stat_num_entries;
-	__le32	tqm_sp_num_entries;
-	__le32	tqm_ring0_num_entries;
-	__le32	tqm_ring1_num_entries;
-	__le32	tqm_ring2_num_entries;
-	__le32	tqm_ring3_num_entries;
-	__le32	tqm_ring4_num_entries;
-	__le32	tqm_ring5_num_entries;
-	__le32	tqm_ring6_num_entries;
-	__le32	tqm_ring7_num_entries;
-	__le32	mrav_num_entries;
-	__le32	tim_num_entries;
-	__le16	qp_num_qp1_entries;
-	__le16	qp_num_l2_entries;
-	__le16	qp_entry_size;
-	__le16	srq_num_l2_entries;
-	__le16	srq_entry_size;
-	__le16	cq_num_l2_entries;
-	__le16	cq_entry_size;
-	__le16	vnic_num_vnic_entries;
-	__le16	vnic_num_ring_table_entries;
-	__le16	vnic_entry_size;
-	__le16	stat_entry_size;
-	__le16	tqm_entry_size;
-	__le16	mrav_entry_size;
-	__le16	tim_entry_size;
-	u8	tqm_ring8_pg_size_tqm_ring_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_1G
-	u8	ring8_unused[3];
-	__le32	tqm_ring8_num_entries;
-	__le64	tqm_ring8_page_dir;
-	u8	tqm_ring9_pg_size_tqm_ring_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_1G
-	u8	ring9_unused[3];
-	__le32	tqm_ring9_num_entries;
-	__le64	tqm_ring9_page_dir;
-	u8	tqm_ring10_pg_size_tqm_ring_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_1G
-	u8	ring10_unused[3];
-	__le32	tqm_ring10_num_entries;
-	__le64	tqm_ring10_page_dir;
-	__le32	tkc_num_entries;
-	__le32	rkc_num_entries;
-	__le64	tkc_page_dir;
-	__le64	rkc_page_dir;
-	__le16	tkc_entry_size;
-	__le16	rkc_entry_size;
-	u8	tkc_pg_size_tkc_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_1G
-	u8	rkc_pg_size_rkc_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_1G
-	__le16	qp_num_fast_qpmd_entries;
-};
-
-/* hwrm_func_backing_store_cfg_output (size:128b/16B) */
-struct hwrm_func_backing_store_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_error_recovery_qcfg_input (size:192b/24B) */
-struct hwrm_error_recovery_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	unused_0[8];
-};
-
-/* hwrm_error_recovery_qcfg_output (size:1664b/208B) */
-struct hwrm_error_recovery_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define ERROR_RECOVERY_QCFG_RESP_FLAGS_HOST       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU     0x2UL
-	__le32	driver_polling_freq;
-	__le32	master_func_wait_period;
-	__le32	normal_func_wait_period;
-	__le32	master_func_wait_period_after_reset;
-	__le32	max_bailout_time_after_reset;
-	__le32	fw_health_status_reg;
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_MASK    0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_SFT     0
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_GRC       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR0      0x2UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1      0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_MASK          0xfffffffcUL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SFT           2
-	__le32	fw_heartbeat_reg;
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_MASK    0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_SFT     0
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_GRC       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR0      0x2UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1      0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_MASK          0xfffffffcUL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SFT           2
-	__le32	fw_reset_cnt_reg;
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_MASK    0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_SFT     0
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_GRC       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR0      0x2UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1      0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_MASK          0xfffffffcUL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SFT           2
-	__le32	reset_inprogress_reg;
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_MASK    0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_SFT     0
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_GRC       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR0      0x2UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1      0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_MASK          0xfffffffcUL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SFT           2
-	__le32	reset_inprogress_reg_mask;
-	u8	unused_0[3];
-	u8	reg_array_cnt;
-	__le32	reset_reg[16];
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_MASK    0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_SFT     0
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_GRC       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR0      0x2UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1      0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_MASK          0xfffffffcUL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SFT           2
-	__le32	reset_reg_val[16];
-	u8	delay_after_reset[16];
-	__le32	err_recovery_cnt_reg;
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_MASK    0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_SFT     0
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_GRC       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR0      0x2UL
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR1      0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR1
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_MASK          0xfffffffcUL
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SFT           2
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_func_echo_response_input (size:192b/24B) */
-struct hwrm_func_echo_response_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	event_data1;
-	__le32	event_data2;
-};
-
-/* hwrm_func_echo_response_output (size:128b/16B) */
-struct hwrm_func_echo_response_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_ptp_pin_qcfg_input (size:192b/24B) */
-struct hwrm_func_ptp_pin_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	unused_0[8];
-};
-
-/* hwrm_func_ptp_pin_qcfg_output (size:128b/16B) */
-struct hwrm_func_ptp_pin_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	num_pins;
-	u8	state;
-	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN0_ENABLED     0x1UL
-	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN1_ENABLED     0x2UL
-	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN2_ENABLED     0x4UL
-	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN3_ENABLED     0x8UL
-	u8	pin0_usage;
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_NONE     0x0UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_PPS_IN   0x1UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_PPS_OUT  0x2UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_IN  0x3UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_OUT 0x4UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_LAST    FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_OUT
-	u8	pin1_usage;
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_NONE     0x0UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_PPS_IN   0x1UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_PPS_OUT  0x2UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_IN  0x3UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_OUT 0x4UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_LAST    FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_OUT
-	u8	pin2_usage;
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_NONE                      0x0UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_IN                    0x1UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_OUT                   0x2UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_IN                   0x3UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_OUT                  0x4UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_LAST                     FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT
-	u8	pin3_usage;
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_NONE                      0x0UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_IN                    0x1UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_OUT                   0x2UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_IN                   0x3UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_OUT                  0x4UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_LAST                     FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT
-	u8	unused_0;
-	u8	valid;
-};
-
-/* hwrm_func_ptp_pin_cfg_input (size:256b/32B) */
-struct hwrm_func_ptp_pin_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN0_STATE     0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN0_USAGE     0x2UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN1_STATE     0x4UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN1_USAGE     0x8UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN2_STATE     0x10UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN2_USAGE     0x20UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN3_STATE     0x40UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN3_USAGE     0x80UL
-	u8	pin0_state;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_DISABLED 0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_ENABLED  0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_ENABLED
-	u8	pin0_usage;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_NONE     0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_PPS_IN   0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_PPS_OUT  0x2UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_IN  0x3UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_OUT 0x4UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_OUT
-	u8	pin1_state;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_DISABLED 0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_ENABLED  0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_ENABLED
-	u8	pin1_usage;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_NONE     0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_PPS_IN   0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_PPS_OUT  0x2UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_IN  0x3UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_OUT 0x4UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_OUT
-	u8	pin2_state;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_DISABLED 0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_ENABLED  0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_ENABLED
-	u8	pin2_usage;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_NONE                      0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_IN                    0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_OUT                   0x2UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_IN                   0x3UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_OUT                  0x4UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_LAST                     FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT
-	u8	pin3_state;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_DISABLED 0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_ENABLED  0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_ENABLED
-	u8	pin3_usage;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_NONE                      0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_IN                    0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_OUT                   0x2UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_IN                   0x3UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_OUT                  0x4UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_LAST                     FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT
-	u8	unused_0[4];
-};
-
-/* hwrm_func_ptp_pin_cfg_output (size:128b/16B) */
-struct hwrm_func_ptp_pin_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_ptp_cfg_input (size:384b/48B) */
-struct hwrm_func_ptp_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	enables;
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_PPS_EVENT               0x1UL
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_DLL_SOURCE     0x2UL
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_DLL_PHASE      0x4UL
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PERIOD     0x8UL
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_UP         0x10UL
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PHASE      0x20UL
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_SET_TIME                0x40UL
-	u8	ptp_pps_event;
-	#define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_INTERNAL     0x1UL
-	#define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_EXTERNAL     0x2UL
-	u8	ptp_freq_adj_dll_source;
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_NONE    0x0UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_0  0x1UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_1  0x2UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_2  0x3UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_3  0x4UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_0  0x5UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_1  0x6UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_2  0x7UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_3  0x8UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_INVALID 0xffUL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_LAST   FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_INVALID
-	u8	ptp_freq_adj_dll_phase;
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_NONE 0x0UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_4K   0x1UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_8K   0x2UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_10M  0x3UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_25M  0x4UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_LAST FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_25M
-	u8	unused_0[3];
-	__le32	ptp_freq_adj_ext_period;
-	__le32	ptp_freq_adj_ext_up;
-	__le32	ptp_freq_adj_ext_phase_lower;
-	__le32	ptp_freq_adj_ext_phase_upper;
-	__le64	ptp_set_time;
-};
-
-/* hwrm_func_ptp_cfg_output (size:128b/16B) */
-struct hwrm_func_ptp_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_ptp_ts_query_input (size:192b/24B) */
-struct hwrm_func_ptp_ts_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define FUNC_PTP_TS_QUERY_REQ_FLAGS_PPS_TIME     0x1UL
-	#define FUNC_PTP_TS_QUERY_REQ_FLAGS_PTM_TIME     0x2UL
-	u8	unused_0[4];
-};
-
-/* hwrm_func_ptp_ts_query_output (size:320b/40B) */
-struct hwrm_func_ptp_ts_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	pps_event_ts;
-	__le64	ptm_local_ts;
-	__le64	ptm_system_ts;
-	__le32	ptm_link_delay;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_func_ptp_ext_cfg_input (size:256b/32B) */
-struct hwrm_func_ptp_ext_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	enables;
-	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_MASTER_FID     0x1UL
-	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_FID        0x2UL
-	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_MODE       0x4UL
-	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_FAILOVER_TIMER     0x8UL
-	__le16	phc_master_fid;
-	__le16	phc_sec_fid;
-	u8	phc_sec_mode;
-	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_SWITCH  0x0UL
-	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_ALL     0x1UL
-	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY 0x2UL
-	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_LAST   FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY
-	u8	unused_0;
-	__le32	failover_timer;
-	u8	unused_1[4];
-};
-
-/* hwrm_func_ptp_ext_cfg_output (size:128b/16B) */
-struct hwrm_func_ptp_ext_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_ptp_ext_qcfg_input (size:192b/24B) */
-struct hwrm_func_ptp_ext_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	unused_0[8];
-};
-
-/* hwrm_func_ptp_ext_qcfg_output (size:256b/32B) */
-struct hwrm_func_ptp_ext_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	phc_master_fid;
-	__le16	phc_sec_fid;
-	__le16	phc_active_fid0;
-	__le16	phc_active_fid1;
-	__le32	last_failover_event;
-	__le16	from_fid;
-	__le16	to_fid;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_backing_store_cfg_v2_input (size:512b/64B) */
-struct hwrm_func_backing_store_cfg_v2_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	type;
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP                  0x0UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ                 0x1UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ                  0x2UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC                0x3UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT                0x4UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING         0x5UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING         0x6UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV                0xeUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM                 0xfUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TX_CK               0x13UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RX_CK               0x14UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING         0x15UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION       0x1dUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT_TRACE           0x1eUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT_TRACE           0x20UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT2_TRACE          0x21UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA0_TRACE           0x26UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA1_TRACE           0x27UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA2_TRACE           0x28UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID             0xffffUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID
-	__le16	instance;
-	__le32	flags;
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_PREBOOT_MODE        0x1UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_BS_CFG_ALL_DONE     0x2UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_BS_EXTEND           0x4UL
-	__le64	page_dir;
-	__le32	num_entries;
-	__le16	entry_size;
-	u8	page_size_pbl_level;
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_MASK  0xfUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_SFT   0
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_0   0x0UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_1   0x1UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2   0x2UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LAST   FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_LAST   FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G
-	u8	subtype_valid_cnt;
-	__le32	split_entry_0;
-	__le32	split_entry_1;
-	__le32	split_entry_2;
-	__le32	split_entry_3;
-	__le32	enables;
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_ENABLES_NEXT_BS_OFFSET     0x1UL
-	__le32	next_bs_offset;
-};
-
-/* hwrm_func_backing_store_cfg_v2_output (size:128b/16B) */
-struct hwrm_func_backing_store_cfg_v2_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	rsvd0[7];
-	u8	valid;
-};
-
-/* hwrm_func_backing_store_qcfg_v2_input (size:192b/24B) */
-struct hwrm_func_backing_store_qcfg_v2_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	type;
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QP                  0x0UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ                 0x1UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ                  0x2UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_VNIC                0x3UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_STAT                0x4UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SP_TQM_RING         0x5UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_FP_TQM_RING         0x6UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MRAV                0xeUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TIM                 0xfUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TX_CK               0x13UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RX_CK               0x14UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MP_TQM_RING         0x15UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_XID_PARTITION_TABLE 0x1dUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRT_TRACE           0x1eUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CRT_TRACE           0x20UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CRT2_TRACE          0x21UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA0_TRACE           0x26UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA1_TRACE           0x27UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA2_TRACE           0x28UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID             0xffffUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID
-	__le16	instance;
-	u8	rsvd[4];
-};
-
-/* hwrm_func_backing_store_qcfg_v2_output (size:448b/56B) */
-struct hwrm_func_backing_store_qcfg_v2_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	type;
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP                  0x0UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ                 0x1UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ                  0x2UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC                0x3UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT                0x4UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING         0x5UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING         0x6UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV                0xeUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM                 0xfUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TX_CK               0x13UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RX_CK               0x14UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING         0x15UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE           0x1cUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION       0x1dUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT_TRACE           0x1eUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT2_TRACE          0x1fUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT_TRACE           0x20UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT2_TRACE          0x21UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP0_TRACE         0x22UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_L2_HWRM_TRACE       0x23UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_ROCE_HWRM_TRACE     0x24UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA0_TRACE           0x26UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA1_TRACE           0x27UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA2_TRACE           0x28UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP1_TRACE         0x29UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID             0xffffUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST               FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID
-	__le16	instance;
-	__le32	flags;
-	__le64	page_dir;
-	__le32	num_entries;
-	u8	page_size_pbl_level;
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_MASK  0xfUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_SFT   0
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_0   0x0UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_1   0x1UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2   0x2UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LAST   FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_LAST   FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G
-	u8	subtype_valid_cnt;
-	u8	rsvd[2];
-	__le32	split_entry_0;
-	__le32	split_entry_1;
-	__le32	split_entry_2;
-	__le32	split_entry_3;
-	u8	rsvd2[7];
-	u8	valid;
-};
-
-/* qpc_split_entries (size:128b/16B) */
-struct qpc_split_entries {
-	__le32	qp_num_l2_entries;
-	__le32	qp_num_qp1_entries;
-	__le32	qp_num_fast_qpmd_entries;
-	__le32	rsvd;
-};
-
-/* srq_split_entries (size:128b/16B) */
-struct srq_split_entries {
-	__le32	srq_num_l2_entries;
-	__le32	rsvd;
-	__le32	rsvd2[2];
-};
-
-/* cq_split_entries (size:128b/16B) */
-struct cq_split_entries {
-	__le32	cq_num_l2_entries;
-	__le32	rsvd;
-	__le32	rsvd2[2];
-};
-
-/* vnic_split_entries (size:128b/16B) */
-struct vnic_split_entries {
-	__le32	vnic_num_vnic_entries;
-	__le32	rsvd;
-	__le32	rsvd2[2];
-};
-
-/* mrav_split_entries (size:128b/16B) */
-struct mrav_split_entries {
-	__le32	mrav_num_av_entries;
-	__le32	rsvd;
-	__le32	rsvd2[2];
-};
-
-/* ts_split_entries (size:128b/16B) */
-struct ts_split_entries {
-	__le32	region_num_entries;
-	u8	tsid;
-	u8	lkup_static_bkt_cnt_exp[2];
-	u8	rsvd;
-	__le32	rsvd2[2];
-};
-
-/* ck_split_entries (size:128b/16B) */
-struct ck_split_entries {
-	__le32	num_quic_entries;
-	__le32	rsvd;
-	__le32	rsvd2[2];
-};
-
-/* hwrm_func_backing_store_qcaps_v2_input (size:192b/24B) */
-struct hwrm_func_backing_store_qcaps_v2_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	type;
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP                  0x0UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ                 0x1UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ                  0x2UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC                0x3UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT                0x4UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING         0x5UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING         0x6UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV                0xeUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM                 0xfUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TX_CK               0x13UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RX_CK               0x14UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING         0x15UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION       0x1dUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE           0x1eUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE           0x20UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT2_TRACE          0x21UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA0_TRACE           0x26UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA1_TRACE           0x27UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA2_TRACE           0x28UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID             0xffffUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID
-	u8	rsvd[6];
-};
-
-/* hwrm_func_backing_store_qcaps_v2_output (size:448b/56B) */
-struct hwrm_func_backing_store_qcaps_v2_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	type;
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP                  0x0UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ                 0x1UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ                  0x2UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC                0x3UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT                0x4UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING         0x5UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING         0x6UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV                0xeUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM                 0xfUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TX_CK               0x13UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RX_CK               0x14UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING         0x15UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW        0x16UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW        0x17UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW       0x18UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW        0x19UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE           0x1cUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION       0x1dUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT_TRACE           0x1eUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT2_TRACE          0x1fUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT_TRACE           0x20UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT2_TRACE          0x21UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP0_TRACE         0x22UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_L2_HWRM_TRACE       0x23UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_ROCE_HWRM_TRACE     0x24UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA0_TRACE           0x26UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA1_TRACE           0x27UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA2_TRACE           0x28UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP1_TRACE         0x29UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID             0xffffUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST               FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID
-	__le16	entry_size;
-	__le32	flags;
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT            0x1UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID                      0x2UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_DRIVER_MANAGED_MEMORY           0x4UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ROCE_QP_PSEUDO_STATIC_ALLOC     0x8UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_FW_DBG_TRACE                    0x10UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_FW_BIN_DBG_TRACE                0x20UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_NEXT_BS_OFFSET                  0x40UL
-	__le32	instance_bit_map;
-	u8	ctx_init_value;
-	u8	ctx_init_offset;
-	u8	entry_multiple;
-	u8	rsvd;
-	__le32	max_num_entries;
-	__le32	min_num_entries;
-	__le16	next_valid_type;
-	u8	subtype_valid_cnt;
-	u8	exact_cnt_bit_map;
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_0_EXACT     0x1UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_1_EXACT     0x2UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_2_EXACT     0x4UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_3_EXACT     0x8UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_UNUSED_MASK             0xf0UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_UNUSED_SFT              4
-	__le32	split_entry_0;
-	__le32	split_entry_1;
-	__le32	split_entry_2;
-	__le32	split_entry_3;
-	__le16	max_instance_count;
-	u8	rsvd3;
-	u8	valid;
-};
-
-/* hwrm_func_dbr_pacing_qcfg_input (size:128b/16B) */
-struct hwrm_func_dbr_pacing_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_func_dbr_pacing_qcfg_output (size:512b/64B) */
-struct hwrm_func_dbr_pacing_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define FUNC_DBR_PACING_QCFG_RESP_FLAGS_DBR_NQ_EVENT_ENABLED     0x1UL
-	u8	unused_0[7];
-	__le32	dbr_stat_db_fifo_reg;
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_MASK    0x3UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_SFT     0
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_GRC       0x1UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR0      0x2UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1      0x3UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_LAST     FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_MASK          0xfffffffcUL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SFT           2
-	__le32	dbr_stat_db_fifo_reg_watermark_mask;
-	u8	dbr_stat_db_fifo_reg_watermark_shift;
-	u8	unused_1[3];
-	__le32	dbr_stat_db_fifo_reg_fifo_room_mask;
-	u8	dbr_stat_db_fifo_reg_fifo_room_shift;
-	u8	unused_2[3];
-	__le32	dbr_throttling_aeq_arm_reg;
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_MASK    0x3UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_SFT     0
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_GRC       0x1UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR0      0x2UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1      0x3UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_LAST     FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_MASK          0xfffffffcUL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SFT           2
-	u8	dbr_throttling_aeq_arm_reg_val;
-	u8	unused_3[3];
-	__le32	dbr_stat_db_max_fifo_depth;
-	__le32	primary_nq_id;
-	__le32	pacing_threshold;
-	u8	unused_4[7];
-	u8	valid;
-};
-
-/* hwrm_func_drv_if_change_input (size:192b/24B) */
-struct hwrm_func_drv_if_change_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP     0x1UL
-	__le32	unused;
-};
-
-/* hwrm_func_drv_if_change_output (size:128b/16B) */
-struct hwrm_func_drv_if_change_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE           0x1UL
-	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE     0x2UL
-	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_CAPS_CHANGE           0x4UL
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_port_phy_cfg_input (size:512b/64B) */
-struct hwrm_port_phy_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define PORT_PHY_CFG_REQ_FLAGS_RESET_PHY                  0x1UL
-	#define PORT_PHY_CFG_REQ_FLAGS_DEPRECATED                 0x2UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FORCE                      0x4UL
-	#define PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG            0x8UL
-	#define PORT_PHY_CFG_REQ_FLAGS_EEE_ENABLE                 0x10UL
-	#define PORT_PHY_CFG_REQ_FLAGS_EEE_DISABLE                0x20UL
-	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_ENABLE          0x40UL
-	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_DISABLE         0x80UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_ENABLE         0x100UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_DISABLE        0x200UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_ENABLE        0x400UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE       0x800UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_ENABLE        0x1000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_DISABLE       0x2000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DWN             0x4000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_ENABLE       0x8000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_DISABLE      0x10000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_IEEE_ENABLE      0x20000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_IEEE_DISABLE     0x40000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_1XN_ENABLE       0x80000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_1XN_DISABLE      0x100000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_ENABLE      0x200000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_DISABLE     0x400000UL
-	__le32	enables;
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_MODE                     0x1UL
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_DUPLEX                   0x2UL
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_PAUSE                    0x4UL
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED               0x8UL
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED_MASK          0x10UL
-	#define PORT_PHY_CFG_REQ_ENABLES_WIRESPEED                     0x20UL
-	#define PORT_PHY_CFG_REQ_ENABLES_LPBK                          0x40UL
-	#define PORT_PHY_CFG_REQ_ENABLES_PREEMPHASIS                   0x80UL
-	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_PAUSE                   0x100UL
-	#define PORT_PHY_CFG_REQ_ENABLES_EEE_LINK_SPEED_MASK           0x200UL
-	#define PORT_PHY_CFG_REQ_ENABLES_TX_LPI_TIMER                  0x400UL
-	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_PAM4_LINK_SPEED         0x800UL
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_PAM4_LINK_SPEED_MASK     0x1000UL
-	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_LINK_SPEEDS2            0x2000UL
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEEDS2_MASK        0x4000UL
-	__le16	port_id;
-	__le16	force_link_speed;
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100MB 0x1UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB   0xaUL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_2GB   0x14UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_2_5GB 0x19UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10GB  0x64UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_20GB  0xc8UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_25GB  0xfaUL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_40GB  0x190UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10MB  0xffffUL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_LAST PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10MB
-	u8	auto_mode;
-	#define PORT_PHY_CFG_REQ_AUTO_MODE_NONE         0x0UL
-	#define PORT_PHY_CFG_REQ_AUTO_MODE_ALL_SPEEDS   0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_MODE_ONE_SPEED    0x2UL
-	#define PORT_PHY_CFG_REQ_AUTO_MODE_ONE_OR_BELOW 0x3UL
-	#define PORT_PHY_CFG_REQ_AUTO_MODE_SPEED_MASK   0x4UL
-	#define PORT_PHY_CFG_REQ_AUTO_MODE_LAST        PORT_PHY_CFG_REQ_AUTO_MODE_SPEED_MASK
-	u8	auto_duplex;
-	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_HALF 0x0UL
-	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_FULL 0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_BOTH 0x2UL
-	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_LAST PORT_PHY_CFG_REQ_AUTO_DUPLEX_BOTH
-	u8	auto_pause;
-	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_TX                0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_RX                0x2UL
-	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_AUTONEG_PAUSE     0x4UL
-	u8	mgmt_flag;
-	#define PORT_PHY_CFG_REQ_MGMT_FLAG_LINK_RELEASE     0x1UL
-	#define PORT_PHY_CFG_REQ_MGMT_FLAG_MGMT_VALID       0x80UL
-	__le16	auto_link_speed;
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100MB 0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_1GB   0xaUL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_2GB   0x14UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_2_5GB 0x19UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10GB  0x64UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_20GB  0xc8UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_25GB  0xfaUL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_40GB  0x190UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10MB  0xffffUL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_LAST PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10MB
-	__le16	auto_link_speed_mask;
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_100MBHD     0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_100MB       0x2UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_1GBHD       0x4UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_1GB         0x8UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_2GB         0x10UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_2_5GB       0x20UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10GB        0x40UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_20GB        0x80UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_25GB        0x100UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_40GB        0x200UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_50GB        0x400UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_100GB       0x800UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10MBHD      0x1000UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10MB        0x2000UL
-	u8	wirespeed;
-	#define PORT_PHY_CFG_REQ_WIRESPEED_OFF 0x0UL
-	#define PORT_PHY_CFG_REQ_WIRESPEED_ON  0x1UL
-	#define PORT_PHY_CFG_REQ_WIRESPEED_LAST PORT_PHY_CFG_REQ_WIRESPEED_ON
-	u8	lpbk;
-	#define PORT_PHY_CFG_REQ_LPBK_NONE     0x0UL
-	#define PORT_PHY_CFG_REQ_LPBK_LOCAL    0x1UL
-	#define PORT_PHY_CFG_REQ_LPBK_REMOTE   0x2UL
-	#define PORT_PHY_CFG_REQ_LPBK_EXTERNAL 0x3UL
-	#define PORT_PHY_CFG_REQ_LPBK_LAST    PORT_PHY_CFG_REQ_LPBK_EXTERNAL
-	u8	force_pause;
-	#define PORT_PHY_CFG_REQ_FORCE_PAUSE_TX     0x1UL
-	#define PORT_PHY_CFG_REQ_FORCE_PAUSE_RX     0x2UL
-	u8	unused_1;
-	__le32	preemphasis;
-	__le16	eee_link_speed_mask;
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD1     0x1UL
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_100MB     0x2UL
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD2     0x4UL
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_1GB       0x8UL
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD3     0x10UL
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD4     0x20UL
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_10GB      0x40UL
-	__le16	force_pam4_link_speed;
-	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB 0x7d0UL
-	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_LAST PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB
-	__le32	tx_lpi_timer;
-	#define PORT_PHY_CFG_REQ_TX_LPI_TIMER_MASK 0xffffffUL
-	#define PORT_PHY_CFG_REQ_TX_LPI_TIMER_SFT 0
-	__le16	auto_link_pam4_speed_mask;
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_50G      0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_100G     0x2UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_200G     0x4UL
-	__le16	force_link_speeds2;
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_1GB            0xaUL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_10GB           0x64UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_25GB           0xfaUL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_40GB           0x190UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB           0x1f4UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB          0x3e8UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB_PAM4_56   0x1f5UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_56  0x3e9UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_56  0x7d1UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_56  0xfa1UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_800GB_PAM4_112 0x1f42UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_LAST          PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_800GB_PAM4_112
-	__le16	auto_link_speeds2_mask;
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_1GB                0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_10GB               0x2UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_25GB               0x4UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_40GB               0x8UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_50GB               0x10UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB              0x20UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_50GB_PAM4_56       0x40UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_56      0x80UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_56      0x100UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_56      0x200UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_112     0x400UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_112     0x800UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_112     0x1000UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_800GB_PAM4_112     0x2000UL
-	u8	unused_2[6];
-};
-
-/* hwrm_port_phy_cfg_output (size:128b/16B) */
-struct hwrm_port_phy_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_port_phy_cfg_cmd_err (size:64b/8B) */
-struct hwrm_port_phy_cfg_cmd_err {
-	u8	code;
-	#define PORT_PHY_CFG_CMD_ERR_CODE_UNKNOWN       0x0UL
-	#define PORT_PHY_CFG_CMD_ERR_CODE_ILLEGAL_SPEED 0x1UL
-	#define PORT_PHY_CFG_CMD_ERR_CODE_RETRY         0x2UL
-	#define PORT_PHY_CFG_CMD_ERR_CODE_LAST         PORT_PHY_CFG_CMD_ERR_CODE_RETRY
-	u8	unused_0[7];
-};
-
-/* hwrm_port_phy_qcfg_input (size:192b/24B) */
-struct hwrm_port_phy_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_phy_qcfg_output (size:832b/104B) */
-struct hwrm_port_phy_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	link;
-	#define PORT_PHY_QCFG_RESP_LINK_NO_LINK 0x0UL
-	#define PORT_PHY_QCFG_RESP_LINK_SIGNAL  0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_LINK    0x2UL
-	#define PORT_PHY_QCFG_RESP_LINK_LAST   PORT_PHY_QCFG_RESP_LINK_LINK
-	u8	active_fec_signal_mode;
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_MASK                0xfUL
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_SFT                 0
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_NRZ                   0x0UL
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4                  0x1UL
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112              0x2UL
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_LAST                 PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_MASK                 0xf0UL
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_SFT                  4
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_NONE_ACTIVE        (0x0UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE74_ACTIVE    (0x1UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE91_ACTIVE    (0x2UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_1XN_ACTIVE   (0x3UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_IEEE_ACTIVE  (0x4UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_1XN_ACTIVE   (0x5UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE  (0x6UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_LAST                  PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE
-	__le16	link_speed;
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_100MB 0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_1GB   0xaUL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_2GB   0x14UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_2_5GB 0x19UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_10GB  0x64UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_20GB  0xc8UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_25GB  0xfaUL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_40GB  0x190UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_200GB 0x7d0UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_400GB 0xfa0UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_800GB 0x1f40UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_10MB  0xffffUL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_LINK_SPEED_10MB
-	u8	duplex_cfg;
-	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_HALF 0x0UL
-	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_FULL 0x1UL
-	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_LAST PORT_PHY_QCFG_RESP_DUPLEX_CFG_FULL
-	u8	pause;
-	#define PORT_PHY_QCFG_RESP_PAUSE_TX     0x1UL
-	#define PORT_PHY_QCFG_RESP_PAUSE_RX     0x2UL
-	__le16	support_speeds;
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100MBHD     0x1UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100MB       0x2UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_1GBHD       0x4UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_1GB         0x8UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_2GB         0x10UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_2_5GB       0x20UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10GB        0x40UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_20GB        0x80UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_25GB        0x100UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_40GB        0x200UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_50GB        0x400UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100GB       0x800UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10MBHD      0x1000UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10MB        0x2000UL
-	__le16	force_link_speed;
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_100MB 0x1UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_1GB   0xaUL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_2GB   0x14UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_2_5GB 0x19UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10GB  0x64UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_20GB  0xc8UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_25GB  0xfaUL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_40GB  0x190UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10MB  0xffffUL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10MB
-	u8	auto_mode;
-	#define PORT_PHY_QCFG_RESP_AUTO_MODE_NONE         0x0UL
-	#define PORT_PHY_QCFG_RESP_AUTO_MODE_ALL_SPEEDS   0x1UL
-	#define PORT_PHY_QCFG_RESP_AUTO_MODE_ONE_SPEED    0x2UL
-	#define PORT_PHY_QCFG_RESP_AUTO_MODE_ONE_OR_BELOW 0x3UL
-	#define PORT_PHY_QCFG_RESP_AUTO_MODE_SPEED_MASK   0x4UL
-	#define PORT_PHY_QCFG_RESP_AUTO_MODE_LAST        PORT_PHY_QCFG_RESP_AUTO_MODE_SPEED_MASK
-	u8	auto_pause;
-	#define PORT_PHY_QCFG_RESP_AUTO_PAUSE_TX                0x1UL
-	#define PORT_PHY_QCFG_RESP_AUTO_PAUSE_RX                0x2UL
-	#define PORT_PHY_QCFG_RESP_AUTO_PAUSE_AUTONEG_PAUSE     0x4UL
-	__le16	auto_link_speed;
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_100MB 0x1UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_1GB   0xaUL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_2GB   0x14UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_2_5GB 0x19UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10GB  0x64UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_20GB  0xc8UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_25GB  0xfaUL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_40GB  0x190UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10MB  0xffffUL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10MB
-	__le16	auto_link_speed_mask;
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_100MBHD     0x1UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_100MB       0x2UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_1GBHD       0x4UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_1GB         0x8UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_2GB         0x10UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_2_5GB       0x20UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10GB        0x40UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_20GB        0x80UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_25GB        0x100UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_40GB        0x200UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_50GB        0x400UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_100GB       0x800UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10MBHD      0x1000UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10MB        0x2000UL
-	u8	wirespeed;
-	#define PORT_PHY_QCFG_RESP_WIRESPEED_OFF 0x0UL
-	#define PORT_PHY_QCFG_RESP_WIRESPEED_ON  0x1UL
-	#define PORT_PHY_QCFG_RESP_WIRESPEED_LAST PORT_PHY_QCFG_RESP_WIRESPEED_ON
-	u8	lpbk;
-	#define PORT_PHY_QCFG_RESP_LPBK_NONE     0x0UL
-	#define PORT_PHY_QCFG_RESP_LPBK_LOCAL    0x1UL
-	#define PORT_PHY_QCFG_RESP_LPBK_REMOTE   0x2UL
-	#define PORT_PHY_QCFG_RESP_LPBK_EXTERNAL 0x3UL
-	#define PORT_PHY_QCFG_RESP_LPBK_LAST    PORT_PHY_QCFG_RESP_LPBK_EXTERNAL
-	u8	force_pause;
-	#define PORT_PHY_QCFG_RESP_FORCE_PAUSE_TX     0x1UL
-	#define PORT_PHY_QCFG_RESP_FORCE_PAUSE_RX     0x2UL
-	u8	module_status;
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NONE          0x0UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_DISABLETX     0x1UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_WARNINGMSG    0x2UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_PWRDOWN       0x3UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTINSERTED   0x4UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_CURRENTFAULT  0x5UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_OVERHEATED    0x6UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE 0xffUL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_LAST         PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE
-	__le32	preemphasis;
-	u8	phy_maj;
-	u8	phy_min;
-	u8	phy_bld;
-	u8	phy_type;
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_UNKNOWN          0x0UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASECR           0x1UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR4          0x2UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASELR           0x3UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASESR           0x4UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR2          0x5UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKX           0x6UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR           0x7UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASET            0x8UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASETE           0x9UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_SGMIIEXTPHY      0xaUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_L  0xbUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_S  0xcUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_N  0xdUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASESR       0xeUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR4     0xfUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR4     0x10UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR4     0x11UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER4     0x12UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR10    0x13UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASECR4      0x14UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASESR4      0x15UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASELR4      0x16UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASEER4      0x17UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_ACTIVE_CABLE 0x18UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASET         0x19UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASESX        0x1aUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASECX        0x1bUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR4     0x1cUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR4     0x1dUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR4     0x1eUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER4     0x1fUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASECR       0x20UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASESR       0x21UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASELR       0x22UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASEER       0x23UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR2     0x24UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR2     0x25UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR2     0x26UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2     0x27UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR      0x28UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR      0x29UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR      0x2aUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER      0x2bUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR2     0x2cUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR2     0x2dUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR2     0x2eUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER2     0x2fUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR8     0x30UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR8     0x31UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR8     0x32UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER8     0x33UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR4     0x34UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR4     0x35UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR4     0x36UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4     0x37UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASECR8     0x38UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASESR8     0x39UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASELR8     0x3aUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEER8     0x3bUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEFR8     0x3cUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEDR8     0x3dUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST            PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEDR8
-	u8	media_type;
-	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_UNKNOWN   0x0UL
-	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP        0x1UL
-	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_DAC       0x2UL
-	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_FIBRE     0x3UL
-	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_BACKPLANE 0x4UL
-	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_LAST     PORT_PHY_QCFG_RESP_MEDIA_TYPE_BACKPLANE
-	u8	xcvr_pkg_type;
-	#define PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_INTERNAL 0x1UL
-	#define PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_EXTERNAL 0x2UL
-	#define PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_LAST         PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_EXTERNAL
-	u8	eee_config_phy_addr;
-	#define PORT_PHY_QCFG_RESP_PHY_ADDR_MASK              0x1fUL
-	#define PORT_PHY_QCFG_RESP_PHY_ADDR_SFT               0
-	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_MASK            0xe0UL
-	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_SFT             5
-	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_EEE_ENABLED      0x20UL
-	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_EEE_ACTIVE       0x40UL
-	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_EEE_TX_LPI       0x80UL
-	u8	parallel_detect;
-	#define PORT_PHY_QCFG_RESP_PARALLEL_DETECT     0x1UL
-	__le16	link_partner_adv_speeds;
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_100MBHD     0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_100MB       0x2UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_1GBHD       0x4UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_1GB         0x8UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_2GB         0x10UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_2_5GB       0x20UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_10GB        0x40UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_20GB        0x80UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_25GB        0x100UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_40GB        0x200UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_50GB        0x400UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_100GB       0x800UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_10MBHD      0x1000UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_10MB        0x2000UL
-	u8	link_partner_adv_auto_mode;
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_NONE         0x0UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_ALL_SPEEDS   0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_ONE_SPEED    0x2UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_ONE_OR_BELOW 0x3UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_SPEED_MASK   0x4UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_LAST        PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_SPEED_MASK
-	u8	link_partner_adv_pause;
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_PAUSE_TX     0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_PAUSE_RX     0x2UL
-	__le16	adv_eee_link_speed_mask;
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD1     0x1UL
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_100MB     0x2UL
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD2     0x4UL
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_1GB       0x8UL
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD3     0x10UL
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD4     0x20UL
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_10GB      0x40UL
-	__le16	link_partner_adv_eee_link_speed_mask;
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD1     0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_100MB     0x2UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD2     0x4UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_1GB       0x8UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD3     0x10UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD4     0x20UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_10GB      0x40UL
-	__le32	xcvr_identifier_type_tx_lpi_timer;
-	#define PORT_PHY_QCFG_RESP_TX_LPI_TIMER_MASK            0xffffffUL
-	#define PORT_PHY_QCFG_RESP_TX_LPI_TIMER_SFT             0
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_MASK    0xff000000UL
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_SFT     24
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_UNKNOWN   (0x0UL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_SFP       (0x3UL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP      (0xcUL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFPPLUS  (0xdUL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP28    (0x11UL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFPDD    (0x18UL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP112   (0x1eUL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_SFPDD     (0x1fUL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_CSFP      (0x20UL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_LAST     PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_CSFP
-	__le16	fec_cfg;
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED           0x1UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_SUPPORTED        0x2UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_ENABLED          0x4UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_SUPPORTED       0x8UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ENABLED         0x10UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_SUPPORTED       0x20UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED         0x40UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_SUPPORTED      0x80UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_ENABLED        0x100UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_IEEE_SUPPORTED     0x200UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_IEEE_ENABLED       0x400UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_SUPPORTED      0x800UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_ENABLED        0x1000UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_SUPPORTED     0x2000UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_ENABLED       0x4000UL
-	u8	duplex_state;
-	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF 0x0UL
-	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL 0x1UL
-	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_LAST PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL
-	u8	option_flags;
-	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_MEDIA_AUTO_DETECT     0x1UL
-	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SIGNAL_MODE_KNOWN     0x2UL
-	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SPEEDS2_SUPPORTED     0x4UL
-	char	phy_vendor_name[16];
-	char	phy_vendor_partnumber[16];
-	__le16	support_pam4_speeds;
-	#define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_50G      0x1UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_100G     0x2UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_200G     0x4UL
-	__le16	force_pam4_link_speed;
-	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_200GB 0x7d0UL
-	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_200GB
-	__le16	auto_pam4_link_speed_mask;
-	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_50G      0x1UL
-	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_100G     0x2UL
-	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_200G     0x4UL
-	u8	link_partner_pam4_adv_speeds;
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_50GB      0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_100GB     0x2UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_200GB     0x4UL
-	u8	link_down_reason;
-	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_RF                      0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_OTP_SPEED_VIOLATION     0x2UL
-	__le16	support_speeds2;
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_1GB                0x1UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_10GB               0x2UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_25GB               0x4UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_40GB               0x8UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB               0x10UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB              0x20UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB_PAM4_56       0x40UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_56      0x80UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_56      0x100UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_56      0x200UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_112     0x400UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_112     0x800UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_112     0x1000UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_800GB_PAM4_112     0x2000UL
-	__le16	force_link_speeds2;
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_1GB            0xaUL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_10GB           0x64UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_25GB           0xfaUL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_40GB           0x190UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_50GB           0x1f4UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB          0x3e8UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_50GB_PAM4_56   0x1f5UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB_PAM4_56  0x3e9UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_200GB_PAM4_56  0x7d1UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_400GB_PAM4_56  0xfa1UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_800GB_PAM4_112 0x1f42UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_LAST          PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_800GB_PAM4_112
-	__le16	auto_link_speeds2;
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_1GB                0x1UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_10GB               0x2UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_25GB               0x4UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_40GB               0x8UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_50GB               0x10UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB              0x20UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_50GB_PAM4_56       0x40UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB_PAM4_56      0x80UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_200GB_PAM4_56      0x100UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_400GB_PAM4_56      0x200UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB_PAM4_112     0x400UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_200GB_PAM4_112     0x800UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_400GB_PAM4_112     0x1000UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_800GB_PAM4_112     0x2000UL
-	u8	active_lanes;
-	u8	valid;
-};
-
-/* hwrm_port_mac_cfg_input (size:448b/56B) */
-struct hwrm_port_mac_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define PORT_MAC_CFG_REQ_FLAGS_MATCH_LINK                    0x1UL
-	#define PORT_MAC_CFG_REQ_FLAGS_VLAN_PRI2COS_ENABLE           0x2UL
-	#define PORT_MAC_CFG_REQ_FLAGS_TUNNEL_PRI2COS_ENABLE         0x4UL
-	#define PORT_MAC_CFG_REQ_FLAGS_IP_DSCP2COS_ENABLE            0x8UL
-	#define PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_ENABLE      0x10UL
-	#define PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_DISABLE     0x20UL
-	#define PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_ENABLE      0x40UL
-	#define PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_DISABLE     0x80UL
-	#define PORT_MAC_CFG_REQ_FLAGS_OOB_WOL_ENABLE                0x100UL
-	#define PORT_MAC_CFG_REQ_FLAGS_OOB_WOL_DISABLE               0x200UL
-	#define PORT_MAC_CFG_REQ_FLAGS_VLAN_PRI2COS_DISABLE          0x400UL
-	#define PORT_MAC_CFG_REQ_FLAGS_TUNNEL_PRI2COS_DISABLE        0x800UL
-	#define PORT_MAC_CFG_REQ_FLAGS_IP_DSCP2COS_DISABLE           0x1000UL
-	#define PORT_MAC_CFG_REQ_FLAGS_PTP_ONE_STEP_TX_TS            0x2000UL
-	#define PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_ENABLE      0x4000UL
-	#define PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_DISABLE     0x8000UL
-	__le32	enables;
-	#define PORT_MAC_CFG_REQ_ENABLES_IPG                            0x1UL
-	#define PORT_MAC_CFG_REQ_ENABLES_LPBK                           0x2UL
-	#define PORT_MAC_CFG_REQ_ENABLES_VLAN_PRI2COS_MAP_PRI           0x4UL
-	#define PORT_MAC_CFG_REQ_ENABLES_TUNNEL_PRI2COS_MAP_PRI         0x10UL
-	#define PORT_MAC_CFG_REQ_ENABLES_DSCP2COS_MAP_PRI               0x20UL
-	#define PORT_MAC_CFG_REQ_ENABLES_RX_TS_CAPTURE_PTP_MSG_TYPE     0x40UL
-	#define PORT_MAC_CFG_REQ_ENABLES_TX_TS_CAPTURE_PTP_MSG_TYPE     0x80UL
-	#define PORT_MAC_CFG_REQ_ENABLES_COS_FIELD_CFG                  0x100UL
-	#define PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB               0x200UL
-	#define PORT_MAC_CFG_REQ_ENABLES_PTP_ADJ_PHASE                  0x400UL
-	#define PORT_MAC_CFG_REQ_ENABLES_PTP_LOAD_CONTROL               0x800UL
-	__le16	port_id;
-	u8	ipg;
-	u8	lpbk;
-	#define PORT_MAC_CFG_REQ_LPBK_NONE   0x0UL
-	#define PORT_MAC_CFG_REQ_LPBK_LOCAL  0x1UL
-	#define PORT_MAC_CFG_REQ_LPBK_REMOTE 0x2UL
-	#define PORT_MAC_CFG_REQ_LPBK_LAST  PORT_MAC_CFG_REQ_LPBK_REMOTE
-	u8	vlan_pri2cos_map_pri;
-	u8	reserved1;
-	u8	tunnel_pri2cos_map_pri;
-	u8	dscp2pri_map_pri;
-	__le16	rx_ts_capture_ptp_msg_type;
-	__le16	tx_ts_capture_ptp_msg_type;
-	u8	cos_field_cfg;
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_RSVD1                     0x1UL
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_MASK         0x6UL
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_SFT          1
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_INNERMOST      (0x0UL << 1)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_OUTER          (0x1UL << 1)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_OUTERMOST      (0x2UL << 1)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_UNSPECIFIED    (0x3UL << 1)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_LAST          PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_UNSPECIFIED
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_MASK       0x18UL
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_SFT        3
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_INNERMOST    (0x0UL << 3)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_OUTER        (0x1UL << 3)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_OUTERMOST    (0x2UL << 3)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_UNSPECIFIED  (0x3UL << 3)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_LAST        PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_UNSPECIFIED
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_MASK          0xe0UL
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_SFT           5
-	u8	unused_0[3];
-	__le32	ptp_freq_adj_ppb;
-	u8	unused_1[3];
-	u8	ptp_load_control;
-	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_NONE      0x0UL
-	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_IMMEDIATE 0x1UL
-	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_PPS_EVENT 0x2UL
-	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_LAST     PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_PPS_EVENT
-	__le64	ptp_adj_phase;
-};
-
-/* hwrm_port_mac_cfg_output (size:128b/16B) */
-struct hwrm_port_mac_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	mru;
-	__le16	mtu;
-	u8	ipg;
-	u8	lpbk;
-	#define PORT_MAC_CFG_RESP_LPBK_NONE   0x0UL
-	#define PORT_MAC_CFG_RESP_LPBK_LOCAL  0x1UL
-	#define PORT_MAC_CFG_RESP_LPBK_REMOTE 0x2UL
-	#define PORT_MAC_CFG_RESP_LPBK_LAST  PORT_MAC_CFG_RESP_LPBK_REMOTE
-	u8	unused_0;
-	u8	valid;
-};
-
-/* hwrm_port_mac_ptp_qcfg_input (size:192b/24B) */
-struct hwrm_port_mac_ptp_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_mac_ptp_qcfg_output (size:704b/88B) */
-struct hwrm_port_mac_ptp_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_DIRECT_ACCESS                       0x1UL
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_ONE_STEP_TX_TS                      0x4UL
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS                         0x8UL
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_PARTIAL_DIRECT_ACCESS_REF_CLOCK     0x10UL
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED                      0x20UL
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_64B_PHC_TIME                        0x40UL
-	u8	unused_0[3];
-	__le32	rx_ts_reg_off_lower;
-	__le32	rx_ts_reg_off_upper;
-	__le32	rx_ts_reg_off_seq_id;
-	__le32	rx_ts_reg_off_src_id_0;
-	__le32	rx_ts_reg_off_src_id_1;
-	__le32	rx_ts_reg_off_src_id_2;
-	__le32	rx_ts_reg_off_domain_id;
-	__le32	rx_ts_reg_off_fifo;
-	__le32	rx_ts_reg_off_fifo_adv;
-	__le32	rx_ts_reg_off_granularity;
-	__le32	tx_ts_reg_off_lower;
-	__le32	tx_ts_reg_off_upper;
-	__le32	tx_ts_reg_off_seq_id;
-	__le32	tx_ts_reg_off_fifo;
-	__le32	tx_ts_reg_off_granularity;
-	__le32	ts_ref_clock_reg_lower;
-	__le32	ts_ref_clock_reg_upper;
-	u8	unused_1[7];
-	u8	valid;
-};
-
-/* tx_port_stats (size:3264b/408B) */
-struct tx_port_stats {
-	__le64	tx_64b_frames;
-	__le64	tx_65b_127b_frames;
-	__le64	tx_128b_255b_frames;
-	__le64	tx_256b_511b_frames;
-	__le64	tx_512b_1023b_frames;
-	__le64	tx_1024b_1518b_frames;
-	__le64	tx_good_vlan_frames;
-	__le64	tx_1519b_2047b_frames;
-	__le64	tx_2048b_4095b_frames;
-	__le64	tx_4096b_9216b_frames;
-	__le64	tx_9217b_16383b_frames;
-	__le64	tx_good_frames;
-	__le64	tx_total_frames;
-	__le64	tx_ucast_frames;
-	__le64	tx_mcast_frames;
-	__le64	tx_bcast_frames;
-	__le64	tx_pause_frames;
-	__le64	tx_pfc_frames;
-	__le64	tx_jabber_frames;
-	__le64	tx_fcs_err_frames;
-	__le64	tx_control_frames;
-	__le64	tx_oversz_frames;
-	__le64	tx_single_dfrl_frames;
-	__le64	tx_multi_dfrl_frames;
-	__le64	tx_single_coll_frames;
-	__le64	tx_multi_coll_frames;
-	__le64	tx_late_coll_frames;
-	__le64	tx_excessive_coll_frames;
-	__le64	tx_frag_frames;
-	__le64	tx_err;
-	__le64	tx_tagged_frames;
-	__le64	tx_dbl_tagged_frames;
-	__le64	tx_runt_frames;
-	__le64	tx_fifo_underruns;
-	__le64	tx_pfc_ena_frames_pri0;
-	__le64	tx_pfc_ena_frames_pri1;
-	__le64	tx_pfc_ena_frames_pri2;
-	__le64	tx_pfc_ena_frames_pri3;
-	__le64	tx_pfc_ena_frames_pri4;
-	__le64	tx_pfc_ena_frames_pri5;
-	__le64	tx_pfc_ena_frames_pri6;
-	__le64	tx_pfc_ena_frames_pri7;
-	__le64	tx_eee_lpi_events;
-	__le64	tx_eee_lpi_duration;
-	__le64	tx_llfc_logical_msgs;
-	__le64	tx_hcfc_msgs;
-	__le64	tx_total_collisions;
-	__le64	tx_bytes;
-	__le64	tx_xthol_frames;
-	__le64	tx_stat_discard;
-	__le64	tx_stat_error;
-};
-
-/* rx_port_stats (size:4224b/528B) */
-struct rx_port_stats {
-	__le64	rx_64b_frames;
-	__le64	rx_65b_127b_frames;
-	__le64	rx_128b_255b_frames;
-	__le64	rx_256b_511b_frames;
-	__le64	rx_512b_1023b_frames;
-	__le64	rx_1024b_1518b_frames;
-	__le64	rx_good_vlan_frames;
-	__le64	rx_1519b_2047b_frames;
-	__le64	rx_2048b_4095b_frames;
-	__le64	rx_4096b_9216b_frames;
-	__le64	rx_9217b_16383b_frames;
-	__le64	rx_total_frames;
-	__le64	rx_ucast_frames;
-	__le64	rx_mcast_frames;
-	__le64	rx_bcast_frames;
-	__le64	rx_fcs_err_frames;
-	__le64	rx_ctrl_frames;
-	__le64	rx_pause_frames;
-	__le64	rx_pfc_frames;
-	__le64	rx_unsupported_opcode_frames;
-	__le64	rx_unsupported_da_pausepfc_frames;
-	__le64	rx_wrong_sa_frames;
-	__le64	rx_align_err_frames;
-	__le64	rx_oor_len_frames;
-	__le64	rx_code_err_frames;
-	__le64	rx_false_carrier_frames;
-	__le64	rx_ovrsz_frames;
-	__le64	rx_jbr_frames;
-	__le64	rx_mtu_err_frames;
-	__le64	rx_match_crc_frames;
-	__le64	rx_promiscuous_frames;
-	__le64	rx_tagged_frames;
-	__le64	rx_double_tagged_frames;
-	__le64	rx_trunc_frames;
-	__le64	rx_good_frames;
-	__le64	rx_pfc_xon2xoff_frames_pri0;
-	__le64	rx_pfc_xon2xoff_frames_pri1;
-	__le64	rx_pfc_xon2xoff_frames_pri2;
-	__le64	rx_pfc_xon2xoff_frames_pri3;
-	__le64	rx_pfc_xon2xoff_frames_pri4;
-	__le64	rx_pfc_xon2xoff_frames_pri5;
-	__le64	rx_pfc_xon2xoff_frames_pri6;
-	__le64	rx_pfc_xon2xoff_frames_pri7;
-	__le64	rx_pfc_ena_frames_pri0;
-	__le64	rx_pfc_ena_frames_pri1;
-	__le64	rx_pfc_ena_frames_pri2;
-	__le64	rx_pfc_ena_frames_pri3;
-	__le64	rx_pfc_ena_frames_pri4;
-	__le64	rx_pfc_ena_frames_pri5;
-	__le64	rx_pfc_ena_frames_pri6;
-	__le64	rx_pfc_ena_frames_pri7;
-	__le64	rx_sch_crc_err_frames;
-	__le64	rx_undrsz_frames;
-	__le64	rx_frag_frames;
-	__le64	rx_eee_lpi_events;
-	__le64	rx_eee_lpi_duration;
-	__le64	rx_llfc_physical_msgs;
-	__le64	rx_llfc_logical_msgs;
-	__le64	rx_llfc_msgs_with_crc_err;
-	__le64	rx_hcfc_msgs;
-	__le64	rx_hcfc_msgs_with_crc_err;
-	__le64	rx_bytes;
-	__le64	rx_runt_bytes;
-	__le64	rx_runt_frames;
-	__le64	rx_stat_discard;
-	__le64	rx_stat_err;
-};
-
-/* hwrm_port_qstats_input (size:320b/40B) */
-struct hwrm_port_qstats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	flags;
-	#define PORT_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0[5];
-	__le64	tx_stat_host_addr;
-	__le64	rx_stat_host_addr;
-};
-
-/* hwrm_port_qstats_output (size:128b/16B) */
-struct hwrm_port_qstats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	tx_stat_size;
-	__le16	rx_stat_size;
-	u8	flags;
-	#define PORT_QSTATS_RESP_FLAGS_CLEARED     0x1UL
-	u8	unused_0[2];
-	u8	valid;
-};
-
-/* tx_port_stats_ext (size:2048b/256B) */
-struct tx_port_stats_ext {
-	__le64	tx_bytes_cos0;
-	__le64	tx_bytes_cos1;
-	__le64	tx_bytes_cos2;
-	__le64	tx_bytes_cos3;
-	__le64	tx_bytes_cos4;
-	__le64	tx_bytes_cos5;
-	__le64	tx_bytes_cos6;
-	__le64	tx_bytes_cos7;
-	__le64	tx_packets_cos0;
-	__le64	tx_packets_cos1;
-	__le64	tx_packets_cos2;
-	__le64	tx_packets_cos3;
-	__le64	tx_packets_cos4;
-	__le64	tx_packets_cos5;
-	__le64	tx_packets_cos6;
-	__le64	tx_packets_cos7;
-	__le64	pfc_pri0_tx_duration_us;
-	__le64	pfc_pri0_tx_transitions;
-	__le64	pfc_pri1_tx_duration_us;
-	__le64	pfc_pri1_tx_transitions;
-	__le64	pfc_pri2_tx_duration_us;
-	__le64	pfc_pri2_tx_transitions;
-	__le64	pfc_pri3_tx_duration_us;
-	__le64	pfc_pri3_tx_transitions;
-	__le64	pfc_pri4_tx_duration_us;
-	__le64	pfc_pri4_tx_transitions;
-	__le64	pfc_pri5_tx_duration_us;
-	__le64	pfc_pri5_tx_transitions;
-	__le64	pfc_pri6_tx_duration_us;
-	__le64	pfc_pri6_tx_transitions;
-	__le64	pfc_pri7_tx_duration_us;
-	__le64	pfc_pri7_tx_transitions;
-};
-
-/* rx_port_stats_ext (size:3904b/488B) */
-struct rx_port_stats_ext {
-	__le64	link_down_events;
-	__le64	continuous_pause_events;
-	__le64	resume_pause_events;
-	__le64	continuous_roce_pause_events;
-	__le64	resume_roce_pause_events;
-	__le64	rx_bytes_cos0;
-	__le64	rx_bytes_cos1;
-	__le64	rx_bytes_cos2;
-	__le64	rx_bytes_cos3;
-	__le64	rx_bytes_cos4;
-	__le64	rx_bytes_cos5;
-	__le64	rx_bytes_cos6;
-	__le64	rx_bytes_cos7;
-	__le64	rx_packets_cos0;
-	__le64	rx_packets_cos1;
-	__le64	rx_packets_cos2;
-	__le64	rx_packets_cos3;
-	__le64	rx_packets_cos4;
-	__le64	rx_packets_cos5;
-	__le64	rx_packets_cos6;
-	__le64	rx_packets_cos7;
-	__le64	pfc_pri0_rx_duration_us;
-	__le64	pfc_pri0_rx_transitions;
-	__le64	pfc_pri1_rx_duration_us;
-	__le64	pfc_pri1_rx_transitions;
-	__le64	pfc_pri2_rx_duration_us;
-	__le64	pfc_pri2_rx_transitions;
-	__le64	pfc_pri3_rx_duration_us;
-	__le64	pfc_pri3_rx_transitions;
-	__le64	pfc_pri4_rx_duration_us;
-	__le64	pfc_pri4_rx_transitions;
-	__le64	pfc_pri5_rx_duration_us;
-	__le64	pfc_pri5_rx_transitions;
-	__le64	pfc_pri6_rx_duration_us;
-	__le64	pfc_pri6_rx_transitions;
-	__le64	pfc_pri7_rx_duration_us;
-	__le64	pfc_pri7_rx_transitions;
-	__le64	rx_bits;
-	__le64	rx_buffer_passed_threshold;
-	__le64	rx_pcs_symbol_err;
-	__le64	rx_corrected_bits;
-	__le64	rx_discard_bytes_cos0;
-	__le64	rx_discard_bytes_cos1;
-	__le64	rx_discard_bytes_cos2;
-	__le64	rx_discard_bytes_cos3;
-	__le64	rx_discard_bytes_cos4;
-	__le64	rx_discard_bytes_cos5;
-	__le64	rx_discard_bytes_cos6;
-	__le64	rx_discard_bytes_cos7;
-	__le64	rx_discard_packets_cos0;
-	__le64	rx_discard_packets_cos1;
-	__le64	rx_discard_packets_cos2;
-	__le64	rx_discard_packets_cos3;
-	__le64	rx_discard_packets_cos4;
-	__le64	rx_discard_packets_cos5;
-	__le64	rx_discard_packets_cos6;
-	__le64	rx_discard_packets_cos7;
-	__le64	rx_fec_corrected_blocks;
-	__le64	rx_fec_uncorrectable_blocks;
-	__le64	rx_filter_miss;
-	__le64	rx_fec_symbol_err;
-};
-
-/* hwrm_port_qstats_ext_input (size:320b/40B) */
-struct hwrm_port_qstats_ext_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	__le16	tx_stat_size;
-	__le16	rx_stat_size;
-	u8	flags;
-	#define PORT_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0;
-	__le64	tx_stat_host_addr;
-	__le64	rx_stat_host_addr;
-};
-
-/* hwrm_port_qstats_ext_output (size:128b/16B) */
-struct hwrm_port_qstats_ext_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	tx_stat_size;
-	__le16	rx_stat_size;
-	__le16	total_active_cos_queues;
-	u8	flags;
-	#define PORT_QSTATS_EXT_RESP_FLAGS_CLEAR_ROCE_COUNTERS_SUPPORTED     0x1UL
-	#define PORT_QSTATS_EXT_RESP_FLAGS_CLEARED                           0x2UL
-	u8	valid;
-};
-
-/* hwrm_port_lpbk_qstats_input (size:256b/32B) */
-struct hwrm_port_lpbk_qstats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	lpbk_stat_size;
-	u8	flags;
-	#define PORT_LPBK_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0[5];
-	__le64	lpbk_stat_host_addr;
-};
-
-/* hwrm_port_lpbk_qstats_output (size:128b/16B) */
-struct hwrm_port_lpbk_qstats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	lpbk_stat_size;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* port_lpbk_stats (size:640b/80B) */
-struct port_lpbk_stats {
-	__le64	lpbk_ucast_frames;
-	__le64	lpbk_mcast_frames;
-	__le64	lpbk_bcast_frames;
-	__le64	lpbk_ucast_bytes;
-	__le64	lpbk_mcast_bytes;
-	__le64	lpbk_bcast_bytes;
-	__le64	lpbk_tx_discards;
-	__le64	lpbk_tx_errors;
-	__le64	lpbk_rx_discards;
-	__le64	lpbk_rx_errors;
-};
-
-/* hwrm_port_ecn_qstats_input (size:256b/32B) */
-struct hwrm_port_ecn_qstats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	__le16	ecn_stat_buf_size;
-	u8	flags;
-	#define PORT_ECN_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0[3];
-	__le64	ecn_stat_host_addr;
-};
-
-/* hwrm_port_ecn_qstats_output (size:128b/16B) */
-struct hwrm_port_ecn_qstats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	ecn_stat_buf_size;
-	u8	mark_en;
-	u8	unused_0[4];
-	u8	valid;
-};
-
-/* port_stats_ecn (size:512b/64B) */
-struct port_stats_ecn {
-	__le64	mark_cnt_cos0;
-	__le64	mark_cnt_cos1;
-	__le64	mark_cnt_cos2;
-	__le64	mark_cnt_cos3;
-	__le64	mark_cnt_cos4;
-	__le64	mark_cnt_cos5;
-	__le64	mark_cnt_cos6;
-	__le64	mark_cnt_cos7;
-};
-
-/* hwrm_port_clr_stats_input (size:192b/24B) */
-struct hwrm_port_clr_stats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	flags;
-	#define PORT_CLR_STATS_REQ_FLAGS_ROCE_COUNTERS     0x1UL
-	u8	unused_0[5];
-};
-
-/* hwrm_port_clr_stats_output (size:128b/16B) */
-struct hwrm_port_clr_stats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_port_lpbk_clr_stats_input (size:192b/24B) */
-struct hwrm_port_lpbk_clr_stats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_lpbk_clr_stats_output (size:128b/16B) */
-struct hwrm_port_lpbk_clr_stats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_port_ts_query_input (size:320b/40B) */
-struct hwrm_port_ts_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define PORT_TS_QUERY_REQ_FLAGS_PATH             0x1UL
-	#define PORT_TS_QUERY_REQ_FLAGS_PATH_TX            0x0UL
-	#define PORT_TS_QUERY_REQ_FLAGS_PATH_RX            0x1UL
-	#define PORT_TS_QUERY_REQ_FLAGS_PATH_LAST         PORT_TS_QUERY_REQ_FLAGS_PATH_RX
-	#define PORT_TS_QUERY_REQ_FLAGS_CURRENT_TIME     0x2UL
-	__le16	port_id;
-	u8	unused_0[2];
-	__le16	enables;
-	#define PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT     0x1UL
-	#define PORT_TS_QUERY_REQ_ENABLES_PTP_SEQ_ID         0x2UL
-	#define PORT_TS_QUERY_REQ_ENABLES_PTP_HDR_OFFSET     0x4UL
-	__le16	ts_req_timeout;
-	__le32	ptp_seq_id;
-	__le16	ptp_hdr_offset;
-	u8	unused_1[6];
-};
-
-/* hwrm_port_ts_query_output (size:192b/24B) */
-struct hwrm_port_ts_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	ptp_msg_ts;
-	__le16	ptp_msg_seqid;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_port_phy_qcaps_input (size:192b/24B) */
-struct hwrm_port_phy_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_phy_qcaps_output (size:320b/40B) */
-struct hwrm_port_phy_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED                    0x1UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_EXTERNAL_LPBK_SUPPORTED          0x2UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_AUTONEG_LPBK_SUPPORTED           0x4UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_SHARED_PHY_CFG_SUPPORTED         0x8UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_CUMULATIVE_COUNTERS_ON_RESET     0x10UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_LOCAL_LPBK_NOT_SUPPORTED         0x20UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_FW_MANAGED_LINK_DOWN             0x40UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_NO_FCS                           0x80UL
-	u8	port_cnt;
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_UNKNOWN 0x0UL
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_1       0x1UL
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_2       0x2UL
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_3       0x3UL
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_4       0x4UL
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_12      0xcUL
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_LAST   PORT_PHY_QCAPS_RESP_PORT_CNT_12
-	__le16	supported_speeds_force_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MBHD     0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MB       0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_1GBHD       0x4UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_1GB         0x8UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_2GB         0x10UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_2_5GB       0x20UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10GB        0x40UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_20GB        0x80UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_25GB        0x100UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_40GB        0x200UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_50GB        0x400UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100GB       0x800UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MBHD      0x1000UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MB        0x2000UL
-	__le16	supported_speeds_auto_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MBHD     0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MB       0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_1GBHD       0x4UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_1GB         0x8UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_2GB         0x10UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_2_5GB       0x20UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10GB        0x40UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_20GB        0x80UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_25GB        0x100UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_40GB        0x200UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_50GB        0x400UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100GB       0x800UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MBHD      0x1000UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MB        0x2000UL
-	__le16	supported_speeds_eee_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD1     0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_100MB     0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD2     0x4UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_1GB       0x8UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD3     0x10UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD4     0x20UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_10GB      0x40UL
-	__le32	tx_lpi_timer_low;
-	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_LOW_MASK 0xffffffUL
-	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_LOW_SFT 0
-	#define PORT_PHY_QCAPS_RESP_RSVD2_MASK           0xff000000UL
-	#define PORT_PHY_QCAPS_RESP_RSVD2_SFT            24
-	__le32	valid_tx_lpi_timer_high;
-	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK 0xffffffUL
-	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_SFT 0
-	#define PORT_PHY_QCAPS_RESP_RSVD_MASK             0xff000000UL
-	#define PORT_PHY_QCAPS_RESP_RSVD_SFT              24
-	__le16	supported_pam4_speeds_auto_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_50G      0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_100G     0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_200G     0x4UL
-	__le16	supported_pam4_speeds_force_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_50G      0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_100G     0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_200G     0x4UL
-	__le16	flags2;
-	#define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED           0x1UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED             0x2UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED         0x4UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED           0x8UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS2_REMOTE_LPBK_UNSUPPORTED     0x10UL
-	u8	internal_port_cnt;
-	u8	unused_0;
-	__le16	supported_speeds2_force_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_1GB                0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_10GB               0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_25GB               0x4UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_40GB               0x8UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_50GB               0x10UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB              0x20UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_50GB_PAM4_56       0x40UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB_PAM4_56      0x80UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_200GB_PAM4_56      0x100UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_400GB_PAM4_56      0x200UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB_PAM4_112     0x400UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_200GB_PAM4_112     0x800UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_400GB_PAM4_112     0x1000UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_800GB_PAM4_112     0x2000UL
-	__le16	supported_speeds2_auto_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_1GB                0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_10GB               0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_25GB               0x4UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_40GB               0x8UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_50GB               0x10UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB              0x20UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_50GB_PAM4_56       0x40UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB_PAM4_56      0x80UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_200GB_PAM4_56      0x100UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_400GB_PAM4_56      0x200UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB_PAM4_112     0x400UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_200GB_PAM4_112     0x800UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_400GB_PAM4_112     0x1000UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_800GB_PAM4_112     0x2000UL
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_port_phy_i2c_read_input (size:320b/40B) */
-struct hwrm_port_phy_i2c_read_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	__le32	enables;
-	#define PORT_PHY_I2C_READ_REQ_ENABLES_PAGE_OFFSET     0x1UL
-	#define PORT_PHY_I2C_READ_REQ_ENABLES_BANK_NUMBER     0x2UL
-	__le16	port_id;
-	u8	i2c_slave_addr;
-	u8	bank_number;
-	__le16	page_number;
-	__le16	page_offset;
-	u8	data_length;
-	u8	unused_1[7];
-};
-
-/* hwrm_port_phy_i2c_read_output (size:640b/80B) */
-struct hwrm_port_phy_i2c_read_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	data[16];
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_port_phy_mdio_write_input (size:320b/40B) */
-struct hwrm_port_phy_mdio_write_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	unused_0[2];
-	__le16	port_id;
-	u8	phy_addr;
-	u8	dev_addr;
-	__le16	reg_addr;
-	__le16	reg_data;
-	u8	cl45_mdio;
-	u8	unused_1[7];
-};
-
-/* hwrm_port_phy_mdio_write_output (size:128b/16B) */
-struct hwrm_port_phy_mdio_write_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_port_phy_mdio_read_input (size:256b/32B) */
-struct hwrm_port_phy_mdio_read_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	unused_0[2];
-	__le16	port_id;
-	u8	phy_addr;
-	u8	dev_addr;
-	__le16	reg_addr;
-	u8	cl45_mdio;
-	u8	unused_1;
-};
-
-/* hwrm_port_phy_mdio_read_output (size:128b/16B) */
-struct hwrm_port_phy_mdio_read_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	reg_data;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_port_led_cfg_input (size:512b/64B) */
-struct hwrm_port_led_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define PORT_LED_CFG_REQ_ENABLES_LED0_ID            0x1UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED0_STATE         0x2UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED0_COLOR         0x4UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED0_BLINK_ON      0x8UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED0_BLINK_OFF     0x10UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED0_GROUP_ID      0x20UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED1_ID            0x40UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED1_STATE         0x80UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED1_COLOR         0x100UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED1_BLINK_ON      0x200UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED1_BLINK_OFF     0x400UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED1_GROUP_ID      0x800UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED2_ID            0x1000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED2_STATE         0x2000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED2_COLOR         0x4000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED2_BLINK_ON      0x8000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED2_BLINK_OFF     0x10000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED2_GROUP_ID      0x20000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED3_ID            0x40000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED3_STATE         0x80000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED3_COLOR         0x100000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED3_BLINK_ON      0x200000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED3_BLINK_OFF     0x400000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED3_GROUP_ID      0x800000UL
-	__le16	port_id;
-	u8	num_leds;
-	u8	rsvd;
-	u8	led0_id;
-	u8	led0_state;
-	#define PORT_LED_CFG_REQ_LED0_STATE_DEFAULT  0x0UL
-	#define PORT_LED_CFG_REQ_LED0_STATE_OFF      0x1UL
-	#define PORT_LED_CFG_REQ_LED0_STATE_ON       0x2UL
-	#define PORT_LED_CFG_REQ_LED0_STATE_BLINK    0x3UL
-	#define PORT_LED_CFG_REQ_LED0_STATE_BLINKALT 0x4UL
-	#define PORT_LED_CFG_REQ_LED0_STATE_LAST    PORT_LED_CFG_REQ_LED0_STATE_BLINKALT
-	u8	led0_color;
-	#define PORT_LED_CFG_REQ_LED0_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_CFG_REQ_LED0_COLOR_AMBER      0x1UL
-	#define PORT_LED_CFG_REQ_LED0_COLOR_GREEN      0x2UL
-	#define PORT_LED_CFG_REQ_LED0_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_CFG_REQ_LED0_COLOR_LAST      PORT_LED_CFG_REQ_LED0_COLOR_GREENAMBER
-	u8	unused_0;
-	__le16	led0_blink_on;
-	__le16	led0_blink_off;
-	u8	led0_group_id;
-	u8	rsvd0;
-	u8	led1_id;
-	u8	led1_state;
-	#define PORT_LED_CFG_REQ_LED1_STATE_DEFAULT  0x0UL
-	#define PORT_LED_CFG_REQ_LED1_STATE_OFF      0x1UL
-	#define PORT_LED_CFG_REQ_LED1_STATE_ON       0x2UL
-	#define PORT_LED_CFG_REQ_LED1_STATE_BLINK    0x3UL
-	#define PORT_LED_CFG_REQ_LED1_STATE_BLINKALT 0x4UL
-	#define PORT_LED_CFG_REQ_LED1_STATE_LAST    PORT_LED_CFG_REQ_LED1_STATE_BLINKALT
-	u8	led1_color;
-	#define PORT_LED_CFG_REQ_LED1_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_CFG_REQ_LED1_COLOR_AMBER      0x1UL
-	#define PORT_LED_CFG_REQ_LED1_COLOR_GREEN      0x2UL
-	#define PORT_LED_CFG_REQ_LED1_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_CFG_REQ_LED1_COLOR_LAST      PORT_LED_CFG_REQ_LED1_COLOR_GREENAMBER
-	u8	unused_1;
-	__le16	led1_blink_on;
-	__le16	led1_blink_off;
-	u8	led1_group_id;
-	u8	rsvd1;
-	u8	led2_id;
-	u8	led2_state;
-	#define PORT_LED_CFG_REQ_LED2_STATE_DEFAULT  0x0UL
-	#define PORT_LED_CFG_REQ_LED2_STATE_OFF      0x1UL
-	#define PORT_LED_CFG_REQ_LED2_STATE_ON       0x2UL
-	#define PORT_LED_CFG_REQ_LED2_STATE_BLINK    0x3UL
-	#define PORT_LED_CFG_REQ_LED2_STATE_BLINKALT 0x4UL
-	#define PORT_LED_CFG_REQ_LED2_STATE_LAST    PORT_LED_CFG_REQ_LED2_STATE_BLINKALT
-	u8	led2_color;
-	#define PORT_LED_CFG_REQ_LED2_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_CFG_REQ_LED2_COLOR_AMBER      0x1UL
-	#define PORT_LED_CFG_REQ_LED2_COLOR_GREEN      0x2UL
-	#define PORT_LED_CFG_REQ_LED2_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_CFG_REQ_LED2_COLOR_LAST      PORT_LED_CFG_REQ_LED2_COLOR_GREENAMBER
-	u8	unused_2;
-	__le16	led2_blink_on;
-	__le16	led2_blink_off;
-	u8	led2_group_id;
-	u8	rsvd2;
-	u8	led3_id;
-	u8	led3_state;
-	#define PORT_LED_CFG_REQ_LED3_STATE_DEFAULT  0x0UL
-	#define PORT_LED_CFG_REQ_LED3_STATE_OFF      0x1UL
-	#define PORT_LED_CFG_REQ_LED3_STATE_ON       0x2UL
-	#define PORT_LED_CFG_REQ_LED3_STATE_BLINK    0x3UL
-	#define PORT_LED_CFG_REQ_LED3_STATE_BLINKALT 0x4UL
-	#define PORT_LED_CFG_REQ_LED3_STATE_LAST    PORT_LED_CFG_REQ_LED3_STATE_BLINKALT
-	u8	led3_color;
-	#define PORT_LED_CFG_REQ_LED3_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_CFG_REQ_LED3_COLOR_AMBER      0x1UL
-	#define PORT_LED_CFG_REQ_LED3_COLOR_GREEN      0x2UL
-	#define PORT_LED_CFG_REQ_LED3_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_CFG_REQ_LED3_COLOR_LAST      PORT_LED_CFG_REQ_LED3_COLOR_GREENAMBER
-	u8	unused_3;
-	__le16	led3_blink_on;
-	__le16	led3_blink_off;
-	u8	led3_group_id;
-	u8	rsvd3;
-};
-
-/* hwrm_port_led_cfg_output (size:128b/16B) */
-struct hwrm_port_led_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_port_led_qcfg_input (size:192b/24B) */
-struct hwrm_port_led_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_led_qcfg_output (size:448b/56B) */
-struct hwrm_port_led_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	num_leds;
-	u8	led0_id;
-	u8	led0_type;
-	#define PORT_LED_QCFG_RESP_LED0_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCFG_RESP_LED0_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCFG_RESP_LED0_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCFG_RESP_LED0_TYPE_LAST    PORT_LED_QCFG_RESP_LED0_TYPE_INVALID
-	u8	led0_state;
-	#define PORT_LED_QCFG_RESP_LED0_STATE_DEFAULT  0x0UL
-	#define PORT_LED_QCFG_RESP_LED0_STATE_OFF      0x1UL
-	#define PORT_LED_QCFG_RESP_LED0_STATE_ON       0x2UL
-	#define PORT_LED_QCFG_RESP_LED0_STATE_BLINK    0x3UL
-	#define PORT_LED_QCFG_RESP_LED0_STATE_BLINKALT 0x4UL
-	#define PORT_LED_QCFG_RESP_LED0_STATE_LAST    PORT_LED_QCFG_RESP_LED0_STATE_BLINKALT
-	u8	led0_color;
-	#define PORT_LED_QCFG_RESP_LED0_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_QCFG_RESP_LED0_COLOR_AMBER      0x1UL
-	#define PORT_LED_QCFG_RESP_LED0_COLOR_GREEN      0x2UL
-	#define PORT_LED_QCFG_RESP_LED0_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_QCFG_RESP_LED0_COLOR_LAST      PORT_LED_QCFG_RESP_LED0_COLOR_GREENAMBER
-	u8	unused_0;
-	__le16	led0_blink_on;
-	__le16	led0_blink_off;
-	u8	led0_group_id;
-	u8	led1_id;
-	u8	led1_type;
-	#define PORT_LED_QCFG_RESP_LED1_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCFG_RESP_LED1_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCFG_RESP_LED1_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCFG_RESP_LED1_TYPE_LAST    PORT_LED_QCFG_RESP_LED1_TYPE_INVALID
-	u8	led1_state;
-	#define PORT_LED_QCFG_RESP_LED1_STATE_DEFAULT  0x0UL
-	#define PORT_LED_QCFG_RESP_LED1_STATE_OFF      0x1UL
-	#define PORT_LED_QCFG_RESP_LED1_STATE_ON       0x2UL
-	#define PORT_LED_QCFG_RESP_LED1_STATE_BLINK    0x3UL
-	#define PORT_LED_QCFG_RESP_LED1_STATE_BLINKALT 0x4UL
-	#define PORT_LED_QCFG_RESP_LED1_STATE_LAST    PORT_LED_QCFG_RESP_LED1_STATE_BLINKALT
-	u8	led1_color;
-	#define PORT_LED_QCFG_RESP_LED1_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_QCFG_RESP_LED1_COLOR_AMBER      0x1UL
-	#define PORT_LED_QCFG_RESP_LED1_COLOR_GREEN      0x2UL
-	#define PORT_LED_QCFG_RESP_LED1_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_QCFG_RESP_LED1_COLOR_LAST      PORT_LED_QCFG_RESP_LED1_COLOR_GREENAMBER
-	u8	unused_1;
-	__le16	led1_blink_on;
-	__le16	led1_blink_off;
-	u8	led1_group_id;
-	u8	led2_id;
-	u8	led2_type;
-	#define PORT_LED_QCFG_RESP_LED2_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCFG_RESP_LED2_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCFG_RESP_LED2_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCFG_RESP_LED2_TYPE_LAST    PORT_LED_QCFG_RESP_LED2_TYPE_INVALID
-	u8	led2_state;
-	#define PORT_LED_QCFG_RESP_LED2_STATE_DEFAULT  0x0UL
-	#define PORT_LED_QCFG_RESP_LED2_STATE_OFF      0x1UL
-	#define PORT_LED_QCFG_RESP_LED2_STATE_ON       0x2UL
-	#define PORT_LED_QCFG_RESP_LED2_STATE_BLINK    0x3UL
-	#define PORT_LED_QCFG_RESP_LED2_STATE_BLINKALT 0x4UL
-	#define PORT_LED_QCFG_RESP_LED2_STATE_LAST    PORT_LED_QCFG_RESP_LED2_STATE_BLINKALT
-	u8	led2_color;
-	#define PORT_LED_QCFG_RESP_LED2_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_QCFG_RESP_LED2_COLOR_AMBER      0x1UL
-	#define PORT_LED_QCFG_RESP_LED2_COLOR_GREEN      0x2UL
-	#define PORT_LED_QCFG_RESP_LED2_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_QCFG_RESP_LED2_COLOR_LAST      PORT_LED_QCFG_RESP_LED2_COLOR_GREENAMBER
-	u8	unused_2;
-	__le16	led2_blink_on;
-	__le16	led2_blink_off;
-	u8	led2_group_id;
-	u8	led3_id;
-	u8	led3_type;
-	#define PORT_LED_QCFG_RESP_LED3_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCFG_RESP_LED3_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCFG_RESP_LED3_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCFG_RESP_LED3_TYPE_LAST    PORT_LED_QCFG_RESP_LED3_TYPE_INVALID
-	u8	led3_state;
-	#define PORT_LED_QCFG_RESP_LED3_STATE_DEFAULT  0x0UL
-	#define PORT_LED_QCFG_RESP_LED3_STATE_OFF      0x1UL
-	#define PORT_LED_QCFG_RESP_LED3_STATE_ON       0x2UL
-	#define PORT_LED_QCFG_RESP_LED3_STATE_BLINK    0x3UL
-	#define PORT_LED_QCFG_RESP_LED3_STATE_BLINKALT 0x4UL
-	#define PORT_LED_QCFG_RESP_LED3_STATE_LAST    PORT_LED_QCFG_RESP_LED3_STATE_BLINKALT
-	u8	led3_color;
-	#define PORT_LED_QCFG_RESP_LED3_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_QCFG_RESP_LED3_COLOR_AMBER      0x1UL
-	#define PORT_LED_QCFG_RESP_LED3_COLOR_GREEN      0x2UL
-	#define PORT_LED_QCFG_RESP_LED3_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_QCFG_RESP_LED3_COLOR_LAST      PORT_LED_QCFG_RESP_LED3_COLOR_GREENAMBER
-	u8	unused_3;
-	__le16	led3_blink_on;
-	__le16	led3_blink_off;
-	u8	led3_group_id;
-	u8	unused_4[6];
-	u8	valid;
-};
-
-/* hwrm_port_led_qcaps_input (size:192b/24B) */
-struct hwrm_port_led_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_led_qcaps_output (size:384b/48B) */
-struct hwrm_port_led_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	num_leds;
-	u8	unused[3];
-	u8	led0_id;
-	u8	led0_type;
-	#define PORT_LED_QCAPS_RESP_LED0_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCAPS_RESP_LED0_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED0_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCAPS_RESP_LED0_TYPE_LAST    PORT_LED_QCAPS_RESP_LED0_TYPE_INVALID
-	u8	led0_group_id;
-	u8	unused_0;
-	__le16	led0_state_caps;
-	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_ENABLED                 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_OFF_SUPPORTED           0x2UL
-	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_ON_SUPPORTED            0x4UL
-	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_BLINK_SUPPORTED         0x8UL
-	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
-	__le16	led0_color_caps;
-	#define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_RSVD                0x1UL
-	#define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_AMBER_SUPPORTED     0x2UL
-	#define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_GREEN_SUPPORTED     0x4UL
-	u8	led1_id;
-	u8	led1_type;
-	#define PORT_LED_QCAPS_RESP_LED1_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCAPS_RESP_LED1_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED1_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCAPS_RESP_LED1_TYPE_LAST    PORT_LED_QCAPS_RESP_LED1_TYPE_INVALID
-	u8	led1_group_id;
-	u8	unused_1;
-	__le16	led1_state_caps;
-	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_ENABLED                 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_OFF_SUPPORTED           0x2UL
-	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_ON_SUPPORTED            0x4UL
-	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_BLINK_SUPPORTED         0x8UL
-	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
-	__le16	led1_color_caps;
-	#define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_RSVD                0x1UL
-	#define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_AMBER_SUPPORTED     0x2UL
-	#define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_GREEN_SUPPORTED     0x4UL
-	u8	led2_id;
-	u8	led2_type;
-	#define PORT_LED_QCAPS_RESP_LED2_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCAPS_RESP_LED2_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED2_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCAPS_RESP_LED2_TYPE_LAST    PORT_LED_QCAPS_RESP_LED2_TYPE_INVALID
-	u8	led2_group_id;
-	u8	unused_2;
-	__le16	led2_state_caps;
-	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_ENABLED                 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_OFF_SUPPORTED           0x2UL
-	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_ON_SUPPORTED            0x4UL
-	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_BLINK_SUPPORTED         0x8UL
-	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
-	__le16	led2_color_caps;
-	#define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_RSVD                0x1UL
-	#define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_AMBER_SUPPORTED     0x2UL
-	#define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_GREEN_SUPPORTED     0x4UL
-	u8	led3_id;
-	u8	led3_type;
-	#define PORT_LED_QCAPS_RESP_LED3_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCAPS_RESP_LED3_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED3_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCAPS_RESP_LED3_TYPE_LAST    PORT_LED_QCAPS_RESP_LED3_TYPE_INVALID
-	u8	led3_group_id;
-	u8	unused_3;
-	__le16	led3_state_caps;
-	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_ENABLED                 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_OFF_SUPPORTED           0x2UL
-	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_ON_SUPPORTED            0x4UL
-	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_BLINK_SUPPORTED         0x8UL
-	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
-	__le16	led3_color_caps;
-	#define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_RSVD                0x1UL
-	#define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_AMBER_SUPPORTED     0x2UL
-	#define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_GREEN_SUPPORTED     0x4UL
-	u8	unused_4[3];
-	u8	valid;
-};
-
-/* hwrm_port_mac_qcaps_input (size:192b/24B) */
-struct hwrm_port_mac_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_mac_qcaps_output (size:128b/16B) */
-struct hwrm_port_mac_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define PORT_MAC_QCAPS_RESP_FLAGS_LOCAL_LPBK_NOT_SUPPORTED     0x1UL
-	#define PORT_MAC_QCAPS_RESP_FLAGS_REMOTE_LPBK_SUPPORTED        0x2UL
-	u8	unused_0[6];
-	u8	valid;
-};
-
-/* hwrm_queue_qportcfg_input (size:192b/24B) */
-struct hwrm_queue_qportcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH     0x1UL
-	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH_TX    0x0UL
-	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH_RX    0x1UL
-	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH_LAST QUEUE_QPORTCFG_REQ_FLAGS_PATH_RX
-	__le16	port_id;
-	u8	drv_qmap_cap;
-	#define QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_DISABLED 0x0UL
-	#define QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_ENABLED  0x1UL
-	#define QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_LAST    QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_ENABLED
-	u8	unused_0;
-};
-
-/* hwrm_queue_qportcfg_output (size:1344b/168B) */
-struct hwrm_queue_qportcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	max_configurable_queues;
-	u8	max_configurable_lossless_queues;
-	u8	queue_cfg_allowed;
-	u8	queue_cfg_info;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG             0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_USE_PROFILE_TYPE     0x2UL
-	u8	queue_pfcenable_cfg_allowed;
-	u8	queue_pri2cos_cfg_allowed;
-	u8	queue_cos2bw_cfg_allowed;
-	u8	queue_id0;
-	u8	queue_id0_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id1;
-	u8	queue_id1_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id2;
-	u8	queue_id2_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id3;
-	u8	queue_id3_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id4;
-	u8	queue_id4_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id5;
-	u8	queue_id5_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id6;
-	u8	queue_id6_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id7;
-	u8	queue_id7_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id0_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	char	qid0_name[16];
-	char	qid1_name[16];
-	char	qid2_name[16];
-	char	qid3_name[16];
-	char	qid4_name[16];
-	char	qid5_name[16];
-	char	qid6_name[16];
-	char	qid7_name[16];
-	u8	queue_id1_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	queue_id2_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	queue_id3_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	queue_id4_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	queue_id5_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	queue_id6_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	queue_id7_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	valid;
-};
-
-/* hwrm_queue_qcfg_input (size:192b/24B) */
-struct hwrm_queue_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define QUEUE_QCFG_REQ_FLAGS_PATH     0x1UL
-	#define QUEUE_QCFG_REQ_FLAGS_PATH_TX    0x0UL
-	#define QUEUE_QCFG_REQ_FLAGS_PATH_RX    0x1UL
-	#define QUEUE_QCFG_REQ_FLAGS_PATH_LAST QUEUE_QCFG_REQ_FLAGS_PATH_RX
-	__le32	queue_id;
-};
-
-/* hwrm_queue_qcfg_output (size:128b/16B) */
-struct hwrm_queue_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	queue_len;
-	u8	service_profile;
-	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_LOSSY    0x0UL
-	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_LOSSLESS 0x1UL
-	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_UNKNOWN  0xffUL
-	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_LAST    QUEUE_QCFG_RESP_SERVICE_PROFILE_UNKNOWN
-	u8	queue_cfg_info;
-	#define QUEUE_QCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG     0x1UL
-	u8	unused_0;
-	u8	valid;
-};
-
-/* hwrm_queue_cfg_input (size:320b/40B) */
-struct hwrm_queue_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define QUEUE_CFG_REQ_FLAGS_PATH_MASK 0x3UL
-	#define QUEUE_CFG_REQ_FLAGS_PATH_SFT  0
-	#define QUEUE_CFG_REQ_FLAGS_PATH_TX     0x0UL
-	#define QUEUE_CFG_REQ_FLAGS_PATH_RX     0x1UL
-	#define QUEUE_CFG_REQ_FLAGS_PATH_BIDIR  0x2UL
-	#define QUEUE_CFG_REQ_FLAGS_PATH_LAST  QUEUE_CFG_REQ_FLAGS_PATH_BIDIR
-	__le32	enables;
-	#define QUEUE_CFG_REQ_ENABLES_DFLT_LEN            0x1UL
-	#define QUEUE_CFG_REQ_ENABLES_SERVICE_PROFILE     0x2UL
-	__le32	queue_id;
-	__le32	dflt_len;
-	u8	service_profile;
-	#define QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSY    0x0UL
-	#define QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSLESS 0x1UL
-	#define QUEUE_CFG_REQ_SERVICE_PROFILE_UNKNOWN  0xffUL
-	#define QUEUE_CFG_REQ_SERVICE_PROFILE_LAST    QUEUE_CFG_REQ_SERVICE_PROFILE_UNKNOWN
-	u8	unused_0[7];
-};
-
-/* hwrm_queue_cfg_output (size:128b/16B) */
-struct hwrm_queue_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_queue_pfcenable_qcfg_input (size:192b/24B) */
-struct hwrm_queue_pfcenable_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_queue_pfcenable_qcfg_output (size:128b/16B) */
-struct hwrm_queue_pfcenable_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI0_PFC_ENABLED              0x1UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI1_PFC_ENABLED              0x2UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI2_PFC_ENABLED              0x4UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI3_PFC_ENABLED              0x8UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI4_PFC_ENABLED              0x10UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI5_PFC_ENABLED              0x20UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI6_PFC_ENABLED              0x40UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI7_PFC_ENABLED              0x80UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI0_PFC_WATCHDOG_ENABLED     0x100UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI1_PFC_WATCHDOG_ENABLED     0x200UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI2_PFC_WATCHDOG_ENABLED     0x400UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI3_PFC_WATCHDOG_ENABLED     0x800UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI4_PFC_WATCHDOG_ENABLED     0x1000UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI5_PFC_WATCHDOG_ENABLED     0x2000UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI6_PFC_WATCHDOG_ENABLED     0x4000UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI7_PFC_WATCHDOG_ENABLED     0x8000UL
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_queue_pfcenable_cfg_input (size:192b/24B) */
-struct hwrm_queue_pfcenable_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI0_PFC_ENABLED              0x1UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI1_PFC_ENABLED              0x2UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI2_PFC_ENABLED              0x4UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI3_PFC_ENABLED              0x8UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI4_PFC_ENABLED              0x10UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI5_PFC_ENABLED              0x20UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI6_PFC_ENABLED              0x40UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI7_PFC_ENABLED              0x80UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI0_PFC_WATCHDOG_ENABLED     0x100UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI1_PFC_WATCHDOG_ENABLED     0x200UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI2_PFC_WATCHDOG_ENABLED     0x400UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI3_PFC_WATCHDOG_ENABLED     0x800UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI4_PFC_WATCHDOG_ENABLED     0x1000UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI5_PFC_WATCHDOG_ENABLED     0x2000UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI6_PFC_WATCHDOG_ENABLED     0x4000UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI7_PFC_WATCHDOG_ENABLED     0x8000UL
-	__le16	port_id;
-	u8	unused_0[2];
-};
-
-/* hwrm_queue_pfcenable_cfg_output (size:128b/16B) */
-struct hwrm_queue_pfcenable_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_queue_pri2cos_qcfg_input (size:192b/24B) */
-struct hwrm_queue_pri2cos_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH      0x1UL
-	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_TX     0x0UL
-	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_RX     0x1UL
-	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_LAST  QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_RX
-	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_IVLAN     0x2UL
-	u8	port_id;
-	u8	unused_0[3];
-};
-
-/* hwrm_queue_pri2cos_qcfg_output (size:192b/24B) */
-struct hwrm_queue_pri2cos_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	pri0_cos_queue_id;
-	u8	pri1_cos_queue_id;
-	u8	pri2_cos_queue_id;
-	u8	pri3_cos_queue_id;
-	u8	pri4_cos_queue_id;
-	u8	pri5_cos_queue_id;
-	u8	pri6_cos_queue_id;
-	u8	pri7_cos_queue_id;
-	u8	queue_cfg_info;
-	#define QUEUE_PRI2COS_QCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG     0x1UL
-	u8	unused_0[6];
-	u8	valid;
-};
-
-/* hwrm_queue_pri2cos_cfg_input (size:320b/40B) */
-struct hwrm_queue_pri2cos_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_MASK 0x3UL
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_SFT  0
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_TX     0x0UL
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_RX     0x1UL
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_BIDIR  0x2UL
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_LAST  QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_BIDIR
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_IVLAN     0x4UL
-	__le32	enables;
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI0_COS_QUEUE_ID     0x1UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI1_COS_QUEUE_ID     0x2UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI2_COS_QUEUE_ID     0x4UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI3_COS_QUEUE_ID     0x8UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI4_COS_QUEUE_ID     0x10UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI5_COS_QUEUE_ID     0x20UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI6_COS_QUEUE_ID     0x40UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI7_COS_QUEUE_ID     0x80UL
-	u8	port_id;
-	u8	pri0_cos_queue_id;
-	u8	pri1_cos_queue_id;
-	u8	pri2_cos_queue_id;
-	u8	pri3_cos_queue_id;
-	u8	pri4_cos_queue_id;
-	u8	pri5_cos_queue_id;
-	u8	pri6_cos_queue_id;
-	u8	pri7_cos_queue_id;
-	u8	unused_0[7];
-};
-
-/* hwrm_queue_pri2cos_cfg_output (size:128b/16B) */
-struct hwrm_queue_pri2cos_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_queue_cos2bw_qcfg_input (size:192b/24B) */
-struct hwrm_queue_cos2bw_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_queue_cos2bw_qcfg_output (size:896b/112B) */
-struct hwrm_queue_cos2bw_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	queue_id0;
-	u8	unused_0;
-	__le16	unused_1;
-	__le32	queue_id0_min_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id0_max_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id0_tsa_assign;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id0_pri_lvl;
-	u8	queue_id0_bw_weight;
-	struct {
-		u8	queue_id;
-		__le32	queue_id_min_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID
-		__le32	queue_id_max_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID
-		u8	queue_id_tsa_assign;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_RESERVED_LAST  0xffUL
-		u8	queue_id_pri_lvl;
-		u8	queue_id_bw_weight;
-	} __packed cfg[7];
-	u8	unused_2[4];
-	u8	valid;
-};
-
-/* hwrm_queue_cos2bw_cfg_input (size:1024b/128B) */
-struct hwrm_queue_cos2bw_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	__le32	enables;
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID0_VALID     0x1UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID1_VALID     0x2UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID2_VALID     0x4UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID3_VALID     0x8UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID4_VALID     0x10UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID5_VALID     0x20UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID6_VALID     0x40UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID7_VALID     0x80UL
-	__le16	port_id;
-	u8	queue_id0;
-	u8	unused_0;
-	__le32	queue_id0_min_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id0_max_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id0_tsa_assign;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id0_pri_lvl;
-	u8	queue_id0_bw_weight;
-	struct {
-		u8	queue_id;
-		__le32	queue_id_min_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID
-		__le32	queue_id_max_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID
-		u8	queue_id_tsa_assign;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_RESERVED_LAST  0xffUL
-		u8	queue_id_pri_lvl;
-		u8	queue_id_bw_weight;
-	} __packed cfg[7];
-	u8	unused_1[5];
-};
-
-/* hwrm_queue_cos2bw_cfg_output (size:128b/16B) */
-struct hwrm_queue_cos2bw_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_queue_dscp_qcaps_input (size:192b/24B) */
-struct hwrm_queue_dscp_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	port_id;
-	u8	unused_0[7];
-};
-
-/* hwrm_queue_dscp_qcaps_output (size:128b/16B) */
-struct hwrm_queue_dscp_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	num_dscp_bits;
-	u8	unused_0;
-	__le16	max_entries;
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_queue_dscp2pri_qcfg_input (size:256b/32B) */
-struct hwrm_queue_dscp2pri_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	dest_data_addr;
-	u8	port_id;
-	u8	unused_0;
-	__le16	dest_data_buffer_size;
-	u8	unused_1[4];
-};
-
-/* hwrm_queue_dscp2pri_qcfg_output (size:128b/16B) */
-struct hwrm_queue_dscp2pri_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	entry_cnt;
-	u8	default_pri;
-	u8	unused_0[4];
-	u8	valid;
-};
-
-/* hwrm_queue_dscp2pri_cfg_input (size:320b/40B) */
-struct hwrm_queue_dscp2pri_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	src_data_addr;
-	__le32	flags;
-	#define QUEUE_DSCP2PRI_CFG_REQ_FLAGS_USE_HW_DEFAULT_PRI     0x1UL
-	__le32	enables;
-	#define QUEUE_DSCP2PRI_CFG_REQ_ENABLES_DEFAULT_PRI     0x1UL
-	u8	port_id;
-	u8	default_pri;
-	__le16	entry_cnt;
-	u8	unused_0[4];
-};
-
-/* hwrm_queue_dscp2pri_cfg_output (size:128b/16B) */
-struct hwrm_queue_dscp2pri_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_alloc_input (size:192b/24B) */
-struct hwrm_vnic_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define VNIC_ALLOC_REQ_FLAGS_DEFAULT                  0x1UL
-	#define VNIC_ALLOC_REQ_FLAGS_VIRTIO_NET_FID_VALID     0x2UL
-	__le16	virtio_net_fid;
-	u8	unused_0[2];
-};
-
-/* hwrm_vnic_alloc_output (size:128b/16B) */
-struct hwrm_vnic_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	vnic_id;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_vnic_update_input (size:256b/32B) */
-struct hwrm_vnic_update_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	vnic_id;
-	__le32	enables;
-	#define VNIC_UPDATE_REQ_ENABLES_VNIC_STATE_VALID               0x1UL
-	#define VNIC_UPDATE_REQ_ENABLES_MRU_VALID                      0x2UL
-	#define VNIC_UPDATE_REQ_ENABLES_METADATA_FORMAT_TYPE_VALID     0x4UL
-	u8	vnic_state;
-	#define VNIC_UPDATE_REQ_VNIC_STATE_NORMAL 0x0UL
-	#define VNIC_UPDATE_REQ_VNIC_STATE_DROP   0x1UL
-	#define VNIC_UPDATE_REQ_VNIC_STATE_LAST  VNIC_UPDATE_REQ_VNIC_STATE_DROP
-	u8	metadata_format_type;
-	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_0 0x0UL
-	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_1 0x1UL
-	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_2 0x2UL
-	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_3 0x3UL
-	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4 0x4UL
-	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_LAST VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4
-	__le16	mru;
-	u8	unused_1[4];
-};
-
-/* hwrm_vnic_update_output (size:128b/16B) */
-struct hwrm_vnic_update_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_free_input (size:192b/24B) */
-struct hwrm_vnic_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	vnic_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_vnic_free_output (size:128b/16B) */
-struct hwrm_vnic_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_cfg_input (size:384b/48B) */
-struct hwrm_vnic_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define VNIC_CFG_REQ_FLAGS_DEFAULT                              0x1UL
-	#define VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE                      0x2UL
-	#define VNIC_CFG_REQ_FLAGS_BD_STALL_MODE                        0x4UL
-	#define VNIC_CFG_REQ_FLAGS_ROCE_DUAL_VNIC_MODE                  0x8UL
-	#define VNIC_CFG_REQ_FLAGS_ROCE_ONLY_VNIC_MODE                  0x10UL
-	#define VNIC_CFG_REQ_FLAGS_RSS_DFLT_CR_MODE                     0x20UL
-	#define VNIC_CFG_REQ_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_MODE     0x40UL
-	#define VNIC_CFG_REQ_FLAGS_PORTCOS_MAPPING_MODE                 0x80UL
-	__le32	enables;
-	#define VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP            0x1UL
-	#define VNIC_CFG_REQ_ENABLES_RSS_RULE                 0x2UL
-	#define VNIC_CFG_REQ_ENABLES_COS_RULE                 0x4UL
-	#define VNIC_CFG_REQ_ENABLES_LB_RULE                  0x8UL
-	#define VNIC_CFG_REQ_ENABLES_MRU                      0x10UL
-	#define VNIC_CFG_REQ_ENABLES_DEFAULT_RX_RING_ID       0x20UL
-	#define VNIC_CFG_REQ_ENABLES_DEFAULT_CMPL_RING_ID     0x40UL
-	#define VNIC_CFG_REQ_ENABLES_QUEUE_ID                 0x80UL
-	#define VNIC_CFG_REQ_ENABLES_RX_CSUM_V2_MODE          0x100UL
-	#define VNIC_CFG_REQ_ENABLES_L2_CQE_MODE              0x200UL
-	__le16	vnic_id;
-	__le16	dflt_ring_grp;
-	__le16	rss_rule;
-	__le16	cos_rule;
-	__le16	lb_rule;
-	__le16	mru;
-	__le16	default_rx_ring_id;
-	__le16	default_cmpl_ring_id;
-	__le16	queue_id;
-	u8	rx_csum_v2_mode;
-	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_DEFAULT 0x0UL
-	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_ALL_OK  0x1UL
-	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_MAX     0x2UL
-	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_LAST   VNIC_CFG_REQ_RX_CSUM_V2_MODE_MAX
-	u8	l2_cqe_mode;
-	#define VNIC_CFG_REQ_L2_CQE_MODE_DEFAULT    0x0UL
-	#define VNIC_CFG_REQ_L2_CQE_MODE_COMPRESSED 0x1UL
-	#define VNIC_CFG_REQ_L2_CQE_MODE_MIXED      0x2UL
-	#define VNIC_CFG_REQ_L2_CQE_MODE_LAST      VNIC_CFG_REQ_L2_CQE_MODE_MIXED
-	u8	unused0[4];
-};
-
-/* hwrm_vnic_cfg_output (size:128b/16B) */
-struct hwrm_vnic_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_qcaps_input (size:192b/24B) */
-struct hwrm_vnic_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	u8	unused_0[4];
-};
-
-/* hwrm_vnic_qcaps_output (size:192b/24B) */
-struct hwrm_vnic_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	mru;
-	u8	unused_0[2];
-	__le32	flags;
-	#define VNIC_QCAPS_RESP_FLAGS_UNUSED                                  0x1UL
-	#define VNIC_QCAPS_RESP_FLAGS_VLAN_STRIP_CAP                          0x2UL
-	#define VNIC_QCAPS_RESP_FLAGS_BD_STALL_CAP                            0x4UL
-	#define VNIC_QCAPS_RESP_FLAGS_ROCE_DUAL_VNIC_CAP                      0x8UL
-	#define VNIC_QCAPS_RESP_FLAGS_ROCE_ONLY_VNIC_CAP                      0x10UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP                         0x20UL
-	#define VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP         0x40UL
-	#define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_CAP                       0x80UL
-	#define VNIC_QCAPS_RESP_FLAGS_COS_ASSIGNMENT_CAP                      0x100UL
-	#define VNIC_QCAPS_RESP_FLAGS_RX_CMPL_V2_CAP                          0x200UL
-	#define VNIC_QCAPS_RESP_FLAGS_VNIC_STATE_CAP                          0x400UL
-	#define VNIC_QCAPS_RESP_FLAGS_VIRTIO_NET_VNIC_ALLOC_CAP               0x800UL
-	#define VNIC_QCAPS_RESP_FLAGS_METADATA_FORMAT_CAP                     0x1000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_STRICT_HASH_TYPE_CAP                0x2000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_HASH_TYPE_DELTA_CAP                 0x4000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RING_SELECT_MODE_TOEPLITZ_CAP           0x8000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RING_SELECT_MODE_XOR_CAP                0x10000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RING_SELECT_MODE_TOEPLITZ_CHKSM_CAP     0x20000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPV6_FLOW_LABEL_CAP                 0x40000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RX_CMPL_V3_CAP                          0x80000UL
-	#define VNIC_QCAPS_RESP_FLAGS_L2_CQE_MODE_CAP                         0x100000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_AH_SPI_IPV4_CAP               0x200000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV4_CAP              0x400000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_AH_SPI_IPV6_CAP               0x800000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV6_CAP              0x1000000UL
-	#define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_TRUSTED_VF_CAP            0x2000000UL
-	#define VNIC_QCAPS_RESP_FLAGS_PORTCOS_MAPPING_MODE                    0x4000000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_PROF_TCAM_MODE_ENABLED              0x8000000UL
-	#define VNIC_QCAPS_RESP_FLAGS_VNIC_RSS_HASH_MODE_CAP                  0x10000000UL
-	#define VNIC_QCAPS_RESP_FLAGS_HW_TUNNEL_TPA_CAP                       0x20000000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RE_FLUSH_CAP                            0x40000000UL
-	__le16	max_aggs_supported;
-	u8	unused_1[5];
-	u8	valid;
-};
-
-/* hwrm_vnic_tpa_cfg_input (size:384b/48B) */
-struct hwrm_vnic_tpa_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define VNIC_TPA_CFG_REQ_FLAGS_TPA                       0x1UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_ENCAP_TPA                 0x2UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_RSC_WND_UPDATE            0x4UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_GRO                       0x8UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_WITH_ECN              0x10UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_WITH_SAME_GRE_SEQ     0x20UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_GRO_IPID_CHECK            0x40UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_GRO_TTL_CHECK             0x80UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_PACK_AS_GRO           0x100UL
-	__le32	enables;
-	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGG_SEGS      0x1UL
-	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGGS          0x2UL
-	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGG_TIMER     0x4UL
-	#define VNIC_TPA_CFG_REQ_ENABLES_MIN_AGG_LEN       0x8UL
-	#define VNIC_TPA_CFG_REQ_ENABLES_TNL_TPA_EN        0x10UL
-	__le16	vnic_id;
-	__le16	max_agg_segs;
-	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_1   0x0UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_2   0x1UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_4   0x2UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_8   0x3UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_MAX 0x1fUL
-	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_LAST VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_MAX
-	__le16	max_aggs;
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_1   0x0UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_2   0x1UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_4   0x2UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_8   0x3UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_16  0x4UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_MAX 0x7UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_LAST VNIC_TPA_CFG_REQ_MAX_AGGS_MAX
-	u8	unused_0[2];
-	__le32	max_agg_timer;
-	__le32	min_agg_len;
-	__le32	tnl_tpa_en_bitmap;
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN           0x1UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GENEVE          0x2UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_NVGRE           0x4UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GRE             0x8UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV4            0x10UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV6            0x20UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN_GPE       0x40UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN_CUST1     0x80UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GRE_CUST1       0x100UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR1           0x200UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR2           0x400UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR3           0x800UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR4           0x1000UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR5           0x2000UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR6           0x4000UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR7           0x8000UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR8           0x10000UL
-	u8	unused_1[4];
-};
-
-/* hwrm_vnic_tpa_cfg_output (size:128b/16B) */
-struct hwrm_vnic_tpa_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_tpa_qcfg_input (size:192b/24B) */
-struct hwrm_vnic_tpa_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	vnic_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_vnic_tpa_qcfg_output (size:256b/32B) */
-struct hwrm_vnic_tpa_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define VNIC_TPA_QCFG_RESP_FLAGS_TPA                       0x1UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_ENCAP_TPA                 0x2UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_RSC_WND_UPDATE            0x4UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_GRO                       0x8UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_AGG_WITH_ECN              0x10UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_AGG_WITH_SAME_GRE_SEQ     0x20UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_GRO_IPID_CHECK            0x40UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_GRO_TTL_CHECK             0x80UL
-	__le16	max_agg_segs;
-	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_1   0x0UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_2   0x1UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_4   0x2UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_8   0x3UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_MAX 0x1fUL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_LAST VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_MAX
-	__le16	max_aggs;
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_1   0x0UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_2   0x1UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_4   0x2UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_8   0x3UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_16  0x4UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_MAX 0x7UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_LAST VNIC_TPA_QCFG_RESP_MAX_AGGS_MAX
-	__le32	max_agg_timer;
-	__le32	min_agg_len;
-	__le32	tnl_tpa_en_bitmap;
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_VXLAN           0x1UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_GENEVE          0x2UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_NVGRE           0x4UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_GRE             0x8UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_IPV4            0x10UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_IPV6            0x20UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_VXLAN_GPE       0x40UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_VXLAN_CUST1     0x80UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_GRE_CUST1       0x100UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR1           0x200UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR2           0x400UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR3           0x800UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR4           0x1000UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR5           0x2000UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR6           0x4000UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR7           0x8000UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR8           0x10000UL
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_vnic_rss_cfg_input (size:384b/48B) */
-struct hwrm_vnic_rss_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	hash_type;
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4                0x1UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4            0x2UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4            0x4UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6                0x8UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6            0x10UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6            0x20UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL     0x40UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV4         0x80UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV4        0x100UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV6         0x200UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV6        0x400UL
-	__le16	vnic_id;
-	u8	ring_table_pair_index;
-	u8	hash_mode_flags;
-	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT         0x1UL
-	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_4     0x2UL
-	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_2     0x4UL
-	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_4     0x8UL
-	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_2     0x10UL
-	__le64	ring_grp_tbl_addr;
-	__le64	hash_key_tbl_addr;
-	__le16	rss_ctx_idx;
-	u8	flags;
-	#define VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_INCLUDE               0x1UL
-	#define VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_EXCLUDE               0x2UL
-	#define VNIC_RSS_CFG_REQ_FLAGS_IPSEC_HASH_TYPE_CFG_SUPPORT     0x4UL
-	u8	ring_select_mode;
-	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_TOEPLITZ          0x0UL
-	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_XOR               0x1UL
-	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_TOEPLITZ_CHECKSUM 0x2UL
-	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_LAST             VNIC_RSS_CFG_REQ_RING_SELECT_MODE_TOEPLITZ_CHECKSUM
-	u8	unused_1[4];
-};
-
-/* hwrm_vnic_rss_cfg_output (size:128b/16B) */
-struct hwrm_vnic_rss_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_rss_cfg_cmd_err (size:64b/8B) */
-struct hwrm_vnic_rss_cfg_cmd_err {
-	u8	code;
-	#define VNIC_RSS_CFG_CMD_ERR_CODE_UNKNOWN             0x0UL
-	#define VNIC_RSS_CFG_CMD_ERR_CODE_INTERFACE_NOT_READY 0x1UL
-	#define VNIC_RSS_CFG_CMD_ERR_CODE_LAST               VNIC_RSS_CFG_CMD_ERR_CODE_INTERFACE_NOT_READY
-	u8	unused_0[7];
-};
-
-/* hwrm_vnic_rss_qcfg_input (size:192b/24B) */
-struct hwrm_vnic_rss_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	rss_ctx_idx;
-	__le16	vnic_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_vnic_rss_qcfg_output (size:512b/64B) */
-struct hwrm_vnic_rss_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	hash_type;
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV4                0x1UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_TCP_IPV4            0x2UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_UDP_IPV4            0x4UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV6                0x8UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_TCP_IPV6            0x10UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_UDP_IPV6            0x20UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV6_FLOW_LABEL     0x40UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_AH_SPI_IPV4         0x80UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_ESP_SPI_IPV4        0x100UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_AH_SPI_IPV6         0x200UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_ESP_SPI_IPV6        0x400UL
-	u8	unused_0[4];
-	__le32	hash_key[10];
-	u8	hash_mode_flags;
-	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_DEFAULT         0x1UL
-	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_INNERMOST_4     0x2UL
-	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_INNERMOST_2     0x4UL
-	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_OUTERMOST_4     0x8UL
-	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_OUTERMOST_2     0x10UL
-	u8	ring_select_mode;
-	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ          0x0UL
-	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_XOR               0x1UL
-	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ_CHECKSUM 0x2UL
-	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_LAST             VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ_CHECKSUM
-	u8	unused_1[5];
-	u8	valid;
-};
-
-/* hwrm_vnic_plcmodes_cfg_input (size:320b/40B) */
-struct hwrm_vnic_plcmodes_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_REGULAR_PLACEMENT     0x1UL
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT       0x2UL
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4              0x4UL
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6              0x8UL
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_FCOE              0x10UL
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_ROCE              0x20UL
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_VIRTIO_PLACEMENT      0x40UL
-	__le32	enables;
-	#define VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID      0x1UL
-	#define VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_OFFSET_VALID        0x2UL
-	#define VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID     0x4UL
-	#define VNIC_PLCMODES_CFG_REQ_ENABLES_MAX_BDS_VALID           0x8UL
-	__le32	vnic_id;
-	__le16	jumbo_thresh;
-	__le16	hds_offset;
-	__le16	hds_threshold;
-	__le16	max_bds;
-	u8	unused_0[4];
-};
-
-/* hwrm_vnic_plcmodes_cfg_output (size:128b/16B) */
-struct hwrm_vnic_plcmodes_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_rss_cos_lb_ctx_alloc_input (size:128b/16B) */
-struct hwrm_vnic_rss_cos_lb_ctx_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_vnic_rss_cos_lb_ctx_alloc_output (size:128b/16B) */
-struct hwrm_vnic_rss_cos_lb_ctx_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	rss_cos_lb_ctx_id;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_vnic_rss_cos_lb_ctx_free_input (size:192b/24B) */
-struct hwrm_vnic_rss_cos_lb_ctx_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	rss_cos_lb_ctx_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_vnic_rss_cos_lb_ctx_free_output (size:128b/16B) */
-struct hwrm_vnic_rss_cos_lb_ctx_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_ring_alloc_input (size:704b/88B) */
-struct hwrm_ring_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define RING_ALLOC_REQ_ENABLES_RING_ARB_CFG           0x2UL
-	#define RING_ALLOC_REQ_ENABLES_STAT_CTX_ID_VALID      0x8UL
-	#define RING_ALLOC_REQ_ENABLES_MAX_BW_VALID           0x20UL
-	#define RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID       0x40UL
-	#define RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID       0x80UL
-	#define RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID      0x100UL
-	#define RING_ALLOC_REQ_ENABLES_SCHQ_ID                0x200UL
-	#define RING_ALLOC_REQ_ENABLES_MPC_CHNLS_TYPE         0x400UL
-	#define RING_ALLOC_REQ_ENABLES_STEERING_TAG_VALID     0x800UL
-	u8	ring_type;
-	#define RING_ALLOC_REQ_RING_TYPE_L2_CMPL   0x0UL
-	#define RING_ALLOC_REQ_RING_TYPE_TX        0x1UL
-	#define RING_ALLOC_REQ_RING_TYPE_RX        0x2UL
-	#define RING_ALLOC_REQ_RING_TYPE_ROCE_CMPL 0x3UL
-	#define RING_ALLOC_REQ_RING_TYPE_RX_AGG    0x4UL
-	#define RING_ALLOC_REQ_RING_TYPE_NQ        0x5UL
-	#define RING_ALLOC_REQ_RING_TYPE_LAST     RING_ALLOC_REQ_RING_TYPE_NQ
-	u8	cmpl_coal_cnt;
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_OFF 0x0UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_4   0x1UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_8   0x2UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_12  0x3UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_16  0x4UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_24  0x5UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_32  0x6UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_48  0x7UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_64  0x8UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_96  0x9UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_128 0xaUL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_192 0xbUL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_256 0xcUL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_320 0xdUL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_384 0xeUL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_MAX 0xfUL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_LAST    RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_MAX
-	__le16	flags;
-	#define RING_ALLOC_REQ_FLAGS_RX_SOP_PAD                        0x1UL
-	#define RING_ALLOC_REQ_FLAGS_DISABLE_CQ_OVERFLOW_DETECTION     0x2UL
-	#define RING_ALLOC_REQ_FLAGS_NQ_DBR_PACING                     0x4UL
-	#define RING_ALLOC_REQ_FLAGS_TX_PKT_TS_CMPL_ENABLE             0x8UL
-	__le64	page_tbl_addr;
-	__le32	fbo;
-	u8	page_size;
-	u8	page_tbl_depth;
-	__le16	schq_id;
-	__le32	length;
-	__le16	logical_id;
-	__le16	cmpl_ring_id;
-	__le16	queue_id;
-	__le16	rx_buf_size;
-	__le16	rx_ring_id;
-	__le16	nq_ring_id;
-	__le16	ring_arb_cfg;
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_MASK      0xfUL
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_SFT       0
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_SP          0x1UL
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_WFQ         0x2UL
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_LAST       RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_WFQ
-	#define RING_ALLOC_REQ_RING_ARB_CFG_RSVD_MASK            0xf0UL
-	#define RING_ALLOC_REQ_RING_ARB_CFG_RSVD_SFT             4
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_PARAM_MASK 0xff00UL
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_PARAM_SFT 8
-	__le16	steering_tag;
-	__le32	reserved3;
-	__le32	stat_ctx_id;
-	__le32	reserved4;
-	__le32	max_bw;
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_SFT              0
-	#define RING_ALLOC_REQ_MAX_BW_SCALE                     0x10000000UL
-	#define RING_ALLOC_REQ_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define RING_ALLOC_REQ_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define RING_ALLOC_REQ_MAX_BW_SCALE_LAST                 RING_ALLOC_REQ_MAX_BW_SCALE_BYTES
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_LAST         RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	int_mode;
-	#define RING_ALLOC_REQ_INT_MODE_LEGACY 0x0UL
-	#define RING_ALLOC_REQ_INT_MODE_RSVD   0x1UL
-	#define RING_ALLOC_REQ_INT_MODE_MSIX   0x2UL
-	#define RING_ALLOC_REQ_INT_MODE_POLL   0x3UL
-	#define RING_ALLOC_REQ_INT_MODE_LAST  RING_ALLOC_REQ_INT_MODE_POLL
-	u8	mpc_chnls_type;
-	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_TCE     0x0UL
-	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_RCE     0x1UL
-	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_TE_CFA  0x2UL
-	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_RE_CFA  0x3UL
-	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE 0x4UL
-	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_LAST   RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE
-	u8	unused_4[2];
-	__le64	cq_handle;
-};
-
-/* hwrm_ring_alloc_output (size:128b/16B) */
-struct hwrm_ring_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	ring_id;
-	__le16	logical_ring_id;
-	u8	push_buffer_index;
-	#define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PING_BUFFER 0x0UL
-	#define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER 0x1UL
-	#define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_LAST       RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER
-	u8	unused_0[2];
-	u8	valid;
-};
-
-/* hwrm_ring_free_input (size:256b/32B) */
-struct hwrm_ring_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	ring_type;
-	#define RING_FREE_REQ_RING_TYPE_L2_CMPL   0x0UL
-	#define RING_FREE_REQ_RING_TYPE_TX        0x1UL
-	#define RING_FREE_REQ_RING_TYPE_RX        0x2UL
-	#define RING_FREE_REQ_RING_TYPE_ROCE_CMPL 0x3UL
-	#define RING_FREE_REQ_RING_TYPE_RX_AGG    0x4UL
-	#define RING_FREE_REQ_RING_TYPE_NQ        0x5UL
-	#define RING_FREE_REQ_RING_TYPE_LAST     RING_FREE_REQ_RING_TYPE_NQ
-	u8	flags;
-	#define RING_FREE_REQ_FLAGS_VIRTIO_RING_VALID 0x1UL
-	#define RING_FREE_REQ_FLAGS_LAST             RING_FREE_REQ_FLAGS_VIRTIO_RING_VALID
-	__le16	ring_id;
-	__le32	prod_idx;
-	__le32	opaque;
-	__le32	unused_1;
-};
-
-/* hwrm_ring_free_output (size:128b/16B) */
-struct hwrm_ring_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_ring_reset_input (size:192b/24B) */
-struct hwrm_ring_reset_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	ring_type;
-	#define RING_RESET_REQ_RING_TYPE_L2_CMPL     0x0UL
-	#define RING_RESET_REQ_RING_TYPE_TX          0x1UL
-	#define RING_RESET_REQ_RING_TYPE_RX          0x2UL
-	#define RING_RESET_REQ_RING_TYPE_ROCE_CMPL   0x3UL
-	#define RING_RESET_REQ_RING_TYPE_RX_RING_GRP 0x6UL
-	#define RING_RESET_REQ_RING_TYPE_LAST       RING_RESET_REQ_RING_TYPE_RX_RING_GRP
-	u8	unused_0;
-	__le16	ring_id;
-	u8	unused_1[4];
-};
-
-/* hwrm_ring_reset_output (size:128b/16B) */
-struct hwrm_ring_reset_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	push_buffer_index;
-	#define RING_RESET_RESP_PUSH_BUFFER_INDEX_PING_BUFFER 0x0UL
-	#define RING_RESET_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER 0x1UL
-	#define RING_RESET_RESP_PUSH_BUFFER_INDEX_LAST       RING_RESET_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER
-	u8	unused_0[3];
-	u8	consumer_idx[3];
-	u8	valid;
-};
-
-/* hwrm_ring_aggint_qcaps_input (size:128b/16B) */
-struct hwrm_ring_aggint_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_ring_aggint_qcaps_output (size:384b/48B) */
-struct hwrm_ring_aggint_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	cmpl_params;
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MIN                  0x1UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MAX                  0x2UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_TIMER_RESET                      0x4UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_RING_IDLE                        0x8UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR                0x10UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR_DURING_INT     0x20UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR                0x40UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR_DURING_INT     0x80UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_AGGR_INT                0x100UL
-	__le32	nq_params;
-	#define RING_AGGINT_QCAPS_RESP_NQ_PARAMS_INT_LAT_TMR_MIN     0x1UL
-	__le16	num_cmpl_dma_aggr_min;
-	__le16	num_cmpl_dma_aggr_max;
-	__le16	num_cmpl_dma_aggr_during_int_min;
-	__le16	num_cmpl_dma_aggr_during_int_max;
-	__le16	cmpl_aggr_dma_tmr_min;
-	__le16	cmpl_aggr_dma_tmr_max;
-	__le16	cmpl_aggr_dma_tmr_during_int_min;
-	__le16	cmpl_aggr_dma_tmr_during_int_max;
-	__le16	int_lat_tmr_min_min;
-	__le16	int_lat_tmr_min_max;
-	__le16	int_lat_tmr_max_min;
-	__le16	int_lat_tmr_max_max;
-	__le16	num_cmpl_aggr_int_min;
-	__le16	num_cmpl_aggr_int_max;
-	__le16	timer_units;
-	u8	unused_0[1];
-	u8	valid;
-};
-
-/* hwrm_ring_cmpl_ring_qaggint_params_input (size:192b/24B) */
-struct hwrm_ring_cmpl_ring_qaggint_params_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	ring_id;
-	__le16	flags;
-	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_UNUSED_0_MASK 0x3UL
-	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_UNUSED_0_SFT 0
-	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_IS_NQ        0x4UL
-	u8	unused_0[4];
-};
-
-/* hwrm_ring_cmpl_ring_qaggint_params_output (size:256b/32B) */
-struct hwrm_ring_cmpl_ring_qaggint_params_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	flags;
-	#define RING_CMPL_RING_QAGGINT_PARAMS_RESP_FLAGS_TIMER_RESET     0x1UL
-	#define RING_CMPL_RING_QAGGINT_PARAMS_RESP_FLAGS_RING_IDLE       0x2UL
-	__le16	num_cmpl_dma_aggr;
-	__le16	num_cmpl_dma_aggr_during_int;
-	__le16	cmpl_aggr_dma_tmr;
-	__le16	cmpl_aggr_dma_tmr_during_int;
-	__le16	int_lat_tmr_min;
-	__le16	int_lat_tmr_max;
-	__le16	num_cmpl_aggr_int;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_ring_cmpl_ring_cfg_aggint_params_input (size:320b/40B) */
-struct hwrm_ring_cmpl_ring_cfg_aggint_params_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	ring_id;
-	__le16	flags;
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_TIMER_RESET     0x1UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_RING_IDLE       0x2UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_IS_NQ           0x4UL
-	__le16	num_cmpl_dma_aggr;
-	__le16	num_cmpl_dma_aggr_during_int;
-	__le16	cmpl_aggr_dma_tmr;
-	__le16	cmpl_aggr_dma_tmr_during_int;
-	__le16	int_lat_tmr_min;
-	__le16	int_lat_tmr_max;
-	__le16	num_cmpl_aggr_int;
-	__le16	enables;
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR                0x1UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR_DURING_INT     0x2UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_CMPL_AGGR_DMA_TMR                0x4UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MIN                  0x8UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MAX                  0x10UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_AGGR_INT                0x20UL
-	u8	unused_0[4];
-};
-
-/* hwrm_ring_cmpl_ring_cfg_aggint_params_output (size:128b/16B) */
-struct hwrm_ring_cmpl_ring_cfg_aggint_params_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_ring_grp_alloc_input (size:192b/24B) */
-struct hwrm_ring_grp_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	cr;
-	__le16	rr;
-	__le16	ar;
-	__le16	sc;
-};
-
-/* hwrm_ring_grp_alloc_output (size:128b/16B) */
-struct hwrm_ring_grp_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	ring_group_id;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_ring_grp_free_input (size:192b/24B) */
-struct hwrm_ring_grp_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	ring_group_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_ring_grp_free_output (size:128b/16B) */
-struct hwrm_ring_grp_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-#define DEFAULT_FLOW_ID 0xFFFFFFFFUL
-#define ROCEV1_FLOW_ID 0xFFFFFFFEUL
-#define ROCEV2_FLOW_ID 0xFFFFFFFDUL
-#define ROCEV2_CNP_FLOW_ID 0xFFFFFFFCUL
-
-/* hwrm_cfa_l2_filter_alloc_input (size:768b/96B) */
-struct hwrm_cfa_l2_filter_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH              0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_TX             0x0UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX             0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_LAST          CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_LOOPBACK          0x2UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_DROP              0x4UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST         0x8UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_MASK      0x30UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_SFT       4
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_NO_ROCE_L2  (0x0UL << 4)
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_L2          (0x1UL << 4)
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_ROCE        (0x2UL << 4)
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_LAST       CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_ROCE
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_XDP_DISABLE       0x40UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_SOURCE_VALID      0x80UL
-	__le32	enables;
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR             0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK        0x2UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_OVLAN            0x4UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_OVLAN_MASK       0x8UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN            0x10UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN_MASK       0x20UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_ADDR           0x40UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_ADDR_MASK      0x80UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_OVLAN          0x100UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_OVLAN_MASK     0x200UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_IVLAN          0x400UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_IVLAN_MASK     0x800UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_SRC_TYPE            0x1000UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_SRC_ID              0x2000UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE         0x4000UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID              0x8000UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID      0x10000UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_NUM_VLANS           0x20000UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_NUM_VLANS         0x40000UL
-	u8	l2_addr[6];
-	u8	num_vlans;
-	u8	t_num_vlans;
-	u8	l2_addr_mask[6];
-	__le16	l2_ovlan;
-	__le16	l2_ovlan_mask;
-	__le16	l2_ivlan;
-	__le16	l2_ivlan_mask;
-	u8	unused_1[2];
-	u8	t_l2_addr[6];
-	u8	unused_2[2];
-	u8	t_l2_addr_mask[6];
-	__le16	t_l2_ovlan;
-	__le16	t_l2_ovlan_mask;
-	__le16	t_l2_ivlan;
-	__le16	t_l2_ivlan_mask;
-	u8	src_type;
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_NPORT 0x0UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_PF    0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_VF    0x2UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_VNIC  0x3UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_KONG  0x4UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_APE   0x5UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_BONO  0x6UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_TANG  0x7UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_LAST CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_TANG
-	u8	unused_3;
-	__le32	src_id;
-	u8	tunnel_type;
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
-	u8	unused_4;
-	__le16	dst_id;
-	__le16	mirror_vnic_id;
-	u8	pri_hint;
-	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER    0x0UL
-	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_ABOVE_FILTER 0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_BELOW_FILTER 0x2UL
-	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_MAX          0x3UL
-	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_MIN          0x4UL
-	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_LAST        CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_MIN
-	u8	unused_5;
-	__le32	unused_6;
-	__le64	l2_filter_id_hint;
-};
-
-/* hwrm_cfa_l2_filter_alloc_output (size:192b/24B) */
-struct hwrm_cfa_l2_filter_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	l2_filter_id;
-	__le32	flow_id;
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_l2_filter_free_input (size:192b/24B) */
-struct hwrm_cfa_l2_filter_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	l2_filter_id;
-};
-
-/* hwrm_cfa_l2_filter_free_output (size:128b/16B) */
-struct hwrm_cfa_l2_filter_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_l2_filter_cfg_input (size:384b/48B) */
-struct hwrm_cfa_l2_filter_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH                  0x1UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX                 0x0UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX                 0x1UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST              CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP                  0x2UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK          0xcUL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT           2
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2      (0x0UL << 2)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2              (0x1UL << 2)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE            (0x2UL << 2)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST           CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_MASK         0x30UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_SFT          4
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_NO_UPDATE      (0x0UL << 4)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_BYPASS_LKUP    (0x1UL << 4)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP    (0x2UL << 4)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP  (0x3UL << 4)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_LAST          CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP
-	__le32	enables;
-	#define CFA_L2_FILTER_CFG_REQ_ENABLES_DST_ID                 0x1UL
-	#define CFA_L2_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID     0x2UL
-	#define CFA_L2_FILTER_CFG_REQ_ENABLES_PROF_FUNC              0x4UL
-	#define CFA_L2_FILTER_CFG_REQ_ENABLES_L2_CONTEXT_ID          0x8UL
-	__le64	l2_filter_id;
-	__le32	dst_id;
-	__le32	new_mirror_vnic_id;
-	__le32	prof_func;
-	__le32	l2_context_id;
-};
-
-/* hwrm_cfa_l2_filter_cfg_output (size:128b/16B) */
-struct hwrm_cfa_l2_filter_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_l2_set_rx_mask_input (size:448b/56B) */
-struct hwrm_cfa_l2_set_rx_mask_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	vnic_id;
-	__le32	mask;
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_MCAST               0x2UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST           0x4UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_BCAST               0x8UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS         0x10UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_OUTERMOST           0x20UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_VLANONLY            0x40UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_VLAN_NONVLAN        0x80UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_ANYVLAN_NONVLAN     0x100UL
-	__le64	mc_tbl_addr;
-	__le32	num_mc_entries;
-	u8	unused_0[4];
-	__le64	vlan_tag_tbl_addr;
-	__le32	num_vlan_tags;
-	u8	unused_1[4];
-};
-
-/* hwrm_cfa_l2_set_rx_mask_output (size:128b/16B) */
-struct hwrm_cfa_l2_set_rx_mask_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_l2_set_rx_mask_cmd_err (size:64b/8B) */
-struct hwrm_cfa_l2_set_rx_mask_cmd_err {
-	u8	code;
-	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_UNKNOWN                    0x0UL
-	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_NTUPLE_FILTER_CONFLICT_ERR 0x1UL
-	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_LAST                      CFA_L2_SET_RX_MASK_CMD_ERR_CODE_NTUPLE_FILTER_CONFLICT_ERR
-	u8	unused_0[7];
-};
-
-/* hwrm_cfa_tunnel_filter_alloc_input (size:704b/88B) */
-struct hwrm_cfa_tunnel_filter_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_FLAGS_LOOPBACK     0x1UL
-	__le32	enables;
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID       0x1UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L2_ADDR            0x2UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN           0x4UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L3_ADDR            0x8UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L3_ADDR_TYPE       0x10UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_T_L3_ADDR_TYPE     0x20UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_T_L3_ADDR          0x40UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE        0x80UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_VNI                0x100UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_DST_VNIC_ID        0x200UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID     0x400UL
-	__le64	l2_filter_id;
-	u8	l2_addr[6];
-	__le16	l2_ivlan;
-	__le32	l3_addr[4];
-	__le32	t_l3_addr[4];
-	u8	l3_addr_type;
-	u8	t_l3_addr_type;
-	u8	tunnel_type;
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
-	u8	tunnel_flags;
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_OAM_CHECKSUM_EXPLHDR     0x1UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_CRITICAL_OPT_S1          0x2UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_EXTHDR_SEQNUM_S0         0x4UL
-	__le32	vni;
-	__le32	dst_vnic_id;
-	__le32	mirror_vnic_id;
-};
-
-/* hwrm_cfa_tunnel_filter_alloc_output (size:192b/24B) */
-struct hwrm_cfa_tunnel_filter_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	tunnel_filter_id;
-	__le32	flow_id;
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_tunnel_filter_free_input (size:192b/24B) */
-struct hwrm_cfa_tunnel_filter_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	tunnel_filter_id;
-};
-
-/* hwrm_cfa_tunnel_filter_free_output (size:128b/16B) */
-struct hwrm_cfa_tunnel_filter_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vxlan_ipv4_hdr (size:128b/16B) */
-struct hwrm_vxlan_ipv4_hdr {
-	u8	ver_hlen;
-	#define VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_MASK 0xfUL
-	#define VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_SFT 0
-	#define VXLAN_IPV4_HDR_VER_HLEN_VERSION_MASK      0xf0UL
-	#define VXLAN_IPV4_HDR_VER_HLEN_VERSION_SFT       4
-	u8	tos;
-	__be16	ip_id;
-	__be16	flags_frag_offset;
-	u8	ttl;
-	u8	protocol;
-	__be32	src_ip_addr;
-	__be32	dest_ip_addr;
-};
-
-/* hwrm_vxlan_ipv6_hdr (size:320b/40B) */
-struct hwrm_vxlan_ipv6_hdr {
-	__be32	ver_tc_flow_label;
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_VER_SFT         0x1cUL
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_VER_MASK        0xf0000000UL
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_TC_SFT          0x14UL
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_TC_MASK         0xff00000UL
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_SFT  0x0UL
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_MASK 0xfffffUL
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_LAST           VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_MASK
-	__be16	payload_len;
-	u8	next_hdr;
-	u8	ttl;
-	__be32	src_ip_addr[4];
-	__be32	dest_ip_addr[4];
-};
-
-/* hwrm_cfa_encap_data_vxlan (size:640b/80B) */
-struct hwrm_cfa_encap_data_vxlan {
-	u8	src_mac_addr[6];
-	__le16	unused_0;
-	u8	dst_mac_addr[6];
-	u8	num_vlan_tags;
-	u8	unused_1;
-	__be16	ovlan_tpid;
-	__be16	ovlan_tci;
-	__be16	ivlan_tpid;
-	__be16	ivlan_tci;
-	__le32	l3[10];
-	#define CFA_ENCAP_DATA_VXLAN_L3_VER_MASK 0xfUL
-	#define CFA_ENCAP_DATA_VXLAN_L3_VER_IPV4 0x4UL
-	#define CFA_ENCAP_DATA_VXLAN_L3_VER_IPV6 0x6UL
-	#define CFA_ENCAP_DATA_VXLAN_L3_LAST    CFA_ENCAP_DATA_VXLAN_L3_VER_IPV6
-	__be16	src_port;
-	__be16	dst_port;
-	__be32	vni;
-	u8	hdr_rsvd0[3];
-	u8	hdr_rsvd1;
-	u8	hdr_flags;
-	u8	unused[3];
-};
-
-/* hwrm_cfa_encap_record_alloc_input (size:832b/104B) */
-struct hwrm_cfa_encap_record_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_LOOPBACK     0x1UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_EXTERNAL     0x2UL
-	u8	encap_type;
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN        0x1UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_NVGRE        0x2UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2GRE        0x3UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPIP         0x4UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_GENEVE       0x5UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_MPLS         0x6UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VLAN         0x7UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE        0x8UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_V4     0x9UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE_V1     0xaUL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2_ETYPE     0xbUL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE_V6 0xcUL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE    0x10UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_LAST        CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE
-	u8	unused_0[3];
-	__le32	encap_data[20];
-};
-
-/* hwrm_cfa_encap_record_alloc_output (size:128b/16B) */
-struct hwrm_cfa_encap_record_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	encap_record_id;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_encap_record_free_input (size:192b/24B) */
-struct hwrm_cfa_encap_record_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	encap_record_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_cfa_encap_record_free_output (size:128b/16B) */
-struct hwrm_cfa_encap_record_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_ntuple_filter_alloc_input (size:1024b/128B) */
-struct hwrm_cfa_ntuple_filter_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_LOOPBACK              0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DROP                  0x2UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_METER                 0x4UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_FID              0x8UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_ARP_REPLY             0x10UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_RFS_RING_IDX     0x20UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_NO_L2_CONTEXT         0x40UL
-	__le32	enables;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID         0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE            0x2UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE          0x4UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR          0x8UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE          0x10UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR           0x20UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR_MASK      0x40UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR           0x80UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR_MASK      0x100UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_IP_PROTOCOL          0x200UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_PORT             0x400UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_PORT_MASK        0x800UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_PORT             0x1000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_PORT_MASK        0x2000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_PRI_HINT             0x4000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_NTUPLE_FILTER_ID     0x8000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_ID               0x10000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID       0x20000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR          0x40000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_RFS_RING_TBL_IDX     0x80000UL
-	__le64	l2_filter_id;
-	u8	src_macaddr[6];
-	__be16	ethertype;
-	u8	ip_addr_type;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_UNKNOWN 0x0UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4    0x4UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6    0x6UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_LAST   CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6
-	u8	ip_protocol;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN 0x0UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP     0x6UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP     0x11UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_ICMP    0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_ICMPV6  0x3aUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD    0xffUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_LAST   CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD
-	__le16	dst_id;
-	__le16	rfs_ring_tbl_idx;
-	u8	tunnel_type;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
-	u8	pri_hint;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER 0x0UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_ABOVE     0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_BELOW     0x2UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_HIGHEST   0x3UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_LOWEST    0x4UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_LAST     CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_LOWEST
-	__be32	src_ipaddr[4];
-	__be32	src_ipaddr_mask[4];
-	__be32	dst_ipaddr[4];
-	__be32	dst_ipaddr_mask[4];
-	__be16	src_port;
-	__be16	src_port_mask;
-	__be16	dst_port;
-	__be16	dst_port_mask;
-	__le64	ntuple_filter_id_hint;
-};
-
-/* hwrm_cfa_ntuple_filter_alloc_output (size:192b/24B) */
-struct hwrm_cfa_ntuple_filter_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	ntuple_filter_id;
-	__le32	flow_id;
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_ntuple_filter_alloc_cmd_err (size:64b/8B) */
-struct hwrm_cfa_ntuple_filter_alloc_cmd_err {
-	u8	code;
-	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_UNKNOWN                   0x0UL
-	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_RX_MASK_VLAN_CONFLICT_ERR 0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_LAST                     CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_RX_MASK_VLAN_CONFLICT_ERR
-	u8	unused_0[7];
-};
-
-/* hwrm_cfa_ntuple_filter_free_input (size:192b/24B) */
-struct hwrm_cfa_ntuple_filter_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	ntuple_filter_id;
-};
-
-/* hwrm_cfa_ntuple_filter_free_output (size:128b/16B) */
-struct hwrm_cfa_ntuple_filter_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_ntuple_filter_cfg_input (size:384b/48B) */
-struct hwrm_cfa_ntuple_filter_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_DST_ID                0x1UL
-	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID        0x2UL
-	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_METER_INSTANCE_ID     0x4UL
-	__le32	flags;
-	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_DEST_FID              0x1UL
-	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_DEST_RFS_RING_IDX     0x2UL
-	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_NO_L2_CONTEXT         0x4UL
-	__le64	ntuple_filter_id;
-	__le32	new_dst_id;
-	__le32	new_mirror_vnic_id;
-	__le16	new_meter_instance_id;
-	#define CFA_NTUPLE_FILTER_CFG_REQ_NEW_METER_INSTANCE_ID_INVALID 0xffffUL
-	#define CFA_NTUPLE_FILTER_CFG_REQ_NEW_METER_INSTANCE_ID_LAST   CFA_NTUPLE_FILTER_CFG_REQ_NEW_METER_INSTANCE_ID_INVALID
-	u8	unused_1[6];
-};
-
-/* hwrm_cfa_ntuple_filter_cfg_output (size:128b/16B) */
-struct hwrm_cfa_ntuple_filter_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_decap_filter_alloc_input (size:832b/104B) */
-struct hwrm_cfa_decap_filter_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_DECAP_FILTER_ALLOC_REQ_FLAGS_OVS_TUNNEL     0x1UL
-	__le32	enables;
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE        0x1UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_ID          0x2UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR        0x4UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR        0x8UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_OVLAN_VID          0x10UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IVLAN_VID          0x20UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_OVLAN_VID        0x40UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_IVLAN_VID        0x80UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE          0x100UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR         0x200UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR         0x400UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE        0x800UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IP_PROTOCOL        0x1000UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_PORT           0x2000UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_PORT           0x4000UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_ID             0x8000UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID     0x10000UL
-	__be32	tunnel_id;
-	u8	tunnel_type;
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
-	u8	unused_0;
-	__le16	unused_1;
-	u8	src_macaddr[6];
-	u8	unused_2[2];
-	u8	dst_macaddr[6];
-	__be16	ovlan_vid;
-	__be16	ivlan_vid;
-	__be16	t_ovlan_vid;
-	__be16	t_ivlan_vid;
-	__be16	ethertype;
-	u8	ip_addr_type;
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_UNKNOWN 0x0UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4    0x4UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6    0x6UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_LAST   CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6
-	u8	ip_protocol;
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN 0x0UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP     0x6UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP     0x11UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_LAST   CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP
-	__le16	unused_3;
-	__le32	unused_4;
-	__be32	src_ipaddr[4];
-	__be32	dst_ipaddr[4];
-	__be16	src_port;
-	__be16	dst_port;
-	__le16	dst_id;
-	__le16	l2_ctxt_ref_id;
-};
-
-/* hwrm_cfa_decap_filter_alloc_output (size:128b/16B) */
-struct hwrm_cfa_decap_filter_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	decap_filter_id;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_decap_filter_free_input (size:192b/24B) */
-struct hwrm_cfa_decap_filter_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	decap_filter_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_cfa_decap_filter_free_output (size:128b/16B) */
-struct hwrm_cfa_decap_filter_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_flow_alloc_input (size:1024b/128B) */
-struct hwrm_cfa_flow_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	flags;
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_TUNNEL                 0x1UL
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_MASK          0x6UL
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_SFT           1
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_NONE            (0x0UL << 1)
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_ONE             (0x1UL << 1)
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO             (0x2UL << 1)
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_LAST           CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_MASK          0x38UL
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_SFT           3
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_L2              (0x0UL << 3)
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV4            (0x1UL << 3)
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6            (0x2UL << 3)
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_LAST           CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_PATH_TX                0x40UL
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_PATH_RX                0x80UL
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_MATCH_VXLAN_IP_VNI     0x100UL
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_VHOST_ID_USE_VLAN      0x200UL
-	__le16	src_fid;
-	__le32	tunnel_handle;
-	__le16	action_flags;
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD                       0x1UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_RECYCLE                   0x2UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP                      0x4UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_METER                     0x8UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL                    0x10UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC                   0x20UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST                  0x40UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_IPV4_ADDRESS          0x80UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE         0x100UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TTL_DECREMENT             0x200UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL_IP                 0x400UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FLOW_AGING_ENABLED        0x800UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_PRI_HINT                  0x1000UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NO_FLOW_COUNTER_ALLOC     0x2000UL
-	__le16	dst_fid;
-	__be16	l2_rewrite_vlan_tpid;
-	__be16	l2_rewrite_vlan_tci;
-	__le16	act_meter_id;
-	__le16	ref_flow_handle;
-	__be16	ethertype;
-	__be16	outer_vlan_tci;
-	__be16	dmac[3];
-	__be16	inner_vlan_tci;
-	__be16	smac[3];
-	u8	ip_dst_mask_len;
-	u8	ip_src_mask_len;
-	__be32	ip_dst[4];
-	__be32	ip_src[4];
-	__be16	l4_src_port;
-	__be16	l4_src_port_mask;
-	__be16	l4_dst_port;
-	__be16	l4_dst_port_mask;
-	__be32	nat_ip_address[4];
-	__be16	l2_rewrite_dmac[3];
-	__be16	nat_port;
-	__be16	l2_rewrite_smac[3];
-	u8	ip_proto;
-	u8	tunnel_type;
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
-};
-
-/* hwrm_cfa_flow_alloc_output (size:256b/32B) */
-struct hwrm_cfa_flow_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	flow_handle;
-	u8	unused_0[2];
-	__le32	flow_id;
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_EXT
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_TX
-	__le64	ext_flow_handle;
-	__le32	flow_counter_id;
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_flow_alloc_cmd_err (size:64b/8B) */
-struct hwrm_cfa_flow_alloc_cmd_err {
-	u8	code;
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_UNKNOWN         0x0UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_L2_CONTEXT_TCAM 0x1UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_ACTION_RECORD   0x2UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_COUNTER    0x3UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_WILD_CARD_TCAM  0x4UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_HASH_COLLISION  0x5UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_KEY_EXISTS      0x6UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_CTXT_DB    0x7UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_LAST           CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_CTXT_DB
-	u8	unused_0[7];
-};
-
-/* hwrm_cfa_flow_free_input (size:256b/32B) */
-struct hwrm_cfa_flow_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	flow_handle;
-	__le16	unused_0;
-	__le32	flow_counter_id;
-	__le64	ext_flow_handle;
-};
-
-/* hwrm_cfa_flow_free_output (size:256b/32B) */
-struct hwrm_cfa_flow_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	packet;
-	__le64	byte;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_flow_info_input (size:256b/32B) */
-struct hwrm_cfa_flow_info_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	flow_handle;
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_MASK      0xfffUL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_CNP_CNT       0x1000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV1_CNT    0x2000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_NIC_TX        0x3000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT    0x4000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_DIR_RX        0x8000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_CNP_CNT_RX    0x9000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV1_CNT_RX 0xa000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_NIC_RX        0xb000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT_RX 0xc000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_LAST         CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT_RX
-	u8	unused_0[6];
-	__le64	ext_flow_handle;
-};
-
-/* hwrm_cfa_flow_info_output (size:5632b/704B) */
-struct hwrm_cfa_flow_info_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define CFA_FLOW_INFO_RESP_FLAGS_PATH_TX     0x1UL
-	#define CFA_FLOW_INFO_RESP_FLAGS_PATH_RX     0x2UL
-	u8	profile;
-	__le16	src_fid;
-	__le16	dst_fid;
-	__le16	l2_ctxt_id;
-	__le64	em_info;
-	__le64	tcam_info;
-	__le64	vfp_tcam_info;
-	__le16	ar_id;
-	__le16	flow_handle;
-	__le32	tunnel_handle;
-	__le16	flow_timer;
-	u8	unused_0[6];
-	__le32	flow_key_data[130];
-	__le32	flow_action_info[30];
-	u8	unused_1[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_flow_stats_input (size:640b/80B) */
-struct hwrm_cfa_flow_stats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	num_flows;
-	__le16	flow_handle_0;
-	__le16	flow_handle_1;
-	__le16	flow_handle_2;
-	__le16	flow_handle_3;
-	__le16	flow_handle_4;
-	__le16	flow_handle_5;
-	__le16	flow_handle_6;
-	__le16	flow_handle_7;
-	__le16	flow_handle_8;
-	__le16	flow_handle_9;
-	u8	unused_0[2];
-	__le32	flow_id_0;
-	__le32	flow_id_1;
-	__le32	flow_id_2;
-	__le32	flow_id_3;
-	__le32	flow_id_4;
-	__le32	flow_id_5;
-	__le32	flow_id_6;
-	__le32	flow_id_7;
-	__le32	flow_id_8;
-	__le32	flow_id_9;
-};
-
-/* hwrm_cfa_flow_stats_output (size:1408b/176B) */
-struct hwrm_cfa_flow_stats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	packet_0;
-	__le64	packet_1;
-	__le64	packet_2;
-	__le64	packet_3;
-	__le64	packet_4;
-	__le64	packet_5;
-	__le64	packet_6;
-	__le64	packet_7;
-	__le64	packet_8;
-	__le64	packet_9;
-	__le64	byte_0;
-	__le64	byte_1;
-	__le64	byte_2;
-	__le64	byte_3;
-	__le64	byte_4;
-	__le64	byte_5;
-	__le64	byte_6;
-	__le64	byte_7;
-	__le64	byte_8;
-	__le64	byte_9;
-	__le16	flow_hits;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_cfa_vfr_alloc_input (size:448b/56B) */
-struct hwrm_cfa_vfr_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	vf_id;
-	__le16	reserved;
-	u8	unused_0[4];
-	char	vfr_name[32];
-};
-
-/* hwrm_cfa_vfr_alloc_output (size:128b/16B) */
-struct hwrm_cfa_vfr_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	rx_cfa_code;
-	__le16	tx_cfa_action;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_vfr_free_input (size:448b/56B) */
-struct hwrm_cfa_vfr_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	char	vfr_name[32];
-	__le16	vf_id;
-	__le16	reserved;
-	u8	unused_0[4];
-};
-
-/* hwrm_cfa_vfr_free_output (size:128b/16B) */
-struct hwrm_cfa_vfr_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_eem_qcaps_input (size:192b/24B) */
-struct hwrm_cfa_eem_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_EEM_QCAPS_REQ_FLAGS_PATH_TX               0x1UL
-	#define CFA_EEM_QCAPS_REQ_FLAGS_PATH_RX               0x2UL
-	#define CFA_EEM_QCAPS_REQ_FLAGS_PREFERRED_OFFLOAD     0x4UL
-	__le32	unused_0;
-};
-
-/* hwrm_cfa_eem_qcaps_output (size:320b/40B) */
-struct hwrm_cfa_eem_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_TX                                         0x1UL
-	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_RX                                         0x2UL
-	#define CFA_EEM_QCAPS_RESP_FLAGS_CENTRALIZED_MEMORY_MODEL_SUPPORTED              0x4UL
-	#define CFA_EEM_QCAPS_RESP_FLAGS_DETACHED_CENTRALIZED_MEMORY_MODEL_SUPPORTED     0x8UL
-	__le32	unused_0;
-	__le32	supported;
-	#define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY0_TABLE                       0x1UL
-	#define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY1_TABLE                       0x2UL
-	#define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_RECORD_TABLE            0x4UL
-	#define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_FLOW_COUNTERS_TABLE     0x8UL
-	#define CFA_EEM_QCAPS_RESP_SUPPORTED_FID_TABLE                        0x10UL
-	__le32	max_entries_supported;
-	__le16	key_entry_size;
-	__le16	record_entry_size;
-	__le16	efc_entry_size;
-	__le16	fid_entry_size;
-	u8	unused_1[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_eem_cfg_input (size:384b/48B) */
-struct hwrm_cfa_eem_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_EEM_CFG_REQ_FLAGS_PATH_TX               0x1UL
-	#define CFA_EEM_CFG_REQ_FLAGS_PATH_RX               0x2UL
-	#define CFA_EEM_CFG_REQ_FLAGS_PREFERRED_OFFLOAD     0x4UL
-	#define CFA_EEM_CFG_REQ_FLAGS_SECONDARY_PF          0x8UL
-	__le16	group_id;
-	__le16	unused_0;
-	__le32	num_entries;
-	__le32	unused_1;
-	__le16	key0_ctx_id;
-	__le16	key1_ctx_id;
-	__le16	record_ctx_id;
-	__le16	efc_ctx_id;
-	__le16	fid_ctx_id;
-	__le16	unused_2;
-	__le32	unused_3;
-};
-
-/* hwrm_cfa_eem_cfg_output (size:128b/16B) */
-struct hwrm_cfa_eem_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_eem_qcfg_input (size:192b/24B) */
-struct hwrm_cfa_eem_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_EEM_QCFG_REQ_FLAGS_PATH_TX     0x1UL
-	#define CFA_EEM_QCFG_REQ_FLAGS_PATH_RX     0x2UL
-	__le32	unused_0;
-};
-
-/* hwrm_cfa_eem_qcfg_output (size:256b/32B) */
-struct hwrm_cfa_eem_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define CFA_EEM_QCFG_RESP_FLAGS_PATH_TX               0x1UL
-	#define CFA_EEM_QCFG_RESP_FLAGS_PATH_RX               0x2UL
-	#define CFA_EEM_QCFG_RESP_FLAGS_PREFERRED_OFFLOAD     0x4UL
-	__le32	num_entries;
-	__le16	key0_ctx_id;
-	__le16	key1_ctx_id;
-	__le16	record_ctx_id;
-	__le16	efc_ctx_id;
-	__le16	fid_ctx_id;
-	u8	unused_2[5];
-	u8	valid;
-};
-
-/* hwrm_cfa_eem_op_input (size:192b/24B) */
-struct hwrm_cfa_eem_op_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_EEM_OP_REQ_FLAGS_PATH_TX     0x1UL
-	#define CFA_EEM_OP_REQ_FLAGS_PATH_RX     0x2UL
-	__le16	unused_0;
-	__le16	op;
-	#define CFA_EEM_OP_REQ_OP_RESERVED    0x0UL
-	#define CFA_EEM_OP_REQ_OP_EEM_DISABLE 0x1UL
-	#define CFA_EEM_OP_REQ_OP_EEM_ENABLE  0x2UL
-	#define CFA_EEM_OP_REQ_OP_EEM_CLEANUP 0x3UL
-	#define CFA_EEM_OP_REQ_OP_LAST       CFA_EEM_OP_REQ_OP_EEM_CLEANUP
-};
-
-/* hwrm_cfa_eem_op_output (size:128b/16B) */
-struct hwrm_cfa_eem_op_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_adv_flow_mgnt_qcaps_input (size:256b/32B) */
-struct hwrm_cfa_adv_flow_mgnt_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	unused_0[4];
-};
-
-/* hwrm_cfa_adv_flow_mgnt_qcaps_output (size:128b/16B) */
-struct hwrm_cfa_adv_flow_mgnt_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_HND_16BIT_SUPPORTED                     0x1UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_HND_64BIT_SUPPORTED                     0x2UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_BATCH_DELETE_SUPPORTED                  0x4UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_RESET_ALL_SUPPORTED                     0x8UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_DEST_FUNC_SUPPORTED              0x10UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_TX_EEM_FLOW_SUPPORTED                        0x20UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RX_EEM_FLOW_SUPPORTED                        0x40UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_COUNTER_ALLOC_SUPPORTED                 0x80UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_SUPPORTED                   0x100UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_UNTAGGED_VLAN_SUPPORTED                      0x200UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_XDP_SUPPORTED                                0x400UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_L2_HEADER_SOURCE_FIELDS_SUPPORTED            0x800UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_ARP_SUPPORTED                 0x1000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_V2_SUPPORTED                0x2000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_ETHERTYPE_IP_SUPPORTED        0x4000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_TRUFLOW_CAPABLE                              0x8000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_L2_FILTER_TRAFFIC_TYPE_L2_ROCE_SUPPORTED     0x10000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_LAG_SUPPORTED                                0x20000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_NO_L2CTX_SUPPORTED               0x40000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NIC_FLOW_STATS_SUPPORTED                     0x80000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_EXT_IP_PROTO_SUPPORTED        0x100000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_V3_SUPPORTED                0x200000UL
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_tunnel_dst_port_query_input (size:192b/24B) */
-struct hwrm_tunnel_dst_port_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	tunnel_type;
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN              0x1UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE             0x5UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4           0x9UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1           0xaUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE           0xbUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6       0xcUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_CUSTOM_GRE         0xdUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ECPRI              0xeUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_SRV6               0xfUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE          0x10UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GRE                0x11UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
-	u8	tunnel_next_proto;
-	u8	unused_0[6];
-};
-
-/* hwrm_tunnel_dst_port_query_output (size:128b/16B) */
-struct hwrm_tunnel_dst_port_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	tunnel_dst_port_id;
-	__be16	tunnel_dst_port_val;
-	u8	upar_in_use;
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR0     0x1UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR1     0x2UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR2     0x4UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR3     0x8UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR4     0x10UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR5     0x20UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR6     0x40UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR7     0x80UL
-	u8	status;
-	#define TUNNEL_DST_PORT_QUERY_RESP_STATUS_CHIP_LEVEL     0x1UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_STATUS_FUNC_LEVEL     0x2UL
-	u8	unused_0;
-	u8	valid;
-};
-
-/* hwrm_tunnel_dst_port_alloc_input (size:192b/24B) */
-struct hwrm_tunnel_dst_port_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	tunnel_type;
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN              0x1UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE             0x5UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4           0x9UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1           0xaUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE           0xbUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6       0xcUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_CUSTOM_GRE         0xdUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ECPRI              0xeUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_SRV6               0xfUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE          0x10UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GRE                0x11UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
-	u8	tunnel_next_proto;
-	__be16	tunnel_dst_port_val;
-	u8	unused_0[4];
-};
-
-/* hwrm_tunnel_dst_port_alloc_output (size:128b/16B) */
-struct hwrm_tunnel_dst_port_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	tunnel_dst_port_id;
-	u8	error_info;
-	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_SUCCESS         0x0UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ALLOCATED   0x1UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_NO_RESOURCE 0x2UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ENABLED     0x3UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_LAST           TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ENABLED
-	u8	upar_in_use;
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR0     0x1UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR1     0x2UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR2     0x4UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR3     0x8UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR4     0x10UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR5     0x20UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR6     0x40UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR7     0x80UL
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_tunnel_dst_port_free_input (size:192b/24B) */
-struct hwrm_tunnel_dst_port_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	tunnel_type;
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN              0x1UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE             0x5UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4           0x9UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1           0xaUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE           0xbUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6       0xcUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_CUSTOM_GRE         0xdUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ECPRI              0xeUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_SRV6               0xfUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE          0x10UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GRE                0x11UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
-	u8	tunnel_next_proto;
-	__le16	tunnel_dst_port_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_tunnel_dst_port_free_output (size:128b/16B) */
-struct hwrm_tunnel_dst_port_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	error_info;
-	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_SUCCESS           0x0UL
-	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_OWNER     0x1UL
-	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_ALLOCATED 0x2UL
-	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_LAST             TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_ALLOCATED
-	u8	unused_1[6];
-	u8	valid;
-};
-
-/* ctx_hw_stats (size:1280b/160B) */
-struct ctx_hw_stats {
-	__le64	rx_ucast_pkts;
-	__le64	rx_mcast_pkts;
-	__le64	rx_bcast_pkts;
-	__le64	rx_discard_pkts;
-	__le64	rx_error_pkts;
-	__le64	rx_ucast_bytes;
-	__le64	rx_mcast_bytes;
-	__le64	rx_bcast_bytes;
-	__le64	tx_ucast_pkts;
-	__le64	tx_mcast_pkts;
-	__le64	tx_bcast_pkts;
-	__le64	tx_error_pkts;
-	__le64	tx_discard_pkts;
-	__le64	tx_ucast_bytes;
-	__le64	tx_mcast_bytes;
-	__le64	tx_bcast_bytes;
-	__le64	tpa_pkts;
-	__le64	tpa_bytes;
-	__le64	tpa_events;
-	__le64	tpa_aborts;
-};
-
-/* ctx_hw_stats_ext (size:1408b/176B) */
-struct ctx_hw_stats_ext {
-	__le64	rx_ucast_pkts;
-	__le64	rx_mcast_pkts;
-	__le64	rx_bcast_pkts;
-	__le64	rx_discard_pkts;
-	__le64	rx_error_pkts;
-	__le64	rx_ucast_bytes;
-	__le64	rx_mcast_bytes;
-	__le64	rx_bcast_bytes;
-	__le64	tx_ucast_pkts;
-	__le64	tx_mcast_pkts;
-	__le64	tx_bcast_pkts;
-	__le64	tx_error_pkts;
-	__le64	tx_discard_pkts;
-	__le64	tx_ucast_bytes;
-	__le64	tx_mcast_bytes;
-	__le64	tx_bcast_bytes;
-	__le64	rx_tpa_eligible_pkt;
-	__le64	rx_tpa_eligible_bytes;
-	__le64	rx_tpa_pkt;
-	__le64	rx_tpa_bytes;
-	__le64	rx_tpa_errors;
-	__le64	rx_tpa_events;
-};
-
-/* hwrm_stat_ctx_alloc_input (size:384b/48B) */
-struct hwrm_stat_ctx_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	stats_dma_addr;
-	__le32	update_period_ms;
-	u8	stat_ctx_flags;
-	#define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE             0x1UL
-	#define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_DUP_HOST_BUF     0x2UL
-	u8	unused_0;
-	__le16	stats_dma_length;
-	__le16	flags;
-	#define STAT_CTX_ALLOC_REQ_FLAGS_STEERING_TAG_VALID     0x1UL
-	__le16	steering_tag;
-	__le32	stat_ctx_id;
-	__le16	alloc_seq_id;
-	u8	unused_1[6];
-};
-
-/* hwrm_stat_ctx_alloc_output (size:128b/16B) */
-struct hwrm_stat_ctx_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	stat_ctx_id;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_stat_ctx_free_input (size:192b/24B) */
-struct hwrm_stat_ctx_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	stat_ctx_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_stat_ctx_free_output (size:128b/16B) */
-struct hwrm_stat_ctx_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	stat_ctx_id;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_stat_ctx_query_input (size:192b/24B) */
-struct hwrm_stat_ctx_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	stat_ctx_id;
-	u8	flags;
-	#define STAT_CTX_QUERY_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0[3];
-};
-
-/* hwrm_stat_ctx_query_output (size:1408b/176B) */
-struct hwrm_stat_ctx_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	tx_ucast_pkts;
-	__le64	tx_mcast_pkts;
-	__le64	tx_bcast_pkts;
-	__le64	tx_discard_pkts;
-	__le64	tx_error_pkts;
-	__le64	tx_ucast_bytes;
-	__le64	tx_mcast_bytes;
-	__le64	tx_bcast_bytes;
-	__le64	rx_ucast_pkts;
-	__le64	rx_mcast_pkts;
-	__le64	rx_bcast_pkts;
-	__le64	rx_discard_pkts;
-	__le64	rx_error_pkts;
-	__le64	rx_ucast_bytes;
-	__le64	rx_mcast_bytes;
-	__le64	rx_bcast_bytes;
-	__le64	rx_agg_pkts;
-	__le64	rx_agg_bytes;
-	__le64	rx_agg_events;
-	__le64	rx_agg_aborts;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_stat_ext_ctx_query_input (size:192b/24B) */
-struct hwrm_stat_ext_ctx_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	stat_ctx_id;
-	u8	flags;
-	#define STAT_EXT_CTX_QUERY_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0[3];
-};
-
-/* hwrm_stat_ext_ctx_query_output (size:1536b/192B) */
-struct hwrm_stat_ext_ctx_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	rx_ucast_pkts;
-	__le64	rx_mcast_pkts;
-	__le64	rx_bcast_pkts;
-	__le64	rx_discard_pkts;
-	__le64	rx_error_pkts;
-	__le64	rx_ucast_bytes;
-	__le64	rx_mcast_bytes;
-	__le64	rx_bcast_bytes;
-	__le64	tx_ucast_pkts;
-	__le64	tx_mcast_pkts;
-	__le64	tx_bcast_pkts;
-	__le64	tx_error_pkts;
-	__le64	tx_discard_pkts;
-	__le64	tx_ucast_bytes;
-	__le64	tx_mcast_bytes;
-	__le64	tx_bcast_bytes;
-	__le64	rx_tpa_eligible_pkt;
-	__le64	rx_tpa_eligible_bytes;
-	__le64	rx_tpa_pkt;
-	__le64	rx_tpa_bytes;
-	__le64	rx_tpa_errors;
-	__le64	rx_tpa_events;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_stat_ctx_clr_stats_input (size:192b/24B) */
-struct hwrm_stat_ctx_clr_stats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	stat_ctx_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_stat_ctx_clr_stats_output (size:128b/16B) */
-struct hwrm_stat_ctx_clr_stats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_pcie_qstats_input (size:256b/32B) */
-struct hwrm_pcie_qstats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	pcie_stat_size;
-	u8	unused_0[6];
-	__le64	pcie_stat_host_addr;
-};
-
-/* hwrm_pcie_qstats_output (size:128b/16B) */
-struct hwrm_pcie_qstats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	pcie_stat_size;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* pcie_ctx_hw_stats (size:768b/96B) */
-struct pcie_ctx_hw_stats {
-	__le64	pcie_pl_signal_integrity;
-	__le64	pcie_dl_signal_integrity;
-	__le64	pcie_tl_signal_integrity;
-	__le64	pcie_link_integrity;
-	__le64	pcie_tx_traffic_rate;
-	__le64	pcie_rx_traffic_rate;
-	__le64	pcie_tx_dllp_statistics;
-	__le64	pcie_rx_dllp_statistics;
-	__le64	pcie_equalization_time;
-	__le32	pcie_ltssm_histogram[4];
-	__le64	pcie_recovery_histogram;
-};
-
-/* hwrm_stat_generic_qstats_input (size:256b/32B) */
-struct hwrm_stat_generic_qstats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	generic_stat_size;
-	u8	flags;
-	#define STAT_GENERIC_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0[5];
-	__le64	generic_stat_host_addr;
-};
-
-/* hwrm_stat_generic_qstats_output (size:128b/16B) */
-struct hwrm_stat_generic_qstats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	generic_stat_size;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* generic_sw_hw_stats (size:1472b/184B) */
-struct generic_sw_hw_stats {
-	__le64	pcie_statistics_tx_tlp;
-	__le64	pcie_statistics_rx_tlp;
-	__le64	pcie_credit_fc_hdr_posted;
-	__le64	pcie_credit_fc_hdr_nonposted;
-	__le64	pcie_credit_fc_hdr_cmpl;
-	__le64	pcie_credit_fc_data_posted;
-	__le64	pcie_credit_fc_data_nonposted;
-	__le64	pcie_credit_fc_data_cmpl;
-	__le64	pcie_credit_fc_tgt_nonposted;
-	__le64	pcie_credit_fc_tgt_data_posted;
-	__le64	pcie_credit_fc_tgt_hdr_posted;
-	__le64	pcie_credit_fc_cmpl_hdr_posted;
-	__le64	pcie_credit_fc_cmpl_data_posted;
-	__le64	pcie_cmpl_longest;
-	__le64	pcie_cmpl_shortest;
-	__le64	cache_miss_count_cfcq;
-	__le64	cache_miss_count_cfcs;
-	__le64	cache_miss_count_cfcc;
-	__le64	cache_miss_count_cfcm;
-	__le64	hw_db_recov_dbs_dropped;
-	__le64	hw_db_recov_drops_serviced;
-	__le64	hw_db_recov_dbs_recovered;
-	__le64	hw_db_recov_oo_drop_count;
-};
-
-/* hwrm_fw_reset_input (size:192b/24B) */
-struct hwrm_fw_reset_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	embedded_proc_type;
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_BOOT                  0x0UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_MGMT                  0x1UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_NETCTRL               0x2UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE                  0x3UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST                  0x4UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP                    0x5UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP                  0x6UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST_RESOURCE_REINIT  0x7UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_IMPACTLESS_ACTIVATION 0x8UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_LAST                 FW_RESET_REQ_EMBEDDED_PROC_TYPE_IMPACTLESS_ACTIVATION
-	u8	selfrst_status;
-	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTNONE      0x0UL
-	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP      0x1UL
-	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTPCIERST   0x2UL
-	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTIMMEDIATE 0x3UL
-	#define FW_RESET_REQ_SELFRST_STATUS_LAST            FW_RESET_REQ_SELFRST_STATUS_SELFRSTIMMEDIATE
-	u8	host_idx;
-	u8	flags;
-	#define FW_RESET_REQ_FLAGS_RESET_GRACEFUL     0x1UL
-	#define FW_RESET_REQ_FLAGS_FW_ACTIVATION      0x2UL
-	u8	unused_0[4];
-};
-
-/* hwrm_fw_reset_output (size:128b/16B) */
-struct hwrm_fw_reset_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	selfrst_status;
-	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTNONE      0x0UL
-	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTASAP      0x1UL
-	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTPCIERST   0x2UL
-	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTIMMEDIATE 0x3UL
-	#define FW_RESET_RESP_SELFRST_STATUS_LAST            FW_RESET_RESP_SELFRST_STATUS_SELFRSTIMMEDIATE
-	u8	unused_0[6];
-	u8	valid;
-};
-
-/* hwrm_fw_qstatus_input (size:192b/24B) */
-struct hwrm_fw_qstatus_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	embedded_proc_type;
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_BOOT    0x0UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_MGMT    0x1UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_NETCTRL 0x2UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_ROCE    0x3UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_HOST    0x4UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_AP      0x5UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_CHIP    0x6UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_LAST   FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_CHIP
-	u8	unused_0[7];
-};
-
-/* hwrm_fw_qstatus_output (size:128b/16B) */
-struct hwrm_fw_qstatus_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	selfrst_status;
-	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTNONE    0x0UL
-	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTASAP    0x1UL
-	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPCIERST 0x2UL
-	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPOWER   0x3UL
-	#define FW_QSTATUS_RESP_SELFRST_STATUS_LAST          FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPOWER
-	u8	nvm_option_action_status;
-	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_NONE     0x0UL
-	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_HOTRESET 0x1UL
-	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_WARMBOOT 0x2UL
-	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_COLDBOOT 0x3UL
-	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_LAST                  FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_COLDBOOT
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_fw_set_time_input (size:256b/32B) */
-struct hwrm_fw_set_time_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	year;
-	#define FW_SET_TIME_REQ_YEAR_UNKNOWN 0x0UL
-	#define FW_SET_TIME_REQ_YEAR_LAST   FW_SET_TIME_REQ_YEAR_UNKNOWN
-	u8	month;
-	u8	day;
-	u8	hour;
-	u8	minute;
-	u8	second;
-	u8	unused_0;
-	__le16	millisecond;
-	__le16	zone;
-	#define FW_SET_TIME_REQ_ZONE_UTC     0
-	#define FW_SET_TIME_REQ_ZONE_UNKNOWN 65535
-	#define FW_SET_TIME_REQ_ZONE_LAST   FW_SET_TIME_REQ_ZONE_UNKNOWN
-	u8	unused_1[4];
-};
-
-/* hwrm_fw_set_time_output (size:128b/16B) */
-struct hwrm_fw_set_time_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_struct_hdr (size:128b/16B) */
-struct hwrm_struct_hdr {
-	__le16	struct_id;
-	#define STRUCT_HDR_STRUCT_ID_LLDP_CFG              0x41bUL
-	#define STRUCT_HDR_STRUCT_ID_DCBX_ETS              0x41dUL
-	#define STRUCT_HDR_STRUCT_ID_DCBX_PFC              0x41fUL
-	#define STRUCT_HDR_STRUCT_ID_DCBX_APP              0x421UL
-	#define STRUCT_HDR_STRUCT_ID_DCBX_FEATURE_STATE    0x422UL
-	#define STRUCT_HDR_STRUCT_ID_LLDP_GENERIC          0x424UL
-	#define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE           0x426UL
-	#define STRUCT_HDR_STRUCT_ID_POWER_BKUP            0x427UL
-	#define STRUCT_HDR_STRUCT_ID_PEER_MMAP             0x429UL
-	#define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE            0x1UL
-	#define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION      0xaUL
-	#define STRUCT_HDR_STRUCT_ID_RSS_V2                0x64UL
-	#define STRUCT_HDR_STRUCT_ID_MSIX_PER_VF           0xc8UL
-	#define STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_COUNT 0x12cUL
-	#define STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_BOUND 0x12dUL
-	#define STRUCT_HDR_STRUCT_ID_LAST                 STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_BOUND
-	__le16	len;
-	u8	version;
-	u8	count;
-	__le16	subtype;
-	__le16	next_offset;
-	#define STRUCT_HDR_NEXT_OFFSET_LAST 0x0UL
-	u8	unused_0[6];
-};
-
-/* hwrm_struct_data_dcbx_app (size:64b/8B) */
-struct hwrm_struct_data_dcbx_app {
-	__be16	protocol_id;
-	u8	protocol_selector;
-	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_ETHER_TYPE   0x1UL
-	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_TCP_PORT     0x2UL
-	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_UDP_PORT     0x3UL
-	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_TCP_UDP_PORT 0x4UL
-	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_LAST        STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_TCP_UDP_PORT
-	u8	priority;
-	u8	valid;
-	u8	unused_0[3];
-};
-
-/* hwrm_fw_set_structured_data_input (size:256b/32B) */
-struct hwrm_fw_set_structured_data_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	src_data_addr;
-	__le16	data_len;
-	u8	hdr_cnt;
-	u8	unused_0[5];
-};
-
-/* hwrm_fw_set_structured_data_output (size:128b/16B) */
-struct hwrm_fw_set_structured_data_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_fw_set_structured_data_cmd_err (size:64b/8B) */
-struct hwrm_fw_set_structured_data_cmd_err {
-	u8	code;
-	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN     0x0UL
-	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_HDR_CNT 0x1UL
-	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_FMT     0x2UL
-	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID      0x3UL
-	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_LAST       FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID
-	u8	unused_0[7];
-};
-
-/* hwrm_fw_get_structured_data_input (size:256b/32B) */
-struct hwrm_fw_get_structured_data_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	dest_data_addr;
-	__le16	data_len;
-	__le16	structure_id;
-	__le16	subtype;
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_UNUSED                  0x0UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_ALL                     0xffffUL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_ADMIN       0x100UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_PEER        0x101UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_OPERATIONAL 0x102UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_ADMIN          0x200UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_PEER           0x201UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_OPERATIONAL    0x202UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_HOST_OPERATIONAL        0x300UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_LAST                   FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_HOST_OPERATIONAL
-	u8	count;
-	u8	unused_0;
-};
-
-/* hwrm_fw_get_structured_data_output (size:128b/16B) */
-struct hwrm_fw_get_structured_data_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	hdr_cnt;
-	u8	unused_0[6];
-	u8	valid;
-};
-
-/* hwrm_fw_get_structured_data_cmd_err (size:64b/8B) */
-struct hwrm_fw_get_structured_data_cmd_err {
-	u8	code;
-	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN 0x0UL
-	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID  0x3UL
-	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_LAST   FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID
-	u8	unused_0[7];
-};
-
-/* hwrm_fw_livepatch_query_input (size:192b/24B) */
-struct hwrm_fw_livepatch_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	fw_target;
-	#define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_COMMON_FW 0x1UL
-	#define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_SECURE_FW 0x2UL
-	#define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_LAST     FW_LIVEPATCH_QUERY_REQ_FW_TARGET_SECURE_FW
-	u8	unused_0[7];
-};
-
-/* hwrm_fw_livepatch_query_output (size:640b/80B) */
-struct hwrm_fw_livepatch_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	char	install_ver[32];
-	char	active_ver[32];
-	__le16	status_flags;
-	#define FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_INSTALL     0x1UL
-	#define FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_ACTIVE      0x2UL
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_fw_livepatch_input (size:256b/32B) */
-struct hwrm_fw_livepatch_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	opcode;
-	#define FW_LIVEPATCH_REQ_OPCODE_ACTIVATE   0x1UL
-	#define FW_LIVEPATCH_REQ_OPCODE_DEACTIVATE 0x2UL
-	#define FW_LIVEPATCH_REQ_OPCODE_LAST      FW_LIVEPATCH_REQ_OPCODE_DEACTIVATE
-	u8	fw_target;
-	#define FW_LIVEPATCH_REQ_FW_TARGET_COMMON_FW 0x1UL
-	#define FW_LIVEPATCH_REQ_FW_TARGET_SECURE_FW 0x2UL
-	#define FW_LIVEPATCH_REQ_FW_TARGET_LAST     FW_LIVEPATCH_REQ_FW_TARGET_SECURE_FW
-	u8	loadtype;
-	#define FW_LIVEPATCH_REQ_LOADTYPE_NVM_INSTALL   0x1UL
-	#define FW_LIVEPATCH_REQ_LOADTYPE_MEMORY_DIRECT 0x2UL
-	#define FW_LIVEPATCH_REQ_LOADTYPE_LAST         FW_LIVEPATCH_REQ_LOADTYPE_MEMORY_DIRECT
-	u8	flags;
-	__le32	patch_len;
-	__le64	host_addr;
-};
-
-/* hwrm_fw_livepatch_output (size:128b/16B) */
-struct hwrm_fw_livepatch_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_fw_livepatch_cmd_err (size:64b/8B) */
-struct hwrm_fw_livepatch_cmd_err {
-	u8	code;
-	#define FW_LIVEPATCH_CMD_ERR_CODE_UNKNOWN         0x0UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_OPCODE  0x1UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_TARGET  0x2UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_NOT_SUPPORTED   0x3UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_NOT_INSTALLED   0x4UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_NOT_PATCHED     0x5UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_AUTH_FAIL       0x6UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_HEADER  0x7UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_SIZE    0x8UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_ALREADY_PATCHED 0x9UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_LAST           FW_LIVEPATCH_CMD_ERR_CODE_ALREADY_PATCHED
-	u8	unused_0[7];
-};
-
-/* hwrm_exec_fwd_resp_input (size:1024b/128B) */
-struct hwrm_exec_fwd_resp_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	encap_request[26];
-	__le16	encap_resp_target_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_exec_fwd_resp_output (size:128b/16B) */
-struct hwrm_exec_fwd_resp_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_reject_fwd_resp_input (size:1024b/128B) */
-struct hwrm_reject_fwd_resp_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	encap_request[26];
-	__le16	encap_resp_target_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_reject_fwd_resp_output (size:128b/16B) */
-struct hwrm_reject_fwd_resp_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_fwd_resp_input (size:1024b/128B) */
-struct hwrm_fwd_resp_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	encap_resp_target_id;
-	__le16	encap_resp_cmpl_ring;
-	__le16	encap_resp_len;
-	u8	unused_0;
-	u8	unused_1;
-	__le64	encap_resp_addr;
-	__le32	encap_resp[24];
-};
-
-/* hwrm_fwd_resp_output (size:128b/16B) */
-struct hwrm_fwd_resp_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_fwd_async_event_cmpl_input (size:320b/40B) */
-struct hwrm_fwd_async_event_cmpl_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	encap_async_event_target_id;
-	u8	unused_0[6];
-	__le32	encap_async_event_cmpl[4];
-};
-
-/* hwrm_fwd_async_event_cmpl_output (size:128b/16B) */
-struct hwrm_fwd_async_event_cmpl_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_temp_monitor_query_input (size:128b/16B) */
-struct hwrm_temp_monitor_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_temp_monitor_query_output (size:192b/24B) */
-struct hwrm_temp_monitor_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	temp;
-	u8	phy_temp;
-	u8	om_temp;
-	u8	flags;
-	#define TEMP_MONITOR_QUERY_RESP_FLAGS_TEMP_NOT_AVAILABLE             0x1UL
-	#define TEMP_MONITOR_QUERY_RESP_FLAGS_PHY_TEMP_NOT_AVAILABLE         0x2UL
-	#define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_NOT_PRESENT                 0x4UL
-	#define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_TEMP_NOT_AVAILABLE          0x8UL
-	#define TEMP_MONITOR_QUERY_RESP_FLAGS_EXT_TEMP_FIELDS_AVAILABLE      0x10UL
-	#define TEMP_MONITOR_QUERY_RESP_FLAGS_THRESHOLD_VALUES_AVAILABLE     0x20UL
-	u8	temp2;
-	u8	phy_temp2;
-	u8	om_temp2;
-	u8	warn_threshold;
-	u8	critical_threshold;
-	u8	fatal_threshold;
-	u8	shutdown_threshold;
-	u8	unused_0[4];
-	u8	valid;
-};
-
-/* hwrm_wol_filter_alloc_input (size:512b/64B) */
-struct hwrm_wol_filter_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	__le32	enables;
-	#define WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS           0x1UL
-	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_OFFSET        0x2UL
-	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_SIZE      0x4UL
-	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_ADDR      0x8UL
-	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_ADDR     0x10UL
-	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_SIZE     0x20UL
-	__le16	port_id;
-	u8	wol_type;
-	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT 0x0UL
-	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_BMP      0x1UL
-	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_INVALID  0xffUL
-	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_LAST    WOL_FILTER_ALLOC_REQ_WOL_TYPE_INVALID
-	u8	unused_0[5];
-	u8	mac_address[6];
-	__le16	pattern_offset;
-	__le16	pattern_buf_size;
-	__le16	pattern_mask_size;
-	u8	unused_1[4];
-	__le64	pattern_buf_addr;
-	__le64	pattern_mask_addr;
-};
-
-/* hwrm_wol_filter_alloc_output (size:128b/16B) */
-struct hwrm_wol_filter_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	wol_filter_id;
-	u8	unused_0[6];
-	u8	valid;
-};
-
-/* hwrm_wol_filter_free_input (size:256b/32B) */
-struct hwrm_wol_filter_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define WOL_FILTER_FREE_REQ_FLAGS_FREE_ALL_WOL_FILTERS     0x1UL
-	__le32	enables;
-	#define WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID     0x1UL
-	__le16	port_id;
-	u8	wol_filter_id;
-	u8	unused_0[5];
-};
-
-/* hwrm_wol_filter_free_output (size:128b/16B) */
-struct hwrm_wol_filter_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_wol_filter_qcfg_input (size:448b/56B) */
-struct hwrm_wol_filter_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	__le16	handle;
-	u8	unused_0[4];
-	__le64	pattern_buf_addr;
-	__le16	pattern_buf_size;
-	u8	unused_1[6];
-	__le64	pattern_mask_addr;
-	__le16	pattern_mask_size;
-	u8	unused_2[6];
-};
-
-/* hwrm_wol_filter_qcfg_output (size:256b/32B) */
-struct hwrm_wol_filter_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	next_handle;
-	u8	wol_filter_id;
-	u8	wol_type;
-	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_MAGICPKT 0x0UL
-	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_BMP      0x1UL
-	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_INVALID  0xffUL
-	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_LAST    WOL_FILTER_QCFG_RESP_WOL_TYPE_INVALID
-	__le32	unused_0;
-	u8	mac_address[6];
-	__le16	pattern_offset;
-	__le16	pattern_size;
-	__le16	pattern_mask_size;
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_wol_reason_qcfg_input (size:320b/40B) */
-struct hwrm_wol_reason_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-	__le64	wol_pkt_buf_addr;
-	__le16	wol_pkt_buf_size;
-	u8	unused_1[6];
-};
-
-/* hwrm_wol_reason_qcfg_output (size:128b/16B) */
-struct hwrm_wol_reason_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	wol_filter_id;
-	u8	wol_reason;
-	#define WOL_REASON_QCFG_RESP_WOL_REASON_MAGICPKT 0x0UL
-	#define WOL_REASON_QCFG_RESP_WOL_REASON_BMP      0x1UL
-	#define WOL_REASON_QCFG_RESP_WOL_REASON_INVALID  0xffUL
-	#define WOL_REASON_QCFG_RESP_WOL_REASON_LAST    WOL_REASON_QCFG_RESP_WOL_REASON_INVALID
-	u8	wol_pkt_len;
-	u8	unused_0[4];
-	u8	valid;
-};
-
-/* hwrm_dbg_read_direct_input (size:256b/32B) */
-struct hwrm_dbg_read_direct_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_dest_addr;
-	__le32	read_addr;
-	__le32	read_len32;
-};
-
-/* hwrm_dbg_read_direct_output (size:128b/16B) */
-struct hwrm_dbg_read_direct_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	crc32;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_dbg_qcaps_input (size:192b/24B) */
-struct hwrm_dbg_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	unused_0[6];
-};
-
-/* hwrm_dbg_qcaps_output (size:192b/24B) */
-struct hwrm_dbg_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	fid;
-	u8	unused_0[2];
-	__le32	coredump_component_disable_caps;
-	#define DBG_QCAPS_RESP_COREDUMP_COMPONENT_DISABLE_CAPS_NVRAM     0x1UL
-	__le32	flags;
-	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_NVM             0x1UL
-	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR        0x2UL
-	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR         0x4UL
-	#define DBG_QCAPS_RESP_FLAGS_USEQ                      0x8UL
-	#define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_DDR         0x10UL
-	#define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_CAPTURE     0x20UL
-	#define DBG_QCAPS_RESP_FLAGS_PTRACE                    0x40UL
-	#define DBG_QCAPS_RESP_FLAGS_REG_ACCESS_RESTRICTED     0x80UL
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_dbg_qcfg_input (size:192b/24B) */
-struct hwrm_dbg_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	__le16	flags;
-	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_MASK         0x3UL
-	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_SFT          0
-	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_NVM       0x0UL
-	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_HOST_DDR  0x1UL
-	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR   0x2UL
-	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_LAST          DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR
-	__le32	coredump_component_disable_flags;
-	#define DBG_QCFG_REQ_COREDUMP_COMPONENT_DISABLE_FLAGS_NVRAM     0x1UL
-};
-
-/* hwrm_dbg_qcfg_output (size:256b/32B) */
-struct hwrm_dbg_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	fid;
-	u8	unused_0[2];
-	__le32	coredump_size;
-	__le32	flags;
-	#define DBG_QCFG_RESP_FLAGS_UART_LOG               0x1UL
-	#define DBG_QCFG_RESP_FLAGS_UART_LOG_SECONDARY     0x2UL
-	#define DBG_QCFG_RESP_FLAGS_FW_TRACE               0x4UL
-	#define DBG_QCFG_RESP_FLAGS_FW_TRACE_SECONDARY     0x8UL
-	#define DBG_QCFG_RESP_FLAGS_DEBUG_NOTIFY           0x10UL
-	#define DBG_QCFG_RESP_FLAGS_JTAG_DEBUG             0x20UL
-	__le16	async_cmpl_ring;
-	u8	unused_2[2];
-	__le32	crashdump_size;
-	u8	unused_3[3];
-	u8	valid;
-};
-
-/* hwrm_dbg_crashdump_medium_cfg_input (size:320b/40B) */
-struct hwrm_dbg_crashdump_medium_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	output_dest_flags;
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_TYPE_DDR     0x1UL
-	__le16	pg_size_lvl;
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_MASK      0x3UL
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_SFT       0
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_0       0x0UL
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_1       0x1UL
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2       0x2UL
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LAST       DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_MASK  0x1cUL
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_SFT   2
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_4K   (0x0UL << 2)
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8K   (0x1UL << 2)
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_64K  (0x2UL << 2)
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_2M   (0x3UL << 2)
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8M   (0x4UL << 2)
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G   (0x5UL << 2)
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_LAST   DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_MASK 0xffe0UL
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_SFT  5
-	__le32	size;
-	__le32	coredump_component_disable_flags;
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_NVRAM     0x1UL
-	__le32	unused_0;
-	__le64	pbl;
-};
-
-/* hwrm_dbg_crashdump_medium_cfg_output (size:128b/16B) */
-struct hwrm_dbg_crashdump_medium_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_1[7];
-	u8	valid;
-};
-
-/* coredump_segment_record (size:128b/16B) */
-struct coredump_segment_record {
-	__le16	component_id;
-	__le16	segment_id;
-	__le16	max_instances;
-	u8	version_hi;
-	u8	version_low;
-	u8	seg_flags;
-	u8	compress_flags;
-	#define SFLAG_COMPRESSED_ZLIB     0x1UL
-	u8	unused_0[2];
-	__le32	segment_len;
-};
-
-/* hwrm_dbg_coredump_list_input (size:256b/32B) */
-struct hwrm_dbg_coredump_list_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_dest_addr;
-	__le32	host_buf_len;
-	__le16	seq_no;
-	u8	flags;
-	#define DBG_COREDUMP_LIST_REQ_FLAGS_CRASHDUMP     0x1UL
-	u8	unused_0[1];
-};
-
-/* hwrm_dbg_coredump_list_output (size:128b/16B) */
-struct hwrm_dbg_coredump_list_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define DBG_COREDUMP_LIST_RESP_FLAGS_MORE     0x1UL
-	u8	unused_0;
-	__le16	total_segments;
-	__le16	data_len;
-	u8	unused_1;
-	u8	valid;
-};
-
-/* hwrm_dbg_coredump_initiate_input (size:256b/32B) */
-struct hwrm_dbg_coredump_initiate_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	component_id;
-	__le16	segment_id;
-	__le16	instance;
-	__le16	unused_0;
-	u8	seg_flags;
-	#define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_LIVE_DATA                0x1UL
-	#define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_CRASH_DATA               0x2UL
-	#define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_COLLECT_CTX_L1_CACHE     0x4UL
-	u8	unused_1[7];
-};
-
-/* hwrm_dbg_coredump_initiate_output (size:128b/16B) */
-struct hwrm_dbg_coredump_initiate_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* coredump_data_hdr (size:128b/16B) */
-struct coredump_data_hdr {
-	__le32	address;
-	__le32	flags_length;
-	#define COREDUMP_DATA_HDR_FLAGS_LENGTH_ACTUAL_LEN_MASK     0xffffffUL
-	#define COREDUMP_DATA_HDR_FLAGS_LENGTH_ACTUAL_LEN_SFT      0
-	#define COREDUMP_DATA_HDR_FLAGS_LENGTH_INDIRECT_ACCESS     0x1000000UL
-	__le32	instance;
-	__le32	next_offset;
-};
-
-/* hwrm_dbg_coredump_retrieve_input (size:448b/56B) */
-struct hwrm_dbg_coredump_retrieve_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_dest_addr;
-	__le32	host_buf_len;
-	__le32	unused_0;
-	__le16	component_id;
-	__le16	segment_id;
-	__le16	instance;
-	__le16	unused_1;
-	u8	seg_flags;
-	u8	unused_2;
-	__le16	unused_3;
-	__le32	unused_4;
-	__le32	seq_no;
-	__le32	unused_5;
-};
-
-/* hwrm_dbg_coredump_retrieve_output (size:128b/16B) */
-struct hwrm_dbg_coredump_retrieve_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define DBG_COREDUMP_RETRIEVE_RESP_FLAGS_MORE     0x1UL
-	u8	unused_0;
-	__le16	data_len;
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_dbg_ring_info_get_input (size:192b/24B) */
-struct hwrm_dbg_ring_info_get_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	ring_type;
-	#define DBG_RING_INFO_GET_REQ_RING_TYPE_L2_CMPL 0x0UL
-	#define DBG_RING_INFO_GET_REQ_RING_TYPE_TX      0x1UL
-	#define DBG_RING_INFO_GET_REQ_RING_TYPE_RX      0x2UL
-	#define DBG_RING_INFO_GET_REQ_RING_TYPE_NQ      0x3UL
-	#define DBG_RING_INFO_GET_REQ_RING_TYPE_LAST   DBG_RING_INFO_GET_REQ_RING_TYPE_NQ
-	u8	unused_0[3];
-	__le32	fw_ring_id;
-};
-
-/* hwrm_dbg_ring_info_get_output (size:192b/24B) */
-struct hwrm_dbg_ring_info_get_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	producer_index;
-	__le32	consumer_index;
-	__le32	cag_vector_ctrl;
-	__le16	st_tag;
-	u8	unused_0;
-	u8	valid;
-};
-
-/* hwrm_dbg_log_buffer_flush_input (size:192b/24B) */
-struct hwrm_dbg_log_buffer_flush_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	type;
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_SRT_TRACE           0x0UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_SRT2_TRACE          0x1UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CRT_TRACE           0x2UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CRT2_TRACE          0x3UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_RIGP0_TRACE         0x4UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_L2_HWRM_TRACE       0x5UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ROCE_HWRM_TRACE     0x6UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA0_TRACE           0x7UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA1_TRACE           0x8UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA2_TRACE           0x9UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_RIGP1_TRACE         0xaUL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_AFM_KONG_HWRM_TRACE 0xbUL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_LAST               DBG_LOG_BUFFER_FLUSH_REQ_TYPE_AFM_KONG_HWRM_TRACE
-	u8	unused_1[2];
-	__le32	flags;
-	#define DBG_LOG_BUFFER_FLUSH_REQ_FLAGS_FLUSH_ALL_BUFFERS     0x1UL
-};
-
-/* hwrm_dbg_log_buffer_flush_output (size:128b/16B) */
-struct hwrm_dbg_log_buffer_flush_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	current_buffer_offset;
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_nvm_read_input (size:320b/40B) */
-struct hwrm_nvm_read_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_dest_addr;
-	__le16	dir_idx;
-	u8	unused_0[2];
-	__le32	offset;
-	__le32	len;
-	u8	unused_1[4];
-};
-
-/* hwrm_nvm_read_output (size:128b/16B) */
-struct hwrm_nvm_read_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_get_dir_entries_input (size:192b/24B) */
-struct hwrm_nvm_get_dir_entries_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_dest_addr;
-};
-
-/* hwrm_nvm_get_dir_entries_output (size:128b/16B) */
-struct hwrm_nvm_get_dir_entries_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_get_dir_info_input (size:128b/16B) */
-struct hwrm_nvm_get_dir_info_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_nvm_get_dir_info_output (size:192b/24B) */
-struct hwrm_nvm_get_dir_info_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	entries;
-	__le32	entry_length;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_write_input (size:448b/56B) */
-struct hwrm_nvm_write_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_src_addr;
-	__le16	dir_type;
-	__le16	dir_ordinal;
-	__le16	dir_ext;
-	__le16	dir_attr;
-	__le32	dir_data_length;
-	__le16	option;
-	__le16	flags;
-	#define NVM_WRITE_REQ_FLAGS_KEEP_ORIG_ACTIVE_IMG     0x1UL
-	#define NVM_WRITE_REQ_FLAGS_BATCH_MODE               0x2UL
-	#define NVM_WRITE_REQ_FLAGS_BATCH_LAST               0x4UL
-	#define NVM_WRITE_REQ_FLAGS_SKIP_CRID_CHECK          0x8UL
-	__le32	dir_item_length;
-	__le32	offset;
-	__le32	len;
-	__le32	unused_0;
-};
-
-/* hwrm_nvm_write_output (size:128b/16B) */
-struct hwrm_nvm_write_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	dir_item_length;
-	__le16	dir_idx;
-	u8	unused_0;
-	u8	valid;
-};
-
-/* hwrm_nvm_write_cmd_err (size:64b/8B) */
-struct hwrm_nvm_write_cmd_err {
-	u8	code;
-	#define NVM_WRITE_CMD_ERR_CODE_UNKNOWN  0x0UL
-	#define NVM_WRITE_CMD_ERR_CODE_FRAG_ERR 0x1UL
-	#define NVM_WRITE_CMD_ERR_CODE_NO_SPACE 0x2UL
-	#define NVM_WRITE_CMD_ERR_CODE_LAST    NVM_WRITE_CMD_ERR_CODE_NO_SPACE
-	u8	unused_0[7];
-};
-
-/* hwrm_nvm_modify_input (size:320b/40B) */
-struct hwrm_nvm_modify_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_src_addr;
-	__le16	dir_idx;
-	__le16	flags;
-	#define NVM_MODIFY_REQ_FLAGS_BATCH_MODE     0x1UL
-	#define NVM_MODIFY_REQ_FLAGS_BATCH_LAST     0x2UL
-	__le32	offset;
-	__le32	len;
-	u8	unused_1[4];
-};
-
-/* hwrm_nvm_modify_output (size:128b/16B) */
-struct hwrm_nvm_modify_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_find_dir_entry_input (size:256b/32B) */
-struct hwrm_nvm_find_dir_entry_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define NVM_FIND_DIR_ENTRY_REQ_ENABLES_DIR_IDX_VALID     0x1UL
-	__le16	dir_idx;
-	__le16	dir_type;
-	__le16	dir_ordinal;
-	__le16	dir_ext;
-	u8	opt_ordinal;
-	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_MASK 0x3UL
-	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_SFT 0
-	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_EQ    0x0UL
-	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_GE    0x1UL
-	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_GT    0x2UL
-	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_LAST NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_GT
-	u8	unused_0[3];
-};
-
-/* hwrm_nvm_find_dir_entry_output (size:256b/32B) */
-struct hwrm_nvm_find_dir_entry_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	dir_item_length;
-	__le32	dir_data_length;
-	__le32	fw_ver;
-	__le16	dir_ordinal;
-	__le16	dir_idx;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_erase_dir_entry_input (size:192b/24B) */
-struct hwrm_nvm_erase_dir_entry_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	dir_idx;
-	u8	unused_0[6];
-};
-
-/* hwrm_nvm_erase_dir_entry_output (size:128b/16B) */
-struct hwrm_nvm_erase_dir_entry_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_get_dev_info_input (size:192b/24B) */
-struct hwrm_nvm_get_dev_info_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	flags;
-	#define NVM_GET_DEV_INFO_REQ_FLAGS_SECURITY_SOC_NVM     0x1UL
-	u8	unused_0[7];
-};
-
-/* hwrm_nvm_get_dev_info_output (size:768b/96B) */
-struct hwrm_nvm_get_dev_info_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	manufacturer_id;
-	__le16	device_id;
-	__le32	sector_size;
-	__le32	nvram_size;
-	__le32	reserved_size;
-	__le32	available_size;
-	u8	nvm_cfg_ver_maj;
-	u8	nvm_cfg_ver_min;
-	u8	nvm_cfg_ver_upd;
-	u8	flags;
-	#define NVM_GET_DEV_INFO_RESP_FLAGS_FW_VER_VALID     0x1UL
-	char	pkg_name[16];
-	__le16	hwrm_fw_major;
-	__le16	hwrm_fw_minor;
-	__le16	hwrm_fw_build;
-	__le16	hwrm_fw_patch;
-	__le16	mgmt_fw_major;
-	__le16	mgmt_fw_minor;
-	__le16	mgmt_fw_build;
-	__le16	mgmt_fw_patch;
-	__le16	roce_fw_major;
-	__le16	roce_fw_minor;
-	__le16	roce_fw_build;
-	__le16	roce_fw_patch;
-	__le16	netctrl_fw_major;
-	__le16	netctrl_fw_minor;
-	__le16	netctrl_fw_build;
-	__le16	netctrl_fw_patch;
-	__le16	srt2_fw_major;
-	__le16	srt2_fw_minor;
-	__le16	srt2_fw_build;
-	__le16	srt2_fw_patch;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_mod_dir_entry_input (size:256b/32B) */
-struct hwrm_nvm_mod_dir_entry_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define NVM_MOD_DIR_ENTRY_REQ_ENABLES_CHECKSUM     0x1UL
-	__le16	dir_idx;
-	__le16	dir_ordinal;
-	__le16	dir_ext;
-	__le16	dir_attr;
-	__le32	checksum;
-};
-
-/* hwrm_nvm_mod_dir_entry_output (size:128b/16B) */
-struct hwrm_nvm_mod_dir_entry_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_verify_update_input (size:192b/24B) */
-struct hwrm_nvm_verify_update_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	dir_type;
-	__le16	dir_ordinal;
-	__le16	dir_ext;
-	u8	unused_0[2];
-};
-
-/* hwrm_nvm_verify_update_output (size:128b/16B) */
-struct hwrm_nvm_verify_update_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_install_update_input (size:192b/24B) */
-struct hwrm_nvm_install_update_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	install_type;
-	#define NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_NORMAL 0x0UL
-	#define NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_ALL    0xffffffffUL
-	#define NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_LAST  NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_ALL
-	__le16	flags;
-	#define NVM_INSTALL_UPDATE_REQ_FLAGS_ERASE_UNUSED_SPACE     0x1UL
-	#define NVM_INSTALL_UPDATE_REQ_FLAGS_REMOVE_UNUSED_PKG      0x2UL
-	#define NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG      0x4UL
-	#define NVM_INSTALL_UPDATE_REQ_FLAGS_VERIFY_ONLY            0x8UL
-	u8	unused_0[2];
-};
-
-/* hwrm_nvm_install_update_output (size:192b/24B) */
-struct hwrm_nvm_install_update_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	installed_items;
-	u8	result;
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_SUCCESS                      0x0UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_FAILURE                      0xffUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_MALLOC_FAILURE               0xfdUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_INDEX_PARAMETER      0xfbUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TYPE_PARAMETER       0xf3UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PREREQUISITE         0xf2UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_FILE_HEADER          0xecUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_SIGNATURE            0xebUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_STREAM          0xeaUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_LENGTH          0xe9UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_MANIFEST             0xe8UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TRAILER              0xe7UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_CHECKSUM             0xe6UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_ITEM_CHECKSUM        0xe5UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DATA_LENGTH          0xe4UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DIRECTIVE            0xe1UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_CHIP_REV         0xceUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_DEVICE_ID        0xcdUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_VENDOR    0xccUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_ID        0xcbUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_PLATFORM         0xc5UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_DUPLICATE_ITEM               0xc4UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_ZERO_LENGTH_ITEM             0xc3UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_CHECKSUM_ERROR       0xb9UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_DATA_ERROR           0xb8UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_AUTHENTICATION_ERROR 0xb7UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_NOT_FOUND               0xb0UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED                  0xa7UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_LAST                        NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED
-	u8	problem_item;
-	#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_NONE    0x0UL
-	#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_PACKAGE 0xffUL
-	#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_LAST   NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_PACKAGE
-	u8	reset_required;
-	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_NONE  0x0UL
-	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_PCI   0x1UL
-	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_POWER 0x2UL
-	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_LAST NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_POWER
-	u8	unused_0[4];
-	u8	valid;
-};
-
-/* hwrm_nvm_install_update_cmd_err (size:64b/8B) */
-struct hwrm_nvm_install_update_cmd_err {
-	u8	code;
-	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_UNKNOWN            0x0UL
-	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR           0x1UL
-	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_SPACE           0x2UL
-	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_ANTI_ROLLBACK      0x3UL
-	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_VOLTREG_SUPPORT 0x4UL
-	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_LAST              NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_VOLTREG_SUPPORT
-	u8	unused_0[7];
-};
-
-/* hwrm_nvm_get_variable_input (size:320b/40B) */
-struct hwrm_nvm_get_variable_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	dest_data_addr;
-	__le16	data_len;
-	__le16	option_num;
-	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_0    0x0UL
-	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF 0xffffUL
-	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_LAST     NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF
-	__le16	dimensions;
-	__le16	index_0;
-	__le16	index_1;
-	__le16	index_2;
-	__le16	index_3;
-	u8	flags;
-	#define NVM_GET_VARIABLE_REQ_FLAGS_FACTORY_DFLT     0x1UL
-	u8	unused_0;
-};
-
-/* hwrm_nvm_get_variable_output (size:128b/16B) */
-struct hwrm_nvm_get_variable_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	data_len;
-	__le16	option_num;
-	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_0    0x0UL
-	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_FFFF 0xffffUL
-	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_LAST     NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_FFFF
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_nvm_get_variable_cmd_err (size:64b/8B) */
-struct hwrm_nvm_get_variable_cmd_err {
-	u8	code;
-	#define NVM_GET_VARIABLE_CMD_ERR_CODE_UNKNOWN       0x0UL
-	#define NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST 0x1UL
-	#define NVM_GET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR   0x2UL
-	#define NVM_GET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT 0x3UL
-	#define NVM_GET_VARIABLE_CMD_ERR_CODE_LAST         NVM_GET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT
-	u8	unused_0[7];
-};
-
-/* hwrm_nvm_set_variable_input (size:320b/40B) */
-struct hwrm_nvm_set_variable_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	src_data_addr;
-	__le16	data_len;
-	__le16	option_num;
-	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_0    0x0UL
-	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF 0xffffUL
-	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_LAST     NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF
-	__le16	dimensions;
-	__le16	index_0;
-	__le16	index_1;
-	__le16	index_2;
-	__le16	index_3;
-	u8	flags;
-	#define NVM_SET_VARIABLE_REQ_FLAGS_FORCE_FLUSH                0x1UL
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_MASK          0xeUL
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_SFT           1
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_NONE            (0x0UL << 1)
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1       (0x1UL << 1)
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_AES256          (0x2UL << 1)
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH  (0x3UL << 1)
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST           NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH
-	#define NVM_SET_VARIABLE_REQ_FLAGS_FLAGS_UNUSED_0_MASK        0x70UL
-	#define NVM_SET_VARIABLE_REQ_FLAGS_FLAGS_UNUSED_0_SFT         4
-	#define NVM_SET_VARIABLE_REQ_FLAGS_FACTORY_DEFAULT            0x80UL
-	u8	unused_0;
-};
-
-/* hwrm_nvm_set_variable_output (size:128b/16B) */
-struct hwrm_nvm_set_variable_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_set_variable_cmd_err (size:64b/8B) */
-struct hwrm_nvm_set_variable_cmd_err {
-	u8	code;
-	#define NVM_SET_VARIABLE_CMD_ERR_CODE_UNKNOWN       0x0UL
-	#define NVM_SET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST 0x1UL
-	#define NVM_SET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR   0x2UL
-	#define NVM_SET_VARIABLE_CMD_ERR_CODE_LAST         NVM_SET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR
-	u8	unused_0[7];
-};
-
-/* hwrm_selftest_qlist_input (size:128b/16B) */
-struct hwrm_selftest_qlist_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_selftest_qlist_output (size:2240b/280B) */
-struct hwrm_selftest_qlist_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	num_tests;
-	u8	available_tests;
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_NVM_TEST                 0x1UL
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_LINK_TEST                0x2UL
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_REGISTER_TEST            0x4UL
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_MEMORY_TEST              0x8UL
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_PCIE_SERDES_TEST         0x10UL
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_ETHERNET_SERDES_TEST     0x20UL
-	u8	offline_tests;
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_NVM_TEST                 0x1UL
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_LINK_TEST                0x2UL
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_REGISTER_TEST            0x4UL
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_MEMORY_TEST              0x8UL
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_PCIE_SERDES_TEST         0x10UL
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_ETHERNET_SERDES_TEST     0x20UL
-	u8	unused_0;
-	__le16	test_timeout;
-	u8	unused_1[2];
-	char	test_name[8][32];
-	u8	eyescope_target_BER_support;
-	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E8_SUPPORTED  0x0UL
-	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E9_SUPPORTED  0x1UL
-	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E10_SUPPORTED 0x2UL
-	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E11_SUPPORTED 0x3UL
-	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E12_SUPPORTED 0x4UL
-	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_LAST              SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E12_SUPPORTED
-	u8	unused_2[6];
-	u8	valid;
-};
-
-/* hwrm_selftest_exec_input (size:192b/24B) */
-struct hwrm_selftest_exec_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	flags;
-	#define SELFTEST_EXEC_REQ_FLAGS_NVM_TEST                 0x1UL
-	#define SELFTEST_EXEC_REQ_FLAGS_LINK_TEST                0x2UL
-	#define SELFTEST_EXEC_REQ_FLAGS_REGISTER_TEST            0x4UL
-	#define SELFTEST_EXEC_REQ_FLAGS_MEMORY_TEST              0x8UL
-	#define SELFTEST_EXEC_REQ_FLAGS_PCIE_SERDES_TEST         0x10UL
-	#define SELFTEST_EXEC_REQ_FLAGS_ETHERNET_SERDES_TEST     0x20UL
-	u8	unused_0[7];
-};
-
-/* hwrm_selftest_exec_output (size:128b/16B) */
-struct hwrm_selftest_exec_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	requested_tests;
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_NVM_TEST                 0x1UL
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_LINK_TEST                0x2UL
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_REGISTER_TEST            0x4UL
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_MEMORY_TEST              0x8UL
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_PCIE_SERDES_TEST         0x10UL
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_ETHERNET_SERDES_TEST     0x20UL
-	u8	test_success;
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_NVM_TEST                 0x1UL
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_LINK_TEST                0x2UL
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_REGISTER_TEST            0x4UL
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_MEMORY_TEST              0x8UL
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_PCIE_SERDES_TEST         0x10UL
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_ETHERNET_SERDES_TEST     0x20UL
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_selftest_irq_input (size:128b/16B) */
-struct hwrm_selftest_irq_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_selftest_irq_output (size:128b/16B) */
-struct hwrm_selftest_irq_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* dbc_dbc (size:64b/8B) */
-struct dbc_dbc {
-	__le32	index;
-	#define DBC_DBC_INDEX_MASK 0xffffffUL
-	#define DBC_DBC_INDEX_SFT  0
-	#define DBC_DBC_EPOCH      0x1000000UL
-	#define DBC_DBC_TOGGLE_MASK 0x6000000UL
-	#define DBC_DBC_TOGGLE_SFT 25
-	__le32	type_path_xid;
-	#define DBC_DBC_XID_MASK          0xfffffUL
-	#define DBC_DBC_XID_SFT           0
-	#define DBC_DBC_PATH_MASK         0x3000000UL
-	#define DBC_DBC_PATH_SFT          24
-	#define DBC_DBC_PATH_ROCE           (0x0UL << 24)
-	#define DBC_DBC_PATH_L2             (0x1UL << 24)
-	#define DBC_DBC_PATH_ENGINE         (0x2UL << 24)
-	#define DBC_DBC_PATH_LAST          DBC_DBC_PATH_ENGINE
-	#define DBC_DBC_VALID             0x4000000UL
-	#define DBC_DBC_DEBUG_TRACE       0x8000000UL
-	#define DBC_DBC_TYPE_MASK         0xf0000000UL
-	#define DBC_DBC_TYPE_SFT          28
-	#define DBC_DBC_TYPE_SQ             (0x0UL << 28)
-	#define DBC_DBC_TYPE_RQ             (0x1UL << 28)
-	#define DBC_DBC_TYPE_SRQ            (0x2UL << 28)
-	#define DBC_DBC_TYPE_SRQ_ARM        (0x3UL << 28)
-	#define DBC_DBC_TYPE_CQ             (0x4UL << 28)
-	#define DBC_DBC_TYPE_CQ_ARMSE       (0x5UL << 28)
-	#define DBC_DBC_TYPE_CQ_ARMALL      (0x6UL << 28)
-	#define DBC_DBC_TYPE_CQ_ARMENA      (0x7UL << 28)
-	#define DBC_DBC_TYPE_SRQ_ARMENA     (0x8UL << 28)
-	#define DBC_DBC_TYPE_CQ_CUTOFF_ACK  (0x9UL << 28)
-	#define DBC_DBC_TYPE_NQ             (0xaUL << 28)
-	#define DBC_DBC_TYPE_NQ_ARM         (0xbUL << 28)
-	#define DBC_DBC_TYPE_NQ_MASK        (0xeUL << 28)
-	#define DBC_DBC_TYPE_NULL           (0xfUL << 28)
-	#define DBC_DBC_TYPE_LAST          DBC_DBC_TYPE_NULL
-};
-
-/* db_push_start (size:64b/8B) */
-struct db_push_start {
-	u64	db;
-	#define DB_PUSH_START_DB_INDEX_MASK     0xffffffUL
-	#define DB_PUSH_START_DB_INDEX_SFT      0
-	#define DB_PUSH_START_DB_PI_LO_MASK     0xff000000UL
-	#define DB_PUSH_START_DB_PI_LO_SFT      24
-	#define DB_PUSH_START_DB_XID_MASK       0xfffff00000000ULL
-	#define DB_PUSH_START_DB_XID_SFT        32
-	#define DB_PUSH_START_DB_PI_HI_MASK     0xf0000000000000ULL
-	#define DB_PUSH_START_DB_PI_HI_SFT      52
-	#define DB_PUSH_START_DB_TYPE_MASK      0xf000000000000000ULL
-	#define DB_PUSH_START_DB_TYPE_SFT       60
-	#define DB_PUSH_START_DB_TYPE_PUSH_START  (0xcULL << 60)
-	#define DB_PUSH_START_DB_TYPE_PUSH_END    (0xdULL << 60)
-	#define DB_PUSH_START_DB_TYPE_LAST       DB_PUSH_START_DB_TYPE_PUSH_END
-};
-
-/* db_push_end (size:64b/8B) */
-struct db_push_end {
-	u64	db;
-	#define DB_PUSH_END_DB_INDEX_MASK      0xffffffUL
-	#define DB_PUSH_END_DB_INDEX_SFT       0
-	#define DB_PUSH_END_DB_PI_LO_MASK      0xff000000UL
-	#define DB_PUSH_END_DB_PI_LO_SFT       24
-	#define DB_PUSH_END_DB_XID_MASK        0xfffff00000000ULL
-	#define DB_PUSH_END_DB_XID_SFT         32
-	#define DB_PUSH_END_DB_PI_HI_MASK      0xf0000000000000ULL
-	#define DB_PUSH_END_DB_PI_HI_SFT       52
-	#define DB_PUSH_END_DB_PATH_MASK       0x300000000000000ULL
-	#define DB_PUSH_END_DB_PATH_SFT        56
-	#define DB_PUSH_END_DB_PATH_ROCE         (0x0ULL << 56)
-	#define DB_PUSH_END_DB_PATH_L2           (0x1ULL << 56)
-	#define DB_PUSH_END_DB_PATH_ENGINE       (0x2ULL << 56)
-	#define DB_PUSH_END_DB_PATH_LAST        DB_PUSH_END_DB_PATH_ENGINE
-	#define DB_PUSH_END_DB_DEBUG_TRACE     0x800000000000000ULL
-	#define DB_PUSH_END_DB_TYPE_MASK       0xf000000000000000ULL
-	#define DB_PUSH_END_DB_TYPE_SFT        60
-	#define DB_PUSH_END_DB_TYPE_PUSH_START   (0xcULL << 60)
-	#define DB_PUSH_END_DB_TYPE_PUSH_END     (0xdULL << 60)
-	#define DB_PUSH_END_DB_TYPE_LAST        DB_PUSH_END_DB_TYPE_PUSH_END
-};
-
-/* db_push_info (size:64b/8B) */
-struct db_push_info {
-	u32	push_size_push_index;
-	#define DB_PUSH_INFO_PUSH_INDEX_MASK 0xffffffUL
-	#define DB_PUSH_INFO_PUSH_INDEX_SFT 0
-	#define DB_PUSH_INFO_PUSH_SIZE_MASK 0x1f000000UL
-	#define DB_PUSH_INFO_PUSH_SIZE_SFT  24
-	u32	reserved32;
-};
-
-/* fw_status_reg (size:32b/4B) */
-struct fw_status_reg {
-	u32	fw_status;
-	#define FW_STATUS_REG_CODE_MASK              0xffffUL
-	#define FW_STATUS_REG_CODE_SFT               0
-	#define FW_STATUS_REG_CODE_READY               0x8000UL
-	#define FW_STATUS_REG_CODE_LAST               FW_STATUS_REG_CODE_READY
-	#define FW_STATUS_REG_IMAGE_DEGRADED         0x10000UL
-	#define FW_STATUS_REG_RECOVERABLE            0x20000UL
-	#define FW_STATUS_REG_CRASHDUMP_ONGOING      0x40000UL
-	#define FW_STATUS_REG_CRASHDUMP_COMPLETE     0x80000UL
-	#define FW_STATUS_REG_SHUTDOWN               0x100000UL
-	#define FW_STATUS_REG_CRASHED_NO_MASTER      0x200000UL
-	#define FW_STATUS_REG_RECOVERING             0x400000UL
-	#define FW_STATUS_REG_MANU_DEBUG_STATUS      0x800000UL
-};
-
-/* hcomm_status (size:64b/8B) */
-struct hcomm_status {
-	u32	sig_ver;
-	#define HCOMM_STATUS_VER_MASK      0xffUL
-	#define HCOMM_STATUS_VER_SFT       0
-	#define HCOMM_STATUS_VER_LATEST      0x1UL
-	#define HCOMM_STATUS_VER_LAST       HCOMM_STATUS_VER_LATEST
-	#define HCOMM_STATUS_SIGNATURE_MASK 0xffffff00UL
-	#define HCOMM_STATUS_SIGNATURE_SFT 8
-	#define HCOMM_STATUS_SIGNATURE_VAL   (0x484353UL << 8)
-	#define HCOMM_STATUS_SIGNATURE_LAST HCOMM_STATUS_SIGNATURE_VAL
-	u32	fw_status_loc;
-	#define HCOMM_STATUS_TRUE_ADDR_SPACE_MASK    0x3UL
-	#define HCOMM_STATUS_TRUE_ADDR_SPACE_SFT     0
-	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_GRC       0x1UL
-	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR0      0x2UL
-	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR1      0x3UL
-	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_LAST     HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR1
-	#define HCOMM_STATUS_TRUE_OFFSET_MASK        0xfffffffcUL
-	#define HCOMM_STATUS_TRUE_OFFSET_SFT         2
-};
-#define HCOMM_STATUS_STRUCT_LOC 0x31001F0UL
-
-#endif /* _BNXT_HSI_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.c
index 669d24ba0e87..de3427c6c6aa 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.c
@@ -12,8 +12,8 @@
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/pci.h>
+#include <linux/bnxt/hsi.h>
 
-#include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_hwmon.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
index d2fd2d04ed47..5ce190f50120 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
@@ -20,8 +20,8 @@
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include <linux/skbuff.h>
+#include <linux/bnxt/hsi.h>
 
-#include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
index 15ca51b5d204..791b3a0cdb83 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
@@ -10,7 +10,7 @@
 #ifndef BNXT_HWRM_H
 #define BNXT_HWRM_H
 
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 
 enum bnxt_hwrm_ctx_flags {
 	/* Update the HWRM_API_FLAGS right below for any new non-internal bit added here */
@@ -58,7 +58,7 @@ void hwrm_update_token(struct bnxt *bp, u16 seq, enum bnxt_hwrm_wait_state s);
 
 #define BNXT_HWRM_MAX_REQ_LEN		(bp->hwrm_max_req_len)
 #define BNXT_HWRM_SHORT_REQ_LEN		sizeof(struct hwrm_short_input)
-#define HWRM_CMD_MAX_TIMEOUT		40000U
+#define HWRM_CMD_MAX_TIMEOUT		60000U
 #define SHORT_HWRM_CMD_TIMEOUT		20
 #define HWRM_CMD_TIMEOUT		(bp->hwrm_cmd_timeout)
 #define HWRM_RESET_TIMEOUT		((HWRM_CMD_TIMEOUT) * 4)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 2d4e19b96ee7..a8a74f07bb54 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -15,7 +15,7 @@
 #include <linux/timekeeping.h>
 #include <linux/ptp_classify.h>
 #include <linux/clocksource.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ptp.h"
@@ -560,10 +560,11 @@ static int bnxt_hwrm_ptp_cfg(struct bnxt *bp)
 	return bnxt_ptp_cfg_tstamp_filters(bp);
 }
 
-int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
+int bnxt_hwtstamp_set(struct net_device *dev,
+		      struct kernel_hwtstamp_config *stmpconf,
+		      struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	struct hwtstamp_config stmpconf;
 	struct bnxt_ptp_cfg *ptp;
 	u16 old_rxctl;
 	int old_rx_filter, rc;
@@ -573,17 +574,14 @@ int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	if (!ptp)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&stmpconf, ifr->ifr_data, sizeof(stmpconf)))
-		return -EFAULT;
-
-	if (stmpconf.tx_type != HWTSTAMP_TX_ON &&
-	    stmpconf.tx_type != HWTSTAMP_TX_OFF)
+	if (stmpconf->tx_type != HWTSTAMP_TX_ON &&
+	    stmpconf->tx_type != HWTSTAMP_TX_OFF)
 		return -ERANGE;
 
 	old_rx_filter = ptp->rx_filter;
 	old_rxctl = ptp->rxctl;
 	old_tx_tstamp_en = ptp->tx_tstamp_en;
-	switch (stmpconf.rx_filter) {
+	switch (stmpconf->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		ptp->rxctl = 0;
 		ptp->rx_filter = HWTSTAMP_FILTER_NONE;
@@ -616,7 +614,7 @@ int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	if (stmpconf.tx_type == HWTSTAMP_TX_ON)
+	if (stmpconf->tx_type == HWTSTAMP_TX_ON)
 		ptp->tx_tstamp_en = 1;
 	else
 		ptp->tx_tstamp_en = 0;
@@ -625,9 +623,8 @@ int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	if (rc)
 		goto ts_set_err;
 
-	stmpconf.rx_filter = ptp->rx_filter;
-	return copy_to_user(ifr->ifr_data, &stmpconf, sizeof(stmpconf)) ?
-		-EFAULT : 0;
+	stmpconf->rx_filter = ptp->rx_filter;
+	return 0;
 
 ts_set_err:
 	ptp->rx_filter = old_rx_filter;
@@ -636,22 +633,22 @@ ts_set_err:
 	return rc;
 }
 
-int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
+int bnxt_hwtstamp_get(struct net_device *dev,
+		      struct kernel_hwtstamp_config *stmpconf)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	struct hwtstamp_config stmpconf;
 	struct bnxt_ptp_cfg *ptp;
 
 	ptp = bp->ptp_cfg;
 	if (!ptp)
 		return -EOPNOTSUPP;
 
-	stmpconf.flags = 0;
-	stmpconf.tx_type = ptp->tx_tstamp_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	stmpconf->flags = 0;
+	stmpconf->tx_type = ptp->tx_tstamp_en ? HWTSTAMP_TX_ON
+					      : HWTSTAMP_TX_OFF;
 
-	stmpconf.rx_filter = ptp->rx_filter;
-	return copy_to_user(ifr->ifr_data, &stmpconf, sizeof(stmpconf)) ?
-		-EFAULT : 0;
+	stmpconf->rx_filter = ptp->rx_filter;
+	return 0;
 }
 
 static int bnxt_map_regs(struct bnxt *bp, u32 *reg_arr, int count, int reg_win)
@@ -702,7 +699,7 @@ static void bnxt_unmap_ptp_regs(struct bnxt *bp)
 		  (BNXT_PTP_GRC_WIN - 1) * 4);
 }
 
-static u64 bnxt_cc_read(const struct cyclecounter *cc)
+static u64 bnxt_cc_read(struct cyclecounter *cc)
 {
 	struct bnxt_ptp_cfg *ptp = container_of(cc, struct bnxt_ptp_cfg, cc);
 	u64 ns = 0;
@@ -794,6 +791,27 @@ next_slot:
 	return HZ;
 }
 
+void bnxt_ptp_free_txts_skbs(struct bnxt_ptp_cfg *ptp)
+{
+	struct bnxt_ptp_tx_req *txts_req;
+	u16 cons = ptp->txts_cons;
+
+	/* make sure ptp aux worker finished with
+	 * possible BNXT_STATE_OPEN set
+	 */
+	ptp_cancel_worker_sync(ptp->ptp_clock);
+
+	ptp->tx_avail = BNXT_MAX_TX_TS;
+	while (cons != ptp->txts_prod) {
+		txts_req = &ptp->txts_req[cons];
+		if (!IS_ERR_OR_NULL(txts_req->tx_skb))
+			dev_kfree_skb_any(txts_req->tx_skb);
+		cons = NEXT_TXTS(cons);
+	}
+	ptp->txts_cons = cons;
+	ptp_schedule_worker(ptp->ptp_clock, 0);
+}
+
 int bnxt_ptp_get_txts_prod(struct bnxt_ptp_cfg *ptp, u16 *prod)
 {
 	spin_lock_bh(&ptp->ptp_tx_lock);
@@ -934,7 +952,6 @@ static int bnxt_ptp_pps_init(struct bnxt *bp)
 		snprintf(ptp_info->pin_config[i].name,
 			 sizeof(ptp_info->pin_config[i].name), "bnxt_pps%d", i);
 		ptp_info->pin_config[i].index = i;
-		ptp_info->pin_config[i].chan = i;
 		if (*pin_usg == BNXT_PPS_PIN_PPS_IN)
 			ptp_info->pin_config[i].func = PTP_PF_EXTTS;
 		else if (*pin_usg == BNXT_PPS_PIN_PPS_OUT)
@@ -951,6 +968,8 @@ static int bnxt_ptp_pps_init(struct bnxt *bp)
 	ptp_info->n_per_out = 1;
 	ptp_info->pps = 1;
 	ptp_info->verify = bnxt_ptp_verify;
+	ptp_info->supported_extts_flags = PTP_RISING_EDGE | PTP_STRICT_FLAGS;
+	ptp_info->supported_perout_flags = PTP_PEROUT_DUTY_CYCLE;
 
 	return 0;
 }
@@ -1033,9 +1052,9 @@ static void bnxt_ptp_free(struct bnxt *bp)
 	if (ptp->ptp_clock) {
 		ptp_clock_unregister(ptp->ptp_clock);
 		ptp->ptp_clock = NULL;
-		kfree(ptp->ptp_info.pin_config);
-		ptp->ptp_info.pin_config = NULL;
 	}
+	kfree(ptp->ptp_info.pin_config);
+	ptp->ptp_info.pin_config = NULL;
 }
 
 int bnxt_ptp_init(struct bnxt *bp)
@@ -1105,7 +1124,6 @@ out:
 void bnxt_ptp_clear(struct bnxt *bp)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
-	int i;
 
 	if (!ptp)
 		return;
@@ -1117,12 +1135,5 @@ void bnxt_ptp_clear(struct bnxt *bp)
 	kfree(ptp->ptp_info.pin_config);
 	ptp->ptp_info.pin_config = NULL;
 
-	for (i = 0; i < BNXT_MAX_TX_TS; i++) {
-		if (ptp->txts_req[i].tx_skb) {
-			dev_kfree_skb_any(ptp->txts_req[i].tx_skb);
-			ptp->txts_req[i].tx_skb = NULL;
-		}
-	}
-
 	bnxt_unmap_ptp_regs(bp);
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index a95f05e9c579..8cc2fae47644 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -160,8 +160,12 @@ void bnxt_ptp_update_current_time(struct bnxt *bp);
 void bnxt_ptp_pps_event(struct bnxt *bp, u32 data1, u32 data2);
 int bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp);
 void bnxt_ptp_reapply_pps(struct bnxt *bp);
-int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr);
-int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr);
+int bnxt_hwtstamp_set(struct net_device *dev,
+		      struct kernel_hwtstamp_config *stmpconf,
+		      struct netlink_ext_ack *extack);
+int bnxt_hwtstamp_get(struct net_device *dev,
+		      struct kernel_hwtstamp_config *stmpconf);
+void bnxt_ptp_free_txts_skbs(struct bnxt_ptp_cfg *ptp);
 int bnxt_ptp_get_txts_prod(struct bnxt_ptp_cfg *ptp, u16 *prod);
 void bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb, u16 prod);
 int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 12b6ed51fd88..be7deb9cc410 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -16,7 +16,7 @@
 #include <linux/interrupt.h>
 #include <linux/etherdevice.h>
 #include <net/dcbnl.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ulp.h"
@@ -332,6 +332,38 @@ int bnxt_set_vf_bw(struct net_device *dev, int vf_id, int min_tx_rate,
 	return rc;
 }
 
+static int bnxt_set_vf_link_admin_state(struct bnxt *bp, int vf_id)
+{
+	struct hwrm_func_cfg_input *req;
+	struct bnxt_vf_info *vf;
+	int rc;
+
+	if (!(bp->fw_cap & BNXT_FW_CAP_LINK_ADMIN))
+		return 0;
+
+	vf = &bp->pf.vf[vf_id];
+
+	rc = bnxt_hwrm_func_cfg_short_req_init(bp, &req);
+	if (rc)
+		return rc;
+
+	req->fid = cpu_to_le16(vf->fw_fid);
+	switch (vf->flags & (BNXT_VF_LINK_FORCED | BNXT_VF_LINK_UP)) {
+	case BNXT_VF_LINK_FORCED:
+		req->options =
+			FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN;
+		break;
+	case (BNXT_VF_LINK_FORCED | BNXT_VF_LINK_UP):
+		req->options = FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_UP;
+		break;
+	default:
+		req->options = FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO;
+		break;
+	}
+	req->enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_ADMIN_LINK_STATE);
+	return hwrm_req_send(bp, req);
+}
+
 int bnxt_set_vf_link_state(struct net_device *dev, int vf_id, int link)
 {
 	struct bnxt *bp = netdev_priv(dev);
@@ -357,10 +389,11 @@ int bnxt_set_vf_link_state(struct net_device *dev, int vf_id, int link)
 		break;
 	default:
 		netdev_err(bp->dev, "Invalid link option\n");
-		rc = -EINVAL;
-		break;
+		return -EINVAL;
 	}
-	if (vf->flags & (BNXT_VF_LINK_UP | BNXT_VF_LINK_FORCED))
+	if (bp->fw_cap & BNXT_FW_CAP_LINK_ADMIN)
+		rc = bnxt_set_vf_link_admin_state(bp, vf_id);
+	else if (vf->flags & (BNXT_VF_LINK_UP | BNXT_VF_LINK_FORCED))
 		rc = bnxt_hwrm_fwd_async_event_cmpl(bp, vf,
 			ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE);
 	return rc;
@@ -541,6 +574,13 @@ static void bnxt_hwrm_roce_sriov_cfg(struct bnxt *bp, int num_vfs)
 	if (rc)
 		goto err;
 
+	/* In case of VF Dynamic resource allocation, driver will provision
+	 * maximum resources to all the VFs. FW will dynamically allocate
+	 * resources to VFs on the fly, so always divide the resources by 1.
+	 */
+	if (BNXT_ROCE_VF_DYN_ALLOC_CAP(bp))
+		num_vfs = 1;
+
 	cfg_req->fid = cpu_to_le16(0xffff);
 	cfg_req->enables2 =
 		cpu_to_le32(FUNC_CFG_REQ_ENABLES2_ROCE_MAX_AV_PER_VF |
@@ -659,15 +699,21 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 
 	hwrm_req_hold(bp, req);
 	for (i = 0; i < num_vfs; i++) {
+		struct bnxt_vf_info *vf = &pf->vf[i];
+
+		vf->fw_fid = pf->first_vf_id + i;
+		rc = bnxt_set_vf_link_admin_state(bp, i);
+		if (rc)
+			break;
+
 		if (reset)
 			__bnxt_set_vf_params(bp, i);
 
-		req->vf_id = cpu_to_le16(pf->first_vf_id + i);
+		req->vf_id = cpu_to_le16(vf->fw_fid);
 		rc = hwrm_req_send(bp, req);
 		if (rc)
 			break;
 		pf->active_vfs = i + 1;
-		pf->vf[i].fw_fid = pf->first_vf_id + i;
 	}
 
 	if (pf->active_vfs) {
@@ -734,7 +780,13 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 				   FUNC_CFG_REQ_ENABLES_NUM_VNICS |
 				   FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS);
 
-	mtu = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
+	if (bp->fw_cap & BNXT_FW_CAP_LINK_ADMIN) {
+		req->options = FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO;
+		req->enables |=
+			cpu_to_le32(FUNC_CFG_REQ_ENABLES_ADMIN_LINK_STATE);
+	}
+
+	mtu = bp->dev->mtu + VLAN_ETH_HLEN;
 	req->mru = cpu_to_le16(mtu);
 	req->admin_mtu = cpu_to_le16(mtu);
 
@@ -823,7 +875,7 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs)
 	int tx_ok = 0, rx_ok = 0, rss_ok = 0;
 	int avail_cp, avail_stat;
 
-	/* Check if we can enable requested num of vf's. At a mininum
+	/* Check if we can enable requested num of vf's. At a minimum
 	 * we require 1 RX 1 TX rings for each VF. In this minimum conf
 	 * features like TPA will not be available.
 	 */
@@ -919,7 +971,7 @@ err_out1:
 	return rc;
 }
 
-void bnxt_sriov_disable(struct bnxt *bp)
+void __bnxt_sriov_disable(struct bnxt *bp)
 {
 	u16 num_vfs = pci_num_vf(bp->pdev);
 
@@ -943,10 +995,20 @@ void bnxt_sriov_disable(struct bnxt *bp)
 	devl_unlock(bp->dl);
 
 	bnxt_free_vf_resources(bp);
+}
+
+static void bnxt_sriov_disable(struct bnxt *bp)
+{
+	if (!pci_num_vf(bp->pdev))
+		return;
+
+	__bnxt_sriov_disable(bp);
 
 	/* Reclaim all resources for the PF. */
 	rtnl_lock();
+	netdev_lock(bp->dev);
 	bnxt_restore_pf_fw_resources(bp);
+	netdev_unlock(bp->dev);
 	rtnl_unlock();
 }
 
@@ -956,17 +1018,21 @@ int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	struct bnxt *bp = netdev_priv(dev);
 
 	rtnl_lock();
+	netdev_lock(dev);
 	if (!netif_running(dev)) {
 		netdev_warn(dev, "Reject SRIOV config request since if is down!\n");
+		netdev_unlock(dev);
 		rtnl_unlock();
 		return 0;
 	}
 	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		netdev_warn(dev, "Reject SRIOV config request when FW reset is in progress\n");
+		netdev_unlock(dev);
 		rtnl_unlock();
 		return 0;
 	}
 	bp->sriov_cfg = true;
+	netdev_unlock(dev);
 	rtnl_unlock();
 
 	if (pci_vfs_assigned(bp->pdev)) {
@@ -1119,7 +1185,7 @@ static int bnxt_vf_validate_set_mac(struct bnxt *bp, struct bnxt_vf_info *vf)
 		/* There are two cases:
 		 * 1.If firmware spec < 0x10202,VF MAC address is not forwarded
 		 *   to the PF and so it doesn't have to match
-		 * 2.Allow VF to modify it's own MAC when PF has not assigned a
+		 * 2.Allow VF to modify its own MAC when PF has not assigned a
 		 *   valid MAC address and firmware spec >= 0x10202
 		 */
 		mac_ok = true;
@@ -1315,7 +1381,7 @@ int bnxt_cfg_hw_sriov(struct bnxt *bp, int *num_vfs, bool reset)
 	return 0;
 }
 
-void bnxt_sriov_disable(struct bnxt *bp)
+void __bnxt_sriov_disable(struct bnxt *bp)
 {
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
index 9a4bacba477b..e4979d729312 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
@@ -38,7 +38,7 @@ bool bnxt_is_trusted_vf(struct bnxt *bp, struct bnxt_vf_info *vf);
 int bnxt_set_vf_trust(struct net_device *dev, int vf_id, bool trust);
 int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs);
 int bnxt_cfg_hw_sriov(struct bnxt *bp, int *num_vfs, bool reset);
-void bnxt_sriov_disable(struct bnxt *);
+void __bnxt_sriov_disable(struct bnxt *bp);
 void bnxt_hwrm_exec_fwd_req(struct bnxt *);
 void bnxt_update_vf_mac(struct bnxt *);
 int bnxt_approve_mac(struct bnxt *, const u8 *, bool);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index d2ca90407cce..2d66bf59cd64 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -19,8 +19,8 @@
 #include <net/tc_act/tc_pedit.h>
 #include <net/tc_act/tc_tunnel_key.h>
 #include <net/vxlan.h>
+#include <linux/bnxt/hsi.h>
 
-#include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_sriov.h"
@@ -244,7 +244,7 @@ bnxt_tc_parse_pedit(struct bnxt *bp, struct bnxt_tc_actions *actions,
 			   offset < offset_of_ip6_daddr + 16) {
 			actions->nat.src_xlate = false;
 			idx = (offset - offset_of_ip6_daddr) / 4;
-			actions->nat.l3.ipv6.saddr.s6_addr32[idx] = htonl(val);
+			actions->nat.l3.ipv6.daddr.s6_addr32[idx] = htonl(val);
 		} else {
 			netdev_err(bp->dev,
 				   "%s: IPv6_hdr: Invalid pedit field\n",
@@ -1316,7 +1316,7 @@ static int bnxt_tc_get_decap_handle(struct bnxt *bp, struct bnxt_tc_flow *flow,
 
 	/* Check if there's another flow using the same tunnel decap.
 	 * If not, add this tunnel to the table and resolve the other
-	 * tunnel header fileds. Ignore src_port in the tunnel_key,
+	 * tunnel header fields. Ignore src_port in the tunnel_key,
 	 * since it is not required for decap filters.
 	 */
 	decap_key->tp_src = 0;
@@ -1410,7 +1410,7 @@ static int bnxt_tc_get_encap_handle(struct bnxt *bp, struct bnxt_tc_flow *flow,
 
 	/* Check if there's another flow using the same tunnel encap.
 	 * If not, add this tunnel to the table and resolve the other
-	 * tunnel header fileds
+	 * tunnel header fields
 	 */
 	encap_node = bnxt_tc_get_tunnel_node(bp, &tc_info->encap_table,
 					     &tc_info->encap_ht_params,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 94c6a0928ca0..927971c362f1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -20,8 +20,9 @@
 #include <asm/byteorder.h>
 #include <linux/bitmap.h>
 #include <linux/auxiliary_bus.h>
+#include <net/netdev_lock.h>
+#include <linux/bnxt/hsi.h>
 
-#include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ulp.h"
@@ -99,6 +100,12 @@ void bnxt_set_dflt_ulp_stat_ctxs(struct bnxt *bp)
 		if (BNXT_PF(bp) && !bp->pf.port_id &&
 		    bp->port_count > 1)
 			bp->edev->ulp_num_ctxs++;
+
+		/* Reserve one additional stat_ctx when the device is capable
+		 * of supporting port mirroring on RDMA device.
+		 */
+		if (BNXT_MIRROR_ON_ROCE_CAP(bp))
+			bp->edev->ulp_num_ctxs++;
 	}
 }
 
@@ -112,7 +119,7 @@ int bnxt_register_dev(struct bnxt_en_dev *edev,
 	struct bnxt_ulp *ulp;
 	int rc = 0;
 
-	rtnl_lock();
+	netdev_lock(dev);
 	mutex_lock(&edev->en_dev_lock);
 	if (!bp->irq_tbl) {
 		rc = -ENODEV;
@@ -135,10 +142,9 @@ int bnxt_register_dev(struct bnxt_en_dev *edev,
 	edev->ulp_tbl->msix_requested = bnxt_get_ulp_msix_num(bp);
 
 	bnxt_fill_msix_vecs(bp, bp->edev->msix_entries);
-	edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED;
 exit:
 	mutex_unlock(&edev->en_dev_lock);
-	rtnl_unlock();
+	netdev_unlock(dev);
 	return rc;
 }
 EXPORT_SYMBOL(bnxt_register_dev);
@@ -148,13 +154,10 @@ void bnxt_unregister_dev(struct bnxt_en_dev *edev)
 	struct net_device *dev = edev->net;
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_ulp *ulp;
-	int i = 0;
 
 	ulp = edev->ulp_tbl;
-	rtnl_lock();
+	netdev_lock(dev);
 	mutex_lock(&edev->en_dev_lock);
-	if (ulp->msix_requested)
-		edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED;
 	edev->ulp_tbl->msix_requested = 0;
 
 	if (ulp->max_async_event_id)
@@ -164,12 +167,8 @@ void bnxt_unregister_dev(struct bnxt_en_dev *edev)
 	synchronize_rcu();
 	ulp->max_async_event_id = 0;
 	ulp->async_events_bmap = NULL;
-	while (atomic_read(&ulp->ref_count) != 0 && i < 10) {
-		msleep(100);
-		i++;
-	}
 	mutex_unlock(&edev->en_dev_lock);
-	rtnl_unlock();
+	netdev_unlock(dev);
 	return;
 }
 EXPORT_SYMBOL(bnxt_unregister_dev);
@@ -208,7 +207,7 @@ int bnxt_send_msg(struct bnxt_en_dev *edev,
 
 	rc = hwrm_req_replace(bp, req, fw_msg->msg, fw_msg->msg_len);
 	if (rc)
-		return rc;
+		goto drop_req;
 
 	hwrm_req_timeout(bp, req, fw_msg->timeout);
 	resp = hwrm_req_hold(bp, req);
@@ -220,6 +219,7 @@ int bnxt_send_msg(struct bnxt_en_dev *edev,
 
 		memcpy(fw_msg->resp, resp, resp_len);
 	}
+drop_req:
 	hwrm_req_drop(bp, req);
 	return rc;
 }
@@ -234,10 +234,9 @@ void bnxt_ulp_stop(struct bnxt *bp)
 		return;
 
 	mutex_lock(&edev->en_dev_lock);
-	if (!bnxt_ulp_registered(edev)) {
-		mutex_unlock(&edev->en_dev_lock);
-		return;
-	}
+	if (!bnxt_ulp_registered(edev) ||
+	    (edev->flags & BNXT_EN_FLAG_ULP_STOPPED))
+		goto ulp_stop_exit;
 
 	edev->flags |= BNXT_EN_FLAG_ULP_STOPPED;
 	if (aux_priv) {
@@ -253,6 +252,7 @@ void bnxt_ulp_stop(struct bnxt *bp)
 			adrv->suspend(adev, pm);
 		}
 	}
+ulp_stop_exit:
 	mutex_unlock(&edev->en_dev_lock);
 }
 
@@ -261,19 +261,13 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
 	struct bnxt_aux_priv *aux_priv = bp->aux_priv;
 	struct bnxt_en_dev *edev = bp->edev;
 
-	if (!edev)
-		return;
-
-	edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED;
-
-	if (err)
+	if (!edev || err)
 		return;
 
 	mutex_lock(&edev->en_dev_lock);
-	if (!bnxt_ulp_registered(edev)) {
-		mutex_unlock(&edev->en_dev_lock);
-		return;
-	}
+	if (!bnxt_ulp_registered(edev) ||
+	    !(edev->flags & BNXT_EN_FLAG_ULP_STOPPED))
+		goto ulp_start_exit;
 
 	if (edev->ulp_tbl->msix_requested)
 		bnxt_fill_msix_vecs(bp, edev->msix_entries);
@@ -290,6 +284,8 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
 			adrv->resume(adev);
 		}
 	}
+ulp_start_exit:
+	edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED;
 	mutex_unlock(&edev->en_dev_lock);
 }
 
@@ -297,8 +293,9 @@ void bnxt_ulp_irq_stop(struct bnxt *bp)
 {
 	struct bnxt_en_dev *edev = bp->edev;
 	struct bnxt_ulp_ops *ops;
+	bool reset = false;
 
-	if (!edev || !(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED))
+	if (!edev)
 		return;
 
 	if (bnxt_ulp_registered(bp->edev)) {
@@ -307,10 +304,12 @@ void bnxt_ulp_irq_stop(struct bnxt *bp)
 		if (!ulp->msix_requested)
 			return;
 
-		ops = rtnl_dereference(ulp->ulp_ops);
+		ops = netdev_lock_dereference(ulp->ulp_ops, bp->dev);
 		if (!ops || !ops->ulp_irq_stop)
 			return;
-		ops->ulp_irq_stop(ulp->handle);
+		if (test_bit(BNXT_STATE_FW_RESET_DET, &bp->state))
+			reset = true;
+		ops->ulp_irq_stop(ulp->handle, reset);
 	}
 }
 
@@ -319,7 +318,7 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err)
 	struct bnxt_en_dev *edev = bp->edev;
 	struct bnxt_ulp_ops *ops;
 
-	if (!edev || !(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED))
+	if (!edev)
 		return;
 
 	if (bnxt_ulp_registered(bp->edev)) {
@@ -329,7 +328,7 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err)
 		if (!ulp->msix_requested)
 			return;
 
-		ops = rtnl_dereference(ulp->ulp_ops);
+		ops = netdev_lock_dereference(ulp->ulp_ops, bp->dev);
 		if (!ops || !ops->ulp_irq_restart)
 			return;
 
@@ -345,9 +344,36 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err)
 	}
 }
 
-int bnxt_register_async_events(struct bnxt_en_dev *edev,
-			       unsigned long *events_bmap,
-			       u16 max_id)
+void bnxt_ulp_async_events(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl)
+{
+	u16 event_id = le16_to_cpu(cmpl->event_id);
+	struct bnxt_en_dev *edev = bp->edev;
+	struct bnxt_ulp_ops *ops;
+	struct bnxt_ulp *ulp;
+
+	if (!bnxt_ulp_registered(edev))
+		return;
+	ulp = edev->ulp_tbl;
+
+	rcu_read_lock();
+
+	ops = rcu_dereference(ulp->ulp_ops);
+	if (!ops || !ops->ulp_async_notifier)
+		goto exit_unlock_rcu;
+	if (!ulp->async_events_bmap || event_id > ulp->max_async_event_id)
+		goto exit_unlock_rcu;
+
+	/* Read max_async_event_id first before testing the bitmap. */
+	smp_rmb();
+
+	if (test_bit(event_id, ulp->async_events_bmap))
+		ops->ulp_async_notifier(ulp->handle, cmpl);
+exit_unlock_rcu:
+	rcu_read_unlock();
+}
+
+void bnxt_register_async_events(struct bnxt_en_dev *edev,
+				unsigned long *events_bmap, u16 max_id)
 {
 	struct net_device *dev = edev->net;
 	struct bnxt *bp = netdev_priv(dev);
@@ -359,7 +385,6 @@ int bnxt_register_async_events(struct bnxt_en_dev *edev,
 	smp_wmb();
 	ulp->max_async_event_id = max_id;
 	bnxt_hwrm_func_drv_rgtr(bp, events_bmap, max_id + 1, true);
-	return 0;
 }
 EXPORT_SYMBOL(bnxt_register_async_events);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index 54ad9f8273d7..3c5b8a53f715 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -10,9 +10,6 @@
 #ifndef BNXT_ULP_H
 #define BNXT_ULP_H
 
-#define BNXT_ROCE_ULP	0
-#define BNXT_MAX_ULP	1
-
 #define BNXT_MIN_ROCE_CP_RINGS	2
 #define BNXT_MIN_ROCE_STAT_CTXS	1
 
@@ -30,7 +27,9 @@ struct bnxt_msix_entry {
 };
 
 struct bnxt_ulp_ops {
-	void (*ulp_irq_stop)(void *);
+	/* async_notifier() cannot sleep (in BH context) */
+	void (*ulp_async_notifier)(void *, struct hwrm_async_event_cmpl *);
+	void (*ulp_irq_stop)(void *, bool);
 	void (*ulp_irq_restart)(void *, struct bnxt_msix_entry *);
 };
 
@@ -48,7 +47,6 @@ struct bnxt_ulp {
 	unsigned long	*async_events_bmap;
 	u16		max_async_event_id;
 	u16		msix_requested;
-	atomic_t	ref_count;
 };
 
 struct bnxt_en_dev {
@@ -60,7 +58,6 @@ struct bnxt_en_dev {
 	#define BNXT_EN_FLAG_ROCEV2_CAP		0x2
 	#define BNXT_EN_FLAG_ROCE_CAP		(BNXT_EN_FLAG_ROCEV1_CAP | \
 						 BNXT_EN_FLAG_ROCEV2_CAP)
-	#define BNXT_EN_FLAG_MSIX_REQUESTED	0x4
 	#define BNXT_EN_FLAG_ULP_STOPPED	0x8
 	#define BNXT_EN_FLAG_VF			0x10
 #define BNXT_EN_VF(edev)	((edev)->flags & BNXT_EN_FLAG_VF)
@@ -126,6 +123,6 @@ int bnxt_register_dev(struct bnxt_en_dev *edev, struct bnxt_ulp_ops *ulp_ops,
 		      void *handle);
 void bnxt_unregister_dev(struct bnxt_en_dev *edev);
 int bnxt_send_msg(struct bnxt_en_dev *edev, struct bnxt_fw_msg *fw_msg);
-int bnxt_register_async_events(struct bnxt_en_dev *edev,
-			       unsigned long *events_bmap, u16 max_id);
+void bnxt_register_async_events(struct bnxt_en_dev *edev,
+				unsigned long *events_bmap, u16 max_id);
 #endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index 1467b94a6427..bd116fd578d8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -12,8 +12,8 @@
 #include <linux/rtnetlink.h>
 #include <linux/jhash.h>
 #include <net/pkt_cls.h>
+#include <linux/bnxt/hsi.h>
 
-#include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_vfr.h"
@@ -257,8 +257,7 @@ bool bnxt_dev_is_vf_rep(struct net_device *dev)
 
 /* Called when the parent PF interface is closed:
  * As the mode transition from SWITCHDEV to LEGACY
- * happens under the rtnl_lock() this routine is safe
- * under the rtnl_lock()
+ * happens under the netdev instance lock this routine is safe
  */
 void bnxt_vf_reps_close(struct bnxt *bp)
 {
@@ -278,8 +277,7 @@ void bnxt_vf_reps_close(struct bnxt *bp)
 
 /* Called when the parent PF interface is opened (re-opened):
  * As the mode transition from SWITCHDEV to LEGACY
- * happen under the rtnl_lock() this routine is safe
- * under the rtnl_lock()
+ * happen under the netdev instance lock this routine is safe
  */
 void bnxt_vf_reps_open(struct bnxt *bp)
 {
@@ -348,7 +346,7 @@ void bnxt_vf_reps_destroy(struct bnxt *bp)
 	/* Ensure that parent PF's and VF-reps' RX/TX has been quiesced
 	 * before proceeding with VF-rep cleanup.
 	 */
-	rtnl_lock();
+	netdev_lock(bp->dev);
 	if (netif_running(bp->dev)) {
 		bnxt_close_nic(bp, false, false);
 		closed = true;
@@ -365,10 +363,10 @@ void bnxt_vf_reps_destroy(struct bnxt *bp)
 		bnxt_open_nic(bp, false, false);
 		bp->eswitch_mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
 	}
-	rtnl_unlock();
+	netdev_unlock(bp->dev);
 
-	/* Need to call vf_reps_destroy() outside of rntl_lock
-	 * as unregister_netdev takes rtnl_lock
+	/* Need to call vf_reps_destroy() outside of netdev instance lock
+	 * as unregister_netdev takes it
 	 */
 	__bnxt_vf_reps_destroy(bp);
 }
@@ -376,7 +374,7 @@ void bnxt_vf_reps_destroy(struct bnxt *bp)
 /* Free the VF-Reps in firmware, during firmware hot-reset processing.
  * Note that the VF-Rep netdevs are still active (not unregistered) during
  * this process. As the mode transition from SWITCHDEV to LEGACY happens
- * under the rtnl_lock() this routine is safe under the rtnl_lock().
+ * under the netdev instance lock this routine is safe.
  */
 void bnxt_vf_reps_free(struct bnxt *bp)
 {
@@ -413,7 +411,7 @@ static int bnxt_alloc_vf_rep(struct bnxt *bp, struct bnxt_vf_rep *vf_rep,
 /* Allocate the VF-Reps in firmware, during firmware hot-reset processing.
  * Note that the VF-Rep netdevs are still active (not unregistered) during
  * this process. As the mode transition from SWITCHDEV to LEGACY happens
- * under the rtnl_lock() this routine is safe under the rtnl_lock().
+ * under the netdev instance lock this routine is safe.
  */
 int bnxt_vf_reps_alloc(struct bnxt *bp)
 {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index f88b641533fc..3e77a96e5a3e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -15,8 +15,9 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/filter.h>
+#include <net/netdev_lock.h>
 #include <net/page_pool/helpers.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_xdp.h"
 
@@ -48,8 +49,7 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
 		tx_buf->page = virt_to_head_page(xdp->data);
 
 	txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
-	flags = (len << TX_BD_LEN_SHIFT) |
-		((num_frags + 1) << TX_BD_FLAGS_BD_CNT_SHIFT) |
+	flags = (len << TX_BD_LEN_SHIFT) | TX_BD_CNT(num_frags + 1) |
 		bnxt_lhint_arr[len >> 9];
 	txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
 	txbd->tx_bd_opaque = SET_TX_OPAQUE(bp, txr, prod, 1 + num_frags);
@@ -115,7 +115,7 @@ static void __bnxt_xmit_xdp_redirect(struct bnxt *bp,
 	tx_buf->action = XDP_REDIRECT;
 	tx_buf->xdpf = xdpf;
 	dma_unmap_addr_set(tx_buf, mapping, mapping);
-	dma_unmap_len_set(tx_buf, len, 0);
+	dma_unmap_len_set(tx_buf, len, len);
 }
 
 void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
@@ -382,19 +382,24 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
 	return nxmit;
 }
 
-/* Under rtnl_lock */
 static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 {
 	struct net_device *dev = bp->dev;
 	int tx_xdp = 0, tx_cp, rc, tc;
 	struct bpf_prog *old;
 
+	netdev_assert_locked(dev);
+
 	if (prog && !prog->aux->xdp_has_frags &&
 	    bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU) {
 		netdev_warn(dev, "MTU %d larger than %d without XDP frag support.\n",
 			    bp->dev->mtu, BNXT_MAX_PAGE_MODE_MTU);
 		return -EOPNOTSUPP;
 	}
+	if (prog && bp->flags & BNXT_FLAG_HDS) {
+		netdev_warn(dev, "XDP is disallowed when HDS is enabled.\n");
+		return -EOPNOTSUPP;
+	}
 	if (!(bp->flags & BNXT_FLAG_SHARED_RINGS)) {
 		netdev_warn(dev, "ethtool rx/tx channels must be combined to support XDP.\n");
 		return -EOPNOTSUPP;
@@ -420,17 +425,10 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 
 	if (prog) {
 		bnxt_set_rx_skb_mode(bp, true);
-		xdp_features_set_redirect_target(dev, true);
+		xdp_features_set_redirect_target_locked(dev, true);
 	} else {
-		int rx, tx;
-
-		xdp_features_clear_redirect_target(dev);
+		xdp_features_clear_redirect_target_locked(dev);
 		bnxt_set_rx_skb_mode(bp, false);
-		bnxt_get_max_rings(bp, &rx, &tx, true);
-		if (rx > 1) {
-			bp->flags &= ~BNXT_FLAG_NO_AGG_RINGS;
-			bp->dev->hw_features |= NETIF_F_LRO;
-		}
 	}
 	bp->tx_nr_rings_xdp = tx_xdp;
 	bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc + tx_xdp;
@@ -463,23 +461,15 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 
 struct sk_buff *
 bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, u8 num_frags,
-		   struct page_pool *pool, struct xdp_buff *xdp,
-		   struct rx_cmp_ext *rxcmp1)
+		   struct page_pool *pool, struct xdp_buff *xdp)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 
 	if (!skb)
 		return NULL;
-	skb_checksum_none_assert(skb);
-	if (RX_CMP_L4_CS_OK(rxcmp1)) {
-		if (bp->dev->features & NETIF_F_RXCSUM) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			skb->csum_level = RX_CMP_ENCAP(rxcmp1);
-		}
-	}
-	xdp_update_skb_shared_info(skb, num_frags,
-				   sinfo->xdp_frags_size,
-				   BNXT_RX_PAGE_SIZE * sinfo->nr_frags,
-				   xdp_buff_is_frag_pfmemalloc(xdp));
+
+	xdp_update_skb_frags_info(skb, num_frags, sinfo->xdp_frags_size,
+				  BNXT_RX_PAGE_SIZE * num_frags,
+				  xdp_buff_get_skb_flags(xdp));
 	return skb;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index 0122782400b8..220285e190fc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -33,6 +33,5 @@ void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
 			      struct xdp_buff *xdp);
 struct sk_buff *bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb,
 				   u8 num_frags, struct page_pool *pool,
-				   struct xdp_buff *xdp,
-				   struct rx_cmp_ext *rxcmp1);
+				   struct xdp_buff *xdp);
 #endif
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index a9040c42d2ff..6e97a5a7daaf 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -4230,8 +4230,7 @@ static void cnic_cm_stop_bnx2x_hw(struct cnic_dev *dev)
 
 	cnic_bnx2x_delete_wait(dev, 0);
 
-	cancel_delayed_work(&cp->delete_task);
-	flush_workqueue(cnic_wq);
+	cancel_delayed_work_sync(&cp->delete_task);
 
 	if (atomic_read(&cp->iscsi_conn) != 0)
 		netdev_warn(dev->netdev, "%d iSCSI connections not destroyed\n",
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 3e93f957430b..05512aa10c20 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2,7 +2,7 @@
 /*
  * Broadcom GENET (Gigabit Ethernet) controller driver
  *
- * Copyright (c) 2014-2024 Broadcom
+ * Copyright (c) 2014-2025 Broadcom
  */
 
 #define pr_fmt(fmt)				"bcmgenet: " fmt
@@ -35,21 +35,18 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/phy.h>
-#include <linux/platform_data/bcmgenet.h>
 
 #include <linux/unaligned.h>
 
 #include "bcmgenet.h"
 
-/* Maximum number of hardware queues, downsized if needed */
-#define GENET_MAX_MQ_CNT	4
-
 /* Default highest priority queue for multi queue support */
-#define GENET_Q0_PRIORITY	0
+#define GENET_Q1_PRIORITY	0
+#define GENET_Q0_PRIORITY	1
 
-#define GENET_Q16_RX_BD_CNT	\
+#define GENET_Q0_RX_BD_CNT	\
 	(TOTAL_DESC - priv->hw_params->rx_queues * priv->hw_params->rx_bds_per_q)
-#define GENET_Q16_TX_BD_CNT	\
+#define GENET_Q0_TX_BD_CNT	\
 	(TOTAL_DESC - priv->hw_params->tx_queues * priv->hw_params->tx_bds_per_q)
 
 #define RX_BUF_LENGTH		2048
@@ -104,7 +101,7 @@ static inline void dmadesc_set_addr(struct bcmgenet_priv *priv,
 	 * the platform is explicitly configured for 64-bits/LPAE.
 	 */
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
-	if (priv->hw_params->flags & GENET_HAS_40BITS)
+	if (bcmgenet_has_40bits(priv))
 		bcmgenet_writel(upper_32_bits(addr), d + DMA_DESC_ADDRESS_HI);
 #endif
 }
@@ -446,33 +443,48 @@ static void bcmgenet_hfb_enable_filter(struct bcmgenet_priv *priv, u32 f_index)
 	u32 offset;
 	u32 reg;
 
-	offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32);
-	reg = bcmgenet_hfb_reg_readl(priv, offset);
-	reg |= (1 << (f_index % 32));
-	bcmgenet_hfb_reg_writel(priv, reg, offset);
-	reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-	reg |= RBUF_HFB_EN;
-	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) {
+		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+		reg |= (1 << ((f_index % 32) + RBUF_HFB_FILTER_EN_SHIFT)) |
+			RBUF_HFB_EN;
+		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+	} else {
+		offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32);
+		reg = bcmgenet_hfb_reg_readl(priv, offset);
+		reg |= (1 << (f_index % 32));
+		bcmgenet_hfb_reg_writel(priv, reg, offset);
+		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+		reg |= RBUF_HFB_EN;
+		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+	}
 }
 
 static void bcmgenet_hfb_disable_filter(struct bcmgenet_priv *priv, u32 f_index)
 {
 	u32 offset, reg, reg1;
 
-	offset = HFB_FLT_ENABLE_V3PLUS;
-	reg = bcmgenet_hfb_reg_readl(priv, offset);
-	reg1 = bcmgenet_hfb_reg_readl(priv, offset + sizeof(u32));
-	if  (f_index < 32) {
-		reg1 &= ~(1 << (f_index % 32));
-		bcmgenet_hfb_reg_writel(priv, reg1, offset + sizeof(u32));
-	} else {
-		reg &= ~(1 << (f_index % 32));
-		bcmgenet_hfb_reg_writel(priv, reg, offset);
-	}
-	if (!reg && !reg1) {
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) {
 		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-		reg &= ~RBUF_HFB_EN;
+		reg &= ~(1 << ((f_index % 32) + RBUF_HFB_FILTER_EN_SHIFT));
+		if (!(reg & RBUF_HFB_FILTER_EN_MASK))
+			reg &= ~RBUF_HFB_EN;
 		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+	} else {
+		offset = HFB_FLT_ENABLE_V3PLUS;
+		reg = bcmgenet_hfb_reg_readl(priv, offset);
+		reg1 = bcmgenet_hfb_reg_readl(priv, offset + sizeof(u32));
+		if  (f_index < 32) {
+			reg1 &= ~(1 << (f_index % 32));
+			bcmgenet_hfb_reg_writel(priv, reg1, offset + sizeof(u32));
+		} else {
+			reg &= ~(1 << (f_index % 32));
+			bcmgenet_hfb_reg_writel(priv, reg, offset);
+		}
+		if (!reg && !reg1) {
+			reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+			reg &= ~RBUF_HFB_EN;
+			bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+		}
 	}
 }
 
@@ -482,6 +494,9 @@ static void bcmgenet_hfb_set_filter_rx_queue_mapping(struct bcmgenet_priv *priv,
 	u32 offset;
 	u32 reg;
 
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
+		return;
+
 	offset = f_index / 8;
 	reg = bcmgenet_rdma_readl(priv, DMA_INDEX2RING_0 + offset);
 	reg &= ~(0xF << (4 * (f_index % 8)));
@@ -495,9 +510,13 @@ static void bcmgenet_hfb_set_filter_length(struct bcmgenet_priv *priv,
 	u32 offset;
 	u32 reg;
 
-	offset = HFB_FLT_LEN_V3PLUS +
-		 ((priv->hw_params->hfb_filter_cnt - 1 - f_index) / 4) *
-		 sizeof(u32);
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
+		offset = HFB_FLT_LEN_V2;
+	else
+		offset = HFB_FLT_LEN_V3PLUS;
+
+	offset += sizeof(u32) *
+		  ((priv->hw_params->hfb_filter_cnt - 1 - f_index) / 4);
 	reg = bcmgenet_hfb_reg_readl(priv, offset);
 	reg &= ~(0xFF << (8 * (f_index % 4)));
 	reg |= ((f_length & 0xFF) << (8 * (f_index % 4)));
@@ -579,13 +598,13 @@ static void bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv,
 					     struct bcmgenet_rxnfc_rule *rule)
 {
 	struct ethtool_rx_flow_spec *fs = &rule->fs;
-	u32 offset = 0, f_length = 0, f;
+	u32 offset = 0, f_length = 0, f, q;
 	u8 val_8, mask_8;
 	__be16 val_16;
 	u16 mask_16;
 	size_t size;
 
-	f = fs->location;
+	f = fs->location + 1;
 	if (fs->flow_type & FLOW_MAC_EXT) {
 		bcmgenet_hfb_insert_data(priv, f, 0,
 					 &fs->h_ext.h_dest, &fs->m_ext.h_dest,
@@ -667,19 +686,16 @@ static void bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv,
 	}
 
 	bcmgenet_hfb_set_filter_length(priv, f, 2 * f_length);
-	if (!fs->ring_cookie || fs->ring_cookie == RX_CLS_FLOW_WAKE) {
-		/* Ring 0 flows can be handled by the default Descriptor Ring
-		 * We'll map them to ring 0, but don't enable the filter
-		 */
-		bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f, 0);
-		rule->state = BCMGENET_RXNFC_STATE_DISABLED;
-	} else {
+	if (fs->ring_cookie == RX_CLS_FLOW_WAKE)
+		q = 0;
+	else if (fs->ring_cookie == RX_CLS_FLOW_DISC)
+		q = priv->hw_params->rx_queues + 1;
+	else
 		/* Other Rx rings are direct mapped here */
-		bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f,
-							 fs->ring_cookie);
-		bcmgenet_hfb_enable_filter(priv, f);
-		rule->state = BCMGENET_RXNFC_STATE_ENABLED;
-	}
+		q = fs->ring_cookie;
+	bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f, q);
+	bcmgenet_hfb_enable_filter(priv, f);
+	rule->state = BCMGENET_RXNFC_STATE_ENABLED;
 }
 
 /* bcmgenet_hfb_clear
@@ -690,6 +706,7 @@ static void bcmgenet_hfb_clear_filter(struct bcmgenet_priv *priv, u32 f_index)
 {
 	u32 base, i;
 
+	bcmgenet_hfb_set_filter_length(priv, f_index, 0);
 	base = f_index * priv->hw_params->hfb_filter_size;
 	for (i = 0; i < priv->hw_params->hfb_filter_size; i++)
 		bcmgenet_hfb_writel(priv, 0x0, (base + i) * sizeof(u32));
@@ -699,22 +716,23 @@ static void bcmgenet_hfb_clear(struct bcmgenet_priv *priv)
 {
 	u32 i;
 
-	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
-		return;
-
-	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_CTRL);
-	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS);
-	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS + 4);
-
-	for (i = DMA_INDEX2RING_0; i <= DMA_INDEX2RING_7; i++)
-		bcmgenet_rdma_writel(priv, 0x0, i);
+	bcmgenet_hfb_reg_writel(priv, 0, HFB_CTRL);
 
-	for (i = 0; i < (priv->hw_params->hfb_filter_cnt / 4); i++)
-		bcmgenet_hfb_reg_writel(priv, 0x0,
-					HFB_FLT_LEN_V3PLUS + i * sizeof(u32));
+	if (!GENET_IS_V1(priv) && !GENET_IS_V2(priv)) {
+		bcmgenet_hfb_reg_writel(priv, 0,
+					HFB_FLT_ENABLE_V3PLUS);
+		bcmgenet_hfb_reg_writel(priv, 0,
+					HFB_FLT_ENABLE_V3PLUS + 4);
+		for (i = DMA_INDEX2RING_0; i <= DMA_INDEX2RING_7; i++)
+			bcmgenet_rdma_writel(priv, 0, i);
+	}
 
 	for (i = 0; i < priv->hw_params->hfb_filter_cnt; i++)
 		bcmgenet_hfb_clear_filter(priv, i);
+
+	/* Enable filter 0 to send default flow to ring 0 */
+	bcmgenet_hfb_set_filter_length(priv, 0, 4);
+	bcmgenet_hfb_enable_filter(priv, 0);
 }
 
 static void bcmgenet_hfb_init(struct bcmgenet_priv *priv)
@@ -722,9 +740,6 @@ static void bcmgenet_hfb_init(struct bcmgenet_priv *priv)
 	int i;
 
 	INIT_LIST_HEAD(&priv->rxnfc_list);
-	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
-		return;
-
 	for (i = 0; i < MAX_NUM_OF_FS_RULES; i++) {
 		INIT_LIST_HEAD(&priv->rxnfc_rules[i].list);
 		priv->rxnfc_rules[i].state = BCMGENET_RXNFC_STATE_UNUSED;
@@ -819,20 +834,16 @@ static int bcmgenet_get_coalesce(struct net_device *dev,
 	unsigned int i;
 
 	ec->tx_max_coalesced_frames =
-		bcmgenet_tdma_ring_readl(priv, DESC_INDEX,
-					 DMA_MBUF_DONE_THRESH);
+		bcmgenet_tdma_ring_readl(priv, 0, DMA_MBUF_DONE_THRESH);
 	ec->rx_max_coalesced_frames =
-		bcmgenet_rdma_ring_readl(priv, DESC_INDEX,
-					 DMA_MBUF_DONE_THRESH);
+		bcmgenet_rdma_ring_readl(priv, 0, DMA_MBUF_DONE_THRESH);
 	ec->rx_coalesce_usecs =
-		bcmgenet_rdma_readl(priv, DMA_RING16_TIMEOUT) * 8192 / 1000;
+		bcmgenet_rdma_readl(priv, DMA_RING0_TIMEOUT) * 8192 / 1000;
 
-	for (i = 0; i < priv->hw_params->rx_queues; i++) {
+	for (i = 0; i <= priv->hw_params->rx_queues; i++) {
 		ring = &priv->rx_rings[i];
 		ec->use_adaptive_rx_coalesce |= ring->dim.use_dim;
 	}
-	ring = &priv->rx_rings[DESC_INDEX];
-	ec->use_adaptive_rx_coalesce |= ring->dim.use_dim;
 
 	return 0;
 }
@@ -902,17 +913,13 @@ static int bcmgenet_set_coalesce(struct net_device *dev,
 	/* Program all TX queues with the same values, as there is no
 	 * ethtool knob to do coalescing on a per-queue basis
 	 */
-	for (i = 0; i < priv->hw_params->tx_queues; i++)
+	for (i = 0; i <= priv->hw_params->tx_queues; i++)
 		bcmgenet_tdma_ring_writel(priv, i,
 					  ec->tx_max_coalesced_frames,
 					  DMA_MBUF_DONE_THRESH);
-	bcmgenet_tdma_ring_writel(priv, DESC_INDEX,
-				  ec->tx_max_coalesced_frames,
-				  DMA_MBUF_DONE_THRESH);
 
-	for (i = 0; i < priv->hw_params->rx_queues; i++)
+	for (i = 0; i <= priv->hw_params->rx_queues; i++)
 		bcmgenet_set_ring_rx_coalesce(&priv->rx_rings[i], ec);
-	bcmgenet_set_ring_rx_coalesce(&priv->rx_rings[DESC_INDEX], ec);
 
 	return 0;
 }
@@ -961,12 +968,13 @@ static int bcmgenet_set_pauseparam(struct net_device *dev,
 
 /* standard ethtool support functions. */
 enum bcmgenet_stat_type {
-	BCMGENET_STAT_NETDEV = -1,
+	BCMGENET_STAT_RTNL = -1,
 	BCMGENET_STAT_MIB_RX,
 	BCMGENET_STAT_MIB_TX,
 	BCMGENET_STAT_RUNT,
 	BCMGENET_STAT_MISC,
 	BCMGENET_STAT_SOFT,
+	BCMGENET_STAT_SOFT64,
 };
 
 struct bcmgenet_stats {
@@ -976,13 +984,15 @@ struct bcmgenet_stats {
 	enum bcmgenet_stat_type type;
 	/* reg offset from UMAC base for misc counters */
 	u16 reg_offset;
+	/* sync for u64 stats counters */
+	int syncp_offset;
 };
 
-#define STAT_NETDEV(m) { \
+#define STAT_RTNL(m) { \
 	.stat_string = __stringify(m), \
-	.stat_sizeof = sizeof(((struct net_device_stats *)0)->m), \
-	.stat_offset = offsetof(struct net_device_stats, m), \
-	.type = BCMGENET_STAT_NETDEV, \
+	.stat_sizeof = sizeof(((struct rtnl_link_stats64 *)0)->m), \
+	.stat_offset = offsetof(struct rtnl_link_stats64, m), \
+	.type = BCMGENET_STAT_RTNL, \
 }
 
 #define STAT_GENET_MIB(str, m, _type) { \
@@ -992,6 +1002,14 @@ struct bcmgenet_stats {
 	.type = _type, \
 }
 
+#define STAT_GENET_SOFT_MIB64(str, s, m) { \
+	.stat_string = str, \
+	.stat_sizeof = sizeof(((struct bcmgenet_priv *)0)->s.m), \
+	.stat_offset = offsetof(struct bcmgenet_priv, s.m), \
+	.type = BCMGENET_STAT_SOFT64, \
+	.syncp_offset = offsetof(struct bcmgenet_priv, s.syncp), \
+}
+
 #define STAT_GENET_MIB_RX(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_MIB_RX)
 #define STAT_GENET_MIB_TX(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_MIB_TX)
 #define STAT_GENET_RUNT(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_RUNT)
@@ -1006,18 +1024,38 @@ struct bcmgenet_stats {
 }
 
 #define STAT_GENET_Q(num) \
-	STAT_GENET_SOFT_MIB("txq" __stringify(num) "_packets", \
-			tx_rings[num].packets), \
-	STAT_GENET_SOFT_MIB("txq" __stringify(num) "_bytes", \
-			tx_rings[num].bytes), \
-	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_bytes", \
-			rx_rings[num].bytes),	 \
-	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_packets", \
-			rx_rings[num].packets), \
-	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_errors", \
-			rx_rings[num].errors), \
-	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_dropped", \
-			rx_rings[num].dropped)
+	STAT_GENET_SOFT_MIB64("txq" __stringify(num) "_packets", \
+			tx_rings[num].stats64, packets), \
+	STAT_GENET_SOFT_MIB64("txq" __stringify(num) "_bytes", \
+			tx_rings[num].stats64, bytes), \
+	STAT_GENET_SOFT_MIB64("txq" __stringify(num) "_errors", \
+			tx_rings[num].stats64, errors), \
+	STAT_GENET_SOFT_MIB64("txq" __stringify(num) "_dropped", \
+			tx_rings[num].stats64, dropped), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_bytes", \
+			rx_rings[num].stats64, bytes),	 \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_packets", \
+			rx_rings[num].stats64, packets), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_errors", \
+			rx_rings[num].stats64, errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_dropped", \
+			rx_rings[num].stats64, dropped), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_multicast", \
+			rx_rings[num].stats64, multicast), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_missed", \
+			rx_rings[num].stats64, missed), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_length_errors", \
+			rx_rings[num].stats64, length_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_over_errors", \
+			rx_rings[num].stats64, over_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_crc_errors", \
+			rx_rings[num].stats64, crc_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_frame_errors", \
+			rx_rings[num].stats64, frame_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_fragmented_errors", \
+			rx_rings[num].stats64, fragmented_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_broadcast", \
+			rx_rings[num].stats64, broadcast)
 
 /* There is a 0xC gap between the end of RX and beginning of TX stats and then
  * between the end of TX stats and the beginning of the RX RUNT
@@ -1029,15 +1067,20 @@ struct bcmgenet_stats {
  */
 static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = {
 	/* general stats */
-	STAT_NETDEV(rx_packets),
-	STAT_NETDEV(tx_packets),
-	STAT_NETDEV(rx_bytes),
-	STAT_NETDEV(tx_bytes),
-	STAT_NETDEV(rx_errors),
-	STAT_NETDEV(tx_errors),
-	STAT_NETDEV(rx_dropped),
-	STAT_NETDEV(tx_dropped),
-	STAT_NETDEV(multicast),
+	STAT_RTNL(rx_packets),
+	STAT_RTNL(tx_packets),
+	STAT_RTNL(rx_bytes),
+	STAT_RTNL(tx_bytes),
+	STAT_RTNL(rx_errors),
+	STAT_RTNL(tx_errors),
+	STAT_RTNL(rx_dropped),
+	STAT_RTNL(tx_dropped),
+	STAT_RTNL(multicast),
+	STAT_RTNL(rx_missed_errors),
+	STAT_RTNL(rx_length_errors),
+	STAT_RTNL(rx_over_errors),
+	STAT_RTNL(rx_crc_errors),
+	STAT_RTNL(rx_frame_errors),
 	/* UniMAC RSV counters */
 	STAT_GENET_MIB_RX("rx_64_octets", mib.rx.pkt_cnt.cnt_64),
 	STAT_GENET_MIB_RX("rx_65_127_oct", mib.rx.pkt_cnt.cnt_127),
@@ -1120,11 +1163,25 @@ static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = {
 	STAT_GENET_Q(1),
 	STAT_GENET_Q(2),
 	STAT_GENET_Q(3),
-	STAT_GENET_Q(16),
+	STAT_GENET_Q(4),
 };
 
 #define BCMGENET_STATS_LEN	ARRAY_SIZE(bcmgenet_gstrings_stats)
 
+#define BCMGENET_STATS64_ADD(stats, m, v) \
+	do { \
+		u64_stats_update_begin(&stats->syncp); \
+		u64_stats_add(&stats->m, v); \
+		u64_stats_update_end(&stats->syncp); \
+	} while (0)
+
+#define BCMGENET_STATS64_INC(stats, m) \
+	do { \
+		u64_stats_update_begin(&stats->syncp); \
+		u64_stats_inc(&stats->m); \
+		u64_stats_update_end(&stats->syncp); \
+	} while (0)
+
 static void bcmgenet_get_drvinfo(struct net_device *dev,
 				 struct ethtool_drvinfo *info)
 {
@@ -1208,8 +1265,9 @@ static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv)
 
 		s = &bcmgenet_gstrings_stats[i];
 		switch (s->type) {
-		case BCMGENET_STAT_NETDEV:
+		case BCMGENET_STAT_RTNL:
 		case BCMGENET_STAT_SOFT:
+		case BCMGENET_STAT_SOFT64:
 			continue;
 		case BCMGENET_STAT_RUNT:
 			offset += BCMGENET_STAT_OFFSET;
@@ -1247,28 +1305,40 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev,
 				       u64 *data)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct rtnl_link_stats64 stats64;
+	struct u64_stats_sync *syncp;
+	unsigned int start;
 	int i;
 
 	if (netif_running(dev))
 		bcmgenet_update_mib_counters(priv);
 
-	dev->netdev_ops->ndo_get_stats(dev);
+	dev_get_stats(dev, &stats64);
 
 	for (i = 0; i < BCMGENET_STATS_LEN; i++) {
 		const struct bcmgenet_stats *s;
 		char *p;
 
 		s = &bcmgenet_gstrings_stats[i];
-		if (s->type == BCMGENET_STAT_NETDEV)
-			p = (char *)&dev->stats;
-		else
-			p = (char *)priv;
-		p += s->stat_offset;
-		if (sizeof(unsigned long) != sizeof(u32) &&
-		    s->stat_sizeof == sizeof(unsigned long))
-			data[i] = *(unsigned long *)p;
-		else
-			data[i] = *(u32 *)p;
+		p = (char *)priv;
+
+		if (s->type == BCMGENET_STAT_SOFT64) {
+			syncp = (struct u64_stats_sync *)(p + s->syncp_offset);
+			do {
+				start = u64_stats_fetch_begin(syncp);
+				data[i] = u64_stats_read((u64_stats_t *)(p + s->stat_offset));
+			} while (u64_stats_fetch_retry(syncp, start));
+		} else {
+			if (s->type == BCMGENET_STAT_RTNL)
+				p = (char *)&stats64;
+
+			p += s->stat_offset;
+			if (sizeof(unsigned long) != sizeof(u32) &&
+				s->stat_sizeof == sizeof(unsigned long))
+				data[i] = *(unsigned long *)p;
+			else
+				data[i] = *(u32 *)p;
+		}
 	}
 }
 
@@ -1438,7 +1508,8 @@ static int bcmgenet_insert_flow(struct net_device *dev,
 	}
 
 	if (cmd->fs.ring_cookie > priv->hw_params->rx_queues &&
-	    cmd->fs.ring_cookie != RX_CLS_FLOW_WAKE) {
+	    cmd->fs.ring_cookie != RX_CLS_FLOW_WAKE &&
+	    cmd->fs.ring_cookie != RX_CLS_FLOW_DISC) {
 		netdev_err(dev, "rxnfc: Unsupported action (%llu)\n",
 			   cmd->fs.ring_cookie);
 		return -EINVAL;
@@ -1472,10 +1543,10 @@ static int bcmgenet_insert_flow(struct net_device *dev,
 		loc_rule = &priv->rxnfc_rules[cmd->fs.location];
 	}
 	if (loc_rule->state == BCMGENET_RXNFC_STATE_ENABLED)
-		bcmgenet_hfb_disable_filter(priv, cmd->fs.location);
+		bcmgenet_hfb_disable_filter(priv, cmd->fs.location + 1);
 	if (loc_rule->state != BCMGENET_RXNFC_STATE_UNUSED) {
 		list_del(&loc_rule->list);
-		bcmgenet_hfb_clear_filter(priv, cmd->fs.location);
+		bcmgenet_hfb_clear_filter(priv, cmd->fs.location + 1);
 	}
 	loc_rule->state = BCMGENET_RXNFC_STATE_UNUSED;
 	memcpy(&loc_rule->fs, &cmd->fs,
@@ -1505,10 +1576,10 @@ static int bcmgenet_delete_flow(struct net_device *dev,
 	}
 
 	if (rule->state == BCMGENET_RXNFC_STATE_ENABLED)
-		bcmgenet_hfb_disable_filter(priv, cmd->fs.location);
+		bcmgenet_hfb_disable_filter(priv, cmd->fs.location + 1);
 	if (rule->state != BCMGENET_RXNFC_STATE_UNUSED) {
 		list_del(&rule->list);
-		bcmgenet_hfb_clear_filter(priv, cmd->fs.location);
+		bcmgenet_hfb_clear_filter(priv, cmd->fs.location + 1);
 	}
 	rule->state = BCMGENET_RXNFC_STATE_UNUSED;
 	memset(&rule->fs, 0, sizeof(struct ethtool_rx_flow_spec));
@@ -1569,6 +1640,13 @@ static int bcmgenet_get_num_flows(struct bcmgenet_priv *priv)
 	return res;
 }
 
+static u32 bcmgenet_get_rx_ring_count(struct net_device *dev)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+
+	return priv->hw_params->rx_queues ?: 1;
+}
+
 static int bcmgenet_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 			      u32 *rule_locs)
 {
@@ -1578,9 +1656,6 @@ static int bcmgenet_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	int i = 0;
 
 	switch (cmd->cmd) {
-	case ETHTOOL_GRXRINGS:
-		cmd->data = priv->hw_params->rx_queues ?: 1;
-		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = bcmgenet_get_num_flows(priv);
 		cmd->data = MAX_NUM_OF_FS_RULES | RX_CLS_LOC_SPECIAL;
@@ -1629,6 +1704,7 @@ static const struct ethtool_ops bcmgenet_ethtool_ops = {
 	.get_ts_info		= ethtool_op_get_ts_info,
 	.get_rxnfc		= bcmgenet_get_rxnfc,
 	.set_rxnfc		= bcmgenet_set_rxnfc,
+	.get_rx_ring_count	= bcmgenet_get_rx_ring_count,
 	.get_pauseparam		= bcmgenet_get_pauseparam,
 	.set_pauseparam		= bcmgenet_set_pauseparam,
 };
@@ -1651,9 +1727,9 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
 
 	case GENET_POWER_PASSIVE:
 		/* Power down LED */
-		if (priv->hw_params->flags & GENET_HAS_EXT) {
+		if (bcmgenet_has_ext(priv)) {
 			reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
-			if (GENET_IS_V5(priv) && !priv->ephy_16nm)
+			if (GENET_IS_V5(priv) && !bcmgenet_has_ephy_16nm(priv))
 				reg |= EXT_PWR_DOWN_PHY_EN |
 				       EXT_PWR_DOWN_PHY_RD |
 				       EXT_PWR_DOWN_PHY_SD |
@@ -1676,13 +1752,14 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
 	return ret;
 }
 
-static void bcmgenet_power_up(struct bcmgenet_priv *priv,
-			      enum bcmgenet_power_mode mode)
+static int bcmgenet_power_up(struct bcmgenet_priv *priv,
+			     enum bcmgenet_power_mode mode)
 {
+	int ret = 0;
 	u32 reg;
 
-	if (!(priv->hw_params->flags & GENET_HAS_EXT))
-		return;
+	if (!bcmgenet_has_ext(priv))
+		return ret;
 
 	reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
 
@@ -1690,7 +1767,7 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 	case GENET_POWER_PASSIVE:
 		reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS |
 			 EXT_ENERGY_DET_MASK);
-		if (GENET_IS_V5(priv) && !priv->ephy_16nm) {
+		if (GENET_IS_V5(priv) && !bcmgenet_has_ephy_16nm(priv)) {
 			reg &= ~(EXT_PWR_DOWN_PHY_EN |
 				 EXT_PWR_DOWN_PHY_RD |
 				 EXT_PWR_DOWN_PHY_SD |
@@ -1718,11 +1795,13 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 		}
 		break;
 	case GENET_POWER_WOL_MAGIC:
-		bcmgenet_wol_power_up_cfg(priv, mode);
-		return;
+		ret = bcmgenet_wol_power_up_cfg(priv, mode);
+		break;
 	default:
 		break;
 	}
+
+	return ret;
 }
 
 static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv,
@@ -1759,18 +1838,6 @@ static struct enet_cb *bcmgenet_put_txcb(struct bcmgenet_priv *priv,
 	return tx_cb_ptr;
 }
 
-static inline void bcmgenet_rx_ring16_int_disable(struct bcmgenet_rx_ring *ring)
-{
-	bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_RXDMA_DONE,
-				 INTRL2_CPU_MASK_SET);
-}
-
-static inline void bcmgenet_rx_ring16_int_enable(struct bcmgenet_rx_ring *ring)
-{
-	bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_RXDMA_DONE,
-				 INTRL2_CPU_MASK_CLEAR);
-}
-
 static inline void bcmgenet_rx_ring_int_disable(struct bcmgenet_rx_ring *ring)
 {
 	bcmgenet_intrl2_1_writel(ring->priv,
@@ -1785,18 +1852,6 @@ static inline void bcmgenet_rx_ring_int_enable(struct bcmgenet_rx_ring *ring)
 				 INTRL2_CPU_MASK_CLEAR);
 }
 
-static inline void bcmgenet_tx_ring16_int_disable(struct bcmgenet_tx_ring *ring)
-{
-	bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_TXDMA_DONE,
-				 INTRL2_CPU_MASK_SET);
-}
-
-static inline void bcmgenet_tx_ring16_int_enable(struct bcmgenet_tx_ring *ring)
-{
-	bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_TXDMA_DONE,
-				 INTRL2_CPU_MASK_CLEAR);
-}
-
 static inline void bcmgenet_tx_ring_int_enable(struct bcmgenet_tx_ring *ring)
 {
 	bcmgenet_intrl2_1_writel(ring->priv, 1 << ring->index,
@@ -1868,6 +1923,7 @@ static struct sk_buff *bcmgenet_free_rx_cb(struct device *dev,
 static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 					  struct bcmgenet_tx_ring *ring)
 {
+	struct bcmgenet_tx_stats64 *stats = &ring->stats64;
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	unsigned int txbds_processed = 0;
 	unsigned int bytes_compl = 0;
@@ -1877,12 +1933,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	struct sk_buff *skb;
 
 	/* Clear status before servicing to reduce spurious interrupts */
-	if (ring->index == DESC_INDEX)
-		bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_TXDMA_DONE,
-					 INTRL2_CPU_CLEAR);
-	else
-		bcmgenet_intrl2_1_writel(priv, (1 << ring->index),
-					 INTRL2_CPU_CLEAR);
+	bcmgenet_intrl2_1_writel(priv, (1 << ring->index), INTRL2_CPU_CLEAR);
 
 	/* Compute how many buffers are transmitted since last xmit call */
 	c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX)
@@ -1913,22 +1964,51 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	ring->free_bds += txbds_processed;
 	ring->c_index = c_index;
 
-	ring->packets += pkts_compl;
-	ring->bytes += bytes_compl;
+	u64_stats_update_begin(&stats->syncp);
+	u64_stats_add(&stats->packets, pkts_compl);
+	u64_stats_add(&stats->bytes, bytes_compl);
+	u64_stats_update_end(&stats->syncp);
 
-	netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->queue),
+	netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->index),
 				  pkts_compl, bytes_compl);
 
 	return txbds_processed;
 }
 
 static unsigned int bcmgenet_tx_reclaim(struct net_device *dev,
-				struct bcmgenet_tx_ring *ring)
+				struct bcmgenet_tx_ring *ring,
+				bool all)
 {
-	unsigned int released;
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct device *kdev = &priv->pdev->dev;
+	unsigned int released, drop, wr_ptr;
+	struct enet_cb *cb_ptr;
+	struct sk_buff *skb;
 
 	spin_lock_bh(&ring->lock);
 	released = __bcmgenet_tx_reclaim(dev, ring);
+	if (all) {
+		skb = NULL;
+		drop = (ring->prod_index - ring->c_index) & DMA_C_INDEX_MASK;
+		released += drop;
+		ring->prod_index = ring->c_index & DMA_C_INDEX_MASK;
+		while (drop--) {
+			cb_ptr = bcmgenet_put_txcb(priv, ring);
+			skb = cb_ptr->skb;
+			bcmgenet_free_tx_cb(kdev, cb_ptr);
+			if (skb && cb_ptr == GENET_CB(skb)->first_cb) {
+				dev_consume_skb_any(skb);
+				skb = NULL;
+			}
+		}
+		if (skb)
+			dev_consume_skb_any(skb);
+		bcmgenet_tdma_ring_writel(priv, ring->index,
+					  ring->prod_index, TDMA_PROD_INDEX);
+		wr_ptr = ring->write_ptr * WORDS_PER_BD(priv);
+		bcmgenet_tdma_ring_writel(priv, ring->index, wr_ptr,
+					  TDMA_WRITE_PTR);
+	}
 	spin_unlock_bh(&ring->lock);
 
 	return released;
@@ -1944,14 +2024,14 @@ static int bcmgenet_tx_poll(struct napi_struct *napi, int budget)
 	spin_lock(&ring->lock);
 	work_done = __bcmgenet_tx_reclaim(ring->priv->dev, ring);
 	if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
-		txq = netdev_get_tx_queue(ring->priv->dev, ring->queue);
+		txq = netdev_get_tx_queue(ring->priv->dev, ring->index);
 		netif_tx_wake_queue(txq);
 	}
 	spin_unlock(&ring->lock);
 
 	if (work_done == 0) {
 		napi_complete(napi);
-		ring->int_enable(ring);
+		bcmgenet_tx_ring_int_enable(ring);
 
 		return 0;
 	}
@@ -1962,22 +2042,21 @@ static int bcmgenet_tx_poll(struct napi_struct *napi, int budget)
 static void bcmgenet_tx_reclaim_all(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	int i;
-
-	if (netif_is_multiqueue(dev)) {
-		for (i = 0; i < priv->hw_params->tx_queues; i++)
-			bcmgenet_tx_reclaim(dev, &priv->tx_rings[i]);
-	}
+	int i = 0;
 
-	bcmgenet_tx_reclaim(dev, &priv->tx_rings[DESC_INDEX]);
+	do {
+		bcmgenet_tx_reclaim(dev, &priv->tx_rings[i++], true);
+	} while (i <= priv->hw_params->tx_queues && netif_is_multiqueue(dev));
 }
 
 /* Reallocate the SKB to put enough headroom in front of it and insert
  * the transmit checksum offsets in the descriptors
  */
 static struct sk_buff *bcmgenet_add_tsb(struct net_device *dev,
-					struct sk_buff *skb)
+					struct sk_buff *skb,
+					struct bcmgenet_tx_ring *ring)
 {
+	struct bcmgenet_tx_stats64 *stats = &ring->stats64;
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct status_64 *status = NULL;
 	struct sk_buff *new_skb;
@@ -1994,7 +2073,7 @@ static struct sk_buff *bcmgenet_add_tsb(struct net_device *dev,
 		if (!new_skb) {
 			dev_kfree_skb_any(skb);
 			priv->mib.tx_realloc_tsb_failed++;
-			dev->stats.tx_dropped++;
+			BCMGENET_STATS64_INC(stats, dropped);
 			return NULL;
 		}
 		dev_consume_skb_any(skb);
@@ -2057,19 +2136,14 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	index = skb_get_queue_mapping(skb);
 	/* Mapping strategy:
-	 * queue_mapping = 0, unclassified, packet xmited through ring16
-	 * queue_mapping = 1, goes to ring 0. (highest priority queue
-	 * queue_mapping = 2, goes to ring 1.
-	 * queue_mapping = 3, goes to ring 2.
-	 * queue_mapping = 4, goes to ring 3.
+	 * queue_mapping = 0, unclassified, packet xmited through ring 0
+	 * queue_mapping = 1, goes to ring 1. (highest priority queue)
+	 * queue_mapping = 2, goes to ring 2.
+	 * queue_mapping = 3, goes to ring 3.
+	 * queue_mapping = 4, goes to ring 4.
 	 */
-	if (index == 0)
-		index = DESC_INDEX;
-	else
-		index -= 1;
-
 	ring = &priv->tx_rings[index];
-	txq = netdev_get_tx_queue(dev, ring->queue);
+	txq = netdev_get_tx_queue(dev, index);
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 
@@ -2087,7 +2161,7 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 	GENET_CB(skb)->bytes_sent = skb->len;
 
 	/* add the Transmit Status Block */
-	skb = bcmgenet_add_tsb(dev, skb);
+	skb = bcmgenet_add_tsb(dev, skb, ring);
 	if (!skb) {
 		ret = NETDEV_TX_OK;
 		goto out;
@@ -2229,6 +2303,7 @@ static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv,
 static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 				     unsigned int budget)
 {
+	struct bcmgenet_rx_stats64 *stats = &ring->stats64;
 	struct bcmgenet_priv *priv = ring->priv;
 	struct net_device *dev = priv->dev;
 	struct enet_cb *cb;
@@ -2242,15 +2317,8 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 	unsigned int discards;
 
 	/* Clear status before servicing to reduce spurious interrupts */
-	if (ring->index == DESC_INDEX) {
-		bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_RXDMA_DONE,
-					 INTRL2_CPU_CLEAR);
-	} else {
-		mask = 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index);
-		bcmgenet_intrl2_1_writel(priv,
-					 mask,
-					 INTRL2_CPU_CLEAR);
-	}
+	mask = 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index);
+	bcmgenet_intrl2_1_writel(priv, mask, INTRL2_CPU_CLEAR);
 
 	p_index = bcmgenet_rdma_ring_readl(priv, ring->index, RDMA_PROD_INDEX);
 
@@ -2258,7 +2326,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		   DMA_P_INDEX_DISCARD_CNT_MASK;
 	if (discards > ring->old_discards) {
 		discards = discards - ring->old_discards;
-		ring->errors += discards;
+		BCMGENET_STATS64_ADD(stats, missed, discards);
 		ring->old_discards += discards;
 
 		/* Clear HW register when we reach 75% of maximum 0xFFFF */
@@ -2284,7 +2352,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		skb = bcmgenet_rx_refill(priv, cb);
 
 		if (unlikely(!skb)) {
-			ring->dropped++;
+			BCMGENET_STATS64_INC(stats, dropped);
 			goto next;
 		}
 
@@ -2311,8 +2379,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 
 		if (unlikely(len > RX_BUF_LENGTH)) {
 			netif_err(priv, rx_status, dev, "oversized packet\n");
-			dev->stats.rx_length_errors++;
-			dev->stats.rx_errors++;
+			BCMGENET_STATS64_INC(stats, length_errors);
 			dev_kfree_skb_any(skb);
 			goto next;
 		}
@@ -2320,7 +2387,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		if (unlikely(!(dma_flag & DMA_EOP) || !(dma_flag & DMA_SOP))) {
 			netif_err(priv, rx_status, dev,
 				  "dropping fragmented packet!\n");
-			ring->errors++;
+			BCMGENET_STATS64_INC(stats, fragmented_errors);
 			dev_kfree_skb_any(skb);
 			goto next;
 		}
@@ -2333,15 +2400,22 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 						DMA_RX_RXER))) {
 			netif_err(priv, rx_status, dev, "dma_flag=0x%x\n",
 				  (unsigned int)dma_flag);
+			u64_stats_update_begin(&stats->syncp);
 			if (dma_flag & DMA_RX_CRC_ERROR)
-				dev->stats.rx_crc_errors++;
+				u64_stats_inc(&stats->crc_errors);
 			if (dma_flag & DMA_RX_OV)
-				dev->stats.rx_over_errors++;
+				u64_stats_inc(&stats->over_errors);
 			if (dma_flag & DMA_RX_NO)
-				dev->stats.rx_frame_errors++;
+				u64_stats_inc(&stats->frame_errors);
 			if (dma_flag & DMA_RX_LG)
-				dev->stats.rx_length_errors++;
-			dev->stats.rx_errors++;
+				u64_stats_inc(&stats->length_errors);
+			if ((dma_flag & (DMA_RX_CRC_ERROR |
+						DMA_RX_OV |
+						DMA_RX_NO |
+						DMA_RX_LG |
+						DMA_RX_RXER)) == DMA_RX_RXER)
+				u64_stats_inc(&stats->errors);
+			u64_stats_update_end(&stats->syncp);
 			dev_kfree_skb_any(skb);
 			goto next;
 		} /* error packet */
@@ -2361,10 +2435,15 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 
 		/*Finish setting up the received SKB and send it to the kernel*/
 		skb->protocol = eth_type_trans(skb, priv->dev);
-		ring->packets++;
-		ring->bytes += len;
+
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->packets);
+		u64_stats_add(&stats->bytes, len);
 		if (dma_flag & DMA_RX_MULT)
-			dev->stats.multicast++;
+			u64_stats_inc(&stats->multicast);
+		else if (dma_flag & DMA_RX_BRDCAST)
+			u64_stats_inc(&stats->broadcast);
+		u64_stats_update_end(&stats->syncp);
 
 		/* Notify kernel */
 		napi_gro_receive(&ring->napi, skb);
@@ -2397,10 +2476,8 @@ static int bcmgenet_rx_poll(struct napi_struct *napi, int budget)
 
 	work_done = bcmgenet_desc_rx(ring, budget);
 
-	if (work_done < budget) {
-		napi_complete_done(napi, work_done);
-		ring->int_enable(ring);
-	}
+	if (work_done < budget && napi_complete_done(napi, work_done))
+		bcmgenet_rx_ring_int_enable(ring);
 
 	if (ring->dim.use_dim) {
 		dim_update_sample(ring->dim.event_ctr, ring->dim.packets,
@@ -2523,7 +2600,7 @@ static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv)
 	} else if (priv->ext_phy) {
 		int0_enable |= UMAC_IRQ_LINK_EVENT;
 	} else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
-		if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
+		if (bcmgenet_has_moca_link_det(priv))
 			int0_enable |= UMAC_IRQ_LINK_EVENT;
 	}
 	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
@@ -2588,8 +2665,8 @@ static void init_umac(struct bcmgenet_priv *priv)
 	}
 
 	/* Enable MDIO interrupts on GENET v3+ */
-	if (priv->hw_params->flags & GENET_HAS_MDIO_INTR)
-		int0_enable |= (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR);
+	if (bcmgenet_has_mdio_intr(priv))
+		int0_enable |= UMAC_IRQ_MDIO_EVENT;
 
 	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
 
@@ -2639,15 +2716,6 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 	spin_lock_init(&ring->lock);
 	ring->priv = priv;
 	ring->index = index;
-	if (index == DESC_INDEX) {
-		ring->queue = 0;
-		ring->int_enable = bcmgenet_tx_ring16_int_enable;
-		ring->int_disable = bcmgenet_tx_ring16_int_disable;
-	} else {
-		ring->queue = index + 1;
-		ring->int_enable = bcmgenet_tx_ring_int_enable;
-		ring->int_disable = bcmgenet_tx_ring_int_disable;
-	}
 	ring->cbs = priv->tx_cbs + start_ptr;
 	ring->size = size;
 	ring->clean_ptr = start_ptr;
@@ -2658,8 +2726,8 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 	ring->end_ptr = end_ptr - 1;
 	ring->prod_index = 0;
 
-	/* Set flow period for ring != 16 */
-	if (index != DESC_INDEX)
+	/* Set flow period for ring != 0 */
+	if (index)
 		flow_period_val = ENET_MAX_MTU_SIZE << 16;
 
 	bcmgenet_tdma_ring_writel(priv, index, 0, TDMA_PROD_INDEX);
@@ -2697,13 +2765,6 @@ static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv,
 
 	ring->priv = priv;
 	ring->index = index;
-	if (index == DESC_INDEX) {
-		ring->int_enable = bcmgenet_rx_ring16_int_enable;
-		ring->int_disable = bcmgenet_rx_ring16_int_disable;
-	} else {
-		ring->int_enable = bcmgenet_rx_ring_int_enable;
-		ring->int_disable = bcmgenet_rx_ring_int_disable;
-	}
 	ring->cbs = priv->rx_cbs + start_ptr;
 	ring->size = size;
 	ring->c_index = 0;
@@ -2749,15 +2810,11 @@ static void bcmgenet_enable_tx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_tx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_enable(&ring->napi);
-		ring->int_enable(ring);
+		bcmgenet_tx_ring_int_enable(ring);
 	}
-
-	ring = &priv->tx_rings[DESC_INDEX];
-	napi_enable(&ring->napi);
-	ring->int_enable(ring);
 }
 
 static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv)
@@ -2765,13 +2822,10 @@ static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_tx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_disable(&ring->napi);
 	}
-
-	ring = &priv->tx_rings[DESC_INDEX];
-	napi_disable(&ring->napi);
 }
 
 static void bcmgenet_fini_tx_napi(struct bcmgenet_priv *priv)
@@ -2779,82 +2833,104 @@ static void bcmgenet_fini_tx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_tx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		netif_napi_del(&ring->napi);
 	}
+}
+
+static int bcmgenet_tdma_disable(struct bcmgenet_priv *priv)
+{
+	int timeout = 0;
+	u32 reg, mask;
+
+	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+	mask = (1 << (priv->hw_params->tx_queues + 1)) - 1;
+	mask = (mask << DMA_RING_BUF_EN_SHIFT) | DMA_EN;
+	reg &= ~mask;
+	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+
+	/* Check DMA status register to confirm DMA is disabled */
+	while (timeout++ < DMA_TIMEOUT_VAL) {
+		reg = bcmgenet_tdma_readl(priv, DMA_STATUS);
+		if ((reg & mask) == mask)
+			return 0;
 
-	ring = &priv->tx_rings[DESC_INDEX];
-	netif_napi_del(&ring->napi);
+		udelay(1);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static int bcmgenet_rdma_disable(struct bcmgenet_priv *priv)
+{
+	int timeout = 0;
+	u32 reg, mask;
+
+	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
+	mask = (1 << (priv->hw_params->rx_queues + 1)) - 1;
+	mask = (mask << DMA_RING_BUF_EN_SHIFT) | DMA_EN;
+	reg &= ~mask;
+	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
+
+	/* Check DMA status register to confirm DMA is disabled */
+	while (timeout++ < DMA_TIMEOUT_VAL) {
+		reg = bcmgenet_rdma_readl(priv, DMA_STATUS);
+		if ((reg & mask) == mask)
+			return 0;
+
+		udelay(1);
+	}
+
+	return -ETIMEDOUT;
 }
 
 /* Initialize Tx queues
  *
- * Queues 0-3 are priority-based, each one has 32 descriptors,
- * with queue 0 being the highest priority queue.
+ * Queues 1-4 are priority-based, each one has 32 descriptors,
+ * with queue 1 being the highest priority queue.
  *
- * Queue 16 is the default Tx queue with
- * GENET_Q16_TX_BD_CNT = 256 - 4 * 32 = 128 descriptors.
+ * Queue 0 is the default Tx queue with
+ * GENET_Q0_TX_BD_CNT = 256 - 4 * 32 = 128 descriptors.
  *
  * The transmit control block pool is then partitioned as follows:
- * - Tx queue 0 uses tx_cbs[0..31]
- * - Tx queue 1 uses tx_cbs[32..63]
- * - Tx queue 2 uses tx_cbs[64..95]
- * - Tx queue 3 uses tx_cbs[96..127]
- * - Tx queue 16 uses tx_cbs[128..255]
+ * - Tx queue 0 uses tx_cbs[0..127]
+ * - Tx queue 1 uses tx_cbs[128..159]
+ * - Tx queue 2 uses tx_cbs[160..191]
+ * - Tx queue 3 uses tx_cbs[192..223]
+ * - Tx queue 4 uses tx_cbs[224..255]
  */
 static void bcmgenet_init_tx_queues(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 i, dma_enable;
-	u32 dma_ctrl, ring_cfg;
-	u32 dma_priority[3] = {0, 0, 0};
-
-	dma_ctrl = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	dma_enable = dma_ctrl & DMA_EN;
-	dma_ctrl &= ~DMA_EN;
-	bcmgenet_tdma_writel(priv, dma_ctrl, DMA_CTRL);
-
-	dma_ctrl = 0;
-	ring_cfg = 0;
+	unsigned int start = 0, end = GENET_Q0_TX_BD_CNT;
+	u32 i, ring_mask, dma_priority[3] = {0, 0, 0};
 
 	/* Enable strict priority arbiter mode */
 	bcmgenet_tdma_writel(priv, DMA_ARBITER_SP, DMA_ARB_CTRL);
 
 	/* Initialize Tx priority queues */
-	for (i = 0; i < priv->hw_params->tx_queues; i++) {
-		bcmgenet_init_tx_ring(priv, i, priv->hw_params->tx_bds_per_q,
-				      i * priv->hw_params->tx_bds_per_q,
-				      (i + 1) * priv->hw_params->tx_bds_per_q);
-		ring_cfg |= (1 << i);
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
+	for (i = 0; i <= priv->hw_params->tx_queues; i++) {
+		bcmgenet_init_tx_ring(priv, i, end - start, start, end);
+		start = end;
+		end += priv->hw_params->tx_bds_per_q;
 		dma_priority[DMA_PRIO_REG_INDEX(i)] |=
-			((GENET_Q0_PRIORITY + i) << DMA_PRIO_REG_SHIFT(i));
+			(i ? GENET_Q1_PRIORITY : GENET_Q0_PRIORITY)
+			<< DMA_PRIO_REG_SHIFT(i);
 	}
 
-	/* Initialize Tx default queue 16 */
-	bcmgenet_init_tx_ring(priv, DESC_INDEX, GENET_Q16_TX_BD_CNT,
-			      priv->hw_params->tx_queues *
-			      priv->hw_params->tx_bds_per_q,
-			      TOTAL_DESC);
-	ring_cfg |= (1 << DESC_INDEX);
-	dma_ctrl |= (1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT));
-	dma_priority[DMA_PRIO_REG_INDEX(DESC_INDEX)] |=
-		((GENET_Q0_PRIORITY + priv->hw_params->tx_queues) <<
-		 DMA_PRIO_REG_SHIFT(DESC_INDEX));
-
 	/* Set Tx queue priorities */
 	bcmgenet_tdma_writel(priv, dma_priority[0], DMA_PRIORITY_0);
 	bcmgenet_tdma_writel(priv, dma_priority[1], DMA_PRIORITY_1);
 	bcmgenet_tdma_writel(priv, dma_priority[2], DMA_PRIORITY_2);
 
-	/* Enable Tx queues */
-	bcmgenet_tdma_writel(priv, ring_cfg, DMA_RING_CFG);
+	/* Configure Tx queues as descriptor rings */
+	ring_mask = (1 << (priv->hw_params->tx_queues + 1)) - 1;
+	bcmgenet_tdma_writel(priv, ring_mask, DMA_RING_CFG);
 
-	/* Enable Tx DMA */
-	if (dma_enable)
-		dma_ctrl |= DMA_EN;
-	bcmgenet_tdma_writel(priv, dma_ctrl, DMA_CTRL);
+	/* Enable Tx rings */
+	ring_mask <<= DMA_RING_BUF_EN_SHIFT;
+	bcmgenet_tdma_writel(priv, ring_mask, DMA_CTRL);
 }
 
 static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv)
@@ -2862,15 +2938,11 @@ static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_rx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_enable(&ring->napi);
-		ring->int_enable(ring);
+		bcmgenet_rx_ring_int_enable(ring);
 	}
-
-	ring = &priv->rx_rings[DESC_INDEX];
-	napi_enable(&ring->napi);
-	ring->int_enable(ring);
 }
 
 static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv)
@@ -2878,15 +2950,11 @@ static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_rx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_disable(&ring->napi);
 		cancel_work_sync(&ring->dim.dim.work);
 	}
-
-	ring = &priv->rx_rings[DESC_INDEX];
-	napi_disable(&ring->napi);
-	cancel_work_sync(&ring->dim.dim.work);
 }
 
 static void bcmgenet_fini_rx_napi(struct bcmgenet_priv *priv)
@@ -2894,13 +2962,10 @@ static void bcmgenet_fini_rx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_rx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		netif_napi_del(&ring->napi);
 	}
-
-	ring = &priv->rx_rings[DESC_INDEX];
-	netif_napi_del(&ring->napi);
 }
 
 /* Initialize Rx queues
@@ -2908,57 +2973,32 @@ static void bcmgenet_fini_rx_napi(struct bcmgenet_priv *priv)
  * Queues 0-15 are priority queues. Hardware Filtering Block (HFB) can be
  * used to direct traffic to these queues.
  *
- * Queue 16 is the default Rx queue with GENET_Q16_RX_BD_CNT descriptors.
+ * Queue 0 is also the default Rx queue with GENET_Q0_RX_BD_CNT descriptors.
  */
 static int bcmgenet_init_rx_queues(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 i;
-	u32 dma_enable;
-	u32 dma_ctrl;
-	u32 ring_cfg;
+	unsigned int start = 0, end = GENET_Q0_RX_BD_CNT;
+	u32 i, ring_mask;
 	int ret;
 
-	dma_ctrl = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	dma_enable = dma_ctrl & DMA_EN;
-	dma_ctrl &= ~DMA_EN;
-	bcmgenet_rdma_writel(priv, dma_ctrl, DMA_CTRL);
-
-	dma_ctrl = 0;
-	ring_cfg = 0;
-
 	/* Initialize Rx priority queues */
-	for (i = 0; i < priv->hw_params->rx_queues; i++) {
-		ret = bcmgenet_init_rx_ring(priv, i,
-					    priv->hw_params->rx_bds_per_q,
-					    i * priv->hw_params->rx_bds_per_q,
-					    (i + 1) *
-					    priv->hw_params->rx_bds_per_q);
+	for (i = 0; i <= priv->hw_params->rx_queues; i++) {
+		ret = bcmgenet_init_rx_ring(priv, i, end - start, start, end);
 		if (ret)
 			return ret;
 
-		ring_cfg |= (1 << i);
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
+		start = end;
+		end += priv->hw_params->rx_bds_per_q;
 	}
 
-	/* Initialize Rx default queue 16 */
-	ret = bcmgenet_init_rx_ring(priv, DESC_INDEX, GENET_Q16_RX_BD_CNT,
-				    priv->hw_params->rx_queues *
-				    priv->hw_params->rx_bds_per_q,
-				    TOTAL_DESC);
-	if (ret)
-		return ret;
-
-	ring_cfg |= (1 << DESC_INDEX);
-	dma_ctrl |= (1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT));
+	/* Configure Rx queues as descriptor rings */
+	ring_mask = (1 << (priv->hw_params->rx_queues + 1)) - 1;
+	bcmgenet_rdma_writel(priv, ring_mask, DMA_RING_CFG);
 
-	/* Enable rings */
-	bcmgenet_rdma_writel(priv, ring_cfg, DMA_RING_CFG);
-
-	/* Configure ring as descriptor ring and re-enable DMA if enabled */
-	if (dma_enable)
-		dma_ctrl |= DMA_EN;
-	bcmgenet_rdma_writel(priv, dma_ctrl, DMA_CTRL);
+	/* Enable Rx rings */
+	ring_mask <<= DMA_RING_BUF_EN_SHIFT;
+	bcmgenet_rdma_writel(priv, ring_mask, DMA_CTRL);
 
 	return 0;
 }
@@ -2966,26 +3006,9 @@ static int bcmgenet_init_rx_queues(struct net_device *dev)
 static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv)
 {
 	int ret = 0;
-	int timeout = 0;
-	u32 reg;
-	u32 dma_ctrl;
-	int i;
 
 	/* Disable TDMA to stop add more frames in TX DMA */
-	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg &= ~DMA_EN;
-	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
-
-	/* Check TDMA status register to confirm TDMA is disabled */
-	while (timeout++ < DMA_TIMEOUT_VAL) {
-		reg = bcmgenet_tdma_readl(priv, DMA_STATUS);
-		if (reg & DMA_DISABLED)
-			break;
-
-		udelay(1);
-	}
-
-	if (timeout == DMA_TIMEOUT_VAL) {
+	if (-ETIMEDOUT == bcmgenet_tdma_disable(priv)) {
 		netdev_warn(priv->dev, "Timed out while disabling TX DMA\n");
 		ret = -ETIMEDOUT;
 	}
@@ -2994,39 +3017,11 @@ static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv)
 	usleep_range(10000, 20000);
 
 	/* Disable RDMA */
-	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg &= ~DMA_EN;
-	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
-
-	timeout = 0;
-	/* Check RDMA status register to confirm RDMA is disabled */
-	while (timeout++ < DMA_TIMEOUT_VAL) {
-		reg = bcmgenet_rdma_readl(priv, DMA_STATUS);
-		if (reg & DMA_DISABLED)
-			break;
-
-		udelay(1);
-	}
-
-	if (timeout == DMA_TIMEOUT_VAL) {
+	if (-ETIMEDOUT == bcmgenet_rdma_disable(priv)) {
 		netdev_warn(priv->dev, "Timed out while disabling RX DMA\n");
 		ret = -ETIMEDOUT;
 	}
 
-	dma_ctrl = 0;
-	for (i = 0; i < priv->hw_params->rx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
-
-	dma_ctrl = 0;
-	for (i = 0; i < priv->hw_params->tx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
-
 	return ret;
 }
 
@@ -3038,32 +3033,53 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
 	bcmgenet_fini_rx_napi(priv);
 	bcmgenet_fini_tx_napi(priv);
 
-	for (i = 0; i < priv->num_tx_bds; i++)
-		dev_kfree_skb(bcmgenet_free_tx_cb(&priv->pdev->dev,
-						  priv->tx_cbs + i));
-
-	for (i = 0; i < priv->hw_params->tx_queues; i++) {
-		txq = netdev_get_tx_queue(priv->dev, priv->tx_rings[i].queue);
+	for (i = 0; i <= priv->hw_params->tx_queues; i++) {
+		txq = netdev_get_tx_queue(priv->dev, i);
 		netdev_tx_reset_queue(txq);
 	}
 
-	txq = netdev_get_tx_queue(priv->dev, priv->tx_rings[DESC_INDEX].queue);
-	netdev_tx_reset_queue(txq);
-
 	bcmgenet_free_rx_buffers(priv);
 	kfree(priv->rx_cbs);
 	kfree(priv->tx_cbs);
 }
 
 /* init_edma: Initialize DMA control register */
-static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
+static int bcmgenet_init_dma(struct bcmgenet_priv *priv, bool flush_rx)
 {
-	int ret;
-	unsigned int i;
 	struct enet_cb *cb;
+	unsigned int i;
+	int ret;
+	u32 reg;
 
 	netif_dbg(priv, hw, priv->dev, "%s\n", __func__);
 
+	/* Disable TX DMA */
+	ret = bcmgenet_tdma_disable(priv);
+	if (ret) {
+		netdev_err(priv->dev, "failed to halt Tx DMA\n");
+		return ret;
+	}
+
+	/* Disable RX DMA */
+	ret = bcmgenet_rdma_disable(priv);
+	if (ret) {
+		netdev_err(priv->dev, "failed to halt Rx DMA\n");
+		return ret;
+	}
+
+	/* Flush TX queues */
+	bcmgenet_umac_writel(priv, 1, UMAC_TX_FLUSH);
+	udelay(10);
+	bcmgenet_umac_writel(priv, 0, UMAC_TX_FLUSH);
+
+	if (flush_rx) {
+		reg = bcmgenet_rbuf_ctrl_get(priv);
+		bcmgenet_rbuf_ctrl_set(priv, reg | BIT(0));
+		udelay(10);
+		bcmgenet_rbuf_ctrl_set(priv, reg);
+		udelay(10);
+	}
+
 	/* Initialize common Rx ring structures */
 	priv->rx_bds = priv->base + priv->hw_params->rdma_offset;
 	priv->num_rx_bds = TOTAL_DESC;
@@ -3113,6 +3129,15 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
 	/* Initialize Tx queues */
 	bcmgenet_init_tx_queues(priv->dev);
 
+	/* Enable RX/TX DMA */
+	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
+	reg |= DMA_EN;
+	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
+
+	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+	reg |= DMA_EN;
+	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+
 	return 0;
 }
 
@@ -3142,7 +3167,7 @@ static void bcmgenet_irq_task(struct work_struct *work)
 
 }
 
-/* bcmgenet_isr1: handle Rx and Tx priority queues */
+/* bcmgenet_isr1: handle Rx and Tx queues */
 static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 {
 	struct bcmgenet_priv *priv = dev_id;
@@ -3161,7 +3186,7 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 		  "%s: IRQ=0x%x\n", __func__, status);
 
 	/* Check Rx priority queue interrupts */
-	for (index = 0; index < priv->hw_params->rx_queues; index++) {
+	for (index = 0; index <= priv->hw_params->rx_queues; index++) {
 		if (!(status & BIT(UMAC_IRQ1_RX_INTR_SHIFT + index)))
 			continue;
 
@@ -3169,20 +3194,20 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 		rx_ring->dim.event_ctr++;
 
 		if (likely(napi_schedule_prep(&rx_ring->napi))) {
-			rx_ring->int_disable(rx_ring);
+			bcmgenet_rx_ring_int_disable(rx_ring);
 			__napi_schedule_irqoff(&rx_ring->napi);
 		}
 	}
 
 	/* Check Tx priority queue interrupts */
-	for (index = 0; index < priv->hw_params->tx_queues; index++) {
+	for (index = 0; index <= priv->hw_params->tx_queues; index++) {
 		if (!(status & BIT(index)))
 			continue;
 
 		tx_ring = &priv->tx_rings[index];
 
 		if (likely(napi_schedule_prep(&tx_ring->napi))) {
-			tx_ring->int_disable(tx_ring);
+			bcmgenet_tx_ring_int_disable(tx_ring);
 			__napi_schedule_irqoff(&tx_ring->napi);
 		}
 	}
@@ -3190,12 +3215,10 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-/* bcmgenet_isr0: handle Rx and Tx default queues + other stuff */
+/* bcmgenet_isr0: handle other stuff */
 static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 {
 	struct bcmgenet_priv *priv = dev_id;
-	struct bcmgenet_rx_ring *rx_ring;
-	struct bcmgenet_tx_ring *tx_ring;
 	unsigned int status;
 	unsigned long flags;
 
@@ -3209,29 +3232,8 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 	netif_dbg(priv, intr, priv->dev,
 		  "IRQ=0x%x\n", status);
 
-	if (status & UMAC_IRQ_RXDMA_DONE) {
-		rx_ring = &priv->rx_rings[DESC_INDEX];
-		rx_ring->dim.event_ctr++;
-
-		if (likely(napi_schedule_prep(&rx_ring->napi))) {
-			rx_ring->int_disable(rx_ring);
-			__napi_schedule_irqoff(&rx_ring->napi);
-		}
-	}
-
-	if (status & UMAC_IRQ_TXDMA_DONE) {
-		tx_ring = &priv->tx_rings[DESC_INDEX];
-
-		if (likely(napi_schedule_prep(&tx_ring->napi))) {
-			tx_ring->int_disable(tx_ring);
-			__napi_schedule_irqoff(&tx_ring->napi);
-		}
-	}
-
-	if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
-		status & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
+	if (bcmgenet_has_mdio_intr(priv) && status & UMAC_IRQ_MDIO_EVENT)
 		wake_up(&priv->wq);
-	}
 
 	/* all other interested interrupts handled in bottom half */
 	status &= (UMAC_IRQ_LINK_EVENT | UMAC_IRQ_PHY_DET_R);
@@ -3285,56 +3287,6 @@ static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv,
 	put_unaligned_be16(addr_tmp, &addr[4]);
 }
 
-/* Returns a reusable dma control register value */
-static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv, bool flush_rx)
-{
-	unsigned int i;
-	u32 reg;
-	u32 dma_ctrl;
-
-	/* disable DMA */
-	dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
-	for (i = 0; i < priv->hw_params->tx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
-
-	dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
-	for (i = 0; i < priv->hw_params->rx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
-
-	bcmgenet_umac_writel(priv, 1, UMAC_TX_FLUSH);
-	udelay(10);
-	bcmgenet_umac_writel(priv, 0, UMAC_TX_FLUSH);
-
-	if (flush_rx) {
-		reg = bcmgenet_rbuf_ctrl_get(priv);
-		bcmgenet_rbuf_ctrl_set(priv, reg | BIT(0));
-		udelay(10);
-		bcmgenet_rbuf_ctrl_set(priv, reg);
-		udelay(10);
-	}
-
-	return dma_ctrl;
-}
-
-static void bcmgenet_enable_dma(struct bcmgenet_priv *priv, u32 dma_ctrl)
-{
-	u32 reg;
-
-	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg |= dma_ctrl;
-	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
-
-	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg |= dma_ctrl;
-	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
-}
-
 static void bcmgenet_netif_start(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
@@ -3358,7 +3310,6 @@ static void bcmgenet_netif_start(struct net_device *dev)
 static int bcmgenet_open(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	unsigned long dma_ctrl;
 	int ret;
 
 	netif_dbg(priv, ifup, dev, "bcmgenet_open\n");
@@ -3384,22 +3335,16 @@ static int bcmgenet_open(struct net_device *dev)
 
 	bcmgenet_set_hw_addr(priv, dev->dev_addr);
 
-	/* Disable RX/TX DMA and flush TX and RX queues */
-	dma_ctrl = bcmgenet_dma_disable(priv, true);
+	/* HFB init */
+	bcmgenet_hfb_init(priv);
 
 	/* Reinitialize TDMA and RDMA and SW housekeeping */
-	ret = bcmgenet_init_dma(priv);
+	ret = bcmgenet_init_dma(priv, true);
 	if (ret) {
 		netdev_err(dev, "failed to initialize DMA\n");
 		goto err_clk_disable;
 	}
 
-	/* Always enable ring 16 - descriptor ring */
-	bcmgenet_enable_dma(priv, dma_ctrl);
-
-	/* HFB init */
-	bcmgenet_hfb_init(priv);
-
 	ret = request_irq(priv->irq0, bcmgenet_isr0, IRQF_SHARED,
 			  dev->name, priv);
 	if (ret < 0) {
@@ -3446,19 +3391,21 @@ static void bcmgenet_netif_stop(struct net_device *dev, bool stop_phy)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
-	bcmgenet_disable_tx_napi(priv);
 	netif_tx_disable(dev);
 
 	/* Disable MAC receive */
+	bcmgenet_hfb_reg_writel(priv, 0, HFB_CTRL);
 	umac_enable_set(priv, CMD_RX_EN, false);
 
+	if (stop_phy)
+		phy_stop(dev->phydev);
+
 	bcmgenet_dma_teardown(priv);
 
 	/* Disable MAC transmit. TX DMA disabled must be done before this */
 	umac_enable_set(priv, CMD_TX_EN, false);
 
-	if (stop_phy)
-		phy_stop(dev->phydev);
+	bcmgenet_disable_tx_napi(priv);
 	bcmgenet_disable_rx_napi(priv);
 	bcmgenet_intr_disable(priv);
 
@@ -3506,16 +3453,11 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 	if (!netif_msg_tx_err(priv))
 		return;
 
-	txq = netdev_get_tx_queue(priv->dev, ring->queue);
+	txq = netdev_get_tx_queue(priv->dev, ring->index);
 
 	spin_lock(&ring->lock);
-	if (ring->index == DESC_INDEX) {
-		intsts = ~bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
-		intmsk = UMAC_IRQ_TXDMA_DONE | UMAC_IRQ_TXDMA_MBDONE;
-	} else {
-		intsts = ~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS);
-		intmsk = 1 << ring->index;
-	}
+	intsts = ~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS);
+	intmsk = 1 << ring->index;
 	c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX);
 	p_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_PROD_INDEX);
 	txq_stopped = netif_tx_queue_stopped(txq);
@@ -3529,7 +3471,7 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 		  "(sw)c_index: %d (hw)c_index: %d\n"
 		  "(sw)clean_p: %d (sw)write_p: %d\n"
 		  "(sw)cb_ptr: %d (sw)end_ptr: %d\n",
-		  ring->index, ring->queue,
+		  ring->index, ring->index,
 		  txq_stopped ? "stopped" : "active",
 		  intsts & intmsk ? "enabled" : "disabled",
 		  free_bds, ring->size,
@@ -3542,30 +3484,25 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 static void bcmgenet_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 int0_enable = 0;
 	u32 int1_enable = 0;
 	unsigned int q;
 
 	netif_dbg(priv, tx_err, dev, "bcmgenet_timeout\n");
 
-	for (q = 0; q < priv->hw_params->tx_queues; q++)
+	for (q = 0; q <= priv->hw_params->tx_queues; q++)
 		bcmgenet_dump_tx_queue(&priv->tx_rings[q]);
-	bcmgenet_dump_tx_queue(&priv->tx_rings[DESC_INDEX]);
 
 	bcmgenet_tx_reclaim_all(dev);
 
-	for (q = 0; q < priv->hw_params->tx_queues; q++)
+	for (q = 0; q <= priv->hw_params->tx_queues; q++)
 		int1_enable |= (1 << q);
 
-	int0_enable = UMAC_IRQ_TXDMA_DONE;
-
 	/* Re-enable TX interrupts if disabled */
-	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
 	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
 
 	netif_trans_update(dev);
 
-	dev->stats.tx_errors++;
+	BCMGENET_STATS64_INC((&priv->tx_rings[txqueue].stats64), errors);
 
 	netif_tx_wake_all_queues(dev);
 }
@@ -3654,47 +3591,72 @@ static int bcmgenet_set_mac_addr(struct net_device *dev, void *p)
 	return 0;
 }
 
-static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev)
+static void bcmgenet_get_stats64(struct net_device *dev,
+				 struct rtnl_link_stats64 *stats)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	unsigned long tx_bytes = 0, tx_packets = 0;
-	unsigned long rx_bytes = 0, rx_packets = 0;
-	unsigned long rx_errors = 0, rx_dropped = 0;
-	struct bcmgenet_tx_ring *tx_ring;
-	struct bcmgenet_rx_ring *rx_ring;
+	struct bcmgenet_tx_stats64 *tx_stats;
+	struct bcmgenet_rx_stats64 *rx_stats;
+	u64 rx_length_errors, rx_over_errors;
+	u64 rx_missed, rx_fragmented_errors;
+	u64 rx_crc_errors, rx_frame_errors;
+	u64 tx_errors, tx_dropped;
+	u64 rx_errors, rx_dropped;
+	u64 tx_bytes, tx_packets;
+	u64 rx_bytes, rx_packets;
+	unsigned int start;
 	unsigned int q;
-
-	for (q = 0; q < priv->hw_params->tx_queues; q++) {
-		tx_ring = &priv->tx_rings[q];
-		tx_bytes += tx_ring->bytes;
-		tx_packets += tx_ring->packets;
+	u64 multicast;
+
+	for (q = 0; q <= priv->hw_params->tx_queues; q++) {
+		tx_stats = &priv->tx_rings[q].stats64;
+		do {
+			start = u64_stats_fetch_begin(&tx_stats->syncp);
+			tx_bytes = u64_stats_read(&tx_stats->bytes);
+			tx_packets = u64_stats_read(&tx_stats->packets);
+			tx_errors = u64_stats_read(&tx_stats->errors);
+			tx_dropped = u64_stats_read(&tx_stats->dropped);
+		} while (u64_stats_fetch_retry(&tx_stats->syncp, start));
+
+		stats->tx_bytes += tx_bytes;
+		stats->tx_packets += tx_packets;
+		stats->tx_errors += tx_errors;
+		stats->tx_dropped += tx_dropped;
 	}
-	tx_ring = &priv->tx_rings[DESC_INDEX];
-	tx_bytes += tx_ring->bytes;
-	tx_packets += tx_ring->packets;
 
-	for (q = 0; q < priv->hw_params->rx_queues; q++) {
-		rx_ring = &priv->rx_rings[q];
-
-		rx_bytes += rx_ring->bytes;
-		rx_packets += rx_ring->packets;
-		rx_errors += rx_ring->errors;
-		rx_dropped += rx_ring->dropped;
+	for (q = 0; q <= priv->hw_params->rx_queues; q++) {
+		rx_stats = &priv->rx_rings[q].stats64;
+		do {
+			start = u64_stats_fetch_begin(&rx_stats->syncp);
+			rx_bytes = u64_stats_read(&rx_stats->bytes);
+			rx_packets = u64_stats_read(&rx_stats->packets);
+			rx_errors = u64_stats_read(&rx_stats->errors);
+			rx_dropped = u64_stats_read(&rx_stats->dropped);
+			rx_missed = u64_stats_read(&rx_stats->missed);
+			rx_length_errors = u64_stats_read(&rx_stats->length_errors);
+			rx_over_errors = u64_stats_read(&rx_stats->over_errors);
+			rx_crc_errors = u64_stats_read(&rx_stats->crc_errors);
+			rx_frame_errors = u64_stats_read(&rx_stats->frame_errors);
+			rx_fragmented_errors = u64_stats_read(&rx_stats->fragmented_errors);
+			multicast = u64_stats_read(&rx_stats->multicast);
+		} while (u64_stats_fetch_retry(&rx_stats->syncp, start));
+
+		rx_errors += rx_length_errors;
+		rx_errors += rx_crc_errors;
+		rx_errors += rx_frame_errors;
+		rx_errors += rx_fragmented_errors;
+
+		stats->rx_bytes += rx_bytes;
+		stats->rx_packets += rx_packets;
+		stats->rx_errors += rx_errors;
+		stats->rx_dropped += rx_dropped;
+		stats->rx_missed_errors += rx_missed;
+		stats->rx_length_errors += rx_length_errors;
+		stats->rx_over_errors += rx_over_errors;
+		stats->rx_crc_errors += rx_crc_errors;
+		stats->rx_frame_errors += rx_frame_errors;
+		stats->multicast += multicast;
 	}
-	rx_ring = &priv->rx_rings[DESC_INDEX];
-	rx_bytes += rx_ring->bytes;
-	rx_packets += rx_ring->packets;
-	rx_errors += rx_ring->errors;
-	rx_dropped += rx_ring->dropped;
-
-	dev->stats.tx_bytes = tx_bytes;
-	dev->stats.tx_packets = tx_packets;
-	dev->stats.rx_bytes = rx_bytes;
-	dev->stats.rx_packets = rx_packets;
-	dev->stats.rx_errors = rx_errors;
-	dev->stats.rx_missed_errors = rx_errors;
-	dev->stats.rx_dropped = rx_dropped;
-	return &dev->stats;
 }
 
 static int bcmgenet_change_carrier(struct net_device *dev, bool new_carrier)
@@ -3722,132 +3684,113 @@ static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_set_mac_address	= bcmgenet_set_mac_addr,
 	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_set_features	= bcmgenet_set_features,
-	.ndo_get_stats		= bcmgenet_get_stats,
+	.ndo_get_stats64	= bcmgenet_get_stats64,
 	.ndo_change_carrier	= bcmgenet_change_carrier,
 };
 
-/* Array of GENET hardware parameters/characteristics */
-static struct bcmgenet_hw_params bcmgenet_hw_params[] = {
-	[GENET_V1] = {
-		.tx_queues = 0,
-		.tx_bds_per_q = 0,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 16,
-		.bp_in_mask = 0xffff,
-		.hfb_filter_cnt = 16,
-		.qtag_mask = 0x1F,
-		.hfb_offset = 0x1000,
-		.rdma_offset = 0x2000,
-		.tdma_offset = 0x3000,
-		.words_per_bd = 2,
-	},
-	[GENET_V2] = {
-		.tx_queues = 4,
-		.tx_bds_per_q = 32,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 16,
-		.bp_in_mask = 0xffff,
-		.hfb_filter_cnt = 16,
-		.qtag_mask = 0x1F,
-		.tbuf_offset = 0x0600,
-		.hfb_offset = 0x1000,
-		.hfb_reg_offset = 0x2000,
-		.rdma_offset = 0x3000,
-		.tdma_offset = 0x4000,
-		.words_per_bd = 2,
-		.flags = GENET_HAS_EXT,
-	},
-	[GENET_V3] = {
-		.tx_queues = 4,
-		.tx_bds_per_q = 32,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 17,
-		.bp_in_mask = 0x1ffff,
-		.hfb_filter_cnt = 48,
-		.hfb_filter_size = 128,
-		.qtag_mask = 0x3F,
-		.tbuf_offset = 0x0600,
-		.hfb_offset = 0x8000,
-		.hfb_reg_offset = 0xfc00,
-		.rdma_offset = 0x10000,
-		.tdma_offset = 0x11000,
-		.words_per_bd = 2,
-		.flags = GENET_HAS_EXT | GENET_HAS_MDIO_INTR |
-			 GENET_HAS_MOCA_LINK_DET,
-	},
-	[GENET_V4] = {
-		.tx_queues = 4,
-		.tx_bds_per_q = 32,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 17,
-		.bp_in_mask = 0x1ffff,
-		.hfb_filter_cnt = 48,
-		.hfb_filter_size = 128,
-		.qtag_mask = 0x3F,
-		.tbuf_offset = 0x0600,
-		.hfb_offset = 0x8000,
-		.hfb_reg_offset = 0xfc00,
-		.rdma_offset = 0x2000,
-		.tdma_offset = 0x4000,
-		.words_per_bd = 3,
-		.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
-			 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
-	},
-	[GENET_V5] = {
-		.tx_queues = 4,
-		.tx_bds_per_q = 32,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 17,
-		.bp_in_mask = 0x1ffff,
-		.hfb_filter_cnt = 48,
-		.hfb_filter_size = 128,
-		.qtag_mask = 0x3F,
-		.tbuf_offset = 0x0600,
-		.hfb_offset = 0x8000,
-		.hfb_reg_offset = 0xfc00,
-		.rdma_offset = 0x2000,
-		.tdma_offset = 0x4000,
-		.words_per_bd = 3,
-		.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
-			 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
-	},
+/* GENET hardware parameters/characteristics */
+static const struct bcmgenet_hw_params bcmgenet_hw_params_v1 = {
+	.tx_queues = 0,
+	.tx_bds_per_q = 0,
+	.rx_queues = 0,
+	.rx_bds_per_q = 0,
+	.bp_in_en_shift = 16,
+	.bp_in_mask = 0xffff,
+	.hfb_filter_cnt = 16,
+	.hfb_filter_size = 64,
+	.qtag_mask = 0x1F,
+	.hfb_offset = 0x1000,
+	.hfb_reg_offset = GENET_RBUF_OFF + RBUF_HFB_CTRL_V1,
+	.rdma_offset = 0x2000,
+	.tdma_offset = 0x3000,
+	.words_per_bd = 2,
+};
+
+static const struct bcmgenet_hw_params bcmgenet_hw_params_v2 = {
+	.tx_queues = 4,
+	.tx_bds_per_q = 32,
+	.rx_queues = 0,
+	.rx_bds_per_q = 0,
+	.bp_in_en_shift = 16,
+	.bp_in_mask = 0xffff,
+	.hfb_filter_cnt = 16,
+	.hfb_filter_size = 64,
+	.qtag_mask = 0x1F,
+	.tbuf_offset = 0x0600,
+	.hfb_offset = 0x1000,
+	.hfb_reg_offset = 0x2000,
+	.rdma_offset = 0x3000,
+	.tdma_offset = 0x4000,
+	.words_per_bd = 2,
+};
+
+static const struct bcmgenet_hw_params bcmgenet_hw_params_v3 = {
+	.tx_queues = 4,
+	.tx_bds_per_q = 32,
+	.rx_queues = 0,
+	.rx_bds_per_q = 0,
+	.bp_in_en_shift = 17,
+	.bp_in_mask = 0x1ffff,
+	.hfb_filter_cnt = 48,
+	.hfb_filter_size = 128,
+	.qtag_mask = 0x3F,
+	.tbuf_offset = 0x0600,
+	.hfb_offset = 0x8000,
+	.hfb_reg_offset = 0xfc00,
+	.rdma_offset = 0x10000,
+	.tdma_offset = 0x11000,
+	.words_per_bd = 2,
+};
+
+static const struct bcmgenet_hw_params bcmgenet_hw_params_v4 = {
+	.tx_queues = 4,
+	.tx_bds_per_q = 32,
+	.rx_queues = 0,
+	.rx_bds_per_q = 0,
+	.bp_in_en_shift = 17,
+	.bp_in_mask = 0x1ffff,
+	.hfb_filter_cnt = 48,
+	.hfb_filter_size = 128,
+	.qtag_mask = 0x3F,
+	.tbuf_offset = 0x0600,
+	.hfb_offset = 0x8000,
+	.hfb_reg_offset = 0xfc00,
+	.rdma_offset = 0x2000,
+	.tdma_offset = 0x4000,
+	.words_per_bd = 3,
 };
 
 /* Infer hardware parameters from the detected GENET version */
 static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 {
-	struct bcmgenet_hw_params *params;
+	const struct bcmgenet_hw_params *params;
 	u32 reg;
 	u8 major;
 	u16 gphy_rev;
 
-	if (GENET_IS_V5(priv) || GENET_IS_V4(priv)) {
-		bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
-		genet_dma_ring_regs = genet_dma_ring_regs_v4;
-	} else if (GENET_IS_V3(priv)) {
+	/* default to latest values */
+	params = &bcmgenet_hw_params_v4;
+	bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
+	genet_dma_ring_regs = genet_dma_ring_regs_v4;
+	if (GENET_IS_V3(priv)) {
+		params = &bcmgenet_hw_params_v3;
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 	} else if (GENET_IS_V2(priv)) {
+		params = &bcmgenet_hw_params_v2;
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v2;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 	} else if (GENET_IS_V1(priv)) {
+		params = &bcmgenet_hw_params_v1;
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v1;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 	}
-
-	/* enum genet_version starts at 1 */
-	priv->hw_params = &bcmgenet_hw_params[priv->version];
-	params = priv->hw_params;
+	priv->hw_params = params;
 
 	/* Read GENET HW version */
 	reg = bcmgenet_sys_readl(priv, SYS_REV_CTRL);
 	major = (reg >> 24 & 0x0f);
-	if (major == 6)
+	if (major == 6 || major == 7)
 		major = 5;
 	else if (major == 5)
 		major = 4;
@@ -3898,7 +3841,7 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 	}
 
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
-	if (!(params->flags & GENET_HAS_40BITS))
+	if (!bcmgenet_has_40bits(priv))
 		pr_warn("GENET does not support 40-bits PA\n");
 #endif
 
@@ -3923,7 +3866,7 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 struct bcmgenet_plat_data {
 	enum bcmgenet_version version;
 	u32 dma_max_burst_length;
-	bool ephy_16nm;
+	u32 flags;
 };
 
 static const struct bcmgenet_plat_data v1_plat_data = {
@@ -3934,32 +3877,43 @@ static const struct bcmgenet_plat_data v1_plat_data = {
 static const struct bcmgenet_plat_data v2_plat_data = {
 	.version = GENET_V2,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
+	.flags = GENET_HAS_EXT,
 };
 
 static const struct bcmgenet_plat_data v3_plat_data = {
 	.version = GENET_V3,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
+	.flags = GENET_HAS_EXT | GENET_HAS_MDIO_INTR |
+		 GENET_HAS_MOCA_LINK_DET,
 };
 
 static const struct bcmgenet_plat_data v4_plat_data = {
 	.version = GENET_V4,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
+	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
 };
 
 static const struct bcmgenet_plat_data v5_plat_data = {
 	.version = GENET_V5,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
+	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
 };
 
 static const struct bcmgenet_plat_data bcm2711_plat_data = {
 	.version = GENET_V5,
 	.dma_max_burst_length = 0x08,
+	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
 };
 
 static const struct bcmgenet_plat_data bcm7712_plat_data = {
 	.version = GENET_V5,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
-	.ephy_16nm = true,
+	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET |
+		 GENET_HAS_EPHY_16NM,
 };
 
 static const struct of_device_id bcmgenet_match[] = {
@@ -3976,7 +3930,6 @@ MODULE_DEVICE_TABLE(of, bcmgenet_match);
 
 static int bcmgenet_probe(struct platform_device *pdev)
 {
-	struct bcmgenet_platform_data *pd = pdev->dev.platform_data;
 	const struct bcmgenet_plat_data *pdata;
 	struct bcmgenet_priv *priv;
 	struct net_device *dev;
@@ -4036,6 +3989,8 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	dev->hw_features |= dev->features;
 	dev->vlan_features |= dev->features;
 
+	netdev_sw_irq_coalesce_default_on(dev);
+
 	/* Request the WOL interrupt and advertise suspend if available */
 	priv->wol_irq_disabled = true;
 	if (priv->wol_irq > 0) {
@@ -4057,10 +4012,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	if (pdata) {
 		priv->version = pdata->version;
 		priv->dma_max_burst_length = pdata->dma_max_burst_length;
-		priv->ephy_16nm = pdata->ephy_16nm;
-	} else {
-		priv->version = pd->genet_version;
-		priv->dma_max_burst_length = DMA_MAX_BURST_LENGTH;
+		priv->flags = pdata->flags;
 	}
 
 	priv->clk = devm_clk_get_optional(&priv->pdev->dev, "enet");
@@ -4077,7 +4029,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	bcmgenet_set_hw_params(priv);
 
 	err = -EIO;
-	if (priv->hw_params->flags & GENET_HAS_40BITS)
+	if (bcmgenet_has_40bits(priv))
 		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40));
 	if (err)
 		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
@@ -4110,16 +4062,13 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	if (device_get_phy_mode(&pdev->dev) == PHY_INTERFACE_MODE_INTERNAL)
 		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
 
-	if (pd && !IS_ERR_OR_NULL(pd->mac_address))
-		eth_hw_addr_set(dev, pd->mac_address);
-	else
-		if (device_get_ethdev_address(&pdev->dev, dev))
-			if (has_acpi_companion(&pdev->dev)) {
-				u8 addr[ETH_ALEN];
+	if (device_get_ethdev_address(&pdev->dev, dev))
+		if (has_acpi_companion(&pdev->dev)) {
+			u8 addr[ETH_ALEN];
 
-				bcmgenet_get_hw_addr(priv, addr);
-				eth_hw_addr_set(dev, addr);
-			}
+			bcmgenet_get_hw_addr(priv, addr);
+			eth_hw_addr_set(dev, addr);
+		}
 
 	if (!is_valid_ether_addr(dev->dev_addr)) {
 		dev_warn(&pdev->dev, "using random Ethernet MAC\n");
@@ -4132,16 +4081,19 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	if (err)
 		goto err_clk_disable;
 
-	/* setup number of real queues  + 1 (GENET_V1 has 0 hardware queues
-	 * just the ring 16 descriptor based TX
-	 */
+	/* setup number of real queues + 1 */
 	netif_set_real_num_tx_queues(priv->dev, priv->hw_params->tx_queues + 1);
 	netif_set_real_num_rx_queues(priv->dev, priv->hw_params->rx_queues + 1);
 
 	/* Set default coalescing parameters */
-	for (i = 0; i < priv->hw_params->rx_queues; i++)
+	for (i = 0; i <= priv->hw_params->rx_queues; i++)
 		priv->rx_rings[i].rx_max_coalesced_frames = 1;
-	priv->rx_rings[DESC_INDEX].rx_max_coalesced_frames = 1;
+
+	/* Initialize u64 stats seq counter for 32bit machines */
+	for (i = 0; i <= priv->hw_params->rx_queues; i++)
+		u64_stats_init(&priv->rx_rings[i].stats64.syncp);
+	for (i = 0; i <= priv->hw_params->tx_queues; i++)
+		u64_stats_init(&priv->tx_rings[i].stats64.syncp);
 
 	/* libphy will determine the link state */
 	netif_carrier_off(dev);
@@ -4205,9 +4157,22 @@ static int bcmgenet_resume_noirq(struct device *d)
 		reg = bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT);
 		if (reg & UMAC_IRQ_WAKE_EVENT)
 			pm_wakeup_event(&priv->pdev->dev, 0);
+
+		/* From WOL-enabled suspend, switch to regular clock */
+		if (!bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC))
+			return 0;
+
+		/* Failed so fall through to reset MAC */
 	}
 
-	bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_WAKE_EVENT, INTRL2_CPU_CLEAR);
+	/* If this is an internal GPHY, power it back on now, before UniMAC is
+	 * brought out of reset as absolutely no UniMAC activity is allowed
+	 */
+	if (priv->internal_phy)
+		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
+
+	/* take MAC out of reset */
+	bcmgenet_umac_reset(priv);
 
 	return 0;
 }
@@ -4217,23 +4182,46 @@ static int bcmgenet_resume(struct device *d)
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct bcmgenet_rxnfc_rule *rule;
-	unsigned long dma_ctrl;
 	int ret;
+	u32 reg;
 
 	if (!netif_running(dev))
 		return 0;
 
-	/* From WOL-enabled suspend, switch to regular clock */
-	if (device_may_wakeup(d) && priv->wolopts)
-		bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
-
-	/* If this is an internal GPHY, power it back on now, before UniMAC is
-	 * brought out of reset as absolutely no UniMAC activity is allowed
-	 */
-	if (priv->internal_phy)
-		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
-
-	bcmgenet_umac_reset(priv);
+	if (device_may_wakeup(d) && priv->wolopts) {
+		reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+		if (reg & CMD_RX_EN) {
+			/* Successfully exited WoL, just resume data flows */
+			list_for_each_entry(rule, &priv->rxnfc_list, list)
+				if (rule->state == BCMGENET_RXNFC_STATE_ENABLED)
+					bcmgenet_hfb_enable_filter(priv,
+							rule->fs.location + 1);
+			bcmgenet_hfb_enable_filter(priv, 0);
+			bcmgenet_set_rx_mode(dev);
+			bcmgenet_enable_rx_napi(priv);
+
+			/* Reinitialize Tx flows */
+			bcmgenet_tdma_disable(priv);
+			bcmgenet_init_tx_queues(priv->dev);
+			reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+			reg |= DMA_EN;
+			bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+			bcmgenet_enable_tx_napi(priv);
+
+			bcmgenet_link_intr_enable(priv);
+			phy_start_machine(dev->phydev);
+
+			netif_device_attach(dev);
+			enable_irq(priv->irq1);
+			return 0;
+		}
+		/* MAC was reset so complete bcmgenet_netif_stop() */
+		umac_enable_set(priv, CMD_RX_EN | CMD_TX_EN, false);
+		bcmgenet_rdma_disable(priv);
+		bcmgenet_intr_disable(priv);
+		bcmgenet_fini_dma(priv);
+		enable_irq(priv->irq1);
+	}
 
 	init_umac(priv);
 
@@ -4254,19 +4242,13 @@ static int bcmgenet_resume(struct device *d)
 		if (rule->state != BCMGENET_RXNFC_STATE_UNUSED)
 			bcmgenet_hfb_create_rxnfc_filter(priv, rule);
 
-	/* Disable RX/TX DMA and flush TX queues */
-	dma_ctrl = bcmgenet_dma_disable(priv, false);
-
 	/* Reinitialize TDMA and RDMA and SW housekeeping */
-	ret = bcmgenet_init_dma(priv);
+	ret = bcmgenet_init_dma(priv, false);
 	if (ret) {
 		netdev_err(dev, "failed to initialize DMA\n");
 		goto out_clk_disable;
 	}
 
-	/* Always enable ring 16 - descriptor ring */
-	bcmgenet_enable_dma(priv, dma_ctrl);
-
 	if (!device_may_wakeup(d))
 		phy_resume(dev->phydev);
 
@@ -4287,19 +4269,52 @@ static int bcmgenet_suspend(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct bcmgenet_rxnfc_rule *rule;
+	u32 reg, hfb_enable = 0;
 
 	if (!netif_running(dev))
 		return 0;
 
 	netif_device_detach(dev);
 
-	bcmgenet_netif_stop(dev, true);
+	if (device_may_wakeup(d) && priv->wolopts) {
+		netif_tx_disable(dev);
+
+		/* Suspend non-wake Rx data flows */
+		if (priv->wolopts & WAKE_FILTER)
+			list_for_each_entry(rule, &priv->rxnfc_list, list)
+				if (rule->fs.ring_cookie == RX_CLS_FLOW_WAKE &&
+				    rule->state == BCMGENET_RXNFC_STATE_ENABLED)
+					hfb_enable |= 1 << rule->fs.location;
+		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+		if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) {
+			reg &= ~RBUF_HFB_FILTER_EN_MASK;
+			reg |= hfb_enable << (RBUF_HFB_FILTER_EN_SHIFT + 1);
+		} else {
+			bcmgenet_hfb_reg_writel(priv, hfb_enable << 1,
+						HFB_FLT_ENABLE_V3PLUS + 4);
+		}
+		if (!hfb_enable)
+			reg &= ~RBUF_HFB_EN;
+		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
 
-	if (!device_may_wakeup(d))
-		phy_suspend(dev->phydev);
+		/* Clear any old filter matches so only new matches wake */
+		bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
+		bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
 
-	/* Disable filtering */
-	bcmgenet_hfb_reg_writel(priv, 0, HFB_CTRL);
+		if (-ETIMEDOUT == bcmgenet_tdma_disable(priv))
+			netdev_warn(priv->dev,
+				    "Timed out while disabling TX DMA\n");
+
+		bcmgenet_disable_tx_napi(priv);
+		bcmgenet_disable_rx_napi(priv);
+		disable_irq(priv->irq1);
+		bcmgenet_tx_reclaim_all(dev);
+		bcmgenet_fini_tx_napi(priv);
+	} else {
+		/* Teardown the interface */
+		bcmgenet_netif_stop(dev, true);
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 43b923c48b14..5ec3979779ec 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (c) 2014-2024 Broadcom
+ * Copyright (c) 2014-2025 Broadcom
  */
 
 #ifndef __BCMGENET_H__
@@ -18,6 +18,9 @@
 
 #include "../unimac.h"
 
+/* Maximum number of hardware queues, downsized if needed */
+#define GENET_MAX_MQ_CNT	4
+
 /* total number of Buffer Descriptors, same for Rx/Tx */
 #define TOTAL_DESC				256
 
@@ -152,6 +155,30 @@ struct bcmgenet_mib_counters {
 	u32	tx_realloc_tsb_failed;
 };
 
+struct bcmgenet_tx_stats64 {
+	struct u64_stats_sync syncp;
+	u64_stats_t	packets;
+	u64_stats_t	bytes;
+	u64_stats_t	errors;
+	u64_stats_t	dropped;
+};
+
+struct bcmgenet_rx_stats64 {
+	struct u64_stats_sync syncp;
+	u64_stats_t	bytes;
+	u64_stats_t	packets;
+	u64_stats_t	errors;
+	u64_stats_t	dropped;
+	u64_stats_t	multicast;
+	u64_stats_t	broadcast;
+	u64_stats_t	missed;
+	u64_stats_t	length_errors;
+	u64_stats_t	over_errors;
+	u64_stats_t	crc_errors;
+	u64_stats_t	frame_errors;
+	u64_stats_t	fragmented_errors;
+};
+
 #define UMAC_MIB_START			0x400
 
 #define UMAC_MDIO_CMD			0x614
@@ -271,6 +298,8 @@ struct bcmgenet_mib_counters {
 /* Only valid for GENETv3+ */
 #define UMAC_IRQ_MDIO_DONE		(1 << 23)
 #define UMAC_IRQ_MDIO_ERROR		(1 << 24)
+#define UMAC_IRQ_MDIO_EVENT		(UMAC_IRQ_MDIO_DONE | \
+					 UMAC_IRQ_MDIO_ERROR)
 
 /* INTRL2 instance 1 definitions */
 #define UMAC_IRQ1_TX_INTR_MASK		0xFFFF
@@ -476,6 +505,7 @@ enum bcmgenet_version {
 #define GENET_HAS_EXT		(1 << 1)
 #define GENET_HAS_MDIO_INTR	(1 << 2)
 #define GENET_HAS_MOCA_LINK_DET	(1 << 3)
+#define GENET_HAS_EPHY_16NM	(1 << 4)
 
 /* BCMGENET hardware parameters, keep this structure nicely aligned
  * since it is going to be used in hot paths
@@ -496,7 +526,6 @@ struct bcmgenet_hw_params {
 	u32		rdma_offset;
 	u32		tdma_offset;
 	u32		words_per_bd;
-	u32		flags;
 };
 
 struct bcmgenet_skb_cb {
@@ -510,10 +539,8 @@ struct bcmgenet_skb_cb {
 struct bcmgenet_tx_ring {
 	spinlock_t	lock;		/* ring lock */
 	struct napi_struct napi;	/* NAPI per tx queue */
-	unsigned long	packets;
-	unsigned long	bytes;
+	struct bcmgenet_tx_stats64 stats64;
 	unsigned int	index;		/* ring index */
-	unsigned int	queue;		/* queue index */
 	struct enet_cb	*cbs;		/* tx ring buffer control block*/
 	unsigned int	size;		/* size of each tx ring */
 	unsigned int    clean_ptr;      /* Tx ring clean pointer */
@@ -523,8 +550,6 @@ struct bcmgenet_tx_ring {
 	unsigned int	prod_index;	/* Tx ring producer index SW copy */
 	unsigned int	cb_ptr;		/* Tx ring initial CB ptr */
 	unsigned int	end_ptr;	/* Tx ring end CB ptr */
-	void (*int_enable)(struct bcmgenet_tx_ring *);
-	void (*int_disable)(struct bcmgenet_tx_ring *);
 	struct bcmgenet_priv *priv;
 };
 
@@ -538,10 +563,7 @@ struct bcmgenet_net_dim {
 
 struct bcmgenet_rx_ring {
 	struct napi_struct napi;	/* Rx NAPI struct */
-	unsigned long	bytes;
-	unsigned long	packets;
-	unsigned long	errors;
-	unsigned long	dropped;
+	struct bcmgenet_rx_stats64 stats64;
 	unsigned int	index;		/* Rx ring index */
 	struct enet_cb	*cbs;		/* Rx ring buffer control block */
 	unsigned int	size;		/* Rx ring size */
@@ -553,8 +575,6 @@ struct bcmgenet_rx_ring {
 	struct bcmgenet_net_dim dim;
 	u32		rx_max_coalesced_frames;
 	u32		rx_coalesce_usecs;
-	void (*int_enable)(struct bcmgenet_rx_ring *);
-	void (*int_disable)(struct bcmgenet_rx_ring *);
 	struct bcmgenet_priv *priv;
 };
 
@@ -583,7 +603,7 @@ struct bcmgenet_priv {
 	struct enet_cb *tx_cbs;
 	unsigned int num_tx_bds;
 
-	struct bcmgenet_tx_ring tx_rings[DESC_INDEX + 1];
+	struct bcmgenet_tx_ring tx_rings[GENET_MAX_MQ_CNT + 1];
 
 	/* receive variables */
 	void __iomem *rx_bds;
@@ -593,10 +613,11 @@ struct bcmgenet_priv {
 	struct bcmgenet_rxnfc_rule rxnfc_rules[MAX_NUM_OF_FS_RULES];
 	struct list_head rxnfc_list;
 
-	struct bcmgenet_rx_ring rx_rings[DESC_INDEX + 1];
+	struct bcmgenet_rx_ring rx_rings[GENET_MAX_MQ_CNT + 1];
 
 	/* other misc variables */
-	struct bcmgenet_hw_params *hw_params;
+	const struct bcmgenet_hw_params *hw_params;
+	u32 flags;
 	unsigned autoneg_pause:1;
 	unsigned tx_pause:1;
 	unsigned rx_pause:1;
@@ -615,7 +636,6 @@ struct bcmgenet_priv {
 	phy_interface_t phy_interface;
 	int phy_addr;
 	int ext_phy;
-	bool ephy_16nm;
 
 	/* Interrupt variables */
 	struct work_struct bcmgenet_irq_work;
@@ -643,13 +663,37 @@ struct bcmgenet_priv {
 	struct clk *clk_wol;
 	u32 wolopts;
 	u8 sopass[SOPASS_MAX];
-	bool wol_active;
 
 	struct bcmgenet_mib_counters mib;
 
 	struct ethtool_keee eee;
 };
 
+static inline bool bcmgenet_has_40bits(struct bcmgenet_priv *priv)
+{
+	return !!(priv->flags & GENET_HAS_40BITS);
+}
+
+static inline bool bcmgenet_has_ext(struct bcmgenet_priv *priv)
+{
+	return !!(priv->flags & GENET_HAS_EXT);
+}
+
+static inline bool bcmgenet_has_mdio_intr(struct bcmgenet_priv *priv)
+{
+	return !!(priv->flags & GENET_HAS_MDIO_INTR);
+}
+
+static inline bool bcmgenet_has_moca_link_det(struct bcmgenet_priv *priv)
+{
+	return !!(priv->flags & GENET_HAS_MOCA_LINK_DET);
+}
+
+static inline bool bcmgenet_has_ephy_16nm(struct bcmgenet_priv *priv)
+{
+	return !!(priv->flags & GENET_HAS_EPHY_16NM);
+}
+
 #define GENET_IO_MACRO(name, offset)					\
 static inline u32 bcmgenet_##name##_readl(struct bcmgenet_priv *priv,	\
 					u32 off)			\
@@ -702,8 +746,8 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol);
 int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol);
 int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 				enum bcmgenet_power_mode mode);
-void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
-			       enum bcmgenet_power_mode mode);
+int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
+			      enum bcmgenet_power_mode mode);
 
 void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
 			     bool tx_lpi_enabled);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 0715ea5bf13e..8fb551288298 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -2,7 +2,7 @@
 /*
  * Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support
  *
- * Copyright (c) 2014-2024 Broadcom
+ * Copyright (c) 2014-2025 Broadcom
  */
 
 #define pr_fmt(fmt)				"bcmgenet_wol: " fmt
@@ -41,9 +41,12 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct device *kdev = &priv->pdev->dev;
+	u32 phy_wolopts = 0;
 
-	if (dev->phydev)
+	if (dev->phydev) {
 		phy_ethtool_get_wol(dev->phydev, wol);
+		phy_wolopts = wol->wolopts;
+	}
 
 	/* MAC is not wake-up capable, return what the PHY does */
 	if (!device_can_wakeup(kdev))
@@ -51,9 +54,14 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 
 	/* Overlay MAC capabilities with that of the PHY queried before */
 	wol->supported |= WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
-	wol->wolopts = priv->wolopts;
-	memset(wol->sopass, 0, sizeof(wol->sopass));
+	wol->wolopts |= priv->wolopts;
+
+	/* Return the PHY configured magic password */
+	if (phy_wolopts & WAKE_MAGICSECURE)
+		return;
 
+	/* Otherwise the MAC one */
+	memset(wol->sopass, 0, sizeof(wol->sopass));
 	if (wol->wolopts & WAKE_MAGICSECURE)
 		memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass));
 }
@@ -70,7 +78,7 @@ int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	/* Try Wake-on-LAN from the PHY first */
 	if (dev->phydev) {
 		ret = phy_ethtool_set_wol(dev->phydev, wol);
-		if (ret != -EOPNOTSUPP)
+		if (ret != -EOPNOTSUPP && wol->wolopts)
 			return ret;
 	}
 
@@ -137,8 +145,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 				enum bcmgenet_power_mode mode)
 {
 	struct net_device *dev = priv->dev;
-	struct bcmgenet_rxnfc_rule *rule;
-	u32 reg, hfb_ctrl_reg, hfb_enable = 0;
+	u32 reg, hfb_ctrl_reg;
 	int retries = 0;
 
 	if (mode != GENET_POWER_WOL_MAGIC) {
@@ -146,18 +153,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 		return -EINVAL;
 	}
 
-	/* Can't suspend with WoL if MAC is still in reset */
-	spin_lock_bh(&priv->reg_lock);
-	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
-	if (reg & CMD_SW_RESET)
-		reg &= ~CMD_SW_RESET;
-
-	/* disable RX */
-	reg &= ~CMD_RX_EN;
-	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
-	spin_unlock_bh(&priv->reg_lock);
-	mdelay(10);
-
 	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) {
 		reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
 		reg |= MPD_EN;
@@ -169,13 +164,8 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	}
 
 	hfb_ctrl_reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-	if (priv->wolopts & WAKE_FILTER) {
-		list_for_each_entry(rule, &priv->rxnfc_list, list)
-			if (rule->fs.ring_cookie == RX_CLS_FLOW_WAKE)
-				hfb_enable |= (1 << rule->fs.location);
-		reg = (hfb_ctrl_reg & ~RBUF_HFB_EN) | RBUF_ACPI_EN;
-		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
-	}
+	reg = hfb_ctrl_reg | RBUF_ACPI_EN;
+	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
 
 	/* Do not leave UniMAC in MPD mode only */
 	retries = bcmgenet_poll_wol_status(priv);
@@ -190,15 +180,12 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	netif_dbg(priv, wol, dev, "MPD WOL-ready status set after %d msec\n",
 		  retries);
 
-	clk_prepare_enable(priv->clk_wol);
-	priv->wol_active = 1;
+	/* Disable phy status updates while suspending */
+	mutex_lock(&dev->phydev->lock);
+	dev->phydev->state = PHY_READY;
+	mutex_unlock(&dev->phydev->lock);
 
-	if (hfb_enable) {
-		bcmgenet_hfb_reg_writel(priv, hfb_enable,
-					HFB_FLT_ENABLE_V3PLUS + 4);
-		hfb_ctrl_reg = RBUF_HFB_EN | RBUF_ACPI_EN;
-		bcmgenet_hfb_reg_writel(priv, hfb_ctrl_reg, HFB_CTRL);
-	}
+	clk_prepare_enable(priv->clk_wol);
 
 	/* Enable CRC forward */
 	spin_lock_bh(&priv->reg_lock);
@@ -206,13 +193,17 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	priv->crc_fwd_en = 1;
 	reg |= CMD_CRC_FWD;
 
+	/* Can't suspend with WoL if MAC is still in reset */
+	if (reg & CMD_SW_RESET)
+		reg &= ~CMD_SW_RESET;
+
 	/* Receiver must be enabled for WOL MP detection */
 	reg |= CMD_RX_EN;
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	spin_unlock_bh(&priv->reg_lock);
 
 	reg = UMAC_IRQ_MPD_R;
-	if (hfb_enable)
+	if (hfb_ctrl_reg & RBUF_HFB_EN)
 		reg |=  UMAC_IRQ_HFB_SM | UMAC_IRQ_HFB_MM;
 
 	bcmgenet_intrl2_0_writel(priv, reg, INTRL2_CPU_MASK_CLEAR);
@@ -220,40 +211,42 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	return 0;
 }
 
-void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
-			       enum bcmgenet_power_mode mode)
+int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
+			      enum bcmgenet_power_mode mode)
 {
+	struct net_device *dev = priv->dev;
 	u32 reg;
 
 	if (mode != GENET_POWER_WOL_MAGIC) {
 		netif_err(priv, wol, priv->dev, "invalid mode: %d\n", mode);
-		return;
+		return -EINVAL;
 	}
 
-	if (!priv->wol_active)
-		return;	/* failed to suspend so skip the rest */
-
-	priv->wol_active = 0;
 	clk_disable_unprepare(priv->clk_wol);
 	priv->crc_fwd_en = 0;
 
+	bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_WAKE_EVENT,
+				 INTRL2_CPU_MASK_SET);
+	if (bcmgenet_has_mdio_intr(priv))
+		bcmgenet_intrl2_0_writel(priv,
+					 UMAC_IRQ_MDIO_EVENT,
+					 INTRL2_CPU_MASK_CLEAR);
+
 	/* Disable Magic Packet Detection */
 	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) {
 		reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
 		if (!(reg & MPD_EN))
-			return;	/* already reset so skip the rest */
+			return -EPERM;	/* already reset so skip the rest */
 		reg &= ~(MPD_EN | MPD_PW_EN);
 		bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 	}
 
-	/* Disable WAKE_FILTER Detection */
-	if (priv->wolopts & WAKE_FILTER) {
-		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-		if (!(reg & RBUF_ACPI_EN))
-			return;	/* already reset so skip the rest */
-		reg &= ~(RBUF_HFB_EN | RBUF_ACPI_EN);
-		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
-	}
+	/* Disable ACPI mode */
+	reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+	if (!(reg & RBUF_ACPI_EN))
+		return -EPERM;	/* already reset so skip the rest */
+	reg &= ~RBUF_ACPI_EN;
+	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
 
 	/* Disable CRC Forward */
 	spin_lock_bh(&priv->reg_lock);
@@ -261,4 +254,14 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	reg &= ~CMD_CRC_FWD;
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	spin_unlock_bh(&priv->reg_lock);
+
+	/* Resume link status tracking */
+	mutex_lock(&dev->phydev->lock);
+	if (dev->phydev->link)
+		dev->phydev->state = PHY_RUNNING;
+	else
+		dev->phydev->state = PHY_NOLINK;
+	mutex_unlock(&dev->phydev->lock);
+
+	return 0;
 }
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index c4a3698cef66..38f854b94a79 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -2,7 +2,7 @@
 /*
  * Broadcom GENET MDIO routines
  *
- * Copyright (c) 2014-2024 Broadcom
+ * Copyright (c) 2014-2025 Broadcom
  */
 
 #include <linux/acpi.h>
@@ -20,7 +20,6 @@
 #include <linux/of.h>
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
-#include <linux/platform_data/bcmgenet.h>
 #include <linux/platform_data/mdio-bcm-unimac.h>
 
 #include "bcmgenet.h"
@@ -154,7 +153,7 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 	u32 reg = 0;
 
 	/* EXT_GPHY_CTRL is only valid for GENETv4 and onward */
-	if (GENET_IS_V4(priv) || priv->ephy_16nm) {
+	if (GENET_IS_V4(priv) || bcmgenet_has_ephy_16nm(priv)) {
 		reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL);
 		if (enable) {
 			reg &= ~EXT_CK25_DIS;
@@ -169,10 +168,15 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 
 			reg &= ~EXT_GPHY_RESET;
 		} else {
+			reg |= EXT_GPHY_RESET;
+			bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
+			mdelay(1);
+
 			reg |= EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN |
-			       EXT_GPHY_RESET | EXT_CFG_IDDQ_GLOBAL_PWR;
+			       EXT_CFG_IDDQ_GLOBAL_PWR;
 			bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
 			mdelay(1);
+
 			reg |= EXT_CK25_DIS;
 		}
 		bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
@@ -184,7 +188,7 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 
 static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 {
-	if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
+	if (bcmgenet_has_moca_link_det(priv))
 		fixed_phy_set_link_update(priv->dev->phydev,
 					  bcmgenet_fixed_phy_link_update);
 }
@@ -431,23 +435,6 @@ static struct device_node *bcmgenet_mii_of_find_mdio(struct bcmgenet_priv *priv)
 	return priv->mdio_dn;
 }
 
-static void bcmgenet_mii_pdata_init(struct bcmgenet_priv *priv,
-				    struct unimac_mdio_pdata *ppd)
-{
-	struct device *kdev = &priv->pdev->dev;
-	struct bcmgenet_platform_data *pd = kdev->platform_data;
-
-	if (pd->phy_interface != PHY_INTERFACE_MODE_MOCA && pd->mdio_enabled) {
-		/*
-		 * Internal or external PHY with MDIO access
-		 */
-		if (pd->phy_address >= 0 && pd->phy_address < PHY_MAX_ADDR)
-			ppd->phy_mask = 1 << pd->phy_address;
-		else
-			ppd->phy_mask = 0;
-	}
-}
-
 static int bcmgenet_mii_wait(void *wait_func_data)
 {
 	struct bcmgenet_priv *priv = wait_func_data;
@@ -462,7 +449,6 @@ static int bcmgenet_mii_wait(void *wait_func_data)
 static int bcmgenet_mii_register(struct bcmgenet_priv *priv)
 {
 	struct platform_device *pdev = priv->pdev;
-	struct bcmgenet_platform_data *pdata = pdev->dev.platform_data;
 	struct device_node *dn = pdev->dev.of_node;
 	struct unimac_mdio_pdata ppd;
 	struct platform_device *ppdev;
@@ -506,8 +492,6 @@ static int bcmgenet_mii_register(struct bcmgenet_priv *priv)
 	ppdev->dev.parent = &pdev->dev;
 	if (dn)
 		ppdev->dev.of_node = bcmgenet_mii_of_find_mdio(priv);
-	else if (pdata)
-		bcmgenet_mii_pdata_init(priv, &ppd);
 	else
 		ppd.phy_mask = ~0;
 
@@ -589,58 +573,6 @@ static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv)
 	return 0;
 }
 
-static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
-{
-	struct device *kdev = &priv->pdev->dev;
-	struct bcmgenet_platform_data *pd = kdev->platform_data;
-	char phy_name[MII_BUS_ID_SIZE + 3];
-	char mdio_bus_id[MII_BUS_ID_SIZE];
-	struct phy_device *phydev;
-
-	snprintf(mdio_bus_id, MII_BUS_ID_SIZE, "%s-%d",
-		 UNIMAC_MDIO_DRV_NAME, priv->pdev->id);
-
-	if (pd->phy_interface != PHY_INTERFACE_MODE_MOCA && pd->mdio_enabled) {
-		snprintf(phy_name, MII_BUS_ID_SIZE, PHY_ID_FMT,
-			 mdio_bus_id, pd->phy_address);
-
-		/*
-		 * Internal or external PHY with MDIO access
-		 */
-		phydev = phy_attach(priv->dev, phy_name, pd->phy_interface);
-		if (IS_ERR(phydev)) {
-			dev_err(kdev, "failed to register PHY device\n");
-			return PTR_ERR(phydev);
-		}
-	} else {
-		/*
-		 * MoCA port or no MDIO access.
-		 * Use fixed PHY to represent the link layer.
-		 */
-		struct fixed_phy_status fphy_status = {
-			.link = 1,
-			.speed = pd->phy_speed,
-			.duplex = pd->phy_duplex,
-			.pause = 0,
-			.asym_pause = 0,
-		};
-
-		phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
-		if (IS_ERR(phydev)) {
-			dev_err(kdev, "failed to register fixed PHY device\n");
-			return PTR_ERR(phydev);
-		}
-
-		/* Make sure we initialize MoCA PHYs with a link down */
-		phydev->link = 0;
-
-	}
-
-	priv->phy_interface = pd->phy_interface;
-
-	return 0;
-}
-
 static int bcmgenet_mii_bus_init(struct bcmgenet_priv *priv)
 {
 	struct device *kdev = &priv->pdev->dev;
@@ -651,7 +583,7 @@ static int bcmgenet_mii_bus_init(struct bcmgenet_priv *priv)
 	else if (has_acpi_companion(kdev))
 		return bcmgenet_phy_interface_init(priv);
 	else
-		return bcmgenet_mii_pd_init(priv);
+		return -EINVAL;
 }
 
 int bcmgenet_mii_init(struct net_device *dev)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 9cc8db10a8d6..75f66587983d 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -54,7 +54,8 @@
 #include <linux/ssb/ssb_driver_gige.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
-#include <linux/crc32poly.h>
+#include <linux/crc32.h>
+#include <linux/dmi.h>
 
 #include <net/checksum.h>
 #include <net/gso.h>
@@ -5802,7 +5803,7 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, bool force_reset)
 	u32 current_speed = SPEED_UNKNOWN;
 	u8 current_duplex = DUPLEX_UNKNOWN;
 	bool current_link_up = false;
-	u32 local_adv, remote_adv, sgsr;
+	u32 local_adv = 0, remote_adv = 0, sgsr;
 
 	if ((tg3_asic_rev(tp) == ASIC_REV_5719 ||
 	     tg3_asic_rev(tp) == ASIC_REV_5720) &&
@@ -5943,9 +5944,6 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, bool force_reset)
 		else
 			current_duplex = DUPLEX_HALF;
 
-		local_adv = 0;
-		remote_adv = 0;
-
 		if (bmcr & BMCR_ANENABLE) {
 			u32 common;
 
@@ -6685,7 +6683,7 @@ static void tg3_rx_data_free(struct tg3 *tp, struct ring_info *ri, u32 map_sz)
  * We only need to fill in the address because the other members
  * of the RX descriptor are invariant, see tg3_init_rings.
  *
- * Note the purposeful assymetry of cpu vs. chip accesses.  For
+ * Note the purposeful asymmetry of cpu vs. chip accesses.  For
  * posting buffers we only dirty the first cache line of the RX
  * descriptor (containing the address).  Whereas for the RX status
  * buffers the cpu only reads the last cacheline of the RX descriptor
@@ -7424,7 +7422,7 @@ static void tg3_napi_enable(struct tg3 *tp)
 
 	for (i = 0; i < tp->irq_cnt; i++) {
 		tnapi = &tp->napi[i];
-		napi_enable(&tnapi->napi);
+		napi_enable_locked(&tnapi->napi);
 		if (tnapi->tx_buffers) {
 			netif_queue_set_napi(tp->dev, txq_idx,
 					     NETDEV_QUEUE_TYPE_TX,
@@ -7445,9 +7443,10 @@ static void tg3_napi_init(struct tg3 *tp)
 	int i;
 
 	for (i = 0; i < tp->irq_cnt; i++) {
-		netif_napi_add(tp->dev, &tp->napi[i].napi,
-			       i ? tg3_poll_msix : tg3_poll);
-		netif_napi_set_irq(&tp->napi[i].napi, tp->napi[i].irq_vec);
+		netif_napi_add_locked(tp->dev, &tp->napi[i].napi,
+				      i ? tg3_poll_msix : tg3_poll);
+		netif_napi_set_irq_locked(&tp->napi[i].napi,
+					  tp->napi[i].irq_vec);
 	}
 }
 
@@ -9807,26 +9806,7 @@ static void tg3_setup_rxbd_thresholds(struct tg3 *tp)
 
 static inline u32 calc_crc(unsigned char *buf, int len)
 {
-	u32 reg;
-	u32 tmp;
-	int j, k;
-
-	reg = 0xffffffff;
-
-	for (j = 0; j < len; j++) {
-		reg ^= buf[j];
-
-		for (k = 0; k < 8; k++) {
-			tmp = reg & 0x01;
-
-			reg >>= 1;
-
-			if (tmp)
-				reg ^= CRC32_POLY_LE;
-		}
-	}
-
-	return ~reg;
+	return ~crc32(~0, buf, len);
 }
 
 static void tg3_set_multi(struct tg3 *tp, unsigned int accept_all)
@@ -10162,7 +10142,7 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy)
 	tp->grc_mode |= GRC_MODE_HOST_SENDBDS;
 
 	/* Pseudo-header checksum is done by hardware logic and not
-	 * the offload processers, so make the chip do the pseudo-
+	 * the offload processors, so make the chip do the pseudo-
 	 * header checksums on receive.  For transmit it is more
 	 * convenient to do the pseudo-header checksum in software
 	 * as Linux does that on transmit for us in all cases.
@@ -11079,7 +11059,7 @@ static void tg3_chk_missed_msi(struct tg3 *tp)
 
 static void tg3_timer(struct timer_list *t)
 {
-	struct tg3 *tp = from_timer(tp, t, timer);
+	struct tg3 *tp = timer_container_of(tp, t, timer);
 
 	spin_lock(&tp->lock);
 
@@ -11250,7 +11230,7 @@ static void tg3_timer_start(struct tg3 *tp)
 
 static void tg3_timer_stop(struct tg3 *tp)
 {
-	del_timer_sync(&tp->timer);
+	timer_delete_sync(&tp->timer);
 }
 
 /* Restart hardware after configuration changes, self-test, etc.
@@ -11259,6 +11239,8 @@ static void tg3_timer_stop(struct tg3 *tp)
 static int tg3_restart_hw(struct tg3 *tp, bool reset_phy)
 	__releases(tp->lock)
 	__acquires(tp->lock)
+	__releases(tp->dev->lock)
+	__acquires(tp->dev->lock)
 {
 	int err;
 
@@ -11271,7 +11253,9 @@ static int tg3_restart_hw(struct tg3 *tp, bool reset_phy)
 		tg3_timer_stop(tp);
 		tp->irq_sync = 0;
 		tg3_napi_enable(tp);
+		netdev_unlock(tp->dev);
 		dev_close(tp->dev);
+		netdev_lock(tp->dev);
 		tg3_full_lock(tp, 0);
 	}
 	return err;
@@ -11299,6 +11283,7 @@ static void tg3_reset_task(struct work_struct *work)
 
 	tg3_netif_stop(tp);
 
+	netdev_lock(tp->dev);
 	tg3_full_lock(tp, 1);
 
 	if (tg3_flag(tp, TX_RECOVERY_PENDING)) {
@@ -11318,12 +11303,14 @@ static void tg3_reset_task(struct work_struct *work)
 		 * call cancel_work_sync() and wait forever.
 		 */
 		tg3_flag_clear(tp, RESET_TASK_PENDING);
+		netdev_unlock(tp->dev);
 		dev_close(tp->dev);
 		goto out;
 	}
 
 	tg3_netif_start(tp);
 	tg3_full_unlock(tp);
+	netdev_unlock(tp->dev);
 	tg3_phy_start(tp);
 	tg3_flag_clear(tp, RESET_TASK_PENDING);
 out:
@@ -11683,9 +11670,11 @@ static int tg3_start(struct tg3 *tp, bool reset_phy, bool test_irq,
 	if (err)
 		goto out_ints_fini;
 
+	netdev_lock(dev);
 	tg3_napi_init(tp);
 
 	tg3_napi_enable(tp);
+	netdev_unlock(dev);
 
 	for (i = 0; i < tp->irq_cnt; i++) {
 		err = tg3_request_irq(tp, i);
@@ -12569,6 +12558,7 @@ static int tg3_set_ringparam(struct net_device *dev,
 		irq_sync = 1;
 	}
 
+	netdev_lock(dev);
 	tg3_full_lock(tp, irq_sync);
 
 	tp->rx_pending = ering->rx_pending;
@@ -12597,6 +12587,7 @@ static int tg3_set_ringparam(struct net_device *dev,
 	}
 
 	tg3_full_unlock(tp);
+	netdev_unlock(dev);
 
 	if (irq_sync && !err)
 		tg3_phy_start(tp);
@@ -12678,6 +12669,7 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 			irq_sync = 1;
 		}
 
+		netdev_lock(dev);
 		tg3_full_lock(tp, irq_sync);
 
 		if (epause->autoneg)
@@ -12707,6 +12699,7 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 		}
 
 		tg3_full_unlock(tp);
+		netdev_unlock(dev);
 	}
 
 	tp->phy_flags |= TG3_PHYFLG_USER_CONFIGURED;
@@ -12726,29 +12719,17 @@ static int tg3_get_sset_count(struct net_device *dev, int sset)
 	}
 }
 
-static int tg3_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
-			 u32 *rules __always_unused)
+static u32 tg3_get_rx_ring_count(struct net_device *dev)
 {
 	struct tg3 *tp = netdev_priv(dev);
 
 	if (!tg3_flag(tp, SUPPORT_MSIX))
-		return -EOPNOTSUPP;
-
-	switch (info->cmd) {
-	case ETHTOOL_GRXRINGS:
-		if (netif_running(tp->dev))
-			info->data = tp->rxq_cnt;
-		else {
-			info->data = num_online_cpus();
-			if (info->data > TG3_RSS_MAX_NUM_QS)
-				info->data = TG3_RSS_MAX_NUM_QS;
-		}
+		return 1;
 
-		return 0;
+	if (netif_running(tp->dev))
+		return tp->rxq_cnt;
 
-	default:
-		return -EOPNOTSUPP;
-	}
+	return min_t(u32, netif_get_num_default_rss_queues(), tp->rxq_max);
 }
 
 static u32 tg3_get_rxfh_indir_size(struct net_device *dev)
@@ -13911,6 +13892,7 @@ static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest,
 			data[TG3_INTERRUPT_TEST] = 1;
 		}
 
+		netdev_lock(dev);
 		tg3_full_lock(tp, 0);
 
 		tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
@@ -13922,6 +13904,7 @@ static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest,
 		}
 
 		tg3_full_unlock(tp);
+		netdev_unlock(dev);
 
 		if (irq_sync && !err2)
 			tg3_phy_start(tp);
@@ -13931,22 +13914,20 @@ static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest,
 
 }
 
-static int tg3_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
+static int tg3_hwtstamp_set(struct net_device *dev,
+			    struct kernel_hwtstamp_config *stmpconf,
+			    struct netlink_ext_ack *extack)
 {
 	struct tg3 *tp = netdev_priv(dev);
-	struct hwtstamp_config stmpconf;
 
 	if (!tg3_flag(tp, PTP_CAPABLE))
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&stmpconf, ifr->ifr_data, sizeof(stmpconf)))
-		return -EFAULT;
-
-	if (stmpconf.tx_type != HWTSTAMP_TX_ON &&
-	    stmpconf.tx_type != HWTSTAMP_TX_OFF)
+	if (stmpconf->tx_type != HWTSTAMP_TX_ON &&
+	    stmpconf->tx_type != HWTSTAMP_TX_OFF)
 		return -ERANGE;
 
-	switch (stmpconf.rx_filter) {
+	switch (stmpconf->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		tp->rxptpctl = 0;
 		break;
@@ -14006,74 +13987,72 @@ static int tg3_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 		tw32(TG3_RX_PTP_CTL,
 		     tp->rxptpctl | TG3_RX_PTP_CTL_HWTS_INTERLOCK);
 
-	if (stmpconf.tx_type == HWTSTAMP_TX_ON)
+	if (stmpconf->tx_type == HWTSTAMP_TX_ON)
 		tg3_flag_set(tp, TX_TSTAMP_EN);
 	else
 		tg3_flag_clear(tp, TX_TSTAMP_EN);
 
-	return copy_to_user(ifr->ifr_data, &stmpconf, sizeof(stmpconf)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
-static int tg3_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
+static int tg3_hwtstamp_get(struct net_device *dev,
+			    struct kernel_hwtstamp_config *stmpconf)
 {
 	struct tg3 *tp = netdev_priv(dev);
-	struct hwtstamp_config stmpconf;
 
 	if (!tg3_flag(tp, PTP_CAPABLE))
 		return -EOPNOTSUPP;
 
-	stmpconf.flags = 0;
-	stmpconf.tx_type = (tg3_flag(tp, TX_TSTAMP_EN) ?
-			    HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF);
+	stmpconf->flags = 0;
+	stmpconf->tx_type = tg3_flag(tp, TX_TSTAMP_EN) ?
+			    HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
 
 	switch (tp->rxptpctl) {
 	case 0:
-		stmpconf.rx_filter = HWTSTAMP_FILTER_NONE;
+		stmpconf->rx_filter = HWTSTAMP_FILTER_NONE;
 		break;
 	case TG3_RX_PTP_CTL_RX_PTP_V1_EN | TG3_RX_PTP_CTL_ALL_V1_EVENTS:
-		stmpconf.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		stmpconf->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		break;
 	case TG3_RX_PTP_CTL_RX_PTP_V1_EN | TG3_RX_PTP_CTL_SYNC_EVNT:
-		stmpconf.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_SYNC;
+		stmpconf->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_SYNC;
 		break;
 	case TG3_RX_PTP_CTL_RX_PTP_V1_EN | TG3_RX_PTP_CTL_DELAY_REQ:
-		stmpconf.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ;
+		stmpconf->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ;
 		break;
 	case TG3_RX_PTP_CTL_RX_PTP_V2_EN | TG3_RX_PTP_CTL_ALL_V2_EVENTS:
-		stmpconf.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		stmpconf->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	case TG3_RX_PTP_CTL_RX_PTP_V2_L2_EN | TG3_RX_PTP_CTL_ALL_V2_EVENTS:
-		stmpconf.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+		stmpconf->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 		break;
 	case TG3_RX_PTP_CTL_RX_PTP_V2_L4_EN | TG3_RX_PTP_CTL_ALL_V2_EVENTS:
-		stmpconf.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
+		stmpconf->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 		break;
 	case TG3_RX_PTP_CTL_RX_PTP_V2_EN | TG3_RX_PTP_CTL_SYNC_EVNT:
-		stmpconf.rx_filter = HWTSTAMP_FILTER_PTP_V2_SYNC;
+		stmpconf->rx_filter = HWTSTAMP_FILTER_PTP_V2_SYNC;
 		break;
 	case TG3_RX_PTP_CTL_RX_PTP_V2_L2_EN | TG3_RX_PTP_CTL_SYNC_EVNT:
-		stmpconf.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_SYNC;
+		stmpconf->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_SYNC;
 		break;
 	case TG3_RX_PTP_CTL_RX_PTP_V2_L4_EN | TG3_RX_PTP_CTL_SYNC_EVNT:
-		stmpconf.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_SYNC;
+		stmpconf->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_SYNC;
 		break;
 	case TG3_RX_PTP_CTL_RX_PTP_V2_EN | TG3_RX_PTP_CTL_DELAY_REQ:
-		stmpconf.rx_filter = HWTSTAMP_FILTER_PTP_V2_DELAY_REQ;
+		stmpconf->rx_filter = HWTSTAMP_FILTER_PTP_V2_DELAY_REQ;
 		break;
 	case TG3_RX_PTP_CTL_RX_PTP_V2_L2_EN | TG3_RX_PTP_CTL_DELAY_REQ:
-		stmpconf.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ;
+		stmpconf->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ;
 		break;
 	case TG3_RX_PTP_CTL_RX_PTP_V2_L4_EN | TG3_RX_PTP_CTL_DELAY_REQ:
-		stmpconf.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ;
+		stmpconf->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ;
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		return -ERANGE;
 	}
 
-	return copy_to_user(ifr->ifr_data, &stmpconf, sizeof(stmpconf)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 static int tg3_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
@@ -14128,12 +14107,6 @@ static int tg3_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 		return err;
 
-	case SIOCSHWTSTAMP:
-		return tg3_hwtstamp_set(dev, ifr);
-
-	case SIOCGHWTSTAMP:
-		return tg3_hwtstamp_get(dev, ifr);
-
 	default:
 		/* do nothing */
 		break;
@@ -14283,7 +14256,7 @@ static const struct ethtool_ops tg3_ethtool_ops = {
 	.get_coalesce		= tg3_get_coalesce,
 	.set_coalesce		= tg3_set_coalesce,
 	.get_sset_count		= tg3_get_sset_count,
-	.get_rxnfc		= tg3_get_rxnfc,
+	.get_rx_ring_count	= tg3_get_rx_ring_count,
 	.get_rxfh_indir_size    = tg3_get_rxfh_indir_size,
 	.get_rxfh		= tg3_get_rxfh,
 	.set_rxfh		= tg3_set_rxfh,
@@ -14365,6 +14338,7 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
 
 	tg3_set_mtu(dev, tp, new_mtu);
 
+	netdev_lock(dev);
 	tg3_full_lock(tp, 1);
 
 	tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
@@ -14384,6 +14358,7 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
 		tg3_netif_start(tp);
 
 	tg3_full_unlock(tp);
+	netdev_unlock(dev);
 
 	if (!err)
 		tg3_phy_start(tp);
@@ -14407,6 +14382,8 @@ static const struct net_device_ops tg3_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= tg3_poll_controller,
 #endif
+	.ndo_hwtstamp_get	= tg3_hwtstamp_get,
+	.ndo_hwtstamp_set	= tg3_hwtstamp_set,
 };
 
 static void tg3_get_eeprom_size(struct tg3 *tp)
@@ -16610,7 +16587,7 @@ static int tg3_get_invariants(struct tg3 *tp, const struct pci_device_id *ent)
 
 			tg3_flag_set(tp, PCIX_TARGET_HWBUG);
 
-			/* The chip can have it's power management PCI config
+			/* The chip can have its power management PCI config
 			 * space registers clobbered due to this bug.
 			 * So explicitly force the chip into D0 here.
 			 */
@@ -18164,6 +18141,7 @@ static int tg3_resume(struct device *device)
 
 	netif_device_attach(dev);
 
+	netdev_lock(dev);
 	tg3_full_lock(tp, 0);
 
 	tg3_ape_driver_state_change(tp, RESET_KIND_INIT);
@@ -18180,6 +18158,7 @@ static int tg3_resume(struct device *device)
 
 out:
 	tg3_full_unlock(tp);
+	netdev_unlock(dev);
 
 	if (!err)
 		tg3_phy_start(tp);
@@ -18192,6 +18171,50 @@ unlock:
 
 static SIMPLE_DEV_PM_OPS(tg3_pm_ops, tg3_suspend, tg3_resume);
 
+/* Systems where ACPI _PTS (Prepare To Sleep) S5 will result in a fatal
+ * PCIe AER event on the tg3 device if the tg3 device is not, or cannot
+ * be, powered down.
+ */
+static const struct dmi_system_id tg3_restart_aer_quirk_table[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R440"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R540"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R640"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R650"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R740"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R750"),
+		},
+	},
+	{}
+};
+
 static void tg3_shutdown(struct pci_dev *pdev)
 {
 	struct net_device *dev = pci_get_drvdata(pdev);
@@ -18208,6 +18231,19 @@ static void tg3_shutdown(struct pci_dev *pdev)
 
 	if (system_state == SYSTEM_POWER_OFF)
 		tg3_power_down(tp);
+	else if (system_state == SYSTEM_RESTART &&
+		 dmi_first_match(tg3_restart_aer_quirk_table) &&
+		 pdev->current_state != PCI_D3cold &&
+		 pdev->current_state != PCI_UNKNOWN) {
+		/* Disable PCIe AER on the tg3 to avoid a fatal
+		 * error during this system restart.
+		 */
+		pcie_capability_clear_word(pdev, PCI_EXP_DEVCTL,
+					   PCI_EXP_DEVCTL_CERE |
+					   PCI_EXP_DEVCTL_NFERE |
+					   PCI_EXP_DEVCTL_FERE |
+					   PCI_EXP_DEVCTL_URRE);
+	}
 
 	rtnl_unlock();
 
@@ -18260,7 +18296,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 done:
 	if (state == pci_channel_io_perm_failure) {
 		if (netdev) {
+			netdev_lock(netdev);
 			tg3_napi_enable(tp);
+			netdev_unlock(netdev);
 			dev_close(netdev);
 		}
 		err = PCI_ERS_RESULT_DISCONNECT;
@@ -18299,7 +18337,6 @@ static pci_ers_result_t tg3_io_slot_reset(struct pci_dev *pdev)
 
 	pci_set_master(pdev);
 	pci_restore_state(pdev);
-	pci_save_state(pdev);
 
 	if (!netdev || !netif_running(netdev)) {
 		rc = PCI_ERS_RESULT_RECOVERED;
@@ -18314,7 +18351,9 @@ static pci_ers_result_t tg3_io_slot_reset(struct pci_dev *pdev)
 
 done:
 	if (rc != PCI_ERS_RESULT_RECOVERED && netdev && netif_running(netdev)) {
+		netdev_lock(netdev);
 		tg3_napi_enable(tp);
+		netdev_unlock(netdev);
 		dev_close(netdev);
 	}
 	rtnl_unlock();
@@ -18340,12 +18379,14 @@ static void tg3_io_resume(struct pci_dev *pdev)
 	if (!netdev || !netif_running(netdev))
 		goto done;
 
+	netdev_lock(netdev);
 	tg3_full_lock(tp, 0);
 	tg3_ape_driver_state_change(tp, RESET_KIND_INIT);
 	tg3_flag_set(tp, INIT_COMPLETE);
 	err = tg3_restart_hw(tp, true);
 	if (err) {
 		tg3_full_unlock(tp);
+		netdev_unlock(netdev);
 		netdev_err(netdev, "Cannot restart hardware after reset.\n");
 		goto done;
 	}
@@ -18357,6 +18398,7 @@ static void tg3_io_resume(struct pci_dev *pdev)
 	tg3_netif_start(tp);
 
 	tg3_full_unlock(tp);
+	netdev_unlock(netdev);
 
 	tg3_phy_start(tp);
 
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index b473f8014d9c..a9e7f88fa26d 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -2390,7 +2390,7 @@
 #define TG3_CL45_D7_EEERES_STAT_LP_1000T	0x0004
 
 
-/* Fast Ethernet Tranceiver definitions */
+/* Fast Ethernet Transceiver definitions */
 #define MII_TG3_FET_PTEST		0x17
 #define  MII_TG3_FET_PTEST_TRIM_SEL	0x0010
 #define  MII_TG3_FET_PTEST_TRIM_2	0x0002
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index 9c80ab07a735..92c7639d1fc7 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -314,13 +314,13 @@ bfa_ioc_sm_getattr(struct bfa_ioc *ioc, enum ioc_event event)
 {
 	switch (event) {
 	case IOC_E_FWRSP_GETATTR:
-		del_timer(&ioc->ioc_timer);
+		timer_delete(&ioc->ioc_timer);
 		bfa_fsm_set_state(ioc, bfa_ioc_sm_op);
 		break;
 
 	case IOC_E_PFFAILED:
 	case IOC_E_HWERROR:
-		del_timer(&ioc->ioc_timer);
+		timer_delete(&ioc->ioc_timer);
 		fallthrough;
 	case IOC_E_TIMEOUT:
 		ioc->cbfn->enable_cbfn(ioc->bfa, BFA_STATUS_IOC_FAILURE);
@@ -330,7 +330,7 @@ bfa_ioc_sm_getattr(struct bfa_ioc *ioc, enum ioc_event event)
 		break;
 
 	case IOC_E_DISABLE:
-		del_timer(&ioc->ioc_timer);
+		timer_delete(&ioc->ioc_timer);
 		bfa_fsm_set_state(ioc, bfa_ioc_sm_disabling);
 		break;
 
@@ -659,13 +659,13 @@ bfa_iocpf_sm_mismatch(struct bfa_iocpf *iocpf, enum iocpf_event event)
 		break;
 
 	case IOCPF_E_DISABLE:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_reset);
 		bfa_ioc_pf_disabled(ioc);
 		break;
 
 	case IOCPF_E_STOP:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_reset);
 		break;
 
@@ -741,7 +741,7 @@ bfa_iocpf_sm_hwinit(struct bfa_iocpf *iocpf, enum iocpf_event event)
 		break;
 
 	case IOCPF_E_DISABLE:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		bfa_ioc_sync_leave(ioc);
 		bfa_nw_ioc_hw_sem_release(ioc);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_disabled);
@@ -774,13 +774,13 @@ bfa_iocpf_sm_enabling(struct bfa_iocpf *iocpf, enum iocpf_event event)
 
 	switch (event) {
 	case IOCPF_E_FWRSP_ENABLE:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		bfa_nw_ioc_hw_sem_release(ioc);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_ready);
 		break;
 
 	case IOCPF_E_INITFAIL:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		fallthrough;
 
 	case IOCPF_E_TIMEOUT:
@@ -791,7 +791,7 @@ bfa_iocpf_sm_enabling(struct bfa_iocpf *iocpf, enum iocpf_event event)
 		break;
 
 	case IOCPF_E_DISABLE:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		bfa_nw_ioc_hw_sem_release(ioc);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_disabling);
 		break;
@@ -844,12 +844,12 @@ bfa_iocpf_sm_disabling(struct bfa_iocpf *iocpf, enum iocpf_event event)
 
 	switch (event) {
 	case IOCPF_E_FWRSP_DISABLE:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_disabling_sync);
 		break;
 
 	case IOCPF_E_FAIL:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		fallthrough;
 
 	case IOCPF_E_TIMEOUT:
@@ -1210,7 +1210,7 @@ bfa_nw_ioc_hw_sem_release(struct bfa_ioc *ioc)
 static void
 bfa_ioc_hw_sem_get_cancel(struct bfa_ioc *ioc)
 {
-	del_timer(&ioc->sem_timer);
+	timer_delete(&ioc->sem_timer);
 }
 
 /* Initialize LPU local memory (aka secondary memory / SRAM) */
@@ -1982,7 +1982,7 @@ bfa_ioc_hb_monitor(struct bfa_ioc *ioc)
 static void
 bfa_ioc_hb_stop(struct bfa_ioc *ioc)
 {
-	del_timer(&ioc->hb_timer);
+	timer_delete(&ioc->hb_timer);
 }
 
 /* Initiate a full firmware download. */
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index ece6f3b48327..9bed33295839 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -19,6 +19,7 @@
 #include <linux/ip.h>
 #include <linux/prefetch.h>
 #include <linux/module.h>
+#include <net/gro.h>
 
 #include "bnad.h"
 #include "bna.h"
@@ -1687,7 +1688,8 @@ err_return:
 static void
 bnad_ioc_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.ioc_timer);
+	struct bnad *bnad = timer_container_of(bnad, t,
+					       bna.ioceth.ioc.ioc_timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
@@ -1698,7 +1700,8 @@ bnad_ioc_timeout(struct timer_list *t)
 static void
 bnad_ioc_hb_check(struct timer_list *t)
 {
-	struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.hb_timer);
+	struct bnad *bnad = timer_container_of(bnad, t,
+					       bna.ioceth.ioc.hb_timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
@@ -1709,7 +1712,8 @@ bnad_ioc_hb_check(struct timer_list *t)
 static void
 bnad_iocpf_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.iocpf_timer);
+	struct bnad *bnad = timer_container_of(bnad, t,
+					       bna.ioceth.ioc.iocpf_timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
@@ -1720,7 +1724,8 @@ bnad_iocpf_timeout(struct timer_list *t)
 static void
 bnad_iocpf_sem_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.sem_timer);
+	struct bnad *bnad = timer_container_of(bnad, t,
+					       bna.ioceth.ioc.sem_timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
@@ -1734,7 +1739,7 @@ bnad_iocpf_sem_timeout(struct timer_list *t)
  *	Time	CPU m	CPU n
  *	0       1 = test_bit
  *	1			clear_bit
- *	2			del_timer_sync
+ *	2			timer_delete_sync
  *	3	mod_timer
  */
 
@@ -1742,7 +1747,7 @@ bnad_iocpf_sem_timeout(struct timer_list *t)
 static void
 bnad_dim_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = from_timer(bnad, t, dim_timer);
+	struct bnad *bnad = timer_container_of(bnad, t, dim_timer);
 	struct bnad_rx_info *rx_info;
 	struct bnad_rx_ctrl *rx_ctrl;
 	int i, j;
@@ -1775,7 +1780,7 @@ bnad_dim_timeout(struct timer_list *t)
 static void
 bnad_stats_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = from_timer(bnad, t, stats_timer);
+	struct bnad *bnad = timer_container_of(bnad, t, stats_timer);
 	unsigned long flags;
 
 	if (!netif_running(bnad->netdev) ||
@@ -1836,7 +1841,7 @@ bnad_stats_timer_stop(struct bnad *bnad)
 		to_del = 1;
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 	if (to_del)
-		del_timer_sync(&bnad->stats_timer);
+		timer_delete_sync(&bnad->stats_timer);
 }
 
 /* Utilities */
@@ -2159,7 +2164,7 @@ bnad_destroy_rx(struct bnad *bnad, u32 rx_id)
 		}
 		spin_unlock_irqrestore(&bnad->bna_lock, flags);
 		if (to_del)
-			del_timer_sync(&bnad->dim_timer);
+			timer_delete_sync(&bnad->dim_timer);
 	}
 
 	init_completion(&bnad->bnad_completions.rx_comp);
@@ -3725,9 +3730,9 @@ probe_uninit:
 	bnad_res_free(bnad, &bnad->mod_res_info[0], BNA_MOD_RES_T_MAX);
 disable_ioceth:
 	bnad_ioceth_disable(bnad);
-	del_timer_sync(&bnad->bna.ioceth.ioc.ioc_timer);
-	del_timer_sync(&bnad->bna.ioceth.ioc.sem_timer);
-	del_timer_sync(&bnad->bna.ioceth.ioc.hb_timer);
+	timer_delete_sync(&bnad->bna.ioceth.ioc.ioc_timer);
+	timer_delete_sync(&bnad->bna.ioceth.ioc.sem_timer);
+	timer_delete_sync(&bnad->bna.ioceth.ioc.hb_timer);
 	spin_lock_irqsave(&bnad->bna_lock, flags);
 	bna_uninit(bna);
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
@@ -3768,9 +3773,9 @@ bnad_pci_remove(struct pci_dev *pdev)
 
 	mutex_lock(&bnad->conf_mutex);
 	bnad_ioceth_disable(bnad);
-	del_timer_sync(&bnad->bna.ioceth.ioc.ioc_timer);
-	del_timer_sync(&bnad->bna.ioceth.ioc.sem_timer);
-	del_timer_sync(&bnad->bna.ioceth.ioc.hb_timer);
+	timer_delete_sync(&bnad->bna.ioceth.ioc.ioc_timer);
+	timer_delete_sync(&bnad->bna.ioceth.ioc.sem_timer);
+	timer_delete_sync(&bnad->bna.ioceth.ioc.hb_timer);
 	spin_lock_irqsave(&bnad->bna_lock, flags);
 	bna_uninit(bna);
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
index d1ad6c9f8140..216e25f26dbb 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
@@ -373,7 +373,7 @@ static int bnad_set_coalesce(struct net_device *netdev,
 			}
 			spin_unlock_irqrestore(&bnad->bna_lock, flags);
 			if (to_del)
-				del_timer_sync(&bnad->dim_timer);
+				timer_delete_sync(&bnad->dim_timer);
 			spin_lock_irqsave(&bnad->bna_lock, flags);
 			bnad_rx_coalescing_timeo_set(bnad);
 		}
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 5740c98d8c9f..87414a2ddf6e 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -15,10 +15,6 @@
 #include <linux/phy/phy.h>
 #include <linux/workqueue.h>
 
-#if defined(CONFIG_ARCH_DMA_ADDR_T_64BIT) || defined(CONFIG_MACB_USE_HWSTAMP)
-#define MACB_EXT_DESC
-#endif
-
 #define MACB_GREGS_NBR 16
 #define MACB_GREGS_VERSION 2
 #define MACB_MAX_QUEUES 8
@@ -184,6 +180,13 @@
 #define GEM_DCFG8		0x029C /* Design Config 8 */
 #define GEM_DCFG10		0x02A4 /* Design Config 10 */
 #define GEM_DCFG12		0x02AC /* Design Config 12 */
+#define GEM_ENST_START_TIME_Q0	0x0800 /* ENST Q0 start time */
+#define GEM_ENST_START_TIME_Q1	0x0804 /* ENST Q1 start time */
+#define GEM_ENST_ON_TIME_Q0	0x0820 /* ENST Q0 on time */
+#define GEM_ENST_ON_TIME_Q1	0x0824 /* ENST Q1 on time */
+#define GEM_ENST_OFF_TIME_Q0	0x0840 /* ENST Q0 off time */
+#define GEM_ENST_OFF_TIME_Q1	0x0844 /* ENST Q1 off time */
+#define GEM_ENST_CONTROL	0x0880 /* ENST control register */
 #define GEM_USX_CONTROL		0x0A80 /* High speed PCS control register */
 #define GEM_USX_STATUS		0x0A88 /* High speed PCS status register */
 
@@ -213,14 +216,19 @@
 
 #define GEM_ISR(hw_q)		(0x0400 + ((hw_q) << 2))
 #define GEM_TBQP(hw_q)		(0x0440 + ((hw_q) << 2))
-#define GEM_TBQPH(hw_q)		(0x04C8)
 #define GEM_RBQP(hw_q)		(0x0480 + ((hw_q) << 2))
 #define GEM_RBQS(hw_q)		(0x04A0 + ((hw_q) << 2))
-#define GEM_RBQPH(hw_q)		(0x04D4)
 #define GEM_IER(hw_q)		(0x0600 + ((hw_q) << 2))
 #define GEM_IDR(hw_q)		(0x0620 + ((hw_q) << 2))
 #define GEM_IMR(hw_q)		(0x0640 + ((hw_q) << 2))
 
+#define GEM_ENST_START_TIME(hw_q)	(0x0800 + ((hw_q) << 2))
+#define GEM_ENST_ON_TIME(hw_q)		(0x0820 + ((hw_q) << 2))
+#define GEM_ENST_OFF_TIME(hw_q)		(0x0840 + ((hw_q) << 2))
+
+/* Bitfields in ENST_CONTROL */
+#define GEM_ENST_DISABLE_QUEUE_OFFSET	16
+
 /* Bitfields in NCR */
 #define MACB_LB_OFFSET		0 /* reserved */
 #define MACB_LB_SIZE		1
@@ -529,6 +537,8 @@
 /* Bitfields in DCFG6. */
 #define GEM_PBUF_LSO_OFFSET			27
 #define GEM_PBUF_LSO_SIZE			1
+#define GEM_PBUF_RSC_OFFSET			26
+#define GEM_PBUF_RSC_SIZE			1
 #define GEM_PBUF_CUTTHRU_OFFSET			25
 #define GEM_PBUF_CUTTHRU_SIZE			1
 #define GEM_DAW64_OFFSET			23
@@ -554,6 +564,23 @@
 #define GEM_HIGH_SPEED_OFFSET			26
 #define GEM_HIGH_SPEED_SIZE			1
 
+/* Bitfields in ENST_START_TIME_Qx. */
+#define GEM_START_TIME_SEC_OFFSET		30
+#define GEM_START_TIME_SEC_SIZE			2
+#define GEM_START_TIME_NSEC_OFFSET		0
+#define GEM_START_TIME_NSEC_SIZE		30
+
+/* Bitfields in ENST_ON_TIME_Qx. */
+#define GEM_ON_TIME_OFFSET			0
+#define GEM_ON_TIME_SIZE			17
+
+/* Bitfields in ENST_OFF_TIME_Qx. */
+#define GEM_OFF_TIME_OFFSET			0
+#define GEM_OFF_TIME_SIZE			17
+
+/* Hardware ENST timing registers granularity */
+#define ENST_TIME_GRANULARITY_NS		8
+
 /* Bitfields in USX_CONTROL. */
 #define GEM_USX_CTRL_SPEED_OFFSET		14
 #define GEM_USX_CTRL_SPEED_SIZE			3
@@ -727,26 +754,31 @@
 #define MACB_MAN_C45_CODE			2
 
 /* Capability mask bits */
-#define MACB_CAPS_ISR_CLEAR_ON_WRITE		0x00000001
-#define MACB_CAPS_USRIO_HAS_CLKEN		0x00000002
-#define MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII	0x00000004
-#define MACB_CAPS_NO_GIGABIT_HALF		0x00000008
-#define MACB_CAPS_USRIO_DISABLED		0x00000010
-#define MACB_CAPS_JUMBO				0x00000020
-#define MACB_CAPS_GEM_HAS_PTP			0x00000040
-#define MACB_CAPS_BD_RD_PREFETCH		0x00000080
-#define MACB_CAPS_NEEDS_RSTONUBR		0x00000100
-#define MACB_CAPS_MIIONRGMII			0x00000200
-#define MACB_CAPS_NEED_TSUCLK			0x00000400
-#define MACB_CAPS_QUEUE_DISABLE			0x00000800
-#define MACB_CAPS_PCS				0x01000000
-#define MACB_CAPS_HIGH_SPEED			0x02000000
-#define MACB_CAPS_CLK_HW_CHG			0x04000000
-#define MACB_CAPS_MACB_IS_EMAC			0x08000000
-#define MACB_CAPS_FIFO_MODE			0x10000000
-#define MACB_CAPS_GIGABIT_MODE_AVAILABLE	0x20000000
-#define MACB_CAPS_SG_DISABLED			0x40000000
-#define MACB_CAPS_MACB_IS_GEM			0x80000000
+#define MACB_CAPS_ISR_CLEAR_ON_WRITE		BIT(0)
+#define MACB_CAPS_USRIO_HAS_CLKEN		BIT(1)
+#define MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII	BIT(2)
+#define MACB_CAPS_NO_GIGABIT_HALF		BIT(3)
+#define MACB_CAPS_USRIO_DISABLED		BIT(4)
+#define MACB_CAPS_JUMBO				BIT(5)
+#define MACB_CAPS_GEM_HAS_PTP			BIT(6)
+#define MACB_CAPS_BD_RD_PREFETCH		BIT(7)
+#define MACB_CAPS_NEEDS_RSTONUBR		BIT(8)
+#define MACB_CAPS_MIIONRGMII			BIT(9)
+#define MACB_CAPS_NEED_TSUCLK			BIT(10)
+#define MACB_CAPS_QUEUE_DISABLE			BIT(11)
+#define MACB_CAPS_QBV				BIT(12)
+#define MACB_CAPS_PCS				BIT(13)
+#define MACB_CAPS_HIGH_SPEED			BIT(14)
+#define MACB_CAPS_CLK_HW_CHG			BIT(15)
+#define MACB_CAPS_MACB_IS_EMAC			BIT(16)
+#define MACB_CAPS_FIFO_MODE			BIT(17)
+#define MACB_CAPS_GIGABIT_MODE_AVAILABLE	BIT(18)
+#define MACB_CAPS_SG_DISABLED			BIT(19)
+#define MACB_CAPS_MACB_IS_GEM			BIT(20)
+#define MACB_CAPS_DMA_64B			BIT(21)
+#define MACB_CAPS_DMA_PTP			BIT(22)
+#define MACB_CAPS_RSC				BIT(23)
+#define MACB_CAPS_NO_LSO			BIT(24)
 
 /* LSO settings */
 #define MACB_LSO_UFO_ENABLE			0x01
@@ -823,12 +855,6 @@ struct macb_dma_desc {
 	u32	ctrl;
 };
 
-#ifdef MACB_EXT_DESC
-#define HW_DMA_CAP_32B		0
-#define HW_DMA_CAP_64B		(1 << 0)
-#define HW_DMA_CAP_PTP		(1 << 1)
-#define HW_DMA_CAP_64B_PTP	(HW_DMA_CAP_64B | HW_DMA_CAP_PTP)
-
 struct macb_dma_desc_64 {
 	u32 addrh;
 	u32 resvd;
@@ -838,7 +864,6 @@ struct macb_dma_desc_ptp {
 	u32	ts_1;
 	u32	ts_2;
 };
-#endif
 
 /* DMA descriptor bitfields */
 #define MACB_RX_USED_OFFSET			0
@@ -951,75 +976,73 @@ struct macb_tx_skb {
  * device stats by a periodic timer.
  */
 struct macb_stats {
-	u32	rx_pause_frames;
-	u32	tx_ok;
-	u32	tx_single_cols;
-	u32	tx_multiple_cols;
-	u32	rx_ok;
-	u32	rx_fcs_errors;
-	u32	rx_align_errors;
-	u32	tx_deferred;
-	u32	tx_late_cols;
-	u32	tx_excessive_cols;
-	u32	tx_underruns;
-	u32	tx_carrier_errors;
-	u32	rx_resource_errors;
-	u32	rx_overruns;
-	u32	rx_symbol_errors;
-	u32	rx_oversize_pkts;
-	u32	rx_jabbers;
-	u32	rx_undersize_pkts;
-	u32	sqe_test_errors;
-	u32	rx_length_mismatch;
-	u32	tx_pause_frames;
+	u64	rx_pause_frames;
+	u64	tx_ok;
+	u64	tx_single_cols;
+	u64	tx_multiple_cols;
+	u64	rx_ok;
+	u64	rx_fcs_errors;
+	u64	rx_align_errors;
+	u64	tx_deferred;
+	u64	tx_late_cols;
+	u64	tx_excessive_cols;
+	u64	tx_underruns;
+	u64	tx_carrier_errors;
+	u64	rx_resource_errors;
+	u64	rx_overruns;
+	u64	rx_symbol_errors;
+	u64	rx_oversize_pkts;
+	u64	rx_jabbers;
+	u64	rx_undersize_pkts;
+	u64	sqe_test_errors;
+	u64	rx_length_mismatch;
+	u64	tx_pause_frames;
 };
 
 struct gem_stats {
-	u32	tx_octets_31_0;
-	u32	tx_octets_47_32;
-	u32	tx_frames;
-	u32	tx_broadcast_frames;
-	u32	tx_multicast_frames;
-	u32	tx_pause_frames;
-	u32	tx_64_byte_frames;
-	u32	tx_65_127_byte_frames;
-	u32	tx_128_255_byte_frames;
-	u32	tx_256_511_byte_frames;
-	u32	tx_512_1023_byte_frames;
-	u32	tx_1024_1518_byte_frames;
-	u32	tx_greater_than_1518_byte_frames;
-	u32	tx_underrun;
-	u32	tx_single_collision_frames;
-	u32	tx_multiple_collision_frames;
-	u32	tx_excessive_collisions;
-	u32	tx_late_collisions;
-	u32	tx_deferred_frames;
-	u32	tx_carrier_sense_errors;
-	u32	rx_octets_31_0;
-	u32	rx_octets_47_32;
-	u32	rx_frames;
-	u32	rx_broadcast_frames;
-	u32	rx_multicast_frames;
-	u32	rx_pause_frames;
-	u32	rx_64_byte_frames;
-	u32	rx_65_127_byte_frames;
-	u32	rx_128_255_byte_frames;
-	u32	rx_256_511_byte_frames;
-	u32	rx_512_1023_byte_frames;
-	u32	rx_1024_1518_byte_frames;
-	u32	rx_greater_than_1518_byte_frames;
-	u32	rx_undersized_frames;
-	u32	rx_oversize_frames;
-	u32	rx_jabbers;
-	u32	rx_frame_check_sequence_errors;
-	u32	rx_length_field_frame_errors;
-	u32	rx_symbol_errors;
-	u32	rx_alignment_errors;
-	u32	rx_resource_errors;
-	u32	rx_overruns;
-	u32	rx_ip_header_checksum_errors;
-	u32	rx_tcp_checksum_errors;
-	u32	rx_udp_checksum_errors;
+	u64	tx_octets;
+	u64	tx_frames;
+	u64	tx_broadcast_frames;
+	u64	tx_multicast_frames;
+	u64	tx_pause_frames;
+	u64	tx_64_byte_frames;
+	u64	tx_65_127_byte_frames;
+	u64	tx_128_255_byte_frames;
+	u64	tx_256_511_byte_frames;
+	u64	tx_512_1023_byte_frames;
+	u64	tx_1024_1518_byte_frames;
+	u64	tx_greater_than_1518_byte_frames;
+	u64	tx_underrun;
+	u64	tx_single_collision_frames;
+	u64	tx_multiple_collision_frames;
+	u64	tx_excessive_collisions;
+	u64	tx_late_collisions;
+	u64	tx_deferred_frames;
+	u64	tx_carrier_sense_errors;
+	u64	rx_octets;
+	u64	rx_frames;
+	u64	rx_broadcast_frames;
+	u64	rx_multicast_frames;
+	u64	rx_pause_frames;
+	u64	rx_64_byte_frames;
+	u64	rx_65_127_byte_frames;
+	u64	rx_128_255_byte_frames;
+	u64	rx_256_511_byte_frames;
+	u64	rx_512_1023_byte_frames;
+	u64	rx_1024_1518_byte_frames;
+	u64	rx_greater_than_1518_byte_frames;
+	u64	rx_undersized_frames;
+	u64	rx_oversize_frames;
+	u64	rx_jabbers;
+	u64	rx_frame_check_sequence_errors;
+	u64	rx_length_field_frame_errors;
+	u64	rx_symbol_errors;
+	u64	rx_alignment_errors;
+	u64	rx_resource_errors;
+	u64	rx_overruns;
+	u64	rx_ip_header_checksum_errors;
+	u64	rx_tcp_checksum_errors;
+	u64	rx_udp_checksum_errors;
 };
 
 /* Describes the name and offset of an individual statistic register, as
@@ -1027,7 +1050,7 @@ struct gem_stats {
  * this register should contribute to.
  */
 struct gem_statistic {
-	char stat_string[ETH_GSTRING_LEN];
+	char stat_string[ETH_GSTRING_LEN] __nonstring;
 	int offset;
 	u32 stat_bits;
 };
@@ -1216,10 +1239,13 @@ struct macb_queue {
 	unsigned int		IDR;
 	unsigned int		IMR;
 	unsigned int		TBQP;
-	unsigned int		TBQPH;
 	unsigned int		RBQS;
 	unsigned int		RBQP;
-	unsigned int		RBQPH;
+
+	/* ENST register offsets for this queue */
+	unsigned int		ENST_START_TIME;
+	unsigned int		ENST_ON_TIME;
+	unsigned int		ENST_OFF_TIME;
 
 	/* Lock to protect tx_head and tx_tail */
 	spinlock_t		tx_ptr_lock;
@@ -1268,7 +1294,6 @@ struct macb {
 	unsigned int		tx_ring_size;
 
 	unsigned int		num_queues;
-	unsigned int		queue_mask;
 	struct macb_queue	queues[MACB_MAX_QUEUES];
 
 	spinlock_t		lock;
@@ -1279,6 +1304,8 @@ struct macb {
 	struct clk		*rx_clk;
 	struct clk		*tsu_clk;
 	struct net_device	*dev;
+	/* Protects hw_stats and ethtool_stats */
+	spinlock_t		stats_lock;
 	union {
 		struct macb_stats	macb;
 		struct gem_stats	gem;
@@ -1314,11 +1341,8 @@ struct macb {
 
 	struct macb_ptp_info	*ptp_info;	/* macb-ptp interface */
 
-	struct phy		*sgmii_phy;	/* for ZynqMP SGMII mode */
+	struct phy		*phy;
 
-#ifdef MACB_EXT_DESC
-	uint8_t hw_dma_cap;
-#endif
 	spinlock_t tsu_clk_lock; /* gem tsu clock locking */
 	unsigned int tsu_rate;
 	struct ptp_clock *ptp_clock;
@@ -1397,6 +1421,31 @@ static inline bool gem_has_ptp(struct macb *bp)
 	return IS_ENABLED(CONFIG_MACB_USE_HWSTAMP) && (bp->caps & MACB_CAPS_GEM_HAS_PTP);
 }
 
+/* ENST Helper functions */
+static inline u64 enst_ns_to_hw_units(size_t ns, u32 speed_mbps)
+{
+	return DIV_ROUND_UP((ns) * (speed_mbps),
+			    (ENST_TIME_GRANULARITY_NS * 1000));
+}
+
+static inline u64 enst_max_hw_interval(u32 speed_mbps)
+{
+	return DIV_ROUND_UP(GENMASK(GEM_ON_TIME_SIZE - 1, 0) *
+			    ENST_TIME_GRANULARITY_NS * 1000, (speed_mbps));
+}
+
+static inline bool macb_dma64(struct macb *bp)
+{
+	return IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) &&
+	       bp->caps & MACB_CAPS_DMA_64B;
+}
+
+static inline bool macb_dma_ptp(struct macb *bp)
+{
+	return IS_ENABLED(CONFIG_MACB_USE_HWSTAMP) &&
+	       bp->caps & MACB_CAPS_DMA_PTP;
+}
+
 /**
  * struct macb_platform_data - platform data for MACB Ethernet used for PCI registration
  * @pclk:		platform clock
@@ -1407,4 +1456,21 @@ struct macb_platform_data {
 	struct clk	*hclk;
 };
 
+/**
+ * struct macb_queue_enst_config - Configuration for Enhanced Scheduled Traffic
+ * @start_time_mask:  Bitmask representing the start time for the queue
+ * @on_time_bytes:    "on" time nsec expressed in bytes
+ * @off_time_bytes:   "off" time nsec expressed in bytes
+ * @queue_id:         Identifier for the queue
+ *
+ * This structure holds the configuration parameters for an ENST queue,
+ * used to control time-based transmission scheduling in the MACB driver.
+ */
+struct macb_queue_enst_config {
+	u32 start_time_mask;
+	u32 on_time_bytes;
+	u32 off_time_bytes;
+	u8 queue_id;
+};
+
 #endif /* _MACB_H */
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 640f500f989d..e461f5072884 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -6,39 +6,37 @@
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/clk.h>
+#include <linux/circ_buf.h>
 #include <linux/clk-provider.h>
+#include <linux/clk.h>
 #include <linux/crc32.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/circ_buf.h>
-#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+#include <linux/etherdevice.h>
+#include <linux/firmware/xlnx-zynqmp.h>
+#include <linux/inetdevice.h>
 #include <linux/init.h>
-#include <linux/io.h>
-#include <linux/gpio.h>
-#include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/ip.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/dma-mapping.h>
-#include <linux/platform_device.h>
-#include <linux/phylink.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
-#include <linux/ip.h>
-#include <linux/udp.h>
-#include <linux/tcp.h>
-#include <linux/iopoll.h>
 #include <linux/phy/phy.h>
+#include <linux/phylink.h>
+#include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/ptp_classify.h>
 #include <linux/reset.h>
-#include <linux/firmware/xlnx-zynqmp.h>
-#include <linux/inetdevice.h>
+#include <linux/slab.h>
+#include <linux/tcp.h>
+#include <linux/types.h>
+#include <linux/udp.h>
+#include <net/pkt_sched.h>
 #include "macb.h"
 
 /* This structure is only used for MACB on SiFive FU540 devices */
@@ -54,14 +52,10 @@ struct sifive_fu540_macb_mgmt {
 #define DEFAULT_RX_RING_SIZE	512 /* must be power of 2 */
 #define MIN_RX_RING_SIZE	64
 #define MAX_RX_RING_SIZE	8192
-#define RX_RING_BYTES(bp)	(macb_dma_desc_get_size(bp)	\
-				 * (bp)->rx_ring_size)
 
 #define DEFAULT_TX_RING_SIZE	512 /* must be power of 2 */
 #define MIN_TX_RING_SIZE	64
 #define MAX_TX_RING_SIZE	4096
-#define TX_RING_BYTES(bp)	(macb_dma_desc_get_size(bp)	\
-				 * (bp)->tx_ring_size)
 
 /* level of occupied TX descriptors under which we wake up TX process */
 #define MACB_TX_WAKEUP_THRESH(bp)	(3 * (bp)->tx_ring_size / 4)
@@ -127,56 +121,26 @@ struct sifive_fu540_macb_mgmt {
  */
 static unsigned int macb_dma_desc_get_size(struct macb *bp)
 {
-#ifdef MACB_EXT_DESC
-	unsigned int desc_size;
+	unsigned int desc_size = sizeof(struct macb_dma_desc);
+
+	if (macb_dma64(bp))
+		desc_size += sizeof(struct macb_dma_desc_64);
+	if (macb_dma_ptp(bp))
+		desc_size += sizeof(struct macb_dma_desc_ptp);
 
-	switch (bp->hw_dma_cap) {
-	case HW_DMA_CAP_64B:
-		desc_size = sizeof(struct macb_dma_desc)
-			+ sizeof(struct macb_dma_desc_64);
-		break;
-	case HW_DMA_CAP_PTP:
-		desc_size = sizeof(struct macb_dma_desc)
-			+ sizeof(struct macb_dma_desc_ptp);
-		break;
-	case HW_DMA_CAP_64B_PTP:
-		desc_size = sizeof(struct macb_dma_desc)
-			+ sizeof(struct macb_dma_desc_64)
-			+ sizeof(struct macb_dma_desc_ptp);
-		break;
-	default:
-		desc_size = sizeof(struct macb_dma_desc);
-	}
 	return desc_size;
-#endif
-	return sizeof(struct macb_dma_desc);
 }
 
 static unsigned int macb_adj_dma_desc_idx(struct macb *bp, unsigned int desc_idx)
 {
-#ifdef MACB_EXT_DESC
-	switch (bp->hw_dma_cap) {
-	case HW_DMA_CAP_64B:
-	case HW_DMA_CAP_PTP:
-		desc_idx <<= 1;
-		break;
-	case HW_DMA_CAP_64B_PTP:
-		desc_idx *= 3;
-		break;
-	default:
-		break;
-	}
-#endif
-	return desc_idx;
+	return desc_idx * (1 + macb_dma64(bp) + macb_dma_ptp(bp));
 }
 
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
 static struct macb_dma_desc_64 *macb_64b_desc(struct macb *bp, struct macb_dma_desc *desc)
 {
 	return (struct macb_dma_desc_64 *)((void *)desc
 		+ sizeof(struct macb_dma_desc));
 }
-#endif
 
 /* Ring buffer accessors */
 static unsigned int macb_tx_ring_wrap(struct macb *bp, unsigned int index)
@@ -281,9 +245,9 @@ static void macb_set_hwaddr(struct macb *bp)
 	u32 bottom;
 	u16 top;
 
-	bottom = cpu_to_le32(*((u32 *)bp->dev->dev_addr));
+	bottom = get_unaligned_le32(bp->dev->dev_addr);
 	macb_or_gem_writel(bp, SA1B, bottom);
-	top = cpu_to_le16(*((u16 *)(bp->dev->dev_addr + 4)));
+	top = get_unaligned_le16(bp->dev->dev_addr + 4);
 	macb_or_gem_writel(bp, SA1T, top);
 
 	if (gem_has_ptp(bp)) {
@@ -363,7 +327,6 @@ static int macb_mdio_read_c22(struct mii_bus *bus, int mii_id, int regnum)
 	status = MACB_BFEXT(DATA, macb_readl(bp, MAN));
 
 mdio_read_exit:
-	pm_runtime_mark_last_busy(&bp->pdev->dev);
 	pm_runtime_put_autosuspend(&bp->pdev->dev);
 mdio_pm_exit:
 	return status;
@@ -409,7 +372,6 @@ static int macb_mdio_read_c45(struct mii_bus *bus, int mii_id, int devad,
 	status = MACB_BFEXT(DATA, macb_readl(bp, MAN));
 
 mdio_read_exit:
-	pm_runtime_mark_last_busy(&bp->pdev->dev);
 	pm_runtime_put_autosuspend(&bp->pdev->dev);
 mdio_pm_exit:
 	return status;
@@ -441,7 +403,6 @@ static int macb_mdio_write_c22(struct mii_bus *bus, int mii_id, int regnum,
 		goto mdio_write_exit;
 
 mdio_write_exit:
-	pm_runtime_mark_last_busy(&bp->pdev->dev);
 	pm_runtime_put_autosuspend(&bp->pdev->dev);
 mdio_pm_exit:
 	return status;
@@ -487,7 +448,6 @@ static int macb_mdio_write_c45(struct mii_bus *bus, int mii_id,
 		goto mdio_write_exit;
 
 mdio_write_exit:
-	pm_runtime_mark_last_busy(&bp->pdev->dev);
 	pm_runtime_put_autosuspend(&bp->pdev->dev);
 mdio_pm_exit:
 	return status;
@@ -498,19 +458,17 @@ static void macb_init_buffers(struct macb *bp)
 	struct macb_queue *queue;
 	unsigned int q;
 
+	/* Single register for all queues' high 32 bits. */
+	if (macb_dma64(bp)) {
+		macb_writel(bp, RBQPH,
+			    upper_32_bits(bp->queues[0].rx_ring_dma));
+		macb_writel(bp, TBQPH,
+			    upper_32_bits(bp->queues[0].tx_ring_dma));
+	}
+
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
 		queue_writel(queue, RBQP, lower_32_bits(queue->rx_ring_dma));
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-		if (bp->hw_dma_cap & HW_DMA_CAP_64B)
-			queue_writel(queue, RBQPH,
-				     upper_32_bits(queue->rx_ring_dma));
-#endif
 		queue_writel(queue, TBQP, lower_32_bits(queue->tx_ring_dma));
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-		if (bp->hw_dma_cap & HW_DMA_CAP_64B)
-			queue_writel(queue, TBQPH,
-				     upper_32_bits(queue->tx_ring_dma));
-#endif
 	}
 }
 
@@ -568,6 +526,7 @@ static void macb_usx_pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode,
 }
 
 static void macb_usx_pcs_get_state(struct phylink_pcs *pcs,
+				   unsigned int neg_mode,
 				   struct phylink_link_state *state)
 {
 	struct macb *bp = container_of(pcs, struct macb, phylink_usx_pcs);
@@ -598,7 +557,7 @@ static int macb_usx_pcs_config(struct phylink_pcs *pcs,
 	return 0;
 }
 
-static void macb_pcs_get_state(struct phylink_pcs *pcs,
+static void macb_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode,
 			       struct phylink_link_state *state)
 {
 	state->link = 0;
@@ -852,9 +811,7 @@ static int macb_mii_probe(struct net_device *dev)
 	struct macb *bp = netdev_priv(dev);
 
 	bp->phylink_sgmii_pcs.ops = &macb_phylink_pcs_ops;
-	bp->phylink_sgmii_pcs.neg_mode = true;
 	bp->phylink_usx_pcs.ops = &macb_phylink_usx_pcs_ops;
-	bp->phylink_usx_pcs.neg_mode = true;
 
 	bp->phylink_config.dev = &dev->dev;
 	bp->phylink_config.type = PHYLINK_NETDEV;
@@ -989,8 +946,8 @@ err_out:
 
 static void macb_update_stats(struct macb *bp)
 {
-	u32 *p = &bp->hw_stats.macb.rx_pause_frames;
-	u32 *end = &bp->hw_stats.macb.tx_pause_frames + 1;
+	u64 *p = &bp->hw_stats.macb.rx_pause_frames;
+	u64 *end = &bp->hw_stats.macb.tx_pause_frames + 1;
 	int offset = MACB_PFR;
 
 	WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4);
@@ -1001,22 +958,15 @@ static void macb_update_stats(struct macb *bp)
 
 static int macb_halt_tx(struct macb *bp)
 {
-	unsigned long	halt_time, timeout;
-	u32		status;
+	u32 status;
 
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(THALT));
 
-	timeout = jiffies + usecs_to_jiffies(MACB_HALT_TIMEOUT);
-	do {
-		halt_time = jiffies;
-		status = macb_readl(bp, TSR);
-		if (!(status & MACB_BIT(TGO)))
-			return 0;
-
-		udelay(250);
-	} while (time_before(halt_time, timeout));
-
-	return -ETIMEDOUT;
+	/* Poll TSR until TGO is cleared or timeout. */
+	return read_poll_timeout_atomic(macb_readl, status,
+					!(status & MACB_BIT(TGO)),
+					250, MACB_HALT_TIMEOUT, false,
+					bp, TSR);
 }
 
 static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb, int budget)
@@ -1039,10 +989,9 @@ static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb, int budge
 
 static void macb_set_addr(struct macb *bp, struct macb_dma_desc *desc, dma_addr_t addr)
 {
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	struct macb_dma_desc_64 *desc_64;
+	if (macb_dma64(bp)) {
+		struct macb_dma_desc_64 *desc_64;
 
-	if (bp->hw_dma_cap & HW_DMA_CAP_64B) {
 		desc_64 = macb_64b_desc(bp, desc);
 		desc_64->addrh = upper_32_bits(addr);
 		/* The low bits of RX address contain the RX_USED bit, clearing
@@ -1051,26 +1000,23 @@ static void macb_set_addr(struct macb *bp, struct macb_dma_desc *desc, dma_addr_
 		 */
 		dma_wmb();
 	}
-#endif
+
 	desc->addr = lower_32_bits(addr);
 }
 
 static dma_addr_t macb_get_addr(struct macb *bp, struct macb_dma_desc *desc)
 {
 	dma_addr_t addr = 0;
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	struct macb_dma_desc_64 *desc_64;
 
-	if (bp->hw_dma_cap & HW_DMA_CAP_64B) {
+	if (macb_dma64(bp)) {
+		struct macb_dma_desc_64 *desc_64;
+
 		desc_64 = macb_64b_desc(bp, desc);
 		addr = ((u64)(desc_64->addrh) << 32);
 	}
-#endif
 	addr |= MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr));
-#ifdef CONFIG_MACB_USE_HWSTAMP
-	if (bp->hw_dma_cap & HW_DMA_CAP_PTP)
+	if (macb_dma_ptp(bp))
 		addr &= ~GEM_BIT(DMA_RXVALID);
-#endif
 	return addr;
 }
 
@@ -1080,15 +1026,18 @@ static void macb_tx_error_task(struct work_struct *work)
 						      tx_error_task);
 	bool			halt_timeout = false;
 	struct macb		*bp = queue->bp;
+	u32			queue_index;
+	u32			packets = 0;
+	u32			bytes = 0;
 	struct macb_tx_skb	*tx_skb;
 	struct macb_dma_desc	*desc;
 	struct sk_buff		*skb;
 	unsigned int		tail;
 	unsigned long		flags;
 
+	queue_index = queue - bp->queues;
 	netdev_vdbg(bp->dev, "macb_tx_error_task: q = %u, t = %u, h = %u\n",
-		    (unsigned int)(queue - bp->queues),
-		    queue->tx_tail, queue->tx_head);
+		    queue_index, queue->tx_tail, queue->tx_head);
 
 	/* Prevent the queue NAPI TX poll from running, as it calls
 	 * macb_tx_complete(), which in turn may call netif_wake_subqueue().
@@ -1141,8 +1090,10 @@ static void macb_tx_error_task(struct work_struct *work)
 					    skb->data);
 				bp->dev->stats.tx_packets++;
 				queue->stats.tx_packets++;
+				packets++;
 				bp->dev->stats.tx_bytes += skb->len;
 				queue->stats.tx_bytes += skb->len;
+				bytes += skb->len;
 			}
 		} else {
 			/* "Buffers exhausted mid-frame" errors may only happen
@@ -1159,6 +1110,9 @@ static void macb_tx_error_task(struct work_struct *work)
 		macb_tx_unmap(bp, tx_skb, 0);
 	}
 
+	netdev_tx_completed_queue(netdev_get_tx_queue(bp->dev, queue_index),
+				  packets, bytes);
+
 	/* Set end of TX queue */
 	desc = macb_tx_desc(queue, 0);
 	macb_set_addr(bp, desc, 0);
@@ -1169,10 +1123,6 @@ static void macb_tx_error_task(struct work_struct *work)
 
 	/* Reinitialize the TX desc queue */
 	queue_writel(queue, TBQP, lower_32_bits(queue->tx_ring_dma));
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	if (bp->hw_dma_cap & HW_DMA_CAP_64B)
-		queue_writel(queue, TBQPH, upper_32_bits(queue->tx_ring_dma));
-#endif
 	/* Make TX ring reflect state of hardware */
 	queue->tx_head = 0;
 	queue->tx_tail = 0;
@@ -1226,11 +1176,13 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 {
 	struct macb *bp = queue->bp;
 	u16 queue_index = queue - bp->queues;
+	unsigned long flags;
 	unsigned int tail;
 	unsigned int head;
 	int packets = 0;
+	u32 bytes = 0;
 
-	spin_lock(&queue->tx_ptr_lock);
+	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
 	head = queue->tx_head;
 	for (tail = queue->tx_tail; tail != head && packets < budget; tail++) {
 		struct macb_tx_skb	*tx_skb;
@@ -1270,6 +1222,7 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 				bp->dev->stats.tx_bytes += skb->len;
 				queue->stats.tx_bytes += skb->len;
 				packets++;
+				bytes += skb->len;
 			}
 
 			/* Now we can safely release resources */
@@ -1284,12 +1237,15 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 		}
 	}
 
+	netdev_tx_completed_queue(netdev_get_tx_queue(bp->dev, queue_index),
+				  packets, bytes);
+
 	queue->tx_tail = tail;
 	if (__netif_subqueue_stopped(bp->dev, queue_index) &&
 	    CIRC_CNT(queue->tx_head, queue->tx_tail,
 		     bp->tx_ring_size) <= MACB_TX_WAKEUP_THRESH(bp))
 		netif_wake_subqueue(bp->dev, queue_index);
-	spin_unlock(&queue->tx_ptr_lock);
+	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
 
 	return packets;
 }
@@ -1340,8 +1296,19 @@ static void gem_rx_refill(struct macb_queue *queue)
 			dma_wmb();
 			macb_set_addr(bp, desc, paddr);
 
-			/* properly align Ethernet header */
-			skb_reserve(skb, NET_IP_ALIGN);
+			/* Properly align Ethernet header.
+			 *
+			 * Hardware can add dummy bytes if asked using the RBOF
+			 * field inside the NCFGR register. That feature isn't
+			 * available if hardware is RSC capable.
+			 *
+			 * We cannot fallback to doing the 2-byte shift before
+			 * DMA mapping because the address field does not allow
+			 * setting the low 2/3 bits.
+			 * It is 3 bits if HW_DMA_CAP_PTP, else 2 bits.
+			 */
+			if (!(bp->caps & MACB_CAPS_RSC))
+				skb_reserve(skb, NET_IP_ALIGN);
 		} else {
 			desc->ctrl = 0;
 			dma_wmb();
@@ -1705,8 +1672,9 @@ static void macb_tx_restart(struct macb_queue *queue)
 {
 	struct macb *bp = queue->bp;
 	unsigned int head_idx, tbqp;
+	unsigned long flags;
 
-	spin_lock(&queue->tx_ptr_lock);
+	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
 
 	if (queue->tx_head == queue->tx_tail)
 		goto out_tx_ptr_unlock;
@@ -1718,19 +1686,20 @@ static void macb_tx_restart(struct macb_queue *queue)
 	if (tbqp == head_idx)
 		goto out_tx_ptr_unlock;
 
-	spin_lock_irq(&bp->lock);
+	spin_lock(&bp->lock);
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
-	spin_unlock_irq(&bp->lock);
+	spin_unlock(&bp->lock);
 
 out_tx_ptr_unlock:
-	spin_unlock(&queue->tx_ptr_lock);
+	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
 }
 
 static bool macb_tx_complete_pending(struct macb_queue *queue)
 {
 	bool retval = false;
+	unsigned long flags;
 
-	spin_lock(&queue->tx_ptr_lock);
+	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
 	if (queue->tx_head != queue->tx_tail) {
 		/* Make hw descriptor updates visible to CPU */
 		rmb();
@@ -1738,7 +1707,7 @@ static bool macb_tx_complete_pending(struct macb_queue *queue)
 		if (macb_tx_desc(queue, queue->tx_tail)->ctrl & MACB_BIT(TX_USED))
 			retval = true;
 	}
-	spin_unlock(&queue->tx_ptr_lock);
+	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
 	return retval;
 }
 
@@ -1977,10 +1946,12 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
 
 		if (status & MACB_BIT(ISR_ROVR)) {
 			/* We missed at least one packet */
+			spin_lock(&bp->stats_lock);
 			if (macb_is_gem(bp))
 				bp->hw_stats.gem.rx_overruns++;
 			else
 				bp->hw_stats.macb.rx_overruns++;
+			spin_unlock(&bp->stats_lock);
 
 			if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
 				queue_writel(queue, ISR, MACB_BIT(ISR_ROVR));
@@ -2024,14 +1995,14 @@ static unsigned int macb_tx_map(struct macb *bp,
 				struct sk_buff *skb,
 				unsigned int hdrlen)
 {
-	dma_addr_t mapping;
-	unsigned int len, entry, i, tx_head = queue->tx_head;
-	struct macb_tx_skb *tx_skb = NULL;
-	struct macb_dma_desc *desc;
-	unsigned int offset, size, count = 0;
 	unsigned int f, nr_frags = skb_shinfo(skb)->nr_frags;
-	unsigned int eof = 1, mss_mfs = 0;
+	unsigned int len, i, tx_head = queue->tx_head;
 	u32 ctrl, lso_ctrl = 0, seq_ctrl = 0;
+	unsigned int eof = 1, mss_mfs = 0;
+	struct macb_tx_skb *tx_skb = NULL;
+	struct macb_dma_desc *desc;
+	unsigned int offset, size;
+	dma_addr_t mapping;
 
 	/* LSO */
 	if (skb_shinfo(skb)->gso_size != 0) {
@@ -2051,8 +2022,7 @@ static unsigned int macb_tx_map(struct macb *bp,
 
 	offset = 0;
 	while (len) {
-		entry = macb_tx_ring_wrap(bp, tx_head);
-		tx_skb = &queue->tx_skb[entry];
+		tx_skb = macb_tx_skb(queue, tx_head);
 
 		mapping = dma_map_single(&bp->pdev->dev,
 					 skb->data + offset,
@@ -2068,10 +2038,9 @@ static unsigned int macb_tx_map(struct macb *bp,
 
 		len -= size;
 		offset += size;
-		count++;
 		tx_head++;
 
-		size = min(len, bp->max_tx_length);
+		size = umin(len, bp->max_tx_length);
 	}
 
 	/* Then, map paged data from fragments */
@@ -2081,9 +2050,8 @@ static unsigned int macb_tx_map(struct macb *bp,
 		len = skb_frag_size(frag);
 		offset = 0;
 		while (len) {
-			size = min(len, bp->max_tx_length);
-			entry = macb_tx_ring_wrap(bp, tx_head);
-			tx_skb = &queue->tx_skb[entry];
+			size = umin(len, bp->max_tx_length);
+			tx_skb = macb_tx_skb(queue, tx_head);
 
 			mapping = skb_frag_dma_map(&bp->pdev->dev, frag,
 						   offset, size, DMA_TO_DEVICE);
@@ -2098,7 +2066,6 @@ static unsigned int macb_tx_map(struct macb *bp,
 
 			len -= size;
 			offset += size;
-			count++;
 			tx_head++;
 		}
 	}
@@ -2120,9 +2087,8 @@ static unsigned int macb_tx_map(struct macb *bp,
 	 * to set the end of TX queue
 	 */
 	i = tx_head;
-	entry = macb_tx_ring_wrap(bp, i);
 	ctrl = MACB_BIT(TX_USED);
-	desc = macb_tx_desc(queue, entry);
+	desc = macb_tx_desc(queue, i);
 	desc->ctrl = ctrl;
 
 	if (lso_ctrl) {
@@ -2142,16 +2108,15 @@ static unsigned int macb_tx_map(struct macb *bp,
 
 	do {
 		i--;
-		entry = macb_tx_ring_wrap(bp, i);
-		tx_skb = &queue->tx_skb[entry];
-		desc = macb_tx_desc(queue, entry);
+		tx_skb = macb_tx_skb(queue, i);
+		desc = macb_tx_desc(queue, i);
 
 		ctrl = (u32)tx_skb->size;
 		if (eof) {
 			ctrl |= MACB_BIT(TX_LAST);
 			eof = 0;
 		}
-		if (unlikely(entry == (bp->tx_ring_size - 1)))
+		if (unlikely(macb_tx_ring_wrap(bp, i) == bp->tx_ring_size - 1))
 			ctrl |= MACB_BIT(TX_WRAP);
 
 		/* First descriptor is header descriptor */
@@ -2179,7 +2144,7 @@ static unsigned int macb_tx_map(struct macb *bp,
 
 	queue->tx_head = tx_head;
 
-	return count;
+	return 0;
 
 dma_error:
 	netdev_err(bp->dev, "TX DMA map failed\n");
@@ -2190,7 +2155,7 @@ dma_error:
 		macb_tx_unmap(bp, tx_skb, 0);
 	}
 
-	return 0;
+	return -ENOMEM;
 }
 
 static netdev_features_t macb_features_check(struct sk_buff *skb,
@@ -2304,6 +2269,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct macb_queue *queue = &bp->queues[queue_index];
 	unsigned int desc_cnt, nr_frags, frag_size, f;
 	unsigned int hdrlen;
+	unsigned long flags;
 	bool is_lso;
 	netdev_tx_t ret = NETDEV_TX_OK;
 
@@ -2317,11 +2283,9 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		return ret;
 	}
 
-#ifdef CONFIG_MACB_USE_HWSTAMP
-	if ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
-	    (bp->hw_dma_cap & HW_DMA_CAP_PTP))
+	if (macb_dma_ptp(bp) &&
+	    (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-#endif
 
 	is_lso = (skb_shinfo(skb)->gso_size != 0);
 
@@ -2338,7 +2302,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			return NETDEV_TX_BUSY;
 		}
 	} else
-		hdrlen = min(skb_headlen(skb), bp->max_tx_length);
+		hdrlen = umin(skb_headlen(skb), bp->max_tx_length);
 
 #if defined(DEBUG) && defined(VERBOSE_DEBUG)
 	netdev_vdbg(bp->dev,
@@ -2364,7 +2328,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		desc_cnt += DIV_ROUND_UP(frag_size, bp->max_tx_length);
 	}
 
-	spin_lock_bh(&queue->tx_ptr_lock);
+	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
 
 	/* This is a hard error, log it. */
 	if (CIRC_SPACE(queue->tx_head, queue->tx_tail,
@@ -2377,7 +2341,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	/* Map socket buffer for DMA transfer */
-	if (!macb_tx_map(bp, queue, skb, hdrlen)) {
+	if (macb_tx_map(bp, queue, skb, hdrlen)) {
 		dev_kfree_skb_any(skb);
 		goto unlock;
 	}
@@ -2385,16 +2349,18 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Make newly initialized descriptor visible to hardware */
 	wmb();
 	skb_tx_timestamp(skb);
+	netdev_tx_sent_queue(netdev_get_tx_queue(bp->dev, queue_index),
+			     skb->len);
 
-	spin_lock_irq(&bp->lock);
+	spin_lock(&bp->lock);
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
-	spin_unlock_irq(&bp->lock);
+	spin_unlock(&bp->lock);
 
 	if (CIRC_SPACE(queue->tx_head, queue->tx_tail, bp->tx_ring_size) < 1)
 		netif_stop_subqueue(dev, queue_index);
 
 unlock:
-	spin_unlock_bh(&queue->tx_ptr_lock);
+	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
 
 	return ret;
 }
@@ -2464,35 +2430,42 @@ static void macb_free_rx_buffers(struct macb *bp)
 	}
 }
 
+static unsigned int macb_tx_ring_size_per_queue(struct macb *bp)
+{
+	return macb_dma_desc_get_size(bp) * bp->tx_ring_size + bp->tx_bd_rd_prefetch;
+}
+
+static unsigned int macb_rx_ring_size_per_queue(struct macb *bp)
+{
+	return macb_dma_desc_get_size(bp) * bp->rx_ring_size + bp->rx_bd_rd_prefetch;
+}
+
 static void macb_free_consistent(struct macb *bp)
 {
+	struct device *dev = &bp->pdev->dev;
 	struct macb_queue *queue;
 	unsigned int q;
-	int size;
+	size_t size;
 
 	if (bp->rx_ring_tieoff) {
-		dma_free_coherent(&bp->pdev->dev, macb_dma_desc_get_size(bp),
+		dma_free_coherent(dev, macb_dma_desc_get_size(bp),
 				  bp->rx_ring_tieoff, bp->rx_ring_tieoff_dma);
 		bp->rx_ring_tieoff = NULL;
 	}
 
 	bp->macbgem_ops.mog_free_rx_buffers(bp);
 
+	size = bp->num_queues * macb_tx_ring_size_per_queue(bp);
+	dma_free_coherent(dev, size, bp->queues[0].tx_ring, bp->queues[0].tx_ring_dma);
+
+	size = bp->num_queues * macb_rx_ring_size_per_queue(bp);
+	dma_free_coherent(dev, size, bp->queues[0].rx_ring, bp->queues[0].rx_ring_dma);
+
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
 		kfree(queue->tx_skb);
 		queue->tx_skb = NULL;
-		if (queue->tx_ring) {
-			size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch;
-			dma_free_coherent(&bp->pdev->dev, size,
-					  queue->tx_ring, queue->tx_ring_dma);
-			queue->tx_ring = NULL;
-		}
-		if (queue->rx_ring) {
-			size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch;
-			dma_free_coherent(&bp->pdev->dev, size,
-					  queue->rx_ring, queue->rx_ring_dma);
-			queue->rx_ring = NULL;
-		}
+		queue->tx_ring = NULL;
+		queue->rx_ring = NULL;
 	}
 }
 
@@ -2534,35 +2507,45 @@ static int macb_alloc_rx_buffers(struct macb *bp)
 
 static int macb_alloc_consistent(struct macb *bp)
 {
+	struct device *dev = &bp->pdev->dev;
+	dma_addr_t tx_dma, rx_dma;
 	struct macb_queue *queue;
 	unsigned int q;
-	int size;
+	void *tx, *rx;
+	size_t size;
+
+	/*
+	 * Upper 32-bits of Tx/Rx DMA descriptor for each queues much match!
+	 * We cannot enforce this guarantee, the best we can do is do a single
+	 * allocation and hope it will land into alloc_pages() that guarantees
+	 * natural alignment of physical addresses.
+	 */
+
+	size = bp->num_queues * macb_tx_ring_size_per_queue(bp);
+	tx = dma_alloc_coherent(dev, size, &tx_dma, GFP_KERNEL);
+	if (!tx || upper_32_bits(tx_dma) != upper_32_bits(tx_dma + size - 1))
+		goto out_err;
+	netdev_dbg(bp->dev, "Allocated %zu bytes for %u TX rings at %08lx (mapped %p)\n",
+		   size, bp->num_queues, (unsigned long)tx_dma, tx);
+
+	size = bp->num_queues * macb_rx_ring_size_per_queue(bp);
+	rx = dma_alloc_coherent(dev, size, &rx_dma, GFP_KERNEL);
+	if (!rx || upper_32_bits(rx_dma) != upper_32_bits(rx_dma + size - 1))
+		goto out_err;
+	netdev_dbg(bp->dev, "Allocated %zu bytes for %u RX rings at %08lx (mapped %p)\n",
+		   size, bp->num_queues, (unsigned long)rx_dma, rx);
 
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-		size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch;
-		queue->tx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
-						    &queue->tx_ring_dma,
-						    GFP_KERNEL);
-		if (!queue->tx_ring)
-			goto out_err;
-		netdev_dbg(bp->dev,
-			   "Allocated TX ring for queue %u of %d bytes at %08lx (mapped %p)\n",
-			   q, size, (unsigned long)queue->tx_ring_dma,
-			   queue->tx_ring);
+		queue->tx_ring = tx + macb_tx_ring_size_per_queue(bp) * q;
+		queue->tx_ring_dma = tx_dma + macb_tx_ring_size_per_queue(bp) * q;
+
+		queue->rx_ring = rx + macb_rx_ring_size_per_queue(bp) * q;
+		queue->rx_ring_dma = rx_dma + macb_rx_ring_size_per_queue(bp) * q;
 
 		size = bp->tx_ring_size * sizeof(struct macb_tx_skb);
 		queue->tx_skb = kmalloc(size, GFP_KERNEL);
 		if (!queue->tx_skb)
 			goto out_err;
-
-		size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch;
-		queue->rx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
-						 &queue->rx_ring_dma, GFP_KERNEL);
-		if (!queue->rx_ring)
-			goto out_err;
-		netdev_dbg(bp->dev,
-			   "Allocated RX ring of %d bytes at %08lx (mapped %p)\n",
-			   size, (unsigned long)queue->rx_ring_dma, queue->rx_ring);
 	}
 	if (bp->macbgem_ops.mog_alloc_rx_buffers(bp))
 		goto out_err;
@@ -2779,14 +2762,10 @@ static void macb_configure_dma(struct macb *bp)
 			dmacfg &= ~GEM_BIT(TXCOEN);
 
 		dmacfg &= ~GEM_BIT(ADDR64);
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-		if (bp->hw_dma_cap & HW_DMA_CAP_64B)
+		if (macb_dma64(bp))
 			dmacfg |= GEM_BIT(ADDR64);
-#endif
-#ifdef CONFIG_MACB_USE_HWSTAMP
-		if (bp->hw_dma_cap & HW_DMA_CAP_PTP)
+		if (macb_dma_ptp(bp))
 			dmacfg |= GEM_BIT(RXEXT) | GEM_BIT(TXEXT);
-#endif
 		netdev_dbg(bp->dev, "Cadence configure DMA with 0x%08x\n",
 			   dmacfg);
 		gem_writel(bp, DMACFG, dmacfg);
@@ -2801,7 +2780,11 @@ static void macb_init_hw(struct macb *bp)
 	macb_set_hwaddr(bp);
 
 	config = macb_mdc_clk_div(bp);
-	config |= MACB_BF(RBOF, NET_IP_ALIGN);	/* Make eth data aligned */
+	/* Make eth data aligned.
+	 * If RSC capable, that offset is ignored by HW.
+	 */
+	if (!(bp->caps & MACB_CAPS_RSC))
+		config |= MACB_BF(RBOF, NET_IP_ALIGN);
 	config |= MACB_BIT(DRFCS);		/* Discard Rx FCS */
 	if (bp->caps & MACB_CAPS_JUMBO)
 		config |= MACB_BIT(JFRAME);	/* Enable jumbo frames */
@@ -2978,7 +2961,11 @@ static int macb_open(struct net_device *dev)
 
 	macb_init_hw(bp);
 
-	err = phy_power_on(bp->sgmii_phy);
+	err = phy_set_mode_ext(bp->phy, PHY_MODE_ETHERNET, bp->phy_interface);
+	if (err)
+		goto reset_hw;
+
+	err = phy_power_on(bp->phy);
 	if (err)
 		goto reset_hw;
 
@@ -2994,7 +2981,7 @@ static int macb_open(struct net_device *dev)
 	return 0;
 
 phy_off:
-	phy_power_off(bp->sgmii_phy);
+	phy_power_off(bp->phy);
 
 reset_hw:
 	macb_reset_hw(bp);
@@ -3020,12 +3007,13 @@ static int macb_close(struct net_device *dev)
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
 		napi_disable(&queue->napi_rx);
 		napi_disable(&queue->napi_tx);
+		netdev_tx_reset_queue(netdev_get_tx_queue(dev, q));
 	}
 
 	phylink_stop(bp->phylink);
 	phylink_disconnect_phy(bp->phylink);
 
-	phy_power_off(bp->sgmii_phy);
+	phy_power_off(bp->phy);
 
 	spin_lock_irqsave(&bp->lock, flags);
 	macb_reset_hw(bp);
@@ -3070,7 +3058,7 @@ static void gem_update_stats(struct macb *bp)
 	unsigned int i, q, idx;
 	unsigned long *stat;
 
-	u32 *p = &bp->hw_stats.gem.tx_octets_31_0;
+	u64 *p = &bp->hw_stats.gem.tx_octets;
 
 	for (i = 0; i < GEM_STATS_LEN; ++i, ++p) {
 		u32 offset = gem_statistics[i].offset;
@@ -3083,7 +3071,7 @@ static void gem_update_stats(struct macb *bp)
 			/* Add GEM_OCTTXH, GEM_OCTRXH */
 			val = bp->macb_reg_readl(bp, offset + 4);
 			bp->ethtool_stats[i] += ((u64)val) << 32;
-			*(++p) += val;
+			*p += ((u64)val) << 32;
 		}
 	}
 
@@ -3093,15 +3081,13 @@ static void gem_update_stats(struct macb *bp)
 			bp->ethtool_stats[idx++] = *stat;
 }
 
-static struct net_device_stats *gem_get_stats(struct macb *bp)
+static void gem_get_stats(struct macb *bp, struct rtnl_link_stats64 *nstat)
 {
 	struct gem_stats *hwstat = &bp->hw_stats.gem;
-	struct net_device_stats *nstat = &bp->dev->stats;
 
-	if (!netif_running(bp->dev))
-		return nstat;
-
-	gem_update_stats(bp);
+	spin_lock_irq(&bp->stats_lock);
+	if (netif_running(bp->dev))
+		gem_update_stats(bp);
 
 	nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors +
 			    hwstat->rx_alignment_errors +
@@ -3130,19 +3116,19 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
 	nstat->tx_aborted_errors = hwstat->tx_excessive_collisions;
 	nstat->tx_carrier_errors = hwstat->tx_carrier_sense_errors;
 	nstat->tx_fifo_errors = hwstat->tx_underrun;
-
-	return nstat;
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 static void gem_get_ethtool_stats(struct net_device *dev,
 				  struct ethtool_stats *stats, u64 *data)
 {
-	struct macb *bp;
+	struct macb *bp = netdev_priv(dev);
 
-	bp = netdev_priv(dev);
+	spin_lock_irq(&bp->stats_lock);
 	gem_update_stats(bp);
 	memcpy(data, &bp->ethtool_stats, sizeof(u64)
 			* (GEM_STATS_LEN + QUEUE_STATS_LEN * MACB_MAX_QUEUES));
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 static int gem_get_sset_count(struct net_device *dev, int sset)
@@ -3182,16 +3168,20 @@ static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p)
 	}
 }
 
-static struct net_device_stats *macb_get_stats(struct net_device *dev)
+static void macb_get_stats(struct net_device *dev,
+			   struct rtnl_link_stats64 *nstat)
 {
 	struct macb *bp = netdev_priv(dev);
-	struct net_device_stats *nstat = &bp->dev->stats;
 	struct macb_stats *hwstat = &bp->hw_stats.macb;
 
-	if (macb_is_gem(bp))
-		return gem_get_stats(bp);
+	netdev_stats_to_stats64(nstat, &bp->dev->stats);
+	if (macb_is_gem(bp)) {
+		gem_get_stats(bp, nstat);
+		return;
+	}
 
 	/* read stats from hardware */
+	spin_lock_irq(&bp->stats_lock);
 	macb_update_stats(bp);
 
 	/* Convert HW stats into netdevice stats */
@@ -3225,8 +3215,171 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev)
 	nstat->tx_carrier_errors = hwstat->tx_carrier_errors;
 	nstat->tx_fifo_errors = hwstat->tx_underruns;
 	/* Don't know about heartbeat or window errors... */
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+static void macb_get_pause_stats(struct net_device *dev,
+				 struct ethtool_pause_stats *pause_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct macb_stats *hwstat = &bp->hw_stats.macb;
+
+	spin_lock_irq(&bp->stats_lock);
+	macb_update_stats(bp);
+	pause_stats->tx_pause_frames = hwstat->tx_pause_frames;
+	pause_stats->rx_pause_frames = hwstat->rx_pause_frames;
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+static void gem_get_pause_stats(struct net_device *dev,
+				struct ethtool_pause_stats *pause_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct gem_stats *hwstat = &bp->hw_stats.gem;
+
+	spin_lock_irq(&bp->stats_lock);
+	gem_update_stats(bp);
+	pause_stats->tx_pause_frames = hwstat->tx_pause_frames;
+	pause_stats->rx_pause_frames = hwstat->rx_pause_frames;
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+static void macb_get_eth_mac_stats(struct net_device *dev,
+				   struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct macb_stats *hwstat = &bp->hw_stats.macb;
+
+	spin_lock_irq(&bp->stats_lock);
+	macb_update_stats(bp);
+	mac_stats->FramesTransmittedOK = hwstat->tx_ok;
+	mac_stats->SingleCollisionFrames = hwstat->tx_single_cols;
+	mac_stats->MultipleCollisionFrames = hwstat->tx_multiple_cols;
+	mac_stats->FramesReceivedOK = hwstat->rx_ok;
+	mac_stats->FrameCheckSequenceErrors = hwstat->rx_fcs_errors;
+	mac_stats->AlignmentErrors = hwstat->rx_align_errors;
+	mac_stats->FramesWithDeferredXmissions = hwstat->tx_deferred;
+	mac_stats->LateCollisions = hwstat->tx_late_cols;
+	mac_stats->FramesAbortedDueToXSColls = hwstat->tx_excessive_cols;
+	mac_stats->FramesLostDueToIntMACXmitError = hwstat->tx_underruns;
+	mac_stats->CarrierSenseErrors = hwstat->tx_carrier_errors;
+	mac_stats->FramesLostDueToIntMACRcvError = hwstat->rx_overruns;
+	mac_stats->InRangeLengthErrors = hwstat->rx_length_mismatch;
+	mac_stats->FrameTooLongErrors = hwstat->rx_oversize_pkts;
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+static void gem_get_eth_mac_stats(struct net_device *dev,
+				  struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct gem_stats *hwstat = &bp->hw_stats.gem;
+
+	spin_lock_irq(&bp->stats_lock);
+	gem_update_stats(bp);
+	mac_stats->FramesTransmittedOK = hwstat->tx_frames;
+	mac_stats->SingleCollisionFrames = hwstat->tx_single_collision_frames;
+	mac_stats->MultipleCollisionFrames =
+		hwstat->tx_multiple_collision_frames;
+	mac_stats->FramesReceivedOK = hwstat->rx_frames;
+	mac_stats->FrameCheckSequenceErrors =
+		hwstat->rx_frame_check_sequence_errors;
+	mac_stats->AlignmentErrors = hwstat->rx_alignment_errors;
+	mac_stats->OctetsTransmittedOK = hwstat->tx_octets;
+	mac_stats->FramesWithDeferredXmissions = hwstat->tx_deferred_frames;
+	mac_stats->LateCollisions = hwstat->tx_late_collisions;
+	mac_stats->FramesAbortedDueToXSColls = hwstat->tx_excessive_collisions;
+	mac_stats->FramesLostDueToIntMACXmitError = hwstat->tx_underrun;
+	mac_stats->CarrierSenseErrors = hwstat->tx_carrier_sense_errors;
+	mac_stats->OctetsReceivedOK = hwstat->rx_octets;
+	mac_stats->MulticastFramesXmittedOK = hwstat->tx_multicast_frames;
+	mac_stats->BroadcastFramesXmittedOK = hwstat->tx_broadcast_frames;
+	mac_stats->MulticastFramesReceivedOK = hwstat->rx_multicast_frames;
+	mac_stats->BroadcastFramesReceivedOK = hwstat->rx_broadcast_frames;
+	mac_stats->InRangeLengthErrors = hwstat->rx_length_field_frame_errors;
+	mac_stats->FrameTooLongErrors = hwstat->rx_oversize_frames;
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+/* TODO: Report SQE test errors when added to phy_stats */
+static void macb_get_eth_phy_stats(struct net_device *dev,
+				   struct ethtool_eth_phy_stats *phy_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct macb_stats *hwstat = &bp->hw_stats.macb;
+
+	spin_lock_irq(&bp->stats_lock);
+	macb_update_stats(bp);
+	phy_stats->SymbolErrorDuringCarrier = hwstat->rx_symbol_errors;
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+static void gem_get_eth_phy_stats(struct net_device *dev,
+				  struct ethtool_eth_phy_stats *phy_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct gem_stats *hwstat = &bp->hw_stats.gem;
+
+	spin_lock_irq(&bp->stats_lock);
+	gem_update_stats(bp);
+	phy_stats->SymbolErrorDuringCarrier = hwstat->rx_symbol_errors;
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+static void macb_get_rmon_stats(struct net_device *dev,
+				struct ethtool_rmon_stats *rmon_stats,
+				const struct ethtool_rmon_hist_range **ranges)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct macb_stats *hwstat = &bp->hw_stats.macb;
+
+	spin_lock_irq(&bp->stats_lock);
+	macb_update_stats(bp);
+	rmon_stats->undersize_pkts = hwstat->rx_undersize_pkts;
+	rmon_stats->oversize_pkts = hwstat->rx_oversize_pkts;
+	rmon_stats->jabbers = hwstat->rx_jabbers;
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+static const struct ethtool_rmon_hist_range gem_rmon_ranges[] = {
+	{   64,    64 },
+	{   65,   127 },
+	{  128,   255 },
+	{  256,   511 },
+	{  512,  1023 },
+	{ 1024,  1518 },
+	{ 1519, 16384 },
+	{ },
+};
 
-	return nstat;
+static void gem_get_rmon_stats(struct net_device *dev,
+			       struct ethtool_rmon_stats *rmon_stats,
+			       const struct ethtool_rmon_hist_range **ranges)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct gem_stats *hwstat = &bp->hw_stats.gem;
+
+	spin_lock_irq(&bp->stats_lock);
+	gem_update_stats(bp);
+	rmon_stats->undersize_pkts = hwstat->rx_undersized_frames;
+	rmon_stats->oversize_pkts = hwstat->rx_oversize_frames;
+	rmon_stats->jabbers = hwstat->rx_jabbers;
+	rmon_stats->hist[0] = hwstat->rx_64_byte_frames;
+	rmon_stats->hist[1] = hwstat->rx_65_127_byte_frames;
+	rmon_stats->hist[2] = hwstat->rx_128_255_byte_frames;
+	rmon_stats->hist[3] = hwstat->rx_256_511_byte_frames;
+	rmon_stats->hist[4] = hwstat->rx_512_1023_byte_frames;
+	rmon_stats->hist[5] = hwstat->rx_1024_1518_byte_frames;
+	rmon_stats->hist[6] = hwstat->rx_greater_than_1518_byte_frames;
+	rmon_stats->hist_tx[0] = hwstat->tx_64_byte_frames;
+	rmon_stats->hist_tx[1] = hwstat->tx_65_127_byte_frames;
+	rmon_stats->hist_tx[2] = hwstat->tx_128_255_byte_frames;
+	rmon_stats->hist_tx[3] = hwstat->tx_256_511_byte_frames;
+	rmon_stats->hist_tx[4] = hwstat->tx_512_1023_byte_frames;
+	rmon_stats->hist_tx[5] = hwstat->tx_1024_1518_byte_frames;
+	rmon_stats->hist_tx[6] = hwstat->tx_greater_than_1518_byte_frames;
+	spin_unlock_irq(&bp->stats_lock);
+	*ranges = gem_rmon_ranges;
 }
 
 static int macb_get_regs_len(struct net_device *netdev)
@@ -3396,7 +3549,7 @@ static int gem_get_ts_info(struct net_device *dev,
 {
 	struct macb *bp = netdev_priv(dev);
 
-	if ((bp->hw_dma_cap & HW_DMA_CAP_PTP) == 0) {
+	if (!macb_dma_ptp(bp)) {
 		ethtool_op_get_ts_info(dev, info);
 		return 0;
 	}
@@ -3755,6 +3908,10 @@ static const struct ethtool_ops macb_ethtool_ops = {
 	.get_regs		= macb_get_regs,
 	.get_link		= ethtool_op_get_link,
 	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_pause_stats	= macb_get_pause_stats,
+	.get_eth_mac_stats	= macb_get_eth_mac_stats,
+	.get_eth_phy_stats	= macb_get_eth_phy_stats,
+	.get_rmon_stats		= macb_get_rmon_stats,
 	.get_wol		= macb_get_wol,
 	.set_wol		= macb_set_wol,
 	.get_link_ksettings     = macb_get_link_ksettings,
@@ -3773,6 +3930,10 @@ static const struct ethtool_ops gem_ethtool_ops = {
 	.get_ethtool_stats	= gem_get_ethtool_stats,
 	.get_strings		= gem_get_ethtool_strings,
 	.get_sset_count		= gem_get_sset_count,
+	.get_pause_stats	= gem_get_pause_stats,
+	.get_eth_mac_stats	= gem_get_eth_mac_stats,
+	.get_eth_phy_stats	= gem_get_eth_phy_stats,
+	.get_rmon_stats		= gem_get_rmon_stats,
 	.get_link_ksettings     = macb_get_link_ksettings,
 	.set_link_ksettings     = macb_set_link_ksettings,
 	.get_ringparam		= macb_get_ringparam,
@@ -3904,12 +4065,234 @@ static void macb_restore_features(struct macb *bp)
 	macb_set_rxflow_feature(bp, features);
 }
 
+static int macb_taprio_setup_replace(struct net_device *ndev,
+				     struct tc_taprio_qopt_offload *conf)
+{
+	u64 total_on_time = 0, start_time_sec = 0, start_time = conf->base_time;
+	u32 configured_queues = 0, speed = 0, start_time_nsec;
+	struct macb_queue_enst_config *enst_queue;
+	struct tc_taprio_sched_entry *entry;
+	struct macb *bp = netdev_priv(ndev);
+	struct ethtool_link_ksettings kset;
+	struct macb_queue *queue;
+	u32 queue_mask;
+	u8 queue_id;
+	size_t i;
+	int err;
+
+	if (conf->num_entries > bp->num_queues) {
+		netdev_err(ndev, "Too many TAPRIO entries: %zu > %d queues\n",
+			   conf->num_entries, bp->num_queues);
+		return -EINVAL;
+	}
+
+	if (conf->base_time < 0) {
+		netdev_err(ndev, "Invalid base_time: must be 0 or positive, got %lld\n",
+			   conf->base_time);
+		return -ERANGE;
+	}
+
+	/* Get the current link speed */
+	err = phylink_ethtool_ksettings_get(bp->phylink, &kset);
+	if (unlikely(err)) {
+		netdev_err(ndev, "Failed to get link settings: %d\n", err);
+		return err;
+	}
+
+	speed = kset.base.speed;
+	if (unlikely(speed <= 0)) {
+		netdev_err(ndev, "Invalid speed: %d\n", speed);
+		return -EINVAL;
+	}
+
+	enst_queue = kcalloc(conf->num_entries, sizeof(*enst_queue), GFP_KERNEL);
+	if (unlikely(!enst_queue))
+		return -ENOMEM;
+
+	/* Pre-validate all entries before making any hardware changes */
+	for (i = 0; i < conf->num_entries; i++) {
+		entry = &conf->entries[i];
+
+		if (entry->command != TC_TAPRIO_CMD_SET_GATES) {
+			netdev_err(ndev, "Entry %zu: unsupported command %d\n",
+				   i, entry->command);
+			err = -EOPNOTSUPP;
+			goto cleanup;
+		}
+
+		/* Validate gate_mask: must be nonzero, single queue, and within range */
+		if (!is_power_of_2(entry->gate_mask)) {
+			netdev_err(ndev, "Entry %zu: gate_mask 0x%x is not a power of 2 (only one queue per entry allowed)\n",
+				   i, entry->gate_mask);
+			err = -EINVAL;
+			goto cleanup;
+		}
+
+		/* gate_mask must not select queues outside the valid queues */
+		queue_id = order_base_2(entry->gate_mask);
+		if (queue_id >= bp->num_queues) {
+			netdev_err(ndev, "Entry %zu: gate_mask 0x%x exceeds queue range (max_queues=%d)\n",
+				   i, entry->gate_mask, bp->num_queues);
+			err = -EINVAL;
+			goto cleanup;
+		}
+
+		/* Check for start time limits */
+		start_time_sec = start_time;
+		start_time_nsec = do_div(start_time_sec, NSEC_PER_SEC);
+		if (start_time_sec > GENMASK(GEM_START_TIME_SEC_SIZE - 1, 0)) {
+			netdev_err(ndev, "Entry %zu: Start time %llu s exceeds hardware limit\n",
+				   i, start_time_sec);
+			err = -ERANGE;
+			goto cleanup;
+		}
+
+		/* Check for on time limit */
+		if (entry->interval > enst_max_hw_interval(speed)) {
+			netdev_err(ndev, "Entry %zu: interval %u ns exceeds hardware limit %llu ns\n",
+				   i, entry->interval, enst_max_hw_interval(speed));
+			err = -ERANGE;
+			goto cleanup;
+		}
+
+		/* Check for off time limit*/
+		if ((conf->cycle_time - entry->interval) > enst_max_hw_interval(speed)) {
+			netdev_err(ndev, "Entry %zu: off_time %llu ns exceeds hardware limit %llu ns\n",
+				   i, conf->cycle_time - entry->interval,
+				   enst_max_hw_interval(speed));
+			err = -ERANGE;
+			goto cleanup;
+		}
+
+		enst_queue[i].queue_id = queue_id;
+		enst_queue[i].start_time_mask =
+			(start_time_sec << GEM_START_TIME_SEC_OFFSET) |
+			start_time_nsec;
+		enst_queue[i].on_time_bytes =
+			enst_ns_to_hw_units(entry->interval, speed);
+		enst_queue[i].off_time_bytes =
+			enst_ns_to_hw_units(conf->cycle_time - entry->interval, speed);
+
+		configured_queues |= entry->gate_mask;
+		total_on_time += entry->interval;
+		start_time += entry->interval;
+	}
+
+	/* Check total interval doesn't exceed cycle time */
+	if (total_on_time > conf->cycle_time) {
+		netdev_err(ndev, "Total ON %llu ns exceeds cycle time %llu ns\n",
+			   total_on_time, conf->cycle_time);
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	netdev_dbg(ndev, "TAPRIO setup: %zu entries, base_time=%lld ns, cycle_time=%llu ns\n",
+		   conf->num_entries, conf->base_time, conf->cycle_time);
+
+	/* All validations passed - proceed with hardware configuration */
+	scoped_guard(spinlock_irqsave, &bp->lock) {
+		/* Disable ENST queues if running before configuring */
+		queue_mask = BIT_U32(bp->num_queues) - 1;
+		gem_writel(bp, ENST_CONTROL,
+			   queue_mask << GEM_ENST_DISABLE_QUEUE_OFFSET);
+
+		for (i = 0; i < conf->num_entries; i++) {
+			queue = &bp->queues[enst_queue[i].queue_id];
+			/* Configure queue timing registers */
+			queue_writel(queue, ENST_START_TIME,
+				     enst_queue[i].start_time_mask);
+			queue_writel(queue, ENST_ON_TIME,
+				     enst_queue[i].on_time_bytes);
+			queue_writel(queue, ENST_OFF_TIME,
+				     enst_queue[i].off_time_bytes);
+		}
+
+		/* Enable ENST for all configured queues in one write */
+		gem_writel(bp, ENST_CONTROL, configured_queues);
+	}
+
+	netdev_info(ndev, "TAPRIO configuration completed successfully: %zu entries, %d queues configured\n",
+		    conf->num_entries, hweight32(configured_queues));
+
+cleanup:
+	kfree(enst_queue);
+	return err;
+}
+
+static void macb_taprio_destroy(struct net_device *ndev)
+{
+	struct macb *bp = netdev_priv(ndev);
+	struct macb_queue *queue;
+	u32 queue_mask;
+	unsigned int q;
+
+	netdev_reset_tc(ndev);
+	queue_mask = BIT_U32(bp->num_queues) - 1;
+
+	scoped_guard(spinlock_irqsave, &bp->lock) {
+		/* Single disable command for all queues */
+		gem_writel(bp, ENST_CONTROL,
+			   queue_mask << GEM_ENST_DISABLE_QUEUE_OFFSET);
+
+		/* Clear all queue ENST registers in batch */
+		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
+			queue_writel(queue, ENST_START_TIME, 0);
+			queue_writel(queue, ENST_ON_TIME, 0);
+			queue_writel(queue, ENST_OFF_TIME, 0);
+		}
+	}
+	netdev_info(ndev, "TAPRIO destroy: All gates disabled\n");
+}
+
+static int macb_setup_taprio(struct net_device *ndev,
+			     struct tc_taprio_qopt_offload *taprio)
+{
+	struct macb *bp = netdev_priv(ndev);
+	int err = 0;
+
+	if (unlikely(!(ndev->hw_features & NETIF_F_HW_TC)))
+		return -EOPNOTSUPP;
+
+	/* Check if Device is in runtime suspend */
+	if (unlikely(pm_runtime_suspended(&bp->pdev->dev))) {
+		netdev_err(ndev, "Device is in runtime suspend\n");
+		return -EOPNOTSUPP;
+	}
+
+	switch (taprio->cmd) {
+	case TAPRIO_CMD_REPLACE:
+		err = macb_taprio_setup_replace(ndev, taprio);
+		break;
+	case TAPRIO_CMD_DESTROY:
+		macb_taprio_destroy(ndev);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static int macb_setup_tc(struct net_device *dev, enum tc_setup_type type,
+			 void *type_data)
+{
+	if (!dev || !type_data)
+		return -EINVAL;
+
+	switch (type) {
+	case TC_SETUP_QDISC_TAPRIO:
+		return macb_setup_taprio(dev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct net_device_ops macb_netdev_ops = {
 	.ndo_open		= macb_open,
 	.ndo_stop		= macb_close,
 	.ndo_start_xmit		= macb_start_xmit,
 	.ndo_set_rx_mode	= macb_set_rx_mode,
-	.ndo_get_stats		= macb_get_stats,
+	.ndo_get_stats64	= macb_get_stats,
 	.ndo_eth_ioctl		= macb_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= macb_change_mtu,
@@ -3921,6 +4304,7 @@ static const struct net_device_ops macb_netdev_ops = {
 	.ndo_features_check	= macb_features_check,
 	.ndo_hwtstamp_set	= macb_hwtstamp_set,
 	.ndo_hwtstamp_get	= macb_hwtstamp_get,
+	.ndo_setup_tc		= macb_setup_tc,
 };
 
 /* Configure peripheral capabilities according to device tree
@@ -3929,8 +4313,12 @@ static const struct net_device_ops macb_netdev_ops = {
 static void macb_configure_caps(struct macb *bp,
 				const struct macb_config *dt_conf)
 {
+	struct device_node *np = bp->pdev->dev.of_node;
+	bool refclk_ext;
 	u32 dcfg;
 
+	refclk_ext = of_property_read_bool(np, "cdns,refclk-ext");
+
 	if (dt_conf)
 		bp->caps = dt_conf->caps;
 
@@ -3948,42 +4336,46 @@ static void macb_configure_caps(struct macb *bp,
 		dcfg = gem_readl(bp, DCFG2);
 		if ((dcfg & (GEM_BIT(RX_PKT_BUFF) | GEM_BIT(TX_PKT_BUFF))) == 0)
 			bp->caps |= MACB_CAPS_FIFO_MODE;
+		if (GEM_BFEXT(PBUF_RSC, gem_readl(bp, DCFG6)))
+			bp->caps |= MACB_CAPS_RSC;
 		if (gem_has_ptp(bp)) {
 			if (!GEM_BFEXT(TSU, gem_readl(bp, DCFG5)))
 				dev_err(&bp->pdev->dev,
 					"GEM doesn't support hardware ptp.\n");
 			else {
 #ifdef CONFIG_MACB_USE_HWSTAMP
-				bp->hw_dma_cap |= HW_DMA_CAP_PTP;
+				bp->caps |= MACB_CAPS_DMA_PTP;
 				bp->ptp_info = &gem_ptp_info;
 #endif
 			}
 		}
 	}
 
+	if (refclk_ext)
+		bp->caps |= MACB_CAPS_USRIO_HAS_CLKEN;
+
 	dev_dbg(&bp->pdev->dev, "Cadence caps 0x%08x\n", bp->caps);
 }
 
-static void macb_probe_queues(void __iomem *mem,
-			      bool native_io,
-			      unsigned int *queue_mask,
-			      unsigned int *num_queues)
+static int macb_probe_queues(struct device *dev, void __iomem *mem, bool native_io)
 {
-	*queue_mask = 0x1;
-	*num_queues = 1;
+	/* BIT(0) is never set but queue 0 always exists. */
+	unsigned int queue_mask = 0x1;
 
-	/* is it macb or gem ?
-	 *
-	 * We need to read directly from the hardware here because
-	 * we are early in the probe process and don't have the
-	 * MACB_CAPS_MACB_IS_GEM flag positioned
-	 */
-	if (!hw_is_gem(mem, native_io))
-		return;
+	/* Use hw_is_gem() as MACB_CAPS_MACB_IS_GEM is not yet positioned. */
+	if (hw_is_gem(mem, native_io)) {
+		if (native_io)
+			queue_mask |= __raw_readl(mem + GEM_DCFG6) & 0xFF;
+		else
+			queue_mask |= readl_relaxed(mem + GEM_DCFG6) & 0xFF;
 
-	/* bit 0 is never set but queue 0 always exists */
-	*queue_mask |= readl_relaxed(mem + GEM_DCFG6) & 0xff;
-	*num_queues = hweight32(*queue_mask);
+		if (fls(queue_mask) != ffz(queue_mask)) {
+			dev_err(dev, "queue mask %#x has a hole\n", queue_mask);
+			return -EINVAL;
+		}
+	}
+
+	return hweight32(queue_mask);
 }
 
 static void macb_clks_disable(struct clk *pclk, struct clk *hclk, struct clk *tx_clk,
@@ -4101,10 +4493,7 @@ static int macb_init(struct platform_device *pdev)
 	 * register mapping but we don't want to test the queue index then
 	 * compute the corresponding register offset at run time.
 	 */
-	for (hw_q = 0, q = 0; hw_q < MACB_MAX_QUEUES; ++hw_q) {
-		if (!(bp->queue_mask & (1 << hw_q)))
-			continue;
-
+	for (hw_q = 0, q = 0; hw_q < bp->num_queues; ++hw_q) {
 		queue = &bp->queues[q];
 		queue->bp = bp;
 		spin_lock_init(&queue->tx_ptr_lock);
@@ -4118,12 +4507,6 @@ static int macb_init(struct platform_device *pdev)
 			queue->TBQP = GEM_TBQP(hw_q - 1);
 			queue->RBQP = GEM_RBQP(hw_q - 1);
 			queue->RBQS = GEM_RBQS(hw_q - 1);
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-			if (bp->hw_dma_cap & HW_DMA_CAP_64B) {
-				queue->TBQPH = GEM_TBQPH(hw_q - 1);
-				queue->RBQPH = GEM_RBQPH(hw_q - 1);
-			}
-#endif
 		} else {
 			/* queue0 uses legacy registers */
 			queue->ISR  = MACB_ISR;
@@ -4132,14 +4515,12 @@ static int macb_init(struct platform_device *pdev)
 			queue->IMR  = MACB_IMR;
 			queue->TBQP = MACB_TBQP;
 			queue->RBQP = MACB_RBQP;
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-			if (bp->hw_dma_cap & HW_DMA_CAP_64B) {
-				queue->TBQPH = MACB_TBQPH;
-				queue->RBQPH = MACB_RBQPH;
-			}
-#endif
 		}
 
+		queue->ENST_START_TIME = GEM_ENST_START_TIME(hw_q);
+		queue->ENST_ON_TIME = GEM_ENST_ON_TIME(hw_q);
+		queue->ENST_OFF_TIME = GEM_ENST_OFF_TIME(hw_q);
+
 		/* get irq: here we use the linux queue index, not the hardware
 		 * queue index. the queue irq definitions in the device tree
 		 * must remove the optional gaps that could exist in the
@@ -4183,8 +4564,11 @@ static int macb_init(struct platform_device *pdev)
 	/* Set features */
 	dev->hw_features = NETIF_F_SG;
 
-	/* Check LSO capability */
-	if (GEM_BFEXT(PBUF_LSO, gem_readl(bp, DCFG6)))
+	/* Check LSO capability; runtime detection can be overridden by a cap
+	 * flag if the hardware is known to be buggy
+	 */
+	if (!(bp->caps & MACB_CAPS_NO_LSO) &&
+	    GEM_BFEXT(PBUF_LSO, gem_readl(bp, DCFG6)))
 		dev->hw_features |= MACB_NETIF_LSO;
 
 	/* Checksum offload is only available on gem with packet buffer */
@@ -4192,6 +4576,10 @@ static int macb_init(struct platform_device *pdev)
 		dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
 	if (bp->caps & MACB_CAPS_SG_DISABLED)
 		dev->hw_features &= ~NETIF_F_SG;
+	/* Enable HW_TC if hardware supports QBV */
+	if (bp->caps & MACB_CAPS_QBV)
+		dev->hw_features |= NETIF_F_HW_TC;
+
 	dev->features = dev->hw_features;
 
 	/* Check RX Flow Filters support.
@@ -4199,8 +4587,8 @@ static int macb_init(struct platform_device *pdev)
 	 * each 4-tuple define requires 1 T2 screener reg + 3 compare regs
 	 */
 	reg = gem_readl(bp, DCFG8);
-	bp->max_tuples = min((GEM_BFEXT(SCR2CMP, reg) / 3),
-			GEM_BFEXT(T2SCR, reg));
+	bp->max_tuples = umin((GEM_BFEXT(SCR2CMP, reg) / 3),
+			      GEM_BFEXT(T2SCR, reg));
 	INIT_LIST_HEAD(&bp->rx_fs_list.list);
 	if (bp->max_tuples > 0) {
 		/* also needs one ethtype match to check IPv4 */
@@ -4570,7 +4958,7 @@ static const struct net_device_ops at91ether_netdev_ops = {
 	.ndo_open		= at91ether_open,
 	.ndo_stop		= at91ether_close,
 	.ndo_start_xmit		= at91ether_start_xmit,
-	.ndo_get_stats		= macb_get_stats,
+	.ndo_get_stats64	= macb_get_stats,
 	.ndo_set_rx_mode	= macb_set_rx_mode,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_eth_ioctl		= macb_ioctl,
@@ -4635,36 +5023,45 @@ static unsigned long fu540_macb_tx_recalc_rate(struct clk_hw *hw,
 	return mgmt->rate;
 }
 
-static long fu540_macb_tx_round_rate(struct clk_hw *hw, unsigned long rate,
-				     unsigned long *parent_rate)
-{
-	if (WARN_ON(rate < 2500000))
-		return 2500000;
-	else if (rate == 2500000)
-		return 2500000;
-	else if (WARN_ON(rate < 13750000))
-		return 2500000;
-	else if (WARN_ON(rate < 25000000))
-		return 25000000;
-	else if (rate == 25000000)
-		return 25000000;
-	else if (WARN_ON(rate < 75000000))
-		return 25000000;
-	else if (WARN_ON(rate < 125000000))
-		return 125000000;
-	else if (rate == 125000000)
-		return 125000000;
-
-	WARN_ON(rate > 125000000);
+static int fu540_macb_tx_determine_rate(struct clk_hw *hw,
+					struct clk_rate_request *req)
+{
+	if (WARN_ON(req->rate < 2500000))
+		req->rate = 2500000;
+	else if (req->rate == 2500000)
+		req->rate = 2500000;
+	else if (WARN_ON(req->rate < 13750000))
+		req->rate = 2500000;
+	else if (WARN_ON(req->rate < 25000000))
+		req->rate = 25000000;
+	else if (req->rate == 25000000)
+		req->rate = 25000000;
+	else if (WARN_ON(req->rate < 75000000))
+		req->rate = 25000000;
+	else if (WARN_ON(req->rate < 125000000))
+		req->rate = 125000000;
+	else if (req->rate == 125000000)
+		req->rate = 125000000;
+	else if (WARN_ON(req->rate > 125000000))
+		req->rate = 125000000;
+	else
+		req->rate = 125000000;
 
-	return 125000000;
+	return 0;
 }
 
 static int fu540_macb_tx_set_rate(struct clk_hw *hw, unsigned long rate,
 				  unsigned long parent_rate)
 {
-	rate = fu540_macb_tx_round_rate(hw, rate, &parent_rate);
-	if (rate != 125000000)
+	struct clk_rate_request req;
+	int ret;
+
+	clk_hw_init_rate_request(hw, &req, rate);
+	ret = fu540_macb_tx_determine_rate(hw, &req);
+	if (ret != 0)
+		return ret;
+
+	if (req.rate != 125000000)
 		iowrite32(1, mgmt->reg);
 	else
 		iowrite32(0, mgmt->reg);
@@ -4675,7 +5072,7 @@ static int fu540_macb_tx_set_rate(struct clk_hw *hw, unsigned long rate,
 
 static const struct clk_ops fu540_c000_ops = {
 	.recalc_rate = fu540_macb_tx_recalc_rate,
-	.round_rate = fu540_macb_tx_round_rate,
+	.determine_rate = fu540_macb_tx_determine_rate,
 	.set_rate = fu540_macb_tx_set_rate,
 };
 
@@ -4744,13 +5141,13 @@ static int init_reset_optional(struct platform_device *pdev)
 
 	if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII) {
 		/* Ensure PHY device used in SGMII mode is ready */
-		bp->sgmii_phy = devm_phy_optional_get(&pdev->dev, NULL);
+		bp->phy = devm_phy_optional_get(&pdev->dev, NULL);
 
-		if (IS_ERR(bp->sgmii_phy))
-			return dev_err_probe(&pdev->dev, PTR_ERR(bp->sgmii_phy),
+		if (IS_ERR(bp->phy))
+			return dev_err_probe(&pdev->dev, PTR_ERR(bp->phy),
 					     "failed to get SGMII PHY\n");
 
-		ret = phy_init(bp->sgmii_phy);
+		ret = phy_init(bp->phy);
 		if (ret)
 			return dev_err_probe(&pdev->dev, ret,
 					     "failed to init SGMII PHY\n");
@@ -4779,7 +5176,7 @@ static int init_reset_optional(struct platform_device *pdev)
 	/* Fully reset controller at hardware level if mapped in device tree */
 	ret = device_reset_optional(&pdev->dev);
 	if (ret) {
-		phy_exit(bp->sgmii_phy);
+		phy_exit(bp->phy);
 		return dev_err_probe(&pdev->dev, ret, "failed to reset controller");
 	}
 
@@ -4787,11 +5184,33 @@ static int init_reset_optional(struct platform_device *pdev)
 
 err_out_phy_exit:
 	if (ret)
-		phy_exit(bp->sgmii_phy);
+		phy_exit(bp->phy);
 
 	return ret;
 }
 
+static int eyeq5_init(struct platform_device *pdev)
+{
+	struct net_device *netdev = platform_get_drvdata(pdev);
+	struct macb *bp = netdev_priv(netdev);
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	bp->phy = devm_phy_get(dev, NULL);
+	if (IS_ERR(bp->phy))
+		return dev_err_probe(dev, PTR_ERR(bp->phy),
+				     "failed to get PHY\n");
+
+	ret = phy_init(bp->phy);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to init PHY\n");
+
+	ret = macb_init(pdev);
+	if (ret)
+		phy_exit(bp->phy);
+	return ret;
+}
+
 static const struct macb_usrio_config sama7g5_usrio = {
 	.mii = 0,
 	.rmii = 1,
@@ -4916,6 +5335,7 @@ static const struct macb_config mpfs_config = {
 
 static const struct macb_config sama7g5_gem_config = {
 	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_CLK_HW_CHG |
+		MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII |
 		MACB_CAPS_MIIONRGMII | MACB_CAPS_GEM_HAS_PTP,
 	.dma_burst_length = 16,
 	.clk_init = macb_clk_init,
@@ -4935,8 +5355,9 @@ static const struct macb_config sama7g5_emac_config = {
 
 static const struct macb_config versal_config = {
 	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO |
-		MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH | MACB_CAPS_NEED_TSUCLK |
-		MACB_CAPS_QUEUE_DISABLE,
+		MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH |
+		MACB_CAPS_NEED_TSUCLK | MACB_CAPS_QUEUE_DISABLE |
+		MACB_CAPS_QBV,
 	.dma_burst_length = 16,
 	.clk_init = macb_clk_init,
 	.init = init_reset_optional,
@@ -4944,6 +5365,28 @@ static const struct macb_config versal_config = {
 	.usrio = &macb_default_usrio,
 };
 
+static const struct macb_config eyeq5_config = {
+	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO |
+		MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_QUEUE_DISABLE |
+		MACB_CAPS_NO_LSO,
+	.dma_burst_length = 16,
+	.clk_init = macb_clk_init,
+	.init = eyeq5_init,
+	.jumbo_max_len = 10240,
+	.usrio = &macb_default_usrio,
+};
+
+static const struct macb_config raspberrypi_rp1_config = {
+	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_CLK_HW_CHG |
+		MACB_CAPS_JUMBO |
+		MACB_CAPS_GEM_HAS_PTP,
+	.dma_burst_length = 16,
+	.clk_init = macb_clk_init,
+	.init = macb_init,
+	.usrio = &macb_default_usrio,
+	.jumbo_max_len = 10240,
+};
+
 static const struct of_device_id macb_dt_ids[] = {
 	{ .compatible = "cdns,at91sam9260-macb", .data = &at91sam9260_config },
 	{ .compatible = "cdns,macb" },
@@ -4964,6 +5407,8 @@ static const struct of_device_id macb_dt_ids[] = {
 	{ .compatible = "microchip,mpfs-macb", .data = &mpfs_config },
 	{ .compatible = "microchip,sama7g5-gem", .data = &sama7g5_gem_config },
 	{ .compatible = "microchip,sama7g5-emac", .data = &sama7g5_emac_config },
+	{ .compatible = "mobileye,eyeq5-gem", .data = &eyeq5_config },
+	{ .compatible = "raspberrypi,rp1-gem", .data = &raspberrypi_rp1_config },
 	{ .compatible = "xlnx,zynqmp-gem", .data = &zynqmp_config},
 	{ .compatible = "xlnx,zynq-gem", .data = &zynq_config },
 	{ .compatible = "xlnx,versal-gem", .data = &versal_config},
@@ -4986,21 +5431,17 @@ static const struct macb_config default_gem_config = {
 static int macb_probe(struct platform_device *pdev)
 {
 	const struct macb_config *macb_config = &default_gem_config;
-	int (*clk_init)(struct platform_device *, struct clk **,
-			struct clk **, struct clk **,  struct clk **,
-			struct clk **) = macb_config->clk_init;
-	int (*init)(struct platform_device *) = macb_config->init;
 	struct device_node *np = pdev->dev.of_node;
 	struct clk *pclk, *hclk = NULL, *tx_clk = NULL, *rx_clk = NULL;
 	struct clk *tsu_clk = NULL;
-	unsigned int queue_mask, num_queues;
-	bool native_io;
 	phy_interface_t interface;
 	struct net_device *dev;
 	struct resource *regs;
 	u32 wtrmrk_rst_val;
 	void __iomem *mem;
 	struct macb *bp;
+	int num_queues;
+	bool native_io;
 	int err, val;
 
 	mem = devm_platform_get_and_ioremap_resource(pdev, 0, &regs);
@@ -5011,14 +5452,11 @@ static int macb_probe(struct platform_device *pdev)
 		const struct of_device_id *match;
 
 		match = of_match_node(macb_dt_ids, np);
-		if (match && match->data) {
+		if (match && match->data)
 			macb_config = match->data;
-			clk_init = macb_config->clk_init;
-			init = macb_config->init;
-		}
 	}
 
-	err = clk_init(pdev, &pclk, &hclk, &tx_clk, &rx_clk, &tsu_clk);
+	err = macb_config->clk_init(pdev, &pclk, &hclk, &tx_clk, &rx_clk, &tsu_clk);
 	if (err)
 		return err;
 
@@ -5029,7 +5467,12 @@ static int macb_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 	native_io = hw_is_native_io(mem);
 
-	macb_probe_queues(mem, native_io, &queue_mask, &num_queues);
+	num_queues = macb_probe_queues(&pdev->dev, mem, native_io);
+	if (num_queues < 0) {
+		err = num_queues;
+		goto err_disable_clocks;
+	}
+
 	dev = alloc_etherdev_mq(sizeof(*bp), num_queues);
 	if (!dev) {
 		err = -ENOMEM;
@@ -5053,16 +5496,13 @@ static int macb_probe(struct platform_device *pdev)
 		bp->macb_reg_writel = hw_writel;
 	}
 	bp->num_queues = num_queues;
-	bp->queue_mask = queue_mask;
-	if (macb_config)
-		bp->dma_burst_length = macb_config->dma_burst_length;
+	bp->dma_burst_length = macb_config->dma_burst_length;
 	bp->pclk = pclk;
 	bp->hclk = hclk;
 	bp->tx_clk = tx_clk;
 	bp->rx_clk = rx_clk;
 	bp->tsu_clk = tsu_clk;
-	if (macb_config)
-		bp->jumbo_max_len = macb_config->jumbo_max_len;
+	bp->jumbo_max_len = macb_config->jumbo_max_len;
 
 	if (!hw_is_gem(bp->regs, bp->native_io))
 		bp->max_tx_length = MACB_MAX_TX_LEN;
@@ -5096,14 +5536,19 @@ static int macb_probe(struct platform_device *pdev)
 		}
 	}
 	spin_lock_init(&bp->lock);
+	spin_lock_init(&bp->stats_lock);
 
 	/* setup capabilities */
 	macb_configure_caps(bp, macb_config);
 
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
 	if (GEM_BFEXT(DAW64, gem_readl(bp, DCFG6))) {
-		dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(44));
-		bp->hw_dma_cap |= HW_DMA_CAP_64B;
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(44));
+		if (err) {
+			dev_err(&pdev->dev, "failed to set DMA mask\n");
+			goto err_out_free_netdev;
+		}
+		bp->caps |= MACB_CAPS_DMA_64B;
 	}
 #endif
 	platform_set_drvdata(pdev, dev);
@@ -5151,7 +5596,7 @@ static int macb_probe(struct platform_device *pdev)
 		bp->phy_interface = interface;
 
 	/* IP specific init */
-	err = init(pdev);
+	err = macb_config->init(pdev);
 	if (err)
 		goto err_out_free_netdev;
 
@@ -5173,7 +5618,6 @@ static int macb_probe(struct platform_device *pdev)
 		    macb_is_gem(bp) ? "GEM" : "MACB", macb_readl(bp, MID),
 		    dev->base_addr, dev->irq, dev->dev_addr);
 
-	pm_runtime_mark_last_busy(&bp->pdev->dev);
 	pm_runtime_put_autosuspend(&bp->pdev->dev);
 
 	return 0;
@@ -5183,7 +5627,7 @@ err_out_unregister_mdio:
 	mdiobus_free(bp->mii_bus);
 
 err_out_phy_exit:
-	phy_exit(bp->sgmii_phy);
+	phy_exit(bp->phy);
 
 err_out_free_netdev:
 	free_netdev(dev);
@@ -5206,19 +5650,16 @@ static void macb_remove(struct platform_device *pdev)
 
 	if (dev) {
 		bp = netdev_priv(dev);
-		phy_exit(bp->sgmii_phy);
+		unregister_netdev(dev);
+		phy_exit(bp->phy);
 		mdiobus_unregister(bp->mii_bus);
 		mdiobus_free(bp->mii_bus);
 
-		unregister_netdev(dev);
+		device_set_wakeup_enable(&bp->pdev->dev, 0);
 		cancel_work_sync(&bp->hresp_err_bh_work);
 		pm_runtime_disable(&pdev->dev);
 		pm_runtime_dont_use_autosuspend(&pdev->dev);
-		if (!pm_runtime_suspended(&pdev->dev)) {
-			macb_clks_disable(bp->pclk, bp->hclk, bp->tx_clk,
-					  bp->rx_clk, bp->tsu_clk);
-			pm_runtime_set_suspended(&pdev->dev);
-		}
+		pm_runtime_set_suspended(&pdev->dev);
 		phylink_destroy(bp->phylink);
 		free_netdev(dev);
 	}
@@ -5237,7 +5678,7 @@ static int __maybe_unused macb_suspend(struct device *dev)
 	u32 tmp;
 
 	if (!device_may_wakeup(&bp->dev->dev))
-		phy_exit(bp->sgmii_phy);
+		phy_exit(bp->phy);
 
 	if (!netif_running(netdev))
 		return 0;
@@ -5258,6 +5699,11 @@ static int __maybe_unused macb_suspend(struct device *dev)
 		 */
 		tmp = macb_readl(bp, NCR);
 		macb_writel(bp, NCR, tmp & ~(MACB_BIT(TE) | MACB_BIT(RE)));
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+		if (!(bp->caps & MACB_CAPS_QUEUE_DISABLE))
+			macb_writel(bp, RBQPH,
+				    upper_32_bits(bp->rx_ring_tieoff_dma));
+#endif
 		for (q = 0, queue = bp->queues; q < bp->num_queues;
 		     ++q, ++queue) {
 			/* Disable RX queues */
@@ -5267,10 +5713,6 @@ static int __maybe_unused macb_suspend(struct device *dev)
 				/* Tie off RX queues */
 				queue_writel(queue, RBQP,
 					     lower_32_bits(bp->rx_ring_tieoff_dma));
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-				queue_writel(queue, RBQPH,
-					     upper_32_bits(bp->rx_ring_tieoff_dma));
-#endif
 			}
 			/* Disable all interrupts */
 			queue_writel(queue, IDR, -1);
@@ -5365,7 +5807,7 @@ static int __maybe_unused macb_resume(struct device *dev)
 	int err;
 
 	if (!device_may_wakeup(&bp->dev->dev))
-		phy_init(bp->sgmii_phy);
+		phy_init(bp->phy);
 
 	if (!netif_running(netdev))
 		return 0;
@@ -5469,6 +5911,20 @@ static int __maybe_unused macb_runtime_resume(struct device *dev)
 	return 0;
 }
 
+static void macb_shutdown(struct platform_device *pdev)
+{
+	struct net_device *netdev = platform_get_drvdata(pdev);
+
+	rtnl_lock();
+
+	if (netif_running(netdev))
+		dev_close(netdev);
+
+	netif_device_detach(netdev);
+
+	rtnl_unlock();
+}
+
 static const struct dev_pm_ops macb_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(macb_suspend, macb_resume)
 	SET_RUNTIME_PM_OPS(macb_runtime_suspend, macb_runtime_resume, NULL)
@@ -5482,6 +5938,7 @@ static struct platform_driver macb_driver = {
 		.of_match_table	= of_match_ptr(macb_dt_ids),
 		.pm	= &macb_pm_ops,
 	},
+	.shutdown	= macb_shutdown,
 };
 
 module_platform_driver(macb_driver);
diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c
index a63bf29c4fa8..c9e77819196e 100644
--- a/drivers/net/ethernet/cadence/macb_ptp.c
+++ b/drivers/net/ethernet/cadence/macb_ptp.c
@@ -28,14 +28,16 @@
 static struct macb_dma_desc_ptp *macb_ptp_desc(struct macb *bp,
 					       struct macb_dma_desc *desc)
 {
-	if (bp->hw_dma_cap == HW_DMA_CAP_PTP)
-		return (struct macb_dma_desc_ptp *)
-				((u8 *)desc + sizeof(struct macb_dma_desc));
-	if (bp->hw_dma_cap == HW_DMA_CAP_64B_PTP)
+	if (!macb_dma_ptp(bp))
+		return NULL;
+
+	if (macb_dma64(bp))
 		return (struct macb_dma_desc_ptp *)
 				((u8 *)desc + sizeof(struct macb_dma_desc)
 				+ sizeof(struct macb_dma_desc_64));
-	return NULL;
+	else
+		return (struct macb_dma_desc_ptp *)
+				((u8 *)desc + sizeof(struct macb_dma_desc));
 }
 
 static int gem_tsu_get_time(struct ptp_clock_info *ptp, struct timespec64 *ts,
@@ -380,7 +382,7 @@ int gem_get_hwtst(struct net_device *dev,
 	struct macb *bp = netdev_priv(dev);
 
 	*tstamp_config = bp->tstamp_config;
-	if ((bp->hw_dma_cap & HW_DMA_CAP_PTP) == 0)
+	if (!macb_dma_ptp(bp))
 		return -EOPNOTSUPP;
 
 	return 0;
@@ -407,7 +409,7 @@ int gem_set_hwtst(struct net_device *dev,
 	struct macb *bp = netdev_priv(dev);
 	u32 regval;
 
-	if ((bp->hw_dma_cap & HW_DMA_CAP_PTP) == 0)
+	if (!macb_dma_ptp(bp))
 		return -EOPNOTSUPP;
 
 	switch (tstamp_config->tx_type) {
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index ca742cc146d7..7dae5aad3689 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -70,8 +70,8 @@ config LIQUIDIO
 	depends on 64BIT && PCI
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
+	select CRC32
 	select FW_LOADER
-	select LIBCRC32C
 	select LIQUIDIO_CORE
 	select NET_DEVLINK
 	help
diff --git a/drivers/net/ethernet/cavium/common/cavium_ptp.c b/drivers/net/ethernet/cavium/common/cavium_ptp.c
index 984f0dd7b62e..61e261657073 100644
--- a/drivers/net/ethernet/cavium/common/cavium_ptp.c
+++ b/drivers/net/ethernet/cavium/common/cavium_ptp.c
@@ -209,7 +209,7 @@ static int cavium_ptp_enable(struct ptp_clock_info *ptp_info,
 	return -EOPNOTSUPP;
 }
 
-static u64 cavium_ptp_cc_read(const struct cyclecounter *cc)
+static u64 cavium_ptp_cc_read(struct cyclecounter *cc)
 {
 	struct cavium_ptp *clock =
 		container_of(cc, struct cavium_ptp, cycle_counter);
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 9ad49aea2673..75f22f74774c 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -49,7 +49,7 @@ static int cn23xx_pf_soft_reset(struct octeon_device *oct)
 	lio_pci_readq(oct, CN23XX_RST_SOFT_RST);
 	lio_pci_writeq(oct, 1, CN23XX_RST_SOFT_RST);
 
-	/* Wait for 100ms as Octeon resets. */
+	/* Wait for 100ms as Octeon resets */
 	mdelay(100);
 
 	if (octeon_read_csr64(oct, CN23XX_SLI_SCRATCH1)) {
@@ -61,7 +61,7 @@ static int cn23xx_pf_soft_reset(struct octeon_device *oct)
 	dev_dbg(&oct->pci_dev->dev, "OCTEON[%d]: Reset completed\n",
 		oct->octeon_id);
 
-	/* restore the  reset value*/
+	/* Restore the reset value */
 	octeon_write_csr64(oct, CN23XX_WIN_WR_MASK_REG, 0xFF);
 
 	return 0;
@@ -121,7 +121,7 @@ u32 cn23xx_pf_get_oq_ticks(struct octeon_device *oct, u32 time_intr_in_us)
 	oqticks_per_us /= 1024;
 
 	/* time_intr is in microseconds. The next 2 steps gives the oq ticks
-	 *  corressponding to time_intr.
+	 * corresponding to time_intr.
 	 */
 	oqticks_per_us *= time_intr_in_us;
 	oqticks_per_us /= 1000;
@@ -136,11 +136,11 @@ static void cn23xx_setup_global_mac_regs(struct octeon_device *oct)
 	u64 reg_val;
 	u64 temp;
 
-	/* programming SRN and TRS for each MAC(0..3)  */
+	/* Programming SRN and TRS for each MAC(0..3) */
 
 	dev_dbg(&oct->pci_dev->dev, "%s:Using pcie port %d\n",
 		__func__, mac_no);
-	/* By default, mapping all 64 IOQs to  a single MACs */
+	/* By default, map all 64 IOQs to a single MAC */
 
 	reg_val =
 	    octeon_read_csr64(oct, CN23XX_SLI_PKT_MAC_RINFO64(mac_no, pf_num));
@@ -164,7 +164,7 @@ static void cn23xx_setup_global_mac_regs(struct octeon_device *oct)
 	temp = oct->sriov_info.max_vfs & 0xff;
 	reg_val |= (temp << CN23XX_PKT_MAC_CTL_RINFO_NVFS_BIT_POS);
 
-	/* write these settings to MAC register */
+	/* Write these settings to MAC register */
 	octeon_write_csr64(oct, CN23XX_SLI_PKT_MAC_RINFO64(mac_no, pf_num),
 			   reg_val);
 
@@ -183,10 +183,10 @@ static int cn23xx_reset_io_queues(struct octeon_device *oct)
 	srn = oct->sriov_info.pf_srn;
 	ern = srn + oct->sriov_info.num_pf_rings;
 
-	/*As per HRM reg description, s/w cant write 0 to ENB. */
-	/*to make the queue off, need to set the RST bit. */
+	/* As per HRM reg description, s/w can't write 0 to ENB. */
+	/* We need to set the RST bit, to turn the queue off. */
 
-	/* Reset the Enable bit for all the 64 IQs.  */
+	/* Reset the enable bit for all the 64 IQs. */
 	for (q_no = srn; q_no < ern; q_no++) {
 		/* set RST bit to 1. This bit applies to both IQ and OQ */
 		d64 = octeon_read_csr64(oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no));
@@ -194,7 +194,7 @@ static int cn23xx_reset_io_queues(struct octeon_device *oct)
 		octeon_write_csr64(oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no), d64);
 	}
 
-	/*wait until the RST bit is clear or the RST and quite bits are set*/
+	/* Wait until the RST bit is clear or the RST and quiet bits are set */
 	for (q_no = srn; q_no < ern; q_no++) {
 		u64 reg_val = octeon_read_csr64(oct,
 					CN23XX_SLI_IQ_PKT_CONTROL64(q_no));
@@ -245,15 +245,15 @@ static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct)
 	if (cn23xx_reset_io_queues(oct))
 		return -1;
 
-	/** Set the MAC_NUM and PVF_NUM in IQ_PKT_CONTROL reg
-	 * for all queues.Only PF can set these bits.
+	/* Set the MAC_NUM and PVF_NUM in IQ_PKT_CONTROL reg
+	 * for all queues. Only PF can set these bits.
 	 * bits 29:30 indicate the MAC num.
 	 * bits 32:47 indicate the PVF num.
 	 */
 	for (q_no = 0; q_no < ern; q_no++) {
 		reg_val = (u64)oct->pcie_port << CN23XX_PKT_INPUT_CTL_MAC_NUM_POS;
 
-		/* for VF assigned queues. */
+		/* For VF assigned queues. */
 		if (q_no < oct->sriov_info.pf_srn) {
 			vf_num = q_no / oct->sriov_info.rings_per_vf;
 			vf_num += 1; /* VF1, VF2,........ */
@@ -268,7 +268,7 @@ static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct)
 				   reg_val);
 	}
 
-	/* Select ES, RO, NS, RDSIZE,DPTR Fomat#0 for
+	/* Select ES, RO, NS, RDSIZE,DPTR Format#0 for
 	 * pf queues
 	 */
 	for (q_no = srn; q_no < ern; q_no++) {
@@ -289,7 +289,7 @@ static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct)
 		octeon_write_csr64(oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no),
 				   reg_val);
 
-		/* Set WMARK level for triggering PI_INT */
+		/* Set WMARK level to trigger PI_INT */
 		/* intr_threshold = CN23XX_DEF_IQ_INTR_THRESHOLD & */
 		intr_threshold = CFG_GET_IQ_INTR_PKT(cn23xx->conf) &
 				 CN23XX_PKT_IN_DONE_WMARK_MASK;
@@ -354,7 +354,7 @@ static void cn23xx_pf_setup_global_output_regs(struct octeon_device *oct)
 		/* set the ES bit */
 		reg_val |= (CN23XX_PKT_OUTPUT_CTL_ES);
 
-		/* write all the selected settings */
+		/* Write all the selected settings */
 		octeon_write_csr(oct, CN23XX_SLI_OQ_PKT_CONTROL(q_no), reg_val);
 
 		/* Enabling these interrupt in oct->fn_list.enable_interrupt()
@@ -373,7 +373,7 @@ static void cn23xx_pf_setup_global_output_regs(struct octeon_device *oct)
 	/** Setting the water mark level for pko back pressure **/
 	writeq(0x40, (u8 *)oct->mmio[0].hw_addr + CN23XX_SLI_OQ_WMARK);
 
-	/** Disabling setting OQs in reset when ring has no dorebells
+	/* Disabling setting OQs in reset when ring has no doorbells
 	 * enabling this will cause of head of line blocking
 	 */
 	/* Do it only for pass1.1. and pass1.2 */
@@ -383,7 +383,7 @@ static void cn23xx_pf_setup_global_output_regs(struct octeon_device *oct)
 				     CN23XX_SLI_GBL_CONTROL) | 0x2,
 		       (u8 *)oct->mmio[0].hw_addr + CN23XX_SLI_GBL_CONTROL);
 
-	/** Enable channel-level backpressure */
+	/** Enable channel-level backpressure **/
 	if (oct->pf_num)
 		writeq(0xffffffffffffffffULL,
 		       (u8 *)oct->mmio[0].hw_addr + CN23XX_SLI_OUT_BP_EN2_W1S);
@@ -396,7 +396,7 @@ static int cn23xx_setup_pf_device_regs(struct octeon_device *oct)
 {
 	cn23xx_enable_error_reporting(oct);
 
-	/* program the MAC(0..3)_RINFO before setting up input/output regs */
+	/* Program the MAC(0..3)_RINFO before setting up input/output regs */
 	cn23xx_setup_global_mac_regs(oct);
 
 	if (cn23xx_pf_setup_global_input_regs(oct))
@@ -410,7 +410,7 @@ static int cn23xx_setup_pf_device_regs(struct octeon_device *oct)
 	octeon_write_csr64(oct, CN23XX_SLI_WINDOW_CTL,
 			   CN23XX_SLI_WINDOW_CTL_DEFAULT);
 
-	/* set SLI_PKT_IN_JABBER to handle large VXLAN packets */
+	/* Set SLI_PKT_IN_JABBER to handle large VXLAN packets */
 	octeon_write_csr64(oct, CN23XX_SLI_PKT_IN_JABBER, CN23XX_INPUT_JABBER);
 	return 0;
 }
@@ -574,7 +574,7 @@ static int cn23xx_setup_pf_mbox(struct octeon_device *oct)
 		mbox->mbox_read_reg = (u8 *)oct->mmio[0].hw_addr +
 				      CN23XX_SLI_PKT_PF_VF_MBOX_SIG(q_no, 1);
 
-		/*Mail Box Thread creation*/
+		/* Mail Box Thread creation */
 		INIT_DELAYED_WORK(&mbox->mbox_poll_wk.work,
 				  cn23xx_pf_mbox_thread);
 		mbox->mbox_poll_wk.ctxptr = (void *)mbox;
@@ -626,7 +626,7 @@ static int cn23xx_enable_io_queues(struct octeon_device *oct)
 	ern = srn + oct->num_iqs;
 
 	for (q_no = srn; q_no < ern; q_no++) {
-		/* set the corresponding IQ IS_64B bit */
+		/* Set the corresponding IQ IS_64B bit */
 		if (oct->io_qmask.iq64B & BIT_ULL(q_no - srn)) {
 			reg_val = octeon_read_csr64(
 			    oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no));
@@ -635,7 +635,7 @@ static int cn23xx_enable_io_queues(struct octeon_device *oct)
 			    oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no), reg_val);
 		}
 
-		/* set the corresponding IQ ENB bit */
+		/* Set the corresponding IQ ENB bit */
 		if (oct->io_qmask.iq & BIT_ULL(q_no - srn)) {
 			/* IOQs are in reset by default in PEM2 mode,
 			 * clearing reset bit
@@ -681,7 +681,7 @@ static int cn23xx_enable_io_queues(struct octeon_device *oct)
 	}
 	for (q_no = srn; q_no < ern; q_no++) {
 		u32 reg_val;
-		/* set the corresponding OQ ENB bit */
+		/* Set the corresponding OQ ENB bit */
 		if (oct->io_qmask.oq & BIT_ULL(q_no - srn)) {
 			reg_val = octeon_read_csr(
 			    oct, CN23XX_SLI_OQ_PKT_CONTROL(q_no));
@@ -707,7 +707,7 @@ static void cn23xx_disable_io_queues(struct octeon_device *oct)
 	for (q_no = srn; q_no < ern; q_no++) {
 		loop = HZ;
 
-		/* start the Reset for a particular ring */
+		/* Start the Reset for a particular ring */
 		WRITE_ONCE(d64, octeon_read_csr64(
 			   oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no)));
 		WRITE_ONCE(d64, READ_ONCE(d64) &
@@ -740,7 +740,7 @@ static void cn23xx_disable_io_queues(struct octeon_device *oct)
 		loop = HZ;
 
 		/* Wait until hardware indicates that the particular IQ
-		 * is out of reset.It given that SLI_PKT_RING_RST is
+		 * is out of reset. Given that SLI_PKT_RING_RST is
 		 * common for both IQs and OQs
 		 */
 		WRITE_ONCE(d64, octeon_read_csr64(
@@ -760,7 +760,7 @@ static void cn23xx_disable_io_queues(struct octeon_device *oct)
 			schedule_timeout_uninterruptible(1);
 		}
 
-		/* clear the SLI_PKT(0..63)_CNTS[CNT] reg value */
+		/* Clear the SLI_PKT(0..63)_CNTS[CNT] reg value */
 		WRITE_ONCE(d32, octeon_read_csr(
 					oct, CN23XX_SLI_OQ_PKTS_SENT(q_no)));
 		octeon_write_csr(oct, CN23XX_SLI_OQ_PKTS_SENT(q_no),
@@ -793,7 +793,7 @@ static u64 cn23xx_pf_msix_interrupt_handler(void *dev)
 	if (!pkts_sent || (pkts_sent == 0xFFFFFFFFFFFFFFFFULL))
 		return ret;
 
-	/* Write count reg in sli_pkt_cnts to clear these int.*/
+	/* Write count reg in sli_pkt_cnts to clear these int. */
 	if ((pkts_sent & CN23XX_INTR_PO_INT) ||
 	    (pkts_sent & CN23XX_INTR_PI_INT)) {
 		if (pkts_sent & CN23XX_INTR_PO_INT)
@@ -908,7 +908,7 @@ static u32 cn23xx_bar1_idx_read(struct octeon_device *oct, u32 idx)
 	    oct, CN23XX_PEM_BAR1_INDEX_REG(oct->pcie_port, idx));
 }
 
-/* always call with lock held */
+/* Always call with lock held */
 static u32 cn23xx_update_read_index(struct octeon_instr_queue *iq)
 {
 	u32 new_idx;
@@ -919,7 +919,7 @@ static u32 cn23xx_update_read_index(struct octeon_instr_queue *iq)
 	iq->pkt_in_done = pkt_in_done;
 
 	/* Modulo of the new index with the IQ size will give us
-	 * the new index.  The iq->reset_instr_cnt is always zero for
+	 * the new index. The iq->reset_instr_cnt is always zero for
 	 * cn23xx, so no extra adjustments are needed.
 	 */
 	new_idx = (iq->octeon_read_index +
@@ -934,8 +934,8 @@ static void cn23xx_enable_pf_interrupt(struct octeon_device *oct, u8 intr_flag)
 	struct octeon_cn23xx_pf *cn23xx = (struct octeon_cn23xx_pf *)oct->chip;
 	u64 intr_val = 0;
 
-	/*  Divide the single write to multiple writes based on the flag. */
-	/* Enable Interrupt */
+	/* Divide the single write to multiple writes based on the flag. */
+	/* Enable Interrupts */
 	if (intr_flag == OCTEON_ALL_INTR) {
 		writeq(cn23xx->intr_mask64, cn23xx->intr_enb_reg64);
 	} else if (intr_flag & OCTEON_OUTPUT_INTR) {
@@ -990,7 +990,7 @@ static int cn23xx_get_pf_num(struct octeon_device *oct)
 
 	ret = 0;
 
-	/** Read Function Dependency Link reg to get the function number */
+	/* Read Function Dependency Link reg to get the function number */
 	if (pci_read_config_dword(oct->pci_dev, CN23XX_PCIE_SRIOV_FDL,
 				  &fdl_bit) == 0) {
 		oct->pf_num = ((fdl_bit >> CN23XX_PCIE_SRIOV_FDL_BIT_POS) &
@@ -1003,13 +1003,13 @@ static int cn23xx_get_pf_num(struct octeon_device *oct)
 		 * In this case, read the PF number from the
 		 * SLI_PKT0_INPUT_CONTROL reg (written by f/w)
 		 */
-		pkt0_in_ctl = octeon_read_csr64(oct,
-						CN23XX_SLI_IQ_PKT_CONTROL64(0));
+		pkt0_in_ctl =
+			octeon_read_csr64(oct, CN23XX_SLI_IQ_PKT_CONTROL64(0));
 		pfnum = (pkt0_in_ctl >> CN23XX_PKT_INPUT_CTL_PF_NUM_POS) &
 			CN23XX_PKT_INPUT_CTL_PF_NUM_MASK;
 		mac = (octeon_read_csr(oct, CN23XX_SLI_MAC_NUMBER)) & 0xff;
 
-		/* validate PF num by reading RINFO; f/w writes RINFO.trs == 1*/
+		/* Validate PF num by reading RINFO; f/w writes RINFO.trs == 1 */
 		d64 = octeon_read_csr64(oct,
 					CN23XX_SLI_PKT_MAC_RINFO64(mac, pfnum));
 		trs = (int)(d64 >> CN23XX_PKT_MAC_CTL_RINFO_TRS_BIT_POS) & 0xff;
@@ -1208,53 +1208,14 @@ int setup_cn23xx_octeon_pf_device(struct octeon_device *oct)
 }
 EXPORT_SYMBOL_GPL(setup_cn23xx_octeon_pf_device);
 
-int validate_cn23xx_pf_config_info(struct octeon_device *oct,
-				   struct octeon_config *conf23xx)
-{
-	if (CFG_GET_IQ_MAX_Q(conf23xx) > CN23XX_MAX_INPUT_QUEUES) {
-		dev_err(&oct->pci_dev->dev, "%s: Num IQ (%d) exceeds Max (%d)\n",
-			__func__, CFG_GET_IQ_MAX_Q(conf23xx),
-			CN23XX_MAX_INPUT_QUEUES);
-		return 1;
-	}
-
-	if (CFG_GET_OQ_MAX_Q(conf23xx) > CN23XX_MAX_OUTPUT_QUEUES) {
-		dev_err(&oct->pci_dev->dev, "%s: Num OQ (%d) exceeds Max (%d)\n",
-			__func__, CFG_GET_OQ_MAX_Q(conf23xx),
-			CN23XX_MAX_OUTPUT_QUEUES);
-		return 1;
-	}
-
-	if (CFG_GET_IQ_INSTR_TYPE(conf23xx) != OCTEON_32BYTE_INSTR &&
-	    CFG_GET_IQ_INSTR_TYPE(conf23xx) != OCTEON_64BYTE_INSTR) {
-		dev_err(&oct->pci_dev->dev, "%s: Invalid instr type for IQ\n",
-			__func__);
-		return 1;
-	}
-
-	if (!CFG_GET_OQ_REFILL_THRESHOLD(conf23xx)) {
-		dev_err(&oct->pci_dev->dev, "%s: Invalid parameter for OQ\n",
-			__func__);
-		return 1;
-	}
-
-	if (!(CFG_GET_OQ_INTR_TIME(conf23xx))) {
-		dev_err(&oct->pci_dev->dev, "%s: Invalid parameter for OQ\n",
-			__func__);
-		return 1;
-	}
-
-	return 0;
-}
-
 int cn23xx_fw_loaded(struct octeon_device *oct)
 {
 	u64 val;
 
 	/* If there's more than one active PF on this NIC, then that
-	 * implies that the NIC firmware is loaded and running.  This check
+	 * implies that the NIC firmware is loaded and running. This check
 	 * prevents a rare false negative that might occur if we only relied
-	 * on checking the SCR2_BIT_FW_LOADED flag.  The false negative would
+	 * on checking the SCR2_BIT_FW_LOADED flag. The false negative would
 	 * happen if the PF driver sees SCR2_BIT_FW_LOADED as cleared even
 	 * though the firmware was already loaded but still booting and has yet
 	 * to set SCR2_BIT_FW_LOADED.
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
index 234b96b4f488..bbe9f3133b07 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
@@ -54,9 +54,6 @@ struct oct_vf_stats {
 
 int setup_cn23xx_octeon_pf_device(struct octeon_device *oct);
 
-int validate_cn23xx_pf_config_info(struct octeon_device *oct,
-				   struct octeon_config *conf23xx);
-
 u32 cn23xx_pf_get_oq_ticks(struct octeon_device *oct, u32 time_intr_in_us);
 
 int cn23xx_sriov_config(struct octeon_device *oct);
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index 674c54831875..215dac201b4a 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -472,7 +472,7 @@ int setup_rx_oom_poll_fn(struct net_device *netdev)
 		q_no = lio->linfo.rxpciq[q].s.q_no;
 		wq = &lio->rxq_status_wq[q_no];
 		wq->wq = alloc_workqueue("rxq-oom-status",
-					 WQ_MEM_RECLAIM, 0);
+					 WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 		if (!wq->wq) {
 			dev_err(&oct->pci_dev->dev, "unable to create cavium rxq oom status wq\n");
 			return -ENOMEM;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 1d79f6eaa41f..0732440eeacd 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -526,7 +526,8 @@ static inline int setup_link_status_change_wq(struct net_device *netdev)
 	struct octeon_device *oct = lio->oct_dev;
 
 	lio->link_status_wq.wq = alloc_workqueue("link-status",
-						 WQ_MEM_RECLAIM, 0);
+						 WQ_MEM_RECLAIM | WQ_PERCPU,
+						 0);
 	if (!lio->link_status_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "unable to create cavium link status wq\n");
 		return -1;
@@ -659,7 +660,8 @@ static inline int setup_sync_octeon_time_wq(struct net_device *netdev)
 	struct octeon_device *oct = lio->oct_dev;
 
 	lio->sync_octeon_time_wq.wq =
-		alloc_workqueue("update-octeon-time", WQ_MEM_RECLAIM, 0);
+		alloc_workqueue("update-octeon-time",
+				WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!lio->sync_octeon_time_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "Unable to create wq to update octeon time\n");
 		return -1;
@@ -1734,7 +1736,7 @@ static inline int setup_tx_poll_fn(struct net_device *netdev)
 	struct octeon_device *oct = lio->oct_dev;
 
 	lio->txq_status_wq.wq = alloc_workqueue("txq-status",
-						WQ_MEM_RECLAIM, 0);
+						WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!lio->txq_status_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "unable to create cavium txq status wq\n");
 		return -1;
@@ -2105,20 +2107,16 @@ liquidio_get_stats64(struct net_device *netdev,
 		lstats->tx_fifo_errors;
 }
 
-/**
- * hwtstamp_ioctl - Handler for SIOCSHWTSTAMP ioctl
- * @netdev: network device
- * @ifr: interface request
- */
-static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
+static int liquidio_hwtstamp_set(struct net_device *netdev,
+				 struct kernel_hwtstamp_config *conf,
+				 struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config conf;
 	struct lio *lio = GET_LIO(netdev);
 
-	if (copy_from_user(&conf, ifr->ifr_data, sizeof(conf)))
-		return -EFAULT;
+	if (!lio->oct_dev->ptp_enable)
+		return -EOPNOTSUPP;
 
-	switch (conf.tx_type) {
+	switch (conf->tx_type) {
 	case HWTSTAMP_TX_ON:
 	case HWTSTAMP_TX_OFF:
 		break;
@@ -2126,7 +2124,7 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (conf.rx_filter) {
+	switch (conf->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		break;
 	case HWTSTAMP_FILTER_ALL:
@@ -2144,39 +2142,32 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 	case HWTSTAMP_FILTER_NTP_ALL:
-		conf.rx_filter = HWTSTAMP_FILTER_ALL;
+		conf->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	if (conf.rx_filter == HWTSTAMP_FILTER_ALL)
+	if (conf->rx_filter == HWTSTAMP_FILTER_ALL)
 		ifstate_set(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED);
 
 	else
 		ifstate_reset(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED);
 
-	return copy_to_user(ifr->ifr_data, &conf, sizeof(conf)) ? -EFAULT : 0;
+	return 0;
 }
 
-/**
- * liquidio_ioctl - ioctl handler
- * @netdev: network device
- * @ifr: interface request
- * @cmd: command
- */
-static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+static int liquidio_hwtstamp_get(struct net_device *netdev,
+				 struct kernel_hwtstamp_config *conf)
 {
 	struct lio *lio = GET_LIO(netdev);
 
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		if (lio->oct_dev->ptp_enable)
-			return hwtstamp_ioctl(netdev, ifr);
-		fallthrough;
-	default:
-		return -EOPNOTSUPP;
-	}
+	/* TX timestamping is technically always on */
+	conf->tx_type = HWTSTAMP_TX_ON;
+	conf->rx_filter = ifstate_check(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED) ?
+			  HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
+
+	return 0;
 }
 
 /**
@@ -3225,7 +3216,6 @@ static const struct net_device_ops lionetdevops = {
 	.ndo_vlan_rx_add_vid    = liquidio_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = liquidio_vlan_rx_kill_vid,
 	.ndo_change_mtu		= liquidio_change_mtu,
-	.ndo_eth_ioctl		= liquidio_ioctl,
 	.ndo_fix_features	= liquidio_fix_features,
 	.ndo_set_features	= liquidio_set_features,
 	.ndo_set_vf_mac		= liquidio_set_vf_mac,
@@ -3236,6 +3226,8 @@ static const struct net_device_ops lionetdevops = {
 	.ndo_set_vf_link_state  = liquidio_set_vf_link_state,
 	.ndo_get_vf_stats	= liquidio_get_vf_stats,
 	.ndo_get_port_parent_id	= liquidio_get_port_parent_id,
+	.ndo_hwtstamp_get	= liquidio_hwtstamp_get,
+	.ndo_hwtstamp_set	= liquidio_hwtstamp_set,
 };
 
 /**
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index 62c2eadc33e3..e02942dbbcce 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -304,7 +304,8 @@ static int setup_link_status_change_wq(struct net_device *netdev)
 	struct octeon_device *oct = lio->oct_dev;
 
 	lio->link_status_wq.wq = alloc_workqueue("link-status",
-						 WQ_MEM_RECLAIM, 0);
+						 WQ_MEM_RECLAIM | WQ_PERCPU,
+						 0);
 	if (!lio->link_status_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "unable to create cavium link status wq\n");
 		return -1;
@@ -1235,20 +1236,13 @@ liquidio_get_stats64(struct net_device *netdev,
 		lstats->tx_carrier_errors;
 }
 
-/**
- * hwtstamp_ioctl - Handler for SIOCSHWTSTAMP ioctl
- * @netdev: network device
- * @ifr: interface request
- */
-static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
+static int liquidio_hwtstamp_set(struct net_device *netdev,
+				 struct kernel_hwtstamp_config *conf,
+				 struct netlink_ext_ack *extack)
 {
 	struct lio *lio = GET_LIO(netdev);
-	struct hwtstamp_config conf;
-
-	if (copy_from_user(&conf, ifr->ifr_data, sizeof(conf)))
-		return -EFAULT;
 
-	switch (conf.tx_type) {
+	switch (conf->tx_type) {
 	case HWTSTAMP_TX_ON:
 	case HWTSTAMP_TX_OFF:
 		break;
@@ -1256,7 +1250,7 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (conf.rx_filter) {
+	switch (conf->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		break;
 	case HWTSTAMP_FILTER_ALL:
@@ -1274,35 +1268,31 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 	case HWTSTAMP_FILTER_NTP_ALL:
-		conf.rx_filter = HWTSTAMP_FILTER_ALL;
+		conf->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	if (conf.rx_filter == HWTSTAMP_FILTER_ALL)
+	if (conf->rx_filter == HWTSTAMP_FILTER_ALL)
 		ifstate_set(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED);
 
 	else
 		ifstate_reset(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED);
 
-	return copy_to_user(ifr->ifr_data, &conf, sizeof(conf)) ? -EFAULT : 0;
+	return 0;
 }
 
-/**
- * liquidio_ioctl - ioctl handler
- * @netdev: network device
- * @ifr: interface request
- * @cmd: command
- */
-static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+static int liquidio_hwtstamp_get(struct net_device *netdev,
+				 struct kernel_hwtstamp_config *conf)
 {
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return hwtstamp_ioctl(netdev, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
+	struct lio *lio = GET_LIO(netdev);
+
+	/* TX timestamping is techically always on */
+	conf->tx_type = HWTSTAMP_TX_ON;
+	conf->rx_filter = ifstate_check(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED) ?
+			  HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
+	return 0;
 }
 
 static void handle_timestamp(struct octeon_device *oct, u32 status, void *buf)
@@ -1880,9 +1870,10 @@ static const struct net_device_ops lionetdevops = {
 	.ndo_vlan_rx_add_vid    = liquidio_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = liquidio_vlan_rx_kill_vid,
 	.ndo_change_mtu		= liquidio_change_mtu,
-	.ndo_eth_ioctl		= liquidio_ioctl,
 	.ndo_fix_features	= liquidio_fix_features,
 	.ndo_set_features	= liquidio_set_features,
+	.ndo_hwtstamp_get	= liquidio_hwtstamp_get,
+	.ndo_hwtstamp_set	= liquidio_hwtstamp_set,
 };
 
 static int lio_nic_info(struct octeon_recv_info *recv_info, void *buf)
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 6b6cb73482d7..1753bb87dfbd 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -1433,22 +1433,6 @@ int octeon_wait_for_ddr_init(struct octeon_device *oct, u32 *timeout)
 }
 EXPORT_SYMBOL_GPL(octeon_wait_for_ddr_init);
 
-/* Get the octeon id assigned to the octeon device passed as argument.
- *  This function is exported to other modules.
- *  @param dev - octeon device pointer passed as a void *.
- *  @return octeon device id
- */
-int lio_get_device_id(void *dev)
-{
-	struct octeon_device *octeon_dev = (struct octeon_device *)dev;
-	u32 i;
-
-	for (i = 0; i < MAX_OCTEON_DEVICES; i++)
-		if (octeon_device[i] == octeon_dev)
-			return octeon_dev->octeon_id;
-	return -1;
-}
-
 void lio_enable_irq(struct octeon_droq *droq, struct octeon_instr_queue *iq)
 {
 	u64 instr_cnt;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index d26364c2ac81..19344b21f8fb 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -705,13 +705,6 @@ octeon_get_dispatch(struct octeon_device *octeon_dev, u16 opcode,
  */
 struct octeon_device *lio_get_device(u32 octeon_id);
 
-/** Get the octeon id assigned to the octeon device passed as argument.
- *  This function is exported to other modules.
- *  @param dev - octeon device pointer passed as a void *.
- *  @return octeon device id
- */
-int lio_get_device_id(void *dev);
-
 /** Read windowed register.
  *  @param  oct   -  pointer to the Octeon device.
  *  @param  addr  -  Address of the register to read.
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
index 5b4cb725f60f..953edf0c7096 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
@@ -157,7 +157,7 @@ err_release_region:
 	    response of the request.
  *          0: the request will wait until its response gets back
  *	       from the firmware within LIO_SC_MAX_TMO_MS milli sec.
- *	       It the response does not return within
+ *	       If the response does not return within
  *	       LIO_SC_MAX_TMO_MS milli sec, lio_process_ordered_list()
  *	       will move the request to zombie response list.
  *
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
index 87dd6f89ce51..c139fc423764 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
@@ -268,7 +268,7 @@ octeon_alloc_soft_command_resp(struct octeon_device    *oct,
  * @param oct - octeon device pointer
  * @param ndata - control structure with queueing, and buffer information
  *
- * @returns IQ_FAILED if it failed to add to the input queue. IQ_STOP if it the
+ * @returns IQ_FAILED if it failed to add to the input queue. IQ_STOP if the
  * queue should be stopped, and IQ_SEND_OK if it sent okay.
  */
 int octnet_send_nic_data_pkt(struct octeon_device *oct,
@@ -278,7 +278,7 @@ int octnet_send_nic_data_pkt(struct octeon_device *oct,
 /** Send a NIC control packet to the device
  * @param oct - octeon device pointer
  * @param nctrl - control structure with command, timout, and callback info
- * @returns IQ_FAILED if it failed to add to the input queue. IQ_STOP if it the
+ * @returns IQ_FAILED if it failed to add to the input queue. IQ_STOP if the
  * queue should be stopped, and IQ_SEND_OK if it sent okay.
  */
 int
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index de8a6ce86ad7..d7cfb20eea00 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -126,13 +126,13 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 	oct->io_qmask.iq |= BIT_ULL(iq_no);
 
 	/* Set the 32B/64B mode for each input queue */
-	oct->io_qmask.iq64B |= ((conf->instr_type == 64) << iq_no);
+	oct->io_qmask.iq64B |= ((u64)(conf->instr_type == 64) << iq_no);
 	iq->iqcmd_64B = (conf->instr_type == 64);
 
 	oct->fn_list.setup_iq_regs(oct, iq_no);
 
 	oct->check_db_wq[iq_no].wq = alloc_workqueue("check_iq_db",
-						     WQ_MEM_RECLAIM,
+						     WQ_MEM_RECLAIM | WQ_PERCPU,
 						     0);
 	if (!oct->check_db_wq[iq_no].wq) {
 		vfree(iq->request_list);
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c
index 861050966e18..de1a8335b545 100644
--- a/drivers/net/ethernet/cavium/liquidio/response_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c
@@ -39,7 +39,8 @@ int octeon_setup_response_list(struct octeon_device *oct)
 	}
 	spin_lock_init(&oct->cmd_resp_wqlock);
 
-	oct->dma_comp_wq.wq = alloc_workqueue("dma-comp", WQ_MEM_RECLAIM, 0);
+	oct->dma_comp_wq.wq = alloc_workqueue("dma-comp",
+					      WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!oct->dma_comp_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "failed to create wq thread\n");
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 393b9951490a..c190fc6538d4 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -690,19 +690,16 @@ static irqreturn_t octeon_mgmt_interrupt(int cpl, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int octeon_mgmt_ioctl_hwtstamp(struct net_device *netdev,
-				      struct ifreq *rq, int cmd)
+static int octeon_mgmt_hwtstamp_set(struct net_device *netdev,
+				    struct kernel_hwtstamp_config *config,
+				    struct netlink_ext_ack *extack)
 {
 	struct octeon_mgmt *p = netdev_priv(netdev);
-	struct hwtstamp_config config;
-	union cvmx_mio_ptp_clock_cfg ptp;
 	union cvmx_agl_gmx_rxx_frm_ctl rxx_frm_ctl;
+	union cvmx_mio_ptp_clock_cfg ptp;
 	bool have_hw_timestamps = false;
 
-	if (copy_from_user(&config, rq->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	/* Check the status of hardware for tiemstamps */
+	/* Check the status of hardware for timestamps */
 	if (OCTEON_IS_MODEL(OCTEON_CN6XXX)) {
 		/* Get the current state of the PTP clock */
 		ptp.u64 = cvmx_read_csr(CVMX_MIO_PTP_CLOCK_CFG);
@@ -733,10 +730,12 @@ static int octeon_mgmt_ioctl_hwtstamp(struct net_device *netdev,
 		have_hw_timestamps = true;
 	}
 
-	if (!have_hw_timestamps)
+	if (!have_hw_timestamps) {
+		NL_SET_ERR_MSG_MOD(extack, "HW doesn't support timestamping");
 		return -EINVAL;
+	}
 
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 	case HWTSTAMP_TX_ON:
 		break;
@@ -744,7 +743,7 @@ static int octeon_mgmt_ioctl_hwtstamp(struct net_device *netdev,
 		return -ERANGE;
 	}
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		p->has_rx_tstamp = false;
 		rxx_frm_ctl.u64 = cvmx_read_csr(p->agl + AGL_GMX_RX_FRM_CTL);
@@ -766,33 +765,34 @@ static int octeon_mgmt_ioctl_hwtstamp(struct net_device *netdev,
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 	case HWTSTAMP_FILTER_NTP_ALL:
-		p->has_rx_tstamp = have_hw_timestamps;
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
-		if (p->has_rx_tstamp) {
-			rxx_frm_ctl.u64 = cvmx_read_csr(p->agl + AGL_GMX_RX_FRM_CTL);
-			rxx_frm_ctl.s.ptp_mode = 1;
-			cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_CTL, rxx_frm_ctl.u64);
-		}
+		p->has_rx_tstamp = true;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
+		rxx_frm_ctl.u64 = cvmx_read_csr(p->agl + AGL_GMX_RX_FRM_CTL);
+		rxx_frm_ctl.s.ptp_mode = 1;
+		cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_CTL, rxx_frm_ctl.u64);
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	if (copy_to_user(rq->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
-
 	return 0;
 }
 
-static int octeon_mgmt_ioctl(struct net_device *netdev,
-			     struct ifreq *rq, int cmd)
+static int octeon_mgmt_hwtstamp_get(struct net_device *netdev,
+				    struct kernel_hwtstamp_config *config)
 {
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return octeon_mgmt_ioctl_hwtstamp(netdev, rq, cmd);
-	default:
-		return phy_do_ioctl(netdev, rq, cmd);
-	}
+	struct octeon_mgmt *p = netdev_priv(netdev);
+
+	/* Check the status of hardware for timestamps */
+	if (!OCTEON_IS_MODEL(OCTEON_CN6XXX))
+		return -EINVAL;
+
+	config->tx_type = HWTSTAMP_TX_ON;
+	config->rx_filter = p->has_rx_tstamp ?
+			    HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
+
+	return 0;
 }
 
 static void octeon_mgmt_disable_link(struct octeon_mgmt *p)
@@ -1370,11 +1370,13 @@ static const struct net_device_ops octeon_mgmt_ops = {
 	.ndo_start_xmit =		octeon_mgmt_xmit,
 	.ndo_set_rx_mode =		octeon_mgmt_set_rx_filtering,
 	.ndo_set_mac_address =		octeon_mgmt_set_mac_address,
-	.ndo_eth_ioctl =			octeon_mgmt_ioctl,
+	.ndo_eth_ioctl =		phy_do_ioctl,
 	.ndo_change_mtu =		octeon_mgmt_change_mtu,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller =		octeon_mgmt_poll_controller,
 #endif
+	.ndo_hwtstamp_get =		octeon_mgmt_hwtstamp_get,
+	.ndo_hwtstamp_set =		octeon_mgmt_hwtstamp_set,
 };
 
 static int octeon_mgmt_probe(struct platform_device *pdev)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index d0ff0c170b1a..413028bdcacb 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -516,8 +516,8 @@ static int nicvf_set_ringparam(struct net_device *netdev,
 	return 0;
 }
 
-static int nicvf_get_rss_hash_opts(struct nicvf *nic,
-				   struct ethtool_rxnfc *info)
+static int nicvf_get_rxfh_fields(struct net_device *dev,
+				 struct ethtool_rxfh_fields *info)
 {
 	info->data = 0;
 
@@ -541,36 +541,29 @@ static int nicvf_get_rss_hash_opts(struct nicvf *nic,
 	return 0;
 }
 
-static int nicvf_get_rxnfc(struct net_device *dev,
-			   struct ethtool_rxnfc *info, u32 *rules)
+static u32 nicvf_get_rx_ring_count(struct net_device *dev)
 {
 	struct nicvf *nic = netdev_priv(dev);
-	int ret = -EOPNOTSUPP;
 
-	switch (info->cmd) {
-	case ETHTOOL_GRXRINGS:
-		info->data = nic->rx_queues;
-		ret = 0;
-		break;
-	case ETHTOOL_GRXFH:
-		return nicvf_get_rss_hash_opts(nic, info);
-	default:
-		break;
-	}
-	return ret;
+	return nic->rx_queues;
 }
 
-static int nicvf_set_rss_hash_opts(struct nicvf *nic,
-				   struct ethtool_rxnfc *info)
+static int nicvf_set_rxfh_fields(struct net_device *dev,
+				 const struct ethtool_rxfh_fields *info,
+				 struct netlink_ext_ack *extack)
 {
-	struct nicvf_rss_info *rss = &nic->rss_info;
-	u64 rss_cfg = nicvf_reg_read(nic, NIC_VNIC_RSS_CFG);
+	struct nicvf *nic = netdev_priv(dev);
+	struct nicvf_rss_info *rss;
+	u64 rss_cfg;
+
+	rss = &nic->rss_info;
+	rss_cfg = nicvf_reg_read(nic, NIC_VNIC_RSS_CFG);
 
 	if (!rss->enable)
 		netdev_err(nic->netdev,
 			   "RSS is disabled, hash cannot be set\n");
 
-	netdev_info(nic->netdev, "Set RSS flow type = %d, data = %lld\n",
+	netdev_info(nic->netdev, "Set RSS flow type = %d, data = %u\n",
 		    info->flow_type, info->data);
 
 	if (!(info->data & RXH_IP_SRC) || !(info->data & RXH_IP_DST))
@@ -628,19 +621,6 @@ static int nicvf_set_rss_hash_opts(struct nicvf *nic,
 	return 0;
 }
 
-static int nicvf_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info)
-{
-	struct nicvf *nic = netdev_priv(dev);
-
-	switch (info->cmd) {
-	case ETHTOOL_SRXFH:
-		return nicvf_set_rss_hash_opts(nic, info);
-	default:
-		break;
-	}
-	return -EOPNOTSUPP;
-}
-
 static u32 nicvf_get_rxfh_key_size(struct net_device *netdev)
 {
 	return RSS_HASH_KEY_SIZE * sizeof(u64);
@@ -871,12 +851,13 @@ static const struct ethtool_ops nicvf_ethtool_ops = {
 	.get_coalesce		= nicvf_get_coalesce,
 	.get_ringparam		= nicvf_get_ringparam,
 	.set_ringparam		= nicvf_set_ringparam,
-	.get_rxnfc		= nicvf_get_rxnfc,
-	.set_rxnfc		= nicvf_set_rxnfc,
+	.get_rx_ring_count	= nicvf_get_rx_ring_count,
 	.get_rxfh_key_size	= nicvf_get_rxfh_key_size,
 	.get_rxfh_indir_size	= nicvf_get_rxfh_indir_size,
 	.get_rxfh		= nicvf_get_rxfh,
 	.set_rxfh		= nicvf_set_rxfh,
+	.get_rxfh_fields	= nicvf_get_rxfh_fields,
+	.set_rxfh_fields	= nicvf_set_rxfh_fields,
 	.get_channels		= nicvf_get_channels,
 	.set_channels		= nicvf_set_channels,
 	.get_pauseparam         = nicvf_get_pauseparam,
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index aebb9fef3f6e..0b6e30a8feb0 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1578,7 +1578,6 @@ napi_del:
 static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct nicvf *nic = netdev_priv(netdev);
-	int orig_mtu = netdev->mtu;
 
 	/* For now just support only the usual MTU sized frames,
 	 * plus some headroom for VLAN, QinQ.
@@ -1589,15 +1588,10 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 		return -EINVAL;
 	}
 
-	WRITE_ONCE(netdev->mtu, new_mtu);
-
-	if (!netif_running(netdev))
-		return 0;
-
-	if (nicvf_update_hw_max_frs(nic, new_mtu)) {
-		netdev->mtu = orig_mtu;
+	if (netif_running(netdev) && nicvf_update_hw_max_frs(nic, new_mtu))
 		return -EINVAL;
-	}
+
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	return 0;
 }
@@ -1905,18 +1899,18 @@ static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 	}
 }
 
-static int nicvf_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr)
+static int nicvf_hwtstamp_set(struct net_device *netdev,
+			      struct kernel_hwtstamp_config *config,
+			      struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
 	struct nicvf *nic = netdev_priv(netdev);
 
-	if (!nic->ptp_clock)
+	if (!nic->ptp_clock) {
+		NL_SET_ERR_MSG_MOD(extack, "HW timestamping is not supported");
 		return -ENODEV;
+	}
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 	case HWTSTAMP_TX_ON:
 		break;
@@ -1924,7 +1918,7 @@ static int nicvf_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		nic->hw_rx_tstamp = false;
 		break;
@@ -1943,7 +1937,7 @@ static int nicvf_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 		nic->hw_rx_tstamp = true;
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
 		return -ERANGE;
@@ -1952,20 +1946,24 @@ static int nicvf_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr)
 	if (netif_running(netdev))
 		nicvf_config_hw_rx_tstamp(nic, nic->hw_rx_tstamp);
 
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
-
 	return 0;
 }
 
-static int nicvf_ioctl(struct net_device *netdev, struct ifreq *req, int cmd)
+static int nicvf_hwtstamp_get(struct net_device *netdev,
+			      struct kernel_hwtstamp_config *config)
 {
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return nicvf_config_hwtstamp(netdev, req);
-	default:
-		return -EOPNOTSUPP;
-	}
+	struct nicvf *nic = netdev_priv(netdev);
+
+	if (!nic->ptp_clock)
+		return -ENODEV;
+
+	/* TX timestamping is technically always on */
+	config->tx_type = HWTSTAMP_TX_ON;
+	config->rx_filter = nic->hw_rx_tstamp ?
+			    HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
+
+	return 0;
 }
 
 static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs,
@@ -2087,8 +2085,9 @@ static const struct net_device_ops nicvf_netdev_ops = {
 	.ndo_fix_features       = nicvf_fix_features,
 	.ndo_set_features       = nicvf_set_features,
 	.ndo_bpf		= nicvf_xdp,
-	.ndo_eth_ioctl           = nicvf_ioctl,
 	.ndo_set_rx_mode        = nicvf_set_rx_mode,
+	.ndo_hwtstamp_get	= nicvf_hwtstamp_get,
+	.ndo_hwtstamp_set	= nicvf_hwtstamp_set,
 };
 
 static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 06397cc8bb36..5211759bfe47 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -1389,11 +1389,9 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry,
 		this_cpu_inc(nic->pnicvf->drv_stats->tx_tso);
 	}
 
-	/* Check if timestamp is requested */
-	if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
-		skb_tx_timestamp(skb);
+	/* Check if hw timestamp is requested */
+	if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
 		return;
-	}
 
 	/* Tx timestamping not supported along with TSO, so ignore request */
 	if (skb_shinfo(skb)->gso_size)
@@ -1472,6 +1470,8 @@ static inline void nicvf_sq_doorbell(struct nicvf *nic, struct sk_buff *skb,
 
 	netdev_tx_sent_queue(txq, skb->len);
 
+	skb_tx_timestamp(skb);
+
 	/* make sure all memory stores are done before ringing doorbell */
 	smp_wmb();
 
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 608cc6af5af1..9efb60842ad1 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1429,9 +1429,9 @@ static acpi_status bgx_acpi_match_id(acpi_handle handle, u32 lvl,
 {
 	struct acpi_buffer string = { ACPI_ALLOCATE_BUFFER, NULL };
 	struct bgx *bgx = context;
-	char bgx_sel[5];
+	char bgx_sel[7];
 
-	snprintf(bgx_sel, 5, "BGX%d", bgx->bgx_id);
+	snprintf(bgx_sel, sizeof(bgx_sel), "BGX%d", bgx->bgx_id);
 	if (ACPI_FAILURE(acpi_get_name(handle, ACPI_SINGLE_NAME, &string))) {
 		pr_warn("Invalid link device\n");
 		return AE_OK;
@@ -1493,13 +1493,17 @@ static int bgx_init_of_phy(struct bgx *bgx)
 		 * this cortina phy, for which there is no driver
 		 * support, ignore it.
 		 */
-		if (phy_np &&
-		    !of_device_is_compatible(phy_np, "cortina,cs4223-slice")) {
-			/* Wait until the phy drivers are available */
-			pd = of_phy_find_device(phy_np);
-			if (!pd)
-				goto defer;
-			bgx->lmac[lmac].phydev = pd;
+		if (phy_np) {
+			if (!of_device_is_compatible(phy_np, "cortina,cs4223-slice")) {
+				/* Wait until the phy drivers are available */
+				pd = of_phy_find_device(phy_np);
+				if (!pd) {
+					of_node_put(phy_np);
+					goto defer;
+				}
+				bgx->lmac[lmac].phydev = pd;
+			}
+			of_node_put(phy_np);
 		}
 
 		lmac++;
@@ -1515,11 +1519,11 @@ defer:
 	 * for phy devices we may have already found.
 	 */
 	while (lmac) {
+		lmac--;
 		if (bgx->lmac[lmac].phydev) {
 			put_device(&bgx->lmac[lmac].phydev->mdio.dev);
 			bgx->lmac[lmac].phydev = NULL;
 		}
-		lmac--;
 	}
 	of_node_put(node);
 	return -EPROBE_DEFER;
@@ -1605,10 +1609,10 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return dev_err_probe(dev, err, "Failed to enable PCI device\n");
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
+	err = pcim_request_all_regions(pdev, DRV_NAME);
 	if (err) {
 		dev_err(dev, "PCI request regions failed 0x%x\n", err);
-		goto err_disable_device;
+		goto err_zero_drv_data;
 	}
 
 	/* MAP configuration registers */
@@ -1616,7 +1620,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!bgx->reg_base) {
 		dev_err(dev, "BGX: Cannot map CSR memory space, aborting\n");
 		err = -ENOMEM;
-		goto err_release_regions;
+		goto err_zero_drv_data;
 	}
 
 	set_max_bgx_per_node(pdev);
@@ -1688,10 +1692,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 err_enable:
 	bgx_vnic[bgx->bgx_id] = NULL;
 	pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
-err_release_regions:
-	pci_release_regions(pdev);
-err_disable_device:
-	pci_disable_device(pdev);
+err_zero_drv_data:
 	pci_set_drvdata(pdev, NULL);
 	return err;
 }
@@ -1710,8 +1711,6 @@ static void bgx_remove(struct pci_dev *pdev)
 	pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
 
 	bgx_vnic[bgx->bgx_id] = NULL;
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
 	pci_set_drvdata(pdev, NULL);
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
index 3b7068832f95..4a0e2d2eb60a 100644
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -351,7 +351,7 @@ static void set_msglevel(struct net_device *dev, u32 val)
 	adapter->msg_enable = val;
 }
 
-static const char stats_strings[][ETH_GSTRING_LEN] = {
+static const char stats_strings[][ETH_GSTRING_LEN] __nonstring_array = {
 	"TxOctetsOK",
 	"TxOctetsBad",
 	"TxUnicastFramesOK",
diff --git a/drivers/net/ethernet/chelsio/cxgb/pm3393.c b/drivers/net/ethernet/chelsio/cxgb/pm3393.c
index cbfa03d5663a..f3ada6e7cdc5 100644
--- a/drivers/net/ethernet/chelsio/cxgb/pm3393.c
+++ b/drivers/net/ethernet/chelsio/cxgb/pm3393.c
@@ -141,7 +141,7 @@ static int pm3393_interrupt_enable(struct cmac *cmac)
 	pmwrite(cmac, SUNI1x10GEXP_REG_GLOBAL_INTERRUPT_ENABLE,
 		0 /*SUNI1x10GEXP_BITMSK_TOP_INTE */ );
 
-	/* TERMINATOR - PL_INTERUPTS_EXT */
+	/* TERMINATOR - PL_INTERRUPTS_EXT */
 	pl_intr = readl(cmac->adapter->regs + A_PL_ENABLE);
 	pl_intr |= F_PL_INTR_EXT;
 	writel(pl_intr, cmac->adapter->regs + A_PL_ENABLE);
@@ -179,7 +179,7 @@ static int pm3393_interrupt_disable(struct cmac *cmac)
 	elmer &= ~ELMER0_GP_BIT1;
 	t1_tpi_write(cmac->adapter, A_ELMER0_INT_ENABLE, elmer);
 
-	/* TERMINATOR - PL_INTERUPTS_EXT */
+	/* TERMINATOR - PL_INTERRUPTS_EXT */
 	/* DO NOT DISABLE TERMINATOR's EXTERNAL INTERRUPTS. ANOTHER CHIP
 	 * COULD WANT THEM ENABLED. We disable PM3393 at the ELMER level.
 	 */
@@ -222,7 +222,7 @@ static int pm3393_interrupt_clear(struct cmac *cmac)
 	elmer |= ELMER0_GP_BIT1;
 	t1_tpi_write(cmac->adapter, A_ELMER0_INT_CAUSE, elmer);
 
-	/* TERMINATOR - PL_INTERUPTS_EXT
+	/* TERMINATOR - PL_INTERRUPTS_EXT
 	 */
 	pl_intr = readl(cmac->adapter->regs + A_PL_CAUSE);
 	pl_intr |= F_PL_INTR_EXT;
@@ -756,7 +756,7 @@ static int pm3393_mac_reset(adapter_t * adapter)
 
 		/* ??? If this fails, might be able to software reset the XAUI part
 		 *     and try to recover... thus saving us from doing another HW reset */
-		/* Has the XAUI MABC PLL circuitry stablized? */
+		/* Has the XAUI MABC PLL circuitry stabilized? */
 		is_xaui_mabc_pll_locked =
 		    (val & SUNI1x10GEXP_BITMSK_TOP_SXRA_EXPIRED);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c
index 861edff5ed89..5f354cf62cdd 100644
--- a/drivers/net/ethernet/chelsio/cxgb/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.c
@@ -1922,7 +1922,7 @@ send:
 static void sge_tx_reclaim_cb(struct timer_list *t)
 {
 	int i;
-	struct sge *sge = from_timer(sge, t, tx_reclaim_timer);
+	struct sge *sge = timer_container_of(sge, t, tx_reclaim_timer);
 
 	for (i = 0; i < SGE_CMDQ_N; ++i) {
 		struct cmdQ *q = &sge->cmdQ[i];
@@ -1984,9 +1984,9 @@ void t1_sge_stop(struct sge *sge)
 	readl(sge->adapter->regs + A_SG_CONTROL); /* flush */
 
 	if (is_T2(sge->adapter))
-		del_timer_sync(&sge->espibug_timer);
+		timer_delete_sync(&sge->espibug_timer);
 
-	del_timer_sync(&sge->tx_reclaim_timer);
+	timer_delete_sync(&sge->tx_reclaim_timer);
 	if (sge->tx_sched)
 		tx_sched_stop(sge);
 
@@ -2017,7 +2017,7 @@ void t1_sge_start(struct sge *sge)
  */
 static void espibug_workaround_t204(struct timer_list *t)
 {
-	struct sge *sge = from_timer(sge, t, espibug_timer);
+	struct sge *sge = timer_container_of(sge, t, espibug_timer);
 	struct adapter *adapter = sge->adapter;
 	unsigned int nports = adapter->params.nports;
 	u32 seop[MAX_NPORTS];
@@ -2060,7 +2060,7 @@ static void espibug_workaround_t204(struct timer_list *t)
 
 static void espibug_workaround(struct timer_list *t)
 {
-	struct sge *sge = from_timer(sge, t, espibug_timer);
+	struct sge *sge = timer_container_of(sge, t, espibug_timer);
 	struct adapter *adapter = sge->adapter;
 
 	if (netif_running(adapter->port[0].dev)) {
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index f92a3550e480..3b1321c8ed14 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -2933,7 +2933,6 @@ static int t3_reenable_adapter(struct adapter *adapter)
 	}
 	pci_set_master(adapter->pdev);
 	pci_restore_state(adapter->pdev);
-	pci_save_state(adapter->pdev);
 
 	/* Free sge resources */
 	t3_free_sge_resources(adapter);
diff --git a/drivers/net/ethernet/chelsio/cxgb3/l2t.c b/drivers/net/ethernet/chelsio/cxgb3/l2t.c
index 9749d1239f58..5d5f3380ecca 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/l2t.c
@@ -176,43 +176,6 @@ again:
 
 EXPORT_SYMBOL(t3_l2t_send_slow);
 
-void t3_l2t_send_event(struct t3cdev *dev, struct l2t_entry *e)
-{
-again:
-	switch (e->state) {
-	case L2T_STATE_STALE:	/* entry is stale, kick off revalidation */
-		neigh_event_send(e->neigh, NULL);
-		spin_lock_bh(&e->lock);
-		if (e->state == L2T_STATE_STALE) {
-			e->state = L2T_STATE_VALID;
-		}
-		spin_unlock_bh(&e->lock);
-		return;
-	case L2T_STATE_VALID:	/* fast-path, send the packet on */
-		return;
-	case L2T_STATE_RESOLVING:
-		spin_lock_bh(&e->lock);
-		if (e->state != L2T_STATE_RESOLVING) {
-			/* ARP already completed */
-			spin_unlock_bh(&e->lock);
-			goto again;
-		}
-		spin_unlock_bh(&e->lock);
-
-		/*
-		 * Only the first packet added to the arpq should kick off
-		 * resolution.  However, because the alloc_skb below can fail,
-		 * we allow each packet added to the arpq to retry resolution
-		 * as a way of recovering from transient memory exhaustion.
-		 * A better way would be to use a work request to retry L2T
-		 * entries when there's no memory.
-		 */
-		neigh_event_send(e->neigh, NULL);
-	}
-}
-
-EXPORT_SYMBOL(t3_l2t_send_event);
-
 /*
  * Allocate a free L2T entry.  Must be called with l2t_data.lock held.
  */
diff --git a/drivers/net/ethernet/chelsio/cxgb3/l2t.h b/drivers/net/ethernet/chelsio/cxgb3/l2t.h
index 646ca0bc25bd..33558f177497 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/l2t.h
+++ b/drivers/net/ethernet/chelsio/cxgb3/l2t.h
@@ -113,7 +113,6 @@ struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct dst_entry *dst,
 			     struct net_device *dev, const void *daddr);
 int t3_l2t_send_slow(struct t3cdev *dev, struct sk_buff *skb,
 		     struct l2t_entry *e);
-void t3_l2t_send_event(struct t3cdev *dev, struct l2t_entry *e);
 struct l2t_data *t3_init_l2t(unsigned int l2t_capacity);
 
 int cxgb3_ofld_send(struct t3cdev *dev, struct sk_buff *skb);
diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index 6268f96cb4aa..b59735d0e065 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -2906,7 +2906,7 @@ void t3_sge_err_intr_handler(struct adapter *adapter)
  */
 static void sge_timer_tx(struct timer_list *t)
 {
-	struct sge_qset *qs = from_timer(qs, t, tx_reclaim_timer);
+	struct sge_qset *qs = timer_container_of(qs, t, tx_reclaim_timer);
 	struct port_info *pi = netdev_priv(qs->netdev);
 	struct adapter *adap = pi->adapter;
 	unsigned int tbd[SGE_TXQ_PER_SET] = {0, 0};
@@ -2947,7 +2947,7 @@ static void sge_timer_tx(struct timer_list *t)
 static void sge_timer_rx(struct timer_list *t)
 {
 	spinlock_t *lock;
-	struct sge_qset *qs = from_timer(qs, t, rx_reclaim_timer);
+	struct sge_qset *qs = timer_container_of(qs, t, rx_reclaim_timer);
 	struct port_info *pi = netdev_priv(qs->netdev);
 	struct adapter *adap = pi->adapter;
 	u32 status;
@@ -3223,9 +3223,9 @@ void t3_stop_sge_timers(struct adapter *adap)
 		struct sge_qset *q = &adap->sge.qs[i];
 
 		if (q->tx_reclaim_timer.function)
-			del_timer_sync(&q->tx_reclaim_timer);
+			timer_delete_sync(&q->tx_reclaim_timer);
 		if (q->rx_reclaim_timer.function)
-			del_timer_sync(&q->rx_reclaim_timer);
+			timer_delete_sync(&q->rx_reclaim_timer);
 	}
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index c7c2c15a1815..f20f4bc58492 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -674,7 +674,7 @@ struct port_info {
 	struct cxgb_fcoe fcoe;
 #endif /* CONFIG_CHELSIO_T4_FCOE */
 	bool rxtstamp;  /* Enable TS */
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 	bool ptp_enable;
 	struct sched_table *sched_tbl;
 	u32 eth_flags;
@@ -1211,9 +1211,6 @@ struct adapter {
 	struct timer_list flower_stats_timer;
 	struct work_struct flower_stats_work;
 
-	/* Ethtool Dump */
-	struct ethtool_dump eth_dump;
-
 	/* HMA */
 	struct hma_data hma;
 
@@ -1233,6 +1230,10 @@ struct adapter {
 
 	/* Ethtool n-tuple */
 	struct cxgb4_ethtool_filter *ethtool_filters;
+
+	/* Ethtool Dump */
+	/* Must be last - ends in a flex-array member. */
+	struct ethtool_dump eth_dump;
 };
 
 /* Support for "sched-class" command to allow a TX Scheduling Class to be
@@ -1315,7 +1316,7 @@ struct ch_sched_flowc {
  * (value, mask) tuples.  The associated ingress packet field matches the
  * tuple when ((field & mask) == value).  (Thus a wildcard "don't care" field
  * rule can be constructed by specifying a tuple of (0, 0).)  A filter rule
- * matches an ingress packet when all of the individual individual field
+ * matches an ingress packet when all of the individual field
  * matching rules are true.
  *
  * Partial field masks are always valid, however, while it may be easy to
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 7f3f5afa864f..23326235d4ab 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -1730,6 +1730,60 @@ static int cxgb4_ntuple_get_filter(struct net_device *dev,
 	return 0;
 }
 
+static int cxgb4_get_rxfh_fields(struct net_device *dev,
+				 struct ethtool_rxfh_fields *info)
+{
+	const struct port_info *pi = netdev_priv(dev);
+	unsigned int v = pi->rss_mode;
+
+	info->data = 0;
+	switch (info->flow_type) {
+	case TCP_V4_FLOW:
+		if (v & FW_RSS_VI_CONFIG_CMD_IP4FOURTUPEN_F)
+			info->data = RXH_IP_SRC | RXH_IP_DST |
+				RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		else if (v & FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F)
+			info->data = RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case UDP_V4_FLOW:
+		if ((v & FW_RSS_VI_CONFIG_CMD_IP4FOURTUPEN_F) &&
+		    (v & FW_RSS_VI_CONFIG_CMD_UDPEN_F))
+			info->data = RXH_IP_SRC | RXH_IP_DST |
+				RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		else if (v & FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F)
+			info->data = RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case SCTP_V4_FLOW:
+	case AH_ESP_V4_FLOW:
+	case IPV4_FLOW:
+		if (v & FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F)
+			info->data = RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case TCP_V6_FLOW:
+		if (v & FW_RSS_VI_CONFIG_CMD_IP6FOURTUPEN_F)
+			info->data = RXH_IP_SRC | RXH_IP_DST |
+				RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		else if (v & FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F)
+			info->data = RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case UDP_V6_FLOW:
+		if ((v & FW_RSS_VI_CONFIG_CMD_IP6FOURTUPEN_F) &&
+		    (v & FW_RSS_VI_CONFIG_CMD_UDPEN_F))
+			info->data = RXH_IP_SRC | RXH_IP_DST |
+				RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		else if (v & FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F)
+			info->data = RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case SCTP_V6_FLOW:
+	case AH_ESP_V6_FLOW:
+	case IPV6_FLOW:
+		if (v & FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F)
+			info->data = RXH_IP_SRC | RXH_IP_DST;
+		break;
+	}
+	return 0;
+}
+
 static int get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
 		     u32 *rules)
 {
@@ -1739,56 +1793,6 @@ static int get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
 	int ret = 0;
 
 	switch (info->cmd) {
-	case ETHTOOL_GRXFH: {
-		unsigned int v = pi->rss_mode;
-
-		info->data = 0;
-		switch (info->flow_type) {
-		case TCP_V4_FLOW:
-			if (v & FW_RSS_VI_CONFIG_CMD_IP4FOURTUPEN_F)
-				info->data = RXH_IP_SRC | RXH_IP_DST |
-					     RXH_L4_B_0_1 | RXH_L4_B_2_3;
-			else if (v & FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F)
-				info->data = RXH_IP_SRC | RXH_IP_DST;
-			break;
-		case UDP_V4_FLOW:
-			if ((v & FW_RSS_VI_CONFIG_CMD_IP4FOURTUPEN_F) &&
-			    (v & FW_RSS_VI_CONFIG_CMD_UDPEN_F))
-				info->data = RXH_IP_SRC | RXH_IP_DST |
-					     RXH_L4_B_0_1 | RXH_L4_B_2_3;
-			else if (v & FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F)
-				info->data = RXH_IP_SRC | RXH_IP_DST;
-			break;
-		case SCTP_V4_FLOW:
-		case AH_ESP_V4_FLOW:
-		case IPV4_FLOW:
-			if (v & FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F)
-				info->data = RXH_IP_SRC | RXH_IP_DST;
-			break;
-		case TCP_V6_FLOW:
-			if (v & FW_RSS_VI_CONFIG_CMD_IP6FOURTUPEN_F)
-				info->data = RXH_IP_SRC | RXH_IP_DST |
-					     RXH_L4_B_0_1 | RXH_L4_B_2_3;
-			else if (v & FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F)
-				info->data = RXH_IP_SRC | RXH_IP_DST;
-			break;
-		case UDP_V6_FLOW:
-			if ((v & FW_RSS_VI_CONFIG_CMD_IP6FOURTUPEN_F) &&
-			    (v & FW_RSS_VI_CONFIG_CMD_UDPEN_F))
-				info->data = RXH_IP_SRC | RXH_IP_DST |
-					     RXH_L4_B_0_1 | RXH_L4_B_2_3;
-			else if (v & FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F)
-				info->data = RXH_IP_SRC | RXH_IP_DST;
-			break;
-		case SCTP_V6_FLOW:
-		case AH_ESP_V6_FLOW:
-		case IPV6_FLOW:
-			if (v & FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F)
-				info->data = RXH_IP_SRC | RXH_IP_DST;
-			break;
-		}
-		return 0;
-	}
 	case ETHTOOL_GRXRINGS:
 		info->data = pi->nqsets;
 		return 0;
@@ -2199,6 +2203,7 @@ static const struct ethtool_ops cxgb_ethtool_ops = {
 	.get_rxfh_indir_size = get_rss_table_size,
 	.get_rxfh	   = get_rss_table,
 	.set_rxfh	   = set_rss_table,
+	.get_rxfh_fields   = cxgb4_get_rxfh_fields,
 	.self_test	   = cxgb4_self_test,
 	.flash_device      = set_flash,
 	.get_ts_info       = get_ts_info,
@@ -2270,6 +2275,7 @@ int cxgb4_init_ethtool_filters(struct adapter *adap)
 		eth_filter->port[i].bmap = bitmap_zalloc(nentries, GFP_KERNEL);
 		if (!eth_filter->port[i].bmap) {
 			ret = -ENOMEM;
+			kvfree(eth_filter->port[i].loc_array);
 			goto free_eth_finfo;
 		}
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index bc3af0054406..043733c5c812 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -1799,7 +1799,10 @@ void cxgb4_remove_tid(struct tid_info *t, unsigned int chan, unsigned int tid,
 	struct adapter *adap = container_of(t, struct adapter, tids);
 	struct sk_buff *skb;
 
-	WARN_ON(tid_out_of_range(&adap->tids, tid));
+	if (tid_out_of_range(&adap->tids, tid)) {
+		dev_err(adap->pdev_dev, "tid %d out of range\n", tid);
+		return;
+	}
 
 	if (t->tid_tab[tid - adap->tids.tid_base]) {
 		t->tid_tab[tid - adap->tids.tid_base] = NULL;
@@ -3039,12 +3042,87 @@ static void cxgb_get_stats(struct net_device *dev,
 		ns->rx_length_errors + stats.rx_len_err + ns->rx_fifo_errors;
 }
 
+static int cxgb_hwtstamp_get(struct net_device *dev,
+			     struct kernel_hwtstamp_config *config)
+{
+	struct port_info *pi = netdev_priv(dev);
+
+	*config = pi->tstamp_config;
+	return 0;
+}
+
+static int cxgb_hwtstamp_set(struct net_device *dev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
+{
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
+
+	if (is_t4(adapter->params.chip)) {
+		/* For T4 Adapters */
+		switch (config->rx_filter) {
+		case HWTSTAMP_FILTER_NONE:
+			pi->rxtstamp = false;
+			break;
+		case HWTSTAMP_FILTER_ALL:
+			pi->rxtstamp = true;
+			break;
+		default:
+			return -ERANGE;
+		}
+		pi->tstamp_config = *config;
+		return 0;
+	}
+
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+	case HWTSTAMP_TX_ON:
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	switch (config->rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		pi->rxtstamp = false;
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+		cxgb4_ptprx_timestamping(pi, pi->port_id, PTP_TS_L4);
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+		cxgb4_ptprx_timestamping(pi, pi->port_id, PTP_TS_L2_L4);
+		break;
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+		pi->rxtstamp = true;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	if (config->tx_type == HWTSTAMP_TX_OFF &&
+	    config->rx_filter == HWTSTAMP_FILTER_NONE) {
+		if (cxgb4_ptp_txtype(adapter, pi->port_id) >= 0)
+			pi->ptp_enable = false;
+	}
+
+	if (config->rx_filter != HWTSTAMP_FILTER_NONE) {
+		if (cxgb4_ptp_redirect_rx_packet(adapter, pi) >= 0)
+			pi->ptp_enable = true;
+	}
+	pi->tstamp_config = *config;
+	return 0;
+}
+
 static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
 {
 	unsigned int mbox;
 	int ret = 0, prtad, devad;
 	struct port_info *pi = netdev_priv(dev);
-	struct adapter *adapter = pi->adapter;
 	struct mii_ioctl_data *data = (struct mii_ioctl_data *)&req->ifr_data;
 
 	switch (cmd) {
@@ -3073,81 +3151,6 @@ static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
 			ret = t4_mdio_wr(pi->adapter, mbox, prtad, devad,
 					 data->reg_num, data->val_in);
 		break;
-	case SIOCGHWTSTAMP:
-		return copy_to_user(req->ifr_data, &pi->tstamp_config,
-				    sizeof(pi->tstamp_config)) ?
-			-EFAULT : 0;
-	case SIOCSHWTSTAMP:
-		if (copy_from_user(&pi->tstamp_config, req->ifr_data,
-				   sizeof(pi->tstamp_config)))
-			return -EFAULT;
-
-		if (!is_t4(adapter->params.chip)) {
-			switch (pi->tstamp_config.tx_type) {
-			case HWTSTAMP_TX_OFF:
-			case HWTSTAMP_TX_ON:
-				break;
-			default:
-				return -ERANGE;
-			}
-
-			switch (pi->tstamp_config.rx_filter) {
-			case HWTSTAMP_FILTER_NONE:
-				pi->rxtstamp = false;
-				break;
-			case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
-			case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
-				cxgb4_ptprx_timestamping(pi, pi->port_id,
-							 PTP_TS_L4);
-				break;
-			case HWTSTAMP_FILTER_PTP_V2_EVENT:
-				cxgb4_ptprx_timestamping(pi, pi->port_id,
-							 PTP_TS_L2_L4);
-				break;
-			case HWTSTAMP_FILTER_ALL:
-			case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
-			case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-			case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
-			case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
-				pi->rxtstamp = true;
-				break;
-			default:
-				pi->tstamp_config.rx_filter =
-					HWTSTAMP_FILTER_NONE;
-				return -ERANGE;
-			}
-
-			if ((pi->tstamp_config.tx_type == HWTSTAMP_TX_OFF) &&
-			    (pi->tstamp_config.rx_filter ==
-				HWTSTAMP_FILTER_NONE)) {
-				if (cxgb4_ptp_txtype(adapter, pi->port_id) >= 0)
-					pi->ptp_enable = false;
-			}
-
-			if (pi->tstamp_config.rx_filter !=
-				HWTSTAMP_FILTER_NONE) {
-				if (cxgb4_ptp_redirect_rx_packet(adapter,
-								 pi) >= 0)
-					pi->ptp_enable = true;
-			}
-		} else {
-			/* For T4 Adapters */
-			switch (pi->tstamp_config.rx_filter) {
-			case HWTSTAMP_FILTER_NONE:
-			pi->rxtstamp = false;
-			break;
-			case HWTSTAMP_FILTER_ALL:
-			pi->rxtstamp = true;
-			break;
-			default:
-			pi->tstamp_config.rx_filter =
-			HWTSTAMP_FILTER_NONE;
-			return -ERANGE;
-			}
-		}
-		return copy_to_user(req->ifr_data, &pi->tstamp_config,
-				    sizeof(pi->tstamp_config)) ?
-			-EFAULT : 0;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -3294,7 +3297,7 @@ static int cxgb4_mgmt_set_vf_rate(struct net_device *dev, int vf,
 	}
 
 	if (max_tx_rate == 0) {
-		/* unbind VF to to any Traffic Class */
+		/* unbind VF to any Traffic Class */
 		fw_pfvf =
 		    (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_PFVF) |
 		     FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_PFVF_SCHEDCLASS_ETH));
@@ -3482,7 +3485,7 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 	struct adapter *adap = pi->adapter;
 	struct ch_sched_queue qe = { 0 };
 	struct ch_sched_params p = { 0 };
-	struct sched_class *e;
+	struct ch_sched_class *e;
 	u32 req_rate;
 	int err = 0;
 
@@ -3872,6 +3875,8 @@ static const struct net_device_ops cxgb4_netdev_ops = {
 	.ndo_setup_tc         = cxgb_setup_tc,
 	.ndo_features_check   = cxgb_features_check,
 	.ndo_fix_features     = cxgb_fix_features,
+	.ndo_hwtstamp_get     = cxgb_hwtstamp_get,
+	.ndo_hwtstamp_set     = cxgb_hwtstamp_set,
 };
 
 #ifdef CONFIG_PCI_IOV
@@ -4813,7 +4818,7 @@ static int adap_init0(struct adapter *adap, int vpd_skip)
 			goto bye;
 		}
 
-		/* Get FW from from /lib/firmware/ */
+		/* Get FW from /lib/firmware/ */
 		ret = request_firmware(&fw, fw_info->fw_mod_name,
 				       adap->pdev_dev);
 		if (ret < 0) {
@@ -5453,7 +5458,6 @@ static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev)
 
 	if (!adap) {
 		pci_restore_state(pdev);
-		pci_save_state(pdev);
 		return PCI_ERS_RESULT_RECOVERED;
 	}
 
@@ -5468,7 +5472,6 @@ static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev)
 
 	pci_set_master(pdev);
 	pci_restore_state(pdev);
-	pci_save_state(pdev);
 
 	if (t4_wait_dev_ready(adap->regs) < 0)
 		return PCI_ERS_RESULT_DISCONNECT;
@@ -6477,10 +6480,11 @@ static const struct tlsdev_ops cxgb4_ktls_ops = {
 
 #if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE)
 
-static int cxgb4_xfrm_add_state(struct xfrm_state *x,
+static int cxgb4_xfrm_add_state(struct net_device *dev,
+				struct xfrm_state *x,
 				struct netlink_ext_ack *extack)
 {
-	struct adapter *adap = netdev2adap(x->xso.dev);
+	struct adapter *adap = netdev2adap(dev);
 	int ret;
 
 	if (!mutex_trylock(&uld_mutex)) {
@@ -6491,7 +6495,8 @@ static int cxgb4_xfrm_add_state(struct xfrm_state *x,
 	if (ret)
 		goto out_unlock;
 
-	ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_add(x, extack);
+	ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_add(dev, x,
+									extack);
 
 out_unlock:
 	mutex_unlock(&uld_mutex);
@@ -6499,9 +6504,9 @@ out_unlock:
 	return ret;
 }
 
-static void cxgb4_xfrm_del_state(struct xfrm_state *x)
+static void cxgb4_xfrm_del_state(struct net_device *dev, struct xfrm_state *x)
 {
-	struct adapter *adap = netdev2adap(x->xso.dev);
+	struct adapter *adap = netdev2adap(dev);
 
 	if (!mutex_trylock(&uld_mutex)) {
 		dev_dbg(adap->pdev_dev,
@@ -6511,15 +6516,15 @@ static void cxgb4_xfrm_del_state(struct xfrm_state *x)
 	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
 		goto out_unlock;
 
-	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_delete(x);
+	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_delete(dev, x);
 
 out_unlock:
 	mutex_unlock(&uld_mutex);
 }
 
-static void cxgb4_xfrm_free_state(struct xfrm_state *x)
+static void cxgb4_xfrm_free_state(struct net_device *dev, struct xfrm_state *x)
 {
-	struct adapter *adap = netdev2adap(x->xso.dev);
+	struct adapter *adap = netdev2adap(dev);
 
 	if (!mutex_trylock(&uld_mutex)) {
 		dev_dbg(adap->pdev_dev,
@@ -6529,36 +6534,19 @@ static void cxgb4_xfrm_free_state(struct xfrm_state *x)
 	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
 		goto out_unlock;
 
-	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_free(x);
-
-out_unlock:
-	mutex_unlock(&uld_mutex);
-}
-
-static bool cxgb4_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
-{
-	struct adapter *adap = netdev2adap(x->xso.dev);
-	bool ret = false;
-
-	if (!mutex_trylock(&uld_mutex)) {
-		dev_dbg(adap->pdev_dev,
-			"crypto uld critical resource is under use\n");
-		return ret;
-	}
-	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
-		goto out_unlock;
-
-	ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_offload_ok(skb, x);
+	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_free(dev, x);
 
 out_unlock:
 	mutex_unlock(&uld_mutex);
-	return ret;
 }
 
 static void cxgb4_advance_esn_state(struct xfrm_state *x)
 {
 	struct adapter *adap = netdev2adap(x->xso.dev);
 
+	if (x->xso.dir != XFRM_DEV_OFFLOAD_IN)
+		return;
+
 	if (!mutex_trylock(&uld_mutex)) {
 		dev_dbg(adap->pdev_dev,
 			"crypto uld critical resource is under use\n");
@@ -6577,7 +6565,6 @@ static const struct xfrmdev_ops cxgb4_xfrmdev_ops = {
 	.xdo_dev_state_add      = cxgb4_xfrm_add_state,
 	.xdo_dev_state_delete   = cxgb4_xfrm_del_state,
 	.xdo_dev_state_free     = cxgb4_xfrm_free_state,
-	.xdo_dev_offload_ok     = cxgb4_ipsec_offload_ok,
 	.xdo_dev_state_advance_esn = cxgb4_advance_esn_state,
 };
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index 69d045d769c4..e2b5554531b5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -161,20 +161,9 @@ static struct ch_tc_flower_entry *ch_flower_lookup(struct adapter *adap,
 
 static void cxgb4_process_flow_match(struct net_device *dev,
 				     struct flow_rule *rule,
+				     u16 addr_type,
 				     struct ch_filter_specification *fs)
 {
-	u16 addr_type = 0;
-
-	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_match_control match;
-
-		flow_rule_match_control(rule, &match);
-		addr_type = match.key->addr_type;
-	} else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
-		addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
-	} else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
-		addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
-	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
 		struct flow_match_basic match;
@@ -327,9 +316,6 @@ static int cxgb4_validate_flow_match(struct netlink_ext_ack *extack,
 		return -EOPNOTSUPP;
 	}
 
-	if (flow_rule_match_has_control_flags(rule, extack))
-		return -EOPNOTSUPP;
-
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
 		struct flow_match_basic match;
 
@@ -858,6 +844,7 @@ int cxgb4_flow_rule_replace(struct net_device *dev, struct flow_rule *rule,
 {
 	struct adapter *adap = netdev2adap(dev);
 	struct filter_ctx ctx;
+	u16 addr_type = 0;
 	u8 inet_family;
 	int fidx, ret;
 
@@ -867,7 +854,28 @@ int cxgb4_flow_rule_replace(struct net_device *dev, struct flow_rule *rule,
 	if (cxgb4_validate_flow_match(extack, rule))
 		return -EOPNOTSUPP;
 
-	cxgb4_process_flow_match(dev, rule, fs);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
+
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
+
+		if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) {
+			fs->val.frag = match.key->flags & FLOW_DIS_IS_FRAGMENT;
+			fs->mask.frag = true;
+		}
+
+		if (!flow_rule_is_supp_control_flags(FLOW_DIS_IS_FRAGMENT,
+						     match.mask->flags, extack))
+			return -EOPNOTSUPP;
+
+	} else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+	} else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+	}
+
+	cxgb4_process_flow_match(dev, rule, addr_type, fs);
 	cxgb4_process_flow_actions(dev, &rule->action, fs);
 
 	fs->hash = is_filter_exact_match(adap, fs);
@@ -1051,7 +1059,7 @@ static void ch_flower_stats_handler(struct work_struct *work)
 
 static void ch_flower_stats_cb(struct timer_list *t)
 {
-	struct adapter *adap = from_timer(adap, t, flower_stats_timer);
+	struct adapter *adap = timer_container_of(adap, t, flower_stats_timer);
 
 	schedule_work(&adap->flower_stats_work);
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c
index 1672d3afe5be..f8dcf0b4abcd 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c
@@ -56,7 +56,7 @@ static int cxgb4_matchall_egress_validate(struct net_device *dev,
 	struct port_info *pi = netdev2pinfo(dev);
 	struct flow_action_entry *entry;
 	struct ch_sched_queue qe;
-	struct sched_class *e;
+	struct ch_sched_class *e;
 	u64 max_link_rate;
 	u32 i, speed;
 	int ret;
@@ -180,7 +180,7 @@ static int cxgb4_matchall_alloc_tc(struct net_device *dev,
 	struct port_info *pi = netdev2pinfo(dev);
 	struct adapter *adap = netdev2adap(dev);
 	struct flow_action_entry *entry;
-	struct sched_class *e;
+	struct ch_sched_class *e;
 	int ret;
 	u32 i;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
index 338b04f339b3..a2dcd2e24263 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
@@ -330,7 +330,7 @@ static int cxgb4_mqprio_alloc_tc(struct net_device *dev,
 	struct cxgb4_tc_port_mqprio *tc_port_mqprio;
 	struct port_info *pi = netdev2pinfo(dev);
 	struct adapter *adap = netdev2adap(dev);
-	struct sched_class *e;
+	struct ch_sched_class *e;
 	int ret;
 	u8 i;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
index a5d2f84dcdd5..8524246fd67e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
@@ -186,7 +186,7 @@ int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls)
 	link_uhtid = TC_U32_USERHTID(cls->knode.link_handle);
 
 	/* Ensure that uhtid is either root u32 (i.e. 0x800)
-	 * or a a valid linked bucket.
+	 * or a valid linked bucket.
 	 */
 	if (uhtid != 0x800 && uhtid >= t->size)
 		return -EINVAL;
@@ -422,7 +422,7 @@ int cxgb4_delete_knode(struct net_device *dev, struct tc_cls_u32_offload *cls)
 	uhtid = TC_U32_USERHTID(cls->knode.handle);
 
 	/* Ensure that uhtid is either root u32 (i.e. 0x800)
-	 * or a a valid linked bucket.
+	 * or a valid linked bucket.
 	 */
 	if (uhtid != 0x800 && uhtid >= t->size)
 		return -EINVAL;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c
index b08356060fb4..7bab8da8f6e6 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c
@@ -29,7 +29,7 @@ static int cxgb4_thermal_get_temp(struct thermal_zone_device *tzdev,
 	return 0;
 }
 
-static struct thermal_zone_device_ops cxgb4_thermal_ops = {
+static const struct thermal_zone_device_ops cxgb4_thermal_ops = {
 	.get_temp = cxgb4_thermal_get_temp,
 };
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c
index a1b14468d1ff..38a30aeee122 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sched.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c
@@ -44,7 +44,7 @@ static int t4_sched_class_fw_cmd(struct port_info *pi,
 {
 	struct adapter *adap = pi->adapter;
 	struct sched_table *s = pi->sched_tbl;
-	struct sched_class *e;
+	struct ch_sched_class *e;
 	int err = 0;
 
 	e = &s->tab[p->u.params.class];
@@ -122,7 +122,7 @@ static void *t4_sched_entry_lookup(struct port_info *pi,
 				   const u32 val)
 {
 	struct sched_table *s = pi->sched_tbl;
-	struct sched_class *e, *end;
+	struct ch_sched_class *e, *end;
 	void *found = NULL;
 
 	/* Look for an entry with matching @val */
@@ -166,8 +166,8 @@ static void *t4_sched_entry_lookup(struct port_info *pi,
 	return found;
 }
 
-struct sched_class *cxgb4_sched_queue_lookup(struct net_device *dev,
-					     struct ch_sched_queue *p)
+struct ch_sched_class *cxgb4_sched_queue_lookup(struct net_device *dev,
+						struct ch_sched_queue *p)
 {
 	struct port_info *pi = netdev2pinfo(dev);
 	struct sched_queue_entry *qe = NULL;
@@ -187,7 +187,7 @@ static int t4_sched_queue_unbind(struct port_info *pi, struct ch_sched_queue *p)
 	struct sched_queue_entry *qe = NULL;
 	struct adapter *adap = pi->adapter;
 	struct sge_eth_txq *txq;
-	struct sched_class *e;
+	struct ch_sched_class *e;
 	int err = 0;
 
 	if (p->queue < 0 || p->queue >= pi->nqsets)
@@ -218,7 +218,7 @@ static int t4_sched_queue_bind(struct port_info *pi, struct ch_sched_queue *p)
 	struct sched_queue_entry *qe = NULL;
 	struct adapter *adap = pi->adapter;
 	struct sge_eth_txq *txq;
-	struct sched_class *e;
+	struct ch_sched_class *e;
 	unsigned int qid;
 	int err = 0;
 
@@ -260,7 +260,7 @@ static int t4_sched_flowc_unbind(struct port_info *pi, struct ch_sched_flowc *p)
 {
 	struct sched_flowc_entry *fe = NULL;
 	struct adapter *adap = pi->adapter;
-	struct sched_class *e;
+	struct ch_sched_class *e;
 	int err = 0;
 
 	if (p->tid < 0 || p->tid >= adap->tids.neotids)
@@ -288,7 +288,7 @@ static int t4_sched_flowc_bind(struct port_info *pi, struct ch_sched_flowc *p)
 	struct sched_table *s = pi->sched_tbl;
 	struct sched_flowc_entry *fe = NULL;
 	struct adapter *adap = pi->adapter;
-	struct sched_class *e;
+	struct ch_sched_class *e;
 	int err = 0;
 
 	if (p->tid < 0 || p->tid >= adap->tids.neotids)
@@ -322,7 +322,7 @@ out_err:
 }
 
 static void t4_sched_class_unbind_all(struct port_info *pi,
-				      struct sched_class *e,
+				      struct ch_sched_class *e,
 				      enum sched_bind_type type)
 {
 	if (!e)
@@ -476,12 +476,12 @@ int cxgb4_sched_class_unbind(struct net_device *dev, void *arg,
 }
 
 /* If @p is NULL, fetch any available unused class */
-static struct sched_class *t4_sched_class_lookup(struct port_info *pi,
-						const struct ch_sched_params *p)
+static struct ch_sched_class *t4_sched_class_lookup(struct port_info *pi,
+						    const struct ch_sched_params *p)
 {
 	struct sched_table *s = pi->sched_tbl;
-	struct sched_class *found = NULL;
-	struct sched_class *e, *end;
+	struct ch_sched_class *found = NULL;
+	struct ch_sched_class *e, *end;
 
 	if (!p) {
 		/* Get any available unused class */
@@ -522,10 +522,10 @@ static struct sched_class *t4_sched_class_lookup(struct port_info *pi,
 	return found;
 }
 
-static struct sched_class *t4_sched_class_alloc(struct port_info *pi,
-						struct ch_sched_params *p)
+static struct ch_sched_class *t4_sched_class_alloc(struct port_info *pi,
+						   struct ch_sched_params *p)
 {
-	struct sched_class *e = NULL;
+	struct ch_sched_class *e = NULL;
 	u8 class_id;
 	int err;
 
@@ -579,8 +579,8 @@ static struct sched_class *t4_sched_class_alloc(struct port_info *pi,
  * scheduling class with matching @p is found, then the matching class is
  * returned.
  */
-struct sched_class *cxgb4_sched_class_alloc(struct net_device *dev,
-					    struct ch_sched_params *p)
+struct ch_sched_class *cxgb4_sched_class_alloc(struct net_device *dev,
+					       struct ch_sched_params *p)
 {
 	struct port_info *pi = netdev2pinfo(dev);
 	u8 class_id;
@@ -607,7 +607,7 @@ void cxgb4_sched_class_free(struct net_device *dev, u8 classid)
 	struct port_info *pi = netdev2pinfo(dev);
 	struct sched_table *s = pi->sched_tbl;
 	struct ch_sched_params p;
-	struct sched_class *e;
+	struct ch_sched_class *e;
 	u32 speed;
 	int ret;
 
@@ -640,7 +640,7 @@ void cxgb4_sched_class_free(struct net_device *dev, u8 classid)
 	}
 }
 
-static void t4_sched_class_free(struct net_device *dev, struct sched_class *e)
+static void t4_sched_class_free(struct net_device *dev, struct ch_sched_class *e)
 {
 	struct port_info *pi = netdev2pinfo(dev);
 
@@ -660,7 +660,7 @@ struct sched_table *t4_init_sched(unsigned int sched_size)
 	s->sched_size = sched_size;
 
 	for (i = 0; i < s->sched_size; i++) {
-		memset(&s->tab[i], 0, sizeof(struct sched_class));
+		memset(&s->tab[i], 0, sizeof(struct ch_sched_class));
 		s->tab[i].idx = i;
 		s->tab[i].state = SCHED_STATE_UNUSED;
 		INIT_LIST_HEAD(&s->tab[i].entry_list);
@@ -682,7 +682,7 @@ void t4_cleanup_sched(struct adapter *adap)
 			continue;
 
 		for (i = 0; i < s->sched_size; i++) {
-			struct sched_class *e;
+			struct ch_sched_class *e;
 
 			e = &s->tab[i];
 			if (e->state == SCHED_STATE_ACTIVE)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.h b/drivers/net/ethernet/chelsio/cxgb4/sched.h
index 6b3c778815f0..4d3b5a757536 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sched.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/sched.h
@@ -71,7 +71,7 @@ struct sched_flowc_entry {
 	struct ch_sched_flowc param;
 };
 
-struct sched_class {
+struct ch_sched_class {
 	u8 state;
 	u8 idx;
 	struct ch_sched_params info;
@@ -82,7 +82,7 @@ struct sched_class {
 
 struct sched_table {      /* per port scheduling table */
 	u8 sched_size;
-	struct sched_class tab[] __counted_by(sched_size);
+	struct ch_sched_class tab[] __counted_by(sched_size);
 };
 
 static inline bool can_sched(struct net_device *dev)
@@ -103,15 +103,15 @@ static inline bool valid_class_id(struct net_device *dev, u8 class_id)
 	return true;
 }
 
-struct sched_class *cxgb4_sched_queue_lookup(struct net_device *dev,
-					     struct ch_sched_queue *p);
+struct ch_sched_class *cxgb4_sched_queue_lookup(struct net_device *dev,
+						struct ch_sched_queue *p);
 int cxgb4_sched_class_bind(struct net_device *dev, void *arg,
 			   enum sched_bind_type type);
 int cxgb4_sched_class_unbind(struct net_device *dev, void *arg,
 			     enum sched_bind_type type);
 
-struct sched_class *cxgb4_sched_class_alloc(struct net_device *dev,
-					    struct ch_sched_params *p);
+struct ch_sched_class *cxgb4_sched_class_alloc(struct net_device *dev,
+					       struct ch_sched_params *p);
 void cxgb4_sched_class_free(struct net_device *dev, u8 classid);
 
 struct sched_table *t4_init_sched(unsigned int size);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index a7d76a8ed050..9fccb8ea9bcd 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -163,7 +163,7 @@ static inline unsigned int fl_mtu_bufsize(struct adapter *adapter,
  * for DMA, but this is of course never sent to the hardware and is only used
  * to prevent double unmappings.  All of the above requires that the Free List
  * Buffers which we allocate have the bottom 5 bits free (0) -- i.e. are
- * 32-byte or or a power of 2 greater in alignment.  Since the SGE's minimal
+ * 32-byte or a power of 2 greater in alignment.  Since the SGE's minimal
  * Free List Buffer alignment is 32 bytes, this works out for us ...
  */
 enum {
@@ -1533,7 +1533,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else {
 		q = &adap->sge.ethtxq[qidx + pi->first_qset];
 	}
-	skb_tx_timestamp(skb);
 
 	reclaim_completed_tx(adap, &q->q, -1, true);
 	cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
@@ -1706,6 +1705,8 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	cpl->len = htons(skb->len);
 	cpl->ctrl1 = cpu_to_be64(cntrl);
 
+	skb_tx_timestamp(skb);
+
 	if (immediate) {
 		cxgb4_inline_tx_skb(skb, &q->q, sgl);
 		dev_consume_skb_any(skb);
@@ -2268,7 +2269,6 @@ static int ethofld_hard_xmit(struct net_device *dev,
 
 	d = &eosw_txq->desc[eosw_txq->last_pidx];
 	skb = d->skb;
-	skb_tx_timestamp(skb);
 
 	wr = (struct fw_eth_tx_eo_wr *)&eohw_txq->q.desc[eohw_txq->q.pidx];
 	if (unlikely(eosw_txq->state != CXGB4_EO_STATE_ACTIVE &&
@@ -2373,6 +2373,7 @@ write_wr_headers:
 		eohw_txq->vlan_ins++;
 
 	txq_advance(&eohw_txq->q, ndesc);
+	skb_tx_timestamp(skb);
 	cxgb4_ring_tx_db(adap, &eohw_txq->q, ndesc);
 	eosw_txq_advance_index(&eosw_txq->last_pidx, 1, eosw_txq->ndesc);
 
@@ -4233,7 +4234,7 @@ static void sge_rx_timer_cb(struct timer_list *t)
 {
 	unsigned long m;
 	unsigned int i;
-	struct adapter *adap = from_timer(adap, t, sge.rx_timer);
+	struct adapter *adap = timer_container_of(adap, t, sge.rx_timer);
 	struct sge *s = &adap->sge;
 
 	for (i = 0; i < BITS_TO_LONGS(s->egr_sz); i++)
@@ -4268,7 +4269,7 @@ done:
 
 static void sge_tx_timer_cb(struct timer_list *t)
 {
-	struct adapter *adap = from_timer(adap, t, sge.tx_timer);
+	struct adapter *adap = timer_container_of(adap, t, sge.tx_timer);
 	struct sge *s = &adap->sge;
 	unsigned long m, period;
 	unsigned int i, budget;
@@ -4996,9 +4997,9 @@ void t4_sge_stop(struct adapter *adap)
 	struct sge *s = &adap->sge;
 
 	if (s->rx_timer.function)
-		del_timer_sync(&s->rx_timer);
+		timer_delete_sync(&s->rx_timer);
 	if (s->tx_timer.function)
-		del_timer_sync(&s->tx_timer);
+		timer_delete_sync(&s->tx_timer);
 
 	if (is_offload(adap)) {
 		struct sge_uld_txq_info *txq_info;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 175bf9b13058..171750fad44f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -9348,7 +9348,7 @@ int t4_init_devlog_params(struct adapter *adap)
 		return 0;
 	}
 
-	/* Otherwise, ask the firmware for it's Device Log Parameters.
+	/* Otherwise, ask the firmware for its Device Log Parameters.
 	 */
 	memset(&devlog_cmd, 0, sizeof(devlog_cmd));
 	devlog_cmd.op_to_write = cpu_to_be32(FW_CMD_OP_V(FW_DEVLOG_CMD) |
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 5b1d746e6563..31fab2415743 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -2062,7 +2062,7 @@ irq_handler_t t4vf_intr_handler(struct adapter *adapter)
  */
 static void sge_rx_timer_cb(struct timer_list *t)
 {
-	struct adapter *adapter = from_timer(adapter, t, sge.rx_timer);
+	struct adapter *adapter = timer_container_of(adapter, t, sge.rx_timer);
 	struct sge *s = &adapter->sge;
 	unsigned int i;
 
@@ -2121,7 +2121,7 @@ static void sge_rx_timer_cb(struct timer_list *t)
  */
 static void sge_tx_timer_cb(struct timer_list *t)
 {
-	struct adapter *adapter = from_timer(adapter, t, sge.tx_timer);
+	struct adapter *adapter = timer_container_of(adapter, t, sge.tx_timer);
 	struct sge *s = &adapter->sge;
 	unsigned int i, budget;
 
@@ -2191,7 +2191,7 @@ static void __iomem *bar2_address(struct adapter *adapter,
 /**
  *	t4vf_sge_alloc_rxq - allocate an SGE RX Queue
  *	@adapter: the adapter
- *	@rspq: pointer to to the new rxq's Response Queue to be filled in
+ *	@rspq: pointer to the new rxq's Response Queue to be filled in
  *	@iqasynch: if 0, a normal rspq; if 1, an asynchronous event queue
  *	@dev: the network device associated with the new rspq
  *	@intr_dest: MSI-X vector index (overriden in MSI mode)
@@ -2609,9 +2609,9 @@ void t4vf_sge_stop(struct adapter *adapter)
 	struct sge *s = &adapter->sge;
 
 	if (s->rx_timer.function)
-		del_timer_sync(&s->rx_timer);
+		timer_delete_sync(&s->rx_timer);
 	if (s->tx_timer.function)
-		del_timer_sync(&s->tx_timer);
+		timer_delete_sync(&s->tx_timer);
 }
 
 /**
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
index 1c52592d3b65..56fcc531af2e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
@@ -706,7 +706,7 @@ int t4vf_fl_pkt_align(struct adapter *adapter)
 	 * separately.  The actual Ingress Packet Data alignment boundary
 	 * within Packed Buffer Mode is the maximum of these two
 	 * specifications.  (Note that it makes no real practical sense to
-	 * have the Pading Boudary be larger than the Packing Boundary but you
+	 * have the Padding Boundary be larger than the Packing Boundary but you
 	 * could set the chip up that way and, in fact, legacy T4 code would
 	 * end doing this because it would initialize the Padding Boundary and
 	 * leave the Packing Boundary initialized to 0 (16 bytes).)
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c
index c7338ac6a5bb..49b57bb5fac1 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c
@@ -71,21 +71,22 @@
 static LIST_HEAD(uld_ctx_list);
 static DEFINE_MUTEX(dev_mutex);
 
-static bool ch_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x);
 static int ch_ipsec_uld_state_change(void *handle, enum cxgb4_state new_state);
 static int ch_ipsec_xmit(struct sk_buff *skb, struct net_device *dev);
 static void *ch_ipsec_uld_add(const struct cxgb4_lld_info *infop);
 static void ch_ipsec_advance_esn_state(struct xfrm_state *x);
-static void ch_ipsec_xfrm_free_state(struct xfrm_state *x);
-static void ch_ipsec_xfrm_del_state(struct xfrm_state *x);
-static int ch_ipsec_xfrm_add_state(struct xfrm_state *x,
+static void ch_ipsec_xfrm_free_state(struct net_device *dev,
+				     struct xfrm_state *x);
+static void ch_ipsec_xfrm_del_state(struct net_device *dev,
+				    struct xfrm_state *x);
+static int ch_ipsec_xfrm_add_state(struct net_device *dev,
+				   struct xfrm_state *x,
 				   struct netlink_ext_ack *extack);
 
 static const struct xfrmdev_ops ch_ipsec_xfrmdev_ops = {
 	.xdo_dev_state_add      = ch_ipsec_xfrm_add_state,
 	.xdo_dev_state_delete   = ch_ipsec_xfrm_del_state,
 	.xdo_dev_state_free     = ch_ipsec_xfrm_free_state,
-	.xdo_dev_offload_ok     = ch_ipsec_offload_ok,
 	.xdo_dev_state_advance_esn = ch_ipsec_advance_esn_state,
 };
 
@@ -225,7 +226,8 @@ out:
  * returns 0 on success, negative error if failed to send message to FPGA
  * positive error if FPGA returned a bad response
  */
-static int ch_ipsec_xfrm_add_state(struct xfrm_state *x,
+static int ch_ipsec_xfrm_add_state(struct net_device *dev,
+				   struct xfrm_state *x,
 				   struct netlink_ext_ack *extack)
 {
 	struct ipsec_sa_entry *sa_entry;
@@ -288,9 +290,15 @@ static int ch_ipsec_xfrm_add_state(struct xfrm_state *x,
 		return -EINVAL;
 	}
 
+	if (unlikely(!try_module_get(THIS_MODULE))) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to acquire module reference");
+		return -ENODEV;
+	}
+
 	sa_entry = kzalloc(sizeof(*sa_entry), GFP_KERNEL);
 	if (!sa_entry) {
 		res = -ENOMEM;
+		module_put(THIS_MODULE);
 		goto out;
 	}
 
@@ -299,19 +307,20 @@ static int ch_ipsec_xfrm_add_state(struct xfrm_state *x,
 		sa_entry->esn = 1;
 	ch_ipsec_setkey(x, sa_entry);
 	x->xso.offload_handle = (unsigned long)sa_entry;
-	try_module_get(THIS_MODULE);
 out:
 	return res;
 }
 
-static void ch_ipsec_xfrm_del_state(struct xfrm_state *x)
+static void ch_ipsec_xfrm_del_state(struct net_device *dev,
+				    struct xfrm_state *x)
 {
 	/* do nothing */
 	if (!x->xso.offload_handle)
 		return;
 }
 
-static void ch_ipsec_xfrm_free_state(struct xfrm_state *x)
+static void ch_ipsec_xfrm_free_state(struct net_device *dev,
+				     struct xfrm_state *x)
 {
 	struct ipsec_sa_entry *sa_entry;
 
@@ -323,20 +332,6 @@ static void ch_ipsec_xfrm_free_state(struct xfrm_state *x)
 	module_put(THIS_MODULE);
 }
 
-static bool ch_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
-{
-	if (x->props.family == AF_INET) {
-		/* Offload with IP options is not supported yet */
-		if (ip_hdr(skb)->ihl > 5)
-			return false;
-	} else {
-		/* Offload with IPv6 extension headers is not support yet */
-		if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr))
-			return false;
-	}
-	return true;
-}
-
 static void ch_ipsec_advance_esn_state(struct xfrm_state *x)
 {
 	/* do nothing */
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index e8e460a92e0e..4e2096e49684 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -1640,6 +1640,7 @@ static int chcr_ktls_tunnel_pkt(struct chcr_ktls_info *tx_info,
 	cxgb4_write_sgl(skb, &q->q, pos, end, 0, sgl_sdesc->addr);
 	sgl_sdesc->skb = skb;
 	chcr_txq_advance(&q->q, ndesc);
+	skb_tx_timestamp(skb);
 	cxgb4_ring_tx_db(tx_info->adap, &q->q, ndesc);
 	return 0;
 }
@@ -1903,7 +1904,6 @@ static int chcr_ktls_sw_fallback(struct sk_buff *skb,
 	th = tcp_hdr(nskb);
 	skb_offset = skb_tcp_all_headers(nskb);
 	data_len = nskb->len - skb_offset;
-	skb_tx_timestamp(nskb);
 
 	if (chcr_ktls_tunnel_pkt(tx_info, nskb, q))
 		goto out;
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
index 6f6525983130..ee0154337a9c 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
@@ -171,7 +171,7 @@ static void chtls_purge_receive_queue(struct sock *sk)
 	struct sk_buff *skb;
 
 	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
-		skb_dst_set(skb, (void *)NULL);
+		skb_dstref_steal(skb);
 		kfree_skb(skb);
 	}
 }
@@ -194,7 +194,7 @@ static void chtls_purge_recv_queue(struct sock *sk)
 	struct sk_buff *skb;
 
 	while ((skb = __skb_dequeue(&tlsk->sk_recv_queue)) != NULL) {
-		skb_dst_set(skb, NULL);
+		skb_dstref_steal(skb);
 		kfree_skb(skb);
 	}
 }
@@ -505,7 +505,7 @@ static void reset_listen_child(struct sock *child)
 
 	chtls_send_reset(child, CPL_ABORT_SEND_RST, skb);
 	sock_orphan(child);
-	INC_ORPHAN_COUNT(child);
+	tcp_orphan_count_inc();
 	if (child->sk_state == TCP_CLOSE)
 		inet_csk_destroy_sock(child);
 }
@@ -870,7 +870,7 @@ static void do_abort_syn_rcv(struct sock *child, struct sock *parent)
 		 * created only after 3 way handshake is done.
 		 */
 		sock_orphan(child);
-		INC_ORPHAN_COUNT(child);
+		tcp_orphan_count_inc();
 		chtls_release_resources(child);
 		chtls_conn_done(child);
 	} else {
@@ -951,6 +951,7 @@ static unsigned int chtls_select_mss(const struct chtls_sock *csk,
 	struct tcp_sock *tp;
 	unsigned int mss;
 	struct sock *sk;
+	u16 user_mss;
 
 	mss = ntohs(req->tcpopt.mss);
 	sk = csk->sk;
@@ -969,8 +970,9 @@ static unsigned int chtls_select_mss(const struct chtls_sock *csk,
 		tcpoptsz += round_up(TCPOLEN_TIMESTAMP, 4);
 
 	tp->advmss = dst_metric_advmss(dst);
-	if (USER_MSS(tp) && tp->advmss > USER_MSS(tp))
-		tp->advmss = USER_MSS(tp);
+	user_mss = USER_MSS(tp);
+	if (user_mss && tp->advmss > user_mss)
+		tp->advmss = user_mss;
 	if (tp->advmss > pmtu - iphdrsz)
 		tp->advmss = pmtu - iphdrsz;
 	if (mss && tp->advmss > mss)
@@ -1197,12 +1199,12 @@ static struct sock *chtls_recv_sock(struct sock *lsk,
 		struct ipv6_pinfo *newnp = inet6_sk(newsk);
 		struct ipv6_pinfo *np = inet6_sk(lsk);
 
-		inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
+		newinet->pinet6 = &newtcp6sk->inet6;
+		newinet->ipv6_fl_list = NULL;
 		memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 		newsk->sk_v6_daddr = treq->ir_v6_rmt_addr;
 		newsk->sk_v6_rcv_saddr = treq->ir_v6_loc_addr;
 		inet6_sk(newsk)->saddr = treq->ir_v6_loc_addr;
-		newnp->ipv6_fl_list = NULL;
 		newnp->pktoptions = NULL;
 		newsk->sk_bound_dev_if = treq->ir_iif;
 		newinet->inet_opt = NULL;
@@ -1734,7 +1736,7 @@ static int chtls_rx_data(struct chtls_dev *cdev, struct sk_buff *skb)
 		pr_err("can't find conn. for hwtid %u.\n", hwtid);
 		return -EINVAL;
 	}
-	skb_dst_set(skb, NULL);
+	skb_dstref_steal(skb);
 	process_cpl_msg(chtls_recv_data, sk, skb);
 	return 0;
 }
@@ -1786,7 +1788,7 @@ static int chtls_rx_pdu(struct chtls_dev *cdev, struct sk_buff *skb)
 		pr_err("can't find conn. for hwtid %u.\n", hwtid);
 		return -EINVAL;
 	}
-	skb_dst_set(skb, NULL);
+	skb_dstref_steal(skb);
 	process_cpl_msg(chtls_recv_pdu, sk, skb);
 	return 0;
 }
@@ -1855,7 +1857,7 @@ static int chtls_rx_cmp(struct chtls_dev *cdev, struct sk_buff *skb)
 		pr_err("can't find conn. for hwtid %u.\n", hwtid);
 		return -EINVAL;
 	}
-	skb_dst_set(skb, NULL);
+	skb_dstref_steal(skb);
 	process_cpl_msg(chtls_rx_hdr, sk, skb);
 
 	return 0;
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h
index f61ca657601c..29ceff5a5fcb 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h
@@ -90,12 +90,11 @@ struct deferred_skb_cb {
 
 #define SND_WSCALE(tp) ((tp)->rx_opt.snd_wscale)
 #define RCV_WSCALE(tp) ((tp)->rx_opt.rcv_wscale)
-#define USER_MSS(tp) ((tp)->rx_opt.user_mss)
+#define USER_MSS(tp) (READ_ONCE((tp)->rx_opt.user_mss))
 #define TS_RECENT_STAMP(tp) ((tp)->rx_opt.ts_recent_stamp)
 #define WSCALE_OK(tp) ((tp)->rx_opt.wscale_ok)
 #define TSTAMP_OK(tp) ((tp)->rx_opt.tstamp_ok)
 #define SACK_OK(tp) ((tp)->rx_opt.sack_ok)
-#define INC_ORPHAN_COUNT(sk) this_cpu_inc(*(sk)->sk_prot->orphan_count)
 
 /* TLS SKB */
 #define skb_ulp_tls_inline(skb)      (ULP_SKB_CB(skb)->ulp.tls.ofld)
@@ -171,14 +170,14 @@ static inline void chtls_set_req_addr(struct request_sock *oreq,
 
 static inline void chtls_free_skb(struct sock *sk, struct sk_buff *skb)
 {
-	skb_dst_set(skb, NULL);
+	skb_dstref_steal(skb);
 	__skb_unlink(skb, &sk->sk_receive_queue);
 	__kfree_skb(skb);
 }
 
 static inline void chtls_kfree_skb(struct sock *sk, struct sk_buff *skb)
 {
-	skb_dst_set(skb, NULL);
+	skb_dstref_steal(skb);
 	__skb_unlink(skb, &sk->sk_receive_queue);
 	kfree_skb(skb);
 }
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
index d567e42e1760..ee19933e2cca 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
@@ -159,19 +159,13 @@ static u8 tcp_state_to_flowc_state(u8 state)
 int send_tx_flowc_wr(struct sock *sk, int compl,
 		     u32 snd_nxt, u32 rcv_nxt)
 {
-	struct flowc_packed {
-		struct fw_flowc_wr fc;
-		struct fw_flowc_mnemval mnemval[FW_FLOWC_MNEM_MAX];
-	} __packed sflowc;
+	DEFINE_RAW_FLEX(struct fw_flowc_wr, flowc, mnemval, FW_FLOWC_MNEM_MAX);
 	int nparams, paramidx, flowclen16, flowclen;
-	struct fw_flowc_wr *flowc;
 	struct chtls_sock *csk;
 	struct tcp_sock *tp;
 
 	csk = rcu_dereference_sk_user_data(sk);
 	tp = tcp_sk(sk);
-	memset(&sflowc, 0, sizeof(sflowc));
-	flowc = &sflowc.fc;
 
 #define FLOWC_PARAM(__m, __v) \
 	do { \
@@ -1096,8 +1090,7 @@ new_buf:
 			copy = size;
 
 		if (msg->msg_flags & MSG_SPLICE_PAGES) {
-			err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
-						   sk->sk_allocation);
+			err = skb_splice_from_iter(skb, &msg->msg_iter, copy);
 			if (err < 0) {
 				if (err == -EMSGSIZE)
 					goto new_buf;
@@ -1435,7 +1428,7 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		continue;
 found_ok_skb:
 		if (!skb->len) {
-			skb_dst_set(skb, NULL);
+			skb_dstref_steal(skb);
 			__skb_unlink(skb, &sk->sk_receive_queue);
 			kfree_skb(skb);
 
diff --git a/drivers/net/ethernet/cisco/enic/Kconfig b/drivers/net/ethernet/cisco/enic/Kconfig
index ad80c0fa96a6..96709875fe4f 100644
--- a/drivers/net/ethernet/cisco/enic/Kconfig
+++ b/drivers/net/ethernet/cisco/enic/Kconfig
@@ -6,5 +6,6 @@
 config ENIC
 	tristate "Cisco VIC Ethernet NIC Support"
 	depends on PCI
+	select PAGE_POOL
 	help
 	  This enables the support for the Cisco VIC Ethernet card.
diff --git a/drivers/net/ethernet/cisco/enic/Makefile b/drivers/net/ethernet/cisco/enic/Makefile
index c3b6febfdbe4..a96b8332e6e2 100644
--- a/drivers/net/ethernet/cisco/enic/Makefile
+++ b/drivers/net/ethernet/cisco/enic/Makefile
@@ -3,5 +3,5 @@ obj-$(CONFIG_ENIC) := enic.o
 
 enic-y := enic_main.o vnic_cq.o vnic_intr.o vnic_wq.o \
 	enic_res.o enic_dev.o enic_pp.o vnic_dev.o vnic_rq.o vnic_vic.o \
-	enic_ethtool.o enic_api.o enic_clsf.o
+	enic_ethtool.o enic_api.o enic_clsf.o enic_rq.o enic_wq.o
 
diff --git a/drivers/net/ethernet/cisco/enic/cq_desc.h b/drivers/net/ethernet/cisco/enic/cq_desc.h
index 462c5435a206..bfb3f14e89f5 100644
--- a/drivers/net/ethernet/cisco/enic/cq_desc.h
+++ b/drivers/net/ethernet/cisco/enic/cq_desc.h
@@ -40,28 +40,7 @@ struct cq_desc {
 #define CQ_DESC_COMP_NDX_BITS    12
 #define CQ_DESC_COMP_NDX_MASK    ((1 << CQ_DESC_COMP_NDX_BITS) - 1)
 
-static inline void cq_desc_dec(const struct cq_desc *desc_arg,
-	u8 *type, u8 *color, u16 *q_number, u16 *completed_index)
-{
-	const struct cq_desc *desc = desc_arg;
-	const u8 type_color = desc->type_color;
-
-	*color = (type_color >> CQ_DESC_COLOR_SHIFT) & CQ_DESC_COLOR_MASK;
-
-	/*
-	 * Make sure color bit is read from desc *before* other fields
-	 * are read from desc.  Hardware guarantees color bit is last
-	 * bit (byte) written.  Adding the rmb() prevents the compiler
-	 * and/or CPU from reordering the reads which would potentially
-	 * result in reading stale values.
-	 */
-
-	rmb();
-
-	*type = type_color & CQ_DESC_TYPE_MASK;
-	*q_number = le16_to_cpu(desc->q_number) & CQ_DESC_Q_NUM_MASK;
-	*completed_index = le16_to_cpu(desc->completed_index) &
-		CQ_DESC_COMP_NDX_MASK;
-}
+#define CQ_DESC_32_FI_MASK (BIT(0) | BIT(1))
+#define CQ_DESC_64_FI_MASK (BIT(0) | BIT(1))
 
 #endif /* _CQ_DESC_H_ */
diff --git a/drivers/net/ethernet/cisco/enic/cq_enet_desc.h b/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
index d25426470a29..50787cff29db 100644
--- a/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
+++ b/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
@@ -17,12 +17,22 @@ struct cq_enet_wq_desc {
 	u8 type_color;
 };
 
-static inline void cq_enet_wq_desc_dec(struct cq_enet_wq_desc *desc,
-	u8 *type, u8 *color, u16 *q_number, u16 *completed_index)
-{
-	cq_desc_dec((struct cq_desc *)desc, type,
-		color, q_number, completed_index);
-}
+/*
+ * Defines and Capabilities for CMD_CQ_ENTRY_SIZE_SET
+ */
+#define VNIC_RQ_ALL (~0ULL)
+
+#define VNIC_RQ_CQ_ENTRY_SIZE_16 0
+#define VNIC_RQ_CQ_ENTRY_SIZE_32 1
+#define VNIC_RQ_CQ_ENTRY_SIZE_64 2
+
+#define VNIC_RQ_CQ_ENTRY_SIZE_16_CAPABLE BIT(VNIC_RQ_CQ_ENTRY_SIZE_16)
+#define VNIC_RQ_CQ_ENTRY_SIZE_32_CAPABLE BIT(VNIC_RQ_CQ_ENTRY_SIZE_32)
+#define VNIC_RQ_CQ_ENTRY_SIZE_64_CAPABLE BIT(VNIC_RQ_CQ_ENTRY_SIZE_64)
+
+#define VNIC_RQ_CQ_ENTRY_SIZE_ALL_BIT  (VNIC_RQ_CQ_ENTRY_SIZE_16_CAPABLE | \
+					VNIC_RQ_CQ_ENTRY_SIZE_32_CAPABLE | \
+					VNIC_RQ_CQ_ENTRY_SIZE_64_CAPABLE)
 
 /* Completion queue descriptor: Ethernet receive queue, 16B */
 struct cq_enet_rq_desc {
@@ -36,6 +46,45 @@ struct cq_enet_rq_desc {
 	u8 type_color;
 };
 
+/* Completion queue descriptor: Ethernet receive queue, 32B */
+struct cq_enet_rq_desc_32 {
+	__le16 completed_index_flags;
+	__le16 q_number_rss_type_flags;
+	__le32 rss_hash;
+	__le16 bytes_written_flags;
+	__le16 vlan;
+	__le16 checksum_fcoe;
+	u8 flags;
+	u8 fetch_index_flags;
+	__le32 time_stamp;
+	__le16 time_stamp2;
+	__le16 pie_info;
+	__le32 pie_info2;
+	__le16 pie_info3;
+	u8 pie_info4;
+	u8 type_color;
+};
+
+/* Completion queue descriptor: Ethernet receive queue, 64B */
+struct cq_enet_rq_desc_64 {
+	__le16 completed_index_flags;
+	__le16 q_number_rss_type_flags;
+	__le32 rss_hash;
+	__le16 bytes_written_flags;
+	__le16 vlan;
+	__le16 checksum_fcoe;
+	u8 flags;
+	u8 fetch_index_flags;
+	__le32 time_stamp;
+	__le16 time_stamp2;
+	__le16 pie_info;
+	__le32 pie_info2;
+	__le16 pie_info3;
+	u8 pie_info4;
+	u8 reserved[32];
+	u8 type_color;
+};
+
 #define CQ_ENET_RQ_DESC_FLAGS_INGRESS_PORT          (0x1 << 12)
 #define CQ_ENET_RQ_DESC_FLAGS_FCOE                  (0x1 << 13)
 #define CQ_ENET_RQ_DESC_FLAGS_EOP                   (0x1 << 14)
@@ -88,85 +137,4 @@ struct cq_enet_rq_desc {
 #define CQ_ENET_RQ_DESC_FLAGS_IPV4_FRAGMENT         (0x1 << 6)
 #define CQ_ENET_RQ_DESC_FLAGS_FCS_OK                (0x1 << 7)
 
-static inline void cq_enet_rq_desc_dec(struct cq_enet_rq_desc *desc,
-	u8 *type, u8 *color, u16 *q_number, u16 *completed_index,
-	u8 *ingress_port, u8 *fcoe, u8 *eop, u8 *sop, u8 *rss_type,
-	u8 *csum_not_calc, u32 *rss_hash, u16 *bytes_written, u8 *packet_error,
-	u8 *vlan_stripped, u16 *vlan_tci, u16 *checksum, u8 *fcoe_sof,
-	u8 *fcoe_fc_crc_ok, u8 *fcoe_enc_error, u8 *fcoe_eof,
-	u8 *tcp_udp_csum_ok, u8 *udp, u8 *tcp, u8 *ipv4_csum_ok,
-	u8 *ipv6, u8 *ipv4, u8 *ipv4_fragment, u8 *fcs_ok)
-{
-	u16 completed_index_flags;
-	u16 q_number_rss_type_flags;
-	u16 bytes_written_flags;
-
-	cq_desc_dec((struct cq_desc *)desc, type,
-		color, q_number, completed_index);
-
-	completed_index_flags = le16_to_cpu(desc->completed_index_flags);
-	q_number_rss_type_flags =
-		le16_to_cpu(desc->q_number_rss_type_flags);
-	bytes_written_flags = le16_to_cpu(desc->bytes_written_flags);
-
-	*ingress_port = (completed_index_flags &
-		CQ_ENET_RQ_DESC_FLAGS_INGRESS_PORT) ? 1 : 0;
-	*fcoe = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_FCOE) ?
-		1 : 0;
-	*eop = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_EOP) ?
-		1 : 0;
-	*sop = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_SOP) ?
-		1 : 0;
-
-	*rss_type = (u8)((q_number_rss_type_flags >> CQ_DESC_Q_NUM_BITS) &
-		CQ_ENET_RQ_DESC_RSS_TYPE_MASK);
-	*csum_not_calc = (q_number_rss_type_flags &
-		CQ_ENET_RQ_DESC_FLAGS_CSUM_NOT_CALC) ? 1 : 0;
-
-	*rss_hash = le32_to_cpu(desc->rss_hash);
-
-	*bytes_written = bytes_written_flags &
-		CQ_ENET_RQ_DESC_BYTES_WRITTEN_MASK;
-	*packet_error = (bytes_written_flags &
-		CQ_ENET_RQ_DESC_FLAGS_TRUNCATED) ? 1 : 0;
-	*vlan_stripped = (bytes_written_flags &
-		CQ_ENET_RQ_DESC_FLAGS_VLAN_STRIPPED) ? 1 : 0;
-
-	/*
-	 * Tag Control Information(16) = user_priority(3) + cfi(1) + vlan(12)
-	 */
-	*vlan_tci = le16_to_cpu(desc->vlan);
-
-	if (*fcoe) {
-		*fcoe_sof = (u8)(le16_to_cpu(desc->checksum_fcoe) &
-			CQ_ENET_RQ_DESC_FCOE_SOF_MASK);
-		*fcoe_fc_crc_ok = (desc->flags &
-			CQ_ENET_RQ_DESC_FCOE_FC_CRC_OK) ? 1 : 0;
-		*fcoe_enc_error = (desc->flags &
-			CQ_ENET_RQ_DESC_FCOE_ENC_ERROR) ? 1 : 0;
-		*fcoe_eof = (u8)((le16_to_cpu(desc->checksum_fcoe) >>
-			CQ_ENET_RQ_DESC_FCOE_EOF_SHIFT) &
-			CQ_ENET_RQ_DESC_FCOE_EOF_MASK);
-		*checksum = 0;
-	} else {
-		*fcoe_sof = 0;
-		*fcoe_fc_crc_ok = 0;
-		*fcoe_enc_error = 0;
-		*fcoe_eof = 0;
-		*checksum = le16_to_cpu(desc->checksum_fcoe);
-	}
-
-	*tcp_udp_csum_ok =
-		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_TCP_UDP_CSUM_OK) ? 1 : 0;
-	*udp = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_UDP) ? 1 : 0;
-	*tcp = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_TCP) ? 1 : 0;
-	*ipv4_csum_ok =
-		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4_CSUM_OK) ? 1 : 0;
-	*ipv6 = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV6) ? 1 : 0;
-	*ipv4 = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4) ? 1 : 0;
-	*ipv4_fragment =
-		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4_FRAGMENT) ? 1 : 0;
-	*fcs_ok = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_FCS_OK) ? 1 : 0;
-}
-
 #endif /* _CQ_ENET_DESC_H_ */
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 10b7e02ba4d0..301b3f3114af 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -17,6 +17,7 @@
 #include "vnic_nic.h"
 #include "vnic_rss.h"
 #include <linux/irq.h>
+#include <net/page_pool/helpers.h>
 
 #define DRV_NAME		"enic"
 #define DRV_DESCRIPTION		"Cisco VIC Ethernet NIC Driver"
@@ -25,11 +26,19 @@
 
 #define ENIC_WQ_MAX		256
 #define ENIC_RQ_MAX		256
+#define ENIC_RQ_MIN_DEFAULT	8
 
 #define ENIC_WQ_NAPI_BUDGET	256
 
 #define ENIC_AIC_LARGE_PKT_DIFF	3
 
+enum ext_cq {
+	ENIC_RQ_CQ_ENTRY_SIZE_16,
+	ENIC_RQ_CQ_ENTRY_SIZE_32,
+	ENIC_RQ_CQ_ENTRY_SIZE_64,
+	ENIC_RQ_CQ_ENTRY_SIZE_MAX,
+};
+
 struct enic_msix_entry {
 	int requested;
 	char devname[IFNAMSIZ + 8];
@@ -75,6 +84,10 @@ struct enic_rx_coal {
 #define ENIC_SET_INSTANCE		(1 << 3)
 #define ENIC_SET_HOST			(1 << 4)
 
+#define MAX_TSO			BIT(16)
+#define WQ_ENET_MAX_DESC_LEN	BIT(WQ_ENET_LEN_BITS)
+#define ENIC_DESC_MAX_SPLITS	(MAX_TSO / WQ_ENET_MAX_DESC_LEN + 1)
+
 struct enic_port_profile {
 	u32 set;
 	u8 request;
@@ -158,6 +171,7 @@ struct enic_rq_stats {
 	u64 pkt_truncated;		/* truncated pkts */
 	u64 no_skb;			/* out of skbs */
 	u64 desc_skip;			/* Rx pkt went into later buffer */
+	u64 pp_alloc_fail;		/* page pool alloc failure */
 };
 
 struct enic_wq {
@@ -169,6 +183,7 @@ struct enic_wq {
 struct enic_rq {
 	struct vnic_rq vrq;
 	struct enic_rq_stats stats;
+	struct page_pool *pool;
 } ____cacheline_aligned;
 
 /* Per-instance private data structure */
@@ -223,9 +238,9 @@ struct enic {
 	unsigned int cq_avail;
 	unsigned int cq_count;
 	struct enic_rfs_flw_tbl rfs_h;
-	u32 rx_copybreak;
 	u8 rss_key[ENIC_RSS_LEN];
 	struct vnic_gen_stats gen_stats;
+	enum ext_cq ext_cq;
 };
 
 static inline struct net_device *vnic_get_netdev(struct vnic_dev *vdev)
@@ -347,5 +362,6 @@ int enic_is_valid_vf(struct enic *enic, int vf);
 int enic_is_dynamic(struct enic *enic);
 void enic_set_ethtool_ops(struct net_device *netdev);
 int __enic_set_rsskey(struct enic *enic);
+void enic_ext_cq(struct enic *enic);
 
 #endif /* _ENIC_H_ */
diff --git a/drivers/net/ethernet/cisco/enic/enic_clsf.c b/drivers/net/ethernet/cisco/enic/enic_clsf.c
index 9900993b6aea..837f954873ee 100644
--- a/drivers/net/ethernet/cisco/enic/enic_clsf.c
+++ b/drivers/net/ethernet/cisco/enic/enic_clsf.c
@@ -125,7 +125,7 @@ struct enic_rfs_fltr_node *htbl_fltr_search(struct enic *enic, u16 fltr_id)
 #ifdef CONFIG_RFS_ACCEL
 void enic_flow_may_expire(struct timer_list *t)
 {
-	struct enic *enic = from_timer(enic, t, rfs_h.rfs_may_expire);
+	struct enic *enic = timer_container_of(enic, t, rfs_h.rfs_may_expire);
 	bool res;
 	int j;
 
diff --git a/drivers/net/ethernet/cisco/enic/enic_clsf.h b/drivers/net/ethernet/cisco/enic/enic_clsf.h
index 8c4ce50da6e1..5f5284102fb0 100644
--- a/drivers/net/ethernet/cisco/enic/enic_clsf.h
+++ b/drivers/net/ethernet/cisco/enic/enic_clsf.h
@@ -26,7 +26,7 @@ static inline void enic_rfs_timer_start(struct enic *enic)
 
 static inline void enic_rfs_timer_stop(struct enic *enic)
 {
-	del_timer_sync(&enic->rfs_h.rfs_may_expire);
+	timer_delete_sync(&enic->rfs_h.rfs_may_expire);
 }
 #else
 static inline void enic_rfs_timer_start(struct enic *enic) {}
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index d607b4f0542c..a50f5dad34d5 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -222,9 +222,9 @@ static void enic_get_ringparam(struct net_device *netdev,
 	struct enic *enic = netdev_priv(netdev);
 	struct vnic_enet_config *c = &enic->config;
 
-	ring->rx_max_pending = ENIC_MAX_RQ_DESCS;
+	ring->rx_max_pending = c->max_rq_ring;
 	ring->rx_pending = c->rq_desc_count;
-	ring->tx_max_pending = ENIC_MAX_WQ_DESCS;
+	ring->tx_max_pending = c->max_wq_ring;
 	ring->tx_pending = c->wq_desc_count;
 }
 
@@ -252,18 +252,18 @@ static int enic_set_ringparam(struct net_device *netdev,
 	}
 	rx_pending = c->rq_desc_count;
 	tx_pending = c->wq_desc_count;
-	if (ring->rx_pending > ENIC_MAX_RQ_DESCS ||
+	if (ring->rx_pending > c->max_rq_ring ||
 	    ring->rx_pending < ENIC_MIN_RQ_DESCS) {
 		netdev_info(netdev, "rx pending (%u) not in range [%u,%u]",
 			    ring->rx_pending, ENIC_MIN_RQ_DESCS,
-			    ENIC_MAX_RQ_DESCS);
+	      c->max_rq_ring);
 		return -EINVAL;
 	}
-	if (ring->tx_pending > ENIC_MAX_WQ_DESCS ||
+	if (ring->tx_pending > c->max_wq_ring ||
 	    ring->tx_pending < ENIC_MIN_WQ_DESCS) {
 		netdev_info(netdev, "tx pending (%u) not in range [%u,%u]",
 			    ring->tx_pending, ENIC_MIN_WQ_DESCS,
-			    ENIC_MAX_WQ_DESCS);
+			c->max_wq_ring);
 		return -EINVAL;
 	}
 	if (running)
@@ -528,8 +528,10 @@ static int enic_grxclsrule(struct enic *enic, struct ethtool_rxnfc *cmd)
 	return 0;
 }
 
-static int enic_get_rx_flow_hash(struct enic *enic, struct ethtool_rxnfc *cmd)
+static int enic_get_rx_flow_hash(struct net_device *dev,
+				 struct ethtool_rxfh_fields *cmd)
 {
+	struct enic *enic = netdev_priv(dev);
 	u8 rss_hash_type = 0;
 	cmd->data = 0;
 
@@ -597,9 +599,6 @@ static int enic_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 		ret = enic_grxclsrule(enic, cmd);
 		spin_unlock_bh(&enic->rfs_h.lock);
 		break;
-	case ETHTOOL_GRXFH:
-		ret = enic_get_rx_flow_hash(enic, cmd);
-		break;
 	default:
 		ret = -EOPNOTSUPP;
 		break;
@@ -608,43 +607,6 @@ static int enic_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	return ret;
 }
 
-static int enic_get_tunable(struct net_device *dev,
-			    const struct ethtool_tunable *tuna, void *data)
-{
-	struct enic *enic = netdev_priv(dev);
-	int ret = 0;
-
-	switch (tuna->id) {
-	case ETHTOOL_RX_COPYBREAK:
-		*(u32 *)data = enic->rx_copybreak;
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
-static int enic_set_tunable(struct net_device *dev,
-			    const struct ethtool_tunable *tuna,
-			    const void *data)
-{
-	struct enic *enic = netdev_priv(dev);
-	int ret = 0;
-
-	switch (tuna->id) {
-	case ETHTOOL_RX_COPYBREAK:
-		enic->rx_copybreak = *(u32 *)data;
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
 static u32 enic_get_rxfh_key_size(struct net_device *netdev)
 {
 	return ENIC_RSS_LEN;
@@ -727,11 +689,10 @@ static const struct ethtool_ops enic_ethtool_ops = {
 	.get_coalesce = enic_get_coalesce,
 	.set_coalesce = enic_set_coalesce,
 	.get_rxnfc = enic_get_rxnfc,
-	.get_tunable = enic_get_tunable,
-	.set_tunable = enic_set_tunable,
 	.get_rxfh_key_size = enic_get_rxfh_key_size,
 	.get_rxfh = enic_get_rxfh,
 	.set_rxfh = enic_set_rxfh,
+	.get_rxfh_fields = enic_get_rx_flow_hash,
 	.get_link_ksettings = enic_get_ksettings,
 	.get_ts_info = enic_get_ts_info,
 	.get_channels = enic_get_channels,
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 9913952ccb42..6bc8dfdb3d4b 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -58,18 +58,15 @@
 #include "enic_dev.h"
 #include "enic_pp.h"
 #include "enic_clsf.h"
+#include "enic_rq.h"
+#include "enic_wq.h"
 
 #define ENIC_NOTIFY_TIMER_PERIOD	(2 * HZ)
-#define WQ_ENET_MAX_DESC_LEN		(1 << WQ_ENET_LEN_BITS)
-#define MAX_TSO				(1 << 16)
-#define ENIC_DESC_MAX_SPLITS		(MAX_TSO / WQ_ENET_MAX_DESC_LEN + 1)
 
 #define PCI_DEVICE_ID_CISCO_VIC_ENET         0x0043  /* ethernet vnic */
 #define PCI_DEVICE_ID_CISCO_VIC_ENET_DYN     0x0044  /* enet dynamic vnic */
 #define PCI_DEVICE_ID_CISCO_VIC_ENET_VF      0x0071  /* enet SRIOV VF */
 
-#define RX_COPYBREAK_DEFAULT		256
-
 /* Supported devices */
 static const struct pci_device_id enic_id_table[] = {
 	{ PCI_VDEVICE(CISCO, PCI_DEVICE_ID_CISCO_VIC_ENET) },
@@ -109,7 +106,7 @@ static struct enic_intr_mod_table mod_table[ENIC_MAX_COALESCE_TIMERS + 1] = {
 static struct enic_intr_mod_range mod_range[ENIC_MAX_LINK_SPEEDS] = {
 	{0,  0}, /* 0  - 4  Gbps */
 	{0,  3}, /* 4  - 10 Gbps */
-	{3,  6}, /* 10 - 40 Gbps */
+	{3,  6}, /* 10+ Gbps */
 };
 
 static void enic_init_affinity_hint(struct enic *enic)
@@ -322,54 +319,6 @@ int enic_is_valid_vf(struct enic *enic, int vf)
 #endif
 }
 
-static void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf)
-{
-	struct enic *enic = vnic_dev_priv(wq->vdev);
-
-	if (buf->sop)
-		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-				 DMA_TO_DEVICE);
-	else
-		dma_unmap_page(&enic->pdev->dev, buf->dma_addr, buf->len,
-			       DMA_TO_DEVICE);
-
-	if (buf->os_buf)
-		dev_kfree_skb_any(buf->os_buf);
-}
-
-static void enic_wq_free_buf(struct vnic_wq *wq,
-	struct cq_desc *cq_desc, struct vnic_wq_buf *buf, void *opaque)
-{
-	struct enic *enic = vnic_dev_priv(wq->vdev);
-
-	enic->wq[wq->index].stats.cq_work++;
-	enic->wq[wq->index].stats.cq_bytes += buf->len;
-	enic_free_wq_buf(wq, buf);
-}
-
-static int enic_wq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc,
-	u8 type, u16 q_number, u16 completed_index, void *opaque)
-{
-	struct enic *enic = vnic_dev_priv(vdev);
-
-	spin_lock(&enic->wq[q_number].lock);
-
-	vnic_wq_service(&enic->wq[q_number].vwq, cq_desc,
-		completed_index, enic_wq_free_buf,
-		opaque);
-
-	if (netif_tx_queue_stopped(netdev_get_tx_queue(enic->netdev, q_number)) &&
-	    vnic_wq_desc_avail(&enic->wq[q_number].vwq) >=
-	    (MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS)) {
-		netif_wake_subqueue(enic->netdev, q_number);
-		enic->wq[q_number].stats.wake++;
-	}
-
-	spin_unlock(&enic->wq[q_number].lock);
-
-	return 0;
-}
-
 static bool enic_log_q_error(struct enic *enic)
 {
 	unsigned int i;
@@ -428,6 +377,36 @@ static void enic_mtu_check(struct enic *enic)
 	}
 }
 
+static void enic_set_rx_coal_setting(struct enic *enic)
+{
+	unsigned int speed;
+	int index = -1;
+	struct enic_rx_coal *rx_coal = &enic->rx_coalesce_setting;
+
+	/* 1. Read the link speed from fw
+	 * 2. Pick the default range for the speed
+	 * 3. Update it in enic->rx_coalesce_setting
+	 */
+	speed = vnic_dev_port_speed(enic->vdev);
+	if (speed > ENIC_LINK_SPEED_10G)
+		index = ENIC_LINK_40G_INDEX;
+	else if (speed > ENIC_LINK_SPEED_4G)
+		index = ENIC_LINK_10G_INDEX;
+	else
+		index = ENIC_LINK_4G_INDEX;
+
+	rx_coal->small_pkt_range_start = mod_range[index].small_pkt_range_start;
+	rx_coal->large_pkt_range_start = mod_range[index].large_pkt_range_start;
+	rx_coal->range_end = ENIC_RX_COALESCE_RANGE_END;
+
+	/* Start with the value provided by UCSM */
+	for (index = 0; index < enic->rq_count; index++)
+		enic->cq[index].cur_rx_coal_timeval =
+				enic->config.intr_timer_usec;
+
+	rx_coal->use_adaptive_rx_coalesce = 1;
+}
+
 static void enic_link_check(struct enic *enic)
 {
 	int link_status = vnic_dev_link_status(enic->vdev);
@@ -436,6 +415,7 @@ static void enic_link_check(struct enic *enic)
 	if (link_status && !carrier_ok) {
 		netdev_info(enic->netdev, "Link UP\n");
 		netif_carrier_on(enic->netdev);
+		enic_set_rx_coal_setting(enic);
 	} else if (!link_status && carrier_ok) {
 		netdev_info(enic->netdev, "Link DOWN\n");
 		netif_carrier_off(enic->netdev);
@@ -1282,243 +1262,6 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf)
-{
-	struct enic *enic = vnic_dev_priv(rq->vdev);
-
-	if (!buf->os_buf)
-		return;
-
-	dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-			 DMA_FROM_DEVICE);
-	dev_kfree_skb_any(buf->os_buf);
-	buf->os_buf = NULL;
-}
-
-static int enic_rq_alloc_buf(struct vnic_rq *rq)
-{
-	struct enic *enic = vnic_dev_priv(rq->vdev);
-	struct net_device *netdev = enic->netdev;
-	struct sk_buff *skb;
-	unsigned int len = netdev->mtu + VLAN_ETH_HLEN;
-	unsigned int os_buf_index = 0;
-	dma_addr_t dma_addr;
-	struct vnic_rq_buf *buf = rq->to_use;
-
-	if (buf->os_buf) {
-		enic_queue_rq_desc(rq, buf->os_buf, os_buf_index, buf->dma_addr,
-				   buf->len);
-
-		return 0;
-	}
-	skb = netdev_alloc_skb_ip_align(netdev, len);
-	if (!skb) {
-		enic->rq[rq->index].stats.no_skb++;
-		return -ENOMEM;
-	}
-
-	dma_addr = dma_map_single(&enic->pdev->dev, skb->data, len,
-				  DMA_FROM_DEVICE);
-	if (unlikely(enic_dma_map_check(enic, dma_addr))) {
-		dev_kfree_skb(skb);
-		return -ENOMEM;
-	}
-
-	enic_queue_rq_desc(rq, skb, os_buf_index,
-		dma_addr, len);
-
-	return 0;
-}
-
-static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size,
-				      u32 pkt_len)
-{
-	if (ENIC_LARGE_PKT_THRESHOLD <= pkt_len)
-		pkt_size->large_pkt_bytes_cnt += pkt_len;
-	else
-		pkt_size->small_pkt_bytes_cnt += pkt_len;
-}
-
-static bool enic_rxcopybreak(struct net_device *netdev, struct sk_buff **skb,
-			     struct vnic_rq_buf *buf, u16 len)
-{
-	struct enic *enic = netdev_priv(netdev);
-	struct sk_buff *new_skb;
-
-	if (len > enic->rx_copybreak)
-		return false;
-	new_skb = netdev_alloc_skb_ip_align(netdev, len);
-	if (!new_skb)
-		return false;
-	dma_sync_single_for_cpu(&enic->pdev->dev, buf->dma_addr, len,
-				DMA_FROM_DEVICE);
-	memcpy(new_skb->data, (*skb)->data, len);
-	*skb = new_skb;
-
-	return true;
-}
-
-static void enic_rq_indicate_buf(struct vnic_rq *rq,
-	struct cq_desc *cq_desc, struct vnic_rq_buf *buf,
-	int skipped, void *opaque)
-{
-	struct enic *enic = vnic_dev_priv(rq->vdev);
-	struct net_device *netdev = enic->netdev;
-	struct sk_buff *skb;
-	struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)];
-	struct enic_rq_stats *rqstats = &enic->rq[rq->index].stats;
-
-	u8 type, color, eop, sop, ingress_port, vlan_stripped;
-	u8 fcoe, fcoe_sof, fcoe_fc_crc_ok, fcoe_enc_error, fcoe_eof;
-	u8 tcp_udp_csum_ok, udp, tcp, ipv4_csum_ok;
-	u8 ipv6, ipv4, ipv4_fragment, fcs_ok, rss_type, csum_not_calc;
-	u8 packet_error;
-	u16 q_number, completed_index, bytes_written, vlan_tci, checksum;
-	u32 rss_hash;
-	bool outer_csum_ok = true, encap = false;
-
-	rqstats->packets++;
-	if (skipped) {
-		rqstats->desc_skip++;
-		return;
-	}
-
-	skb = buf->os_buf;
-
-	cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc,
-		&type, &color, &q_number, &completed_index,
-		&ingress_port, &fcoe, &eop, &sop, &rss_type,
-		&csum_not_calc, &rss_hash, &bytes_written,
-		&packet_error, &vlan_stripped, &vlan_tci, &checksum,
-		&fcoe_sof, &fcoe_fc_crc_ok, &fcoe_enc_error,
-		&fcoe_eof, &tcp_udp_csum_ok, &udp, &tcp,
-		&ipv4_csum_ok, &ipv6, &ipv4, &ipv4_fragment,
-		&fcs_ok);
-
-	if (packet_error) {
-
-		if (!fcs_ok) {
-			if (bytes_written > 0)
-				rqstats->bad_fcs++;
-			else if (bytes_written == 0)
-				rqstats->pkt_truncated++;
-		}
-
-		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-				 DMA_FROM_DEVICE);
-		dev_kfree_skb_any(skb);
-		buf->os_buf = NULL;
-
-		return;
-	}
-
-	if (eop && bytes_written > 0) {
-
-		/* Good receive
-		 */
-		rqstats->bytes += bytes_written;
-		if (!enic_rxcopybreak(netdev, &skb, buf, bytes_written)) {
-			buf->os_buf = NULL;
-			dma_unmap_single(&enic->pdev->dev, buf->dma_addr,
-					 buf->len, DMA_FROM_DEVICE);
-		}
-		prefetch(skb->data - NET_IP_ALIGN);
-
-		skb_put(skb, bytes_written);
-		skb->protocol = eth_type_trans(skb, netdev);
-		skb_record_rx_queue(skb, q_number);
-		if ((netdev->features & NETIF_F_RXHASH) && rss_hash &&
-		    (type == 3)) {
-			switch (rss_type) {
-			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv4:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6_EX:
-				skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L4);
-				rqstats->l4_rss_hash++;
-				break;
-			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv4:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6_EX:
-				skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L3);
-				rqstats->l3_rss_hash++;
-				break;
-			}
-		}
-		if (enic->vxlan.vxlan_udp_port_number) {
-			switch (enic->vxlan.patch_level) {
-			case 0:
-				if (fcoe) {
-					encap = true;
-					outer_csum_ok = fcoe_fc_crc_ok;
-				}
-				break;
-			case 2:
-				if ((type == 7) &&
-				    (rss_hash & BIT(0))) {
-					encap = true;
-					outer_csum_ok = (rss_hash & BIT(1)) &&
-							(rss_hash & BIT(2));
-				}
-				break;
-			}
-		}
-
-		/* Hardware does not provide whole packet checksum. It only
-		 * provides pseudo checksum. Since hw validates the packet
-		 * checksum but not provide us the checksum value. use
-		 * CHECSUM_UNNECESSARY.
-		 *
-		 * In case of encap pkt tcp_udp_csum_ok/tcp_udp_csum_ok is
-		 * inner csum_ok. outer_csum_ok is set by hw when outer udp
-		 * csum is correct or is zero.
-		 */
-		if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc &&
-		    tcp_udp_csum_ok && outer_csum_ok &&
-		    (ipv4_csum_ok || ipv6)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			skb->csum_level = encap;
-			if (encap)
-				rqstats->csum_unnecessary_encap++;
-			else
-				rqstats->csum_unnecessary++;
-		}
-
-		if (vlan_stripped) {
-			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
-			rqstats->vlan_stripped++;
-		}
-		skb_mark_napi_id(skb, &enic->napi[rq->index]);
-		if (!(netdev->features & NETIF_F_GRO))
-			netif_receive_skb(skb);
-		else
-			napi_gro_receive(&enic->napi[q_number], skb);
-		if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce)
-			enic_intr_update_pkt_size(&cq->pkt_size_counter,
-						  bytes_written);
-	} else {
-
-		/* Buffer overflow
-		 */
-		rqstats->pkt_truncated++;
-		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-				 DMA_FROM_DEVICE);
-		dev_kfree_skb_any(skb);
-		buf->os_buf = NULL;
-	}
-}
-
-static int enic_rq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc,
-	u8 type, u16 q_number, u16 completed_index, void *opaque)
-{
-	struct enic *enic = vnic_dev_priv(vdev);
-
-	vnic_rq_service(&enic->rq[q_number].vrq, cq_desc,
-		completed_index, VNIC_RQ_RETURN_DESC,
-		enic_rq_indicate_buf, opaque);
-
-	return 0;
-}
-
 static void enic_set_int_moderation(struct enic *enic, struct vnic_rq *rq)
 {
 	unsigned int intr = enic_msix_rq_intr(enic, rq->index);
@@ -1589,12 +1332,10 @@ static int enic_poll(struct napi_struct *napi, int budget)
 	unsigned int  work_done, rq_work_done = 0, wq_work_done;
 	int err;
 
-	wq_work_done = vnic_cq_service(&enic->cq[cq_wq], wq_work_to_do,
-				       enic_wq_service, NULL);
+	wq_work_done = enic_wq_cq_service(enic, cq_wq, wq_work_to_do);
 
 	if (budget > 0)
-		rq_work_done = vnic_cq_service(&enic->cq[cq_rq],
-			rq_work_to_do, enic_rq_service, NULL);
+		rq_work_done = enic_rq_cq_service(enic, cq_rq, rq_work_to_do);
 
 	/* Accumulate intr event credits for this polling
 	 * cycle.  An intr event is the completion of a
@@ -1693,8 +1434,8 @@ static int enic_poll_msix_wq(struct napi_struct *napi, int budget)
 	wq_irq = wq->index;
 	cq = enic_cq_wq(enic, wq_irq);
 	intr = enic_msix_wq_intr(enic, wq_irq);
-	wq_work_done = vnic_cq_service(&enic->cq[cq], wq_work_to_do,
-				       enic_wq_service, NULL);
+
+	wq_work_done = enic_wq_cq_service(enic, cq, wq_work_to_do);
 
 	vnic_intr_return_credits(&enic->intr[intr], wq_work_done,
 				 0 /* don't unmask intr */,
@@ -1723,8 +1464,7 @@ static int enic_poll_msix_rq(struct napi_struct *napi, int budget)
 	 */
 
 	if (budget > 0)
-		work_done = vnic_cq_service(&enic->cq[cq],
-			work_to_do, enic_rq_service, NULL);
+		work_done = enic_rq_cq_service(enic, cq, work_to_do);
 
 	/* Return intr event credits for this polling
 	 * cycle.  An intr event is the completion of a
@@ -1770,7 +1510,7 @@ static int enic_poll_msix_rq(struct napi_struct *napi, int budget)
 
 static void enic_notify_timer(struct timer_list *t)
 {
-	struct enic *enic = from_timer(enic, t, notify_timer);
+	struct enic *enic = timer_container_of(enic, t, notify_timer);
 
 	enic_notify_check(enic);
 
@@ -1901,36 +1641,6 @@ static void enic_synchronize_irqs(struct enic *enic)
 	}
 }
 
-static void enic_set_rx_coal_setting(struct enic *enic)
-{
-	unsigned int speed;
-	int index = -1;
-	struct enic_rx_coal *rx_coal = &enic->rx_coalesce_setting;
-
-	/* 1. Read the link speed from fw
-	 * 2. Pick the default range for the speed
-	 * 3. Update it in enic->rx_coalesce_setting
-	 */
-	speed = vnic_dev_port_speed(enic->vdev);
-	if (ENIC_LINK_SPEED_10G < speed)
-		index = ENIC_LINK_40G_INDEX;
-	else if (ENIC_LINK_SPEED_4G < speed)
-		index = ENIC_LINK_10G_INDEX;
-	else
-		index = ENIC_LINK_4G_INDEX;
-
-	rx_coal->small_pkt_range_start = mod_range[index].small_pkt_range_start;
-	rx_coal->large_pkt_range_start = mod_range[index].large_pkt_range_start;
-	rx_coal->range_end = ENIC_RX_COALESCE_RANGE_END;
-
-	/* Start with the value provided by UCSM */
-	for (index = 0; index < enic->rq_count; index++)
-		enic->cq[index].cur_rx_coal_timeval =
-				enic->config.intr_timer_usec;
-
-	rx_coal->use_adaptive_rx_coalesce = 1;
-}
-
 static int enic_dev_notify_set(struct enic *enic)
 {
 	int err;
@@ -1971,6 +1681,17 @@ static int enic_open(struct net_device *netdev)
 	struct enic *enic = netdev_priv(netdev);
 	unsigned int i;
 	int err, ret;
+	unsigned int max_pkt_len = netdev->mtu + VLAN_ETH_HLEN;
+	struct page_pool_params pp_params = {
+		.order = get_order(max_pkt_len),
+		.pool_size = enic->config.rq_desc_count,
+		.nid = dev_to_node(&enic->pdev->dev),
+		.dev = &enic->pdev->dev,
+		.dma_dir = DMA_FROM_DEVICE,
+		.max_len = (max_pkt_len > PAGE_SIZE) ? max_pkt_len : PAGE_SIZE,
+		.netdev = netdev,
+		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
+	};
 
 	err = enic_request_intr(enic);
 	if (err) {
@@ -1988,6 +1709,16 @@ static int enic_open(struct net_device *netdev)
 	}
 
 	for (i = 0; i < enic->rq_count; i++) {
+		/* create a page pool for each RQ */
+		pp_params.napi = &enic->napi[i];
+		pp_params.queue_idx = i;
+		enic->rq[i].pool = page_pool_create(&pp_params);
+		if (IS_ERR(enic->rq[i].pool)) {
+			err = PTR_ERR(enic->rq[i].pool);
+			enic->rq[i].pool = NULL;
+			goto err_out_free_rq;
+		}
+
 		/* enable rq before updating rq desc */
 		vnic_rq_enable(&enic->rq[i].vrq);
 		vnic_rq_fill(&enic->rq[i].vrq, enic_rq_alloc_buf);
@@ -2028,8 +1759,11 @@ static int enic_open(struct net_device *netdev)
 err_out_free_rq:
 	for (i = 0; i < enic->rq_count; i++) {
 		ret = vnic_rq_disable(&enic->rq[i].vrq);
-		if (!ret)
+		if (!ret) {
 			vnic_rq_clean(&enic->rq[i].vrq, enic_free_rq_buf);
+			page_pool_destroy(enic->rq[i].pool);
+			enic->rq[i].pool = NULL;
+		}
 	}
 	enic_dev_notify_unset(enic);
 err_out_free_intr:
@@ -2053,7 +1787,7 @@ static int enic_stop(struct net_device *netdev)
 
 	enic_synchronize_irqs(enic);
 
-	del_timer_sync(&enic->notify_timer);
+	timer_delete_sync(&enic->notify_timer);
 	enic_rfs_flw_tbl_free(enic);
 
 	enic_dev_disable(enic);
@@ -2087,8 +1821,11 @@ static int enic_stop(struct net_device *netdev)
 
 	for (i = 0; i < enic->wq_count; i++)
 		vnic_wq_clean(&enic->wq[i].vwq, enic_free_wq_buf);
-	for (i = 0; i < enic->rq_count; i++)
+	for (i = 0; i < enic->rq_count; i++) {
 		vnic_rq_clean(&enic->rq[i].vrq, enic_free_rq_buf);
+		page_pool_destroy(enic->rq[i].pool);
+		enic->rq[i].pool = NULL;
+	}
 	for (i = 0; i < enic->cq_count; i++)
 		vnic_cq_clean(&enic->cq[i]);
 	for (i = 0; i < enic->intr_count; i++)
@@ -2127,10 +1864,10 @@ static int enic_change_mtu(struct net_device *netdev, int new_mtu)
 	if (enic_is_dynamic(enic) || enic_is_sriov_vf(enic))
 		return -EOPNOTSUPP;
 
-	if (netdev->mtu > enic->port_mtu)
+	if (new_mtu > enic->port_mtu)
 		netdev_warn(netdev,
 			    "interface MTU (%d) set higher than port MTU (%d)\n",
-			    netdev->mtu, enic->port_mtu);
+			    new_mtu, enic->port_mtu);
 
 	return _enic_change_mtu(netdev, new_mtu);
 }
@@ -2404,6 +2141,7 @@ static void enic_reset(struct work_struct *work)
 	enic_init_vnic_resources(enic);
 	enic_set_rss_nic_cfg(enic);
 	enic_dev_set_ig_vlan_rewrite_mode(enic);
+	enic_ext_cq(enic);
 	enic_open(enic->netdev);
 
 	/* Allow infiniband to fiddle with the device again */
@@ -2430,6 +2168,7 @@ static void enic_tx_hang_reset(struct work_struct *work)
 	enic_init_vnic_resources(enic);
 	enic_set_rss_nic_cfg(enic);
 	enic_dev_set_ig_vlan_rewrite_mode(enic);
+	enic_ext_cq(enic);
 	enic_open(enic->netdev);
 
 	/* Allow infiniband to fiddle with the device again */
@@ -2557,7 +2296,8 @@ static int enic_adjust_resources(struct enic *enic)
 		 * used based on which resource is the most constrained
 		 */
 		wq_avail = min(enic->wq_avail, ENIC_WQ_MAX);
-		rq_default = netif_get_num_default_rss_queues();
+		rq_default = max(netif_get_num_default_rss_queues(),
+				 ENIC_RQ_MIN_DEFAULT);
 		rq_avail = min3(enic->rq_avail, ENIC_RQ_MAX, rq_default);
 		max_queues = min(enic->cq_avail,
 				 enic->intr_avail - ENIC_MSIX_RESERVED_INTR);
@@ -2598,6 +2338,7 @@ static void enic_get_queue_stats_rx(struct net_device *dev, int idx,
 	rxs->hw_drop_overruns = rqstats->pkt_truncated;
 	rxs->csum_unnecessary = rqstats->csum_unnecessary +
 				rqstats->csum_unnecessary_encap;
+	rxs->alloc_fail = rqstats->pp_alloc_fail;
 }
 
 static void enic_get_queue_stats_tx(struct net_device *dev, int idx,
@@ -2625,6 +2366,7 @@ static void enic_get_base_stats(struct net_device *dev,
 	rxs->hw_drops = 0;
 	rxs->hw_drop_overruns = 0;
 	rxs->csum_unnecessary = 0;
+	rxs->alloc_fail = 0;
 	txs->bytes = 0;
 	txs->packets = 0;
 	txs->csum_none = 0;
@@ -2802,6 +2544,8 @@ static int enic_dev_init(struct enic *enic)
 
 	enic_get_res_counts(enic);
 
+	enic_ext_cq(enic);
+
 	err = enic_alloc_enic_resources(enic);
 	if (err) {
 		dev_err(dev, "Failed to allocate enic resources\n");
@@ -3063,7 +2807,6 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	timer_setup(&enic->notify_timer, enic_notify_timer, 0);
 
 	enic_rfs_flw_tbl_init(enic);
-	enic_set_rx_coal_setting(enic);
 	INIT_WORK(&enic->reset, enic_reset);
 	INIT_WORK(&enic->tx_hang_reset, enic_tx_hang_reset);
 	INIT_WORK(&enic->change_mtu_work, enic_change_mtu_work);
@@ -3179,7 +2922,6 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_err(dev, "Cannot register net device, aborting\n");
 		goto err_out_dev_deinit;
 	}
-	enic->rx_copybreak = RX_COPYBREAK_DEFAULT;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/cisco/enic/enic_res.c b/drivers/net/ethernet/cisco/enic/enic_res.c
index 126125199833..bbd3143ed73e 100644
--- a/drivers/net/ethernet/cisco/enic/enic_res.c
+++ b/drivers/net/ethernet/cisco/enic/enic_res.c
@@ -59,31 +59,38 @@ int enic_get_vnic_config(struct enic *enic)
 	GET_CONFIG(intr_timer_usec);
 	GET_CONFIG(loop_tag);
 	GET_CONFIG(num_arfs);
+	GET_CONFIG(max_rq_ring);
+	GET_CONFIG(max_wq_ring);
+	GET_CONFIG(max_cq_ring);
+
+	if (!c->max_wq_ring)
+		c->max_wq_ring = ENIC_MAX_WQ_DESCS_DEFAULT;
+	if (!c->max_rq_ring)
+		c->max_rq_ring = ENIC_MAX_RQ_DESCS_DEFAULT;
+	if (!c->max_cq_ring)
+		c->max_cq_ring = ENIC_MAX_CQ_DESCS_DEFAULT;
 
 	c->wq_desc_count =
-		min_t(u32, ENIC_MAX_WQ_DESCS,
-		max_t(u32, ENIC_MIN_WQ_DESCS,
-		c->wq_desc_count));
+		min_t(u32, c->max_wq_ring,
+		      max_t(u32, ENIC_MIN_WQ_DESCS, c->wq_desc_count));
 	c->wq_desc_count &= 0xffffffe0; /* must be aligned to groups of 32 */
 
 	c->rq_desc_count =
-		min_t(u32, ENIC_MAX_RQ_DESCS,
-		max_t(u32, ENIC_MIN_RQ_DESCS,
-		c->rq_desc_count));
+		min_t(u32, c->max_rq_ring,
+		      max_t(u32, ENIC_MIN_RQ_DESCS, c->rq_desc_count));
 	c->rq_desc_count &= 0xffffffe0; /* must be aligned to groups of 32 */
 
 	if (c->mtu == 0)
 		c->mtu = 1500;
-	c->mtu = min_t(u16, ENIC_MAX_MTU,
-		max_t(u16, ENIC_MIN_MTU,
-		c->mtu));
+	c->mtu = min_t(u16, ENIC_MAX_MTU, max_t(u16, ENIC_MIN_MTU, c->mtu));
 
 	c->intr_timer_usec = min_t(u32, c->intr_timer_usec,
 		vnic_dev_get_intr_coal_timer_max(enic->vdev));
 
 	dev_info(enic_get_dev(enic),
-		"vNIC MAC addr %pM wq/rq %d/%d mtu %d\n",
-		enic->mac_addr, c->wq_desc_count, c->rq_desc_count, c->mtu);
+		 "vNIC MAC addr %pM wq/rq %d/%d max wq/rq/cq %d/%d/%d mtu %d\n",
+		 enic->mac_addr, c->wq_desc_count, c->rq_desc_count,
+		 c->max_wq_ring, c->max_rq_ring, c->max_cq_ring, c->mtu);
 
 	dev_info(enic_get_dev(enic), "vNIC csum tx/rx %s/%s "
 		"tso/lro %s/%s rss %s intr mode %s type %s timer %d usec "
@@ -312,6 +319,7 @@ void enic_init_vnic_resources(struct enic *enic)
 int enic_alloc_vnic_resources(struct enic *enic)
 {
 	enum vnic_dev_intr_mode intr_mode;
+	int rq_cq_desc_size;
 	unsigned int i;
 	int err;
 
@@ -326,6 +334,24 @@ int enic_alloc_vnic_resources(struct enic *enic)
 		intr_mode == VNIC_DEV_INTR_MODE_MSIX ? "MSI-X" :
 		"unknown");
 
+	switch (enic->ext_cq) {
+	case ENIC_RQ_CQ_ENTRY_SIZE_16:
+		rq_cq_desc_size = 16;
+		break;
+	case ENIC_RQ_CQ_ENTRY_SIZE_32:
+		rq_cq_desc_size = 32;
+		break;
+	case ENIC_RQ_CQ_ENTRY_SIZE_64:
+		rq_cq_desc_size = 64;
+		break;
+	default:
+		dev_err(enic_get_dev(enic),
+			"Unable to determine rq cq desc size: %d",
+			enic->ext_cq);
+		err = -ENODEV;
+		goto err_out;
+	}
+
 	/* Allocate queue resources
 	 */
 
@@ -348,8 +374,8 @@ int enic_alloc_vnic_resources(struct enic *enic)
 	for (i = 0; i < enic->cq_count; i++) {
 		if (i < enic->rq_count)
 			err = vnic_cq_alloc(enic->vdev, &enic->cq[i], i,
-				enic->config.rq_desc_count,
-				sizeof(struct cq_enet_rq_desc));
+					enic->config.rq_desc_count,
+					rq_cq_desc_size);
 		else
 			err = vnic_cq_alloc(enic->vdev, &enic->cq[i], i,
 				enic->config.wq_desc_count,
@@ -380,6 +406,39 @@ int enic_alloc_vnic_resources(struct enic *enic)
 
 err_out_cleanup:
 	enic_free_vnic_resources(enic);
-
+err_out:
 	return err;
 }
+
+/*
+ * CMD_CQ_ENTRY_SIZE_SET can fail on older hw generations that don't support
+ * that command
+ */
+void enic_ext_cq(struct enic *enic)
+{
+	u64 a0 = CMD_CQ_ENTRY_SIZE_SET, a1 = 0;
+	int wait = 1000;
+	int ret;
+
+	spin_lock_bh(&enic->devcmd_lock);
+	ret = vnic_dev_cmd(enic->vdev, CMD_CAPABILITY, &a0, &a1, wait);
+	if (ret || a0) {
+		dev_info(&enic->pdev->dev,
+			 "CMD_CQ_ENTRY_SIZE_SET not supported.");
+		enic->ext_cq = ENIC_RQ_CQ_ENTRY_SIZE_16;
+		goto out;
+	}
+	a1 &= VNIC_RQ_CQ_ENTRY_SIZE_ALL_BIT;
+	enic->ext_cq = fls(a1) - 1;
+	a0 = VNIC_RQ_ALL;
+	a1 = enic->ext_cq;
+	ret = vnic_dev_cmd(enic->vdev, CMD_CQ_ENTRY_SIZE_SET, &a0, &a1, wait);
+	if (ret) {
+		dev_info(&enic->pdev->dev, "CMD_CQ_ENTRY_SIZE_SET failed.");
+		enic->ext_cq = ENIC_RQ_CQ_ENTRY_SIZE_16;
+	}
+out:
+	spin_unlock_bh(&enic->devcmd_lock);
+	dev_info(&enic->pdev->dev, "CQ entry size set to %d bytes",
+		 16 << enic->ext_cq);
+}
diff --git a/drivers/net/ethernet/cisco/enic/enic_res.h b/drivers/net/ethernet/cisco/enic/enic_res.h
index b8ee42d297aa..02dca1ae4a22 100644
--- a/drivers/net/ethernet/cisco/enic/enic_res.h
+++ b/drivers/net/ethernet/cisco/enic/enic_res.h
@@ -12,10 +12,13 @@
 #include "vnic_wq.h"
 #include "vnic_rq.h"
 
-#define ENIC_MIN_WQ_DESCS		64
-#define ENIC_MAX_WQ_DESCS		4096
-#define ENIC_MIN_RQ_DESCS		64
-#define ENIC_MAX_RQ_DESCS		4096
+#define ENIC_MIN_WQ_DESCS 64
+#define ENIC_MAX_WQ_DESCS_DEFAULT 4096
+#define ENIC_MAX_WQ_DESCS 16384
+#define ENIC_MIN_RQ_DESCS 64
+#define ENIC_MAX_RQ_DESCS 16384
+#define ENIC_MAX_RQ_DESCS_DEFAULT 4096
+#define ENIC_MAX_CQ_DESCS_DEFAULT (64 * 1024)
 
 #define ENIC_MIN_MTU			ETH_MIN_MTU
 #define ENIC_MAX_MTU			9000
diff --git a/drivers/net/ethernet/cisco/enic/enic_rq.c b/drivers/net/ethernet/cisco/enic/enic_rq.c
new file mode 100644
index 000000000000..ccbf5c9a21d0
--- /dev/null
+++ b/drivers/net/ethernet/cisco/enic/enic_rq.c
@@ -0,0 +1,436 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright 2024 Cisco Systems, Inc.  All rights reserved.
+
+#include <linux/skbuff.h>
+#include <linux/if_vlan.h>
+#include <net/busy_poll.h>
+#include "enic.h"
+#include "enic_res.h"
+#include "enic_rq.h"
+#include "vnic_rq.h"
+#include "cq_enet_desc.h"
+
+#define ENIC_LARGE_PKT_THRESHOLD                1000
+
+static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size,
+				      u32 pkt_len)
+{
+	if (pkt_len > ENIC_LARGE_PKT_THRESHOLD)
+		pkt_size->large_pkt_bytes_cnt += pkt_len;
+	else
+		pkt_size->small_pkt_bytes_cnt += pkt_len;
+}
+
+static void enic_rq_cq_desc_dec(void *cq_desc, u8 cq_desc_size, u8 *type,
+				u8 *color, u16 *q_number, u16 *completed_index)
+{
+	/* type_color is the last field for all cq structs */
+	u8 type_color;
+
+	switch (cq_desc_size) {
+	case VNIC_RQ_CQ_ENTRY_SIZE_16: {
+		struct cq_enet_rq_desc *desc =
+			(struct cq_enet_rq_desc *)cq_desc;
+		type_color = desc->type_color;
+
+		/* Make sure color bit is read from desc *before* other fields
+		 * are read from desc.  Hardware guarantees color bit is last
+		 * bit (byte) written.  Adding the rmb() prevents the compiler
+		 * and/or CPU from reordering the reads which would potentially
+		 * result in reading stale values.
+		 */
+		rmb();
+
+		*q_number = le16_to_cpu(desc->q_number_rss_type_flags) &
+			    CQ_DESC_Q_NUM_MASK;
+		*completed_index = le16_to_cpu(desc->completed_index_flags) &
+				   CQ_DESC_COMP_NDX_MASK;
+		break;
+	}
+	case VNIC_RQ_CQ_ENTRY_SIZE_32: {
+		struct cq_enet_rq_desc_32 *desc =
+			(struct cq_enet_rq_desc_32 *)cq_desc;
+		type_color = desc->type_color;
+
+		/* Make sure color bit is read from desc *before* other fields
+		 * are read from desc.  Hardware guarantees color bit is last
+		 * bit (byte) written.  Adding the rmb() prevents the compiler
+		 * and/or CPU from reordering the reads which would potentially
+		 * result in reading stale values.
+		 */
+		rmb();
+
+		*q_number = le16_to_cpu(desc->q_number_rss_type_flags) &
+			    CQ_DESC_Q_NUM_MASK;
+		*completed_index = le16_to_cpu(desc->completed_index_flags) &
+				   CQ_DESC_COMP_NDX_MASK;
+		*completed_index |= (desc->fetch_index_flags & CQ_DESC_32_FI_MASK) <<
+				CQ_DESC_COMP_NDX_BITS;
+		break;
+	}
+	case VNIC_RQ_CQ_ENTRY_SIZE_64: {
+		struct cq_enet_rq_desc_64 *desc =
+			(struct cq_enet_rq_desc_64 *)cq_desc;
+		type_color = desc->type_color;
+
+		/* Make sure color bit is read from desc *before* other fields
+		 * are read from desc.  Hardware guarantees color bit is last
+		 * bit (byte) written.  Adding the rmb() prevents the compiler
+		 * and/or CPU from reordering the reads which would potentially
+		 * result in reading stale values.
+		 */
+		rmb();
+
+		*q_number = le16_to_cpu(desc->q_number_rss_type_flags) &
+			    CQ_DESC_Q_NUM_MASK;
+		*completed_index = le16_to_cpu(desc->completed_index_flags) &
+				   CQ_DESC_COMP_NDX_MASK;
+		*completed_index |= (desc->fetch_index_flags & CQ_DESC_64_FI_MASK) <<
+				CQ_DESC_COMP_NDX_BITS;
+		break;
+	}
+	}
+
+	*color = (type_color >> CQ_DESC_COLOR_SHIFT) & CQ_DESC_COLOR_MASK;
+	*type = type_color & CQ_DESC_TYPE_MASK;
+}
+
+static void enic_rq_set_skb_flags(struct vnic_rq *vrq, u8 type, u32 rss_hash,
+				  u8 rss_type, u8 fcoe, u8 fcoe_fc_crc_ok,
+				  u8 vlan_stripped, u8 csum_not_calc,
+				  u8 tcp_udp_csum_ok, u8 ipv6, u8 ipv4_csum_ok,
+				  u16 vlan_tci, struct sk_buff *skb)
+{
+	struct enic *enic = vnic_dev_priv(vrq->vdev);
+	struct net_device *netdev = enic->netdev;
+	struct enic_rq_stats *rqstats =  &enic->rq[vrq->index].stats;
+	bool outer_csum_ok = true, encap = false;
+
+	if ((netdev->features & NETIF_F_RXHASH) && rss_hash && type == 3) {
+		switch (rss_type) {
+		case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv4:
+		case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6:
+		case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6_EX:
+			skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L4);
+			rqstats->l4_rss_hash++;
+			break;
+		case CQ_ENET_RQ_DESC_RSS_TYPE_IPv4:
+		case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6:
+		case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6_EX:
+			skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L3);
+			rqstats->l3_rss_hash++;
+			break;
+		}
+	}
+	if (enic->vxlan.vxlan_udp_port_number) {
+		switch (enic->vxlan.patch_level) {
+		case 0:
+			if (fcoe) {
+				encap = true;
+				outer_csum_ok = fcoe_fc_crc_ok;
+			}
+			break;
+		case 2:
+			if (type == 7 && (rss_hash & BIT(0))) {
+				encap = true;
+				outer_csum_ok = (rss_hash & BIT(1)) &&
+						(rss_hash & BIT(2));
+			}
+			break;
+		}
+	}
+
+	/* Hardware does not provide whole packet checksum. It only
+	 * provides pseudo checksum. Since hw validates the packet
+	 * checksum but not provide us the checksum value. use
+	 * CHECSUM_UNNECESSARY.
+	 *
+	 * In case of encap pkt tcp_udp_csum_ok/tcp_udp_csum_ok is
+	 * inner csum_ok. outer_csum_ok is set by hw when outer udp
+	 * csum is correct or is zero.
+	 */
+	if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc &&
+	    tcp_udp_csum_ok && outer_csum_ok && (ipv4_csum_ok || ipv6)) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		skb->csum_level = encap;
+		if (encap)
+			rqstats->csum_unnecessary_encap++;
+		else
+			rqstats->csum_unnecessary++;
+	}
+
+	if (vlan_stripped) {
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
+		rqstats->vlan_stripped++;
+	}
+}
+
+/*
+ * cq_enet_rq_desc accesses section uses only the 1st 15 bytes of the cq which
+ * is identical for all type (16,32 and 64 byte) of cqs.
+ */
+static void cq_enet_rq_desc_dec(struct cq_enet_rq_desc *desc, u8 *ingress_port,
+				u8 *fcoe, u8 *eop, u8 *sop, u8 *rss_type,
+				u8 *csum_not_calc, u32 *rss_hash,
+				u16 *bytes_written, u8 *packet_error,
+				u8 *vlan_stripped, u16 *vlan_tci,
+				u16 *checksum, u8 *fcoe_sof,
+				u8 *fcoe_fc_crc_ok, u8 *fcoe_enc_error,
+				u8 *fcoe_eof, u8 *tcp_udp_csum_ok, u8 *udp,
+				u8 *tcp, u8 *ipv4_csum_ok, u8 *ipv6, u8 *ipv4,
+				u8 *ipv4_fragment, u8 *fcs_ok)
+{
+	u16 completed_index_flags;
+	u16 q_number_rss_type_flags;
+	u16 bytes_written_flags;
+
+	completed_index_flags = le16_to_cpu(desc->completed_index_flags);
+	q_number_rss_type_flags =
+		le16_to_cpu(desc->q_number_rss_type_flags);
+	bytes_written_flags = le16_to_cpu(desc->bytes_written_flags);
+
+	*ingress_port = (completed_index_flags &
+		CQ_ENET_RQ_DESC_FLAGS_INGRESS_PORT) ? 1 : 0;
+	*fcoe = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_FCOE) ?
+		1 : 0;
+	*eop = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_EOP) ?
+		1 : 0;
+	*sop = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_SOP) ?
+		1 : 0;
+
+	*rss_type = (u8)((q_number_rss_type_flags >> CQ_DESC_Q_NUM_BITS) &
+		CQ_ENET_RQ_DESC_RSS_TYPE_MASK);
+	*csum_not_calc = (q_number_rss_type_flags &
+		CQ_ENET_RQ_DESC_FLAGS_CSUM_NOT_CALC) ? 1 : 0;
+
+	*rss_hash = le32_to_cpu(desc->rss_hash);
+
+	*bytes_written = bytes_written_flags &
+		CQ_ENET_RQ_DESC_BYTES_WRITTEN_MASK;
+	*packet_error = (bytes_written_flags &
+		CQ_ENET_RQ_DESC_FLAGS_TRUNCATED) ? 1 : 0;
+	*vlan_stripped = (bytes_written_flags &
+		CQ_ENET_RQ_DESC_FLAGS_VLAN_STRIPPED) ? 1 : 0;
+
+	/*
+	 * Tag Control Information(16) = user_priority(3) + cfi(1) + vlan(12)
+	 */
+	*vlan_tci = le16_to_cpu(desc->vlan);
+
+	if (*fcoe) {
+		*fcoe_sof = (u8)(le16_to_cpu(desc->checksum_fcoe) &
+			CQ_ENET_RQ_DESC_FCOE_SOF_MASK);
+		*fcoe_fc_crc_ok = (desc->flags &
+			CQ_ENET_RQ_DESC_FCOE_FC_CRC_OK) ? 1 : 0;
+		*fcoe_enc_error = (desc->flags &
+			CQ_ENET_RQ_DESC_FCOE_ENC_ERROR) ? 1 : 0;
+		*fcoe_eof = (u8)((le16_to_cpu(desc->checksum_fcoe) >>
+			CQ_ENET_RQ_DESC_FCOE_EOF_SHIFT) &
+			CQ_ENET_RQ_DESC_FCOE_EOF_MASK);
+		*checksum = 0;
+	} else {
+		*fcoe_sof = 0;
+		*fcoe_fc_crc_ok = 0;
+		*fcoe_enc_error = 0;
+		*fcoe_eof = 0;
+		*checksum = le16_to_cpu(desc->checksum_fcoe);
+	}
+
+	*tcp_udp_csum_ok =
+		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_TCP_UDP_CSUM_OK) ? 1 : 0;
+	*udp = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_UDP) ? 1 : 0;
+	*tcp = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_TCP) ? 1 : 0;
+	*ipv4_csum_ok =
+		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4_CSUM_OK) ? 1 : 0;
+	*ipv6 = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV6) ? 1 : 0;
+	*ipv4 = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4) ? 1 : 0;
+	*ipv4_fragment =
+		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4_FRAGMENT) ? 1 : 0;
+	*fcs_ok = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_FCS_OK) ? 1 : 0;
+}
+
+static bool enic_rq_pkt_error(struct vnic_rq *vrq, u8 packet_error, u8 fcs_ok,
+			      u16 bytes_written)
+{
+	struct enic *enic = vnic_dev_priv(vrq->vdev);
+	struct enic_rq_stats *rqstats = &enic->rq[vrq->index].stats;
+
+	if (packet_error) {
+		if (!fcs_ok) {
+			if (bytes_written > 0)
+				rqstats->bad_fcs++;
+			else if (bytes_written == 0)
+				rqstats->pkt_truncated++;
+		}
+		return true;
+	}
+	return false;
+}
+
+int enic_rq_alloc_buf(struct vnic_rq *rq)
+{
+	struct enic *enic = vnic_dev_priv(rq->vdev);
+	struct net_device *netdev = enic->netdev;
+	struct enic_rq *erq = &enic->rq[rq->index];
+	struct enic_rq_stats *rqstats = &erq->stats;
+	unsigned int offset = 0;
+	unsigned int len = netdev->mtu + VLAN_ETH_HLEN;
+	unsigned int os_buf_index = 0;
+	dma_addr_t dma_addr;
+	struct vnic_rq_buf *buf = rq->to_use;
+	struct page *page;
+	unsigned int truesize = len;
+
+	if (buf->os_buf) {
+		enic_queue_rq_desc(rq, buf->os_buf, os_buf_index, buf->dma_addr,
+				   buf->len);
+
+		return 0;
+	}
+
+	page = page_pool_dev_alloc(erq->pool, &offset, &truesize);
+	if (unlikely(!page)) {
+		rqstats->pp_alloc_fail++;
+		return -ENOMEM;
+	}
+	buf->offset = offset;
+	buf->truesize = truesize;
+	dma_addr = page_pool_get_dma_addr(page) + offset;
+	enic_queue_rq_desc(rq, (void *)page, os_buf_index, dma_addr, len);
+
+	return 0;
+}
+
+void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf)
+{
+	struct enic *enic = vnic_dev_priv(rq->vdev);
+	struct enic_rq *erq = &enic->rq[rq->index];
+
+	if (!buf->os_buf)
+		return;
+
+	page_pool_put_full_page(erq->pool, (struct page *)buf->os_buf, true);
+	buf->os_buf = NULL;
+}
+
+static void enic_rq_indicate_buf(struct enic *enic, struct vnic_rq *rq,
+				 struct vnic_rq_buf *buf, void *cq_desc,
+				 u8 type, u16 q_number, u16 completed_index)
+{
+	struct sk_buff *skb;
+	struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)];
+	struct enic_rq_stats *rqstats = &enic->rq[rq->index].stats;
+	struct napi_struct *napi;
+
+	u8 eop, sop, ingress_port, vlan_stripped;
+	u8 fcoe, fcoe_sof, fcoe_fc_crc_ok, fcoe_enc_error, fcoe_eof;
+	u8 tcp_udp_csum_ok, udp, tcp, ipv4_csum_ok;
+	u8 ipv6, ipv4, ipv4_fragment, fcs_ok, rss_type, csum_not_calc;
+	u8 packet_error;
+	u16 bytes_written, vlan_tci, checksum;
+	u32 rss_hash;
+
+	rqstats->packets++;
+
+	cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc, &ingress_port,
+			    &fcoe, &eop, &sop, &rss_type, &csum_not_calc,
+			    &rss_hash, &bytes_written, &packet_error,
+			    &vlan_stripped, &vlan_tci, &checksum, &fcoe_sof,
+			    &fcoe_fc_crc_ok, &fcoe_enc_error, &fcoe_eof,
+			    &tcp_udp_csum_ok, &udp, &tcp, &ipv4_csum_ok, &ipv6,
+			    &ipv4, &ipv4_fragment, &fcs_ok);
+
+	if (enic_rq_pkt_error(rq, packet_error, fcs_ok, bytes_written))
+		return;
+
+	if (eop && bytes_written > 0) {
+		/* Good receive
+		 */
+		rqstats->bytes += bytes_written;
+		napi = &enic->napi[rq->index];
+		skb = napi_get_frags(napi);
+		if (unlikely(!skb)) {
+			net_warn_ratelimited("%s: skb alloc error rq[%d], desc[%d]\n",
+					     enic->netdev->name, rq->index,
+					     completed_index);
+			rqstats->no_skb++;
+			return;
+		}
+
+		prefetch(skb->data - NET_IP_ALIGN);
+
+		dma_sync_single_for_cpu(&enic->pdev->dev, buf->dma_addr,
+					bytes_written, DMA_FROM_DEVICE);
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				(struct page *)buf->os_buf, buf->offset,
+				bytes_written, buf->truesize);
+		skb_record_rx_queue(skb, q_number);
+		enic_rq_set_skb_flags(rq, type, rss_hash, rss_type, fcoe,
+				      fcoe_fc_crc_ok, vlan_stripped,
+				      csum_not_calc, tcp_udp_csum_ok, ipv6,
+				      ipv4_csum_ok, vlan_tci, skb);
+		skb_mark_for_recycle(skb);
+		napi_gro_frags(napi);
+		if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce)
+			enic_intr_update_pkt_size(&cq->pkt_size_counter,
+						  bytes_written);
+		buf->os_buf = NULL;
+		buf->dma_addr = 0;
+		buf = buf->next;
+	} else {
+		/* Buffer overflow
+		 */
+		rqstats->pkt_truncated++;
+	}
+}
+
+static void enic_rq_service(struct enic *enic, void *cq_desc, u8 type,
+			    u16 q_number, u16 completed_index)
+{
+	struct enic_rq_stats *rqstats = &enic->rq[q_number].stats;
+	struct vnic_rq *vrq = &enic->rq[q_number].vrq;
+	struct vnic_rq_buf *vrq_buf = vrq->to_clean;
+	int skipped;
+
+	while (1) {
+		skipped = (vrq_buf->index != completed_index);
+		if (!skipped)
+			enic_rq_indicate_buf(enic, vrq, vrq_buf, cq_desc, type,
+					     q_number, completed_index);
+		else
+			rqstats->desc_skip++;
+
+		vrq->ring.desc_avail++;
+		vrq->to_clean = vrq_buf->next;
+		vrq_buf = vrq_buf->next;
+		if (!skipped)
+			break;
+	}
+}
+
+unsigned int enic_rq_cq_service(struct enic *enic, unsigned int cq_index,
+				unsigned int work_to_do)
+{
+	struct vnic_cq *cq = &enic->cq[cq_index];
+	void *cq_desc = vnic_cq_to_clean(cq);
+	u16 q_number, completed_index;
+	unsigned int work_done = 0;
+	u8 type, color;
+
+	enic_rq_cq_desc_dec(cq_desc, enic->ext_cq, &type, &color, &q_number,
+			    &completed_index);
+
+	while (color != cq->last_color) {
+		enic_rq_service(enic, cq_desc, type, q_number, completed_index);
+		vnic_cq_inc_to_clean(cq);
+
+		if (++work_done >= work_to_do)
+			break;
+
+		cq_desc = vnic_cq_to_clean(cq);
+		enic_rq_cq_desc_dec(cq_desc, enic->ext_cq, &type, &color,
+				    &q_number, &completed_index);
+	}
+
+	return work_done;
+}
diff --git a/drivers/net/ethernet/cisco/enic/enic_rq.h b/drivers/net/ethernet/cisco/enic/enic_rq.h
new file mode 100644
index 000000000000..98476a7297af
--- /dev/null
+++ b/drivers/net/ethernet/cisco/enic/enic_rq.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright 2024 Cisco Systems, Inc.  All rights reserved.
+ */
+
+unsigned int enic_rq_cq_service(struct enic *enic, unsigned int cq_index,
+				unsigned int work_to_do);
+int enic_rq_alloc_buf(struct vnic_rq *rq);
+void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf);
diff --git a/drivers/net/ethernet/cisco/enic/enic_wq.c b/drivers/net/ethernet/cisco/enic/enic_wq.c
new file mode 100644
index 000000000000..07936f8b4231
--- /dev/null
+++ b/drivers/net/ethernet/cisco/enic/enic_wq.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright 2025 Cisco Systems, Inc.  All rights reserved.
+
+#include <net/netdev_queues.h>
+#include "enic_res.h"
+#include "enic.h"
+#include "enic_wq.h"
+
+#define ENET_CQ_DESC_COMP_NDX_BITS 14
+#define ENET_CQ_DESC_COMP_NDX_MASK GENMASK(ENET_CQ_DESC_COMP_NDX_BITS - 1, 0)
+
+static void enic_wq_cq_desc_dec(const struct cq_desc *desc_arg, bool ext_wq,
+				u8 *type, u8 *color, u16 *q_number,
+				u16 *completed_index)
+{
+	const struct cq_desc *desc = desc_arg;
+	const u8 type_color = desc->type_color;
+
+	*color = (type_color >> CQ_DESC_COLOR_SHIFT) & CQ_DESC_COLOR_MASK;
+
+	/*
+	 * Make sure color bit is read from desc *before* other fields
+	 * are read from desc.  Hardware guarantees color bit is last
+	 * bit (byte) written.  Adding the rmb() prevents the compiler
+	 * and/or CPU from reordering the reads which would potentially
+	 * result in reading stale values.
+	 */
+	rmb();
+
+	*type = type_color & CQ_DESC_TYPE_MASK;
+	*q_number = le16_to_cpu(desc->q_number) & CQ_DESC_Q_NUM_MASK;
+
+	if (ext_wq)
+		*completed_index = le16_to_cpu(desc->completed_index) &
+			ENET_CQ_DESC_COMP_NDX_MASK;
+	else
+		*completed_index = le16_to_cpu(desc->completed_index) &
+			CQ_DESC_COMP_NDX_MASK;
+}
+
+void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf)
+{
+	struct enic *enic = vnic_dev_priv(wq->vdev);
+
+	if (buf->sop)
+		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
+				 DMA_TO_DEVICE);
+	else
+		dma_unmap_page(&enic->pdev->dev, buf->dma_addr, buf->len,
+			       DMA_TO_DEVICE);
+
+	if (buf->os_buf)
+		dev_kfree_skb_any(buf->os_buf);
+}
+
+static void enic_wq_free_buf(struct vnic_wq *wq, struct cq_desc *cq_desc,
+			     struct vnic_wq_buf *buf, void *opaque)
+{
+	struct enic *enic = vnic_dev_priv(wq->vdev);
+
+	enic->wq[wq->index].stats.cq_work++;
+	enic->wq[wq->index].stats.cq_bytes += buf->len;
+	enic_free_wq_buf(wq, buf);
+}
+
+static void enic_wq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc,
+			    u8 type, u16 q_number, u16 completed_index)
+{
+	struct enic *enic = vnic_dev_priv(vdev);
+
+	spin_lock(&enic->wq[q_number].lock);
+
+	vnic_wq_service(&enic->wq[q_number].vwq, cq_desc,
+			completed_index, enic_wq_free_buf, NULL);
+
+	if (netif_tx_queue_stopped(netdev_get_tx_queue(enic->netdev, q_number))
+	    && vnic_wq_desc_avail(&enic->wq[q_number].vwq) >=
+	    (MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS)) {
+		netif_wake_subqueue(enic->netdev, q_number);
+		enic->wq[q_number].stats.wake++;
+	}
+
+	spin_unlock(&enic->wq[q_number].lock);
+}
+
+unsigned int enic_wq_cq_service(struct enic *enic, unsigned int cq_index,
+				unsigned int work_to_do)
+{
+	struct vnic_cq *cq = &enic->cq[cq_index];
+	u16 q_number, completed_index;
+	unsigned int work_done = 0;
+	struct cq_desc *cq_desc;
+	u8 type, color;
+	bool ext_wq;
+
+	ext_wq = cq->ring.size > ENIC_MAX_WQ_DESCS_DEFAULT;
+
+	cq_desc = (struct cq_desc *)vnic_cq_to_clean(cq);
+	enic_wq_cq_desc_dec(cq_desc, ext_wq, &type, &color,
+			    &q_number, &completed_index);
+
+	while (color != cq->last_color) {
+		enic_wq_service(cq->vdev, cq_desc, type, q_number,
+				completed_index);
+
+		vnic_cq_inc_to_clean(cq);
+
+		if (++work_done >= work_to_do)
+			break;
+
+		cq_desc = (struct cq_desc *)vnic_cq_to_clean(cq);
+		enic_wq_cq_desc_dec(cq_desc, ext_wq, &type, &color,
+				    &q_number, &completed_index);
+	}
+
+	return work_done;
+}
diff --git a/drivers/net/ethernet/cisco/enic/enic_wq.h b/drivers/net/ethernet/cisco/enic/enic_wq.h
new file mode 100644
index 000000000000..12acb3f2fbc9
--- /dev/null
+++ b/drivers/net/ethernet/cisco/enic/enic_wq.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright 2025 Cisco Systems, Inc.  All rights reserved.
+ */
+
+void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf);
+unsigned int enic_wq_cq_service(struct enic *enic, unsigned int cq_index,
+				unsigned int work_to_do);
diff --git a/drivers/net/ethernet/cisco/enic/vnic_cq.h b/drivers/net/ethernet/cisco/enic/vnic_cq.h
index eed5bf59e5d2..0e37f5d5e527 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_cq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_cq.h
@@ -56,45 +56,18 @@ struct vnic_cq {
 	ktime_t prev_ts;
 };
 
-static inline unsigned int vnic_cq_service(struct vnic_cq *cq,
-	unsigned int work_to_do,
-	int (*q_service)(struct vnic_dev *vdev, struct cq_desc *cq_desc,
-	u8 type, u16 q_number, u16 completed_index, void *opaque),
-	void *opaque)
+static inline void *vnic_cq_to_clean(struct vnic_cq *cq)
 {
-	struct cq_desc *cq_desc;
-	unsigned int work_done = 0;
-	u16 q_number, completed_index;
-	u8 type, color;
-
-	cq_desc = (struct cq_desc *)((u8 *)cq->ring.descs +
-		cq->ring.desc_size * cq->to_clean);
-	cq_desc_dec(cq_desc, &type, &color,
-		&q_number, &completed_index);
-
-	while (color != cq->last_color) {
-
-		if ((*q_service)(cq->vdev, cq_desc, type,
-			q_number, completed_index, opaque))
-			break;
-
-		cq->to_clean++;
-		if (cq->to_clean == cq->ring.desc_count) {
-			cq->to_clean = 0;
-			cq->last_color = cq->last_color ? 0 : 1;
-		}
-
-		cq_desc = (struct cq_desc *)((u8 *)cq->ring.descs +
-			cq->ring.desc_size * cq->to_clean);
-		cq_desc_dec(cq_desc, &type, &color,
-			&q_number, &completed_index);
+	return ((u8 *)cq->ring.descs + cq->ring.desc_size * cq->to_clean);
+}
 
-		work_done++;
-		if (work_done >= work_to_do)
-			break;
+static inline void vnic_cq_inc_to_clean(struct vnic_cq *cq)
+{
+	cq->to_clean++;
+	if (cq->to_clean == cq->ring.desc_count) {
+		cq->to_clean = 0;
+		cq->last_color = cq->last_color ? 0 : 1;
 	}
-
-	return work_done;
 }
 
 void vnic_cq_free(struct vnic_cq *cq);
diff --git a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h
index db56d778877a..605ef17f967e 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h
@@ -436,6 +436,25 @@ enum vnic_devcmd_cmd {
 	 * in: (u16) a2 = unsigned short int port information
 	 */
 	CMD_OVERLAY_OFFLOAD_CFG = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 73),
+
+	/*
+	 * Set extended CQ field in MREGS of RQ (or all RQs)
+	 * for given vNIC
+	 * in: (u64) a0 = RQ selection (VNIC_RQ_ALL for all RQs)
+	 *     (u32) a1 = CQ entry size
+	 *         VNIC_RQ_CQ_ENTRY_SIZE_16 --> 16 bytes
+	 *         VNIC_RQ_CQ_ENTRY_SIZE_32 --> 32 bytes
+	 *         VNIC_RQ_CQ_ENTRY_SIZE_64 --> 64 bytes
+	 *
+	 * Capability query:
+	 * out: (u32) a0 = errno, 0:valid cmd
+	 *      (u32) a1 = value consisting of supported entries
+	 *         bit 0: 16 bytes
+	 *         bit 1: 32 bytes
+	 *         bit 2: 64 bytes
+	 */
+	CMD_CQ_ENTRY_SIZE_SET = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 90),
+
 };
 
 /* CMD_ENABLE2 flags */
diff --git a/drivers/net/ethernet/cisco/enic/vnic_enet.h b/drivers/net/ethernet/cisco/enic/vnic_enet.h
index 5acc236069de..9e8e86262a3f 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_enet.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_enet.h
@@ -21,6 +21,11 @@ struct vnic_enet_config {
 	u16 loop_tag;
 	u16 vf_rq_count;
 	u16 num_arfs;
+	u8 reserved[66];
+	u32 max_rq_ring;	// MAX RQ ring size
+	u32 max_wq_ring;	// MAX WQ ring size
+	u32 max_cq_ring;	// MAX CQ ring size
+	u32 rdma_rsvd_lkey;	// Reserved (privileged) LKey
 };
 
 #define VENETF_TSO		0x1	/* TSO enabled */
diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.h b/drivers/net/ethernet/cisco/enic/vnic_rq.h
index 0bc595abc03b..a1cdd729caec 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_rq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_rq.h
@@ -50,7 +50,7 @@ struct vnic_rq_ctrl {
 	(VNIC_RQ_BUF_BLK_ENTRIES(entries) * sizeof(struct vnic_rq_buf))
 #define VNIC_RQ_BUF_BLKS_NEEDED(entries) \
 	DIV_ROUND_UP(entries, VNIC_RQ_BUF_BLK_ENTRIES(entries))
-#define VNIC_RQ_BUF_BLKS_MAX VNIC_RQ_BUF_BLKS_NEEDED(4096)
+#define VNIC_RQ_BUF_BLKS_MAX VNIC_RQ_BUF_BLKS_NEEDED(16384)
 
 struct vnic_rq_buf {
 	struct vnic_rq_buf *next;
@@ -61,6 +61,8 @@ struct vnic_rq_buf {
 	unsigned int index;
 	void *desc;
 	uint64_t wr_id;
+	unsigned int offset;
+	unsigned int truesize;
 };
 
 enum enic_poll_state {
diff --git a/drivers/net/ethernet/cisco/enic/vnic_wq.h b/drivers/net/ethernet/cisco/enic/vnic_wq.h
index 75c526911074..3bb4758100ba 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_wq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_wq.h
@@ -62,7 +62,7 @@ struct vnic_wq_buf {
 	(VNIC_WQ_BUF_BLK_ENTRIES(entries) * sizeof(struct vnic_wq_buf))
 #define VNIC_WQ_BUF_BLKS_NEEDED(entries) \
 	DIV_ROUND_UP(entries, VNIC_WQ_BUF_BLK_ENTRIES(entries))
-#define VNIC_WQ_BUF_BLKS_MAX VNIC_WQ_BUF_BLKS_NEEDED(4096)
+#define VNIC_WQ_BUF_BLKS_MAX VNIC_WQ_BUF_BLKS_NEEDED(16384)
 
 struct vnic_wq {
 	unsigned int index;
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 991e3839858b..6a2004bbe87f 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -40,6 +40,7 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <net/gro.h>
 
 #include "gemini.h"
 
@@ -1143,6 +1144,7 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 	struct gmac_txdesc *txd;
 	skb_frag_t *skb_frag;
 	dma_addr_t mapping;
+	bool tcp = false;
 	void *buffer;
 	u16 mss;
 	int ret;
@@ -1150,6 +1152,13 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 	word1 = skb->len;
 	word3 = SOF_BIT;
 
+	/* Determine if we are doing TCP */
+	if (skb->protocol == htons(ETH_P_IP))
+		tcp = (ip_hdr(skb)->protocol == IPPROTO_TCP);
+	else
+		/* IPv6 */
+		tcp = (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP);
+
 	mss = skb_shinfo(skb)->gso_size;
 	if (mss) {
 		/* This means we are dealing with TCP and skb->len is the
@@ -1162,8 +1171,26 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 			   mss, skb->len);
 		word1 |= TSS_MTU_ENABLE_BIT;
 		word3 |= mss;
+	} else if (tcp) {
+		/* Even if we are not using TSO, use the hardware offloader
+		 * for transferring the TCP frame: this hardware has partial
+		 * TCP awareness (called TOE - TCP Offload Engine) and will
+		 * according to the datasheet put packets belonging to the
+		 * same TCP connection in the same queue for the TOE/TSO
+		 * engine to process. The engine will deal with chopping
+		 * up frames that exceed ETH_DATA_LEN which the
+		 * checksumming engine cannot handle (see below) into
+		 * manageable chunks. It flawlessly deals with quite big
+		 * frames and frames containing custom DSA EtherTypes.
+		 */
+		mss = netdev->mtu + skb_tcp_all_headers(skb);
+		mss = min(mss, skb->len);
+		netdev_dbg(netdev, "TOE/TSO len %04x mtu %04x mss %04x\n",
+			   skb->len, netdev->mtu, mss);
+		word1 |= TSS_MTU_ENABLE_BIT;
+		word3 |= mss;
 	} else if (skb->len >= ETH_FRAME_LEN) {
-		/* Hardware offloaded checksumming isn't working on frames
+		/* Hardware offloaded checksumming isn't working on non-TCP frames
 		 * bigger than 1514 bytes. A hypothesis about this is that the
 		 * checksum buffer is only 1518 bytes, so when the frames get
 		 * bigger they get truncated, or the last few bytes get
@@ -1180,21 +1207,16 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 	}
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		int tcp = 0;
-
 		/* We do not switch off the checksumming on non TCP/UDP
 		 * frames: as is shown from tests, the checksumming engine
 		 * is smart enough to see that a frame is not actually TCP
 		 * or UDP and then just pass it through without any changes
 		 * to the frame.
 		 */
-		if (skb->protocol == htons(ETH_P_IP)) {
+		if (skb->protocol == htons(ETH_P_IP))
 			word1 |= TSS_IP_CHKSUM_BIT;
-			tcp = ip_hdr(skb)->protocol == IPPROTO_TCP;
-		} else { /* IPv6 */
+		else
 			word1 |= TSS_IPV6_ENABLE_BIT;
-			tcp = ipv6_hdr(skb)->nexthdr == IPPROTO_TCP;
-		}
 
 		word1 |= tcp ? TSS_TCP_CHKSUM_BIT : TSS_UDP_CHKSUM_BIT;
 	}
@@ -1833,9 +1855,8 @@ static int gmac_open(struct net_device *netdev)
 	gmac_enable_tx_rx(netdev);
 	netif_tx_start_all_queues(netdev);
 
-	hrtimer_init(&port->rx_coalesce_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
-	port->rx_coalesce_timer.function = &gmac_coalesce_delay_expired;
+	hrtimer_setup(&port->rx_coalesce_timer, &gmac_coalesce_delay_expired, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	netdev_dbg(netdev, "opened\n");
 
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 8735e333034c..b87eaf0c250c 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1777,10 +1777,11 @@ static void dm9000_drv_remove(struct platform_device *pdev)
 
 	unregister_netdev(ndev);
 	dm9000_release_board(pdev, dm);
-	free_netdev(ndev);		/* free device structure */
 	if (dm->power_supply)
 		regulator_disable(dm->power_supply);
 
+	free_netdev(ndev);		/* free device structure */
+
 	dev_dbg(&pdev->dev, "released and freed device\n");
 }
 
diff --git a/drivers/net/ethernet/dec/tulip/21142.c b/drivers/net/ethernet/dec/tulip/21142.c
index 369858272650..76767dec216d 100644
--- a/drivers/net/ethernet/dec/tulip/21142.c
+++ b/drivers/net/ethernet/dec/tulip/21142.c
@@ -216,7 +216,7 @@ void t21142_lnk_change(struct net_device *dev, int csr5)
 		    (csr12 & 2) == 2) ||
 		   (tp->nway && (csr5 & (TPLnkFail)))) {
 		/* Link blew? Maybe restart NWay. */
-		del_timer_sync(&tp->timer);
+		timer_delete_sync(&tp->timer);
 		t21142_start_nway(dev);
 		tp->timer.expires = RUN_AT(3*HZ);
 		add_timer(&tp->timer);
@@ -226,7 +226,7 @@ void t21142_lnk_change(struct net_device *dev, int csr5)
 				 medianame[dev->if_port],
 				 (csr12 & 2) ? "failed" : "good");
 		if ((csr12 & 2)  &&  ! tp->medialock) {
-			del_timer_sync(&tp->timer);
+			timer_delete_sync(&tp->timer);
 			t21142_start_nway(dev);
 			tp->timer.expires = RUN_AT(3*HZ);
 			add_timer(&tp->timer);
diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c
index 0a161a4db242..f9504f340c4a 100644
--- a/drivers/net/ethernet/dec/tulip/de2104x.c
+++ b/drivers/net/ethernet/dec/tulip/de2104x.c
@@ -963,7 +963,7 @@ static void de_next_media (struct de_private *de, const u32 *media,
 
 static void de21040_media_timer (struct timer_list *t)
 {
-	struct de_private *de = from_timer(de, t, media_timer);
+	struct de_private *de = timer_container_of(de, t, media_timer);
 	struct net_device *dev = de->dev;
 	u32 status = dr32(SIAStatus);
 	unsigned int carrier;
@@ -1044,7 +1044,7 @@ static unsigned int de_ok_to_advertise (struct de_private *de, u32 new_media)
 
 static void de21041_media_timer (struct timer_list *t)
 {
-	struct de_private *de = from_timer(de, t, media_timer);
+	struct de_private *de = timer_container_of(de, t, media_timer);
 	struct net_device *dev = de->dev;
 	u32 status = dr32(SIAStatus);
 	unsigned int carrier;
@@ -1428,7 +1428,7 @@ static int de_close (struct net_device *dev)
 
 	netif_dbg(de, ifdown, dev, "disabling interface\n");
 
-	del_timer_sync(&de->media_timer);
+	timer_delete_sync(&de->media_timer);
 
 	spin_lock_irqsave(&de->lock, flags);
 	de_stop_hw(de);
@@ -1452,7 +1452,7 @@ static void de_tx_timeout (struct net_device *dev, unsigned int txqueue)
 		   dr32(MacStatus), dr32(MacMode), dr32(SIAStatus),
 		   de->rx_tail, de->tx_head, de->tx_tail);
 
-	del_timer_sync(&de->media_timer);
+	timer_delete_sync(&de->media_timer);
 
 	disable_irq(irq);
 	spin_lock_irq(&de->lock);
@@ -2126,7 +2126,7 @@ static int __maybe_unused de_suspend(struct device *dev_d)
 	if (netif_running (dev)) {
 		const int irq = pdev->irq;
 
-		del_timer_sync(&de->media_timer);
+		timer_delete_sync(&de->media_timer);
 
 		disable_irq(irq);
 		spin_lock_irq(&de->lock);
diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c
index 3188ba7b450f..2d3bd343b6e6 100644
--- a/drivers/net/ethernet/dec/tulip/dmfe.c
+++ b/drivers/net/ethernet/dec/tulip/dmfe.c
@@ -745,7 +745,7 @@ static int dmfe_stop(struct net_device *dev)
 	netif_stop_queue(dev);
 
 	/* deleted timer */
-	del_timer_sync(&db->timer);
+	timer_delete_sync(&db->timer);
 
 	/* Reset & stop DM910X board */
 	dw32(DCR0, DM910X_RESET);
@@ -1115,7 +1115,7 @@ static const struct ethtool_ops netdev_ethtool_ops = {
 
 static void dmfe_timer(struct timer_list *t)
 {
-	struct dmfe_board_info *db = from_timer(db, t, timer);
+	struct dmfe_board_info *db = timer_container_of(db, t, timer);
 	struct net_device *dev = pci_get_drvdata(db->pdev);
 	void __iomem *ioaddr = db->ioaddr;
 	u32 tmp_cr8;
diff --git a/drivers/net/ethernet/dec/tulip/interrupt.c b/drivers/net/ethernet/dec/tulip/interrupt.c
index 54560f9a1651..0a12cb9b3ba7 100644
--- a/drivers/net/ethernet/dec/tulip/interrupt.c
+++ b/drivers/net/ethernet/dec/tulip/interrupt.c
@@ -104,7 +104,7 @@ int tulip_refill_rx(struct net_device *dev)
 
 void oom_timer(struct timer_list *t)
 {
-	struct tulip_private *tp = from_timer(tp, t, oom_timer);
+	struct tulip_private *tp = timer_container_of(tp, t, oom_timer);
 
 	napi_schedule(&tp->napi);
 }
@@ -699,8 +699,8 @@ irqreturn_t tulip_interrupt(int irq, void *dev_instance)
 				tulip_start_rxtx(tp);
 			}
 			/*
-			 * NB: t21142_lnk_change() does a del_timer_sync(), so be careful if this
-			 * call is ever done under the spinlock
+			 * NB: t21142_lnk_change() does a timer_delete_sync(), so be careful
+			 * if this call is ever done under the spinlock
 			 */
 			if (csr5 & (TPLnkPass | TPLnkFail | 0x08000000)) {
 				if (tp->link_change)
diff --git a/drivers/net/ethernet/dec/tulip/pnic.c b/drivers/net/ethernet/dec/tulip/pnic.c
index 653bde48ef44..1de5ed967070 100644
--- a/drivers/net/ethernet/dec/tulip/pnic.c
+++ b/drivers/net/ethernet/dec/tulip/pnic.c
@@ -86,7 +86,7 @@ void pnic_lnk_change(struct net_device *dev, int csr5)
 
 void pnic_timer(struct timer_list *t)
 {
-	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct tulip_private *tp = timer_container_of(tp, t, timer);
 	struct net_device *dev = tp->dev;
 	void __iomem *ioaddr = tp->base_addr;
 	int next_tick = 60*HZ;
diff --git a/drivers/net/ethernet/dec/tulip/pnic2.c b/drivers/net/ethernet/dec/tulip/pnic2.c
index 72a09156b48b..39c410bf224e 100644
--- a/drivers/net/ethernet/dec/tulip/pnic2.c
+++ b/drivers/net/ethernet/dec/tulip/pnic2.c
@@ -78,7 +78,7 @@
 
 void pnic2_timer(struct timer_list *t)
 {
-	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct tulip_private *tp = timer_container_of(tp, t, timer);
 	struct net_device *dev = tp->dev;
 	void __iomem *ioaddr = tp->base_addr;
 	int next_tick = 60*HZ;
@@ -323,7 +323,7 @@ void pnic2_lnk_change(struct net_device *dev, int csr5)
 		if (tulip_debug > 2)
 			netdev_dbg(dev, "Ugh! Link blew?\n");
 
-		del_timer_sync(&tp->timer);
+		timer_delete_sync(&tp->timer);
 		pnic2_start_nway(dev);
 		tp->timer.expires = RUN_AT(3*HZ);
 		add_timer(&tp->timer);
@@ -348,7 +348,7 @@ void pnic2_lnk_change(struct net_device *dev, int csr5)
 
                 /* if failed then try doing an nway to get in sync */
 		if ((csr12 & 2)  &&  ! tp->medialock) {
-			del_timer_sync(&tp->timer);
+			timer_delete_sync(&tp->timer);
 			pnic2_start_nway(dev);
 			tp->timer.expires = RUN_AT(3*HZ);
 			add_timer(&tp->timer);
@@ -372,7 +372,7 @@ void pnic2_lnk_change(struct net_device *dev, int csr5)
 
                 /* if failed, try doing an nway to get in sync */
 		if ((csr12 & 4)  &&  ! tp->medialock) {
-			del_timer_sync(&tp->timer);
+			timer_delete_sync(&tp->timer);
 			pnic2_start_nway(dev);
 			tp->timer.expires = RUN_AT(3*HZ);
 			add_timer(&tp->timer);
diff --git a/drivers/net/ethernet/dec/tulip/timer.c b/drivers/net/ethernet/dec/tulip/timer.c
index 642e9dfc5451..ca0c509b601c 100644
--- a/drivers/net/ethernet/dec/tulip/timer.c
+++ b/drivers/net/ethernet/dec/tulip/timer.c
@@ -139,7 +139,7 @@ void tulip_media_task(struct work_struct *work)
 
 void mxic_timer(struct timer_list *t)
 {
-	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct tulip_private *tp = timer_container_of(tp, t, timer);
 	struct net_device *dev = tp->dev;
 	void __iomem *ioaddr = tp->base_addr;
 	int next_tick = 60*HZ;
@@ -156,7 +156,7 @@ void mxic_timer(struct timer_list *t)
 
 void comet_timer(struct timer_list *t)
 {
-	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct tulip_private *tp = timer_container_of(tp, t, timer);
 	struct net_device *dev = tp->dev;
 	int next_tick = 2*HZ;
 
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index 27e01d780cd0..b608585f1954 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -114,7 +114,7 @@ int tulip_debug = 1;
 
 static void tulip_timer(struct timer_list *t)
 {
-	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct tulip_private *tp = timer_container_of(tp, t, timer);
 	struct net_device *dev = tp->dev;
 
 	if (netif_running(dev))
@@ -747,9 +747,9 @@ static void tulip_down (struct net_device *dev)
 	napi_disable(&tp->napi);
 #endif
 
-	del_timer_sync (&tp->timer);
+	timer_delete_sync(&tp->timer);
 #ifdef CONFIG_TULIP_NAPI
-	del_timer_sync (&tp->oom_timer);
+	timer_delete_sync(&tp->oom_timer);
 #endif
 	spin_lock_irqsave (&tp->lock, flags);
 
@@ -1177,7 +1177,6 @@ static void set_rx_mode(struct net_device *dev)
 	iowrite32(csr6, ioaddr + CSR6);
 }
 
-#ifdef CONFIG_TULIP_MWI
 static void tulip_mwi_config(struct pci_dev *pdev, struct net_device *dev)
 {
 	struct tulip_private *tp = netdev_priv(dev);
@@ -1251,7 +1250,6 @@ out:
 		netdev_dbg(dev, "MWI config cacheline=%d, csr0=%08x\n",
 			   cache, csr0);
 }
-#endif
 
 /*
  *	Chips that have the MRM/reserved bit quirk and the burst quirk. That
@@ -1413,7 +1411,7 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* grab all resources from both PIO and MMIO regions, as we
 	 * don't want anyone else messing around with our hardware */
-	if (pci_request_regions(pdev, DRV_NAME))
+	if (pcim_request_all_regions(pdev, DRV_NAME))
 		return -ENODEV;
 
 	ioaddr = pcim_iomap(pdev, TULIP_BAR, tulip_tbl[chip_idx].io_size);
@@ -1463,10 +1461,9 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_WORK(&tp->media_work, tulip_tbl[tp->chip_id].media_task);
 
-#ifdef CONFIG_TULIP_MWI
-	if (!force_csr0 && (tp->flags & HAS_PCI_MWI))
+	if (IS_ENABLED(CONFIG_TULIP_MWI) && !force_csr0 &&
+	    (tp->flags & HAS_PCI_MWI))
 		tulip_mwi_config (pdev, dev);
-#endif
 
 	/* Stop the chip's Tx and Rx processes. */
 	tulip_stop_rxtx(tp);
@@ -1553,7 +1550,7 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
                     (PCI_SLOT(pdev->devfn) == 12))) {
                        /* Cobalt MAC address in first EEPROM locations. */
                        sa_offset = 0;
-		       /* Ensure our media table fixup get's applied */
+		       /* Ensure our media table fixup gets applied */
 		       memcpy(ee_data + 16, ee_data, 8);
                }
 #endif
diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c
index ff080ab0f116..6e4d8d31aba9 100644
--- a/drivers/net/ethernet/dec/tulip/uli526x.c
+++ b/drivers/net/ethernet/dec/tulip/uli526x.c
@@ -656,7 +656,7 @@ static int uli526x_stop(struct net_device *dev)
 	netif_stop_queue(dev);
 
 	/* deleted timer */
-	del_timer_sync(&db->timer);
+	timer_delete_sync(&db->timer);
 
 	/* Reset & stop ULI526X board */
 	uw32(DCR0, ULI526X_RESET);
@@ -1014,7 +1014,7 @@ static const struct ethtool_ops netdev_ethtool_ops = {
 
 static void uli526x_timer(struct timer_list *t)
 {
-	struct uli526x_board_info *db = from_timer(db, t, timer);
+	struct uli526x_board_info *db = timer_container_of(db, t, timer);
 	struct net_device *dev = pci_get_drvdata(db->pdev);
 	struct uli_phy_ops *phy = &db->phy;
 	void __iomem *ioaddr = db->ioaddr;
diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c
index 37fba39c0056..a24a25a5f73d 100644
--- a/drivers/net/ethernet/dec/tulip/winbond-840.c
+++ b/drivers/net/ethernet/dec/tulip/winbond-840.c
@@ -375,7 +375,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return -ENOMEM;
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
-	if (pci_request_regions(pdev, DRV_NAME))
+	if (pcim_request_all_regions(pdev, DRV_NAME))
 		goto err_out_netdev;
 
 	ioaddr = pci_iomap(pdev, TULIP_BAR, netdev_res_size);
@@ -763,7 +763,7 @@ static inline void update_csr6(struct net_device *dev, int new)
 
 static void netdev_timer(struct timer_list *t)
 {
-	struct netdev_private *np = from_timer(np, t, timer);
+	struct netdev_private *np = timer_container_of(np, t, timer);
 	struct net_device *dev = pci_get_drvdata(np->pci_dev);
 	void __iomem *ioaddr = np->base_addr;
 
@@ -1509,7 +1509,7 @@ static int netdev_close(struct net_device *dev)
 	}
 #endif /* __i386__ debugging only */
 
-	del_timer_sync(&np->timer);
+	timer_delete_sync(&np->timer);
 
 	free_rxtx_rings(np);
 	free_ringdesc(np);
@@ -1560,7 +1560,7 @@ static int __maybe_unused w840_suspend(struct device *dev_d)
 
 	rtnl_lock();
 	if (netif_running (dev)) {
-		del_timer_sync(&np->timer);
+		timer_delete_sync(&np->timer);
 
 		spin_lock_irq(&np->lock);
 		netif_device_detach(dev);
diff --git a/drivers/net/ethernet/dec/tulip/xircom_cb.c b/drivers/net/ethernet/dec/tulip/xircom_cb.c
index 8759f9f76b62..e5d2ede13845 100644
--- a/drivers/net/ethernet/dec/tulip/xircom_cb.c
+++ b/drivers/net/ethernet/dec/tulip/xircom_cb.c
@@ -143,7 +143,7 @@ static const struct pci_device_id xircom_pci_table[] = {
 };
 MODULE_DEVICE_TABLE(pci, xircom_pci_table);
 
-static struct pci_driver xircom_ops = {
+static struct pci_driver xircom_driver = {
 	.name		= "xircom_cb",
 	.id_table	= xircom_pci_table,
 	.probe		= xircom_probe,
@@ -1169,4 +1169,4 @@ investigate_write_descriptor(struct net_device *dev,
 	}
 }
 
-module_pci_driver(xircom_ops);
+module_pci_driver(xircom_driver);
diff --git a/drivers/net/ethernet/dlink/Kconfig b/drivers/net/ethernet/dlink/Kconfig
index e9e13654812c..0d77f84c8e7b 100644
--- a/drivers/net/ethernet/dlink/Kconfig
+++ b/drivers/net/ethernet/dlink/Kconfig
@@ -32,4 +32,24 @@ config DL2K
 	  To compile this driver as a module, choose M here: the
 	  module will be called dl2k.
 
+config SUNDANCE
+	tristate "Sundance Alta support"
+	depends on PCI
+	select CRC32
+	select MII
+	help
+	  This driver is for the Sundance "Alta" chip.
+	  More specific information and updates are available from
+	  <http://www.scyld.com/network/sundance.html>.
+
+config SUNDANCE_MMIO
+	bool "Use MMIO instead of PIO"
+	depends on SUNDANCE
+	help
+	  Enable memory-mapped I/O for interaction with Sundance NIC registers.
+	  Do NOT enable this by default, PIO (enabled when MMIO is disabled)
+	  is known to solve bugs on certain chips.
+
+	  If unsure, say N.
+
 endif # NET_VENDOR_DLINK
diff --git a/drivers/net/ethernet/dlink/Makefile b/drivers/net/ethernet/dlink/Makefile
index 38c236eb6007..3ff503c747db 100644
--- a/drivers/net/ethernet/dlink/Makefile
+++ b/drivers/net/ethernet/dlink/Makefile
@@ -4,3 +4,4 @@
 #
 
 obj-$(CONFIG_DL2K) += dl2k.o
+obj-$(CONFIG_SUNDANCE) += sundance.o
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index d0ea92607870..846d58c769ea 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -41,7 +41,7 @@ module_param(tx_flow, int, 0);
 module_param(rx_flow, int, 0);
 module_param(copy_thresh, int, 0);
 module_param(rx_coalesce, int, 0);	/* Rx frame count each interrupt */
-module_param(rx_timeout, int, 0);	/* Rx DMA wait time in 64ns increments */
+module_param(rx_timeout, int, 0);  /* Rx DMA wait time in 640ns increments */
 module_param(tx_coalesce, int, 0); /* HW xmit count each TxDMAComplete */
 
 
@@ -99,6 +99,13 @@ static const struct net_device_ops netdev_ops = {
 	.ndo_tx_timeout		= rio_tx_timeout,
 };
 
+static bool is_support_rmon_mmio(struct pci_dev *pdev)
+{
+	return pdev->vendor == PCI_VENDOR_ID_DLINK &&
+	       pdev->device == 0x4000 &&
+	       pdev->revision == 0x0c;
+}
+
 static int
 rio_probe1 (struct pci_dev *pdev, const struct pci_device_id *ent)
 {
@@ -131,21 +138,27 @@ rio_probe1 (struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	np = netdev_priv(dev);
 
+	if (is_support_rmon_mmio(pdev))
+		np->rmon_enable = true;
+
 	/* IO registers range. */
 	ioaddr = pci_iomap(pdev, 0, 0);
 	if (!ioaddr)
 		goto err_out_dev;
 	np->eeprom_addr = ioaddr;
 
-#ifdef MEM_MAPPING
-	/* MM registers range. */
-	ioaddr = pci_iomap(pdev, 1, 0);
-	if (!ioaddr)
-		goto err_out_iounmap;
-#endif
+	if (np->rmon_enable) {
+		/* MM registers range. */
+		ioaddr = pci_iomap(pdev, 1, 0);
+		if (!ioaddr)
+			goto err_out_iounmap;
+	}
+
 	np->ioaddr = ioaddr;
 	np->chip_id = chip_idx;
 	np->pdev = pdev;
+
+	spin_lock_init(&np->stats_lock);
 	spin_lock_init (&np->tx_lock);
 	spin_lock_init (&np->rx_lock);
 
@@ -249,7 +262,7 @@ rio_probe1 (struct pci_dev *pdev, const struct pci_device_id *ent)
 	np->link_status = 0;
 	/* Set media and reset PHY */
 	if (np->phy_media) {
-		/* default Auto-Negotiation for fiber deivices */
+		/* default Auto-Negotiation for fiber devices */
 	 	if (np->an_enable == 2) {
 			np->an_enable = 1;
 		}
@@ -287,9 +300,8 @@ err_out_unmap_tx:
 	dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, np->tx_ring,
 			  np->tx_ring_dma);
 err_out_iounmap:
-#ifdef MEM_MAPPING
-	pci_iounmap(pdev, np->ioaddr);
-#endif
+	if (np->rmon_enable)
+		pci_iounmap(pdev, np->ioaddr);
 	pci_iounmap(pdev, np->eeprom_addr);
 err_out_dev:
 	free_netdev (dev);
@@ -352,7 +364,7 @@ parse_eeprom (struct net_device *dev)
 	eth_hw_addr_set(dev, psrom->mac_addr);
 
 	if (np->chip_id == CHIP_IP1000A) {
-		np->led_mode = psrom->led_mode;
+		np->led_mode = le16_to_cpu(psrom->led_mode);
 		return 0;
 	}
 
@@ -496,25 +508,34 @@ static int alloc_list(struct net_device *dev)
 	for (i = 0; i < RX_RING_SIZE; i++) {
 		/* Allocated fixed size of skbuff */
 		struct sk_buff *skb;
+		dma_addr_t addr;
 
 		skb = netdev_alloc_skb_ip_align(dev, np->rx_buf_sz);
 		np->rx_skbuff[i] = skb;
-		if (!skb) {
-			free_list(dev);
-			return -ENOMEM;
-		}
+		if (!skb)
+			goto err_free_list;
+
+		addr = dma_map_single(&np->pdev->dev, skb->data,
+				      np->rx_buf_sz, DMA_FROM_DEVICE);
+		if (dma_mapping_error(&np->pdev->dev, addr))
+			goto err_kfree_skb;
 
 		np->rx_ring[i].next_desc = cpu_to_le64(np->rx_ring_dma +
 						((i + 1) % RX_RING_SIZE) *
 						sizeof(struct netdev_desc));
 		/* Rubicon now supports 40 bits of addressing space. */
-		np->rx_ring[i].fraginfo =
-		    cpu_to_le64(dma_map_single(&np->pdev->dev, skb->data,
-					       np->rx_buf_sz, DMA_FROM_DEVICE));
+		np->rx_ring[i].fraginfo = cpu_to_le64(addr);
 		np->rx_ring[i].fraginfo |= cpu_to_le64((u64)np->rx_buf_sz << 48);
 	}
 
 	return 0;
+
+err_kfree_skb:
+	dev_kfree_skb(np->rx_skbuff[i]);
+	np->rx_skbuff[i] = NULL;
+err_free_list:
+	free_list(dev);
+	return -ENOMEM;
 }
 
 static void rio_hw_init(struct net_device *dev)
@@ -576,7 +597,8 @@ static void rio_hw_init(struct net_device *dev)
 	dw8(TxDMAPollPeriod, 0xff);
 	dw8(RxDMABurstThresh, 0x30);
 	dw8(RxDMAUrgentThresh, 0x30);
-	dw32(RmonStatMask, 0x0007ffff);
+	if (!np->rmon_enable)
+		dw32(RmonStatMask, 0x0007ffff);
 	/* clear statistics */
 	clear_stats (dev);
 
@@ -648,7 +670,7 @@ static int rio_open(struct net_device *dev)
 static void
 rio_timer (struct timer_list *t)
 {
-	struct netdev_private *np = from_timer(np, t, timer);
+	struct netdev_private *np = timer_container_of(np, t, timer);
 	struct net_device *dev = pci_get_drvdata(np->pdev);
 	unsigned int entry;
 	int next_tick = 1*HZ;
@@ -711,7 +733,7 @@ start_xmit (struct sk_buff *skb, struct net_device *dev)
 	u64 tfc_vlan_tag = 0;
 
 	if (np->link_status == 0) {	/* Link Down */
-		dev_kfree_skb(skb);
+		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
 	entry = np->cur_tx % TX_RING_SIZE;
@@ -865,8 +887,7 @@ tx_error (struct net_device *dev, int tx_status)
 	frame_id = (tx_status & 0xffff0000);
 	printk (KERN_ERR "%s: Transmit error, TxStatus %4.4x, FrameId %d.\n",
 		dev->name, tx_status, frame_id);
-	dev->stats.tx_errors++;
-	/* Ttransmit Underrun */
+	/* Transmit Underrun */
 	if (tx_status & 0x10) {
 		dev->stats.tx_fifo_errors++;
 		dw16(TxStartThresh, dr16(TxStartThresh) + 0x10);
@@ -902,9 +923,15 @@ tx_error (struct net_device *dev, int tx_status)
 		rio_set_led_mode(dev);
 		/* Let TxStartThresh stay default value */
 	}
+
+	spin_lock(&np->stats_lock);
 	/* Maximum Collisions */
 	if (tx_status & 0x08)
 		dev->stats.collisions++;
+
+	dev->stats.tx_errors++;
+	spin_unlock(&np->stats_lock);
+
 	/* Restart the Tx */
 	dw32(MACCtrl, dr16(MACCtrl) | TxEnable);
 }
@@ -946,15 +973,18 @@ receive_packet (struct net_device *dev)
 		} else {
 			struct sk_buff *skb;
 
+			skb = NULL;
 			/* Small skbuffs for short packets */
-			if (pkt_len > copy_thresh) {
+			if (pkt_len <= copy_thresh)
+				skb = netdev_alloc_skb_ip_align(dev, pkt_len);
+			if (!skb) {
 				dma_unmap_single(&np->pdev->dev,
 						 desc_to_dma(desc),
 						 np->rx_buf_sz,
 						 DMA_FROM_DEVICE);
 				skb_put (skb = np->rx_skbuff[entry], pkt_len);
 				np->rx_skbuff[entry] = NULL;
-			} else if ((skb = netdev_alloc_skb_ip_align(dev, pkt_len))) {
+			} else {
 				dma_sync_single_for_cpu(&np->pdev->dev,
 							desc_to_dma(desc),
 							np->rx_buf_sz,
@@ -1053,7 +1083,7 @@ rio_error (struct net_device *dev, int int_status)
 		get_stats (dev);
 	}
 
-	/* PCI Error, a catastronphic error related to the bus interface
+	/* PCI Error, a catastrophic error related to the bus interface
 	   occurs, set GlobalReset and HostReset to reset. */
 	if (int_status & HostError) {
 		printk (KERN_ERR "%s: HostError! IntStatus %4.4x.\n",
@@ -1069,11 +1099,10 @@ get_stats (struct net_device *dev)
 {
 	struct netdev_private *np = netdev_priv(dev);
 	void __iomem *ioaddr = np->ioaddr;
-#ifdef MEM_MAPPING
-	int i;
-#endif
 	unsigned int stat_reg;
+	unsigned long flags;
 
+	spin_lock_irqsave(&np->stats_lock, flags);
 	/* All statistics registers need to be acknowledged,
 	   else statistic overflow could cause problems */
 
@@ -1082,7 +1111,7 @@ get_stats (struct net_device *dev)
 	dev->stats.rx_bytes += dr32(OctetRcvOk);
 	dev->stats.tx_bytes += dr32(OctetXmtOk);
 
-	dev->stats.multicast = dr32(McstFramesRcvdOk);
+	dev->stats.multicast += dr32(McstFramesRcvdOk);
 	dev->stats.collisions += dr32(SingleColFrames)
 			     +  dr32(MultiColFrames);
 
@@ -1114,15 +1143,18 @@ get_stats (struct net_device *dev)
 	dr16(MacControlFramesXmtd);
 	dr16(FramesWEXDeferal);
 
-#ifdef MEM_MAPPING
-	for (i = 0x100; i <= 0x150; i += 4)
-		dr32(i);
-#endif
+	if (np->rmon_enable)
+		for (int i = 0x100; i <= 0x150; i += 4)
+			dr32(i);
+
 	dr16(TxJumboFrames);
 	dr16(RxJumboFrames);
 	dr16(TCPCheckSumErrors);
 	dr16(UDPCheckSumErrors);
 	dr16(IPCheckSumErrors);
+
+	spin_unlock_irqrestore(&np->stats_lock, flags);
+
 	return &dev->stats;
 }
 
@@ -1131,9 +1163,6 @@ clear_stats (struct net_device *dev)
 {
 	struct netdev_private *np = netdev_priv(dev);
 	void __iomem *ioaddr = np->ioaddr;
-#ifdef MEM_MAPPING
-	int i;
-#endif
 
 	/* All statistics registers need to be acknowledged,
 	   else statistic overflow could cause problems */
@@ -1169,10 +1198,9 @@ clear_stats (struct net_device *dev)
 	dr16(BcstFramesXmtdOk);
 	dr16(MacControlFramesXmtd);
 	dr16(FramesWEXDeferal);
-#ifdef MEM_MAPPING
-	for (i = 0x100; i <= 0x150; i += 4)
-		dr32(i);
-#endif
+	if (np->rmon_enable)
+		for (int i = 0x100; i <= 0x150; i += 4)
+			dr32(i);
 	dr16(TxJumboFrames);
 	dr16(RxJumboFrames);
 	dr16(TCPCheckSumErrors);
@@ -1778,7 +1806,7 @@ rio_close (struct net_device *dev)
 	rio_hw_stop(dev);
 
 	free_irq(pdev->irq, dev);
-	del_timer_sync (&np->timer);
+	timer_delete_sync(&np->timer);
 
 	free_list(dev);
 
@@ -1798,9 +1826,8 @@ rio_remove1 (struct pci_dev *pdev)
 				  np->rx_ring_dma);
 		dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, np->tx_ring,
 				  np->tx_ring_dma);
-#ifdef MEM_MAPPING
-		pci_iounmap(pdev, np->ioaddr);
-#endif
+		if (np->rmon_enable)
+			pci_iounmap(pdev, np->ioaddr);
 		pci_iounmap(pdev, np->eeprom_addr);
 		free_netdev (dev);
 		pci_release_regions (pdev);
@@ -1818,7 +1845,7 @@ static int rio_suspend(struct device *device)
 		return 0;
 
 	netif_device_detach(dev);
-	del_timer_sync(&np->timer);
+	timer_delete_sync(&np->timer);
 	rio_hw_stop(dev);
 
 	return 0;
diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h
index 195dc6cfd895..9ebf7a6db93e 100644
--- a/drivers/net/ethernet/dlink/dl2k.h
+++ b/drivers/net/ethernet/dlink/dl2k.h
@@ -270,7 +270,7 @@ enum _pcs_reg {
 	PCS_ESR = 15,
 };
 
-/* IEEE Extened Status Register */
+/* IEEE Extended Status Register */
 enum _mii_esr {
 	MII_ESR_1000BX_FD = 0x8000,
 	MII_ESR_1000BX_HD = 0x4000,
@@ -329,18 +329,18 @@ enum _pcs_anlpar {
 };
 
 typedef struct t_SROM {
-	u16 config_param;	/* 0x00 */
-	u16 asic_ctrl;		/* 0x02 */
-	u16 sub_vendor_id;	/* 0x04 */
-	u16 sub_system_id;	/* 0x06 */
-	u16 pci_base_1;		/* 0x08 (IP1000A only) */
-	u16 pci_base_2;		/* 0x0a (IP1000A only) */
-	u16 led_mode;		/* 0x0c (IP1000A only) */
-	u16 reserved1[9];	/* 0x0e-0x1f */
+	__le16 config_param;	/* 0x00 */
+	__le16 asic_ctrl;	/* 0x02 */
+	__le16 sub_vendor_id;	/* 0x04 */
+	__le16 sub_system_id;	/* 0x06 */
+	__le16 pci_base_1;	/* 0x08 (IP1000A only) */
+	__le16 pci_base_2;	/* 0x0a (IP1000A only) */
+	__le16 led_mode;	/* 0x0c (IP1000A only) */
+	__le16 reserved1[9];	/* 0x0e-0x1f */
 	u8 mac_addr[6];		/* 0x20-0x25 */
 	u8 reserved2[10];	/* 0x26-0x2f */
 	u8 sib[204];		/* 0x30-0xfb */
-	u32 crc;		/* 0xfc-0xff */
+	__le32 crc;		/* 0xfc-0xff */
 } SROM_t, *PSROM_t;
 
 /* Ioctl custom data */
@@ -372,6 +372,8 @@ struct netdev_private {
 	struct pci_dev *pdev;
 	void __iomem *ioaddr;
 	void __iomem *eeprom_addr;
+	// To ensure synchronization when stats are updated.
+	spinlock_t stats_lock;
 	spinlock_t tx_lock;
 	spinlock_t rx_lock;
 	unsigned int rx_buf_sz;		/* Based on MTU+slack. */
@@ -401,6 +403,8 @@ struct netdev_private {
 	u16 negotiate;		/* Negotiated media */
 	int phy_addr;		/* PHY addresses. */
 	u16 led_mode;		/* LED mode read from EEPROM (IP1000A only) */
+
+	bool rmon_enable;
 };
 
 /* The station address location in the EEPROM. */
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
new file mode 100644
index 000000000000..277c50ef773f
--- /dev/null
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -0,0 +1,1990 @@
+/* sundance.c: A Linux device driver for the Sundance ST201 "Alta". */
+/*
+	Written 1999-2000 by Donald Becker.
+
+	This software may be used and distributed according to the terms of
+	the GNU General Public License (GPL), incorporated herein by reference.
+	Drivers based on or derived from this code fall under the GPL and must
+	retain the authorship, copyright and license notice.  This file is not
+	a complete program and may only be used when the entire operating
+	system is licensed under the GPL.
+
+	The author may be reached as becker@scyld.com, or C/O
+	Scyld Computing Corporation
+	410 Severn Ave., Suite 210
+	Annapolis MD 21403
+
+	Support and updates available at
+	http://www.scyld.com/network/sundance.html
+	[link no longer provides useful info -jgarzik]
+	Archives of the mailing list are still available at
+	https://www.beowulf.org/pipermail/netdrivers/
+
+*/
+
+#define DRV_NAME	"sundance"
+
+/* The user-configurable values.
+   These may be modified when a driver module is loaded.*/
+static int debug = 1;			/* 1 normal messages, 0 quiet .. 7 verbose. */
+/* Maximum number of multicast addresses to filter (vs. rx-all-multicast).
+   Typical is a 64 element hash table based on the Ethernet CRC.  */
+static const int multicast_filter_limit = 32;
+
+/* Set the copy breakpoint for the copy-only-tiny-frames scheme.
+   Setting to > 1518 effectively disables this feature.
+   This chip can receive into offset buffers, so the Alpha does not
+   need a copy-align. */
+static int rx_copybreak;
+static int flowctrl=1;
+
+/* media[] specifies the media type the NIC operates at.
+		 autosense	Autosensing active media.
+		 10mbps_hd 	10Mbps half duplex.
+		 10mbps_fd 	10Mbps full duplex.
+		 100mbps_hd 	100Mbps half duplex.
+		 100mbps_fd 	100Mbps full duplex.
+		 0		Autosensing active media.
+		 1	 	10Mbps half duplex.
+		 2	 	10Mbps full duplex.
+		 3	 	100Mbps half duplex.
+		 4	 	100Mbps full duplex.
+*/
+#define MAX_UNITS 8
+static char *media[MAX_UNITS];
+
+
+/* Operational parameters that are set at compile time. */
+
+/* Keep the ring sizes a power of two for compile efficiency.
+   The compiler will convert <unsigned>'%'<2^N> into a bit mask.
+   Making the Tx ring too large decreases the effectiveness of channel
+   bonding and packet priority, and more than 128 requires modifying the
+   Tx error recovery.
+   Large receive rings merely waste memory. */
+#define TX_RING_SIZE	32
+#define TX_QUEUE_LEN	(TX_RING_SIZE - 1) /* Limit ring entries actually used.  */
+#define RX_RING_SIZE	64
+#define RX_BUDGET	32
+#define TX_TOTAL_SIZE	TX_RING_SIZE*sizeof(struct netdev_desc)
+#define RX_TOTAL_SIZE	RX_RING_SIZE*sizeof(struct netdev_desc)
+
+/* Operational parameters that usually are not changed. */
+/* Time in jiffies before concluding the transmitter is hung. */
+#define TX_TIMEOUT  (4*HZ)
+#define PKT_BUF_SZ		1536	/* Size of each temporary Rx buffer.*/
+
+/* Include files, designed to support most kernel versions 2.0.0 and later. */
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/timer.h>
+#include <linux/errno.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <linux/bitops.h>
+#include <linux/uaccess.h>
+#include <asm/processor.h>		/* Processor type for cache alignment. */
+#include <asm/io.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/dma-mapping.h>
+#include <linux/crc32.h>
+#include <linux/ethtool.h>
+#include <linux/mii.h>
+
+MODULE_AUTHOR("Donald Becker <becker@scyld.com>");
+MODULE_DESCRIPTION("Sundance Alta Ethernet driver");
+MODULE_LICENSE("GPL");
+
+module_param(debug, int, 0);
+module_param(rx_copybreak, int, 0);
+module_param_array(media, charp, NULL, 0);
+module_param(flowctrl, int, 0);
+MODULE_PARM_DESC(debug, "Sundance Alta debug level (0-5)");
+MODULE_PARM_DESC(rx_copybreak, "Sundance Alta copy breakpoint for copy-only-tiny-frames");
+MODULE_PARM_DESC(flowctrl, "Sundance Alta flow control [0|1]");
+
+/*
+				Theory of Operation
+
+I. Board Compatibility
+
+This driver is designed for the Sundance Technologies "Alta" ST201 chip.
+
+II. Board-specific settings
+
+III. Driver operation
+
+IIIa. Ring buffers
+
+This driver uses two statically allocated fixed-size descriptor lists
+formed into rings by a branch from the final descriptor to the beginning of
+the list.  The ring sizes are set at compile time by RX/TX_RING_SIZE.
+Some chips explicitly use only 2^N sized rings, while others use a
+'next descriptor' pointer that the driver forms into rings.
+
+IIIb/c. Transmit/Receive Structure
+
+This driver uses a zero-copy receive and transmit scheme.
+The driver allocates full frame size skbuffs for the Rx ring buffers at
+open() time and passes the skb->data field to the chip as receive data
+buffers.  When an incoming frame is less than RX_COPYBREAK bytes long,
+a fresh skbuff is allocated and the frame is copied to the new skbuff.
+When the incoming frame is larger, the skbuff is passed directly up the
+protocol stack.  Buffers consumed this way are replaced by newly allocated
+skbuffs in a later phase of receives.
+
+The RX_COPYBREAK value is chosen to trade-off the memory wasted by
+using a full-sized skbuff for small frames vs. the copying costs of larger
+frames.  New boards are typically used in generously configured machines
+and the underfilled buffers have negligible impact compared to the benefit of
+a single allocation size, so the default value of zero results in never
+copying packets.  When copying is done, the cost is usually mitigated by using
+a combined copy/checksum routine.  Copying also preloads the cache, which is
+most useful with small frames.
+
+A subtle aspect of the operation is that the IP header at offset 14 in an
+ethernet frame isn't longword aligned for further processing.
+Unaligned buffers are permitted by the Sundance hardware, so
+frames are received into the skbuff at an offset of "+2", 16-byte aligning
+the IP header.
+
+IIId. Synchronization
+
+The driver runs as two independent, single-threaded flows of control.  One
+is the send-packet routine, which enforces single-threaded use by the
+dev->tbusy flag.  The other thread is the interrupt handler, which is single
+threaded by the hardware and interrupt handling software.
+
+The send packet thread has partial control over the Tx ring and 'dev->tbusy'
+flag.  It sets the tbusy flag whenever it's queuing a Tx packet. If the next
+queue slot is empty, it clears the tbusy flag when finished otherwise it sets
+the 'lp->tx_full' flag.
+
+The interrupt handler has exclusive control over the Rx ring and records stats
+from the Tx ring.  After reaping the stats, it marks the Tx queue entry as
+empty by incrementing the dirty_tx mark. Iff the 'lp->tx_full' flag is set, it
+clears both the tx_full and tbusy flags.
+
+IV. Notes
+
+IVb. References
+
+The Sundance ST201 datasheet, preliminary version.
+The Kendin KS8723 datasheet, preliminary version.
+The ICplus IP100 datasheet, preliminary version.
+http://www.scyld.com/expert/100mbps.html
+http://www.scyld.com/expert/NWay.html
+
+IVc. Errata
+
+*/
+
+/* Work-around for Kendin chip bugs. */
+#ifndef CONFIG_SUNDANCE_MMIO
+#define USE_IO_OPS 1
+#endif
+
+static const struct pci_device_id sundance_pci_tbl[] = {
+	{ 0x1186, 0x1002, 0x1186, 0x1002, 0, 0, 0 },
+	{ 0x1186, 0x1002, 0x1186, 0x1003, 0, 0, 1 },
+	{ 0x1186, 0x1002, 0x1186, 0x1012, 0, 0, 2 },
+	{ 0x1186, 0x1002, 0x1186, 0x1040, 0, 0, 3 },
+	{ 0x1186, 0x1002, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 4 },
+	{ 0x13F0, 0x0201, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 5 },
+	{ 0x13F0, 0x0200, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 6 },
+	{ }
+};
+MODULE_DEVICE_TABLE(pci, sundance_pci_tbl);
+
+enum {
+	netdev_io_size = 128
+};
+
+struct pci_id_info {
+        const char *name;
+};
+static const struct pci_id_info pci_id_tbl[] = {
+	{"D-Link DFE-550TX FAST Ethernet Adapter"},
+	{"D-Link DFE-550FX 100Mbps Fiber-optics Adapter"},
+	{"D-Link DFE-580TX 4 port Server Adapter"},
+	{"D-Link DFE-530TXS FAST Ethernet Adapter"},
+	{"D-Link DL10050-based FAST Ethernet Adapter"},
+	{"Sundance Technology Alta"},
+	{"IC Plus Corporation IP100A FAST Ethernet Adapter"},
+	{ }	/* terminate list. */
+};
+
+/* This driver was written to use PCI memory space, however x86-oriented
+   hardware often uses I/O space accesses. */
+
+/* Offsets to the device registers.
+   Unlike software-only systems, device drivers interact with complex hardware.
+   It's not useful to define symbolic names for every register bit in the
+   device.  The name can only partially document the semantics and make
+   the driver longer and more difficult to read.
+   In general, only the important configuration values or bits changed
+   multiple times should be defined symbolically.
+*/
+enum alta_offsets {
+	DMACtrl = 0x00,
+	TxListPtr = 0x04,
+	TxDMABurstThresh = 0x08,
+	TxDMAUrgentThresh = 0x09,
+	TxDMAPollPeriod = 0x0a,
+	RxDMAStatus = 0x0c,
+	RxListPtr = 0x10,
+	DebugCtrl0 = 0x1a,
+	DebugCtrl1 = 0x1c,
+	RxDMABurstThresh = 0x14,
+	RxDMAUrgentThresh = 0x15,
+	RxDMAPollPeriod = 0x16,
+	LEDCtrl = 0x1a,
+	ASICCtrl = 0x30,
+	EEData = 0x34,
+	EECtrl = 0x36,
+	FlashAddr = 0x40,
+	FlashData = 0x44,
+	WakeEvent = 0x45,
+	TxStatus = 0x46,
+	TxFrameId = 0x47,
+	DownCounter = 0x18,
+	IntrClear = 0x4a,
+	IntrEnable = 0x4c,
+	IntrStatus = 0x4e,
+	MACCtrl0 = 0x50,
+	MACCtrl1 = 0x52,
+	StationAddr = 0x54,
+	MaxFrameSize = 0x5A,
+	RxMode = 0x5c,
+	MIICtrl = 0x5e,
+	MulticastFilter0 = 0x60,
+	MulticastFilter1 = 0x64,
+	RxOctetsLow = 0x68,
+	RxOctetsHigh = 0x6a,
+	TxOctetsLow = 0x6c,
+	TxOctetsHigh = 0x6e,
+	TxFramesOK = 0x70,
+	RxFramesOK = 0x72,
+	StatsCarrierError = 0x74,
+	StatsLateColl = 0x75,
+	StatsMultiColl = 0x76,
+	StatsOneColl = 0x77,
+	StatsTxDefer = 0x78,
+	RxMissed = 0x79,
+	StatsTxXSDefer = 0x7a,
+	StatsTxAbort = 0x7b,
+	StatsBcastTx = 0x7c,
+	StatsBcastRx = 0x7d,
+	StatsMcastTx = 0x7e,
+	StatsMcastRx = 0x7f,
+	/* Aliased and bogus values! */
+	RxStatus = 0x0c,
+};
+
+#define ASIC_HI_WORD(x)	((x) + 2)
+
+enum ASICCtrl_HiWord_bit {
+	GlobalReset = 0x0001,
+	RxReset = 0x0002,
+	TxReset = 0x0004,
+	DMAReset = 0x0008,
+	FIFOReset = 0x0010,
+	NetworkReset = 0x0020,
+	HostReset = 0x0040,
+	ResetBusy = 0x0400,
+};
+
+/* Bits in the interrupt status/mask registers. */
+enum intr_status_bits {
+	IntrSummary=0x0001, IntrPCIErr=0x0002, IntrMACCtrl=0x0008,
+	IntrTxDone=0x0004, IntrRxDone=0x0010, IntrRxStart=0x0020,
+	IntrDrvRqst=0x0040,
+	StatsMax=0x0080, LinkChange=0x0100,
+	IntrTxDMADone=0x0200, IntrRxDMADone=0x0400,
+};
+
+/* Bits in the RxMode register. */
+enum rx_mode_bits {
+	AcceptAllIPMulti=0x20, AcceptMultiHash=0x10, AcceptAll=0x08,
+	AcceptBroadcast=0x04, AcceptMulticast=0x02, AcceptMyPhys=0x01,
+};
+/* Bits in MACCtrl. */
+enum mac_ctrl0_bits {
+	EnbFullDuplex=0x20, EnbRcvLargeFrame=0x40,
+	EnbFlowCtrl=0x100, EnbPassRxCRC=0x200,
+};
+enum mac_ctrl1_bits {
+	StatsEnable=0x0020,	StatsDisable=0x0040, StatsEnabled=0x0080,
+	TxEnable=0x0100, TxDisable=0x0200, TxEnabled=0x0400,
+	RxEnable=0x0800, RxDisable=0x1000, RxEnabled=0x2000,
+};
+
+/* Bits in WakeEvent register. */
+enum wake_event_bits {
+	WakePktEnable = 0x01,
+	MagicPktEnable = 0x02,
+	LinkEventEnable = 0x04,
+	WolEnable = 0x80,
+};
+
+/* The Rx and Tx buffer descriptors. */
+/* Note that using only 32 bit fields simplifies conversion to big-endian
+   architectures. */
+struct netdev_desc {
+	__le32 next_desc;
+	__le32 status;
+	struct desc_frag { __le32 addr, length; } frag;
+};
+
+/* Bits in netdev_desc.status */
+enum desc_status_bits {
+	DescOwn=0x8000,
+	DescEndPacket=0x4000,
+	DescEndRing=0x2000,
+	LastFrag=0x80000000,
+	DescIntrOnTx=0x8000,
+	DescIntrOnDMADone=0x80000000,
+	DisableAlign = 0x00000001,
+};
+
+#define PRIV_ALIGN	15 	/* Required alignment mask */
+/* Use  __attribute__((aligned (L1_CACHE_BYTES)))  to maintain alignment
+   within the structure. */
+#define MII_CNT		4
+struct netdev_private {
+	/* Descriptor rings first for alignment. */
+	struct netdev_desc *rx_ring;
+	struct netdev_desc *tx_ring;
+	struct sk_buff* rx_skbuff[RX_RING_SIZE];
+	struct sk_buff* tx_skbuff[TX_RING_SIZE];
+        dma_addr_t tx_ring_dma;
+        dma_addr_t rx_ring_dma;
+	struct timer_list timer;		/* Media monitoring timer. */
+	struct net_device *ndev;		/* backpointer */
+	/* ethtool extra stats */
+	struct {
+		u64 tx_multiple_collisions;
+		u64 tx_single_collisions;
+		u64 tx_late_collisions;
+		u64 tx_deferred;
+		u64 tx_deferred_excessive;
+		u64 tx_aborted;
+		u64 tx_bcasts;
+		u64 rx_bcasts;
+		u64 tx_mcasts;
+		u64 rx_mcasts;
+	} xstats;
+	/* Frequently used values: keep some adjacent for cache effect. */
+	spinlock_t lock;
+	int msg_enable;
+	int chip_id;
+	unsigned int cur_rx, dirty_rx;		/* Producer/consumer ring indices */
+	unsigned int rx_buf_sz;			/* Based on MTU+slack. */
+	struct netdev_desc *last_tx;		/* Last Tx descriptor used. */
+	unsigned int cur_tx, dirty_tx;
+	/* These values are keep track of the transceiver/media in use. */
+	unsigned int flowctrl:1;
+	unsigned int default_port:4;		/* Last dev->if_port value. */
+	unsigned int an_enable:1;
+	unsigned int speed;
+	unsigned int wol_enabled:1;			/* Wake on LAN enabled */
+	struct tasklet_struct rx_tasklet;
+	struct tasklet_struct tx_tasklet;
+	int budget;
+	int cur_task;
+	/* Multicast and receive mode. */
+	spinlock_t mcastlock;			/* SMP lock multicast updates. */
+	u16 mcast_filter[4];
+	/* MII transceiver section. */
+	struct mii_if_info mii_if;
+	int mii_preamble_required;
+	unsigned char phys[MII_CNT];		/* MII device addresses, only first one used. */
+	struct pci_dev *pci_dev;
+	void __iomem *base;
+	spinlock_t statlock;
+};
+
+/* The station address location in the EEPROM. */
+#define EEPROM_SA_OFFSET	0x10
+#define DEFAULT_INTR (IntrRxDMADone | IntrPCIErr | \
+			IntrDrvRqst | IntrTxDone | StatsMax | \
+			LinkChange)
+
+static int  change_mtu(struct net_device *dev, int new_mtu);
+static int  eeprom_read(void __iomem *ioaddr, int location);
+static int  mdio_read(struct net_device *dev, int phy_id, int location);
+static void mdio_write(struct net_device *dev, int phy_id, int location, int value);
+static int  mdio_wait_link(struct net_device *dev, int wait);
+static int  netdev_open(struct net_device *dev);
+static void check_duplex(struct net_device *dev);
+static void netdev_timer(struct timer_list *t);
+static void tx_timeout(struct net_device *dev, unsigned int txqueue);
+static void init_ring(struct net_device *dev);
+static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev);
+static int reset_tx (struct net_device *dev);
+static irqreturn_t intr_handler(int irq, void *dev_instance);
+static void rx_poll(struct tasklet_struct *t);
+static void tx_poll(struct tasklet_struct *t);
+static void refill_rx (struct net_device *dev);
+static void netdev_error(struct net_device *dev, int intr_status);
+static void netdev_error(struct net_device *dev, int intr_status);
+static void set_rx_mode(struct net_device *dev);
+static int __set_mac_addr(struct net_device *dev);
+static int sundance_set_mac_addr(struct net_device *dev, void *data);
+static struct net_device_stats *get_stats(struct net_device *dev);
+static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
+static int  netdev_close(struct net_device *dev);
+static const struct ethtool_ops ethtool_ops;
+
+static void sundance_reset(struct net_device *dev, unsigned long reset_cmd)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base + ASICCtrl;
+	int countdown;
+
+	/* ST201 documentation states ASICCtrl is a 32bit register */
+	iowrite32 (reset_cmd | ioread32 (ioaddr), ioaddr);
+	/* ST201 documentation states reset can take up to 1 ms */
+	countdown = 10 + 1;
+	while (ioread32 (ioaddr) & (ResetBusy << 16)) {
+		if (--countdown == 0) {
+			printk(KERN_WARNING "%s : reset not completed !!\n", dev->name);
+			break;
+		}
+		udelay(100);
+	}
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void sundance_poll_controller(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+
+	disable_irq(np->pci_dev->irq);
+	intr_handler(np->pci_dev->irq, dev);
+	enable_irq(np->pci_dev->irq);
+}
+#endif
+
+static const struct net_device_ops netdev_ops = {
+	.ndo_open		= netdev_open,
+	.ndo_stop		= netdev_close,
+	.ndo_start_xmit		= start_tx,
+	.ndo_get_stats 		= get_stats,
+	.ndo_set_rx_mode	= set_rx_mode,
+	.ndo_eth_ioctl		= netdev_ioctl,
+	.ndo_tx_timeout		= tx_timeout,
+	.ndo_change_mtu		= change_mtu,
+	.ndo_set_mac_address 	= sundance_set_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller 	= sundance_poll_controller,
+#endif
+};
+
+static int sundance_probe1(struct pci_dev *pdev,
+			   const struct pci_device_id *ent)
+{
+	struct net_device *dev;
+	struct netdev_private *np;
+	static int card_idx;
+	int chip_idx = ent->driver_data;
+	int irq;
+	int i;
+	void __iomem *ioaddr;
+	u16 mii_ctl;
+	void *ring_space;
+	dma_addr_t ring_dma;
+#ifdef USE_IO_OPS
+	int bar = 0;
+#else
+	int bar = 1;
+#endif
+	int phy, phy_end, phy_idx = 0;
+	__le16 addr[ETH_ALEN / 2];
+
+	if (pci_enable_device(pdev))
+		return -EIO;
+	pci_set_master(pdev);
+
+	irq = pdev->irq;
+
+	dev = alloc_etherdev(sizeof(*np));
+	if (!dev)
+		return -ENOMEM;
+	SET_NETDEV_DEV(dev, &pdev->dev);
+
+	if (pci_request_regions(pdev, DRV_NAME))
+		goto err_out_netdev;
+
+	ioaddr = pci_iomap(pdev, bar, netdev_io_size);
+	if (!ioaddr)
+		goto err_out_res;
+
+	for (i = 0; i < 3; i++)
+		addr[i] =
+			cpu_to_le16(eeprom_read(ioaddr, i + EEPROM_SA_OFFSET));
+	eth_hw_addr_set(dev, (u8 *)addr);
+
+	np = netdev_priv(dev);
+	np->ndev = dev;
+	np->base = ioaddr;
+	np->pci_dev = pdev;
+	np->chip_id = chip_idx;
+	np->msg_enable = (1 << debug) - 1;
+	spin_lock_init(&np->lock);
+	spin_lock_init(&np->statlock);
+	tasklet_setup(&np->rx_tasklet, rx_poll);
+	tasklet_setup(&np->tx_tasklet, tx_poll);
+
+	ring_space = dma_alloc_coherent(&pdev->dev, TX_TOTAL_SIZE,
+			&ring_dma, GFP_KERNEL);
+	if (!ring_space)
+		goto err_out_cleardev;
+	np->tx_ring = (struct netdev_desc *)ring_space;
+	np->tx_ring_dma = ring_dma;
+
+	ring_space = dma_alloc_coherent(&pdev->dev, RX_TOTAL_SIZE,
+			&ring_dma, GFP_KERNEL);
+	if (!ring_space)
+		goto err_out_unmap_tx;
+	np->rx_ring = (struct netdev_desc *)ring_space;
+	np->rx_ring_dma = ring_dma;
+
+	np->mii_if.dev = dev;
+	np->mii_if.mdio_read = mdio_read;
+	np->mii_if.mdio_write = mdio_write;
+	np->mii_if.phy_id_mask = 0x1f;
+	np->mii_if.reg_num_mask = 0x1f;
+
+	/* The chip-specific entries in the device structure. */
+	dev->netdev_ops = &netdev_ops;
+	dev->ethtool_ops = &ethtool_ops;
+	dev->watchdog_timeo = TX_TIMEOUT;
+
+	/* MTU range: 68 - 8191 */
+	dev->min_mtu = ETH_MIN_MTU;
+	dev->max_mtu = 8191;
+
+	pci_set_drvdata(pdev, dev);
+
+	i = register_netdev(dev);
+	if (i)
+		goto err_out_unmap_rx;
+
+	printk(KERN_INFO "%s: %s at %p, %pM, IRQ %d.\n",
+	       dev->name, pci_id_tbl[chip_idx].name, ioaddr,
+	       dev->dev_addr, irq);
+
+	np->phys[0] = 1;		/* Default setting */
+	np->mii_preamble_required++;
+
+	/*
+	 * It seems some phys doesn't deal well with address 0 being accessed
+	 * first
+	 */
+	if (sundance_pci_tbl[np->chip_id].device == 0x0200) {
+		phy = 0;
+		phy_end = 31;
+	} else {
+		phy = 1;
+		phy_end = 32;	/* wraps to zero, due to 'phy & 0x1f' */
+	}
+	for (; phy <= phy_end && phy_idx < MII_CNT; phy++) {
+		int phyx = phy & 0x1f;
+		int mii_status = mdio_read(dev, phyx, MII_BMSR);
+		if (mii_status != 0xffff  &&  mii_status != 0x0000) {
+			np->phys[phy_idx++] = phyx;
+			np->mii_if.advertising = mdio_read(dev, phyx, MII_ADVERTISE);
+			if ((mii_status & 0x0040) == 0)
+				np->mii_preamble_required++;
+			printk(KERN_INFO "%s: MII PHY found at address %d, status "
+				   "0x%4.4x advertising %4.4x.\n",
+				   dev->name, phyx, mii_status, np->mii_if.advertising);
+		}
+	}
+	np->mii_preamble_required--;
+
+	if (phy_idx == 0) {
+		printk(KERN_INFO "%s: No MII transceiver found, aborting.  ASIC status %x\n",
+			   dev->name, ioread32(ioaddr + ASICCtrl));
+		goto err_out_unregister;
+	}
+
+	np->mii_if.phy_id = np->phys[0];
+
+	/* Parse override configuration */
+	np->an_enable = 1;
+	if (card_idx < MAX_UNITS) {
+		if (media[card_idx] != NULL) {
+			np->an_enable = 0;
+			if (strcmp (media[card_idx], "100mbps_fd") == 0 ||
+			    strcmp (media[card_idx], "4") == 0) {
+				np->speed = 100;
+				np->mii_if.full_duplex = 1;
+			} else if (strcmp (media[card_idx], "100mbps_hd") == 0 ||
+				   strcmp (media[card_idx], "3") == 0) {
+				np->speed = 100;
+				np->mii_if.full_duplex = 0;
+			} else if (strcmp (media[card_idx], "10mbps_fd") == 0 ||
+				   strcmp (media[card_idx], "2") == 0) {
+				np->speed = 10;
+				np->mii_if.full_duplex = 1;
+			} else if (strcmp (media[card_idx], "10mbps_hd") == 0 ||
+				   strcmp (media[card_idx], "1") == 0) {
+				np->speed = 10;
+				np->mii_if.full_duplex = 0;
+			} else {
+				np->an_enable = 1;
+			}
+		}
+		if (flowctrl == 1)
+			np->flowctrl = 1;
+	}
+
+	/* Fibre PHY? */
+	if (ioread32 (ioaddr + ASICCtrl) & 0x80) {
+		/* Default 100Mbps Full */
+		if (np->an_enable) {
+			np->speed = 100;
+			np->mii_if.full_duplex = 1;
+			np->an_enable = 0;
+		}
+	}
+	/* Reset PHY */
+	mdio_write (dev, np->phys[0], MII_BMCR, BMCR_RESET);
+	mdelay (300);
+	/* If flow control enabled, we need to advertise it.*/
+	if (np->flowctrl)
+		mdio_write (dev, np->phys[0], MII_ADVERTISE, np->mii_if.advertising | 0x0400);
+	mdio_write (dev, np->phys[0], MII_BMCR, BMCR_ANENABLE|BMCR_ANRESTART);
+	/* Force media type */
+	if (!np->an_enable) {
+		mii_ctl = 0;
+		mii_ctl |= (np->speed == 100) ? BMCR_SPEED100 : 0;
+		mii_ctl |= (np->mii_if.full_duplex) ? BMCR_FULLDPLX : 0;
+		mdio_write (dev, np->phys[0], MII_BMCR, mii_ctl);
+		printk (KERN_INFO "Override speed=%d, %s duplex\n",
+			np->speed, np->mii_if.full_duplex ? "Full" : "Half");
+
+	}
+
+	/* Perhaps move the reset here? */
+	/* Reset the chip to erase previous misconfiguration. */
+	if (netif_msg_hw(np))
+		printk("ASIC Control is %x.\n", ioread32(ioaddr + ASICCtrl));
+	sundance_reset(dev, 0x00ff << 16);
+	if (netif_msg_hw(np))
+		printk("ASIC Control is now %x.\n", ioread32(ioaddr + ASICCtrl));
+
+	card_idx++;
+	return 0;
+
+err_out_unregister:
+	unregister_netdev(dev);
+err_out_unmap_rx:
+	dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE,
+		np->rx_ring, np->rx_ring_dma);
+err_out_unmap_tx:
+	dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE,
+		np->tx_ring, np->tx_ring_dma);
+err_out_cleardev:
+	pci_iounmap(pdev, ioaddr);
+err_out_res:
+	pci_release_regions(pdev);
+err_out_netdev:
+	free_netdev (dev);
+	return -ENODEV;
+}
+
+static int change_mtu(struct net_device *dev, int new_mtu)
+{
+	if (netif_running(dev))
+		return -EBUSY;
+	WRITE_ONCE(dev->mtu, new_mtu);
+	return 0;
+}
+
+#define eeprom_delay(ee_addr)	ioread32(ee_addr)
+/* Read the EEPROM and MII Management Data I/O (MDIO) interfaces. */
+static int eeprom_read(void __iomem *ioaddr, int location)
+{
+	int boguscnt = 10000;		/* Typical 1900 ticks. */
+	iowrite16(0x0200 | (location & 0xff), ioaddr + EECtrl);
+	do {
+		eeprom_delay(ioaddr + EECtrl);
+		if (! (ioread16(ioaddr + EECtrl) & 0x8000)) {
+			return ioread16(ioaddr + EEData);
+		}
+	} while (--boguscnt > 0);
+	return 0;
+}
+
+/*  MII transceiver control section.
+	Read and write the MII registers using software-generated serial
+	MDIO protocol.  See the MII specifications or DP83840A data sheet
+	for details.
+
+	The maximum data clock rate is 2.5 Mhz.  The minimum timing is usually
+	met by back-to-back 33Mhz PCI cycles. */
+#define mdio_delay() ioread8(mdio_addr)
+
+enum mii_reg_bits {
+	MDIO_ShiftClk=0x0001, MDIO_Data=0x0002, MDIO_EnbOutput=0x0004,
+};
+#define MDIO_EnbIn  (0)
+#define MDIO_WRITE0 (MDIO_EnbOutput)
+#define MDIO_WRITE1 (MDIO_Data | MDIO_EnbOutput)
+
+/* Generate the preamble required for initial synchronization and
+   a few older transceivers. */
+static void mdio_sync(void __iomem *mdio_addr)
+{
+	int bits = 32;
+
+	/* Establish sync by sending at least 32 logic ones. */
+	while (--bits >= 0) {
+		iowrite8(MDIO_WRITE1, mdio_addr);
+		mdio_delay();
+		iowrite8(MDIO_WRITE1 | MDIO_ShiftClk, mdio_addr);
+		mdio_delay();
+	}
+}
+
+static int mdio_read(struct net_device *dev, int phy_id, int location)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *mdio_addr = np->base + MIICtrl;
+	int mii_cmd = (0xf6 << 10) | (phy_id << 5) | location;
+	int i, retval = 0;
+
+	if (np->mii_preamble_required)
+		mdio_sync(mdio_addr);
+
+	/* Shift the read command bits out. */
+	for (i = 15; i >= 0; i--) {
+		int dataval = (mii_cmd & (1 << i)) ? MDIO_WRITE1 : MDIO_WRITE0;
+
+		iowrite8(dataval, mdio_addr);
+		mdio_delay();
+		iowrite8(dataval | MDIO_ShiftClk, mdio_addr);
+		mdio_delay();
+	}
+	/* Read the two transition, 16 data, and wire-idle bits. */
+	for (i = 19; i > 0; i--) {
+		iowrite8(MDIO_EnbIn, mdio_addr);
+		mdio_delay();
+		retval = (retval << 1) | ((ioread8(mdio_addr) & MDIO_Data) ? 1 : 0);
+		iowrite8(MDIO_EnbIn | MDIO_ShiftClk, mdio_addr);
+		mdio_delay();
+	}
+	return (retval>>1) & 0xffff;
+}
+
+static void mdio_write(struct net_device *dev, int phy_id, int location, int value)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *mdio_addr = np->base + MIICtrl;
+	int mii_cmd = (0x5002 << 16) | (phy_id << 23) | (location<<18) | value;
+	int i;
+
+	if (np->mii_preamble_required)
+		mdio_sync(mdio_addr);
+
+	/* Shift the command bits out. */
+	for (i = 31; i >= 0; i--) {
+		int dataval = (mii_cmd & (1 << i)) ? MDIO_WRITE1 : MDIO_WRITE0;
+
+		iowrite8(dataval, mdio_addr);
+		mdio_delay();
+		iowrite8(dataval | MDIO_ShiftClk, mdio_addr);
+		mdio_delay();
+	}
+	/* Clear out extra bits. */
+	for (i = 2; i > 0; i--) {
+		iowrite8(MDIO_EnbIn, mdio_addr);
+		mdio_delay();
+		iowrite8(MDIO_EnbIn | MDIO_ShiftClk, mdio_addr);
+		mdio_delay();
+	}
+}
+
+static int mdio_wait_link(struct net_device *dev, int wait)
+{
+	int bmsr;
+	int phy_id;
+	struct netdev_private *np;
+
+	np = netdev_priv(dev);
+	phy_id = np->phys[0];
+
+	do {
+		bmsr = mdio_read(dev, phy_id, MII_BMSR);
+		if (bmsr & 0x0004)
+			return 0;
+		mdelay(1);
+	} while (--wait > 0);
+	return -1;
+}
+
+static int netdev_open(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	const int irq = np->pci_dev->irq;
+	unsigned long flags;
+	int i;
+
+	sundance_reset(dev, 0x00ff << 16);
+
+	i = request_irq(irq, intr_handler, IRQF_SHARED, dev->name, dev);
+	if (i)
+		return i;
+
+	if (netif_msg_ifup(np))
+		printk(KERN_DEBUG "%s: netdev_open() irq %d\n", dev->name, irq);
+
+	init_ring(dev);
+
+	iowrite32(np->rx_ring_dma, ioaddr + RxListPtr);
+	/* The Tx list pointer is written as packets are queued. */
+
+	/* Initialize other registers. */
+	__set_mac_addr(dev);
+#if IS_ENABLED(CONFIG_VLAN_8021Q)
+	iowrite16(dev->mtu + 18, ioaddr + MaxFrameSize);
+#else
+	iowrite16(dev->mtu + 14, ioaddr + MaxFrameSize);
+#endif
+	if (dev->mtu > 2047)
+		iowrite32(ioread32(ioaddr + ASICCtrl) | 0x0C, ioaddr + ASICCtrl);
+
+	/* Configure the PCI bus bursts and FIFO thresholds. */
+
+	if (dev->if_port == 0)
+		dev->if_port = np->default_port;
+
+	spin_lock_init(&np->mcastlock);
+
+	set_rx_mode(dev);
+	iowrite16(0, ioaddr + IntrEnable);
+	iowrite16(0, ioaddr + DownCounter);
+	/* Set the chip to poll every N*320nsec. */
+	iowrite8(100, ioaddr + RxDMAPollPeriod);
+	iowrite8(127, ioaddr + TxDMAPollPeriod);
+	/* Fix DFE-580TX packet drop issue */
+	if (np->pci_dev->revision >= 0x14)
+		iowrite8(0x01, ioaddr + DebugCtrl1);
+	netif_start_queue(dev);
+
+	spin_lock_irqsave(&np->lock, flags);
+	reset_tx(dev);
+	spin_unlock_irqrestore(&np->lock, flags);
+
+	iowrite16 (StatsEnable | RxEnable | TxEnable, ioaddr + MACCtrl1);
+
+	/* Disable Wol */
+	iowrite8(ioread8(ioaddr + WakeEvent) | 0x00, ioaddr + WakeEvent);
+	np->wol_enabled = 0;
+
+	if (netif_msg_ifup(np))
+		printk(KERN_DEBUG "%s: Done netdev_open(), status: Rx %x Tx %x "
+			   "MAC Control %x, %4.4x %4.4x.\n",
+			   dev->name, ioread32(ioaddr + RxStatus), ioread8(ioaddr + TxStatus),
+			   ioread32(ioaddr + MACCtrl0),
+			   ioread16(ioaddr + MACCtrl1), ioread16(ioaddr + MACCtrl0));
+
+	/* Set the timer to check for link beat. */
+	timer_setup(&np->timer, netdev_timer, 0);
+	np->timer.expires = jiffies + 3*HZ;
+	add_timer(&np->timer);
+
+	/* Enable interrupts by setting the interrupt mask. */
+	iowrite16(DEFAULT_INTR, ioaddr + IntrEnable);
+
+	return 0;
+}
+
+static void check_duplex(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	int mii_lpa = mdio_read(dev, np->phys[0], MII_LPA);
+	int negotiated = mii_lpa & np->mii_if.advertising;
+	int duplex;
+
+	/* Force media */
+	if (!np->an_enable || mii_lpa == 0xffff) {
+		if (np->mii_if.full_duplex)
+			iowrite16 (ioread16 (ioaddr + MACCtrl0) | EnbFullDuplex,
+				ioaddr + MACCtrl0);
+		return;
+	}
+
+	/* Autonegotiation */
+	duplex = (negotiated & 0x0100) || (negotiated & 0x01C0) == 0x0040;
+	if (np->mii_if.full_duplex != duplex) {
+		np->mii_if.full_duplex = duplex;
+		if (netif_msg_link(np))
+			printk(KERN_INFO "%s: Setting %s-duplex based on MII #%d "
+				   "negotiated capability %4.4x.\n", dev->name,
+				   duplex ? "full" : "half", np->phys[0], negotiated);
+		iowrite16(ioread16(ioaddr + MACCtrl0) | (duplex ? 0x20 : 0), ioaddr + MACCtrl0);
+	}
+}
+
+static void netdev_timer(struct timer_list *t)
+{
+	struct netdev_private *np = timer_container_of(np, t, timer);
+	struct net_device *dev = np->mii_if.dev;
+	void __iomem *ioaddr = np->base;
+	int next_tick = 10*HZ;
+
+	if (netif_msg_timer(np)) {
+		printk(KERN_DEBUG "%s: Media selection timer tick, intr status %4.4x, "
+			   "Tx %x Rx %x.\n",
+			   dev->name, ioread16(ioaddr + IntrEnable),
+			   ioread8(ioaddr + TxStatus), ioread32(ioaddr + RxStatus));
+	}
+	check_duplex(dev);
+	np->timer.expires = jiffies + next_tick;
+	add_timer(&np->timer);
+}
+
+static void tx_timeout(struct net_device *dev, unsigned int txqueue)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	unsigned long flag;
+
+	netif_stop_queue(dev);
+	tasklet_disable_in_atomic(&np->tx_tasklet);
+	iowrite16(0, ioaddr + IntrEnable);
+	printk(KERN_WARNING "%s: Transmit timed out, TxStatus %2.2x "
+		   "TxFrameId %2.2x,"
+		   " resetting...\n", dev->name, ioread8(ioaddr + TxStatus),
+		   ioread8(ioaddr + TxFrameId));
+
+	{
+		int i;
+		for (i=0; i<TX_RING_SIZE; i++) {
+			printk(KERN_DEBUG "%02x %08llx %08x %08x(%02x) %08x %08x\n", i,
+				(unsigned long long)(np->tx_ring_dma + i*sizeof(*np->tx_ring)),
+				le32_to_cpu(np->tx_ring[i].next_desc),
+				le32_to_cpu(np->tx_ring[i].status),
+				(le32_to_cpu(np->tx_ring[i].status) >> 2) & 0xff,
+				le32_to_cpu(np->tx_ring[i].frag.addr),
+				le32_to_cpu(np->tx_ring[i].frag.length));
+		}
+		printk(KERN_DEBUG "TxListPtr=%08x netif_queue_stopped=%d\n",
+			ioread32(np->base + TxListPtr),
+			netif_queue_stopped(dev));
+		printk(KERN_DEBUG "cur_tx=%d(%02x) dirty_tx=%d(%02x)\n",
+			np->cur_tx, np->cur_tx % TX_RING_SIZE,
+			np->dirty_tx, np->dirty_tx % TX_RING_SIZE);
+		printk(KERN_DEBUG "cur_rx=%d dirty_rx=%d\n", np->cur_rx, np->dirty_rx);
+		printk(KERN_DEBUG "cur_task=%d\n", np->cur_task);
+	}
+	spin_lock_irqsave(&np->lock, flag);
+
+	/* Stop and restart the chip's Tx processes . */
+	reset_tx(dev);
+	spin_unlock_irqrestore(&np->lock, flag);
+
+	dev->if_port = 0;
+
+	netif_trans_update(dev); /* prevent tx timeout */
+	dev->stats.tx_errors++;
+	if (np->cur_tx - np->dirty_tx < TX_QUEUE_LEN - 4) {
+		netif_wake_queue(dev);
+	}
+	iowrite16(DEFAULT_INTR, ioaddr + IntrEnable);
+	tasklet_enable(&np->tx_tasklet);
+}
+
+
+/* Initialize the Rx and Tx rings, along with various 'dev' bits. */
+static void init_ring(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	int i;
+
+	np->cur_rx = np->cur_tx = 0;
+	np->dirty_rx = np->dirty_tx = 0;
+	np->cur_task = 0;
+
+	np->rx_buf_sz = (dev->mtu <= 1520 ? PKT_BUF_SZ : dev->mtu + 16);
+
+	/* Initialize all Rx descriptors. */
+	for (i = 0; i < RX_RING_SIZE; i++) {
+		np->rx_ring[i].next_desc = cpu_to_le32(np->rx_ring_dma +
+			((i+1)%RX_RING_SIZE)*sizeof(*np->rx_ring));
+		np->rx_ring[i].status = 0;
+		np->rx_ring[i].frag.length = 0;
+		np->rx_skbuff[i] = NULL;
+	}
+
+	/* Fill in the Rx buffers.  Handle allocation failure gracefully. */
+	for (i = 0; i < RX_RING_SIZE; i++) {
+		dma_addr_t addr;
+
+		struct sk_buff *skb =
+			netdev_alloc_skb(dev, np->rx_buf_sz + 2);
+		np->rx_skbuff[i] = skb;
+		if (skb == NULL)
+			break;
+		skb_reserve(skb, 2);	/* 16 byte align the IP header. */
+		addr = dma_map_single(&np->pci_dev->dev, skb->data,
+				      np->rx_buf_sz, DMA_FROM_DEVICE);
+		if (dma_mapping_error(&np->pci_dev->dev, addr)) {
+			dev_kfree_skb(skb);
+			np->rx_skbuff[i] = NULL;
+			break;
+		}
+		np->rx_ring[i].frag.addr = cpu_to_le32(addr);
+		np->rx_ring[i].frag.length = cpu_to_le32(np->rx_buf_sz | LastFrag);
+	}
+	np->dirty_rx = (unsigned int)(i - RX_RING_SIZE);
+
+	for (i = 0; i < TX_RING_SIZE; i++) {
+		np->tx_skbuff[i] = NULL;
+		np->tx_ring[i].status = 0;
+	}
+}
+
+static void tx_poll(struct tasklet_struct *t)
+{
+	struct netdev_private *np = from_tasklet(np, t, tx_tasklet);
+	unsigned head = np->cur_task % TX_RING_SIZE;
+	struct netdev_desc *txdesc =
+		&np->tx_ring[(np->cur_tx - 1) % TX_RING_SIZE];
+
+	/* Chain the next pointer */
+	for (; np->cur_tx - np->cur_task > 0; np->cur_task++) {
+		int entry = np->cur_task % TX_RING_SIZE;
+		txdesc = &np->tx_ring[entry];
+		if (np->last_tx) {
+			np->last_tx->next_desc = cpu_to_le32(np->tx_ring_dma +
+				entry*sizeof(struct netdev_desc));
+		}
+		np->last_tx = txdesc;
+	}
+	/* Indicate the latest descriptor of tx ring */
+	txdesc->status |= cpu_to_le32(DescIntrOnTx);
+
+	if (ioread32 (np->base + TxListPtr) == 0)
+		iowrite32 (np->tx_ring_dma + head * sizeof(struct netdev_desc),
+			np->base + TxListPtr);
+}
+
+static netdev_tx_t
+start_tx (struct sk_buff *skb, struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	struct netdev_desc *txdesc;
+	dma_addr_t addr;
+	unsigned entry;
+
+	/* Calculate the next Tx descriptor entry. */
+	entry = np->cur_tx % TX_RING_SIZE;
+	np->tx_skbuff[entry] = skb;
+	txdesc = &np->tx_ring[entry];
+
+	addr = dma_map_single(&np->pci_dev->dev, skb->data, skb->len,
+			      DMA_TO_DEVICE);
+	if (dma_mapping_error(&np->pci_dev->dev, addr))
+		goto drop_frame;
+
+	txdesc->next_desc = 0;
+	txdesc->status = cpu_to_le32 ((entry << 2) | DisableAlign);
+	txdesc->frag.addr = cpu_to_le32(addr);
+	txdesc->frag.length = cpu_to_le32 (skb->len | LastFrag);
+
+	/* Increment cur_tx before tasklet_schedule() */
+	np->cur_tx++;
+	mb();
+	/* Schedule a tx_poll() task */
+	tasklet_schedule(&np->tx_tasklet);
+
+	/* On some architectures: explicitly flush cache lines here. */
+	if (np->cur_tx - np->dirty_tx < TX_QUEUE_LEN - 1 &&
+	    !netif_queue_stopped(dev)) {
+		/* do nothing */
+	} else {
+		netif_stop_queue (dev);
+	}
+	if (netif_msg_tx_queued(np)) {
+		printk (KERN_DEBUG
+			"%s: Transmit frame #%d queued in slot %d.\n",
+			dev->name, np->cur_tx, entry);
+	}
+	return NETDEV_TX_OK;
+
+drop_frame:
+	dev_kfree_skb_any(skb);
+	np->tx_skbuff[entry] = NULL;
+	dev->stats.tx_dropped++;
+	return NETDEV_TX_OK;
+}
+
+/* Reset hardware tx and free all of tx buffers */
+static int
+reset_tx (struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	struct sk_buff *skb;
+	int i;
+
+	/* Reset tx logic, TxListPtr will be cleaned */
+	iowrite16 (TxDisable, ioaddr + MACCtrl1);
+	sundance_reset(dev, (NetworkReset|FIFOReset|DMAReset|TxReset) << 16);
+
+	/* free all tx skbuff */
+	for (i = 0; i < TX_RING_SIZE; i++) {
+		np->tx_ring[i].next_desc = 0;
+
+		skb = np->tx_skbuff[i];
+		if (skb) {
+			dma_unmap_single(&np->pci_dev->dev,
+				le32_to_cpu(np->tx_ring[i].frag.addr),
+				skb->len, DMA_TO_DEVICE);
+			dev_kfree_skb_any(skb);
+			np->tx_skbuff[i] = NULL;
+			dev->stats.tx_dropped++;
+		}
+	}
+	np->cur_tx = np->dirty_tx = 0;
+	np->cur_task = 0;
+
+	np->last_tx = NULL;
+	iowrite8(127, ioaddr + TxDMAPollPeriod);
+
+	iowrite16 (StatsEnable | RxEnable | TxEnable, ioaddr + MACCtrl1);
+	return 0;
+}
+
+/* The interrupt handler cleans up after the Tx thread,
+   and schedule a Rx thread work */
+static irqreturn_t intr_handler(int irq, void *dev_instance)
+{
+	struct net_device *dev = (struct net_device *)dev_instance;
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	int hw_frame_id;
+	int tx_cnt;
+	int tx_status;
+	int handled = 0;
+	int i;
+
+	do {
+		int intr_status = ioread16(ioaddr + IntrStatus);
+		iowrite16(intr_status, ioaddr + IntrStatus);
+
+		if (netif_msg_intr(np))
+			printk(KERN_DEBUG "%s: Interrupt, status %4.4x.\n",
+				   dev->name, intr_status);
+
+		if (!(intr_status & DEFAULT_INTR))
+			break;
+
+		handled = 1;
+
+		if (intr_status & (IntrRxDMADone)) {
+			iowrite16(DEFAULT_INTR & ~(IntrRxDone|IntrRxDMADone),
+					ioaddr + IntrEnable);
+			if (np->budget < 0)
+				np->budget = RX_BUDGET;
+			tasklet_schedule(&np->rx_tasklet);
+		}
+		if (intr_status & (IntrTxDone | IntrDrvRqst)) {
+			tx_status = ioread16 (ioaddr + TxStatus);
+			for (tx_cnt=32; tx_status & 0x80; --tx_cnt) {
+				if (netif_msg_tx_done(np))
+					printk
+					    ("%s: Transmit status is %2.2x.\n",
+				     	dev->name, tx_status);
+				if (tx_status & 0x1e) {
+					if (netif_msg_tx_err(np))
+						printk("%s: Transmit error status %4.4x.\n",
+							   dev->name, tx_status);
+					dev->stats.tx_errors++;
+					if (tx_status & 0x10)
+						dev->stats.tx_fifo_errors++;
+					if (tx_status & 0x08)
+						dev->stats.collisions++;
+					if (tx_status & 0x04)
+						dev->stats.tx_fifo_errors++;
+					if (tx_status & 0x02)
+						dev->stats.tx_window_errors++;
+
+					/*
+					** This reset has been verified on
+					** DFE-580TX boards ! phdm@macqel.be.
+					*/
+					if (tx_status & 0x10) {	/* TxUnderrun */
+						/* Restart Tx FIFO and transmitter */
+						sundance_reset(dev, (NetworkReset|FIFOReset|TxReset) << 16);
+						/* No need to reset the Tx pointer here */
+					}
+					/* Restart the Tx. Need to make sure tx enabled */
+					i = 10;
+					do {
+						iowrite16(ioread16(ioaddr + MACCtrl1) | TxEnable, ioaddr + MACCtrl1);
+						if (ioread16(ioaddr + MACCtrl1) & TxEnabled)
+							break;
+						mdelay(1);
+					} while (--i);
+				}
+				/* Yup, this is a documentation bug.  It cost me *hours*. */
+				iowrite16 (0, ioaddr + TxStatus);
+				if (tx_cnt < 0) {
+					iowrite32(5000, ioaddr + DownCounter);
+					break;
+				}
+				tx_status = ioread16 (ioaddr + TxStatus);
+			}
+			hw_frame_id = (tx_status >> 8) & 0xff;
+		} else 	{
+			hw_frame_id = ioread8(ioaddr + TxFrameId);
+		}
+
+		if (np->pci_dev->revision >= 0x14) {
+			spin_lock(&np->lock);
+			for (; np->cur_tx - np->dirty_tx > 0; np->dirty_tx++) {
+				int entry = np->dirty_tx % TX_RING_SIZE;
+				struct sk_buff *skb;
+				int sw_frame_id;
+				sw_frame_id = (le32_to_cpu(
+					np->tx_ring[entry].status) >> 2) & 0xff;
+				if (sw_frame_id == hw_frame_id &&
+					!(le32_to_cpu(np->tx_ring[entry].status)
+					& 0x00010000))
+						break;
+				if (sw_frame_id == (hw_frame_id + 1) %
+					TX_RING_SIZE)
+						break;
+				skb = np->tx_skbuff[entry];
+				/* Free the original skb. */
+				dma_unmap_single(&np->pci_dev->dev,
+					le32_to_cpu(np->tx_ring[entry].frag.addr),
+					skb->len, DMA_TO_DEVICE);
+				dev_consume_skb_irq(np->tx_skbuff[entry]);
+				np->tx_skbuff[entry] = NULL;
+				np->tx_ring[entry].frag.addr = 0;
+				np->tx_ring[entry].frag.length = 0;
+			}
+			spin_unlock(&np->lock);
+		} else {
+			spin_lock(&np->lock);
+			for (; np->cur_tx - np->dirty_tx > 0; np->dirty_tx++) {
+				int entry = np->dirty_tx % TX_RING_SIZE;
+				struct sk_buff *skb;
+				if (!(le32_to_cpu(np->tx_ring[entry].status)
+							& 0x00010000))
+					break;
+				skb = np->tx_skbuff[entry];
+				/* Free the original skb. */
+				dma_unmap_single(&np->pci_dev->dev,
+					le32_to_cpu(np->tx_ring[entry].frag.addr),
+					skb->len, DMA_TO_DEVICE);
+				dev_consume_skb_irq(np->tx_skbuff[entry]);
+				np->tx_skbuff[entry] = NULL;
+				np->tx_ring[entry].frag.addr = 0;
+				np->tx_ring[entry].frag.length = 0;
+			}
+			spin_unlock(&np->lock);
+		}
+
+		if (netif_queue_stopped(dev) &&
+			np->cur_tx - np->dirty_tx < TX_QUEUE_LEN - 4) {
+			/* The ring is no longer full, clear busy flag. */
+			netif_wake_queue (dev);
+		}
+		/* Abnormal error summary/uncommon events handlers. */
+		if (intr_status & (IntrPCIErr | LinkChange | StatsMax))
+			netdev_error(dev, intr_status);
+	} while (0);
+	if (netif_msg_intr(np))
+		printk(KERN_DEBUG "%s: exiting interrupt, status=%#4.4x.\n",
+			   dev->name, ioread16(ioaddr + IntrStatus));
+	return IRQ_RETVAL(handled);
+}
+
+static void rx_poll(struct tasklet_struct *t)
+{
+	struct netdev_private *np = from_tasklet(np, t, rx_tasklet);
+	struct net_device *dev = np->ndev;
+	int entry = np->cur_rx % RX_RING_SIZE;
+	int boguscnt = np->budget;
+	void __iomem *ioaddr = np->base;
+	int received = 0;
+
+	/* If EOP is set on the next entry, it's a new packet. Send it up. */
+	while (1) {
+		struct netdev_desc *desc = &(np->rx_ring[entry]);
+		u32 frame_status = le32_to_cpu(desc->status);
+		int pkt_len;
+
+		if (--boguscnt < 0) {
+			goto not_done;
+		}
+		if (!(frame_status & DescOwn))
+			break;
+		pkt_len = frame_status & 0x1fff;	/* Chip omits the CRC. */
+		if (netif_msg_rx_status(np))
+			printk(KERN_DEBUG "  netdev_rx() status was %8.8x.\n",
+				   frame_status);
+		if (frame_status & 0x001f4000) {
+			/* There was a error. */
+			if (netif_msg_rx_err(np))
+				printk(KERN_DEBUG "  netdev_rx() Rx error was %8.8x.\n",
+					   frame_status);
+			dev->stats.rx_errors++;
+			if (frame_status & 0x00100000)
+				dev->stats.rx_length_errors++;
+			if (frame_status & 0x00010000)
+				dev->stats.rx_fifo_errors++;
+			if (frame_status & 0x00060000)
+				dev->stats.rx_frame_errors++;
+			if (frame_status & 0x00080000)
+				dev->stats.rx_crc_errors++;
+			if (frame_status & 0x00100000) {
+				printk(KERN_WARNING "%s: Oversized Ethernet frame,"
+					   " status %8.8x.\n",
+					   dev->name, frame_status);
+			}
+		} else {
+			struct sk_buff *skb;
+#ifndef final_version
+			if (netif_msg_rx_status(np))
+				printk(KERN_DEBUG "  netdev_rx() normal Rx pkt length %d"
+					   ", bogus_cnt %d.\n",
+					   pkt_len, boguscnt);
+#endif
+			/* Check if the packet is long enough to accept without copying
+			   to a minimally-sized skbuff. */
+			if (pkt_len < rx_copybreak &&
+			    (skb = netdev_alloc_skb(dev, pkt_len + 2)) != NULL) {
+				skb_reserve(skb, 2);	/* 16 byte align the IP header */
+				dma_sync_single_for_cpu(&np->pci_dev->dev,
+						le32_to_cpu(desc->frag.addr),
+						np->rx_buf_sz, DMA_FROM_DEVICE);
+				skb_copy_to_linear_data(skb, np->rx_skbuff[entry]->data, pkt_len);
+				dma_sync_single_for_device(&np->pci_dev->dev,
+						le32_to_cpu(desc->frag.addr),
+						np->rx_buf_sz, DMA_FROM_DEVICE);
+				skb_put(skb, pkt_len);
+			} else {
+				dma_unmap_single(&np->pci_dev->dev,
+					le32_to_cpu(desc->frag.addr),
+					np->rx_buf_sz, DMA_FROM_DEVICE);
+				skb_put(skb = np->rx_skbuff[entry], pkt_len);
+				np->rx_skbuff[entry] = NULL;
+			}
+			skb->protocol = eth_type_trans(skb, dev);
+			/* Note: checksum -> skb->ip_summed = CHECKSUM_UNNECESSARY; */
+			netif_rx(skb);
+		}
+		entry = (entry + 1) % RX_RING_SIZE;
+		received++;
+	}
+	np->cur_rx = entry;
+	refill_rx (dev);
+	np->budget -= received;
+	iowrite16(DEFAULT_INTR, ioaddr + IntrEnable);
+	return;
+
+not_done:
+	np->cur_rx = entry;
+	refill_rx (dev);
+	if (!received)
+		received = 1;
+	np->budget -= received;
+	if (np->budget <= 0)
+		np->budget = RX_BUDGET;
+	tasklet_schedule(&np->rx_tasklet);
+}
+
+static void refill_rx (struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	int entry;
+
+	/* Refill the Rx ring buffers. */
+	for (;(np->cur_rx - np->dirty_rx + RX_RING_SIZE) % RX_RING_SIZE > 0;
+		np->dirty_rx = (np->dirty_rx + 1) % RX_RING_SIZE) {
+		struct sk_buff *skb;
+		dma_addr_t addr;
+
+		entry = np->dirty_rx % RX_RING_SIZE;
+		if (np->rx_skbuff[entry] == NULL) {
+			skb = netdev_alloc_skb(dev, np->rx_buf_sz + 2);
+			np->rx_skbuff[entry] = skb;
+			if (skb == NULL)
+				break;		/* Better luck next round. */
+			skb_reserve(skb, 2);	/* Align IP on 16 byte boundaries */
+			addr = dma_map_single(&np->pci_dev->dev, skb->data,
+					      np->rx_buf_sz, DMA_FROM_DEVICE);
+			if (dma_mapping_error(&np->pci_dev->dev, addr)) {
+			    dev_kfree_skb_irq(skb);
+			    np->rx_skbuff[entry] = NULL;
+			    break;
+			}
+
+			np->rx_ring[entry].frag.addr = cpu_to_le32(addr);
+		}
+		/* Perhaps we need not reset this field. */
+		np->rx_ring[entry].frag.length =
+			cpu_to_le32(np->rx_buf_sz | LastFrag);
+		np->rx_ring[entry].status = 0;
+	}
+}
+static void netdev_error(struct net_device *dev, int intr_status)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	u16 mii_ctl, mii_advertise, mii_lpa;
+	int speed;
+
+	if (intr_status & LinkChange) {
+		if (mdio_wait_link(dev, 10) == 0) {
+			printk(KERN_INFO "%s: Link up\n", dev->name);
+			if (np->an_enable) {
+				mii_advertise = mdio_read(dev, np->phys[0],
+							   MII_ADVERTISE);
+				mii_lpa = mdio_read(dev, np->phys[0], MII_LPA);
+				mii_advertise &= mii_lpa;
+				printk(KERN_INFO "%s: Link changed: ",
+					dev->name);
+				if (mii_advertise & ADVERTISE_100FULL) {
+					np->speed = 100;
+					printk("100Mbps, full duplex\n");
+				} else if (mii_advertise & ADVERTISE_100HALF) {
+					np->speed = 100;
+					printk("100Mbps, half duplex\n");
+				} else if (mii_advertise & ADVERTISE_10FULL) {
+					np->speed = 10;
+					printk("10Mbps, full duplex\n");
+				} else if (mii_advertise & ADVERTISE_10HALF) {
+					np->speed = 10;
+					printk("10Mbps, half duplex\n");
+				} else
+					printk("\n");
+
+			} else {
+				mii_ctl = mdio_read(dev, np->phys[0], MII_BMCR);
+				speed = (mii_ctl & BMCR_SPEED100) ? 100 : 10;
+				np->speed = speed;
+				printk(KERN_INFO "%s: Link changed: %dMbps ,",
+					dev->name, speed);
+				printk("%s duplex.\n",
+					(mii_ctl & BMCR_FULLDPLX) ?
+						"full" : "half");
+			}
+			check_duplex(dev);
+			if (np->flowctrl && np->mii_if.full_duplex) {
+				iowrite16(ioread16(ioaddr + MulticastFilter1+2) | 0x0200,
+					ioaddr + MulticastFilter1+2);
+				iowrite16(ioread16(ioaddr + MACCtrl0) | EnbFlowCtrl,
+					ioaddr + MACCtrl0);
+			}
+			netif_carrier_on(dev);
+		} else {
+			printk(KERN_INFO "%s: Link down\n", dev->name);
+			netif_carrier_off(dev);
+		}
+	}
+	if (intr_status & StatsMax) {
+		get_stats(dev);
+	}
+	if (intr_status & IntrPCIErr) {
+		printk(KERN_ERR "%s: Something Wicked happened! %4.4x.\n",
+			   dev->name, intr_status);
+		/* We must do a global reset of DMA to continue. */
+	}
+}
+
+static struct net_device_stats *get_stats(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	unsigned long flags;
+	u8 late_coll, single_coll, mult_coll;
+
+	spin_lock_irqsave(&np->statlock, flags);
+	/* The chip only need report frame silently dropped. */
+	dev->stats.rx_missed_errors	+= ioread8(ioaddr + RxMissed);
+	dev->stats.tx_packets += ioread16(ioaddr + TxFramesOK);
+	dev->stats.rx_packets += ioread16(ioaddr + RxFramesOK);
+	dev->stats.tx_carrier_errors += ioread8(ioaddr + StatsCarrierError);
+
+	mult_coll = ioread8(ioaddr + StatsMultiColl);
+	np->xstats.tx_multiple_collisions += mult_coll;
+	single_coll = ioread8(ioaddr + StatsOneColl);
+	np->xstats.tx_single_collisions += single_coll;
+	late_coll = ioread8(ioaddr + StatsLateColl);
+	np->xstats.tx_late_collisions += late_coll;
+	dev->stats.collisions += mult_coll
+		+ single_coll
+		+ late_coll;
+
+	np->xstats.tx_deferred += ioread8(ioaddr + StatsTxDefer);
+	np->xstats.tx_deferred_excessive += ioread8(ioaddr + StatsTxXSDefer);
+	np->xstats.tx_aborted += ioread8(ioaddr + StatsTxAbort);
+	np->xstats.tx_bcasts += ioread8(ioaddr + StatsBcastTx);
+	np->xstats.rx_bcasts += ioread8(ioaddr + StatsBcastRx);
+	np->xstats.tx_mcasts += ioread8(ioaddr + StatsMcastTx);
+	np->xstats.rx_mcasts += ioread8(ioaddr + StatsMcastRx);
+
+	dev->stats.tx_bytes += ioread16(ioaddr + TxOctetsLow);
+	dev->stats.tx_bytes += ioread16(ioaddr + TxOctetsHigh) << 16;
+	dev->stats.rx_bytes += ioread16(ioaddr + RxOctetsLow);
+	dev->stats.rx_bytes += ioread16(ioaddr + RxOctetsHigh) << 16;
+
+	spin_unlock_irqrestore(&np->statlock, flags);
+
+	return &dev->stats;
+}
+
+static void set_rx_mode(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	u16 mc_filter[4];			/* Multicast hash filter */
+	u32 rx_mode;
+	int i;
+
+	if (dev->flags & IFF_PROMISC) {			/* Set promiscuous. */
+		memset(mc_filter, 0xff, sizeof(mc_filter));
+		rx_mode = AcceptBroadcast | AcceptMulticast | AcceptAll | AcceptMyPhys;
+	} else if ((netdev_mc_count(dev) > multicast_filter_limit) ||
+		   (dev->flags & IFF_ALLMULTI)) {
+		/* Too many to match, or accept all multicasts. */
+		memset(mc_filter, 0xff, sizeof(mc_filter));
+		rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys;
+	} else if (!netdev_mc_empty(dev)) {
+		struct netdev_hw_addr *ha;
+		int bit;
+		int index;
+		int crc;
+		memset (mc_filter, 0, sizeof (mc_filter));
+		netdev_for_each_mc_addr(ha, dev) {
+			crc = ether_crc_le(ETH_ALEN, ha->addr);
+			for (index=0, bit=0; bit < 6; bit++, crc <<= 1)
+				if (crc & 0x80000000) index |= 1 << bit;
+			mc_filter[index/16] |= (1 << (index % 16));
+		}
+		rx_mode = AcceptBroadcast | AcceptMultiHash | AcceptMyPhys;
+	} else {
+		iowrite8(AcceptBroadcast | AcceptMyPhys, ioaddr + RxMode);
+		return;
+	}
+	if (np->mii_if.full_duplex && np->flowctrl)
+		mc_filter[3] |= 0x0200;
+
+	for (i = 0; i < 4; i++)
+		iowrite16(mc_filter[i], ioaddr + MulticastFilter0 + i*2);
+	iowrite8(rx_mode, ioaddr + RxMode);
+}
+
+static int __set_mac_addr(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	u16 addr16;
+
+	addr16 = (dev->dev_addr[0] | (dev->dev_addr[1] << 8));
+	iowrite16(addr16, np->base + StationAddr);
+	addr16 = (dev->dev_addr[2] | (dev->dev_addr[3] << 8));
+	iowrite16(addr16, np->base + StationAddr+2);
+	addr16 = (dev->dev_addr[4] | (dev->dev_addr[5] << 8));
+	iowrite16(addr16, np->base + StationAddr+4);
+	return 0;
+}
+
+/* Invoked with rtnl_lock held */
+static int sundance_set_mac_addr(struct net_device *dev, void *data)
+{
+	const struct sockaddr *addr = data;
+
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+	eth_hw_addr_set(dev, addr->sa_data);
+	__set_mac_addr(dev);
+
+	return 0;
+}
+
+static const struct {
+	const char name[ETH_GSTRING_LEN];
+} sundance_stats[] = {
+	{ "tx_multiple_collisions" },
+	{ "tx_single_collisions" },
+	{ "tx_late_collisions" },
+	{ "tx_deferred" },
+	{ "tx_deferred_excessive" },
+	{ "tx_aborted" },
+	{ "tx_bcasts" },
+	{ "rx_bcasts" },
+	{ "tx_mcasts" },
+	{ "rx_mcasts" },
+};
+
+static int check_if_running(struct net_device *dev)
+{
+	if (!netif_running(dev))
+		return -EINVAL;
+	return 0;
+}
+
+static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	strscpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strscpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
+}
+
+static int get_link_ksettings(struct net_device *dev,
+			      struct ethtool_link_ksettings *cmd)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	spin_lock_irq(&np->lock);
+	mii_ethtool_get_link_ksettings(&np->mii_if, cmd);
+	spin_unlock_irq(&np->lock);
+	return 0;
+}
+
+static int set_link_ksettings(struct net_device *dev,
+			      const struct ethtool_link_ksettings *cmd)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	int res;
+	spin_lock_irq(&np->lock);
+	res = mii_ethtool_set_link_ksettings(&np->mii_if, cmd);
+	spin_unlock_irq(&np->lock);
+	return res;
+}
+
+static int nway_reset(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	return mii_nway_restart(&np->mii_if);
+}
+
+static u32 get_link(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	return mii_link_ok(&np->mii_if);
+}
+
+static u32 get_msglevel(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	return np->msg_enable;
+}
+
+static void set_msglevel(struct net_device *dev, u32 val)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	np->msg_enable = val;
+}
+
+static void get_strings(struct net_device *dev, u32 stringset,
+		u8 *data)
+{
+	if (stringset == ETH_SS_STATS)
+		memcpy(data, sundance_stats, sizeof(sundance_stats));
+}
+
+static int get_sset_count(struct net_device *dev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+		return ARRAY_SIZE(sundance_stats);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void get_ethtool_stats(struct net_device *dev,
+		struct ethtool_stats *stats, u64 *data)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	int i = 0;
+
+	get_stats(dev);
+	data[i++] = np->xstats.tx_multiple_collisions;
+	data[i++] = np->xstats.tx_single_collisions;
+	data[i++] = np->xstats.tx_late_collisions;
+	data[i++] = np->xstats.tx_deferred;
+	data[i++] = np->xstats.tx_deferred_excessive;
+	data[i++] = np->xstats.tx_aborted;
+	data[i++] = np->xstats.tx_bcasts;
+	data[i++] = np->xstats.rx_bcasts;
+	data[i++] = np->xstats.tx_mcasts;
+	data[i++] = np->xstats.rx_mcasts;
+}
+
+#ifdef CONFIG_PM
+
+static void sundance_get_wol(struct net_device *dev,
+		struct ethtool_wolinfo *wol)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	u8 wol_bits;
+
+	wol->wolopts = 0;
+
+	wol->supported = (WAKE_PHY | WAKE_MAGIC);
+	if (!np->wol_enabled)
+		return;
+
+	wol_bits = ioread8(ioaddr + WakeEvent);
+	if (wol_bits & MagicPktEnable)
+		wol->wolopts |= WAKE_MAGIC;
+	if (wol_bits & LinkEventEnable)
+		wol->wolopts |= WAKE_PHY;
+}
+
+static int sundance_set_wol(struct net_device *dev,
+	struct ethtool_wolinfo *wol)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	u8 wol_bits;
+
+	if (!device_can_wakeup(&np->pci_dev->dev))
+		return -EOPNOTSUPP;
+
+	np->wol_enabled = !!(wol->wolopts);
+	wol_bits = ioread8(ioaddr + WakeEvent);
+	wol_bits &= ~(WakePktEnable | MagicPktEnable |
+			LinkEventEnable | WolEnable);
+
+	if (np->wol_enabled) {
+		if (wol->wolopts & WAKE_MAGIC)
+			wol_bits |= (MagicPktEnable | WolEnable);
+		if (wol->wolopts & WAKE_PHY)
+			wol_bits |= (LinkEventEnable | WolEnable);
+	}
+	iowrite8(wol_bits, ioaddr + WakeEvent);
+
+	device_set_wakeup_enable(&np->pci_dev->dev, np->wol_enabled);
+
+	return 0;
+}
+#else
+#define sundance_get_wol NULL
+#define sundance_set_wol NULL
+#endif /* CONFIG_PM */
+
+static const struct ethtool_ops ethtool_ops = {
+	.begin = check_if_running,
+	.get_drvinfo = get_drvinfo,
+	.nway_reset = nway_reset,
+	.get_link = get_link,
+	.get_wol = sundance_get_wol,
+	.set_wol = sundance_set_wol,
+	.get_msglevel = get_msglevel,
+	.set_msglevel = set_msglevel,
+	.get_strings = get_strings,
+	.get_sset_count = get_sset_count,
+	.get_ethtool_stats = get_ethtool_stats,
+	.get_link_ksettings = get_link_ksettings,
+	.set_link_ksettings = set_link_ksettings,
+};
+
+static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	int rc;
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	spin_lock_irq(&np->lock);
+	rc = generic_mii_ioctl(&np->mii_if, if_mii(rq), cmd, NULL);
+	spin_unlock_irq(&np->lock);
+
+	return rc;
+}
+
+static int netdev_close(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	struct sk_buff *skb;
+	int i;
+
+	/* Wait and kill tasklet */
+	tasklet_kill(&np->rx_tasklet);
+	tasklet_kill(&np->tx_tasklet);
+	np->cur_tx = 0;
+	np->dirty_tx = 0;
+	np->cur_task = 0;
+	np->last_tx = NULL;
+
+	netif_stop_queue(dev);
+
+	if (netif_msg_ifdown(np)) {
+		printk(KERN_DEBUG "%s: Shutting down ethercard, status was Tx %2.2x "
+			   "Rx %4.4x Int %2.2x.\n",
+			   dev->name, ioread8(ioaddr + TxStatus),
+			   ioread32(ioaddr + RxStatus), ioread16(ioaddr + IntrStatus));
+		printk(KERN_DEBUG "%s: Queue pointers were Tx %d / %d,  Rx %d / %d.\n",
+			   dev->name, np->cur_tx, np->dirty_tx, np->cur_rx, np->dirty_rx);
+	}
+
+	/* Disable interrupts by clearing the interrupt mask. */
+	iowrite16(0x0000, ioaddr + IntrEnable);
+
+	/* Disable Rx and Tx DMA for safely release resource */
+	iowrite32(0x500, ioaddr + DMACtrl);
+
+	/* Stop the chip's Tx and Rx processes. */
+	iowrite16(TxDisable | RxDisable | StatsDisable, ioaddr + MACCtrl1);
+
+	for (i = 2000; i > 0; i--) {
+		if ((ioread32(ioaddr + DMACtrl) & 0xc000) == 0)
+			break;
+		mdelay(1);
+	}
+
+	iowrite16(GlobalReset | DMAReset | FIFOReset | NetworkReset,
+			ioaddr + ASIC_HI_WORD(ASICCtrl));
+
+	for (i = 2000; i > 0; i--) {
+		if ((ioread16(ioaddr + ASIC_HI_WORD(ASICCtrl)) & ResetBusy) == 0)
+			break;
+		mdelay(1);
+	}
+
+#ifdef __i386__
+	if (netif_msg_hw(np)) {
+		printk(KERN_DEBUG "  Tx ring at %8.8x:\n",
+			   (int)(np->tx_ring_dma));
+		for (i = 0; i < TX_RING_SIZE; i++)
+			printk(KERN_DEBUG " #%d desc. %4.4x %8.8x %8.8x.\n",
+				   i, np->tx_ring[i].status, np->tx_ring[i].frag.addr,
+				   np->tx_ring[i].frag.length);
+		printk(KERN_DEBUG "  Rx ring %8.8x:\n",
+			   (int)(np->rx_ring_dma));
+		for (i = 0; i < /*RX_RING_SIZE*/4 ; i++) {
+			printk(KERN_DEBUG " #%d desc. %4.4x %4.4x %8.8x\n",
+				   i, np->rx_ring[i].status, np->rx_ring[i].frag.addr,
+				   np->rx_ring[i].frag.length);
+		}
+	}
+#endif /* __i386__ debugging only */
+
+	free_irq(np->pci_dev->irq, dev);
+
+	timer_delete_sync(&np->timer);
+
+	/* Free all the skbuffs in the Rx queue. */
+	for (i = 0; i < RX_RING_SIZE; i++) {
+		np->rx_ring[i].status = 0;
+		skb = np->rx_skbuff[i];
+		if (skb) {
+			dma_unmap_single(&np->pci_dev->dev,
+				le32_to_cpu(np->rx_ring[i].frag.addr),
+				np->rx_buf_sz, DMA_FROM_DEVICE);
+			dev_kfree_skb(skb);
+			np->rx_skbuff[i] = NULL;
+		}
+		np->rx_ring[i].frag.addr = cpu_to_le32(0xBADF00D0); /* poison */
+	}
+	for (i = 0; i < TX_RING_SIZE; i++) {
+		np->tx_ring[i].next_desc = 0;
+		skb = np->tx_skbuff[i];
+		if (skb) {
+			dma_unmap_single(&np->pci_dev->dev,
+				le32_to_cpu(np->tx_ring[i].frag.addr),
+				skb->len, DMA_TO_DEVICE);
+			dev_kfree_skb(skb);
+			np->tx_skbuff[i] = NULL;
+		}
+	}
+
+	return 0;
+}
+
+static void sundance_remove1(struct pci_dev *pdev)
+{
+	struct net_device *dev = pci_get_drvdata(pdev);
+
+	if (dev) {
+	    struct netdev_private *np = netdev_priv(dev);
+	    unregister_netdev(dev);
+	    dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE,
+		    np->rx_ring, np->rx_ring_dma);
+	    dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE,
+		    np->tx_ring, np->tx_ring_dma);
+	    pci_iounmap(pdev, np->base);
+	    pci_release_regions(pdev);
+	    free_netdev(dev);
+	}
+}
+
+static int __maybe_unused sundance_suspend(struct device *dev_d)
+{
+	struct net_device *dev = dev_get_drvdata(dev_d);
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+
+	if (!netif_running(dev))
+		return 0;
+
+	netdev_close(dev);
+	netif_device_detach(dev);
+
+	if (np->wol_enabled) {
+		iowrite8(AcceptBroadcast | AcceptMyPhys, ioaddr + RxMode);
+		iowrite16(RxEnable, ioaddr + MACCtrl1);
+	}
+
+	device_set_wakeup_enable(dev_d, np->wol_enabled);
+
+	return 0;
+}
+
+static int __maybe_unused sundance_resume(struct device *dev_d)
+{
+	struct net_device *dev = dev_get_drvdata(dev_d);
+	int err = 0;
+
+	if (!netif_running(dev))
+		return 0;
+
+	err = netdev_open(dev);
+	if (err) {
+		printk(KERN_ERR "%s: Can't resume interface!\n",
+				dev->name);
+		goto out;
+	}
+
+	netif_device_attach(dev);
+
+out:
+	return err;
+}
+
+static SIMPLE_DEV_PM_OPS(sundance_pm_ops, sundance_suspend, sundance_resume);
+
+static struct pci_driver sundance_driver = {
+	.name		= DRV_NAME,
+	.id_table	= sundance_pci_tbl,
+	.probe		= sundance_probe1,
+	.remove		= sundance_remove1,
+	.driver.pm	= &sundance_pm_ops,
+};
+
+module_pci_driver(sundance_driver);
diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c
index 44af1d13d931..67275aa4f65b 100644
--- a/drivers/net/ethernet/ec_bhf.c
+++ b/drivers/net/ethernet/ec_bhf.c
@@ -416,8 +416,7 @@ static int ec_bhf_open(struct net_device *net_dev)
 
 	netif_start_queue(net_dev);
 
-	hrtimer_init(&priv->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	priv->hrtimer.function = ec_bhf_timer_fun;
+	hrtimer_setup(&priv->hrtimer, ec_bhf_timer_fun, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer_start(&priv->hrtimer, polling_frequency, HRTIMER_MODE_REL);
 
 	return 0;
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index e48b861e4ce1..270ff9aab335 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -562,7 +562,7 @@ struct be_adapter {
 	struct be_dma_mem mbox_mem_alloced;
 
 	struct be_mcc_obj mcc_obj;
-	struct mutex mcc_lock;	/* For serializing mcc cmds to BE card */
+	spinlock_t mcc_lock;	/* For serializing mcc cmds to BE card */
 	spinlock_t mcc_cq_lock;
 
 	u16 cfg_num_rx_irqs;		/* configured via set-channels */
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 61adcebeef01..bb5d2fa15736 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -575,7 +575,7 @@ int be_process_mcc(struct be_adapter *adapter)
 /* Wait till no more pending mcc requests are present */
 static int be_mcc_wait_compl(struct be_adapter *adapter)
 {
-#define mcc_timeout		12000 /* 12s timeout */
+#define mcc_timeout		120000 /* 12s timeout */
 	int i, status = 0;
 	struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
 
@@ -589,7 +589,7 @@ static int be_mcc_wait_compl(struct be_adapter *adapter)
 
 		if (atomic_read(&mcc_obj->q.used) == 0)
 			break;
-		usleep_range(500, 1000);
+		udelay(100);
 	}
 	if (i == mcc_timeout) {
 		dev_err(&adapter->pdev->dev, "FW not responding\n");
@@ -866,7 +866,7 @@ static bool use_mcc(struct be_adapter *adapter)
 static int be_cmd_lock(struct be_adapter *adapter)
 {
 	if (use_mcc(adapter)) {
-		mutex_lock(&adapter->mcc_lock);
+		spin_lock_bh(&adapter->mcc_lock);
 		return 0;
 	} else {
 		return mutex_lock_interruptible(&adapter->mbox_lock);
@@ -877,7 +877,7 @@ static int be_cmd_lock(struct be_adapter *adapter)
 static void be_cmd_unlock(struct be_adapter *adapter)
 {
 	if (use_mcc(adapter))
-		return mutex_unlock(&adapter->mcc_lock);
+		return spin_unlock_bh(&adapter->mcc_lock);
 	else
 		return mutex_unlock(&adapter->mbox_lock);
 }
@@ -1047,7 +1047,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 	struct be_cmd_req_mac_query *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1076,7 +1076,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1088,7 +1088,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr,
 	struct be_cmd_req_pmac_add *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1113,7 +1113,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (base_status(status) == MCC_STATUS_UNAUTHORIZED_REQUEST)
 		status = -EPERM;
@@ -1131,7 +1131,7 @@ int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 dom)
 	if (pmac_id == -1)
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1151,7 +1151,7 @@ int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 dom)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1414,7 +1414,7 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 	struct be_dma_mem *q_mem = &rxq->dma_mem;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1444,7 +1444,7 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1508,7 +1508,7 @@ int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q)
 	struct be_cmd_req_q_destroy *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1525,7 +1525,7 @@ int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q)
 	q->created = false;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1593,7 +1593,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	struct be_cmd_req_hdr *hdr;
 	int status = 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1609,7 +1609,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	/* version 1 of the cmd is not supported only by BE2 */
 	if (BE2_chip(adapter))
 		hdr->version = 0;
-	if (BE3_chip(adapter) || lancer_chip(adapter))
+	else if (BE3_chip(adapter) || lancer_chip(adapter))
 		hdr->version = 1;
 	else
 		hdr->version = 2;
@@ -1621,7 +1621,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	adapter->stats_cmd_sent = true;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1637,7 +1637,7 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
 			    CMD_SUBSYSTEM_ETH))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1660,7 +1660,7 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
 	adapter->stats_cmd_sent = true;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1697,7 +1697,7 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
 	struct be_cmd_req_link_status *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	if (link_status)
 		*link_status = LINK_DOWN;
@@ -1736,7 +1736,7 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1747,7 +1747,7 @@ int be_cmd_get_die_temperature(struct be_adapter *adapter)
 	struct be_cmd_req_get_cntl_addnl_attribs *req;
 	int status = 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1762,7 +1762,7 @@ int be_cmd_get_die_temperature(struct be_adapter *adapter)
 
 	status = be_mcc_notify(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1811,7 +1811,7 @@ int be_cmd_get_fat_dump(struct be_adapter *adapter, u32 buf_len, void *buf)
 	if (!get_fat_cmd.va)
 		return -ENOMEM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	while (total_size) {
 		buf_size = min(total_size, (u32)60 * 1024);
@@ -1849,9 +1849,9 @@ int be_cmd_get_fat_dump(struct be_adapter *adapter, u32 buf_len, void *buf)
 		log_offset += buf_size;
 	}
 err:
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, get_fat_cmd.size,
 			  get_fat_cmd.va, get_fat_cmd.dma);
-	mutex_unlock(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1862,7 +1862,7 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter)
 	struct be_cmd_req_get_fw_version *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1885,7 +1885,7 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter)
 			sizeof(adapter->fw_on_flash));
 	}
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1899,7 +1899,7 @@ static int __be_cmd_modify_eqd(struct be_adapter *adapter,
 	struct be_cmd_req_modify_eq_delay *req;
 	int status = 0, i;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1922,7 +1922,7 @@ static int __be_cmd_modify_eqd(struct be_adapter *adapter,
 
 	status = be_mcc_notify(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1949,7 +1949,7 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
 	struct be_cmd_req_vlan_config *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1971,7 +1971,7 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1982,7 +1982,7 @@ static int __be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value)
 	struct be_cmd_req_rx_filter *req = mem->va;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2015,7 +2015,7 @@ static int __be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value)
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2046,7 +2046,7 @@ int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2066,7 +2066,7 @@ int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (base_status(status) == MCC_STATUS_FEATURE_NOT_SUPPORTED)
 		return  -EOPNOTSUPP;
@@ -2085,7 +2085,7 @@ int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2108,7 +2108,7 @@ int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc)
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2189,7 +2189,7 @@ int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
 	if (!(be_if_cap_flags(adapter) & BE_IF_FLAGS_RSS))
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2214,7 +2214,7 @@ int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2226,7 +2226,7 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num,
 	struct be_cmd_req_enable_disable_beacon *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2247,7 +2247,7 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2258,7 +2258,7 @@ int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state)
 	struct be_cmd_req_get_beacon_state *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2282,7 +2282,7 @@ int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state)
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2306,7 +2306,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		return -ENOMEM;
 	}
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2328,7 +2328,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		memcpy(data, resp->page_data + off, len);
 	}
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 	return status;
 }
@@ -2345,7 +2345,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	void *ctxt = NULL;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 	adapter->flash_status = 0;
 
 	wrb = wrb_from_mccq(adapter);
@@ -2387,7 +2387,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(60000)))
@@ -2406,7 +2406,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2460,7 +2460,7 @@ static int lancer_cmd_delete_object(struct be_adapter *adapter,
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2478,7 +2478,7 @@ static int lancer_cmd_delete_object(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2491,7 +2491,7 @@ int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	struct lancer_cmd_resp_read_object *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2525,7 +2525,7 @@ int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	}
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2537,7 +2537,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	struct be_cmd_write_flashrom *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 	adapter->flash_status = 0;
 
 	wrb = wrb_from_mccq(adapter);
@@ -2562,7 +2562,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(40000)))
@@ -2573,7 +2573,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2584,7 +2584,7 @@ static int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2611,11 +2611,15 @@ static int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
 		memcpy(flashed_crc, req->crc, 4);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
-static char flash_cookie[2][16] = {"*** SE FLAS", "H DIRECTORY *** "};
+/*
+ * Since the cookie is text, add a parsing-skipped space to keep it from
+ * ever being matched on storage holding this source file.
+ */
+static const char flash_cookie[32] __nonstring = "*** SE FLAS" "H DIRECTORY *** ";
 
 static bool phy_flashing_required(struct be_adapter *adapter)
 {
@@ -3217,7 +3221,7 @@ int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
 	struct be_cmd_req_acpi_wol_magic_config *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3234,7 +3238,7 @@ int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3249,7 +3253,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3272,7 +3276,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(SET_LB_MODE_TIMEOUT)))
@@ -3281,7 +3285,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3298,7 +3302,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3324,7 +3328,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 	if (status)
 		goto err;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	wait_for_completion(&adapter->et_cmd_compl);
 	resp = embedded_payload(wrb);
@@ -3332,7 +3336,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 
 	return status;
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3348,7 +3352,7 @@ int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3382,7 +3386,7 @@ int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3393,7 +3397,7 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 	struct be_cmd_req_seeprom_read *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3409,7 +3413,7 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3424,7 +3428,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3469,7 +3473,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 	}
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3479,7 +3483,7 @@ static int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain)
 	struct be_cmd_req_set_qos *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3499,7 +3503,7 @@ static int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3611,7 +3615,7 @@ int be_cmd_get_fn_privileges(struct be_adapter *adapter, u32 *privilege,
 	struct be_cmd_req_get_fn_privileges *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3643,7 +3647,7 @@ int be_cmd_get_fn_privileges(struct be_adapter *adapter, u32 *privilege,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3655,7 +3659,7 @@ int be_cmd_set_fn_privileges(struct be_adapter *adapter, u32 privileges,
 	struct be_cmd_req_set_fn_privileges *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3675,7 +3679,7 @@ int be_cmd_set_fn_privileges(struct be_adapter *adapter, u32 privileges,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3707,7 +3711,7 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 		return -ENOMEM;
 	}
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3771,7 +3775,7 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 	}
 
 out:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, get_mac_list_cmd.size,
 			  get_mac_list_cmd.va, get_mac_list_cmd.dma);
 	return status;
@@ -3831,7 +3835,7 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 	if (!cmd.va)
 		return -ENOMEM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3852,8 +3856,8 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 	status = be_mcc_notify_wait(adapter);
 
 err:
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
-	mutex_unlock(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3889,7 +3893,7 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3930,7 +3934,7 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3944,7 +3948,7 @@ int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
 	int status;
 	u16 vid;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3991,7 +3995,7 @@ int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4190,7 +4194,7 @@ int be_cmd_set_ext_fat_capabilites(struct be_adapter *adapter,
 	struct be_cmd_req_set_ext_fat_caps *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4206,7 +4210,7 @@ int be_cmd_set_ext_fat_capabilites(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4684,7 +4688,7 @@ int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op)
 	if (iface == 0xFFFFFFFF)
 		return -1;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4701,7 +4705,7 @@ int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op)
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4735,7 +4739,7 @@ int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
 	struct be_cmd_resp_get_iface_list *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4756,7 +4760,7 @@ int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4850,7 +4854,7 @@ int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain)
 	if (BEx_chip(adapter))
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4868,7 +4872,7 @@ int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain)
 	req->enable = 1;
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4941,7 +4945,7 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter,
 	u32 link_config = 0;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4969,7 +4973,7 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -5000,8 +5004,7 @@ int be_cmd_set_features(struct be_adapter *adapter)
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	if (mutex_lock_interruptible(&adapter->mcc_lock))
-		return -1;
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -5039,7 +5042,7 @@ err:
 		dev_info(&adapter->pdev->dev,
 			 "Adapter does not support HW error recovery\n");
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -5053,7 +5056,7 @@ int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
 	struct be_cmd_resp_hdr *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -5076,7 +5079,7 @@ int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
 	memcpy(wrb_payload, resp, sizeof(*resp) + resp->response_length);
 	be_dws_le_to_cpu(wrb_payload, sizeof(*resp) + resp->response_length);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 EXPORT_SYMBOL(be_roce_mcc_cmd);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index d70818f06be7..5e2d3ddb5d43 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -1415,7 +1415,7 @@ struct flash_section_entry {
 } __packed;
 
 struct flash_section_info {
-	u8 cookie[32];
+	u8 cookie[32] __nonstring;
 	struct flash_section_hdr fsec_hdr;
 	struct flash_section_entry fsec_entry[32];
 } __packed;
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index f001a649f58f..f9216326bdfe 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -1073,10 +1073,19 @@ static void be_set_msg_level(struct net_device *netdev, u32 level)
 	adapter->msg_enable = level;
 }
 
-static u64 be_get_rss_hash_opts(struct be_adapter *adapter, u64 flow_type)
+static int be_get_rxfh_fields(struct net_device *netdev,
+			      struct ethtool_rxfh_fields *cmd)
 {
+	struct be_adapter *adapter = netdev_priv(netdev);
+	u64 flow_type = cmd->flow_type;
 	u64 data = 0;
 
+	if (!be_multi_rxq(adapter)) {
+		dev_info(&adapter->pdev->dev,
+			 "ethtool::get_rxfh: RX flow hashing is disabled\n");
+		return -EINVAL;
+	}
+
 	switch (flow_type) {
 	case TCP_V4_FLOW:
 		if (adapter->rss_info.rss_flags & RSS_ENABLE_IPV4)
@@ -1104,7 +1113,8 @@ static u64 be_get_rss_hash_opts(struct be_adapter *adapter, u64 flow_type)
 		break;
 	}
 
-	return data;
+	cmd->data = data;
+	return 0;
 }
 
 static int be_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
@@ -1119,9 +1129,6 @@ static int be_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 	}
 
 	switch (cmd->cmd) {
-	case ETHTOOL_GRXFH:
-		cmd->data = be_get_rss_hash_opts(adapter, cmd->flow_type);
-		break;
 	case ETHTOOL_GRXRINGS:
 		cmd->data = adapter->num_rx_qs;
 		break;
@@ -1132,11 +1139,19 @@ static int be_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 	return 0;
 }
 
-static int be_set_rss_hash_opts(struct be_adapter *adapter,
-				struct ethtool_rxnfc *cmd)
+static int be_set_rxfh_fields(struct net_device *netdev,
+			      const struct ethtool_rxfh_fields *cmd,
+			      struct netlink_ext_ack *extack)
 {
-	int status;
+	struct be_adapter *adapter = netdev_priv(netdev);
 	u32 rss_flags = adapter->rss_info.rss_flags;
+	int status;
+
+	if (!be_multi_rxq(adapter)) {
+		dev_err(&adapter->pdev->dev,
+			"ethtool::set_rxfh: RX flow hashing is disabled\n");
+		return -EINVAL;
+	}
 
 	if (cmd->data != L3_RSS_FLAGS &&
 	    cmd->data != (L3_RSS_FLAGS | L4_RSS_FLAGS))
@@ -1195,28 +1210,6 @@ static int be_set_rss_hash_opts(struct be_adapter *adapter,
 	return be_cmd_status(status);
 }
 
-static int be_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
-{
-	struct be_adapter *adapter = netdev_priv(netdev);
-	int status = 0;
-
-	if (!be_multi_rxq(adapter)) {
-		dev_err(&adapter->pdev->dev,
-			"ethtool::set_rxnfc: RX flow hashing is disabled\n");
-		return -EINVAL;
-	}
-
-	switch (cmd->cmd) {
-	case ETHTOOL_SRXFH:
-		status = be_set_rss_hash_opts(adapter, cmd);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return status;
-}
-
 static void be_get_channels(struct net_device *netdev,
 			    struct ethtool_channels *ch)
 {
@@ -1449,7 +1442,8 @@ const struct ethtool_ops be_ethtool_ops = {
 	.flash_device = be_do_flash,
 	.self_test = be_self_test,
 	.get_rxnfc = be_get_rxnfc,
-	.set_rxnfc = be_set_rxnfc,
+	.get_rxfh_fields = be_get_rxfh_fields,
+	.set_rxfh_fields = be_set_rxfh_fields,
 	.get_rxfh_indir_size = be_get_rxfh_indir_size,
 	.get_rxfh_key_size = be_get_rxfh_key_size,
 	.get_rxfh = be_get_rxfh,
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 875fe379eea2..5bb31c8fab39 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1296,7 +1296,8 @@ static void be_xmit_flush(struct be_adapter *adapter, struct be_tx_obj *txo)
 		(adapter->bmc_filt_mask & BMC_FILT_MULTICAST)
 
 static bool be_send_pkt_to_bmc(struct be_adapter *adapter,
-			       struct sk_buff **skb)
+			       struct sk_buff **skb,
+			       struct be_wrb_params *wrb_params)
 {
 	struct ethhdr *eh = (struct ethhdr *)(*skb)->data;
 	bool os2bmc = false;
@@ -1360,7 +1361,7 @@ done:
 	 * to BMC, asic expects the vlan to be inline in the packet.
 	 */
 	if (os2bmc)
-		*skb = be_insert_vlan_in_pkt(adapter, *skb, NULL);
+		*skb = be_insert_vlan_in_pkt(adapter, *skb, wrb_params);
 
 	return os2bmc;
 }
@@ -1387,7 +1388,7 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
 	/* if os2bmc is enabled and if the pkt is destined to bmc,
 	 * enqueue the pkt a 2nd time with mgmt bit set.
 	 */
-	if (be_send_pkt_to_bmc(adapter, &skb)) {
+	if (be_send_pkt_to_bmc(adapter, &skb, &wrb_params)) {
 		BE_WRB_F_SET(wrb_params.features, OS2BMC, 1);
 		wrb_cnt = be_xmit_enqueue(adapter, txo, skb, &wrb_params);
 		if (unlikely(!wrb_cnt))
@@ -1465,10 +1466,10 @@ static void be_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 						 ntohs(tcphdr->source));
 					dev_info(dev, "TCP dest port %d\n",
 						 ntohs(tcphdr->dest));
-					dev_info(dev, "TCP sequence num %d\n",
-						 ntohs(tcphdr->seq));
-					dev_info(dev, "TCP ack_seq %d\n",
-						 ntohs(tcphdr->ack_seq));
+					dev_info(dev, "TCP sequence num %u\n",
+						 ntohl(tcphdr->seq));
+					dev_info(dev, "TCP ack_seq %u\n",
+						 ntohl(tcphdr->ack_seq));
 				} else if (ip_hdr(skb)->protocol ==
 					   IPPROTO_UDP) {
 					udphdr = udp_hdr(skb);
@@ -4031,8 +4032,7 @@ static int be_vxlan_unset_port(struct net_device *netdev, unsigned int table,
 static const struct udp_tunnel_nic_info be_udp_tunnels = {
 	.set_port	= be_vxlan_set_port,
 	.unset_port	= be_vxlan_unset_port,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-			  UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.flags		= UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, },
 	},
@@ -5667,8 +5667,8 @@ static int be_drv_init(struct be_adapter *adapter)
 	}
 
 	mutex_init(&adapter->mbox_lock);
-	mutex_init(&adapter->mcc_lock);
 	mutex_init(&adapter->rx_filter_lock);
+	spin_lock_init(&adapter->mcc_lock);
 	spin_lock_init(&adapter->mcc_cq_lock);
 	init_completion(&adapter->et_cmd_compl);
 
diff --git a/drivers/net/ethernet/engleder/tsnep.h b/drivers/net/ethernet/engleder/tsnep.h
index f188fba021a6..03e19aea9ea4 100644
--- a/drivers/net/ethernet/engleder/tsnep.h
+++ b/drivers/net/ethernet/engleder/tsnep.h
@@ -176,7 +176,7 @@ struct tsnep_adapter {
 	struct tsnep_gcl gcl[2];
 	int next_gcl;
 
-	struct hwtstamp_config hwtstamp_config;
+	struct kernel_hwtstamp_config hwtstamp_config;
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_clock_info;
 	/* ptp clock lock */
@@ -203,7 +203,11 @@ extern const struct ethtool_ops tsnep_ethtool_ops;
 
 int tsnep_ptp_init(struct tsnep_adapter *adapter);
 void tsnep_ptp_cleanup(struct tsnep_adapter *adapter);
-int tsnep_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd);
+int tsnep_ptp_hwtstamp_get(struct net_device *netdev,
+			   struct kernel_hwtstamp_config *config);
+int tsnep_ptp_hwtstamp_set(struct net_device *netdev,
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack);
 
 int tsnep_tc_init(struct tsnep_adapter *adapter);
 void tsnep_tc_cleanup(struct tsnep_adapter *adapter);
diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 95a5295d0361..b118407c30e8 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -67,6 +67,8 @@
 #define TSNEP_TX_TYPE_XDP_NDO_MAP_PAGE	(TSNEP_TX_TYPE_XDP_NDO | TSNEP_TX_TYPE_MAP_PAGE)
 #define TSNEP_TX_TYPE_XDP		(TSNEP_TX_TYPE_XDP_TX | TSNEP_TX_TYPE_XDP_NDO)
 #define TSNEP_TX_TYPE_XSK		BIT(12)
+#define TSNEP_TX_TYPE_TSTAMP		BIT(13)
+#define TSNEP_TX_TYPE_SKB_TSTAMP	(TSNEP_TX_TYPE_SKB | TSNEP_TX_TYPE_TSTAMP)
 
 #define TSNEP_XDP_TX		BIT(0)
 #define TSNEP_XDP_REDIRECT	BIT(1)
@@ -221,20 +223,19 @@ static void tsnep_phy_link_status_change(struct net_device *netdev)
 
 static int tsnep_phy_loopback(struct tsnep_adapter *adapter, bool enable)
 {
-	int retval;
-
-	retval = phy_loopback(adapter->phydev, enable);
+	int speed;
 
-	/* PHY link state change is not signaled if loopback is enabled, it
-	 * would delay a working loopback anyway, let's ensure that loopback
-	 * is working immediately by setting link mode directly
-	 */
-	if (!retval && enable) {
-		netif_carrier_on(adapter->netdev);
-		tsnep_set_link_mode(adapter);
+	if (enable) {
+		if (adapter->phydev->autoneg == AUTONEG_DISABLE &&
+		    adapter->phydev->speed == SPEED_100)
+			speed = SPEED_100;
+		else
+			speed = SPEED_1000;
+	} else {
+		speed = 0;
 	}
 
-	return retval;
+	return phy_loopback(adapter->phydev, enable, speed);
 }
 
 static int tsnep_phy_open(struct tsnep_adapter *adapter)
@@ -387,8 +388,7 @@ static void tsnep_tx_activate(struct tsnep_tx *tx, int index, int length,
 	if (entry->skb) {
 		entry->properties = length & TSNEP_DESC_LENGTH_MASK;
 		entry->properties |= TSNEP_DESC_INTERRUPT_FLAG;
-		if ((entry->type & TSNEP_TX_TYPE_SKB) &&
-		    (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS))
+		if ((entry->type & TSNEP_TX_TYPE_SKB_TSTAMP) == TSNEP_TX_TYPE_SKB_TSTAMP)
 			entry->properties |= TSNEP_DESC_EXTENDED_WRITEBACK_FLAG;
 
 		/* toggle user flag to prevent false acknowledge
@@ -480,7 +480,8 @@ static int tsnep_tx_map_frag(skb_frag_t *frag, struct tsnep_tx_entry *entry,
 	return mapped;
 }
 
-static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count)
+static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count,
+			bool do_tstamp)
 {
 	struct device *dmadev = tx->adapter->dmadev;
 	struct tsnep_tx_entry *entry;
@@ -506,6 +507,9 @@ static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count)
 				entry->type = TSNEP_TX_TYPE_SKB_INLINE;
 				mapped = 0;
 			}
+
+			if (do_tstamp)
+				entry->type |= TSNEP_TX_TYPE_TSTAMP;
 		} else {
 			skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
 
@@ -559,11 +563,12 @@ static int tsnep_tx_unmap(struct tsnep_tx *tx, int index, int count)
 static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
 					 struct tsnep_tx *tx)
 {
-	int count = 1;
 	struct tsnep_tx_entry *entry;
+	bool do_tstamp = false;
+	int count = 1;
 	int length;
-	int i;
 	int retval;
+	int i;
 
 	if (skb_shinfo(skb)->nr_frags > 0)
 		count += skb_shinfo(skb)->nr_frags;
@@ -580,7 +585,13 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
 	entry = &tx->entry[tx->write];
 	entry->skb = skb;
 
-	retval = tsnep_tx_map(skb, tx, count);
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    tx->adapter->hwtstamp_config.tx_type == HWTSTAMP_TX_ON) {
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+		do_tstamp = true;
+	}
+
+	retval = tsnep_tx_map(skb, tx, count, do_tstamp);
 	if (retval < 0) {
 		tsnep_tx_unmap(tx, tx->write, count);
 		dev_kfree_skb_any(entry->skb);
@@ -592,9 +603,6 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
 	}
 	length = retval;
 
-	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)
-		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-
 	for (i = 0; i < count; i++)
 		tsnep_tx_activate(tx, (tx->write + i) & TSNEP_RING_MASK, length,
 				  i == count - 1);
@@ -845,15 +853,14 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget)
 
 		length = tsnep_tx_unmap(tx, tx->read, count);
 
-		if ((entry->type & TSNEP_TX_TYPE_SKB) &&
-		    (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS) &&
+		if (((entry->type & TSNEP_TX_TYPE_SKB_TSTAMP) == TSNEP_TX_TYPE_SKB_TSTAMP) &&
 		    (__le32_to_cpu(entry->desc_wb->properties) &
 		     TSNEP_DESC_EXTENDED_WRITEBACK_FLAG)) {
 			struct skb_shared_hwtstamps hwtstamps;
 			u64 timestamp;
 
-			if (skb_shinfo(entry->skb)->tx_flags &
-			    SKBTX_HW_TSTAMP_USE_CYCLES)
+			if (entry->skb->sk &&
+			    READ_ONCE(entry->skb->sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC)
 				timestamp =
 					__le64_to_cpu(entry->desc_wb->counter);
 			else
@@ -1966,23 +1973,41 @@ failed:
 
 static void tsnep_queue_enable(struct tsnep_queue *queue)
 {
+	struct tsnep_adapter *adapter = queue->adapter;
+
+	netif_napi_set_irq(&queue->napi, queue->irq);
 	napi_enable(&queue->napi);
-	tsnep_enable_irq(queue->adapter, queue->irq_mask);
+	tsnep_enable_irq(adapter, queue->irq_mask);
 
-	if (queue->tx)
+	if (queue->tx) {
+		netif_queue_set_napi(adapter->netdev, queue->tx->queue_index,
+				     NETDEV_QUEUE_TYPE_TX, &queue->napi);
 		tsnep_tx_enable(queue->tx);
+	}
 
-	if (queue->rx)
+	if (queue->rx) {
+		netif_queue_set_napi(adapter->netdev, queue->rx->queue_index,
+				     NETDEV_QUEUE_TYPE_RX, &queue->napi);
 		tsnep_rx_enable(queue->rx);
+	}
 }
 
 static void tsnep_queue_disable(struct tsnep_queue *queue)
 {
-	if (queue->tx)
+	struct tsnep_adapter *adapter = queue->adapter;
+
+	if (queue->rx)
+		netif_queue_set_napi(adapter->netdev, queue->rx->queue_index,
+				     NETDEV_QUEUE_TYPE_RX, NULL);
+
+	if (queue->tx) {
 		tsnep_tx_disable(queue->tx, &queue->napi);
+		netif_queue_set_napi(adapter->netdev, queue->tx->queue_index,
+				     NETDEV_QUEUE_TYPE_TX, NULL);
+	}
 
 	napi_disable(&queue->napi);
-	tsnep_disable_irq(queue->adapter, queue->irq_mask);
+	tsnep_disable_irq(adapter, queue->irq_mask);
 
 	/* disable RX after NAPI polling has been disabled, because RX can be
 	 * enabled during NAPI polling
@@ -2143,16 +2168,6 @@ static netdev_tx_t tsnep_netdev_xmit_frame(struct sk_buff *skb,
 	return tsnep_xmit_frame_ring(skb, &adapter->tx[queue_mapping]);
 }
 
-static int tsnep_netdev_ioctl(struct net_device *netdev, struct ifreq *ifr,
-			      int cmd)
-{
-	if (!netif_running(netdev))
-		return -EINVAL;
-	if (cmd == SIOCSHWTSTAMP || cmd == SIOCGHWTSTAMP)
-		return tsnep_ptp_ioctl(netdev, ifr, cmd);
-	return phy_mii_ioctl(netdev->phydev, ifr, cmd);
-}
-
 static void tsnep_netdev_set_multicast(struct net_device *netdev)
 {
 	struct tsnep_adapter *adapter = netdev_priv(netdev);
@@ -2359,7 +2374,7 @@ static const struct net_device_ops tsnep_netdev_ops = {
 	.ndo_open = tsnep_netdev_open,
 	.ndo_stop = tsnep_netdev_close,
 	.ndo_start_xmit = tsnep_netdev_xmit_frame,
-	.ndo_eth_ioctl = tsnep_netdev_ioctl,
+	.ndo_eth_ioctl = phy_do_ioctl_running,
 	.ndo_set_rx_mode = tsnep_netdev_set_multicast,
 	.ndo_get_stats64 = tsnep_netdev_get_stats64,
 	.ndo_set_mac_address = tsnep_netdev_set_mac_address,
@@ -2369,6 +2384,8 @@ static const struct net_device_ops tsnep_netdev_ops = {
 	.ndo_bpf = tsnep_netdev_bpf,
 	.ndo_xdp_xmit = tsnep_netdev_xdp_xmit,
 	.ndo_xsk_wakeup = tsnep_netdev_xsk_wakeup,
+	.ndo_hwtstamp_get = tsnep_ptp_hwtstamp_get,
+	.ndo_hwtstamp_set = tsnep_ptp_hwtstamp_set,
 };
 
 static int tsnep_mac_init(struct tsnep_adapter *adapter)
diff --git a/drivers/net/ethernet/engleder/tsnep_ptp.c b/drivers/net/ethernet/engleder/tsnep_ptp.c
index 54fbf0126815..ae1308eb813d 100644
--- a/drivers/net/ethernet/engleder/tsnep_ptp.c
+++ b/drivers/net/ethernet/engleder/tsnep_ptp.c
@@ -19,57 +19,53 @@ void tsnep_get_system_time(struct tsnep_adapter *adapter, u64 *time)
 	*time = (((u64)high) << 32) | ((u64)low);
 }
 
-int tsnep_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+int tsnep_ptp_hwtstamp_get(struct net_device *netdev,
+			   struct kernel_hwtstamp_config *config)
 {
 	struct tsnep_adapter *adapter = netdev_priv(netdev);
-	struct hwtstamp_config config;
-
-	if (!ifr)
-		return -EINVAL;
-
-	if (cmd == SIOCSHWTSTAMP) {
-		if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-			return -EFAULT;
-
-		switch (config.tx_type) {
-		case HWTSTAMP_TX_OFF:
-		case HWTSTAMP_TX_ON:
-			break;
-		default:
-			return -ERANGE;
-		}
-
-		switch (config.rx_filter) {
-		case HWTSTAMP_FILTER_NONE:
-			break;
-		case HWTSTAMP_FILTER_ALL:
-		case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
-		case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
-		case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-		case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
-		case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
-		case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
-		case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
-		case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
-		case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
-		case HWTSTAMP_FILTER_PTP_V2_EVENT:
-		case HWTSTAMP_FILTER_PTP_V2_SYNC:
-		case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-		case HWTSTAMP_FILTER_NTP_ALL:
-			config.rx_filter = HWTSTAMP_FILTER_ALL;
-			break;
-		default:
-			return -ERANGE;
-		}
-
-		memcpy(&adapter->hwtstamp_config, &config,
-		       sizeof(adapter->hwtstamp_config));
+
+	*config = adapter->hwtstamp_config;
+	return 0;
+}
+
+int tsnep_ptp_hwtstamp_set(struct net_device *netdev,
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack)
+{
+	struct tsnep_adapter *adapter = netdev_priv(netdev);
+
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+	case HWTSTAMP_TX_ON:
+		break;
+	default:
+		return -ERANGE;
 	}
 
-	if (copy_to_user(ifr->ifr_data, &adapter->hwtstamp_config,
-			 sizeof(adapter->hwtstamp_config)))
-		return -EFAULT;
+	switch (config->rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		break;
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
+		break;
+	default:
+		return -ERANGE;
+	}
 
+	adapter->hwtstamp_config = *config;
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/faraday/Kconfig b/drivers/net/ethernet/faraday/Kconfig
index c699bd6bcbb9..474073c7f94d 100644
--- a/drivers/net/ethernet/faraday/Kconfig
+++ b/drivers/net/ethernet/faraday/Kconfig
@@ -31,6 +31,7 @@ config FTGMAC100
 	depends on ARM || COMPILE_TEST
 	depends on !64BIT || BROKEN
 	select PHYLIB
+	select FIXED_PHY
 	select MDIO_ASPEED if MACH_ASPEED_G6
 	select CRC32
 	help
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 17ec35e75a65..a863f7841210 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -9,6 +9,7 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <linux/clk.h>
+#include <linux/reset.h>
 #include <linux/dma-mapping.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
@@ -101,6 +102,8 @@ struct ftgmac100 {
 
 	/* AST2500/AST2600 RMII ref clock gate */
 	struct clk *rclk;
+	/* Aspeed reset control */
+	struct reset_control *rst;
 
 	/* Link management */
 	int cur_speed;
@@ -148,6 +151,23 @@ static int ftgmac100_reset_and_config_mac(struct ftgmac100 *priv)
 {
 	u32 maccr = 0;
 
+	/* Aspeed RMII needs SCU reset to clear status */
+	if (priv->is_aspeed && priv->netdev->phydev->interface == PHY_INTERFACE_MODE_RMII) {
+		int err;
+
+		err = reset_control_assert(priv->rst);
+		if (err) {
+			dev_err(priv->dev, "Failed to reset mac (%d)\n", err);
+			return err;
+		}
+		usleep_range(10000, 20000);
+		err = reset_control_deassert(priv->rst);
+		if (err) {
+			dev_err(priv->dev, "Failed to deassert mac reset (%d)\n", err);
+			return err;
+		}
+	}
+
 	switch (priv->cur_speed) {
 	case SPEED_10:
 	case 0: /* no link */
@@ -1428,7 +1448,7 @@ static void ftgmac100_adjust_link(struct net_device *netdev)
 	/* Disable all interrupts */
 	iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
 
-	/* Release phy lock to allow ftgmac100_reset to aquire it, keeping lock
+	/* Release phy lock to allow ftgmac100_reset to acquire it, keeping lock
 	 * order consistent to prevent dead lock.
 	 */
 	if (netdev->phydev)
@@ -1730,16 +1750,17 @@ err_register_mdiobus:
 static void ftgmac100_phy_disconnect(struct net_device *netdev)
 {
 	struct ftgmac100 *priv = netdev_priv(netdev);
+	struct phy_device *phydev = netdev->phydev;
 
-	if (!netdev->phydev)
+	if (!phydev)
 		return;
 
-	phy_disconnect(netdev->phydev);
+	phy_disconnect(phydev);
 	if (of_phy_is_fixed_link(priv->dev->of_node))
 		of_phy_deregister_fixed_link(priv->dev->of_node);
 
 	if (priv->use_ncsi)
-		fixed_phy_unregister(netdev->phydev);
+		fixed_phy_unregister(phydev);
 }
 
 static void ftgmac100_destroy_mdio(struct net_device *netdev)
@@ -1906,7 +1927,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
 			goto err_phy_connect;
 		}
 
-		phydev = fixed_phy_register(PHY_POLL, &ncsi_phy_status, np);
+		phydev = fixed_phy_register(&ncsi_phy_status, np);
 		if (IS_ERR(phydev)) {
 			dev_err(&pdev->dev, "failed to register fixed PHY device\n");
 			err = PTR_ERR(phydev);
@@ -1968,6 +1989,12 @@ static int ftgmac100_probe(struct platform_device *pdev)
 
 	}
 
+	priv->rst = devm_reset_control_get_optional_exclusive(priv->dev, NULL);
+	if (IS_ERR(priv->rst)) {
+		err = PTR_ERR(priv->rst);
+		goto err_phy_connect;
+	}
+
 	if (priv->is_aspeed) {
 		err = ftgmac100_setup_clk(priv);
 		if (err)
diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c
index ed18450fd2cc..3c9961806f75 100644
--- a/drivers/net/ethernet/fealnx.c
+++ b/drivers/net/ethernet/fealnx.c
@@ -196,7 +196,7 @@ enum intr_status_bits {
 	ERI = 0x00000080,	/* receive early int */
 	CNTOVF = 0x00000040,	/* counter overflow */
 	RBU = 0x00000020,	/* receive buffer unavailable */
-	TBU = 0x00000010,	/* transmit buffer unavilable */
+	TBU = 0x00000010,	/* transmit buffer unavailable */
 	TI = 0x00000008,	/* transmit interrupt */
 	RI = 0x00000004,	/* receive interrupt */
 	RxErr = 0x00000002,	/* receive error */
@@ -215,7 +215,7 @@ enum rx_mode_bits {
 	CR_W_RXMODEMASK	= 0x000000e0,
 	CR_W_PROM	= 0x00000080,	/* promiscuous mode */
 	CR_W_AB		= 0x00000040,	/* accept broadcast */
-	CR_W_AM		= 0x00000020,	/* accept mutlicast */
+	CR_W_AM		= 0x00000020,	/* accept multicast */
 	CR_W_ARP	= 0x00000008,	/* receive runt pkt */
 	CR_W_ALP	= 0x00000004,	/* receive long pkt */
 	CR_W_SEP	= 0x00000002,	/* receive error pkt */
@@ -1074,7 +1074,7 @@ static void allocate_rx_buffers(struct net_device *dev)
 
 static void netdev_timer(struct timer_list *t)
 {
-	struct netdev_private *np = from_timer(np, t, timer);
+	struct netdev_private *np = timer_container_of(np, t, timer);
 	struct net_device *dev = np->mii.dev;
 	void __iomem *ioaddr = np->mem;
 	int old_crvalue = np->crvalue;
@@ -1163,7 +1163,7 @@ static void enable_rxtx(struct net_device *dev)
 
 static void reset_timer(struct timer_list *t)
 {
-	struct netdev_private *np = from_timer(np, t, reset_timer);
+	struct netdev_private *np = timer_container_of(np, t, reset_timer);
 	struct net_device *dev = np->mii.dev;
 	unsigned long flags;
 
@@ -1900,8 +1900,8 @@ static int netdev_close(struct net_device *dev)
 	/* Stop the chip's Tx and Rx processes. */
 	stop_nic_rxtx(ioaddr, 0);
 
-	del_timer_sync(&np->timer);
-	del_timer_sync(&np->reset_timer);
+	timer_delete_sync(&np->timer);
+	timer_delete_sync(&np->reset_timer);
 
 	free_irq(np->pci_dev->irq, dev);
 
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index a2d7300925a8..e2a591cf9601 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -28,6 +28,7 @@ config FEC
 	depends on PTP_1588_CLOCK_OPTIONAL
 	select CRC32
 	select PHYLIB
+	select FIXED_PHY if M5272
 	select PAGE_POOL
 	imply PAGE_POOL_STATS
 	imply NET_SELFTESTS
@@ -71,7 +72,6 @@ config FSL_XGMAC_MDIO
 	tristate "Freescale XGMAC MDIO"
 	select PHYLIB
 	depends on OF
-	select MDIO_DEVRES
 	select OF_MDIO
 	help
 	  This driver supports the MDIO bus on the Fman 10G Ethernet MACs, and
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 4948b4906584..3edc8d142dd5 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -28,7 +28,6 @@
 #include <linux/percpu.h>
 #include <linux/dma-mapping.h>
 #include <linux/sort.h>
-#include <linux/phy_fixed.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <soc/fsl/bman.h>
@@ -3089,15 +3088,25 @@ static int dpaa_xdp_xmit(struct net_device *net_dev, int n,
 	return nxmit;
 }
 
-static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+static int dpaa_hwtstamp_get(struct net_device *dev,
+			     struct kernel_hwtstamp_config *config)
 {
 	struct dpaa_priv *priv = netdev_priv(dev);
-	struct hwtstamp_config config;
 
-	if (copy_from_user(&config, rq->ifr_data, sizeof(config)))
-		return -EFAULT;
+	config->tx_type = priv->tx_tstamp ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	config->rx_filter = priv->rx_tstamp ? HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
 
-	switch (config.tx_type) {
+	return 0;
+}
+
+static int dpaa_hwtstamp_set(struct net_device *dev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
+{
+	struct dpaa_priv *priv = netdev_priv(dev);
+
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		/* Couldn't disable rx/tx timestamping separately.
 		 * Do nothing here.
@@ -3112,7 +3121,7 @@ static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		return -ERANGE;
 	}
 
-	if (config.rx_filter == HWTSTAMP_FILTER_NONE) {
+	if (config->rx_filter == HWTSTAMP_FILTER_NONE) {
 		/* Couldn't disable rx/tx timestamping separately.
 		 * Do nothing here.
 		 */
@@ -3121,28 +3130,17 @@ static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		priv->mac_dev->set_tstamp(priv->mac_dev->fman_mac, true);
 		priv->rx_tstamp = true;
 		/* TS is set for all frame types, not only those requested */
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 	}
 
-	return copy_to_user(rq->ifr_data, &config, sizeof(config)) ?
-			-EFAULT : 0;
+	return 0;
 }
 
 static int dpaa_ioctl(struct net_device *net_dev, struct ifreq *rq, int cmd)
 {
-	int ret = -EINVAL;
 	struct dpaa_priv *priv = netdev_priv(net_dev);
 
-	if (cmd == SIOCGMIIREG) {
-		if (net_dev->phydev)
-			return phylink_mii_ioctl(priv->mac_dev->phylink, rq,
-						 cmd);
-	}
-
-	if (cmd == SIOCSHWTSTAMP)
-		return dpaa_ts_ioctl(net_dev, rq, cmd);
-
-	return ret;
+	return phylink_mii_ioctl(priv->mac_dev->phylink, rq, cmd);
 }
 
 static const struct net_device_ops dpaa_ops = {
@@ -3151,7 +3149,6 @@ static const struct net_device_ops dpaa_ops = {
 	.ndo_stop = dpaa_eth_stop,
 	.ndo_tx_timeout = dpaa_tx_timeout,
 	.ndo_get_stats64 = dpaa_get_stats64,
-	.ndo_change_carrier = fixed_phy_change_carrier,
 	.ndo_set_mac_address = dpaa_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_set_rx_mode = dpaa_set_rx_mode,
@@ -3160,6 +3157,8 @@ static const struct net_device_ops dpaa_ops = {
 	.ndo_change_mtu = dpaa_change_mtu,
 	.ndo_bpf = dpaa_xdp,
 	.ndo_xdp_xmit = dpaa_xdp_xmit,
+	.ndo_hwtstamp_get = dpaa_hwtstamp_get,
+	.ndo_hwtstamp_set = dpaa_hwtstamp_set,
 };
 
 static int dpaa_napi_add(struct net_device *net_dev)
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
index 9986f6e1f587..ed3fa80af8c3 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
@@ -263,8 +263,8 @@ static void dpaa_get_strings(struct net_device *net_dev, u32 stringset,
 		ethtool_puts(&data, dpaa_stats_global[i]);
 }
 
-static int dpaa_get_hash_opts(struct net_device *dev,
-			      struct ethtool_rxnfc *cmd)
+static int dpaa_get_rxfh_fields(struct net_device *dev,
+				struct ethtool_rxfh_fields *cmd)
 {
 	struct dpaa_priv *priv = netdev_priv(dev);
 
@@ -299,22 +299,6 @@ static int dpaa_get_hash_opts(struct net_device *dev,
 	return 0;
 }
 
-static int dpaa_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
-			  u32 *unused)
-{
-	int ret = -EOPNOTSUPP;
-
-	switch (cmd->cmd) {
-	case ETHTOOL_GRXFH:
-		ret = dpaa_get_hash_opts(dev, cmd);
-		break;
-	default:
-		break;
-	}
-
-	return ret;
-}
-
 static void dpaa_set_hash(struct net_device *net_dev, bool enable)
 {
 	struct mac_device *mac_dev;
@@ -329,8 +313,9 @@ static void dpaa_set_hash(struct net_device *net_dev, bool enable)
 	priv->keygen_in_use = enable;
 }
 
-static int dpaa_set_hash_opts(struct net_device *dev,
-			      struct ethtool_rxnfc *nfc)
+static int dpaa_set_rxfh_fields(struct net_device *dev,
+				const struct ethtool_rxfh_fields *nfc,
+				struct netlink_ext_ack *extack)
 {
 	int ret = -EINVAL;
 
@@ -364,21 +349,6 @@ static int dpaa_set_hash_opts(struct net_device *dev,
 	return ret;
 }
 
-static int dpaa_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
-{
-	int ret = -EOPNOTSUPP;
-
-	switch (cmd->cmd) {
-	case ETHTOOL_SRXFH:
-		ret = dpaa_set_hash_opts(dev, cmd);
-		break;
-	default:
-		break;
-	}
-
-	return ret;
-}
-
 static int dpaa_get_ts_info(struct net_device *net_dev,
 			    struct kernel_ethtool_ts_info *info)
 {
@@ -401,8 +371,10 @@ static int dpaa_get_ts_info(struct net_device *net_dev,
 		of_node_put(ptp_node);
 	}
 
-	if (ptp_dev)
+	if (ptp_dev) {
 		ptp = platform_get_drvdata(ptp_dev);
+		put_device(&ptp_dev->dev);
+	}
 
 	if (ptp)
 		info->phc_index = ptp->phc_index;
@@ -495,6 +467,47 @@ revert_values:
 	return res;
 }
 
+static void dpaa_get_pause_stats(struct net_device *net_dev,
+				 struct ethtool_pause_stats *s)
+{
+	struct dpaa_priv *priv = netdev_priv(net_dev);
+	struct mac_device *mac_dev = priv->mac_dev;
+
+	if (mac_dev->get_pause_stats)
+		mac_dev->get_pause_stats(mac_dev->fman_mac, s);
+}
+
+static void dpaa_get_rmon_stats(struct net_device *net_dev,
+				struct ethtool_rmon_stats *s,
+				const struct ethtool_rmon_hist_range **ranges)
+{
+	struct dpaa_priv *priv = netdev_priv(net_dev);
+	struct mac_device *mac_dev = priv->mac_dev;
+
+	if (mac_dev->get_rmon_stats)
+		mac_dev->get_rmon_stats(mac_dev->fman_mac, s, ranges);
+}
+
+static void dpaa_get_eth_ctrl_stats(struct net_device *net_dev,
+				    struct ethtool_eth_ctrl_stats *s)
+{
+	struct dpaa_priv *priv = netdev_priv(net_dev);
+	struct mac_device *mac_dev = priv->mac_dev;
+
+	if (mac_dev->get_eth_ctrl_stats)
+		mac_dev->get_eth_ctrl_stats(mac_dev->fman_mac, s);
+}
+
+static void dpaa_get_eth_mac_stats(struct net_device *net_dev,
+				   struct ethtool_eth_mac_stats *s)
+{
+	struct dpaa_priv *priv = netdev_priv(net_dev);
+	struct mac_device *mac_dev = priv->mac_dev;
+
+	if (mac_dev->get_eth_mac_stats)
+		mac_dev->get_eth_mac_stats(mac_dev->fman_mac, s);
+}
+
 const struct ethtool_ops dpaa_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS |
 				     ETHTOOL_COALESCE_RX_MAX_FRAMES,
@@ -510,9 +523,13 @@ const struct ethtool_ops dpaa_ethtool_ops = {
 	.get_strings = dpaa_get_strings,
 	.get_link_ksettings = dpaa_get_link_ksettings,
 	.set_link_ksettings = dpaa_set_link_ksettings,
-	.get_rxnfc = dpaa_get_rxnfc,
-	.set_rxnfc = dpaa_set_rxnfc,
+	.get_rxfh_fields = dpaa_get_rxfh_fields,
+	.set_rxfh_fields = dpaa_set_rxfh_fields,
 	.get_ts_info = dpaa_get_ts_info,
 	.get_coalesce = dpaa_get_coalesce,
 	.set_coalesce = dpaa_set_coalesce,
+	.get_pause_stats = dpaa_get_pause_stats,
+	.get_rmon_stats = dpaa_get_rmon_stats,
+	.get_eth_ctrl_stats = dpaa_get_eth_ctrl_stats,
+	.get_eth_mac_stats = dpaa_get_eth_mac_stats,
 };
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 29886a8ba73f..18d86badd6ea 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1077,8 +1077,7 @@ static int dpaa2_eth_build_single_fd(struct dpaa2_eth_priv *priv,
 	dma_addr_t addr;
 
 	buffer_start = skb->data - dpaa2_eth_needed_headroom(skb);
-	aligned_start = PTR_ALIGN(buffer_start - DPAA2_ETH_TX_BUF_ALIGN,
-				  DPAA2_ETH_TX_BUF_ALIGN);
+	aligned_start = PTR_ALIGN(buffer_start, DPAA2_ETH_TX_BUF_ALIGN);
 	if (aligned_start >= skb->head)
 		buffer_start = aligned_start;
 	else
@@ -2585,40 +2584,52 @@ static int dpaa2_eth_set_features(struct net_device *net_dev,
 	return 0;
 }
 
-static int dpaa2_eth_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+static int dpaa2_eth_hwtstamp_set(struct net_device *dev,
+				  struct kernel_hwtstamp_config *config,
+				  struct netlink_ext_ack *extack)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(dev);
-	struct hwtstamp_config config;
 
 	if (!dpaa2_ptp)
 		return -EINVAL;
 
-	if (copy_from_user(&config, rq->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 	case HWTSTAMP_TX_ON:
 	case HWTSTAMP_TX_ONESTEP_SYNC:
-		priv->tx_tstamp_type = config.tx_type;
+		priv->tx_tstamp_type = config->tx_type;
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	if (config.rx_filter == HWTSTAMP_FILTER_NONE) {
+	if (config->rx_filter == HWTSTAMP_FILTER_NONE) {
 		priv->rx_tstamp = false;
 	} else {
 		priv->rx_tstamp = true;
 		/* TS is set for all frame types, not only those requested */
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 	}
 
 	if (priv->tx_tstamp_type == HWTSTAMP_TX_ONESTEP_SYNC)
 		dpaa2_ptp_onestep_reg_update_method(priv);
 
-	return copy_to_user(rq->ifr_data, &config, sizeof(config)) ?
-			-EFAULT : 0;
+	return 0;
+}
+
+static int dpaa2_eth_hwtstamp_get(struct net_device *dev,
+				  struct kernel_hwtstamp_config *config)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(dev);
+
+	if (!dpaa2_ptp)
+		return -EINVAL;
+
+	config->tx_type = priv->tx_tstamp_type;
+	config->rx_filter = priv->rx_tstamp ? HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
+
+	return 0;
 }
 
 static int dpaa2_eth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
@@ -2626,9 +2637,6 @@ static int dpaa2_eth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	struct dpaa2_eth_priv *priv = netdev_priv(dev);
 	int err;
 
-	if (cmd == SIOCSHWTSTAMP)
-		return dpaa2_eth_ts_ioctl(dev, rq, cmd);
-
 	mutex_lock(&priv->mac_lock);
 
 	if (dpaa2_eth_is_type_phy(priv)) {
@@ -3034,7 +3042,9 @@ static const struct net_device_ops dpaa2_eth_ops = {
 	.ndo_xsk_wakeup = dpaa2_xsk_wakeup,
 	.ndo_setup_tc = dpaa2_eth_setup_tc,
 	.ndo_vlan_rx_add_vid = dpaa2_eth_rx_add_vid,
-	.ndo_vlan_rx_kill_vid = dpaa2_eth_rx_kill_vid
+	.ndo_vlan_rx_kill_vid = dpaa2_eth_rx_kill_vid,
+	.ndo_hwtstamp_get = dpaa2_eth_hwtstamp_get,
+	.ndo_hwtstamp_set = dpaa2_eth_hwtstamp_set,
 };
 
 static void dpaa2_eth_cdan_cb(struct dpaa2_io_notification_ctx *ctx)
@@ -3928,6 +3938,7 @@ static int dpaa2_eth_setup_rx_flow(struct dpaa2_eth_priv *priv,
 					 MEM_TYPE_PAGE_ORDER0, NULL);
 	if (err) {
 		dev_err(dev, "xdp_rxq_info_reg_mem_model failed\n");
+		xdp_rxq_info_unreg(&fq->channel->xdp_rxq);
 		return err;
 	}
 
@@ -4421,17 +4432,25 @@ static int dpaa2_eth_bind_dpni(struct dpaa2_eth_priv *priv)
 			return -EINVAL;
 		}
 		if (err)
-			return err;
+			goto out;
 	}
 
 	err = dpni_get_qdid(priv->mc_io, 0, priv->mc_token,
 			    DPNI_QUEUE_TX, &priv->tx_qdid);
 	if (err) {
 		dev_err(dev, "dpni_get_qdid() failed\n");
-		return err;
+		goto out;
 	}
 
 	return 0;
+
+out:
+	while (i--) {
+		if (priv->fq[i].type == DPAA2_RX_FQ &&
+		    xdp_rxq_info_is_reg(&priv->fq[i].channel->xdp_rxq))
+			xdp_rxq_info_unreg(&priv->fq[i].channel->xdp_rxq);
+	}
+	return err;
 }
 
 /* Allocate rings for storing incoming frame descriptors */
@@ -4646,12 +4665,19 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv)
 		return PTR_ERR(dpmac_dev);
 	}
 
-	if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type)
+	if (IS_ERR(dpmac_dev))
 		return 0;
 
+	if (dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) {
+		err = 0;
+		goto out_put_device;
+	}
+
 	mac = kzalloc(sizeof(struct dpaa2_mac), GFP_KERNEL);
-	if (!mac)
-		return -ENOMEM;
+	if (!mac) {
+		err = -ENOMEM;
+		goto out_put_device;
+	}
 
 	mac->mc_dev = dpmac_dev;
 	mac->mc_io = priv->mc_io;
@@ -4685,6 +4711,8 @@ err_close_mac:
 	dpaa2_mac_close(mac);
 err_free_mac:
 	kfree(mac);
+out_put_device:
+	put_device(&dpmac_dev->dev);
 	return err;
 }
 
@@ -4814,6 +4842,17 @@ static void dpaa2_eth_del_ch_napi(struct dpaa2_eth_priv *priv)
 	}
 }
 
+static void dpaa2_eth_free_rx_xdp_rxq(struct dpaa2_eth_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_fqs; i++) {
+		if (priv->fq[i].type == DPAA2_RX_FQ &&
+		    xdp_rxq_info_is_reg(&priv->fq[i].channel->xdp_rxq))
+			xdp_rxq_info_unreg(&priv->fq[i].channel->xdp_rxq);
+	}
+}
+
 static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 {
 	struct device *dev;
@@ -4844,7 +4883,7 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 	priv->tx_tstamp_type = HWTSTAMP_TX_OFF;
 	priv->rx_tstamp = false;
 
-	priv->dpaa2_ptp_wq = alloc_workqueue("dpaa2_ptp_wq", 0, 0);
+	priv->dpaa2_ptp_wq = alloc_workqueue("dpaa2_ptp_wq", WQ_PERCPU, 0);
 	if (!priv->dpaa2_ptp_wq) {
 		err = -ENOMEM;
 		goto err_wq_alloc;
@@ -5017,6 +5056,7 @@ err_alloc_percpu_extras:
 	free_percpu(priv->percpu_stats);
 err_alloc_percpu_stats:
 	dpaa2_eth_del_ch_napi(priv);
+	dpaa2_eth_free_rx_xdp_rxq(priv);
 err_bind:
 	dpaa2_eth_free_dpbps(priv);
 err_dpbp_setup:
@@ -5069,6 +5109,7 @@ static void dpaa2_eth_remove(struct fsl_mc_device *ls_dev)
 	free_percpu(priv->percpu_extras);
 
 	dpaa2_eth_del_ch_napi(priv);
+	dpaa2_eth_free_rx_xdp_rxq(priv);
 	dpaa2_eth_free_dpbps(priv);
 	dpaa2_eth_free_dpio(priv);
 	dpaa2_eth_free_dpni(priv);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index 74ef77cb7078..baab4f1c908d 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -711,6 +711,13 @@ static int dpaa2_eth_update_cls_rule(struct net_device *net_dev,
 	return 0;
 }
 
+static u32 dpaa2_eth_get_rx_ring_count(struct net_device *net_dev)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+
+	return dpaa2_eth_queue_count(priv);
+}
+
 static int dpaa2_eth_get_rxnfc(struct net_device *net_dev,
 			       struct ethtool_rxnfc *rxnfc, u32 *rule_locs)
 {
@@ -719,16 +726,6 @@ static int dpaa2_eth_get_rxnfc(struct net_device *net_dev,
 	int i, j = 0;
 
 	switch (rxnfc->cmd) {
-	case ETHTOOL_GRXFH:
-		/* we purposely ignore cmd->flow_type for now, because the
-		 * classifier only supports a single set of fields for all
-		 * protocols
-		 */
-		rxnfc->data = priv->rx_hash_fields;
-		break;
-	case ETHTOOL_GRXRINGS:
-		rxnfc->data = dpaa2_eth_queue_count(priv);
-		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		rxnfc->rule_cnt = 0;
 		rxnfc->rule_cnt = dpaa2_eth_num_cls_rules(priv);
@@ -767,11 +764,6 @@ static int dpaa2_eth_set_rxnfc(struct net_device *net_dev,
 	int err = 0;
 
 	switch (rxnfc->cmd) {
-	case ETHTOOL_SRXFH:
-		if ((rxnfc->data & DPAA2_RXH_SUPPORTED) != rxnfc->data)
-			return -EOPNOTSUPP;
-		err = dpaa2_eth_set_hash(net_dev, rxnfc->data);
-		break;
 	case ETHTOOL_SRXCLSRLINS:
 		err = dpaa2_eth_update_cls_rule(net_dev, &rxnfc->fs, rxnfc->fs.location);
 		break;
@@ -785,6 +777,28 @@ static int dpaa2_eth_set_rxnfc(struct net_device *net_dev,
 	return err;
 }
 
+static int dpaa2_eth_get_rxfh_fields(struct net_device *net_dev,
+				     struct ethtool_rxfh_fields *rxnfc)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+
+	/* we purposely ignore cmd->flow_type for now, because the
+	 * classifier only supports a single set of fields for all
+	 * protocols
+	 */
+	rxnfc->data = priv->rx_hash_fields;
+	return 0;
+}
+
+static int dpaa2_eth_set_rxfh_fields(struct net_device *net_dev,
+				     const struct ethtool_rxfh_fields *rxnfc,
+				     struct netlink_ext_ack *extack)
+{
+	if ((rxnfc->data & DPAA2_RXH_SUPPORTED) != rxnfc->data)
+		return -EOPNOTSUPP;
+	return dpaa2_eth_set_hash(net_dev, rxnfc->data);
+}
+
 int dpaa2_phc_index = -1;
 EXPORT_SYMBOL(dpaa2_phc_index);
 
@@ -939,6 +953,9 @@ const struct ethtool_ops dpaa2_ethtool_ops = {
 	.get_strings = dpaa2_eth_get_strings,
 	.get_rxnfc = dpaa2_eth_get_rxnfc,
 	.set_rxnfc = dpaa2_eth_set_rxnfc,
+	.get_rx_ring_count = dpaa2_eth_get_rx_ring_count,
+	.get_rxfh_fields = dpaa2_eth_get_rxfh_fields,
+	.set_rxfh_fields = dpaa2_eth_set_rxfh_fields,
 	.get_ts_info = dpaa2_eth_get_ts_info,
 	.get_tunable = dpaa2_eth_get_tunable,
 	.set_tunable = dpaa2_eth_set_tunable,
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index 147a93bf9fa9..b1e1ad9e4b48 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -1448,12 +1448,19 @@ static int dpaa2_switch_port_connect_mac(struct ethsw_port_priv *port_priv)
 	if (PTR_ERR(dpmac_dev) == -EPROBE_DEFER)
 		return PTR_ERR(dpmac_dev);
 
-	if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type)
+	if (IS_ERR(dpmac_dev))
 		return 0;
 
+	if (dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) {
+		err = 0;
+		goto out_put_device;
+	}
+
 	mac = kzalloc(sizeof(*mac), GFP_KERNEL);
-	if (!mac)
-		return -ENOMEM;
+	if (!mac) {
+		err = -ENOMEM;
+		goto out_put_device;
+	}
 
 	mac->mc_dev = dpmac_dev;
 	mac->mc_io = port_priv->ethsw_data->mc_io;
@@ -1483,6 +1490,8 @@ err_close_mac:
 	dpaa2_mac_close(mac);
 err_free_mac:
 	kfree(mac);
+out_put_device:
+	put_device(&dpmac_dev->dev);
 	return err;
 }
 
@@ -2727,7 +2736,7 @@ static int dpaa2_switch_setup_dpbp(struct ethsw_core *ethsw)
 		dev_err(dev, "dpsw_ctrl_if_set_pools() failed\n");
 		goto err_get_attr;
 	}
-	ethsw->bpid = dpbp_attrs.id;
+	ethsw->bpid = dpbp_attrs.bpid;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c
index a466c2379146..4b0ae7d9af92 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c
@@ -448,7 +448,5 @@ bool dpaa2_xsk_tx(struct dpaa2_eth_priv *priv,
 		percpu_stats->tx_errors++;
 	}
 
-	xsk_tx_release(ch->xsk_pool);
-
 	return total_enqueued == budget;
 }
diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig
index 6c2779047dcd..117038104b69 100644
--- a/drivers/net/ethernet/freescale/enetc/Kconfig
+++ b/drivers/net/ethernet/freescale/enetc/Kconfig
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 config FSL_ENETC_CORE
 	tristate
+	select NXP_NETC_LIB if NXP_NTMP
 	help
 	  This module supports common functionality between the PF and VF
 	  drivers for the NXP ENETC controller.
@@ -15,10 +16,20 @@ config NXP_ENETC_PF_COMMON
 
 	  If compiled as module (M), the module name is nxp-enetc-pf-common.
 
+config NXP_NETC_LIB
+	tristate
+	help
+	  This module provides common functionalities for both ENETC and NETC
+	  Switch, such as NETC Table Management Protocol (NTMP) 2.0, common tc
+	  flower and debugfs interfaces and so on.
+
+config NXP_NTMP
+	bool
+
 config FSL_ENETC
 	tristate "ENETC PF driver"
+	depends on PTP_1588_CLOCK_OPTIONAL
 	depends on PCI_MSI
-	select MDIO_DEVRES
 	select FSL_ENETC_CORE
 	select FSL_ENETC_IERB
 	select FSL_ENETC_MDIO
@@ -35,11 +46,12 @@ config FSL_ENETC
 
 config NXP_ENETC4
 	tristate "ENETC4 PF driver"
+	depends on PTP_1588_CLOCK_OPTIONAL
 	depends on PCI_MSI
-	select MDIO_DEVRES
 	select FSL_ENETC_CORE
 	select FSL_ENETC_MDIO
 	select NXP_ENETC_PF_COMMON
+	select NXP_NTMP
 	select PHYLINK
 	select DIMLIB
 	help
@@ -52,6 +64,7 @@ config NXP_ENETC4
 
 config FSL_ENETC_VF
 	tristate "ENETC VF driver"
+	depends on PTP_1588_CLOCK_OPTIONAL
 	depends on PCI_MSI
 	select FSL_ENETC_CORE
 	select FSL_ENETC_MDIO
@@ -73,7 +86,7 @@ config FSL_ENETC_IERB
 
 config FSL_ENETC_MDIO
 	tristate "ENETC MDIO driver"
-	depends on PCI && MDIO_DEVRES && MDIO_BUS
+	depends on PCI && PHYLIB
 	help
 	  This driver supports NXP ENETC Central MDIO controller as a PCIe
 	  physical function (PF) device.
diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile
index 6fd27ee4fcd1..f1c5ad45fd76 100644
--- a/drivers/net/ethernet/freescale/enetc/Makefile
+++ b/drivers/net/ethernet/freescale/enetc/Makefile
@@ -6,6 +6,9 @@ fsl-enetc-core-y := enetc.o enetc_cbdr.o enetc_ethtool.o
 obj-$(CONFIG_NXP_ENETC_PF_COMMON) += nxp-enetc-pf-common.o
 nxp-enetc-pf-common-y := enetc_pf_common.o
 
+obj-$(CONFIG_NXP_NETC_LIB) += nxp-netc-lib.o
+nxp-netc-lib-y := ntmp.o
+
 obj-$(CONFIG_FSL_ENETC) += fsl-enetc.o
 fsl-enetc-y := enetc_pf.o
 fsl-enetc-$(CONFIG_PCI_IOV) += enetc_msg.o
@@ -13,6 +16,7 @@ fsl-enetc-$(CONFIG_FSL_ENETC_QOS) += enetc_qos.o
 
 obj-$(CONFIG_NXP_ENETC4) += nxp-enetc4.o
 nxp-enetc4-y := enetc4_pf.o
+nxp-enetc4-$(CONFIG_DEBUG_FS) += enetc4_debugfs.o
 
 obj-$(CONFIG_FSL_ENETC_VF) += fsl-enetc-vf.o
 fsl-enetc-vf-y := enetc_vf.o
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 6a6fc819dfde..d5e5800b84ef 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -14,12 +14,21 @@
 
 u32 enetc_port_mac_rd(struct enetc_si *si, u32 reg)
 {
+	/* ENETC with pseudo MAC does not have Ethernet MAC
+	 * port registers.
+	 */
+	if (enetc_is_pseudo_mac(si))
+		return 0;
+
 	return enetc_port_rd(&si->hw, reg);
 }
 EXPORT_SYMBOL_GPL(enetc_port_mac_rd);
 
 void enetc_port_mac_wr(struct enetc_si *si, u32 reg, u32 val)
 {
+	if (enetc_is_pseudo_mac(si))
+		return;
+
 	enetc_port_wr(&si->hw, reg, val);
 	if (si->hw_features & ENETC_SI_F_QBU)
 		enetc_port_wr(&si->hw, reg + si->drvdata->pmac_offset, val);
@@ -36,6 +45,42 @@ static void enetc_change_preemptible_tcs(struct enetc_ndev_priv *priv,
 	enetc_mm_commit_preemptible_tcs(priv);
 }
 
+static int enetc_mac_addr_hash_idx(const u8 *addr)
+{
+	u64 fold = __swab64(ether_addr_to_u64(addr)) >> 16;
+	u64 mask = 0;
+	int res = 0;
+	int i;
+
+	for (i = 0; i < 8; i++)
+		mask |= BIT_ULL(i * 6);
+
+	for (i = 0; i < 6; i++)
+		res |= (hweight64(fold & (mask << i)) & 0x1) << i;
+
+	return res;
+}
+
+void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
+				  const unsigned char *addr)
+{
+	int idx = enetc_mac_addr_hash_idx(addr);
+
+	/* add hash table entry */
+	__set_bit(idx, filter->mac_hash_table);
+	filter->mac_addr_cnt++;
+}
+EXPORT_SYMBOL_GPL(enetc_add_mac_addr_ht_filter);
+
+void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter)
+{
+	filter->mac_addr_cnt = 0;
+
+	bitmap_zero(filter->mac_hash_table,
+		    ENETC_MADDR_HASH_TBL_SZ);
+}
+EXPORT_SYMBOL_GPL(enetc_reset_mac_addr_filter);
+
 static int enetc_num_stack_tx_queues(struct enetc_ndev_priv *priv)
 {
 	int num_tx_rings = priv->num_tx_rings;
@@ -167,22 +212,129 @@ static bool enetc_skb_is_tcp(struct sk_buff *skb)
 	return skb->csum_offset == offsetof(struct tcphdr, check);
 }
 
+/**
+ * enetc_unwind_tx_frame() - Unwind the DMA mappings of a multi-buffer Tx frame
+ * @tx_ring: Pointer to the Tx ring on which the buffer descriptors are located
+ * @count: Number of Tx buffer descriptors which need to be unmapped
+ * @i: Index of the last successfully mapped Tx buffer descriptor
+ */
+static void enetc_unwind_tx_frame(struct enetc_bdr *tx_ring, int count, int i)
+{
+	while (count--) {
+		struct enetc_tx_swbd *tx_swbd = &tx_ring->tx_swbd[i];
+
+		enetc_free_tx_frame(tx_ring, tx_swbd);
+		if (i == 0)
+			i = tx_ring->bd_count;
+		i--;
+	}
+}
+
+static void enetc_set_one_step_ts(struct enetc_si *si, bool udp, int offset)
+{
+	u32 val = ENETC_PM0_SINGLE_STEP_EN;
+
+	val |= ENETC_SET_SINGLE_STEP_OFFSET(offset);
+	if (udp)
+		val |= ENETC_PM0_SINGLE_STEP_CH;
+
+	/* The "Correction" field of a packet is updated based on the
+	 * current time and the timestamp provided
+	 */
+	enetc_port_mac_wr(si, ENETC_PM0_SINGLE_STEP, val);
+}
+
+static void enetc4_set_one_step_ts(struct enetc_si *si, bool udp, int offset)
+{
+	u32 val = PM_SINGLE_STEP_EN;
+
+	val |= PM_SINGLE_STEP_OFFSET_SET(offset);
+	if (udp)
+		val |= PM_SINGLE_STEP_CH;
+
+	enetc_port_mac_wr(si, ENETC4_PM_SINGLE_STEP(0), val);
+}
+
+static u32 enetc_update_ptp_sync_msg(struct enetc_ndev_priv *priv,
+				     struct sk_buff *skb, bool csum_offload)
+{
+	struct enetc_skb_cb *enetc_cb = ENETC_SKB_CB(skb);
+	u16 tstamp_off = enetc_cb->origin_tstamp_off;
+	u16 corr_off = enetc_cb->correction_off;
+	struct enetc_si *si = priv->si;
+	struct enetc_hw *hw = &si->hw;
+	__be32 new_sec_l, new_nsec;
+	__be16 new_sec_h;
+	u32 lo, hi, nsec;
+	u8 *data;
+	u64 sec;
+
+	lo = enetc_rd_hot(hw, ENETC_SICTR0);
+	hi = enetc_rd_hot(hw, ENETC_SICTR1);
+	sec = (u64)hi << 32 | lo;
+	nsec = do_div(sec, 1000000000);
+
+	/* Update originTimestamp field of Sync packet
+	 * - 48 bits seconds field
+	 * - 32 bits nanseconds field
+	 *
+	 * In addition, if csum_offload is false, the UDP checksum needs
+	 * to be updated by software after updating originTimestamp field,
+	 * otherwise the hardware will calculate the wrong checksum when
+	 * updating the correction field and update it to the packet.
+	 */
+
+	data = skb_mac_header(skb);
+	new_sec_h = htons((sec >> 32) & 0xffff);
+	new_sec_l = htonl(sec & 0xffffffff);
+	new_nsec = htonl(nsec);
+	if (enetc_cb->udp && !csum_offload) {
+		struct udphdr *uh = udp_hdr(skb);
+		__be32 old_sec_l, old_nsec;
+		__be16 old_sec_h;
+
+		old_sec_h = *(__be16 *)(data + tstamp_off);
+		inet_proto_csum_replace2(&uh->check, skb, old_sec_h,
+					 new_sec_h, false);
+
+		old_sec_l = *(__be32 *)(data + tstamp_off + 2);
+		inet_proto_csum_replace4(&uh->check, skb, old_sec_l,
+					 new_sec_l, false);
+
+		old_nsec = *(__be32 *)(data + tstamp_off + 6);
+		inet_proto_csum_replace4(&uh->check, skb, old_nsec,
+					 new_nsec, false);
+	}
+
+	*(__be16 *)(data + tstamp_off) = new_sec_h;
+	*(__be32 *)(data + tstamp_off + 2) = new_sec_l;
+	*(__be32 *)(data + tstamp_off + 6) = new_nsec;
+
+	/* Configure single-step register */
+	if (is_enetc_rev1(si))
+		enetc_set_one_step_ts(si, enetc_cb->udp, corr_off);
+	else
+		enetc4_set_one_step_ts(si, enetc_cb->udp, corr_off);
+
+	return lo & ENETC_TXBD_TSTAMP;
+}
+
 static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 {
 	bool do_vlan, do_onestep_tstamp = false, do_twostep_tstamp = false;
 	struct enetc_ndev_priv *priv = netdev_priv(tx_ring->ndev);
-	struct enetc_hw *hw = &priv->si->hw;
+	struct enetc_skb_cb *enetc_cb = ENETC_SKB_CB(skb);
 	struct enetc_tx_swbd *tx_swbd;
 	int len = skb_headlen(skb);
 	union enetc_tx_bd temp_bd;
-	u8 msgtype, twostep, udp;
+	bool csum_offload = false;
 	union enetc_tx_bd *txbd;
-	u16 offset1, offset2;
 	int i, count = 0;
 	skb_frag_t *frag;
 	unsigned int f;
 	dma_addr_t dma;
 	u8 flags = 0;
+	u32 tstamp;
 
 	enetc_clear_tx_bd(&temp_bd);
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
@@ -202,11 +354,19 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 				temp_bd.l4_aux = FIELD_PREP(ENETC_TX_BD_L4T,
 							    ENETC_TXBD_L4T_UDP);
 			flags |= ENETC_TXBD_FLAGS_CSUM_LSO | ENETC_TXBD_FLAGS_L4CS;
+			csum_offload = true;
 		} else if (skb_checksum_help(skb)) {
 			return 0;
 		}
 	}
 
+	if (enetc_cb->flag & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) {
+		do_onestep_tstamp = true;
+		tstamp = enetc_update_ptp_sync_msg(priv, skb, csum_offload);
+	} else if (enetc_cb->flag & ENETC_F_TX_TSTAMP) {
+		do_twostep_tstamp = true;
+	}
+
 	i = tx_ring->next_to_use;
 	txbd = ENETC_TXBD(*tx_ring, i);
 	prefetchw(txbd);
@@ -226,17 +386,6 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 	count++;
 
 	do_vlan = skb_vlan_tag_present(skb);
-	if (skb->cb[0] & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) {
-		if (enetc_ptp_parse(skb, &udp, &msgtype, &twostep, &offset1,
-				    &offset2) ||
-		    msgtype != PTP_MSGTYPE_SYNC || twostep)
-			WARN_ONCE(1, "Bad packet for one-step timestamping\n");
-		else
-			do_onestep_tstamp = true;
-	} else if (skb->cb[0] & ENETC_F_TX_TSTAMP) {
-		do_twostep_tstamp = true;
-	}
-
 	tx_swbd->do_twostep_tstamp = do_twostep_tstamp;
 	tx_swbd->qbv_en = !!(priv->active_offloads & ENETC_F_QBV);
 	tx_swbd->check_wb = tx_swbd->do_twostep_tstamp || tx_swbd->qbv_en;
@@ -279,38 +428,9 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 		}
 
 		if (do_onestep_tstamp) {
-			u32 lo, hi, val;
-			u64 sec, nsec;
-			u8 *data;
-
-			lo = enetc_rd_hot(hw, ENETC_SICTR0);
-			hi = enetc_rd_hot(hw, ENETC_SICTR1);
-			sec = (u64)hi << 32 | lo;
-			nsec = do_div(sec, 1000000000);
-
 			/* Configure extension BD */
-			temp_bd.ext.tstamp = cpu_to_le32(lo & 0x3fffffff);
+			temp_bd.ext.tstamp = cpu_to_le32(tstamp);
 			e_flags |= ENETC_TXBD_E_FLAGS_ONE_STEP_PTP;
-
-			/* Update originTimestamp field of Sync packet
-			 * - 48 bits seconds field
-			 * - 32 bits nanseconds field
-			 */
-			data = skb_mac_header(skb);
-			*(__be16 *)(data + offset2) =
-				htons((sec >> 32) & 0xffff);
-			*(__be32 *)(data + offset2 + 2) =
-				htonl(sec & 0xffffffff);
-			*(__be32 *)(data + offset2 + 6) = htonl(nsec);
-
-			/* Configure single-step register */
-			val = ENETC_PM0_SINGLE_STEP_EN;
-			val |= ENETC_SET_SINGLE_STEP_OFFSET(offset1);
-			if (udp)
-				val |= ENETC_PM0_SINGLE_STEP_CH;
-
-			enetc_port_mac_wr(priv->si, ENETC_PM0_SINGLE_STEP,
-					  val);
 		} else if (do_twostep_tstamp) {
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 			e_flags |= ENETC_TXBD_E_FLAGS_TWO_STEP_PTP;
@@ -372,25 +492,20 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 dma_err:
 	dev_err(tx_ring->dev, "DMA map error");
 
-	do {
-		tx_swbd = &tx_ring->tx_swbd[i];
-		enetc_free_tx_frame(tx_ring, tx_swbd);
-		if (i == 0)
-			i = tx_ring->bd_count;
-		i--;
-	} while (count--);
+	enetc_unwind_tx_frame(tx_ring, count, i);
 
 	return 0;
 }
 
-static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
-				 struct enetc_tx_swbd *tx_swbd,
-				 union enetc_tx_bd *txbd, int *i, int hdr_len,
-				 int data_len)
+static int enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
+				struct enetc_tx_swbd *tx_swbd,
+				union enetc_tx_bd *txbd, int *i, int hdr_len,
+				int data_len)
 {
 	union enetc_tx_bd txbd_tmp;
 	u8 flags = 0, e_flags = 0;
 	dma_addr_t addr;
+	int count = 1;
 
 	enetc_clear_tx_bd(&txbd_tmp);
 	addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE;
@@ -433,7 +548,10 @@ static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
 		/* Write the BD */
 		txbd_tmp.ext.e_flags = e_flags;
 		*txbd = txbd_tmp;
+		count++;
 	}
+
+	return count;
 }
 
 static int enetc_map_tx_tso_data(struct enetc_bdr *tx_ring, struct sk_buff *skb,
@@ -790,9 +908,9 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
 
 		/* compute the csum over the L4 header */
 		csum = enetc_tso_hdr_csum(&tso, skb, hdr, hdr_len, &pos);
-		enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd, &i, hdr_len, data_len);
+		count += enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd,
+					      &i, hdr_len, data_len);
 		bd_data_num = 0;
-		count++;
 
 		while (data_len > 0) {
 			int size;
@@ -816,8 +934,13 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
 			err = enetc_map_tx_tso_data(tx_ring, skb, tx_swbd, txbd,
 						    tso.data, size,
 						    size == data_len);
-			if (err)
+			if (err) {
+				if (i == 0)
+					i = tx_ring->bd_count;
+				i--;
+
 				goto err_map_data;
+			}
 
 			data_len -= size;
 			count++;
@@ -846,13 +969,7 @@ err_map_data:
 	dev_err(tx_ring->dev, "DMA map error");
 
 err_chained_bd:
-	do {
-		tx_swbd = &tx_ring->tx_swbd[i];
-		enetc_free_tx_frame(tx_ring, tx_swbd);
-		if (i == 0)
-			i = tx_ring->bd_count;
-		i--;
-	} while (count--);
+	enetc_unwind_tx_frame(tx_ring, count, i);
 
 	return 0;
 }
@@ -860,12 +977,13 @@ err_chained_bd:
 static netdev_tx_t enetc_start_xmit(struct sk_buff *skb,
 				    struct net_device *ndev)
 {
+	struct enetc_skb_cb *enetc_cb = ENETC_SKB_CB(skb);
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	struct enetc_bdr *tx_ring;
 	int count;
 
 	/* Queue one-step Sync packet if already locked */
-	if (skb->cb[0] & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) {
+	if (enetc_cb->flag & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) {
 		if (test_and_set_bit_lock(ENETC_TX_ONESTEP_TSTAMP_IN_PROGRESS,
 					  &priv->flags)) {
 			skb_queue_tail(&priv->tx_skbs, skb);
@@ -927,24 +1045,29 @@ drop_packet_err:
 
 netdev_tx_t enetc_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
+	struct enetc_skb_cb *enetc_cb = ENETC_SKB_CB(skb);
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	u8 udp, msgtype, twostep;
 	u16 offset1, offset2;
 
-	/* Mark tx timestamp type on skb->cb[0] if requires */
+	/* Mark tx timestamp type on enetc_cb->flag if requires */
 	if ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
-	    (priv->active_offloads & ENETC_F_TX_TSTAMP_MASK)) {
-		skb->cb[0] = priv->active_offloads & ENETC_F_TX_TSTAMP_MASK;
-	} else {
-		skb->cb[0] = 0;
-	}
+	    (priv->active_offloads & ENETC_F_TX_TSTAMP_MASK))
+		enetc_cb->flag = priv->active_offloads & ENETC_F_TX_TSTAMP_MASK;
+	else
+		enetc_cb->flag = 0;
 
 	/* Fall back to two-step timestamp if not one-step Sync packet */
-	if (skb->cb[0] & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) {
+	if (enetc_cb->flag & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) {
 		if (enetc_ptp_parse(skb, &udp, &msgtype, &twostep,
 				    &offset1, &offset2) ||
-		    msgtype != PTP_MSGTYPE_SYNC || twostep != 0)
-			skb->cb[0] = ENETC_F_TX_TSTAMP;
+		    msgtype != PTP_MSGTYPE_SYNC || twostep != 0) {
+			enetc_cb->flag = ENETC_F_TX_TSTAMP;
+		} else {
+			enetc_cb->udp = !!udp;
+			enetc_cb->correction_off = offset1;
+			enetc_cb->origin_tstamp_off = offset2;
+		}
 	}
 
 	return enetc_start_xmit(skb, ndev);
@@ -1136,7 +1259,9 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget)
 		if (xdp_frame) {
 			xdp_return_frame(xdp_frame);
 		} else if (skb) {
-			if (unlikely(skb->cb[0] & ENETC_F_TX_ONESTEP_SYNC_TSTAMP)) {
+			struct enetc_skb_cb *enetc_cb = ENETC_SKB_CB(skb);
+
+			if (unlikely(enetc_cb->flag & ENETC_F_TX_ONESTEP_SYNC_TSTAMP)) {
 				/* Start work to release lock for next one-step
 				 * timestamping packet. And send one skb in
 				 * tx_skbs queue if has.
@@ -1297,6 +1422,7 @@ static void enetc_get_offloads(struct enetc_bdr *rx_ring,
 	}
 
 	if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_VLAN) {
+		struct enetc_hw *hw = &priv->si->hw;
 		__be16 tpid = 0;
 
 		switch (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_TPID) {
@@ -1307,22 +1433,18 @@ static void enetc_get_offloads(struct enetc_bdr *rx_ring,
 			tpid = htons(ETH_P_8021AD);
 			break;
 		case 2:
-			tpid = htons(enetc_port_rd(&priv->si->hw,
-						   ENETC_PCVLANR1));
+			tpid = htons(enetc_rd_hot(hw, ENETC_SICVLANR1) &
+				     SICVLANR_ETYPE);
 			break;
 		case 3:
-			tpid = htons(enetc_port_rd(&priv->si->hw,
-						   ENETC_PCVLANR2));
-			break;
-		default:
-			break;
+			tpid = htons(enetc_rd_hot(hw, ENETC_SICVLANR2) &
+				     SICVLANR_ETYPE);
 		}
 
 		__vlan_hwaccel_put_tag(skb, tpid, le16_to_cpu(rxbd->r.vlan_opt));
 	}
 
-	if (IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK) &&
-	    (priv->active_offloads & ENETC_F_RX_TSTAMP))
+	if (priv->active_offloads & ENETC_F_RX_TSTAMP)
 		enetc_get_rx_tstamp(rx_ring->ndev, rxbd, skb);
 }
 
@@ -1482,6 +1604,8 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
 	/* next descriptor to process */
 	i = rx_ring->next_to_clean;
 
+	enetc_lock_mdio();
+
 	while (likely(rx_frm_cnt < work_limit)) {
 		union enetc_rx_bd *rxbd;
 		struct sk_buff *skb;
@@ -1517,7 +1641,9 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
 		rx_byte_cnt += skb->len + ETH_HLEN;
 		rx_frm_cnt++;
 
+		enetc_unlock_mdio();
 		napi_gro_receive(napi, skb);
+		enetc_lock_mdio();
 	}
 
 	rx_ring->next_to_clean = i;
@@ -1525,6 +1651,8 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
 	rx_ring->stats.packets += rx_frm_cnt;
 	rx_ring->stats.bytes += rx_byte_cnt;
 
+	enetc_unlock_mdio();
+
 	return rx_frm_cnt;
 }
 
@@ -1808,6 +1936,16 @@ static void enetc_xdp_drop(struct enetc_bdr *rx_ring, int rx_ring_first,
 	}
 }
 
+static void enetc_bulk_flip_buff(struct enetc_bdr *rx_ring, int rx_ring_first,
+				 int rx_ring_last)
+{
+	while (rx_ring_first != rx_ring_last) {
+		enetc_flip_rx_buff(rx_ring,
+				   &rx_ring->rx_swbd[rx_ring_first]);
+		enetc_bdr_idx_inc(rx_ring, &rx_ring_first);
+	}
+}
+
 static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				   struct napi_struct *napi, int work_limit,
 				   struct bpf_prog *prog)
@@ -1824,13 +1962,14 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 	/* next descriptor to process */
 	i = rx_ring->next_to_clean;
 
+	enetc_lock_mdio();
+
 	while (likely(rx_frm_cnt < work_limit)) {
 		union enetc_rx_bd *rxbd, *orig_rxbd;
-		int orig_i, orig_cleaned_cnt;
 		struct xdp_buff xdp_buff;
 		struct sk_buff *skb;
+		int orig_i, err;
 		u32 bd_status;
-		int err;
 
 		rxbd = enetc_rxbd(rx_ring, i);
 		bd_status = le32_to_cpu(rxbd->r.lstatus);
@@ -1845,7 +1984,6 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 			break;
 
 		orig_rxbd = rxbd;
-		orig_cleaned_cnt = cleaned_cnt;
 		orig_i = i;
 
 		enetc_build_xdp_buff(rx_ring, bd_status, &rxbd, &i,
@@ -1873,17 +2011,25 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 			rx_ring->stats.xdp_drops++;
 			break;
 		case XDP_PASS:
-			rxbd = orig_rxbd;
-			cleaned_cnt = orig_cleaned_cnt;
-			i = orig_i;
-
-			skb = enetc_build_skb(rx_ring, bd_status, &rxbd,
-					      &i, &cleaned_cnt,
-					      ENETC_RXB_DMA_SIZE_XDP);
-			if (unlikely(!skb))
+			skb = xdp_build_skb_from_buff(&xdp_buff);
+			/* Probably under memory pressure, stop NAPI */
+			if (unlikely(!skb)) {
+				enetc_xdp_drop(rx_ring, orig_i, i);
+				rx_ring->stats.xdp_drops++;
 				goto out;
+			}
+
+			enetc_get_offloads(rx_ring, orig_rxbd, skb);
+
+			/* These buffers are about to be owned by the stack.
+			 * Update our buffer cache (the rx_swbd array elements)
+			 * with their other page halves.
+			 */
+			enetc_bulk_flip_buff(rx_ring, orig_i, i);
 
+			enetc_unlock_mdio();
 			napi_gro_receive(napi, skb);
+			enetc_lock_mdio();
 			break;
 		case XDP_TX:
 			tx_ring = priv->xdp_tx_ring[rx_ring->index];
@@ -1901,7 +2047,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				enetc_xdp_drop(rx_ring, orig_i, i);
 				tx_ring->stats.xdp_tx_drops++;
 			} else {
-				tx_ring->stats.xdp_tx += xdp_tx_bd_cnt;
+				tx_ring->stats.xdp_tx++;
 				rx_ring->xdp.xdp_tx_in_flight += xdp_tx_bd_cnt;
 				xdp_tx_frm_cnt++;
 				/* The XDP_TX enqueue was successful, so we
@@ -1918,16 +2064,14 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 			}
 			break;
 		case XDP_REDIRECT:
+			enetc_unlock_mdio();
 			err = xdp_do_redirect(rx_ring->ndev, &xdp_buff, prog);
+			enetc_lock_mdio();
 			if (unlikely(err)) {
 				enetc_xdp_drop(rx_ring, orig_i, i);
 				rx_ring->stats.xdp_redirect_failures++;
 			} else {
-				while (orig_i != i) {
-					enetc_flip_rx_buff(rx_ring,
-							   &rx_ring->rx_swbd[orig_i]);
-					enetc_bdr_idx_inc(rx_ring, &orig_i);
-				}
+				enetc_bulk_flip_buff(rx_ring, orig_i, i);
 				xdp_redirect_frm_cnt++;
 				rx_ring->stats.xdp_redirect++;
 			}
@@ -1942,8 +2086,11 @@ out:
 	rx_ring->stats.packets += rx_frm_cnt;
 	rx_ring->stats.bytes += rx_byte_cnt;
 
-	if (xdp_redirect_frm_cnt)
+	if (xdp_redirect_frm_cnt) {
+		enetc_unlock_mdio();
 		xdp_do_flush();
+		enetc_lock_mdio();
+	}
 
 	if (xdp_tx_frm_cnt)
 		enetc_update_tx_ring_tail(tx_ring);
@@ -1952,6 +2099,8 @@ out:
 		enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring) -
 				     rx_ring->xdp.xdp_tx_in_flight);
 
+	enetc_unlock_mdio();
+
 	return rx_frm_cnt;
 }
 
@@ -1970,6 +2119,7 @@ static int enetc_poll(struct napi_struct *napi, int budget)
 	for (i = 0; i < v->count_tx_rings; i++)
 		if (!enetc_clean_tx_ring(&v->tx_ring[i], budget))
 			complete = false;
+	enetc_unlock_mdio();
 
 	prog = rx_ring->xdp.prog;
 	if (prog)
@@ -1981,10 +2131,8 @@ static int enetc_poll(struct napi_struct *napi, int budget)
 	if (work_done)
 		v->rx_napi_work = true;
 
-	if (!complete) {
-		enetc_unlock_mdio();
+	if (!complete)
 		return budget;
-	}
 
 	napi_complete_done(napi, work_done);
 
@@ -1993,6 +2141,7 @@ static int enetc_poll(struct napi_struct *napi, int budget)
 
 	v->rx_napi_work = false;
 
+	enetc_lock_mdio();
 	/* enable interrupts */
 	enetc_wr_reg_hot(v->rbier, ENETC_RBIER_RXTIE);
 
@@ -2327,7 +2476,7 @@ static int enetc_setup_default_rss_table(struct enetc_si *si, int num_groups)
 	for (i = 0; i < si->num_rss; i++)
 		rss_table[i] = i % num_groups;
 
-	enetc_set_rss_table(si, rss_table, si->num_rss);
+	si->ops->set_rss_table(si, rss_table, si->num_rss);
 
 	kfree(rss_table);
 
@@ -2342,6 +2491,20 @@ static void enetc_set_lso_flags_mask(struct enetc_hw *hw)
 	enetc_wr(hw, ENETC4_SILSOSFMR1, 0);
 }
 
+static void enetc_set_rss(struct net_device *ndev, int en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	u32 reg;
+
+	enetc_wr(hw, ENETC_SIRBGCR, priv->num_rx_rings);
+
+	reg = enetc_rd(hw, ENETC_SIMR);
+	reg &= ~ENETC_SIMR_RSSE;
+	reg |= (en) ? ENETC_SIMR_RSSE : 0;
+	enetc_wr(hw, ENETC_SIMR, reg);
+}
+
 int enetc_configure_si(struct enetc_ndev_priv *priv)
 {
 	struct enetc_si *si = priv->si;
@@ -2358,13 +2521,13 @@ int enetc_configure_si(struct enetc_ndev_priv *priv)
 	if (si->hw_features & ENETC_SI_F_LSO)
 		enetc_set_lso_flags_mask(hw);
 
-	/* TODO: RSS support for i.MX95 will be supported later, and the
-	 * is_enetc_rev1() condition will be removed
-	 */
-	if (si->num_rss && is_enetc_rev1(si)) {
+	if (si->num_rss) {
 		err = enetc_setup_default_rss_table(si, priv->num_rx_rings);
 		if (err)
 			return err;
+
+		if (priv->ndev->features & NETIF_F_RXHASH)
+			enetc_set_rss(priv->ndev, true);
 	}
 
 	return 0;
@@ -3157,22 +3320,6 @@ struct net_device_stats *enetc_get_stats(struct net_device *ndev)
 }
 EXPORT_SYMBOL_GPL(enetc_get_stats);
 
-static int enetc_set_rss(struct net_device *ndev, int en)
-{
-	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_hw *hw = &priv->si->hw;
-	u32 reg;
-
-	enetc_wr(hw, ENETC_SIRBGCR, priv->num_rx_rings);
-
-	reg = enetc_rd(hw, ENETC_SIMR);
-	reg &= ~ENETC_SIMR_RSSE;
-	reg |= (en) ? ENETC_SIMR_RSSE : 0;
-	enetc_wr(hw, ENETC_SIMR, reg);
-
-	return 0;
-}
-
 static void enetc_enable_rxvlan(struct net_device *ndev, bool en)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
@@ -3210,16 +3357,17 @@ void enetc_set_features(struct net_device *ndev, netdev_features_t features)
 }
 EXPORT_SYMBOL_GPL(enetc_set_features);
 
-static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
+int enetc_hwtstamp_set(struct net_device *ndev,
+		       struct kernel_hwtstamp_config *config,
+		       struct netlink_ext_ack *extack)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	int err, new_offloads = priv->active_offloads;
-	struct hwtstamp_config config;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	if (!enetc_ptp_clock_is_enabled(priv->si))
+		return -EOPNOTSUPP;
 
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		new_offloads &= ~ENETC_F_TX_TSTAMP_MASK;
 		break;
@@ -3228,6 +3376,10 @@ static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
 		new_offloads |= ENETC_F_TX_TSTAMP;
 		break;
 	case HWTSTAMP_TX_ONESTEP_SYNC:
+		if (!enetc_si_is_pf(priv->si) ||
+		    enetc_is_pseudo_mac(priv->si))
+			return -EOPNOTSUPP;
+
 		new_offloads &= ~ENETC_F_TX_TSTAMP_MASK;
 		new_offloads |= ENETC_F_TX_ONESTEP_SYNC_TSTAMP;
 		break;
@@ -3235,13 +3387,13 @@ static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		new_offloads &= ~ENETC_F_RX_TSTAMP;
 		break;
 	default:
 		new_offloads |= ENETC_F_RX_TSTAMP;
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 	}
 
 	if ((new_offloads ^ priv->active_offloads) & ENETC_F_RX_TSTAMP) {
@@ -3254,42 +3406,36 @@ static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
 
 	priv->active_offloads = new_offloads;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-	       -EFAULT : 0;
+	return 0;
 }
+EXPORT_SYMBOL_GPL(enetc_hwtstamp_set);
 
-static int enetc_hwtstamp_get(struct net_device *ndev, struct ifreq *ifr)
+int enetc_hwtstamp_get(struct net_device *ndev,
+		       struct kernel_hwtstamp_config *config)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct hwtstamp_config config;
 
-	config.flags = 0;
+	if (!enetc_ptp_clock_is_enabled(priv->si))
+		return -EOPNOTSUPP;
 
 	if (priv->active_offloads & ENETC_F_TX_ONESTEP_SYNC_TSTAMP)
-		config.tx_type = HWTSTAMP_TX_ONESTEP_SYNC;
+		config->tx_type = HWTSTAMP_TX_ONESTEP_SYNC;
 	else if (priv->active_offloads & ENETC_F_TX_TSTAMP)
-		config.tx_type = HWTSTAMP_TX_ON;
+		config->tx_type = HWTSTAMP_TX_ON;
 	else
-		config.tx_type = HWTSTAMP_TX_OFF;
+		config->tx_type = HWTSTAMP_TX_OFF;
 
-	config.rx_filter = (priv->active_offloads & ENETC_F_RX_TSTAMP) ?
-			    HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
+	config->rx_filter = (priv->active_offloads & ENETC_F_RX_TSTAMP) ?
+			     HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-	       -EFAULT : 0;
+	return 0;
 }
+EXPORT_SYMBOL_GPL(enetc_hwtstamp_get);
 
 int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 
-	if (IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK)) {
-		if (cmd == SIOCSHWTSTAMP)
-			return enetc_hwtstamp_set(ndev, rq);
-		if (cmd == SIOCGHWTSTAMP)
-			return enetc_hwtstamp_get(ndev, rq);
-	}
-
 	if (!priv->phylink)
 		return -EOPNOTSUPP;
 
@@ -3317,7 +3463,8 @@ static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i,
 	bdr->buffer_offset = ENETC_RXB_PAD;
 	priv->rx_ring[i] = bdr;
 
-	err = xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0);
+	err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0,
+				 ENETC_RXB_DMA_SIZE_XDP);
 	if (err)
 		goto free_vector;
 
@@ -3571,6 +3718,13 @@ static const struct enetc_drvdata enetc4_pf_data = {
 	.eth_ops = &enetc4_pf_ethtool_ops,
 };
 
+static const struct enetc_drvdata enetc4_ppm_data = {
+	.sysclk_freq = ENETC_CLK_333M,
+	.tx_csum = true,
+	.max_frags = ENETC4_MAX_SKB_FRAGS,
+	.eth_ops = &enetc4_ppm_ethtool_ops,
+};
+
 static const struct enetc_drvdata enetc_vf_data = {
 	.sysclk_freq = ENETC_CLK_400M,
 	.max_frags = ENETC_MAX_SKB_FRAGS,
@@ -3590,6 +3744,15 @@ static const struct enetc_platform_info enetc_info[] = {
 	  .dev_id = ENETC_DEV_ID_VF,
 	  .data = &enetc_vf_data,
 	},
+	{
+	  .revision = ENETC_REV_4_3,
+	  .dev_id = NXP_ENETC_PPM_DEV_ID,
+	  .data = &enetc4_ppm_data,
+	},
+	{ .revision = ENETC_REV_4_3,
+	  .dev_id = NXP_ENETC_PF_DEV_ID,
+	  .data = &enetc4_pf_data,
+	},
 };
 
 int enetc_get_driver_data(struct enetc_si *si)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 4ad4eb5c5a74..dce27bd67a7d 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -8,6 +8,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/skbuff.h>
 #include <linux/ethtool.h>
+#include <linux/fsl/ntmp.h>
 #include <linux/if_vlan.h>
 #include <linux/phylink.h>
 #include <linux/dim.h>
@@ -22,6 +23,18 @@
 
 #define ENETC_CBD_DATA_MEM_ALIGN 64
 
+#define ENETC_MADDR_HASH_TBL_SZ	64
+
+enum enetc_mac_addr_type {UC, MC, MADDR_TYPE};
+
+struct enetc_mac_filter {
+	union {
+		char mac_addr[ETH_ALEN];
+		DECLARE_BITMAP(mac_hash_table, ENETC_MADDR_HASH_TBL_SZ);
+	};
+	int mac_addr_cnt;
+};
+
 struct enetc_tx_swbd {
 	union {
 		struct sk_buff *skb;
@@ -41,6 +54,15 @@ struct enetc_tx_swbd {
 	u8 qbv_en:1;
 };
 
+struct enetc_skb_cb {
+	u8 flag;
+	bool udp;
+	u16 correction_off;
+	u16 origin_tstamp_off;
+};
+
+#define ENETC_SKB_CB(skb) ((struct enetc_skb_cb *)((skb)->cb))
+
 struct enetc_lso_t {
 	bool	ipv6;
 	bool	tcp;
@@ -54,7 +76,7 @@ struct enetc_lso_t {
 #define ENETC_LSO_MAX_DATA_LEN		SZ_256K
 
 #define ENETC_RX_MAXFRM_SIZE	ENETC_MAC_MAXFRM_SIZE
-#define ENETC_RXB_TRUESIZE	2048 /* PAGE_SIZE >> 1 */
+#define ENETC_RXB_TRUESIZE	(PAGE_SIZE >> 1)
 #define ENETC_RXB_PAD		NET_SKB_PAD /* add extra space if needed */
 #define ENETC_RXB_DMA_SIZE	\
 	(SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - ENETC_RXB_PAD)
@@ -83,17 +105,17 @@ struct enetc_rx_swbd {
 #define ENETC_TXBDS_MAX_NEEDED(x)	ENETC_TXBDS_NEEDED((x) + 1)
 
 struct enetc_ring_stats {
-	unsigned int packets;
-	unsigned int bytes;
-	unsigned int rx_alloc_errs;
-	unsigned int xdp_drops;
-	unsigned int xdp_tx;
-	unsigned int xdp_tx_drops;
-	unsigned int xdp_redirect;
-	unsigned int xdp_redirect_failures;
-	unsigned int recycles;
-	unsigned int recycle_failures;
-	unsigned int win_drop;
+	unsigned long packets;
+	unsigned long bytes;
+	unsigned long rx_alloc_errs;
+	unsigned long xdp_drops;
+	unsigned long xdp_tx;
+	unsigned long xdp_tx_drops;
+	unsigned long xdp_redirect;
+	unsigned long xdp_redirect_failures;
+	unsigned long recycles;
+	unsigned long recycle_failures;
+	unsigned long win_drop;
 };
 
 struct enetc_xdp_data {
@@ -204,7 +226,7 @@ static inline union enetc_rx_bd *enetc_rxbd(struct enetc_bdr *rx_ring, int i)
 {
 	int hw_idx = i;
 
-	if (IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK) && rx_ring->ext_en)
+	if (rx_ring->ext_en)
 		hw_idx = 2 * i;
 
 	return &(((union enetc_rx_bd *)rx_ring->bd_base)[hw_idx]);
@@ -218,7 +240,7 @@ static inline void enetc_rxbd_next(struct enetc_bdr *rx_ring,
 
 	new_rxbd++;
 
-	if (IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK) && rx_ring->ext_en)
+	if (rx_ring->ext_en)
 		new_rxbd++;
 
 	if (unlikely(++new_index == rx_ring->bd_count)) {
@@ -251,6 +273,7 @@ enum enetc_errata {
 #define ENETC_SI_F_QBV  BIT(1)
 #define ENETC_SI_F_QBU  BIT(2)
 #define ENETC_SI_F_LSO	BIT(3)
+#define ENETC_SI_F_PPM	BIT(4) /* pseudo MAC */
 
 struct enetc_drvdata {
 	u32 pmac_offset; /* Only valid for PSI which supports 802.1Qbu */
@@ -266,6 +289,19 @@ struct enetc_platform_info {
 	const struct enetc_drvdata *data;
 };
 
+struct enetc_si;
+
+/*
+ * This structure defines the some common hooks for ENETC PSI and VSI.
+ * In addition, since VSI only uses the struct enetc_si as its private
+ * driver data, so this structure also define some hooks specifically
+ * for VSI. For VSI-specific hooks, the format is ‘vf_*()’.
+ */
+struct enetc_si_ops {
+	int (*get_rss_table)(struct enetc_si *si, u32 *table, int count);
+	int (*set_rss_table)(struct enetc_si *si, const u32 *table, int count);
+};
+
 /* PCI IEP device data */
 struct enetc_si {
 	struct pci_dev *pdev;
@@ -274,7 +310,10 @@ struct enetc_si {
 
 	struct net_device *ndev; /* back ref. */
 
-	struct enetc_cbdr cbd_ring;
+	union {
+		struct enetc_cbdr cbd_ring; /* Only ENETC 1.0 */
+		struct ntmp_user ntmp_user; /* ENETC 4.1 and later */
+	};
 
 	int num_rx_rings; /* how many rings are available in the SI */
 	int num_tx_rings;
@@ -284,6 +323,11 @@ struct enetc_si {
 	u16 revision;
 	int hw_features;
 	const struct enetc_drvdata *drvdata;
+	const struct enetc_si_ops *ops;
+
+	struct workqueue_struct *workqueue;
+	struct work_struct rx_mode_task;
+	struct dentry *debugfs_root;
 };
 
 #define ENETC_SI_ALIGN	32
@@ -319,6 +363,11 @@ static inline int enetc_pf_to_port(struct pci_dev *pf_pdev)
 	}
 }
 
+static inline bool enetc_is_pseudo_mac(struct enetc_si *si)
+{
+	return si->hw_features & ENETC_SI_F_PPM;
+}
+
 #define ENETC_MAX_NUM_TXQS	8
 #define ENETC_INT_NAME_MAX	(IFNAMSIZ + 8)
 
@@ -450,9 +499,6 @@ struct enetc_msg_cmd_set_primary_mac {
 
 #define ENETC_CBDR_TIMEOUT	1000 /* usecs */
 
-/* PTP driver exports */
-extern int enetc_phc_index;
-
 /* SI common */
 u32 enetc_port_mac_rd(struct enetc_si *si, u32 reg);
 void enetc_port_mac_wr(struct enetc_si *si, u32 reg, u32 val);
@@ -466,6 +512,9 @@ int enetc_alloc_si_resources(struct enetc_ndev_priv *priv);
 void enetc_free_si_resources(struct enetc_ndev_priv *priv);
 int enetc_configure_si(struct enetc_ndev_priv *priv);
 int enetc_get_driver_data(struct enetc_si *si);
+void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
+				  const unsigned char *addr);
+void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter);
 
 int enetc_open(struct net_device *ndev);
 int enetc_close(struct net_device *ndev);
@@ -481,10 +530,18 @@ int enetc_setup_bpf(struct net_device *ndev, struct netdev_bpf *bpf);
 int enetc_xdp_xmit(struct net_device *ndev, int num_frames,
 		   struct xdp_frame **frames, u32 flags);
 
+int enetc_hwtstamp_get(struct net_device *ndev,
+		       struct kernel_hwtstamp_config *config);
+int enetc_hwtstamp_set(struct net_device *ndev,
+		       struct kernel_hwtstamp_config *config,
+		       struct netlink_ext_ack *extack);
+
 /* ethtool */
 extern const struct ethtool_ops enetc_pf_ethtool_ops;
 extern const struct ethtool_ops enetc4_pf_ethtool_ops;
 extern const struct ethtool_ops enetc_vf_ethtool_ops;
+extern const struct ethtool_ops enetc4_ppm_ethtool_ops;
+
 void enetc_set_ethtool_ops(struct net_device *ndev);
 void enetc_mm_link_state_update(struct enetc_ndev_priv *priv, bool link);
 void enetc_mm_commit_preemptible_tcs(struct enetc_ndev_priv *priv);
@@ -493,15 +550,19 @@ void enetc_mm_commit_preemptible_tcs(struct enetc_ndev_priv *priv);
 int enetc_setup_cbdr(struct device *dev, struct enetc_hw *hw, int bd_count,
 		     struct enetc_cbdr *cbdr);
 void enetc_teardown_cbdr(struct enetc_cbdr *cbdr);
+int enetc4_setup_cbdr(struct enetc_si *si);
+void enetc4_teardown_cbdr(struct enetc_si *si);
 int enetc_set_mac_flt_entry(struct enetc_si *si, int index,
 			    char *mac_addr, int si_map);
 int enetc_clear_mac_flt_entry(struct enetc_si *si, int index);
 int enetc_set_fs_entry(struct enetc_si *si, struct enetc_cmd_rfse *rfse,
 		       int index);
-void enetc_set_rss_key(struct enetc_hw *hw, const u8 *bytes);
+void enetc_set_rss_key(struct enetc_si *si, const u8 *bytes);
 int enetc_get_rss_table(struct enetc_si *si, u32 *table, int count);
 int enetc_set_rss_table(struct enetc_si *si, const u32 *table, int count);
 int enetc_send_cmd(struct enetc_si *si, struct enetc_cbd *cbd);
+int enetc4_get_rss_table(struct enetc_si *si, u32 *table, int count);
+int enetc4_set_rss_table(struct enetc_si *si, const u32 *table, int count);
 
 static inline void *enetc_cbd_alloc_data_mem(struct enetc_si *si,
 					     struct enetc_cbd *cbd,
@@ -542,6 +603,14 @@ static inline void enetc_cbd_free_data_mem(struct enetc_si *si, int size,
 void enetc_reset_ptcmsdur(struct enetc_hw *hw);
 void enetc_set_ptcmsdur(struct enetc_hw *hw, u32 *queue_max_sdu);
 
+static inline bool enetc_ptp_clock_is_enabled(struct enetc_si *si)
+{
+	if (is_enetc_rev1(si))
+		return IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK);
+
+	return IS_ENABLED(CONFIG_PTP_NETC_V4_TIMER);
+}
+
 #ifdef CONFIG_FSL_ENETC_QOS
 int enetc_qos_query_caps(struct net_device *ndev, void *type_data);
 int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
new file mode 100644
index 000000000000..1b1591dce73d
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright 2025 NXP */
+
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/string_choices.h>
+
+#include "enetc_pf.h"
+#include "enetc4_debugfs.h"
+
+static void enetc_show_si_mac_hash_filter(struct seq_file *s, int i)
+{
+	struct enetc_si *si = s->private;
+	struct enetc_hw *hw = &si->hw;
+	u32 hash_h, hash_l;
+
+	hash_l = enetc_port_rd(hw, ENETC4_PSIUMHFR0(i));
+	hash_h = enetc_port_rd(hw, ENETC4_PSIUMHFR1(i));
+	seq_printf(s, "SI %d unicast MAC hash filter: 0x%08x%08x\n",
+		   i, hash_h, hash_l);
+
+	hash_l = enetc_port_rd(hw, ENETC4_PSIMMHFR0(i));
+	hash_h = enetc_port_rd(hw, ENETC4_PSIMMHFR1(i));
+	seq_printf(s, "SI %d multicast MAC hash filter: 0x%08x%08x\n",
+		   i, hash_h, hash_l);
+}
+
+static int enetc_mac_filter_show(struct seq_file *s, void *data)
+{
+	struct enetc_si *si = s->private;
+	struct enetc_hw *hw = &si->hw;
+	struct maft_entry_data maft;
+	struct enetc_pf *pf;
+	int i, err, num_si;
+	u32 val;
+
+	pf = enetc_si_priv(si);
+	num_si = pf->caps.num_vsi + 1;
+
+	val = enetc_port_rd(hw, ENETC4_PSIPMMR);
+	for (i = 0; i < num_si; i++) {
+		seq_printf(s, "SI %d Unicast Promiscuous mode: %s\n", i,
+			   str_enabled_disabled(PSIPMMR_SI_MAC_UP(i) & val));
+		seq_printf(s, "SI %d Multicast Promiscuous mode: %s\n", i,
+			   str_enabled_disabled(PSIPMMR_SI_MAC_MP(i) & val));
+	}
+
+	/* MAC hash filter table */
+	for (i = 0; i < num_si; i++)
+		enetc_show_si_mac_hash_filter(s, i);
+
+	if (!pf->num_mfe)
+		return 0;
+
+	/* MAC address filter table */
+	seq_puts(s, "MAC address filter table\n");
+	for (i = 0; i < pf->num_mfe; i++) {
+		memset(&maft, 0, sizeof(maft));
+		err = ntmp_maft_query_entry(&si->ntmp_user, i, &maft);
+		if (err)
+			return err;
+
+		seq_printf(s, "Entry %d, MAC: %pM, SI bitmap: 0x%04x\n", i,
+			   maft.keye.mac_addr, le16_to_cpu(maft.cfge.si_bitmap));
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(enetc_mac_filter);
+
+void enetc_create_debugfs(struct enetc_si *si)
+{
+	struct net_device *ndev = si->ndev;
+	struct dentry *root;
+
+	root = debugfs_create_dir(netdev_name(ndev), NULL);
+	if (IS_ERR(root))
+		return;
+
+	si->debugfs_root = root;
+
+	debugfs_create_file("mac_filter", 0444, root, si, &enetc_mac_filter_fops);
+}
+
+void enetc_remove_debugfs(struct enetc_si *si)
+{
+	debugfs_remove(si->debugfs_root);
+	si->debugfs_root = NULL;
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.h b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.h
new file mode 100644
index 000000000000..96caca35f79d
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2025 NXP */
+
+#ifndef __ENETC4_DEBUGFS_H
+#define __ENETC4_DEBUGFS_H
+
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+void enetc_create_debugfs(struct enetc_si *si);
+void enetc_remove_debugfs(struct enetc_si *si);
+#else
+static inline void enetc_create_debugfs(struct enetc_si *si)
+{
+}
+
+static inline void enetc_remove_debugfs(struct enetc_si *si)
+{
+}
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
index 695cb07c74bc..3ed0f7a02767 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
@@ -11,6 +11,7 @@
 
 #define NXP_ENETC_VENDOR_ID		0x1131
 #define NXP_ENETC_PF_DEV_ID		0xe101
+#define NXP_ENETC_PPM_DEV_ID		0xe110
 
 /**********************Station interface registers************************/
 /* Station interface LSO segmentation flag mask register 0/1 */
@@ -99,10 +100,26 @@
 #define ENETC4_PSICFGR2(a)		((a) * 0x80 + 0x2018)
 #define  PSICFGR2_NUM_MSIX		GENMASK(5, 0)
 
+/* Port station interface a unicast MAC hash filter register 0/1 */
+#define ENETC4_PSIUMHFR0(a)		((a) * 0x80 + 0x2050)
+#define ENETC4_PSIUMHFR1(a)		((a) * 0x80 + 0x2054)
+
+/* Port station interface a multicast MAC hash filter register 0/1 */
+#define ENETC4_PSIMMHFR0(a)		((a) * 0x80 + 0x2058)
+#define ENETC4_PSIMMHFR1(a)		((a) * 0x80 + 0x205c)
+
+/* Port station interface a VLAN hash filter register 0/1 */
+#define ENETC4_PSIVHFR0(a)		((a) * 0x80 + 0x2060)
+#define ENETC4_PSIVHFR1(a)		((a) * 0x80 + 0x2064)
+
 #define ENETC4_PMCAPR			0x4004
 #define  PMCAPR_HD			BIT(8)
 #define  PMCAPR_FP			GENMASK(10, 9)
 
+/* Port capability register */
+#define ENETC4_PCAPR			0x4000
+#define  PCAPR_LINK_TYPE		BIT(4)
+
 /* Port configuration register */
 #define ENETC4_PCR			0x4010
 #define  PCR_HDR_FMT			BIT(0)
@@ -153,12 +170,21 @@
 /* Port MAC 0/1 Maximum Frame Length Register */
 #define ENETC4_PM_MAXFRM(mac)		(0x5014 + (mac) * 0x400)
 
+/* Port internal MDIO base address, use to access PCS */
+#define ENETC4_PM_IMDIO_BASE		0x5030
+
 /* Port MAC 0/1 Pause Quanta Register */
 #define ENETC4_PM_PAUSE_QUANTA(mac)	(0x5054 + (mac) * 0x400)
 
 /* Port MAC 0/1 Pause Quanta Threshold Register */
 #define ENETC4_PM_PAUSE_THRESH(mac)	(0x5064 + (mac) * 0x400)
 
+#define ENETC4_PM_SINGLE_STEP(mac)	(0x50c0 + (mac) * 0x400)
+#define  PM_SINGLE_STEP_CH		BIT(6)
+#define  PM_SINGLE_STEP_OFFSET		GENMASK(15, 7)
+#define  PM_SINGLE_STEP_OFFSET_SET(o)	FIELD_PREP(PM_SINGLE_STEP_OFFSET, o)
+#define  PM_SINGLE_STEP_EN		BIT(31)
+
 /* Port MAC 0 Interface Mode Control Register */
 #define ENETC4_PM_IF_MODE(mac)		(0x5300 + (mac) * 0x400)
 #define  PM_IF_MODE_IFMODE		GENMASK(2, 0)
@@ -175,4 +201,32 @@
 #define   SSP_1G			2
 #define  PM_IF_MODE_ENA			BIT(15)
 
+/* Port external MDIO Base address, use to access off-chip PHY */
+#define ENETC4_EMDIO_BASE		0x5c00
+
+/**********************ENETC Pseudo MAC port registers************************/
+/* Port pseudo MAC receive octets counter (64-bit) */
+#define ENETC4_PPMROCR			0x5080
+
+/* Port pseudo MAC receive unicast frame counter register (64-bit) */
+#define ENETC4_PPMRUFCR			0x5088
+
+/* Port pseudo MAC receive multicast frame counter register (64-bit) */
+#define ENETC4_PPMRMFCR			0x5090
+
+/* Port pseudo MAC receive broadcast frame counter register (64-bit) */
+#define ENETC4_PPMRBFCR			0x5098
+
+/* Port pseudo MAC transmit octets counter (64-bit) */
+#define ENETC4_PPMTOCR			0x50c0
+
+/* Port pseudo MAC transmit unicast frame counter register (64-bit) */
+#define ENETC4_PPMTUFCR			0x50c8
+
+/* Port pseudo MAC transmit multicast frame counter register (64-bit) */
+#define ENETC4_PPMTMFCR			0x50d0
+
+/* Port pseudo MAC transmit broadcast frame counter register (64-bit) */
+#define ENETC4_PPMTBFCR			0x50d8
+
 #endif
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index fc41078c4f5d..498346dd996a 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -8,9 +8,19 @@
 #include <linux/unaligned.h>
 
 #include "enetc_pf_common.h"
+#include "enetc4_debugfs.h"
 
 #define ENETC_SI_MAX_RING_NUM	8
 
+#define ENETC_MAC_FILTER_TYPE_UC	BIT(0)
+#define ENETC_MAC_FILTER_TYPE_MC	BIT(1)
+#define ENETC_MAC_FILTER_TYPE_ALL	(ENETC_MAC_FILTER_TYPE_UC | \
+					 ENETC_MAC_FILTER_TYPE_MC)
+
+struct enetc_mac_addr {
+	u8 addr[ETH_ALEN];
+};
+
 static void enetc4_get_port_caps(struct enetc_pf *pf)
 {
 	struct enetc_hw *hw = &pf->si->hw;
@@ -26,6 +36,19 @@ static void enetc4_get_port_caps(struct enetc_pf *pf)
 
 	val = enetc_port_rd(hw, ENETC4_PMCAPR);
 	pf->caps.half_duplex = (val & PMCAPR_HD) ? 1 : 0;
+
+	val = enetc_port_rd(hw, ENETC4_PSIMAFCAPR);
+	pf->caps.mac_filter_num = val & PSIMAFCAPR_NUM_MAC_AFTE;
+}
+
+static void enetc4_get_psi_hw_features(struct enetc_si *si)
+{
+	struct enetc_hw *hw = &si->hw;
+	u32 val;
+
+	val = enetc_port_rd(hw, ENETC4_PCAPR);
+	if (val & PCAPR_LINK_TYPE)
+		si->hw_features |= ENETC_SI_F_PPM;
 }
 
 static void enetc4_pf_set_si_primary_mac(struct enetc_hw *hw, int si,
@@ -56,6 +79,200 @@ static void enetc4_pf_get_si_primary_mac(struct enetc_hw *hw, int si,
 	put_unaligned_le16(lower, addr + 4);
 }
 
+static void enetc4_pf_set_si_mac_promisc(struct enetc_hw *hw, int si,
+					 bool uc_promisc, bool mc_promisc)
+{
+	u32 val = enetc_port_rd(hw, ENETC4_PSIPMMR);
+
+	if (uc_promisc)
+		val |= PSIPMMR_SI_MAC_UP(si);
+	else
+		val &= ~PSIPMMR_SI_MAC_UP(si);
+
+	if (mc_promisc)
+		val |= PSIPMMR_SI_MAC_MP(si);
+	else
+		val &= ~PSIPMMR_SI_MAC_MP(si);
+
+	enetc_port_wr(hw, ENETC4_PSIPMMR, val);
+}
+
+static void enetc4_pf_set_si_uc_hash_filter(struct enetc_hw *hw, int si,
+					    u64 hash)
+{
+	enetc_port_wr(hw, ENETC4_PSIUMHFR0(si), lower_32_bits(hash));
+	enetc_port_wr(hw, ENETC4_PSIUMHFR1(si), upper_32_bits(hash));
+}
+
+static void enetc4_pf_set_si_mc_hash_filter(struct enetc_hw *hw, int si,
+					    u64 hash)
+{
+	enetc_port_wr(hw, ENETC4_PSIMMHFR0(si), lower_32_bits(hash));
+	enetc_port_wr(hw, ENETC4_PSIMMHFR1(si), upper_32_bits(hash));
+}
+
+static void enetc4_pf_set_loopback(struct net_device *ndev, bool en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_si *si = priv->si;
+	u32 val;
+
+	val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0));
+	val = u32_replace_bits(val, en ? 1 : 0, PM_CMD_CFG_LOOP_EN);
+	/* Default to select MAC level loopback mode if loopback is enabled. */
+	val = u32_replace_bits(val, en ? LPBCK_MODE_MAC_LEVEL : 0,
+			       PM_CMD_CFG_LPBK_MODE);
+
+	enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val);
+}
+
+static void enetc4_pf_clear_maft_entries(struct enetc_pf *pf)
+{
+	int i;
+
+	for (i = 0; i < pf->num_mfe; i++)
+		ntmp_maft_delete_entry(&pf->si->ntmp_user, i);
+
+	pf->num_mfe = 0;
+}
+
+static int enetc4_pf_add_maft_entries(struct enetc_pf *pf,
+				      struct enetc_mac_addr *mac,
+				      int mac_cnt)
+{
+	struct maft_entry_data maft = {};
+	u16 si_bit = BIT(0);
+	int i, err;
+
+	maft.cfge.si_bitmap = cpu_to_le16(si_bit);
+	for (i = 0; i < mac_cnt; i++) {
+		ether_addr_copy(maft.keye.mac_addr, mac[i].addr);
+		err = ntmp_maft_add_entry(&pf->si->ntmp_user, i, &maft);
+		if (unlikely(err)) {
+			pf->num_mfe = i;
+			goto clear_maft_entries;
+		}
+	}
+
+	pf->num_mfe = mac_cnt;
+
+	return 0;
+
+clear_maft_entries:
+	enetc4_pf_clear_maft_entries(pf);
+
+	return  err;
+}
+
+static int enetc4_pf_set_uc_exact_filter(struct enetc_pf *pf)
+{
+	int max_num_mfe = pf->caps.mac_filter_num;
+	struct enetc_mac_filter mac_filter = {};
+	struct net_device *ndev = pf->si->ndev;
+	struct enetc_hw *hw = &pf->si->hw;
+	struct enetc_mac_addr *mac_tbl;
+	struct netdev_hw_addr *ha;
+	int i = 0, err;
+	int mac_cnt;
+
+	netif_addr_lock_bh(ndev);
+
+	mac_cnt = netdev_uc_count(ndev);
+	if (!mac_cnt) {
+		netif_addr_unlock_bh(ndev);
+		/* clear both MAC hash and exact filters */
+		enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+		enetc4_pf_clear_maft_entries(pf);
+
+		return 0;
+	}
+
+	if (mac_cnt > max_num_mfe) {
+		err = -ENOSPC;
+		goto unlock_netif_addr;
+	}
+
+	mac_tbl = kcalloc(mac_cnt, sizeof(*mac_tbl), GFP_ATOMIC);
+	if (!mac_tbl) {
+		err = -ENOMEM;
+		goto unlock_netif_addr;
+	}
+
+	netdev_for_each_uc_addr(ha, ndev) {
+		enetc_add_mac_addr_ht_filter(&mac_filter, ha->addr);
+		ether_addr_copy(mac_tbl[i++].addr, ha->addr);
+	}
+
+	netif_addr_unlock_bh(ndev);
+
+	/* Set temporary unicast hash filters in case of Rx loss when
+	 * updating MAC address filter table
+	 */
+	enetc4_pf_set_si_uc_hash_filter(hw, 0, *mac_filter.mac_hash_table);
+	enetc4_pf_clear_maft_entries(pf);
+
+	if (!enetc4_pf_add_maft_entries(pf, mac_tbl, i))
+		enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+
+	kfree(mac_tbl);
+
+	return 0;
+
+unlock_netif_addr:
+	netif_addr_unlock_bh(ndev);
+
+	return err;
+}
+
+static void enetc4_pf_set_mac_hash_filter(struct enetc_pf *pf, int type)
+{
+	struct net_device *ndev = pf->si->ndev;
+	struct enetc_mac_filter *mac_filter;
+	struct enetc_hw *hw = &pf->si->hw;
+	struct netdev_hw_addr *ha;
+
+	netif_addr_lock_bh(ndev);
+	if (type & ENETC_MAC_FILTER_TYPE_UC) {
+		mac_filter = &pf->mac_filter[UC];
+		enetc_reset_mac_addr_filter(mac_filter);
+		netdev_for_each_uc_addr(ha, ndev)
+			enetc_add_mac_addr_ht_filter(mac_filter, ha->addr);
+
+		enetc4_pf_set_si_uc_hash_filter(hw, 0,
+						*mac_filter->mac_hash_table);
+	}
+
+	if (type & ENETC_MAC_FILTER_TYPE_MC) {
+		mac_filter = &pf->mac_filter[MC];
+		enetc_reset_mac_addr_filter(mac_filter);
+		netdev_for_each_mc_addr(ha, ndev)
+			enetc_add_mac_addr_ht_filter(mac_filter, ha->addr);
+
+		enetc4_pf_set_si_mc_hash_filter(hw, 0,
+						*mac_filter->mac_hash_table);
+	}
+	netif_addr_unlock_bh(ndev);
+}
+
+static void enetc4_pf_set_mac_filter(struct enetc_pf *pf, int type)
+{
+	/* Currently, the MAC address filter table (MAFT) only has 4 entries,
+	 * and multiple multicast addresses for filtering will be configured
+	 * in the default network configuration, so MAFT is only suitable for
+	 * unicast filtering. If the number of unicast addresses exceeds the
+	 * table capacity, the MAC hash filter will be used.
+	 */
+	if (type & ENETC_MAC_FILTER_TYPE_UC && enetc4_pf_set_uc_exact_filter(pf)) {
+		/* Fall back to the MAC hash filter */
+		enetc4_pf_set_mac_hash_filter(pf, ENETC_MAC_FILTER_TYPE_UC);
+		/* Clear the old MAC exact filter */
+		enetc4_pf_clear_maft_entries(pf);
+	}
+
+	if (type & ENETC_MAC_FILTER_TYPE_MC)
+		enetc4_pf_set_mac_hash_filter(pf, ENETC_MAC_FILTER_TYPE_MC);
+}
+
 static const struct enetc_pf_ops enetc4_pf_ops = {
 	.set_si_primary_mac = enetc4_pf_set_si_primary_mac,
 	.get_si_primary_mac = enetc4_pf_get_si_primary_mac,
@@ -70,6 +287,7 @@ static int enetc4_pf_struct_init(struct enetc_si *si)
 	pf->ops = &enetc4_pf_ops;
 
 	enetc4_get_port_caps(pf);
+	enetc4_get_psi_hw_features(si);
 
 	return 0;
 }
@@ -226,24 +444,6 @@ static void enetc4_set_trx_frame_size(struct enetc_pf *pf)
 	enetc4_pf_reset_tc_msdu(&si->hw);
 }
 
-static void enetc4_set_rss_key(struct enetc_hw *hw, const u8 *bytes)
-{
-	int i;
-
-	for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
-		enetc_port_wr(hw, ENETC4_PRSSKR(i), ((u32 *)bytes)[i]);
-}
-
-static void enetc4_set_default_rss_key(struct enetc_pf *pf)
-{
-	u8 hash_key[ENETC_RSSHASH_KEY_SIZE] = {0};
-	struct enetc_hw *hw = &pf->si->hw;
-
-	/* set up hash key */
-	get_random_bytes(hash_key, ENETC_RSSHASH_KEY_SIZE);
-	enetc4_set_rss_key(hw, hash_key);
-}
-
 static void enetc4_enable_trx(struct enetc_pf *pf)
 {
 	struct enetc_hw *hw = &pf->si->hw;
@@ -256,10 +456,25 @@ static void enetc4_configure_port(struct enetc_pf *pf)
 {
 	enetc4_configure_port_si(pf);
 	enetc4_set_trx_frame_size(pf);
-	enetc4_set_default_rss_key(pf);
+	enetc_set_default_rss_key(pf);
 	enetc4_enable_trx(pf);
 }
 
+static int enetc4_init_ntmp_user(struct enetc_si *si)
+{
+	struct ntmp_user *user = &si->ntmp_user;
+
+	/* For ENETC 4.1, all table versions are 0 */
+	memset(&user->tbl, 0, sizeof(user->tbl));
+
+	return enetc4_setup_cbdr(si);
+}
+
+static void enetc4_free_ntmp_user(struct enetc_si *si)
+{
+	enetc4_teardown_cbdr(si);
+}
+
 static int enetc4_pf_init(struct enetc_pf *pf)
 {
 	struct device *dev = &pf->si->pdev->dev;
@@ -272,17 +487,102 @@ static int enetc4_pf_init(struct enetc_pf *pf)
 		return err;
 	}
 
+	err = enetc4_init_ntmp_user(pf->si);
+	if (err) {
+		dev_err(dev, "Failed to init CBDR\n");
+		return err;
+	}
+
 	enetc4_configure_port(pf);
 
 	return 0;
 }
 
+static void enetc4_pf_free(struct enetc_pf *pf)
+{
+	enetc4_free_ntmp_user(pf->si);
+}
+
+static void enetc4_psi_do_set_rx_mode(struct work_struct *work)
+{
+	struct enetc_si *si = container_of(work, struct enetc_si, rx_mode_task);
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct net_device *ndev = si->ndev;
+	struct enetc_hw *hw = &si->hw;
+	bool uc_promisc = false;
+	bool mc_promisc = false;
+	int type = 0;
+
+	rtnl_lock();
+
+	if (ndev->flags & IFF_PROMISC) {
+		uc_promisc = true;
+		mc_promisc = true;
+	} else if (ndev->flags & IFF_ALLMULTI) {
+		mc_promisc = true;
+		type = ENETC_MAC_FILTER_TYPE_UC;
+	} else {
+		type = ENETC_MAC_FILTER_TYPE_ALL;
+	}
+
+	enetc4_pf_set_si_mac_promisc(hw, 0, uc_promisc, mc_promisc);
+
+	if (uc_promisc) {
+		enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+		enetc4_pf_clear_maft_entries(pf);
+	}
+
+	if (mc_promisc)
+		enetc4_pf_set_si_mc_hash_filter(hw, 0, 0);
+
+	/* Set new MAC filter */
+	enetc4_pf_set_mac_filter(pf, type);
+
+	rtnl_unlock();
+}
+
+static void enetc4_pf_set_rx_mode(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_si *si = priv->si;
+
+	queue_work(si->workqueue, &si->rx_mode_task);
+}
+
+static int enetc4_pf_set_features(struct net_device *ndev,
+				  netdev_features_t features)
+{
+	netdev_features_t changed = ndev->features ^ features;
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+
+	if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) {
+		bool promisc_en = !(features & NETIF_F_HW_VLAN_CTAG_FILTER);
+
+		enetc4_pf_set_si_vlan_promisc(hw, 0, promisc_en);
+	}
+
+	if (changed & NETIF_F_LOOPBACK)
+		enetc4_pf_set_loopback(ndev, !!(features & NETIF_F_LOOPBACK));
+
+	enetc_set_features(ndev, features);
+
+	return 0;
+}
+
 static const struct net_device_ops enetc4_ndev_ops = {
 	.ndo_open		= enetc_open,
 	.ndo_stop		= enetc_close,
 	.ndo_start_xmit		= enetc_xmit,
 	.ndo_get_stats		= enetc_get_stats,
 	.ndo_set_mac_address	= enetc_pf_set_mac_addr,
+	.ndo_set_rx_mode	= enetc4_pf_set_rx_mode,
+	.ndo_set_features	= enetc4_pf_set_features,
+	.ndo_vlan_rx_add_vid	= enetc_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= enetc_vlan_rx_del_vid,
+	.ndo_eth_ioctl		= enetc_ioctl,
+	.ndo_hwtstamp_get	= enetc_hwtstamp_get,
+	.ndo_hwtstamp_set	= enetc_hwtstamp_set,
 };
 
 static struct phylink_pcs *
@@ -300,6 +600,9 @@ static void enetc4_mac_config(struct enetc_pf *pf, unsigned int mode,
 	struct enetc_si *si = pf->si;
 	u32 val;
 
+	if (enetc_is_pseudo_mac(si))
+		return;
+
 	val = enetc_port_mac_rd(si, ENETC4_PM_IF_MODE(0));
 	val &= ~(PM_IF_MODE_IFMODE | PM_IF_MODE_ENA);
 
@@ -617,6 +920,19 @@ static void enetc4_link_deinit(struct enetc_ndev_priv *priv)
 	enetc_mdiobus_destroy(pf);
 }
 
+static int enetc4_psi_wq_task_init(struct enetc_si *si)
+{
+	char wq_name[24];
+
+	INIT_WORK(&si->rx_mode_task, enetc4_psi_do_set_rx_mode);
+	snprintf(wq_name, sizeof(wq_name), "enetc-%s", pci_name(si->pdev));
+	si->workqueue = create_singlethread_workqueue(wq_name);
+	if (!si->workqueue)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int enetc4_pf_netdev_create(struct enetc_si *si)
 {
 	struct device *dev = &si->pdev->dev;
@@ -657,6 +973,12 @@ static int enetc4_pf_netdev_create(struct enetc_si *si)
 	if (err)
 		goto err_link_init;
 
+	err = enetc4_psi_wq_task_init(si);
+	if (err) {
+		dev_err(dev, "Failed to init workqueue\n");
+		goto err_wq_init;
+	}
+
 	err = register_netdev(ndev);
 	if (err) {
 		dev_err(dev, "Failed to register netdev\n");
@@ -666,13 +988,14 @@ static int enetc4_pf_netdev_create(struct enetc_si *si)
 	return 0;
 
 err_reg_netdev:
+	destroy_workqueue(si->workqueue);
+err_wq_init:
 	enetc4_link_deinit(priv);
 err_link_init:
 	enetc_free_msix(priv);
 err_alloc_msix:
 err_config_si:
 err_clk_get:
-	mutex_destroy(&priv->mm_lock);
 	free_netdev(ndev);
 
 	return err;
@@ -684,10 +1007,18 @@ static void enetc4_pf_netdev_destroy(struct enetc_si *si)
 	struct net_device *ndev = si->ndev;
 
 	unregister_netdev(ndev);
+	cancel_work(&si->rx_mode_task);
+	destroy_workqueue(si->workqueue);
+	enetc4_link_deinit(priv);
 	enetc_free_msix(priv);
 	free_netdev(ndev);
 }
 
+static const struct enetc_si_ops enetc4_psi_ops = {
+	.get_rss_table = enetc4_get_rss_table,
+	.set_rss_table = enetc4_set_rss_table,
+};
+
 static int enetc4_pf_probe(struct pci_dev *pdev,
 			   const struct pci_device_id *ent)
 {
@@ -702,8 +1033,7 @@ static int enetc4_pf_probe(struct pci_dev *pdev,
 
 	err = devm_add_action_or_reset(dev, enetc4_pci_remove, pdev);
 	if (err)
-		return dev_err_probe(dev, err,
-				     "Add enetc4_pci_remove() action failed\n");
+		return err;
 
 	/* si is the private data. */
 	si = pci_get_drvdata(pdev);
@@ -712,10 +1042,11 @@ static int enetc4_pf_probe(struct pci_dev *pdev,
 				     "Couldn't map PF only space\n");
 
 	si->revision = enetc_get_ip_revision(&si->hw);
+	si->ops = &enetc4_psi_ops;
 	err = enetc_get_driver_data(si);
 	if (err)
 		return dev_err_probe(dev, err,
-				     "Could not get VF driver data\n");
+				     "Could not get PF driver data\n");
 
 	err = enetc4_pf_struct_init(si);
 	if (err)
@@ -728,18 +1059,33 @@ static int enetc4_pf_probe(struct pci_dev *pdev,
 
 	enetc_get_si_caps(si);
 
-	return enetc4_pf_netdev_create(si);
+	err = enetc4_pf_netdev_create(si);
+	if (err)
+		goto err_netdev_create;
+
+	enetc_create_debugfs(si);
+
+	return 0;
+
+err_netdev_create:
+	enetc4_pf_free(pf);
+
+	return err;
 }
 
 static void enetc4_pf_remove(struct pci_dev *pdev)
 {
 	struct enetc_si *si = pci_get_drvdata(pdev);
+	struct enetc_pf *pf = enetc_si_priv(si);
 
+	enetc_remove_debugfs(si);
 	enetc4_pf_netdev_destroy(si);
+	enetc4_pf_free(pf);
 }
 
 static const struct pci_device_id enetc4_pf_id_table[] = {
 	{ PCI_DEVICE(NXP_ENETC_VENDOR_ID, NXP_ENETC_PF_DEV_ID) },
+	{ PCI_DEVICE(NXP_ENETC_VENDOR_ID, NXP_ENETC_PPM_DEV_ID) },
 	{ 0, } /* End of table. */
 };
 MODULE_DEVICE_TABLE(pci, enetc4_pf_id_table);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
index 20bfdf7fb4b4..3d5f31879d5c 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
@@ -60,6 +60,44 @@ void enetc_teardown_cbdr(struct enetc_cbdr *cbdr)
 }
 EXPORT_SYMBOL_GPL(enetc_teardown_cbdr);
 
+int enetc4_setup_cbdr(struct enetc_si *si)
+{
+	struct ntmp_user *user = &si->ntmp_user;
+	struct device *dev = &si->pdev->dev;
+	struct enetc_hw *hw = &si->hw;
+	struct netc_cbdr_regs regs;
+
+	user->cbdr_num = 1;
+	user->dev = dev;
+	user->ring = devm_kcalloc(dev, user->cbdr_num,
+				  sizeof(struct netc_cbdr), GFP_KERNEL);
+	if (!user->ring)
+		return -ENOMEM;
+
+	/* set CBDR cache attributes */
+	enetc_wr(hw, ENETC_SICAR2,
+		 ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT);
+
+	regs.pir = hw->reg + ENETC_SICBDRPIR;
+	regs.cir = hw->reg + ENETC_SICBDRCIR;
+	regs.mr = hw->reg + ENETC_SICBDRMR;
+	regs.bar0 = hw->reg + ENETC_SICBDRBAR0;
+	regs.bar1 = hw->reg + ENETC_SICBDRBAR1;
+	regs.lenr = hw->reg + ENETC_SICBDRLENR;
+
+	return ntmp_init_cbdr(user->ring, dev, &regs);
+}
+EXPORT_SYMBOL_GPL(enetc4_setup_cbdr);
+
+void enetc4_teardown_cbdr(struct enetc_si *si)
+{
+	struct ntmp_user *user = &si->ntmp_user;
+
+	ntmp_free_cbdr(user->ring);
+	user->dev = NULL;
+}
+EXPORT_SYMBOL_GPL(enetc4_teardown_cbdr);
+
 static void enetc_clean_cbdr(struct enetc_cbdr *ring)
 {
 	struct enetc_cbd *dest_cbd;
@@ -256,3 +294,15 @@ int enetc_set_rss_table(struct enetc_si *si, const u32 *table, int count)
 	return enetc_cmd_rss_table(si, (u32 *)table, count, false);
 }
 EXPORT_SYMBOL_GPL(enetc_set_rss_table);
+
+int enetc4_get_rss_table(struct enetc_si *si, u32 *table, int count)
+{
+	return ntmp_rsst_query_entry(&si->ntmp_user, table, count);
+}
+EXPORT_SYMBOL_GPL(enetc4_get_rss_table);
+
+int enetc4_set_rss_table(struct enetc_si *si, const u32 *table, int count)
+{
+	return ntmp_rsst_update_entry(&si->ntmp_user, table, count);
+}
+EXPORT_SYMBOL_GPL(enetc4_set_rss_table);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index bf34b5bb1e35..fed89d4f1e1d 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -4,6 +4,9 @@
 #include <linux/ethtool_netlink.h>
 #include <linux/net_tstamp.h>
 #include <linux/module.h>
+#include <linux/of.h>
+#include <linux/ptp_clock_kernel.h>
+
 #include "enetc.h"
 
 static const u32 enetc_si_regs[] = {
@@ -141,8 +144,8 @@ static const struct {
 
 static const struct {
 	int reg;
-	char name[ETH_GSTRING_LEN];
-} enetc_port_counters[] = {
+	char name[ETH_GSTRING_LEN] __nonstring;
+} enetc_pm_counters[] = {
 	{ ENETC_PM_REOCT(0),	"MAC rx ethernet octets" },
 	{ ENETC_PM_RALN(0),	"MAC rx alignment errors" },
 	{ ENETC_PM_RXPF(0),	"MAC rx valid pause frames" },
@@ -194,6 +197,12 @@ static const struct {
 	{ ENETC_PM_TSCOL(0),	"MAC tx single collisions" },
 	{ ENETC_PM_TLCOL(0),	"MAC tx late collisions" },
 	{ ENETC_PM_TECOL(0),	"MAC tx excessive collisions" },
+};
+
+static const struct {
+	int reg;
+	char name[ETH_GSTRING_LEN] __nonstring;
+} enetc_port_counters[] = {
 	{ ENETC_UFDMF,		"SI MAC nomatch u-cast discards" },
 	{ ENETC_MFDMF,		"SI MAC nomatch m-cast discards" },
 	{ ENETC_PBFDSIR,	"SI MAC nomatch b-cast discards" },
@@ -240,6 +249,7 @@ static int enetc_get_sset_count(struct net_device *ndev, int sset)
 		return len;
 
 	len += ARRAY_SIZE(enetc_port_counters);
+	len += ARRAY_SIZE(enetc_pm_counters);
 
 	return len;
 }
@@ -264,7 +274,10 @@ static void enetc_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
 			break;
 
 		for (i = 0; i < ARRAY_SIZE(enetc_port_counters); i++)
-			ethtool_puts(&data, enetc_port_counters[i].name);
+			ethtool_cpy(&data, enetc_port_counters[i].name);
+
+		for (i = 0; i < ARRAY_SIZE(enetc_pm_counters); i++)
+			ethtool_cpy(&data, enetc_pm_counters[i].name);
 
 		break;
 	}
@@ -302,13 +315,16 @@ static void enetc_get_ethtool_stats(struct net_device *ndev,
 
 	for (i = 0; i < ARRAY_SIZE(enetc_port_counters); i++)
 		data[o++] = enetc_port_rd(hw, enetc_port_counters[i].reg);
+
+	for (i = 0; i < ARRAY_SIZE(enetc_pm_counters); i++)
+		data[o++] = enetc_port_rd64(hw, enetc_pm_counters[i].reg);
 }
 
 static void enetc_pause_stats(struct enetc_hw *hw, int mac,
 			      struct ethtool_pause_stats *pause_stats)
 {
-	pause_stats->tx_pause_frames = enetc_port_rd(hw, ENETC_PM_TXPF(mac));
-	pause_stats->rx_pause_frames = enetc_port_rd(hw, ENETC_PM_RXPF(mac));
+	pause_stats->tx_pause_frames = enetc_port_rd64(hw, ENETC_PM_TXPF(mac));
+	pause_stats->rx_pause_frames = enetc_port_rd64(hw, ENETC_PM_RXPF(mac));
 }
 
 static void enetc_get_pause_stats(struct net_device *ndev,
@@ -335,31 +351,31 @@ static void enetc_get_pause_stats(struct net_device *ndev,
 static void enetc_mac_stats(struct enetc_hw *hw, int mac,
 			    struct ethtool_eth_mac_stats *s)
 {
-	s->FramesTransmittedOK = enetc_port_rd(hw, ENETC_PM_TFRM(mac));
-	s->SingleCollisionFrames = enetc_port_rd(hw, ENETC_PM_TSCOL(mac));
-	s->MultipleCollisionFrames = enetc_port_rd(hw, ENETC_PM_TMCOL(mac));
-	s->FramesReceivedOK = enetc_port_rd(hw, ENETC_PM_RFRM(mac));
-	s->FrameCheckSequenceErrors = enetc_port_rd(hw, ENETC_PM_RFCS(mac));
-	s->AlignmentErrors = enetc_port_rd(hw, ENETC_PM_RALN(mac));
-	s->OctetsTransmittedOK = enetc_port_rd(hw, ENETC_PM_TEOCT(mac));
-	s->FramesWithDeferredXmissions = enetc_port_rd(hw, ENETC_PM_TDFR(mac));
-	s->LateCollisions = enetc_port_rd(hw, ENETC_PM_TLCOL(mac));
-	s->FramesAbortedDueToXSColls = enetc_port_rd(hw, ENETC_PM_TECOL(mac));
-	s->FramesLostDueToIntMACXmitError = enetc_port_rd(hw, ENETC_PM_TERR(mac));
-	s->CarrierSenseErrors = enetc_port_rd(hw, ENETC_PM_TCRSE(mac));
-	s->OctetsReceivedOK = enetc_port_rd(hw, ENETC_PM_REOCT(mac));
-	s->FramesLostDueToIntMACRcvError = enetc_port_rd(hw, ENETC_PM_RDRNTP(mac));
-	s->MulticastFramesXmittedOK = enetc_port_rd(hw, ENETC_PM_TMCA(mac));
-	s->BroadcastFramesXmittedOK = enetc_port_rd(hw, ENETC_PM_TBCA(mac));
-	s->MulticastFramesReceivedOK = enetc_port_rd(hw, ENETC_PM_RMCA(mac));
-	s->BroadcastFramesReceivedOK = enetc_port_rd(hw, ENETC_PM_RBCA(mac));
+	s->FramesTransmittedOK = enetc_port_rd64(hw, ENETC_PM_TFRM(mac));
+	s->SingleCollisionFrames = enetc_port_rd64(hw, ENETC_PM_TSCOL(mac));
+	s->MultipleCollisionFrames = enetc_port_rd64(hw, ENETC_PM_TMCOL(mac));
+	s->FramesReceivedOK = enetc_port_rd64(hw, ENETC_PM_RFRM(mac));
+	s->FrameCheckSequenceErrors = enetc_port_rd64(hw, ENETC_PM_RFCS(mac));
+	s->AlignmentErrors = enetc_port_rd64(hw, ENETC_PM_RALN(mac));
+	s->OctetsTransmittedOK = enetc_port_rd64(hw, ENETC_PM_TEOCT(mac));
+	s->FramesWithDeferredXmissions = enetc_port_rd64(hw, ENETC_PM_TDFR(mac));
+	s->LateCollisions = enetc_port_rd64(hw, ENETC_PM_TLCOL(mac));
+	s->FramesAbortedDueToXSColls = enetc_port_rd64(hw, ENETC_PM_TECOL(mac));
+	s->FramesLostDueToIntMACXmitError = enetc_port_rd64(hw, ENETC_PM_TERR(mac));
+	s->CarrierSenseErrors = enetc_port_rd64(hw, ENETC_PM_TCRSE(mac));
+	s->OctetsReceivedOK = enetc_port_rd64(hw, ENETC_PM_REOCT(mac));
+	s->FramesLostDueToIntMACRcvError = enetc_port_rd64(hw, ENETC_PM_RDRNTP(mac));
+	s->MulticastFramesXmittedOK = enetc_port_rd64(hw, ENETC_PM_TMCA(mac));
+	s->BroadcastFramesXmittedOK = enetc_port_rd64(hw, ENETC_PM_TBCA(mac));
+	s->MulticastFramesReceivedOK = enetc_port_rd64(hw, ENETC_PM_RMCA(mac));
+	s->BroadcastFramesReceivedOK = enetc_port_rd64(hw, ENETC_PM_RBCA(mac));
 }
 
 static void enetc_ctrl_stats(struct enetc_hw *hw, int mac,
 			     struct ethtool_eth_ctrl_stats *s)
 {
-	s->MACControlFramesTransmitted = enetc_port_rd(hw, ENETC_PM_TCNP(mac));
-	s->MACControlFramesReceived = enetc_port_rd(hw, ENETC_PM_RCNP(mac));
+	s->MACControlFramesTransmitted = enetc_port_rd64(hw, ENETC_PM_TCNP(mac));
+	s->MACControlFramesReceived = enetc_port_rd64(hw, ENETC_PM_RCNP(mac));
 }
 
 static const struct ethtool_rmon_hist_range enetc_rmon_ranges[] = {
@@ -376,26 +392,26 @@ static const struct ethtool_rmon_hist_range enetc_rmon_ranges[] = {
 static void enetc_rmon_stats(struct enetc_hw *hw, int mac,
 			     struct ethtool_rmon_stats *s)
 {
-	s->undersize_pkts = enetc_port_rd(hw, ENETC_PM_RUND(mac));
-	s->oversize_pkts = enetc_port_rd(hw, ENETC_PM_ROVR(mac));
-	s->fragments = enetc_port_rd(hw, ENETC_PM_RFRG(mac));
-	s->jabbers = enetc_port_rd(hw, ENETC_PM_RJBR(mac));
-
-	s->hist[0] = enetc_port_rd(hw, ENETC_PM_R64(mac));
-	s->hist[1] = enetc_port_rd(hw, ENETC_PM_R127(mac));
-	s->hist[2] = enetc_port_rd(hw, ENETC_PM_R255(mac));
-	s->hist[3] = enetc_port_rd(hw, ENETC_PM_R511(mac));
-	s->hist[4] = enetc_port_rd(hw, ENETC_PM_R1023(mac));
-	s->hist[5] = enetc_port_rd(hw, ENETC_PM_R1522(mac));
-	s->hist[6] = enetc_port_rd(hw, ENETC_PM_R1523X(mac));
-
-	s->hist_tx[0] = enetc_port_rd(hw, ENETC_PM_T64(mac));
-	s->hist_tx[1] = enetc_port_rd(hw, ENETC_PM_T127(mac));
-	s->hist_tx[2] = enetc_port_rd(hw, ENETC_PM_T255(mac));
-	s->hist_tx[3] = enetc_port_rd(hw, ENETC_PM_T511(mac));
-	s->hist_tx[4] = enetc_port_rd(hw, ENETC_PM_T1023(mac));
-	s->hist_tx[5] = enetc_port_rd(hw, ENETC_PM_T1522(mac));
-	s->hist_tx[6] = enetc_port_rd(hw, ENETC_PM_T1523X(mac));
+	s->undersize_pkts = enetc_port_rd64(hw, ENETC_PM_RUND(mac));
+	s->oversize_pkts = enetc_port_rd64(hw, ENETC_PM_ROVR(mac));
+	s->fragments = enetc_port_rd64(hw, ENETC_PM_RFRG(mac));
+	s->jabbers = enetc_port_rd64(hw, ENETC_PM_RJBR(mac));
+
+	s->hist[0] = enetc_port_rd64(hw, ENETC_PM_R64(mac));
+	s->hist[1] = enetc_port_rd64(hw, ENETC_PM_R127(mac));
+	s->hist[2] = enetc_port_rd64(hw, ENETC_PM_R255(mac));
+	s->hist[3] = enetc_port_rd64(hw, ENETC_PM_R511(mac));
+	s->hist[4] = enetc_port_rd64(hw, ENETC_PM_R1023(mac));
+	s->hist[5] = enetc_port_rd64(hw, ENETC_PM_R1522(mac));
+	s->hist[6] = enetc_port_rd64(hw, ENETC_PM_R1523X(mac));
+
+	s->hist_tx[0] = enetc_port_rd64(hw, ENETC_PM_T64(mac));
+	s->hist_tx[1] = enetc_port_rd64(hw, ENETC_PM_T127(mac));
+	s->hist_tx[2] = enetc_port_rd64(hw, ENETC_PM_T255(mac));
+	s->hist_tx[3] = enetc_port_rd64(hw, ENETC_PM_T511(mac));
+	s->hist_tx[4] = enetc_port_rd64(hw, ENETC_PM_T1023(mac));
+	s->hist_tx[5] = enetc_port_rd64(hw, ENETC_PM_T1522(mac));
+	s->hist_tx[6] = enetc_port_rd64(hw, ENETC_PM_T1523X(mac));
 }
 
 static void enetc_get_eth_mac_stats(struct net_device *ndev,
@@ -419,6 +435,48 @@ static void enetc_get_eth_mac_stats(struct net_device *ndev,
 	}
 }
 
+static void enetc_ppm_mac_stats(struct enetc_si *si,
+				struct ethtool_eth_mac_stats *s)
+{
+	struct enetc_hw *hw = &si->hw;
+	u64 rufcr, rmfcr, rbfcr;
+	u64 tufcr, tmfcr, tbfcr;
+
+	rufcr = enetc_port_rd64(hw, ENETC4_PPMRUFCR);
+	rmfcr = enetc_port_rd64(hw, ENETC4_PPMRMFCR);
+	rbfcr = enetc_port_rd64(hw, ENETC4_PPMRBFCR);
+
+	tufcr = enetc_port_rd64(hw, ENETC4_PPMTUFCR);
+	tmfcr = enetc_port_rd64(hw, ENETC4_PPMTMFCR);
+	tbfcr = enetc_port_rd64(hw, ENETC4_PPMTBFCR);
+
+	s->FramesTransmittedOK = tufcr + tmfcr + tbfcr;
+	s->FramesReceivedOK = rufcr + rmfcr + rbfcr;
+	s->OctetsTransmittedOK = enetc_port_rd64(hw, ENETC4_PPMTOCR);
+	s->OctetsReceivedOK = enetc_port_rd64(hw, ENETC4_PPMROCR);
+	s->MulticastFramesXmittedOK = tmfcr;
+	s->BroadcastFramesXmittedOK = tbfcr;
+	s->MulticastFramesReceivedOK = rmfcr;
+	s->BroadcastFramesReceivedOK = rbfcr;
+}
+
+static void enetc_ppm_get_eth_mac_stats(struct net_device *ndev,
+					struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	switch (mac_stats->src) {
+	case ETHTOOL_MAC_STATS_SRC_EMAC:
+		enetc_ppm_mac_stats(priv->si, mac_stats);
+		break;
+	case ETHTOOL_MAC_STATS_SRC_PMAC:
+		break;
+	case ETHTOOL_MAC_STATS_SRC_AGGREGATE:
+		ethtool_aggregate_mac_stats(ndev, mac_stats);
+		break;
+	}
+}
+
 static void enetc_get_eth_ctrl_stats(struct net_device *ndev,
 				     struct ethtool_eth_ctrl_stats *ctrl_stats)
 {
@@ -467,7 +525,8 @@ static void enetc_get_rmon_stats(struct net_device *ndev,
 #define ENETC_RSSHASH_L3 (RXH_L2DA | RXH_VLAN | RXH_L3_PROTO | RXH_IP_SRC | \
 			  RXH_IP_DST)
 #define ENETC_RSSHASH_L4 (ENETC_RSSHASH_L3 | RXH_L4_B_0_1 | RXH_L4_B_2_3)
-static int enetc_get_rsshash(struct ethtool_rxnfc *rxnfc)
+static int enetc_get_rxfh_fields(struct net_device *netdev,
+				 struct ethtool_rxfh_fields *rxnfc)
 {
 	static const u32 rsshash[] = {
 			[TCP_V4_FLOW]    = ENETC_RSSHASH_L4,
@@ -574,6 +633,13 @@ done:
 	return enetc_set_fs_entry(si, &rfse, fs->location);
 }
 
+static u32 enetc_get_rx_ring_count(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	return priv->num_rx_rings;
+}
+
 static int enetc_get_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc,
 			   u32 *rule_locs)
 {
@@ -581,12 +647,6 @@ static int enetc_get_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc,
 	int i, j;
 
 	switch (rxnfc->cmd) {
-	case ETHTOOL_GRXRINGS:
-		rxnfc->data = priv->num_rx_rings;
-		break;
-	case ETHTOOL_GRXFH:
-		/* get RSS hash config */
-		return enetc_get_rsshash(rxnfc);
 	case ETHTOOL_GRXCLSRLCNT:
 		/* total number of entries */
 		rxnfc->data = priv->si->num_fs_entries;
@@ -677,36 +737,53 @@ static u32 enetc_get_rxfh_indir_size(struct net_device *ndev)
 	return priv->si->num_rss;
 }
 
+static int enetc_get_rss_key_base(struct enetc_si *si)
+{
+	if (is_enetc_rev1(si))
+		return ENETC_PRSSK(0);
+
+	return ENETC4_PRSSKR(0);
+}
+
+static void enetc_get_rss_key(struct enetc_si *si, const u8 *key)
+{
+	int base = enetc_get_rss_key_base(si);
+	struct enetc_hw *hw = &si->hw;
+	int i;
+
+	for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
+		((u32 *)key)[i] = enetc_port_rd(hw, base + i * 4);
+}
+
 static int enetc_get_rxfh(struct net_device *ndev,
 			  struct ethtool_rxfh_param *rxfh)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_hw *hw = &priv->si->hw;
-	int err = 0, i;
+	struct enetc_si *si = priv->si;
+	int err = 0;
 
 	/* return hash function */
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	/* return hash key */
-	if (rxfh->key && hw->port)
-		for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
-			((u32 *)rxfh->key)[i] = enetc_port_rd(hw,
-							      ENETC_PRSSK(i));
+	if (rxfh->key && enetc_si_is_pf(si))
+		enetc_get_rss_key(si, rxfh->key);
 
 	/* return RSS table */
 	if (rxfh->indir)
-		err = enetc_get_rss_table(priv->si, rxfh->indir,
-					  priv->si->num_rss);
+		err = si->ops->get_rss_table(si, rxfh->indir, si->num_rss);
 
 	return err;
 }
 
-void enetc_set_rss_key(struct enetc_hw *hw, const u8 *bytes)
+void enetc_set_rss_key(struct enetc_si *si, const u8 *bytes)
 {
+	int base = enetc_get_rss_key_base(si);
+	struct enetc_hw *hw = &si->hw;
 	int i;
 
 	for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
-		enetc_port_wr(hw, ENETC_PRSSK(i), ((u32 *)bytes)[i]);
+		enetc_port_wr(hw, base + i * 4, ((u32 *)bytes)[i]);
 }
 EXPORT_SYMBOL_GPL(enetc_set_rss_key);
 
@@ -715,17 +792,16 @@ static int enetc_set_rxfh(struct net_device *ndev,
 			  struct netlink_ext_ack *extack)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_hw *hw = &priv->si->hw;
+	struct enetc_si *si = priv->si;
 	int err = 0;
 
 	/* set hash key, if PF */
-	if (rxfh->key && hw->port)
-		enetc_set_rss_key(hw, rxfh->key);
+	if (rxfh->key && enetc_si_is_pf(si))
+		enetc_set_rss_key(si, rxfh->key);
 
 	/* set RSS table */
 	if (rxfh->indir)
-		err = enetc_set_rss_table(priv->si, rxfh->indir,
-					  priv->si->num_rss);
+		err = si->ops->set_rss_table(si, rxfh->indir, si->num_rss);
 
 	return err;
 }
@@ -829,22 +905,61 @@ static int enetc_set_coalesce(struct net_device *ndev,
 	return 0;
 }
 
-static int enetc_get_ts_info(struct net_device *ndev,
-			     struct kernel_ethtool_ts_info *info)
+static int enetc_get_phc_index_by_pdev(struct enetc_si *si)
 {
-	int *phc_idx;
-
-	phc_idx = symbol_get(enetc_phc_index);
-	if (phc_idx) {
-		info->phc_index = *phc_idx;
-		symbol_put(enetc_phc_index);
+	struct pci_bus *bus = si->pdev->bus;
+	struct pci_dev *timer_pdev;
+	unsigned int devfn;
+	int phc_index;
+
+	switch (si->revision) {
+	case ENETC_REV_1_0:
+		devfn = PCI_DEVFN(0, 4);
+		break;
+	case ENETC_REV_4_1:
+		devfn = PCI_DEVFN(24, 0);
+		break;
+	case ENETC_REV_4_3:
+		devfn = PCI_DEVFN(0, 1);
+		break;
+	default:
+		return -1;
 	}
 
-	if (!IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK)) {
-		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE;
+	timer_pdev = pci_get_domain_bus_and_slot(pci_domain_nr(bus),
+						 bus->number, devfn);
+	if (!timer_pdev)
+		return -1;
 
-		return 0;
-	}
+	phc_index = ptp_clock_index_by_dev(&timer_pdev->dev);
+	pci_dev_put(timer_pdev);
+
+	return phc_index;
+}
+
+static int enetc_get_phc_index(struct enetc_si *si)
+{
+	struct device_node *np = si->pdev->dev.of_node;
+	struct device_node *timer_np;
+	int phc_index;
+
+	if (!np)
+		return enetc_get_phc_index_by_pdev(si);
+
+	timer_np = of_parse_phandle(np, "ptp-timer", 0);
+	if (!timer_np)
+		return enetc_get_phc_index_by_pdev(si);
+
+	phc_index = ptp_clock_index_by_of_node(timer_np);
+	of_node_put(timer_np);
+
+	return phc_index;
+}
+
+static void enetc_get_ts_generic_info(struct net_device *ndev,
+				      struct kernel_ethtool_ts_info *info)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
@@ -852,11 +967,34 @@ static int enetc_get_ts_info(struct net_device *ndev,
 				SOF_TIMESTAMPING_TX_SOFTWARE;
 
 	info->tx_types = (1 << HWTSTAMP_TX_OFF) |
-			 (1 << HWTSTAMP_TX_ON) |
-			 (1 << HWTSTAMP_TX_ONESTEP_SYNC);
+			 (1 << HWTSTAMP_TX_ON);
+
+	if (enetc_si_is_pf(priv->si))
+		info->tx_types |= (1 << HWTSTAMP_TX_ONESTEP_SYNC);
 
 	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
 			   (1 << HWTSTAMP_FILTER_ALL);
+}
+
+static int enetc_get_ts_info(struct net_device *ndev,
+			     struct kernel_ethtool_ts_info *info)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_si *si = priv->si;
+
+	if (!enetc_ptp_clock_is_enabled(si))
+		goto timestamp_tx_sw;
+
+	info->phc_index = enetc_get_phc_index(si);
+	if (info->phc_index < 0)
+		goto timestamp_tx_sw;
+
+	enetc_get_ts_generic_info(ndev, info);
+
+	return 0;
+
+timestamp_tx_sw:
+	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE;
 
 	return 0;
 }
@@ -1180,12 +1318,14 @@ const struct ethtool_ops enetc_pf_ethtool_ops = {
 	.get_rmon_stats = enetc_get_rmon_stats,
 	.get_eth_ctrl_stats = enetc_get_eth_ctrl_stats,
 	.get_eth_mac_stats = enetc_get_eth_mac_stats,
+	.get_rx_ring_count = enetc_get_rx_ring_count,
 	.get_rxnfc = enetc_get_rxnfc,
 	.set_rxnfc = enetc_set_rxnfc,
 	.get_rxfh_key_size = enetc_get_rxfh_key_size,
 	.get_rxfh_indir_size = enetc_get_rxfh_indir_size,
 	.get_rxfh = enetc_get_rxfh,
 	.set_rxfh = enetc_set_rxfh,
+	.get_rxfh_fields = enetc_get_rxfh_fields,
 	.get_ringparam = enetc_get_ringparam,
 	.get_coalesce = enetc_get_coalesce,
 	.set_coalesce = enetc_set_coalesce,
@@ -1202,6 +1342,25 @@ const struct ethtool_ops enetc_pf_ethtool_ops = {
 	.get_mm_stats = enetc_get_mm_stats,
 };
 
+const struct ethtool_ops enetc4_ppm_ethtool_ops = {
+	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
+				     ETHTOOL_COALESCE_MAX_FRAMES |
+				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
+	.get_eth_mac_stats = enetc_ppm_get_eth_mac_stats,
+	.get_rx_ring_count = enetc_get_rx_ring_count,
+	.get_rxfh_key_size = enetc_get_rxfh_key_size,
+	.get_rxfh_indir_size = enetc_get_rxfh_indir_size,
+	.get_rxfh = enetc_get_rxfh,
+	.set_rxfh = enetc_set_rxfh,
+	.get_rxfh_fields = enetc_get_rxfh_fields,
+	.get_ringparam = enetc_get_ringparam,
+	.get_coalesce = enetc_get_coalesce,
+	.set_coalesce = enetc_set_coalesce,
+	.get_link_ksettings = enetc_get_link_ksettings,
+	.set_link_ksettings = enetc_set_link_ksettings,
+	.get_link = ethtool_op_get_link,
+};
+
 const struct ethtool_ops enetc_vf_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
@@ -1211,11 +1370,13 @@ const struct ethtool_ops enetc_vf_ethtool_ops = {
 	.get_sset_count = enetc_get_sset_count,
 	.get_strings = enetc_get_strings,
 	.get_ethtool_stats = enetc_get_ethtool_stats,
+	.get_rx_ring_count = enetc_get_rx_ring_count,
 	.get_rxnfc = enetc_get_rxnfc,
 	.set_rxnfc = enetc_set_rxnfc,
 	.get_rxfh_indir_size = enetc_get_rxfh_indir_size,
 	.get_rxfh = enetc_get_rxfh,
 	.set_rxfh = enetc_set_rxfh,
+	.get_rxfh_fields = enetc_get_rxfh_fields,
 	.get_ringparam = enetc_get_ringparam,
 	.get_coalesce = enetc_get_coalesce,
 	.set_coalesce = enetc_set_coalesce,
@@ -1237,6 +1398,13 @@ const struct ethtool_ops enetc4_pf_ethtool_ops = {
 	.set_wol = enetc_set_wol,
 	.get_pauseparam = enetc_get_pauseparam,
 	.set_pauseparam = enetc_set_pauseparam,
+	.get_rx_ring_count = enetc_get_rx_ring_count,
+	.get_rxfh_key_size = enetc_get_rxfh_key_size,
+	.get_rxfh_indir_size = enetc_get_rxfh_indir_size,
+	.get_rxfh = enetc_get_rxfh,
+	.set_rxfh = enetc_set_rxfh,
+	.get_rxfh_fields = enetc_get_rxfh_fields,
+	.get_ts_info = enetc_get_ts_info,
 };
 
 void enetc_set_ethtool_ops(struct net_device *ndev)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 4098f01479bc..7b882b8921fe 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -43,6 +43,9 @@
 
 #define ENETC_SIPMAR0	0x80
 #define ENETC_SIPMAR1	0x84
+#define ENETC_SICVLANR1	0x90
+#define ENETC_SICVLANR2	0x94
+#define  SICVLANR_ETYPE	GENMASK(15, 0)
 
 /* VF-PF Message passing */
 #define ENETC_DEFAULT_MSG_SIZE	1024	/* and max size */
@@ -375,6 +378,7 @@ enum enetc_bdr_type {TX, RX};
 #define EIPBRR0_REVISION	GENMASK(15, 0)
 #define ENETC_REV_1_0		0x0100
 #define ENETC_REV_4_1		0X0401
+#define ENETC_REV_4_3		0x0403
 
 #define ENETC_G_EIPBRR1		0x0bfc
 #define ENETC_G_EPFBLPR(n)	(0xd00 + 4 * (n))
@@ -507,7 +511,7 @@ static inline u64 _enetc_rd_reg64(void __iomem *reg)
 		tmp = ioread32(reg + 4);
 	} while (high != tmp);
 
-	return le64_to_cpu((__le64)high << 32 | low);
+	return (u64)high << 32 | low;
 }
 #endif
 
@@ -533,6 +537,7 @@ static inline u64 _enetc_rd_reg64_wa(void __iomem *reg)
 /* port register accessors - PF only */
 #define enetc_port_rd(hw, off)		enetc_rd_reg((hw)->port + (off))
 #define enetc_port_wr(hw, off, val)	enetc_wr_reg((hw)->port + (off), val)
+#define enetc_port_rd64(hw, off)	_enetc_rd_reg64_wa((hw)->port + (off))
 #define enetc_port_rd_mdio(hw, off)	_enetc_rd_mdio_reg_wa((hw)->port + (off))
 #define enetc_port_wr_mdio(hw, off, val)	_enetc_wr_mdio_reg_wa(\
 							(hw)->port + (off), val)
@@ -610,6 +615,7 @@ enum enetc_txbd_flags {
 #define ENETC_TXBD_STATS_WIN	BIT(7)
 #define ENETC_TXBD_TXSTART_MASK GENMASK(24, 0)
 #define ENETC_TXBD_FLAGS_OFFSET 24
+#define ENETC_TXBD_TSTAMP	GENMASK(29, 0)
 
 static inline __le32 enetc_txbd_set_tx_start(u64 tx_start, u8 flags)
 {
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 203862ec1114..de0fb272c847 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -72,30 +72,6 @@ static void enetc_set_isol_vlan(struct enetc_hw *hw, int si, u16 vlan, u8 qos)
 	enetc_port_wr(hw, ENETC_PSIVLANR(si), val);
 }
 
-static int enetc_mac_addr_hash_idx(const u8 *addr)
-{
-	u64 fold = __swab64(ether_addr_to_u64(addr)) >> 16;
-	u64 mask = 0;
-	int res = 0;
-	int i;
-
-	for (i = 0; i < 8; i++)
-		mask |= BIT_ULL(i * 6);
-
-	for (i = 0; i < 6; i++)
-		res |= (hweight64(fold & (mask << i)) & 0x1) << i;
-
-	return res;
-}
-
-static void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter)
-{
-	filter->mac_addr_cnt = 0;
-
-	bitmap_zero(filter->mac_hash_table,
-		    ENETC_MADDR_HASH_TBL_SZ);
-}
-
 static void enetc_add_mac_addr_em_filter(struct enetc_mac_filter *filter,
 					 const unsigned char *addr)
 {
@@ -104,16 +80,6 @@ static void enetc_add_mac_addr_em_filter(struct enetc_mac_filter *filter,
 	filter->mac_addr_cnt++;
 }
 
-static void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
-					 const unsigned char *addr)
-{
-	int idx = enetc_mac_addr_hash_idx(addr);
-
-	/* add hash table entry */
-	__set_bit(idx, filter->mac_hash_table);
-	filter->mac_addr_cnt++;
-}
-
 static void enetc_clear_mac_ht_flt(struct enetc_si *si, int si_idx, int type)
 {
 	bool err = si->errata & ENETC_ERR_UCMCSWP;
@@ -250,67 +216,6 @@ static void enetc_pf_set_rx_mode(struct net_device *ndev)
 	enetc_port_wr(hw, ENETC_PSIPMR, psipmr);
 }
 
-static void enetc_set_vlan_ht_filter(struct enetc_hw *hw, int si_idx,
-				     unsigned long hash)
-{
-	enetc_port_wr(hw, ENETC_PSIVHFR0(si_idx), lower_32_bits(hash));
-	enetc_port_wr(hw, ENETC_PSIVHFR1(si_idx), upper_32_bits(hash));
-}
-
-static int enetc_vid_hash_idx(unsigned int vid)
-{
-	int res = 0;
-	int i;
-
-	for (i = 0; i < 6; i++)
-		res |= (hweight8(vid & (BIT(i) | BIT(i + 6))) & 0x1) << i;
-
-	return res;
-}
-
-static void enetc_sync_vlan_ht_filter(struct enetc_pf *pf, bool rehash)
-{
-	int i;
-
-	if (rehash) {
-		bitmap_zero(pf->vlan_ht_filter, ENETC_VLAN_HT_SIZE);
-
-		for_each_set_bit(i, pf->active_vlans, VLAN_N_VID) {
-			int hidx = enetc_vid_hash_idx(i);
-
-			__set_bit(hidx, pf->vlan_ht_filter);
-		}
-	}
-
-	enetc_set_vlan_ht_filter(&pf->si->hw, 0, *pf->vlan_ht_filter);
-}
-
-static int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid)
-{
-	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_pf *pf = enetc_si_priv(priv->si);
-	int idx;
-
-	__set_bit(vid, pf->active_vlans);
-
-	idx = enetc_vid_hash_idx(vid);
-	if (!__test_and_set_bit(idx, pf->vlan_ht_filter))
-		enetc_sync_vlan_ht_filter(pf, false);
-
-	return 0;
-}
-
-static int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid)
-{
-	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_pf *pf = enetc_si_priv(priv->si);
-
-	__clear_bit(vid, pf->active_vlans);
-	enetc_sync_vlan_ht_filter(pf, true);
-
-	return 0;
-}
-
 static void enetc_set_loopback(struct net_device *ndev, bool en)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
@@ -549,7 +454,6 @@ static void enetc_mac_enable(struct enetc_si *si, bool en)
 
 static void enetc_configure_port(struct enetc_pf *pf)
 {
-	u8 hash_key[ENETC_RSSHASH_KEY_SIZE];
 	struct enetc_hw *hw = &pf->si->hw;
 
 	enetc_configure_port_mac(pf->si);
@@ -557,8 +461,7 @@ static void enetc_configure_port(struct enetc_pf *pf)
 	enetc_port_si_configure(pf->si);
 
 	/* set up hash key */
-	get_random_bytes(hash_key, ENETC_RSSHASH_KEY_SIZE);
-	enetc_set_rss_key(hw, hash_key);
+	enetc_set_default_rss_key(pf);
 
 	/* split up RFS entries */
 	enetc_port_assign_rfs_entries(pf->si);
@@ -728,6 +631,8 @@ static const struct net_device_ops enetc_ndev_ops = {
 	.ndo_setup_tc		= enetc_pf_setup_tc,
 	.ndo_bpf		= enetc_setup_bpf,
 	.ndo_xdp_xmit		= enetc_xdp_xmit,
+	.ndo_hwtstamp_get	= enetc_hwtstamp_get,
+	.ndo_hwtstamp_set	= enetc_hwtstamp_set,
 };
 
 static struct phylink_pcs *
@@ -924,21 +829,36 @@ static int enetc_pf_register_with_ierb(struct pci_dev *pdev)
 {
 	struct platform_device *ierb_pdev;
 	struct device_node *ierb_node;
+	int ret;
 
 	ierb_node = of_find_compatible_node(NULL, NULL,
 					    "fsl,ls1028a-enetc-ierb");
-	if (!ierb_node || !of_device_is_available(ierb_node))
+	if (!ierb_node)
 		return -ENODEV;
 
+	if (!of_device_is_available(ierb_node)) {
+		of_node_put(ierb_node);
+		return -ENODEV;
+	}
+
 	ierb_pdev = of_find_device_by_node(ierb_node);
 	of_node_put(ierb_node);
 
 	if (!ierb_pdev)
 		return -EPROBE_DEFER;
 
-	return enetc_ierb_register_pf(ierb_pdev, pdev);
+	ret = enetc_ierb_register_pf(ierb_pdev, pdev);
+
+	put_device(&ierb_pdev->dev);
+
+	return ret;
 }
 
+static const struct enetc_si_ops enetc_psi_ops = {
+	.get_rss_table = enetc_get_rss_table,
+	.set_rss_table = enetc_set_rss_table,
+};
+
 static struct enetc_si *enetc_psi_create(struct pci_dev *pdev)
 {
 	struct enetc_si *si;
@@ -958,6 +878,7 @@ static struct enetc_si *enetc_psi_create(struct pci_dev *pdev)
 	}
 
 	si->revision = enetc_get_ip_revision(&si->hw);
+	si->ops = &enetc_psi_ops;
 	err = enetc_get_driver_data(si);
 	if (err) {
 		dev_err(&pdev->dev, "Could not get PF driver data\n");
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
index a26a12863855..ae407e9e9ee7 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
@@ -5,19 +5,8 @@
 #include <linux/phylink.h>
 
 #define ENETC_PF_NUM_RINGS	8
-
-enum enetc_mac_addr_type {UC, MC, MADDR_TYPE};
 #define ENETC_MAX_NUM_MAC_FLT	((ENETC_MAX_NUM_VFS + 1) * MADDR_TYPE)
 
-#define ENETC_MADDR_HASH_TBL_SZ	64
-struct enetc_mac_filter {
-	union {
-		char mac_addr[ETH_ALEN];
-		DECLARE_BITMAP(mac_hash_table, ENETC_MADDR_HASH_TBL_SZ);
-	};
-	int mac_addr_cnt;
-};
-
 #define ENETC_VLAN_HT_SIZE	64
 
 enum enetc_vf_flags {
@@ -34,6 +23,7 @@ struct enetc_port_caps {
 	int num_msix;
 	int num_rx_bdr;
 	int num_tx_bdr;
+	int mac_filter_num;
 };
 
 struct enetc_pf;
@@ -71,6 +61,8 @@ struct enetc_pf {
 
 	struct enetc_port_caps caps;
 	const struct enetc_pf_ops *ops;
+
+	int num_mfe;	/* number of mac address filter table entries */
 };
 
 #define phylink_to_enetc_pf(config) \
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index 3fd9b0727875..76263b8566bb 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
@@ -109,7 +109,7 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 
 	ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
 			    NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
-			    NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK |
+			    NETIF_F_HW_VLAN_CTAG_FILTER |
 			    NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 |
 			    NETIF_F_GSO_UDP_L4;
 	ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM |
@@ -128,14 +128,17 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 	if (si->hw_features & ENETC_SI_F_LSO)
 		priv->active_offloads |= ENETC_F_LSO;
 
-	/* TODO: currently, i.MX95 ENETC driver does not support advanced features */
-	if (!is_enetc_rev1(si)) {
-		ndev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK);
-		goto end;
+	if (si->num_rss) {
+		ndev->hw_features |= NETIF_F_RXHASH;
+		ndev->features |= NETIF_F_RXHASH;
 	}
 
-	if (si->num_rss)
-		ndev->hw_features |= NETIF_F_RXHASH;
+	if (!enetc_is_pseudo_mac(si))
+		ndev->hw_features |= NETIF_F_LOOPBACK;
+
+	/* TODO: currently, i.MX95 ENETC driver does not support advanced features */
+	if (!is_enetc_rev1(si))
+		goto end;
 
 	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
 			     NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
@@ -173,7 +176,12 @@ static int enetc_mdio_probe(struct enetc_pf *pf, struct device_node *np)
 	bus->parent = dev;
 	mdio_priv = bus->priv;
 	mdio_priv->hw = &pf->si->hw;
-	mdio_priv->mdio_base = ENETC_EMDIO_BASE;
+
+	if (is_enetc_rev1(pf->si))
+		mdio_priv->mdio_base = ENETC_EMDIO_BASE;
+	else
+		mdio_priv->mdio_base = ENETC4_EMDIO_BASE;
+
 	snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev));
 
 	err = of_mdiobus_register(bus, np);
@@ -218,7 +226,12 @@ static int enetc_imdio_create(struct enetc_pf *pf)
 	bus->phy_mask = ~0;
 	mdio_priv = bus->priv;
 	mdio_priv->hw = &pf->si->hw;
-	mdio_priv->mdio_base = ENETC_PM_IMDIO_BASE;
+
+	if (is_enetc_rev1(pf->si))
+		mdio_priv->mdio_base = ENETC_PM_IMDIO_BASE;
+	else
+		mdio_priv->mdio_base = ENETC4_PM_IMDIO_BASE;
+
 	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-imdio", dev_name(dev));
 
 	err = mdiobus_register(bus);
@@ -341,5 +354,86 @@ void enetc_phylink_destroy(struct enetc_ndev_priv *priv)
 }
 EXPORT_SYMBOL_GPL(enetc_phylink_destroy);
 
+void enetc_set_default_rss_key(struct enetc_pf *pf)
+{
+	u8 hash_key[ENETC_RSSHASH_KEY_SIZE] = {0};
+
+	/* set up hash key */
+	get_random_bytes(hash_key, ENETC_RSSHASH_KEY_SIZE);
+	enetc_set_rss_key(pf->si, hash_key);
+}
+EXPORT_SYMBOL_GPL(enetc_set_default_rss_key);
+
+static int enetc_vid_hash_idx(unsigned int vid)
+{
+	int res = 0;
+	int i;
+
+	for (i = 0; i < 6; i++)
+		res |= (hweight8(vid & (BIT(i) | BIT(i + 6))) & 0x1) << i;
+
+	return res;
+}
+
+static void enetc_refresh_vlan_ht_filter(struct enetc_pf *pf)
+{
+	int i;
+
+	bitmap_zero(pf->vlan_ht_filter, ENETC_VLAN_HT_SIZE);
+	for_each_set_bit(i, pf->active_vlans, VLAN_N_VID) {
+		int hidx = enetc_vid_hash_idx(i);
+
+		__set_bit(hidx, pf->vlan_ht_filter);
+	}
+}
+
+static void enetc_set_si_vlan_ht_filter(struct enetc_si *si,
+					int si_id, u64 hash)
+{
+	struct enetc_hw *hw = &si->hw;
+	int high_reg_off, low_reg_off;
+
+	if (is_enetc_rev1(si)) {
+		low_reg_off = ENETC_PSIVHFR0(si_id);
+		high_reg_off = ENETC_PSIVHFR1(si_id);
+	} else {
+		low_reg_off = ENETC4_PSIVHFR0(si_id);
+		high_reg_off = ENETC4_PSIVHFR1(si_id);
+	}
+
+	enetc_port_wr(hw, low_reg_off, lower_32_bits(hash));
+	enetc_port_wr(hw, high_reg_off, upper_32_bits(hash));
+}
+
+int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	int idx;
+
+	__set_bit(vid, pf->active_vlans);
+
+	idx = enetc_vid_hash_idx(vid);
+	if (!__test_and_set_bit(idx, pf->vlan_ht_filter))
+		enetc_set_si_vlan_ht_filter(pf->si, 0, *pf->vlan_ht_filter);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(enetc_vlan_rx_add_vid);
+
+int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+
+	if (__test_and_clear_bit(vid, pf->active_vlans)) {
+		enetc_refresh_vlan_ht_filter(pf);
+		enetc_set_si_vlan_ht_filter(pf->si, 0, *pf->vlan_ht_filter);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(enetc_vlan_rx_del_vid);
+
 MODULE_DESCRIPTION("NXP ENETC PF common functionality driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
index 48f55ee743ad..96d4840a3107 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
@@ -12,6 +12,9 @@ void enetc_mdiobus_destroy(struct enetc_pf *pf);
 int enetc_phylink_create(struct enetc_ndev_priv *priv, struct device_node *node,
 			 const struct phylink_mac_ops *ops);
 void enetc_phylink_destroy(struct enetc_ndev_priv *priv);
+void enetc_set_default_rss_key(struct enetc_pf *pf);
+int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid);
+int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid);
 
 static inline u16 enetc_get_ip_revision(struct enetc_hw *hw)
 {
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ptp.c b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c
index 5243fc031058..b8413d3b4f16 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ptp.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c
@@ -7,9 +7,6 @@
 
 #include "enetc.h"
 
-int enetc_phc_index = -1;
-EXPORT_SYMBOL_GPL(enetc_phc_index);
-
 static struct ptp_clock_info enetc_ptp_caps = {
 	.owner		= THIS_MODULE,
 	.name		= "ENETC PTP clock",
@@ -92,7 +89,6 @@ static int enetc_ptp_probe(struct pci_dev *pdev,
 	if (err)
 		goto err_no_clock;
 
-	enetc_phc_index = ptp_qoriq->phc_index;
 	pci_set_drvdata(pdev, ptp_qoriq);
 
 	return 0;
@@ -118,7 +114,6 @@ static void enetc_ptp_remove(struct pci_dev *pdev)
 {
 	struct ptp_qoriq *ptp_qoriq = pci_get_drvdata(pdev);
 
-	enetc_phc_index = -1;
 	ptp_qoriq_free(ptp_qoriq);
 	pci_free_irq_vectors(pdev);
 	kfree(ptp_qoriq);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
index 3768752b6008..6c4b374bcb0e 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
@@ -121,6 +121,8 @@ static const struct net_device_ops enetc_ndev_ops = {
 	.ndo_set_features	= enetc_vf_set_features,
 	.ndo_eth_ioctl		= enetc_ioctl,
 	.ndo_setup_tc		= enetc_vf_setup_tc,
+	.ndo_hwtstamp_get	= enetc_hwtstamp_get,
+	.ndo_hwtstamp_set	= enetc_hwtstamp_set,
 };
 
 static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
@@ -155,13 +157,20 @@ static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 	ndev->vlan_features = NETIF_F_SG | NETIF_F_HW_CSUM |
 			      NETIF_F_TSO | NETIF_F_TSO6;
 
-	if (si->num_rss)
+	if (si->num_rss) {
 		ndev->hw_features |= NETIF_F_RXHASH;
+		ndev->features |= NETIF_F_RXHASH;
+	}
 
 	/* pick up primary MAC address from SI */
 	enetc_load_primary_mac_addr(&si->hw, ndev);
 }
 
+static const struct enetc_si_ops enetc_vsi_ops = {
+	.get_rss_table = enetc_get_rss_table,
+	.set_rss_table = enetc_set_rss_table,
+};
+
 static int enetc_vf_probe(struct pci_dev *pdev,
 			  const struct pci_device_id *ent)
 {
@@ -176,6 +185,7 @@ static int enetc_vf_probe(struct pci_dev *pdev,
 
 	si = pci_get_drvdata(pdev);
 	si->revision = ENETC_REV_1_0;
+	si->ops = &enetc_vsi_ops;
 	err = enetc_get_driver_data(si);
 	if (err) {
 		dev_err_probe(&pdev->dev, err,
diff --git a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
index bcb8eefeb93c..443983fdecd9 100644
--- a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
+++ b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
@@ -47,6 +47,13 @@
 #define PCS_PROT_SFI			BIT(4)
 #define PCS_PROT_10G_SXGMII		BIT(6)
 
+#define IMX94_EXT_PIN_CONTROL		0x10
+#define  MAC2_MAC3_SEL			BIT(1)
+
+#define IMX94_NETC_LINK_CFG(a)		(0x4c + (a) * 4)
+#define  NETC_LINK_CFG_MII_PROT		GENMASK(3, 0)
+#define  NETC_LINK_CFG_IO_VAR		GENMASK(19, 16)
+
 /* NETC privileged register block register */
 #define PRB_NETCRR			0x100
 #define  NETCRR_SR			BIT(0)
@@ -59,6 +66,10 @@
 /* NETC integrated endpoint register block register */
 #define IERB_EMDIOFAUXR			0x344
 #define IERB_T0FAUXR			0x444
+#define IERB_ETBCR(a)			(0x300c + 0x100 * (a))
+#define IERB_LBCR(a)			(0x1010 + 0x40 * (a))
+#define  LBCR_MDIO_PHYAD_PRTAD(addr)	(((addr) & 0x1f) << 8)
+
 #define IERB_EFAUXR(a)			(0x3044 + 0x100 * (a))
 #define IERB_VFAUXR(a)			(0x4004 + 0x40 * (a))
 #define FAUXR_LDID			GENMASK(3, 0)
@@ -68,6 +79,19 @@
 #define IMX95_ENETC1_BUS_DEVFN		0x40
 #define IMX95_ENETC2_BUS_DEVFN		0x80
 
+#define IMX94_ENETC0_BUS_DEVFN		0x100
+#define IMX94_ENETC1_BUS_DEVFN		0x140
+#define IMX94_ENETC2_BUS_DEVFN		0x180
+#define IMX94_TIMER0_BUS_DEVFN		0x1
+#define IMX94_TIMER1_BUS_DEVFN		0x101
+#define IMX94_TIMER2_BUS_DEVFN		0x181
+#define IMX94_ENETC0_LINK		3
+#define IMX94_ENETC1_LINK		4
+#define IMX94_ENETC2_LINK		5
+
+#define NETC_ENETC_ID(a)		(a)
+#define NETC_TIMER_ID(a)		(a)
+
 /* Flags for different platforms */
 #define NETC_HAS_NETCMIX		BIT(0)
 
@@ -192,6 +216,90 @@ static int imx95_netcmix_init(struct platform_device *pdev)
 	return 0;
 }
 
+static int imx94_enetc_get_link_id(struct device_node *np)
+{
+	int bus_devfn = netc_of_pci_get_bus_devfn(np);
+
+	/* Parse ENETC link number */
+	switch (bus_devfn) {
+	case IMX94_ENETC0_BUS_DEVFN:
+		return IMX94_ENETC0_LINK;
+	case IMX94_ENETC1_BUS_DEVFN:
+		return IMX94_ENETC1_LINK;
+	case IMX94_ENETC2_BUS_DEVFN:
+		return IMX94_ENETC2_LINK;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int imx94_link_config(struct netc_blk_ctrl *priv,
+			     struct device_node *np, int link_id)
+{
+	phy_interface_t interface;
+	int mii_proto;
+	u32 val;
+
+	/* The node may be disabled and does not have a 'phy-mode'
+	 * or 'phy-connection-type' property.
+	 */
+	if (of_get_phy_mode(np, &interface))
+		return 0;
+
+	mii_proto = netc_get_link_mii_protocol(interface);
+	if (mii_proto < 0)
+		return mii_proto;
+
+	val = mii_proto & NETC_LINK_CFG_MII_PROT;
+	if (val == MII_PROT_SERIAL)
+		val = u32_replace_bits(val, IO_VAR_16FF_16G_SERDES,
+				       NETC_LINK_CFG_IO_VAR);
+
+	netc_reg_write(priv->netcmix, IMX94_NETC_LINK_CFG(link_id), val);
+
+	return 0;
+}
+
+static int imx94_enetc_link_config(struct netc_blk_ctrl *priv,
+				   struct device_node *np)
+{
+	int link_id = imx94_enetc_get_link_id(np);
+
+	if (link_id < 0)
+		return link_id;
+
+	return imx94_link_config(priv, np, link_id);
+}
+
+static int imx94_netcmix_init(struct platform_device *pdev)
+{
+	struct netc_blk_ctrl *priv = platform_get_drvdata(pdev);
+	struct device_node *np = pdev->dev.of_node;
+	u32 val;
+	int err;
+
+	for_each_child_of_node_scoped(np, child) {
+		for_each_child_of_node_scoped(child, gchild) {
+			if (!of_device_is_compatible(gchild, "pci1131,e101"))
+				continue;
+
+			err = imx94_enetc_link_config(priv, gchild);
+			if (err)
+				return err;
+		}
+	}
+
+	/* ENETC 0 and switch port 2 share the same parallel interface.
+	 * Currently, the switch is not supported, so this interface is
+	 * used by ENETC 0 by default.
+	 */
+	val = netc_reg_read(priv->netcmix, IMX94_EXT_PIN_CONTROL);
+	val |= MAC2_MAC3_SEL;
+	netc_reg_write(priv->netcmix, IMX94_EXT_PIN_CONTROL, val);
+
+	return 0;
+}
+
 static bool netc_ierb_is_locked(struct netc_blk_ctrl *priv)
 {
 	return !!(netc_reg_read(priv->prb, PRB_NETCRR) & NETCRR_LOCK);
@@ -217,6 +325,142 @@ static int netc_unlock_ierb_with_warm_reset(struct netc_blk_ctrl *priv)
 				 1000, 100000, true, priv->prb, PRB_NETCRR);
 }
 
+static int netc_get_phy_addr(struct device_node *np)
+{
+	struct device_node *mdio_node, *phy_node;
+	u32 addr = 0;
+	int err = 0;
+
+	mdio_node = of_get_child_by_name(np, "mdio");
+	if (!mdio_node)
+		return 0;
+
+	phy_node = of_get_next_child(mdio_node, NULL);
+	if (!phy_node)
+		goto of_put_mdio_node;
+
+	err = of_property_read_u32(phy_node, "reg", &addr);
+	if (err)
+		goto of_put_phy_node;
+
+	if (addr >= PHY_MAX_ADDR)
+		err = -EINVAL;
+
+of_put_phy_node:
+	of_node_put(phy_node);
+
+of_put_mdio_node:
+	of_node_put(mdio_node);
+
+	return err ? err : addr;
+}
+
+static int netc_parse_emdio_phy_mask(struct device_node *np, u32 *phy_mask)
+{
+	u32 mask = 0;
+
+	for_each_child_of_node_scoped(np, child) {
+		u32 addr;
+		int err;
+
+		err = of_property_read_u32(child, "reg", &addr);
+		if (err)
+			return err;
+
+		if (addr >= PHY_MAX_ADDR)
+			return -EINVAL;
+
+		mask |= BIT(addr);
+	}
+
+	*phy_mask = mask;
+
+	return 0;
+}
+
+static int netc_get_emdio_phy_mask(struct device_node *np, u32 *phy_mask)
+{
+	for_each_child_of_node_scoped(np, child) {
+		for_each_child_of_node_scoped(child, gchild) {
+			if (!of_device_is_compatible(gchild, "pci1131,ee00"))
+				continue;
+
+			return netc_parse_emdio_phy_mask(gchild, phy_mask);
+		}
+	}
+
+	return 0;
+}
+
+static int imx95_enetc_mdio_phyaddr_config(struct platform_device *pdev)
+{
+	struct netc_blk_ctrl *priv = platform_get_drvdata(pdev);
+	struct device_node *np = pdev->dev.of_node;
+	struct device *dev = &pdev->dev;
+	int bus_devfn, addr, err;
+	u32 phy_mask = 0;
+
+	err = netc_get_emdio_phy_mask(np, &phy_mask);
+	if (err) {
+		dev_err(dev, "Failed to get PHY address mask\n");
+		return err;
+	}
+
+	/* Update the port EMDIO PHY address through parsing phy properties.
+	 * This is needed when using the port EMDIO but it's harmless when
+	 * using the central EMDIO. So apply it on all cases.
+	 */
+	for_each_child_of_node_scoped(np, child) {
+		for_each_child_of_node_scoped(child, gchild) {
+			if (!of_device_is_compatible(gchild, "pci1131,e101"))
+				continue;
+
+			bus_devfn = netc_of_pci_get_bus_devfn(gchild);
+			if (bus_devfn < 0) {
+				dev_err(dev, "Failed to get BDF number\n");
+				return bus_devfn;
+			}
+
+			addr = netc_get_phy_addr(gchild);
+			if (addr < 0) {
+				dev_err(dev, "Failed to get PHY address\n");
+				return addr;
+			}
+
+			if (phy_mask & BIT(addr)) {
+				dev_err(dev,
+					"Find same PHY address in EMDIO and ENETC node\n");
+				return -EINVAL;
+			}
+
+			/* The default value of LaBCR[MDIO_PHYAD_PRTAD ] is
+			 * 0, so no need to set the register.
+			 */
+			if (!addr)
+				continue;
+
+			switch (bus_devfn) {
+			case IMX95_ENETC0_BUS_DEVFN:
+				netc_reg_write(priv->ierb, IERB_LBCR(0),
+					       LBCR_MDIO_PHYAD_PRTAD(addr));
+				break;
+			case IMX95_ENETC1_BUS_DEVFN:
+				netc_reg_write(priv->ierb, IERB_LBCR(1),
+					       LBCR_MDIO_PHYAD_PRTAD(addr));
+				break;
+			case IMX95_ENETC2_BUS_DEVFN:
+				netc_reg_write(priv->ierb, IERB_LBCR(2),
+					       LBCR_MDIO_PHYAD_PRTAD(addr));
+				break;
+			default:
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+
 static int imx95_ierb_init(struct platform_device *pdev)
 {
 	struct netc_blk_ctrl *priv = platform_get_drvdata(pdev);
@@ -244,6 +488,155 @@ static int imx95_ierb_init(struct platform_device *pdev)
 	/* NETC TIMER */
 	netc_reg_write(priv->ierb, IERB_T0FAUXR, 7);
 
+	return imx95_enetc_mdio_phyaddr_config(pdev);
+}
+
+static int imx94_get_enetc_id(struct device_node *np)
+{
+	int bus_devfn = netc_of_pci_get_bus_devfn(np);
+
+	/* Parse ENETC offset */
+	switch (bus_devfn) {
+	case IMX94_ENETC0_BUS_DEVFN:
+		return NETC_ENETC_ID(0);
+	case IMX94_ENETC1_BUS_DEVFN:
+		return NETC_ENETC_ID(1);
+	case IMX94_ENETC2_BUS_DEVFN:
+		return NETC_ENETC_ID(2);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int imx94_get_timer_id(struct device_node *np)
+{
+	int bus_devfn = netc_of_pci_get_bus_devfn(np);
+
+	/* Parse NETC PTP timer ID, the timer0 is on bus 0,
+	 * the timer 1 and timer2 is on bus 1.
+	 */
+	switch (bus_devfn) {
+	case IMX94_TIMER0_BUS_DEVFN:
+		return NETC_TIMER_ID(0);
+	case IMX94_TIMER1_BUS_DEVFN:
+		return NETC_TIMER_ID(1);
+	case IMX94_TIMER2_BUS_DEVFN:
+		return NETC_TIMER_ID(2);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int imx94_enetc_update_tid(struct netc_blk_ctrl *priv,
+				  struct device_node *np)
+{
+	struct device *dev = &priv->pdev->dev;
+	struct device_node *timer_np;
+	int eid, tid;
+
+	eid = imx94_get_enetc_id(np);
+	if (eid < 0) {
+		dev_err(dev, "Failed to get ENETC ID\n");
+		return eid;
+	}
+
+	timer_np = of_parse_phandle(np, "ptp-timer", 0);
+	if (!timer_np) {
+		/* If 'ptp-timer' is not present, the timer1 is the default
+		 * timer of all standalone ENETCs, which is on the same PCIe
+		 * bus as these ENETCs.
+		 */
+		tid = NETC_TIMER_ID(1);
+		goto end;
+	}
+
+	tid = imx94_get_timer_id(timer_np);
+	of_node_put(timer_np);
+	if (tid < 0) {
+		dev_err(dev, "Failed to get NETC Timer ID\n");
+		return tid;
+	}
+
+end:
+	netc_reg_write(priv->ierb, IERB_ETBCR(eid), tid);
+
+	return 0;
+}
+
+static int imx94_enetc_mdio_phyaddr_config(struct netc_blk_ctrl *priv,
+					   struct device_node *np,
+					   u32 phy_mask)
+{
+	struct device *dev = &priv->pdev->dev;
+	int bus_devfn, addr;
+
+	bus_devfn = netc_of_pci_get_bus_devfn(np);
+	if (bus_devfn < 0) {
+		dev_err(dev, "Failed to get BDF number\n");
+		return bus_devfn;
+	}
+
+	addr = netc_get_phy_addr(np);
+	if (addr <= 0) {
+		dev_err(dev, "Failed to get PHY address\n");
+		return addr;
+	}
+
+	if (phy_mask & BIT(addr)) {
+		dev_err(dev,
+			"Find same PHY address in EMDIO and ENETC node\n");
+		return -EINVAL;
+	}
+
+	switch (bus_devfn) {
+	case IMX94_ENETC0_BUS_DEVFN:
+		netc_reg_write(priv->ierb, IERB_LBCR(IMX94_ENETC0_LINK),
+			       LBCR_MDIO_PHYAD_PRTAD(addr));
+		break;
+	case IMX94_ENETC1_BUS_DEVFN:
+		netc_reg_write(priv->ierb, IERB_LBCR(IMX94_ENETC1_LINK),
+			       LBCR_MDIO_PHYAD_PRTAD(addr));
+		break;
+	case IMX94_ENETC2_BUS_DEVFN:
+		netc_reg_write(priv->ierb, IERB_LBCR(IMX94_ENETC2_LINK),
+			       LBCR_MDIO_PHYAD_PRTAD(addr));
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int imx94_ierb_init(struct platform_device *pdev)
+{
+	struct netc_blk_ctrl *priv = platform_get_drvdata(pdev);
+	struct device_node *np = pdev->dev.of_node;
+	u32 phy_mask = 0;
+	int err;
+
+	err = netc_get_emdio_phy_mask(np, &phy_mask);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to get PHY address mask\n");
+		return err;
+	}
+
+	for_each_child_of_node_scoped(np, child) {
+		for_each_child_of_node_scoped(child, gchild) {
+			if (!of_device_is_compatible(gchild, "pci1131,e101"))
+				continue;
+
+			err = imx94_enetc_update_tid(priv, gchild);
+			if (err)
+				return err;
+
+			err = imx94_enetc_mdio_phyaddr_config(priv, gchild,
+							      phy_mask);
+			if (err)
+				return err;
+		}
+	}
+
 	return 0;
 }
 
@@ -340,8 +733,15 @@ static const struct netc_devinfo imx95_devinfo = {
 	.ierb_init = imx95_ierb_init,
 };
 
+static const struct netc_devinfo imx94_devinfo = {
+	.flags = NETC_HAS_NETCMIX,
+	.netcmix_init = imx94_netcmix_init,
+	.ierb_init = imx94_ierb_init,
+};
+
 static const struct of_device_id netc_blk_ctrl_match[] = {
 	{ .compatible = "nxp,imx95-netc-blk-ctrl", .data = &imx95_devinfo },
+	{ .compatible = "nxp,imx94-netc-blk-ctrl", .data = &imx94_devinfo },
 	{},
 };
 MODULE_DEVICE_TABLE(of, netc_blk_ctrl_match);
diff --git a/drivers/net/ethernet/freescale/enetc/ntmp.c b/drivers/net/ethernet/freescale/enetc/ntmp.c
new file mode 100644
index 000000000000..0c1d343253bf
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/ntmp.c
@@ -0,0 +1,457 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/*
+ * NETC NTMP (NETC Table Management Protocol) 2.0 Library
+ * Copyright 2025 NXP
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/fsl/netc_global.h>
+#include <linux/iopoll.h>
+
+#include "ntmp_private.h"
+
+#define NETC_CBDR_TIMEOUT		1000 /* us */
+#define NETC_CBDR_DELAY_US		10
+#define NETC_CBDR_MR_EN			BIT(31)
+
+#define NTMP_BASE_ADDR_ALIGN		128
+#define NTMP_DATA_ADDR_ALIGN		32
+
+/* Define NTMP Table ID */
+#define NTMP_MAFT_ID			1
+#define NTMP_RSST_ID			3
+
+/* Generic Update Actions for most tables */
+#define NTMP_GEN_UA_CFGEU		BIT(0)
+#define NTMP_GEN_UA_STSEU		BIT(1)
+
+#define NTMP_ENTRY_ID_SIZE		4
+#define RSST_ENTRY_NUM			64
+#define RSST_STSE_DATA_SIZE(n)		((n) * 8)
+#define RSST_CFGE_DATA_SIZE(n)		(n)
+
+int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev,
+		   const struct netc_cbdr_regs *regs)
+{
+	int cbd_num = NETC_CBDR_BD_NUM;
+	size_t size;
+
+	size = cbd_num * sizeof(union netc_cbd) + NTMP_BASE_ADDR_ALIGN;
+	cbdr->addr_base = dma_alloc_coherent(dev, size, &cbdr->dma_base,
+					     GFP_KERNEL);
+	if (!cbdr->addr_base)
+		return -ENOMEM;
+
+	cbdr->dma_size = size;
+	cbdr->bd_num = cbd_num;
+	cbdr->regs = *regs;
+	cbdr->dev = dev;
+
+	/* The base address of the Control BD Ring must be 128 bytes aligned */
+	cbdr->dma_base_align =  ALIGN(cbdr->dma_base,  NTMP_BASE_ADDR_ALIGN);
+	cbdr->addr_base_align = PTR_ALIGN(cbdr->addr_base,
+					  NTMP_BASE_ADDR_ALIGN);
+
+	spin_lock_init(&cbdr->ring_lock);
+
+	cbdr->next_to_use = netc_read(cbdr->regs.pir);
+	cbdr->next_to_clean = netc_read(cbdr->regs.cir);
+
+	/* Step 1: Configure the base address of the Control BD Ring */
+	netc_write(cbdr->regs.bar0, lower_32_bits(cbdr->dma_base_align));
+	netc_write(cbdr->regs.bar1, upper_32_bits(cbdr->dma_base_align));
+
+	/* Step 2: Configure the number of BDs of the Control BD Ring */
+	netc_write(cbdr->regs.lenr, cbdr->bd_num);
+
+	/* Step 3: Enable the Control BD Ring */
+	netc_write(cbdr->regs.mr, NETC_CBDR_MR_EN);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ntmp_init_cbdr);
+
+void ntmp_free_cbdr(struct netc_cbdr *cbdr)
+{
+	/* Disable the Control BD Ring */
+	netc_write(cbdr->regs.mr, 0);
+	dma_free_coherent(cbdr->dev, cbdr->dma_size, cbdr->addr_base,
+			  cbdr->dma_base);
+	memset(cbdr, 0, sizeof(*cbdr));
+}
+EXPORT_SYMBOL_GPL(ntmp_free_cbdr);
+
+static int ntmp_get_free_cbd_num(struct netc_cbdr *cbdr)
+{
+	return (cbdr->next_to_clean - cbdr->next_to_use - 1 +
+		cbdr->bd_num) % cbdr->bd_num;
+}
+
+static union netc_cbd *ntmp_get_cbd(struct netc_cbdr *cbdr, int index)
+{
+	return &((union netc_cbd *)(cbdr->addr_base_align))[index];
+}
+
+static void ntmp_clean_cbdr(struct netc_cbdr *cbdr)
+{
+	union netc_cbd *cbd;
+	int i;
+
+	i = cbdr->next_to_clean;
+	while (netc_read(cbdr->regs.cir) != i) {
+		cbd = ntmp_get_cbd(cbdr, i);
+		memset(cbd, 0, sizeof(*cbd));
+		i = (i + 1) % cbdr->bd_num;
+	}
+
+	cbdr->next_to_clean = i;
+}
+
+static int netc_xmit_ntmp_cmd(struct ntmp_user *user, union netc_cbd *cbd)
+{
+	union netc_cbd *cur_cbd;
+	struct netc_cbdr *cbdr;
+	int i, err;
+	u16 status;
+	u32 val;
+
+	/* Currently only i.MX95 ENETC is supported, and it only has one
+	 * command BD ring
+	 */
+	cbdr = &user->ring[0];
+
+	spin_lock_bh(&cbdr->ring_lock);
+
+	if (unlikely(!ntmp_get_free_cbd_num(cbdr)))
+		ntmp_clean_cbdr(cbdr);
+
+	i = cbdr->next_to_use;
+	cur_cbd = ntmp_get_cbd(cbdr, i);
+	*cur_cbd = *cbd;
+	dma_wmb();
+
+	/* Update producer index of both software and hardware */
+	i = (i + 1) % cbdr->bd_num;
+	cbdr->next_to_use = i;
+	netc_write(cbdr->regs.pir, i);
+
+	err = read_poll_timeout_atomic(netc_read, val, val == i,
+				       NETC_CBDR_DELAY_US, NETC_CBDR_TIMEOUT,
+				       true, cbdr->regs.cir);
+	if (unlikely(err))
+		goto cbdr_unlock;
+
+	dma_rmb();
+	/* Get the writeback command BD, because the caller may need
+	 * to check some other fields of the response header.
+	 */
+	*cbd = *cur_cbd;
+
+	/* Check the writeback error status */
+	status = le16_to_cpu(cbd->resp_hdr.error_rr) & NTMP_RESP_ERROR;
+	if (unlikely(status)) {
+		err = -EIO;
+		dev_err(user->dev, "Command BD error: 0x%04x\n", status);
+	}
+
+	ntmp_clean_cbdr(cbdr);
+	dma_wmb();
+
+cbdr_unlock:
+	spin_unlock_bh(&cbdr->ring_lock);
+
+	return err;
+}
+
+static int ntmp_alloc_data_mem(struct ntmp_dma_buf *data, void **buf_align)
+{
+	void *buf;
+
+	buf = dma_alloc_coherent(data->dev, data->size + NTMP_DATA_ADDR_ALIGN,
+				 &data->dma, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	data->buf = buf;
+	*buf_align = PTR_ALIGN(buf, NTMP_DATA_ADDR_ALIGN);
+
+	return 0;
+}
+
+static void ntmp_free_data_mem(struct ntmp_dma_buf *data)
+{
+	dma_free_coherent(data->dev, data->size + NTMP_DATA_ADDR_ALIGN,
+			  data->buf, data->dma);
+}
+
+static void ntmp_fill_request_hdr(union netc_cbd *cbd, dma_addr_t dma,
+				  int len, int table_id, int cmd,
+				  int access_method)
+{
+	dma_addr_t dma_align;
+
+	memset(cbd, 0, sizeof(*cbd));
+	dma_align = ALIGN(dma, NTMP_DATA_ADDR_ALIGN);
+	cbd->req_hdr.addr = cpu_to_le64(dma_align);
+	cbd->req_hdr.len = cpu_to_le32(len);
+	cbd->req_hdr.cmd = cmd;
+	cbd->req_hdr.access_method = FIELD_PREP(NTMP_ACCESS_METHOD,
+						access_method);
+	cbd->req_hdr.table_id = table_id;
+	cbd->req_hdr.ver_cci_rr = FIELD_PREP(NTMP_HDR_VERSION,
+					     NTMP_HDR_VER2);
+	/* For NTMP version 2.0 or later version */
+	cbd->req_hdr.npf = cpu_to_le32(NTMP_NPF);
+}
+
+static void ntmp_fill_crd(struct ntmp_cmn_req_data *crd, u8 tblv,
+			  u8 qa, u16 ua)
+{
+	crd->update_act = cpu_to_le16(ua);
+	crd->tblv_qact = NTMP_TBLV_QACT(tblv, qa);
+}
+
+static void ntmp_fill_crd_eid(struct ntmp_req_by_eid *rbe, u8 tblv,
+			      u8 qa, u16 ua, u32 entry_id)
+{
+	ntmp_fill_crd(&rbe->crd, tblv, qa, ua);
+	rbe->entry_id = cpu_to_le32(entry_id);
+}
+
+static const char *ntmp_table_name(int tbl_id)
+{
+	switch (tbl_id) {
+	case NTMP_MAFT_ID:
+		return "MAC Address Filter Table";
+	case NTMP_RSST_ID:
+		return "RSS Table";
+	default:
+		return "Unknown Table";
+	};
+}
+
+static int ntmp_delete_entry_by_id(struct ntmp_user *user, int tbl_id,
+				   u8 tbl_ver, u32 entry_id, u32 req_len,
+				   u32 resp_len)
+{
+	struct ntmp_dma_buf data = {
+		.dev = user->dev,
+		.size = max(req_len, resp_len),
+	};
+	struct ntmp_req_by_eid *req;
+	union netc_cbd cbd;
+	int err;
+
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	ntmp_fill_crd_eid(req, tbl_ver, 0, 0, entry_id);
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(req_len, resp_len),
+			      tbl_id, NTMP_CMD_DELETE, NTMP_AM_ENTRY_ID);
+
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err)
+		dev_err(user->dev,
+			"Failed to delete entry 0x%x of %s, err: %pe",
+			entry_id, ntmp_table_name(tbl_id), ERR_PTR(err));
+
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+
+static int ntmp_query_entry_by_id(struct ntmp_user *user, int tbl_id,
+				  u32 len, struct ntmp_req_by_eid *req,
+				  dma_addr_t dma, bool compare_eid)
+{
+	struct ntmp_cmn_resp_query *resp;
+	int cmd = NTMP_CMD_QUERY;
+	union netc_cbd cbd;
+	u32 entry_id;
+	int err;
+
+	entry_id = le32_to_cpu(req->entry_id);
+	if (le16_to_cpu(req->crd.update_act))
+		cmd = NTMP_CMD_QU;
+
+	/* Request header */
+	ntmp_fill_request_hdr(&cbd, dma, len, tbl_id, cmd, NTMP_AM_ENTRY_ID);
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err) {
+		dev_err(user->dev,
+			"Failed to query entry 0x%x of %s, err: %pe\n",
+			entry_id, ntmp_table_name(tbl_id), ERR_PTR(err));
+		return err;
+	}
+
+	/* For a few tables, the first field of their response data is not
+	 * entry_id, so directly return success.
+	 */
+	if (!compare_eid)
+		return 0;
+
+	resp = (struct ntmp_cmn_resp_query *)req;
+	if (unlikely(le32_to_cpu(resp->entry_id) != entry_id)) {
+		dev_err(user->dev,
+			"%s: query EID 0x%x doesn't match response EID 0x%x\n",
+			ntmp_table_name(tbl_id), entry_id, le32_to_cpu(resp->entry_id));
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int ntmp_maft_add_entry(struct ntmp_user *user, u32 entry_id,
+			struct maft_entry_data *maft)
+{
+	struct ntmp_dma_buf data = {
+		.dev = user->dev,
+		.size = sizeof(struct maft_req_add),
+	};
+	struct maft_req_add *req;
+	union netc_cbd cbd;
+	int err;
+
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	/* Set mac address filter table request data buffer */
+	ntmp_fill_crd_eid(&req->rbe, user->tbl.maft_ver, 0, 0, entry_id);
+	req->keye = maft->keye;
+	req->cfge = maft->cfge;
+
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(data.size, 0),
+			      NTMP_MAFT_ID, NTMP_CMD_ADD, NTMP_AM_ENTRY_ID);
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err)
+		dev_err(user->dev, "Failed to add MAFT entry 0x%x, err: %pe\n",
+			entry_id, ERR_PTR(err));
+
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_maft_add_entry);
+
+int ntmp_maft_query_entry(struct ntmp_user *user, u32 entry_id,
+			  struct maft_entry_data *maft)
+{
+	struct ntmp_dma_buf data = {
+		.dev = user->dev,
+		.size = sizeof(struct maft_resp_query),
+	};
+	struct maft_resp_query *resp;
+	struct ntmp_req_by_eid *req;
+	int err;
+
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	ntmp_fill_crd_eid(req, user->tbl.maft_ver, 0, 0, entry_id);
+	err = ntmp_query_entry_by_id(user, NTMP_MAFT_ID,
+				     NTMP_LEN(sizeof(*req), data.size),
+				     req, data.dma, true);
+	if (err)
+		goto end;
+
+	resp = (struct maft_resp_query *)req;
+	maft->keye = resp->keye;
+	maft->cfge = resp->cfge;
+
+end:
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_maft_query_entry);
+
+int ntmp_maft_delete_entry(struct ntmp_user *user, u32 entry_id)
+{
+	return ntmp_delete_entry_by_id(user, NTMP_MAFT_ID, user->tbl.maft_ver,
+				       entry_id, NTMP_EID_REQ_LEN, 0);
+}
+EXPORT_SYMBOL_GPL(ntmp_maft_delete_entry);
+
+int ntmp_rsst_update_entry(struct ntmp_user *user, const u32 *table,
+			   int count)
+{
+	struct ntmp_dma_buf data = {.dev = user->dev};
+	struct rsst_req_update *req;
+	union netc_cbd cbd;
+	int err, i;
+
+	if (count != RSST_ENTRY_NUM)
+		/* HW only takes in a full 64 entry table */
+		return -EINVAL;
+
+	data.size = struct_size(req, groups, count);
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	/* Set the request data buffer */
+	ntmp_fill_crd_eid(&req->rbe, user->tbl.rsst_ver, 0,
+			  NTMP_GEN_UA_CFGEU | NTMP_GEN_UA_STSEU, 0);
+	for (i = 0; i < count; i++)
+		req->groups[i] = (u8)(table[i]);
+
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(data.size, 0),
+			      NTMP_RSST_ID, NTMP_CMD_UPDATE, NTMP_AM_ENTRY_ID);
+
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err)
+		dev_err(user->dev, "Failed to update RSST entry, err: %pe\n",
+			ERR_PTR(err));
+
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_rsst_update_entry);
+
+int ntmp_rsst_query_entry(struct ntmp_user *user, u32 *table, int count)
+{
+	struct ntmp_dma_buf data = {.dev = user->dev};
+	struct ntmp_req_by_eid *req;
+	union netc_cbd cbd;
+	int err, i;
+	u8 *group;
+
+	if (count != RSST_ENTRY_NUM)
+		/* HW only takes in a full 64 entry table */
+		return -EINVAL;
+
+	data.size = NTMP_ENTRY_ID_SIZE + RSST_STSE_DATA_SIZE(count) +
+		    RSST_CFGE_DATA_SIZE(count);
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	/* Set the request data buffer */
+	ntmp_fill_crd_eid(req, user->tbl.rsst_ver, 0, 0, 0);
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(sizeof(*req), data.size),
+			      NTMP_RSST_ID, NTMP_CMD_QUERY, NTMP_AM_ENTRY_ID);
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err) {
+		dev_err(user->dev, "Failed to query RSST entry, err: %pe\n",
+			ERR_PTR(err));
+		goto end;
+	}
+
+	group = (u8 *)req;
+	group += NTMP_ENTRY_ID_SIZE + RSST_STSE_DATA_SIZE(count);
+	for (i = 0; i < count; i++)
+		table[i] = group[i];
+
+end:
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_rsst_query_entry);
+
+MODULE_DESCRIPTION("NXP NETC Library");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/freescale/enetc/ntmp_private.h b/drivers/net/ethernet/freescale/enetc/ntmp_private.h
new file mode 100644
index 000000000000..34394e40fddd
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/ntmp_private.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/*
+ * NTMP table request and response data buffer formats
+ * Copyright 2025 NXP
+ */
+
+#ifndef __NTMP_PRIVATE_H
+#define __NTMP_PRIVATE_H
+
+#include <linux/bitfield.h>
+#include <linux/fsl/ntmp.h>
+
+#define NTMP_EID_REQ_LEN	8
+#define NETC_CBDR_BD_NUM	256
+
+union netc_cbd {
+	struct {
+		__le64 addr;
+		__le32 len;
+#define NTMP_RESP_LEN		GENMASK(19, 0)
+#define NTMP_REQ_LEN		GENMASK(31, 20)
+#define NTMP_LEN(req, resp)	(FIELD_PREP(NTMP_REQ_LEN, (req)) | \
+				((resp) & NTMP_RESP_LEN))
+		u8 cmd;
+#define NTMP_CMD_DELETE		BIT(0)
+#define NTMP_CMD_UPDATE		BIT(1)
+#define NTMP_CMD_QUERY		BIT(2)
+#define NTMP_CMD_ADD		BIT(3)
+#define NTMP_CMD_QU		(NTMP_CMD_QUERY | NTMP_CMD_UPDATE)
+		u8 access_method;
+#define NTMP_ACCESS_METHOD	GENMASK(7, 4)
+#define NTMP_AM_ENTRY_ID	0
+#define NTMP_AM_EXACT_KEY	1
+#define NTMP_AM_SEARCH		2
+#define NTMP_AM_TERNARY_KEY	3
+		u8 table_id;
+		u8 ver_cci_rr;
+#define NTMP_HDR_VERSION	GENMASK(5, 0)
+#define NTMP_HDR_VER2		2
+#define NTMP_CCI		BIT(6)
+#define NTMP_RR			BIT(7)
+		__le32 resv[3];
+		__le32 npf;
+#define NTMP_NPF		BIT(15)
+	} req_hdr;	/* NTMP Request Message Header Format */
+
+	struct {
+		__le32 resv0[3];
+		__le16 num_matched;
+		__le16 error_rr;
+#define NTMP_RESP_ERROR		GENMASK(11, 0)
+#define NTMP_RESP_RR		BIT(15)
+		__le32 resv1[4];
+	} resp_hdr; /* NTMP Response Message Header Format */
+};
+
+struct ntmp_dma_buf {
+	struct device *dev;
+	size_t size;
+	void *buf;
+	dma_addr_t dma;
+};
+
+struct ntmp_cmn_req_data {
+	__le16 update_act;
+	u8 dbg_opt;
+	u8 tblv_qact;
+#define NTMP_QUERY_ACT		GENMASK(3, 0)
+#define NTMP_TBL_VER		GENMASK(7, 4)
+#define NTMP_TBLV_QACT(v, a)	(FIELD_PREP(NTMP_TBL_VER, (v)) | \
+				 ((a) & NTMP_QUERY_ACT))
+};
+
+struct ntmp_cmn_resp_query {
+	__le32 entry_id;
+};
+
+/* Generic structure for request data by entry ID  */
+struct ntmp_req_by_eid {
+	struct ntmp_cmn_req_data crd;
+	__le32 entry_id;
+};
+
+/* MAC Address Filter Table Request Data Buffer Format of Add action */
+struct maft_req_add {
+	struct ntmp_req_by_eid rbe;
+	struct maft_keye_data keye;
+	struct maft_cfge_data cfge;
+};
+
+/* MAC Address Filter Table Response Data Buffer Format of Query action */
+struct maft_resp_query {
+	__le32 entry_id;
+	struct maft_keye_data keye;
+	struct maft_cfge_data cfge;
+};
+
+/* RSS Table Request Data Buffer Format of Update action */
+struct rsst_req_update {
+	struct ntmp_req_by_eid rbe;
+	u8 groups[];
+};
+
+#endif
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index c81f2ea588f2..fd9a93d02f8e 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -14,19 +14,17 @@
 #define	FEC_H
 /****************************************************************************/
 
+#include <dt-bindings/firmware/imx/rsrc.h>
+#include <linux/bpf.h>
 #include <linux/clocksource.h>
+#include <linux/firmware/imx/sci.h>
 #include <linux/net_tstamp.h>
 #include <linux/pm_qos.h>
-#include <linux/bpf.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/timecounter.h>
-#include <dt-bindings/firmware/imx/rsrc.h>
-#include <linux/firmware/imx/sci.h>
 #include <net/xdp.h>
 
-#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
-    defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \
-    defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST)
+#if !defined(CONFIG_M5272) || defined(CONFIG_COMPILE_TEST)
 /*
  *	Just figures, Motorola would have to change the offsets for
  *	registers in the same peripheral device on different models
@@ -115,7 +113,7 @@
 #define IEEE_T_MCOL		0x254 /* Frames tx'd with multiple collision */
 #define IEEE_T_DEF		0x258 /* Frames tx'd after deferral delay */
 #define IEEE_T_LCOL		0x25c /* Frames tx'd with late collision */
-#define IEEE_T_EXCOL		0x260 /* Frames tx'd with excesv collisions */
+#define IEEE_T_EXCOL		0x260 /* Frames tx'd with excessive collisions */
 #define IEEE_T_MACERR		0x264 /* Frames tx'd with TX FIFO underrun */
 #define IEEE_T_CSERR		0x268 /* Frames tx'd with carrier sense err */
 #define IEEE_T_SQE		0x26c /* Frames tx'd with SQE err */
@@ -242,23 +240,6 @@ struct bufdesc_ex {
 	__fec16 res0[4];
 };
 
-/*
- *	The following definitions courtesy of commproc.h, which where
- *	Copyright (c) 1997 Dan Malek (dmalek@jlc.net).
- */
-#define BD_SC_EMPTY	((ushort)0x8000)	/* Receive is empty */
-#define BD_SC_READY	((ushort)0x8000)	/* Transmit is ready */
-#define BD_SC_WRAP	((ushort)0x2000)	/* Last buffer descriptor */
-#define BD_SC_INTRPT	((ushort)0x1000)	/* Interrupt on change */
-#define BD_SC_CM	((ushort)0x0200)	/* Continuous mode */
-#define BD_SC_ID	((ushort)0x0100)	/* Rec'd too many idles */
-#define BD_SC_P		((ushort)0x0100)	/* xmt preamble */
-#define BD_SC_BR	((ushort)0x0020)	/* Break received */
-#define BD_SC_FR	((ushort)0x0010)	/* Framing error */
-#define BD_SC_PR	((ushort)0x0008)	/* Parity error */
-#define BD_SC_OV	((ushort)0x0002)	/* Overrun */
-#define BD_SC_CD	((ushort)0x0001)	/* ?? */
-
 /* Buffer descriptor control/status used by Ethernet receive.
  */
 #define BD_ENET_RX_EMPTY	((ushort)0x8000)
@@ -342,16 +323,17 @@ struct bufdesc_ex {
 #define FEC_TX_BD_FTYPE(X)	(((X) & 0xf) << 20)
 
 /* The number of Tx and Rx buffers.  These are allocated from the page
- * pool.  The code may assume these are power of two, so it it best
+ * pool.  The code may assume these are power of two, so it is best
  * to keep them that size.
  * We don't need to allocate pages for the transmitter.  We just use
  * the skbuffer directly.
  */
 
+#define FEC_DRV_RESERVE_SPACE (XDP_PACKET_HEADROOM + \
+		SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 #define FEC_ENET_XDP_HEADROOM	(XDP_PACKET_HEADROOM)
 #define FEC_ENET_RX_PAGES	256
-#define FEC_ENET_RX_FRSIZE	(PAGE_SIZE - FEC_ENET_XDP_HEADROOM \
-		- SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define FEC_ENET_RX_FRSIZE	(PAGE_SIZE - FEC_DRV_RESERVE_SPACE)
 #define FEC_ENET_RX_FRPPG	(PAGE_SIZE / FEC_ENET_RX_FRSIZE)
 #define RX_RING_SIZE		(FEC_ENET_RX_FRPPG * FEC_ENET_RX_PAGES)
 #define FEC_ENET_TX_FRSIZE	2048
@@ -460,7 +442,7 @@ struct bufdesc_ex {
 #define FEC_QUIRK_SINGLE_MDIO		(1 << 11)
 /* Controller supports RACC register */
 #define FEC_QUIRK_HAS_RACC		(1 << 12)
-/* Controller supports interrupt coalesc */
+/* Controller supports interrupt coalesce */
 #define FEC_QUIRK_HAS_COALESCE		(1 << 13)
 /* Interrupt doesn't wake CPU from deep idle */
 #define FEC_QUIRK_ERR006687		(1 << 14)
@@ -495,7 +477,7 @@ struct bufdesc_ex {
  */
 #define FEC_QUIRK_HAS_EEE		(1 << 20)
 
-/* i.MX8QM ENET IP version add new feture to generate delayed TXC/RXC
+/* i.MX8QM ENET IP version add new feature to generate delayed TXC/RXC
  * as an alternative option to make sure it works well with various PHYs.
  * For the implementation of delayed clock, ENET takes synchronized 250MHz
  * clocks to generate 2ns delay.
@@ -513,6 +495,9 @@ struct bufdesc_ex {
  */
 #define FEC_QUIRK_HAS_MDIO_C45		BIT(24)
 
+/* Jumbo Frame support */
+#define FEC_QUIRK_JUMBO_FRAME		BIT(25)
+
 struct bufdesc_prop {
 	int qid;
 	/* Address of Rx and Tx buffers */
@@ -526,12 +511,6 @@ struct bufdesc_prop {
 	unsigned char dsize_log2;
 };
 
-struct fec_enet_priv_txrx_info {
-	int	offset;
-	struct	page *page;
-	struct  sk_buff *skb;
-};
-
 enum {
 	RX_XDP_REDIRECT = 0,
 	RX_XDP_PASS,
@@ -571,7 +550,7 @@ struct fec_enet_priv_tx_q {
 
 struct fec_enet_priv_rx_q {
 	struct bufdesc_prop bd;
-	struct  fec_enet_priv_txrx_info rx_skb_info[RX_RING_SIZE];
+	struct page *rx_buf[RX_RING_SIZE];
 
 	/* page_pool */
 	struct page_pool *page_pool;
@@ -614,12 +593,14 @@ struct fec_enet_private {
 	unsigned int num_tx_queues;
 	unsigned int num_rx_queues;
 
-	/* The saved address of a sent-in-place packet/buffer, for skfree(). */
 	struct fec_enet_priv_tx_q *tx_queue[FEC_ENET_MAX_TX_QS];
 	struct fec_enet_priv_rx_q *rx_queue[FEC_ENET_MAX_RX_QS];
 
 	unsigned int total_tx_ring_size;
 	unsigned int total_rx_ring_size;
+	unsigned int max_buf_size;
+	unsigned int pagepool_order;
+	unsigned int rx_frame_size;
 
 	struct	platform_device *pdev;
 
@@ -662,7 +643,6 @@ struct fec_enet_private {
 	struct pm_qos_request pm_qos_req;
 
 	unsigned int tx_align;
-	unsigned int rx_align;
 
 	/* hw interrupt coalesce */
 	unsigned int rx_pkts_itr;
@@ -681,6 +661,7 @@ struct fec_enet_private {
 	unsigned int reload_period;
 	int pps_enable;
 	unsigned int next_counter;
+	bool perout_enable;
 	struct hrtimer perout_timer;
 	u64 perout_stime;
 
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index b2daed55bf6c..c685a5c0cc51 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -22,56 +22,56 @@
  * Copyright (C) 2010-2011 Freescale Semiconductor, Inc.
  */
 
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/pm_runtime.h>
-#include <linux/ptrace.h>
-#include <linux/errno.h>
-#include <linux/ioport.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
+#include <linux/bitops.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
+#include <linux/cacheflush.h>
+#include <linux/clk.h>
+#include <linux/crc32.h>
 #include <linux/delay.h>
-#include <linux/netdevice.h>
+#include <linux/errno.h>
 #include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/in.h>
-#include <linux/ip.h>
-#include <net/ip.h>
-#include <net/page_pool/helpers.h>
-#include <net/selftests.h>
-#include <net/tso.h>
-#include <linux/tcp.h>
-#include <linux/udp.h>
+#include <linux/fec.h>
+#include <linux/filter.h>
+#include <linux/gpio/consumer.h>
 #include <linux/icmp.h>
-#include <linux/spinlock.h>
-#include <linux/workqueue.h>
-#include <linux/bitops.h>
+#include <linux/if_vlan.h>
+#include <linux/in.h>
+#include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/ip.h>
 #include <linux/irq.h>
-#include <linux/clk.h>
-#include <linux/crc32.h>
-#include <linux/platform_device.h>
-#include <linux/property.h>
+#include <linux/kernel.h>
 #include <linux/mdio.h>
-#include <linux/phy.h>
-#include <linux/fec.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
 #include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
-#include <linux/regulator/consumer.h>
-#include <linux/if_vlan.h>
+#include <linux/phy.h>
 #include <linux/pinctrl/consumer.h>
-#include <linux/gpio/consumer.h>
+#include <linux/phy_fixed.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/prefetch.h>
-#include <linux/mfd/syscon.h>
+#include <linux/property.h>
+#include <linux/ptrace.h>
 #include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/workqueue.h>
+#include <net/ip.h>
+#include <net/page_pool/helpers.h>
+#include <net/selftests.h>
+#include <net/tso.h>
 #include <soc/imx/cpuidle.h>
-#include <linux/filter.h>
-#include <linux/bpf.h>
-#include <linux/bpf_trace.h>
-
-#include <asm/cacheflush.h>
 
 #include "fec.h"
 
@@ -131,7 +131,7 @@ static const struct fec_devinfo fec_mvf600_info = {
 		  FEC_QUIRK_HAS_MDIO_C45,
 };
 
-static const struct fec_devinfo fec_imx6x_info = {
+static const struct fec_devinfo fec_imx6sx_info = {
 	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
 		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
 		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
@@ -168,7 +168,8 @@ static const struct fec_devinfo fec_imx8qm_info = {
 		  FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
 		  FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE |
 		  FEC_QUIRK_CLEAR_SETUP_MII | FEC_QUIRK_HAS_MULTI_QUEUES |
-		  FEC_QUIRK_DELAYED_CLKS_SUPPORT | FEC_QUIRK_HAS_MDIO_C45,
+		  FEC_QUIRK_DELAYED_CLKS_SUPPORT | FEC_QUIRK_HAS_MDIO_C45 |
+		  FEC_QUIRK_JUMBO_FRAME,
 };
 
 static const struct fec_devinfo fec_s32v234_info = {
@@ -196,7 +197,7 @@ static const struct of_device_id fec_dt_ids[] = {
 	{ .compatible = "fsl,imx28-fec", .data = &fec_imx28_info, },
 	{ .compatible = "fsl,imx6q-fec", .data = &fec_imx6q_info, },
 	{ .compatible = "fsl,mvf600-fec", .data = &fec_mvf600_info, },
-	{ .compatible = "fsl,imx6sx-fec", .data = &fec_imx6x_info, },
+	{ .compatible = "fsl,imx6sx-fec", .data = &fec_imx6sx_info, },
 	{ .compatible = "fsl,imx6ul-fec", .data = &fec_imx6ul_info, },
 	{ .compatible = "fsl,imx8mq-fec", .data = &fec_imx8mq_info, },
 	{ .compatible = "fsl,imx8qm-fec", .data = &fec_imx8qm_info, },
@@ -234,6 +235,7 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
  * 2048 byte skbufs are allocated. However, alignment requirements
  * varies between FEC variants. Worst case is 64, so round down by 64.
  */
+#define MAX_JUMBO_BUF_SIZE	(round_down(16384 - FEC_DRV_RESERVE_SPACE - 64, 64))
 #define PKT_MAXBUF_SIZE		(round_down(2048 - 64, 64))
 #define PKT_MINBUF_SIZE		64
 
@@ -251,12 +253,10 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
  * size bits. Other FEC hardware does not, so we need to take that into
  * account when setting it.
  */
-#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
-    defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \
-    defined(CONFIG_ARM64)
-#define	OPT_FRAME_SIZE	(PKT_MAXBUF_SIZE << 16)
+#ifndef CONFIG_M5272
+#define	OPT_ARCH_HAS_MAX_FL	1
 #else
-#define	OPT_FRAME_SIZE	0
+#define	OPT_ARCH_HAS_MAX_FL	0
 #endif
 
 /* FEC MII MMFR bits definition */
@@ -276,16 +276,19 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 #define FEC_ECR_MAGICEN         BIT(2)
 #define FEC_ECR_SLEEP           BIT(3)
 #define FEC_ECR_EN1588          BIT(4)
+#define FEC_ECR_SPEED           BIT(5)
 #define FEC_ECR_BYTESWP         BIT(8)
 /* FEC RCR bits definition */
 #define FEC_RCR_LOOP            BIT(0)
-#define FEC_RCR_HALFDPX         BIT(1)
+#define FEC_RCR_DRT		BIT(1)
 #define FEC_RCR_MII             BIT(2)
 #define FEC_RCR_PROMISC         BIT(3)
 #define FEC_RCR_BC_REJ          BIT(4)
 #define FEC_RCR_FLOWCTL         BIT(5)
+#define FEC_RCR_RGMII		BIT(6)
 #define FEC_RCR_RMII            BIT(8)
 #define FEC_RCR_10BASET         BIT(9)
+#define FEC_RCR_NLC		BIT(30)
 /* TX WMARK bits */
 #define FEC_TXWMRK_STRFWD       BIT(8)
 
@@ -468,14 +471,14 @@ fec_enet_create_page_pool(struct fec_enet_private *fep,
 {
 	struct bpf_prog *xdp_prog = READ_ONCE(fep->xdp_prog);
 	struct page_pool_params pp_params = {
-		.order = 0,
+		.order = fep->pagepool_order,
 		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
 		.pool_size = size,
 		.nid = dev_to_node(&fep->pdev->dev),
 		.dev = &fep->pdev->dev,
 		.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE,
 		.offset = FEC_ENET_XDP_HEADROOM,
-		.max_len = FEC_ENET_RX_FRSIZE,
+		.max_len = fep->rx_frame_size,
 	};
 	int err;
 
@@ -714,7 +717,12 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 	txq->bd.cur = bdp;
 
 	/* Trigger transmission start */
-	writel(0, txq->bd.reg_desc_active);
+	if (!(fep->quirks & FEC_QUIRK_ERR007885) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active))
+		writel(0, txq->bd.reg_desc_active);
 
 	return 0;
 }
@@ -840,6 +848,8 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int hdr_len, total_len, data_left;
 	struct bufdesc *bdp = txq->bd.cur;
+	struct bufdesc *tmp_bdp;
+	struct bufdesc_ex *ebdp;
 	struct tso_t tso;
 	unsigned int index = 0;
 	int ret;
@@ -913,7 +923,34 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	return 0;
 
 err_release:
-	/* TODO: Release all used data descriptors for TSO */
+	/* Release all used data descriptors for TSO */
+	tmp_bdp = txq->bd.cur;
+
+	while (tmp_bdp != bdp) {
+		/* Unmap data buffers */
+		if (tmp_bdp->cbd_bufaddr &&
+		    !IS_TSO_HEADER(txq, fec32_to_cpu(tmp_bdp->cbd_bufaddr)))
+			dma_unmap_single(&fep->pdev->dev,
+					 fec32_to_cpu(tmp_bdp->cbd_bufaddr),
+					 fec16_to_cpu(tmp_bdp->cbd_datlen),
+					 DMA_TO_DEVICE);
+
+		/* Clear standard buffer descriptor fields */
+		tmp_bdp->cbd_sc = 0;
+		tmp_bdp->cbd_datlen = 0;
+		tmp_bdp->cbd_bufaddr = 0;
+
+		/* Handle extended descriptor if enabled */
+		if (fep->bufdesc_ex) {
+			ebdp = (struct bufdesc_ex *)tmp_bdp;
+			ebdp->cbd_esc = 0;
+		}
+
+		tmp_bdp = fec_enet_get_nextdesc(tmp_bdp, &txq->bd);
+	}
+
+	dev_kfree_skb_any(skb);
+
 	return ret;
 }
 
@@ -973,7 +1010,7 @@ static void fec_enet_bd_init(struct net_device *dev)
 
 		/* Set the last buffer to wrap */
 		bdp = fec_enet_get_prevdesc(bdp, &rxq->bd);
-		bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP);
+		bdp->cbd_sc |= cpu_to_fec16(BD_ENET_RX_WRAP);
 
 		rxq->bd.cur = rxq->bd.base;
 	}
@@ -1009,7 +1046,9 @@ static void fec_enet_bd_init(struct net_device *dev)
 				struct page *page = txq->tx_buf[i].buf_p;
 
 				if (page)
-					page_pool_put_page(page->pp, page, 0, false);
+					page_pool_put_page(pp_page_to_nmdesc(page)->pp,
+							   page, 0,
+							   false);
 			}
 
 			txq->tx_buf[i].buf_p = NULL;
@@ -1021,7 +1060,7 @@ static void fec_enet_bd_init(struct net_device *dev)
 
 		/* Set the last buffer to wrap */
 		bdp = fec_enet_get_prevdesc(bdp, &txq->bd);
-		bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP);
+		bdp->cbd_sc |= cpu_to_fec16(BD_ENET_TX_WRAP);
 		txq->dirty_tx = bdp;
 	}
 }
@@ -1045,7 +1084,7 @@ static void fec_enet_enable_ring(struct net_device *ndev)
 	for (i = 0; i < fep->num_rx_queues; i++) {
 		rxq = fep->rx_queue[i];
 		writel(rxq->bd.dma, fep->hwp + FEC_R_DES_START(i));
-		writel(PKT_MAXBUF_SIZE, fep->hwp + FEC_R_BUFF_SIZE(i));
+		writel(fep->max_buf_size, fep->hwp + FEC_R_BUFF_SIZE(i));
 
 		/* enable DMA1/2 */
 		if (i)
@@ -1064,6 +1103,40 @@ static void fec_enet_enable_ring(struct net_device *ndev)
 	}
 }
 
+/* Whack a reset.  We should wait for this.
+ * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
+ * instead of reset MAC itself.
+ */
+static void fec_ctrl_reset(struct fec_enet_private *fep, bool allow_wol)
+{
+	u32 val;
+
+	if (!allow_wol || !(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) {
+		if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES ||
+		    ((fep->quirks & FEC_QUIRK_NO_HARD_RESET) && fep->link)) {
+			writel(0, fep->hwp + FEC_ECNTRL);
+		} else {
+			writel(FEC_ECR_RESET, fep->hwp + FEC_ECNTRL);
+			udelay(10);
+		}
+	} else {
+		val = readl(fep->hwp + FEC_ECNTRL);
+		val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
+		writel(val, fep->hwp + FEC_ECNTRL);
+	}
+}
+
+static void fec_set_hw_mac_addr(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	writel(ndev->dev_addr[3] | (ndev->dev_addr[2] << 8) |
+	       (ndev->dev_addr[1] << 16) | (ndev->dev_addr[0] << 24),
+	       fep->hwp + FEC_ADDR_LOW);
+	writel((ndev->dev_addr[5] << 16) | (ndev->dev_addr[4] << 24),
+	       fep->hwp + FEC_ADDR_HIGH);
+}
+
 /*
  * This function is called to start or restart the FEC during a link
  * change, transmit timeout, or to reconfigure the FEC.  The network
@@ -1073,34 +1146,22 @@ static void
 fec_restart(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	u32 temp_mac[2];
-	u32 rcntl = OPT_FRAME_SIZE | 0x04;
 	u32 ecntl = FEC_ECR_ETHEREN;
+	u32 rcntl = FEC_RCR_MII;
+
+	if (OPT_ARCH_HAS_MAX_FL)
+		rcntl |= (fep->netdev->mtu + ETH_HLEN + ETH_FCS_LEN) << 16;
 
 	if (fep->bufdesc_ex)
 		fec_ptp_save_state(fep);
 
-	/* Whack a reset.  We should wait for this.
-	 * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
-	 * instead of reset MAC itself.
-	 */
-	if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES ||
-	    ((fep->quirks & FEC_QUIRK_NO_HARD_RESET) && fep->link)) {
-		writel(0, fep->hwp + FEC_ECNTRL);
-	} else {
-		writel(1, fep->hwp + FEC_ECNTRL);
-		udelay(10);
-	}
+	fec_ctrl_reset(fep, false);
 
 	/*
 	 * enet-mac reset will reset mac address registers too,
 	 * so need to reconfigure it.
 	 */
-	memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN);
-	writel((__force u32)cpu_to_be32(temp_mac[0]),
-	       fep->hwp + FEC_ADDR_LOW);
-	writel((__force u32)cpu_to_be32(temp_mac[1]),
-	       fep->hwp + FEC_ADDR_HIGH);
+	fec_set_hw_mac_addr(ndev);
 
 	/* Clear any outstanding interrupt, except MDIO. */
 	writel((0xffffffff & ~FEC_ENET_MII), fep->hwp + FEC_IEVENT);
@@ -1115,7 +1176,7 @@ fec_restart(struct net_device *ndev)
 		writel(0x04, fep->hwp + FEC_X_CNTRL);
 	} else {
 		/* No Rcv on Xmit */
-		rcntl |= 0x02;
+		rcntl |= FEC_RCR_DRT;
 		writel(0x0, fep->hwp + FEC_X_CNTRL);
 	}
 
@@ -1134,7 +1195,7 @@ fec_restart(struct net_device *ndev)
 		else
 			val &= ~FEC_RACC_OPTIONS;
 		writel(val, fep->hwp + FEC_RACC);
-		writel(PKT_MAXBUF_SIZE, fep->hwp + FEC_FTRL);
+		writel(min(fep->rx_frame_size, fep->max_buf_size), fep->hwp + FEC_FTRL);
 	}
 #endif
 
@@ -1144,14 +1205,11 @@ fec_restart(struct net_device *ndev)
 	 */
 	if (fep->quirks & FEC_QUIRK_ENET_MAC) {
 		/* Enable flow control and length check */
-		rcntl |= 0x40000000 | 0x00000020;
+		rcntl |= FEC_RCR_NLC | FEC_RCR_FLOWCTL;
 
 		/* RGMII, RMII or MII */
-		if (fep->phy_interface == PHY_INTERFACE_MODE_RGMII ||
-		    fep->phy_interface == PHY_INTERFACE_MODE_RGMII_ID ||
-		    fep->phy_interface == PHY_INTERFACE_MODE_RGMII_RXID ||
-		    fep->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID)
-			rcntl |= (1 << 6);
+		if (phy_interface_mode_is_rgmii(fep->phy_interface))
+			rcntl |= FEC_RCR_RGMII;
 		else if (fep->phy_interface == PHY_INTERFACE_MODE_RMII)
 			rcntl |= FEC_RCR_RMII;
 		else
@@ -1160,7 +1218,7 @@ fec_restart(struct net_device *ndev)
 		/* 1G, 100M or 10M */
 		if (ndev->phydev) {
 			if (ndev->phydev->speed == SPEED_1000)
-				ecntl |= (1 << 5);
+				ecntl |= FEC_ECR_SPEED;
 			else if (ndev->phydev->speed == SPEED_100)
 				rcntl &= ~FEC_RCR_10BASET;
 			else
@@ -1224,8 +1282,18 @@ fec_restart(struct net_device *ndev)
 	if (fep->quirks & FEC_QUIRK_ENET_MAC) {
 		/* enable ENET endian swap */
 		ecntl |= FEC_ECR_BYTESWP;
-		/* enable ENET store and forward mode */
-		writel(FEC_TXWMRK_STRFWD, fep->hwp + FEC_X_WMRK);
+
+		/* When Jumbo Frame is enabled, the FIFO may not be large enough
+		 * to hold an entire frame. In such cases, if the MTU exceeds
+		 * (PKT_MAXBUF_SIZE - ETH_HLEN - ETH_FCS_LEN), configure the interface
+		 * to operate in cut-through mode, triggered by the FIFO threshold.
+		 * Otherwise, enable the ENET store-and-forward mode.
+		 */
+		if ((fep->quirks & FEC_QUIRK_JUMBO_FRAME) &&
+		    (ndev->mtu > (PKT_MAXBUF_SIZE - ETH_HLEN - ETH_FCS_LEN)))
+			writel(0xF, fep->hwp + FEC_X_WMRK);
+		else
+			writel(FEC_TXWMRK_STRFWD, fep->hwp + FEC_X_WMRK);
 	}
 
 	if (fep->bufdesc_ex)
@@ -1344,22 +1412,7 @@ fec_stop(struct net_device *ndev)
 	if (fep->bufdesc_ex)
 		fec_ptp_save_state(fep);
 
-	/* Whack a reset.  We should wait for this.
-	 * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
-	 * instead of reset MAC itself.
-	 */
-	if (!(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) {
-		if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES) {
-			writel(0, fep->hwp + FEC_ECNTRL);
-		} else {
-			writel(FEC_ECR_RESET, fep->hwp + FEC_ECNTRL);
-			udelay(10);
-		}
-	} else {
-		val = readl(fep->hwp + FEC_ECNTRL);
-		val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
-		writel(val, fep->hwp + FEC_ECNTRL);
-	}
+	fec_ctrl_reset(fep, true);
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 	writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
 
@@ -1549,7 +1602,8 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget)
 			xdp_return_frame_rx_napi(xdpf);
 		} else { /* recycle pages of XDP_TX frames */
 			/* The dma_sync_size = 0 as XDP_TX has already synced DMA for_device */
-			page_pool_put_page(page->pp, page, 0, true);
+			page_pool_put_page(pp_page_to_nmdesc(page)->pp, page,
+					   0, true);
 		}
 
 		txq->tx_buf[index].buf_p = NULL;
@@ -1591,19 +1645,21 @@ static void fec_enet_tx(struct net_device *ndev, int budget)
 		fec_enet_tx_queue(ndev, i, budget);
 }
 
-static void fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq,
+static int fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq,
 				struct bufdesc *bdp, int index)
 {
 	struct page *new_page;
 	dma_addr_t phys_addr;
 
 	new_page = page_pool_dev_alloc_pages(rxq->page_pool);
-	WARN_ON(!new_page);
-	rxq->rx_skb_info[index].page = new_page;
+	if (unlikely(!new_page))
+		return -ENOMEM;
 
-	rxq->rx_skb_info[index].offset = FEC_ENET_XDP_HEADROOM;
+	rxq->rx_buf[index] = new_page;
 	phys_addr = page_pool_get_dma_addr(new_page) + FEC_ENET_XDP_HEADROOM;
 	bdp->cbd_bufaddr = cpu_to_fec32(phys_addr);
+
+	return 0;
 }
 
 static u32
@@ -1671,13 +1727,29 @@ xdp_err:
 	return ret;
 }
 
+static void fec_enet_rx_vlan(const struct net_device *ndev, struct sk_buff *skb)
+{
+	if (ndev->features & NETIF_F_HW_VLAN_CTAG_RX) {
+		const struct vlan_ethhdr *vlan_header = skb_vlan_eth_hdr(skb);
+		const u16 vlan_tag = ntohs(vlan_header->h_vlan_TCI);
+
+		/* Push and remove the vlan tag */
+
+		memmove(skb->data + VLAN_HLEN, skb->data, ETH_ALEN * 2);
+		skb_pull(skb, VLAN_HLEN);
+		__vlan_hwaccel_put_tag(skb,
+				       htons(ETH_P_8021Q),
+				       vlan_tag);
+	}
+}
+
 /* During a receive, the bd_rx.cur points to the current incoming buffer.
  * When we update through the ring, if the next incoming buffer has
  * not been given to the system, we just set the empty indicator,
  * effectively tossing the packet.
  */
 static int
-fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
+fec_enet_rx_queue(struct net_device *ndev, u16 queue_id, int budget)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	struct fec_enet_priv_rx_q *rxq;
@@ -1685,11 +1757,8 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 	unsigned short status;
 	struct  sk_buff *skb;
 	ushort	pkt_len;
-	__u8 *data;
 	int	pkt_received = 0;
 	struct	bufdesc_ex *ebdp = NULL;
-	bool	vlan_packet_rcvd = false;
-	u16	vlan_tag;
 	int	index = 0;
 	bool	need_swap = fep->quirks & FEC_QUIRK_SWAP_FRAME;
 	struct bpf_prog *xdp_prog = READ_ONCE(fep->xdp_prog);
@@ -1698,9 +1767,9 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 	int cpu = smp_processor_id();
 	struct xdp_buff xdp;
 	struct page *page;
+	__fec32 cbd_bufaddr;
 	u32 sub_len = 4;
 
-#if !defined(CONFIG_M5272)
 	/*If it has the FEC_QUIRK_HAS_RACC quirk property, the bit of
 	 * FEC_RACC_SHIFT16 is set by default in the probe function.
 	 */
@@ -1708,7 +1777,6 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 		data_start += 2;
 		sub_len += 2;
 	}
-#endif
 
 #if defined(CONFIG_COLDFIRE) && !defined(CONFIG_COLDFIRE_COHERENT_DMA)
 	/*
@@ -1723,7 +1791,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 	 * These get messed up if we get called due to a busy condition.
 	 */
 	bdp = rxq->bd.cur;
-	xdp_init_buff(&xdp, PAGE_SIZE, &rxq->xdp_rxq);
+	xdp_init_buff(&xdp, PAGE_SIZE << fep->pagepool_order, &rxq->xdp_rxq);
 
 	while (!((status = fec16_to_cpu(bdp->cbd_sc)) & BD_ENET_RX_EMPTY)) {
 
@@ -1763,15 +1831,22 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 		ndev->stats.rx_packets++;
 		pkt_len = fec16_to_cpu(bdp->cbd_datlen);
 		ndev->stats.rx_bytes += pkt_len;
+		if (fep->quirks & FEC_QUIRK_HAS_RACC)
+			ndev->stats.rx_bytes -= 2;
 
 		index = fec_enet_get_bd_index(bdp, &rxq->bd);
-		page = rxq->rx_skb_info[index].page;
+		page = rxq->rx_buf[index];
+		cbd_bufaddr = bdp->cbd_bufaddr;
+		if (fec_enet_update_cbd(rxq, bdp, index)) {
+			ndev->stats.rx_dropped++;
+			goto rx_processing_done;
+		}
+
 		dma_sync_single_for_cpu(&fep->pdev->dev,
-					fec32_to_cpu(bdp->cbd_bufaddr),
+					fec32_to_cpu(cbd_bufaddr),
 					pkt_len,
 					DMA_FROM_DEVICE);
 		prefetch(page_address(page));
-		fec_enet_update_cbd(rxq, bdp, index);
 
 		if (xdp_prog) {
 			xdp_buff_clear_frags_flag(&xdp);
@@ -1788,7 +1863,8 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 		 * include that when passing upstream as it messes up
 		 * bridging applications.
 		 */
-		skb = build_skb(page_address(page), PAGE_SIZE);
+		skb = build_skb(page_address(page),
+				PAGE_SIZE << fep->pagepool_order);
 		if (unlikely(!skb)) {
 			page_pool_recycle_direct(rxq->page_pool, page);
 			ndev->stats.rx_dropped++;
@@ -1802,10 +1878,11 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 		skb_mark_for_recycle(skb);
 
 		if (unlikely(need_swap)) {
+			u8 *data;
+
 			data = page_address(page) + FEC_ENET_XDP_HEADROOM;
 			swap_buffer(data, pkt_len);
 		}
-		data = skb->data;
 
 		/* Extract the enhanced buffer descriptor */
 		ebdp = NULL;
@@ -1813,20 +1890,9 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 			ebdp = (struct bufdesc_ex *)bdp;
 
 		/* If this is a VLAN packet remove the VLAN Tag */
-		vlan_packet_rcvd = false;
-		if ((ndev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
-		    fep->bufdesc_ex &&
-		    (ebdp->cbd_esc & cpu_to_fec32(BD_ENET_RX_VLAN))) {
-			/* Push and remove the vlan tag */
-			struct vlan_hdr *vlan_header =
-					(struct vlan_hdr *) (data + ETH_HLEN);
-			vlan_tag = ntohs(vlan_header->h_vlan_TCI);
-
-			vlan_packet_rcvd = true;
-
-			memmove(skb->data + VLAN_HLEN, data, ETH_ALEN * 2);
-			skb_pull(skb, VLAN_HLEN);
-		}
+		if (fep->bufdesc_ex &&
+		    (ebdp->cbd_esc & cpu_to_fec32(BD_ENET_RX_VLAN)))
+			fec_enet_rx_vlan(ndev, skb);
 
 		skb->protocol = eth_type_trans(skb, ndev);
 
@@ -1845,12 +1911,6 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 			}
 		}
 
-		/* Handle received VLAN packets */
-		if (vlan_packet_rcvd)
-			__vlan_hwaccel_put_tag(skb,
-					       htons(ETH_P_8021Q),
-					       vlan_tag);
-
 		skb_record_rx_queue(skb, queue_id);
 		napi_gro_receive(&fep->napi, skb);
 
@@ -1898,7 +1958,7 @@ static int fec_enet_rx(struct net_device *ndev, int budget)
 
 	/* Make sure that AVB queues are processed first. */
 	for (i = fep->num_rx_queues - 1; i >= 0; i--)
-		done += fec_enet_rx_queue(ndev, budget - done, i);
+		done += fec_enet_rx_queue(ndev, i, budget - done);
 
 	return done;
 }
@@ -2169,7 +2229,6 @@ static int fec_enet_mdio_read_c22(struct mii_bus *bus, int mii_id, int regnum)
 	ret = FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
 
 out:
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return ret;
@@ -2218,7 +2277,6 @@ static int fec_enet_mdio_read_c45(struct mii_bus *bus, int mii_id,
 	ret = FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
 
 out:
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return ret;
@@ -2250,7 +2308,6 @@ static int fec_enet_mdio_write_c22(struct mii_bus *bus, int mii_id, int regnum,
 	if (ret)
 		netdev_err(fep->netdev, "MDIO write timeout\n");
 
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return ret;
@@ -2294,7 +2351,6 @@ static int fec_enet_mdio_write_c45(struct mii_bus *bus, int mii_id,
 		netdev_err(fep->netdev, "MDIO write timeout\n");
 
 out:
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return ret;
@@ -2317,7 +2373,8 @@ static void fec_enet_phy_reset_after_clk_enable(struct net_device *ndev)
 		 */
 		phy_dev = of_phy_find_device(fep->phy_node);
 		phy_reset_after_clk_enable(phy_dev);
-		put_device(&phy_dev->mdio.dev);
+		if (phy_dev)
+			put_device(&phy_dev->mdio.dev);
 	}
 }
 
@@ -2413,11 +2470,8 @@ static int fec_enet_parse_rgmii_delay(struct fec_enet_private *fep,
 static int fec_enet_mii_probe(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct phy_device *phy_dev = NULL;
-	char mdio_bus_id[MII_BUS_ID_SIZE];
-	char phy_name[MII_BUS_ID_SIZE + 3];
-	int phy_id;
-	int dev_id = fep->dev_id;
+	struct phy_device *phy_dev;
+	int ret;
 
 	if (fep->phy_node) {
 		phy_dev = of_phy_connect(ndev, fep->phy_node,
@@ -2429,30 +2483,28 @@ static int fec_enet_mii_probe(struct net_device *ndev)
 		}
 	} else {
 		/* check for attached phy */
-		for (phy_id = 0; (phy_id < PHY_MAX_ADDR); phy_id++) {
-			if (!mdiobus_is_registered_device(fep->mii_bus, phy_id))
-				continue;
-			if (dev_id--)
-				continue;
-			strscpy(mdio_bus_id, fep->mii_bus->id, MII_BUS_ID_SIZE);
-			break;
-		}
+		phy_dev = phy_find_first(fep->mii_bus);
+		if (fep->dev_id && phy_dev)
+			phy_dev = phy_find_next(fep->mii_bus, phy_dev);
 
-		if (phy_id >= PHY_MAX_ADDR) {
+		if (!phy_dev) {
 			netdev_info(ndev, "no PHY, assuming direct connection to switch\n");
-			strscpy(mdio_bus_id, "fixed-0", MII_BUS_ID_SIZE);
-			phy_id = 0;
+			phy_dev = fixed_phy_register_100fd();
+			if (IS_ERR(phy_dev)) {
+				netdev_err(ndev, "could not register fixed PHY\n");
+				return PTR_ERR(phy_dev);
+			}
 		}
 
-		snprintf(phy_name, sizeof(phy_name),
-			 PHY_ID_FMT, mdio_bus_id, phy_id);
-		phy_dev = phy_connect(ndev, phy_name, &fec_enet_adjust_link,
-				      fep->phy_interface);
-	}
+		ret = phy_connect_direct(ndev, phy_dev, &fec_enet_adjust_link,
+					 fep->phy_interface);
+		if (ret) {
+			if (phy_is_pseudo_fixed_link(phy_dev))
+				fixed_phy_unregister(phy_dev);
+			netdev_err(ndev, "could not attach to PHY\n");
+			return ret;
+		}
 
-	if (IS_ERR(phy_dev)) {
-		netdev_err(ndev, "could not attach to PHY\n");
-		return PTR_ERR(phy_dev);
 	}
 
 	/* mask with MAC supported features */
@@ -2460,9 +2512,7 @@ static int fec_enet_mii_probe(struct net_device *ndev)
 		phy_set_max_speed(phy_dev, 1000);
 		phy_remove_link_mode(phy_dev,
 				     ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
-#if !defined(CONFIG_M5272)
 		phy_support_sym_pause(phy_dev);
-#endif
 	}
 	else
 		phy_set_max_speed(phy_dev, 100);
@@ -2489,7 +2539,6 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	int err = -ENXIO;
 	u32 mii_speed, holdtime;
 	u32 bus_freq;
-	int addr;
 
 	/*
 	 * The i.MX28 dual fec interfaces are not equal.
@@ -2604,11 +2653,8 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	of_node_put(node);
 
 	/* find all the PHY devices on the bus and set mac_managed_pm to true */
-	for (addr = 0; addr < PHY_MAX_ADDR; addr++) {
-		phydev = mdiobus_get_phy(fep->mii_bus, addr);
-		if (phydev)
-			phydev->mac_managed_pm = true;
-	}
+	mdiobus_for_each_phy(fep->mii_bus, phydev)
+		phydev->mac_managed_pm = true;
 
 	mii_cnt++;
 
@@ -2657,9 +2703,7 @@ static int fec_enet_get_regs_len(struct net_device *ndev)
 }
 
 /* List of registers that can be safety be read to dump them with ethtool */
-#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
-	defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \
-	defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST)
+#if !defined(CONFIG_M5272) || defined(CONFIG_COMPILE_TEST)
 static __u32 fec_enet_register_version = 2;
 static u32 fec_enet_register_offset[] = {
 	FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0,
@@ -2733,30 +2777,22 @@ static u32 fec_enet_register_offset[] = {
 static void fec_enet_get_regs(struct net_device *ndev,
 			      struct ethtool_regs *regs, void *regbuf)
 {
+	u32 reg_cnt = ARRAY_SIZE(fec_enet_register_offset);
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	u32 __iomem *theregs = (u32 __iomem *)fep->hwp;
+	u32 *reg_list = fec_enet_register_offset;
 	struct device *dev = &fep->pdev->dev;
 	u32 *buf = (u32 *)regbuf;
 	u32 i, off;
 	int ret;
-#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
-	defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \
-	defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST)
-	u32 *reg_list;
-	u32 reg_cnt;
-
-	if (!of_machine_is_compatible("fsl,imx6ul")) {
-		reg_list = fec_enet_register_offset;
-		reg_cnt = ARRAY_SIZE(fec_enet_register_offset);
-	} else {
+
+#if !defined(CONFIG_M5272) || defined(CONFIG_COMPILE_TEST)
+	if (of_machine_is_compatible("fsl,imx6ul")) {
 		reg_list = fec_enet_register_offset_6ul;
 		reg_cnt = ARRAY_SIZE(fec_enet_register_offset_6ul);
 	}
-#else
-	/* coldfire */
-	static u32 *reg_list = fec_enet_register_offset;
-	static const u32 reg_cnt = ARRAY_SIZE(fec_enet_register_offset);
 #endif
+
 	ret = pm_runtime_resume_and_get(dev);
 	if (ret < 0)
 		return;
@@ -2776,7 +2812,6 @@ static void fec_enet_get_regs(struct net_device *ndev,
 		buf[off] = readl(&theregs[off]);
 	}
 
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 }
 
@@ -3083,27 +3118,25 @@ static int fec_enet_us_to_itr_clock(struct net_device *ndev, int us)
 static void fec_enet_itr_coal_set(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	int rx_itr, tx_itr;
-
-	/* Must be greater than zero to avoid unpredictable behavior */
-	if (!fep->rx_time_itr || !fep->rx_pkts_itr ||
-	    !fep->tx_time_itr || !fep->tx_pkts_itr)
-		return;
+	u32 rx_itr = 0, tx_itr = 0;
+	int rx_ictt, tx_ictt;
 
-	/* Select enet system clock as Interrupt Coalescing
-	 * timer Clock Source
-	 */
-	rx_itr = FEC_ITR_CLK_SEL;
-	tx_itr = FEC_ITR_CLK_SEL;
+	rx_ictt = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr);
+	tx_ictt = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr);
 
-	/* set ICFT and ICTT */
-	rx_itr |= FEC_ITR_ICFT(fep->rx_pkts_itr);
-	rx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr));
-	tx_itr |= FEC_ITR_ICFT(fep->tx_pkts_itr);
-	tx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr));
+	if (rx_ictt > 0 && fep->rx_pkts_itr > 1) {
+		/* Enable with enet system clock as Interrupt Coalescing timer Clock Source */
+		rx_itr = FEC_ITR_EN | FEC_ITR_CLK_SEL;
+		rx_itr |= FEC_ITR_ICFT(fep->rx_pkts_itr);
+		rx_itr |= FEC_ITR_ICTT(rx_ictt);
+	}
 
-	rx_itr |= FEC_ITR_EN;
-	tx_itr |= FEC_ITR_EN;
+	if (tx_ictt > 0 && fep->tx_pkts_itr > 1) {
+		/* Enable with enet system clock as Interrupt Coalescing timer Clock Source */
+		tx_itr = FEC_ITR_EN | FEC_ITR_CLK_SEL;
+		tx_itr |= FEC_ITR_ICFT(fep->tx_pkts_itr);
+		tx_itr |= FEC_ITR_ICTT(tx_ictt);
+	}
 
 	writel(tx_itr, fep->hwp + FEC_TXIC0);
 	writel(rx_itr, fep->hwp + FEC_RXIC0);
@@ -3278,7 +3311,8 @@ static void fec_enet_free_buffers(struct net_device *ndev)
 	for (q = 0; q < fep->num_rx_queues; q++) {
 		rxq = fep->rx_queue[q];
 		for (i = 0; i < rxq->bd.ring_size; i++)
-			page_pool_put_full_page(rxq->page_pool, rxq->rx_skb_info[i].page, false);
+			page_pool_put_full_page(rxq->page_pool, rxq->rx_buf[i],
+						false);
 
 		for (i = 0; i < XDP_STATS_TOTAL; i++)
 			rxq->stats[i] = 0;
@@ -3307,7 +3341,8 @@ static void fec_enet_free_buffers(struct net_device *ndev)
 			} else {
 				struct page *page = txq->tx_buf[i].buf_p;
 
-				page_pool_put_page(page->pp, page, 0, false);
+				page_pool_put_page(pp_page_to_nmdesc(page)->pp,
+						   page, 0, false);
 			}
 
 			txq->tx_buf[i].buf_p = NULL;
@@ -3403,6 +3438,19 @@ fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue)
 		return err;
 	}
 
+	/* Some platforms require the RX buffer must be 64 bytes alignment.
+	 * Some platforms require 16 bytes alignment. And some platforms
+	 * require 4 bytes alignment. But since the page pool have been
+	 * introduced into the driver, the address of RX buffer is always
+	 * the page address plus FEC_ENET_XDP_HEADROOM, and
+	 * FEC_ENET_XDP_HEADROOM is 256 bytes. Therefore, this address can
+	 * satisfy all platforms. To prevent future modifications to
+	 * FEC_ENET_XDP_HEADROOM from ignoring this hardware limitation, a
+	 * BUILD_BUG_ON() test has been added, which ensures that
+	 * FEC_ENET_XDP_HEADROOM provides the required alignment.
+	 */
+	BUILD_BUG_ON(FEC_ENET_XDP_HEADROOM & 0x3f);
+
 	for (i = 0; i < rxq->bd.ring_size; i++) {
 		page = page_pool_dev_alloc_pages(rxq->page_pool);
 		if (!page)
@@ -3411,8 +3459,7 @@ fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue)
 		phys_addr = page_pool_get_dma_addr(page) + FEC_ENET_XDP_HEADROOM;
 		bdp->cbd_bufaddr = cpu_to_fec32(phys_addr);
 
-		rxq->rx_skb_info[i].page = page;
-		rxq->rx_skb_info[i].offset = FEC_ENET_XDP_HEADROOM;
+		rxq->rx_buf[i] = page;
 		bdp->cbd_sc = cpu_to_fec16(BD_ENET_RX_EMPTY);
 
 		if (fep->bufdesc_ex) {
@@ -3425,7 +3472,7 @@ fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue)
 
 	/* Set the last buffer to wrap. */
 	bdp = fec_enet_get_prevdesc(bdp, &rxq->bd);
-	bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP);
+	bdp->cbd_sc |= cpu_to_fec16(BD_ENET_RX_WRAP);
 	return 0;
 
  err_alloc:
@@ -3461,7 +3508,7 @@ fec_enet_alloc_txq_buffers(struct net_device *ndev, unsigned int queue)
 
 	/* Set the last buffer to wrap. */
 	bdp = fec_enet_get_prevdesc(bdp, &txq->bd);
-	bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP);
+	bdp->cbd_sc |= cpu_to_fec16(BD_ENET_TX_WRAP);
 
 	return 0;
 
@@ -3554,7 +3601,6 @@ err_enet_mii_probe:
 err_enet_alloc:
 	fec_enet_clk_enable(ndev, false);
 clk_enable:
-	pm_runtime_mark_last_busy(&fep->pdev->dev);
 	pm_runtime_put_autosuspend(&fep->pdev->dev);
 	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
 	return ret;
@@ -3564,8 +3610,9 @@ static int
 fec_enet_close(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
+	struct phy_device *phy_dev = ndev->phydev;
 
-	phy_stop(ndev->phydev);
+	phy_stop(phy_dev);
 
 	if (netif_device_present(ndev)) {
 		napi_disable(&fep->napi);
@@ -3573,7 +3620,10 @@ fec_enet_close(struct net_device *ndev)
 		fec_stop(ndev);
 	}
 
-	phy_disconnect(ndev->phydev);
+	phy_disconnect(phy_dev);
+
+	if (!fep->phy_node && phy_is_pseudo_fixed_link(phy_dev))
+		fixed_phy_unregister(phy_dev);
 
 	if (fep->quirks & FEC_QUIRK_ERR006687)
 		imx6q_cpuidle_fec_irqs_unused();
@@ -3585,7 +3635,6 @@ fec_enet_close(struct net_device *ndev)
 		cpu_latency_qos_remove_request(&fep->pm_qos_req);
 
 	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
-	pm_runtime_mark_last_busy(&fep->pdev->dev);
 	pm_runtime_put_autosuspend(&fep->pdev->dev);
 
 	fec_enet_free_buffers(ndev);
@@ -3658,7 +3707,6 @@ static void set_multicast_list(struct net_device *ndev)
 static int
 fec_set_mac_address(struct net_device *ndev, void *p)
 {
-	struct fec_enet_private *fep = netdev_priv(ndev);
 	struct sockaddr *addr = p;
 
 	if (addr) {
@@ -3675,11 +3723,8 @@ fec_set_mac_address(struct net_device *ndev, void *p)
 	if (!netif_running(ndev))
 		return 0;
 
-	writel(ndev->dev_addr[3] | (ndev->dev_addr[2] << 8) |
-		(ndev->dev_addr[1] << 16) | (ndev->dev_addr[0] << 24),
-		fep->hwp + FEC_ADDR_LOW);
-	writel((ndev->dev_addr[5] << 16) | (ndev->dev_addr[4] << 24),
-		fep->hwp + FEC_ADDR_HIGH);
+	fec_set_hw_mac_addr(ndev);
+
 	return 0;
 }
 
@@ -3979,6 +4024,23 @@ static int fec_hwtstamp_set(struct net_device *ndev,
 	return fec_ptp_set(ndev, config, extack);
 }
 
+static int fec_change_mtu(struct net_device *ndev, int new_mtu)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	int order;
+
+	if (netif_running(ndev))
+		return -EBUSY;
+
+	order = get_order(new_mtu + ETH_HLEN + ETH_FCS_LEN
+			  + FEC_DRV_RESERVE_SPACE);
+	fep->rx_frame_size = (PAGE_SIZE << order) - FEC_DRV_RESERVE_SPACE;
+	fep->pagepool_order = order;
+	WRITE_ONCE(ndev->mtu, new_mtu);
+
+	return 0;
+}
+
 static const struct net_device_ops fec_netdev_ops = {
 	.ndo_open		= fec_enet_open,
 	.ndo_stop		= fec_enet_close,
@@ -3988,6 +4050,7 @@ static const struct net_device_ops fec_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_tx_timeout		= fec_timeout,
 	.ndo_set_mac_address	= fec_set_mac_address,
+	.ndo_change_mtu		= fec_change_mtu,
 	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_set_features	= fec_set_features,
 	.ndo_bpf		= fec_enet_bpf,
@@ -4022,10 +4085,8 @@ static int fec_enet_init(struct net_device *ndev)
 
 	WARN_ON(dsize != (1 << dsize_log2));
 #if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
-	fep->rx_align = 0xf;
 	fep->tx_align = 0xf;
 #else
-	fep->rx_align = 0x3;
 	fep->tx_align = 0x3;
 #endif
 	fep->rx_pkts_itr = FEC_ITR_ICFT_DEFAULT;
@@ -4114,10 +4175,8 @@ static int fec_enet_init(struct net_device *ndev)
 		fep->csum_flags |= FLAG_RX_CSUM_ENABLED;
 	}
 
-	if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES) {
+	if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES)
 		fep->tx_align = 0;
-		fep->rx_align = 0x3f;
-	}
 
 	ndev->hw_features = ndev->features;
 
@@ -4335,11 +4394,9 @@ fec_probe(struct platform_device *pdev)
 	fep->num_rx_queues = num_rx_qs;
 	fep->num_tx_queues = num_tx_qs;
 
-#if !defined(CONFIG_M5272)
 	/* default enable pause frame auto negotiation */
 	if (fep->quirks & FEC_QUIRK_HAS_GBIT)
 		fep->pause_flag |= FEC_PAUSE_FLAG_AUTONEG;
-#endif
 
 	/* Select default pin state */
 	pinctrl_pm_select_default_state(&pdev->dev);
@@ -4518,7 +4575,15 @@ fec_probe(struct platform_device *pdev)
 	fec_enet_clk_enable(ndev, false);
 	pinctrl_pm_select_sleep_state(&pdev->dev);
 
-	ndev->max_mtu = PKT_MAXBUF_SIZE - ETH_HLEN - ETH_FCS_LEN;
+	fep->pagepool_order = 0;
+	fep->rx_frame_size = FEC_ENET_RX_FRSIZE;
+
+	if (fep->quirks & FEC_QUIRK_JUMBO_FRAME)
+		fep->max_buf_size = MAX_JUMBO_BUF_SIZE;
+	else
+		fep->max_buf_size = PKT_MAXBUF_SIZE;
+
+	ndev->max_mtu = fep->max_buf_size - ETH_HLEN - ETH_FCS_LEN;
 
 	ret = register_netdev(ndev);
 	if (ret)
@@ -4532,7 +4597,6 @@ fec_probe(struct platform_device *pdev)
 
 	INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work);
 
-	pm_runtime_mark_last_busy(&pdev->dev);
 	pm_runtime_put_autosuspend(&pdev->dev);
 
 	return 0;
diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c
index 2bfaf14f65c8..3fc29afc9854 100644
--- a/drivers/net/ethernet/freescale/fec_mpc52xx.c
+++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c
@@ -619,7 +619,7 @@ static void mpc52xx_fec_hw_init(struct net_device *dev)
 	out_be32(&fec->rfifo_alarm, 0x0000030c);
 	out_be32(&fec->tfifo_alarm, 0x00000100);
 
-	/* begin transmittion when 256 bytes are in FIFO (or EOF or FIFO full) */
+	/* begin transmission when 256 bytes are in FIFO (or EOF or FIFO full) */
 	out_be32(&fec->x_wmrk, FEC_FIFO_WMRK_256B);
 
 	/* enable crc generation */
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 7f6b57432071..4b7bad9a485d 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -7,31 +7,30 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/ptrace.h>
-#include <linux/errno.h>
-#include <linux/ioport.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/pci.h>
+#include <linux/bitops.h>
+#include <linux/clk.h>
 #include <linux/delay.h>
-#include <linux/netdevice.h>
+#include <linux/errno.h>
 #include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/spinlock.h>
-#include <linux/workqueue.h>
-#include <linux/bitops.h>
+#include <linux/fec.h>
+#include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/ioport.h>
 #include <linux/irq.h>
-#include <linux/clk.h>
-#include <linux/platform_device.h>
-#include <linux/phy.h>
-#include <linux/fec.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/of_net.h>
+#include <linux/pci.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/ptrace.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/workqueue.h>
 
 #include "fec.h"
 
@@ -97,7 +96,7 @@
  * cyclecounter structure used to construct a ns counter from the
  * arbitrary fixed point registers
  */
-static u64 fec_ptp_read(const struct cyclecounter *cc)
+static u64 fec_ptp_read(struct cyclecounter *cc)
 {
 	struct fec_enet_private *fep =
 		container_of(cc, struct fec_enet_private, cc);
@@ -118,7 +117,7 @@ static u64 fec_ptp_read(const struct cyclecounter *cc)
  * @fep: the fec_enet_private structure handle
  * @enable: enable the channel pps output
  *
- * This function enble the PPS ouput on the timer channel.
+ * This function enables the PPS output on the timer channel.
  */
 static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 {
@@ -129,6 +128,12 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 
 	spin_lock_irqsave(&fep->tmreg_lock, flags);
 
+	if (fep->perout_enable) {
+		spin_unlock_irqrestore(&fep->tmreg_lock, flags);
+		dev_err(&fep->pdev->dev, "PEROUT is running");
+		return -EBUSY;
+	}
+
 	if (fep->pps_enable == enable) {
 		spin_unlock_irqrestore(&fep->tmreg_lock, flags);
 		return 0;
@@ -173,7 +178,7 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 		 * very close to the second point, which means NSEC_PER_SEC
 		 * - ts.tv_nsec is close to be zero(For example 20ns); Since the timer
 		 * is still running when we calculate the first compare event, it is
-		 * possible that the remaining nanoseonds run out before the compare
+		 * possible that the remaining nanoseconds run out before the compare
 		 * counter is calculated and written into TCCR register. To avoid
 		 * this possibility, we will set the compare event to be the next
 		 * of next second. The current setting is 31-bit timer and wrap
@@ -244,6 +249,7 @@ static int fec_ptp_pps_perout(struct fec_enet_private *fep)
 	 * the FEC_TCCR register in time and missed the start time.
 	 */
 	if (fep->perout_stime < curr_time + 100 * NSEC_PER_MSEC) {
+		fep->perout_enable = false;
 		dev_err(&fep->pdev->dev, "Current time is too close to the start time!\n");
 		spin_unlock_irqrestore(&fep->tmreg_lock, flags);
 		return -1;
@@ -498,7 +504,10 @@ static int fec_ptp_pps_disable(struct fec_enet_private *fep, uint channel)
 {
 	unsigned long flags;
 
+	hrtimer_cancel(&fep->perout_timer);
+
 	spin_lock_irqsave(&fep->tmreg_lock, flags);
+	fep->perout_enable = false;
 	writel(0, fep->hwp + FEC_TCSR(channel));
 	spin_unlock_irqrestore(&fep->tmreg_lock, flags);
 
@@ -530,6 +539,8 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp,
 
 		return ret;
 	} else if (rq->type == PTP_CLK_REQ_PEROUT) {
+		u32 reload_period;
+
 		/* Reject requests with unsupported flags */
 		if (rq->perout.flags)
 			return -EOPNOTSUPP;
@@ -549,12 +560,14 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp,
 			return -EOPNOTSUPP;
 		}
 
-		fep->reload_period = div_u64(period_ns, 2);
-		if (on && fep->reload_period) {
+		reload_period = div_u64(period_ns, 2);
+		if (on && reload_period) {
+			u64 perout_stime;
+
 			/* Convert 1588 timestamp to ns*/
 			start_time.tv_sec = rq->perout.start.sec;
 			start_time.tv_nsec = rq->perout.start.nsec;
-			fep->perout_stime = timespec64_to_ns(&start_time);
+			perout_stime = timespec64_to_ns(&start_time);
 
 			mutex_lock(&fep->ptp_clk_mutex);
 			if (!fep->ptp_clk_on) {
@@ -563,18 +576,41 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp,
 				return -EOPNOTSUPP;
 			}
 			spin_lock_irqsave(&fep->tmreg_lock, flags);
+
+			if (fep->pps_enable) {
+				dev_err(&fep->pdev->dev, "PPS is running");
+				ret = -EBUSY;
+				goto unlock;
+			}
+
+			if (fep->perout_enable) {
+				dev_err(&fep->pdev->dev,
+					"PEROUT has been enabled\n");
+				ret = -EBUSY;
+				goto unlock;
+			}
+
 			/* Read current timestamp */
 			curr_time = timecounter_read(&fep->tc);
-			spin_unlock_irqrestore(&fep->tmreg_lock, flags);
-			mutex_unlock(&fep->ptp_clk_mutex);
+			if (perout_stime <= curr_time) {
+				dev_err(&fep->pdev->dev,
+					"Start time must be greater than current time\n");
+				ret = -EINVAL;
+				goto unlock;
+			}
 
 			/* Calculate time difference */
-			delta = fep->perout_stime - curr_time;
+			delta = perout_stime - curr_time;
+			fep->reload_period = reload_period;
+			fep->perout_stime = perout_stime;
+			fep->perout_enable = true;
 
-			if (fep->perout_stime <= curr_time) {
-				dev_err(&fep->pdev->dev, "Start time must larger than current time!\n");
-				return -EINVAL;
-			}
+unlock:
+			spin_unlock_irqrestore(&fep->tmreg_lock, flags);
+			mutex_unlock(&fep->ptp_clk_mutex);
+
+			if (ret)
+				return ret;
 
 			/* Because the timer counter of FEC only has 31-bits, correspondingly,
 			 * the time comparison register FEC_TCCR also only low 31 bits can be
@@ -682,8 +718,11 @@ static irqreturn_t fec_pps_interrupt(int irq, void *dev_id)
 		fep->next_counter = (fep->next_counter + fep->reload_period) &
 				fep->cc.mask;
 
-		event.type = PTP_CLOCK_PPS;
-		ptp_clock_event(fep->ptp_clock, &event);
+		if (fep->pps_enable) {
+			event.type = PTP_CLOCK_PPS;
+			ptp_clock_event(fep->ptp_clock, &event);
+		}
+
 		return IRQ_HANDLED;
 	}
 
@@ -739,8 +778,8 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx)
 
 	INIT_DELAYED_WORK(&fep->time_keep, fec_time_keep);
 
-	hrtimer_init(&fep->perout_timer, CLOCK_REALTIME, HRTIMER_MODE_REL);
-	fep->perout_timer.function = fec_ptp_pps_perout_handler;
+	hrtimer_setup(&fep->perout_timer, fec_ptp_pps_perout_handler, CLOCK_REALTIME,
+		      HRTIMER_MODE_REL);
 
 	irq = platform_get_irq_byname_optional(pdev, "pps");
 	if (irq < 0)
diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
index 85617bb94959..51402dff72c5 100644
--- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
@@ -755,12 +755,12 @@ static struct fman_mac *pcs_to_dtsec(struct phylink_pcs *pcs)
 	return container_of(pcs, struct fman_mac, pcs);
 }
 
-static void dtsec_pcs_get_state(struct phylink_pcs *pcs,
+static void dtsec_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode,
 				struct phylink_link_state *state)
 {
 	struct fman_mac *dtsec = pcs_to_dtsec(pcs);
 
-	phylink_mii_c22_pcs_get_state(dtsec->tbidev, state);
+	phylink_mii_c22_pcs_get_state(dtsec->tbidev, neg_mode, state);
 }
 
 static int dtsec_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode,
@@ -1446,7 +1446,6 @@ int dtsec_initialization(struct mac_device *mac_dev,
 		goto _return_fm_mac_free;
 	}
 	dtsec->pcs.ops = &dtsec_pcs_ops;
-	dtsec->pcs.neg_mode = true;
 	dtsec->pcs.poll = true;
 
 	supported = mac_dev->phylink_config.supported_interfaces;
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index 3925441143fa..c84f0336c94c 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -649,6 +649,7 @@ static u32 memac_if_mode(phy_interface_t interface)
 		return IF_MODE_GMII | IF_MODE_RGMII;
 	case PHY_INTERFACE_MODE_SGMII:
 	case PHY_INTERFACE_MODE_1000BASEX:
+	case PHY_INTERFACE_MODE_2500BASEX:
 	case PHY_INTERFACE_MODE_QSGMII:
 		return IF_MODE_GMII;
 	case PHY_INTERFACE_MODE_10GBASER:
@@ -667,6 +668,7 @@ static struct phylink_pcs *memac_select_pcs(struct phylink_config *config,
 	switch (iface) {
 	case PHY_INTERFACE_MODE_SGMII:
 	case PHY_INTERFACE_MODE_1000BASEX:
+	case PHY_INTERFACE_MODE_2500BASEX:
 		return memac->sgmii_pcs;
 	case PHY_INTERFACE_MODE_QSGMII:
 		return memac->qsgmii_pcs;
@@ -685,6 +687,7 @@ static int memac_prepare(struct phylink_config *config, unsigned int mode,
 	switch (iface) {
 	case PHY_INTERFACE_MODE_SGMII:
 	case PHY_INTERFACE_MODE_1000BASEX:
+	case PHY_INTERFACE_MODE_2500BASEX:
 	case PHY_INTERFACE_MODE_QSGMII:
 	case PHY_INTERFACE_MODE_10GBASER:
 		return phy_set_mode_ext(memac->serdes, PHY_MODE_ETHERNET,
@@ -897,6 +900,89 @@ static int memac_set_exception(struct fman_mac *memac,
 	return 0;
 }
 
+static u64 memac_read64(void __iomem *reg)
+{
+	u32 low, high, tmp;
+
+	do {
+		high = ioread32be(reg + 4);
+		low = ioread32be(reg);
+		tmp = ioread32be(reg + 4);
+	} while (high != tmp);
+
+	return ((u64)high << 32) | low;
+}
+
+static void memac_get_pause_stats(struct fman_mac *memac,
+				  struct ethtool_pause_stats *s)
+{
+	s->tx_pause_frames = memac_read64(&memac->regs->txpf_l);
+	s->rx_pause_frames = memac_read64(&memac->regs->rxpf_l);
+}
+
+static const struct ethtool_rmon_hist_range memac_rmon_ranges[] = {
+	{   64,   64 },
+	{   65,  127 },
+	{  128,  255 },
+	{  256,  511 },
+	{  512, 1023 },
+	{ 1024, 1518 },
+	{ 1519, 9600 },
+	{},
+};
+
+static void memac_get_rmon_stats(struct fman_mac *memac,
+				 struct ethtool_rmon_stats *s,
+				 const struct ethtool_rmon_hist_range **ranges)
+{
+	s->undersize_pkts = memac_read64(&memac->regs->rund_l);
+	s->oversize_pkts = memac_read64(&memac->regs->rovr_l);
+	s->fragments = memac_read64(&memac->regs->rfrg_l);
+	s->jabbers = memac_read64(&memac->regs->rjbr_l);
+
+	s->hist[0] = memac_read64(&memac->regs->r64_l);
+	s->hist[1] = memac_read64(&memac->regs->r127_l);
+	s->hist[2] = memac_read64(&memac->regs->r255_l);
+	s->hist[3] = memac_read64(&memac->regs->r511_l);
+	s->hist[4] = memac_read64(&memac->regs->r1023_l);
+	s->hist[5] = memac_read64(&memac->regs->r1518_l);
+	s->hist[6] = memac_read64(&memac->regs->r1519x_l);
+
+	s->hist_tx[0] = memac_read64(&memac->regs->t64_l);
+	s->hist_tx[1] = memac_read64(&memac->regs->t127_l);
+	s->hist_tx[2] = memac_read64(&memac->regs->t255_l);
+	s->hist_tx[3] = memac_read64(&memac->regs->t511_l);
+	s->hist_tx[4] = memac_read64(&memac->regs->t1023_l);
+	s->hist_tx[5] = memac_read64(&memac->regs->t1518_l);
+	s->hist_tx[6] = memac_read64(&memac->regs->t1519x_l);
+
+	*ranges = memac_rmon_ranges;
+}
+
+static void memac_get_eth_ctrl_stats(struct fman_mac *memac,
+				     struct ethtool_eth_ctrl_stats *s)
+{
+	s->MACControlFramesTransmitted = memac_read64(&memac->regs->tcnp_l);
+	s->MACControlFramesReceived = memac_read64(&memac->regs->rcnp_l);
+}
+
+static void memac_get_eth_mac_stats(struct fman_mac *memac,
+				    struct ethtool_eth_mac_stats *s)
+{
+	s->FramesTransmittedOK = memac_read64(&memac->regs->tfrm_l);
+	s->FramesReceivedOK = memac_read64(&memac->regs->rfrm_l);
+	s->FrameCheckSequenceErrors = memac_read64(&memac->regs->rfcs_l);
+	s->AlignmentErrors = memac_read64(&memac->regs->raln_l);
+	s->OctetsTransmittedOK = memac_read64(&memac->regs->teoct_l);
+	s->FramesLostDueToIntMACXmitError = memac_read64(&memac->regs->terr_l);
+	s->OctetsReceivedOK = memac_read64(&memac->regs->reoct_l);
+	s->FramesLostDueToIntMACRcvError = memac_read64(&memac->regs->rdrntp_l);
+	s->MulticastFramesXmittedOK = memac_read64(&memac->regs->tmca_l);
+	s->BroadcastFramesXmittedOK = memac_read64(&memac->regs->tbca_l);
+	s->MulticastFramesReceivedOK = memac_read64(&memac->regs->rmca_l);
+	s->BroadcastFramesReceivedOK = memac_read64(&memac->regs->rbca_l);
+}
+
 static int memac_init(struct fman_mac *memac)
 {
 	struct memac_cfg *memac_drv_param;
@@ -1089,6 +1175,10 @@ int memac_initialization(struct mac_device *mac_dev,
 	mac_dev->set_tstamp		= memac_set_tstamp;
 	mac_dev->enable			= memac_enable;
 	mac_dev->disable		= memac_disable;
+	mac_dev->get_pause_stats	= memac_get_pause_stats;
+	mac_dev->get_rmon_stats		= memac_get_rmon_stats;
+	mac_dev->get_eth_ctrl_stats	= memac_get_eth_ctrl_stats;
+	mac_dev->get_eth_mac_stats	= memac_get_eth_mac_stats;
 
 	mac_dev->fman_mac = memac_config(mac_dev, params);
 	if (!mac_dev->fman_mac)
@@ -1225,7 +1315,8 @@ int memac_initialization(struct mac_device *mac_dev,
 	 * be careful and not enable this if we are using MII or RGMII, since
 	 * those configurations modes don't use in-band autonegotiation.
 	 */
-	if (!of_property_read_bool(mac_node, "managed") &&
+	if (!of_property_present(mac_node, "managed") &&
+	    mac_dev->phy_if != PHY_INTERFACE_MODE_2500BASEX &&
 	    mac_dev->phy_if != PHY_INTERFACE_MODE_MII &&
 	    !phy_interface_mode_is_rgmii(mac_dev->phy_if))
 		mac_dev->phylink_config.default_an_inband = true;
diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index a39fcea6a77a..f27ff625fe29 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -14,8 +14,6 @@
 #include <linux/device.h>
 #include <linux/phy.h>
 #include <linux/netdevice.h>
-#include <linux/phy_fixed.h>
-#include <linux/phylink.h>
 #include <linux/etherdevice.h>
 #include <linux/libfdt_env.h>
 #include <linux/platform_device.h>
diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h
index 955ace338965..63c2c5b4f99e 100644
--- a/drivers/net/ethernet/freescale/fman/mac.h
+++ b/drivers/net/ethernet/freescale/fman/mac.h
@@ -16,6 +16,11 @@
 #include "fman.h"
 #include "fman_mac.h"
 
+struct ethtool_eth_ctrl_stats;
+struct ethtool_eth_mac_stats;
+struct ethtool_pause_stats;
+struct ethtool_rmon_stats;
+struct ethtool_rmon_hist_range;
 struct fman_mac;
 struct mac_priv_s;
 
@@ -46,6 +51,15 @@ struct mac_device {
 				 enet_addr_t *eth_addr);
 	int (*remove_hash_mac_addr)(struct fman_mac *mac_dev,
 				    enet_addr_t *eth_addr);
+	void (*get_pause_stats)(struct fman_mac *memac,
+				struct ethtool_pause_stats *s);
+	void (*get_rmon_stats)(struct fman_mac *memac,
+			       struct ethtool_rmon_stats *s,
+			       const struct ethtool_rmon_hist_range **ranges);
+	void (*get_eth_ctrl_stats)(struct fman_mac *memac,
+				   struct ethtool_eth_ctrl_stats *s);
+	void (*get_eth_mac_stats)(struct fman_mac *memac,
+				  struct ethtool_eth_mac_stats *s);
 
 	void (*update_speed)(struct mac_device *mac_dev, int speed);
 
diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
index 56d2f79fb7e3..de88776dd2a2 100644
--- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c
+++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
@@ -479,10 +479,12 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev)
 					"missing 'reg' property in node %pOF\n",
 					tbi);
 				err = -EBUSY;
+				of_node_put(tbi);
 				goto error;
 			}
 			set_tbipa(*prop, pdev,
 				  data->get_tbipa, priv->map, &res);
+			of_node_put(tbi);
 		}
 	}
 
@@ -491,8 +493,8 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev)
 
 	err = of_mdiobus_register(new_bus, np);
 	if (err) {
-		dev_err(&pdev->dev, "cannot register %s as MDIO bus\n",
-			new_bus->name);
+		dev_err_probe(&pdev->dev, err, "cannot register %s as MDIO bus\n",
+			      new_bus->name);
 		goto error;
 	}
 
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 435138f4699d..7c0f049f0938 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -97,6 +97,7 @@
 #include <linux/phy_fixed.h>
 #include <linux/of.h>
 #include <linux/of_net.h>
+#include <linux/property.h>
 
 #include "gianfar.h"
 
@@ -571,18 +572,6 @@ static int gfar_parse_group(struct device_node *np,
 	return 0;
 }
 
-static int gfar_of_group_count(struct device_node *np)
-{
-	struct device_node *child;
-	int num = 0;
-
-	for_each_available_child_of_node(np, child)
-		if (of_node_name_eq(child, "queue-group"))
-			num++;
-
-	return num;
-}
-
 /* Reads the controller's registers to determine what interface
  * connects it to the PHY.
  */
@@ -654,8 +643,10 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev)
 		num_rx_qs = 1;
 	} else { /* MQ_MG_MODE */
 		/* get the actual number of supported groups */
-		unsigned int num_grps = gfar_of_group_count(np);
+		unsigned int num_grps;
 
+		num_grps = device_get_named_child_node_count(&ofdev->dev,
+							     "queue-group");
 		if (num_grps == 0 || num_grps > MAXGROUPS) {
 			dev_err(&ofdev->dev, "Invalid # of int groups(%d)\n",
 				num_grps);
@@ -1647,20 +1638,11 @@ static void gfar_configure_serdes(struct net_device *dev)
  */
 static int init_phy(struct net_device *dev)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct gfar_private *priv = netdev_priv(dev);
 	phy_interface_t interface = priv->interface;
 	struct phy_device *phydev;
 	struct ethtool_keee edata;
 
-	linkmode_set_bit_array(phy_10_100_features_array,
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask);
-	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, mask);
-
 	priv->oldlink = 0;
 	priv->oldspeed = 0;
 	priv->oldduplex = -1;
@@ -1675,9 +1657,8 @@ static int init_phy(struct net_device *dev)
 	if (interface == PHY_INTERFACE_MODE_SGMII)
 		gfar_configure_serdes(dev);
 
-	/* Remove any features not supported by the controller */
-	linkmode_and(phydev->supported, phydev->supported, mask);
-	linkmode_copy(phydev->advertising, phydev->supported);
+	if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT))
+		phy_set_max_speed(phydev, SPEED_100);
 
 	/* Add support for flow control */
 	phy_support_asym_pause(phydev);
@@ -2071,15 +2052,13 @@ static void gfar_timeout(struct net_device *dev, unsigned int txqueue)
 	schedule_work(&priv->reset_task);
 }
 
-static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
+static int gfar_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
 	struct gfar_private *priv = netdev_priv(netdev);
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		priv->hwts_tx_en = 0;
 		break;
@@ -2092,7 +2071,7 @@ static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		if (priv->hwts_rx_en) {
 			priv->hwts_rx_en = 0;
@@ -2106,44 +2085,23 @@ static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 			priv->hwts_rx_en = 1;
 			reset_gfar(netdev);
 		}
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	}
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
-static int gfar_hwtstamp_get(struct net_device *netdev, struct ifreq *ifr)
+static int gfar_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config config;
 	struct gfar_private *priv = netdev_priv(netdev);
 
-	config.flags = 0;
-	config.tx_type = priv->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
-	config.rx_filter = (priv->hwts_rx_en ?
-			    HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE);
-
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
-}
-
-static int gfar_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
-	struct phy_device *phydev = dev->phydev;
-
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	if (cmd == SIOCSHWTSTAMP)
-		return gfar_hwtstamp_set(dev, rq);
-	if (cmd == SIOCGHWTSTAMP)
-		return gfar_hwtstamp_get(dev, rq);
+	config->tx_type = priv->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	config->rx_filter = priv->hwts_rx_en ? HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
 
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_mii_ioctl(phydev, rq, cmd);
+	return 0;
 }
 
 /* Interrupt Handler for Transmit complete */
@@ -3184,7 +3142,7 @@ static const struct net_device_ops gfar_netdev_ops = {
 	.ndo_set_features = gfar_set_features,
 	.ndo_set_rx_mode = gfar_set_multi,
 	.ndo_tx_timeout = gfar_timeout,
-	.ndo_eth_ioctl = gfar_ioctl,
+	.ndo_eth_ioctl = phy_do_ioctl_running,
 	.ndo_get_stats64 = gfar_get_stats64,
 	.ndo_change_carrier = fixed_phy_change_carrier,
 	.ndo_set_mac_address = gfar_set_mac_addr,
@@ -3192,6 +3150,8 @@ static const struct net_device_ops gfar_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = gfar_netpoll,
 #endif
+	.ndo_hwtstamp_get = gfar_hwtstamp_get,
+	.ndo_hwtstamp_set = gfar_hwtstamp_set,
 };
 
 /* Set up the ethernet device structure, private data,
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 781d92e703cb..6fa752d3b60d 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -781,14 +781,26 @@ err:
 	return ret;
 }
 
-static int gfar_set_hash_opts(struct gfar_private *priv,
-			      struct ethtool_rxnfc *cmd)
+static int gfar_set_rxfh_fields(struct net_device *dev,
+				const struct ethtool_rxfh_fields *cmd,
+				struct netlink_ext_ack *extack)
 {
+	struct gfar_private *priv = netdev_priv(dev);
+	int ret;
+
+	if (test_bit(GFAR_RESETTING, &priv->state))
+		return -EBUSY;
+
+	mutex_lock(&priv->rx_queue_access);
+
+	ret = 0;
 	/* write the filer rules here */
 	if (!gfar_ethflow_to_filer_table(priv, cmd->data, cmd->flow_type))
-		return -EINVAL;
+		ret = -EINVAL;
 
-	return 0;
+	mutex_unlock(&priv->rx_queue_access);
+
+	return ret;
 }
 
 static int gfar_check_filer_hardware(struct gfar_private *priv)
@@ -1398,9 +1410,6 @@ static int gfar_set_nfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	mutex_lock(&priv->rx_queue_access);
 
 	switch (cmd->cmd) {
-	case ETHTOOL_SRXFH:
-		ret = gfar_set_hash_opts(priv, cmd);
-		break;
 	case ETHTOOL_SRXCLSRLINS:
 		if ((cmd->fs.ring_cookie != RX_CLS_FLOW_DISC &&
 		     cmd->fs.ring_cookie >= priv->num_rx_queues) ||
@@ -1422,6 +1431,13 @@ static int gfar_set_nfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	return ret;
 }
 
+static u32 gfar_get_rx_ring_count(struct net_device *dev)
+{
+	struct gfar_private *priv = netdev_priv(dev);
+
+	return priv->num_rx_queues;
+}
+
 static int gfar_get_nfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 			u32 *rule_locs)
 {
@@ -1429,9 +1445,6 @@ static int gfar_get_nfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	int ret = 0;
 
 	switch (cmd->cmd) {
-	case ETHTOOL_GRXRINGS:
-		cmd->data = priv->num_rx_queues;
-		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = priv->rx_list.count;
 		break;
@@ -1466,8 +1479,10 @@ static int gfar_get_ts_info(struct net_device *dev,
 	if (ptp_node) {
 		ptp_dev = of_find_device_by_node(ptp_node);
 		of_node_put(ptp_node);
-		if (ptp_dev)
+		if (ptp_dev) {
 			ptp = platform_get_drvdata(ptp_dev);
+			put_device(&ptp_dev->dev);
+		}
 	}
 
 	if (ptp)
@@ -1508,6 +1523,8 @@ const struct ethtool_ops gfar_ethtool_ops = {
 #endif
 	.set_rxnfc = gfar_set_nfc,
 	.get_rxnfc = gfar_get_nfc,
+	.get_rx_ring_count = gfar_get_rx_ring_count,
+	.set_rxfh_fields = gfar_set_rxfh_fields,
 	.get_ts_info = gfar_get_ts_info,
 	.get_link_ksettings = phy_ethtool_get_link_ksettings,
 	.set_link_ksettings = phy_ethtool_set_link_ksettings,
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index f47f8177a93b..affd5a6c44e7 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -1434,7 +1434,7 @@ static void ugeth_activate(struct ucc_geth_private *ugeth)
 
 	/* allow to xmit again  */
 	netif_tx_wake_all_queues(ugeth->ndev);
-	__netdev_watchdog_up(ugeth->ndev);
+	netdev_watchdog_up(ugeth->ndev);
 }
 
 /* Initialize TBI PHY interface for communicating with the
@@ -3408,7 +3408,7 @@ static int ucc_geth_parse_clock(struct device_node *np, const char *which,
 	return 0;
 }
 
-struct phylink_mac_ops ugeth_mac_ops = {
+static const struct phylink_mac_ops ugeth_mac_ops = {
 	.mac_link_up = ugeth_mac_link_up,
 	.mac_link_down = ugeth_mac_link_down,
 	.mac_config = ugeth_mac_config,
diff --git a/drivers/net/ethernet/freescale/ucc_geth.h b/drivers/net/ethernet/freescale/ucc_geth.h
index 38789faae706..84f92f6384e7 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.h
+++ b/drivers/net/ethernet/freescale/ucc_geth.h
@@ -890,8 +890,6 @@ struct ucc_geth_hardware_statistics {
 							   addresses */
 
 #define TX_TIMEOUT                              (1*HZ)
-#define PHY_INIT_TIMEOUT                        100000
-#define PHY_CHANGE_TIME                         2
 
 /* Fast Ethernet (10/100 Mbps) */
 #define UCC_GETH_URFS_INIT                      512	/* Rx virtual FIFO size
diff --git a/drivers/net/ethernet/fungible/funeth/funeth.h b/drivers/net/ethernet/fungible/funeth/funeth.h
index 1250e10d21db..55e705e239f8 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth.h
+++ b/drivers/net/ethernet/fungible/funeth/funeth.h
@@ -4,7 +4,7 @@
 #define _FUNETH_H
 
 #include <uapi/linux/if_ether.h>
-#include <uapi/linux/net_tstamp.h>
+#include <linux/net_tstamp.h>
 #include <linux/mutex.h>
 #include <linux/seqlock.h>
 #include <linux/xarray.h>
@@ -121,7 +121,7 @@ struct funeth_priv {
 	u8 rx_coal_usec;
 	u8 rx_coal_count;
 
-	struct hwtstamp_config hwtstamp_cfg;
+	struct kernel_hwtstamp_config hwtstamp_cfg;
 
 	/* cumulative queue stats from earlier queue instances */
 	u64 tx_packets;
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c b/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c
index ba83dbf4ed22..1966dba512f8 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c
+++ b/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c
@@ -930,7 +930,8 @@ static void fun_get_rmon_stats(struct net_device *netdev,
 }
 
 static void fun_get_fec_stats(struct net_device *netdev,
-			      struct ethtool_fec_stats *stats)
+			      struct ethtool_fec_stats *stats,
+			      struct ethtool_fec_hist *hist)
 {
 	const struct funeth_priv *fp = netdev_priv(netdev);
 
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_main.c b/drivers/net/ethernet/fungible/funeth/funeth_main.c
index ac86179a0a81..792cddac6f1b 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_main.c
+++ b/drivers/net/ethernet/fungible/funeth/funeth_main.c
@@ -1014,26 +1014,25 @@ static int fun_get_port_attributes(struct net_device *netdev)
 	return 0;
 }
 
-static int fun_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
+static int fun_hwtstamp_get(struct net_device *dev,
+			    struct kernel_hwtstamp_config *config)
 {
 	const struct funeth_priv *fp = netdev_priv(dev);
 
-	return copy_to_user(ifr->ifr_data, &fp->hwtstamp_cfg,
-			    sizeof(fp->hwtstamp_cfg)) ? -EFAULT : 0;
+	*config = fp->hwtstamp_cfg;
+	return 0;
 }
 
-static int fun_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
+static int fun_hwtstamp_set(struct net_device *dev,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack)
 {
 	struct funeth_priv *fp = netdev_priv(dev);
-	struct hwtstamp_config cfg;
-
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
 
 	/* no TX HW timestamps */
-	cfg.tx_type = HWTSTAMP_TX_OFF;
+	config->tx_type = HWTSTAMP_TX_OFF;
 
-	switch (cfg.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		break;
 	case HWTSTAMP_FILTER_ALL:
@@ -1051,26 +1050,14 @@ static int fun_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 	case HWTSTAMP_FILTER_NTP_ALL:
-		cfg.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	fp->hwtstamp_cfg = cfg;
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
-}
-
-static int fun_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return fun_hwtstamp_set(dev, ifr);
-	case SIOCGHWTSTAMP:
-		return fun_hwtstamp_get(dev, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
+	fp->hwtstamp_cfg = *config;
+	return 0;
 }
 
 /* Prepare the queues for XDP. */
@@ -1340,7 +1327,6 @@ static const struct net_device_ops fun_netdev_ops = {
 	.ndo_change_mtu		= fun_change_mtu,
 	.ndo_set_mac_address	= fun_set_macaddr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_eth_ioctl		= fun_ioctl,
 	.ndo_uninit		= fun_uninit,
 	.ndo_bpf		= fun_xdp,
 	.ndo_xdp_xmit		= fun_xdp_xmit_frames,
@@ -1348,6 +1334,8 @@ static const struct net_device_ops fun_netdev_ops = {
 	.ndo_set_vf_vlan	= fun_set_vf_vlan,
 	.ndo_set_vf_rate	= fun_set_vf_rate,
 	.ndo_get_vf_config	= fun_get_vf_config,
+	.ndo_hwtstamp_get	= fun_hwtstamp_get,
+	.ndo_hwtstamp_set	= fun_hwtstamp_set,
 };
 
 #define GSO_ENCAP_FLAGS (NETIF_F_GSO_GRE | NETIF_F_GSO_IPXIP4 | \
diff --git a/drivers/net/ethernet/google/Kconfig b/drivers/net/ethernet/google/Kconfig
index 564862a57124..14c9431e15e5 100644
--- a/drivers/net/ethernet/google/Kconfig
+++ b/drivers/net/ethernet/google/Kconfig
@@ -18,6 +18,7 @@ if NET_VENDOR_GOOGLE
 config GVE
 	tristate "Google Virtual NIC (gVNIC) support"
 	depends on (PCI_MSI && (X86 || CPU_LITTLE_ENDIAN))
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select PAGE_POOL
 	help
 	  This driver supports Google Virtual NIC (gVNIC)"
diff --git a/drivers/net/ethernet/google/gve/Makefile b/drivers/net/ethernet/google/gve/Makefile
index 4520f1c07a63..e0ec227a50f7 100644
--- a/drivers/net/ethernet/google/gve/Makefile
+++ b/drivers/net/ethernet/google/gve/Makefile
@@ -1,5 +1,7 @@
 # Makefile for the Google virtual Ethernet (gve) driver
 
 obj-$(CONFIG_GVE) += gve.o
-gve-objs := gve_main.o gve_tx.o gve_tx_dqo.o gve_rx.o gve_rx_dqo.o gve_ethtool.o gve_adminq.o gve_utils.o gve_flow_rule.o \
+gve-y := gve_main.o gve_tx.o gve_tx_dqo.o gve_rx.o gve_rx_dqo.o gve_ethtool.o gve_adminq.o gve_utils.o gve_flow_rule.o \
 	    gve_buffer_mgmt_dqo.o
+
+gve-$(CONFIG_PTP_1588_CLOCK) += gve_ptp.o
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index dd92949bb214..970d5ca8cdde 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -11,7 +11,9 @@
 #include <linux/dmapool.h>
 #include <linux/ethtool_netlink.h>
 #include <linux/netdevice.h>
+#include <linux/net_tstamp.h>
 #include <linux/pci.h>
+#include <linux/ptp_clock_kernel.h>
 #include <linux/u64_stats_sync.h>
 #include <net/page_pool/helpers.h>
 #include <net/xdp.h>
@@ -57,7 +59,7 @@
 
 #define GVE_DEFAULT_RX_BUFFER_SIZE 2048
 
-#define GVE_MAX_RX_BUFFER_SIZE 4096
+#define GVE_XDP_RX_BUFFER_SIZE_DQO 4096
 
 #define GVE_DEFAULT_RX_BUFFER_OFFSET 2048
 
@@ -68,6 +70,9 @@
 #define GVE_FLOW_RULE_IDS_CACHE_SIZE \
 	(GVE_ADMINQ_BUFFER_SIZE / sizeof(((struct gve_adminq_queried_flow_rule *)0)->location))
 
+#define GVE_RSS_KEY_SIZE	40
+#define GVE_RSS_INDIR_SIZE	128
+
 #define GVE_XDP_ACTIONS 5
 
 #define GVE_GQ_TX_MIN_PKT_DESC_BYTES 182
@@ -93,6 +98,8 @@
  */
 #define GVE_DQO_QPL_ONDEMAND_ALLOC_THRESHOLD 96
 
+#define GVE_DQO_RX_HWTSTAMP_VALID 0x1
+
 /* Each slot in the desc ring has a 1:1 mapping to a slot in the data ring */
 struct gve_rx_desc_queue {
 	struct gve_rx_desc *desc_ring; /* the descriptor ring */
@@ -102,7 +109,13 @@ struct gve_rx_desc_queue {
 
 /* The page info for a single slot in the RX data queue */
 struct gve_rx_slot_page_info {
-	struct page *page;
+	/* netmem is used for DQO RDA mode
+	 * page is used in all other modes
+	 */
+	union {
+		struct page *page;
+		netmem_ref netmem;
+	};
 	void *page_address;
 	u32 page_offset; /* offset to write to in page */
 	unsigned int buf_size;
@@ -177,6 +190,9 @@ struct gve_rx_buf_state_dqo {
 	/* The page posted to HW. */
 	struct gve_rx_slot_page_info page_info;
 
+	/* XSK buffer */
+	struct xdp_buff *xsk_buff;
+
 	/* The DMA address corresponding to `page_info`. */
 	dma_addr_t addr;
 
@@ -189,6 +205,13 @@ struct gve_rx_buf_state_dqo {
 	s16 next;
 };
 
+/* Wrapper for XDP Rx metadata */
+struct gve_xdp_buff {
+	struct xdp_buff xdp;
+	struct gve_priv *gve;
+	const struct gve_rx_compl_desc_dqo *compl_desc;
+};
+
 /* `head` and `tail` are indices into an array, or -1 if empty. */
 struct gve_index_list {
 	s16 head;
@@ -218,6 +241,11 @@ struct gve_rx_cnts {
 /* Contains datapath state used to represent an RX queue. */
 struct gve_rx_ring {
 	struct gve_priv *gve;
+
+	u16 packet_buffer_size;		/* Size of buffer posted to NIC */
+	u16 packet_buffer_truesize;	/* Total size of RX buffer */
+	u16 rx_headroom;
+
 	union {
 		/* GQI fields */
 		struct {
@@ -226,7 +254,6 @@ struct gve_rx_ring {
 
 			/* threshold for posting new buffs and descs */
 			u32 db_threshold;
-			u16 packet_buffer_size;
 
 			u32 qpl_copy_pool_mask;
 			u32 qpl_copy_pool_head;
@@ -314,7 +341,6 @@ struct gve_rx_ring {
 
 	/* XDP stuff */
 	struct xdp_rxq_info xdp_rxq;
-	struct xdp_rxq_info xsk_rxq;
 	struct xsk_buff_pool *xsk_pool;
 	struct page_frag_cache page_cache; /* Page cache to allocate XDP frames */
 };
@@ -383,10 +409,24 @@ enum gve_packet_state {
 	GVE_PACKET_STATE_PENDING_REINJECT_COMPL,
 	/* No valid completion received within the specified timeout. */
 	GVE_PACKET_STATE_TIMED_OUT_COMPL,
+	/* XSK pending packet has received a packet/reinjection completion, or
+	 * has timed out. At this point, the pending packet can be counted by
+	 * xsk_tx_complete and freed.
+	 */
+	GVE_PACKET_STATE_XSK_COMPLETE,
+};
+
+enum gve_tx_pending_packet_dqo_type {
+	GVE_TX_PENDING_PACKET_DQO_SKB,
+	GVE_TX_PENDING_PACKET_DQO_XDP_FRAME,
+	GVE_TX_PENDING_PACKET_DQO_XSK,
 };
 
 struct gve_tx_pending_packet_dqo {
-	struct sk_buff *skb; /* skb for this packet */
+	union {
+		struct sk_buff *skb;
+		struct xdp_frame *xdpf;
+	};
 
 	/* 0th element corresponds to the linear portion of `skb`, should be
 	 * unmapped with `dma_unmap_single`.
@@ -416,7 +456,10 @@ struct gve_tx_pending_packet_dqo {
 	/* Identifies the current state of the packet as defined in
 	 * `enum gve_packet_state`.
 	 */
-	u8 state;
+	u8 state : 3;
+
+	/* gve_tx_pending_packet_dqo_type */
+	u8 type : 2;
 
 	/* If packet is an outstanding miss completion, then the packet is
 	 * freed if the corresponding re-injection completion is not received
@@ -438,6 +481,9 @@ struct gve_tx_ring {
 
 		/* DQO fields. */
 		struct {
+			/* Spinlock for XDP tx traffic */
+			spinlock_t xdp_lock;
+
 			/* Linked list of gve_tx_pending_packet_dqo. Index into
 			 * pending_packets, or -1 if empty.
 			 *
@@ -482,6 +528,8 @@ struct gve_tx_ring {
 				/* Cached value of `dqo_compl.free_tx_qpl_buf_cnt` */
 				u32 free_tx_qpl_buf_cnt;
 			};
+
+			atomic_t xsk_reorder_queue_tail;
 		} dqo_tx;
 	};
 
@@ -515,6 +563,9 @@ struct gve_tx_ring {
 			/* Last TX ring index fetched by HW */
 			atomic_t hw_tx_head;
 
+			u16 xsk_reorder_queue_head;
+			u16 xsk_reorder_queue_tail;
+
 			/* List to track pending packets which received a miss
 			 * completion but not a corresponding reinjection.
 			 */
@@ -568,6 +619,8 @@ struct gve_tx_ring {
 			struct gve_tx_pending_packet_dqo *pending_packets;
 			s16 num_pending_packets;
 
+			u16 *xsk_reorder_queue;
+
 			u32 complq_mask; /* complq size is complq_mask + 1 */
 
 			/* QPL fields */
@@ -604,8 +657,6 @@ struct gve_tx_ring {
 	dma_addr_t complq_bus_dqo; /* dma address of the dqo.compl_ring */
 	struct u64_stats_sync statss; /* sync stats for 32bit archs */
 	struct xsk_buff_pool *xsk_pool;
-	u32 xdp_xsk_wakeup;
-	u32 xdp_xsk_done;
 	u64 xdp_xsk_sent;
 	u64 xdp_xmit;
 	u64 xdp_xmit_errors;
@@ -624,10 +675,18 @@ struct gve_notify_block {
 	u32 irq;
 };
 
-/* Tracks allowed and current queue settings */
-struct gve_queue_config {
+/* Tracks allowed and current rx queue settings */
+struct gve_rx_queue_config {
 	u16 max_queues;
-	u16 num_queues; /* current */
+	u16 num_queues;
+	u16 packet_buffer_size;
+};
+
+/* Tracks allowed and current tx queue settings */
+struct gve_tx_queue_config {
+	u16 max_queues;
+	u16 num_queues; /* number of TX queues, excluding XDP queues */
+	u16 num_xdp_queues;
 };
 
 /* Tracks the available and used qpl IDs */
@@ -651,11 +710,11 @@ struct gve_ptype_lut {
 
 /* Parameters for allocating resources for tx queues */
 struct gve_tx_alloc_rings_cfg {
-	struct gve_queue_config *qcfg;
+	struct gve_tx_queue_config *qcfg;
+
+	u16 num_xdp_rings;
 
 	u16 ring_size;
-	u16 start_idx;
-	u16 num_rings;
 	bool raw_addressing;
 
 	/* Allocated resources are returned here */
@@ -665,13 +724,15 @@ struct gve_tx_alloc_rings_cfg {
 /* Parameters for allocating resources for rx queues */
 struct gve_rx_alloc_rings_cfg {
 	/* tx config is also needed to determine QPL ids */
-	struct gve_queue_config *qcfg;
-	struct gve_queue_config *qcfg_tx;
+	struct gve_rx_queue_config *qcfg_rx;
+	struct gve_tx_queue_config *qcfg_tx;
 
 	u16 ring_size;
 	u16 packet_buffer_size;
 	bool raw_addressing;
 	bool enable_header_split;
+	bool reset_rss;
+	bool xdp;
 
 	/* Allocated resources are returned here */
 	struct gve_rx_ring *rx;
@@ -722,6 +783,17 @@ struct gve_flow_rules_cache {
 	u32 rule_ids_cache_num;
 };
 
+struct gve_rss_config {
+	u8 *hash_key;
+	u32 *hash_lut;
+};
+
+struct gve_ptp {
+	struct ptp_clock_info info;
+	struct ptp_clock *clock;
+	struct gve_priv *priv;
+};
+
 struct gve_priv {
 	struct net_device *dev;
 	struct gve_tx_ring *tx; /* array of tx_cfg.num_queues */
@@ -751,10 +823,11 @@ struct gve_priv {
 	u32 rx_copybreak; /* copy packets smaller than this */
 	u16 default_num_queues; /* default num queues to set up */
 
-	u16 num_xdp_queues;
-	struct gve_queue_config tx_cfg;
-	struct gve_queue_config rx_cfg;
-	u32 num_ntfy_blks; /* spilt between TX and RX so must be even */
+	struct gve_tx_queue_config tx_cfg;
+	struct gve_rx_queue_config rx_cfg;
+	unsigned long *xsk_pools; /* bitmap of RX queues with XSK pools */
+	u32 num_ntfy_blks; /* split between TX and RX so must be even */
+	int numa_node;
 
 	struct gve_registers __iomem *reg_bar0; /* see gve_register.h */
 	__be32 __iomem *db_bar2; /* "array" of doorbells */
@@ -786,6 +859,7 @@ struct gve_priv {
 	u32 adminq_set_driver_parameter_cnt;
 	u32 adminq_report_stats_cnt;
 	u32 adminq_report_link_speed_cnt;
+	u32 adminq_report_nic_timestamp_cnt;
 	u32 adminq_get_ptype_map_cnt;
 	u32 adminq_verify_driver_compatibility_cnt;
 	u32 adminq_query_flow_rules_cnt;
@@ -823,7 +897,6 @@ struct gve_priv {
 	struct gve_ptype_lut *ptype_lut_dqo;
 
 	/* Must be a power of two. */
-	u16 data_buffer_size_dqo;
 	u16 max_rx_buffer_size; /* device limit */
 
 	enum gve_queue_format queue_format;
@@ -842,6 +915,16 @@ struct gve_priv {
 
 	u16 rss_key_size;
 	u16 rss_lut_size;
+	bool cache_rss_config;
+	struct gve_rss_config rss_config;
+
+	/* True if the device supports reading the nic clock */
+	bool nic_timestamp_supported;
+	struct gve_ptp *ptp;
+	struct kernel_hwtstamp_config ts_config;
+	struct gve_nic_ts_report *nic_ts_report;
+	dma_addr_t nic_ts_report_bus;
+	u64 last_sync_nic_counter; /* Clock counter from last NIC TS report */
 };
 
 enum gve_service_task_flags_bit {
@@ -1024,27 +1107,16 @@ static inline bool gve_is_qpl(struct gve_priv *priv)
 }
 
 /* Returns the number of tx queue page lists */
-static inline u32 gve_num_tx_qpls(const struct gve_queue_config *tx_cfg,
-				  int num_xdp_queues,
+static inline u32 gve_num_tx_qpls(const struct gve_tx_queue_config *tx_cfg,
 				  bool is_qpl)
 {
 	if (!is_qpl)
 		return 0;
-	return tx_cfg->num_queues + num_xdp_queues;
-}
-
-/* Returns the number of XDP tx queue page lists
- */
-static inline u32 gve_num_xdp_qpls(struct gve_priv *priv)
-{
-	if (priv->queue_format != GVE_GQI_QPL_FORMAT)
-		return 0;
-
-	return priv->num_xdp_queues;
+	return tx_cfg->num_queues + tx_cfg->num_xdp_queues;
 }
 
 /* Returns the number of rx queue page lists */
-static inline u32 gve_num_rx_qpls(const struct gve_queue_config *rx_cfg,
+static inline u32 gve_num_rx_qpls(const struct gve_rx_queue_config *rx_cfg,
 				  bool is_qpl)
 {
 	if (!is_qpl)
@@ -1062,7 +1134,8 @@ static inline u32 gve_rx_qpl_id(struct gve_priv *priv, int rx_qid)
 	return priv->tx_cfg.max_queues + rx_qid;
 }
 
-static inline u32 gve_get_rx_qpl_id(const struct gve_queue_config *tx_cfg, int rx_qid)
+static inline u32 gve_get_rx_qpl_id(const struct gve_tx_queue_config *tx_cfg,
+				    int rx_qid)
 {
 	return tx_cfg->max_queues + rx_qid;
 }
@@ -1072,7 +1145,7 @@ static inline u32 gve_tx_start_qpl_id(struct gve_priv *priv)
 	return gve_tx_qpl_id(priv, 0);
 }
 
-static inline u32 gve_rx_start_qpl_id(const struct gve_queue_config *tx_cfg)
+static inline u32 gve_rx_start_qpl_id(const struct gve_tx_queue_config *tx_cfg)
 {
 	return gve_get_rx_qpl_id(tx_cfg, 0);
 }
@@ -1101,9 +1174,15 @@ static inline bool gve_is_gqi(struct gve_priv *priv)
 		priv->queue_format == GVE_GQI_QPL_FORMAT;
 }
 
+static inline bool gve_is_dqo(struct gve_priv *priv)
+{
+	return priv->queue_format == GVE_DQO_RDA_FORMAT ||
+	       priv->queue_format == GVE_DQO_QPL_FORMAT;
+}
+
 static inline u32 gve_num_tx_queues(struct gve_priv *priv)
 {
-	return priv->tx_cfg.num_queues + priv->num_xdp_queues;
+	return priv->tx_cfg.num_queues + priv->tx_cfg.num_xdp_queues;
 }
 
 static inline u32 gve_xdp_tx_queue_id(struct gve_priv *priv, u32 queue_id)
@@ -1116,6 +1195,17 @@ static inline u32 gve_xdp_tx_start_queue_id(struct gve_priv *priv)
 	return gve_xdp_tx_queue_id(priv, 0);
 }
 
+static inline bool gve_supports_xdp_xmit(struct gve_priv *priv)
+{
+	switch (priv->queue_format) {
+	case GVE_GQI_QPL_FORMAT:
+	case GVE_DQO_RDA_FORMAT:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /* gqi napi handler defined in gve_main.c */
 int gve_napi_poll(struct napi_struct *napi, int budget);
 
@@ -1133,13 +1223,18 @@ void gve_free_queue_page_list(struct gve_priv *priv,
 			      u32 id);
 /* tx handling */
 netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev);
-int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
-		 u32 flags);
+int gve_xdp_xmit_gqi(struct net_device *dev, int n, struct xdp_frame **frames,
+		     u32 flags);
+int gve_xdp_xmit_dqo(struct net_device *dev, int n, struct xdp_frame **frames,
+		     u32 flags);
 int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx,
 		     void *data, int len, void *frame_p);
 void gve_xdp_tx_flush(struct gve_priv *priv, u32 xdp_qid);
+int gve_xdp_xmit_one_dqo(struct gve_priv *priv, struct gve_tx_ring *tx,
+			 struct xdp_frame *xdpf);
 bool gve_tx_poll(struct gve_notify_block *block, int budget);
 bool gve_xdp_poll(struct gve_notify_block *block, int budget);
+int gve_xsk_tx_poll(struct gve_notify_block *block, int budget);
 int gve_tx_alloc_rings_gqi(struct gve_priv *priv,
 			   struct gve_tx_alloc_rings_cfg *cfg);
 void gve_tx_free_rings_gqi(struct gve_priv *priv,
@@ -1165,9 +1260,12 @@ void gve_rx_free_rings_gqi(struct gve_priv *priv,
 			   struct gve_rx_alloc_rings_cfg *cfg);
 void gve_rx_start_ring_gqi(struct gve_priv *priv, int idx);
 void gve_rx_stop_ring_gqi(struct gve_priv *priv, int idx);
-u16 gve_get_pkt_buf_size(const struct gve_priv *priv, bool enable_hplit);
 bool gve_header_split_supported(const struct gve_priv *priv);
-int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split);
+int gve_set_rx_buf_len_config(struct gve_priv *priv, u32 rx_buf_len,
+			      struct netlink_ext_ack *extack,
+			      struct gve_rx_alloc_rings_cfg *rx_alloc_cfg);
+int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split,
+			  struct gve_rx_alloc_rings_cfg *rx_alloc_cfg);
 /* rx buffer handling */
 int gve_buf_ref_cnt(struct gve_rx_buf_state_dqo *bs);
 void gve_free_page_dqo(struct gve_priv *priv, struct gve_rx_buf_state_dqo *bs,
@@ -1196,7 +1294,8 @@ void gve_free_buffer(struct gve_rx_ring *rx,
 		     struct gve_rx_buf_state_dqo *buf_state);
 int gve_alloc_buffer(struct gve_rx_ring *rx, struct gve_rx_desc_dqo *desc);
 struct page_pool *gve_rx_create_page_pool(struct gve_priv *priv,
-					  struct gve_rx_ring *rx);
+					  struct gve_rx_ring *rx,
+					  bool xdp);
 
 /* Reset */
 void gve_schedule_reset(struct gve_priv *priv);
@@ -1208,14 +1307,35 @@ int gve_adjust_config(struct gve_priv *priv,
 		      struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
 		      struct gve_rx_alloc_rings_cfg *rx_alloc_cfg);
 int gve_adjust_queues(struct gve_priv *priv,
-		      struct gve_queue_config new_rx_config,
-		      struct gve_queue_config new_tx_config);
+		      struct gve_rx_queue_config new_rx_config,
+		      struct gve_tx_queue_config new_tx_config,
+		      bool reset_rss);
 /* flow steering rule */
 int gve_get_flow_rule_entry(struct gve_priv *priv, struct ethtool_rxnfc *cmd);
 int gve_get_flow_rule_ids(struct gve_priv *priv, struct ethtool_rxnfc *cmd, u32 *rule_locs);
 int gve_add_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd);
 int gve_del_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd);
 int gve_flow_rules_reset(struct gve_priv *priv);
+/* RSS config */
+int gve_init_rss_config(struct gve_priv *priv, u16 num_queues);
+/* PTP and timestamping */
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+int gve_clock_nic_ts_read(struct gve_priv *priv);
+int gve_init_clock(struct gve_priv *priv);
+void gve_teardown_clock(struct gve_priv *priv);
+#else /* CONFIG_PTP_1588_CLOCK */
+static inline int gve_clock_nic_ts_read(struct gve_priv *priv)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int gve_init_clock(struct gve_priv *priv)
+{
+	return 0;
+}
+
+static inline void gve_teardown_clock(struct gve_priv *priv) { }
+#endif /* CONFIG_PTP_1588_CLOCK */
 /* report stats handling */
 void gve_handle_report_stats(struct gve_priv *priv);
 /* exported by ethtool.c */
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index aa7d723011d0..b72cc0fa2ba2 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -46,6 +46,7 @@ void gve_parse_device_option(struct gve_priv *priv,
 			     struct gve_device_option_buffer_sizes **dev_op_buffer_sizes,
 			     struct gve_device_option_flow_steering **dev_op_flow_steering,
 			     struct gve_device_option_rss_config **dev_op_rss_config,
+			     struct gve_device_option_nic_timestamp **dev_op_nic_timestamp,
 			     struct gve_device_option_modify_ring **dev_op_modify_ring)
 {
 	u32 req_feat_mask = be32_to_cpu(option->required_features_mask);
@@ -225,6 +226,23 @@ void gve_parse_device_option(struct gve_priv *priv,
 				 "RSS config");
 		*dev_op_rss_config = (void *)(option + 1);
 		break;
+	case GVE_DEV_OPT_ID_NIC_TIMESTAMP:
+		if (option_length < sizeof(**dev_op_nic_timestamp) ||
+		    req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_NIC_TIMESTAMP) {
+			dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT,
+				 "Nic Timestamp",
+				 (int)sizeof(**dev_op_nic_timestamp),
+				 GVE_DEV_OPT_REQ_FEAT_MASK_NIC_TIMESTAMP,
+				 option_length, req_feat_mask);
+			break;
+		}
+
+		if (option_length > sizeof(**dev_op_nic_timestamp))
+			dev_warn(&priv->pdev->dev,
+				 GVE_DEVICE_OPTION_TOO_BIG_FMT,
+				 "Nic Timestamp");
+		*dev_op_nic_timestamp = (void *)(option + 1);
+		break;
 	default:
 		/* If we don't recognize the option just continue
 		 * without doing anything.
@@ -246,6 +264,7 @@ gve_process_device_options(struct gve_priv *priv,
 			   struct gve_device_option_buffer_sizes **dev_op_buffer_sizes,
 			   struct gve_device_option_flow_steering **dev_op_flow_steering,
 			   struct gve_device_option_rss_config **dev_op_rss_config,
+			   struct gve_device_option_nic_timestamp **dev_op_nic_timestamp,
 			   struct gve_device_option_modify_ring **dev_op_modify_ring)
 {
 	const int num_options = be16_to_cpu(descriptor->num_device_options);
@@ -269,6 +288,7 @@ gve_process_device_options(struct gve_priv *priv,
 					dev_op_dqo_rda, dev_op_jumbo_frames,
 					dev_op_dqo_qpl, dev_op_buffer_sizes,
 					dev_op_flow_steering, dev_op_rss_config,
+					dev_op_nic_timestamp,
 					dev_op_modify_ring);
 		dev_opt = next_opt;
 	}
@@ -306,6 +326,7 @@ int gve_adminq_alloc(struct device *dev, struct gve_priv *priv)
 	priv->adminq_set_driver_parameter_cnt = 0;
 	priv->adminq_report_stats_cnt = 0;
 	priv->adminq_report_link_speed_cnt = 0;
+	priv->adminq_report_nic_timestamp_cnt = 0;
 	priv->adminq_get_ptype_map_cnt = 0;
 	priv->adminq_query_flow_rules_cnt = 0;
 	priv->adminq_cfg_flow_rule_cnt = 0;
@@ -442,6 +463,8 @@ static int gve_adminq_kick_and_wait(struct gve_priv *priv)
 	int tail, head;
 	int i;
 
+	lockdep_assert_held(&priv->adminq_lock);
+
 	tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
 	head = priv->adminq_prod_cnt;
 
@@ -467,9 +490,6 @@ static int gve_adminq_kick_and_wait(struct gve_priv *priv)
 	return 0;
 }
 
-/* This function is not threadsafe - the caller is responsible for any
- * necessary locks.
- */
 static int gve_adminq_issue_cmd(struct gve_priv *priv,
 				union gve_adminq_command *cmd_orig)
 {
@@ -477,6 +497,8 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv,
 	u32 opcode;
 	u32 tail;
 
+	lockdep_assert_held(&priv->adminq_lock);
+
 	tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
 
 	// Check if next command will overflow the buffer.
@@ -544,6 +566,9 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv,
 	case GVE_ADMINQ_REPORT_LINK_SPEED:
 		priv->adminq_report_link_speed_cnt++;
 		break;
+	case GVE_ADMINQ_REPORT_NIC_TIMESTAMP:
+		priv->adminq_report_nic_timestamp_cnt++;
+		break;
 	case GVE_ADMINQ_GET_PTYPE_MAP:
 		priv->adminq_get_ptype_map_cnt++;
 		break;
@@ -564,6 +589,7 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv,
 		break;
 	default:
 		dev_err(&priv->pdev->dev, "unknown AQ command opcode %d\n", opcode);
+		return -EINVAL;
 	}
 
 	return 0;
@@ -625,7 +651,7 @@ static int gve_adminq_execute_extended_cmd(struct gve_priv *priv, u32 opcode,
 
 /* The device specifies that the management vector can either be the first irq
  * or the last irq. ntfy_blk_msix_base_idx indicates the first irq assigned to
- * the ntfy blks. It if is 0 then the management vector is last, if it is 1 then
+ * the ntfy blks. If it is 0 then the management vector is last, if it is 1 then
  * the management vector is first.
  *
  * gve arranges the msix vectors so that the management vector is last.
@@ -709,13 +735,19 @@ int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_que
 	int err;
 	int i;
 
+	mutex_lock(&priv->adminq_lock);
+
 	for (i = start_id; i < start_id + num_queues; i++) {
 		err = gve_adminq_create_tx_queue(priv, i);
 		if (err)
-			return err;
+			goto out;
 	}
 
-	return gve_adminq_kick_and_wait(priv);
+	err = gve_adminq_kick_and_wait(priv);
+
+out:
+	mutex_unlock(&priv->adminq_lock);
+	return err;
 }
 
 static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv,
@@ -731,6 +763,7 @@ static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv,
 		.ntfy_id = cpu_to_be32(rx->ntfy_id),
 		.queue_resources_addr = cpu_to_be64(rx->q_resources_bus),
 		.rx_ring_size = cpu_to_be16(priv->rx_desc_cnt),
+		.packet_buffer_size = cpu_to_be16(rx->packet_buffer_size),
 	};
 
 	if (gve_is_gqi(priv)) {
@@ -743,7 +776,6 @@ static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv,
 			cpu_to_be64(rx->data.data_bus);
 		cmd->create_rx_queue.index = cpu_to_be32(queue_index);
 		cmd->create_rx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
-		cmd->create_rx_queue.packet_buffer_size = cpu_to_be16(rx->packet_buffer_size);
 	} else {
 		u32 qpl_id = 0;
 
@@ -756,8 +788,6 @@ static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv,
 			cpu_to_be64(rx->dqo.complq.bus);
 		cmd->create_rx_queue.rx_data_ring_addr =
 			cpu_to_be64(rx->dqo.bufq.bus);
-		cmd->create_rx_queue.packet_buffer_size =
-			cpu_to_be16(priv->data_buffer_size_dqo);
 		cmd->create_rx_queue.rx_buff_ring_size =
 			cpu_to_be16(priv->rx_desc_cnt);
 		cmd->create_rx_queue.enable_rsc =
@@ -790,13 +820,19 @@ int gve_adminq_create_rx_queues(struct gve_priv *priv, u32 num_queues)
 	int err;
 	int i;
 
+	mutex_lock(&priv->adminq_lock);
+
 	for (i = 0; i < num_queues; i++) {
 		err = gve_adminq_create_rx_queue(priv, i);
 		if (err)
-			return err;
+			goto out;
 	}
 
-	return gve_adminq_kick_and_wait(priv);
+	err = gve_adminq_kick_and_wait(priv);
+
+out:
+	mutex_unlock(&priv->adminq_lock);
+	return err;
 }
 
 static int gve_adminq_destroy_tx_queue(struct gve_priv *priv, u32 queue_index)
@@ -822,13 +858,19 @@ int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_qu
 	int err;
 	int i;
 
+	mutex_lock(&priv->adminq_lock);
+
 	for (i = start_id; i < start_id + num_queues; i++) {
 		err = gve_adminq_destroy_tx_queue(priv, i);
 		if (err)
-			return err;
+			goto out;
 	}
 
-	return gve_adminq_kick_and_wait(priv);
+	err = gve_adminq_kick_and_wait(priv);
+
+out:
+	mutex_unlock(&priv->adminq_lock);
+	return err;
 }
 
 static void gve_adminq_make_destroy_rx_queue_cmd(union gve_adminq_command *cmd,
@@ -863,13 +905,19 @@ int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 num_queues)
 	int err;
 	int i;
 
+	mutex_lock(&priv->adminq_lock);
+
 	for (i = 0; i < num_queues; i++) {
 		err = gve_adminq_destroy_rx_queue(priv, i);
 		if (err)
-			return err;
+			goto out;
 	}
 
-	return gve_adminq_kick_and_wait(priv);
+	err = gve_adminq_kick_and_wait(priv);
+
+out:
+	mutex_unlock(&priv->adminq_lock);
+	return err;
 }
 
 static void gve_set_default_desc_cnt(struct gve_priv *priv,
@@ -885,6 +933,15 @@ static void gve_set_default_desc_cnt(struct gve_priv *priv,
 	priv->min_rx_desc_cnt = priv->rx_desc_cnt;
 }
 
+static void gve_set_default_rss_sizes(struct gve_priv *priv)
+{
+	if (!gve_is_gqi(priv)) {
+		priv->rss_key_size = GVE_RSS_KEY_SIZE;
+		priv->rss_lut_size = GVE_RSS_INDIR_SIZE;
+		priv->cache_rss_config = true;
+	}
+}
+
 static void gve_enable_supported_features(struct gve_priv *priv,
 					  u32 supported_features_mask,
 					  const struct gve_device_option_jumbo_frames
@@ -897,6 +954,8 @@ static void gve_enable_supported_features(struct gve_priv *priv,
 					  *dev_op_flow_steering,
 					  const struct gve_device_option_rss_config
 					  *dev_op_rss_config,
+					  const struct gve_device_option_nic_timestamp
+					  *dev_op_nic_timestamp,
 					  const struct gve_device_option_modify_ring
 					  *dev_op_modify_ring)
 {
@@ -928,6 +987,10 @@ static void gve_enable_supported_features(struct gve_priv *priv,
 		dev_info(&priv->pdev->dev,
 			 "BUFFER SIZES device option enabled with max_rx_buffer_size of %u, header_buf_size of %u.\n",
 			 priv->max_rx_buffer_size, priv->header_buf_size);
+		if (gve_is_dqo(priv) &&
+		    priv->max_rx_buffer_size > GVE_DEFAULT_RX_BUFFER_SIZE)
+			priv->rx_cfg.packet_buffer_size =
+				priv->max_rx_buffer_size;
 	}
 
 	/* Read and store ring size ranges given by device */
@@ -968,11 +1031,20 @@ static void gve_enable_supported_features(struct gve_priv *priv,
 			be16_to_cpu(dev_op_rss_config->hash_key_size);
 		priv->rss_lut_size =
 			be16_to_cpu(dev_op_rss_config->hash_lut_size);
+		priv->cache_rss_config = false;
+		dev_dbg(&priv->pdev->dev,
+			"RSS device option enabled with key size of %u, lut size of %u.\n",
+			priv->rss_key_size, priv->rss_lut_size);
 	}
+
+	if (dev_op_nic_timestamp &&
+	    (supported_features_mask & GVE_SUP_NIC_TIMESTAMP_MASK))
+		priv->nic_timestamp_supported = true;
 }
 
 int gve_adminq_describe_device(struct gve_priv *priv)
 {
+	struct gve_device_option_nic_timestamp *dev_op_nic_timestamp = NULL;
 	struct gve_device_option_flow_steering *dev_op_flow_steering = NULL;
 	struct gve_device_option_buffer_sizes *dev_op_buffer_sizes = NULL;
 	struct gve_device_option_jumbo_frames *dev_op_jumbo_frames = NULL;
@@ -1013,6 +1085,7 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 					 &dev_op_buffer_sizes,
 					 &dev_op_flow_steering,
 					 &dev_op_rss_config,
+					 &dev_op_nic_timestamp,
 					 &dev_op_modify_ring);
 	if (err)
 		goto free_device_descriptor;
@@ -1052,6 +1125,8 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 	/* set default descriptor counts */
 	gve_set_default_desc_cnt(priv, descriptor);
 
+	gve_set_default_rss_sizes(priv);
+
 	/* DQO supports LRO. */
 	if (!gve_is_gqi(priv))
 		priv->dev->hw_features |= NETIF_F_LRO;
@@ -1075,7 +1150,8 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 	gve_enable_supported_features(priv, supported_features_mask,
 				      dev_op_jumbo_frames, dev_op_dqo_qpl,
 				      dev_op_buffer_sizes, dev_op_flow_steering,
-				      dev_op_rss_config, dev_op_modify_ring);
+				      dev_op_rss_config, dev_op_nic_timestamp,
+				      dev_op_modify_ring);
 
 free_device_descriptor:
 	dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus);
@@ -1187,6 +1263,22 @@ int gve_adminq_report_link_speed(struct gve_priv *priv)
 	return err;
 }
 
+int gve_adminq_report_nic_ts(struct gve_priv *priv,
+			     dma_addr_t nic_ts_report_addr)
+{
+	union gve_adminq_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_REPORT_NIC_TIMESTAMP);
+	cmd.report_nic_ts = (struct gve_adminq_report_nic_ts) {
+		.nic_ts_report_len =
+			cpu_to_be64(sizeof(struct gve_nic_ts_report)),
+		.nic_ts_report_addr = cpu_to_be64(nic_ts_report_addr),
+	};
+
+	return gve_adminq_execute_cmd(priv, &cmd);
+}
+
 int gve_adminq_get_ptype_map_dqo(struct gve_priv *priv,
 				 struct gve_ptype_lut *ptype_lut)
 {
@@ -1276,8 +1368,9 @@ int gve_adminq_reset_flow_rules(struct gve_priv *priv)
 
 int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh)
 {
+	const u32 *hash_lut_to_config = NULL;
+	const u8 *hash_key_to_config = NULL;
 	dma_addr_t lut_bus = 0, key_bus = 0;
-	u16 key_size = 0, lut_size = 0;
 	union gve_adminq_command cmd;
 	__be32 *lut = NULL;
 	u8 hash_alg = 0;
@@ -1287,7 +1380,7 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r
 
 	switch (rxfh->hfunc) {
 	case ETH_RSS_HASH_NO_CHANGE:
-		break;
+		fallthrough;
 	case ETH_RSS_HASH_TOP:
 		hash_alg = ETH_RSS_HASH_TOP;
 		break;
@@ -1296,27 +1389,46 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r
 	}
 
 	if (rxfh->indir) {
-		lut_size = priv->rss_lut_size;
+		if (rxfh->indir_size != priv->rss_lut_size)
+			return -EINVAL;
+
+		hash_lut_to_config = rxfh->indir;
+	} else if (priv->cache_rss_config) {
+		hash_lut_to_config = priv->rss_config.hash_lut;
+	}
+
+	if (hash_lut_to_config) {
 		lut = dma_alloc_coherent(&priv->pdev->dev,
-					 lut_size * sizeof(*lut),
+					 priv->rss_lut_size * sizeof(*lut),
 					 &lut_bus, GFP_KERNEL);
 		if (!lut)
 			return -ENOMEM;
 
 		for (i = 0; i < priv->rss_lut_size; i++)
-			lut[i] = cpu_to_be32(rxfh->indir[i]);
+			lut[i] = cpu_to_be32(hash_lut_to_config[i]);
 	}
 
 	if (rxfh->key) {
-		key_size = priv->rss_key_size;
+		if (rxfh->key_size != priv->rss_key_size) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		hash_key_to_config = rxfh->key;
+	} else if (priv->cache_rss_config) {
+		hash_key_to_config = priv->rss_config.hash_key;
+	}
+
+	if (hash_key_to_config) {
 		key = dma_alloc_coherent(&priv->pdev->dev,
-					 key_size, &key_bus, GFP_KERNEL);
+					 priv->rss_key_size,
+					 &key_bus, GFP_KERNEL);
 		if (!key) {
 			err = -ENOMEM;
 			goto out;
 		}
 
-		memcpy(key, rxfh->key, key_size);
+		memcpy(key, hash_key_to_config, priv->rss_key_size);
 	}
 
 	/* Zero-valued fields in the cmd.configure_rss instruct the device to
@@ -1330,8 +1442,10 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r
 					  BIT(GVE_RSS_HASH_TCPV6) |
 					  BIT(GVE_RSS_HASH_UDPV6)),
 		.hash_alg = hash_alg,
-		.hash_key_size = cpu_to_be16(key_size),
-		.hash_lut_size = cpu_to_be16(lut_size),
+		.hash_key_size =
+			cpu_to_be16((key_bus) ? priv->rss_key_size : 0),
+		.hash_lut_size =
+			cpu_to_be16((lut_bus) ? priv->rss_lut_size : 0),
 		.hash_key_addr = cpu_to_be64(key_bus),
 		.hash_lut_addr = cpu_to_be64(lut_bus),
 	};
@@ -1341,11 +1455,11 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r
 out:
 	if (lut)
 		dma_free_coherent(&priv->pdev->dev,
-				  lut_size * sizeof(*lut),
+				  priv->rss_lut_size * sizeof(*lut),
 				  lut, lut_bus);
 	if (key)
 		dma_free_coherent(&priv->pdev->dev,
-				  key_size, key, key_bus);
+				  priv->rss_key_size, key, key_bus);
 	return err;
 }
 
@@ -1449,12 +1563,15 @@ static int gve_adminq_process_rss_query(struct gve_priv *priv,
 	rxfh->hfunc = descriptor->hash_alg;
 
 	rss_info_addr = (void *)(descriptor + 1);
-	if (rxfh->key)
+	if (rxfh->key) {
+		rxfh->key_size = priv->rss_key_size;
 		memcpy(rxfh->key, rss_info_addr, priv->rss_key_size);
+	}
 
 	rss_info_addr += priv->rss_key_size;
 	lut = (__be32 *)rss_info_addr;
 	if (rxfh->indir) {
+		rxfh->indir_size = priv->rss_lut_size;
 		for (i = 0; i < priv->rss_lut_size; i++)
 			rxfh->indir[i] = be32_to_cpu(lut[i]);
 	}
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h
index 228217458275..22a74b6aa17e 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.h
+++ b/drivers/net/ethernet/google/gve/gve_adminq.h
@@ -27,6 +27,7 @@ enum gve_adminq_opcodes {
 	GVE_ADMINQ_GET_PTYPE_MAP		= 0xE,
 	GVE_ADMINQ_VERIFY_DRIVER_COMPATIBILITY	= 0xF,
 	GVE_ADMINQ_QUERY_FLOW_RULES		= 0x10,
+	GVE_ADMINQ_REPORT_NIC_TIMESTAMP		= 0x11,
 	GVE_ADMINQ_QUERY_RSS			= 0x12,
 
 	/* For commands that are larger than 56 bytes */
@@ -174,6 +175,12 @@ struct gve_device_option_rss_config {
 
 static_assert(sizeof(struct gve_device_option_rss_config) == 8);
 
+struct gve_device_option_nic_timestamp {
+	__be32 supported_features_mask;
+};
+
+static_assert(sizeof(struct gve_device_option_nic_timestamp) == 4);
+
 /* Terminology:
  *
  * RDA - Raw DMA Addressing - Buffers associated with SKBs are directly DMA
@@ -192,6 +199,7 @@ enum gve_dev_opt_id {
 	GVE_DEV_OPT_ID_JUMBO_FRAMES		= 0x8,
 	GVE_DEV_OPT_ID_BUFFER_SIZES		= 0xa,
 	GVE_DEV_OPT_ID_FLOW_STEERING		= 0xb,
+	GVE_DEV_OPT_ID_NIC_TIMESTAMP		= 0xd,
 	GVE_DEV_OPT_ID_RSS_CONFIG		= 0xe,
 };
 
@@ -206,6 +214,7 @@ enum gve_dev_opt_req_feat_mask {
 	GVE_DEV_OPT_REQ_FEAT_MASK_MODIFY_RING		= 0x0,
 	GVE_DEV_OPT_REQ_FEAT_MASK_FLOW_STEERING		= 0x0,
 	GVE_DEV_OPT_REQ_FEAT_MASK_RSS_CONFIG		= 0x0,
+	GVE_DEV_OPT_REQ_FEAT_MASK_NIC_TIMESTAMP		= 0x0,
 };
 
 enum gve_sup_feature_mask {
@@ -214,6 +223,7 @@ enum gve_sup_feature_mask {
 	GVE_SUP_BUFFER_SIZES_MASK	= 1 << 4,
 	GVE_SUP_FLOW_STEERING_MASK	= 1 << 5,
 	GVE_SUP_RSS_CONFIG_MASK		= 1 << 7,
+	GVE_SUP_NIC_TIMESTAMP_MASK	= 1 << 8,
 };
 
 #define GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING 0x0
@@ -392,6 +402,21 @@ struct gve_adminq_report_link_speed {
 
 static_assert(sizeof(struct gve_adminq_report_link_speed) == 8);
 
+struct gve_adminq_report_nic_ts {
+	__be64 nic_ts_report_len;
+	__be64 nic_ts_report_addr;
+};
+
+static_assert(sizeof(struct gve_adminq_report_nic_ts) == 16);
+
+struct gve_nic_ts_report {
+	__be64 nic_timestamp; /* NIC clock in nanoseconds */
+	__be64 reserved1;
+	__be64 reserved2;
+	__be64 reserved3;
+	__be64 reserved4;
+};
+
 struct stats {
 	__be32 stat_name;
 	__be32 queue_id;
@@ -451,7 +476,7 @@ struct gve_ptype_entry {
 };
 
 struct gve_ptype_map {
-	struct gve_ptype_entry ptypes[1 << 10]; /* PTYPES are always 10 bits. */
+	struct gve_ptype_entry ptypes[GVE_NUM_PTYPES]; /* PTYPES are always 10 bits. */
 };
 
 struct gve_adminq_get_ptype_map {
@@ -585,6 +610,7 @@ union gve_adminq_command {
 			struct gve_adminq_query_flow_rules query_flow_rules;
 			struct gve_adminq_configure_rss configure_rss;
 			struct gve_adminq_query_rss query_rss;
+			struct gve_adminq_report_nic_ts report_nic_ts;
 			struct gve_adminq_extended_command extended_command;
 		};
 	};
@@ -624,6 +650,8 @@ int gve_adminq_reset_flow_rules(struct gve_priv *priv);
 int gve_adminq_query_flow_rules(struct gve_priv *priv, u16 query_opcode, u32 starting_loc);
 int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh);
 int gve_adminq_query_rss_config(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh);
+int gve_adminq_report_nic_ts(struct gve_priv *priv,
+			     dma_addr_t nic_ts_report_addr);
 
 struct gve_ptype_lut;
 int gve_adminq_get_ptype_map_dqo(struct gve_priv *priv,
diff --git a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
index 403f0f335ba6..0e2b703c673a 100644
--- a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2015-2024 Google, Inc.
  */
 
+#include <net/xdp_sock_drv.h>
 #include "gve.h"
 #include "gve_utils.h"
 
@@ -29,6 +30,10 @@ struct gve_rx_buf_state_dqo *gve_alloc_buf_state(struct gve_rx_ring *rx)
 	/* Point buf_state to itself to mark it as allocated */
 	buf_state->next = buffer_id;
 
+	/* Clear the buffer pointers */
+	buf_state->page_info.page = NULL;
+	buf_state->xsk_buff = NULL;
+
 	return buf_state;
 }
 
@@ -139,7 +144,8 @@ int gve_alloc_qpl_page_dqo(struct gve_rx_ring *rx,
 	buf_state->page_info.page_offset = 0;
 	buf_state->page_info.page_address =
 		page_address(buf_state->page_info.page);
-	buf_state->page_info.buf_size = priv->data_buffer_size_dqo;
+	buf_state->page_info.buf_size = rx->packet_buffer_truesize;
+	buf_state->page_info.pad = rx->rx_headroom;
 	buf_state->last_single_ref_offset = 0;
 
 	/* The page already has 1 ref. */
@@ -162,7 +168,7 @@ void gve_free_qpl_page_dqo(struct gve_rx_buf_state_dqo *buf_state)
 void gve_try_recycle_buf(struct gve_priv *priv, struct gve_rx_ring *rx,
 			 struct gve_rx_buf_state_dqo *buf_state)
 {
-	const u16 data_buffer_size = priv->data_buffer_size_dqo;
+	const u16 data_buffer_size = rx->packet_buffer_truesize;
 	int pagecount;
 
 	/* Can't reuse if we only fit one buffer per page */
@@ -205,51 +211,60 @@ void gve_free_to_page_pool(struct gve_rx_ring *rx,
 			   struct gve_rx_buf_state_dqo *buf_state,
 			   bool allow_direct)
 {
-	struct page *page = buf_state->page_info.page;
+	netmem_ref netmem = buf_state->page_info.netmem;
 
-	if (!page)
+	if (!netmem)
 		return;
 
-	page_pool_put_full_page(page->pp, page, allow_direct);
-	buf_state->page_info.page = NULL;
+	page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, allow_direct);
+	buf_state->page_info.netmem = 0;
 }
 
 static int gve_alloc_from_page_pool(struct gve_rx_ring *rx,
 				    struct gve_rx_buf_state_dqo *buf_state)
 {
-	struct gve_priv *priv = rx->gve;
-	struct page *page;
+	netmem_ref netmem;
 
-	buf_state->page_info.buf_size = priv->data_buffer_size_dqo;
-	page = page_pool_alloc(rx->dqo.page_pool,
-			       &buf_state->page_info.page_offset,
-			       &buf_state->page_info.buf_size, GFP_ATOMIC);
+	buf_state->page_info.buf_size = rx->packet_buffer_truesize;
+	netmem = page_pool_alloc_netmem(rx->dqo.page_pool,
+					&buf_state->page_info.page_offset,
+					&buf_state->page_info.buf_size,
+					GFP_ATOMIC);
 
-	if (!page)
+	if (!netmem)
 		return -ENOMEM;
 
-	buf_state->page_info.page = page;
-	buf_state->page_info.page_address = page_address(page);
-	buf_state->addr = page_pool_get_dma_addr(page);
+	buf_state->page_info.netmem = netmem;
+	buf_state->page_info.page_address = netmem_address(netmem);
+	buf_state->addr = page_pool_get_dma_addr_netmem(netmem);
+	buf_state->page_info.pad = rx->dqo.page_pool->p.offset;
 
 	return 0;
 }
 
 struct page_pool *gve_rx_create_page_pool(struct gve_priv *priv,
-					  struct gve_rx_ring *rx)
+					  struct gve_rx_ring *rx,
+					  bool xdp)
 {
 	u32 ntfy_id = gve_rx_idx_to_ntfy(priv, rx->q_num);
 	struct page_pool_params pp = {
 		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
 		.order = 0,
 		.pool_size = GVE_PAGE_POOL_SIZE_MULTIPLIER * priv->rx_desc_cnt,
+		.nid = priv->numa_node,
 		.dev = &priv->pdev->dev,
 		.netdev = priv->dev,
 		.napi = &priv->ntfy_blocks[ntfy_id].napi,
 		.max_len = PAGE_SIZE,
-		.dma_dir = DMA_FROM_DEVICE,
+		.dma_dir = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE,
+		.offset = xdp ? XDP_PACKET_HEADROOM : 0,
 	};
 
+	if (priv->header_split_enabled) {
+		pp.flags |= PP_FLAG_ALLOW_UNREADABLE_NETMEM;
+		pp.queue_idx = rx->q_num;
+	}
+
 	return page_pool_create(&pp);
 }
 
@@ -269,7 +284,7 @@ void gve_reuse_buffer(struct gve_rx_ring *rx,
 		      struct gve_rx_buf_state_dqo *buf_state)
 {
 	if (rx->dqo.page_pool) {
-		buf_state->page_info.page = NULL;
+		buf_state->page_info.netmem = 0;
 		gve_free_buf_state(rx, buf_state);
 	} else {
 		gve_dec_pagecnt_bias(&buf_state->page_info);
@@ -281,7 +296,24 @@ int gve_alloc_buffer(struct gve_rx_ring *rx, struct gve_rx_desc_dqo *desc)
 {
 	struct gve_rx_buf_state_dqo *buf_state;
 
-	if (rx->dqo.page_pool) {
+	if (rx->xsk_pool) {
+		buf_state = gve_alloc_buf_state(rx);
+		if (unlikely(!buf_state))
+			return -ENOMEM;
+
+		buf_state->xsk_buff = xsk_buff_alloc(rx->xsk_pool);
+		if (unlikely(!buf_state->xsk_buff)) {
+			xsk_set_rx_need_wakeup(rx->xsk_pool);
+			gve_free_buf_state(rx, buf_state);
+			return -ENOMEM;
+		}
+		/* Allocated xsk buffer. Clear wakeup in case it was set. */
+		xsk_clear_rx_need_wakeup(rx->xsk_pool);
+		desc->buf_id = cpu_to_le16(buf_state - rx->dqo.buf_states);
+		desc->buf_addr =
+			cpu_to_le64(xsk_buff_xdp_get_dma(buf_state->xsk_buff));
+		return 0;
+	} else if (rx->dqo.page_pool) {
 		buf_state = gve_alloc_buf_state(rx);
 		if (WARN_ON_ONCE(!buf_state))
 			return -ENOMEM;
@@ -301,7 +333,8 @@ int gve_alloc_buffer(struct gve_rx_ring *rx, struct gve_rx_desc_dqo *desc)
 	}
 	desc->buf_id = cpu_to_le16(buf_state - rx->dqo.buf_states);
 	desc->buf_addr = cpu_to_le64(buf_state->addr +
-				     buf_state->page_info.page_offset);
+				     buf_state->page_info.page_offset +
+				     buf_state->page_info.pad);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/google/gve/gve_desc_dqo.h b/drivers/net/ethernet/google/gve/gve_desc_dqo.h
index f79cd0591110..f7786b03c744 100644
--- a/drivers/net/ethernet/google/gve/gve_desc_dqo.h
+++ b/drivers/net/ethernet/google/gve/gve_desc_dqo.h
@@ -236,7 +236,8 @@ struct gve_rx_compl_desc_dqo {
 
 	u8 status_error1;
 
-	__le16 reserved5;
+	u8 reserved5;
+	u8 ts_sub_nsecs_low;
 	__le16 buf_id; /* Buffer ID which was sent on the buffer queue. */
 
 	union {
@@ -247,7 +248,8 @@ struct gve_rx_compl_desc_dqo {
 	};
 	__le32 hash;
 	__le32 reserved6;
-	__le64 reserved7;
+	__le32 reserved7;
+	__le32 ts; /* timestamp in nanosecs */
 } __packed;
 
 static_assert(sizeof(struct gve_rx_compl_desc_dqo) == 32);
diff --git a/drivers/net/ethernet/google/gve/gve_dqo.h b/drivers/net/ethernet/google/gve/gve_dqo.h
index e83773fb891f..5871f773f0c7 100644
--- a/drivers/net/ethernet/google/gve/gve_dqo.h
+++ b/drivers/net/ethernet/google/gve/gve_dqo.h
@@ -36,7 +36,10 @@ netdev_tx_t gve_tx_dqo(struct sk_buff *skb, struct net_device *dev);
 netdev_features_t gve_features_check_dqo(struct sk_buff *skb,
 					 struct net_device *dev,
 					 netdev_features_t features);
+int gve_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp);
 bool gve_tx_poll_dqo(struct gve_notify_block *block, bool do_clean);
+bool gve_xdp_poll_dqo(struct gve_notify_block *block);
+bool gve_xsk_tx_poll_dqo(struct gve_notify_block *block, int budget);
 int gve_rx_poll_dqo(struct gve_notify_block *block, int budget);
 int gve_tx_alloc_rings_dqo(struct gve_priv *priv,
 			   struct gve_tx_alloc_rings_cfg *cfg);
@@ -60,6 +63,7 @@ int gve_clean_tx_done_dqo(struct gve_priv *priv, struct gve_tx_ring *tx,
 			  struct napi_struct *napi);
 void gve_rx_post_buffers_dqo(struct gve_rx_ring *rx);
 void gve_rx_write_doorbell_dqo(const struct gve_priv *priv, int queue_idx);
+void gve_xdp_tx_flush_dqo(struct gve_priv *priv, u32 xdp_qid);
 
 static inline void
 gve_tx_put_doorbell_dqo(const struct gve_priv *priv,
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index bdfc6e77b2af..52500ae8348e 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -63,11 +63,11 @@ static const char gve_gstrings_rx_stats[][ETH_GSTRING_LEN] = {
 static const char gve_gstrings_tx_stats[][ETH_GSTRING_LEN] = {
 	"tx_posted_desc[%u]", "tx_completed_desc[%u]", "tx_consumed_desc[%u]", "tx_bytes[%u]",
 	"tx_wake[%u]", "tx_stop[%u]", "tx_event_counter[%u]",
-	"tx_dma_mapping_error[%u]", "tx_xsk_wakeup[%u]",
-	"tx_xsk_done[%u]", "tx_xsk_sent[%u]", "tx_xdp_xmit[%u]", "tx_xdp_xmit_errors[%u]"
+	"tx_dma_mapping_error[%u]",
+	"tx_xsk_sent[%u]", "tx_xdp_xmit[%u]", "tx_xdp_xmit_errors[%u]"
 };
 
-static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = {
+static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] __nonstring_array = {
 	"adminq_prod_cnt", "adminq_cmd_fail", "adminq_timeouts",
 	"adminq_describe_device_cnt", "adminq_cfg_device_resources_cnt",
 	"adminq_register_page_list_cnt", "adminq_unregister_page_list_cnt",
@@ -76,7 +76,7 @@ static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = {
 	"adminq_dcfg_device_resources_cnt", "adminq_set_driver_parameter_cnt",
 	"adminq_report_stats_cnt", "adminq_report_link_speed_cnt", "adminq_get_ptype_map_cnt",
 	"adminq_query_flow_rules", "adminq_cfg_flow_rule", "adminq_cfg_rss_cnt",
-	"adminq_query_rss_cnt",
+	"adminq_query_rss_cnt", "adminq_report_nic_timestamp_cnt",
 };
 
 static const char gve_gstrings_priv_flags[][ETH_GSTRING_LEN] = {
@@ -113,7 +113,7 @@ static void gve_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 						i);
 
 		for (i = 0; i < ARRAY_SIZE(gve_gstrings_adminq_stats); i++)
-			ethtool_puts(&s, gve_gstrings_adminq_stats[i]);
+			ethtool_cpy(&s, gve_gstrings_adminq_stats[i]);
 
 		break;
 
@@ -392,7 +392,9 @@ gve_get_ethtool_stats(struct net_device *netdev,
 				 */
 				data[i++] = 0;
 				data[i++] = 0;
-				data[i++] = tx->dqo_tx.tail - tx->dqo_tx.head;
+				data[i++] =
+					(tx->dqo_tx.tail - tx->dqo_tx.head) &
+					tx->mask;
 			}
 			do {
 				start =
@@ -417,9 +419,7 @@ gve_get_ethtool_stats(struct net_device *netdev,
 					data[i++] = value;
 				}
 			}
-			/* XDP xsk counters */
-			data[i++] = tx->xdp_xsk_wakeup;
-			data[i++] = tx->xdp_xsk_done;
+			/* XDP counters */
 			do {
 				start = u64_stats_fetch_begin(&priv->tx[ring].statss);
 				data[i] = tx->xdp_xsk_sent;
@@ -456,6 +456,7 @@ gve_get_ethtool_stats(struct net_device *netdev,
 	data[i++] = priv->adminq_cfg_flow_rule_cnt;
 	data[i++] = priv->adminq_cfg_rss_cnt;
 	data[i++] = priv->adminq_query_rss_cnt;
+	data[i++] = priv->adminq_report_nic_timestamp_cnt;
 }
 
 static void gve_get_channels(struct net_device *netdev,
@@ -477,11 +478,12 @@ static int gve_set_channels(struct net_device *netdev,
 			    struct ethtool_channels *cmd)
 {
 	struct gve_priv *priv = netdev_priv(netdev);
-	struct gve_queue_config new_tx_cfg = priv->tx_cfg;
-	struct gve_queue_config new_rx_cfg = priv->rx_cfg;
+	struct gve_tx_queue_config new_tx_cfg = priv->tx_cfg;
+	struct gve_rx_queue_config new_rx_cfg = priv->rx_cfg;
 	struct ethtool_channels old_settings;
 	int new_tx = cmd->tx_count;
 	int new_rx = cmd->rx_count;
+	bool reset_rss = false;
 
 	gve_get_channels(netdev, &old_settings);
 
@@ -492,22 +494,27 @@ static int gve_set_channels(struct net_device *netdev,
 	if (!new_rx || !new_tx)
 		return -EINVAL;
 
-	if (priv->num_xdp_queues &&
-	    (new_tx != new_rx || (2 * new_tx > priv->tx_cfg.max_queues))) {
-		dev_err(&priv->pdev->dev, "XDP load failed: The number of configured RX queues should be equal to the number of configured TX queues and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues");
-		return -EINVAL;
-	}
+	if (priv->xdp_prog) {
+		if (new_tx != new_rx ||
+		    (2 * new_tx > priv->tx_cfg.max_queues)) {
+			dev_err(&priv->pdev->dev, "The number of configured RX queues should be equal to the number of configured TX queues and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues when XDP program is installed");
+			return -EINVAL;
+		}
 
-	if (!netif_running(netdev)) {
-		priv->tx_cfg.num_queues = new_tx;
-		priv->rx_cfg.num_queues = new_rx;
-		return 0;
+		/* One XDP TX queue per RX queue. */
+		new_tx_cfg.num_xdp_queues = new_rx;
+	} else {
+		new_tx_cfg.num_xdp_queues = 0;
 	}
 
+	if (new_rx != priv->rx_cfg.num_queues &&
+	    priv->cache_rss_config && !netif_is_rxfh_configured(netdev))
+		reset_rss = true;
+
 	new_tx_cfg.num_queues = new_tx;
 	new_rx_cfg.num_queues = new_rx;
 
-	return gve_adjust_queues(priv, new_rx_cfg, new_tx_cfg);
+	return gve_adjust_queues(priv, new_rx_cfg, new_tx_cfg, reset_rss);
 }
 
 static void gve_get_ringparam(struct net_device *netdev,
@@ -522,6 +529,8 @@ static void gve_get_ringparam(struct net_device *netdev,
 	cmd->rx_pending = priv->rx_desc_cnt;
 	cmd->tx_pending = priv->tx_desc_cnt;
 
+	kernel_cmd->rx_buf_len = priv->rx_cfg.packet_buffer_size;
+
 	if (!gve_header_split_supported(priv))
 		kernel_cmd->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_UNKNOWN;
 	else if (priv->header_split_enabled)
@@ -530,34 +539,6 @@ static void gve_get_ringparam(struct net_device *netdev,
 		kernel_cmd->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_DISABLED;
 }
 
-static int gve_adjust_ring_sizes(struct gve_priv *priv,
-				 u16 new_tx_desc_cnt,
-				 u16 new_rx_desc_cnt)
-{
-	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
-	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
-	int err;
-
-	/* get current queue configuration */
-	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
-
-	/* copy over the new ring_size from ethtool */
-	tx_alloc_cfg.ring_size = new_tx_desc_cnt;
-	rx_alloc_cfg.ring_size = new_rx_desc_cnt;
-
-	if (netif_running(priv->dev)) {
-		err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
-		if (err)
-			return err;
-	}
-
-	/* Set new ring_size for the next up */
-	priv->tx_desc_cnt = new_tx_desc_cnt;
-	priv->rx_desc_cnt = new_rx_desc_cnt;
-
-	return 0;
-}
-
 static int gve_validate_req_ring_size(struct gve_priv *priv, u16 new_tx_desc_cnt,
 				      u16 new_rx_desc_cnt)
 {
@@ -577,34 +558,68 @@ static int gve_validate_req_ring_size(struct gve_priv *priv, u16 new_tx_desc_cnt
 	return 0;
 }
 
+static int gve_set_ring_sizes_config(struct gve_priv *priv, u16 new_tx_desc_cnt,
+				     u16 new_rx_desc_cnt,
+				     struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
+				     struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
+{
+	if (new_tx_desc_cnt == priv->tx_desc_cnt &&
+	    new_rx_desc_cnt == priv->rx_desc_cnt)
+		return 0;
+
+	if (!priv->modify_ring_size_enabled) {
+		dev_err(&priv->pdev->dev, "Modify ring size is not supported.\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (gve_validate_req_ring_size(priv, new_tx_desc_cnt, new_rx_desc_cnt))
+		return -EINVAL;
+
+	tx_alloc_cfg->ring_size = new_tx_desc_cnt;
+	rx_alloc_cfg->ring_size = new_rx_desc_cnt;
+	return 0;
+}
+
 static int gve_set_ringparam(struct net_device *netdev,
 			     struct ethtool_ringparam *cmd,
 			     struct kernel_ethtool_ringparam *kernel_cmd,
 			     struct netlink_ext_ack *extack)
 {
+	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
+	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
 	struct gve_priv *priv = netdev_priv(netdev);
-	u16 new_tx_cnt, new_rx_cnt;
 	int err;
 
-	err = gve_set_hsplit_config(priv, kernel_cmd->tcp_data_split);
+	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
+
+	err = gve_set_rx_buf_len_config(priv, kernel_cmd->rx_buf_len, extack,
+					&rx_alloc_cfg);
 	if (err)
 		return err;
 
-	if (cmd->tx_pending == priv->tx_desc_cnt && cmd->rx_pending == priv->rx_desc_cnt)
-		return 0;
-
-	if (!priv->modify_ring_size_enabled) {
-		dev_err(&priv->pdev->dev, "Modify ring size is not supported.\n");
-		return -EOPNOTSUPP;
-	}
-
-	new_tx_cnt = cmd->tx_pending;
-	new_rx_cnt = cmd->rx_pending;
+	err = gve_set_hsplit_config(priv, kernel_cmd->tcp_data_split,
+				    &rx_alloc_cfg);
+	if (err)
+		return err;
 
-	if (gve_validate_req_ring_size(priv, new_tx_cnt, new_rx_cnt))
-		return -EINVAL;
+	err = gve_set_ring_sizes_config(priv, cmd->tx_pending, cmd->rx_pending,
+					&tx_alloc_cfg, &rx_alloc_cfg);
+	if (err)
+		return err;
 
-	return gve_adjust_ring_sizes(priv, new_tx_cnt, new_rx_cnt);
+	if (netif_running(priv->dev)) {
+		err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
+		if (err)
+			return err;
+	} else {
+		/* Set ring params for the next up */
+		priv->rx_cfg.packet_buffer_size =
+			rx_alloc_cfg.packet_buffer_size;
+		priv->header_split_enabled = rx_alloc_cfg.enable_header_split;
+		priv->tx_desc_cnt = tx_alloc_cfg.ring_size;
+		priv->rx_desc_cnt = rx_alloc_cfg.ring_size;
+	}
+	return 0;
 }
 
 static int gve_user_reset(struct net_device *netdev, u32 *flags)
@@ -643,8 +658,7 @@ static int gve_set_tunable(struct net_device *netdev,
 	switch (etuna->id) {
 	case ETHTOOL_RX_COPYBREAK:
 	{
-		u32 max_copybreak = gve_is_gqi(priv) ?
-			GVE_DEFAULT_RX_BUFFER_SIZE : priv->data_buffer_size_dqo;
+		u32 max_copybreak = priv->rx_cfg.packet_buffer_size;
 
 		len = *(u32 *)value;
 		if (len > max_copybreak)
@@ -662,7 +676,7 @@ static u32 gve_get_priv_flags(struct net_device *netdev)
 	struct gve_priv *priv = netdev_priv(netdev);
 	u32 ret_flags = 0;
 
-	/* Only 1 flag exists currently: report-stats (BIT(O)), so set that flag. */
+	/* Only 1 flag exists currently: report-stats (BIT(0)), so set that flag. */
 	if (priv->ethtool_flags & BIT(0))
 		ret_flags |= BIT(0);
 	return ret_flags;
@@ -700,7 +714,7 @@ static int gve_set_priv_flags(struct net_device *netdev, u32 flags)
 
 		memset(priv->stats_report->stats, 0, (tx_stats_num + rx_stats_num) *
 				   sizeof(struct stats));
-		del_timer_sync(&priv->stats_report_timer);
+		timer_delete_sync(&priv->stats_report_timer);
 	}
 	return 0;
 }
@@ -793,9 +807,6 @@ static int gve_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 	case ETHTOOL_SRXCLSRLDEL:
 		err = gve_del_flow_rule(priv, cmd);
 		break;
-	case ETHTOOL_SRXFH:
-		err = -EOPNOTSUPP;
-		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;
@@ -830,9 +841,6 @@ static int gve_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, u
 	case ETHTOOL_GRXCLSRLALL:
 		err = gve_get_flow_rule_ids(priv, cmd, (u32 *)rule_locs);
 		break;
-	case ETHTOOL_GRXFH:
-		err = -EOPNOTSUPP;
-		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;
@@ -855,6 +863,25 @@ static u32 gve_get_rxfh_indir_size(struct net_device *netdev)
 	return priv->rss_lut_size;
 }
 
+static void gve_get_rss_config_cache(struct gve_priv *priv,
+				     struct ethtool_rxfh_param *rxfh)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+
+	if (rxfh->key) {
+		rxfh->key_size = priv->rss_key_size;
+		memcpy(rxfh->key, rss_config->hash_key, priv->rss_key_size);
+	}
+
+	if (rxfh->indir) {
+		rxfh->indir_size = priv->rss_lut_size;
+		memcpy(rxfh->indir, rss_config->hash_lut,
+		       priv->rss_lut_size * sizeof(*rxfh->indir));
+	}
+}
+
 static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
 	struct gve_priv *priv = netdev_priv(netdev);
@@ -862,23 +889,73 @@ static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rx
 	if (!priv->rss_key_size || !priv->rss_lut_size)
 		return -EOPNOTSUPP;
 
+	if (priv->cache_rss_config) {
+		gve_get_rss_config_cache(priv, rxfh);
+		return 0;
+	}
+
 	return gve_adminq_query_rss_config(priv, rxfh);
 }
 
+static void gve_set_rss_config_cache(struct gve_priv *priv,
+				     struct ethtool_rxfh_param *rxfh)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+
+	if (rxfh->key)
+		memcpy(rss_config->hash_key, rxfh->key, priv->rss_key_size);
+
+	if (rxfh->indir)
+		memcpy(rss_config->hash_lut, rxfh->indir,
+		       priv->rss_lut_size * sizeof(*rxfh->indir));
+}
+
 static int gve_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
 			struct netlink_ext_ack *extack)
 {
 	struct gve_priv *priv = netdev_priv(netdev);
+	int err;
 
 	if (!priv->rss_key_size || !priv->rss_lut_size)
 		return -EOPNOTSUPP;
 
-	return gve_adminq_configure_rss(priv, rxfh);
+	err = gve_adminq_configure_rss(priv, rxfh);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Fail to configure RSS config");
+		return err;
+	}
+
+	if (priv->cache_rss_config)
+		gve_set_rss_config_cache(priv, rxfh);
+
+	return 0;
+}
+
+static int gve_get_ts_info(struct net_device *netdev,
+			   struct kernel_ethtool_ts_info *info)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+
+	ethtool_op_get_ts_info(netdev, info);
+
+	if (priv->nic_timestamp_supported) {
+		info->so_timestamping |= SOF_TIMESTAMPING_RX_HARDWARE |
+					 SOF_TIMESTAMPING_RAW_HARDWARE;
+
+		info->rx_filters |= BIT(HWTSTAMP_FILTER_NONE) |
+				    BIT(HWTSTAMP_FILTER_ALL);
+
+		if (priv->ptp)
+			info->phc_index = ptp_clock_index(priv->ptp->clock);
+	}
+
+	return 0;
 }
 
 const struct ethtool_ops gve_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS,
-	.supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT,
+	.supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT |
+				 ETHTOOL_RING_USE_RX_BUF_LEN,
 	.get_drvinfo = gve_get_drvinfo,
 	.get_strings = gve_get_strings,
 	.get_sset_count = gve_get_sset_count,
@@ -904,5 +981,5 @@ const struct ethtool_ops gve_ethtool_ops = {
 	.get_priv_flags = gve_get_priv_flags,
 	.set_priv_flags = gve_set_priv_flags,
 	.get_link_ksettings = gve_get_link_ksettings,
-	.get_ts_info = ethtool_op_get_ts_info,
+	.get_ts_info = gve_get_ts_info,
 };
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index e171ca248f9a..a5a2b18d309b 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2015-2024 Google LLC
  */
 
+#include <linux/bitmap.h>
 #include <linux/bpf.h>
 #include <linux/cpumask.h>
 #include <linux/etherdevice.h>
@@ -184,6 +185,43 @@ static void gve_free_flow_rule_caches(struct gve_priv *priv)
 	flow_rules_cache->rules_cache = NULL;
 }
 
+static int gve_alloc_rss_config_cache(struct gve_priv *priv)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+
+	if (!priv->cache_rss_config)
+		return 0;
+
+	rss_config->hash_key = kcalloc(priv->rss_key_size,
+				       sizeof(rss_config->hash_key[0]),
+				       GFP_KERNEL);
+	if (!rss_config->hash_key)
+		return -ENOMEM;
+
+	rss_config->hash_lut = kcalloc(priv->rss_lut_size,
+				       sizeof(rss_config->hash_lut[0]),
+				       GFP_KERNEL);
+	if (!rss_config->hash_lut)
+		goto free_rss_key_cache;
+
+	return 0;
+
+free_rss_key_cache:
+	kfree(rss_config->hash_key);
+	rss_config->hash_key = NULL;
+	return -ENOMEM;
+}
+
+static void gve_free_rss_config_cache(struct gve_priv *priv)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+
+	kfree(rss_config->hash_key);
+	kfree(rss_config->hash_lut);
+
+	memset(rss_config, 0, sizeof(*rss_config));
+}
+
 static int gve_alloc_counter_array(struct gve_priv *priv)
 {
 	priv->counter_array =
@@ -231,7 +269,8 @@ static void gve_stats_report_schedule(struct gve_priv *priv)
 
 static void gve_stats_report_timer(struct timer_list *t)
 {
-	struct gve_priv *priv = from_timer(priv, t, stats_report_timer);
+	struct gve_priv *priv = timer_container_of(priv, t,
+						   stats_report_timer);
 
 	mod_timer(&priv->stats_report_timer,
 		  round_jiffies(jiffies +
@@ -265,7 +304,7 @@ static void gve_free_stats_report(struct gve_priv *priv)
 	if (!priv->stats_report)
 		return;
 
-	del_timer_sync(&priv->stats_report_timer);
+	timer_delete_sync(&priv->stats_report_timer);
 	dma_free_coherent(&priv->pdev->dev, priv->stats_report_len,
 			  priv->stats_report, priv->stats_report_bus);
 	priv->stats_report = NULL;
@@ -333,6 +372,14 @@ int gve_napi_poll(struct napi_struct *napi, int budget)
 
 	if (block->rx) {
 		work_done = gve_rx_poll(block, budget);
+
+		/* Poll XSK TX as part of RX NAPI. Setup re-poll based on max of
+		 * TX and RX work done.
+		 */
+		if (priv->xdp_prog)
+			work_done = max_t(int, work_done,
+					  gve_xsk_tx_poll(block, budget));
+
 		reschedule |= work_done == budget;
 	}
 
@@ -368,14 +415,24 @@ int gve_napi_poll_dqo(struct napi_struct *napi, int budget)
 	bool reschedule = false;
 	int work_done = 0;
 
-	if (block->tx)
-		reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true);
+	if (block->tx) {
+		if (block->tx->q_num < priv->tx_cfg.num_queues)
+			reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true);
+		else
+			reschedule |= gve_xdp_poll_dqo(block);
+	}
 
 	if (!budget)
 		return 0;
 
 	if (block->rx) {
 		work_done = gve_rx_poll_dqo(block, budget);
+
+		/* Poll XSK TX as part of RX NAPI. Setup re-poll based on if
+		 * either datapath has more work to do.
+		 */
+		if (priv->xdp_prog)
+			reschedule |= gve_xsk_tx_poll_dqo(block, budget);
 		reschedule |= work_done == budget;
 	}
 
@@ -411,10 +468,19 @@ int gve_napi_poll_dqo(struct napi_struct *napi, int budget)
 	return work_done;
 }
 
+static const struct cpumask *gve_get_node_mask(struct gve_priv *priv)
+{
+	if (priv->numa_node == NUMA_NO_NODE)
+		return cpu_all_mask;
+	else
+		return cpumask_of_node(priv->numa_node);
+}
+
 static int gve_alloc_notify_blocks(struct gve_priv *priv)
 {
 	int num_vecs_requested = priv->num_ntfy_blks + 1;
-	unsigned int active_cpus;
+	const struct cpumask *node_mask;
+	unsigned int cur_cpu;
 	int vecs_enabled;
 	int i, j;
 	int err;
@@ -453,8 +519,6 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv)
 		if (priv->rx_cfg.num_queues > priv->rx_cfg.max_queues)
 			priv->rx_cfg.num_queues = priv->rx_cfg.max_queues;
 	}
-	/* Half the notification blocks go to TX and half to RX */
-	active_cpus = min_t(int, priv->num_ntfy_blks / 2, num_online_cpus());
 
 	/* Setup Management Vector  - the last vector */
 	snprintf(priv->mgmt_msix_name, sizeof(priv->mgmt_msix_name), "gve-mgmnt@pci:%s",
@@ -483,6 +547,8 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv)
 	}
 
 	/* Setup the other blocks - the first n-1 vectors */
+	node_mask = gve_get_node_mask(priv);
+	cur_cpu = cpumask_first(node_mask);
 	for (i = 0; i < priv->num_ntfy_blks; i++) {
 		struct gve_notify_block *block = &priv->ntfy_blocks[i];
 		int msix_idx = i;
@@ -499,9 +565,17 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv)
 			goto abort_with_some_ntfy_blocks;
 		}
 		block->irq = priv->msix_vectors[msix_idx].vector;
-		irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector,
-				      get_cpu_mask(i % active_cpus));
+		irq_set_affinity_and_hint(block->irq,
+					  cpumask_of(cur_cpu));
 		block->irq_db_index = &priv->irq_db_indices[i].index;
+
+		cur_cpu = cpumask_next(cur_cpu, node_mask);
+		/* Wrap once CPUs in the node have been exhausted, or when
+		 * starting RX queue affinities. TX and RX queues of the same
+		 * index share affinity.
+		 */
+		if (cur_cpu >= nr_cpu_ids || (i + 1) == priv->tx_cfg.max_queues)
+			cur_cpu = cpumask_first(node_mask);
 	}
 	return 0;
 abort_with_some_ntfy_blocks:
@@ -567,12 +641,18 @@ static int gve_setup_device_resources(struct gve_priv *priv)
 	err = gve_alloc_flow_rule_caches(priv);
 	if (err)
 		return err;
-	err = gve_alloc_counter_array(priv);
+	err = gve_alloc_rss_config_cache(priv);
 	if (err)
 		goto abort_with_flow_rule_caches;
-	err = gve_alloc_notify_blocks(priv);
+	err = gve_alloc_counter_array(priv);
+	if (err)
+		goto abort_with_rss_config_cache;
+	err = gve_init_clock(priv);
 	if (err)
 		goto abort_with_counter;
+	err = gve_alloc_notify_blocks(priv);
+	if (err)
+		goto abort_with_clock;
 	err = gve_alloc_stats_report(priv);
 	if (err)
 		goto abort_with_ntfy_blocks;
@@ -603,6 +683,12 @@ static int gve_setup_device_resources(struct gve_priv *priv)
 		}
 	}
 
+	err = gve_init_rss_config(priv, priv->rx_cfg.num_queues);
+	if (err) {
+		dev_err(&priv->pdev->dev, "Failed to init RSS config");
+		goto abort_with_ptype_lut;
+	}
+
 	err = gve_adminq_report_stats(priv, priv->stats_report_len,
 				      priv->stats_report_bus,
 				      GVE_STATS_REPORT_TIMER_PERIOD);
@@ -619,8 +705,12 @@ abort_with_stats_report:
 	gve_free_stats_report(priv);
 abort_with_ntfy_blocks:
 	gve_free_notify_blocks(priv);
+abort_with_clock:
+	gve_teardown_clock(priv);
 abort_with_counter:
 	gve_free_counter_array(priv);
+abort_with_rss_config_cache:
+	gve_free_rss_config_cache(priv);
 abort_with_flow_rule_caches:
 	gve_free_flow_rule_caches(priv);
 
@@ -661,9 +751,11 @@ static void gve_teardown_device_resources(struct gve_priv *priv)
 	priv->ptype_lut_dqo = NULL;
 
 	gve_free_flow_rule_caches(priv);
+	gve_free_rss_config_cache(priv);
 	gve_free_counter_array(priv);
 	gve_free_notify_blocks(priv);
 	gve_free_stats_report(priv);
+	gve_teardown_clock(priv);
 	gve_clear_device_resources_ok(priv);
 }
 
@@ -738,30 +830,13 @@ static struct gve_queue_page_list *gve_rx_get_qpl(struct gve_priv *priv, int idx
 		return rx->dqo.qpl;
 }
 
-static int gve_register_xdp_qpls(struct gve_priv *priv)
-{
-	int start_id;
-	int err;
-	int i;
-
-	start_id = gve_xdp_tx_start_queue_id(priv);
-	for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) {
-		err = gve_register_qpl(priv, gve_tx_get_qpl(priv, i));
-		/* This failure will trigger a reset - no need to clean up */
-		if (err)
-			return err;
-	}
-	return 0;
-}
-
 static int gve_register_qpls(struct gve_priv *priv)
 {
 	int num_tx_qpls, num_rx_qpls;
 	int err;
 	int i;
 
-	num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_num_xdp_qpls(priv),
-				      gve_is_qpl(priv));
+	num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_is_qpl(priv));
 	num_rx_qpls = gve_num_rx_qpls(&priv->rx_cfg, gve_is_qpl(priv));
 
 	for (i = 0; i < num_tx_qpls; i++) {
@@ -779,30 +854,13 @@ static int gve_register_qpls(struct gve_priv *priv)
 	return 0;
 }
 
-static int gve_unregister_xdp_qpls(struct gve_priv *priv)
-{
-	int start_id;
-	int err;
-	int i;
-
-	start_id = gve_xdp_tx_start_queue_id(priv);
-	for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) {
-		err = gve_unregister_qpl(priv, gve_tx_get_qpl(priv, i));
-		/* This failure will trigger a reset - no need to clean */
-		if (err)
-			return err;
-	}
-	return 0;
-}
-
 static int gve_unregister_qpls(struct gve_priv *priv)
 {
 	int num_tx_qpls, num_rx_qpls;
 	int err;
 	int i;
 
-	num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_num_xdp_qpls(priv),
-				      gve_is_qpl(priv));
+	num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_is_qpl(priv));
 	num_rx_qpls = gve_num_rx_qpls(&priv->rx_cfg, gve_is_qpl(priv));
 
 	for (i = 0; i < num_tx_qpls; i++) {
@@ -821,27 +879,6 @@ static int gve_unregister_qpls(struct gve_priv *priv)
 	return 0;
 }
 
-static int gve_create_xdp_rings(struct gve_priv *priv)
-{
-	int err;
-
-	err = gve_adminq_create_tx_queues(priv,
-					  gve_xdp_tx_start_queue_id(priv),
-					  priv->num_xdp_queues);
-	if (err) {
-		netif_err(priv, drv, priv->dev, "failed to create %d XDP tx queues\n",
-			  priv->num_xdp_queues);
-		/* This failure will trigger a reset - no need to clean
-		 * up
-		 */
-		return err;
-	}
-	netif_dbg(priv, drv, priv->dev, "created %d XDP tx queues\n",
-		  priv->num_xdp_queues);
-
-	return 0;
-}
-
 static int gve_create_rings(struct gve_priv *priv)
 {
 	int num_tx_queues = gve_num_tx_queues(priv);
@@ -897,7 +934,7 @@ static void init_xdp_sync_stats(struct gve_priv *priv)
 	int i;
 
 	/* Init stats */
-	for (i = start_id; i < start_id + priv->num_xdp_queues; i++) {
+	for (i = start_id; i < start_id + priv->tx_cfg.num_xdp_queues; i++) {
 		int ntfy_idx = gve_tx_idx_to_ntfy(priv, i);
 
 		u64_stats_init(&priv->tx[i].statss);
@@ -925,19 +962,18 @@ static void gve_tx_get_curr_alloc_cfg(struct gve_priv *priv,
 	cfg->qcfg = &priv->tx_cfg;
 	cfg->raw_addressing = !gve_is_qpl(priv);
 	cfg->ring_size = priv->tx_desc_cnt;
-	cfg->start_idx = 0;
-	cfg->num_rings = gve_num_tx_queues(priv);
+	cfg->num_xdp_rings = cfg->qcfg->num_xdp_queues;
 	cfg->tx = priv->tx;
 }
 
-static void gve_tx_stop_rings(struct gve_priv *priv, int start_id, int num_rings)
+static void gve_tx_stop_rings(struct gve_priv *priv, int num_rings)
 {
 	int i;
 
 	if (!priv->tx)
 		return;
 
-	for (i = start_id; i < start_id + num_rings; i++) {
+	for (i = 0; i < num_rings; i++) {
 		if (gve_is_gqi(priv))
 			gve_tx_stop_ring_gqi(priv, i);
 		else
@@ -945,12 +981,11 @@ static void gve_tx_stop_rings(struct gve_priv *priv, int start_id, int num_rings
 	}
 }
 
-static void gve_tx_start_rings(struct gve_priv *priv, int start_id,
-			       int num_rings)
+static void gve_tx_start_rings(struct gve_priv *priv, int num_rings)
 {
 	int i;
 
-	for (i = start_id; i < start_id + num_rings; i++) {
+	for (i = 0; i < num_rings; i++) {
 		if (gve_is_gqi(priv))
 			gve_tx_start_ring_gqi(priv, i);
 		else
@@ -958,28 +993,6 @@ static void gve_tx_start_rings(struct gve_priv *priv, int start_id,
 	}
 }
 
-static int gve_alloc_xdp_rings(struct gve_priv *priv)
-{
-	struct gve_tx_alloc_rings_cfg cfg = {0};
-	int err = 0;
-
-	if (!priv->num_xdp_queues)
-		return 0;
-
-	gve_tx_get_curr_alloc_cfg(priv, &cfg);
-	cfg.start_idx = gve_xdp_tx_start_queue_id(priv);
-	cfg.num_rings = priv->num_xdp_queues;
-
-	err = gve_tx_alloc_rings_gqi(priv, &cfg);
-	if (err)
-		return err;
-
-	gve_tx_start_rings(priv, cfg.start_idx, cfg.num_rings);
-	init_xdp_sync_stats(priv);
-
-	return 0;
-}
-
 static int gve_queues_mem_alloc(struct gve_priv *priv,
 				struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
 				struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
@@ -1010,26 +1023,6 @@ free_tx:
 	return err;
 }
 
-static int gve_destroy_xdp_rings(struct gve_priv *priv)
-{
-	int start_id;
-	int err;
-
-	start_id = gve_xdp_tx_start_queue_id(priv);
-	err = gve_adminq_destroy_tx_queues(priv,
-					   start_id,
-					   priv->num_xdp_queues);
-	if (err) {
-		netif_err(priv, drv, priv->dev,
-			  "failed to destroy XDP queues\n");
-		/* This failure will trigger a reset - no need to clean up */
-		return err;
-	}
-	netif_dbg(priv, drv, priv->dev, "destroyed XDP queues\n");
-
-	return 0;
-}
-
 static int gve_destroy_rings(struct gve_priv *priv)
 {
 	int num_tx_queues = gve_num_tx_queues(priv);
@@ -1054,20 +1047,6 @@ static int gve_destroy_rings(struct gve_priv *priv)
 	return 0;
 }
 
-static void gve_free_xdp_rings(struct gve_priv *priv)
-{
-	struct gve_tx_alloc_rings_cfg cfg = {0};
-
-	gve_tx_get_curr_alloc_cfg(priv, &cfg);
-	cfg.start_idx = gve_xdp_tx_start_queue_id(priv);
-	cfg.num_rings = priv->num_xdp_queues;
-
-	if (priv->tx) {
-		gve_tx_stop_rings(priv, cfg.start_idx, cfg.num_rings);
-		gve_tx_free_rings_gqi(priv, &cfg);
-	}
-}
-
 static void gve_queues_mem_free(struct gve_priv *priv,
 				struct gve_tx_alloc_rings_cfg *tx_cfg,
 				struct gve_rx_alloc_rings_cfg *rx_cfg)
@@ -1085,7 +1064,7 @@ int gve_alloc_page(struct gve_priv *priv, struct device *dev,
 		   struct page **page, dma_addr_t *dma,
 		   enum dma_data_direction dir, gfp_t gfp_flags)
 {
-	*page = alloc_page(gfp_flags);
+	*page = alloc_pages_node(priv->numa_node, gfp_flags, 0);
 	if (!*page) {
 		priv->page_alloc_fail++;
 		return -ENOMEM;
@@ -1186,18 +1165,84 @@ static int gve_reset_recovery(struct gve_priv *priv, bool was_up);
 static void gve_turndown(struct gve_priv *priv);
 static void gve_turnup(struct gve_priv *priv);
 
+static void gve_unreg_xsk_pool(struct gve_priv *priv, u16 qid)
+{
+	struct gve_rx_ring *rx;
+
+	if (!priv->rx)
+		return;
+
+	rx = &priv->rx[qid];
+	rx->xsk_pool = NULL;
+	if (xdp_rxq_info_is_reg(&rx->xdp_rxq))
+		xdp_rxq_info_unreg_mem_model(&rx->xdp_rxq);
+
+	if (!priv->tx)
+		return;
+	priv->tx[gve_xdp_tx_queue_id(priv, qid)].xsk_pool = NULL;
+}
+
+static int gve_reg_xsk_pool(struct gve_priv *priv, struct net_device *dev,
+			    struct xsk_buff_pool *pool, u16 qid)
+{
+	struct gve_rx_ring *rx;
+	u16 tx_qid;
+	int err;
+
+	rx = &priv->rx[qid];
+	err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq,
+					 MEM_TYPE_XSK_BUFF_POOL, pool);
+	if (err) {
+		gve_unreg_xsk_pool(priv, qid);
+		return err;
+	}
+
+	rx->xsk_pool = pool;
+
+	tx_qid = gve_xdp_tx_queue_id(priv, qid);
+	priv->tx[tx_qid].xsk_pool = pool;
+
+	return 0;
+}
+
+static void gve_unreg_xdp_info(struct gve_priv *priv)
+{
+	int i;
+
+	if (!priv->tx_cfg.num_xdp_queues || !priv->rx)
+		return;
+
+	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
+		struct gve_rx_ring *rx = &priv->rx[i];
+
+		if (xdp_rxq_info_is_reg(&rx->xdp_rxq))
+			xdp_rxq_info_unreg(&rx->xdp_rxq);
+
+		gve_unreg_xsk_pool(priv, i);
+	}
+}
+
+static struct xsk_buff_pool *gve_get_xsk_pool(struct gve_priv *priv, int qid)
+{
+	if (!test_bit(qid, priv->xsk_pools))
+		return NULL;
+
+	return xsk_get_pool_from_qid(priv->dev, qid);
+}
+
 static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev)
 {
 	struct napi_struct *napi;
 	struct gve_rx_ring *rx;
 	int err = 0;
-	int i, j;
-	u32 tx_qid;
+	int i;
 
-	if (!priv->num_xdp_queues)
+	if (!priv->tx_cfg.num_xdp_queues)
 		return 0;
 
 	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
+		struct xsk_buff_pool *xsk_pool;
+
 		rx = &priv->rx[i];
 		napi = &priv->ntfy_blocks[rx->ntfy_id].napi;
 
@@ -1205,64 +1250,28 @@ static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev)
 				       napi->napi_id);
 		if (err)
 			goto err;
-		err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq,
-						 MEM_TYPE_PAGE_SHARED, NULL);
+
+		xsk_pool = gve_get_xsk_pool(priv, i);
+		if (xsk_pool)
+			err = gve_reg_xsk_pool(priv, dev, xsk_pool, i);
+		else if (gve_is_qpl(priv))
+			err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq,
+							 MEM_TYPE_PAGE_SHARED,
+							 NULL);
+		else
+			err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq,
+							 MEM_TYPE_PAGE_POOL,
+							 rx->dqo.page_pool);
 		if (err)
 			goto err;
-		rx->xsk_pool = xsk_get_pool_from_qid(dev, i);
-		if (rx->xsk_pool) {
-			err = xdp_rxq_info_reg(&rx->xsk_rxq, dev, i,
-					       napi->napi_id);
-			if (err)
-				goto err;
-			err = xdp_rxq_info_reg_mem_model(&rx->xsk_rxq,
-							 MEM_TYPE_XSK_BUFF_POOL, NULL);
-			if (err)
-				goto err;
-			xsk_pool_set_rxq_info(rx->xsk_pool,
-					      &rx->xsk_rxq);
-		}
-	}
-
-	for (i = 0; i < priv->num_xdp_queues; i++) {
-		tx_qid = gve_xdp_tx_queue_id(priv, i);
-		priv->tx[tx_qid].xsk_pool = xsk_get_pool_from_qid(dev, i);
 	}
 	return 0;
 
 err:
-	for (j = i; j >= 0; j--) {
-		rx = &priv->rx[j];
-		if (xdp_rxq_info_is_reg(&rx->xdp_rxq))
-			xdp_rxq_info_unreg(&rx->xdp_rxq);
-		if (xdp_rxq_info_is_reg(&rx->xsk_rxq))
-			xdp_rxq_info_unreg(&rx->xsk_rxq);
-	}
+	gve_unreg_xdp_info(priv);
 	return err;
 }
 
-static void gve_unreg_xdp_info(struct gve_priv *priv)
-{
-	int i, tx_qid;
-
-	if (!priv->num_xdp_queues)
-		return;
-
-	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
-		struct gve_rx_ring *rx = &priv->rx[i];
-
-		xdp_rxq_info_unreg(&rx->xdp_rxq);
-		if (rx->xsk_pool) {
-			xdp_rxq_info_unreg(&rx->xsk_rxq);
-			rx->xsk_pool = NULL;
-		}
-	}
-
-	for (i = 0; i < priv->num_xdp_queues; i++) {
-		tx_qid = gve_xdp_tx_queue_id(priv, i);
-		priv->tx[tx_qid].xsk_pool = NULL;
-	}
-}
 
 static void gve_drain_page_cache(struct gve_priv *priv)
 {
@@ -1275,15 +1284,14 @@ static void gve_drain_page_cache(struct gve_priv *priv)
 static void gve_rx_get_curr_alloc_cfg(struct gve_priv *priv,
 				      struct gve_rx_alloc_rings_cfg *cfg)
 {
-	cfg->qcfg = &priv->rx_cfg;
+	cfg->qcfg_rx = &priv->rx_cfg;
 	cfg->qcfg_tx = &priv->tx_cfg;
 	cfg->raw_addressing = !gve_is_qpl(priv);
 	cfg->enable_header_split = priv->header_split_enabled;
 	cfg->ring_size = priv->rx_desc_cnt;
-	cfg->packet_buffer_size = gve_is_gqi(priv) ?
-				  GVE_DEFAULT_RX_BUFFER_SIZE :
-				  priv->data_buffer_size_dqo;
+	cfg->packet_buffer_size = priv->rx_cfg.packet_buffer_size;
 	cfg->rx = priv->rx;
+	cfg->xdp = !!cfg->qcfg_tx->num_xdp_queues;
 }
 
 void gve_get_curr_alloc_cfgs(struct gve_priv *priv,
@@ -1356,17 +1364,13 @@ static int gve_queues_start(struct gve_priv *priv,
 
 	/* Record new configs into priv */
 	priv->tx_cfg = *tx_alloc_cfg->qcfg;
-	priv->rx_cfg = *rx_alloc_cfg->qcfg;
+	priv->tx_cfg.num_xdp_queues = tx_alloc_cfg->num_xdp_rings;
+	priv->rx_cfg = *rx_alloc_cfg->qcfg_rx;
 	priv->tx_desc_cnt = tx_alloc_cfg->ring_size;
 	priv->rx_desc_cnt = rx_alloc_cfg->ring_size;
 
-	if (priv->xdp_prog)
-		priv->num_xdp_queues = priv->rx_cfg.num_queues;
-	else
-		priv->num_xdp_queues = 0;
-
-	gve_tx_start_rings(priv, 0, tx_alloc_cfg->num_rings);
-	gve_rx_start_rings(priv, rx_alloc_cfg->qcfg->num_queues);
+	gve_tx_start_rings(priv, gve_num_tx_queues(priv));
+	gve_rx_start_rings(priv, rx_alloc_cfg->qcfg_rx->num_queues);
 	gve_init_sync_stats(priv);
 
 	err = netif_set_real_num_tx_queues(dev, priv->tx_cfg.num_queues);
@@ -1380,12 +1384,18 @@ static int gve_queues_start(struct gve_priv *priv,
 	if (err)
 		goto stop_and_free_rings;
 
+	if (rx_alloc_cfg->reset_rss) {
+		err = gve_init_rss_config(priv, priv->rx_cfg.num_queues);
+		if (err)
+			goto reset;
+	}
+
 	err = gve_register_qpls(priv);
 	if (err)
 		goto reset;
 
 	priv->header_split_enabled = rx_alloc_cfg->enable_header_split;
-	priv->data_buffer_size_dqo = rx_alloc_cfg->packet_buffer_size;
+	priv->rx_cfg.packet_buffer_size = rx_alloc_cfg->packet_buffer_size;
 
 	err = gve_create_rings(priv);
 	if (err)
@@ -1412,7 +1422,7 @@ reset:
 	/* return the original error */
 	return err;
 stop_and_free_rings:
-	gve_tx_stop_rings(priv, 0, gve_num_tx_queues(priv));
+	gve_tx_stop_rings(priv, gve_num_tx_queues(priv));
 	gve_rx_stop_rings(priv, priv->rx_cfg.num_queues);
 	gve_queues_mem_remove(priv);
 	return err;
@@ -1457,11 +1467,11 @@ static int gve_queues_stop(struct gve_priv *priv)
 			goto err;
 		gve_clear_device_rings_ok(priv);
 	}
-	del_timer_sync(&priv->stats_report_timer);
+	timer_delete_sync(&priv->stats_report_timer);
 
 	gve_unreg_xdp_info(priv);
 
-	gve_tx_stop_rings(priv, 0, gve_num_tx_queues(priv));
+	gve_tx_stop_rings(priv, gve_num_tx_queues(priv));
 	gve_rx_stop_rings(priv, priv->rx_cfg.num_queues);
 
 	priv->interface_down_cnt++;
@@ -1491,56 +1501,6 @@ static int gve_close(struct net_device *dev)
 	return 0;
 }
 
-static int gve_remove_xdp_queues(struct gve_priv *priv)
-{
-	int err;
-
-	err = gve_destroy_xdp_rings(priv);
-	if (err)
-		return err;
-
-	err = gve_unregister_xdp_qpls(priv);
-	if (err)
-		return err;
-
-	gve_unreg_xdp_info(priv);
-	gve_free_xdp_rings(priv);
-
-	priv->num_xdp_queues = 0;
-	return 0;
-}
-
-static int gve_add_xdp_queues(struct gve_priv *priv)
-{
-	int err;
-
-	priv->num_xdp_queues = priv->rx_cfg.num_queues;
-
-	err = gve_alloc_xdp_rings(priv);
-	if (err)
-		goto err;
-
-	err = gve_reg_xdp_info(priv, priv->dev);
-	if (err)
-		goto free_xdp_rings;
-
-	err = gve_register_xdp_qpls(priv);
-	if (err)
-		goto free_xdp_rings;
-
-	err = gve_create_xdp_rings(priv);
-	if (err)
-		goto free_xdp_rings;
-
-	return 0;
-
-free_xdp_rings:
-	gve_free_xdp_rings(priv);
-err:
-	priv->num_xdp_queues = 0;
-	return err;
-}
-
 static void gve_handle_link_status(struct gve_priv *priv, bool link_status)
 {
 	if (!gve_get_napi_enabled(priv))
@@ -1558,6 +1518,19 @@ static void gve_handle_link_status(struct gve_priv *priv, bool link_status)
 	}
 }
 
+static int gve_configure_rings_xdp(struct gve_priv *priv,
+				   u16 num_xdp_rings)
+{
+	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
+	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
+
+	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
+	tx_alloc_cfg.num_xdp_rings = num_xdp_rings;
+
+	rx_alloc_cfg.xdp = !!num_xdp_rings;
+	return gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
+}
+
 static int gve_set_xdp(struct gve_priv *priv, struct bpf_prog *prog,
 		       struct netlink_ext_ack *extack)
 {
@@ -1570,42 +1543,49 @@ static int gve_set_xdp(struct gve_priv *priv, struct bpf_prog *prog,
 		WRITE_ONCE(priv->xdp_prog, prog);
 		if (old_prog)
 			bpf_prog_put(old_prog);
+
+		/* Update priv XDP queue configuration */
+		priv->tx_cfg.num_xdp_queues = priv->xdp_prog ?
+			priv->rx_cfg.num_queues : 0;
 		return 0;
 	}
 
-	gve_turndown(priv);
-	if (!old_prog && prog) {
-		// Allocate XDP TX queues if an XDP program is
-		// being installed
-		err = gve_add_xdp_queues(priv);
-		if (err)
-			goto out;
-	} else if (old_prog && !prog) {
-		// Remove XDP TX queues if an XDP program is
-		// being uninstalled
-		err = gve_remove_xdp_queues(priv);
-		if (err)
-			goto out;
-	}
+	if (!old_prog && prog)
+		err = gve_configure_rings_xdp(priv, priv->rx_cfg.num_queues);
+	else if (old_prog && !prog)
+		err = gve_configure_rings_xdp(priv, 0);
+
+	if (err)
+		goto out;
+
 	WRITE_ONCE(priv->xdp_prog, prog);
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
 out:
-	gve_turnup(priv);
 	status = ioread32be(&priv->reg_bar0->device_status);
 	gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status);
 	return err;
 }
 
+static int gve_xdp_xmit(struct net_device *dev, int n,
+			struct xdp_frame **frames, u32 flags)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+
+	if (priv->queue_format == GVE_GQI_QPL_FORMAT)
+		return gve_xdp_xmit_gqi(dev, n, frames, flags);
+	else if (priv->queue_format == GVE_DQO_RDA_FORMAT)
+		return gve_xdp_xmit_dqo(dev, n, frames, flags);
+
+	return -EOPNOTSUPP;
+}
+
 static int gve_xsk_pool_enable(struct net_device *dev,
 			       struct xsk_buff_pool *pool,
 			       u16 qid)
 {
 	struct gve_priv *priv = netdev_priv(dev);
-	struct napi_struct *napi;
-	struct gve_rx_ring *rx;
-	int tx_qid;
 	int err;
 
 	if (qid >= priv->rx_cfg.num_queues) {
@@ -1623,34 +1603,31 @@ static int gve_xsk_pool_enable(struct net_device *dev,
 	if (err)
 		return err;
 
-	/* If XDP prog is not installed, return */
-	if (!priv->xdp_prog)
-		return 0;
+	set_bit(qid, priv->xsk_pools);
 
-	rx = &priv->rx[qid];
-	napi = &priv->ntfy_blocks[rx->ntfy_id].napi;
-	err = xdp_rxq_info_reg(&rx->xsk_rxq, dev, qid, napi->napi_id);
-	if (err)
-		goto err;
+	/* If XDP prog is not installed or interface is down, return. */
+	if (!priv->xdp_prog || !netif_running(dev))
+		return 0;
 
-	err = xdp_rxq_info_reg_mem_model(&rx->xsk_rxq,
-					 MEM_TYPE_XSK_BUFF_POOL, NULL);
+	err = gve_reg_xsk_pool(priv, dev, pool, qid);
 	if (err)
-		goto err;
-
-	xsk_pool_set_rxq_info(pool, &rx->xsk_rxq);
-	rx->xsk_pool = pool;
-
-	tx_qid = gve_xdp_tx_queue_id(priv, qid);
-	priv->tx[tx_qid].xsk_pool = pool;
+		goto err_xsk_pool_dma_mapped;
 
+	/* Stop and start RDA queues to repost buffers. */
+	if (!gve_is_qpl(priv)) {
+		err = gve_configure_rings_xdp(priv, priv->rx_cfg.num_queues);
+		if (err)
+			goto err_xsk_pool_registered;
+	}
 	return 0;
-err:
-	if (xdp_rxq_info_is_reg(&rx->xsk_rxq))
-		xdp_rxq_info_unreg(&rx->xsk_rxq);
 
+err_xsk_pool_registered:
+	gve_unreg_xsk_pool(priv, qid);
+err_xsk_pool_dma_mapped:
+	clear_bit(qid, priv->xsk_pools);
 	xsk_pool_dma_unmap(pool,
-			   DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
+			   DMA_ATTR_SKIP_CPU_SYNC |
+			   DMA_ATTR_WEAK_ORDERING);
 	return err;
 }
 
@@ -1662,103 +1639,118 @@ static int gve_xsk_pool_disable(struct net_device *dev,
 	struct napi_struct *napi_tx;
 	struct xsk_buff_pool *pool;
 	int tx_qid;
+	int err;
 
-	pool = xsk_get_pool_from_qid(dev, qid);
-	if (!pool)
-		return -EINVAL;
 	if (qid >= priv->rx_cfg.num_queues)
 		return -EINVAL;
 
-	/* If XDP prog is not installed, unmap DMA and return */
-	if (!priv->xdp_prog)
-		goto done;
+	clear_bit(qid, priv->xsk_pools);
 
-	tx_qid = gve_xdp_tx_queue_id(priv, qid);
-	if (!netif_running(dev)) {
-		priv->rx[qid].xsk_pool = NULL;
-		xdp_rxq_info_unreg(&priv->rx[qid].xsk_rxq);
-		priv->tx[tx_qid].xsk_pool = NULL;
-		goto done;
+	pool = xsk_get_pool_from_qid(dev, qid);
+	if (pool)
+		xsk_pool_dma_unmap(pool,
+				   DMA_ATTR_SKIP_CPU_SYNC |
+				   DMA_ATTR_WEAK_ORDERING);
+
+	if (!netif_running(dev) || !priv->tx_cfg.num_xdp_queues)
+		return 0;
+
+	/* Stop and start RDA queues to repost buffers. */
+	if (!gve_is_qpl(priv) && priv->xdp_prog) {
+		err = gve_configure_rings_xdp(priv, priv->rx_cfg.num_queues);
+		if (err)
+			return err;
 	}
 
 	napi_rx = &priv->ntfy_blocks[priv->rx[qid].ntfy_id].napi;
 	napi_disable(napi_rx); /* make sure current rx poll is done */
 
+	tx_qid = gve_xdp_tx_queue_id(priv, qid);
 	napi_tx = &priv->ntfy_blocks[priv->tx[tx_qid].ntfy_id].napi;
 	napi_disable(napi_tx); /* make sure current tx poll is done */
 
-	priv->rx[qid].xsk_pool = NULL;
-	xdp_rxq_info_unreg(&priv->rx[qid].xsk_rxq);
-	priv->tx[tx_qid].xsk_pool = NULL;
+	gve_unreg_xsk_pool(priv, qid);
 	smp_mb(); /* Make sure it is visible to the workers on datapath */
 
 	napi_enable(napi_rx);
-	if (gve_rx_work_pending(&priv->rx[qid]))
-		napi_schedule(napi_rx);
-
 	napi_enable(napi_tx);
-	if (gve_tx_clean_pending(priv, &priv->tx[tx_qid]))
-		napi_schedule(napi_tx);
+	if (gve_is_gqi(priv)) {
+		if (gve_rx_work_pending(&priv->rx[qid]))
+			napi_schedule(napi_rx);
+
+		if (gve_tx_clean_pending(priv, &priv->tx[tx_qid]))
+			napi_schedule(napi_tx);
+	}
 
-done:
-	xsk_pool_dma_unmap(pool,
-			   DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
 	return 0;
 }
 
 static int gve_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 {
 	struct gve_priv *priv = netdev_priv(dev);
-	int tx_queue_id = gve_xdp_tx_queue_id(priv, queue_id);
+	struct napi_struct *napi;
+
+	if (!gve_get_napi_enabled(priv))
+		return -ENETDOWN;
 
 	if (queue_id >= priv->rx_cfg.num_queues || !priv->xdp_prog)
 		return -EINVAL;
 
-	if (flags & XDP_WAKEUP_TX) {
-		struct gve_tx_ring *tx = &priv->tx[tx_queue_id];
-		struct napi_struct *napi =
-			&priv->ntfy_blocks[tx->ntfy_id].napi;
-
-		if (!napi_if_scheduled_mark_missed(napi)) {
-			/* Call local_bh_enable to trigger SoftIRQ processing */
-			local_bh_disable();
-			napi_schedule(napi);
-			local_bh_enable();
-		}
-
-		tx->xdp_xsk_wakeup++;
+	napi = &priv->ntfy_blocks[gve_rx_idx_to_ntfy(priv, queue_id)].napi;
+	if (!napi_if_scheduled_mark_missed(napi)) {
+		/* Call local_bh_enable to trigger SoftIRQ processing */
+		local_bh_disable();
+		napi_schedule(napi);
+		local_bh_enable();
 	}
 
 	return 0;
 }
 
-static int verify_xdp_configuration(struct net_device *dev)
+static int gve_verify_xdp_configuration(struct net_device *dev,
+					struct netlink_ext_ack *extack)
 {
 	struct gve_priv *priv = netdev_priv(dev);
+	u16 max_xdp_mtu;
 
 	if (dev->features & NETIF_F_LRO) {
-		netdev_warn(dev, "XDP is not supported when LRO is on.\n");
+		NL_SET_ERR_MSG_MOD(extack,
+				   "XDP is not supported when LRO is on.");
 		return -EOPNOTSUPP;
 	}
 
-	if (priv->queue_format != GVE_GQI_QPL_FORMAT) {
-		netdev_warn(dev, "XDP is not supported in mode %d.\n",
-			    priv->queue_format);
+	if (priv->header_split_enabled) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "XDP is not supported when header-data split is enabled.");
 		return -EOPNOTSUPP;
 	}
 
-	if (dev->mtu > GVE_DEFAULT_RX_BUFFER_SIZE - sizeof(struct ethhdr) - GVE_RX_PAD) {
-		netdev_warn(dev, "XDP is not supported for mtu %d.\n",
-			    dev->mtu);
+	if (priv->rx_cfg.packet_buffer_size != SZ_2K) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "XDP is not supported for Rx buf len %d, only %d supported.",
+				       priv->rx_cfg.packet_buffer_size, SZ_2K);
+		return -EOPNOTSUPP;
+	}
+
+	max_xdp_mtu = priv->rx_cfg.packet_buffer_size - sizeof(struct ethhdr);
+	if (priv->queue_format == GVE_GQI_QPL_FORMAT)
+		max_xdp_mtu -= GVE_RX_PAD;
+
+	if (dev->mtu > max_xdp_mtu) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "XDP is not supported for mtu %d.",
+				       dev->mtu);
 		return -EOPNOTSUPP;
 	}
 
 	if (priv->rx_cfg.num_queues != priv->tx_cfg.num_queues ||
 	    (2 * priv->tx_cfg.num_queues > priv->tx_cfg.max_queues)) {
-		netdev_warn(dev, "XDP load failed: The number of configured RX queues %d should be equal to the number of configured TX queues %d and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues %d",
-			    priv->rx_cfg.num_queues,
-			    priv->tx_cfg.num_queues,
+		netdev_warn(dev,
+			    "XDP load failed: The number of configured RX queues %d should be equal to the number of configured TX queues %d and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues %d.",
+			    priv->rx_cfg.num_queues, priv->tx_cfg.num_queues,
 			    priv->tx_cfg.max_queues);
+		NL_SET_ERR_MSG_MOD(extack,
+				   "XDP load failed: The number of configured RX queues should be equal to the number of configured TX queues and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues");
 		return -EINVAL;
 	}
 	return 0;
@@ -1769,7 +1761,7 @@ static int gve_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	struct gve_priv *priv = netdev_priv(dev);
 	int err;
 
-	err = verify_xdp_configuration(dev);
+	err = gve_verify_xdp_configuration(dev, xdp->extack);
 	if (err)
 		return err;
 	switch (xdp->command) {
@@ -1785,6 +1777,26 @@ static int gve_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
+int gve_init_rss_config(struct gve_priv *priv, u16 num_queues)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+	struct ethtool_rxfh_param rxfh = {0};
+	u16 i;
+
+	if (!priv->cache_rss_config)
+		return 0;
+
+	for (i = 0; i < priv->rss_lut_size; i++)
+		rss_config->hash_lut[i] =
+			ethtool_rxfh_indir_default(i, num_queues);
+
+	netdev_rss_key_fill(rss_config->hash_key, priv->rss_key_size);
+
+	rxfh.hfunc = ETH_RSS_HASH_TOP;
+
+	return gve_adminq_configure_rss(priv, &rxfh);
+}
+
 int gve_flow_rules_reset(struct gve_priv *priv)
 {
 	if (!priv->max_flow_rules)
@@ -1799,7 +1811,7 @@ int gve_adjust_config(struct gve_priv *priv,
 {
 	int err;
 
-	/* Allocate resources for the new confiugration */
+	/* Allocate resources for the new configuration */
 	err = gve_queues_mem_alloc(priv, tx_alloc_cfg, rx_alloc_cfg);
 	if (err) {
 		netif_err(priv, drv, priv->dev,
@@ -1832,8 +1844,9 @@ int gve_adjust_config(struct gve_priv *priv,
 }
 
 int gve_adjust_queues(struct gve_priv *priv,
-		      struct gve_queue_config new_rx_config,
-		      struct gve_queue_config new_tx_config)
+		      struct gve_rx_queue_config new_rx_config,
+		      struct gve_tx_queue_config new_tx_config,
+		      bool reset_rss)
 {
 	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
 	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
@@ -1844,14 +1857,19 @@ int gve_adjust_queues(struct gve_priv *priv,
 	/* Relay the new config from ethtool */
 	tx_alloc_cfg.qcfg = &new_tx_config;
 	rx_alloc_cfg.qcfg_tx = &new_tx_config;
-	rx_alloc_cfg.qcfg = &new_rx_config;
-	tx_alloc_cfg.num_rings = new_tx_config.num_queues;
+	rx_alloc_cfg.qcfg_rx = &new_rx_config;
+	rx_alloc_cfg.reset_rss = reset_rss;
 
 	if (netif_running(priv->dev)) {
 		err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 		return err;
 	}
 	/* Set the config for the next up. */
+	if (reset_rss) {
+		err = gve_init_rss_config(priv, new_rx_config.num_queues);
+		if (err)
+			return err;
+	}
 	priv->tx_cfg = new_tx_config;
 	priv->rx_cfg = new_rx_config;
 
@@ -1880,7 +1898,7 @@ static void gve_turndown(struct gve_priv *priv)
 			netif_queue_set_napi(priv->dev, idx,
 					     NETDEV_QUEUE_TYPE_TX, NULL);
 
-		napi_disable(&block->napi);
+		napi_disable_locked(&block->napi);
 	}
 	for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) {
 		int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
@@ -1891,14 +1909,19 @@ static void gve_turndown(struct gve_priv *priv)
 
 		netif_queue_set_napi(priv->dev, idx, NETDEV_QUEUE_TYPE_RX,
 				     NULL);
-		napi_disable(&block->napi);
+		napi_disable_locked(&block->napi);
 	}
 
 	/* Stop tx queues */
 	netif_tx_disable(priv->dev);
 
+	xdp_features_clear_redirect_target_locked(priv->dev);
+
 	gve_clear_napi_enabled(priv);
 	gve_clear_report_stats(priv);
+
+	/* Make sure that all traffic is finished processing. */
+	synchronize_net();
 }
 
 static void gve_turnup(struct gve_priv *priv)
@@ -1916,7 +1939,7 @@ static void gve_turnup(struct gve_priv *priv)
 		if (!gve_tx_was_added_to_block(priv, idx))
 			continue;
 
-		napi_enable(&block->napi);
+		napi_enable_locked(&block->napi);
 
 		if (idx < priv->tx_cfg.num_queues)
 			netif_queue_set_napi(priv->dev, idx,
@@ -1944,7 +1967,7 @@ static void gve_turnup(struct gve_priv *priv)
 		if (!gve_rx_was_added_to_block(priv, idx))
 			continue;
 
-		napi_enable(&block->napi);
+		napi_enable_locked(&block->napi);
 		netif_queue_set_napi(priv->dev, idx, NETDEV_QUEUE_TYPE_RX,
 				     &block->napi);
 
@@ -1963,6 +1986,9 @@ static void gve_turnup(struct gve_priv *priv)
 		napi_schedule(&block->napi);
 	}
 
+	if (priv->tx_cfg.num_xdp_queues && gve_supports_xdp_xmit(priv))
+		xdp_features_set_redirect_target_locked(priv->dev, false);
+
 	gve_set_napi_enabled(priv);
 }
 
@@ -1975,72 +2001,104 @@ static void gve_turnup_and_check_status(struct gve_priv *priv)
 	gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status);
 }
 
-static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue)
+static struct gve_notify_block *gve_get_tx_notify_block(struct gve_priv *priv,
+							unsigned int txqueue)
 {
-	struct gve_notify_block *block;
-	struct gve_tx_ring *tx = NULL;
-	struct gve_priv *priv;
-	u32 last_nic_done;
-	u32 current_time;
 	u32 ntfy_idx;
 
-	netdev_info(dev, "Timeout on tx queue, %d", txqueue);
-	priv = netdev_priv(dev);
 	if (txqueue > priv->tx_cfg.num_queues)
-		goto reset;
+		return NULL;
 
 	ntfy_idx = gve_tx_idx_to_ntfy(priv, txqueue);
 	if (ntfy_idx >= priv->num_ntfy_blks)
-		goto reset;
+		return NULL;
+
+	return &priv->ntfy_blocks[ntfy_idx];
+}
+
+static bool gve_tx_timeout_try_q_kick(struct gve_priv *priv,
+				      unsigned int txqueue)
+{
+	struct gve_notify_block *block;
+	u32 current_time;
 
-	block = &priv->ntfy_blocks[ntfy_idx];
-	tx = block->tx;
+	block = gve_get_tx_notify_block(priv, txqueue);
+
+	if (!block)
+		return false;
 
 	current_time = jiffies_to_msecs(jiffies);
-	if (tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time)
-		goto reset;
+	if (block->tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time)
+		return false;
 
-	/* Check to see if there are missed completions, which will allow us to
-	 * kick the queue.
-	 */
-	last_nic_done = gve_tx_load_event_counter(priv, tx);
-	if (last_nic_done - tx->done) {
-		netdev_info(dev, "Kicking queue %d", txqueue);
-		iowrite32be(GVE_IRQ_MASK, gve_irq_doorbell(priv, block));
-		napi_schedule(&block->napi);
-		tx->last_kick_msec = current_time;
-		goto out;
-	} // Else reset.
+	netdev_info(priv->dev, "Kicking queue %d", txqueue);
+	napi_schedule(&block->napi);
+	block->tx->last_kick_msec = current_time;
+	return true;
+}
 
-reset:
-	gve_schedule_reset(priv);
+static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue)
+{
+	struct gve_notify_block *block;
+	struct gve_priv *priv;
 
-out:
-	if (tx)
-		tx->queue_timeout++;
+	netdev_info(dev, "Timeout on tx queue, %d", txqueue);
+	priv = netdev_priv(dev);
+
+	if (!gve_tx_timeout_try_q_kick(priv, txqueue))
+		gve_schedule_reset(priv);
+
+	block = gve_get_tx_notify_block(priv, txqueue);
+	if (block)
+		block->tx->queue_timeout++;
 	priv->tx_timeo_cnt++;
 }
 
-u16 gve_get_pkt_buf_size(const struct gve_priv *priv, bool enable_hsplit)
+/* Header split is only supported on DQ RDA queue format. If XDP is enabled,
+ * header split is not allowed.
+ */
+bool gve_header_split_supported(const struct gve_priv *priv)
 {
-	if (enable_hsplit && priv->max_rx_buffer_size >= GVE_MAX_RX_BUFFER_SIZE)
-		return GVE_MAX_RX_BUFFER_SIZE;
-	else
-		return GVE_DEFAULT_RX_BUFFER_SIZE;
+	return priv->header_buf_size &&
+		priv->queue_format == GVE_DQO_RDA_FORMAT && !priv->xdp_prog;
 }
 
-/* header-split is not supported on non-DQO_RDA yet even if device advertises it */
-bool gve_header_split_supported(const struct gve_priv *priv)
+int gve_set_rx_buf_len_config(struct gve_priv *priv, u32 rx_buf_len,
+			      struct netlink_ext_ack *extack,
+			      struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
 {
-	return priv->header_buf_size && priv->queue_format == GVE_DQO_RDA_FORMAT;
+	u32 old_rx_buf_len = rx_alloc_cfg->packet_buffer_size;
+
+	if (rx_buf_len == old_rx_buf_len)
+		return 0;
+
+	/* device options may not always contain support for 4K buffers */
+	if (!gve_is_dqo(priv) || priv->max_rx_buffer_size < SZ_4K) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Modifying Rx buf len is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (priv->xdp_prog && rx_buf_len != SZ_2K) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Rx buf len can only be 2048 when XDP is on");
+		return -EINVAL;
+	}
+
+	if (rx_buf_len != SZ_2K && rx_buf_len != SZ_4K) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Rx buf len can only be 2048 or 4096");
+		return -EINVAL;
+	}
+	rx_alloc_cfg->packet_buffer_size = rx_buf_len;
+
+	return 0;
 }
 
-int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split)
+int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split,
+			  struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
 {
-	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
-	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
 	bool enable_hdr_split;
-	int err = 0;
 
 	if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN)
 		return 0;
@@ -2058,14 +2116,9 @@ int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split)
 	if (enable_hdr_split == priv->header_split_enabled)
 		return 0;
 
-	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
-
-	rx_alloc_cfg.enable_header_split = enable_hdr_split;
-	rx_alloc_cfg.packet_buffer_size = gve_get_pkt_buf_size(priv, enable_hdr_split);
+	rx_alloc_cfg->enable_header_split = enable_hdr_split;
 
-	if (netif_running(priv->dev))
-		err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
-	return err;
+	return 0;
 }
 
 static int gve_set_features(struct net_device *netdev,
@@ -2081,6 +2134,12 @@ static int gve_set_features(struct net_device *netdev,
 
 	if ((netdev->features & NETIF_F_LRO) != (features & NETIF_F_LRO)) {
 		netdev->features ^= NETIF_F_LRO;
+		if (priv->xdp_prog && (netdev->features & NETIF_F_LRO)) {
+			netdev_warn(netdev,
+				    "XDP is not supported when LRO is on.\n");
+			err =  -EOPNOTSUPP;
+			goto revert_features;
+		}
 		if (netif_running(netdev)) {
 			err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 			if (err)
@@ -2100,6 +2159,42 @@ revert_features:
 	return err;
 }
 
+static int gve_get_ts_config(struct net_device *dev,
+			     struct kernel_hwtstamp_config *kernel_config)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+
+	*kernel_config = priv->ts_config;
+	return 0;
+}
+
+static int gve_set_ts_config(struct net_device *dev,
+			     struct kernel_hwtstamp_config *kernel_config,
+			     struct netlink_ext_ack *extack)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+
+	if (kernel_config->tx_type != HWTSTAMP_TX_OFF) {
+		NL_SET_ERR_MSG_MOD(extack, "TX timestamping is not supported");
+		return -ERANGE;
+	}
+
+	if (kernel_config->rx_filter != HWTSTAMP_FILTER_NONE) {
+		if (!priv->nic_ts_report) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "RX timestamping is not supported");
+			kernel_config->rx_filter = HWTSTAMP_FILTER_NONE;
+			return -EOPNOTSUPP;
+		}
+
+		kernel_config->rx_filter = HWTSTAMP_FILTER_ALL;
+	}
+
+	priv->ts_config.rx_filter = kernel_config->rx_filter;
+
+	return 0;
+}
+
 static const struct net_device_ops gve_netdev_ops = {
 	.ndo_start_xmit		=	gve_start_xmit,
 	.ndo_features_check	=	gve_features_check,
@@ -2111,6 +2206,8 @@ static const struct net_device_ops gve_netdev_ops = {
 	.ndo_bpf		=	gve_xdp,
 	.ndo_xdp_xmit		=	gve_xdp_xmit,
 	.ndo_xsk_wakeup		=	gve_xsk_wakeup,
+	.ndo_hwtstamp_get	=	gve_get_ts_config,
+	.ndo_hwtstamp_set	=	gve_set_ts_config,
 };
 
 static void gve_handle_status(struct gve_priv *priv, u32 status)
@@ -2136,7 +2233,9 @@ static void gve_handle_reset(struct gve_priv *priv)
 
 	if (gve_get_do_reset(priv)) {
 		rtnl_lock();
+		netdev_lock(priv->dev);
 		gve_reset(priv, false);
+		netdev_unlock(priv->dev);
 		rtnl_unlock();
 	}
 }
@@ -2210,7 +2309,7 @@ void gve_handle_report_stats(struct gve_priv *priv)
 			};
 			stats[stats_idx++] = (struct stats) {
 				.stat_name = cpu_to_be32(RX_BUFFERS_POSTED),
-				.value = cpu_to_be64(priv->rx[0].fill_cnt),
+				.value = cpu_to_be64(priv->rx[idx].fill_cnt),
 				.queue_id = cpu_to_be32(idx),
 			};
 		}
@@ -2232,16 +2331,27 @@ static void gve_service_task(struct work_struct *work)
 
 static void gve_set_netdev_xdp_features(struct gve_priv *priv)
 {
+	xdp_features_t xdp_features;
+
 	if (priv->queue_format == GVE_GQI_QPL_FORMAT) {
-		priv->dev->xdp_features = NETDEV_XDP_ACT_BASIC;
-		priv->dev->xdp_features |= NETDEV_XDP_ACT_REDIRECT;
-		priv->dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT;
-		priv->dev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
+		xdp_features = NETDEV_XDP_ACT_BASIC;
+		xdp_features |= NETDEV_XDP_ACT_REDIRECT;
+		xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
+	} else if (priv->queue_format == GVE_DQO_RDA_FORMAT) {
+		xdp_features = NETDEV_XDP_ACT_BASIC;
+		xdp_features |= NETDEV_XDP_ACT_REDIRECT;
+		xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
 	} else {
-		priv->dev->xdp_features = 0;
+		xdp_features = 0;
 	}
+
+	xdp_set_features_flag_locked(priv->dev, xdp_features);
 }
 
+static const struct xdp_metadata_ops gve_xdp_metadata_ops = {
+	.xmo_rx_timestamp	= gve_xdp_rx_timestamp,
+};
+
 static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device)
 {
 	int num_ntfy;
@@ -2289,7 +2399,7 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device)
 		goto err;
 	}
 
-	/* Big TCP is only supported on DQ*/
+	/* Big TCP is only supported on DQO */
 	if (!gve_is_gqi(priv))
 		netif_set_tso_max_size(priv->dev, GVE_DQO_TX_MAX);
 
@@ -2299,6 +2409,7 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device)
 	 */
 	priv->num_ntfy_blks = (num_ntfy - 1) & ~0x1;
 	priv->mgmt_msix_idx = priv->num_ntfy_blks;
+	priv->numa_node = dev_to_node(&priv->pdev->dev);
 
 	priv->tx_cfg.max_queues =
 		min_t(int, priv->tx_cfg.max_queues, priv->num_ntfy_blks / 2);
@@ -2313,6 +2424,7 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device)
 		priv->rx_cfg.num_queues = min_t(int, priv->default_num_queues,
 						priv->rx_cfg.num_queues);
 	}
+	priv->tx_cfg.num_xdp_queues = 0;
 
 	dev_info(&priv->pdev->dev, "TX queues %d, RX queues %d\n",
 		 priv->tx_cfg.num_queues, priv->rx_cfg.num_queues);
@@ -2324,11 +2436,29 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device)
 		priv->rx_coalesce_usecs = GVE_RX_IRQ_RATELIMIT_US_DQO;
 	}
 
+	priv->ts_config.tx_type = HWTSTAMP_TX_OFF;
+	priv->ts_config.rx_filter = HWTSTAMP_FILTER_NONE;
+
 setup_device:
+	priv->xsk_pools = bitmap_zalloc(priv->rx_cfg.max_queues, GFP_KERNEL);
+	if (!priv->xsk_pools) {
+		err = -ENOMEM;
+		goto err;
+	}
+
 	gve_set_netdev_xdp_features(priv);
+	if (!gve_is_gqi(priv))
+		priv->dev->xdp_metadata_ops = &gve_xdp_metadata_ops;
+
 	err = gve_setup_device_resources(priv);
-	if (!err)
-		return 0;
+	if (err)
+		goto err_free_xsk_bitmap;
+
+	return 0;
+
+err_free_xsk_bitmap:
+	bitmap_free(priv->xsk_pools);
+	priv->xsk_pools = NULL;
 err:
 	gve_adminq_free(&priv->pdev->dev, priv);
 	return err;
@@ -2338,6 +2468,8 @@ static void gve_teardown_priv_resources(struct gve_priv *priv)
 {
 	gve_teardown_device_resources(priv);
 	gve_adminq_free(&priv->pdev->dev, priv);
+	bitmap_free(priv->xsk_pools);
+	priv->xsk_pools = NULL;
 }
 
 static void gve_trigger_reset(struct gve_priv *priv)
@@ -2693,7 +2825,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	priv->service_task_flags = 0x0;
 	priv->state_flags = 0x0;
 	priv->ethtool_flags = 0x0;
-	priv->data_buffer_size_dqo = GVE_DEFAULT_RX_BUFFER_SIZE;
+	priv->rx_cfg.packet_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE;
 	priv->max_rx_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE;
 
 	gve_set_probe_in_progress(priv);
@@ -2712,6 +2844,9 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto abort_with_wq;
 
+	if (!gve_is_gqi(priv) && !gve_is_qpl(priv))
+		dev->netmem_tx = true;
+
 	err = register_netdev(dev);
 	if (err)
 		goto abort_with_gve_init;
@@ -2768,7 +2903,10 @@ static void gve_shutdown(struct pci_dev *pdev)
 	struct gve_priv *priv = netdev_priv(netdev);
 	bool was_up = netif_running(priv->dev);
 
+	netif_device_detach(netdev);
+
 	rtnl_lock();
+	netdev_lock(netdev);
 	if (was_up && gve_close(priv->dev)) {
 		/* If the dev was up, attempt to close, if close fails, reset */
 		gve_reset_and_teardown(priv, was_up);
@@ -2776,6 +2914,7 @@ static void gve_shutdown(struct pci_dev *pdev)
 		/* If the dev wasn't up or close worked, finish tearing down */
 		gve_teardown_priv_resources(priv);
 	}
+	netdev_unlock(netdev);
 	rtnl_unlock();
 }
 
@@ -2788,6 +2927,7 @@ static int gve_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	priv->suspend_cnt++;
 	rtnl_lock();
+	netdev_lock(netdev);
 	if (was_up && gve_close(priv->dev)) {
 		/* If the dev was up, attempt to close, if close fails, reset */
 		gve_reset_and_teardown(priv, was_up);
@@ -2796,6 +2936,7 @@ static int gve_suspend(struct pci_dev *pdev, pm_message_t state)
 		gve_teardown_priv_resources(priv);
 	}
 	priv->up_before_suspend = was_up;
+	netdev_unlock(netdev);
 	rtnl_unlock();
 	return 0;
 }
@@ -2808,7 +2949,9 @@ static int gve_resume(struct pci_dev *pdev)
 
 	priv->resume_cnt++;
 	rtnl_lock();
+	netdev_lock(netdev);
 	err = gve_reset_recovery(priv, priv->up_before_suspend);
+	netdev_unlock(netdev);
 	rtnl_unlock();
 	return err;
 }
diff --git a/drivers/net/ethernet/google/gve/gve_ptp.c b/drivers/net/ethernet/google/gve/gve_ptp.c
new file mode 100644
index 000000000000..073677d82ee8
--- /dev/null
+++ b/drivers/net/ethernet/google/gve/gve_ptp.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Google virtual Ethernet (gve) driver
+ *
+ * Copyright (C) 2025 Google LLC
+ */
+
+#include "gve.h"
+#include "gve_adminq.h"
+
+/* Interval to schedule a nic timestamp calibration, 250ms. */
+#define GVE_NIC_TS_SYNC_INTERVAL_MS 250
+
+/* Read the nic timestamp from hardware via the admin queue. */
+int gve_clock_nic_ts_read(struct gve_priv *priv)
+{
+	u64 nic_raw;
+	int err;
+
+	err = gve_adminq_report_nic_ts(priv, priv->nic_ts_report_bus);
+	if (err)
+		return err;
+
+	nic_raw = be64_to_cpu(priv->nic_ts_report->nic_timestamp);
+	WRITE_ONCE(priv->last_sync_nic_counter, nic_raw);
+
+	return 0;
+}
+
+static int gve_ptp_gettimex64(struct ptp_clock_info *info,
+			      struct timespec64 *ts,
+			      struct ptp_system_timestamp *sts)
+{
+	return -EOPNOTSUPP;
+}
+
+static int gve_ptp_settime64(struct ptp_clock_info *info,
+			     const struct timespec64 *ts)
+{
+	return -EOPNOTSUPP;
+}
+
+static long gve_ptp_do_aux_work(struct ptp_clock_info *info)
+{
+	const struct gve_ptp *ptp = container_of(info, struct gve_ptp, info);
+	struct gve_priv *priv = ptp->priv;
+	int err;
+
+	if (gve_get_reset_in_progress(priv) || !gve_get_admin_queue_ok(priv))
+		goto out;
+
+	err = gve_clock_nic_ts_read(priv);
+	if (err && net_ratelimit())
+		dev_err(&priv->pdev->dev,
+			"%s read err %d\n", __func__, err);
+
+out:
+	return msecs_to_jiffies(GVE_NIC_TS_SYNC_INTERVAL_MS);
+}
+
+static const struct ptp_clock_info gve_ptp_caps = {
+	.owner          = THIS_MODULE,
+	.name		= "gve clock",
+	.gettimex64	= gve_ptp_gettimex64,
+	.settime64	= gve_ptp_settime64,
+	.do_aux_work	= gve_ptp_do_aux_work,
+};
+
+static int gve_ptp_init(struct gve_priv *priv)
+{
+	struct gve_ptp *ptp;
+	int err;
+
+	if (!priv->nic_timestamp_supported) {
+		dev_dbg(&priv->pdev->dev, "Device does not support PTP\n");
+		return -EOPNOTSUPP;
+	}
+
+	priv->ptp = kzalloc(sizeof(*priv->ptp), GFP_KERNEL);
+	if (!priv->ptp)
+		return -ENOMEM;
+
+	ptp = priv->ptp;
+	ptp->info = gve_ptp_caps;
+	ptp->clock = ptp_clock_register(&ptp->info, &priv->pdev->dev);
+
+	if (IS_ERR(ptp->clock)) {
+		dev_err(&priv->pdev->dev, "PTP clock registration failed\n");
+		err  = PTR_ERR(ptp->clock);
+		goto free_ptp;
+	}
+
+	ptp->priv = priv;
+	return 0;
+
+free_ptp:
+	kfree(ptp);
+	priv->ptp = NULL;
+	return err;
+}
+
+static void gve_ptp_release(struct gve_priv *priv)
+{
+	struct gve_ptp *ptp = priv->ptp;
+
+	if (!ptp)
+		return;
+
+	if (ptp->clock)
+		ptp_clock_unregister(ptp->clock);
+
+	kfree(ptp);
+	priv->ptp = NULL;
+}
+
+int gve_init_clock(struct gve_priv *priv)
+{
+	int err;
+
+	if (!priv->nic_timestamp_supported)
+		return 0;
+
+	err = gve_ptp_init(priv);
+	if (err)
+		return err;
+
+	priv->nic_ts_report =
+		dma_alloc_coherent(&priv->pdev->dev,
+				   sizeof(struct gve_nic_ts_report),
+				   &priv->nic_ts_report_bus,
+				   GFP_KERNEL);
+	if (!priv->nic_ts_report) {
+		dev_err(&priv->pdev->dev, "%s dma alloc error\n", __func__);
+		err = -ENOMEM;
+		goto release_ptp;
+	}
+	err = gve_clock_nic_ts_read(priv);
+	if (err) {
+		dev_err(&priv->pdev->dev, "failed to read NIC clock %d\n", err);
+		goto release_nic_ts_report;
+	}
+	ptp_schedule_worker(priv->ptp->clock,
+			    msecs_to_jiffies(GVE_NIC_TS_SYNC_INTERVAL_MS));
+
+	return 0;
+
+release_nic_ts_report:
+	dma_free_coherent(&priv->pdev->dev,
+			  sizeof(struct gve_nic_ts_report),
+			  priv->nic_ts_report, priv->nic_ts_report_bus);
+	priv->nic_ts_report = NULL;
+release_ptp:
+	gve_ptp_release(priv);
+	return err;
+}
+
+void gve_teardown_clock(struct gve_priv *priv)
+{
+	gve_ptp_release(priv);
+
+	if (priv->nic_ts_report) {
+		dma_free_coherent(&priv->pdev->dev,
+				  sizeof(struct gve_nic_ts_report),
+				  priv->nic_ts_report, priv->nic_ts_report_bus);
+		priv->nic_ts_report = NULL;
+	}
+}
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index acb73d4d0de6..ec424d2f4f57 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -141,12 +141,15 @@ void gve_rx_free_ring_gqi(struct gve_priv *priv, struct gve_rx_ring *rx,
 	netif_dbg(priv, drv, priv->dev, "freed rx ring %d\n", idx);
 }
 
-static void gve_setup_rx_buffer(struct gve_rx_slot_page_info *page_info,
-			     dma_addr_t addr, struct page *page, __be64 *slot_addr)
+static void gve_setup_rx_buffer(struct gve_rx_ring *rx,
+				struct gve_rx_slot_page_info *page_info,
+				dma_addr_t addr, struct page *page,
+				__be64 *slot_addr)
 {
 	page_info->page = page;
 	page_info->page_offset = 0;
 	page_info->page_address = page_address(page);
+	page_info->buf_size = rx->packet_buffer_size;
 	*slot_addr = cpu_to_be64(addr);
 	/* The page already has 1 ref */
 	page_ref_add(page, INT_MAX - 1);
@@ -171,7 +174,7 @@ static int gve_rx_alloc_buffer(struct gve_priv *priv, struct device *dev,
 		return err;
 	}
 
-	gve_setup_rx_buffer(page_info, dma, page, &data_slot->addr);
+	gve_setup_rx_buffer(rx, page_info, dma, page, &data_slot->addr);
 	return 0;
 }
 
@@ -189,8 +192,8 @@ static int gve_rx_prefill_pages(struct gve_rx_ring *rx,
 	 */
 	slots = rx->mask + 1;
 
-	rx->data.page_info = kvzalloc(slots *
-				      sizeof(*rx->data.page_info), GFP_KERNEL);
+	rx->data.page_info = kvcalloc_node(slots, sizeof(*rx->data.page_info),
+					   GFP_KERNEL, priv->numa_node);
 	if (!rx->data.page_info)
 		return -ENOMEM;
 
@@ -199,7 +202,8 @@ static int gve_rx_prefill_pages(struct gve_rx_ring *rx,
 			struct page *page = rx->data.qpl->pages[i];
 			dma_addr_t addr = i * PAGE_SIZE;
 
-			gve_setup_rx_buffer(&rx->data.page_info[i], addr, page,
+			gve_setup_rx_buffer(rx, &rx->data.page_info[i], addr,
+					    page,
 					    &rx->data.data_ring[i].qpl_offset);
 			continue;
 		}
@@ -212,7 +216,8 @@ static int gve_rx_prefill_pages(struct gve_rx_ring *rx,
 
 	if (!rx->data.raw_addressing) {
 		for (j = 0; j < rx->qpl_copy_pool_mask + 1; j++) {
-			struct page *page = alloc_page(GFP_KERNEL);
+			struct page *page = alloc_pages_node(priv->numa_node,
+							     GFP_KERNEL, 0);
 
 			if (!page) {
 				err = -ENOMEM;
@@ -222,6 +227,7 @@ static int gve_rx_prefill_pages(struct gve_rx_ring *rx,
 			rx->qpl_copy_pool[j].page = page;
 			rx->qpl_copy_pool[j].page_offset = 0;
 			rx->qpl_copy_pool[j].page_address = page_address(page);
+			rx->qpl_copy_pool[j].buf_size = rx->packet_buffer_size;
 
 			/* The page already has 1 ref. */
 			page_ref_add(page, INT_MAX - 1);
@@ -283,6 +289,7 @@ int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
 
 	rx->gve = priv;
 	rx->q_num = idx;
+	rx->packet_buffer_size = cfg->packet_buffer_size;
 
 	rx->mask = slots - 1;
 	rx->data.raw_addressing = cfg->raw_addressing;
@@ -297,10 +304,9 @@ int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
 
 	rx->qpl_copy_pool_mask = min_t(u32, U32_MAX, slots * 2) - 1;
 	rx->qpl_copy_pool_head = 0;
-	rx->qpl_copy_pool = kvcalloc(rx->qpl_copy_pool_mask + 1,
-				     sizeof(rx->qpl_copy_pool[0]),
-				     GFP_KERNEL);
-
+	rx->qpl_copy_pool = kvcalloc_node(rx->qpl_copy_pool_mask + 1,
+					  sizeof(rx->qpl_copy_pool[0]),
+					  GFP_KERNEL, priv->numa_node);
 	if (!rx->qpl_copy_pool) {
 		err = -ENOMEM;
 		goto abort_with_slots;
@@ -351,7 +357,6 @@ int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
 	rx->db_threshold = slots / 2;
 	gve_rx_init_ring_state_gqi(rx);
 
-	rx->packet_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE;
 	gve_rx_ctx_clear(&rx->ctx);
 
 	return 0;
@@ -385,12 +390,12 @@ int gve_rx_alloc_rings_gqi(struct gve_priv *priv,
 	int err = 0;
 	int i, j;
 
-	rx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_rx_ring),
+	rx = kvcalloc(cfg->qcfg_rx->max_queues, sizeof(struct gve_rx_ring),
 		      GFP_KERNEL);
 	if (!rx)
 		return -ENOMEM;
 
-	for (i = 0; i < cfg->qcfg->num_queues; i++) {
+	for (i = 0; i < cfg->qcfg_rx->num_queues; i++) {
 		err = gve_rx_alloc_ring_gqi(priv, cfg, &rx[i], i);
 		if (err) {
 			netif_err(priv, drv, priv->dev,
@@ -419,7 +424,7 @@ void gve_rx_free_rings_gqi(struct gve_priv *priv,
 	if (!rx)
 		return;
 
-	for (i = 0; i < cfg->qcfg->num_queues;  i++)
+	for (i = 0; i < cfg->qcfg_rx->num_queues;  i++)
 		gve_rx_free_ring_gqi(priv, &rx[i], cfg);
 
 	kvfree(rx);
@@ -590,7 +595,7 @@ static struct sk_buff *gve_rx_copy_to_pool(struct gve_rx_ring *rx,
 	copy_page_info->pad = page_info->pad;
 
 	skb = gve_rx_add_frags(napi, copy_page_info,
-			       rx->packet_buffer_size, len, ctx);
+			       copy_page_info->buf_size, len, ctx);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -630,7 +635,8 @@ gve_rx_qpl(struct device *dev, struct net_device *netdev,
 	 * device.
 	 */
 	if (page_info->can_flip) {
-		skb = gve_rx_add_frags(napi, page_info, rx->packet_buffer_size, len, ctx);
+		skb = gve_rx_add_frags(napi, page_info, page_info->buf_size,
+				       len, ctx);
 		/* No point in recycling if we didn't get the skb */
 		if (skb) {
 			/* Make sure that the page isn't freed. */
@@ -680,7 +686,7 @@ static struct sk_buff *gve_rx_skb(struct gve_priv *priv, struct gve_rx_ring *rx,
 			skb = gve_rx_raw_addressing(&priv->pdev->dev, netdev,
 						    page_info, len, napi,
 						    data_slot,
-						    rx->packet_buffer_size, ctx);
+						    page_info->buf_size, ctx);
 		} else {
 			skb = gve_rx_qpl(&priv->pdev->dev, netdev, rx,
 					 page_info, len, napi, data_slot);
@@ -855,7 +861,7 @@ static void gve_rx(struct gve_rx_ring *rx, netdev_features_t feat,
 		void *old_data;
 		int xdp_act;
 
-		xdp_init_buff(&xdp, rx->packet_buffer_size, &rx->xdp_rxq);
+		xdp_init_buff(&xdp, page_info->buf_size, &rx->xdp_rxq);
 		xdp_prepare_buff(&xdp, page_info->page_address +
 				 page_info->page_offset, GVE_RX_PAD,
 				 len, false);
diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 8ac0047f1ada..f1bd8f5d5732 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -8,6 +8,7 @@
 #include "gve_dqo.h"
 #include "gve_adminq.h"
 #include "gve_utils.h"
+#include <linux/bpf.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/skbuff.h>
@@ -15,6 +16,7 @@
 #include <net/ip6_checksum.h>
 #include <net/ipv6.h>
 #include <net/tcp.h>
+#include <net/xdp_sock_drv.h>
 
 static void gve_rx_free_hdr_bufs(struct gve_priv *priv, struct gve_rx_ring *rx)
 {
@@ -109,10 +111,13 @@ static void gve_rx_reset_ring_dqo(struct gve_priv *priv, int idx)
 void gve_rx_stop_ring_dqo(struct gve_priv *priv, int idx)
 {
 	int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
+	struct gve_rx_ring *rx = &priv->rx[idx];
 
 	if (!gve_rx_was_added_to_block(priv, idx))
 		return;
 
+	if (rx->dqo.page_pool)
+		page_pool_disable_direct_recycling(rx->dqo.page_pool);
 	gve_remove_napi(priv, ntfy_idx);
 	gve_rx_remove_from_block(priv, idx);
 	gve_rx_reset_ring_dqo(priv, idx);
@@ -145,6 +150,10 @@ void gve_rx_free_ring_dqo(struct gve_priv *priv, struct gve_rx_ring *rx,
 			gve_free_to_page_pool(rx, bs, false);
 		else
 			gve_free_qpl_page_dqo(bs);
+		if (gve_buf_state_is_allocated(rx, bs) && bs->xsk_buff) {
+			xsk_buff_free(bs->xsk_buff);
+			bs->xsk_buff = NULL;
+		}
 	}
 
 	if (rx->dqo.qpl) {
@@ -221,12 +230,26 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 	memset(rx, 0, sizeof(*rx));
 	rx->gve = priv;
 	rx->q_num = idx;
+	rx->packet_buffer_size = cfg->packet_buffer_size;
+
+	if (cfg->xdp) {
+		rx->packet_buffer_truesize = GVE_XDP_RX_BUFFER_SIZE_DQO;
+		rx->rx_headroom = XDP_PACKET_HEADROOM;
+	} else {
+		rx->packet_buffer_truesize = rx->packet_buffer_size;
+		rx->rx_headroom = 0;
+	}
+
+	/* struct gve_xdp_buff is overlaid on struct xdp_buff_xsk and utilizes
+	 * the 24 byte field cb to store gve specific data.
+	 */
+	XSK_CHECK_PRIV_TYPE(struct gve_xdp_buff);
 
 	rx->dqo.num_buf_states = cfg->raw_addressing ? buffer_queue_slots :
 		gve_get_rx_pages_per_qpl_dqo(cfg->ring_size);
-	rx->dqo.buf_states = kvcalloc(rx->dqo.num_buf_states,
-				      sizeof(rx->dqo.buf_states[0]),
-				      GFP_KERNEL);
+	rx->dqo.buf_states = kvcalloc_node(rx->dqo.num_buf_states,
+					   sizeof(rx->dqo.buf_states[0]),
+					   GFP_KERNEL, priv->numa_node);
 	if (!rx->dqo.buf_states)
 		return -ENOMEM;
 
@@ -251,7 +274,7 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 		goto err;
 
 	if (cfg->raw_addressing) {
-		pool = gve_rx_create_page_pool(priv, rx);
+		pool = gve_rx_create_page_pool(priv, rx, cfg->xdp);
 		if (IS_ERR(pool))
 			goto err;
 
@@ -297,12 +320,12 @@ int gve_rx_alloc_rings_dqo(struct gve_priv *priv,
 	int err;
 	int i;
 
-	rx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_rx_ring),
+	rx = kvcalloc(cfg->qcfg_rx->max_queues, sizeof(struct gve_rx_ring),
 		      GFP_KERNEL);
 	if (!rx)
 		return -ENOMEM;
 
-	for (i = 0; i < cfg->qcfg->num_queues; i++) {
+	for (i = 0; i < cfg->qcfg_rx->num_queues; i++) {
 		err = gve_rx_alloc_ring_dqo(priv, cfg, &rx[i], i);
 		if (err) {
 			netif_err(priv, drv, priv->dev,
@@ -331,7 +354,7 @@ void gve_rx_free_rings_dqo(struct gve_priv *priv,
 	if (!rx)
 		return;
 
-	for (i = 0; i < cfg->qcfg->num_queues;  i++)
+	for (i = 0; i < cfg->qcfg_rx->num_queues;  i++)
 		gve_rx_free_ring_dqo(priv, &rx[i], cfg);
 
 	kvfree(rx);
@@ -425,6 +448,53 @@ static void gve_rx_skb_hash(struct sk_buff *skb,
 	skb_set_hash(skb, le32_to_cpu(compl_desc->hash), hash_type);
 }
 
+/* Expand the hardware timestamp to the full 64 bits of width, and add it to the
+ * skb.
+ *
+ * This algorithm works by using the passed hardware timestamp to generate a
+ * diff relative to the last read of the nic clock. This diff can be positive or
+ * negative, as it is possible that we have read the clock more recently than
+ * the hardware has received this packet. To detect this, we use the high bit of
+ * the diff, and assume that the read is more recent if the high bit is set. In
+ * this case we invert the process.
+ *
+ * Note that this means if the time delta between packet reception and the last
+ * clock read is greater than ~2 seconds, this will provide invalid results.
+ */
+static ktime_t gve_rx_get_hwtstamp(struct gve_priv *gve, u32 hwts)
+{
+	u64 last_read = READ_ONCE(gve->last_sync_nic_counter);
+	u32 low = (u32)last_read;
+	s32 diff = hwts - low;
+
+	return ns_to_ktime(last_read + diff);
+}
+
+static void gve_rx_skb_hwtstamp(struct gve_rx_ring *rx,
+				const struct gve_rx_compl_desc_dqo *desc)
+{
+	struct sk_buff *skb = rx->ctx.skb_head;
+
+	if (desc->ts_sub_nsecs_low & GVE_DQO_RX_HWTSTAMP_VALID)
+		skb_hwtstamps(skb)->hwtstamp =
+			gve_rx_get_hwtstamp(rx->gve, le32_to_cpu(desc->ts));
+}
+
+int gve_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp)
+{
+	const struct gve_xdp_buff *ctx = (void *)_ctx;
+
+	if (!ctx->gve->nic_ts_report)
+		return -ENODATA;
+
+	if (!(ctx->compl_desc->ts_sub_nsecs_low & GVE_DQO_RX_HWTSTAMP_VALID))
+		return -ENODATA;
+
+	*timestamp = gve_rx_get_hwtstamp(ctx->gve,
+					 le32_to_cpu(ctx->compl_desc->ts));
+	return 0;
+}
+
 static void gve_rx_free_skb(struct napi_struct *napi, struct gve_rx_ring *rx)
 {
 	if (!rx->ctx.skb_head)
@@ -452,7 +522,7 @@ static int gve_rx_copy_ondemand(struct gve_rx_ring *rx,
 				struct gve_rx_buf_state_dqo *buf_state,
 				u16 buf_len)
 {
-	struct page *page = alloc_page(GFP_ATOMIC);
+	struct page *page = alloc_pages_node(rx->gve->numa_node, GFP_ATOMIC, 0);
 	int num_frags;
 
 	if (!page)
@@ -474,6 +544,25 @@ static int gve_rx_copy_ondemand(struct gve_rx_ring *rx,
 	return 0;
 }
 
+static void gve_skb_add_rx_frag(struct gve_rx_ring *rx,
+				struct gve_rx_buf_state_dqo *buf_state,
+				int num_frags, u16 buf_len)
+{
+	if (rx->dqo.page_pool) {
+		skb_add_rx_frag_netmem(rx->ctx.skb_tail, num_frags,
+				       buf_state->page_info.netmem,
+				       buf_state->page_info.page_offset +
+				       buf_state->page_info.pad, buf_len,
+				       buf_state->page_info.buf_size);
+	} else {
+		skb_add_rx_frag(rx->ctx.skb_tail, num_frags,
+				buf_state->page_info.page,
+				buf_state->page_info.page_offset +
+				buf_state->page_info.pad, buf_len,
+				buf_state->page_info.buf_size);
+	}
+}
+
 /* Chains multi skbs for single rx packet.
  * Returns 0 if buffer is appended, -1 otherwise.
  */
@@ -511,14 +600,178 @@ static int gve_rx_append_frags(struct napi_struct *napi,
 	if (gve_rx_should_trigger_copy_ondemand(rx))
 		return gve_rx_copy_ondemand(rx, buf_state, buf_len);
 
-	skb_add_rx_frag(rx->ctx.skb_tail, num_frags,
-			buf_state->page_info.page,
-			buf_state->page_info.page_offset,
-			buf_len, buf_state->page_info.buf_size);
+	gve_skb_add_rx_frag(rx, buf_state, num_frags, buf_len);
 	gve_reuse_buffer(rx, buf_state);
 	return 0;
 }
 
+static int gve_xdp_tx_dqo(struct gve_priv *priv, struct gve_rx_ring *rx,
+			  struct xdp_buff *xdp)
+{
+	struct gve_tx_ring *tx;
+	struct xdp_frame *xdpf;
+	u32 tx_qid;
+	int err;
+
+	xdpf = xdp_convert_buff_to_frame(xdp);
+	if (unlikely(!xdpf)) {
+		if (rx->xsk_pool)
+			xsk_buff_free(xdp);
+		return -ENOSPC;
+	}
+
+	tx_qid = gve_xdp_tx_queue_id(priv, rx->q_num);
+	tx = &priv->tx[tx_qid];
+	spin_lock(&tx->dqo_tx.xdp_lock);
+	err = gve_xdp_xmit_one_dqo(priv, tx, xdpf);
+	spin_unlock(&tx->dqo_tx.xdp_lock);
+
+	return err;
+}
+
+static void gve_xsk_done_dqo(struct gve_priv *priv, struct gve_rx_ring *rx,
+			     struct xdp_buff *xdp, struct bpf_prog *xprog,
+			     int xdp_act)
+{
+	switch (xdp_act) {
+	case XDP_ABORTED:
+	case XDP_DROP:
+	default:
+		xsk_buff_free(xdp);
+		break;
+	case XDP_TX:
+		if (unlikely(gve_xdp_tx_dqo(priv, rx, xdp)))
+			goto err;
+		break;
+	case XDP_REDIRECT:
+		if (unlikely(xdp_do_redirect(priv->dev, xdp, xprog)))
+			goto err;
+		break;
+	}
+
+	u64_stats_update_begin(&rx->statss);
+	if ((u32)xdp_act < GVE_XDP_ACTIONS)
+		rx->xdp_actions[xdp_act]++;
+	u64_stats_update_end(&rx->statss);
+	return;
+
+err:
+	u64_stats_update_begin(&rx->statss);
+	if (xdp_act == XDP_TX)
+		rx->xdp_tx_errors++;
+	if (xdp_act == XDP_REDIRECT)
+		rx->xdp_redirect_errors++;
+	u64_stats_update_end(&rx->statss);
+}
+
+static void gve_xdp_done_dqo(struct gve_priv *priv, struct gve_rx_ring *rx,
+			     struct xdp_buff *xdp, struct bpf_prog *xprog,
+			     int xdp_act,
+			     struct gve_rx_buf_state_dqo *buf_state)
+{
+	int err;
+	switch (xdp_act) {
+	case XDP_ABORTED:
+	case XDP_DROP:
+	default:
+		gve_free_buffer(rx, buf_state);
+		break;
+	case XDP_TX:
+		err = gve_xdp_tx_dqo(priv, rx, xdp);
+		if (unlikely(err))
+			goto err;
+		gve_reuse_buffer(rx, buf_state);
+		break;
+	case XDP_REDIRECT:
+		err = xdp_do_redirect(priv->dev, xdp, xprog);
+		if (unlikely(err))
+			goto err;
+		gve_reuse_buffer(rx, buf_state);
+		break;
+	}
+	u64_stats_update_begin(&rx->statss);
+	if ((u32)xdp_act < GVE_XDP_ACTIONS)
+		rx->xdp_actions[xdp_act]++;
+	u64_stats_update_end(&rx->statss);
+	return;
+err:
+	u64_stats_update_begin(&rx->statss);
+	if (xdp_act == XDP_TX)
+		rx->xdp_tx_errors++;
+	else if (xdp_act == XDP_REDIRECT)
+		rx->xdp_redirect_errors++;
+	u64_stats_update_end(&rx->statss);
+	gve_free_buffer(rx, buf_state);
+	return;
+}
+
+static int gve_rx_xsk_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
+			  const struct gve_rx_compl_desc_dqo *compl_desc,
+			  struct gve_rx_buf_state_dqo *buf_state,
+			  struct bpf_prog *xprog)
+{
+	struct xdp_buff *xdp = buf_state->xsk_buff;
+	int buf_len = compl_desc->packet_len;
+	struct gve_priv *priv = rx->gve;
+	struct gve_xdp_buff *gve_xdp;
+	int xdp_act;
+
+	xdp->data_end = xdp->data + buf_len;
+	xsk_buff_dma_sync_for_cpu(xdp);
+
+	gve_xdp = (void *)xdp;
+	gve_xdp->gve = priv;
+	gve_xdp->compl_desc = compl_desc;
+
+	if (xprog) {
+		xdp_act = bpf_prog_run_xdp(xprog, xdp);
+		buf_len = xdp->data_end - xdp->data;
+		if (xdp_act != XDP_PASS) {
+			gve_xsk_done_dqo(priv, rx, xdp, xprog, xdp_act);
+			gve_free_buf_state(rx, buf_state);
+			return 0;
+		}
+	}
+
+	/* Copy the data to skb */
+	rx->ctx.skb_head = gve_rx_copy_data(priv->dev, napi,
+					    xdp->data, buf_len);
+	if (unlikely(!rx->ctx.skb_head)) {
+		xsk_buff_free(xdp);
+		gve_free_buf_state(rx, buf_state);
+		return -ENOMEM;
+	}
+	rx->ctx.skb_tail = rx->ctx.skb_head;
+
+	/* Free XSK buffer and Buffer state */
+	xsk_buff_free(xdp);
+	gve_free_buf_state(rx, buf_state);
+
+	/* Update Stats */
+	u64_stats_update_begin(&rx->statss);
+	rx->xdp_actions[XDP_PASS]++;
+	u64_stats_update_end(&rx->statss);
+	return 0;
+}
+
+static void gve_dma_sync(struct gve_priv *priv, struct gve_rx_ring *rx,
+			 struct gve_rx_buf_state_dqo *buf_state, u16 buf_len)
+{
+	struct gve_rx_slot_page_info *page_info = &buf_state->page_info;
+
+	if (rx->dqo.page_pool) {
+		page_pool_dma_sync_netmem_for_cpu(rx->dqo.page_pool,
+						  page_info->netmem,
+						  page_info->page_offset,
+						  buf_len);
+	} else {
+		dma_sync_single_range_for_cpu(&priv->pdev->dev, buf_state->addr,
+					      page_info->page_offset +
+					      page_info->pad,
+					      buf_len, DMA_FROM_DEVICE);
+	}
+}
+
 /* Returns 0 if descriptor is completed successfully.
  * Returns -EINVAL if descriptor is invalid.
  * Returns -ENOMEM if data cannot be copied to skb.
@@ -533,6 +786,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 	const bool hsplit = compl_desc->split_header;
 	struct gve_rx_buf_state_dqo *buf_state;
 	struct gve_priv *priv = rx->gve;
+	struct bpf_prog *xprog;
 	u16 buf_len;
 	u16 hdr_len;
 
@@ -556,10 +810,19 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 	buf_len = compl_desc->packet_len;
 	hdr_len = compl_desc->header_len;
 
+	xprog = READ_ONCE(priv->xdp_prog);
+	if (buf_state->xsk_buff)
+		return gve_rx_xsk_dqo(napi, rx, compl_desc, buf_state, xprog);
+
 	/* Page might have not been used for awhile and was likely last written
 	 * by a different thread.
 	 */
-	prefetch(buf_state->page_info.page);
+	if (rx->dqo.page_pool) {
+		if (!netmem_is_net_iov(buf_state->page_info.netmem))
+			prefetch(netmem_to_page(buf_state->page_info.netmem));
+	} else {
+		prefetch(buf_state->page_info.page);
+	}
 
 	/* Copy the header into the skb in the case of header split */
 	if (hsplit) {
@@ -584,12 +847,18 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 		rx->rx_hsplit_unsplit_pkt += unsplit;
 		rx->rx_hsplit_bytes += hdr_len;
 		u64_stats_update_end(&rx->statss);
+	} else if (!rx->ctx.skb_head && rx->dqo.page_pool &&
+		   netmem_is_net_iov(buf_state->page_info.netmem)) {
+		/* when header split is disabled, the header went to the packet
+		 * buffer. If the packet buffer is a net_iov, those can't be
+		 * easily mapped into the kernel space to access the header
+		 * required to process the packet.
+		 */
+		goto error;
 	}
 
 	/* Sync the portion of dma buffer for CPU to read. */
-	dma_sync_single_range_for_cpu(&priv->pdev->dev, buf_state->addr,
-				      buf_state->page_info.page_offset,
-				      buf_len, DMA_FROM_DEVICE);
+	gve_dma_sync(priv, rx, buf_state, buf_len);
 
 	/* Append to current skb if one exists. */
 	if (rx->ctx.skb_head) {
@@ -600,7 +869,39 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 		return 0;
 	}
 
-	if (eop && buf_len <= priv->rx_copybreak) {
+	if (xprog) {
+		struct gve_xdp_buff gve_xdp;
+		void *old_data;
+		int xdp_act;
+
+		xdp_init_buff(&gve_xdp.xdp, buf_state->page_info.buf_size,
+			      &rx->xdp_rxq);
+		xdp_prepare_buff(&gve_xdp.xdp,
+				 buf_state->page_info.page_address +
+				 buf_state->page_info.page_offset,
+				 buf_state->page_info.pad,
+				 buf_len, false);
+		gve_xdp.gve = priv;
+		gve_xdp.compl_desc = compl_desc;
+
+		old_data = gve_xdp.xdp.data;
+		xdp_act = bpf_prog_run_xdp(xprog, &gve_xdp.xdp);
+		buf_state->page_info.pad += gve_xdp.xdp.data - old_data;
+		buf_len = gve_xdp.xdp.data_end - gve_xdp.xdp.data;
+		if (xdp_act != XDP_PASS) {
+			gve_xdp_done_dqo(priv, rx, &gve_xdp.xdp, xprog, xdp_act,
+					 buf_state);
+			return 0;
+		}
+
+		u64_stats_update_begin(&rx->statss);
+		rx->xdp_actions[XDP_PASS]++;
+		u64_stats_update_end(&rx->statss);
+	}
+
+	if (eop && buf_len <= priv->rx_copybreak &&
+	    !(rx->dqo.page_pool &&
+	      netmem_is_net_iov(buf_state->page_info.netmem))) {
 		rx->ctx.skb_head = gve_rx_copy(priv->dev, napi,
 					       &buf_state->page_info, buf_len);
 		if (unlikely(!rx->ctx.skb_head))
@@ -630,9 +931,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 	if (rx->dqo.page_pool)
 		skb_mark_for_recycle(rx->ctx.skb_head);
 
-	skb_add_rx_frag(rx->ctx.skb_head, 0, buf_state->page_info.page,
-			buf_state->page_info.page_offset, buf_len,
-			buf_state->page_info.buf_size);
+	gve_skb_add_rx_frag(rx, buf_state, 0, buf_len);
 	gve_reuse_buffer(rx, buf_state);
 	return 0;
 
@@ -683,6 +982,9 @@ static int gve_rx_complete_skb(struct gve_rx_ring *rx, struct napi_struct *napi,
 	if (feat & NETIF_F_RXCSUM)
 		gve_rx_skb_csum(rx->ctx.skb_head, desc, ptype);
 
+	if (rx->gve->ts_config.rx_filter == HWTSTAMP_FILTER_ALL)
+		gve_rx_skb_hwtstamp(rx, desc);
+
 	/* RSC packets must set gso_size otherwise the TCP stack will complain
 	 * that packets are larger than MTU.
 	 */
@@ -702,16 +1004,27 @@ static int gve_rx_complete_skb(struct gve_rx_ring *rx, struct napi_struct *napi,
 
 int gve_rx_poll_dqo(struct gve_notify_block *block, int budget)
 {
-	struct napi_struct *napi = &block->napi;
-	netdev_features_t feat = napi->dev->features;
-
-	struct gve_rx_ring *rx = block->rx;
-	struct gve_rx_compl_queue_dqo *complq = &rx->dqo.complq;
-
+	struct gve_rx_compl_queue_dqo *complq;
+	struct napi_struct *napi;
+	netdev_features_t feat;
+	struct gve_rx_ring *rx;
+	struct gve_priv *priv;
+	u64 xdp_redirects;
 	u32 work_done = 0;
 	u64 bytes = 0;
+	u64 xdp_txs;
 	int err;
 
+	napi = &block->napi;
+	feat = napi->dev->features;
+
+	rx = block->rx;
+	priv = rx->gve;
+	complq = &rx->dqo.complq;
+
+	xdp_redirects = rx->xdp_actions[XDP_REDIRECT];
+	xdp_txs = rx->xdp_actions[XDP_TX];
+
 	while (work_done < budget) {
 		struct gve_rx_compl_desc_dqo *compl_desc =
 			&complq->desc_ring[complq->head];
@@ -785,6 +1098,12 @@ int gve_rx_poll_dqo(struct gve_notify_block *block, int budget)
 		rx->ctx.skb_tail = NULL;
 	}
 
+	if (xdp_txs != rx->xdp_actions[XDP_TX])
+		gve_xdp_tx_flush_dqo(priv, rx->q_num);
+
+	if (xdp_redirects != rx->xdp_actions[XDP_REDIRECT])
+		xdp_do_flush();
+
 	gve_rx_post_buffers_dqo(rx);
 
 	u64_stats_update_begin(&rx->statss);
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index e7fb7d6d283d..97efc8d27e6f 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -206,7 +206,10 @@ void gve_tx_stop_ring_gqi(struct gve_priv *priv, int idx)
 		return;
 
 	gve_remove_napi(priv, ntfy_idx);
-	gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false);
+	if (tx->q_num < priv->tx_cfg.num_queues)
+		gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false);
+	else
+		gve_clean_xdp_done(priv, tx, priv->tx_desc_cnt);
 	netdev_tx_reset_queue(tx->netdev_txq);
 	gve_tx_remove_from_block(priv, idx);
 }
@@ -331,27 +334,23 @@ int gve_tx_alloc_rings_gqi(struct gve_priv *priv,
 			   struct gve_tx_alloc_rings_cfg *cfg)
 {
 	struct gve_tx_ring *tx = cfg->tx;
+	int total_queues;
 	int err = 0;
 	int i, j;
 
-	if (cfg->start_idx + cfg->num_rings > cfg->qcfg->max_queues) {
+	total_queues = cfg->qcfg->num_queues + cfg->num_xdp_rings;
+	if (total_queues > cfg->qcfg->max_queues) {
 		netif_err(priv, drv, priv->dev,
 			  "Cannot alloc more than the max num of Tx rings\n");
 		return -EINVAL;
 	}
 
-	if (cfg->start_idx == 0) {
-		tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring),
-			      GFP_KERNEL);
-		if (!tx)
-			return -ENOMEM;
-	} else if (!tx) {
-		netif_err(priv, drv, priv->dev,
-			  "Cannot alloc tx rings from a nonzero start idx without tx array\n");
-		return -EINVAL;
-	}
+	tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring),
+		      GFP_KERNEL);
+	if (!tx)
+		return -ENOMEM;
 
-	for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++) {
+	for (i = 0; i < total_queues; i++) {
 		err = gve_tx_alloc_ring_gqi(priv, cfg, &tx[i], i);
 		if (err) {
 			netif_err(priv, drv, priv->dev,
@@ -367,8 +366,7 @@ int gve_tx_alloc_rings_gqi(struct gve_priv *priv,
 cleanup:
 	for (j = 0; j < i; j++)
 		gve_tx_free_ring_gqi(priv, &tx[j], cfg);
-	if (cfg->start_idx == 0)
-		kvfree(tx);
+	kvfree(tx);
 	return err;
 }
 
@@ -381,13 +379,11 @@ void gve_tx_free_rings_gqi(struct gve_priv *priv,
 	if (!tx)
 		return;
 
-	for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++)
+	for (i = 0; i < cfg->qcfg->num_queues + cfg->qcfg->num_xdp_queues; i++)
 		gve_tx_free_ring_gqi(priv, &tx[i], cfg);
 
-	if (cfg->start_idx == 0) {
-		kvfree(tx);
-		cfg->tx = NULL;
-	}
+	kvfree(tx);
+	cfg->tx = NULL;
 }
 
 /* gve_tx_avail - Calculates the number of slots available in the ring
@@ -734,7 +730,9 @@ unmap_drop:
 		gve_tx_unmap_buf(tx->dev, &tx->info[idx & tx->mask]);
 	}
 drop:
+	u64_stats_update_begin(&tx->statss);
 	tx->dropped_pkt++;
+	u64_stats_update_end(&tx->statss);
 	return 0;
 }
 
@@ -827,18 +825,21 @@ static int gve_tx_fill_xdp(struct gve_priv *priv, struct gve_tx_ring *tx,
 	return ndescs;
 }
 
-int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
-		 u32 flags)
+int gve_xdp_xmit_gqi(struct net_device *dev, int n, struct xdp_frame **frames,
+		     u32 flags)
 {
 	struct gve_priv *priv = netdev_priv(dev);
 	struct gve_tx_ring *tx;
 	int i, err = 0, qid;
 
-	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK) || !priv->xdp_prog)
 		return -EINVAL;
 
+	if (!gve_get_napi_enabled(priv))
+		return -ENETDOWN;
+
 	qid = gve_xdp_tx_queue_id(priv,
-				  smp_processor_id() % priv->num_xdp_queues);
+				  smp_processor_id() % priv->tx_cfg.num_xdp_queues);
 
 	tx = &priv->tx[qid];
 
@@ -953,14 +954,10 @@ static int gve_xsk_tx(struct gve_priv *priv, struct gve_tx_ring *tx,
 
 	spin_lock(&tx->xdp_lock);
 	while (sent < budget) {
-		if (!gve_can_tx(tx, GVE_TX_START_THRESH))
+		if (!gve_can_tx(tx, GVE_TX_START_THRESH) ||
+		    !xsk_tx_peek_desc(tx->xsk_pool, &desc))
 			goto out;
 
-		if (!xsk_tx_peek_desc(tx->xsk_pool, &desc)) {
-			tx->xdp_xsk_done = tx->xdp_xsk_wakeup;
-			goto out;
-		}
-
 		data = xsk_buff_raw_get_data(tx->xsk_pool, desc.addr);
 		nsegs = gve_tx_fill_xdp(priv, tx, data, desc.len, NULL, true);
 		tx->req += nsegs;
@@ -975,33 +972,41 @@ out:
 	return sent;
 }
 
+int gve_xsk_tx_poll(struct gve_notify_block *rx_block, int budget)
+{
+	struct gve_rx_ring *rx = rx_block->rx;
+	struct gve_priv *priv = rx->gve;
+	struct gve_tx_ring *tx;
+	int sent = 0;
+
+	tx = &priv->tx[gve_xdp_tx_queue_id(priv, rx->q_num)];
+	if (tx->xsk_pool) {
+		sent = gve_xsk_tx(priv, tx, budget);
+
+		u64_stats_update_begin(&tx->statss);
+		tx->xdp_xsk_sent += sent;
+		u64_stats_update_end(&tx->statss);
+		if (xsk_uses_need_wakeup(tx->xsk_pool))
+			xsk_set_tx_need_wakeup(tx->xsk_pool);
+	}
+
+	return sent;
+}
+
 bool gve_xdp_poll(struct gve_notify_block *block, int budget)
 {
 	struct gve_priv *priv = block->priv;
 	struct gve_tx_ring *tx = block->tx;
 	u32 nic_done;
-	bool repoll;
 	u32 to_do;
 
 	/* Find out how much work there is to be done */
 	nic_done = gve_tx_load_event_counter(priv, tx);
 	to_do = min_t(u32, (nic_done - tx->done), budget);
 	gve_clean_xdp_done(priv, tx, to_do);
-	repoll = nic_done != tx->done;
-
-	if (tx->xsk_pool) {
-		int sent = gve_xsk_tx(priv, tx, budget);
-
-		u64_stats_update_begin(&tx->statss);
-		tx->xdp_xsk_sent += sent;
-		u64_stats_update_end(&tx->statss);
-		repoll |= (sent == budget);
-		if (xsk_uses_need_wakeup(tx->xsk_pool))
-			xsk_set_tx_need_wakeup(tx->xsk_pool);
-	}
 
 	/* If we still have work we want to repoll */
-	return repoll;
+	return nic_done != tx->done;
 }
 
 bool gve_tx_poll(struct gve_notify_block *block, int budget)
diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index 394debc62268..40b89b3e5a31 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -9,9 +9,11 @@
 #include "gve_utils.h"
 #include "gve_dqo.h"
 #include <net/ip.h>
+#include <linux/bpf.h>
 #include <linux/tcp.h>
 #include <linux/slab.h>
 #include <linux/skbuff.h>
+#include <net/xdp_sock_drv.h>
 
 /* Returns true if tx_bufs are available. */
 static bool gve_has_free_tx_qpl_bufs(struct gve_tx_ring *tx, int count)
@@ -110,6 +112,14 @@ static bool gve_has_pending_packet(struct gve_tx_ring *tx)
 	return false;
 }
 
+void gve_xdp_tx_flush_dqo(struct gve_priv *priv, u32 xdp_qid)
+{
+	u32 tx_qid = gve_xdp_tx_queue_id(priv, xdp_qid);
+	struct gve_tx_ring *tx = &priv->tx[tx_qid];
+
+	gve_tx_put_doorbell_dqo(priv, tx->q_resources, tx->dqo_tx.tail);
+}
+
 static struct gve_tx_pending_packet_dqo *
 gve_alloc_pending_packet(struct gve_tx_ring *tx)
 {
@@ -198,7 +208,8 @@ void gve_tx_stop_ring_dqo(struct gve_priv *priv, int idx)
 
 	gve_remove_napi(priv, ntfy_idx);
 	gve_clean_tx_done_dqo(priv, tx, /*napi=*/NULL);
-	netdev_tx_reset_queue(tx->netdev_txq);
+	if (tx->netdev_txq)
+		netdev_tx_reset_queue(tx->netdev_txq);
 	gve_tx_clean_pending_packets(tx);
 	gve_tx_remove_from_block(priv, idx);
 }
@@ -231,6 +242,9 @@ static void gve_tx_free_ring_dqo(struct gve_priv *priv, struct gve_tx_ring *tx,
 		tx->dqo.tx_ring = NULL;
 	}
 
+	kvfree(tx->dqo.xsk_reorder_queue);
+	tx->dqo.xsk_reorder_queue = NULL;
+
 	kvfree(tx->dqo.pending_packets);
 	tx->dqo.pending_packets = NULL;
 
@@ -276,7 +290,8 @@ void gve_tx_start_ring_dqo(struct gve_priv *priv, int idx)
 
 	gve_tx_add_to_block(priv, idx);
 
-	tx->netdev_txq = netdev_get_tx_queue(priv->dev, idx);
+	if (idx < priv->tx_cfg.num_queues)
+		tx->netdev_txq = netdev_get_tx_queue(priv->dev, idx);
 	gve_add_napi(priv, ntfy_idx, gve_napi_poll_dqo);
 }
 
@@ -295,6 +310,7 @@ static int gve_tx_alloc_ring_dqo(struct gve_priv *priv,
 	memset(tx, 0, sizeof(*tx));
 	tx->q_num = idx;
 	tx->dev = hdev;
+	spin_lock_init(&tx->dqo_tx.xdp_lock);
 	atomic_set_release(&tx->dqo_compl.hw_tx_head, 0);
 
 	/* Queue sizes must be a power of 2 */
@@ -333,6 +349,17 @@ static int gve_tx_alloc_ring_dqo(struct gve_priv *priv,
 
 	tx->dqo.pending_packets[tx->dqo.num_pending_packets - 1].next = -1;
 	atomic_set_release(&tx->dqo_compl.free_pending_packets, -1);
+
+	/* Only alloc xsk pool for XDP queues */
+	if (idx >= cfg->qcfg->num_queues && cfg->num_xdp_rings) {
+		tx->dqo.xsk_reorder_queue =
+			kvcalloc(tx->dqo.complq_mask + 1,
+				 sizeof(tx->dqo.xsk_reorder_queue[0]),
+				 GFP_KERNEL);
+		if (!tx->dqo.xsk_reorder_queue)
+			goto err;
+	}
+
 	tx->dqo_compl.miss_completions.head = -1;
 	tx->dqo_compl.miss_completions.tail = -1;
 	tx->dqo_compl.timed_out_completions.head = -1;
@@ -379,27 +406,23 @@ int gve_tx_alloc_rings_dqo(struct gve_priv *priv,
 			   struct gve_tx_alloc_rings_cfg *cfg)
 {
 	struct gve_tx_ring *tx = cfg->tx;
+	int total_queues;
 	int err = 0;
 	int i, j;
 
-	if (cfg->start_idx + cfg->num_rings > cfg->qcfg->max_queues) {
+	total_queues = cfg->qcfg->num_queues + cfg->num_xdp_rings;
+	if (total_queues > cfg->qcfg->max_queues) {
 		netif_err(priv, drv, priv->dev,
 			  "Cannot alloc more than the max num of Tx rings\n");
 		return -EINVAL;
 	}
 
-	if (cfg->start_idx == 0) {
-		tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring),
-			      GFP_KERNEL);
-		if (!tx)
-			return -ENOMEM;
-	} else if (!tx) {
-		netif_err(priv, drv, priv->dev,
-			  "Cannot alloc tx rings from a nonzero start idx without tx array\n");
-		return -EINVAL;
-	}
+	tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring),
+		      GFP_KERNEL);
+	if (!tx)
+		return -ENOMEM;
 
-	for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++) {
+	for (i = 0; i < total_queues; i++) {
 		err = gve_tx_alloc_ring_dqo(priv, cfg, &tx[i], i);
 		if (err) {
 			netif_err(priv, drv, priv->dev,
@@ -415,8 +438,7 @@ int gve_tx_alloc_rings_dqo(struct gve_priv *priv,
 err:
 	for (j = 0; j < i; j++)
 		gve_tx_free_ring_dqo(priv, &tx[j], cfg);
-	if (cfg->start_idx == 0)
-		kvfree(tx);
+	kvfree(tx);
 	return err;
 }
 
@@ -429,13 +451,11 @@ void gve_tx_free_rings_dqo(struct gve_priv *priv,
 	if (!tx)
 		return;
 
-	for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++)
+	for (i = 0; i < cfg->qcfg->num_queues + cfg->qcfg->num_xdp_queues; i++)
 		gve_tx_free_ring_dqo(priv, &tx[i], cfg);
 
-	if (cfg->start_idx == 0) {
-		kvfree(tx);
-		cfg->tx = NULL;
-	}
+	kvfree(tx);
+	cfg->tx = NULL;
 }
 
 /* Returns the number of slots available in the ring */
@@ -446,12 +466,28 @@ static u32 num_avail_tx_slots(const struct gve_tx_ring *tx)
 	return tx->mask - num_used;
 }
 
+/* Checks if the requested number of slots are available in the ring */
+static bool gve_has_tx_slots_available(struct gve_tx_ring *tx, u32 slots_req)
+{
+	u32 num_avail = num_avail_tx_slots(tx);
+
+	slots_req += GVE_TX_MIN_DESC_PREVENT_CACHE_OVERLAP;
+
+	if (num_avail >= slots_req)
+		return true;
+
+	/* Update cached TX head pointer */
+	tx->dqo_tx.head = atomic_read_acquire(&tx->dqo_compl.hw_tx_head);
+
+	return num_avail_tx_slots(tx) >= slots_req;
+}
+
 static bool gve_has_avail_slots_tx_dqo(struct gve_tx_ring *tx,
 				       int desc_count, int buf_count)
 {
 	return gve_has_pending_packet(tx) &&
-		   num_avail_tx_slots(tx) >= desc_count &&
-		   gve_has_free_tx_qpl_bufs(tx, buf_count);
+		gve_has_tx_slots_available(tx, desc_count) &&
+		gve_has_free_tx_qpl_bufs(tx, buf_count);
 }
 
 /* Stops the queue if available descriptors is less than 'count'.
@@ -463,12 +499,6 @@ static int gve_maybe_stop_tx_dqo(struct gve_tx_ring *tx,
 	if (likely(gve_has_avail_slots_tx_dqo(tx, desc_count, buf_count)))
 		return 0;
 
-	/* Update cached TX head pointer */
-	tx->dqo_tx.head = atomic_read_acquire(&tx->dqo_compl.hw_tx_head);
-
-	if (likely(gve_has_avail_slots_tx_dqo(tx, desc_count, buf_count)))
-		return 0;
-
 	/* No space, so stop the queue */
 	tx->stop_queue++;
 	netif_tx_stop_queue(tx->netdev_txq);
@@ -479,8 +509,6 @@ static int gve_maybe_stop_tx_dqo(struct gve_tx_ring *tx,
 	/* After stopping queue, check if we can transmit again in order to
 	 * avoid TOCTOU bug.
 	 */
-	tx->dqo_tx.head = atomic_read_acquire(&tx->dqo_compl.hw_tx_head);
-
 	if (likely(!gve_has_avail_slots_tx_dqo(tx, desc_count, buf_count)))
 		return -EBUSY;
 
@@ -507,11 +535,9 @@ static void gve_extract_tx_metadata_dqo(const struct sk_buff *skb,
 }
 
 static void gve_tx_fill_pkt_desc_dqo(struct gve_tx_ring *tx, u32 *desc_idx,
-				     struct sk_buff *skb, u32 len, u64 addr,
+				     bool enable_csum, u32 len, u64 addr,
 				     s16 compl_tag, bool eop, bool is_gso)
 {
-	const bool checksum_offload_en = skb->ip_summed == CHECKSUM_PARTIAL;
-
 	while (len > 0) {
 		struct gve_tx_pkt_desc_dqo *desc =
 			&tx->dqo.tx_ring[*desc_idx].pkt;
@@ -522,7 +548,7 @@ static void gve_tx_fill_pkt_desc_dqo(struct gve_tx_ring *tx, u32 *desc_idx,
 			.buf_addr = cpu_to_le64(addr),
 			.dtype = GVE_TX_PKT_DESC_DTYPE_DQO,
 			.end_of_packet = cur_eop,
-			.checksum_offload_enable = checksum_offload_en,
+			.checksum_offload_enable = enable_csum,
 			.compl_tag = cpu_to_le16(compl_tag),
 			.buf_size = cur_len,
 		};
@@ -619,6 +645,25 @@ gve_tx_fill_general_ctx_desc(struct gve_tx_general_context_desc_dqo *desc,
 	};
 }
 
+static void gve_tx_update_tail(struct gve_tx_ring *tx, u32 desc_idx)
+{
+	u32 last_desc_idx = (desc_idx - 1) & tx->mask;
+	u32 last_report_event_interval =
+			(last_desc_idx - tx->dqo_tx.last_re_idx) & tx->mask;
+
+	/* Commit the changes to our state */
+	tx->dqo_tx.tail = desc_idx;
+
+	/* Request a descriptor completion on the last descriptor of the
+	 * packet if we are allowed to by the HW enforced interval.
+	 */
+
+	if (unlikely(last_report_event_interval >= GVE_TX_MIN_RE_INTERVAL)) {
+		tx->dqo.tx_ring[last_desc_idx].pkt.report_event = true;
+		tx->dqo_tx.last_re_idx = last_desc_idx;
+	}
+}
+
 static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx,
 				      struct sk_buff *skb,
 				      struct gve_tx_pending_packet_dqo *pkt,
@@ -626,6 +671,7 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx,
 				      u32 *desc_idx,
 				      bool is_gso)
 {
+	bool enable_csum = skb->ip_summed == CHECKSUM_PARTIAL;
 	const struct skb_shared_info *shinfo = skb_shinfo(skb);
 	int i;
 
@@ -651,7 +697,7 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx,
 		dma_unmap_addr_set(pkt, dma[pkt->num_bufs], addr);
 		++pkt->num_bufs;
 
-		gve_tx_fill_pkt_desc_dqo(tx, desc_idx, skb, len, addr,
+		gve_tx_fill_pkt_desc_dqo(tx, desc_idx, enable_csum, len, addr,
 					 completion_tag,
 					 /*eop=*/shinfo->nr_frags == 0, is_gso);
 	}
@@ -667,10 +713,11 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx,
 			goto err;
 
 		dma_unmap_len_set(pkt, len[pkt->num_bufs], len);
-		dma_unmap_addr_set(pkt, dma[pkt->num_bufs], addr);
+		netmem_dma_unmap_addr_set(skb_frag_netmem(frag), pkt,
+					  dma[pkt->num_bufs], addr);
 		++pkt->num_bufs;
 
-		gve_tx_fill_pkt_desc_dqo(tx, desc_idx, skb, len, addr,
+		gve_tx_fill_pkt_desc_dqo(tx, desc_idx, enable_csum, len, addr,
 					 completion_tag, is_eop, is_gso);
 	}
 
@@ -715,6 +762,7 @@ static int gve_tx_add_skb_copy_dqo(struct gve_tx_ring *tx,
 				   u32 *desc_idx,
 				   bool is_gso)
 {
+	bool enable_csum = skb->ip_summed == CHECKSUM_PARTIAL;
 	u32 copy_offset = 0;
 	dma_addr_t dma_addr;
 	u32 copy_len;
@@ -736,7 +784,7 @@ static int gve_tx_add_skb_copy_dqo(struct gve_tx_ring *tx,
 		copy_offset += copy_len;
 		dma_sync_single_for_device(tx->dev, dma_addr,
 					   copy_len, DMA_TO_DEVICE);
-		gve_tx_fill_pkt_desc_dqo(tx, desc_idx, skb,
+		gve_tx_fill_pkt_desc_dqo(tx, desc_idx, enable_csum,
 					 copy_len,
 					 dma_addr,
 					 completion_tag,
@@ -770,7 +818,11 @@ static int gve_tx_add_skb_dqo(struct gve_tx_ring *tx,
 	s16 completion_tag;
 
 	pkt = gve_alloc_pending_packet(tx);
+	if (!pkt)
+		return -ENOMEM;
+
 	pkt->skb = skb;
+	pkt->type = GVE_TX_PENDING_PACKET_DQO_SKB;
 	completion_tag = pkt - tx->dqo.pending_packets;
 
 	gve_extract_tx_metadata_dqo(skb, &metadata);
@@ -803,24 +855,7 @@ static int gve_tx_add_skb_dqo(struct gve_tx_ring *tx,
 
 	tx->dqo_tx.posted_packet_desc_cnt += pkt->num_bufs;
 
-	/* Commit the changes to our state */
-	tx->dqo_tx.tail = desc_idx;
-
-	/* Request a descriptor completion on the last descriptor of the
-	 * packet if we are allowed to by the HW enforced interval.
-	 */
-	{
-		u32 last_desc_idx = (desc_idx - 1) & tx->mask;
-		u32 last_report_event_interval =
-			(last_desc_idx - tx->dqo_tx.last_re_idx) & tx->mask;
-
-		if (unlikely(last_report_event_interval >=
-			     GVE_TX_MIN_RE_INTERVAL)) {
-			tx->dqo.tx_ring[last_desc_idx].pkt.report_event = true;
-			tx->dqo_tx.last_re_idx = last_desc_idx;
-		}
-	}
-
+	gve_tx_update_tail(tx, desc_idx);
 	return 0;
 
 err:
@@ -954,9 +989,8 @@ static int gve_try_tx_skb(struct gve_priv *priv, struct gve_tx_ring *tx,
 
 	/* Metadata + (optional TSO) + data descriptors. */
 	total_num_descs = 1 + skb_is_gso(skb) + num_buffer_descs;
-	if (unlikely(gve_maybe_stop_tx_dqo(tx, total_num_descs +
-			GVE_TX_MIN_DESC_PREVENT_CACHE_OVERLAP,
-			num_buffer_descs))) {
+	if (unlikely(gve_maybe_stop_tx_dqo(tx, total_num_descs,
+					   num_buffer_descs))) {
 		return -1;
 	}
 
@@ -968,11 +1002,45 @@ static int gve_try_tx_skb(struct gve_priv *priv, struct gve_tx_ring *tx,
 	return 0;
 
 drop:
+	u64_stats_update_begin(&tx->statss);
 	tx->dropped_pkt++;
+	u64_stats_update_end(&tx->statss);
 	dev_kfree_skb_any(skb);
 	return 0;
 }
 
+static void gve_xsk_reorder_queue_push_dqo(struct gve_tx_ring *tx,
+					   u16 completion_tag)
+{
+	u32 tail = atomic_read(&tx->dqo_tx.xsk_reorder_queue_tail);
+
+	tx->dqo.xsk_reorder_queue[tail] = completion_tag;
+	tail = (tail + 1) & tx->dqo.complq_mask;
+	atomic_set_release(&tx->dqo_tx.xsk_reorder_queue_tail, tail);
+}
+
+static struct gve_tx_pending_packet_dqo *
+gve_xsk_reorder_queue_head(struct gve_tx_ring *tx)
+{
+	u32 head = tx->dqo_compl.xsk_reorder_queue_head;
+
+	if (head == tx->dqo_compl.xsk_reorder_queue_tail) {
+		tx->dqo_compl.xsk_reorder_queue_tail =
+			atomic_read_acquire(&tx->dqo_tx.xsk_reorder_queue_tail);
+
+		if (head == tx->dqo_compl.xsk_reorder_queue_tail)
+			return NULL;
+	}
+
+	return &tx->dqo.pending_packets[tx->dqo.xsk_reorder_queue[head]];
+}
+
+static void gve_xsk_reorder_queue_pop_dqo(struct gve_tx_ring *tx)
+{
+	tx->dqo_compl.xsk_reorder_queue_head++;
+	tx->dqo_compl.xsk_reorder_queue_head &= tx->dqo.complq_mask;
+}
+
 /* Transmit a given skb and ring the doorbell. */
 netdev_tx_t gve_tx_dqo(struct sk_buff *skb, struct net_device *dev)
 {
@@ -996,6 +1064,62 @@ netdev_tx_t gve_tx_dqo(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
+static bool gve_xsk_tx_dqo(struct gve_priv *priv, struct gve_tx_ring *tx,
+			   int budget)
+{
+	struct xsk_buff_pool *pool = tx->xsk_pool;
+	struct xdp_desc desc;
+	bool repoll = false;
+	int sent = 0;
+
+	spin_lock(&tx->dqo_tx.xdp_lock);
+	for (; sent < budget; sent++) {
+		struct gve_tx_pending_packet_dqo *pkt;
+		s16 completion_tag;
+		dma_addr_t addr;
+		u32 desc_idx;
+
+		if (unlikely(!gve_has_avail_slots_tx_dqo(tx, 1, 1))) {
+			repoll = true;
+			break;
+		}
+
+		if (!xsk_tx_peek_desc(pool, &desc))
+			break;
+
+		pkt = gve_alloc_pending_packet(tx);
+		pkt->type = GVE_TX_PENDING_PACKET_DQO_XSK;
+		pkt->num_bufs = 0;
+		completion_tag = pkt - tx->dqo.pending_packets;
+
+		addr = xsk_buff_raw_get_dma(pool, desc.addr);
+		xsk_buff_raw_dma_sync_for_device(pool, addr, desc.len);
+
+		desc_idx = tx->dqo_tx.tail;
+		gve_tx_fill_pkt_desc_dqo(tx, &desc_idx,
+					 true, desc.len,
+					 addr, completion_tag, true,
+					 false);
+		++pkt->num_bufs;
+		gve_tx_update_tail(tx, desc_idx);
+		tx->dqo_tx.posted_packet_desc_cnt += pkt->num_bufs;
+		gve_xsk_reorder_queue_push_dqo(tx, completion_tag);
+	}
+
+	if (sent) {
+		gve_tx_put_doorbell_dqo(priv, tx->q_resources, tx->dqo_tx.tail);
+		xsk_tx_release(pool);
+	}
+
+	spin_unlock(&tx->dqo_tx.xdp_lock);
+
+	u64_stats_update_begin(&tx->statss);
+	tx->xdp_xsk_sent += sent;
+	u64_stats_update_end(&tx->statss);
+
+	return (sent == budget) || repoll;
+}
+
 static void add_to_list(struct gve_tx_ring *tx, struct gve_index_list *list,
 			struct gve_tx_pending_packet_dqo *pending_packet)
 {
@@ -1045,8 +1169,9 @@ static void gve_unmap_packet(struct device *dev,
 	dma_unmap_single(dev, dma_unmap_addr(pkt, dma[0]),
 			 dma_unmap_len(pkt, len[0]), DMA_TO_DEVICE);
 	for (i = 1; i < pkt->num_bufs; i++) {
-		dma_unmap_page(dev, dma_unmap_addr(pkt, dma[i]),
-			       dma_unmap_len(pkt, len[i]), DMA_TO_DEVICE);
+		netmem_dma_unmap_page_attrs(dev, dma_unmap_addr(pkt, dma[i]),
+					    dma_unmap_len(pkt, len[i]),
+					    DMA_TO_DEVICE, 0);
 	}
 	pkt->num_bufs = 0;
 }
@@ -1109,16 +1234,35 @@ static void gve_handle_packet_completion(struct gve_priv *priv,
 		}
 	}
 	tx->dqo_tx.completed_packet_desc_cnt += pending_packet->num_bufs;
-	if (tx->dqo.qpl)
-		gve_free_tx_qpl_bufs(tx, pending_packet);
-	else
+
+	switch (pending_packet->type) {
+	case GVE_TX_PENDING_PACKET_DQO_SKB:
+		if (tx->dqo.qpl)
+			gve_free_tx_qpl_bufs(tx, pending_packet);
+		else
+			gve_unmap_packet(tx->dev, pending_packet);
+		(*pkts)++;
+		*bytes += pending_packet->skb->len;
+
+		napi_consume_skb(pending_packet->skb, is_napi);
+		pending_packet->skb = NULL;
+		gve_free_pending_packet(tx, pending_packet);
+		break;
+	case GVE_TX_PENDING_PACKET_DQO_XDP_FRAME:
 		gve_unmap_packet(tx->dev, pending_packet);
+		(*pkts)++;
+		*bytes += pending_packet->xdpf->len;
 
-	*bytes += pending_packet->skb->len;
-	(*pkts)++;
-	napi_consume_skb(pending_packet->skb, is_napi);
-	pending_packet->skb = NULL;
-	gve_free_pending_packet(tx, pending_packet);
+		xdp_return_frame(pending_packet->xdpf);
+		pending_packet->xdpf = NULL;
+		gve_free_pending_packet(tx, pending_packet);
+		break;
+	case GVE_TX_PENDING_PACKET_DQO_XSK:
+		pending_packet->state = GVE_PACKET_STATE_XSK_COMPLETE;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+	}
 }
 
 static void gve_handle_miss_completion(struct gve_priv *priv,
@@ -1182,7 +1326,11 @@ static void remove_miss_completions(struct gve_priv *priv,
 		/* This indicates the packet was dropped. */
 		dev_kfree_skb_any(pending_packet->skb);
 		pending_packet->skb = NULL;
+
+		u64_stats_update_begin(&tx->statss);
 		tx->dropped_pkt++;
+		u64_stats_update_end(&tx->statss);
+
 		net_err_ratelimited("%s: No reinjection completion was received for: %d.\n",
 				    priv->dev->name,
 				    (int)(pending_packet - tx->dqo.pending_packets));
@@ -1215,8 +1363,34 @@ static void remove_timed_out_completions(struct gve_priv *priv,
 
 		remove_from_list(tx, &tx->dqo_compl.timed_out_completions,
 				 pending_packet);
+
+		/* Need to count XSK packets in xsk_tx_completed. */
+		if (pending_packet->type == GVE_TX_PENDING_PACKET_DQO_XSK)
+			pending_packet->state = GVE_PACKET_STATE_XSK_COMPLETE;
+		else
+			gve_free_pending_packet(tx, pending_packet);
+	}
+}
+
+static void gve_tx_process_xsk_completions(struct gve_tx_ring *tx)
+{
+	u32 num_xsks = 0;
+
+	while (true) {
+		struct gve_tx_pending_packet_dqo *pending_packet =
+			gve_xsk_reorder_queue_head(tx);
+
+		if (!pending_packet ||
+		    pending_packet->state != GVE_PACKET_STATE_XSK_COMPLETE)
+			break;
+
+		num_xsks++;
+		gve_xsk_reorder_queue_pop_dqo(tx);
 		gve_free_pending_packet(tx, pending_packet);
 	}
+
+	if (num_xsks)
+		xsk_tx_completed(tx->xsk_pool, num_xsks);
 }
 
 int gve_clean_tx_done_dqo(struct gve_priv *priv, struct gve_tx_ring *tx,
@@ -1289,13 +1463,17 @@ int gve_clean_tx_done_dqo(struct gve_priv *priv, struct gve_tx_ring *tx,
 		num_descs_cleaned++;
 	}
 
-	netdev_tx_completed_queue(tx->netdev_txq,
-				  pkt_compl_pkts + miss_compl_pkts,
-				  pkt_compl_bytes + miss_compl_bytes);
+	if (tx->netdev_txq)
+		netdev_tx_completed_queue(tx->netdev_txq,
+					  pkt_compl_pkts + miss_compl_pkts,
+					  pkt_compl_bytes + miss_compl_bytes);
 
 	remove_miss_completions(priv, tx);
 	remove_timed_out_completions(priv, tx);
 
+	if (tx->xsk_pool)
+		gve_tx_process_xsk_completions(tx);
+
 	u64_stats_update_begin(&tx->statss);
 	tx->bytes_done += pkt_compl_bytes + reinject_compl_bytes;
 	tx->pkt_done += pkt_compl_pkts + reinject_compl_pkts;
@@ -1327,3 +1505,111 @@ bool gve_tx_poll_dqo(struct gve_notify_block *block, bool do_clean)
 	compl_desc = &tx->dqo.compl_ring[tx->dqo_compl.head];
 	return compl_desc->generation != tx->dqo_compl.cur_gen_bit;
 }
+
+bool gve_xsk_tx_poll_dqo(struct gve_notify_block *rx_block, int budget)
+{
+	struct gve_rx_ring *rx = rx_block->rx;
+	struct gve_priv *priv = rx->gve;
+	struct gve_tx_ring *tx;
+
+	tx = &priv->tx[gve_xdp_tx_queue_id(priv, rx->q_num)];
+	if (tx->xsk_pool)
+		return gve_xsk_tx_dqo(priv, tx, budget);
+
+	return 0;
+}
+
+bool gve_xdp_poll_dqo(struct gve_notify_block *block)
+{
+	struct gve_tx_compl_desc *compl_desc;
+	struct gve_tx_ring *tx = block->tx;
+	struct gve_priv *priv = block->priv;
+
+	gve_clean_tx_done_dqo(priv, tx, &block->napi);
+
+	/* Return true if we still have work. */
+	compl_desc = &tx->dqo.compl_ring[tx->dqo_compl.head];
+	return compl_desc->generation != tx->dqo_compl.cur_gen_bit;
+}
+
+int gve_xdp_xmit_one_dqo(struct gve_priv *priv, struct gve_tx_ring *tx,
+			 struct xdp_frame *xdpf)
+{
+	struct gve_tx_pending_packet_dqo *pkt;
+	u32 desc_idx = tx->dqo_tx.tail;
+	s16 completion_tag;
+	int num_descs = 1;
+	dma_addr_t addr;
+	int err;
+
+	if (unlikely(!gve_has_tx_slots_available(tx, num_descs)))
+		return -EBUSY;
+
+	pkt = gve_alloc_pending_packet(tx);
+	if (unlikely(!pkt))
+		return -EBUSY;
+
+	pkt->type = GVE_TX_PENDING_PACKET_DQO_XDP_FRAME;
+	pkt->num_bufs = 0;
+	pkt->xdpf = xdpf;
+	completion_tag = pkt - tx->dqo.pending_packets;
+
+	/* Generate Packet Descriptor */
+	addr = dma_map_single(tx->dev, xdpf->data, xdpf->len, DMA_TO_DEVICE);
+	err = dma_mapping_error(tx->dev, addr);
+	if (unlikely(err))
+		goto err;
+
+	dma_unmap_len_set(pkt, len[pkt->num_bufs], xdpf->len);
+	dma_unmap_addr_set(pkt, dma[pkt->num_bufs], addr);
+	pkt->num_bufs++;
+
+	gve_tx_fill_pkt_desc_dqo(tx, &desc_idx,
+				 false, xdpf->len,
+				 addr, completion_tag, true,
+				 false);
+
+	gve_tx_update_tail(tx, desc_idx);
+	return 0;
+
+err:
+	pkt->xdpf = NULL;
+	pkt->num_bufs = 0;
+	gve_free_pending_packet(tx, pkt);
+	return err;
+}
+
+int gve_xdp_xmit_dqo(struct net_device *dev, int n, struct xdp_frame **frames,
+		     u32 flags)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+	struct gve_tx_ring *tx;
+	int i, err = 0, qid;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	qid = gve_xdp_tx_queue_id(priv,
+				  smp_processor_id() % priv->tx_cfg.num_xdp_queues);
+
+	tx = &priv->tx[qid];
+
+	spin_lock(&tx->dqo_tx.xdp_lock);
+	for (i = 0; i < n; i++) {
+		err = gve_xdp_xmit_one_dqo(priv, tx, frames[i]);
+		if (err)
+			break;
+	}
+
+	if (flags & XDP_XMIT_FLUSH)
+		gve_tx_put_doorbell_dqo(priv, tx->q_resources, tx->dqo_tx.tail);
+
+	spin_unlock(&tx->dqo_tx.xdp_lock);
+
+	u64_stats_update_begin(&tx->statss);
+	tx->xdp_xmit += n;
+	tx->xdp_xmit_errors += n - i;
+	u64_stats_update_end(&tx->statss);
+
+	return i ? i : err;
+}
diff --git a/drivers/net/ethernet/google/gve/gve_utils.c b/drivers/net/ethernet/google/gve/gve_utils.c
index 30fef100257e..ace9b8698021 100644
--- a/drivers/net/ethernet/google/gve/gve_utils.c
+++ b/drivers/net/ethernet/google/gve/gve_utils.c
@@ -110,13 +110,13 @@ void gve_add_napi(struct gve_priv *priv, int ntfy_idx,
 {
 	struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
 
-	netif_napi_add(priv->dev, &block->napi, gve_poll);
-	netif_napi_set_irq(&block->napi, block->irq);
+	netif_napi_add_locked(priv->dev, &block->napi, gve_poll);
+	netif_napi_set_irq_locked(&block->napi, block->irq);
 }
 
 void gve_remove_napi(struct gve_priv *priv, int ntfy_idx)
 {
 	struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
 
-	netif_napi_del(&block->napi);
+	netif_napi_del_locked(&block->napi);
 }
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index 65302c41bfb1..18eca7d12c20 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -148,8 +148,10 @@ config HIBMCGE
 	tristate "Hisilicon BMC Gigabit Ethernet Device Support"
 	depends on PCI && PCI_MSI
 	select PHYLIB
+	select FIXED_PHY
 	select MOTORCOMM_PHY
 	select REALTEK_PHY
+	select PAGE_POOL
 	help
 	  If you wish to compile a kernel for a BMC with HIBMC-xx_gmac
 	  then you should answer Y to this. This makes this driver suitable for use
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/Makefile b/drivers/net/ethernet/hisilicon/hibmcge/Makefile
index 7ea15f9ef849..d6610ba16855 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/Makefile
+++ b/drivers/net/ethernet/hisilicon/hibmcge/Makefile
@@ -3,7 +3,8 @@
 # Makefile for the HISILICON BMC GE network device drivers.
 #
 
+ccflags-y += -I$(src)
 obj-$(CONFIG_HIBMCGE) += hibmcge.o
 
 hibmcge-objs = hbg_main.o hbg_hw.o hbg_mdio.o hbg_irq.o hbg_txrx.o hbg_ethtool.o \
-		hbg_debugfs.o hbg_err.o
+		hbg_debugfs.o hbg_err.o hbg_diagnose.o
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
index b4300d8ea4ad..8e134da3e217 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
@@ -7,6 +7,7 @@
 #include <linux/ethtool.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
+#include <net/page_pool/helpers.h>
 #include "hbg_reg.h"
 
 #define HBG_STATUS_DISABLE		0x0
@@ -17,6 +18,7 @@
 #define HBG_PCU_CACHE_LINE_SIZE		32
 #define HBG_TX_TIMEOUT_BUF_LEN		1024
 #define HBG_RX_DESCR			0x01
+#define HBG_NO_PHY			0xFF
 
 #define HBG_PACKET_HEAD_SIZE	((HBG_RX_SKIP1 + HBG_RX_SKIP2 + \
 				  HBG_RX_DESCR) * HBG_PCU_CACHE_LINE_SIZE)
@@ -36,6 +38,8 @@ enum hbg_nic_state {
 	HBG_NIC_STATE_EVENT_HANDLING = 0,
 	HBG_NIC_STATE_RESETTING,
 	HBG_NIC_STATE_RESET_FAIL,
+	HBG_NIC_STATE_NEED_RESET, /* trigger a reset in scheduled task */
+	HBG_NIC_STATE_NP_LINK_FAIL,
 };
 
 enum hbg_reset_type {
@@ -52,6 +56,12 @@ struct hbg_buffer {
 	dma_addr_t skb_dma;
 	u32 skb_len;
 
+	struct page *page;
+	void *page_addr;
+	dma_addr_t page_dma;
+	u32 page_size;
+	u32 page_offset;
+
 	enum hbg_dir dir;
 	struct hbg_ring *ring;
 	struct hbg_priv *priv;
@@ -75,12 +85,14 @@ struct hbg_ring {
 	struct hbg_priv *priv;
 	struct napi_struct napi;
 	char *tout_log_buf; /* tx timeout log buffer */
+	struct page_pool *page_pool; /* only for rx */
 };
 
 enum hbg_hw_event_type {
 	HBG_HW_EVENT_NONE = 0,
 	HBG_HW_EVENT_INIT, /* driver is loading */
 	HBG_HW_EVENT_RESET,
+	HBG_HW_EVENT_CORE_RESET,
 };
 
 struct hbg_dev_specs {
@@ -104,14 +116,17 @@ struct hbg_irq_info {
 	u32 mask;
 	bool re_enable;
 	bool need_print;
-	u64 count;
+	bool need_reset;
 
-	void (*irq_handle)(struct hbg_priv *priv, struct hbg_irq_info *info);
+	void (*irq_handle)(struct hbg_priv *priv,
+			   const struct hbg_irq_info *info);
 };
 
 struct hbg_vector {
 	char name[HBG_VECTOR_NUM][32];
-	struct hbg_irq_info *info_array;
+
+	u64 *stats_array;
+	const struct hbg_irq_info *info_array;
 	u32 info_array_len;
 };
 
@@ -142,6 +157,119 @@ struct hbg_user_def {
 	struct ethtool_pauseparam pause_param;
 };
 
+struct hbg_stats {
+	u64 rx_desc_drop;
+	u64 rx_desc_l2_err_cnt;
+	u64 rx_desc_pkt_len_err_cnt;
+	u64 rx_desc_l3l4_err_cnt;
+	u64 rx_desc_l3_wrong_head_cnt;
+	u64 rx_desc_l3_csum_err_cnt;
+	u64 rx_desc_l3_len_err_cnt;
+	u64 rx_desc_l3_zero_ttl_cnt;
+	u64 rx_desc_l3_other_cnt;
+	u64 rx_desc_l4_err_cnt;
+	u64 rx_desc_l4_wrong_head_cnt;
+	u64 rx_desc_l4_len_err_cnt;
+	u64 rx_desc_l4_csum_err_cnt;
+	u64 rx_desc_l4_zero_port_num_cnt;
+	u64 rx_desc_l4_other_cnt;
+	u64 rx_desc_frag_cnt;
+	u64 rx_desc_ip_ver_err_cnt;
+	u64 rx_desc_ipv4_pkt_cnt;
+	u64 rx_desc_ipv6_pkt_cnt;
+	u64 rx_desc_no_ip_pkt_cnt;
+	u64 rx_desc_ip_pkt_cnt;
+	u64 rx_desc_tcp_pkt_cnt;
+	u64 rx_desc_udp_pkt_cnt;
+	u64 rx_desc_vlan_pkt_cnt;
+	u64 rx_desc_icmp_pkt_cnt;
+	u64 rx_desc_arp_pkt_cnt;
+	u64 rx_desc_rarp_pkt_cnt;
+	u64 rx_desc_multicast_pkt_cnt;
+	u64 rx_desc_broadcast_pkt_cnt;
+	u64 rx_desc_ipsec_pkt_cnt;
+	u64 rx_desc_ip_opt_pkt_cnt;
+	u64 rx_desc_key_not_match_cnt;
+
+	u64 rx_octets_total_ok_cnt;
+	u64 rx_uc_pkt_cnt;
+	u64 rx_mc_pkt_cnt;
+	u64 rx_bc_pkt_cnt;
+	u64 rx_vlan_pkt_cnt;
+	u64 rx_octets_bad_cnt;
+	u64 rx_octets_total_filt_cnt;
+	u64 rx_filt_pkt_cnt;
+	u64 rx_trans_pkt_cnt;
+	u64 rx_framesize_64;
+	u64 rx_framesize_65_127;
+	u64 rx_framesize_128_255;
+	u64 rx_framesize_256_511;
+	u64 rx_framesize_512_1023;
+	u64 rx_framesize_1024_1518;
+	u64 rx_framesize_bt_1518;
+	u64 rx_fcs_error_cnt;
+	u64 rx_data_error_cnt;
+	u64 rx_align_error_cnt;
+	u64 rx_pause_macctl_frame_cnt;
+	u64 rx_unknown_macctl_frame_cnt;
+	/* crc ok, > max_frm_size, < 2max_frm_size */
+	u64 rx_frame_long_err_cnt;
+	/* crc fail, > max_frm_size, < 2max_frm_size */
+	u64 rx_jabber_err_cnt;
+	/* > 2max_frm_size */
+	u64 rx_frame_very_long_err_cnt;
+	/* < 64byte, >= short_runts_thr */
+	u64 rx_frame_runt_err_cnt;
+	/* < short_runts_thr */
+	u64 rx_frame_short_err_cnt;
+	/* PCU: dropped when the RX FIFO is full.*/
+	u64 rx_overflow_cnt;
+	/* GMAC: the count of overflows of the RX FIFO */
+	u64 rx_overrun_cnt;
+	/* PCU: the count of buffer alloc errors in RX */
+	u64 rx_bufrq_err_cnt;
+	/* PCU: the count of write descriptor errors in RX */
+	u64 rx_we_err_cnt;
+	/* GMAC: the count of pkts that contain PAD but length is not 64 */
+	u64 rx_lengthfield_err_cnt;
+	u64 rx_fail_comma_cnt;
+
+	u64 rx_dma_err_cnt;
+	u64 rx_fifo_less_empty_thrsld_cnt;
+
+	u64 tx_octets_total_ok_cnt;
+	u64 tx_uc_pkt_cnt;
+	u64 tx_mc_pkt_cnt;
+	u64 tx_bc_pkt_cnt;
+	u64 tx_vlan_pkt_cnt;
+	u64 tx_octets_bad_cnt;
+	u64 tx_trans_pkt_cnt;
+	u64 tx_pause_frame_cnt;
+	u64 tx_framesize_64;
+	u64 tx_framesize_65_127;
+	u64 tx_framesize_128_255;
+	u64 tx_framesize_256_511;
+	u64 tx_framesize_512_1023;
+	u64 tx_framesize_1024_1518;
+	u64 tx_framesize_bt_1518;
+	/* GMAC: the count of times that frames fail to be transmitted
+	 *       due to internal errors.
+	 */
+	u64 tx_underrun_err_cnt;
+	u64 tx_add_cs_fail_cnt;
+	/* PCU: the count of buffer free errors in TX */
+	u64 tx_bufrl_err_cnt;
+	u64 tx_crc_err_cnt;
+	u64 tx_drop_cnt;
+	u64 tx_excessive_length_drop_cnt;
+
+	u64 tx_timeout_cnt;
+	u64 tx_dma_err_cnt;
+
+	u64 np_link_fail_cnt;
+	u64 reset_fail_cnt;
+};
+
 struct hbg_priv {
 	struct net_device *netdev;
 	struct pci_dev *pdev;
@@ -155,6 +283,12 @@ struct hbg_priv {
 	struct hbg_mac_filter filter;
 	enum hbg_reset_type reset_type;
 	struct hbg_user_def user_def;
+	struct hbg_stats stats;
+	unsigned long last_update_stats_time;
+	struct delayed_work service_task;
 };
 
+void hbg_err_reset_task_schedule(struct hbg_priv *priv);
+void hbg_np_link_fail_task_schedule(struct hbg_priv *priv);
+
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
index 8473c43d171a..01ad82d2f5cc 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
@@ -61,18 +61,19 @@ static int hbg_dbg_irq_info(struct seq_file *s, void *unused)
 {
 	struct net_device *netdev = dev_get_drvdata(s->private);
 	struct hbg_priv *priv = netdev_priv(netdev);
-	struct hbg_irq_info *info;
+	const struct hbg_irq_info *info;
 	u32 i;
 
 	for (i = 0; i < priv->vectors.info_array_len; i++) {
 		info = &priv->vectors.info_array[i];
 		seq_printf(s,
-			   "%-20s: enabled: %-5s, logged: %-5s, count: %llu\n",
+			   "%-20s: enabled: %-5s, reset: %-5s, logged: %-5s, count: %llu\n",
 			   info->name,
 			   str_true_false(hbg_hw_irq_is_enabled(priv,
 								info->mask)),
+			   str_true_false(info->need_reset),
 			   str_true_false(info->need_print),
-			   info->count);
+			   priv->vectors.stats_array[i]);
 	}
 
 	return 0;
@@ -105,6 +106,7 @@ static int hbg_dbg_nic_state(struct seq_file *s, void *unused)
 {
 	struct net_device *netdev = dev_get_drvdata(s->private);
 	struct hbg_priv *priv = netdev_priv(netdev);
+	bool np_link_fail;
 
 	seq_printf(s, "event handling state: %s\n",
 		   state_str_true_false(priv, HBG_NIC_STATE_EVENT_HANDLING));
@@ -114,6 +116,12 @@ static int hbg_dbg_nic_state(struct seq_file *s, void *unused)
 		   state_str_true_false(priv, HBG_NIC_STATE_RESET_FAIL));
 	seq_printf(s, "last reset type: %s\n",
 		   reset_type_str[priv->reset_type]);
+	seq_printf(s, "need reset state: %s\n",
+		   state_str_true_false(priv, HBG_NIC_STATE_NEED_RESET));
+
+	np_link_fail = !hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR,
+					   HBG_REG_AN_NEG_STATE_NP_LINK_OK_B);
+	seq_printf(s, "np_link fail state: %s\n", str_true_false(np_link_fail));
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c
new file mode 100644
index 000000000000..c0ce74cf7382
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c
@@ -0,0 +1,349 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2025 Hisilicon Limited.
+
+#include <linux/iopoll.h>
+#include <linux/phy.h>
+#include "hbg_common.h"
+#include "hbg_ethtool.h"
+#include "hbg_hw.h"
+#include "hbg_diagnose.h"
+
+#define HBG_MSG_DATA_MAX_NUM	64
+
+struct hbg_diagnose_message {
+	u32 opcode;
+	u32 status;
+	u32 data_num;
+	struct hbg_priv *priv;
+
+	u32 data[HBG_MSG_DATA_MAX_NUM];
+};
+
+#define HBG_HW_PUSH_WAIT_TIMEOUT_US	(2 * 1000 * 1000)
+#define HBG_HW_PUSH_WAIT_INTERVAL_US	(1 * 1000)
+
+enum hbg_push_cmd {
+	HBG_PUSH_CMD_IRQ = 0,
+	HBG_PUSH_CMD_STATS,
+	HBG_PUSH_CMD_LINK,
+};
+
+struct hbg_push_stats_info {
+	/* id is used to match the name of the current stats item.
+	 * and is used for pretty print on BMC
+	 */
+	u32 id;
+	u64 offset;
+};
+
+struct hbg_push_irq_info {
+	/* id is used to match the name of the current irq.
+	 * and is used for pretty print on BMC
+	 */
+	u32 id;
+	u32 mask;
+};
+
+#define HBG_PUSH_IRQ_I(name, id) {id, HBG_INT_MSK_##name##_B}
+static const struct hbg_push_irq_info hbg_push_irq_list[] = {
+	HBG_PUSH_IRQ_I(RX, 0),
+	HBG_PUSH_IRQ_I(TX, 1),
+	HBG_PUSH_IRQ_I(TX_PKT_CPL, 2),
+	HBG_PUSH_IRQ_I(MAC_MII_FIFO_ERR, 3),
+	HBG_PUSH_IRQ_I(MAC_PCS_RX_FIFO_ERR, 4),
+	HBG_PUSH_IRQ_I(MAC_PCS_TX_FIFO_ERR, 5),
+	HBG_PUSH_IRQ_I(MAC_APP_RX_FIFO_ERR, 6),
+	HBG_PUSH_IRQ_I(MAC_APP_TX_FIFO_ERR, 7),
+	HBG_PUSH_IRQ_I(SRAM_PARITY_ERR, 8),
+	HBG_PUSH_IRQ_I(TX_AHB_ERR, 9),
+	HBG_PUSH_IRQ_I(RX_BUF_AVL, 10),
+	HBG_PUSH_IRQ_I(REL_BUF_ERR, 11),
+	HBG_PUSH_IRQ_I(TXCFG_AVL, 12),
+	HBG_PUSH_IRQ_I(TX_DROP, 13),
+	HBG_PUSH_IRQ_I(RX_DROP, 14),
+	HBG_PUSH_IRQ_I(RX_AHB_ERR, 15),
+	HBG_PUSH_IRQ_I(MAC_FIFO_ERR, 16),
+	HBG_PUSH_IRQ_I(RBREQ_ERR, 17),
+	HBG_PUSH_IRQ_I(WE_ERR, 18),
+};
+
+#define HBG_PUSH_STATS_I(name, id) {id, HBG_STATS_FIELD_OFF(name)}
+static const struct hbg_push_stats_info hbg_push_stats_list[] = {
+	HBG_PUSH_STATS_I(rx_desc_drop, 0),
+	HBG_PUSH_STATS_I(rx_desc_l2_err_cnt, 1),
+	HBG_PUSH_STATS_I(rx_desc_pkt_len_err_cnt, 2),
+	HBG_PUSH_STATS_I(rx_desc_l3_wrong_head_cnt, 3),
+	HBG_PUSH_STATS_I(rx_desc_l3_csum_err_cnt, 4),
+	HBG_PUSH_STATS_I(rx_desc_l3_len_err_cnt, 5),
+	HBG_PUSH_STATS_I(rx_desc_l3_zero_ttl_cnt, 6),
+	HBG_PUSH_STATS_I(rx_desc_l3_other_cnt, 7),
+	HBG_PUSH_STATS_I(rx_desc_l4_err_cnt, 8),
+	HBG_PUSH_STATS_I(rx_desc_l4_wrong_head_cnt, 9),
+	HBG_PUSH_STATS_I(rx_desc_l4_len_err_cnt, 10),
+	HBG_PUSH_STATS_I(rx_desc_l4_csum_err_cnt, 11),
+	HBG_PUSH_STATS_I(rx_desc_l4_zero_port_num_cnt, 12),
+	HBG_PUSH_STATS_I(rx_desc_l4_other_cnt, 13),
+	HBG_PUSH_STATS_I(rx_desc_frag_cnt, 14),
+	HBG_PUSH_STATS_I(rx_desc_ip_ver_err_cnt, 15),
+	HBG_PUSH_STATS_I(rx_desc_ipv4_pkt_cnt, 16),
+	HBG_PUSH_STATS_I(rx_desc_ipv6_pkt_cnt, 17),
+	HBG_PUSH_STATS_I(rx_desc_no_ip_pkt_cnt, 18),
+	HBG_PUSH_STATS_I(rx_desc_ip_pkt_cnt, 19),
+	HBG_PUSH_STATS_I(rx_desc_tcp_pkt_cnt, 20),
+	HBG_PUSH_STATS_I(rx_desc_udp_pkt_cnt, 21),
+	HBG_PUSH_STATS_I(rx_desc_vlan_pkt_cnt, 22),
+	HBG_PUSH_STATS_I(rx_desc_icmp_pkt_cnt, 23),
+	HBG_PUSH_STATS_I(rx_desc_arp_pkt_cnt, 24),
+	HBG_PUSH_STATS_I(rx_desc_rarp_pkt_cnt, 25),
+	HBG_PUSH_STATS_I(rx_desc_multicast_pkt_cnt, 26),
+	HBG_PUSH_STATS_I(rx_desc_broadcast_pkt_cnt, 27),
+	HBG_PUSH_STATS_I(rx_desc_ipsec_pkt_cnt, 28),
+	HBG_PUSH_STATS_I(rx_desc_ip_opt_pkt_cnt, 29),
+	HBG_PUSH_STATS_I(rx_desc_key_not_match_cnt, 30),
+	HBG_PUSH_STATS_I(rx_octets_total_ok_cnt, 31),
+	HBG_PUSH_STATS_I(rx_uc_pkt_cnt, 32),
+	HBG_PUSH_STATS_I(rx_mc_pkt_cnt, 33),
+	HBG_PUSH_STATS_I(rx_bc_pkt_cnt, 34),
+	HBG_PUSH_STATS_I(rx_vlan_pkt_cnt, 35),
+	HBG_PUSH_STATS_I(rx_octets_bad_cnt, 36),
+	HBG_PUSH_STATS_I(rx_octets_total_filt_cnt, 37),
+	HBG_PUSH_STATS_I(rx_filt_pkt_cnt, 38),
+	HBG_PUSH_STATS_I(rx_trans_pkt_cnt, 39),
+	HBG_PUSH_STATS_I(rx_framesize_64, 40),
+	HBG_PUSH_STATS_I(rx_framesize_65_127, 41),
+	HBG_PUSH_STATS_I(rx_framesize_128_255, 42),
+	HBG_PUSH_STATS_I(rx_framesize_256_511, 43),
+	HBG_PUSH_STATS_I(rx_framesize_512_1023, 44),
+	HBG_PUSH_STATS_I(rx_framesize_1024_1518, 45),
+	HBG_PUSH_STATS_I(rx_framesize_bt_1518, 46),
+	HBG_PUSH_STATS_I(rx_fcs_error_cnt, 47),
+	HBG_PUSH_STATS_I(rx_data_error_cnt, 48),
+	HBG_PUSH_STATS_I(rx_align_error_cnt, 49),
+	HBG_PUSH_STATS_I(rx_frame_long_err_cnt, 50),
+	HBG_PUSH_STATS_I(rx_jabber_err_cnt, 51),
+	HBG_PUSH_STATS_I(rx_pause_macctl_frame_cnt, 52),
+	HBG_PUSH_STATS_I(rx_unknown_macctl_frame_cnt, 53),
+	HBG_PUSH_STATS_I(rx_frame_very_long_err_cnt, 54),
+	HBG_PUSH_STATS_I(rx_frame_runt_err_cnt, 55),
+	HBG_PUSH_STATS_I(rx_frame_short_err_cnt, 56),
+	HBG_PUSH_STATS_I(rx_overflow_cnt, 57),
+	HBG_PUSH_STATS_I(rx_bufrq_err_cnt, 58),
+	HBG_PUSH_STATS_I(rx_we_err_cnt, 59),
+	HBG_PUSH_STATS_I(rx_overrun_cnt, 60),
+	HBG_PUSH_STATS_I(rx_lengthfield_err_cnt, 61),
+	HBG_PUSH_STATS_I(rx_fail_comma_cnt, 62),
+	HBG_PUSH_STATS_I(rx_dma_err_cnt, 63),
+	HBG_PUSH_STATS_I(rx_fifo_less_empty_thrsld_cnt, 64),
+	HBG_PUSH_STATS_I(tx_octets_total_ok_cnt, 65),
+	HBG_PUSH_STATS_I(tx_uc_pkt_cnt, 66),
+	HBG_PUSH_STATS_I(tx_mc_pkt_cnt, 67),
+	HBG_PUSH_STATS_I(tx_bc_pkt_cnt, 68),
+	HBG_PUSH_STATS_I(tx_vlan_pkt_cnt, 69),
+	HBG_PUSH_STATS_I(tx_octets_bad_cnt, 70),
+	HBG_PUSH_STATS_I(tx_trans_pkt_cnt, 71),
+	HBG_PUSH_STATS_I(tx_pause_frame_cnt, 72),
+	HBG_PUSH_STATS_I(tx_framesize_64, 73),
+	HBG_PUSH_STATS_I(tx_framesize_65_127, 74),
+	HBG_PUSH_STATS_I(tx_framesize_128_255, 75),
+	HBG_PUSH_STATS_I(tx_framesize_256_511, 76),
+	HBG_PUSH_STATS_I(tx_framesize_512_1023, 77),
+	HBG_PUSH_STATS_I(tx_framesize_1024_1518, 78),
+	HBG_PUSH_STATS_I(tx_framesize_bt_1518, 79),
+	HBG_PUSH_STATS_I(tx_underrun_err_cnt, 80),
+	HBG_PUSH_STATS_I(tx_add_cs_fail_cnt, 81),
+	HBG_PUSH_STATS_I(tx_bufrl_err_cnt, 82),
+	HBG_PUSH_STATS_I(tx_crc_err_cnt, 83),
+	HBG_PUSH_STATS_I(tx_drop_cnt, 84),
+	HBG_PUSH_STATS_I(tx_excessive_length_drop_cnt, 85),
+	HBG_PUSH_STATS_I(tx_dma_err_cnt, 86),
+	HBG_PUSH_STATS_I(reset_fail_cnt, 87),
+};
+
+static int hbg_push_msg_send(struct hbg_priv *priv,
+			     struct hbg_diagnose_message *msg)
+{
+	u32 header = 0;
+	u32 i;
+
+	if (msg->data_num == 0)
+		return 0;
+
+	for (i = 0; i < msg->data_num && i < HBG_MSG_DATA_MAX_NUM; i++)
+		hbg_reg_write(priv,
+			      HBG_REG_MSG_DATA_BASE_ADDR + i * sizeof(u32),
+			      msg->data[i]);
+
+	hbg_field_modify(header, HBG_REG_MSG_HEADER_OPCODE_M, msg->opcode);
+	hbg_field_modify(header, HBG_REG_MSG_HEADER_DATA_NUM_M,  msg->data_num);
+	hbg_field_modify(header, HBG_REG_MSG_HEADER_RESP_CODE_M, ETIMEDOUT);
+
+	/* start status */
+	hbg_field_modify(header, HBG_REG_MSG_HEADER_STATUS_M, 1);
+
+	/* write header msg to start push */
+	hbg_reg_write(priv, HBG_REG_MSG_HEADER_ADDR, header);
+
+	/* wait done */
+	readl_poll_timeout(priv->io_base + HBG_REG_MSG_HEADER_ADDR, header,
+			   !FIELD_GET(HBG_REG_MSG_HEADER_STATUS_M, header),
+			   HBG_HW_PUSH_WAIT_INTERVAL_US,
+			   HBG_HW_PUSH_WAIT_TIMEOUT_US);
+
+	msg->status = FIELD_GET(HBG_REG_MSG_HEADER_STATUS_M, header);
+	return -(int)FIELD_GET(HBG_REG_MSG_HEADER_RESP_CODE_M, header);
+}
+
+static int hbg_push_data(struct hbg_priv *priv,
+			 u32 opcode, u32 *data, u32 data_num)
+{
+	struct hbg_diagnose_message msg = {0};
+	u32 data_left_num;
+	u32 i, j;
+	int ret;
+
+	msg.priv = priv;
+	msg.opcode = opcode;
+	for (i = 0; i < data_num / HBG_MSG_DATA_MAX_NUM + 1; i++) {
+		if (i * HBG_MSG_DATA_MAX_NUM >= data_num)
+			break;
+
+		data_left_num = data_num - i * HBG_MSG_DATA_MAX_NUM;
+		for (j = 0; j < data_left_num && j < HBG_MSG_DATA_MAX_NUM; j++)
+			msg.data[j] = data[i * HBG_MSG_DATA_MAX_NUM + j];
+
+		msg.data_num = j;
+		ret = hbg_push_msg_send(priv, &msg);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int hbg_push_data_u64(struct hbg_priv *priv, u32 opcode,
+			     u64 *data, u32 data_num)
+{
+	/* The length of u64 is twice that of u32,
+	 * the data_num must be multiplied by 2.
+	 */
+	return hbg_push_data(priv, opcode, (u32 *)data, data_num * 2);
+}
+
+static u64 hbg_get_irq_stats(struct hbg_vector *vectors, u32 mask)
+{
+	u32 i = 0;
+
+	for (i = 0; i < vectors->info_array_len; i++)
+		if (vectors->info_array[i].mask == mask)
+			return vectors->stats_array[i];
+
+	return 0;
+}
+
+static int hbg_push_irq_cnt(struct hbg_priv *priv)
+{
+	/* An id needs to be added for each data.
+	 * Therefore, the data_num must be multiplied by 2.
+	 */
+	u32 data_num = ARRAY_SIZE(hbg_push_irq_list) * 2;
+	struct hbg_vector *vectors = &priv->vectors;
+	const struct hbg_push_irq_info *info;
+	u32 i, j = 0;
+	u64 *data;
+	int ret;
+
+	data = kcalloc(data_num, sizeof(u64), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	/* An id needs to be added for each data.
+	 * So i + 2 for each loop.
+	 */
+	for (i = 0; i < data_num; i += 2) {
+		info = &hbg_push_irq_list[j++];
+		data[i] = info->id;
+		data[i + 1] = hbg_get_irq_stats(vectors, info->mask);
+	}
+
+	ret = hbg_push_data_u64(priv, HBG_PUSH_CMD_IRQ, data, data_num);
+	kfree(data);
+	return ret;
+}
+
+static int hbg_push_link_status(struct hbg_priv *priv)
+{
+	u32 link_status[2];
+
+	/* phy link status */
+	link_status[0] = priv->mac.phydev->link;
+	/* mac link status */
+	link_status[1] = hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR,
+					    HBG_REG_AN_NEG_STATE_NP_LINK_OK_B);
+
+	return hbg_push_data(priv, HBG_PUSH_CMD_LINK,
+			     link_status, ARRAY_SIZE(link_status));
+}
+
+static int hbg_push_stats(struct hbg_priv *priv)
+{
+	/* An id needs to be added for each data.
+	 * Therefore, the data_num must be multiplied by 2.
+	 */
+	u64 data_num = ARRAY_SIZE(hbg_push_stats_list) * 2;
+	struct hbg_stats *stats = &priv->stats;
+	const struct hbg_push_stats_info *info;
+	u32 i, j = 0;
+	u64 *data;
+	int ret;
+
+	data = kcalloc(data_num, sizeof(u64), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	/* An id needs to be added for each data.
+	 * So i + 2 for each loop.
+	 */
+	for (i = 0; i < data_num; i += 2) {
+		info = &hbg_push_stats_list[j++];
+		data[i] = info->id;
+		data[i + 1] = HBG_STATS_R(stats, info->offset);
+	}
+
+	ret = hbg_push_data_u64(priv, HBG_PUSH_CMD_STATS, data, data_num);
+	kfree(data);
+	return ret;
+}
+
+void hbg_diagnose_message_push(struct hbg_priv *priv)
+{
+	int ret;
+
+	if (test_bit(HBG_NIC_STATE_RESETTING, &priv->state))
+		return;
+
+	/* only 1 is the right value */
+	if (hbg_reg_read(priv, HBG_REG_PUSH_REQ_ADDR) != 1)
+		return;
+
+	ret = hbg_push_irq_cnt(priv);
+	if (ret) {
+		dev_err(&priv->pdev->dev,
+			"failed to push irq cnt, ret = %d\n", ret);
+		goto push_done;
+	}
+
+	ret = hbg_push_link_status(priv);
+	if (ret) {
+		dev_err(&priv->pdev->dev,
+			"failed to push link status, ret = %d\n", ret);
+		goto push_done;
+	}
+
+	ret = hbg_push_stats(priv);
+	if (ret)
+		dev_err(&priv->pdev->dev,
+			"failed to push stats, ret = %d\n", ret);
+
+push_done:
+	hbg_reg_write(priv, HBG_REG_PUSH_REQ_ADDR, 0);
+}
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.h
new file mode 100644
index 000000000000..ba04c6d8c03d
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2025 Hisilicon Limited. */
+
+#ifndef __HBG_DIAGNOSE_H
+#define __HBG_DIAGNOSE_H
+
+#include "hbg_common.h"
+
+void hbg_diagnose_message_push(struct hbg_priv *priv);
+
+#endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
index 4d1f4a33391a..7234618e8e81 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
@@ -26,12 +26,15 @@ static void hbg_restore_mac_table(struct hbg_priv *priv)
 
 static void hbg_restore_user_def_settings(struct hbg_priv *priv)
 {
+	/* The index of host mac is always 0. */
+	u64 rx_pause_addr = ether_addr_to_u64(priv->filter.mac_table[0].addr);
 	struct ethtool_pauseparam *pause_param = &priv->user_def.pause_param;
 
 	hbg_restore_mac_table(priv);
 	hbg_hw_set_mtu(priv, priv->netdev->mtu);
 	hbg_hw_set_pause_enable(priv, pause_param->tx_pause,
 				pause_param->rx_pause);
+	hbg_hw_set_rx_pause_mac_addr(priv, rx_pause_addr);
 }
 
 int hbg_rebuild(struct hbg_priv *priv)
@@ -50,19 +53,23 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
 {
 	int ret;
 
-	ASSERT_RTNL();
+	if (test_and_set_bit(HBG_NIC_STATE_RESETTING, &priv->state))
+		return -EBUSY;
 
 	if (netif_running(priv->netdev)) {
+		clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
 		dev_warn(&priv->pdev->dev,
 			 "failed to reset because port is up\n");
 		return -EBUSY;
 	}
 
+	netif_device_detach(priv->netdev);
+
 	priv->reset_type = type;
-	set_bit(HBG_NIC_STATE_RESETTING, &priv->state);
 	clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
 	ret = hbg_hw_event_notify(priv, HBG_HW_EVENT_RESET);
 	if (ret) {
+		priv->stats.reset_fail_cnt++;
 		set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
 		clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
 	}
@@ -78,26 +85,26 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type)
 	    type != priv->reset_type)
 		return 0;
 
-	ASSERT_RTNL();
-
-	clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
 	ret = hbg_rebuild(priv);
 	if (ret) {
+		priv->stats.reset_fail_cnt++;
 		set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
+		clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
 		dev_err(&priv->pdev->dev, "failed to rebuild after reset\n");
 		return ret;
 	}
 
+	netif_device_attach(priv->netdev);
+	clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
+
 	dev_info(&priv->pdev->dev, "reset done\n");
 	return ret;
 }
 
-/* must be protected by rtnl lock */
 int hbg_reset(struct hbg_priv *priv)
 {
 	int ret;
 
-	ASSERT_RTNL();
 	ret = hbg_reset_prepare(priv, HBG_RESET_TYPE_FUNCTION);
 	if (ret)
 		return ret;
@@ -105,12 +112,64 @@ int hbg_reset(struct hbg_priv *priv)
 	return hbg_reset_done(priv, HBG_RESET_TYPE_FUNCTION);
 }
 
+void hbg_err_reset(struct hbg_priv *priv)
+{
+	bool running;
+
+	rtnl_lock();
+	running = netif_running(priv->netdev);
+	if (running)
+		dev_close(priv->netdev);
+
+	if (hbg_reset(priv))
+		goto err_unlock;
+
+	if (running)
+		dev_open(priv->netdev, NULL);
+
+err_unlock:
+	rtnl_unlock();
+}
+
+static pci_ers_result_t hbg_pci_err_detected(struct pci_dev *pdev,
+					     pci_channel_state_t state)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+
+	if (state == pci_channel_io_perm_failure) {
+		netif_device_detach(netdev);
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+static pci_ers_result_t hbg_pci_err_slot_reset(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct hbg_priv *priv = netdev_priv(netdev);
+
+	netif_device_detach(netdev);
+	pci_disable_device(pdev);
+
+	if (pci_enable_device(pdev)) {
+		dev_err(&pdev->dev,
+			"failed to re-enable PCI device after reset\n");
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	pci_set_master(pdev);
+	pci_restore_state(pdev);
+
+	hbg_err_reset(priv);
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
 static void hbg_pci_err_reset_prepare(struct pci_dev *pdev)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct hbg_priv *priv = netdev_priv(netdev);
 
-	rtnl_lock();
 	hbg_reset_prepare(priv, HBG_RESET_TYPE_FLR);
 }
 
@@ -120,10 +179,11 @@ static void hbg_pci_err_reset_done(struct pci_dev *pdev)
 	struct hbg_priv *priv = netdev_priv(netdev);
 
 	hbg_reset_done(priv, HBG_RESET_TYPE_FLR);
-	rtnl_unlock();
 }
 
 static const struct pci_error_handlers hbg_pci_err_handler = {
+	.error_detected = hbg_pci_err_detected,
+	.slot_reset = hbg_pci_err_slot_reset,
 	.reset_prepare = hbg_pci_err_reset_prepare,
 	.reset_done = hbg_pci_err_reset_done,
 };
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h
index d7828e446308..fb9fbe7004e8 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h
@@ -9,5 +9,6 @@
 void hbg_set_pci_err_handler(struct pci_driver *pdrv);
 int hbg_reset(struct hbg_priv *priv);
 int hbg_rebuild(struct hbg_priv *priv);
+void hbg_err_reset(struct hbg_priv *priv);
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
index 00364a438ec2..1d62ff913737 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
@@ -9,6 +9,137 @@
 #include "hbg_ethtool.h"
 #include "hbg_hw.h"
 
+struct hbg_ethtool_stats {
+	char name[ETH_GSTRING_LEN];
+	unsigned long offset;
+	u32 reg; /* set to 0 if stats is not updated via dump reg */
+};
+
+#define HBG_STATS_I(stats) { #stats, HBG_STATS_FIELD_OFF(stats), 0}
+#define HBG_STATS_REG_I(stats, reg) { #stats, HBG_STATS_FIELD_OFF(stats), reg}
+
+static const struct hbg_ethtool_stats hbg_ethtool_stats_info[] = {
+	HBG_STATS_I(rx_desc_l2_err_cnt),
+	HBG_STATS_I(rx_desc_pkt_len_err_cnt),
+	HBG_STATS_I(rx_desc_l3_wrong_head_cnt),
+	HBG_STATS_I(rx_desc_l3_csum_err_cnt),
+	HBG_STATS_I(rx_desc_l3_len_err_cnt),
+	HBG_STATS_I(rx_desc_l3_zero_ttl_cnt),
+	HBG_STATS_I(rx_desc_l3_other_cnt),
+	HBG_STATS_I(rx_desc_l4_wrong_head_cnt),
+	HBG_STATS_I(rx_desc_l4_len_err_cnt),
+	HBG_STATS_I(rx_desc_l4_csum_err_cnt),
+	HBG_STATS_I(rx_desc_l4_zero_port_num_cnt),
+	HBG_STATS_I(rx_desc_l4_other_cnt),
+	HBG_STATS_I(rx_desc_ip_ver_err_cnt),
+	HBG_STATS_I(rx_desc_ipv4_pkt_cnt),
+	HBG_STATS_I(rx_desc_ipv6_pkt_cnt),
+	HBG_STATS_I(rx_desc_no_ip_pkt_cnt),
+	HBG_STATS_I(rx_desc_ip_pkt_cnt),
+	HBG_STATS_I(rx_desc_tcp_pkt_cnt),
+	HBG_STATS_I(rx_desc_udp_pkt_cnt),
+	HBG_STATS_I(rx_desc_vlan_pkt_cnt),
+	HBG_STATS_I(rx_desc_icmp_pkt_cnt),
+	HBG_STATS_I(rx_desc_arp_pkt_cnt),
+	HBG_STATS_I(rx_desc_rarp_pkt_cnt),
+	HBG_STATS_I(rx_desc_multicast_pkt_cnt),
+	HBG_STATS_I(rx_desc_broadcast_pkt_cnt),
+	HBG_STATS_I(rx_desc_ipsec_pkt_cnt),
+	HBG_STATS_I(rx_desc_ip_opt_pkt_cnt),
+	HBG_STATS_I(rx_desc_key_not_match_cnt),
+
+	HBG_STATS_REG_I(rx_octets_bad_cnt, HBG_REG_RX_OCTETS_BAD_ADDR),
+	HBG_STATS_REG_I(rx_octets_total_filt_cnt,
+			HBG_REG_RX_OCTETS_TOTAL_FILT_ADDR),
+	HBG_STATS_REG_I(rx_uc_pkt_cnt, HBG_REG_RX_UC_PKTS_ADDR),
+	HBG_STATS_REG_I(rx_vlan_pkt_cnt, HBG_REG_RX_TAGGED_ADDR),
+	HBG_STATS_REG_I(rx_filt_pkt_cnt, HBG_REG_RX_FILT_PKT_CNT_ADDR),
+	HBG_STATS_REG_I(rx_data_error_cnt, HBG_REG_RX_DATA_ERR_ADDR),
+	HBG_STATS_REG_I(rx_frame_long_err_cnt, HBG_REG_RX_LONG_ERRORS_ADDR),
+	HBG_STATS_REG_I(rx_jabber_err_cnt, HBG_REG_RX_JABBER_ERRORS_ADDR),
+	HBG_STATS_REG_I(rx_frame_very_long_err_cnt,
+			HBG_REG_RX_VERY_LONG_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_frame_runt_err_cnt, HBG_REG_RX_RUNT_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_frame_short_err_cnt, HBG_REG_RX_SHORT_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_overflow_cnt, HBG_REG_RX_OVER_FLOW_CNT_ADDR),
+	HBG_STATS_REG_I(rx_bufrq_err_cnt, HBG_REG_RX_BUFRQ_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_we_err_cnt, HBG_REG_RX_WE_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_overrun_cnt, HBG_REG_RX_OVERRUN_CNT_ADDR),
+	HBG_STATS_REG_I(rx_lengthfield_err_cnt,
+			HBG_REG_RX_LENGTHFIELD_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_fail_comma_cnt, HBG_REG_RX_FAIL_COMMA_CNT_ADDR),
+	HBG_STATS_I(rx_dma_err_cnt),
+	HBG_STATS_I(rx_fifo_less_empty_thrsld_cnt),
+
+	HBG_STATS_REG_I(tx_uc_pkt_cnt, HBG_REG_TX_UC_PKTS_ADDR),
+	HBG_STATS_REG_I(tx_vlan_pkt_cnt, HBG_REG_TX_TAGGED_ADDR),
+	HBG_STATS_REG_I(tx_octets_bad_cnt, HBG_REG_OCTETS_TRANSMITTED_BAD_ADDR),
+
+	HBG_STATS_REG_I(tx_underrun_err_cnt, HBG_REG_TX_UNDERRUN_ADDR),
+	HBG_STATS_REG_I(tx_add_cs_fail_cnt, HBG_REG_TX_CS_FAIL_CNT_ADDR),
+	HBG_STATS_REG_I(tx_bufrl_err_cnt, HBG_REG_TX_BUFRL_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(tx_crc_err_cnt, HBG_REG_TX_CRC_ERROR_ADDR),
+	HBG_STATS_REG_I(tx_drop_cnt, HBG_REG_TX_DROP_CNT_ADDR),
+	HBG_STATS_REG_I(tx_excessive_length_drop_cnt,
+			HBG_REG_TX_EXCESSIVE_LENGTH_DROP_ADDR),
+	HBG_STATS_I(tx_dma_err_cnt),
+	HBG_STATS_I(tx_timeout_cnt),
+	HBG_STATS_I(reset_fail_cnt),
+};
+
+static const struct hbg_ethtool_stats hbg_ethtool_rmon_stats_info[] = {
+	HBG_STATS_I(rx_desc_frag_cnt),
+	HBG_STATS_REG_I(rx_framesize_64, HBG_REG_RX_PKTS_64OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_65_127,
+			HBG_REG_RX_PKTS_65TO127OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_128_255,
+			HBG_REG_RX_PKTS_128TO255OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_256_511,
+			HBG_REG_RX_PKTS_256TO511OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_512_1023,
+			HBG_REG_RX_PKTS_512TO1023OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_1024_1518,
+			HBG_REG_RX_PKTS_1024TO1518OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_bt_1518,
+			HBG_REG_RX_PKTS_1519TOMAXOCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_64, HBG_REG_TX_PKTS_64OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_65_127,
+			HBG_REG_TX_PKTS_65TO127OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_128_255,
+			HBG_REG_TX_PKTS_128TO255OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_256_511,
+			HBG_REG_TX_PKTS_256TO511OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_512_1023,
+			HBG_REG_TX_PKTS_512TO1023OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_1024_1518,
+			HBG_REG_TX_PKTS_1024TO1518OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_bt_1518,
+			HBG_REG_TX_PKTS_1519TOMAXOCTETS_ADDR),
+};
+
+static const struct hbg_ethtool_stats hbg_ethtool_mac_stats_info[] = {
+	HBG_STATS_REG_I(rx_mc_pkt_cnt, HBG_REG_RX_MC_PKTS_ADDR),
+	HBG_STATS_REG_I(rx_bc_pkt_cnt, HBG_REG_RX_BC_PKTS_ADDR),
+	HBG_STATS_REG_I(rx_align_error_cnt, HBG_REG_RX_ALIGN_ERRORS_ADDR),
+	HBG_STATS_REG_I(rx_octets_total_ok_cnt,
+			HBG_REG_RX_OCTETS_TOTAL_OK_ADDR),
+	HBG_STATS_REG_I(rx_trans_pkt_cnt, HBG_REG_RX_TRANS_PKG_CNT_ADDR),
+	HBG_STATS_REG_I(rx_fcs_error_cnt, HBG_REG_RX_FCS_ERRORS_ADDR),
+	HBG_STATS_REG_I(tx_mc_pkt_cnt, HBG_REG_TX_MC_PKTS_ADDR),
+	HBG_STATS_REG_I(tx_bc_pkt_cnt, HBG_REG_TX_BC_PKTS_ADDR),
+	HBG_STATS_REG_I(tx_octets_total_ok_cnt,
+			HBG_REG_OCTETS_TRANSMITTED_OK_ADDR),
+	HBG_STATS_REG_I(tx_trans_pkt_cnt, HBG_REG_TX_TRANS_PKG_CNT_ADDR),
+};
+
+static const struct hbg_ethtool_stats hbg_ethtool_ctrl_stats_info[] = {
+	HBG_STATS_REG_I(rx_pause_macctl_frame_cnt,
+			HBG_REG_RX_PAUSE_MACCTL_FRAMCOUNTER_ADDR),
+	HBG_STATS_REG_I(tx_pause_frame_cnt, HBG_REG_TX_PAUSE_FRAMES_ADDR),
+	HBG_STATS_REG_I(rx_unknown_macctl_frame_cnt,
+			HBG_REG_RX_UNKNOWN_MACCTL_FRAMCOUNTER_ADDR),
+};
+
 enum hbg_reg_dump_type {
 	HBG_DUMP_REG_TYPE_SPEC = 0,
 	HBG_DUMP_REG_TYPE_MDIO,
@@ -180,6 +311,170 @@ static int hbg_ethtool_reset(struct net_device *netdev, u32 *flags)
 	return hbg_reset(priv);
 }
 
+static void hbg_update_stats_by_info(struct hbg_priv *priv,
+				     const struct hbg_ethtool_stats *info,
+				     u32 info_len)
+{
+	const struct hbg_ethtool_stats *stats;
+	u32 i;
+
+	if (test_bit(HBG_NIC_STATE_RESETTING, &priv->state))
+		return;
+
+	for (i = 0; i < info_len; i++) {
+		stats = &info[i];
+		if (!stats->reg)
+			continue;
+
+		HBG_STATS_U(&priv->stats, stats->offset,
+			    hbg_reg_read(priv, stats->reg));
+	}
+}
+
+void hbg_update_stats(struct hbg_priv *priv)
+{
+	hbg_update_stats_by_info(priv, hbg_ethtool_stats_info,
+				 ARRAY_SIZE(hbg_ethtool_stats_info));
+	hbg_update_stats_by_info(priv, hbg_ethtool_rmon_stats_info,
+				 ARRAY_SIZE(hbg_ethtool_rmon_stats_info));
+	hbg_update_stats_by_info(priv, hbg_ethtool_mac_stats_info,
+				 ARRAY_SIZE(hbg_ethtool_mac_stats_info));
+	hbg_update_stats_by_info(priv, hbg_ethtool_ctrl_stats_info,
+				 ARRAY_SIZE(hbg_ethtool_ctrl_stats_info));
+}
+
+static int hbg_ethtool_get_sset_count(struct net_device *netdev, int stringset)
+{
+	if (stringset != ETH_SS_STATS)
+		return -EOPNOTSUPP;
+
+	return ARRAY_SIZE(hbg_ethtool_stats_info);
+}
+
+static void hbg_ethtool_get_strings(struct net_device *netdev,
+				    u32 stringset, u8 *data)
+{
+	u32 i;
+
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(hbg_ethtool_stats_info); i++)
+		ethtool_puts(&data, hbg_ethtool_stats_info[i].name);
+}
+
+static void hbg_ethtool_get_stats(struct net_device *netdev,
+				  struct ethtool_stats *stats, u64 *data)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	u32 i;
+
+	hbg_update_stats(priv);
+	for (i = 0; i < ARRAY_SIZE(hbg_ethtool_stats_info); i++)
+		*data++ = HBG_STATS_R(&priv->stats,
+				      hbg_ethtool_stats_info[i].offset);
+}
+
+static void hbg_ethtool_get_pause_stats(struct net_device *netdev,
+					struct ethtool_pause_stats *epstats)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *stats = &priv->stats;
+
+	hbg_update_stats(priv);
+	epstats->rx_pause_frames = stats->rx_pause_macctl_frame_cnt;
+	epstats->tx_pause_frames = stats->tx_pause_frame_cnt;
+}
+
+static void hbg_ethtool_get_eth_mac_stats(struct net_device *netdev,
+					  struct ethtool_eth_mac_stats *emstats)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *stats = &priv->stats;
+
+	hbg_update_stats(priv);
+	emstats->FramesTransmittedOK = stats->tx_trans_pkt_cnt;
+	emstats->FramesReceivedOK = stats->rx_trans_pkt_cnt;
+	emstats->FrameCheckSequenceErrors = stats->rx_fcs_error_cnt;
+	emstats->AlignmentErrors = stats->rx_align_error_cnt;
+	emstats->OctetsTransmittedOK = stats->tx_octets_total_ok_cnt;
+	emstats->OctetsReceivedOK = stats->rx_octets_total_ok_cnt;
+
+	emstats->MulticastFramesXmittedOK = stats->tx_mc_pkt_cnt;
+	emstats->BroadcastFramesXmittedOK = stats->tx_bc_pkt_cnt;
+	emstats->MulticastFramesReceivedOK = stats->rx_mc_pkt_cnt;
+	emstats->BroadcastFramesReceivedOK = stats->rx_bc_pkt_cnt;
+	emstats->InRangeLengthErrors = stats->rx_fcs_error_cnt +
+				       stats->rx_jabber_err_cnt +
+				       stats->rx_unknown_macctl_frame_cnt +
+				       stats->rx_bufrq_err_cnt +
+				       stats->rx_we_err_cnt;
+	emstats->OutOfRangeLengthField = stats->rx_frame_short_err_cnt +
+					 stats->rx_frame_runt_err_cnt +
+					 stats->rx_lengthfield_err_cnt +
+					 stats->rx_frame_long_err_cnt +
+					 stats->rx_frame_very_long_err_cnt;
+	emstats->FrameTooLongErrors = stats->rx_frame_long_err_cnt +
+				      stats->rx_frame_very_long_err_cnt;
+}
+
+static void
+hbg_ethtool_get_eth_ctrl_stats(struct net_device *netdev,
+			       struct ethtool_eth_ctrl_stats *ecstats)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *s = &priv->stats;
+
+	hbg_update_stats(priv);
+	ecstats->MACControlFramesTransmitted = s->tx_pause_frame_cnt;
+	ecstats->MACControlFramesReceived = s->rx_pause_macctl_frame_cnt;
+	ecstats->UnsupportedOpcodesReceived = s->rx_unknown_macctl_frame_cnt;
+}
+
+static const struct ethtool_rmon_hist_range hbg_rmon_ranges[] = {
+	{    0,    64 },
+	{   65,   127 },
+	{  128,   255 },
+	{  256,   511 },
+	{  512,  1023 },
+	{ 1024,  1518 },
+	{ 1519,  4095 },
+};
+
+static void
+hbg_ethtool_get_rmon_stats(struct net_device *netdev,
+			   struct ethtool_rmon_stats *rmon_stats,
+			   const struct ethtool_rmon_hist_range **ranges)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *stats = &priv->stats;
+
+	hbg_update_stats(priv);
+	rmon_stats->undersize_pkts = stats->rx_frame_short_err_cnt +
+				     stats->rx_frame_runt_err_cnt +
+				     stats->rx_lengthfield_err_cnt;
+	rmon_stats->oversize_pkts = stats->rx_frame_long_err_cnt +
+				    stats->rx_frame_very_long_err_cnt;
+	rmon_stats->fragments = stats->rx_desc_frag_cnt;
+	rmon_stats->hist[0] = stats->rx_framesize_64;
+	rmon_stats->hist[1] = stats->rx_framesize_65_127;
+	rmon_stats->hist[2] = stats->rx_framesize_128_255;
+	rmon_stats->hist[3] = stats->rx_framesize_256_511;
+	rmon_stats->hist[4] = stats->rx_framesize_512_1023;
+	rmon_stats->hist[5] = stats->rx_framesize_1024_1518;
+	rmon_stats->hist[6] = stats->rx_framesize_bt_1518;
+
+	rmon_stats->hist_tx[0] = stats->tx_framesize_64;
+	rmon_stats->hist_tx[1] = stats->tx_framesize_65_127;
+	rmon_stats->hist_tx[2] = stats->tx_framesize_128_255;
+	rmon_stats->hist_tx[3] = stats->tx_framesize_256_511;
+	rmon_stats->hist_tx[4] = stats->tx_framesize_512_1023;
+	rmon_stats->hist_tx[5] = stats->tx_framesize_1024_1518;
+	rmon_stats->hist_tx[6] = stats->tx_framesize_bt_1518;
+
+	*ranges = hbg_rmon_ranges;
+}
+
 static const struct ethtool_ops hbg_ethtool_ops = {
 	.get_link		= ethtool_op_get_link,
 	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
@@ -190,6 +485,13 @@ static const struct ethtool_ops hbg_ethtool_ops = {
 	.set_pauseparam         = hbg_ethtool_set_pauseparam,
 	.reset			= hbg_ethtool_reset,
 	.nway_reset		= phy_ethtool_nway_reset,
+	.get_sset_count		= hbg_ethtool_get_sset_count,
+	.get_strings		= hbg_ethtool_get_strings,
+	.get_ethtool_stats	= hbg_ethtool_get_stats,
+	.get_pause_stats	= hbg_ethtool_get_pause_stats,
+	.get_eth_mac_stats	= hbg_ethtool_get_eth_mac_stats,
+	.get_eth_ctrl_stats	= hbg_ethtool_get_eth_ctrl_stats,
+	.get_rmon_stats		= hbg_ethtool_get_rmon_stats,
 };
 
 void hbg_ethtool_set_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.h
index 628707ec2686..e173155b146a 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.h
@@ -6,6 +6,11 @@
 
 #include <linux/netdevice.h>
 
+#define HBG_STATS_FIELD_OFF(f) (offsetof(struct hbg_stats, f))
+#define HBG_STATS_R(p, offset) (*(u64 *)((u8 *)(p) + (offset)))
+#define HBG_STATS_U(p, offset, val) (HBG_STATS_R(p, offset) += (val))
+
 void hbg_ethtool_set_ops(struct net_device *netdev);
+void hbg_update_stats(struct hbg_priv *priv);
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
index e7798f213645..d6e8ce8e351a 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
@@ -12,12 +12,21 @@
 
 #define HBG_HW_EVENT_WAIT_TIMEOUT_US	(2 * 1000 * 1000)
 #define HBG_HW_EVENT_WAIT_INTERVAL_US	(10 * 1000)
+#define HBG_MAC_LINK_WAIT_TIMEOUT_US	(500 * 1000)
+#define HBG_MAC_LINK_WAIT_INTERVAL_US	(5 * 1000)
 /* little endian or big endian.
  * ctrl means packet description, data means skb packet data
  */
 #define HBG_ENDIAN_CTRL_LE_DATA_BE	0x0
 #define HBG_PCU_FRAME_LEN_PLUS 4
 
+#define HBG_FIFO_TX_FULL_THRSLD		0x3F0
+#define HBG_FIFO_TX_EMPTY_THRSLD	0x1F0
+#define HBG_FIFO_RX_FULL_THRSLD		0x240
+#define HBG_FIFO_RX_EMPTY_THRSLD	0x190
+#define HBG_CFG_FIFO_FULL_THRSLD	0x10
+#define HBG_CFG_FIFO_EMPTY_THRSLD	0x01
+
 static bool hbg_hw_spec_is_valid(struct hbg_priv *priv)
 {
 	return hbg_reg_read(priv, HBG_REG_SPEC_VALID_ADDR) &&
@@ -168,6 +177,11 @@ static void hbg_hw_set_mac_max_frame_len(struct hbg_priv *priv,
 
 void hbg_hw_set_mtu(struct hbg_priv *priv, u16 mtu)
 {
+	/* burst_len BIT(29) set to 1 can improve the TX performance.
+	 * But packet drop occurs when mtu > 2000.
+	 * So, BIT(29) reset to 0 when mtu > 2000.
+	 */
+	u32 burst_len_bit = (mtu > 2000) ? 0 : 1;
 	u32 frame_len;
 
 	frame_len = mtu + VLAN_HLEN * priv->dev_specs.vlan_layers +
@@ -175,6 +189,9 @@ void hbg_hw_set_mtu(struct hbg_priv *priv, u16 mtu)
 
 	hbg_hw_set_pcu_max_frame_len(priv, frame_len);
 	hbg_hw_set_mac_max_frame_len(priv, frame_len);
+
+	hbg_reg_write_field(priv, HBG_REG_BRUST_LENGTH_ADDR,
+			    HBG_REG_BRUST_LENGTH_B, burst_len_bit);
 }
 
 void hbg_hw_mac_enable(struct hbg_priv *priv, u32 enable)
@@ -213,10 +230,32 @@ void hbg_hw_fill_buffer(struct hbg_priv *priv, u32 buffer_dma_addr)
 
 void hbg_hw_adjust_link(struct hbg_priv *priv, u32 speed, u32 duplex)
 {
+	u32 link_status;
+	int ret;
+
+	hbg_hw_mac_enable(priv, HBG_STATUS_DISABLE);
+
 	hbg_reg_write_field(priv, HBG_REG_PORT_MODE_ADDR,
 			    HBG_REG_PORT_MODE_M, speed);
 	hbg_reg_write_field(priv, HBG_REG_DUPLEX_TYPE_ADDR,
 			    HBG_REG_DUPLEX_B, duplex);
+
+	hbg_hw_event_notify(priv, HBG_HW_EVENT_CORE_RESET);
+
+	hbg_hw_mac_enable(priv, HBG_STATUS_ENABLE);
+
+	if (priv->mac.phy_addr == HBG_NO_PHY)
+		return;
+
+	/* wait MAC link up */
+	ret = readl_poll_timeout(priv->io_base + HBG_REG_AN_NEG_STATE_ADDR,
+				 link_status,
+				 FIELD_GET(HBG_REG_AN_NEG_STATE_NP_LINK_OK_B,
+					   link_status),
+				 HBG_MAC_LINK_WAIT_INTERVAL_US,
+				 HBG_MAC_LINK_WAIT_TIMEOUT_US);
+	if (ret)
+		hbg_np_link_fail_task_schedule(priv);
 }
 
 /* only support uc filter */
@@ -224,6 +263,10 @@ void hbg_hw_set_mac_filter_enable(struct hbg_priv *priv, u32 enable)
 {
 	hbg_reg_write_field(priv, HBG_REG_REC_FILT_CTRL_ADDR,
 			    HBG_REG_REC_FILT_CTRL_UC_MATCH_EN_B, enable);
+
+	/* only uc filter is supported, so set all bits of mc mask reg to 1 */
+	hbg_reg_write64(priv, HBG_REG_STATION_ADDR_LOW_MSK_0, U64_MAX);
+	hbg_reg_write64(priv, HBG_REG_STATION_ADDR_LOW_MSK_1, U64_MAX);
 }
 
 void hbg_hw_set_pause_enable(struct hbg_priv *priv, u32 tx_en, u32 rx_en)
@@ -232,6 +275,9 @@ void hbg_hw_set_pause_enable(struct hbg_priv *priv, u32 tx_en, u32 rx_en)
 			    HBG_REG_PAUSE_ENABLE_TX_B, tx_en);
 	hbg_reg_write_field(priv, HBG_REG_PAUSE_ENABLE_ADDR,
 			    HBG_REG_PAUSE_ENABLE_RX_B, rx_en);
+
+	hbg_reg_write_field(priv, HBG_REG_REC_FILT_CTRL_ADDR,
+			    HBG_REG_REC_FILT_CTRL_PAUSE_FRM_PASS_B, rx_en);
 }
 
 void hbg_hw_get_pause_enable(struct hbg_priv *priv, u32 *tx_en, u32 *rx_en)
@@ -247,6 +293,41 @@ void hbg_hw_set_rx_pause_mac_addr(struct hbg_priv *priv, u64 mac_addr)
 	hbg_reg_write64(priv, HBG_REG_FD_FC_ADDR_LOW_ADDR, mac_addr);
 }
 
+static void hbg_hw_set_fifo_thrsld(struct hbg_priv *priv,
+				   u32 full, u32 empty, enum hbg_dir dir)
+{
+	u32 value = 0;
+
+	value |= FIELD_PREP(HBG_REG_FIFO_THRSLD_FULL_M, full);
+	value |= FIELD_PREP(HBG_REG_FIFO_THRSLD_EMPTY_M, empty);
+
+	if (dir & HBG_DIR_TX)
+		hbg_reg_write(priv, HBG_REG_TX_FIFO_THRSLD_ADDR, value);
+
+	if (dir & HBG_DIR_RX)
+		hbg_reg_write(priv, HBG_REG_RX_FIFO_THRSLD_ADDR, value);
+}
+
+static void hbg_hw_set_cfg_fifo_thrsld(struct hbg_priv *priv,
+				       u32 full, u32 empty, enum hbg_dir dir)
+{
+	u32 value;
+
+	value = hbg_reg_read(priv, HBG_REG_CFG_FIFO_THRSLD_ADDR);
+
+	if (dir & HBG_DIR_TX) {
+		value |= FIELD_PREP(HBG_REG_CFG_FIFO_THRSLD_TX_FULL_M, full);
+		value |= FIELD_PREP(HBG_REG_CFG_FIFO_THRSLD_TX_EMPTY_M, empty);
+	}
+
+	if (dir & HBG_DIR_RX) {
+		value |= FIELD_PREP(HBG_REG_CFG_FIFO_THRSLD_RX_FULL_M, full);
+		value |= FIELD_PREP(HBG_REG_CFG_FIFO_THRSLD_RX_EMPTY_M, empty);
+	}
+
+	hbg_reg_write(priv, HBG_REG_CFG_FIFO_THRSLD_ADDR, value);
+}
+
 static void hbg_hw_init_transmit_ctrl(struct hbg_priv *priv)
 {
 	u32 ctrl = 0;
@@ -307,5 +388,12 @@ int hbg_hw_init(struct hbg_priv *priv)
 
 	hbg_hw_init_rx_control(priv);
 	hbg_hw_init_transmit_ctrl(priv);
+
+	hbg_hw_set_fifo_thrsld(priv, HBG_FIFO_TX_FULL_THRSLD,
+			       HBG_FIFO_TX_EMPTY_THRSLD, HBG_DIR_TX);
+	hbg_hw_set_fifo_thrsld(priv, HBG_FIFO_RX_FULL_THRSLD,
+			       HBG_FIFO_RX_EMPTY_THRSLD, HBG_DIR_RX);
+	hbg_hw_set_cfg_fifo_thrsld(priv, HBG_CFG_FIFO_FULL_THRSLD,
+				   HBG_CFG_FIFO_EMPTY_THRSLD, HBG_DIR_TX_RX);
 	return 0;
 }
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
index 25dd25f096fe..ae4cb35186d8 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
@@ -6,54 +6,66 @@
 #include "hbg_hw.h"
 
 static void hbg_irq_handle_err(struct hbg_priv *priv,
-			       struct hbg_irq_info *irq_info)
+			       const struct hbg_irq_info *irq_info)
 {
 	if (irq_info->need_print)
 		dev_err(&priv->pdev->dev,
 			"receive error interrupt: %s\n", irq_info->name);
+
+	if (irq_info->need_reset)
+		hbg_err_reset_task_schedule(priv);
 }
 
 static void hbg_irq_handle_tx(struct hbg_priv *priv,
-			      struct hbg_irq_info *irq_info)
+			      const struct hbg_irq_info *irq_info)
 {
 	napi_schedule(&priv->tx_ring.napi);
 }
 
 static void hbg_irq_handle_rx(struct hbg_priv *priv,
-			      struct hbg_irq_info *irq_info)
+			      const struct hbg_irq_info *irq_info)
 {
 	napi_schedule(&priv->rx_ring.napi);
 }
 
-#define HBG_TXRX_IRQ_I(name, handle) \
-	{#name, HBG_INT_MSK_##name##_B, false, false, 0, handle}
-#define HBG_ERR_IRQ_I(name, need_print) \
-	{#name, HBG_INT_MSK_##name##_B, true, need_print, 0, hbg_irq_handle_err}
-
-static struct hbg_irq_info hbg_irqs[] = {
-	HBG_TXRX_IRQ_I(RX, hbg_irq_handle_rx),
-	HBG_TXRX_IRQ_I(TX, hbg_irq_handle_tx),
-	HBG_ERR_IRQ_I(MAC_MII_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(MAC_PCS_RX_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(MAC_PCS_TX_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(MAC_APP_RX_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(MAC_APP_TX_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(SRAM_PARITY_ERR, true),
-	HBG_ERR_IRQ_I(TX_AHB_ERR, true),
-	HBG_ERR_IRQ_I(RX_BUF_AVL, false),
-	HBG_ERR_IRQ_I(REL_BUF_ERR, true),
-	HBG_ERR_IRQ_I(TXCFG_AVL, false),
-	HBG_ERR_IRQ_I(TX_DROP, false),
-	HBG_ERR_IRQ_I(RX_DROP, false),
-	HBG_ERR_IRQ_I(RX_AHB_ERR, true),
-	HBG_ERR_IRQ_I(MAC_FIFO_ERR, false),
-	HBG_ERR_IRQ_I(RBREQ_ERR, false),
-	HBG_ERR_IRQ_I(WE_ERR, false),
+static void hbg_irq_handle_rx_buf_val(struct hbg_priv *priv,
+				      const struct hbg_irq_info *irq_info)
+{
+	priv->stats.rx_fifo_less_empty_thrsld_cnt++;
+	hbg_hw_irq_enable(priv, irq_info->mask, true);
+}
+
+#define HBG_IRQ_I(name, handle) \
+	{#name, HBG_INT_MSK_##name##_B, false, false, false, handle}
+#define HBG_ERR_IRQ_I(name, need_print, ndde_reset) \
+	{#name, HBG_INT_MSK_##name##_B, true, need_print, \
+	ndde_reset, hbg_irq_handle_err}
+
+static const struct hbg_irq_info hbg_irqs[] = {
+	HBG_IRQ_I(RX, hbg_irq_handle_rx),
+	HBG_IRQ_I(TX, hbg_irq_handle_tx),
+	HBG_ERR_IRQ_I(TX_PKT_CPL, true, true),
+	HBG_ERR_IRQ_I(MAC_MII_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(MAC_PCS_RX_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(MAC_PCS_TX_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(MAC_APP_RX_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(MAC_APP_TX_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(SRAM_PARITY_ERR, true, false),
+	HBG_ERR_IRQ_I(TX_AHB_ERR, true, true),
+	HBG_IRQ_I(RX_BUF_AVL, hbg_irq_handle_rx_buf_val),
+	HBG_ERR_IRQ_I(REL_BUF_ERR, true, false),
+	HBG_ERR_IRQ_I(TXCFG_AVL, false, false),
+	HBG_ERR_IRQ_I(TX_DROP, false, false),
+	HBG_ERR_IRQ_I(RX_DROP, false, false),
+	HBG_ERR_IRQ_I(RX_AHB_ERR, true, false),
+	HBG_ERR_IRQ_I(MAC_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(RBREQ_ERR, true, true),
+	HBG_ERR_IRQ_I(WE_ERR, true, true),
 };
 
 static irqreturn_t hbg_irq_handle(int irq_num, void *p)
 {
-	struct hbg_irq_info *info;
+	const struct hbg_irq_info *info;
 	struct hbg_priv *priv = p;
 	u32 status;
 	u32 i;
@@ -68,7 +80,7 @@ static irqreturn_t hbg_irq_handle(int irq_num, void *p)
 			hbg_hw_irq_enable(priv, info->mask, false);
 			hbg_hw_irq_clear(priv, info->mask);
 
-			info->count++;
+			priv->vectors.stats_array[i]++;
 			if (info->irq_handle)
 				info->irq_handle(priv, info);
 
@@ -121,6 +133,12 @@ int hbg_irq_init(struct hbg_priv *priv)
 					     irq_names_map[i]);
 	}
 
+	vectors->stats_array = devm_kcalloc(&priv->pdev->dev,
+					    ARRAY_SIZE(hbg_irqs),
+					    sizeof(u64), GFP_KERNEL);
+	if (!vectors->stats_array)
+		return -ENOMEM;
+
 	vectors->info_array = hbg_irqs;
 	vectors->info_array_len = ARRAY_SIZE(hbg_irqs);
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
index bb0f25ac9760..068da2fd1fea 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
@@ -5,7 +5,9 @@
 #include <linux/if_vlan.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
+#include <linux/phy.h>
 #include "hbg_common.h"
+#include "hbg_diagnose.h"
 #include "hbg_err.h"
 #include "hbg_ethtool.h"
 #include "hbg_hw.h"
@@ -14,9 +16,12 @@
 #include "hbg_txrx.h"
 #include "hbg_debugfs.h"
 
+#define HBG_SUPPORT_FEATURES (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \
+			     NETIF_F_RXCSUM)
+
 static void hbg_all_irq_enable(struct hbg_priv *priv, bool enabled)
 {
-	struct hbg_irq_info *info;
+	const struct hbg_irq_info *info;
 	u32 i;
 
 	for (i = 0; i < priv->vectors.info_array_len; i++) {
@@ -198,12 +203,12 @@ static int hbg_net_change_mtu(struct net_device *netdev, int new_mtu)
 	if (netif_running(netdev))
 		return -EBUSY;
 
-	hbg_hw_set_mtu(priv, new_mtu);
-	WRITE_ONCE(netdev->mtu, new_mtu);
-
 	dev_dbg(&priv->pdev->dev,
 		"change mtu from %u to %u\n", netdev->mtu, new_mtu);
 
+	hbg_hw_set_mtu(priv, new_mtu);
+	WRITE_ONCE(netdev->mtu, new_mtu);
+
 	return 0;
 }
 
@@ -214,6 +219,10 @@ static void hbg_net_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	char *buf = ring->tout_log_buf;
 	u32 pos = 0;
 
+	priv->stats.tx_timeout_cnt++;
+
+	pos += scnprintf(buf + pos, HBG_TX_TIMEOUT_BUF_LEN - pos,
+			 "tx_timeout cnt: %llu\n", priv->stats.tx_timeout_cnt);
 	pos += scnprintf(buf + pos, HBG_TX_TIMEOUT_BUF_LEN - pos,
 			 "ring used num: %u, fifo used num: %u\n",
 			 hbg_get_queue_used_num(ring),
@@ -226,6 +235,39 @@ static void hbg_net_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	netdev_info(netdev, "%s", buf);
 }
 
+static void hbg_net_get_stats(struct net_device *netdev,
+			      struct rtnl_link_stats64 *stats)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *h_stats = &priv->stats;
+
+	hbg_update_stats(priv);
+	dev_get_tstats64(netdev, stats);
+
+	/* fifo empty */
+	stats->tx_fifo_errors += h_stats->tx_drop_cnt;
+
+	stats->tx_dropped += h_stats->tx_excessive_length_drop_cnt +
+			     h_stats->tx_drop_cnt;
+	stats->tx_errors += h_stats->tx_add_cs_fail_cnt +
+			    h_stats->tx_bufrl_err_cnt +
+			    h_stats->tx_underrun_err_cnt +
+			    h_stats->tx_crc_err_cnt;
+	stats->rx_errors += h_stats->rx_data_error_cnt;
+	stats->multicast += h_stats->rx_mc_pkt_cnt;
+	stats->rx_dropped += h_stats->rx_desc_drop;
+	stats->rx_length_errors += h_stats->rx_frame_very_long_err_cnt +
+				   h_stats->rx_frame_long_err_cnt +
+				   h_stats->rx_frame_runt_err_cnt +
+				   h_stats->rx_frame_short_err_cnt +
+				   h_stats->rx_lengthfield_err_cnt;
+	stats->rx_frame_errors += h_stats->rx_desc_l2_err_cnt +
+				  h_stats->rx_desc_l3l4_err_cnt;
+	stats->rx_fifo_errors += h_stats->rx_overflow_cnt +
+				 h_stats->rx_overrun_cnt;
+	stats->rx_crc_errors += h_stats->rx_fcs_error_cnt;
+}
+
 static const struct net_device_ops hbg_netdev_ops = {
 	.ndo_open		= hbg_net_open,
 	.ndo_stop		= hbg_net_stop,
@@ -235,8 +277,62 @@ static const struct net_device_ops hbg_netdev_ops = {
 	.ndo_change_mtu		= hbg_net_change_mtu,
 	.ndo_tx_timeout		= hbg_net_tx_timeout,
 	.ndo_set_rx_mode	= hbg_net_set_rx_mode,
+	.ndo_get_stats64	= hbg_net_get_stats,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 };
 
+static void hbg_service_task(struct work_struct *work)
+{
+	struct hbg_priv *priv = container_of(work, struct hbg_priv,
+					     service_task.work);
+
+	if (test_and_clear_bit(HBG_NIC_STATE_NEED_RESET, &priv->state))
+		hbg_err_reset(priv);
+
+	if (test_and_clear_bit(HBG_NIC_STATE_NP_LINK_FAIL, &priv->state))
+		hbg_fix_np_link_fail(priv);
+
+	hbg_diagnose_message_push(priv);
+
+	/* The type of statistics register is u32,
+	 * To prevent the statistics register from overflowing,
+	 * the driver dumps the statistics every 30 seconds.
+	 */
+	if (time_after(jiffies, priv->last_update_stats_time + 30 * HZ)) {
+		hbg_update_stats(priv);
+		priv->last_update_stats_time = jiffies;
+	}
+
+	schedule_delayed_work(&priv->service_task,
+			      msecs_to_jiffies(MSEC_PER_SEC));
+}
+
+void hbg_err_reset_task_schedule(struct hbg_priv *priv)
+{
+	set_bit(HBG_NIC_STATE_NEED_RESET, &priv->state);
+	schedule_delayed_work(&priv->service_task, 0);
+}
+
+void hbg_np_link_fail_task_schedule(struct hbg_priv *priv)
+{
+	set_bit(HBG_NIC_STATE_NP_LINK_FAIL, &priv->state);
+	schedule_delayed_work(&priv->service_task, 0);
+}
+
+static void hbg_cancel_delayed_work_sync(void *data)
+{
+	cancel_delayed_work_sync(data);
+}
+
+static int hbg_delaywork_init(struct hbg_priv *priv)
+{
+	INIT_DELAYED_WORK(&priv->service_task, hbg_service_task);
+	schedule_delayed_work(&priv->service_task, 0);
+	return devm_add_action_or_reset(&priv->pdev->dev,
+					hbg_cancel_delayed_work_sync,
+					&priv->service_task);
+}
+
 static int hbg_mac_filter_init(struct hbg_priv *priv)
 {
 	struct hbg_dev_specs *dev_specs = &priv->dev_specs;
@@ -291,6 +387,10 @@ static int hbg_init(struct hbg_priv *priv)
 	if (ret)
 		return ret;
 
+	ret = hbg_delaywork_init(priv);
+	if (ret)
+		return ret;
+
 	hbg_debugfs_init(priv);
 	hbg_init_user_def(priv);
 	return 0;
@@ -317,7 +417,7 @@ static int hbg_pci_init(struct pci_dev *pdev)
 
 	priv->io_base = pcim_iomap_table(pdev)[0];
 	if (!priv->io_base)
-		return dev_err_probe(dev, -ENOMEM, "failed to get io base\n");
+		return -ENOMEM;
 
 	pci_set_master(pdev);
 	return 0;
@@ -349,6 +449,9 @@ static int hbg_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ret)
 		return ret;
 
+	/* set default features */
+	netdev->features |= HBG_SUPPORT_FEATURES;
+	netdev->hw_features |= HBG_SUPPORT_FEATURES;
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
 	netdev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
@@ -369,6 +472,22 @@ static int hbg_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 }
 
+static void hbg_shutdown(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+
+	rtnl_lock();
+	if (netif_running(netdev))
+		dev_close(netdev);
+	rtnl_unlock();
+
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+
+	if (system_state == SYSTEM_POWER_OFF)
+		pci_set_power_state(pdev, PCI_D3hot);
+}
+
 static const struct pci_device_id hbg_pci_tbl[] = {
 	{PCI_VDEVICE(HUAWEI, 0x3730), 0},
 	{ }
@@ -379,6 +498,7 @@ static struct pci_driver hbg_driver = {
 	.name		= "hibmcge",
 	.id_table	= hbg_pci_tbl,
 	.probe		= hbg_probe,
+	.shutdown	= hbg_shutdown,
 };
 
 static int __init hbg_module_init(void)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
index db6bc4cfb971..b6f0a2780ea8 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
@@ -2,6 +2,8 @@
 // Copyright (c) 2024 Hisilicon Limited.
 
 #include <linux/phy.h>
+#include <linux/phy_fixed.h>
+#include <linux/rtnetlink.h>
 #include "hbg_common.h"
 #include "hbg_hw.h"
 #include "hbg_mdio.h"
@@ -17,6 +19,8 @@
 #define HBG_MDIO_OP_TIMEOUT_US		(1 * 1000 * 1000)
 #define HBG_MDIO_OP_INTERVAL_US		(5 * 1000)
 
+#define HBG_NP_LINK_FAIL_RETRY_TIMES	5
+
 static void hbg_mdio_set_command(struct hbg_mac *mac, u32 cmd)
 {
 	hbg_reg_write(HBG_MAC_GET_PRIV(mac), HBG_REG_MDIO_COMMAND_ADDR, cmd);
@@ -127,6 +131,34 @@ static void hbg_flowctrl_cfg(struct hbg_priv *priv)
 	hbg_hw_set_pause_enable(priv, tx_pause, rx_pause);
 }
 
+void hbg_fix_np_link_fail(struct hbg_priv *priv)
+{
+	struct device *dev = &priv->pdev->dev;
+
+	rtnl_lock();
+
+	if (priv->stats.np_link_fail_cnt >= HBG_NP_LINK_FAIL_RETRY_TIMES) {
+		dev_err(dev, "failed to fix the MAC link status\n");
+		priv->stats.np_link_fail_cnt = 0;
+		goto unlock;
+	}
+
+	if (!priv->mac.phydev->link)
+		goto unlock;
+
+	priv->stats.np_link_fail_cnt++;
+	dev_err(dev, "failed to link between MAC and PHY, try to fix...\n");
+
+	/* Replace phy_reset() with phy_stop() and phy_start(),
+	 * as suggested by Andrew.
+	 */
+	hbg_phy_stop(priv);
+	hbg_phy_start(priv);
+
+unlock:
+	rtnl_unlock();
+}
+
 static void hbg_phy_adjust_link(struct net_device *netdev)
 {
 	struct hbg_priv *priv = netdev_priv(netdev);
@@ -198,6 +230,39 @@ void hbg_phy_stop(struct hbg_priv *priv)
 	phy_stop(priv->mac.phydev);
 }
 
+static void hbg_fixed_phy_uninit(void *data)
+{
+	fixed_phy_unregister((struct phy_device *)data);
+}
+
+static int hbg_fixed_phy_init(struct hbg_priv *priv)
+{
+	struct fixed_phy_status hbg_fixed_phy_status = {
+		.link = 1,
+		.speed = SPEED_1000,
+		.duplex = DUPLEX_FULL,
+		.pause = 1,
+		.asym_pause = 1,
+	};
+	struct device *dev = &priv->pdev->dev;
+	struct phy_device *phydev;
+	int ret;
+
+	phydev = fixed_phy_register(&hbg_fixed_phy_status, NULL);
+	if (IS_ERR(phydev)) {
+		dev_err_probe(dev, PTR_ERR(phydev),
+			      "failed to register fixed PHY device\n");
+		return PTR_ERR(phydev);
+	}
+
+	ret = devm_add_action_or_reset(dev, hbg_fixed_phy_uninit, phydev);
+	if (ret)
+		return ret;
+
+	priv->mac.phydev = phydev;
+	return hbg_phy_connect(priv);
+}
+
 int hbg_mdio_init(struct hbg_priv *priv)
 {
 	struct device *dev = &priv->pdev->dev;
@@ -207,10 +272,12 @@ int hbg_mdio_init(struct hbg_priv *priv)
 	int ret;
 
 	mac->phy_addr = priv->dev_specs.phy_addr;
+	if (mac->phy_addr == HBG_NO_PHY)
+		return hbg_fixed_phy_init(priv);
+
 	mdio_bus = devm_mdiobus_alloc(dev);
 	if (!mdio_bus)
-		return dev_err_probe(dev, -ENOMEM,
-				     "failed to alloc MDIO bus\n");
+		return -ENOMEM;
 
 	mdio_bus->parent = dev;
 	mdio_bus->priv = priv;
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.h
index febd02a309c7..f3771c1bbd34 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.h
@@ -9,4 +9,6 @@
 int hbg_mdio_init(struct hbg_priv *priv);
 void hbg_phy_start(struct hbg_priv *priv);
 void hbg_phy_stop(struct hbg_priv *priv);
+void hbg_fix_np_link_fail(struct hbg_priv *priv);
+
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
index f12efc12f3c5..30b3903c8f2d 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
@@ -18,6 +18,13 @@
 #define HBG_REG_TX_FIFO_NUM_ADDR		0x0030
 #define HBG_REG_RX_FIFO_NUM_ADDR		0x0034
 #define HBG_REG_VLAN_LAYERS_ADDR		0x0038
+#define HBG_REG_PUSH_REQ_ADDR			0x00F0
+#define HBG_REG_MSG_HEADER_ADDR			0x00F4
+#define HBG_REG_MSG_HEADER_OPCODE_M		GENMASK(7, 0)
+#define HBG_REG_MSG_HEADER_STATUS_M		GENMASK(11, 8)
+#define HBG_REG_MSG_HEADER_DATA_NUM_M		GENMASK(19, 12)
+#define HBG_REG_MSG_HEADER_RESP_CODE_M		GENMASK(27, 20)
+#define HBG_REG_MSG_DATA_BASE_ADDR		0x0100
 
 /* MDIO */
 #define HBG_REG_MDIO_BASE			0x8000
@@ -54,12 +61,56 @@
 #define HBG_REG_PAUSE_ENABLE_RX_B		BIT(0)
 #define HBG_REG_PAUSE_ENABLE_TX_B		BIT(1)
 #define HBG_REG_AN_NEG_STATE_ADDR		(HBG_REG_SGMII_BASE + 0x0058)
+#define HBG_REG_AN_NEG_STATE_NP_LINK_OK_B	BIT(15)
 #define HBG_REG_TRANSMIT_CTRL_ADDR		(HBG_REG_SGMII_BASE + 0x0060)
 #define HBG_REG_TRANSMIT_CTRL_PAD_EN_B		BIT(7)
 #define HBG_REG_TRANSMIT_CTRL_CRC_ADD_B		BIT(6)
 #define HBG_REG_TRANSMIT_CTRL_AN_EN_B		BIT(5)
 #define HBG_REG_REC_FILT_CTRL_ADDR		(HBG_REG_SGMII_BASE + 0x0064)
 #define HBG_REG_REC_FILT_CTRL_UC_MATCH_EN_B	BIT(0)
+#define HBG_REG_REC_FILT_CTRL_PAUSE_FRM_PASS_B	BIT(4)
+#define HBG_REG_RX_OCTETS_TOTAL_OK_ADDR		(HBG_REG_SGMII_BASE + 0x0080)
+#define HBG_REG_RX_OCTETS_BAD_ADDR		(HBG_REG_SGMII_BASE + 0x0084)
+#define HBG_REG_RX_UC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x0088)
+#define HBG_REG_RX_MC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x008C)
+#define HBG_REG_RX_BC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x0090)
+#define HBG_REG_RX_PKTS_64OCTETS_ADDR		(HBG_REG_SGMII_BASE + 0x0094)
+#define HBG_REG_RX_PKTS_65TO127OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0098)
+#define HBG_REG_RX_PKTS_128TO255OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x009C)
+#define HBG_REG_RX_PKTS_256TO511OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x00A0)
+#define HBG_REG_RX_PKTS_512TO1023OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x00A4)
+#define HBG_REG_RX_PKTS_1024TO1518OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x00A8)
+#define HBG_REG_RX_PKTS_1519TOMAXOCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x00AC)
+#define HBG_REG_RX_FCS_ERRORS_ADDR		(HBG_REG_SGMII_BASE + 0x00B0)
+#define HBG_REG_RX_TAGGED_ADDR			(HBG_REG_SGMII_BASE + 0x00B4)
+#define HBG_REG_RX_DATA_ERR_ADDR		(HBG_REG_SGMII_BASE + 0x00B8)
+#define HBG_REG_RX_ALIGN_ERRORS_ADDR		(HBG_REG_SGMII_BASE + 0x00BC)
+#define HBG_REG_RX_LONG_ERRORS_ADDR		(HBG_REG_SGMII_BASE + 0x00C0)
+#define HBG_REG_RX_JABBER_ERRORS_ADDR		(HBG_REG_SGMII_BASE + 0x00C4)
+#define HBG_REG_RX_PAUSE_MACCTL_FRAMCOUNTER_ADDR   (HBG_REG_SGMII_BASE + 0x00C8)
+#define HBG_REG_RX_UNKNOWN_MACCTL_FRAMCOUNTER_ADDR (HBG_REG_SGMII_BASE + 0x00CC)
+#define HBG_REG_RX_VERY_LONG_ERR_CNT_ADDR	(HBG_REG_SGMII_BASE + 0x00D0)
+#define HBG_REG_RX_RUNT_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x00D4)
+#define HBG_REG_RX_SHORT_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x00D8)
+#define HBG_REG_RX_FILT_PKT_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x00E8)
+#define HBG_REG_RX_OCTETS_TOTAL_FILT_ADDR	(HBG_REG_SGMII_BASE + 0x00EC)
+#define HBG_REG_OCTETS_TRANSMITTED_OK_ADDR	(HBG_REG_SGMII_BASE + 0x0100)
+#define HBG_REG_OCTETS_TRANSMITTED_BAD_ADDR	(HBG_REG_SGMII_BASE + 0x0104)
+#define HBG_REG_TX_UC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x0108)
+#define HBG_REG_TX_MC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x010C)
+#define HBG_REG_TX_BC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x0110)
+#define HBG_REG_TX_PKTS_64OCTETS_ADDR		(HBG_REG_SGMII_BASE + 0x0114)
+#define HBG_REG_TX_PKTS_65TO127OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0118)
+#define HBG_REG_TX_PKTS_128TO255OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x011C)
+#define HBG_REG_TX_PKTS_256TO511OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0120)
+#define HBG_REG_TX_PKTS_512TO1023OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0124)
+#define HBG_REG_TX_PKTS_1024TO1518OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0128)
+#define HBG_REG_TX_PKTS_1519TOMAXOCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x012C)
+#define HBG_REG_TX_EXCESSIVE_LENGTH_DROP_ADDR	(HBG_REG_SGMII_BASE + 0x014C)
+#define HBG_REG_TX_UNDERRUN_ADDR		(HBG_REG_SGMII_BASE + 0x0150)
+#define HBG_REG_TX_TAGGED_ADDR			(HBG_REG_SGMII_BASE + 0x0154)
+#define HBG_REG_TX_CRC_ERROR_ADDR		(HBG_REG_SGMII_BASE + 0x0158)
+#define HBG_REG_TX_PAUSE_FRAMES_ADDR		(HBG_REG_SGMII_BASE + 0x015C)
 #define HBG_REG_LINE_LOOP_BACK_ADDR		(HBG_REG_SGMII_BASE + 0x01A8)
 #define HBG_REG_CF_CRC_STRIP_ADDR		(HBG_REG_SGMII_BASE + 0x01B0)
 #define HBG_REG_CF_CRC_STRIP_B			BIT(0)
@@ -69,6 +120,9 @@
 #define HBG_REG_RECV_CTRL_ADDR			(HBG_REG_SGMII_BASE + 0x01E0)
 #define HBG_REG_RECV_CTRL_STRIP_PAD_EN_B	BIT(3)
 #define HBG_REG_VLAN_CODE_ADDR			(HBG_REG_SGMII_BASE + 0x01E8)
+#define HBG_REG_RX_OVERRUN_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x01EC)
+#define HBG_REG_RX_LENGTHFIELD_ERR_CNT_ADDR	(HBG_REG_SGMII_BASE + 0x01F4)
+#define HBG_REG_RX_FAIL_COMMA_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x01F8)
 #define HBG_REG_STATION_ADDR_LOW_0_ADDR		(HBG_REG_SGMII_BASE + 0x0200)
 #define HBG_REG_STATION_ADDR_HIGH_0_ADDR	(HBG_REG_SGMII_BASE + 0x0204)
 #define HBG_REG_STATION_ADDR_LOW_1_ADDR		(HBG_REG_SGMII_BASE + 0x0208)
@@ -81,11 +135,19 @@
 #define HBG_REG_STATION_ADDR_HIGH_4_ADDR	(HBG_REG_SGMII_BASE + 0x0224)
 #define HBG_REG_STATION_ADDR_LOW_5_ADDR		(HBG_REG_SGMII_BASE + 0x0228)
 #define HBG_REG_STATION_ADDR_HIGH_5_ADDR	(HBG_REG_SGMII_BASE + 0x022C)
+#define HBG_REG_STATION_ADDR_LOW_MSK_0		(HBG_REG_SGMII_BASE + 0x0230)
+#define HBG_REG_STATION_ADDR_LOW_MSK_1		(HBG_REG_SGMII_BASE + 0x0238)
 
 /* PCU */
 #define HBG_REG_TX_FIFO_THRSLD_ADDR		(HBG_REG_SGMII_BASE + 0x0420)
 #define HBG_REG_RX_FIFO_THRSLD_ADDR		(HBG_REG_SGMII_BASE + 0x0424)
+#define HBG_REG_FIFO_THRSLD_FULL_M		GENMASK(25, 16)
+#define HBG_REG_FIFO_THRSLD_EMPTY_M		GENMASK(9, 0)
 #define HBG_REG_CFG_FIFO_THRSLD_ADDR		(HBG_REG_SGMII_BASE + 0x0428)
+#define HBG_REG_CFG_FIFO_THRSLD_TX_FULL_M	GENMASK(31, 24)
+#define HBG_REG_CFG_FIFO_THRSLD_TX_EMPTY_M	GENMASK(23, 16)
+#define HBG_REG_CFG_FIFO_THRSLD_RX_FULL_M	GENMASK(15, 8)
+#define HBG_REG_CFG_FIFO_THRSLD_RX_EMPTY_M	GENMASK(7, 0)
 #define HBG_REG_CF_INTRPT_MSK_ADDR		(HBG_REG_SGMII_BASE + 0x042C)
 #define HBG_INT_MSK_WE_ERR_B			BIT(31)
 #define HBG_INT_MSK_RBREQ_ERR_B			BIT(30)
@@ -103,6 +165,7 @@
 #define HBG_INT_MSK_MAC_PCS_TX_FIFO_ERR_B	BIT(17)
 #define HBG_INT_MSK_MAC_PCS_RX_FIFO_ERR_B	BIT(16)
 #define HBG_INT_MSK_MAC_MII_FIFO_ERR_B		BIT(15)
+#define HBG_INT_MSK_TX_PKT_CPL_B		BIT(14)
 #define HBG_INT_MSK_TX_B			BIT(1) /* just used in driver */
 #define HBG_INT_MSK_RX_B			BIT(0) /* just used in driver */
 #define HBG_REG_CF_INTRPT_STAT_ADDR		(HBG_REG_SGMII_BASE + 0x0434)
@@ -111,18 +174,25 @@
 #define HBG_REG_RX_BUS_ERR_ADDR_ADDR		(HBG_REG_SGMII_BASE + 0x0440)
 #define HBG_REG_MAX_FRAME_LEN_ADDR		(HBG_REG_SGMII_BASE + 0x0444)
 #define HBG_REG_MAX_FRAME_LEN_M			GENMASK(15, 0)
+#define HBG_REG_TX_DROP_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0448)
+#define HBG_REG_RX_OVER_FLOW_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x044C)
 #define HBG_REG_DEBUG_ST_MCH_ADDR		(HBG_REG_SGMII_BASE + 0x0450)
 #define HBG_REG_FIFO_CURR_STATUS_ADDR		(HBG_REG_SGMII_BASE + 0x0454)
 #define HBG_REG_FIFO_HIST_STATUS_ADDR		(HBG_REG_SGMII_BASE + 0x0458)
 #define HBG_REG_CF_CFF_DATA_NUM_ADDR		(HBG_REG_SGMII_BASE + 0x045C)
 #define HBG_REG_CF_CFF_DATA_NUM_ADDR_TX_M	GENMASK(8, 0)
 #define HBG_REG_CF_CFF_DATA_NUM_ADDR_RX_M	GENMASK(24, 16)
+#define HBG_REG_TX_CS_FAIL_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0460)
+#define HBG_REG_RX_TRANS_PKG_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0464)
+#define HBG_REG_TX_TRANS_PKG_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0468)
 #define HBG_REG_CF_TX_PAUSE_ADDR		(HBG_REG_SGMII_BASE + 0x0470)
 #define HBG_REG_TX_CFF_ADDR_0_ADDR		(HBG_REG_SGMII_BASE + 0x0488)
 #define HBG_REG_TX_CFF_ADDR_1_ADDR		(HBG_REG_SGMII_BASE + 0x048C)
 #define HBG_REG_TX_CFF_ADDR_2_ADDR		(HBG_REG_SGMII_BASE + 0x0490)
 #define HBG_REG_TX_CFF_ADDR_3_ADDR		(HBG_REG_SGMII_BASE + 0x0494)
 #define HBG_REG_RX_CFF_ADDR_ADDR		(HBG_REG_SGMII_BASE + 0x04A0)
+#define HBG_REG_BRUST_LENGTH_ADDR		(HBG_REG_SGMII_BASE + 0x04C4)
+#define HBG_REG_BRUST_LENGTH_B			BIT(29)
 #define HBG_REG_RX_BUF_SIZE_ADDR		(HBG_REG_SGMII_BASE + 0x04E4)
 #define HBG_REG_RX_BUF_SIZE_M			GENMASK(15, 0)
 #define HBG_REG_BUS_CTRL_ADDR			(HBG_REG_SGMII_BASE + 0x04E8)
@@ -136,6 +206,9 @@
 #define HBG_REG_RX_CTRL_RXBUF_1ST_SKIP_SIZE2_M	GENMASK(3, 0)
 #define HBG_REG_RX_PKT_MODE_ADDR		(HBG_REG_SGMII_BASE + 0x04F4)
 #define HBG_REG_RX_PKT_MODE_PARSE_MODE_M	GENMASK(22, 21)
+#define HBG_REG_RX_BUFRQ_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x058C)
+#define HBG_REG_TX_BUFRL_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0590)
+#define HBG_REG_RX_WE_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0594)
 #define HBG_REG_DBG_ST0_ADDR			(HBG_REG_SGMII_BASE + 0x05E4)
 #define HBG_REG_DBG_ST1_ADDR			(HBG_REG_SGMII_BASE + 0x05E8)
 #define HBG_REG_DBG_ST2_ADDR			(HBG_REG_SGMII_BASE + 0x05EC)
@@ -178,5 +251,52 @@ struct hbg_rx_desc {
 };
 
 #define HBG_RX_DESC_W2_PKT_LEN_M	GENMASK(31, 16)
+#define HBG_RX_DESC_W2_PORT_NUM_M	GENMASK(15, 12)
+#define HBG_RX_DESC_W3_IP_OFFSET_M	GENMASK(23, 16)
+#define HBG_RX_DESC_W3_VLAN_M		GENMASK(15, 0)
+#define HBG_RX_DESC_W4_IP_TCP_UDP_M	GENMASK(31, 30)
+#define HBG_RX_DESC_W4_IPSEC_B		BIT(29)
+#define HBG_RX_DESC_W4_IP_VERSION_B	BIT(28)
+#define HBG_RX_DESC_W4_L4_ERR_CODE_M	GENMASK(26, 23)
+#define HBG_RX_DESC_W4_FRAG_B		BIT(22)
+#define HBG_RX_DESC_W4_OPT_B		BIT(21)
+#define HBG_RX_DESC_W4_IP_VERSION_ERR_B	BIT(20)
+#define HBG_RX_DESC_W4_BRD_CST_B	BIT(19)
+#define HBG_RX_DESC_W4_MUL_CST_B	BIT(18)
+#define HBG_RX_DESC_W4_ARP_B		BIT(17)
+#define HBG_RX_DESC_W4_RARP_B		BIT(16)
+#define HBG_RX_DESC_W4_ICMP_B		BIT(15)
+#define HBG_RX_DESC_W4_VLAN_FLAG_B	BIT(14)
+#define HBG_RX_DESC_W4_DROP_B		BIT(13)
+#define HBG_RX_DESC_W4_L3_ERR_CODE_M	GENMASK(12, 9)
+#define HBG_RX_DESC_W4_L2_ERR_B		BIT(8)
+#define HBG_RX_DESC_W4_IDX_MATCH_B	BIT(7)
+#define HBG_RX_DESC_W4_PARSE_MODE_M	GENMASK(6, 5)
+#define HBG_RX_DESC_W5_VALID_SIZE_M	GENMASK(15, 0)
+
+enum hbg_l3_err_code {
+	HBG_L3_OK = 0,
+	HBG_L3_WRONG_HEAD,
+	HBG_L3_CSUM_ERR,
+	HBG_L3_LEN_ERR,
+	HBG_L3_ZERO_TTL,
+	HBG_L3_RSVD,
+};
+
+enum hbg_l4_err_code {
+	HBG_L4_OK = 0,
+	HBG_L4_WRONG_HEAD,
+	HBG_L4_LEN_ERR,
+	HBG_L4_CSUM_ERR,
+	HBG_L4_ZERO_PORT_NUM,
+	HBG_L4_RSVD,
+};
+
+enum hbg_pkt_type_code {
+	HBG_NO_IP_PKT = 0,
+	HBG_IP_PKT,
+	HBG_TCP_PKT,
+	HBG_UDP_PKT,
+};
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_trace.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_trace.h
new file mode 100644
index 000000000000..b70fd960da8d
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_trace.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2025 Hisilicon Limited. */
+
+/* This must be outside ifdef _HBG_TRACE_H */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM hibmcge
+
+#if !defined(_HBG_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _HBG_TRACE_H_
+
+#include <linux/bitfield.h>
+#include <linux/pci.h>
+#include <linux/tracepoint.h>
+#include <linux/types.h>
+#include "hbg_reg.h"
+
+TRACE_EVENT(hbg_rx_desc,
+	    TP_PROTO(struct hbg_priv *priv, u32 index,
+		     struct hbg_rx_desc *rx_desc),
+	    TP_ARGS(priv, index, rx_desc),
+
+	    TP_STRUCT__entry(__field(u32, index)
+			     __field(u8, port_num)
+			     __field(u8, ip_offset)
+			     __field(u8, parse_mode)
+			     __field(u8, l4_error_code)
+			     __field(u8, l3_error_code)
+			     __field(u8, l2_error_code)
+			     __field(u16, packet_len)
+			     __field(u16, valid_size)
+			     __field(u16, vlan)
+			     __string(pciname, pci_name(priv->pdev))
+			     __string(devname, priv->netdev->name)
+	    ),
+
+	    TP_fast_assign(__entry->index = index,
+			   __entry->packet_len =
+				FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M,
+					  rx_desc->word2);
+			   __entry->port_num =
+				FIELD_GET(HBG_RX_DESC_W2_PORT_NUM_M,
+					  rx_desc->word2);
+			   __entry->ip_offset =
+				FIELD_GET(HBG_RX_DESC_W3_IP_OFFSET_M,
+					  rx_desc->word3);
+			   __entry->vlan =
+				FIELD_GET(HBG_RX_DESC_W3_VLAN_M,
+					  rx_desc->word3);
+			   __entry->parse_mode =
+				FIELD_GET(HBG_RX_DESC_W4_PARSE_MODE_M,
+					  rx_desc->word4);
+			   __entry->l4_error_code =
+				FIELD_GET(HBG_RX_DESC_W4_L4_ERR_CODE_M,
+					  rx_desc->word4);
+			   __entry->l3_error_code =
+				FIELD_GET(HBG_RX_DESC_W4_L3_ERR_CODE_M,
+					  rx_desc->word4);
+			   __entry->l2_error_code =
+				FIELD_GET(HBG_RX_DESC_W4_L2_ERR_B,
+					  rx_desc->word4);
+			   __entry->valid_size =
+				FIELD_GET(HBG_RX_DESC_W5_VALID_SIZE_M,
+					  rx_desc->word5);
+			   __assign_str(pciname);
+			   __assign_str(devname);
+	    ),
+
+	    TP_printk("%s %s index:%u, port num:%u, len:%u, valid size:%u, ip_offset:%u, vlan:0x%04x, parse mode:%u, l4_err:0x%x, l3_err:0x%x, l2_err:0x%x",
+		      __get_str(pciname), __get_str(devname), __entry->index,
+		      __entry->port_num, __entry->packet_len,
+		      __entry->valid_size, __entry->ip_offset,  __entry->vlan,
+		      __entry->parse_mode, __entry->l4_error_code,
+		      __entry->l3_error_code, __entry->l2_error_code
+	    )
+);
+
+#endif /* _HBG_TRACE_H_ */
+
+/* This must be outside ifdef _HBG_TRACE_H */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE hbg_trace
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
index f4f256a0dfea..a4ea92c31c2f 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
@@ -7,6 +7,9 @@
 #include "hbg_reg.h"
 #include "hbg_txrx.h"
 
+#define CREATE_TRACE_POINTS
+#include "hbg_trace.h"
+
 #define netdev_get_tx_ring(netdev) \
 			(&(((struct hbg_priv *)netdev_priv(netdev))->tx_ring))
 
@@ -28,6 +31,11 @@
 	typeof(ring) _ring = (ring); \
 	_ring->p = hbg_queue_next_prt(_ring->p, _ring); })
 
+#define hbg_get_page_order(ring) ({ \
+	typeof(ring) _ring = (ring); \
+	get_order(hbg_spec_max_frame_len(_ring->priv, _ring->dir)); })
+#define hbg_get_page_size(ring) (PAGE_SIZE << hbg_get_page_order((ring)))
+
 #define HBG_TX_STOP_THRS	2
 #define HBG_TX_START_THRS	(2 * HBG_TX_STOP_THRS)
 
@@ -38,8 +46,14 @@ static int hbg_dma_map(struct hbg_buffer *buffer)
 	buffer->skb_dma = dma_map_single(&priv->pdev->dev,
 					 buffer->skb->data, buffer->skb_len,
 					 buffer_to_dma_dir(buffer));
-	if (unlikely(dma_mapping_error(&priv->pdev->dev, buffer->skb_dma)))
+	if (unlikely(dma_mapping_error(&priv->pdev->dev, buffer->skb_dma))) {
+		if (buffer->dir == HBG_DIR_RX)
+			priv->stats.rx_dma_err_cnt++;
+		else
+			priv->stats.tx_dma_err_cnt++;
+
 		return -ENOMEM;
+	}
 
 	return 0;
 }
@@ -56,6 +70,43 @@ static void hbg_dma_unmap(struct hbg_buffer *buffer)
 	buffer->skb_dma = 0;
 }
 
+static void hbg_buffer_free_page(struct hbg_buffer *buffer)
+{
+	struct hbg_ring *ring = buffer->ring;
+
+	if (unlikely(!buffer->page))
+		return;
+
+	page_pool_put_full_page(ring->page_pool, buffer->page, false);
+
+	buffer->page = NULL;
+	buffer->page_dma = 0;
+	buffer->page_addr = NULL;
+	buffer->page_size = 0;
+	buffer->page_offset = 0;
+}
+
+static int hbg_buffer_alloc_page(struct hbg_buffer *buffer)
+{
+	struct hbg_ring *ring = buffer->ring;
+	u32 len = hbg_get_page_size(ring);
+	u32 offset;
+
+	if (unlikely(!ring->page_pool))
+		return 0;
+
+	buffer->page = page_pool_dev_alloc_frag(ring->page_pool, &offset, len);
+	if (unlikely(!buffer->page))
+		return -ENOMEM;
+
+	buffer->page_dma = page_pool_get_dma_addr(buffer->page) + offset;
+	buffer->page_addr = page_address(buffer->page) + offset;
+	buffer->page_size = len;
+	buffer->page_offset = offset;
+
+	return 0;
+}
+
 static void hbg_init_tx_desc(struct hbg_buffer *buffer,
 			     struct hbg_tx_desc *tx_desc)
 {
@@ -129,24 +180,14 @@ static void hbg_buffer_free_skb(struct hbg_buffer *buffer)
 	buffer->skb = NULL;
 }
 
-static int hbg_buffer_alloc_skb(struct hbg_buffer *buffer)
-{
-	u32 len = hbg_spec_max_frame_len(buffer->priv, buffer->dir);
-	struct hbg_priv *priv = buffer->priv;
-
-	buffer->skb = netdev_alloc_skb(priv->netdev, len);
-	if (unlikely(!buffer->skb))
-		return -ENOMEM;
-
-	buffer->skb_len = len;
-	memset(buffer->skb->data, 0, HBG_PACKET_HEAD_SIZE);
-	return 0;
-}
-
 static void hbg_buffer_free(struct hbg_buffer *buffer)
 {
-	hbg_dma_unmap(buffer);
-	hbg_buffer_free_skb(buffer);
+	if (buffer->skb) {
+		hbg_dma_unmap(buffer);
+		return hbg_buffer_free_skb(buffer);
+	}
+
+	hbg_buffer_free_page(buffer);
 }
 
 static int hbg_napi_tx_recycle(struct napi_struct *napi, int budget)
@@ -195,31 +236,217 @@ static int hbg_napi_tx_recycle(struct napi_struct *napi, int budget)
 	return packet_done;
 }
 
+static bool hbg_rx_check_l3l4_error(struct hbg_priv *priv,
+				    struct hbg_rx_desc *desc,
+				    struct sk_buff *skb)
+{
+	bool rx_checksum_offload = !!(priv->netdev->features & NETIF_F_RXCSUM);
+
+	skb->ip_summed = rx_checksum_offload ?
+			 CHECKSUM_UNNECESSARY : CHECKSUM_NONE;
+
+	if (likely(!FIELD_GET(HBG_RX_DESC_W4_L3_ERR_CODE_M, desc->word4) &&
+		   !FIELD_GET(HBG_RX_DESC_W4_L4_ERR_CODE_M, desc->word4)))
+		return true;
+
+	switch (FIELD_GET(HBG_RX_DESC_W4_L3_ERR_CODE_M, desc->word4)) {
+	case HBG_L3_OK:
+		break;
+	case HBG_L3_WRONG_HEAD:
+		priv->stats.rx_desc_l3_wrong_head_cnt++;
+		return false;
+	case HBG_L3_CSUM_ERR:
+		skb->ip_summed = CHECKSUM_NONE;
+		priv->stats.rx_desc_l3_csum_err_cnt++;
+
+		/* Don't drop packets on csum validation failure,
+		 * suggest by Jakub
+		 */
+		break;
+	case HBG_L3_LEN_ERR:
+		priv->stats.rx_desc_l3_len_err_cnt++;
+		return false;
+	case HBG_L3_ZERO_TTL:
+		priv->stats.rx_desc_l3_zero_ttl_cnt++;
+		return false;
+	default:
+		priv->stats.rx_desc_l3_other_cnt++;
+		return false;
+	}
+
+	switch (FIELD_GET(HBG_RX_DESC_W4_L4_ERR_CODE_M, desc->word4)) {
+	case HBG_L4_OK:
+		break;
+	case HBG_L4_WRONG_HEAD:
+		priv->stats.rx_desc_l4_wrong_head_cnt++;
+		return false;
+	case HBG_L4_LEN_ERR:
+		priv->stats.rx_desc_l4_len_err_cnt++;
+		return false;
+	case HBG_L4_CSUM_ERR:
+		skb->ip_summed = CHECKSUM_NONE;
+		priv->stats.rx_desc_l4_csum_err_cnt++;
+
+		/* Don't drop packets on csum validation failure,
+		 * suggest by Jakub
+		 */
+		break;
+	case HBG_L4_ZERO_PORT_NUM:
+		priv->stats.rx_desc_l4_zero_port_num_cnt++;
+		return false;
+	default:
+		priv->stats.rx_desc_l4_other_cnt++;
+		return false;
+	}
+
+	return true;
+}
+
+static void hbg_update_rx_ip_protocol_stats(struct hbg_priv *priv,
+					    struct hbg_rx_desc *desc)
+{
+	if (unlikely(!FIELD_GET(HBG_RX_DESC_W4_IP_TCP_UDP_M, desc->word4))) {
+		priv->stats.rx_desc_no_ip_pkt_cnt++;
+		return;
+	}
+
+	if (unlikely(FIELD_GET(HBG_RX_DESC_W4_IP_VERSION_ERR_B, desc->word4))) {
+		priv->stats.rx_desc_ip_ver_err_cnt++;
+		return;
+	}
+
+	/* 0:ipv4, 1:ipv6 */
+	if (FIELD_GET(HBG_RX_DESC_W4_IP_VERSION_B, desc->word4))
+		priv->stats.rx_desc_ipv6_pkt_cnt++;
+	else
+		priv->stats.rx_desc_ipv4_pkt_cnt++;
+
+	switch (FIELD_GET(HBG_RX_DESC_W4_IP_TCP_UDP_M, desc->word4)) {
+	case HBG_IP_PKT:
+		priv->stats.rx_desc_ip_pkt_cnt++;
+		if (FIELD_GET(HBG_RX_DESC_W4_OPT_B, desc->word4))
+			priv->stats.rx_desc_ip_opt_pkt_cnt++;
+		if (FIELD_GET(HBG_RX_DESC_W4_FRAG_B, desc->word4))
+			priv->stats.rx_desc_frag_cnt++;
+
+		if (FIELD_GET(HBG_RX_DESC_W4_ICMP_B, desc->word4))
+			priv->stats.rx_desc_icmp_pkt_cnt++;
+		else if (FIELD_GET(HBG_RX_DESC_W4_IPSEC_B, desc->word4))
+			priv->stats.rx_desc_ipsec_pkt_cnt++;
+		break;
+	case HBG_TCP_PKT:
+		priv->stats.rx_desc_tcp_pkt_cnt++;
+		break;
+	case HBG_UDP_PKT:
+		priv->stats.rx_desc_udp_pkt_cnt++;
+		break;
+	default:
+		priv->stats.rx_desc_no_ip_pkt_cnt++;
+		break;
+	}
+}
+
+static void hbg_update_rx_protocol_stats(struct hbg_priv *priv,
+					 struct hbg_rx_desc *desc)
+{
+	if (unlikely(!FIELD_GET(HBG_RX_DESC_W4_IDX_MATCH_B, desc->word4))) {
+		priv->stats.rx_desc_key_not_match_cnt++;
+		return;
+	}
+
+	if (FIELD_GET(HBG_RX_DESC_W4_BRD_CST_B, desc->word4))
+		priv->stats.rx_desc_broadcast_pkt_cnt++;
+	else if (FIELD_GET(HBG_RX_DESC_W4_MUL_CST_B, desc->word4))
+		priv->stats.rx_desc_multicast_pkt_cnt++;
+
+	if (FIELD_GET(HBG_RX_DESC_W4_VLAN_FLAG_B, desc->word4))
+		priv->stats.rx_desc_vlan_pkt_cnt++;
+
+	if (FIELD_GET(HBG_RX_DESC_W4_ARP_B, desc->word4)) {
+		priv->stats.rx_desc_arp_pkt_cnt++;
+		return;
+	} else if (FIELD_GET(HBG_RX_DESC_W4_RARP_B, desc->word4)) {
+		priv->stats.rx_desc_rarp_pkt_cnt++;
+		return;
+	}
+
+	hbg_update_rx_ip_protocol_stats(priv, desc);
+}
+
+static bool hbg_rx_pkt_check(struct hbg_priv *priv, struct hbg_rx_desc *desc,
+			     struct sk_buff *skb)
+{
+	if (unlikely(FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, desc->word2) >
+		     priv->dev_specs.max_frame_len)) {
+		priv->stats.rx_desc_pkt_len_err_cnt++;
+		return false;
+	}
+
+	if (unlikely(FIELD_GET(HBG_RX_DESC_W2_PORT_NUM_M, desc->word2) !=
+		     priv->dev_specs.mac_id ||
+		     FIELD_GET(HBG_RX_DESC_W4_DROP_B, desc->word4))) {
+		priv->stats.rx_desc_drop++;
+		return false;
+	}
+
+	if (unlikely(FIELD_GET(HBG_RX_DESC_W4_L2_ERR_B, desc->word4))) {
+		priv->stats.rx_desc_l2_err_cnt++;
+		return false;
+	}
+
+	if (unlikely(!hbg_rx_check_l3l4_error(priv, desc, skb))) {
+		priv->stats.rx_desc_l3l4_err_cnt++;
+		return false;
+	}
+
+	hbg_update_rx_protocol_stats(priv, desc);
+	return true;
+}
+
 static int hbg_rx_fill_one_buffer(struct hbg_priv *priv)
 {
 	struct hbg_ring *ring = &priv->rx_ring;
 	struct hbg_buffer *buffer;
 	int ret;
 
-	if (hbg_queue_is_full(ring->ntc, ring->ntu, ring))
+	if (hbg_queue_is_full(ring->ntc, ring->ntu, ring) ||
+	    hbg_fifo_is_full(priv, ring->dir))
 		return 0;
 
 	buffer = &ring->queue[ring->ntu];
-	ret = hbg_buffer_alloc_skb(buffer);
+	ret = hbg_buffer_alloc_page(buffer);
 	if (unlikely(ret))
 		return ret;
 
-	ret = hbg_dma_map(buffer);
-	if (unlikely(ret)) {
-		hbg_buffer_free_skb(buffer);
-		return ret;
-	}
+	memset(buffer->page_addr, 0, HBG_PACKET_HEAD_SIZE);
+	dma_sync_single_for_device(&priv->pdev->dev, buffer->page_dma,
+				   HBG_PACKET_HEAD_SIZE, DMA_TO_DEVICE);
 
-	hbg_hw_fill_buffer(priv, buffer->skb_dma);
+	hbg_hw_fill_buffer(priv, buffer->page_dma);
 	hbg_queue_move_next(ntu, ring);
 	return 0;
 }
 
+static int hbg_rx_fill_buffers(struct hbg_priv *priv)
+{
+	u32 remained = hbg_hw_get_fifo_used_num(priv, HBG_DIR_RX);
+	u32 max_count = priv->dev_specs.rx_fifo_num;
+	u32 refill_count;
+	int ret;
+
+	if (unlikely(remained >= max_count))
+		return 0;
+
+	refill_count = max_count - remained;
+	while (refill_count--) {
+		ret = hbg_rx_fill_one_buffer(priv);
+		if (unlikely(ret))
+			break;
+	}
+
+	return ret;
+}
+
 static bool hbg_sync_data_from_hw(struct hbg_priv *priv,
 				  struct hbg_buffer *buffer)
 {
@@ -228,13 +455,29 @@ static bool hbg_sync_data_from_hw(struct hbg_priv *priv,
 	/* make sure HW write desc complete */
 	dma_rmb();
 
-	dma_sync_single_for_cpu(&priv->pdev->dev, buffer->skb_dma,
-				buffer->skb_len, DMA_FROM_DEVICE);
+	dma_sync_single_for_cpu(&priv->pdev->dev, buffer->page_dma,
+				buffer->page_size, DMA_FROM_DEVICE);
 
-	rx_desc = (struct hbg_rx_desc *)buffer->skb->data;
+	rx_desc = (struct hbg_rx_desc *)buffer->page_addr;
 	return FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, rx_desc->word2) != 0;
 }
 
+static int hbg_build_skb(struct hbg_priv *priv,
+			 struct hbg_buffer *buffer, u32 pkt_len)
+{
+	net_prefetch(buffer->page_addr);
+
+	buffer->skb = napi_build_skb(buffer->page_addr, buffer->page_size);
+	if (unlikely(!buffer->skb))
+		return -ENOMEM;
+	skb_mark_for_recycle(buffer->skb);
+
+	/* page will be freed together with the skb */
+	buffer->page = NULL;
+
+	return 0;
+}
+
 static int hbg_napi_rx_poll(struct napi_struct *napi, int budget)
 {
 	struct hbg_ring *ring = container_of(napi, struct hbg_ring, napi);
@@ -244,29 +487,39 @@ static int hbg_napi_rx_poll(struct napi_struct *napi, int budget)
 	u32 packet_done = 0;
 	u32 pkt_len;
 
+	hbg_rx_fill_buffers(priv);
 	while (packet_done < budget) {
 		if (unlikely(hbg_queue_is_empty(ring->ntc, ring->ntu, ring)))
 			break;
 
 		buffer = &ring->queue[ring->ntc];
-		if (unlikely(!buffer->skb))
+		if (unlikely(!buffer->page))
 			goto next_buffer;
 
 		if (unlikely(!hbg_sync_data_from_hw(priv, buffer)))
 			break;
-		rx_desc = (struct hbg_rx_desc *)buffer->skb->data;
+		rx_desc = (struct hbg_rx_desc *)buffer->page_addr;
 		pkt_len = FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, rx_desc->word2);
+		trace_hbg_rx_desc(priv, ring->ntc, rx_desc);
 
-		hbg_dma_unmap(buffer);
+		if (unlikely(hbg_build_skb(priv, buffer, pkt_len))) {
+			hbg_buffer_free_page(buffer);
+			goto next_buffer;
+		}
+
+		if (unlikely(!hbg_rx_pkt_check(priv, rx_desc, buffer->skb))) {
+			hbg_buffer_free_skb(buffer);
+			goto next_buffer;
+		}
 
 		skb_reserve(buffer->skb, HBG_PACKET_HEAD_SIZE + NET_IP_ALIGN);
 		skb_put(buffer->skb, pkt_len);
 		buffer->skb->protocol = eth_type_trans(buffer->skb,
 						       priv->netdev);
-
 		dev_sw_netstats_rx_add(priv->netdev, pkt_len);
 		napi_gro_receive(napi, buffer->skb);
 		buffer->skb = NULL;
+		buffer->page = NULL;
 
 next_buffer:
 		hbg_rx_fill_one_buffer(priv);
@@ -281,6 +534,42 @@ next_buffer:
 	return packet_done;
 }
 
+static void hbg_ring_page_pool_destory(struct hbg_ring *ring)
+{
+	if (!ring->page_pool)
+		return;
+
+	page_pool_destroy(ring->page_pool);
+	ring->page_pool = NULL;
+}
+
+static int hbg_ring_page_pool_init(struct hbg_priv *priv, struct hbg_ring *ring)
+{
+	u32 buf_size = hbg_spec_max_frame_len(priv, ring->dir);
+	struct page_pool_params pp_params = {
+		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
+		.order = hbg_get_page_order(ring),
+		.pool_size = ring->len * buf_size / hbg_get_page_size(ring),
+		.nid = dev_to_node(&priv->pdev->dev),
+		.dev = &priv->pdev->dev,
+		.napi = &ring->napi,
+		.dma_dir = DMA_FROM_DEVICE,
+		.offset = 0,
+		.max_len = hbg_get_page_size(ring),
+	};
+	int ret = 0;
+
+	ring->page_pool = page_pool_create(&pp_params);
+	if (IS_ERR(ring->page_pool)) {
+		ret = PTR_ERR(ring->page_pool);
+		dev_err(&priv->pdev->dev,
+			"failed to create page pool, ret = %d\n", ret);
+		ring->page_pool = NULL;
+	}
+
+	return ret;
+}
+
 static void hbg_ring_uninit(struct hbg_ring *ring)
 {
 	struct hbg_buffer *buffer;
@@ -299,6 +588,7 @@ static void hbg_ring_uninit(struct hbg_ring *ring)
 		buffer->priv = NULL;
 	}
 
+	hbg_ring_page_pool_destory(ring);
 	dma_free_coherent(&ring->priv->pdev->dev,
 			  ring->len * sizeof(*ring->queue),
 			  ring->queue, ring->queue_dma);
@@ -314,8 +604,19 @@ static int hbg_ring_init(struct hbg_priv *priv, struct hbg_ring *ring,
 {
 	struct hbg_buffer *buffer;
 	u32 i, len;
+	int ret;
 
 	len = hbg_get_spec_fifo_max_num(priv, dir) + 1;
+	/* To improve receiving performance under high-stress scenarios,
+	 * in the `hbg_napi_rx_poll()`, we first use the other half of
+	 * the buffer to receive packets from the hardware via the
+	 * `hbg_rx_fill_buffers()`, and then process the packets in the
+	 * original half of the buffer to avoid packet loss caused by
+	 * hardware overflow as much as possible.
+	 */
+	if (dir == HBG_DIR_RX)
+		len += hbg_get_spec_fifo_max_num(priv, dir);
+
 	ring->queue = dma_alloc_coherent(&priv->pdev->dev,
 					 len * sizeof(*ring->queue),
 					 &ring->queue_dma, GFP_KERNEL);
@@ -337,11 +638,23 @@ static int hbg_ring_init(struct hbg_priv *priv, struct hbg_ring *ring,
 	ring->ntu = 0;
 	ring->len = len;
 
-	if (dir == HBG_DIR_TX)
+	if (dir == HBG_DIR_TX) {
 		netif_napi_add_tx(priv->netdev, &ring->napi, napi_poll);
-	else
+	} else {
 		netif_napi_add(priv->netdev, &ring->napi, napi_poll);
 
+		ret = hbg_ring_page_pool_init(priv, ring);
+		if (ret) {
+			netif_napi_del(&ring->napi);
+			dma_free_coherent(&ring->priv->pdev->dev,
+					  ring->len * sizeof(*ring->queue),
+					  ring->queue, ring->queue_dma);
+			ring->queue = NULL;
+			ring->len = 0;
+			return ret;
+		}
+	}
+
 	napi_enable(&ring->napi);
 	return 0;
 }
@@ -364,21 +677,16 @@ static int hbg_tx_ring_init(struct hbg_priv *priv)
 static int hbg_rx_ring_init(struct hbg_priv *priv)
 {
 	int ret;
-	u32 i;
 
 	ret = hbg_ring_init(priv, &priv->rx_ring, hbg_napi_rx_poll, HBG_DIR_RX);
 	if (ret)
 		return ret;
 
-	for (i = 0; i < priv->rx_ring.len - 1; i++) {
-		ret = hbg_rx_fill_one_buffer(priv);
-		if (ret) {
-			hbg_ring_uninit(&priv->rx_ring);
-			return ret;
-		}
-	}
+	ret = hbg_rx_fill_buffers(priv);
+	if (ret)
+		hbg_ring_uninit(&priv->rx_ring);
 
-	return 0;
+	return ret;
 }
 
 int hbg_txrx_init(struct hbg_priv *priv)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h
index 2883a5899ae2..8b6110599e10 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h
@@ -29,7 +29,12 @@ static inline bool hbg_fifo_is_full(struct hbg_priv *priv, enum hbg_dir dir)
 
 static inline u32 hbg_get_queue_used_num(struct hbg_ring *ring)
 {
-	return (ring->ntu + ring->len - ring->ntc) % ring->len;
+	u32 len = READ_ONCE(ring->len);
+
+	if (!len)
+		return 0;
+
+	return (READ_ONCE(ring->ntu) + len - READ_ONCE(ring->ntc)) % len;
 }
 
 netdev_tx_t hbg_net_start_xmit(struct sk_buff *skb, struct net_device *netdev);
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index a376d4bdf281..18376bcc718a 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -934,8 +934,6 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	priv->chan = arg.args[1] * RX_DESC_NUM;
 	priv->group = arg.args[2];
 
-	hrtimer_init(&priv->tx_coalesce_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-
 	/* BQL will try to keep the TX queue as short as possible, but it can't
 	 * be faster than tx_coalesce_usecs, so we need a fast timeout here,
 	 * but also long enough to gather up enough frames to ensure we don't
@@ -944,7 +942,7 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	 */
 	priv->tx_coalesce_frames = TX_DESC_NUM * 3 / 4;
 	priv->tx_coalesce_usecs = 200;
-	priv->tx_coalesce_timer.function = tx_done;
+	hrtimer_setup(&priv->tx_coalesce_timer, tx_done, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 	priv->map = syscon_node_to_regmap(arg.np);
 	of_node_put(arg.np);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 42bb341fd80b..e905f10b894e 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -1402,7 +1402,7 @@ static void hns_nic_net_down(struct net_device *ndev)
 	if (test_and_set_bit(NIC_STATE_DOWN, &priv->state))
 		return;
 
-	(void)del_timer_sync(&priv->service_timer);
+	(void) timer_delete_sync(&priv->service_timer);
 	netif_tx_stop_all_queues(ndev);
 	netif_carrier_off(ndev);
 	netif_tx_disable(ndev);
@@ -2075,7 +2075,7 @@ static void hns_nic_task_schedule(struct hns_nic_priv *priv)
 
 static void hns_nic_service_timer(struct timer_list *t)
 {
-	struct hns_nic_priv *priv = from_timer(priv, t, service_timer);
+	struct hns_nic_priv *priv = timer_container_of(priv, t, service_timer);
 
 	(void)mod_timer(&priv->service_timer, jiffies + SERVICE_TIMER_HZ);
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 6c458f037262..60a586a951a0 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -266,9 +266,9 @@ static int hns_nic_config_phy_loopback(struct phy_device *phy_dev, u8 en)
 		if (err)
 			goto out;
 
-		err = phy_loopback(phy_dev, true);
+		err = phy_loopback(phy_dev, true, 0);
 	} else {
-		err = phy_loopback(phy_dev, false);
+		err = phy_loopback(phy_dev, false, 0);
 		if (err)
 			goto out;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index 9a63fbc69408..b25fb400f476 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -40,6 +40,21 @@ EXPORT_SYMBOL(hnae3_unregister_ae_algo_prepare);
  */
 static DEFINE_MUTEX(hnae3_common_lock);
 
+/* ensure the drivers being unloaded one by one */
+static DEFINE_MUTEX(hnae3_unload_lock);
+
+void hnae3_acquire_unload_lock(void)
+{
+	mutex_lock(&hnae3_unload_lock);
+}
+EXPORT_SYMBOL(hnae3_acquire_unload_lock);
+
+void hnae3_release_unload_lock(void)
+{
+	mutex_unlock(&hnae3_unload_lock);
+}
+EXPORT_SYMBOL(hnae3_release_unload_lock);
+
 static bool hnae3_client_match(enum hnae3_client_type client_type)
 {
 	if (client_type == HNAE3_CLIENT_KNIC ||
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 710a8f9f2248..d7c3df1958f3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -339,6 +339,10 @@ enum hnae3_dbg_cmd {
 	HNAE3_DBG_CMD_UNKNOWN,
 };
 
+#define hnae3_seq_file_to_ae_dev(s)	(dev_get_drvdata((s)->private))
+#define hnae3_seq_file_to_handle(s)	\
+		(((struct hnae3_ae_dev *)hnae3_seq_file_to_ae_dev(s))->handle)
+
 enum hnae3_tc_map_mode {
 	HNAE3_TC_MAP_MODE_PRIO,
 	HNAE3_TC_MAP_MODE_DSCP,
@@ -434,8 +438,11 @@ struct hnae3_ae_dev {
 	u32 dev_version;
 	DECLARE_BITMAP(caps, HNAE3_DEV_CAPS_MAX_NUM);
 	void *priv;
+	struct hnae3_handle *handle;
 };
 
+typedef int (*read_func)(struct seq_file *s, void *data);
+
 /* This struct defines the operation on the handle.
  *
  * init_ae_dev(): (mandatory)
@@ -580,8 +587,6 @@ struct hnae3_ae_dev {
  *   Delete clsflower rule
  * cls_flower_active
  *   Check if any cls flower rule exist
- * dbg_read_cmd
- *   Execute debugfs read command.
  * set_tx_hwts_info
  *   Save information for 1588 tx packet
  * get_rx_hwts
@@ -594,6 +599,8 @@ struct hnae3_ae_dev {
  *   Get wake on lan info
  * set_wol
  *   Config wake on lan
+ * dbg_get_read_func
+ *   Return the read func for debugfs seq file
  */
 struct hnae3_ae_ops {
 	int (*init_ae_dev)(struct hnae3_ae_dev *ae_dev);
@@ -690,9 +697,9 @@ struct hnae3_ae_ops {
 	int (*set_rss)(struct hnae3_handle *handle, const u32 *indir,
 		       const u8 *key, const u8 hfunc);
 	int (*set_rss_tuple)(struct hnae3_handle *handle,
-			     struct ethtool_rxnfc *cmd);
+			     const struct ethtool_rxfh_fields *cmd);
 	int (*get_rss_tuple)(struct hnae3_handle *handle,
-			     struct ethtool_rxnfc *cmd);
+			     struct ethtool_rxfh_fields *cmd);
 
 	int (*get_tc_size)(struct hnae3_handle *handle);
 
@@ -748,8 +755,6 @@ struct hnae3_ae_ops {
 	void (*enable_fd)(struct hnae3_handle *handle, bool enable);
 	int (*add_arfs_entry)(struct hnae3_handle *handle, u16 queue_id,
 			      u16 flow_id, struct flow_keys *fkeys);
-	int (*dbg_read_cmd)(struct hnae3_handle *handle, enum hnae3_dbg_cmd cmd,
-			    char *buf, int len);
 	pci_ers_result_t (*handle_hw_ras_error)(struct hnae3_ae_dev *ae_dev);
 	bool (*get_hw_reset_stat)(struct hnae3_handle *handle);
 	bool (*ae_dev_resetting)(struct hnae3_handle *handle);
@@ -796,6 +801,14 @@ struct hnae3_ae_ops {
 			struct ethtool_wolinfo *wol);
 	int (*set_wol)(struct hnae3_handle *handle,
 		       struct ethtool_wolinfo *wol);
+	int (*dbg_get_read_func)(struct hnae3_handle *handle,
+				 enum hnae3_dbg_cmd cmd,
+				 read_func *func);
+	int (*hwtstamp_get)(struct hnae3_handle *handle,
+			    struct kernel_hwtstamp_config *config);
+	int (*hwtstamp_set)(struct hnae3_handle *handle,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack);
 };
 
 struct hnae3_dcb_ops {
@@ -916,9 +929,6 @@ struct hnae3_handle {
 
 	u8 netdev_flags;
 	struct dentry *hnae3_dbgfs;
-	/* protects concurrent contention between debugfs commands */
-	struct mutex dbgfs_lock;
-	char **dbgfs_buf;
 
 	/* Network interface message level enabled bits */
 	u32 msg_enable;
@@ -966,4 +976,6 @@ int hnae3_register_client(struct hnae3_client *client);
 void hnae3_set_client_init_flag(struct hnae3_client *client,
 				struct hnae3_ae_dev *ae_dev,
 				unsigned int inited);
+void hnae3_acquire_unload_lock(void);
+void hnae3_release_unload_lock(void);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c
index 4ad4e8ab2f1f..37396ca4ecfc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c
@@ -348,7 +348,7 @@ static int hclge_comm_cmd_csq_clean(struct hclge_comm_hw *hw)
 static int hclge_comm_cmd_csq_done(struct hclge_comm_hw *hw)
 {
 	u32 head = hclge_comm_read_dev(hw, HCLGE_COMM_NIC_CSQ_HEAD_REG);
-	return head == hw->cmq.csq.next_to_use;
+	return head == (u32)hw->cmq.csq.next_to_use;
 }
 
 static u32 hclge_get_cmdq_tx_timeout(u16 opcode, u32 tx_timeout)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c
index 4e2bb6556b1c..1eca53aaf598 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c
@@ -151,7 +151,7 @@ EXPORT_SYMBOL_GPL(hclge_comm_set_rss_hash_key);
 int hclge_comm_set_rss_tuple(struct hnae3_ae_dev *ae_dev,
 			     struct hclge_comm_hw *hw,
 			     struct hclge_comm_rss_cfg *rss_cfg,
-			     struct ethtool_rxnfc *nfc)
+			     const struct ethtool_rxfh_fields *nfc)
 {
 	struct hclge_comm_rss_input_tuple_cmd *req;
 	struct hclge_desc desc;
@@ -422,7 +422,7 @@ int hclge_comm_set_rss_algo_key(struct hclge_comm_hw *hw, const u8 hfunc,
 }
 EXPORT_SYMBOL_GPL(hclge_comm_set_rss_algo_key);
 
-static u8 hclge_comm_get_rss_hash_bits(struct ethtool_rxnfc *nfc)
+static u8 hclge_comm_get_rss_hash_bits(const struct ethtool_rxfh_fields *nfc)
 {
 	u8 hash_sets = nfc->data & RXH_L4_B_0_1 ? HCLGE_COMM_S_PORT_BIT : 0;
 
@@ -448,7 +448,7 @@ static u8 hclge_comm_get_rss_hash_bits(struct ethtool_rxnfc *nfc)
 }
 
 int hclge_comm_init_rss_tuple_cmd(struct hclge_comm_rss_cfg *rss_cfg,
-				  struct ethtool_rxnfc *nfc,
+				  const struct ethtool_rxfh_fields *nfc,
 				  struct hnae3_ae_dev *ae_dev,
 				  struct hclge_comm_rss_input_tuple_cmd *req)
 {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.h b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.h
index cdafa63fe38b..cbc02b50c6e7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.h
@@ -108,7 +108,7 @@ void hclge_comm_get_rss_indir_tbl(struct hclge_comm_rss_cfg *rss_cfg,
 int hclge_comm_set_rss_algo_key(struct hclge_comm_hw *hw, const u8 hfunc,
 				const u8 *key);
 int hclge_comm_init_rss_tuple_cmd(struct hclge_comm_rss_cfg *rss_cfg,
-				  struct ethtool_rxnfc *nfc,
+				  const struct ethtool_rxfh_fields *nfc,
 				  struct hnae3_ae_dev *ae_dev,
 				  struct hclge_comm_rss_input_tuple_cmd *req);
 u64 hclge_comm_convert_rss_tuple(u8 tuple_sets);
@@ -129,5 +129,5 @@ int hclge_comm_set_rss_hash_key(struct hclge_comm_rss_cfg *rss_cfg,
 int hclge_comm_set_rss_tuple(struct hnae3_ae_dev *ae_dev,
 			     struct hclge_comm_hw *hw,
 			     struct hclge_comm_rss_cfg *rss_cfg,
-			     struct ethtool_rxnfc *nfc);
+			     const struct ethtool_rxfh_fields *nfc);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 807eb3bbb11c..4cce4f4ba6b0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -3,6 +3,8 @@
 
 #include <linux/debugfs.h>
 #include <linux/device.h>
+#include <linux/seq_file.h>
+#include <linux/string_choices.h>
 
 #include "hnae3.h"
 #include "hns3_debugfs.h"
@@ -39,323 +41,279 @@ static struct hns3_dbg_dentry_info hns3_dbg_dentry[] = {
 };
 
 static int hns3_dbg_bd_file_init(struct hnae3_handle *handle, u32 cmd);
-static int hns3_dbg_common_file_init(struct hnae3_handle *handle, u32 cmd);
+static int hns3_dbg_common_init_t1(struct hnae3_handle *handle, u32 cmd);
+static int hns3_dbg_common_init_t2(struct hnae3_handle *handle, u32 cmd);
 
 static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
 	{
 		.name = "tm_nodes",
 		.cmd = HNAE3_DBG_CMD_TM_NODES,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "tm_priority",
 		.cmd = HNAE3_DBG_CMD_TM_PRI,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "tm_qset",
 		.cmd = HNAE3_DBG_CMD_TM_QSET,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "tm_map",
 		.cmd = HNAE3_DBG_CMD_TM_MAP,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN_1MB,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "tm_pg",
 		.cmd = HNAE3_DBG_CMD_TM_PG,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "tm_port",
 		.cmd = HNAE3_DBG_CMD_TM_PORT,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "tc_sch_info",
 		.cmd = HNAE3_DBG_CMD_TC_SCH_INFO,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "qos_pause_cfg",
 		.cmd = HNAE3_DBG_CMD_QOS_PAUSE_CFG,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "qos_pri_map",
 		.cmd = HNAE3_DBG_CMD_QOS_PRI_MAP,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "qos_dscp_map",
 		.cmd = HNAE3_DBG_CMD_QOS_DSCP_MAP,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "qos_buf_cfg",
 		.cmd = HNAE3_DBG_CMD_QOS_BUF_CFG,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "dev_info",
 		.cmd = HNAE3_DBG_CMD_DEV_INFO,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t1,
 	},
 	{
 		.name = "tx_bd_queue",
 		.cmd = HNAE3_DBG_CMD_TX_BD,
 		.dentry = HNS3_DBG_DENTRY_TX_BD,
-		.buf_len = HNS3_DBG_READ_LEN_5MB,
 		.init = hns3_dbg_bd_file_init,
 	},
 	{
 		.name = "rx_bd_queue",
 		.cmd = HNAE3_DBG_CMD_RX_BD,
 		.dentry = HNS3_DBG_DENTRY_RX_BD,
-		.buf_len = HNS3_DBG_READ_LEN_4MB,
 		.init = hns3_dbg_bd_file_init,
 	},
 	{
 		.name = "uc",
 		.cmd = HNAE3_DBG_CMD_MAC_UC,
 		.dentry = HNS3_DBG_DENTRY_MAC,
-		.buf_len = HNS3_DBG_READ_LEN_128KB,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "mc",
 		.cmd = HNAE3_DBG_CMD_MAC_MC,
 		.dentry = HNS3_DBG_DENTRY_MAC,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "mng_tbl",
 		.cmd = HNAE3_DBG_CMD_MNG_TBL,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "loopback",
 		.cmd = HNAE3_DBG_CMD_LOOPBACK,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "interrupt_info",
 		.cmd = HNAE3_DBG_CMD_INTERRUPT_INFO,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "reset_info",
 		.cmd = HNAE3_DBG_CMD_RESET_INFO,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "imp_info",
 		.cmd = HNAE3_DBG_CMD_IMP_INFO,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "ncl_config",
 		.cmd = HNAE3_DBG_CMD_NCL_CONFIG,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN_128KB,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "mac_tnl_status",
 		.cmd = HNAE3_DBG_CMD_MAC_TNL_STATUS,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "bios_common",
 		.cmd = HNAE3_DBG_CMD_REG_BIOS_COMMON,
 		.dentry = HNS3_DBG_DENTRY_REG,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "ssu",
 		.cmd = HNAE3_DBG_CMD_REG_SSU,
 		.dentry = HNS3_DBG_DENTRY_REG,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "igu_egu",
 		.cmd = HNAE3_DBG_CMD_REG_IGU_EGU,
 		.dentry = HNS3_DBG_DENTRY_REG,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "rpu",
 		.cmd = HNAE3_DBG_CMD_REG_RPU,
 		.dentry = HNS3_DBG_DENTRY_REG,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "ncsi",
 		.cmd = HNAE3_DBG_CMD_REG_NCSI,
 		.dentry = HNS3_DBG_DENTRY_REG,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "rtc",
 		.cmd = HNAE3_DBG_CMD_REG_RTC,
 		.dentry = HNS3_DBG_DENTRY_REG,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "ppp",
 		.cmd = HNAE3_DBG_CMD_REG_PPP,
 		.dentry = HNS3_DBG_DENTRY_REG,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "rcb",
 		.cmd = HNAE3_DBG_CMD_REG_RCB,
 		.dentry = HNS3_DBG_DENTRY_REG,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "tqp",
 		.cmd = HNAE3_DBG_CMD_REG_TQP,
 		.dentry = HNS3_DBG_DENTRY_REG,
-		.buf_len = HNS3_DBG_READ_LEN_128KB,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "mac",
 		.cmd = HNAE3_DBG_CMD_REG_MAC,
 		.dentry = HNS3_DBG_DENTRY_REG,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "dcb",
 		.cmd = HNAE3_DBG_CMD_REG_DCB,
 		.dentry = HNS3_DBG_DENTRY_REG,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "queue_map",
 		.cmd = HNAE3_DBG_CMD_QUEUE_MAP,
 		.dentry = HNS3_DBG_DENTRY_QUEUE,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t1,
 	},
 	{
 		.name = "rx_queue_info",
 		.cmd = HNAE3_DBG_CMD_RX_QUEUE_INFO,
 		.dentry = HNS3_DBG_DENTRY_QUEUE,
-		.buf_len = HNS3_DBG_READ_LEN_1MB,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t1,
 	},
 	{
 		.name = "tx_queue_info",
 		.cmd = HNAE3_DBG_CMD_TX_QUEUE_INFO,
 		.dentry = HNS3_DBG_DENTRY_QUEUE,
-		.buf_len = HNS3_DBG_READ_LEN_1MB,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t1,
 	},
 	{
 		.name = "fd_tcam",
 		.cmd = HNAE3_DBG_CMD_FD_TCAM,
 		.dentry = HNS3_DBG_DENTRY_FD,
-		.buf_len = HNS3_DBG_READ_LEN_1MB,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "service_task_info",
 		.cmd = HNAE3_DBG_CMD_SERV_INFO,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "vlan_config",
 		.cmd = HNAE3_DBG_CMD_VLAN_CONFIG,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "ptp_info",
 		.cmd = HNAE3_DBG_CMD_PTP_INFO,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "fd_counter",
 		.cmd = HNAE3_DBG_CMD_FD_COUNTER,
 		.dentry = HNS3_DBG_DENTRY_FD,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "umv_info",
 		.cmd = HNAE3_DBG_CMD_UMV_INFO,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t2,
 	},
 	{
 		.name = "page_pool_info",
 		.cmd = HNAE3_DBG_CMD_PAGE_POOL_INFO,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t1,
 	},
 	{
 		.name = "coalesce_info",
 		.cmd = HNAE3_DBG_CMD_COAL_INFO,
 		.dentry = HNS3_DBG_DENTRY_COMMON,
-		.buf_len = HNS3_DBG_READ_LEN_1MB,
-		.init = hns3_dbg_common_file_init,
+		.init = hns3_dbg_common_init_t1,
 	},
 };
 
@@ -420,71 +378,17 @@ static struct hns3_dbg_cap_info hns3_dbg_cap[] = {
 	}
 };
 
-static const struct hns3_dbg_item coal_info_items[] = {
-	{ "VEC_ID", 2 },
-	{ "ALGO_STATE", 2 },
-	{ "PROFILE_ID", 2 },
-	{ "CQE_MODE", 2 },
-	{ "TUNE_STATE", 2 },
-	{ "STEPS_LEFT", 2 },
-	{ "STEPS_RIGHT", 2 },
-	{ "TIRED", 2 },
-	{ "SW_GL", 2 },
-	{ "SW_QL", 2 },
-	{ "HW_GL", 2 },
-	{ "HW_QL", 2 },
-};
-
 static const char * const dim_cqe_mode_str[] = { "EQE", "CQE" };
 static const char * const dim_state_str[] = { "START", "IN_PROG", "APPLY" };
 static const char * const
 dim_tune_stat_str[] = { "ON_TOP", "TIRED", "RIGHT", "LEFT" };
 
-static void hns3_dbg_fill_content(char *content, u16 len,
-				  const struct hns3_dbg_item *items,
-				  const char **result, u16 size)
-{
-#define HNS3_DBG_LINE_END_LEN	2
-	char *pos = content;
-	u16 item_len;
-	u16 i;
-
-	if (!len) {
-		return;
-	} else if (len <= HNS3_DBG_LINE_END_LEN) {
-		*pos++ = '\0';
-		return;
-	}
-
-	memset(content, ' ', len);
-	len -= HNS3_DBG_LINE_END_LEN;
-
-	for (i = 0; i < size; i++) {
-		item_len = strlen(items[i].name) + items[i].interval;
-		if (len < item_len)
-			break;
-
-		if (result) {
-			if (item_len < strlen(result[i]))
-				break;
-			memcpy(pos, result[i], strlen(result[i]));
-		} else {
-			memcpy(pos, items[i].name, strlen(items[i].name));
-		}
-		pos += item_len;
-		len -= item_len;
-	}
-	*pos++ = '\n';
-	*pos++ = '\0';
-}
-
 static void hns3_get_coal_info(struct hns3_enet_tqp_vector *tqp_vector,
-			       char **result, int i, bool is_tx)
+			       struct seq_file *s, int i, bool is_tx)
 {
 	unsigned int gl_offset, ql_offset;
 	struct hns3_enet_coalesce *coal;
 	unsigned int reg_val;
-	unsigned int j = 0;
 	struct dim *dim;
 	bool ql_enable;
 
@@ -502,191 +406,96 @@ static void hns3_get_coal_info(struct hns3_enet_tqp_vector *tqp_vector,
 		ql_enable = tqp_vector->rx_group.coal.ql_enable;
 	}
 
-	sprintf(result[j++], "%d", i);
-	sprintf(result[j++], "%s", dim->state < ARRAY_SIZE(dim_state_str) ?
-		dim_state_str[dim->state] : "unknown");
-	sprintf(result[j++], "%u", dim->profile_ix);
-	sprintf(result[j++], "%s", dim->mode < ARRAY_SIZE(dim_cqe_mode_str) ?
-		dim_cqe_mode_str[dim->mode] : "unknown");
-	sprintf(result[j++], "%s",
-		dim->tune_state < ARRAY_SIZE(dim_tune_stat_str) ?
-		dim_tune_stat_str[dim->tune_state] : "unknown");
-	sprintf(result[j++], "%u", dim->steps_left);
-	sprintf(result[j++], "%u", dim->steps_right);
-	sprintf(result[j++], "%u", dim->tired);
-	sprintf(result[j++], "%u", coal->int_gl);
-	sprintf(result[j++], "%u", coal->int_ql);
+	seq_printf(s, "%-8d", i);
+	seq_printf(s, "%-12s", dim->state < ARRAY_SIZE(dim_state_str) ?
+		   dim_state_str[dim->state] : "unknown");
+	seq_printf(s, "%-12u", dim->profile_ix);
+	seq_printf(s, "%-10s", dim->mode < ARRAY_SIZE(dim_cqe_mode_str) ?
+		   dim_cqe_mode_str[dim->mode] : "unknown");
+	seq_printf(s, "%-12s", dim->tune_state < ARRAY_SIZE(dim_tune_stat_str) ?
+		   dim_tune_stat_str[dim->tune_state] : "unknown");
+	seq_printf(s, "%-12u%-13u%-7u%-7u%-7u", dim->steps_left,
+		   dim->steps_right, dim->tired, coal->int_gl, coal->int_ql);
 	reg_val = readl(tqp_vector->mask_addr + gl_offset) &
 		  HNS3_VECTOR_GL_MASK;
-	sprintf(result[j++], "%u", reg_val);
+	seq_printf(s, "%-7u", reg_val);
 	if (ql_enable) {
 		reg_val = readl(tqp_vector->mask_addr + ql_offset) &
 			  HNS3_VECTOR_QL_MASK;
-		sprintf(result[j++], "%u", reg_val);
+		seq_printf(s, "%u\n", reg_val);
 	} else {
-		sprintf(result[j++], "NA");
+		seq_puts(s, "NA\n");
 	}
 }
 
-static void hns3_dump_coal_info(struct hnae3_handle *h, char *buf, int len,
-				int *pos, bool is_tx)
+static void hns3_dump_coal_info(struct seq_file *s, bool is_tx)
 {
-	char data_str[ARRAY_SIZE(coal_info_items)][HNS3_DBG_DATA_STR_LEN];
-	char *result[ARRAY_SIZE(coal_info_items)];
+	struct hnae3_handle *h = hnae3_seq_file_to_handle(s);
 	struct hns3_enet_tqp_vector *tqp_vector;
 	struct hns3_nic_priv *priv = h->priv;
-	char content[HNS3_DBG_INFO_LEN];
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(coal_info_items); i++)
-		result[i] = &data_str[i][0];
+	seq_printf(s, "%s interrupt coalesce info:\n", is_tx ? "tx" : "rx");
 
-	*pos += scnprintf(buf + *pos, len - *pos,
-			  "%s interrupt coalesce info:\n",
-			  is_tx ? "tx" : "rx");
-	hns3_dbg_fill_content(content, sizeof(content), coal_info_items,
-			      NULL, ARRAY_SIZE(coal_info_items));
-	*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
+	seq_puts(s, "VEC_ID  ALGO_STATE  PROFILE_ID  CQE_MODE  TUNE_STATE  ");
+	seq_puts(s, "STEPS_LEFT  STEPS_RIGHT  TIRED  SW_GL  SW_QL  ");
+	seq_puts(s, "HW_GL  HW_QL\n");
 
 	for (i = 0; i < priv->vector_num; i++) {
 		tqp_vector = &priv->tqp_vector[i];
-		hns3_get_coal_info(tqp_vector, result, i, is_tx);
-		hns3_dbg_fill_content(content, sizeof(content), coal_info_items,
-				      (const char **)result,
-				      ARRAY_SIZE(coal_info_items));
-		*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
+		hns3_get_coal_info(tqp_vector, s, i, is_tx);
 	}
 }
 
-static int hns3_dbg_coal_info(struct hnae3_handle *h, char *buf, int len)
+static int hns3_dbg_coal_info(struct seq_file *s, void *data)
 {
-	int pos = 0;
-
-	hns3_dump_coal_info(h, buf, len, &pos, true);
-	pos += scnprintf(buf + pos, len - pos, "\n");
-	hns3_dump_coal_info(h, buf, len, &pos, false);
+	hns3_dump_coal_info(s, true);
+	seq_puts(s, "\n");
+	hns3_dump_coal_info(s, false);
 
 	return 0;
 }
 
-static const struct hns3_dbg_item tx_spare_info_items[] = {
-	{ "QUEUE_ID", 2 },
-	{ "COPYBREAK", 2 },
-	{ "LEN", 7 },
-	{ "NTU", 4 },
-	{ "NTC", 4 },
-	{ "LTC", 4 },
-	{ "DMA", 17 },
-};
-
-static void hns3_dbg_tx_spare_info(struct hns3_enet_ring *ring, char *buf,
-				   int len, u32 ring_num, int *pos)
-{
-	char data_str[ARRAY_SIZE(tx_spare_info_items)][HNS3_DBG_DATA_STR_LEN];
-	struct hns3_tx_spare *tx_spare = ring->tx_spare;
-	char *result[ARRAY_SIZE(tx_spare_info_items)];
-	char content[HNS3_DBG_INFO_LEN];
-	u32 i, j;
-
-	if (!tx_spare) {
-		*pos += scnprintf(buf + *pos, len - *pos,
-				  "tx spare buffer is not enabled\n");
-		return;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(tx_spare_info_items); i++)
-		result[i] = &data_str[i][0];
-
-	*pos += scnprintf(buf + *pos, len - *pos, "tx spare buffer info\n");
-	hns3_dbg_fill_content(content, sizeof(content), tx_spare_info_items,
-			      NULL, ARRAY_SIZE(tx_spare_info_items));
-	*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
-
-	for (i = 0; i < ring_num; i++) {
-		j = 0;
-		sprintf(result[j++], "%u", i);
-		sprintf(result[j++], "%u", ring->tx_copybreak);
-		sprintf(result[j++], "%u", tx_spare->len);
-		sprintf(result[j++], "%u", tx_spare->next_to_use);
-		sprintf(result[j++], "%u", tx_spare->next_to_clean);
-		sprintf(result[j++], "%u", tx_spare->last_to_clean);
-		sprintf(result[j++], "%pad", &tx_spare->dma);
-		hns3_dbg_fill_content(content, sizeof(content),
-				      tx_spare_info_items,
-				      (const char **)result,
-				      ARRAY_SIZE(tx_spare_info_items));
-		*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
-	}
-}
-
-static const struct hns3_dbg_item rx_queue_info_items[] = {
-	{ "QUEUE_ID", 2 },
-	{ "BD_NUM", 2 },
-	{ "BD_LEN", 2 },
-	{ "TAIL", 2 },
-	{ "HEAD", 2 },
-	{ "FBDNUM", 2 },
-	{ "PKTNUM", 5 },
-	{ "COPYBREAK", 2 },
-	{ "RING_EN", 2 },
-	{ "RX_RING_EN", 2 },
-	{ "BASE_ADDR", 10 },
-};
-
 static void hns3_dump_rx_queue_info(struct hns3_enet_ring *ring,
-				    struct hnae3_ae_dev *ae_dev, char **result,
-				    u32 index)
+				    struct seq_file *s, u32 index)
 {
+	struct hnae3_ae_dev *ae_dev = hnae3_seq_file_to_ae_dev(s);
+	void __iomem *base = ring->tqp->io_base;
 	u32 base_add_l, base_add_h;
-	u32 j = 0;
-
-	sprintf(result[j++], "%u", index);
-
-	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_RX_RING_BD_NUM_REG));
-
-	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_RX_RING_BD_LEN_REG));
-
-	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_RX_RING_TAIL_REG));
-
-	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_RX_RING_HEAD_REG));
-
-	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_RX_RING_FBDNUM_REG));
-
-	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_RX_RING_PKTNUM_RECORD_REG));
-	sprintf(result[j++], "%u", ring->rx_copybreak);
 
-	sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_EN_REG) ? "on" : "off");
+	seq_printf(s, "%-10u", index);
+	seq_printf(s, "%-8u",
+		   readl_relaxed(base + HNS3_RING_RX_RING_BD_NUM_REG));
+	seq_printf(s, "%-8u",
+		   readl_relaxed(base + HNS3_RING_RX_RING_BD_LEN_REG));
+	seq_printf(s, "%-6u",
+		   readl_relaxed(base + HNS3_RING_RX_RING_TAIL_REG));
+	seq_printf(s, "%-6u",
+		   readl_relaxed(base + HNS3_RING_RX_RING_HEAD_REG));
+	seq_printf(s, "%-8u",
+		   readl_relaxed(base + HNS3_RING_RX_RING_FBDNUM_REG));
+	seq_printf(s, "%-11u", readl_relaxed(base +
+		   HNS3_RING_RX_RING_PKTNUM_RECORD_REG));
+	seq_printf(s, "%-11u", ring->rx_copybreak);
+	seq_printf(s, "%-9s",
+		   str_on_off(readl_relaxed(base + HNS3_RING_EN_REG)));
 
 	if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev))
-		sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base +
-			HNS3_RING_RX_EN_REG) ? "on" : "off");
+		seq_printf(s, "%-12s", str_on_off(readl_relaxed(base +
+						  HNS3_RING_RX_EN_REG)));
 	else
-		sprintf(result[j++], "%s", "NA");
+		seq_printf(s, "%-12s", "NA");
 
-	base_add_h = readl_relaxed(ring->tqp->io_base +
-					HNS3_RING_RX_RING_BASEADDR_H_REG);
-	base_add_l = readl_relaxed(ring->tqp->io_base +
-					HNS3_RING_RX_RING_BASEADDR_L_REG);
-	sprintf(result[j++], "0x%08x%08x", base_add_h, base_add_l);
+	base_add_h = readl_relaxed(base + HNS3_RING_RX_RING_BASEADDR_H_REG);
+	base_add_l = readl_relaxed(base + HNS3_RING_RX_RING_BASEADDR_L_REG);
+	seq_printf(s, "0x%08x%08x\n", base_add_h, base_add_l);
 }
 
-static int hns3_dbg_rx_queue_info(struct hnae3_handle *h,
-				  char *buf, int len)
+static int hns3_dbg_rx_queue_info(struct seq_file *s, void *data)
 {
-	char data_str[ARRAY_SIZE(rx_queue_info_items)][HNS3_DBG_DATA_STR_LEN];
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
-	char *result[ARRAY_SIZE(rx_queue_info_items)];
+	struct hnae3_handle *h = hnae3_seq_file_to_handle(s);
 	struct hns3_nic_priv *priv = h->priv;
-	char content[HNS3_DBG_INFO_LEN];
 	struct hns3_enet_ring *ring;
-	int pos = 0;
 	u32 i;
 
 	if (!priv->ring) {
@@ -694,12 +503,9 @@ static int hns3_dbg_rx_queue_info(struct hnae3_handle *h,
 		return -EFAULT;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(rx_queue_info_items); i++)
-		result[i] = &data_str[i][0];
+	seq_puts(s, "QUEUE_ID  BD_NUM  BD_LEN  TAIL  HEAD  FBDNUM  ");
+	seq_puts(s, "PKTNUM     COPYBREAK  RING_EN  RX_RING_EN  BASE_ADDR\n");
 
-	hns3_dbg_fill_content(content, sizeof(content), rx_queue_info_items,
-			      NULL, ARRAY_SIZE(rx_queue_info_items));
-	pos += scnprintf(buf + pos, len - pos, "%s", content);
 	for (i = 0; i < h->kinfo.num_tqps; i++) {
 		/* Each cycle needs to determine whether the instance is reset,
 		 * to prevent reference to invalid memory. And need to ensure
@@ -710,86 +516,51 @@ static int hns3_dbg_rx_queue_info(struct hnae3_handle *h,
 			return -EPERM;
 
 		ring = &priv->ring[(u32)(i + h->kinfo.num_tqps)];
-		hns3_dump_rx_queue_info(ring, ae_dev, result, i);
-		hns3_dbg_fill_content(content, sizeof(content),
-				      rx_queue_info_items,
-				      (const char **)result,
-				      ARRAY_SIZE(rx_queue_info_items));
-		pos += scnprintf(buf + pos, len - pos, "%s", content);
+		hns3_dump_rx_queue_info(ring, s, i);
 	}
 
 	return 0;
 }
 
-static const struct hns3_dbg_item tx_queue_info_items[] = {
-	{ "QUEUE_ID", 2 },
-	{ "BD_NUM", 2 },
-	{ "TC", 2 },
-	{ "TAIL", 2 },
-	{ "HEAD", 2 },
-	{ "FBDNUM", 2 },
-	{ "OFFSET", 2 },
-	{ "PKTNUM", 5 },
-	{ "RING_EN", 2 },
-	{ "TX_RING_EN", 2 },
-	{ "BASE_ADDR", 10 },
-};
-
 static void hns3_dump_tx_queue_info(struct hns3_enet_ring *ring,
-				    struct hnae3_ae_dev *ae_dev, char **result,
-				    u32 index)
+				    struct seq_file *s, u32 index)
 {
+	struct hnae3_ae_dev *ae_dev = hnae3_seq_file_to_ae_dev(s);
+	void __iomem *base = ring->tqp->io_base;
 	u32 base_add_l, base_add_h;
-	u32 j = 0;
-
-	sprintf(result[j++], "%u", index);
-	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_TX_RING_BD_NUM_REG));
-
-	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_TX_RING_TC_REG));
-
-	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_TX_RING_TAIL_REG));
-
-	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_TX_RING_HEAD_REG));
-
-	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_TX_RING_FBDNUM_REG));
-
-	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_TX_RING_OFFSET_REG));
 
-	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_TX_RING_PKTNUM_RECORD_REG));
-
-	sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_EN_REG) ? "on" : "off");
+	seq_printf(s, "%-10u", index);
+	seq_printf(s, "%-8u",
+		   readl_relaxed(base + HNS3_RING_TX_RING_BD_NUM_REG));
+	seq_printf(s, "%-4u", readl_relaxed(base + HNS3_RING_TX_RING_TC_REG));
+	seq_printf(s, "%-6u", readl_relaxed(base + HNS3_RING_TX_RING_TAIL_REG));
+	seq_printf(s, "%-6u", readl_relaxed(base + HNS3_RING_TX_RING_HEAD_REG));
+	seq_printf(s, "%-8u",
+		   readl_relaxed(base + HNS3_RING_TX_RING_FBDNUM_REG));
+	seq_printf(s, "%-8u",
+		   readl_relaxed(base + HNS3_RING_TX_RING_OFFSET_REG));
+	seq_printf(s, "%-11u",
+		   readl_relaxed(base + HNS3_RING_TX_RING_PKTNUM_RECORD_REG));
+	seq_printf(s, "%-9s",
+		   str_on_off(readl_relaxed(base + HNS3_RING_EN_REG)));
 
 	if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev))
-		sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base +
-			HNS3_RING_TX_EN_REG) ? "on" : "off");
+		seq_printf(s, "%-12s",
+			   str_on_off(readl_relaxed(base +
+						    HNS3_RING_TX_EN_REG)));
 	else
-		sprintf(result[j++], "%s", "NA");
+		seq_printf(s, "%-12s", "NA");
 
-	base_add_h = readl_relaxed(ring->tqp->io_base +
-					HNS3_RING_TX_RING_BASEADDR_H_REG);
-	base_add_l = readl_relaxed(ring->tqp->io_base +
-					HNS3_RING_TX_RING_BASEADDR_L_REG);
-	sprintf(result[j++], "0x%08x%08x", base_add_h, base_add_l);
+	base_add_h = readl_relaxed(base + HNS3_RING_TX_RING_BASEADDR_H_REG);
+	base_add_l = readl_relaxed(base + HNS3_RING_TX_RING_BASEADDR_L_REG);
+	seq_printf(s, "0x%08x%08x\n", base_add_h, base_add_l);
 }
 
-static int hns3_dbg_tx_queue_info(struct hnae3_handle *h,
-				  char *buf, int len)
+static int hns3_dbg_tx_queue_info(struct seq_file *s, void *data)
 {
-	char data_str[ARRAY_SIZE(tx_queue_info_items)][HNS3_DBG_DATA_STR_LEN];
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
-	char *result[ARRAY_SIZE(tx_queue_info_items)];
+	struct hnae3_handle *h = hnae3_seq_file_to_handle(s);
 	struct hns3_nic_priv *priv = h->priv;
-	char content[HNS3_DBG_INFO_LEN];
 	struct hns3_enet_ring *ring;
-	int pos = 0;
 	u32 i;
 
 	if (!priv->ring) {
@@ -797,12 +568,8 @@ static int hns3_dbg_tx_queue_info(struct hnae3_handle *h,
 		return -EFAULT;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(tx_queue_info_items); i++)
-		result[i] = &data_str[i][0];
-
-	hns3_dbg_fill_content(content, sizeof(content), tx_queue_info_items,
-			      NULL, ARRAY_SIZE(tx_queue_info_items));
-	pos += scnprintf(buf + pos, len - pos, "%s", content);
+	seq_puts(s, "QUEUE_ID  BD_NUM  TC  TAIL  HEAD  FBDNUM  OFFSET  ");
+	seq_puts(s, "PKTNUM     RING_EN  TX_RING_EN  BASE_ADDR\n");
 
 	for (i = 0; i < h->kinfo.num_tqps; i++) {
 		/* Each cycle needs to determine whether the instance is reset,
@@ -814,339 +581,213 @@ static int hns3_dbg_tx_queue_info(struct hnae3_handle *h,
 			return -EPERM;
 
 		ring = &priv->ring[i];
-		hns3_dump_tx_queue_info(ring, ae_dev, result, i);
-		hns3_dbg_fill_content(content, sizeof(content),
-				      tx_queue_info_items,
-				      (const char **)result,
-				      ARRAY_SIZE(tx_queue_info_items));
-		pos += scnprintf(buf + pos, len - pos, "%s", content);
+		hns3_dump_tx_queue_info(ring, s, i);
 	}
 
-	hns3_dbg_tx_spare_info(ring, buf, len, h->kinfo.num_tqps, &pos);
-
 	return 0;
 }
 
-static const struct hns3_dbg_item queue_map_items[] = {
-	{ "local_queue_id", 2 },
-	{ "global_queue_id", 2 },
-	{ "vector_id", 2 },
-};
-
-static int hns3_dbg_queue_map(struct hnae3_handle *h, char *buf, int len)
+static int hns3_dbg_queue_map(struct seq_file *s, void *data)
 {
-	char data_str[ARRAY_SIZE(queue_map_items)][HNS3_DBG_DATA_STR_LEN];
-	char *result[ARRAY_SIZE(queue_map_items)];
+	struct hnae3_handle *h = hnae3_seq_file_to_handle(s);
 	struct hns3_nic_priv *priv = h->priv;
-	char content[HNS3_DBG_INFO_LEN];
-	int pos = 0;
-	int j;
 	u32 i;
 
 	if (!h->ae_algo->ops->get_global_queue_id)
 		return -EOPNOTSUPP;
 
-	for (i = 0; i < ARRAY_SIZE(queue_map_items); i++)
-		result[i] = &data_str[i][0];
+	seq_puts(s, "local_queue_id  global_queue_id  vector_id\n");
 
-	hns3_dbg_fill_content(content, sizeof(content), queue_map_items,
-			      NULL, ARRAY_SIZE(queue_map_items));
-	pos += scnprintf(buf + pos, len - pos, "%s", content);
 	for (i = 0; i < h->kinfo.num_tqps; i++) {
 		if (!priv->ring || !priv->ring[i].tqp_vector)
 			continue;
-		j = 0;
-		sprintf(result[j++], "%u", i);
-		sprintf(result[j++], "%u",
-			h->ae_algo->ops->get_global_queue_id(h, i));
-		sprintf(result[j++], "%d",
-			priv->ring[i].tqp_vector->vector_irq);
-		hns3_dbg_fill_content(content, sizeof(content), queue_map_items,
-				      (const char **)result,
-				      ARRAY_SIZE(queue_map_items));
-		pos += scnprintf(buf + pos, len - pos, "%s", content);
+		seq_printf(s, "%-16u%-17u%d\n", i,
+			   h->ae_algo->ops->get_global_queue_id(h, i),
+			   priv->ring[i].tqp_vector->vector_irq);
 	}
 
 	return 0;
 }
 
-static const struct hns3_dbg_item rx_bd_info_items[] = {
-	{ "BD_IDX", 3 },
-	{ "L234_INFO", 2 },
-	{ "PKT_LEN", 3 },
-	{ "SIZE", 4 },
-	{ "RSS_HASH", 4 },
-	{ "FD_ID", 2 },
-	{ "VLAN_TAG", 2 },
-	{ "O_DM_VLAN_ID_FB", 2 },
-	{ "OT_VLAN_TAG", 2 },
-	{ "BD_BASE_INFO", 2 },
-	{ "PTYPE", 2 },
-	{ "HW_CSUM", 2 },
-};
-
 static void hns3_dump_rx_bd_info(struct hns3_nic_priv *priv,
-				 struct hns3_desc *desc, char **result, int idx)
+				 struct hns3_desc *desc, struct seq_file *s,
+				 int idx)
 {
-	unsigned int j = 0;
-
-	sprintf(result[j++], "%d", idx);
-	sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.l234_info));
-	sprintf(result[j++], "%u", le16_to_cpu(desc->rx.pkt_len));
-	sprintf(result[j++], "%u", le16_to_cpu(desc->rx.size));
-	sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.rss_hash));
-	sprintf(result[j++], "%u", le16_to_cpu(desc->rx.fd_id));
-	sprintf(result[j++], "%u", le16_to_cpu(desc->rx.vlan_tag));
-	sprintf(result[j++], "%u", le16_to_cpu(desc->rx.o_dm_vlan_id_fb));
-	sprintf(result[j++], "%u", le16_to_cpu(desc->rx.ot_vlan_tag));
-	sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.bd_base_info));
+	seq_printf(s, "%-9d%#-11x%-10u%-8u%#-12x%-7u%-10u%-17u%-13u%#-14x",
+		   idx, le32_to_cpu(desc->rx.l234_info),
+		   le16_to_cpu(desc->rx.pkt_len), le16_to_cpu(desc->rx.size),
+		   le32_to_cpu(desc->rx.rss_hash), le16_to_cpu(desc->rx.fd_id),
+		   le16_to_cpu(desc->rx.vlan_tag),
+		   le16_to_cpu(desc->rx.o_dm_vlan_id_fb),
+		   le16_to_cpu(desc->rx.ot_vlan_tag),
+		   le32_to_cpu(desc->rx.bd_base_info));
+
 	if (test_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state)) {
 		u32 ol_info = le32_to_cpu(desc->rx.ol_info);
 
-		sprintf(result[j++], "%5lu", hnae3_get_field(ol_info,
-							     HNS3_RXD_PTYPE_M,
-							     HNS3_RXD_PTYPE_S));
-		sprintf(result[j++], "%7u", le16_to_cpu(desc->csum));
+		seq_printf(s, "%-7lu%-9u\n",
+			   hnae3_get_field(ol_info, HNS3_RXD_PTYPE_M,
+					   HNS3_RXD_PTYPE_S),
+			   le16_to_cpu(desc->csum));
 	} else {
-		sprintf(result[j++], "NA");
-		sprintf(result[j++], "NA");
+		seq_puts(s, "NA     NA\n");
 	}
 }
 
-static int hns3_dbg_rx_bd_info(struct hns3_dbg_data *d, char *buf, int len)
+static int hns3_dbg_rx_bd_info(struct seq_file *s, void *private)
 {
-	char data_str[ARRAY_SIZE(rx_bd_info_items)][HNS3_DBG_DATA_STR_LEN];
-	struct hns3_nic_priv *priv = d->handle->priv;
-	char *result[ARRAY_SIZE(rx_bd_info_items)];
-	char content[HNS3_DBG_INFO_LEN];
+	struct hns3_dbg_data *data = s->private;
+	struct hnae3_handle *h = data->handle;
+	struct hns3_nic_priv *priv = h->priv;
 	struct hns3_enet_ring *ring;
 	struct hns3_desc *desc;
 	unsigned int i;
-	int pos = 0;
 
-	if (d->qid >= d->handle->kinfo.num_tqps) {
-		dev_err(&d->handle->pdev->dev,
-			"queue%u is not in use\n", d->qid);
+	if (data->qid >= h->kinfo.num_tqps) {
+		dev_err(&h->pdev->dev, "queue%u is not in use\n", data->qid);
 		return -EINVAL;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(rx_bd_info_items); i++)
-		result[i] = &data_str[i][0];
+	seq_printf(s, "Queue %u rx bd info:\n", data->qid);
+	seq_puts(s, "BD_IDX   L234_INFO  PKT_LEN   SIZE    ");
+	seq_puts(s, "RSS_HASH    FD_ID  VLAN_TAG  O_DM_VLAN_ID_FB  ");
+	seq_puts(s, "OT_VLAN_TAG  BD_BASE_INFO  PTYPE  HW_CSUM\n");
 
-	pos += scnprintf(buf + pos, len - pos,
-			  "Queue %u rx bd info:\n", d->qid);
-	hns3_dbg_fill_content(content, sizeof(content), rx_bd_info_items,
-			      NULL, ARRAY_SIZE(rx_bd_info_items));
-	pos += scnprintf(buf + pos, len - pos, "%s", content);
-
-	ring = &priv->ring[d->qid + d->handle->kinfo.num_tqps];
+	ring = &priv->ring[data->qid + data->handle->kinfo.num_tqps];
 	for (i = 0; i < ring->desc_num; i++) {
 		desc = &ring->desc[i];
 
-		hns3_dump_rx_bd_info(priv, desc, result, i);
-		hns3_dbg_fill_content(content, sizeof(content),
-				      rx_bd_info_items, (const char **)result,
-				      ARRAY_SIZE(rx_bd_info_items));
-		pos += scnprintf(buf + pos, len - pos, "%s", content);
+		hns3_dump_rx_bd_info(priv, desc, s, i);
 	}
 
 	return 0;
 }
 
-static const struct hns3_dbg_item tx_bd_info_items[] = {
-	{ "BD_IDX", 2 },
-	{ "ADDRESS", 13 },
-	{ "VLAN_TAG", 2 },
-	{ "SIZE", 2 },
-	{ "T_CS_VLAN_TSO", 2 },
-	{ "OT_VLAN_TAG", 3 },
-	{ "TV", 5 },
-	{ "OLT_VLAN_LEN", 2 },
-	{ "PAYLEN_OL4CS", 2 },
-	{ "BD_FE_SC_VLD", 2 },
-	{ "MSS_HW_CSUM", 0 },
-};
-
-static void hns3_dump_tx_bd_info(struct hns3_desc *desc, char **result, int idx)
+static void hns3_dump_tx_bd_info(struct hns3_desc *desc, struct seq_file *s,
+				 int idx)
 {
-	unsigned int j = 0;
-
-	sprintf(result[j++], "%d", idx);
-	sprintf(result[j++], "%#llx", le64_to_cpu(desc->addr));
-	sprintf(result[j++], "%u", le16_to_cpu(desc->tx.vlan_tag));
-	sprintf(result[j++], "%u", le16_to_cpu(desc->tx.send_size));
-	sprintf(result[j++], "%#x",
-		le32_to_cpu(desc->tx.type_cs_vlan_tso_len));
-	sprintf(result[j++], "%u", le16_to_cpu(desc->tx.outer_vlan_tag));
-	sprintf(result[j++], "%u", le16_to_cpu(desc->tx.tv));
-	sprintf(result[j++], "%u",
-		le32_to_cpu(desc->tx.ol_type_vlan_len_msec));
-	sprintf(result[j++], "%#x", le32_to_cpu(desc->tx.paylen_ol4cs));
-	sprintf(result[j++], "%#x", le16_to_cpu(desc->tx.bdtp_fe_sc_vld_ra_ri));
-	sprintf(result[j++], "%u", le16_to_cpu(desc->tx.mss_hw_csum));
+	seq_printf(s, "%-8d%#-20llx%-10u%-6u%#-15x%-14u%-7u%-16u%#-14x%#-14x%-11u\n",
+		   idx, le64_to_cpu(desc->addr),
+		   le16_to_cpu(desc->tx.vlan_tag),
+		   le16_to_cpu(desc->tx.send_size),
+		   le32_to_cpu(desc->tx.type_cs_vlan_tso_len),
+		   le16_to_cpu(desc->tx.outer_vlan_tag),
+		   le16_to_cpu(desc->tx.tv),
+		   le32_to_cpu(desc->tx.ol_type_vlan_len_msec),
+		   le32_to_cpu(desc->tx.paylen_ol4cs),
+		   le16_to_cpu(desc->tx.bdtp_fe_sc_vld_ra_ri),
+		   le16_to_cpu(desc->tx.mss_hw_csum));
 }
 
-static int hns3_dbg_tx_bd_info(struct hns3_dbg_data *d, char *buf, int len)
+static int hns3_dbg_tx_bd_info(struct seq_file *s, void *private)
 {
-	char data_str[ARRAY_SIZE(tx_bd_info_items)][HNS3_DBG_DATA_STR_LEN];
-	struct hns3_nic_priv *priv = d->handle->priv;
-	char *result[ARRAY_SIZE(tx_bd_info_items)];
-	char content[HNS3_DBG_INFO_LEN];
+	struct hns3_dbg_data *data = s->private;
+	struct hnae3_handle *h = data->handle;
+	struct hns3_nic_priv *priv = h->priv;
 	struct hns3_enet_ring *ring;
 	struct hns3_desc *desc;
 	unsigned int i;
-	int pos = 0;
 
-	if (d->qid >= d->handle->kinfo.num_tqps) {
-		dev_err(&d->handle->pdev->dev,
-			"queue%u is not in use\n", d->qid);
+	if (data->qid >= h->kinfo.num_tqps) {
+		dev_err(&h->pdev->dev, "queue%u is not in use\n", data->qid);
 		return -EINVAL;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(tx_bd_info_items); i++)
-		result[i] = &data_str[i][0];
-
-	pos += scnprintf(buf + pos, len - pos,
-			  "Queue %u tx bd info:\n", d->qid);
-	hns3_dbg_fill_content(content, sizeof(content), tx_bd_info_items,
-			      NULL, ARRAY_SIZE(tx_bd_info_items));
-	pos += scnprintf(buf + pos, len - pos, "%s", content);
+	seq_printf(s, "Queue %u tx bd info:\n", data->qid);
+	seq_puts(s, "BD_IDX  ADDRESS             VLAN_TAG  SIZE  ");
+	seq_puts(s, "T_CS_VLAN_TSO  OT_VLAN_TAG   TV     OLT_VLAN_LEN  ");
+	seq_puts(s, "PAYLEN_OL4CS  BD_FE_SC_VLD   MSS_HW_CSUM\n");
 
-	ring = &priv->ring[d->qid];
+	ring = &priv->ring[data->qid];
 	for (i = 0; i < ring->desc_num; i++) {
 		desc = &ring->desc[i];
 
-		hns3_dump_tx_bd_info(desc, result, i);
-		hns3_dbg_fill_content(content, sizeof(content),
-				      tx_bd_info_items, (const char **)result,
-				      ARRAY_SIZE(tx_bd_info_items));
-		pos += scnprintf(buf + pos, len - pos, "%s", content);
+		hns3_dump_tx_bd_info(desc, s, i);
 	}
 
 	return 0;
 }
 
-static void
-hns3_dbg_dev_caps(struct hnae3_handle *h, char *buf, int len, int *pos)
+static void hns3_dbg_dev_caps(struct hnae3_handle *h, struct seq_file *s)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
-	const char * const str[] = {"no", "yes"};
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(h);
 	unsigned long *caps = ae_dev->caps;
 	u32 i, state;
 
-	*pos += scnprintf(buf + *pos, len - *pos, "dev capability:\n");
+	seq_puts(s, "dev capability:\n");
 
 	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cap); i++) {
 		state = test_bit(hns3_dbg_cap[i].cap_bit, caps);
-		*pos += scnprintf(buf + *pos, len - *pos, "%s: %s\n",
-				  hns3_dbg_cap[i].name, str[state]);
+		seq_printf(s, "%s: %s\n", hns3_dbg_cap[i].name,
+			   str_yes_no(state));
 	}
 
-	*pos += scnprintf(buf + *pos, len - *pos, "\n");
+	seq_puts(s, "\n");
 }
 
-static void
-hns3_dbg_dev_specs(struct hnae3_handle *h, char *buf, int len, int *pos)
+static void hns3_dbg_dev_specs(struct hnae3_handle *h, struct seq_file *s)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
 	struct hnae3_dev_specs *dev_specs = &ae_dev->dev_specs;
 	struct hnae3_knic_private_info *kinfo = &h->kinfo;
 	struct net_device *dev = kinfo->netdev;
 
-	*pos += scnprintf(buf + *pos, len - *pos, "dev_spec:\n");
-	*pos += scnprintf(buf + *pos, len - *pos, "MAC entry num: %u\n",
-			  dev_specs->mac_entry_num);
-	*pos += scnprintf(buf + *pos, len - *pos, "MNG entry num: %u\n",
-			  dev_specs->mng_entry_num);
-	*pos += scnprintf(buf + *pos, len - *pos, "MAX non tso bd num: %u\n",
-			  dev_specs->max_non_tso_bd_num);
-	*pos += scnprintf(buf + *pos, len - *pos, "RSS ind tbl size: %u\n",
-			  dev_specs->rss_ind_tbl_size);
-	*pos += scnprintf(buf + *pos, len - *pos, "RSS key size: %u\n",
-			  dev_specs->rss_key_size);
-	*pos += scnprintf(buf + *pos, len - *pos, "RSS size: %u\n",
-			  kinfo->rss_size);
-	*pos += scnprintf(buf + *pos, len - *pos, "Allocated RSS size: %u\n",
-			  kinfo->req_rss_size);
-	*pos += scnprintf(buf + *pos, len - *pos,
-			  "Task queue pairs numbers: %u\n",
-			  kinfo->num_tqps);
-	*pos += scnprintf(buf + *pos, len - *pos, "RX buffer length: %u\n",
-			  kinfo->rx_buf_len);
-	*pos += scnprintf(buf + *pos, len - *pos, "Desc num per TX queue: %u\n",
-			  kinfo->num_tx_desc);
-	*pos += scnprintf(buf + *pos, len - *pos, "Desc num per RX queue: %u\n",
-			  kinfo->num_rx_desc);
-	*pos += scnprintf(buf + *pos, len - *pos,
-			  "Total number of enabled TCs: %u\n",
-			  kinfo->tc_info.num_tc);
-	*pos += scnprintf(buf + *pos, len - *pos, "MAX INT QL: %u\n",
-			  dev_specs->int_ql_max);
-	*pos += scnprintf(buf + *pos, len - *pos, "MAX INT GL: %u\n",
-			  dev_specs->max_int_gl);
-	*pos += scnprintf(buf + *pos, len - *pos, "MAX TM RATE: %u\n",
-			  dev_specs->max_tm_rate);
-	*pos += scnprintf(buf + *pos, len - *pos, "MAX QSET number: %u\n",
-			  dev_specs->max_qset_num);
-	*pos += scnprintf(buf + *pos, len - *pos, "umv size: %u\n",
-			  dev_specs->umv_size);
-	*pos += scnprintf(buf + *pos, len - *pos, "mc mac size: %u\n",
-			  dev_specs->mc_mac_size);
-	*pos += scnprintf(buf + *pos, len - *pos, "MAC statistics number: %u\n",
-			  dev_specs->mac_stats_num);
-	*pos += scnprintf(buf + *pos, len - *pos,
-			  "TX timeout threshold: %d seconds\n",
-			  dev->watchdog_timeo / HZ);
-	*pos += scnprintf(buf + *pos, len - *pos, "Hilink Version: %u\n",
-			  dev_specs->hilink_version);
+	seq_puts(s, "dev_spec:\n");
+	seq_printf(s, "MAC entry num: %u\n", dev_specs->mac_entry_num);
+	seq_printf(s, "MNG entry num: %u\n", dev_specs->mng_entry_num);
+	seq_printf(s, "MAX non tso bd num: %u\n",
+		   dev_specs->max_non_tso_bd_num);
+	seq_printf(s, "RSS ind tbl size: %u\n", dev_specs->rss_ind_tbl_size);
+	seq_printf(s, "RSS key size: %u\n", dev_specs->rss_key_size);
+	seq_printf(s, "RSS size: %u\n", kinfo->rss_size);
+	seq_printf(s, "Allocated RSS size: %u\n", kinfo->req_rss_size);
+	seq_printf(s, "Task queue pairs numbers: %u\n", kinfo->num_tqps);
+	seq_printf(s, "RX buffer length: %u\n", kinfo->rx_buf_len);
+	seq_printf(s, "Desc num per TX queue: %u\n", kinfo->num_tx_desc);
+	seq_printf(s, "Desc num per RX queue: %u\n", kinfo->num_rx_desc);
+	seq_printf(s, "Total number of enabled TCs: %u\n",
+		   kinfo->tc_info.num_tc);
+	seq_printf(s, "MAX INT QL: %u\n", dev_specs->int_ql_max);
+	seq_printf(s, "MAX INT GL: %u\n", dev_specs->max_int_gl);
+	seq_printf(s, "MAX TM RATE: %u\n", dev_specs->max_tm_rate);
+	seq_printf(s, "MAX QSET number: %u\n", dev_specs->max_qset_num);
+	seq_printf(s, "umv size: %u\n", dev_specs->umv_size);
+	seq_printf(s, "mc mac size: %u\n", dev_specs->mc_mac_size);
+	seq_printf(s, "MAC statistics number: %u\n", dev_specs->mac_stats_num);
+	seq_printf(s, "TX timeout threshold: %d seconds\n",
+		   dev->watchdog_timeo / HZ);
+	seq_printf(s, "mac tunnel number: %u\n", dev_specs->tnl_num);
+	seq_printf(s, "Hilink Version: %u\n", dev_specs->hilink_version);
 }
 
-static int hns3_dbg_dev_info(struct hnae3_handle *h, char *buf, int len)
+static int hns3_dbg_dev_info(struct seq_file *s, void *data)
 {
-	int pos = 0;
-
-	hns3_dbg_dev_caps(h, buf, len, &pos);
+	struct hnae3_handle *h = hnae3_seq_file_to_handle(s);
 
-	hns3_dbg_dev_specs(h, buf, len, &pos);
+	hns3_dbg_dev_caps(h, s);
+	hns3_dbg_dev_specs(h, s);
 
 	return 0;
 }
 
-static const struct hns3_dbg_item page_pool_info_items[] = {
-	{ "QUEUE_ID", 2 },
-	{ "ALLOCATE_CNT", 2 },
-	{ "FREE_CNT", 6 },
-	{ "POOL_SIZE(PAGE_NUM)", 2 },
-	{ "ORDER", 2 },
-	{ "NUMA_ID", 2 },
-	{ "MAX_LEN", 2 },
-};
-
 static void hns3_dump_page_pool_info(struct hns3_enet_ring *ring,
-				     char **result, u32 index)
+				     struct seq_file *s, u32 index)
 {
-	u32 j = 0;
-
-	sprintf(result[j++], "%u", index);
-	sprintf(result[j++], "%u",
-		READ_ONCE(ring->page_pool->pages_state_hold_cnt));
-	sprintf(result[j++], "%d",
-		atomic_read(&ring->page_pool->pages_state_release_cnt));
-	sprintf(result[j++], "%u", ring->page_pool->p.pool_size);
-	sprintf(result[j++], "%u", ring->page_pool->p.order);
-	sprintf(result[j++], "%d", ring->page_pool->p.nid);
-	sprintf(result[j++], "%uK", ring->page_pool->p.max_len / 1024);
+	seq_printf(s, "%-10u%-14u%-14d%-21u%-7u%-9d%uK\n",
+		   index,
+		   READ_ONCE(ring->page_pool->pages_state_hold_cnt),
+		   atomic_read(&ring->page_pool->pages_state_release_cnt),
+		   ring->page_pool->p.pool_size,
+		   ring->page_pool->p.order,
+		   ring->page_pool->p.nid,
+		   ring->page_pool->p.max_len / 1024);
 }
 
-static int
-hns3_dbg_page_pool_info(struct hnae3_handle *h, char *buf, int len)
+static int hns3_dbg_page_pool_info(struct seq_file *s, void *data)
 {
-	char data_str[ARRAY_SIZE(page_pool_info_items)][HNS3_DBG_DATA_STR_LEN];
-	char *result[ARRAY_SIZE(page_pool_info_items)];
+	struct hnae3_handle *h = hnae3_seq_file_to_handle(s);
 	struct hns3_nic_priv *priv = h->priv;
-	char content[HNS3_DBG_INFO_LEN];
 	struct hns3_enet_ring *ring;
-	int pos = 0;
 	u32 i;
 
 	if (!priv->ring) {
@@ -1159,182 +800,50 @@ hns3_dbg_page_pool_info(struct hnae3_handle *h, char *buf, int len)
 		return -EFAULT;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(page_pool_info_items); i++)
-		result[i] = &data_str[i][0];
+	seq_puts(s, "QUEUE_ID  ALLOCATE_CNT  FREE_CNT      ");
+	seq_puts(s, "POOL_SIZE(PAGE_NUM)  ORDER  NUMA_ID  MAX_LEN\n");
 
-	hns3_dbg_fill_content(content, sizeof(content), page_pool_info_items,
-			      NULL, ARRAY_SIZE(page_pool_info_items));
-	pos += scnprintf(buf + pos, len - pos, "%s", content);
 	for (i = 0; i < h->kinfo.num_tqps; i++) {
 		if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
 		    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
 			return -EPERM;
+
 		ring = &priv->ring[(u32)(i + h->kinfo.num_tqps)];
-		hns3_dump_page_pool_info(ring, result, i);
-		hns3_dbg_fill_content(content, sizeof(content),
-				      page_pool_info_items,
-				      (const char **)result,
-				      ARRAY_SIZE(page_pool_info_items));
-		pos += scnprintf(buf + pos, len - pos, "%s", content);
+		hns3_dump_page_pool_info(ring, s, i);
 	}
 
 	return 0;
 }
 
-static int hns3_dbg_get_cmd_index(struct hns3_dbg_data *dbg_data, u32 *index)
-{
-	u32 i;
-
-	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) {
-		if (hns3_dbg_cmd[i].cmd == dbg_data->cmd) {
-			*index = i;
-			return 0;
-		}
-	}
-
-	dev_err(&dbg_data->handle->pdev->dev, "unknown command(%d)\n",
-		dbg_data->cmd);
-	return -EINVAL;
-}
-
-static const struct hns3_dbg_func hns3_dbg_cmd_func[] = {
-	{
-		.cmd = HNAE3_DBG_CMD_QUEUE_MAP,
-		.dbg_dump = hns3_dbg_queue_map,
-	},
-	{
-		.cmd = HNAE3_DBG_CMD_DEV_INFO,
-		.dbg_dump = hns3_dbg_dev_info,
-	},
-	{
-		.cmd = HNAE3_DBG_CMD_TX_BD,
-		.dbg_dump_bd = hns3_dbg_tx_bd_info,
-	},
-	{
-		.cmd = HNAE3_DBG_CMD_RX_BD,
-		.dbg_dump_bd = hns3_dbg_rx_bd_info,
-	},
-	{
-		.cmd = HNAE3_DBG_CMD_RX_QUEUE_INFO,
-		.dbg_dump = hns3_dbg_rx_queue_info,
-	},
-	{
-		.cmd = HNAE3_DBG_CMD_TX_QUEUE_INFO,
-		.dbg_dump = hns3_dbg_tx_queue_info,
-	},
-	{
-		.cmd = HNAE3_DBG_CMD_PAGE_POOL_INFO,
-		.dbg_dump = hns3_dbg_page_pool_info,
-	},
-	{
-		.cmd = HNAE3_DBG_CMD_COAL_INFO,
-		.dbg_dump = hns3_dbg_coal_info,
-	},
-};
-
-static int hns3_dbg_read_cmd(struct hns3_dbg_data *dbg_data,
-			     enum hnae3_dbg_cmd cmd, char *buf, int len)
-{
-	const struct hnae3_ae_ops *ops = dbg_data->handle->ae_algo->ops;
-	const struct hns3_dbg_func *cmd_func;
-	u32 i;
-
-	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd_func); i++) {
-		if (cmd == hns3_dbg_cmd_func[i].cmd) {
-			cmd_func = &hns3_dbg_cmd_func[i];
-			if (cmd_func->dbg_dump)
-				return cmd_func->dbg_dump(dbg_data->handle, buf,
-							  len);
-			else
-				return cmd_func->dbg_dump_bd(dbg_data, buf,
-							     len);
-		}
-	}
-
-	if (!ops->dbg_read_cmd)
-		return -EOPNOTSUPP;
-
-	return ops->dbg_read_cmd(dbg_data->handle, cmd, buf, len);
-}
-
-static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer,
-			     size_t count, loff_t *ppos)
+static int hns3_dbg_bd_info_show(struct seq_file *s, void *private)
 {
-	struct hns3_dbg_data *dbg_data = filp->private_data;
-	struct hnae3_handle *handle = dbg_data->handle;
-	struct hns3_nic_priv *priv = handle->priv;
-	ssize_t size = 0;
-	char **save_buf;
-	char *read_buf;
-	u32 index;
-	int ret;
-
-	ret = hns3_dbg_get_cmd_index(dbg_data, &index);
-	if (ret)
-		return ret;
-
-	mutex_lock(&handle->dbgfs_lock);
-	save_buf = &handle->dbgfs_buf[index];
+	struct hns3_dbg_data *data = s->private;
+	struct hnae3_handle *h = data->handle;
+	struct hns3_nic_priv *priv = h->priv;
 
 	if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
-	    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	if (*save_buf) {
-		read_buf = *save_buf;
-	} else {
-		read_buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL);
-		if (!read_buf) {
-			ret = -ENOMEM;
-			goto out;
-		}
+	    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
+		return -EBUSY;
 
-		/* save the buffer addr until the last read operation */
-		*save_buf = read_buf;
+	if (data->cmd == HNAE3_DBG_CMD_TX_BD)
+		return hns3_dbg_tx_bd_info(s, private);
+	else if (data->cmd == HNAE3_DBG_CMD_RX_BD)
+		return hns3_dbg_rx_bd_info(s, private);
 
-		/* get data ready for the first time to read */
-		ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd,
-					read_buf, hns3_dbg_cmd[index].buf_len);
-		if (ret)
-			goto out;
-	}
-
-	size = simple_read_from_buffer(buffer, count, ppos, read_buf,
-				       strlen(read_buf));
-	if (size > 0) {
-		mutex_unlock(&handle->dbgfs_lock);
-		return size;
-	}
-
-out:
-	/* free the buffer for the last read operation */
-	if (*save_buf) {
-		kvfree(*save_buf);
-		*save_buf = NULL;
-	}
-
-	mutex_unlock(&handle->dbgfs_lock);
-	return ret;
+	return -EOPNOTSUPP;
 }
-
-static const struct file_operations hns3_dbg_fops = {
-	.owner = THIS_MODULE,
-	.open  = simple_open,
-	.read  = hns3_dbg_read,
-};
+DEFINE_SHOW_ATTRIBUTE(hns3_dbg_bd_info);
 
 static int hns3_dbg_bd_file_init(struct hnae3_handle *handle, u32 cmd)
 {
-	struct dentry *entry_dir;
 	struct hns3_dbg_data *data;
+	struct dentry *entry_dir;
 	u16 max_queue_num;
 	unsigned int i;
 
 	entry_dir = hns3_dbg_dentry[hns3_dbg_cmd[cmd].dentry].dentry;
 	max_queue_num = hns3_get_max_available_channels(handle);
-	data = devm_kzalloc(&handle->pdev->dev, max_queue_num * sizeof(*data),
+	data = devm_kcalloc(&handle->pdev->dev, max_queue_num, sizeof(*data),
 			    GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
@@ -1347,45 +856,77 @@ static int hns3_dbg_bd_file_init(struct hnae3_handle *handle, u32 cmd)
 		data[i].qid = i;
 		sprintf(name, "%s%u", hns3_dbg_cmd[cmd].name, i);
 		debugfs_create_file(name, 0400, entry_dir, &data[i],
-				    &hns3_dbg_fops);
+				    &hns3_dbg_bd_info_fops);
 	}
 
 	return 0;
 }
 
-static int
-hns3_dbg_common_file_init(struct hnae3_handle *handle, u32 cmd)
+static int hns3_dbg_common_init_t1(struct hnae3_handle *handle, u32 cmd)
 {
-	struct hns3_dbg_data *data;
+	struct device *dev = &handle->pdev->dev;
 	struct dentry *entry_dir;
+	read_func func = NULL;
+
+	switch (hns3_dbg_cmd[cmd].cmd) {
+	case HNAE3_DBG_CMD_TX_QUEUE_INFO:
+		func = hns3_dbg_tx_queue_info;
+		break;
+	case HNAE3_DBG_CMD_RX_QUEUE_INFO:
+		func = hns3_dbg_rx_queue_info;
+		break;
+	case HNAE3_DBG_CMD_QUEUE_MAP:
+		func = hns3_dbg_queue_map;
+		break;
+	case HNAE3_DBG_CMD_PAGE_POOL_INFO:
+		func = hns3_dbg_page_pool_info;
+		break;
+	case HNAE3_DBG_CMD_COAL_INFO:
+		func = hns3_dbg_coal_info;
+		break;
+	case HNAE3_DBG_CMD_DEV_INFO:
+		func = hns3_dbg_dev_info;
+		break;
+	default:
+		return -EINVAL;
+	}
 
-	data = devm_kzalloc(&handle->pdev->dev, sizeof(*data), GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
+	entry_dir = hns3_dbg_dentry[hns3_dbg_cmd[cmd].dentry].dentry;
+	debugfs_create_devm_seqfile(dev, hns3_dbg_cmd[cmd].name, entry_dir,
+				    func);
+
+	return 0;
+}
+
+static int hns3_dbg_common_init_t2(struct hnae3_handle *handle, u32 cmd)
+{
+	const struct hnae3_ae_ops *ops = hns3_get_ops(handle);
+	struct device *dev = &handle->pdev->dev;
+	struct dentry *entry_dir;
+	read_func func;
+	int ret;
+
+	if (!ops->dbg_get_read_func)
+		return 0;
+
+	ret = ops->dbg_get_read_func(handle, hns3_dbg_cmd[cmd].cmd, &func);
+	if (ret)
+		return ret;
 
-	data->handle = handle;
-	data->cmd = hns3_dbg_cmd[cmd].cmd;
 	entry_dir = hns3_dbg_dentry[hns3_dbg_cmd[cmd].dentry].dentry;
-	debugfs_create_file(hns3_dbg_cmd[cmd].name, 0400, entry_dir,
-			    data, &hns3_dbg_fops);
+	debugfs_create_devm_seqfile(dev, hns3_dbg_cmd[cmd].name, entry_dir,
+				    func);
 
 	return 0;
 }
 
 int hns3_dbg_init(struct hnae3_handle *handle)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(handle);
 	const char *name = pci_name(handle->pdev);
 	int ret;
 	u32 i;
 
-	handle->dbgfs_buf = devm_kcalloc(&handle->pdev->dev,
-					 ARRAY_SIZE(hns3_dbg_cmd),
-					 sizeof(*handle->dbgfs_buf),
-					 GFP_KERNEL);
-	if (!handle->dbgfs_buf)
-		return -ENOMEM;
-
 	hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry =
 				debugfs_create_dir(name, hns3_dbgfs_root);
 	handle->hnae3_dbgfs = hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry;
@@ -1395,8 +936,6 @@ int hns3_dbg_init(struct hnae3_handle *handle)
 			debugfs_create_dir(hns3_dbg_dentry[i].name,
 					   handle->hnae3_dbgfs);
 
-	mutex_init(&handle->dbgfs_lock);
-
 	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) {
 		if ((hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES &&
 		     ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) ||
@@ -1425,24 +964,13 @@ int hns3_dbg_init(struct hnae3_handle *handle)
 out:
 	debugfs_remove_recursive(handle->hnae3_dbgfs);
 	handle->hnae3_dbgfs = NULL;
-	mutex_destroy(&handle->dbgfs_lock);
 	return ret;
 }
 
 void hns3_dbg_uninit(struct hnae3_handle *handle)
 {
-	u32 i;
-
 	debugfs_remove_recursive(handle->hnae3_dbgfs);
 	handle->hnae3_dbgfs = NULL;
-
-	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++)
-		if (handle->dbgfs_buf[i]) {
-			kvfree(handle->dbgfs_buf[i]);
-			handle->dbgfs_buf[i] = NULL;
-		}
-
-	mutex_destroy(&handle->dbgfs_lock);
 }
 
 void hns3_dbg_register_debugfs(const char *debugfs_dir_name)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h
index 4a5ef8a90a10..57c9d3fc1b27 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h
@@ -6,15 +6,6 @@
 
 #include "hnae3.h"
 
-#define HNS3_DBG_READ_LEN	65536
-#define HNS3_DBG_READ_LEN_128KB	0x20000
-#define HNS3_DBG_READ_LEN_1MB	0x100000
-#define HNS3_DBG_READ_LEN_4MB	0x400000
-#define HNS3_DBG_READ_LEN_5MB	0x500000
-#define HNS3_DBG_WRITE_LEN	1024
-
-#define HNS3_DBG_DATA_STR_LEN	32
-#define HNS3_DBG_INFO_LEN	256
 #define HNS3_DBG_ITEM_NAME_LEN	32
 #define HNS3_DBG_FILE_NAME_LEN	16
 
@@ -49,16 +40,9 @@ struct hns3_dbg_cmd_info {
 	const char *name;
 	enum hnae3_dbg_cmd cmd;
 	enum hns3_dbg_dentry_type dentry;
-	u32 buf_len;
 	int (*init)(struct hnae3_handle *handle, unsigned int cmd);
 };
 
-struct hns3_dbg_func {
-	enum hnae3_dbg_cmd cmd;
-	int (*dbg_dump)(struct hnae3_handle *handle, char *buf, int len);
-	int (*dbg_dump_bd)(struct hns3_dbg_data *data, char *buf, int len);
-};
-
 struct hns3_dbg_cap_info {
 	const char *name;
 	enum HNAE3_DEV_CAP_BITS cap_bit;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 43377a7b2426..7a0654e2d3dd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -11,6 +11,7 @@
 #include <linux/irq.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/skbuff.h>
@@ -473,20 +474,14 @@ static void hns3_mask_vector_irq(struct hns3_enet_tqp_vector *tqp_vector,
 	writel(mask_en, tqp_vector->mask_addr);
 }
 
-static void hns3_vector_enable(struct hns3_enet_tqp_vector *tqp_vector)
+static void hns3_irq_enable(struct hns3_enet_tqp_vector *tqp_vector)
 {
 	napi_enable(&tqp_vector->napi);
 	enable_irq(tqp_vector->vector_irq);
-
-	/* enable vector */
-	hns3_mask_vector_irq(tqp_vector, 1);
 }
 
-static void hns3_vector_disable(struct hns3_enet_tqp_vector *tqp_vector)
+static void hns3_irq_disable(struct hns3_enet_tqp_vector *tqp_vector)
 {
-	/* disable vector */
-	hns3_mask_vector_irq(tqp_vector, 0);
-
 	disable_irq(tqp_vector->vector_irq);
 	napi_disable(&tqp_vector->napi);
 	cancel_work_sync(&tqp_vector->rx_group.dim.work);
@@ -553,9 +548,9 @@ void hns3_set_vector_coalesce_rx_ql(struct hns3_enet_tqp_vector *tqp_vector,
 static void hns3_vector_coalesce_init(struct hns3_enet_tqp_vector *tqp_vector,
 				      struct hns3_nic_priv *priv)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev);
 	struct hns3_enet_coalesce *tx_coal = &tqp_vector->tx_group.coal;
 	struct hns3_enet_coalesce *rx_coal = &tqp_vector->rx_group.coal;
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(priv->ae_handle);
 	struct hns3_enet_coalesce *ptx_coal = &priv->tx_coal;
 	struct hns3_enet_coalesce *prx_coal = &priv->rx_coal;
 
@@ -707,11 +702,42 @@ static int hns3_set_rx_cpu_rmap(struct net_device *netdev)
 	return 0;
 }
 
+static void hns3_enable_irqs_and_tqps(struct net_device *netdev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = priv->ae_handle;
+	u16 i;
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_irq_enable(&priv->tqp_vector[i]);
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_mask_vector_irq(&priv->tqp_vector[i], 1);
+
+	for (i = 0; i < h->kinfo.num_tqps; i++)
+		hns3_tqp_enable(h->kinfo.tqp[i]);
+}
+
+static void hns3_disable_irqs_and_tqps(struct net_device *netdev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = priv->ae_handle;
+	u16 i;
+
+	for (i = 0; i < h->kinfo.num_tqps; i++)
+		hns3_tqp_disable(h->kinfo.tqp[i]);
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_mask_vector_irq(&priv->tqp_vector[i], 0);
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_irq_disable(&priv->tqp_vector[i]);
+}
+
 static int hns3_nic_net_up(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = priv->ae_handle;
-	int i, j;
 	int ret;
 
 	ret = hns3_nic_reset_all_ring(h);
@@ -720,23 +746,13 @@ static int hns3_nic_net_up(struct net_device *netdev)
 
 	clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
-	/* enable the vectors */
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_enable(&priv->tqp_vector[i]);
-
-	/* enable rcb */
-	for (j = 0; j < h->kinfo.num_tqps; j++)
-		hns3_tqp_enable(h->kinfo.tqp[j]);
+	hns3_enable_irqs_and_tqps(netdev);
 
 	/* start the ae_dev */
 	ret = h->ae_algo->ops->start ? h->ae_algo->ops->start(h) : 0;
 	if (ret) {
 		set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
-		while (j--)
-			hns3_tqp_disable(h->kinfo.tqp[j]);
-
-		for (j = i - 1; j >= 0; j--)
-			hns3_vector_disable(&priv->tqp_vector[j]);
+		hns3_disable_irqs_and_tqps(netdev);
 	}
 
 	return ret;
@@ -823,17 +839,9 @@ static void hns3_reset_tx_queue(struct hnae3_handle *h)
 static void hns3_nic_net_down(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = hns3_get_handle(netdev);
 	const struct hnae3_ae_ops *ops;
-	int i;
 
-	/* disable vectors */
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_disable(&priv->tqp_vector[i]);
-
-	/* disable rcb */
-	for (i = 0; i < h->kinfo.num_tqps; i++)
-		hns3_tqp_disable(h->kinfo.tqp[i]);
+	hns3_disable_irqs_and_tqps(netdev);
 
 	/* stop ae_dev */
 	ops = priv->ae_handle->ae_algo->ops;
@@ -953,7 +961,7 @@ static void hns3_nic_set_rx_mode(struct net_device *netdev)
 
 void hns3_request_update_promisc_mode(struct hnae3_handle *handle)
 {
-	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	const struct hnae3_ae_ops *ops = hns3_get_ops(handle);
 
 	if (ops->request_update_promisc_mode)
 		ops->request_update_promisc_mode(handle);
@@ -1032,6 +1040,8 @@ static bool hns3_can_use_tx_sgl(struct hns3_enet_ring *ring,
 static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
 {
 	u32 alloc_size = ring->tqp->handle->kinfo.tx_spare_buf_size;
+	struct net_device *netdev = ring_to_netdev(ring);
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hns3_tx_spare *tx_spare;
 	struct page *page;
 	dma_addr_t dma;
@@ -1073,6 +1083,7 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
 	tx_spare->buf = page_address(page);
 	tx_spare->len = PAGE_SIZE << order;
 	ring->tx_spare = tx_spare;
+	ring->tx_copybreak = priv->tx_copybreak;
 	return;
 
 dma_mapping_error:
@@ -1297,7 +1308,7 @@ static int hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto,
 static bool hns3_tunnel_csum_bug(struct sk_buff *skb)
 {
 	struct hns3_nic_priv *priv = netdev_priv(skb->dev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(priv->ae_handle);
 	union l4_hdr_info l4;
 
 	/* device version above V3(include V3), the hardware can
@@ -1497,7 +1508,7 @@ static int hns3_handle_vtags(struct hns3_enet_ring *tx_ring,
 	 * VLAN enabled, only one VLAN header is allowed in skb, otherwise it
 	 * will cause RAS error.
 	 */
-	ae_dev = pci_get_drvdata(handle->pdev);
+	ae_dev = hns3_get_ae_dev(handle);
 	if (unlikely(skb_vlan_tagged_multi(skb) &&
 		     ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2 &&
 		     handle->port_base_vlan_state ==
@@ -1683,8 +1694,8 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, dma_addr_t dma,
 #define HNS3_LIKELY_BD_NUM	1
 
 	struct hns3_desc *desc = &ring->desc[ring->next_to_use];
-	unsigned int frag_buf_num;
-	int k, sizeoflast;
+	unsigned int frag_buf_num, k;
+	int sizeoflast;
 
 	if (likely(size <= HNS3_MAX_BD_SIZE)) {
 		desc->addr = cpu_to_le64(dma);
@@ -1856,7 +1867,7 @@ static bool hns3_skb_need_linearized(struct sk_buff *skb, unsigned int *bd_size,
 				     unsigned int bd_num, u8 max_non_tso_bd_num)
 {
 	unsigned int tot_len = 0;
-	int i;
+	unsigned int i;
 
 	for (i = 0; i < max_non_tso_bd_num - 1U; i++)
 		tot_len += bd_size[i];
@@ -1884,7 +1895,7 @@ static bool hns3_skb_need_linearized(struct sk_buff *skb, unsigned int *bd_size,
 
 void hns3_shinfo_pack(struct skb_shared_info *shinfo, __u32 *size)
 {
-	int i;
+	u32 i;
 
 	for (i = 0; i < MAX_SKB_FRAGS; i++)
 		size[i] = skb_frag_size(&shinfo->frags[i]);
@@ -2099,7 +2110,7 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
 	 */
 	if (test_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state) && num &&
 	    !ring->pending_buf && num <= HNS3_MAX_PUSH_BD_NUM && doorbell) {
-		/* This smp_store_release() pairs with smp_load_aquire() in
+		/* This smp_store_release() pairs with smp_load_acquire() in
 		 * hns3_nic_reclaim_desc(). Ensure that the BD valid bit
 		 * is updated.
 		 */
@@ -2115,7 +2126,7 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
 		return;
 	}
 
-	/* This smp_store_release() pairs with smp_load_aquire() in
+	/* This smp_store_release() pairs with smp_load_acquire() in
 	 * hns3_nic_reclaim_desc(). Ensure that the BD valid bit is updated.
 	 */
 	smp_store_release(&ring->last_to_use, ring->next_to_use);
@@ -2200,9 +2211,9 @@ static int hns3_handle_tx_sgl(struct hns3_enet_ring *ring,
 	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
 	u32 nfrag = skb_shinfo(skb)->nr_frags + 1;
 	struct sg_table *sgt;
-	int i, bd_num = 0;
+	int bd_num = 0;
 	dma_addr_t dma;
-	u32 cb_len;
+	u32 cb_len, i;
 	int nents;
 
 	if (skb_has_frag_list(skb))
@@ -2408,6 +2419,35 @@ static int hns3_nic_do_ioctl(struct net_device *netdev,
 	return h->ae_algo->ops->do_ioctl(h, ifr, cmd);
 }
 
+static int hns3_nic_hwtstamp_get(struct net_device *netdev,
+				 struct kernel_hwtstamp_config *config)
+{
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+
+	if (!netif_running(netdev))
+		return -EINVAL;
+
+	if (!h->ae_algo->ops->hwtstamp_get)
+		return -EOPNOTSUPP;
+
+	return h->ae_algo->ops->hwtstamp_get(h, config);
+}
+
+static int hns3_nic_hwtstamp_set(struct net_device *netdev,
+				 struct kernel_hwtstamp_config *config,
+				 struct netlink_ext_ack *extack)
+{
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+
+	if (!netif_running(netdev))
+		return -EINVAL;
+
+	if (!h->ae_algo->ops->hwtstamp_set)
+		return -EOPNOTSUPP;
+
+	return h->ae_algo->ops->hwtstamp_set(h, config, extack);
+}
+
 static int hns3_nic_set_features(struct net_device *netdev,
 				 netdev_features_t features)
 {
@@ -2440,7 +2480,7 @@ static int hns3_nic_set_features(struct net_device *netdev,
 	if ((netdev->features & NETIF_F_HW_TC) > (features & NETIF_F_HW_TC) &&
 	    h->ae_algo->ops->cls_flower_active(h)) {
 		netdev_err(netdev,
-			   "there are offloaded TC filters active, cannot disable HW TC offload");
+			   "there are offloaded TC filters active, cannot disable HW TC offload\n");
 		return -EINVAL;
 	}
 
@@ -2452,7 +2492,6 @@ static int hns3_nic_set_features(struct net_device *netdev,
 			return ret;
 	}
 
-	netdev->features = features;
 	return 0;
 }
 
@@ -2538,7 +2577,7 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 	struct hnae3_handle *handle = priv->ae_handle;
 	struct rtnl_link_stats64 ring_total_stats;
 	struct hns3_enet_ring *ring;
-	unsigned int idx;
+	int idx;
 
 	if (test_bit(HNS3_NIC_STATE_DOWN, &priv->state))
 		return;
@@ -2764,7 +2803,7 @@ static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu)
 
 static int hns3_get_timeout_queue(struct net_device *ndev)
 {
-	int i;
+	unsigned int i;
 
 	/* Find the stopped queue the same way the stack does */
 	for (i = 0; i < ndev->num_tx_queues; i++) {
@@ -2845,7 +2884,7 @@ static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev)
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 	struct hns3_enet_ring *tx_ring;
-	int timeout_queue;
+	u32 timeout_queue;
 
 	timeout_queue = hns3_get_timeout_queue(ndev);
 	if (timeout_queue >= ndev->num_tx_queues) {
@@ -3038,6 +3077,8 @@ static const struct net_device_ops hns3_nic_netdev_ops = {
 	.ndo_set_vf_rate	= hns3_nic_set_vf_rate,
 	.ndo_set_vf_mac		= hns3_nic_set_vf_mac,
 	.ndo_select_queue	= hns3_nic_select_queue,
+	.ndo_hwtstamp_get	= hns3_nic_hwtstamp_get,
+	.ndo_hwtstamp_set	= hns3_nic_hwtstamp_set,
 };
 
 bool hns3_is_phys_func(struct pci_dev *pdev)
@@ -3815,7 +3856,7 @@ static int hns3_gro_complete(struct sk_buff *skb, u32 l234info)
 {
 	__be16 type = skb->protocol;
 	struct tcphdr *th;
-	int depth = 0;
+	u32 depth = 0;
 
 	while (eth_type_vlan(type)) {
 		struct vlan_hdr *vh;
@@ -4741,7 +4782,7 @@ map_ring_fail:
 
 static void hns3_nic_init_coal_cfg(struct hns3_nic_priv *priv)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(priv->ae_handle);
 	struct hns3_enet_coalesce *tx_coal = &priv->tx_coal;
 	struct hns3_enet_coalesce *rx_coal = &priv->rx_coal;
 
@@ -4868,6 +4909,30 @@ static void hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv)
 	devm_kfree(&pdev->dev, priv->tqp_vector);
 }
 
+static void hns3_update_tx_spare_buf_config(struct hns3_nic_priv *priv)
+{
+#define HNS3_MIN_SPARE_BUF_SIZE (2 * 1024 * 1024)
+#define HNS3_MAX_PACKET_SIZE (64 * 1024)
+
+	struct iommu_domain *domain = iommu_get_domain_for_dev(priv->dev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(priv->ae_handle);
+	struct hnae3_handle *handle = priv->ae_handle;
+
+	if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3)
+		return;
+
+	if (!(domain && iommu_is_dma_domain(domain)))
+		return;
+
+	priv->min_tx_copybreak = HNS3_MAX_PACKET_SIZE;
+	priv->min_tx_spare_buf_size = HNS3_MIN_SPARE_BUF_SIZE;
+
+	if (priv->tx_copybreak < priv->min_tx_copybreak)
+		priv->tx_copybreak = priv->min_tx_copybreak;
+	if (handle->kinfo.tx_spare_buf_size < priv->min_tx_spare_buf_size)
+		handle->kinfo.tx_spare_buf_size = priv->min_tx_spare_buf_size;
+}
+
 static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
 			      unsigned int ring_type)
 {
@@ -5101,6 +5166,7 @@ int hns3_init_all_ring(struct hns3_nic_priv *priv)
 	int i, j;
 	int ret;
 
+	hns3_update_tx_spare_buf_config(priv);
 	for (i = 0; i < ring_num; i++) {
 		ret = hns3_alloc_ring_memory(&priv->ring[i]);
 		if (ret) {
@@ -5220,7 +5286,7 @@ static void hns3_info_show(struct hns3_nic_priv *priv)
 static void hns3_set_cq_period_mode(struct hns3_nic_priv *priv,
 				    enum dim_cq_period_mode mode, bool is_tx)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(priv->ae_handle);
 	struct hnae3_handle *handle = priv->ae_handle;
 	int i;
 
@@ -5258,7 +5324,7 @@ void hns3_cq_period_mode_init(struct hns3_nic_priv *priv,
 
 static void hns3_state_init(struct hnae3_handle *handle)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(handle);
 	struct net_device *netdev = handle->kinfo.netdev;
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 
@@ -5293,6 +5359,8 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	struct net_device *netdev;
 	int ret;
 
+	ae_dev->handle = handle;
+
 	handle->ae_algo->ops->get_tqps_and_rss_info(handle, &alloc_tqps,
 						    &max_rss_size);
 	netdev = alloc_etherdev_mq(sizeof(struct hns3_nic_priv), alloc_tqps);
@@ -5305,6 +5373,8 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	priv->ae_handle = handle;
 	priv->tx_timeout_count = 0;
 	priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num;
+	priv->min_tx_copybreak = 0;
+	priv->min_tx_spare_buf_size = 0;
 	set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
 	handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL);
@@ -5865,8 +5935,6 @@ int hns3_set_channels(struct net_device *netdev,
 void hns3_external_lb_prepare(struct net_device *ndev, bool if_running)
 {
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
-	struct hnae3_handle *h = priv->ae_handle;
-	int i;
 
 	if (!if_running)
 		return;
@@ -5877,11 +5945,7 @@ void hns3_external_lb_prepare(struct net_device *ndev, bool if_running)
 	netif_carrier_off(ndev);
 	netif_tx_disable(ndev);
 
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_disable(&priv->tqp_vector[i]);
-
-	for (i = 0; i < h->kinfo.num_tqps; i++)
-		hns3_tqp_disable(h->kinfo.tqp[i]);
+	hns3_disable_irqs_and_tqps(ndev);
 
 	/* delay ring buffer clearing to hns3_reset_notify_uninit_enet
 	 * during reset process, because driver may not be able
@@ -5897,7 +5961,6 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running)
 {
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
 	struct hnae3_handle *h = priv->ae_handle;
-	int i;
 
 	if (!if_running)
 		return;
@@ -5913,11 +5976,7 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running)
 
 	clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_enable(&priv->tqp_vector[i]);
-
-	for (i = 0; i < h->kinfo.num_tqps; i++)
-		hns3_tqp_enable(h->kinfo.tqp[i]);
+	hns3_enable_irqs_and_tqps(ndev);
 
 	netif_tx_wake_all_queues(ndev);
 
@@ -5939,7 +5998,7 @@ static const struct hns3_hw_error_info hns3_hw_err[] = {
 static void hns3_process_hw_error(struct hnae3_handle *handle,
 				  enum hnae3_hw_error_type type)
 {
-	int i;
+	u32 i;
 
 	for (i = 0; i < ARRAY_SIZE(hns3_hw_err); i++) {
 		if (hns3_hw_err[i].type == type) {
@@ -5966,8 +6025,8 @@ static int __init hns3_init_module(void)
 {
 	int ret;
 
-	pr_info("%s: %s - version\n", hns3_driver_name, hns3_driver_string);
-	pr_info("%s: %s\n", hns3_driver_name, hns3_copyright);
+	pr_debug("%s: %s - version\n", hns3_driver_name, hns3_driver_string);
+	pr_debug("%s: %s\n", hns3_driver_name, hns3_copyright);
 
 	client.type = HNAE3_CLIENT_KNIC;
 	snprintf(client.name, HNAE3_CLIENT_NAME_LENGTH, "%s",
@@ -6003,9 +6062,11 @@ module_init(hns3_init_module);
  */
 static void __exit hns3_exit_module(void)
 {
+	hnae3_acquire_unload_lock();
 	pci_unregister_driver(&hns3_driver);
 	hnae3_unregister_client(&client);
 	hns3_dbg_unregister_debugfs();
+	hnae3_release_unload_lock();
 }
 module_exit(hns3_exit_module);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index d36c4ed16d8d..933e3527ed82 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -596,6 +596,8 @@ struct hns3_nic_priv {
 	struct hns3_enet_coalesce rx_coal;
 	u32 tx_copybreak;
 	u32 rx_copybreak;
+	u32 min_tx_copybreak;
+	u32 min_tx_spare_buf_size;
 };
 
 union l3_hdr_info {
@@ -621,7 +623,7 @@ struct hns3_reset_type_map {
 	enum hnae3_reset_type rst_type;
 };
 
-static inline int ring_space(struct hns3_enet_ring *ring)
+static inline u32 ring_space(struct hns3_enet_ring *ring)
 {
 	/* This smp_load_acquire() pairs with smp_store_release() in
 	 * hns3_nic_reclaim_one_desc called by hns3_clean_tx_ring.
@@ -692,7 +694,7 @@ static inline unsigned int hns3_page_order(struct hns3_enet_ring *ring)
 
 /* iterator for handling rings in ring group */
 #define hns3_for_each_ring(pos, head) \
-	for (pos = (head).ring; (pos); pos = (pos)->next)
+	for ((pos) = (head).ring; (pos); (pos) = (pos)->next)
 
 #define hns3_get_handle(ndev) \
 	(((struct hns3_nic_priv *)netdev_priv(ndev))->ae_handle)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index b771a2daba43..a5eefa28454c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -3,6 +3,7 @@
 
 #include <linux/etherdevice.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/phy.h>
 #include <linux/sfp.h>
 
@@ -85,7 +86,7 @@ static int hns3_get_sset_count(struct net_device *netdev, int stringset);
 static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(h);
 	int ret;
 
 	if (!h->ae_algo->ops->set_loopback ||
@@ -170,7 +171,7 @@ static void hns3_lp_setup_skb(struct sk_buff *skb)
 	 * the purpose of mac or serdes selftest.
 	 */
 	handle = hns3_get_handle(ndev);
-	ae_dev = pci_get_drvdata(handle->pdev);
+	ae_dev = hns3_get_ae_dev(handle);
 	if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2)
 		ethh->h_dest[5] += HNS3_NIC_LB_DST_MAC_ADDR;
 	eth_zero_addr(ethh->h_source);
@@ -435,7 +436,7 @@ static void hns3_self_test(struct net_device *ndev,
 		data[i] = HNS3_NIC_LB_TEST_UNEXECUTED;
 
 	if (hns3_nic_resetting(ndev)) {
-		netdev_err(ndev, "dev resetting!");
+		netdev_err(ndev, "dev resetting!\n");
 		goto failure;
 	}
 
@@ -488,7 +489,7 @@ static const struct hns3_pflag_desc hns3_priv_flags[HNAE3_PFLAG_MAX] = {
 static int hns3_get_sset_count(struct net_device *netdev, int stringset)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
-	const struct hnae3_ae_ops *ops = h->ae_algo->ops;
+	const struct hnae3_ae_ops *ops = hns3_get_ops(h);
 
 	if (!ops->get_sset_count)
 		return -EOPNOTSUPP;
@@ -539,8 +540,8 @@ static void hns3_get_strings_tqps(struct hnae3_handle *handle, u8 **data)
 static void hns3_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
-	const struct hnae3_ae_ops *ops = h->ae_algo->ops;
-	int i;
+	const struct hnae3_ae_ops *ops = hns3_get_ops(h);
+	u32 i;
 
 	if (!ops->get_strings)
 		return;
@@ -568,7 +569,7 @@ static u64 *hns3_get_stats_tqps(struct hnae3_handle *handle, u64 *data)
 	struct hns3_nic_priv *nic_priv = handle->priv;
 	struct hns3_enet_ring *ring;
 	u8 *stat;
-	int i, j;
+	u32 i, j;
 
 	/* get stats for Tx */
 	for (i = 0; i < kinfo->num_tqps; i++) {
@@ -691,7 +692,7 @@ static void hns3_get_pauseparam(struct net_device *netdev,
 				struct ethtool_pauseparam *param)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(h);
 
 	if (!test_bit(HNAE3_DEV_SUPPORT_PAUSE_B, ae_dev->caps))
 		return;
@@ -705,7 +706,7 @@ static int hns3_set_pauseparam(struct net_device *netdev,
 			       struct ethtool_pauseparam *param)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(h);
 
 	if (!test_bit(HNAE3_DEV_SUPPORT_PAUSE_B, ae_dev->caps))
 		return -EOPNOTSUPP;
@@ -724,7 +725,7 @@ static int hns3_set_pauseparam(struct net_device *netdev,
 static void hns3_get_ksettings(struct hnae3_handle *h,
 			       struct ethtool_link_ksettings *cmd)
 {
-	const struct hnae3_ae_ops *ops = h->ae_algo->ops;
+	const struct hnae3_ae_ops *ops = hns3_get_ops(h);
 
 	/* 1.auto_neg & speed & duplex from cmd */
 	if (ops->get_ksettings_an_result)
@@ -750,7 +751,7 @@ static int hns3_get_link_ksettings(struct net_device *netdev,
 				   struct ethtool_link_ksettings *cmd)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(h);
 	const struct hnae3_ae_ops *ops;
 	u8 module_type;
 	u8 media_type;
@@ -793,7 +794,7 @@ static int hns3_get_link_ksettings(struct net_device *netdev,
 		break;
 	default:
 
-		netdev_warn(netdev, "Unknown media type");
+		netdev_warn(netdev, "Unknown media type\n");
 		return 0;
 	}
 
@@ -813,7 +814,7 @@ static int hns3_check_ksettings_param(const struct net_device *netdev,
 				      const struct ethtool_link_ksettings *cmd)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
-	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	const struct hnae3_ae_ops *ops = hns3_get_ops(handle);
 	u8 module_type = HNAE3_MODULE_TYPE_UNKNOWN;
 	u8 media_type = HNAE3_MEDIA_TYPE_UNKNOWN;
 	u32 lane_num;
@@ -841,7 +842,7 @@ static int hns3_check_ksettings_param(const struct net_device *netdev,
 	if (cmd->base.duplex == DUPLEX_HALF &&
 	    media_type != HNAE3_MEDIA_TYPE_COPPER) {
 		netdev_err(netdev,
-			   "only copper port supports half duplex!");
+			   "only copper port supports half duplex!\n");
 		return -EINVAL;
 	}
 
@@ -860,8 +861,8 @@ static int hns3_set_link_ksettings(struct net_device *netdev,
 				   const struct ethtool_link_ksettings *cmd)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
-	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(handle);
+	const struct hnae3_ae_ops *ops = hns3_get_ops(handle);
 	int ret;
 
 	/* Chip don't support this mode. */
@@ -931,7 +932,7 @@ static u32 hns3_get_rss_key_size(struct net_device *netdev)
 static u32 hns3_get_rss_indir_size(struct net_device *netdev)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(h);
 
 	return ae_dev->dev_specs.rss_ind_tbl_size;
 }
@@ -953,7 +954,7 @@ static int hns3_set_rss(struct net_device *netdev,
 			struct netlink_ext_ack *extack)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(h);
 
 	if (!h->ae_algo->ops->set_rss)
 		return -EOPNOTSUPP;
@@ -977,6 +978,16 @@ static int hns3_set_rss(struct net_device *netdev,
 					rxfh->hfunc);
 }
 
+static int hns3_get_rxfh_fields(struct net_device *netdev,
+				struct ethtool_rxfh_fields *cmd)
+{
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+
+	if (h->ae_algo->ops->get_rss_tuple)
+		return h->ae_algo->ops->get_rss_tuple(h, cmd);
+	return -EOPNOTSUPP;
+}
+
 static int hns3_get_rxnfc(struct net_device *netdev,
 			  struct ethtool_rxnfc *cmd,
 			  u32 *rule_locs)
@@ -987,10 +998,6 @@ static int hns3_get_rxnfc(struct net_device *netdev,
 	case ETHTOOL_GRXRINGS:
 		cmd->data = h->kinfo.num_tqps;
 		return 0;
-	case ETHTOOL_GRXFH:
-		if (h->ae_algo->ops->get_rss_tuple)
-			return h->ae_algo->ops->get_rss_tuple(h, cmd);
-		return -EOPNOTSUPP;
 	case ETHTOOL_GRXCLSRLCNT:
 		if (h->ae_algo->ops->get_fd_rule_cnt)
 			return h->ae_algo->ops->get_fd_rule_cnt(h, cmd);
@@ -1023,8 +1030,8 @@ static int hns3_set_reset(struct net_device *netdev, u32 *flags)
 {
 	enum hnae3_reset_type rst_type = HNAE3_NONE_RESET;
 	struct hnae3_handle *h = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
-	const struct hnae3_ae_ops *ops = h->ae_algo->ops;
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(h);
+	const struct hnae3_ae_ops *ops = hns3_get_ops(h);
 	const struct hns3_reset_type_map *rst_type_map;
 	enum ethtool_reset_flags rst_flags;
 	u32 i, size;
@@ -1188,7 +1195,7 @@ static int hns3_set_tx_push(struct net_device *netdev, u32 tx_push)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(h);
 	u32 old_state = test_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state);
 
 	if (!test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, ae_dev->caps) && tx_push)
@@ -1198,7 +1205,7 @@ static int hns3_set_tx_push(struct net_device *netdev, u32 tx_push)
 		return 0;
 
 	netdev_dbg(netdev, "Changing tx push from %s to %s\n",
-		   old_state ? "on" : "off", tx_push ? "on" : "off");
+		   str_on_off(old_state), str_on_off(tx_push));
 
 	if (tx_push)
 		set_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state);
@@ -1274,15 +1281,22 @@ static int hns3_set_ringparam(struct net_device *ndev,
 	return ret;
 }
 
+static int hns3_set_rxfh_fields(struct net_device *netdev,
+				const struct ethtool_rxfh_fields *cmd,
+				struct netlink_ext_ack *extack)
+{
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+
+	if (h->ae_algo->ops->set_rss_tuple)
+		return h->ae_algo->ops->set_rss_tuple(h, cmd);
+	return -EOPNOTSUPP;
+}
+
 static int hns3_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	switch (cmd->cmd) {
-	case ETHTOOL_SRXFH:
-		if (h->ae_algo->ops->set_rss_tuple)
-			return h->ae_algo->ops->set_rss_tuple(h, cmd);
-		return -EOPNOTSUPP;
 	case ETHTOOL_SRXCLSRLINS:
 		if (h->ae_algo->ops->add_fd_entry)
 			return h->ae_algo->ops->add_fd_entry(h, cmd);
@@ -1299,7 +1313,7 @@ static int hns3_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 static int hns3_nway_reset(struct net_device *netdev)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
-	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	const struct hnae3_ae_ops *ops = hns3_get_ops(handle);
 	struct phy_device *phy = netdev->phydev;
 	int autoneg;
 
@@ -1307,7 +1321,7 @@ static int hns3_nway_reset(struct net_device *netdev)
 		return 0;
 
 	if (hns3_nic_resetting(netdev)) {
-		netdev_err(netdev, "dev resetting!");
+		netdev_err(netdev, "dev resetting!\n");
 		return -EBUSY;
 	}
 
@@ -1376,7 +1390,7 @@ static int hns3_check_gl_coalesce_para(struct net_device *netdev,
 				       struct ethtool_coalesce *cmd)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(handle);
 	u32 rx_gl, tx_gl;
 
 	if (cmd->rx_coalesce_usecs > ae_dev->dev_specs.max_int_gl) {
@@ -1448,7 +1462,7 @@ static int hns3_check_ql_coalesce_param(struct net_device *netdev,
 					struct ethtool_coalesce *cmd)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(handle);
 
 	if ((cmd->tx_max_coalesced_frames || cmd->rx_max_coalesced_frames) &&
 	    !ae_dev->dev_specs.int_ql_max) {
@@ -1472,7 +1486,7 @@ hns3_check_cqe_coalesce_param(struct net_device *netdev,
 			      struct kernel_ethtool_coalesce *kernel_coal)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(handle);
 
 	if ((kernel_coal->use_cqe_mode_tx || kernel_coal->use_cqe_mode_rx) &&
 	    !hnae3_ae_dev_cq_supported(ae_dev)) {
@@ -1645,11 +1659,12 @@ static void hns3_set_msglevel(struct net_device *netdev, u32 msg_level)
 }
 
 static void hns3_get_fec_stats(struct net_device *netdev,
-			       struct ethtool_fec_stats *fec_stats)
+			       struct ethtool_fec_stats *fec_stats,
+			       struct ethtool_fec_hist *hist)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
-	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(handle);
+	const struct hnae3_ae_ops *ops = hns3_get_ops(handle);
 
 	if (!hnae3_ae_dev_fec_stats_supported(ae_dev) || !ops->get_fec_stats)
 		return;
@@ -1699,8 +1714,8 @@ static int hns3_get_fecparam(struct net_device *netdev,
 			     struct ethtool_fecparam *fec)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
-	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(handle);
+	const struct hnae3_ae_ops *ops = hns3_get_ops(handle);
 	u8 fec_ability;
 	u8 fec_mode;
 
@@ -1724,8 +1739,8 @@ static int hns3_set_fecparam(struct net_device *netdev,
 			     struct ethtool_fecparam *fec)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
-	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(handle);
+	const struct hnae3_ae_ops *ops = hns3_get_ops(handle);
 	u32 fec_mode;
 
 	if (!test_bit(HNAE3_DEV_SUPPORT_FEC_B, ae_dev->caps))
@@ -1746,8 +1761,8 @@ static int hns3_get_module_info(struct net_device *netdev,
 #define HNS3_SFF_8636_V1_3 0x03
 
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
-	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(handle);
+	const struct hnae3_ae_ops *ops = hns3_get_ops(handle);
 	struct hns3_sfp_type sfp_type;
 	int ret;
 
@@ -1796,8 +1811,8 @@ static int hns3_get_module_eeprom(struct net_device *netdev,
 				  struct ethtool_eeprom *ee, u8 *data)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
-	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(handle);
+	const struct hnae3_ae_ops *ops = hns3_get_ops(handle);
 
 	if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2 ||
 	    !ops->get_module_eeprom)
@@ -1913,6 +1928,31 @@ static int hns3_set_tx_spare_buf_size(struct net_device *netdev,
 	return ret;
 }
 
+static int hns3_check_tx_copybreak(struct net_device *netdev, u32 copybreak)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+
+	if (copybreak < priv->min_tx_copybreak) {
+		netdev_err(netdev, "tx copybreak %u should be no less than %u!\n",
+			   copybreak, priv->min_tx_copybreak);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int hns3_check_tx_spare_buf_size(struct net_device *netdev, u32 buf_size)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+
+	if (buf_size < priv->min_tx_spare_buf_size) {
+		netdev_err(netdev,
+			   "tx spare buf size %u should be no less than %u!\n",
+			   buf_size, priv->min_tx_spare_buf_size);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int hns3_set_tunable(struct net_device *netdev,
 			    const struct ethtool_tunable *tuna,
 			    const void *data)
@@ -1923,12 +1963,16 @@ static int hns3_set_tunable(struct net_device *netdev,
 	int i, ret = 0;
 
 	if (hns3_nic_resetting(netdev) || !priv->ring) {
-		netdev_err(netdev, "failed to set tunable value, dev resetting!");
+		netdev_err(netdev, "failed to set tunable value, dev resetting!\n");
 		return -EBUSY;
 	}
 
 	switch (tuna->id) {
 	case ETHTOOL_TX_COPYBREAK:
+		ret = hns3_check_tx_copybreak(netdev, *(u32 *)data);
+		if (ret)
+			return ret;
+
 		priv->tx_copybreak = *(u32 *)data;
 
 		for (i = 0; i < h->kinfo.num_tqps; i++)
@@ -1943,6 +1987,10 @@ static int hns3_set_tunable(struct net_device *netdev,
 
 		break;
 	case ETHTOOL_TX_COPYBREAK_BUF_SIZE:
+		ret = hns3_check_tx_spare_buf_size(netdev, *(u32 *)data);
+		if (ret)
+			return ret;
+
 		old_tx_spare_buf_size = h->kinfo.tx_spare_buf_size;
 		new_tx_spare_buf_size = *(u32 *)data;
 		netdev_info(netdev, "request to set tx spare buf size from %u to %u\n",
@@ -2104,6 +2152,8 @@ static const struct ethtool_ops hns3vf_ethtool_ops = {
 	.get_rxfh_indir_size = hns3_get_rss_indir_size,
 	.get_rxfh = hns3_get_rss,
 	.set_rxfh = hns3_set_rss,
+	.get_rxfh_fields = hns3_get_rxfh_fields,
+	.set_rxfh_fields = hns3_set_rxfh_fields,
 	.get_link_ksettings = hns3_get_link_ksettings,
 	.get_channels = hns3_get_channels,
 	.set_channels = hns3_set_channels,
@@ -2141,6 +2191,8 @@ static const struct ethtool_ops hns3_ethtool_ops = {
 	.get_rxfh_indir_size = hns3_get_rss_indir_size,
 	.get_rxfh = hns3_get_rss,
 	.set_rxfh = hns3_set_rss,
+	.get_rxfh_fields = hns3_get_rxfh_fields,
+	.set_rxfh_fields = hns3_set_rxfh_fields,
 	.get_link_ksettings = hns3_get_link_ksettings,
 	.set_link_ksettings = hns3_set_link_ksettings,
 	.nway_reset = hns3_nway_reset,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index debf143e9940..b76d25074e99 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -3,6 +3,7 @@
 
 #include <linux/device.h>
 #include <linux/sched/clock.h>
+#include <linux/string_choices.h>
 
 #include "hclge_debugfs.h"
 #include "hclge_err.h"
@@ -11,7 +12,9 @@
 #include "hclge_tm.h"
 #include "hnae3.h"
 
-static const char * const state_str[] = { "off", "on" };
+#define hclge_seq_file_to_hdev(s)	\
+		(((struct hnae3_ae_dev *)hnae3_seq_file_to_ae_dev(s))->priv)
+
 static const char * const hclge_mac_state_str[] = {
 	"TO_ADD", "TO_DEL", "ACTIVE"
 };
@@ -721,48 +724,6 @@ static const struct hclge_dbg_reg_type_info hclge_dbg_reg_info[] = {
 		       .cmd = HCLGE_OPC_DFX_TQP_REG } },
 };
 
-/* make sure: len(name) + interval >= maxlen(item data) + 2,
- * for example, name = "pkt_num"(len: 7), the prototype of item data is u32,
- * and print as "%u"(maxlen: 10), so the interval should be at least 5.
- */
-static void hclge_dbg_fill_content(char *content, u16 len,
-				   const struct hclge_dbg_item *items,
-				   const char **result, u16 size)
-{
-#define HCLGE_DBG_LINE_END_LEN	2
-	char *pos = content;
-	u16 item_len;
-	u16 i;
-
-	if (!len) {
-		return;
-	} else if (len <= HCLGE_DBG_LINE_END_LEN) {
-		*pos++ = '\0';
-		return;
-	}
-
-	memset(content, ' ', len);
-	len -= HCLGE_DBG_LINE_END_LEN;
-
-	for (i = 0; i < size; i++) {
-		item_len = strlen(items[i].name) + items[i].interval;
-		if (len < item_len)
-			break;
-
-		if (result) {
-			if (item_len < strlen(result[i]))
-				break;
-			memcpy(pos, result[i], strlen(result[i]));
-		} else {
-			memcpy(pos, items[i].name, strlen(items[i].name));
-		}
-		pos += item_len;
-		len -= item_len;
-	}
-	*pos++ = '\n';
-	*pos++ = '\0';
-}
-
 static char *hclge_dbg_get_func_id_str(char *buf, u8 id)
 {
 	if (id)
@@ -826,14 +787,14 @@ int hclge_dbg_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc_src,
 static int
 hclge_dbg_dump_reg_tqp(struct hclge_dev *hdev,
 		       const struct hclge_dbg_reg_type_info *reg_info,
-		       char *buf, int len, int *pos)
+		       struct seq_file *s)
 {
 	const struct hclge_dbg_dfx_message *dfx_message = reg_info->dfx_msg;
 	const struct hclge_dbg_reg_common_msg *reg_msg = &reg_info->reg_msg;
+	u32 index, entry, i, cnt, min_num;
 	struct hclge_desc *desc_src;
-	u32 index, entry, i, cnt;
-	int bd_num, min_num, ret;
 	struct hclge_desc *desc;
+	int bd_num, ret;
 
 	ret = hclge_dbg_get_dfx_bd_num(hdev, reg_msg->offset, &bd_num);
 	if (ret)
@@ -846,13 +807,12 @@ hclge_dbg_dump_reg_tqp(struct hclge_dev *hdev,
 	min_num = min_t(int, bd_num * HCLGE_DESC_DATA_LEN, reg_msg->msg_num);
 
 	for (i = 0, cnt = 0; i < min_num; i++, dfx_message++)
-		*pos += scnprintf(buf + *pos, len - *pos, "item%u = %s\n",
-				  cnt++, dfx_message->message);
+		seq_printf(s, "item%u = %s\n", cnt++, dfx_message->message);
 
 	for (i = 0; i < cnt; i++)
-		*pos += scnprintf(buf + *pos, len - *pos, "item%u\t", i);
+		seq_printf(s, "item%u\t", i);
 
-	*pos += scnprintf(buf + *pos, len - *pos, "\n");
+	seq_puts(s, "\n");
 
 	for (index = 0; index < hdev->vport[0].alloc_tqps; index++) {
 		dfx_message = reg_info->dfx_msg;
@@ -867,10 +827,9 @@ hclge_dbg_dump_reg_tqp(struct hclge_dev *hdev,
 			if (i > 0 && !entry)
 				desc++;
 
-			*pos += scnprintf(buf + *pos, len - *pos, "%#x\t",
-					  le32_to_cpu(desc->data[entry]));
+			seq_printf(s, "%#x\t", le32_to_cpu(desc->data[entry]));
 		}
-		*pos += scnprintf(buf + *pos, len - *pos, "\n");
+		seq_puts(s, "\n");
 	}
 
 	kfree(desc_src);
@@ -880,14 +839,14 @@ hclge_dbg_dump_reg_tqp(struct hclge_dev *hdev,
 static int
 hclge_dbg_dump_reg_common(struct hclge_dev *hdev,
 			  const struct hclge_dbg_reg_type_info *reg_info,
-			  char *buf, int len, int *pos)
+			  struct seq_file *s)
 {
 	const struct hclge_dbg_reg_common_msg *reg_msg = &reg_info->reg_msg;
 	const struct hclge_dbg_dfx_message *dfx_message = reg_info->dfx_msg;
 	struct hclge_desc *desc_src;
-	int bd_num, min_num, ret;
+	int bd_num, min_num, ret, i;
 	struct hclge_desc *desc;
-	u32 entry, i;
+	u32 entry;
 
 	ret = hclge_dbg_get_dfx_bd_num(hdev, reg_msg->offset, &bd_num);
 	if (ret)
@@ -914,9 +873,8 @@ hclge_dbg_dump_reg_common(struct hclge_dev *hdev,
 		if (!dfx_message->flag)
 			continue;
 
-		*pos += scnprintf(buf + *pos, len - *pos, "%s: %#x\n",
-				  dfx_message->message,
-				  le32_to_cpu(desc->data[entry]));
+		seq_printf(s, "%s: %#x\n", dfx_message->message,
+			   le32_to_cpu(desc->data[entry]));
 	}
 
 	kfree(desc_src);
@@ -940,8 +898,8 @@ static const struct hclge_dbg_status_dfx_info hclge_dbg_mac_en_status[] = {
 	{HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, "mac_tx_oversize_truncate_en"}
 };
 
-static int  hclge_dbg_dump_mac_enable_status(struct hclge_dev *hdev, char *buf,
-					     int len, int *pos)
+static int hclge_dbg_dump_mac_enable_status(struct hclge_dev *hdev,
+					    struct seq_file *s)
 {
 	struct hclge_config_mac_mode_cmd *req;
 	struct hclge_desc desc;
@@ -962,16 +920,15 @@ static int  hclge_dbg_dump_mac_enable_status(struct hclge_dev *hdev, char *buf,
 
 	for (i = 0; i < ARRAY_SIZE(hclge_dbg_mac_en_status); i++) {
 		offset = hclge_dbg_mac_en_status[i].offset;
-		*pos += scnprintf(buf + *pos, len - *pos, "%s: %#x\n",
-				  hclge_dbg_mac_en_status[i].message,
-				  hnae3_get_bit(loop_en, offset));
+		seq_printf(s, "%s: %#x\n", hclge_dbg_mac_en_status[i].message,
+			   hnae3_get_bit(loop_en, offset));
 	}
 
 	return 0;
 }
 
-static int hclge_dbg_dump_mac_frame_size(struct hclge_dev *hdev, char *buf,
-					 int len, int *pos)
+static int hclge_dbg_dump_mac_frame_size(struct hclge_dev *hdev,
+					 struct seq_file *s)
 {
 	struct hclge_config_max_frm_size_cmd *req;
 	struct hclge_desc desc;
@@ -988,16 +945,14 @@ static int hclge_dbg_dump_mac_frame_size(struct hclge_dev *hdev, char *buf,
 
 	req = (struct hclge_config_max_frm_size_cmd *)desc.data;
 
-	*pos += scnprintf(buf + *pos, len - *pos, "max_frame_size: %u\n",
-			  le16_to_cpu(req->max_frm_size));
-	*pos += scnprintf(buf + *pos, len - *pos, "min_frame_size: %u\n",
-			  req->min_frm_size);
+	seq_printf(s, "max_frame_size: %u\n", le16_to_cpu(req->max_frm_size));
+	seq_printf(s, "min_frame_size: %u\n", req->min_frm_size);
 
 	return 0;
 }
 
-static int hclge_dbg_dump_mac_speed_duplex(struct hclge_dev *hdev, char *buf,
-					   int len, int *pos)
+static int hclge_dbg_dump_mac_speed_duplex(struct hclge_dev *hdev,
+					   struct seq_file *s)
 {
 #define HCLGE_MAC_SPEED_SHIFT	0
 #define HCLGE_MAC_SPEED_MASK	GENMASK(5, 0)
@@ -1018,33 +973,31 @@ static int hclge_dbg_dump_mac_speed_duplex(struct hclge_dev *hdev, char *buf,
 
 	req = (struct hclge_config_mac_speed_dup_cmd *)desc.data;
 
-	*pos += scnprintf(buf + *pos, len - *pos, "speed: %#lx\n",
-			  hnae3_get_field(req->speed_dup, HCLGE_MAC_SPEED_MASK,
-					  HCLGE_MAC_SPEED_SHIFT));
-	*pos += scnprintf(buf + *pos, len - *pos, "duplex: %#x\n",
-			  hnae3_get_bit(req->speed_dup,
-					HCLGE_MAC_DUPLEX_SHIFT));
+	seq_printf(s, "speed: %#lx\n",
+		   hnae3_get_field(req->speed_dup, HCLGE_MAC_SPEED_MASK,
+				   HCLGE_MAC_SPEED_SHIFT));
+	seq_printf(s, "duplex: %#x\n",
+		   hnae3_get_bit(req->speed_dup, HCLGE_MAC_DUPLEX_SHIFT));
 	return 0;
 }
 
-static int hclge_dbg_dump_mac(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_mac(struct seq_file *s, void *data)
 {
-	int pos = 0;
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	int ret;
 
-	ret = hclge_dbg_dump_mac_enable_status(hdev, buf, len, &pos);
+	ret = hclge_dbg_dump_mac_enable_status(hdev, s);
 	if (ret)
 		return ret;
 
-	ret = hclge_dbg_dump_mac_frame_size(hdev, buf, len, &pos);
+	ret = hclge_dbg_dump_mac_frame_size(hdev, s);
 	if (ret)
 		return ret;
 
-	return hclge_dbg_dump_mac_speed_duplex(hdev, buf, len, &pos);
+	return hclge_dbg_dump_mac_speed_duplex(hdev, s);
 }
 
-static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len,
-				   int *pos)
+static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, struct seq_file *s)
 {
 	struct hclge_dbg_bitmap_cmd req;
 	struct hclge_desc desc;
@@ -1055,8 +1008,8 @@ static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len,
 	if (ret)
 		return ret;
 
-	*pos += scnprintf(buf + *pos, len - *pos,
-			  "qset_id  roce_qset_mask  nic_qset_mask  qset_shaping_pass  qset_bp_status\n");
+	seq_puts(s, "qset_id  roce_qset_mask  nic_qset_mask  ");
+	seq_puts(s, "qset_shaping_pass  qset_bp_status\n");
 	for (qset_id = 0; qset_id < qset_num; qset_id++) {
 		ret = hclge_dbg_cmd_send(hdev, &desc, qset_id, 1,
 					 HCLGE_OPC_QSET_DFX_STS);
@@ -1065,17 +1018,14 @@ static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len,
 
 		req.bitmap = (u8)le32_to_cpu(desc.data[1]);
 
-		*pos += scnprintf(buf + *pos, len - *pos,
-				  "%04u           %#x            %#x             %#x               %#x\n",
-				  qset_id, req.bit0, req.bit1, req.bit2,
-				  req.bit3);
+		seq_printf(s, "%04u     %#-16x%#-15x%#-19x%#-x\n",
+			   qset_id, req.bit0, req.bit1, req.bit2, req.bit3);
 	}
 
 	return 0;
 }
 
-static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len,
-				  int *pos)
+static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, struct seq_file *s)
 {
 	struct hclge_dbg_bitmap_cmd req;
 	struct hclge_desc desc;
@@ -1086,8 +1036,7 @@ static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len,
 	if (ret)
 		return ret;
 
-	*pos += scnprintf(buf + *pos, len - *pos,
-			  "pri_id  pri_mask  pri_cshaping_pass  pri_pshaping_pass\n");
+	seq_puts(s, "pri_id  pri_mask  pri_cshaping_pass  pri_pshaping_pass\n");
 	for (pri_id = 0; pri_id < pri_num; pri_id++) {
 		ret = hclge_dbg_cmd_send(hdev, &desc, pri_id, 1,
 					 HCLGE_OPC_PRI_DFX_STS);
@@ -1096,24 +1045,21 @@ static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len,
 
 		req.bitmap = (u8)le32_to_cpu(desc.data[1]);
 
-		*pos += scnprintf(buf + *pos, len - *pos,
-				  "%03u       %#x           %#x                %#x\n",
-				  pri_id, req.bit0, req.bit1, req.bit2);
+		seq_printf(s, "%03u     %#-10x%#-19x%#-x\n",
+			   pri_id, req.bit0, req.bit1, req.bit2);
 	}
 
 	return 0;
 }
 
-static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, char *buf, int len,
-				 int *pos)
+static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, struct seq_file *s)
 {
 	struct hclge_dbg_bitmap_cmd req;
 	struct hclge_desc desc;
 	u8 pg_id;
 	int ret;
 
-	*pos += scnprintf(buf + *pos, len - *pos,
-			  "pg_id  pg_mask  pg_cshaping_pass  pg_pshaping_pass\n");
+	seq_puts(s, "pg_id  pg_mask  pg_cshaping_pass  pg_pshaping_pass\n");
 	for (pg_id = 0; pg_id < hdev->tm_info.num_pg; pg_id++) {
 		ret = hclge_dbg_cmd_send(hdev, &desc, pg_id, 1,
 					 HCLGE_OPC_PG_DFX_STS);
@@ -1122,47 +1068,41 @@ static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, char *buf, int len,
 
 		req.bitmap = (u8)le32_to_cpu(desc.data[1]);
 
-		*pos += scnprintf(buf + *pos, len - *pos,
-				  "%03u      %#x           %#x               %#x\n",
-				  pg_id, req.bit0, req.bit1, req.bit2);
+		seq_printf(s, "%03u    %#-9x%#-18x%#-x\n",
+			   pg_id, req.bit0, req.bit1, req.bit2);
 	}
 
 	return 0;
 }
 
-static int hclge_dbg_dump_dcb_queue(struct hclge_dev *hdev, char *buf, int len,
-				    int *pos)
+static int hclge_dbg_dump_dcb_queue(struct hclge_dev *hdev, struct seq_file *s)
 {
 	struct hclge_desc desc;
 	u16 nq_id;
 	int ret;
 
-	*pos += scnprintf(buf + *pos, len - *pos,
-			  "nq_id  sch_nic_queue_cnt  sch_roce_queue_cnt\n");
+	seq_puts(s, "nq_id  sch_nic_queue_cnt  sch_roce_queue_cnt\n");
 	for (nq_id = 0; nq_id < hdev->num_tqps; nq_id++) {
 		ret = hclge_dbg_cmd_send(hdev, &desc, nq_id, 1,
 					 HCLGE_OPC_SCH_NQ_CNT);
 		if (ret)
 			return ret;
 
-		*pos += scnprintf(buf + *pos, len - *pos, "%04u           %#x",
-				  nq_id, le32_to_cpu(desc.data[1]));
+		seq_printf(s, "%04u   %#-19x",
+			   nq_id, le32_to_cpu(desc.data[1]));
 
 		ret = hclge_dbg_cmd_send(hdev, &desc, nq_id, 1,
 					 HCLGE_OPC_SCH_RQ_CNT);
 		if (ret)
 			return ret;
 
-		*pos += scnprintf(buf + *pos, len - *pos,
-				  "               %#x\n",
-				  le32_to_cpu(desc.data[1]));
+		seq_printf(s, "%#-x\n", le32_to_cpu(desc.data[1]));
 	}
 
 	return 0;
 }
 
-static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, char *buf, int len,
-				   int *pos)
+static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, struct seq_file *s)
 {
 	struct hclge_dbg_bitmap_cmd req;
 	struct hclge_desc desc;
@@ -1176,16 +1116,13 @@ static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, char *buf, int len,
 
 	req.bitmap = (u8)le32_to_cpu(desc.data[1]);
 
-	*pos += scnprintf(buf + *pos, len - *pos, "port_mask: %#x\n",
-			 req.bit0);
-	*pos += scnprintf(buf + *pos, len - *pos, "port_shaping_pass: %#x\n",
-			 req.bit1);
+	seq_printf(s, "port_mask: %#x\n", req.bit0);
+	seq_printf(s, "port_shaping_pass: %#x\n", req.bit1);
 
 	return 0;
 }
 
-static int hclge_dbg_dump_dcb_tm(struct hclge_dev *hdev, char *buf, int len,
-				 int *pos)
+static int hclge_dbg_dump_dcb_tm(struct hclge_dev *hdev, struct seq_file *s)
 {
 	struct hclge_desc desc[2];
 	u8 port_id = 0;
@@ -1196,32 +1133,23 @@ static int hclge_dbg_dump_dcb_tm(struct hclge_dev *hdev, char *buf, int len,
 	if (ret)
 		return ret;
 
-	*pos += scnprintf(buf + *pos, len - *pos, "SCH_NIC_NUM: %#x\n",
-			  le32_to_cpu(desc[0].data[1]));
-	*pos += scnprintf(buf + *pos, len - *pos, "SCH_ROCE_NUM: %#x\n",
-			  le32_to_cpu(desc[0].data[2]));
+	seq_printf(s, "SCH_NIC_NUM: %#x\n", le32_to_cpu(desc[0].data[1]));
+	seq_printf(s, "SCH_ROCE_NUM: %#x\n", le32_to_cpu(desc[0].data[2]));
 
 	ret = hclge_dbg_cmd_send(hdev, desc, port_id, 2,
 				 HCLGE_OPC_TM_INTERNAL_STS);
 	if (ret)
 		return ret;
 
-	*pos += scnprintf(buf + *pos, len - *pos, "pri_bp: %#x\n",
-			  le32_to_cpu(desc[0].data[1]));
-	*pos += scnprintf(buf + *pos, len - *pos, "fifo_dfx_info: %#x\n",
-			  le32_to_cpu(desc[0].data[2]));
-	*pos += scnprintf(buf + *pos, len - *pos,
-			  "sch_roce_fifo_afull_gap: %#x\n",
-			  le32_to_cpu(desc[0].data[3]));
-	*pos += scnprintf(buf + *pos, len - *pos,
-			  "tx_private_waterline: %#x\n",
-			  le32_to_cpu(desc[0].data[4]));
-	*pos += scnprintf(buf + *pos, len - *pos, "tm_bypass_en: %#x\n",
-			  le32_to_cpu(desc[0].data[5]));
-	*pos += scnprintf(buf + *pos, len - *pos, "SSU_TM_BYPASS_EN: %#x\n",
-			  le32_to_cpu(desc[1].data[0]));
-	*pos += scnprintf(buf + *pos, len - *pos, "SSU_RESERVE_CFG: %#x\n",
-			  le32_to_cpu(desc[1].data[1]));
+	seq_printf(s, "pri_bp: %#x\n", le32_to_cpu(desc[0].data[1]));
+	seq_printf(s, "fifo_dfx_info: %#x\n", le32_to_cpu(desc[0].data[2]));
+	seq_printf(s, "sch_roce_fifo_afull_gap: %#x\n",
+		   le32_to_cpu(desc[0].data[3]));
+	seq_printf(s, "tx_private_waterline: %#x\n",
+		   le32_to_cpu(desc[0].data[4]));
+	seq_printf(s, "tm_bypass_en: %#x\n", le32_to_cpu(desc[0].data[5]));
+	seq_printf(s, "SSU_TM_BYPASS_EN: %#x\n", le32_to_cpu(desc[1].data[0]));
+	seq_printf(s, "SSU_RESERVE_CFG: %#x\n", le32_to_cpu(desc[1].data[1]));
 
 	if (hdev->hw.mac.media_type == HNAE3_MEDIA_TYPE_COPPER)
 		return 0;
@@ -1231,65 +1159,60 @@ static int hclge_dbg_dump_dcb_tm(struct hclge_dev *hdev, char *buf, int len,
 	if (ret)
 		return ret;
 
-	*pos += scnprintf(buf + *pos, len - *pos, "TC_MAP_SEL: %#x\n",
-			  le32_to_cpu(desc[0].data[1]));
-	*pos += scnprintf(buf + *pos, len - *pos, "IGU_PFC_PRI_EN: %#x\n",
-			  le32_to_cpu(desc[0].data[2]));
-	*pos += scnprintf(buf + *pos, len - *pos, "MAC_PFC_PRI_EN: %#x\n",
-			  le32_to_cpu(desc[0].data[3]));
-	*pos += scnprintf(buf + *pos, len - *pos, "IGU_PRI_MAP_TC_CFG: %#x\n",
-			  le32_to_cpu(desc[0].data[4]));
-	*pos += scnprintf(buf + *pos, len - *pos,
-			  "IGU_TX_PRI_MAP_TC_CFG: %#x\n",
-			  le32_to_cpu(desc[0].data[5]));
+	seq_printf(s, "TC_MAP_SEL: %#x\n", le32_to_cpu(desc[0].data[1]));
+	seq_printf(s, "IGU_PFC_PRI_EN: %#x\n", le32_to_cpu(desc[0].data[2]));
+	seq_printf(s, "MAC_PFC_PRI_EN: %#x\n", le32_to_cpu(desc[0].data[3]));
+	seq_printf(s, "IGU_PRI_MAP_TC_CFG: %#x\n",
+		   le32_to_cpu(desc[0].data[4]));
+	seq_printf(s, "IGU_TX_PRI_MAP_TC_CFG: %#x\n",
+		   le32_to_cpu(desc[0].data[5]));
 
 	return 0;
 }
 
-static int hclge_dbg_dump_dcb(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_dcb(struct seq_file *s, void *data)
 {
-	int pos = 0;
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	int ret;
 
-	ret = hclge_dbg_dump_dcb_qset(hdev, buf, len, &pos);
+	ret = hclge_dbg_dump_dcb_qset(hdev, s);
 	if (ret)
 		return ret;
 
-	ret = hclge_dbg_dump_dcb_pri(hdev, buf, len, &pos);
+	ret = hclge_dbg_dump_dcb_pri(hdev, s);
 	if (ret)
 		return ret;
 
-	ret = hclge_dbg_dump_dcb_pg(hdev, buf, len, &pos);
+	ret = hclge_dbg_dump_dcb_pg(hdev, s);
 	if (ret)
 		return ret;
 
-	ret = hclge_dbg_dump_dcb_queue(hdev, buf, len, &pos);
+	ret = hclge_dbg_dump_dcb_queue(hdev, s);
 	if (ret)
 		return ret;
 
-	ret = hclge_dbg_dump_dcb_port(hdev, buf, len, &pos);
+	ret = hclge_dbg_dump_dcb_port(hdev, s);
 	if (ret)
 		return ret;
 
-	return hclge_dbg_dump_dcb_tm(hdev, buf, len, &pos);
+	return hclge_dbg_dump_dcb_tm(hdev, s);
 }
 
-static int hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev,
-				  enum hnae3_dbg_cmd cmd, char *buf, int len)
+static int hclge_dbg_dump_reg_cmd(enum hnae3_dbg_cmd cmd, struct seq_file *s)
 {
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	const struct hclge_dbg_reg_type_info *reg_info;
-	int pos = 0, ret = 0;
-	int i;
+	int ret = 0;
+	u32 i;
 
 	for (i = 0; i < ARRAY_SIZE(hclge_dbg_reg_info); i++) {
 		reg_info = &hclge_dbg_reg_info[i];
 		if (cmd == reg_info->cmd) {
 			if (cmd == HNAE3_DBG_CMD_REG_TQP)
-				return hclge_dbg_dump_reg_tqp(hdev, reg_info,
-							      buf, len, &pos);
+				return hclge_dbg_dump_reg_tqp(hdev,
+							      reg_info, s);
 
-			ret = hclge_dbg_dump_reg_common(hdev, reg_info, buf,
-							len, &pos);
+			ret = hclge_dbg_dump_reg_common(hdev, reg_info, s);
 			if (ret)
 				break;
 		}
@@ -1298,12 +1221,57 @@ static int hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev,
 	return ret;
 }
 
-static int hclge_dbg_dump_tc(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_bios_reg_cmd(struct seq_file *s, void *data)
 {
+	return hclge_dbg_dump_reg_cmd(HNAE3_DBG_CMD_REG_BIOS_COMMON, s);
+}
+
+static int hclge_dbg_dump_ssu_reg_cmd(struct seq_file *s, void *data)
+{
+	return hclge_dbg_dump_reg_cmd(HNAE3_DBG_CMD_REG_SSU, s);
+}
+
+static int hclge_dbg_dump_igu_egu_reg_cmd(struct seq_file *s, void *data)
+{
+	return hclge_dbg_dump_reg_cmd(HNAE3_DBG_CMD_REG_IGU_EGU, s);
+}
+
+static int hclge_dbg_dump_rpu_reg_cmd(struct seq_file *s, void *data)
+{
+	return hclge_dbg_dump_reg_cmd(HNAE3_DBG_CMD_REG_RPU, s);
+}
+
+static int hclge_dbg_dump_ncsi_reg_cmd(struct seq_file *s, void *data)
+{
+	return hclge_dbg_dump_reg_cmd(HNAE3_DBG_CMD_REG_NCSI, s);
+}
+
+static int hclge_dbg_dump_rtc_reg_cmd(struct seq_file *s, void *data)
+{
+	return hclge_dbg_dump_reg_cmd(HNAE3_DBG_CMD_REG_RTC, s);
+}
+
+static int hclge_dbg_dump_ppp_reg_cmd(struct seq_file *s, void *data)
+{
+	return hclge_dbg_dump_reg_cmd(HNAE3_DBG_CMD_REG_PPP, s);
+}
+
+static int hclge_dbg_dump_rcb_reg_cmd(struct seq_file *s, void *data)
+{
+	return hclge_dbg_dump_reg_cmd(HNAE3_DBG_CMD_REG_RCB, s);
+}
+
+static int hclge_dbg_dump_tqp_reg_cmd(struct seq_file *s, void *data)
+{
+	return hclge_dbg_dump_reg_cmd(HNAE3_DBG_CMD_REG_TQP, s);
+}
+
+static int hclge_dbg_dump_tc(struct seq_file *s, void *data)
+{
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	struct hclge_ets_tc_weight_cmd *ets_weight;
+	const char *sch_mode_str;
 	struct hclge_desc desc;
-	char *sch_mode_str;
-	int pos = 0;
 	int ret;
 	u8 i;
 
@@ -1323,72 +1291,37 @@ static int hclge_dbg_dump_tc(struct hclge_dev *hdev, char *buf, int len)
 
 	ets_weight = (struct hclge_ets_tc_weight_cmd *)desc.data;
 
-	pos += scnprintf(buf + pos, len - pos, "enabled tc number: %u\n",
-			 hdev->tm_info.num_tc);
-	pos += scnprintf(buf + pos, len - pos, "weight_offset: %u\n",
-			 ets_weight->weight_offset);
+	seq_printf(s, "enabled tc number: %u\n", hdev->tm_info.num_tc);
+	seq_printf(s, "weight_offset: %u\n", ets_weight->weight_offset);
 
-	pos += scnprintf(buf + pos, len - pos, "TC    MODE  WEIGHT\n");
+	seq_puts(s, "TC    MODE  WEIGHT\n");
 	for (i = 0; i < HNAE3_MAX_TC; i++) {
 		sch_mode_str = ets_weight->tc_weight[i] ? "dwrr" : "sp";
-		pos += scnprintf(buf + pos, len - pos, "%u     %4s    %3u\n",
-				 i, sch_mode_str, ets_weight->tc_weight[i]);
+		seq_printf(s, "%u     %4s    %3u\n", i, sch_mode_str,
+			   ets_weight->tc_weight[i]);
 	}
 
 	return 0;
 }
 
-static const struct hclge_dbg_item tm_pg_items[] = {
-	{ "ID", 2 },
-	{ "PRI_MAP", 2 },
-	{ "MODE", 2 },
-	{ "DWRR", 2 },
-	{ "C_IR_B", 2 },
-	{ "C_IR_U", 2 },
-	{ "C_IR_S", 2 },
-	{ "C_BS_B", 2 },
-	{ "C_BS_S", 2 },
-	{ "C_FLAG", 2 },
-	{ "C_RATE(Mbps)", 2 },
-	{ "P_IR_B", 2 },
-	{ "P_IR_U", 2 },
-	{ "P_IR_S", 2 },
-	{ "P_BS_B", 2 },
-	{ "P_BS_S", 2 },
-	{ "P_FLAG", 2 },
-	{ "P_RATE(Mbps)", 0 }
-};
-
-static void hclge_dbg_fill_shaper_content(struct hclge_tm_shaper_para *para,
-					  char **result, u8 *index)
+static void hclge_dbg_fill_shaper_content(struct seq_file *s,
+					  struct hclge_tm_shaper_para *para)
 {
-	sprintf(result[(*index)++], "%3u", para->ir_b);
-	sprintf(result[(*index)++], "%3u", para->ir_u);
-	sprintf(result[(*index)++], "%3u", para->ir_s);
-	sprintf(result[(*index)++], "%3u", para->bs_b);
-	sprintf(result[(*index)++], "%3u", para->bs_s);
-	sprintf(result[(*index)++], "%3u", para->flag);
-	sprintf(result[(*index)++], "%6u", para->rate);
+	seq_printf(s, "%-8u%-8u%-8u%-8u%-8u%-8u%-14u", para->ir_b, para->ir_u,
+		   para->ir_s, para->bs_b, para->bs_s, para->flag, para->rate);
 }
 
-static int __hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *data_str,
-				  char *buf, int len)
+static int hclge_dbg_dump_tm_pg(struct seq_file *s, void *data)
 {
 	struct hclge_tm_shaper_para c_shaper_para, p_shaper_para;
-	char *result[ARRAY_SIZE(tm_pg_items)], *sch_mode_str;
-	u8 pg_id, sch_mode, weight, pri_bit_map, i, j;
-	char content[HCLGE_DBG_TM_INFO_LEN];
-	int pos = 0;
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
+	u8 pg_id, sch_mode, weight, pri_bit_map;
+	const char *sch_mode_str;
 	int ret;
 
-	for (i = 0; i < ARRAY_SIZE(tm_pg_items); i++) {
-		result[i] = data_str;
-		data_str += HCLGE_DBG_DATA_STR_LEN;
-	}
-
-	hclge_dbg_fill_content(content, sizeof(content), tm_pg_items,
-			       NULL, ARRAY_SIZE(tm_pg_items));
-	pos += scnprintf(buf + pos, len - pos, "%s", content);
+	seq_puts(s, "ID  PRI_MAP  MODE  DWRR  C_IR_B  C_IR_U  C_IR_S  C_BS_B  ");
+	seq_puts(s, "C_BS_S  C_FLAG  C_RATE(Mbps)  P_IR_B  P_IR_U  P_IR_S  ");
+	seq_puts(s, "P_BS_B  P_BS_S  P_FLAG  P_RATE(Mbps)\n");
 
 	for (pg_id = 0; pg_id < hdev->tm_info.num_pg; pg_id++) {
 		ret = hclge_tm_get_pg_to_pri_map(hdev, pg_id, &pri_bit_map);
@@ -1418,68 +1351,41 @@ static int __hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *data_str,
 		sch_mode_str = sch_mode & HCLGE_TM_TX_SCHD_DWRR_MSK ? "dwrr" :
 				       "sp";
 
-		j = 0;
-		sprintf(result[j++], "%02u", pg_id);
-		sprintf(result[j++], "0x%02x", pri_bit_map);
-		sprintf(result[j++], "%4s", sch_mode_str);
-		sprintf(result[j++], "%3u", weight);
-		hclge_dbg_fill_shaper_content(&c_shaper_para, result, &j);
-		hclge_dbg_fill_shaper_content(&p_shaper_para, result, &j);
-
-		hclge_dbg_fill_content(content, sizeof(content), tm_pg_items,
-				       (const char **)result,
-				       ARRAY_SIZE(tm_pg_items));
-		pos += scnprintf(buf + pos, len - pos, "%s", content);
+		seq_printf(s, "%02u  0x%-7x%-6s%-6u", pg_id, pri_bit_map,
+			   sch_mode_str, weight);
+		hclge_dbg_fill_shaper_content(s, &c_shaper_para);
+		hclge_dbg_fill_shaper_content(s, &p_shaper_para);
+		seq_puts(s, "\n");
 	}
 
 	return 0;
 }
 
-static int hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *buf, int len)
-{
-	char *data_str;
-	int ret;
-
-	data_str = kcalloc(ARRAY_SIZE(tm_pg_items),
-			   HCLGE_DBG_DATA_STR_LEN, GFP_KERNEL);
-	if (!data_str)
-		return -ENOMEM;
-
-	ret = __hclge_dbg_dump_tm_pg(hdev, data_str, buf, len);
-
-	kfree(data_str);
-
-	return ret;
-}
-
-static int hclge_dbg_dump_tm_port(struct hclge_dev *hdev,  char *buf, int len)
+static int hclge_dbg_dump_tm_port(struct seq_file *s, void *data)
 {
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	struct hclge_tm_shaper_para shaper_para;
-	int pos = 0;
 	int ret;
 
 	ret = hclge_tm_get_port_shaper(hdev, &shaper_para);
 	if (ret)
 		return ret;
 
-	pos += scnprintf(buf + pos, len - pos,
-			 "IR_B  IR_U  IR_S  BS_B  BS_S  FLAG  RATE(Mbps)\n");
-	pos += scnprintf(buf + pos, len - pos,
-			 "%3u   %3u   %3u   %3u   %3u     %1u   %6u\n",
-			 shaper_para.ir_b, shaper_para.ir_u, shaper_para.ir_s,
-			 shaper_para.bs_b, shaper_para.bs_s, shaper_para.flag,
-			 shaper_para.rate);
+	seq_puts(s, "IR_B  IR_U  IR_S  BS_B  BS_S  FLAG  RATE(Mbps)\n");
+	seq_printf(s, "%3u   %3u   %3u   %3u   %3u     %1u   %6u\n",
+		   shaper_para.ir_b, shaper_para.ir_u, shaper_para.ir_s,
+		   shaper_para.bs_b, shaper_para.bs_s, shaper_para.flag,
+		   shaper_para.rate);
 
 	return 0;
 }
 
 static int hclge_dbg_dump_tm_bp_qset_map(struct hclge_dev *hdev, u8 tc_id,
-					 char *buf, int len)
+					 struct seq_file *s)
 {
 	u32 qset_mapping[HCLGE_BP_EXT_GRP_NUM];
 	struct hclge_bp_to_qs_map_cmd *map;
 	struct hclge_desc desc;
-	int pos = 0;
 	u8 group_id;
 	u8 grp_num;
 	u16 i = 0;
@@ -1505,27 +1411,27 @@ static int hclge_dbg_dump_tm_bp_qset_map(struct hclge_dev *hdev, u8 tc_id,
 		qset_mapping[group_id] = le32_to_cpu(map->qs_bit_map);
 	}
 
-	pos += scnprintf(buf + pos, len - pos, "INDEX | TM BP QSET MAPPING:\n");
+	seq_puts(s, "INDEX | TM BP QSET MAPPING:\n");
 	for (group_id = 0; group_id < grp_num / 8; group_id++) {
-		pos += scnprintf(buf + pos, len - pos,
-			 "%04d  | %08x:%08x:%08x:%08x:%08x:%08x:%08x:%08x\n",
-			 group_id * 256, qset_mapping[i + 7],
-			 qset_mapping[i + 6], qset_mapping[i + 5],
-			 qset_mapping[i + 4], qset_mapping[i + 3],
-			 qset_mapping[i + 2], qset_mapping[i + 1],
-			 qset_mapping[i]);
+		seq_printf(s,
+			   "%04d  | %08x:%08x:%08x:%08x:%08x:%08x:%08x:%08x\n",
+			   group_id * 256, qset_mapping[i + 7],
+			   qset_mapping[i + 6], qset_mapping[i + 5],
+			   qset_mapping[i + 4], qset_mapping[i + 3],
+			   qset_mapping[i + 2], qset_mapping[i + 1],
+			   qset_mapping[i]);
 		i += 8;
 	}
 
-	return pos;
+	return 0;
 }
 
-static int hclge_dbg_dump_tm_map(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_tm_map(struct seq_file *s, void *data)
 {
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	u16 queue_id;
 	u16 qset_id;
 	u8 link_vld;
-	int pos = 0;
 	u8 pri_id;
 	u8 tc_id;
 	int ret;
@@ -1544,32 +1450,28 @@ static int hclge_dbg_dump_tm_map(struct hclge_dev *hdev, char *buf, int len)
 		if (ret)
 			return ret;
 
-		pos += scnprintf(buf + pos, len - pos,
-				 "QUEUE_ID   QSET_ID   PRI_ID   TC_ID\n");
-		pos += scnprintf(buf + pos, len - pos,
-				 "%04u        %4u       %3u      %2u\n",
-				 queue_id, qset_id, pri_id, tc_id);
+		seq_puts(s, "QUEUE_ID   QSET_ID   PRI_ID   TC_ID\n");
+		seq_printf(s, "%04u        %4u       %3u      %2u\n",
+			   queue_id, qset_id, pri_id, tc_id);
 
 		if (!hnae3_dev_dcb_supported(hdev))
 			continue;
 
-		ret = hclge_dbg_dump_tm_bp_qset_map(hdev, tc_id, buf + pos,
-						    len - pos);
+		ret = hclge_dbg_dump_tm_bp_qset_map(hdev, tc_id, s);
 		if (ret < 0)
 			return ret;
-		pos += ret;
 
-		pos += scnprintf(buf + pos, len - pos, "\n");
+		seq_puts(s, "\n");
 	}
 
 	return 0;
 }
 
-static int hclge_dbg_dump_tm_nodes(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_tm_nodes(struct seq_file *s, void *data)
 {
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	struct hclge_tm_nodes_cmd *nodes;
 	struct hclge_desc desc;
-	int pos = 0;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_NODES, true);
@@ -1582,65 +1484,36 @@ static int hclge_dbg_dump_tm_nodes(struct hclge_dev *hdev, char *buf, int len)
 
 	nodes = (struct hclge_tm_nodes_cmd *)desc.data;
 
-	pos += scnprintf(buf + pos, len - pos, "       BASE_ID  MAX_NUM\n");
-	pos += scnprintf(buf + pos, len - pos, "PG      %4u      %4u\n",
-			 nodes->pg_base_id, nodes->pg_num);
-	pos += scnprintf(buf + pos, len - pos, "PRI     %4u      %4u\n",
-			 nodes->pri_base_id, nodes->pri_num);
-	pos += scnprintf(buf + pos, len - pos, "QSET    %4u      %4u\n",
-			 le16_to_cpu(nodes->qset_base_id),
-			 le16_to_cpu(nodes->qset_num));
-	pos += scnprintf(buf + pos, len - pos, "QUEUE   %4u      %4u\n",
-			 le16_to_cpu(nodes->queue_base_id),
-			 le16_to_cpu(nodes->queue_num));
+	seq_puts(s, "       BASE_ID  MAX_NUM\n");
+	seq_printf(s, "PG      %4u      %4u\n", nodes->pg_base_id,
+		   nodes->pg_num);
+	seq_printf(s, "PRI     %4u      %4u\n", nodes->pri_base_id,
+		   nodes->pri_num);
+	seq_printf(s, "QSET    %4u      %4u\n",
+		   le16_to_cpu(nodes->qset_base_id),
+		   le16_to_cpu(nodes->qset_num));
+	seq_printf(s, "QUEUE   %4u      %4u\n",
+		   le16_to_cpu(nodes->queue_base_id),
+		   le16_to_cpu(nodes->queue_num));
 
 	return 0;
 }
 
-static const struct hclge_dbg_item tm_pri_items[] = {
-	{ "ID", 4 },
-	{ "MODE", 2 },
-	{ "DWRR", 2 },
-	{ "C_IR_B", 2 },
-	{ "C_IR_U", 2 },
-	{ "C_IR_S", 2 },
-	{ "C_BS_B", 2 },
-	{ "C_BS_S", 2 },
-	{ "C_FLAG", 2 },
-	{ "C_RATE(Mbps)", 2 },
-	{ "P_IR_B", 2 },
-	{ "P_IR_U", 2 },
-	{ "P_IR_S", 2 },
-	{ "P_BS_B", 2 },
-	{ "P_BS_S", 2 },
-	{ "P_FLAG", 2 },
-	{ "P_RATE(Mbps)", 0 }
-};
-
-static int hclge_dbg_dump_tm_pri(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_tm_pri(struct seq_file *s, void *data)
 {
 	struct hclge_tm_shaper_para c_shaper_para, p_shaper_para;
-	char *result[ARRAY_SIZE(tm_pri_items)], *sch_mode_str;
-	char content[HCLGE_DBG_TM_INFO_LEN];
-	u8 pri_num, sch_mode, weight, i, j;
-	char *data_str;
-	int pos, ret;
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
+	u8 pri_num, sch_mode, weight, i;
+	const char *sch_mode_str;
+	int ret;
 
 	ret = hclge_tm_get_pri_num(hdev, &pri_num);
 	if (ret)
 		return ret;
 
-	data_str = kcalloc(ARRAY_SIZE(tm_pri_items), HCLGE_DBG_DATA_STR_LEN,
-			   GFP_KERNEL);
-	if (!data_str)
-		return -ENOMEM;
-
-	for (i = 0; i < ARRAY_SIZE(tm_pri_items); i++)
-		result[i] = &data_str[i * HCLGE_DBG_DATA_STR_LEN];
-
-	hclge_dbg_fill_content(content, sizeof(content), tm_pri_items,
-			       NULL, ARRAY_SIZE(tm_pri_items));
-	pos = scnprintf(buf, len, "%s", content);
+	seq_puts(s, "ID  MODE  DWRR  C_IR_B  C_IR_U  C_IR_S  C_BS_B  ");
+	seq_puts(s, "C_BS_S  C_FLAG  C_RATE(Mbps)  P_IR_B  P_IR_U  P_IR_S  ");
+	seq_puts(s, "P_BS_B  P_BS_S  P_FLAG  P_RATE(Mbps)\n");
 
 	for (i = 0; i < pri_num; i++) {
 		ret = hclge_tm_get_pri_sch_mode(hdev, i, &sch_mode);
@@ -1666,59 +1539,31 @@ static int hclge_dbg_dump_tm_pri(struct hclge_dev *hdev, char *buf, int len)
 		sch_mode_str = sch_mode & HCLGE_TM_TX_SCHD_DWRR_MSK ? "dwrr" :
 			       "sp";
 
-		j = 0;
-		sprintf(result[j++], "%04u", i);
-		sprintf(result[j++], "%4s", sch_mode_str);
-		sprintf(result[j++], "%3u", weight);
-		hclge_dbg_fill_shaper_content(&c_shaper_para, result, &j);
-		hclge_dbg_fill_shaper_content(&p_shaper_para, result, &j);
-		hclge_dbg_fill_content(content, sizeof(content), tm_pri_items,
-				       (const char **)result,
-				       ARRAY_SIZE(tm_pri_items));
-		pos += scnprintf(buf + pos, len - pos, "%s", content);
+		seq_printf(s, "%04u  %-6s%-6u", i, sch_mode_str, weight);
+		hclge_dbg_fill_shaper_content(s, &c_shaper_para);
+		hclge_dbg_fill_shaper_content(s, &p_shaper_para);
+		seq_puts(s, "\n");
 	}
 
 out:
-	kfree(data_str);
 	return ret;
 }
 
-static const struct hclge_dbg_item tm_qset_items[] = {
-	{ "ID", 4 },
-	{ "MAP_PRI", 2 },
-	{ "LINK_VLD", 2 },
-	{ "MODE", 2 },
-	{ "DWRR", 2 },
-	{ "IR_B", 2 },
-	{ "IR_U", 2 },
-	{ "IR_S", 2 },
-	{ "BS_B", 2 },
-	{ "BS_S", 2 },
-	{ "FLAG", 2 },
-	{ "RATE(Mbps)", 0 }
-};
-
-static int hclge_dbg_dump_tm_qset(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_tm_qset(struct seq_file *s, void *data)
 {
-	char data_str[ARRAY_SIZE(tm_qset_items)][HCLGE_DBG_DATA_STR_LEN];
-	char *result[ARRAY_SIZE(tm_qset_items)], *sch_mode_str;
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	u8 priority, link_vld, sch_mode, weight;
 	struct hclge_tm_shaper_para shaper_para;
-	char content[HCLGE_DBG_TM_INFO_LEN];
+	const char *sch_mode_str;
 	u16 qset_num, i;
-	int ret, pos;
-	u8 j;
+	int ret;
 
 	ret = hclge_tm_get_qset_num(hdev, &qset_num);
 	if (ret)
 		return ret;
 
-	for (i = 0; i < ARRAY_SIZE(tm_qset_items); i++)
-		result[i] = &data_str[i][0];
-
-	hclge_dbg_fill_content(content, sizeof(content), tm_qset_items,
-			       NULL, ARRAY_SIZE(tm_qset_items));
-	pos = scnprintf(buf, len, "%s", content);
+	seq_puts(s, "ID    MAP_PRI  LINK_VLD  MODE  DWRR  IR_B  IR_U  IR_S  ");
+	seq_puts(s, "BS_B  BS_S  FLAG  RATE(Mbps)\n");
 
 	for (i = 0; i < qset_num; i++) {
 		ret = hclge_tm_get_qset_map_pri(hdev, i, &priority, &link_vld);
@@ -1740,29 +1585,22 @@ static int hclge_dbg_dump_tm_qset(struct hclge_dev *hdev, char *buf, int len)
 		sch_mode_str = sch_mode & HCLGE_TM_TX_SCHD_DWRR_MSK ? "dwrr" :
 			       "sp";
 
-		j = 0;
-		sprintf(result[j++], "%04u", i);
-		sprintf(result[j++], "%4u", priority);
-		sprintf(result[j++], "%4u", link_vld);
-		sprintf(result[j++], "%4s", sch_mode_str);
-		sprintf(result[j++], "%3u", weight);
-		hclge_dbg_fill_shaper_content(&shaper_para, result, &j);
-
-		hclge_dbg_fill_content(content, sizeof(content), tm_qset_items,
-				       (const char **)result,
-				       ARRAY_SIZE(tm_qset_items));
-		pos += scnprintf(buf + pos, len - pos, "%s", content);
+		seq_printf(s, "%04u  %-9u%-10u%-6s%-6u", i, priority, link_vld,
+			   sch_mode_str, weight);
+		seq_printf(s, "%-6u%-6u%-6u%-6u%-6u%-6u%-14u\n",
+			   shaper_para.ir_b, shaper_para.ir_u, shaper_para.ir_s,
+			   shaper_para.bs_b, shaper_para.bs_s, shaper_para.flag,
+			   shaper_para.rate);
 	}
 
 	return 0;
 }
 
-static int hclge_dbg_dump_qos_pause_cfg(struct hclge_dev *hdev, char *buf,
-					int len)
+static int hclge_dbg_dump_qos_pause_cfg(struct seq_file *s, void *data)
 {
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	struct hclge_cfg_pause_param_cmd *pause_param;
 	struct hclge_desc desc;
-	int pos = 0;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_MAC_PARA, true);
@@ -1775,23 +1613,21 @@ static int hclge_dbg_dump_qos_pause_cfg(struct hclge_dev *hdev, char *buf,
 
 	pause_param = (struct hclge_cfg_pause_param_cmd *)desc.data;
 
-	pos += scnprintf(buf + pos, len - pos, "pause_trans_gap: 0x%x\n",
-			 pause_param->pause_trans_gap);
-	pos += scnprintf(buf + pos, len - pos, "pause_trans_time: 0x%x\n",
-			 le16_to_cpu(pause_param->pause_trans_time));
+	seq_printf(s, "pause_trans_gap: 0x%x\n", pause_param->pause_trans_gap);
+	seq_printf(s, "pause_trans_time: 0x%x\n",
+		   le16_to_cpu(pause_param->pause_trans_time));
 	return 0;
 }
 
 #define HCLGE_DBG_TC_MASK		0x0F
 
-static int hclge_dbg_dump_qos_pri_map(struct hclge_dev *hdev, char *buf,
-				      int len)
+static int hclge_dbg_dump_qos_pri_map(struct seq_file *s, void *data)
 {
 #define HCLGE_DBG_TC_BIT_WIDTH		4
 
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	struct hclge_qos_pri_map_cmd *pri_map;
 	struct hclge_desc desc;
-	int pos = 0;
 	u8 *pri_tc;
 	u8 tc, i;
 	int ret;
@@ -1806,33 +1642,33 @@ static int hclge_dbg_dump_qos_pri_map(struct hclge_dev *hdev, char *buf,
 
 	pri_map = (struct hclge_qos_pri_map_cmd *)desc.data;
 
-	pos += scnprintf(buf + pos, len - pos, "vlan_to_pri: 0x%x\n",
-			 pri_map->vlan_pri);
-	pos += scnprintf(buf + pos, len - pos, "PRI  TC\n");
+	seq_printf(s, "vlan_to_pri: 0x%x\n", pri_map->vlan_pri);
+	seq_puts(s, "PRI  TC\n");
 
 	pri_tc = (u8 *)pri_map;
 	for (i = 0; i < HNAE3_MAX_TC; i++) {
 		tc = pri_tc[i >> 1] >> ((i & 1) * HCLGE_DBG_TC_BIT_WIDTH);
 		tc &= HCLGE_DBG_TC_MASK;
-		pos += scnprintf(buf + pos, len - pos, "%u     %u\n", i, tc);
+		seq_printf(s, "%u     %u\n", i, tc);
 	}
 
 	return 0;
 }
 
-static int hclge_dbg_dump_qos_dscp_map(struct hclge_dev *hdev, char *buf,
-				       int len)
+static int hclge_dbg_dump_qos_dscp_map(struct seq_file *s, void *data)
 {
-	struct hnae3_knic_private_info *kinfo = &hdev->vport[0].nic.kinfo;
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	struct hclge_desc desc[HCLGE_DSCP_MAP_TC_BD_NUM];
+	struct hnae3_knic_private_info *kinfo;
 	u8 *req0 = (u8 *)desc[0].data;
 	u8 *req1 = (u8 *)desc[1].data;
 	u8 dscp_tc[HNAE3_MAX_DSCP];
-	int pos, ret;
+	int ret;
 	u8 i, j;
 
-	pos = scnprintf(buf, len, "tc map mode: %s\n",
-			tc_map_mode_str[kinfo->tc_map_mode]);
+	kinfo = &hdev->vport[0].nic.kinfo;
+
+	seq_printf(s, "tc map mode: %s\n", tc_map_mode_str[kinfo->tc_map_mode]);
 
 	if (kinfo->tc_map_mode != HNAE3_TC_MAP_MODE_DSCP)
 		return 0;
@@ -1847,7 +1683,7 @@ static int hclge_dbg_dump_qos_dscp_map(struct hclge_dev *hdev, char *buf,
 		return ret;
 	}
 
-	pos += scnprintf(buf + pos, len - pos, "\nDSCP  PRIO  TC\n");
+	seq_puts(s, "\nDSCP  PRIO  TC\n");
 
 	/* The low 32 dscp setting use bd0, high 32 dscp setting use bd1 */
 	for (i = 0; i < HNAE3_MAX_DSCP / HCLGE_DSCP_MAP_TC_BD_NUM; i++) {
@@ -1865,18 +1701,17 @@ static int hclge_dbg_dump_qos_dscp_map(struct hclge_dev *hdev, char *buf,
 		if (kinfo->dscp_prio[i] == HNAE3_PRIO_ID_INVALID)
 			continue;
 
-		pos += scnprintf(buf + pos, len - pos, " %2u    %u    %u\n",
-				 i, kinfo->dscp_prio[i], dscp_tc[i]);
+		seq_printf(s, " %2u    %u    %u\n", i, kinfo->dscp_prio[i],
+			   dscp_tc[i]);
 	}
 
 	return 0;
 }
 
-static int hclge_dbg_dump_tx_buf_cfg(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_tx_buf_cfg(struct hclge_dev *hdev, struct seq_file *s)
 {
 	struct hclge_tx_buff_alloc_cmd *tx_buf_cmd;
 	struct hclge_desc desc;
-	int pos = 0;
 	int i, ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, true);
@@ -1889,19 +1724,17 @@ static int hclge_dbg_dump_tx_buf_cfg(struct hclge_dev *hdev, char *buf, int len)
 
 	tx_buf_cmd = (struct hclge_tx_buff_alloc_cmd *)desc.data;
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++)
-		pos += scnprintf(buf + pos, len - pos,
-				 "tx_packet_buf_tc_%d: 0x%x\n", i,
-				 le16_to_cpu(tx_buf_cmd->tx_pkt_buff[i]));
+		seq_printf(s, "tx_packet_buf_tc_%d: 0x%x\n", i,
+			   le16_to_cpu(tx_buf_cmd->tx_pkt_buff[i]));
 
-	return pos;
+	return 0;
 }
 
-static int hclge_dbg_dump_rx_priv_buf_cfg(struct hclge_dev *hdev, char *buf,
-					  int len)
+static int hclge_dbg_dump_rx_priv_buf_cfg(struct hclge_dev *hdev,
+					  struct seq_file *s)
 {
 	struct hclge_rx_priv_buff_cmd *rx_buf_cmd;
 	struct hclge_desc desc;
-	int pos = 0;
 	int i, ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_PRIV_BUFF_ALLOC, true);
@@ -1912,26 +1745,24 @@ static int hclge_dbg_dump_rx_priv_buf_cfg(struct hclge_dev *hdev, char *buf,
 		return ret;
 	}
 
-	pos += scnprintf(buf + pos, len - pos, "\n");
+	seq_puts(s, "\n");
 
 	rx_buf_cmd = (struct hclge_rx_priv_buff_cmd *)desc.data;
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++)
-		pos += scnprintf(buf + pos, len - pos,
-				 "rx_packet_buf_tc_%d: 0x%x\n", i,
-				 le16_to_cpu(rx_buf_cmd->buf_num[i]));
+		seq_printf(s, "rx_packet_buf_tc_%d: 0x%x\n", i,
+			   le16_to_cpu(rx_buf_cmd->buf_num[i]));
 
-	pos += scnprintf(buf + pos, len - pos, "rx_share_buf: 0x%x\n",
-			 le16_to_cpu(rx_buf_cmd->shared_buf));
+	seq_printf(s, "rx_share_buf: 0x%x\n",
+		   le16_to_cpu(rx_buf_cmd->shared_buf));
 
-	return pos;
+	return 0;
 }
 
-static int hclge_dbg_dump_rx_common_wl_cfg(struct hclge_dev *hdev, char *buf,
-					   int len)
+static int hclge_dbg_dump_rx_common_wl_cfg(struct hclge_dev *hdev,
+					   struct seq_file *s)
 {
 	struct hclge_rx_com_wl *rx_com_wl;
 	struct hclge_desc desc;
-	int pos = 0;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_COM_WL_ALLOC, true);
@@ -1943,21 +1774,19 @@ static int hclge_dbg_dump_rx_common_wl_cfg(struct hclge_dev *hdev, char *buf,
 	}
 
 	rx_com_wl = (struct hclge_rx_com_wl *)desc.data;
-	pos += scnprintf(buf + pos, len - pos, "\n");
-	pos += scnprintf(buf + pos, len - pos,
-			 "rx_com_wl: high: 0x%x, low: 0x%x\n",
-			 le16_to_cpu(rx_com_wl->com_wl.high),
-			 le16_to_cpu(rx_com_wl->com_wl.low));
+	seq_puts(s, "\n");
+	seq_printf(s, "rx_com_wl: high: 0x%x, low: 0x%x\n",
+		   le16_to_cpu(rx_com_wl->com_wl.high),
+		   le16_to_cpu(rx_com_wl->com_wl.low));
 
-	return pos;
+	return 0;
 }
 
-static int hclge_dbg_dump_rx_global_pkt_cnt(struct hclge_dev *hdev, char *buf,
-					    int len)
+static int hclge_dbg_dump_rx_global_pkt_cnt(struct hclge_dev *hdev,
+					    struct seq_file *s)
 {
 	struct hclge_rx_com_wl *rx_packet_cnt;
 	struct hclge_desc desc;
-	int pos = 0;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_GBL_PKT_CNT, true);
@@ -1969,20 +1798,18 @@ static int hclge_dbg_dump_rx_global_pkt_cnt(struct hclge_dev *hdev, char *buf,
 	}
 
 	rx_packet_cnt = (struct hclge_rx_com_wl *)desc.data;
-	pos += scnprintf(buf + pos, len - pos,
-			 "rx_global_packet_cnt: high: 0x%x, low: 0x%x\n",
-			 le16_to_cpu(rx_packet_cnt->com_wl.high),
-			 le16_to_cpu(rx_packet_cnt->com_wl.low));
+	seq_printf(s, "rx_global_packet_cnt: high: 0x%x, low: 0x%x\n",
+		   le16_to_cpu(rx_packet_cnt->com_wl.high),
+		   le16_to_cpu(rx_packet_cnt->com_wl.low));
 
-	return pos;
+	return 0;
 }
 
-static int hclge_dbg_dump_rx_priv_wl_buf_cfg(struct hclge_dev *hdev, char *buf,
-					     int len)
+static int hclge_dbg_dump_rx_priv_wl_buf_cfg(struct hclge_dev *hdev,
+					     struct seq_file *s)
 {
 	struct hclge_rx_priv_wl_buf *rx_priv_wl;
 	struct hclge_desc desc[2];
-	int pos = 0;
 	int i, ret;
 
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_RX_PRIV_WL_ALLOC, true);
@@ -1997,28 +1824,25 @@ static int hclge_dbg_dump_rx_priv_wl_buf_cfg(struct hclge_dev *hdev, char *buf,
 
 	rx_priv_wl = (struct hclge_rx_priv_wl_buf *)desc[0].data;
 	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
-		pos += scnprintf(buf + pos, len - pos,
-			 "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n", i,
-			 le16_to_cpu(rx_priv_wl->tc_wl[i].high),
-			 le16_to_cpu(rx_priv_wl->tc_wl[i].low));
+		seq_printf(s, "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n", i,
+			   le16_to_cpu(rx_priv_wl->tc_wl[i].high),
+			   le16_to_cpu(rx_priv_wl->tc_wl[i].low));
 
 	rx_priv_wl = (struct hclge_rx_priv_wl_buf *)desc[1].data;
 	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
-		pos += scnprintf(buf + pos, len - pos,
-			 "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n",
-			 i + HCLGE_TC_NUM_ONE_DESC,
-			 le16_to_cpu(rx_priv_wl->tc_wl[i].high),
-			 le16_to_cpu(rx_priv_wl->tc_wl[i].low));
+		seq_printf(s, "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n",
+			   i + HCLGE_TC_NUM_ONE_DESC,
+			   le16_to_cpu(rx_priv_wl->tc_wl[i].high),
+			   le16_to_cpu(rx_priv_wl->tc_wl[i].low));
 
-	return pos;
+	return 0;
 }
 
 static int hclge_dbg_dump_rx_common_threshold_cfg(struct hclge_dev *hdev,
-						  char *buf, int len)
+						  struct seq_file *s)
 {
 	struct hclge_rx_com_thrd *rx_com_thrd;
 	struct hclge_desc desc[2];
-	int pos = 0;
 	int i, ret;
 
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_RX_COM_THRD_ALLOC, true);
@@ -2031,86 +1855,75 @@ static int hclge_dbg_dump_rx_common_threshold_cfg(struct hclge_dev *hdev,
 		return ret;
 	}
 
-	pos += scnprintf(buf + pos, len - pos, "\n");
+	seq_puts(s, "\n");
 	rx_com_thrd = (struct hclge_rx_com_thrd *)desc[0].data;
 	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
-		pos += scnprintf(buf + pos, len - pos,
-			 "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n", i,
-			 le16_to_cpu(rx_com_thrd->com_thrd[i].high),
-			 le16_to_cpu(rx_com_thrd->com_thrd[i].low));
+		seq_printf(s, "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n", i,
+			   le16_to_cpu(rx_com_thrd->com_thrd[i].high),
+			   le16_to_cpu(rx_com_thrd->com_thrd[i].low));
 
 	rx_com_thrd = (struct hclge_rx_com_thrd *)desc[1].data;
 	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
-		pos += scnprintf(buf + pos, len - pos,
-			 "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n",
-			 i + HCLGE_TC_NUM_ONE_DESC,
-			 le16_to_cpu(rx_com_thrd->com_thrd[i].high),
-			 le16_to_cpu(rx_com_thrd->com_thrd[i].low));
+		seq_printf(s, "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n",
+			   i + HCLGE_TC_NUM_ONE_DESC,
+			   le16_to_cpu(rx_com_thrd->com_thrd[i].high),
+			   le16_to_cpu(rx_com_thrd->com_thrd[i].low));
 
-	return pos;
+	return 0;
 }
 
-static int hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev, char *buf,
-				      int len)
+static int hclge_dbg_dump_qos_buf_cfg(struct seq_file *s, void *data)
 {
-	int pos = 0;
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	int ret;
 
-	ret = hclge_dbg_dump_tx_buf_cfg(hdev, buf + pos, len - pos);
+	ret = hclge_dbg_dump_tx_buf_cfg(hdev, s);
 	if (ret < 0)
 		return ret;
-	pos += ret;
 
-	ret = hclge_dbg_dump_rx_priv_buf_cfg(hdev, buf + pos, len - pos);
+	ret = hclge_dbg_dump_rx_priv_buf_cfg(hdev, s);
 	if (ret < 0)
 		return ret;
-	pos += ret;
 
-	ret = hclge_dbg_dump_rx_common_wl_cfg(hdev, buf + pos, len - pos);
+	ret = hclge_dbg_dump_rx_common_wl_cfg(hdev, s);
 	if (ret < 0)
 		return ret;
-	pos += ret;
 
-	ret = hclge_dbg_dump_rx_global_pkt_cnt(hdev, buf + pos, len - pos);
+	ret = hclge_dbg_dump_rx_global_pkt_cnt(hdev, s);
 	if (ret < 0)
 		return ret;
-	pos += ret;
 
-	pos += scnprintf(buf + pos, len - pos, "\n");
+	seq_puts(s, "\n");
 	if (!hnae3_dev_dcb_supported(hdev))
 		return 0;
 
-	ret = hclge_dbg_dump_rx_priv_wl_buf_cfg(hdev, buf + pos, len - pos);
+	ret = hclge_dbg_dump_rx_priv_wl_buf_cfg(hdev, s);
 	if (ret < 0)
 		return ret;
-	pos += ret;
 
-	ret = hclge_dbg_dump_rx_common_threshold_cfg(hdev, buf + pos,
-						     len - pos);
+	ret = hclge_dbg_dump_rx_common_threshold_cfg(hdev, s);
 	if (ret < 0)
 		return ret;
 
 	return 0;
 }
 
-static int hclge_dbg_dump_mng_table(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_mng_table(struct seq_file *s, void *data)
 {
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	struct hclge_mac_ethertype_idx_rd_cmd *req0;
 	struct hclge_desc desc;
 	u32 msg_egress_port;
-	int pos = 0;
 	int ret, i;
 
-	pos += scnprintf(buf + pos, len - pos,
-			 "entry  mac_addr          mask  ether  ");
-	pos += scnprintf(buf + pos, len - pos,
-			 "mask  vlan  mask  i_map  i_dir  e_type  ");
-	pos += scnprintf(buf + pos, len - pos, "pf_id  vf_id  q_id  drop\n");
+	seq_puts(s, "entry  mac_addr          mask  ether  ");
+	seq_puts(s, "mask  vlan  mask  i_map  i_dir  e_type  ");
+	seq_puts(s, "pf_id  vf_id  q_id  drop\n");
 
 	for (i = 0; i < HCLGE_DBG_MNG_TBL_MAX; i++) {
 		hclge_cmd_setup_basic_desc(&desc, HCLGE_MAC_ETHERTYPE_IDX_RD,
 					   true);
-		req0 = (struct hclge_mac_ethertype_idx_rd_cmd *)&desc.data;
+		req0 = (struct hclge_mac_ethertype_idx_rd_cmd *)desc.data;
 		req0->index = cpu_to_le16(i);
 
 		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2123,46 +1936,40 @@ static int hclge_dbg_dump_mng_table(struct hclge_dev *hdev, char *buf, int len)
 		if (!req0->resp_code)
 			continue;
 
-		pos += scnprintf(buf + pos, len - pos, "%02u     %pM ",
-				 le16_to_cpu(req0->index), req0->mac_addr);
+		seq_printf(s, "%02u     %pM ",
+			   le16_to_cpu(req0->index), req0->mac_addr);
 
-		pos += scnprintf(buf + pos, len - pos,
-				 "%x     %04x   %x     %04x  ",
-				 !!(req0->flags & HCLGE_DBG_MNG_MAC_MASK_B),
-				 le16_to_cpu(req0->ethter_type),
-				 !!(req0->flags & HCLGE_DBG_MNG_ETHER_MASK_B),
-				 le16_to_cpu(req0->vlan_tag) &
-				 HCLGE_DBG_MNG_VLAN_TAG);
+		seq_printf(s, "%x     %04x   %x     %04x  ",
+			   !!(req0->flags & HCLGE_DBG_MNG_MAC_MASK_B),
+			   le16_to_cpu(req0->ethter_type),
+			   !!(req0->flags & HCLGE_DBG_MNG_ETHER_MASK_B),
+			   le16_to_cpu(req0->vlan_tag) &
+			   HCLGE_DBG_MNG_VLAN_TAG);
 
-		pos += scnprintf(buf + pos, len - pos,
-				 "%x     %02x     %02x     ",
-				 !!(req0->flags & HCLGE_DBG_MNG_VLAN_MASK_B),
-				 req0->i_port_bitmap, req0->i_port_direction);
+		seq_printf(s, "%x     %02x     %02x     ",
+			   !!(req0->flags & HCLGE_DBG_MNG_VLAN_MASK_B),
+			   req0->i_port_bitmap, req0->i_port_direction);
 
 		msg_egress_port = le16_to_cpu(req0->egress_port);
-		pos += scnprintf(buf + pos, len - pos,
-				 "%x       %x      %02x     %04x  %x\n",
-				 !!(msg_egress_port & HCLGE_DBG_MNG_E_TYPE_B),
-				 msg_egress_port & HCLGE_DBG_MNG_PF_ID,
-				 (msg_egress_port >> 3) & HCLGE_DBG_MNG_VF_ID,
-				 le16_to_cpu(req0->egress_queue),
-				 !!(msg_egress_port & HCLGE_DBG_MNG_DROP_B));
+		seq_printf(s, "%x       %x      %02x     %04x  %x\n",
+			   !!(msg_egress_port & HCLGE_DBG_MNG_E_TYPE_B),
+			   msg_egress_port & HCLGE_DBG_MNG_PF_ID,
+			   (msg_egress_port >> 3) & HCLGE_DBG_MNG_VF_ID,
+			   le16_to_cpu(req0->egress_queue),
+			   !!(msg_egress_port & HCLGE_DBG_MNG_DROP_B));
 	}
 
 	return 0;
 }
 
-#define HCLGE_DBG_TCAM_BUF_SIZE 256
-
 static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, bool sel_x,
-				  char *tcam_buf,
+				  struct seq_file *s,
 				  struct hclge_dbg_tcam_msg tcam_msg)
 {
 	struct hclge_fd_tcam_config_1_cmd *req1;
 	struct hclge_fd_tcam_config_2_cmd *req2;
 	struct hclge_fd_tcam_config_3_cmd *req3;
 	struct hclge_desc desc[3];
-	int pos = 0;
 	int ret, i;
 	__le32 *req;
 
@@ -2184,27 +1991,23 @@ static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, bool sel_x,
 	if (ret)
 		return ret;
 
-	pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
-			 "read result tcam key %s(%u):\n", sel_x ? "x" : "y",
-			 tcam_msg.loc);
+	seq_printf(s, "read result tcam key %s(%u):\n",
+		   sel_x ? "x" : "y", tcam_msg.loc);
 
 	/* tcam_data0 ~ tcam_data1 */
 	req = (__le32 *)req1->tcam_data;
 	for (i = 0; i < 2; i++)
-		pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
-				 "%08x\n", le32_to_cpu(*req++));
+		seq_printf(s, "%08x\n", le32_to_cpu(*req++));
 
 	/* tcam_data2 ~ tcam_data7 */
 	req = (__le32 *)req2->tcam_data;
 	for (i = 0; i < 6; i++)
-		pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
-				 "%08x\n", le32_to_cpu(*req++));
+		seq_printf(s, "%08x\n", le32_to_cpu(*req++));
 
 	/* tcam_data8 ~ tcam_data12 */
 	req = (__le32 *)req3->tcam_data;
 	for (i = 0; i < 5; i++)
-		pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
-				 "%08x\n", le32_to_cpu(*req++));
+		seq_printf(s, "%08x\n", le32_to_cpu(*req++));
 
 	return ret;
 }
@@ -2228,14 +2031,13 @@ static int hclge_dbg_get_rules_location(struct hclge_dev *hdev, u16 *rule_locs)
 	return cnt;
 }
 
-static int hclge_dbg_dump_fd_tcam(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_fd_tcam(struct seq_file *s, void *data)
 {
-	u32 rule_num = hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1];
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	struct hclge_dbg_tcam_msg tcam_msg;
 	int i, ret, rule_cnt;
 	u16 *rule_locs;
-	char *tcam_buf;
-	int pos = 0;
+	u32 rule_num;
 
 	if (!hnae3_ae_dev_fd_supported(hdev->ae_dev)) {
 		dev_err(&hdev->pdev->dev,
@@ -2243,6 +2045,7 @@ static int hclge_dbg_dump_fd_tcam(struct hclge_dev *hdev, char *buf, int len)
 		return -EOPNOTSUPP;
 	}
 
+	rule_num = hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1];
 	if (!hdev->hclge_fd_rule_num || !rule_num)
 		return 0;
 
@@ -2250,12 +2053,6 @@ static int hclge_dbg_dump_fd_tcam(struct hclge_dev *hdev, char *buf, int len)
 	if (!rule_locs)
 		return -ENOMEM;
 
-	tcam_buf = kzalloc(HCLGE_DBG_TCAM_BUF_SIZE, GFP_KERNEL);
-	if (!tcam_buf) {
-		kfree(rule_locs);
-		return -ENOMEM;
-	}
-
 	rule_cnt = hclge_dbg_get_rules_location(hdev, rule_locs);
 	if (rule_cnt < 0) {
 		ret = rule_cnt;
@@ -2269,38 +2066,34 @@ static int hclge_dbg_dump_fd_tcam(struct hclge_dev *hdev, char *buf, int len)
 		tcam_msg.stage = HCLGE_FD_STAGE_1;
 		tcam_msg.loc = rule_locs[i];
 
-		ret = hclge_dbg_fd_tcam_read(hdev, true, tcam_buf, tcam_msg);
+		ret = hclge_dbg_fd_tcam_read(hdev, true, s, tcam_msg);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
 				"failed to get fd tcam key x, ret = %d\n", ret);
 			goto out;
 		}
 
-		pos += scnprintf(buf + pos, len - pos, "%s", tcam_buf);
-
-		ret = hclge_dbg_fd_tcam_read(hdev, false, tcam_buf, tcam_msg);
+		ret = hclge_dbg_fd_tcam_read(hdev, false, s, tcam_msg);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
 				"failed to get fd tcam key y, ret = %d\n", ret);
 			goto out;
 		}
 
-		pos += scnprintf(buf + pos, len - pos, "%s", tcam_buf);
 	}
 
 out:
-	kfree(tcam_buf);
 	kfree(rule_locs);
 	return ret;
 }
 
-static int hclge_dbg_dump_fd_counter(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_fd_counter(struct seq_file *s, void *data)
 {
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	u8 func_num = pci_num_vf(hdev->pdev) + 1; /* pf and enabled vf num */
 	struct hclge_fd_ad_cnt_read_cmd *req;
 	char str_id[HCLGE_DBG_ID_LEN];
 	struct hclge_desc desc;
-	int pos = 0;
 	int ret;
 	u64 cnt;
 	u8 i;
@@ -2308,8 +2101,7 @@ static int hclge_dbg_dump_fd_counter(struct hclge_dev *hdev, char *buf, int len)
 	if (!hnae3_ae_dev_fd_supported(hdev->ae_dev))
 		return -EOPNOTSUPP;
 
-	pos += scnprintf(buf + pos, len - pos,
-			 "func_id\thit_times\n");
+	seq_puts(s, "func_id\thit_times\n");
 
 	for (i = 0; i < func_num; i++) {
 		hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_FD_CNT_OP, true);
@@ -2323,8 +2115,7 @@ static int hclge_dbg_dump_fd_counter(struct hclge_dev *hdev, char *buf, int len)
 		}
 		cnt = le64_to_cpu(req->cnt);
 		hclge_dbg_get_func_id_str(str_id, i);
-		pos += scnprintf(buf + pos, len - pos,
-				 "%s\t%llu\n", str_id, cnt);
+		seq_printf(s, "%s\t%llu\n", str_id, cnt);
 	}
 
 	return 0;
@@ -2375,74 +2166,95 @@ int hclge_dbg_dump_rst_info(struct hclge_dev *hdev, char *buf, int len)
 	return 0;
 }
 
-static int hclge_dbg_dump_serv_info(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_seq_dump_rst_info(struct seq_file *s, void *data)
 {
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
+	u32 i, offset;
+
+	seq_printf(s, "PF reset count: %u\n", hdev->rst_stats.pf_rst_cnt);
+	seq_printf(s, "FLR reset count: %u\n", hdev->rst_stats.flr_rst_cnt);
+	seq_printf(s, "GLOBAL reset count: %u\n",
+		   hdev->rst_stats.global_rst_cnt);
+	seq_printf(s, "IMP reset count: %u\n", hdev->rst_stats.imp_rst_cnt);
+	seq_printf(s, "reset done count: %u\n", hdev->rst_stats.reset_done_cnt);
+	seq_printf(s, "HW reset done count: %u\n",
+		   hdev->rst_stats.hw_reset_done_cnt);
+	seq_printf(s, "reset count: %u\n", hdev->rst_stats.reset_cnt);
+	seq_printf(s, "reset fail count: %u\n", hdev->rst_stats.reset_fail_cnt);
+
+	for (i = 0; i < ARRAY_SIZE(hclge_dbg_rst_info); i++) {
+		offset = hclge_dbg_rst_info[i].offset;
+		seq_printf(s, "%s: 0x%x\n",
+			   hclge_dbg_rst_info[i].message,
+			   hclge_read_dev(&hdev->hw, offset));
+	}
+
+	seq_printf(s, "hdev state: 0x%lx\n", hdev->state);
+
+	return 0;
+}
+
+static int hclge_dbg_dump_serv_info(struct seq_file *s, void *data)
+{
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	unsigned long rem_nsec;
-	int pos = 0;
 	u64 lc;
 
 	lc = local_clock();
 	rem_nsec = do_div(lc, HCLGE_BILLION_NANO_SECONDS);
 
-	pos += scnprintf(buf + pos, len - pos, "local_clock: [%5lu.%06lu]\n",
-			 (unsigned long)lc, rem_nsec / 1000);
-	pos += scnprintf(buf + pos, len - pos, "delta: %u(ms)\n",
-			 jiffies_to_msecs(jiffies - hdev->last_serv_processed));
-	pos += scnprintf(buf + pos, len - pos,
-			 "last_service_task_processed: %lu(jiffies)\n",
-			 hdev->last_serv_processed);
-	pos += scnprintf(buf + pos, len - pos, "last_service_task_cnt: %lu\n",
-			 hdev->serv_processed_cnt);
+	seq_printf(s, "local_clock: [%5lu.%06lu]\n",
+		   (unsigned long)lc, rem_nsec / 1000);
+	seq_printf(s, "delta: %u(ms)\n",
+		   jiffies_to_msecs(jiffies - hdev->last_serv_processed));
+	seq_printf(s, "last_service_task_processed: %lu(jiffies)\n",
+		   hdev->last_serv_processed);
+	seq_printf(s, "last_service_task_cnt: %lu\n", hdev->serv_processed_cnt);
 
 	return 0;
 }
 
-static int hclge_dbg_dump_interrupt(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_interrupt(struct seq_file *s, void *data)
 {
-	int pos = 0;
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 
-	pos += scnprintf(buf + pos, len - pos, "num_nic_msi: %u\n",
-			 hdev->num_nic_msi);
-	pos += scnprintf(buf + pos, len - pos, "num_roce_msi: %u\n",
-			 hdev->num_roce_msi);
-	pos += scnprintf(buf + pos, len - pos, "num_msi_used: %u\n",
-			 hdev->num_msi_used);
-	pos += scnprintf(buf + pos, len - pos, "num_msi_left: %u\n",
-			 hdev->num_msi_left);
+	seq_printf(s, "num_nic_msi: %u\n", hdev->num_nic_msi);
+	seq_printf(s, "num_roce_msi: %u\n", hdev->num_roce_msi);
+	seq_printf(s, "num_msi_used: %u\n", hdev->num_msi_used);
+	seq_printf(s, "num_msi_left: %u\n", hdev->num_msi_left);
 
 	return 0;
 }
 
-static void hclge_dbg_imp_info_data_print(struct hclge_desc *desc_src,
-					  char *buf, int len, u32 bd_num)
+static void hclge_dbg_imp_info_data_print(struct seq_file *s,
+					  struct hclge_desc *desc_src,
+					  u32 bd_num)
 {
 #define HCLGE_DBG_IMP_INFO_PRINT_OFFSET 0x2
 
 	struct hclge_desc *desc_index = desc_src;
 	u32 offset = 0;
-	int pos = 0;
 	u32 i, j;
 
-	pos += scnprintf(buf + pos, len - pos, "offset | data\n");
+	seq_puts(s, "offset | data\n");
 
 	for (i = 0; i < bd_num; i++) {
 		j = 0;
 		while (j < HCLGE_DESC_DATA_LEN - 1) {
-			pos += scnprintf(buf + pos, len - pos, "0x%04x | ",
-					 offset);
-			pos += scnprintf(buf + pos, len - pos, "0x%08x  ",
-					 le32_to_cpu(desc_index->data[j++]));
-			pos += scnprintf(buf + pos, len - pos, "0x%08x\n",
-					 le32_to_cpu(desc_index->data[j++]));
+			seq_printf(s, "0x%04x | ", offset);
+			seq_printf(s, "0x%08x  ",
+				   le32_to_cpu(desc_index->data[j++]));
+			seq_printf(s, "0x%08x\n",
+				   le32_to_cpu(desc_index->data[j++]));
 			offset += sizeof(u32) * HCLGE_DBG_IMP_INFO_PRINT_OFFSET;
 		}
 		desc_index++;
 	}
 }
 
-static int
-hclge_dbg_get_imp_stats_info(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_get_imp_stats_info(struct seq_file *s, void *data)
 {
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	struct hclge_get_imp_bd_cmd *req;
 	struct hclge_desc *desc_src;
 	struct hclge_desc desc;
@@ -2479,7 +2291,7 @@ hclge_dbg_get_imp_stats_info(struct hclge_dev *hdev, char *buf, int len)
 		return ret;
 	}
 
-	hclge_dbg_imp_info_data_print(desc_src, buf, len, bd_num);
+	hclge_dbg_imp_info_data_print(s, desc_src, bd_num);
 
 	kfree(desc_src);
 
@@ -2490,7 +2302,7 @@ hclge_dbg_get_imp_stats_info(struct hclge_dev *hdev, char *buf, int len)
 #define HCLGE_MAX_NCL_CONFIG_LENGTH	16384
 
 static void hclge_ncl_config_data_print(struct hclge_desc *desc, int *index,
-					char *buf, int len, int *pos)
+					struct seq_file *s)
 {
 #define HCLGE_CMD_DATA_NUM		6
 
@@ -2502,9 +2314,8 @@ static void hclge_ncl_config_data_print(struct hclge_desc *desc, int *index,
 			if (i == 0 && j == 0)
 				continue;
 
-			*pos += scnprintf(buf + *pos, len - *pos,
-					  "0x%04x | 0x%08x\n", offset,
-					  le32_to_cpu(desc[i].data[j]));
+			seq_printf(s, "0x%04x | 0x%08x\n", offset,
+				   le32_to_cpu(desc[i].data[j]));
 
 			offset += sizeof(u32);
 			*index -= sizeof(u32);
@@ -2515,19 +2326,18 @@ static void hclge_ncl_config_data_print(struct hclge_desc *desc, int *index,
 	}
 }
 
-static int
-hclge_dbg_dump_ncl_config(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_ncl_config(struct seq_file *s, void *data)
 {
 #define HCLGE_NCL_CONFIG_LENGTH_IN_EACH_CMD	(20 + 24 * 4)
 
 	struct hclge_desc desc[HCLGE_CMD_NCL_CONFIG_BD_NUM];
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	int bd_num = HCLGE_CMD_NCL_CONFIG_BD_NUM;
 	int index = HCLGE_MAX_NCL_CONFIG_LENGTH;
-	int pos = 0;
 	u32 data0;
 	int ret;
 
-	pos += scnprintf(buf + pos, len - pos, "offset | data\n");
+	seq_puts(s, "offset | data\n");
 
 	while (index > 0) {
 		data0 = HCLGE_MAX_NCL_CONFIG_LENGTH - index;
@@ -2540,27 +2350,26 @@ hclge_dbg_dump_ncl_config(struct hclge_dev *hdev, char *buf, int len)
 		if (ret)
 			return ret;
 
-		hclge_ncl_config_data_print(desc, &index, buf, len, &pos);
+		hclge_ncl_config_data_print(desc, &index, s);
 	}
 
 	return 0;
 }
 
-static int hclge_dbg_dump_loopback(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_loopback(struct seq_file *s, void *data)
 {
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	struct phy_device *phydev = hdev->hw.mac.phydev;
 	struct hclge_config_mac_mode_cmd *req_app;
 	struct hclge_common_lb_cmd *req_common;
 	struct hclge_desc desc;
 	u8 loopback_en;
-	int pos = 0;
 	int ret;
 
 	req_app = (struct hclge_config_mac_mode_cmd *)desc.data;
 	req_common = (struct hclge_common_lb_cmd *)desc.data;
 
-	pos += scnprintf(buf + pos, len - pos, "mac id: %u\n",
-			 hdev->hw.mac.mac_id);
+	seq_printf(s, "mac id: %u\n", hdev->hw.mac.mac_id);
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, true);
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2572,8 +2381,7 @@ static int hclge_dbg_dump_loopback(struct hclge_dev *hdev, char *buf, int len)
 
 	loopback_en = hnae3_get_bit(le32_to_cpu(req_app->txrx_pad_fcs_loop_en),
 				    HCLGE_MAC_APP_LP_B);
-	pos += scnprintf(buf + pos, len - pos, "app loopback: %s\n",
-			 state_str[loopback_en]);
+	seq_printf(s, "app loopback: %s\n", str_on_off(loopback_en));
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_COMMON_LOOPBACK, true);
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2584,24 +2392,22 @@ static int hclge_dbg_dump_loopback(struct hclge_dev *hdev, char *buf, int len)
 		return ret;
 	}
 
-	loopback_en = req_common->enable & HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B;
-	pos += scnprintf(buf + pos, len - pos, "serdes serial loopback: %s\n",
-			 state_str[loopback_en]);
+	loopback_en = req_common->enable &
+		      HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B;
+	seq_printf(s, "serdes serial loopback: %s\n", str_on_off(loopback_en));
 
 	loopback_en = req_common->enable &
-			HCLGE_CMD_SERDES_PARALLEL_INNER_LOOP_B ? 1 : 0;
-	pos += scnprintf(buf + pos, len - pos, "serdes parallel loopback: %s\n",
-			 state_str[loopback_en]);
+		      HCLGE_CMD_SERDES_PARALLEL_INNER_LOOP_B ? 1 : 0;
+	seq_printf(s, "serdes parallel loopback: %s\n",
+		   str_on_off(loopback_en));
 
 	if (phydev) {
 		loopback_en = phydev->loopback_enabled;
-		pos += scnprintf(buf + pos, len - pos, "phy loopback: %s\n",
-				 state_str[loopback_en]);
+		seq_printf(s, "phy loopback: %s\n", str_on_off(loopback_en));
 	} else if (hnae3_dev_phy_imp_supported(hdev)) {
 		loopback_en = req_common->enable &
 			      HCLGE_CMD_GE_PHY_INNER_LOOP_B;
-		pos += scnprintf(buf + pos, len - pos, "phy loopback: %s\n",
-				 state_str[loopback_en]);
+		seq_printf(s, "phy loopback: %s\n", str_on_off(loopback_en));
 	}
 
 	return 0;
@@ -2610,107 +2416,75 @@ static int hclge_dbg_dump_loopback(struct hclge_dev *hdev, char *buf, int len)
 /* hclge_dbg_dump_mac_tnl_status: print message about mac tnl interrupt
  * @hdev: pointer to struct hclge_dev
  */
-static int
-hclge_dbg_dump_mac_tnl_status(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_mac_tnl_status(struct seq_file *s, void *data)
 {
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	struct hclge_mac_tnl_stats stats;
 	unsigned long rem_nsec;
-	int pos = 0;
 
-	pos += scnprintf(buf + pos, len - pos,
-			 "Recently generated mac tnl interruption:\n");
+	seq_puts(s, "Recently generated mac tnl interruption:\n");
 
 	while (kfifo_get(&hdev->mac_tnl_log, &stats)) {
 		rem_nsec = do_div(stats.time, HCLGE_BILLION_NANO_SECONDS);
 
-		pos += scnprintf(buf + pos, len - pos,
-				 "[%07lu.%03lu] status = 0x%x\n",
-				 (unsigned long)stats.time, rem_nsec / 1000,
-				 stats.status);
+		seq_printf(s, "[%07lu.%03lu] status = 0x%x\n",
+			   (unsigned long)stats.time, rem_nsec / 1000,
+			   stats.status);
 	}
 
 	return 0;
 }
 
-
-static const struct hclge_dbg_item mac_list_items[] = {
-	{ "FUNC_ID", 2 },
-	{ "MAC_ADDR", 12 },
-	{ "STATE", 2 },
-};
-
-static void hclge_dbg_dump_mac_list(struct hclge_dev *hdev, char *buf, int len,
-				    bool is_unicast)
+static void hclge_dbg_dump_mac_list(struct seq_file *s, bool is_unicast)
 {
-	char data_str[ARRAY_SIZE(mac_list_items)][HCLGE_DBG_DATA_STR_LEN];
-	char content[HCLGE_DBG_INFO_LEN], str_id[HCLGE_DBG_ID_LEN];
-	char *result[ARRAY_SIZE(mac_list_items)];
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	struct hclge_mac_node *mac_node, *tmp;
 	struct hclge_vport *vport;
 	struct list_head *list;
 	u32 func_id;
-	int pos = 0;
-	int i;
 
-	for (i = 0; i < ARRAY_SIZE(mac_list_items); i++)
-		result[i] = &data_str[i][0];
-
-	pos += scnprintf(buf + pos, len - pos, "%s MAC_LIST:\n",
-			 is_unicast ? "UC" : "MC");
-	hclge_dbg_fill_content(content, sizeof(content), mac_list_items,
-			       NULL, ARRAY_SIZE(mac_list_items));
-	pos += scnprintf(buf + pos, len - pos, "%s", content);
+	seq_printf(s, "%s MAC_LIST:\n", is_unicast ? "UC" : "MC");
+	seq_puts(s, "FUNC_ID  MAC_ADDR            STATE\n");
 
 	for (func_id = 0; func_id < hdev->num_alloc_vport; func_id++) {
 		vport = &hdev->vport[func_id];
 		list = is_unicast ? &vport->uc_mac_list : &vport->mc_mac_list;
 		spin_lock_bh(&vport->mac_list_lock);
 		list_for_each_entry_safe(mac_node, tmp, list, node) {
-			i = 0;
-			result[i++] = hclge_dbg_get_func_id_str(str_id,
-								func_id);
-			sprintf(result[i++], "%pM", mac_node->mac_addr);
-			sprintf(result[i++], "%5s",
-				hclge_mac_state_str[mac_node->state]);
-			hclge_dbg_fill_content(content, sizeof(content),
-					       mac_list_items,
-					       (const char **)result,
-					       ARRAY_SIZE(mac_list_items));
-			pos += scnprintf(buf + pos, len - pos, "%s", content);
+			if (func_id)
+				seq_printf(s, "vf%-7u", func_id - 1U);
+			else
+				seq_puts(s, "pf       ");
+			seq_printf(s, "%pM   ", mac_node->mac_addr);
+			seq_printf(s, "%5s\n",
+				   hclge_mac_state_str[mac_node->state]);
 		}
 		spin_unlock_bh(&vport->mac_list_lock);
 	}
 }
 
-static int hclge_dbg_dump_umv_info(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_umv_info(struct seq_file *s, void *data)
 {
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	u8 func_num = pci_num_vf(hdev->pdev) + 1;
 	struct hclge_vport *vport;
-	int pos = 0;
 	u8 i;
 
-	pos += scnprintf(buf, len, "num_alloc_vport   : %u\n",
-			  hdev->num_alloc_vport);
-	pos += scnprintf(buf + pos, len - pos, "max_umv_size     : %u\n",
-			 hdev->max_umv_size);
-	pos += scnprintf(buf + pos, len - pos, "wanted_umv_size  : %u\n",
-			 hdev->wanted_umv_size);
-	pos += scnprintf(buf + pos, len - pos, "priv_umv_size    : %u\n",
-			 hdev->priv_umv_size);
+	seq_printf(s, "num_alloc_vport   : %u\n", hdev->num_alloc_vport);
+	seq_printf(s, "max_umv_size     : %u\n", hdev->max_umv_size);
+	seq_printf(s, "wanted_umv_size  : %u\n", hdev->wanted_umv_size);
+	seq_printf(s, "priv_umv_size    : %u\n", hdev->priv_umv_size);
 
 	mutex_lock(&hdev->vport_lock);
-	pos += scnprintf(buf + pos, len - pos, "share_umv_size   : %u\n",
-			 hdev->share_umv_size);
+	seq_printf(s, "share_umv_size   : %u\n", hdev->share_umv_size);
 	for (i = 0; i < func_num; i++) {
 		vport = &hdev->vport[i];
-		pos += scnprintf(buf + pos, len - pos,
-				 "vport(%u) used_umv_num : %u\n",
-				 i, vport->used_umv_num);
+		seq_printf(s, "vport(%u) used_umv_num : %u\n",
+			   i, vport->used_umv_num);
 	}
 	mutex_unlock(&hdev->vport_lock);
 
-	pos += scnprintf(buf + pos, len - pos, "used_mc_mac_num  : %u\n",
-			 hdev->used_mc_mac_num);
+	seq_printf(s, "used_mc_mac_num  : %u\n", hdev->used_mc_mac_num);
 
 	return 0;
 }
@@ -2852,38 +2626,12 @@ static int hclge_get_port_vlan_filter_bypass_state(struct hclge_dev *hdev,
 	return 0;
 }
 
-static const struct hclge_dbg_item vlan_filter_items[] = {
-	{ "FUNC_ID", 2 },
-	{ "I_VF_VLAN_FILTER", 2 },
-	{ "E_VF_VLAN_FILTER", 2 },
-	{ "PORT_VLAN_FILTER_BYPASS", 0 }
-};
-
-static const struct hclge_dbg_item vlan_offload_items[] = {
-	{ "FUNC_ID", 2 },
-	{ "PVID", 4 },
-	{ "ACCEPT_TAG1", 2 },
-	{ "ACCEPT_TAG2", 2 },
-	{ "ACCEPT_UNTAG1", 2 },
-	{ "ACCEPT_UNTAG2", 2 },
-	{ "INSERT_TAG1", 2 },
-	{ "INSERT_TAG2", 2 },
-	{ "SHIFT_TAG", 2 },
-	{ "STRIP_TAG1", 2 },
-	{ "STRIP_TAG2", 2 },
-	{ "DROP_TAG1", 2 },
-	{ "DROP_TAG2", 2 },
-	{ "PRI_ONLY_TAG1", 2 },
-	{ "PRI_ONLY_TAG2", 0 }
-};
-
-static int hclge_dbg_dump_vlan_filter_config(struct hclge_dev *hdev, char *buf,
-					     int len, int *pos)
+static int hclge_dbg_dump_vlan_filter_config(struct hclge_dev *hdev,
+					     struct seq_file *s)
 {
-	char content[HCLGE_DBG_VLAN_FLTR_INFO_LEN], str_id[HCLGE_DBG_ID_LEN];
-	const char *result[ARRAY_SIZE(vlan_filter_items)];
-	u8 i, j, vlan_fe, bypass, ingress, egress;
 	u8 func_num = pci_num_vf(hdev->pdev) + 1; /* pf and enabled vf num */
+	u8 i, vlan_fe, bypass, ingress, egress;
+	char str_id[HCLGE_DBG_ID_LEN];
 	int ret;
 
 	ret = hclge_get_vlan_filter_state(hdev, HCLGE_FILTER_TYPE_PORT, 0,
@@ -2893,14 +2641,11 @@ static int hclge_dbg_dump_vlan_filter_config(struct hclge_dev *hdev, char *buf,
 	ingress = vlan_fe & HCLGE_FILTER_FE_NIC_INGRESS_B;
 	egress = vlan_fe & HCLGE_FILTER_FE_NIC_EGRESS_B ? 1 : 0;
 
-	*pos += scnprintf(buf, len, "I_PORT_VLAN_FILTER: %s\n",
-			  state_str[ingress]);
-	*pos += scnprintf(buf + *pos, len - *pos, "E_PORT_VLAN_FILTER: %s\n",
-			  state_str[egress]);
+	seq_printf(s, "I_PORT_VLAN_FILTER: %s\n", str_on_off(ingress));
+	seq_printf(s, "E_PORT_VLAN_FILTER: %s\n", str_on_off(egress));
 
-	hclge_dbg_fill_content(content, sizeof(content), vlan_filter_items,
-			       NULL, ARRAY_SIZE(vlan_filter_items));
-	*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
+	seq_puts(s, "FUNC_ID  I_VF_VLAN_FILTER  E_VF_VLAN_FILTER  ");
+	seq_puts(s, "PORT_VLAN_FILTER_BYPASS\n");
 
 	for (i = 0; i < func_num; i++) {
 		ret = hclge_get_vlan_filter_state(hdev, HCLGE_FILTER_TYPE_VF, i,
@@ -2913,37 +2658,32 @@ static int hclge_dbg_dump_vlan_filter_config(struct hclge_dev *hdev, char *buf,
 		ret = hclge_get_port_vlan_filter_bypass_state(hdev, i, &bypass);
 		if (ret)
 			return ret;
-		j = 0;
-		result[j++] = hclge_dbg_get_func_id_str(str_id, i);
-		result[j++] = state_str[ingress];
-		result[j++] = state_str[egress];
-		result[j++] =
-			test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B,
-				 hdev->ae_dev->caps) ? state_str[bypass] : "NA";
-		hclge_dbg_fill_content(content, sizeof(content),
-				       vlan_filter_items, result,
-				       ARRAY_SIZE(vlan_filter_items));
-		*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
+
+		seq_printf(s, "%-9s%-18s%-18s%s\n",
+			   hclge_dbg_get_func_id_str(str_id, i),
+			   str_on_off(ingress), str_on_off(egress),
+			   test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B,
+				    hdev->ae_dev->caps) ?
+						str_on_off(bypass) : "NA");
 	}
-	*pos += scnprintf(buf + *pos, len - *pos, "\n");
+	seq_puts(s, "\n");
 
 	return 0;
 }
 
-static int hclge_dbg_dump_vlan_offload_config(struct hclge_dev *hdev, char *buf,
-					      int len, int *pos)
+static int hclge_dbg_dump_vlan_offload_config(struct hclge_dev *hdev,
+					      struct seq_file *s)
 {
-	char str_id[HCLGE_DBG_ID_LEN], str_pvid[HCLGE_DBG_ID_LEN];
-	const char *result[ARRAY_SIZE(vlan_offload_items)];
-	char content[HCLGE_DBG_VLAN_OFFLOAD_INFO_LEN];
 	u8 func_num = pci_num_vf(hdev->pdev) + 1; /* pf and enabled vf num */
 	struct hclge_dbg_vlan_cfg vlan_cfg;
+	char str_id[HCLGE_DBG_ID_LEN];
 	int ret;
-	u8 i, j;
+	u8 i;
 
-	hclge_dbg_fill_content(content, sizeof(content), vlan_offload_items,
-			       NULL, ARRAY_SIZE(vlan_offload_items));
-	*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
+	seq_puts(s, "FUNC_ID  PVID  ACCEPT_TAG1  ACCEPT_TAG2 ACCEPT_UNTAG1  ");
+	seq_puts(s, "ACCEPT_UNTAG2  INSERT_TAG1  INSERT_TAG2  SHIFT_TAG  ");
+	seq_puts(s, "STRIP_TAG1  STRIP_TAG2  DROP_TAG1  DROP_TAG2  ");
+	seq_puts(s, "PRI_ONLY_TAG1  PRI_ONLY_TAG2\n");
 
 	for (i = 0; i < func_num; i++) {
 		ret = hclge_get_vlan_tx_offload_cfg(hdev, i, &vlan_cfg);
@@ -2954,107 +2694,92 @@ static int hclge_dbg_dump_vlan_offload_config(struct hclge_dev *hdev, char *buf,
 		if (ret)
 			return ret;
 
-		sprintf(str_pvid, "%u", vlan_cfg.pvid);
-		j = 0;
-		result[j++] = hclge_dbg_get_func_id_str(str_id, i);
-		result[j++] = str_pvid;
-		result[j++] = state_str[vlan_cfg.accept_tag1];
-		result[j++] = state_str[vlan_cfg.accept_tag2];
-		result[j++] = state_str[vlan_cfg.accept_untag1];
-		result[j++] = state_str[vlan_cfg.accept_untag2];
-		result[j++] = state_str[vlan_cfg.insert_tag1];
-		result[j++] = state_str[vlan_cfg.insert_tag2];
-		result[j++] = state_str[vlan_cfg.shift_tag];
-		result[j++] = state_str[vlan_cfg.strip_tag1];
-		result[j++] = state_str[vlan_cfg.strip_tag2];
-		result[j++] = state_str[vlan_cfg.drop_tag1];
-		result[j++] = state_str[vlan_cfg.drop_tag2];
-		result[j++] = state_str[vlan_cfg.pri_only1];
-		result[j++] = state_str[vlan_cfg.pri_only2];
-
-		hclge_dbg_fill_content(content, sizeof(content),
-				       vlan_offload_items, result,
-				       ARRAY_SIZE(vlan_offload_items));
-		*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
+		seq_printf(s, "%-9s", hclge_dbg_get_func_id_str(str_id, i));
+		seq_printf(s, "%-6u", vlan_cfg.pvid);
+		seq_printf(s, "%-13s", str_on_off(vlan_cfg.accept_tag1));
+		seq_printf(s, "%-12s", str_on_off(vlan_cfg.accept_tag2));
+		seq_printf(s, "%-15s", str_on_off(vlan_cfg.accept_untag1));
+		seq_printf(s, "%-15s", str_on_off(vlan_cfg.accept_untag2));
+		seq_printf(s, "%-13s", str_on_off(vlan_cfg.insert_tag1));
+		seq_printf(s, "%-13s", str_on_off(vlan_cfg.insert_tag2));
+		seq_printf(s, "%-11s", str_on_off(vlan_cfg.shift_tag));
+		seq_printf(s, "%-12s", str_on_off(vlan_cfg.strip_tag1));
+		seq_printf(s, "%-12s", str_on_off(vlan_cfg.strip_tag2));
+		seq_printf(s, "%-11s", str_on_off(vlan_cfg.drop_tag1));
+		seq_printf(s, "%-11s", str_on_off(vlan_cfg.drop_tag2));
+		seq_printf(s, "%-15s", str_on_off(vlan_cfg.pri_only1));
+		seq_printf(s, "%s\n", str_on_off(vlan_cfg.pri_only2));
 	}
 
 	return 0;
 }
 
-static int hclge_dbg_dump_vlan_config(struct hclge_dev *hdev, char *buf,
-				      int len)
+static int hclge_dbg_dump_vlan_config(struct seq_file *s, void *data)
 {
-	int pos = 0;
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	int ret;
 
-	ret = hclge_dbg_dump_vlan_filter_config(hdev, buf, len, &pos);
+	ret = hclge_dbg_dump_vlan_filter_config(hdev, s);
 	if (ret)
 		return ret;
 
-	return hclge_dbg_dump_vlan_offload_config(hdev, buf, len, &pos);
+	return hclge_dbg_dump_vlan_offload_config(hdev, s);
 }
 
-static int hclge_dbg_dump_ptp_info(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_ptp_info(struct seq_file *s, void *data)
 {
+	struct hclge_dev *hdev = hclge_seq_file_to_hdev(s);
 	struct hclge_ptp *ptp = hdev->ptp;
 	u32 sw_cfg = ptp->ptp_cfg;
 	unsigned int tx_start;
 	unsigned int last_rx;
-	int pos = 0;
 	u32 hw_cfg;
 	int ret;
 
-	pos += scnprintf(buf + pos, len - pos, "phc %s's debug info:\n",
-			 ptp->info.name);
-	pos += scnprintf(buf + pos, len - pos, "ptp enable: %s\n",
-			 test_bit(HCLGE_PTP_FLAG_EN, &ptp->flags) ?
-			 "yes" : "no");
-	pos += scnprintf(buf + pos, len - pos, "ptp tx enable: %s\n",
-			 test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) ?
-			 "yes" : "no");
-	pos += scnprintf(buf + pos, len - pos, "ptp rx enable: %s\n",
-			 test_bit(HCLGE_PTP_FLAG_RX_EN, &ptp->flags) ?
-			 "yes" : "no");
+	seq_printf(s, "phc %s's debug info:\n", ptp->info.name);
+	seq_printf(s, "ptp enable: %s\n",
+		   str_yes_no(test_bit(HCLGE_PTP_FLAG_EN, &ptp->flags)));
+	seq_printf(s, "ptp tx enable: %s\n",
+		   str_yes_no(test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags)));
+	seq_printf(s, "ptp rx enable: %s\n",
+		   str_yes_no(test_bit(HCLGE_PTP_FLAG_RX_EN, &ptp->flags)));
 
 	last_rx = jiffies_to_msecs(ptp->last_rx);
-	pos += scnprintf(buf + pos, len - pos, "last rx time: %lu.%lu\n",
-			 last_rx / MSEC_PER_SEC, last_rx % MSEC_PER_SEC);
-	pos += scnprintf(buf + pos, len - pos, "rx count: %lu\n", ptp->rx_cnt);
+	seq_printf(s, "last rx time: %lu.%lu\n",
+		   last_rx / MSEC_PER_SEC, last_rx % MSEC_PER_SEC);
+	seq_printf(s, "rx count: %lu\n", ptp->rx_cnt);
 
 	tx_start = jiffies_to_msecs(ptp->tx_start);
-	pos += scnprintf(buf + pos, len - pos, "last tx start time: %lu.%lu\n",
-			 tx_start / MSEC_PER_SEC, tx_start % MSEC_PER_SEC);
-	pos += scnprintf(buf + pos, len - pos, "tx count: %lu\n", ptp->tx_cnt);
-	pos += scnprintf(buf + pos, len - pos, "tx skipped count: %lu\n",
-			 ptp->tx_skipped);
-	pos += scnprintf(buf + pos, len - pos, "tx timeout count: %lu\n",
-			 ptp->tx_timeout);
-	pos += scnprintf(buf + pos, len - pos, "last tx seqid: %u\n",
-			 ptp->last_tx_seqid);
+	seq_printf(s, "last tx start time: %lu.%lu\n",
+		   tx_start / MSEC_PER_SEC, tx_start % MSEC_PER_SEC);
+	seq_printf(s, "tx count: %lu\n", ptp->tx_cnt);
+	seq_printf(s, "tx skipped count: %lu\n", ptp->tx_skipped);
+	seq_printf(s, "tx timeout count: %lu\n", ptp->tx_timeout);
+	seq_printf(s, "last tx seqid: %u\n", ptp->last_tx_seqid);
+
 
 	ret = hclge_ptp_cfg_qry(hdev, &hw_cfg);
 	if (ret)
 		return ret;
 
-	pos += scnprintf(buf + pos, len - pos, "sw_cfg: %#x, hw_cfg: %#x\n",
-			 sw_cfg, hw_cfg);
+	seq_printf(s, "sw_cfg: %#x, hw_cfg: %#x\n", sw_cfg, hw_cfg);
 
-	pos += scnprintf(buf + pos, len - pos, "tx type: %d, rx filter: %d\n",
-			 ptp->ts_cfg.tx_type, ptp->ts_cfg.rx_filter);
+	seq_printf(s, "tx type: %d, rx filter: %d\n",
+		   ptp->ts_cfg.tx_type, ptp->ts_cfg.rx_filter);
 
 	return 0;
 }
 
-static int hclge_dbg_dump_mac_uc(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_mac_uc(struct seq_file *s, void *data)
 {
-	hclge_dbg_dump_mac_list(hdev, buf, len, true);
+	hclge_dbg_dump_mac_list(s, true);
 
 	return 0;
 }
 
-static int hclge_dbg_dump_mac_mc(struct hclge_dev *hdev, char *buf, int len)
+static int hclge_dbg_dump_mac_mc(struct seq_file *s, void *data)
 {
-	hclge_dbg_dump_mac_list(hdev, buf, len, false);
+	hclge_dbg_dump_mac_list(s, false);
 
 	return 0;
 }
@@ -3062,156 +2787,156 @@ static int hclge_dbg_dump_mac_mc(struct hclge_dev *hdev, char *buf, int len)
 static const struct hclge_dbg_func hclge_dbg_cmd_func[] = {
 	{
 		.cmd = HNAE3_DBG_CMD_TM_NODES,
-		.dbg_dump = hclge_dbg_dump_tm_nodes,
+		.dbg_read_func = hclge_dbg_dump_tm_nodes,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_TM_PRI,
-		.dbg_dump = hclge_dbg_dump_tm_pri,
+		.dbg_read_func = hclge_dbg_dump_tm_pri,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_TM_QSET,
-		.dbg_dump = hclge_dbg_dump_tm_qset,
+		.dbg_read_func = hclge_dbg_dump_tm_qset,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_TM_MAP,
-		.dbg_dump = hclge_dbg_dump_tm_map,
+		.dbg_read_func = hclge_dbg_dump_tm_map,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_TM_PG,
-		.dbg_dump = hclge_dbg_dump_tm_pg,
+		.dbg_read_func = hclge_dbg_dump_tm_pg,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_TM_PORT,
-		.dbg_dump = hclge_dbg_dump_tm_port,
+		.dbg_read_func = hclge_dbg_dump_tm_port,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_TC_SCH_INFO,
-		.dbg_dump = hclge_dbg_dump_tc,
+		.dbg_read_func = hclge_dbg_dump_tc,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_QOS_PAUSE_CFG,
-		.dbg_dump = hclge_dbg_dump_qos_pause_cfg,
+		.dbg_read_func = hclge_dbg_dump_qos_pause_cfg,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_QOS_PRI_MAP,
-		.dbg_dump = hclge_dbg_dump_qos_pri_map,
+		.dbg_read_func = hclge_dbg_dump_qos_pri_map,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_QOS_DSCP_MAP,
-		.dbg_dump = hclge_dbg_dump_qos_dscp_map,
+		.dbg_read_func = hclge_dbg_dump_qos_dscp_map,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_QOS_BUF_CFG,
-		.dbg_dump = hclge_dbg_dump_qos_buf_cfg,
+		.dbg_read_func = hclge_dbg_dump_qos_buf_cfg,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_MAC_UC,
-		.dbg_dump = hclge_dbg_dump_mac_uc,
+		.dbg_read_func = hclge_dbg_dump_mac_uc,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_MAC_MC,
-		.dbg_dump = hclge_dbg_dump_mac_mc,
+		.dbg_read_func = hclge_dbg_dump_mac_mc,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_MNG_TBL,
-		.dbg_dump = hclge_dbg_dump_mng_table,
+		.dbg_read_func = hclge_dbg_dump_mng_table,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_LOOPBACK,
-		.dbg_dump = hclge_dbg_dump_loopback,
+		.dbg_read_func = hclge_dbg_dump_loopback,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_PTP_INFO,
-		.dbg_dump = hclge_dbg_dump_ptp_info,
+		.dbg_read_func = hclge_dbg_dump_ptp_info,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_INTERRUPT_INFO,
-		.dbg_dump = hclge_dbg_dump_interrupt,
+		.dbg_read_func = hclge_dbg_dump_interrupt,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_RESET_INFO,
-		.dbg_dump = hclge_dbg_dump_rst_info,
+		.dbg_read_func = hclge_dbg_seq_dump_rst_info,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_IMP_INFO,
-		.dbg_dump = hclge_dbg_get_imp_stats_info,
+		.dbg_read_func = hclge_dbg_get_imp_stats_info,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_NCL_CONFIG,
-		.dbg_dump = hclge_dbg_dump_ncl_config,
+		.dbg_read_func = hclge_dbg_dump_ncl_config,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_REG_BIOS_COMMON,
-		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+		.dbg_read_func = hclge_dbg_dump_bios_reg_cmd,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_REG_SSU,
-		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+		.dbg_read_func = hclge_dbg_dump_ssu_reg_cmd,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_REG_IGU_EGU,
-		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+		.dbg_read_func = hclge_dbg_dump_igu_egu_reg_cmd,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_REG_RPU,
-		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+		.dbg_read_func = hclge_dbg_dump_rpu_reg_cmd,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_REG_NCSI,
-		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+		.dbg_read_func = hclge_dbg_dump_ncsi_reg_cmd,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_REG_RTC,
-		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+		.dbg_read_func = hclge_dbg_dump_rtc_reg_cmd,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_REG_PPP,
-		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+		.dbg_read_func = hclge_dbg_dump_ppp_reg_cmd,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_REG_RCB,
-		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+		.dbg_read_func = hclge_dbg_dump_rcb_reg_cmd,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_REG_TQP,
-		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+		.dbg_read_func = hclge_dbg_dump_tqp_reg_cmd,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_REG_MAC,
-		.dbg_dump = hclge_dbg_dump_mac,
+		.dbg_read_func = hclge_dbg_dump_mac,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_REG_DCB,
-		.dbg_dump = hclge_dbg_dump_dcb,
+		.dbg_read_func = hclge_dbg_dump_dcb,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_FD_TCAM,
-		.dbg_dump = hclge_dbg_dump_fd_tcam,
+		.dbg_read_func = hclge_dbg_dump_fd_tcam,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_MAC_TNL_STATUS,
-		.dbg_dump = hclge_dbg_dump_mac_tnl_status,
+		.dbg_read_func = hclge_dbg_dump_mac_tnl_status,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_SERV_INFO,
-		.dbg_dump = hclge_dbg_dump_serv_info,
+		.dbg_read_func = hclge_dbg_dump_serv_info,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_VLAN_CONFIG,
-		.dbg_dump = hclge_dbg_dump_vlan_config,
+		.dbg_read_func = hclge_dbg_dump_vlan_config,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_FD_COUNTER,
-		.dbg_dump = hclge_dbg_dump_fd_counter,
+		.dbg_read_func = hclge_dbg_dump_fd_counter,
 	},
 	{
 		.cmd = HNAE3_DBG_CMD_UMV_INFO,
-		.dbg_dump = hclge_dbg_dump_umv_info,
+		.dbg_read_func = hclge_dbg_dump_umv_info,
 	},
 };
 
-int hclge_dbg_read_cmd(struct hnae3_handle *handle, enum hnae3_dbg_cmd cmd,
-		       char *buf, int len)
+int hclge_dbg_get_read_func(struct hnae3_handle *handle, enum hnae3_dbg_cmd cmd,
+			    read_func *func)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	const struct hclge_dbg_func *cmd_func;
@@ -3221,11 +2946,8 @@ int hclge_dbg_read_cmd(struct hnae3_handle *handle, enum hnae3_dbg_cmd cmd,
 	for (i = 0; i < ARRAY_SIZE(hclge_dbg_cmd_func); i++) {
 		if (cmd == hclge_dbg_cmd_func[i].cmd) {
 			cmd_func = &hclge_dbg_cmd_func[i];
-			if (cmd_func->dbg_dump)
-				return cmd_func->dbg_dump(hdev, buf, len);
-			else
-				return cmd_func->dbg_dump_reg(hdev, cmd, buf,
-							      len);
+			*func = cmd_func->dbg_read_func;
+			return 0;
 		}
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
index 2b998cbed826..317f79efd54c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
@@ -92,6 +92,7 @@ struct hclge_dbg_func {
 	int (*dbg_dump)(struct hclge_dev *hdev, char *buf, int len);
 	int (*dbg_dump_reg)(struct hclge_dev *hdev, enum hnae3_dbg_cmd cmd,
 			    char *buf, int len);
+	read_func dbg_read_func;
 };
 
 struct hclge_dbg_status_dfx_info {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 05942fa78b11..cf8abbe01840 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -6,6 +6,7 @@
 #include <linux/etherdevice.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
@@ -489,7 +490,7 @@ static int hclge_mac_update_stats_complete(struct hclge_dev *hdev)
 	desc_num = reg_num / HCLGE_REG_NUM_PER_DESC + 1;
 
 	/* This may be called inside atomic sections,
-	 * so GFP_ATOMIC is more suitalbe here
+	 * so GFP_ATOMIC is more suitable here
 	 */
 	desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_ATOMIC);
 	if (!desc)
@@ -581,7 +582,7 @@ static u64 *hclge_comm_get_stats(struct hclge_dev *hdev,
 				 int size, u64 *data)
 {
 	u64 *buf = data;
-	u32 i;
+	int i;
 
 	for (i = 0; i < size; i++) {
 		if (strs[i].stats_num > hdev->ae_dev->dev_specs.mac_stats_num)
@@ -598,7 +599,7 @@ static void hclge_comm_get_strings(struct hclge_dev *hdev, u32 stringset,
 				   const struct hclge_comm_stats_str strs[],
 				   int size, u8 **data)
 {
-	u32 i;
+	int i;
 
 	if (stringset != ETH_SS_STATS)
 		return;
@@ -2181,8 +2182,8 @@ static bool hclge_drop_pfc_buf_till_fit(struct hclge_dev *hdev,
 	return hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all);
 }
 
-static int hclge_only_alloc_priv_buff(struct hclge_dev *hdev,
-				      struct hclge_pkt_buf_alloc *buf_alloc)
+static bool hclge_only_alloc_priv_buff(struct hclge_dev *hdev,
+				       struct hclge_pkt_buf_alloc *buf_alloc)
 {
 #define COMPENSATE_BUFFER	0x3C00
 #define COMPENSATE_HALF_MPS_NUM	5
@@ -2357,7 +2358,7 @@ static int hclge_common_thrd_config(struct hclge_dev *hdev,
 	for (i = 0; i < 2; i++) {
 		hclge_cmd_setup_basic_desc(&desc[i],
 					   HCLGE_OPC_RX_COM_THRD_ALLOC, false);
-		req = (struct hclge_rx_com_thrd *)&desc[i].data;
+		req = (struct hclge_rx_com_thrd *)desc[i].data;
 
 		/* The first descriptor set the NEXT bit to 1 */
 		if (i == 0)
@@ -2623,7 +2624,7 @@ int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex, u8 lan
 	int ret;
 
 	duplex = hclge_check_speed_dup(duplex, speed);
-	if (!mac->support_autoneg && mac->speed == speed &&
+	if (!mac->support_autoneg && mac->speed == (u32)speed &&
 	    mac->duplex == duplex && (mac->lane_num == lane_num || lane_num == 0))
 		return 0;
 
@@ -2651,7 +2652,7 @@ static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed,
 	if (ret)
 		return ret;
 
-	hdev->hw.mac.req_speed = speed;
+	hdev->hw.mac.req_speed = (u32)speed;
 	hdev->hw.mac.req_duplex = duplex;
 
 	return 0;
@@ -3445,7 +3446,7 @@ static int hclge_tp_port_init(struct hclge_dev *hdev)
 static int hclge_update_port_info(struct hclge_dev *hdev)
 {
 	struct hclge_mac *mac = &hdev->hw.mac;
-	int speed;
+	u32 speed;
 	int ret;
 
 	/* get the port info from SFP cmd if not copper port */
@@ -3574,6 +3575,17 @@ static int hclge_set_vf_link_state(struct hnae3_handle *handle, int vf,
 	return ret;
 }
 
+static void hclge_set_reset_pending(struct hclge_dev *hdev,
+				    enum hnae3_reset_type reset_type)
+{
+	/* When an incorrect reset type is executed, the get_reset_level
+	 * function generates the HNAE3_NONE_RESET flag. As a result, this
+	 * type do not need to pending.
+	 */
+	if (reset_type != HNAE3_NONE_RESET)
+		set_bit(reset_type, &hdev->reset_pending);
+}
+
 static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 {
 	u32 cmdq_src_reg, msix_src_reg, hw_err_src_reg;
@@ -3594,7 +3606,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	 */
 	if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & msix_src_reg) {
 		dev_info(&hdev->pdev->dev, "IMP reset interrupt\n");
-		set_bit(HNAE3_IMP_RESET, &hdev->reset_pending);
+		hclge_set_reset_pending(hdev, HNAE3_IMP_RESET);
 		set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state);
 		*clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B);
 		hdev->rst_stats.imp_rst_cnt++;
@@ -3604,7 +3616,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & msix_src_reg) {
 		dev_info(&hdev->pdev->dev, "global reset interrupt\n");
 		set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state);
-		set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending);
+		hclge_set_reset_pending(hdev, HNAE3_GLOBAL_RESET);
 		*clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B);
 		hdev->rst_stats.global_rst_cnt++;
 		return HCLGE_VECTOR0_EVENT_RST;
@@ -3759,7 +3771,7 @@ static int hclge_misc_irq_init(struct hclge_dev *hdev)
 	snprintf(hdev->misc_vector.name, HNAE3_INT_NAME_LEN, "%s-misc-%s",
 		 HCLGE_NAME, pci_name(hdev->pdev));
 	ret = request_irq(hdev->misc_vector.vector_irq, hclge_misc_irq_handle,
-			  0, hdev->misc_vector.name, hdev);
+			  IRQF_NO_AUTOEN, hdev->misc_vector.name, hdev);
 	if (ret) {
 		hclge_free_vector(hdev, 0);
 		dev_err(&hdev->pdev->dev, "request misc irq(%d) fail\n",
@@ -4052,7 +4064,7 @@ static void hclge_do_reset(struct hclge_dev *hdev)
 	case HNAE3_FUNC_RESET:
 		dev_info(&pdev->dev, "PF reset requested\n");
 		/* schedule again to check later */
-		set_bit(HNAE3_FUNC_RESET, &hdev->reset_pending);
+		hclge_set_reset_pending(hdev, HNAE3_FUNC_RESET);
 		hclge_reset_task_schedule(hdev);
 		break;
 	default:
@@ -4086,6 +4098,8 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev,
 		clear_bit(HNAE3_FLR_RESET, addr);
 	}
 
+	clear_bit(HNAE3_NONE_RESET, addr);
+
 	if (hdev->reset_type != HNAE3_NONE_RESET &&
 	    rst_level < hdev->reset_type)
 		return HNAE3_NONE_RESET;
@@ -4227,7 +4241,7 @@ static bool hclge_reset_err_handle(struct hclge_dev *hdev)
 		return false;
 	} else if (hdev->rst_stats.reset_fail_cnt < MAX_RESET_FAIL_CNT) {
 		hdev->rst_stats.reset_fail_cnt++;
-		set_bit(hdev->reset_type, &hdev->reset_pending);
+		hclge_set_reset_pending(hdev, hdev->reset_type);
 		dev_info(&hdev->pdev->dev,
 			 "re-schedule reset task(%u)\n",
 			 hdev->rst_stats.reset_fail_cnt);
@@ -4470,14 +4484,26 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
 static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
 					enum hnae3_reset_type rst_type)
 {
+#define HCLGE_SUPPORT_RESET_TYPE \
+	(BIT(HNAE3_FLR_RESET) | BIT(HNAE3_FUNC_RESET) | \
+	BIT(HNAE3_GLOBAL_RESET) | BIT(HNAE3_IMP_RESET))
+
 	struct hclge_dev *hdev = ae_dev->priv;
 
+	if (!(BIT(rst_type) & HCLGE_SUPPORT_RESET_TYPE)) {
+		/* To prevent reset triggered by hclge_reset_event */
+		set_bit(HNAE3_NONE_RESET, &hdev->default_reset_request);
+		dev_warn(&hdev->pdev->dev, "unsupported reset type %d\n",
+			 rst_type);
+		return;
+	}
+
 	set_bit(rst_type, &hdev->default_reset_request);
 }
 
 static void hclge_reset_timer(struct timer_list *t)
 {
-	struct hclge_dev *hdev = from_timer(hdev, t, reset_timer);
+	struct hclge_dev *hdev = timer_container_of(hdev, t, reset_timer);
 
 	/* if default_reset_request has no value, it means that this reset
 	 * request has already be handled, so just return here
@@ -4846,7 +4872,7 @@ static int hclge_set_rss(struct hnae3_handle *handle, const u32 *indir,
 }
 
 static int hclge_set_rss_tuple(struct hnae3_handle *handle,
-			       struct ethtool_rxnfc *nfc)
+			       const struct ethtool_rxfh_fields *nfc)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
@@ -4864,7 +4890,7 @@ static int hclge_set_rss_tuple(struct hnae3_handle *handle,
 }
 
 static int hclge_get_rss_tuple(struct hnae3_handle *handle,
-			       struct ethtool_rxnfc *nfc)
+			       struct ethtool_rxfh_fields *nfc)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	u8 tuple_sets;
@@ -6963,7 +6989,7 @@ static int hclge_get_all_rules(struct hnae3_handle *handle,
 	struct hclge_dev *hdev = vport->back;
 	struct hclge_fd_rule *rule;
 	struct hlist_node *node2;
-	int cnt = 0;
+	u32 cnt = 0;
 
 	if (!hnae3_ae_dev_fd_supported(hdev->ae_dev))
 		return -EOPNOTSUPP;
@@ -7849,7 +7875,7 @@ static int hclge_enable_phy_loopback(struct hclge_dev *hdev,
 	if (ret)
 		return ret;
 
-	return phy_loopback(phydev, true);
+	return phy_loopback(phydev, true, 0);
 }
 
 static int hclge_disable_phy_loopback(struct hclge_dev *hdev,
@@ -7857,7 +7883,7 @@ static int hclge_disable_phy_loopback(struct hclge_dev *hdev,
 {
 	int ret;
 
-	ret = phy_loopback(phydev, false);
+	ret = phy_loopback(phydev, false, 0);
 	if (ret)
 		return ret;
 
@@ -7974,7 +8000,7 @@ static int hclge_set_loopback(struct hnae3_handle *handle,
 	ret = hclge_tqp_enable(handle, en);
 	if (ret)
 		dev_err(&hdev->pdev->dev, "failed to %s tqp in loopback, ret = %d\n",
-			en ? "enable" : "disable", ret);
+			str_enable_disable(en), ret);
 
 	return ret;
 }
@@ -8197,14 +8223,14 @@ static int hclge_update_desc_vfid(struct hclge_desc *desc, int vfid, bool clr)
 		word_num = vfid / 32;
 		bit_num  = vfid % 32;
 		if (clr)
-			desc[1].data[word_num] &= cpu_to_le32(~(1 << bit_num));
+			desc[1].data[word_num] &= cpu_to_le32(~(1U << bit_num));
 		else
 			desc[1].data[word_num] |= cpu_to_le32(1 << bit_num);
 	} else {
 		word_num = (vfid - HCLGE_VF_NUM_IN_FIRST_DESC) / 32;
 		bit_num  = vfid % 32;
 		if (clr)
-			desc[2].data[word_num] &= cpu_to_le32(~(1 << bit_num));
+			desc[2].data[word_num] &= cpu_to_le32(~(1U << bit_num));
 		else
 			desc[2].data[word_num] |= cpu_to_le32(1 << bit_num);
 	}
@@ -9266,7 +9292,7 @@ static int hclge_add_mgr_tbl(struct hclge_dev *hdev,
 static int init_mgr_tbl(struct hclge_dev *hdev)
 {
 	int ret;
-	int i;
+	u32 i;
 
 	for (i = 0; i < ARRAY_SIZE(hclge_mgr_table); i++) {
 		ret = hclge_add_mgr_tbl(hdev, &hclge_mgr_table[i]);
@@ -9403,8 +9429,7 @@ static int hclge_mii_ioctl(struct hclge_dev *hdev, struct ifreq *ifr, int cmd)
 		/* this command reads phy id and register at the same time */
 		fallthrough;
 	case SIOCGMIIREG:
-		data->val_out = hclge_read_phy_reg(hdev, data->reg_num);
-		return 0;
+		return hclge_read_phy_reg(hdev, data->reg_num, &data->val_out);
 
 	case SIOCSMIIREG:
 		return hclge_write_phy_reg(hdev, data->reg_num, data->val_in);
@@ -9419,15 +9444,8 @@ static int hclge_do_ioctl(struct hnae3_handle *handle, struct ifreq *ifr,
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 
-	switch (cmd) {
-	case SIOCGHWTSTAMP:
-		return hclge_ptp_get_cfg(hdev, ifr);
-	case SIOCSHWTSTAMP:
-		return hclge_ptp_set_cfg(hdev, ifr);
-	default:
-		if (!hdev->hw.mac.phydev)
-			return hclge_mii_ioctl(hdev, ifr, cmd);
-	}
+	if (!hdev->hw.mac.phydev)
+		return hclge_mii_ioctl(hdev, ifr, cmd);
 
 	return phy_mii_ioctl(hdev->hw.mac.phydev, ifr, cmd);
 }
@@ -9550,33 +9568,36 @@ static bool hclge_need_enable_vport_vlan_filter(struct hclge_vport *vport)
 	return false;
 }
 
-int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en)
+static int __hclge_enable_vport_vlan_filter(struct hclge_vport *vport,
+					    bool request_en)
 {
-	struct hclge_dev *hdev = vport->back;
 	bool need_en;
 	int ret;
 
-	mutex_lock(&hdev->vport_lock);
-
-	vport->req_vlan_fltr_en = request_en;
-
 	need_en = hclge_need_enable_vport_vlan_filter(vport);
-	if (need_en == vport->cur_vlan_fltr_en) {
-		mutex_unlock(&hdev->vport_lock);
+	if (need_en == vport->cur_vlan_fltr_en)
 		return 0;
-	}
 
 	ret = hclge_set_vport_vlan_filter(vport, need_en);
-	if (ret) {
-		mutex_unlock(&hdev->vport_lock);
+	if (ret)
 		return ret;
-	}
 
 	vport->cur_vlan_fltr_en = need_en;
 
+	return 0;
+}
+
+int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en)
+{
+	struct hclge_dev *hdev = vport->back;
+	int ret;
+
+	mutex_lock(&hdev->vport_lock);
+	vport->req_vlan_fltr_en = request_en;
+	ret = __hclge_enable_vport_vlan_filter(vport, request_en);
 	mutex_unlock(&hdev->vport_lock);
 
-	return 0;
+	return ret;
 }
 
 static int hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable)
@@ -10597,16 +10618,19 @@ static void hclge_sync_vlan_fltr_state(struct hclge_dev *hdev)
 					&vport->state))
 			continue;
 
-		ret = hclge_enable_vport_vlan_filter(vport,
-						     vport->req_vlan_fltr_en);
+		mutex_lock(&hdev->vport_lock);
+		ret = __hclge_enable_vport_vlan_filter(vport,
+						       vport->req_vlan_fltr_en);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
 				"failed to sync vlan filter state for vport%u, ret = %d\n",
 				vport->vport_id, ret);
 			set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
 				&vport->state);
+			mutex_unlock(&hdev->vport_lock);
 			return;
 		}
+		mutex_unlock(&hdev->vport_lock);
 	}
 }
 
@@ -10687,7 +10711,7 @@ int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu)
 	max_frm_size = max(max_frm_size, HCLGE_MAC_DEFAULT_FRAME);
 	mutex_lock(&hdev->vport_lock);
 	/* VF's mps must fit within hdev->mps */
-	if (vport->vport_id && max_frm_size > hdev->mps) {
+	if (vport->vport_id && (u32)max_frm_size > hdev->mps) {
 		mutex_unlock(&hdev->vport_lock);
 		return -EINVAL;
 	} else if (vport->vport_id) {
@@ -10698,7 +10722,7 @@ int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu)
 
 	/* PF's mps must be greater then VF's mps */
 	for (i = 1; i < hdev->num_alloc_vport; i++)
-		if (max_frm_size < hdev->vport[i].mps) {
+		if ((u32)max_frm_size < hdev->vport[i].mps) {
 			dev_err(&hdev->pdev->dev,
 				"failed to set pf mtu for less than vport %d, mps = %u.\n",
 				i, hdev->vport[i].mps);
@@ -11174,9 +11198,9 @@ static void hclge_info_show(struct hclge_dev *hdev)
 	dev_info(dev, "This is %s PF\n",
 		 hdev->flag & HCLGE_FLAG_MAIN ? "main" : "not main");
 	dev_info(dev, "DCB %s\n",
-		 handle->kinfo.tc_info.dcb_ets_active ? "enable" : "disable");
+		 str_enable_disable(handle->kinfo.tc_info.dcb_ets_active));
 	dev_info(dev, "MQPRIO %s\n",
-		 handle->kinfo.tc_info.mqprio_active ? "enable" : "disable");
+		 str_enable_disable(handle->kinfo.tc_info.mqprio_active));
 	dev_info(dev, "Default tx spare buffer size: %u\n",
 		 hdev->tx_spare_buf_size);
 
@@ -11188,7 +11212,7 @@ static int hclge_init_nic_client_instance(struct hnae3_ae_dev *ae_dev,
 {
 	struct hnae3_client *client = vport->nic.client;
 	struct hclge_dev *hdev = ae_dev->priv;
-	int rst_cnt = hdev->rst_stats.reset_cnt;
+	u32 rst_cnt = hdev->rst_stats.reset_cnt;
 	int ret;
 
 	ret = client->ops->init_instance(&vport->nic);
@@ -11232,7 +11256,7 @@ static int hclge_init_roce_client_instance(struct hnae3_ae_dev *ae_dev,
 {
 	struct hclge_dev *hdev = ae_dev->priv;
 	struct hnae3_client *client;
-	int rst_cnt;
+	u32 rst_cnt;
 	int ret;
 
 	if (!hnae3_dev_roce_supported(hdev) || !hdev->roce_client ||
@@ -11397,7 +11421,7 @@ static int hclge_pci_init(struct hclge_dev *hdev)
 		ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 		if (ret) {
 			dev_err(&pdev->dev,
-				"can't set consistent PCI DMA");
+				"can't set consistent PCI DMA\n");
 			goto err_disable_device;
 		}
 		dev_warn(&pdev->dev, "set DMA mask to 32 bits\n");
@@ -11466,7 +11490,7 @@ static void hclge_state_uninit(struct hclge_dev *hdev)
 	set_bit(HCLGE_STATE_REMOVING, &hdev->state);
 
 	if (hdev->reset_timer.function)
-		del_timer_sync(&hdev->reset_timer);
+		timer_delete_sync(&hdev->reset_timer);
 	if (hdev->service_task.work.func)
 		cancel_delayed_work_sync(&hdev->service_task);
 }
@@ -11881,9 +11905,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 
 	hclge_init_rxd_adv_layout(hdev);
 
-	/* Enable MISC vector(vector0) */
-	hclge_enable_vector(&hdev->misc_vector, true);
-
 	ret = hclge_init_wol(hdev);
 	if (ret)
 		dev_warn(&pdev->dev,
@@ -11896,6 +11917,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hclge_state_init(hdev);
 	hdev->last_reset_time = jiffies;
 
+	/* Enable MISC vector(vector0) */
+	enable_irq(hdev->misc_vector.vector_irq);
+	hclge_enable_vector(&hdev->misc_vector, true);
+
 	dev_info(&hdev->pdev->dev, "%s driver initialization finished.\n",
 		 HCLGE_DRIVER_NAME);
 
@@ -11949,7 +11974,7 @@ static int hclge_set_vf_spoofchk_hw(struct hclge_dev *hdev, int vf, bool enable)
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Set vf %d mac spoof check %s failed, ret=%d\n",
-			vf, enable ? "on" : "off", ret);
+			vf, str_on_off(enable), ret);
 		return ret;
 	}
 
@@ -11957,7 +11982,7 @@ static int hclge_set_vf_spoofchk_hw(struct hclge_dev *hdev, int vf, bool enable)
 	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Set vf %d vlan spoof check %s failed, ret=%d\n",
-			vf, enable ? "on" : "off", ret);
+			vf, str_on_off(enable), ret);
 
 	return ret;
 }
@@ -12061,7 +12086,7 @@ static int hclge_vf_rate_param_check(struct hclge_dev *hdev,
 				     int min_tx_rate, int max_tx_rate)
 {
 	if (min_tx_rate != 0 ||
-	    max_tx_rate < 0 || max_tx_rate > hdev->hw.mac.max_speed) {
+	    max_tx_rate < 0 || (u32)max_tx_rate > hdev->hw.mac.max_speed) {
 		dev_err(&hdev->pdev->dev,
 			"min_tx_rate:%d [0], max_tx_rate:%d [0, %u]\n",
 			min_tx_rate, max_tx_rate, hdev->hw.mac.max_speed);
@@ -12086,7 +12111,7 @@ static int hclge_set_vf_rate(struct hnae3_handle *handle, int vf,
 	if (!vport)
 		return -EINVAL;
 
-	if (!force && max_tx_rate == vport->vf_info.max_tx_rate)
+	if (!force && (u32)max_tx_rate == vport->vf_info.max_tx_rate)
 		return 0;
 
 	ret = hclge_tm_qs_shaper_cfg(vport, max_tx_rate);
@@ -12301,7 +12326,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 
 	/* Disable MISC vector(vector0) */
 	hclge_enable_vector(&hdev->misc_vector, false);
-	synchronize_irq(hdev->misc_vector.vector_irq);
+	disable_irq(hdev->misc_vector.vector_irq);
 
 	/* Disable all hw interrupts */
 	hclge_config_mac_tnl_int(hdev, false);
@@ -12837,7 +12862,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.get_fd_all_rules = hclge_get_all_rules,
 	.enable_fd = hclge_enable_fd,
 	.add_arfs_entry = hclge_add_fd_entry_by_arfs,
-	.dbg_read_cmd = hclge_dbg_read_cmd,
+	.dbg_get_read_func = hclge_dbg_get_read_func,
 	.handle_hw_ras_error = hclge_handle_hw_ras_error,
 	.get_hw_reset_stat = hclge_get_hw_reset_stat,
 	.ae_dev_resetting = hclge_ae_dev_resetting,
@@ -12868,6 +12893,8 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.get_dscp_prio = hclge_get_dscp_prio,
 	.get_wol = hclge_get_wol,
 	.set_wol = hclge_set_wol,
+	.hwtstamp_get = hclge_ptp_get_cfg,
+	.hwtstamp_set = hclge_ptp_set_cfg,
 };
 
 static struct hnae3_ae_algo ae_algo = {
@@ -12877,9 +12904,10 @@ static struct hnae3_ae_algo ae_algo = {
 
 static int __init hclge_init(void)
 {
-	pr_info("%s is initializing\n", HCLGE_NAME);
+	pr_debug("%s is initializing\n", HCLGE_NAME);
 
-	hclge_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, HCLGE_NAME);
+	hclge_wq = alloc_workqueue("%s", WQ_UNBOUND, 0,
+				   HCLGE_NAME);
 	if (!hclge_wq) {
 		pr_err("%s: failed to create workqueue\n", HCLGE_NAME);
 		return -ENOMEM;
@@ -12892,9 +12920,11 @@ static int __init hclge_init(void)
 
 static void __exit hclge_exit(void)
 {
+	hnae3_acquire_unload_lock();
 	hnae3_unregister_ae_algo_prepare(&ae_algo);
 	hnae3_unregister_ae_algo(&ae_algo);
 	destroy_workqueue(hclge_wq);
+	hnae3_release_unload_lock();
 }
 module_init(hclge_init);
 module_exit(hclge_exit);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index b9fc719880bb..032b472d2368 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -1142,8 +1142,8 @@ int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id);
 int hclge_vport_start(struct hclge_vport *vport);
 void hclge_vport_stop(struct hclge_vport *vport);
 int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu);
-int hclge_dbg_read_cmd(struct hnae3_handle *handle, enum hnae3_dbg_cmd cmd,
-		       char *buf, int len);
+int hclge_dbg_get_read_func(struct hnae3_handle *handle, enum hnae3_dbg_cmd cmd,
+			    read_func *func);
 u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, u16 queue_id);
 int hclge_notify_client(struct hclge_dev *hdev,
 			enum hnae3_reset_notify_type type);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index 59c863306657..c7ff12a6c076 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -749,16 +749,17 @@ static int hclge_get_rss_key(struct hclge_vport *vport,
 #define HCLGE_RSS_MBX_RESP_LEN	8
 	struct hclge_dev *hdev = vport->back;
 	struct hclge_comm_rss_cfg *rss_cfg;
+	int rss_hash_key_size;
 	u8 index;
 
 	index = mbx_req->msg.data[0];
 	rss_cfg = &hdev->rss_cfg;
+	rss_hash_key_size = sizeof(rss_cfg->rss_hash_key);
 
 	/* Check the query index of rss_hash_key from VF, make sure no
 	 * more than the size of rss_hash_key.
 	 */
-	if (((index + 1) * HCLGE_RSS_MBX_RESP_LEN) >
-	      sizeof(rss_cfg->rss_hash_key)) {
+	if (((index + 1) * HCLGE_RSS_MBX_RESP_LEN) > rss_hash_key_size) {
 		dev_warn(&hdev->pdev->dev,
 			 "failed to get the rss hash key, the index(%u) invalid !\n",
 			 index);
@@ -800,7 +801,7 @@ static void hclge_handle_link_change_event(struct hclge_dev *hdev,
 
 static bool hclge_cmd_crq_empty(struct hclge_hw *hw)
 {
-	u32 tail = hclge_read_dev(hw, HCLGE_COMM_NIC_CRQ_TAIL_REG);
+	int tail = hclge_read_dev(hw, HCLGE_COMM_NIC_CRQ_TAIL_REG);
 
 	return tail == hw->hw.cmq.crq.next_to_use;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index 80079657afeb..cf881108fa57 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -151,7 +151,7 @@ int hclge_mac_mdio_config(struct hclge_dev *hdev)
 
 	mdio_bus->parent = &hdev->pdev->dev;
 	mdio_bus->priv = hdev;
-	mdio_bus->phy_mask = ~(1 << mac->phy_addr);
+	mdio_bus->phy_mask = ~(1U << mac->phy_addr);
 	ret = mdiobus_register(mdio_bus);
 	if (ret) {
 		dev_err(mdio_bus->parent,
@@ -258,7 +258,7 @@ void hclge_mac_start_phy(struct hclge_dev *hdev)
 	if (!phydev)
 		return;
 
-	phy_loopback(phydev, false);
+	phy_loopback(phydev, false, 0);
 
 	phy_start(phydev);
 }
@@ -274,7 +274,7 @@ void hclge_mac_stop_phy(struct hclge_dev *hdev)
 	phy_stop(phydev);
 }
 
-u16 hclge_read_phy_reg(struct hclge_dev *hdev, u16 reg_addr)
+int hclge_read_phy_reg(struct hclge_dev *hdev, u16 reg_addr, u16 *val)
 {
 	struct hclge_phy_reg_cmd *req;
 	struct hclge_desc desc;
@@ -286,11 +286,14 @@ u16 hclge_read_phy_reg(struct hclge_dev *hdev, u16 reg_addr)
 	req->reg_addr = cpu_to_le16(reg_addr);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
+	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to read phy reg, ret = %d.\n", ret);
+		return ret;
+	}
 
-	return le16_to_cpu(req->reg_val);
+	*val = le16_to_cpu(req->reg_val);
+	return 0;
 }
 
 int hclge_write_phy_reg(struct hclge_dev *hdev, u16 reg_addr, u16 val)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
index 4200d0b6d931..21d434c82475 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
@@ -13,7 +13,7 @@ int hclge_mac_connect_phy(struct hnae3_handle *handle);
 void hclge_mac_disconnect_phy(struct hnae3_handle *handle);
 void hclge_mac_start_phy(struct hclge_dev *hdev);
 void hclge_mac_stop_phy(struct hclge_dev *hdev);
-u16 hclge_read_phy_reg(struct hclge_dev *hdev, u16 reg_addr);
+int hclge_read_phy_reg(struct hclge_dev *hdev, u16 reg_addr, u16 *val);
 int hclge_write_phy_reg(struct hclge_dev *hdev, u16 reg_addr, u16 val);
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
index 5505caea88e9..0081c5281455 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
@@ -2,6 +2,7 @@
 // Copyright (c) 2021 Hisilicon Limited.
 
 #include <linux/skbuff.h>
+#include <linux/string_choices.h>
 #include "hclge_main.h"
 #include "hnae3.h"
 
@@ -58,6 +59,9 @@ bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb)
 	struct hclge_dev *hdev = vport->back;
 	struct hclge_ptp *ptp = hdev->ptp;
 
+	if (!ptp)
+		return false;
+
 	if (!test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) ||
 	    test_and_set_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state)) {
 		ptp->tx_skipped++;
@@ -200,13 +204,17 @@ static int hclge_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	return 0;
 }
 
-int hclge_ptp_get_cfg(struct hclge_dev *hdev, struct ifreq *ifr)
+int hclge_ptp_get_cfg(struct hnae3_handle *handle,
+		      struct kernel_hwtstamp_config *config)
 {
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
 	if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state))
 		return -EOPNOTSUPP;
 
-	return copy_to_user(ifr->ifr_data, &hdev->ptp->ts_cfg,
-		sizeof(struct hwtstamp_config)) ? -EFAULT : 0;
+	*config = hdev->ptp->ts_cfg;
+	return 0;
 }
 
 static int hclge_ptp_int_en(struct hclge_dev *hdev, bool en)
@@ -223,7 +231,7 @@ static int hclge_ptp_int_en(struct hclge_dev *hdev, bool en)
 	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"failed to %s ptp interrupt, ret = %d\n",
-			en ? "enable" : "disable", ret);
+			str_enable_disable(en), ret);
 
 	return ret;
 }
@@ -265,7 +273,7 @@ static int hclge_ptp_cfg(struct hclge_dev *hdev, u32 cfg)
 	return ret;
 }
 
-static int hclge_ptp_set_tx_mode(struct hwtstamp_config *cfg,
+static int hclge_ptp_set_tx_mode(struct kernel_hwtstamp_config *cfg,
 				 unsigned long *flags, u32 *ptp_cfg)
 {
 	switch (cfg->tx_type) {
@@ -283,7 +291,7 @@ static int hclge_ptp_set_tx_mode(struct hwtstamp_config *cfg,
 	return 0;
 }
 
-static int hclge_ptp_set_rx_mode(struct hwtstamp_config *cfg,
+static int hclge_ptp_set_rx_mode(struct kernel_hwtstamp_config *cfg,
 				 unsigned long *flags, u32 *ptp_cfg)
 {
 	int rx_filter = cfg->rx_filter;
@@ -328,7 +336,7 @@ static int hclge_ptp_set_rx_mode(struct hwtstamp_config *cfg,
 }
 
 static int hclge_ptp_set_ts_mode(struct hclge_dev *hdev,
-				 struct hwtstamp_config *cfg)
+				 struct kernel_hwtstamp_config *cfg)
 {
 	unsigned long flags = hdev->ptp->flags;
 	u32 ptp_cfg = 0;
@@ -355,9 +363,12 @@ static int hclge_ptp_set_ts_mode(struct hclge_dev *hdev,
 	return 0;
 }
 
-int hclge_ptp_set_cfg(struct hclge_dev *hdev, struct ifreq *ifr)
+int hclge_ptp_set_cfg(struct hnae3_handle *handle,
+		      struct kernel_hwtstamp_config *config,
+		      struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config cfg;
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
 	int ret;
 
 	if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state)) {
@@ -365,16 +376,13 @@ int hclge_ptp_set_cfg(struct hclge_dev *hdev, struct ifreq *ifr)
 		return -EOPNOTSUPP;
 	}
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	ret = hclge_ptp_set_ts_mode(hdev, &cfg);
+	ret = hclge_ptp_set_ts_mode(hdev, config);
 	if (ret)
 		return ret;
 
-	hdev->ptp->ts_cfg = cfg;
+	hdev->ptp->ts_cfg = *config;
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
 int hclge_ptp_get_ts_info(struct hnae3_handle *handle,
@@ -436,6 +444,13 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev)
 	ptp->info.settime64 = hclge_ptp_settime;
 
 	ptp->info.n_alarm = 0;
+
+	spin_lock_init(&ptp->lock);
+	ptp->io_base = hdev->hw.hw.io_base + HCLGE_PTP_REG_OFFSET;
+	ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
+	ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
+	hdev->ptp = ptp;
+
 	ptp->clock = ptp_clock_register(&ptp->info, &hdev->pdev->dev);
 	if (IS_ERR(ptp->clock)) {
 		dev_err(&hdev->pdev->dev,
@@ -447,12 +462,6 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev)
 		return -ENODEV;
 	}
 
-	spin_lock_init(&ptp->lock);
-	ptp->io_base = hdev->hw.hw.io_base + HCLGE_PTP_REG_OFFSET;
-	ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
-	ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
-	hdev->ptp = ptp;
-
 	return 0;
 }
 
@@ -480,7 +489,7 @@ int hclge_ptp_init(struct hclge_dev *hdev)
 
 		ret = hclge_ptp_get_cycle(hdev);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	ret = hclge_ptp_int_en(hdev, true);
@@ -492,14 +501,14 @@ int hclge_ptp_init(struct hclge_dev *hdev)
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to init freq, ret = %d\n", ret);
-		goto out;
+		goto out_clear_int;
 	}
 
 	ret = hclge_ptp_set_ts_mode(hdev, &hdev->ptp->ts_cfg);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to init ts mode, ret = %d\n", ret);
-		goto out;
+		goto out_clear_int;
 	}
 
 	ktime_get_real_ts64(&ts);
@@ -507,7 +516,7 @@ int hclge_ptp_init(struct hclge_dev *hdev)
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to init ts time, ret = %d\n", ret);
-		goto out;
+		goto out_clear_int;
 	}
 
 	set_bit(HCLGE_STATE_PTP_EN, &hdev->state);
@@ -515,6 +524,9 @@ int hclge_ptp_init(struct hclge_dev *hdev)
 
 	return 0;
 
+out_clear_int:
+	clear_bit(HCLGE_PTP_FLAG_EN, &hdev->ptp->flags);
+	hclge_ptp_int_en(hdev, false);
 out:
 	hclge_ptp_destroy_clock(hdev);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h
index 63483636c074..0162fa5ac146 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h
@@ -25,7 +25,7 @@ struct ifreq;
 #define HCLGE_PTP_TIME_SEC_H_MASK	GENMASK(15, 0)
 #define HCLGE_PTP_TIME_SEC_L_REG	0x54
 #define HCLGE_PTP_TIME_NSEC_REG		0x58
-#define HCLGE_PTP_TIME_NSEC_MASK	GENMASK(29, 0)
+#define HCLGE_PTP_TIME_NSEC_MASK	0x3fffffffLL
 #define HCLGE_PTP_TIME_NSEC_NEG		BIT(31)
 #define HCLGE_PTP_TIME_SYNC_REG		0x5C
 #define HCLGE_PTP_TIME_SYNC_EN		BIT(0)
@@ -62,7 +62,7 @@ struct hclge_ptp {
 	unsigned long flags;
 	void __iomem *io_base;
 	struct ptp_clock_info info;
-	struct hwtstamp_config ts_cfg;
+	struct kernel_hwtstamp_config ts_cfg;
 	spinlock_t lock;	/* protects ptp registers */
 	u32 ptp_cfg;
 	u32 last_tx_seqid;
@@ -133,8 +133,11 @@ bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb);
 void hclge_ptp_clean_tx_hwts(struct hclge_dev *hdev);
 void hclge_ptp_get_rx_hwts(struct hnae3_handle *handle, struct sk_buff *skb,
 			   u32 nsec, u32 sec);
-int hclge_ptp_get_cfg(struct hclge_dev *hdev, struct ifreq *ifr);
-int hclge_ptp_set_cfg(struct hclge_dev *hdev, struct ifreq *ifr);
+int hclge_ptp_get_cfg(struct hnae3_handle *handle,
+		      struct kernel_hwtstamp_config *config);
+int hclge_ptp_set_cfg(struct hnae3_handle *handle,
+		      struct kernel_hwtstamp_config *config,
+		      struct netlink_ext_ack *extack);
 int hclge_ptp_init(struct hclge_dev *hdev);
 void hclge_ptp_uninit(struct hclge_dev *hdev);
 int hclge_ptp_get_ts_info(struct hnae3_handle *handle,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
index 43c1c18fa81f..8c057192aae6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
@@ -510,9 +510,9 @@ out:
 static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data,
 			      struct hnae3_knic_private_info *kinfo)
 {
-#define HCLGE_RING_REG_OFFSET		0x200
 #define HCLGE_RING_INT_REG_OFFSET	0x4
 
+	struct hnae3_queue *tqp;
 	int i, j, reg_num;
 	int data_num_sum;
 	u32 *reg = data;
@@ -533,10 +533,11 @@ static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data,
 	reg_num = ARRAY_SIZE(ring_reg_addr_list);
 	for (j = 0; j < kinfo->num_tqps; j++) {
 		reg += hclge_reg_get_tlv(HCLGE_REG_TAG_RING, reg_num, reg);
+		tqp = kinfo->tqp[j];
 		for (i = 0; i < reg_num; i++)
-			*reg++ = hclge_read_dev(&hdev->hw,
-						ring_reg_addr_list[i] +
-						HCLGE_RING_REG_OFFSET * j);
+			*reg++ = readl_relaxed(tqp->io_base -
+					       HCLGE_TQP_REG_OFFSET +
+					       ring_reg_addr_list[i]);
 	}
 	data_num_sum += (reg_num + HCLGE_REG_TLV_SPACE) * kinfo->num_tqps;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 2f6ffb88e700..8fcf220a120d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -606,7 +606,7 @@ static int hclgevf_set_rss(struct hnae3_handle *handle, const u32 *indir,
 }
 
 static int hclgevf_set_rss_tuple(struct hnae3_handle *handle,
-				 struct ethtool_rxnfc *nfc)
+				 const struct ethtool_rxfh_fields *nfc)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	int ret;
@@ -624,7 +624,7 @@ static int hclgevf_set_rss_tuple(struct hnae3_handle *handle,
 }
 
 static int hclgevf_get_rss_tuple(struct hnae3_handle *handle,
-				 struct ethtool_rxnfc *nfc)
+				 struct ethtool_rxfh_fields *nfc)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	u8 tuple_sets;
@@ -1292,9 +1292,8 @@ static void hclgevf_sync_vlan_filter(struct hclgevf_dev *hdev)
 	rtnl_unlock();
 }
 
-static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+static int hclgevf_en_hw_strip_rxvtag_cmd(struct hclgevf_dev *hdev, bool enable)
 {
-	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	struct hclge_vf_to_pf_msg send_msg;
 
 	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN,
@@ -1303,6 +1302,19 @@ static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
 	return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
 }
 
+static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int ret;
+
+	ret = hclgevf_en_hw_strip_rxvtag_cmd(hdev, enable);
+	if (ret)
+		return ret;
+
+	hdev->rxvtag_strip_en = enable;
+	return 0;
+}
+
 static int hclgevf_reset_tqp(struct hnae3_handle *handle)
 {
 #define HCLGEVF_RESET_ALL_QUEUE_DONE	1U
@@ -1393,6 +1405,17 @@ static int hclgevf_notify_roce_client(struct hclgevf_dev *hdev,
 	return ret;
 }
 
+static void hclgevf_set_reset_pending(struct hclgevf_dev *hdev,
+				      enum hnae3_reset_type reset_type)
+{
+	/* When an incorrect reset type is executed, the get_reset_level
+	 * function generates the HNAE3_NONE_RESET flag. As a result, this
+	 * type do not need to pending.
+	 */
+	if (reset_type != HNAE3_NONE_RESET)
+		set_bit(reset_type, &hdev->reset_pending);
+}
+
 static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
 {
 #define HCLGEVF_RESET_WAIT_US	20000
@@ -1542,7 +1565,7 @@ static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev)
 		hdev->rst_stats.rst_fail_cnt);
 
 	if (hdev->rst_stats.rst_fail_cnt < HCLGEVF_RESET_MAX_FAIL_CNT)
-		set_bit(hdev->reset_type, &hdev->reset_pending);
+		hclgevf_set_reset_pending(hdev, hdev->reset_type);
 
 	if (hclgevf_is_reset_pending(hdev)) {
 		set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
@@ -1662,6 +1685,8 @@ static enum hnae3_reset_type hclgevf_get_reset_level(unsigned long *addr)
 		clear_bit(HNAE3_FLR_RESET, addr);
 	}
 
+	clear_bit(HNAE3_NONE_RESET, addr);
+
 	return rst_level;
 }
 
@@ -1671,14 +1696,15 @@ static void hclgevf_reset_event(struct pci_dev *pdev,
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
 	struct hclgevf_dev *hdev = ae_dev->priv;
 
-	dev_info(&hdev->pdev->dev, "received reset request from VF enet\n");
-
 	if (hdev->default_reset_request)
 		hdev->reset_level =
 			hclgevf_get_reset_level(&hdev->default_reset_request);
 	else
 		hdev->reset_level = HNAE3_VF_FUNC_RESET;
 
+	dev_info(&hdev->pdev->dev, "received reset request from VF enet, reset level is %d\n",
+		 hdev->reset_level);
+
 	/* reset of this VF requested */
 	set_bit(HCLGEVF_RESET_REQUESTED, &hdev->reset_state);
 	hclgevf_reset_task_schedule(hdev);
@@ -1689,8 +1715,20 @@ static void hclgevf_reset_event(struct pci_dev *pdev,
 static void hclgevf_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
 					  enum hnae3_reset_type rst_type)
 {
+#define HCLGEVF_SUPPORT_RESET_TYPE \
+	(BIT(HNAE3_VF_RESET) | BIT(HNAE3_VF_FUNC_RESET) | \
+	BIT(HNAE3_VF_PF_FUNC_RESET) | BIT(HNAE3_VF_FULL_RESET) | \
+	BIT(HNAE3_FLR_RESET) | BIT(HNAE3_VF_EXP_RESET))
+
 	struct hclgevf_dev *hdev = ae_dev->priv;
 
+	if (!(BIT(rst_type) & HCLGEVF_SUPPORT_RESET_TYPE)) {
+		/* To prevent reset triggered by hclge_reset_event */
+		set_bit(HNAE3_NONE_RESET, &hdev->default_reset_request);
+		dev_info(&hdev->pdev->dev, "unsupported reset type %d\n",
+			 rst_type);
+		return;
+	}
 	set_bit(rst_type, &hdev->default_reset_request);
 }
 
@@ -1847,14 +1885,14 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev)
 		 */
 		if (hdev->reset_attempts > HCLGEVF_MAX_RESET_ATTEMPTS_CNT) {
 			/* prepare for full reset of stack + pcie interface */
-			set_bit(HNAE3_VF_FULL_RESET, &hdev->reset_pending);
+			hclgevf_set_reset_pending(hdev, HNAE3_VF_FULL_RESET);
 
 			/* "defer" schedule the reset task again */
 			set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 		} else {
 			hdev->reset_attempts++;
 
-			set_bit(hdev->reset_level, &hdev->reset_pending);
+			hclgevf_set_reset_pending(hdev, hdev->reset_level);
 			set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 		}
 		hclgevf_reset_task_schedule(hdev);
@@ -1977,7 +2015,7 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 		rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
 		dev_info(&hdev->pdev->dev,
 			 "receive reset interrupt 0x%x!\n", rst_ing_reg);
-		set_bit(HNAE3_VF_RESET, &hdev->reset_pending);
+		hclgevf_set_reset_pending(hdev, HNAE3_VF_RESET);
 		set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 		set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state);
 		*clearval = ~(1U << HCLGEVF_VECTOR0_RST_INT_B);
@@ -2019,7 +2057,7 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 
 static void hclgevf_reset_timer(struct timer_list *t)
 {
-	struct hclgevf_dev *hdev = from_timer(hdev, t, reset_timer);
+	struct hclgevf_dev *hdev = timer_container_of(hdev, t, reset_timer);
 
 	hclgevf_clear_event_cause(hdev, HCLGEVF_VECTOR0_EVENT_RST);
 	hclgevf_reset_task_schedule(hdev);
@@ -2178,12 +2216,13 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
 					  tc_valid, tc_size);
 }
 
-static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
+static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev,
+				    bool rxvtag_strip_en)
 {
 	struct hnae3_handle *nic = &hdev->nic;
 	int ret;
 
-	ret = hclgevf_en_hw_strip_rxvtag(nic, true);
+	ret = hclgevf_en_hw_strip_rxvtag(nic, rxvtag_strip_en);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to enable rx vlan offload, ret = %d\n", ret);
@@ -2287,6 +2326,8 @@ static void hclgevf_state_init(struct hclgevf_dev *hdev)
 	clear_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state);
 
 	INIT_DELAYED_WORK(&hdev->service_task, hclgevf_service_task);
+	/* timer needs to be initialized before misc irq */
+	timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0);
 
 	mutex_init(&hdev->mbx_resp.mbx_mutex);
 	sema_init(&hdev->reset_sem, 1);
@@ -2424,7 +2465,7 @@ static int hclgevf_init_nic_client_instance(struct hnae3_ae_dev *ae_dev,
 					    struct hnae3_client *client)
 {
 	struct hclgevf_dev *hdev = ae_dev->priv;
-	int rst_cnt = hdev->rst_stats.rst_cnt;
+	u32 rst_cnt = hdev->rst_stats.rst_cnt;
 	int ret;
 
 	ret = client->ops->init_instance(&hdev->nic);
@@ -2584,7 +2625,7 @@ static int hclgevf_pci_init(struct hclgevf_dev *hdev)
 
 	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (ret) {
-		dev_err(&pdev->dev, "can't set consistent PCI DMA, exiting");
+		dev_err(&pdev->dev, "can't set consistent PCI DMA, exiting\n");
 		goto err_disable_device;
 	}
 
@@ -2851,7 +2892,7 @@ static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 	if (ret)
 		return ret;
 
-	ret = hclgevf_init_vlan_config(hdev);
+	ret = hclgevf_init_vlan_config(hdev, hdev->rxvtag_strip_en);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed(%d) to initialize VLAN config\n", ret);
@@ -2966,7 +3007,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		goto err_config;
 	}
 
-	ret = hclgevf_init_vlan_config(hdev);
+	ret = hclgevf_init_vlan_config(hdev, true);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed(%d) to initialize VLAN config\n", ret);
@@ -2986,7 +3027,6 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		 HCLGEVF_DRIVER_NAME);
 
 	hclgevf_task_schedule(hdev, round_jiffies_relative(HZ));
-	timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0);
 
 	return 0;
 
@@ -3054,11 +3094,7 @@ static void hclgevf_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 
 static u32 hclgevf_get_max_channels(struct hclgevf_dev *hdev)
 {
-	struct hnae3_handle *nic = &hdev->nic;
-	struct hnae3_knic_private_info *kinfo = &nic->kinfo;
-
-	return min_t(u32, hdev->rss_size_max,
-		     hdev->num_tqps / kinfo->tc_info.num_tc);
+	return min(hdev->rss_size_max, hdev->num_tqps);
 }
 
 /**
@@ -3383,8 +3419,10 @@ static int __init hclgevf_init(void)
 
 static void __exit hclgevf_exit(void)
 {
+	hnae3_acquire_unload_lock();
 	hnae3_unregister_ae_algo(&ae_algovf);
 	destroy_workqueue(hclgevf_wq);
+	hnae3_release_unload_lock();
 }
 module_init(hclgevf_init);
 module_exit(hclgevf_exit);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index cccef3228461..0208425ab594 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -253,6 +253,7 @@ struct hclgevf_dev {
 	int *vector_irq;
 
 	bool gro_en;
+	bool rxvtag_strip_en;
 
 	unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)];
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index 85c2a634c8f9..f5c99ca54369 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -159,7 +159,7 @@ static bool hclgevf_cmd_crq_empty(struct hclgevf_hw *hw)
 {
 	u32 tail = hclgevf_read_dev(hw, HCLGE_COMM_NIC_CRQ_TAIL_REG);
 
-	return tail == hw->hw.cmq.crq.next_to_use;
+	return tail == (u32)hw->hw.cmq.crq.next_to_use;
 }
 
 static void hclgevf_handle_mbx_response(struct hclgevf_dev *hdev,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
index 6db415d8b917..9de01e344e27 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
@@ -123,40 +123,42 @@ int hclgevf_get_regs_len(struct hnae3_handle *handle)
 void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
 		      void *data)
 {
-#define HCLGEVF_RING_REG_OFFSET		0x200
 #define HCLGEVF_RING_INT_REG_OFFSET	0x4
 
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-	int i, j, reg_um;
+	struct hnae3_queue *tqp;
+	int i, j, reg_num;
 	u32 *reg = data;
 
 	*version = hdev->fw_version;
 	reg += hclgevf_reg_get_header(reg);
 
 	/* fetching per-VF registers values from VF PCIe register space */
-	reg_um = ARRAY_SIZE(cmdq_reg_addr_list);
-	reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_CMDQ, reg_um, reg);
-	for (i = 0; i < reg_um; i++)
+	reg_num = ARRAY_SIZE(cmdq_reg_addr_list);
+	reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_CMDQ, reg_num, reg);
+	for (i = 0; i < reg_num; i++)
 		*reg++ = hclgevf_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
 
-	reg_um = ARRAY_SIZE(common_reg_addr_list);
-	reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_COMMON, reg_um, reg);
-	for (i = 0; i < reg_um; i++)
+	reg_num = ARRAY_SIZE(common_reg_addr_list);
+	reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_COMMON, reg_num, reg);
+	for (i = 0; i < reg_num; i++)
 		*reg++ = hclgevf_read_dev(&hdev->hw, common_reg_addr_list[i]);
 
-	reg_um = ARRAY_SIZE(ring_reg_addr_list);
+	reg_num = ARRAY_SIZE(ring_reg_addr_list);
 	for (j = 0; j < hdev->num_tqps; j++) {
-		reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_RING, reg_um, reg);
-		for (i = 0; i < reg_um; i++)
-			*reg++ = hclgevf_read_dev(&hdev->hw,
-						  ring_reg_addr_list[i] +
-						  HCLGEVF_RING_REG_OFFSET * j);
+		reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_RING, reg_num, reg);
+		tqp = &hdev->htqp[j].q;
+		for (i = 0; i < reg_num; i++)
+			*reg++ = readl_relaxed(tqp->io_base -
+					       HCLGEVF_TQP_REG_OFFSET +
+					       ring_reg_addr_list[i]);
 	}
 
-	reg_um = ARRAY_SIZE(tqp_intr_reg_addr_list);
+	reg_num = ARRAY_SIZE(tqp_intr_reg_addr_list);
 	for (j = 0; j < hdev->num_msi_used - 1; j++) {
-		reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_TQP_INTR, reg_um, reg);
-		for (i = 0; i < reg_um; i++)
+		reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_TQP_INTR,
+					   reg_num, reg);
+		for (i = 0; i < reg_num; i++)
 			*reg++ = hclgevf_read_dev(&hdev->hw,
 						  tqp_intr_reg_addr_list[i] +
 						  HCLGEVF_RING_INT_REG_OFFSET * j);
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index a1aa6c1f966e..6812be8dc64f 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -640,7 +640,7 @@ static struct platform_driver hns_mdio_driver = {
 	.driver = {
 		   .name = MDIO_DRV_NAME,
 		   .of_match_table = hns_mdio_match,
-		   .acpi_match_table = ACPI_PTR(hns_mdio_acpi_match),
+		   .acpi_match_table = hns_mdio_acpi_match,
 		   },
 };
 
diff --git a/drivers/net/ethernet/huawei/Kconfig b/drivers/net/ethernet/huawei/Kconfig
index c05fce15eb51..7d0feb1da158 100644
--- a/drivers/net/ethernet/huawei/Kconfig
+++ b/drivers/net/ethernet/huawei/Kconfig
@@ -16,5 +16,6 @@ config NET_VENDOR_HUAWEI
 if NET_VENDOR_HUAWEI
 
 source "drivers/net/ethernet/huawei/hinic/Kconfig"
+source "drivers/net/ethernet/huawei/hinic3/Kconfig"
 
 endif # NET_VENDOR_HUAWEI
diff --git a/drivers/net/ethernet/huawei/Makefile b/drivers/net/ethernet/huawei/Makefile
index 2549ad5afe6d..59865b882879 100644
--- a/drivers/net/ethernet/huawei/Makefile
+++ b/drivers/net/ethernet/huawei/Makefile
@@ -4,3 +4,4 @@
 #
 
 obj-$(CONFIG_HINIC) += hinic/
+obj-$(CONFIG_HINIC3) += hinic3/
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
index 03e42512a2d5..300bc267a259 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
@@ -443,8 +443,9 @@ int hinic_health_reporters_create(struct hinic_devlink_priv *priv)
 	struct devlink *devlink = priv_to_devlink(priv);
 
 	priv->hw_fault_reporter =
-		devlink_health_reporter_create(devlink, &hinic_hw_fault_reporter_ops,
-					       0, priv);
+		devlink_health_reporter_create(devlink,
+					       &hinic_hw_fault_reporter_ops,
+					       priv);
 	if (IS_ERR(priv->hw_fault_reporter)) {
 		dev_warn(&priv->hwdev->hwif->pdev->dev, "Failed to create hw fault reporter, err: %ld\n",
 			 PTR_ERR(priv->hw_fault_reporter));
@@ -452,8 +453,9 @@ int hinic_health_reporters_create(struct hinic_devlink_priv *priv)
 	}
 
 	priv->fw_fault_reporter =
-		devlink_health_reporter_create(devlink, &hinic_fw_fault_reporter_ops,
-					       0, priv);
+		devlink_health_reporter_create(devlink,
+					       &hinic_fw_fault_reporter_ops,
+					       priv);
 	if (IS_ERR(priv->fw_fault_reporter)) {
 		dev_warn(&priv->hwdev->hwif->pdev->dev, "Failed to create fw fault reporter, err: %ld\n",
 			 PTR_ERR(priv->fw_fault_reporter));
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
index c559dd4291d3..e9f338e9dbe7 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
@@ -919,9 +919,10 @@ static int hinic_set_channels(struct net_device *netdev,
 	return 0;
 }
 
-static int hinic_get_rss_hash_opts(struct hinic_dev *nic_dev,
-				   struct ethtool_rxnfc *cmd)
+static int hinic_get_rxfh_fields(struct net_device *netdev,
+				 struct ethtool_rxfh_fields *cmd)
 {
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	struct hinic_rss_type rss_type = { 0 };
 	int err;
 
@@ -964,7 +965,7 @@ static int hinic_get_rss_hash_opts(struct hinic_dev *nic_dev,
 	return 0;
 }
 
-static int set_l4_rss_hash_ops(struct ethtool_rxnfc *cmd,
+static int set_l4_rss_hash_ops(const struct ethtool_rxfh_fields *cmd,
 			       struct hinic_rss_type *rss_type)
 {
 	u8 rss_l4_en = 0;
@@ -1000,16 +1001,18 @@ static int set_l4_rss_hash_ops(struct ethtool_rxnfc *cmd,
 	return 0;
 }
 
-static int hinic_set_rss_hash_opts(struct hinic_dev *nic_dev,
-				   struct ethtool_rxnfc *cmd)
+static int hinic_set_rxfh_fields(struct net_device *dev,
+				 const struct ethtool_rxfh_fields *cmd,
+				 struct netlink_ext_ack *extack)
 {
-	struct hinic_rss_type *rss_type = &nic_dev->rss_type;
+	struct hinic_dev *nic_dev = netdev_priv(dev);
+	struct hinic_rss_type *rss_type;
 	int err;
 
-	if (!(nic_dev->flags & HINIC_RSS_ENABLE)) {
-		cmd->data = 0;
+	rss_type = &nic_dev->rss_type;
+
+	if (!(nic_dev->flags & HINIC_RSS_ENABLE))
 		return -EOPNOTSUPP;
-	}
 
 	/* RSS does not support anything other than hashing
 	 * to queues on src and dst IPs and ports
@@ -1108,26 +1111,6 @@ static int hinic_get_rxnfc(struct net_device *netdev,
 	case ETHTOOL_GRXRINGS:
 		cmd->data = nic_dev->num_qps;
 		break;
-	case ETHTOOL_GRXFH:
-		err = hinic_get_rss_hash_opts(nic_dev, cmd);
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		break;
-	}
-
-	return err;
-}
-
-static int hinic_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
-{
-	struct hinic_dev *nic_dev = netdev_priv(netdev);
-	int err = 0;
-
-	switch (cmd->cmd) {
-	case ETHTOOL_SRXFH:
-		err = hinic_set_rss_hash_opts(nic_dev, cmd);
-		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;
@@ -1797,11 +1780,12 @@ static const struct ethtool_ops hinic_ethtool_ops = {
 	.get_channels = hinic_get_channels,
 	.set_channels = hinic_set_channels,
 	.get_rxnfc = hinic_get_rxnfc,
-	.set_rxnfc = hinic_set_rxnfc,
 	.get_rxfh_key_size = hinic_get_rxfh_key_size,
 	.get_rxfh_indir_size = hinic_get_rxfh_indir_size,
 	.get_rxfh = hinic_get_rxfh,
 	.set_rxfh = hinic_set_rxfh,
+	.get_rxfh_fields = hinic_get_rxfh_fields,
+	.set_rxfh_fields = hinic_set_rxfh_fields,
 	.get_sset_count = hinic_get_sset_count,
 	.get_ethtool_stats = hinic_get_ethtool_stats,
 	.get_strings = hinic_get_strings,
@@ -1829,11 +1813,12 @@ static const struct ethtool_ops hinicvf_ethtool_ops = {
 	.get_channels = hinic_get_channels,
 	.set_channels = hinic_set_channels,
 	.get_rxnfc = hinic_get_rxnfc,
-	.set_rxnfc = hinic_set_rxnfc,
 	.get_rxfh_key_size = hinic_get_rxfh_key_size,
 	.get_rxfh_indir_size = hinic_get_rxfh_indir_size,
 	.get_rxfh = hinic_get_rxfh,
 	.set_rxfh = hinic_set_rxfh,
+	.get_rxfh_fields = hinic_get_rxfh_fields,
+	.set_rxfh_fields = hinic_set_rxfh_fields,
 	.get_sset_count = hinic_get_sset_count,
 	.get_ethtool_stats = hinic_get_ethtool_stats,
 	.get_strings = hinic_get_strings,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
index 045c47786a04..28114a59347e 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
@@ -605,7 +605,7 @@ static void aeq_elements_init(struct hinic_eq *eq, u32 init_val)
 /**
  * ceq_elements_init - Initialize all the elements in the ceq
  * @eq: the event queue
- * @init_val: value to init with it the elements
+ * @init_val: value to init the elements with
  **/
 static void ceq_elements_init(struct hinic_eq *eq, u32 init_val)
 {
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
index 3f9c31d29215..97c1584dc05b 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
@@ -861,7 +861,7 @@ static int send_mbox_to_func(struct hinic_mbox_func_to_func *func_to_func,
 		 HINIC_MBOX_HEADER_SET(NOT_LAST_SEG, LAST) |
 		 HINIC_MBOX_HEADER_SET(direction, DIRECTION) |
 		 HINIC_MBOX_HEADER_SET(cmd, CMD) |
-		 /* The vf's offset to it's associated pf */
+		 /* The vf's offset to its associated pf */
 		 HINIC_MBOX_HEADER_SET(msg_info->msg_id, MSG_ID) |
 		 HINIC_MBOX_HEADER_SET(msg_info->status, STATUS) |
 		 HINIC_MBOX_HEADER_SET(hinic_global_func_id_hw(hwdev->hwif),
diff --git a/drivers/net/ethernet/huawei/hinic3/Kconfig b/drivers/net/ethernet/huawei/hinic3/Kconfig
new file mode 100644
index 000000000000..ce4331d1387b
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/Kconfig
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Huawei driver configuration
+#
+
+config HINIC3
+	tristate "Huawei 3rd generation network adapters (HINIC3) support"
+	# Fields of HW and management structures are little endian and are
+	# currently not converted
+	depends on !CPU_BIG_ENDIAN
+	depends on X86 || ARM64 || COMPILE_TEST
+	depends on PCI_MSI && 64BIT
+	select AUXILIARY_BUS
+	select PAGE_POOL
+	help
+	  This driver supports HiNIC 3rd gen Network Adapter (HINIC3).
+	  The driver is supported on X86_64 and ARM64 little endian.
+
+	  To compile this driver as a module, choose M here.
+	  The module will be called hinic3.
diff --git a/drivers/net/ethernet/huawei/hinic3/Makefile b/drivers/net/ethernet/huawei/hinic3/Makefile
new file mode 100644
index 000000000000..c3efa45a6a42
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/Makefile
@@ -0,0 +1,25 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+obj-$(CONFIG_HINIC3) += hinic3.o
+
+hinic3-objs := hinic3_cmdq.o \
+	       hinic3_common.o \
+	       hinic3_eqs.o \
+	       hinic3_hw_cfg.o \
+	       hinic3_hw_comm.o \
+	       hinic3_hwdev.o \
+	       hinic3_hwif.o \
+	       hinic3_irq.o \
+	       hinic3_lld.o \
+	       hinic3_main.o \
+	       hinic3_mbox.o \
+	       hinic3_mgmt.o \
+	       hinic3_netdev_ops.o \
+	       hinic3_nic_cfg.o \
+	       hinic3_nic_io.o \
+	       hinic3_queue_common.o \
+	       hinic3_rss.o \
+	       hinic3_rx.o \
+	       hinic3_tx.o \
+	       hinic3_wq.o
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_cmdq.c b/drivers/net/ethernet/huawei/hinic3/hinic3_cmdq.c
new file mode 100644
index 000000000000..ef539d1b69a3
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_cmdq.c
@@ -0,0 +1,915 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+
+#include "hinic3_cmdq.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+#define CMDQ_BUF_SIZE             2048
+#define CMDQ_WQEBB_SIZE           64
+
+#define CMDQ_CMD_TIMEOUT          5000
+#define CMDQ_ENABLE_WAIT_TIMEOUT  300
+
+#define CMDQ_CTXT_CURR_WQE_PAGE_PFN_MASK  GENMASK_ULL(51, 0)
+#define CMDQ_CTXT_EQ_ID_MASK              GENMASK_ULL(60, 53)
+#define CMDQ_CTXT_CEQ_ARM_MASK            BIT_ULL(61)
+#define CMDQ_CTXT_CEQ_EN_MASK             BIT_ULL(62)
+#define CMDQ_CTXT_HW_BUSY_BIT_MASK        BIT_ULL(63)
+
+#define CMDQ_CTXT_WQ_BLOCK_PFN_MASK       GENMASK_ULL(51, 0)
+#define CMDQ_CTXT_CI_MASK                 GENMASK_ULL(63, 52)
+#define CMDQ_CTXT_SET(val, member)  \
+	FIELD_PREP(CMDQ_CTXT_##member##_MASK, val)
+
+#define CMDQ_WQE_HDR_BUFDESC_LEN_MASK        GENMASK(7, 0)
+#define CMDQ_WQE_HDR_COMPLETE_FMT_MASK       BIT(15)
+#define CMDQ_WQE_HDR_DATA_FMT_MASK           BIT(22)
+#define CMDQ_WQE_HDR_COMPLETE_REQ_MASK       BIT(23)
+#define CMDQ_WQE_HDR_COMPLETE_SECT_LEN_MASK  GENMASK(28, 27)
+#define CMDQ_WQE_HDR_CTRL_LEN_MASK           GENMASK(30, 29)
+#define CMDQ_WQE_HDR_HW_BUSY_BIT_MASK        BIT(31)
+#define CMDQ_WQE_HDR_SET(val, member)  \
+	FIELD_PREP(CMDQ_WQE_HDR_##member##_MASK, val)
+#define CMDQ_WQE_HDR_GET(val, member)  \
+	FIELD_GET(CMDQ_WQE_HDR_##member##_MASK, le32_to_cpu(val))
+
+#define CMDQ_CTRL_PI_MASK              GENMASK(15, 0)
+#define CMDQ_CTRL_CMD_MASK             GENMASK(23, 16)
+#define CMDQ_CTRL_MOD_MASK             GENMASK(28, 24)
+#define CMDQ_CTRL_HW_BUSY_BIT_MASK     BIT(31)
+#define CMDQ_CTRL_SET(val, member)  \
+	FIELD_PREP(CMDQ_CTRL_##member##_MASK, val)
+#define CMDQ_CTRL_GET(val, member)  \
+	FIELD_GET(CMDQ_CTRL_##member##_MASK, val)
+
+#define CMDQ_WQE_ERRCODE_VAL_MASK      GENMASK(30, 0)
+#define CMDQ_WQE_ERRCODE_GET(val, member)  \
+	FIELD_GET(CMDQ_WQE_ERRCODE_##member##_MASK, le32_to_cpu(val))
+
+#define CMDQ_DB_INFO_HI_PROD_IDX_MASK  GENMASK(7, 0)
+#define CMDQ_DB_INFO_SET(val, member)  \
+	FIELD_PREP(CMDQ_DB_INFO_##member##_MASK, val)
+
+#define CMDQ_DB_HEAD_QUEUE_TYPE_MASK   BIT(23)
+#define CMDQ_DB_HEAD_CMDQ_TYPE_MASK    GENMASK(26, 24)
+#define CMDQ_DB_HEAD_SET(val, member)  \
+	FIELD_PREP(CMDQ_DB_HEAD_##member##_MASK, val)
+
+#define CMDQ_CEQE_TYPE_MASK            GENMASK(2, 0)
+#define CMDQ_CEQE_GET(val, member)  \
+	FIELD_GET(CMDQ_CEQE_##member##_MASK, le32_to_cpu(val))
+
+#define CMDQ_WQE_HEADER(wqe)           ((struct cmdq_header *)(wqe))
+#define CMDQ_WQE_COMPLETED(ctrl_info)  \
+	CMDQ_CTRL_GET(le32_to_cpu(ctrl_info), HW_BUSY_BIT)
+
+#define CMDQ_PFN(addr)  ((addr) >> 12)
+
+/* cmdq work queue's chip logical address table is up to 512B */
+#define CMDQ_WQ_CLA_SIZE  512
+
+/* Completion codes: send, direct sync, force stop */
+#define CMDQ_SEND_CMPT_CODE         10
+#define CMDQ_DIRECT_SYNC_CMPT_CODE  11
+#define CMDQ_FORCE_STOP_CMPT_CODE   12
+
+enum cmdq_data_format {
+	CMDQ_DATA_SGE    = 0,
+	CMDQ_DATA_DIRECT = 1,
+};
+
+enum cmdq_ctrl_sect_len {
+	CMDQ_CTRL_SECT_LEN        = 1,
+	CMDQ_CTRL_DIRECT_SECT_LEN = 2,
+};
+
+enum cmdq_bufdesc_len {
+	CMDQ_BUFDESC_LCMD_LEN = 2,
+	CMDQ_BUFDESC_SCMD_LEN = 3,
+};
+
+enum cmdq_completion_format {
+	CMDQ_COMPLETE_DIRECT = 0,
+	CMDQ_COMPLETE_SGE    = 1,
+};
+
+enum cmdq_cmd_type {
+	CMDQ_CMD_DIRECT_RESP,
+	CMDQ_CMD_SGE_RESP,
+};
+
+#define CMDQ_WQE_NUM_WQEBBS  1
+
+static struct cmdq_wqe *cmdq_read_wqe(struct hinic3_wq *wq, u16 *ci)
+{
+	if (hinic3_wq_get_used(wq) == 0)
+		return NULL;
+
+	*ci = wq->cons_idx & wq->idx_mask;
+
+	return get_q_element(&wq->qpages, wq->cons_idx, NULL);
+}
+
+struct hinic3_cmd_buf *hinic3_alloc_cmd_buf(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_cmd_buf *cmd_buf;
+	struct hinic3_cmdqs *cmdqs;
+
+	cmdqs = hwdev->cmdqs;
+
+	cmd_buf = kmalloc(sizeof(*cmd_buf), GFP_ATOMIC);
+	if (!cmd_buf)
+		return NULL;
+
+	cmd_buf->buf = dma_pool_alloc(cmdqs->cmd_buf_pool, GFP_ATOMIC,
+				      &cmd_buf->dma_addr);
+	if (!cmd_buf->buf) {
+		dev_err(hwdev->dev, "Failed to allocate cmdq cmd buf from the pool\n");
+		goto err_free_cmd_buf;
+	}
+
+	cmd_buf->size = cpu_to_le16(CMDQ_BUF_SIZE);
+	refcount_set(&cmd_buf->ref_cnt, 1);
+
+	return cmd_buf;
+
+err_free_cmd_buf:
+	kfree(cmd_buf);
+
+	return NULL;
+}
+
+void hinic3_free_cmd_buf(struct hinic3_hwdev *hwdev,
+			 struct hinic3_cmd_buf *cmd_buf)
+{
+	struct hinic3_cmdqs *cmdqs;
+
+	if (!refcount_dec_and_test(&cmd_buf->ref_cnt))
+		return;
+
+	cmdqs = hwdev->cmdqs;
+
+	dma_pool_free(cmdqs->cmd_buf_pool, cmd_buf->buf, cmd_buf->dma_addr);
+	kfree(cmd_buf);
+}
+
+static void cmdq_clear_cmd_buf(struct hinic3_cmdq_cmd_info *cmd_info,
+			       struct hinic3_hwdev *hwdev)
+{
+	if (cmd_info->buf_in) {
+		hinic3_free_cmd_buf(hwdev, cmd_info->buf_in);
+		cmd_info->buf_in = NULL;
+	}
+}
+
+static void clear_wqe_complete_bit(struct hinic3_cmdq *cmdq,
+				   struct cmdq_wqe *wqe, u16 ci)
+{
+	struct cmdq_header *hdr = CMDQ_WQE_HEADER(wqe);
+	__le32 header_info = hdr->header_info;
+	enum cmdq_data_format df;
+	struct cmdq_ctrl *ctrl;
+
+	df = CMDQ_WQE_HDR_GET(header_info, DATA_FMT);
+	if (df == CMDQ_DATA_SGE)
+		ctrl = &wqe->wqe_lcmd.ctrl;
+	else
+		ctrl = &wqe->wqe_scmd.ctrl;
+
+	/* clear HW busy bit */
+	ctrl->ctrl_info = 0;
+	cmdq->cmd_infos[ci].cmd_type = HINIC3_CMD_TYPE_NONE;
+	wmb(); /* verify wqe is clear before updating ci */
+	hinic3_wq_put_wqebbs(&cmdq->wq, CMDQ_WQE_NUM_WQEBBS);
+}
+
+static void cmdq_update_cmd_status(struct hinic3_cmdq *cmdq, u16 prod_idx,
+				   struct cmdq_wqe *wqe)
+{
+	struct hinic3_cmdq_cmd_info *cmd_info;
+	struct cmdq_wqe_lcmd *wqe_lcmd;
+	__le32 status_info;
+
+	wqe_lcmd = &wqe->wqe_lcmd;
+	cmd_info = &cmdq->cmd_infos[prod_idx];
+	if (cmd_info->errcode) {
+		status_info = wqe_lcmd->status.status_info;
+		*cmd_info->errcode = CMDQ_WQE_ERRCODE_GET(status_info, VAL);
+	}
+
+	if (cmd_info->direct_resp)
+		*cmd_info->direct_resp = wqe_lcmd->completion.resp.direct.val;
+}
+
+static void cmdq_sync_cmd_handler(struct hinic3_cmdq *cmdq,
+				  struct cmdq_wqe *wqe, u16 ci)
+{
+	spin_lock(&cmdq->cmdq_lock);
+	cmdq_update_cmd_status(cmdq, ci, wqe);
+	if (cmdq->cmd_infos[ci].cmpt_code) {
+		*cmdq->cmd_infos[ci].cmpt_code = CMDQ_DIRECT_SYNC_CMPT_CODE;
+		cmdq->cmd_infos[ci].cmpt_code = NULL;
+	}
+
+	/* Ensure that completion code has been updated before updating done */
+	smp_wmb();
+	if (cmdq->cmd_infos[ci].done) {
+		complete(cmdq->cmd_infos[ci].done);
+		cmdq->cmd_infos[ci].done = NULL;
+	}
+	spin_unlock(&cmdq->cmdq_lock);
+
+	cmdq_clear_cmd_buf(&cmdq->cmd_infos[ci], cmdq->hwdev);
+	clear_wqe_complete_bit(cmdq, wqe, ci);
+}
+
+void hinic3_cmdq_ceq_handler(struct hinic3_hwdev *hwdev, __le32 ceqe_data)
+{
+	enum hinic3_cmdq_type cmdq_type = CMDQ_CEQE_GET(ceqe_data, TYPE);
+	struct hinic3_cmdqs *cmdqs = hwdev->cmdqs;
+	struct hinic3_cmdq_cmd_info *cmd_info;
+	struct cmdq_wqe_lcmd *wqe_lcmd;
+	struct hinic3_cmdq *cmdq;
+	struct cmdq_wqe *wqe;
+	__le32 ctrl_info;
+	u16 ci;
+
+	if (unlikely(cmdq_type >= ARRAY_SIZE(cmdqs->cmdq)))
+		return;
+
+	cmdq = &cmdqs->cmdq[cmdq_type];
+	while ((wqe = cmdq_read_wqe(&cmdq->wq, &ci)) != NULL) {
+		cmd_info = &cmdq->cmd_infos[ci];
+		switch (cmd_info->cmd_type) {
+		case HINIC3_CMD_TYPE_NONE:
+			return;
+		case HINIC3_CMD_TYPE_TIMEOUT:
+			dev_warn(hwdev->dev, "Cmdq timeout, q_id: %u, ci: %u\n",
+				 cmdq_type, ci);
+			fallthrough;
+		case HINIC3_CMD_TYPE_FAKE_TIMEOUT:
+			cmdq_clear_cmd_buf(cmd_info, hwdev);
+			clear_wqe_complete_bit(cmdq, wqe, ci);
+			break;
+		default:
+			/* only arm bit is using scmd wqe,
+			 * the other wqe is lcmd
+			 */
+			wqe_lcmd = &wqe->wqe_lcmd;
+			ctrl_info = wqe_lcmd->ctrl.ctrl_info;
+			if (!CMDQ_WQE_COMPLETED(ctrl_info))
+				return;
+
+			dma_rmb();
+			/* For FORCE_STOP cmd_type, we also need to wait for
+			 * the firmware processing to complete to prevent the
+			 * firmware from accessing the released cmd_buf
+			 */
+			if (cmd_info->cmd_type == HINIC3_CMD_TYPE_FORCE_STOP) {
+				cmdq_clear_cmd_buf(cmd_info, hwdev);
+				clear_wqe_complete_bit(cmdq, wqe, ci);
+			} else {
+				cmdq_sync_cmd_handler(cmdq, wqe, ci);
+			}
+
+			break;
+		}
+	}
+}
+
+static int wait_cmdqs_enable(struct hinic3_cmdqs *cmdqs)
+{
+	unsigned long end;
+
+	end = jiffies + msecs_to_jiffies(CMDQ_ENABLE_WAIT_TIMEOUT);
+	do {
+		if (cmdqs->status & HINIC3_CMDQ_ENABLE)
+			return 0;
+		usleep_range(1000, 2000);
+	} while (time_before(jiffies, end) && !cmdqs->disable_flag);
+
+	cmdqs->disable_flag = 1;
+
+	return -EBUSY;
+}
+
+static void cmdq_set_completion(struct cmdq_completion *complete,
+				struct hinic3_cmd_buf *buf_out)
+{
+	struct hinic3_sge *sge = &complete->resp.sge;
+
+	hinic3_set_sge(sge, buf_out->dma_addr, cpu_to_le32(CMDQ_BUF_SIZE));
+}
+
+static struct cmdq_wqe *cmdq_get_wqe(struct hinic3_wq *wq, u16 *pi)
+{
+	if (!hinic3_wq_free_wqebbs(wq))
+		return NULL;
+
+	return hinic3_wq_get_one_wqebb(wq, pi);
+}
+
+static void cmdq_set_lcmd_bufdesc(struct cmdq_wqe_lcmd *wqe,
+				  struct hinic3_cmd_buf *buf_in)
+{
+	hinic3_set_sge(&wqe->buf_desc.sge, buf_in->dma_addr,
+		       (__force __le32)buf_in->size);
+}
+
+static void cmdq_set_db(struct hinic3_cmdq *cmdq,
+			enum hinic3_cmdq_type cmdq_type, u16 prod_idx)
+{
+	u8 __iomem *db_base = cmdq->hwdev->cmdqs->cmdqs_db_base;
+	u16 db_ofs = (prod_idx & 0xFF) << 3;
+	struct cmdq_db db;
+
+	db.db_info = cpu_to_le32(CMDQ_DB_INFO_SET(prod_idx >> 8, HI_PROD_IDX));
+	db.db_head = cpu_to_le32(CMDQ_DB_HEAD_SET(1, QUEUE_TYPE) |
+				 CMDQ_DB_HEAD_SET(cmdq_type, CMDQ_TYPE));
+	writeq(*(u64 *)&db, db_base + db_ofs);
+}
+
+static void cmdq_wqe_fill(struct cmdq_wqe *hw_wqe,
+			  const struct cmdq_wqe *shadow_wqe)
+{
+	const struct cmdq_header *src = (struct cmdq_header *)shadow_wqe;
+	struct cmdq_header *dst = (struct cmdq_header *)hw_wqe;
+	size_t len;
+
+	len = sizeof(struct cmdq_wqe) - sizeof(struct cmdq_header);
+	memcpy(dst + 1, src + 1, len);
+	/* Ensure buffer len before updating header */
+	wmb();
+	WRITE_ONCE(*dst, *src);
+}
+
+static void cmdq_prepare_wqe_ctrl(struct cmdq_wqe *wqe, u8 wrapped,
+				  u8 mod, u8 cmd, u16 prod_idx,
+				  enum cmdq_completion_format complete_format,
+				  enum cmdq_data_format data_format,
+				  enum cmdq_bufdesc_len buf_len)
+{
+	struct cmdq_header *hdr = CMDQ_WQE_HEADER(wqe);
+	enum cmdq_ctrl_sect_len ctrl_len;
+	struct cmdq_wqe_lcmd *wqe_lcmd;
+	struct cmdq_wqe_scmd *wqe_scmd;
+	struct cmdq_ctrl *ctrl;
+
+	if (data_format == CMDQ_DATA_SGE) {
+		wqe_lcmd = &wqe->wqe_lcmd;
+		wqe_lcmd->status.status_info = 0;
+		ctrl = &wqe_lcmd->ctrl;
+		ctrl_len = CMDQ_CTRL_SECT_LEN;
+	} else {
+		wqe_scmd = &wqe->wqe_scmd;
+		wqe_scmd->status.status_info = 0;
+		ctrl = &wqe_scmd->ctrl;
+		ctrl_len = CMDQ_CTRL_DIRECT_SECT_LEN;
+	}
+
+	ctrl->ctrl_info =
+		cpu_to_le32(CMDQ_CTRL_SET(prod_idx, PI) |
+			    CMDQ_CTRL_SET(cmd, CMD) |
+			    CMDQ_CTRL_SET(mod, MOD));
+
+	hdr->header_info =
+		cpu_to_le32(CMDQ_WQE_HDR_SET(buf_len, BUFDESC_LEN) |
+			    CMDQ_WQE_HDR_SET(complete_format, COMPLETE_FMT) |
+			    CMDQ_WQE_HDR_SET(data_format, DATA_FMT) |
+			    CMDQ_WQE_HDR_SET(1, COMPLETE_REQ) |
+			    CMDQ_WQE_HDR_SET(3, COMPLETE_SECT_LEN) |
+			    CMDQ_WQE_HDR_SET(ctrl_len, CTRL_LEN) |
+			    CMDQ_WQE_HDR_SET(wrapped, HW_BUSY_BIT));
+}
+
+static void cmdq_set_lcmd_wqe(struct cmdq_wqe *wqe,
+			      enum cmdq_cmd_type cmd_type,
+			      struct hinic3_cmd_buf *buf_in,
+			      struct hinic3_cmd_buf *buf_out,
+			      u8 wrapped, u8 mod, u8 cmd, u16 prod_idx)
+{
+	enum cmdq_completion_format complete_format = CMDQ_COMPLETE_DIRECT;
+	struct cmdq_wqe_lcmd *wqe_lcmd = &wqe->wqe_lcmd;
+
+	switch (cmd_type) {
+	case CMDQ_CMD_DIRECT_RESP:
+		wqe_lcmd->completion.resp.direct.val = 0;
+		break;
+	case CMDQ_CMD_SGE_RESP:
+		if (buf_out) {
+			complete_format = CMDQ_COMPLETE_SGE;
+			cmdq_set_completion(&wqe_lcmd->completion, buf_out);
+		}
+		break;
+	}
+
+	cmdq_prepare_wqe_ctrl(wqe, wrapped, mod, cmd, prod_idx, complete_format,
+			      CMDQ_DATA_SGE, CMDQ_BUFDESC_LCMD_LEN);
+	cmdq_set_lcmd_bufdesc(wqe_lcmd, buf_in);
+}
+
+static int hinic3_cmdq_sync_timeout_check(struct hinic3_cmdq *cmdq,
+					  struct cmdq_wqe *wqe, u16 pi)
+{
+	struct cmdq_wqe_lcmd *wqe_lcmd;
+	struct cmdq_ctrl *ctrl;
+	__le32 ctrl_info;
+
+	wqe_lcmd = &wqe->wqe_lcmd;
+	ctrl = &wqe_lcmd->ctrl;
+	ctrl_info = ctrl->ctrl_info;
+	if (!CMDQ_WQE_COMPLETED(ctrl_info)) {
+		dev_dbg(cmdq->hwdev->dev, "Cmdq sync command check busy bit not set\n");
+		return -EFAULT;
+	}
+	cmdq_update_cmd_status(cmdq, pi, wqe);
+
+	return 0;
+}
+
+static void clear_cmd_info(struct hinic3_cmdq_cmd_info *cmd_info,
+			   const struct hinic3_cmdq_cmd_info *saved_cmd_info)
+{
+	if (cmd_info->errcode == saved_cmd_info->errcode)
+		cmd_info->errcode = NULL;
+
+	if (cmd_info->done == saved_cmd_info->done)
+		cmd_info->done = NULL;
+
+	if (cmd_info->direct_resp == saved_cmd_info->direct_resp)
+		cmd_info->direct_resp = NULL;
+}
+
+static int wait_cmdq_sync_cmd_completion(struct hinic3_cmdq *cmdq,
+					 struct hinic3_cmdq_cmd_info *cmd_info,
+					 struct hinic3_cmdq_cmd_info *saved_cmd_info,
+					 u64 curr_msg_id, u16 curr_prod_idx,
+					 struct cmdq_wqe *curr_wqe,
+					 u32 timeout)
+{
+	ulong timeo = msecs_to_jiffies(timeout);
+	int err;
+
+	if (wait_for_completion_timeout(saved_cmd_info->done, timeo))
+		return 0;
+
+	spin_lock_bh(&cmdq->cmdq_lock);
+	if (cmd_info->cmpt_code == saved_cmd_info->cmpt_code)
+		cmd_info->cmpt_code = NULL;
+
+	if (*saved_cmd_info->cmpt_code == CMDQ_DIRECT_SYNC_CMPT_CODE) {
+		dev_dbg(cmdq->hwdev->dev, "Cmdq direct sync command has been completed\n");
+		spin_unlock_bh(&cmdq->cmdq_lock);
+		return 0;
+	}
+
+	if (curr_msg_id == cmd_info->cmdq_msg_id) {
+		err = hinic3_cmdq_sync_timeout_check(cmdq, curr_wqe,
+						     curr_prod_idx);
+		if (err)
+			cmd_info->cmd_type = HINIC3_CMD_TYPE_TIMEOUT;
+		else
+			cmd_info->cmd_type = HINIC3_CMD_TYPE_FAKE_TIMEOUT;
+	} else {
+		err = -ETIMEDOUT;
+		dev_err(cmdq->hwdev->dev,
+			"Cmdq sync command current msg id mismatch cmd_info msg id\n");
+	}
+
+	clear_cmd_info(cmd_info, saved_cmd_info);
+	spin_unlock_bh(&cmdq->cmdq_lock);
+
+	return err;
+}
+
+static int cmdq_sync_cmd_direct_resp(struct hinic3_cmdq *cmdq, u8 mod, u8 cmd,
+				     struct hinic3_cmd_buf *buf_in,
+				     __le64 *out_param)
+{
+	struct hinic3_cmdq_cmd_info *cmd_info, saved_cmd_info;
+	int cmpt_code = CMDQ_SEND_CMPT_CODE;
+	struct cmdq_wqe *curr_wqe, wqe = {};
+	struct hinic3_wq *wq = &cmdq->wq;
+	u16 curr_prod_idx, next_prod_idx;
+	struct completion done;
+	u64 curr_msg_id;
+	int errcode;
+	u8 wrapped;
+	int err;
+
+	spin_lock_bh(&cmdq->cmdq_lock);
+	curr_wqe = cmdq_get_wqe(wq, &curr_prod_idx);
+	if (!curr_wqe) {
+		spin_unlock_bh(&cmdq->cmdq_lock);
+		return -EBUSY;
+	}
+
+	wrapped = cmdq->wrapped;
+	next_prod_idx = curr_prod_idx + CMDQ_WQE_NUM_WQEBBS;
+	if (next_prod_idx >= wq->q_depth) {
+		cmdq->wrapped ^= 1;
+		next_prod_idx -= wq->q_depth;
+	}
+
+	cmd_info = &cmdq->cmd_infos[curr_prod_idx];
+	init_completion(&done);
+	refcount_inc(&buf_in->ref_cnt);
+	cmd_info->cmd_type = HINIC3_CMD_TYPE_DIRECT_RESP;
+	cmd_info->done = &done;
+	cmd_info->errcode = &errcode;
+	cmd_info->direct_resp = out_param;
+	cmd_info->cmpt_code = &cmpt_code;
+	cmd_info->buf_in = buf_in;
+	saved_cmd_info = *cmd_info;
+	cmdq_set_lcmd_wqe(&wqe, CMDQ_CMD_DIRECT_RESP, buf_in, NULL,
+			  wrapped, mod, cmd, curr_prod_idx);
+
+	cmdq_wqe_fill(curr_wqe, &wqe);
+	(cmd_info->cmdq_msg_id)++;
+	curr_msg_id = cmd_info->cmdq_msg_id;
+	cmdq_set_db(cmdq, HINIC3_CMDQ_SYNC, next_prod_idx);
+	spin_unlock_bh(&cmdq->cmdq_lock);
+
+	err = wait_cmdq_sync_cmd_completion(cmdq, cmd_info, &saved_cmd_info,
+					    curr_msg_id, curr_prod_idx,
+					    curr_wqe, CMDQ_CMD_TIMEOUT);
+	if (err) {
+		dev_err(cmdq->hwdev->dev,
+			"Cmdq sync command timeout, mod: %u, cmd: %u, prod idx: 0x%x\n",
+			mod, cmd, curr_prod_idx);
+		err = -ETIMEDOUT;
+	}
+
+	if (cmpt_code == CMDQ_FORCE_STOP_CMPT_CODE) {
+		dev_dbg(cmdq->hwdev->dev,
+			"Force stop cmdq cmd, mod: %u, cmd: %u\n", mod, cmd);
+		err = -EAGAIN;
+	}
+
+	smp_rmb(); /* read error code after completion */
+
+	return err ? err : errcode;
+}
+
+int hinic3_cmdq_direct_resp(struct hinic3_hwdev *hwdev, u8 mod, u8 cmd,
+			    struct hinic3_cmd_buf *buf_in, __le64 *out_param)
+{
+	struct hinic3_cmdqs *cmdqs;
+	int err;
+
+	cmdqs = hwdev->cmdqs;
+	err = wait_cmdqs_enable(cmdqs);
+	if (err) {
+		dev_err(hwdev->dev, "Cmdq is disabled\n");
+		return err;
+	}
+
+	err = cmdq_sync_cmd_direct_resp(&cmdqs->cmdq[HINIC3_CMDQ_SYNC],
+					mod, cmd, buf_in, out_param);
+
+	return err;
+}
+
+static void cmdq_init_queue_ctxt(struct hinic3_hwdev *hwdev, u8 cmdq_id,
+				 struct comm_cmdq_ctxt_info *ctxt_info)
+{
+	const struct hinic3_cmdqs *cmdqs;
+	u64 cmdq_first_block_paddr, pfn;
+	const struct hinic3_wq *wq;
+
+	cmdqs = hwdev->cmdqs;
+	wq = &cmdqs->cmdq[cmdq_id].wq;
+	pfn = CMDQ_PFN(hinic3_wq_get_first_wqe_page_addr(wq));
+
+	ctxt_info->curr_wqe_page_pfn =
+		cpu_to_le64(CMDQ_CTXT_SET(1, HW_BUSY_BIT) |
+			    CMDQ_CTXT_SET(1, CEQ_EN)	|
+			    CMDQ_CTXT_SET(1, CEQ_ARM)	|
+			    CMDQ_CTXT_SET(0, EQ_ID) |
+			    CMDQ_CTXT_SET(pfn, CURR_WQE_PAGE_PFN));
+
+	if (!hinic3_wq_is_0_level_cla(wq)) {
+		cmdq_first_block_paddr = cmdqs->wq_block_paddr;
+		pfn = CMDQ_PFN(cmdq_first_block_paddr);
+	}
+
+	ctxt_info->wq_block_pfn = cpu_to_le64(CMDQ_CTXT_SET(wq->cons_idx, CI) |
+					      CMDQ_CTXT_SET(pfn, WQ_BLOCK_PFN));
+}
+
+static int init_cmdq(struct hinic3_cmdq *cmdq, struct hinic3_hwdev *hwdev,
+		     enum hinic3_cmdq_type q_type)
+{
+	int err;
+
+	cmdq->cmdq_type = q_type;
+	cmdq->wrapped = 1;
+	cmdq->hwdev = hwdev;
+
+	spin_lock_init(&cmdq->cmdq_lock);
+
+	cmdq->cmd_infos = kcalloc(cmdq->wq.q_depth, sizeof(*cmdq->cmd_infos),
+				  GFP_KERNEL);
+	if (!cmdq->cmd_infos) {
+		err = -ENOMEM;
+		return err;
+	}
+
+	return 0;
+}
+
+static int hinic3_set_cmdq_ctxt(struct hinic3_hwdev *hwdev, u8 cmdq_id)
+{
+	struct comm_cmd_set_cmdq_ctxt cmdq_ctxt = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	cmdq_init_queue_ctxt(hwdev, cmdq_id, &cmdq_ctxt.ctxt);
+	cmdq_ctxt.func_id = hinic3_global_func_id(hwdev);
+	cmdq_ctxt.cmdq_id = cmdq_id;
+
+	mgmt_msg_params_init_default(&msg_params, &cmdq_ctxt,
+				     sizeof(cmdq_ctxt));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_SET_CMDQ_CTXT, &msg_params);
+	if (err || cmdq_ctxt.head.status) {
+		dev_err(hwdev->dev, "Failed to set cmdq ctxt, err: %d, status: 0x%x\n",
+			err, cmdq_ctxt.head.status);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int hinic3_set_cmdq_ctxts(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_cmdqs *cmdqs = hwdev->cmdqs;
+	u8 cmdq_type;
+	int err;
+
+	for (cmdq_type = 0; cmdq_type < cmdqs->cmdq_num; cmdq_type++) {
+		err = hinic3_set_cmdq_ctxt(hwdev, cmdq_type);
+		if (err)
+			return err;
+	}
+
+	cmdqs->status |= HINIC3_CMDQ_ENABLE;
+	cmdqs->disable_flag = 0;
+
+	return 0;
+}
+
+static int create_cmdq_wq(struct hinic3_hwdev *hwdev,
+			  struct hinic3_cmdqs *cmdqs)
+{
+	u8 cmdq_type;
+	int err;
+
+	for (cmdq_type = 0; cmdq_type < cmdqs->cmdq_num; cmdq_type++) {
+		err = hinic3_wq_create(hwdev, &cmdqs->cmdq[cmdq_type].wq,
+				       CMDQ_DEPTH, CMDQ_WQEBB_SIZE);
+		if (err) {
+			dev_err(hwdev->dev, "Failed to create cmdq wq\n");
+			goto err_destroy_wq;
+		}
+	}
+
+	/* 1-level Chip Logical Address (CLA) must put all
+	 * cmdq's wq page addr in one wq block
+	 */
+	if (!hinic3_wq_is_0_level_cla(&cmdqs->cmdq[HINIC3_CMDQ_SYNC].wq)) {
+		if (cmdqs->cmdq[HINIC3_CMDQ_SYNC].wq.qpages.num_pages >
+		    CMDQ_WQ_CLA_SIZE / sizeof(u64)) {
+			err = -EINVAL;
+			dev_err(hwdev->dev,
+				"Cmdq number of wq pages exceeds limit: %lu\n",
+				CMDQ_WQ_CLA_SIZE / sizeof(u64));
+			goto err_destroy_wq;
+		}
+
+		cmdqs->wq_block_vaddr =
+			dma_alloc_coherent(hwdev->dev, HINIC3_MIN_PAGE_SIZE,
+					   &cmdqs->wq_block_paddr, GFP_KERNEL);
+		if (!cmdqs->wq_block_vaddr) {
+			err = -ENOMEM;
+			goto err_destroy_wq;
+		}
+
+		for (cmdq_type = 0; cmdq_type < cmdqs->cmdq_num; cmdq_type++)
+			memcpy((u8 *)cmdqs->wq_block_vaddr +
+			       CMDQ_WQ_CLA_SIZE * cmdq_type,
+			       cmdqs->cmdq[cmdq_type].wq.wq_block_vaddr,
+			       cmdqs->cmdq[cmdq_type].wq.qpages.num_pages *
+			       sizeof(__be64));
+	}
+
+	return 0;
+
+err_destroy_wq:
+	while (cmdq_type > 0) {
+		cmdq_type--;
+		hinic3_wq_destroy(hwdev, &cmdqs->cmdq[cmdq_type].wq);
+	}
+
+	return err;
+}
+
+static void destroy_cmdq_wq(struct hinic3_hwdev *hwdev,
+			    struct hinic3_cmdqs *cmdqs)
+{
+	u8 cmdq_type;
+
+	if (cmdqs->wq_block_vaddr)
+		dma_free_coherent(hwdev->dev, HINIC3_MIN_PAGE_SIZE,
+				  cmdqs->wq_block_vaddr, cmdqs->wq_block_paddr);
+
+	for (cmdq_type = 0; cmdq_type < cmdqs->cmdq_num; cmdq_type++)
+		hinic3_wq_destroy(hwdev, &cmdqs->cmdq[cmdq_type].wq);
+}
+
+static int init_cmdqs(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_cmdqs *cmdqs;
+
+	cmdqs = kzalloc(sizeof(*cmdqs), GFP_KERNEL);
+	if (!cmdqs)
+		return -ENOMEM;
+
+	hwdev->cmdqs = cmdqs;
+	cmdqs->hwdev = hwdev;
+	cmdqs->cmdq_num = hwdev->max_cmdq;
+
+	cmdqs->cmd_buf_pool = dma_pool_create("hinic3_cmdq", hwdev->dev,
+					      CMDQ_BUF_SIZE, CMDQ_BUF_SIZE, 0);
+	if (!cmdqs->cmd_buf_pool) {
+		dev_err(hwdev->dev, "Failed to create cmdq buffer pool\n");
+		kfree(cmdqs);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void cmdq_flush_sync_cmd(struct hinic3_cmdq_cmd_info *cmd_info)
+{
+	if (cmd_info->cmd_type != HINIC3_CMD_TYPE_DIRECT_RESP)
+		return;
+
+	cmd_info->cmd_type = HINIC3_CMD_TYPE_FORCE_STOP;
+
+	if (cmd_info->cmpt_code &&
+	    *cmd_info->cmpt_code == CMDQ_SEND_CMPT_CODE)
+		*cmd_info->cmpt_code = CMDQ_FORCE_STOP_CMPT_CODE;
+
+	if (cmd_info->done) {
+		complete(cmd_info->done);
+		cmd_info->done = NULL;
+		cmd_info->cmpt_code = NULL;
+		cmd_info->direct_resp = NULL;
+		cmd_info->errcode = NULL;
+	}
+}
+
+static void hinic3_cmdq_flush_cmd(struct hinic3_cmdq *cmdq)
+{
+	struct hinic3_cmdq_cmd_info *cmd_info;
+	u16 ci;
+
+	spin_lock_bh(&cmdq->cmdq_lock);
+	while (cmdq_read_wqe(&cmdq->wq, &ci)) {
+		hinic3_wq_put_wqebbs(&cmdq->wq, CMDQ_WQE_NUM_WQEBBS);
+		cmd_info = &cmdq->cmd_infos[ci];
+		if (cmd_info->cmd_type == HINIC3_CMD_TYPE_DIRECT_RESP)
+			cmdq_flush_sync_cmd(cmd_info);
+	}
+	spin_unlock_bh(&cmdq->cmdq_lock);
+}
+
+void hinic3_cmdq_flush_sync_cmd(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_cmdq *cmdq;
+	u16 wqe_cnt, wqe_idx, i;
+	struct hinic3_wq *wq;
+
+	cmdq = &hwdev->cmdqs->cmdq[HINIC3_CMDQ_SYNC];
+	spin_lock_bh(&cmdq->cmdq_lock);
+	wq = &cmdq->wq;
+	wqe_cnt = hinic3_wq_get_used(wq);
+	for (i = 0; i < wqe_cnt; i++) {
+		wqe_idx = (wq->cons_idx + i) & wq->idx_mask;
+		cmdq_flush_sync_cmd(cmdq->cmd_infos + wqe_idx);
+	}
+	spin_unlock_bh(&cmdq->cmdq_lock);
+}
+
+static void hinic3_cmdq_reset_all_cmd_buf(struct hinic3_cmdq *cmdq)
+{
+	u16 i;
+
+	for (i = 0; i < cmdq->wq.q_depth; i++)
+		cmdq_clear_cmd_buf(&cmdq->cmd_infos[i], cmdq->hwdev);
+}
+
+int hinic3_reinit_cmdq_ctxts(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_cmdqs *cmdqs = hwdev->cmdqs;
+	u8 cmdq_type;
+
+	for (cmdq_type = 0; cmdq_type < cmdqs->cmdq_num; cmdq_type++) {
+		hinic3_cmdq_flush_cmd(&cmdqs->cmdq[cmdq_type]);
+		hinic3_cmdq_reset_all_cmd_buf(&cmdqs->cmdq[cmdq_type]);
+		cmdqs->cmdq[cmdq_type].wrapped = 1;
+		hinic3_wq_reset(&cmdqs->cmdq[cmdq_type].wq);
+	}
+
+	return hinic3_set_cmdq_ctxts(hwdev);
+}
+
+int hinic3_cmdqs_init(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_cmdqs *cmdqs;
+	void __iomem *db_base;
+	u8 cmdq_type;
+	int err;
+
+	err = init_cmdqs(hwdev);
+	if (err)
+		goto err_out;
+
+	cmdqs = hwdev->cmdqs;
+	err = create_cmdq_wq(hwdev, cmdqs);
+	if (err)
+		goto err_free_cmdqs;
+
+	err = hinic3_alloc_db_addr(hwdev, &db_base, NULL);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to allocate doorbell address\n");
+		goto err_destroy_cmdq_wq;
+	}
+	cmdqs->cmdqs_db_base = db_base;
+
+	for (cmdq_type = 0; cmdq_type < cmdqs->cmdq_num; cmdq_type++) {
+		err = init_cmdq(&cmdqs->cmdq[cmdq_type], hwdev, cmdq_type);
+		if (err) {
+			dev_err(hwdev->dev,
+				"Failed to initialize cmdq type : %d\n",
+				cmdq_type);
+			goto err_free_cmd_infos;
+		}
+	}
+
+	err = hinic3_set_cmdq_ctxts(hwdev);
+	if (err)
+		goto err_free_cmd_infos;
+
+	return 0;
+
+err_free_cmd_infos:
+	while (cmdq_type > 0) {
+		cmdq_type--;
+		kfree(cmdqs->cmdq[cmdq_type].cmd_infos);
+	}
+
+	hinic3_free_db_addr(hwdev, cmdqs->cmdqs_db_base);
+
+err_destroy_cmdq_wq:
+	destroy_cmdq_wq(hwdev, cmdqs);
+
+err_free_cmdqs:
+	dma_pool_destroy(cmdqs->cmd_buf_pool);
+	kfree(cmdqs);
+
+err_out:
+	return err;
+}
+
+void hinic3_cmdqs_free(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_cmdqs *cmdqs = hwdev->cmdqs;
+	u8 cmdq_type;
+
+	cmdqs->status &= ~HINIC3_CMDQ_ENABLE;
+
+	for (cmdq_type = 0; cmdq_type < cmdqs->cmdq_num; cmdq_type++) {
+		hinic3_cmdq_flush_cmd(&cmdqs->cmdq[cmdq_type]);
+		hinic3_cmdq_reset_all_cmd_buf(&cmdqs->cmdq[cmdq_type]);
+		kfree(cmdqs->cmdq[cmdq_type].cmd_infos);
+	}
+
+	hinic3_free_db_addr(hwdev, cmdqs->cmdqs_db_base);
+	destroy_cmdq_wq(hwdev, cmdqs);
+	dma_pool_destroy(cmdqs->cmd_buf_pool);
+	kfree(cmdqs);
+}
+
+bool hinic3_cmdq_idle(struct hinic3_cmdq *cmdq)
+{
+	return hinic3_wq_get_used(&cmdq->wq) == 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_cmdq.h b/drivers/net/ethernet/huawei/hinic3/hinic3_cmdq.h
new file mode 100644
index 000000000000..f99c386a2780
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_cmdq.h
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_CMDQ_H_
+#define _HINIC3_CMDQ_H_
+
+#include <linux/dmapool.h>
+
+#include "hinic3_hw_intf.h"
+#include "hinic3_wq.h"
+
+#define CMDQ_DEPTH  4096
+
+struct cmdq_db {
+	__le32 db_head;
+	__le32 db_info;
+};
+
+/* hw defined cmdq wqe header */
+struct cmdq_header {
+	__le32 header_info;
+	__le32 saved_data;
+};
+
+struct cmdq_lcmd_bufdesc {
+	struct hinic3_sge sge;
+	__le64            rsvd2;
+	__le64            rsvd3;
+};
+
+struct cmdq_status {
+	__le32 status_info;
+};
+
+struct cmdq_ctrl {
+	__le32 ctrl_info;
+};
+
+struct cmdq_direct_resp {
+	__le64 val;
+	__le64 rsvd;
+};
+
+struct cmdq_completion {
+	union {
+		struct hinic3_sge       sge;
+		struct cmdq_direct_resp direct;
+	} resp;
+};
+
+struct cmdq_wqe_scmd {
+	struct cmdq_header     header;
+	__le64                 rsvd3;
+	struct cmdq_status     status;
+	struct cmdq_ctrl       ctrl;
+	struct cmdq_completion completion;
+	__le32                 rsvd10[6];
+};
+
+struct cmdq_wqe_lcmd {
+	struct cmdq_header       header;
+	struct cmdq_status       status;
+	struct cmdq_ctrl         ctrl;
+	struct cmdq_completion   completion;
+	struct cmdq_lcmd_bufdesc buf_desc;
+};
+
+struct cmdq_wqe {
+	union {
+		struct cmdq_wqe_scmd wqe_scmd;
+		struct cmdq_wqe_lcmd wqe_lcmd;
+	};
+};
+
+static_assert(sizeof(struct cmdq_wqe) == 64);
+
+enum hinic3_cmdq_type {
+	HINIC3_CMDQ_SYNC      = 0,
+	HINIC3_MAX_CMDQ_TYPES = 4
+};
+
+enum hinic3_cmdq_status {
+	HINIC3_CMDQ_ENABLE = BIT(0),
+};
+
+enum hinic3_cmdq_cmd_type {
+	HINIC3_CMD_TYPE_NONE,
+	HINIC3_CMD_TYPE_DIRECT_RESP,
+	HINIC3_CMD_TYPE_FAKE_TIMEOUT,
+	HINIC3_CMD_TYPE_TIMEOUT,
+	HINIC3_CMD_TYPE_FORCE_STOP,
+};
+
+struct hinic3_cmd_buf {
+	void       *buf;
+	dma_addr_t dma_addr;
+	__le16     size;
+	refcount_t ref_cnt;
+};
+
+struct hinic3_cmdq_cmd_info {
+	enum hinic3_cmdq_cmd_type cmd_type;
+	struct completion         *done;
+	int                       *errcode;
+	/* completion code */
+	int                       *cmpt_code;
+	__le64                    *direct_resp;
+	u64                       cmdq_msg_id;
+	struct hinic3_cmd_buf     *buf_in;
+};
+
+struct hinic3_cmdq {
+	struct hinic3_wq            wq;
+	enum hinic3_cmdq_type       cmdq_type;
+	u8                          wrapped;
+	/* synchronize command submission with completions via event queue */
+	spinlock_t                  cmdq_lock;
+	struct hinic3_cmdq_cmd_info *cmd_infos;
+	struct hinic3_hwdev         *hwdev;
+};
+
+struct hinic3_cmdqs {
+	struct hinic3_hwdev *hwdev;
+	struct hinic3_cmdq  cmdq[HINIC3_MAX_CMDQ_TYPES];
+	struct dma_pool     *cmd_buf_pool;
+	/* doorbell area */
+	u8 __iomem          *cmdqs_db_base;
+
+	/* When command queue uses multiple memory pages (1-level CLA), this
+	 * block will hold aggregated indirection table for all command queues
+	 * of cmdqs. Not used for small cmdq (0-level CLA).
+	 */
+	dma_addr_t          wq_block_paddr;
+	void                *wq_block_vaddr;
+
+	u32                 status;
+	u32                 disable_flag;
+	u8                  cmdq_num;
+};
+
+int hinic3_cmdqs_init(struct hinic3_hwdev *hwdev);
+void hinic3_cmdqs_free(struct hinic3_hwdev *hwdev);
+
+struct hinic3_cmd_buf *hinic3_alloc_cmd_buf(struct hinic3_hwdev *hwdev);
+void hinic3_free_cmd_buf(struct hinic3_hwdev *hwdev,
+			 struct hinic3_cmd_buf *cmd_buf);
+void hinic3_cmdq_ceq_handler(struct hinic3_hwdev *hwdev, __le32 ceqe_data);
+
+int hinic3_cmdq_direct_resp(struct hinic3_hwdev *hwdev, u8 mod, u8 cmd,
+			    struct hinic3_cmd_buf *buf_in, __le64 *out_param);
+
+void hinic3_cmdq_flush_sync_cmd(struct hinic3_hwdev *hwdev);
+int hinic3_reinit_cmdq_ctxts(struct hinic3_hwdev *hwdev);
+bool hinic3_cmdq_idle(struct hinic3_cmdq *cmdq);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_common.c b/drivers/net/ethernet/huawei/hinic3/hinic3_common.c
new file mode 100644
index 000000000000..fe4778d152cf
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_common.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/iopoll.h>
+
+#include "hinic3_common.h"
+
+int hinic3_dma_zalloc_coherent_align(struct device *dev, u32 size, u32 align,
+				     gfp_t flag,
+				     struct hinic3_dma_addr_align *mem_align)
+{
+	dma_addr_t paddr, align_paddr;
+	void *vaddr, *align_vaddr;
+	u32 real_size = size;
+
+	vaddr = dma_alloc_coherent(dev, real_size, &paddr, flag);
+	if (!vaddr)
+		return -ENOMEM;
+
+	align_paddr = ALIGN(paddr, align);
+	if (align_paddr == paddr) {
+		align_vaddr = vaddr;
+		goto out;
+	}
+
+	dma_free_coherent(dev, real_size, vaddr, paddr);
+
+	/* realloc memory for align */
+	real_size = size + align;
+	vaddr = dma_alloc_coherent(dev, real_size, &paddr, flag);
+	if (!vaddr)
+		return -ENOMEM;
+
+	align_paddr = ALIGN(paddr, align);
+	align_vaddr = vaddr + (align_paddr - paddr);
+
+out:
+	mem_align->real_size = real_size;
+	mem_align->ori_vaddr = vaddr;
+	mem_align->ori_paddr = paddr;
+	mem_align->align_vaddr = align_vaddr;
+	mem_align->align_paddr = align_paddr;
+
+	return 0;
+}
+
+void hinic3_dma_free_coherent_align(struct device *dev,
+				    struct hinic3_dma_addr_align *mem_align)
+{
+	dma_free_coherent(dev, mem_align->real_size,
+			  mem_align->ori_vaddr, mem_align->ori_paddr);
+}
+
+int hinic3_wait_for_timeout(void *priv_data, wait_cpl_handler handler,
+			    u32 wait_total_ms, u32 wait_once_us)
+{
+	enum hinic3_wait_return ret;
+	int err;
+
+	err = read_poll_timeout(handler, ret, ret == HINIC3_WAIT_PROCESS_CPL,
+				wait_once_us, wait_total_ms * USEC_PER_MSEC,
+				false, priv_data);
+
+	return err;
+}
+
+/* Data provided to/by cmdq is arranged in structs with little endian fields but
+ * every dword (32bits) should be swapped since HW swaps it again when it
+ * copies it from/to host memory.
+ */
+void hinic3_cmdq_buf_swab32(void *data, int len)
+{
+	swab32_array(data, len / sizeof(u32));
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_common.h b/drivers/net/ethernet/huawei/hinic3/hinic3_common.h
new file mode 100644
index 000000000000..a8fabfae90fb
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_common.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_COMMON_H_
+#define _HINIC3_COMMON_H_
+
+#include <linux/device.h>
+
+#define HINIC3_MIN_PAGE_SIZE  0x1000
+
+struct hinic3_dma_addr_align {
+	u32        real_size;
+
+	void       *ori_vaddr;
+	dma_addr_t ori_paddr;
+
+	void       *align_vaddr;
+	dma_addr_t align_paddr;
+};
+
+enum hinic3_wait_return {
+	HINIC3_WAIT_PROCESS_CPL     = 0,
+	HINIC3_WAIT_PROCESS_WAITING = 1,
+};
+
+struct hinic3_sge {
+	__le32 hi_addr;
+	__le32 lo_addr;
+	__le32 len;
+	__le32 rsvd;
+};
+
+static inline void hinic3_set_sge(struct hinic3_sge *sge, dma_addr_t addr,
+				  __le32 len)
+{
+	sge->hi_addr = cpu_to_le32(upper_32_bits(addr));
+	sge->lo_addr = cpu_to_le32(lower_32_bits(addr));
+	sge->len = len;
+	sge->rsvd = 0;
+}
+
+int hinic3_dma_zalloc_coherent_align(struct device *dev, u32 size, u32 align,
+				     gfp_t flag,
+				     struct hinic3_dma_addr_align *mem_align);
+void hinic3_dma_free_coherent_align(struct device *dev,
+				    struct hinic3_dma_addr_align *mem_align);
+
+typedef enum hinic3_wait_return (*wait_cpl_handler)(void *priv_data);
+int hinic3_wait_for_timeout(void *priv_data, wait_cpl_handler handler,
+			    u32 wait_total_ms, u32 wait_once_us);
+
+void hinic3_cmdq_buf_swab32(void *data, int len);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_csr.h b/drivers/net/ethernet/huawei/hinic3/hinic3_csr.h
new file mode 100644
index 000000000000..e7417e8efa99
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_csr.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_CSR_H_
+#define _HINIC3_CSR_H_
+
+#define HINIC3_CFG_REGS_FLAG                  0x40000000
+#define HINIC3_REGS_FLAG_MASK                 0x3FFFFFFF
+
+#define HINIC3_VF_CFG_REG_OFFSET              0x2000
+
+/* HW interface registers */
+#define HINIC3_CSR_FUNC_ATTR0_ADDR            (HINIC3_CFG_REGS_FLAG + 0x0)
+#define HINIC3_CSR_FUNC_ATTR1_ADDR            (HINIC3_CFG_REGS_FLAG + 0x4)
+#define HINIC3_CSR_FUNC_ATTR2_ADDR            (HINIC3_CFG_REGS_FLAG + 0x8)
+#define HINIC3_CSR_FUNC_ATTR3_ADDR            (HINIC3_CFG_REGS_FLAG + 0xC)
+#define HINIC3_CSR_FUNC_ATTR4_ADDR            (HINIC3_CFG_REGS_FLAG + 0x10)
+#define HINIC3_CSR_FUNC_ATTR5_ADDR            (HINIC3_CFG_REGS_FLAG + 0x14)
+#define HINIC3_CSR_FUNC_ATTR6_ADDR            (HINIC3_CFG_REGS_FLAG + 0x18)
+
+#define HINIC3_FUNC_CSR_MAILBOX_DATA_OFF      0x80
+#define HINIC3_FUNC_CSR_MAILBOX_CONTROL_OFF   (HINIC3_CFG_REGS_FLAG + 0x0100)
+#define HINIC3_FUNC_CSR_MAILBOX_INT_OFF       (HINIC3_CFG_REGS_FLAG + 0x0104)
+#define HINIC3_FUNC_CSR_MAILBOX_RESULT_H_OFF  (HINIC3_CFG_REGS_FLAG + 0x0108)
+#define HINIC3_FUNC_CSR_MAILBOX_RESULT_L_OFF  (HINIC3_CFG_REGS_FLAG + 0x010C)
+
+#define HINIC3_CSR_DMA_ATTR_TBL_ADDR          (HINIC3_CFG_REGS_FLAG + 0x380)
+#define HINIC3_CSR_DMA_ATTR_INDIR_IDX_ADDR    (HINIC3_CFG_REGS_FLAG + 0x390)
+
+/* MSI-X registers */
+#define HINIC3_CSR_FUNC_MSI_CLR_WR_ADDR       (HINIC3_CFG_REGS_FLAG + 0x58)
+
+#define HINIC3_MSI_CLR_INDIR_RESEND_TIMER_CLR_MASK  BIT(0)
+#define HINIC3_MSI_CLR_INDIR_INT_MSK_SET_MASK       BIT(1)
+#define HINIC3_MSI_CLR_INDIR_INT_MSK_CLR_MASK       BIT(2)
+#define HINIC3_MSI_CLR_INDIR_AUTO_MSK_SET_MASK      BIT(3)
+#define HINIC3_MSI_CLR_INDIR_AUTO_MSK_CLR_MASK      BIT(4)
+#define HINIC3_MSI_CLR_INDIR_SIMPLE_INDIR_IDX_MASK  GENMASK(31, 22)
+#define HINIC3_MSI_CLR_INDIR_SET(val, member)  \
+	FIELD_PREP(HINIC3_MSI_CLR_INDIR_##member##_MASK, val)
+
+/* EQ registers */
+#define HINIC3_AEQ_INDIR_IDX_ADDR      (HINIC3_CFG_REGS_FLAG + 0x210)
+#define HINIC3_CEQ_INDIR_IDX_ADDR      (HINIC3_CFG_REGS_FLAG + 0x290)
+
+#define HINIC3_EQ_INDIR_IDX_ADDR(type)  \
+	((type == HINIC3_AEQ) ? HINIC3_AEQ_INDIR_IDX_ADDR :  \
+	 HINIC3_CEQ_INDIR_IDX_ADDR)
+
+#define HINIC3_AEQ_MTT_OFF_BASE_ADDR   (HINIC3_CFG_REGS_FLAG + 0x240)
+#define HINIC3_CEQ_MTT_OFF_BASE_ADDR   (HINIC3_CFG_REGS_FLAG + 0x2C0)
+
+#define HINIC3_CSR_EQ_PAGE_OFF_STRIDE  8
+
+#define HINIC3_AEQ_HI_PHYS_ADDR_REG(pg_num)  \
+	(HINIC3_AEQ_MTT_OFF_BASE_ADDR + (pg_num) *  \
+	 HINIC3_CSR_EQ_PAGE_OFF_STRIDE)
+
+#define HINIC3_AEQ_LO_PHYS_ADDR_REG(pg_num)  \
+	(HINIC3_AEQ_MTT_OFF_BASE_ADDR + (pg_num) *  \
+	 HINIC3_CSR_EQ_PAGE_OFF_STRIDE + 4)
+
+#define HINIC3_CEQ_HI_PHYS_ADDR_REG(pg_num)  \
+	(HINIC3_CEQ_MTT_OFF_BASE_ADDR + (pg_num) *  \
+	 HINIC3_CSR_EQ_PAGE_OFF_STRIDE)
+
+#define HINIC3_CEQ_LO_PHYS_ADDR_REG(pg_num)  \
+	(HINIC3_CEQ_MTT_OFF_BASE_ADDR + (pg_num) *  \
+	 HINIC3_CSR_EQ_PAGE_OFF_STRIDE + 4)
+
+#define HINIC3_CSR_AEQ_CTRL_0_ADDR           (HINIC3_CFG_REGS_FLAG + 0x200)
+#define HINIC3_CSR_AEQ_CTRL_1_ADDR           (HINIC3_CFG_REGS_FLAG + 0x204)
+#define HINIC3_CSR_AEQ_PROD_IDX_ADDR         (HINIC3_CFG_REGS_FLAG + 0x20C)
+#define HINIC3_CSR_AEQ_CI_SIMPLE_INDIR_ADDR  (HINIC3_CFG_REGS_FLAG + 0x50)
+
+#define HINIC3_CSR_CEQ_PROD_IDX_ADDR         (HINIC3_CFG_REGS_FLAG + 0x28c)
+#define HINIC3_CSR_CEQ_CI_SIMPLE_INDIR_ADDR  (HINIC3_CFG_REGS_FLAG + 0x54)
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_eqs.c b/drivers/net/ethernet/huawei/hinic3/hinic3_eqs.c
new file mode 100644
index 000000000000..01686472985b
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_eqs.c
@@ -0,0 +1,776 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/delay.h>
+
+#include "hinic3_csr.h"
+#include "hinic3_eqs.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+#define AEQ_CTRL_0_INTR_IDX_MASK      GENMASK(9, 0)
+#define AEQ_CTRL_0_DMA_ATTR_MASK      GENMASK(17, 12)
+#define AEQ_CTRL_0_PCI_INTF_IDX_MASK  GENMASK(22, 20)
+#define AEQ_CTRL_0_INTR_MODE_MASK     BIT(31)
+#define AEQ_CTRL_0_SET(val, member)  \
+	FIELD_PREP(AEQ_CTRL_0_##member##_MASK, val)
+
+#define AEQ_CTRL_1_LEN_MASK           GENMASK(20, 0)
+#define AEQ_CTRL_1_ELEM_SIZE_MASK     GENMASK(25, 24)
+#define AEQ_CTRL_1_PAGE_SIZE_MASK     GENMASK(31, 28)
+#define AEQ_CTRL_1_SET(val, member)  \
+	FIELD_PREP(AEQ_CTRL_1_##member##_MASK, val)
+
+#define CEQ_CTRL_0_INTR_IDX_MASK      GENMASK(9, 0)
+#define CEQ_CTRL_0_DMA_ATTR_MASK      GENMASK(17, 12)
+#define CEQ_CTRL_0_LIMIT_KICK_MASK    GENMASK(23, 20)
+#define CEQ_CTRL_0_PCI_INTF_IDX_MASK  GENMASK(25, 24)
+#define CEQ_CTRL_0_PAGE_SIZE_MASK     GENMASK(30, 27)
+#define CEQ_CTRL_0_INTR_MODE_MASK     BIT(31)
+#define CEQ_CTRL_0_SET(val, member)  \
+	FIELD_PREP(CEQ_CTRL_0_##member##_MASK, val)
+
+#define CEQ_CTRL_1_LEN_MASK           GENMASK(19, 0)
+#define CEQ_CTRL_1_SET(val, member)  \
+	FIELD_PREP(CEQ_CTRL_1_##member##_MASK, val)
+
+#define CEQE_TYPE_MASK                GENMASK(25, 23)
+#define CEQE_TYPE(type)  \
+	FIELD_GET(CEQE_TYPE_MASK, le32_to_cpu(type))
+
+#define CEQE_DATA_MASK                GENMASK(25, 0)
+#define CEQE_DATA(data)               ((data) & cpu_to_le32(CEQE_DATA_MASK))
+
+#define EQ_ELEM_DESC_TYPE_MASK        GENMASK(6, 0)
+#define EQ_ELEM_DESC_SRC_MASK         BIT(7)
+#define EQ_ELEM_DESC_SIZE_MASK        GENMASK(15, 8)
+#define EQ_ELEM_DESC_WRAPPED_MASK     BIT(31)
+#define EQ_ELEM_DESC_GET(val, member)  \
+	FIELD_GET(EQ_ELEM_DESC_##member##_MASK, le32_to_cpu(val))
+
+#define EQ_CI_SIMPLE_INDIR_CI_MASK       GENMASK(20, 0)
+#define EQ_CI_SIMPLE_INDIR_ARMED_MASK    BIT(21)
+#define EQ_CI_SIMPLE_INDIR_AEQ_IDX_MASK  GENMASK(31, 30)
+#define EQ_CI_SIMPLE_INDIR_CEQ_IDX_MASK  GENMASK(31, 24)
+#define EQ_CI_SIMPLE_INDIR_SET(val, member)  \
+	FIELD_PREP(EQ_CI_SIMPLE_INDIR_##member##_MASK, val)
+
+#define EQ_CI_SIMPLE_INDIR_REG_ADDR(eq)  \
+	(((eq)->type == HINIC3_AEQ) ?  \
+	 HINIC3_CSR_AEQ_CI_SIMPLE_INDIR_ADDR :  \
+	 HINIC3_CSR_CEQ_CI_SIMPLE_INDIR_ADDR)
+
+#define EQ_PROD_IDX_REG_ADDR(eq)  \
+	(((eq)->type == HINIC3_AEQ) ?  \
+	 HINIC3_CSR_AEQ_PROD_IDX_ADDR : HINIC3_CSR_CEQ_PROD_IDX_ADDR)
+
+#define EQ_HI_PHYS_ADDR_REG(type, pg_num)  \
+	(((type) == HINIC3_AEQ) ?  \
+	       HINIC3_AEQ_HI_PHYS_ADDR_REG(pg_num) :  \
+	       HINIC3_CEQ_HI_PHYS_ADDR_REG(pg_num))
+
+#define EQ_LO_PHYS_ADDR_REG(type, pg_num)  \
+	(((type) == HINIC3_AEQ) ?  \
+	       HINIC3_AEQ_LO_PHYS_ADDR_REG(pg_num) :  \
+	       HINIC3_CEQ_LO_PHYS_ADDR_REG(pg_num))
+
+#define EQ_MSIX_RESEND_TIMER_CLEAR  1
+
+#define HINIC3_EQ_MAX_PAGES(eq)  \
+	((eq)->type == HINIC3_AEQ ?  \
+	 HINIC3_AEQ_MAX_PAGES : HINIC3_CEQ_MAX_PAGES)
+
+#define HINIC3_TASK_PROCESS_EQE_LIMIT  1024
+#define HINIC3_EQ_UPDATE_CI_STEP       64
+#define HINIC3_EQS_WQ_NAME             "hinic3_eqs"
+
+#define HINIC3_EQ_VALID_SHIFT          31
+#define HINIC3_EQ_WRAPPED(eq)  \
+	((eq)->wrapped << HINIC3_EQ_VALID_SHIFT)
+
+#define HINIC3_EQ_WRAPPED_SHIFT        20
+#define HINIC3_EQ_CONS_IDX(eq)  \
+	((eq)->cons_idx | ((eq)->wrapped << HINIC3_EQ_WRAPPED_SHIFT))
+
+static const struct hinic3_aeq_elem *get_curr_aeq_elem(const struct hinic3_eq *eq)
+{
+	return get_q_element(&eq->qpages, eq->cons_idx, NULL);
+}
+
+static const __be32 *get_curr_ceq_elem(const struct hinic3_eq *eq)
+{
+	return get_q_element(&eq->qpages, eq->cons_idx, NULL);
+}
+
+int hinic3_aeq_register_cb(struct hinic3_hwdev *hwdev,
+			   enum hinic3_aeq_type event,
+			   hinic3_aeq_event_cb hwe_cb)
+{
+	struct hinic3_aeqs *aeqs;
+
+	aeqs = hwdev->aeqs;
+	aeqs->aeq_cb[event] = hwe_cb;
+	spin_lock_init(&aeqs->aeq_lock);
+
+	return 0;
+}
+
+void hinic3_aeq_unregister_cb(struct hinic3_hwdev *hwdev,
+			      enum hinic3_aeq_type event)
+{
+	struct hinic3_aeqs *aeqs;
+
+	aeqs = hwdev->aeqs;
+
+	spin_lock_bh(&aeqs->aeq_lock);
+	aeqs->aeq_cb[event] = NULL;
+	spin_unlock_bh(&aeqs->aeq_lock);
+}
+
+int hinic3_ceq_register_cb(struct hinic3_hwdev *hwdev,
+			   enum hinic3_ceq_event event,
+			   hinic3_ceq_event_cb callback)
+{
+	struct hinic3_ceqs *ceqs;
+
+	ceqs = hwdev->ceqs;
+	ceqs->ceq_cb[event] = callback;
+	spin_lock_init(&ceqs->ceq_lock);
+
+	return 0;
+}
+
+void hinic3_ceq_unregister_cb(struct hinic3_hwdev *hwdev,
+			      enum hinic3_ceq_event event)
+{
+	struct hinic3_ceqs *ceqs;
+
+	ceqs = hwdev->ceqs;
+
+	spin_lock_bh(&ceqs->ceq_lock);
+	ceqs->ceq_cb[event] = NULL;
+	spin_unlock_bh(&ceqs->ceq_lock);
+}
+
+/* Set consumer index in the hw. */
+static void set_eq_cons_idx(struct hinic3_eq *eq, u32 arm_state)
+{
+	u32 addr = EQ_CI_SIMPLE_INDIR_REG_ADDR(eq);
+	u32 eq_wrap_ci, val;
+
+	eq_wrap_ci = HINIC3_EQ_CONS_IDX(eq);
+	val = EQ_CI_SIMPLE_INDIR_SET(arm_state, ARMED);
+	if (eq->type == HINIC3_AEQ) {
+		val = val |
+			EQ_CI_SIMPLE_INDIR_SET(eq_wrap_ci, CI) |
+			EQ_CI_SIMPLE_INDIR_SET(eq->q_id, AEQ_IDX);
+	} else {
+		val = val |
+			EQ_CI_SIMPLE_INDIR_SET(eq_wrap_ci, CI) |
+			EQ_CI_SIMPLE_INDIR_SET(eq->q_id, CEQ_IDX);
+	}
+
+	hinic3_hwif_write_reg(eq->hwdev->hwif, addr, val);
+}
+
+static struct hinic3_ceqs *ceq_to_ceqs(const struct hinic3_eq *eq)
+{
+	return container_of(eq, struct hinic3_ceqs, ceq[eq->q_id]);
+}
+
+static void ceq_event_handler(struct hinic3_ceqs *ceqs, __le32 ceqe)
+{
+	enum hinic3_ceq_event event = CEQE_TYPE(ceqe);
+	struct hinic3_hwdev *hwdev = ceqs->hwdev;
+	__le32 ceqe_data = CEQE_DATA(ceqe);
+
+	if (event >= HINIC3_MAX_CEQ_EVENTS) {
+		dev_warn(hwdev->dev, "Ceq unknown event:%d, ceqe data: 0x%x\n",
+			 event, ceqe_data);
+		return;
+	}
+
+	spin_lock_bh(&ceqs->ceq_lock);
+	if (ceqs->ceq_cb[event])
+		ceqs->ceq_cb[event](hwdev, ceqe_data);
+
+	spin_unlock_bh(&ceqs->ceq_lock);
+}
+
+static struct hinic3_aeqs *aeq_to_aeqs(const struct hinic3_eq *eq)
+{
+	return container_of(eq, struct hinic3_aeqs, aeq[eq->q_id]);
+}
+
+static void aeq_event_handler(struct hinic3_aeqs *aeqs, __le32 aeqe,
+			      const struct hinic3_aeq_elem *aeqe_pos)
+{
+	struct hinic3_hwdev *hwdev = aeqs->hwdev;
+	u8 data[HINIC3_AEQE_DATA_SIZE], size;
+	enum hinic3_aeq_type event;
+	hinic3_aeq_event_cb hwe_cb;
+
+	if (EQ_ELEM_DESC_GET(aeqe, SRC))
+		return;
+
+	event = EQ_ELEM_DESC_GET(aeqe, TYPE);
+	if (event >= HINIC3_MAX_AEQ_EVENTS) {
+		dev_warn(hwdev->dev, "Aeq unknown event:%d\n", event);
+		return;
+	}
+
+	memcpy(data, aeqe_pos->aeqe_data, HINIC3_AEQE_DATA_SIZE);
+	swab32_array((u32 *)data, HINIC3_AEQE_DATA_SIZE / sizeof(u32));
+	size = EQ_ELEM_DESC_GET(aeqe, SIZE);
+
+	spin_lock_bh(&aeqs->aeq_lock);
+	hwe_cb = aeqs->aeq_cb[event];
+	if (hwe_cb)
+		hwe_cb(aeqs->hwdev, data, size);
+	spin_unlock_bh(&aeqs->aeq_lock);
+}
+
+static int aeq_irq_handler(struct hinic3_eq *eq)
+{
+	const struct hinic3_aeq_elem *aeqe_pos;
+	struct hinic3_aeqs *aeqs;
+	u32 i, eqe_cnt = 0;
+	__le32 aeqe;
+
+	aeqs = aeq_to_aeqs(eq);
+	for (i = 0; i < HINIC3_TASK_PROCESS_EQE_LIMIT; i++) {
+		aeqe_pos = get_curr_aeq_elem(eq);
+		aeqe = (__force __le32)swab32((__force __u32)aeqe_pos->desc);
+		/* HW updates wrapped bit, when it adds eq element event */
+		if (EQ_ELEM_DESC_GET(aeqe, WRAPPED) == eq->wrapped)
+			return 0;
+
+		/* Prevent speculative reads from element */
+		dma_rmb();
+		aeq_event_handler(aeqs, aeqe, aeqe_pos);
+		eq->cons_idx++;
+		if (eq->cons_idx == eq->eq_len) {
+			eq->cons_idx = 0;
+			eq->wrapped = !eq->wrapped;
+		}
+
+		if (++eqe_cnt >= HINIC3_EQ_UPDATE_CI_STEP) {
+			eqe_cnt = 0;
+			set_eq_cons_idx(eq, HINIC3_EQ_NOT_ARMED);
+		}
+	}
+
+	return -EAGAIN;
+}
+
+static int ceq_irq_handler(struct hinic3_eq *eq)
+{
+	struct hinic3_ceqs *ceqs;
+	u32 eqe_cnt = 0;
+	__be32 ceqe_raw;
+	__le32 ceqe;
+	u32 i;
+
+	ceqs = ceq_to_ceqs(eq);
+	for (i = 0; i < HINIC3_TASK_PROCESS_EQE_LIMIT; i++) {
+		ceqe_raw = *get_curr_ceq_elem(eq);
+		ceqe = (__force __le32)swab32((__force __u32)ceqe_raw);
+
+		/* HW updates wrapped bit, when it adds eq element event */
+		if (EQ_ELEM_DESC_GET(ceqe, WRAPPED) == eq->wrapped)
+			return 0;
+
+		ceq_event_handler(ceqs, ceqe);
+		eq->cons_idx++;
+		if (eq->cons_idx == eq->eq_len) {
+			eq->cons_idx = 0;
+			eq->wrapped = !eq->wrapped;
+		}
+
+		if (++eqe_cnt >= HINIC3_EQ_UPDATE_CI_STEP) {
+			eqe_cnt = 0;
+			set_eq_cons_idx(eq, HINIC3_EQ_NOT_ARMED);
+		}
+	}
+
+	return -EAGAIN;
+}
+
+static void reschedule_aeq_handler(struct hinic3_eq *eq)
+{
+	struct hinic3_aeqs *aeqs = aeq_to_aeqs(eq);
+
+	queue_work(aeqs->workq, &eq->aeq_work);
+}
+
+static int eq_irq_handler(struct hinic3_eq *eq)
+{
+	int err;
+
+	if (eq->type == HINIC3_AEQ)
+		err = aeq_irq_handler(eq);
+	else
+		err = ceq_irq_handler(eq);
+
+	set_eq_cons_idx(eq, err ? HINIC3_EQ_NOT_ARMED :
+			HINIC3_EQ_ARMED);
+
+	return err;
+}
+
+static void aeq_irq_work(struct work_struct *work)
+{
+	struct hinic3_eq *eq = container_of(work, struct hinic3_eq, aeq_work);
+	int err;
+
+	err = eq_irq_handler(eq);
+	if (err)
+		reschedule_aeq_handler(eq);
+}
+
+static irqreturn_t aeq_interrupt(int irq, void *data)
+{
+	struct workqueue_struct *workq;
+	struct hinic3_eq *aeq = data;
+	struct hinic3_hwdev *hwdev;
+	struct hinic3_aeqs *aeqs;
+
+	aeqs = aeq_to_aeqs(aeq);
+	hwdev = aeq->hwdev;
+
+	/* clear resend timer cnt register */
+	workq = aeqs->workq;
+	hinic3_msix_intr_clear_resend_bit(hwdev, aeq->msix_entry_idx,
+					  EQ_MSIX_RESEND_TIMER_CLEAR);
+	queue_work(workq, &aeq->aeq_work);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ceq_interrupt(int irq, void *data)
+{
+	struct hinic3_eq *ceq = data;
+	int err;
+
+	/* clear resend timer counters */
+	hinic3_msix_intr_clear_resend_bit(ceq->hwdev, ceq->msix_entry_idx,
+					  EQ_MSIX_RESEND_TIMER_CLEAR);
+	err = eq_irq_handler(ceq);
+	if (err)
+		return IRQ_NONE;
+
+	return IRQ_HANDLED;
+}
+
+static int hinic3_set_ceq_ctrl_reg(struct hinic3_hwdev *hwdev, u16 q_id,
+				   u32 ctrl0, u32 ctrl1)
+{
+	struct comm_cmd_set_ceq_ctrl_reg ceq_ctrl = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	ceq_ctrl.func_id = hinic3_global_func_id(hwdev);
+	ceq_ctrl.q_id = q_id;
+	ceq_ctrl.ctrl0 = ctrl0;
+	ceq_ctrl.ctrl1 = ctrl1;
+
+	mgmt_msg_params_init_default(&msg_params, &ceq_ctrl, sizeof(ceq_ctrl));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_SET_CEQ_CTRL_REG, &msg_params);
+	if (err || ceq_ctrl.head.status) {
+		dev_err(hwdev->dev, "Failed to set ceq %u ctrl reg, err: %d status: 0x%x\n",
+			q_id, err, ceq_ctrl.head.status);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int set_eq_ctrls(struct hinic3_eq *eq)
+{
+	struct hinic3_hwif *hwif = eq->hwdev->hwif;
+	struct hinic3_queue_pages *qpages;
+	u8 pci_intf_idx, elem_size;
+	u32 mask, ctrl0, ctrl1;
+	u32 page_size_val;
+	int err;
+
+	qpages = &eq->qpages;
+	page_size_val = ilog2(qpages->page_size / HINIC3_MIN_PAGE_SIZE);
+	pci_intf_idx = hwif->attr.pci_intf_idx;
+
+	if (eq->type == HINIC3_AEQ) {
+		/* set ctrl0 using read-modify-write */
+		mask = AEQ_CTRL_0_INTR_IDX_MASK |
+		       AEQ_CTRL_0_DMA_ATTR_MASK |
+		       AEQ_CTRL_0_PCI_INTF_IDX_MASK |
+		       AEQ_CTRL_0_INTR_MODE_MASK;
+		ctrl0 = hinic3_hwif_read_reg(hwif, HINIC3_CSR_AEQ_CTRL_0_ADDR);
+		ctrl0 = (ctrl0 & ~mask) |
+			AEQ_CTRL_0_SET(eq->msix_entry_idx, INTR_IDX) |
+			AEQ_CTRL_0_SET(0, DMA_ATTR) |
+			AEQ_CTRL_0_SET(pci_intf_idx, PCI_INTF_IDX) |
+			AEQ_CTRL_0_SET(HINIC3_INTR_MODE_ARMED, INTR_MODE);
+		hinic3_hwif_write_reg(hwif, HINIC3_CSR_AEQ_CTRL_0_ADDR, ctrl0);
+
+		/* HW expects log2(number of 32 byte units). */
+		elem_size = qpages->elem_size_shift - 5;
+		ctrl1 = AEQ_CTRL_1_SET(eq->eq_len, LEN) |
+			AEQ_CTRL_1_SET(elem_size, ELEM_SIZE) |
+			AEQ_CTRL_1_SET(page_size_val, PAGE_SIZE);
+		hinic3_hwif_write_reg(hwif, HINIC3_CSR_AEQ_CTRL_1_ADDR, ctrl1);
+	} else {
+		ctrl0 = CEQ_CTRL_0_SET(eq->msix_entry_idx, INTR_IDX) |
+			CEQ_CTRL_0_SET(0, DMA_ATTR) |
+			CEQ_CTRL_0_SET(0, LIMIT_KICK) |
+			CEQ_CTRL_0_SET(pci_intf_idx, PCI_INTF_IDX) |
+			CEQ_CTRL_0_SET(page_size_val, PAGE_SIZE) |
+			CEQ_CTRL_0_SET(HINIC3_INTR_MODE_ARMED, INTR_MODE);
+
+		ctrl1 = CEQ_CTRL_1_SET(eq->eq_len, LEN);
+
+		/* set ceq ctrl reg through mgmt cpu */
+		err = hinic3_set_ceq_ctrl_reg(eq->hwdev, eq->q_id, ctrl0,
+					      ctrl1);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void ceq_elements_init(struct hinic3_eq *eq, u32 init_val)
+{
+	__be32 *ceqe;
+	u32 i;
+
+	for (i = 0; i < eq->eq_len; i++) {
+		ceqe = get_q_element(&eq->qpages, i, NULL);
+		*ceqe = cpu_to_be32(init_val);
+	}
+
+	wmb();    /* Clear ceq elements bit */
+}
+
+static void aeq_elements_init(struct hinic3_eq *eq, u32 init_val)
+{
+	struct hinic3_aeq_elem *aeqe;
+	u32 i;
+
+	for (i = 0; i < eq->eq_len; i++) {
+		aeqe = get_q_element(&eq->qpages, i, NULL);
+		aeqe->desc = cpu_to_be32(init_val);
+	}
+
+	wmb();    /* Clear aeq elements bit */
+}
+
+static void eq_elements_init(struct hinic3_eq *eq, u32 init_val)
+{
+	if (eq->type == HINIC3_AEQ)
+		aeq_elements_init(eq, init_val);
+	else
+		ceq_elements_init(eq, init_val);
+}
+
+static int alloc_eq_pages(struct hinic3_eq *eq)
+{
+	struct hinic3_hwif *hwif = eq->hwdev->hwif;
+	struct hinic3_queue_pages *qpages;
+	dma_addr_t page_paddr;
+	u32 reg, init_val;
+	u16 pg_idx;
+	int err;
+
+	qpages = &eq->qpages;
+	err = hinic3_queue_pages_alloc(eq->hwdev, qpages, HINIC3_MIN_PAGE_SIZE);
+	if (err)
+		return err;
+
+	for (pg_idx = 0; pg_idx < qpages->num_pages; pg_idx++) {
+		page_paddr = qpages->pages[pg_idx].align_paddr;
+		reg = EQ_HI_PHYS_ADDR_REG(eq->type, pg_idx);
+		hinic3_hwif_write_reg(hwif, reg, upper_32_bits(page_paddr));
+		reg = EQ_LO_PHYS_ADDR_REG(eq->type, pg_idx);
+		hinic3_hwif_write_reg(hwif, reg, lower_32_bits(page_paddr));
+	}
+
+	init_val = HINIC3_EQ_WRAPPED(eq);
+	eq_elements_init(eq, init_val);
+
+	return 0;
+}
+
+static void eq_calc_page_size_and_num(struct hinic3_eq *eq, u32 elem_size)
+{
+	u32 max_pages, min_page_size, page_size, total_size;
+
+	/* No need for complicated arithmetic. All values must be power of 2.
+	 * Multiplications give power of 2 and divisions give power of 2 without
+	 * remainder.
+	 */
+	max_pages = HINIC3_EQ_MAX_PAGES(eq);
+	min_page_size = HINIC3_MIN_PAGE_SIZE;
+	total_size = eq->eq_len * elem_size;
+
+	if (total_size <= max_pages * min_page_size)
+		page_size = min_page_size;
+	else
+		page_size = total_size / max_pages;
+
+	hinic3_queue_pages_init(&eq->qpages, eq->eq_len, page_size, elem_size);
+}
+
+static int request_eq_irq(struct hinic3_eq *eq)
+{
+	int err;
+
+	if (eq->type == HINIC3_AEQ) {
+		INIT_WORK(&eq->aeq_work, aeq_irq_work);
+		snprintf(eq->irq_name, sizeof(eq->irq_name),
+			 "hinic3_aeq%u@pci:%s", eq->q_id,
+			 pci_name(eq->hwdev->pdev));
+		err = request_irq(eq->irq_id, aeq_interrupt, 0,
+				  eq->irq_name, eq);
+	} else {
+		snprintf(eq->irq_name, sizeof(eq->irq_name),
+			 "hinic3_ceq%u@pci:%s", eq->q_id,
+			 pci_name(eq->hwdev->pdev));
+		err = request_threaded_irq(eq->irq_id, NULL, ceq_interrupt,
+					   IRQF_ONESHOT, eq->irq_name, eq);
+	}
+
+	return err;
+}
+
+static void reset_eq(struct hinic3_eq *eq)
+{
+	/* clear eq_len to force eqe drop in hardware */
+	if (eq->type == HINIC3_AEQ)
+		hinic3_hwif_write_reg(eq->hwdev->hwif,
+				      HINIC3_CSR_AEQ_CTRL_1_ADDR, 0);
+	else
+		hinic3_set_ceq_ctrl_reg(eq->hwdev, eq->q_id, 0, 0);
+
+	hinic3_hwif_write_reg(eq->hwdev->hwif, EQ_PROD_IDX_REG_ADDR(eq), 0);
+}
+
+static int init_eq(struct hinic3_eq *eq, struct hinic3_hwdev *hwdev, u16 q_id,
+		   u32 q_len, enum hinic3_eq_type type,
+		   struct msix_entry *msix_entry)
+{
+	u32 elem_size;
+	int err;
+
+	eq->hwdev = hwdev;
+	eq->q_id = q_id;
+	eq->type = type;
+	eq->eq_len = q_len;
+
+	/* Indirect access should set q_id first */
+	hinic3_hwif_write_reg(hwdev->hwif, HINIC3_EQ_INDIR_IDX_ADDR(eq->type),
+			      eq->q_id);
+
+	reset_eq(eq);
+
+	eq->cons_idx = 0;
+	eq->wrapped = 0;
+
+	elem_size = (type == HINIC3_AEQ) ? HINIC3_AEQE_SIZE : HINIC3_CEQE_SIZE;
+	eq_calc_page_size_and_num(eq, elem_size);
+
+	err = alloc_eq_pages(eq);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to allocate pages for eq\n");
+		return err;
+	}
+
+	eq->msix_entry_idx = msix_entry->entry;
+	eq->irq_id = msix_entry->vector;
+
+	err = set_eq_ctrls(eq);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set ctrls for eq\n");
+		goto err_free_queue_pages;
+	}
+
+	set_eq_cons_idx(eq, HINIC3_EQ_ARMED);
+
+	err = request_eq_irq(eq);
+	if (err) {
+		dev_err(hwdev->dev,
+			"Failed to request irq for the eq, err: %d\n", err);
+		goto err_free_queue_pages;
+	}
+
+	hinic3_set_msix_state(hwdev, eq->msix_entry_idx, HINIC3_MSIX_DISABLE);
+
+	return 0;
+
+err_free_queue_pages:
+	hinic3_queue_pages_free(hwdev, &eq->qpages);
+
+	return err;
+}
+
+static void remove_eq(struct hinic3_eq *eq)
+{
+	hinic3_set_msix_state(eq->hwdev, eq->msix_entry_idx,
+			      HINIC3_MSIX_DISABLE);
+	free_irq(eq->irq_id, eq);
+	/* Indirect access should set q_id first */
+	hinic3_hwif_write_reg(eq->hwdev->hwif,
+			      HINIC3_EQ_INDIR_IDX_ADDR(eq->type),
+			      eq->q_id);
+
+	if (eq->type == HINIC3_AEQ) {
+		disable_work_sync(&eq->aeq_work);
+		/* clear eq_len to avoid hw access host memory */
+		hinic3_hwif_write_reg(eq->hwdev->hwif,
+				      HINIC3_CSR_AEQ_CTRL_1_ADDR, 0);
+	} else {
+		hinic3_set_ceq_ctrl_reg(eq->hwdev, eq->q_id, 0, 0);
+	}
+
+	/* update consumer index to avoid invalid interrupt */
+	eq->cons_idx = hinic3_hwif_read_reg(eq->hwdev->hwif,
+					    EQ_PROD_IDX_REG_ADDR(eq));
+	set_eq_cons_idx(eq, HINIC3_EQ_NOT_ARMED);
+	hinic3_queue_pages_free(eq->hwdev, &eq->qpages);
+}
+
+int hinic3_aeqs_init(struct hinic3_hwdev *hwdev, u16 num_aeqs,
+		     struct msix_entry *msix_entries)
+{
+	struct hinic3_aeqs *aeqs;
+	u16 q_id;
+	int err;
+
+	aeqs = kzalloc(sizeof(*aeqs), GFP_KERNEL);
+	if (!aeqs)
+		return -ENOMEM;
+
+	hwdev->aeqs = aeqs;
+	aeqs->hwdev = hwdev;
+	aeqs->num_aeqs = num_aeqs;
+	aeqs->workq = alloc_workqueue(HINIC3_EQS_WQ_NAME, WQ_MEM_RECLAIM,
+				      HINIC3_MAX_AEQS);
+	if (!aeqs->workq) {
+		dev_err(hwdev->dev, "Failed to initialize aeq workqueue\n");
+		err = -ENOMEM;
+		goto err_free_aeqs;
+	}
+
+	for (q_id = 0; q_id < num_aeqs; q_id++) {
+		err = init_eq(&aeqs->aeq[q_id], hwdev, q_id,
+			      HINIC3_DEFAULT_AEQ_LEN, HINIC3_AEQ,
+			      &msix_entries[q_id]);
+		if (err) {
+			dev_err(hwdev->dev, "Failed to init aeq %u\n",
+				q_id);
+			goto err_remove_eqs;
+		}
+	}
+	for (q_id = 0; q_id < num_aeqs; q_id++)
+		hinic3_set_msix_state(hwdev, aeqs->aeq[q_id].msix_entry_idx,
+				      HINIC3_MSIX_ENABLE);
+
+	return 0;
+
+err_remove_eqs:
+	while (q_id > 0) {
+		q_id--;
+		remove_eq(&aeqs->aeq[q_id]);
+	}
+
+	destroy_workqueue(aeqs->workq);
+
+err_free_aeqs:
+	kfree(aeqs);
+
+	return err;
+}
+
+void hinic3_aeqs_free(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_aeqs *aeqs = hwdev->aeqs;
+	enum hinic3_aeq_type aeq_event;
+	struct hinic3_eq *eq;
+	u16 q_id;
+
+	for (q_id = 0; q_id < aeqs->num_aeqs; q_id++) {
+		eq = aeqs->aeq + q_id;
+		remove_eq(eq);
+		hinic3_free_irq(hwdev, eq->irq_id);
+	}
+
+	for (aeq_event = 0; aeq_event < HINIC3_MAX_AEQ_EVENTS; aeq_event++)
+		hinic3_aeq_unregister_cb(hwdev, aeq_event);
+
+	destroy_workqueue(aeqs->workq);
+
+	kfree(aeqs);
+}
+
+int hinic3_ceqs_init(struct hinic3_hwdev *hwdev, u16 num_ceqs,
+		     struct msix_entry *msix_entries)
+{
+	struct hinic3_ceqs *ceqs;
+	u16 q_id;
+	int err;
+
+	ceqs = kzalloc(sizeof(*ceqs), GFP_KERNEL);
+	if (!ceqs)
+		return -ENOMEM;
+
+	hwdev->ceqs = ceqs;
+	ceqs->hwdev = hwdev;
+	ceqs->num_ceqs = num_ceqs;
+
+	for (q_id = 0; q_id < num_ceqs; q_id++) {
+		err = init_eq(&ceqs->ceq[q_id], hwdev, q_id,
+			      HINIC3_DEFAULT_CEQ_LEN, HINIC3_CEQ,
+			      &msix_entries[q_id]);
+		if (err) {
+			dev_err(hwdev->dev, "Failed to init ceq %u\n",
+				q_id);
+			goto err_free_ceqs;
+		}
+	}
+	for (q_id = 0; q_id < num_ceqs; q_id++)
+		hinic3_set_msix_state(hwdev, ceqs->ceq[q_id].msix_entry_idx,
+				      HINIC3_MSIX_ENABLE);
+
+	return 0;
+
+err_free_ceqs:
+	while (q_id > 0) {
+		q_id--;
+		remove_eq(&ceqs->ceq[q_id]);
+	}
+
+	kfree(ceqs);
+
+	return err;
+}
+
+void hinic3_ceqs_free(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_ceqs *ceqs = hwdev->ceqs;
+	enum hinic3_ceq_event ceq_event;
+	struct hinic3_eq *eq;
+	u16 q_id;
+
+	for (q_id = 0; q_id < ceqs->num_ceqs; q_id++) {
+		eq = ceqs->ceq + q_id;
+		remove_eq(eq);
+		hinic3_free_irq(hwdev, eq->irq_id);
+	}
+
+	for (ceq_event = 0; ceq_event < HINIC3_MAX_CEQ_EVENTS; ceq_event++)
+		hinic3_ceq_unregister_cb(hwdev, ceq_event);
+
+	kfree(ceqs);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_eqs.h b/drivers/net/ethernet/huawei/hinic3/hinic3_eqs.h
new file mode 100644
index 000000000000..005a6e0745b3
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_eqs.h
@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_EQS_H_
+#define _HINIC3_EQS_H_
+
+#include <linux/interrupt.h>
+
+#include "hinic3_hw_cfg.h"
+#include "hinic3_queue_common.h"
+
+#define HINIC3_MAX_AEQS              4
+#define HINIC3_MAX_CEQS              32
+
+#define HINIC3_AEQ_MAX_PAGES         4
+#define HINIC3_CEQ_MAX_PAGES         8
+
+#define HINIC3_AEQE_SIZE             64
+#define HINIC3_CEQE_SIZE             4
+
+#define HINIC3_AEQE_DESC_SIZE        4
+#define HINIC3_AEQE_DATA_SIZE        (HINIC3_AEQE_SIZE - HINIC3_AEQE_DESC_SIZE)
+
+#define HINIC3_DEFAULT_AEQ_LEN       0x10000
+#define HINIC3_DEFAULT_CEQ_LEN       0x10000
+
+#define HINIC3_EQ_IRQ_NAME_LEN       64
+
+#define HINIC3_EQ_USLEEP_LOW_BOUND   900
+#define HINIC3_EQ_USLEEP_HIGH_BOUND  1000
+
+enum hinic3_eq_type {
+	HINIC3_AEQ = 0,
+	HINIC3_CEQ = 1,
+};
+
+enum hinic3_eq_intr_mode {
+	HINIC3_INTR_MODE_ARMED  = 0,
+	HINIC3_INTR_MODE_ALWAYS = 1,
+};
+
+enum hinic3_eq_ci_arm_state {
+	HINIC3_EQ_NOT_ARMED = 0,
+	HINIC3_EQ_ARMED     = 1,
+};
+
+struct hinic3_eq {
+	struct hinic3_hwdev       *hwdev;
+	struct hinic3_queue_pages qpages;
+	u16                       q_id;
+	enum hinic3_eq_type       type;
+	u32                       eq_len;
+	u32                       cons_idx;
+	u8                        wrapped;
+	u32                       irq_id;
+	u16                       msix_entry_idx;
+	char                      irq_name[HINIC3_EQ_IRQ_NAME_LEN];
+	struct work_struct        aeq_work;
+};
+
+struct hinic3_aeq_elem {
+	u8     aeqe_data[HINIC3_AEQE_DATA_SIZE];
+	__be32 desc;
+};
+
+enum hinic3_aeq_type {
+	HINIC3_HW_INTER_INT   = 0,
+	HINIC3_MBX_FROM_FUNC  = 1,
+	HINIC3_MSG_FROM_FW    = 2,
+	HINIC3_MAX_AEQ_EVENTS = 6,
+};
+
+typedef void (*hinic3_aeq_event_cb)(struct hinic3_hwdev *hwdev, u8 *data,
+				    u8 size);
+
+struct hinic3_aeqs {
+	struct hinic3_hwdev     *hwdev;
+	hinic3_aeq_event_cb     aeq_cb[HINIC3_MAX_AEQ_EVENTS];
+	struct hinic3_eq        aeq[HINIC3_MAX_AEQS];
+	u16                     num_aeqs;
+	struct workqueue_struct *workq;
+	/* lock for aeq event flag */
+	spinlock_t              aeq_lock;
+};
+
+enum hinic3_ceq_event {
+	HINIC3_CMDQ           = 3,
+	HINIC3_MAX_CEQ_EVENTS = 6,
+};
+
+typedef void (*hinic3_ceq_event_cb)(struct hinic3_hwdev *hwdev,
+				    __le32 ceqe_data);
+
+struct hinic3_ceqs {
+	struct hinic3_hwdev *hwdev;
+
+	hinic3_ceq_event_cb ceq_cb[HINIC3_MAX_CEQ_EVENTS];
+
+	struct hinic3_eq    ceq[HINIC3_MAX_CEQS];
+	u16                 num_ceqs;
+	/* lock for ceq event flag */
+	spinlock_t          ceq_lock;
+};
+
+int hinic3_aeqs_init(struct hinic3_hwdev *hwdev, u16 num_aeqs,
+		     struct msix_entry *msix_entries);
+void hinic3_aeqs_free(struct hinic3_hwdev *hwdev);
+int hinic3_aeq_register_cb(struct hinic3_hwdev *hwdev,
+			   enum hinic3_aeq_type event,
+			   hinic3_aeq_event_cb hwe_cb);
+void hinic3_aeq_unregister_cb(struct hinic3_hwdev *hwdev,
+			      enum hinic3_aeq_type event);
+int hinic3_ceqs_init(struct hinic3_hwdev *hwdev, u16 num_ceqs,
+		     struct msix_entry *msix_entries);
+void hinic3_ceqs_free(struct hinic3_hwdev *hwdev);
+int hinic3_ceq_register_cb(struct hinic3_hwdev *hwdev,
+			   enum hinic3_ceq_event event,
+			   hinic3_ceq_event_cb callback);
+void hinic3_ceq_unregister_cb(struct hinic3_hwdev *hwdev,
+			      enum hinic3_ceq_event event);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.c
new file mode 100644
index 000000000000..7827c1f626db
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.c
@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/device.h>
+
+#include "hinic3_hw_cfg.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+#define HINIC3_CFG_MAX_QP  256
+
+static void hinic3_parse_pub_res_cap(struct hinic3_hwdev *hwdev,
+				     struct hinic3_dev_cap *cap,
+				     const struct cfg_cmd_dev_cap *dev_cap,
+				     enum hinic3_func_type type)
+{
+	cap->port_id = dev_cap->port_id;
+	cap->supp_svcs_bitmap = dev_cap->svc_cap_en;
+}
+
+static void hinic3_parse_l2nic_res_cap(struct hinic3_hwdev *hwdev,
+				       struct hinic3_dev_cap *cap,
+				       const struct cfg_cmd_dev_cap *dev_cap,
+				       enum hinic3_func_type type)
+{
+	struct hinic3_nic_service_cap *nic_svc_cap = &cap->nic_svc_cap;
+
+	nic_svc_cap->max_sqs = min(dev_cap->nic_max_sq_id + 1,
+				   HINIC3_CFG_MAX_QP);
+}
+
+static void hinic3_parse_dev_cap(struct hinic3_hwdev *hwdev,
+				 const struct cfg_cmd_dev_cap *dev_cap,
+				 enum hinic3_func_type type)
+{
+	struct hinic3_dev_cap *cap = &hwdev->cfg_mgmt->cap;
+
+	/* Public resource */
+	hinic3_parse_pub_res_cap(hwdev, cap, dev_cap, type);
+
+	/* L2 NIC resource */
+	if (hinic3_support_nic(hwdev))
+		hinic3_parse_l2nic_res_cap(hwdev, cap, dev_cap, type);
+}
+
+static int get_cap_from_fw(struct hinic3_hwdev *hwdev,
+			   enum hinic3_func_type type)
+{
+	struct mgmt_msg_params msg_params = {};
+	struct cfg_cmd_dev_cap dev_cap = {};
+	int err;
+
+	dev_cap.func_id = hinic3_global_func_id(hwdev);
+
+	mgmt_msg_params_init_default(&msg_params, &dev_cap, sizeof(dev_cap));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_CFGM,
+				       CFG_CMD_GET_DEV_CAP, &msg_params);
+	if (err || dev_cap.head.status) {
+		dev_err(hwdev->dev,
+			"Failed to get capability from FW, err: %d, status: 0x%x\n",
+			err, dev_cap.head.status);
+		return -EIO;
+	}
+
+	hinic3_parse_dev_cap(hwdev, &dev_cap, type);
+
+	return 0;
+}
+
+static int hinic3_init_irq_info(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_cfg_mgmt_info *cfg_mgmt = hwdev->cfg_mgmt;
+	struct hinic3_hwif *hwif = hwdev->hwif;
+	u16 intr_num = hwif->attr.num_irqs;
+	struct hinic3_irq_info *irq_info;
+	u16 intr_needed;
+
+	intr_needed = hwif->attr.msix_flex_en ? (hwif->attr.num_aeqs +
+		      hwif->attr.num_ceqs + hwif->attr.num_sq) : intr_num;
+	if (intr_needed > intr_num) {
+		dev_warn(hwdev->dev, "Irq num cfg %d is less than the needed irq num %d msix_flex_en %d\n",
+			 intr_num, intr_needed, hwdev->hwif->attr.msix_flex_en);
+		intr_needed = intr_num;
+	}
+
+	irq_info = &cfg_mgmt->irq_info;
+	irq_info->irq = kcalloc(intr_num, sizeof(struct hinic3_irq),
+				GFP_KERNEL);
+	if (!irq_info->irq)
+		return -ENOMEM;
+
+	irq_info->num_irq_hw = intr_needed;
+	mutex_init(&irq_info->irq_mutex);
+
+	return 0;
+}
+
+static int hinic3_init_irq_alloc_info(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_cfg_mgmt_info *cfg_mgmt = hwdev->cfg_mgmt;
+	struct hinic3_irq *irq = cfg_mgmt->irq_info.irq;
+	u16 nreq = cfg_mgmt->irq_info.num_irq_hw;
+	struct pci_dev *pdev = hwdev->pdev;
+	int actual_irq;
+	u16 i;
+
+	actual_irq = pci_alloc_irq_vectors(pdev, 2, nreq, PCI_IRQ_MSIX);
+	if (actual_irq < 0) {
+		dev_err(hwdev->dev, "Alloc msix entries with threshold 2 failed. actual_irq: %d\n",
+			actual_irq);
+		return -ENOMEM;
+	}
+
+	nreq = actual_irq;
+	cfg_mgmt->irq_info.num_irq = nreq;
+
+	for (i = 0; i < nreq; ++i) {
+		irq[i].msix_entry_idx = i;
+		irq[i].irq_id = pci_irq_vector(pdev, i);
+		irq[i].allocated = false;
+	}
+
+	return 0;
+}
+
+int hinic3_init_cfg_mgmt(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_cfg_mgmt_info *cfg_mgmt;
+	int err;
+
+	cfg_mgmt = kzalloc(sizeof(*cfg_mgmt), GFP_KERNEL);
+	if (!cfg_mgmt)
+		return -ENOMEM;
+
+	hwdev->cfg_mgmt = cfg_mgmt;
+
+	err = hinic3_init_irq_info(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init hinic3_irq_mgmt_info, err: %d\n",
+			err);
+		goto err_free_cfg_mgmt;
+	}
+
+	err = hinic3_init_irq_alloc_info(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init hinic3_irq_info, err: %d\n",
+			err);
+		goto err_free_irq_info;
+	}
+
+	return 0;
+
+err_free_irq_info:
+	kfree(cfg_mgmt->irq_info.irq);
+	cfg_mgmt->irq_info.irq = NULL;
+err_free_cfg_mgmt:
+	kfree(cfg_mgmt);
+
+	return err;
+}
+
+void hinic3_free_cfg_mgmt(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_cfg_mgmt_info *cfg_mgmt = hwdev->cfg_mgmt;
+
+	pci_free_irq_vectors(hwdev->pdev);
+	kfree(cfg_mgmt->irq_info.irq);
+	cfg_mgmt->irq_info.irq = NULL;
+	kfree(cfg_mgmt);
+}
+
+int hinic3_alloc_irqs(struct hinic3_hwdev *hwdev, u16 num,
+		      struct msix_entry *alloc_arr, u16 *act_num)
+{
+	struct hinic3_irq_info *irq_info;
+	struct hinic3_irq *curr;
+	u16 i, found = 0;
+
+	irq_info = &hwdev->cfg_mgmt->irq_info;
+	mutex_lock(&irq_info->irq_mutex);
+	for (i = 0; i < irq_info->num_irq && found < num; i++) {
+		curr = irq_info->irq + i;
+		if (curr->allocated)
+			continue;
+		curr->allocated = true;
+		alloc_arr[found].vector = curr->irq_id;
+		alloc_arr[found].entry = curr->msix_entry_idx;
+		found++;
+	}
+	mutex_unlock(&irq_info->irq_mutex);
+
+	*act_num = found;
+
+	return found == 0 ? -ENOMEM : 0;
+}
+
+void hinic3_free_irq(struct hinic3_hwdev *hwdev, u32 irq_id)
+{
+	struct hinic3_irq_info *irq_info;
+	struct hinic3_irq *curr;
+	u16 i;
+
+	irq_info = &hwdev->cfg_mgmt->irq_info;
+	mutex_lock(&irq_info->irq_mutex);
+	for (i = 0; i < irq_info->num_irq; i++) {
+		curr = irq_info->irq + i;
+		if (curr->irq_id == irq_id) {
+			curr->allocated = false;
+			break;
+		}
+	}
+	mutex_unlock(&irq_info->irq_mutex);
+}
+
+int hinic3_init_capability(struct hinic3_hwdev *hwdev)
+{
+	return get_cap_from_fw(hwdev, HINIC3_FUNC_TYPE_VF);
+}
+
+bool hinic3_support_nic(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->cfg_mgmt->cap.supp_svcs_bitmap &
+	       BIT(HINIC3_SERVICE_T_NIC);
+}
+
+u16 hinic3_func_max_qnum(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->cfg_mgmt->cap.nic_svc_cap.max_sqs;
+}
+
+u8 hinic3_physical_port_id(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->cfg_mgmt->cap.port_id;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.h
new file mode 100644
index 000000000000..58806199bf54
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HW_CFG_H_
+#define _HINIC3_HW_CFG_H_
+
+#include <linux/mutex.h>
+#include <linux/pci.h>
+
+struct hinic3_hwdev;
+
+struct hinic3_irq {
+	u32  irq_id;
+	u16  msix_entry_idx;
+	bool allocated;
+};
+
+struct hinic3_irq_info {
+	struct hinic3_irq *irq;
+	u16               num_irq;
+	/* device max irq number */
+	u16               num_irq_hw;
+	/* protect irq alloc and free */
+	struct mutex      irq_mutex;
+};
+
+struct hinic3_nic_service_cap {
+	u16 max_sqs;
+};
+
+/* Device capabilities */
+struct hinic3_dev_cap {
+	/* Bitmasks of services supported by device */
+	u16                           supp_svcs_bitmap;
+	/* Physical port */
+	u8                            port_id;
+	struct hinic3_nic_service_cap nic_svc_cap;
+};
+
+struct hinic3_cfg_mgmt_info {
+	struct hinic3_irq_info irq_info;
+	struct hinic3_dev_cap  cap;
+};
+
+int hinic3_init_cfg_mgmt(struct hinic3_hwdev *hwdev);
+void hinic3_free_cfg_mgmt(struct hinic3_hwdev *hwdev);
+
+int hinic3_alloc_irqs(struct hinic3_hwdev *hwdev, u16 num,
+		      struct msix_entry *alloc_arr, u16 *act_num);
+void hinic3_free_irq(struct hinic3_hwdev *hwdev, u32 irq_id);
+
+int hinic3_init_capability(struct hinic3_hwdev *hwdev);
+bool hinic3_support_nic(struct hinic3_hwdev *hwdev);
+u16 hinic3_func_max_qnum(struct hinic3_hwdev *hwdev);
+u8 hinic3_physical_port_id(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.c
new file mode 100644
index 000000000000..89638813df40
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.c
@@ -0,0 +1,426 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/delay.h>
+
+#include "hinic3_cmdq.h"
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+int hinic3_set_interrupt_cfg_direct(struct hinic3_hwdev *hwdev,
+				    const struct hinic3_interrupt_info *info)
+{
+	struct comm_cmd_cfg_msix_ctrl_reg msix_cfg = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	msix_cfg.func_id = hinic3_global_func_id(hwdev);
+	msix_cfg.msix_index = info->msix_index;
+	msix_cfg.opcode = MGMT_MSG_CMD_OP_SET;
+
+	msix_cfg.lli_credit_cnt = info->lli_credit_limit;
+	msix_cfg.lli_timer_cnt = info->lli_timer_cfg;
+	msix_cfg.pending_cnt = info->pending_limit;
+	msix_cfg.coalesce_timer_cnt = info->coalesc_timer_cfg;
+	msix_cfg.resend_timer_cnt = info->resend_timer_cfg;
+
+	mgmt_msg_params_init_default(&msg_params, &msix_cfg, sizeof(msix_cfg));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_CFG_MSIX_CTRL_REG, &msg_params);
+	if (err || msix_cfg.head.status) {
+		dev_err(hwdev->dev,
+			"Failed to set interrupt config, err: %d, status: 0x%x\n",
+			err, msix_cfg.head.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int hinic3_func_reset(struct hinic3_hwdev *hwdev, u16 func_id, u64 reset_flag)
+{
+	struct comm_cmd_func_reset func_reset = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	func_reset.func_id = func_id;
+	func_reset.reset_flag = reset_flag;
+
+	mgmt_msg_params_init_default(&msg_params, &func_reset,
+				     sizeof(func_reset));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_FUNC_RESET, &msg_params);
+	if (err || func_reset.head.status) {
+		dev_err(hwdev->dev, "Failed to reset func resources, reset_flag 0x%llx, err: %d, status: 0x%x\n",
+			reset_flag, err, func_reset.head.status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int hinic3_comm_features_nego(struct hinic3_hwdev *hwdev, u8 opcode,
+				     u64 *s_feature, u16 size)
+{
+	struct comm_cmd_feature_nego feature_nego = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	feature_nego.func_id = hinic3_global_func_id(hwdev);
+	feature_nego.opcode = opcode;
+	if (opcode == MGMT_MSG_CMD_OP_SET)
+		memcpy(feature_nego.s_feature, s_feature,
+		       array_size(size, sizeof(u64)));
+
+	mgmt_msg_params_init_default(&msg_params, &feature_nego,
+				     sizeof(feature_nego));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_FEATURE_NEGO, &msg_params);
+	if (err || feature_nego.head.status) {
+		dev_err(hwdev->dev, "Failed to negotiate feature, err: %d, status: 0x%x\n",
+			err, feature_nego.head.status);
+		return -EINVAL;
+	}
+
+	if (opcode == MGMT_MSG_CMD_OP_GET)
+		memcpy(s_feature, feature_nego.s_feature,
+		       array_size(size, sizeof(u64)));
+
+	return 0;
+}
+
+int hinic3_get_comm_features(struct hinic3_hwdev *hwdev, u64 *s_feature,
+			     u16 size)
+{
+	return hinic3_comm_features_nego(hwdev, MGMT_MSG_CMD_OP_GET, s_feature,
+					 size);
+}
+
+int hinic3_set_comm_features(struct hinic3_hwdev *hwdev, u64 *s_feature,
+			     u16 size)
+{
+	return hinic3_comm_features_nego(hwdev, MGMT_MSG_CMD_OP_SET, s_feature,
+					 size);
+}
+
+int hinic3_get_global_attr(struct hinic3_hwdev *hwdev,
+			   struct comm_global_attr *attr)
+{
+	struct comm_cmd_get_glb_attr get_attr = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	mgmt_msg_params_init_default(&msg_params, &get_attr, sizeof(get_attr));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_GET_GLOBAL_ATTR, &msg_params);
+	if (err || get_attr.head.status) {
+		dev_err(hwdev->dev,
+			"Failed to get global attribute, err: %d, status: 0x%x\n",
+			err, get_attr.head.status);
+		return -EIO;
+	}
+
+	memcpy(attr, &get_attr.attr, sizeof(*attr));
+
+	return 0;
+}
+
+int hinic3_set_func_svc_used_state(struct hinic3_hwdev *hwdev, u16 svc_type,
+				   u8 state)
+{
+	struct comm_cmd_set_func_svc_used_state used_state = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	used_state.func_id = hinic3_global_func_id(hwdev);
+	used_state.svc_type = svc_type;
+	used_state.used_state = state;
+
+	mgmt_msg_params_init_default(&msg_params, &used_state,
+				     sizeof(used_state));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_SET_FUNC_SVC_USED_STATE,
+				       &msg_params);
+	if (err || used_state.head.status) {
+		dev_err(hwdev->dev,
+			"Failed to set func service used state, err: %d, status: 0x%x\n",
+			err, used_state.head.status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int hinic3_set_dma_attr_tbl(struct hinic3_hwdev *hwdev, u8 entry_idx, u8 st,
+			    u8 at, u8 ph, u8 no_snooping, u8 tph_en)
+{
+	struct comm_cmd_set_dma_attr dma_attr = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	dma_attr.func_id = hinic3_global_func_id(hwdev);
+	dma_attr.entry_idx = entry_idx;
+	dma_attr.st = st;
+	dma_attr.at = at;
+	dma_attr.ph = ph;
+	dma_attr.no_snooping = no_snooping;
+	dma_attr.tph_en = tph_en;
+
+	mgmt_msg_params_init_default(&msg_params, &dma_attr, sizeof(dma_attr));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_SET_DMA_ATTR, &msg_params);
+	if (err || dma_attr.head.status) {
+		dev_err(hwdev->dev, "Failed to set dma attr, err: %d, status: 0x%x\n",
+			err, dma_attr.head.status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int hinic3_set_wq_page_size(struct hinic3_hwdev *hwdev, u16 func_idx,
+			    u32 page_size)
+{
+	struct comm_cmd_cfg_wq_page_size page_size_info = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	page_size_info.func_id = func_idx;
+	page_size_info.page_size = ilog2(page_size / HINIC3_MIN_PAGE_SIZE);
+	page_size_info.opcode = MGMT_MSG_CMD_OP_SET;
+
+	mgmt_msg_params_init_default(&msg_params, &page_size_info,
+				     sizeof(page_size_info));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_CFG_PAGESIZE, &msg_params);
+	if (err || page_size_info.head.status) {
+		dev_err(hwdev->dev,
+			"Failed to set wq page size, err: %d, status: 0x%x\n",
+			err, page_size_info.head.status);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+int hinic3_set_cmdq_depth(struct hinic3_hwdev *hwdev, u16 cmdq_depth)
+{
+	struct comm_cmd_set_root_ctxt root_ctxt = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	root_ctxt.func_id = hinic3_global_func_id(hwdev);
+
+	root_ctxt.set_cmdq_depth = 1;
+	root_ctxt.cmdq_depth = ilog2(cmdq_depth);
+
+	mgmt_msg_params_init_default(&msg_params, &root_ctxt,
+				     sizeof(root_ctxt));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_SET_VAT, &msg_params);
+	if (err || root_ctxt.head.status) {
+		dev_err(hwdev->dev,
+			"Failed to set cmdq depth, err: %d, status: 0x%x\n",
+			err, root_ctxt.head.status);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+#define HINIC3_WAIT_CMDQ_IDLE_TIMEOUT    5000
+
+static enum hinic3_wait_return check_cmdq_stop_handler(void *priv_data)
+{
+	struct hinic3_hwdev *hwdev = priv_data;
+	enum hinic3_cmdq_type cmdq_type;
+	struct hinic3_cmdqs *cmdqs;
+
+	cmdqs = hwdev->cmdqs;
+	for (cmdq_type = 0; cmdq_type < cmdqs->cmdq_num; cmdq_type++) {
+		if (!hinic3_cmdq_idle(&cmdqs->cmdq[cmdq_type]))
+			return HINIC3_WAIT_PROCESS_WAITING;
+	}
+
+	return HINIC3_WAIT_PROCESS_CPL;
+}
+
+static int wait_cmdq_stop(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_cmdqs *cmdqs = hwdev->cmdqs;
+	enum hinic3_cmdq_type cmdq_type;
+	int err;
+
+	if (!(cmdqs->status & HINIC3_CMDQ_ENABLE))
+		return 0;
+
+	cmdqs->status &= ~HINIC3_CMDQ_ENABLE;
+	err = hinic3_wait_for_timeout(hwdev, check_cmdq_stop_handler,
+				      HINIC3_WAIT_CMDQ_IDLE_TIMEOUT,
+				      USEC_PER_MSEC);
+
+	if (err)
+		goto err_reenable_cmdq;
+
+	return 0;
+
+err_reenable_cmdq:
+	for (cmdq_type = 0; cmdq_type < cmdqs->cmdq_num; cmdq_type++) {
+		if (!hinic3_cmdq_idle(&cmdqs->cmdq[cmdq_type]))
+			dev_err(hwdev->dev, "Cmdq %d is busy\n", cmdq_type);
+	}
+	cmdqs->status |= HINIC3_CMDQ_ENABLE;
+
+	return err;
+}
+
+int hinic3_func_rx_tx_flush(struct hinic3_hwdev *hwdev)
+{
+	struct comm_cmd_clear_resource clear_db = {};
+	struct comm_cmd_clear_resource clr_res = {};
+	struct hinic3_hwif *hwif = hwdev->hwif;
+	struct mgmt_msg_params msg_params = {};
+	int ret = 0;
+	int err;
+
+	err = wait_cmdq_stop(hwdev);
+	if (err) {
+		dev_warn(hwdev->dev, "CMDQ is still working, CMDQ timeout value is unreasonable\n");
+		ret = err;
+	}
+
+	hinic3_toggle_doorbell(hwif, DISABLE_DOORBELL);
+
+	clear_db.func_id = hwif->attr.func_global_idx;
+	mgmt_msg_params_init_default(&msg_params, &clear_db, sizeof(clear_db));
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_FLUSH_DOORBELL, &msg_params);
+	if (err || clear_db.head.status) {
+		dev_warn(hwdev->dev, "Failed to flush doorbell, err: %d, status: 0x%x\n",
+			 err, clear_db.head.status);
+		if (err)
+			ret = err;
+		else
+			ret = -EFAULT;
+	}
+
+	clr_res.func_id = hwif->attr.func_global_idx;
+	msg_params.buf_in = &clr_res;
+	msg_params.in_size = sizeof(clr_res);
+	err = hinic3_send_mbox_to_mgmt_no_ack(hwdev, MGMT_MOD_COMM,
+					      COMM_CMD_START_FLUSH,
+					      &msg_params);
+	if (err) {
+		dev_warn(hwdev->dev, "Failed to notice flush message, err: %d\n",
+			 err);
+		ret = err;
+	}
+
+	hinic3_toggle_doorbell(hwif, ENABLE_DOORBELL);
+
+	err = hinic3_reinit_cmdq_ctxts(hwdev);
+	if (err) {
+		dev_warn(hwdev->dev, "Failed to reinit cmdq\n");
+		ret = err;
+	}
+
+	return ret;
+}
+
+static int get_hw_rx_buf_size_idx(int rx_buf_sz, u16 *buf_sz_idx)
+{
+	/* Supported RX buffer sizes in bytes. Configured by array index. */
+	static const int supported_sizes[16] = {
+		[0] = 32,     [1] = 64,     [2] = 96,     [3] = 128,
+		[4] = 192,    [5] = 256,    [6] = 384,    [7] = 512,
+		[8] = 768,    [9] = 1024,   [10] = 1536,  [11] = 2048,
+		[12] = 3072,  [13] = 4096,  [14] = 8192,  [15] = 16384,
+	};
+	u16 idx;
+
+	/* Scan from biggest to smallest. Choose supported size that is equal or
+	 * smaller. For smaller value HW will under-utilize posted buffers. For
+	 * bigger value HW may overrun posted buffers.
+	 */
+	idx = ARRAY_SIZE(supported_sizes);
+	while (idx > 0) {
+		idx--;
+		if (supported_sizes[idx] <= rx_buf_sz) {
+			*buf_sz_idx = idx;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+int hinic3_set_root_ctxt(struct hinic3_hwdev *hwdev, u32 rq_depth, u32 sq_depth,
+			 int rx_buf_sz)
+{
+	struct comm_cmd_set_root_ctxt root_ctxt = {};
+	struct mgmt_msg_params msg_params = {};
+	u16 buf_sz_idx;
+	int err;
+
+	err = get_hw_rx_buf_size_idx(rx_buf_sz, &buf_sz_idx);
+	if (err)
+		return err;
+
+	root_ctxt.func_id = hinic3_global_func_id(hwdev);
+
+	root_ctxt.set_cmdq_depth = 0;
+	root_ctxt.cmdq_depth = 0;
+
+	root_ctxt.lro_en = 1;
+
+	root_ctxt.rq_depth  = ilog2(rq_depth);
+	root_ctxt.rx_buf_sz = buf_sz_idx;
+	root_ctxt.sq_depth  = ilog2(sq_depth);
+
+	mgmt_msg_params_init_default(&msg_params, &root_ctxt,
+				     sizeof(root_ctxt));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_SET_VAT, &msg_params);
+	if (err || root_ctxt.head.status) {
+		dev_err(hwdev->dev,
+			"Failed to set root context, err: %d, status: 0x%x\n",
+			err, root_ctxt.head.status);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+int hinic3_clean_root_ctxt(struct hinic3_hwdev *hwdev)
+{
+	struct comm_cmd_set_root_ctxt root_ctxt = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	root_ctxt.func_id = hinic3_global_func_id(hwdev);
+
+	mgmt_msg_params_init_default(&msg_params, &root_ctxt,
+				     sizeof(root_ctxt));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_SET_VAT, &msg_params);
+	if (err || root_ctxt.head.status) {
+		dev_err(hwdev->dev,
+			"Failed to set root context, err: %d, status: 0x%x\n",
+			err, root_ctxt.head.status);
+		return -EFAULT;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.h
new file mode 100644
index 000000000000..304f5691f0c2
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HW_COMM_H_
+#define _HINIC3_HW_COMM_H_
+
+#include "hinic3_hw_intf.h"
+
+struct hinic3_hwdev;
+
+#define HINIC3_WQ_PAGE_SIZE_ORDER  8
+
+struct hinic3_interrupt_info {
+	u32 lli_set;
+	u32 interrupt_coalesc_set;
+	u16 msix_index;
+	u8  lli_credit_limit;
+	u8  lli_timer_cfg;
+	u8  pending_limit;
+	u8  coalesc_timer_cfg;
+	u8  resend_timer_cfg;
+};
+
+int hinic3_set_interrupt_cfg_direct(struct hinic3_hwdev *hwdev,
+				    const struct hinic3_interrupt_info *info);
+int hinic3_func_reset(struct hinic3_hwdev *hwdev, u16 func_id, u64 reset_flag);
+
+int hinic3_get_comm_features(struct hinic3_hwdev *hwdev, u64 *s_feature,
+			     u16 size);
+int hinic3_set_comm_features(struct hinic3_hwdev *hwdev, u64 *s_feature,
+			     u16 size);
+int hinic3_get_global_attr(struct hinic3_hwdev *hwdev,
+			   struct comm_global_attr *attr);
+int hinic3_set_func_svc_used_state(struct hinic3_hwdev *hwdev, u16 svc_type,
+				   u8 state);
+int hinic3_set_dma_attr_tbl(struct hinic3_hwdev *hwdev, u8 entry_idx, u8 st,
+			    u8 at, u8 ph, u8 no_snooping, u8 tph_en);
+
+int hinic3_set_wq_page_size(struct hinic3_hwdev *hwdev, u16 func_idx,
+			    u32 page_size);
+int hinic3_set_cmdq_depth(struct hinic3_hwdev *hwdev, u16 cmdq_depth);
+int hinic3_func_rx_tx_flush(struct hinic3_hwdev *hwdev);
+int hinic3_set_root_ctxt(struct hinic3_hwdev *hwdev, u32 rq_depth, u32 sq_depth,
+			 int rx_buf_sz);
+int hinic3_clean_root_ctxt(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_intf.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_intf.h
new file mode 100644
index 000000000000..623cf2d14cbc
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_intf.h
@@ -0,0 +1,264 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HW_INTF_H_
+#define _HINIC3_HW_INTF_H_
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+#define MGMT_MSG_CMD_OP_SET   1
+#define MGMT_MSG_CMD_OP_GET   0
+
+#define MGMT_STATUS_PF_SET_VF_ALREADY  0x4
+#define MGMT_STATUS_EXIST              0x6
+#define MGMT_STATUS_CMD_UNSUPPORTED    0xFF
+
+#define MGMT_MSG_POLLING_TIMEOUT 0
+
+struct mgmt_msg_head {
+	u8 status;
+	u8 version;
+	u8 rsvd0[6];
+};
+
+struct mgmt_msg_params {
+	const void  *buf_in;
+	u32         in_size;
+	void        *buf_out;
+	u32         expected_out_size;
+	u32         timeout_ms;
+};
+
+/* CMDQ MODULE_TYPE */
+enum mgmt_mod_type {
+	/* HW communication module */
+	MGMT_MOD_COMM   = 0,
+	/* L2NIC module */
+	MGMT_MOD_L2NIC  = 1,
+	/* Configuration module */
+	MGMT_MOD_CFGM   = 7,
+	MGMT_MOD_HILINK = 14,
+};
+
+static inline void mgmt_msg_params_init_default(struct mgmt_msg_params *msg_params,
+						void *inout_buf, u32 buf_size)
+{
+	msg_params->buf_in = inout_buf;
+	msg_params->buf_out = inout_buf;
+	msg_params->in_size = buf_size;
+	msg_params->expected_out_size = buf_size;
+	msg_params->timeout_ms = 0;
+}
+
+enum cfg_cmd {
+	CFG_CMD_GET_DEV_CAP = 0,
+};
+
+/* Device capabilities, defined by hw */
+struct cfg_cmd_dev_cap {
+	struct mgmt_msg_head head;
+
+	u16                  func_id;
+	u16                  rsvd1;
+
+	/* Public resources */
+	u8                   host_id;
+	u8                   ep_id;
+	u8                   er_id;
+	u8                   port_id;
+
+	u16                  host_total_func;
+	u8                   host_pf_num;
+	u8                   pf_id_start;
+	u16                  host_vf_num;
+	u16                  vf_id_start;
+	u8                   host_oq_id_mask_val;
+	u8                   timer_en;
+	u8                   host_valid_bitmap;
+	u8                   rsvd_host;
+
+	u16                  svc_cap_en;
+	u16                  max_vf;
+	u8                   flexq_en;
+	u8                   valid_cos_bitmap;
+	u8                   port_cos_valid_bitmap;
+	u8                   rsvd2[45];
+
+	/* l2nic */
+	u16                  nic_max_sq_id;
+	u16                  nic_max_rq_id;
+	u16                  nic_default_num_queues;
+
+	u8                   rsvd3[250];
+};
+
+/* COMM Commands between Driver to fw */
+enum comm_cmd {
+	/* Commands for clearing FLR and resources */
+	COMM_CMD_FUNC_RESET              = 0,
+	COMM_CMD_FEATURE_NEGO            = 1,
+	COMM_CMD_FLUSH_DOORBELL          = 2,
+	COMM_CMD_START_FLUSH             = 3,
+	COMM_CMD_GET_GLOBAL_ATTR         = 5,
+	COMM_CMD_SET_FUNC_SVC_USED_STATE = 7,
+
+	/* Driver Configuration Commands */
+	COMM_CMD_SET_CMDQ_CTXT           = 20,
+	COMM_CMD_SET_VAT                 = 21,
+	COMM_CMD_CFG_PAGESIZE            = 22,
+	COMM_CMD_CFG_MSIX_CTRL_REG       = 23,
+	COMM_CMD_SET_CEQ_CTRL_REG        = 24,
+	COMM_CMD_SET_DMA_ATTR            = 25,
+};
+
+struct comm_cmd_cfg_msix_ctrl_reg {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u8                   opcode;
+	u8                   rsvd1;
+	u16                  msix_index;
+	u8                   pending_cnt;
+	u8                   coalesce_timer_cnt;
+	u8                   resend_timer_cnt;
+	u8                   lli_timer_cnt;
+	u8                   lli_credit_cnt;
+	u8                   rsvd2[5];
+};
+
+enum comm_func_reset_bits {
+	COMM_FUNC_RESET_BIT_FLUSH        = BIT(0),
+	COMM_FUNC_RESET_BIT_MQM          = BIT(1),
+	COMM_FUNC_RESET_BIT_SMF          = BIT(2),
+	COMM_FUNC_RESET_BIT_PF_BW_CFG    = BIT(3),
+
+	COMM_FUNC_RESET_BIT_COMM         = BIT(10),
+	/* clear mbox and aeq, The COMM_FUNC_RESET_BIT_COMM bit must be set */
+	COMM_FUNC_RESET_BIT_COMM_MGMT_CH = BIT(11),
+	/* clear cmdq and ceq, The COMM_FUNC_RESET_BIT_COMM bit must be set */
+	COMM_FUNC_RESET_BIT_COMM_CMD_CH  = BIT(12),
+	COMM_FUNC_RESET_BIT_NIC          = BIT(13),
+};
+
+#define COMM_FUNC_RESET_FLAG \
+	(COMM_FUNC_RESET_BIT_COMM | COMM_FUNC_RESET_BIT_COMM_CMD_CH | \
+	 COMM_FUNC_RESET_BIT_FLUSH | COMM_FUNC_RESET_BIT_MQM | \
+	 COMM_FUNC_RESET_BIT_SMF | COMM_FUNC_RESET_BIT_PF_BW_CFG)
+
+struct comm_cmd_func_reset {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u16                  rsvd1[3];
+	u64                  reset_flag;
+};
+
+#define COMM_MAX_FEATURE_QWORD  4
+struct comm_cmd_feature_nego {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u8                   opcode;
+	u8                   rsvd;
+	u64                  s_feature[COMM_MAX_FEATURE_QWORD];
+};
+
+struct comm_global_attr {
+	u8  max_host_num;
+	u8  max_pf_num;
+	u16 vf_id_start;
+	/* for api cmd to mgmt cpu */
+	u8  mgmt_host_node_id;
+	u8  cmdq_num;
+	u8  rsvd1[34];
+};
+
+struct comm_cmd_get_glb_attr {
+	struct mgmt_msg_head    head;
+	struct comm_global_attr attr;
+};
+
+enum comm_func_svc_type {
+	COMM_FUNC_SVC_T_COMM = 0,
+	COMM_FUNC_SVC_T_NIC  = 1,
+};
+
+struct comm_cmd_set_func_svc_used_state {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u16                  svc_type;
+	u8                   used_state;
+	u8                   rsvd[35];
+};
+
+struct comm_cmd_set_dma_attr {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u8                   entry_idx;
+	u8                   st;
+	u8                   at;
+	u8                   ph;
+	u8                   no_snooping;
+	u8                   tph_en;
+	u32                  resv1;
+};
+
+struct comm_cmd_set_ceq_ctrl_reg {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u16                  q_id;
+	u32                  ctrl0;
+	u32                  ctrl1;
+	u32                  rsvd1;
+};
+
+struct comm_cmd_cfg_wq_page_size {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u8                   opcode;
+	/* real_size=4KB*2^page_size, range(0~20) must be checked by driver */
+	u8                   page_size;
+	u32                  rsvd1;
+};
+
+struct comm_cmd_set_root_ctxt {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u8                   set_cmdq_depth;
+	u8                   cmdq_depth;
+	u16                  rx_buf_sz;
+	u8                   lro_en;
+	u8                   rsvd1;
+	u16                  sq_depth;
+	u16                  rq_depth;
+	u64                  rsvd2;
+};
+
+struct comm_cmdq_ctxt_info {
+	__le64 curr_wqe_page_pfn;
+	__le64 wq_block_pfn;
+};
+
+struct comm_cmd_set_cmdq_ctxt {
+	struct mgmt_msg_head       head;
+	u16                        func_id;
+	u8                         cmdq_id;
+	u8                         rsvd1[5];
+	struct comm_cmdq_ctxt_info ctxt;
+};
+
+struct comm_cmd_clear_resource {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u16                  rsvd1[3];
+};
+
+/* Services supported by HW. HW uses these values when delivering events.
+ * HW supports multiple services that are not yet supported by driver
+ * (e.g. RoCE).
+ */
+enum hinic3_service_type {
+	HINIC3_SERVICE_T_NIC = 0,
+	/* MAX is only used by SW for array sizes. */
+	HINIC3_SERVICE_T_MAX = 1,
+};
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.c
new file mode 100644
index 000000000000..95a213133be9
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.c
@@ -0,0 +1,557 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include "hinic3_cmdq.h"
+#include "hinic3_csr.h"
+#include "hinic3_eqs.h"
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+#include "hinic3_mgmt.h"
+
+#define HINIC3_PCIE_SNOOP        0
+#define HINIC3_PCIE_TPH_DISABLE  0
+
+#define HINIC3_DMA_ATTR_INDIR_IDX_MASK          GENMASK(9, 0)
+#define HINIC3_DMA_ATTR_INDIR_IDX_SET(val, member)  \
+	FIELD_PREP(HINIC3_DMA_ATTR_INDIR_##member##_MASK, val)
+
+#define HINIC3_DMA_ATTR_ENTRY_ST_MASK           GENMASK(7, 0)
+#define HINIC3_DMA_ATTR_ENTRY_AT_MASK           GENMASK(9, 8)
+#define HINIC3_DMA_ATTR_ENTRY_PH_MASK           GENMASK(11, 10)
+#define HINIC3_DMA_ATTR_ENTRY_NO_SNOOPING_MASK  BIT(12)
+#define HINIC3_DMA_ATTR_ENTRY_TPH_EN_MASK       BIT(13)
+#define HINIC3_DMA_ATTR_ENTRY_SET(val, member)  \
+	FIELD_PREP(HINIC3_DMA_ATTR_ENTRY_##member##_MASK, val)
+
+#define HINIC3_PCIE_ST_DISABLE       0
+#define HINIC3_PCIE_AT_DISABLE       0
+#define HINIC3_PCIE_PH_DISABLE       0
+#define HINIC3_PCIE_MSIX_ATTR_ENTRY  0
+
+#define HINIC3_DEFAULT_EQ_MSIX_PENDING_LIMIT      0
+#define HINIC3_DEFAULT_EQ_MSIX_COALESC_TIMER_CFG  0xFF
+#define HINIC3_DEFAULT_EQ_MSIX_RESEND_TIMER_CFG   7
+
+#define HINIC3_HWDEV_WQ_NAME    "hinic3_hardware"
+#define HINIC3_WQ_MAX_REQ       10
+
+enum hinic3_hwdev_init_state {
+	HINIC3_HWDEV_MBOX_INITED = 2,
+	HINIC3_HWDEV_CMDQ_INITED = 3,
+};
+
+static int hinic3_comm_aeqs_init(struct hinic3_hwdev *hwdev)
+{
+	struct msix_entry aeq_msix_entries[HINIC3_MAX_AEQS];
+	u16 num_aeqs, resp_num_irq, i;
+	int err;
+
+	num_aeqs = hwdev->hwif->attr.num_aeqs;
+	if (num_aeqs > HINIC3_MAX_AEQS) {
+		dev_warn(hwdev->dev, "Adjust aeq num to %d\n",
+			 HINIC3_MAX_AEQS);
+		num_aeqs = HINIC3_MAX_AEQS;
+	}
+	err = hinic3_alloc_irqs(hwdev, num_aeqs, aeq_msix_entries,
+				&resp_num_irq);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc aeq irqs, num_aeqs: %u\n",
+			num_aeqs);
+		return err;
+	}
+
+	if (resp_num_irq < num_aeqs) {
+		dev_warn(hwdev->dev, "Adjust aeq num to %u\n",
+			 resp_num_irq);
+		num_aeqs = resp_num_irq;
+	}
+
+	err = hinic3_aeqs_init(hwdev, num_aeqs, aeq_msix_entries);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init aeqs\n");
+		goto err_free_irqs;
+	}
+
+	return 0;
+
+err_free_irqs:
+	for (i = 0; i < num_aeqs; i++)
+		hinic3_free_irq(hwdev, aeq_msix_entries[i].vector);
+
+	return err;
+}
+
+static int hinic3_comm_ceqs_init(struct hinic3_hwdev *hwdev)
+{
+	struct msix_entry ceq_msix_entries[HINIC3_MAX_CEQS];
+	u16 num_ceqs, resp_num_irq, i;
+	int err;
+
+	num_ceqs = hwdev->hwif->attr.num_ceqs;
+	if (num_ceqs > HINIC3_MAX_CEQS) {
+		dev_warn(hwdev->dev, "Adjust ceq num to %d\n",
+			 HINIC3_MAX_CEQS);
+		num_ceqs = HINIC3_MAX_CEQS;
+	}
+
+	err = hinic3_alloc_irqs(hwdev, num_ceqs, ceq_msix_entries,
+				&resp_num_irq);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc ceq irqs, num_ceqs: %u\n",
+			num_ceqs);
+		return err;
+	}
+
+	if (resp_num_irq < num_ceqs) {
+		dev_warn(hwdev->dev, "Adjust ceq num to %u\n",
+			 resp_num_irq);
+		num_ceqs = resp_num_irq;
+	}
+
+	err = hinic3_ceqs_init(hwdev, num_ceqs, ceq_msix_entries);
+	if (err) {
+		dev_err(hwdev->dev,
+			"Failed to init ceqs, err:%d\n", err);
+		goto err_free_irqs;
+	}
+
+	return 0;
+
+err_free_irqs:
+	for (i = 0; i < num_ceqs; i++)
+		hinic3_free_irq(hwdev, ceq_msix_entries[i].vector);
+
+	return err;
+}
+
+static int hinic3_comm_mbox_init(struct hinic3_hwdev *hwdev)
+{
+	int err;
+
+	err = hinic3_init_mbox(hwdev);
+	if (err)
+		return err;
+
+	hinic3_aeq_register_cb(hwdev, HINIC3_MBX_FROM_FUNC,
+			       hinic3_mbox_func_aeqe_handler);
+	hinic3_aeq_register_cb(hwdev, HINIC3_MSG_FROM_FW,
+			       hinic3_mgmt_msg_aeqe_handler);
+
+	set_bit(HINIC3_HWDEV_MBOX_INITED, &hwdev->func_state);
+
+	return 0;
+}
+
+static void hinic3_comm_mbox_free(struct hinic3_hwdev *hwdev)
+{
+	spin_lock_bh(&hwdev->channel_lock);
+	clear_bit(HINIC3_HWDEV_MBOX_INITED, &hwdev->func_state);
+	spin_unlock_bh(&hwdev->channel_lock);
+	hinic3_aeq_unregister_cb(hwdev, HINIC3_MBX_FROM_FUNC);
+	hinic3_aeq_unregister_cb(hwdev, HINIC3_MSG_FROM_FW);
+	hinic3_free_mbox(hwdev);
+}
+
+static int init_aeqs_msix_attr(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_aeqs *aeqs = hwdev->aeqs;
+	struct hinic3_interrupt_info info = {};
+	struct hinic3_eq *eq;
+	u16 q_id;
+	int err;
+
+	info.interrupt_coalesc_set = 1;
+	info.pending_limit = HINIC3_DEFAULT_EQ_MSIX_PENDING_LIMIT;
+	info.coalesc_timer_cfg = HINIC3_DEFAULT_EQ_MSIX_COALESC_TIMER_CFG;
+	info.resend_timer_cfg = HINIC3_DEFAULT_EQ_MSIX_RESEND_TIMER_CFG;
+
+	for (q_id = 0; q_id < aeqs->num_aeqs; q_id++) {
+		eq = &aeqs->aeq[q_id];
+		info.msix_index = eq->msix_entry_idx;
+		err = hinic3_set_interrupt_cfg_direct(hwdev, &info);
+		if (err) {
+			dev_err(hwdev->dev, "Set msix attr for aeq %d failed\n",
+				q_id);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int init_ceqs_msix_attr(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_ceqs *ceqs = hwdev->ceqs;
+	struct hinic3_interrupt_info info = {};
+	struct hinic3_eq *eq;
+	u16 q_id;
+	int err;
+
+	info.interrupt_coalesc_set = 1;
+	info.pending_limit = HINIC3_DEFAULT_EQ_MSIX_PENDING_LIMIT;
+	info.coalesc_timer_cfg = HINIC3_DEFAULT_EQ_MSIX_COALESC_TIMER_CFG;
+	info.resend_timer_cfg = HINIC3_DEFAULT_EQ_MSIX_RESEND_TIMER_CFG;
+
+	for (q_id = 0; q_id < ceqs->num_ceqs; q_id++) {
+		eq = &ceqs->ceq[q_id];
+		info.msix_index = eq->msix_entry_idx;
+		err = hinic3_set_interrupt_cfg_direct(hwdev, &info);
+		if (err) {
+			dev_err(hwdev->dev, "Set msix attr for ceq %u failed\n",
+				q_id);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int init_basic_mgmt_channel(struct hinic3_hwdev *hwdev)
+{
+	int err;
+
+	err = hinic3_comm_aeqs_init(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init async event queues\n");
+		return err;
+	}
+
+	err = hinic3_comm_mbox_init(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init mailbox\n");
+		goto err_free_comm_aeqs;
+	}
+
+	err = init_aeqs_msix_attr(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init aeqs msix attr\n");
+		goto err_free_comm_mbox;
+	}
+
+	return 0;
+
+err_free_comm_mbox:
+	hinic3_comm_mbox_free(hwdev);
+err_free_comm_aeqs:
+	hinic3_aeqs_free(hwdev);
+
+	return err;
+}
+
+static void free_base_mgmt_channel(struct hinic3_hwdev *hwdev)
+{
+	hinic3_comm_mbox_free(hwdev);
+	hinic3_aeqs_free(hwdev);
+}
+
+static int dma_attr_table_init(struct hinic3_hwdev *hwdev)
+{
+	u32 addr, val, dst_attr;
+
+	/* Indirect access, set entry_idx first */
+	addr = HINIC3_CSR_DMA_ATTR_INDIR_IDX_ADDR;
+	val = hinic3_hwif_read_reg(hwdev->hwif, addr);
+	val &= ~HINIC3_DMA_ATTR_ENTRY_AT_MASK;
+	val |= HINIC3_DMA_ATTR_INDIR_IDX_SET(HINIC3_PCIE_MSIX_ATTR_ENTRY, IDX);
+	hinic3_hwif_write_reg(hwdev->hwif, addr, val);
+
+	addr = HINIC3_CSR_DMA_ATTR_TBL_ADDR;
+	val = hinic3_hwif_read_reg(hwdev->hwif, addr);
+
+	dst_attr = HINIC3_DMA_ATTR_ENTRY_SET(HINIC3_PCIE_ST_DISABLE, ST) |
+		   HINIC3_DMA_ATTR_ENTRY_SET(HINIC3_PCIE_AT_DISABLE, AT) |
+		   HINIC3_DMA_ATTR_ENTRY_SET(HINIC3_PCIE_PH_DISABLE, PH) |
+		   HINIC3_DMA_ATTR_ENTRY_SET(HINIC3_PCIE_SNOOP, NO_SNOOPING) |
+		   HINIC3_DMA_ATTR_ENTRY_SET(HINIC3_PCIE_TPH_DISABLE, TPH_EN);
+	if (val == dst_attr)
+		return 0;
+
+	return hinic3_set_dma_attr_tbl(hwdev,
+				       HINIC3_PCIE_MSIX_ATTR_ENTRY,
+				       HINIC3_PCIE_ST_DISABLE,
+				       HINIC3_PCIE_AT_DISABLE,
+				       HINIC3_PCIE_PH_DISABLE,
+				       HINIC3_PCIE_SNOOP,
+				       HINIC3_PCIE_TPH_DISABLE);
+}
+
+static int init_basic_attributes(struct hinic3_hwdev *hwdev)
+{
+	struct comm_global_attr glb_attr;
+	int err;
+
+	err = hinic3_func_reset(hwdev, hinic3_global_func_id(hwdev),
+				COMM_FUNC_RESET_FLAG);
+	if (err)
+		return err;
+
+	err = hinic3_get_comm_features(hwdev, hwdev->features,
+				       COMM_MAX_FEATURE_QWORD);
+	if (err)
+		return err;
+
+	dev_dbg(hwdev->dev, "Comm hw features: 0x%llx\n", hwdev->features[0]);
+
+	err = hinic3_get_global_attr(hwdev, &glb_attr);
+	if (err)
+		return err;
+
+	err = hinic3_set_func_svc_used_state(hwdev, COMM_FUNC_SVC_T_COMM, 1);
+	if (err)
+		return err;
+
+	err = dma_attr_table_init(hwdev);
+	if (err)
+		return err;
+
+	hwdev->max_cmdq = min(glb_attr.cmdq_num, HINIC3_MAX_CMDQ_TYPES);
+	dev_dbg(hwdev->dev,
+		"global attribute: max_host: 0x%x, max_pf: 0x%x, vf_id_start: 0x%x, mgmt node id: 0x%x, cmdq_num: 0x%x\n",
+		glb_attr.max_host_num, glb_attr.max_pf_num,
+		glb_attr.vf_id_start, glb_attr.mgmt_host_node_id,
+		glb_attr.cmdq_num);
+
+	return 0;
+}
+
+static int hinic3_comm_cmdqs_init(struct hinic3_hwdev *hwdev)
+{
+	int err;
+
+	err = hinic3_cmdqs_init(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init cmd queues\n");
+		return err;
+	}
+
+	hinic3_ceq_register_cb(hwdev, HINIC3_CMDQ, hinic3_cmdq_ceq_handler);
+
+	err = hinic3_set_cmdq_depth(hwdev, CMDQ_DEPTH);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set cmdq depth\n");
+		goto err_free_cmdqs;
+	}
+
+	set_bit(HINIC3_HWDEV_CMDQ_INITED, &hwdev->func_state);
+
+	return 0;
+
+err_free_cmdqs:
+	hinic3_cmdqs_free(hwdev);
+
+	return err;
+}
+
+static void hinic3_comm_cmdqs_free(struct hinic3_hwdev *hwdev)
+{
+	spin_lock_bh(&hwdev->channel_lock);
+	clear_bit(HINIC3_HWDEV_CMDQ_INITED, &hwdev->func_state);
+	spin_unlock_bh(&hwdev->channel_lock);
+
+	hinic3_ceq_unregister_cb(hwdev, HINIC3_CMDQ);
+	hinic3_cmdqs_free(hwdev);
+}
+
+static int init_cmdqs_channel(struct hinic3_hwdev *hwdev)
+{
+	int err;
+
+	err = hinic3_comm_ceqs_init(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init completion event queues\n");
+		return err;
+	}
+
+	err = init_ceqs_msix_attr(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init ceqs msix attr\n");
+		goto err_free_ceqs;
+	}
+
+	hwdev->wq_page_size = HINIC3_MIN_PAGE_SIZE << HINIC3_WQ_PAGE_SIZE_ORDER;
+	err = hinic3_set_wq_page_size(hwdev, hinic3_global_func_id(hwdev),
+				      hwdev->wq_page_size);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set wq page size\n");
+		goto err_free_ceqs;
+	}
+
+	err = hinic3_comm_cmdqs_init(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init cmd queues\n");
+		goto err_reset_wq_page_size;
+	}
+
+	return 0;
+
+err_reset_wq_page_size:
+	hinic3_set_wq_page_size(hwdev, hinic3_global_func_id(hwdev),
+				HINIC3_MIN_PAGE_SIZE);
+err_free_ceqs:
+	hinic3_ceqs_free(hwdev);
+
+	return err;
+}
+
+static void hinic3_free_cmdqs_channel(struct hinic3_hwdev *hwdev)
+{
+	hinic3_comm_cmdqs_free(hwdev);
+	hinic3_ceqs_free(hwdev);
+}
+
+static int hinic3_init_comm_ch(struct hinic3_hwdev *hwdev)
+{
+	int err;
+
+	err = init_basic_mgmt_channel(hwdev);
+	if (err)
+		return err;
+
+	err = init_basic_attributes(hwdev);
+	if (err)
+		goto err_free_basic_mgmt_ch;
+
+	err = init_cmdqs_channel(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init cmdq channel\n");
+		goto err_clear_func_svc_used_state;
+	}
+
+	return 0;
+
+err_clear_func_svc_used_state:
+	hinic3_set_func_svc_used_state(hwdev, COMM_FUNC_SVC_T_COMM, 0);
+err_free_basic_mgmt_ch:
+	free_base_mgmt_channel(hwdev);
+
+	return err;
+}
+
+static void hinic3_uninit_comm_ch(struct hinic3_hwdev *hwdev)
+{
+	hinic3_free_cmdqs_channel(hwdev);
+	hinic3_set_func_svc_used_state(hwdev, COMM_FUNC_SVC_T_COMM, 0);
+	free_base_mgmt_channel(hwdev);
+}
+
+static DEFINE_IDA(hinic3_adev_ida);
+
+static int hinic3_adev_idx_alloc(void)
+{
+	return ida_alloc(&hinic3_adev_ida, GFP_KERNEL);
+}
+
+static void hinic3_adev_idx_free(int id)
+{
+	ida_free(&hinic3_adev_ida, id);
+}
+
+int hinic3_init_hwdev(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+	struct hinic3_hwdev *hwdev;
+	int err;
+
+	hwdev = kzalloc(sizeof(*hwdev), GFP_KERNEL);
+	if (!hwdev)
+		return -ENOMEM;
+
+	pci_adapter->hwdev = hwdev;
+	hwdev->adapter = pci_adapter;
+	hwdev->pdev = pci_adapter->pdev;
+	hwdev->dev = &pci_adapter->pdev->dev;
+	hwdev->func_state = 0;
+	hwdev->dev_id = hinic3_adev_idx_alloc();
+	spin_lock_init(&hwdev->channel_lock);
+
+	err = hinic3_init_hwif(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init hwif\n");
+		goto err_free_hwdev;
+	}
+
+	hwdev->workq = alloc_workqueue(HINIC3_HWDEV_WQ_NAME, WQ_MEM_RECLAIM,
+				       HINIC3_WQ_MAX_REQ);
+	if (!hwdev->workq) {
+		dev_err(hwdev->dev, "Failed to alloc hardware workq\n");
+		err = -ENOMEM;
+		goto err_free_hwif;
+	}
+
+	err = hinic3_init_cfg_mgmt(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init config mgmt\n");
+		goto err_destroy_workqueue;
+	}
+
+	err = hinic3_init_comm_ch(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init communication channel\n");
+		goto err_free_cfg_mgmt;
+	}
+
+	err = hinic3_init_capability(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init capability\n");
+		goto err_uninit_comm_ch;
+	}
+
+	err = hinic3_set_comm_features(hwdev, hwdev->features,
+				       COMM_MAX_FEATURE_QWORD);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set comm features\n");
+		goto err_uninit_comm_ch;
+	}
+
+	return 0;
+
+err_uninit_comm_ch:
+	hinic3_uninit_comm_ch(hwdev);
+err_free_cfg_mgmt:
+	hinic3_free_cfg_mgmt(hwdev);
+err_destroy_workqueue:
+	destroy_workqueue(hwdev->workq);
+err_free_hwif:
+	hinic3_free_hwif(hwdev);
+err_free_hwdev:
+	pci_adapter->hwdev = NULL;
+	hinic3_adev_idx_free(hwdev->dev_id);
+	kfree(hwdev);
+
+	return err;
+}
+
+void hinic3_free_hwdev(struct hinic3_hwdev *hwdev)
+{
+	u64 drv_features[COMM_MAX_FEATURE_QWORD] = {};
+
+	hinic3_set_comm_features(hwdev, drv_features, COMM_MAX_FEATURE_QWORD);
+	hinic3_func_rx_tx_flush(hwdev);
+	hinic3_uninit_comm_ch(hwdev);
+	hinic3_free_cfg_mgmt(hwdev);
+	destroy_workqueue(hwdev->workq);
+	hinic3_free_hwif(hwdev);
+	hinic3_adev_idx_free(hwdev->dev_id);
+	kfree(hwdev);
+}
+
+void hinic3_set_api_stop(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_mbox *mbox;
+
+	spin_lock_bh(&hwdev->channel_lock);
+	if (test_bit(HINIC3_HWDEV_MBOX_INITED, &hwdev->func_state)) {
+		mbox = hwdev->mbox;
+		spin_lock(&mbox->mbox_lock);
+		if (mbox->event_flag == MBOX_EVENT_START)
+			mbox->event_flag = MBOX_EVENT_TIMEOUT;
+		spin_unlock(&mbox->mbox_lock);
+	}
+
+	if (test_bit(HINIC3_HWDEV_CMDQ_INITED, &hwdev->func_state))
+		hinic3_cmdq_flush_sync_cmd(hwdev);
+
+	spin_unlock_bh(&hwdev->channel_lock);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.h
new file mode 100644
index 000000000000..62e2745e9316
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HWDEV_H_
+#define _HINIC3_HWDEV_H_
+
+#include <linux/auxiliary_bus.h>
+#include <linux/pci.h>
+
+#include "hinic3_hw_intf.h"
+
+struct hinic3_cmdqs;
+struct hinic3_hwif;
+
+enum hinic3_event_service_type {
+	HINIC3_EVENT_SRV_COMM = 0,
+	HINIC3_EVENT_SRV_NIC  = 1
+};
+
+#define HINIC3_SRV_EVENT_TYPE(svc, type)    (((svc) << 16) | (type))
+
+/* driver-specific data of pci_dev */
+struct hinic3_pcidev {
+	struct pci_dev       *pdev;
+	struct hinic3_hwdev  *hwdev;
+	/* Auxiliary devices */
+	struct hinic3_adev   *hadev[HINIC3_SERVICE_T_MAX];
+
+	void __iomem         *cfg_reg_base;
+	void __iomem         *intr_reg_base;
+	void __iomem         *db_base;
+	u64                  db_dwqe_len;
+	u64                  db_base_phy;
+
+	/* lock for attach/detach uld */
+	struct mutex         pdev_mutex;
+	unsigned long        state;
+};
+
+struct hinic3_hwdev {
+	struct hinic3_pcidev        *adapter;
+	struct pci_dev              *pdev;
+	struct device               *dev;
+	int                         dev_id;
+	struct hinic3_hwif          *hwif;
+	struct hinic3_cfg_mgmt_info *cfg_mgmt;
+	struct hinic3_aeqs          *aeqs;
+	struct hinic3_ceqs          *ceqs;
+	struct hinic3_mbox          *mbox;
+	struct hinic3_cmdqs         *cmdqs;
+	struct workqueue_struct     *workq;
+	/* protect channel init and uninit */
+	spinlock_t                  channel_lock;
+	u64                         features[COMM_MAX_FEATURE_QWORD];
+	u32                         wq_page_size;
+	u8                          max_cmdq;
+	ulong                       func_state;
+};
+
+struct hinic3_event_info {
+	/* enum hinic3_event_service_type */
+	u16 service;
+	u16 type;
+	u8  event_data[104];
+};
+
+struct hinic3_adev {
+	struct auxiliary_device  adev;
+	struct hinic3_hwdev      *hwdev;
+	enum hinic3_service_type svc_type;
+
+	void (*event)(struct auxiliary_device *adev,
+		      struct hinic3_event_info *event);
+};
+
+int hinic3_init_hwdev(struct pci_dev *pdev);
+void hinic3_free_hwdev(struct hinic3_hwdev *hwdev);
+
+void hinic3_set_api_stop(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.c
new file mode 100644
index 000000000000..f76f140fb6f7
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.c
@@ -0,0 +1,436 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/bitfield.h>
+#include <linux/device.h>
+#include <linux/io.h>
+
+#include "hinic3_common.h"
+#include "hinic3_csr.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+
+#define HINIC3_HWIF_READY_TIMEOUT          10000
+#define HINIC3_DB_AND_OUTBOUND_EN_TIMEOUT  60000
+#define HINIC3_PCIE_LINK_DOWN              0xFFFFFFFF
+
+/* config BAR4/5 4MB, DB & DWQE both 2MB */
+#define HINIC3_DB_DWQE_SIZE    0x00400000
+
+/* db/dwqe page size: 4K */
+#define HINIC3_DB_PAGE_SIZE    0x00001000
+#define HINIC3_DWQE_OFFSET     0x00000800
+#define HINIC3_DB_MAX_AREAS    (HINIC3_DB_DWQE_SIZE / HINIC3_DB_PAGE_SIZE)
+
+#define HINIC3_MAX_MSIX_ENTRY  2048
+
+#define HINIC3_AF0_FUNC_GLOBAL_IDX_MASK  GENMASK(11, 0)
+#define HINIC3_AF0_P2P_IDX_MASK          GENMASK(16, 12)
+#define HINIC3_AF0_PCI_INTF_IDX_MASK     GENMASK(19, 17)
+#define HINIC3_AF0_FUNC_TYPE_MASK        BIT(28)
+#define HINIC3_AF0_GET(val, member) \
+	FIELD_GET(HINIC3_AF0_##member##_MASK, val)
+
+#define HINIC3_AF1_AEQS_PER_FUNC_MASK     GENMASK(9, 8)
+#define HINIC3_AF1_MGMT_INIT_STATUS_MASK  BIT(30)
+#define HINIC3_AF1_GET(val, member) \
+	FIELD_GET(HINIC3_AF1_##member##_MASK, val)
+
+#define HINIC3_AF2_CEQS_PER_FUNC_MASK      GENMASK(8, 0)
+#define HINIC3_AF2_IRQS_PER_FUNC_MASK      GENMASK(26, 16)
+#define HINIC3_AF2_GET(val, member) \
+	FIELD_GET(HINIC3_AF2_##member##_MASK, val)
+
+#define HINIC3_AF4_DOORBELL_CTRL_MASK  BIT(0)
+#define HINIC3_AF4_GET(val, member) \
+	FIELD_GET(HINIC3_AF4_##member##_MASK, val)
+#define HINIC3_AF4_SET(val, member) \
+	FIELD_PREP(HINIC3_AF4_##member##_MASK, val)
+
+#define HINIC3_AF5_OUTBOUND_CTRL_MASK  BIT(0)
+#define HINIC3_AF5_GET(val, member) \
+	FIELD_GET(HINIC3_AF5_##member##_MASK, val)
+
+#define HINIC3_AF6_PF_STATUS_MASK     GENMASK(15, 0)
+#define HINIC3_AF6_FUNC_MAX_SQ_MASK   GENMASK(31, 23)
+#define HINIC3_AF6_MSIX_FLEX_EN_MASK  BIT(22)
+#define HINIC3_AF6_GET(val, member) \
+	FIELD_GET(HINIC3_AF6_##member##_MASK, val)
+
+#define HINIC3_GET_REG_ADDR(reg)  ((reg) & (HINIC3_REGS_FLAG_MASK))
+
+static void __iomem *hinic3_reg_addr(struct hinic3_hwif *hwif, u32 reg)
+{
+	return hwif->cfg_regs_base + HINIC3_GET_REG_ADDR(reg);
+}
+
+u32 hinic3_hwif_read_reg(struct hinic3_hwif *hwif, u32 reg)
+{
+	void __iomem *addr = hinic3_reg_addr(hwif, reg);
+
+	return ioread32be(addr);
+}
+
+void hinic3_hwif_write_reg(struct hinic3_hwif *hwif, u32 reg, u32 val)
+{
+	void __iomem *addr = hinic3_reg_addr(hwif, reg);
+
+	iowrite32be(val, addr);
+}
+
+static enum hinic3_wait_return check_hwif_ready_handler(void *priv_data)
+{
+	struct hinic3_hwdev *hwdev = priv_data;
+	u32 attr1;
+
+	attr1 = hinic3_hwif_read_reg(hwdev->hwif, HINIC3_CSR_FUNC_ATTR1_ADDR);
+
+	return HINIC3_AF1_GET(attr1, MGMT_INIT_STATUS) ?
+	       HINIC3_WAIT_PROCESS_CPL : HINIC3_WAIT_PROCESS_WAITING;
+}
+
+static int wait_hwif_ready(struct hinic3_hwdev *hwdev)
+{
+	return hinic3_wait_for_timeout(hwdev, check_hwif_ready_handler,
+				       HINIC3_HWIF_READY_TIMEOUT,
+				       USEC_PER_MSEC);
+}
+
+/* Set attr struct from HW attr values. */
+static void set_hwif_attr(struct hinic3_func_attr *attr, u32 attr0, u32 attr1,
+			  u32 attr2, u32 attr3, u32 attr6)
+{
+	attr->func_global_idx = HINIC3_AF0_GET(attr0, FUNC_GLOBAL_IDX);
+	attr->port_to_port_idx = HINIC3_AF0_GET(attr0, P2P_IDX);
+	attr->pci_intf_idx = HINIC3_AF0_GET(attr0, PCI_INTF_IDX);
+	attr->func_type = HINIC3_AF0_GET(attr0, FUNC_TYPE);
+
+	attr->num_aeqs = BIT(HINIC3_AF1_GET(attr1, AEQS_PER_FUNC));
+	attr->num_ceqs = HINIC3_AF2_GET(attr2, CEQS_PER_FUNC);
+	attr->num_irqs = HINIC3_AF2_GET(attr2, IRQS_PER_FUNC);
+	if (attr->num_irqs > HINIC3_MAX_MSIX_ENTRY)
+		attr->num_irqs = HINIC3_MAX_MSIX_ENTRY;
+
+	attr->num_sq = HINIC3_AF6_GET(attr6, FUNC_MAX_SQ);
+	attr->msix_flex_en = HINIC3_AF6_GET(attr6, MSIX_FLEX_EN);
+}
+
+/* Read attributes from HW and set attribute struct. */
+static int init_hwif_attr(struct hinic3_hwdev *hwdev)
+{
+	u32 attr0, attr1, attr2, attr3, attr6;
+	struct hinic3_hwif *hwif;
+
+	hwif = hwdev->hwif;
+	attr0 = hinic3_hwif_read_reg(hwif, HINIC3_CSR_FUNC_ATTR0_ADDR);
+	if (attr0 == HINIC3_PCIE_LINK_DOWN)
+		return -EFAULT;
+
+	attr1 = hinic3_hwif_read_reg(hwif, HINIC3_CSR_FUNC_ATTR1_ADDR);
+	if (attr1 == HINIC3_PCIE_LINK_DOWN)
+		return -EFAULT;
+
+	attr2 = hinic3_hwif_read_reg(hwif, HINIC3_CSR_FUNC_ATTR2_ADDR);
+	if (attr2 == HINIC3_PCIE_LINK_DOWN)
+		return -EFAULT;
+
+	attr3 = hinic3_hwif_read_reg(hwif, HINIC3_CSR_FUNC_ATTR3_ADDR);
+	if (attr3 == HINIC3_PCIE_LINK_DOWN)
+		return -EFAULT;
+
+	attr6 = hinic3_hwif_read_reg(hwif, HINIC3_CSR_FUNC_ATTR6_ADDR);
+	if (attr6 == HINIC3_PCIE_LINK_DOWN)
+		return -EFAULT;
+
+	set_hwif_attr(&hwif->attr, attr0, attr1, attr2, attr3, attr6);
+
+	if (!hwif->attr.num_ceqs) {
+		dev_err(hwdev->dev, "Ceq num cfg in fw is zero\n");
+		return -EFAULT;
+	}
+
+	if (!hwif->attr.num_irqs) {
+		dev_err(hwdev->dev,
+			"Irq num cfg in fw is zero, msix_flex_en %d\n",
+			hwif->attr.msix_flex_en);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static enum hinic3_doorbell_ctrl hinic3_get_doorbell_ctrl_status(struct hinic3_hwif *hwif)
+{
+	u32 attr4 = hinic3_hwif_read_reg(hwif, HINIC3_CSR_FUNC_ATTR4_ADDR);
+
+	return HINIC3_AF4_GET(attr4, DOORBELL_CTRL);
+}
+
+static enum hinic3_outbound_ctrl hinic3_get_outbound_ctrl_status(struct hinic3_hwif *hwif)
+{
+	u32 attr5 = hinic3_hwif_read_reg(hwif, HINIC3_CSR_FUNC_ATTR5_ADDR);
+
+	return HINIC3_AF5_GET(attr5, OUTBOUND_CTRL);
+}
+
+void hinic3_toggle_doorbell(struct hinic3_hwif *hwif,
+			    enum hinic3_doorbell_ctrl flag)
+{
+	u32 addr, attr4;
+
+	addr = HINIC3_CSR_FUNC_ATTR4_ADDR;
+	attr4 = hinic3_hwif_read_reg(hwif, addr);
+
+	attr4 &= ~HINIC3_AF4_DOORBELL_CTRL_MASK;
+	attr4 |= HINIC3_AF4_SET(flag, DOORBELL_CTRL);
+
+	hinic3_hwif_write_reg(hwif, addr, attr4);
+}
+
+static int db_area_idx_init(struct hinic3_hwif *hwif, u64 db_base_phy,
+			    u8 __iomem *db_base, u64 db_dwqe_len)
+{
+	struct hinic3_db_area *db_area = &hwif->db_area;
+	u32 db_max_areas;
+
+	hwif->db_base_phy = db_base_phy;
+	hwif->db_base = db_base;
+	hwif->db_dwqe_len = db_dwqe_len;
+
+	db_max_areas = db_dwqe_len > HINIC3_DB_DWQE_SIZE ?
+		       HINIC3_DB_MAX_AREAS : db_dwqe_len / HINIC3_DB_PAGE_SIZE;
+	db_area->db_bitmap_array = bitmap_zalloc(db_max_areas, GFP_KERNEL);
+	if (!db_area->db_bitmap_array)
+		return -ENOMEM;
+
+	db_area->db_max_areas = db_max_areas;
+	spin_lock_init(&db_area->idx_lock);
+
+	return 0;
+}
+
+static void db_area_idx_free(struct hinic3_db_area *db_area)
+{
+	bitmap_free(db_area->db_bitmap_array);
+}
+
+static int get_db_idx(struct hinic3_hwif *hwif, u32 *idx)
+{
+	struct hinic3_db_area *db_area = &hwif->db_area;
+	u32 pg_idx;
+
+	spin_lock(&db_area->idx_lock);
+	pg_idx = find_first_zero_bit(db_area->db_bitmap_array,
+				     db_area->db_max_areas);
+	if (pg_idx == db_area->db_max_areas) {
+		spin_unlock(&db_area->idx_lock);
+		return -ENOMEM;
+	}
+	set_bit(pg_idx, db_area->db_bitmap_array);
+	spin_unlock(&db_area->idx_lock);
+
+	*idx = pg_idx;
+
+	return 0;
+}
+
+static void free_db_idx(struct hinic3_hwif *hwif, u32 idx)
+{
+	struct hinic3_db_area *db_area = &hwif->db_area;
+
+	spin_lock(&db_area->idx_lock);
+	clear_bit(idx, db_area->db_bitmap_array);
+	spin_unlock(&db_area->idx_lock);
+}
+
+void hinic3_free_db_addr(struct hinic3_hwdev *hwdev, const u8 __iomem *db_base)
+{
+	struct hinic3_hwif *hwif;
+	uintptr_t distance;
+	u32 idx;
+
+	hwif = hwdev->hwif;
+	distance = db_base - hwif->db_base;
+	idx = distance / HINIC3_DB_PAGE_SIZE;
+
+	free_db_idx(hwif, idx);
+}
+
+int hinic3_alloc_db_addr(struct hinic3_hwdev *hwdev, void __iomem **db_base,
+			 void __iomem **dwqe_base)
+{
+	struct hinic3_hwif *hwif;
+	u8 __iomem *addr;
+	u32 idx;
+	int err;
+
+	hwif = hwdev->hwif;
+
+	err = get_db_idx(hwif, &idx);
+	if (err)
+		return err;
+
+	addr = hwif->db_base + idx * HINIC3_DB_PAGE_SIZE;
+	*db_base = addr;
+
+	if (dwqe_base)
+		*dwqe_base = addr + HINIC3_DWQE_OFFSET;
+
+	return 0;
+}
+
+void hinic3_set_msix_state(struct hinic3_hwdev *hwdev, u16 msix_idx,
+			   enum hinic3_msix_state flag)
+{
+	struct hinic3_hwif *hwif;
+	u8 int_msk = 1;
+	u32 mask_bits;
+	u32 addr;
+
+	hwif = hwdev->hwif;
+
+	if (flag)
+		mask_bits = HINIC3_MSI_CLR_INDIR_SET(int_msk, INT_MSK_SET);
+	else
+		mask_bits = HINIC3_MSI_CLR_INDIR_SET(int_msk, INT_MSK_CLR);
+	mask_bits = mask_bits |
+		    HINIC3_MSI_CLR_INDIR_SET(msix_idx, SIMPLE_INDIR_IDX);
+
+	addr = HINIC3_CSR_FUNC_MSI_CLR_WR_ADDR;
+	hinic3_hwif_write_reg(hwif, addr, mask_bits);
+}
+
+static void disable_all_msix(struct hinic3_hwdev *hwdev)
+{
+	u16 num_irqs = hwdev->hwif->attr.num_irqs;
+	u16 i;
+
+	for (i = 0; i < num_irqs; i++)
+		hinic3_set_msix_state(hwdev, i, HINIC3_MSIX_DISABLE);
+}
+
+void hinic3_msix_intr_clear_resend_bit(struct hinic3_hwdev *hwdev, u16 msix_idx,
+				       u8 clear_resend_en)
+{
+	struct hinic3_hwif *hwif;
+	u32 msix_ctrl, addr;
+
+	hwif = hwdev->hwif;
+
+	msix_ctrl = HINIC3_MSI_CLR_INDIR_SET(msix_idx, SIMPLE_INDIR_IDX) |
+		    HINIC3_MSI_CLR_INDIR_SET(clear_resend_en, RESEND_TIMER_CLR);
+
+	addr = HINIC3_CSR_FUNC_MSI_CLR_WR_ADDR;
+	hinic3_hwif_write_reg(hwif, addr, msix_ctrl);
+}
+
+void hinic3_set_msix_auto_mask_state(struct hinic3_hwdev *hwdev, u16 msix_idx,
+				     enum hinic3_msix_auto_mask flag)
+{
+	struct hinic3_hwif *hwif;
+	u32 mask_bits;
+	u32 addr;
+
+	hwif = hwdev->hwif;
+
+	if (flag)
+		mask_bits = HINIC3_MSI_CLR_INDIR_SET(1, AUTO_MSK_SET);
+	else
+		mask_bits = HINIC3_MSI_CLR_INDIR_SET(1, AUTO_MSK_CLR);
+
+	mask_bits = mask_bits |
+		    HINIC3_MSI_CLR_INDIR_SET(msix_idx, SIMPLE_INDIR_IDX);
+
+	addr = HINIC3_CSR_FUNC_MSI_CLR_WR_ADDR;
+	hinic3_hwif_write_reg(hwif, addr, mask_bits);
+}
+
+static enum hinic3_wait_return check_db_outbound_enable_handler(void *priv_data)
+{
+	enum hinic3_outbound_ctrl outbound_ctrl;
+	struct hinic3_hwif *hwif = priv_data;
+	enum hinic3_doorbell_ctrl db_ctrl;
+
+	db_ctrl = hinic3_get_doorbell_ctrl_status(hwif);
+	outbound_ctrl = hinic3_get_outbound_ctrl_status(hwif);
+	if (outbound_ctrl == ENABLE_OUTBOUND && db_ctrl == ENABLE_DOORBELL)
+		return HINIC3_WAIT_PROCESS_CPL;
+
+	return HINIC3_WAIT_PROCESS_WAITING;
+}
+
+static int wait_until_doorbell_and_outbound_enabled(struct hinic3_hwif *hwif)
+{
+	return hinic3_wait_for_timeout(hwif, check_db_outbound_enable_handler,
+				       HINIC3_DB_AND_OUTBOUND_EN_TIMEOUT,
+				       USEC_PER_MSEC);
+}
+
+int hinic3_init_hwif(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_pcidev *pci_adapter = hwdev->adapter;
+	struct hinic3_hwif *hwif;
+	u32 attr1, attr4, attr5;
+	int err;
+
+	hwif = kzalloc(sizeof(*hwif), GFP_KERNEL);
+	if (!hwif)
+		return -ENOMEM;
+
+	hwdev->hwif = hwif;
+	hwif->cfg_regs_base = (u8 __iomem *)pci_adapter->cfg_reg_base +
+			      HINIC3_VF_CFG_REG_OFFSET;
+
+	err = db_area_idx_init(hwif, pci_adapter->db_base_phy,
+			       pci_adapter->db_base,
+			       pci_adapter->db_dwqe_len);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init db area.\n");
+		goto err_free_hwif;
+	}
+
+	err = wait_hwif_ready(hwdev);
+	if (err) {
+		attr1 = hinic3_hwif_read_reg(hwif, HINIC3_CSR_FUNC_ATTR1_ADDR);
+		dev_err(hwdev->dev, "Chip status is not ready, attr1:0x%x\n",
+			attr1);
+		goto err_free_db_area_idx;
+	}
+
+	err = init_hwif_attr(hwdev);
+	if (err) {
+		dev_err(hwdev->dev, "Init hwif attr failed\n");
+		goto err_free_db_area_idx;
+	}
+
+	err = wait_until_doorbell_and_outbound_enabled(hwif);
+	if (err) {
+		attr4 = hinic3_hwif_read_reg(hwif, HINIC3_CSR_FUNC_ATTR4_ADDR);
+		attr5 = hinic3_hwif_read_reg(hwif, HINIC3_CSR_FUNC_ATTR5_ADDR);
+		dev_err(hwdev->dev, "HW doorbell/outbound is disabled, attr4 0x%x attr5 0x%x\n",
+			attr4, attr5);
+		goto err_free_db_area_idx;
+	}
+
+	disable_all_msix(hwdev);
+
+	return 0;
+
+err_free_db_area_idx:
+	db_area_idx_free(&hwif->db_area);
+err_free_hwif:
+	kfree(hwif);
+
+	return err;
+}
+
+void hinic3_free_hwif(struct hinic3_hwdev *hwdev)
+{
+	db_area_idx_free(&hwdev->hwif->db_area);
+	kfree(hwdev->hwif);
+}
+
+u16 hinic3_global_func_id(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->hwif->attr.func_global_idx;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.h
new file mode 100644
index 000000000000..c02904e861cc
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HWIF_H_
+#define _HINIC3_HWIF_H_
+
+#include <linux/build_bug.h>
+#include <linux/spinlock_types.h>
+
+struct hinic3_hwdev;
+
+enum hinic3_func_type {
+	HINIC3_FUNC_TYPE_VF = 1,
+};
+
+struct hinic3_db_area {
+	unsigned long *db_bitmap_array;
+	u32           db_max_areas;
+	/* protect doorbell area alloc and free */
+	spinlock_t    idx_lock;
+};
+
+struct hinic3_func_attr {
+	enum hinic3_func_type func_type;
+	u16                   func_global_idx;
+	u16                   global_vf_id_of_pf;
+	u16                   num_irqs;
+	u16                   num_sq;
+	u8                    port_to_port_idx;
+	u8                    pci_intf_idx;
+	u8                    ppf_idx;
+	u8                    num_aeqs;
+	u8                    num_ceqs;
+	u8                    msix_flex_en;
+};
+
+static_assert(sizeof(struct hinic3_func_attr) == 20);
+
+struct hinic3_hwif {
+	u8 __iomem              *cfg_regs_base;
+	u64                     db_base_phy;
+	u64                     db_dwqe_len;
+	u8 __iomem              *db_base;
+	struct hinic3_db_area   db_area;
+	struct hinic3_func_attr attr;
+};
+
+enum hinic3_outbound_ctrl {
+	ENABLE_OUTBOUND  = 0x0,
+	DISABLE_OUTBOUND = 0x1,
+};
+
+enum hinic3_doorbell_ctrl {
+	ENABLE_DOORBELL  = 0,
+	DISABLE_DOORBELL = 1,
+};
+
+enum hinic3_msix_state {
+	HINIC3_MSIX_ENABLE,
+	HINIC3_MSIX_DISABLE,
+};
+
+enum hinic3_msix_auto_mask {
+	HINIC3_CLR_MSIX_AUTO_MASK,
+	HINIC3_SET_MSIX_AUTO_MASK,
+};
+
+u32 hinic3_hwif_read_reg(struct hinic3_hwif *hwif, u32 reg);
+void hinic3_hwif_write_reg(struct hinic3_hwif *hwif, u32 reg, u32 val);
+
+void hinic3_toggle_doorbell(struct hinic3_hwif *hwif,
+			    enum hinic3_doorbell_ctrl flag);
+
+int hinic3_alloc_db_addr(struct hinic3_hwdev *hwdev, void __iomem **db_base,
+			 void __iomem **dwqe_base);
+void hinic3_free_db_addr(struct hinic3_hwdev *hwdev, const u8 __iomem *db_base);
+
+int hinic3_init_hwif(struct hinic3_hwdev *hwdev);
+void hinic3_free_hwif(struct hinic3_hwdev *hwdev);
+
+void hinic3_set_msix_state(struct hinic3_hwdev *hwdev, u16 msix_idx,
+			   enum hinic3_msix_state flag);
+void hinic3_msix_intr_clear_resend_bit(struct hinic3_hwdev *hwdev, u16 msix_idx,
+				       u8 clear_resend_en);
+void hinic3_set_msix_auto_mask_state(struct hinic3_hwdev *hwdev, u16 msix_idx,
+				     enum hinic3_msix_auto_mask flag);
+
+u16 hinic3_global_func_id(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c
new file mode 100644
index 000000000000..a69b361225e9
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c
@@ -0,0 +1,194 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/netdevice.h>
+
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_rx.h"
+#include "hinic3_tx.h"
+
+static int hinic3_poll(struct napi_struct *napi, int budget)
+{
+	struct hinic3_irq_cfg *irq_cfg =
+		container_of(napi, struct hinic3_irq_cfg, napi);
+	struct hinic3_nic_dev *nic_dev;
+	bool busy = false;
+	int work_done;
+
+	nic_dev = netdev_priv(irq_cfg->netdev);
+
+	busy |= hinic3_tx_poll(irq_cfg->txq, budget);
+
+	if (unlikely(!budget))
+		return 0;
+
+	work_done = hinic3_rx_poll(irq_cfg->rxq, budget);
+	busy |= work_done >= budget;
+
+	if (busy)
+		return budget;
+
+	if (likely(napi_complete_done(napi, work_done)))
+		hinic3_set_msix_state(nic_dev->hwdev, irq_cfg->msix_entry_idx,
+				      HINIC3_MSIX_ENABLE);
+
+	return work_done;
+}
+
+static void qp_add_napi(struct hinic3_irq_cfg *irq_cfg)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(irq_cfg->netdev);
+
+	netif_napi_add(nic_dev->netdev, &irq_cfg->napi, hinic3_poll);
+	netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id,
+			     NETDEV_QUEUE_TYPE_RX, &irq_cfg->napi);
+	netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id,
+			     NETDEV_QUEUE_TYPE_TX, &irq_cfg->napi);
+	napi_enable(&irq_cfg->napi);
+}
+
+static void qp_del_napi(struct hinic3_irq_cfg *irq_cfg)
+{
+	napi_disable(&irq_cfg->napi);
+	netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id,
+			     NETDEV_QUEUE_TYPE_RX, NULL);
+	netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id,
+			     NETDEV_QUEUE_TYPE_TX, NULL);
+	netif_stop_subqueue(irq_cfg->netdev, irq_cfg->irq_id);
+	netif_napi_del(&irq_cfg->napi);
+}
+
+static irqreturn_t qp_irq(int irq, void *data)
+{
+	struct hinic3_irq_cfg *irq_cfg = data;
+	struct hinic3_nic_dev *nic_dev;
+
+	nic_dev = netdev_priv(irq_cfg->netdev);
+	hinic3_msix_intr_clear_resend_bit(nic_dev->hwdev,
+					  irq_cfg->msix_entry_idx, 1);
+
+	napi_schedule(&irq_cfg->napi);
+
+	return IRQ_HANDLED;
+}
+
+static int hinic3_request_irq(struct hinic3_irq_cfg *irq_cfg, u16 q_id)
+{
+	struct hinic3_interrupt_info info = {};
+	struct hinic3_nic_dev *nic_dev;
+	struct net_device *netdev;
+	int err;
+
+	netdev = irq_cfg->netdev;
+	nic_dev = netdev_priv(netdev);
+	qp_add_napi(irq_cfg);
+
+	info.msix_index = irq_cfg->msix_entry_idx;
+	info.interrupt_coalesc_set = 1;
+	info.pending_limit = nic_dev->intr_coalesce[q_id].pending_limit;
+	info.coalesc_timer_cfg =
+		nic_dev->intr_coalesce[q_id].coalesce_timer_cfg;
+	info.resend_timer_cfg = nic_dev->intr_coalesce[q_id].resend_timer_cfg;
+	err = hinic3_set_interrupt_cfg_direct(nic_dev->hwdev, &info);
+	if (err) {
+		netdev_err(netdev, "Failed to set RX interrupt coalescing attribute.\n");
+		qp_del_napi(irq_cfg);
+		return err;
+	}
+
+	err = request_irq(irq_cfg->irq_id, qp_irq, 0, irq_cfg->irq_name,
+			  irq_cfg);
+	if (err) {
+		qp_del_napi(irq_cfg);
+		return err;
+	}
+
+	irq_set_affinity_hint(irq_cfg->irq_id, &irq_cfg->affinity_mask);
+
+	return 0;
+}
+
+static void hinic3_release_irq(struct hinic3_irq_cfg *irq_cfg)
+{
+	irq_set_affinity_hint(irq_cfg->irq_id, NULL);
+	free_irq(irq_cfg->irq_id, irq_cfg);
+}
+
+int hinic3_qps_irq_init(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct pci_dev *pdev = nic_dev->pdev;
+	struct hinic3_irq_cfg *irq_cfg;
+	struct msix_entry *msix_entry;
+	u32 local_cpu;
+	u16 q_id;
+	int err;
+
+	for (q_id = 0; q_id < nic_dev->q_params.num_qps; q_id++) {
+		msix_entry = &nic_dev->qps_msix_entries[q_id];
+		irq_cfg = &nic_dev->q_params.irq_cfg[q_id];
+
+		irq_cfg->irq_id = msix_entry->vector;
+		irq_cfg->msix_entry_idx = msix_entry->entry;
+		irq_cfg->netdev = netdev;
+		irq_cfg->txq = &nic_dev->txqs[q_id];
+		irq_cfg->rxq = &nic_dev->rxqs[q_id];
+		nic_dev->rxqs[q_id].irq_cfg = irq_cfg;
+
+		local_cpu = cpumask_local_spread(q_id, dev_to_node(&pdev->dev));
+		cpumask_set_cpu(local_cpu, &irq_cfg->affinity_mask);
+
+		snprintf(irq_cfg->irq_name, sizeof(irq_cfg->irq_name),
+			 "%s_qp%u", netdev->name, q_id);
+
+		err = hinic3_request_irq(irq_cfg, q_id);
+		if (err) {
+			netdev_err(netdev, "Failed to request Rx irq\n");
+			goto err_release_irqs;
+		}
+
+		hinic3_set_msix_auto_mask_state(nic_dev->hwdev,
+						irq_cfg->msix_entry_idx,
+						HINIC3_SET_MSIX_AUTO_MASK);
+		hinic3_set_msix_state(nic_dev->hwdev, irq_cfg->msix_entry_idx,
+				      HINIC3_MSIX_ENABLE);
+	}
+
+	return 0;
+
+err_release_irqs:
+	while (q_id > 0) {
+		q_id--;
+		irq_cfg = &nic_dev->q_params.irq_cfg[q_id];
+		qp_del_napi(irq_cfg);
+		hinic3_set_msix_state(nic_dev->hwdev, irq_cfg->msix_entry_idx,
+				      HINIC3_MSIX_DISABLE);
+		hinic3_set_msix_auto_mask_state(nic_dev->hwdev,
+						irq_cfg->msix_entry_idx,
+						HINIC3_CLR_MSIX_AUTO_MASK);
+		hinic3_release_irq(irq_cfg);
+	}
+
+	return err;
+}
+
+void hinic3_qps_irq_uninit(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_irq_cfg *irq_cfg;
+	u16 q_id;
+
+	for (q_id = 0; q_id < nic_dev->q_params.num_qps; q_id++) {
+		irq_cfg = &nic_dev->q_params.irq_cfg[q_id];
+		qp_del_napi(irq_cfg);
+		hinic3_set_msix_state(nic_dev->hwdev, irq_cfg->msix_entry_idx,
+				      HINIC3_MSIX_DISABLE);
+		hinic3_set_msix_auto_mask_state(nic_dev->hwdev,
+						irq_cfg->msix_entry_idx,
+						HINIC3_CLR_MSIX_AUTO_MASK);
+		hinic3_release_irq(irq_cfg);
+	}
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_lld.c b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.c
new file mode 100644
index 000000000000..3db8241a3b0c
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.c
@@ -0,0 +1,421 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/delay.h>
+#include <linux/iopoll.h>
+
+#include "hinic3_hw_cfg.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_lld.h"
+#include "hinic3_mgmt.h"
+#include "hinic3_pci_id_tbl.h"
+
+#define HINIC3_VF_PCI_CFG_REG_BAR  0
+#define HINIC3_PCI_INTR_REG_BAR    2
+#define HINIC3_PCI_DB_BAR          4
+
+#define HINIC3_EVENT_POLL_SLEEP_US   1000
+#define HINIC3_EVENT_POLL_TIMEOUT_US 10000000
+
+static struct hinic3_adev_device {
+	const char *name;
+} hinic3_adev_devices[HINIC3_SERVICE_T_MAX] = {
+	[HINIC3_SERVICE_T_NIC] = {
+		.name = "nic",
+	},
+};
+
+static bool hinic3_adev_svc_supported(struct hinic3_hwdev *hwdev,
+				      enum hinic3_service_type svc_type)
+{
+	switch (svc_type) {
+	case HINIC3_SERVICE_T_NIC:
+		return hinic3_support_nic(hwdev);
+	default:
+		break;
+	}
+
+	return false;
+}
+
+static void hinic3_comm_adev_release(struct device *dev)
+{
+	struct hinic3_adev *hadev = container_of(dev, struct hinic3_adev,
+						 adev.dev);
+
+	kfree(hadev);
+}
+
+static struct hinic3_adev *hinic3_add_one_adev(struct hinic3_hwdev *hwdev,
+					       enum hinic3_service_type svc_type)
+{
+	struct hinic3_adev *hadev;
+	const char *svc_name;
+	int ret;
+
+	hadev = kzalloc(sizeof(*hadev), GFP_KERNEL);
+	if (!hadev)
+		return NULL;
+
+	svc_name = hinic3_adev_devices[svc_type].name;
+	hadev->adev.name = svc_name;
+	hadev->adev.id = hwdev->dev_id;
+	hadev->adev.dev.parent = hwdev->dev;
+	hadev->adev.dev.release = hinic3_comm_adev_release;
+	hadev->svc_type = svc_type;
+	hadev->hwdev = hwdev;
+
+	ret = auxiliary_device_init(&hadev->adev);
+	if (ret) {
+		dev_err(hwdev->dev, "failed init adev %s %u\n",
+			svc_name, hwdev->dev_id);
+		kfree(hadev);
+		return NULL;
+	}
+
+	ret = auxiliary_device_add(&hadev->adev);
+	if (ret) {
+		dev_err(hwdev->dev, "failed to add adev %s %u\n",
+			svc_name, hwdev->dev_id);
+		auxiliary_device_uninit(&hadev->adev);
+		return NULL;
+	}
+
+	return hadev;
+}
+
+static void hinic3_del_one_adev(struct hinic3_hwdev *hwdev,
+				enum hinic3_service_type svc_type)
+{
+	struct hinic3_pcidev *pci_adapter = hwdev->adapter;
+	struct hinic3_adev *hadev;
+	int timeout;
+	bool state;
+
+	timeout = read_poll_timeout(test_and_set_bit, state, !state,
+				    HINIC3_EVENT_POLL_SLEEP_US,
+				    HINIC3_EVENT_POLL_TIMEOUT_US,
+				    false, svc_type, &pci_adapter->state);
+
+	hadev = pci_adapter->hadev[svc_type];
+	auxiliary_device_delete(&hadev->adev);
+	auxiliary_device_uninit(&hadev->adev);
+	pci_adapter->hadev[svc_type] = NULL;
+	if (!timeout)
+		clear_bit(svc_type, &pci_adapter->state);
+}
+
+static int hinic3_attach_aux_devices(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_pcidev *pci_adapter = hwdev->adapter;
+	enum hinic3_service_type svc_type;
+
+	mutex_lock(&pci_adapter->pdev_mutex);
+
+	for (svc_type = 0; svc_type < HINIC3_SERVICE_T_MAX; svc_type++) {
+		if (!hinic3_adev_svc_supported(hwdev, svc_type))
+			continue;
+
+		pci_adapter->hadev[svc_type] = hinic3_add_one_adev(hwdev,
+								   svc_type);
+		if (!pci_adapter->hadev[svc_type])
+			goto err_del_adevs;
+	}
+	mutex_unlock(&pci_adapter->pdev_mutex);
+
+	return 0;
+
+err_del_adevs:
+	while (svc_type > 0) {
+		svc_type--;
+		if (pci_adapter->hadev[svc_type]) {
+			hinic3_del_one_adev(hwdev, svc_type);
+			pci_adapter->hadev[svc_type] = NULL;
+		}
+	}
+	mutex_unlock(&pci_adapter->pdev_mutex);
+
+	return -ENOMEM;
+}
+
+static void hinic3_detach_aux_devices(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_pcidev *pci_adapter = hwdev->adapter;
+	int i;
+
+	mutex_lock(&pci_adapter->pdev_mutex);
+	for (i = 0; i < ARRAY_SIZE(hinic3_adev_devices); i++) {
+		if (pci_adapter->hadev[i])
+			hinic3_del_one_adev(hwdev, i);
+	}
+	mutex_unlock(&pci_adapter->pdev_mutex);
+}
+
+struct hinic3_hwdev *hinic3_adev_get_hwdev(struct auxiliary_device *adev)
+{
+	struct hinic3_adev *hadev;
+
+	hadev = container_of(adev, struct hinic3_adev, adev);
+
+	return hadev->hwdev;
+}
+
+void hinic3_adev_event_register(struct auxiliary_device *adev,
+				void (*event_handler)(struct auxiliary_device *adev,
+						      struct hinic3_event_info *event))
+{
+	struct hinic3_adev *hadev;
+
+	hadev = container_of(adev, struct hinic3_adev, adev);
+	hadev->event = event_handler;
+}
+
+void hinic3_adev_event_unregister(struct auxiliary_device *adev)
+{
+	struct hinic3_adev *hadev;
+
+	hadev = container_of(adev, struct hinic3_adev, adev);
+	hadev->event = NULL;
+}
+
+static int hinic3_mapping_bar(struct pci_dev *pdev,
+			      struct hinic3_pcidev *pci_adapter)
+{
+	pci_adapter->cfg_reg_base = pci_ioremap_bar(pdev,
+						    HINIC3_VF_PCI_CFG_REG_BAR);
+	if (!pci_adapter->cfg_reg_base) {
+		dev_err(&pdev->dev, "Failed to map configuration regs\n");
+		return -ENOMEM;
+	}
+
+	pci_adapter->intr_reg_base = pci_ioremap_bar(pdev,
+						     HINIC3_PCI_INTR_REG_BAR);
+	if (!pci_adapter->intr_reg_base) {
+		dev_err(&pdev->dev, "Failed to map interrupt regs\n");
+		goto err_unmap_cfg_reg_base;
+	}
+
+	pci_adapter->db_base_phy = pci_resource_start(pdev, HINIC3_PCI_DB_BAR);
+	pci_adapter->db_dwqe_len = pci_resource_len(pdev, HINIC3_PCI_DB_BAR);
+	pci_adapter->db_base = pci_ioremap_bar(pdev, HINIC3_PCI_DB_BAR);
+	if (!pci_adapter->db_base) {
+		dev_err(&pdev->dev, "Failed to map doorbell regs\n");
+		goto err_unmap_intr_reg_base;
+	}
+
+	return 0;
+
+err_unmap_intr_reg_base:
+	iounmap(pci_adapter->intr_reg_base);
+
+err_unmap_cfg_reg_base:
+	iounmap(pci_adapter->cfg_reg_base);
+
+	return -ENOMEM;
+}
+
+static void hinic3_unmapping_bar(struct hinic3_pcidev *pci_adapter)
+{
+	iounmap(pci_adapter->db_base);
+	iounmap(pci_adapter->intr_reg_base);
+	iounmap(pci_adapter->cfg_reg_base);
+}
+
+static int hinic3_pci_init(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter;
+	int err;
+
+	pci_adapter = kzalloc(sizeof(*pci_adapter), GFP_KERNEL);
+	if (!pci_adapter)
+		return -ENOMEM;
+
+	pci_adapter->pdev = pdev;
+	mutex_init(&pci_adapter->pdev_mutex);
+
+	pci_set_drvdata(pdev, pci_adapter);
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to enable PCI device\n");
+		goto err_free_pci_adapter;
+	}
+
+	err = pci_request_regions(pdev, HINIC3_NIC_DRV_NAME);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to request regions\n");
+		goto err_disable_device;
+	}
+
+	pci_set_master(pdev);
+
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (err) {
+		dev_err(&pdev->dev, "Failed to set DMA mask\n");
+		goto err_release_regions;
+	}
+
+	return 0;
+
+err_release_regions:
+	pci_clear_master(pdev);
+	pci_release_regions(pdev);
+
+err_disable_device:
+	pci_disable_device(pdev);
+
+err_free_pci_adapter:
+	pci_set_drvdata(pdev, NULL);
+	mutex_destroy(&pci_adapter->pdev_mutex);
+	kfree(pci_adapter);
+
+	return err;
+}
+
+static void hinic3_pci_uninit(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	pci_clear_master(pdev);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+	mutex_destroy(&pci_adapter->pdev_mutex);
+	kfree(pci_adapter);
+}
+
+static int hinic3_func_init(struct pci_dev *pdev,
+			    struct hinic3_pcidev *pci_adapter)
+{
+	int err;
+
+	err = hinic3_init_hwdev(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to initialize hardware device\n");
+		return err;
+	}
+
+	err = hinic3_attach_aux_devices(pci_adapter->hwdev);
+	if (err)
+		goto err_free_hwdev;
+
+	return 0;
+
+err_free_hwdev:
+	hinic3_free_hwdev(pci_adapter->hwdev);
+
+	return err;
+}
+
+static void hinic3_func_uninit(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	hinic3_flush_mgmt_workq(pci_adapter->hwdev);
+	hinic3_detach_aux_devices(pci_adapter->hwdev);
+	hinic3_free_hwdev(pci_adapter->hwdev);
+}
+
+static int hinic3_probe_func(struct hinic3_pcidev *pci_adapter)
+{
+	struct pci_dev *pdev = pci_adapter->pdev;
+	int err;
+
+	err = hinic3_mapping_bar(pdev, pci_adapter);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to map bar\n");
+		goto err_out;
+	}
+
+	err = hinic3_func_init(pdev, pci_adapter);
+	if (err)
+		goto err_unmap_bar;
+
+	return 0;
+
+err_unmap_bar:
+	hinic3_unmapping_bar(pci_adapter);
+
+err_out:
+	dev_err(&pdev->dev, "PCIe device probe function failed\n");
+
+	return err;
+}
+
+static void hinic3_remove_func(struct hinic3_pcidev *pci_adapter)
+{
+	struct pci_dev *pdev = pci_adapter->pdev;
+
+	hinic3_func_uninit(pdev);
+	hinic3_unmapping_bar(pci_adapter);
+}
+
+static int hinic3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct hinic3_pcidev *pci_adapter;
+	int err;
+
+	err = hinic3_pci_init(pdev);
+	if (err)
+		goto err_out;
+
+	pci_adapter = pci_get_drvdata(pdev);
+	err = hinic3_probe_func(pci_adapter);
+	if (err)
+		goto err_uninit_pci;
+
+	return 0;
+
+err_uninit_pci:
+	hinic3_pci_uninit(pdev);
+
+err_out:
+	dev_err(&pdev->dev, "PCIe device probe failed\n");
+
+	return err;
+}
+
+static void hinic3_remove(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	hinic3_remove_func(pci_adapter);
+	hinic3_pci_uninit(pdev);
+}
+
+static const struct pci_device_id hinic3_pci_table[] = {
+	{PCI_VDEVICE(HUAWEI, PCI_DEV_ID_HINIC3_VF), 0},
+	{0, 0}
+
+};
+
+MODULE_DEVICE_TABLE(pci, hinic3_pci_table);
+
+static void hinic3_shutdown(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	pci_disable_device(pdev);
+
+	if (pci_adapter)
+		hinic3_set_api_stop(pci_adapter->hwdev);
+}
+
+static struct pci_driver hinic3_driver = {
+	.name            = HINIC3_NIC_DRV_NAME,
+	.id_table        = hinic3_pci_table,
+	.probe           = hinic3_probe,
+	.remove          = hinic3_remove,
+	.shutdown        = hinic3_shutdown,
+	.sriov_configure = pci_sriov_configure_simple
+};
+
+int hinic3_lld_init(void)
+{
+	return pci_register_driver(&hinic3_driver);
+}
+
+void hinic3_lld_exit(void)
+{
+	pci_unregister_driver(&hinic3_driver);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_lld.h b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.h
new file mode 100644
index 000000000000..322b44803476
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_LLD_H_
+#define _HINIC3_LLD_H_
+
+#include <linux/auxiliary_bus.h>
+
+struct hinic3_event_info;
+
+#define HINIC3_NIC_DRV_NAME "hinic3"
+
+int hinic3_lld_init(void);
+void hinic3_lld_exit(void);
+void hinic3_adev_event_register(struct auxiliary_device *adev,
+				void (*event_handler)(struct auxiliary_device *adev,
+						      struct hinic3_event_info *event));
+void hinic3_adev_event_unregister(struct auxiliary_device *adev);
+struct hinic3_hwdev *hinic3_adev_get_hwdev(struct auxiliary_device *adev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_main.c b/drivers/net/ethernet/huawei/hinic3/hinic3_main.c
new file mode 100644
index 000000000000..6d87d4d895ba
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_main.c
@@ -0,0 +1,409 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+
+#include "hinic3_common.h"
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_lld.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_rss.h"
+#include "hinic3_rx.h"
+#include "hinic3_tx.h"
+
+#define HINIC3_NIC_DRV_DESC  "Intelligent Network Interface Card Driver"
+
+#define HINIC3_RX_BUF_LEN          2048
+#define HINIC3_LRO_REPLENISH_THLD  256
+#define HINIC3_NIC_DEV_WQ_NAME     "hinic3_nic_dev_wq"
+
+#define HINIC3_SQ_DEPTH            1024
+#define HINIC3_RQ_DEPTH            1024
+
+#define HINIC3_DEFAULT_TXRX_MSIX_PENDING_LIMIT      2
+#define HINIC3_DEFAULT_TXRX_MSIX_COALESC_TIMER_CFG  25
+#define HINIC3_DEFAULT_TXRX_MSIX_RESEND_TIMER_CFG   7
+
+static void init_intr_coal_param(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_intr_coal_info *info;
+	u16 i;
+
+	for (i = 0; i < nic_dev->max_qps; i++) {
+		info = &nic_dev->intr_coalesce[i];
+		info->pending_limit = HINIC3_DEFAULT_TXRX_MSIX_PENDING_LIMIT;
+		info->coalesce_timer_cfg = HINIC3_DEFAULT_TXRX_MSIX_COALESC_TIMER_CFG;
+		info->resend_timer_cfg = HINIC3_DEFAULT_TXRX_MSIX_RESEND_TIMER_CFG;
+	}
+}
+
+static int hinic3_init_intr_coalesce(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	nic_dev->intr_coalesce = kcalloc(nic_dev->max_qps,
+					 sizeof(*nic_dev->intr_coalesce),
+					 GFP_KERNEL);
+
+	if (!nic_dev->intr_coalesce)
+		return -ENOMEM;
+
+	init_intr_coal_param(netdev);
+
+	return 0;
+}
+
+static void hinic3_free_intr_coalesce(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	kfree(nic_dev->intr_coalesce);
+}
+
+static int hinic3_alloc_txrxqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	int err;
+
+	err = hinic3_alloc_txqs(netdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc txqs\n");
+		return err;
+	}
+
+	err = hinic3_alloc_rxqs(netdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc rxqs\n");
+		goto err_free_txqs;
+	}
+
+	err = hinic3_init_intr_coalesce(netdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init_intr_coalesce\n");
+		goto err_free_rxqs;
+	}
+
+	return 0;
+
+err_free_rxqs:
+	hinic3_free_rxqs(netdev);
+
+err_free_txqs:
+	hinic3_free_txqs(netdev);
+
+	return err;
+}
+
+static void hinic3_free_txrxqs(struct net_device *netdev)
+{
+	hinic3_free_intr_coalesce(netdev);
+	hinic3_free_rxqs(netdev);
+	hinic3_free_txqs(netdev);
+}
+
+static int hinic3_init_nic_dev(struct net_device *netdev,
+			       struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct pci_dev *pdev = hwdev->pdev;
+
+	nic_dev->netdev = netdev;
+	SET_NETDEV_DEV(netdev, &pdev->dev);
+	nic_dev->hwdev = hwdev;
+	nic_dev->pdev = pdev;
+
+	nic_dev->rx_buf_len = HINIC3_RX_BUF_LEN;
+	nic_dev->lro_replenish_thld = HINIC3_LRO_REPLENISH_THLD;
+	nic_dev->nic_svc_cap = hwdev->cfg_mgmt->cap.nic_svc_cap;
+
+	return 0;
+}
+
+static int hinic3_sw_init(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	int err;
+
+	nic_dev->q_params.sq_depth = HINIC3_SQ_DEPTH;
+	nic_dev->q_params.rq_depth = HINIC3_RQ_DEPTH;
+
+	hinic3_try_to_enable_rss(netdev);
+
+	/* VF driver always uses random MAC address. During VM migration to a
+	 * new device, the new device should learn the VMs old MAC rather than
+	 * provide its own MAC. The product design assumes that every VF is
+	 * suspectable to migration so the device avoids offering MAC address
+	 * to VFs.
+	 */
+	eth_hw_addr_random(netdev);
+	err = hinic3_set_mac(hwdev, netdev->dev_addr, 0,
+			     hinic3_global_func_id(hwdev));
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set default MAC\n");
+		goto err_clear_rss_config;
+	}
+
+	err = hinic3_alloc_txrxqs(netdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc qps\n");
+		goto err_del_mac;
+	}
+
+	return 0;
+
+err_del_mac:
+	hinic3_del_mac(hwdev, netdev->dev_addr, 0,
+		       hinic3_global_func_id(hwdev));
+err_clear_rss_config:
+	hinic3_clear_rss_config(netdev);
+
+	return err;
+}
+
+static void hinic3_sw_uninit(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	hinic3_free_txrxqs(netdev);
+	hinic3_del_mac(nic_dev->hwdev, netdev->dev_addr, 0,
+		       hinic3_global_func_id(nic_dev->hwdev));
+	hinic3_clear_rss_config(netdev);
+}
+
+static void hinic3_assign_netdev_ops(struct net_device *netdev)
+{
+	hinic3_set_netdev_ops(netdev);
+}
+
+static void netdev_feature_init(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	netdev_features_t cso_fts = 0;
+	netdev_features_t tso_fts = 0;
+	netdev_features_t dft_fts;
+
+	dft_fts = NETIF_F_SG | NETIF_F_HIGHDMA;
+	if (hinic3_test_support(nic_dev, HINIC3_NIC_F_CSUM))
+		cso_fts |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM;
+	if (hinic3_test_support(nic_dev, HINIC3_NIC_F_SCTP_CRC))
+		cso_fts |= NETIF_F_SCTP_CRC;
+	if (hinic3_test_support(nic_dev, HINIC3_NIC_F_TSO))
+		tso_fts |= NETIF_F_TSO | NETIF_F_TSO6;
+
+	netdev->features |= dft_fts | cso_fts | tso_fts;
+}
+
+static int hinic3_set_default_hw_feature(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	int err;
+
+	err = hinic3_set_nic_feature_to_hw(nic_dev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set nic features\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static void hinic3_link_status_change(struct net_device *netdev,
+				      bool link_status_up)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	if (link_status_up) {
+		if (netif_carrier_ok(netdev))
+			return;
+
+		nic_dev->link_status_up = true;
+		netif_carrier_on(netdev);
+		netdev_dbg(netdev, "Link is up\n");
+	} else {
+		if (!netif_carrier_ok(netdev))
+			return;
+
+		nic_dev->link_status_up = false;
+		netif_carrier_off(netdev);
+		netdev_dbg(netdev, "Link is down\n");
+	}
+}
+
+static void hinic3_nic_event(struct auxiliary_device *adev,
+			     struct hinic3_event_info *event)
+{
+	struct hinic3_nic_dev *nic_dev = dev_get_drvdata(&adev->dev);
+	struct net_device *netdev;
+
+	netdev = nic_dev->netdev;
+
+	switch (HINIC3_SRV_EVENT_TYPE(event->service, event->type)) {
+	case HINIC3_SRV_EVENT_TYPE(HINIC3_EVENT_SRV_NIC,
+				   HINIC3_NIC_EVENT_LINK_UP):
+		hinic3_link_status_change(netdev, true);
+		break;
+	case HINIC3_SRV_EVENT_TYPE(HINIC3_EVENT_SRV_NIC,
+				   HINIC3_NIC_EVENT_LINK_DOWN):
+		hinic3_link_status_change(netdev, false);
+		break;
+	default:
+		break;
+	}
+}
+
+static int hinic3_nic_probe(struct auxiliary_device *adev,
+			    const struct auxiliary_device_id *id)
+{
+	struct hinic3_hwdev *hwdev = hinic3_adev_get_hwdev(adev);
+	struct pci_dev *pdev = hwdev->pdev;
+	struct hinic3_nic_dev *nic_dev;
+	struct net_device *netdev;
+	u16 max_qps, glb_func_id;
+	int err;
+
+	if (!hinic3_support_nic(hwdev)) {
+		dev_dbg(&adev->dev, "HW doesn't support nic\n");
+		return 0;
+	}
+
+	hinic3_adev_event_register(adev, hinic3_nic_event);
+
+	glb_func_id = hinic3_global_func_id(hwdev);
+	err = hinic3_func_reset(hwdev, glb_func_id, COMM_FUNC_RESET_BIT_NIC);
+	if (err) {
+		dev_err(&adev->dev, "Failed to reset function\n");
+		goto err_unregister_adev_event;
+	}
+
+	max_qps = hinic3_func_max_qnum(hwdev);
+	netdev = alloc_etherdev_mq(sizeof(*nic_dev), max_qps);
+	if (!netdev) {
+		dev_err(&adev->dev, "Failed to allocate netdev\n");
+		err = -ENOMEM;
+		goto err_unregister_adev_event;
+	}
+
+	nic_dev = netdev_priv(netdev);
+	dev_set_drvdata(&adev->dev, nic_dev);
+	err = hinic3_init_nic_dev(netdev, hwdev);
+	if (err)
+		goto err_free_netdev;
+
+	err = hinic3_init_nic_io(nic_dev);
+	if (err)
+		goto err_free_netdev;
+
+	err = hinic3_sw_init(netdev);
+	if (err)
+		goto err_free_nic_io;
+
+	hinic3_assign_netdev_ops(netdev);
+
+	netdev_feature_init(netdev);
+	err = hinic3_set_default_hw_feature(netdev);
+	if (err)
+		goto err_uninit_sw;
+
+	netif_carrier_off(netdev);
+
+	err = register_netdev(netdev);
+	if (err)
+		goto err_uninit_nic_feature;
+
+	return 0;
+
+err_uninit_nic_feature:
+	hinic3_update_nic_feature(nic_dev, 0);
+	hinic3_set_nic_feature_to_hw(nic_dev);
+
+err_uninit_sw:
+	hinic3_sw_uninit(netdev);
+
+err_free_nic_io:
+	hinic3_free_nic_io(nic_dev);
+
+err_free_netdev:
+	free_netdev(netdev);
+
+err_unregister_adev_event:
+	hinic3_adev_event_unregister(adev);
+	dev_err(&pdev->dev, "NIC service probe failed\n");
+
+	return err;
+}
+
+static void hinic3_nic_remove(struct auxiliary_device *adev)
+{
+	struct hinic3_nic_dev *nic_dev = dev_get_drvdata(&adev->dev);
+	struct net_device *netdev;
+
+	if (!hinic3_support_nic(nic_dev->hwdev))
+		return;
+
+	netdev = nic_dev->netdev;
+	unregister_netdev(netdev);
+
+	hinic3_update_nic_feature(nic_dev, 0);
+	hinic3_set_nic_feature_to_hw(nic_dev);
+	hinic3_sw_uninit(netdev);
+
+	hinic3_free_nic_io(nic_dev);
+
+	free_netdev(netdev);
+}
+
+static const struct auxiliary_device_id hinic3_nic_id_table[] = {
+	{
+		.name = HINIC3_NIC_DRV_NAME ".nic",
+	},
+	{}
+};
+
+static struct auxiliary_driver hinic3_nic_driver = {
+	.probe    = hinic3_nic_probe,
+	.remove   = hinic3_nic_remove,
+	.suspend  = NULL,
+	.resume   = NULL,
+	.name     = "nic",
+	.id_table = hinic3_nic_id_table,
+};
+
+static __init int hinic3_nic_lld_init(void)
+{
+	int err;
+
+	err = hinic3_lld_init();
+	if (err)
+		return err;
+
+	err = auxiliary_driver_register(&hinic3_nic_driver);
+	if (err) {
+		hinic3_lld_exit();
+		return err;
+	}
+
+	return 0;
+}
+
+static __exit void hinic3_nic_lld_exit(void)
+{
+	auxiliary_driver_unregister(&hinic3_nic_driver);
+
+	hinic3_lld_exit();
+}
+
+module_init(hinic3_nic_lld_init);
+module_exit(hinic3_nic_lld_exit);
+
+MODULE_AUTHOR("Huawei Technologies CO., Ltd");
+MODULE_DESCRIPTION(HINIC3_NIC_DRV_DESC);
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.c b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.c
new file mode 100644
index 000000000000..cf67e26acece
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.c
@@ -0,0 +1,860 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/dma-mapping.h>
+
+#include "hinic3_common.h"
+#include "hinic3_csr.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+#define MBOX_INT_DST_AEQN_MASK        GENMASK(11, 10)
+#define MBOX_INT_SRC_RESP_AEQN_MASK   GENMASK(13, 12)
+#define MBOX_INT_STAT_DMA_MASK        GENMASK(19, 14)
+/* TX size, expressed in 4 bytes units */
+#define MBOX_INT_TX_SIZE_MASK         GENMASK(24, 20)
+/* SO_RO == strong order, relaxed order */
+#define MBOX_INT_STAT_DMA_SO_RO_MASK  GENMASK(26, 25)
+#define MBOX_INT_WB_EN_MASK           BIT(28)
+#define MBOX_INT_SET(val, field)  \
+	FIELD_PREP(MBOX_INT_##field##_MASK, val)
+
+#define MBOX_CTRL_TRIGGER_AEQE_MASK   BIT(0)
+#define MBOX_CTRL_TX_STATUS_MASK      BIT(1)
+#define MBOX_CTRL_DST_FUNC_MASK       GENMASK(28, 16)
+#define MBOX_CTRL_SET(val, field)  \
+	FIELD_PREP(MBOX_CTRL_##field##_MASK, val)
+
+#define MBOX_MSG_POLLING_TIMEOUT_MS  8000 // send msg seg timeout
+#define MBOX_COMP_POLLING_TIMEOUT_MS 40000 // response
+
+#define MBOX_MAX_BUF_SZ           2048
+#define MBOX_HEADER_SZ            8
+
+/* MBOX size is 64B, 8B for mbox_header, 8B reserved */
+#define MBOX_SEG_LEN              48
+#define MBOX_SEG_LEN_ALIGN        4
+#define MBOX_WB_STATUS_LEN        16
+
+#define MBOX_SEQ_ID_START_VAL     0
+#define MBOX_SEQ_ID_MAX_VAL       42
+#define MBOX_LAST_SEG_MAX_LEN  \
+	(MBOX_MAX_BUF_SZ - MBOX_SEQ_ID_MAX_VAL * MBOX_SEG_LEN)
+
+/* mbox write back status is 16B, only first 4B is used */
+#define MBOX_WB_STATUS_ERRCODE_MASK      0xFFFF
+#define MBOX_WB_STATUS_MASK              0xFF
+#define MBOX_WB_ERROR_CODE_MASK          0xFF00
+#define MBOX_WB_STATUS_FINISHED_SUCCESS  0xFF
+#define MBOX_WB_STATUS_NOT_FINISHED      0x00
+
+#define MBOX_STATUS_FINISHED(wb)  \
+	((FIELD_PREP(MBOX_WB_STATUS_MASK, (wb))) != MBOX_WB_STATUS_NOT_FINISHED)
+#define MBOX_STATUS_SUCCESS(wb)  \
+	((FIELD_PREP(MBOX_WB_STATUS_MASK, (wb))) ==  \
+	MBOX_WB_STATUS_FINISHED_SUCCESS)
+#define MBOX_STATUS_ERRCODE(wb)  \
+	((wb) & MBOX_WB_ERROR_CODE_MASK)
+
+#define MBOX_DMA_MSG_QUEUE_DEPTH    32
+#define MBOX_AREA(hwif)  \
+	((hwif)->cfg_regs_base + HINIC3_FUNC_CSR_MAILBOX_DATA_OFF)
+
+#define MBOX_MQ_CI_OFFSET  \
+	(HINIC3_CFG_REGS_FLAG + HINIC3_FUNC_CSR_MAILBOX_DATA_OFF + \
+	 MBOX_HEADER_SZ + MBOX_SEG_LEN)
+
+#define MBOX_MQ_SYNC_CI_MASK   GENMASK(7, 0)
+#define MBOX_MQ_ASYNC_CI_MASK  GENMASK(15, 8)
+#define MBOX_MQ_CI_GET(val, field)  \
+	FIELD_GET(MBOX_MQ_##field##_CI_MASK, val)
+
+#define MBOX_MGMT_FUNC_ID         0x1FFF
+#define MBOX_COMM_F_MBOX_SEGMENT  BIT(3)
+
+static u8 *get_mobx_body_from_hdr(u8 *header)
+{
+	return header + MBOX_HEADER_SZ;
+}
+
+static struct hinic3_msg_desc *get_mbox_msg_desc(struct hinic3_mbox *mbox,
+						 enum mbox_msg_direction_type dir,
+						 u16 src_func_id)
+{
+	struct hinic3_msg_channel *msg_ch;
+
+	msg_ch = (src_func_id == MBOX_MGMT_FUNC_ID) ?
+		&mbox->mgmt_msg : mbox->func_msg;
+
+	return (dir == MBOX_MSG_SEND) ?
+		&msg_ch->recv_msg : &msg_ch->resp_msg;
+}
+
+static void resp_mbox_handler(struct hinic3_mbox *mbox,
+			      const struct hinic3_msg_desc *msg_desc)
+{
+	spin_lock(&mbox->mbox_lock);
+	if (msg_desc->msg_info.msg_id == mbox->send_msg_id &&
+	    mbox->event_flag == MBOX_EVENT_START)
+		mbox->event_flag = MBOX_EVENT_SUCCESS;
+	spin_unlock(&mbox->mbox_lock);
+}
+
+static bool mbox_segment_valid(struct hinic3_mbox *mbox,
+			       struct hinic3_msg_desc *msg_desc,
+			       __le64 mbox_header)
+{
+	u8 seq_id, seg_len, msg_id, mod;
+	__le16 src_func_idx, cmd;
+
+	seq_id = MBOX_MSG_HEADER_GET(mbox_header, SEQID);
+	seg_len = MBOX_MSG_HEADER_GET(mbox_header, SEG_LEN);
+	msg_id = MBOX_MSG_HEADER_GET(mbox_header, MSG_ID);
+	mod = MBOX_MSG_HEADER_GET(mbox_header, MODULE);
+	cmd = cpu_to_le16(MBOX_MSG_HEADER_GET(mbox_header, CMD));
+	src_func_idx = cpu_to_le16(MBOX_MSG_HEADER_GET(mbox_header,
+						       SRC_GLB_FUNC_IDX));
+
+	if (seq_id > MBOX_SEQ_ID_MAX_VAL || seg_len > MBOX_SEG_LEN ||
+	    (seq_id == MBOX_SEQ_ID_MAX_VAL && seg_len > MBOX_LAST_SEG_MAX_LEN))
+		goto err_seg;
+
+	if (seq_id == 0) {
+		msg_desc->seq_id = seq_id;
+		msg_desc->msg_info.msg_id = msg_id;
+		msg_desc->mod = mod;
+		msg_desc->cmd = cmd;
+	} else {
+		if (seq_id != msg_desc->seq_id + 1 ||
+		    msg_id != msg_desc->msg_info.msg_id ||
+		    mod != msg_desc->mod || cmd != msg_desc->cmd)
+			goto err_seg;
+
+		msg_desc->seq_id = seq_id;
+	}
+
+	return true;
+
+err_seg:
+	dev_err(mbox->hwdev->dev,
+		"Mailbox segment check failed, src func id: 0x%x, front seg info: seq id: 0x%x, msg id: 0x%x, mod: 0x%x, cmd: 0x%x\n",
+		src_func_idx, msg_desc->seq_id, msg_desc->msg_info.msg_id,
+		msg_desc->mod, msg_desc->cmd);
+	dev_err(mbox->hwdev->dev,
+		"Current seg info: seg len: 0x%x, seq id: 0x%x, msg id: 0x%x, mod: 0x%x, cmd: 0x%x\n",
+		seg_len, seq_id, msg_id, mod, cmd);
+
+	return false;
+}
+
+static void recv_mbox_handler(struct hinic3_mbox *mbox,
+			      u8 *header, struct hinic3_msg_desc *msg_desc)
+{
+	__le64 mbox_header = *((__force __le64 *)header);
+	u8 *mbox_body = get_mobx_body_from_hdr(header);
+	u8 seq_id, seg_len;
+	int pos;
+
+	if (!mbox_segment_valid(mbox, msg_desc, mbox_header)) {
+		msg_desc->seq_id = MBOX_SEQ_ID_MAX_VAL;
+		return;
+	}
+
+	seq_id = MBOX_MSG_HEADER_GET(mbox_header, SEQID);
+	seg_len = MBOX_MSG_HEADER_GET(mbox_header, SEG_LEN);
+
+	pos = seq_id * MBOX_SEG_LEN;
+	memcpy(msg_desc->msg + pos, mbox_body, seg_len);
+
+	if (!MBOX_MSG_HEADER_GET(mbox_header, LAST))
+		return;
+
+	msg_desc->msg_len = cpu_to_le16(MBOX_MSG_HEADER_GET(mbox_header,
+							    MSG_LEN));
+	msg_desc->msg_info.status = MBOX_MSG_HEADER_GET(mbox_header, STATUS);
+
+	if (MBOX_MSG_HEADER_GET(mbox_header, DIRECTION) == MBOX_MSG_RESP)
+		resp_mbox_handler(mbox, msg_desc);
+}
+
+void hinic3_mbox_func_aeqe_handler(struct hinic3_hwdev *hwdev, u8 *header,
+				   u8 size)
+{
+	__le64 mbox_header = *((__force __le64 *)header);
+	enum mbox_msg_direction_type dir;
+	struct hinic3_msg_desc *msg_desc;
+	struct hinic3_mbox *mbox;
+	u16 src_func_id;
+
+	mbox = hwdev->mbox;
+	dir = MBOX_MSG_HEADER_GET(mbox_header, DIRECTION);
+	src_func_id = MBOX_MSG_HEADER_GET(mbox_header, SRC_GLB_FUNC_IDX);
+	msg_desc = get_mbox_msg_desc(mbox, dir, src_func_id);
+	recv_mbox_handler(mbox, header, msg_desc);
+}
+
+static int init_mbox_dma_queue(struct hinic3_hwdev *hwdev,
+			       struct mbox_dma_queue *mq)
+{
+	u32 size;
+
+	mq->depth = MBOX_DMA_MSG_QUEUE_DEPTH;
+	mq->prod_idx = 0;
+	mq->cons_idx = 0;
+
+	size = mq->depth * MBOX_MAX_BUF_SZ;
+	mq->dma_buf_vaddr = dma_alloc_coherent(hwdev->dev, size,
+					       &mq->dma_buf_paddr,
+					       GFP_KERNEL);
+	if (!mq->dma_buf_vaddr)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void uninit_mbox_dma_queue(struct hinic3_hwdev *hwdev,
+				  struct mbox_dma_queue *mq)
+{
+	dma_free_coherent(hwdev->dev, mq->depth * MBOX_MAX_BUF_SZ,
+			  mq->dma_buf_vaddr, mq->dma_buf_paddr);
+}
+
+static int hinic3_init_mbox_dma_queue(struct hinic3_mbox *mbox)
+{
+	u32 val;
+	int err;
+
+	err = init_mbox_dma_queue(mbox->hwdev, &mbox->sync_msg_queue);
+	if (err)
+		return err;
+
+	err = init_mbox_dma_queue(mbox->hwdev, &mbox->async_msg_queue);
+	if (err) {
+		uninit_mbox_dma_queue(mbox->hwdev, &mbox->sync_msg_queue);
+		return err;
+	}
+
+	val = hinic3_hwif_read_reg(mbox->hwdev->hwif, MBOX_MQ_CI_OFFSET);
+	val &= ~MBOX_MQ_SYNC_CI_MASK;
+	val &= ~MBOX_MQ_ASYNC_CI_MASK;
+	hinic3_hwif_write_reg(mbox->hwdev->hwif, MBOX_MQ_CI_OFFSET, val);
+
+	return 0;
+}
+
+static void hinic3_uninit_mbox_dma_queue(struct hinic3_mbox *mbox)
+{
+	uninit_mbox_dma_queue(mbox->hwdev, &mbox->sync_msg_queue);
+	uninit_mbox_dma_queue(mbox->hwdev, &mbox->async_msg_queue);
+}
+
+static int alloc_mbox_msg_channel(struct hinic3_msg_channel *msg_ch)
+{
+	msg_ch->resp_msg.msg = kzalloc(MBOX_MAX_BUF_SZ, GFP_KERNEL);
+	if (!msg_ch->resp_msg.msg)
+		return -ENOMEM;
+
+	msg_ch->recv_msg.msg = kzalloc(MBOX_MAX_BUF_SZ, GFP_KERNEL);
+	if (!msg_ch->recv_msg.msg) {
+		kfree(msg_ch->resp_msg.msg);
+		return -ENOMEM;
+	}
+
+	msg_ch->resp_msg.seq_id = MBOX_SEQ_ID_MAX_VAL;
+	msg_ch->recv_msg.seq_id = MBOX_SEQ_ID_MAX_VAL;
+
+	return 0;
+}
+
+static void free_mbox_msg_channel(struct hinic3_msg_channel *msg_ch)
+{
+	kfree(msg_ch->recv_msg.msg);
+	kfree(msg_ch->resp_msg.msg);
+}
+
+static int init_mgmt_msg_channel(struct hinic3_mbox *mbox)
+{
+	int err;
+
+	err = alloc_mbox_msg_channel(&mbox->mgmt_msg);
+	if (err) {
+		dev_err(mbox->hwdev->dev, "Failed to alloc mgmt message channel\n");
+		return err;
+	}
+
+	err = hinic3_init_mbox_dma_queue(mbox);
+	if (err) {
+		dev_err(mbox->hwdev->dev, "Failed to init mbox dma queue\n");
+		free_mbox_msg_channel(&mbox->mgmt_msg);
+		return err;
+	}
+
+	return 0;
+}
+
+static void uninit_mgmt_msg_channel(struct hinic3_mbox *mbox)
+{
+	hinic3_uninit_mbox_dma_queue(mbox);
+	free_mbox_msg_channel(&mbox->mgmt_msg);
+}
+
+static int hinic3_init_func_mbox_msg_channel(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_mbox *mbox;
+	int err;
+
+	mbox = hwdev->mbox;
+	mbox->func_msg = kzalloc(sizeof(*mbox->func_msg), GFP_KERNEL);
+	if (!mbox->func_msg)
+		return -ENOMEM;
+
+	err = alloc_mbox_msg_channel(mbox->func_msg);
+	if (err)
+		goto err_free_func_msg;
+
+	return 0;
+
+err_free_func_msg:
+	kfree(mbox->func_msg);
+	mbox->func_msg = NULL;
+
+	return err;
+}
+
+static void hinic3_uninit_func_mbox_msg_channel(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_mbox *mbox = hwdev->mbox;
+
+	free_mbox_msg_channel(mbox->func_msg);
+	kfree(mbox->func_msg);
+	mbox->func_msg = NULL;
+}
+
+static void prepare_send_mbox(struct hinic3_mbox *mbox)
+{
+	struct hinic3_send_mbox *send_mbox = &mbox->send_mbox;
+
+	send_mbox->data = MBOX_AREA(mbox->hwdev->hwif);
+}
+
+static int alloc_mbox_wb_status(struct hinic3_mbox *mbox)
+{
+	struct hinic3_send_mbox *send_mbox = &mbox->send_mbox;
+	struct hinic3_hwdev *hwdev = mbox->hwdev;
+	u32 addr_h, addr_l;
+
+	send_mbox->wb_vaddr = dma_alloc_coherent(hwdev->dev,
+						 MBOX_WB_STATUS_LEN,
+						 &send_mbox->wb_paddr,
+						 GFP_KERNEL);
+	if (!send_mbox->wb_vaddr)
+		return -ENOMEM;
+
+	addr_h = upper_32_bits(send_mbox->wb_paddr);
+	addr_l = lower_32_bits(send_mbox->wb_paddr);
+	hinic3_hwif_write_reg(hwdev->hwif, HINIC3_FUNC_CSR_MAILBOX_RESULT_H_OFF,
+			      addr_h);
+	hinic3_hwif_write_reg(hwdev->hwif, HINIC3_FUNC_CSR_MAILBOX_RESULT_L_OFF,
+			      addr_l);
+
+	return 0;
+}
+
+static void free_mbox_wb_status(struct hinic3_mbox *mbox)
+{
+	struct hinic3_send_mbox *send_mbox = &mbox->send_mbox;
+	struct hinic3_hwdev *hwdev = mbox->hwdev;
+
+	hinic3_hwif_write_reg(hwdev->hwif, HINIC3_FUNC_CSR_MAILBOX_RESULT_H_OFF,
+			      0);
+	hinic3_hwif_write_reg(hwdev->hwif, HINIC3_FUNC_CSR_MAILBOX_RESULT_L_OFF,
+			      0);
+
+	dma_free_coherent(hwdev->dev, MBOX_WB_STATUS_LEN,
+			  send_mbox->wb_vaddr, send_mbox->wb_paddr);
+}
+
+static int hinic3_mbox_pre_init(struct hinic3_hwdev *hwdev,
+				struct hinic3_mbox *mbox)
+{
+	mbox->hwdev = hwdev;
+	mutex_init(&mbox->mbox_send_lock);
+	spin_lock_init(&mbox->mbox_lock);
+
+	mbox->workq = create_singlethread_workqueue(HINIC3_MBOX_WQ_NAME);
+	if (!mbox->workq) {
+		dev_err(hwdev->dev, "Failed to initialize MBOX workqueue\n");
+		return -ENOMEM;
+	}
+	hwdev->mbox = mbox;
+
+	return 0;
+}
+
+int hinic3_init_mbox(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_mbox *mbox;
+	int err;
+
+	mbox = kzalloc(sizeof(*mbox), GFP_KERNEL);
+	if (!mbox)
+		return -ENOMEM;
+
+	err = hinic3_mbox_pre_init(hwdev, mbox);
+	if (err)
+		goto err_free_mbox;
+
+	err = init_mgmt_msg_channel(mbox);
+	if (err)
+		goto err_destroy_workqueue;
+
+	err = hinic3_init_func_mbox_msg_channel(hwdev);
+	if (err)
+		goto err_uninit_mgmt_msg_ch;
+
+	err = alloc_mbox_wb_status(mbox);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc mbox write back status\n");
+		goto err_uninit_func_mbox_msg_ch;
+	}
+
+	prepare_send_mbox(mbox);
+
+	return 0;
+
+err_uninit_func_mbox_msg_ch:
+	hinic3_uninit_func_mbox_msg_channel(hwdev);
+
+err_uninit_mgmt_msg_ch:
+	uninit_mgmt_msg_channel(mbox);
+
+err_destroy_workqueue:
+	destroy_workqueue(mbox->workq);
+
+err_free_mbox:
+	kfree(mbox);
+
+	return err;
+}
+
+void hinic3_free_mbox(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_mbox *mbox = hwdev->mbox;
+
+	destroy_workqueue(mbox->workq);
+	free_mbox_wb_status(mbox);
+	hinic3_uninit_func_mbox_msg_channel(hwdev);
+	uninit_mgmt_msg_channel(mbox);
+	kfree(mbox);
+}
+
+#define MBOX_DMA_MSG_INIT_XOR_VAL    0x5a5a5a5a
+#define MBOX_XOR_DATA_ALIGN          4
+static u32 mbox_dma_msg_xor(u32 *data, u32 msg_len)
+{
+	u32 xor = MBOX_DMA_MSG_INIT_XOR_VAL;
+	u32 dw_len = msg_len / sizeof(u32);
+	u32 i;
+
+	for (i = 0; i < dw_len; i++)
+		xor ^= data[i];
+
+	return xor;
+}
+
+#define MBOX_MQ_ID_MASK(mq, idx)  ((idx) & ((mq)->depth - 1))
+
+static bool is_msg_queue_full(struct mbox_dma_queue *mq)
+{
+	return MBOX_MQ_ID_MASK(mq, (mq)->prod_idx + 1) ==
+	       MBOX_MQ_ID_MASK(mq, (mq)->cons_idx);
+}
+
+static int mbox_prepare_dma_entry(struct hinic3_mbox *mbox,
+				  struct mbox_dma_queue *mq,
+				  struct mbox_dma_msg *dma_msg,
+				  const void *msg, u32 msg_len)
+{
+	u64 dma_addr, offset;
+	void *dma_vaddr;
+
+	if (is_msg_queue_full(mq)) {
+		dev_err(mbox->hwdev->dev, "Mbox sync message queue is busy, pi: %u, ci: %u\n",
+			mq->prod_idx, MBOX_MQ_ID_MASK(mq, mq->cons_idx));
+		return -EBUSY;
+	}
+
+	/* copy data to DMA buffer */
+	offset = mq->prod_idx * MBOX_MAX_BUF_SZ;
+	dma_vaddr = (u8 *)mq->dma_buf_vaddr + offset;
+	memcpy(dma_vaddr, msg, msg_len);
+	dma_addr = mq->dma_buf_paddr + offset;
+	dma_msg->dma_addr_high = cpu_to_le32(upper_32_bits(dma_addr));
+	dma_msg->dma_addr_low = cpu_to_le32(lower_32_bits(dma_addr));
+	dma_msg->msg_len = cpu_to_le32(msg_len);
+	/* The firmware obtains message based on 4B alignment. */
+	dma_msg->xor = cpu_to_le32(mbox_dma_msg_xor(dma_vaddr,
+						    ALIGN(msg_len, MBOX_XOR_DATA_ALIGN)));
+	mq->prod_idx++;
+	mq->prod_idx = MBOX_MQ_ID_MASK(mq, mq->prod_idx);
+
+	return 0;
+}
+
+static int mbox_prepare_dma_msg(struct hinic3_mbox *mbox,
+				enum mbox_msg_ack_type ack_type,
+				struct mbox_dma_msg *dma_msg, const void *msg,
+				u32 msg_len)
+{
+	struct mbox_dma_queue *mq;
+	u32 val;
+
+	val = hinic3_hwif_read_reg(mbox->hwdev->hwif, MBOX_MQ_CI_OFFSET);
+	if (ack_type == MBOX_MSG_ACK) {
+		mq = &mbox->sync_msg_queue;
+		mq->cons_idx = MBOX_MQ_CI_GET(val, SYNC);
+	} else {
+		mq = &mbox->async_msg_queue;
+		mq->cons_idx = MBOX_MQ_CI_GET(val, ASYNC);
+	}
+
+	return mbox_prepare_dma_entry(mbox, mq, dma_msg, msg, msg_len);
+}
+
+static void clear_mbox_status(struct hinic3_send_mbox *mbox)
+{
+	__be64 *wb_status = mbox->wb_vaddr;
+
+	*wb_status = 0;
+	/* clear mailbox write back status */
+	wmb();
+}
+
+static void mbox_dword_write(const void *src, void __iomem *dst, u32 count)
+{
+	const __le32 *src32 = src;
+	u32 __iomem *dst32 = dst;
+	u32 i;
+
+	/* Data written to mbox is arranged in structs with little endian fields
+	 * but when written to HW every dword (32bits) should be swapped since
+	 * the HW will swap it again.
+	 */
+	for (i = 0; i < count; i++)
+		__raw_writel(swab32((__force __u32)src32[i]), dst32 + i);
+}
+
+static void mbox_copy_header(struct hinic3_hwdev *hwdev,
+			     struct hinic3_send_mbox *mbox, __le64 *header)
+{
+	mbox_dword_write(header, mbox->data, MBOX_HEADER_SZ / sizeof(__le32));
+}
+
+static void mbox_copy_send_data(struct hinic3_hwdev *hwdev,
+				struct hinic3_send_mbox *mbox, void *seg,
+				u32 seg_len)
+{
+	u32 __iomem *dst = (u32 __iomem *)(mbox->data + MBOX_HEADER_SZ);
+	u32 count, leftover, last_dword;
+	const __le32 *src = seg;
+
+	count = seg_len / sizeof(u32);
+	leftover = seg_len % sizeof(u32);
+	if (count > 0)
+		mbox_dword_write(src, dst, count);
+
+	if (leftover > 0) {
+		last_dword = 0;
+		memcpy(&last_dword, src + count, leftover);
+		mbox_dword_write(&last_dword, dst + count, 1);
+	}
+}
+
+static void write_mbox_msg_attr(struct hinic3_mbox *mbox,
+				u16 dst_func, u16 dst_aeqn, u32 seg_len)
+{
+	struct hinic3_hwif *hwif = mbox->hwdev->hwif;
+	u32 mbox_int, mbox_ctrl, tx_size;
+
+	tx_size = ALIGN(seg_len + MBOX_HEADER_SZ, MBOX_SEG_LEN_ALIGN) >> 2;
+
+	mbox_int = MBOX_INT_SET(dst_aeqn, DST_AEQN) |
+		   MBOX_INT_SET(0, STAT_DMA) |
+		   MBOX_INT_SET(tx_size, TX_SIZE) |
+		   MBOX_INT_SET(0, STAT_DMA_SO_RO) |
+		   MBOX_INT_SET(1, WB_EN);
+
+	mbox_ctrl = MBOX_CTRL_SET(1, TX_STATUS) |
+		    MBOX_CTRL_SET(0, TRIGGER_AEQE) |
+		    MBOX_CTRL_SET(dst_func, DST_FUNC);
+
+	hinic3_hwif_write_reg(hwif, HINIC3_FUNC_CSR_MAILBOX_INT_OFF, mbox_int);
+	hinic3_hwif_write_reg(hwif, HINIC3_FUNC_CSR_MAILBOX_CONTROL_OFF,
+			      mbox_ctrl);
+}
+
+static u16 get_mbox_status(const struct hinic3_send_mbox *mbox)
+{
+	__be64 *wb_status = mbox->wb_vaddr;
+	u64 wb_val;
+
+	wb_val = be64_to_cpu(*wb_status);
+	/* verify reading before check */
+	rmb();
+
+	return wb_val & MBOX_WB_STATUS_ERRCODE_MASK;
+}
+
+static enum hinic3_wait_return check_mbox_wb_status(void *priv_data)
+{
+	struct hinic3_mbox *mbox = priv_data;
+	u16 wb_status;
+
+	wb_status = get_mbox_status(&mbox->send_mbox);
+
+	return MBOX_STATUS_FINISHED(wb_status) ?
+	       HINIC3_WAIT_PROCESS_CPL : HINIC3_WAIT_PROCESS_WAITING;
+}
+
+static int send_mbox_seg(struct hinic3_mbox *mbox, __le64 header,
+			 u16 dst_func, void *seg, u32 seg_len, void *msg_info)
+{
+	struct hinic3_send_mbox *send_mbox = &mbox->send_mbox;
+	struct hinic3_hwdev *hwdev = mbox->hwdev;
+	u8 num_aeqs = hwdev->hwif->attr.num_aeqs;
+	enum mbox_msg_direction_type dir;
+	u16 dst_aeqn, wb_status, errcode;
+	int err;
+
+	/* mbox to mgmt cpu, hardware doesn't care about dst aeq id */
+	if (num_aeqs > MBOX_MSG_AEQ_FOR_MBOX) {
+		dir = MBOX_MSG_HEADER_GET(header, DIRECTION);
+		dst_aeqn = (dir == MBOX_MSG_SEND) ?
+			   MBOX_MSG_AEQ_FOR_EVENT : MBOX_MSG_AEQ_FOR_MBOX;
+	} else {
+		dst_aeqn = 0;
+	}
+
+	clear_mbox_status(send_mbox);
+	mbox_copy_header(hwdev, send_mbox, &header);
+	mbox_copy_send_data(hwdev, send_mbox, seg, seg_len);
+	write_mbox_msg_attr(mbox, dst_func, dst_aeqn, seg_len);
+
+	err = hinic3_wait_for_timeout(mbox, check_mbox_wb_status,
+				      MBOX_MSG_POLLING_TIMEOUT_MS,
+				      USEC_PER_MSEC);
+	wb_status = get_mbox_status(send_mbox);
+	if (err) {
+		dev_err(hwdev->dev, "Send mailbox segment timeout, wb status: 0x%x\n",
+			wb_status);
+		return err;
+	}
+
+	if (!MBOX_STATUS_SUCCESS(wb_status)) {
+		dev_err(hwdev->dev,
+			"Send mailbox segment to function %u error, wb status: 0x%x\n",
+			dst_func, wb_status);
+		errcode = MBOX_STATUS_ERRCODE(wb_status);
+		return errcode ? errcode : -EFAULT;
+	}
+
+	return 0;
+}
+
+static int send_mbox_msg(struct hinic3_mbox *mbox, u8 mod, u16 cmd,
+			 const void *msg, u32 msg_len, u16 dst_func,
+			 enum mbox_msg_direction_type direction,
+			 enum mbox_msg_ack_type ack_type,
+			 struct mbox_msg_info *msg_info)
+{
+	enum mbox_msg_data_type data_type = MBOX_MSG_DATA_INLINE;
+	struct hinic3_hwdev *hwdev = mbox->hwdev;
+	struct mbox_dma_msg dma_msg;
+	u32 seg_len = MBOX_SEG_LEN;
+	__le64 header = 0;
+	u32 seq_id = 0;
+	u16 rsp_aeq_id;
+	u8 *msg_seg;
+	int err = 0;
+	u32 left;
+
+	if (hwdev->hwif->attr.num_aeqs > MBOX_MSG_AEQ_FOR_MBOX)
+		rsp_aeq_id = MBOX_MSG_AEQ_FOR_MBOX;
+	else
+		rsp_aeq_id = 0;
+
+	if (dst_func == MBOX_MGMT_FUNC_ID &&
+	    !(hwdev->features[0] & MBOX_COMM_F_MBOX_SEGMENT)) {
+		err = mbox_prepare_dma_msg(mbox, ack_type, &dma_msg,
+					   msg, msg_len);
+		if (err)
+			goto err_send;
+
+		msg = &dma_msg;
+		msg_len = sizeof(dma_msg);
+		data_type = MBOX_MSG_DATA_DMA;
+	}
+
+	msg_seg = (u8 *)msg;
+	left = msg_len;
+
+	header = cpu_to_le64(MBOX_MSG_HEADER_SET(msg_len, MSG_LEN) |
+			     MBOX_MSG_HEADER_SET(mod, MODULE) |
+			     MBOX_MSG_HEADER_SET(seg_len, SEG_LEN) |
+			     MBOX_MSG_HEADER_SET(ack_type, NO_ACK) |
+			     MBOX_MSG_HEADER_SET(data_type, DATA_TYPE) |
+			     MBOX_MSG_HEADER_SET(MBOX_SEQ_ID_START_VAL, SEQID) |
+			     MBOX_MSG_HEADER_SET(direction, DIRECTION) |
+			     MBOX_MSG_HEADER_SET(cmd, CMD) |
+			     MBOX_MSG_HEADER_SET(msg_info->msg_id, MSG_ID) |
+			     MBOX_MSG_HEADER_SET(rsp_aeq_id, AEQ_ID) |
+			     MBOX_MSG_HEADER_SET(MBOX_MSG_FROM_MBOX, SOURCE) |
+			     MBOX_MSG_HEADER_SET(!!msg_info->status, STATUS));
+
+	while (!(MBOX_MSG_HEADER_GET(header, LAST))) {
+		if (left <= MBOX_SEG_LEN) {
+			header &= cpu_to_le64(~MBOX_MSG_HEADER_SEG_LEN_MASK);
+			header |=
+				cpu_to_le64(MBOX_MSG_HEADER_SET(left, SEG_LEN) |
+					    MBOX_MSG_HEADER_SET(1, LAST));
+			seg_len = left;
+		}
+
+		err = send_mbox_seg(mbox, header, dst_func, msg_seg,
+				    seg_len, msg_info);
+		if (err) {
+			dev_err(hwdev->dev, "Failed to send mbox seg, seq_id=0x%llx\n",
+				MBOX_MSG_HEADER_GET(header, SEQID));
+			goto err_send;
+		}
+
+		left -= MBOX_SEG_LEN;
+		msg_seg += MBOX_SEG_LEN;
+		seq_id++;
+		header &= cpu_to_le64(~MBOX_MSG_HEADER_SEG_LEN_MASK);
+		header |= cpu_to_le64(MBOX_MSG_HEADER_SET(seq_id, SEQID));
+	}
+
+err_send:
+	return err;
+}
+
+static void set_mbox_to_func_event(struct hinic3_mbox *mbox,
+				   enum mbox_event_state event_flag)
+{
+	spin_lock(&mbox->mbox_lock);
+	mbox->event_flag = event_flag;
+	spin_unlock(&mbox->mbox_lock);
+}
+
+static enum hinic3_wait_return check_mbox_msg_finish(void *priv_data)
+{
+	struct hinic3_mbox *mbox = priv_data;
+
+	return (mbox->event_flag == MBOX_EVENT_SUCCESS) ?
+		HINIC3_WAIT_PROCESS_CPL : HINIC3_WAIT_PROCESS_WAITING;
+}
+
+static int wait_mbox_msg_completion(struct hinic3_mbox *mbox,
+				    u32 timeout)
+{
+	u32 wait_time;
+	int err;
+
+	wait_time = (timeout != 0) ? timeout : MBOX_COMP_POLLING_TIMEOUT_MS;
+	err = hinic3_wait_for_timeout(mbox, check_mbox_msg_finish,
+				      wait_time, USEC_PER_MSEC);
+	if (err) {
+		set_mbox_to_func_event(mbox, MBOX_EVENT_TIMEOUT);
+		return err;
+	}
+	set_mbox_to_func_event(mbox, MBOX_EVENT_END);
+
+	return 0;
+}
+
+int hinic3_send_mbox_to_mgmt(struct hinic3_hwdev *hwdev, u8 mod, u16 cmd,
+			     const struct mgmt_msg_params *msg_params)
+{
+	struct hinic3_mbox *mbox = hwdev->mbox;
+	struct mbox_msg_info msg_info = {};
+	struct hinic3_msg_desc *msg_desc;
+	u32 msg_len;
+	int err;
+
+	/* expect response message */
+	msg_desc = get_mbox_msg_desc(mbox, MBOX_MSG_RESP, MBOX_MGMT_FUNC_ID);
+	mutex_lock(&mbox->mbox_send_lock);
+	msg_info.msg_id = (mbox->send_msg_id + 1) & 0xF;
+	mbox->send_msg_id = msg_info.msg_id;
+	set_mbox_to_func_event(mbox, MBOX_EVENT_START);
+
+	err = send_mbox_msg(mbox, mod, cmd, msg_params->buf_in,
+			    msg_params->in_size, MBOX_MGMT_FUNC_ID,
+			    MBOX_MSG_SEND, MBOX_MSG_ACK, &msg_info);
+	if (err) {
+		dev_err(hwdev->dev, "Send mailbox mod %u, cmd %u failed, msg_id: %u, err: %d\n",
+			mod, cmd, msg_info.msg_id, err);
+		set_mbox_to_func_event(mbox, MBOX_EVENT_FAIL);
+		goto err_send;
+	}
+
+	if (wait_mbox_msg_completion(mbox, msg_params->timeout_ms)) {
+		dev_err(hwdev->dev,
+			"Send mbox msg timeout, msg_id: %u\n", msg_info.msg_id);
+		err = -ETIMEDOUT;
+		goto err_send;
+	}
+
+	if (mod != msg_desc->mod || cmd != le16_to_cpu(msg_desc->cmd)) {
+		dev_err(hwdev->dev,
+			"Invalid response mbox message, mod: 0x%x, cmd: 0x%x, expect mod: 0x%x, cmd: 0x%x\n",
+			msg_desc->mod, msg_desc->cmd, mod, cmd);
+		err = -EFAULT;
+		goto err_send;
+	}
+
+	if (msg_desc->msg_info.status) {
+		err = msg_desc->msg_info.status;
+		goto err_send;
+	}
+
+	if (msg_params->buf_out) {
+		msg_len = le16_to_cpu(msg_desc->msg_len);
+		if (msg_len != msg_params->expected_out_size) {
+			dev_err(hwdev->dev,
+				"Invalid response mbox message length: %u for mod %d cmd %u, expected length: %u\n",
+				msg_desc->msg_len, mod, cmd,
+				msg_params->expected_out_size);
+			err = -EFAULT;
+			goto err_send;
+		}
+
+		memcpy(msg_params->buf_out, msg_desc->msg, msg_len);
+	}
+
+err_send:
+	mutex_unlock(&mbox->mbox_send_lock);
+
+	return err;
+}
+
+int hinic3_send_mbox_to_mgmt_no_ack(struct hinic3_hwdev *hwdev, u8 mod, u16 cmd,
+				    const struct mgmt_msg_params *msg_params)
+{
+	struct hinic3_mbox *mbox = hwdev->mbox;
+	struct mbox_msg_info msg_info = {};
+	int err;
+
+	mutex_lock(&mbox->mbox_send_lock);
+	err = send_mbox_msg(mbox, mod, cmd, msg_params->buf_in,
+			    msg_params->in_size, MBOX_MGMT_FUNC_ID,
+			    MBOX_MSG_SEND, MBOX_MSG_NO_ACK, &msg_info);
+	if (err)
+		dev_err(hwdev->dev, "Send mailbox no ack failed\n");
+
+	mutex_unlock(&mbox->mbox_send_lock);
+
+	return err;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.h b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.h
new file mode 100644
index 000000000000..e71629e95086
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.h
@@ -0,0 +1,141 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_MBOX_H_
+#define _HINIC3_MBOX_H_
+
+#include <linux/bitfield.h>
+#include <linux/mutex.h>
+
+struct hinic3_hwdev;
+struct mgmt_msg_params;
+
+#define MBOX_MSG_HEADER_SRC_GLB_FUNC_IDX_MASK  GENMASK_ULL(12, 0)
+#define MBOX_MSG_HEADER_STATUS_MASK            BIT_ULL(13)
+#define MBOX_MSG_HEADER_SOURCE_MASK            BIT_ULL(15)
+#define MBOX_MSG_HEADER_AEQ_ID_MASK            GENMASK_ULL(17, 16)
+#define MBOX_MSG_HEADER_MSG_ID_MASK            GENMASK_ULL(21, 18)
+#define MBOX_MSG_HEADER_CMD_MASK               GENMASK_ULL(31, 22)
+#define MBOX_MSG_HEADER_MSG_LEN_MASK           GENMASK_ULL(42, 32)
+#define MBOX_MSG_HEADER_MODULE_MASK            GENMASK_ULL(47, 43)
+#define MBOX_MSG_HEADER_SEG_LEN_MASK           GENMASK_ULL(53, 48)
+#define MBOX_MSG_HEADER_NO_ACK_MASK            BIT_ULL(54)
+#define MBOX_MSG_HEADER_DATA_TYPE_MASK         BIT_ULL(55)
+#define MBOX_MSG_HEADER_SEQID_MASK             GENMASK_ULL(61, 56)
+#define MBOX_MSG_HEADER_LAST_MASK              BIT_ULL(62)
+#define MBOX_MSG_HEADER_DIRECTION_MASK         BIT_ULL(63)
+
+#define MBOX_MSG_HEADER_SET(val, member) \
+	FIELD_PREP(MBOX_MSG_HEADER_##member##_MASK, val)
+#define MBOX_MSG_HEADER_GET(val, member) \
+	FIELD_GET(MBOX_MSG_HEADER_##member##_MASK, le64_to_cpu(val))
+
+/* identifies if a segment belongs to a message or to a response. A VF is only
+ * expected to send messages and receive responses. PF driver could receive
+ * messages and send responses.
+ */
+enum mbox_msg_direction_type {
+	MBOX_MSG_SEND = 0,
+	MBOX_MSG_RESP = 1,
+};
+
+/* Indicates if mbox message expects a response (ack) or not */
+enum mbox_msg_ack_type {
+	MBOX_MSG_ACK    = 0,
+	MBOX_MSG_NO_ACK = 1,
+};
+
+enum mbox_msg_data_type {
+	MBOX_MSG_DATA_INLINE = 0,
+	MBOX_MSG_DATA_DMA    = 1,
+};
+
+enum mbox_msg_src_type {
+	MBOX_MSG_FROM_MBOX = 1,
+};
+
+enum mbox_msg_aeq_type {
+	MBOX_MSG_AEQ_FOR_EVENT = 0,
+	MBOX_MSG_AEQ_FOR_MBOX  = 1,
+};
+
+#define HINIC3_MBOX_WQ_NAME  "hinic3_mbox"
+
+struct mbox_msg_info {
+	u8 msg_id;
+	u8 status;
+};
+
+struct hinic3_msg_desc {
+	u8                   *msg;
+	__le16               msg_len;
+	u8                   seq_id;
+	u8                   mod;
+	__le16               cmd;
+	struct mbox_msg_info msg_info;
+};
+
+struct hinic3_msg_channel {
+	struct   hinic3_msg_desc resp_msg;
+	struct   hinic3_msg_desc recv_msg;
+};
+
+struct hinic3_send_mbox {
+	u8 __iomem *data;
+	void       *wb_vaddr;
+	dma_addr_t wb_paddr;
+};
+
+enum mbox_event_state {
+	MBOX_EVENT_START   = 0,
+	MBOX_EVENT_FAIL    = 1,
+	MBOX_EVENT_SUCCESS = 2,
+	MBOX_EVENT_TIMEOUT = 3,
+	MBOX_EVENT_END     = 4,
+};
+
+struct mbox_dma_msg {
+	__le32 xor;
+	__le32 dma_addr_high;
+	__le32 dma_addr_low;
+	__le32 msg_len;
+	__le64 rsvd;
+};
+
+struct mbox_dma_queue {
+	void       *dma_buf_vaddr;
+	dma_addr_t dma_buf_paddr;
+	u16        depth;
+	u16        prod_idx;
+	u16        cons_idx;
+};
+
+struct hinic3_mbox {
+	struct hinic3_hwdev       *hwdev;
+	/* lock for send mbox message and ack message */
+	struct mutex              mbox_send_lock;
+	struct hinic3_send_mbox   send_mbox;
+	struct mbox_dma_queue     sync_msg_queue;
+	struct mbox_dma_queue     async_msg_queue;
+	struct workqueue_struct   *workq;
+	/* driver and MGMT CPU */
+	struct hinic3_msg_channel mgmt_msg;
+	/* VF to PF */
+	struct hinic3_msg_channel *func_msg;
+	u8                        send_msg_id;
+	enum mbox_event_state     event_flag;
+	/* lock for mbox event flag */
+	spinlock_t                mbox_lock;
+};
+
+void hinic3_mbox_func_aeqe_handler(struct hinic3_hwdev *hwdev, u8 *header,
+				   u8 size);
+int hinic3_init_mbox(struct hinic3_hwdev *hwdev);
+void hinic3_free_mbox(struct hinic3_hwdev *hwdev);
+
+int hinic3_send_mbox_to_mgmt(struct hinic3_hwdev *hwdev, u8 mod, u16 cmd,
+			     const struct mgmt_msg_params *msg_params);
+int hinic3_send_mbox_to_mgmt_no_ack(struct hinic3_hwdev *hwdev, u8 mod, u16 cmd,
+				    const struct mgmt_msg_params *msg_params);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.c b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.c
new file mode 100644
index 000000000000..c38d10cd7fac
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include "hinic3_eqs.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_mbox.h"
+#include "hinic3_mgmt.h"
+
+void hinic3_flush_mgmt_workq(struct hinic3_hwdev *hwdev)
+{
+	if (hwdev->aeqs)
+		flush_workqueue(hwdev->aeqs->workq);
+}
+
+void hinic3_mgmt_msg_aeqe_handler(struct hinic3_hwdev *hwdev, u8 *header,
+				  u8 size)
+{
+	if (MBOX_MSG_HEADER_GET(*(__force __le64 *)header, SOURCE) ==
+				MBOX_MSG_FROM_MBOX)
+		hinic3_mbox_func_aeqe_handler(hwdev, header, size);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.h b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.h
new file mode 100644
index 000000000000..bbef3b32a6ec
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_MGMT_H_
+#define _HINIC3_MGMT_H_
+
+#include <linux/types.h>
+
+struct hinic3_hwdev;
+
+void hinic3_flush_mgmt_workq(struct hinic3_hwdev *hwdev);
+void hinic3_mgmt_msg_aeqe_handler(struct hinic3_hwdev *hwdev,
+				  u8 *header, u8 size);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h
new file mode 100644
index 000000000000..6cc0345c39e4
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h
@@ -0,0 +1,224 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_MGMT_INTERFACE_H_
+#define _HINIC3_MGMT_INTERFACE_H_
+
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/if_ether.h>
+
+#include "hinic3_hw_intf.h"
+
+struct l2nic_cmd_feature_nego {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u8                   opcode;
+	u8                   rsvd;
+	u64                  s_feature[4];
+};
+
+enum l2nic_func_tbl_cfg_bitmap {
+	L2NIC_FUNC_TBL_CFG_INIT        = 0,
+	L2NIC_FUNC_TBL_CFG_RX_BUF_SIZE = 1,
+	L2NIC_FUNC_TBL_CFG_MTU         = 2,
+};
+
+struct l2nic_func_tbl_cfg {
+	u16 rx_wqe_buf_size;
+	u16 mtu;
+	u32 rsvd[9];
+};
+
+struct l2nic_cmd_set_func_tbl {
+	struct mgmt_msg_head      msg_head;
+	u16                       func_id;
+	u16                       rsvd;
+	u32                       cfg_bitmap;
+	struct l2nic_func_tbl_cfg tbl_cfg;
+};
+
+struct l2nic_cmd_set_mac {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u16                  vlan_id;
+	u16                  rsvd1;
+	u8                   mac[ETH_ALEN];
+};
+
+struct l2nic_cmd_update_mac {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u16                  vlan_id;
+	u16                  rsvd1;
+	u8                   old_mac[ETH_ALEN];
+	u16                  rsvd2;
+	u8                   new_mac[ETH_ALEN];
+};
+
+struct l2nic_cmd_set_ci_attr {
+	struct mgmt_msg_head msg_head;
+	u16                  func_idx;
+	u8                   dma_attr_off;
+	u8                   pending_limit;
+	u8                   coalescing_time;
+	u8                   intr_en;
+	u16                  intr_idx;
+	u32                  l2nic_sqn;
+	u32                  rsvd;
+	u64                  ci_addr;
+};
+
+struct l2nic_cmd_clear_qp_resource {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u16                  rsvd1;
+};
+
+struct l2nic_cmd_force_pkt_drop {
+	struct mgmt_msg_head msg_head;
+	u8                   port;
+	u8                   rsvd1[3];
+};
+
+struct l2nic_cmd_set_vport_state {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u16                  rsvd1;
+	/* 0--disable, 1--enable */
+	u8                   state;
+	u8                   rsvd2[3];
+};
+
+struct l2nic_cmd_set_dcb_state {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	/* 0 - get dcb state, 1 - set dcb state */
+	u8                   op_code;
+	/* 0 - disable, 1 - enable dcb */
+	u8                   state;
+	/* 0 - disable, 1 - enable dcb */
+	u8                   port_state;
+	u8                   rsvd[7];
+};
+
+#define L2NIC_RSS_TYPE_VALID_MASK         BIT(23)
+#define L2NIC_RSS_TYPE_TCP_IPV6_EXT_MASK  BIT(24)
+#define L2NIC_RSS_TYPE_IPV6_EXT_MASK      BIT(25)
+#define L2NIC_RSS_TYPE_TCP_IPV6_MASK      BIT(26)
+#define L2NIC_RSS_TYPE_IPV6_MASK          BIT(27)
+#define L2NIC_RSS_TYPE_TCP_IPV4_MASK      BIT(28)
+#define L2NIC_RSS_TYPE_IPV4_MASK          BIT(29)
+#define L2NIC_RSS_TYPE_UDP_IPV6_MASK      BIT(30)
+#define L2NIC_RSS_TYPE_UDP_IPV4_MASK      BIT(31)
+#define L2NIC_RSS_TYPE_SET(val, member)  \
+	FIELD_PREP(L2NIC_RSS_TYPE_##member##_MASK, val)
+#define L2NIC_RSS_TYPE_GET(val, member)  \
+	FIELD_GET(L2NIC_RSS_TYPE_##member##_MASK, val)
+
+#define L2NIC_RSS_INDIR_SIZE  256
+#define L2NIC_RSS_KEY_SIZE    40
+
+/* IEEE 802.1Qaz std */
+#define L2NIC_DCB_COS_MAX     0x8
+
+struct l2nic_cmd_set_rss_ctx_tbl {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u16                  rsvd1;
+	u32                  context;
+};
+
+struct l2nic_cmd_cfg_rss_engine {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u8                   opcode;
+	u8                   hash_engine;
+	u8                   rsvd1[4];
+};
+
+struct l2nic_cmd_cfg_rss_hash_key {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u8                   opcode;
+	u8                   rsvd1;
+	u8                   key[L2NIC_RSS_KEY_SIZE];
+};
+
+struct l2nic_cmd_cfg_rss {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u8                   rss_en;
+	u8                   rq_priority_number;
+	u8                   prio_tc[L2NIC_DCB_COS_MAX];
+	u16                  num_qps;
+	u16                  rsvd1;
+};
+
+/* Commands between NIC to fw */
+enum l2nic_cmd {
+	/* FUNC CFG */
+	L2NIC_CMD_SET_FUNC_TBL        = 5,
+	L2NIC_CMD_SET_VPORT_ENABLE    = 6,
+	L2NIC_CMD_SET_SQ_CI_ATTR      = 8,
+	L2NIC_CMD_CLEAR_QP_RESOURCE   = 11,
+	L2NIC_CMD_FEATURE_NEGO        = 15,
+	L2NIC_CMD_SET_MAC             = 21,
+	L2NIC_CMD_DEL_MAC             = 22,
+	L2NIC_CMD_UPDATE_MAC          = 23,
+	L2NIC_CMD_CFG_RSS             = 60,
+	L2NIC_CMD_CFG_RSS_HASH_KEY    = 63,
+	L2NIC_CMD_CFG_RSS_HASH_ENGINE = 64,
+	L2NIC_CMD_SET_RSS_CTX_TBL     = 65,
+	L2NIC_CMD_QOS_DCB_STATE       = 110,
+	L2NIC_CMD_FORCE_PKT_DROP      = 113,
+	L2NIC_CMD_MAX                 = 256,
+};
+
+struct l2nic_cmd_rss_set_indir_tbl {
+	__le32 rsvd[4];
+	__le16 entry[L2NIC_RSS_INDIR_SIZE];
+};
+
+/* NIC CMDQ MODE */
+enum l2nic_ucode_cmd {
+	L2NIC_UCODE_CMD_MODIFY_QUEUE_CTX  = 0,
+	L2NIC_UCODE_CMD_CLEAN_QUEUE_CTX   = 1,
+	L2NIC_UCODE_CMD_SET_RSS_INDIR_TBL = 4,
+};
+
+/* hilink mac group command */
+enum mag_cmd {
+	MAG_CMD_GET_LINK_STATUS = 7,
+};
+
+/* firmware also use this cmd report link event to driver */
+struct mag_cmd_get_link_status {
+	struct mgmt_msg_head head;
+	u8                   port_id;
+	/* 0:link down  1:link up */
+	u8                   status;
+	u8                   rsvd0[2];
+};
+
+enum hinic3_nic_feature_cap {
+	HINIC3_NIC_F_CSUM           = BIT(0),
+	HINIC3_NIC_F_SCTP_CRC       = BIT(1),
+	HINIC3_NIC_F_TSO            = BIT(2),
+	HINIC3_NIC_F_LRO            = BIT(3),
+	HINIC3_NIC_F_UFO            = BIT(4),
+	HINIC3_NIC_F_RSS            = BIT(5),
+	HINIC3_NIC_F_RX_VLAN_FILTER = BIT(6),
+	HINIC3_NIC_F_RX_VLAN_STRIP  = BIT(7),
+	HINIC3_NIC_F_TX_VLAN_INSERT = BIT(8),
+	HINIC3_NIC_F_VXLAN_OFFLOAD  = BIT(9),
+	HINIC3_NIC_F_FDIR           = BIT(11),
+	HINIC3_NIC_F_PROMISC        = BIT(12),
+	HINIC3_NIC_F_ALLMULTI       = BIT(13),
+	HINIC3_NIC_F_RATE_LIMIT     = BIT(16),
+};
+
+#define HINIC3_NIC_F_ALL_MASK           0x33bff
+#define HINIC3_NIC_DRV_DEFAULT_FEATURE  0x3f03f
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c b/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c
new file mode 100644
index 000000000000..bbf22811a029
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c
@@ -0,0 +1,496 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+
+#include "hinic3_hwif.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_rss.h"
+#include "hinic3_rx.h"
+#include "hinic3_tx.h"
+
+/* try to modify the number of irq to the target number,
+ * and return the actual number of irq.
+ */
+static u16 hinic3_qp_irq_change(struct net_device *netdev,
+				u16 dst_num_qp_irq)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct msix_entry *qps_msix_entries;
+	u16 resp_irq_num, irq_num_gap, i;
+	u16 idx;
+	int err;
+
+	qps_msix_entries = nic_dev->qps_msix_entries;
+	if (dst_num_qp_irq > nic_dev->num_qp_irq) {
+		irq_num_gap = dst_num_qp_irq - nic_dev->num_qp_irq;
+		err = hinic3_alloc_irqs(nic_dev->hwdev, irq_num_gap,
+					&qps_msix_entries[nic_dev->num_qp_irq],
+					&resp_irq_num);
+		if (err) {
+			netdev_err(netdev, "Failed to alloc irqs\n");
+			return nic_dev->num_qp_irq;
+		}
+
+		nic_dev->num_qp_irq += resp_irq_num;
+	} else if (dst_num_qp_irq < nic_dev->num_qp_irq) {
+		irq_num_gap = nic_dev->num_qp_irq - dst_num_qp_irq;
+		for (i = 0; i < irq_num_gap; i++) {
+			idx = (nic_dev->num_qp_irq - i) - 1;
+			hinic3_free_irq(nic_dev->hwdev,
+					qps_msix_entries[idx].vector);
+			qps_msix_entries[idx].vector = 0;
+			qps_msix_entries[idx].entry = 0;
+		}
+		nic_dev->num_qp_irq = dst_num_qp_irq;
+	}
+
+	return nic_dev->num_qp_irq;
+}
+
+static void hinic3_config_num_qps(struct net_device *netdev,
+				  struct hinic3_dyna_txrxq_params *q_params)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	u16 alloc_num_irq, cur_num_irq;
+	u16 dst_num_irq;
+
+	if (!test_bit(HINIC3_RSS_ENABLE, &nic_dev->flags))
+		q_params->num_qps = 1;
+
+	if (nic_dev->num_qp_irq >= q_params->num_qps)
+		goto out;
+
+	cur_num_irq = nic_dev->num_qp_irq;
+
+	alloc_num_irq = hinic3_qp_irq_change(netdev, q_params->num_qps);
+	if (alloc_num_irq < q_params->num_qps) {
+		q_params->num_qps = alloc_num_irq;
+		netdev_warn(netdev, "Can not get enough irqs, adjust num_qps to %u\n",
+			    q_params->num_qps);
+
+		/* The current irq may be in use, we must keep it */
+		dst_num_irq = max_t(u16, cur_num_irq, q_params->num_qps);
+		hinic3_qp_irq_change(netdev, dst_num_irq);
+	}
+
+out:
+	netdev_dbg(netdev, "No need to change irqs, num_qps is %u\n",
+		   q_params->num_qps);
+}
+
+static int hinic3_setup_num_qps(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	nic_dev->num_qp_irq = 0;
+
+	nic_dev->qps_msix_entries = kcalloc(nic_dev->max_qps,
+					    sizeof(struct msix_entry),
+					    GFP_KERNEL);
+	if (!nic_dev->qps_msix_entries)
+		return -ENOMEM;
+
+	hinic3_config_num_qps(netdev, &nic_dev->q_params);
+
+	return 0;
+}
+
+static void hinic3_destroy_num_qps(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	u16 i;
+
+	for (i = 0; i < nic_dev->num_qp_irq; i++)
+		hinic3_free_irq(nic_dev->hwdev,
+				nic_dev->qps_msix_entries[i].vector);
+
+	kfree(nic_dev->qps_msix_entries);
+}
+
+static int hinic3_alloc_txrxq_resources(struct net_device *netdev,
+					struct hinic3_dyna_txrxq_params *q_params)
+{
+	int err;
+
+	q_params->txqs_res = kcalloc(q_params->num_qps,
+				     sizeof(*q_params->txqs_res), GFP_KERNEL);
+	if (!q_params->txqs_res)
+		return -ENOMEM;
+
+	q_params->rxqs_res = kcalloc(q_params->num_qps,
+				     sizeof(*q_params->rxqs_res), GFP_KERNEL);
+	if (!q_params->rxqs_res) {
+		err = -ENOMEM;
+		goto err_free_txqs_res_arr;
+	}
+
+	q_params->irq_cfg = kcalloc(q_params->num_qps,
+				    sizeof(*q_params->irq_cfg), GFP_KERNEL);
+	if (!q_params->irq_cfg) {
+		err = -ENOMEM;
+		goto err_free_rxqs_res_arr;
+	}
+
+	err = hinic3_alloc_txqs_res(netdev, q_params->num_qps,
+				    q_params->sq_depth, q_params->txqs_res);
+	if (err) {
+		netdev_err(netdev, "Failed to alloc txqs resource\n");
+		goto err_free_irq_cfg;
+	}
+
+	err = hinic3_alloc_rxqs_res(netdev, q_params->num_qps,
+				    q_params->rq_depth, q_params->rxqs_res);
+	if (err) {
+		netdev_err(netdev, "Failed to alloc rxqs resource\n");
+		goto err_free_txqs_res;
+	}
+
+	return 0;
+
+err_free_txqs_res:
+	hinic3_free_txqs_res(netdev, q_params->num_qps, q_params->sq_depth,
+			     q_params->txqs_res);
+err_free_irq_cfg:
+	kfree(q_params->irq_cfg);
+	q_params->irq_cfg = NULL;
+err_free_rxqs_res_arr:
+	kfree(q_params->rxqs_res);
+	q_params->rxqs_res = NULL;
+err_free_txqs_res_arr:
+	kfree(q_params->txqs_res);
+	q_params->txqs_res = NULL;
+
+	return err;
+}
+
+static void hinic3_free_txrxq_resources(struct net_device *netdev,
+					struct hinic3_dyna_txrxq_params *q_params)
+{
+	hinic3_free_rxqs_res(netdev, q_params->num_qps, q_params->rq_depth,
+			     q_params->rxqs_res);
+	hinic3_free_txqs_res(netdev, q_params->num_qps, q_params->sq_depth,
+			     q_params->txqs_res);
+
+	kfree(q_params->irq_cfg);
+	q_params->irq_cfg = NULL;
+
+	kfree(q_params->rxqs_res);
+	q_params->rxqs_res = NULL;
+
+	kfree(q_params->txqs_res);
+	q_params->txqs_res = NULL;
+}
+
+static int hinic3_configure_txrxqs(struct net_device *netdev,
+				   struct hinic3_dyna_txrxq_params *q_params)
+{
+	int err;
+
+	err = hinic3_configure_txqs(netdev, q_params->num_qps,
+				    q_params->sq_depth, q_params->txqs_res);
+	if (err) {
+		netdev_err(netdev, "Failed to configure txqs\n");
+		return err;
+	}
+
+	err = hinic3_configure_rxqs(netdev, q_params->num_qps,
+				    q_params->rq_depth, q_params->rxqs_res);
+	if (err) {
+		netdev_err(netdev, "Failed to configure rxqs\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static int hinic3_configure(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	int err;
+
+	netdev->min_mtu = HINIC3_MIN_MTU_SIZE;
+	netdev->max_mtu = HINIC3_MAX_JUMBO_FRAME_SIZE;
+	err = hinic3_set_port_mtu(netdev, netdev->mtu);
+	if (err) {
+		netdev_err(netdev, "Failed to set mtu\n");
+		return err;
+	}
+
+	/* Ensure DCB is disabled */
+	hinic3_sync_dcb_state(nic_dev->hwdev, 1, 0);
+
+	if (test_bit(HINIC3_RSS_ENABLE, &nic_dev->flags)) {
+		err = hinic3_rss_init(netdev);
+		if (err) {
+			netdev_err(netdev, "Failed to init rss\n");
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static void hinic3_remove_configure(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	if (test_bit(HINIC3_RSS_ENABLE, &nic_dev->flags))
+		hinic3_rss_uninit(netdev);
+}
+
+static int hinic3_alloc_channel_resources(struct net_device *netdev,
+					  struct hinic3_dyna_qp_params *qp_params,
+					  struct hinic3_dyna_txrxq_params *trxq_params)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	int err;
+
+	qp_params->num_qps = trxq_params->num_qps;
+	qp_params->sq_depth = trxq_params->sq_depth;
+	qp_params->rq_depth = trxq_params->rq_depth;
+
+	err = hinic3_alloc_qps(nic_dev, qp_params);
+	if (err) {
+		netdev_err(netdev, "Failed to alloc qps\n");
+		return err;
+	}
+
+	err = hinic3_alloc_txrxq_resources(netdev, trxq_params);
+	if (err) {
+		netdev_err(netdev, "Failed to alloc txrxq resources\n");
+		hinic3_free_qps(nic_dev, qp_params);
+		return err;
+	}
+
+	return 0;
+}
+
+static void hinic3_free_channel_resources(struct net_device *netdev,
+					  struct hinic3_dyna_qp_params *qp_params,
+					  struct hinic3_dyna_txrxq_params *trxq_params)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	hinic3_free_txrxq_resources(netdev, trxq_params);
+	hinic3_free_qps(nic_dev, qp_params);
+}
+
+static int hinic3_open_channel(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	int err;
+
+	err = hinic3_init_qp_ctxts(nic_dev);
+	if (err) {
+		netdev_err(netdev, "Failed to init qps\n");
+		return err;
+	}
+
+	err = hinic3_configure_txrxqs(netdev, &nic_dev->q_params);
+	if (err) {
+		netdev_err(netdev, "Failed to configure txrxqs\n");
+		goto err_free_qp_ctxts;
+	}
+
+	err = hinic3_qps_irq_init(netdev);
+	if (err) {
+		netdev_err(netdev, "Failed to init txrxq irq\n");
+		goto err_free_qp_ctxts;
+	}
+
+	err = hinic3_configure(netdev);
+	if (err) {
+		netdev_err(netdev, "Failed to configure device resources\n");
+		goto err_uninit_qps_irq;
+	}
+
+	return 0;
+
+err_uninit_qps_irq:
+	hinic3_qps_irq_uninit(netdev);
+err_free_qp_ctxts:
+	hinic3_free_qp_ctxts(nic_dev);
+
+	return err;
+}
+
+static void hinic3_close_channel(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	hinic3_remove_configure(netdev);
+	hinic3_qps_irq_uninit(netdev);
+	hinic3_free_qp_ctxts(nic_dev);
+}
+
+static int hinic3_vport_up(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	bool link_status_up;
+	u16 glb_func_id;
+	int err;
+
+	glb_func_id = hinic3_global_func_id(nic_dev->hwdev);
+	err = hinic3_set_vport_enable(nic_dev->hwdev, glb_func_id, true);
+	if (err) {
+		netdev_err(netdev, "Failed to enable vport\n");
+		goto err_flush_qps_res;
+	}
+
+	err = netif_set_real_num_queues(netdev, nic_dev->q_params.num_qps,
+					nic_dev->q_params.num_qps);
+	if (err) {
+		netdev_err(netdev, "Failed to set real number of queues\n");
+		goto err_flush_qps_res;
+	}
+	netif_tx_start_all_queues(netdev);
+
+	err = hinic3_get_link_status(nic_dev->hwdev, &link_status_up);
+	if (!err && link_status_up)
+		netif_carrier_on(netdev);
+
+	return 0;
+
+err_flush_qps_res:
+	hinic3_flush_qps_res(nic_dev->hwdev);
+	/* wait to guarantee that no packets will be sent to host */
+	msleep(100);
+
+	return err;
+}
+
+static void hinic3_vport_down(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	u16 glb_func_id;
+
+	netif_carrier_off(netdev);
+	netif_tx_disable(netdev);
+
+	glb_func_id = hinic3_global_func_id(nic_dev->hwdev);
+	hinic3_set_vport_enable(nic_dev->hwdev, glb_func_id, false);
+
+	hinic3_flush_txqs(netdev);
+	/* wait to guarantee that no packets will be sent to host */
+	msleep(100);
+	hinic3_flush_qps_res(nic_dev->hwdev);
+}
+
+static int hinic3_open(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_dyna_qp_params qp_params;
+	int err;
+
+	err = hinic3_init_nicio_res(nic_dev);
+	if (err) {
+		netdev_err(netdev, "Failed to init nicio resources\n");
+		return err;
+	}
+
+	err = hinic3_setup_num_qps(netdev);
+	if (err) {
+		netdev_err(netdev, "Failed to setup num_qps\n");
+		goto err_free_nicio_res;
+	}
+
+	err = hinic3_alloc_channel_resources(netdev, &qp_params,
+					     &nic_dev->q_params);
+	if (err)
+		goto err_destroy_num_qps;
+
+	hinic3_init_qps(nic_dev, &qp_params);
+
+	err = hinic3_open_channel(netdev);
+	if (err)
+		goto err_uninit_qps;
+
+	err = hinic3_vport_up(netdev);
+	if (err)
+		goto err_close_channel;
+
+	return 0;
+
+err_close_channel:
+	hinic3_close_channel(netdev);
+err_uninit_qps:
+	hinic3_uninit_qps(nic_dev, &qp_params);
+	hinic3_free_channel_resources(netdev, &qp_params, &nic_dev->q_params);
+err_destroy_num_qps:
+	hinic3_destroy_num_qps(netdev);
+err_free_nicio_res:
+	hinic3_free_nicio_res(nic_dev);
+
+	return err;
+}
+
+static int hinic3_close(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_dyna_qp_params qp_params;
+
+	hinic3_vport_down(netdev);
+	hinic3_close_channel(netdev);
+	hinic3_uninit_qps(nic_dev, &qp_params);
+	hinic3_free_channel_resources(netdev, &qp_params, &nic_dev->q_params);
+
+	return 0;
+}
+
+static int hinic3_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	int err;
+
+	err = hinic3_set_port_mtu(netdev, new_mtu);
+	if (err) {
+		netdev_err(netdev, "Failed to change port mtu to %d\n",
+			   new_mtu);
+		return err;
+	}
+
+	netdev_dbg(netdev, "Change mtu from %u to %d\n", netdev->mtu, new_mtu);
+	WRITE_ONCE(netdev->mtu, new_mtu);
+
+	return 0;
+}
+
+static int hinic3_set_mac_addr(struct net_device *netdev, void *addr)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct sockaddr *saddr = addr;
+	int err;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	if (ether_addr_equal(netdev->dev_addr, saddr->sa_data))
+		return 0;
+
+	err = hinic3_update_mac(nic_dev->hwdev, netdev->dev_addr,
+				saddr->sa_data, 0,
+				hinic3_global_func_id(nic_dev->hwdev));
+
+	if (err)
+		return err;
+
+	eth_hw_addr_set(netdev, saddr->sa_data);
+
+	return 0;
+}
+
+static const struct net_device_ops hinic3_netdev_ops = {
+	.ndo_open             = hinic3_open,
+	.ndo_stop             = hinic3_close,
+	.ndo_change_mtu       = hinic3_change_mtu,
+	.ndo_set_mac_address  = hinic3_set_mac_addr,
+	.ndo_start_xmit       = hinic3_xmit_frame,
+};
+
+void hinic3_set_netdev_ops(struct net_device *netdev)
+{
+	netdev->netdev_ops = &hinic3_netdev_ops;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c
new file mode 100644
index 000000000000..979f47ca77f9
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c
@@ -0,0 +1,385 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/if_vlan.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+
+static int hinic3_feature_nego(struct hinic3_hwdev *hwdev, u8 opcode,
+			       u64 *s_feature, u16 size)
+{
+	struct l2nic_cmd_feature_nego feature_nego = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	feature_nego.func_id = hinic3_global_func_id(hwdev);
+	feature_nego.opcode = opcode;
+	if (opcode == MGMT_MSG_CMD_OP_SET)
+		memcpy(feature_nego.s_feature, s_feature, size * sizeof(u64));
+
+	mgmt_msg_params_init_default(&msg_params, &feature_nego,
+				     sizeof(feature_nego));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_FEATURE_NEGO, &msg_params);
+	if (err || feature_nego.msg_head.status) {
+		dev_err(hwdev->dev, "Failed to negotiate nic feature, err:%d, status: 0x%x\n",
+			err, feature_nego.msg_head.status);
+		return -EIO;
+	}
+
+	if (opcode == MGMT_MSG_CMD_OP_GET)
+		memcpy(s_feature, feature_nego.s_feature, size * sizeof(u64));
+
+	return 0;
+}
+
+int hinic3_get_nic_feature_from_hw(struct hinic3_nic_dev *nic_dev)
+{
+	return hinic3_feature_nego(nic_dev->hwdev, MGMT_MSG_CMD_OP_GET,
+				   &nic_dev->nic_io->feature_cap, 1);
+}
+
+int hinic3_set_nic_feature_to_hw(struct hinic3_nic_dev *nic_dev)
+{
+	return hinic3_feature_nego(nic_dev->hwdev, MGMT_MSG_CMD_OP_SET,
+				   &nic_dev->nic_io->feature_cap, 1);
+}
+
+bool hinic3_test_support(struct hinic3_nic_dev *nic_dev,
+			 enum hinic3_nic_feature_cap feature_bits)
+{
+	return (nic_dev->nic_io->feature_cap & feature_bits) == feature_bits;
+}
+
+void hinic3_update_nic_feature(struct hinic3_nic_dev *nic_dev, u64 feature_cap)
+{
+	nic_dev->nic_io->feature_cap = feature_cap;
+}
+
+static int hinic3_set_function_table(struct hinic3_hwdev *hwdev, u32 cfg_bitmap,
+				     const struct l2nic_func_tbl_cfg *cfg)
+{
+	struct l2nic_cmd_set_func_tbl cmd_func_tbl = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	cmd_func_tbl.func_id = hinic3_global_func_id(hwdev);
+	cmd_func_tbl.cfg_bitmap = cfg_bitmap;
+	cmd_func_tbl.tbl_cfg = *cfg;
+
+	mgmt_msg_params_init_default(&msg_params, &cmd_func_tbl,
+				     sizeof(cmd_func_tbl));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_SET_FUNC_TBL, &msg_params);
+	if (err || cmd_func_tbl.msg_head.status) {
+		dev_err(hwdev->dev,
+			"Failed to set func table, bitmap: 0x%x, err: %d, status: 0x%x\n",
+			cfg_bitmap, err, cmd_func_tbl.msg_head.status);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+int hinic3_init_function_table(struct hinic3_nic_dev *nic_dev)
+{
+	struct hinic3_nic_io *nic_io = nic_dev->nic_io;
+	struct l2nic_func_tbl_cfg func_tbl_cfg = {};
+	u32 cfg_bitmap;
+
+	func_tbl_cfg.mtu = 0x3FFF; /* default, max mtu */
+	func_tbl_cfg.rx_wqe_buf_size = nic_io->rx_buf_len;
+
+	cfg_bitmap = BIT(L2NIC_FUNC_TBL_CFG_INIT) |
+		     BIT(L2NIC_FUNC_TBL_CFG_MTU) |
+		     BIT(L2NIC_FUNC_TBL_CFG_RX_BUF_SIZE);
+
+	return hinic3_set_function_table(nic_dev->hwdev, cfg_bitmap,
+					 &func_tbl_cfg);
+}
+
+int hinic3_set_port_mtu(struct net_device *netdev, u16 new_mtu)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct l2nic_func_tbl_cfg func_tbl_cfg = {};
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+
+	func_tbl_cfg.mtu = new_mtu;
+
+	return hinic3_set_function_table(hwdev, BIT(L2NIC_FUNC_TBL_CFG_MTU),
+					 &func_tbl_cfg);
+}
+
+static int hinic3_check_mac_info(struct hinic3_hwdev *hwdev, u8 status,
+				 u16 vlan_id)
+{
+	if ((status && status != MGMT_STATUS_EXIST) ||
+	    ((vlan_id & BIT(15)) && status == MGMT_STATUS_EXIST)) {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int hinic3_set_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
+		   u16 func_id)
+{
+	struct l2nic_cmd_set_mac mac_info = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	if ((vlan_id & HINIC3_VLAN_ID_MASK) >= VLAN_N_VID) {
+		dev_err(hwdev->dev, "Invalid VLAN number: %d\n",
+			(vlan_id & HINIC3_VLAN_ID_MASK));
+		return -EINVAL;
+	}
+
+	mac_info.func_id = func_id;
+	mac_info.vlan_id = vlan_id;
+	ether_addr_copy(mac_info.mac, mac_addr);
+
+	mgmt_msg_params_init_default(&msg_params, &mac_info, sizeof(mac_info));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_SET_MAC, &msg_params);
+	if (err || hinic3_check_mac_info(hwdev, mac_info.msg_head.status,
+					 mac_info.vlan_id)) {
+		dev_err(hwdev->dev,
+			"Failed to update MAC, err: %d, status: 0x%x\n",
+			err, mac_info.msg_head.status);
+		return -EIO;
+	}
+
+	if (mac_info.msg_head.status == MGMT_STATUS_PF_SET_VF_ALREADY) {
+		dev_warn(hwdev->dev, "PF has already set VF mac, Ignore set operation\n");
+		return 0;
+	}
+
+	if (mac_info.msg_head.status == MGMT_STATUS_EXIST) {
+		dev_warn(hwdev->dev, "MAC is repeated. Ignore update operation\n");
+		return 0;
+	}
+
+	return 0;
+}
+
+int hinic3_del_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
+		   u16 func_id)
+{
+	struct l2nic_cmd_set_mac mac_info = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	if ((vlan_id & HINIC3_VLAN_ID_MASK) >= VLAN_N_VID) {
+		dev_err(hwdev->dev, "Invalid VLAN number: %d\n",
+			(vlan_id & HINIC3_VLAN_ID_MASK));
+		return -EINVAL;
+	}
+
+	mac_info.func_id = func_id;
+	mac_info.vlan_id = vlan_id;
+	ether_addr_copy(mac_info.mac, mac_addr);
+
+	mgmt_msg_params_init_default(&msg_params, &mac_info, sizeof(mac_info));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_DEL_MAC, &msg_params);
+	if (err) {
+		dev_err(hwdev->dev,
+			"Failed to delete MAC, err: %d, status: 0x%x\n",
+			err, mac_info.msg_head.status);
+		return err;
+	}
+
+	return 0;
+}
+
+int hinic3_update_mac(struct hinic3_hwdev *hwdev, const u8 *old_mac,
+		      u8 *new_mac, u16 vlan_id, u16 func_id)
+{
+	struct l2nic_cmd_update_mac mac_info = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	if ((vlan_id & HINIC3_VLAN_ID_MASK) >= VLAN_N_VID) {
+		dev_err(hwdev->dev, "Invalid VLAN number: %d\n",
+			(vlan_id & HINIC3_VLAN_ID_MASK));
+		return -EINVAL;
+	}
+
+	mac_info.func_id = func_id;
+	mac_info.vlan_id = vlan_id;
+	ether_addr_copy(mac_info.old_mac, old_mac);
+	ether_addr_copy(mac_info.new_mac, new_mac);
+
+	mgmt_msg_params_init_default(&msg_params, &mac_info, sizeof(mac_info));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_UPDATE_MAC, &msg_params);
+	if (err || hinic3_check_mac_info(hwdev, mac_info.msg_head.status,
+					 mac_info.vlan_id)) {
+		dev_err(hwdev->dev,
+			"Failed to update MAC, err: %d, status: 0x%x\n",
+			err, mac_info.msg_head.status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int hinic3_set_ci_table(struct hinic3_hwdev *hwdev, struct hinic3_sq_attr *attr)
+{
+	struct l2nic_cmd_set_ci_attr cons_idx_attr = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	cons_idx_attr.func_idx = hinic3_global_func_id(hwdev);
+	cons_idx_attr.dma_attr_off  = attr->dma_attr_off;
+	cons_idx_attr.pending_limit = attr->pending_limit;
+	cons_idx_attr.coalescing_time  = attr->coalescing_time;
+
+	if (attr->intr_en) {
+		cons_idx_attr.intr_en = attr->intr_en;
+		cons_idx_attr.intr_idx = attr->intr_idx;
+	}
+
+	cons_idx_attr.l2nic_sqn = attr->l2nic_sqn;
+	cons_idx_attr.ci_addr = attr->ci_dma_base;
+
+	mgmt_msg_params_init_default(&msg_params, &cons_idx_attr,
+				     sizeof(cons_idx_attr));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_SET_SQ_CI_ATTR, &msg_params);
+	if (err || cons_idx_attr.msg_head.status) {
+		dev_err(hwdev->dev,
+			"Failed to set ci attribute table, err: %d, status: 0x%x\n",
+			err, cons_idx_attr.msg_head.status);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+int hinic3_flush_qps_res(struct hinic3_hwdev *hwdev)
+{
+	struct l2nic_cmd_clear_qp_resource sq_res = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	sq_res.func_id = hinic3_global_func_id(hwdev);
+
+	mgmt_msg_params_init_default(&msg_params, &sq_res, sizeof(sq_res));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_CLEAR_QP_RESOURCE,
+				       &msg_params);
+	if (err || sq_res.msg_head.status) {
+		dev_err(hwdev->dev, "Failed to clear sq resources, err: %d, status: 0x%x\n",
+			err, sq_res.msg_head.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int hinic3_force_drop_tx_pkt(struct hinic3_hwdev *hwdev)
+{
+	struct l2nic_cmd_force_pkt_drop pkt_drop = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	pkt_drop.port = hinic3_physical_port_id(hwdev);
+
+	mgmt_msg_params_init_default(&msg_params, &pkt_drop, sizeof(pkt_drop));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_FORCE_PKT_DROP, &msg_params);
+	if ((pkt_drop.msg_head.status != MGMT_STATUS_CMD_UNSUPPORTED &&
+	     pkt_drop.msg_head.status) || err) {
+		dev_err(hwdev->dev,
+			"Failed to set force tx packets drop, err: %d, status: 0x%x\n",
+			err, pkt_drop.msg_head.status);
+		return -EFAULT;
+	}
+
+	return pkt_drop.msg_head.status;
+}
+
+int hinic3_sync_dcb_state(struct hinic3_hwdev *hwdev, u8 op_code, u8 state)
+{
+	struct l2nic_cmd_set_dcb_state dcb_state = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	dcb_state.op_code = op_code;
+	dcb_state.state = state;
+	dcb_state.func_id = hinic3_global_func_id(hwdev);
+
+	mgmt_msg_params_init_default(&msg_params, &dcb_state,
+				     sizeof(dcb_state));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_QOS_DCB_STATE, &msg_params);
+	if (err || dcb_state.head.status) {
+		dev_err(hwdev->dev,
+			"Failed to set dcb state, err: %d, status: 0x%x\n",
+			err, dcb_state.head.status);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+int hinic3_get_link_status(struct hinic3_hwdev *hwdev, bool *link_status_up)
+{
+	struct mag_cmd_get_link_status get_link = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	get_link.port_id = hinic3_physical_port_id(hwdev);
+
+	mgmt_msg_params_init_default(&msg_params, &get_link, sizeof(get_link));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_HILINK,
+				       MAG_CMD_GET_LINK_STATUS, &msg_params);
+	if (err || get_link.head.status) {
+		dev_err(hwdev->dev, "Failed to get link state, err: %d, status: 0x%x\n",
+			err, get_link.head.status);
+		return -EIO;
+	}
+
+	*link_status_up = !!get_link.status;
+
+	return 0;
+}
+
+int hinic3_set_vport_enable(struct hinic3_hwdev *hwdev, u16 func_id,
+			    bool enable)
+{
+	struct l2nic_cmd_set_vport_state en_state = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	en_state.func_id = func_id;
+	en_state.state = enable ? 1 : 0;
+
+	mgmt_msg_params_init_default(&msg_params, &en_state, sizeof(en_state));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_SET_VPORT_ENABLE, &msg_params);
+	if (err || en_state.msg_head.status) {
+		dev_err(hwdev->dev, "Failed to set vport state, err: %d, status: 0x%x\n",
+			err, en_state.msg_head.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h
new file mode 100644
index 000000000000..b83b567fa542
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_NIC_CFG_H_
+#define _HINIC3_NIC_CFG_H_
+
+#include <linux/types.h>
+
+#include "hinic3_hw_intf.h"
+#include "hinic3_mgmt_interface.h"
+
+struct hinic3_hwdev;
+struct hinic3_nic_dev;
+
+#define HINIC3_MIN_MTU_SIZE          256
+#define HINIC3_MAX_JUMBO_FRAME_SIZE  9600
+
+#define HINIC3_VLAN_ID_MASK          0x7FFF
+
+enum hinic3_nic_event_type {
+	HINIC3_NIC_EVENT_LINK_DOWN = 0,
+	HINIC3_NIC_EVENT_LINK_UP   = 1,
+};
+
+struct hinic3_sq_attr {
+	u8  dma_attr_off;
+	u8  pending_limit;
+	u8  coalescing_time;
+	u8  intr_en;
+	u16 intr_idx;
+	u32 l2nic_sqn;
+	u64 ci_dma_base;
+};
+
+int hinic3_get_nic_feature_from_hw(struct hinic3_nic_dev *nic_dev);
+int hinic3_set_nic_feature_to_hw(struct hinic3_nic_dev *nic_dev);
+bool hinic3_test_support(struct hinic3_nic_dev *nic_dev,
+			 enum hinic3_nic_feature_cap feature_bits);
+void hinic3_update_nic_feature(struct hinic3_nic_dev *nic_dev, u64 feature_cap);
+
+int hinic3_init_function_table(struct hinic3_nic_dev *nic_dev);
+int hinic3_set_port_mtu(struct net_device *netdev, u16 new_mtu);
+
+int hinic3_set_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
+		   u16 func_id);
+int hinic3_del_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
+		   u16 func_id);
+int hinic3_update_mac(struct hinic3_hwdev *hwdev, const u8 *old_mac,
+		      u8 *new_mac, u16 vlan_id, u16 func_id);
+
+int hinic3_set_ci_table(struct hinic3_hwdev *hwdev,
+			struct hinic3_sq_attr *attr);
+int hinic3_flush_qps_res(struct hinic3_hwdev *hwdev);
+int hinic3_force_drop_tx_pkt(struct hinic3_hwdev *hwdev);
+
+int hinic3_sync_dcb_state(struct hinic3_hwdev *hwdev, u8 op_code, u8 state);
+int hinic3_get_link_status(struct hinic3_hwdev *hwdev, bool *link_status_up);
+int hinic3_set_vport_enable(struct hinic3_hwdev *hwdev, u16 func_id,
+			    bool enable);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h
new file mode 100644
index 000000000000..5ba83261616c
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_NIC_DEV_H_
+#define _HINIC3_NIC_DEV_H_
+
+#include <linux/netdevice.h>
+
+#include "hinic3_hw_cfg.h"
+#include "hinic3_mgmt_interface.h"
+
+enum hinic3_flags {
+	HINIC3_RSS_ENABLE,
+};
+
+enum hinic3_rss_hash_type {
+	HINIC3_RSS_HASH_ENGINE_TYPE_XOR  = 0,
+	HINIC3_RSS_HASH_ENGINE_TYPE_TOEP = 1,
+};
+
+struct hinic3_rss_type {
+	u8 tcp_ipv6_ext;
+	u8 ipv6_ext;
+	u8 tcp_ipv6;
+	u8 ipv6;
+	u8 tcp_ipv4;
+	u8 ipv4;
+	u8 udp_ipv6;
+	u8 udp_ipv4;
+};
+
+struct hinic3_irq_cfg {
+	struct net_device  *netdev;
+	u16                msix_entry_idx;
+	/* provided by OS */
+	u32                irq_id;
+	char               irq_name[IFNAMSIZ + 16];
+	struct napi_struct napi;
+	cpumask_t          affinity_mask;
+	struct hinic3_txq  *txq;
+	struct hinic3_rxq  *rxq;
+};
+
+struct hinic3_dyna_txrxq_params {
+	u16                        num_qps;
+	u32                        sq_depth;
+	u32                        rq_depth;
+
+	struct hinic3_dyna_txq_res *txqs_res;
+	struct hinic3_dyna_rxq_res *rxqs_res;
+	struct hinic3_irq_cfg      *irq_cfg;
+};
+
+struct hinic3_intr_coal_info {
+	u8 pending_limit;
+	u8 coalesce_timer_cfg;
+	u8 resend_timer_cfg;
+};
+
+struct hinic3_nic_dev {
+	struct pci_dev                  *pdev;
+	struct net_device               *netdev;
+	struct hinic3_hwdev             *hwdev;
+	struct hinic3_nic_io            *nic_io;
+
+	u16                             max_qps;
+	u16                             rx_buf_len;
+	u32                             lro_replenish_thld;
+	unsigned long                   flags;
+	struct hinic3_nic_service_cap   nic_svc_cap;
+
+	struct hinic3_dyna_txrxq_params q_params;
+	struct hinic3_txq               *txqs;
+	struct hinic3_rxq               *rxqs;
+
+	enum hinic3_rss_hash_type       rss_hash_type;
+	struct hinic3_rss_type          rss_type;
+	u8                              *rss_hkey;
+	u16                             *rss_indir;
+
+	u16                             num_qp_irq;
+	struct msix_entry               *qps_msix_entries;
+
+	struct hinic3_intr_coal_info    *intr_coalesce;
+
+	bool                            link_status_up;
+};
+
+void hinic3_set_netdev_ops(struct net_device *netdev);
+int hinic3_qps_irq_init(struct net_device *netdev);
+void hinic3_qps_irq_uninit(struct net_device *netdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c
new file mode 100644
index 000000000000..d86cd1ba4605
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c
@@ -0,0 +1,885 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include "hinic3_cmdq.h"
+#include "hinic3_hw_comm.h"
+#include "hinic3_hw_intf.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+
+#define HINIC3_DEFAULT_TX_CI_PENDING_LIMIT    1
+#define HINIC3_DEFAULT_TX_CI_COALESCING_TIME  1
+#define HINIC3_DEFAULT_DROP_THD_ON            (0xFFFF)
+#define HINIC3_DEFAULT_DROP_THD_OFF           0
+
+#define HINIC3_CI_Q_ADDR_SIZE                (64)
+
+#define HINIC3_CI_TABLE_SIZE(num_qps)  \
+	(ALIGN((num_qps) * HINIC3_CI_Q_ADDR_SIZE, HINIC3_MIN_PAGE_SIZE))
+
+#define HINIC3_CI_VADDR(base_addr, q_id)  \
+	((u8 *)(base_addr) + (q_id) * HINIC3_CI_Q_ADDR_SIZE)
+
+#define HINIC3_CI_PADDR(base_paddr, q_id)  \
+	((base_paddr) + (q_id) * HINIC3_CI_Q_ADDR_SIZE)
+
+#define SQ_WQ_PREFETCH_MAX        1
+#define SQ_WQ_PREFETCH_MIN        1
+#define SQ_WQ_PREFETCH_THRESHOLD  16
+
+#define RQ_WQ_PREFETCH_MAX        4
+#define RQ_WQ_PREFETCH_MIN        1
+#define RQ_WQ_PREFETCH_THRESHOLD  256
+
+/* (2048 - 8) / 64 */
+#define HINIC3_Q_CTXT_MAX         31
+
+enum hinic3_qp_ctxt_type {
+	HINIC3_QP_CTXT_TYPE_SQ = 0,
+	HINIC3_QP_CTXT_TYPE_RQ = 1,
+};
+
+struct hinic3_qp_ctxt_hdr {
+	__le16 num_queues;
+	__le16 queue_type;
+	__le16 start_qid;
+	__le16 rsvd;
+};
+
+struct hinic3_sq_ctxt {
+	__le32 ci_pi;
+	__le32 drop_mode_sp;
+	__le32 wq_pfn_hi_owner;
+	__le32 wq_pfn_lo;
+
+	__le32 rsvd0;
+	__le32 pkt_drop_thd;
+	__le32 global_sq_id;
+	__le32 vlan_ceq_attr;
+
+	__le32 pref_cache;
+	__le32 pref_ci_owner;
+	__le32 pref_wq_pfn_hi_ci;
+	__le32 pref_wq_pfn_lo;
+
+	__le32 rsvd8;
+	__le32 rsvd9;
+	__le32 wq_block_pfn_hi;
+	__le32 wq_block_pfn_lo;
+};
+
+struct hinic3_rq_ctxt {
+	__le32 ci_pi;
+	__le32 ceq_attr;
+	__le32 wq_pfn_hi_type_owner;
+	__le32 wq_pfn_lo;
+
+	__le32 rsvd[3];
+	__le32 cqe_sge_len;
+
+	__le32 pref_cache;
+	__le32 pref_ci_owner;
+	__le32 pref_wq_pfn_hi_ci;
+	__le32 pref_wq_pfn_lo;
+
+	__le32 pi_paddr_hi;
+	__le32 pi_paddr_lo;
+	__le32 wq_block_pfn_hi;
+	__le32 wq_block_pfn_lo;
+};
+
+struct hinic3_sq_ctxt_block {
+	struct hinic3_qp_ctxt_hdr cmdq_hdr;
+	struct hinic3_sq_ctxt     sq_ctxt[HINIC3_Q_CTXT_MAX];
+};
+
+struct hinic3_rq_ctxt_block {
+	struct hinic3_qp_ctxt_hdr cmdq_hdr;
+	struct hinic3_rq_ctxt     rq_ctxt[HINIC3_Q_CTXT_MAX];
+};
+
+struct hinic3_clean_queue_ctxt {
+	struct hinic3_qp_ctxt_hdr cmdq_hdr;
+	__le32                    rsvd;
+};
+
+#define SQ_CTXT_SIZE(num_sqs)  \
+	(sizeof(struct hinic3_qp_ctxt_hdr) +  \
+	(num_sqs) * sizeof(struct hinic3_sq_ctxt))
+
+#define RQ_CTXT_SIZE(num_rqs)  \
+	(sizeof(struct hinic3_qp_ctxt_hdr) +  \
+	(num_rqs) * sizeof(struct hinic3_rq_ctxt))
+
+#define SQ_CTXT_PREF_CI_HI_SHIFT           12
+#define SQ_CTXT_PREF_CI_HI(val)            ((val) >> SQ_CTXT_PREF_CI_HI_SHIFT)
+
+#define SQ_CTXT_PI_IDX_MASK                GENMASK(15, 0)
+#define SQ_CTXT_CI_IDX_MASK                GENMASK(31, 16)
+#define SQ_CTXT_CI_PI_SET(val, member)  \
+	FIELD_PREP(SQ_CTXT_##member##_MASK, val)
+
+#define SQ_CTXT_MODE_SP_FLAG_MASK          BIT(0)
+#define SQ_CTXT_MODE_PKT_DROP_MASK         BIT(1)
+#define SQ_CTXT_MODE_SET(val, member)  \
+	FIELD_PREP(SQ_CTXT_MODE_##member##_MASK, val)
+
+#define SQ_CTXT_WQ_PAGE_HI_PFN_MASK        GENMASK(19, 0)
+#define SQ_CTXT_WQ_PAGE_OWNER_MASK         BIT(23)
+#define SQ_CTXT_WQ_PAGE_SET(val, member)  \
+	FIELD_PREP(SQ_CTXT_WQ_PAGE_##member##_MASK, val)
+
+#define SQ_CTXT_PKT_DROP_THD_ON_MASK       GENMASK(15, 0)
+#define SQ_CTXT_PKT_DROP_THD_OFF_MASK      GENMASK(31, 16)
+#define SQ_CTXT_PKT_DROP_THD_SET(val, member)  \
+	FIELD_PREP(SQ_CTXT_PKT_DROP_##member##_MASK, val)
+
+#define SQ_CTXT_GLOBAL_SQ_ID_MASK          GENMASK(12, 0)
+#define SQ_CTXT_GLOBAL_QUEUE_ID_SET(val, member)  \
+	FIELD_PREP(SQ_CTXT_##member##_MASK, val)
+
+#define SQ_CTXT_VLAN_INSERT_MODE_MASK      GENMASK(20, 19)
+#define SQ_CTXT_VLAN_CEQ_EN_MASK           BIT(23)
+#define SQ_CTXT_VLAN_CEQ_SET(val, member)  \
+	FIELD_PREP(SQ_CTXT_VLAN_##member##_MASK, val)
+
+#define SQ_CTXT_PREF_CACHE_THRESHOLD_MASK  GENMASK(13, 0)
+#define SQ_CTXT_PREF_CACHE_MAX_MASK        GENMASK(24, 14)
+#define SQ_CTXT_PREF_CACHE_MIN_MASK        GENMASK(31, 25)
+
+#define SQ_CTXT_PREF_CI_HI_MASK            GENMASK(3, 0)
+#define SQ_CTXT_PREF_OWNER_MASK            BIT(4)
+
+#define SQ_CTXT_PREF_WQ_PFN_HI_MASK        GENMASK(19, 0)
+#define SQ_CTXT_PREF_CI_LOW_MASK           GENMASK(31, 20)
+#define SQ_CTXT_PREF_SET(val, member)  \
+	FIELD_PREP(SQ_CTXT_PREF_##member##_MASK, val)
+
+#define SQ_CTXT_WQ_BLOCK_PFN_HI_MASK       GENMASK(22, 0)
+#define SQ_CTXT_WQ_BLOCK_SET(val, member)  \
+	FIELD_PREP(SQ_CTXT_WQ_BLOCK_##member##_MASK, val)
+
+#define RQ_CTXT_PI_IDX_MASK                GENMASK(15, 0)
+#define RQ_CTXT_CI_IDX_MASK                GENMASK(31, 16)
+#define RQ_CTXT_CI_PI_SET(val, member)  \
+	FIELD_PREP(RQ_CTXT_##member##_MASK, val)
+
+#define RQ_CTXT_CEQ_ATTR_INTR_MASK         GENMASK(30, 21)
+#define RQ_CTXT_CEQ_ATTR_EN_MASK           BIT(31)
+#define RQ_CTXT_CEQ_ATTR_SET(val, member)  \
+	FIELD_PREP(RQ_CTXT_CEQ_ATTR_##member##_MASK, val)
+
+#define RQ_CTXT_WQ_PAGE_HI_PFN_MASK        GENMASK(19, 0)
+#define RQ_CTXT_WQ_PAGE_WQE_TYPE_MASK      GENMASK(29, 28)
+#define RQ_CTXT_WQ_PAGE_OWNER_MASK         BIT(31)
+#define RQ_CTXT_WQ_PAGE_SET(val, member)  \
+	FIELD_PREP(RQ_CTXT_WQ_PAGE_##member##_MASK, val)
+
+#define RQ_CTXT_CQE_LEN_MASK               GENMASK(29, 28)
+#define RQ_CTXT_CQE_LEN_SET(val, member)  \
+	FIELD_PREP(RQ_CTXT_##member##_MASK, val)
+
+#define RQ_CTXT_PREF_CACHE_THRESHOLD_MASK  GENMASK(13, 0)
+#define RQ_CTXT_PREF_CACHE_MAX_MASK        GENMASK(24, 14)
+#define RQ_CTXT_PREF_CACHE_MIN_MASK        GENMASK(31, 25)
+
+#define RQ_CTXT_PREF_CI_HI_MASK            GENMASK(3, 0)
+#define RQ_CTXT_PREF_OWNER_MASK            BIT(4)
+
+#define RQ_CTXT_PREF_WQ_PFN_HI_MASK        GENMASK(19, 0)
+#define RQ_CTXT_PREF_CI_LOW_MASK           GENMASK(31, 20)
+#define RQ_CTXT_PREF_SET(val, member)  \
+	FIELD_PREP(RQ_CTXT_PREF_##member##_MASK, val)
+
+#define RQ_CTXT_WQ_BLOCK_PFN_HI_MASK       GENMASK(22, 0)
+#define RQ_CTXT_WQ_BLOCK_SET(val, member)  \
+	FIELD_PREP(RQ_CTXT_WQ_BLOCK_##member##_MASK, val)
+
+#define WQ_PAGE_PFN_SHIFT       12
+#define WQ_BLOCK_PFN_SHIFT      9
+#define WQ_PAGE_PFN(page_addr)  ((page_addr) >> WQ_PAGE_PFN_SHIFT)
+#define WQ_BLOCK_PFN(page_addr) ((page_addr) >> WQ_BLOCK_PFN_SHIFT)
+
+int hinic3_init_nic_io(struct hinic3_nic_dev *nic_dev)
+{
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic3_nic_io *nic_io;
+	int err;
+
+	nic_io = kzalloc(sizeof(*nic_io), GFP_KERNEL);
+	if (!nic_io)
+		return -ENOMEM;
+
+	nic_dev->nic_io = nic_io;
+
+	err = hinic3_set_func_svc_used_state(hwdev, COMM_FUNC_SVC_T_NIC, 1);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set function svc used state\n");
+		goto err_free_nicio;
+	}
+
+	err = hinic3_init_function_table(nic_dev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init function table\n");
+		goto err_clear_func_svc_used_state;
+	}
+
+	nic_io->rx_buf_len = nic_dev->rx_buf_len;
+
+	err = hinic3_get_nic_feature_from_hw(nic_dev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to get nic features\n");
+		goto err_clear_func_svc_used_state;
+	}
+
+	nic_io->feature_cap &= HINIC3_NIC_F_ALL_MASK;
+	nic_io->feature_cap &= HINIC3_NIC_DRV_DEFAULT_FEATURE;
+	dev_dbg(hwdev->dev, "nic features: 0x%llx\n\n", nic_io->feature_cap);
+
+	return 0;
+
+err_clear_func_svc_used_state:
+	hinic3_set_func_svc_used_state(hwdev, COMM_FUNC_SVC_T_NIC, 0);
+err_free_nicio:
+	nic_dev->nic_io = NULL;
+	kfree(nic_io);
+
+	return err;
+}
+
+void hinic3_free_nic_io(struct hinic3_nic_dev *nic_dev)
+{
+	struct hinic3_nic_io *nic_io = nic_dev->nic_io;
+
+	hinic3_set_func_svc_used_state(nic_dev->hwdev, COMM_FUNC_SVC_T_NIC, 0);
+	nic_dev->nic_io = NULL;
+	kfree(nic_io);
+}
+
+int hinic3_init_nicio_res(struct hinic3_nic_dev *nic_dev)
+{
+	struct hinic3_nic_io *nic_io = nic_dev->nic_io;
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	void __iomem *db_base;
+	int err;
+
+	nic_io->max_qps = hinic3_func_max_qnum(hwdev);
+
+	err = hinic3_alloc_db_addr(hwdev, &db_base, NULL);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to allocate doorbell for sqs\n");
+		return err;
+	}
+	nic_io->sqs_db_addr = db_base;
+
+	err = hinic3_alloc_db_addr(hwdev, &db_base, NULL);
+	if (err) {
+		hinic3_free_db_addr(hwdev, nic_io->sqs_db_addr);
+		dev_err(hwdev->dev, "Failed to allocate doorbell for rqs\n");
+		return err;
+	}
+	nic_io->rqs_db_addr = db_base;
+
+	nic_io->ci_vaddr_base =
+		dma_alloc_coherent(hwdev->dev,
+				   HINIC3_CI_TABLE_SIZE(nic_io->max_qps),
+				   &nic_io->ci_dma_base,
+				   GFP_KERNEL);
+	if (!nic_io->ci_vaddr_base) {
+		hinic3_free_db_addr(hwdev, nic_io->sqs_db_addr);
+		hinic3_free_db_addr(hwdev, nic_io->rqs_db_addr);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void hinic3_free_nicio_res(struct hinic3_nic_dev *nic_dev)
+{
+	struct hinic3_nic_io *nic_io = nic_dev->nic_io;
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+
+	dma_free_coherent(hwdev->dev,
+			  HINIC3_CI_TABLE_SIZE(nic_io->max_qps),
+			  nic_io->ci_vaddr_base, nic_io->ci_dma_base);
+
+	hinic3_free_db_addr(hwdev, nic_io->sqs_db_addr);
+	hinic3_free_db_addr(hwdev, nic_io->rqs_db_addr);
+}
+
+static int hinic3_create_sq(struct hinic3_hwdev *hwdev,
+			    struct hinic3_io_queue *sq,
+			    u16 q_id, u32 sq_depth, u16 sq_msix_idx)
+{
+	int err;
+
+	/* sq used & hardware request init 1 */
+	sq->owner = 1;
+
+	sq->q_id = q_id;
+	sq->msix_entry_idx = sq_msix_idx;
+
+	err = hinic3_wq_create(hwdev, &sq->wq, sq_depth,
+			       BIT(HINIC3_SQ_WQEBB_SHIFT));
+	if (err) {
+		dev_err(hwdev->dev, "Failed to create tx queue %u wq\n",
+			q_id);
+		return err;
+	}
+
+	return 0;
+}
+
+static int hinic3_create_rq(struct hinic3_hwdev *hwdev,
+			    struct hinic3_io_queue *rq,
+			    u16 q_id, u32 rq_depth, u16 rq_msix_idx)
+{
+	int err;
+
+	rq->q_id = q_id;
+	rq->msix_entry_idx = rq_msix_idx;
+
+	err = hinic3_wq_create(hwdev, &rq->wq, rq_depth,
+			       BIT(HINIC3_RQ_WQEBB_SHIFT +
+				   HINIC3_NORMAL_RQ_WQE));
+	if (err) {
+		dev_err(hwdev->dev, "Failed to create rx queue %u wq\n",
+			q_id);
+		return err;
+	}
+
+	return 0;
+}
+
+static int hinic3_create_qp(struct hinic3_hwdev *hwdev,
+			    struct hinic3_io_queue *sq,
+			    struct hinic3_io_queue *rq, u16 q_id, u32 sq_depth,
+			    u32 rq_depth, u16 qp_msix_idx)
+{
+	int err;
+
+	err = hinic3_create_sq(hwdev, sq, q_id, sq_depth, qp_msix_idx);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to create sq, qid: %u\n",
+			q_id);
+		return err;
+	}
+
+	err = hinic3_create_rq(hwdev, rq, q_id, rq_depth, qp_msix_idx);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to create rq, qid: %u\n",
+			q_id);
+		goto err_destroy_sq_wq;
+	}
+
+	return 0;
+
+err_destroy_sq_wq:
+	hinic3_wq_destroy(hwdev, &sq->wq);
+
+	return err;
+}
+
+static void hinic3_destroy_qp(struct hinic3_hwdev *hwdev,
+			      struct hinic3_io_queue *sq,
+			      struct hinic3_io_queue *rq)
+{
+	hinic3_wq_destroy(hwdev, &sq->wq);
+	hinic3_wq_destroy(hwdev, &rq->wq);
+}
+
+int hinic3_alloc_qps(struct hinic3_nic_dev *nic_dev,
+		     struct hinic3_dyna_qp_params *qp_params)
+{
+	struct msix_entry *qps_msix_entries = nic_dev->qps_msix_entries;
+	struct hinic3_nic_io *nic_io = nic_dev->nic_io;
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic3_io_queue *sqs;
+	struct hinic3_io_queue *rqs;
+	u16 q_id;
+	int err;
+
+	if (qp_params->num_qps > nic_io->max_qps || !qp_params->num_qps)
+		return -EINVAL;
+
+	sqs = kcalloc(qp_params->num_qps, sizeof(*sqs), GFP_KERNEL);
+	if (!sqs) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	rqs = kcalloc(qp_params->num_qps, sizeof(*rqs), GFP_KERNEL);
+	if (!rqs) {
+		err = -ENOMEM;
+		goto err_free_sqs;
+	}
+
+	for (q_id = 0; q_id < qp_params->num_qps; q_id++) {
+		err = hinic3_create_qp(hwdev, &sqs[q_id], &rqs[q_id], q_id,
+				       qp_params->sq_depth, qp_params->rq_depth,
+				       qps_msix_entries[q_id].entry);
+		if (err) {
+			dev_err(hwdev->dev, "Failed to allocate qp %u, err: %d\n",
+				q_id, err);
+			goto err_destroy_qp;
+		}
+	}
+
+	qp_params->sqs = sqs;
+	qp_params->rqs = rqs;
+
+	return 0;
+
+err_destroy_qp:
+	while (q_id > 0) {
+		q_id--;
+		hinic3_destroy_qp(hwdev, &sqs[q_id], &rqs[q_id]);
+	}
+	kfree(rqs);
+err_free_sqs:
+	kfree(sqs);
+err_out:
+	return err;
+}
+
+void hinic3_free_qps(struct hinic3_nic_dev *nic_dev,
+		     struct hinic3_dyna_qp_params *qp_params)
+{
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	u16 q_id;
+
+	for (q_id = 0; q_id < qp_params->num_qps; q_id++)
+		hinic3_destroy_qp(hwdev, &qp_params->sqs[q_id],
+				  &qp_params->rqs[q_id]);
+
+	kfree(qp_params->sqs);
+	kfree(qp_params->rqs);
+}
+
+void hinic3_init_qps(struct hinic3_nic_dev *nic_dev,
+		     struct hinic3_dyna_qp_params *qp_params)
+{
+	struct hinic3_nic_io *nic_io = nic_dev->nic_io;
+	struct hinic3_io_queue *sqs = qp_params->sqs;
+	struct hinic3_io_queue *rqs = qp_params->rqs;
+	u16 q_id;
+
+	nic_io->num_qps = qp_params->num_qps;
+	nic_io->sq = qp_params->sqs;
+	nic_io->rq = qp_params->rqs;
+	for (q_id = 0; q_id < nic_io->num_qps; q_id++) {
+		sqs[q_id].cons_idx_addr =
+			(u16 *)HINIC3_CI_VADDR(nic_io->ci_vaddr_base, q_id);
+		/* clear ci value */
+		WRITE_ONCE(*sqs[q_id].cons_idx_addr, 0);
+
+		sqs[q_id].db_addr = nic_io->sqs_db_addr;
+		rqs[q_id].db_addr = nic_io->rqs_db_addr;
+	}
+}
+
+void hinic3_uninit_qps(struct hinic3_nic_dev *nic_dev,
+		       struct hinic3_dyna_qp_params *qp_params)
+{
+	struct hinic3_nic_io *nic_io = nic_dev->nic_io;
+
+	qp_params->sqs = nic_io->sq;
+	qp_params->rqs = nic_io->rq;
+	qp_params->num_qps = nic_io->num_qps;
+}
+
+static void hinic3_qp_prepare_cmdq_header(struct hinic3_qp_ctxt_hdr *qp_ctxt_hdr,
+					  enum hinic3_qp_ctxt_type ctxt_type,
+					  u16 num_queues, u16 q_id)
+{
+	qp_ctxt_hdr->queue_type = cpu_to_le16(ctxt_type);
+	qp_ctxt_hdr->num_queues = cpu_to_le16(num_queues);
+	qp_ctxt_hdr->start_qid = cpu_to_le16(q_id);
+	qp_ctxt_hdr->rsvd = 0;
+}
+
+static void hinic3_sq_prepare_ctxt(struct hinic3_io_queue *sq, u16 sq_id,
+				   struct hinic3_sq_ctxt *sq_ctxt)
+{
+	u64 wq_page_addr, wq_page_pfn, wq_block_pfn;
+	u32 wq_block_pfn_hi, wq_block_pfn_lo;
+	u32 wq_page_pfn_hi, wq_page_pfn_lo;
+	u16 pi_start, ci_start;
+
+	ci_start = hinic3_get_sq_local_ci(sq);
+	pi_start = hinic3_get_sq_local_pi(sq);
+
+	wq_page_addr = hinic3_wq_get_first_wqe_page_addr(&sq->wq);
+
+	wq_page_pfn = WQ_PAGE_PFN(wq_page_addr);
+	wq_page_pfn_hi = upper_32_bits(wq_page_pfn);
+	wq_page_pfn_lo = lower_32_bits(wq_page_pfn);
+
+	wq_block_pfn = WQ_BLOCK_PFN(sq->wq.wq_block_paddr);
+	wq_block_pfn_hi = upper_32_bits(wq_block_pfn);
+	wq_block_pfn_lo = lower_32_bits(wq_block_pfn);
+
+	sq_ctxt->ci_pi =
+		cpu_to_le32(SQ_CTXT_CI_PI_SET(ci_start, CI_IDX) |
+			    SQ_CTXT_CI_PI_SET(pi_start, PI_IDX));
+
+	sq_ctxt->drop_mode_sp =
+		cpu_to_le32(SQ_CTXT_MODE_SET(0, SP_FLAG) |
+			    SQ_CTXT_MODE_SET(0, PKT_DROP));
+
+	sq_ctxt->wq_pfn_hi_owner =
+		cpu_to_le32(SQ_CTXT_WQ_PAGE_SET(wq_page_pfn_hi, HI_PFN) |
+			    SQ_CTXT_WQ_PAGE_SET(1, OWNER));
+
+	sq_ctxt->wq_pfn_lo = cpu_to_le32(wq_page_pfn_lo);
+
+	sq_ctxt->pkt_drop_thd =
+		cpu_to_le32(SQ_CTXT_PKT_DROP_THD_SET(HINIC3_DEFAULT_DROP_THD_ON, THD_ON) |
+			    SQ_CTXT_PKT_DROP_THD_SET(HINIC3_DEFAULT_DROP_THD_OFF, THD_OFF));
+
+	sq_ctxt->global_sq_id =
+		cpu_to_le32(SQ_CTXT_GLOBAL_QUEUE_ID_SET((u32)sq_id,
+							GLOBAL_SQ_ID));
+
+	/* enable insert c-vlan by default */
+	sq_ctxt->vlan_ceq_attr =
+		cpu_to_le32(SQ_CTXT_VLAN_CEQ_SET(0, CEQ_EN) |
+			    SQ_CTXT_VLAN_CEQ_SET(1, INSERT_MODE));
+
+	sq_ctxt->rsvd0 = 0;
+
+	sq_ctxt->pref_cache =
+		cpu_to_le32(SQ_CTXT_PREF_SET(SQ_WQ_PREFETCH_MIN, CACHE_MIN) |
+			    SQ_CTXT_PREF_SET(SQ_WQ_PREFETCH_MAX, CACHE_MAX) |
+			    SQ_CTXT_PREF_SET(SQ_WQ_PREFETCH_THRESHOLD, CACHE_THRESHOLD));
+
+	sq_ctxt->pref_ci_owner =
+		cpu_to_le32(SQ_CTXT_PREF_SET(SQ_CTXT_PREF_CI_HI(ci_start), CI_HI) |
+			    SQ_CTXT_PREF_SET(1, OWNER));
+
+	sq_ctxt->pref_wq_pfn_hi_ci =
+		cpu_to_le32(SQ_CTXT_PREF_SET(ci_start, CI_LOW) |
+			    SQ_CTXT_PREF_SET(wq_page_pfn_hi, WQ_PFN_HI));
+
+	sq_ctxt->pref_wq_pfn_lo = cpu_to_le32(wq_page_pfn_lo);
+
+	sq_ctxt->wq_block_pfn_hi =
+		cpu_to_le32(SQ_CTXT_WQ_BLOCK_SET(wq_block_pfn_hi, PFN_HI));
+
+	sq_ctxt->wq_block_pfn_lo = cpu_to_le32(wq_block_pfn_lo);
+}
+
+static void hinic3_rq_prepare_ctxt_get_wq_info(struct hinic3_io_queue *rq,
+					       u32 *wq_page_pfn_hi,
+					       u32 *wq_page_pfn_lo,
+					       u32 *wq_block_pfn_hi,
+					       u32 *wq_block_pfn_lo)
+{
+	u64 wq_page_addr, wq_page_pfn, wq_block_pfn;
+
+	wq_page_addr = hinic3_wq_get_first_wqe_page_addr(&rq->wq);
+
+	wq_page_pfn = WQ_PAGE_PFN(wq_page_addr);
+	*wq_page_pfn_hi = upper_32_bits(wq_page_pfn);
+	*wq_page_pfn_lo = lower_32_bits(wq_page_pfn);
+
+	wq_block_pfn = WQ_BLOCK_PFN(rq->wq.wq_block_paddr);
+	*wq_block_pfn_hi = upper_32_bits(wq_block_pfn);
+	*wq_block_pfn_lo = lower_32_bits(wq_block_pfn);
+}
+
+static void hinic3_rq_prepare_ctxt(struct hinic3_io_queue *rq,
+				   struct hinic3_rq_ctxt *rq_ctxt)
+{
+	u32 wq_block_pfn_hi, wq_block_pfn_lo;
+	u32 wq_page_pfn_hi, wq_page_pfn_lo;
+	u16 pi_start, ci_start;
+
+	ci_start = (rq->wq.cons_idx & rq->wq.idx_mask) << HINIC3_NORMAL_RQ_WQE;
+	pi_start = (rq->wq.prod_idx & rq->wq.idx_mask) << HINIC3_NORMAL_RQ_WQE;
+
+	hinic3_rq_prepare_ctxt_get_wq_info(rq, &wq_page_pfn_hi, &wq_page_pfn_lo,
+					   &wq_block_pfn_hi, &wq_block_pfn_lo);
+
+	rq_ctxt->ci_pi =
+		cpu_to_le32(RQ_CTXT_CI_PI_SET(ci_start, CI_IDX) |
+			    RQ_CTXT_CI_PI_SET(pi_start, PI_IDX));
+
+	rq_ctxt->ceq_attr =
+		cpu_to_le32(RQ_CTXT_CEQ_ATTR_SET(0, EN) |
+			    RQ_CTXT_CEQ_ATTR_SET(rq->msix_entry_idx, INTR));
+
+	rq_ctxt->wq_pfn_hi_type_owner =
+		cpu_to_le32(RQ_CTXT_WQ_PAGE_SET(wq_page_pfn_hi, HI_PFN) |
+			    RQ_CTXT_WQ_PAGE_SET(1, OWNER));
+
+	/* use 16Byte WQE */
+	rq_ctxt->wq_pfn_hi_type_owner |=
+		cpu_to_le32(RQ_CTXT_WQ_PAGE_SET(2, WQE_TYPE));
+	rq_ctxt->cqe_sge_len = cpu_to_le32(RQ_CTXT_CQE_LEN_SET(1, CQE_LEN));
+
+	rq_ctxt->wq_pfn_lo = cpu_to_le32(wq_page_pfn_lo);
+
+	rq_ctxt->pref_cache =
+		cpu_to_le32(RQ_CTXT_PREF_SET(RQ_WQ_PREFETCH_MIN, CACHE_MIN) |
+			    RQ_CTXT_PREF_SET(RQ_WQ_PREFETCH_MAX, CACHE_MAX) |
+			    RQ_CTXT_PREF_SET(RQ_WQ_PREFETCH_THRESHOLD, CACHE_THRESHOLD));
+
+	rq_ctxt->pref_ci_owner =
+		cpu_to_le32(RQ_CTXT_PREF_SET(SQ_CTXT_PREF_CI_HI(ci_start), CI_HI) |
+			    RQ_CTXT_PREF_SET(1, OWNER));
+
+	rq_ctxt->pref_wq_pfn_hi_ci =
+		cpu_to_le32(RQ_CTXT_PREF_SET(wq_page_pfn_hi, WQ_PFN_HI) |
+			    RQ_CTXT_PREF_SET(ci_start, CI_LOW));
+
+	rq_ctxt->pref_wq_pfn_lo = cpu_to_le32(wq_page_pfn_lo);
+
+	rq_ctxt->wq_block_pfn_hi =
+		cpu_to_le32(RQ_CTXT_WQ_BLOCK_SET(wq_block_pfn_hi, PFN_HI));
+
+	rq_ctxt->wq_block_pfn_lo = cpu_to_le32(wq_block_pfn_lo);
+}
+
+static int init_sq_ctxts(struct hinic3_nic_dev *nic_dev)
+{
+	struct hinic3_nic_io *nic_io = nic_dev->nic_io;
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic3_sq_ctxt_block *sq_ctxt_block;
+	u16 q_id, curr_id, max_ctxts, i;
+	struct hinic3_sq_ctxt *sq_ctxt;
+	struct hinic3_cmd_buf *cmd_buf;
+	struct hinic3_io_queue *sq;
+	__le64 out_param;
+	int err = 0;
+
+	cmd_buf = hinic3_alloc_cmd_buf(hwdev);
+	if (!cmd_buf) {
+		dev_err(hwdev->dev, "Failed to allocate cmd buf\n");
+		return -ENOMEM;
+	}
+
+	q_id = 0;
+	while (q_id < nic_io->num_qps) {
+		sq_ctxt_block = cmd_buf->buf;
+		sq_ctxt = sq_ctxt_block->sq_ctxt;
+
+		max_ctxts = (nic_io->num_qps - q_id) > HINIC3_Q_CTXT_MAX ?
+			     HINIC3_Q_CTXT_MAX : (nic_io->num_qps - q_id);
+
+		hinic3_qp_prepare_cmdq_header(&sq_ctxt_block->cmdq_hdr,
+					      HINIC3_QP_CTXT_TYPE_SQ, max_ctxts,
+					      q_id);
+
+		for (i = 0; i < max_ctxts; i++) {
+			curr_id = q_id + i;
+			sq = &nic_io->sq[curr_id];
+			hinic3_sq_prepare_ctxt(sq, curr_id, &sq_ctxt[i]);
+		}
+
+		hinic3_cmdq_buf_swab32(sq_ctxt_block, sizeof(*sq_ctxt_block));
+
+		cmd_buf->size = cpu_to_le16(SQ_CTXT_SIZE(max_ctxts));
+		err = hinic3_cmdq_direct_resp(hwdev, MGMT_MOD_L2NIC,
+					      L2NIC_UCODE_CMD_MODIFY_QUEUE_CTX,
+					      cmd_buf, &out_param);
+		if (err || out_param) {
+			dev_err(hwdev->dev, "Failed to set SQ ctxts, err: %d, out_param: 0x%llx\n",
+				err, out_param);
+			err = -EFAULT;
+			break;
+		}
+
+		q_id += max_ctxts;
+	}
+
+	hinic3_free_cmd_buf(hwdev, cmd_buf);
+
+	return err;
+}
+
+static int init_rq_ctxts(struct hinic3_nic_dev *nic_dev)
+{
+	struct hinic3_nic_io *nic_io = nic_dev->nic_io;
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic3_rq_ctxt_block *rq_ctxt_block;
+	u16 q_id, curr_id, max_ctxts, i;
+	struct hinic3_rq_ctxt *rq_ctxt;
+	struct hinic3_cmd_buf *cmd_buf;
+	struct hinic3_io_queue *rq;
+	__le64 out_param;
+	int err = 0;
+
+	cmd_buf = hinic3_alloc_cmd_buf(hwdev);
+	if (!cmd_buf) {
+		dev_err(hwdev->dev, "Failed to allocate cmd buf\n");
+		return -ENOMEM;
+	}
+
+	q_id = 0;
+	while (q_id < nic_io->num_qps) {
+		rq_ctxt_block = cmd_buf->buf;
+		rq_ctxt = rq_ctxt_block->rq_ctxt;
+
+		max_ctxts = (nic_io->num_qps - q_id) > HINIC3_Q_CTXT_MAX ?
+				HINIC3_Q_CTXT_MAX : (nic_io->num_qps - q_id);
+
+		hinic3_qp_prepare_cmdq_header(&rq_ctxt_block->cmdq_hdr,
+					      HINIC3_QP_CTXT_TYPE_RQ, max_ctxts,
+					      q_id);
+
+		for (i = 0; i < max_ctxts; i++) {
+			curr_id = q_id + i;
+			rq = &nic_io->rq[curr_id];
+			hinic3_rq_prepare_ctxt(rq, &rq_ctxt[i]);
+		}
+
+		hinic3_cmdq_buf_swab32(rq_ctxt_block, sizeof(*rq_ctxt_block));
+
+		cmd_buf->size = cpu_to_le16(RQ_CTXT_SIZE(max_ctxts));
+
+		err = hinic3_cmdq_direct_resp(hwdev, MGMT_MOD_L2NIC,
+					      L2NIC_UCODE_CMD_MODIFY_QUEUE_CTX,
+					      cmd_buf, &out_param);
+		if (err || out_param) {
+			dev_err(hwdev->dev, "Failed to set RQ ctxts, err: %d, out_param: 0x%llx\n",
+				err, out_param);
+			err = -EFAULT;
+			break;
+		}
+
+		q_id += max_ctxts;
+	}
+
+	hinic3_free_cmd_buf(hwdev, cmd_buf);
+
+	return err;
+}
+
+static int init_qp_ctxts(struct hinic3_nic_dev *nic_dev)
+{
+	int err;
+
+	err = init_sq_ctxts(nic_dev);
+	if (err)
+		return err;
+
+	err = init_rq_ctxts(nic_dev);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int clean_queue_offload_ctxt(struct hinic3_nic_dev *nic_dev,
+				    enum hinic3_qp_ctxt_type ctxt_type)
+{
+	struct hinic3_nic_io *nic_io = nic_dev->nic_io;
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic3_clean_queue_ctxt *ctxt_block;
+	struct hinic3_cmd_buf *cmd_buf;
+	__le64 out_param;
+	int err;
+
+	cmd_buf = hinic3_alloc_cmd_buf(hwdev);
+	if (!cmd_buf) {
+		dev_err(hwdev->dev, "Failed to allocate cmd buf\n");
+		return -ENOMEM;
+	}
+
+	ctxt_block = cmd_buf->buf;
+	ctxt_block->cmdq_hdr.num_queues = cpu_to_le16(nic_io->max_qps);
+	ctxt_block->cmdq_hdr.queue_type = cpu_to_le16(ctxt_type);
+	ctxt_block->cmdq_hdr.start_qid = 0;
+	ctxt_block->cmdq_hdr.rsvd = 0;
+	ctxt_block->rsvd = 0;
+
+	hinic3_cmdq_buf_swab32(ctxt_block, sizeof(*ctxt_block));
+
+	cmd_buf->size = cpu_to_le16(sizeof(*ctxt_block));
+
+	err = hinic3_cmdq_direct_resp(hwdev, MGMT_MOD_L2NIC,
+				      L2NIC_UCODE_CMD_CLEAN_QUEUE_CTX,
+				      cmd_buf, &out_param);
+	if (err || out_param) {
+		dev_err(hwdev->dev, "Failed to clean queue offload ctxts, err: %d,out_param: 0x%llx\n",
+			err, out_param);
+
+		err = -EFAULT;
+	}
+
+	hinic3_free_cmd_buf(hwdev, cmd_buf);
+
+	return err;
+}
+
+static int clean_qp_offload_ctxt(struct hinic3_nic_dev *nic_dev)
+{
+	/* clean LRO/TSO context space */
+	return clean_queue_offload_ctxt(nic_dev, HINIC3_QP_CTXT_TYPE_SQ) ||
+	       clean_queue_offload_ctxt(nic_dev, HINIC3_QP_CTXT_TYPE_RQ);
+}
+
+/* init qps ctxt and set sq ci attr and arm all sq */
+int hinic3_init_qp_ctxts(struct hinic3_nic_dev *nic_dev)
+{
+	struct hinic3_nic_io *nic_io = nic_dev->nic_io;
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic3_sq_attr sq_attr;
+	u32 rq_depth;
+	u16 q_id;
+	int err;
+
+	err = init_qp_ctxts(nic_dev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to init QP ctxts\n");
+		return err;
+	}
+
+	/* clean LRO/TSO context space */
+	err = clean_qp_offload_ctxt(nic_dev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to clean qp offload ctxts\n");
+		return err;
+	}
+
+	rq_depth = nic_io->rq[0].wq.q_depth << HINIC3_NORMAL_RQ_WQE;
+
+	err = hinic3_set_root_ctxt(hwdev, rq_depth, nic_io->sq[0].wq.q_depth,
+				   nic_io->rx_buf_len);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set root context\n");
+		return err;
+	}
+
+	for (q_id = 0; q_id < nic_io->num_qps; q_id++) {
+		sq_attr.ci_dma_base =
+			HINIC3_CI_PADDR(nic_io->ci_dma_base, q_id) >> 0x2;
+		sq_attr.pending_limit = HINIC3_DEFAULT_TX_CI_PENDING_LIMIT;
+		sq_attr.coalescing_time = HINIC3_DEFAULT_TX_CI_COALESCING_TIME;
+		sq_attr.intr_en = 1;
+		sq_attr.intr_idx = nic_io->sq[q_id].msix_entry_idx;
+		sq_attr.l2nic_sqn = q_id;
+		sq_attr.dma_attr_off = 0;
+		err = hinic3_set_ci_table(hwdev, &sq_attr);
+		if (err) {
+			dev_err(hwdev->dev, "Failed to set ci table\n");
+			goto err_clean_root_ctxt;
+		}
+	}
+
+	return 0;
+
+err_clean_root_ctxt:
+	hinic3_clean_root_ctxt(hwdev);
+
+	return err;
+}
+
+void hinic3_free_qp_ctxts(struct hinic3_nic_dev *nic_dev)
+{
+	hinic3_clean_root_ctxt(nic_dev->hwdev);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h
new file mode 100644
index 000000000000..12eefabcf1db
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h
@@ -0,0 +1,145 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_NIC_IO_H_
+#define _HINIC3_NIC_IO_H_
+
+#include <linux/bitfield.h>
+
+#include "hinic3_wq.h"
+
+struct hinic3_nic_dev;
+
+#define HINIC3_SQ_WQEBB_SHIFT      4
+#define HINIC3_RQ_WQEBB_SHIFT      3
+#define HINIC3_SQ_WQEBB_SIZE       BIT(HINIC3_SQ_WQEBB_SHIFT)
+
+/* ******************** RQ_CTRL ******************** */
+enum hinic3_rq_wqe_type {
+	HINIC3_NORMAL_RQ_WQE = 1,
+};
+
+/* ******************** SQ_CTRL ******************** */
+#define HINIC3_TX_MSS_DEFAULT  0x3E00
+#define HINIC3_TX_MSS_MIN      0x50
+#define HINIC3_MAX_SQ_SGE      18
+
+struct hinic3_io_queue {
+	struct hinic3_wq  wq;
+	u8                owner;
+	u16               q_id;
+	u16               msix_entry_idx;
+	u8 __iomem        *db_addr;
+	u16               *cons_idx_addr;
+} ____cacheline_aligned;
+
+static inline u16 hinic3_get_sq_local_ci(const struct hinic3_io_queue *sq)
+{
+	const struct hinic3_wq *wq = &sq->wq;
+
+	return wq->cons_idx & wq->idx_mask;
+}
+
+static inline u16 hinic3_get_sq_local_pi(const struct hinic3_io_queue *sq)
+{
+	const struct hinic3_wq *wq = &sq->wq;
+
+	return wq->prod_idx & wq->idx_mask;
+}
+
+static inline u16 hinic3_get_sq_hw_ci(const struct hinic3_io_queue *sq)
+{
+	const struct hinic3_wq *wq = &sq->wq;
+
+	return READ_ONCE(*sq->cons_idx_addr) & wq->idx_mask;
+}
+
+/* ******************** DB INFO ******************** */
+#define DB_INFO_QID_MASK    GENMASK(12, 0)
+#define DB_INFO_CFLAG_MASK  BIT(23)
+#define DB_INFO_COS_MASK    GENMASK(26, 24)
+#define DB_INFO_TYPE_MASK   GENMASK(31, 27)
+#define DB_INFO_SET(val, member)  \
+	FIELD_PREP(DB_INFO_##member##_MASK, val)
+
+#define DB_PI_LOW_MASK   0xFFU
+#define DB_PI_HIGH_MASK  0xFFU
+#define DB_PI_HI_SHIFT   8
+#define DB_PI_LOW(pi)    ((pi) & DB_PI_LOW_MASK)
+#define DB_PI_HIGH(pi)   (((pi) >> DB_PI_HI_SHIFT) & DB_PI_HIGH_MASK)
+#define DB_ADDR(q, pi)   ((u64 __iomem *)((q)->db_addr) + DB_PI_LOW(pi))
+#define DB_SRC_TYPE      1
+
+/* CFLAG_DATA_PATH */
+#define DB_CFLAG_DP_SQ   0
+#define DB_CFLAG_DP_RQ   1
+
+struct hinic3_nic_db {
+	__le32 db_info;
+	__le32 pi_hi;
+};
+
+static inline void hinic3_write_db(struct hinic3_io_queue *queue, int cos,
+				   u8 cflag, u16 pi)
+{
+	struct hinic3_nic_db db;
+
+	db.db_info =
+		cpu_to_le32(DB_INFO_SET(DB_SRC_TYPE, TYPE) |
+			    DB_INFO_SET(cflag, CFLAG) |
+			    DB_INFO_SET(cos, COS) |
+			    DB_INFO_SET(queue->q_id, QID));
+	db.pi_hi = cpu_to_le32(DB_PI_HIGH(pi));
+
+	writeq(*((u64 *)&db), DB_ADDR(queue, pi));
+}
+
+struct hinic3_dyna_qp_params {
+	u16                    num_qps;
+	u32                    sq_depth;
+	u32                    rq_depth;
+
+	struct hinic3_io_queue *sqs;
+	struct hinic3_io_queue *rqs;
+};
+
+struct hinic3_nic_io {
+	struct hinic3_io_queue *sq;
+	struct hinic3_io_queue *rq;
+
+	u16                    num_qps;
+	u16                    max_qps;
+
+	/* Base address for consumer index of all tx queues. Each queue is
+	 * given a full cache line to hold its consumer index. HW updates
+	 * current consumer index as it consumes tx WQEs.
+	 */
+	void                   *ci_vaddr_base;
+	dma_addr_t             ci_dma_base;
+
+	u8 __iomem             *sqs_db_addr;
+	u8 __iomem             *rqs_db_addr;
+
+	u16                    rx_buf_len;
+	u64                    feature_cap;
+};
+
+int hinic3_init_nic_io(struct hinic3_nic_dev *nic_dev);
+void hinic3_free_nic_io(struct hinic3_nic_dev *nic_dev);
+
+int hinic3_init_nicio_res(struct hinic3_nic_dev *nic_dev);
+void hinic3_free_nicio_res(struct hinic3_nic_dev *nic_dev);
+
+int hinic3_alloc_qps(struct hinic3_nic_dev *nic_dev,
+		     struct hinic3_dyna_qp_params *qp_params);
+void hinic3_free_qps(struct hinic3_nic_dev *nic_dev,
+		     struct hinic3_dyna_qp_params *qp_params);
+void hinic3_init_qps(struct hinic3_nic_dev *nic_dev,
+		     struct hinic3_dyna_qp_params *qp_params);
+void hinic3_uninit_qps(struct hinic3_nic_dev *nic_dev,
+		       struct hinic3_dyna_qp_params *qp_params);
+
+int hinic3_init_qp_ctxts(struct hinic3_nic_dev *nic_dev);
+void hinic3_free_qp_ctxts(struct hinic3_nic_dev *nic_dev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_pci_id_tbl.h b/drivers/net/ethernet/huawei/hinic3/hinic3_pci_id_tbl.h
new file mode 100644
index 000000000000..86c88d0bb4bd
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_pci_id_tbl.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_PCI_ID_TBL_H_
+#define _HINIC3_PCI_ID_TBL_H_
+
+#define PCI_DEV_ID_HINIC3_VF    0x375F
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.c b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.c
new file mode 100644
index 000000000000..fab9011de9ad
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/device.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_queue_common.h"
+
+void hinic3_queue_pages_init(struct hinic3_queue_pages *qpages, u32 q_depth,
+			     u32 page_size, u32 elem_size)
+{
+	u32 elem_per_page;
+
+	elem_per_page = min(page_size / elem_size, q_depth);
+
+	qpages->pages = NULL;
+	qpages->page_size = page_size;
+	qpages->num_pages = max(q_depth / elem_per_page, 1);
+	qpages->elem_size_shift = ilog2(elem_size);
+	qpages->elem_per_pg_shift = ilog2(elem_per_page);
+}
+
+static void __queue_pages_free(struct hinic3_hwdev *hwdev,
+			       struct hinic3_queue_pages *qpages, u32 pg_cnt)
+{
+	while (pg_cnt > 0) {
+		pg_cnt--;
+		hinic3_dma_free_coherent_align(hwdev->dev,
+					       qpages->pages + pg_cnt);
+	}
+	kfree(qpages->pages);
+	qpages->pages = NULL;
+}
+
+void hinic3_queue_pages_free(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages)
+{
+	__queue_pages_free(hwdev, qpages, qpages->num_pages);
+}
+
+int hinic3_queue_pages_alloc(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages, u32 align)
+{
+	u32 pg_idx;
+	int err;
+
+	qpages->pages = kcalloc(qpages->num_pages, sizeof(qpages->pages[0]),
+				GFP_KERNEL);
+	if (!qpages->pages)
+		return -ENOMEM;
+
+	if (align == 0)
+		align = qpages->page_size;
+
+	for (pg_idx = 0; pg_idx < qpages->num_pages; pg_idx++) {
+		err = hinic3_dma_zalloc_coherent_align(hwdev->dev,
+						       qpages->page_size,
+						       align,
+						       GFP_KERNEL,
+						       qpages->pages + pg_idx);
+		if (err) {
+			__queue_pages_free(hwdev, qpages, pg_idx);
+			return err;
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.h b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.h
new file mode 100644
index 000000000000..ec4cae0a0929
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_QUEUE_COMMON_H_
+#define _HINIC3_QUEUE_COMMON_H_
+
+#include <linux/types.h>
+
+#include "hinic3_common.h"
+
+struct hinic3_hwdev;
+
+struct hinic3_queue_pages {
+	/* Array of DMA-able pages that actually holds the queue entries. */
+	struct hinic3_dma_addr_align  *pages;
+	/* Page size in bytes. */
+	u32                           page_size;
+	/* Number of pages, must be power of 2. */
+	u16                           num_pages;
+	u8                            elem_size_shift;
+	u8                            elem_per_pg_shift;
+};
+
+void hinic3_queue_pages_init(struct hinic3_queue_pages *qpages, u32 q_depth,
+			     u32 page_size, u32 elem_size);
+int hinic3_queue_pages_alloc(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages, u32 align);
+void hinic3_queue_pages_free(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages);
+
+/* Get pointer to queue entry at the specified index. Index does not have to be
+ * masked to queue depth, only least significant bits will be used. Also
+ * provides remaining elements in same page (including the first one) in case
+ * caller needs multiple entries.
+ */
+static inline void *get_q_element(const struct hinic3_queue_pages *qpages,
+				  u32 idx, u32 *remaining_in_page)
+{
+	const struct hinic3_dma_addr_align *page;
+	u32 page_idx, elem_idx, elem_per_pg, ofs;
+	u8 shift;
+
+	shift = qpages->elem_per_pg_shift;
+	page_idx = (idx >> shift) & (qpages->num_pages - 1);
+	elem_per_pg = 1 << shift;
+	elem_idx = idx & (elem_per_pg - 1);
+	if (remaining_in_page)
+		*remaining_in_page = elem_per_pg - elem_idx;
+	ofs = elem_idx << qpages->elem_size_shift;
+	page = qpages->pages + page_idx;
+	return (char *)page->align_vaddr + ofs;
+}
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_rss.c b/drivers/net/ethernet/huawei/hinic3/hinic3_rss.c
new file mode 100644
index 000000000000..4ff1b2f79838
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_rss.c
@@ -0,0 +1,336 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/ethtool.h>
+
+#include "hinic3_cmdq.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_rss.h"
+
+static void hinic3_fillout_indir_tbl(struct net_device *netdev, u16 *indir)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	u16 i, num_qps;
+
+	num_qps = nic_dev->q_params.num_qps;
+	for (i = 0; i < L2NIC_RSS_INDIR_SIZE; i++)
+		indir[i] = ethtool_rxfh_indir_default(i, num_qps);
+}
+
+static int hinic3_rss_cfg(struct hinic3_hwdev *hwdev, u8 rss_en, u16 num_qps)
+{
+	struct mgmt_msg_params msg_params = {};
+	struct l2nic_cmd_cfg_rss rss_cfg = {};
+	int err;
+
+	rss_cfg.func_id = hinic3_global_func_id(hwdev);
+	rss_cfg.rss_en = rss_en;
+	rss_cfg.rq_priority_number = 0;
+	rss_cfg.num_qps = num_qps;
+
+	mgmt_msg_params_init_default(&msg_params, &rss_cfg, sizeof(rss_cfg));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_CFG_RSS, &msg_params);
+	if (err || rss_cfg.msg_head.status) {
+		dev_err(hwdev->dev, "Failed to set rss cfg, err: %d, status: 0x%x\n",
+			err, rss_cfg.msg_head.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void hinic3_init_rss_parameters(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	nic_dev->rss_hash_type = HINIC3_RSS_HASH_ENGINE_TYPE_XOR;
+	nic_dev->rss_type.tcp_ipv6_ext = 1;
+	nic_dev->rss_type.ipv6_ext = 1;
+	nic_dev->rss_type.tcp_ipv6 = 1;
+	nic_dev->rss_type.ipv6 = 1;
+	nic_dev->rss_type.tcp_ipv4 = 1;
+	nic_dev->rss_type.ipv4 = 1;
+	nic_dev->rss_type.udp_ipv6 = 1;
+	nic_dev->rss_type.udp_ipv4 = 1;
+}
+
+static void decide_num_qps(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	unsigned int dev_cpus;
+
+	dev_cpus = netif_get_num_default_rss_queues();
+	nic_dev->q_params.num_qps = min(dev_cpus, nic_dev->max_qps);
+}
+
+static int alloc_rss_resource(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	nic_dev->rss_hkey = kmalloc_array(L2NIC_RSS_KEY_SIZE,
+					  sizeof(nic_dev->rss_hkey[0]),
+					  GFP_KERNEL);
+	if (!nic_dev->rss_hkey)
+		return -ENOMEM;
+
+	netdev_rss_key_fill(nic_dev->rss_hkey, L2NIC_RSS_KEY_SIZE);
+
+	nic_dev->rss_indir = kcalloc(L2NIC_RSS_INDIR_SIZE, sizeof(u16),
+				     GFP_KERNEL);
+	if (!nic_dev->rss_indir) {
+		kfree(nic_dev->rss_hkey);
+		nic_dev->rss_hkey = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int hinic3_rss_set_indir_tbl(struct hinic3_hwdev *hwdev,
+				    const u16 *indir_table)
+{
+	struct l2nic_cmd_rss_set_indir_tbl *indir_tbl;
+	struct hinic3_cmd_buf *cmd_buf;
+	__le64 out_param;
+	int err;
+	u32 i;
+
+	cmd_buf = hinic3_alloc_cmd_buf(hwdev);
+	if (!cmd_buf) {
+		dev_err(hwdev->dev, "Failed to allocate cmd buf\n");
+		return -ENOMEM;
+	}
+
+	cmd_buf->size = cpu_to_le16(sizeof(struct l2nic_cmd_rss_set_indir_tbl));
+	indir_tbl = cmd_buf->buf;
+	memset(indir_tbl, 0, sizeof(*indir_tbl));
+
+	for (i = 0; i < L2NIC_RSS_INDIR_SIZE; i++)
+		indir_tbl->entry[i] = cpu_to_le16(indir_table[i]);
+
+	hinic3_cmdq_buf_swab32(indir_tbl, sizeof(*indir_tbl));
+
+	err = hinic3_cmdq_direct_resp(hwdev, MGMT_MOD_L2NIC,
+				      L2NIC_UCODE_CMD_SET_RSS_INDIR_TBL,
+				      cmd_buf, &out_param);
+	if (err || out_param) {
+		dev_err(hwdev->dev, "Failed to set rss indir table\n");
+		err = -EFAULT;
+	}
+
+	hinic3_free_cmd_buf(hwdev, cmd_buf);
+
+	return err;
+}
+
+static int hinic3_set_rss_type(struct hinic3_hwdev *hwdev,
+			       struct hinic3_rss_type rss_type)
+{
+	struct l2nic_cmd_set_rss_ctx_tbl ctx_tbl = {};
+	struct mgmt_msg_params msg_params = {};
+	u32 ctx;
+	int err;
+
+	ctx_tbl.func_id = hinic3_global_func_id(hwdev);
+	ctx = L2NIC_RSS_TYPE_SET(1, VALID) |
+	      L2NIC_RSS_TYPE_SET(rss_type.ipv4, IPV4) |
+	      L2NIC_RSS_TYPE_SET(rss_type.ipv6, IPV6) |
+	      L2NIC_RSS_TYPE_SET(rss_type.ipv6_ext, IPV6_EXT) |
+	      L2NIC_RSS_TYPE_SET(rss_type.tcp_ipv4, TCP_IPV4) |
+	      L2NIC_RSS_TYPE_SET(rss_type.tcp_ipv6, TCP_IPV6) |
+	      L2NIC_RSS_TYPE_SET(rss_type.tcp_ipv6_ext, TCP_IPV6_EXT) |
+	      L2NIC_RSS_TYPE_SET(rss_type.udp_ipv4, UDP_IPV4) |
+	      L2NIC_RSS_TYPE_SET(rss_type.udp_ipv6, UDP_IPV6);
+	ctx_tbl.context = ctx;
+
+	mgmt_msg_params_init_default(&msg_params, &ctx_tbl, sizeof(ctx_tbl));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_SET_RSS_CTX_TBL, &msg_params);
+
+	if (ctx_tbl.msg_head.status == MGMT_STATUS_CMD_UNSUPPORTED) {
+		return MGMT_STATUS_CMD_UNSUPPORTED;
+	} else if (err || ctx_tbl.msg_head.status) {
+		dev_err(hwdev->dev, "mgmt Failed to set rss context offload, err: %d, status: 0x%x\n",
+			err, ctx_tbl.msg_head.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hinic3_rss_cfg_hash_type(struct hinic3_hwdev *hwdev, u8 opcode,
+				    enum hinic3_rss_hash_type *type)
+{
+	struct l2nic_cmd_cfg_rss_engine hash_type_cmd = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	hash_type_cmd.func_id = hinic3_global_func_id(hwdev);
+	hash_type_cmd.opcode = opcode;
+
+	if (opcode == MGMT_MSG_CMD_OP_SET)
+		hash_type_cmd.hash_engine = *type;
+
+	mgmt_msg_params_init_default(&msg_params, &hash_type_cmd,
+				     sizeof(hash_type_cmd));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_CFG_RSS_HASH_ENGINE,
+				       &msg_params);
+	if (err || hash_type_cmd.msg_head.status) {
+		dev_err(hwdev->dev, "Failed to %s hash engine, err: %d, status: 0x%x\n",
+			opcode == MGMT_MSG_CMD_OP_SET ? "set" : "get",
+			err, hash_type_cmd.msg_head.status);
+		return -EIO;
+	}
+
+	if (opcode == MGMT_MSG_CMD_OP_GET)
+		*type = hash_type_cmd.hash_engine;
+
+	return 0;
+}
+
+static int hinic3_rss_set_hash_type(struct hinic3_hwdev *hwdev,
+				    enum hinic3_rss_hash_type type)
+{
+	return hinic3_rss_cfg_hash_type(hwdev, MGMT_MSG_CMD_OP_SET, &type);
+}
+
+static int hinic3_config_rss_hw_resource(struct net_device *netdev,
+					 u16 *indir_tbl)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	int err;
+
+	err = hinic3_rss_set_indir_tbl(nic_dev->hwdev, indir_tbl);
+	if (err)
+		return err;
+
+	err = hinic3_set_rss_type(nic_dev->hwdev, nic_dev->rss_type);
+	if (err)
+		return err;
+
+	return hinic3_rss_set_hash_type(nic_dev->hwdev, nic_dev->rss_hash_type);
+}
+
+static int hinic3_rss_cfg_hash_key(struct hinic3_hwdev *hwdev, u8 opcode,
+				   u8 *key)
+{
+	struct l2nic_cmd_cfg_rss_hash_key hash_key = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	hash_key.func_id = hinic3_global_func_id(hwdev);
+	hash_key.opcode = opcode;
+
+	if (opcode == MGMT_MSG_CMD_OP_SET)
+		memcpy(hash_key.key, key, L2NIC_RSS_KEY_SIZE);
+
+	mgmt_msg_params_init_default(&msg_params, &hash_key, sizeof(hash_key));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_CFG_RSS_HASH_KEY, &msg_params);
+	if (err || hash_key.msg_head.status) {
+		dev_err(hwdev->dev, "Failed to %s hash key, err: %d, status: 0x%x\n",
+			opcode == MGMT_MSG_CMD_OP_SET ? "set" : "get",
+			err, hash_key.msg_head.status);
+		return -EINVAL;
+	}
+
+	if (opcode == MGMT_MSG_CMD_OP_GET)
+		memcpy(key, hash_key.key, L2NIC_RSS_KEY_SIZE);
+
+	return 0;
+}
+
+static int hinic3_rss_set_hash_key(struct hinic3_hwdev *hwdev, u8 *key)
+{
+	return hinic3_rss_cfg_hash_key(hwdev, MGMT_MSG_CMD_OP_SET, key);
+}
+
+static int hinic3_set_hw_rss_parameters(struct net_device *netdev, u8 rss_en)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	int err;
+
+	err = hinic3_rss_set_hash_key(nic_dev->hwdev, nic_dev->rss_hkey);
+	if (err)
+		return err;
+
+	hinic3_fillout_indir_tbl(netdev, nic_dev->rss_indir);
+
+	err = hinic3_config_rss_hw_resource(netdev, nic_dev->rss_indir);
+	if (err)
+		return err;
+
+	err = hinic3_rss_cfg(nic_dev->hwdev, rss_en, nic_dev->q_params.num_qps);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int hinic3_rss_init(struct net_device *netdev)
+{
+	return hinic3_set_hw_rss_parameters(netdev, 1);
+}
+
+void hinic3_rss_uninit(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	hinic3_rss_cfg(nic_dev->hwdev, 0, 0);
+}
+
+void hinic3_clear_rss_config(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	kfree(nic_dev->rss_hkey);
+	nic_dev->rss_hkey = NULL;
+
+	kfree(nic_dev->rss_indir);
+	nic_dev->rss_indir = NULL;
+}
+
+void hinic3_try_to_enable_rss(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	int err;
+
+	nic_dev->max_qps = hinic3_func_max_qnum(hwdev);
+	if (nic_dev->max_qps <= 1 ||
+	    !hinic3_test_support(nic_dev, HINIC3_NIC_F_RSS))
+		goto err_reset_q_params;
+
+	err = alloc_rss_resource(netdev);
+	if (err) {
+		nic_dev->max_qps = 1;
+		goto err_reset_q_params;
+	}
+
+	set_bit(HINIC3_RSS_ENABLE, &nic_dev->flags);
+	decide_num_qps(netdev);
+	hinic3_init_rss_parameters(netdev);
+	err = hinic3_set_hw_rss_parameters(netdev, 0);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set hardware rss parameters\n");
+		hinic3_clear_rss_config(netdev);
+		nic_dev->max_qps = 1;
+		goto err_reset_q_params;
+	}
+
+	return;
+
+err_reset_q_params:
+	clear_bit(HINIC3_RSS_ENABLE, &nic_dev->flags);
+	nic_dev->q_params.num_qps = nic_dev->max_qps;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_rss.h b/drivers/net/ethernet/huawei/hinic3/hinic3_rss.h
new file mode 100644
index 000000000000..78d82c2aca06
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_rss.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_RSS_H_
+#define _HINIC3_RSS_H_
+
+#include <linux/netdevice.h>
+
+int hinic3_rss_init(struct net_device *netdev);
+void hinic3_rss_uninit(struct net_device *netdev);
+void hinic3_try_to_enable_rss(struct net_device *netdev);
+void hinic3_clear_rss_config(struct net_device *netdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_rx.c b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.c
new file mode 100644
index 000000000000..16c00c3bb1ed
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.c
@@ -0,0 +1,551 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/netdevice.h>
+#include <net/gro.h>
+#include <net/page_pool/helpers.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_rx.h"
+
+#define HINIC3_RX_HDR_SIZE              256
+#define HINIC3_RX_BUFFER_WRITE          16
+
+#define HINIC3_RX_TCP_PKT               0x3
+#define HINIC3_RX_UDP_PKT               0x4
+#define HINIC3_RX_SCTP_PKT              0x7
+
+#define HINIC3_RX_IPV4_PKT              0
+#define HINIC3_RX_IPV6_PKT              1
+#define HINIC3_RX_INVALID_IP_TYPE       2
+
+#define HINIC3_RX_PKT_FORMAT_NON_TUNNEL 0
+#define HINIC3_RX_PKT_FORMAT_VXLAN      1
+
+#define HINIC3_LRO_PKT_HDR_LEN_IPV4     66
+#define HINIC3_LRO_PKT_HDR_LEN_IPV6     86
+#define HINIC3_LRO_PKT_HDR_LEN(cqe) \
+	(RQ_CQE_OFFOLAD_TYPE_GET((cqe)->offload_type, IP_TYPE) == \
+	 HINIC3_RX_IPV6_PKT ? HINIC3_LRO_PKT_HDR_LEN_IPV6 : \
+	 HINIC3_LRO_PKT_HDR_LEN_IPV4)
+
+int hinic3_alloc_rxqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct pci_dev *pdev = nic_dev->pdev;
+	u16 num_rxqs = nic_dev->max_qps;
+	struct hinic3_rxq *rxq;
+	u16 q_id;
+
+	nic_dev->rxqs = kcalloc(num_rxqs, sizeof(*nic_dev->rxqs), GFP_KERNEL);
+	if (!nic_dev->rxqs)
+		return -ENOMEM;
+
+	for (q_id = 0; q_id < num_rxqs; q_id++) {
+		rxq = &nic_dev->rxqs[q_id];
+		rxq->netdev = netdev;
+		rxq->dev = &pdev->dev;
+		rxq->q_id = q_id;
+		rxq->buf_len = nic_dev->rx_buf_len;
+		rxq->buf_len_shift = ilog2(nic_dev->rx_buf_len);
+		rxq->q_depth = nic_dev->q_params.rq_depth;
+		rxq->q_mask = nic_dev->q_params.rq_depth - 1;
+	}
+
+	return 0;
+}
+
+void hinic3_free_rxqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	kfree(nic_dev->rxqs);
+}
+
+static int rx_alloc_mapped_page(struct page_pool *page_pool,
+				struct hinic3_rx_info *rx_info, u16 buf_len)
+{
+	struct page *page;
+	u32 page_offset;
+
+	if (likely(rx_info->page))
+		return 0;
+
+	page = page_pool_dev_alloc_frag(page_pool, &page_offset, buf_len);
+	if (unlikely(!page))
+		return -ENOMEM;
+
+	rx_info->page = page;
+	rx_info->page_offset = page_offset;
+
+	return 0;
+}
+
+/* Associate fixed completion element to every wqe in the rq. Every rq wqe will
+ * always post completion to the same place.
+ */
+static void rq_associate_cqes(struct hinic3_rxq *rxq)
+{
+	struct hinic3_queue_pages *qpages;
+	struct hinic3_rq_wqe *rq_wqe;
+	dma_addr_t cqe_dma;
+	u32 i;
+
+	qpages = &rxq->rq->wq.qpages;
+
+	for (i = 0; i < rxq->q_depth; i++) {
+		rq_wqe = get_q_element(qpages, i, NULL);
+		cqe_dma = rxq->cqe_start_paddr +
+			  i * sizeof(struct hinic3_rq_cqe);
+		rq_wqe->cqe_hi_addr = cpu_to_le32(upper_32_bits(cqe_dma));
+		rq_wqe->cqe_lo_addr = cpu_to_le32(lower_32_bits(cqe_dma));
+	}
+}
+
+static void rq_wqe_buf_set(struct hinic3_io_queue *rq, uint32_t wqe_idx,
+			   dma_addr_t dma_addr, u16 len)
+{
+	struct hinic3_rq_wqe *rq_wqe;
+
+	rq_wqe = get_q_element(&rq->wq.qpages, wqe_idx, NULL);
+	rq_wqe->buf_hi_addr = cpu_to_le32(upper_32_bits(dma_addr));
+	rq_wqe->buf_lo_addr = cpu_to_le32(lower_32_bits(dma_addr));
+}
+
+static u32 hinic3_rx_fill_buffers(struct hinic3_rxq *rxq)
+{
+	u32 i, free_wqebbs = rxq->delta - 1;
+	struct hinic3_rx_info *rx_info;
+	dma_addr_t dma_addr;
+	int err;
+
+	for (i = 0; i < free_wqebbs; i++) {
+		rx_info = &rxq->rx_info[rxq->next_to_update];
+
+		err = rx_alloc_mapped_page(rxq->page_pool, rx_info,
+					   rxq->buf_len);
+		if (unlikely(err))
+			break;
+
+		dma_addr = page_pool_get_dma_addr(rx_info->page) +
+			rx_info->page_offset;
+		rq_wqe_buf_set(rxq->rq, rxq->next_to_update, dma_addr,
+			       rxq->buf_len);
+		rxq->next_to_update = (rxq->next_to_update + 1) & rxq->q_mask;
+	}
+
+	if (likely(i)) {
+		hinic3_write_db(rxq->rq, rxq->q_id & 3, DB_CFLAG_DP_RQ,
+				rxq->next_to_update << HINIC3_NORMAL_RQ_WQE);
+		rxq->delta -= i;
+		rxq->next_to_alloc = rxq->next_to_update;
+	}
+
+	return i;
+}
+
+static u32 hinic3_alloc_rx_buffers(struct hinic3_dyna_rxq_res *rqres,
+				   u32 rq_depth, u16 buf_len)
+{
+	u32 free_wqebbs = rq_depth - 1;
+	u32 idx;
+	int err;
+
+	for (idx = 0; idx < free_wqebbs; idx++) {
+		err = rx_alloc_mapped_page(rqres->page_pool,
+					   &rqres->rx_info[idx], buf_len);
+		if (err)
+			break;
+	}
+
+	return idx;
+}
+
+static void hinic3_free_rx_buffers(struct hinic3_dyna_rxq_res *rqres,
+				   u32 q_depth)
+{
+	struct hinic3_rx_info *rx_info;
+	u32 i;
+
+	/* Free all the Rx ring sk_buffs */
+	for (i = 0; i < q_depth; i++) {
+		rx_info = &rqres->rx_info[i];
+
+		if (rx_info->page) {
+			page_pool_put_full_page(rqres->page_pool,
+						rx_info->page, false);
+			rx_info->page = NULL;
+		}
+	}
+}
+
+static void hinic3_add_rx_frag(struct hinic3_rxq *rxq,
+			       struct hinic3_rx_info *rx_info,
+			       struct sk_buff *skb, u32 size)
+{
+	struct page *page;
+	u8 *va;
+
+	page = rx_info->page;
+	va = (u8 *)page_address(page) + rx_info->page_offset;
+	net_prefetch(va);
+
+	page_pool_dma_sync_for_cpu(rxq->page_pool, page, rx_info->page_offset,
+				   rxq->buf_len);
+
+	if (size <= HINIC3_RX_HDR_SIZE && !skb_is_nonlinear(skb)) {
+		memcpy(__skb_put(skb, size), va,
+		       ALIGN(size, sizeof(long)));
+		page_pool_put_full_page(rxq->page_pool, page, false);
+
+		return;
+	}
+
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+			rx_info->page_offset, size, rxq->buf_len);
+	skb_mark_for_recycle(skb);
+}
+
+static void packaging_skb(struct hinic3_rxq *rxq, struct sk_buff *skb,
+			  u32 sge_num, u32 pkt_len)
+{
+	struct hinic3_rx_info *rx_info;
+	u32 temp_pkt_len = pkt_len;
+	u32 temp_sge_num = sge_num;
+	u32 sw_ci;
+	u32 size;
+
+	sw_ci = rxq->cons_idx & rxq->q_mask;
+	while (temp_sge_num) {
+		rx_info = &rxq->rx_info[sw_ci];
+		sw_ci = (sw_ci + 1) & rxq->q_mask;
+		if (unlikely(temp_pkt_len > rxq->buf_len)) {
+			size = rxq->buf_len;
+			temp_pkt_len -= rxq->buf_len;
+		} else {
+			size = temp_pkt_len;
+		}
+
+		hinic3_add_rx_frag(rxq, rx_info, skb, size);
+
+		/* clear contents of buffer_info */
+		rx_info->page = NULL;
+		temp_sge_num--;
+	}
+}
+
+static u32 hinic3_get_sge_num(struct hinic3_rxq *rxq, u32 pkt_len)
+{
+	u32 sge_num;
+
+	sge_num = pkt_len >> rxq->buf_len_shift;
+	sge_num += (pkt_len & (rxq->buf_len - 1)) ? 1 : 0;
+
+	return sge_num;
+}
+
+static struct sk_buff *hinic3_fetch_rx_buffer(struct hinic3_rxq *rxq,
+					      u32 pkt_len)
+{
+	struct sk_buff *skb;
+	u32 sge_num;
+
+	skb = napi_alloc_skb(&rxq->irq_cfg->napi, HINIC3_RX_HDR_SIZE);
+	if (unlikely(!skb))
+		return NULL;
+
+	sge_num = hinic3_get_sge_num(rxq, pkt_len);
+
+	net_prefetchw(skb->data);
+	packaging_skb(rxq, skb, sge_num, pkt_len);
+
+	rxq->cons_idx += sge_num;
+	rxq->delta += sge_num;
+
+	return skb;
+}
+
+static void hinic3_pull_tail(struct sk_buff *skb)
+{
+	skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
+	unsigned int pull_len;
+	unsigned char *va;
+
+	va = skb_frag_address(frag);
+
+	/* we need the header to contain the greater of either ETH_HLEN or
+	 * 60 bytes if the skb->len is less than 60 for skb_pad.
+	 */
+	pull_len = eth_get_headlen(skb->dev, va, HINIC3_RX_HDR_SIZE);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
+
+	/* update all of the pointers */
+	skb_frag_size_sub(frag, pull_len);
+	skb_frag_off_add(frag, pull_len);
+
+	skb->data_len -= pull_len;
+	skb->tail += pull_len;
+}
+
+static void hinic3_rx_csum(struct hinic3_rxq *rxq, u32 offload_type,
+			   u32 status, struct sk_buff *skb)
+{
+	u32 pkt_fmt = RQ_CQE_OFFOLAD_TYPE_GET(offload_type, TUNNEL_PKT_FORMAT);
+	u32 pkt_type = RQ_CQE_OFFOLAD_TYPE_GET(offload_type, PKT_TYPE);
+	u32 ip_type = RQ_CQE_OFFOLAD_TYPE_GET(offload_type, IP_TYPE);
+	u32 csum_err = RQ_CQE_STATUS_GET(status, CSUM_ERR);
+	struct net_device *netdev = rxq->netdev;
+
+	if (!(netdev->features & NETIF_F_RXCSUM))
+		return;
+
+	if (unlikely(csum_err)) {
+		/* pkt type is recognized by HW, and csum is wrong */
+		skb->ip_summed = CHECKSUM_NONE;
+		return;
+	}
+
+	if (ip_type == HINIC3_RX_INVALID_IP_TYPE ||
+	    !(pkt_fmt == HINIC3_RX_PKT_FORMAT_NON_TUNNEL ||
+	      pkt_fmt == HINIC3_RX_PKT_FORMAT_VXLAN)) {
+		skb->ip_summed = CHECKSUM_NONE;
+		return;
+	}
+
+	switch (pkt_type) {
+	case HINIC3_RX_TCP_PKT:
+	case HINIC3_RX_UDP_PKT:
+	case HINIC3_RX_SCTP_PKT:
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		break;
+	default:
+		skb->ip_summed = CHECKSUM_NONE;
+		break;
+	}
+}
+
+static void hinic3_lro_set_gso_params(struct sk_buff *skb, u16 num_lro)
+{
+	struct ethhdr *eth = (struct ethhdr *)(skb->data);
+	__be16 proto;
+
+	proto = __vlan_get_protocol(skb, eth->h_proto, NULL);
+
+	skb_shinfo(skb)->gso_size = DIV_ROUND_UP(skb->len - skb_headlen(skb),
+						 num_lro);
+	skb_shinfo(skb)->gso_type = proto == htons(ETH_P_IP) ?
+				    SKB_GSO_TCPV4 : SKB_GSO_TCPV6;
+	skb_shinfo(skb)->gso_segs = num_lro;
+}
+
+static int recv_one_pkt(struct hinic3_rxq *rxq, struct hinic3_rq_cqe *rx_cqe,
+			u32 pkt_len, u32 vlan_len, u32 status)
+{
+	struct net_device *netdev = rxq->netdev;
+	struct sk_buff *skb;
+	u32 offload_type;
+	u16 num_lro;
+
+	skb = hinic3_fetch_rx_buffer(rxq, pkt_len);
+	if (unlikely(!skb))
+		return -ENOMEM;
+
+	/* place header in linear portion of buffer */
+	if (skb_is_nonlinear(skb))
+		hinic3_pull_tail(skb);
+
+	offload_type = le32_to_cpu(rx_cqe->offload_type);
+	hinic3_rx_csum(rxq, offload_type, status, skb);
+
+	num_lro = RQ_CQE_STATUS_GET(status, NUM_LRO);
+	if (num_lro)
+		hinic3_lro_set_gso_params(skb, num_lro);
+
+	skb_record_rx_queue(skb, rxq->q_id);
+	skb->protocol = eth_type_trans(skb, netdev);
+
+	if (skb_has_frag_list(skb)) {
+		napi_gro_flush(&rxq->irq_cfg->napi, false);
+		netif_receive_skb(skb);
+	} else {
+		napi_gro_receive(&rxq->irq_cfg->napi, skb);
+	}
+
+	return 0;
+}
+
+int hinic3_alloc_rxqs_res(struct net_device *netdev, u16 num_rq,
+			  u32 rq_depth, struct hinic3_dyna_rxq_res *rxqs_res)
+{
+	u64 cqe_mem_size = sizeof(struct hinic3_rq_cqe) * rq_depth;
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct page_pool_params pp_params = {};
+	struct hinic3_dyna_rxq_res *rqres;
+	u32 pkt_idx;
+	int idx;
+
+	for (idx = 0; idx < num_rq; idx++) {
+		rqres = &rxqs_res[idx];
+		rqres->rx_info = kcalloc(rq_depth, sizeof(*rqres->rx_info),
+					 GFP_KERNEL);
+		if (!rqres->rx_info)
+			goto err_free_rqres;
+
+		rqres->cqe_start_vaddr =
+			dma_alloc_coherent(&nic_dev->pdev->dev, cqe_mem_size,
+					   &rqres->cqe_start_paddr, GFP_KERNEL);
+		if (!rqres->cqe_start_vaddr) {
+			netdev_err(netdev, "Failed to alloc rxq%d rx cqe\n",
+				   idx);
+			goto err_free_rx_info;
+		}
+
+		pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+		pp_params.pool_size = rq_depth * nic_dev->rx_buf_len /
+				      PAGE_SIZE;
+		pp_params.nid = dev_to_node(&nic_dev->pdev->dev);
+		pp_params.dev = &nic_dev->pdev->dev;
+		pp_params.dma_dir = DMA_FROM_DEVICE;
+		pp_params.max_len = PAGE_SIZE;
+		rqres->page_pool = page_pool_create(&pp_params);
+		if (IS_ERR(rqres->page_pool)) {
+			netdev_err(netdev, "Failed to create rxq%d page pool\n",
+				   idx);
+			goto err_free_cqe;
+		}
+
+		pkt_idx = hinic3_alloc_rx_buffers(rqres, rq_depth,
+						  nic_dev->rx_buf_len);
+		if (!pkt_idx) {
+			netdev_err(netdev, "Failed to alloc rxq%d rx buffers\n",
+				   idx);
+			goto err_destroy_page_pool;
+		}
+		rqres->next_to_alloc = pkt_idx;
+	}
+
+	return 0;
+
+err_destroy_page_pool:
+	page_pool_destroy(rqres->page_pool);
+err_free_cqe:
+	dma_free_coherent(&nic_dev->pdev->dev, cqe_mem_size,
+			  rqres->cqe_start_vaddr,
+			  rqres->cqe_start_paddr);
+err_free_rx_info:
+	kfree(rqres->rx_info);
+err_free_rqres:
+	hinic3_free_rxqs_res(netdev, idx, rq_depth, rxqs_res);
+
+	return -ENOMEM;
+}
+
+void hinic3_free_rxqs_res(struct net_device *netdev, u16 num_rq,
+			  u32 rq_depth, struct hinic3_dyna_rxq_res *rxqs_res)
+{
+	u64 cqe_mem_size = sizeof(struct hinic3_rq_cqe) * rq_depth;
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_dyna_rxq_res *rqres;
+	int idx;
+
+	for (idx = 0; idx < num_rq; idx++) {
+		rqres = &rxqs_res[idx];
+
+		hinic3_free_rx_buffers(rqres, rq_depth);
+		page_pool_destroy(rqres->page_pool);
+		dma_free_coherent(&nic_dev->pdev->dev, cqe_mem_size,
+				  rqres->cqe_start_vaddr,
+				  rqres->cqe_start_paddr);
+		kfree(rqres->rx_info);
+	}
+}
+
+int hinic3_configure_rxqs(struct net_device *netdev, u16 num_rq,
+			  u32 rq_depth, struct hinic3_dyna_rxq_res *rxqs_res)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_dyna_rxq_res *rqres;
+	struct msix_entry *msix_entry;
+	struct hinic3_rxq *rxq;
+	u16 q_id;
+	u32 pkts;
+
+	for (q_id = 0; q_id < num_rq; q_id++) {
+		rxq = &nic_dev->rxqs[q_id];
+		rqres = &rxqs_res[q_id];
+		msix_entry = &nic_dev->qps_msix_entries[q_id];
+
+		rxq->irq_id = msix_entry->vector;
+		rxq->msix_entry_idx = msix_entry->entry;
+		rxq->next_to_update = 0;
+		rxq->next_to_alloc = rqres->next_to_alloc;
+		rxq->q_depth = rq_depth;
+		rxq->delta = rxq->q_depth;
+		rxq->q_mask = rxq->q_depth - 1;
+		rxq->cons_idx = 0;
+
+		rxq->cqe_arr = rqres->cqe_start_vaddr;
+		rxq->cqe_start_paddr = rqres->cqe_start_paddr;
+		rxq->rx_info = rqres->rx_info;
+		rxq->page_pool = rqres->page_pool;
+
+		rxq->rq = &nic_dev->nic_io->rq[rxq->q_id];
+
+		rq_associate_cqes(rxq);
+
+		pkts = hinic3_rx_fill_buffers(rxq);
+		if (!pkts) {
+			netdev_err(netdev, "Failed to fill Rx buffer\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+int hinic3_rx_poll(struct hinic3_rxq *rxq, int budget)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(rxq->netdev);
+	u32 sw_ci, status, pkt_len, vlan_len;
+	struct hinic3_rq_cqe *rx_cqe;
+	u32 num_wqe = 0;
+	int nr_pkts = 0;
+	u16 num_lro;
+
+	while (likely(nr_pkts < budget)) {
+		sw_ci = rxq->cons_idx & rxq->q_mask;
+		rx_cqe = rxq->cqe_arr + sw_ci;
+		status = le32_to_cpu(rx_cqe->status);
+		if (!RQ_CQE_STATUS_GET(status, RXDONE))
+			break;
+
+		/* make sure we read rx_done before packet length */
+		rmb();
+
+		vlan_len = le32_to_cpu(rx_cqe->vlan_len);
+		pkt_len = RQ_CQE_SGE_GET(vlan_len, LEN);
+		if (recv_one_pkt(rxq, rx_cqe, pkt_len, vlan_len, status))
+			break;
+
+		nr_pkts++;
+		num_lro = RQ_CQE_STATUS_GET(status, NUM_LRO);
+		if (num_lro)
+			num_wqe += hinic3_get_sge_num(rxq, pkt_len);
+
+		rx_cqe->status = 0;
+
+		if (num_wqe >= nic_dev->lro_replenish_thld)
+			break;
+	}
+
+	if (rxq->delta >= HINIC3_RX_BUFFER_WRITE)
+		hinic3_rx_fill_buffers(rxq);
+
+	return nr_pkts;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_rx.h b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.h
new file mode 100644
index 000000000000..44ae841a3648
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_RX_H_
+#define _HINIC3_RX_H_
+
+#include <linux/bitfield.h>
+#include <linux/netdevice.h>
+
+#define RQ_CQE_OFFOLAD_TYPE_PKT_TYPE_MASK           GENMASK(4, 0)
+#define RQ_CQE_OFFOLAD_TYPE_IP_TYPE_MASK            GENMASK(6, 5)
+#define RQ_CQE_OFFOLAD_TYPE_TUNNEL_PKT_FORMAT_MASK  GENMASK(11, 8)
+#define RQ_CQE_OFFOLAD_TYPE_VLAN_EN_MASK            BIT(21)
+#define RQ_CQE_OFFOLAD_TYPE_GET(val, member) \
+	FIELD_GET(RQ_CQE_OFFOLAD_TYPE_##member##_MASK, val)
+
+#define RQ_CQE_SGE_VLAN_MASK  GENMASK(15, 0)
+#define RQ_CQE_SGE_LEN_MASK   GENMASK(31, 16)
+#define RQ_CQE_SGE_GET(val, member) \
+	FIELD_GET(RQ_CQE_SGE_##member##_MASK, val)
+
+#define RQ_CQE_STATUS_CSUM_ERR_MASK  GENMASK(15, 0)
+#define RQ_CQE_STATUS_NUM_LRO_MASK   GENMASK(23, 16)
+#define RQ_CQE_STATUS_RXDONE_MASK    BIT(31)
+#define RQ_CQE_STATUS_GET(val, member) \
+	FIELD_GET(RQ_CQE_STATUS_##member##_MASK, val)
+
+/* RX Completion information that is provided by HW for a specific RX WQE */
+struct hinic3_rq_cqe {
+	__le32 status;
+	__le32 vlan_len;
+	__le32 offload_type;
+	__le32 rsvd3;
+	__le32 rsvd4;
+	__le32 rsvd5;
+	__le32 rsvd6;
+	__le32 pkt_info;
+};
+
+struct hinic3_rq_wqe {
+	__le32 buf_hi_addr;
+	__le32 buf_lo_addr;
+	__le32 cqe_hi_addr;
+	__le32 cqe_lo_addr;
+};
+
+struct hinic3_rx_info {
+	struct page      *page;
+	u32              page_offset;
+};
+
+struct hinic3_rxq {
+	struct net_device       *netdev;
+
+	u16                     q_id;
+	u32                     q_depth;
+	u32                     q_mask;
+
+	u16                     buf_len;
+	u32                     buf_len_shift;
+
+	u32                     cons_idx;
+	u32                     delta;
+
+	u32                     irq_id;
+	u16                     msix_entry_idx;
+
+	/* cqe_arr and rx_info are arrays of rq_depth elements. Each element is
+	 * statically associated (by index) to a specific rq_wqe.
+	 */
+	struct hinic3_rq_cqe   *cqe_arr;
+	struct hinic3_rx_info  *rx_info;
+	struct page_pool       *page_pool;
+
+	struct hinic3_io_queue *rq;
+
+	struct hinic3_irq_cfg  *irq_cfg;
+	u16                    next_to_alloc;
+	u16                    next_to_update;
+	struct device          *dev; /* device for DMA mapping */
+
+	dma_addr_t             cqe_start_paddr;
+} ____cacheline_aligned;
+
+struct hinic3_dyna_rxq_res {
+	u16                   next_to_alloc;
+	struct hinic3_rx_info *rx_info;
+	dma_addr_t            cqe_start_paddr;
+	void                  *cqe_start_vaddr;
+	struct page_pool      *page_pool;
+};
+
+int hinic3_alloc_rxqs(struct net_device *netdev);
+void hinic3_free_rxqs(struct net_device *netdev);
+
+int hinic3_alloc_rxqs_res(struct net_device *netdev, u16 num_rq,
+			  u32 rq_depth, struct hinic3_dyna_rxq_res *rxqs_res);
+void hinic3_free_rxqs_res(struct net_device *netdev, u16 num_rq,
+			  u32 rq_depth, struct hinic3_dyna_rxq_res *rxqs_res);
+int hinic3_configure_rxqs(struct net_device *netdev, u16 num_rq,
+			  u32 rq_depth, struct hinic3_dyna_rxq_res *rxqs_res);
+int hinic3_rx_poll(struct hinic3_rxq *rxq, int budget);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c
new file mode 100644
index 000000000000..92c43c05e3f2
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c
@@ -0,0 +1,779 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/if_vlan.h>
+#include <linux/iopoll.h>
+#include <net/ip6_checksum.h>
+#include <net/ipv6.h>
+#include <net/netdev_queues.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_tx.h"
+#include "hinic3_wq.h"
+
+#define MIN_SKB_LEN                32
+
+int hinic3_alloc_txqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	u16 q_id, num_txqs = nic_dev->max_qps;
+	struct pci_dev *pdev = nic_dev->pdev;
+	struct hinic3_txq *txq;
+
+	if (!num_txqs) {
+		dev_err(hwdev->dev, "Cannot allocate zero size txqs\n");
+		return -EINVAL;
+	}
+
+	nic_dev->txqs = kcalloc(num_txqs, sizeof(*nic_dev->txqs),  GFP_KERNEL);
+	if (!nic_dev->txqs)
+		return -ENOMEM;
+
+	for (q_id = 0; q_id < num_txqs; q_id++) {
+		txq = &nic_dev->txqs[q_id];
+		txq->netdev = netdev;
+		txq->q_id = q_id;
+		txq->q_depth = nic_dev->q_params.sq_depth;
+		txq->q_mask = nic_dev->q_params.sq_depth - 1;
+		txq->dev = &pdev->dev;
+	}
+
+	return 0;
+}
+
+void hinic3_free_txqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	kfree(nic_dev->txqs);
+}
+
+static void hinic3_set_buf_desc(struct hinic3_sq_bufdesc *buf_descs,
+				dma_addr_t addr, u32 len)
+{
+	buf_descs->hi_addr = cpu_to_le32(upper_32_bits(addr));
+	buf_descs->lo_addr = cpu_to_le32(lower_32_bits(addr));
+	buf_descs->len = cpu_to_le32(len);
+}
+
+static int hinic3_tx_map_skb(struct net_device *netdev, struct sk_buff *skb,
+			     struct hinic3_txq *txq,
+			     struct hinic3_tx_info *tx_info,
+			     struct hinic3_sq_wqe_combo *wqe_combo)
+{
+	struct hinic3_sq_wqe_desc *wqe_desc = wqe_combo->ctrl_bd0;
+	struct hinic3_sq_bufdesc *buf_desc = wqe_combo->bds_head;
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_dma_info *dma_info = tx_info->dma_info;
+	struct pci_dev *pdev = nic_dev->pdev;
+	skb_frag_t *frag;
+	u32 i, idx;
+	int err;
+
+	dma_info[0].dma = dma_map_single(&pdev->dev, skb->data,
+					 skb_headlen(skb), DMA_TO_DEVICE);
+	if (dma_mapping_error(&pdev->dev, dma_info[0].dma))
+		return -EFAULT;
+
+	dma_info[0].len = skb_headlen(skb);
+
+	wqe_desc->hi_addr = cpu_to_le32(upper_32_bits(dma_info[0].dma));
+	wqe_desc->lo_addr = cpu_to_le32(lower_32_bits(dma_info[0].dma));
+
+	wqe_desc->ctrl_len = cpu_to_le32(dma_info[0].len);
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		frag = &(skb_shinfo(skb)->frags[i]);
+		if (unlikely(i == wqe_combo->first_bds_num))
+			buf_desc = wqe_combo->bds_sec2;
+
+		idx = i + 1;
+		dma_info[idx].dma = skb_frag_dma_map(&pdev->dev, frag, 0,
+						     skb_frag_size(frag),
+						     DMA_TO_DEVICE);
+		if (dma_mapping_error(&pdev->dev, dma_info[idx].dma)) {
+			err = -EFAULT;
+			goto err_unmap_page;
+		}
+		dma_info[idx].len = skb_frag_size(frag);
+
+		hinic3_set_buf_desc(buf_desc, dma_info[idx].dma,
+				    dma_info[idx].len);
+		buf_desc++;
+	}
+
+	return 0;
+
+err_unmap_page:
+	while (idx > 1) {
+		idx--;
+		dma_unmap_page(&pdev->dev, dma_info[idx].dma,
+			       dma_info[idx].len, DMA_TO_DEVICE);
+	}
+	dma_unmap_single(&pdev->dev, dma_info[0].dma, dma_info[0].len,
+			 DMA_TO_DEVICE);
+
+	return err;
+}
+
+static void hinic3_tx_unmap_skb(struct net_device *netdev,
+				struct sk_buff *skb,
+				struct hinic3_dma_info *dma_info)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct pci_dev *pdev = nic_dev->pdev;
+	int i;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags;) {
+		i++;
+		dma_unmap_page(&pdev->dev,
+			       dma_info[i].dma,
+			       dma_info[i].len, DMA_TO_DEVICE);
+	}
+
+	dma_unmap_single(&pdev->dev, dma_info[0].dma,
+			 dma_info[0].len, DMA_TO_DEVICE);
+}
+
+static void free_all_tx_skbs(struct net_device *netdev, u32 sq_depth,
+			     struct hinic3_tx_info *tx_info_arr)
+{
+	struct hinic3_tx_info *tx_info;
+	u32 idx;
+
+	for (idx = 0; idx < sq_depth; idx++) {
+		tx_info = &tx_info_arr[idx];
+		if (tx_info->skb) {
+			hinic3_tx_unmap_skb(netdev, tx_info->skb,
+					    tx_info->dma_info);
+			dev_kfree_skb_any(tx_info->skb);
+			tx_info->skb = NULL;
+		}
+	}
+}
+
+union hinic3_ip {
+	struct iphdr   *v4;
+	struct ipv6hdr *v6;
+	unsigned char  *hdr;
+};
+
+union hinic3_l4 {
+	struct tcphdr *tcp;
+	struct udphdr *udp;
+	unsigned char *hdr;
+};
+
+enum hinic3_l3_type {
+	HINIC3_L3_UNKNOWN         = 0,
+	HINIC3_L3_IP6_PKT         = 1,
+	HINIC3_L3_IP4_PKT_NO_CSUM = 2,
+	HINIC3_L3_IP4_PKT_CSUM    = 3,
+};
+
+enum hinic3_l4_offload_type {
+	HINIC3_L4_OFFLOAD_DISABLE = 0,
+	HINIC3_L4_OFFLOAD_TCP     = 1,
+	HINIC3_L4_OFFLOAD_STCP    = 2,
+	HINIC3_L4_OFFLOAD_UDP     = 3,
+};
+
+/* initialize l4 offset and offload */
+static void get_inner_l4_info(struct sk_buff *skb, union hinic3_l4 *l4,
+			      u8 l4_proto, u32 *offset,
+			      enum hinic3_l4_offload_type *l4_offload)
+{
+	switch (l4_proto) {
+	case IPPROTO_TCP:
+		*l4_offload = HINIC3_L4_OFFLOAD_TCP;
+		/* To be same with TSO, payload offset begins from payload */
+		*offset = (l4->tcp->doff << TCP_HDR_DATA_OFF_UNIT_SHIFT) +
+			   TRANSPORT_OFFSET(l4->hdr, skb);
+		break;
+
+	case IPPROTO_UDP:
+		*l4_offload = HINIC3_L4_OFFLOAD_UDP;
+		*offset = TRANSPORT_OFFSET(l4->hdr, skb);
+		break;
+	default:
+		*l4_offload = HINIC3_L4_OFFLOAD_DISABLE;
+		*offset = 0;
+	}
+}
+
+static int hinic3_tx_csum(struct hinic3_txq *txq, struct hinic3_sq_task *task,
+			  struct sk_buff *skb)
+{
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
+	if (skb->encapsulation) {
+		union hinic3_ip ip;
+		u8 l4_proto;
+
+		task->pkt_info0 |= cpu_to_le32(SQ_TASK_INFO0_SET(1,
+								 TUNNEL_FLAG));
+
+		ip.hdr = skb_network_header(skb);
+		if (ip.v4->version == 4) {
+			l4_proto = ip.v4->protocol;
+		} else if (ip.v4->version == 6) {
+			union hinic3_l4 l4;
+			unsigned char *exthdr;
+			__be16 frag_off;
+
+			exthdr = ip.hdr + sizeof(*ip.v6);
+			l4_proto = ip.v6->nexthdr;
+			l4.hdr = skb_transport_header(skb);
+			if (l4.hdr != exthdr)
+				ipv6_skip_exthdr(skb, exthdr - skb->data,
+						 &l4_proto, &frag_off);
+		} else {
+			l4_proto = IPPROTO_RAW;
+		}
+
+		if (l4_proto != IPPROTO_UDP ||
+		    ((struct udphdr *)skb_transport_header(skb))->dest !=
+		    VXLAN_OFFLOAD_PORT_LE) {
+			/* Unsupported tunnel packet, disable csum offload */
+			skb_checksum_help(skb);
+			return 0;
+		}
+	}
+
+	task->pkt_info0 |= cpu_to_le32(SQ_TASK_INFO0_SET(1, INNER_L4_EN));
+
+	return 1;
+}
+
+static void get_inner_l3_l4_type(struct sk_buff *skb, union hinic3_ip *ip,
+				 union hinic3_l4 *l4,
+				 enum hinic3_l3_type *l3_type, u8 *l4_proto)
+{
+	unsigned char *exthdr;
+	__be16 frag_off;
+
+	if (ip->v4->version == 4) {
+		*l3_type = HINIC3_L3_IP4_PKT_CSUM;
+		*l4_proto = ip->v4->protocol;
+	} else if (ip->v4->version == 6) {
+		*l3_type = HINIC3_L3_IP6_PKT;
+		exthdr = ip->hdr + sizeof(*ip->v6);
+		*l4_proto = ip->v6->nexthdr;
+		if (exthdr != l4->hdr) {
+			ipv6_skip_exthdr(skb, exthdr - skb->data,
+					 l4_proto, &frag_off);
+		}
+	} else {
+		*l3_type = HINIC3_L3_UNKNOWN;
+		*l4_proto = 0;
+	}
+}
+
+static void hinic3_set_tso_info(struct hinic3_sq_task *task, __le32 *queue_info,
+				enum hinic3_l4_offload_type l4_offload,
+				u32 offset, u32 mss)
+{
+	if (l4_offload == HINIC3_L4_OFFLOAD_TCP) {
+		*queue_info |= cpu_to_le32(SQ_CTRL_QUEUE_INFO_SET(1, TSO));
+		task->pkt_info0 |= cpu_to_le32(SQ_TASK_INFO0_SET(1,
+								 INNER_L4_EN));
+	} else if (l4_offload == HINIC3_L4_OFFLOAD_UDP) {
+		*queue_info |= cpu_to_le32(SQ_CTRL_QUEUE_INFO_SET(1, UFO));
+		task->pkt_info0 |= cpu_to_le32(SQ_TASK_INFO0_SET(1,
+								 INNER_L4_EN));
+	}
+
+	/* enable L3 calculation */
+	task->pkt_info0 |= cpu_to_le32(SQ_TASK_INFO0_SET(1, INNER_L3_EN));
+
+	*queue_info |= cpu_to_le32(SQ_CTRL_QUEUE_INFO_SET(offset >> 1, PLDOFF));
+
+	/* set MSS value */
+	*queue_info &= cpu_to_le32(~SQ_CTRL_QUEUE_INFO_MSS_MASK);
+	*queue_info |= cpu_to_le32(SQ_CTRL_QUEUE_INFO_SET(mss, MSS));
+}
+
+static __sum16 csum_magic(union hinic3_ip *ip, unsigned short proto)
+{
+	return (ip->v4->version == 4) ?
+		csum_tcpudp_magic(ip->v4->saddr, ip->v4->daddr, 0, proto, 0) :
+		csum_ipv6_magic(&ip->v6->saddr, &ip->v6->daddr, 0, proto, 0);
+}
+
+static int hinic3_tso(struct hinic3_sq_task *task, __le32 *queue_info,
+		      struct sk_buff *skb)
+{
+	enum hinic3_l4_offload_type l4_offload;
+	enum hinic3_l3_type l3_type;
+	union hinic3_ip ip;
+	union hinic3_l4 l4;
+	u8 l4_proto;
+	u32 offset;
+	int err;
+
+	if (!skb_is_gso(skb))
+		return 0;
+
+	err = skb_cow_head(skb, 0);
+	if (err < 0)
+		return err;
+
+	if (skb->encapsulation) {
+		u32 gso_type = skb_shinfo(skb)->gso_type;
+		/* L3 checksum is always enabled */
+		task->pkt_info0 |= cpu_to_le32(SQ_TASK_INFO0_SET(1, OUT_L3_EN));
+		task->pkt_info0 |= cpu_to_le32(SQ_TASK_INFO0_SET(1,
+								 TUNNEL_FLAG));
+
+		l4.hdr = skb_transport_header(skb);
+		ip.hdr = skb_network_header(skb);
+
+		if (gso_type & SKB_GSO_UDP_TUNNEL_CSUM) {
+			l4.udp->check = ~csum_magic(&ip, IPPROTO_UDP);
+			task->pkt_info0 |=
+				cpu_to_le32(SQ_TASK_INFO0_SET(1, OUT_L4_EN));
+		}
+
+		ip.hdr = skb_inner_network_header(skb);
+		l4.hdr = skb_inner_transport_header(skb);
+	} else {
+		ip.hdr = skb_network_header(skb);
+		l4.hdr = skb_transport_header(skb);
+	}
+
+	get_inner_l3_l4_type(skb, &ip, &l4, &l3_type, &l4_proto);
+
+	if (l4_proto == IPPROTO_TCP)
+		l4.tcp->check = ~csum_magic(&ip, IPPROTO_TCP);
+
+	get_inner_l4_info(skb, &l4, l4_proto, &offset, &l4_offload);
+
+	hinic3_set_tso_info(task, queue_info, l4_offload, offset,
+			    skb_shinfo(skb)->gso_size);
+
+	return 1;
+}
+
+static void hinic3_set_vlan_tx_offload(struct hinic3_sq_task *task,
+				       u16 vlan_tag, u8 vlan_tpid)
+{
+	/* vlan_tpid: 0=select TPID0 in IPSU, 1=select TPID1 in IPSU
+	 * 2=select TPID2 in IPSU, 3=select TPID3 in IPSU,
+	 * 4=select TPID4 in IPSU
+	 */
+	task->vlan_offload =
+		cpu_to_le32(SQ_TASK_INFO3_SET(vlan_tag, VLAN_TAG) |
+			    SQ_TASK_INFO3_SET(vlan_tpid, VLAN_TPID) |
+			    SQ_TASK_INFO3_SET(1, VLAN_TAG_VALID));
+}
+
+static u32 hinic3_tx_offload(struct sk_buff *skb, struct hinic3_sq_task *task,
+			     __le32 *queue_info, struct hinic3_txq *txq)
+{
+	u32 offload = 0;
+	int tso_cs_en;
+
+	task->pkt_info0 = 0;
+	task->ip_identify = 0;
+	task->rsvd = 0;
+	task->vlan_offload = 0;
+
+	tso_cs_en = hinic3_tso(task, queue_info, skb);
+	if (tso_cs_en < 0) {
+		offload = HINIC3_TX_OFFLOAD_INVALID;
+		return offload;
+	} else if (tso_cs_en) {
+		offload |= HINIC3_TX_OFFLOAD_TSO;
+	} else {
+		tso_cs_en = hinic3_tx_csum(txq, task, skb);
+		if (tso_cs_en)
+			offload |= HINIC3_TX_OFFLOAD_CSUM;
+	}
+
+#define VLAN_INSERT_MODE_MAX 5
+	if (unlikely(skb_vlan_tag_present(skb))) {
+		/* select vlan insert mode by qid, default 802.1Q Tag type */
+		hinic3_set_vlan_tx_offload(task, skb_vlan_tag_get(skb),
+					   txq->q_id % VLAN_INSERT_MODE_MAX);
+		offload |= HINIC3_TX_OFFLOAD_VLAN;
+	}
+
+	if (unlikely(SQ_CTRL_QUEUE_INFO_GET(*queue_info, PLDOFF) >
+		     SQ_CTRL_MAX_PLDOFF)) {
+		offload = HINIC3_TX_OFFLOAD_INVALID;
+		return offload;
+	}
+
+	return offload;
+}
+
+static u16 hinic3_get_and_update_sq_owner(struct hinic3_io_queue *sq,
+					  u16 curr_pi, u16 wqebb_cnt)
+{
+	u16 owner = sq->owner;
+
+	if (unlikely(curr_pi + wqebb_cnt >= sq->wq.q_depth))
+		sq->owner = !sq->owner;
+
+	return owner;
+}
+
+static u16 hinic3_set_wqe_combo(struct hinic3_txq *txq,
+				struct hinic3_sq_wqe_combo *wqe_combo,
+				u32 offload, u16 num_sge, u16 *curr_pi)
+{
+	struct hinic3_sq_bufdesc *first_part_wqebbs, *second_part_wqebbs;
+	u16 first_part_wqebbs_num, tmp_pi;
+
+	wqe_combo->ctrl_bd0 = hinic3_wq_get_one_wqebb(&txq->sq->wq, curr_pi);
+	if (!offload && num_sge == 1) {
+		wqe_combo->wqe_type = SQ_WQE_COMPACT_TYPE;
+		return hinic3_get_and_update_sq_owner(txq->sq, *curr_pi, 1);
+	}
+
+	wqe_combo->wqe_type = SQ_WQE_EXTENDED_TYPE;
+
+	if (offload) {
+		wqe_combo->task = hinic3_wq_get_one_wqebb(&txq->sq->wq,
+							  &tmp_pi);
+		wqe_combo->task_type = SQ_WQE_TASKSECT_16BYTES;
+	} else {
+		wqe_combo->task_type = SQ_WQE_TASKSECT_46BITS;
+	}
+
+	if (num_sge > 1) {
+		/* first wqebb contain bd0, and bd size is equal to sq wqebb
+		 * size, so we use (num_sge - 1) as wanted weqbb_cnt
+		 */
+		hinic3_wq_get_multi_wqebbs(&txq->sq->wq, num_sge - 1, &tmp_pi,
+					   &first_part_wqebbs,
+					   &second_part_wqebbs,
+					   &first_part_wqebbs_num);
+		wqe_combo->bds_head = first_part_wqebbs;
+		wqe_combo->bds_sec2 = second_part_wqebbs;
+		wqe_combo->first_bds_num = first_part_wqebbs_num;
+	}
+
+	return hinic3_get_and_update_sq_owner(txq->sq, *curr_pi,
+					      num_sge + !!offload);
+}
+
+static void hinic3_prepare_sq_ctrl(struct hinic3_sq_wqe_combo *wqe_combo,
+				   __le32 queue_info, int nr_descs, u16 owner)
+{
+	struct hinic3_sq_wqe_desc *wqe_desc = wqe_combo->ctrl_bd0;
+
+	if (wqe_combo->wqe_type == SQ_WQE_COMPACT_TYPE) {
+		wqe_desc->ctrl_len |=
+			cpu_to_le32(SQ_CTRL_SET(SQ_NORMAL_WQE, DATA_FORMAT) |
+				    SQ_CTRL_SET(wqe_combo->wqe_type, EXTENDED) |
+				    SQ_CTRL_SET(owner, OWNER));
+
+		/* compact wqe queue_info will transfer to chip */
+		wqe_desc->queue_info = 0;
+		return;
+	}
+
+	wqe_desc->ctrl_len |=
+		cpu_to_le32(SQ_CTRL_SET(nr_descs, BUFDESC_NUM) |
+			    SQ_CTRL_SET(wqe_combo->task_type, TASKSECT_LEN) |
+			    SQ_CTRL_SET(SQ_NORMAL_WQE, DATA_FORMAT) |
+			    SQ_CTRL_SET(wqe_combo->wqe_type, EXTENDED) |
+			    SQ_CTRL_SET(owner, OWNER));
+
+	wqe_desc->queue_info = queue_info;
+	wqe_desc->queue_info |= cpu_to_le32(SQ_CTRL_QUEUE_INFO_SET(1, UC));
+
+	if (!SQ_CTRL_QUEUE_INFO_GET(wqe_desc->queue_info, MSS)) {
+		wqe_desc->queue_info |=
+		    cpu_to_le32(SQ_CTRL_QUEUE_INFO_SET(HINIC3_TX_MSS_DEFAULT, MSS));
+	} else if (SQ_CTRL_QUEUE_INFO_GET(wqe_desc->queue_info, MSS) <
+		   HINIC3_TX_MSS_MIN) {
+		/* mss should not be less than 80 */
+		wqe_desc->queue_info &=
+		    cpu_to_le32(~SQ_CTRL_QUEUE_INFO_MSS_MASK);
+		wqe_desc->queue_info |=
+		    cpu_to_le32(SQ_CTRL_QUEUE_INFO_SET(HINIC3_TX_MSS_MIN, MSS));
+	}
+}
+
+static netdev_tx_t hinic3_send_one_skb(struct sk_buff *skb,
+				       struct net_device *netdev,
+				       struct hinic3_txq *txq)
+{
+	struct hinic3_sq_wqe_combo wqe_combo = {};
+	struct hinic3_tx_info *tx_info;
+	struct hinic3_sq_task task;
+	u16 wqebb_cnt, num_sge;
+	__le32 queue_info = 0;
+	u16 saved_wq_prod_idx;
+	u16 owner, pi = 0;
+	u8 saved_sq_owner;
+	u32 offload;
+	int err;
+
+	if (unlikely(skb->len < MIN_SKB_LEN)) {
+		if (skb_pad(skb, MIN_SKB_LEN - skb->len))
+			goto err_out;
+
+		skb->len = MIN_SKB_LEN;
+	}
+
+	num_sge = skb_shinfo(skb)->nr_frags + 1;
+	/* assume normal wqe format + 1 wqebb for task info */
+	wqebb_cnt = num_sge + 1;
+
+	if (unlikely(hinic3_wq_free_wqebbs(&txq->sq->wq) < wqebb_cnt)) {
+		if (likely(wqebb_cnt > txq->tx_stop_thrs))
+			txq->tx_stop_thrs = min(wqebb_cnt, txq->tx_start_thrs);
+
+		netif_subqueue_try_stop(netdev, txq->sq->q_id,
+					hinic3_wq_free_wqebbs(&txq->sq->wq),
+					txq->tx_start_thrs);
+
+		return NETDEV_TX_BUSY;
+	}
+
+	offload = hinic3_tx_offload(skb, &task, &queue_info, txq);
+	if (unlikely(offload == HINIC3_TX_OFFLOAD_INVALID)) {
+		goto err_drop_pkt;
+	} else if (!offload) {
+		wqebb_cnt -= 1;
+		if (unlikely(num_sge == 1 &&
+			     skb->len > HINIC3_COMPACT_WQEE_SKB_MAX_LEN))
+			goto err_drop_pkt;
+	}
+
+	saved_wq_prod_idx = txq->sq->wq.prod_idx;
+	saved_sq_owner = txq->sq->owner;
+
+	owner = hinic3_set_wqe_combo(txq, &wqe_combo, offload, num_sge, &pi);
+	if (offload)
+		*wqe_combo.task = task;
+
+	tx_info = &txq->tx_info[pi];
+	tx_info->skb = skb;
+	tx_info->wqebb_cnt = wqebb_cnt;
+
+	err = hinic3_tx_map_skb(netdev, skb, txq, tx_info, &wqe_combo);
+	if (err) {
+		/* Rollback work queue to reclaim the wqebb we did not use */
+		txq->sq->wq.prod_idx = saved_wq_prod_idx;
+		txq->sq->owner = saved_sq_owner;
+		goto err_drop_pkt;
+	}
+
+	netif_subqueue_sent(netdev, txq->sq->q_id, skb->len);
+	netif_subqueue_maybe_stop(netdev, txq->sq->q_id,
+				  hinic3_wq_free_wqebbs(&txq->sq->wq),
+				  txq->tx_stop_thrs,
+				  txq->tx_start_thrs);
+
+	hinic3_prepare_sq_ctrl(&wqe_combo, queue_info, num_sge, owner);
+	hinic3_write_db(txq->sq, 0, DB_CFLAG_DP_SQ,
+			hinic3_get_sq_local_pi(txq->sq));
+
+	return NETDEV_TX_OK;
+
+err_drop_pkt:
+	dev_kfree_skb_any(skb);
+
+err_out:
+	return NETDEV_TX_OK;
+}
+
+netdev_tx_t hinic3_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	u16 q_id = skb_get_queue_mapping(skb);
+
+	if (unlikely(!netif_carrier_ok(netdev)))
+		goto err_drop_pkt;
+
+	if (unlikely(q_id >= nic_dev->q_params.num_qps))
+		goto err_drop_pkt;
+
+	return hinic3_send_one_skb(skb, netdev, &nic_dev->txqs[q_id]);
+
+err_drop_pkt:
+	dev_kfree_skb_any(skb);
+
+	return NETDEV_TX_OK;
+}
+
+static bool is_hw_complete_sq_process(struct hinic3_io_queue *sq)
+{
+	u16 sw_pi, hw_ci;
+
+	sw_pi = hinic3_get_sq_local_pi(sq);
+	hw_ci = hinic3_get_sq_hw_ci(sq);
+
+	return sw_pi == hw_ci;
+}
+
+#define HINIC3_FLUSH_QUEUE_POLL_SLEEP_US   10000
+#define HINIC3_FLUSH_QUEUE_POLL_TIMEOUT_US 10000000
+static int hinic3_stop_sq(struct hinic3_txq *txq)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(txq->netdev);
+	int err, rc;
+
+	err = read_poll_timeout(hinic3_force_drop_tx_pkt, rc,
+				is_hw_complete_sq_process(txq->sq) || rc,
+				HINIC3_FLUSH_QUEUE_POLL_SLEEP_US,
+				HINIC3_FLUSH_QUEUE_POLL_TIMEOUT_US,
+				true, nic_dev->hwdev);
+	if (rc)
+		return rc;
+	else
+		return err;
+}
+
+/* packet transmission should be stopped before calling this function */
+void hinic3_flush_txqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	u16 qid;
+	int err;
+
+	for (qid = 0; qid < nic_dev->q_params.num_qps; qid++) {
+		err = hinic3_stop_sq(&nic_dev->txqs[qid]);
+		netdev_tx_reset_subqueue(netdev, qid);
+		if (err)
+			netdev_err(netdev, "Failed to stop sq%u\n", qid);
+	}
+}
+
+#define HINIC3_BDS_PER_SQ_WQEBB \
+	(HINIC3_SQ_WQEBB_SIZE / sizeof(struct hinic3_sq_bufdesc))
+
+int hinic3_alloc_txqs_res(struct net_device *netdev, u16 num_sq,
+			  u32 sq_depth, struct hinic3_dyna_txq_res *txqs_res)
+{
+	struct hinic3_dyna_txq_res *tqres;
+	int idx;
+
+	for (idx = 0; idx < num_sq; idx++) {
+		tqres = &txqs_res[idx];
+
+		tqres->tx_info = kcalloc(sq_depth, sizeof(*tqres->tx_info),
+					 GFP_KERNEL);
+		if (!tqres->tx_info)
+			goto err_free_tqres;
+
+		tqres->bds = kcalloc(sq_depth * HINIC3_BDS_PER_SQ_WQEBB +
+				     HINIC3_MAX_SQ_SGE, sizeof(*tqres->bds),
+				     GFP_KERNEL);
+		if (!tqres->bds) {
+			kfree(tqres->tx_info);
+			goto err_free_tqres;
+		}
+	}
+
+	return 0;
+
+err_free_tqres:
+	while (idx > 0) {
+		idx--;
+		tqres = &txqs_res[idx];
+
+		kfree(tqres->bds);
+		kfree(tqres->tx_info);
+	}
+
+	return -ENOMEM;
+}
+
+void hinic3_free_txqs_res(struct net_device *netdev, u16 num_sq,
+			  u32 sq_depth, struct hinic3_dyna_txq_res *txqs_res)
+{
+	struct hinic3_dyna_txq_res *tqres;
+	int idx;
+
+	for (idx = 0; idx < num_sq; idx++) {
+		tqres = &txqs_res[idx];
+
+		free_all_tx_skbs(netdev, sq_depth, tqres->tx_info);
+		kfree(tqres->bds);
+		kfree(tqres->tx_info);
+	}
+}
+
+int hinic3_configure_txqs(struct net_device *netdev, u16 num_sq,
+			  u32 sq_depth, struct hinic3_dyna_txq_res *txqs_res)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_dyna_txq_res *tqres;
+	struct hinic3_txq *txq;
+	u16 q_id;
+	u32 idx;
+
+	for (q_id = 0; q_id < num_sq; q_id++) {
+		txq = &nic_dev->txqs[q_id];
+		tqres = &txqs_res[q_id];
+
+		txq->q_depth = sq_depth;
+		txq->q_mask = sq_depth - 1;
+
+		txq->tx_stop_thrs = min(HINIC3_DEFAULT_STOP_THRS,
+					sq_depth / 20);
+		txq->tx_start_thrs = min(HINIC3_DEFAULT_START_THRS,
+					 sq_depth / 10);
+
+		txq->tx_info = tqres->tx_info;
+		for (idx = 0; idx < sq_depth; idx++)
+			txq->tx_info[idx].dma_info =
+				&tqres->bds[idx * HINIC3_BDS_PER_SQ_WQEBB];
+
+		txq->sq = &nic_dev->nic_io->sq[q_id];
+	}
+
+	return 0;
+}
+
+bool hinic3_tx_poll(struct hinic3_txq *txq, int budget)
+{
+	struct net_device *netdev = txq->netdev;
+	u16 hw_ci, sw_ci, q_id = txq->sq->q_id;
+	struct hinic3_tx_info *tx_info;
+	unsigned int bytes_compl = 0;
+	unsigned int pkts = 0;
+	u16 wqebb_cnt = 0;
+
+	hw_ci = hinic3_get_sq_hw_ci(txq->sq);
+	dma_rmb();
+	sw_ci = hinic3_get_sq_local_ci(txq->sq);
+
+	do {
+		tx_info = &txq->tx_info[sw_ci];
+
+		/* Did all wqebb of this wqe complete? */
+		if (hw_ci == sw_ci ||
+		    ((hw_ci - sw_ci) & txq->q_mask) < tx_info->wqebb_cnt)
+			break;
+
+		sw_ci = (sw_ci + tx_info->wqebb_cnt) & txq->q_mask;
+		net_prefetch(&txq->tx_info[sw_ci]);
+
+		wqebb_cnt += tx_info->wqebb_cnt;
+		bytes_compl += tx_info->skb->len;
+		pkts++;
+
+		hinic3_tx_unmap_skb(netdev, tx_info->skb, tx_info->dma_info);
+		napi_consume_skb(tx_info->skb, budget);
+		tx_info->skb = NULL;
+	} while (likely(pkts < HINIC3_TX_POLL_WEIGHT));
+
+	hinic3_wq_put_wqebbs(&txq->sq->wq, wqebb_cnt);
+
+	netif_subqueue_completed_wake(netdev, q_id, pkts, bytes_compl,
+				      hinic3_wq_free_wqebbs(&txq->sq->wq),
+				      txq->tx_start_thrs);
+
+	return pkts == HINIC3_TX_POLL_WEIGHT;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_tx.h b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.h
new file mode 100644
index 000000000000..7e1b872ba752
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.h
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_TX_H_
+#define _HINIC3_TX_H_
+
+#include <linux/bitops.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/netdevice.h>
+#include <net/checksum.h>
+
+#define VXLAN_OFFLOAD_PORT_LE            cpu_to_be16(4789)
+#define TCP_HDR_DATA_OFF_UNIT_SHIFT      2
+#define TRANSPORT_OFFSET(l4_hdr, skb)    ((l4_hdr) - (skb)->data)
+
+#define HINIC3_COMPACT_WQEE_SKB_MAX_LEN  16383
+#define HINIC3_TX_POLL_WEIGHT		 64
+#define HINIC3_DEFAULT_STOP_THRS	 6
+#define HINIC3_DEFAULT_START_THRS	 24
+
+enum sq_wqe_data_format {
+	SQ_NORMAL_WQE = 0,
+};
+
+enum sq_wqe_ec_type {
+	SQ_WQE_COMPACT_TYPE  = 0,
+	SQ_WQE_EXTENDED_TYPE = 1,
+};
+
+enum sq_wqe_tasksect_len_type {
+	SQ_WQE_TASKSECT_46BITS  = 0,
+	SQ_WQE_TASKSECT_16BYTES = 1,
+};
+
+enum hinic3_tx_offload_type {
+	HINIC3_TX_OFFLOAD_TSO     = BIT(0),
+	HINIC3_TX_OFFLOAD_CSUM    = BIT(1),
+	HINIC3_TX_OFFLOAD_VLAN    = BIT(2),
+	HINIC3_TX_OFFLOAD_INVALID = BIT(3),
+	HINIC3_TX_OFFLOAD_ESP     = BIT(4),
+};
+
+#define SQ_CTRL_BUFDESC_NUM_MASK   GENMASK(26, 19)
+#define SQ_CTRL_TASKSECT_LEN_MASK  BIT(27)
+#define SQ_CTRL_DATA_FORMAT_MASK   BIT(28)
+#define SQ_CTRL_EXTENDED_MASK      BIT(30)
+#define SQ_CTRL_OWNER_MASK         BIT(31)
+#define SQ_CTRL_SET(val, member) \
+	FIELD_PREP(SQ_CTRL_##member##_MASK, val)
+
+#define SQ_CTRL_QUEUE_INFO_PLDOFF_MASK  GENMASK(9, 2)
+#define SQ_CTRL_QUEUE_INFO_UFO_MASK     BIT(10)
+#define SQ_CTRL_QUEUE_INFO_TSO_MASK     BIT(11)
+#define SQ_CTRL_QUEUE_INFO_MSS_MASK     GENMASK(26, 13)
+#define SQ_CTRL_QUEUE_INFO_UC_MASK      BIT(28)
+
+#define SQ_CTRL_QUEUE_INFO_SET(val, member) \
+	FIELD_PREP(SQ_CTRL_QUEUE_INFO_##member##_MASK, val)
+#define SQ_CTRL_QUEUE_INFO_GET(val, member) \
+	FIELD_GET(SQ_CTRL_QUEUE_INFO_##member##_MASK, le32_to_cpu(val))
+
+#define SQ_CTRL_MAX_PLDOFF  221
+
+#define SQ_TASK_INFO0_TUNNEL_FLAG_MASK  BIT(19)
+#define SQ_TASK_INFO0_INNER_L4_EN_MASK  BIT(24)
+#define SQ_TASK_INFO0_INNER_L3_EN_MASK  BIT(25)
+#define SQ_TASK_INFO0_OUT_L4_EN_MASK    BIT(27)
+#define SQ_TASK_INFO0_OUT_L3_EN_MASK    BIT(28)
+#define SQ_TASK_INFO0_SET(val, member) \
+	FIELD_PREP(SQ_TASK_INFO0_##member##_MASK, val)
+
+#define SQ_TASK_INFO3_VLAN_TAG_MASK        GENMASK(15, 0)
+#define SQ_TASK_INFO3_VLAN_TPID_MASK       GENMASK(18, 16)
+#define SQ_TASK_INFO3_VLAN_TAG_VALID_MASK  BIT(19)
+#define SQ_TASK_INFO3_SET(val, member) \
+	FIELD_PREP(SQ_TASK_INFO3_##member##_MASK, val)
+
+struct hinic3_sq_wqe_desc {
+	__le32 ctrl_len;
+	__le32 queue_info;
+	__le32 hi_addr;
+	__le32 lo_addr;
+};
+
+struct hinic3_sq_task {
+	__le32 pkt_info0;
+	__le32 ip_identify;
+	__le32 rsvd;
+	__le32 vlan_offload;
+};
+
+struct hinic3_sq_wqe_combo {
+	struct hinic3_sq_wqe_desc *ctrl_bd0;
+	struct hinic3_sq_task     *task;
+	struct hinic3_sq_bufdesc  *bds_head;
+	struct hinic3_sq_bufdesc  *bds_sec2;
+	u16                       first_bds_num;
+	u32                       wqe_type;
+	u32                       task_type;
+};
+
+struct hinic3_dma_info {
+	dma_addr_t dma;
+	u32        len;
+};
+
+struct hinic3_tx_info {
+	struct sk_buff         *skb;
+	u16                    wqebb_cnt;
+	struct hinic3_dma_info *dma_info;
+};
+
+struct hinic3_txq {
+	struct net_device       *netdev;
+	struct device           *dev;
+
+	u16                     q_id;
+	u16                     tx_stop_thrs;
+	u16                     tx_start_thrs;
+	u32                     q_mask;
+	u32                     q_depth;
+
+	struct hinic3_tx_info   *tx_info;
+	struct hinic3_io_queue  *sq;
+} ____cacheline_aligned;
+
+struct hinic3_dyna_txq_res {
+	struct hinic3_tx_info  *tx_info;
+	struct hinic3_dma_info *bds;
+};
+
+int hinic3_alloc_txqs(struct net_device *netdev);
+void hinic3_free_txqs(struct net_device *netdev);
+
+int hinic3_alloc_txqs_res(struct net_device *netdev, u16 num_sq,
+			  u32 sq_depth, struct hinic3_dyna_txq_res *txqs_res);
+void hinic3_free_txqs_res(struct net_device *netdev, u16 num_sq,
+			  u32 sq_depth, struct hinic3_dyna_txq_res *txqs_res);
+int hinic3_configure_txqs(struct net_device *netdev, u16 num_sq,
+			  u32 sq_depth, struct hinic3_dyna_txq_res *txqs_res);
+
+netdev_tx_t hinic3_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
+bool hinic3_tx_poll(struct hinic3_txq *txq, int budget);
+void hinic3_flush_txqs(struct net_device *netdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_wq.c b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.c
new file mode 100644
index 000000000000..bc3ffdc25cf6
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/dma-mapping.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_wq.h"
+
+#define WQ_MIN_DEPTH            64
+#define WQ_MAX_DEPTH            65536
+#define WQ_PAGE_ADDR_SIZE       sizeof(u64)
+#define WQ_MAX_NUM_PAGES        (HINIC3_MIN_PAGE_SIZE / WQ_PAGE_ADDR_SIZE)
+
+static int wq_init_wq_block(struct hinic3_hwdev *hwdev, struct hinic3_wq *wq)
+{
+	struct hinic3_queue_pages *qpages = &wq->qpages;
+	int i;
+
+	if (hinic3_wq_is_0_level_cla(wq)) {
+		wq->wq_block_paddr = qpages->pages[0].align_paddr;
+		wq->wq_block_vaddr = qpages->pages[0].align_vaddr;
+
+		return 0;
+	}
+
+	if (wq->qpages.num_pages > WQ_MAX_NUM_PAGES) {
+		dev_err(hwdev->dev, "wq num_pages exceed limit: %lu\n",
+			WQ_MAX_NUM_PAGES);
+		return -EFAULT;
+	}
+
+	wq->wq_block_vaddr = dma_alloc_coherent(hwdev->dev,
+						HINIC3_MIN_PAGE_SIZE,
+						&wq->wq_block_paddr,
+						GFP_KERNEL);
+	if (!wq->wq_block_vaddr)
+		return -ENOMEM;
+
+	for (i = 0; i < qpages->num_pages; i++)
+		wq->wq_block_vaddr[i] = cpu_to_be64(qpages->pages[i].align_paddr);
+
+	return 0;
+}
+
+static int wq_alloc_pages(struct hinic3_hwdev *hwdev, struct hinic3_wq *wq)
+{
+	int err;
+
+	err = hinic3_queue_pages_alloc(hwdev, &wq->qpages, 0);
+	if (err)
+		return err;
+
+	err = wq_init_wq_block(hwdev, wq);
+	if (err) {
+		hinic3_queue_pages_free(hwdev, &wq->qpages);
+		return err;
+	}
+
+	return 0;
+}
+
+static void wq_free_pages(struct hinic3_hwdev *hwdev, struct hinic3_wq *wq)
+{
+	if (!hinic3_wq_is_0_level_cla(wq))
+		dma_free_coherent(hwdev->dev,
+				  HINIC3_MIN_PAGE_SIZE,
+				  wq->wq_block_vaddr,
+				  wq->wq_block_paddr);
+
+	hinic3_queue_pages_free(hwdev, &wq->qpages);
+}
+
+int hinic3_wq_create(struct hinic3_hwdev *hwdev, struct hinic3_wq *wq,
+		     u32 q_depth, u16 wqebb_size)
+{
+	u32 wq_page_size;
+
+	if (q_depth < WQ_MIN_DEPTH || q_depth > WQ_MAX_DEPTH ||
+	    !is_power_of_2(q_depth) || !is_power_of_2(wqebb_size)) {
+		dev_err(hwdev->dev, "Invalid WQ: q_depth %u, wqebb_size %u\n",
+			q_depth, wqebb_size);
+		return -EINVAL;
+	}
+
+	wq_page_size = ALIGN(hwdev->wq_page_size, HINIC3_MIN_PAGE_SIZE);
+
+	memset(wq, 0, sizeof(*wq));
+	wq->q_depth = q_depth;
+	wq->idx_mask = q_depth - 1;
+
+	hinic3_queue_pages_init(&wq->qpages, q_depth, wq_page_size, wqebb_size);
+
+	return wq_alloc_pages(hwdev, wq);
+}
+
+void hinic3_wq_destroy(struct hinic3_hwdev *hwdev, struct hinic3_wq *wq)
+{
+	wq_free_pages(hwdev, wq);
+}
+
+void hinic3_wq_reset(struct hinic3_wq *wq)
+{
+	struct hinic3_queue_pages *qpages = &wq->qpages;
+	u16 pg_idx;
+
+	wq->cons_idx = 0;
+	wq->prod_idx = 0;
+
+	for (pg_idx = 0; pg_idx < qpages->num_pages; pg_idx++)
+		memset(qpages->pages[pg_idx].align_vaddr, 0, qpages->page_size);
+}
+
+void hinic3_wq_get_multi_wqebbs(struct hinic3_wq *wq,
+				u16 num_wqebbs, u16 *prod_idx,
+				struct hinic3_sq_bufdesc **first_part_wqebbs,
+				struct hinic3_sq_bufdesc **second_part_wqebbs,
+				u16 *first_part_wqebbs_num)
+{
+	u32 idx, remaining;
+
+	idx = wq->prod_idx & wq->idx_mask;
+	wq->prod_idx += num_wqebbs;
+	*prod_idx = idx;
+	*first_part_wqebbs = get_q_element(&wq->qpages, idx, &remaining);
+	if (likely(remaining >= num_wqebbs)) {
+		*first_part_wqebbs_num = num_wqebbs;
+		*second_part_wqebbs = NULL;
+	} else {
+		*first_part_wqebbs_num = remaining;
+		idx += remaining;
+		*second_part_wqebbs = get_q_element(&wq->qpages, idx, NULL);
+	}
+}
+
+bool hinic3_wq_is_0_level_cla(const struct hinic3_wq *wq)
+{
+	return wq->qpages.num_pages == 1;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_wq.h b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.h
new file mode 100644
index 000000000000..9b3f012bec80
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_WQ_H_
+#define _HINIC3_WQ_H_
+
+#include <linux/io.h>
+
+#include "hinic3_queue_common.h"
+
+struct hinic3_sq_bufdesc {
+	/* 31-bits Length, L2NIC only uses length[17:0] */
+	__le32 len;
+	__le32 rsvd;
+	__le32 hi_addr;
+	__le32 lo_addr;
+};
+
+/* Work queue is used to submit elements (tx, rx, cmd) to hw.
+ * Driver is the producer that advances prod_idx. cons_idx is advanced when
+ * HW reports completions of previously submitted elements.
+ */
+struct hinic3_wq {
+	struct hinic3_queue_pages qpages;
+	/* Unmasked producer/consumer indices that are advanced to natural
+	 * integer overflow regardless of queue depth.
+	 */
+	u16                       cons_idx;
+	u16                       prod_idx;
+
+	u32                       q_depth;
+	u16                       idx_mask;
+
+	/* Work Queue (logical WQEBB array) is mapped to hw via Chip Logical
+	 * Address (CLA) using 1 of 2 levels:
+	 *     level 0 - direct mapping of single wq page
+	 *     level 1 - indirect mapping of multiple pages via additional page
+	 *               table.
+	 * When wq uses level 1, wq_block will hold the allocated indirection
+	 * table.
+	 */
+	dma_addr_t                wq_block_paddr;
+	__be64                    *wq_block_vaddr;
+} ____cacheline_aligned;
+
+/* Get number of elements in work queue that are in-use. */
+static inline u16 hinic3_wq_get_used(const struct hinic3_wq *wq)
+{
+	return READ_ONCE(wq->prod_idx) - READ_ONCE(wq->cons_idx);
+}
+
+static inline u16 hinic3_wq_free_wqebbs(struct hinic3_wq *wq)
+{
+	/* Don't allow queue to become completely full, report (free - 1). */
+	return wq->q_depth - hinic3_wq_get_used(wq) - 1;
+}
+
+static inline void *hinic3_wq_get_one_wqebb(struct hinic3_wq *wq, u16 *pi)
+{
+	*pi = wq->prod_idx & wq->idx_mask;
+	wq->prod_idx++;
+
+	return get_q_element(&wq->qpages, *pi, NULL);
+}
+
+static inline void hinic3_wq_put_wqebbs(struct hinic3_wq *wq, u16 num_wqebbs)
+{
+	wq->cons_idx += num_wqebbs;
+}
+
+static inline u64 hinic3_wq_get_first_wqe_page_addr(const struct hinic3_wq *wq)
+{
+	return wq->qpages.pages[0].align_paddr;
+}
+
+int hinic3_wq_create(struct hinic3_hwdev *hwdev, struct hinic3_wq *wq,
+		     u32 q_depth, u16 wqebb_size);
+void hinic3_wq_destroy(struct hinic3_hwdev *hwdev, struct hinic3_wq *wq);
+void hinic3_wq_reset(struct hinic3_wq *wq);
+void hinic3_wq_get_multi_wqebbs(struct hinic3_wq *wq,
+				u16 num_wqebbs, u16 *prod_idx,
+				struct hinic3_sq_bufdesc **first_part_wqebbs,
+				struct hinic3_sq_bufdesc **second_part_wqebbs,
+				u16 *first_part_wqebbs_num);
+bool hinic3_wq_is_0_level_cla(const struct hinic3_wq *wq);
+
+#endif
diff --git a/drivers/net/ethernet/ibm/Kconfig b/drivers/net/ethernet/ibm/Kconfig
index c0c112d95b89..4f4b23465c47 100644
--- a/drivers/net/ethernet/ibm/Kconfig
+++ b/drivers/net/ethernet/ibm/Kconfig
@@ -27,6 +27,19 @@ config IBMVETH
 	  To compile this driver as a module, choose M here. The module will
 	  be called ibmveth.
 
+config IBMVETH_KUNIT_TEST
+	bool "KUnit test for IBM LAN Virtual Ethernet support" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	depends on KUNIT=y && IBMVETH=y
+	default KUNIT_ALL_TESTS
+	help
+	  This builds unit tests for the IBM LAN Virtual Ethernet driver.
+
+	  For more information on KUnit and unit tests in general, please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
 source "drivers/net/ethernet/ibm/emac/Kconfig"
 
 config EHEA
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 25b8a3556004..417dfa18daae 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2554,17 +2554,12 @@ static int emac_dt_mdio_probe(struct emac_instance *dev)
 	struct mii_bus *bus;
 	int res;
 
-	mii_np = of_get_child_by_name(dev->ofdev->dev.of_node, "mdio");
+	mii_np = of_get_available_child_by_name(dev->ofdev->dev.of_node, "mdio");
 	if (!mii_np) {
 		dev_err(&dev->ofdev->dev, "no mdio definition found.");
 		return -ENODEV;
 	}
 
-	if (!of_device_is_available(mii_np)) {
-		res = -ENODEV;
-		goto put_node;
-	}
-
 	bus = devm_mdiobus_alloc(&dev->ofdev->dev);
 	if (!bus) {
 		res = -ENOMEM;
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index b619a3ec245b..6f0821f1e798 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -39,8 +39,6 @@
 #include "ibmveth.h"
 
 static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance);
-static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter,
-				       bool reuse);
 static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev);
 
 static struct kobj_type ktype_veth_pool;
@@ -213,94 +211,169 @@ static inline void ibmveth_flush_buffer(void *addr, unsigned long length)
 static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter,
 					  struct ibmveth_buff_pool *pool)
 {
-	u32 i;
-	u32 count = pool->size - atomic_read(&pool->available);
-	u32 buffers_added = 0;
-	struct sk_buff *skb;
-	unsigned int free_index, index;
-	u64 correlator;
+	union ibmveth_buf_desc descs[IBMVETH_MAX_RX_PER_HCALL] = {0};
+	u32 remaining = pool->size - atomic_read(&pool->available);
+	u64 correlators[IBMVETH_MAX_RX_PER_HCALL] = {0};
 	unsigned long lpar_rc;
+	u32 buffers_added = 0;
+	u32 i, filled, batch;
+	struct vio_dev *vdev;
 	dma_addr_t dma_addr;
+	struct device *dev;
+	u32 index;
+
+	vdev = adapter->vdev;
+	dev = &vdev->dev;
 
 	mb();
 
-	for (i = 0; i < count; ++i) {
-		union ibmveth_buf_desc desc;
+	batch = adapter->rx_buffers_per_hcall;
+
+	while (remaining > 0) {
+		unsigned int free_index = pool->consumer_index;
+
+		/* Fill a batch of descriptors */
+		for (filled = 0; filled < min(remaining, batch); filled++) {
+			index = pool->free_map[free_index];
+			if (WARN_ON(index == IBM_VETH_INVALID_MAP)) {
+				adapter->replenish_add_buff_failure++;
+				netdev_info(adapter->netdev,
+					    "Invalid map index %u, reset\n",
+					    index);
+				schedule_work(&adapter->work);
+				break;
+			}
 
-		free_index = pool->consumer_index;
-		index = pool->free_map[free_index];
-		skb = NULL;
+			if (!pool->skbuff[index]) {
+				struct sk_buff *skb = NULL;
 
-		BUG_ON(index == IBM_VETH_INVALID_MAP);
+				skb = netdev_alloc_skb(adapter->netdev,
+						       pool->buff_size);
+				if (!skb) {
+					adapter->replenish_no_mem++;
+					adapter->replenish_add_buff_failure++;
+					break;
+				}
 
-		/* are we allocating a new buffer or recycling an old one */
-		if (pool->skbuff[index])
-			goto reuse;
+				dma_addr = dma_map_single(dev, skb->data,
+							  pool->buff_size,
+							  DMA_FROM_DEVICE);
+				if (dma_mapping_error(dev, dma_addr)) {
+					dev_kfree_skb_any(skb);
+					adapter->replenish_add_buff_failure++;
+					break;
+				}
 
-		skb = netdev_alloc_skb(adapter->netdev, pool->buff_size);
+				pool->dma_addr[index] = dma_addr;
+				pool->skbuff[index] = skb;
+			} else {
+				/* re-use case */
+				dma_addr = pool->dma_addr[index];
+			}
 
-		if (!skb) {
-			netdev_dbg(adapter->netdev,
-				   "replenish: unable to allocate skb\n");
-			adapter->replenish_no_mem++;
-			break;
-		}
+			if (rx_flush) {
+				unsigned int len;
 
-		dma_addr = dma_map_single(&adapter->vdev->dev, skb->data,
-				pool->buff_size, DMA_FROM_DEVICE);
+				len = adapter->netdev->mtu + IBMVETH_BUFF_OH;
+				len = min(pool->buff_size, len);
+				ibmveth_flush_buffer(pool->skbuff[index]->data,
+						     len);
+			}
 
-		if (dma_mapping_error(&adapter->vdev->dev, dma_addr))
-			goto failure;
+			descs[filled].fields.flags_len = IBMVETH_BUF_VALID |
+							  pool->buff_size;
+			descs[filled].fields.address = dma_addr;
 
-		pool->dma_addr[index] = dma_addr;
-		pool->skbuff[index] = skb;
+			correlators[filled] = ((u64)pool->index << 32) | index;
+			*(u64 *)pool->skbuff[index]->data = correlators[filled];
 
-		if (rx_flush) {
-			unsigned int len = min(pool->buff_size,
-					       adapter->netdev->mtu +
-					       IBMVETH_BUFF_OH);
-			ibmveth_flush_buffer(skb->data, len);
+			free_index++;
+			if (free_index >= pool->size)
+				free_index = 0;
 		}
-reuse:
-		dma_addr = pool->dma_addr[index];
-		desc.fields.flags_len = IBMVETH_BUF_VALID | pool->buff_size;
-		desc.fields.address = dma_addr;
-
-		correlator = ((u64)pool->index << 32) | index;
-		*(u64 *)pool->skbuff[index]->data = correlator;
 
-		lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address,
-						   desc.desc);
+		if (!filled)
+			break;
 
+		/* single buffer case*/
+		if (filled == 1)
+			lpar_rc = h_add_logical_lan_buffer(vdev->unit_address,
+							   descs[0].desc);
+		else
+			/* Multi-buffer hcall */
+			lpar_rc = h_add_logical_lan_buffers(vdev->unit_address,
+							    descs[0].desc,
+							    descs[1].desc,
+							    descs[2].desc,
+							    descs[3].desc,
+							    descs[4].desc,
+							    descs[5].desc,
+							    descs[6].desc,
+							    descs[7].desc);
 		if (lpar_rc != H_SUCCESS) {
-			netdev_warn(adapter->netdev,
-				    "%sadd_logical_lan failed %lu\n",
-				    skb ? "" : "When recycling: ", lpar_rc);
-			goto failure;
+			dev_warn_ratelimited(dev,
+					     "RX h_add_logical_lan failed: filled=%u, rc=%lu, batch=%u\n",
+					     filled, lpar_rc, batch);
+			goto hcall_failure;
 		}
 
-		pool->free_map[free_index] = IBM_VETH_INVALID_MAP;
-		pool->consumer_index++;
-		if (pool->consumer_index >= pool->size)
-			pool->consumer_index = 0;
+		/* Only update pool state after hcall succeeds */
+		for (i = 0; i < filled; i++) {
+			free_index = pool->consumer_index;
+			pool->free_map[free_index] = IBM_VETH_INVALID_MAP;
 
-		buffers_added++;
-		adapter->replenish_add_buff_success++;
-	}
+			pool->consumer_index++;
+			if (pool->consumer_index >= pool->size)
+				pool->consumer_index = 0;
+		}
 
-	mb();
-	atomic_add(buffers_added, &(pool->available));
-	return;
+		buffers_added += filled;
+		adapter->replenish_add_buff_success += filled;
+		remaining -= filled;
 
-failure:
+		memset(&descs, 0, sizeof(descs));
+		memset(&correlators, 0, sizeof(correlators));
+		continue;
 
-	if (dma_addr && !dma_mapping_error(&adapter->vdev->dev, dma_addr))
-		dma_unmap_single(&adapter->vdev->dev,
-		                 pool->dma_addr[index], pool->buff_size,
-		                 DMA_FROM_DEVICE);
-	dev_kfree_skb_any(pool->skbuff[index]);
-	pool->skbuff[index] = NULL;
-	adapter->replenish_add_buff_failure++;
+hcall_failure:
+		for (i = 0; i < filled; i++) {
+			index = correlators[i] & 0xffffffffUL;
+			dma_addr =  pool->dma_addr[index];
+
+			if (pool->skbuff[index]) {
+				if (dma_addr &&
+				    !dma_mapping_error(dev, dma_addr))
+					dma_unmap_single(dev, dma_addr,
+							 pool->buff_size,
+							 DMA_FROM_DEVICE);
+
+				dev_kfree_skb_any(pool->skbuff[index]);
+				pool->skbuff[index] = NULL;
+			}
+		}
+		adapter->replenish_add_buff_failure += filled;
+
+		/*
+		 * If multi rx buffers hcall is no longer supported by FW
+		 * e.g. in the case of Live Parttion Migration
+		 */
+		if (batch > 1 && lpar_rc == H_FUNCTION) {
+			/*
+			 * Instead of retry submit single buffer individually
+			 * here just set the max rx buffer per hcall to 1
+			 * buffers will be respleshed next time
+			 * when ibmveth_replenish_buffer_pool() is called again
+			 * with single-buffer case
+			 */
+			netdev_info(adapter->netdev,
+				    "RX Multi buffers not supported by FW, rc=%lu\n",
+				    lpar_rc);
+			adapter->rx_buffers_per_hcall = 1;
+			netdev_info(adapter->netdev,
+				    "Next rx replesh will fall back to single-buffer hcall\n");
+		}
+		break;
+	}
 
 	mb();
 	atomic_add(buffers_added, &(pool->available));
@@ -370,20 +443,36 @@ static void ibmveth_free_buffer_pool(struct ibmveth_adapter *adapter,
 	}
 }
 
-/* remove a buffer from a pool */
-static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
-					    u64 correlator, bool reuse)
+/**
+ * ibmveth_remove_buffer_from_pool - remove a buffer from a pool
+ * @adapter: adapter instance
+ * @correlator: identifies pool and index
+ * @reuse: whether to reuse buffer
+ *
+ * Return:
+ * * %0       - success
+ * * %-EINVAL - correlator maps to pool or index out of range
+ * * %-EFAULT - pool and index map to null skb
+ */
+static int ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
+					   u64 correlator, bool reuse)
 {
 	unsigned int pool  = correlator >> 32;
 	unsigned int index = correlator & 0xffffffffUL;
 	unsigned int free_index;
 	struct sk_buff *skb;
 
-	BUG_ON(pool >= IBMVETH_NUM_BUFF_POOLS);
-	BUG_ON(index >= adapter->rx_buff_pool[pool].size);
+	if (WARN_ON(pool >= IBMVETH_NUM_BUFF_POOLS) ||
+	    WARN_ON(index >= adapter->rx_buff_pool[pool].size)) {
+		schedule_work(&adapter->work);
+		return -EINVAL;
+	}
 
 	skb = adapter->rx_buff_pool[pool].skbuff[index];
-	BUG_ON(skb == NULL);
+	if (WARN_ON(!skb)) {
+		schedule_work(&adapter->work);
+		return -EFAULT;
+	}
 
 	/* if we are going to reuse the buffer then keep the pointers around
 	 * but mark index as available. replenish will see the skb pointer and
@@ -411,6 +500,8 @@ static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
 	mb();
 
 	atomic_dec(&(adapter->rx_buff_pool[pool].available));
+
+	return 0;
 }
 
 /* get the current buffer on the rx queue */
@@ -420,24 +511,44 @@ static inline struct sk_buff *ibmveth_rxq_get_buffer(struct ibmveth_adapter *ada
 	unsigned int pool = correlator >> 32;
 	unsigned int index = correlator & 0xffffffffUL;
 
-	BUG_ON(pool >= IBMVETH_NUM_BUFF_POOLS);
-	BUG_ON(index >= adapter->rx_buff_pool[pool].size);
+	if (WARN_ON(pool >= IBMVETH_NUM_BUFF_POOLS) ||
+	    WARN_ON(index >= adapter->rx_buff_pool[pool].size)) {
+		schedule_work(&adapter->work);
+		return NULL;
+	}
 
 	return adapter->rx_buff_pool[pool].skbuff[index];
 }
 
-static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter,
-				       bool reuse)
+/**
+ * ibmveth_rxq_harvest_buffer - Harvest buffer from pool
+ *
+ * @adapter: pointer to adapter
+ * @reuse:   whether to reuse buffer
+ *
+ * Context: called from ibmveth_poll
+ *
+ * Return:
+ * * %0    - success
+ * * other - non-zero return from ibmveth_remove_buffer_from_pool
+ */
+static int ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter,
+				      bool reuse)
 {
 	u64 cor;
+	int rc;
 
 	cor = adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator;
-	ibmveth_remove_buffer_from_pool(adapter, cor, reuse);
+	rc = ibmveth_remove_buffer_from_pool(adapter, cor, reuse);
+	if (unlikely(rc))
+		return rc;
 
 	if (++adapter->rx_queue.index == adapter->rx_queue.num_slots) {
 		adapter->rx_queue.index = 0;
 		adapter->rx_queue.toggle = !adapter->rx_queue.toggle;
 	}
+
+	return 0;
 }
 
 static void ibmveth_free_tx_ltb(struct ibmveth_adapter *adapter, int idx)
@@ -709,6 +820,35 @@ static int ibmveth_close(struct net_device *netdev)
 	return 0;
 }
 
+/**
+ * ibmveth_reset - Handle scheduled reset work
+ *
+ * @w: pointer to work_struct embedded in adapter structure
+ *
+ * Context: This routine acquires rtnl_mutex and disables its NAPI through
+ *          ibmveth_close. It can't be called directly in a context that has
+ *          already acquired rtnl_mutex or disabled its NAPI, or directly from
+ *          a poll routine.
+ *
+ * Return: void
+ */
+static void ibmveth_reset(struct work_struct *w)
+{
+	struct ibmveth_adapter *adapter = container_of(w, struct ibmveth_adapter, work);
+	struct net_device *netdev = adapter->netdev;
+
+	netdev_dbg(netdev, "reset starting\n");
+
+	rtnl_lock();
+
+	dev_close(adapter->netdev);
+	dev_open(adapter->netdev, NULL);
+
+	rtnl_unlock();
+
+	netdev_dbg(netdev, "reset complete\n");
+}
+
 static int ibmveth_set_link_ksettings(struct net_device *dev,
 				      const struct ethtool_link_ksettings *cmd)
 {
@@ -1324,7 +1464,8 @@ restart_poll:
 			wmb(); /* suggested by larson1 */
 			adapter->rx_invalid_buffer++;
 			netdev_dbg(netdev, "recycling invalid buffer\n");
-			ibmveth_rxq_harvest_buffer(adapter, true);
+			if (unlikely(ibmveth_rxq_harvest_buffer(adapter, true)))
+				break;
 		} else {
 			struct sk_buff *skb, *new_skb;
 			int length = ibmveth_rxq_frame_length(adapter);
@@ -1334,6 +1475,8 @@ restart_poll:
 			__sum16 iph_check = 0;
 
 			skb = ibmveth_rxq_get_buffer(adapter);
+			if (unlikely(!skb))
+				break;
 
 			/* if the large packet bit is set in the rx queue
 			 * descriptor, the mss will be written by PHYP eight
@@ -1357,10 +1500,12 @@ restart_poll:
 				if (rx_flush)
 					ibmveth_flush_buffer(skb->data,
 						length + offset);
-				ibmveth_rxq_harvest_buffer(adapter, true);
+				if (unlikely(ibmveth_rxq_harvest_buffer(adapter, true)))
+					break;
 				skb = new_skb;
 			} else {
-				ibmveth_rxq_harvest_buffer(adapter, false);
+				if (unlikely(ibmveth_rxq_harvest_buffer(adapter, false)))
+					break;
 				skb_reserve(skb, offset);
 			}
 
@@ -1407,7 +1552,10 @@ restart_poll:
 	 * then check once more to make sure we are done.
 	 */
 	lpar_rc = h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_ENABLE);
-	BUG_ON(lpar_rc != H_SUCCESS);
+	if (WARN_ON(lpar_rc != H_SUCCESS)) {
+		schedule_work(&adapter->work);
+		goto out;
+	}
 
 	if (ibmveth_rxq_pending_buffer(adapter) && napi_schedule(napi)) {
 		lpar_rc = h_vio_signal(adapter->vdev->unit_address,
@@ -1428,7 +1576,7 @@ static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance)
 	if (napi_schedule_prep(&adapter->napi)) {
 		lpar_rc = h_vio_signal(adapter->vdev->unit_address,
 				       VIO_IRQ_DISABLE);
-		BUG_ON(lpar_rc != H_SUCCESS);
+		WARN_ON(lpar_rc != H_SUCCESS);
 		__napi_schedule(&adapter->napi);
 	}
 	return IRQ_HANDLED;
@@ -1670,6 +1818,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 
 	adapter->vdev = dev;
 	adapter->netdev = netdev;
+	INIT_WORK(&adapter->work, ibmveth_reset);
 	adapter->mcastFilterSize = be32_to_cpu(*mcastFilterSize_p);
 	ibmveth_init_link_settings(netdev);
 
@@ -1705,6 +1854,19 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 		netdev->features |= NETIF_F_FRAGLIST;
 	}
 
+	if (ret == H_SUCCESS &&
+	    (ret_attr & IBMVETH_ILLAN_RX_MULTI_BUFF_SUPPORT)) {
+		adapter->rx_buffers_per_hcall = IBMVETH_MAX_RX_PER_HCALL;
+		netdev_dbg(netdev,
+			   "RX Multi-buffer hcall supported by FW, batch set to %u\n",
+			    adapter->rx_buffers_per_hcall);
+	} else {
+		adapter->rx_buffers_per_hcall = 1;
+		netdev_dbg(netdev,
+			   "RX Single-buffer hcall mode, batch set to %u\n",
+			   adapter->rx_buffers_per_hcall);
+	}
+
 	netdev->min_mtu = IBMVETH_MIN_MTU;
 	netdev->max_mtu = ETH_MAX_MTU - IBMVETH_BUFF_OH;
 
@@ -1762,6 +1924,8 @@ static void ibmveth_remove(struct vio_dev *dev)
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
 	int i;
 
+	cancel_work_sync(&adapter->work);
+
 	for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
 		kobject_put(&adapter->rx_buff_pool[i].kobj);
 
@@ -1791,6 +1955,26 @@ static ssize_t veth_pool_show(struct kobject *kobj,
 	return 0;
 }
 
+/**
+ * veth_pool_store - sysfs store handler for pool attributes
+ * @kobj: kobject embedded in pool
+ * @attr: attribute being changed
+ * @buf: value being stored
+ * @count: length of @buf in bytes
+ *
+ * Stores new value in pool attribute. Verifies the range of the new value for
+ * size and buff_size. Verifies that at least one pool remains available to
+ * receive MTU-sized packets.
+ *
+ * Context: Process context.
+ *          Takes and releases rtnl_mutex to ensure correct ordering of close
+ *	    and open calls.
+ * Return:
+ * * %-EPERM  - Not allowed to disabled all MTU-sized buffer pools
+ * * %-EINVAL - New pool size or buffer size is out of range
+ * * count    - Return count for success
+ * * other    - Return value from a failed ibmveth_open call
+ */
 static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 			       const char *buf, size_t count)
 {
@@ -1800,24 +1984,30 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 	struct net_device *netdev = dev_get_drvdata(kobj_to_dev(kobj->parent));
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
 	long value = simple_strtol(buf, NULL, 10);
+	bool change = false;
+	u32 newbuff_size;
+	u32 oldbuff_size;
+	int newactive;
+	int oldactive;
+	u32 newsize;
+	u32 oldsize;
 	long rc;
 
+	rtnl_lock();
+
+	oldbuff_size = pool->buff_size;
+	oldactive = pool->active;
+	oldsize = pool->size;
+
+	newbuff_size = oldbuff_size;
+	newactive = oldactive;
+	newsize = oldsize;
+
 	if (attr == &veth_active_attr) {
-		if (value && !pool->active) {
-			if (netif_running(netdev)) {
-				if (ibmveth_alloc_buffer_pool(pool)) {
-					netdev_err(netdev,
-						   "unable to alloc pool\n");
-					return -ENOMEM;
-				}
-				pool->active = 1;
-				ibmveth_close(netdev);
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
-			} else {
-				pool->active = 1;
-			}
-		} else if (!value && pool->active) {
+		if (value && !oldactive) {
+			newactive = 1;
+			change = true;
+		} else if (!value && oldactive) {
 			int mtu = netdev->mtu + IBMVETH_BUFF_OH;
 			int i;
 			/* Make sure there is a buffer pool with buffers that
@@ -1833,48 +2023,60 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 
 			if (i == IBMVETH_NUM_BUFF_POOLS) {
 				netdev_err(netdev, "no active pool >= MTU\n");
-				return -EPERM;
+				rc = -EPERM;
+				goto unlock_err;
 			}
 
-			if (netif_running(netdev)) {
-				ibmveth_close(netdev);
-				pool->active = 0;
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
-			}
-			pool->active = 0;
+			newactive = 0;
+			change = true;
 		}
 	} else if (attr == &veth_num_attr) {
 		if (value <= 0 || value > IBMVETH_MAX_POOL_COUNT) {
-			return -EINVAL;
-		} else {
-			if (netif_running(netdev)) {
-				ibmveth_close(netdev);
-				pool->size = value;
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
-			} else {
-				pool->size = value;
-			}
+			rc = -EINVAL;
+			goto unlock_err;
+		}
+		if (value != oldsize) {
+			newsize = value;
+			change = true;
 		}
 	} else if (attr == &veth_size_attr) {
 		if (value <= IBMVETH_BUFF_OH || value > IBMVETH_MAX_BUF_SIZE) {
-			return -EINVAL;
-		} else {
-			if (netif_running(netdev)) {
-				ibmveth_close(netdev);
-				pool->buff_size = value;
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
-			} else {
-				pool->buff_size = value;
+			rc = -EINVAL;
+			goto unlock_err;
+		}
+		if (value != oldbuff_size) {
+			newbuff_size = value;
+			change = true;
+		}
+	}
+
+	if (change) {
+		if (netif_running(netdev))
+			ibmveth_close(netdev);
+
+		pool->active = newactive;
+		pool->buff_size = newbuff_size;
+		pool->size = newsize;
+
+		if (netif_running(netdev)) {
+			rc = ibmveth_open(netdev);
+			if (rc) {
+				pool->active = oldactive;
+				pool->buff_size = oldbuff_size;
+				pool->size = oldsize;
+				goto unlock_err;
 			}
 		}
 	}
+	rtnl_unlock();
 
 	/* kick the interrupt handler to allocate/deallocate pools */
 	ibmveth_interrupt(netdev->irq, netdev);
 	return count;
+
+unlock_err:
+	rtnl_unlock();
+	return rc;
 }
 
 
@@ -1947,3 +2149,132 @@ static void __exit ibmveth_module_exit(void)
 
 module_init(ibmveth_module_init);
 module_exit(ibmveth_module_exit);
+
+#ifdef CONFIG_IBMVETH_KUNIT_TEST
+#include <kunit/test.h>
+
+/**
+ * ibmveth_reset_kunit - reset routine for running in KUnit environment
+ *
+ * @w: pointer to work_struct embedded in adapter structure
+ *
+ * Context: Called in the KUnit environment. Does nothing.
+ *
+ * Return: void
+ */
+static void ibmveth_reset_kunit(struct work_struct *w)
+{
+	netdev_dbg(NULL, "reset_kunit starting\n");
+	netdev_dbg(NULL, "reset_kunit complete\n");
+}
+
+/**
+ * ibmveth_remove_buffer_from_pool_test - unit test for some of
+ *                                        ibmveth_remove_buffer_from_pool
+ * @test: pointer to kunit structure
+ *
+ * Tests the error returns from ibmveth_remove_buffer_from_pool.
+ * ibmveth_remove_buffer_from_pool also calls WARN_ON, so dmesg should be
+ * checked to see that these warnings happened.
+ *
+ * Return: void
+ */
+static void ibmveth_remove_buffer_from_pool_test(struct kunit *test)
+{
+	struct ibmveth_adapter *adapter = kunit_kzalloc(test, sizeof(*adapter), GFP_KERNEL);
+	struct ibmveth_buff_pool *pool;
+	u64 correlator;
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, adapter);
+
+	INIT_WORK(&adapter->work, ibmveth_reset_kunit);
+
+	/* Set sane values for buffer pools */
+	for (int i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
+		ibmveth_init_buffer_pool(&adapter->rx_buff_pool[i], i,
+					 pool_count[i], pool_size[i],
+					 pool_active[i]);
+
+	pool = &adapter->rx_buff_pool[0];
+	pool->skbuff = kunit_kcalloc(test, pool->size, sizeof(void *), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pool->skbuff);
+
+	correlator = ((u64)IBMVETH_NUM_BUFF_POOLS << 32) | 0;
+	KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, false));
+	KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, true));
+
+	correlator = ((u64)0 << 32) | adapter->rx_buff_pool[0].size;
+	KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, false));
+	KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, true));
+
+	correlator = (u64)0 | 0;
+	pool->skbuff[0] = NULL;
+	KUNIT_EXPECT_EQ(test, -EFAULT, ibmveth_remove_buffer_from_pool(adapter, correlator, false));
+	KUNIT_EXPECT_EQ(test, -EFAULT, ibmveth_remove_buffer_from_pool(adapter, correlator, true));
+
+	flush_work(&adapter->work);
+}
+
+/**
+ * ibmveth_rxq_get_buffer_test - unit test for ibmveth_rxq_get_buffer
+ * @test: pointer to kunit structure
+ *
+ * Tests ibmveth_rxq_get_buffer. ibmveth_rxq_get_buffer also calls WARN_ON for
+ * the NULL returns, so dmesg should be checked to see that these warnings
+ * happened.
+ *
+ * Return: void
+ */
+static void ibmveth_rxq_get_buffer_test(struct kunit *test)
+{
+	struct ibmveth_adapter *adapter = kunit_kzalloc(test, sizeof(*adapter), GFP_KERNEL);
+	struct sk_buff *skb = kunit_kzalloc(test, sizeof(*skb), GFP_KERNEL);
+	struct ibmveth_buff_pool *pool;
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, adapter);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+	INIT_WORK(&adapter->work, ibmveth_reset_kunit);
+
+	adapter->rx_queue.queue_len = 1;
+	adapter->rx_queue.index = 0;
+	adapter->rx_queue.queue_addr = kunit_kzalloc(test, sizeof(struct ibmveth_rx_q_entry),
+						     GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, adapter->rx_queue.queue_addr);
+
+	/* Set sane values for buffer pools */
+	for (int i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
+		ibmveth_init_buffer_pool(&adapter->rx_buff_pool[i], i,
+					 pool_count[i], pool_size[i],
+					 pool_active[i]);
+
+	pool = &adapter->rx_buff_pool[0];
+	pool->skbuff = kunit_kcalloc(test, pool->size, sizeof(void *), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pool->skbuff);
+
+	adapter->rx_queue.queue_addr[0].correlator = (u64)IBMVETH_NUM_BUFF_POOLS << 32 | 0;
+	KUNIT_EXPECT_PTR_EQ(test, NULL, ibmveth_rxq_get_buffer(adapter));
+
+	adapter->rx_queue.queue_addr[0].correlator = (u64)0 << 32 | adapter->rx_buff_pool[0].size;
+	KUNIT_EXPECT_PTR_EQ(test, NULL, ibmveth_rxq_get_buffer(adapter));
+
+	pool->skbuff[0] = skb;
+	adapter->rx_queue.queue_addr[0].correlator = (u64)0 << 32 | 0;
+	KUNIT_EXPECT_PTR_EQ(test, skb, ibmveth_rxq_get_buffer(adapter));
+
+	flush_work(&adapter->work);
+}
+
+static struct kunit_case ibmveth_test_cases[] = {
+	KUNIT_CASE(ibmveth_remove_buffer_from_pool_test),
+	KUNIT_CASE(ibmveth_rxq_get_buffer_test),
+	{}
+};
+
+static struct kunit_suite ibmveth_test_suite = {
+	.name = "ibmveth-kunit-test",
+	.test_cases = ibmveth_test_cases,
+};
+
+kunit_test_suite(ibmveth_test_suite);
+#endif
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index 8468e2c59d7a..068f99df133e 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -28,6 +28,7 @@
 #define IbmVethMcastRemoveFilter     0x2UL
 #define IbmVethMcastClearFilterTable 0x3UL
 
+#define IBMVETH_ILLAN_RX_MULTI_BUFF_SUPPORT	0x0000000000040000UL
 #define IBMVETH_ILLAN_LRG_SR_ENABLED	0x0000000000010000UL
 #define IBMVETH_ILLAN_LRG_SND_SUPPORT	0x0000000000008000UL
 #define IBMVETH_ILLAN_PADDED_PKT_CSUM	0x0000000000002000UL
@@ -46,6 +47,24 @@
 #define h_add_logical_lan_buffer(ua, buf) \
   plpar_hcall_norets(H_ADD_LOGICAL_LAN_BUFFER, ua, buf)
 
+static inline long h_add_logical_lan_buffers(unsigned long unit_address,
+					     unsigned long desc1,
+					     unsigned long desc2,
+					     unsigned long desc3,
+					     unsigned long desc4,
+					     unsigned long desc5,
+					     unsigned long desc6,
+					     unsigned long desc7,
+					     unsigned long desc8)
+{
+	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+
+	return plpar_hcall9(H_ADD_LOGICAL_LAN_BUFFERS,
+			    retbuf, unit_address,
+			    desc1, desc2, desc3, desc4,
+			    desc5, desc6, desc7, desc8);
+}
+
 /* FW allows us to send 6 descriptors but we only use one so mark
  * the other 5 as unused (0)
  */
@@ -101,6 +120,7 @@ static inline long h_illan_attributes(unsigned long unit_address,
 #define IBMVETH_MAX_TX_BUF_SIZE (1024 * 64)
 #define IBMVETH_MAX_QUEUES 16U
 #define IBMVETH_DEFAULT_QUEUES 8U
+#define IBMVETH_MAX_RX_PER_HCALL 8U
 
 static int pool_size[] = { 512, 1024 * 2, 1024 * 16, 1024 * 32, 1024 * 64 };
 static int pool_count[] = { 256, 512, 256, 256, 256 };
@@ -134,38 +154,40 @@ struct ibmveth_rx_q {
 };
 
 struct ibmveth_adapter {
-    struct vio_dev *vdev;
-    struct net_device *netdev;
-    struct napi_struct napi;
-    unsigned int mcastFilterSize;
-    void * buffer_list_addr;
-    void * filter_list_addr;
-    void *tx_ltb_ptr[IBMVETH_MAX_QUEUES];
-    unsigned int tx_ltb_size;
-    dma_addr_t tx_ltb_dma[IBMVETH_MAX_QUEUES];
-    dma_addr_t buffer_list_dma;
-    dma_addr_t filter_list_dma;
-    struct ibmveth_buff_pool rx_buff_pool[IBMVETH_NUM_BUFF_POOLS];
-    struct ibmveth_rx_q rx_queue;
-    int rx_csum;
-    int large_send;
-    bool is_active_trunk;
-
-    u64 fw_ipv6_csum_support;
-    u64 fw_ipv4_csum_support;
-    u64 fw_large_send_support;
-    /* adapter specific stats */
-    u64 replenish_task_cycles;
-    u64 replenish_no_mem;
-    u64 replenish_add_buff_failure;
-    u64 replenish_add_buff_success;
-    u64 rx_invalid_buffer;
-    u64 rx_no_buffer;
-    u64 tx_map_failed;
-    u64 tx_send_failed;
-    u64 tx_large_packets;
-    u64 rx_large_packets;
-    /* Ethtool settings */
+	struct vio_dev *vdev;
+	struct net_device *netdev;
+	struct napi_struct napi;
+	struct work_struct work;
+	unsigned int mcastFilterSize;
+	void *buffer_list_addr;
+	void *filter_list_addr;
+	void *tx_ltb_ptr[IBMVETH_MAX_QUEUES];
+	unsigned int tx_ltb_size;
+	dma_addr_t tx_ltb_dma[IBMVETH_MAX_QUEUES];
+	dma_addr_t buffer_list_dma;
+	dma_addr_t filter_list_dma;
+	struct ibmveth_buff_pool rx_buff_pool[IBMVETH_NUM_BUFF_POOLS];
+	struct ibmveth_rx_q rx_queue;
+	int rx_csum;
+	int large_send;
+	bool is_active_trunk;
+	unsigned int rx_buffers_per_hcall;
+
+	u64 fw_ipv6_csum_support;
+	u64 fw_ipv4_csum_support;
+	u64 fw_large_send_support;
+	/* adapter specific stats */
+	u64 replenish_task_cycles;
+	u64 replenish_no_mem;
+	u64 replenish_add_buff_failure;
+	u64 replenish_add_buff_success;
+	u64 rx_invalid_buffer;
+	u64 rx_no_buffer;
+	u64 tx_map_failed;
+	u64 tx_send_failed;
+	u64 tx_large_packets;
+	u64 rx_large_packets;
+	/* Ethtool settings */
 	u8 duplex;
 	u32 speed;
 };
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index e95ae0d39948..3808148c1fc7 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -234,11 +234,17 @@ static int ibmvnic_set_queue_affinity(struct ibmvnic_sub_crq_queue *queue,
 		(*stragglers)--;
 	}
 	/* atomic write is safer than writing bit by bit directly */
-	for (i = 0; i < stride; i++) {
-		cpumask_set_cpu(*cpu, mask);
-		*cpu = cpumask_next_wrap(*cpu, cpu_online_mask,
-					 nr_cpu_ids, false);
+	for_each_online_cpu_wrap(i, *cpu) {
+		if (!stride--) {
+			/* For the next queue we start from the first
+			 * unused CPU in this queue
+			 */
+			*cpu = i;
+			break;
+		}
+		cpumask_set_cpu(i, mask);
 	}
+
 	/* set queue affinity mask */
 	cpumask_copy(queue->affinity_mask, mask);
 	rc = irq_set_affinity_and_hint(queue->irq, queue->affinity_mask);
@@ -256,7 +262,7 @@ static void ibmvnic_set_affinity(struct ibmvnic_adapter *adapter)
 	int num_rxqs = adapter->num_active_rx_scrqs, i_rxqs = 0;
 	int num_txqs = adapter->num_active_tx_scrqs, i_txqs = 0;
 	int total_queues, stride, stragglers, i;
-	unsigned int num_cpu, cpu;
+	unsigned int num_cpu, cpu = 0;
 	bool is_rx_queue;
 	int rc = 0;
 
@@ -274,8 +280,6 @@ static void ibmvnic_set_affinity(struct ibmvnic_adapter *adapter)
 	stride = max_t(int, num_cpu / total_queues, 1);
 	/* number of leftover cpu's */
 	stragglers = num_cpu >= total_queues ? num_cpu % total_queues : 0;
-	/* next available cpu to assign irq to */
-	cpu = cpumask_next(-1, cpu_online_mask);
 
 	for (i = 0; i < total_queues; i++) {
 		is_rx_queue = false;
@@ -752,6 +756,17 @@ static void deactivate_rx_pools(struct ibmvnic_adapter *adapter)
 		adapter->rx_pool[i].active = 0;
 }
 
+static void ibmvnic_set_safe_max_ind_descs(struct ibmvnic_adapter *adapter)
+{
+	if (adapter->cur_max_ind_descs > IBMVNIC_SAFE_IND_DESC) {
+		netdev_info(adapter->netdev,
+			    "set max ind descs from %u to safe limit %u\n",
+			    adapter->cur_max_ind_descs,
+			    IBMVNIC_SAFE_IND_DESC);
+		adapter->cur_max_ind_descs = IBMVNIC_SAFE_IND_DESC;
+	}
+}
+
 static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
 			      struct ibmvnic_rx_pool *pool)
 {
@@ -839,7 +854,7 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
 		sub_crq->rx_add.len = cpu_to_be32(pool->buff_size << shift);
 
 		/* if send_subcrq_indirect queue is full, flush to VIOS */
-		if (ind_bufp->index == IBMVNIC_MAX_IND_DESCS ||
+		if (ind_bufp->index == adapter->cur_max_ind_descs ||
 		    i == count - 1) {
 			lpar_rc =
 				send_subcrq_indirect(adapter, handle,
@@ -858,6 +873,14 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
 failure:
 	if (lpar_rc != H_PARAMETER && lpar_rc != H_CLOSED)
 		dev_err_ratelimited(dev, "rx: replenish packet buffer failed\n");
+
+	/* Detect platform limit H_PARAMETER */
+	if (lpar_rc == H_PARAMETER)
+		ibmvnic_set_safe_max_ind_descs(adapter);
+
+	/* For all error case, temporarily drop only this batch
+	 * Rely on TCP/IP retransmissions to retry and recover
+	 */
 	for (i = ind_bufp->index - 1; i >= 0; --i) {
 		struct ibmvnic_rx_buff *rx_buff;
 
@@ -2308,8 +2331,6 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter,
 					  tx_pool->num_buffers - 1 :
 					  tx_pool->consumer_index - 1;
 		tx_buff = &tx_pool->tx_buff[index];
-		adapter->netdev->stats.tx_packets--;
-		adapter->netdev->stats.tx_bytes -= tx_buff->skb->len;
 		adapter->tx_stats_buffers[queue_num].batched_packets--;
 		adapter->tx_stats_buffers[queue_num].bytes -=
 						tx_buff->skb->len;
@@ -2379,16 +2400,28 @@ static int ibmvnic_tx_scrq_flush(struct ibmvnic_adapter *adapter,
 		rc = send_subcrq_direct(adapter, handle,
 					(u64 *)ind_bufp->indir_arr);
 
-	if (rc)
+	if (rc) {
+		dev_err_ratelimited(&adapter->vdev->dev,
+				    "tx_flush failed, rc=%u (%llu entries dma=%pad handle=%llx)\n",
+				    rc, entries, &dma_addr, handle);
+		/* Detect platform limit H_PARAMETER */
+		if (rc == H_PARAMETER)
+			ibmvnic_set_safe_max_ind_descs(adapter);
+
+		/* For all error case, temporarily drop only this batch
+		 * Rely on TCP/IP retransmissions to retry and recover
+		 */
 		ibmvnic_tx_scrq_clean_buffer(adapter, tx_scrq);
-	else
+	} else {
 		ind_bufp->index = 0;
+	}
 	return rc;
 }
 
 static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	u32 cur_max_ind_descs = adapter->cur_max_ind_descs;
 	int queue_num = skb_get_queue_mapping(skb);
 	u8 *hdrs = (u8 *)&adapter->tx_rx_desc_req;
 	struct device *dev = &adapter->vdev->dev;
@@ -2408,6 +2441,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	dma_addr_t data_dma_addr;
 	struct netdev_queue *txq;
 	unsigned long lpar_rc;
+	unsigned int skblen;
 	union sub_crq tx_crq;
 	unsigned int offset;
 	bool use_scrq_send_direct = false;
@@ -2522,6 +2556,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	tx_buff->skb = skb;
 	tx_buff->index = bufidx;
 	tx_buff->pool_index = queue_num;
+	skblen = skb->len;
 
 	memset(&tx_crq, 0, sizeof(tx_crq));
 	tx_crq.v1.first = IBMVNIC_CRQ_CMD;
@@ -2586,7 +2621,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	tx_crq.v1.n_crq_elem = num_entries;
 	tx_buff->num_entries = num_entries;
 	/* flush buffer if current entry can not fit */
-	if (num_entries + ind_bufp->index > IBMVNIC_MAX_IND_DESCS) {
+	if (num_entries + ind_bufp->index > cur_max_ind_descs) {
 		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true);
 		if (lpar_rc != H_SUCCESS)
 			goto tx_flush_err;
@@ -2599,7 +2634,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	ind_bufp->index += num_entries;
 	if (__netdev_tx_sent_queue(txq, skb->len,
 				   netdev_xmit_more() &&
-				   ind_bufp->index < IBMVNIC_MAX_IND_DESCS)) {
+				   ind_bufp->index < cur_max_ind_descs)) {
 		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true);
 		if (lpar_rc != H_SUCCESS)
 			goto tx_err;
@@ -2614,7 +2649,7 @@ early_exit:
 		netif_stop_subqueue(netdev, queue_num);
 	}
 
-	tx_bytes += skb->len;
+	tx_bytes += skblen;
 	txq_trans_cond_update(txq);
 	ret = NETDEV_TX_OK;
 	goto out;
@@ -2641,9 +2676,6 @@ tx_err:
 	}
 out:
 	rcu_read_unlock();
-	netdev->stats.tx_dropped += tx_dropped;
-	netdev->stats.tx_bytes += tx_bytes;
-	netdev->stats.tx_packets += tx_bpackets + tx_dpackets;
 	adapter->tx_send_failed += tx_send_failed;
 	adapter->tx_map_failed += tx_map_failed;
 	adapter->tx_stats_buffers[queue_num].batched_packets += tx_bpackets;
@@ -3446,6 +3478,25 @@ err:
 	return -ret;
 }
 
+static void ibmvnic_get_stats64(struct net_device *netdev,
+				struct rtnl_link_stats64 *stats)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	int i;
+
+	for (i = 0; i < adapter->req_rx_queues; i++) {
+		stats->rx_packets += adapter->rx_stats_buffers[i].packets;
+		stats->rx_bytes   += adapter->rx_stats_buffers[i].bytes;
+	}
+
+	for (i = 0; i < adapter->req_tx_queues; i++) {
+		stats->tx_packets += adapter->tx_stats_buffers[i].batched_packets;
+		stats->tx_packets += adapter->tx_stats_buffers[i].direct_packets;
+		stats->tx_bytes   += adapter->tx_stats_buffers[i].bytes;
+		stats->tx_dropped += adapter->tx_stats_buffers[i].dropped_packets;
+	}
+}
+
 static void ibmvnic_tx_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(dev);
@@ -3561,8 +3612,6 @@ restart_poll:
 
 		length = skb->len;
 		napi_gro_receive(napi, skb); /* send it up */
-		netdev->stats.rx_packets++;
-		netdev->stats.rx_bytes += length;
 		adapter->rx_stats_buffers[scrq_num].packets++;
 		adapter->rx_stats_buffers[scrq_num].bytes += length;
 		frames_processed++;
@@ -3672,6 +3721,7 @@ static const struct net_device_ops ibmvnic_netdev_ops = {
 	.ndo_set_rx_mode	= ibmvnic_set_multi,
 	.ndo_set_mac_address	= ibmvnic_set_mac,
 	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_get_stats64	= ibmvnic_get_stats64,
 	.ndo_tx_timeout		= ibmvnic_tx_timeout,
 	.ndo_change_mtu		= ibmvnic_change_mtu,
 	.ndo_features_check     = ibmvnic_features_check,
@@ -3987,7 +4037,7 @@ static void release_sub_crq_queue(struct ibmvnic_adapter *adapter,
 	}
 
 	dma_free_coherent(dev,
-			  IBMVNIC_IND_ARR_SZ,
+			  IBMVNIC_IND_MAX_ARR_SZ,
 			  scrq->ind_buf.indir_arr,
 			  scrq->ind_buf.indir_dma);
 
@@ -4044,7 +4094,7 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter
 
 	scrq->ind_buf.indir_arr =
 		dma_alloc_coherent(dev,
-				   IBMVNIC_IND_ARR_SZ,
+				   IBMVNIC_IND_MAX_ARR_SZ,
 				   &scrq->ind_buf.indir_dma,
 				   GFP_KERNEL);
 
@@ -4827,6 +4877,18 @@ static void vnic_add_client_data(struct ibmvnic_adapter *adapter,
 	strscpy(vlcd->name, adapter->netdev->name, len);
 }
 
+static void ibmvnic_print_hex_dump(struct net_device *dev, void *buf,
+				   size_t len)
+{
+	unsigned char hex_str[16 * 3];
+
+	for (size_t i = 0; i < len; i += 16) {
+		hex_dump_to_buffer((unsigned char *)buf + i, len - i, 16, 8,
+				   hex_str, sizeof(hex_str), false);
+		netdev_dbg(dev, "%s\n", hex_str);
+	}
+}
+
 static int send_login(struct ibmvnic_adapter *adapter)
 {
 	struct ibmvnic_login_rsp_buffer *login_rsp_buffer;
@@ -4937,10 +4999,8 @@ static int send_login(struct ibmvnic_adapter *adapter)
 	vnic_add_client_data(adapter, vlcd);
 
 	netdev_dbg(adapter->netdev, "Login Buffer:\n");
-	for (i = 0; i < (adapter->login_buf_sz - 1) / 8 + 1; i++) {
-		netdev_dbg(adapter->netdev, "%016lx\n",
-			   ((unsigned long *)(adapter->login_buf))[i]);
-	}
+	ibmvnic_print_hex_dump(adapter->netdev, adapter->login_buf,
+			       adapter->login_buf_sz);
 
 	memset(&crq, 0, sizeof(crq));
 	crq.login.first = IBMVNIC_CRQ_CMD;
@@ -5317,15 +5377,13 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
 	struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf;
-	int i;
 
 	dma_unmap_single(dev, adapter->ip_offload_tok,
 			 sizeof(adapter->ip_offload_buf), DMA_FROM_DEVICE);
 
 	netdev_dbg(adapter->netdev, "Query IP Offload Buffer:\n");
-	for (i = 0; i < (sizeof(adapter->ip_offload_buf) - 1) / 8 + 1; i++)
-		netdev_dbg(adapter->netdev, "%016lx\n",
-			   ((unsigned long *)(buf))[i]);
+	ibmvnic_print_hex_dump(adapter->netdev, buf,
+			       sizeof(adapter->ip_offload_buf));
 
 	netdev_dbg(adapter->netdev, "ipv4_chksum = %d\n", buf->ipv4_chksum);
 	netdev_dbg(adapter->netdev, "ipv6_chksum = %d\n", buf->ipv6_chksum);
@@ -5556,10 +5614,8 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 	netdev->mtu = adapter->req_mtu - ETH_HLEN;
 
 	netdev_dbg(adapter->netdev, "Login Response Buffer:\n");
-	for (i = 0; i < (adapter->login_rsp_buf_sz - 1) / 8 + 1; i++) {
-		netdev_dbg(adapter->netdev, "%016lx\n",
-			   ((unsigned long *)(adapter->login_rsp_buf))[i]);
-	}
+	ibmvnic_print_hex_dump(netdev, adapter->login_rsp_buf,
+			       adapter->login_rsp_buf_sz);
 
 	/* Sanity checks */
 	if (login->num_txcomp_subcrqs != login_rsp->num_txsubm_subcrqs ||
@@ -6344,6 +6400,19 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset)
 			rc = reset_sub_crq_queues(adapter);
 		}
 	} else {
+		if (adapter->reset_reason == VNIC_RESET_MOBILITY) {
+			/* After an LPM, reset the max number of indirect
+			 * subcrq descriptors per H_SEND_SUB_CRQ_INDIRECT
+			 * hcall to the default max (e.g POWER8 -> POWER10)
+			 *
+			 * If the new destination platform does not support
+			 * the higher limit max (e.g. POWER10-> POWER8 LPM)
+			 * H_PARAMETER will trigger automatic fallback to the
+			 * safe minimum limit.
+			 */
+			adapter->cur_max_ind_descs = IBMVNIC_MAX_IND_DESCS;
+		}
+
 		rc = init_sub_crqs(adapter);
 	}
 
@@ -6495,6 +6564,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 
 	adapter->wait_for_reset = false;
 	adapter->last_reset_time = jiffies;
+	adapter->cur_max_ind_descs = IBMVNIC_MAX_IND_DESCS;
 
 	rc = register_netdev(netdev);
 	if (rc) {
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index a189038d88df..480dc587078f 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -29,8 +29,9 @@
 #define IBMVNIC_BUFFS_PER_POOL	100
 #define IBMVNIC_MAX_QUEUES	16
 #define IBMVNIC_MAX_QUEUE_SZ   4096
-#define IBMVNIC_MAX_IND_DESCS  16
-#define IBMVNIC_IND_ARR_SZ	(IBMVNIC_MAX_IND_DESCS * 32)
+#define IBMVNIC_MAX_IND_DESCS 128
+#define IBMVNIC_SAFE_IND_DESC 16
+#define IBMVNIC_IND_MAX_ARR_SZ (IBMVNIC_MAX_IND_DESCS * 32)
 
 #define IBMVNIC_TSO_BUF_SZ	65536
 #define IBMVNIC_TSO_BUFS	64
@@ -211,7 +212,6 @@ struct ibmvnic_statistics {
 	u8 reserved[72];
 } __packed __aligned(8);
 
-#define NUM_TX_STATS 3
 struct ibmvnic_tx_queue_stats {
 	u64 batched_packets;
 	u64 direct_packets;
@@ -219,13 +219,18 @@ struct ibmvnic_tx_queue_stats {
 	u64 dropped_packets;
 };
 
-#define NUM_RX_STATS 3
+#define NUM_TX_STATS \
+	(sizeof(struct ibmvnic_tx_queue_stats) / sizeof(u64))
+
 struct ibmvnic_rx_queue_stats {
 	u64 packets;
 	u64 bytes;
 	u64 interrupts;
 };
 
+#define NUM_RX_STATS \
+	(sizeof(struct ibmvnic_rx_queue_stats) / sizeof(u64))
+
 struct ibmvnic_acl_buffer {
 	__be32 len;
 	__be32 version;
@@ -926,6 +931,7 @@ struct ibmvnic_adapter {
 	struct ibmvnic_control_ip_offload_buffer ip_offload_ctrl;
 	dma_addr_t ip_offload_ctrl_tok;
 	u32 msg_enable;
+	u32 cur_max_ind_descs;
 
 	/* Vital Product Data (VPD) */
 	struct ibmvnic_vpd *vpd;
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 24ec9a4f1ffa..288fa8ce53af 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -146,7 +146,10 @@ config IXGBE
 	tristate "Intel(R) 10GbE PCI Express adapters support"
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
+	select LIBIE_FWLOG if DEBUG_FS
 	select MDIO
+	select NET_DEVLINK
+	select PLDMFW
 	select PHYLIB
 	help
 	  This driver supports Intel(R) 10GbE PCI Express family of
@@ -229,6 +232,7 @@ config I40E
 	depends on PCI
 	select AUXILIARY_BUS
 	select LIBIE
+	select LIBIE_ADMINQ
 	select NET_DEVLINK
 	help
 	  This driver supports Intel(R) Ethernet Controller XL710 Family of
@@ -258,12 +262,14 @@ config I40E_DCB
 config IAVF
 	tristate
 	select LIBIE
+	select LIBIE_ADMINQ
 	select NET_SHAPER
 
 config I40EVF
 	tristate "Intel(R) Ethernet Adaptive Virtual Function support"
 	select IAVF
 	depends on PCI_MSI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  This driver supports virtual functions for Intel XL710,
 	  X710, X722, XXV710, and all devices advertising support for
@@ -290,7 +296,10 @@ config ICE
 	depends on GNSS || GNSS = n
 	select AUXILIARY_BUS
 	select DIMLIB
+	select LIBETH_XDP
 	select LIBIE
+	select LIBIE_ADMINQ
+	select LIBIE_FWLOG if DEBUG_FS
 	select NET_DEVLINK
 	select PACKING
 	select PLDMFW
@@ -336,7 +345,7 @@ config ICE_SWITCHDEV
 config ICE_HWTS
 	bool "Support HW cross-timestamp on platforms with PTM support"
 	default y
-	depends on ICE && X86
+	depends on ICE && X86 && PCIE_PTM
 	help
 	  Say Y to enable hardware supported cross-timestamping on platforms
 	  with PCIe PTM support. The cross-timestamp is available through
@@ -366,6 +375,7 @@ config IGC
 	default n
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
+	depends on ETHTOOL_NETLINK
 	help
 	  This driver supports Intel(R) Ethernet Controller I225-LM/I225-V
 	  family of adapters.
diff --git a/drivers/net/ethernet/intel/Makefile b/drivers/net/ethernet/intel/Makefile
index 04c844ef4964..9a37dc76aef0 100644
--- a/drivers/net/ethernet/intel/Makefile
+++ b/drivers/net/ethernet/intel/Makefile
@@ -4,7 +4,7 @@
 #
 
 obj-$(CONFIG_LIBETH) += libeth/
-obj-$(CONFIG_LIBIE) += libie/
+obj-y += libie/
 
 obj-$(CONFIG_E100) += e100.o
 obj-$(CONFIG_E1000) += e1000/
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 3a5bbda235cb..5c56c1edd492 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -1682,7 +1682,7 @@ static void e100_adjust_adaptive_ifs(struct nic *nic, int speed, int duplex)
 
 static void e100_watchdog(struct timer_list *t)
 {
-	struct nic *nic = from_timer(nic, t, watchdog);
+	struct nic *nic = timer_container_of(nic, t, watchdog);
 	struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET };
 	u32 speed;
 
@@ -2293,7 +2293,7 @@ static int e100_up(struct nic *nic)
 	return 0;
 
 err_no_irq:
-	del_timer_sync(&nic->watchdog);
+	timer_delete_sync(&nic->watchdog);
 err_clean_cbs:
 	e100_clean_cbs(nic);
 err_rx_clean_list:
@@ -2308,7 +2308,7 @@ static void e100_down(struct nic *nic)
 	netif_stop_queue(nic->netdev);
 	e100_hw_reset(nic);
 	free_irq(nic->pdev->irq, nic->netdev);
-	del_timer_sync(&nic->watchdog);
+	timer_delete_sync(&nic->watchdog);
 	netif_carrier_off(nic->netdev);
 	e100_clean_cbs(nic);
 	e100_rx_clean_list(nic);
diff --git a/drivers/net/ethernet/intel/e1000/e1000.h b/drivers/net/ethernet/intel/e1000/e1000.h
index 75f3fd1d8d6e..ea6ccf4b728b 100644
--- a/drivers/net/ethernet/intel/e1000/e1000.h
+++ b/drivers/net/ethernet/intel/e1000/e1000.h
@@ -116,7 +116,7 @@ struct e1000_adapter;
 #define E1000_MASTER_SLAVE	e1000_ms_hw_default
 #endif
 
-#define E1000_MNG_VLAN_NONE	(-1)
+#define E1000_MNG_VLAN_NONE	0xFFFF
 
 /* wrapper around a pointer to a socket buffer,
  * so a DMA handle can be stored along with the buffer
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index d06d29c6c037..726365c567ef 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -806,7 +806,7 @@ static int e1000_eeprom_test(struct e1000_adapter *adapter, u64 *data)
 	}
 
 	/* If Checksum is not Correct return error else test passed */
-	if ((checksum != (u16)EEPROM_SUM) && !(*data))
+	if (checksum != EEPROM_SUM && !(*data))
 		*data = 2;
 
 	return *data;
diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c
index f9328f2e669f..0e5de52b1067 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_hw.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c
@@ -3970,7 +3970,7 @@ s32 e1000_validate_eeprom_checksum(struct e1000_hw *hw)
 		return E1000_SUCCESS;
 
 #endif
-	if (checksum == (u16)EEPROM_SUM)
+	if (checksum == EEPROM_SUM)
 		return E1000_SUCCESS;
 	else {
 		e_dbg("EEPROM Checksum Invalid\n");
@@ -3997,7 +3997,7 @@ s32 e1000_update_eeprom_checksum(struct e1000_hw *hw)
 		}
 		checksum += eeprom_data;
 	}
-	checksum = (u16)EEPROM_SUM - checksum;
+	checksum = EEPROM_SUM - checksum;
 	if (e1000_write_eeprom(hw, EEPROM_CHECKSUM_REG, 1, &checksum) < 0) {
 		e_dbg("EEPROM Write Error\n");
 		return -E1000_ERR_EEPROM;
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 3f089c3d47b2..292389aceb2d 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -313,8 +313,7 @@ static void e1000_update_mng_vlan(struct e1000_adapter *adapter)
 		} else {
 			adapter->mng_vlan_id = E1000_MNG_VLAN_NONE;
 		}
-		if ((old_vid != (u16)E1000_MNG_VLAN_NONE) &&
-		    (vid != old_vid) &&
+		if (old_vid != E1000_MNG_VLAN_NONE && vid != old_vid &&
 		    !test_bit(old_vid, adapter->active_vlans))
 			e1000_vlan_rx_kill_vid(netdev, htons(ETH_P_8021Q),
 					       old_vid);
@@ -477,10 +476,6 @@ static void e1000_down_and_stop(struct e1000_adapter *adapter)
 
 	cancel_delayed_work_sync(&adapter->phy_info_task);
 	cancel_delayed_work_sync(&adapter->fifo_stall_task);
-
-	/* Only kill reset task if adapter is not resetting */
-	if (!test_bit(__E1000_RESETTING, &adapter->flags))
-		cancel_work_sync(&adapter->reset_task);
 }
 
 void e1000_down(struct e1000_adapter *adapter)
@@ -1266,6 +1261,10 @@ static void e1000_remove(struct pci_dev *pdev)
 
 	unregister_netdev(netdev);
 
+	/* Only kill reset task if adapter is not resetting */
+	if (!test_bit(__E1000_RESETTING, &adapter->flags))
+		cancel_work_sync(&adapter->reset_task);
+
 	e1000_phy_hw_reset(hw);
 
 	kfree(adapter->tx_ring);
diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index 5e2cfa73f889..ba331899d186 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -638,6 +638,9 @@
 /* For checksumming, the sum of all words in the NVM should equal 0xBABA. */
 #define NVM_SUM                    0xBABA
 
+/* Uninitialized ("empty") checksum word value */
+#define NVM_CHECKSUM_UNINITIALIZED 0xFFFF
+
 /* PBA (printed board assembly) number words */
 #define NVM_PBA_OFFSET_0           8
 #define NVM_PBA_OFFSET_1           9
@@ -803,4 +806,7 @@
 /* SerDes Control */
 #define E1000_GEN_POLL_TIMEOUT          640
 
+#define E1000_FEXTNVM12_PHYPD_CTRL_MASK	0x00C00000
+#define E1000_FEXTNVM12_PHYPD_CTRL_P1	0x00800000
+
 #endif /* _E1000_DEFINES_H_ */
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index ba9c19e6994c..aa08f397988e 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -64,7 +64,7 @@ struct e1000_info;
 #define AUTO_ALL_MODES			0
 #define E1000_EEPROM_APME		0x0400
 
-#define E1000_MNG_VLAN_NONE		(-1)
+#define E1000_MNG_VLAN_NONE		0xFFFF
 
 #define DEFAULT_JUMBO			9234
 
@@ -319,7 +319,7 @@ struct e1000_adapter {
 	u16 tx_ring_count;
 	u16 rx_ring_count;
 
-	struct hwtstamp_config hwtstamp_config;
+	struct kernel_hwtstamp_config hwtstamp_config;
 	struct delayed_work systim_overflow_work;
 	struct sk_buff *tx_hwtstamp_skb;
 	unsigned long tx_hwtstamp_start;
@@ -461,6 +461,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca);
 #define FLAG2_CHECK_RX_HWTSTAMP           BIT(13)
 #define FLAG2_CHECK_SYSTIM_OVERFLOW       BIT(14)
 #define FLAG2_ENABLE_S0IX_FLOWS           BIT(15)
+#define FLAG2_DISABLE_K1		   BIT(16)
 
 #define E1000_RX_DESC_PS(R, i)	    \
 	(&(((union e1000_rx_desc_packet_split *)((R).desc))[i]))
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 9364bc2b4eb1..7b1ac90b3de4 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -26,6 +26,8 @@ struct e1000_stats {
 static const char e1000e_priv_flags_strings[][ETH_GSTRING_LEN] = {
 #define E1000E_PRIV_FLAGS_S0IX_ENABLED	BIT(0)
 	"s0ix-enabled",
+#define E1000E_PRIV_FLAGS_DISABLE_K1	BIT(1)
+	"disable-k1",
 };
 
 #define E1000E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(e1000e_priv_flags_strings)
@@ -550,11 +552,11 @@ static int e1000_set_eeprom(struct net_device *netdev,
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 	u16 *eeprom_buff;
-	void *ptr;
-	int max_len;
+	int ret_val = 0;
+	size_t max_len;
 	int first_word;
 	int last_word;
-	int ret_val = 0;
+	void *ptr;
 	u16 i;
 
 	if (eeprom->len == 0)
@@ -959,7 +961,7 @@ static int e1000_eeprom_test(struct e1000_adapter *adapter, u64 *data)
 	}
 
 	/* If Checksum is not Correct return error else test passed */
-	if ((checksum != (u16)NVM_SUM) && !(*data))
+	if (checksum != NVM_SUM && !(*data))
 		*data = 2;
 
 	return *data;
@@ -2096,54 +2098,47 @@ static void e1000_get_strings(struct net_device __always_unused *netdev,
 	}
 }
 
-static int e1000_get_rxnfc(struct net_device *netdev,
-			   struct ethtool_rxnfc *info,
-			   u32 __always_unused *rule_locs)
+static int e1000_get_rxfh_fields(struct net_device *netdev,
+				 struct ethtool_rxfh_fields *info)
 {
-	info->data = 0;
-
-	switch (info->cmd) {
-	case ETHTOOL_GRXFH: {
-		struct e1000_adapter *adapter = netdev_priv(netdev);
-		struct e1000_hw *hw = &adapter->hw;
-		u32 mrqc;
+	struct e1000_adapter *adapter = netdev_priv(netdev);
+	struct e1000_hw *hw = &adapter->hw;
+	u32 mrqc;
 
-		mrqc = er32(MRQC);
+	info->data = 0;
 
-		if (!(mrqc & E1000_MRQC_RSS_FIELD_MASK))
-			return 0;
+	mrqc = er32(MRQC);
 
-		switch (info->flow_type) {
-		case TCP_V4_FLOW:
-			if (mrqc & E1000_MRQC_RSS_FIELD_IPV4_TCP)
-				info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
-			fallthrough;
-		case UDP_V4_FLOW:
-		case SCTP_V4_FLOW:
-		case AH_ESP_V4_FLOW:
-		case IPV4_FLOW:
-			if (mrqc & E1000_MRQC_RSS_FIELD_IPV4)
-				info->data |= RXH_IP_SRC | RXH_IP_DST;
-			break;
-		case TCP_V6_FLOW:
-			if (mrqc & E1000_MRQC_RSS_FIELD_IPV6_TCP)
-				info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
-			fallthrough;
-		case UDP_V6_FLOW:
-		case SCTP_V6_FLOW:
-		case AH_ESP_V6_FLOW:
-		case IPV6_FLOW:
-			if (mrqc & E1000_MRQC_RSS_FIELD_IPV6)
-				info->data |= RXH_IP_SRC | RXH_IP_DST;
-			break;
-		default:
-			break;
-		}
+	if (!(mrqc & E1000_MRQC_RSS_FIELD_MASK))
 		return 0;
-	}
+
+	switch (info->flow_type) {
+	case TCP_V4_FLOW:
+		if (mrqc & E1000_MRQC_RSS_FIELD_IPV4_TCP)
+			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		fallthrough;
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+	case AH_ESP_V4_FLOW:
+	case IPV4_FLOW:
+		if (mrqc & E1000_MRQC_RSS_FIELD_IPV4)
+			info->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case TCP_V6_FLOW:
+		if (mrqc & E1000_MRQC_RSS_FIELD_IPV6_TCP)
+			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		fallthrough;
+	case UDP_V6_FLOW:
+	case SCTP_V6_FLOW:
+	case AH_ESP_V6_FLOW:
+	case IPV6_FLOW:
+		if (mrqc & E1000_MRQC_RSS_FIELD_IPV6)
+			info->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
 	default:
-		return -EOPNOTSUPP;
+		break;
 	}
+	return 0;
 }
 
 static int e1000e_get_eee(struct net_device *netdev, struct ethtool_keee *edata)
@@ -2304,26 +2299,59 @@ static u32 e1000e_get_priv_flags(struct net_device *netdev)
 	if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS)
 		priv_flags |= E1000E_PRIV_FLAGS_S0IX_ENABLED;
 
+	if (adapter->flags2 & FLAG2_DISABLE_K1)
+		priv_flags |= E1000E_PRIV_FLAGS_DISABLE_K1;
+
 	return priv_flags;
 }
 
 static int e1000e_set_priv_flags(struct net_device *netdev, u32 priv_flags)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
+	struct e1000_hw *hw = &adapter->hw;
 	unsigned int flags2 = adapter->flags2;
+	unsigned int changed;
 
-	flags2 &= ~FLAG2_ENABLE_S0IX_FLOWS;
-	if (priv_flags & E1000E_PRIV_FLAGS_S0IX_ENABLED) {
-		struct e1000_hw *hw = &adapter->hw;
+	flags2 &= ~(FLAG2_ENABLE_S0IX_FLOWS | FLAG2_DISABLE_K1);
 
-		if (hw->mac.type < e1000_pch_cnp)
+	if (priv_flags & E1000E_PRIV_FLAGS_S0IX_ENABLED) {
+		if (hw->mac.type < e1000_pch_cnp) {
+			e_err("S0ix is not supported on this device\n");
 			return -EINVAL;
+		}
+
 		flags2 |= FLAG2_ENABLE_S0IX_FLOWS;
 	}
 
-	if (flags2 != adapter->flags2)
+	if (priv_flags & E1000E_PRIV_FLAGS_DISABLE_K1) {
+		if (hw->mac.type < e1000_ich8lan) {
+			e_err("Disabling K1 is not supported on this device\n");
+			return -EINVAL;
+		}
+
+		flags2 |= FLAG2_DISABLE_K1;
+	}
+
+	changed = adapter->flags2 ^ flags2;
+	if (changed)
 		adapter->flags2 = flags2;
 
+	if (changed & FLAG2_DISABLE_K1) {
+		/* reset the hardware to apply the changes */
+		while (test_and_set_bit(__E1000_RESETTING,
+					&adapter->state))
+			usleep_range(1000, 2000);
+
+		if (netif_running(adapter->netdev)) {
+			e1000e_down(adapter, true);
+			e1000e_up(adapter);
+		} else {
+			e1000e_reset(adapter);
+		}
+
+		clear_bit(__E1000_RESETTING, &adapter->state);
+	}
+
 	return 0;
 }
 
@@ -2352,7 +2380,7 @@ static const struct ethtool_ops e1000_ethtool_ops = {
 	.get_sset_count		= e1000e_get_sset_count,
 	.get_coalesce		= e1000_get_coalesce,
 	.set_coalesce		= e1000_set_coalesce,
-	.get_rxnfc		= e1000_get_rxnfc,
+	.get_rxfh_fields	= e1000_get_rxfh_fields,
 	.get_ts_info		= e1000e_get_ts_info,
 	.get_eee		= e1000e_get_eee,
 	.set_eee		= e1000e_set_eee,
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 2f9655cf5dd9..0ff8688ac3b8 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -286,6 +286,52 @@ static void e1000_toggle_lanphypc_pch_lpt(struct e1000_hw *hw)
 }
 
 /**
+ * e1000_reconfigure_k1_params - reconfigure Kumeran K1 parameters.
+ * @hw: pointer to the HW structure
+ *
+ * By default K1 is enabled after MAC reset, so this function only
+ * disables it.
+ *
+ * Context: PHY semaphore must be held by caller.
+ * Return: 0 on success, negative on failure
+ */
+static s32 e1000_reconfigure_k1_params(struct e1000_hw *hw)
+{
+	u16 phy_timeout;
+	u32 fextnvm12;
+	s32 ret_val;
+
+	if (hw->mac.type < e1000_pch_mtp) {
+		if (hw->adapter->flags2 & FLAG2_DISABLE_K1)
+			return e1000_configure_k1_ich8lan(hw, false);
+		return 0;
+	}
+
+	/* Change Kumeran K1 power down state from P0s to P1 */
+	fextnvm12 = er32(FEXTNVM12);
+	fextnvm12 &= ~E1000_FEXTNVM12_PHYPD_CTRL_MASK;
+	fextnvm12 |= E1000_FEXTNVM12_PHYPD_CTRL_P1;
+	ew32(FEXTNVM12, fextnvm12);
+
+	/* Wait for the interface the settle */
+	usleep_range(1000, 1100);
+	if (hw->adapter->flags2 & FLAG2_DISABLE_K1)
+		return e1000_configure_k1_ich8lan(hw, false);
+
+	/* Change K1 exit timeout */
+	ret_val = e1e_rphy_locked(hw, I217_PHY_TIMEOUTS_REG,
+				  &phy_timeout);
+	if (ret_val)
+		return ret_val;
+
+	phy_timeout &= ~I217_PHY_TIMEOUTS_K1_EXIT_TO_MASK;
+	phy_timeout |= 0xF00;
+
+	return e1e_wphy_locked(hw, I217_PHY_TIMEOUTS_REG,
+				  phy_timeout);
+}
+
+/**
  *  e1000_init_phy_workarounds_pchlan - PHY initialization workarounds
  *  @hw: pointer to the HW structure
  *
@@ -327,15 +373,22 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
 	 * LANPHYPC Value bit to force the interconnect to PCIe mode.
 	 */
 	switch (hw->mac.type) {
+	case e1000_pch_mtp:
+	case e1000_pch_lnp:
+	case e1000_pch_ptp:
+	case e1000_pch_nvp:
+		/* At this point the PHY might be inaccessible so don't
+		 * propagate the failure
+		 */
+		if (e1000_reconfigure_k1_params(hw))
+			e_dbg("Failed to reconfigure K1 parameters\n");
+
+		fallthrough;
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
-	case e1000_pch_mtp:
-	case e1000_pch_lnp:
-	case e1000_pch_ptp:
-	case e1000_pch_nvp:
 		if (e1000_phy_is_accessible_pchlan(hw))
 			break;
 
@@ -419,8 +472,20 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
 		 *  the PHY is in.
 		 */
 		ret_val = hw->phy.ops.check_reset_block(hw);
-		if (ret_val)
+		if (ret_val) {
 			e_err("ME blocked access to PHY after reset\n");
+			goto out;
+		}
+
+		if (hw->mac.type >= e1000_pch_mtp) {
+			ret_val = hw->phy.ops.acquire(hw);
+			if (ret_val) {
+				e_err("Failed to reconfigure K1 parameters\n");
+				goto out;
+			}
+			ret_val = e1000_reconfigure_k1_params(hw);
+			hw->phy.ops.release(hw);
+		}
 	}
 
 out:
@@ -4216,6 +4281,8 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw)
 			ret_val = e1000e_update_nvm_checksum(hw);
 			if (ret_val)
 				return ret_val;
+		} else if (hw->mac.type == e1000_pch_tgp) {
+			return 0;
 		}
 	}
 
@@ -4888,6 +4955,16 @@ static s32 e1000_init_hw_ich8lan(struct e1000_hw *hw)
 	u16 i;
 
 	e1000_initialize_hw_bits_ich8lan(hw);
+	ret_val = hw->phy.ops.acquire(hw);
+	if (ret_val)
+		return ret_val;
+
+	ret_val = e1000_reconfigure_k1_params(hw);
+	hw->phy.ops.release(hw);
+	if (ret_val) {
+		e_dbg("Error failed to reconfigure K1 parameters\n");
+		return ret_val;
+	}
 
 	/* Initialize identification LED */
 	ret_val = mac->ops.id_led_init(hw);
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h
index 2504b11c3169..5feb589a9b5f 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.h
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h
@@ -219,6 +219,10 @@
 #define I217_PLL_CLOCK_GATE_REG	PHY_REG(772, 28)
 #define I217_PLL_CLOCK_GATE_MASK	0x07FF
 
+/* PHY Timeouts */
+#define I217_PHY_TIMEOUTS_REG                   PHY_REG(770, 21)
+#define I217_PHY_TIMEOUTS_K1_EXIT_TO_MASK       0x0FC0
+
 #define SW_FLAG_TIMEOUT		1000	/* SW Semaphore flag timeout in ms */
 
 /* Inband Control */
diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c
index d7df2a0ed629..44249dd91bd6 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.c
+++ b/drivers/net/ethernet/intel/e1000e/mac.c
@@ -331,8 +331,21 @@ void e1000e_update_mc_addr_list_generic(struct e1000_hw *hw,
 	}
 
 	/* replace the entire MTA table */
-	for (i = hw->mac.mta_reg_count - 1; i >= 0; i--)
+	for (i = hw->mac.mta_reg_count - 1; i >= 0; i--) {
 		E1000_WRITE_REG_ARRAY(hw, E1000_MTA, i, hw->mac.mta_shadow[i]);
+
+		if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+			/*
+			 * Do not queue up too many posted writes to prevent
+			 * increased latency for other devices on the
+			 * interconnect. Flush after each 8th posted write,
+			 * to keep additional execution time low while still
+			 * preventing increased latency.
+			 */
+			if (!(i % 8) && i)
+				e1e_flush();
+		}
+	}
 	e1e_flush();
 }
 
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 286155efcedf..ddbe2f7d8112 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -2761,7 +2761,7 @@ static void e1000e_vlan_filter_disable(struct e1000_adapter *adapter)
 		rctl &= ~(E1000_RCTL_VFE | E1000_RCTL_CFIEN);
 		ew32(RCTL, rctl);
 
-		if (adapter->mng_vlan_id != (u16)E1000_MNG_VLAN_NONE) {
+		if (adapter->mng_vlan_id != E1000_MNG_VLAN_NONE) {
 			e1000_vlan_rx_kill_vid(netdev, htons(ETH_P_8021Q),
 					       adapter->mng_vlan_id);
 			adapter->mng_vlan_id = E1000_MNG_VLAN_NONE;
@@ -2828,7 +2828,7 @@ static void e1000_update_mng_vlan(struct e1000_adapter *adapter)
 		adapter->mng_vlan_id = vid;
 	}
 
-	if ((old_vid != (u16)E1000_MNG_VLAN_NONE) && (vid != old_vid))
+	if (old_vid != E1000_MNG_VLAN_NONE && vid != old_vid)
 		e1000_vlan_rx_kill_vid(netdev, htons(ETH_P_8021Q), old_vid);
 }
 
@@ -3534,9 +3534,6 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
-	case e1000_pch_mtp:
-	case e1000_pch_lnp:
-	case e1000_pch_ptp:
 	case e1000_pch_nvp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
 			/* Stable 24MHz frequency */
@@ -3552,6 +3549,17 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 			adapter->cc.shift = shift;
 		}
 		break;
+	case e1000_pch_mtp:
+	case e1000_pch_lnp:
+	case e1000_pch_ptp:
+		/* System firmware can misreport this value, so set it to a
+		 * stable 38400KHz frequency.
+		 */
+		incperiod = INCPERIOD_38400KHZ;
+		incvalue = INCVALUE_38400KHZ;
+		shift = INCVALUE_SHIFT_38400KHZ;
+		adapter->cc.shift = shift;
+		break;
 	case e1000_82574:
 	case e1000_82583:
 		/* Stable 25MHz frequency */
@@ -3574,6 +3582,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
  * e1000e_config_hwtstamp - configure the hwtstamp registers and enable/disable
  * @adapter: board private structure
  * @config: timestamp configuration
+ * @extack: netlink extended ACK for error report
  *
  * Outgoing time stamping can be enabled and disabled. Play nice and
  * disable it when requested, although it shouldn't cause any overhead
@@ -3587,7 +3596,8 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
  * exception of "all V2 events regardless of level 2 or 4".
  **/
 static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
-				  struct hwtstamp_config *config)
+				  struct kernel_hwtstamp_config *config,
+				  struct netlink_ext_ack *extack)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED;
@@ -3598,8 +3608,10 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 	bool is_l2 = false;
 	u32 regval;
 
-	if (!(adapter->flags & FLAG_HAS_HW_TIMESTAMP))
+	if (!(adapter->flags & FLAG_HAS_HW_TIMESTAMP)) {
+		NL_SET_ERR_MSG(extack, "No HW timestamp support");
 		return -EINVAL;
+	}
 
 	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
@@ -3608,6 +3620,7 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 	case HWTSTAMP_TX_ON:
 		break;
 	default:
+		NL_SET_ERR_MSG(extack, "Unsupported TX HW timestamp type");
 		return -ERANGE;
 	}
 
@@ -3681,6 +3694,7 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
+		NL_SET_ERR_MSG(extack, "Unsupported RX HW timestamp filter");
 		return -ERANGE;
 	}
 
@@ -3693,7 +3707,8 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 	ew32(TSYNCTXCTL, regval);
 	if ((er32(TSYNCTXCTL) & E1000_TSYNCTXCTL_ENABLED) !=
 	    (regval & E1000_TSYNCTXCTL_ENABLED)) {
-		e_err("Timesync Tx Control register not set as expected\n");
+		NL_SET_ERR_MSG(extack,
+			       "Timesync Tx Control register not set as expected");
 		return -EAGAIN;
 	}
 
@@ -3706,7 +3721,8 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 				 E1000_TSYNCRXCTL_TYPE_MASK)) !=
 	    (regval & (E1000_TSYNCRXCTL_ENABLED |
 		       E1000_TSYNCRXCTL_TYPE_MASK))) {
-		e_err("Timesync Rx Control register not set as expected\n");
+		NL_SET_ERR_MSG(extack,
+			       "Timesync Rx Control register not set as expected");
 		return -EAGAIN;
 	}
 
@@ -3901,6 +3917,7 @@ static void e1000e_systim_reset(struct e1000_adapter *adapter)
 {
 	struct ptp_clock_info *info = &adapter->ptp_clock_info;
 	struct e1000_hw *hw = &adapter->hw;
+	struct netlink_ext_ack extack = {};
 	unsigned long flags;
 	u32 timinca;
 	s32 ret_val;
@@ -3932,7 +3949,12 @@ static void e1000e_systim_reset(struct e1000_adapter *adapter)
 	spin_unlock_irqrestore(&adapter->systim_lock, flags);
 
 	/* restore the previous hwtstamp configuration settings */
-	e1000e_config_hwtstamp(adapter, &adapter->hwtstamp_config);
+	ret_val = e1000e_config_hwtstamp(adapter, &adapter->hwtstamp_config,
+					 &extack);
+	if (ret_val) {
+		if (extack._msg)
+			e_err("%s\n", extack._msg);
+	}
 }
 
 /**
@@ -4287,8 +4309,8 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset)
 
 	napi_synchronize(&adapter->napi);
 
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_info_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_info_timer);
 
 	spin_lock(&adapter->stats64_lock);
 	e1000e_update_stats(adapter);
@@ -4414,7 +4436,7 @@ u64 e1000e_read_systim(struct e1000_adapter *adapter,
  * e1000e_cyclecounter_read - read raw cycle counter (used by time counter)
  * @cc: cyclecounter structure
  **/
-static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
+static u64 e1000e_cyclecounter_read(struct cyclecounter *cc)
 {
 	struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter,
 						     cc);
@@ -4839,7 +4861,8 @@ static void e1000e_update_phy_task(struct work_struct *work)
  **/
 static void e1000_update_phy_info(struct timer_list *t)
 {
-	struct e1000_adapter *adapter = from_timer(adapter, t, phy_info_timer);
+	struct e1000_adapter *adapter = timer_container_of(adapter, t,
+							   phy_info_timer);
 
 	if (test_bit(__E1000_DOWN, &adapter->state))
 		return;
@@ -5175,7 +5198,8 @@ static void e1000e_check_82574_phy_workaround(struct e1000_adapter *adapter)
  **/
 static void e1000_watchdog(struct timer_list *t)
 {
-	struct e1000_adapter *adapter = from_timer(adapter, t, watchdog_timer);
+	struct e1000_adapter *adapter = timer_container_of(adapter, t,
+							   watchdog_timer);
 
 	/* Do the rest outside of interrupt context */
 	schedule_work(&adapter->watchdog_task);
@@ -6079,8 +6103,7 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
 	return 0;
 }
 
-static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
-			   int cmd)
+static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct mii_ioctl_data *data = if_mii(ifr);
@@ -6140,7 +6163,8 @@ static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
 /**
  * e1000e_hwtstamp_set - control hardware time stamping
  * @netdev: network interface device structure
- * @ifr: interface request
+ * @config: timestamp configuration
+ * @extack: netlink extended ACK report
  *
  * Outgoing time stamping can be enabled and disabled. Play nice and
  * disable it when requested, although it shouldn't cause any overhead
@@ -6153,20 +6177,18 @@ static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
  * specified. Matching the kind of event packet is not supported, with the
  * exception of "all V2 events regardless of level 2 or 4".
  **/
-static int e1000e_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
+static int e1000e_hwtstamp_set(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
-	struct hwtstamp_config config;
 	int ret_val;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	ret_val = e1000e_config_hwtstamp(adapter, &config);
+	ret_val = e1000e_config_hwtstamp(adapter, config, extack);
 	if (ret_val)
 		return ret_val;
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
@@ -6178,38 +6200,23 @@ static int e1000e_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 		 * by hardware so notify the caller the requested packets plus
 		 * some others are time stamped.
 		 */
-		config.rx_filter = HWTSTAMP_FILTER_SOME;
+		config->rx_filter = HWTSTAMP_FILTER_SOME;
 		break;
 	default:
 		break;
 	}
 
-	return copy_to_user(ifr->ifr_data, &config,
-			    sizeof(config)) ? -EFAULT : 0;
+	return 0;
 }
 
-static int e1000e_hwtstamp_get(struct net_device *netdev, struct ifreq *ifr)
+static int e1000e_hwtstamp_get(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *kernel_config)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 
-	return copy_to_user(ifr->ifr_data, &adapter->hwtstamp_config,
-			    sizeof(adapter->hwtstamp_config)) ? -EFAULT : 0;
-}
+	*kernel_config = adapter->hwtstamp_config;
 
-static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
-{
-	switch (cmd) {
-	case SIOCGMIIPHY:
-	case SIOCGMIIREG:
-	case SIOCSMIIREG:
-		return e1000_mii_ioctl(netdev, ifr, cmd);
-	case SIOCSHWTSTAMP:
-		return e1000e_hwtstamp_set(netdev, ifr);
-	case SIOCGHWTSTAMP:
-		return e1000e_hwtstamp_get(netdev, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
+	return 0;
 }
 
 static int e1000_init_phy_wakeup(struct e1000_adapter *adapter, u32 wufc)
@@ -7188,7 +7195,6 @@ static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev)
 			"Cannot re-enable PCI device after reset.\n");
 		result = PCI_ERS_RESULT_DISCONNECT;
 	} else {
-		pdev->state_saved = true;
 		pci_restore_state(pdev);
 		pci_set_master(pdev);
 
@@ -7346,9 +7352,11 @@ static const struct net_device_ops e1000e_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= e1000_netpoll,
 #endif
-	.ndo_set_features = e1000_set_features,
-	.ndo_fix_features = e1000_fix_features,
+	.ndo_set_features	= e1000_set_features,
+	.ndo_fix_features	= e1000_fix_features,
 	.ndo_features_check	= passthru_features_check,
+	.ndo_hwtstamp_get	= e1000e_hwtstamp_get,
+	.ndo_hwtstamp_set	= e1000e_hwtstamp_set,
 };
 
 /**
@@ -7666,6 +7674,9 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* init PTP hardware clock */
 	e1000e_ptp_init(adapter);
 
+	if (hw->mac.type >= e1000_pch_mtp)
+		adapter->flags2 |= FLAG2_DISABLE_K1;
+
 	/* reset the hardware with the new settings */
 	e1000e_reset(adapter);
 
@@ -7741,8 +7752,8 @@ static void e1000_remove(struct pci_dev *pdev)
 	 * from being rescheduled.
 	 */
 	set_bit(__E1000_DOWN, &adapter->state);
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_info_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_info_timer);
 
 	cancel_work_sync(&adapter->reset_task);
 	cancel_work_sync(&adapter->watchdog_task);
diff --git a/drivers/net/ethernet/intel/e1000e/nvm.c b/drivers/net/ethernet/intel/e1000e/nvm.c
index e609f4df86f4..4bde1c9de1b9 100644
--- a/drivers/net/ethernet/intel/e1000e/nvm.c
+++ b/drivers/net/ethernet/intel/e1000e/nvm.c
@@ -558,7 +558,13 @@ s32 e1000e_validate_nvm_checksum_generic(struct e1000_hw *hw)
 		checksum += nvm_data;
 	}
 
-	if (checksum != (u16)NVM_SUM) {
+	if (hw->mac.type == e1000_pch_tgp &&
+	    nvm_data == NVM_CHECKSUM_UNINITIALIZED) {
+		e_dbg("Uninitialized NVM Checksum on TGP platform - ignoring\n");
+		return 0;
+	}
+
+	if (checksum != NVM_SUM) {
 		e_dbg("NVM Checksum Invalid\n");
 		return -E1000_ERR_NVM;
 	}
@@ -588,7 +594,7 @@ s32 e1000e_update_nvm_checksum_generic(struct e1000_hw *hw)
 		}
 		checksum += nvm_data;
 	}
-	checksum = (u16)NVM_SUM - checksum;
+	checksum = NVM_SUM - checksum;
 	ret_val = e1000_write_nvm(hw, NVM_CHECKSUM_REG, 1, &checksum);
 	if (ret_val)
 		e_dbg("NVM Write Error while updating checksum.\n");
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 89d57dd911dc..ec39e35f3857 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -229,14 +229,11 @@ static void e1000e_systim_overflow_work(struct work_struct *work)
 						     systim_overflow_work.work);
 	struct e1000_hw *hw = &adapter->hw;
 	struct timespec64 ts;
-	u64 ns;
 
 	/* Update the timecounter */
-	ns = timecounter_read(&adapter->tc);
+	ts = ns_to_timespec64(timecounter_read(&adapter->tc));
 
-	ts = ns_to_timespec64(ns);
-	e_dbg("SYSTIM overflow check at %lld.%09lu\n",
-	      (long long) ts.tv_sec, ts.tv_nsec);
+	e_dbg("SYSTIM overflow check at %ptSp\n", &ts);
 
 	schedule_delayed_work(&adapter->systim_overflow_work,
 			      E1000_SYSTIM_OVERFLOW_PERIOD);
@@ -295,15 +292,17 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
-	case e1000_pch_mtp:
-	case e1000_pch_lnp:
-	case e1000_pch_ptp:
 	case e1000_pch_nvp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
 			adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
 		else
 			adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
 		break;
+	case e1000_pch_mtp:
+	case e1000_pch_lnp:
+	case e1000_pch_ptp:
+		adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
+		break;
 	case e1000_82574:
 	case e1000_82583:
 		adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
index 6119a4108838..65a2816142d9 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -189,13 +189,14 @@ struct fm10k_q_vector {
 	struct fm10k_ring_container rx, tx;
 
 	struct napi_struct napi;
+	struct rcu_head rcu;	/* to avoid race with update stats on free */
+
 	cpumask_t affinity_mask;
 	char name[IFNAMSIZ + 9];
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dbg_q_vector;
 #endif /* CONFIG_DEBUG_FS */
-	struct rcu_head rcu;	/* to avoid race with update stats on free */
 
 	/* for dynamic allocation of rings associated with this q_vector */
 	struct fm10k_ring ring[] ____cacheline_internodealigned_in_smp;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.c b/drivers/net/ethernet/intel/fm10k/fm10k_common.c
index f51a63fca513..1f919a50c765 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_common.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.c
@@ -447,17 +447,16 @@ void fm10k_update_hw_stats_q(struct fm10k_hw *hw, struct fm10k_hw_stats_q *q,
 /**
  *  fm10k_unbind_hw_stats_q - Unbind the queue counters from their queues
  *  @q: pointer to the ring of hardware statistics queue
- *  @idx: index pointing to the start of the ring iteration
  *  @count: number of queues to iterate over
  *
  *  Function invalidates the index values for the queues so any updates that
  *  may have happened are ignored and the base for the queue stats is reset.
  **/
-void fm10k_unbind_hw_stats_q(struct fm10k_hw_stats_q *q, u32 idx, u32 count)
+void fm10k_unbind_hw_stats_q(struct fm10k_hw_stats_q *q, u32 count)
 {
 	u32 i;
 
-	for (i = 0; i < count; i++, idx++, q++) {
+	for (i = 0; i < count; i++, q++) {
 		q->rx_stats_idx = 0;
 		q->tx_stats_idx = 0;
 	}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.h b/drivers/net/ethernet/intel/fm10k/fm10k_common.h
index 4c48fb73b3e7..13fca6a91a01 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_common.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.h
@@ -43,6 +43,6 @@ u32 fm10k_read_hw_stats_32b(struct fm10k_hw *hw, u32 addr,
 void fm10k_update_hw_stats_q(struct fm10k_hw *hw, struct fm10k_hw_stats_q *q,
 			     u32 idx, u32 count);
 #define fm10k_unbind_hw_stats_32b(s) ((s)->base_h = 0)
-void fm10k_unbind_hw_stats_q(struct fm10k_hw_stats_q *q, u32 idx, u32 count);
+void fm10k_unbind_hw_stats_q(struct fm10k_hw_stats_q *q, u32 count);
 s32 fm10k_get_host_state_generic(struct fm10k_hw *hw, bool *host_ready);
 #endif /* _FM10K_COMMON_H_ */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
index 1bc5b6c0b897..76e42abca965 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
@@ -560,7 +560,7 @@ static int fm10k_set_ringparam(struct net_device *netdev,
 
 	/* allocate temporary buffer to store rings in */
 	i = max_t(int, interface->num_tx_queues, interface->num_rx_queues);
-	temp_ring = vmalloc(array_size(i, sizeof(struct fm10k_ring)));
+	temp_ring = vmalloc_array(i, sizeof(struct fm10k_ring));
 
 	if (!temp_ring) {
 		err = -ENOMEM;
@@ -691,9 +691,11 @@ static int fm10k_set_coalesce(struct net_device *dev,
 	return 0;
 }
 
-static int fm10k_get_rss_hash_opts(struct fm10k_intfc *interface,
-				   struct ethtool_rxnfc *cmd)
+static int fm10k_get_rssh_fields(struct net_device *dev,
+				 struct ethtool_rxfh_fields *cmd)
 {
+	struct fm10k_intfc *interface = netdev_priv(dev);
+
 	cmd->data = 0;
 
 	/* Report default options for RSS on fm10k */
@@ -732,30 +734,18 @@ static int fm10k_get_rss_hash_opts(struct fm10k_intfc *interface,
 	return 0;
 }
 
-static int fm10k_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
-			   u32 __always_unused *rule_locs)
+static u32 fm10k_get_rx_ring_count(struct net_device *dev)
 {
 	struct fm10k_intfc *interface = netdev_priv(dev);
-	int ret = -EOPNOTSUPP;
-
-	switch (cmd->cmd) {
-	case ETHTOOL_GRXRINGS:
-		cmd->data = interface->num_rx_queues;
-		ret = 0;
-		break;
-	case ETHTOOL_GRXFH:
-		ret = fm10k_get_rss_hash_opts(interface, cmd);
-		break;
-	default:
-		break;
-	}
 
-	return ret;
+	return interface->num_rx_queues;
 }
 
-static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface,
-				  struct ethtool_rxnfc *nfc)
+static int fm10k_set_rssh_fields(struct net_device *dev,
+				 const struct ethtool_rxfh_fields *nfc,
+				 struct netlink_ext_ack *extack)
 {
+	struct fm10k_intfc *interface = netdev_priv(dev);
 	int rss_ipv4_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
 				    interface->flags);
 	int rss_ipv6_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
@@ -871,22 +861,6 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface,
 	return 0;
 }
 
-static int fm10k_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
-{
-	struct fm10k_intfc *interface = netdev_priv(dev);
-	int ret = -EOPNOTSUPP;
-
-	switch (cmd->cmd) {
-	case ETHTOOL_SRXFH:
-		ret = fm10k_set_rss_hash_opt(interface, cmd);
-		break;
-	default:
-		break;
-	}
-
-	return ret;
-}
-
 static int fm10k_mbx_test(struct fm10k_intfc *interface, u64 *data)
 {
 	struct fm10k_hw *hw = &interface->hw;
@@ -1175,8 +1149,7 @@ static const struct ethtool_ops fm10k_ethtool_ops = {
 	.set_ringparam		= fm10k_set_ringparam,
 	.get_coalesce		= fm10k_get_coalesce,
 	.set_coalesce		= fm10k_set_coalesce,
-	.get_rxnfc		= fm10k_get_rxnfc,
-	.set_rxnfc		= fm10k_set_rxnfc,
+	.get_rx_ring_count	= fm10k_get_rx_ring_count,
 	.get_regs               = fm10k_get_regs,
 	.get_regs_len           = fm10k_get_regs_len,
 	.self_test		= fm10k_self_test,
@@ -1186,6 +1159,8 @@ static const struct ethtool_ops fm10k_ethtool_ops = {
 	.get_rxfh_key_size	= fm10k_get_rssrk_size,
 	.get_rxfh		= fm10k_get_rssh,
 	.set_rxfh		= fm10k_set_rssh,
+	.get_rxfh_fields	= fm10k_get_rssh_fields,
+	.set_rxfh_fields	= fm10k_set_rssh_fields,
 	.get_channels		= fm10k_get_channels,
 	.set_channels		= fm10k_set_channels,
 	.get_ts_info		= ethtool_op_get_ts_info,
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 142f07ca8bc0..b8c15b837fda 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -37,7 +37,7 @@ static int __init fm10k_init_module(void)
 	pr_info("%s\n", fm10k_copyright);
 
 	/* create driver workqueue */
-	fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
+	fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM | WQ_PERCPU, 0,
 					  fm10k_driver_name);
 	if (!fm10k_workqueue)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index 92de609b7218..d75b8a50413d 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -199,8 +199,8 @@ static void fm10k_start_service_event(struct fm10k_intfc *interface)
  **/
 static void fm10k_service_timer(struct timer_list *t)
 {
-	struct fm10k_intfc *interface = from_timer(interface, t,
-						   service_timer);
+	struct fm10k_intfc *interface = timer_container_of(interface, t,
+							   service_timer);
 
 	/* Reset the timer */
 	mod_timer(&interface->service_timer, (HZ * 2) + jiffies);
@@ -2245,7 +2245,7 @@ static void fm10k_remove(struct pci_dev *pdev)
 	struct fm10k_intfc *interface = pci_get_drvdata(pdev);
 	struct net_device *netdev = interface->netdev;
 
-	del_timer_sync(&interface->service_timer);
+	timer_delete_sync(&interface->service_timer);
 
 	fm10k_stop_service_event(interface);
 	fm10k_stop_macvlan_task(interface);
@@ -2423,12 +2423,6 @@ static pci_ers_result_t fm10k_io_slot_reset(struct pci_dev *pdev)
 	} else {
 		pci_set_master(pdev);
 		pci_restore_state(pdev);
-
-		/* After second error pci->state_saved is false, this
-		 * resets it so EEH doesn't break.
-		 */
-		pci_save_state(pdev);
-
 		pci_wake_from_d3(pdev, false);
 
 		result = PCI_ERS_RESULT_RECOVERED;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
index 98861cc6df7c..3394645a18fe 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
@@ -1180,126 +1180,6 @@ s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid)
 }
 
 /**
- *  fm10k_iov_msg_mac_vlan_pf - Message handler for MAC/VLAN request from VF
- *  @hw: Pointer to hardware structure
- *  @results: Pointer array to message, results[0] is pointer to message
- *  @mbx: Pointer to mailbox information structure
- *
- *  This function is a default handler for MAC/VLAN requests from the VF.
- *  The assumption is that in this case it is acceptable to just directly
- *  hand off the message from the VF to the underlying shared code.
- **/
-s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results,
-			      struct fm10k_mbx_info *mbx)
-{
-	struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx;
-	u8 mac[ETH_ALEN];
-	u32 *result;
-	int err = 0;
-	bool set;
-	u16 vlan;
-	u32 vid;
-
-	/* we shouldn't be updating rules on a disabled interface */
-	if (!FM10K_VF_FLAG_ENABLED(vf_info))
-		err = FM10K_ERR_PARAM;
-
-	if (!err && !!results[FM10K_MAC_VLAN_MSG_VLAN]) {
-		result = results[FM10K_MAC_VLAN_MSG_VLAN];
-
-		/* record VLAN id requested */
-		err = fm10k_tlv_attr_get_u32(result, &vid);
-		if (err)
-			return err;
-
-		set = !(vid & FM10K_VLAN_CLEAR);
-		vid &= ~FM10K_VLAN_CLEAR;
-
-		/* if the length field has been set, this is a multi-bit
-		 * update request. For multi-bit requests, simply disallow
-		 * them when the pf_vid has been set. In this case, the PF
-		 * should have already cleared the VLAN_TABLE, and if we
-		 * allowed them, it could allow a rogue VF to receive traffic
-		 * on a VLAN it was not assigned. In the single-bit case, we
-		 * need to modify requests for VLAN 0 to use the default PF or
-		 * SW vid when assigned.
-		 */
-
-		if (vid >> 16) {
-			/* prevent multi-bit requests when PF has
-			 * administratively set the VLAN for this VF
-			 */
-			if (vf_info->pf_vid)
-				return FM10K_ERR_PARAM;
-		} else {
-			err = fm10k_iov_select_vid(vf_info, (u16)vid);
-			if (err < 0)
-				return err;
-
-			vid = err;
-		}
-
-		/* update VSI info for VF in regards to VLAN table */
-		err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, set);
-	}
-
-	if (!err && !!results[FM10K_MAC_VLAN_MSG_MAC]) {
-		result = results[FM10K_MAC_VLAN_MSG_MAC];
-
-		/* record unicast MAC address requested */
-		err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
-		if (err)
-			return err;
-
-		/* block attempts to set MAC for a locked device */
-		if (is_valid_ether_addr(vf_info->mac) &&
-		    !ether_addr_equal(mac, vf_info->mac))
-			return FM10K_ERR_PARAM;
-
-		set = !(vlan & FM10K_VLAN_CLEAR);
-		vlan &= ~FM10K_VLAN_CLEAR;
-
-		err = fm10k_iov_select_vid(vf_info, vlan);
-		if (err < 0)
-			return err;
-
-		vlan = (u16)err;
-
-		/* notify switch of request for new unicast address */
-		err = hw->mac.ops.update_uc_addr(hw, vf_info->glort,
-						 mac, vlan, set, 0);
-	}
-
-	if (!err && !!results[FM10K_MAC_VLAN_MSG_MULTICAST]) {
-		result = results[FM10K_MAC_VLAN_MSG_MULTICAST];
-
-		/* record multicast MAC address requested */
-		err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
-		if (err)
-			return err;
-
-		/* verify that the VF is allowed to request multicast */
-		if (!(vf_info->vf_flags & FM10K_VF_FLAG_MULTI_ENABLED))
-			return FM10K_ERR_PARAM;
-
-		set = !(vlan & FM10K_VLAN_CLEAR);
-		vlan &= ~FM10K_VLAN_CLEAR;
-
-		err = fm10k_iov_select_vid(vf_info, vlan);
-		if (err < 0)
-			return err;
-
-		vlan = (u16)err;
-
-		/* notify switch of request for new multicast address */
-		err = hw->mac.ops.update_mc_addr(hw, vf_info->glort,
-						 mac, vlan, set);
-	}
-
-	return err;
-}
-
-/**
  *  fm10k_iov_supported_xcast_mode_pf - Determine best match for xcast mode
  *  @vf_info: VF info structure containing capability flags
  *  @mode: Requested xcast mode
@@ -1509,7 +1389,7 @@ static void fm10k_rebind_hw_stats_pf(struct fm10k_hw *hw,
 	fm10k_unbind_hw_stats_32b(&stats->nodesc_drop);
 
 	/* Unbind Queue Statistics */
-	fm10k_unbind_hw_stats_q(stats->q, 0, hw->mac.max_queues);
+	fm10k_unbind_hw_stats_q(stats->q, hw->mac.max_queues);
 
 	/* Reinitialize bases for all stats */
 	fm10k_update_hw_stats_pf(hw, stats);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
index 8e814df709d2..ad3696893cb1 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
@@ -99,8 +99,6 @@ extern const struct fm10k_tlv_attr fm10k_err_msg_attr[];
 
 s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid);
 s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *);
-s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *, u32 **,
-			      struct fm10k_mbx_info *);
 s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *, u32 **,
 				 struct fm10k_mbx_info *);
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
index 7fb1961f2921..6861a0bdc14e 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
@@ -465,7 +465,7 @@ static void fm10k_rebind_hw_stats_vf(struct fm10k_hw *hw,
 				     struct fm10k_hw_stats *stats)
 {
 	/* Unbind Queue Statistics */
-	fm10k_unbind_hw_stats_q(stats->q, 0, hw->mac.max_queues);
+	fm10k_unbind_hw_stats_q(stats->q, hw->mac.max_queues);
 
 	/* Reinitialize bases for all stats */
 	fm10k_update_hw_stats_vf(hw, stats);
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index d4255c2706fa..d2d03db2acec 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -88,6 +88,7 @@ enum i40e_state {
 	__I40E_SERVICE_SCHED,
 	__I40E_ADMINQ_EVENT_PENDING,
 	__I40E_MDD_EVENT_PENDING,
+	__I40E_MDD_VF_PRINT_PENDING,
 	__I40E_VFLR_EVENT_PENDING,
 	__I40E_RESET_RECOVERY_PENDING,
 	__I40E_TIMEOUT_RECOVERY_PENDING,
@@ -191,6 +192,7 @@ enum i40e_pf_flags {
 	 */
 	I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA,
 	I40E_FLAG_VF_VLAN_PRUNING_ENA,
+	I40E_FLAG_MDD_AUTO_RESET_VF,
 	I40E_PF_FLAGS_NBITS,		/* must be last */
 };
 
@@ -546,6 +548,7 @@ struct i40e_pf {
 	u16 empr_count; /* EMP reset count */
 	u16 pfr_count; /* PF reset count */
 	u16 sw_int_count; /* SW interrupt count */
+	u32 link_down_events;
 
 	struct mutex switch_mutex;
 	u16 lan_vsi;       /* our default LAN VSI */
@@ -571,8 +574,12 @@ struct i40e_pf {
 	struct i40e_vf *vf;
 	int num_alloc_vfs;	/* actual number of VFs allocated */
 	u32 vf_aq_requests;
+	/* If set to non-zero, the device uses this value
+	 * as maximum number of MAC filters per VF.
+	 */
+	u32 max_mac_per_vf;
 	u32 arq_overflows;	/* Not fatal, possibly indicative of problems */
-
+	struct ratelimit_state mdd_message_rate_limit;
 	/* DCBx/DCBNL capability for PF that indicates
 	 * whether DCBx is managed by firmware or host
 	 * based agent (LLDPAD). Also, indicates what
@@ -658,7 +665,7 @@ struct i40e_pf {
 	struct ptp_clock_info ptp_caps;
 	struct sk_buff *ptp_tx_skb;
 	unsigned long ptp_tx_start;
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 	struct timespec64 ptp_prev_hw_time;
 	struct work_struct ptp_extts0_work;
 	ktime_t ptp_reset_start;
@@ -943,6 +950,7 @@ struct i40e_q_vector {
 	u16 reg_idx;		/* register index of the interrupt */
 
 	struct napi_struct napi;
+	struct rcu_head rcu;	/* to avoid race with update stats on free */
 
 	struct i40e_ring_container rx;
 	struct i40e_ring_container tx;
@@ -953,7 +961,6 @@ struct i40e_q_vector {
 	cpumask_t affinity_mask;
 	struct irq_affinity_notify affinity_notify;
 
-	struct rcu_head rcu;	/* to avoid race with update stats on free */
 	char name[I40E_INT_NAME_STR_LEN];
 	bool arm_wb_state;
 	bool in_busy_poll;
@@ -1189,7 +1196,6 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
 		      struct i40e_fdir_filter *input, bool add);
 void i40e_fdir_check_and_reenable(struct i40e_pf *pf);
 u32 i40e_get_current_fd_count(struct i40e_pf *pf);
-u32 i40e_get_cur_guaranteed_fd_count(struct i40e_pf *pf);
 u32 i40e_get_current_atr_cnt(struct i40e_pf *pf);
 u32 i40e_get_global_fd_count(struct i40e_pf *pf);
 bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features);
@@ -1197,7 +1203,6 @@ void i40e_set_ethtool_ops(struct net_device *netdev);
 struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
 					const u8 *macaddr, s16 vlan);
 void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f);
-void i40e_del_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan);
 int i40e_sync_vsi_filters(struct i40e_vsi *vsi);
 struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 				u16 uplink, u32 param1);
@@ -1277,7 +1282,8 @@ struct i40e_mac_filter *i40e_add_mac_filter(struct i40e_vsi *vsi,
 					    const u8 *macaddr);
 int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr);
 bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi);
-int i40e_count_filters(struct i40e_vsi *vsi);
+int i40e_count_all_filters(struct i40e_vsi *vsi);
+int i40e_count_active_filters(struct i40e_vsi *vsi);
 struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, const u8 *macaddr);
 void i40e_vlan_stripping_enable(struct i40e_vsi *vsi);
 static inline bool i40e_is_sw_dcb(struct i40e_pf *pf)
@@ -1302,8 +1308,11 @@ void i40e_ptp_tx_hang(struct i40e_pf *pf);
 void i40e_ptp_tx_hwtstamp(struct i40e_pf *pf);
 void i40e_ptp_rx_hwtstamp(struct i40e_pf *pf, struct sk_buff *skb, u8 index);
 void i40e_ptp_set_increment(struct i40e_pf *pf);
-int i40e_ptp_set_ts_config(struct i40e_pf *pf, struct ifreq *ifr);
-int i40e_ptp_get_ts_config(struct i40e_pf *pf, struct ifreq *ifr);
+int i40e_ptp_hwtstamp_get(struct net_device *netdev,
+			  struct kernel_hwtstamp_config *config);
+int i40e_ptp_hwtstamp_set(struct net_device *netdev,
+			  struct kernel_hwtstamp_config *config,
+			  struct netlink_ext_ack *extack);
 void i40e_ptp_save_hw_time(struct i40e_pf *pf);
 void i40e_ptp_restore_hw_time(struct i40e_pf *pf);
 void i40e_ptp_init(struct i40e_pf *pf);
@@ -1313,7 +1322,6 @@ int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset);
 int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi);
 int i40e_get_partition_bw_setting(struct i40e_pf *pf);
 int i40e_set_partition_bw_setting(struct i40e_pf *pf);
-int i40e_commit_partition_bw_setting(struct i40e_pf *pf);
 void i40e_print_link_message(struct i40e_vsi *vsi, bool isup);
 
 void i40e_set_fec_in_flags(u8 fec_cfg, unsigned long *flags);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index f73f5930fc58..096ec46bb619 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -18,7 +18,7 @@ static int i40e_alloc_adminq_asq_ring(struct i40e_hw *hw)
 
 	ret_code = i40e_allocate_dma_mem(hw, &hw->aq.asq.desc_buf,
 					 (hw->aq.num_asq_entries *
-					 sizeof(struct i40e_aq_desc)),
+					 sizeof(struct libie_aq_desc)),
 					 I40E_ADMINQ_DESC_ALIGNMENT);
 	if (ret_code)
 		return ret_code;
@@ -44,7 +44,7 @@ static int i40e_alloc_adminq_arq_ring(struct i40e_hw *hw)
 
 	ret_code = i40e_allocate_dma_mem(hw, &hw->aq.arq.desc_buf,
 					 (hw->aq.num_arq_entries *
-					 sizeof(struct i40e_aq_desc)),
+					 sizeof(struct libie_aq_desc)),
 					 I40E_ADMINQ_DESC_ALIGNMENT);
 
 	return ret_code;
@@ -80,7 +80,7 @@ static void i40e_free_adminq_arq(struct i40e_hw *hw)
  **/
 static int i40e_alloc_arq_bufs(struct i40e_hw *hw)
 {
-	struct i40e_aq_desc *desc;
+	struct libie_aq_desc *desc;
 	struct i40e_dma_mem *bi;
 	int ret_code;
 	int i;
@@ -108,9 +108,9 @@ static int i40e_alloc_arq_bufs(struct i40e_hw *hw)
 		/* now configure the descriptors for use */
 		desc = I40E_ADMINQ_DESC(hw->aq.arq, i);
 
-		desc->flags = cpu_to_le16(I40E_AQ_FLAG_BUF);
+		desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_BUF);
 		if (hw->aq.arq_buf_size > I40E_AQ_LARGE_BUF)
-			desc->flags |= cpu_to_le16(I40E_AQ_FLAG_LB);
+			desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
 		desc->opcode = 0;
 		/* This is in accordance with Admin queue design, there is no
 		 * register for buffer size configuration
@@ -119,12 +119,12 @@ static int i40e_alloc_arq_bufs(struct i40e_hw *hw)
 		desc->retval = 0;
 		desc->cookie_high = 0;
 		desc->cookie_low = 0;
-		desc->params.external.addr_high =
+		desc->params.generic.addr_high =
 			cpu_to_le32(upper_32_bits(bi->pa));
-		desc->params.external.addr_low =
+		desc->params.generic.addr_low =
 			cpu_to_le32(lower_32_bits(bi->pa));
-		desc->params.external.param0 = 0;
-		desc->params.external.param1 = 0;
+		desc->params.generic.param0 = 0;
+		desc->params.generic.param1 = 0;
 	}
 
 alloc_arq_bufs:
@@ -691,8 +691,8 @@ static u16 i40e_clean_asq(struct i40e_hw *hw)
 	struct i40e_adminq_ring *asq = &(hw->aq.asq);
 	struct i40e_asq_cmd_details *details;
 	u16 ntc = asq->next_to_clean;
-	struct i40e_aq_desc desc_cb;
-	struct i40e_aq_desc *desc;
+	struct libie_aq_desc desc_cb;
+	struct libie_aq_desc *desc;
 
 	desc = I40E_ADMINQ_DESC(*asq, ntc);
 	details = I40E_ADMINQ_DETAILS(*asq, ntc);
@@ -750,7 +750,7 @@ static bool i40e_asq_done(struct i40e_hw *hw)
  **/
 static int
 i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
-				  struct i40e_aq_desc *desc,
+				  struct libie_aq_desc *desc,
 				  void *buff, /* can be NULL */
 				  u16  buff_size,
 				  struct i40e_asq_cmd_details *cmd_details,
@@ -758,7 +758,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 {
 	struct i40e_dma_mem *dma_buff = NULL;
 	struct i40e_asq_cmd_details *details;
-	struct i40e_aq_desc *desc_on_ring;
+	struct libie_aq_desc *desc_on_ring;
 	bool cmd_completed = false;
 	u16  retval = 0;
 	int status = 0;
@@ -771,7 +771,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 		goto asq_send_command_error;
 	}
 
-	hw->aq.asq_last_status = I40E_AQ_RC_OK;
+	hw->aq.asq_last_status = LIBIE_AQ_RC_OK;
 
 	val = rd32(hw, I40E_PF_ATQH);
 	if (val >= hw->aq.num_asq_entries) {
@@ -851,9 +851,9 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 		/* Update the address values in the desc with the pa value
 		 * for respective buffer
 		 */
-		desc_on_ring->params.external.addr_high =
+		desc_on_ring->params.generic.addr_high =
 				cpu_to_le32(upper_32_bits(dma_buff->pa));
-		desc_on_ring->params.external.addr_low =
+		desc_on_ring->params.generic.addr_low =
 				cpu_to_le32(lower_32_bits(dma_buff->pa));
 	}
 
@@ -905,13 +905,13 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 			retval &= 0xff;
 		}
 		cmd_completed = true;
-		if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_OK)
+		if ((enum libie_aq_err)retval == LIBIE_AQ_RC_OK)
 			status = 0;
-		else if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_EBUSY)
+		else if ((enum libie_aq_err)retval == LIBIE_AQ_RC_EBUSY)
 			status = -EBUSY;
 		else
 			status = -EIO;
-		hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
+		hw->aq.asq_last_status = (enum libie_aq_err)retval;
 	}
 
 	i40e_debug(hw, I40E_DEBUG_AQ_COMMAND,
@@ -954,7 +954,7 @@ asq_send_command_error:
  **/
 int
 i40e_asq_send_command_atomic(struct i40e_hw *hw,
-			     struct i40e_aq_desc *desc,
+			     struct libie_aq_desc *desc,
 			     void *buff, /* can be NULL */
 			     u16  buff_size,
 			     struct i40e_asq_cmd_details *cmd_details,
@@ -972,7 +972,7 @@ i40e_asq_send_command_atomic(struct i40e_hw *hw,
 }
 
 int
-i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc,
+i40e_asq_send_command(struct i40e_hw *hw, struct libie_aq_desc *desc,
 		      void *buff, /* can be NULL */ u16  buff_size,
 		      struct i40e_asq_cmd_details *cmd_details)
 {
@@ -996,12 +996,12 @@ i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc,
  **/
 int
 i40e_asq_send_command_atomic_v2(struct i40e_hw *hw,
-				struct i40e_aq_desc *desc,
+				struct libie_aq_desc *desc,
 				void *buff, /* can be NULL */
 				u16  buff_size,
 				struct i40e_asq_cmd_details *cmd_details,
 				bool is_atomic_context,
-				enum i40e_admin_queue_err *aq_status)
+				enum libie_aq_err *aq_status)
 {
 	int status;
 
@@ -1016,16 +1016,6 @@ i40e_asq_send_command_atomic_v2(struct i40e_hw *hw,
 	return status;
 }
 
-int
-i40e_asq_send_command_v2(struct i40e_hw *hw, struct i40e_aq_desc *desc,
-			 void *buff, /* can be NULL */ u16  buff_size,
-			 struct i40e_asq_cmd_details *cmd_details,
-			 enum i40e_admin_queue_err *aq_status)
-{
-	return i40e_asq_send_command_atomic_v2(hw, desc, buff, buff_size,
-					       cmd_details, true, aq_status);
-}
-
 /**
  *  i40e_fill_default_direct_cmd_desc - AQ descriptor helper function
  *  @desc:     pointer to the temp descriptor (non DMA mem)
@@ -1033,13 +1023,13 @@ i40e_asq_send_command_v2(struct i40e_hw *hw, struct i40e_aq_desc *desc,
  *
  *  Fill the desc with default values
  **/
-void i40e_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc,
+void i40e_fill_default_direct_cmd_desc(struct libie_aq_desc *desc,
 				       u16 opcode)
 {
 	/* zero out the desc */
-	memset((void *)desc, 0, sizeof(struct i40e_aq_desc));
+	memset((void *)desc, 0, sizeof(struct libie_aq_desc));
 	desc->opcode = cpu_to_le16(opcode);
-	desc->flags = cpu_to_le16(I40E_AQ_FLAG_SI);
+	desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_SI);
 }
 
 /**
@@ -1057,7 +1047,7 @@ int i40e_clean_arq_element(struct i40e_hw *hw,
 			   u16 *pending)
 {
 	u16 ntc = hw->aq.arq.next_to_clean;
-	struct i40e_aq_desc *desc;
+	struct libie_aq_desc *desc;
 	struct i40e_dma_mem *bi;
 	int ret_code = 0;
 	u16 desc_idx;
@@ -1091,9 +1081,9 @@ int i40e_clean_arq_element(struct i40e_hw *hw,
 	desc_idx = ntc;
 
 	hw->aq.arq_last_status =
-		(enum i40e_admin_queue_err)le16_to_cpu(desc->retval);
+		(enum libie_aq_err)le16_to_cpu(desc->retval);
 	flags = le16_to_cpu(desc->flags);
-	if (flags & I40E_AQ_FLAG_ERR) {
+	if (flags & LIBIE_AQ_FLAG_ERR) {
 		ret_code = -EIO;
 		i40e_debug(hw,
 			   I40E_DEBUG_AQ_MESSAGE,
@@ -1117,14 +1107,14 @@ int i40e_clean_arq_element(struct i40e_hw *hw,
 	 * size
 	 */
 	bi = &hw->aq.arq.r.arq_bi[ntc];
-	memset((void *)desc, 0, sizeof(struct i40e_aq_desc));
+	memset((void *)desc, 0, sizeof(struct libie_aq_desc));
 
-	desc->flags = cpu_to_le16(I40E_AQ_FLAG_BUF);
+	desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_BUF);
 	if (hw->aq.arq_buf_size > I40E_AQ_LARGE_BUF)
-		desc->flags |= cpu_to_le16(I40E_AQ_FLAG_LB);
+		desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
 	desc->datalen = cpu_to_le16((u16)bi->size);
-	desc->params.external.addr_high = cpu_to_le32(upper_32_bits(bi->pa));
-	desc->params.external.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
+	desc->params.generic.addr_high = cpu_to_le32(upper_32_bits(bi->pa));
+	desc->params.generic.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
 
 	/* set tail = the last cleaned desc index. */
 	wr32(hw, I40E_PF_ARQT, ntc);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
index 55b5bb884d73..1be97a3a86ce 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
@@ -9,7 +9,7 @@
 #include "i40e_adminq_cmd.h"
 
 #define I40E_ADMINQ_DESC(R, i)   \
-	(&(((struct i40e_aq_desc *)((R).desc_buf.va))[i]))
+	(&(((struct libie_aq_desc *)((R).desc_buf.va))[i]))
 
 #define I40E_ADMINQ_DESC_ALIGNMENT 4096
 
@@ -39,7 +39,7 @@ struct i40e_asq_cmd_details {
 	u16 flags_dis;
 	bool async;
 	bool postpone;
-	struct i40e_aq_desc *wb_desc;
+	struct libie_aq_desc *wb_desc;
 };
 
 #define I40E_ADMINQ_DETAILS(R, i)   \
@@ -47,7 +47,7 @@ struct i40e_asq_cmd_details {
 
 /* ARQ event information */
 struct i40e_arq_event_info {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 msg_len;
 	u16 buf_len;
 	u8 *msg_buf;
@@ -72,8 +72,8 @@ struct i40e_adminq_info {
 	struct mutex arq_mutex; /* Receive queue lock */
 
 	/* last status values on send and receive queues */
-	enum i40e_admin_queue_err asq_last_status;
-	enum i40e_admin_queue_err arq_last_status;
+	enum libie_aq_err asq_last_status;
+	enum libie_aq_err arq_last_status;
 };
 
 /**
@@ -119,7 +119,7 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc)
 #define I40E_AQ_LARGE_BUF	512
 #define I40E_ASQ_CMD_TIMEOUT	250000  /* usecs */
 
-void i40e_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc,
+void i40e_fill_default_direct_cmd_desc(struct libie_aq_desc *desc,
 				       u16 opcode);
 
 #endif /* _I40E_ADMINQ_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index c8f35d4de271..cc02a85ad42b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -4,6 +4,8 @@
 #ifndef _I40E_ADMINQ_CMD_H_
 #define _I40E_ADMINQ_CMD_H_
 
+#include <linux/net/intel/libie/adminq.h>
+
 #include <linux/bits.h>
 #include <linux/types.h>
 
@@ -30,75 +32,6 @@
 /* API version 1.10 for X722 devices adds ability to request FEC encoding */
 #define I40E_MINOR_VER_FW_REQUEST_FEC_X722 0x000A
 
-struct i40e_aq_desc {
-	__le16 flags;
-	__le16 opcode;
-	__le16 datalen;
-	__le16 retval;
-	__le32 cookie_high;
-	__le32 cookie_low;
-	union {
-		struct {
-			__le32 param0;
-			__le32 param1;
-			__le32 param2;
-			__le32 param3;
-		} internal;
-		struct {
-			__le32 param0;
-			__le32 param1;
-			__le32 addr_high;
-			__le32 addr_low;
-		} external;
-		u8 raw[16];
-	} params;
-};
-
-/* Flags sub-structure
- * |0  |1  |2  |3  |4  |5  |6  |7  |8  |9  |10 |11 |12 |13 |14 |15 |
- * |DD |CMP|ERR|VFE| * *  RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE |
- */
-
-/* command flags and offsets*/
-#define I40E_AQ_FLAG_ERR_SHIFT	2
-#define I40E_AQ_FLAG_LB_SHIFT	9
-#define I40E_AQ_FLAG_RD_SHIFT	10
-#define I40E_AQ_FLAG_BUF_SHIFT	12
-#define I40E_AQ_FLAG_SI_SHIFT	13
-
-#define I40E_AQ_FLAG_ERR	BIT(I40E_AQ_FLAG_ERR_SHIFT) /* 0x4    */
-#define I40E_AQ_FLAG_LB		BIT(I40E_AQ_FLAG_LB_SHIFT)  /* 0x200  */
-#define I40E_AQ_FLAG_RD		BIT(I40E_AQ_FLAG_RD_SHIFT)  /* 0x400  */
-#define I40E_AQ_FLAG_BUF	BIT(I40E_AQ_FLAG_BUF_SHIFT) /* 0x1000 */
-#define I40E_AQ_FLAG_SI		BIT(I40E_AQ_FLAG_SI_SHIFT)  /* 0x2000 */
-
-/* error codes */
-enum i40e_admin_queue_err {
-	I40E_AQ_RC_OK		= 0,  /* success */
-	I40E_AQ_RC_EPERM	= 1,  /* Operation not permitted */
-	I40E_AQ_RC_ENOENT	= 2,  /* No such element */
-	I40E_AQ_RC_ESRCH	= 3,  /* Bad opcode */
-	I40E_AQ_RC_EINTR	= 4,  /* operation interrupted */
-	I40E_AQ_RC_EIO		= 5,  /* I/O error */
-	I40E_AQ_RC_ENXIO	= 6,  /* No such resource */
-	I40E_AQ_RC_E2BIG	= 7,  /* Arg too long */
-	I40E_AQ_RC_EAGAIN	= 8,  /* Try again */
-	I40E_AQ_RC_ENOMEM	= 9,  /* Out of memory */
-	I40E_AQ_RC_EACCES	= 10, /* Permission denied */
-	I40E_AQ_RC_EFAULT	= 11, /* Bad address */
-	I40E_AQ_RC_EBUSY	= 12, /* Device or resource busy */
-	I40E_AQ_RC_EEXIST	= 13, /* object already exists */
-	I40E_AQ_RC_EINVAL	= 14, /* Invalid argument */
-	I40E_AQ_RC_ENOTTY	= 15, /* Not a typewriter */
-	I40E_AQ_RC_ENOSPC	= 16, /* No space left or alloc failure */
-	I40E_AQ_RC_ENOSYS	= 17, /* Function not implemented */
-	I40E_AQ_RC_ERANGE	= 18, /* Parameter out of range */
-	I40E_AQ_RC_EFLUSHED	= 19, /* Cmd flushed due to prev cmd error */
-	I40E_AQ_RC_BAD_ADDR	= 20, /* Descriptor contains a bad pointer */
-	I40E_AQ_RC_EMODE	= 21, /* Op not allowed in current dev mode */
-	I40E_AQ_RC_EFBIG	= 22, /* File too large */
-};
-
 /* Admin Queue command opcodes */
 enum i40e_admin_queue_opc {
 	/* aq commands */
@@ -320,21 +253,6 @@ struct i40e_aqc_get_version {
 	__le16 api_minor;
 };
 
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_version);
-
-/* Send driver version (indirect 0x0002) */
-struct i40e_aqc_driver_version {
-	u8	driver_major_ver;
-	u8	driver_minor_ver;
-	u8	driver_build_ver;
-	u8	driver_subbuild_ver;
-	u8	reserved[4];
-	__le32	address_high;
-	__le32	address_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_driver_version);
-
 /* Queue Shutdown (direct 0x0003) */
 struct i40e_aqc_queue_shutdown {
 	__le32	driver_unloading;
@@ -352,75 +270,6 @@ struct i40e_aqc_set_pf_context {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_set_pf_context);
 
-/* Request resource ownership (direct 0x0008)
- * Release resource ownership (direct 0x0009)
- */
-struct i40e_aqc_request_resource {
-	__le16	resource_id;
-	__le16	access_type;
-	__le32	timeout;
-	__le32	resource_number;
-	u8	reserved[4];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_request_resource);
-
-/* Get function capabilities (indirect 0x000A)
- * Get device capabilities (indirect 0x000B)
- */
-struct i40e_aqc_list_capabilites {
-	u8 command_flags;
-	u8 pf_index;
-	u8 reserved[2];
-	__le32 count;
-	__le32 addr_high;
-	__le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_list_capabilites);
-
-struct i40e_aqc_list_capabilities_element_resp {
-	__le16	id;
-	u8	major_rev;
-	u8	minor_rev;
-	__le32	number;
-	__le32	logical_id;
-	__le32	phys_id;
-	u8	reserved[16];
-};
-
-/* list of caps */
-
-#define I40E_AQ_CAP_ID_SWITCH_MODE	0x0001
-#define I40E_AQ_CAP_ID_MNG_MODE		0x0002
-#define I40E_AQ_CAP_ID_NPAR_ACTIVE	0x0003
-#define I40E_AQ_CAP_ID_OS2BMC_CAP	0x0004
-#define I40E_AQ_CAP_ID_FUNCTIONS_VALID	0x0005
-#define I40E_AQ_CAP_ID_SRIOV		0x0012
-#define I40E_AQ_CAP_ID_VF		0x0013
-#define I40E_AQ_CAP_ID_VMDQ		0x0014
-#define I40E_AQ_CAP_ID_8021QBG		0x0015
-#define I40E_AQ_CAP_ID_8021QBR		0x0016
-#define I40E_AQ_CAP_ID_VSI		0x0017
-#define I40E_AQ_CAP_ID_DCB		0x0018
-#define I40E_AQ_CAP_ID_FCOE		0x0021
-#define I40E_AQ_CAP_ID_ISCSI		0x0022
-#define I40E_AQ_CAP_ID_RSS		0x0040
-#define I40E_AQ_CAP_ID_RXQ		0x0041
-#define I40E_AQ_CAP_ID_TXQ		0x0042
-#define I40E_AQ_CAP_ID_MSIX		0x0043
-#define I40E_AQ_CAP_ID_VF_MSIX		0x0044
-#define I40E_AQ_CAP_ID_FLOW_DIRECTOR	0x0045
-#define I40E_AQ_CAP_ID_1588		0x0046
-#define I40E_AQ_CAP_ID_IWARP		0x0051
-#define I40E_AQ_CAP_ID_LED		0x0061
-#define I40E_AQ_CAP_ID_SDP		0x0062
-#define I40E_AQ_CAP_ID_MDIO		0x0063
-#define I40E_AQ_CAP_ID_WSR_PROT		0x0064
-#define I40E_AQ_CAP_ID_NVM_MGMT		0x0080
-#define I40E_AQ_CAP_ID_FLEX10		0x00F1
-#define I40E_AQ_CAP_ID_CEM		0x00F2
-
 /* Set CPPM Configuration (direct 0x0103) */
 struct i40e_aqc_cppm_configuration {
 	__le16	command_flags;
@@ -1712,6 +1561,7 @@ I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config);
 struct i40e_aq_set_mac_config {
 	__le16	max_frame_size;
 	u8	params;
+#define I40E_AQ_SET_MAC_CONFIG_CRC_EN	BIT(2)
 	u8	tx_timer_priority; /* bitmap */
 	__le16	tx_timer_value;
 	__le16	fc_refresh_threshold;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index 59263551c383..518bc738ea3b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -359,8 +359,8 @@ static void i40e_client_add_instance(struct i40e_pf *pf)
 	if (i40e_client_get_params(vsi, &cdev->lan_info.params))
 		goto free_cdev;
 
-	mac = list_first_entry(&cdev->lan_info.netdev->dev_addrs.list,
-			       struct netdev_hw_addr, list);
+	mac = list_first_entry_or_null(&cdev->lan_info.netdev->dev_addrs.list,
+				       struct netdev_hw_addr, list);
 	if (mac)
 		ether_addr_copy(cdev->lan_info.lanmac, mac->addr);
 	else
@@ -682,9 +682,7 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev,
 	if (err) {
 		dev_info(&pf->pdev->dev,
 			 "couldn't get PF vsi config, err %pe aq_err %s\n",
-			 ERR_PTR(err),
-			 i40e_aq_str(&pf->hw,
-				     pf->hw.aq.asq_last_status));
+			 ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status));
 		return -ENOENT;
 	}
 
@@ -711,8 +709,7 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev,
 			dev_info(&pf->pdev->dev,
 				 "update VSI ctxt for PE failed, err %pe aq_err %s\n",
 				 ERR_PTR(err),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+				 libie_aq_str(pf->hw.aq.asq_last_status));
 		}
 	}
 	return err;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index e8031f1a9b4f..59f5c1e810eb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -69,66 +69,6 @@ int i40e_set_mac_type(struct i40e_hw *hw)
 }
 
 /**
- * i40e_aq_str - convert AQ err code to a string
- * @hw: pointer to the HW structure
- * @aq_err: the AQ error code to convert
- **/
-const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err)
-{
-	switch (aq_err) {
-	case I40E_AQ_RC_OK:
-		return "OK";
-	case I40E_AQ_RC_EPERM:
-		return "I40E_AQ_RC_EPERM";
-	case I40E_AQ_RC_ENOENT:
-		return "I40E_AQ_RC_ENOENT";
-	case I40E_AQ_RC_ESRCH:
-		return "I40E_AQ_RC_ESRCH";
-	case I40E_AQ_RC_EINTR:
-		return "I40E_AQ_RC_EINTR";
-	case I40E_AQ_RC_EIO:
-		return "I40E_AQ_RC_EIO";
-	case I40E_AQ_RC_ENXIO:
-		return "I40E_AQ_RC_ENXIO";
-	case I40E_AQ_RC_E2BIG:
-		return "I40E_AQ_RC_E2BIG";
-	case I40E_AQ_RC_EAGAIN:
-		return "I40E_AQ_RC_EAGAIN";
-	case I40E_AQ_RC_ENOMEM:
-		return "I40E_AQ_RC_ENOMEM";
-	case I40E_AQ_RC_EACCES:
-		return "I40E_AQ_RC_EACCES";
-	case I40E_AQ_RC_EFAULT:
-		return "I40E_AQ_RC_EFAULT";
-	case I40E_AQ_RC_EBUSY:
-		return "I40E_AQ_RC_EBUSY";
-	case I40E_AQ_RC_EEXIST:
-		return "I40E_AQ_RC_EEXIST";
-	case I40E_AQ_RC_EINVAL:
-		return "I40E_AQ_RC_EINVAL";
-	case I40E_AQ_RC_ENOTTY:
-		return "I40E_AQ_RC_ENOTTY";
-	case I40E_AQ_RC_ENOSPC:
-		return "I40E_AQ_RC_ENOSPC";
-	case I40E_AQ_RC_ENOSYS:
-		return "I40E_AQ_RC_ENOSYS";
-	case I40E_AQ_RC_ERANGE:
-		return "I40E_AQ_RC_ERANGE";
-	case I40E_AQ_RC_EFLUSHED:
-		return "I40E_AQ_RC_EFLUSHED";
-	case I40E_AQ_RC_BAD_ADDR:
-		return "I40E_AQ_RC_BAD_ADDR";
-	case I40E_AQ_RC_EMODE:
-		return "I40E_AQ_RC_EMODE";
-	case I40E_AQ_RC_EFBIG:
-		return "I40E_AQ_RC_EFBIG";
-	}
-
-	snprintf(hw->err_str, sizeof(hw->err_str), "%d", aq_err);
-	return hw->err_str;
-}
-
-/**
  * i40e_debug_aq
  * @hw: debug mask related to admin queue
  * @mask: debug mask
@@ -141,7 +81,7 @@ const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err)
 void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
 		   void *buffer, u16 buf_len)
 {
-	struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc;
+	struct libie_aq_desc *aq_desc = (struct libie_aq_desc *)desc;
 	u32 effective_mask = hw->debug_mask & mask;
 	char prefix[27];
 	u16 len;
@@ -164,12 +104,12 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
 		   le32_to_cpu(aq_desc->cookie_low));
 	i40e_debug(hw, mask & I40E_DEBUG_AQ_DESCRIPTOR,
 		   "\tparam (0,1)  0x%08X 0x%08X\n",
-		   le32_to_cpu(aq_desc->params.internal.param0),
-		   le32_to_cpu(aq_desc->params.internal.param1));
+		   le32_to_cpu(aq_desc->params.generic.param0),
+		   le32_to_cpu(aq_desc->params.generic.param1));
 	i40e_debug(hw, mask & I40E_DEBUG_AQ_DESCRIPTOR,
 		   "\taddr (h,l)   0x%08X 0x%08X\n",
-		   le32_to_cpu(aq_desc->params.external.addr_high),
-		   le32_to_cpu(aq_desc->params.external.addr_low));
+		   le32_to_cpu(aq_desc->params.generic.addr_high),
+		   le32_to_cpu(aq_desc->params.generic.addr_low));
 
 	if (buffer && buf_len != 0 && len != 0 &&
 	    (effective_mask & I40E_DEBUG_AQ_DESC_BUFFER)) {
@@ -214,14 +154,14 @@ bool i40e_check_asq_alive(struct i40e_hw *hw)
 int i40e_aq_queue_shutdown(struct i40e_hw *hw,
 			   bool unloading)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_queue_shutdown *cmd =
-		(struct i40e_aqc_queue_shutdown *)&desc.params.raw;
+	struct i40e_aqc_queue_shutdown *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_queue_shutdown);
 
+	cmd = libie_aq_raw(&desc);
 	if (unloading)
 		cmd->driver_unloading = cpu_to_le32(I40E_AQ_DRIVER_UNLOADING);
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, NULL);
@@ -245,9 +185,8 @@ static int i40e_aq_get_set_rss_lut(struct i40e_hw *hw,
 				   u8 *lut, u16 lut_size,
 				   bool set)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_set_rss_lut *cmd_resp =
-		   (struct i40e_aqc_get_set_rss_lut *)&desc.params.raw;
+	struct i40e_aqc_get_set_rss_lut *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 	u16 flags;
 
@@ -258,9 +197,10 @@ static int i40e_aq_get_set_rss_lut(struct i40e_hw *hw,
 		i40e_fill_default_direct_cmd_desc(&desc,
 						  i40e_aqc_opc_get_rss_lut);
 
+	cmd_resp = libie_aq_raw(&desc);
 	/* Indirect command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_RD);
 
 	vsi_id = FIELD_PREP(I40E_AQC_SET_RSS_LUT_VSI_ID_MASK, vsi_id) |
 		 FIELD_PREP(I40E_AQC_SET_RSS_LUT_VSI_VALID, 1);
@@ -326,10 +266,9 @@ static int i40e_aq_get_set_rss_key(struct i40e_hw *hw,
 				   struct i40e_aqc_get_set_rss_key_data *key,
 				   bool set)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_set_rss_key *cmd_resp =
-			(struct i40e_aqc_get_set_rss_key *)&desc.params.raw;
 	u16 key_size = sizeof(struct i40e_aqc_get_set_rss_key_data);
+	struct i40e_aqc_get_set_rss_key *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (set)
@@ -339,9 +278,10 @@ static int i40e_aq_get_set_rss_key(struct i40e_hw *hw,
 		i40e_fill_default_direct_cmd_desc(&desc,
 						  i40e_aqc_opc_get_rss_key);
 
+	cmd_resp = libie_aq_raw(&desc);
 	/* Indirect command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_RD);
 
 	vsi_id = FIELD_PREP(I40E_AQC_SET_RSS_KEY_VSI_ID_MASK, vsi_id) |
 		 FIELD_PREP(I40E_AQC_SET_RSS_KEY_VSI_VALID, 1);
@@ -439,13 +379,13 @@ i40e_aq_mac_address_read(struct i40e_hw *hw,
 			 struct i40e_aqc_mac_address_read_data *addrs,
 			 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_mac_address_read *cmd_data =
-		(struct i40e_aqc_mac_address_read *)&desc.params.raw;
+	struct i40e_aqc_mac_address_read *cmd_data;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_mac_address_read);
-	desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF);
+	cmd_data = libie_aq_raw(&desc);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_BUF);
 
 	status = i40e_asq_send_command(hw, &desc, addrs,
 				       sizeof(*addrs), cmd_details);
@@ -465,13 +405,13 @@ int i40e_aq_mac_address_write(struct i40e_hw *hw,
 			      u16 flags, u8 *mac_addr,
 			      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_mac_address_write *cmd_data =
-		(struct i40e_aqc_mac_address_write *)&desc.params.raw;
+	struct i40e_aqc_mac_address_write *cmd_data;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_mac_address_write);
+	cmd_data = libie_aq_raw(&desc);
 	cmd_data->command_flags = cpu_to_le16(flags);
 	cmd_data->mac_sah = cpu_to_le16((u16)mac_addr[0] << 8 | mac_addr[1]);
 	cmd_data->mac_sal = cpu_to_le32(((u32)mac_addr[2] << 24) |
@@ -817,10 +757,11 @@ int i40e_pf_reset(struct i40e_hw *hw)
 void i40e_clear_hw(struct i40e_hw *hw)
 {
 	u32 num_queues, base_queue;
-	u32 num_pf_int;
-	u32 num_vf_int;
+	s32 num_pf_int;
+	s32 num_vf_int;
 	u32 num_vfs;
-	u32 i, j;
+	s32 i;
+	u32 j;
 	u32 val;
 	u32 eol = 0x7ff;
 
@@ -1060,7 +1001,7 @@ i40e_aq_get_phy_capabilities(struct i40e_hw *hw,
 {
 	u16 abilities_size = sizeof(struct i40e_aq_get_phy_abilities_resp);
 	u16 max_delay = I40E_MAX_PHY_TIMEOUT, total_delay = 0;
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!abilities)
@@ -1070,36 +1011,36 @@ i40e_aq_get_phy_capabilities(struct i40e_hw *hw,
 		i40e_fill_default_direct_cmd_desc(&desc,
 					       i40e_aqc_opc_get_phy_abilities);
 
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 		if (abilities_size > I40E_AQ_LARGE_BUF)
-			desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+			desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 		if (qualified_modules)
-			desc.params.external.param0 |=
+			desc.params.generic.param0 |=
 			cpu_to_le32(I40E_AQ_PHY_REPORT_QUALIFIED_MODULES);
 
 		if (report_init)
-			desc.params.external.param0 |=
+			desc.params.generic.param0 |=
 			cpu_to_le32(I40E_AQ_PHY_REPORT_INITIAL_VALUES);
 
 		status = i40e_asq_send_command(hw, &desc, abilities,
 					       abilities_size, cmd_details);
 
 		switch (hw->aq.asq_last_status) {
-		case I40E_AQ_RC_EIO:
+		case LIBIE_AQ_RC_EIO:
 			status = -EIO;
 			break;
-		case I40E_AQ_RC_EAGAIN:
+		case LIBIE_AQ_RC_EAGAIN:
 			usleep_range(1000, 2000);
 			total_delay++;
 			status = -EIO;
 			break;
-		/* also covers I40E_AQ_RC_OK */
+		/* also covers LIBIE_AQ_RC_OK */
 		default:
 			break;
 		}
 
-	} while ((hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN) &&
+	} while ((hw->aq.asq_last_status == LIBIE_AQ_RC_EAGAIN) &&
 		(total_delay < max_delay));
 
 	if (status)
@@ -1136,9 +1077,8 @@ int i40e_aq_set_phy_config(struct i40e_hw *hw,
 			   struct i40e_aq_set_phy_config *config,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aq_set_phy_config *cmd =
-			(struct i40e_aq_set_phy_config *)&desc.params.raw;
+	struct i40e_aq_set_phy_config *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!config)
@@ -1147,6 +1087,7 @@ int i40e_aq_set_phy_config(struct i40e_hw *hw,
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_phy_config);
 
+	cmd = libie_aq_raw(&desc);
 	*cmd = *config;
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -1249,6 +1190,40 @@ int i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures,
 }
 
 /**
+ * i40e_aq_set_mac_config - Configure MAC settings
+ * @hw: pointer to the hw struct
+ * @max_frame_size: Maximum Frame Size to be supported by the port
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Set MAC configuration (0x0603). Note that max_frame_size must be greater
+ * than zero.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+int i40e_aq_set_mac_config(struct i40e_hw *hw, u16 max_frame_size,
+			   struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_set_mac_config *cmd;
+	struct libie_aq_desc desc;
+
+	cmd = libie_aq_raw(&desc);
+
+	if (max_frame_size == 0)
+		return -EINVAL;
+
+	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_mac_config);
+
+	cmd->max_frame_size = cpu_to_le16(max_frame_size);
+	cmd->params = I40E_AQ_SET_MAC_CONFIG_CRC_EN;
+
+#define I40E_AQ_SET_MAC_CONFIG_FC_DEFAULT_THRESHOLD	0x7FFF
+	cmd->fc_refresh_threshold =
+		cpu_to_le16(I40E_AQ_SET_MAC_CONFIG_FC_DEFAULT_THRESHOLD);
+
+	return i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+}
+
+/**
  * i40e_aq_clear_pxe_mode
  * @hw: pointer to the hw struct
  * @cmd_details: pointer to command details structure or NULL
@@ -1258,14 +1233,14 @@ int i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures,
 int i40e_aq_clear_pxe_mode(struct i40e_hw *hw,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_clear_pxe *cmd =
-		(struct i40e_aqc_clear_pxe *)&desc.params.raw;
+	struct i40e_aqc_clear_pxe *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_clear_pxe_mode);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->rx_cnt = 0x2;
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -1287,14 +1262,14 @@ int i40e_aq_set_link_restart_an(struct i40e_hw *hw,
 				bool enable_link,
 				struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_link_restart_an *cmd =
-		(struct i40e_aqc_set_link_restart_an *)&desc.params.raw;
+	struct i40e_aqc_set_link_restart_an *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_link_restart_an);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->command = I40E_AQ_PHY_RESTART_AN;
 	if (enable_link)
 		cmd->command |= I40E_AQ_PHY_LINK_ENABLE;
@@ -1319,16 +1294,16 @@ int i40e_aq_get_link_info(struct i40e_hw *hw,
 			  bool enable_lse, struct i40e_link_status *link,
 			  struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_link_status *resp =
-		(struct i40e_aqc_get_link_status *)&desc.params.raw;
 	struct i40e_link_status *hw_link_info = &hw->phy.link_info;
+	struct i40e_aqc_get_link_status *resp;
+	struct libie_aq_desc desc;
 	bool tx_pause, rx_pause;
 	u16 command_flags;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_link_status);
 
+	resp = libie_aq_raw(&desc);
 	if (enable_lse)
 		command_flags = I40E_AQ_LSE_ENABLE;
 	else
@@ -1414,14 +1389,14 @@ int i40e_aq_set_phy_int_mask(struct i40e_hw *hw,
 			     u16 mask,
 			     struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_phy_int_mask *cmd =
-		(struct i40e_aqc_set_phy_int_mask *)&desc.params.raw;
+	struct i40e_aqc_set_phy_int_mask *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_phy_int_mask);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->event_mask = cpu_to_le16(mask);
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -1440,11 +1415,11 @@ int i40e_aq_set_phy_int_mask(struct i40e_hw *hw,
 int i40e_aq_set_mac_loopback(struct i40e_hw *hw, bool ena_lpbk,
 			     struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_lb_mode *cmd =
-		(struct i40e_aqc_set_lb_mode *)&desc.params.raw;
+	struct i40e_aqc_set_lb_mode *cmd;
+	struct libie_aq_desc desc;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_lb_modes);
+	cmd = libie_aq_raw(&desc);
 	if (ena_lpbk) {
 		if (hw->nvm.version <= I40E_LEGACY_LOOPBACK_NVM_VER)
 			cmd->lb_mode = cpu_to_le16(I40E_AQ_LB_MAC_LOCAL_LEGACY);
@@ -1466,14 +1441,14 @@ int i40e_aq_set_mac_loopback(struct i40e_hw *hw, bool ena_lpbk,
 int i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags,
 			  struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_phy_debug *cmd =
-		(struct i40e_aqc_set_phy_debug *)&desc.params.raw;
+	struct i40e_aqc_set_phy_debug *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_phy_debug);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->command_flags = cmd_flags;
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -1493,23 +1468,22 @@ int i40e_aq_add_vsi(struct i40e_hw *hw,
 		    struct i40e_vsi_context *vsi_ctx,
 		    struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_get_update_vsi *cmd =
-		(struct i40e_aqc_add_get_update_vsi *)&desc.params.raw;
-	struct i40e_aqc_add_get_update_vsi_completion *resp =
-		(struct i40e_aqc_add_get_update_vsi_completion *)
-		&desc.params.raw;
+	struct i40e_aqc_add_get_update_vsi_completion *resp;
+	struct i40e_aqc_add_get_update_vsi *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_add_vsi);
 
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	cmd->uplink_seid = cpu_to_le16(vsi_ctx->uplink_seid);
 	cmd->connection_type = vsi_ctx->connection_type;
 	cmd->vf_id = vsi_ctx->vf_num;
 	cmd->vsi_flags = cpu_to_le16(vsi_ctx->flags);
 
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 
 	status = i40e_asq_send_command_atomic(hw, &desc, &vsi_ctx->info,
 					      sizeof(vsi_ctx->info),
@@ -1537,15 +1511,14 @@ int i40e_aq_set_default_vsi(struct i40e_hw *hw,
 			    u16 seid,
 			    struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)
-		&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->promiscuous_flags = cpu_to_le16(I40E_AQC_SET_VSI_DEFAULT);
 	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_DEFAULT);
 	cmd->seid = cpu_to_le16(seid);
@@ -1565,15 +1538,14 @@ int i40e_aq_clear_default_vsi(struct i40e_hw *hw,
 			      u16 seid,
 			      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)
-		&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->promiscuous_flags = cpu_to_le16(0);
 	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_DEFAULT);
 	cmd->seid = cpu_to_le16(seid);
@@ -1596,15 +1568,15 @@ int i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw,
 					struct i40e_asq_cmd_details *cmd_details,
 					bool rx_only_promisc)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	u16 flags = 0;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	if (set) {
 		flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST;
 		if (rx_only_promisc && i40e_is_aq_api_ver_ge(hw, 1, 5))
@@ -1635,15 +1607,15 @@ int i40e_aq_set_vsi_multicast_promiscuous(struct i40e_hw *hw,
 					  u16 seid, bool set,
 					  struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	u16 flags = 0;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	if (set)
 		flags |= I40E_AQC_SET_VSI_PROMISC_MULTICAST;
 
@@ -1670,15 +1642,15 @@ int i40e_aq_set_vsi_mc_promisc_on_vlan(struct i40e_hw *hw,
 				       u16 vid,
 				       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	u16 flags = 0;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	if (enable)
 		flags |= I40E_AQC_SET_VSI_PROMISC_MULTICAST;
 
@@ -1706,15 +1678,15 @@ int i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw,
 				       u16 vid,
 				       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	u16 flags = 0;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	if (enable) {
 		flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST;
 		if (i40e_is_aq_api_ver_ge(hw, 1, 5))
@@ -1747,9 +1719,8 @@ int i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw,
 				       u16 seid, bool enable, u16 vid,
 				       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	u16 flags = 0;
 	int status;
 
@@ -1759,6 +1730,7 @@ int i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw,
 	if (enable)
 		flags |= I40E_AQC_SET_VSI_PROMISC_BROADCAST;
 
+	cmd = libie_aq_raw(&desc);
 	cmd->promiscuous_flags = cpu_to_le16(flags);
 	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_BROADCAST);
 	cmd->seid = cpu_to_le16(seid);
@@ -1782,14 +1754,14 @@ int i40e_aq_set_vsi_broadcast(struct i40e_hw *hw,
 			      u16 seid, bool set_filter,
 			      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	if (set_filter)
 		cmd->promiscuous_flags
 			    |= cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_BROADCAST);
@@ -1805,37 +1777,6 @@ int i40e_aq_set_vsi_broadcast(struct i40e_hw *hw,
 }
 
 /**
- * i40e_aq_set_vsi_vlan_promisc - control the VLAN promiscuous setting
- * @hw: pointer to the hw struct
- * @seid: vsi number
- * @enable: set MAC L2 layer unicast promiscuous enable/disable for a given VLAN
- * @cmd_details: pointer to command details structure or NULL
- **/
-int i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw,
-				 u16 seid, bool enable,
-				 struct i40e_asq_cmd_details *cmd_details)
-{
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
-	u16 flags = 0;
-	int status;
-
-	i40e_fill_default_direct_cmd_desc(&desc,
-					i40e_aqc_opc_set_vsi_promiscuous_modes);
-	if (enable)
-		flags |= I40E_AQC_SET_VSI_PROMISC_VLAN;
-
-	cmd->promiscuous_flags = cpu_to_le16(flags);
-	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_VLAN);
-	cmd->seid = cpu_to_le16(seid);
-
-	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
-
-	return status;
-}
-
-/**
  * i40e_aq_get_vsi_params - get VSI configuration info
  * @hw: pointer to the hw struct
  * @vsi_ctx: pointer to a vsi context struct
@@ -1845,20 +1786,19 @@ int i40e_aq_get_vsi_params(struct i40e_hw *hw,
 			   struct i40e_vsi_context *vsi_ctx,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_get_update_vsi *cmd =
-		(struct i40e_aqc_add_get_update_vsi *)&desc.params.raw;
-	struct i40e_aqc_add_get_update_vsi_completion *resp =
-		(struct i40e_aqc_add_get_update_vsi_completion *)
-		&desc.params.raw;
+	struct i40e_aqc_add_get_update_vsi_completion *resp;
+	struct i40e_aqc_add_get_update_vsi *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_get_vsi_parameters);
 
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	cmd->uplink_seid = cpu_to_le16(vsi_ctx->seid);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 
 	status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info,
 				    sizeof(vsi_ctx->info), NULL);
@@ -1887,19 +1827,18 @@ int i40e_aq_update_vsi_params(struct i40e_hw *hw,
 			      struct i40e_vsi_context *vsi_ctx,
 			      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_get_update_vsi *cmd =
-		(struct i40e_aqc_add_get_update_vsi *)&desc.params.raw;
-	struct i40e_aqc_add_get_update_vsi_completion *resp =
-		(struct i40e_aqc_add_get_update_vsi_completion *)
-		&desc.params.raw;
+	struct i40e_aqc_add_get_update_vsi_completion *resp;
+	struct i40e_aqc_add_get_update_vsi *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_update_vsi_parameters);
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	cmd->uplink_seid = cpu_to_le16(vsi_ctx->seid);
 
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 
 	status = i40e_asq_send_command_atomic(hw, &desc, &vsi_ctx->info,
 					      sizeof(vsi_ctx->info),
@@ -1926,16 +1865,16 @@ int i40e_aq_get_switch_config(struct i40e_hw *hw,
 			      u16 buf_size, u16 *start_seid,
 			      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_switch_seid *scfg =
-		(struct i40e_aqc_switch_seid *)&desc.params.raw;
+	struct i40e_aqc_switch_seid *scfg;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_get_switch_config);
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	scfg = libie_aq_raw(&desc);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (buf_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 	scfg->seid = cpu_to_le16(*start_seid);
 
 	status = i40e_asq_send_command(hw, &desc, buf, buf_size, cmd_details);
@@ -1960,13 +1899,13 @@ int i40e_aq_set_switch_config(struct i40e_hw *hw,
 			      u16 valid_flags, u8 mode,
 			      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_switch_config *scfg =
-		(struct i40e_aqc_set_switch_config *)&desc.params.raw;
+	struct i40e_aqc_set_switch_config *scfg;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_switch_config);
+	scfg = libie_aq_raw(&desc);
 	scfg->flags = cpu_to_le16(flags);
 	scfg->valid_flags = cpu_to_le16(valid_flags);
 	scfg->mode = mode;
@@ -1998,11 +1937,11 @@ int i40e_aq_get_firmware_version(struct i40e_hw *hw,
 				 u16 *api_major_version, u16 *api_minor_version,
 				 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_version *resp =
-		(struct i40e_aqc_get_version *)&desc.params.raw;
+	struct i40e_aqc_get_version *resp;
+	struct libie_aq_desc desc;
 	int status;
 
+	resp = libie_aq_raw(&desc);
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_version);
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -2035,22 +1974,22 @@ int i40e_aq_send_driver_version(struct i40e_hw *hw,
 				struct i40e_driver_version *dv,
 				struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_driver_version *cmd =
-		(struct i40e_aqc_driver_version *)&desc.params.raw;
+	struct libie_aqc_driver_ver *cmd;
+	struct libie_aq_desc desc;
 	int status;
 	u16 len;
 
 	if (dv == NULL)
 		return -EINVAL;
 
+	cmd = libie_aq_raw(&desc);
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_driver_version);
 
-	desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD);
-	cmd->driver_major_ver = dv->major_version;
-	cmd->driver_minor_ver = dv->minor_version;
-	cmd->driver_build_ver = dv->build_version;
-	cmd->driver_subbuild_ver = dv->subbuild_version;
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD);
+	cmd->major_ver = dv->major_version;
+	cmd->minor_ver = dv->minor_version;
+	cmd->build_ver = dv->build_version;
+	cmd->subbuild_ver = dv->subbuild_version;
 
 	len = 0;
 	while (len < sizeof(dv->driver_string) &&
@@ -2150,11 +2089,9 @@ int i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid,
 		    bool enable_stats,
 		    struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_veb *cmd =
-		(struct i40e_aqc_add_veb *)&desc.params.raw;
-	struct i40e_aqc_add_veb_completion *resp =
-		(struct i40e_aqc_add_veb_completion *)&desc.params.raw;
+	struct i40e_aqc_add_veb_completion *resp;
+	struct i40e_aqc_add_veb *cmd;
+	struct libie_aq_desc desc;
 	u16 veb_flags = 0;
 	int status;
 
@@ -2162,6 +2099,8 @@ int i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid,
 	if (!!uplink_seid != !!downlink_seid)
 		return -EINVAL;
 
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_veb);
 
 	cmd->uplink_seid = cpu_to_le16(uplink_seid);
@@ -2208,15 +2147,14 @@ int i40e_aq_get_veb_parameters(struct i40e_hw *hw,
 			       u16 *vebs_used, u16 *vebs_free,
 			       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_veb_parameters_completion *cmd_resp =
-		(struct i40e_aqc_get_veb_parameters_completion *)
-		&desc.params.raw;
+	struct i40e_aqc_get_veb_parameters_completion *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (veb_seid == 0)
 		return -EINVAL;
 
+	cmd_resp = libie_aq_raw(&desc);
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_get_veb_parameters);
 	cmd_resp->seid = cpu_to_le16(veb_seid);
@@ -2258,10 +2196,9 @@ get_veb_exit:
  **/
 static u16
 i40e_prepare_add_macvlan(struct i40e_aqc_add_macvlan_element_data *mv_list,
-			 struct i40e_aq_desc *desc, u16 count, u16 seid)
+			 struct libie_aq_desc *desc, u16 count, u16 seid)
 {
-	struct i40e_aqc_macvlan *cmd =
-		(struct i40e_aqc_macvlan *)&desc->params.raw;
+	struct i40e_aqc_macvlan *cmd = libie_aq_raw(desc);
 	u16 buf_size;
 	int i;
 
@@ -2279,9 +2216,9 @@ i40e_prepare_add_macvlan(struct i40e_aqc_add_macvlan_element_data *mv_list,
 			mv_list[i].flags |=
 			       cpu_to_le16(I40E_AQC_MACVLAN_ADD_USE_SHARED_MAC);
 
-	desc->flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc->flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	if (buf_size > I40E_AQ_LARGE_BUF)
-		desc->flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc->flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	return buf_size;
 }
@@ -2301,7 +2238,7 @@ i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid,
 		    struct i40e_aqc_add_macvlan_element_data *mv_list,
 		    u16 count, struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 buf_size;
 
 	if (count == 0 || !mv_list || !hw)
@@ -2332,9 +2269,9 @@ int
 i40e_aq_add_macvlan_v2(struct i40e_hw *hw, u16 seid,
 		       struct i40e_aqc_add_macvlan_element_data *mv_list,
 		       u16 count, struct i40e_asq_cmd_details *cmd_details,
-		       enum i40e_admin_queue_err *aq_status)
+		       enum libie_aq_err *aq_status)
 {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 buf_size;
 
 	if (count == 0 || !mv_list || !hw)
@@ -2361,9 +2298,8 @@ i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid,
 		       struct i40e_aqc_remove_macvlan_element_data *mv_list,
 		       u16 count, struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_macvlan *cmd =
-		(struct i40e_aqc_macvlan *)&desc.params.raw;
+	struct i40e_aqc_macvlan *cmd;
+	struct libie_aq_desc desc;
 	u16 buf_size;
 	int status;
 
@@ -2374,14 +2310,15 @@ i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid,
 
 	/* prep the rest of the request */
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_remove_macvlan);
+	cmd = libie_aq_raw(&desc);
 	cmd->num_addresses = cpu_to_le16(count);
 	cmd->seid[0] = cpu_to_le16(I40E_AQC_MACVLAN_CMD_SEID_VALID | seid);
 	cmd->seid[1] = 0;
 	cmd->seid[2] = 0;
 
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	if (buf_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command_atomic(hw, &desc, mv_list, buf_size,
 					      cmd_details, true);
@@ -2408,10 +2345,10 @@ int
 i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid,
 			  struct i40e_aqc_remove_macvlan_element_data *mv_list,
 			  u16 count, struct i40e_asq_cmd_details *cmd_details,
-			  enum i40e_admin_queue_err *aq_status)
+			  enum libie_aq_err *aq_status)
 {
 	struct i40e_aqc_macvlan *cmd;
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 buf_size;
 
 	if (count == 0 || !mv_list || !hw)
@@ -2421,151 +2358,21 @@ i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid,
 
 	/* prep the rest of the request */
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_remove_macvlan);
-	cmd = (struct i40e_aqc_macvlan *)&desc.params.raw;
+	cmd = libie_aq_raw(&desc);
 	cmd->num_addresses = cpu_to_le16(count);
 	cmd->seid[0] = cpu_to_le16(I40E_AQC_MACVLAN_CMD_SEID_VALID | seid);
 	cmd->seid[1] = 0;
 	cmd->seid[2] = 0;
 
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	if (buf_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	return i40e_asq_send_command_atomic_v2(hw, &desc, mv_list, buf_size,
 						 cmd_details, true, aq_status);
 }
 
 /**
- * i40e_mirrorrule_op - Internal helper function to add/delete mirror rule
- * @hw: pointer to the hw struct
- * @opcode: AQ opcode for add or delete mirror rule
- * @sw_seid: Switch SEID (to which rule refers)
- * @rule_type: Rule Type (ingress/egress/VLAN)
- * @id: Destination VSI SEID or Rule ID
- * @count: length of the list
- * @mr_list: list of mirrored VSI SEIDs or VLAN IDs
- * @cmd_details: pointer to command details structure or NULL
- * @rule_id: Rule ID returned from FW
- * @rules_used: Number of rules used in internal switch
- * @rules_free: Number of rules free in internal switch
- *
- * Add/Delete a mirror rule to a specific switch. Mirror rules are supported for
- * VEBs/VEPA elements only
- **/
-static int i40e_mirrorrule_op(struct i40e_hw *hw,
-			      u16 opcode, u16 sw_seid, u16 rule_type, u16 id,
-			      u16 count, __le16 *mr_list,
-			      struct i40e_asq_cmd_details *cmd_details,
-			      u16 *rule_id, u16 *rules_used, u16 *rules_free)
-{
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_delete_mirror_rule *cmd =
-		(struct i40e_aqc_add_delete_mirror_rule *)&desc.params.raw;
-	struct i40e_aqc_add_delete_mirror_rule_completion *resp =
-	(struct i40e_aqc_add_delete_mirror_rule_completion *)&desc.params.raw;
-	u16 buf_size;
-	int status;
-
-	buf_size = count * sizeof(*mr_list);
-
-	/* prep the rest of the request */
-	i40e_fill_default_direct_cmd_desc(&desc, opcode);
-	cmd->seid = cpu_to_le16(sw_seid);
-	cmd->rule_type = cpu_to_le16(rule_type &
-				     I40E_AQC_MIRROR_RULE_TYPE_MASK);
-	cmd->num_entries = cpu_to_le16(count);
-	/* Dest VSI for add, rule_id for delete */
-	cmd->destination = cpu_to_le16(id);
-	if (mr_list) {
-		desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF |
-						I40E_AQ_FLAG_RD));
-		if (buf_size > I40E_AQ_LARGE_BUF)
-			desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
-	}
-
-	status = i40e_asq_send_command(hw, &desc, mr_list, buf_size,
-				       cmd_details);
-	if (!status ||
-	    hw->aq.asq_last_status == I40E_AQ_RC_ENOSPC) {
-		if (rule_id)
-			*rule_id = le16_to_cpu(resp->rule_id);
-		if (rules_used)
-			*rules_used = le16_to_cpu(resp->mirror_rules_used);
-		if (rules_free)
-			*rules_free = le16_to_cpu(resp->mirror_rules_free);
-	}
-	return status;
-}
-
-/**
- * i40e_aq_add_mirrorrule - add a mirror rule
- * @hw: pointer to the hw struct
- * @sw_seid: Switch SEID (to which rule refers)
- * @rule_type: Rule Type (ingress/egress/VLAN)
- * @dest_vsi: SEID of VSI to which packets will be mirrored
- * @count: length of the list
- * @mr_list: list of mirrored VSI SEIDs or VLAN IDs
- * @cmd_details: pointer to command details structure or NULL
- * @rule_id: Rule ID returned from FW
- * @rules_used: Number of rules used in internal switch
- * @rules_free: Number of rules free in internal switch
- *
- * Add mirror rule. Mirror rules are supported for VEBs or VEPA elements only
- **/
-int i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
-			   u16 rule_type, u16 dest_vsi, u16 count,
-			   __le16 *mr_list,
-			   struct i40e_asq_cmd_details *cmd_details,
-			   u16 *rule_id, u16 *rules_used, u16 *rules_free)
-{
-	if (!(rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_INGRESS ||
-	    rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_EGRESS)) {
-		if (count == 0 || !mr_list)
-			return -EINVAL;
-	}
-
-	return i40e_mirrorrule_op(hw, i40e_aqc_opc_add_mirror_rule, sw_seid,
-				  rule_type, dest_vsi, count, mr_list,
-				  cmd_details, rule_id, rules_used, rules_free);
-}
-
-/**
- * i40e_aq_delete_mirrorrule - delete a mirror rule
- * @hw: pointer to the hw struct
- * @sw_seid: Switch SEID (to which rule refers)
- * @rule_type: Rule Type (ingress/egress/VLAN)
- * @count: length of the list
- * @rule_id: Rule ID that is returned in the receive desc as part of
- *		add_mirrorrule.
- * @mr_list: list of mirrored VLAN IDs to be removed
- * @cmd_details: pointer to command details structure or NULL
- * @rules_used: Number of rules used in internal switch
- * @rules_free: Number of rules free in internal switch
- *
- * Delete a mirror rule. Mirror rules are supported for VEBs/VEPA elements only
- **/
-int i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
-			      u16 rule_type, u16 rule_id, u16 count,
-			      __le16 *mr_list,
-			      struct i40e_asq_cmd_details *cmd_details,
-			      u16 *rules_used, u16 *rules_free)
-{
-	/* Rule ID has to be valid except rule_type: INGRESS VLAN mirroring */
-	if (rule_type == I40E_AQC_MIRROR_RULE_TYPE_VLAN) {
-		/* count and mr_list shall be valid for rule_type INGRESS VLAN
-		 * mirroring. For other rule_type, count and rule_type should
-		 * not matter.
-		 */
-		if (count == 0 || !mr_list)
-			return -EINVAL;
-	}
-
-	return i40e_mirrorrule_op(hw, i40e_aqc_opc_delete_mirror_rule, sw_seid,
-				  rule_type, rule_id, count, mr_list,
-				  cmd_details, NULL, rules_used, rules_free);
-}
-
-/**
  * i40e_aq_send_msg_to_vf
  * @hw: pointer to the hardware structure
  * @vfid: VF id to send msg
@@ -2581,21 +2388,21 @@ int i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid,
 			   u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_pf_vf_message *cmd =
-		(struct i40e_aqc_pf_vf_message *)&desc.params.raw;
+	struct i40e_aqc_pf_vf_message *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_send_msg_to_vf);
+	cmd = libie_aq_raw(&desc);
 	cmd->id = cpu_to_le32(vfid);
 	desc.cookie_high = cpu_to_le32(v_opcode);
 	desc.cookie_low = cpu_to_le32(v_retval);
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_SI);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_SI);
 	if (msglen) {
-		desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF |
-						I40E_AQ_FLAG_RD));
+		desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF |
+						LIBIE_AQ_FLAG_RD));
 		if (msglen > I40E_AQ_LARGE_BUF)
-			desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+			desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 		desc.datalen = cpu_to_le16(msglen);
 	}
 	status = i40e_asq_send_command(hw, &desc, msg, msglen, cmd_details);
@@ -2616,9 +2423,8 @@ int i40e_aq_debug_read_register(struct i40e_hw *hw,
 				u32 reg_addr, u64 *reg_val,
 				struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_debug_reg_read_write *cmd_resp =
-		(struct i40e_aqc_debug_reg_read_write *)&desc.params.raw;
+	struct i40e_aqc_debug_reg_read_write *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (reg_val == NULL)
@@ -2626,6 +2432,7 @@ int i40e_aq_debug_read_register(struct i40e_hw *hw,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_debug_read_reg);
 
+	cmd_resp = libie_aq_raw(&desc);
 	cmd_resp->address = cpu_to_le32(reg_addr);
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -2651,13 +2458,13 @@ int i40e_aq_debug_write_register(struct i40e_hw *hw,
 				 u32 reg_addr, u64 reg_val,
 				 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_debug_reg_read_write *cmd =
-		(struct i40e_aqc_debug_reg_read_write *)&desc.params.raw;
+	struct i40e_aqc_debug_reg_read_write *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_debug_write_reg);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->address = cpu_to_le32(reg_addr);
 	cmd->value_high = cpu_to_le32((u32)(reg_val >> 32));
 	cmd->value_low = cpu_to_le32((u32)(reg_val & 0xFFFFFFFF));
@@ -2684,16 +2491,16 @@ int i40e_aq_request_resource(struct i40e_hw *hw,
 			     u8 sdp_number, u64 *timeout,
 			     struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_request_resource *cmd_resp =
-		(struct i40e_aqc_request_resource *)&desc.params.raw;
+	struct libie_aqc_req_res *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_request_resource);
 
-	cmd_resp->resource_id = cpu_to_le16(resource);
+	cmd_resp = libie_aq_raw(&desc);
+	cmd_resp->res_id = cpu_to_le16(resource);
 	cmd_resp->access_type = cpu_to_le16(access);
-	cmd_resp->resource_number = cpu_to_le32(sdp_number);
+	cmd_resp->res_number = cpu_to_le32(sdp_number);
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
 	/* The completion specifies the maximum time in ms that the driver
@@ -2702,7 +2509,7 @@ int i40e_aq_request_resource(struct i40e_hw *hw,
 	 * busy return value and the timeout field indicates the maximum time
 	 * the current owner of the resource has to free it.
 	 */
-	if (!status || hw->aq.asq_last_status == I40E_AQ_RC_EBUSY)
+	if (!status || hw->aq.asq_last_status == LIBIE_AQ_RC_EBUSY)
 		*timeout = le32_to_cpu(cmd_resp->timeout);
 
 	return status;
@@ -2722,15 +2529,15 @@ int i40e_aq_release_resource(struct i40e_hw *hw,
 			     u8 sdp_number,
 			     struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_request_resource *cmd =
-		(struct i40e_aqc_request_resource *)&desc.params.raw;
+	struct libie_aqc_req_res *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_release_resource);
 
-	cmd->resource_id = cpu_to_le16(resource);
-	cmd->resource_number = cpu_to_le32(sdp_number);
+	cmd = libie_aq_raw(&desc);
+	cmd->res_id = cpu_to_le16(resource);
+	cmd->res_number = cpu_to_le32(sdp_number);
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
 
@@ -2754,9 +2561,8 @@ int i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer,
 		     bool last_command,
 		     struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_nvm_update *cmd =
-		(struct i40e_aqc_nvm_update *)&desc.params.raw;
+	struct i40e_aqc_nvm_update *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	/* In offset the highest byte must be zeroed. */
@@ -2767,6 +2573,7 @@ int i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_nvm_read);
 
+	cmd = libie_aq_raw(&desc);
 	/* If this is the last command in a series, set the proper flag. */
 	if (last_command)
 		cmd->command_flags |= I40E_AQ_NVM_LAST_CMD;
@@ -2774,9 +2581,9 @@ int i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer,
 	cmd->offset = cpu_to_le32(offset);
 	cmd->length = cpu_to_le16(length);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (length > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command(hw, &desc, data, length, cmd_details);
 
@@ -2799,9 +2606,8 @@ int i40e_aq_erase_nvm(struct i40e_hw *hw, u8 module_pointer,
 		      u32 offset, u16 length, bool last_command,
 		      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_nvm_update *cmd =
-		(struct i40e_aqc_nvm_update *)&desc.params.raw;
+	struct i40e_aqc_nvm_update *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	/* In offset the highest byte must be zeroed. */
@@ -2812,6 +2618,7 @@ int i40e_aq_erase_nvm(struct i40e_hw *hw, u8 module_pointer,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_nvm_erase);
 
+	cmd = libie_aq_raw(&desc);
 	/* If this is the last command in a series, set the proper flag. */
 	if (last_command)
 		cmd->command_flags |= I40E_AQ_NVM_LAST_CMD;
@@ -2838,7 +2645,7 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
 				     u32 cap_count,
 				     enum i40e_admin_queue_opc list_type_opc)
 {
-	struct i40e_aqc_list_capabilities_element_resp *cap;
+	struct libie_aqc_list_caps_elem *cap;
 	u32 valid_functions, num_functions;
 	u32 number, logical_id, phys_id;
 	struct i40e_hw_capabilities *p;
@@ -2847,7 +2654,7 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
 	int status;
 	u32 i = 0;
 
-	cap = (struct i40e_aqc_list_capabilities_element_resp *) buff;
+	cap = (struct libie_aqc_list_caps_elem *)buff;
 
 	if (list_type_opc == i40e_aqc_opc_list_dev_capabilities)
 		p = &hw->dev_caps;
@@ -2857,17 +2664,17 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
 		return;
 
 	for (i = 0; i < cap_count; i++, cap++) {
-		id = le16_to_cpu(cap->id);
+		id = le16_to_cpu(cap->cap);
 		number = le32_to_cpu(cap->number);
 		logical_id = le32_to_cpu(cap->logical_id);
 		phys_id = le32_to_cpu(cap->phys_id);
-		major_rev = cap->major_rev;
+		major_rev = cap->major_ver;
 
 		switch (id) {
-		case I40E_AQ_CAP_ID_SWITCH_MODE:
+		case LIBIE_AQC_CAPS_SWITCH_MODE:
 			p->switch_mode = number;
 			break;
-		case I40E_AQ_CAP_ID_MNG_MODE:
+		case LIBIE_AQC_CAPS_MNG_MODE:
 			p->management_mode = number;
 			if (major_rev > 1) {
 				p->mng_protocols_over_mctp = logical_id;
@@ -2878,76 +2685,76 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
 				p->mng_protocols_over_mctp = 0;
 			}
 			break;
-		case I40E_AQ_CAP_ID_NPAR_ACTIVE:
+		case LIBIE_AQC_CAPS_NPAR_ACTIVE:
 			p->npar_enable = number;
 			break;
-		case I40E_AQ_CAP_ID_OS2BMC_CAP:
+		case LIBIE_AQC_CAPS_OS2BMC_CAP:
 			p->os2bmc = number;
 			break;
-		case I40E_AQ_CAP_ID_FUNCTIONS_VALID:
+		case LIBIE_AQC_CAPS_VALID_FUNCTIONS:
 			p->valid_functions = number;
 			break;
-		case I40E_AQ_CAP_ID_SRIOV:
+		case LIBIE_AQC_CAPS_SRIOV:
 			if (number == 1)
 				p->sr_iov_1_1 = true;
 			break;
-		case I40E_AQ_CAP_ID_VF:
+		case LIBIE_AQC_CAPS_VF:
 			p->num_vfs = number;
 			p->vf_base_id = logical_id;
 			break;
-		case I40E_AQ_CAP_ID_VMDQ:
+		case LIBIE_AQC_CAPS_VMDQ:
 			if (number == 1)
 				p->vmdq = true;
 			break;
-		case I40E_AQ_CAP_ID_8021QBG:
+		case LIBIE_AQC_CAPS_8021QBG:
 			if (number == 1)
 				p->evb_802_1_qbg = true;
 			break;
-		case I40E_AQ_CAP_ID_8021QBR:
+		case LIBIE_AQC_CAPS_8021QBR:
 			if (number == 1)
 				p->evb_802_1_qbh = true;
 			break;
-		case I40E_AQ_CAP_ID_VSI:
+		case LIBIE_AQC_CAPS_VSI:
 			p->num_vsis = number;
 			break;
-		case I40E_AQ_CAP_ID_DCB:
+		case LIBIE_AQC_CAPS_DCB:
 			if (number == 1) {
 				p->dcb = true;
 				p->enabled_tcmap = logical_id;
 				p->maxtc = phys_id;
 			}
 			break;
-		case I40E_AQ_CAP_ID_FCOE:
+		case LIBIE_AQC_CAPS_FCOE:
 			if (number == 1)
 				p->fcoe = true;
 			break;
-		case I40E_AQ_CAP_ID_ISCSI:
+		case LIBIE_AQC_CAPS_ISCSI:
 			if (number == 1)
 				p->iscsi = true;
 			break;
-		case I40E_AQ_CAP_ID_RSS:
+		case LIBIE_AQC_CAPS_RSS:
 			p->rss = true;
 			p->rss_table_size = number;
 			p->rss_table_entry_width = logical_id;
 			break;
-		case I40E_AQ_CAP_ID_RXQ:
+		case LIBIE_AQC_CAPS_RXQS:
 			p->num_rx_qp = number;
 			p->base_queue = phys_id;
 			break;
-		case I40E_AQ_CAP_ID_TXQ:
+		case LIBIE_AQC_CAPS_TXQS:
 			p->num_tx_qp = number;
 			p->base_queue = phys_id;
 			break;
-		case I40E_AQ_CAP_ID_MSIX:
+		case LIBIE_AQC_CAPS_MSIX:
 			p->num_msix_vectors = number;
 			i40e_debug(hw, I40E_DEBUG_INIT,
 				   "HW Capability: MSIX vector count = %d\n",
 				   p->num_msix_vectors);
 			break;
-		case I40E_AQ_CAP_ID_VF_MSIX:
+		case LIBIE_AQC_CAPS_VF_MSIX:
 			p->num_msix_vectors_vf = number;
 			break;
-		case I40E_AQ_CAP_ID_FLEX10:
+		case LIBIE_AQC_CAPS_FLEX10:
 			if (major_rev == 1) {
 				if (number == 1) {
 					p->flex10_enable = true;
@@ -2963,42 +2770,42 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
 			p->flex10_mode = logical_id;
 			p->flex10_status = phys_id;
 			break;
-		case I40E_AQ_CAP_ID_CEM:
+		case LIBIE_AQC_CAPS_CEM:
 			if (number == 1)
 				p->mgmt_cem = true;
 			break;
-		case I40E_AQ_CAP_ID_IWARP:
+		case LIBIE_AQC_CAPS_RDMA:
 			if (number == 1)
 				p->iwarp = true;
 			break;
-		case I40E_AQ_CAP_ID_LED:
+		case LIBIE_AQC_CAPS_LED:
 			if (phys_id < I40E_HW_CAP_MAX_GPIO)
 				p->led[phys_id] = true;
 			break;
-		case I40E_AQ_CAP_ID_SDP:
+		case LIBIE_AQC_CAPS_SDP:
 			if (phys_id < I40E_HW_CAP_MAX_GPIO)
 				p->sdp[phys_id] = true;
 			break;
-		case I40E_AQ_CAP_ID_MDIO:
+		case LIBIE_AQC_CAPS_MDIO:
 			if (number == 1) {
 				p->mdio_port_num = phys_id;
 				p->mdio_port_mode = logical_id;
 			}
 			break;
-		case I40E_AQ_CAP_ID_1588:
+		case LIBIE_AQC_CAPS_1588:
 			if (number == 1)
 				p->ieee_1588 = true;
 			break;
-		case I40E_AQ_CAP_ID_FLOW_DIRECTOR:
+		case LIBIE_AQC_CAPS_FD:
 			p->fd = true;
 			p->fd_filters_guaranteed = number;
 			p->fd_filters_best_effort = logical_id;
 			break;
-		case I40E_AQ_CAP_ID_WSR_PROT:
+		case LIBIE_AQC_CAPS_WSR_PROT:
 			p->wr_csr_prot = (u64)number;
 			p->wr_csr_prot |= (u64)logical_id << 32;
 			break;
-		case I40E_AQ_CAP_ID_NVM_MGMT:
+		case LIBIE_AQC_CAPS_NVM_MGMT:
 			if (number & I40E_NVM_MGMT_SEC_REV_DISABLED)
 				p->sec_rev_disabled = true;
 			if (number & I40E_NVM_MGMT_UPDATE_DISABLED)
@@ -3090,11 +2897,11 @@ int i40e_aq_discover_capabilities(struct i40e_hw *hw,
 				  enum i40e_admin_queue_opc list_type_opc,
 				  struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aqc_list_capabilites *cmd;
-	struct i40e_aq_desc desc;
+	struct libie_aqc_list_caps *cmd;
+	struct libie_aq_desc desc;
 	int status = 0;
 
-	cmd = (struct i40e_aqc_list_capabilites *)&desc.params.raw;
+	cmd = libie_aq_raw(&desc);
 
 	if (list_type_opc != i40e_aqc_opc_list_func_capabilities &&
 		list_type_opc != i40e_aqc_opc_list_dev_capabilities) {
@@ -3104,9 +2911,9 @@ int i40e_aq_discover_capabilities(struct i40e_hw *hw,
 
 	i40e_fill_default_direct_cmd_desc(&desc, list_type_opc);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
 	*data_size = le16_to_cpu(desc.datalen);
@@ -3139,9 +2946,8 @@ int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer,
 		       bool last_command, u8 preservation_flags,
 		       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_nvm_update *cmd =
-		(struct i40e_aqc_nvm_update *)&desc.params.raw;
+	struct i40e_aqc_nvm_update *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	/* In offset the highest byte must be zeroed. */
@@ -3152,6 +2958,7 @@ int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_nvm_update);
 
+	cmd = libie_aq_raw(&desc);
 	/* If this is the last command in a series, set the proper flag. */
 	if (last_command)
 		cmd->command_flags |= I40E_AQ_NVM_LAST_CMD;
@@ -3169,9 +2976,9 @@ int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer,
 	cmd->offset = cpu_to_le32(offset);
 	cmd->length = cpu_to_le16(length);
 
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	if (length > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command(hw, &desc, data, length, cmd_details);
 
@@ -3180,41 +2987,6 @@ i40e_aq_update_nvm_exit:
 }
 
 /**
- * i40e_aq_rearrange_nvm
- * @hw: pointer to the hw struct
- * @rearrange_nvm: defines direction of rearrangement
- * @cmd_details: pointer to command details structure or NULL
- *
- * Rearrange NVM structure, available only for transition FW
- **/
-int i40e_aq_rearrange_nvm(struct i40e_hw *hw,
-			  u8 rearrange_nvm,
-			  struct i40e_asq_cmd_details *cmd_details)
-{
-	struct i40e_aqc_nvm_update *cmd;
-	struct i40e_aq_desc desc;
-	int status;
-
-	cmd = (struct i40e_aqc_nvm_update *)&desc.params.raw;
-
-	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_nvm_update);
-
-	rearrange_nvm &= (I40E_AQ_NVM_REARRANGE_TO_FLAT |
-			 I40E_AQ_NVM_REARRANGE_TO_STRUCT);
-
-	if (!rearrange_nvm) {
-		status = -EINVAL;
-		goto i40e_aq_rearrange_nvm_exit;
-	}
-
-	cmd->command_flags |= rearrange_nvm;
-	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
-
-i40e_aq_rearrange_nvm_exit:
-	return status;
-}
-
-/**
  * i40e_aq_get_lldp_mib
  * @hw: pointer to the hw struct
  * @bridge_type: type of bridge requested
@@ -3232,11 +3004,9 @@ int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type,
 			 u16 *local_len, u16 *remote_len,
 			 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_lldp_get_mib *cmd =
-		(struct i40e_aqc_lldp_get_mib *)&desc.params.raw;
-	struct i40e_aqc_lldp_get_mib *resp =
-		(struct i40e_aqc_lldp_get_mib *)&desc.params.raw;
+	struct i40e_aqc_lldp_get_mib *resp;
+	struct i40e_aqc_lldp_get_mib *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (buff_size == 0 || !buff)
@@ -3244,16 +3014,18 @@ int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_get_mib);
 	/* Indirect Command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	cmd->type = mib_type & I40E_AQ_LLDP_MIB_TYPE_MASK;
 	cmd->type |= FIELD_PREP(I40E_AQ_LLDP_BRIDGE_TYPE_MASK, bridge_type);
 
 	desc.datalen = cpu_to_le16(buff_size);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
 	if (!status) {
@@ -3282,19 +3054,19 @@ i40e_aq_set_lldp_mib(struct i40e_hw *hw,
 		     struct i40e_asq_cmd_details *cmd_details)
 {
 	struct i40e_aqc_lldp_set_local_mib *cmd;
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = (struct i40e_aqc_lldp_set_local_mib *)&desc.params.raw;
+	cmd = libie_aq_raw(&desc);
 	if (buff_size == 0 || !buff)
 		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_lldp_set_local_mib);
 	/* Indirect Command */
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 	desc.datalen = cpu_to_le16(buff_size);
 
 	cmd->type = mib_type;
@@ -3319,13 +3091,13 @@ int i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw,
 				      bool enable_update,
 				      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_lldp_update_mib *cmd =
-		(struct i40e_aqc_lldp_update_mib *)&desc.params.raw;
+	struct i40e_aqc_lldp_update_mib *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_update_mib);
 
+	cmd = libie_aq_raw(&desc);
 	if (!enable_update)
 		cmd->command |= I40E_AQ_LLDP_MIB_UPDATE_DISABLE;
 
@@ -3335,44 +3107,6 @@ int i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw,
 }
 
 /**
- * i40e_aq_restore_lldp
- * @hw: pointer to the hw struct
- * @setting: pointer to factory setting variable or NULL
- * @restore: True if factory settings should be restored
- * @cmd_details: pointer to command details structure or NULL
- *
- * Restore LLDP Agent factory settings if @restore set to True. In other case
- * only returns factory setting in AQ response.
- **/
-int
-i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore,
-		     struct i40e_asq_cmd_details *cmd_details)
-{
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_lldp_restore *cmd =
-		(struct i40e_aqc_lldp_restore *)&desc.params.raw;
-	int status;
-
-	if (!test_bit(I40E_HW_CAP_FW_LLDP_PERSISTENT, hw->caps)) {
-		i40e_debug(hw, I40E_DEBUG_ALL,
-			   "Restore LLDP not supported by current FW version.\n");
-		return -ENODEV;
-	}
-
-	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_restore);
-
-	if (restore)
-		cmd->command |= I40E_AQ_LLDP_AGENT_RESTORE;
-
-	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
-
-	if (setting)
-		*setting = cmd->command & 1;
-
-	return status;
-}
-
-/**
  * i40e_aq_stop_lldp
  * @hw: pointer to the hw struct
  * @shutdown_agent: True if LLDP Agent needs to be Shutdown
@@ -3385,13 +3119,13 @@ int i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
 		      bool persist,
 		      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_lldp_stop *cmd =
-		(struct i40e_aqc_lldp_stop *)&desc.params.raw;
+	struct i40e_aqc_lldp_stop *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_stop);
 
+	cmd = libie_aq_raw(&desc);
 	if (shutdown_agent)
 		cmd->command |= I40E_AQ_LLDP_AGENT_SHUTDOWN;
 
@@ -3419,13 +3153,13 @@ int i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
 int i40e_aq_start_lldp(struct i40e_hw *hw, bool persist,
 		       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_lldp_start *cmd =
-		(struct i40e_aqc_lldp_start *)&desc.params.raw;
+	struct i40e_aqc_lldp_start *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_start);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->command = I40E_AQ_LLDP_AGENT_START;
 
 	if (persist) {
@@ -3452,9 +3186,8 @@ int
 i40e_aq_set_dcb_parameters(struct i40e_hw *hw, bool dcb_enable,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_dcb_parameters *cmd =
-		(struct i40e_aqc_set_dcb_parameters *)&desc.params.raw;
+	struct i40e_aqc_set_dcb_parameters *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!test_bit(I40E_HW_CAP_FW_LLDP_STOPPABLE, hw->caps))
@@ -3463,6 +3196,7 @@ i40e_aq_set_dcb_parameters(struct i40e_hw *hw, bool dcb_enable,
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_dcb_parameters);
 
+	cmd = libie_aq_raw(&desc);
 	if (dcb_enable) {
 		cmd->valid_flags = I40E_DCB_VALID;
 		cmd->command = I40E_AQ_DCB_SET_AGENT;
@@ -3485,7 +3219,7 @@ int i40e_aq_get_cee_dcb_config(struct i40e_hw *hw,
 			       void *buff, u16 buff_size,
 			       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (buff_size == 0 || !buff)
@@ -3493,7 +3227,7 @@ int i40e_aq_get_cee_dcb_config(struct i40e_hw *hw,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_cee_dcb_cfg);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	status = i40e_asq_send_command(hw, &desc, (void *)buff, buff_size,
 				       cmd_details);
 
@@ -3517,15 +3251,15 @@ int i40e_aq_add_udp_tunnel(struct i40e_hw *hw,
 			   u8 *filter_index,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_udp_tunnel *cmd =
-		(struct i40e_aqc_add_udp_tunnel *)&desc.params.raw;
-	struct i40e_aqc_del_udp_tunnel_completion *resp =
-		(struct i40e_aqc_del_udp_tunnel_completion *)&desc.params.raw;
+	struct i40e_aqc_del_udp_tunnel_completion *resp;
+	struct i40e_aqc_add_udp_tunnel *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_udp_tunnel);
 
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	cmd->udp_port = cpu_to_le16(udp_port);
 	cmd->protocol_type = protocol_index;
 
@@ -3546,13 +3280,13 @@ int i40e_aq_add_udp_tunnel(struct i40e_hw *hw,
 int i40e_aq_del_udp_tunnel(struct i40e_hw *hw, u8 index,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_remove_udp_tunnel *cmd =
-		(struct i40e_aqc_remove_udp_tunnel *)&desc.params.raw;
+	struct i40e_aqc_remove_udp_tunnel *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_del_udp_tunnel);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->index = index;
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -3571,9 +3305,8 @@ int i40e_aq_del_udp_tunnel(struct i40e_hw *hw, u8 index,
 int i40e_aq_delete_element(struct i40e_hw *hw, u16 seid,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_switch_seid *cmd =
-		(struct i40e_aqc_switch_seid *)&desc.params.raw;
+	struct i40e_aqc_switch_seid *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (seid == 0)
@@ -3581,6 +3314,7 @@ int i40e_aq_delete_element(struct i40e_hw *hw, u16 seid,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_delete_element);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->seid = cpu_to_le16(seid);
 
 	status = i40e_asq_send_command_atomic(hw, &desc, NULL, 0,
@@ -3601,7 +3335,7 @@ int i40e_aq_delete_element(struct i40e_hw *hw, u16 seid,
 int i40e_aq_dcb_updated(struct i40e_hw *hw,
 			struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_dcb_updated);
@@ -3627,9 +3361,8 @@ static int i40e_aq_tx_sched_cmd(struct i40e_hw *hw, u16 seid,
 				enum i40e_admin_queue_opc opcode,
 				struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_tx_sched_ind *cmd =
-		(struct i40e_aqc_tx_sched_ind *)&desc.params.raw;
+	struct i40e_aqc_tx_sched_ind *cmd;
+	struct libie_aq_desc desc;
 	int status;
 	bool cmd_param_flag = false;
 
@@ -3656,12 +3389,13 @@ static int i40e_aq_tx_sched_cmd(struct i40e_hw *hw, u16 seid,
 
 	i40e_fill_default_direct_cmd_desc(&desc, opcode);
 
+	cmd = libie_aq_raw(&desc);
 	/* Indirect command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (cmd_param_flag)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_RD);
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	desc.datalen = cpu_to_le16(buff_size);
 
@@ -3684,14 +3418,14 @@ int i40e_aq_config_vsi_bw_limit(struct i40e_hw *hw,
 				u16 seid, u16 credit, u8 max_credit,
 				struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_configure_vsi_bw_limit *cmd =
-		(struct i40e_aqc_configure_vsi_bw_limit *)&desc.params.raw;
+	struct i40e_aqc_configure_vsi_bw_limit *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_configure_vsi_bw_limit);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->vsi_seid = cpu_to_le16(seid);
 	cmd->credit = cpu_to_le16(credit);
 	cmd->max_credit = max_credit;
@@ -4019,18 +3753,16 @@ int i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw,
 					  struct i40e_control_filter_stats *stats,
 					  struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_remove_control_packet_filter *cmd =
-		(struct i40e_aqc_add_remove_control_packet_filter *)
-		&desc.params.raw;
-	struct i40e_aqc_add_remove_control_packet_filter_completion *resp =
-		(struct i40e_aqc_add_remove_control_packet_filter_completion *)
-		&desc.params.raw;
+	struct i40e_aqc_add_remove_control_packet_filter_completion *resp;
+	struct i40e_aqc_add_remove_control_packet_filter *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (vsi_seid == 0)
 		return -EINVAL;
 
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	if (is_add) {
 		i40e_fill_default_direct_cmd_desc(&desc,
 				i40e_aqc_opc_add_control_packet_filter);
@@ -4098,15 +3830,15 @@ static int i40e_aq_alternate_read(struct i40e_hw *hw,
 				  u32 reg_addr0, u32 *reg_val0,
 				  u32 reg_addr1, u32 *reg_val1)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_alternate_write *cmd_resp =
-		(struct i40e_aqc_alternate_write *)&desc.params.raw;
+	struct i40e_aqc_alternate_write *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!reg_val0)
 		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_alternate_read);
+	cmd_resp = libie_aq_raw(&desc);
 	cmd_resp->address0 = cpu_to_le32(reg_addr0);
 	cmd_resp->address1 = cpu_to_le32(reg_addr1);
 
@@ -4134,10 +3866,10 @@ int i40e_aq_suspend_port_tx(struct i40e_hw *hw, u16 seid,
 			    struct i40e_asq_cmd_details *cmd_details)
 {
 	struct i40e_aqc_tx_sched_ind *cmd;
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = (struct i40e_aqc_tx_sched_ind *)&desc.params.raw;
+	cmd = libie_aq_raw(&desc);
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_suspend_port_tx);
 	cmd->vsi_seid = cpu_to_le16(seid);
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -4155,7 +3887,7 @@ int i40e_aq_suspend_port_tx(struct i40e_hw *hw, u16 seid,
 int i40e_aq_resume_port_tx(struct i40e_hw *hw,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_resume_port_tx);
@@ -4232,11 +3964,9 @@ int i40e_aq_debug_dump(struct i40e_hw *hw, u8 cluster_id,
 		       u8 *ret_next_table, u32 *ret_next_index,
 		       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_debug_dump_internals *cmd =
-		(struct i40e_aqc_debug_dump_internals *)&desc.params.raw;
-	struct i40e_aqc_debug_dump_internals *resp =
-		(struct i40e_aqc_debug_dump_internals *)&desc.params.raw;
+	struct i40e_aqc_debug_dump_internals *resp;
+	struct i40e_aqc_debug_dump_internals *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (buff_size == 0 || !buff)
@@ -4244,10 +3974,12 @@ int i40e_aq_debug_dump(struct i40e_hw *hw, u8 cluster_id,
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_debug_dump_internals);
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	/* Indirect Command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	cmd->cluster_id = cluster_id;
 	cmd->table_id = table_id;
@@ -4324,18 +4056,18 @@ i40e_aq_configure_partition_bw(struct i40e_hw *hw,
 			       struct i40e_asq_cmd_details *cmd_details)
 {
 	u16 bwd_size = sizeof(*bw_data);
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_configure_partition_bw);
 
 	/* Indirect command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_RD);
 
 	if (bwd_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	desc.datalen = cpu_to_le16(bwd_size);
 
@@ -4570,84 +4302,6 @@ phy_write_end:
 }
 
 /**
- * i40e_write_phy_register
- * @hw: pointer to the HW structure
- * @page: registers page number
- * @reg: register address in the page
- * @phy_addr: PHY address on MDIO interface
- * @value: PHY register value
- *
- * Writes value to specified PHY register
- **/
-int i40e_write_phy_register(struct i40e_hw *hw,
-			    u8 page, u16 reg, u8 phy_addr, u16 value)
-{
-	int status;
-
-	switch (hw->device_id) {
-	case I40E_DEV_ID_1G_BASE_T_X722:
-		status = i40e_write_phy_register_clause22(hw, reg, phy_addr,
-							  value);
-		break;
-	case I40E_DEV_ID_1G_BASE_T_BC:
-	case I40E_DEV_ID_5G_BASE_T_BC:
-	case I40E_DEV_ID_10G_BASE_T:
-	case I40E_DEV_ID_10G_BASE_T4:
-	case I40E_DEV_ID_10G_BASE_T_BC:
-	case I40E_DEV_ID_10G_BASE_T_X722:
-	case I40E_DEV_ID_25G_B:
-	case I40E_DEV_ID_25G_SFP28:
-		status = i40e_write_phy_register_clause45(hw, page, reg,
-							  phy_addr, value);
-		break;
-	default:
-		status = -EIO;
-		break;
-	}
-
-	return status;
-}
-
-/**
- * i40e_read_phy_register
- * @hw: pointer to the HW structure
- * @page: registers page number
- * @reg: register address in the page
- * @phy_addr: PHY address on MDIO interface
- * @value: PHY register value
- *
- * Reads specified PHY register value
- **/
-int i40e_read_phy_register(struct i40e_hw *hw,
-			   u8 page, u16 reg, u8 phy_addr, u16 *value)
-{
-	int status;
-
-	switch (hw->device_id) {
-	case I40E_DEV_ID_1G_BASE_T_X722:
-		status = i40e_read_phy_register_clause22(hw, reg, phy_addr,
-							 value);
-		break;
-	case I40E_DEV_ID_1G_BASE_T_BC:
-	case I40E_DEV_ID_5G_BASE_T_BC:
-	case I40E_DEV_ID_10G_BASE_T:
-	case I40E_DEV_ID_10G_BASE_T4:
-	case I40E_DEV_ID_10G_BASE_T_BC:
-	case I40E_DEV_ID_10G_BASE_T_X722:
-	case I40E_DEV_ID_25G_B:
-	case I40E_DEV_ID_25G_SFP28:
-		status = i40e_read_phy_register_clause45(hw, page, reg,
-							 phy_addr, value);
-		break;
-	default:
-		status = -EIO;
-		break;
-	}
-
-	return status;
-}
-
-/**
  * i40e_get_phy_address
  * @hw: pointer to the HW structure
  * @dev_num: PHY port num that address we want
@@ -4663,80 +4317,6 @@ u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num)
 }
 
 /**
- * i40e_blink_phy_link_led
- * @hw: pointer to the HW structure
- * @time: time how long led will blinks in secs
- * @interval: gap between LED on and off in msecs
- *
- * Blinks PHY link LED
- **/
-int i40e_blink_phy_link_led(struct i40e_hw *hw,
-			    u32 time, u32 interval)
-{
-	u16 led_addr = I40E_PHY_LED_PROV_REG_1;
-	u16 gpio_led_port;
-	u8 phy_addr = 0;
-	int status = 0;
-	u16 led_ctl;
-	u8 port_num;
-	u16 led_reg;
-	u32 i;
-
-	i = rd32(hw, I40E_PFGEN_PORTNUM);
-	port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK);
-	phy_addr = i40e_get_phy_address(hw, port_num);
-
-	for (gpio_led_port = 0; gpio_led_port < 3; gpio_led_port++,
-	     led_addr++) {
-		status = i40e_read_phy_register_clause45(hw,
-							 I40E_PHY_COM_REG_PAGE,
-							 led_addr, phy_addr,
-							 &led_reg);
-		if (status)
-			goto phy_blinking_end;
-		led_ctl = led_reg;
-		if (led_reg & I40E_PHY_LED_LINK_MODE_MASK) {
-			led_reg = 0;
-			status = i40e_write_phy_register_clause45(hw,
-							 I40E_PHY_COM_REG_PAGE,
-							 led_addr, phy_addr,
-							 led_reg);
-			if (status)
-				goto phy_blinking_end;
-			break;
-		}
-	}
-
-	if (time > 0 && interval > 0) {
-		for (i = 0; i < time * 1000; i += interval) {
-			status = i40e_read_phy_register_clause45(hw,
-						I40E_PHY_COM_REG_PAGE,
-						led_addr, phy_addr, &led_reg);
-			if (status)
-				goto restore_config;
-			if (led_reg & I40E_PHY_LED_MANUAL_ON)
-				led_reg = 0;
-			else
-				led_reg = I40E_PHY_LED_MANUAL_ON;
-			status = i40e_write_phy_register_clause45(hw,
-						I40E_PHY_COM_REG_PAGE,
-						led_addr, phy_addr, led_reg);
-			if (status)
-				goto restore_config;
-			msleep(interval);
-		}
-	}
-
-restore_config:
-	status = i40e_write_phy_register_clause45(hw,
-						  I40E_PHY_COM_REG_PAGE,
-						  led_addr, phy_addr, led_ctl);
-
-phy_blinking_end:
-	return status;
-}
-
-/**
  * i40e_led_get_reg - read LED register
  * @hw: pointer to the HW structure
  * @led_addr: LED register address
@@ -4919,9 +4499,8 @@ int i40e_aq_rx_ctl_read_register(struct i40e_hw *hw,
 				 u32 reg_addr, u32 *reg_val,
 				 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_rx_ctl_reg_read_write *cmd_resp =
-		(struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw;
+	struct i40e_aqc_rx_ctl_reg_read_write *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!reg_val)
@@ -4929,6 +4508,7 @@ int i40e_aq_rx_ctl_read_register(struct i40e_hw *hw,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_rx_ctl_reg_read);
 
+	cmd_resp = libie_aq_raw(&desc);
 	cmd_resp->address = cpu_to_le32(reg_addr);
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -4957,7 +4537,7 @@ u32 i40e_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr)
 	if (!use_register) {
 do_retry:
 		status = i40e_aq_rx_ctl_read_register(hw, reg_addr, &val, NULL);
-		if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) {
+		if (hw->aq.asq_last_status == LIBIE_AQ_RC_EAGAIN && retry) {
 			usleep_range(1000, 2000);
 			retry--;
 			goto do_retry;
@@ -4985,13 +4565,13 @@ int i40e_aq_rx_ctl_write_register(struct i40e_hw *hw,
 				  u32 reg_addr, u32 reg_val,
 				  struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_rx_ctl_reg_read_write *cmd =
-		(struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw;
+	struct i40e_aqc_rx_ctl_reg_read_write *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_rx_ctl_reg_write);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->address = cpu_to_le32(reg_addr);
 	cmd->value = cpu_to_le32(reg_val);
 
@@ -5019,7 +4599,7 @@ void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val)
 do_retry:
 		status = i40e_aq_rx_ctl_write_register(hw, reg_addr,
 						       reg_val, NULL);
-		if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) {
+		if (hw->aq.asq_last_status == LIBIE_AQ_RC_EAGAIN && retry) {
 			usleep_range(1000, 2000);
 			retry--;
 			goto do_retry;
@@ -5078,14 +4658,14 @@ int i40e_aq_set_phy_register_ext(struct i40e_hw *hw,
 				 u32 reg_addr, u32 reg_val,
 				 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_phy_register_access *cmd =
-		(struct i40e_aqc_phy_register_access *)&desc.params.raw;
+	struct i40e_aqc_phy_register_access *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_phy_register);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->phy_interface = phy_select;
 	cmd->dev_address = dev_addr;
 	cmd->reg_address = cpu_to_le32(reg_addr);
@@ -5123,14 +4703,14 @@ int i40e_aq_get_phy_register_ext(struct i40e_hw *hw,
 				 u32 reg_addr, u32 *reg_val,
 				 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_phy_register_access *cmd =
-		(struct i40e_aqc_phy_register_access *)&desc.params.raw;
+	struct i40e_aqc_phy_register_access *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_get_phy_register);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->phy_interface = phy_select;
 	cmd->dev_address = dev_addr;
 	cmd->reg_address = cpu_to_le32(reg_addr);
@@ -5162,19 +4742,18 @@ int i40e_aq_write_ddp(struct i40e_hw *hw, void *buff,
 		      u32 *error_offset, u32 *error_info,
 		      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_write_personalization_profile *cmd =
-		(struct i40e_aqc_write_personalization_profile *)
-		&desc.params.raw;
+	struct i40e_aqc_write_personalization_profile *cmd;
 	struct i40e_aqc_write_ddp_resp *resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_write_personalization_profile);
 
-	desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD);
+	cmd = libie_aq_raw(&desc);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD);
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	desc.datalen = cpu_to_le16(buff_size);
 
@@ -5182,7 +4761,7 @@ int i40e_aq_write_ddp(struct i40e_hw *hw, void *buff,
 
 	status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
 	if (!status) {
-		resp = (struct i40e_aqc_write_ddp_resp *)&desc.params.raw;
+		resp = libie_aq_raw(&desc);
 		if (error_offset)
 			*error_offset = le32_to_cpu(resp->error_offset);
 		if (error_info)
@@ -5204,17 +4783,17 @@ int i40e_aq_get_ddp_list(struct i40e_hw *hw, void *buff,
 			 u16 buff_size, u8 flags,
 			 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_applied_profiles *cmd =
-		(struct i40e_aqc_get_applied_profiles *)&desc.params.raw;
+	struct i40e_aqc_get_applied_profiles *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_get_personalization_profile_list);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	cmd = libie_aq_raw(&desc);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 	desc.datalen = cpu_to_le16(buff_size);
 
 	cmd->flags = flags;
@@ -5269,39 +4848,6 @@ i40e_find_segment_in_package(u32 segment_type,
 	(struct i40e_profile_section_header *)((u8 *)(profile) + (offset))
 
 /**
- * i40e_find_section_in_profile
- * @section_type: the section type to search for (i.e., SECTION_TYPE_NOTE)
- * @profile: pointer to the i40e segment header to be searched
- *
- * This function searches i40e segment for a particular section type. On
- * success it returns a pointer to the section header, otherwise it will
- * return NULL.
- **/
-struct i40e_profile_section_header *
-i40e_find_section_in_profile(u32 section_type,
-			     struct i40e_profile_segment *profile)
-{
-	struct i40e_profile_section_header *sec;
-	struct i40e_section_table *sec_tbl;
-	u32 sec_off;
-	u32 i;
-
-	if (profile->header.type != SEGMENT_TYPE_I40E)
-		return NULL;
-
-	I40E_SECTION_TABLE(profile, sec_tbl);
-
-	for (i = 0; i < sec_tbl->section_count; i++) {
-		sec_off = sec_tbl->section_offset[i];
-		sec = I40E_SECTION_HEADER(profile, sec_off);
-		if (sec->section.type == section_type)
-			return sec;
-	}
-
-	return NULL;
-}
-
-/**
  * i40e_ddp_exec_aq_section - Execute generic AQ for DDP
  * @hw: pointer to the hw struct
  * @aq: command buffer containing all data to execute AQ
@@ -5309,7 +4855,7 @@ i40e_find_section_in_profile(u32 section_type,
 static int i40e_ddp_exec_aq_section(struct i40e_hw *hw,
 				    struct i40e_profile_aq_section *aq)
 {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	u8 *msg = NULL;
 	u16 msglen;
 	int status;
@@ -5320,10 +4866,10 @@ static int i40e_ddp_exec_aq_section(struct i40e_hw *hw,
 
 	msglen = aq->datalen;
 	if (msglen) {
-		desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF |
-						I40E_AQ_FLAG_RD));
+		desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF |
+						LIBIE_AQ_FLAG_RD));
 		if (msglen > I40E_AQ_LARGE_BUF)
-			desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+			desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 		desc.datalen = cpu_to_le16(msglen);
 		msg = &aq->data[0];
 	}
@@ -5524,45 +5070,6 @@ i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
 }
 
 /**
- * i40e_add_pinfo_to_list
- * @hw: pointer to the hardware structure
- * @profile: pointer to the profile segment of the package
- * @profile_info_sec: buffer for information section
- * @track_id: package tracking id
- *
- * Register a profile to the list of loaded profiles.
- */
-int
-i40e_add_pinfo_to_list(struct i40e_hw *hw,
-		       struct i40e_profile_segment *profile,
-		       u8 *profile_info_sec, u32 track_id)
-{
-	struct i40e_profile_section_header *sec = NULL;
-	struct i40e_profile_info *pinfo;
-	u32 offset = 0, info = 0;
-	int status = 0;
-
-	sec = (struct i40e_profile_section_header *)profile_info_sec;
-	sec->tbl_size = 1;
-	sec->data_end = sizeof(struct i40e_profile_section_header) +
-			sizeof(struct i40e_profile_info);
-	sec->section.type = SECTION_TYPE_INFO;
-	sec->section.offset = sizeof(struct i40e_profile_section_header);
-	sec->section.size = sizeof(struct i40e_profile_info);
-	pinfo = (struct i40e_profile_info *)(profile_info_sec +
-					     sec->section.offset);
-	pinfo->track_id = track_id;
-	pinfo->version = profile->version;
-	pinfo->op = I40E_DDP_ADD_TRACKID;
-	memcpy(pinfo->name, profile->name, I40E_DDP_NAME_SIZE);
-
-	status = i40e_aq_write_ddp(hw, (void *)sec, sec->data_end,
-				   track_id, &offset, &info, NULL);
-
-	return status;
-}
-
-/**
  * i40e_aq_add_cloud_filters
  * @hw: pointer to the hardware structure
  * @seid: VSI seid to add cloud filters from
@@ -5579,18 +5086,18 @@ i40e_aq_add_cloud_filters(struct i40e_hw *hw, u16 seid,
 			  struct i40e_aqc_cloud_filters_element_data *filters,
 			  u8 filter_count)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_remove_cloud_filters *cmd =
-	(struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+	struct i40e_aqc_add_remove_cloud_filters *cmd;
+	struct libie_aq_desc desc;
 	u16 buff_len;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_add_cloud_filters);
 
+	cmd = libie_aq_raw(&desc);
 	buff_len = filter_count * sizeof(*filters);
 	desc.datalen = cpu_to_le16(buff_len);
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	cmd->num_filters = filter_count;
 	cmd->seid = cpu_to_le16(seid);
 
@@ -5616,9 +5123,8 @@ i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
 			     struct i40e_aqc_cloud_filters_element_bb *filters,
 			     u8 filter_count)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_remove_cloud_filters *cmd =
-	(struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+	struct i40e_aqc_add_remove_cloud_filters *cmd;
+	struct libie_aq_desc desc;
 	u16 buff_len;
 	int status;
 	int i;
@@ -5626,9 +5132,10 @@ i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_add_cloud_filters);
 
+	cmd = libie_aq_raw(&desc);
 	buff_len = filter_count * sizeof(*filters);
 	desc.datalen = cpu_to_le16(buff_len);
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	cmd->num_filters = filter_count;
 	cmd->seid = cpu_to_le16(seid);
 	cmd->big_buffer_flag = I40E_AQC_ADD_CLOUD_CMD_BB;
@@ -5672,18 +5179,18 @@ i40e_aq_rem_cloud_filters(struct i40e_hw *hw, u16 seid,
 			  struct i40e_aqc_cloud_filters_element_data *filters,
 			  u8 filter_count)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_remove_cloud_filters *cmd =
-	(struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+	struct i40e_aqc_add_remove_cloud_filters *cmd;
+	struct libie_aq_desc desc;
 	u16 buff_len;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_remove_cloud_filters);
 
+	cmd = libie_aq_raw(&desc);
 	buff_len = filter_count * sizeof(*filters);
 	desc.datalen = cpu_to_le16(buff_len);
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	cmd->num_filters = filter_count;
 	cmd->seid = cpu_to_le16(seid);
 
@@ -5709,9 +5216,8 @@ i40e_aq_rem_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
 			     struct i40e_aqc_cloud_filters_element_bb *filters,
 			     u8 filter_count)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_remove_cloud_filters *cmd =
-	(struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+	struct i40e_aqc_add_remove_cloud_filters *cmd;
+	struct libie_aq_desc desc;
 	u16 buff_len;
 	int status;
 	int i;
@@ -5719,9 +5225,10 @@ i40e_aq_rem_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_remove_cloud_filters);
 
+	cmd = libie_aq_raw(&desc);
 	buff_len = filter_count * sizeof(*filters);
 	desc.datalen = cpu_to_le16(buff_len);
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	cmd->num_filters = filter_count;
 	cmd->seid = cpu_to_le16(seid);
 	cmd->big_buffer_flag = I40E_AQC_ADD_CLOUD_CMD_BB;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
index 8db1eb0c1768..9e0c9597aeb9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
@@ -750,7 +750,7 @@ static int i40e_get_ieee_dcb_config(struct i40e_hw *hw)
 				     I40E_AQ_LLDP_BRIDGE_TYPE_NEAREST_BRIDGE,
 				     &hw->remote_dcbx_config);
 	/* Don't treat ENOENT as an error for Remote MIBs */
-	if (hw->aq.asq_last_status == I40E_AQ_RC_ENOENT)
+	if (hw->aq.asq_last_status == LIBIE_AQ_RC_ENOENT)
 		ret = 0;
 
 out:
@@ -799,7 +799,7 @@ int i40e_get_dcb_config(struct i40e_hw *hw)
 	}
 
 	/* CEE mode not enabled try querying IEEE data */
-	if (hw->aq.asq_last_status == I40E_AQ_RC_ENOENT)
+	if (hw->aq.asq_last_status == LIBIE_AQ_RC_ENOENT)
 		return i40e_get_ieee_dcb_config(hw);
 
 	if (ret)
@@ -816,7 +816,7 @@ int i40e_get_dcb_config(struct i40e_hw *hw)
 				     I40E_AQ_LLDP_BRIDGE_TYPE_NEAREST_BRIDGE,
 				     &hw->remote_dcbx_config);
 	/* Don't treat ENOENT as an error for Remote MIBs */
-	if (hw->aq.asq_last_status == I40E_AQ_RC_ENOENT)
+	if (hw->aq.asq_last_status == LIBIE_AQ_RC_ENOENT)
 		ret = 0;
 
 out:
@@ -925,11 +925,11 @@ i40e_get_fw_lldp_status(struct i40e_hw *hw,
 
 	if (!ret) {
 		*lldp_status = I40E_GET_FW_LLDP_STATUS_ENABLED;
-	} else if (hw->aq.asq_last_status == I40E_AQ_RC_ENOENT) {
+	} else if (hw->aq.asq_last_status == LIBIE_AQ_RC_ENOENT) {
 		/* MIB is not available yet but the agent is running */
 		*lldp_status = I40E_GET_FW_LLDP_STATUS_ENABLED;
 		ret = 0;
-	} else if (hw->aq.asq_last_status == I40E_AQ_RC_EPERM) {
+	} else if (hw->aq.asq_last_status == LIBIE_AQ_RC_EPERM) {
 		*lldp_status = I40E_GET_FW_LLDP_STATUS_DISABLED;
 		ret = 0;
 	}
@@ -1491,19 +1491,6 @@ void i40e_dcb_hw_set_num_tc(struct i40e_hw *hw, u8 num_tc)
 }
 
 /**
- * i40e_dcb_hw_get_num_tc
- * @hw: pointer to the hw struct
- *
- * Returns number of traffic classes configured in HW
- **/
-u8 i40e_dcb_hw_get_num_tc(struct i40e_hw *hw)
-{
-	u32 reg = rd32(hw, I40E_PRTDCB_GENC);
-
-	return FIELD_GET(I40E_PRTDCB_GENC_NUMTC_MASK, reg);
-}
-
-/**
  * i40e_dcb_hw_rx_ets_bw_config
  * @hw: pointer to the hw struct
  * @bw_share: Bandwidth share indexed per traffic class
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
index d76497566e40..d5662c639c41 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
@@ -253,7 +253,6 @@ void i40e_dcb_hw_rx_cmd_monitor_config(struct i40e_hw *hw,
 void i40e_dcb_hw_pfc_config(struct i40e_hw *hw,
 			    u8 pfc_en, u8 *prio_tc);
 void i40e_dcb_hw_set_num_tc(struct i40e_hw *hw, u8 num_tc);
-u8 i40e_dcb_hw_get_num_tc(struct i40e_hw *hw);
 void i40e_dcb_hw_rx_ets_bw_config(struct i40e_hw *hw, u8 *bw_share,
 				  u8 *mode, u8 *prio_type);
 void i40e_dcb_hw_rx_up2tc_config(struct i40e_hw *hw, u8 *prio_tc);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c
index 8aa43aefe84c..a2ccf4c5e30b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c
@@ -136,7 +136,7 @@ static int i40e_dcbnl_ieee_setets(struct net_device *netdev,
 		dev_info(&pf->pdev->dev,
 			 "Failed setting DCB ETS configuration err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 libie_aq_str(pf->hw.aq.asq_last_status));
 		return -EINVAL;
 	}
 
@@ -175,7 +175,7 @@ static int i40e_dcbnl_ieee_setpfc(struct net_device *netdev,
 		dev_info(&pf->pdev->dev,
 			 "Failed setting DCB PFC configuration err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 libie_aq_str(pf->hw.aq.asq_last_status));
 		return -EINVAL;
 	}
 
@@ -226,7 +226,7 @@ static int i40e_dcbnl_ieee_setapp(struct net_device *netdev,
 		dev_info(&pf->pdev->dev,
 			 "Failed setting DCB configuration err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 libie_aq_str(pf->hw.aq.asq_last_status));
 		return -EINVAL;
 	}
 
@@ -291,7 +291,7 @@ static int i40e_dcbnl_ieee_delapp(struct net_device *netdev,
 		dev_info(&pf->pdev->dev,
 			 "Failed setting DCB configuration err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 libie_aq_str(pf->hw.aq.asq_last_status));
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 208c2f0857b6..c17b5d290f0a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -40,48 +40,6 @@ static struct i40e_vsi *i40e_dbg_find_vsi(struct i40e_pf *pf, int seid)
  * setup, adding or removing filters, or other things.  Many of
  * these will be useful for some forms of unit testing.
  **************************************************************/
-static char i40e_dbg_command_buf[256] = "";
-
-/**
- * i40e_dbg_command_read - read for command datum
- * @filp: the opened file
- * @buffer: where to write the data for the user to read
- * @count: the size of the user's buffer
- * @ppos: file position offset
- **/
-static ssize_t i40e_dbg_command_read(struct file *filp, char __user *buffer,
-				     size_t count, loff_t *ppos)
-{
-	struct i40e_pf *pf = filp->private_data;
-	struct i40e_vsi *main_vsi;
-	int bytes_not_copied;
-	int buf_size = 256;
-	char *buf;
-	int len;
-
-	/* don't allow partial reads */
-	if (*ppos != 0)
-		return 0;
-	if (count < buf_size)
-		return -ENOSPC;
-
-	buf = kzalloc(buf_size, GFP_KERNEL);
-	if (!buf)
-		return -ENOSPC;
-
-	main_vsi = i40e_pf_get_main_vsi(pf);
-	len = snprintf(buf, buf_size, "%s: %s\n", main_vsi->netdev->name,
-		       i40e_dbg_command_buf);
-
-	bytes_not_copied = copy_to_user(buffer, buf, len);
-	kfree(buf);
-
-	if (bytes_not_copied)
-		return -EFAULT;
-
-	*ppos = len;
-	return len;
-}
 
 static char *i40e_filter_state_string[] = {
 	"INVALID",
@@ -489,7 +447,7 @@ static void i40e_dbg_dump_aq_desc(struct i40e_pf *pf)
 	dev_info(&pf->pdev->dev, "AdminQ Tx Ring\n");
 	ring = &(hw->aq.asq);
 	for (i = 0; i < ring->count; i++) {
-		struct i40e_aq_desc *d = I40E_ADMINQ_DESC(*ring, i);
+		struct libie_aq_desc *d = I40E_ADMINQ_DESC(*ring, i);
 
 		dev_info(&pf->pdev->dev,
 			 "   at[%02d] flags=0x%04x op=0x%04x dlen=0x%04x ret=0x%04x cookie_h=0x%08x cookie_l=0x%08x\n",
@@ -502,7 +460,7 @@ static void i40e_dbg_dump_aq_desc(struct i40e_pf *pf)
 	dev_info(&pf->pdev->dev, "AdminQ Rx Ring\n");
 	ring = &(hw->aq.arq);
 	for (i = 0; i < ring->count; i++) {
-		struct i40e_aq_desc *d = I40E_ADMINQ_DESC(*ring, i);
+		struct libie_aq_desc *d = I40E_ADMINQ_DESC(*ring, i);
 
 		dev_info(&pf->pdev->dev,
 			 "   ar[%02d] flags=0x%04x op=0x%04x dlen=0x%04x ret=0x%04x cookie_h=0x%08x cookie_l=0x%08x\n",
@@ -722,7 +680,7 @@ static void i40e_dbg_dump_vf(struct i40e_pf *pf, int vf_id)
 		dev_info(&pf->pdev->dev, "vf %2d: VSI id=%d, seid=%d, qps=%d\n",
 			 vf_id, vf->lan_vsi_id, vsi->seid, vf->num_queue_pairs);
 		dev_info(&pf->pdev->dev, "       num MDD=%lld\n",
-			 vf->num_mdd_events);
+			 vf->mdd_tx_events.count + vf->mdd_rx_events.count);
 	} else {
 		dev_info(&pf->pdev->dev, "invalid VF id %d\n", vf_id);
 	}
@@ -1268,10 +1226,10 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			dev_info(&pf->pdev->dev, "clear_stats vsi [seid] or clear_stats port\n");
 		}
 	} else if (strncmp(cmd_buf, "send aq_cmd", 11) == 0) {
-		struct i40e_aq_desc *desc;
+		struct libie_aq_desc *desc;
 		int ret;
 
-		desc = kzalloc(sizeof(struct i40e_aq_desc), GFP_KERNEL);
+		desc = kzalloc(sizeof(*desc), GFP_KERNEL);
 		if (!desc)
 			goto command_write_done;
 		cnt = sscanf(&cmd_buf[11],
@@ -1279,10 +1237,10 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			     &desc->flags,
 			     &desc->opcode, &desc->datalen, &desc->retval,
 			     &desc->cookie_high, &desc->cookie_low,
-			     &desc->params.internal.param0,
-			     &desc->params.internal.param1,
-			     &desc->params.internal.param2,
-			     &desc->params.internal.param3);
+			     &desc->params.generic.param0,
+			     &desc->params.generic.param1,
+			     &desc->params.generic.addr_high,
+			     &desc->params.generic.addr_low);
 		if (cnt != 10) {
 			dev_info(&pf->pdev->dev,
 				 "send aq_cmd: bad command string, cnt=%d\n",
@@ -1307,19 +1265,19 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			 "AQ desc WB 0x%04x 0x%04x 0x%04x 0x%04x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x\n",
 			 desc->flags, desc->opcode, desc->datalen, desc->retval,
 			 desc->cookie_high, desc->cookie_low,
-			 desc->params.internal.param0,
-			 desc->params.internal.param1,
-			 desc->params.internal.param2,
-			 desc->params.internal.param3);
+			 desc->params.generic.param0,
+			 desc->params.generic.param1,
+			 desc->params.generic.addr_high,
+			 desc->params.generic.addr_low);
 		kfree(desc);
 		desc = NULL;
 	} else if (strncmp(cmd_buf, "send indirect aq_cmd", 20) == 0) {
-		struct i40e_aq_desc *desc;
+		struct libie_aq_desc *desc;
 		u16 buffer_len;
 		u8 *buff;
 		int ret;
 
-		desc = kzalloc(sizeof(struct i40e_aq_desc), GFP_KERNEL);
+		desc = kzalloc(sizeof(*desc), GFP_KERNEL);
 		if (!desc)
 			goto command_write_done;
 		cnt = sscanf(&cmd_buf[20],
@@ -1327,10 +1285,10 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			     &desc->flags,
 			     &desc->opcode, &desc->datalen, &desc->retval,
 			     &desc->cookie_high, &desc->cookie_low,
-			     &desc->params.internal.param0,
-			     &desc->params.internal.param1,
-			     &desc->params.internal.param2,
-			     &desc->params.internal.param3,
+			     &desc->params.generic.param0,
+			     &desc->params.generic.param1,
+			     &desc->params.generic.addr_high,
+			     &desc->params.generic.addr_low,
 			     &buffer_len);
 		if (cnt != 11) {
 			dev_info(&pf->pdev->dev,
@@ -1350,7 +1308,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			desc = NULL;
 			goto command_write_done;
 		}
-		desc->flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+		desc->flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 		ret = i40e_asq_send_command(&pf->hw, desc, buff,
 					    buffer_len, NULL);
 		if (!ret) {
@@ -1368,10 +1326,10 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			 "AQ desc WB 0x%04x 0x%04x 0x%04x 0x%04x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x\n",
 			 desc->flags, desc->opcode, desc->datalen, desc->retval,
 			 desc->cookie_high, desc->cookie_low,
-			 desc->params.internal.param0,
-			 desc->params.internal.param1,
-			 desc->params.internal.param2,
-			 desc->params.internal.param3);
+			 desc->params.generic.param0,
+			 desc->params.generic.param1,
+			 desc->params.generic.addr_high,
+			 desc->params.generic.addr_low);
 		print_hex_dump(KERN_INFO, "AQ buffer WB: ",
 			       DUMP_PREFIX_OFFSET, 16, 1,
 			       buff, buffer_len, true);
@@ -1621,7 +1579,6 @@ command_write_done:
 static const struct file_operations i40e_dbg_command_fops = {
 	.owner = THIS_MODULE,
 	.open =  simple_open,
-	.read =  i40e_dbg_command_read,
 	.write = i40e_dbg_command_write,
 };
 
@@ -1630,48 +1587,6 @@ static const struct file_operations i40e_dbg_command_fops = {
  * The netdev_ops entry in debugfs is for giving the driver commands
  * to be executed from the netdev operations.
  **************************************************************/
-static char i40e_dbg_netdev_ops_buf[256] = "";
-
-/**
- * i40e_dbg_netdev_ops_read - read for netdev_ops datum
- * @filp: the opened file
- * @buffer: where to write the data for the user to read
- * @count: the size of the user's buffer
- * @ppos: file position offset
- **/
-static ssize_t i40e_dbg_netdev_ops_read(struct file *filp, char __user *buffer,
-					size_t count, loff_t *ppos)
-{
-	struct i40e_pf *pf = filp->private_data;
-	struct i40e_vsi *main_vsi;
-	int bytes_not_copied;
-	int buf_size = 256;
-	char *buf;
-	int len;
-
-	/* don't allow partal reads */
-	if (*ppos != 0)
-		return 0;
-	if (count < buf_size)
-		return -ENOSPC;
-
-	buf = kzalloc(buf_size, GFP_KERNEL);
-	if (!buf)
-		return -ENOSPC;
-
-	main_vsi = i40e_pf_get_main_vsi(pf);
-	len = snprintf(buf, buf_size, "%s: %s\n", main_vsi->netdev->name,
-		       i40e_dbg_netdev_ops_buf);
-
-	bytes_not_copied = copy_to_user(buffer, buf, len);
-	kfree(buf);
-
-	if (bytes_not_copied)
-		return -EFAULT;
-
-	*ppos = len;
-	return len;
-}
 
 /**
  * i40e_dbg_netdev_ops_write - write into netdev_ops datum
@@ -1685,35 +1600,36 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
 					 size_t count, loff_t *ppos)
 {
 	struct i40e_pf *pf = filp->private_data;
+	char *cmd_buf, *buf_tmp;
 	int bytes_not_copied;
 	struct i40e_vsi *vsi;
-	char *buf_tmp;
 	int vsi_seid;
 	int i, cnt;
 
 	/* don't allow partial writes */
 	if (*ppos != 0)
 		return 0;
-	if (count >= sizeof(i40e_dbg_netdev_ops_buf))
-		return -ENOSPC;
 
-	memset(i40e_dbg_netdev_ops_buf, 0, sizeof(i40e_dbg_netdev_ops_buf));
-	bytes_not_copied = copy_from_user(i40e_dbg_netdev_ops_buf,
-					  buffer, count);
-	if (bytes_not_copied)
+	cmd_buf = kzalloc(count + 1, GFP_KERNEL);
+	if (!cmd_buf)
+		return count;
+	bytes_not_copied = copy_from_user(cmd_buf, buffer, count);
+	if (bytes_not_copied) {
+		kfree(cmd_buf);
 		return -EFAULT;
-	i40e_dbg_netdev_ops_buf[count] = '\0';
+	}
+	cmd_buf[count] = '\0';
 
-	buf_tmp = strchr(i40e_dbg_netdev_ops_buf, '\n');
+	buf_tmp = strchr(cmd_buf, '\n');
 	if (buf_tmp) {
 		*buf_tmp = '\0';
-		count = buf_tmp - i40e_dbg_netdev_ops_buf + 1;
+		count = buf_tmp - cmd_buf + 1;
 	}
 
-	if (strncmp(i40e_dbg_netdev_ops_buf, "change_mtu", 10) == 0) {
+	if (strncmp(cmd_buf, "change_mtu", 10) == 0) {
 		int mtu;
 
-		cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i %i",
+		cnt = sscanf(&cmd_buf[11], "%i %i",
 			     &vsi_seid, &mtu);
 		if (cnt != 2) {
 			dev_info(&pf->pdev->dev, "change_mtu <vsi_seid> <mtu>\n");
@@ -1735,8 +1651,8 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
 			dev_info(&pf->pdev->dev, "Could not acquire RTNL - please try again\n");
 		}
 
-	} else if (strncmp(i40e_dbg_netdev_ops_buf, "set_rx_mode", 11) == 0) {
-		cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i", &vsi_seid);
+	} else if (strncmp(cmd_buf, "set_rx_mode", 11) == 0) {
+		cnt = sscanf(&cmd_buf[11], "%i", &vsi_seid);
 		if (cnt != 1) {
 			dev_info(&pf->pdev->dev, "set_rx_mode <vsi_seid>\n");
 			goto netdev_ops_write_done;
@@ -1756,8 +1672,8 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
 			dev_info(&pf->pdev->dev, "Could not acquire RTNL - please try again\n");
 		}
 
-	} else if (strncmp(i40e_dbg_netdev_ops_buf, "napi", 4) == 0) {
-		cnt = sscanf(&i40e_dbg_netdev_ops_buf[4], "%i", &vsi_seid);
+	} else if (strncmp(cmd_buf, "napi", 4) == 0) {
+		cnt = sscanf(&cmd_buf[4], "%i", &vsi_seid);
 		if (cnt != 1) {
 			dev_info(&pf->pdev->dev, "napi <vsi_seid>\n");
 			goto netdev_ops_write_done;
@@ -1775,21 +1691,20 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
 			dev_info(&pf->pdev->dev, "napi called\n");
 		}
 	} else {
-		dev_info(&pf->pdev->dev, "unknown command '%s'\n",
-			 i40e_dbg_netdev_ops_buf);
+		dev_info(&pf->pdev->dev, "unknown command '%s'\n", cmd_buf);
 		dev_info(&pf->pdev->dev, "available commands\n");
 		dev_info(&pf->pdev->dev, "  change_mtu <vsi_seid> <mtu>\n");
 		dev_info(&pf->pdev->dev, "  set_rx_mode <vsi_seid>\n");
 		dev_info(&pf->pdev->dev, "  napi <vsi_seid>\n");
 	}
 netdev_ops_write_done:
+	kfree(cmd_buf);
 	return count;
 }
 
 static const struct file_operations i40e_dbg_netdev_ops_fops = {
 	.owner = THIS_MODULE,
 	.open = simple_open,
-	.read = i40e_dbg_netdev_ops_read,
 	.write = i40e_dbg_netdev_ops_write,
 };
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_devlink.c b/drivers/net/ethernet/intel/i40e/i40e_devlink.c
index cc4e9e2addb7..229179ccc131 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_devlink.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_devlink.c
@@ -5,6 +5,42 @@
 #include "i40e.h"
 #include "i40e_devlink.h"
 
+static int i40e_max_mac_per_vf_set(struct devlink *devlink,
+				   u32 id,
+				   struct devlink_param_gset_ctx *ctx,
+				   struct netlink_ext_ack *extack)
+{
+	struct i40e_pf *pf = devlink_priv(devlink);
+
+	if (pf->num_alloc_vfs > 0) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot change max_mac_per_vf while SR-IOV is enabled");
+		return -EBUSY;
+	}
+
+	pf->max_mac_per_vf = ctx->val.vu32;
+	return 0;
+}
+
+static int i40e_max_mac_per_vf_get(struct devlink *devlink,
+				   u32 id,
+				   struct devlink_param_gset_ctx *ctx,
+				   struct netlink_ext_ack *extack)
+{
+	struct i40e_pf *pf = devlink_priv(devlink);
+
+	ctx->val.vu32 = pf->max_mac_per_vf;
+	return 0;
+}
+
+static const struct devlink_param i40e_dl_params[] = {
+	DEVLINK_PARAM_GENERIC(MAX_MAC_PER_VF,
+			      BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			      i40e_max_mac_per_vf_get,
+			      i40e_max_mac_per_vf_set,
+			      NULL),
+};
+
 static void i40e_info_get_dsn(struct i40e_pf *pf, char *buf, size_t len)
 {
 	u8 dsn[8];
@@ -165,7 +201,18 @@ void i40e_free_pf(struct i40e_pf *pf)
  **/
 void i40e_devlink_register(struct i40e_pf *pf)
 {
-	devlink_register(priv_to_devlink(pf));
+	struct devlink *dl = priv_to_devlink(pf);
+	struct device *dev = &pf->pdev->dev;
+	int err;
+
+	err = devlink_params_register(dl, i40e_dl_params,
+				      ARRAY_SIZE(i40e_dl_params));
+	if (err)
+		dev_err(dev,
+			"devlink params register failed with error %d", err);
+
+	devlink_register(dl);
+
 }
 
 /**
@@ -176,7 +223,11 @@ void i40e_devlink_register(struct i40e_pf *pf)
  **/
 void i40e_devlink_unregister(struct i40e_pf *pf)
 {
-	devlink_unregister(priv_to_devlink(pf));
+	struct devlink *dl = priv_to_devlink(pf);
+
+	devlink_unregister(dl);
+	devlink_params_unregister(dl, i40e_dl_params,
+				  ARRAY_SIZE(i40e_dl_params));
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index bce5b76f1e7a..f2c2646ea298 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -3,6 +3,7 @@
 
 /* ethtool support for i40e */
 
+#include <linux/net/intel/libie/pctype.h>
 #include "i40e_devids.h"
 #include "i40e_diag.h"
 #include "i40e_txrx_common.h"
@@ -459,6 +460,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = {
 	I40E_PRIV_FLAG("base-r-fec", I40E_FLAG_BASE_R_FEC, 0),
 	I40E_PRIV_FLAG("vf-vlan-pruning",
 		       I40E_FLAG_VF_VLAN_PRUNING_ENA, 0),
+	I40E_PRIV_FLAG("mdd-auto-reset-vf",
+		       I40E_FLAG_MDD_AUTO_RESET_VF, 0),
 };
 
 #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags)
@@ -1459,7 +1462,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 			netdev_info(netdev,
 				    "Set phy config failed, err %pe aq_err %s\n",
 				    ERR_PTR(status),
-				    i40e_aq_str(hw, hw->aq.asq_last_status));
+				    libie_aq_str(hw->aq.asq_last_status));
 			err = -EAGAIN;
 			goto done;
 		}
@@ -1469,7 +1472,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 			netdev_dbg(netdev,
 				   "Updating link info failed with err %pe aq_err %s\n",
 				   ERR_PTR(status),
-				   i40e_aq_str(hw, hw->aq.asq_last_status));
+				   libie_aq_str(hw->aq.asq_last_status));
 
 	} else {
 		netdev_info(netdev, "Nothing changed, exiting without setting anything.\n");
@@ -1517,7 +1520,7 @@ static int i40e_set_fec_cfg(struct net_device *netdev, u8 fec_cfg)
 			netdev_info(netdev,
 				    "Set phy config failed, err %pe aq_err %s\n",
 				    ERR_PTR(status),
-				    i40e_aq_str(hw, hw->aq.asq_last_status));
+				    libie_aq_str(hw->aq.asq_last_status));
 			err = -EAGAIN;
 			goto done;
 		}
@@ -1531,7 +1534,7 @@ static int i40e_set_fec_cfg(struct net_device *netdev, u8 fec_cfg)
 			netdev_dbg(netdev,
 				   "Updating link info failed with err %pe aq_err %s\n",
 				   ERR_PTR(status),
-				   i40e_aq_str(hw, hw->aq.asq_last_status));
+				   libie_aq_str(hw->aq.asq_last_status));
 	}
 
 done:
@@ -1638,7 +1641,7 @@ static int i40e_nway_reset(struct net_device *netdev)
 	if (ret) {
 		netdev_info(netdev, "link restart failed, err %pe aq_err %s\n",
 			    ERR_PTR(ret),
-			    i40e_aq_str(hw, hw->aq.asq_last_status));
+			    libie_aq_str(hw->aq.asq_last_status));
 		return -EIO;
 	}
 
@@ -1755,19 +1758,19 @@ static int i40e_set_pauseparam(struct net_device *netdev,
 	if (aq_failures & I40E_SET_FC_AQ_FAIL_GET) {
 		netdev_info(netdev, "Set fc failed on the get_phy_capabilities call with err %pe aq_err %s\n",
 			    ERR_PTR(status),
-			    i40e_aq_str(hw, hw->aq.asq_last_status));
+			    libie_aq_str(hw->aq.asq_last_status));
 		err = -EAGAIN;
 	}
 	if (aq_failures & I40E_SET_FC_AQ_FAIL_SET) {
 		netdev_info(netdev, "Set fc failed on the set_phy_config call with err %pe aq_err %s\n",
 			    ERR_PTR(status),
-			    i40e_aq_str(hw, hw->aq.asq_last_status));
+			    libie_aq_str(hw->aq.asq_last_status));
 		err = -EAGAIN;
 	}
 	if (aq_failures & I40E_SET_FC_AQ_FAIL_UPDATE) {
 		netdev_info(netdev, "Set fc failed on the get_link_info call with err %pe aq_err %s\n",
 			    ERR_PTR(status),
-			    i40e_aq_str(hw, hw->aq.asq_last_status));
+			    libie_aq_str(hw->aq.asq_last_status));
 		err = -EAGAIN;
 	}
 
@@ -1915,13 +1918,13 @@ static int i40e_get_eeprom(struct net_device *netdev,
 		ret_val = i40e_aq_read_nvm(hw, 0x0, offset, len,
 				(u8 *)eeprom_buff + (I40E_NVM_SECTOR_SIZE * i),
 				last, NULL);
-		if (ret_val && hw->aq.asq_last_status == I40E_AQ_RC_EPERM) {
+		if (ret_val && hw->aq.asq_last_status == LIBIE_AQ_RC_EPERM) {
 			dev_info(&pf->pdev->dev,
 				 "read NVM failed, invalid offset 0x%x\n",
 				 offset);
 			break;
 		} else if (ret_val &&
-			   hw->aq.asq_last_status == I40E_AQ_RC_EACCES) {
+			   hw->aq.asq_last_status == LIBIE_AQ_RC_EACCES) {
 			dev_info(&pf->pdev->dev,
 				 "read NVM failed, access, offset 0x%x\n",
 				 offset);
@@ -2747,6 +2750,15 @@ skip_ol_tests:
 	netif_info(pf, drv, netdev, "testing failed\n");
 }
 
+static void i40e_get_link_ext_stats(struct net_device *netdev,
+				    struct ethtool_link_ext_stats *stats)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_pf *pf = np->vsi->back;
+
+	stats->link_down_events = pf->link_down_events;
+}
+
 static void i40e_get_wol(struct net_device *netdev,
 			 struct ethtool_wolinfo *wol)
 {
@@ -3127,15 +3139,12 @@ static int i40e_set_per_queue_coalesce(struct net_device *netdev, u32 queue,
 	return __i40e_set_coalesce(netdev, ec, queue);
 }
 
-/**
- * i40e_get_rss_hash_opts - Get RSS hash Input Set for each flow type
- * @pf: pointer to the physical function struct
- * @cmd: ethtool rxnfc command
- *
- * Returns Success if the flow is supported, else Invalid Input.
- **/
-static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd)
+static int i40e_get_rxfh_fields(struct net_device *netdev,
+				struct ethtool_rxfh_fields *cmd)
 {
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
 	struct i40e_hw *hw = &pf->hw;
 	u8 flow_pctype = 0;
 	u64 i_set = 0;
@@ -3144,16 +3153,16 @@ static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd)
 
 	switch (cmd->flow_type) {
 	case TCP_V4_FLOW:
-		flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+		flow_pctype = LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP;
 		break;
 	case UDP_V4_FLOW:
-		flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
+		flow_pctype = LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP;
 		break;
 	case TCP_V6_FLOW:
-		flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_TCP;
+		flow_pctype = LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP;
 		break;
 	case UDP_V6_FLOW:
-		flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_UDP;
+		flow_pctype = LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP;
 		break;
 	case SCTP_V4_FLOW:
 	case AH_ESP_V4_FLOW:
@@ -3410,28 +3419,28 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
 
 	switch (rule->flow_type) {
 	case SCTP_V4_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP;
 		break;
 	case TCP_V4_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP;
 		break;
 	case UDP_V4_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP;
 		break;
 	case SCTP_V6_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_SCTP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP;
 		break;
 	case TCP_V6_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_TCP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP;
 		break;
 	case UDP_V6_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_UDP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP;
 		break;
 	case IP_USER_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER;
 		break;
 	case IPV6_USER_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_OTHER;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER;
 		break;
 	default:
 		/* If we have stored a filter with a flow type not listed here
@@ -3513,6 +3522,20 @@ no_input_set:
 }
 
 /**
+ * i40e_get_rx_ring_count - get RX ring count
+ * @netdev: network interface device structure
+ *
+ * Return: number of RX rings.
+ **/
+static u32 i40e_get_rx_ring_count(struct net_device *netdev)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_vsi *vsi = np->vsi;
+
+	return vsi->rss_size;
+}
+
+/**
  * i40e_get_rxnfc - command to get RX flow classification rules
  * @netdev: network interface device structure
  * @cmd: ethtool rxnfc command
@@ -3529,13 +3552,6 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 	int ret = -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
-	case ETHTOOL_GRXRINGS:
-		cmd->data = vsi->rss_size;
-		ret = 0;
-		break;
-	case ETHTOOL_GRXFH:
-		ret = i40e_get_rss_hash_opts(pf, cmd);
-		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = pf->fdir_pf_active_filters;
 		/* report total rule count */
@@ -3564,7 +3580,7 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
  * Returns value of bits to be set per user request
  **/
 static u64 i40e_get_rss_hash_bits(struct i40e_hw *hw,
-				  struct ethtool_rxnfc *nfc,
+				  const struct ethtool_rxfh_fields *nfc,
 				  u64 i_setc)
 {
 	u64 i_set = i_setc;
@@ -3609,15 +3625,13 @@ static u64 i40e_get_rss_hash_bits(struct i40e_hw *hw,
 }
 
 #define FLOW_PCTYPES_SIZE 64
-/**
- * i40e_set_rss_hash_opt - Enable/Disable flow types for RSS hash
- * @pf: pointer to the physical function struct
- * @nfc: ethtool rxnfc command
- *
- * Returns Success if the flow input set is supported.
- **/
-static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
+static int i40e_set_rxfh_fields(struct net_device *netdev,
+				const struct ethtool_rxfh_fields *nfc,
+				struct netlink_ext_ack *extack)
 {
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
 	struct i40e_hw *hw = &pf->hw;
 	u64 hena = (u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(0)) |
 		   ((u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(1)) << 32);
@@ -3641,40 +3655,40 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 
 	switch (nfc->flow_type) {
 	case TCP_V4_FLOW:
-		set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP, flow_pctypes);
+		set_bit(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP, flow_pctypes);
 		if (test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE,
 			     pf->hw.caps))
-			set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK,
+			set_bit(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK,
 				flow_pctypes);
 		break;
 	case TCP_V6_FLOW:
-		set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP, flow_pctypes);
+		set_bit(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP, flow_pctypes);
 		if (test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE,
 			     pf->hw.caps))
-			set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK,
+			set_bit(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK,
 				flow_pctypes);
 		break;
 	case UDP_V4_FLOW:
-		set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_UDP, flow_pctypes);
+		set_bit(LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP, flow_pctypes);
 		if (test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE,
 			     pf->hw.caps)) {
-			set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP,
+			set_bit(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP,
 				flow_pctypes);
-			set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP,
+			set_bit(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP,
 				flow_pctypes);
 		}
-		hena |= BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4);
+		hena |= BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV4);
 		break;
 	case UDP_V6_FLOW:
-		set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_UDP, flow_pctypes);
+		set_bit(LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP, flow_pctypes);
 		if (test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE,
 			     pf->hw.caps)) {
-			set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP,
+			set_bit(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP,
 				flow_pctypes);
-			set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP,
+			set_bit(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP,
 				flow_pctypes);
 		}
-		hena |= BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6);
+		hena |= BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV6);
 		break;
 	case AH_ESP_V4_FLOW:
 	case AH_V4_FLOW:
@@ -3683,7 +3697,7 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 		if ((nfc->data & RXH_L4_B_0_1) ||
 		    (nfc->data & RXH_L4_B_2_3))
 			return -EINVAL;
-		hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_OTHER);
+		hena |= BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER);
 		break;
 	case AH_ESP_V6_FLOW:
 	case AH_V6_FLOW:
@@ -3692,15 +3706,15 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 		if ((nfc->data & RXH_L4_B_0_1) ||
 		    (nfc->data & RXH_L4_B_2_3))
 			return -EINVAL;
-		hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_OTHER);
+		hena |= BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER);
 		break;
 	case IPV4_FLOW:
-		hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_OTHER) |
-			BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4);
+		hena |= BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER) |
+			BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV4);
 		break;
 	case IPV6_FLOW:
-		hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_OTHER) |
-			BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6);
+		hena |= BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER) |
+			BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV6);
 		break;
 	default:
 		return -EINVAL;
@@ -4310,36 +4324,36 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi,
 
 	switch (fsp->flow_type & ~FLOW_EXT) {
 	case SCTP_V4_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP;
 		fdir_filter_count = &pf->fd_sctp4_filter_cnt;
 		break;
 	case TCP_V4_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP;
 		fdir_filter_count = &pf->fd_tcp4_filter_cnt;
 		break;
 	case UDP_V4_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP;
 		fdir_filter_count = &pf->fd_udp4_filter_cnt;
 		break;
 	case SCTP_V6_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_SCTP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP;
 		fdir_filter_count = &pf->fd_sctp6_filter_cnt;
 		break;
 	case TCP_V6_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_TCP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP;
 		fdir_filter_count = &pf->fd_tcp6_filter_cnt;
 		break;
 	case UDP_V6_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_UDP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP;
 		fdir_filter_count = &pf->fd_udp6_filter_cnt;
 		break;
 	case IP_USER_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER;
 		fdir_filter_count = &pf->fd_ip4_filter_cnt;
 		flex_l3 = true;
 		break;
 	case IPV6_USER_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_OTHER;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER;
 		fdir_filter_count = &pf->fd_ip6_filter_cnt;
 		flex_l3 = true;
 		break;
@@ -4675,8 +4689,8 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi,
 	 * separate support, we'll always assume and enforce that the two flow
 	 * types must have matching input sets.
 	 */
-	if (index == I40E_FILTER_PCTYPE_NONF_IPV4_OTHER)
-		i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_FRAG_IPV4,
+	if (index == LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER)
+		i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_FRAG_IPV4,
 					new_mask);
 
 	/* Add the new offset and update table, if necessary */
@@ -4952,13 +4966,9 @@ static int i40e_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
-	struct i40e_pf *pf = vsi->back;
 	int ret = -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
-	case ETHTOOL_SRXFH:
-		ret = i40e_set_rss_hash_opt(pf, cmd);
-		break;
 	case ETHTOOL_SRXCLSRLINS:
 		ret = i40e_add_fdir_ethtool(vsi, cmd);
 		break;
@@ -5249,9 +5259,9 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 	DECLARE_BITMAP(orig_flags, I40E_PF_FLAGS_NBITS);
 	DECLARE_BITMAP(new_flags, I40E_PF_FLAGS_NBITS);
 	struct i40e_netdev_priv *np = netdev_priv(dev);
-	enum i40e_admin_queue_err adq_err;
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
+	enum libie_aq_err adq_err;
 	u32 reset_needed = 0;
 	int status;
 	u32 i, j;
@@ -5371,12 +5381,11 @@ flags_complete:
 		valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
 		ret = i40e_aq_set_switch_config(&pf->hw, sw_flags, valid_flags,
 						0, NULL);
-		if (ret && pf->hw.aq.asq_last_status != I40E_AQ_RC_ESRCH) {
+		if (ret && pf->hw.aq.asq_last_status != LIBIE_AQ_RC_ESRCH) {
 			dev_info(&pf->pdev->dev,
 				 "couldn't set switch config bits, err %pe aq_err %s\n",
 				 ERR_PTR(ret),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+				 libie_aq_str(pf->hw.aq.asq_last_status));
 			/* not a fatal problem, just keep going */
 		}
 	}
@@ -5438,16 +5447,16 @@ flags_complete:
 			if (status) {
 				adq_err = pf->hw.aq.asq_last_status;
 				switch (adq_err) {
-				case I40E_AQ_RC_EEXIST:
+				case LIBIE_AQ_RC_EEXIST:
 					dev_warn(&pf->pdev->dev,
 						 "FW LLDP agent is already running\n");
 					reset_needed = 0;
 					break;
-				case I40E_AQ_RC_EPERM:
+				case LIBIE_AQ_RC_EPERM:
 					dev_warn(&pf->pdev->dev,
 						 "Device configuration forbids SW from starting the LLDP agent.\n");
 					return -EINVAL;
-				case I40E_AQ_RC_EAGAIN:
+				case LIBIE_AQ_RC_EAGAIN:
 					dev_warn(&pf->pdev->dev,
 						 "Stop FW LLDP agent command is still being processed, please try again in a second.\n");
 					return -EBUSY;
@@ -5455,8 +5464,7 @@ flags_complete:
 					dev_warn(&pf->pdev->dev,
 						 "Starting FW LLDP agent failed: error: %pe, %s\n",
 						 ERR_PTR(status),
-						 i40e_aq_str(&pf->hw,
-							     adq_err));
+						 libie_aq_str(adq_err));
 					return -EINVAL;
 				}
 			}
@@ -5807,6 +5815,7 @@ static const struct ethtool_ops i40e_ethtool_ops = {
 	.get_regs		= i40e_get_regs,
 	.nway_reset		= i40e_nway_reset,
 	.get_link		= ethtool_op_get_link,
+	.get_link_ext_stats	= i40e_get_link_ext_stats,
 	.get_wol		= i40e_get_wol,
 	.set_wol		= i40e_set_wol,
 	.set_eeprom		= i40e_set_eeprom,
@@ -5820,6 +5829,7 @@ static const struct ethtool_ops i40e_ethtool_ops = {
 	.set_msglevel		= i40e_set_msglevel,
 	.get_rxnfc		= i40e_get_rxnfc,
 	.set_rxnfc		= i40e_set_rxnfc,
+	.get_rx_ring_count	= i40e_get_rx_ring_count,
 	.self_test		= i40e_diag_test,
 	.get_strings		= i40e_get_strings,
 	.get_eee		= i40e_get_eee,
@@ -5833,6 +5843,8 @@ static const struct ethtool_ops i40e_ethtool_ops = {
 	.get_rxfh_indir_size	= i40e_get_rxfh_indir_size,
 	.get_rxfh		= i40e_get_rxfh,
 	.set_rxfh		= i40e_set_rxfh,
+	.get_rxfh_fields	= i40e_get_rxfh_fields,
+	.set_rxfh_fields	= i40e_set_rxfh_fields,
 	.get_channels		= i40e_get_channels,
 	.set_channels		= i40e_set_channels,
 	.get_module_info	= i40e_get_module_info,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 0e1d9e2fbf38..d8192aa23254 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3,6 +3,7 @@
 
 #include <generated/utsrelease.h>
 #include <linux/crash_dump.h>
+#include <linux/net/intel/libie/pctype.h>
 #include <linux/if_bridge.h>
 #include <linux/if_macvlan.h>
 #include <linux/module.h>
@@ -100,6 +101,7 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all), Debug mask (0x8XXXXXXX
 
 MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver");
 MODULE_IMPORT_NS("LIBIE");
+MODULE_IMPORT_NS("LIBIE_ADMINQ");
 MODULE_LICENSE("GPL v2");
 
 static struct workqueue_struct *i40e_wq;
@@ -1241,12 +1243,30 @@ void i40e_update_stats(struct i40e_vsi *vsi)
 }
 
 /**
- * i40e_count_filters - counts VSI mac filters
+ * i40e_count_all_filters - counts VSI MAC filters
  * @vsi: the VSI to be searched
  *
- * Returns count of mac filters
- **/
-int i40e_count_filters(struct i40e_vsi *vsi)
+ * Return: count of MAC filters in any state.
+ */
+int i40e_count_all_filters(struct i40e_vsi *vsi)
+{
+	struct i40e_mac_filter *f;
+	struct hlist_node *h;
+	int bkt, cnt = 0;
+
+	hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist)
+		cnt++;
+
+	return cnt;
+}
+
+/**
+ * i40e_count_active_filters - counts VSI MAC filters
+ * @vsi: the VSI to be searched
+ *
+ * Return: count of active MAC filters.
+ */
+int i40e_count_active_filters(struct i40e_vsi *vsi)
 {
 	struct i40e_mac_filter *f;
 	struct hlist_node *h;
@@ -1666,9 +1686,8 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
  * @vsi: VSI to remove from
  * @f: the filter to remove from the list
  *
- * This function should be called instead of i40e_del_filter only if you know
- * the exact filter you will remove already, such as via i40e_find_filter or
- * i40e_find_mac.
+ * This function requires you've found * the exact filter you will remove
+ * already, such as via i40e_find_filter or i40e_find_mac.
  *
  * NOTE: This function is expected to be called with mac_filter_hash_lock
  * being held.
@@ -1698,29 +1717,6 @@ void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f)
 }
 
 /**
- * i40e_del_filter - Remove a MAC/VLAN filter from the VSI
- * @vsi: the VSI to be searched
- * @macaddr: the MAC address
- * @vlan: the VLAN
- *
- * NOTE: This function is expected to be called with mac_filter_hash_lock
- * being held.
- * ANOTHER NOTE: This function MUST be called from within the context of
- * the "safe" variants of any list iterators, e.g. list_for_each_entry_safe()
- * instead of list_for_each_entry().
- **/
-void i40e_del_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan)
-{
-	struct i40e_mac_filter *f;
-
-	if (!vsi || !macaddr)
-		return;
-
-	f = i40e_find_filter(vsi, macaddr, vlan);
-	__i40e_del_filter(vsi, f);
-}
-
-/**
  * i40e_add_mac_filter - Add a MAC filter for all active VLANs
  * @vsi: the VSI to be searched
  * @macaddr: the mac address to be filtered
@@ -1837,7 +1833,7 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
 		if (ret)
 			netdev_info(netdev, "Ignoring error from firmware on LAA update, status %pe, AQ ret %s\n",
 				    ERR_PTR(ret),
-				    i40e_aq_str(hw, hw->aq.asq_last_status));
+				    libie_aq_str(hw->aq.asq_last_status));
 	}
 
 	/* schedule our worker thread which will take care of
@@ -1869,7 +1865,7 @@ static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
 			dev_info(&pf->pdev->dev,
 				 "Cannot set RSS key, err %pe aq_err %s\n",
 				 ERR_PTR(ret),
-				 i40e_aq_str(hw, hw->aq.asq_last_status));
+				 libie_aq_str(hw->aq.asq_last_status));
 			return ret;
 		}
 	}
@@ -1881,7 +1877,7 @@ static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
 			dev_info(&pf->pdev->dev,
 				 "Cannot set RSS lut, err %pe aq_err %s\n",
 				 ERR_PTR(ret),
-				 i40e_aq_str(hw, hw->aq.asq_last_status));
+				 libie_aq_str(hw->aq.asq_last_status));
 			return ret;
 		}
 	}
@@ -2363,19 +2359,18 @@ void i40e_aqc_del_filters(struct i40e_vsi *vsi, const char *vsi_name,
 			  int num_del, int *retval)
 {
 	struct i40e_hw *hw = &vsi->back->hw;
-	enum i40e_admin_queue_err aq_status;
+	enum libie_aq_err aq_status;
 	int aq_ret;
 
 	aq_ret = i40e_aq_remove_macvlan_v2(hw, vsi->seid, list, num_del, NULL,
 					   &aq_status);
 
 	/* Explicitly ignore and do not report when firmware returns ENOENT */
-	if (aq_ret && !(aq_status == I40E_AQ_RC_ENOENT)) {
+	if (aq_ret && !(aq_status == LIBIE_AQ_RC_ENOENT)) {
 		*retval = -EIO;
 		dev_info(&vsi->back->pdev->dev,
 			 "ignoring delete macvlan error on %s, err %pe, aq_err %s\n",
-			 vsi_name, ERR_PTR(aq_ret),
-			 i40e_aq_str(hw, aq_status));
+			 vsi_name, ERR_PTR(aq_ret), libie_aq_str(aq_status));
 	}
 }
 
@@ -2398,7 +2393,7 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name,
 			  int num_add)
 {
 	struct i40e_hw *hw = &vsi->back->hw;
-	enum i40e_admin_queue_err aq_status;
+	enum libie_aq_err aq_status;
 	int fcnt;
 
 	i40e_aq_add_macvlan_v2(hw, vsi->seid, list, num_add, NULL, &aq_status);
@@ -2409,19 +2404,17 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name,
 			set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
 			dev_warn(&vsi->back->pdev->dev,
 				 "Error %s adding RX filters on %s, promiscuous mode forced on\n",
-				 i40e_aq_str(hw, aq_status), vsi_name);
+				 libie_aq_str(aq_status), vsi_name);
 		} else if (vsi->type == I40E_VSI_SRIOV ||
 			   vsi->type == I40E_VSI_VMDQ1 ||
 			   vsi->type == I40E_VSI_VMDQ2) {
 			dev_warn(&vsi->back->pdev->dev,
 				 "Error %s adding RX filters on %s, please set promiscuous on manually for %s\n",
-				 i40e_aq_str(hw, aq_status), vsi_name,
-					     vsi_name);
+				 libie_aq_str(aq_status), vsi_name, vsi_name);
 		} else {
 			dev_warn(&vsi->back->pdev->dev,
 				 "Error %s adding RX filters on %s, incorrect VSI type: %i.\n",
-				 i40e_aq_str(hw, aq_status), vsi_name,
-					     vsi->type);
+				 libie_aq_str(aq_status), vsi_name, vsi->type);
 		}
 	}
 }
@@ -2464,8 +2457,7 @@ i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name,
 		set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
 		dev_warn(&vsi->back->pdev->dev,
 			 "Error %s, forcing overflow promiscuous on %s\n",
-			 i40e_aq_str(hw, hw->aq.asq_last_status),
-			 vsi_name);
+			 libie_aq_str(hw->aq.asq_last_status), vsi_name);
 	}
 
 	return aq_ret;
@@ -2506,7 +2498,7 @@ static int i40e_set_promiscuous(struct i40e_pf *pf, bool promisc)
 			dev_info(&pf->pdev->dev,
 				 "Set default VSI failed, err %pe, aq_err %s\n",
 				 ERR_PTR(aq_ret),
-				 i40e_aq_str(hw, hw->aq.asq_last_status));
+				 libie_aq_str(hw->aq.asq_last_status));
 		}
 	} else {
 		aq_ret = i40e_aq_set_vsi_unicast_promiscuous(
@@ -2518,7 +2510,7 @@ static int i40e_set_promiscuous(struct i40e_pf *pf, bool promisc)
 			dev_info(&pf->pdev->dev,
 				 "set unicast promisc failed, err %pe, aq_err %s\n",
 				 ERR_PTR(aq_ret),
-				 i40e_aq_str(hw, hw->aq.asq_last_status));
+				 libie_aq_str(hw->aq.asq_last_status));
 		}
 		aq_ret = i40e_aq_set_vsi_multicast_promiscuous(
 						  hw,
@@ -2528,7 +2520,7 @@ static int i40e_set_promiscuous(struct i40e_pf *pf, bool promisc)
 			dev_info(&pf->pdev->dev,
 				 "set multicast promisc failed, err %pe, aq_err %s\n",
 				 ERR_PTR(aq_ret),
-				 i40e_aq_str(hw, hw->aq.asq_last_status));
+				 libie_aq_str(hw->aq.asq_last_status));
 		}
 	}
 
@@ -2836,7 +2828,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 				 "set multi promisc failed on %s, err %pe aq_err %s\n",
 				 vsi_name,
 				 ERR_PTR(aq_ret),
-				 i40e_aq_str(hw, hw->aq.asq_last_status));
+				 libie_aq_str(hw->aq.asq_last_status));
 		} else {
 			dev_info(&pf->pdev->dev, "%s allmulti mode.\n",
 				 cur_multipromisc ? "entering" : "leaving");
@@ -2857,7 +2849,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 				 cur_promisc ? "on" : "off",
 				 vsi_name,
 				 ERR_PTR(aq_ret),
-				 i40e_aq_str(hw, hw->aq.asq_last_status));
+				 libie_aq_str(hw->aq.asq_last_status));
 		}
 	}
 out:
@@ -2978,27 +2970,6 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu)
 }
 
 /**
- * i40e_ioctl - Access the hwtstamp interface
- * @netdev: network interface device structure
- * @ifr: interface request data
- * @cmd: ioctl command
- **/
-int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
-{
-	struct i40e_netdev_priv *np = netdev_priv(netdev);
-	struct i40e_pf *pf = np->vsi->back;
-
-	switch (cmd) {
-	case SIOCGHWTSTAMP:
-		return i40e_ptp_get_ts_config(pf, ifr);
-	case SIOCSHWTSTAMP:
-		return i40e_ptp_set_ts_config(pf, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-/**
  * i40e_vlan_stripping_enable - Turn on vlan stripping for the VSI
  * @vsi: the vsi being adjusted
  **/
@@ -3027,8 +2998,7 @@ void i40e_vlan_stripping_enable(struct i40e_vsi *vsi)
 		dev_info(&vsi->back->pdev->dev,
 			 "update vlan stripping failed, err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(&vsi->back->hw,
-				     vsi->back->hw.aq.asq_last_status));
+			 libie_aq_str(vsi->back->hw.aq.asq_last_status));
 	}
 }
 
@@ -3062,8 +3032,7 @@ void i40e_vlan_stripping_disable(struct i40e_vsi *vsi)
 		dev_info(&vsi->back->pdev->dev,
 			 "update vlan stripping failed, err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(&vsi->back->hw,
-				     vsi->back->hw.aq.asq_last_status));
+			 libie_aq_str(vsi->back->hw.aq.asq_last_status));
 	}
 }
 
@@ -3307,8 +3276,7 @@ int i40e_vsi_add_pvid(struct i40e_vsi *vsi, u16 vid)
 		dev_info(&vsi->back->pdev->dev,
 			 "add pvid failed, err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(&vsi->back->hw,
-				     vsi->back->hw.aq.asq_last_status));
+			 libie_aq_str(vsi->back->hw.aq.asq_last_status));
 		return -ENOENT;
 	}
 
@@ -4206,7 +4174,7 @@ free_queue_irqs:
 		irq_num = pf->msix_entries[base + vector].vector;
 		irq_set_affinity_notifier(irq_num, NULL);
 		irq_update_affinity_hint(irq_num, NULL);
-		free_irq(irq_num, &vsi->q_vectors[vector]);
+		free_irq(irq_num, vsi->q_vectors[vector]);
 	}
 	return err;
 }
@@ -5578,7 +5546,7 @@ static int i40e_vsi_get_bw_info(struct i40e_vsi *vsi)
 		dev_info(&pf->pdev->dev,
 			 "couldn't get PF vsi bw config, err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 libie_aq_str(pf->hw.aq.asq_last_status));
 		return -EINVAL;
 	}
 
@@ -5589,7 +5557,7 @@ static int i40e_vsi_get_bw_info(struct i40e_vsi *vsi)
 		dev_info(&pf->pdev->dev,
 			 "couldn't get PF vsi ets bw config, err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 libie_aq_str(pf->hw.aq.asq_last_status));
 		return -EINVAL;
 	}
 
@@ -5779,7 +5747,7 @@ int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset)
 	if (ret) {
 		dev_info(&pf->pdev->dev, "Update vsi config failed, err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(hw, hw->aq.asq_last_status));
+			 libie_aq_str(hw->aq.asq_last_status));
 		return ret;
 	}
 	/* update the local VSI info with updated queue map */
@@ -5835,7 +5803,7 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc)
 			dev_info(&pf->pdev->dev,
 				 "Failed querying vsi bw info, err %pe aq_err %s\n",
 				 ERR_PTR(ret),
-				 i40e_aq_str(hw, hw->aq.asq_last_status));
+				 libie_aq_str(hw->aq.asq_last_status));
 			goto out;
 		}
 		if ((bw_config.tc_valid_bits & enabled_tc) != enabled_tc) {
@@ -5902,7 +5870,7 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc)
 		dev_info(&pf->pdev->dev,
 			 "Update vsi tc config failed, err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(hw, hw->aq.asq_last_status));
+			 libie_aq_str(hw->aq.asq_last_status));
 		goto out;
 	}
 	/* update the local VSI info with updated queue map */
@@ -5915,7 +5883,7 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc)
 		dev_info(&pf->pdev->dev,
 			 "Failed updating vsi bw info, err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(hw, hw->aq.asq_last_status));
+			 libie_aq_str(hw->aq.asq_last_status));
 		goto out;
 	}
 
@@ -6029,7 +5997,7 @@ int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate)
 		dev_err(&pf->pdev->dev,
 			"Failed set tx rate (%llu Mbps) for vsi->seid %u, err %pe aq_err %s\n",
 			max_tx_rate, seid, ERR_PTR(ret),
-			i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			libie_aq_str(pf->hw.aq.asq_last_status));
 	return ret;
 }
 
@@ -6041,8 +6009,8 @@ int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate)
  **/
 static void i40e_remove_queue_channels(struct i40e_vsi *vsi)
 {
-	enum i40e_admin_queue_err last_aq_status;
 	struct i40e_cloud_filter *cfilter;
+	enum libie_aq_err last_aq_status;
 	struct i40e_channel *ch, *ch_tmp;
 	struct i40e_pf *pf = vsi->back;
 	struct hlist_node *node;
@@ -6105,7 +6073,7 @@ static void i40e_remove_queue_channels(struct i40e_vsi *vsi)
 				dev_info(&pf->pdev->dev,
 					 "Failed to delete cloud filter, err %pe aq_err %s\n",
 					 ERR_PTR(ret),
-					 i40e_aq_str(&pf->hw, last_aq_status));
+					 libie_aq_str(last_aq_status));
 			kfree(cfilter);
 		}
 
@@ -6240,7 +6208,7 @@ static int i40e_vsi_reconfig_rss(struct i40e_vsi *vsi, u16 rss_size)
 		dev_info(&pf->pdev->dev,
 			 "Cannot set RSS lut, err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(hw, hw->aq.asq_last_status));
+			 libie_aq_str(hw->aq.asq_last_status));
 		kfree(lut);
 		return ret;
 	}
@@ -6339,8 +6307,7 @@ static int i40e_add_channel(struct i40e_pf *pf, u16 uplink_seid,
 		dev_info(&pf->pdev->dev,
 			 "add new vsi failed, err %pe aq_err %s\n",
 			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw,
-				     pf->hw.aq.asq_last_status));
+			 libie_aq_str(pf->hw.aq.asq_last_status));
 		return -ENOENT;
 	}
 
@@ -6583,12 +6550,10 @@ static int i40e_validate_and_set_switch_mode(struct i40e_vsi *vsi)
 	ret = i40e_aq_set_switch_config(hw, pf->last_sw_conf_flags,
 					pf->last_sw_conf_valid_flags,
 					mode, NULL);
-	if (ret && hw->aq.asq_last_status != I40E_AQ_RC_ESRCH)
+	if (ret && hw->aq.asq_last_status != LIBIE_AQ_RC_ESRCH)
 		dev_err(&pf->pdev->dev,
 			"couldn't set switch config bits, err %pe aq_err %s\n",
-			ERR_PTR(ret),
-			i40e_aq_str(hw,
-				    hw->aq.asq_last_status));
+			ERR_PTR(ret), libie_aq_str(hw->aq.asq_last_status));
 
 	return ret;
 }
@@ -6787,8 +6752,7 @@ int i40e_veb_config_tc(struct i40e_veb *veb, u8 enabled_tc)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "VEB bw config failed, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 		goto out;
 	}
 
@@ -6797,8 +6761,7 @@ int i40e_veb_config_tc(struct i40e_veb *veb, u8 enabled_tc)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "Failed getting veb bw config, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 	}
 
 out:
@@ -6879,7 +6842,7 @@ static int i40e_resume_port_tx(struct i40e_pf *pf)
 		dev_info(&pf->pdev->dev,
 			 "Resume Port Tx failed, err %pe aq_err %s\n",
 			  ERR_PTR(ret),
-			  i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			  libie_aq_str(pf->hw.aq.asq_last_status));
 		/* Schedule PF reset to recover */
 		set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 		i40e_service_event_schedule(pf);
@@ -6903,8 +6866,7 @@ static int i40e_suspend_port_tx(struct i40e_pf *pf)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "Suspend Port Tx failed, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 		/* Schedule PF reset to recover */
 		set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 		i40e_service_event_schedule(pf);
@@ -6943,8 +6905,7 @@ static int i40e_hw_set_dcb_config(struct i40e_pf *pf,
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "Set DCB Config failed, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 		goto out;
 	}
 
@@ -7060,8 +7021,7 @@ int i40e_hw_dcb_config(struct i40e_pf *pf, struct i40e_dcbx_config *new_cfg)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "Modify Port ETS failed, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 		goto out;
 	}
 
@@ -7100,8 +7060,7 @@ int i40e_hw_dcb_config(struct i40e_pf *pf, struct i40e_dcbx_config *new_cfg)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "DCB Updated failed, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 		goto out;
 	}
 
@@ -7184,8 +7143,7 @@ int i40e_dcb_sw_default_config(struct i40e_pf *pf)
 	if (err) {
 		dev_info(&pf->pdev->dev,
 			 "Enable Port ETS failed, err %pe aq_err %s\n",
-			 ERR_PTR(err),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status));
 		err = -ENOENT;
 		goto out;
 	}
@@ -7258,14 +7216,13 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 			dev_dbg(&pf->pdev->dev,
 				"DCBX offload is supported for this PF.\n");
 		}
-	} else if (pf->hw.aq.asq_last_status == I40E_AQ_RC_EPERM) {
+	} else if (pf->hw.aq.asq_last_status == LIBIE_AQ_RC_EPERM) {
 		dev_info(&pf->pdev->dev, "FW LLDP disabled for this PF.\n");
 		set_bit(I40E_FLAG_FW_LLDP_DIS, pf->flags);
 	} else {
 		dev_info(&pf->pdev->dev,
 			 "Query for DCB configuration failed, err %pe aq_err %s\n",
-			 ERR_PTR(err),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status));
 	}
 
 out:
@@ -7521,8 +7478,7 @@ static int i40e_force_link_state(struct i40e_pf *pf, bool is_up)
 	if (err) {
 		dev_err(&pf->pdev->dev,
 			"failed to get phy cap., ret =  %pe last_status =  %s\n",
-			ERR_PTR(err),
-			i40e_aq_str(hw, hw->aq.asq_last_status));
+			ERR_PTR(err), libie_aq_str(hw->aq.asq_last_status));
 		return err;
 	}
 	speed = abilities.link_speed;
@@ -7533,8 +7489,7 @@ static int i40e_force_link_state(struct i40e_pf *pf, bool is_up)
 	if (err) {
 		dev_err(&pf->pdev->dev,
 			"failed to get phy cap., ret =  %pe last_status =  %s\n",
-			ERR_PTR(err),
-			i40e_aq_str(hw, hw->aq.asq_last_status));
+			ERR_PTR(err), libie_aq_str(hw->aq.asq_last_status));
 		return err;
 	}
 
@@ -7578,8 +7533,7 @@ static int i40e_force_link_state(struct i40e_pf *pf, bool is_up)
 	if (err) {
 		dev_err(&pf->pdev->dev,
 			"set phy config ret =  %pe last_status =  %s\n",
-			ERR_PTR(err),
-			i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status));
 		return err;
 	}
 
@@ -7919,8 +7873,7 @@ static int i40e_fwd_ring_up(struct i40e_vsi *vsi, struct net_device *vdev,
 		}
 		dev_info(&pf->pdev->dev,
 			 "Error adding mac filter on macvlan err %pe, aq_err %s\n",
-			  ERR_PTR(ret),
-			  i40e_aq_str(hw, aq_err));
+			  ERR_PTR(ret), libie_aq_str(aq_err));
 		netdev_err(vdev, "L2fwd offload disabled to L2 filter error\n");
 	}
 
@@ -7992,8 +7945,7 @@ static int i40e_setup_macvlans(struct i40e_vsi *vsi, u16 macvlan_cnt, u16 qcnt,
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "Update vsi tc config failed, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(hw, hw->aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(hw->aq.asq_last_status));
 		return ret;
 	}
 	/* update the local VSI info with updated queue map */
@@ -8208,8 +8160,7 @@ static void i40e_fwd_del(struct net_device *netdev, void *vdev)
 			} else {
 				dev_info(&pf->pdev->dev,
 					 "Error deleting mac filter on macvlan err %pe, aq_err %s\n",
-					  ERR_PTR(ret),
-					  i40e_aq_str(hw, aq_err));
+					  ERR_PTR(ret), libie_aq_str(aq_err));
 			}
 			break;
 		}
@@ -9212,47 +9163,47 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf)
 	i40e_reset_fdir_filter_cnt(pf);
 
 	/* Reprogram the default input set for TCP/IPv4 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_TCP,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
 				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
 	/* Reprogram the default input set for TCP/IPv6 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV6_TCP,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP,
 				I40E_L3_V6_SRC_MASK | I40E_L3_V6_DST_MASK |
 				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
 	/* Reprogram the default input set for UDP/IPv4 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_UDP,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
 				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
 	/* Reprogram the default input set for UDP/IPv6 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV6_UDP,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP,
 				I40E_L3_V6_SRC_MASK | I40E_L3_V6_DST_MASK |
 				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
 	/* Reprogram the default input set for SCTP/IPv4 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_SCTP,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
 				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
 	/* Reprogram the default input set for SCTP/IPv6 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV6_SCTP,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP,
 				I40E_L3_V6_SRC_MASK | I40E_L3_V6_DST_MASK |
 				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
 	/* Reprogram the default input set for Other/IPv4 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_OTHER,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
 
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_FRAG_IPV4,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_FRAG_IPV4,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
 
 	/* Reprogram the default input set for Other/IPv6 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV6_OTHER,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
 
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_FRAG_IPV6,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_FRAG_IPV6,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
 }
 
@@ -9463,8 +9414,7 @@ bool i40e_dcb_need_reconfig(struct i40e_pf *pf,
 static int i40e_handle_lldp_event(struct i40e_pf *pf,
 				  struct i40e_arq_event_info *e)
 {
-	struct i40e_aqc_lldp_get_mib *mib =
-		(struct i40e_aqc_lldp_get_mib *)&e->desc.params.raw;
+	struct i40e_aqc_lldp_get_mib *mib = libie_aq_raw(&e->desc);
 	struct i40e_hw *hw = &pf->hw;
 	struct i40e_dcbx_config tmp_dcbx_cfg;
 	bool need_reconfig = false;
@@ -9521,8 +9471,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 			dev_info(&pf->pdev->dev,
 				 "Failed querying DCB configuration data from firmware, err %pe aq_err %s\n",
 				 ERR_PTR(ret),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+				 libie_aq_str(pf->hw.aq.asq_last_status));
 		}
 		goto exit;
 	}
@@ -9603,8 +9552,7 @@ void i40e_do_reset_safe(struct i40e_pf *pf, u32 reset_flags)
 static void i40e_handle_lan_overflow_event(struct i40e_pf *pf,
 					   struct i40e_arq_event_info *e)
 {
-	struct i40e_aqc_lan_overflow *data =
-		(struct i40e_aqc_lan_overflow *)&e->desc.params.raw;
+	struct i40e_aqc_lan_overflow *data = libie_aq_raw(&e->desc);
 	u32 queue = le32_to_cpu(data->prtdcb_rupto);
 	u32 qtx_ctl = le32_to_cpu(data->otx_ctl);
 	struct i40e_hw *hw = &pf->hw;
@@ -9629,19 +9577,6 @@ static void i40e_handle_lan_overflow_event(struct i40e_pf *pf,
 }
 
 /**
- * i40e_get_cur_guaranteed_fd_count - Get the consumed guaranteed FD filters
- * @pf: board private structure
- **/
-u32 i40e_get_cur_guaranteed_fd_count(struct i40e_pf *pf)
-{
-	u32 val, fcnt_prog;
-
-	val = rd32(&pf->hw, I40E_PFQF_FDSTAT);
-	fcnt_prog = (val & I40E_PFQF_FDSTAT_GUARANT_CNT_MASK);
-	return fcnt_prog;
-}
-
-/**
  * i40e_get_current_fd_count - Get total FD filters programmed for this PF
  * @pf: board private structure
  **/
@@ -9693,7 +9628,7 @@ static void i40e_reenable_fdir_atr(struct i40e_pf *pf)
 		 * settings. It is safe to restore the default input set
 		 * because there are no active TCPv4 filter rules.
 		 */
-		i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_TCP,
+		i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP,
 					I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
 					I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
@@ -9996,6 +9931,9 @@ static void i40e_link_event(struct i40e_pf *pf)
 	     new_link == netif_carrier_ok(vsi->netdev)))
 		return;
 
+	if (!new_link && old_link)
+		pf->link_down_events++;
+
 	i40e_print_link_message(vsi, new_link);
 
 	/* Notify the base of the switch tree connected to
@@ -10134,8 +10072,7 @@ static void i40e_reset_subtask(struct i40e_pf *pf)
 static void i40e_handle_link_event(struct i40e_pf *pf,
 				   struct i40e_arq_event_info *e)
 {
-	struct i40e_aqc_get_link_status *status =
-		(struct i40e_aqc_get_link_status *)&e->desc.params.raw;
+	struct i40e_aqc_get_link_status *status = libie_aq_raw(&e->desc);
 
 	/* Do a new status request to re-enable LSE reporting
 	 * and load new status information into the hw struct
@@ -10343,8 +10280,7 @@ static void i40e_enable_pf_switch_lb(struct i40e_pf *pf)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "couldn't get PF vsi config, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 		return;
 	}
 	ctxt.flags = I40E_AQ_VSI_TYPE_PF;
@@ -10355,8 +10291,7 @@ static void i40e_enable_pf_switch_lb(struct i40e_pf *pf)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "update vsi switch failed, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 	}
 }
 
@@ -10379,8 +10314,7 @@ static void i40e_disable_pf_switch_lb(struct i40e_pf *pf)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "couldn't get PF vsi config, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 		return;
 	}
 	ctxt.flags = I40E_AQ_VSI_TYPE_PF;
@@ -10391,8 +10325,7 @@ static void i40e_disable_pf_switch_lb(struct i40e_pf *pf)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "update vsi switch failed, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 	}
 }
 
@@ -10507,12 +10440,12 @@ static int i40e_reconstitute_veb(struct i40e_veb *veb)
 static int i40e_get_capabilities(struct i40e_pf *pf,
 				 enum i40e_admin_queue_opc list_type)
 {
-	struct i40e_aqc_list_capabilities_element_resp *cap_buf;
+	struct libie_aqc_list_caps_elem *cap_buf;
 	u16 data_size;
 	int buf_len;
 	int err;
 
-	buf_len = 40 * sizeof(struct i40e_aqc_list_capabilities_element_resp);
+	buf_len = 40 * sizeof(struct libie_aqc_list_caps_elem);
 	do {
 		cap_buf = kzalloc(buf_len, GFP_KERNEL);
 		if (!cap_buf)
@@ -10525,15 +10458,14 @@ static int i40e_get_capabilities(struct i40e_pf *pf,
 		/* data loaded, buffer no longer needed */
 		kfree(cap_buf);
 
-		if (pf->hw.aq.asq_last_status == I40E_AQ_RC_ENOMEM) {
+		if (pf->hw.aq.asq_last_status == LIBIE_AQ_RC_ENOMEM) {
 			/* retry with a larger buffer */
 			buf_len = data_size;
-		} else if (pf->hw.aq.asq_last_status != I40E_AQ_RC_OK || err) {
+		} else if (pf->hw.aq.asq_last_status != LIBIE_AQ_RC_OK || err) {
 			dev_info(&pf->pdev->dev,
 				 "capability discovery failed, err %pe aq_err %s\n",
 				 ERR_PTR(err),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+				 libie_aq_str(pf->hw.aq.asq_last_status));
 			return -ENODEV;
 		}
 	} while (err);
@@ -10670,8 +10602,7 @@ static int i40e_rebuild_cloud_filters(struct i40e_vsi *vsi, u16 seid)
 			dev_dbg(&pf->pdev->dev,
 				"Failed to rebuild cloud filter, err %pe aq_err %s\n",
 				ERR_PTR(ret),
-				i40e_aq_str(&pf->hw,
-					    pf->hw.aq.asq_last_status));
+				libie_aq_str(pf->hw.aq.asq_last_status));
 			return ret;
 		}
 	}
@@ -10912,8 +10843,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 	ret = i40e_init_adminq(&pf->hw);
 	if (ret) {
 		dev_info(&pf->pdev->dev, "Rebuild AdminQ failed, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 		goto clear_recovery;
 	}
 	i40e_get_oem_version(&pf->hw);
@@ -11024,8 +10954,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 					 I40E_AQ_EVENT_MODULE_QUAL_FAIL), NULL);
 	if (ret)
 		dev_info(&pf->pdev->dev, "set phy mask fail, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 
 	/* Rebuild the VSIs and VEBs that existed before reset.
 	 * They are still in our local switch element arrays, so only
@@ -11123,8 +11052,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 		if (ret)
 			dev_info(&pf->pdev->dev, "link restart failed, err %pe aq_err %s\n",
 				 ERR_PTR(ret),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+				 libie_aq_str(pf->hw.aq.asq_last_status));
 	}
 	/* reinit the misc interrupt */
 	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags)) {
@@ -11155,8 +11083,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 		dev_warn(&pf->pdev->dev,
 			 "Failed to restore promiscuous setting: %s, err %pe aq_err %s\n",
 			 pf->cur_promisc ? "on" : "off",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 
 	i40e_reset_all_vfs(pf, true);
 
@@ -11217,6 +11144,67 @@ static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired)
 }
 
 /**
+ * i40e_print_vf_mdd_event - print VF Tx/Rx malicious driver detect event
+ * @pf: board private structure
+ * @vf: pointer to the VF structure
+ * @is_tx: true - for Tx event, false - for  Rx
+ */
+static void i40e_print_vf_mdd_event(struct i40e_pf *pf, struct i40e_vf *vf,
+				    bool is_tx)
+{
+	dev_err(&pf->pdev->dev, is_tx ?
+		"%lld Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pm. mdd-auto-reset-vfs=%s\n" :
+		"%lld Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pm. mdd-auto-reset-vfs=%s\n",
+		is_tx ? vf->mdd_tx_events.count : vf->mdd_rx_events.count,
+		pf->hw.pf_id,
+		vf->vf_id,
+		vf->default_lan_addr.addr,
+		str_on_off(test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags)));
+}
+
+/**
+ * i40e_print_vfs_mdd_events - print VFs malicious driver detect event
+ * @pf: pointer to the PF structure
+ *
+ * Called from i40e_handle_mdd_event to rate limit and print VFs MDD events.
+ */
+static void i40e_print_vfs_mdd_events(struct i40e_pf *pf)
+{
+	unsigned int i;
+
+	/* check that there are pending MDD events to print */
+	if (!test_and_clear_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state))
+		return;
+
+	if (!__ratelimit(&pf->mdd_message_rate_limit))
+		return;
+
+	for (i = 0; i < pf->num_alloc_vfs; i++) {
+		struct i40e_vf *vf = &pf->vf[i];
+		bool is_printed = false;
+
+		/* only print Rx MDD event message if there are new events */
+		if (vf->mdd_rx_events.count != vf->mdd_rx_events.last_printed) {
+			vf->mdd_rx_events.last_printed = vf->mdd_rx_events.count;
+			i40e_print_vf_mdd_event(pf, vf, false);
+			is_printed = true;
+		}
+
+		/* only print Tx MDD event message if there are new events */
+		if (vf->mdd_tx_events.count != vf->mdd_tx_events.last_printed) {
+			vf->mdd_tx_events.last_printed = vf->mdd_tx_events.count;
+			i40e_print_vf_mdd_event(pf, vf, true);
+			is_printed = true;
+		}
+
+		if (is_printed && !test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags))
+			dev_info(&pf->pdev->dev,
+				 "Use PF Control I/F to re-enable the VF #%d\n",
+				 i);
+	}
+}
+
+/**
  * i40e_handle_mdd_event
  * @pf: pointer to the PF structure
  *
@@ -11230,8 +11218,13 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 	u32 reg;
 	int i;
 
-	if (!test_bit(__I40E_MDD_EVENT_PENDING, pf->state))
+	if (!test_and_clear_bit(__I40E_MDD_EVENT_PENDING, pf->state)) {
+		/* Since the VF MDD event logging is rate limited, check if
+		 * there are pending MDD events.
+		 */
+		i40e_print_vfs_mdd_events(pf);
 		return;
+	}
 
 	/* find what triggered the MDD event */
 	reg = rd32(hw, I40E_GL_MDET_TX);
@@ -11275,36 +11268,48 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 
 	/* see if one of the VFs needs its hand slapped */
 	for (i = 0; i < pf->num_alloc_vfs && mdd_detected; i++) {
+		bool is_mdd_on_tx = false;
+		bool is_mdd_on_rx = false;
+
 		vf = &(pf->vf[i]);
 		reg = rd32(hw, I40E_VP_MDET_TX(i));
 		if (reg & I40E_VP_MDET_TX_VALID_MASK) {
+			set_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state);
 			wr32(hw, I40E_VP_MDET_TX(i), 0xFFFF);
-			vf->num_mdd_events++;
-			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
-				 i);
-			dev_info(&pf->pdev->dev,
-				 "Use PF Control I/F to re-enable the VF\n");
+			vf->mdd_tx_events.count++;
 			set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
+			is_mdd_on_tx = true;
 		}
 
 		reg = rd32(hw, I40E_VP_MDET_RX(i));
 		if (reg & I40E_VP_MDET_RX_VALID_MASK) {
+			set_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state);
 			wr32(hw, I40E_VP_MDET_RX(i), 0xFFFF);
-			vf->num_mdd_events++;
-			dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n",
-				 i);
-			dev_info(&pf->pdev->dev,
-				 "Use PF Control I/F to re-enable the VF\n");
+			vf->mdd_rx_events.count++;
 			set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
+			is_mdd_on_rx = true;
+		}
+
+		if ((is_mdd_on_tx || is_mdd_on_rx) &&
+		    test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags)) {
+			/* VF MDD event counters will be cleared by
+			 * reset, so print the event prior to reset.
+			 */
+			if (is_mdd_on_rx)
+				i40e_print_vf_mdd_event(pf, vf, false);
+			if (is_mdd_on_tx)
+				i40e_print_vf_mdd_event(pf, vf, true);
+
+			i40e_vc_reset_vf(vf, true);
 		}
 	}
 
-	/* re-enable mdd interrupt cause */
-	clear_bit(__I40E_MDD_EVENT_PENDING, pf->state);
 	reg = rd32(hw, I40E_PFINT_ICR0_ENA);
 	reg |=  I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK;
 	wr32(hw, I40E_PFINT_ICR0_ENA, reg);
 	i40e_flush(hw);
+
+	i40e_print_vfs_mdd_events(pf);
 }
 
 /**
@@ -11371,7 +11376,7 @@ static void i40e_service_task(struct work_struct *work)
  **/
 static void i40e_service_timer(struct timer_list *t)
 {
-	struct i40e_pf *pf = from_timer(pf, t, service_timer);
+	struct i40e_pf *pf = timer_container_of(pf, t, service_timer);
 
 	mod_timer(&pf->service_timer,
 		  round_jiffies(jiffies + pf->service_timer_period));
@@ -12284,8 +12289,7 @@ static int i40e_get_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
 			dev_info(&pf->pdev->dev,
 				 "Cannot get RSS key, err %pe aq_err %s\n",
 				 ERR_PTR(ret),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+				 libie_aq_str(pf->hw.aq.asq_last_status));
 			return ret;
 		}
 	}
@@ -12298,8 +12302,7 @@ static int i40e_get_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
 			dev_info(&pf->pdev->dev,
 				 "Cannot get RSS lut, err %pe aq_err %s\n",
 				 ERR_PTR(ret),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+				 libie_aq_str(pf->hw.aq.asq_last_status));
 			return ret;
 		}
 	}
@@ -12466,7 +12469,7 @@ static int i40e_pf_config_rss(struct i40e_pf *pf)
 	/* By default we enable TCP/UDP with IPv4/IPv6 ptypes */
 	hena = (u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(0)) |
 		((u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(1)) << 32);
-	hena |= i40e_pf_get_default_rss_hena(pf);
+	hena |= i40e_pf_get_default_rss_hashcfg(pf);
 
 	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), (u32)hena);
 	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), (u32)(hena >> 32));
@@ -12614,89 +12617,6 @@ int i40e_set_partition_bw_setting(struct i40e_pf *pf)
 }
 
 /**
- * i40e_commit_partition_bw_setting - Commit BW settings for this PF partition
- * @pf: board private structure
- **/
-int i40e_commit_partition_bw_setting(struct i40e_pf *pf)
-{
-	/* Commit temporary BW setting to permanent NVM image */
-	enum i40e_admin_queue_err last_aq_status;
-	u16 nvm_word;
-	int ret;
-
-	if (pf->hw.partition_id != 1) {
-		dev_info(&pf->pdev->dev,
-			 "Commit BW only works on partition 1! This is partition %d",
-			 pf->hw.partition_id);
-		ret = -EOPNOTSUPP;
-		goto bw_commit_out;
-	}
-
-	/* Acquire NVM for read access */
-	ret = i40e_acquire_nvm(&pf->hw, I40E_RESOURCE_READ);
-	last_aq_status = pf->hw.aq.asq_last_status;
-	if (ret) {
-		dev_info(&pf->pdev->dev,
-			 "Cannot acquire NVM for read access, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, last_aq_status));
-		goto bw_commit_out;
-	}
-
-	/* Read word 0x10 of NVM - SW compatibility word 1 */
-	ret = i40e_aq_read_nvm(&pf->hw,
-			       I40E_SR_NVM_CONTROL_WORD,
-			       0x10, sizeof(nvm_word), &nvm_word,
-			       false, NULL);
-	/* Save off last admin queue command status before releasing
-	 * the NVM
-	 */
-	last_aq_status = pf->hw.aq.asq_last_status;
-	i40e_release_nvm(&pf->hw);
-	if (ret) {
-		dev_info(&pf->pdev->dev, "NVM read error, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, last_aq_status));
-		goto bw_commit_out;
-	}
-
-	/* Wait a bit for NVM release to complete */
-	msleep(50);
-
-	/* Acquire NVM for write access */
-	ret = i40e_acquire_nvm(&pf->hw, I40E_RESOURCE_WRITE);
-	last_aq_status = pf->hw.aq.asq_last_status;
-	if (ret) {
-		dev_info(&pf->pdev->dev,
-			 "Cannot acquire NVM for write access, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, last_aq_status));
-		goto bw_commit_out;
-	}
-	/* Write it back out unchanged to initiate update NVM,
-	 * which will force a write of the shadow (alt) RAM to
-	 * the NVM - thus storing the bandwidth values permanently.
-	 */
-	ret = i40e_aq_update_nvm(&pf->hw,
-				 I40E_SR_NVM_CONTROL_WORD,
-				 0x10, sizeof(nvm_word),
-				 &nvm_word, true, 0, NULL);
-	/* Save off last admin queue command status before releasing
-	 * the NVM
-	 */
-	last_aq_status = pf->hw.aq.asq_last_status;
-	i40e_release_nvm(&pf->hw);
-	if (ret)
-		dev_info(&pf->pdev->dev,
-			 "BW settings NOT SAVED, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, last_aq_status));
-bw_commit_out:
-
-	return ret;
-}
-
-/**
  * i40e_is_total_port_shutdown_enabled - read NVM and return value
  * if total port shutdown feature is enabled for this PF
  * @pf: board private structure
@@ -13043,8 +12963,7 @@ static int i40e_udp_tunnel_set_port(struct net_device *netdev,
 				     NULL);
 	if (ret) {
 		netdev_info(netdev, "add UDP port failed, err %pe aq_err %s\n",
-			    ERR_PTR(ret),
-			    i40e_aq_str(hw, hw->aq.asq_last_status));
+			    ERR_PTR(ret), libie_aq_str(hw->aq.asq_last_status));
 		return -EIO;
 	}
 
@@ -13063,8 +12982,7 @@ static int i40e_udp_tunnel_unset_port(struct net_device *netdev,
 	ret = i40e_aq_del_udp_tunnel(hw, ti->hw_priv, NULL);
 	if (ret) {
 		netdev_info(netdev, "delete UDP port failed, err %pe aq_err %s\n",
-			    ERR_PTR(ret),
-			    i40e_aq_str(hw, hw->aq.asq_last_status));
+			    ERR_PTR(ret), libie_aq_str(hw->aq.asq_last_status));
 		return -EIO;
 	}
 
@@ -13664,7 +13582,6 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= i40e_set_mac,
 	.ndo_change_mtu		= i40e_change_mtu,
-	.ndo_eth_ioctl		= i40e_ioctl,
 	.ndo_tx_timeout		= i40e_tx_timeout,
 	.ndo_vlan_rx_add_vid	= i40e_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= i40e_vlan_rx_kill_vid,
@@ -13692,6 +13609,8 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_xsk_wakeup	        = i40e_xsk_wakeup,
 	.ndo_dfwd_add_station	= i40e_fwd_add,
 	.ndo_dfwd_del_station	= i40e_fwd_del,
+	.ndo_hwtstamp_get	= i40e_ptp_hwtstamp_get,
+	.ndo_hwtstamp_set	= i40e_ptp_hwtstamp_set,
 };
 
 /**
@@ -13953,8 +13872,7 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 			dev_info(&pf->pdev->dev,
 				 "couldn't get PF vsi config, err %pe aq_err %s\n",
 				 ERR_PTR(ret),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+				 libie_aq_str(pf->hw.aq.asq_last_status));
 			return -ENOENT;
 		}
 		vsi->info = ctxt.info;
@@ -13983,8 +13901,7 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 				dev_info(&pf->pdev->dev,
 					 "update vsi failed, err %d aq_err %s\n",
 					 ret,
-					 i40e_aq_str(&pf->hw,
-						     pf->hw.aq.asq_last_status));
+					 libie_aq_str(pf->hw.aq.asq_last_status));
 				ret = -ENOENT;
 				goto err;
 			}
@@ -14003,8 +13920,7 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 				dev_info(&pf->pdev->dev,
 					 "update vsi failed, err %pe aq_err %s\n",
 					 ERR_PTR(ret),
-					 i40e_aq_str(&pf->hw,
-						    pf->hw.aq.asq_last_status));
+					 libie_aq_str(pf->hw.aq.asq_last_status));
 				ret = -ENOENT;
 				goto err;
 			}
@@ -14027,8 +13943,7 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 					 "failed to configure TCs for main VSI tc_map 0x%08x, err %pe aq_err %s\n",
 					 enabled_tc,
 					 ERR_PTR(ret),
-					 i40e_aq_str(&pf->hw,
-						    pf->hw.aq.asq_last_status));
+					 libie_aq_str(pf->hw.aq.asq_last_status));
 			}
 		}
 		break;
@@ -14122,8 +14037,7 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 			dev_info(&vsi->back->pdev->dev,
 				 "add vsi failed, err %pe aq_err %s\n",
 				 ERR_PTR(ret),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+				 libie_aq_str(pf->hw.aq.asq_last_status));
 			ret = -ENOENT;
 			goto err;
 		}
@@ -14153,8 +14067,7 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "couldn't get vsi bw info, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 		/* VSI is already added so not tearing that up */
 		ret = 0;
 	}
@@ -14602,8 +14515,7 @@ static int i40e_veb_get_bw_info(struct i40e_veb *veb)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "query veb bw config failed, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, hw->aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(hw->aq.asq_last_status));
 		goto out;
 	}
 
@@ -14612,8 +14524,7 @@ static int i40e_veb_get_bw_info(struct i40e_veb *veb)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "query veb bw ets config failed, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, hw->aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(hw->aq.asq_last_status));
 		goto out;
 	}
 
@@ -14801,8 +14712,7 @@ static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "couldn't add VEB, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 		return -EPERM;
 	}
 
@@ -14812,16 +14722,14 @@ static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi)
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "couldn't get VEB statistics idx, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 		return -EPERM;
 	}
 	ret = i40e_veb_get_bw_info(veb);
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "couldn't get VEB bw info, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 		i40e_aq_delete_element(&pf->hw, veb->seid, NULL);
 		return -ENOENT;
 	}
@@ -15016,9 +14924,7 @@ int i40e_fetch_switch_configuration(struct i40e_pf *pf, bool printconfig)
 		if (ret) {
 			dev_info(&pf->pdev->dev,
 				 "get switch config failed err %d aq_err %s\n",
-				 ret,
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+				 ret, libie_aq_str(pf->hw.aq.asq_last_status));
 			kfree(aq_buf);
 			return -ENOENT;
 		}
@@ -15063,8 +14969,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acqui
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "couldn't fetch switch config, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(ret), libie_aq_str(pf->hw.aq.asq_last_status));
 		return ret;
 	}
 	i40e_pf_reset_stats(pf);
@@ -15087,12 +14992,11 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acqui
 		valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
 		ret = i40e_aq_set_switch_config(&pf->hw, flags, valid_flags, 0,
 						NULL);
-		if (ret && pf->hw.aq.asq_last_status != I40E_AQ_RC_ESRCH) {
+		if (ret && pf->hw.aq.asq_last_status != LIBIE_AQ_RC_ESRCH) {
 			dev_info(&pf->pdev->dev,
 				 "couldn't set switch config bits, err %pe aq_err %s\n",
 				 ERR_PTR(ret),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+				 libie_aq_str(pf->hw.aq.asq_last_status));
 			/* not a fatal problem, just keep going */
 		}
 		pf->last_sw_conf_valid_flags = valid_flags;
@@ -15933,7 +15837,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pf->udp_tunnel_nic.set_port = i40e_udp_tunnel_set_port;
 	pf->udp_tunnel_nic.unset_port = i40e_udp_tunnel_unset_port;
-	pf->udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP;
 	pf->udp_tunnel_nic.shared = &pf->udp_tunnel_shared;
 	pf->udp_tunnel_nic.tables[0].n_entries = I40E_MAX_PF_UDP_OFFLOAD_PORTS;
 	pf->udp_tunnel_nic.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN |
@@ -15995,8 +15898,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 					 I40E_AQ_EVENT_MODULE_QUAL_FAIL), NULL);
 	if (err)
 		dev_info(&pf->pdev->dev, "set phy mask fail, err %pe aq_err %s\n",
-			 ERR_PTR(err),
-			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			 ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status));
+
+	/* VF MDD event logs are rate limited to one second intervals */
+	ratelimit_state_init(&pf->mdd_message_rate_limit, 1 * HZ, 1);
 
 	/* Reconfigure hardware for allowing smaller MSS in the case
 	 * of TSO, so that we avoid the MDD being fired and causing
@@ -16015,8 +15920,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		if (err)
 			dev_info(&pf->pdev->dev, "link restart failed, err %pe aq_err %s\n",
 				 ERR_PTR(err),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+				 libie_aq_str(pf->hw.aq.asq_last_status));
 	}
 	/* The main driver is (mostly) up and happy. We need to set this state
 	 * before setting up the misc vector or we get a race and the vector
@@ -16147,8 +16051,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	err = i40e_aq_get_phy_capabilities(hw, false, false, &abilities, NULL);
 	if (err)
 		dev_dbg(&pf->pdev->dev, "get requested speeds ret =  %pe last_status =  %s\n",
-			ERR_PTR(err),
-			i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status));
 	pf->hw.phy.link_info.requested_speeds = abilities.link_speed;
 
 	/* set the FEC config due to the board capabilities */
@@ -16158,16 +16061,19 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	err = i40e_aq_get_phy_capabilities(hw, false, true, &abilities, NULL);
 	if (err)
 		dev_dbg(&pf->pdev->dev, "get supported phy types ret =  %pe last_status =  %s\n",
-			ERR_PTR(err),
-			i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status));
 
-	/* make sure the MFS hasn't been set lower than the default */
 #define MAX_FRAME_SIZE_DEFAULT 0x2600
-	val = FIELD_GET(I40E_PRTGL_SAH_MFS_MASK,
-			rd32(&pf->hw, I40E_PRTGL_SAH));
-	if (val < MAX_FRAME_SIZE_DEFAULT)
-		dev_warn(&pdev->dev, "MFS for port %x (%d) has been set below the default (%d)\n",
-			 pf->hw.port, val, MAX_FRAME_SIZE_DEFAULT);
+
+	err = i40e_aq_set_mac_config(hw, MAX_FRAME_SIZE_DEFAULT, NULL);
+	if (err)
+		dev_warn(&pdev->dev, "set mac config ret = %pe last_status = %s\n",
+			 ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status));
+
+	/* Make sure the MFS is set to the expected value */
+	val = rd32(hw, I40E_PRTGL_SAH);
+	FIELD_MODIFY(I40E_PRTGL_SAH_MFS_MASK, &val, MAX_FRAME_SIZE_DEFAULT);
+	wr32(hw, I40E_PRTGL_SAH, val);
 
 	/* Add a filter to drop all Flow control frames from any VSI from being
 	 * transmitted. By doing so we stop a malicious VF from sending out
@@ -16421,7 +16327,7 @@ static int i40e_io_suspend(struct i40e_pf *pf)
 	set_bit(__I40E_DOWN, pf->state);
 
 	/* Ensure service task will not be running */
-	del_timer_sync(&pf->service_timer);
+	timer_delete_sync(&pf->service_timer);
 	cancel_work_sync(&pf->service_task);
 
 	/* Client close must be called explicitly here because the timer
@@ -16549,7 +16455,6 @@ static pci_ers_result_t i40e_pci_error_slot_reset(struct pci_dev *pdev)
 	} else {
 		pci_set_master(pdev);
 		pci_restore_state(pdev);
-		pci_save_state(pdev);
 		pci_wake_from_d3(pdev, false);
 
 		reg = rd32(&pf->hw, I40E_GLGEN_RTRIG);
@@ -16620,7 +16525,7 @@ static void i40e_shutdown(struct pci_dev *pdev)
 	set_bit(__I40E_SUSPENDED, pf->state);
 	set_bit(__I40E_DOWN, pf->state);
 
-	del_timer_sync(&pf->service_timer);
+	timer_delete_sync(&pf->service_timer);
 	cancel_work_sync(&pf->service_task);
 	i40e_cloud_filter_exit(pf);
 	i40e_fdir_teardown(pf);
@@ -16729,7 +16634,7 @@ static int __init i40e_init_module(void)
 	 * since we need to be able to guarantee forward progress even under
 	 * memory pressure.
 	 */
-	i40e_wq = alloc_workqueue("%s", 0, 0, i40e_driver_name);
+	i40e_wq = alloc_workqueue("%s", WQ_PERCPU, 0, i40e_driver_name);
 	if (!i40e_wq) {
 		pr_err("%s: Failed to create workqueue\n", i40e_driver_name);
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 7f0936f4e05e..ed3c54e36be3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -997,7 +997,7 @@ static int i40e_nvmupd_exec_aq(struct i40e_hw *hw,
 			       u8 *bytes, int *perrno)
 {
 	struct i40e_asq_cmd_details cmd_details;
-	struct i40e_aq_desc *aq_desc;
+	struct libie_aq_desc *aq_desc;
 	u32 buff_size = 0;
 	u8 *buff = NULL;
 	u32 aq_desc_len;
@@ -1011,7 +1011,7 @@ static int i40e_nvmupd_exec_aq(struct i40e_hw *hw,
 	memset(&cmd_details, 0, sizeof(cmd_details));
 	cmd_details.wb_desc = &hw->nvm_wb_desc;
 
-	aq_desc_len = sizeof(struct i40e_aq_desc);
+	aq_desc_len = sizeof(struct libie_aq_desc);
 	memset(&hw->nvm_wb_desc, 0, aq_desc_len);
 
 	/* get the aq descriptor */
@@ -1022,7 +1022,7 @@ static int i40e_nvmupd_exec_aq(struct i40e_hw *hw,
 		*perrno = -EINVAL;
 		return -EINVAL;
 	}
-	aq_desc = (struct i40e_aq_desc *)bytes;
+	aq_desc = (struct libie_aq_desc *)bytes;
 
 	/* if data buffer needed, make sure it's ready */
 	aq_data_len = cmd->data_size - aq_desc_len;
@@ -1053,7 +1053,7 @@ static int i40e_nvmupd_exec_aq(struct i40e_hw *hw,
 		i40e_debug(hw, I40E_DEBUG_NVM,
 			   "%s err %pe aq_err %s\n",
 			   __func__, ERR_PTR(status),
-			   i40e_aq_str(hw, hw->aq.asq_last_status));
+			   libie_aq_str(hw->aq.asq_last_status));
 		*perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status);
 		return status;
 	}
@@ -1087,7 +1087,7 @@ static int i40e_nvmupd_get_aq_result(struct i40e_hw *hw,
 
 	i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__);
 
-	aq_desc_len = sizeof(struct i40e_aq_desc);
+	aq_desc_len = sizeof(struct libie_aq_desc);
 	aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_wb_desc.datalen);
 
 	/* check offset range */
@@ -1154,7 +1154,7 @@ static int i40e_nvmupd_get_aq_event(struct i40e_hw *hw,
 
 	i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__);
 
-	aq_desc_len = sizeof(struct i40e_aq_desc);
+	aq_desc_len = sizeof(struct libie_aq_desc);
 	aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_aq_event_desc.datalen);
 
 	/* check copylength range */
@@ -1442,7 +1442,7 @@ retry:
 	 * so here we try to reacquire the semaphore then retry the write.
 	 * We only do one retry, then give up.
 	 */
-	if (status && hw->aq.asq_last_status == I40E_AQ_RC_EBUSY &&
+	if (status && hw->aq.asq_last_status == LIBIE_AQ_RC_EBUSY &&
 	    !retry_attempt) {
 		u32 old_asq_status = hw->aq.asq_last_status;
 		int old_status = status;
@@ -1628,9 +1628,9 @@ void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw)
  * @desc: AdminQ descriptor
  **/
 void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode,
-				  struct i40e_aq_desc *desc)
+				  struct libie_aq_desc *desc)
 {
-	u32 aq_desc_len = sizeof(struct i40e_aq_desc);
+	u32 aq_desc_len = sizeof(struct libie_aq_desc);
 
 	if (opcode == hw->nvm_wait_opcode) {
 		memcpy(&hw->nvm_aq_event_desc, desc, aq_desc_len);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 5a0699ca7ce5..26bb7bffe361 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -23,29 +23,22 @@ int i40e_clean_arq_element(struct i40e_hw *hw,
 			   struct i40e_arq_event_info *e,
 			   u16 *events_pending);
 int
-i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc,
+i40e_asq_send_command(struct i40e_hw *hw, struct libie_aq_desc *desc,
 		      void *buff, /* can be NULL */ u16  buff_size,
 		      struct i40e_asq_cmd_details *cmd_details);
 int
-i40e_asq_send_command_v2(struct i40e_hw *hw,
-			 struct i40e_aq_desc *desc,
-			 void *buff, /* can be NULL */
-			 u16  buff_size,
-			 struct i40e_asq_cmd_details *cmd_details,
-			 enum i40e_admin_queue_err *aq_status);
-int
-i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc,
+i40e_asq_send_command_atomic(struct i40e_hw *hw, struct libie_aq_desc *desc,
 			     void *buff, /* can be NULL */ u16  buff_size,
 			     struct i40e_asq_cmd_details *cmd_details,
 			     bool is_atomic_context);
 int
 i40e_asq_send_command_atomic_v2(struct i40e_hw *hw,
-				struct i40e_aq_desc *desc,
+				struct libie_aq_desc *desc,
 				void *buff, /* can be NULL */
 				u16  buff_size,
 				struct i40e_asq_cmd_details *cmd_details,
 				bool is_atomic_context,
-				enum i40e_admin_queue_err *aq_status);
+				enum libie_aq_err *aq_status);
 
 /* debug function for adminq */
 void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask,
@@ -53,7 +46,6 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask,
 
 bool i40e_check_asq_alive(struct i40e_hw *hw);
 int i40e_aq_queue_shutdown(struct i40e_hw *hw, bool unloading);
-const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err);
 
 int i40e_aq_get_rss_lut(struct i40e_hw *hw, u16 seid,
 			bool pf_lut, u8 *lut, u16 lut_size);
@@ -72,8 +64,6 @@ int i40e_led_set_phy(struct i40e_hw *hw, bool on,
 		     u16 led_addr, u32 mode);
 int i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr,
 		     u16 *val);
-int i40e_blink_phy_link_led(struct i40e_hw *hw,
-			    u32 time, u32 interval);
 
 /* admin send queue commands */
 
@@ -108,6 +98,8 @@ int i40e_aq_set_mac_loopback(struct i40e_hw *hw,
 			     struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_set_phy_int_mask(struct i40e_hw *hw, u16 mask,
 			     struct i40e_asq_cmd_details *cmd_details);
+int i40e_aq_set_mac_config(struct i40e_hw *hw, u16 max_frame_size,
+			   struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_clear_pxe_mode(struct i40e_hw *hw,
 			   struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_set_link_restart_an(struct i40e_hw *hw,
@@ -141,9 +133,6 @@ int i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw,
 int i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw,
 				       u16 seid, bool enable, u16 vid,
 				       struct i40e_asq_cmd_details *cmd_details);
-int i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw,
-				 u16 seid, bool enable,
-				 struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_get_vsi_params(struct i40e_hw *hw,
 			   struct i40e_vsi_context *vsi_ctx,
 			   struct i40e_asq_cmd_details *cmd_details);
@@ -167,7 +156,7 @@ int
 i40e_aq_add_macvlan_v2(struct i40e_hw *hw, u16 seid,
 		       struct i40e_aqc_add_macvlan_element_data *mv_list,
 		       u16 count, struct i40e_asq_cmd_details *cmd_details,
-		       enum i40e_admin_queue_err *aq_status);
+		       enum libie_aq_err *aq_status);
 int i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 vsi_id,
 			   struct i40e_aqc_remove_macvlan_element_data *mv_list,
 			   u16 count, struct i40e_asq_cmd_details *cmd_details);
@@ -175,15 +164,7 @@ int
 i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid,
 			  struct i40e_aqc_remove_macvlan_element_data *mv_list,
 			  u16 count, struct i40e_asq_cmd_details *cmd_details,
-			  enum i40e_admin_queue_err *aq_status);
-int i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
-			   u16 rule_type, u16 dest_vsi, u16 count, __le16 *mr_list,
-			   struct i40e_asq_cmd_details *cmd_details,
-			   u16 *rule_id, u16 *rules_used, u16 *rules_free);
-int i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
-			      u16 rule_type, u16 rule_id, u16 count, __le16 *mr_list,
-			      struct i40e_asq_cmd_details *cmd_details,
-			      u16 *rules_used, u16 *rules_free);
+			  enum libie_aq_err *aq_status);
 
 int i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid,
 			   u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen,
@@ -220,9 +201,6 @@ int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer,
 		       u32 offset, u16 length, void *data,
 		       bool last_command, u8 preservation_flags,
 		       struct i40e_asq_cmd_details *cmd_details);
-int i40e_aq_rearrange_nvm(struct i40e_hw *hw,
-			  u8 rearrange_nvm,
-			  struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type,
 			 u8 mib_type, void *buff, u16 buff_size,
 			 u16 *local_len, u16 *remote_len,
@@ -234,9 +212,6 @@ i40e_aq_set_lldp_mib(struct i40e_hw *hw,
 int i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw,
 				      bool enable_update,
 				      struct i40e_asq_cmd_details *cmd_details);
-int
-i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore,
-		     struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
 		      bool persist,
 		      struct i40e_asq_cmd_details *cmd_details);
@@ -365,7 +340,7 @@ int i40e_nvmupd_command(struct i40e_hw *hw,
 			struct i40e_nvm_access *cmd,
 			u8 *bytes, int *errno);
 void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode,
-				  struct i40e_aq_desc *desc);
+				  struct libie_aq_desc *desc);
 void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw);
 void i40e_set_pci_config_data(struct i40e_hw *hw, u16 link_status);
 
@@ -458,13 +433,7 @@ int i40e_read_phy_register_clause45(struct i40e_hw *hw,
 				    u8 page, u16 reg, u8 phy_addr, u16 *value);
 int i40e_write_phy_register_clause45(struct i40e_hw *hw,
 				     u8 page, u16 reg, u8 phy_addr, u16 value);
-int i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg,
-			   u8 phy_addr, u16 *value);
-int i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg,
-			    u8 phy_addr, u16 value);
 u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num);
-int i40e_blink_phy_link_led(struct i40e_hw *hw,
-			    u32 time, u32 interval);
 int i40e_aq_write_ddp(struct i40e_hw *hw, void *buff,
 		      u16 buff_size, u32 track_id,
 		      u32 *error_offset, u32 *error_info,
@@ -477,20 +446,12 @@ int i40e_aq_get_ddp_list(struct i40e_hw *hw, void *buff,
 struct i40e_generic_seg_header *
 i40e_find_segment_in_package(u32 segment_type,
 			     struct i40e_package_header *pkg_header);
-struct i40e_profile_section_header *
-i40e_find_section_in_profile(u32 section_type,
-			     struct i40e_profile_segment *profile);
 int
 i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg,
 		   u32 track_id);
 int
 i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg,
 		      u32 track_id);
-int
-i40e_add_pinfo_to_list(struct i40e_hw *hw,
-		       struct i40e_profile_segment *profile,
-		       u8 *profile_info_sec, u32 track_id);
-
 /* i40e_ddp */
 int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index b72a4b5d76b9..33535418178b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -550,7 +550,7 @@ static int i40e_ptp_enable_pin(struct i40e_pf *pf, unsigned int chan,
 	pins.gpio_4 = pf->ptp_pins->gpio_4;
 
 	/* To turn on the pin - find the corresponding one based on
-	 * the given index. To to turn the function off - find
+	 * the given index. To turn the function off - find
 	 * which pin had it assigned. Don't use ptp_find_pin here
 	 * because it tries to lock the pincfg_mux which is locked by
 	 * ptp_pin_store() that calls here.
@@ -912,23 +912,26 @@ void i40e_ptp_set_increment(struct i40e_pf *pf)
 }
 
 /**
- * i40e_ptp_get_ts_config - ioctl interface to read the HW timestamping
- * @pf: Board private structure
- * @ifr: ioctl data
+ * i40e_ptp_hwtstamp_get - interface to read the HW timestamping
+ * @netdev: Network device structure
+ * @config: Timestamping configuration structure
  *
  * Obtain the current hardware timestamping settigs as requested. To do this,
  * keep a shadow copy of the timestamp settings rather than attempting to
  * deconstruct it from the registers.
  **/
-int i40e_ptp_get_ts_config(struct i40e_pf *pf, struct ifreq *ifr)
+int i40e_ptp_hwtstamp_get(struct net_device *netdev,
+			  struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config *config = &pf->tstamp_config;
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_pf *pf = np->vsi->back;
 
 	if (!test_bit(I40E_FLAG_PTP_ENA, pf->flags))
 		return -EOPNOTSUPP;
 
-	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
-		-EFAULT : 0;
+	*config = pf->tstamp_config;
+
+	return 0;
 }
 
 /**
@@ -1167,7 +1170,7 @@ int i40e_ptp_alloc_pins(struct i40e_pf *pf)
  * more broad if the specific filter is not directly supported.
  **/
 static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf,
-				       struct hwtstamp_config *config)
+				       struct kernel_hwtstamp_config *config)
 {
 	struct i40e_hw *hw = &pf->hw;
 	u32 tsyntype, regval;
@@ -1290,9 +1293,10 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf,
 }
 
 /**
- * i40e_ptp_set_ts_config - ioctl interface to control the HW timestamping
- * @pf: Board private structure
- * @ifr: ioctl data
+ * i40e_ptp_hwtstamp_set - interface to control the HW timestamping
+ * @netdev: Network device structure
+ * @config: Timestamping configuration structure
+ * @extack: Netlink extended ack structure for error reporting
  *
  * Respond to the user filter requests and make the appropriate hardware
  * changes here. The XL710 cannot support splitting of the Tx/Rx timestamping
@@ -1303,26 +1307,25 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf,
  * as the user receives the timestamps they care about and the user is notified
  * the filter has been broadened.
  **/
-int i40e_ptp_set_ts_config(struct i40e_pf *pf, struct ifreq *ifr)
+int i40e_ptp_hwtstamp_set(struct net_device *netdev,
+			  struct kernel_hwtstamp_config *config,
+			  struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_pf *pf = np->vsi->back;
 	int err;
 
 	if (!test_bit(I40E_FLAG_PTP_ENA, pf->flags))
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	err = i40e_ptp_set_timestamp_mode(pf, &config);
+	err = i40e_ptp_set_timestamp_mode(pf, config);
 	if (err)
 		return err;
 
 	/* save these settings for future reference */
-	pf->tstamp_config = config;
+	pf->tstamp_config = *config;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index c006f716a3bd..cc0b9efc2637 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
 #include <linux/bpf_trace.h>
+#include <linux/net/intel/libie/pctype.h>
 #include <linux/net/intel/libie/rx.h>
 #include <linux/prefetch.h>
 #include <linux/sctp.h>
@@ -397,12 +398,12 @@ static int i40e_add_del_fdir_udp(struct i40e_vsi *vsi,
 		ret = i40e_prepare_fdir_filter
 			(pf, fd_data, add, raw_packet,
 			 I40E_UDPIP_DUMMY_PACKET_LEN,
-			 I40E_FILTER_PCTYPE_NONF_IPV4_UDP);
+			 LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP);
 	else
 		ret = i40e_prepare_fdir_filter
 			(pf, fd_data, add, raw_packet,
 			 I40E_UDPIP6_DUMMY_PACKET_LEN,
-			 I40E_FILTER_PCTYPE_NONF_IPV6_UDP);
+			 LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP);
 
 	if (ret) {
 		kfree(raw_packet);
@@ -444,12 +445,12 @@ static int i40e_add_del_fdir_tcp(struct i40e_vsi *vsi,
 		ret = i40e_prepare_fdir_filter
 			(pf, fd_data, add, raw_packet,
 			 I40E_TCPIP_DUMMY_PACKET_LEN,
-			 I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
+			 LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP);
 	else
 		ret = i40e_prepare_fdir_filter
 			(pf, fd_data, add, raw_packet,
 			 I40E_TCPIP6_DUMMY_PACKET_LEN,
-			 I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
+			 LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP);
 
 	if (ret) {
 		kfree(raw_packet);
@@ -499,12 +500,12 @@ static int i40e_add_del_fdir_sctp(struct i40e_vsi *vsi,
 		ret = i40e_prepare_fdir_filter
 			(pf, fd_data, add, raw_packet,
 			 I40E_SCTPIP_DUMMY_PACKET_LEN,
-			 I40E_FILTER_PCTYPE_NONF_IPV4_SCTP);
+			 LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP);
 	else
 		ret = i40e_prepare_fdir_filter
 			(pf, fd_data, add, raw_packet,
 			 I40E_SCTPIP6_DUMMY_PACKET_LEN,
-			 I40E_FILTER_PCTYPE_NONF_IPV6_SCTP);
+			 LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP);
 
 	if (ret) {
 		kfree(raw_packet);
@@ -543,11 +544,11 @@ static int i40e_add_del_fdir_ip(struct i40e_vsi *vsi,
 	int i;
 
 	if (ipv4) {
-		iter_start = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
-		iter_end = I40E_FILTER_PCTYPE_FRAG_IPV4;
+		iter_start = LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER;
+		iter_end = LIBIE_FILTER_PCTYPE_FRAG_IPV4;
 	} else {
-		iter_start = I40E_FILTER_PCTYPE_NONF_IPV6_OTHER;
-		iter_end = I40E_FILTER_PCTYPE_FRAG_IPV6;
+		iter_start = LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER;
+		iter_end = LIBIE_FILTER_PCTYPE_FRAG_IPV6;
 	}
 
 	for (i = iter_start; i <= iter_end; i++) {
@@ -947,9 +948,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		if (!eop_desc)
 			break;
 
-		/* prevent any other reads prior to eop_desc */
-		smp_rmb();
-
 		i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf);
 		/* we have caught up to head, no work left to do */
 		if (tx_head == tx_desc)
@@ -2150,10 +2148,10 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 		memcpy(&skinfo->frags[skinfo->nr_frags], &sinfo->frags[0],
 		       sizeof(skb_frag_t) * nr_frags);
 
-		xdp_update_skb_shared_info(skb, skinfo->nr_frags + nr_frags,
-					   sinfo->xdp_frags_size,
-					   nr_frags * xdp->frame_sz,
-					   xdp_buff_is_frag_pfmemalloc(xdp));
+		xdp_update_skb_frags_info(skb, skinfo->nr_frags + nr_frags,
+					  sinfo->xdp_frags_size,
+					  nr_frags * xdp->frame_sz,
+					  xdp_buff_get_skb_flags(xdp));
 
 		/* First buffer has already been processed, so bump ntc */
 		if (++rx_ring->next_to_clean == rx_ring->count)
@@ -2205,10 +2203,9 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
 		skb_metadata_set(skb, metasize);
 
 	if (unlikely(xdp_buff_has_frags(xdp))) {
-		xdp_update_skb_shared_info(skb, nr_frags,
-					   sinfo->xdp_frags_size,
-					   nr_frags * xdp->frame_sz,
-					   xdp_buff_is_frag_pfmemalloc(xdp));
+		xdp_update_skb_frags_info(skb, nr_frags, sinfo->xdp_frags_size,
+					  nr_frags * xdp->frame_sz,
+					  xdp_buff_get_skb_flags(xdp));
 
 		i40e_process_rx_buffs(rx_ring, I40E_XDP_PASS, xdp);
 	} else {
@@ -2948,9 +2945,9 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	flex_ptype = FIELD_PREP(I40E_TXD_FLTR_QW0_QINDEX_MASK,
 				tx_ring->queue_index);
 	flex_ptype |= (tx_flags & I40E_TX_FLAGS_IPV4) ?
-		      (I40E_FILTER_PCTYPE_NONF_IPV4_TCP <<
+		      (LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP <<
 		       I40E_TXD_FLTR_QW0_PCTYPE_SHIFT) :
-		      (I40E_FILTER_PCTYPE_NONF_IPV6_TCP <<
+		      (LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP <<
 		       I40E_TXD_FLTR_QW0_PCTYPE_SHIFT);
 
 	flex_ptype |= tx_ring->vsi->id << I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 7c26c9a2bf65..1e5fd63d47f4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -4,6 +4,7 @@
 #ifndef _I40E_TXRX_H_
 #define _I40E_TXRX_H_
 
+#include <linux/net/intel/libie/pctype.h>
 #include <net/xdp.h>
 #include "i40e_type.h"
 
@@ -71,30 +72,30 @@ enum i40e_dyn_idx {
 #define I40E_SW_ITR    I40E_IDX_ITR2
 
 /* Supported RSS offloads */
-#define I40E_DEFAULT_RSS_HENA ( \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_SCTP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_L2_PAYLOAD))
-
-#define I40E_DEFAULT_RSS_HENA_EXPANDED (I40E_DEFAULT_RSS_HENA | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
-
-#define i40e_pf_get_default_rss_hena(pf) \
+#define I40E_DEFAULT_RSS_HASHCFG ( \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV4) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV6) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_L2_PAYLOAD))
+
+#define I40E_DEFAULT_RSS_HASHCFG_EXPANDED (I40E_DEFAULT_RSS_HASHCFG | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
+
+#define i40e_pf_get_default_rss_hashcfg(pf) \
 	(test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE, (pf)->hw.caps) ? \
-	 I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA)
+	 I40E_DEFAULT_RSS_HASHCFG_EXPANDED : I40E_DEFAULT_RSS_HASHCFG)
 
 /* Supported Rx Buffer Sizes (a multiple of 128) */
 #define I40E_RXBUFFER_256   256
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 28568e126850..ed8bbdb586da 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -24,7 +24,7 @@
 
 /* forward declaration */
 struct i40e_hw;
-typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct i40e_aq_desc *);
+typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct libie_aq_desc *);
 
 /* Data type manipulation macros. */
 
@@ -555,8 +555,8 @@ struct i40e_hw {
 
 	/* state of nvm update process */
 	enum i40e_nvmupd_state nvmupd_state;
-	struct i40e_aq_desc nvm_wb_desc;
-	struct i40e_aq_desc nvm_aq_event_desc;
+	struct libie_aq_desc nvm_wb_desc;
+	struct libie_aq_desc nvm_aq_event_desc;
 	struct i40e_virt_mem nvm_buff;
 	bool nvm_release_on_done;
 	u16 nvm_wait_opcode;
@@ -929,38 +929,6 @@ struct i40e_filter_program_desc {
 #define I40E_TXD_FLTR_QW0_PCTYPE_MASK	(0x3FUL << \
 					 I40E_TXD_FLTR_QW0_PCTYPE_SHIFT)
 
-/* Packet Classifier Types for filters */
-enum i40e_filter_pctype {
-	/* Note: Values 0-28 are reserved for future use.
-	 * Value 29, 30, 32 are not supported on XL710 and X710.
-	 */
-	I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP	= 29,
-	I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP	= 30,
-	I40E_FILTER_PCTYPE_NONF_IPV4_UDP		= 31,
-	I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK	= 32,
-	I40E_FILTER_PCTYPE_NONF_IPV4_TCP		= 33,
-	I40E_FILTER_PCTYPE_NONF_IPV4_SCTP		= 34,
-	I40E_FILTER_PCTYPE_NONF_IPV4_OTHER		= 35,
-	I40E_FILTER_PCTYPE_FRAG_IPV4			= 36,
-	/* Note: Values 37-38 are reserved for future use.
-	 * Value 39, 40, 42 are not supported on XL710 and X710.
-	 */
-	I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP	= 39,
-	I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP	= 40,
-	I40E_FILTER_PCTYPE_NONF_IPV6_UDP		= 41,
-	I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK	= 42,
-	I40E_FILTER_PCTYPE_NONF_IPV6_TCP		= 43,
-	I40E_FILTER_PCTYPE_NONF_IPV6_SCTP		= 44,
-	I40E_FILTER_PCTYPE_NONF_IPV6_OTHER		= 45,
-	I40E_FILTER_PCTYPE_FRAG_IPV6			= 46,
-	/* Note: Value 47 is reserved for future use */
-	I40E_FILTER_PCTYPE_FCOE_OX			= 48,
-	I40E_FILTER_PCTYPE_FCOE_RX			= 49,
-	I40E_FILTER_PCTYPE_FCOE_OTHER			= 50,
-	/* Note: Values 51-62 are reserved for future use */
-	I40E_FILTER_PCTYPE_L2_PAYLOAD			= 63,
-};
-
 enum i40e_filter_program_desc_dest {
 	I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET		= 0x0,
 	I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX	= 0x1,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index dfa785e39458..8b30a3accd31 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -216,7 +216,7 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf)
  * @notify_vf: notify vf about reset or not
  * Reset VF handler.
  **/
-static void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf)
+void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf)
 {
 	struct i40e_pf *pf = vf->pf;
 	int i;
@@ -448,7 +448,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id,
 		    (qtype << I40E_QINT_RQCTL_NEXTQ_TYPE_SHIFT) |
 		    (pf_queue_id << I40E_QINT_RQCTL_NEXTQ_INDX_SHIFT) |
 		    BIT(I40E_QINT_RQCTL_CAUSE_ENA_SHIFT) |
-		    (itr_idx << I40E_QINT_RQCTL_ITR_INDX_SHIFT);
+		    FIELD_PREP(I40E_QINT_RQCTL_ITR_INDX_MASK, itr_idx);
 		wr32(hw, reg_idx, reg);
 	}
 
@@ -653,6 +653,13 @@ static int i40e_config_vsi_tx_queue(struct i40e_vf *vf, u16 vsi_id,
 
 	/* only set the required fields */
 	tx_ctx.base = info->dma_ring_addr / 128;
+
+	/* ring_len has to be multiple of 8 */
+	if (!IS_ALIGNED(info->ring_len, 8) ||
+	    info->ring_len > I40E_MAX_NUM_DESCRIPTORS_XL710) {
+		ret = -EINVAL;
+		goto error_context;
+	}
 	tx_ctx.qlen = info->ring_len;
 	tx_ctx.rdylist = le16_to_cpu(vsi->info.qs_handle[0]);
 	tx_ctx.rdylist_act = 0;
@@ -716,6 +723,13 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id,
 
 	/* only set the required fields */
 	rx_ctx.base = info->dma_ring_addr / 128;
+
+	/* ring_len has to be multiple of 32 */
+	if (!IS_ALIGNED(info->ring_len, 32) ||
+	    info->ring_len > I40E_MAX_NUM_DESCRIPTORS_XL710) {
+		ret = -EINVAL;
+		goto error_param;
+	}
 	rx_ctx.qlen = info->ring_len;
 
 	if (info->splithdr_enabled) {
@@ -812,7 +826,7 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, u8 idx)
 	}
 
 	if (!idx) {
-		u64 hena = i40e_pf_get_default_rss_hena(pf);
+		u64 hashcfg = i40e_pf_get_default_rss_hashcfg(pf);
 		u8 broadcast[ETH_ALEN];
 
 		vf->lan_vsi_idx = vsi->idx;
@@ -841,8 +855,9 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, u8 idx)
 			dev_info(&pf->pdev->dev,
 				 "Could not allocate VF broadcast filter\n");
 		spin_unlock_bh(&vsi->mac_filter_hash_lock);
-		wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hena);
-		wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), (u32)(hena >> 32));
+		wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hashcfg);
+		wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id),
+		     (u32)(hashcfg >> 32));
 		/* program mac filter only for VF VSI */
 		ret = i40e_sync_vsi_filters(vsi);
 		if (ret)
@@ -1289,9 +1304,8 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable,
 
 			dev_err(&pf->pdev->dev,
 				"VF %d failed to set multicast promiscuous mode err %pe aq_err %s\n",
-				vf->vf_id,
-				ERR_PTR(aq_ret),
-				i40e_aq_str(&pf->hw, aq_err));
+				vf->vf_id, ERR_PTR(aq_ret),
+				libie_aq_str(aq_err));
 
 			return aq_ret;
 		}
@@ -1305,9 +1319,8 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable,
 
 			dev_err(&pf->pdev->dev,
 				"VF %d failed to set unicast promiscuous mode err %pe aq_err %s\n",
-				vf->vf_id,
-				ERR_PTR(aq_ret),
-				i40e_aq_str(&pf->hw, aq_err));
+				vf->vf_id, ERR_PTR(aq_ret),
+				libie_aq_str(aq_err));
 		}
 
 		return aq_ret;
@@ -1322,9 +1335,8 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable,
 
 			dev_err(&pf->pdev->dev,
 				"VF %d failed to set multicast promiscuous mode err %pe aq_err %s\n",
-				vf->vf_id,
-				ERR_PTR(aq_ret),
-				i40e_aq_str(&pf->hw, aq_err));
+				vf->vf_id, ERR_PTR(aq_ret),
+				libie_aq_str(aq_err));
 
 			if (!aq_tmp)
 				aq_tmp = aq_ret;
@@ -1338,9 +1350,8 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable,
 
 			dev_err(&pf->pdev->dev,
 				"VF %d failed to set unicast promiscuous mode err %pe aq_err %s\n",
-				vf->vf_id,
-				ERR_PTR(aq_ret),
-				i40e_aq_str(&pf->hw, aq_err));
+				vf->vf_id, ERR_PTR(aq_ret),
+				libie_aq_str(aq_err));
 
 			if (!aq_tmp)
 				aq_tmp = aq_ret;
@@ -1453,6 +1464,7 @@ static void i40e_trigger_vf_reset(struct i40e_vf *vf, bool flr)
 	 * functions that may still be running at this point.
 	 */
 	clear_bit(I40E_VF_STATE_INIT, &vf->vf_states);
+	clear_bit(I40E_VF_STATE_RESOURCES_LOADED, &vf->vf_states);
 
 	/* In the case of a VFLR, the HW has already reset the VF and we
 	 * just need to clean up, so don't hit the VFRTRIG register.
@@ -1546,8 +1558,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf)
  * @vf: pointer to the VF structure
  * @flr: VFLR was issued or not
  *
- * Returns true if the VF is in reset, resets successfully, or resets
- * are disabled and false otherwise.
+ * Return: True if reset was performed successfully or if resets are disabled.
+ * False if reset is already in progress.
  **/
 bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 {
@@ -1566,7 +1578,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 
 	/* If VF is being reset already we don't need to continue. */
 	if (test_and_set_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
-		return true;
+		return false;
 
 	i40e_trigger_vf_reset(vf, flr);
 
@@ -2119,7 +2131,10 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 	size_t len = 0;
 	int ret;
 
-	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_INIT)) {
+	i40e_sync_vf_state(vf, I40E_VF_STATE_INIT);
+
+	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states) ||
+	    test_bit(I40E_VF_STATE_RESOURCES_LOADED, &vf->vf_states)) {
 		aq_ret = -EINVAL;
 		goto err;
 	}
@@ -2222,6 +2237,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 				vf->default_lan_addr.addr);
 	}
 	set_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states);
+	set_bit(I40E_VF_STATE_RESOURCES_LOADED, &vf->vf_states);
 
 err:
 	/* send the response back to the VF */
@@ -2384,7 +2400,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 		}
 
 		if (vf->adq_enabled) {
-			if (idx >= ARRAY_SIZE(vf->ch)) {
+			if (idx >= vf->num_tc) {
 				aq_ret = -ENODEV;
 				goto error_param;
 			}
@@ -2405,7 +2421,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 		 * to its appropriate VSIs based on TC mapping
 		 */
 		if (vf->adq_enabled) {
-			if (idx >= ARRAY_SIZE(vf->ch)) {
+			if (idx >= vf->num_tc) {
 				aq_ret = -ENODEV;
 				goto error_param;
 			}
@@ -2455,8 +2471,10 @@ static int i40e_validate_queue_map(struct i40e_vf *vf, u16 vsi_id,
 	u16 vsi_queue_id, queue_id;
 
 	for_each_set_bit(vsi_queue_id, &queuemap, I40E_MAX_VSI_QP) {
-		if (vf->adq_enabled) {
-			vsi_id = vf->ch[vsi_queue_id / I40E_MAX_VF_VSI].vsi_id;
+		u16 idx = vsi_queue_id / I40E_MAX_VF_VSI;
+
+		if (vf->adq_enabled && idx < vf->num_tc) {
+			vsi_id = vf->ch[idx].vsi_id;
 			queue_id = (vsi_queue_id % I40E_DEFAULT_QUEUES_PER_VF);
 		} else {
 			queue_id = vsi_queue_id;
@@ -2844,24 +2862,6 @@ error_param:
 				      (u8 *)&stats, sizeof(stats));
 }
 
-/**
- * i40e_can_vf_change_mac
- * @vf: pointer to the VF info
- *
- * Return true if the VF is allowed to change its MAC filters, false otherwise
- */
-static bool i40e_can_vf_change_mac(struct i40e_vf *vf)
-{
-	/* If the VF MAC address has been set administratively (via the
-	 * ndo_set_vf_mac command), then deny permission to the VF to
-	 * add/delete unicast MAC addresses, unless the VF is trusted
-	 */
-	if (vf->pf_set_mac && !vf->trusted)
-		return false;
-
-	return true;
-}
-
 #define I40E_MAX_MACVLAN_PER_HW 3072
 #define I40E_MAX_MACVLAN_PER_PF(num_ports) (I40E_MAX_MACVLAN_PER_HW /	\
 	(num_ports))
@@ -2900,8 +2900,10 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf,
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = pf->vsi[vf->lan_vsi_idx];
 	struct i40e_hw *hw = &pf->hw;
-	int mac2add_cnt = 0;
-	int i;
+	int i, mac_add_max, mac_add_cnt = 0;
+	bool vf_trusted;
+
+	vf_trusted = test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
 
 	for (i = 0; i < al->num_elements; i++) {
 		struct i40e_mac_filter *f;
@@ -2921,9 +2923,8 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf,
 		 * The VF may request to set the MAC address filter already
 		 * assigned to it so do not return an error in that case.
 		 */
-		if (!i40e_can_vf_change_mac(vf) &&
-		    !is_multicast_ether_addr(addr) &&
-		    !ether_addr_equal(addr, vf->default_lan_addr.addr)) {
+		if (!vf_trusted && !is_multicast_ether_addr(addr) &&
+		    vf->pf_set_mac && !ether_addr_equal(addr, vf->default_lan_addr.addr)) {
 			dev_err(&pf->pdev->dev,
 				"VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n");
 			return -EPERM;
@@ -2932,31 +2933,50 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf,
 		/*count filters that really will be added*/
 		f = i40e_find_mac(vsi, addr);
 		if (!f)
-			++mac2add_cnt;
+			++mac_add_cnt;
 	}
+	/* Determine the maximum number of MAC addresses this VF may use.
+	 *
+	 * - For untrusted VFs: use a fixed small limit.
+	 *
+	 * - For trusted VFs: limit is calculated by dividing total MAC
+	 *  filter pool across all VFs/ports.
+	 *
+	 * - User can override this by devlink param "max_mac_per_vf".
+	 *   If set its value is used as a strict cap for both trusted and
+	 *   untrusted VFs.
+	 *   Note:
+	 *    even when overridden, this is a theoretical maximum; hardware
+	 *    may reject additional MACs if the absolute HW limit is reached.
+	 */
+	if (!vf_trusted)
+		mac_add_max = I40E_VC_MAX_MAC_ADDR_PER_VF;
+	else
+		mac_add_max = I40E_VC_MAX_MACVLAN_PER_TRUSTED_VF(pf->num_alloc_vfs, hw->num_ports);
+
+	if (pf->max_mac_per_vf > 0)
+		mac_add_max = pf->max_mac_per_vf;
 
-	/* If this VF is not privileged, then we can't add more than a limited
-	 * number of addresses. Check to make sure that the additions do not
-	 * push us over the limit.
+	/* VF can replace all its filters in one step, in this case mac_add_max
+	 * will be added as active and another mac_add_max will be in
+	 * a to-be-removed state. Account for that.
 	 */
-	if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) {
-		if ((i40e_count_filters(vsi) + mac2add_cnt) >
-		    I40E_VC_MAX_MAC_ADDR_PER_VF) {
+	if ((i40e_count_active_filters(vsi) + mac_add_cnt) > mac_add_max ||
+	    (i40e_count_all_filters(vsi) + mac_add_cnt) > 2 * mac_add_max) {
+		if (pf->max_mac_per_vf == mac_add_max && mac_add_max > 0) {
 			dev_err(&pf->pdev->dev,
-				"Cannot add more MAC addresses, VF is not trusted, switch the VF to trusted to add more functionality\n");
+				"Cannot add more MAC addresses: VF reached its maximum allowed limit (%d)\n",
+				mac_add_max);
 			return -EPERM;
 		}
-	/* If this VF is trusted, it can use more resources than untrusted.
-	 * However to ensure that every trusted VF has appropriate number of
-	 * resources, divide whole pool of resources per port and then across
-	 * all VFs.
-	 */
-	} else {
-		if ((i40e_count_filters(vsi) + mac2add_cnt) >
-		    I40E_VC_MAX_MACVLAN_PER_TRUSTED_VF(pf->num_alloc_vfs,
-						       hw->num_ports)) {
+		if (!vf_trusted) {
+			dev_err(&pf->pdev->dev,
+				"Cannot add more MAC addresses, VF is not trusted, switch the VF to trusted to add more functionality\n");
+			return -EPERM;
+		} else {
 			dev_err(&pf->pdev->dev,
-				"Cannot add more MAC addresses, trusted VF exhausted it's resources\n");
+				"Cannot add more MAC addresses: trusted VF reached its maximum allowed limit (%d)\n",
+				mac_add_max);
 			return -EPERM;
 		}
 	}
@@ -3137,10 +3157,10 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 		const u8 *addr = al->list[i].addr;
 
 		/* Allow to delete VF primary MAC only if it was not set
-		 * administratively by PF or if VF is trusted.
+		 * administratively by PF.
 		 */
 		if (ether_addr_equal(addr, vf->default_lan_addr.addr)) {
-			if (i40e_can_vf_change_mac(vf))
+			if (!vf->pf_set_mac)
 				was_unimac_deleted = true;
 			else
 				continue;
@@ -3447,15 +3467,15 @@ err:
 }
 
 /**
- * i40e_vc_get_rss_hena
+ * i40e_vc_get_rss_hashcfg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
  *
- * Return the RSS HENA bits allowed by the hardware
+ * Return the RSS Hash configuration bits allowed by the hardware
  **/
-static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg)
+static int i40e_vc_get_rss_hashcfg(struct i40e_vf *vf, u8 *msg)
 {
-	struct virtchnl_rss_hena *vrh = NULL;
+	struct virtchnl_rss_hashcfg *vrh = NULL;
 	struct i40e_pf *pf = vf->pf;
 	int aq_ret = 0;
 	int len = 0;
@@ -3464,7 +3484,7 @@ static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg)
 		aq_ret = -EINVAL;
 		goto err;
 	}
-	len = sizeof(struct virtchnl_rss_hena);
+	len = sizeof(struct virtchnl_rss_hashcfg);
 
 	vrh = kzalloc(len, GFP_KERNEL);
 	if (!vrh) {
@@ -3472,26 +3492,26 @@ static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg)
 		len = 0;
 		goto err;
 	}
-	vrh->hena = i40e_pf_get_default_rss_hena(pf);
+	vrh->hashcfg = i40e_pf_get_default_rss_hashcfg(pf);
 err:
 	/* send the response back to the VF */
-	aq_ret = i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_RSS_HENA_CAPS,
+	aq_ret = i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS,
 					aq_ret, (u8 *)vrh, len);
 	kfree(vrh);
 	return aq_ret;
 }
 
 /**
- * i40e_vc_set_rss_hena
+ * i40e_vc_set_rss_hashcfg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
  *
- * Set the RSS HENA bits for the VF
+ * Set the RSS Hash configuration bits for the VF
  **/
-static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg)
+static int i40e_vc_set_rss_hashcfg(struct i40e_vf *vf, u8 *msg)
 {
-	struct virtchnl_rss_hena *vrh =
-		(struct virtchnl_rss_hena *)msg;
+	struct virtchnl_rss_hashcfg *vrh =
+		(struct virtchnl_rss_hashcfg *)msg;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_hw *hw = &pf->hw;
 	int aq_ret = 0;
@@ -3500,13 +3520,14 @@ static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg)
 		aq_ret = -EINVAL;
 		goto err;
 	}
-	i40e_write_rx_ctl(hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)vrh->hena);
+	i40e_write_rx_ctl(hw, I40E_VFQF_HENA1(0, vf->vf_id),
+			  (u32)vrh->hashcfg);
 	i40e_write_rx_ctl(hw, I40E_VFQF_HENA1(1, vf->vf_id),
-			  (u32)(vrh->hena >> 32));
+			  (u32)(vrh->hashcfg >> 32));
 
 	/* send the response to the VF */
 err:
-	return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_SET_RSS_HENA, aq_ret);
+	return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_SET_RSS_HASHCFG, aq_ret);
 }
 
 /**
@@ -3589,7 +3610,7 @@ static int i40e_validate_cloud_filter(struct i40e_vf *vf,
 
 	/* action_meta is TC number here to which the filter is applied */
 	if (!tc_filter->action_meta ||
-	    tc_filter->action_meta > vf->num_tc) {
+	    tc_filter->action_meta >= vf->num_tc) {
 		dev_info(&pf->pdev->dev, "VF %d: Invalid TC number %u\n",
 			 vf->vf_id, tc_filter->action_meta);
 		goto err;
@@ -3746,8 +3767,7 @@ static void i40e_del_all_cloud_filters(struct i40e_vf *vf)
 			dev_err(&pf->pdev->dev,
 				"VF %d: Failed to delete cloud filter, err %pe aq_err %s\n",
 				vf->vf_id, ERR_PTR(ret),
-				i40e_aq_str(&pf->hw,
-					    pf->hw.aq.asq_last_status));
+				libie_aq_str(pf->hw.aq.asq_last_status));
 
 		hlist_del(&cfilter->cloud_node);
 		kfree(cfilter);
@@ -3849,7 +3869,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		dev_err(&pf->pdev->dev,
 			"VF %d: Failed to delete cloud filter, err %pe aq_err %s\n",
 			vf->vf_id, ERR_PTR(ret),
-			i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			libie_aq_str(pf->hw.aq.asq_last_status));
 		goto err;
 	}
 
@@ -3887,6 +3907,8 @@ err:
 				       aq_ret);
 }
 
+#define I40E_MAX_VF_CLOUD_FILTER 0xFF00
+
 /**
  * i40e_vc_add_cloud_filter
  * @vf: pointer to the VF info
@@ -3926,6 +3948,14 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		goto err_out;
 	}
 
+	if (vf->num_cloud_filters >= I40E_MAX_VF_CLOUD_FILTER) {
+		dev_warn(&pf->pdev->dev,
+			 "VF %d: Max number of filters reached, can't apply cloud filter\n",
+			 vf->vf_id);
+		aq_ret = -ENOSPC;
+		goto err_out;
+	}
+
 	cfilter = kzalloc(sizeof(*cfilter), GFP_KERNEL);
 	if (!cfilter) {
 		aq_ret = -ENOMEM;
@@ -3985,7 +4015,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		dev_err(&pf->pdev->dev,
 			"VF %d: Failed to add cloud filter, err %pe aq_err %s\n",
 			vf->vf_id, ERR_PTR(aq_ret),
-			i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+			libie_aq_str(pf->hw.aq.asq_last_status));
 		goto err_free;
 	}
 
@@ -4253,11 +4283,11 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 	case VIRTCHNL_OP_CONFIG_RSS_LUT:
 		ret = i40e_vc_config_rss_lut(vf, msg);
 		break;
-	case VIRTCHNL_OP_GET_RSS_HENA_CAPS:
-		ret = i40e_vc_get_rss_hena(vf, msg);
+	case VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS:
+		ret = i40e_vc_get_rss_hashcfg(vf, msg);
 		break;
-	case VIRTCHNL_OP_SET_RSS_HENA:
-		ret = i40e_vc_set_rss_hena(vf, msg);
+	case VIRTCHNL_OP_SET_RSS_HASHCFG:
+		ret = i40e_vc_set_rss_hashcfg(vf, msg);
 		break;
 	case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING:
 		ret = i40e_vc_enable_vlan_stripping(vf, msg);
@@ -4328,7 +4358,10 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf)
 		reg = rd32(hw, I40E_GLGEN_VFLRSTAT(reg_idx));
 		if (reg & BIT(bit_idx))
 			/* i40e_reset_vf will clear the bit in GLGEN_VFLRSTAT */
-			i40e_reset_vf(vf, true);
+			if (!i40e_reset_vf(vf, true)) {
+				/* At least one VF did not finish resetting, retry next time */
+				set_bit(__I40E_VFLR_EVENT_PENDING, pf->state);
+			}
 	}
 
 	return 0;
@@ -4770,6 +4803,7 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
 	unsigned long q_map;
 	struct i40e_vf *vf;
 	int abs_vf_id;
+	int old_link;
 	int ret = 0;
 	int tmp;
 
@@ -4788,6 +4822,17 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
 	vf = &pf->vf[vf_id];
 	abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id;
 
+	/* skip VF link state change if requested state is already set */
+	if (!vf->link_forced)
+		old_link = IFLA_VF_LINK_STATE_AUTO;
+	else if (vf->link_up)
+		old_link = IFLA_VF_LINK_STATE_ENABLE;
+	else
+		old_link = IFLA_VF_LINK_STATE_DISABLE;
+
+	if (link == old_link)
+		goto error_out;
+
 	pfe.event = VIRTCHNL_EVENT_LINK_CHANGE;
 	pfe.severity = PF_EVENT_SEVERITY_INFO;
 
@@ -5003,7 +5048,7 @@ int i40e_get_vf_stats(struct net_device *netdev, int vf_id,
 	vf_stats->broadcast  = stats->rx_broadcast;
 	vf_stats->multicast  = stats->rx_multicast;
 	vf_stats->rx_dropped = stats->rx_discards + stats->rx_discards_other;
-	vf_stats->tx_dropped = stats->tx_discards;
+	vf_stats->tx_dropped = stats->tx_errors;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 66f95e2f3146..f558b45725c8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -41,7 +41,8 @@ enum i40e_vf_states {
 	I40E_VF_STATE_MC_PROMISC,
 	I40E_VF_STATE_UC_PROMISC,
 	I40E_VF_STATE_PRE_ENABLE,
-	I40E_VF_STATE_RESETTING
+	I40E_VF_STATE_RESETTING,
+	I40E_VF_STATE_RESOURCES_LOADED,
 };
 
 /* VF capabilities */
@@ -64,6 +65,12 @@ struct i40evf_channel {
 	u64 max_tx_rate; /* bandwidth rate allocation for VSIs */
 };
 
+struct i40e_mdd_vf_events {
+	u64 count;      /* total count of Rx|Tx events */
+	/* count number of the last printed event */
+	u64 last_printed;
+};
+
 /* VF information structure */
 struct i40e_vf {
 	struct i40e_pf *pf;
@@ -92,7 +99,9 @@ struct i40e_vf {
 
 	u8 num_queue_pairs;	/* num of qps assigned to VF vsis */
 	u8 num_req_queues;	/* num of requested qps */
-	u64 num_mdd_events;	/* num of mdd events detected */
+	/* num of mdd tx and rx events detected */
+	struct i40e_mdd_vf_events mdd_rx_events;
+	struct i40e_mdd_vf_events mdd_tx_events;
 
 	unsigned long vf_caps;	/* vf's adv. capabilities */
 	unsigned long vf_states;	/* vf's runtime states */
@@ -120,6 +129,7 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs);
 int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 			   u32 v_retval, u8 *msg, u16 msglen);
 int i40e_vc_process_vflr_event(struct i40e_pf *pf);
+void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf);
 bool i40e_reset_vf(struct i40e_vf *vf, bool flr);
 bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr);
 void i40e_vc_notify_vf_reset(struct i40e_vf *vf);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index e28f1905a4a0..9f47388eaba5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2018 Intel Corporation. */
 
 #include <linux/bpf_trace.h>
+#include <linux/unroll.h>
 #include <net/xdp_sock_drv.h>
 #include "i40e_txrx_common.h"
 #include "i40e_xsk.h"
@@ -529,7 +530,8 @@ static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *des
 	dma_addr_t dma;
 	u32 i;
 
-	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+	unrolled_count(PKTS_PER_BATCH)
+	for (i = 0; i < PKTS_PER_BATCH; i++) {
 		u32 cmd = I40E_TX_DESC_CMD_ICRC | xsk_is_eop_desc(&desc[i]);
 
 		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc[i].addr);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index ef156fad52f2..dd16351a7af8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -6,7 +6,7 @@
 
 #include <linux/types.h>
 
-/* This value should match the pragma in the loop_unrolled_for
+/* This value should match the pragma in the unrolled_count()
  * macro. Why 4? It is strictly empirical. It seems to be a good
  * compromise between the advantage of having simultaneous outstanding
  * reads to the DMA array that can hide each others latency and the
@@ -14,14 +14,6 @@
  */
 #define PKTS_PER_BATCH 4
 
-#ifdef __clang__
-#define loop_unrolled_for _Pragma("clang loop unroll_count(4)") for
-#elif __GNUC__ >= 8
-#define loop_unrolled_for _Pragma("GCC unroll 4") for
-#else
-#define loop_unrolled_for for
-#endif
-
 struct i40e_ring;
 struct i40e_vsi;
 struct net_device;
diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile
index 356ac9faa5bf..e13720a728ff 100644
--- a/drivers/net/ethernet/intel/iavf/Makefile
+++ b/drivers/net/ethernet/intel/iavf/Makefile
@@ -13,3 +13,5 @@ obj-$(CONFIG_IAVF) += iavf.o
 
 iavf-y := iavf_main.o iavf_ethtool.o iavf_virtchnl.o iavf_fdir.o \
 	  iavf_adv_rss.o iavf_txrx.o iavf_common.o iavf_adminq.o
+
+iavf-$(CONFIG_PTP_1588_CLOCK) += iavf_ptp.o
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 532a0a595fe8..a87e0c6d4017 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -41,6 +41,7 @@
 #include "iavf_txrx.h"
 #include "iavf_fdir.h"
 #include "iavf_adv_rss.h"
+#include "iavf_types.h"
 #include <linux/bitmap.h>
 
 #define DEFAULT_DEBUG_LEVEL_SHIFT 3
@@ -82,7 +83,7 @@ struct iavf_vsi {
 
 #define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)
 
-#define IAVF_RX_DESC(R, i) (&(((union iavf_32byte_rx_desc *)((R)->desc))[i]))
+#define IAVF_RX_DESC(R, i) (&(((struct iavf_rx_desc *)((R)->desc))[i]))
 #define IAVF_TX_DESC(R, i) (&(((struct iavf_tx_desc *)((R)->desc))[i]))
 #define IAVF_TX_CTXTDESC(R, i) \
 	(&(((struct iavf_tx_context_desc *)((R)->desc))[i]))
@@ -113,8 +114,6 @@ struct iavf_q_vector {
 	u16 reg_idx;		/* register index of the interrupt */
 	char name[IFNAMSIZ + 15];
 	bool arm_wb_state;
-	cpumask_t affinity_mask;
-	struct irq_affinity_notify affinity_notify;
 };
 
 /* Helper macros to switch between ints/sec and what the register uses.
@@ -267,10 +266,10 @@ struct iavf_adapter {
 	struct list_head vlan_filter_list;
 	int num_vlan_filters;
 	struct list_head mac_filter_list;
-	struct mutex crit_lock;
 	/* Lock to protect accesses to MAC and VLAN lists */
 	spinlock_t mac_vlan_list_lock;
 	char misc_vector_name[IFNAMSIZ + 9];
+	u8 rxdid;
 	int num_active_queues;
 	int num_req_queues;
 
@@ -314,8 +313,8 @@ struct iavf_adapter {
 #define IAVF_FLAG_AQ_CONFIGURE_RSS		BIT_ULL(9) /* direct AQ config */
 #define IAVF_FLAG_AQ_GET_CONFIG			BIT_ULL(10)
 /* Newer style, RSS done by the PF so we can ignore hardware vagaries. */
-#define IAVF_FLAG_AQ_GET_HENA			BIT_ULL(11)
-#define IAVF_FLAG_AQ_SET_HENA			BIT_ULL(12)
+#define IAVF_FLAG_AQ_GET_RSS_HASHCFG		BIT_ULL(11)
+#define IAVF_FLAG_AQ_SET_RSS_HASHCFG		BIT_ULL(12)
 #define IAVF_FLAG_AQ_SET_RSS_KEY		BIT_ULL(13)
 #define IAVF_FLAG_AQ_SET_RSS_LUT		BIT_ULL(14)
 #define IAVF_FLAG_AQ_SET_RSS_HFUNC		BIT_ULL(15)
@@ -343,6 +342,17 @@ struct iavf_adapter {
 #define IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW		BIT_ULL(39)
 #define IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE		BIT_ULL(40)
 #define IAVF_FLAG_AQ_GET_QOS_CAPS			BIT_ULL(41)
+#define IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS		BIT_ULL(42)
+#define IAVF_FLAG_AQ_GET_PTP_CAPS			BIT_ULL(43)
+#define IAVF_FLAG_AQ_SEND_PTP_CMD			BIT_ULL(44)
+
+	/* AQ messages that must be sent after IAVF_FLAG_AQ_GET_CONFIG, in
+	 * order to negotiated extended capabilities.
+	 */
+#define IAVF_FLAG_AQ_EXTENDED_CAPS			\
+	(IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS |	\
+	 IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS |		\
+	 IAVF_FLAG_AQ_GET_PTP_CAPS)
 
 	/* flags for processing extended capability messages during
 	 * __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires
@@ -354,10 +364,18 @@ struct iavf_adapter {
 	u64 extended_caps;
 #define IAVF_EXTENDED_CAP_SEND_VLAN_V2			BIT_ULL(0)
 #define IAVF_EXTENDED_CAP_RECV_VLAN_V2			BIT_ULL(1)
+#define IAVF_EXTENDED_CAP_SEND_RXDID			BIT_ULL(2)
+#define IAVF_EXTENDED_CAP_RECV_RXDID			BIT_ULL(3)
+#define IAVF_EXTENDED_CAP_SEND_PTP			BIT_ULL(4)
+#define IAVF_EXTENDED_CAP_RECV_PTP			BIT_ULL(5)
 
 #define IAVF_EXTENDED_CAPS				\
 	(IAVF_EXTENDED_CAP_SEND_VLAN_V2 |		\
-	 IAVF_EXTENDED_CAP_RECV_VLAN_V2)
+	 IAVF_EXTENDED_CAP_RECV_VLAN_V2 |		\
+	 IAVF_EXTENDED_CAP_SEND_RXDID |			\
+	 IAVF_EXTENDED_CAP_RECV_RXDID |			\
+	 IAVF_EXTENDED_CAP_SEND_PTP |			\
+	 IAVF_EXTENDED_CAP_RECV_PTP)
 
 	/* Lock to prevent possible clobbering of
 	 * current_netdev_promisc_flags
@@ -417,12 +435,18 @@ struct iavf_adapter {
 			     VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF)
 #define QOS_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \
 			 VIRTCHNL_VF_OFFLOAD_QOS)
+#define IAVF_RXDID_ALLOWED(a)						\
+	((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC)
+#define IAVF_PTP_ALLOWED(a)						\
+	((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_CAP_PTP)
 	struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */
 	struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */
 	struct virtchnl_version_info pf_version;
 #define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \
 		       ((_a)->pf_version.minor == 1))
 	struct virtchnl_vlan_caps vlan_v2_caps;
+	u64 supp_rxdids;
+	struct iavf_ptp ptp;
 	u16 msg_enable;
 	struct iavf_eth_stats current_stats;
 	struct virtchnl_qos_cap_list *qos_caps;
@@ -430,7 +454,7 @@ struct iavf_adapter {
 	u32 aq_wait_count;
 	/* RSS stuff */
 	enum virtchnl_rss_algorithm hfunc;
-	u64 hena;
+	u64 rss_hashcfg;
 	u16 rss_key_size;
 	u16 rss_lut_size;
 	u8 *rss_key;
@@ -555,6 +579,10 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter);
 int iavf_get_vf_config(struct iavf_adapter *adapter);
 int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter);
 int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter);
+int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter);
+int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter);
+int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter);
+int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter);
 void iavf_set_queue_vlan_tag_loc(struct iavf_adapter *adapter);
 u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter);
 void iavf_irq_enable(struct iavf_adapter *adapter, bool flush);
@@ -570,8 +598,8 @@ void iavf_set_promiscuous(struct iavf_adapter *adapter);
 bool iavf_promiscuous_mode_changed(struct iavf_adapter *adapter);
 void iavf_request_stats(struct iavf_adapter *adapter);
 int iavf_request_reset(struct iavf_adapter *adapter);
-void iavf_get_hena(struct iavf_adapter *adapter);
-void iavf_set_hena(struct iavf_adapter *adapter);
+void iavf_get_rss_hashcfg(struct iavf_adapter *adapter);
+void iavf_set_rss_hashcfg(struct iavf_adapter *adapter);
 void iavf_set_rss_key(struct iavf_adapter *adapter);
 void iavf_set_rss_lut(struct iavf_adapter *adapter);
 void iavf_set_rss_hfunc(struct iavf_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adminq.c b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
index 82fcd18ad660..6937b7dd44cb 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adminq.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
@@ -18,7 +18,7 @@ static enum iavf_status iavf_alloc_adminq_asq_ring(struct iavf_hw *hw)
 	ret_code = iavf_allocate_dma_mem(hw, &hw->aq.asq.desc_buf,
 					 iavf_mem_atq_ring,
 					 (hw->aq.num_asq_entries *
-					 sizeof(struct iavf_aq_desc)),
+					 sizeof(struct libie_aq_desc)),
 					 IAVF_ADMINQ_DESC_ALIGNMENT);
 	if (ret_code)
 		return ret_code;
@@ -45,7 +45,7 @@ static enum iavf_status iavf_alloc_adminq_arq_ring(struct iavf_hw *hw)
 	ret_code = iavf_allocate_dma_mem(hw, &hw->aq.arq.desc_buf,
 					 iavf_mem_arq_ring,
 					 (hw->aq.num_arq_entries *
-					 sizeof(struct iavf_aq_desc)),
+					 sizeof(struct libie_aq_desc)),
 					 IAVF_ADMINQ_DESC_ALIGNMENT);
 
 	return ret_code;
@@ -81,7 +81,7 @@ static void iavf_free_adminq_arq(struct iavf_hw *hw)
  **/
 static enum iavf_status iavf_alloc_arq_bufs(struct iavf_hw *hw)
 {
-	struct iavf_aq_desc *desc;
+	struct libie_aq_desc *desc;
 	struct iavf_dma_mem *bi;
 	enum iavf_status ret_code;
 	int i;
@@ -111,9 +111,9 @@ static enum iavf_status iavf_alloc_arq_bufs(struct iavf_hw *hw)
 		/* now configure the descriptors for use */
 		desc = IAVF_ADMINQ_DESC(hw->aq.arq, i);
 
-		desc->flags = cpu_to_le16(IAVF_AQ_FLAG_BUF);
+		desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_BUF);
 		if (hw->aq.arq_buf_size > IAVF_AQ_LARGE_BUF)
-			desc->flags |= cpu_to_le16(IAVF_AQ_FLAG_LB);
+			desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
 		desc->opcode = 0;
 		/* This is in accordance with Admin queue design, there is no
 		 * register for buffer size configuration
@@ -122,12 +122,12 @@ static enum iavf_status iavf_alloc_arq_bufs(struct iavf_hw *hw)
 		desc->retval = 0;
 		desc->cookie_high = 0;
 		desc->cookie_low = 0;
-		desc->params.external.addr_high =
+		desc->params.generic.addr_high =
 			cpu_to_le32(upper_32_bits(bi->pa));
-		desc->params.external.addr_low =
+		desc->params.generic.addr_low =
 			cpu_to_le32(lower_32_bits(bi->pa));
-		desc->params.external.param0 = 0;
-		desc->params.external.param1 = 0;
+		desc->params.generic.param0 = 0;
+		desc->params.generic.param1 = 0;
 	}
 
 alloc_arq_bufs:
@@ -558,8 +558,8 @@ static u16 iavf_clean_asq(struct iavf_hw *hw)
 	struct iavf_adminq_ring *asq = &hw->aq.asq;
 	struct iavf_asq_cmd_details *details;
 	u16 ntc = asq->next_to_clean;
-	struct iavf_aq_desc desc_cb;
-	struct iavf_aq_desc *desc;
+	struct libie_aq_desc desc_cb;
+	struct libie_aq_desc *desc;
 
 	desc = IAVF_ADMINQ_DESC(*asq, ntc);
 	details = IAVF_ADMINQ_DETAILS(*asq, ntc);
@@ -573,7 +573,7 @@ static u16 iavf_clean_asq(struct iavf_hw *hw)
 			desc_cb = *desc;
 			cb_func(hw, &desc_cb);
 		}
-		memset((void *)desc, 0, sizeof(struct iavf_aq_desc));
+		memset((void *)desc, 0, sizeof(struct libie_aq_desc));
 		memset((void *)details, 0,
 		       sizeof(struct iavf_asq_cmd_details));
 		ntc++;
@@ -615,14 +615,14 @@ bool iavf_asq_done(struct iavf_hw *hw)
  *  queue.  It runs the queue, cleans the queue, etc
  **/
 enum iavf_status iavf_asq_send_command(struct iavf_hw *hw,
-				       struct iavf_aq_desc *desc,
+				       struct libie_aq_desc *desc,
 				       void *buff, /* can be NULL */
 				       u16  buff_size,
 				       struct iavf_asq_cmd_details *cmd_details)
 {
 	struct iavf_dma_mem *dma_buff = NULL;
 	struct iavf_asq_cmd_details *details;
-	struct iavf_aq_desc *desc_on_ring;
+	struct libie_aq_desc *desc_on_ring;
 	bool cmd_completed = false;
 	enum iavf_status status = 0;
 	u16  retval = 0;
@@ -637,7 +637,7 @@ enum iavf_status iavf_asq_send_command(struct iavf_hw *hw,
 		goto asq_send_command_error;
 	}
 
-	hw->aq.asq_last_status = IAVF_AQ_RC_OK;
+	hw->aq.asq_last_status = LIBIE_AQ_RC_OK;
 
 	val = rd32(hw, IAVF_VF_ATQH1);
 	if (val >= hw->aq.num_asq_entries) {
@@ -717,9 +717,9 @@ enum iavf_status iavf_asq_send_command(struct iavf_hw *hw,
 		/* Update the address values in the desc with the pa value
 		 * for respective buffer
 		 */
-		desc_on_ring->params.external.addr_high =
+		desc_on_ring->params.generic.addr_high =
 				cpu_to_le32(upper_32_bits(dma_buff->pa));
-		desc_on_ring->params.external.addr_low =
+		desc_on_ring->params.generic.addr_low =
 				cpu_to_le32(lower_32_bits(dma_buff->pa));
 	}
 
@@ -766,13 +766,13 @@ enum iavf_status iavf_asq_send_command(struct iavf_hw *hw,
 			retval &= 0xff;
 		}
 		cmd_completed = true;
-		if ((enum iavf_admin_queue_err)retval == IAVF_AQ_RC_OK)
+		if ((enum libie_aq_err)retval == LIBIE_AQ_RC_OK)
 			status = 0;
-		else if ((enum iavf_admin_queue_err)retval == IAVF_AQ_RC_EBUSY)
+		else if ((enum libie_aq_err)retval == LIBIE_AQ_RC_EBUSY)
 			status = IAVF_ERR_NOT_READY;
 		else
 			status = IAVF_ERR_ADMIN_QUEUE_ERROR;
-		hw->aq.asq_last_status = (enum iavf_admin_queue_err)retval;
+		hw->aq.asq_last_status = (enum libie_aq_err)retval;
 	}
 
 	iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
@@ -809,12 +809,12 @@ asq_send_command_error:
  *
  *  Fill the desc with default values
  **/
-void iavf_fill_default_direct_cmd_desc(struct iavf_aq_desc *desc, u16 opcode)
+void iavf_fill_default_direct_cmd_desc(struct libie_aq_desc *desc, u16 opcode)
 {
 	/* zero out the desc */
-	memset((void *)desc, 0, sizeof(struct iavf_aq_desc));
+	memset((void *)desc, 0, sizeof(struct libie_aq_desc));
 	desc->opcode = cpu_to_le16(opcode);
-	desc->flags = cpu_to_le16(IAVF_AQ_FLAG_SI);
+	desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_SI);
 }
 
 /**
@@ -832,7 +832,7 @@ enum iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
 					u16 *pending)
 {
 	u16 ntc = hw->aq.arq.next_to_clean;
-	struct iavf_aq_desc *desc;
+	struct libie_aq_desc *desc;
 	enum iavf_status ret_code = 0;
 	struct iavf_dma_mem *bi;
 	u16 desc_idx;
@@ -866,9 +866,9 @@ enum iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
 	desc_idx = ntc;
 
 	hw->aq.arq_last_status =
-		(enum iavf_admin_queue_err)le16_to_cpu(desc->retval);
+		(enum libie_aq_err)le16_to_cpu(desc->retval);
 	flags = le16_to_cpu(desc->flags);
-	if (flags & IAVF_AQ_FLAG_ERR) {
+	if (flags & LIBIE_AQ_FLAG_ERR) {
 		ret_code = IAVF_ERR_ADMIN_QUEUE_ERROR;
 		iavf_debug(hw,
 			   IAVF_DEBUG_AQ_MESSAGE,
@@ -892,14 +892,14 @@ enum iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
 	 * size
 	 */
 	bi = &hw->aq.arq.r.arq_bi[ntc];
-	memset((void *)desc, 0, sizeof(struct iavf_aq_desc));
+	memset((void *)desc, 0, sizeof(struct libie_aq_desc));
 
-	desc->flags = cpu_to_le16(IAVF_AQ_FLAG_BUF);
+	desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_BUF);
 	if (hw->aq.arq_buf_size > IAVF_AQ_LARGE_BUF)
-		desc->flags |= cpu_to_le16(IAVF_AQ_FLAG_LB);
+		desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
 	desc->datalen = cpu_to_le16((u16)bi->size);
-	desc->params.external.addr_high = cpu_to_le32(upper_32_bits(bi->pa));
-	desc->params.external.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
+	desc->params.generic.addr_high = cpu_to_le32(upper_32_bits(bi->pa));
+	desc->params.generic.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
 
 	/* set tail = the last cleaned desc index. */
 	wr32(hw, IAVF_VF_ARQT1, ntc);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adminq.h b/drivers/net/ethernet/intel/iavf/iavf_adminq.h
index 406506f64bdd..bbf5c4b3a2ae 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adminq.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq.h
@@ -9,7 +9,7 @@
 #include "iavf_adminq_cmd.h"
 
 #define IAVF_ADMINQ_DESC(R, i)   \
-	(&(((struct iavf_aq_desc *)((R).desc_buf.va))[i]))
+	(&(((struct libie_aq_desc *)((R).desc_buf.va))[i]))
 
 #define IAVF_ADMINQ_DESC_ALIGNMENT 4096
 
@@ -39,7 +39,7 @@ struct iavf_asq_cmd_details {
 	u16 flags_dis;
 	bool async;
 	bool postpone;
-	struct iavf_aq_desc *wb_desc;
+	struct libie_aq_desc *wb_desc;
 };
 
 #define IAVF_ADMINQ_DETAILS(R, i)   \
@@ -47,7 +47,7 @@ struct iavf_asq_cmd_details {
 
 /* ARQ event information */
 struct iavf_arq_event_info {
-	struct iavf_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 msg_len;
 	u16 buf_len;
 	u8 *msg_buf;
@@ -72,8 +72,8 @@ struct iavf_adminq_info {
 	struct mutex arq_mutex; /* Receive queue lock */
 
 	/* last status values on send and receive queues */
-	enum iavf_admin_queue_err asq_last_status;
-	enum iavf_admin_queue_err arq_last_status;
+	enum libie_aq_err asq_last_status;
+	enum libie_aq_err arq_last_status;
 };
 
 /**
@@ -123,6 +123,6 @@ static inline int iavf_aq_rc_to_posix(int aq_ret, int aq_rc)
 #define IAVF_AQ_LARGE_BUF	512
 #define IAVF_ASQ_CMD_TIMEOUT	250000  /* usecs */
 
-void iavf_fill_default_direct_cmd_desc(struct iavf_aq_desc *desc, u16 opcode);
+void iavf_fill_default_direct_cmd_desc(struct libie_aq_desc *desc, u16 opcode);
 
 #endif /* _IAVF_ADMINQ_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adminq_cmd.h b/drivers/net/ethernet/intel/iavf/iavf_adminq_cmd.h
index bc512308557b..0482c9ce9b9c 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq_cmd.h
@@ -4,6 +4,8 @@
 #ifndef _IAVF_ADMINQ_CMD_H_
 #define _IAVF_ADMINQ_CMD_H_
 
+#include <linux/net/intel/libie/adminq.h>
+
 /* This header file defines the iavf Admin Queue commands and is shared between
  * iavf Firmware and Software.
  *
@@ -21,87 +23,6 @@
 /* API version 1.7 implements additional link and PHY-specific APIs  */
 #define IAVF_MINOR_VER_GET_LINK_INFO_XL710 0x0007
 
-struct iavf_aq_desc {
-	__le16 flags;
-	__le16 opcode;
-	__le16 datalen;
-	__le16 retval;
-	__le32 cookie_high;
-	__le32 cookie_low;
-	union {
-		struct {
-			__le32 param0;
-			__le32 param1;
-			__le32 param2;
-			__le32 param3;
-		} internal;
-		struct {
-			__le32 param0;
-			__le32 param1;
-			__le32 addr_high;
-			__le32 addr_low;
-		} external;
-		u8 raw[16];
-	} params;
-};
-
-/* Flags sub-structure
- * |0  |1  |2  |3  |4  |5  |6  |7  |8  |9  |10 |11 |12 |13 |14 |15 |
- * |DD |CMP|ERR|VFE| * *  RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE |
- */
-
-/* command flags and offsets*/
-#define IAVF_AQ_FLAG_DD_SHIFT	0
-#define IAVF_AQ_FLAG_CMP_SHIFT	1
-#define IAVF_AQ_FLAG_ERR_SHIFT	2
-#define IAVF_AQ_FLAG_VFE_SHIFT	3
-#define IAVF_AQ_FLAG_LB_SHIFT	9
-#define IAVF_AQ_FLAG_RD_SHIFT	10
-#define IAVF_AQ_FLAG_VFC_SHIFT	11
-#define IAVF_AQ_FLAG_BUF_SHIFT	12
-#define IAVF_AQ_FLAG_SI_SHIFT	13
-#define IAVF_AQ_FLAG_EI_SHIFT	14
-#define IAVF_AQ_FLAG_FE_SHIFT	15
-
-#define IAVF_AQ_FLAG_DD		BIT(IAVF_AQ_FLAG_DD_SHIFT)  /* 0x1    */
-#define IAVF_AQ_FLAG_CMP	BIT(IAVF_AQ_FLAG_CMP_SHIFT) /* 0x2    */
-#define IAVF_AQ_FLAG_ERR	BIT(IAVF_AQ_FLAG_ERR_SHIFT) /* 0x4    */
-#define IAVF_AQ_FLAG_VFE	BIT(IAVF_AQ_FLAG_VFE_SHIFT) /* 0x8    */
-#define IAVF_AQ_FLAG_LB		BIT(IAVF_AQ_FLAG_LB_SHIFT)  /* 0x200  */
-#define IAVF_AQ_FLAG_RD		BIT(IAVF_AQ_FLAG_RD_SHIFT)  /* 0x400  */
-#define IAVF_AQ_FLAG_VFC	BIT(IAVF_AQ_FLAG_VFC_SHIFT) /* 0x800  */
-#define IAVF_AQ_FLAG_BUF	BIT(IAVF_AQ_FLAG_BUF_SHIFT) /* 0x1000 */
-#define IAVF_AQ_FLAG_SI		BIT(IAVF_AQ_FLAG_SI_SHIFT)  /* 0x2000 */
-#define IAVF_AQ_FLAG_EI		BIT(IAVF_AQ_FLAG_EI_SHIFT)  /* 0x4000 */
-#define IAVF_AQ_FLAG_FE		BIT(IAVF_AQ_FLAG_FE_SHIFT)  /* 0x8000 */
-
-/* error codes */
-enum iavf_admin_queue_err {
-	IAVF_AQ_RC_OK		= 0,  /* success */
-	IAVF_AQ_RC_EPERM	= 1,  /* Operation not permitted */
-	IAVF_AQ_RC_ENOENT	= 2,  /* No such element */
-	IAVF_AQ_RC_ESRCH	= 3,  /* Bad opcode */
-	IAVF_AQ_RC_EINTR	= 4,  /* operation interrupted */
-	IAVF_AQ_RC_EIO		= 5,  /* I/O error */
-	IAVF_AQ_RC_ENXIO	= 6,  /* No such resource */
-	IAVF_AQ_RC_E2BIG	= 7,  /* Arg too long */
-	IAVF_AQ_RC_EAGAIN	= 8,  /* Try again */
-	IAVF_AQ_RC_ENOMEM	= 9,  /* Out of memory */
-	IAVF_AQ_RC_EACCES	= 10, /* Permission denied */
-	IAVF_AQ_RC_EFAULT	= 11, /* Bad address */
-	IAVF_AQ_RC_EBUSY	= 12, /* Device or resource busy */
-	IAVF_AQ_RC_EEXIST	= 13, /* object already exists */
-	IAVF_AQ_RC_EINVAL	= 14, /* Invalid argument */
-	IAVF_AQ_RC_ENOTTY	= 15, /* Not a typewriter */
-	IAVF_AQ_RC_ENOSPC	= 16, /* No space left or alloc failure */
-	IAVF_AQ_RC_ENOSYS	= 17, /* Function not implemented */
-	IAVF_AQ_RC_ERANGE	= 18, /* Parameter out of range */
-	IAVF_AQ_RC_EFLUSHED	= 19, /* Cmd flushed due to prev cmd error */
-	IAVF_AQ_RC_BAD_ADDR	= 20, /* Descriptor contains a bad pointer */
-	IAVF_AQ_RC_EMODE	= 21, /* Op not allowed in current dev mode */
-	IAVF_AQ_RC_EFBIG	= 22, /* File too large */
-};
-
 /* Admin Queue command opcodes */
 enum iavf_admin_queue_opc {
 	/* aq commands */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c
index a9e1da35e248..4d12dfe1b481 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c
@@ -91,6 +91,55 @@ iavf_fill_adv_rss_sctp_hdr(struct virtchnl_proto_hdr *hdr, u64 hash_flds)
 }
 
 /**
+ * iavf_fill_adv_rss_gtp_hdr - Fill GTP-related RSS protocol headers
+ * @proto_hdrs: pointer to the virtchnl protocol headers structure to populate
+ * @packet_hdrs: bitmask of packet header types to configure
+ * @hash_flds: RSS hash field configuration
+ *
+ * This function populates the virtchnl protocol header structure with
+ * appropriate GTP-related header types based on the specified packet_hdrs.
+ * It supports GTPC, GTPU with extension headers, and uplink/downlink PDU
+ * types. For certain GTPU types, it also appends an IPv4 header to enable
+ * hashing on the destination IP address.
+ *
+ * Return: 0 on success or -EOPNOTSUPP if the packet_hdrs value is unsupported.
+ */
+static int
+iavf_fill_adv_rss_gtp_hdr(struct virtchnl_proto_hdrs *proto_hdrs,
+			  u32 packet_hdrs, u64 hash_flds)
+{
+	struct virtchnl_proto_hdr *hdr;
+
+	hdr = &proto_hdrs->proto_hdr[proto_hdrs->count - 1];
+
+	switch (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_GTP) {
+	case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC_TEID:
+	case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC:
+		VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, GTPC);
+		break;
+	case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_EH:
+		VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, GTPU_EH);
+		break;
+	case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_UP:
+		VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, GTPU_EH_PDU_UP);
+		hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
+		iavf_fill_adv_rss_ip4_hdr(hdr, IAVF_ADV_RSS_HASH_FLD_IPV4_DA);
+		break;
+	case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_DWN:
+		VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, GTPU_EH_PDU_DWN);
+		fallthrough;
+	case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_IP:
+		hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
+		iavf_fill_adv_rss_ip4_hdr(hdr, IAVF_ADV_RSS_HASH_FLD_IPV4_DA);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+/**
  * iavf_fill_adv_rss_cfg_msg - fill the RSS configuration into virtchnl message
  * @rss_cfg: the virtchnl message to be filled with RSS configuration setting
  * @packet_hdrs: the RSS configuration protocol header types
@@ -103,6 +152,8 @@ int
 iavf_fill_adv_rss_cfg_msg(struct virtchnl_rss_cfg *rss_cfg,
 			  u32 packet_hdrs, u64 hash_flds, bool symm)
 {
+	const u32 packet_l3_hdrs = packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L3;
+	const u32 packet_l4_hdrs = packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L4;
 	struct virtchnl_proto_hdrs *proto_hdrs = &rss_cfg->proto_hdrs;
 	struct virtchnl_proto_hdr *hdr;
 
@@ -113,31 +164,41 @@ iavf_fill_adv_rss_cfg_msg(struct virtchnl_rss_cfg *rss_cfg,
 
 	proto_hdrs->tunnel_level = 0;	/* always outer layer */
 
-	hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
-	switch (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L3) {
-	case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4:
-		iavf_fill_adv_rss_ip4_hdr(hdr, hash_flds);
-		break;
-	case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6:
-		iavf_fill_adv_rss_ip6_hdr(hdr, hash_flds);
-		break;
-	default:
-		return -EINVAL;
+	if (packet_l3_hdrs) {
+		hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
+		switch (packet_l3_hdrs) {
+		case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4:
+			iavf_fill_adv_rss_ip4_hdr(hdr, hash_flds);
+			break;
+		case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6:
+			iavf_fill_adv_rss_ip6_hdr(hdr, hash_flds);
+			break;
+		default:
+			return -EINVAL;
+		}
 	}
 
-	hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
-	switch (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L4) {
-	case IAVF_ADV_RSS_FLOW_SEG_HDR_TCP:
-		iavf_fill_adv_rss_tcp_hdr(hdr, hash_flds);
-		break;
-	case IAVF_ADV_RSS_FLOW_SEG_HDR_UDP:
-		iavf_fill_adv_rss_udp_hdr(hdr, hash_flds);
-		break;
-	case IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP:
-		iavf_fill_adv_rss_sctp_hdr(hdr, hash_flds);
-		break;
-	default:
-		return -EINVAL;
+	if (packet_l4_hdrs) {
+		hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
+		switch (packet_l4_hdrs) {
+		case IAVF_ADV_RSS_FLOW_SEG_HDR_TCP:
+			iavf_fill_adv_rss_tcp_hdr(hdr, hash_flds);
+			break;
+		case IAVF_ADV_RSS_FLOW_SEG_HDR_UDP:
+			iavf_fill_adv_rss_udp_hdr(hdr, hash_flds);
+			break;
+		case IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP:
+			iavf_fill_adv_rss_sctp_hdr(hdr, hash_flds);
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	if (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_GTP) {
+		hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
+		if (iavf_fill_adv_rss_gtp_hdr(proto_hdrs, packet_hdrs, hash_flds))
+			return -EINVAL;
 	}
 
 	return 0;
@@ -186,6 +247,8 @@ iavf_print_adv_rss_cfg(struct iavf_adapter *adapter, struct iavf_adv_rss *rss,
 		proto = "UDP";
 	else if (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP)
 		proto = "SCTP";
+	else if (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_GTP)
+		proto = "GTP";
 	else
 		return;
 
@@ -211,6 +274,16 @@ iavf_print_adv_rss_cfg(struct iavf_adapter *adapter, struct iavf_adv_rss *rss,
 			 IAVF_ADV_RSS_HASH_FLD_UDP_DST_PORT |
 			 IAVF_ADV_RSS_HASH_FLD_SCTP_DST_PORT))
 		strcat(hash_opt, "dst port,");
+	if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPC_TEID)
+		strcat(hash_opt, "gtp-c,");
+	if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPU_IP_TEID)
+		strcat(hash_opt, "gtp-u ip,");
+	if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPU_EH_TEID)
+		strcat(hash_opt, "gtp-u ext,");
+	if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPU_UP_TEID)
+		strcat(hash_opt, "gtp-u ul,");
+	if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPU_DWN_TEID)
+		strcat(hash_opt, "gtp-u dl,");
 
 	if (!action)
 		action = "";
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h
index e31eb2afebea..74cc9e0d528c 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h
@@ -22,6 +22,12 @@ enum iavf_adv_rss_flow_seg_hdr {
 	IAVF_ADV_RSS_FLOW_SEG_HDR_TCP	= 0x00000004,
 	IAVF_ADV_RSS_FLOW_SEG_HDR_UDP	= 0x00000008,
 	IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP	= 0x00000010,
+	IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC		= 0x00000400,
+	IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC_TEID	= 0x00000800,
+	IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_IP	= 0x00001000,
+	IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_EH	= 0x00002000,
+	IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_DWN	= 0x00004000,
+	IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_UP	= 0x00008000,
 };
 
 #define IAVF_ADV_RSS_FLOW_SEG_HDR_L3		\
@@ -33,6 +39,14 @@ enum iavf_adv_rss_flow_seg_hdr {
 	 IAVF_ADV_RSS_FLOW_SEG_HDR_UDP |	\
 	 IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP)
 
+#define IAVF_ADV_RSS_FLOW_SEG_HDR_GTP		\
+	(IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC |	\
+	 IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC_TEID |	\
+	 IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_IP |	\
+	 IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_EH |	\
+	 IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_DWN |	\
+	 IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_UP)
+
 enum iavf_adv_rss_flow_field {
 	/* L3 */
 	IAVF_ADV_RSS_FLOW_FIELD_IDX_IPV4_SA,
@@ -46,6 +60,17 @@ enum iavf_adv_rss_flow_field {
 	IAVF_ADV_RSS_FLOW_FIELD_IDX_UDP_DST_PORT,
 	IAVF_ADV_RSS_FLOW_FIELD_IDX_SCTP_SRC_PORT,
 	IAVF_ADV_RSS_FLOW_FIELD_IDX_SCTP_DST_PORT,
+	/* GTPC_TEID */
+	IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPC_TEID,
+	/* GTPU_IP */
+	IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_IP_TEID,
+	/* GTPU_EH */
+	IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_EH_TEID,
+	IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_EH_QFI,
+	/* GTPU_UP */
+	IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_UP_TEID,
+	/* GTPU_DWN */
+	IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_DWN_TEID,
 
 	/* The total number of enums must not exceed 64 */
 	IAVF_ADV_RSS_FLOW_FIELD_IDX_MAX
@@ -72,6 +97,12 @@ enum iavf_adv_rss_flow_field {
 	BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_SCTP_SRC_PORT)
 #define IAVF_ADV_RSS_HASH_FLD_SCTP_DST_PORT	\
 	BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_SCTP_DST_PORT)
+#define IAVF_ADV_RSS_HASH_FLD_GTPC_TEID	BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPC_TEID)
+#define IAVF_ADV_RSS_HASH_FLD_GTPU_IP_TEID BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_IP_TEID)
+#define IAVF_ADV_RSS_HASH_FLD_GTPU_EH_TEID BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_EH_TEID)
+#define IAVF_ADV_RSS_HASH_FLD_GTPU_UP_TEID BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_UP_TEID)
+#define IAVF_ADV_RSS_HASH_FLD_GTPU_DWN_TEID \
+	BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_DWN_TEID)
 
 /* bookkeeping of advanced RSS configuration */
 struct iavf_adv_rss {
diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c
index aa751ce3425b..614a886bca99 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_common.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_common.c
@@ -8,66 +8,6 @@
 #include "iavf_prototype.h"
 
 /**
- * iavf_aq_str - convert AQ err code to a string
- * @hw: pointer to the HW structure
- * @aq_err: the AQ error code to convert
- **/
-const char *iavf_aq_str(struct iavf_hw *hw, enum iavf_admin_queue_err aq_err)
-{
-	switch (aq_err) {
-	case IAVF_AQ_RC_OK:
-		return "OK";
-	case IAVF_AQ_RC_EPERM:
-		return "IAVF_AQ_RC_EPERM";
-	case IAVF_AQ_RC_ENOENT:
-		return "IAVF_AQ_RC_ENOENT";
-	case IAVF_AQ_RC_ESRCH:
-		return "IAVF_AQ_RC_ESRCH";
-	case IAVF_AQ_RC_EINTR:
-		return "IAVF_AQ_RC_EINTR";
-	case IAVF_AQ_RC_EIO:
-		return "IAVF_AQ_RC_EIO";
-	case IAVF_AQ_RC_ENXIO:
-		return "IAVF_AQ_RC_ENXIO";
-	case IAVF_AQ_RC_E2BIG:
-		return "IAVF_AQ_RC_E2BIG";
-	case IAVF_AQ_RC_EAGAIN:
-		return "IAVF_AQ_RC_EAGAIN";
-	case IAVF_AQ_RC_ENOMEM:
-		return "IAVF_AQ_RC_ENOMEM";
-	case IAVF_AQ_RC_EACCES:
-		return "IAVF_AQ_RC_EACCES";
-	case IAVF_AQ_RC_EFAULT:
-		return "IAVF_AQ_RC_EFAULT";
-	case IAVF_AQ_RC_EBUSY:
-		return "IAVF_AQ_RC_EBUSY";
-	case IAVF_AQ_RC_EEXIST:
-		return "IAVF_AQ_RC_EEXIST";
-	case IAVF_AQ_RC_EINVAL:
-		return "IAVF_AQ_RC_EINVAL";
-	case IAVF_AQ_RC_ENOTTY:
-		return "IAVF_AQ_RC_ENOTTY";
-	case IAVF_AQ_RC_ENOSPC:
-		return "IAVF_AQ_RC_ENOSPC";
-	case IAVF_AQ_RC_ENOSYS:
-		return "IAVF_AQ_RC_ENOSYS";
-	case IAVF_AQ_RC_ERANGE:
-		return "IAVF_AQ_RC_ERANGE";
-	case IAVF_AQ_RC_EFLUSHED:
-		return "IAVF_AQ_RC_EFLUSHED";
-	case IAVF_AQ_RC_BAD_ADDR:
-		return "IAVF_AQ_RC_BAD_ADDR";
-	case IAVF_AQ_RC_EMODE:
-		return "IAVF_AQ_RC_EMODE";
-	case IAVF_AQ_RC_EFBIG:
-		return "IAVF_AQ_RC_EFBIG";
-	}
-
-	snprintf(hw->err_str, sizeof(hw->err_str), "%d", aq_err);
-	return hw->err_str;
-}
-
-/**
  * iavf_stat_str - convert status err code to a string
  * @hw: pointer to the HW structure
  * @stat_err: the status error code to convert
@@ -228,7 +168,7 @@ const char *iavf_stat_str(struct iavf_hw *hw, enum iavf_status stat_err)
 void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask, void *desc,
 		   void *buffer, u16 buf_len)
 {
-	struct iavf_aq_desc *aq_desc = (struct iavf_aq_desc *)desc;
+	struct libie_aq_desc *aq_desc = (struct libie_aq_desc *)desc;
 	u8 *buf = (u8 *)buffer;
 
 	if ((!(mask & hw->debug_mask)) || !desc)
@@ -244,11 +184,11 @@ void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask, void *desc,
 		   le32_to_cpu(aq_desc->cookie_high),
 		   le32_to_cpu(aq_desc->cookie_low));
 	iavf_debug(hw, mask, "\tparam (0,1)  0x%08X 0x%08X\n",
-		   le32_to_cpu(aq_desc->params.internal.param0),
-		   le32_to_cpu(aq_desc->params.internal.param1));
+		   le32_to_cpu(aq_desc->params.generic.param0),
+		   le32_to_cpu(aq_desc->params.generic.param1));
 	iavf_debug(hw, mask, "\taddr (h,l)   0x%08X 0x%08X\n",
-		   le32_to_cpu(aq_desc->params.external.addr_high),
-		   le32_to_cpu(aq_desc->params.external.addr_low));
+		   le32_to_cpu(aq_desc->params.generic.addr_high),
+		   le32_to_cpu(aq_desc->params.generic.addr_low));
 
 	if (buffer && aq_desc->datalen) {
 		u16 len = le16_to_cpu(aq_desc->datalen);
@@ -297,11 +237,11 @@ bool iavf_check_asq_alive(struct iavf_hw *hw)
  **/
 enum iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading)
 {
-	struct iavf_aq_desc desc;
-	struct iavf_aqc_queue_shutdown *cmd =
-		(struct iavf_aqc_queue_shutdown *)&desc.params.raw;
+	struct iavf_aqc_queue_shutdown *cmd;
+	struct libie_aq_desc desc;
 	enum iavf_status status;
 
+	cmd = libie_aq_raw(&desc);
 	iavf_fill_default_direct_cmd_desc(&desc, iavf_aqc_opc_queue_shutdown);
 
 	if (unloading)
@@ -327,12 +267,13 @@ static enum iavf_status iavf_aq_get_set_rss_lut(struct iavf_hw *hw,
 						u8 *lut, u16 lut_size,
 						bool set)
 {
+	struct iavf_aqc_get_set_rss_lut *cmd_resp;
+	struct libie_aq_desc desc;
 	enum iavf_status status;
-	struct iavf_aq_desc desc;
-	struct iavf_aqc_get_set_rss_lut *cmd_resp =
-		   (struct iavf_aqc_get_set_rss_lut *)&desc.params.raw;
 	u16 flags;
 
+	cmd_resp = libie_aq_raw(&desc);
+
 	if (set)
 		iavf_fill_default_direct_cmd_desc(&desc,
 						  iavf_aqc_opc_set_rss_lut);
@@ -341,8 +282,8 @@ static enum iavf_status iavf_aq_get_set_rss_lut(struct iavf_hw *hw,
 						  iavf_aqc_opc_get_rss_lut);
 
 	/* Indirect command */
-	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_BUF);
-	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_RD);
 
 	vsi_id = FIELD_PREP(IAVF_AQC_SET_RSS_LUT_VSI_ID_MASK, vsi_id) |
 		 FIELD_PREP(IAVF_AQC_SET_RSS_LUT_VSI_VALID, 1);
@@ -392,11 +333,12 @@ iavf_status iavf_aq_get_set_rss_key(struct iavf_hw *hw, u16 vsi_id,
 				    struct iavf_aqc_get_set_rss_key_data *key,
 				    bool set)
 {
-	enum iavf_status status;
-	struct iavf_aq_desc desc;
-	struct iavf_aqc_get_set_rss_key *cmd_resp =
-			(struct iavf_aqc_get_set_rss_key *)&desc.params.raw;
 	u16 key_size = sizeof(struct iavf_aqc_get_set_rss_key_data);
+	struct iavf_aqc_get_set_rss_key *cmd_resp;
+	struct libie_aq_desc desc;
+	enum iavf_status status;
+
+	cmd_resp = libie_aq_raw(&desc);
 
 	if (set)
 		iavf_fill_default_direct_cmd_desc(&desc,
@@ -406,8 +348,8 @@ iavf_status iavf_aq_get_set_rss_key(struct iavf_hw *hw, u16 vsi_id,
 						  iavf_aqc_opc_get_rss_key);
 
 	/* Indirect command */
-	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_BUF);
-	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_RD);
 
 	vsi_id = FIELD_PREP(IAVF_AQC_SET_RSS_KEY_VSI_ID_MASK, vsi_id) |
 		 FIELD_PREP(IAVF_AQC_SET_RSS_KEY_VSI_VALID, 1);
@@ -452,18 +394,18 @@ enum iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw,
 					struct iavf_asq_cmd_details *cmd_details)
 {
 	struct iavf_asq_cmd_details details;
-	struct iavf_aq_desc desc;
+	struct libie_aq_desc desc;
 	enum iavf_status status;
 
 	iavf_fill_default_direct_cmd_desc(&desc, iavf_aqc_opc_send_msg_to_pf);
-	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_SI);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_SI);
 	desc.cookie_high = cpu_to_le32(v_opcode);
 	desc.cookie_low = cpu_to_le32(v_retval);
 	if (msglen) {
-		desc.flags |= cpu_to_le16((u16)(IAVF_AQ_FLAG_BUF
-						| IAVF_AQ_FLAG_RD));
+		desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF
+						| LIBIE_AQ_FLAG_RD));
 		if (msglen > IAVF_AQ_LARGE_BUF)
-			desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_LB);
+			desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 		desc.datalen = cpu_to_le16(msglen);
 	}
 	if (!cmd_details) {
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 74a1e9fe1821..2cc21289a707 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -4,6 +4,8 @@
 #include <linux/bitfield.h>
 #include <linux/uaccess.h>
 
+#include <net/netdev_lock.h>
+
 /* ethtool support for iavf */
 #include "iavf.h"
 
@@ -1256,9 +1258,10 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 {
 	struct ethtool_rx_flow_spec *fsp = &cmd->fs;
 	struct iavf_fdir_fltr *fltr;
-	int count = 50;
 	int err;
 
+	netdev_assert_locked(adapter->netdev);
+
 	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
@@ -1277,14 +1280,6 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	if (!fltr)
 		return -ENOMEM;
 
-	while (!mutex_trylock(&adapter->crit_lock)) {
-		if (--count == 0) {
-			kfree(fltr);
-			return -EINVAL;
-		}
-		udelay(1);
-	}
-
 	err = iavf_add_fdir_fltr_info(adapter, fsp, fltr);
 	if (!err)
 		err = iavf_fdir_add_fltr(adapter, fltr);
@@ -1292,7 +1287,6 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	if (err)
 		kfree(fltr);
 
-	mutex_unlock(&adapter->crit_lock);
 	return err;
 }
 
@@ -1313,14 +1307,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	return iavf_fdir_del_fltr(adapter, false, fsp->location);
 }
 
-/**
- * iavf_adv_rss_parse_hdrs - parses headers from RSS hash input
- * @cmd: ethtool rxnfc command
- *
- * This function parses the rxnfc command and returns intended
- * header types for RSS configuration
- */
-static u32 iavf_adv_rss_parse_hdrs(struct ethtool_rxnfc *cmd)
+static u32 iavf_adv_rss_parse_hdrs(const struct ethtool_rxfh_fields *cmd)
 {
 	u32 hdrs = IAVF_ADV_RSS_FLOW_SEG_HDR_NONE;
 
@@ -1349,6 +1336,56 @@ static u32 iavf_adv_rss_parse_hdrs(struct ethtool_rxnfc *cmd)
 		hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP |
 			IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6;
 		break;
+	case GTPU_V4_FLOW:
+		hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_IP |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4;
+		break;
+	case GTPC_V4_FLOW:
+		hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_UDP |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4;
+		break;
+	case GTPC_TEID_V4_FLOW:
+		hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC_TEID |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_UDP |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4;
+		break;
+	case GTPU_EH_V4_FLOW:
+		hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_EH |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4;
+		break;
+	case GTPU_UL_V4_FLOW:
+		hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_UP |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4;
+		break;
+	case GTPU_DL_V4_FLOW:
+		hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_DWN |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4;
+		break;
+	case GTPU_V6_FLOW:
+		hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_IP |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6;
+		break;
+	case GTPC_V6_FLOW:
+		hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6;
+		break;
+	case GTPC_TEID_V6_FLOW:
+		hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC_TEID |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6;
+		break;
+	case GTPU_EH_V6_FLOW:
+		hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_EH |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6;
+		break;
+	case GTPU_UL_V6_FLOW:
+		hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_UP |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6;
+		break;
+	case GTPU_DL_V6_FLOW:
+		hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_DWN |
+			IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6;
+		break;
 	default:
 		break;
 	}
@@ -1356,15 +1393,8 @@ static u32 iavf_adv_rss_parse_hdrs(struct ethtool_rxnfc *cmd)
 	return hdrs;
 }
 
-/**
- * iavf_adv_rss_parse_hash_flds - parses hash fields from RSS hash input
- * @cmd: ethtool rxnfc command
- * @symm: true if Symmetric Topelitz is set
- *
- * This function parses the rxnfc command and returns intended hash fields for
- * RSS configuration
- */
-static u64 iavf_adv_rss_parse_hash_flds(struct ethtool_rxnfc *cmd, bool symm)
+static u64
+iavf_adv_rss_parse_hash_flds(const struct ethtool_rxfh_fields *cmd, bool symm)
 {
 	u64 hfld = IAVF_ADV_RSS_HASH_INVALID;
 
@@ -1373,6 +1403,12 @@ static u64 iavf_adv_rss_parse_hash_flds(struct ethtool_rxnfc *cmd, bool symm)
 		case TCP_V4_FLOW:
 		case UDP_V4_FLOW:
 		case SCTP_V4_FLOW:
+		case GTPU_V4_FLOW:
+		case GTPC_V4_FLOW:
+		case GTPC_TEID_V4_FLOW:
+		case GTPU_EH_V4_FLOW:
+		case GTPU_UL_V4_FLOW:
+		case GTPU_DL_V4_FLOW:
 			if (cmd->data & RXH_IP_SRC)
 				hfld |= IAVF_ADV_RSS_HASH_FLD_IPV4_SA;
 			if (cmd->data & RXH_IP_DST)
@@ -1381,6 +1417,12 @@ static u64 iavf_adv_rss_parse_hash_flds(struct ethtool_rxnfc *cmd, bool symm)
 		case TCP_V6_FLOW:
 		case UDP_V6_FLOW:
 		case SCTP_V6_FLOW:
+		case GTPU_V6_FLOW:
+		case GTPC_V6_FLOW:
+		case GTPC_TEID_V6_FLOW:
+		case GTPU_EH_V6_FLOW:
+		case GTPU_UL_V6_FLOW:
+		case GTPU_DL_V6_FLOW:
 			if (cmd->data & RXH_IP_SRC)
 				hfld |= IAVF_ADV_RSS_HASH_FLD_IPV6_SA;
 			if (cmd->data & RXH_IP_DST)
@@ -1402,6 +1444,7 @@ static u64 iavf_adv_rss_parse_hash_flds(struct ethtool_rxnfc *cmd, bool symm)
 			break;
 		case UDP_V4_FLOW:
 		case UDP_V6_FLOW:
+		case GTPC_V4_FLOW:
 			if (cmd->data & RXH_L4_B_0_1)
 				hfld |= IAVF_ADV_RSS_HASH_FLD_UDP_SRC_PORT;
 			if (cmd->data & RXH_L4_B_2_3)
@@ -1418,28 +1461,51 @@ static u64 iavf_adv_rss_parse_hash_flds(struct ethtool_rxnfc *cmd, bool symm)
 			break;
 		}
 	}
+	if (cmd->data & RXH_GTP_TEID) {
+		switch (cmd->flow_type) {
+		case GTPC_TEID_V4_FLOW:
+		case GTPC_TEID_V6_FLOW:
+			hfld |= IAVF_ADV_RSS_HASH_FLD_GTPC_TEID;
+			break;
+		case GTPU_V4_FLOW:
+		case GTPU_V6_FLOW:
+			hfld |= IAVF_ADV_RSS_HASH_FLD_GTPU_IP_TEID;
+			break;
+		case GTPU_EH_V4_FLOW:
+		case GTPU_EH_V6_FLOW:
+			hfld |= IAVF_ADV_RSS_HASH_FLD_GTPU_EH_TEID;
+			break;
+		case GTPU_UL_V4_FLOW:
+		case GTPU_UL_V6_FLOW:
+			hfld |= IAVF_ADV_RSS_HASH_FLD_GTPU_UP_TEID;
+			break;
+		case GTPU_DL_V4_FLOW:
+		case GTPU_DL_V6_FLOW:
+			hfld |= IAVF_ADV_RSS_HASH_FLD_GTPU_DWN_TEID;
+			break;
+		default:
+			break;
+		}
+	}
 
 	return hfld;
 }
 
-/**
- * iavf_set_adv_rss_hash_opt - Enable/Disable flow types for RSS hash
- * @adapter: pointer to the VF adapter structure
- * @cmd: ethtool rxnfc command
- *
- * Returns Success if the flow input set is supported.
- */
 static int
-iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
-			  struct ethtool_rxnfc *cmd)
+iavf_set_rxfh_fields(struct net_device *netdev,
+		     const struct ethtool_rxfh_fields *cmd,
+		     struct netlink_ext_ack *extack)
 {
+	struct iavf_adapter *adapter = netdev_priv(netdev);
 	struct iavf_adv_rss *rss_old, *rss_new;
 	bool rss_new_add = false;
-	int count = 50, err = 0;
 	bool symm = false;
 	u64 hash_flds;
+	int err = 0;
 	u32 hdrs;
 
+	netdev_assert_locked(adapter->netdev);
+
 	if (!ADV_RSS_SUPPORT(adapter))
 		return -EOPNOTSUPP;
 
@@ -1463,15 +1529,6 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 		return -EINVAL;
 	}
 
-	while (!mutex_trylock(&adapter->crit_lock)) {
-		if (--count == 0) {
-			kfree(rss_new);
-			return -EINVAL;
-		}
-
-		udelay(1);
-	}
-
 	spin_lock_bh(&adapter->adv_rss_lock);
 	rss_old = iavf_find_adv_rss_cfg_by_hdrs(adapter, hdrs);
 	if (rss_old) {
@@ -1500,25 +1557,16 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 	if (!err)
 		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_ADV_RSS_CFG);
 
-	mutex_unlock(&adapter->crit_lock);
-
 	if (!rss_new_add)
 		kfree(rss_new);
 
 	return err;
 }
 
-/**
- * iavf_get_adv_rss_hash_opt - Retrieve hash fields for a given flow-type
- * @adapter: pointer to the VF adapter structure
- * @cmd: ethtool rxnfc command
- *
- * Returns Success if the flow input set is supported.
- */
 static int
-iavf_get_adv_rss_hash_opt(struct iavf_adapter *adapter,
-			  struct ethtool_rxnfc *cmd)
+iavf_get_rxfh_fields(struct net_device *netdev, struct ethtool_rxfh_fields *cmd)
 {
+	struct iavf_adapter *adapter = netdev_priv(netdev);
 	struct iavf_adv_rss *rss;
 	u64 hash_flds;
 	u32 hdrs;
@@ -1583,9 +1631,6 @@ static int iavf_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 	case ETHTOOL_SRXCLSRLDEL:
 		ret = iavf_del_fdir_ethtool(adapter, cmd);
 		break;
-	case ETHTOOL_SRXFH:
-		ret = iavf_set_adv_rss_hash_opt(adapter, cmd);
-		break;
 	default:
 		break;
 	}
@@ -1594,6 +1639,19 @@ static int iavf_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 }
 
 /**
+ * iavf_get_rx_ring_count - get RX ring count
+ * @netdev: network interface device structure
+ *
+ * Return: number of RX rings.
+ **/
+static u32 iavf_get_rx_ring_count(struct net_device *netdev)
+{
+	struct iavf_adapter *adapter = netdev_priv(netdev);
+
+	return adapter->num_active_queues;
+}
+
+/**
  * iavf_get_rxnfc - command to get RX flow classification rules
  * @netdev: network interface device structure
  * @cmd: ethtool rxnfc command
@@ -1608,10 +1666,6 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 	int ret = -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
-	case ETHTOOL_GRXRINGS:
-		cmd->data = adapter->num_active_queues;
-		ret = 0;
-		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 			break;
@@ -1627,9 +1681,6 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 	case ETHTOOL_GRXCLSRLALL:
 		ret = iavf_get_fdir_fltr_ids(adapter, cmd, (u32 *)rule_locs);
 		break;
-	case ETHTOOL_GRXFH:
-		ret = iavf_get_adv_rss_hash_opt(adapter, cmd);
-		break;
 	default:
 		break;
 	}
@@ -1808,7 +1859,7 @@ static int iavf_set_rxfh(struct net_device *netdev,
 static const struct ethtool_ops iavf_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
-	.cap_rss_sym_xor_supported = true,
+	.supported_input_xfrm	= RXH_XFRM_SYM_XOR,
 	.get_drvinfo		= iavf_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_ringparam		= iavf_get_ringparam,
@@ -1824,9 +1875,12 @@ static const struct ethtool_ops iavf_ethtool_ops = {
 	.set_per_queue_coalesce = iavf_set_per_queue_coalesce,
 	.set_rxnfc		= iavf_set_rxnfc,
 	.get_rxnfc		= iavf_get_rxnfc,
+	.get_rx_ring_count	= iavf_get_rx_ring_count,
 	.get_rxfh_indir_size	= iavf_get_rxfh_indir_size,
 	.get_rxfh		= iavf_get_rxfh,
 	.set_rxfh		= iavf_set_rxfh,
+	.get_rxfh_fields	= iavf_get_rxfh_fields,
+	.set_rxfh_fields	= iavf_set_rxfh_fields,
 	.get_channels		= iavf_get_channels,
 	.set_channels		= iavf_set_channels,
 	.get_rxfh_key_size	= iavf_get_rxfh_key_size,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index a9e54866ae6b..c2fbe443ef85 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2,8 +2,10 @@
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
 #include <linux/net/intel/libie/rx.h>
+#include <net/netdev_lock.h>
 
 #include "iavf.h"
+#include "iavf_ptp.h"
 #include "iavf_prototype.h"
 /* All iavf tracepoints are defined by the include below, which must
  * be included exactly once across the whole kernel with
@@ -48,6 +50,7 @@ MODULE_ALIAS("i40evf");
 MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver");
 MODULE_IMPORT_NS("LIBETH");
 MODULE_IMPORT_NS("LIBIE");
+MODULE_IMPORT_NS("LIBIE_ADMINQ");
 MODULE_LICENSE("GPL v2");
 
 static const struct net_device_ops iavf_netdev_ops;
@@ -526,33 +529,6 @@ static void iavf_map_rings_to_vectors(struct iavf_adapter *adapter)
 }
 
 /**
- * iavf_irq_affinity_notify - Callback for affinity changes
- * @notify: context as to what irq was changed
- * @mask: the new affinity mask
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * so that we may register to receive changes to the irq affinity masks.
- **/
-static void iavf_irq_affinity_notify(struct irq_affinity_notify *notify,
-				     const cpumask_t *mask)
-{
-	struct iavf_q_vector *q_vector =
-		container_of(notify, struct iavf_q_vector, affinity_notify);
-
-	cpumask_copy(&q_vector->affinity_mask, mask);
-}
-
-/**
- * iavf_irq_affinity_release - Callback for affinity notifier release
- * @ref: internal core kernel usage
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * to inform the current notification subscriber that they will no longer
- * receive notifications.
- **/
-static void iavf_irq_affinity_release(struct kref *ref) {}
-
-/**
  * iavf_request_traffic_irqs - Initialize MSI-X interrupts
  * @adapter: board private structure
  * @basename: device basename
@@ -566,7 +542,6 @@ iavf_request_traffic_irqs(struct iavf_adapter *adapter, char *basename)
 	unsigned int vector, q_vectors;
 	unsigned int rx_int_idx = 0, tx_int_idx = 0;
 	int irq_num, err;
-	int cpu;
 
 	iavf_irq_disable(adapter);
 	/* Decrement for Other and TCP Timer vectors */
@@ -601,17 +576,6 @@ iavf_request_traffic_irqs(struct iavf_adapter *adapter, char *basename)
 				 "Request_irq failed, error: %d\n", err);
 			goto free_queue_irqs;
 		}
-		/* register for affinity change notifications */
-		q_vector->affinity_notify.notify = iavf_irq_affinity_notify;
-		q_vector->affinity_notify.release =
-						   iavf_irq_affinity_release;
-		irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);
-		/* Spread the IRQ affinity hints across online CPUs. Note that
-		 * get_cpu_mask returns a mask with a permanent lifetime so
-		 * it's safe to use as a hint for irq_update_affinity_hint.
-		 */
-		cpu = cpumask_local_spread(q_vector->v_idx, -1);
-		irq_update_affinity_hint(irq_num, get_cpu_mask(cpu));
 	}
 
 	return 0;
@@ -620,8 +584,6 @@ free_queue_irqs:
 	while (vector) {
 		vector--;
 		irq_num = adapter->msix_entries[vector + NONQ_VECS].vector;
-		irq_set_affinity_notifier(irq_num, NULL);
-		irq_update_affinity_hint(irq_num, NULL);
 		free_irq(irq_num, &adapter->q_vectors[vector]);
 	}
 	return err;
@@ -663,6 +625,7 @@ static int iavf_request_misc_irq(struct iavf_adapter *adapter)
  **/
 static void iavf_free_traffic_irqs(struct iavf_adapter *adapter)
 {
+	struct iavf_q_vector *q_vector;
 	int vector, irq_num, q_vectors;
 
 	if (!adapter->msix_entries)
@@ -671,10 +634,10 @@ static void iavf_free_traffic_irqs(struct iavf_adapter *adapter)
 	q_vectors = adapter->num_msix_vectors - NONQ_VECS;
 
 	for (vector = 0; vector < q_vectors; vector++) {
+		q_vector = &adapter->q_vectors[vector];
+		netif_napi_set_irq_locked(&q_vector->napi, -1);
 		irq_num = adapter->msix_entries[vector + NONQ_VECS].vector;
-		irq_set_affinity_notifier(irq_num, NULL);
-		irq_update_affinity_hint(irq_num, NULL);
-		free_irq(irq_num, &adapter->q_vectors[vector]);
+		free_irq(irq_num, q_vector);
 	}
 }
 
@@ -710,6 +673,47 @@ static void iavf_configure_tx(struct iavf_adapter *adapter)
 }
 
 /**
+ * iavf_select_rx_desc_format - Select Rx descriptor format
+ * @adapter: adapter private structure
+ *
+ * Select what Rx descriptor format based on availability and enabled
+ * features.
+ *
+ * Return: the desired RXDID to select for a given Rx queue, as defined by
+ *         enum virtchnl_rxdid_format.
+ */
+static u8 iavf_select_rx_desc_format(const struct iavf_adapter *adapter)
+{
+	u64 rxdids = adapter->supp_rxdids;
+
+	/* If we did not negotiate VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC, we must
+	 * stick with the default value of the legacy 32 byte format.
+	 */
+	if (!IAVF_RXDID_ALLOWED(adapter))
+		return VIRTCHNL_RXDID_1_32B_BASE;
+
+	/* Rx timestamping requires the use of flexible NIC descriptors */
+	if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) {
+		if (rxdids & BIT(VIRTCHNL_RXDID_2_FLEX_SQ_NIC))
+			return VIRTCHNL_RXDID_2_FLEX_SQ_NIC;
+
+		pci_warn(adapter->pdev,
+			 "Unable to negotiate flexible descriptor format\n");
+	}
+
+	/* Warn if the PF does not list support for the default legacy
+	 * descriptor format. This shouldn't happen, as this is the format
+	 * used if VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is not supported. It is
+	 * likely caused by a bug in the PF implementation failing to indicate
+	 * support for the format.
+	 */
+	if (!(rxdids & VIRTCHNL_RXDID_1_32B_BASE_M))
+		netdev_warn(adapter->netdev, "PF does not list support for default Rx descriptor format\n");
+
+	return VIRTCHNL_RXDID_1_32B_BASE;
+}
+
+/**
  * iavf_configure_rx - Configure Receive Unit after Reset
  * @adapter: board private structure
  *
@@ -719,8 +723,12 @@ static void iavf_configure_rx(struct iavf_adapter *adapter)
 {
 	struct iavf_hw *hw = &adapter->hw;
 
-	for (u32 i = 0; i < adapter->num_active_queues; i++)
+	adapter->rxdid = iavf_select_rx_desc_format(adapter);
+
+	for (u32 i = 0; i < adapter->num_active_queues; i++) {
 		adapter->rx_rings[i].tail = hw->hw_addr + IAVF_QRX_TAIL1(i);
+		adapter->rx_rings[i].rxdid = adapter->rxdid;
+	}
 }
 
 /**
@@ -773,6 +781,11 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter,
 		f->state = IAVF_VLAN_ADD;
 		adapter->num_vlan_filters++;
 		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER);
+	} else if (f->state == IAVF_VLAN_REMOVE) {
+		/* IAVF_VLAN_REMOVE means that VLAN wasn't yet removed.
+		 * We can safely only change the state here.
+		 */
+		f->state = IAVF_VLAN_ACTIVE;
 	}
 
 clearout:
@@ -793,8 +806,18 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan)
 
 	f = iavf_find_vlan(adapter, vlan);
 	if (f) {
-		f->state = IAVF_VLAN_REMOVE;
-		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER);
+		/* IAVF_ADD_VLAN means that VLAN wasn't even added yet.
+		 * Remove it from the list.
+		 */
+		if (f->state == IAVF_VLAN_ADD) {
+			list_del(&f->list);
+			kfree(f);
+			adapter->num_vlan_filters--;
+		} else {
+			f->state = IAVF_VLAN_REMOVE;
+			iavf_schedule_aq_request(adapter,
+						 IAVF_FLAG_AQ_DEL_VLAN_FILTER);
+		}
 	}
 
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
@@ -1180,7 +1203,7 @@ static void iavf_napi_enable_all(struct iavf_adapter *adapter)
 
 		q_vector = &adapter->q_vectors[q_idx];
 		napi = &q_vector->napi;
-		napi_enable(napi);
+		napi_enable_locked(napi);
 	}
 }
 
@@ -1196,7 +1219,7 @@ static void iavf_napi_disable_all(struct iavf_adapter *adapter)
 
 	for (q_idx = 0; q_idx < q_vectors; q_idx++) {
 		q_vector = &adapter->q_vectors[q_idx];
-		napi_disable(&q_vector->napi);
+		napi_disable_locked(&q_vector->napi);
 	}
 }
 
@@ -1225,11 +1248,11 @@ static void iavf_configure(struct iavf_adapter *adapter)
 /**
  * iavf_up_complete - Finish the last steps of bringing up a connection
  * @adapter: board private structure
- *
- * Expects to be called while holding crit_lock.
- **/
+ */
 static void iavf_up_complete(struct iavf_adapter *adapter)
 {
+	netdev_assert_locked(adapter->netdev);
+
 	iavf_change_state(adapter, __IAVF_RUNNING);
 	clear_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
 
@@ -1348,13 +1371,13 @@ static void iavf_clear_adv_rss_conf(struct iavf_adapter *adapter)
 /**
  * iavf_down - Shutdown the connection processing
  * @adapter: board private structure
- *
- * Expects to be called while holding crit_lock.
- **/
+ */
 void iavf_down(struct iavf_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 
+	netdev_assert_locked(netdev);
+
 	if (adapter->state <= __IAVF_DOWN_PENDING)
 		return;
 
@@ -1672,7 +1695,7 @@ static int iavf_config_rss_aq(struct iavf_adapter *adapter)
 	if (status) {
 		dev_err(&adapter->pdev->dev, "Cannot set RSS key, err %s aq_err %s\n",
 			iavf_stat_str(hw, status),
-			iavf_aq_str(hw, hw->aq.asq_last_status));
+			libie_aq_str(hw->aq.asq_last_status));
 		return iavf_status_to_errno(status);
 
 	}
@@ -1682,7 +1705,7 @@ static int iavf_config_rss_aq(struct iavf_adapter *adapter)
 	if (status) {
 		dev_err(&adapter->pdev->dev, "Cannot set RSS lut, err %s aq_err %s\n",
 			iavf_stat_str(hw, status),
-			iavf_aq_str(hw, hw->aq.asq_last_status));
+			libie_aq_str(hw->aq.asq_last_status));
 		return iavf_status_to_errno(status);
 	}
 
@@ -1761,12 +1784,13 @@ static int iavf_init_rss(struct iavf_adapter *adapter)
 		/* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */
 		if (adapter->vf_res->vf_cap_flags &
 		    VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
-			adapter->hena = IAVF_DEFAULT_RSS_HENA_EXPANDED;
+			adapter->rss_hashcfg =
+				IAVF_DEFAULT_RSS_HASHCFG_EXPANDED;
 		else
-			adapter->hena = IAVF_DEFAULT_RSS_HENA;
+			adapter->rss_hashcfg = IAVF_DEFAULT_RSS_HASHCFG;
 
-		wr32(hw, IAVF_VFQF_HENA(0), (u32)adapter->hena);
-		wr32(hw, IAVF_VFQF_HENA(1), (u32)(adapter->hena >> 32));
+		wr32(hw, IAVF_VFQF_HENA(0), (u32)adapter->rss_hashcfg);
+		wr32(hw, IAVF_VFQF_HENA(1), (u32)(adapter->rss_hashcfg >> 32));
 	}
 
 	iavf_fill_rss_lut(adapter);
@@ -1784,7 +1808,7 @@ static int iavf_init_rss(struct iavf_adapter *adapter)
  **/
 static int iavf_alloc_q_vectors(struct iavf_adapter *adapter)
 {
-	int q_idx = 0, num_q_vectors;
+	int q_idx = 0, num_q_vectors, irq_num;
 	struct iavf_q_vector *q_vector;
 
 	num_q_vectors = adapter->num_msix_vectors - NONQ_VECS;
@@ -1794,14 +1818,15 @@ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter)
 		return -ENOMEM;
 
 	for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
+		irq_num = adapter->msix_entries[q_idx + NONQ_VECS].vector;
 		q_vector = &adapter->q_vectors[q_idx];
 		q_vector->adapter = adapter;
 		q_vector->vsi = &adapter->vsi;
 		q_vector->v_idx = q_idx;
 		q_vector->reg_idx = q_idx;
-		cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask);
-		netif_napi_add(adapter->netdev, &q_vector->napi,
-			       iavf_napi_poll);
+		netif_napi_add_config_locked(adapter->netdev, &q_vector->napi,
+					     iavf_napi_poll, q_idx);
+		netif_napi_set_irq_locked(&q_vector->napi, irq_num);
 	}
 
 	return 0;
@@ -1827,7 +1852,7 @@ static void iavf_free_q_vectors(struct iavf_adapter *adapter)
 	for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
 		struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx];
 
-		netif_napi_del(&q_vector->napi);
+		netif_napi_del_locked(&q_vector->napi);
 	}
 	kfree(adapter->q_vectors);
 	adapter->q_vectors = NULL;
@@ -1963,21 +1988,21 @@ err:
  * iavf_finish_config - do all netdev work that needs RTNL
  * @work: our work_struct
  *
- * Do work that needs both RTNL and crit_lock.
- **/
+ * Do work that needs RTNL.
+ */
 static void iavf_finish_config(struct work_struct *work)
 {
 	struct iavf_adapter *adapter;
+	bool netdev_released = false;
 	int pairs, err;
 
 	adapter = container_of(work, struct iavf_adapter, finish_config);
 
 	/* Always take RTNL first to prevent circular lock dependency;
-	 * The dev->lock is needed to update the queue number
+	 * the dev->lock (== netdev lock) is needed to update the queue number.
 	 */
 	rtnl_lock();
-	mutex_lock(&adapter->netdev->lock);
-	mutex_lock(&adapter->crit_lock);
+	netdev_lock(adapter->netdev);
 
 	if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) &&
 	    adapter->netdev->reg_state == NETREG_REGISTERED &&
@@ -1988,26 +2013,33 @@ static void iavf_finish_config(struct work_struct *work)
 
 	switch (adapter->state) {
 	case __IAVF_DOWN:
+		/* Set the real number of queues when reset occurs while
+		 * state == __IAVF_DOWN
+		 */
+		pairs = adapter->num_active_queues;
+		netif_set_real_num_rx_queues(adapter->netdev, pairs);
+		netif_set_real_num_tx_queues(adapter->netdev, pairs);
+
 		if (adapter->netdev->reg_state != NETREG_REGISTERED) {
+			netdev_unlock(adapter->netdev);
+			netdev_released = true;
 			err = register_netdevice(adapter->netdev);
 			if (err) {
 				dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n",
 					err);
 
 				/* go back and try again.*/
+				netdev_lock(adapter->netdev);
 				iavf_free_rss(adapter);
 				iavf_free_misc_irq(adapter);
 				iavf_reset_interrupt_capability(adapter);
 				iavf_change_state(adapter,
 						  __IAVF_INIT_CONFIG_ADAPTER);
+				netdev_unlock(adapter->netdev);
 				goto out;
 			}
 		}
-
-		/* Set the real number of queues when reset occurs while
-		 * state == __IAVF_DOWN
-		 */
-		fallthrough;
+		break;
 	case __IAVF_RUNNING:
 		pairs = adapter->num_active_queues;
 		netif_set_real_num_rx_queues(adapter->netdev, pairs);
@@ -2019,8 +2051,8 @@ static void iavf_finish_config(struct work_struct *work)
 	}
 
 out:
-	mutex_unlock(&adapter->crit_lock);
-	mutex_unlock(&adapter->netdev->lock);
+	if (!netdev_released)
+		netdev_unlock(adapter->netdev);
 	rtnl_unlock();
 }
 
@@ -2049,6 +2081,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		return iavf_send_vf_config_msg(adapter);
 	if (adapter->aq_required & IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS)
 		return iavf_send_vf_offload_vlan_v2_msg(adapter);
+	if (adapter->aq_required & IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS)
+		return iavf_send_vf_supported_rxdids_msg(adapter);
+	if (adapter->aq_required & IAVF_FLAG_AQ_GET_PTP_CAPS)
+		return iavf_send_vf_ptp_caps_msg(adapter);
 	if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) {
 		iavf_disable_queues(adapter);
 		return 0;
@@ -2122,12 +2158,12 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_RSS;
 		return 0;
 	}
-	if (adapter->aq_required & IAVF_FLAG_AQ_GET_HENA) {
-		iavf_get_hena(adapter);
+	if (adapter->aq_required & IAVF_FLAG_AQ_GET_RSS_HASHCFG) {
+		iavf_get_rss_hashcfg(adapter);
 		return 0;
 	}
-	if (adapter->aq_required & IAVF_FLAG_AQ_SET_HENA) {
-		iavf_set_hena(adapter);
+	if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_HASHCFG) {
+		iavf_set_rss_hashcfg(adapter);
 		return 0;
 	}
 	if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_KEY) {
@@ -2213,7 +2249,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		iavf_enable_vlan_insertion_v2(adapter, ETH_P_8021AD);
 		return 0;
 	}
-
+	if (adapter->aq_required & IAVF_FLAG_AQ_SEND_PTP_CMD) {
+		iavf_virtchnl_send_ptp_cmd(adapter);
+		return IAVF_SUCCESS;
+	}
 	if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_STATS) {
 		iavf_request_stats(adapter);
 		return 0;
@@ -2578,6 +2617,112 @@ err:
 }
 
 /**
+ * iavf_init_send_supported_rxdids - part of querying for supported RXDID
+ * formats
+ * @adapter: board private structure
+ *
+ * Function processes send of the request for supported RXDIDs to the PF.
+ * Must clear IAVF_EXTENDED_CAP_RECV_RXDID if the message is not sent, e.g.
+ * due to the PF not negotiating VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC.
+ */
+static void iavf_init_send_supported_rxdids(struct iavf_adapter *adapter)
+{
+	int ret;
+
+	ret = iavf_send_vf_supported_rxdids_msg(adapter);
+	if (ret == -EOPNOTSUPP) {
+		/* PF does not support VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC. In this
+		 * case, we did not send the capability exchange message and
+		 * do not expect a response.
+		 */
+		adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID;
+	}
+
+	/* We sent the message, so move on to the next step */
+	adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_RXDID;
+}
+
+/**
+ * iavf_init_recv_supported_rxdids - part of querying for supported RXDID
+ * formats
+ * @adapter: board private structure
+ *
+ * Function processes receipt of the supported RXDIDs message from the PF.
+ **/
+static void iavf_init_recv_supported_rxdids(struct iavf_adapter *adapter)
+{
+	int ret;
+
+	memset(&adapter->supp_rxdids, 0, sizeof(adapter->supp_rxdids));
+
+	ret = iavf_get_vf_supported_rxdids(adapter);
+	if (ret)
+		goto err;
+
+	/* We've processed the PF response to the
+	 * VIRTCHNL_OP_GET_SUPPORTED_RXDIDS message we sent previously.
+	 */
+	adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID;
+	return;
+
+err:
+	/* We didn't receive a reply. Make sure we try sending again when
+	 * __IAVF_INIT_FAILED attempts to recover.
+	 */
+	adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_RXDID;
+	iavf_change_state(adapter, __IAVF_INIT_FAILED);
+}
+
+/**
+ * iavf_init_send_ptp_caps - part of querying for extended PTP capabilities
+ * @adapter: board private structure
+ *
+ * Function processes send of the request for 1588 PTP capabilities to the PF.
+ * Must clear IAVF_EXTENDED_CAP_SEND_PTP if the message is not sent, e.g.
+ * due to the PF not negotiating VIRTCHNL_VF_PTP_CAP
+ */
+static void iavf_init_send_ptp_caps(struct iavf_adapter *adapter)
+{
+	if (iavf_send_vf_ptp_caps_msg(adapter) == -EOPNOTSUPP) {
+		/* PF does not support VIRTCHNL_VF_PTP_CAP. In this case, we
+		 * did not send the capability exchange message and do not
+		 * expect a response.
+		 */
+		adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP;
+	}
+
+	/* We sent the message, so move on to the next step */
+	adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_PTP;
+}
+
+/**
+ * iavf_init_recv_ptp_caps - part of querying for supported PTP capabilities
+ * @adapter: board private structure
+ *
+ * Function processes receipt of the PTP capabilities supported on this VF.
+ **/
+static void iavf_init_recv_ptp_caps(struct iavf_adapter *adapter)
+{
+	memset(&adapter->ptp.hw_caps, 0, sizeof(adapter->ptp.hw_caps));
+
+	if (iavf_get_vf_ptp_caps(adapter))
+		goto err;
+
+	/* We've processed the PF response to the VIRTCHNL_OP_1588_PTP_GET_CAPS
+	 * message we sent previously.
+	 */
+	adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP;
+	return;
+
+err:
+	/* We didn't receive a reply. Make sure we try sending again when
+	 * __IAVF_INIT_FAILED attempts to recover.
+	 */
+	adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_PTP;
+	iavf_change_state(adapter, __IAVF_INIT_FAILED);
+}
+
+/**
  * iavf_init_process_extended_caps - Part of driver startup
  * @adapter: board private structure
  *
@@ -2601,6 +2746,24 @@ static void iavf_init_process_extended_caps(struct iavf_adapter *adapter)
 		return;
 	}
 
+	/* Process capability exchange for RXDID formats */
+	if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_RXDID) {
+		iavf_init_send_supported_rxdids(adapter);
+		return;
+	} else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_RXDID) {
+		iavf_init_recv_supported_rxdids(adapter);
+		return;
+	}
+
+	/* Process capability exchange for PTP features */
+	if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_PTP) {
+		iavf_init_send_ptp_caps(adapter);
+		return;
+	} else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_PTP) {
+		iavf_init_recv_ptp_caps(adapter);
+		return;
+	}
+
 	/* When we reach here, no further extended capabilities exchanges are
 	 * necessary, so we finally transition into __IAVF_INIT_CONFIG_ADAPTER
 	 */
@@ -2692,6 +2855,9 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)
 	if (QOS_ALLOWED(adapter))
 		adapter->aq_required |= IAVF_FLAG_AQ_GET_QOS_CAPS;
 
+	/* Setup initial PTP configuration */
+	iavf_ptp_init(adapter);
+
 	iavf_schedule_finish_config(adapter);
 	return;
 
@@ -2704,24 +2870,15 @@ err:
 	iavf_change_state(adapter, __IAVF_INIT_FAILED);
 }
 
-/**
- * iavf_watchdog_task - Periodic call-back task
- * @work: pointer to work_struct
- **/
-static void iavf_watchdog_task(struct work_struct *work)
+static const int IAVF_NO_RESCHED = -1;
+
+/* return: msec delay for requeueing itself */
+static int iavf_watchdog_step(struct iavf_adapter *adapter)
 {
-	struct iavf_adapter *adapter = container_of(work,
-						    struct iavf_adapter,
-						    watchdog_task.work);
 	struct iavf_hw *hw = &adapter->hw;
 	u32 reg_val;
 
-	if (!mutex_trylock(&adapter->crit_lock)) {
-		if (adapter->state == __IAVF_REMOVE)
-			return;
-
-		goto restart_watchdog;
-	}
+	netdev_assert_locked(adapter->netdev);
 
 	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
 		iavf_change_state(adapter, __IAVF_COMM_FAILED);
@@ -2729,34 +2886,19 @@ static void iavf_watchdog_task(struct work_struct *work)
 	switch (adapter->state) {
 	case __IAVF_STARTUP:
 		iavf_startup(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(30));
-		return;
+		return 30;
 	case __IAVF_INIT_VERSION_CHECK:
 		iavf_init_version_check(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(30));
-		return;
+		return 30;
 	case __IAVF_INIT_GET_RESOURCES:
 		iavf_init_get_resources(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(1));
-		return;
+		return 1;
 	case __IAVF_INIT_EXTENDED_CAPS:
 		iavf_init_process_extended_caps(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(1));
-		return;
+		return 1;
 	case __IAVF_INIT_CONFIG_ADAPTER:
 		iavf_init_config_adapter(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(1));
-		return;
+		return 1;
 	case __IAVF_INIT_FAILED:
 		if (test_bit(__IAVF_IN_REMOVE_TASK,
 			     &adapter->crit_section)) {
@@ -2764,24 +2906,18 @@ static void iavf_watchdog_task(struct work_struct *work)
 			 * watchdog task, iavf_remove should handle this state
 			 * as it can loop forever
 			 */
-			mutex_unlock(&adapter->crit_lock);
-			return;
+			return IAVF_NO_RESCHED;
 		}
 		if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) {
 			dev_err(&adapter->pdev->dev,
 				"Failed to communicate with PF; waiting before retry\n");
 			adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED;
 			iavf_shutdown_adminq(hw);
-			mutex_unlock(&adapter->crit_lock);
-			queue_delayed_work(adapter->wq,
-					   &adapter->watchdog_task, (5 * HZ));
-			return;
+			return 5000;
 		}
 		/* Try again from failed step*/
 		iavf_change_state(adapter, adapter->last_state);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ);
-		return;
+		return 1000;
 	case __IAVF_COMM_FAILED:
 		if (test_bit(__IAVF_IN_REMOVE_TASK,
 			     &adapter->crit_section)) {
@@ -2791,8 +2927,7 @@ static void iavf_watchdog_task(struct work_struct *work)
 			 */
 			iavf_change_state(adapter, __IAVF_INIT_FAILED);
 			adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED;
-			mutex_unlock(&adapter->crit_lock);
-			return;
+			return IAVF_NO_RESCHED;
 		}
 		reg_val = rd32(hw, IAVF_VFGEN_RSTAT) &
 			  IAVF_VFGEN_RSTAT_VFR_STATE_MASK;
@@ -2810,16 +2945,9 @@ static void iavf_watchdog_task(struct work_struct *work)
 		}
 		adapter->aq_required = 0;
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq,
-				   &adapter->watchdog_task,
-				   msecs_to_jiffies(10));
-		return;
+		return 10;
 	case __IAVF_RESETTING:
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   HZ * 2);
-		return;
+		return 2000;
 	case __IAVF_DOWN:
 	case __IAVF_DOWN_PENDING:
 	case __IAVF_TESTING:
@@ -2846,8 +2974,7 @@ static void iavf_watchdog_task(struct work_struct *work)
 		break;
 	case __IAVF_REMOVE:
 	default:
-		mutex_unlock(&adapter->crit_lock);
-		return;
+		return IAVF_NO_RESCHED;
 	}
 
 	/* check for hw reset */
@@ -2857,22 +2984,29 @@ static void iavf_watchdog_task(struct work_struct *work)
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
 		dev_err(&adapter->pdev->dev, "Hardware reset detected\n");
 		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq,
-				   &adapter->watchdog_task, HZ * 2);
-		return;
 	}
 
-	mutex_unlock(&adapter->crit_lock);
-restart_watchdog:
+	return adapter->aq_required ? 20 : 2000;
+}
+
+static void iavf_watchdog_task(struct work_struct *work)
+{
+	struct iavf_adapter *adapter = container_of(work,
+						    struct iavf_adapter,
+						    watchdog_task.work);
+	struct net_device *netdev = adapter->netdev;
+	int msec_delay;
+
+	netdev_lock(netdev);
+	msec_delay = iavf_watchdog_step(adapter);
+	/* note that we schedule a different task */
 	if (adapter->state >= __IAVF_DOWN)
 		queue_work(adapter->wq, &adapter->adminq_task);
-	if (adapter->aq_required)
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(20));
-	else
+
+	if (msec_delay != IAVF_NO_RESCHED)
 		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   HZ * 2);
+				   msecs_to_jiffies(msec_delay));
+	netdev_unlock(netdev);
 }
 
 /**
@@ -2880,14 +3014,15 @@ restart_watchdog:
  * @adapter: board private structure
  *
  * Set communication failed flag and free all resources.
- * NOTE: This function is expected to be called with crit_lock being held.
- **/
+ */
 static void iavf_disable_vf(struct iavf_adapter *adapter)
 {
 	struct iavf_mac_filter *f, *ftmp;
 	struct iavf_vlan_filter *fv, *fvtmp;
 	struct iavf_cloud_filter *cf, *cftmp;
 
+	netdev_assert_locked(adapter->netdev);
+
 	adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED;
 
 	/* We don't use netif_running() because it may be true prior to
@@ -2987,17 +3122,7 @@ static void iavf_reset_task(struct work_struct *work)
 	int i = 0, err;
 	bool running;
 
-	/* When device is being removed it doesn't make sense to run the reset
-	 * task, just return in such a case.
-	 */
-	mutex_lock(&netdev->lock);
-	if (!mutex_trylock(&adapter->crit_lock)) {
-		if (adapter->state != __IAVF_REMOVE)
-			queue_work(adapter->wq, &adapter->reset_task);
-
-		mutex_unlock(&netdev->lock);
-		return;
-	}
+	netdev_lock(netdev);
 
 	iavf_misc_irq_disable(adapter);
 	if (adapter->flags & IAVF_FLAG_RESET_NEEDED) {
@@ -3042,12 +3167,22 @@ static void iavf_reset_task(struct work_struct *work)
 		dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
 			reg_val);
 		iavf_disable_vf(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		mutex_unlock(&netdev->lock);
+		netdev_unlock(netdev);
 		return; /* Do not attempt to reinit. It's dead, Jim. */
 	}
 
 continue_reset:
+	/* If we are still early in the state machine, just restart. */
+	if (adapter->state <= __IAVF_INIT_FAILED) {
+		iavf_shutdown_adminq(hw);
+		iavf_change_state(adapter, __IAVF_STARTUP);
+		iavf_startup(adapter);
+		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
+				   msecs_to_jiffies(30));
+		netdev_unlock(netdev);
+		return;
+	}
+
 	/* We don't use netif_running() because it may be true prior to
 	 * ndo_open() returning, so we can't assume it means all our open
 	 * tasks have finished, since we're not holding the rtnl_lock here.
@@ -3099,15 +3234,18 @@ continue_reset:
 	}
 
 	adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG;
-	/* always set since VIRTCHNL_OP_GET_VF_RESOURCES has not been
-	 * sent/received yet, so VLAN_V2_ALLOWED() cannot is not reliable here,
-	 * however the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS won't be sent until
-	 * VIRTCHNL_OP_GET_VF_RESOURCES and VIRTCHNL_VF_OFFLOAD_VLAN_V2 have
-	 * been successfully sent and negotiated
-	 */
-	adapter->aq_required |= IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS;
 	adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS;
 
+	/* Certain capabilities require an extended negotiation process using
+	 * extra messages that must be processed after getting the VF
+	 * configuration. The related checks such as VLAN_V2_ALLOWED() are not
+	 * reliable here, since the configuration has not yet been negotiated.
+	 *
+	 * Always set these flags, since them related VIRTCHNL messages won't
+	 * be sent until after VIRTCHNL_OP_GET_VF_RESOURCES.
+	 */
+	adapter->aq_required |= IAVF_FLAG_AQ_EXTENDED_CAPS;
+
 	spin_lock_bh(&adapter->mac_vlan_list_lock);
 
 	/* Delete filter for the current MAC address, it could have
@@ -3183,8 +3321,7 @@ continue_reset:
 	adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
 
 	wake_up(&adapter->reset_waitqueue);
-	mutex_unlock(&adapter->crit_lock);
-	mutex_unlock(&netdev->lock);
+	netdev_unlock(netdev);
 
 	return;
 reset_err:
@@ -3194,8 +3331,7 @@ reset_err:
 	}
 	iavf_disable_vf(adapter);
 
-	mutex_unlock(&adapter->crit_lock);
-	mutex_unlock(&netdev->lock);
+	netdev_unlock(netdev);
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
 }
 
@@ -3207,6 +3343,7 @@ static void iavf_adminq_task(struct work_struct *work)
 {
 	struct iavf_adapter *adapter =
 		container_of(work, struct iavf_adapter, adminq_task);
+	struct net_device *netdev = adapter->netdev;
 	struct iavf_hw *hw = &adapter->hw;
 	struct iavf_arq_event_info event;
 	enum virtchnl_ops v_op;
@@ -3214,13 +3351,7 @@ static void iavf_adminq_task(struct work_struct *work)
 	u32 val, oldval;
 	u16 pending;
 
-	if (!mutex_trylock(&adapter->crit_lock)) {
-		if (adapter->state == __IAVF_REMOVE)
-			return;
-
-		queue_work(adapter->wq, &adapter->adminq_task);
-		goto out;
-	}
+	netdev_lock(netdev);
 
 	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
 		goto unlock;
@@ -3287,8 +3418,7 @@ static void iavf_adminq_task(struct work_struct *work)
 freedom:
 	kfree(event.msg_buf);
 unlock:
-	mutex_unlock(&adapter->crit_lock);
-out:
+	netdev_unlock(netdev);
 	/* re-enable Admin queue interrupt cause */
 	iavf_misc_irq_enable(adapter);
 }
@@ -3667,10 +3797,8 @@ exit:
 	if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
 		return 0;
 
-	mutex_lock(&netdev->lock);
 	netif_set_real_num_rx_queues(netdev, total_qps);
 	netif_set_real_num_tx_queues(netdev, total_qps);
-	mutex_unlock(&netdev->lock);
 
 	return ret;
 }
@@ -3983,8 +4111,8 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter,
 				    struct flow_cls_offload *cls_flower)
 {
 	int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid);
-	struct iavf_cloud_filter *filter = NULL;
-	int err = -EINVAL, count = 50;
+	struct iavf_cloud_filter *filter;
+	int err;
 
 	if (tc < 0) {
 		dev_err(&adapter->pdev->dev, "Invalid traffic class\n");
@@ -3994,17 +4122,10 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter,
 	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
 	if (!filter)
 		return -ENOMEM;
-
-	while (!mutex_trylock(&adapter->crit_lock)) {
-		if (--count == 0) {
-			kfree(filter);
-			return err;
-		}
-		udelay(1);
-	}
-
 	filter->cookie = cls_flower->cookie;
 
+	netdev_lock(adapter->netdev);
+
 	/* bail out here if filter already exists */
 	spin_lock_bh(&adapter->cloud_filter_list_lock);
 	if (iavf_find_cf(adapter, &cls_flower->cookie)) {
@@ -4038,7 +4159,7 @@ err:
 	if (err)
 		kfree(filter);
 
-	mutex_unlock(&adapter->crit_lock);
+	netdev_unlock(adapter->netdev);
 	return err;
 }
 
@@ -4335,33 +4456,20 @@ static int iavf_open(struct net_device *netdev)
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	int err;
 
+	netdev_assert_locked(netdev);
+
 	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) {
 		dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n");
 		return -EIO;
 	}
 
-	while (!mutex_trylock(&adapter->crit_lock)) {
-		/* If we are in __IAVF_INIT_CONFIG_ADAPTER state the crit_lock
-		 * is already taken and iavf_open is called from an upper
-		 * device's notifier reacting on NETDEV_REGISTER event.
-		 * We have to leave here to avoid dead lock.
-		 */
-		if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER)
-			return -EBUSY;
-
-		usleep_range(500, 1000);
-	}
-
-	if (adapter->state != __IAVF_DOWN) {
-		err = -EBUSY;
-		goto err_unlock;
-	}
+	if (adapter->state != __IAVF_DOWN)
+		return -EBUSY;
 
 	if (adapter->state == __IAVF_RUNNING &&
 	    !test_bit(__IAVF_VSI_DOWN, adapter->vsi.state)) {
 		dev_dbg(&adapter->pdev->dev, "VF is already open.\n");
-		err = 0;
-		goto err_unlock;
+		return 0;
 	}
 
 	/* allocate transmit descriptors */
@@ -4380,9 +4488,7 @@ static int iavf_open(struct net_device *netdev)
 		goto err_req_irq;
 
 	spin_lock_bh(&adapter->mac_vlan_list_lock);
-
 	iavf_add_filter(adapter, adapter->hw.mac.addr);
-
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
 	/* Restore filters that were removed with IFF_DOWN */
@@ -4395,8 +4501,6 @@ static int iavf_open(struct net_device *netdev)
 
 	iavf_irq_enable(adapter, true);
 
-	mutex_unlock(&adapter->crit_lock);
-
 	return 0;
 
 err_req_irq:
@@ -4406,8 +4510,6 @@ err_setup_rx:
 	iavf_free_all_rx_resources(adapter);
 err_setup_tx:
 	iavf_free_all_tx_resources(adapter);
-err_unlock:
-	mutex_unlock(&adapter->crit_lock);
 
 	return err;
 }
@@ -4429,12 +4531,10 @@ static int iavf_close(struct net_device *netdev)
 	u64 aq_to_restore;
 	int status;
 
-	mutex_lock(&adapter->crit_lock);
+	netdev_assert_locked(netdev);
 
-	if (adapter->state <= __IAVF_DOWN_PENDING) {
-		mutex_unlock(&adapter->crit_lock);
+	if (adapter->state <= __IAVF_DOWN_PENDING)
 		return 0;
-	}
 
 	set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
 	/* We cannot send IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS before
@@ -4465,7 +4565,7 @@ static int iavf_close(struct net_device *netdev)
 	iavf_change_state(adapter, __IAVF_DOWN_PENDING);
 	iavf_free_traffic_irqs(adapter);
 
-	mutex_unlock(&adapter->crit_lock);
+	netdev_unlock(netdev);
 
 	/* We explicitly don't free resources here because the hardware is
 	 * still active and can DMA into memory. Resources are cleared in
@@ -4483,10 +4583,10 @@ static int iavf_close(struct net_device *netdev)
 				    msecs_to_jiffies(500));
 	if (!status)
 		netdev_warn(netdev, "Device resources not yet released\n");
+	netdev_lock(netdev);
 
-	mutex_lock(&adapter->crit_lock);
 	adapter->aq_required |= aq_to_restore;
-	mutex_unlock(&adapter->crit_lock);
+
 	return 0;
 }
 
@@ -4948,6 +5048,25 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev,
 	return iavf_fix_strip_features(adapter, features);
 }
 
+static int iavf_hwstamp_get(struct net_device *netdev,
+			    struct kernel_hwtstamp_config *config)
+{
+	struct iavf_adapter *adapter = netdev_priv(netdev);
+
+	*config = adapter->ptp.hwtstamp_config;
+
+	return 0;
+}
+
+static int iavf_hwstamp_set(struct net_device *netdev,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack)
+{
+	struct iavf_adapter *adapter = netdev_priv(netdev);
+
+	return iavf_ptp_set_ts_config(adapter, config, extack);
+}
+
 static int
 iavf_verify_shaper(struct net_shaper_binding *binding,
 		   const struct net_shaper *shaper,
@@ -4976,15 +5095,16 @@ iavf_shaper_set(struct net_shaper_binding *binding,
 	struct iavf_adapter *adapter = netdev_priv(binding->netdev);
 	const struct net_shaper_handle *handle = &shaper->handle;
 	struct iavf_ring *tx_ring;
-	int ret = 0;
+	int ret;
+
+	netdev_assert_locked(adapter->netdev);
 
-	mutex_lock(&adapter->crit_lock);
 	if (handle->id >= adapter->num_active_queues)
-		goto unlock;
+		return 0;
 
 	ret = iavf_verify_shaper(binding, shaper, extack);
 	if (ret)
-		goto unlock;
+		return ret;
 
 	tx_ring = &adapter->tx_rings[handle->id];
 
@@ -4994,9 +5114,7 @@ iavf_shaper_set(struct net_shaper_binding *binding,
 
 	adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW;
 
-unlock:
-	mutex_unlock(&adapter->crit_lock);
-	return ret;
+	return 0;
 }
 
 static int iavf_shaper_del(struct net_shaper_binding *binding,
@@ -5006,9 +5124,10 @@ static int iavf_shaper_del(struct net_shaper_binding *binding,
 	struct iavf_adapter *adapter = netdev_priv(binding->netdev);
 	struct iavf_ring *tx_ring;
 
-	mutex_lock(&adapter->crit_lock);
+	netdev_assert_locked(adapter->netdev);
+
 	if (handle->id >= adapter->num_active_queues)
-		goto unlock;
+		return 0;
 
 	tx_ring = &adapter->tx_rings[handle->id];
 	tx_ring->q_shaper.bw_min = 0;
@@ -5017,8 +5136,6 @@ static int iavf_shaper_del(struct net_shaper_binding *binding,
 
 	adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW;
 
-unlock:
-	mutex_unlock(&adapter->crit_lock);
 	return 0;
 }
 
@@ -5056,6 +5173,8 @@ static const struct net_device_ops iavf_netdev_ops = {
 	.ndo_set_features	= iavf_set_features,
 	.ndo_setup_tc		= iavf_setup_tc,
 	.net_shaper_ops		= &iavf_shaper_ops,
+	.ndo_hwtstamp_get	= iavf_hwstamp_get,
+	.ndo_hwtstamp_set	= iavf_hwstamp_set,
 };
 
 /**
@@ -5231,6 +5350,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_alloc_etherdev;
 	}
 
+	netif_set_affinity_auto(netdev);
 	SET_NETDEV_DEV(netdev, &pdev->dev);
 
 	pci_set_drvdata(pdev, netdev);
@@ -5277,10 +5397,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_alloc_qos_cap;
 	}
 
-	/* set up the locks for the AQ, do this only once in probe
-	 * and destroy them only once in remove
-	 */
-	mutex_init(&adapter->crit_lock);
 	mutex_init(&hw->aq.asq_mutex);
 	mutex_init(&hw->aq.arq_mutex);
 
@@ -5310,6 +5426,10 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Setup the wait queue for indicating virtchannel events */
 	init_waitqueue_head(&adapter->vc_waitqueue);
 
+	INIT_LIST_HEAD(&adapter->ptp.aq_cmds);
+	init_waitqueue_head(&adapter->ptp.phc_time_waitqueue);
+	mutex_init(&adapter->ptp.aq_cmd_lock);
+
 	queue_delayed_work(adapter->wq, &adapter->watchdog_task,
 			   msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
 	/* Initialization goes on in the work. Do not add more of it below. */
@@ -5339,20 +5459,24 @@ static int iavf_suspend(struct device *dev_d)
 {
 	struct net_device *netdev = dev_get_drvdata(dev_d);
 	struct iavf_adapter *adapter = netdev_priv(netdev);
+	bool running;
 
 	netif_device_detach(netdev);
 
-	mutex_lock(&adapter->crit_lock);
-
-	if (netif_running(netdev)) {
+	running = netif_running(netdev);
+	if (running)
 		rtnl_lock();
+	netdev_lock(netdev);
+
+	if (running)
 		iavf_down(adapter);
-		rtnl_unlock();
-	}
+
 	iavf_free_misc_irq(adapter);
 	iavf_reset_interrupt_capability(adapter);
 
-	mutex_unlock(&adapter->crit_lock);
+	netdev_unlock(netdev);
+	if (running)
+		rtnl_unlock();
 
 	return 0;
 }
@@ -5367,7 +5491,7 @@ static int iavf_resume(struct device *dev_d)
 {
 	struct pci_dev *pdev = to_pci_dev(dev_d);
 	struct iavf_adapter *adapter;
-	u32 err;
+	int err;
 
 	adapter = iavf_pdev_to_adapter(pdev);
 
@@ -5429,20 +5553,20 @@ static void iavf_remove(struct pci_dev *pdev)
 	 * There are flows where register/unregister netdev may race.
 	 */
 	while (1) {
-		mutex_lock(&adapter->crit_lock);
+		netdev_lock(netdev);
 		if (adapter->state == __IAVF_RUNNING ||
 		    adapter->state == __IAVF_DOWN ||
 		    adapter->state == __IAVF_INIT_FAILED) {
-			mutex_unlock(&adapter->crit_lock);
+			netdev_unlock(netdev);
 			break;
 		}
 		/* Simply return if we already went through iavf_shutdown */
 		if (adapter->state == __IAVF_REMOVE) {
-			mutex_unlock(&adapter->crit_lock);
+			netdev_unlock(netdev);
 			return;
 		}
 
-		mutex_unlock(&adapter->crit_lock);
+		netdev_unlock(netdev);
 		usleep_range(500, 1000);
 	}
 	cancel_delayed_work_sync(&adapter->watchdog_task);
@@ -5451,7 +5575,7 @@ static void iavf_remove(struct pci_dev *pdev)
 	if (netdev->reg_state == NETREG_REGISTERED)
 		unregister_netdev(netdev);
 
-	mutex_lock(&adapter->crit_lock);
+	netdev_lock(netdev);
 	dev_info(&adapter->pdev->dev, "Removing device\n");
 	iavf_change_state(adapter, __IAVF_REMOVE);
 
@@ -5463,11 +5587,15 @@ static void iavf_remove(struct pci_dev *pdev)
 		msleep(50);
 	}
 
+	iavf_ptp_release(adapter);
+
 	iavf_misc_irq_disable(adapter);
 	/* Shut down all the garbage mashers on the detention level */
+	netdev_unlock(netdev);
 	cancel_work_sync(&adapter->reset_task);
 	cancel_delayed_work_sync(&adapter->watchdog_task);
 	cancel_work_sync(&adapter->adminq_task);
+	netdev_lock(netdev);
 
 	adapter->aq_required = 0;
 	adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
@@ -5485,8 +5613,7 @@ static void iavf_remove(struct pci_dev *pdev)
 	/* destroy the locks only once, here */
 	mutex_destroy(&hw->aq.arq_mutex);
 	mutex_destroy(&hw->aq.asq_mutex);
-	mutex_unlock(&adapter->crit_lock);
-	mutex_destroy(&adapter->crit_lock);
+	netdev_unlock(netdev);
 
 	iounmap(hw->hw_addr);
 	pci_release_regions(pdev);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_prototype.h b/drivers/net/ethernet/intel/iavf/iavf_prototype.h
index cac9d1a35a52..7f9f9dbf959a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_prototype.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_prototype.h
@@ -22,7 +22,7 @@ enum iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
 					struct iavf_arq_event_info *e,
 					u16 *events_pending);
 enum iavf_status iavf_asq_send_command(struct iavf_hw *hw,
-				       struct iavf_aq_desc *desc,
+				       struct libie_aq_desc *desc,
 				       void *buff, /* can be NULL */
 				       u16 buff_size,
 				       struct iavf_asq_cmd_details *cmd_details);
@@ -34,7 +34,6 @@ void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask,
 
 bool iavf_check_asq_alive(struct iavf_hw *hw);
 enum iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading);
-const char *iavf_aq_str(struct iavf_hw *hw, enum iavf_admin_queue_err aq_err);
 const char *iavf_stat_str(struct iavf_hw *hw, enum iavf_status stat_err);
 
 enum iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 seid,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.c b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
new file mode 100644
index 000000000000..9cbd8c154031
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
@@ -0,0 +1,492 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024 Intel Corporation. */
+
+#include "iavf.h"
+#include "iavf_ptp.h"
+
+#define iavf_clock_to_adapter(info)				\
+	container_of_const(info, struct iavf_adapter, ptp.info)
+
+/**
+ * iavf_ptp_disable_rx_tstamp - Disable timestamping in Rx rings
+ * @adapter: private adapter structure
+ *
+ * Disable timestamp reporting for all Rx rings.
+ */
+static void iavf_ptp_disable_rx_tstamp(struct iavf_adapter *adapter)
+{
+	for (u32 i = 0; i < adapter->num_active_queues; i++)
+		adapter->rx_rings[i].flags &= ~IAVF_TXRX_FLAGS_HW_TSTAMP;
+}
+
+/**
+ * iavf_ptp_enable_rx_tstamp - Enable timestamping in Rx rings
+ * @adapter: private adapter structure
+ *
+ * Enable timestamp reporting for all Rx rings.
+ */
+static void iavf_ptp_enable_rx_tstamp(struct iavf_adapter *adapter)
+{
+	for (u32 i = 0; i < adapter->num_active_queues; i++)
+		adapter->rx_rings[i].flags |= IAVF_TXRX_FLAGS_HW_TSTAMP;
+}
+
+/**
+ * iavf_ptp_set_timestamp_mode - Set device timestamping mode
+ * @adapter: private adapter structure
+ * @config: pointer to kernel_hwtstamp_config
+ *
+ * Set the timestamping mode requested from the userspace.
+ *
+ * Note: this function always translates Rx timestamp requests for any packet
+ * category into HWTSTAMP_FILTER_ALL.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+static int iavf_ptp_set_timestamp_mode(struct iavf_adapter *adapter,
+				       struct kernel_hwtstamp_config *config)
+{
+	/* Reserved for future extensions. */
+	if (config->flags)
+		return -EINVAL;
+
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+		break;
+	case HWTSTAMP_TX_ON:
+		return -EOPNOTSUPP;
+	default:
+		return -ERANGE;
+	}
+
+	if (config->rx_filter == HWTSTAMP_FILTER_NONE) {
+		iavf_ptp_disable_rx_tstamp(adapter);
+		return 0;
+	} else if (config->rx_filter > HWTSTAMP_FILTER_NTP_ALL) {
+		return -ERANGE;
+	} else if (!(iavf_ptp_cap_supported(adapter,
+					    VIRTCHNL_1588_PTP_CAP_RX_TSTAMP))) {
+		return -EOPNOTSUPP;
+	}
+
+	config->rx_filter = HWTSTAMP_FILTER_ALL;
+	iavf_ptp_enable_rx_tstamp(adapter);
+
+	return 0;
+}
+
+/**
+ * iavf_ptp_set_ts_config - Set timestamping configuration
+ * @adapter: private adapter structure
+ * @config: pointer to kernel_hwtstamp_config structure
+ * @extack: pointer to netlink_ext_ack structure
+ *
+ * Program the requested timestamping configuration to the device.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack)
+{
+	int err;
+
+	err = iavf_ptp_set_timestamp_mode(adapter, config);
+	if (err)
+		return err;
+
+	/* Save successful settings for future reference */
+	adapter->ptp.hwtstamp_config = *config;
+
+	return 0;
+}
+
+/**
+ * iavf_ptp_cap_supported - Check if a PTP capability is supported
+ * @adapter: private adapter structure
+ * @cap: the capability bitmask to check
+ *
+ * Return: true if every capability set in cap is also set in the enabled
+ *         capabilities reported by the PF, false otherwise.
+ */
+bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap)
+{
+	if (!IAVF_PTP_ALLOWED(adapter))
+		return false;
+
+	/* Only return true if every bit in cap is set in hw_caps.caps */
+	return (adapter->ptp.hw_caps.caps & cap) == cap;
+}
+
+/**
+ * iavf_allocate_ptp_cmd - Allocate a PTP command message structure
+ * @v_opcode: the virtchnl opcode
+ * @msglen: length in bytes of the associated virtchnl structure
+ *
+ * Allocates a PTP command message and pre-fills it with the provided message
+ * length and opcode.
+ *
+ * Return: allocated PTP command.
+ */
+static struct iavf_ptp_aq_cmd *iavf_allocate_ptp_cmd(enum virtchnl_ops v_opcode,
+						     u16 msglen)
+{
+	struct iavf_ptp_aq_cmd *cmd;
+
+	cmd = kzalloc(struct_size(cmd, msg, msglen), GFP_KERNEL);
+	if (!cmd)
+		return NULL;
+
+	cmd->v_opcode = v_opcode;
+	cmd->msglen = msglen;
+
+	return cmd;
+}
+
+/**
+ * iavf_queue_ptp_cmd - Queue PTP command for sending over virtchnl
+ * @adapter: private adapter structure
+ * @cmd: the command structure to send
+ *
+ * Queue the given command structure into the PTP virtchnl command queue tos
+ * end to the PF.
+ */
+static void iavf_queue_ptp_cmd(struct iavf_adapter *adapter,
+			       struct iavf_ptp_aq_cmd *cmd)
+{
+	mutex_lock(&adapter->ptp.aq_cmd_lock);
+	list_add_tail(&cmd->list, &adapter->ptp.aq_cmds);
+	mutex_unlock(&adapter->ptp.aq_cmd_lock);
+
+	adapter->aq_required |= IAVF_FLAG_AQ_SEND_PTP_CMD;
+	mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+}
+
+/**
+ * iavf_send_phc_read - Send request to read PHC time
+ * @adapter: private adapter structure
+ *
+ * Send a request to obtain the PTP hardware clock time. This allocates the
+ * VIRTCHNL_OP_1588_PTP_GET_TIME message and queues it up to send to
+ * indirectly read the PHC time.
+ *
+ * This function does not wait for the reply from the PF.
+ *
+ * Return: 0 if success, error code otherwise.
+ */
+static int iavf_send_phc_read(struct iavf_adapter *adapter)
+{
+	struct iavf_ptp_aq_cmd *cmd;
+
+	if (!adapter->ptp.clock)
+		return -EOPNOTSUPP;
+
+	cmd = iavf_allocate_ptp_cmd(VIRTCHNL_OP_1588_PTP_GET_TIME,
+				    sizeof(struct virtchnl_phc_time));
+	if (!cmd)
+		return -ENOMEM;
+
+	iavf_queue_ptp_cmd(adapter, cmd);
+
+	return 0;
+}
+
+/**
+ * iavf_read_phc_indirect - Indirectly read the PHC time via virtchnl
+ * @adapter: private adapter structure
+ * @ts: storage for the timestamp value
+ * @sts: system timestamp values before and after the read
+ *
+ * Used when the device does not have direct register access to the PHC time.
+ * Indirectly reads the time via the VIRTCHNL_OP_1588_PTP_GET_TIME, and waits
+ * for the reply from the PF.
+ *
+ * Based on some simple measurements using ftrace and phc2sys, this clock
+ * access method has about a ~110 usec latency even when the system is not
+ * under load. In order to achieve acceptable results when using phc2sys with
+ * the indirect clock access method, it is recommended to use more
+ * conservative proportional and integration constants with the P/I servo.
+ *
+ * Return: 0 if success, error code otherwise.
+ */
+static int iavf_read_phc_indirect(struct iavf_adapter *adapter,
+				  struct timespec64 *ts,
+				  struct ptp_system_timestamp *sts)
+{
+	long ret;
+	int err;
+
+	adapter->ptp.phc_time_ready = false;
+
+	ptp_read_system_prets(sts);
+
+	err = iavf_send_phc_read(adapter);
+	if (err)
+		return err;
+
+	ret = wait_event_interruptible_timeout(adapter->ptp.phc_time_waitqueue,
+					       adapter->ptp.phc_time_ready,
+					       HZ);
+
+	ptp_read_system_postts(sts);
+
+	if (ret < 0)
+		return ret;
+	else if (!ret)
+		return -EBUSY;
+
+	*ts = ns_to_timespec64(adapter->ptp.cached_phc_time);
+
+	return 0;
+}
+
+static int iavf_ptp_gettimex64(struct ptp_clock_info *info,
+			       struct timespec64 *ts,
+			       struct ptp_system_timestamp *sts)
+{
+	struct iavf_adapter *adapter = iavf_clock_to_adapter(info);
+
+	if (!adapter->ptp.clock)
+		return -EOPNOTSUPP;
+
+	return iavf_read_phc_indirect(adapter, ts, sts);
+}
+
+static int iavf_ptp_settime64(struct ptp_clock_info *info,
+			      const struct timespec64 *ts)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * iavf_ptp_cache_phc_time - Cache PHC time for performing timestamp extension
+ * @adapter: private adapter structure
+ *
+ * Periodically cache the PHC time in order to allow for timestamp extension.
+ * This is required because the Tx and Rx timestamps only contain 32bits of
+ * nanoseconds. Timestamp extension allows calculating the corrected 64bit
+ * timestamp. This algorithm relies on the cached time being within ~1 second
+ * of the timestamp.
+ */
+static void iavf_ptp_cache_phc_time(struct iavf_adapter *adapter)
+{
+	if (!time_is_before_jiffies(adapter->ptp.cached_phc_updated + HZ))
+		return;
+
+	/* The response from virtchnl will store the time into
+	 * cached_phc_time.
+	 */
+	iavf_send_phc_read(adapter);
+}
+
+/**
+ * iavf_ptp_do_aux_work - Perform periodic work required for PTP support
+ * @info: PTP clock info structure
+ *
+ * Handler to take care of periodic work required for PTP operation. This
+ * includes the following tasks:
+ *
+ *   1) updating cached_phc_time
+ *
+ *      cached_phc_time is used by the Tx and Rx timestamp flows in order to
+ *      perform timestamp extension, by carefully comparing the timestamp
+ *      32bit nanosecond timestamps and determining the corrected 64bit
+ *      timestamp value to report to userspace. This algorithm only works if
+ *      the cached_phc_time is within ~1 second of the Tx or Rx timestamp
+ *      event. This task periodically reads the PHC time and stores it, to
+ *      ensure that timestamp extension operates correctly.
+ *
+ * Returns: time in jiffies until the periodic task should be re-scheduled.
+ */
+static long iavf_ptp_do_aux_work(struct ptp_clock_info *info)
+{
+	struct iavf_adapter *adapter = iavf_clock_to_adapter(info);
+
+	iavf_ptp_cache_phc_time(adapter);
+
+	/* Check work about twice a second */
+	return msecs_to_jiffies(500);
+}
+
+/**
+ * iavf_ptp_register_clock - Register a new PTP for userspace
+ * @adapter: private adapter structure
+ *
+ * Allocate and register a new PTP clock device if necessary.
+ *
+ * Return: 0 if success, error otherwise.
+ */
+static int iavf_ptp_register_clock(struct iavf_adapter *adapter)
+{
+	struct ptp_clock_info *ptp_info = &adapter->ptp.info;
+	struct device *dev = &adapter->pdev->dev;
+	struct ptp_clock *clock;
+
+	snprintf(ptp_info->name, sizeof(ptp_info->name), "%s-%s-clk",
+		 KBUILD_MODNAME, dev_name(dev));
+	ptp_info->owner = THIS_MODULE;
+	ptp_info->gettimex64 = iavf_ptp_gettimex64;
+	ptp_info->settime64 = iavf_ptp_settime64;
+	ptp_info->do_aux_work = iavf_ptp_do_aux_work;
+
+	clock = ptp_clock_register(ptp_info, dev);
+	if (IS_ERR(clock))
+		return PTR_ERR(clock);
+
+	adapter->ptp.clock = clock;
+
+	dev_dbg(&adapter->pdev->dev, "PTP clock %s registered\n",
+		adapter->ptp.info.name);
+
+	return 0;
+}
+
+/**
+ * iavf_ptp_init - Initialize PTP support if capability was negotiated
+ * @adapter: private adapter structure
+ *
+ * Initialize PTP functionality, based on the capabilities that the PF has
+ * enabled for this VF.
+ */
+void iavf_ptp_init(struct iavf_adapter *adapter)
+{
+	int err;
+
+	if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC)) {
+		pci_notice(adapter->pdev,
+			   "Device does not have PTP clock support\n");
+		return;
+	}
+
+	err = iavf_ptp_register_clock(adapter);
+	if (err) {
+		pci_err(adapter->pdev,
+			"Failed to register PTP clock device (%p)\n",
+			ERR_PTR(err));
+		return;
+	}
+
+	for (int i = 0; i < adapter->num_active_queues; i++) {
+		struct iavf_ring *rx_ring = &adapter->rx_rings[i];
+
+		rx_ring->ptp = &adapter->ptp;
+	}
+
+	ptp_schedule_worker(adapter->ptp.clock, 0);
+}
+
+/**
+ * iavf_ptp_release - Disable PTP support
+ * @adapter: private adapter structure
+ *
+ * Release all PTP resources that were previously initialized.
+ */
+void iavf_ptp_release(struct iavf_adapter *adapter)
+{
+	struct iavf_ptp_aq_cmd *cmd, *tmp;
+
+	if (!adapter->ptp.clock)
+		return;
+
+	pci_dbg(adapter->pdev, "removing PTP clock %s\n",
+		adapter->ptp.info.name);
+	ptp_clock_unregister(adapter->ptp.clock);
+	adapter->ptp.clock = NULL;
+
+	/* Cancel any remaining uncompleted PTP clock commands */
+	mutex_lock(&adapter->ptp.aq_cmd_lock);
+	list_for_each_entry_safe(cmd, tmp, &adapter->ptp.aq_cmds, list) {
+		list_del(&cmd->list);
+		kfree(cmd);
+	}
+	adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+	mutex_unlock(&adapter->ptp.aq_cmd_lock);
+
+	adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+	iavf_ptp_disable_rx_tstamp(adapter);
+}
+
+/**
+ * iavf_ptp_process_caps - Handle change in PTP capabilities
+ * @adapter: private adapter structure
+ *
+ * Handle any state changes necessary due to change in PTP capabilities, such
+ * as after a device reset or change in configuration from the PF.
+ */
+void iavf_ptp_process_caps(struct iavf_adapter *adapter)
+{
+	bool phc = iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC);
+
+	/* Check if the device gained or lost necessary access to support the
+	 * PTP hardware clock. If so, driver must respond appropriately by
+	 * creating or destroying the PTP clock device.
+	 */
+	if (adapter->ptp.clock && !phc)
+		iavf_ptp_release(adapter);
+	else if (!adapter->ptp.clock && phc)
+		iavf_ptp_init(adapter);
+
+	/* Check if the device lost access to Rx timestamp incoming packets */
+	if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) {
+		adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+		iavf_ptp_disable_rx_tstamp(adapter);
+	}
+}
+
+/**
+ * iavf_ptp_extend_32b_timestamp - Convert a 32b nanoseconds timestamp to 64b
+ * nanoseconds
+ * @cached_phc_time: recently cached copy of PHC time
+ * @in_tstamp: Ingress/egress 32b nanoseconds timestamp value
+ *
+ * Hardware captures timestamps which contain only 32 bits of nominal
+ * nanoseconds, as opposed to the 64bit timestamps that the stack expects.
+ *
+ * Extend the 32bit nanosecond timestamp using the following algorithm and
+ * assumptions:
+ *
+ * 1) have a recently cached copy of the PHC time
+ * 2) assume that the in_tstamp was captured 2^31 nanoseconds (~2.1
+ *    seconds) before or after the PHC time was captured.
+ * 3) calculate the delta between the cached time and the timestamp
+ * 4) if the delta is smaller than 2^31 nanoseconds, then the timestamp was
+ *    captured after the PHC time. In this case, the full timestamp is just
+ *    the cached PHC time plus the delta.
+ * 5) otherwise, if the delta is larger than 2^31 nanoseconds, then the
+ *    timestamp was captured *before* the PHC time, i.e. because the PHC
+ *    cache was updated after the timestamp was captured by hardware. In this
+ *    case, the full timestamp is the cached time minus the inverse delta.
+ *
+ * This algorithm works even if the PHC time was updated after a Tx timestamp
+ * was requested, but before the Tx timestamp event was reported from
+ * hardware.
+ *
+ * This calculation primarily relies on keeping the cached PHC time up to
+ * date. If the timestamp was captured more than 2^31 nanoseconds after the
+ * PHC time, it is possible that the lower 32bits of PHC time have
+ * overflowed more than once, and we might generate an incorrect timestamp.
+ *
+ * This is prevented by (a) periodically updating the cached PHC time once
+ * a second, and (b) discarding any Tx timestamp packet if it has waited for
+ * a timestamp for more than one second.
+ *
+ * Return: extended timestamp (to 64b).
+ */
+u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp)
+{
+	u32 low = lower_32_bits(cached_phc_time);
+	u32 delta = in_tstamp - low;
+	u64 ns;
+
+	/* Do not assume that the in_tstamp is always more recent than the
+	 * cached PHC time. If the delta is large, it indicates that the
+	 * in_tstamp was taken in the past, and should be converted
+	 * forward.
+	 */
+	if (delta > S32_MAX)
+		ns = cached_phc_time - (low - in_tstamp);
+	else
+		ns = cached_phc_time + delta;
+
+	return ns;
+}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.h b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
new file mode 100644
index 000000000000..783b8f287cd9
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IAVF_PTP_H_
+#define _IAVF_PTP_H_
+
+#include "iavf_types.h"
+
+/* bit indicating whether a 40bit timestamp is valid */
+#define IAVF_PTP_40B_TSTAMP_VALID	BIT(24)
+
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+void iavf_ptp_init(struct iavf_adapter *adapter);
+void iavf_ptp_release(struct iavf_adapter *adapter);
+void iavf_ptp_process_caps(struct iavf_adapter *adapter);
+bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap);
+void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter);
+int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack);
+u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp);
+#else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
+static inline void iavf_ptp_init(struct iavf_adapter *adapter) { }
+static inline void iavf_ptp_release(struct iavf_adapter *adapter) { }
+static inline void iavf_ptp_process_caps(struct iavf_adapter *adapter) { }
+static inline bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter,
+					  u32 cap)
+{
+	return false;
+}
+
+static inline void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter) { }
+static inline int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
+					 struct kernel_hwtstamp_config *config,
+					 struct netlink_ext_ack *extack)
+{
+	return -1;
+}
+
+static inline u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time,
+						u32 in_tstamp)
+{
+	return 0;
+}
+
+#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
+#endif /* _IAVF_PTP_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h
index 62212011c807..c5e4d1823886 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_trace.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h
@@ -112,7 +112,7 @@ DECLARE_EVENT_CLASS(
 	iavf_rx_template,
 
 	TP_PROTO(struct iavf_ring *ring,
-		 union iavf_32byte_rx_desc *desc,
+		 struct iavf_rx_desc *desc,
 		 struct sk_buff *skb),
 
 	TP_ARGS(ring, desc, skb),
@@ -140,7 +140,7 @@ DECLARE_EVENT_CLASS(
 DEFINE_EVENT(
 	iavf_rx_template, iavf_clean_rx_irq,
 	TP_PROTO(struct iavf_ring *ring,
-		 union iavf_32byte_rx_desc *desc,
+		 struct iavf_rx_desc *desc,
 		 struct sk_buff *skb),
 
 	TP_ARGS(ring, desc, skb));
@@ -148,7 +148,7 @@ DEFINE_EVENT(
 DEFINE_EVENT(
 	iavf_rx_template, iavf_clean_rx_irq_rx,
 	TP_PROTO(struct iavf_ring *ring,
-		 union iavf_32byte_rx_desc *desc,
+		 struct iavf_rx_desc *desc,
 		 struct sk_buff *skb),
 
 	TP_ARGS(ring, desc, skb));
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 26b424fd6718..363c42bf3dcf 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -8,6 +8,26 @@
 #include "iavf.h"
 #include "iavf_trace.h"
 #include "iavf_prototype.h"
+#include "iavf_ptp.h"
+
+/**
+ * iavf_is_descriptor_done - tests DD bit in Rx descriptor
+ * @qw1: quad word 1 from descriptor to get Descriptor Done field from
+ * @flex: is the descriptor flex or legacy
+ *
+ * This function tests the descriptor done bit in specified descriptor. Because
+ * there are two types of descriptors (legacy and flex) the parameter rx_ring
+ * is used to distinguish.
+ *
+ * Return: true or false based on the state of DD bit in Rx descriptor.
+ */
+static bool iavf_is_descriptor_done(u64 qw1, bool flex)
+{
+	if (flex)
+		return FIELD_GET(IAVF_RXD_FLEX_DD_M, qw1);
+	else
+		return FIELD_GET(IAVF_RXD_LEGACY_DD_M, qw1);
+}
 
 static __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
 			 u32 td_tag)
@@ -703,7 +723,7 @@ static void iavf_clean_rx_ring(struct iavf_ring *rx_ring)
 	for (u32 i = rx_ring->next_to_clean; i != rx_ring->next_to_use; ) {
 		const struct libeth_fqe *rx_fqes = &rx_ring->rx_fqes[i];
 
-		page_pool_put_full_page(rx_ring->pp, rx_fqes->page, false);
+		libeth_rx_recycle_slow(rx_fqes->netmem);
 
 		if (unlikely(++i == rx_ring->count))
 			i = 0;
@@ -766,7 +786,7 @@ int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring)
 	u64_stats_init(&rx_ring->syncp);
 
 	/* Round up to nearest 4K */
-	rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_rx_desc);
+	rx_ring->size = rx_ring->count * sizeof(struct iavf_rx_desc);
 	rx_ring->size = ALIGN(rx_ring->size, 4096);
 	rx_ring->desc = dma_alloc_coherent(fq.pp->p.dev, rx_ring->size,
 					   &rx_ring->dma, GFP_KERNEL);
@@ -845,7 +865,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
 		.count		= rx_ring->count,
 	};
 	u16 ntu = rx_ring->next_to_use;
-	union iavf_rx_desc *rx_desc;
+	struct iavf_rx_desc *rx_desc;
 
 	/* do nothing if no valid netdev defined */
 	if (!rx_ring->netdev || !cleaned_count)
@@ -863,7 +883,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
-		rx_desc->read.pkt_addr = cpu_to_le64(addr);
+		rx_desc->qw0 = cpu_to_le64(addr);
 
 		rx_desc++;
 		ntu++;
@@ -873,7 +893,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
 		}
 
 		/* clear the status bits for the next_to_use descriptor */
-		rx_desc->wb.qword1.status_error_len = 0;
+		rx_desc->qw1 = 0;
 
 		cleaned_count--;
 	} while (cleaned_count);
@@ -896,60 +916,43 @@ no_buffers:
 }
 
 /**
- * iavf_rx_checksum - Indicate in skb if hw indicated a good cksum
+ * iavf_rx_csum - Indicate in skb if hw indicated a good checksum
  * @vsi: the VSI we care about
  * @skb: skb currently being received and modified
- * @rx_desc: the receive descriptor
+ * @decoded_pt: decoded ptype information
+ * @csum_bits: decoded Rx descriptor information
  **/
-static void iavf_rx_checksum(struct iavf_vsi *vsi,
-			     struct sk_buff *skb,
-			     union iavf_rx_desc *rx_desc)
+static void iavf_rx_csum(const struct iavf_vsi *vsi, struct sk_buff *skb,
+			 struct libeth_rx_pt decoded_pt,
+			 struct libeth_rx_csum csum_bits)
 {
-	struct libeth_rx_pt decoded;
-	u32 rx_error, rx_status;
 	bool ipv4, ipv6;
-	u8 ptype;
-	u64 qword;
 
 	skb->ip_summed = CHECKSUM_NONE;
 
-	qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
-
-	decoded = libie_rx_pt_parse(ptype);
-	if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded))
-		return;
-
-	rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword);
-	rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword);
-
 	/* did the hardware decode the packet and checksum? */
-	if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT)))
+	if (unlikely(!csum_bits.l3l4p))
 		return;
 
-	ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4;
-	ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6;
+	ipv4 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV4;
+	ipv6 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV6;
 
-	if (ipv4 &&
-	    (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) |
-			 BIT(IAVF_RX_DESC_ERROR_EIPE_SHIFT))))
+	if (unlikely(ipv4 && (csum_bits.ipe || csum_bits.eipe)))
 		goto checksum_fail;
 
 	/* likely incorrect csum if alternate IP extension headers found */
-	if (ipv6 &&
-	    rx_status & BIT(IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT))
-		/* don't increment checksum err here, non-fatal err */
+	if (unlikely(ipv6 && csum_bits.ipv6exadd))
 		return;
 
 	/* there was some L4 error, count error and punt packet to the stack */
-	if (rx_error & BIT(IAVF_RX_DESC_ERROR_L4E_SHIFT))
+	if (unlikely(csum_bits.l4e))
 		goto checksum_fail;
 
 	/* handle packets that were not able to be checksummed due
 	 * to arrival speed, in this case the stack can compute
 	 * the csum.
 	 */
-	if (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT))
+	if (unlikely(csum_bits.pprs))
 		return;
 
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -960,52 +963,196 @@ checksum_fail:
 }
 
 /**
- * iavf_rx_hash - set the hash value in the skb
+ * iavf_legacy_rx_csum - Indicate in skb if hw indicated a good checksum
+ * @vsi: the VSI we care about
+ * @qw1: quad word 1
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ *
+ * Return: decoded checksum bits.
+ **/
+static struct libeth_rx_csum
+iavf_legacy_rx_csum(const struct iavf_vsi *vsi, u64 qw1,
+		    const struct libeth_rx_pt decoded_pt)
+{
+	struct libeth_rx_csum csum_bits = {};
+
+	if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt))
+		return csum_bits;
+
+	csum_bits.ipe = FIELD_GET(IAVF_RXD_LEGACY_IPE_M, qw1);
+	csum_bits.eipe = FIELD_GET(IAVF_RXD_LEGACY_EIPE_M, qw1);
+	csum_bits.l4e = FIELD_GET(IAVF_RXD_LEGACY_L4E_M, qw1);
+	csum_bits.pprs = FIELD_GET(IAVF_RXD_LEGACY_PPRS_M, qw1);
+	csum_bits.l3l4p = FIELD_GET(IAVF_RXD_LEGACY_L3L4P_M, qw1);
+	csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_LEGACY_IPV6EXADD_M, qw1);
+
+	return csum_bits;
+}
+
+/**
+ * iavf_flex_rx_csum - Indicate in skb if hw indicated a good checksum
+ * @vsi: the VSI we care about
+ * @qw1: quad word 1
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ *
+ * Return: decoded checksum bits.
+ **/
+static struct libeth_rx_csum
+iavf_flex_rx_csum(const struct iavf_vsi *vsi, u64 qw1,
+		  const struct libeth_rx_pt decoded_pt)
+{
+	struct libeth_rx_csum csum_bits = {};
+
+	if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt))
+		return csum_bits;
+
+	csum_bits.ipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_IPE_M, qw1);
+	csum_bits.eipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EIPE_M, qw1);
+	csum_bits.l4e = FIELD_GET(IAVF_RXD_FLEX_XSUM_L4E_M, qw1);
+	csum_bits.eudpe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EUDPE_M, qw1);
+	csum_bits.l3l4p = FIELD_GET(IAVF_RXD_FLEX_L3L4P_M, qw1);
+	csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_FLEX_IPV6EXADD_M, qw1);
+	csum_bits.nat = FIELD_GET(IAVF_RXD_FLEX_NAT_M, qw1);
+
+	return csum_bits;
+}
+
+/**
+ * iavf_legacy_rx_hash - set the hash value in the skb
+ * @ring: descriptor ring
+ * @qw0: quad word 0
+ * @qw1: quad word 1
+ * @skb: skb currently being received and modified
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ **/
+static void iavf_legacy_rx_hash(const struct iavf_ring *ring, __le64 qw0,
+				__le64 qw1, struct sk_buff *skb,
+				const struct libeth_rx_pt decoded_pt)
+{
+	const __le64 rss_mask = cpu_to_le64(IAVF_RXD_LEGACY_FLTSTAT_M);
+	u32 hash;
+
+	if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt))
+		return;
+
+	if ((qw1 & rss_mask) == rss_mask) {
+		hash = le64_get_bits(qw0, IAVF_RXD_LEGACY_RSS_M);
+		libeth_rx_pt_set_hash(skb, hash, decoded_pt);
+	}
+}
+
+/**
+ * iavf_flex_rx_hash - set the hash value in the skb
  * @ring: descriptor ring
- * @rx_desc: specific descriptor
+ * @qw1: quad word 1
  * @skb: skb currently being received and modified
- * @rx_ptype: Rx packet type
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
  **/
-static void iavf_rx_hash(struct iavf_ring *ring,
-			 union iavf_rx_desc *rx_desc,
-			 struct sk_buff *skb,
-			 u8 rx_ptype)
+static void iavf_flex_rx_hash(const struct iavf_ring *ring, __le64 qw1,
+			      struct sk_buff *skb,
+			      const struct libeth_rx_pt decoded_pt)
 {
-	struct libeth_rx_pt decoded;
+	bool rss_valid;
 	u32 hash;
-	const __le64 rss_mask =
-		cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH <<
-			    IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT);
 
-	decoded = libie_rx_pt_parse(rx_ptype);
-	if (!libeth_rx_pt_has_hash(ring->netdev, decoded))
+	if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt))
 		return;
 
-	if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) {
-		hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
-		libeth_rx_pt_set_hash(skb, hash, decoded);
+	rss_valid = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_VALID_M);
+	if (rss_valid) {
+		hash = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_HASH_M);
+		libeth_rx_pt_set_hash(skb, hash, decoded_pt);
 	}
 }
 
 /**
+ * iavf_flex_rx_tstamp - Capture Rx timestamp from the descriptor
+ * @rx_ring: descriptor ring
+ * @qw2: quad word 2 of descriptor
+ * @qw3: quad word 3 of descriptor
+ * @skb: skb currently being received
+ *
+ * Read the Rx timestamp value from the descriptor and pass it to the stack.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ */
+static void iavf_flex_rx_tstamp(const struct iavf_ring *rx_ring, __le64 qw2,
+				__le64 qw3, struct sk_buff *skb)
+{
+	u32 tstamp;
+	u64 ns;
+
+	/* Skip processing if timestamps aren't enabled */
+	if (!(rx_ring->flags & IAVF_TXRX_FLAGS_HW_TSTAMP))
+		return;
+
+	/* Check if this Rx descriptor has a valid timestamp */
+	if (!le64_get_bits(qw2, IAVF_PTP_40B_TSTAMP_VALID))
+		return;
+
+	/* the ts_low field only contains the valid bit and sub-nanosecond
+	 * precision, so we don't need to extract it.
+	 */
+	tstamp = le64_get_bits(qw3, IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M);
+
+	ns = iavf_ptp_extend_32b_timestamp(rx_ring->ptp->cached_phc_time,
+					   tstamp);
+
+	*skb_hwtstamps(skb) = (struct skb_shared_hwtstamps) {
+		.hwtstamp = ns_to_ktime(ns),
+	};
+}
+
+/**
  * iavf_process_skb_fields - Populate skb header fields from Rx descriptor
  * @rx_ring: rx descriptor ring packet is being transacted on
  * @rx_desc: pointer to the EOP Rx descriptor
  * @skb: pointer to current skb being populated
- * @rx_ptype: the packet type decoded by hardware
+ * @ptype: the packet type decoded by hardware
+ * @flex: is the descriptor flex or legacy
  *
  * This function checks the ring, descriptor, and packet information in
  * order to populate the hash, checksum, VLAN, protocol, and
  * other fields within the skb.
  **/
-static void
-iavf_process_skb_fields(struct iavf_ring *rx_ring,
-			union iavf_rx_desc *rx_desc, struct sk_buff *skb,
-			u8 rx_ptype)
+static void iavf_process_skb_fields(const struct iavf_ring *rx_ring,
+				    const struct iavf_rx_desc *rx_desc,
+				    struct sk_buff *skb, u32 ptype,
+				    bool flex)
 {
-	iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
-
-	iavf_rx_checksum(rx_ring->vsi, skb, rx_desc);
+	struct libeth_rx_csum csum_bits;
+	struct libeth_rx_pt decoded_pt;
+	__le64 qw0 = rx_desc->qw0;
+	__le64 qw1 = rx_desc->qw1;
+	__le64 qw2 = rx_desc->qw2;
+	__le64 qw3 = rx_desc->qw3;
+
+	decoded_pt = libie_rx_pt_parse(ptype);
+
+	if (flex) {
+		iavf_flex_rx_hash(rx_ring, qw1, skb, decoded_pt);
+		iavf_flex_rx_tstamp(rx_ring, qw2, qw3, skb);
+		csum_bits = iavf_flex_rx_csum(rx_ring->vsi, le64_to_cpu(qw1),
+					      decoded_pt);
+	} else {
+		iavf_legacy_rx_hash(rx_ring, qw0, qw1, skb, decoded_pt);
+		csum_bits = iavf_legacy_rx_csum(rx_ring->vsi, le64_to_cpu(qw1),
+						decoded_pt);
+	}
+	iavf_rx_csum(rx_ring->vsi, skb, decoded_pt, csum_bits);
 
 	skb_record_rx_queue(skb, rx_ring->queue_index);
 
@@ -1050,10 +1197,11 @@ static void iavf_add_rx_frag(struct sk_buff *skb,
 			     const struct libeth_fqe *rx_buffer,
 			     unsigned int size)
 {
-	u32 hr = rx_buffer->page->pp->p.offset;
+	u32 hr = netmem_get_pp(rx_buffer->netmem)->p.offset;
 
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
-			rx_buffer->offset + hr, size, rx_buffer->truesize);
+	skb_add_rx_frag_netmem(skb, skb_shinfo(skb)->nr_frags,
+			       rx_buffer->netmem, rx_buffer->offset + hr,
+			       size, rx_buffer->truesize);
 }
 
 /**
@@ -1067,12 +1215,13 @@ static void iavf_add_rx_frag(struct sk_buff *skb,
 static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer,
 				      unsigned int size)
 {
-	u32 hr = rx_buffer->page->pp->p.offset;
+	struct page *buf_page = __netmem_to_page(rx_buffer->netmem);
+	u32 hr = pp_page_to_nmdesc(buf_page)->pp->p.offset;
 	struct sk_buff *skb;
 	void *va;
 
 	/* prefetch first cache line of first page */
-	va = page_address(rx_buffer->page) + rx_buffer->offset;
+	va = page_address(buf_page) + rx_buffer->offset;
 	net_prefetch(va + hr);
 
 	/* build an skb around the page buffer */
@@ -1092,8 +1241,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer,
 /**
  * iavf_is_non_eop - process handling of non-EOP buffers
  * @rx_ring: Rx ring being processed
- * @rx_desc: Rx descriptor for current buffer
- * @skb: Current socket buffer containing buffer in progress
+ * @fields: Rx descriptor extracted fields
  *
  * This function updates next to clean.  If the buffer is an EOP buffer
  * this function exits returning false, otherwise it will place the
@@ -1101,8 +1249,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer,
  * that this is in fact a non-EOP buffer.
  **/
 static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
-			    union iavf_rx_desc *rx_desc,
-			    struct sk_buff *skb)
+			    struct libeth_rqe_info fields)
 {
 	u32 ntc = rx_ring->next_to_clean + 1;
 
@@ -1113,8 +1260,7 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
 	prefetch(IAVF_RX_DESC(rx_ring, ntc));
 
 	/* if we are the last buffer then there is nothing else to do */
-#define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT)
-	if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF)))
+	if (likely(fields.eop))
 		return false;
 
 	rx_ring->rx_stats.non_eop_descs++;
@@ -1123,6 +1269,109 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
 }
 
 /**
+ * iavf_extract_legacy_rx_fields - Extract fields from the Rx descriptor
+ * @rx_ring: rx descriptor ring
+ * @rx_desc: the descriptor to process
+ *
+ * Decode the Rx descriptor and extract relevant information including the
+ * size, VLAN tag, Rx packet type, end of packet field and RXE field value.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ *
+ * Return: fields extracted from the Rx descriptor.
+ */
+static struct libeth_rqe_info
+iavf_extract_legacy_rx_fields(const struct iavf_ring *rx_ring,
+			      const struct iavf_rx_desc *rx_desc)
+{
+	u64 qw0 = le64_to_cpu(rx_desc->qw0);
+	u64 qw1 = le64_to_cpu(rx_desc->qw1);
+	u64 qw2 = le64_to_cpu(rx_desc->qw2);
+	struct libeth_rqe_info fields;
+	bool l2tag1p, l2tag2p;
+
+	fields.eop = FIELD_GET(IAVF_RXD_LEGACY_EOP_M, qw1);
+	fields.len = FIELD_GET(IAVF_RXD_LEGACY_LENGTH_M, qw1);
+
+	if (!fields.eop)
+		return fields;
+
+	fields.rxe = FIELD_GET(IAVF_RXD_LEGACY_RXE_M, qw1);
+	fields.ptype = FIELD_GET(IAVF_RXD_LEGACY_PTYPE_M, qw1);
+	fields.vlan = 0;
+
+	if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) {
+		l2tag1p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1P_M, qw1);
+		if (l2tag1p)
+			fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1_M, qw0);
+	} else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) {
+		l2tag2p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2P_M, qw2);
+		if (l2tag2p)
+			fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2_M, qw2);
+	}
+
+	return fields;
+}
+
+/**
+ * iavf_extract_flex_rx_fields - Extract fields from the Rx descriptor
+ * @rx_ring: rx descriptor ring
+ * @rx_desc: the descriptor to process
+ *
+ * Decode the Rx descriptor and extract relevant information including the
+ * size, VLAN tag, Rx packet type, end of packet field and RXE field value.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ *
+ * Return: fields extracted from the Rx descriptor.
+ */
+static struct libeth_rqe_info
+iavf_extract_flex_rx_fields(const struct iavf_ring *rx_ring,
+			    const struct iavf_rx_desc *rx_desc)
+{
+	struct libeth_rqe_info fields = {};
+	u64 qw0 = le64_to_cpu(rx_desc->qw0);
+	u64 qw1 = le64_to_cpu(rx_desc->qw1);
+	u64 qw2 = le64_to_cpu(rx_desc->qw2);
+	bool l2tag1p, l2tag2p;
+
+	fields.eop = FIELD_GET(IAVF_RXD_FLEX_EOP_M, qw1);
+	fields.len = FIELD_GET(IAVF_RXD_FLEX_PKT_LEN_M, qw0);
+
+	if (!fields.eop)
+		return fields;
+
+	fields.rxe = FIELD_GET(IAVF_RXD_FLEX_RXE_M, qw1);
+	fields.ptype = FIELD_GET(IAVF_RXD_FLEX_PTYPE_M, qw0);
+	fields.vlan = 0;
+
+	if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) {
+		l2tag1p = FIELD_GET(IAVF_RXD_FLEX_L2TAG1P_M, qw1);
+		if (l2tag1p)
+			fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG1_M, qw1);
+	} else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) {
+		l2tag2p = FIELD_GET(IAVF_RXD_FLEX_L2TAG2P_M, qw2);
+		if (l2tag2p)
+			fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG2_2_M, qw2);
+	}
+
+	return fields;
+}
+
+static struct libeth_rqe_info
+iavf_extract_rx_fields(const struct iavf_ring *rx_ring,
+		       const struct iavf_rx_desc *rx_desc,
+		       bool flex)
+{
+	if (flex)
+		return iavf_extract_flex_rx_fields(rx_ring, rx_desc);
+	else
+		return iavf_extract_legacy_rx_fields(rx_ring, rx_desc);
+}
+
+/**
  * iavf_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @rx_ring: rx descriptor ring to transact packets on
  * @budget: Total limit on number of packets to process
@@ -1136,18 +1385,17 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
  **/
 static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 {
+	bool flex = rx_ring->rxdid == VIRTCHNL_RXDID_2_FLEX_SQ_NIC;
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	struct sk_buff *skb = rx_ring->skb;
 	u16 cleaned_count = IAVF_DESC_UNUSED(rx_ring);
 	bool failure = false;
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
+		struct libeth_rqe_info fields;
 		struct libeth_fqe *rx_buffer;
-		union iavf_rx_desc *rx_desc;
-		unsigned int size;
-		u16 vlan_tag = 0;
-		u8 rx_ptype;
-		u64 qword;
+		struct iavf_rx_desc *rx_desc;
+		u64 qw1;
 
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IAVF_RX_BUFFER_WRITE) {
@@ -1158,35 +1406,32 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 
 		rx_desc = IAVF_RX_DESC(rx_ring, rx_ring->next_to_clean);
 
-		/* status_error_len will always be zero for unused descriptors
-		 * because it's cleared in cleanup, and overlaps with hdr_addr
-		 * which is always zero because packet split isn't used, if the
-		 * hardware wrote DD then the length will be non-zero
-		 */
-		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-
 		/* This memory barrier is needed to keep us from reading
 		 * any other fields out of the rx_desc until we have
 		 * verified the descriptor has been written back.
 		 */
 		dma_rmb();
-#define IAVF_RXD_DD BIT(IAVF_RX_DESC_STATUS_DD_SHIFT)
-		if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD))
+
+		qw1 = le64_to_cpu(rx_desc->qw1);
+		/* If DD field (descriptor done) is unset then other fields are
+		 * not valid
+		 */
+		if (!iavf_is_descriptor_done(qw1, flex))
 			break;
 
-		size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword);
+		fields = iavf_extract_rx_fields(rx_ring, rx_desc, flex);
 
 		iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb);
 
 		rx_buffer = &rx_ring->rx_fqes[rx_ring->next_to_clean];
-		if (!libeth_rx_sync_for_cpu(rx_buffer, size))
+		if (!libeth_rx_sync_for_cpu(rx_buffer, fields.len))
 			goto skip_data;
 
 		/* retrieve a buffer from the ring */
 		if (skb)
-			iavf_add_rx_frag(skb, rx_buffer, size);
+			iavf_add_rx_frag(skb, rx_buffer, fields.len);
 		else
-			skb = iavf_build_skb(rx_buffer, size);
+			skb = iavf_build_skb(rx_buffer, fields.len);
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
@@ -1197,15 +1442,14 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 skip_data:
 		cleaned_count++;
 
-		if (iavf_is_non_eop(rx_ring, rx_desc, skb) || unlikely(!skb))
+		if (iavf_is_non_eop(rx_ring, fields) || unlikely(!skb))
 			continue;
 
-		/* ERR_MASK will only have valid bits if EOP set, and
-		 * what we are doing here is actually checking
-		 * IAVF_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in
-		 * the error field
+		/* RXE field in descriptor is an indication of the MAC errors
+		 * (like CRC, alignment, oversize etc). If it is set then iavf
+		 * should finish.
 		 */
-		if (unlikely(iavf_test_staterr(rx_desc, BIT(IAVF_RXD_QW1_ERROR_SHIFT)))) {
+		if (unlikely(fields.rxe)) {
 			dev_kfree_skb_any(skb);
 			skb = NULL;
 			continue;
@@ -1219,22 +1463,11 @@ skip_data:
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 
-		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-		rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
-
 		/* populate checksum, VLAN, and protocol */
-		iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
-
-		if (qword & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT) &&
-		    rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1)
-			vlan_tag = le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1);
-		if (rx_desc->wb.qword2.ext_status &
-		    cpu_to_le16(BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)) &&
-		    rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2)
-			vlan_tag = le16_to_cpu(rx_desc->wb.qword2.l2tag2_2);
+		iavf_process_skb_fields(rx_ring, rx_desc, skb, fields.ptype, flex);
 
 		iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
-		iavf_receive_skb(rx_ring, skb, vlan_tag);
+		iavf_receive_skb(rx_ring, skb, fields.vlan);
 		skb = NULL;
 
 		/* update budget accounting */
@@ -1417,7 +1650,8 @@ int iavf_napi_poll(struct napi_struct *napi, int budget)
 		 * continue to poll, otherwise we must stop polling so the
 		 * interrupt can move to the correct cpu.
 		 */
-		if (!cpumask_test_cpu(cpu_id, &q_vector->affinity_mask)) {
+		if (!cpumask_test_cpu(cpu_id,
+				      &q_vector->napi.config->affinity_mask)) {
 			/* Tell napi that we are done polling */
 			napi_complete_done(napi, work_done);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index f97c702c0802..df49b0b1d54a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -4,6 +4,8 @@
 #ifndef _IAVF_TXRX_H_
 #define _IAVF_TXRX_H_
 
+#include <linux/net/intel/libie/pctype.h>
+
 /* Interrupt Throttling and Rate Limiting Goodies */
 #define IAVF_DEFAULT_IRQ_WORK      256
 
@@ -59,45 +61,26 @@ enum iavf_dyn_idx_t {
 #define IAVF_PE_ITR    IAVF_IDX_ITR2
 
 /* Supported RSS offloads */
-#define IAVF_DEFAULT_RSS_HENA ( \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_UDP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_FRAG_IPV4) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_UDP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_TCP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_SCTP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_FRAG_IPV6) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_L2_PAYLOAD))
-
-#define IAVF_DEFAULT_RSS_HENA_EXPANDED (IAVF_DEFAULT_RSS_HENA | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
-
-#define iavf_rx_desc iavf_32byte_rx_desc
-
-/**
- * iavf_test_staterr - tests bits in Rx descriptor status and error fields
- * @rx_desc: pointer to receive descriptor (in le64 format)
- * @stat_err_bits: value to mask
- *
- * This function does some fast chicanery in order to return the
- * value of the mask which is really only used for boolean tests.
- * The status_error_len doesn't need to be shifted because it begins
- * at offset zero.
- */
-static inline bool iavf_test_staterr(union iavf_rx_desc *rx_desc,
-				     const u64 stat_err_bits)
-{
-	return !!(rx_desc->wb.qword1.status_error_len &
-		  cpu_to_le64(stat_err_bits));
-}
+#define IAVF_DEFAULT_RSS_HASHCFG ( \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV4) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV6) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_L2_PAYLOAD))
+
+#define IAVF_DEFAULT_RSS_HASHCFG_EXPANDED (IAVF_DEFAULT_RSS_HASHCFG | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
 #define IAVF_RX_INCREMENT(r, i) \
@@ -262,6 +245,8 @@ struct iavf_ring {
 	u16 next_to_use;
 	u16 next_to_clean;
 
+	u16 rxdid;		/* Rx descriptor format */
+
 	u16 flags;
 #define IAVF_TXR_FLAGS_WB_ON_ITR		BIT(0)
 #define IAVF_TXR_FLAGS_ARM_WB			BIT(1)
@@ -269,6 +254,7 @@ struct iavf_ring {
 #define IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1	BIT(3)
 #define IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2	BIT(4)
 #define IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2	BIT(5)
+#define IAVF_TXRX_FLAGS_HW_TSTAMP		BIT(6)
 
 	/* stats structs */
 	struct iavf_queue_stats	stats;
@@ -295,6 +281,8 @@ struct iavf_ring {
 					 * for this ring.
 					 */
 
+	struct iavf_ptp *ptp;
+
 	u32 rx_buf_len;
 	struct net_shaper q_shaper;
 	bool q_shaper_update;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h
index f6b09e57abce..1d8cf29cb65a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_type.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_type.h
@@ -19,7 +19,7 @@
 
 /* forward declaration */
 struct iavf_hw;
-typedef void (*IAVF_ADMINQ_CALLBACK)(struct iavf_hw *, struct iavf_aq_desc *);
+typedef void (*IAVF_ADMINQ_CALLBACK)(struct iavf_hw *, struct libie_aq_desc *);
 
 /* Data type manipulation macros. */
 
@@ -178,110 +178,116 @@ struct iavf_hw {
 	char err_str[16];
 };
 
-/* RX Descriptors */
-union iavf_16byte_rx_desc {
-	struct {
-		__le64 pkt_addr; /* Packet buffer address */
-		__le64 hdr_addr; /* Header buffer address */
-	} read;
-	struct {
-		struct {
-			struct {
-				union {
-					__le16 mirroring_status;
-					__le16 fcoe_ctx_id;
-				} mirr_fcoe;
-				__le16 l2tag1;
-			} lo_dword;
-			union {
-				__le32 rss; /* RSS Hash */
-				__le32 fd_id; /* Flow director filter id */
-				__le32 fcoe_param; /* FCoE DDP Context id */
-			} hi_dword;
-		} qword0;
-		struct {
-			/* ext status/error/pktype/length */
-			__le64 status_error_len;
-		} qword1;
-	} wb;  /* writeback */
-};
-
-union iavf_32byte_rx_desc {
-	struct {
-		__le64  pkt_addr; /* Packet buffer address */
-		__le64  hdr_addr; /* Header buffer address */
-			/* bit 0 of hdr_buffer_addr is DD bit */
-		__le64  rsvd1;
-		__le64  rsvd2;
-	} read;
-	struct {
-		struct {
-			struct {
-				union {
-					__le16 mirroring_status;
-					__le16 fcoe_ctx_id;
-				} mirr_fcoe;
-				__le16 l2tag1;
-			} lo_dword;
-			union {
-				__le32 rss; /* RSS Hash */
-				__le32 fcoe_param; /* FCoE DDP Context id */
-				/* Flow director filter id in case of
-				 * Programming status desc WB
-				 */
-				__le32 fd_id;
-			} hi_dword;
-		} qword0;
-		struct {
-			/* status/error/pktype/length */
-			__le64 status_error_len;
-		} qword1;
-		struct {
-			__le16 ext_status; /* extended status */
-			__le16 rsvd;
-			__le16 l2tag2_1;
-			__le16 l2tag2_2;
-		} qword2;
-		struct {
-			union {
-				__le32 flex_bytes_lo;
-				__le32 pe_status;
-			} lo_dword;
-			union {
-				__le32 flex_bytes_hi;
-				__le32 fd_id;
-			} hi_dword;
-		} qword3;
-	} wb;  /* writeback */
-};
-
-enum iavf_rx_desc_status_bits {
-	/* Note: These are predefined bit offsets */
-	IAVF_RX_DESC_STATUS_DD_SHIFT		= 0,
-	IAVF_RX_DESC_STATUS_EOF_SHIFT		= 1,
-	IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT	= 2,
-	IAVF_RX_DESC_STATUS_L3L4P_SHIFT		= 3,
-	IAVF_RX_DESC_STATUS_CRCP_SHIFT		= 4,
-	IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT	= 5, /* 2 BITS */
-	IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT	= 7,
-	/* Note: Bit 8 is reserved in X710 and XL710 */
-	IAVF_RX_DESC_STATUS_EXT_UDP_0_SHIFT	= 8,
-	IAVF_RX_DESC_STATUS_UMBCAST_SHIFT	= 9, /* 2 BITS */
-	IAVF_RX_DESC_STATUS_FLM_SHIFT		= 11,
-	IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT	= 12, /* 2 BITS */
-	IAVF_RX_DESC_STATUS_LPBK_SHIFT		= 14,
-	IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT	= 15,
-	IAVF_RX_DESC_STATUS_RESERVED_SHIFT	= 16, /* 2 BITS */
-	/* Note: For non-tunnel packets INT_UDP_0 is the right status for
-	 * UDP header
-	 */
-	IAVF_RX_DESC_STATUS_INT_UDP_0_SHIFT	= 18,
-	IAVF_RX_DESC_STATUS_LAST /* this entry must be last!!! */
-};
-
-#define IAVF_RXD_QW1_STATUS_SHIFT	0
-#define IAVF_RXD_QW1_STATUS_MASK	((BIT(IAVF_RX_DESC_STATUS_LAST) - 1) \
-					 << IAVF_RXD_QW1_STATUS_SHIFT)
+/**
+ * struct iavf_rx_desc - Receive descriptor (both legacy and flexible)
+ * @qw0: quad word 0 fields:
+ *	 Legacy: Descriptor Type; Mirror ID; L2TAG1P (S-TAG); Filter Status
+ *	 Flex: Descriptor Type; Mirror ID; UMBCAST; Packet Type; Flexible Flags
+ *	       Section 0; Packet Length; Header Length; Split Header Flag;
+ *	       Flexible Flags section 1 / Extended Status
+ * @qw1: quad word 1 fields:
+ *	 Legacy: Status Field; Error Field; Packet Type; Packet Length (packet,
+ *		 header, Split Header Flag)
+ *	 Flex: Status / Error 0 Field; L2TAG1P (S-TAG); Flexible Metadata
+ *	       Container #0; Flexible Metadata Container #1
+ * @qw2: quad word 2 fields:
+ *	 Legacy: Extended Status; 1st L2TAG2P (C-TAG); 2nd L2TAG2P (C-TAG)
+ *	 Flex: Status / Error 1 Field; Flexible Flags section 2; Timestamp Low;
+ *	       1st L2TAG2 (C-TAG); 2nd L2TAG2 (C-TAG)
+ * @qw3: quad word 3 fields:
+ *	 Legacy: FD Filter ID / Flexible Bytes
+ *	 Flex: Flexible Metadata Container #2; Flexible Metadata Container #3;
+ *	       Flexible Metadata Container #4 / Timestamp High 0; Flexible
+ *	       Metadata Container #5 / Timestamp High 1;
+ */
+struct iavf_rx_desc {
+	aligned_le64 qw0;
+/* The hash signature (RSS) */
+#define IAVF_RXD_LEGACY_RSS_M			GENMASK_ULL(63, 32)
+/* Stripped C-TAG VLAN from the receive packet */
+#define IAVF_RXD_LEGACY_L2TAG1_M		GENMASK_ULL(33, 16)
+/* Packet type */
+#define IAVF_RXD_FLEX_PTYPE_M			GENMASK_ULL(25, 16)
+/* Packet length */
+#define IAVF_RXD_FLEX_PKT_LEN_M			GENMASK_ULL(45, 32)
+
+	aligned_le64 qw1;
+/* Descriptor done indication flag. */
+#define IAVF_RXD_LEGACY_DD_M			BIT(0)
+/* End of packet. Set to 1 if this descriptor is the last one of the packet */
+#define IAVF_RXD_LEGACY_EOP_M			BIT(1)
+/* L2 TAG 1 presence indication */
+#define IAVF_RXD_LEGACY_L2TAG1P_M		BIT(2)
+/* Detectable L3 and L4 integrity check is processed by the HW */
+#define IAVF_RXD_LEGACY_L3L4P_M			BIT(3)
+/* Set when an IPv6 packet contains a Destination Options Header or a Routing
+ * Header.
+ */
+#define IAVF_RXD_LEGACY_IPV6EXADD_M		BIT(15)
+/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */
+#define IAVF_RXD_LEGACY_RXE_M			BIT(19)
+/* Checksum reports:
+ * - IPE: IP checksum error
+ * - L4E: L4 integrity error
+ * - EIPE: External IP header (tunneled packets)
+ */
+#define IAVF_RXD_LEGACY_IPE_M			BIT(22)
+#define IAVF_RXD_LEGACY_L4E_M			BIT(23)
+#define IAVF_RXD_LEGACY_EIPE_M			BIT(24)
+/* Set for packets that skip checksum calculation in pre-parser */
+#define IAVF_RXD_LEGACY_PPRS_M			BIT(26)
+/* Indicates the content in the Filter Status field */
+#define IAVF_RXD_LEGACY_FLTSTAT_M		GENMASK_ULL(13, 12)
+/* Packet type */
+#define IAVF_RXD_LEGACY_PTYPE_M			GENMASK_ULL(37, 30)
+/* Packet length */
+#define IAVF_RXD_LEGACY_LENGTH_M		GENMASK_ULL(51, 38)
+/* Descriptor done indication flag */
+#define IAVF_RXD_FLEX_DD_M			BIT(0)
+/* End of packet. Set to 1 if this descriptor is the last one of the packet */
+#define IAVF_RXD_FLEX_EOP_M			BIT(1)
+/* Detectable L3 and L4 integrity check is processed by the HW */
+#define IAVF_RXD_FLEX_L3L4P_M			BIT(3)
+/* Checksum reports:
+ * - IPE: IP checksum error
+ * - L4E: L4 integrity error
+ * - EIPE: External IP header (tunneled packets)
+ * - EUDPE: External UDP checksum error (tunneled packets)
+ */
+#define IAVF_RXD_FLEX_XSUM_IPE_M		BIT(4)
+#define IAVF_RXD_FLEX_XSUM_L4E_M		BIT(5)
+#define IAVF_RXD_FLEX_XSUM_EIPE_M		BIT(6)
+#define IAVF_RXD_FLEX_XSUM_EUDPE_M		BIT(7)
+/* Set when an IPv6 packet contains a Destination Options Header or a Routing
+ * Header.
+ */
+#define IAVF_RXD_FLEX_IPV6EXADD_M		BIT(9)
+/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */
+#define IAVF_RXD_FLEX_RXE_M			BIT(10)
+/* Indicates that the RSS/HASH result is valid */
+#define IAVF_RXD_FLEX_RSS_VALID_M		BIT(12)
+/* L2 TAG 1 presence indication */
+#define IAVF_RXD_FLEX_L2TAG1P_M			BIT(13)
+/* Stripped L2 Tag from the receive packet */
+#define IAVF_RXD_FLEX_L2TAG1_M			GENMASK_ULL(31, 16)
+/* The hash signature (RSS) */
+#define IAVF_RXD_FLEX_RSS_HASH_M		GENMASK_ULL(63, 32)
+
+	aligned_le64 qw2;
+/* L2 Tag 2 Presence */
+#define IAVF_RXD_LEGACY_L2TAG2P_M		BIT(0)
+/* Stripped S-TAG VLAN from the receive packet */
+#define IAVF_RXD_LEGACY_L2TAG2_M		GENMASK_ULL(63, 32)
+/* Stripped S-TAG VLAN from the receive packet */
+#define IAVF_RXD_FLEX_L2TAG2_2_M		GENMASK_ULL(63, 48)
+/* The packet is a UDP tunneled packet */
+#define IAVF_RXD_FLEX_NAT_M			BIT(4)
+/* L2 Tag 2 Presence */
+#define IAVF_RXD_FLEX_L2TAG2P_M			BIT(11)
+	aligned_le64 qw3;
+#define IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M		GENMASK_ULL(63, 32)
+} __aligned(4 * sizeof(__le64));
+static_assert(sizeof(struct iavf_rx_desc) == 32);
 
 #define IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT
 #define IAVF_RXD_QW1_STATUS_TSYNINDX_MASK  (0x3UL << \
@@ -298,22 +304,6 @@ enum iavf_rx_desc_fltstat_values {
 	IAVF_RX_DESC_FLTSTAT_RSS_HASH	= 3,
 };
 
-#define IAVF_RXD_QW1_ERROR_SHIFT	19
-#define IAVF_RXD_QW1_ERROR_MASK		(0xFFUL << IAVF_RXD_QW1_ERROR_SHIFT)
-
-enum iavf_rx_desc_error_bits {
-	/* Note: These are predefined bit offsets */
-	IAVF_RX_DESC_ERROR_RXE_SHIFT		= 0,
-	IAVF_RX_DESC_ERROR_RECIPE_SHIFT		= 1,
-	IAVF_RX_DESC_ERROR_HBO_SHIFT		= 2,
-	IAVF_RX_DESC_ERROR_L3L4E_SHIFT		= 3, /* 3 BITS */
-	IAVF_RX_DESC_ERROR_IPE_SHIFT		= 3,
-	IAVF_RX_DESC_ERROR_L4E_SHIFT		= 4,
-	IAVF_RX_DESC_ERROR_EIPE_SHIFT		= 5,
-	IAVF_RX_DESC_ERROR_OVERSIZE_SHIFT	= 6,
-	IAVF_RX_DESC_ERROR_PPRS_SHIFT		= 7
-};
-
 enum iavf_rx_desc_error_l3l4e_fcoe_masks {
 	IAVF_RX_DESC_ERROR_L3L4E_NONE		= 0,
 	IAVF_RX_DESC_ERROR_L3L4E_PROT		= 1,
@@ -322,13 +312,6 @@ enum iavf_rx_desc_error_l3l4e_fcoe_masks {
 	IAVF_RX_DESC_ERROR_L3L4E_DMAC_WARN	= 4
 };
 
-#define IAVF_RXD_QW1_PTYPE_SHIFT	30
-#define IAVF_RXD_QW1_PTYPE_MASK		(0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT)
-
-#define IAVF_RXD_QW1_LENGTH_PBUF_SHIFT	38
-#define IAVF_RXD_QW1_LENGTH_PBUF_MASK	(0x3FFFULL << \
-					 IAVF_RXD_QW1_LENGTH_PBUF_SHIFT)
-
 #define IAVF_RXD_QW1_LENGTH_HBUF_SHIFT	52
 #define IAVF_RXD_QW1_LENGTH_HBUF_MASK	(0x7FFULL << \
 					 IAVF_RXD_QW1_LENGTH_HBUF_SHIFT)
@@ -347,6 +330,8 @@ enum iavf_rx_desc_ext_status_bits {
 	IAVF_RX_DESC_EXT_STATUS_PELONGB_SHIFT	= 11,
 };
 
+#define IAVF_RX_DESC_EXT_STATUS_L2TAG2P_M	BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)
+
 enum iavf_rx_desc_pe_status_bits {
 	/* Note: These are predefined bit offsets */
 	IAVF_RX_DESC_PE_STATUS_QPID_SHIFT	= 0, /* 18 BITS */
@@ -478,38 +463,6 @@ enum iavf_tx_ctx_desc_cmd_bits {
 	IAVF_TX_CTX_DESC_SWPE		= 0x40
 };
 
-/* Packet Classifier Types for filters */
-enum iavf_filter_pctype {
-	/* Note: Values 0-28 are reserved for future use.
-	 * Value 29, 30, 32 are not supported on XL710 and X710.
-	 */
-	IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP	= 29,
-	IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP	= 30,
-	IAVF_FILTER_PCTYPE_NONF_IPV4_UDP		= 31,
-	IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK	= 32,
-	IAVF_FILTER_PCTYPE_NONF_IPV4_TCP		= 33,
-	IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP		= 34,
-	IAVF_FILTER_PCTYPE_NONF_IPV4_OTHER		= 35,
-	IAVF_FILTER_PCTYPE_FRAG_IPV4			= 36,
-	/* Note: Values 37-38 are reserved for future use.
-	 * Value 39, 40, 42 are not supported on XL710 and X710.
-	 */
-	IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP	= 39,
-	IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP	= 40,
-	IAVF_FILTER_PCTYPE_NONF_IPV6_UDP		= 41,
-	IAVF_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK	= 42,
-	IAVF_FILTER_PCTYPE_NONF_IPV6_TCP		= 43,
-	IAVF_FILTER_PCTYPE_NONF_IPV6_SCTP		= 44,
-	IAVF_FILTER_PCTYPE_NONF_IPV6_OTHER		= 45,
-	IAVF_FILTER_PCTYPE_FRAG_IPV6			= 46,
-	/* Note: Value 47 is reserved for future use */
-	IAVF_FILTER_PCTYPE_FCOE_OX			= 48,
-	IAVF_FILTER_PCTYPE_FCOE_RX			= 49,
-	IAVF_FILTER_PCTYPE_FCOE_OTHER			= 50,
-	/* Note: Values 51-62 are reserved for future use */
-	IAVF_FILTER_PCTYPE_L2_PAYLOAD			= 63,
-};
-
 #define IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT	30
 #define IAVF_TXD_CTX_QW1_TSO_LEN_MASK	(0x3FFFFULL << \
 					 IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT)
diff --git a/drivers/net/ethernet/intel/iavf/iavf_types.h b/drivers/net/ethernet/intel/iavf/iavf_types.h
new file mode 100644
index 000000000000..a095855122bf
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_types.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IAVF_TYPES_H_
+#define _IAVF_TYPES_H_
+
+#include "iavf_types.h"
+
+#include <linux/avf/virtchnl.h>
+#include <linux/ptp_clock_kernel.h>
+
+/* structure used to queue PTP commands for processing */
+struct iavf_ptp_aq_cmd {
+	struct list_head list;
+	enum virtchnl_ops v_opcode:16;
+	u16 msglen;
+	u8 msg[] __counted_by(msglen);
+};
+
+struct iavf_ptp {
+	wait_queue_head_t phc_time_waitqueue;
+	struct virtchnl_ptp_caps hw_caps;
+	struct ptp_clock_info info;
+	struct ptp_clock *clock;
+	struct list_head aq_cmds;
+	u64 cached_phc_time;
+	unsigned long cached_phc_updated;
+	/* Lock protecting access to the AQ command list */
+	struct mutex aq_cmd_lock;
+	struct kernel_hwtstamp_config hwtstamp_config;
+	bool phc_time_ready:1;
+};
+
+#endif /* _IAVF_TYPES_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 15d388b431c5..88156082a41d 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -4,6 +4,7 @@
 #include <linux/net/intel/libie/rx.h>
 
 #include "iavf.h"
+#include "iavf_ptp.h"
 #include "iavf_prototype.h"
 
 /**
@@ -28,7 +29,7 @@ static int iavf_send_pf_msg(struct iavf_adapter *adapter,
 	if (status)
 		dev_dbg(&adapter->pdev->dev, "Unable to send opcode %d to PF, status %s, aq_err %s\n",
 			op, iavf_stat_str(hw, status),
-			iavf_aq_str(hw, hw->aq.asq_last_status));
+			libie_aq_str(hw->aq.asq_last_status));
 	return iavf_status_to_errno(status);
 }
 
@@ -78,6 +79,23 @@ iavf_poll_virtchnl_msg(struct iavf_hw *hw, struct iavf_arq_event_info *event,
 			return iavf_status_to_errno(status);
 		received_op =
 		    (enum virtchnl_ops)le32_to_cpu(event->desc.cookie_high);
+
+		if (received_op == VIRTCHNL_OP_EVENT) {
+			struct iavf_adapter *adapter = hw->back;
+			struct virtchnl_pf_event *vpe =
+				(struct virtchnl_pf_event *)event->msg_buf;
+
+			if (vpe->event != VIRTCHNL_EVENT_RESET_IMPENDING)
+				continue;
+
+			dev_info(&adapter->pdev->dev, "Reset indication received from the PF\n");
+			if (!(adapter->flags & IAVF_FLAG_RESET_PENDING))
+				iavf_schedule_reset(adapter,
+						    IAVF_FLAG_RESET_PENDING);
+
+			return -EIO;
+		}
+
 		if (op_to_poll == received_op)
 			break;
 	}
@@ -144,9 +162,11 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter)
 	       VIRTCHNL_VF_OFFLOAD_ENCAP |
 	       VIRTCHNL_VF_OFFLOAD_TC_U32 |
 	       VIRTCHNL_VF_OFFLOAD_VLAN_V2 |
+	       VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC |
 	       VIRTCHNL_VF_OFFLOAD_CRC |
 	       VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM |
 	       VIRTCHNL_VF_OFFLOAD_REQ_QUEUES |
+	       VIRTCHNL_VF_CAP_PTP |
 	       VIRTCHNL_VF_OFFLOAD_ADQ |
 	       VIRTCHNL_VF_OFFLOAD_USO |
 	       VIRTCHNL_VF_OFFLOAD_FDIR_PF |
@@ -177,6 +197,54 @@ int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter)
 				NULL, 0);
 }
 
+int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter)
+{
+	adapter->aq_required &= ~IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS;
+
+	if (!IAVF_RXDID_ALLOWED(adapter))
+		return -EOPNOTSUPP;
+
+	adapter->current_op = VIRTCHNL_OP_GET_SUPPORTED_RXDIDS;
+
+	return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS,
+				NULL, 0);
+}
+
+/**
+ * iavf_send_vf_ptp_caps_msg - Send request for PTP capabilities
+ * @adapter: private adapter structure
+ *
+ * Send the VIRTCHNL_OP_1588_PTP_GET_CAPS command to the PF to request the PTP
+ * capabilities available to this device. This includes the following
+ * potential access:
+ *
+ * * READ_PHC - access to read the PTP hardware clock time
+ * * RX_TSTAMP - access to request Rx timestamps on all received packets
+ *
+ * The PF will reply with the same opcode a filled out copy of the
+ * virtchnl_ptp_caps structure which defines the specifics of which features
+ * are accessible to this device.
+ *
+ * Return: 0 if success, error code otherwise.
+ */
+int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter)
+{
+	struct virtchnl_ptp_caps hw_caps = {
+		.caps = VIRTCHNL_1588_PTP_CAP_READ_PHC |
+			VIRTCHNL_1588_PTP_CAP_RX_TSTAMP
+	};
+
+	adapter->aq_required &= ~IAVF_FLAG_AQ_GET_PTP_CAPS;
+
+	if (!IAVF_PTP_ALLOWED(adapter))
+		return -EOPNOTSUPP;
+
+	adapter->current_op = VIRTCHNL_OP_1588_PTP_GET_CAPS;
+
+	return iavf_send_pf_msg(adapter, VIRTCHNL_OP_1588_PTP_GET_CAPS,
+				(u8 *)&hw_caps, sizeof(hw_caps));
+}
+
 /**
  * iavf_validate_num_queues
  * @adapter: adapter structure
@@ -263,6 +331,40 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter)
 	return err;
 }
 
+int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter)
+{
+	struct iavf_arq_event_info event;
+	u64 rxdids;
+	int err;
+
+	event.msg_buf = (u8 *)&rxdids;
+	event.buf_len = sizeof(rxdids);
+
+	err = iavf_poll_virtchnl_msg(&adapter->hw, &event,
+				     VIRTCHNL_OP_GET_SUPPORTED_RXDIDS);
+	if (!err)
+		adapter->supp_rxdids = rxdids;
+
+	return err;
+}
+
+int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter)
+{
+	struct virtchnl_ptp_caps caps = {};
+	struct iavf_arq_event_info event;
+	int err;
+
+	event.msg_buf = (u8 *)&caps;
+	event.buf_len = sizeof(caps);
+
+	err = iavf_poll_virtchnl_msg(&adapter->hw, &event,
+				     VIRTCHNL_OP_1588_PTP_GET_CAPS);
+	if (!err)
+		adapter->ptp.hw_caps = caps;
+
+	return err;
+}
+
 /**
  * iavf_configure_queues
  * @adapter: adapter structure
@@ -275,6 +377,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 	int pairs = adapter->num_active_queues;
 	struct virtchnl_queue_pair_info *vqpi;
 	u32 i, max_frame;
+	u8 rx_flags = 0;
 	size_t len;
 
 	max_frame = LIBIE_MAX_RX_FRM_LEN(adapter->rx_rings->pp->p.offset);
@@ -292,6 +395,9 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 	if (!vqci)
 		return;
 
+	if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP))
+		rx_flags |= VIRTCHNL_PTP_RX_TSTAMP;
+
 	vqci->vsi_id = adapter->vsi_res->vsi_id;
 	vqci->num_queue_pairs = pairs;
 	vqpi = vqci->qpair;
@@ -309,9 +415,12 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 		vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma;
 		vqpi->rxq.max_pkt_size = max_frame;
 		vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len;
+		if (IAVF_RXDID_ALLOWED(adapter))
+			vqpi->rxq.rxdid = adapter->rxdid;
 		if (CRC_OFFLOAD_ALLOWED(adapter))
 			vqpi->rxq.crc_disable = !!(adapter->netdev->features &
 						   NETIF_F_RXFCS);
+		vqpi->rxq.flags = rx_flags;
 		vqpi++;
 	}
 
@@ -684,7 +793,8 @@ void iavf_add_vlans(struct iavf_adapter *adapter)
 
 		len = virtchnl_struct_size(vvfl, vlan_id, count);
 		if (len > IAVF_MAX_AQ_BUF_SIZE) {
-			dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n");
+			dev_info(&adapter->pdev->dev,
+				 "virtchnl: Too many VLAN add (v1) requests; splitting into multiple messages to PF\n");
 			while (len > IAVF_MAX_AQ_BUF_SIZE)
 				len = virtchnl_struct_size(vvfl, vlan_id,
 							   --count);
@@ -729,7 +839,8 @@ void iavf_add_vlans(struct iavf_adapter *adapter)
 
 		len = virtchnl_struct_size(vvfl_v2, filters, count);
 		if (len > IAVF_MAX_AQ_BUF_SIZE) {
-			dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n");
+			dev_info(&adapter->pdev->dev,
+				 "virtchnl: Too many VLAN add (v2) requests; splitting into multiple messages to PF\n");
 			while (len > IAVF_MAX_AQ_BUF_SIZE)
 				len = virtchnl_struct_size(vvfl_v2, filters,
 							   --count);
@@ -832,7 +943,8 @@ void iavf_del_vlans(struct iavf_adapter *adapter)
 
 		len = virtchnl_struct_size(vvfl, vlan_id, count);
 		if (len > IAVF_MAX_AQ_BUF_SIZE) {
-			dev_warn(&adapter->pdev->dev, "Too many delete VLAN changes in one request\n");
+			dev_info(&adapter->pdev->dev,
+				 "virtchnl: Too many VLAN delete (v1) requests; splitting into multiple messages to PF\n");
 			while (len > IAVF_MAX_AQ_BUF_SIZE)
 				len = virtchnl_struct_size(vvfl, vlan_id,
 							   --count);
@@ -878,7 +990,8 @@ void iavf_del_vlans(struct iavf_adapter *adapter)
 
 		len = virtchnl_struct_size(vvfl_v2, filters, count);
 		if (len > IAVF_MAX_AQ_BUF_SIZE) {
-			dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n");
+			dev_info(&adapter->pdev->dev,
+				 "virtchnl: Too many VLAN delete (v2) requests; splitting into multiple messages to PF\n");
 			while (len > IAVF_MAX_AQ_BUF_SIZE)
 				len = virtchnl_struct_size(vvfl_v2, filters,
 							   --count);
@@ -1036,12 +1149,12 @@ void iavf_request_stats(struct iavf_adapter *adapter)
 }
 
 /**
- * iavf_get_hena
+ * iavf_get_rss_hashcfg
  * @adapter: adapter structure
  *
- * Request hash enable capabilities from PF
+ * Request RSS Hash enable bits from PF
  **/
-void iavf_get_hena(struct iavf_adapter *adapter)
+void iavf_get_rss_hashcfg(struct iavf_adapter *adapter)
 {
 	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -1049,20 +1162,20 @@ void iavf_get_hena(struct iavf_adapter *adapter)
 			adapter->current_op);
 		return;
 	}
-	adapter->current_op = VIRTCHNL_OP_GET_RSS_HENA_CAPS;
-	adapter->aq_required &= ~IAVF_FLAG_AQ_GET_HENA;
-	iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_RSS_HENA_CAPS, NULL, 0);
+	adapter->current_op = VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS;
+	adapter->aq_required &= ~IAVF_FLAG_AQ_GET_RSS_HASHCFG;
+	iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS, NULL, 0);
 }
 
 /**
- * iavf_set_hena
+ * iavf_set_rss_hashcfg
  * @adapter: adapter structure
  *
  * Request the PF to set our RSS hash capabilities
  **/
-void iavf_set_hena(struct iavf_adapter *adapter)
+void iavf_set_rss_hashcfg(struct iavf_adapter *adapter)
 {
-	struct virtchnl_rss_hena vrh;
+	struct virtchnl_rss_hashcfg vrh;
 
 	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -1070,10 +1183,10 @@ void iavf_set_hena(struct iavf_adapter *adapter)
 			adapter->current_op);
 		return;
 	}
-	vrh.hena = adapter->hena;
-	adapter->current_op = VIRTCHNL_OP_SET_RSS_HENA;
-	adapter->aq_required &= ~IAVF_FLAG_AQ_SET_HENA;
-	iavf_send_pf_msg(adapter, VIRTCHNL_OP_SET_RSS_HENA, (u8 *)&vrh,
+	vrh.hashcfg = adapter->rss_hashcfg;
+	adapter->current_op = VIRTCHNL_OP_SET_RSS_HASHCFG;
+	adapter->aq_required &= ~IAVF_FLAG_AQ_SET_RSS_HASHCFG;
+	iavf_send_pf_msg(adapter, VIRTCHNL_OP_SET_RSS_HASHCFG, (u8 *)&vrh,
 			 sizeof(vrh));
 }
 
@@ -1402,6 +1515,67 @@ void iavf_disable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid)
 				  VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2);
 }
 
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+/**
+ * iavf_virtchnl_send_ptp_cmd - Send one queued PTP command
+ * @adapter: adapter private structure
+ *
+ * De-queue one PTP command request and send the command message to the PF.
+ * Clear IAVF_FLAG_AQ_SEND_PTP_CMD if no more messages are left to send.
+ */
+void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter)
+{
+	struct iavf_ptp_aq_cmd *cmd;
+	int err;
+
+	if (!adapter->ptp.clock) {
+		/* This shouldn't be possible to hit, since no messages should
+		 * be queued if PTP is not initialized.
+		 */
+		pci_err(adapter->pdev, "PTP is not initialized\n");
+		adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+		return;
+	}
+
+	mutex_lock(&adapter->ptp.aq_cmd_lock);
+	cmd = list_first_entry_or_null(&adapter->ptp.aq_cmds,
+				       struct iavf_ptp_aq_cmd, list);
+	if (!cmd) {
+		/* no further PTP messages to send */
+		adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+		goto out_unlock;
+	}
+
+	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+		/* bail because we already have a command pending */
+		pci_err(adapter->pdev,
+			"Cannot send PTP command %d, command %d pending\n",
+			cmd->v_opcode, adapter->current_op);
+		goto out_unlock;
+	}
+
+	err = iavf_send_pf_msg(adapter, cmd->v_opcode, cmd->msg, cmd->msglen);
+	if (!err) {
+		/* Command was sent without errors, so we can remove it from
+		 * the list and discard it.
+		 */
+		list_del(&cmd->list);
+		kfree(cmd);
+	} else {
+		/* We failed to send the command, try again next cycle */
+		pci_err(adapter->pdev, "Failed to send PTP command %d\n",
+			cmd->v_opcode);
+	}
+
+	if (list_empty(&adapter->ptp.aq_cmds))
+		/* no further PTP messages to send */
+		adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+
+out_unlock:
+	mutex_unlock(&adapter->ptp.aq_cmd_lock);
+}
+#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
+
 /**
  * iavf_print_link_message - print link up or down
  * @adapter: adapter structure
@@ -2098,6 +2272,37 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter)
 }
 
 /**
+ * iavf_virtchnl_ptp_get_time - Respond to VIRTCHNL_OP_1588_PTP_GET_TIME
+ * @adapter: private adapter structure
+ * @data: the message from the PF
+ * @len: length of the message from the PF
+ *
+ * Handle the VIRTCHNL_OP_1588_PTP_GET_TIME message from the PF. This message
+ * is sent by the PF in response to the same op as a request from the VF.
+ * Extract the 64bit nanoseconds time from the message and store it in
+ * cached_phc_time. Then, notify any thread that is waiting for the update via
+ * the wait queue.
+ */
+static void iavf_virtchnl_ptp_get_time(struct iavf_adapter *adapter,
+				       void *data, u16 len)
+{
+	struct virtchnl_phc_time *msg = data;
+
+	if (len != sizeof(*msg)) {
+		dev_err_once(&adapter->pdev->dev,
+			     "Invalid VIRTCHNL_OP_1588_PTP_GET_TIME from PF. Got size %u, expected %zu\n",
+			     len, sizeof(*msg));
+		return;
+	}
+
+	adapter->ptp.cached_phc_time = msg->time;
+	adapter->ptp.cached_phc_updated = jiffies;
+	adapter->ptp.phc_time_ready = true;
+
+	wake_up(&adapter->ptp.phc_time_waitqueue);
+}
+
+/**
  * iavf_virtchnl_completion
  * @adapter: adapter structure
  * @v_opcode: opcode sent by PF
@@ -2509,6 +2714,25 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 			aq_required;
 		}
 		break;
+	case VIRTCHNL_OP_GET_SUPPORTED_RXDIDS:
+		if (msglen != sizeof(u64))
+			return;
+
+		adapter->supp_rxdids = *(u64 *)msg;
+
+		break;
+	case VIRTCHNL_OP_1588_PTP_GET_CAPS:
+		if (msglen != sizeof(adapter->ptp.hw_caps))
+			return;
+
+		adapter->ptp.hw_caps = *(struct virtchnl_ptp_caps *)msg;
+
+		/* process any state change needed due to new capabilities */
+		iavf_ptp_process_caps(adapter);
+		break;
+	case VIRTCHNL_OP_1588_PTP_GET_TIME:
+		iavf_virtchnl_ptp_get_time(adapter, msg, msglen);
+		break;
 	case VIRTCHNL_OP_ENABLE_QUEUES:
 		/* enable transmits */
 		iavf_irq_enable(adapter, true);
@@ -2532,11 +2756,12 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		if (v_opcode != adapter->current_op)
 			return;
 		break;
-	case VIRTCHNL_OP_GET_RSS_HENA_CAPS: {
-		struct virtchnl_rss_hena *vrh = (struct virtchnl_rss_hena *)msg;
+	case VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS: {
+		struct virtchnl_rss_hashcfg *vrh =
+			(struct virtchnl_rss_hashcfg *)msg;
 
 		if (msglen == sizeof(*vrh))
-			adapter->hena = vrh->hena;
+			adapter->rss_hashcfg = vrh->hashcfg;
 		else
 			dev_warn(&adapter->pdev->dev,
 				 "Invalid message %d from PF\n", v_opcode);
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 9e0d9f710441..5b2c666496e7 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -42,18 +42,19 @@ ice-y := ice_main.o	\
 	 ice_ethtool.o  \
 	 ice_repr.o	\
 	 ice_tc_lib.o	\
-	 ice_fwlog.o	\
 	 ice_debugfs.o  \
 	 ice_adapter.o
 ice-$(CONFIG_PCI_IOV) +=	\
 	ice_sriov.o		\
-	ice_virtchnl.o		\
-	ice_virtchnl_allowlist.o \
-	ice_virtchnl_fdir.o	\
+	virt/allowlist.o	\
+	virt/fdir.o		\
+	virt/queues.o		\
+	virt/virtchnl.o		\
+	virt/rss.o		\
 	ice_vf_mbx.o		\
 	ice_vf_vsi_vlan_ops.o	\
 	ice_vf_lib.o
-ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o ice_dpll.o
+ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o ice_dpll.o ice_tspll.o
 ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o
 ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o
 ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index 1b10682c00b8..d88b7f3fd1f9 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -293,7 +293,7 @@ static int ice_devlink_info_get(struct devlink *devlink,
 	err = ice_discover_dev_caps(hw, &ctx->dev_caps);
 	if (err) {
 		dev_dbg(dev, "Failed to discover device capabilities, status %d aq_err %s\n",
-			err, ice_aq_str(hw->adminq.sq_last_status));
+			err, libie_aq_str(hw->adminq.sq_last_status));
 		NL_SET_ERR_MSG_MOD(extack, "Unable to discover device capabilities");
 		goto out_free_ctx;
 	}
@@ -302,7 +302,7 @@ static int ice_devlink_info_get(struct devlink *devlink,
 		err = ice_get_inactive_orom_ver(hw, &ctx->pending_orom);
 		if (err) {
 			dev_dbg(dev, "Unable to read inactive Option ROM version data, status %d aq_err %s\n",
-				err, ice_aq_str(hw->adminq.sq_last_status));
+				err, libie_aq_str(hw->adminq.sq_last_status));
 
 			/* disable display of pending Option ROM */
 			ctx->dev_caps.common_cap.nvm_update_pending_orom = false;
@@ -313,7 +313,7 @@ static int ice_devlink_info_get(struct devlink *devlink,
 		err = ice_get_inactive_nvm_ver(hw, &ctx->pending_nvm);
 		if (err) {
 			dev_dbg(dev, "Unable to read inactive NVM version data, status %d aq_err %s\n",
-				err, ice_aq_str(hw->adminq.sq_last_status));
+				err, libie_aq_str(hw->adminq.sq_last_status));
 
 			/* disable display of pending Option ROM */
 			ctx->dev_caps.common_cap.nvm_update_pending_nvm = false;
@@ -324,7 +324,7 @@ static int ice_devlink_info_get(struct devlink *devlink,
 		err = ice_get_inactive_netlist_ver(hw, &ctx->pending_netlist);
 		if (err) {
 			dev_dbg(dev, "Unable to read inactive Netlist version data, status %d aq_err %s\n",
-				err, ice_aq_str(hw->adminq.sq_last_status));
+				err, libie_aq_str(hw->adminq.sq_last_status));
 
 			/* disable display of pending Option ROM */
 			ctx->dev_caps.common_cap.nvm_update_pending_netlist = false;
@@ -368,14 +368,18 @@ static int ice_devlink_info_get(struct devlink *devlink,
 			}
 			break;
 		case ICE_VERSION_RUNNING:
-			err = devlink_info_version_running_put(req, key, ctx->buf);
+			err = devlink_info_version_running_put_ext(req, key,
+								   ctx->buf,
+								   DEVLINK_INFO_VERSION_TYPE_COMPONENT);
 			if (err) {
 				NL_SET_ERR_MSG_MOD(extack, "Unable to set running version");
 				goto out_free_ctx;
 			}
 			break;
 		case ICE_VERSION_STORED:
-			err = devlink_info_version_stored_put(req, key, ctx->buf);
+			err = devlink_info_version_stored_put_ext(req, key,
+								  ctx->buf,
+								  DEVLINK_INFO_VERSION_TYPE_COMPONENT);
 			if (err) {
 				NL_SET_ERR_MSG_MOD(extack, "Unable to set stored version");
 				goto out_free_ctx;
@@ -436,7 +440,7 @@ ice_devlink_reload_empr_start(struct ice_pf *pf,
 	err = ice_aq_nvm_update_empr(hw);
 	if (err) {
 		dev_err(dev, "Failed to trigger EMP device reset to reload firmware, err %d aq_err %s\n",
-			err, ice_aq_str(hw->adminq.sq_last_status));
+			err, libie_aq_str(hw->adminq.sq_last_status));
 		NL_SET_ERR_MSG_MOD(extack, "Failed to trigger EMP device reset to reload firmware");
 		return err;
 	}
@@ -455,6 +459,7 @@ static void ice_devlink_reinit_down(struct ice_pf *pf)
 	rtnl_lock();
 	ice_vsi_decfg(ice_get_main_vsi(pf));
 	rtnl_unlock();
+	ice_deinit_pf(pf);
 	ice_deinit_dev(pf);
 }
 
@@ -605,11 +610,13 @@ exit_release_res:
  * @devlink: pointer to the devlink instance
  * @id: the parameter ID to set
  * @ctx: context to store the parameter value
+ * @extack: netlink extended ACK structure
  *
  * Return: zero on success and negative value on failure.
  */
 static int ice_devlink_tx_sched_layers_get(struct devlink *devlink, u32 id,
-					   struct devlink_param_gset_ctx *ctx)
+					   struct devlink_param_gset_ctx *ctx,
+					   struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
 	int err;
@@ -977,6 +984,9 @@ static int ice_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv
 
 	/* preallocate memory for ice_sched_node */
 	node = devm_kzalloc(ice_hw_to_dev(pi->hw), sizeof(*node), GFP_KERNEL);
+	if (!node)
+		return -ENOMEM;
+
 	*priv = node;
 
 	return 0;
@@ -1198,6 +1208,25 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate,
 	return status;
 }
 
+static void ice_set_min_max_msix(struct ice_pf *pf)
+{
+	struct devlink *devlink = priv_to_devlink(pf);
+	union devlink_param_value val;
+	int err;
+
+	err = devl_param_driverinit_value_get(devlink,
+					      DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
+					      &val);
+	if (!err)
+		pf->msix.min = val.vu32;
+
+	err = devl_param_driverinit_value_get(devlink,
+					      DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
+					      &val);
+	if (!err)
+		pf->msix.max = val.vu32;
+}
+
 /**
  * ice_devlink_reinit_up - do reinit of the given PF
  * @pf: pointer to the PF struct
@@ -1205,11 +1234,28 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate,
 static int ice_devlink_reinit_up(struct ice_pf *pf)
 {
 	struct ice_vsi *vsi = ice_get_main_vsi(pf);
+	struct device *dev = ice_pf_to_dev(pf);
+	bool need_dev_deinit = false;
 	int err;
 
+	err = ice_init_hw(&pf->hw);
+	if (err) {
+		dev_err(dev, "ice_init_hw failed: %d\n", err);
+		return err;
+	}
+
+	/* load MSI-X values */
+	ice_set_min_max_msix(pf);
+
 	err = ice_init_dev(pf);
 	if (err)
-		return err;
+		goto unroll_hw_init;
+
+	err = ice_init_pf(pf);
+	if (err) {
+		dev_err(dev, "ice_init_pf failed: %d\n", err);
+		goto unroll_dev_init;
+	}
 
 	vsi->flags = ICE_VSI_FLAG_INIT;
 
@@ -1217,7 +1263,7 @@ static int ice_devlink_reinit_up(struct ice_pf *pf)
 	err = ice_vsi_cfg(vsi);
 	rtnl_unlock();
 	if (err)
-		goto err_vsi_cfg;
+		goto unroll_pf_init;
 
 	/* No need to take devl_lock, it's already taken by devlink API */
 	err = ice_load(pf);
@@ -1230,8 +1276,14 @@ err_load:
 	rtnl_lock();
 	ice_vsi_decfg(vsi);
 	rtnl_unlock();
-err_vsi_cfg:
-	ice_deinit_dev(pf);
+unroll_pf_init:
+	ice_deinit_pf(pf);
+unroll_dev_init:
+	need_dev_deinit = true;
+unroll_hw_init:
+	ice_deinit_hw(&pf->hw);
+	if (need_dev_deinit)
+		ice_deinit_dev(pf);
 	return err;
 }
 
@@ -1299,11 +1351,17 @@ static const struct devlink_ops ice_sf_devlink_ops;
 
 static int
 ice_devlink_enable_roce_get(struct devlink *devlink, u32 id,
-			    struct devlink_param_gset_ctx *ctx)
+			    struct devlink_param_gset_ctx *ctx,
+			    struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
+
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
 
-	ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ? true : false;
+	ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2);
 
 	return 0;
 }
@@ -1313,19 +1371,24 @@ static int ice_devlink_enable_roce_set(struct devlink *devlink, u32 id,
 				       struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
 	bool roce_ena = ctx->val.vbool;
 	int ret;
 
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
+
 	if (!roce_ena) {
 		ice_unplug_aux_dev(pf);
-		pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2;
+		cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_ROCEV2;
 		return 0;
 	}
 
-	pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2;
+	cdev->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2;
 	ret = ice_plug_aux_dev(pf);
 	if (ret)
-		pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2;
+		cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_ROCEV2;
 
 	return ret;
 }
@@ -1336,11 +1399,16 @@ ice_devlink_enable_roce_validate(struct devlink *devlink, u32 id,
 				 struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
+
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
 
 	if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags))
 		return -EOPNOTSUPP;
 
-	if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP) {
+	if (cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP) {
 		NL_SET_ERR_MSG_MOD(extack, "iWARP is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously");
 		return -EOPNOTSUPP;
 	}
@@ -1350,11 +1418,17 @@ ice_devlink_enable_roce_validate(struct devlink *devlink, u32 id,
 
 static int
 ice_devlink_enable_iw_get(struct devlink *devlink, u32 id,
-			  struct devlink_param_gset_ctx *ctx)
+			  struct devlink_param_gset_ctx *ctx,
+			  struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
 
-	ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP;
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
+
+	ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP);
 
 	return 0;
 }
@@ -1364,19 +1438,24 @@ static int ice_devlink_enable_iw_set(struct devlink *devlink, u32 id,
 				     struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
 	bool iw_ena = ctx->val.vbool;
 	int ret;
 
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
+
 	if (!iw_ena) {
 		ice_unplug_aux_dev(pf);
-		pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP;
+		cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_IWARP;
 		return 0;
 	}
 
-	pf->rdma_mode |= IIDC_RDMA_PROTOCOL_IWARP;
+	cdev->rdma_protocol |= IIDC_RDMA_PROTOCOL_IWARP;
 	ret = ice_plug_aux_dev(pf);
 	if (ret)
-		pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP;
+		cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_IWARP;
 
 	return ret;
 }
@@ -1391,7 +1470,7 @@ ice_devlink_enable_iw_validate(struct devlink *devlink, u32 id,
 	if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags))
 		return -EOPNOTSUPP;
 
-	if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2) {
+	if (pf->cdev_info->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2) {
 		NL_SET_ERR_MSG_MOD(extack, "RoCEv2 is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously");
 		return -EOPNOTSUPP;
 	}
@@ -1447,11 +1526,13 @@ static int ice_devlink_local_fwd_str_to_mode(const char *mode_str)
  * @devlink: Pointer to the devlink instance.
  * @id: The parameter ID to set.
  * @ctx: Context to store the parameter value.
+ * @extack: netlink extended ACK structure
  *
  * Return: Zero.
  */
 static int ice_devlink_local_fwd_get(struct devlink *devlink, u32 id,
-				     struct devlink_param_gset_ctx *ctx)
+				     struct devlink_param_gset_ctx *ctx,
+				     struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
 	struct ice_port_info *pi;
@@ -1518,6 +1599,43 @@ static int ice_devlink_local_fwd_validate(struct devlink *devlink, u32 id,
 	return 0;
 }
 
+static int
+ice_devlink_msix_max_pf_validate(struct devlink *devlink, u32 id,
+				 union devlink_param_value val,
+				 struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_priv(devlink);
+
+	if (val.vu32 > pf->hw.func_caps.common_cap.num_msix_vectors)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int
+ice_devlink_msix_min_pf_validate(struct devlink *devlink, u32 id,
+				 union devlink_param_value val,
+				 struct netlink_ext_ack *extack)
+{
+	if (val.vu32 < ICE_MIN_MSIX)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int ice_devlink_enable_rdma_validate(struct devlink *devlink, u32 id,
+					    union devlink_param_value val,
+					    struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_priv(devlink);
+	bool new_state = val.vbool;
+
+	if (new_state && !test_bit(ICE_FLAG_RDMA_ENA, pf->flags))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 enum ice_param_id {
 	ICE_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
 	ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
@@ -1533,6 +1651,17 @@ static const struct devlink_param ice_dvl_rdma_params[] = {
 			      ice_devlink_enable_iw_get,
 			      ice_devlink_enable_iw_set,
 			      ice_devlink_enable_iw_validate),
+	DEVLINK_PARAM_GENERIC(ENABLE_RDMA, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, ice_devlink_enable_rdma_validate),
+};
+
+static const struct devlink_param ice_dvl_msix_params[] = {
+	DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MAX,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, ice_devlink_msix_max_pf_validate),
+	DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MIN,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, ice_devlink_msix_min_pf_validate),
 };
 
 static const struct devlink_param ice_dvl_sched_params[] = {
@@ -1636,6 +1765,7 @@ void ice_devlink_unregister(struct ice_pf *pf)
 int ice_devlink_register_params(struct ice_pf *pf)
 {
 	struct devlink *devlink = priv_to_devlink(pf);
+	union devlink_param_value value;
 	struct ice_hw *hw = &pf->hw;
 	int status;
 
@@ -1644,10 +1774,39 @@ int ice_devlink_register_params(struct ice_pf *pf)
 	if (status)
 		return status;
 
+	status = devl_params_register(devlink, ice_dvl_msix_params,
+				      ARRAY_SIZE(ice_dvl_msix_params));
+	if (status)
+		goto unregister_rdma_params;
+
 	if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
 		status = devl_params_register(devlink, ice_dvl_sched_params,
 					      ARRAY_SIZE(ice_dvl_sched_params));
+	if (status)
+		goto unregister_msix_params;
+
+	value.vu32 = pf->msix.max;
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
+					value);
+	value.vu32 = pf->msix.min;
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
+					value);
+
+	value.vbool = test_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA,
+					value);
 
+	return 0;
+
+unregister_msix_params:
+	devl_params_unregister(devlink, ice_dvl_msix_params,
+			       ARRAY_SIZE(ice_dvl_msix_params));
+unregister_rdma_params:
+	devl_params_unregister(devlink, ice_dvl_rdma_params,
+			       ARRAY_SIZE(ice_dvl_rdma_params));
 	return status;
 }
 
@@ -1658,6 +1817,8 @@ void ice_devlink_unregister_params(struct ice_pf *pf)
 
 	devl_params_unregister(devlink, ice_dvl_rdma_params,
 			       ARRAY_SIZE(ice_dvl_rdma_params));
+	devl_params_unregister(devlink, ice_dvl_msix_params,
+			       ARRAY_SIZE(ice_dvl_msix_params));
 
 	if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
 		devl_params_unregister(devlink, ice_dvl_sched_params,
diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c
index d23ae3aafaa7..8e9a8a8178d4 100644
--- a/drivers/net/ethernet/intel/ice/devlink/health.c
+++ b/drivers/net/ethernet/intel/ice/devlink/health.c
@@ -1,12 +1,272 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2024, Intel Corporation. */
 
-#include "health.h"
 #include "ice.h"
+#include "ice_adminq_cmd.h" /* for enum ice_aqc_health_status_elem */
+#include "health.h"
 
 #define ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, obj, name) \
 	devlink_fmsg_put(fmsg, #name, (obj)->name)
 
+#define ICE_HEALTH_STATUS_DATA_SIZE 2
+
+struct ice_health_status {
+	enum ice_aqc_health_status code;
+	const char *description;
+	const char *solution;
+	const char *data_label[ICE_HEALTH_STATUS_DATA_SIZE];
+};
+
+/*
+ * In addition to the health status codes provided below, the firmware might
+ * generate Health Status Codes that are not pertinent to the end-user.
+ * For instance, Health Code 0x1002 is triggered when the command fails.
+ * Such codes should be disregarded by the end-user.
+ * The below lookup requires to be sorted by code.
+ */
+
+static const char ice_common_port_solutions[] =
+	"Check your cable connection. Change or replace the module or cable. Manually set speed and duplex.";
+static const char ice_port_number_label[] = "Port Number";
+static const char ice_update_nvm_solution[] = "Update to the latest NVM image.";
+
+static const struct ice_health_status ice_health_status_lookup[] = {
+	{ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT, "An unsupported module was detected.",
+		ice_common_port_solutions, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE, "Module type is not supported.",
+		"Change or replace the module or cable.", {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL, "Module is not qualified.",
+		ice_common_port_solutions, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM,
+		"Device cannot communicate with the module.",
+		"Check your cable connection. Change or replace the module or cable. Manually set speed and duplex.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT, "Unresolved module conflict.",
+		"Manually set speed/duplex or change the port option. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT, "Module is not present.",
+		"Check that the module is inserted correctly. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED, "Underutilized module.",
+		"Change or replace the module or cable. Change the port option.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT, "An unsupported module was detected.",
+		ice_common_port_solutions, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG, "Invalid link configuration.",
+		NULL, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS, "Port hardware access error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE, "A port is unreachable.",
+		"Change the port option. Update to the latest NVM image."},
+	{ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED, "Port speed is limited due to module.",
+		"Change the module or configure the port option to match the current module speed. Change the port option.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT,
+		"All configured link modes were attempted but failed to establish link. The device will restart the process to establish link.",
+		"Check link partner connection and configuration.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED,
+		"Port speed is limited by PHY capabilities.",
+		"Change the module to align to port option.", {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO, "LOM topology netlist is corrupted.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_NETLIST, "Unrecoverable netlist error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT, "Port topology conflict.",
+		"Change the port option. Update to the latest NVM image."},
+	{ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS, "Unrecoverable hardware access error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME, "Unrecoverable runtime error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT, "Link management engine failed to initialize.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD,
+		"Failed to load the firmware image in the external PHY.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_INFO_RECOVERY, "The device is in firmware recovery mode.",
+		ice_update_nvm_solution, {"Extended Error"}},
+	{ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS, "The flash chip cannot be accessed.",
+		"If issue persists, call customer support.", {"Access Type"}},
+	{ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH, "NVM authentication failed.",
+		ice_update_nvm_solution},
+	{ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH, "Option ROM authentication failed.",
+		ice_update_nvm_solution},
+	{ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH, "DDP package authentication failed.",
+		"Update to latest base driver and DDP package."},
+	{ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT, "NVM image is incompatible.",
+		ice_update_nvm_solution},
+	{ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT, "Option ROM is incompatible.",
+		ice_update_nvm_solution, {"Expected PCI Device ID", "Expected Module ID"}},
+	{ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB,
+		"Supplied MIB file is invalid. DCB reverted to default configuration.",
+		"Disable FW-LLDP and check DCBx system configuration.",
+		{ice_port_number_label, "MIB ID"}},
+};
+
+static int ice_health_status_lookup_compare(const void *a, const void *b)
+{
+	return ((struct ice_health_status *)a)->code - ((struct ice_health_status *)b)->code;
+}
+
+static const struct ice_health_status *ice_get_health_status(u16 code)
+{
+	struct ice_health_status key = { .code = code };
+
+	return bsearch(&key, ice_health_status_lookup, ARRAY_SIZE(ice_health_status_lookup),
+		       sizeof(struct ice_health_status), ice_health_status_lookup_compare);
+}
+
+static void ice_describe_status_code(struct devlink_fmsg *fmsg,
+				     struct ice_aqc_health_status_elem *hse)
+{
+	static const char *const aux_label[] = { "Aux Data 1", "Aux Data 2" };
+	const struct ice_health_status *health_code;
+	u32 internal_data[2];
+	u16 status_code;
+
+	status_code = le16_to_cpu(hse->health_status_code);
+
+	devlink_fmsg_put(fmsg, "Syndrome", status_code);
+	if (status_code) {
+		internal_data[0] = le32_to_cpu(hse->internal_data1);
+		internal_data[1] = le32_to_cpu(hse->internal_data2);
+
+		health_code = ice_get_health_status(status_code);
+		if (!health_code)
+			return;
+
+		devlink_fmsg_string_pair_put(fmsg, "Description", health_code->description);
+		if (health_code->solution)
+			devlink_fmsg_string_pair_put(fmsg, "Possible Solution",
+						     health_code->solution);
+
+		for (size_t i = 0; i < ICE_HEALTH_STATUS_DATA_SIZE; i++) {
+			if (internal_data[i] != ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA)
+				devlink_fmsg_u32_pair_put(fmsg,
+							  health_code->data_label[i] ?
+							  health_code->data_label[i] :
+							  aux_label[i],
+							  internal_data[i]);
+		}
+	}
+}
+
+static int
+ice_port_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+			   struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.port_status);
+	return 0;
+}
+
+static int
+ice_port_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+		       void *priv_ctx, struct netlink_ext_ack __always_unused *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.port_status);
+	return 0;
+}
+
+static int
+ice_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+			 struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.fw_status);
+	return 0;
+}
+
+static int
+ice_fw_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+		     void *priv_ctx, struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.fw_status);
+	return 0;
+}
+
+static void ice_config_health_events(struct ice_pf *pf, bool enable)
+{
+	u8 enable_bits = 0;
+	int ret;
+
+	if (enable)
+		enable_bits = ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK |
+			      ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK;
+
+	ret = ice_aq_set_health_status_cfg(&pf->hw, enable_bits);
+	if (ret)
+		dev_err(ice_pf_to_dev(pf), "Failed to %s firmware health events, err %d aq_err %s\n",
+			str_enable_disable(enable), ret,
+			libie_aq_str(pf->hw.adminq.sq_last_status));
+}
+
+/**
+ * ice_process_health_status_event - Process the health status event from FW
+ * @pf: pointer to the PF structure
+ * @event: event structure containing the Health Status Event opcode
+ *
+ * Decode the Health Status Events and print the associated messages
+ */
+void ice_process_health_status_event(struct ice_pf *pf, struct ice_rq_event_info *event)
+{
+	const struct ice_aqc_health_status_elem *health_info;
+	const struct ice_aqc_get_health_status *cmd;
+	u16 count;
+
+	health_info = (struct ice_aqc_health_status_elem *)event->msg_buf;
+	cmd = libie_aq_raw(&event->desc);
+	count = le16_to_cpu(cmd->health_status_count);
+
+	if (count > (event->buf_len / sizeof(*health_info))) {
+		dev_err(ice_pf_to_dev(pf), "Received a health status event with invalid element count\n");
+		return;
+	}
+
+	for (size_t i = 0; i < count; i++) {
+		const struct ice_health_status *health_code;
+		u16 status_code;
+
+		status_code = le16_to_cpu(health_info->health_status_code);
+		health_code = ice_get_health_status(status_code);
+
+		if (health_code) {
+			switch (le16_to_cpu(health_info->event_source)) {
+			case ICE_AQC_HEALTH_STATUS_GLOBAL:
+				pf->health_reporters.fw_status = *health_info;
+				devlink_health_report(pf->health_reporters.fw,
+						      "FW syndrome reported", NULL);
+				break;
+			case ICE_AQC_HEALTH_STATUS_PF:
+			case ICE_AQC_HEALTH_STATUS_PORT:
+				pf->health_reporters.port_status = *health_info;
+				devlink_health_report(pf->health_reporters.port,
+						      "Port syndrome reported", NULL);
+				break;
+			default:
+				dev_err(ice_pf_to_dev(pf), "Health code with unknown source\n");
+			}
+		} else {
+			u32 data1, data2;
+			u16 source;
+
+			source = le16_to_cpu(health_info->event_source);
+			data1 = le32_to_cpu(health_info->internal_data1);
+			data2 = le32_to_cpu(health_info->internal_data2);
+			dev_dbg(ice_pf_to_dev(pf),
+				"Received internal health status code 0x%08x, source: 0x%08x, data1: 0x%08x, data2: 0x%08x",
+				status_code, source, data1, data2);
+		}
+		health_info++;
+	}
+}
+
 /**
  * ice_devlink_health_report - boilerplate to call given @reporter
  *
@@ -190,9 +450,8 @@ ice_init_devlink_rep(struct ice_pf *pf,
 {
 	struct devlink *devlink = priv_to_devlink(pf);
 	struct devlink_health_reporter *rep;
-	const u64 graceful_period = 0;
 
-	rep = devl_health_reporter_create(devlink, ops, graceful_period, pf);
+	rep = devl_health_reporter_create(devlink, ops, pf);
 	if (IS_ERR(rep)) {
 		struct device *dev = ice_pf_to_dev(pf);
 
@@ -203,14 +462,26 @@ ice_init_devlink_rep(struct ice_pf *pf,
 	return rep;
 }
 
-#define ICE_DEFINE_HEALTH_REPORTER_OPS(_name) \
-	static const struct devlink_health_reporter_ops ice_ ## _name ## _reporter_ops = { \
+#define ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field) \
+	._field = ice_##_name##_reporter_##_field,
+
+#define ICE_DEFINE_HEALTH_REPORTER_OPS_1(_name, _field1) \
+	static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \
 	.name = #_name, \
-	.dump = ice_ ## _name ## _reporter_dump, \
-}
+	ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \
+	}
+
+#define ICE_DEFINE_HEALTH_REPORTER_OPS_2(_name, _field1, _field2) \
+	static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \
+	.name = #_name, \
+	ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \
+	ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field2) \
+	}
 
-ICE_DEFINE_HEALTH_REPORTER_OPS(mdd);
-ICE_DEFINE_HEALTH_REPORTER_OPS(tx_hang);
+ICE_DEFINE_HEALTH_REPORTER_OPS_1(mdd, dump);
+ICE_DEFINE_HEALTH_REPORTER_OPS_1(tx_hang, dump);
+ICE_DEFINE_HEALTH_REPORTER_OPS_2(fw, dump, diagnose);
+ICE_DEFINE_HEALTH_REPORTER_OPS_2(port, dump, diagnose);
 
 /**
  * ice_health_init - allocate and init all ice devlink health reporters and
@@ -224,6 +495,12 @@ void ice_health_init(struct ice_pf *pf)
 
 	reps->mdd = ice_init_devlink_rep(pf, &ice_mdd_reporter_ops);
 	reps->tx_hang = ice_init_devlink_rep(pf, &ice_tx_hang_reporter_ops);
+
+	if (ice_is_fw_health_report_supported(&pf->hw)) {
+		reps->fw = ice_init_devlink_rep(pf, &ice_fw_reporter_ops);
+		reps->port = ice_init_devlink_rep(pf, &ice_port_reporter_ops);
+		ice_config_health_events(pf, true);
+	}
 }
 
 /**
@@ -246,6 +523,11 @@ void ice_health_deinit(struct ice_pf *pf)
 {
 	ice_deinit_devl_reporter(pf->health_reporters.mdd);
 	ice_deinit_devl_reporter(pf->health_reporters.tx_hang);
+	if (ice_is_fw_health_report_supported(&pf->hw)) {
+		ice_deinit_devl_reporter(pf->health_reporters.fw);
+		ice_deinit_devl_reporter(pf->health_reporters.port);
+		ice_config_health_events(pf, false);
+	}
 }
 
 static
diff --git a/drivers/net/ethernet/intel/ice/devlink/health.h b/drivers/net/ethernet/intel/ice/devlink/health.h
index 532277fc57d7..5edfc4d2adce 100644
--- a/drivers/net/ethernet/intel/ice/devlink/health.h
+++ b/drivers/net/ethernet/intel/ice/devlink/health.h
@@ -13,8 +13,10 @@
  * devlink health mechanism for ice driver.
  */
 
+struct ice_aqc_health_status_elem;
 struct ice_pf;
 struct ice_tx_ring;
+struct ice_rq_event_info;
 
 enum ice_mdd_src {
 	ICE_MDD_SRC_TX_PQM,
@@ -25,17 +27,23 @@ enum ice_mdd_src {
 
 /**
  * struct ice_health - stores ice devlink health reporters and accompanied data
- * @tx_hang: devlink health reporter for tx_hang event
+ * @fw: devlink health reporter for FW Health Status events
  * @mdd: devlink health reporter for MDD detection event
+ * @port: devlink health reporter for Port Health Status events
+ * @tx_hang: devlink health reporter for tx_hang event
  * @tx_hang_buf: pre-allocated place to put info for Tx hang reporter from
  *               non-sleeping context
  * @tx_ring: ring that the hang occurred on
  * @head: descriptor head
  * @intr: interrupt register value
  * @vsi_num: VSI owning the queue that the hang occurred on
+ * @fw_status: buffer for last received FW Status event
+ * @port_status: buffer for last received Port Status event
  */
 struct ice_health {
+	struct devlink_health_reporter *fw;
 	struct devlink_health_reporter *mdd;
+	struct devlink_health_reporter *port;
 	struct devlink_health_reporter *tx_hang;
 	struct_group_tagged(ice_health_tx_hang_buf, tx_hang_buf,
 		struct ice_tx_ring *tx_ring;
@@ -43,8 +51,13 @@ struct ice_health {
 		u32 intr;
 		u16 vsi_num;
 	);
+	struct ice_aqc_health_status_elem fw_status;
+	struct ice_aqc_health_status_elem port_status;
 };
 
+void ice_process_health_status_event(struct ice_pf *pf,
+				     struct ice_rq_event_info *event);
+
 void ice_health_init(struct ice_pf *pf);
 void ice_health_deinit(struct ice_pf *pf);
 void ice_health_clear(struct ice_pf *pf);
diff --git a/drivers/net/ethernet/intel/ice/devlink/port.c b/drivers/net/ethernet/intel/ice/devlink/port.c
index 767419a67fef..63fb36fc4b3d 100644
--- a/drivers/net/ethernet/intel/ice/devlink/port.c
+++ b/drivers/net/ethernet/intel/ice/devlink/port.c
@@ -30,6 +30,8 @@ static const char *ice_devlink_port_opt_speed_str(u8 speed)
 		return "10";
 	case ICE_AQC_PORT_OPT_MAX_LANE_25G:
 		return "25";
+	case ICE_AQC_PORT_OPT_MAX_LANE_40G:
+		return "40";
 	case ICE_AQC_PORT_OPT_MAX_LANE_50G:
 		return "50";
 	case ICE_AQC_PORT_OPT_MAX_LANE_100G:
diff --git a/drivers/net/ethernet/intel/ice/devlink/port.h b/drivers/net/ethernet/intel/ice/devlink/port.h
index d60efc340945..e89ddd60eeac 100644
--- a/drivers/net/ethernet/intel/ice/devlink/port.h
+++ b/drivers/net/ethernet/intel/ice/devlink/port.h
@@ -11,7 +11,7 @@
  * struct ice_dynamic_port - Track dynamically added devlink port instance
  * @hw_addr: the HW address for this port
  * @active: true if the port has been activated
- * @attached: true it the prot is attached
+ * @attached: true if the prot is attached
  * @devlink_port: the associated devlink port structure
  * @pf: pointer to the PF private structure
  * @vsi: the VSI associated with this port
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 71e05d30f0fd..147aaee192a7 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -67,6 +67,7 @@
 #include "ice_sriov.h"
 #include "ice_vf_mbx.h"
 #include "ice_ptp.h"
+#include "ice_tspll.h"
 #include "ice_fdir.h"
 #include "ice_xsk.h"
 #include "ice_arfs.h"
@@ -83,7 +84,11 @@
 #define ICE_BAR0		0
 #define ICE_REQ_DESC_MULTIPLE	32
 #define ICE_MIN_NUM_DESC	64
-#define ICE_MAX_NUM_DESC	8160
+#define ICE_MAX_NUM_DESC_E810	8160
+#define ICE_MAX_NUM_DESC_E830	8096
+#define ICE_MAX_NUM_DESC_BY_MAC(hw) ((hw)->mac_type == ICE_MAC_E830 ? \
+				     ICE_MAX_NUM_DESC_E830 : \
+				     ICE_MAX_NUM_DESC_E810)
 #define ICE_DFLT_MIN_RX_DESC	512
 #define ICE_DFLT_NUM_TX_DESC	256
 #define ICE_DFLT_NUM_RX_DESC	2048
@@ -97,9 +102,6 @@
 #define ICE_MIN_LAN_OICR_MSIX	1
 #define ICE_MIN_MSIX		(ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX)
 #define ICE_FDIR_MSIX		2
-#define ICE_RDMA_NUM_AEQ_MSIX	4
-#define ICE_MIN_RDMA_MSIX	2
-#define ICE_ESWITCH_MSIX	1
 #define ICE_NO_VSI		0xffff
 #define ICE_VSI_MAP_CONTIG	0
 #define ICE_VSI_MAP_SCATTER	1
@@ -196,16 +198,17 @@
 
 #define ice_pf_to_dev(pf) (&((pf)->pdev->dev))
 
-#define ice_pf_src_tmr_owned(pf) ((pf)->hw.func_caps.ts_func_info.src_tmr_owned)
-
 enum ice_feature {
 	ICE_F_DSCP,
 	ICE_F_PHY_RCLK,
 	ICE_F_SMA_CTRL,
 	ICE_F_CGU,
 	ICE_F_GNSS,
+	ICE_F_TXTIME,
+	ICE_F_GCS,
 	ICE_F_ROCE_LAG,
 	ICE_F_SRIOV_LAG,
+	ICE_F_SRIOV_AA_LAG,
 	ICE_F_MBX_LIMIT,
 	ICE_F_MAX
 };
@@ -348,6 +351,7 @@ struct ice_vsi {
 	u16 num_q_vectors;
 	/* tell if only dynamic irq allocation is allowed */
 	bool irq_dyn_alloc;
+	bool hsplit:1;
 
 	u16 vsi_num;			/* HW (absolute) index of this VSI */
 	u16 idx;			/* software index in pf->vsi[] */
@@ -371,6 +375,8 @@ struct ice_vsi {
 	spinlock_t arfs_lock;	/* protects aRFS hash table and filter state */
 	atomic_t *arfs_last_fltr_id;
 
+	u16 max_frame;
+
 	struct ice_aqc_vsi_props info;	 /* VSI properties */
 	struct ice_vsi_vlan_info vlan_info;	/* vlan config to be restored */
 
@@ -403,7 +409,6 @@ struct ice_vsi {
 	u16 req_rxq;			 /* User requested Rx queues */
 	u16 num_rx_desc;
 	u16 num_tx_desc;
-	u16 qset_handle[ICE_MAX_TRAFFIC_CLASS];
 	struct ice_tc_cfg tc_cfg;
 	struct bpf_prog *xdp_prog;
 	struct ice_tx_ring **xdp_rings;	 /* XDP ring array */
@@ -478,9 +483,6 @@ struct ice_q_vector {
 	struct ice_ring_container rx;
 	struct ice_ring_container tx;
 
-	cpumask_t affinity_mask;
-	struct irq_affinity_notify affinity_notify;
-
 	struct ice_channel *ch;
 
 	char name[ICE_INT_NAME_STR_LEN];
@@ -510,16 +512,17 @@ enum ice_pf_flags {
 	ICE_FLAG_MOD_POWER_UNSUPPORTED,
 	ICE_FLAG_PHY_FW_LOAD_FAILED,
 	ICE_FLAG_ETHTOOL_CTXT,		/* set when ethtool holds RTNL lock */
-	ICE_FLAG_LEGACY_RX,
 	ICE_FLAG_VF_TRUE_PROMISC_ENA,
 	ICE_FLAG_MDD_AUTO_RESET_VF,
 	ICE_FLAG_VF_VLAN_PRUNING,
 	ICE_FLAG_LINK_LENIENT_MODE_ENA,
 	ICE_FLAG_PLUG_AUX_DEV,
 	ICE_FLAG_UNPLUG_AUX_DEV,
+	ICE_FLAG_AUX_DEV_CREATED,
 	ICE_FLAG_MTU_CHANGED,
 	ICE_FLAG_GNSS,			/* GNSS successfully initialized */
 	ICE_FLAG_DPLL,			/* SyncE/PTP dplls initialized */
+	ICE_FLAG_LLDP_AQ_FLTR,
 	ICE_PF_FLAGS_NBITS		/* must be last */
 };
 
@@ -542,6 +545,14 @@ struct ice_agg_node {
 	u8 valid;
 };
 
+struct ice_pf_msix {
+	u32 cur;
+	u32 min;
+	u32 max;
+	u32 total;
+	u32 rest;
+};
+
 struct ice_pf {
 	struct pci_dev *pdev;
 	struct ice_adapter *adapter;
@@ -554,15 +565,8 @@ struct ice_pf {
 	struct devlink_port devlink_port;
 
 	/* OS reserved IRQ details */
-	struct msix_entry *msix_entries;
 	struct ice_irq_tracker irq_tracker;
-	/* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the
-	 * number of MSIX vectors needed for all SR-IOV VFs from the number of
-	 * MSIX vectors allowed on this PF.
-	 */
-	u16 sriov_base_vector;
-	unsigned long *sriov_irq_bm;	/* bitmap to track irq usage */
-	u16 sriov_irq_size;		/* size of the irq_bm bitmap */
+	struct ice_virt_irq_tracker virt_irq_tracker;
 
 	u16 ctrl_vsi_idx;		/* control VSI index in pf->vsi array */
 
@@ -571,9 +575,6 @@ struct ice_pf {
 	struct ice_sw *first_sw;	/* first switch created by firmware */
 	u16 eswitch_mode;		/* current mode of eswitch */
 	struct dentry *ice_debugfs_pf;
-	struct dentry *ice_debugfs_pf_fwlog;
-	/* keep track of all the dentrys for FW log modules */
-	struct dentry **ice_debugfs_pf_fwlog_modules;
 	struct ice_vfs vfs;
 	DECLARE_BITMAP(features, ICE_F_MAX);
 	DECLARE_BITMAP(state, ICE_STATE_NBITS);
@@ -581,6 +582,7 @@ struct ice_pf {
 	DECLARE_BITMAP(misc_thread, ICE_MISC_THREAD_NBITS);
 	unsigned long *avail_txqs;	/* bitmap to track PF Tx queue usage */
 	unsigned long *avail_rxqs;	/* bitmap to track PF Rx queue usage */
+	unsigned long *txtime_txqs;     /* bitmap to track PF Tx Time queue */
 	unsigned long serv_tmr_period;
 	unsigned long serv_tmr_prev;
 	struct timer_list serv_tmr;
@@ -595,7 +597,6 @@ struct ice_pf {
 	struct gnss_serial *gnss_serial;
 	struct gnss_device *gnss_dev;
 	u16 num_rdma_msix;		/* Total MSIX vectors for RDMA driver */
-	u16 rdma_base_vector;
 
 	/* spinlock to protect the AdminQ wait list */
 	spinlock_t aq_wait_lock;
@@ -612,7 +613,7 @@ struct ice_pf {
 	struct msi_map ll_ts_irq;	/* LL_TS interrupt MSIX vector */
 	u16 max_pf_txqs;	/* Total Tx queues PF wide */
 	u16 max_pf_rxqs;	/* Total Rx queues PF wide */
-	u16 num_lan_msix;	/* Total MSIX vectors for base driver */
+	struct ice_pf_msix msix;
 	u16 num_lan_tx;		/* num LAN Tx queues setup */
 	u16 num_lan_rx;		/* num LAN Rx queues setup */
 	u16 next_vsi;		/* Next free slot in pf->vsi[] - 0-based! */
@@ -621,6 +622,7 @@ struct ice_pf {
 	u16 globr_count;	/* Global reset count */
 	u16 empr_count;		/* EMP reset count */
 	u16 pfr_count;		/* PF reset count */
+	u32 link_down_events;
 
 	u8 wol_ena : 1;		/* software state of WoL */
 	u32 wakeup_reason;	/* last wakeup reason */
@@ -628,14 +630,12 @@ struct ice_pf {
 	struct ice_hw_port_stats stats_prev;
 	struct ice_hw hw;
 	u8 stat_prev_loaded:1; /* has previous stats been loaded */
-	u8 rdma_mode;
 	u16 dcbx_cap;
 	u32 tx_timeout_count;
 	unsigned long tx_timeout_last_recovery;
 	u32 tx_timeout_recovery_level;
 	char int_name[ICE_INT_NAME_STR_LEN];
 	char int_name_ll_ts[ICE_INT_NAME_STR_LEN];
-	struct auxiliary_device *adev;
 	int aux_idx;
 	u32 sw_int_count;
 	/* count of tc_flower filters specific to channel (aka where filter
@@ -667,6 +667,7 @@ struct ice_pf {
 	struct ice_dplls dplls;
 	struct device *hwmon_dev;
 	struct ice_health health_reporters;
+	struct iidc_rdma_core_dev_info *cdev_info;
 
 	u8 num_quanta_prof_used;
 };
@@ -756,6 +757,31 @@ static inline void ice_set_ring_xdp(struct ice_tx_ring *ring)
 }
 
 /**
+ * ice_is_txtime_ena - check if Tx Time is enabled on the Tx ring
+ * @ring: pointer to Tx ring
+ *
+ * Return: true if the Tx ring has Tx Time enabled, false otherwise.
+ */
+static inline bool ice_is_txtime_ena(const struct ice_tx_ring *ring)
+{
+	struct ice_vsi *vsi = ring->vsi;
+	struct ice_pf *pf = vsi->back;
+
+	return test_bit(ring->q_index,  pf->txtime_txqs);
+}
+
+/**
+ * ice_is_txtime_cfg - check if Tx Time is configured on the Tx ring
+ * @ring: pointer to Tx ring
+ *
+ * Return: true if the Tx ring is configured for Tx ring, false otherwise.
+ */
+static inline bool ice_is_txtime_cfg(const struct ice_tx_ring *ring)
+{
+	return !!(ring->flags & ICE_TX_FLAGS_TXTIME);
+}
+
+/**
  * ice_get_xp_from_qid - get ZC XSK buffer pool bound to a queue ID
  * @vsi: pointer to VSI
  * @qid: index of a queue to look at XSK buff pool presence
@@ -912,11 +938,10 @@ static inline bool ice_is_adq_active(struct ice_pf *pf)
 	return false;
 }
 
-void ice_debugfs_fwlog_init(struct ice_pf *pf);
+int ice_debugfs_pf_init(struct ice_pf *pf);
 void ice_debugfs_pf_deinit(struct ice_pf *pf);
 void ice_debugfs_init(void);
 void ice_debugfs_exit(void);
-void ice_pf_fwlog_update_module(struct ice_pf *pf, int log_level, int module);
 
 bool netif_is_ice(const struct net_device *dev);
 int ice_vsi_setup_tx_rings(struct ice_vsi *vsi);
@@ -966,7 +991,6 @@ int ice_plug_aux_dev(struct ice_pf *pf);
 void ice_unplug_aux_dev(struct ice_pf *pf);
 int ice_init_rdma(struct ice_pf *pf);
 void ice_deinit_rdma(struct ice_pf *pf);
-const char *ice_aq_str(enum ice_aq_err aq_err);
 bool ice_is_wol_supported(struct ice_hw *hw);
 void ice_fdir_del_all_fltrs(struct ice_vsi *vsi);
 int
@@ -1007,11 +1031,15 @@ int ice_open(struct net_device *netdev);
 int ice_open_internal(struct net_device *netdev);
 int ice_stop(struct net_device *netdev);
 void ice_service_task_schedule(struct ice_pf *pf);
+void ice_start_service_task(struct ice_pf *pf);
 int ice_load(struct ice_pf *pf);
 void ice_unload(struct ice_pf *pf);
 void ice_adv_lnk_speed_maps_init(void);
+void ice_init_dev_hw(struct ice_pf *pf);
 int ice_init_dev(struct ice_pf *pf);
 void ice_deinit_dev(struct ice_pf *pf);
+int ice_init_pf(struct ice_pf *pf);
+void ice_deinit_pf(struct ice_pf *pf);
 int ice_change_mtu(struct net_device *netdev, int new_mtu);
 void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue);
 int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp);
@@ -1047,10 +1075,63 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf)
 	clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
 }
 
-static inline enum ice_phy_model ice_get_phy_model(const struct ice_hw *hw)
+extern const struct xdp_metadata_ops ice_xdp_md_ops;
+
+/**
+ * ice_is_dual - Check if given config is multi-NAC
+ * @hw: pointer to HW structure
+ *
+ * Return: true if the device is running in mutli-NAC (Network
+ * Acceleration Complex) configuration variant, false otherwise
+ * (always false for non-E825 devices).
+ */
+static inline bool ice_is_dual(struct ice_hw *hw)
 {
-	return hw->ptp.phy_model;
+	return hw->mac_type == ICE_MAC_GENERIC_3K_E825 &&
+	       (hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_DUAL_M);
 }
 
-extern const struct xdp_metadata_ops ice_xdp_md_ops;
+/**
+ * ice_is_primary - Check if given device belongs to the primary complex
+ * @hw: pointer to HW structure
+ *
+ * Check if given PF/HW is running on primary complex in multi-NAC
+ * configuration.
+ *
+ * Return: true if the device is dual, false otherwise (always true
+ * for non-E825 devices).
+ */
+static inline bool ice_is_primary(struct ice_hw *hw)
+{
+	return hw->mac_type != ICE_MAC_GENERIC_3K_E825 ||
+	       !ice_is_dual(hw) ||
+	       (hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M);
+}
+
+/**
+ * ice_pf_src_tmr_owned - Check if a primary timer is owned by PF
+ * @pf: pointer to PF structure
+ *
+ * Return: true if PF owns primary timer, false otherwise.
+ */
+static inline bool ice_pf_src_tmr_owned(struct ice_pf *pf)
+{
+	return pf->hw.func_caps.ts_func_info.src_tmr_owned &&
+	       ice_is_primary(&pf->hw);
+}
+
+/**
+ * ice_get_primary_hw - Get pointer to primary ice_hw structure
+ * @pf: pointer to PF structure
+ *
+ * Return: A pointer to ice_hw structure with access to timesync
+ * register space.
+ */
+static inline struct ice_hw *ice_get_primary_hw(struct ice_pf *pf)
+{
+	if (!pf->adapter->ctrl_pf)
+		return &pf->hw;
+	else
+		return &pf->adapter->ctrl_pf->hw;
+}
 #endif /* _ICE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c
index 01a08cfd0090..0a8a48cd4bce 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.c
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 // SPDX-FileCopyrightText: Copyright Red Hat
 
-#include <linux/bitfield.h>
 #include <linux/cleanup.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
@@ -14,32 +13,45 @@
 static DEFINE_XARRAY(ice_adapters);
 static DEFINE_MUTEX(ice_adapters_mutex);
 
-/* PCI bus number is 8 bits. Slot is 5 bits. Domain can have the rest. */
-#define INDEX_FIELD_DOMAIN GENMASK(BITS_PER_LONG - 1, 13)
-#define INDEX_FIELD_DEV    GENMASK(31, 16)
-#define INDEX_FIELD_BUS    GENMASK(12, 5)
-#define INDEX_FIELD_SLOT   GENMASK(4, 0)
+#define ICE_ADAPTER_FIXED_INDEX	BIT_ULL(63)
 
-static unsigned long ice_adapter_index(const struct pci_dev *pdev)
-{
-	unsigned int domain = pci_domain_nr(pdev->bus);
-
-	WARN_ON(domain > FIELD_MAX(INDEX_FIELD_DOMAIN));
+#define ICE_ADAPTER_INDEX_E825C	\
+	(ICE_DEV_ID_E825C_BACKPLANE | ICE_ADAPTER_FIXED_INDEX)
 
+static u64 ice_adapter_index(struct pci_dev *pdev)
+{
 	switch (pdev->device) {
 	case ICE_DEV_ID_E825C_BACKPLANE:
 	case ICE_DEV_ID_E825C_QSFP:
 	case ICE_DEV_ID_E825C_SFP:
 	case ICE_DEV_ID_E825C_SGMII:
-		return FIELD_PREP(INDEX_FIELD_DEV, pdev->device);
+		/* E825C devices have multiple NACs which are connected to the
+		 * same clock source, and which must share the same
+		 * ice_adapter structure. We can't use the serial number since
+		 * each NAC has its own NVM generated with its own unique
+		 * Device Serial Number. Instead, rely on the embedded nature
+		 * of the E825C devices, and use a fixed index. This relies on
+		 * the fact that all E825C physical functions in a given
+		 * system are part of the same overall device.
+		 */
+		return ICE_ADAPTER_INDEX_E825C;
 	default:
-		return FIELD_PREP(INDEX_FIELD_DOMAIN, domain) |
-		       FIELD_PREP(INDEX_FIELD_BUS,    pdev->bus->number) |
-		       FIELD_PREP(INDEX_FIELD_SLOT,   PCI_SLOT(pdev->devfn));
+		return pci_get_dsn(pdev) & ~ICE_ADAPTER_FIXED_INDEX;
 	}
 }
 
-static struct ice_adapter *ice_adapter_new(void)
+static unsigned long ice_adapter_xa_index(struct pci_dev *pdev)
+{
+	u64 index = ice_adapter_index(pdev);
+
+#if BITS_PER_LONG == 64
+	return index;
+#else
+	return (u32)index ^ (u32)(index >> 32);
+#endif
+}
+
+static struct ice_adapter *ice_adapter_new(struct pci_dev *pdev)
 {
 	struct ice_adapter *adapter;
 
@@ -47,7 +59,9 @@ static struct ice_adapter *ice_adapter_new(void)
 	if (!adapter)
 		return NULL;
 
+	adapter->index = ice_adapter_index(pdev);
 	spin_lock_init(&adapter->ptp_gltsyn_time_lock);
+	spin_lock_init(&adapter->txq_ctx_lock);
 	refcount_set(&adapter->refcount, 1);
 
 	mutex_init(&adapter->ports.lock);
@@ -77,25 +91,29 @@ static void ice_adapter_free(struct ice_adapter *adapter)
  * Return:  Pointer to ice_adapter on success.
  *          ERR_PTR() on error. -ENOMEM is the only possible error.
  */
-struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
+struct ice_adapter *ice_adapter_get(struct pci_dev *pdev)
 {
-	unsigned long index = ice_adapter_index(pdev);
 	struct ice_adapter *adapter;
+	unsigned long index;
 	int err;
 
+	index = ice_adapter_xa_index(pdev);
 	scoped_guard(mutex, &ice_adapters_mutex) {
-		err = xa_insert(&ice_adapters, index, NULL, GFP_KERNEL);
-		if (err == -EBUSY) {
-			adapter = xa_load(&ice_adapters, index);
+		adapter = xa_load(&ice_adapters, index);
+		if (adapter) {
 			refcount_inc(&adapter->refcount);
+			WARN_ON_ONCE(adapter->index != ice_adapter_index(pdev));
 			return adapter;
 		}
+		err = xa_reserve(&ice_adapters, index, GFP_KERNEL);
 		if (err)
 			return ERR_PTR(err);
 
-		adapter = ice_adapter_new();
-		if (!adapter)
+		adapter = ice_adapter_new(pdev);
+		if (!adapter) {
+			xa_release(&ice_adapters, index);
 			return ERR_PTR(-ENOMEM);
+		}
 		xa_store(&ice_adapters, index, adapter, GFP_KERNEL);
 	}
 	return adapter;
@@ -110,11 +128,12 @@ struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
  *
  * Context: Process, may sleep.
  */
-void ice_adapter_put(const struct pci_dev *pdev)
+void ice_adapter_put(struct pci_dev *pdev)
 {
-	unsigned long index = ice_adapter_index(pdev);
 	struct ice_adapter *adapter;
+	unsigned long index;
 
+	index = ice_adapter_xa_index(pdev);
 	scoped_guard(mutex, &ice_adapters_mutex) {
 		adapter = xa_load(&ice_adapters, index);
 		if (WARN_ON(!adapter))
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h
index e233225848b3..e95266c7f20b 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.h
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.h
@@ -27,22 +27,27 @@ struct ice_port_list {
 
 /**
  * struct ice_adapter - PCI adapter resources shared across PFs
+ * @refcount: Reference count. struct ice_pf objects hold the references.
  * @ptp_gltsyn_time_lock: Spinlock protecting access to the GLTSYN_TIME
  *                        register of the PTP clock.
- * @refcount: Reference count. struct ice_pf objects hold the references.
+ * @txq_ctx_lock: Spinlock protecting access to the GLCOMM_QTX_CNTX_CTL register
  * @ctrl_pf: Control PF of the adapter
  * @ports: Ports list
+ * @index: 64-bit index cached for collision detection on 32bit systems
  */
 struct ice_adapter {
 	refcount_t refcount;
 	/* For access to the GLTSYN_TIME register */
 	spinlock_t ptp_gltsyn_time_lock;
+	/* For access to GLCOMM_QTX_CNTX_CTL register */
+	spinlock_t txq_ctx_lock;
 
 	struct ice_pf *ctrl_pf;
 	struct ice_port_list ports;
+	u64 index;
 };
 
-struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev);
-void ice_adapter_put(const struct pci_dev *pdev);
+struct ice_adapter *ice_adapter_get(struct pci_dev *pdev);
+void ice_adapter_put(struct pci_dev *pdev);
 
 #endif /* _ICE_ADAPTER_H */
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 3bf05b135b35..859e9c66f3e7 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -4,6 +4,8 @@
 #ifndef _ICE_ADMINQ_CMD_H_
 #define _ICE_ADMINQ_CMD_H_
 
+#include <linux/net/intel/libie/adminq.h>
+
 /* This header file defines the Admin Queue commands, error codes and
  * descriptor format. It is shared between Firmware and Software.
  */
@@ -14,42 +16,26 @@
 
 #define ICE_RXQ_CTX_SIZE_DWORDS		8
 #define ICE_RXQ_CTX_SZ			(ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32))
-#define ICE_TXQ_CTX_SZ			22
 
 typedef struct __packed { u8 buf[ICE_RXQ_CTX_SZ]; } ice_rxq_ctx_buf_t;
+
+/* The Tx queue context is 40 bytes, and includes some internal state. The
+ * Admin Queue buffers don't include the internal state, so only include the
+ * first 22 bytes of the context.
+ */
+#define ICE_TXQ_CTX_SZ			22
+
 typedef struct __packed { u8 buf[ICE_TXQ_CTX_SZ]; } ice_txq_ctx_buf_t;
 
-struct ice_aqc_generic {
-	__le32 param0;
-	__le32 param1;
-	__le32 addr_high;
-	__le32 addr_low;
-};
+#define ICE_TXQ_CTX_FULL_SIZE_DWORDS	10
+#define ICE_TXQ_CTX_FULL_SZ \
+	(ICE_TXQ_CTX_FULL_SIZE_DWORDS * sizeof(u32))
 
-/* Get version (direct 0x0001) */
-struct ice_aqc_get_ver {
-	__le32 rom_ver;
-	__le32 fw_build;
-	u8 fw_branch;
-	u8 fw_major;
-	u8 fw_minor;
-	u8 fw_patch;
-	u8 api_branch;
-	u8 api_major;
-	u8 api_minor;
-	u8 api_patch;
-};
-
-/* Send driver version (indirect 0x0002) */
-struct ice_aqc_driver_ver {
-	u8 major_ver;
-	u8 minor_ver;
-	u8 build_ver;
-	u8 subbuild_ver;
-	u8 reserved[4];
-	__le32 addr_high;
-	__le32 addr_low;
-};
+typedef struct __packed { u8 buf[ICE_TXQ_CTX_FULL_SZ]; } ice_txq_ctx_buf_full_t;
+
+#define ICE_TXTIME_CTX_SZ		25
+
+typedef struct __packed { u8 buf[ICE_TXTIME_CTX_SZ]; } ice_txtime_ctx_buf_t;
 
 /* Queue Shutdown (direct 0x0003) */
 struct ice_aqc_q_shutdown {
@@ -58,94 +44,6 @@ struct ice_aqc_q_shutdown {
 	u8 reserved[15];
 };
 
-/* Request resource ownership (direct 0x0008)
- * Release resource ownership (direct 0x0009)
- */
-struct ice_aqc_req_res {
-	__le16 res_id;
-#define ICE_AQC_RES_ID_NVM		1
-#define ICE_AQC_RES_ID_SDP		2
-#define ICE_AQC_RES_ID_CHNG_LOCK	3
-#define ICE_AQC_RES_ID_GLBL_LOCK	4
-	__le16 access_type;
-#define ICE_AQC_RES_ACCESS_READ		1
-#define ICE_AQC_RES_ACCESS_WRITE	2
-
-	/* Upon successful completion, FW writes this value and driver is
-	 * expected to release resource before timeout. This value is provided
-	 * in milliseconds.
-	 */
-	__le32 timeout;
-#define ICE_AQ_RES_NVM_READ_DFLT_TIMEOUT_MS	3000
-#define ICE_AQ_RES_NVM_WRITE_DFLT_TIMEOUT_MS	180000
-#define ICE_AQ_RES_CHNG_LOCK_DFLT_TIMEOUT_MS	1000
-#define ICE_AQ_RES_GLBL_LOCK_DFLT_TIMEOUT_MS	3000
-	/* For SDP: pin ID of the SDP */
-	__le32 res_number;
-	/* Status is only used for ICE_AQC_RES_ID_GLBL_LOCK */
-	__le16 status;
-#define ICE_AQ_RES_GLBL_SUCCESS		0
-#define ICE_AQ_RES_GLBL_IN_PROG		1
-#define ICE_AQ_RES_GLBL_DONE		2
-	u8 reserved[2];
-};
-
-/* Get function capabilities (indirect 0x000A)
- * Get device capabilities (indirect 0x000B)
- */
-struct ice_aqc_list_caps {
-	u8 cmd_flags;
-	u8 pf_index;
-	u8 reserved[2];
-	__le32 count;
-	__le32 addr_high;
-	__le32 addr_low;
-};
-
-/* Device/Function buffer entry, repeated per reported capability */
-struct ice_aqc_list_caps_elem {
-	__le16 cap;
-#define ICE_AQC_CAPS_VALID_FUNCTIONS			0x0005
-#define ICE_AQC_CAPS_SRIOV				0x0012
-#define ICE_AQC_CAPS_VF					0x0013
-#define ICE_AQC_CAPS_VSI				0x0017
-#define ICE_AQC_CAPS_DCB				0x0018
-#define ICE_AQC_CAPS_RSS				0x0040
-#define ICE_AQC_CAPS_RXQS				0x0041
-#define ICE_AQC_CAPS_TXQS				0x0042
-#define ICE_AQC_CAPS_MSIX				0x0043
-#define ICE_AQC_CAPS_FD					0x0045
-#define ICE_AQC_CAPS_1588				0x0046
-#define ICE_AQC_CAPS_MAX_MTU				0x0047
-#define ICE_AQC_CAPS_NVM_VER				0x0048
-#define ICE_AQC_CAPS_PENDING_NVM_VER			0x0049
-#define ICE_AQC_CAPS_OROM_VER				0x004A
-#define ICE_AQC_CAPS_PENDING_OROM_VER			0x004B
-#define ICE_AQC_CAPS_NET_VER				0x004C
-#define ICE_AQC_CAPS_PENDING_NET_VER			0x004D
-#define ICE_AQC_CAPS_RDMA				0x0051
-#define ICE_AQC_CAPS_SENSOR_READING			0x0067
-#define ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE		0x0076
-#define ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT		0x0077
-#define ICE_AQC_CAPS_NVM_MGMT				0x0080
-#define ICE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE		0x0085
-#define ICE_AQC_CAPS_NAC_TOPOLOGY			0x0087
-#define ICE_AQC_CAPS_FW_LAG_SUPPORT			0x0092
-#define ICE_AQC_BIT_ROCEV2_LAG				0x01
-#define ICE_AQC_BIT_SRIOV_LAG				0x02
-
-	u8 major_ver;
-	u8 minor_ver;
-	/* Number of resources described by this capability */
-	__le32 number;
-	/* Only meaningful for some types of resources */
-	__le32 logical_id;
-	/* Only meaningful for some types of resources */
-	__le32 phys_id;
-	__le64 rsvd1;
-	__le64 rsvd2;
-};
-
 /* Manage MAC address, read command - indirect (0x0107)
  * This struct is also used for the response
  */
@@ -1498,7 +1396,6 @@ struct ice_aqc_dnl_equa_param {
 #define ICE_AQC_RX_EQU_POST1 (0x12 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_BFLF (0x13 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_BFHF (0x14 << ICE_AQC_RX_EQU_SHIFT)
-#define ICE_AQC_RX_EQU_DRATE (0x15 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_CTLE_GAINHF (0x20 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_CTLE_GAINLF (0x21 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_CTLE_GAINDC (0x22 << ICE_AQC_RX_EQU_SHIFT)
@@ -1672,6 +1569,8 @@ struct ice_aqc_get_port_options_elem {
 #define ICE_AQC_PORT_OPT_MAX_LANE_25G	5
 #define ICE_AQC_PORT_OPT_MAX_LANE_50G	6
 #define ICE_AQC_PORT_OPT_MAX_LANE_100G	7
+#define ICE_AQC_PORT_OPT_MAX_LANE_200G	8
+#define ICE_AQC_PORT_OPT_MAX_LANE_40G	9
 
 	u8 global_scid[2];
 	u8 phy_scid[2];
@@ -1814,6 +1713,7 @@ struct ice_aqc_nvm_pass_comp_tbl {
 #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED		0x0
 #define ICE_AQ_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE	0x1
 #define ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED		0x2
+#define ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK		0x3
 	u8 component_response_code; /* Response only */
 #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED_CODE	0x0
 #define ICE_AQ_NVM_PASS_COMP_STAMP_IDENTICAL_CODE	0x1
@@ -2164,6 +2064,10 @@ struct ice_aqc_cfg_txqs {
 #define ICE_AQC_Q_CFG_SRC_PRT_M		0x7
 #define ICE_AQC_Q_CFG_DST_PRT_S		3
 #define ICE_AQC_Q_CFG_DST_PRT_M		(0x7 << ICE_AQC_Q_CFG_DST_PRT_S)
+#define ICE_AQC_Q_CFG_MODE_M		GENMASK(7, 6)
+#define ICE_AQC_Q_CFG_MODE_SAME_PF	0x0
+#define ICE_AQC_Q_CFG_MODE_GIVE_OWN	0x1
+#define ICE_AQC_Q_CFG_MODE_KEEP_OWN	0x2
 	u8 time_out;
 #define ICE_AQC_Q_CFG_TIMEOUT_S		2
 #define ICE_AQC_Q_CFG_TIMEOUT_M		(0x1F << ICE_AQC_Q_CFG_TIMEOUT_S)
@@ -2217,6 +2121,34 @@ struct ice_aqc_add_rdma_qset_data {
 	struct ice_aqc_add_tx_rdma_qset_entry rdma_qsets[];
 };
 
+/* Set Tx Time LAN Queue (indirect 0x0C35) */
+struct ice_aqc_set_txtimeqs {
+	__le16 q_id;
+	__le16 q_amount;
+	u8 reserved[4];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* This is the descriptor of each queue entry for the Set Tx Time Queue
+ * command (0x0C35). Only used within struct ice_aqc_set_txtime_qgrp.
+ */
+struct ice_aqc_set_txtimeqs_perq {
+	u8 reserved[4];
+	ice_txtime_ctx_buf_t txtime_ctx;
+	u8 reserved1[3];
+};
+
+/* The format of the command buffer for Set Tx Time Queue (0x0C35)
+ * is an array of the following structs. Please note that the length of
+ * each struct ice_aqc_set_txtime_qgrp is variable due to the variable
+ * number of queues in each group!
+ */
+struct ice_aqc_set_txtime_qgrp {
+	u8 reserved[8];
+	struct ice_aqc_set_txtimeqs_perq txtimeqs[];
+};
+
 /* Download Package (indirect 0x0C40) */
 /* Also used for Update Package (indirect 0x0C41 and 0x0C42) */
 struct ice_aqc_download_pkg {
@@ -2271,6 +2203,24 @@ struct ice_aqc_get_pkg_info_resp {
 	struct ice_aqc_get_pkg_info pkg_info[];
 };
 
+#define ICE_CGU_INPUT_PHASE_OFFSET_BYTES	6
+
+struct ice_cgu_input_measure {
+	u8 phase_offset[ICE_CGU_INPUT_PHASE_OFFSET_BYTES];
+	__le32 freq;
+} __packed __aligned(sizeof(__le16));
+
+#define ICE_AQC_GET_CGU_IN_MEAS_DPLL_IDX_M	ICE_M(0xf, 0)
+
+/* Get CGU input measure command response data structure (indirect 0x0C59) */
+struct ice_aqc_get_cgu_input_measure {
+	u8 dpll_idx_opt;
+	u8 length;
+	u8 rsvd[6];
+};
+
+#define ICE_AQC_GET_CGU_MAX_PHASE_ADJ	GENMASK(30, 0)
+
 /* Get CGU abilities command response data structure (indirect 0x0C61) */
 struct ice_aqc_get_cgu_abilities {
 	u8 num_inputs;
@@ -2285,6 +2235,8 @@ struct ice_aqc_get_cgu_abilities {
 	u8 rsvd[3];
 };
 
+#define ICE_AQC_CGU_IN_CFG_FLG2_REFSYNC_EN		BIT(7)
+
 /* Set CGU input config (direct 0x0C62) */
 struct ice_aqc_set_cgu_input_config {
 	u8 input_idx;
@@ -2479,225 +2431,85 @@ struct ice_aqc_event_lan_overflow {
 	u8 reserved[8];
 };
 
-enum ice_aqc_fw_logging_mod {
-	ICE_AQC_FW_LOG_ID_GENERAL = 0,
-	ICE_AQC_FW_LOG_ID_CTRL,
-	ICE_AQC_FW_LOG_ID_LINK,
-	ICE_AQC_FW_LOG_ID_LINK_TOPO,
-	ICE_AQC_FW_LOG_ID_DNL,
-	ICE_AQC_FW_LOG_ID_I2C,
-	ICE_AQC_FW_LOG_ID_SDP,
-	ICE_AQC_FW_LOG_ID_MDIO,
-	ICE_AQC_FW_LOG_ID_ADMINQ,
-	ICE_AQC_FW_LOG_ID_HDMA,
-	ICE_AQC_FW_LOG_ID_LLDP,
-	ICE_AQC_FW_LOG_ID_DCBX,
-	ICE_AQC_FW_LOG_ID_DCB,
-	ICE_AQC_FW_LOG_ID_XLR,
-	ICE_AQC_FW_LOG_ID_NVM,
-	ICE_AQC_FW_LOG_ID_AUTH,
-	ICE_AQC_FW_LOG_ID_VPD,
-	ICE_AQC_FW_LOG_ID_IOSF,
-	ICE_AQC_FW_LOG_ID_PARSER,
-	ICE_AQC_FW_LOG_ID_SW,
-	ICE_AQC_FW_LOG_ID_SCHEDULER,
-	ICE_AQC_FW_LOG_ID_TXQ,
-	ICE_AQC_FW_LOG_ID_RSVD,
-	ICE_AQC_FW_LOG_ID_POST,
-	ICE_AQC_FW_LOG_ID_WATCHDOG,
-	ICE_AQC_FW_LOG_ID_TASK_DISPATCH,
-	ICE_AQC_FW_LOG_ID_MNG,
-	ICE_AQC_FW_LOG_ID_SYNCE,
-	ICE_AQC_FW_LOG_ID_HEALTH,
-	ICE_AQC_FW_LOG_ID_TSDRV,
-	ICE_AQC_FW_LOG_ID_PFREG,
-	ICE_AQC_FW_LOG_ID_MDLVER,
-	ICE_AQC_FW_LOG_ID_MAX,
-};
-
-/* Set FW Logging configuration (indirect 0xFF30)
- * Register for FW Logging (indirect 0xFF31)
- * Query FW Logging (indirect 0xFF32)
- * FW Log Event (indirect 0xFF33)
- */
-struct ice_aqc_fw_log {
-	u8 cmd_flags;
-#define ICE_AQC_FW_LOG_CONF_UART_EN	BIT(0)
-#define ICE_AQC_FW_LOG_CONF_AQ_EN	BIT(1)
-#define ICE_AQC_FW_LOG_QUERY_REGISTERED	BIT(2)
-#define ICE_AQC_FW_LOG_CONF_SET_VALID	BIT(3)
-#define ICE_AQC_FW_LOG_AQ_REGISTER	BIT(0)
-#define ICE_AQC_FW_LOG_AQ_QUERY		BIT(2)
-
-	u8 rsp_flag;
-	__le16 fw_rt_msb;
-	union {
-		struct {
-			__le32 fw_rt_lsb;
-		} sync;
-		struct {
-			__le16 log_resolution;
-#define ICE_AQC_FW_LOG_MIN_RESOLUTION		(1)
-#define ICE_AQC_FW_LOG_MAX_RESOLUTION		(128)
-
-			__le16 mdl_cnt;
-		} cfg;
-	} ops;
+enum ice_aqc_health_status_mask {
+	ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK = BIT(0),
+	ICE_AQC_HEALTH_STATUS_SET_ALL_PF_MASK      = BIT(1),
+	ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK      = BIT(2),
+};
+
+/* Set Health Status (direct 0xFF20) */
+struct ice_aqc_set_health_status_cfg {
+	u8 event_source;
+	u8 reserved[15];
+};
+
+enum ice_aqc_health_status {
+	ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT		= 0x101,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE			= 0x102,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL			= 0x103,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM			= 0x104,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT			= 0x105,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT		= 0x106,
+	ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED		= 0x107,
+	ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT		= 0x108,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_DIAGNOSTIC_FEATURE	= 0x109,
+	ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG		= 0x10B,
+	ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS			= 0x10C,
+	ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE		= 0x10D,
+	ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED	= 0x10F,
+	ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT		= 0x110,
+	ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED	= 0x111,
+	ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO			= 0x112,
+	ICE_AQC_HEALTH_STATUS_ERR_NETLIST			= 0x113,
+	ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT			= 0x114,
+	ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS		= 0x115,
+	ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME			= 0x116,
+	ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT			= 0x117,
+	ICE_AQC_HEALTH_STATUS_ERR_PHY_NVM_PROG			= 0x120,
+	ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD			= 0x121,
+	ICE_AQC_HEALTH_STATUS_INFO_RECOVERY			= 0x500,
+	ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS			= 0x501,
+	ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH			= 0x502,
+	ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH			= 0x503,
+	ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH			= 0x504,
+	ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT			= 0x505,
+	ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT			= 0x506,
+	ICE_AQC_HEALTH_STATUS_ERR_NVM_SEC_VIOLATION		= 0x507,
+	ICE_AQC_HEALTH_STATUS_ERR_OROM_SEC_VIOLATION		= 0x508,
+	ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB			= 0x509,
+	ICE_AQC_HEALTH_STATUS_ERR_MNG_TIMEOUT			= 0x50A,
+	ICE_AQC_HEALTH_STATUS_ERR_BMC_RESET			= 0x50B,
+	ICE_AQC_HEALTH_STATUS_ERR_LAST_MNG_FAIL			= 0x50C,
+	ICE_AQC_HEALTH_STATUS_ERR_RESOURCE_ALLOC_FAIL		= 0x50D,
+	ICE_AQC_HEALTH_STATUS_ERR_FW_LOOP			= 0x1000,
+	ICE_AQC_HEALTH_STATUS_ERR_FW_PFR_FAIL			= 0x1001,
+	ICE_AQC_HEALTH_STATUS_ERR_LAST_FAIL_AQ			= 0x1002,
+};
+
+/* Get Health Status (indirect 0xFF22) */
+struct ice_aqc_get_health_status {
+	__le16 health_status_count;
+	u8 reserved[6];
 	__le32 addr_high;
 	__le32 addr_low;
 };
 
-/* Response Buffer for:
- *    Set Firmware Logging Configuration (0xFF30)
- *    Query FW Logging (0xFF32)
- */
-struct ice_aqc_fw_log_cfg_resp {
-	__le16 module_identifier;
-	u8 log_level;
-	u8 rsvd0;
+enum ice_aqc_health_status_scope {
+	ICE_AQC_HEALTH_STATUS_PF	= 0x1,
+	ICE_AQC_HEALTH_STATUS_PORT	= 0x2,
+	ICE_AQC_HEALTH_STATUS_GLOBAL	= 0x3,
 };
 
-/**
- * struct ice_aq_desc - Admin Queue (AQ) descriptor
- * @flags: ICE_AQ_FLAG_* flags
- * @opcode: AQ command opcode
- * @datalen: length in bytes of indirect/external data buffer
- * @retval: return value from firmware
- * @cookie_high: opaque data high-half
- * @cookie_low: opaque data low-half
- * @params: command-specific parameters
- *
- * Descriptor format for commands the driver posts on the Admin Transmit Queue
- * (ATQ). The firmware writes back onto the command descriptor and returns
- * the result of the command. Asynchronous events that are not an immediate
- * result of the command are written to the Admin Receive Queue (ARQ) using
- * the same descriptor format. Descriptors are in little-endian notation with
- * 32-bit words.
+#define ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA	0xDEADBEEF
+
+/* Get Health Status event buffer entry (0xFF22),
+ * repeated per reported health status.
  */
-struct ice_aq_desc {
-	__le16 flags;
-	__le16 opcode;
-	__le16 datalen;
-	__le16 retval;
-	__le32 cookie_high;
-	__le32 cookie_low;
-	union {
-		u8 raw[16];
-		struct ice_aqc_generic generic;
-		struct ice_aqc_get_ver get_ver;
-		struct ice_aqc_driver_ver driver_ver;
-		struct ice_aqc_q_shutdown q_shutdown;
-		struct ice_aqc_req_res res_owner;
-		struct ice_aqc_manage_mac_read mac_read;
-		struct ice_aqc_manage_mac_write mac_write;
-		struct ice_aqc_clear_pxe clear_pxe;
-		struct ice_aqc_list_caps get_cap;
-		struct ice_aqc_get_phy_caps get_phy;
-		struct ice_aqc_set_phy_cfg set_phy;
-		struct ice_aqc_restart_an restart_an;
-		struct ice_aqc_set_phy_rec_clk_out set_phy_rec_clk_out;
-		struct ice_aqc_get_phy_rec_clk_out get_phy_rec_clk_out;
-		struct ice_aqc_get_sensor_reading get_sensor_reading;
-		struct ice_aqc_get_sensor_reading_resp get_sensor_reading_resp;
-		struct ice_aqc_gpio read_write_gpio;
-		struct ice_aqc_sff_eeprom read_write_sff_param;
-		struct ice_aqc_set_port_id_led set_port_id_led;
-		struct ice_aqc_get_port_options get_port_options;
-		struct ice_aqc_set_port_option set_port_option;
-		struct ice_aqc_get_sw_cfg get_sw_conf;
-		struct ice_aqc_set_port_params set_port_params;
-		struct ice_aqc_sw_rules sw_rules;
-		struct ice_aqc_add_get_recipe add_get_recipe;
-		struct ice_aqc_recipe_to_profile recipe_to_profile;
-		struct ice_aqc_get_topo get_topo;
-		struct ice_aqc_sched_elem_cmd sched_elem_cmd;
-		struct ice_aqc_query_txsched_res query_sched_res;
-		struct ice_aqc_query_port_ets port_ets;
-		struct ice_aqc_rl_profile rl_profile;
-		struct ice_aqc_nvm nvm;
-		struct ice_aqc_nvm_checksum nvm_checksum;
-		struct ice_aqc_nvm_pkg_data pkg_data;
-		struct ice_aqc_nvm_pass_comp_tbl pass_comp_tbl;
-		struct ice_aqc_pf_vf_msg virt;
-		struct ice_aqc_set_query_pfc_mode set_query_pfc_mode;
-		struct ice_aqc_lldp_get_mib lldp_get_mib;
-		struct ice_aqc_lldp_set_mib_change lldp_set_event;
-		struct ice_aqc_lldp_stop lldp_stop;
-		struct ice_aqc_lldp_start lldp_start;
-		struct ice_aqc_lldp_set_local_mib lldp_set_mib;
-		struct ice_aqc_lldp_stop_start_specific_agent lldp_agent_ctrl;
-		struct ice_aqc_lldp_filter_ctrl lldp_filter_ctrl;
-		struct ice_aqc_get_set_rss_lut get_set_rss_lut;
-		struct ice_aqc_get_set_rss_key get_set_rss_key;
-		struct ice_aqc_neigh_dev_req neigh_dev;
-		struct ice_aqc_add_txqs add_txqs;
-		struct ice_aqc_dis_txqs dis_txqs;
-		struct ice_aqc_cfg_txqs cfg_txqs;
-		struct ice_aqc_add_rdma_qset add_rdma_qset;
-		struct ice_aqc_add_get_update_free_vsi vsi_cmd;
-		struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res;
-		struct ice_aqc_download_pkg download_pkg;
-		struct ice_aqc_set_cgu_input_config set_cgu_input_config;
-		struct ice_aqc_get_cgu_input_config get_cgu_input_config;
-		struct ice_aqc_set_cgu_output_config set_cgu_output_config;
-		struct ice_aqc_get_cgu_output_config get_cgu_output_config;
-		struct ice_aqc_get_cgu_dpll_status get_cgu_dpll_status;
-		struct ice_aqc_set_cgu_dpll_config set_cgu_dpll_config;
-		struct ice_aqc_set_cgu_ref_prio set_cgu_ref_prio;
-		struct ice_aqc_get_cgu_ref_prio get_cgu_ref_prio;
-		struct ice_aqc_get_cgu_info get_cgu_info;
-		struct ice_aqc_driver_shared_params drv_shared_params;
-		struct ice_aqc_fw_log fw_log;
-		struct ice_aqc_set_mac_lb set_mac_lb;
-		struct ice_aqc_alloc_free_res_cmd sw_res_ctrl;
-		struct ice_aqc_set_mac_cfg set_mac_cfg;
-		struct ice_aqc_set_event_mask set_event_mask;
-		struct ice_aqc_get_link_status get_link_status;
-		struct ice_aqc_event_lan_overflow lan_overflow;
-		struct ice_aqc_get_link_topo get_link_topo;
-		struct ice_aqc_dnl_call_command dnl_call;
-		struct ice_aqc_i2c read_write_i2c;
-		struct ice_aqc_read_i2c_resp read_i2c_resp;
-		struct ice_aqc_get_set_tx_topo get_set_tx_topo;
-	} params;
-};
-
-/* FW defined boundary for a large buffer, 4k >= Large buffer > 512 bytes */
-#define ICE_AQ_LG_BUF	512
-
-#define ICE_AQ_FLAG_DD_S	0
-#define ICE_AQ_FLAG_CMP_S	1
-#define ICE_AQ_FLAG_ERR_S	2
-#define ICE_AQ_FLAG_LB_S	9
-#define ICE_AQ_FLAG_RD_S	10
-#define ICE_AQ_FLAG_BUF_S	12
-#define ICE_AQ_FLAG_SI_S	13
-
-#define ICE_AQ_FLAG_DD		BIT(ICE_AQ_FLAG_DD_S)  /* 0x1    */
-#define ICE_AQ_FLAG_CMP		BIT(ICE_AQ_FLAG_CMP_S) /* 0x2    */
-#define ICE_AQ_FLAG_ERR		BIT(ICE_AQ_FLAG_ERR_S) /* 0x4    */
-#define ICE_AQ_FLAG_LB		BIT(ICE_AQ_FLAG_LB_S)  /* 0x200  */
-#define ICE_AQ_FLAG_RD		BIT(ICE_AQ_FLAG_RD_S)  /* 0x400  */
-#define ICE_AQ_FLAG_BUF		BIT(ICE_AQ_FLAG_BUF_S) /* 0x1000 */
-#define ICE_AQ_FLAG_SI		BIT(ICE_AQ_FLAG_SI_S)  /* 0x2000 */
-
-/* error codes */
-enum ice_aq_err {
-	ICE_AQ_RC_OK		= 0,  /* Success */
-	ICE_AQ_RC_EPERM		= 1,  /* Operation not permitted */
-	ICE_AQ_RC_ENOENT	= 2,  /* No such element */
-	ICE_AQ_RC_ENOMEM	= 9,  /* Out of memory */
-	ICE_AQ_RC_EBUSY		= 12, /* Device or resource busy */
-	ICE_AQ_RC_EEXIST	= 13, /* Object already exists */
-	ICE_AQ_RC_EINVAL	= 14, /* Invalid argument */
-	ICE_AQ_RC_ENOSPC	= 16, /* No space left or allocation failure */
-	ICE_AQ_RC_ENOSYS	= 17, /* Function not implemented */
-	ICE_AQ_RC_EMODE		= 21, /* Op not allowed in current dev mode */
-	ICE_AQ_RC_ENOSEC	= 24, /* Missing security manifest */
-	ICE_AQ_RC_EBADSIG	= 25, /* Bad RSA signature */
-	ICE_AQ_RC_ESVN		= 26, /* SVN number prohibits this package */
-	ICE_AQ_RC_EBADMAN	= 27, /* Manifest hash mismatch */
-	ICE_AQ_RC_EBADBUF	= 28, /* Buffer hash mismatches manifest */
+struct ice_aqc_health_status_elem {
+	__le16 health_status_code;
+	__le16 event_source;
+	__le32 internal_data1;
+	__le32 internal_data2;
 };
 
 /* Admin Queue command opcodes */
@@ -2834,6 +2646,9 @@ enum ice_adminq_opc {
 	ice_aqc_opc_cfg_txqs				= 0x0C32,
 	ice_aqc_opc_add_rdma_qset			= 0x0C33,
 
+	/* Tx Time queue commands */
+	ice_aqc_opc_set_txtimeqs			= 0x0C35,
+
 	/* package commands */
 	ice_aqc_opc_download_pkg			= 0x0C40,
 	ice_aqc_opc_upload_section			= 0x0C41,
@@ -2841,6 +2656,7 @@ enum ice_adminq_opc {
 	ice_aqc_opc_get_pkg_info_list			= 0x0C43,
 
 	/* 1588/SyncE commands/events */
+	ice_aqc_opc_get_cgu_input_measure		= 0x0C59,
 	ice_aqc_opc_get_cgu_abilities			= 0x0C61,
 	ice_aqc_opc_set_cgu_input_config		= 0x0C62,
 	ice_aqc_opc_get_cgu_input_config		= 0x0C63,
@@ -2857,6 +2673,10 @@ enum ice_adminq_opc {
 	/* Standalone Commands/Events */
 	ice_aqc_opc_event_lan_overflow			= 0x1001,
 
+	/* System Diagnostic commands */
+	ice_aqc_opc_set_health_status_cfg		= 0xFF20,
+	ice_aqc_opc_get_health_status			= 0xFF22,
+
 	/* FW Logging Commands */
 	ice_aqc_opc_fw_logs_config			= 0xFF30,
 	ice_aqc_opc_fw_logs_register			= 0xFF31,
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c
index 7cee365cc7d1..1f7834c03550 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.c
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.c
@@ -378,6 +378,50 @@ ice_arfs_is_perfect_flow_set(struct ice_hw *hw, __be16 l3_proto, u8 l4_proto)
 }
 
 /**
+ * ice_arfs_cmp - Check if aRFS filter matches this flow.
+ * @fltr_info: filter info of the saved ARFS entry.
+ * @fk: flow dissector keys.
+ * @n_proto:  One of htons(ETH_P_IP) or htons(ETH_P_IPV6).
+ * @ip_proto: One of IPPROTO_TCP or IPPROTO_UDP.
+ *
+ * Since this function assumes limited values for n_proto and ip_proto, it
+ * is meant to be called only from ice_rx_flow_steer().
+ *
+ * Return:
+ * * true	- fltr_info refers to the same flow as fk.
+ * * false	- fltr_info and fk refer to different flows.
+ */
+static bool
+ice_arfs_cmp(const struct ice_fdir_fltr *fltr_info, const struct flow_keys *fk,
+	     __be16 n_proto, u8 ip_proto)
+{
+	/* Determine if the filter is for IPv4 or IPv6 based on flow_type,
+	 * which is one of ICE_FLTR_PTYPE_NONF_IPV{4,6}_{TCP,UDP}.
+	 */
+	bool is_v4 = fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP ||
+		     fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP;
+
+	/* Following checks are arranged in the quickest and most discriminative
+	 * fields first for early failure.
+	 */
+	if (is_v4)
+		return n_proto == htons(ETH_P_IP) &&
+			fltr_info->ip.v4.src_port == fk->ports.src &&
+			fltr_info->ip.v4.dst_port == fk->ports.dst &&
+			fltr_info->ip.v4.src_ip == fk->addrs.v4addrs.src &&
+			fltr_info->ip.v4.dst_ip == fk->addrs.v4addrs.dst &&
+			fltr_info->ip.v4.proto == ip_proto;
+
+	return fltr_info->ip.v6.src_port == fk->ports.src &&
+		fltr_info->ip.v6.dst_port == fk->ports.dst &&
+		fltr_info->ip.v6.proto == ip_proto &&
+		!memcmp(&fltr_info->ip.v6.src_ip, &fk->addrs.v6addrs.src,
+			sizeof(struct in6_addr)) &&
+		!memcmp(&fltr_info->ip.v6.dst_ip, &fk->addrs.v6addrs.dst,
+			sizeof(struct in6_addr));
+}
+
+/**
  * ice_rx_flow_steer - steer the Rx flow to where application is being run
  * @netdev: ptr to the netdev being adjusted
  * @skb: buffer with required header information
@@ -448,6 +492,10 @@ ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb,
 			continue;
 
 		fltr_info = &arfs_entry->fltr_info;
+
+		if (!ice_arfs_cmp(fltr_info, &fk, n_proto, ip_proto))
+			continue;
+
 		ret = fltr_info->fltr_id;
 
 		if (fltr_info->q_index == rxq_idx ||
@@ -511,7 +559,7 @@ void ice_init_arfs(struct ice_vsi *vsi)
 	struct hlist_head *arfs_fltr_list;
 	unsigned int i;
 
-	if (!vsi || vsi->type != ICE_VSI_PF)
+	if (!vsi || vsi->type != ICE_VSI_PF || ice_is_arfs_active(vsi))
 		return;
 
 	arfs_fltr_list = kcalloc(ICE_MAX_ARFS_LIST, sizeof(*arfs_fltr_list),
@@ -571,25 +619,6 @@ void ice_clear_arfs(struct ice_vsi *vsi)
 }
 
 /**
- * ice_free_cpu_rx_rmap - free setup CPU reverse map
- * @vsi: the VSI to be forwarded to
- */
-void ice_free_cpu_rx_rmap(struct ice_vsi *vsi)
-{
-	struct net_device *netdev;
-
-	if (!vsi || vsi->type != ICE_VSI_PF)
-		return;
-
-	netdev = vsi->netdev;
-	if (!netdev || !netdev->rx_cpu_rmap)
-		return;
-
-	free_irq_cpu_rmap(netdev->rx_cpu_rmap);
-	netdev->rx_cpu_rmap = NULL;
-}
-
-/**
  * ice_set_cpu_rx_rmap - setup CPU reverse map for each queue
  * @vsi: the VSI to be forwarded to
  */
@@ -597,7 +626,6 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi)
 {
 	struct net_device *netdev;
 	struct ice_pf *pf;
-	int i;
 
 	if (!vsi || vsi->type != ICE_VSI_PF)
 		return 0;
@@ -610,18 +638,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi)
 	netdev_dbg(netdev, "Setup CPU RMAP: vsi type 0x%x, ifname %s, q_vectors %d\n",
 		   vsi->type, netdev->name, vsi->num_q_vectors);
 
-	netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(vsi->num_q_vectors);
-	if (unlikely(!netdev->rx_cpu_rmap))
-		return -EINVAL;
-
-	ice_for_each_q_vector(vsi, i)
-		if (irq_cpu_rmap_add(netdev->rx_cpu_rmap,
-				     vsi->q_vectors[i]->irq.virq)) {
-			ice_free_cpu_rx_rmap(vsi);
-			return -EINVAL;
-		}
-
-	return 0;
+	return netif_enable_cpu_rmap(netdev, vsi->num_q_vectors);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.h b/drivers/net/ethernet/intel/ice/ice_arfs.h
index 9669ad9bf7b5..9706293128c3 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.h
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.h
@@ -45,7 +45,6 @@ int
 ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb,
 		  u16 rxq_idx, u32 flow_id);
 void ice_clear_arfs(struct ice_vsi *vsi);
-void ice_free_cpu_rx_rmap(struct ice_vsi *vsi);
 void ice_init_arfs(struct ice_vsi *vsi);
 void ice_sync_arfs_fltrs(struct ice_pf *pf);
 int ice_set_cpu_rx_rmap(struct ice_vsi *vsi);
@@ -56,7 +55,6 @@ ice_is_arfs_using_perfect_flow(struct ice_hw *hw,
 			       enum ice_fltr_ptype flow_type);
 #else
 static inline void ice_clear_arfs(struct ice_vsi *vsi) { }
-static inline void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { }
 static inline void ice_init_arfs(struct ice_vsi *vsi) { }
 static inline void ice_sync_arfs_fltrs(struct ice_pf *pf) { }
 static inline void ice_remove_arfs(struct ice_pf *pf) { }
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index b2af8e3586f7..eadb1e3d12b3 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019, Intel Corporation. */
 
 #include <net/xdp_sock_drv.h>
+#include <linux/net/intel/libie/rx.h>
 #include "ice_base.h"
 #include "ice_lib.h"
 #include "ice_dcb_lib.h"
@@ -147,10 +148,6 @@ skip_alloc:
 	q_vector->reg_idx = q_vector->irq.index;
 	q_vector->vf_reg_idx = q_vector->irq.index;
 
-	/* only set affinity_mask if the CPU is online */
-	if (cpu_online(v_idx))
-		cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
-
 	/* This will not be called in the driver load path because the netdev
 	 * will not be created yet. All other cases with register the NAPI
 	 * handler here (i.e. resume, reset/rebuild, etc.)
@@ -246,7 +243,8 @@ static void ice_cfg_itr_gran(struct ice_hw *hw)
  * @ring: ring to get the absolute queue index
  * @tc: traffic class number
  */
-static u16 ice_calc_txq_handle(struct ice_vsi *vsi, struct ice_tx_ring *ring, u8 tc)
+static u16
+ice_calc_txq_handle(const struct ice_vsi *vsi, struct ice_tx_ring *ring, u8 tc)
 {
 	WARN_ONCE(ice_ring_is_xdp(ring) && tc, "XDP ring can't belong to TC other than 0\n");
 
@@ -254,7 +252,7 @@ static u16 ice_calc_txq_handle(struct ice_vsi *vsi, struct ice_tx_ring *ring, u8
 		return ring->q_index - ring->ch->base_q;
 
 	/* Idea here for calculation is that we subtract the number of queue
-	 * count from TC that ring belongs to from it's absolute queue index
+	 * count from TC that ring belongs to from its absolute queue index
 	 * and as a result we get the queue's index within TC.
 	 */
 	return ring->q_index - vsi->tc_cfg.tc_info[tc].qoffset;
@@ -276,35 +274,26 @@ static void ice_cfg_xps_tx_ring(struct ice_tx_ring *ring)
 	if (test_and_set_bit(ICE_TX_XPS_INIT_DONE, ring->xps_state))
 		return;
 
-	netif_set_xps_queue(ring->netdev, &ring->q_vector->affinity_mask,
+	netif_set_xps_queue(ring->netdev,
+			    &ring->q_vector->napi.config->affinity_mask,
 			    ring->q_index);
 }
 
 /**
- * ice_setup_tx_ctx - setup a struct ice_tlan_ctx instance
- * @ring: The Tx ring to configure
- * @tlan_ctx: Pointer to the Tx LAN queue context structure to be initialized
- * @pf_q: queue index in the PF space
+ * ice_set_txq_ctx_vmvf - set queue context VM/VF type and number by VSI type
+ * @ring: the Tx ring to configure
+ * @vmvf_type: VM/VF type
+ * @vmvf_num: VM/VF number
  *
- * Configure the Tx descriptor ring in TLAN context.
+ * Return: 0 on success and a negative value on error.
  */
-static void
-ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q)
+static int
+ice_set_txq_ctx_vmvf(struct ice_tx_ring *ring, u8 *vmvf_type, u16 *vmvf_num)
 {
 	struct ice_vsi *vsi = ring->vsi;
-	struct ice_hw *hw = &vsi->back->hw;
-
-	tlan_ctx->base = ring->dma >> ICE_TLAN_CTX_BASE_S;
-
-	tlan_ctx->port_num = vsi->port_info->lport;
-
-	/* Transmit Queue Length */
-	tlan_ctx->qlen = ring->count;
-
-	ice_set_cgd_num(tlan_ctx, ring->dcb_tc);
+	struct ice_hw *hw;
 
-	/* PF number */
-	tlan_ctx->pf_num = hw->pf_id;
+	hw = &vsi->back->hw;
 
 	/* queue belongs to a specific VSI type
 	 * VF / VM index should be programmed per vmvf_type setting:
@@ -317,21 +306,60 @@ ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf
 	case ICE_VSI_CTRL:
 	case ICE_VSI_PF:
 		if (ring->ch)
-			tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VMQ;
+			*vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VMQ;
 		else
-			tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF;
+			*vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF;
 		break;
 	case ICE_VSI_VF:
 		/* Firmware expects vmvf_num to be absolute VF ID */
-		tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf->vf_id;
-		tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VF;
+		*vmvf_num = hw->func_caps.vf_base_id + vsi->vf->vf_id;
+		*vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VF;
 		break;
 	case ICE_VSI_SF:
-		tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VMQ;
+		*vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VMQ;
 		break;
 	default:
-		return;
+		dev_info(ice_pf_to_dev(vsi->back),
+			 "Unable to set VMVF type for VSI type %d\n",
+			 vsi->type);
+		return -EINVAL;
 	}
+	return 0;
+}
+
+/**
+ * ice_setup_tx_ctx - setup a struct ice_tlan_ctx instance
+ * @ring: the Tx ring to configure
+ * @tlan_ctx: pointer to the Tx LAN queue context structure to be initialized
+ * @pf_q: queue index in the PF space
+ *
+ * Configure the Tx descriptor ring in TLAN context.
+ *
+ * Return: 0 on success and a negative value on error.
+ */
+static int
+ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q)
+{
+	struct ice_vsi *vsi = ring->vsi;
+	struct ice_hw *hw;
+	int err;
+
+	hw = &vsi->back->hw;
+	tlan_ctx->base = ring->dma >> ICE_TLAN_CTX_BASE_S;
+	tlan_ctx->port_num = vsi->port_info->lport;
+
+	/* Transmit Queue Length */
+	tlan_ctx->qlen = ring->count;
+
+	ice_set_cgd_num(tlan_ctx, ring->dcb_tc);
+
+	/* PF number */
+	tlan_ctx->pf_num = hw->pf_id;
+
+	err = ice_set_txq_ctx_vmvf(ring, &tlan_ctx->vmvf_type,
+				   &tlan_ctx->vmvf_num);
+	if (err)
+		return err;
 
 	/* make sure the context is associated with the right VSI */
 	if (ring->ch)
@@ -358,22 +386,83 @@ ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf
 	 * 1: Legacy Host Interface
 	 */
 	tlan_ctx->legacy_int = ICE_TX_LEGACY;
+
+	return 0;
 }
 
 /**
- * ice_rx_offset - Return expected offset into page to access data
- * @rx_ring: Ring we are requesting offset of
+ * ice_setup_txtime_ctx - setup a struct ice_txtime_ctx instance
+ * @ring: the tstamp ring to configure
+ * @txtime_ctx: pointer to the Tx time queue context structure to be initialized
  *
- * Returns the offset value for ring into the data buffer.
+ * Return: 0 on success and a negative value on error.
  */
-static unsigned int ice_rx_offset(struct ice_rx_ring *rx_ring)
+static int
+ice_setup_txtime_ctx(const struct ice_tstamp_ring *ring,
+		     struct ice_txtime_ctx *txtime_ctx)
 {
-	if (ice_ring_uses_build_skb(rx_ring))
-		return ICE_SKB_PAD;
+	struct ice_tx_ring *tx_ring = ring->tx_ring;
+	struct ice_vsi *vsi = tx_ring->vsi;
+	struct ice_hw *hw = &vsi->back->hw;
+	int err;
+
+	txtime_ctx->base = ring->dma >> ICE_TXTIME_CTX_BASE_S;
+
+	/* Tx time Queue Length */
+	txtime_ctx->qlen = ring->count;
+	txtime_ctx->txtime_ena_q = 1;
+
+	/* PF number */
+	txtime_ctx->pf_num = hw->pf_id;
+
+	err = ice_set_txq_ctx_vmvf(tx_ring, &txtime_ctx->vmvf_type,
+				   &txtime_ctx->vmvf_num);
+	if (err)
+		return err;
+
+	/* make sure the context is associated with the right VSI */
+	if (tx_ring->ch)
+		txtime_ctx->src_vsi = tx_ring->ch->vsi_num;
+	else
+		txtime_ctx->src_vsi = ice_get_hw_vsi_num(hw, vsi->idx);
+
+	txtime_ctx->ts_res = ICE_TXTIME_CTX_RESOLUTION_128NS;
+	txtime_ctx->drbell_mode_32 = ICE_TXTIME_CTX_DRBELL_MODE_32;
+	txtime_ctx->ts_fetch_prof_id = ICE_TXTIME_CTX_FETCH_PROF_ID_0;
+
 	return 0;
 }
 
 /**
+ * ice_calc_ts_ring_count - calculate the number of Tx time stamp descriptors
+ * @tx_ring: Tx ring to calculate the count for
+ *
+ * Return: the number of Tx time stamp descriptors.
+ */
+u16 ice_calc_ts_ring_count(struct ice_tx_ring *tx_ring)
+{
+	u16 prof = ICE_TXTIME_CTX_FETCH_PROF_ID_0;
+	struct ice_vsi *vsi = tx_ring->vsi;
+	struct ice_hw *hw = &vsi->back->hw;
+	u16 max_fetch_desc = 0, fetch, i;
+	u32 reg;
+
+	for (i = 0; i < ICE_TXTIME_FETCH_PROFILE_CNT; i++) {
+		reg = rd32(hw, E830_GLTXTIME_FETCH_PROFILE(prof, 0));
+		fetch = FIELD_GET(E830_GLTXTIME_FETCH_PROFILE_FETCH_TS_DESC_M,
+				  reg);
+		max_fetch_desc = max(fetch, max_fetch_desc);
+	}
+
+	if (!max_fetch_desc)
+		max_fetch_desc = ICE_TXTIME_FETCH_TS_DESC_DFLT;
+
+	max_fetch_desc = ALIGN(max_fetch_desc, ICE_REQ_DESC_MULTIPLE);
+
+	return tx_ring->count + max_fetch_desc;
+}
+
+/**
  * ice_setup_rx_ctx - Configure a receive ring context
  * @ring: The Rx ring to configure
  *
@@ -435,8 +524,29 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring)
 	else
 		rlan_ctx.l2tsel = 1;
 
-	rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT;
-	rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT;
+	if (ring->hdr_pp) {
+		rlan_ctx.hbuf = ring->rx_hdr_len >> ICE_RLAN_CTX_HBUF_S;
+		rlan_ctx.dtype = ICE_RX_DTYPE_HEADER_SPLIT;
+
+		/*
+		 * If the frame is TCP/UDP/SCTP, it will be split by the
+		 * payload.
+		 * If not, but it's an IPv4/IPv6 frame, it will be split by
+		 * the IP header.
+		 * If not IP, it will be split by the Ethernet header.
+		 *
+		 * In any case, the header buffer will never be left empty.
+		 */
+		rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_SPLIT_L2 |
+				    ICE_RLAN_RX_HSPLIT_0_SPLIT_IP |
+				    ICE_RLAN_RX_HSPLIT_0_SPLIT_TCP_UDP |
+				    ICE_RLAN_RX_HSPLIT_0_SPLIT_SCTP;
+	} else {
+		rlan_ctx.hbuf = 0;
+		rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT;
+		rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT;
+	}
+
 	rlan_ctx.hsplit_1 = ICE_RLAN_RX_HSPLIT_1_NO_SPLIT;
 
 	/* This controls whether VLAN is stripped from inner headers
@@ -448,7 +558,7 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring)
 	/* Max packet size for this queue - must not be set to a larger value
 	 * than 5 x DBUF
 	 */
-	rlan_ctx.rxmax = min_t(u32, ring->max_frame,
+	rlan_ctx.rxmax = min_t(u32, vsi->max_frame,
 			       ICE_MAX_CHAINED_RX_BUFS * ring->rx_buf_len);
 
 	/* Rx queue threshold in units of 64 */
@@ -473,9 +583,6 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring)
 	 */
 	if (vsi->type != ICE_VSI_VF)
 		ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3, true);
-	else
-		ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3,
-					false);
 
 	/* Absolute queue number out of 2K needs to be passed */
 	err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q);
@@ -488,14 +595,6 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring)
 	if (vsi->type == ICE_VSI_VF)
 		return 0;
 
-	/* configure Rx buffer alignment */
-	if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags))
-		ice_clear_ring_build_skb_ena(ring);
-	else
-		ice_set_ring_build_skb_ena(ring);
-
-	ring->rx_offset = ice_rx_offset(ring);
-
 	/* init queue specific tail register */
 	ring->tail = hw->hw_addr + QRX_TAIL(pf_q);
 	writel(0, ring->tail);
@@ -503,36 +602,51 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring)
 	return 0;
 }
 
-static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring)
+static int ice_rxq_pp_create(struct ice_rx_ring *rq)
 {
-	void *ctx_ptr = &ring->pkt_ctx;
-	struct xsk_cb_desc desc = {};
-
-	XSK_CHECK_PRIV_TYPE(struct ice_xdp_buff);
-	desc.src = &ctx_ptr;
-	desc.off = offsetof(struct ice_xdp_buff, pkt_ctx) -
-		   sizeof(struct xdp_buff);
-	desc.bytes = sizeof(ctx_ptr);
-	xsk_pool_fill_cb(ring->xsk_pool, &desc);
-}
+	struct libeth_fq fq = {
+		.count		= rq->count,
+		.nid		= NUMA_NO_NODE,
+		.hsplit		= rq->vsi->hsplit,
+		.xdp		= ice_is_xdp_ena_vsi(rq->vsi),
+		.buf_len	= LIBIE_MAX_RX_BUF_LEN,
+	};
+	int err;
 
-/**
- * ice_get_frame_sz - calculate xdp_buff::frame_sz
- * @rx_ring: the ring being configured
- *
- * Return frame size based on underlying PAGE_SIZE
- */
-static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring)
-{
-	unsigned int frame_sz;
+	err = libeth_rx_fq_create(&fq, &rq->q_vector->napi);
+	if (err)
+		return err;
+
+	rq->pp = fq.pp;
+	rq->rx_fqes = fq.fqes;
+	rq->truesize = fq.truesize;
+	rq->rx_buf_len = fq.buf_len;
+
+	if (!fq.hsplit)
+		return 0;
+
+	fq = (struct libeth_fq){
+		.count		= rq->count,
+		.type		= LIBETH_FQE_HDR,
+		.nid		= NUMA_NO_NODE,
+		.xdp		= ice_is_xdp_ena_vsi(rq->vsi),
+	};
 
-#if (PAGE_SIZE >= 8192)
-	frame_sz = rx_ring->rx_buf_len;
-#else
-	frame_sz = ice_rx_pg_size(rx_ring) / 2;
-#endif
+	err = libeth_rx_fq_create(&fq, &rq->q_vector->napi);
+	if (err)
+		goto destroy;
 
-	return frame_sz;
+	rq->hdr_pp = fq.pp;
+	rq->hdr_fqes = fq.fqes;
+	rq->hdr_truesize = fq.truesize;
+	rq->rx_hdr_len = fq.buf_len;
+
+	return 0;
+
+destroy:
+	ice_rxq_pp_destroy(rq);
+
+	return err;
 }
 
 /**
@@ -544,7 +658,8 @@ static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring)
 static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 {
 	struct device *dev = ice_pf_to_dev(ring->vsi->back);
-	u32 num_bufs = ICE_RX_DESC_UNUSED(ring);
+	u32 num_bufs = ICE_DESC_UNUSED(ring);
+	u32 rx_buf_len;
 	int err;
 
 	if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF) {
@@ -558,15 +673,19 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 		}
 
 		ice_rx_xsk_pool(ring);
+		err = ice_realloc_rx_xdp_bufs(ring, ring->xsk_pool);
+		if (err)
+			return err;
+
 		if (ring->xsk_pool) {
 			xdp_rxq_info_unreg(&ring->xdp_rxq);
 
-			ring->rx_buf_len =
+			rx_buf_len =
 				xsk_pool_get_rx_frame_size(ring->xsk_pool);
 			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 						 ring->q_index,
 						 ring->q_vector->napi.napi_id,
-						 ring->rx_buf_len);
+						 rx_buf_len);
 			if (err)
 				return err;
 			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
@@ -575,36 +694,33 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			if (err)
 				return err;
 			xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
-			ice_xsk_pool_fill_cb(ring);
 
 			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 				 ring->q_index);
 		} else {
+			err = ice_rxq_pp_create(ring);
+			if (err)
+				return err;
+
 			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
 				err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 							 ring->q_index,
 							 ring->q_vector->napi.napi_id,
 							 ring->rx_buf_len);
 				if (err)
-					return err;
+					goto err_destroy_fq;
 			}
-
-			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-							 MEM_TYPE_PAGE_SHARED,
-							 NULL);
-			if (err)
-				return err;
+			xdp_rxq_info_attach_page_pool(&ring->xdp_rxq,
+						      ring->pp);
 		}
 	}
 
-	xdp_init_buff(&ring->xdp, ice_get_frame_sz(ring), &ring->xdp_rxq);
 	ring->xdp.data = NULL;
-	ring->xdp_ext.pkt_ctx = &ring->pkt_ctx;
 	err = ice_setup_rx_ctx(ring);
 	if (err) {
 		dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n",
 			ring->q_index, err);
-		return err;
+		goto err_destroy_fq;
 	}
 
 	if (ring->xsk_pool) {
@@ -629,9 +745,20 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 		return 0;
 	}
 
-	ice_alloc_rx_bufs(ring, num_bufs);
+	if (ring->vsi->type == ICE_VSI_CTRL)
+		ice_init_ctrl_rx_descs(ring, num_bufs);
+	else
+		err = ice_alloc_rx_bufs(ring, num_bufs);
+
+	if (err)
+		goto err_destroy_fq;
 
 	return 0;
+
+err_destroy_fq:
+	ice_rxq_pp_destroy(ring);
+
+	return err;
 }
 
 int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx)
@@ -652,18 +779,10 @@ int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx)
  */
 static void ice_vsi_cfg_frame_size(struct ice_vsi *vsi, struct ice_rx_ring *ring)
 {
-	if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) {
-		ring->max_frame = ICE_MAX_FRAME_LEGACY_RX;
-		ring->rx_buf_len = ICE_RXBUF_1664;
-#if (PAGE_SIZE < 8192)
-	} else if (!ICE_2K_TOO_SMALL_WITH_PADDING &&
-		   (vsi->netdev->mtu <= ETH_DATA_LEN)) {
-		ring->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN;
-		ring->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN;
-#endif
+	if (!vsi->netdev) {
+		vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX;
 	} else {
-		ring->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX;
-		ring->rx_buf_len = ICE_RXBUF_3072;
+		vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX;
 	}
 }
 
@@ -801,13 +920,11 @@ int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
 	return 0;
 
 err_out:
-	while (v_idx--)
-		ice_free_q_vector(vsi, v_idx);
 
-	dev_err(dev, "Failed to allocate %d q_vector for VSI %d, ret=%d\n",
-		vsi->num_q_vectors, vsi->vsi_num, err);
-	vsi->num_q_vectors = 0;
-	return err;
+	dev_info(dev, "Failed to allocate %d q_vectors for VSI %d, new value %d",
+		 vsi->num_q_vectors, vsi->vsi_num, v_idx);
+	vsi->num_q_vectors = v_idx;
+	return v_idx ? 0 : err;
 }
 
 /**
@@ -887,13 +1004,49 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_cfg_tstamp - Configure Tx time stamp queue
+ * @tx_ring: Tx ring to be configured with timestamping
+ *
+ * Return: 0 on success and a negative value on error.
+ */
+static int
+ice_cfg_tstamp(struct ice_tx_ring *tx_ring)
+{
+	DEFINE_RAW_FLEX(struct ice_aqc_set_txtime_qgrp, txtime_qg_buf,
+			txtimeqs, 1);
+	u8 txtime_buf_len = struct_size(txtime_qg_buf, txtimeqs, 1);
+	struct ice_tstamp_ring *tstamp_ring = tx_ring->tstamp_ring;
+	struct ice_txtime_ctx txtime_ctx = {};
+	struct ice_vsi *vsi = tx_ring->vsi;
+	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+	u16 pf_q = tx_ring->reg_idx;
+	int err;
+
+	err = ice_setup_txtime_ctx(tstamp_ring, &txtime_ctx);
+	if (err) {
+		dev_err(ice_pf_to_dev(pf), "Failed to setup Tx time queue context for queue %d, error: %d\n",
+			pf_q, err);
+		return err;
+	}
+	ice_pack_txtime_ctx(&txtime_ctx,
+			    &txtime_qg_buf->txtimeqs[0].txtime_ctx);
+
+	tstamp_ring->tail = hw->hw_addr + E830_GLQTX_TXTIME_DBELL_LSB(pf_q);
+	return ice_aq_set_txtimeq(hw, pf_q, 1, txtime_qg_buf,
+				  txtime_buf_len, NULL);
+}
+
+/**
  * ice_vsi_cfg_txq - Configure single Tx queue
  * @vsi: the VSI that queue belongs to
  * @ring: Tx ring to be configured
  * @qg_buf: queue group buffer
+ *
+ * Return: 0 on success and a negative value on error.
  */
 static int
-ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring,
+ice_vsi_cfg_txq(const struct ice_vsi *vsi, struct ice_tx_ring *ring,
 		struct ice_aqc_add_tx_qgrp *qg_buf)
 {
 	u8 buf_len = struct_size(qg_buf, txqs, 1);
@@ -902,15 +1055,20 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring,
 	struct ice_channel *ch = ring->ch;
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
+	u32 pf_q, vsi_idx;
 	int status;
-	u16 pf_q;
 	u8 tc;
 
 	/* Configure XPS */
 	ice_cfg_xps_tx_ring(ring);
 
 	pf_q = ring->reg_idx;
-	ice_setup_tx_ctx(ring, &tlan_ctx, pf_q);
+	status = ice_setup_tx_ctx(ring, &tlan_ctx, pf_q);
+	if (status) {
+		dev_err(ice_pf_to_dev(pf), "Failed to setup Tx context for queue %d, error: %d\n",
+			pf_q, status);
+		return status;
+	}
 	/* copy context contents into the qg_buf */
 	qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q);
 	ice_pack_txq_ctx(&tlan_ctx, &qg_buf->txqs[0].txq_ctx);
@@ -930,14 +1088,15 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring,
 	 */
 	ring->q_handle = ice_calc_txq_handle(vsi, ring, tc);
 
-	if (ch)
-		status = ice_ena_vsi_txq(vsi->port_info, ch->ch_vsi->idx, 0,
-					 ring->q_handle, 1, qg_buf, buf_len,
-					 NULL);
-	else
-		status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc,
-					 ring->q_handle, 1, qg_buf, buf_len,
-					 NULL);
+	if (ch) {
+		tc = 0;
+		vsi_idx = ch->ch_vsi->idx;
+	} else {
+		vsi_idx = vsi->idx;
+	}
+
+	status = ice_ena_vsi_txq(vsi->port_info, vsi_idx, tc, ring->q_handle,
+				 1, qg_buf, buf_len, NULL);
 	if (status) {
 		dev_err(ice_pf_to_dev(pf), "Failed to set LAN Tx queue context, error: %d\n",
 			status);
@@ -952,7 +1111,32 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring,
 	if (pf_q == le16_to_cpu(txq->txq_id))
 		ring->txq_teid = le32_to_cpu(txq->q_teid);
 
+	if (ice_is_txtime_ena(ring)) {
+		status = ice_alloc_setup_tstamp_ring(ring);
+		if (status) {
+			dev_err(ice_pf_to_dev(pf),
+				"Failed to allocate Tx timestamp ring, error: %d\n",
+				status);
+			goto err_setup_tstamp;
+		}
+
+		status = ice_cfg_tstamp(ring);
+		if (status) {
+			dev_err(ice_pf_to_dev(pf), "Failed to set Tx Time queue context, error: %d\n",
+				status);
+			goto err_cfg_tstamp;
+		}
+	}
 	return 0;
+
+err_cfg_tstamp:
+	ice_free_tx_tstamp_ring(ring);
+err_setup_tstamp:
+	ice_dis_vsi_txq(vsi->port_info, vsi_idx, tc, 1, &ring->q_handle,
+			&ring->reg_idx, &ring->txq_teid, ICE_NO_RESET,
+			tlan_ctx.vmvf_num, NULL);
+
+	return status;
 }
 
 int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings,
@@ -1211,3 +1395,148 @@ ice_fill_txq_meta(const struct ice_vsi *vsi, struct ice_tx_ring *ring,
 		txq_meta->tc = tc;
 	}
 }
+
+/**
+ * ice_qp_reset_stats - Resets all stats for rings of given index
+ * @vsi: VSI that contains rings of interest
+ * @q_idx: ring index in array
+ */
+static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
+{
+	struct ice_vsi_stats *vsi_stat;
+	struct ice_pf *pf;
+
+	pf = vsi->back;
+	if (!pf->vsi_stats)
+		return;
+
+	vsi_stat = pf->vsi_stats[vsi->idx];
+	if (!vsi_stat)
+		return;
+
+	memset(&vsi_stat->rx_ring_stats[q_idx]->rx_stats, 0,
+	       sizeof(vsi_stat->rx_ring_stats[q_idx]->rx_stats));
+	memset(&vsi_stat->tx_ring_stats[q_idx]->stats, 0,
+	       sizeof(vsi_stat->tx_ring_stats[q_idx]->stats));
+	if (vsi->xdp_rings)
+		memset(&vsi->xdp_rings[q_idx]->ring_stats->stats, 0,
+		       sizeof(vsi->xdp_rings[q_idx]->ring_stats->stats));
+}
+
+/**
+ * ice_qp_clean_rings - Cleans all the rings of a given index
+ * @vsi: VSI that contains rings of interest
+ * @q_idx: ring index in array
+ */
+static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
+{
+	ice_clean_tx_ring(vsi->tx_rings[q_idx]);
+	if (vsi->xdp_rings)
+		ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
+	ice_clean_rx_ring(vsi->rx_rings[q_idx]);
+}
+
+/**
+ * ice_qp_dis - Disables a queue pair
+ * @vsi: VSI of interest
+ * @q_idx: ring index in array
+ *
+ * Returns 0 on success, negative on failure.
+ */
+int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
+{
+	struct ice_txq_meta txq_meta = { };
+	struct ice_q_vector *q_vector;
+	struct ice_tx_ring *tx_ring;
+	struct ice_rx_ring *rx_ring;
+	int fail = 0;
+	int err;
+
+	if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq)
+		return -EINVAL;
+
+	tx_ring = vsi->tx_rings[q_idx];
+	rx_ring = vsi->rx_rings[q_idx];
+	q_vector = rx_ring->q_vector;
+
+	synchronize_net();
+	netif_carrier_off(vsi->netdev);
+	netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+
+	ice_qvec_dis_irq(vsi, rx_ring, q_vector);
+	ice_qvec_toggle_napi(vsi, q_vector, false);
+
+	ice_fill_txq_meta(vsi, tx_ring, &txq_meta);
+	err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta);
+	if (!fail)
+		fail = err;
+	if (vsi->xdp_rings) {
+		struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
+
+		memset(&txq_meta, 0, sizeof(txq_meta));
+		ice_fill_txq_meta(vsi, xdp_ring, &txq_meta);
+		err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, xdp_ring,
+					   &txq_meta);
+		if (!fail)
+			fail = err;
+	}
+
+	ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, false);
+	ice_qp_clean_rings(vsi, q_idx);
+	ice_qp_reset_stats(vsi, q_idx);
+
+	return fail;
+}
+
+/**
+ * ice_qp_ena - Enables a queue pair
+ * @vsi: VSI of interest
+ * @q_idx: ring index in array
+ *
+ * Returns 0 on success, negative on failure.
+ */
+int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
+{
+	struct ice_q_vector *q_vector;
+	int fail = 0;
+	bool link_up;
+	int err;
+
+	err = ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx);
+	if (!fail)
+		fail = err;
+
+	if (ice_is_xdp_ena_vsi(vsi)) {
+		struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
+
+		err = ice_vsi_cfg_single_txq(vsi, vsi->xdp_rings, q_idx);
+		if (!fail)
+			fail = err;
+		ice_set_ring_xdp(xdp_ring);
+		ice_tx_xsk_pool(vsi, q_idx);
+	}
+
+	err = ice_vsi_cfg_single_rxq(vsi, q_idx);
+	if (!fail)
+		fail = err;
+
+	q_vector = vsi->rx_rings[q_idx]->q_vector;
+	ice_qvec_cfg_msix(vsi, q_vector, q_idx);
+
+	err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true);
+	if (!fail)
+		fail = err;
+
+	ice_qvec_toggle_napi(vsi, q_vector, true);
+	ice_qvec_ena_irq(vsi, q_vector);
+
+	/* make sure NAPI sees updated ice_{t,x}_ring::xsk_pool */
+	synchronize_net();
+	ice_get_link_status(vsi->port_info, &link_up);
+	if (link_up) {
+		netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+		netif_carrier_on(vsi->netdev);
+	}
+
+	return fail;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_base.h b/drivers/net/ethernet/intel/ice/ice_base.h
index b711bc921928..d28294247599 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.h
+++ b/drivers/net/ethernet/intel/ice/ice_base.h
@@ -32,4 +32,7 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 void
 ice_fill_txq_meta(const struct ice_vsi *vsi, struct ice_tx_ring *ring,
 		  struct ice_txq_meta *txq_meta);
+int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx);
+int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx);
+u16 ice_calc_ts_ring_count(struct ice_tx_ring *tx_ring);
 #endif /* _ICE_BASE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_cgu_regs.h b/drivers/net/ethernet/intel/ice/ice_cgu_regs.h
deleted file mode 100644
index 10d9d74f3545..000000000000
--- a/drivers/net/ethernet/intel/ice/ice_cgu_regs.h
+++ /dev/null
@@ -1,181 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2018-2021, Intel Corporation. */
-
-#ifndef _ICE_CGU_REGS_H_
-#define _ICE_CGU_REGS_H_
-
-#define NAC_CGU_DWORD9 0x24
-union nac_cgu_dword9 {
-	struct {
-		u32 time_ref_freq_sel : 3;
-		u32 clk_eref1_en : 1;
-		u32 clk_eref0_en : 1;
-		u32 time_ref_en : 1;
-		u32 time_sync_en : 1;
-		u32 one_pps_out_en : 1;
-		u32 clk_ref_synce_en : 1;
-		u32 clk_synce1_en : 1;
-		u32 clk_synce0_en : 1;
-		u32 net_clk_ref1_en : 1;
-		u32 net_clk_ref0_en : 1;
-		u32 clk_synce1_amp : 2;
-		u32 misc6 : 1;
-		u32 clk_synce0_amp : 2;
-		u32 one_pps_out_amp : 2;
-		u32 misc24 : 12;
-	};
-	u32 val;
-};
-
-#define NAC_CGU_DWORD16_E825C 0x40
-union nac_cgu_dword16_e825c {
-	struct {
-		u32 synce_remndr : 6;
-		u32 synce_phlmt_en : 1;
-		u32 misc13 : 17;
-		u32 tspll_ck_refclkfreq : 8;
-	};
-	u32 val;
-};
-
-#define NAC_CGU_DWORD19 0x4c
-union nac_cgu_dword19 {
-	struct {
-		u32 tspll_fbdiv_intgr : 8;
-		u32 fdpll_ulck_thr : 5;
-		u32 misc15 : 3;
-		u32 tspll_ndivratio : 4;
-		u32 tspll_iref_ndivratio : 3;
-		u32 misc19 : 1;
-		u32 japll_ndivratio : 4;
-		u32 japll_iref_ndivratio : 3;
-		u32 misc27 : 1;
-	};
-	u32 val;
-};
-
-#define NAC_CGU_DWORD22 0x58
-union nac_cgu_dword22 {
-	struct {
-		u32 fdpll_frac_div_out_nc : 2;
-		u32 fdpll_lock_int_for : 1;
-		u32 synce_hdov_int_for : 1;
-		u32 synce_lock_int_for : 1;
-		u32 fdpll_phlead_slip_nc : 1;
-		u32 fdpll_acc1_ovfl_nc : 1;
-		u32 fdpll_acc2_ovfl_nc : 1;
-		u32 synce_status_nc : 6;
-		u32 fdpll_acc1f_ovfl : 1;
-		u32 misc18 : 1;
-		u32 fdpllclk_div : 4;
-		u32 time1588clk_div : 4;
-		u32 synceclk_div : 4;
-		u32 synceclk_sel_div2 : 1;
-		u32 fdpllclk_sel_div2 : 1;
-		u32 time1588clk_sel_div2 : 1;
-		u32 misc3 : 1;
-	};
-	u32 val;
-};
-
-#define NAC_CGU_DWORD23_E825C 0x5C
-union nac_cgu_dword23_e825c {
-	struct {
-		u32 cgupll_fbdiv_intgr : 10;
-		u32 ux56pll_fbdiv_intgr : 10;
-		u32 misc20 : 4;
-		u32 ts_pll_enable : 1;
-		u32 time_sync_tspll_align_sel : 1;
-		u32 ext_synce_sel : 1;
-		u32 ref1588_ck_div : 4;
-		u32 time_ref_sel : 1;
-
-	};
-	u32 val;
-};
-
-#define NAC_CGU_DWORD24 0x60
-union nac_cgu_dword24 {
-	struct {
-		u32 tspll_fbdiv_frac : 22;
-		u32 misc20 : 2;
-		u32 ts_pll_enable : 1;
-		u32 time_sync_tspll_align_sel : 1;
-		u32 ext_synce_sel : 1;
-		u32 ref1588_ck_div : 4;
-		u32 time_ref_sel : 1;
-	};
-	u32 val;
-};
-
-#define TSPLL_CNTR_BIST_SETTINGS 0x344
-union tspll_cntr_bist_settings {
-	struct {
-		u32 i_irefgen_settling_time_cntr_7_0 : 8;
-		u32 i_irefgen_settling_time_ro_standby_1_0 : 2;
-		u32 reserved195 : 5;
-		u32 i_plllock_sel_0 : 1;
-		u32 i_plllock_sel_1 : 1;
-		u32 i_plllock_cnt_6_0 : 7;
-		u32 i_plllock_cnt_10_7 : 4;
-		u32 reserved200 : 4;
-	};
-	u32 val;
-};
-
-#define TSPLL_RO_BWM_LF 0x370
-union tspll_ro_bwm_lf {
-	struct {
-		u32 bw_freqov_high_cri_7_0 : 8;
-		u32 bw_freqov_high_cri_9_8 : 2;
-		u32 biascaldone_cri : 1;
-		u32 plllock_gain_tran_cri : 1;
-		u32 plllock_true_lock_cri : 1;
-		u32 pllunlock_flag_cri : 1;
-		u32 afcerr_cri : 1;
-		u32 afcdone_cri : 1;
-		u32 feedfwrdgain_cal_cri_7_0 : 8;
-		u32 m2fbdivmod_cri_7_0 : 8;
-	};
-	u32 val;
-};
-
-#define TSPLL_RO_LOCK_E825C 0x3f0
-union tspll_ro_lock_e825c {
-	struct {
-		u32 bw_freqov_high_cri_7_0 : 8;
-		u32 bw_freqov_high_cri_9_8 : 2;
-		u32 reserved455 : 1;
-		u32 plllock_gain_tran_cri : 1;
-		u32 plllock_true_lock_cri : 1;
-		u32 pllunlock_flag_cri : 1;
-		u32 afcerr_cri : 1;
-		u32 afcdone_cri : 1;
-		u32 feedfwrdgain_cal_cri_7_0 : 8;
-		u32 reserved462 : 8;
-	};
-	u32 val;
-};
-
-#define TSPLL_BW_TDC_E825C 0x31c
-union tspll_bw_tdc_e825c {
-	struct {
-		u32 i_tdc_offset_lock_1_0 : 2;
-		u32 i_bbthresh1_2_0 : 3;
-		u32 i_bbthresh2_2_0 : 3;
-		u32 i_tdcsel_1_0 : 2;
-		u32 i_tdcovccorr_en_h : 1;
-		u32 i_divretimeren : 1;
-		u32 i_bw_ampmeas_window : 1;
-		u32 i_bw_lowerbound_2_0 : 3;
-		u32 i_bw_upperbound_2_0 : 3;
-		u32 i_bw_mode_1_0 : 2;
-		u32 i_ft_mode_sel_2_0 : 3;
-		u32 i_bwphase_4_0 : 5;
-		u32 i_plllock_sel_1_0 : 2;
-		u32 i_afc_divratio : 1;
-	};
-	u32 val;
-};
-
-#endif /* _ICE_CGU_REGS_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index f89bc6ede315..046bc9c65c51 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -171,6 +171,15 @@ static int ice_set_mac_type(struct ice_hw *hw)
 	case ICE_DEV_ID_E830_XXV_QSFP:
 	case ICE_DEV_ID_E830C_SFP:
 	case ICE_DEV_ID_E830_XXV_SFP:
+	case ICE_DEV_ID_E835CC_BACKPLANE:
+	case ICE_DEV_ID_E835CC_QSFP56:
+	case ICE_DEV_ID_E835CC_SFP:
+	case ICE_DEV_ID_E835C_BACKPLANE:
+	case ICE_DEV_ID_E835C_QSFP:
+	case ICE_DEV_ID_E835C_SFP:
+	case ICE_DEV_ID_E835_L_BACKPLANE:
+	case ICE_DEV_ID_E835_L_QSFP:
+	case ICE_DEV_ID_E835_L_SFP:
 		hw->mac_type = ICE_MAC_E830;
 		break;
 	default:
@@ -186,7 +195,7 @@ static int ice_set_mac_type(struct ice_hw *hw)
  * ice_is_generic_mac - check if device's mac_type is generic
  * @hw: pointer to the hardware structure
  *
- * Return: true if mac_type is generic (with SBQ support), false if not
+ * Return: true if mac_type is ICE_MAC_GENERIC*, false otherwise.
  */
 bool ice_is_generic_mac(struct ice_hw *hw)
 {
@@ -195,117 +204,39 @@ bool ice_is_generic_mac(struct ice_hw *hw)
 }
 
 /**
- * ice_is_e810
- * @hw: pointer to the hardware structure
- *
- * returns true if the device is E810 based, false if not.
- */
-bool ice_is_e810(struct ice_hw *hw)
-{
-	return hw->mac_type == ICE_MAC_E810;
-}
-
-/**
- * ice_is_e810t
- * @hw: pointer to the hardware structure
+ * ice_is_pf_c827 - check if pf contains c827 phy
+ * @hw: pointer to the hw struct
  *
- * returns true if the device is E810T based, false if not.
+ * Return: true if the device has c827 phy.
  */
-bool ice_is_e810t(struct ice_hw *hw)
+static bool ice_is_pf_c827(struct ice_hw *hw)
 {
-	switch (hw->device_id) {
-	case ICE_DEV_ID_E810C_SFP:
-		switch (hw->subsystem_device_id) {
-		case ICE_SUBDEV_ID_E810T:
-		case ICE_SUBDEV_ID_E810T2:
-		case ICE_SUBDEV_ID_E810T3:
-		case ICE_SUBDEV_ID_E810T4:
-		case ICE_SUBDEV_ID_E810T6:
-		case ICE_SUBDEV_ID_E810T7:
-			return true;
-		}
-		break;
-	case ICE_DEV_ID_E810C_QSFP:
-		switch (hw->subsystem_device_id) {
-		case ICE_SUBDEV_ID_E810T2:
-		case ICE_SUBDEV_ID_E810T3:
-		case ICE_SUBDEV_ID_E810T5:
-			return true;
-		}
-		break;
-	default:
-		break;
-	}
-
-	return false;
-}
+	struct ice_aqc_get_link_topo cmd = {};
+	u8 node_part_number;
+	u16 node_handle;
+	int status;
 
-/**
- * ice_is_e822 - Check if a device is E822 family device
- * @hw: pointer to the hardware structure
- *
- * Return: true if the device is E822 based, false if not.
- */
-bool ice_is_e822(struct ice_hw *hw)
-{
-	switch (hw->device_id) {
-	case ICE_DEV_ID_E822C_BACKPLANE:
-	case ICE_DEV_ID_E822C_QSFP:
-	case ICE_DEV_ID_E822C_SFP:
-	case ICE_DEV_ID_E822C_10G_BASE_T:
-	case ICE_DEV_ID_E822C_SGMII:
-	case ICE_DEV_ID_E822L_BACKPLANE:
-	case ICE_DEV_ID_E822L_SFP:
-	case ICE_DEV_ID_E822L_10G_BASE_T:
-	case ICE_DEV_ID_E822L_SGMII:
-		return true;
-	default:
+	if (hw->mac_type != ICE_MAC_E810)
 		return false;
-	}
-}
 
-/**
- * ice_is_e823
- * @hw: pointer to the hardware structure
- *
- * returns true if the device is E823-L or E823-C based, false if not.
- */
-bool ice_is_e823(struct ice_hw *hw)
-{
-	switch (hw->device_id) {
-	case ICE_DEV_ID_E823L_BACKPLANE:
-	case ICE_DEV_ID_E823L_SFP:
-	case ICE_DEV_ID_E823L_10G_BASE_T:
-	case ICE_DEV_ID_E823L_1GBE:
-	case ICE_DEV_ID_E823L_QSFP:
-	case ICE_DEV_ID_E823C_BACKPLANE:
-	case ICE_DEV_ID_E823C_QSFP:
-	case ICE_DEV_ID_E823C_SFP:
-	case ICE_DEV_ID_E823C_10G_BASE_T:
-	case ICE_DEV_ID_E823C_SGMII:
+	if (hw->device_id != ICE_DEV_ID_E810C_QSFP)
 		return true;
-	default:
+
+	cmd.addr.topo_params.node_type_ctx =
+		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) |
+		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT);
+	cmd.addr.topo_params.index = 0;
+
+	status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number,
+					 &node_handle);
+
+	if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827)
 		return false;
-	}
-}
 
-/**
- * ice_is_e825c - Check if a device is E825C family device
- * @hw: pointer to the hardware structure
- *
- * Return: true if the device is E825-C based, false if not.
- */
-bool ice_is_e825c(struct ice_hw *hw)
-{
-	switch (hw->device_id) {
-	case ICE_DEV_ID_E825C_BACKPLANE:
-	case ICE_DEV_ID_E825C_QSFP:
-	case ICE_DEV_ID_E825C_SFP:
-	case ICE_DEV_ID_E825C_SGMII:
+	if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE)
 		return true;
-	default:
-		return false;
-	}
+
+	return false;
 }
 
 /**
@@ -317,7 +248,7 @@ bool ice_is_e825c(struct ice_hw *hw)
  */
 int ice_clear_pf_cfg(struct ice_hw *hw)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_clear_pf_cfg);
 
@@ -345,12 +276,12 @@ ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size,
 {
 	struct ice_aqc_manage_mac_read_resp *resp;
 	struct ice_aqc_manage_mac_read *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 	u16 flags;
 	u8 i;
 
-	cmd = &desc.params.mac_read;
+	cmd = libie_aq_raw(&desc);
 
 	if (buf_size < sizeof(*resp))
 		return -EINVAL;
@@ -399,12 +330,12 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode,
 {
 	struct ice_aqc_get_phy_caps *cmd;
 	u16 pcaps_size = sizeof(*pcaps);
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	const char *prefix;
 	struct ice_hw *hw;
 	int status;
 
-	cmd = &desc.params.get_phy;
+	cmd = libie_aq_raw(&desc);
 
 	if (!pcaps || (report_mode & ~ICE_AQC_REPORT_MODE_M) || !pi)
 		return -EINVAL;
@@ -493,9 +424,9 @@ ice_aq_get_link_topo_handle(struct ice_port_info *pi, u8 node_type,
 			    struct ice_sq_cd *cd)
 {
 	struct ice_aqc_get_link_topo *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.get_link_topo;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
 
@@ -523,19 +454,20 @@ int
 ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd,
 			u8 *node_part_number, u16 *node_handle)
 {
-	struct ice_aq_desc desc;
+	struct ice_aqc_get_link_topo *resp;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
-	desc.params.get_link_topo = *cmd;
+	resp = libie_aq_raw(&desc);
+	*resp = *cmd;
 
 	if (ice_aq_send_cmd(hw, &desc, NULL, 0, NULL))
 		return -EINTR;
 
 	if (node_handle)
-		*node_handle =
-			le16_to_cpu(desc.params.get_link_topo.addr.handle);
+		*node_handle = le16_to_cpu(resp->addr.handle);
 	if (node_part_number)
-		*node_part_number = desc.params.get_link_topo.node_part_num;
+		*node_part_number = resp->node_part_num;
 
 	return 0;
 }
@@ -758,8 +690,8 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 	struct ice_link_status *li_old, *li;
 	enum ice_media_type *hw_media_type;
 	struct ice_fc_info *hw_fc_info;
+	struct libie_aq_desc desc;
 	bool tx_pause, rx_pause;
-	struct ice_aq_desc desc;
 	struct ice_hw *hw;
 	u16 cmd_flags;
 	int status;
@@ -774,7 +706,7 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_status);
 	cmd_flags = (ena_lse) ? ICE_AQ_LSE_ENA : ICE_AQ_LSE_DIS;
-	resp = &desc.params.get_link_status;
+	resp = libie_aq_raw(&desc);
 	resp->cmd_flags = cpu_to_le16(cmd_flags);
 	resp->lport_num = pi->lport;
 
@@ -903,9 +835,9 @@ int
 ice_aq_set_mac_cfg(struct ice_hw *hw, u16 max_frame_size, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_set_mac_cfg *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.set_mac_cfg;
+	cmd = libie_aq_raw(&desc);
 
 	if (max_frame_size == 0)
 		return -EINVAL;
@@ -1026,6 +958,64 @@ static void ice_get_itr_intrl_gran(struct ice_hw *hw)
 }
 
 /**
+ * ice_wait_for_fw - wait for full FW readiness
+ * @hw: pointer to the hardware structure
+ * @timeout: milliseconds that can elapse before timing out
+ *
+ * Return: 0 on success, -ETIMEDOUT on timeout.
+ */
+static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout)
+{
+	int fw_loading;
+	u32 elapsed = 0;
+
+	while (elapsed <= timeout) {
+		fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M;
+
+		/* firmware was not yet loaded, we have to wait more */
+		if (fw_loading) {
+			elapsed += 100;
+			msleep(100);
+			continue;
+		}
+		return 0;
+	}
+
+	return -ETIMEDOUT;
+}
+
+static int __fwlog_send_cmd(void *priv, struct libie_aq_desc *desc, void *buf,
+			    u16 size)
+{
+	struct ice_hw *hw = priv;
+
+	return ice_aq_send_cmd(hw, desc, buf, size, NULL);
+}
+
+static int __fwlog_init(struct ice_hw *hw)
+{
+	struct ice_pf *pf = hw->back;
+	struct libie_fwlog_api api = {
+		.pdev = pf->pdev,
+		.send_cmd = __fwlog_send_cmd,
+		.priv = hw,
+	};
+	int err;
+
+	/* only support fw log commands on PF 0 */
+	if (hw->bus.func)
+		return -EINVAL;
+
+	err = ice_debugfs_pf_init(pf);
+	if (err)
+		return err;
+
+	api.debugfs_root = pf->ice_debugfs_pf;
+
+	return libie_fwlog_init(&hw->fwlog, &api);
+}
+
+/**
  * ice_init_hw - main hardware initialization routine
  * @hw: pointer to the hardware structure
  */
@@ -1053,7 +1043,7 @@ int ice_init_hw(struct ice_hw *hw)
 	if (status)
 		goto err_unroll_cqinit;
 
-	status = ice_fwlog_init(hw);
+	status = __fwlog_init(hw);
 	if (status)
 		ice_debug(hw, ICE_DBG_FW_LOG, "Error initializing FW logging: %d\n",
 			  status);
@@ -1171,11 +1161,27 @@ int ice_init_hw(struct ice_hw *hw)
 	status = ice_init_hw_tbls(hw);
 	if (status)
 		goto err_unroll_fltr_mgmt_struct;
+
+	ice_init_dev_hw(hw->back);
+
 	mutex_init(&hw->tnl_lock);
 	ice_init_chk_recipe_reuse_support(hw);
 
-	return 0;
+	/* Some cards require longer initialization times
+	 * due to necessity of loading FW from an external source.
+	 * This can take even half a minute.
+	 */
+	if (ice_is_pf_c827(hw)) {
+		status = ice_wait_for_fw(hw, 30000);
+		if (status) {
+			dev_err(ice_hw_to_dev(hw), "ice_wait_for_fw timed out");
+			goto err_unroll_fltr_mgmt_struct;
+		}
+	}
+
+	hw->lane_num = ice_get_phy_lane_number(hw);
 
+	return 0;
 err_unroll_fltr_mgmt_struct:
 	ice_cleanup_fltr_mgmt_struct(hw);
 err_unroll_sched:
@@ -1187,6 +1193,16 @@ err_unroll_cqinit:
 	return status;
 }
 
+static void __fwlog_deinit(struct ice_hw *hw)
+{
+	/* only support fw log commands on PF 0 */
+	if (hw->bus.func)
+		return;
+
+	ice_debugfs_pf_deinit(hw->back);
+	libie_fwlog_deinit(&hw->fwlog);
+}
+
 /**
  * ice_deinit_hw - unroll initialization operations done by ice_init_hw
  * @hw: pointer to the hardware structure
@@ -1205,8 +1221,7 @@ void ice_deinit_hw(struct ice_hw *hw)
 	ice_free_seg(hw);
 	ice_free_hw_tbls(hw);
 	mutex_destroy(&hw->tnl_lock);
-
-	ice_fwlog_deinit(hw);
+	__fwlog_deinit(hw);
 	ice_destroy_all_ctrlq(hw);
 
 	/* Clear VSI contexts if not already cleared */
@@ -1380,6 +1395,26 @@ static void ice_copy_rxq_ctx_to_hw(struct ice_hw *hw,
 	}
 }
 
+/**
+ * ice_copy_rxq_ctx_from_hw - Copy packed Rx Queue context from HW registers
+ * @hw: pointer to the hardware structure
+ * @rxq_ctx: pointer to the packed Rx queue context
+ * @rxq_index: the index of the Rx queue
+ */
+static void ice_copy_rxq_ctx_from_hw(struct ice_hw *hw,
+				     ice_rxq_ctx_buf_t *rxq_ctx,
+				     u32 rxq_index)
+{
+	u32 *ctx = (u32 *)rxq_ctx;
+
+	/* Copy each dword separately from HW */
+	for (int i = 0; i < ICE_RXQ_CTX_SIZE_DWORDS; i++, ctx++) {
+		*ctx = rd32(hw, QRX_CONTEXT(i, rxq_index));
+
+		ice_debug(hw, ICE_DBG_QCTX, "qrxdata[%d]: %08X\n", i, *ctx);
+	}
+}
+
 #define ICE_CTX_STORE(struct_name, struct_field, width, lsb) \
 	PACKED_FIELD((lsb) + (width) - 1, (lsb), struct struct_name, struct_field)
 
@@ -1424,6 +1459,21 @@ static void ice_pack_rxq_ctx(const struct ice_rlan_ctx *ctx,
 }
 
 /**
+ * ice_unpack_rxq_ctx - Unpack Rx queue context from a HW buffer
+ * @buf: the HW buffer to unpack from
+ * @ctx: the Rx queue context to unpack
+ *
+ * Unpack the Rx queue context from the HW buffer into the CPU-friendly
+ * structure.
+ */
+static void ice_unpack_rxq_ctx(const ice_rxq_ctx_buf_t *buf,
+			       struct ice_rlan_ctx *ctx)
+{
+	unpack_fields(buf, sizeof(*buf), ctx, ice_rlan_ctx_fields,
+		      QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST);
+}
+
+/**
  * ice_write_rxq_ctx - Write Rx Queue context to hardware
  * @hw: pointer to the hardware structure
  * @rlan_ctx: pointer to the unpacked Rx queue context
@@ -1448,6 +1498,31 @@ int ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
 	return 0;
 }
 
+/**
+ * ice_read_rxq_ctx - Read Rx queue context from HW
+ * @hw: pointer to the hardware structure
+ * @rlan_ctx: pointer to the Rx queue context
+ * @rxq_index: the index of the Rx queue
+ *
+ * Read the Rx queue context from the hardware registers, and unpack it into
+ * the sparse Rx queue context structure.
+ *
+ * Returns: 0 on success, or -EINVAL if the Rx queue index is invalid.
+ */
+int ice_read_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
+		     u32 rxq_index)
+{
+	ice_rxq_ctx_buf_t buf = {};
+
+	if (rxq_index > QRX_CTRL_MAX_INDEX)
+		return -EINVAL;
+
+	ice_copy_rxq_ctx_from_hw(hw, &buf, rxq_index);
+	ice_unpack_rxq_ctx(&buf, rlan_ctx);
+
+	return 0;
+}
+
 /* LAN Tx Queue Context */
 static const struct packed_field_u8 ice_tlan_ctx_fields[] = {
 				    /* Field			Width	LSB */
@@ -1481,12 +1556,12 @@ static const struct packed_field_u8 ice_tlan_ctx_fields[] = {
 };
 
 /**
- * ice_pack_txq_ctx - Pack Tx queue context into a HW buffer
+ * ice_pack_txq_ctx - Pack Tx queue context into Admin Queue buffer
  * @ctx: the Tx queue context to pack
- * @buf: the HW buffer to pack into
+ * @buf: the Admin Queue HW buffer to pack into
  *
  * Pack the Tx queue context from the CPU-friendly unpacked buffer into its
- * bit-packed HW layout.
+ * bit-packed Admin Queue layout.
  */
 void ice_pack_txq_ctx(const struct ice_tlan_ctx *ctx, ice_txq_ctx_buf_t *buf)
 {
@@ -1494,6 +1569,211 @@ void ice_pack_txq_ctx(const struct ice_tlan_ctx *ctx, ice_txq_ctx_buf_t *buf)
 		    QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST);
 }
 
+/**
+ * ice_pack_txq_ctx_full - Pack Tx queue context into a HW buffer
+ * @ctx: the Tx queue context to pack
+ * @buf: the HW buffer to pack into
+ *
+ * Pack the Tx queue context from the CPU-friendly unpacked buffer into its
+ * bit-packed HW layout, including the internal data portion.
+ */
+static void ice_pack_txq_ctx_full(const struct ice_tlan_ctx *ctx,
+				  ice_txq_ctx_buf_full_t *buf)
+{
+	pack_fields(buf, sizeof(*buf), ctx, ice_tlan_ctx_fields,
+		    QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST);
+}
+
+/**
+ * ice_unpack_txq_ctx_full - Unpack Tx queue context from a HW buffer
+ * @buf: the HW buffer to unpack from
+ * @ctx: the Tx queue context to unpack
+ *
+ * Unpack the Tx queue context from the HW buffer (including the full internal
+ * state) into the CPU-friendly structure.
+ */
+static void ice_unpack_txq_ctx_full(const ice_txq_ctx_buf_full_t *buf,
+				    struct ice_tlan_ctx *ctx)
+{
+	unpack_fields(buf, sizeof(*buf), ctx, ice_tlan_ctx_fields,
+		      QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST);
+}
+
+/**
+ * ice_copy_txq_ctx_from_hw - Copy Tx Queue context from HW registers
+ * @hw: pointer to the hardware structure
+ * @txq_ctx: pointer to the packed Tx queue context, including internal state
+ * @txq_index: the index of the Tx queue
+ *
+ * Copy Tx Queue context from HW register space to dense structure
+ */
+static void ice_copy_txq_ctx_from_hw(struct ice_hw *hw,
+				     ice_txq_ctx_buf_full_t *txq_ctx,
+				     u32 txq_index)
+{
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
+	u32 *ctx = (u32 *)txq_ctx;
+	u32 txq_base, reg;
+
+	/* Get Tx queue base within card space */
+	txq_base = rd32(hw, PFLAN_TX_QALLOC(hw->pf_id));
+	txq_base = FIELD_GET(PFLAN_TX_QALLOC_FIRSTQ_M, txq_base);
+
+	reg = FIELD_PREP(GLCOMM_QTX_CNTX_CTL_CMD_M,
+			 GLCOMM_QTX_CNTX_CTL_CMD_READ) |
+	      FIELD_PREP(GLCOMM_QTX_CNTX_CTL_QUEUE_ID_M,
+			 txq_base + txq_index) |
+	      GLCOMM_QTX_CNTX_CTL_CMD_EXEC_M;
+
+	/* Prevent other PFs on the same adapter from accessing the Tx queue
+	 * context interface concurrently.
+	 */
+	spin_lock(&pf->adapter->txq_ctx_lock);
+
+	wr32(hw, GLCOMM_QTX_CNTX_CTL, reg);
+	ice_flush(hw);
+
+	/* Copy each dword separately from HW */
+	for (int i = 0; i < ICE_TXQ_CTX_FULL_SIZE_DWORDS; i++, ctx++) {
+		*ctx = rd32(hw, GLCOMM_QTX_CNTX_DATA(i));
+
+		ice_debug(hw, ICE_DBG_QCTX, "qtxdata[%d]: %08X\n", i, *ctx);
+	}
+
+	spin_unlock(&pf->adapter->txq_ctx_lock);
+}
+
+/**
+ * ice_copy_txq_ctx_to_hw - Copy Tx Queue context into HW registers
+ * @hw: pointer to the hardware structure
+ * @txq_ctx: pointer to the packed Tx queue context, including internal state
+ * @txq_index: the index of the Tx queue
+ */
+static void ice_copy_txq_ctx_to_hw(struct ice_hw *hw,
+				   const ice_txq_ctx_buf_full_t *txq_ctx,
+				   u32 txq_index)
+{
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
+	u32 txq_base, reg;
+
+	/* Get Tx queue base within card space */
+	txq_base = rd32(hw, PFLAN_TX_QALLOC(hw->pf_id));
+	txq_base = FIELD_GET(PFLAN_TX_QALLOC_FIRSTQ_M, txq_base);
+
+	reg = FIELD_PREP(GLCOMM_QTX_CNTX_CTL_CMD_M,
+			 GLCOMM_QTX_CNTX_CTL_CMD_WRITE_NO_DYN) |
+	      FIELD_PREP(GLCOMM_QTX_CNTX_CTL_QUEUE_ID_M,
+			 txq_base + txq_index) |
+	      GLCOMM_QTX_CNTX_CTL_CMD_EXEC_M;
+
+	/* Prevent other PFs on the same adapter from accessing the Tx queue
+	 * context interface concurrently.
+	 */
+	spin_lock(&pf->adapter->txq_ctx_lock);
+
+	/* Copy each dword separately to HW */
+	for (int i = 0; i < ICE_TXQ_CTX_FULL_SIZE_DWORDS; i++) {
+		u32 ctx = ((const u32 *)txq_ctx)[i];
+
+		wr32(hw, GLCOMM_QTX_CNTX_DATA(i), ctx);
+
+		ice_debug(hw, ICE_DBG_QCTX, "qtxdata[%d]: %08X\n", i, ctx);
+	}
+
+	wr32(hw, GLCOMM_QTX_CNTX_CTL, reg);
+	ice_flush(hw);
+
+	spin_unlock(&pf->adapter->txq_ctx_lock);
+}
+
+/**
+ * ice_read_txq_ctx - Read Tx queue context from HW
+ * @hw: pointer to the hardware structure
+ * @tlan_ctx: pointer to the Tx queue context
+ * @txq_index: the index of the Tx queue
+ *
+ * Read the Tx queue context from the HW registers, then unpack it into the
+ * ice_tlan_ctx structure for use.
+ *
+ * Returns: 0 on success, or -EINVAL on an invalid Tx queue index.
+ */
+int ice_read_txq_ctx(struct ice_hw *hw, struct ice_tlan_ctx *tlan_ctx,
+		     u32 txq_index)
+{
+	ice_txq_ctx_buf_full_t buf = {};
+
+	if (txq_index > QTX_COMM_HEAD_MAX_INDEX)
+		return -EINVAL;
+
+	ice_copy_txq_ctx_from_hw(hw, &buf, txq_index);
+	ice_unpack_txq_ctx_full(&buf, tlan_ctx);
+
+	return 0;
+}
+
+/**
+ * ice_write_txq_ctx - Write Tx queue context to HW
+ * @hw: pointer to the hardware structure
+ * @tlan_ctx: pointer to the Tx queue context
+ * @txq_index: the index of the Tx queue
+ *
+ * Pack the Tx queue context into the dense HW layout, then write it into the
+ * HW registers.
+ *
+ * Returns: 0 on success, or -EINVAL on an invalid Tx queue index.
+ */
+int ice_write_txq_ctx(struct ice_hw *hw, struct ice_tlan_ctx *tlan_ctx,
+		      u32 txq_index)
+{
+	ice_txq_ctx_buf_full_t buf = {};
+
+	if (txq_index > QTX_COMM_HEAD_MAX_INDEX)
+		return -EINVAL;
+
+	ice_pack_txq_ctx_full(tlan_ctx, &buf);
+	ice_copy_txq_ctx_to_hw(hw, &buf, txq_index);
+
+	return 0;
+}
+
+/* Tx time Queue Context */
+static const struct packed_field_u8 ice_txtime_ctx_fields[] = {
+				    /* Field			Width	LSB */
+	ICE_CTX_STORE(ice_txtime_ctx, base,			57,	0),
+	ICE_CTX_STORE(ice_txtime_ctx, pf_num,			3,	57),
+	ICE_CTX_STORE(ice_txtime_ctx, vmvf_num,			10,	60),
+	ICE_CTX_STORE(ice_txtime_ctx, vmvf_type,		2,	70),
+	ICE_CTX_STORE(ice_txtime_ctx, src_vsi,			10,	72),
+	ICE_CTX_STORE(ice_txtime_ctx, cpuid,			8,	82),
+	ICE_CTX_STORE(ice_txtime_ctx, tphrd_desc,		1,	90),
+	ICE_CTX_STORE(ice_txtime_ctx, qlen,			13,	91),
+	ICE_CTX_STORE(ice_txtime_ctx, timer_num,		1,	104),
+	ICE_CTX_STORE(ice_txtime_ctx, txtime_ena_q,		1,	105),
+	ICE_CTX_STORE(ice_txtime_ctx, drbell_mode_32,		1,	106),
+	ICE_CTX_STORE(ice_txtime_ctx, ts_res,			4,	107),
+	ICE_CTX_STORE(ice_txtime_ctx, ts_round_type,		2,	111),
+	ICE_CTX_STORE(ice_txtime_ctx, ts_pacing_slot,		3,	113),
+	ICE_CTX_STORE(ice_txtime_ctx, merging_ena,		1,	116),
+	ICE_CTX_STORE(ice_txtime_ctx, ts_fetch_prof_id,		4,	117),
+	ICE_CTX_STORE(ice_txtime_ctx, ts_fetch_cache_line_aln_thld, 4,	121),
+	ICE_CTX_STORE(ice_txtime_ctx, tx_pipe_delay_mode,	1,	125),
+};
+
+/**
+ * ice_pack_txtime_ctx - pack Tx time queue context into a HW buffer
+ * @ctx: the Tx time queue context to pack
+ * @buf: the HW buffer to pack into
+ *
+ * Pack the Tx time queue context from the CPU-friendly unpacked buffer into
+ * its bit-packed HW layout.
+ */
+void ice_pack_txtime_ctx(const struct ice_txtime_ctx *ctx,
+			 ice_txtime_ctx_buf_t *buf)
+{
+	pack_fields(buf, sizeof(*buf), ctx, ice_txtime_ctx_fields,
+		    QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST);
+}
+
 /* Sideband Queue command wrappers */
 
 /**
@@ -1509,7 +1789,7 @@ ice_sbq_send_cmd(struct ice_hw *hw, struct ice_sbq_cmd_desc *desc,
 		 void *buf, u16 buf_size, struct ice_sq_cd *cd)
 {
 	return ice_sq_send_cmd(hw, ice_get_sbq(hw),
-			       (struct ice_aq_desc *)desc, buf, buf_size, cd);
+			       (struct libie_aq_desc *)desc, buf, buf_size, cd);
 }
 
 /**
@@ -1594,10 +1874,10 @@ static bool ice_should_retry_sq_send_cmd(u16 opcode)
  */
 static int
 ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq,
-		      struct ice_aq_desc *desc, void *buf, u16 buf_size,
+		      struct libie_aq_desc *desc, void *buf, u16 buf_size,
 		      struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc_cpy;
+	struct libie_aq_desc desc_cpy;
 	bool is_cmd_for_retry;
 	u8 idx = 0;
 	u16 opcode;
@@ -1618,7 +1898,7 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		status = ice_sq_send_cmd(hw, cq, desc, buf, buf_size, cd);
 
 		if (!is_cmd_for_retry || !status ||
-		    hw->adminq.sq_last_status != ICE_AQ_RC_EBUSY)
+		    hw->adminq.sq_last_status != LIBIE_AQ_RC_EBUSY)
 			break;
 
 		memcpy(desc, &desc_cpy, sizeof(desc_cpy));
@@ -1641,10 +1921,10 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq,
  * Helper function to send FW Admin Queue commands to the FW Admin Queue.
  */
 int
-ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf,
+ice_aq_send_cmd(struct ice_hw *hw, struct libie_aq_desc *desc, void *buf,
 		u16 buf_size, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_req_res *cmd = &desc->params.res_owner;
+	struct libie_aqc_req_res *cmd = libie_aq_raw(desc);
 	bool lock_acquired = false;
 	int status;
 
@@ -1675,7 +1955,7 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf,
 	case ice_aqc_opc_get_recipe_to_profile:
 		break;
 	case ice_aqc_opc_release_res:
-		if (le16_to_cpu(cmd->res_id) == ICE_AQC_RES_ID_GLBL_LOCK)
+		if (le16_to_cpu(cmd->res_id) == LIBIE_AQC_RES_ID_GLBL_LOCK)
 			break;
 		fallthrough;
 	default:
@@ -1700,8 +1980,8 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf,
  */
 int ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_get_ver *resp;
-	struct ice_aq_desc desc;
+	struct libie_aqc_get_ver *resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	resp = &desc.params.get_ver;
@@ -1737,8 +2017,8 @@ int
 ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv,
 		       struct ice_sq_cd *cd)
 {
-	struct ice_aqc_driver_ver *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aqc_driver_ver *cmd;
+	struct libie_aq_desc desc;
 	u16 len;
 
 	cmd = &desc.params.driver_ver;
@@ -1748,7 +2028,7 @@ ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv,
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_driver_ver);
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 	cmd->major_ver = dv->major_ver;
 	cmd->minor_ver = dv->minor_ver;
 	cmd->build_ver = dv->build_ver;
@@ -1773,9 +2053,9 @@ ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv,
 int ice_aq_q_shutdown(struct ice_hw *hw, bool unloading)
 {
 	struct ice_aqc_q_shutdown *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.q_shutdown;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_q_shutdown);
 
@@ -1816,8 +2096,8 @@ ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res,
 	       enum ice_aq_res_access_type access, u8 sdp_number, u32 *timeout,
 	       struct ice_sq_cd *cd)
 {
-	struct ice_aqc_req_res *cmd_resp;
-	struct ice_aq_desc desc;
+	struct libie_aqc_req_res *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	cmd_resp = &desc.params.res_owner;
@@ -1839,20 +2119,20 @@ ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res,
 	/* Global config lock response utilizes an additional status field.
 	 *
 	 * If the Global config lock resource is held by some other driver, the
-	 * command completes with ICE_AQ_RES_GLBL_IN_PROG in the status field
+	 * command completes with LIBIE_AQ_RES_GLBL_IN_PROG in the status field
 	 * and the timeout field indicates the maximum time the current owner
 	 * of the resource has to free it.
 	 */
 	if (res == ICE_GLOBAL_CFG_LOCK_RES_ID) {
-		if (le16_to_cpu(cmd_resp->status) == ICE_AQ_RES_GLBL_SUCCESS) {
+		if (le16_to_cpu(cmd_resp->status) == LIBIE_AQ_RES_GLBL_SUCCESS) {
 			*timeout = le32_to_cpu(cmd_resp->timeout);
 			return 0;
 		} else if (le16_to_cpu(cmd_resp->status) ==
-			   ICE_AQ_RES_GLBL_IN_PROG) {
+			   LIBIE_AQ_RES_GLBL_IN_PROG) {
 			*timeout = le32_to_cpu(cmd_resp->timeout);
 			return -EIO;
 		} else if (le16_to_cpu(cmd_resp->status) ==
-			   ICE_AQ_RES_GLBL_DONE) {
+			   LIBIE_AQ_RES_GLBL_DONE) {
 			return -EALREADY;
 		}
 
@@ -1865,7 +2145,7 @@ ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res,
 	 * with a busy return value and the timeout field indicates the maximum
 	 * time the current owner of the resource has to free it.
 	 */
-	if (!status || hw->adminq.sq_last_status == ICE_AQ_RC_EBUSY)
+	if (!status || hw->adminq.sq_last_status == LIBIE_AQ_RC_EBUSY)
 		*timeout = le32_to_cpu(cmd_resp->timeout);
 
 	return status;
@@ -1884,8 +2164,8 @@ static int
 ice_aq_release_res(struct ice_hw *hw, enum ice_aq_res_ids res, u8 sdp_number,
 		   struct ice_sq_cd *cd)
 {
-	struct ice_aqc_req_res *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aqc_req_res *cmd;
+	struct libie_aq_desc desc;
 
 	cmd = &desc.params.res_owner;
 
@@ -1994,16 +2274,16 @@ int ice_aq_alloc_free_res(struct ice_hw *hw,
 			  enum ice_adminq_opc opc)
 {
 	struct ice_aqc_alloc_free_res_cmd *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.sw_res_ctrl;
+	cmd = libie_aq_raw(&desc);
 
 	if (!buf || buf_size < flex_array_size(buf, elem, 1))
 		return -EINVAL;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, opc);
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	cmd->num_entries = cpu_to_le16(1);
 
@@ -2117,7 +2397,7 @@ static u32 ice_get_num_per_func(struct ice_hw *hw, u32 max)
  */
 static bool
 ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
-		      struct ice_aqc_list_caps_elem *elem, const char *prefix)
+		      struct libie_aqc_list_caps_elem *elem, const char *prefix)
 {
 	u32 logical_id = le32_to_cpu(elem->logical_id);
 	u32 phys_id = le32_to_cpu(elem->phys_id);
@@ -2126,17 +2406,17 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 	bool found = true;
 
 	switch (cap) {
-	case ICE_AQC_CAPS_VALID_FUNCTIONS:
+	case LIBIE_AQC_CAPS_VALID_FUNCTIONS:
 		caps->valid_functions = number;
 		ice_debug(hw, ICE_DBG_INIT, "%s: valid_functions (bitmap) = %d\n", prefix,
 			  caps->valid_functions);
 		break;
-	case ICE_AQC_CAPS_SRIOV:
+	case LIBIE_AQC_CAPS_SRIOV:
 		caps->sr_iov_1_1 = (number == 1);
 		ice_debug(hw, ICE_DBG_INIT, "%s: sr_iov_1_1 = %d\n", prefix,
 			  caps->sr_iov_1_1);
 		break;
-	case ICE_AQC_CAPS_DCB:
+	case LIBIE_AQC_CAPS_DCB:
 		caps->dcb = (number == 1);
 		caps->active_tc_bitmap = logical_id;
 		caps->maxtc = phys_id;
@@ -2145,7 +2425,7 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 			  caps->active_tc_bitmap);
 		ice_debug(hw, ICE_DBG_INIT, "%s: maxtc = %d\n", prefix, caps->maxtc);
 		break;
-	case ICE_AQC_CAPS_RSS:
+	case LIBIE_AQC_CAPS_RSS:
 		caps->rss_table_size = number;
 		caps->rss_table_entry_width = logical_id;
 		ice_debug(hw, ICE_DBG_INIT, "%s: rss_table_size = %d\n", prefix,
@@ -2153,7 +2433,7 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 		ice_debug(hw, ICE_DBG_INIT, "%s: rss_table_entry_width = %d\n", prefix,
 			  caps->rss_table_entry_width);
 		break;
-	case ICE_AQC_CAPS_RXQS:
+	case LIBIE_AQC_CAPS_RXQS:
 		caps->num_rxq = number;
 		caps->rxq_first_id = phys_id;
 		ice_debug(hw, ICE_DBG_INIT, "%s: num_rxq = %d\n", prefix,
@@ -2161,7 +2441,7 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 		ice_debug(hw, ICE_DBG_INIT, "%s: rxq_first_id = %d\n", prefix,
 			  caps->rxq_first_id);
 		break;
-	case ICE_AQC_CAPS_TXQS:
+	case LIBIE_AQC_CAPS_TXQS:
 		caps->num_txq = number;
 		caps->txq_first_id = phys_id;
 		ice_debug(hw, ICE_DBG_INIT, "%s: num_txq = %d\n", prefix,
@@ -2169,7 +2449,7 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 		ice_debug(hw, ICE_DBG_INIT, "%s: txq_first_id = %d\n", prefix,
 			  caps->txq_first_id);
 		break;
-	case ICE_AQC_CAPS_MSIX:
+	case LIBIE_AQC_CAPS_MSIX:
 		caps->num_msix_vectors = number;
 		caps->msix_vector_first_id = phys_id;
 		ice_debug(hw, ICE_DBG_INIT, "%s: num_msix_vectors = %d\n", prefix,
@@ -2177,55 +2457,59 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 		ice_debug(hw, ICE_DBG_INIT, "%s: msix_vector_first_id = %d\n", prefix,
 			  caps->msix_vector_first_id);
 		break;
-	case ICE_AQC_CAPS_PENDING_NVM_VER:
+	case LIBIE_AQC_CAPS_PENDING_NVM_VER:
 		caps->nvm_update_pending_nvm = true;
 		ice_debug(hw, ICE_DBG_INIT, "%s: update_pending_nvm\n", prefix);
 		break;
-	case ICE_AQC_CAPS_PENDING_OROM_VER:
+	case LIBIE_AQC_CAPS_PENDING_OROM_VER:
 		caps->nvm_update_pending_orom = true;
 		ice_debug(hw, ICE_DBG_INIT, "%s: update_pending_orom\n", prefix);
 		break;
-	case ICE_AQC_CAPS_PENDING_NET_VER:
+	case LIBIE_AQC_CAPS_PENDING_NET_VER:
 		caps->nvm_update_pending_netlist = true;
 		ice_debug(hw, ICE_DBG_INIT, "%s: update_pending_netlist\n", prefix);
 		break;
-	case ICE_AQC_CAPS_NVM_MGMT:
+	case LIBIE_AQC_CAPS_NVM_MGMT:
 		caps->nvm_unified_update =
 			(number & ICE_NVM_MGMT_UNIFIED_UPD_SUPPORT) ?
 			true : false;
 		ice_debug(hw, ICE_DBG_INIT, "%s: nvm_unified_update = %d\n", prefix,
 			  caps->nvm_unified_update);
 		break;
-	case ICE_AQC_CAPS_RDMA:
-		caps->rdma = (number == 1);
+	case LIBIE_AQC_CAPS_RDMA:
+		if (IS_ENABLED(CONFIG_INFINIBAND_IRDMA))
+			caps->rdma = (number == 1);
 		ice_debug(hw, ICE_DBG_INIT, "%s: rdma = %d\n", prefix, caps->rdma);
 		break;
-	case ICE_AQC_CAPS_MAX_MTU:
+	case LIBIE_AQC_CAPS_MAX_MTU:
 		caps->max_mtu = number;
 		ice_debug(hw, ICE_DBG_INIT, "%s: max_mtu = %d\n",
 			  prefix, caps->max_mtu);
 		break;
-	case ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE:
+	case LIBIE_AQC_CAPS_PCIE_RESET_AVOIDANCE:
 		caps->pcie_reset_avoidance = (number > 0);
 		ice_debug(hw, ICE_DBG_INIT,
 			  "%s: pcie_reset_avoidance = %d\n", prefix,
 			  caps->pcie_reset_avoidance);
 		break;
-	case ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT:
+	case LIBIE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT:
 		caps->reset_restrict_support = (number == 1);
 		ice_debug(hw, ICE_DBG_INIT,
 			  "%s: reset_restrict_support = %d\n", prefix,
 			  caps->reset_restrict_support);
 		break;
-	case ICE_AQC_CAPS_FW_LAG_SUPPORT:
-		caps->roce_lag = !!(number & ICE_AQC_BIT_ROCEV2_LAG);
+	case LIBIE_AQC_CAPS_FW_LAG_SUPPORT:
+		caps->roce_lag = number & LIBIE_AQC_BIT_ROCEV2_LAG;
 		ice_debug(hw, ICE_DBG_INIT, "%s: roce_lag = %u\n",
 			  prefix, caps->roce_lag);
-		caps->sriov_lag = !!(number & ICE_AQC_BIT_SRIOV_LAG);
+		caps->sriov_lag = number & LIBIE_AQC_BIT_SRIOV_LAG;
 		ice_debug(hw, ICE_DBG_INIT, "%s: sriov_lag = %u\n",
 			  prefix, caps->sriov_lag);
+		caps->sriov_aa_lag = number & LIBIE_AQC_BIT_SRIOV_AA_LAG;
+		ice_debug(hw, ICE_DBG_INIT, "%s: sriov_aa_lag = %u\n",
+			  prefix, caps->sriov_aa_lag);
 		break;
-	case ICE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE:
+	case LIBIE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE:
 		caps->tx_sched_topo_comp_mode_en = (number == 1);
 		break;
 	default:
@@ -2279,7 +2563,7 @@ ice_recalc_port_limited_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps)
  */
 static void
 ice_parse_vf_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
-		       struct ice_aqc_list_caps_elem *cap)
+		       struct libie_aqc_list_caps_elem *cap)
 {
 	u32 logical_id = le32_to_cpu(cap->logical_id);
 	u32 number = le32_to_cpu(cap->number);
@@ -2302,7 +2586,7 @@ ice_parse_vf_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
  */
 static void
 ice_parse_vsi_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
-			struct ice_aqc_list_caps_elem *cap)
+			struct libie_aqc_list_caps_elem *cap)
 {
 	func_p->guar_num_vsi = ice_get_num_per_func(hw, ICE_MAX_VSI);
 	ice_debug(hw, ICE_DBG_INIT, "func caps: guar_num_vsi (fw) = %d\n",
@@ -2321,7 +2605,7 @@ ice_parse_vsi_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
  */
 static void
 ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
-			 struct ice_aqc_list_caps_elem *cap)
+			 struct libie_aqc_list_caps_elem *cap)
 {
 	struct ice_ts_func_info *info = &func_p->ts_func_info;
 	u32 number = le32_to_cpu(cap->number);
@@ -2334,16 +2618,16 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 	info->tmr_index_owned = ((number & ICE_TS_TMR_IDX_OWND_M) != 0);
 	info->tmr_index_assoc = ((number & ICE_TS_TMR_IDX_ASSOC_M) != 0);
 
-	if (!ice_is_e825c(hw)) {
+	if (hw->mac_type != ICE_MAC_GENERIC_3K_E825) {
 		info->clk_freq = FIELD_GET(ICE_TS_CLK_FREQ_M, number);
 		info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0);
 	} else {
-		info->clk_freq = ICE_TIME_REF_FREQ_156_250;
-		info->clk_src = ICE_CLK_SRC_TCXO;
+		info->clk_freq = ICE_TSPLL_FREQ_156_250;
+		info->clk_src = ICE_CLK_SRC_TIME_REF;
 	}
 
-	if (info->clk_freq < NUM_ICE_TIME_REF_FREQ) {
-		info->time_ref = (enum ice_time_ref_freq)info->clk_freq;
+	if (info->clk_freq < NUM_ICE_TSPLL_FREQ) {
+		info->time_ref = (enum ice_tspll_freq)info->clk_freq;
 	} else {
 		/* Unknown clock frequency, so assume a (probably incorrect)
 		 * default to avoid out-of-bounds look ups of frequency
@@ -2351,7 +2635,7 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 		 */
 		ice_debug(hw, ICE_DBG_INIT, "1588 func caps: unknown clock frequency %u\n",
 			  info->clk_freq);
-		info->time_ref = ICE_TIME_REF_FREQ_25_000;
+		info->time_ref = ICE_TSPLL_FREQ_25_000;
 	}
 
 	ice_debug(hw, ICE_DBG_INIT, "func caps: ieee_1588 = %u\n",
@@ -2420,7 +2704,7 @@ static void
 ice_parse_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 		    void *buf, u32 cap_count)
 {
-	struct ice_aqc_list_caps_elem *cap_resp;
+	struct libie_aqc_list_caps_elem *cap_resp;
 	u32 i;
 
 	cap_resp = buf;
@@ -2435,16 +2719,16 @@ ice_parse_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 					      &cap_resp[i], "func caps");
 
 		switch (cap) {
-		case ICE_AQC_CAPS_VF:
+		case LIBIE_AQC_CAPS_VF:
 			ice_parse_vf_func_caps(hw, func_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_VSI:
+		case LIBIE_AQC_CAPS_VSI:
 			ice_parse_vsi_func_caps(hw, func_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_1588:
+		case LIBIE_AQC_CAPS_1588:
 			ice_parse_1588_func_caps(hw, func_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_FD:
+		case LIBIE_AQC_CAPS_FD:
 			ice_parse_fdir_func_caps(hw, func_p);
 			break;
 		default:
@@ -2488,7 +2772,7 @@ static int ice_func_id_to_logical_id(u32 active_function_bitmap, u8 pf_id)
  */
 static void
 ice_parse_valid_functions_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
-			      struct ice_aqc_list_caps_elem *cap)
+			      struct libie_aqc_list_caps_elem *cap)
 {
 	u32 number = le32_to_cpu(cap->number);
 
@@ -2509,7 +2793,7 @@ ice_parse_valid_functions_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
  */
 static void
 ice_parse_vf_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
-		      struct ice_aqc_list_caps_elem *cap)
+		      struct libie_aqc_list_caps_elem *cap)
 {
 	u32 number = le32_to_cpu(cap->number);
 
@@ -2528,7 +2812,7 @@ ice_parse_vf_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
  */
 static void
 ice_parse_vsi_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
-		       struct ice_aqc_list_caps_elem *cap)
+		       struct libie_aqc_list_caps_elem *cap)
 {
 	u32 number = le32_to_cpu(cap->number);
 
@@ -2547,7 +2831,7 @@ ice_parse_vsi_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
  */
 static void
 ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
-			struct ice_aqc_list_caps_elem *cap)
+			struct libie_aqc_list_caps_elem *cap)
 {
 	struct ice_ts_dev_info *info = &dev_p->ts_dev_info;
 	u32 logical_id = le32_to_cpu(cap->logical_id);
@@ -2567,6 +2851,7 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 
 	info->ts_ll_read = ((number & ICE_TS_LL_TX_TS_READ_M) != 0);
 	info->ts_ll_int_read = ((number & ICE_TS_LL_TX_TS_INT_READ_M) != 0);
+	info->ll_phy_tmr_update = ((number & ICE_TS_LL_PHY_TMR_UPDATE_M) != 0);
 
 	info->ena_ports = logical_id;
 	info->tmr_own_map = phys_id;
@@ -2589,6 +2874,8 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 		  info->ts_ll_read);
 	ice_debug(hw, ICE_DBG_INIT, "dev caps: ts_ll_int_read = %u\n",
 		  info->ts_ll_int_read);
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: ll_phy_tmr_update = %u\n",
+		  info->ll_phy_tmr_update);
 	ice_debug(hw, ICE_DBG_INIT, "dev caps: ieee_1588 ena_ports = %u\n",
 		  info->ena_ports);
 	ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr_own_map = %u\n",
@@ -2605,7 +2892,7 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
  */
 static void
 ice_parse_fdir_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
-			struct ice_aqc_list_caps_elem *cap)
+			struct libie_aqc_list_caps_elem *cap)
 {
 	u32 number = le32_to_cpu(cap->number);
 
@@ -2625,7 +2912,7 @@ ice_parse_fdir_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
  */
 static void
 ice_parse_sensor_reading_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
-			     struct ice_aqc_list_caps_elem *cap)
+			     struct libie_aqc_list_caps_elem *cap)
 {
 	dev_p->supported_sensors = le32_to_cpu(cap->number);
 
@@ -2644,7 +2931,7 @@ ice_parse_sensor_reading_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
  */
 static void ice_parse_nac_topo_dev_caps(struct ice_hw *hw,
 					struct ice_hw_dev_caps *dev_p,
-					struct ice_aqc_list_caps_elem *cap)
+					struct libie_aqc_list_caps_elem *cap)
 {
 	dev_p->nac_topo.mode = le32_to_cpu(cap->number);
 	dev_p->nac_topo.id = le32_to_cpu(cap->phys_id) & ICE_NAC_TOPO_ID_M;
@@ -2680,7 +2967,7 @@ static void
 ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 		   void *buf, u32 cap_count)
 {
-	struct ice_aqc_list_caps_elem *cap_resp;
+	struct libie_aqc_list_caps_elem *cap_resp;
 	u32 i;
 
 	cap_resp = buf;
@@ -2695,25 +2982,25 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 					      &cap_resp[i], "dev caps");
 
 		switch (cap) {
-		case ICE_AQC_CAPS_VALID_FUNCTIONS:
+		case LIBIE_AQC_CAPS_VALID_FUNCTIONS:
 			ice_parse_valid_functions_cap(hw, dev_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_VF:
+		case LIBIE_AQC_CAPS_VF:
 			ice_parse_vf_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_VSI:
+		case LIBIE_AQC_CAPS_VSI:
 			ice_parse_vsi_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_1588:
+		case LIBIE_AQC_CAPS_1588:
 			ice_parse_1588_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_FD:
+		case LIBIE_AQC_CAPS_FD:
 			ice_parse_fdir_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_SENSOR_READING:
+		case LIBIE_AQC_CAPS_SENSOR_READING:
 			ice_parse_sensor_reading_cap(hw, dev_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_NAC_TOPOLOGY:
+		case LIBIE_AQC_CAPS_NAC_TOPOLOGY:
 			ice_parse_nac_topo_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
 		default:
@@ -2729,40 +3016,6 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 }
 
 /**
- * ice_is_pf_c827 - check if pf contains c827 phy
- * @hw: pointer to the hw struct
- */
-bool ice_is_pf_c827(struct ice_hw *hw)
-{
-	struct ice_aqc_get_link_topo cmd = {};
-	u8 node_part_number;
-	u16 node_handle;
-	int status;
-
-	if (hw->mac_type != ICE_MAC_E810)
-		return false;
-
-	if (hw->device_id != ICE_DEV_ID_E810C_QSFP)
-		return true;
-
-	cmd.addr.topo_params.node_type_ctx =
-		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) |
-		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT);
-	cmd.addr.topo_params.index = 0;
-
-	status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number,
-					 &node_handle);
-
-	if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827)
-		return false;
-
-	if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE)
-		return true;
-
-	return false;
-}
-
-/**
  * ice_is_phy_rclk_in_netlist
  * @hw: pointer to the hw struct
  *
@@ -2867,8 +3120,8 @@ int
 ice_aq_list_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count,
 		 enum ice_adminq_opc opc, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_list_caps *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aqc_list_caps *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	cmd = &desc.params.get_cap;
@@ -2909,7 +3162,7 @@ ice_discover_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_caps)
 	 * device will return, we can simply send a 4KB buffer, the maximum
 	 * possible size that firmware can return.
 	 */
-	cap_count = ICE_AQ_MAX_BUF_LEN / sizeof(struct ice_aqc_list_caps_elem);
+	cap_count = ICE_AQ_MAX_BUF_LEN / sizeof(struct libie_aqc_list_caps_elem);
 
 	status = ice_aq_list_caps(hw, cbuf, ICE_AQ_MAX_BUF_LEN, &cap_count,
 				  ice_aqc_opc_list_dev_caps, NULL);
@@ -2943,7 +3196,7 @@ ice_discover_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_caps)
 	 * device will return, we can simply send a 4KB buffer, the maximum
 	 * possible size that firmware can return.
 	 */
-	cap_count = ICE_AQ_MAX_BUF_LEN / sizeof(struct ice_aqc_list_caps_elem);
+	cap_count = ICE_AQ_MAX_BUF_LEN / sizeof(struct libie_aqc_list_caps_elem);
 
 	status = ice_aq_list_caps(hw, cbuf, ICE_AQ_MAX_BUF_LEN, &cap_count,
 				  ice_aqc_opc_list_func_caps, NULL);
@@ -3052,9 +3305,9 @@ ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
 			struct ice_sq_cd *cd)
 {
 	struct ice_aqc_manage_mac_write *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.mac_write;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_manage_mac_write);
 
 	cmd->flags = flags;
@@ -3071,10 +3324,12 @@ ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
  */
 static int ice_aq_clear_pxe_mode(struct ice_hw *hw)
 {
-	struct ice_aq_desc desc;
+	struct ice_aqc_clear_pxe *cmd;
+	struct libie_aq_desc desc;
 
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_clear_pxe_mode);
-	desc.params.clear_pxe.rx_cnt = ICE_AQC_CLEAR_PXE_RX_CNT;
+	cmd->rx_cnt = ICE_AQC_CLEAR_PXE_RX_CNT;
 
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
 }
@@ -3107,10 +3362,10 @@ ice_aq_set_port_params(struct ice_port_info *pi, bool double_vlan,
 {
 	struct ice_aqc_set_port_params *cmd;
 	struct ice_hw *hw = pi->hw;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 cmd_flags = 0;
 
-	cmd = &desc.params.set_port_params;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_params);
 	if (double_vlan)
@@ -3137,6 +3392,7 @@ bool ice_is_100m_speed_supported(struct ice_hw *hw)
 	case ICE_DEV_ID_E822L_SGMII:
 	case ICE_DEV_ID_E823L_1GBE:
 	case ICE_DEV_ID_E823C_SGMII:
+	case ICE_DEV_ID_E825C_SGMII:
 		return true;
 	default:
 		return false;
@@ -3347,7 +3603,8 @@ int
 ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi,
 		   struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct ice_aqc_set_phy_cfg *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!cfg)
@@ -3362,8 +3619,9 @@ ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi,
 	}
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_phy_cfg);
-	desc.params.set_phy.lport_num = pi->lport;
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	cmd = libie_aq_raw(&desc);
+	cmd->lport_num = pi->lport;
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	ice_debug(hw, ICE_DBG_LINK, "set phy cfg\n");
 	ice_debug(hw, ICE_DBG_LINK, "	phy_type_low = 0x%llx\n",
@@ -3379,7 +3637,7 @@ ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi,
 		  cfg->link_fec_opt);
 
 	status = ice_aq_send_cmd(hw, &desc, cfg, sizeof(*cfg), cd);
-	if (hw->adminq.sq_last_status == ICE_AQ_RC_EMODE)
+	if (hw->adminq.sq_last_status == LIBIE_AQ_RC_EMODE)
 		status = 0;
 
 	if (!status)
@@ -3436,17 +3694,17 @@ int ice_aq_get_phy_equalization(struct ice_hw *hw, u16 data_in, u16 op_code,
 {
 	struct ice_aqc_dnl_call_command *cmd;
 	struct ice_aqc_dnl_call buf = {};
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int err;
 
 	buf.sto.txrx_equa_reqs.data_in = cpu_to_le16(data_in);
 	buf.sto.txrx_equa_reqs.op_code_serdes_sel =
 		cpu_to_le16(op_code | (serdes_num & 0xF));
-	cmd = &desc.params.dnl_call;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_dnl_call);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_BUF |
-				  ICE_AQ_FLAG_RD |
-				  ICE_AQ_FLAG_SI);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_BUF |
+				  LIBIE_AQ_FLAG_RD |
+				  LIBIE_AQ_FLAG_SI);
 	desc.datalen = cpu_to_le16(sizeof(struct ice_aqc_dnl_call));
 	cmd->activity_id = cpu_to_le16(ICE_AQC_ACT_ID_DNL);
 
@@ -3484,7 +3742,7 @@ static const u32 fec_reg[][ICE_FEC_MAX] = {
 int ice_aq_get_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port,
 			 enum ice_fec_stats_types fec_type, u32 *output)
 {
-	u16 flag = (ICE_AQ_FLAG_RD | ICE_AQ_FLAG_BUF | ICE_AQ_FLAG_SI);
+	u16 flag = (LIBIE_AQ_FLAG_RD | LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_SI);
 	struct ice_sbq_msg_input msg = {};
 	u32 receiver_id, reg_offset;
 	int err;
@@ -3504,7 +3762,7 @@ int ice_aq_get_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port,
 	msg.msg_addr_low = lower_16_bits(reg_offset);
 	msg.msg_addr_high = receiver_id;
 	msg.opcode = ice_sbq_msg_rd;
-	msg.dest_dev = rmn_0;
+	msg.dest_dev = ice_sbq_dev_phy_0;
 
 	err = ice_sbq_rw_reg(hw, &msg, flag);
 	if (err)
@@ -3907,9 +4165,9 @@ ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
 			   struct ice_sq_cd *cd)
 {
 	struct ice_aqc_restart_an *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.restart_an;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_restart_an);
 
@@ -3937,9 +4195,9 @@ ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask,
 		      struct ice_sq_cd *cd)
 {
 	struct ice_aqc_set_event_mask *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.set_event_mask;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_event_mask);
 
@@ -3961,9 +4219,9 @@ int
 ice_aq_set_mac_loopback(struct ice_hw *hw, bool ena_lpbk, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_set_mac_lb *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.set_mac_lb;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_mac_lb);
 	if (ena_lpbk)
@@ -3986,9 +4244,9 @@ ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode,
 {
 	struct ice_aqc_set_port_id_led *cmd;
 	struct ice_hw *hw = pi->hw;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.set_port_id_led;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_id_led);
 
@@ -4024,7 +4282,7 @@ ice_aq_get_port_options(struct ice_hw *hw,
 			u8 *pending_option_idx, bool *pending_option_valid)
 {
 	struct ice_aqc_get_port_options *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 	u8 i;
 
@@ -4032,7 +4290,7 @@ ice_aq_get_port_options(struct ice_hw *hw,
 	if (*option_count < ICE_AQC_PORT_OPT_COUNT_M)
 		return -EINVAL;
 
-	cmd = &desc.params.get_port_options;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_port_options);
 
 	if (lport_valid)
@@ -4098,12 +4356,12 @@ ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid,
 		       u8 new_option)
 {
 	struct ice_aqc_set_port_option *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	if (new_option > ICE_AQC_PORT_OPT_COUNT_M)
 		return -EINVAL;
 
-	cmd = &desc.params.set_port_option;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_option);
 
 	if (lport_valid)
@@ -4116,6 +4374,68 @@ ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid,
 }
 
 /**
+ * ice_get_phy_lane_number - Get PHY lane number for current adapter
+ * @hw: pointer to the hw struct
+ *
+ * Return: PHY lane number on success, negative error code otherwise.
+ */
+int ice_get_phy_lane_number(struct ice_hw *hw)
+{
+	struct ice_aqc_get_port_options_elem *options;
+	unsigned int lport = 0;
+	unsigned int lane;
+	int err;
+
+	/* E82X does not have sequential IDs, lane number is PF ID.
+	 * For E825 device, the exception is the variant with external
+	 * PHY (0x579F), in which there is also 1:1 pf_id -> lane_number
+	 * mapping.
+	 */
+	if (hw->mac_type == ICE_MAC_GENERIC ||
+	    hw->device_id == ICE_DEV_ID_E825C_SGMII)
+		return hw->pf_id;
+
+	options = kcalloc(ICE_AQC_PORT_OPT_MAX, sizeof(*options), GFP_KERNEL);
+	if (!options)
+		return -ENOMEM;
+
+	for (lane = 0; lane < ICE_MAX_PORT_PER_PCI_DEV; lane++) {
+		u8 options_count = ICE_AQC_PORT_OPT_MAX;
+		u8 speed, active_idx, pending_idx;
+		bool active_valid, pending_valid;
+
+		err = ice_aq_get_port_options(hw, options, &options_count, lane,
+					      true, &active_idx, &active_valid,
+					      &pending_idx, &pending_valid);
+		if (err)
+			goto err;
+
+		if (!active_valid)
+			continue;
+
+		speed = options[active_idx].max_lane_speed;
+		/* If we don't get speed for this lane, it's unoccupied */
+		if (speed > ICE_AQC_PORT_OPT_MAX_LANE_40G)
+			continue;
+
+		if (hw->pf_id == lport) {
+			if (hw->mac_type == ICE_MAC_GENERIC_3K_E825 &&
+			    ice_is_dual(hw) && !ice_is_primary(hw))
+				lane += ICE_PORTS_PER_QUAD;
+			kfree(options);
+			return lane;
+		}
+		lport++;
+	}
+
+	/* PHY lane not found */
+	err = -ENXIO;
+err:
+	kfree(options);
+	return err;
+}
+
+/**
  * ice_aq_sff_eeprom
  * @hw: pointer to the HW struct
  * @lport: bits [7:0] = logical port, bit [8] = logical port valid
@@ -4136,7 +4456,7 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr,
 		  bool write, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_sff_eeprom *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 i2c_bus_addr;
 	int status;
 
@@ -4144,8 +4464,8 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr,
 		return -EINVAL;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_sff_eeprom);
-	cmd = &desc.params.read_write_sff_param;
-	desc.flags = cpu_to_le16(ICE_AQ_FLAG_RD);
+	cmd = libie_aq_raw(&desc);
+	desc.flags = cpu_to_le16(LIBIE_AQ_FLAG_RD);
 	cmd->lport_num = (u8)(lport & 0xff);
 	cmd->lport_num_valid = (u8)((lport >> 8) & 0x01);
 	i2c_bus_addr = FIELD_PREP(ICE_AQC_SFF_I2CBUS_7BIT_M, bus_addr >> 1) |
@@ -4205,7 +4525,7 @@ __ice_aq_get_set_rss_lut(struct ice_hw *hw,
 	struct ice_aqc_get_set_rss_lut *desc_params;
 	enum ice_aqc_lut_flags flags;
 	enum ice_lut_size lut_size;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u8 *lut = params->lut;
 
 
@@ -4221,9 +4541,9 @@ __ice_aq_get_set_rss_lut(struct ice_hw *hw,
 	opcode = set ? ice_aqc_opc_set_rss_lut : ice_aqc_opc_get_rss_lut;
 	ice_fill_dflt_direct_cmd_desc(&desc, opcode);
 	if (set)
-		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+		desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
-	desc_params = &desc.params.get_set_rss_lut;
+	desc_params = libie_aq_raw(&desc);
 	vsi_id = ice_get_hw_vsi_num(hw, vsi_handle);
 	desc_params->vsi_id = cpu_to_le16(vsi_id | ICE_AQC_RSS_VSI_VALID);
 
@@ -4278,16 +4598,16 @@ __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id,
 {
 	struct ice_aqc_get_set_rss_key *desc_params;
 	u16 key_size = sizeof(*key);
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	if (set) {
 		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_rss_key);
-		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+		desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 	} else {
 		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_rss_key);
 	}
 
-	desc_params = &desc.params.get_set_rss_key;
+	desc_params = libie_aq_raw(&desc);
 	desc_params->vsi_id = cpu_to_le16(vsi_id | ICE_AQC_RSS_VSI_VALID);
 
 	return ice_aq_send_cmd(hw, &desc, key, key_size, NULL);
@@ -4359,10 +4679,10 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 {
 	struct ice_aqc_add_tx_qgrp *list;
 	struct ice_aqc_add_txqs *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 i, sum_size = 0;
 
-	cmd = &desc.params.add_txqs;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_txqs);
 
@@ -4381,7 +4701,7 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 	if (buf_size != sum_size)
 		return -EINVAL;
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	cmd->num_qgrps = num_qgrps;
 
@@ -4408,12 +4728,12 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 {
 	struct ice_aqc_dis_txq_item *item;
 	struct ice_aqc_dis_txqs *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 vmvf_and_timeout;
 	u16 i, sz = 0;
 	int status;
 
-	cmd = &desc.params.dis_txqs;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_dis_txqs);
 
 	/* qg_list can be NULL only in VM/VF reset flow */
@@ -4454,7 +4774,7 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 	/* set RD bit to indicate that command buffer is provided by the driver
 	 * and it needs to be read by the firmware
 	 */
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	for (i = 0, item = qg_list; i < num_qgrps; i++) {
 		u16 item_size = struct_size(item, q_id, item->num_qs);
@@ -4486,40 +4806,42 @@ do_aq:
 }
 
 /**
- * ice_aq_cfg_lan_txq
+ * ice_aq_cfg_lan_txq - send AQ command 0x0C32 to FW
  * @hw: pointer to the hardware structure
  * @buf: buffer for command
  * @buf_size: size of buffer in bytes
  * @num_qs: number of queues being configured
  * @oldport: origination lport
  * @newport: destination lport
+ * @mode: cmd_type for move to use
  * @cd: pointer to command details structure or NULL
  *
  * Move/Configure LAN Tx queue (0x0C32)
  *
- * There is a better AQ command to use for moving nodes, so only coding
- * this one for configuring the node.
+ * Return: Zero on success, associated error code on failure.
  */
 int
 ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf,
 		   u16 buf_size, u16 num_qs, u8 oldport, u8 newport,
-		   struct ice_sq_cd *cd)
+		   u8 mode, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_cfg_txqs *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.cfg_txqs;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_cfg_txqs);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	if (!buf)
 		return -EINVAL;
 
-	cmd->cmd_type = ICE_AQC_Q_CFG_TC_CHNG;
+	cmd->cmd_type = mode;
 	cmd->num_qs = num_qs;
 	cmd->port_num_chng = (oldport & ICE_AQC_Q_CFG_SRC_PRT_M);
 	cmd->port_num_chng |= FIELD_PREP(ICE_AQC_Q_CFG_DST_PRT_M, newport);
+	cmd->port_num_chng |= FIELD_PREP(ICE_AQC_Q_CFG_MODE_M,
+					 ICE_AQC_Q_CFG_MODE_KEEP_OWN);
 	cmd->time_out = FIELD_PREP(ICE_AQC_Q_CFG_TIMEOUT_M, 5);
 	cmd->blocked_cgds = 0;
 
@@ -4547,10 +4869,10 @@ ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps,
 {
 	struct ice_aqc_add_rdma_qset_data *list;
 	struct ice_aqc_add_rdma_qset *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 i, sum_size = 0;
 
-	cmd = &desc.params.add_rdma_qset;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_rdma_qset);
 
@@ -4568,13 +4890,53 @@ ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps,
 	if (buf_size != sum_size)
 		return -EINVAL;
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	cmd->num_qset_grps = num_qset_grps;
 
 	return ice_aq_send_cmd(hw, &desc, qset_list, buf_size, cd);
 }
 
+/**
+ * ice_aq_set_txtimeq - set Tx time queues
+ * @hw: pointer to the hardware structure
+ * @txtimeq: first Tx time queue id to configure
+ * @q_count: number of queues to configure
+ * @txtime_qg: queue group to be set
+ * @buf_size: size of buffer for indirect command
+ * @cd: pointer to command details structure or NULL
+ *
+ * Set Tx Time queue (0x0C35)
+ * Return: 0 on success or negative value on failure.
+ */
+int
+ice_aq_set_txtimeq(struct ice_hw *hw, u16 txtimeq, u8 q_count,
+		   struct ice_aqc_set_txtime_qgrp *txtime_qg, u16 buf_size,
+		   struct ice_sq_cd *cd)
+{
+	struct ice_aqc_set_txtimeqs *cmd;
+	struct libie_aq_desc desc;
+	u16 size;
+
+	if (!txtime_qg || txtimeq > ICE_TXTIME_MAX_QUEUE ||
+	    q_count < 1 || q_count > ICE_SET_TXTIME_MAX_Q_AMOUNT)
+		return -EINVAL;
+
+	size = struct_size(txtime_qg, txtimeqs, q_count);
+	if (buf_size != size)
+		return -EINVAL;
+
+	cmd = libie_aq_raw(&desc);
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_txtimeqs);
+
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
+
+	cmd->q_id = cpu_to_le16(txtimeq);
+	cmd->q_amount = cpu_to_le16(q_count);
+	return ice_aq_send_cmd(hw, &desc, txtime_qg, buf_size, cd);
+}
+
 /* End of FW Admin Queue command wrappers */
 
 /**
@@ -4986,6 +5348,32 @@ ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid,
 }
 
 /**
+ * ice_aq_get_cgu_input_pin_measure - get input pin signal measurements
+ * @hw: pointer to the HW struct
+ * @dpll_idx: index of dpll to be measured
+ * @meas: array to be filled with results
+ * @meas_num: max number of results array can hold
+ *
+ * Get CGU measurements (0x0C59) of phase and frequency offsets for input
+ * pins on given dpll.
+ *
+ * Return: 0 on success or negative value on failure.
+ */
+int ice_aq_get_cgu_input_pin_measure(struct ice_hw *hw, u8 dpll_idx,
+				     struct ice_cgu_input_measure *meas,
+				     u16 meas_num)
+{
+	struct ice_aqc_get_cgu_input_measure *cmd;
+	struct libie_aq_desc desc;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_input_measure);
+	cmd = libie_aq_raw(&desc);
+	cmd->dpll_idx_opt = dpll_idx & ICE_AQC_GET_CGU_IN_MEAS_DPLL_IDX_M;
+
+	return ice_aq_send_cmd(hw, &desc, meas, meas_num * sizeof(*meas), NULL);
+}
+
+/**
  * ice_aq_get_cgu_abilities - get cgu abilities
  * @hw: pointer to the HW struct
  * @abilities: CGU abilities
@@ -4997,7 +5385,7 @@ int
 ice_aq_get_cgu_abilities(struct ice_hw *hw,
 			 struct ice_aqc_get_cgu_abilities *abilities)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_abilities);
 	return ice_aq_send_cmd(hw, &desc, abilities, sizeof(*abilities), NULL);
@@ -5020,10 +5408,10 @@ ice_aq_set_input_pin_cfg(struct ice_hw *hw, u8 input_idx, u8 flags1, u8 flags2,
 			 u32 freq, s32 phase_delay)
 {
 	struct ice_aqc_set_cgu_input_config *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_input_config);
-	cmd = &desc.params.set_cgu_input_config;
+	cmd = libie_aq_raw(&desc);
 	cmd->input_idx = input_idx;
 	cmd->flags1 = flags1;
 	cmd->flags2 = flags2;
@@ -5052,11 +5440,11 @@ ice_aq_get_input_pin_cfg(struct ice_hw *hw, u8 input_idx, u8 *status, u8 *type,
 			 u8 *flags1, u8 *flags2, u32 *freq, s32 *phase_delay)
 {
 	struct ice_aqc_get_cgu_input_config *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int ret;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_input_config);
-	cmd = &desc.params.get_cgu_input_config;
+	cmd = libie_aq_raw(&desc);
 	cmd->input_idx = input_idx;
 
 	ret = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
@@ -5095,10 +5483,10 @@ ice_aq_set_output_pin_cfg(struct ice_hw *hw, u8 output_idx, u8 flags,
 			  u8 src_sel, u32 freq, s32 phase_delay)
 {
 	struct ice_aqc_set_cgu_output_config *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_output_config);
-	cmd = &desc.params.set_cgu_output_config;
+	cmd = libie_aq_raw(&desc);
 	cmd->output_idx = output_idx;
 	cmd->flags = flags;
 	cmd->src_sel = src_sel;
@@ -5125,11 +5513,11 @@ ice_aq_get_output_pin_cfg(struct ice_hw *hw, u8 output_idx, u8 *flags,
 			  u8 *src_sel, u32 *freq, u32 *src_freq)
 {
 	struct ice_aqc_get_cgu_output_config *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int ret;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_output_config);
-	cmd = &desc.params.get_cgu_output_config;
+	cmd = libie_aq_raw(&desc);
 	cmd->output_idx = output_idx;
 
 	ret = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
@@ -5166,11 +5554,11 @@ ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state,
 			   u8 *eec_mode)
 {
 	struct ice_aqc_get_cgu_dpll_status *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_dpll_status);
-	cmd = &desc.params.get_cgu_dpll_status;
+	cmd = libie_aq_raw(&desc);
 	cmd->dpll_num = dpll_num;
 
 	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
@@ -5204,10 +5592,10 @@ ice_aq_set_cgu_dpll_config(struct ice_hw *hw, u8 dpll_num, u8 ref_state,
 			   u8 config, u8 eec_mode)
 {
 	struct ice_aqc_set_cgu_dpll_config *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_dpll_config);
-	cmd = &desc.params.set_cgu_dpll_config;
+	cmd = libie_aq_raw(&desc);
 	cmd->dpll_num = dpll_num;
 	cmd->ref_state = ref_state;
 	cmd->config = config;
@@ -5231,10 +5619,10 @@ ice_aq_set_cgu_ref_prio(struct ice_hw *hw, u8 dpll_num, u8 ref_idx,
 			u8 ref_priority)
 {
 	struct ice_aqc_set_cgu_ref_prio *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_ref_prio);
-	cmd = &desc.params.set_cgu_ref_prio;
+	cmd = libie_aq_raw(&desc);
 	cmd->dpll_num = dpll_num;
 	cmd->ref_idx = ref_idx;
 	cmd->ref_priority = ref_priority;
@@ -5257,11 +5645,11 @@ ice_aq_get_cgu_ref_prio(struct ice_hw *hw, u8 dpll_num, u8 ref_idx,
 			u8 *ref_prio)
 {
 	struct ice_aqc_get_cgu_ref_prio *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_ref_prio);
-	cmd = &desc.params.get_cgu_ref_prio;
+	cmd = libie_aq_raw(&desc);
 	cmd->dpll_num = dpll_num;
 	cmd->ref_idx = ref_idx;
 
@@ -5287,11 +5675,11 @@ ice_aq_get_cgu_info(struct ice_hw *hw, u32 *cgu_id, u32 *cgu_cfg_ver,
 		    u32 *cgu_fw_ver)
 {
 	struct ice_aqc_get_cgu_info *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_info);
-	cmd = &desc.params.get_cgu_info;
+	cmd = libie_aq_raw(&desc);
 
 	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
 	if (!status) {
@@ -5318,11 +5706,11 @@ ice_aq_set_phy_rec_clk_out(struct ice_hw *hw, u8 phy_output, bool enable,
 			   u32 *freq)
 {
 	struct ice_aqc_set_phy_rec_clk_out *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_phy_rec_clk_out);
-	cmd = &desc.params.set_phy_rec_clk_out;
+	cmd = libie_aq_raw(&desc);
 	cmd->phy_output = phy_output;
 	cmd->port_num = ICE_AQC_SET_PHY_REC_CLK_OUT_CURR_PORT;
 	cmd->flags = enable & ICE_AQC_SET_PHY_REC_CLK_OUT_OUT_EN;
@@ -5351,11 +5739,11 @@ ice_aq_get_phy_rec_clk_out(struct ice_hw *hw, u8 *phy_output, u8 *port_num,
 			   u8 *flags, u16 *node_handle)
 {
 	struct ice_aqc_get_phy_rec_clk_out *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_phy_rec_clk_out);
-	cmd = &desc.params.get_phy_rec_clk_out;
+	cmd = libie_aq_raw(&desc);
 	cmd->phy_output = *phy_output;
 
 	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
@@ -5383,11 +5771,11 @@ int ice_aq_get_sensor_reading(struct ice_hw *hw,
 			      struct ice_aqc_get_sensor_reading_resp *data)
 {
 	struct ice_aqc_get_sensor_reading *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_sensor_reading);
-	cmd = &desc.params.get_sensor_reading;
+	cmd = libie_aq_raw(&desc);
 #define ICE_INTERNAL_TEMP_SENSOR_FORMAT	0
 #define ICE_INTERNAL_TEMP_SENSOR	0
 	cmd->sensor = ICE_INTERNAL_TEMP_SENSOR;
@@ -5395,7 +5783,7 @@ int ice_aq_get_sensor_reading(struct ice_hw *hw,
 
 	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
 	if (!status)
-		memcpy(data, &desc.params.get_sensor_reading_resp,
+		memcpy(data, &desc.params.raw,
 		       sizeof(*data));
 
 	return status;
@@ -5592,13 +5980,13 @@ ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 		u16 bus_addr, __le16 addr, u8 params, u8 *data,
 		struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc = { 0 };
+	struct libie_aq_desc desc = { 0 };
 	struct ice_aqc_i2c *cmd;
 	u8 data_size;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_read_i2c);
-	cmd = &desc.params.read_write_i2c;
+	cmd = libie_aq_raw(&desc);
 
 	if (!data)
 		return -EINVAL;
@@ -5615,7 +6003,7 @@ ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 		struct ice_aqc_read_i2c_resp *resp;
 		u8 i;
 
-		resp = &desc.params.read_i2c_resp;
+		resp = libie_aq_raw(&desc);
 		for (i = 0; i < data_size; i++) {
 			*data = resp->i2c_data[i];
 			data++;
@@ -5647,12 +6035,12 @@ ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 		 u16 bus_addr, __le16 addr, u8 params, const u8 *data,
 		 struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc = { 0 };
+	struct libie_aq_desc desc = { 0 };
 	struct ice_aqc_i2c *cmd;
 	u8 data_size;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_write_i2c);
-	cmd = &desc.params.read_write_i2c;
+	cmd = libie_aq_raw(&desc);
 
 	data_size = FIELD_GET(ICE_AQC_I2C_DATA_SIZE_M, params);
 
@@ -5671,6 +6059,95 @@ ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 }
 
 /**
+ * ice_get_pca9575_handle - find and return the PCA9575 controller
+ * @hw: pointer to the hw struct
+ * @pca9575_handle: GPIO controller's handle
+ *
+ * Find and return the GPIO controller's handle in the netlist.
+ * When found - the value will be cached in the hw structure and following calls
+ * will return cached value.
+ *
+ * Return: 0 on success, -ENXIO when there's no PCA9575 present.
+ */
+int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle)
+{
+	struct ice_aqc_get_link_topo *cmd;
+	struct libie_aq_desc desc;
+	int err;
+	u8 idx;
+
+	/* If handle was read previously return cached value */
+	if (hw->io_expander_handle) {
+		*pca9575_handle = hw->io_expander_handle;
+		return 0;
+	}
+
+#define SW_PCA9575_SFP_TOPO_IDX		2
+#define SW_PCA9575_QSFP_TOPO_IDX	1
+
+	/* Check if the SW IO expander controlling SMA exists in the netlist. */
+	if (hw->device_id == ICE_DEV_ID_E810C_SFP)
+		idx = SW_PCA9575_SFP_TOPO_IDX;
+	else if (hw->device_id == ICE_DEV_ID_E810C_QSFP)
+		idx = SW_PCA9575_QSFP_TOPO_IDX;
+	else
+		return -ENXIO;
+
+	/* If handle was not detected read it from the netlist */
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
+	cmd = libie_aq_raw(&desc);
+	cmd->addr.topo_params.node_type_ctx =
+		ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL;
+	cmd->addr.topo_params.index = idx;
+
+	err = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
+	if (err)
+		return -ENXIO;
+
+	/* Verify if we found the right IO expander type */
+	if (cmd->node_part_num != ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575)
+		return -ENXIO;
+
+	/* If present save the handle and return it */
+	hw->io_expander_handle =
+		le16_to_cpu(cmd->addr.handle);
+	*pca9575_handle = hw->io_expander_handle;
+
+	return 0;
+}
+
+/**
+ * ice_read_pca9575_reg - read the register from the PCA9575 controller
+ * @hw: pointer to the hw struct
+ * @offset: GPIO controller register offset
+ * @data: pointer to data to be read from the GPIO controller
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data)
+{
+	struct ice_aqc_link_topo_addr link_topo;
+	__le16 addr;
+	u16 handle;
+	int err;
+
+	memset(&link_topo, 0, sizeof(link_topo));
+
+	err = ice_get_pca9575_handle(hw, &handle);
+	if (err)
+		return err;
+
+	link_topo.handle = cpu_to_le16(handle);
+	link_topo.topo_params.node_type_ctx =
+		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M,
+			   ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED);
+
+	addr = cpu_to_le16((u16)offset);
+
+	return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL);
+}
+
+/**
  * ice_aq_set_gpio
  * @hw: pointer to the hw struct
  * @gpio_ctrl_handle: GPIO controller node handle
@@ -5684,11 +6161,11 @@ int
 ice_aq_set_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool value,
 		struct ice_sq_cd *cd)
 {
+	struct libie_aq_desc desc;
 	struct ice_aqc_gpio *cmd;
-	struct ice_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_gpio);
-	cmd = &desc.params.read_write_gpio;
+	cmd = libie_aq_raw(&desc);
 	cmd->gpio_ctrl_handle = cpu_to_le16(gpio_ctrl_handle);
 	cmd->gpio_num = pin_idx;
 	cmd->gpio_val = value ? 1 : 0;
@@ -5711,12 +6188,12 @@ int
 ice_aq_get_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx,
 		bool *value, struct ice_sq_cd *cd)
 {
+	struct libie_aq_desc desc;
 	struct ice_aqc_gpio *cmd;
-	struct ice_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_gpio);
-	cmd = &desc.params.read_write_gpio;
+	cmd = libie_aq_raw(&desc);
 	cmd->gpio_ctrl_handle = cpu_to_le16(gpio_ctrl_handle);
 	cmd->gpio_num = pin_idx;
 
@@ -5853,6 +6330,44 @@ bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps)
 }
 
 /**
+ * ice_is_fw_health_report_supported - checks if firmware supports health events
+ * @hw: pointer to the hardware structure
+ *
+ * Return: true if firmware supports health status reports,
+ * false otherwise
+ */
+bool ice_is_fw_health_report_supported(struct ice_hw *hw)
+{
+	return ice_is_fw_api_min_ver(hw, ICE_FW_API_HEALTH_REPORT_MAJ,
+				     ICE_FW_API_HEALTH_REPORT_MIN,
+				     ICE_FW_API_HEALTH_REPORT_PATCH);
+}
+
+/**
+ * ice_aq_set_health_status_cfg - Configure FW health events
+ * @hw: pointer to the HW struct
+ * @event_source: type of diagnostic events to enable
+ *
+ * Configure the health status event types that the firmware will send to this
+ * PF. The supported event types are: PF-specific, all PFs, and global.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source)
+{
+	struct ice_aqc_set_health_status_cfg *cmd;
+	struct libie_aq_desc desc;
+
+	cmd = libie_aq_raw(&desc);
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_health_status_cfg);
+
+	cmd->event_source = event_source;
+
+	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
+}
+
+/**
  * ice_aq_set_lldp_mib - Set the LLDP MIB
  * @hw: pointer to the HW struct
  * @mib_type: Local, Remote or both Local and Remote MIBs
@@ -5867,16 +6382,16 @@ ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size,
 		    struct ice_sq_cd *cd)
 {
 	struct ice_aqc_lldp_set_local_mib *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.lldp_set_mib;
+	cmd = libie_aq_raw(&desc);
 
 	if (buf_size == 0 || !buf)
 		return -EINVAL;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_set_local_mib);
 
-	desc.flags |= cpu_to_le16((u16)ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_RD);
 	desc.datalen = cpu_to_le16(buf_size);
 
 	cmd->type = mib_type;
@@ -5902,16 +6417,22 @@ bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw)
 /**
  * ice_lldp_fltr_add_remove - add or remove a LLDP Rx switch filter
  * @hw: pointer to HW struct
- * @vsi_num: absolute HW index for VSI
+ * @vsi: VSI to add the filter to
  * @add: boolean for if adding or removing a filter
+ *
+ * Return: 0 on success, -EOPNOTSUPP if the operation cannot be performed
+ *	   with this HW or VSI, otherwise an error corresponding to
+ *	   the AQ transaction result.
  */
-int
-ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add)
+int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add)
 {
 	struct ice_aqc_lldp_filter_ctrl *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
+
+	if (vsi->type != ICE_VSI_PF || !ice_fw_supports_lldp_fltr_ctrl(hw))
+		return -EOPNOTSUPP;
 
-	cmd = &desc.params.lldp_filter_ctrl;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_filter_ctrl);
 
@@ -5920,7 +6441,7 @@ ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add)
 	else
 		cmd->cmd_flags = ICE_AQC_LLDP_FILTER_ACTION_DELETE;
 
-	cmd->vsi_num = cpu_to_le16(vsi_num);
+	cmd->vsi_num = cpu_to_le16(vsi->vsi_num);
 
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
 }
@@ -5931,7 +6452,7 @@ ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add)
  */
 int ice_lldp_execute_pending_mib(struct ice_hw *hw)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_execute_pending_mib);
 
@@ -5987,3 +6508,86 @@ u32 ice_get_link_speed(u16 index)
 
 	return ice_aq_to_link_speed[index];
 }
+
+/**
+ * ice_get_dest_cgu - get destination CGU dev for given HW
+ * @hw: pointer to the HW struct
+ *
+ * Get CGU client id for CGU register read/write operations.
+ *
+ * Return: CGU device id to use in SBQ transactions.
+ */
+static enum ice_sbq_dev_id ice_get_dest_cgu(struct ice_hw *hw)
+{
+	/* On dual complex E825 only complex 0 has functional CGU powering all
+	 * the PHYs.
+	 * SBQ destination device cgu points to CGU on a current complex and to
+	 * access primary CGU from the secondary complex, the driver should use
+	 * cgu_peer as a destination device.
+	 */
+	if (hw->mac_type == ICE_MAC_GENERIC_3K_E825 && ice_is_dual(hw) &&
+	    !ice_is_primary(hw))
+		return ice_sbq_dev_cgu_peer;
+	return ice_sbq_dev_cgu;
+}
+
+/**
+ * ice_read_cgu_reg - Read a CGU register
+ * @hw: Pointer to the HW struct
+ * @addr: Register address to read
+ * @val: Storage for register value read
+ *
+ * Read the contents of a register of the Clock Generation Unit. Only
+ * applicable to E82X devices.
+ *
+ * Return: 0 on success, other error codes when failed to read from CGU.
+ */
+int ice_read_cgu_reg(struct ice_hw *hw, u32 addr, u32 *val)
+{
+	struct ice_sbq_msg_input cgu_msg = {
+		.dest_dev = ice_get_dest_cgu(hw),
+		.opcode = ice_sbq_msg_rd,
+		.msg_addr_low = addr
+	};
+	int err;
+
+	err = ice_sbq_rw_reg(hw, &cgu_msg, LIBIE_AQ_FLAG_RD);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read CGU register 0x%04x, err %d\n",
+			  addr, err);
+		return err;
+	}
+
+	*val = cgu_msg.data;
+
+	return 0;
+}
+
+/**
+ * ice_write_cgu_reg - Write a CGU register
+ * @hw: Pointer to the HW struct
+ * @addr: Register address to write
+ * @val: Value to write into the register
+ *
+ * Write the specified value to a register of the Clock Generation Unit. Only
+ * applicable to E82X devices.
+ *
+ * Return: 0 on success, other error codes when failed to write to CGU.
+ */
+int ice_write_cgu_reg(struct ice_hw *hw, u32 addr, u32 val)
+{
+	struct ice_sbq_msg_input cgu_msg = {
+		.dest_dev = ice_get_dest_cgu(hw),
+		.opcode = ice_sbq_msg_wr,
+		.msg_addr_low = addr,
+		.data = val
+	};
+	int err;
+
+	err = ice_sbq_rw_reg(hw, &cgu_msg, LIBIE_AQ_FLAG_RD);
+	if (err)
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write CGU register 0x%04x, err %d\n",
+			  addr, err);
+
+	return err;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index a68bea3934e3..e700ac0dc347 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -39,6 +39,47 @@
 #define FEC_RECEIVER_ID_PCS0 (0x33 << FEC_RECV_ID_SHIFT)
 #define FEC_RECEIVER_ID_PCS1 (0x34 << FEC_RECV_ID_SHIFT)
 
+#define ICE_CGU_R9			0x24
+#define ICE_CGU_R9_TIME_REF_FREQ_SEL	GENMASK(2, 0)
+#define ICE_CGU_R9_CLK_EREF0_EN		BIT(4)
+#define ICE_CGU_R9_TIME_REF_EN		BIT(5)
+#define ICE_CGU_R9_TIME_SYNC_EN		BIT(6)
+#define ICE_CGU_R9_ONE_PPS_OUT_EN	BIT(7)
+#define ICE_CGU_R9_ONE_PPS_OUT_AMP	GENMASK(19, 18)
+
+#define ICE_CGU_R16			0x40
+#define ICE_CGU_R16_TSPLL_CK_REFCLKFREQ	GENMASK(31, 24)
+
+#define ICE_CGU_R19			0x4C
+#define ICE_CGU_R19_TSPLL_FBDIV_INTGR_E82X	GENMASK(7, 0)
+#define ICE_CGU_R19_TSPLL_FBDIV_INTGR_E825	GENMASK(9, 0)
+#define ICE_CGU_R19_TSPLL_NDIVRATIO	GENMASK(19, 16)
+
+#define ICE_CGU_R22			0x58
+#define ICE_CGU_R22_TIME1588CLK_DIV	GENMASK(23, 20)
+#define ICE_CGU_R22_TIME1588CLK_DIV2	BIT(30)
+
+#define ICE_CGU_R23			0x5C
+#define ICE_CGU_R24			0x60
+#define ICE_CGU_R24_FBDIV_FRAC		GENMASK(21, 0)
+#define ICE_CGU_R23_R24_TSPLL_ENABLE	BIT(24)
+#define ICE_CGU_R23_R24_REF1588_CK_DIV	GENMASK(30, 27)
+#define ICE_CGU_R23_R24_TIME_REF_SEL	BIT(31)
+
+#define ICE_CGU_BW_TDC			0x31C
+#define ICE_CGU_BW_TDC_PLLLOCK_SEL	GENMASK(30, 29)
+
+#define ICE_CGU_RO_LOCK			0x3F0
+#define ICE_CGU_RO_LOCK_TRUE_LOCK	BIT(12)
+#define ICE_CGU_RO_LOCK_UNLOCK		BIT(13)
+
+#define ICE_CGU_CNTR_BIST		0x344
+#define ICE_CGU_CNTR_BIST_PLLLOCK_SEL_0	BIT(15)
+#define ICE_CGU_CNTR_BIST_PLLLOCK_SEL_1	BIT(16)
+
+#define ICE_CGU_RO_BWM_LF		0x370
+#define ICE_CGU_RO_BWM_LF_TRUE_LOCK	BIT(12)
+
 int ice_init_hw(struct ice_hw *hw);
 void ice_deinit_hw(struct ice_hw *hw);
 int ice_check_reset(struct ice_hw *hw);
@@ -68,7 +109,7 @@ bool ice_is_sbq_supported(struct ice_hw *hw);
 struct ice_ctl_q_info *ice_get_sbq(struct ice_hw *hw);
 int
 ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
-		struct ice_aq_desc *desc, void *buf, u16 buf_size,
+		struct libie_aq_desc *desc, void *buf, u16 buf_size,
 		struct ice_sq_cd *cd);
 void ice_clear_pxe_mode(struct ice_hw *hw);
 int ice_get_caps(struct ice_hw *hw);
@@ -77,6 +118,12 @@ void ice_set_safe_mode_caps(struct ice_hw *hw);
 
 int ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
 		      u32 rxq_index);
+int ice_read_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
+		     u32 rxq_index);
+int ice_read_txq_ctx(struct ice_hw *hw, struct ice_tlan_ctx *tlan_ctx,
+		     u32 txq_index);
+int ice_write_txq_ctx(struct ice_hw *hw, struct ice_tlan_ctx *tlan_ctx,
+		      u32 txq_index);
 
 int
 ice_aq_get_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *get_params);
@@ -91,14 +138,14 @@ ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle,
 
 bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq);
 int ice_aq_q_shutdown(struct ice_hw *hw, bool unloading);
-void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode);
+void ice_fill_dflt_direct_cmd_desc(struct libie_aq_desc *desc, u16 opcode);
 
 void ice_pack_txq_ctx(const struct ice_tlan_ctx *ctx, ice_txq_ctx_buf_t *buf);
 
 extern struct mutex ice_global_cfg_lock_sw;
 
 int
-ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc,
+ice_aq_send_cmd(struct ice_hw *hw, struct libie_aq_desc *desc,
 		void *buf, u16 buf_size, struct ice_sq_cd *cd);
 int ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd);
 
@@ -112,7 +159,6 @@ int
 ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode,
 		    struct ice_aqc_get_phy_caps_data *caps,
 		    struct ice_sq_cd *cd);
-bool ice_is_pf_c827(struct ice_hw *hw);
 bool ice_is_phy_rclk_in_netlist(struct ice_hw *hw);
 bool ice_is_clock_mux_in_netlist(struct ice_hw *hw);
 bool ice_is_cgu_in_netlist(struct ice_hw *hw);
@@ -132,7 +178,6 @@ int
 ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
 			struct ice_sq_cd *cd);
 bool ice_is_generic_mac(struct ice_hw *hw);
-bool ice_is_e810(struct ice_hw *hw);
 int ice_clear_pf_cfg(struct ice_hw *hw);
 int
 ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi,
@@ -142,6 +187,8 @@ int
 ice_get_link_default_override(struct ice_link_default_override_tlv *ldo,
 			      struct ice_port_info *pi);
 bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps);
+bool ice_is_fw_health_report_supported(struct ice_hw *hw);
+int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source);
 int ice_aq_get_phy_equalization(struct ice_hw *hw, u16 data_in, u16 op_code,
 				u8 serdes_num, int *output);
 int
@@ -192,6 +239,7 @@ ice_aq_get_port_options(struct ice_hw *hw,
 int
 ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid,
 		       u8 new_option);
+int ice_get_phy_lane_number(struct ice_hw *hw);
 int
 ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr,
 		  u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length,
@@ -222,12 +270,21 @@ ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle,
 int
 ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf,
 		   u16 buf_size, u16 num_qs, u8 oldport, u8 newport,
-		   struct ice_sq_cd *cd);
+		   u8 mode, struct ice_sq_cd *cd);
 int ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle);
 void ice_replay_post(struct ice_hw *hw);
 struct ice_q_ctx *
 ice_get_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 q_handle);
+int
+ice_aq_set_txtimeq(struct ice_hw *hw, u16 txtimeq, u8 q_count,
+		   struct ice_aqc_set_txtime_qgrp *txtime_qg,
+		   u16 buf_size, struct ice_sq_cd *cd);
+void ice_pack_txtime_ctx(const struct ice_txtime_ctx *ctx,
+			 ice_txtime_ctx_buf_t *buf);
 int ice_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in, u16 flag);
+int ice_aq_get_cgu_input_pin_measure(struct ice_hw *hw, u8 dpll_idx,
+				     struct ice_cgu_input_measure *meas,
+				     u16 meas_num);
 int
 ice_aq_get_cgu_abilities(struct ice_hw *hw,
 			 struct ice_aqc_get_cgu_abilities *abilities);
@@ -274,10 +331,6 @@ ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
 void
 ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
 		  u64 *prev_stat, u64 *cur_stat);
-bool ice_is_e810t(struct ice_hw *hw);
-bool ice_is_e822(struct ice_hw *hw);
-bool ice_is_e823(struct ice_hw *hw);
-bool ice_is_e825c(struct ice_hw *hw);
 int
 ice_sched_query_elem(struct ice_hw *hw, u32 node_teid,
 		     struct ice_aqc_txsched_elem_data *buf);
@@ -293,8 +346,7 @@ int
 ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size,
 		    struct ice_sq_cd *cd);
 bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw);
-int
-ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add);
+int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add);
 int ice_lldp_execute_pending_mib(struct ice_hw *hw);
 int
 ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
@@ -304,5 +356,9 @@ int
 ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 		 u16 bus_addr, __le16 addr, u8 params, const u8 *data,
 		 struct ice_sq_cd *cd);
+int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle);
+int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data);
 bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw);
+int ice_read_cgu_reg(struct ice_hw *hw, u32 addr, u32 *val);
+int ice_write_cgu_reg(struct ice_hw *hw, u32 addr, u32 val);
 #endif /* _ICE_COMMON_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index e3959ad442a2..dcb837cadd18 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -90,7 +90,7 @@ bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 static int
 ice_alloc_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 {
-	size_t size = cq->num_sq_entries * sizeof(struct ice_aq_desc);
+	size_t size = cq->num_sq_entries * sizeof(struct libie_aq_desc);
 
 	cq->sq.desc_buf.va = dmam_alloc_coherent(ice_hw_to_dev(hw), size,
 						 &cq->sq.desc_buf.pa,
@@ -110,7 +110,7 @@ ice_alloc_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 static int
 ice_alloc_ctrlq_rq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 {
-	size_t size = cq->num_rq_entries * sizeof(struct ice_aq_desc);
+	size_t size = cq->num_rq_entries * sizeof(struct libie_aq_desc);
 
 	cq->rq.desc_buf.va = dmam_alloc_coherent(ice_hw_to_dev(hw), size,
 						 &cq->rq.desc_buf.pa,
@@ -159,7 +159,7 @@ ice_alloc_rq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 
 	/* allocate the mapped buffers */
 	for (i = 0; i < cq->num_rq_entries; i++) {
-		struct ice_aq_desc *desc;
+		struct libie_aq_desc *desc;
 		struct ice_dma_mem *bi;
 
 		bi = &cq->rq.r.rq_bi[i];
@@ -173,9 +173,9 @@ ice_alloc_rq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 		/* now configure the descriptors for use */
 		desc = ICE_CTL_Q_DESC(cq->rq, i);
 
-		desc->flags = cpu_to_le16(ICE_AQ_FLAG_BUF);
-		if (cq->rq_buf_size > ICE_AQ_LG_BUF)
-			desc->flags |= cpu_to_le16(ICE_AQ_FLAG_LB);
+		desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_BUF);
+		if (cq->rq_buf_size > LIBIE_AQ_LG_BUF)
+			desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
 		desc->opcode = 0;
 		/* This is in accordance with control queue design, there is no
 		 * register for buffer size configuration
@@ -858,7 +858,7 @@ static u16 ice_clean_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 {
 	struct ice_ctl_q_ring *sq = &cq->sq;
 	u16 ntc = sq->next_to_clean;
-	struct ice_aq_desc *desc;
+	struct libie_aq_desc *desc;
 
 	desc = ICE_CTL_Q_DESC(*sq, ntc);
 
@@ -912,7 +912,7 @@ static const char *ice_ctl_q_str(enum ice_ctl_q qtype)
 static void ice_debug_cq(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 			 void *desc, void *buf, u16 buf_len, bool response)
 {
-	struct ice_aq_desc *cq_desc = desc;
+	struct libie_aq_desc *cq_desc = desc;
 	u16 datalen, flags;
 
 	if (!IS_ENABLED(CONFIG_DYNAMIC_DEBUG) &&
@@ -939,7 +939,8 @@ static void ice_debug_cq(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	 * by the DD and/or CMP flag set or a command with the RD flag set.
 	 */
 	if (buf && cq_desc->datalen &&
-	    (flags & (ICE_AQ_FLAG_DD | ICE_AQ_FLAG_CMP | ICE_AQ_FLAG_RD))) {
+	    (flags & (LIBIE_AQ_FLAG_DD | LIBIE_AQ_FLAG_CMP |
+		      LIBIE_AQ_FLAG_RD))) {
 		char prefix[] = KBUILD_MODNAME " 0x12341234 0x12341234 ";
 
 		sprintf(prefix, KBUILD_MODNAME " 0x%08X 0x%08X ",
@@ -992,11 +993,11 @@ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq)
  */
 int
 ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
-		struct ice_aq_desc *desc, void *buf, u16 buf_size,
+		struct libie_aq_desc *desc, void *buf, u16 buf_size,
 		struct ice_sq_cd *cd)
 {
 	struct ice_dma_mem *dma_buf = NULL;
-	struct ice_aq_desc *desc_on_ring;
+	struct libie_aq_desc *desc_on_ring;
 	bool cmd_completed = false;
 	int status = 0;
 	u16 retval = 0;
@@ -1007,7 +1008,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		return -EBUSY;
 	mutex_lock(&cq->sq_lock);
 
-	cq->sq_last_status = ICE_AQ_RC_OK;
+	cq->sq_last_status = LIBIE_AQ_RC_OK;
 
 	if (!cq->sq.count) {
 		ice_debug(hw, ICE_DBG_AQ_MSG, "Control Send queue not initialized.\n");
@@ -1028,9 +1029,9 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 			goto sq_send_command_error;
 		}
 
-		desc->flags |= cpu_to_le16(ICE_AQ_FLAG_BUF);
-		if (buf_size > ICE_AQ_LG_BUF)
-			desc->flags |= cpu_to_le16(ICE_AQ_FLAG_LB);
+		desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_BUF);
+		if (buf_size > LIBIE_AQ_LG_BUF)
+			desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
 	}
 
 	val = rd32(hw, cq->sq.head);
@@ -1112,9 +1113,9 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 			retval &= 0xff;
 		}
 		cmd_completed = true;
-		if (!status && retval != ICE_AQ_RC_OK)
+		if (!status && retval != LIBIE_AQ_RC_OK)
 			status = -EIO;
-		cq->sq_last_status = (enum ice_aq_err)retval;
+		cq->sq_last_status = (enum libie_aq_err)retval;
 	}
 
 	ice_debug(hw, ICE_DBG_AQ_MSG, "ATQ: desc and buffer writeback:\n");
@@ -1149,12 +1150,12 @@ sq_send_command_error:
  *
  * Fill the desc with default values
  */
-void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode)
+void ice_fill_dflt_direct_cmd_desc(struct libie_aq_desc *desc, u16 opcode)
 {
 	/* zero out the desc */
 	memset(desc, 0, sizeof(*desc));
 	desc->opcode = cpu_to_le16(opcode);
-	desc->flags = cpu_to_le16(ICE_AQ_FLAG_SI);
+	desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_SI);
 }
 
 /**
@@ -1172,9 +1173,9 @@ int
 ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		  struct ice_rq_event_info *e, u16 *pending)
 {
+	enum libie_aq_err rq_last_status;
 	u16 ntc = cq->rq.next_to_clean;
-	enum ice_aq_err rq_last_status;
-	struct ice_aq_desc *desc;
+	struct libie_aq_desc *desc;
 	struct ice_dma_mem *bi;
 	int ret_code = 0;
 	u16 desc_idx;
@@ -1207,9 +1208,9 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	desc = ICE_CTL_Q_DESC(cq->rq, ntc);
 	desc_idx = ntc;
 
-	rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval);
+	rq_last_status = (enum libie_aq_err)le16_to_cpu(desc->retval);
 	flags = le16_to_cpu(desc->flags);
-	if (flags & ICE_AQ_FLAG_ERR) {
+	if (flags & LIBIE_AQ_FLAG_ERR) {
 		ret_code = -EIO;
 		ice_debug(hw, ICE_DBG_AQ_MSG, "Control Receive Queue Event 0x%04X received with error 0x%X\n",
 			  le16_to_cpu(desc->opcode), rq_last_status);
@@ -1230,9 +1231,9 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	bi = &cq->rq.r.rq_bi[ntc];
 	memset(desc, 0, sizeof(*desc));
 
-	desc->flags = cpu_to_le16(ICE_AQ_FLAG_BUF);
-	if (cq->rq_buf_size > ICE_AQ_LG_BUF)
-		desc->flags |= cpu_to_le16(ICE_AQ_FLAG_LB);
+	desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_BUF);
+	if (cq->rq_buf_size > LIBIE_AQ_LG_BUF)
+		desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
 	desc->datalen = cpu_to_le16(bi->size);
 	desc->params.generic.addr_high = cpu_to_le32(upper_32_bits(bi->pa));
 	desc->params.generic.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h
index ca97b7365a1b..788040dd662e 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.h
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.h
@@ -12,7 +12,7 @@
 #define ICE_SBQ_MAX_BUF_LEN 512
 
 #define ICE_CTL_Q_DESC(R, i) \
-	(&(((struct ice_aq_desc *)((R).desc_buf.va))[i]))
+	(&(((struct libie_aq_desc *)((R).desc_buf.va))[i]))
 
 #define ICE_CTL_Q_DESC_UNUSED(R) \
 	((u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
@@ -76,12 +76,12 @@ struct ice_ctl_q_ring {
 
 /* sq transaction details */
 struct ice_sq_cd {
-	struct ice_aq_desc *wb_desc;
+	struct libie_aq_desc *wb_desc;
 };
 
 /* rq event information */
 struct ice_rq_event_info {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 msg_len;
 	u16 buf_len;
 	u8 *msg_buf;
@@ -96,7 +96,7 @@ struct ice_ctl_q_info {
 	u16 num_sq_entries;		/* send queue depth */
 	u16 rq_buf_size;		/* receive queue buffer size */
 	u16 sq_buf_size;		/* send queue buffer size */
-	enum ice_aq_err sq_last_status;	/* last status on send queue */
+	enum libie_aq_err sq_last_status;	/* last status on send queue */
 	struct mutex sq_lock;		/* Send queue lock */
 	struct mutex rq_lock;		/* Receive queue lock */
 };
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c
index 74418c445cc4..abea84f14658 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.c
@@ -24,10 +24,10 @@ ice_aq_get_lldp_mib(struct ice_hw *hw, u8 bridge_type, u8 mib_type, void *buf,
 		    struct ice_sq_cd *cd)
 {
 	struct ice_aqc_lldp_get_mib *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.lldp_get_mib;
+	cmd = libie_aq_raw(&desc);
 
 	if (buf_size == 0 || !buf)
 		return -EINVAL;
@@ -64,9 +64,9 @@ ice_aq_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_update,
 			   struct ice_sq_cd *cd)
 {
 	struct ice_aqc_lldp_set_mib_change *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.lldp_set_event;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_set_mib_change);
 
@@ -95,9 +95,9 @@ ice_aq_stop_lldp(struct ice_hw *hw, bool shutdown_lldp_agent, bool persist,
 		 struct ice_sq_cd *cd)
 {
 	struct ice_aqc_lldp_stop *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.lldp_stop;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_stop);
 
@@ -121,9 +121,9 @@ ice_aq_stop_lldp(struct ice_hw *hw, bool shutdown_lldp_agent, bool persist,
 int ice_aq_start_lldp(struct ice_hw *hw, bool persist, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_lldp_start *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.lldp_start;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_start);
 
@@ -677,11 +677,11 @@ ice_aq_start_stop_dcbx(struct ice_hw *hw, bool start_dcbx_agent,
 		       bool *dcbx_agent_status, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_lldp_stop_start_specific_agent *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 opcode;
 	int status;
 
-	cmd = &desc.params.lldp_agent_ctrl;
+	cmd = libie_aq_raw(&desc);
 
 	opcode = ice_aqc_opc_lldp_stop_start_specific_agent;
 
@@ -714,7 +714,7 @@ ice_aq_get_cee_dcb_cfg(struct ice_hw *hw,
 		       struct ice_aqc_get_cee_dcb_cfg_resp *buff,
 		       struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cee_dcb_cfg);
 
@@ -733,13 +733,13 @@ ice_aq_get_cee_dcb_cfg(struct ice_hw *hw,
 int ice_aq_set_pfc_mode(struct ice_hw *hw, u8 pfc_mode, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_set_query_pfc_mode *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (pfc_mode > ICE_AQC_PFC_DSCP_BASED_PFC)
 		return -EINVAL;
 
-	cmd = &desc.params.set_query_pfc_mode;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_pfc_mode);
 
@@ -914,7 +914,7 @@ static int ice_get_ieee_or_cee_dcb_cfg(struct ice_port_info *pi, u8 dcbx_mode)
 	ret = ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_REMOTE,
 				 ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID, dcbx_cfg);
 	/* Don't treat ENOENT as an error for Remote MIBs */
-	if (pi->hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT)
+	if (pi->hw->adminq.sq_last_status == LIBIE_AQ_RC_ENOENT)
 		ret = 0;
 
 out:
@@ -941,7 +941,7 @@ int ice_get_dcb_cfg(struct ice_port_info *pi)
 		/* CEE mode */
 		ret = ice_get_ieee_or_cee_dcb_cfg(pi, ICE_DCBX_MODE_CEE);
 		ice_cee_to_dcb_cfg(&cee_cfg, pi);
-	} else if (pi->hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT) {
+	} else if (pi->hw->adminq.sq_last_status == LIBIE_AQ_RC_ENOENT) {
 		/* CEE mode not enabled try querying IEEE data */
 		dcbx_cfg = &pi->qos_cfg.local_dcbx_cfg;
 		dcbx_cfg->dcbx_mode = ICE_DCBX_MODE_IEEE;
@@ -965,7 +965,7 @@ void ice_get_dcb_cfg_from_mib_change(struct ice_port_info *pi,
 	struct ice_aqc_lldp_get_mib *mib;
 	u8 change_type, dcbx_mode;
 
-	mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw;
+	mib = libie_aq_raw(&event->desc);
 
 	change_type = FIELD_GET(ICE_AQ_LLDP_MIB_TYPE_M, mib->type);
 	if (change_type == ICE_AQ_LLDP_MIB_REMOTE)
@@ -1288,7 +1288,7 @@ ice_add_dscp_up_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
 	tlv->ouisubtype = htonl(ouisubtype);
 
 	/* bytes 0 - 63 - IPv4 DSCP2UP LUT */
-	for (i = 0; i < ICE_DSCP_NUM_VAL; i++) {
+	for (i = 0; i < DSCP_MAX; i++) {
 		/* IPv4 mapping */
 		buf[i] = dcbcfg->dscp_map[i];
 		/* IPv6 mapping */
@@ -1537,12 +1537,12 @@ ice_aq_query_port_ets(struct ice_port_info *pi,
 		      struct ice_sq_cd *cd)
 {
 	struct ice_aqc_query_port_ets *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!pi)
 		return -EINVAL;
-	cmd = &desc.params.port_ets;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_query_port_ets);
 	cmd->port_teid = pi->root->info.node_teid;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index a7c510832824..9fc8681cc58e 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -352,8 +352,8 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
 	struct ice_aqc_port_ets_elem buf = { 0 };
 	struct ice_dcbx_cfg *old_cfg, *curr_cfg;
 	struct device *dev = ice_pf_to_dev(pf);
+	struct iidc_rdma_event *event;
 	int ret = ICE_DCB_NO_HW_CHG;
-	struct iidc_event *event;
 	struct ice_vsi *pf_vsi;
 
 	curr_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
@@ -405,7 +405,7 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
 		goto free_cfg;
 	}
 
-	set_bit(IIDC_EVENT_BEFORE_TC_CHANGE, event->type);
+	set_bit(IIDC_RDMA_EVENT_BEFORE_TC_CHANGE, event->type);
 	ice_send_event_to_aux(pf, event);
 	kfree(event);
 
@@ -740,7 +740,9 @@ static int ice_dcb_noncontig_cfg(struct ice_pf *pf)
 void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked)
 {
 	struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
-	struct iidc_event *event;
+	struct iidc_rdma_priv_dev_info *privd;
+	struct iidc_rdma_core_dev_info *cdev;
+	struct iidc_rdma_event *event;
 	u8 tc_map = 0;
 	int v, ret;
 
@@ -783,13 +785,17 @@ void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked)
 		if (vsi->type == ICE_VSI_PF)
 			ice_dcbnl_set_all(vsi);
 	}
-	if (!locked) {
+
+	cdev = pf->cdev_info;
+	if (cdev && !locked) {
+		privd = cdev->iidc_priv;
+		ice_setup_dcb_qos_info(pf, &privd->qos_info);
 		/* Notify the AUX drivers that TC change is finished */
 		event = kzalloc(sizeof(*event), GFP_KERNEL);
 		if (!event)
 			return;
 
-		set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type);
+		set_bit(IIDC_RDMA_EVENT_AFTER_TC_CHANGE, event->type);
 		ice_send_event_to_aux(pf, event);
 		kfree(event);
 	}
@@ -846,7 +852,7 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked)
 			goto dcb_init_err;
 		}
 
-		ice_cfg_sw_lldp(pf_vsi, false, true);
+		ice_cfg_sw_rx_lldp(pf, true);
 
 		pf->dcbx_cap = ice_dcb_get_mode(port_info, true);
 		return 0;
@@ -945,6 +951,37 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring,
 }
 
 /**
+ * ice_setup_dcb_qos_info - Setup DCB QoS information
+ * @pf: ptr to ice_pf
+ * @qos_info: QoS param instance
+ */
+void ice_setup_dcb_qos_info(struct ice_pf *pf, struct iidc_rdma_qos_params *qos_info)
+{
+	struct ice_dcbx_cfg *dcbx_cfg;
+	unsigned int i;
+	u32 up2tc;
+
+	if (!pf || !qos_info)
+		return;
+
+	dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
+	up2tc = rd32(&pf->hw, PRTDCB_TUP2TC);
+
+	qos_info->num_tc = ice_dcb_get_num_tc(dcbx_cfg);
+
+	for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++)
+		qos_info->up2tc[i] = (up2tc >> (i * 3)) & 0x7;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		qos_info->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i];
+
+	qos_info->pfc_mode = dcbx_cfg->pfc_mode;
+	if (qos_info->pfc_mode == IIDC_DSCP_PFC_MODE)
+		for (i = 0; i < DSCP_MAX; i++)
+			qos_info->dscp_map[i] = dcbx_cfg->dscp_map[i];
+}
+
+/**
  * ice_dcb_is_mib_change_pending - Check if MIB change is pending
  * @state: MIB change state
  */
@@ -983,7 +1020,7 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
 	}
 
 	pi = pf->hw.port_info;
-	mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw;
+	mib = libie_aq_raw(&event->desc);
 
 	/* Ignore if event is not for Nearest Bridge */
 	mib_type = FIELD_GET(ICE_AQ_LLDP_BRID_TYPE_M, mib->type);
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
index 800879a88c5e..da9ba814b4e8 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
@@ -31,6 +31,9 @@ void
 ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring,
 			      struct ice_tx_buf *first);
 void
+ice_setup_dcb_qos_info(struct ice_pf *pf,
+		       struct iidc_rdma_qos_params *qos_info);
+void
 ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
 				    struct ice_rq_event_info *event);
 /**
@@ -134,5 +137,11 @@ static inline void ice_update_dcb_stats(struct ice_pf *pf) { }
 static inline void
 ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event) { }
 static inline void ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, u8 dcb_tc) { }
+static inline void
+ice_setup_dcb_qos_info(struct ice_pf *pf, struct iidc_rdma_qos_params *qos_info)
+{
+	qos_info->num_tc = 1;
+	qos_info->tc_info[0].rel_bw = 100;
+}
 #endif /* CONFIG_DCB */
 #endif /* _ICE_DCB_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
index 6d50b90a7359..a10c1c8d8697 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
@@ -754,7 +754,7 @@ static int ice_dcbnl_setapp(struct net_device *netdev, struct dcb_app *app)
 	if (!ice_is_feature_supported(pf, ICE_F_DSCP))
 		return -EOPNOTSUPP;
 
-	if (app->protocol >= ICE_DSCP_NUM_VAL) {
+	if (app->protocol >= DSCP_MAX) {
 		netdev_err(netdev, "DSCP value 0x%04X out of range\n",
 			   app->protocol);
 		return -EINVAL;
@@ -931,7 +931,7 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app)
 	/* if the last DSCP mapping just got deleted, need to switch
 	 * to L2 VLAN QoS mode
 	 */
-	if (bitmap_empty(new_cfg->dscp_mapped, ICE_DSCP_NUM_VAL) &&
+	if (bitmap_empty(new_cfg->dscp_mapped, DSCP_MAX) &&
 	    new_cfg->pfc_mode == ICE_QOS_MODE_DSCP) {
 		ret = ice_aq_set_pfc_mode(&pf->hw,
 					  ICE_AQC_PFC_VLAN_BASED_PFC,
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index 03988be03729..3b2d9c436979 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -1101,16 +1101,16 @@ struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld)
 	return &bld->buf;
 }
 
-static enum ice_ddp_state ice_map_aq_err_to_ddp_state(enum ice_aq_err aq_err)
+static enum ice_ddp_state ice_map_aq_err_to_ddp_state(enum libie_aq_err aq_err)
 {
 	switch (aq_err) {
-	case ICE_AQ_RC_ENOSEC:
-	case ICE_AQ_RC_EBADSIG:
+	case LIBIE_AQ_RC_ENOSEC:
+	case LIBIE_AQ_RC_EBADSIG:
 		return ICE_DDP_PKG_FILE_SIGNATURE_INVALID;
-	case ICE_AQ_RC_ESVN:
+	case LIBIE_AQ_RC_ESVN:
 		return ICE_DDP_PKG_FILE_REVISION_TOO_LOW;
-	case ICE_AQ_RC_EBADMAN:
-	case ICE_AQ_RC_EBADBUF:
+	case LIBIE_AQ_RC_EBADMAN:
+	case LIBIE_AQ_RC_EBADBUF:
 		return ICE_DDP_PKG_LOAD_ERROR;
 	default:
 		return ICE_DDP_PKG_ERR;
@@ -1180,7 +1180,7 @@ ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 		    u32 *error_info, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_download_pkg *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (error_offset)
@@ -1188,9 +1188,9 @@ ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 	if (error_info)
 		*error_info = 0;
 
-	cmd = &desc.params.download_pkg;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	if (last_buf)
 		cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF;
@@ -1259,7 +1259,7 @@ static enum ice_ddp_state ice_ddp_send_hunk(struct ice_ddp_send_ctx *ctx,
 	struct ice_buf_hdr *prev_hunk = ctx->hdr;
 	struct ice_hw *hw = ctx->hw;
 	bool prev_was_last = !hunk;
-	enum ice_aq_err aq_err;
+	enum libie_aq_err aq_err;
 	u32 offset, info;
 	int attempt, err;
 
@@ -1278,7 +1278,8 @@ static enum ice_ddp_state ice_ddp_send_hunk(struct ice_ddp_send_ctx *ctx,
 					  prev_was_last, &offset, &info, NULL);
 
 		aq_err = hw->adminq.sq_last_status;
-		if (aq_err != ICE_AQ_RC_ENOSEC && aq_err != ICE_AQ_RC_EBADSIG)
+		if (aq_err != LIBIE_AQ_RC_ENOSEC &&
+		    aq_err != LIBIE_AQ_RC_EBADSIG)
 			break;
 	}
 
@@ -1537,7 +1538,7 @@ ice_post_dwnld_pkg_actions(struct ice_hw *hw)
 static enum ice_ddp_state
 ice_download_pkg_with_sig_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
 {
-	enum ice_aq_err aq_err = hw->adminq.sq_last_status;
+	enum libie_aq_err aq_err = hw->adminq.sq_last_status;
 	enum ice_ddp_state state = ICE_DDP_PKG_ERR;
 	struct ice_ddp_send_ctx ctx = { .hw = hw };
 	int status;
@@ -1687,7 +1688,7 @@ static int ice_aq_get_pkg_info_list(struct ice_hw *hw,
 				    struct ice_aqc_get_pkg_info_resp *pkg_info,
 				    u16 buf_size, struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_pkg_info_list);
 
@@ -1711,7 +1712,7 @@ static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 			     u32 *error_info, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_download_pkg *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (error_offset)
@@ -1719,9 +1720,9 @@ static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 	if (error_info)
 		*error_info = 0;
 
-	cmd = &desc.params.download_pkg;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_pkg);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	if (last_buf)
 		cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF;
@@ -1753,10 +1754,10 @@ static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 			  u16 buf_size, struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_upload_section);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	return ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd);
 }
@@ -2301,6 +2302,8 @@ enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf,
 		return ICE_DDP_PKG_ERR;
 
 	buf_copy = devm_kmemdup(ice_hw_to_dev(hw), buf, len, GFP_KERNEL);
+	if (!buf_copy)
+		return ICE_DDP_PKG_ERR;
 
 	state = ice_init_pkg(hw, buf_copy, len);
 	if (!ice_is_init_pkg_successful(state)) {
@@ -2333,10 +2336,10 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
 		    struct ice_sq_cd *cd, u8 *flags, bool set)
 {
 	struct ice_aqc_get_set_tx_topo *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.get_set_tx_topo;
+	cmd = libie_aq_raw(&desc);
 	if (set) {
 		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_tx_topo);
 		cmd->set_flags = ICE_AQC_TX_TOPO_FLAGS_ISSUED;
@@ -2345,22 +2348,22 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
 			cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM |
 					  ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW;
 
-		if (ice_is_e825c(hw))
-			desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+		desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 	} else {
 		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo);
 		cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM;
-	}
 
-	if (!ice_is_e825c(hw))
-		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+		if (hw->mac_type == ICE_MAC_E810 ||
+		    hw->mac_type == ICE_MAC_GENERIC)
+			desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
+	}
 
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
 	if (status)
 		return status;
 	/* read the return flag values (first byte) for get operation */
 	if (!set && flags)
-		*flags = desc.params.get_set_tx_topo.set_flags;
+		*flags = cmd->set_flags;
 
 	return 0;
 }
@@ -2374,7 +2377,13 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
  * The function will apply the new Tx topology from the package buffer
  * if available.
  *
- * Return: zero when update was successful, negative values otherwise.
+ * Return:
+ * * 0 - Successfully applied topology configuration.
+ * * -EBUSY - Failed to acquire global configuration lock.
+ * * -EEXIST - Topology configuration has already been applied.
+ * * -EIO - Unable to apply topology configuration.
+ * * -ENODEV - Failed to re-initialize device after applying configuration.
+ * * Other negative error codes indicate unexpected failures.
  */
 int ice_cfg_tx_topo(struct ice_hw *hw, const void *buf, u32 len)
 {
@@ -2407,7 +2416,7 @@ int ice_cfg_tx_topo(struct ice_hw *hw, const void *buf, u32 len)
 
 	if (status) {
 		ice_debug(hw, ICE_DBG_INIT, "Get current topology is failed\n");
-		return status;
+		return -EIO;
 	}
 
 	/* Is default topology already applied ? */
@@ -2494,31 +2503,45 @@ update_topo:
 				 ICE_GLOBAL_CFG_LOCK_TIMEOUT);
 	if (status) {
 		ice_debug(hw, ICE_DBG_INIT, "Failed to acquire global lock\n");
-		return status;
+		return -EBUSY;
 	}
 
 	/* Check if reset was triggered already. */
 	reg = rd32(hw, GLGEN_RSTAT);
 	if (reg & GLGEN_RSTAT_DEVSTATE_M) {
-		/* Reset is in progress, re-init the HW again */
 		ice_debug(hw, ICE_DBG_INIT, "Reset is in progress. Layer topology might be applied already\n");
 		ice_check_reset(hw);
-		return 0;
+		/* Reset is in progress, re-init the HW again */
+		goto reinit_hw;
 	}
 
 	/* Set new topology */
 	status = ice_get_set_tx_topo(hw, new_topo, size, NULL, NULL, true);
 	if (status) {
-		ice_debug(hw, ICE_DBG_INIT, "Failed setting Tx topology\n");
-		return status;
+		ice_debug(hw, ICE_DBG_INIT, "Failed to set Tx topology, status %pe\n",
+			  ERR_PTR(status));
+		/* only report -EIO here as the caller checks the error value
+		 * and reports an informational error message informing that
+		 * the driver failed to program Tx topology.
+		 */
+		status = -EIO;
 	}
 
-	/* New topology is updated, delay 1 second before issuing the CORER */
+	/* Even if Tx topology config failed, we need to CORE reset here to
+	 * clear the global configuration lock. Delay 1 second to allow
+	 * hardware to settle then issue a CORER
+	 */
 	msleep(1000);
 	ice_reset(hw, ICE_RESET_CORER);
-	/* CORER will clear the global lock, so no explicit call
-	 * required for release.
-	 */
+	ice_check_reset(hw);
+
+reinit_hw:
+	/* Since we triggered a CORER, re-initialize hardware */
+	ice_deinit_hw(hw);
+	if (ice_init_hw(hw)) {
+		ice_debug(hw, ICE_DBG_INIT, "Failed to re-init hardware after setting Tx topology\n");
+		return -ENODEV;
+	}
 
-	return 0;
+	return status;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_debugfs.c b/drivers/net/ethernet/intel/ice/ice_debugfs.c
index 9fc0fd95a13d..f450250fc827 100644
--- a/drivers/net/ethernet/intel/ice/ice_debugfs.c
+++ b/drivers/net/ethernet/intel/ice/ice_debugfs.c
@@ -1,647 +1,20 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2022, Intel Corporation. */
 
-#include <linux/fs.h>
 #include <linux/debugfs.h>
-#include <linux/random.h>
-#include <linux/vmalloc.h>
 #include "ice.h"
 
 static struct dentry *ice_debugfs_root;
 
-/* create a define that has an extra module that doesn't really exist. this
- * is so we can add a module 'all' to easily enable/disable all the modules
- */
-#define ICE_NR_FW_LOG_MODULES (ICE_AQC_FW_LOG_ID_MAX + 1)
-
-/* the ordering in this array is important. it matches the ordering of the
- * values in the FW so the index is the same value as in ice_aqc_fw_logging_mod
- */
-static const char * const ice_fwlog_module_string[] = {
-	"general",
-	"ctrl",
-	"link",
-	"link_topo",
-	"dnl",
-	"i2c",
-	"sdp",
-	"mdio",
-	"adminq",
-	"hdma",
-	"lldp",
-	"dcbx",
-	"dcb",
-	"xlr",
-	"nvm",
-	"auth",
-	"vpd",
-	"iosf",
-	"parser",
-	"sw",
-	"scheduler",
-	"txq",
-	"rsvd",
-	"post",
-	"watchdog",
-	"task_dispatch",
-	"mng",
-	"synce",
-	"health",
-	"tsdrv",
-	"pfreg",
-	"mdlver",
-	"all",
-};
-
-/* the ordering in this array is important. it matches the ordering of the
- * values in the FW so the index is the same value as in ice_fwlog_level
- */
-static const char * const ice_fwlog_level_string[] = {
-	"none",
-	"error",
-	"warning",
-	"normal",
-	"verbose",
-};
-
-static const char * const ice_fwlog_log_size[] = {
-	"128K",
-	"256K",
-	"512K",
-	"1M",
-	"2M",
-};
-
-/**
- * ice_fwlog_print_module_cfg - print current FW logging module configuration
- * @hw: pointer to the HW structure
- * @module: module to print
- * @s: the seq file to put data into
- */
-static void
-ice_fwlog_print_module_cfg(struct ice_hw *hw, int module, struct seq_file *s)
-{
-	struct ice_fwlog_cfg *cfg = &hw->fwlog_cfg;
-	struct ice_fwlog_module_entry *entry;
-
-	if (module != ICE_AQC_FW_LOG_ID_MAX) {
-		entry =	&cfg->module_entries[module];
-
-		seq_printf(s, "\tModule: %s, Log Level: %s\n",
-			   ice_fwlog_module_string[entry->module_id],
-			   ice_fwlog_level_string[entry->log_level]);
-	} else {
-		int i;
-
-		for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) {
-			entry =	&cfg->module_entries[i];
-
-			seq_printf(s, "\tModule: %s, Log Level: %s\n",
-				   ice_fwlog_module_string[entry->module_id],
-				   ice_fwlog_level_string[entry->log_level]);
-		}
-	}
-}
-
-static int ice_find_module_by_dentry(struct ice_pf *pf, struct dentry *d)
-{
-	int i, module;
-
-	module = -1;
-	/* find the module based on the dentry */
-	for (i = 0; i < ICE_NR_FW_LOG_MODULES; i++) {
-		if (d == pf->ice_debugfs_pf_fwlog_modules[i]) {
-			module = i;
-			break;
-		}
-	}
-
-	return module;
-}
-
-/**
- * ice_debugfs_module_show - read from 'module' file
- * @s: the opened file
- * @v: pointer to the offset
- */
-static int ice_debugfs_module_show(struct seq_file *s, void *v)
-{
-	const struct file *filp = s->file;
-	struct dentry *dentry;
-	struct ice_pf *pf;
-	int module;
-
-	dentry = file_dentry(filp);
-	pf = s->private;
-
-	module = ice_find_module_by_dentry(pf, dentry);
-	if (module < 0) {
-		dev_info(ice_pf_to_dev(pf), "unknown module\n");
-		return -EINVAL;
-	}
-
-	ice_fwlog_print_module_cfg(&pf->hw, module, s);
-
-	return 0;
-}
-
-static int ice_debugfs_module_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, ice_debugfs_module_show, inode->i_private);
-}
-
-/**
- * ice_debugfs_module_write - write into 'module' file
- * @filp: the opened file
- * @buf: where to find the user's data
- * @count: the length of the user's data
- * @ppos: file position offset
- */
-static ssize_t
-ice_debugfs_module_write(struct file *filp, const char __user *buf,
-			 size_t count, loff_t *ppos)
-{
-	struct ice_pf *pf = file_inode(filp)->i_private;
-	struct dentry *dentry = file_dentry(filp);
-	struct device *dev = ice_pf_to_dev(pf);
-	char user_val[16], *cmd_buf;
-	int module, log_level, cnt;
-
-	/* don't allow partial writes or invalid input */
-	if (*ppos != 0 || count > 8)
-		return -EINVAL;
-
-	cmd_buf = memdup_user_nul(buf, count);
-	if (IS_ERR(cmd_buf))
-		return PTR_ERR(cmd_buf);
-
-	module = ice_find_module_by_dentry(pf, dentry);
-	if (module < 0) {
-		dev_info(dev, "unknown module\n");
-		return -EINVAL;
-	}
-
-	cnt = sscanf(cmd_buf, "%s", user_val);
-	if (cnt != 1)
-		return -EINVAL;
-
-	log_level = sysfs_match_string(ice_fwlog_level_string, user_val);
-	if (log_level < 0) {
-		dev_info(dev, "unknown log level '%s'\n", user_val);
-		return -EINVAL;
-	}
-
-	if (module != ICE_AQC_FW_LOG_ID_MAX) {
-		ice_pf_fwlog_update_module(pf, log_level, module);
-	} else {
-		/* the module 'all' is a shortcut so that we can set
-		 * all of the modules to the same level quickly
-		 */
-		int i;
-
-		for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++)
-			ice_pf_fwlog_update_module(pf, log_level, i);
-	}
-
-	return count;
-}
-
-static const struct file_operations ice_debugfs_module_fops = {
-	.owner = THIS_MODULE,
-	.open  = ice_debugfs_module_open,
-	.read = seq_read,
-	.release = single_release,
-	.write = ice_debugfs_module_write,
-};
-
-/**
- * ice_debugfs_nr_messages_read - read from 'nr_messages' file
- * @filp: the opened file
- * @buffer: where to write the data for the user to read
- * @count: the size of the user's buffer
- * @ppos: file position offset
- */
-static ssize_t ice_debugfs_nr_messages_read(struct file *filp,
-					    char __user *buffer, size_t count,
-					    loff_t *ppos)
-{
-	struct ice_pf *pf = filp->private_data;
-	struct ice_hw *hw = &pf->hw;
-	char buff[32] = {};
-
-	snprintf(buff, sizeof(buff), "%d\n",
-		 hw->fwlog_cfg.log_resolution);
-
-	return simple_read_from_buffer(buffer, count, ppos, buff, strlen(buff));
-}
-
-/**
- * ice_debugfs_nr_messages_write - write into 'nr_messages' file
- * @filp: the opened file
- * @buf: where to find the user's data
- * @count: the length of the user's data
- * @ppos: file position offset
- */
-static ssize_t
-ice_debugfs_nr_messages_write(struct file *filp, const char __user *buf,
-			      size_t count, loff_t *ppos)
-{
-	struct ice_pf *pf = filp->private_data;
-	struct device *dev = ice_pf_to_dev(pf);
-	struct ice_hw *hw = &pf->hw;
-	char user_val[8], *cmd_buf;
-	s16 nr_messages;
-	ssize_t ret;
-
-	/* don't allow partial writes or invalid input */
-	if (*ppos != 0 || count > 4)
-		return -EINVAL;
-
-	cmd_buf = memdup_user_nul(buf, count);
-	if (IS_ERR(cmd_buf))
-		return PTR_ERR(cmd_buf);
-
-	ret = sscanf(cmd_buf, "%s", user_val);
-	if (ret != 1)
-		return -EINVAL;
-
-	ret = kstrtos16(user_val, 0, &nr_messages);
-	if (ret)
-		return ret;
-
-	if (nr_messages < ICE_AQC_FW_LOG_MIN_RESOLUTION ||
-	    nr_messages > ICE_AQC_FW_LOG_MAX_RESOLUTION) {
-		dev_err(dev, "Invalid FW log number of messages %d, value must be between %d - %d\n",
-			nr_messages, ICE_AQC_FW_LOG_MIN_RESOLUTION,
-			ICE_AQC_FW_LOG_MAX_RESOLUTION);
-		return -EINVAL;
-	}
-
-	hw->fwlog_cfg.log_resolution = nr_messages;
-
-	return count;
-}
-
-static const struct file_operations ice_debugfs_nr_messages_fops = {
-	.owner = THIS_MODULE,
-	.open  = simple_open,
-	.read = ice_debugfs_nr_messages_read,
-	.write = ice_debugfs_nr_messages_write,
-};
-
-/**
- * ice_debugfs_enable_read - read from 'enable' file
- * @filp: the opened file
- * @buffer: where to write the data for the user to read
- * @count: the size of the user's buffer
- * @ppos: file position offset
- */
-static ssize_t ice_debugfs_enable_read(struct file *filp,
-				       char __user *buffer, size_t count,
-				       loff_t *ppos)
-{
-	struct ice_pf *pf = filp->private_data;
-	struct ice_hw *hw = &pf->hw;
-	char buff[32] = {};
-
-	snprintf(buff, sizeof(buff), "%u\n",
-		 (u16)(hw->fwlog_cfg.options &
-		 ICE_FWLOG_OPTION_IS_REGISTERED) >> 3);
-
-	return simple_read_from_buffer(buffer, count, ppos, buff, strlen(buff));
-}
-
-/**
- * ice_debugfs_enable_write - write into 'enable' file
- * @filp: the opened file
- * @buf: where to find the user's data
- * @count: the length of the user's data
- * @ppos: file position offset
- */
-static ssize_t
-ice_debugfs_enable_write(struct file *filp, const char __user *buf,
-			 size_t count, loff_t *ppos)
-{
-	struct ice_pf *pf = filp->private_data;
-	struct ice_hw *hw = &pf->hw;
-	char user_val[8], *cmd_buf;
-	bool enable;
-	ssize_t ret;
-
-	/* don't allow partial writes or invalid input */
-	if (*ppos != 0 || count > 2)
-		return -EINVAL;
-
-	cmd_buf = memdup_user_nul(buf, count);
-	if (IS_ERR(cmd_buf))
-		return PTR_ERR(cmd_buf);
-
-	ret = sscanf(cmd_buf, "%s", user_val);
-	if (ret != 1)
-		return -EINVAL;
-
-	ret = kstrtobool(user_val, &enable);
-	if (ret)
-		goto enable_write_error;
-
-	if (enable)
-		hw->fwlog_cfg.options |= ICE_FWLOG_OPTION_ARQ_ENA;
-	else
-		hw->fwlog_cfg.options &= ~ICE_FWLOG_OPTION_ARQ_ENA;
-
-	ret = ice_fwlog_set(hw, &hw->fwlog_cfg);
-	if (ret)
-		goto enable_write_error;
-
-	if (enable)
-		ret = ice_fwlog_register(hw);
-	else
-		ret = ice_fwlog_unregister(hw);
-
-	if (ret)
-		goto enable_write_error;
-
-	/* if we get here, nothing went wrong; return count since we didn't
-	 * really write anything
-	 */
-	ret = (ssize_t)count;
-
-enable_write_error:
-	/* This function always consumes all of the written input, or produces
-	 * an error. Check and enforce this. Otherwise, the write operation
-	 * won't complete properly.
-	 */
-	if (WARN_ON(ret != (ssize_t)count && ret >= 0))
-		ret = -EIO;
-
-	return ret;
-}
-
-static const struct file_operations ice_debugfs_enable_fops = {
-	.owner = THIS_MODULE,
-	.open  = simple_open,
-	.read = ice_debugfs_enable_read,
-	.write = ice_debugfs_enable_write,
-};
-
-/**
- * ice_debugfs_log_size_read - read from 'log_size' file
- * @filp: the opened file
- * @buffer: where to write the data for the user to read
- * @count: the size of the user's buffer
- * @ppos: file position offset
- */
-static ssize_t ice_debugfs_log_size_read(struct file *filp,
-					 char __user *buffer, size_t count,
-					 loff_t *ppos)
-{
-	struct ice_pf *pf = filp->private_data;
-	struct ice_hw *hw = &pf->hw;
-	char buff[32] = {};
-	int index;
-
-	index = hw->fwlog_ring.index;
-	snprintf(buff, sizeof(buff), "%s\n", ice_fwlog_log_size[index]);
-
-	return simple_read_from_buffer(buffer, count, ppos, buff, strlen(buff));
-}
-
-/**
- * ice_debugfs_log_size_write - write into 'log_size' file
- * @filp: the opened file
- * @buf: where to find the user's data
- * @count: the length of the user's data
- * @ppos: file position offset
- */
-static ssize_t
-ice_debugfs_log_size_write(struct file *filp, const char __user *buf,
-			   size_t count, loff_t *ppos)
-{
-	struct ice_pf *pf = filp->private_data;
-	struct device *dev = ice_pf_to_dev(pf);
-	struct ice_hw *hw = &pf->hw;
-	char user_val[8], *cmd_buf;
-	ssize_t ret;
-	int index;
-
-	/* don't allow partial writes or invalid input */
-	if (*ppos != 0 || count > 5)
-		return -EINVAL;
-
-	cmd_buf = memdup_user_nul(buf, count);
-	if (IS_ERR(cmd_buf))
-		return PTR_ERR(cmd_buf);
-
-	ret = sscanf(cmd_buf, "%s", user_val);
-	if (ret != 1)
-		return -EINVAL;
-
-	index = sysfs_match_string(ice_fwlog_log_size, user_val);
-	if (index < 0) {
-		dev_info(dev, "Invalid log size '%s'. The value must be one of 128K, 256K, 512K, 1M, 2M\n",
-			 user_val);
-		ret = -EINVAL;
-		goto log_size_write_error;
-	} else if (hw->fwlog_cfg.options & ICE_FWLOG_OPTION_IS_REGISTERED) {
-		dev_info(dev, "FW logging is currently running. Please disable FW logging to change log_size\n");
-		ret = -EINVAL;
-		goto log_size_write_error;
-	}
-
-	/* free all the buffers and the tracking info and resize */
-	ice_fwlog_realloc_rings(hw, index);
-
-	/* if we get here, nothing went wrong; return count since we didn't
-	 * really write anything
-	 */
-	ret = (ssize_t)count;
-
-log_size_write_error:
-	/* This function always consumes all of the written input, or produces
-	 * an error. Check and enforce this. Otherwise, the write operation
-	 * won't complete properly.
-	 */
-	if (WARN_ON(ret != (ssize_t)count && ret >= 0))
-		ret = -EIO;
-
-	return ret;
-}
-
-static const struct file_operations ice_debugfs_log_size_fops = {
-	.owner = THIS_MODULE,
-	.open  = simple_open,
-	.read = ice_debugfs_log_size_read,
-	.write = ice_debugfs_log_size_write,
-};
-
-/**
- * ice_debugfs_data_read - read from 'data' file
- * @filp: the opened file
- * @buffer: where to write the data for the user to read
- * @count: the size of the user's buffer
- * @ppos: file position offset
- */
-static ssize_t ice_debugfs_data_read(struct file *filp, char __user *buffer,
-				     size_t count, loff_t *ppos)
-{
-	struct ice_pf *pf = filp->private_data;
-	struct ice_hw *hw = &pf->hw;
-	int data_copied = 0;
-	bool done = false;
-
-	if (ice_fwlog_ring_empty(&hw->fwlog_ring))
-		return 0;
-
-	while (!ice_fwlog_ring_empty(&hw->fwlog_ring) && !done) {
-		struct ice_fwlog_data *log;
-		u16 cur_buf_len;
-
-		log = &hw->fwlog_ring.rings[hw->fwlog_ring.head];
-		cur_buf_len = log->data_size;
-		if (cur_buf_len >= count) {
-			done = true;
-			continue;
-		}
-
-		if (copy_to_user(buffer, log->data, cur_buf_len)) {
-			/* if there is an error then bail and return whatever
-			 * the driver has copied so far
-			 */
-			done = true;
-			continue;
-		}
-
-		data_copied += cur_buf_len;
-		buffer += cur_buf_len;
-		count -= cur_buf_len;
-		*ppos += cur_buf_len;
-		ice_fwlog_ring_increment(&hw->fwlog_ring.head,
-					 hw->fwlog_ring.size);
-	}
-
-	return data_copied;
-}
-
-/**
- * ice_debugfs_data_write - write into 'data' file
- * @filp: the opened file
- * @buf: where to find the user's data
- * @count: the length of the user's data
- * @ppos: file position offset
- */
-static ssize_t
-ice_debugfs_data_write(struct file *filp, const char __user *buf, size_t count,
-		       loff_t *ppos)
-{
-	struct ice_pf *pf = filp->private_data;
-	struct device *dev = ice_pf_to_dev(pf);
-	struct ice_hw *hw = &pf->hw;
-	ssize_t ret;
-
-	/* don't allow partial writes */
-	if (*ppos != 0)
-		return 0;
-
-	/* any value is allowed to clear the buffer so no need to even look at
-	 * what the value is
-	 */
-	if (!(hw->fwlog_cfg.options & ICE_FWLOG_OPTION_IS_REGISTERED)) {
-		hw->fwlog_ring.head = 0;
-		hw->fwlog_ring.tail = 0;
-	} else {
-		dev_info(dev, "Can't clear FW log data while FW log running\n");
-		ret = -EINVAL;
-		goto nr_buffs_write_error;
-	}
-
-	/* if we get here, nothing went wrong; return count since we didn't
-	 * really write anything
-	 */
-	ret = (ssize_t)count;
-
-nr_buffs_write_error:
-	/* This function always consumes all of the written input, or produces
-	 * an error. Check and enforce this. Otherwise, the write operation
-	 * won't complete properly.
-	 */
-	if (WARN_ON(ret != (ssize_t)count && ret >= 0))
-		ret = -EIO;
-
-	return ret;
-}
-
-static const struct file_operations ice_debugfs_data_fops = {
-	.owner = THIS_MODULE,
-	.open  = simple_open,
-	.read = ice_debugfs_data_read,
-	.write = ice_debugfs_data_write,
-};
-
-/**
- * ice_debugfs_fwlog_init - setup the debugfs directory
- * @pf: the ice that is starting up
- */
-void ice_debugfs_fwlog_init(struct ice_pf *pf)
+int ice_debugfs_pf_init(struct ice_pf *pf)
 {
 	const char *name = pci_name(pf->pdev);
-	struct dentry *fw_modules_dir;
-	struct dentry **fw_modules;
-	int i;
-
-	/* only support fw log commands on PF 0 */
-	if (pf->hw.bus.func)
-		return;
-
-	/* allocate space for this first because if it fails then we don't
-	 * need to unwind
-	 */
-	fw_modules = kcalloc(ICE_NR_FW_LOG_MODULES, sizeof(*fw_modules),
-			     GFP_KERNEL);
-	if (!fw_modules)
-		return;
 
 	pf->ice_debugfs_pf = debugfs_create_dir(name, ice_debugfs_root);
 	if (IS_ERR(pf->ice_debugfs_pf))
-		goto err_create_module_files;
-
-	pf->ice_debugfs_pf_fwlog = debugfs_create_dir("fwlog",
-						      pf->ice_debugfs_pf);
-	if (IS_ERR(pf->ice_debugfs_pf))
-		goto err_create_module_files;
+		return PTR_ERR(pf->ice_debugfs_pf);
 
-	fw_modules_dir = debugfs_create_dir("modules",
-					    pf->ice_debugfs_pf_fwlog);
-	if (IS_ERR(fw_modules_dir))
-		goto err_create_module_files;
-
-	for (i = 0; i < ICE_NR_FW_LOG_MODULES; i++) {
-		fw_modules[i] = debugfs_create_file(ice_fwlog_module_string[i],
-						    0600, fw_modules_dir, pf,
-						    &ice_debugfs_module_fops);
-		if (IS_ERR(fw_modules[i]))
-			goto err_create_module_files;
-	}
-
-	debugfs_create_file("nr_messages", 0600,
-			    pf->ice_debugfs_pf_fwlog, pf,
-			    &ice_debugfs_nr_messages_fops);
-
-	pf->ice_debugfs_pf_fwlog_modules = fw_modules;
-
-	debugfs_create_file("enable", 0600, pf->ice_debugfs_pf_fwlog,
-			    pf, &ice_debugfs_enable_fops);
-
-	debugfs_create_file("log_size", 0600, pf->ice_debugfs_pf_fwlog,
-			    pf, &ice_debugfs_log_size_fops);
-
-	debugfs_create_file("data", 0600, pf->ice_debugfs_pf_fwlog,
-			    pf, &ice_debugfs_data_fops);
-
-	return;
-
-err_create_module_files:
-	debugfs_remove_recursive(pf->ice_debugfs_pf_fwlog);
-	kfree(fw_modules);
+	return 0;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h
index 34fd604132f5..bd4e66df0372 100644
--- a/drivers/net/ethernet/intel/ice/ice_devids.h
+++ b/drivers/net/ethernet/intel/ice/ice_devids.h
@@ -6,6 +6,24 @@
 
 /* Device IDs */
 #define ICE_DEV_ID_E822_SI_DFLT         0x1888
+/* Intel(R) Ethernet Controller E835-CC for backplane */
+#define ICE_DEV_ID_E835CC_BACKPLANE	0x1248
+/* Intel(R) Ethernet Controller E835-CC for QSFP */
+#define ICE_DEV_ID_E835CC_QSFP56	0x1249
+/* Intel(R) Ethernet Controller E835-CC for SFP */
+#define ICE_DEV_ID_E835CC_SFP		0x124A
+/* Intel(R) Ethernet Controller E835-C for backplane */
+#define ICE_DEV_ID_E835C_BACKPLANE	0x1261
+/* Intel(R) Ethernet Controller E835-C for QSFP */
+#define ICE_DEV_ID_E835C_QSFP		0x1262
+/* Intel(R) Ethernet Controller E835-C for SFP */
+#define ICE_DEV_ID_E835C_SFP		0x1263
+/* Intel(R) Ethernet Controller E835-L for backplane */
+#define ICE_DEV_ID_E835_L_BACKPLANE	0x1265
+/* Intel(R) Ethernet Controller E835-L for QSFP */
+#define ICE_DEV_ID_E835_L_QSFP		0x1266
+/* Intel(R) Ethernet Controller E835-L for SFP */
+#define ICE_DEV_ID_E835_L_SFP		0x1267
 /* Intel(R) Ethernet Connection E823-L for backplane */
 #define ICE_DEV_ID_E823L_BACKPLANE	0x124C
 /* Intel(R) Ethernet Connection E823-L for SFP */
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c
index d5ad6d84007c..53b54e395a2e 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.c
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.c
@@ -11,6 +11,43 @@
 #define ICE_DPLL_RCLK_NUM_PER_PF		1
 #define ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT	25
 #define ICE_DPLL_PIN_GEN_RCLK_FREQ		1953125
+#define ICE_DPLL_PIN_PRIO_OUTPUT		0xff
+#define ICE_DPLL_INPUT_REF_NUM			10
+#define ICE_DPLL_PHASE_OFFSET_PERIOD		2
+#define ICE_DPLL_SW_PIN_INPUT_BASE_SFP		4
+#define ICE_DPLL_SW_PIN_INPUT_BASE_QSFP		6
+#define ICE_DPLL_SW_PIN_OUTPUT_BASE		0
+
+#define ICE_DPLL_PIN_SW_INPUT_ABS(in_idx) \
+	(ICE_DPLL_SW_PIN_INPUT_BASE_SFP + (in_idx))
+
+#define ICE_DPLL_PIN_SW_1_INPUT_ABS_IDX \
+	(ICE_DPLL_PIN_SW_INPUT_ABS(ICE_DPLL_PIN_SW_1_IDX))
+
+#define ICE_DPLL_PIN_SW_2_INPUT_ABS_IDX \
+	(ICE_DPLL_PIN_SW_INPUT_ABS(ICE_DPLL_PIN_SW_2_IDX))
+
+#define ICE_DPLL_PIN_SW_OUTPUT_ABS(out_idx) \
+	(ICE_DPLL_SW_PIN_OUTPUT_BASE + (out_idx))
+
+#define ICE_DPLL_PIN_SW_1_OUTPUT_ABS_IDX \
+	(ICE_DPLL_PIN_SW_OUTPUT_ABS(ICE_DPLL_PIN_SW_1_IDX))
+
+#define ICE_DPLL_PIN_SW_2_OUTPUT_ABS_IDX \
+	(ICE_DPLL_PIN_SW_OUTPUT_ABS(ICE_DPLL_PIN_SW_2_IDX))
+
+#define ICE_SR_PFA_DPLL_DEFAULTS		0x152
+#define ICE_DPLL_PFA_REF_SYNC_TYPE		0x2420
+#define ICE_DPLL_PFA_REF_SYNC_TYPE2		0x2424
+#define ICE_DPLL_PFA_END			0xFFFF
+#define ICE_DPLL_PFA_HEADER_LEN			4
+#define ICE_DPLL_PFA_ENTRY_LEN			3
+#define ICE_DPLL_PFA_MAILBOX_REF_SYNC_PIN_S	4
+#define ICE_DPLL_PFA_MASK_OFFSET		1
+#define ICE_DPLL_PFA_VALUE_OFFSET		2
+
+#define ICE_DPLL_E810C_SFP_NC_PINS		2
+#define ICE_DPLL_E810C_SFP_NC_START		4
 
 /**
  * enum ice_dpll_pin_type - enumerate ice pin types:
@@ -18,25 +55,61 @@
  * @ICE_DPLL_PIN_TYPE_INPUT: input pin
  * @ICE_DPLL_PIN_TYPE_OUTPUT: output pin
  * @ICE_DPLL_PIN_TYPE_RCLK_INPUT: recovery clock input pin
+ * @ICE_DPLL_PIN_TYPE_SOFTWARE: software controlled SMA/U.FL pins
  */
 enum ice_dpll_pin_type {
 	ICE_DPLL_PIN_INVALID,
 	ICE_DPLL_PIN_TYPE_INPUT,
 	ICE_DPLL_PIN_TYPE_OUTPUT,
 	ICE_DPLL_PIN_TYPE_RCLK_INPUT,
+	ICE_DPLL_PIN_TYPE_SOFTWARE,
 };
 
 static const char * const pin_type_name[] = {
 	[ICE_DPLL_PIN_TYPE_INPUT] = "input",
 	[ICE_DPLL_PIN_TYPE_OUTPUT] = "output",
 	[ICE_DPLL_PIN_TYPE_RCLK_INPUT] = "rclk-input",
+	[ICE_DPLL_PIN_TYPE_SOFTWARE] = "software",
 };
 
+static const char * const ice_dpll_sw_pin_sma[] = { "SMA1", "SMA2" };
+static const char * const ice_dpll_sw_pin_ufl[] = { "U.FL1", "U.FL2" };
+
 static const struct dpll_pin_frequency ice_esync_range[] = {
 	DPLL_PIN_FREQUENCY_RANGE(0, DPLL_PIN_FREQUENCY_1_HZ),
 };
 
 /**
+ * ice_dpll_is_sw_pin - check if given pin shall be controlled by SW
+ * @pf: private board structure
+ * @index: index of a pin as understood by FW
+ * @input: true for input, false for output
+ *
+ * Check if the pin shall be controlled by SW - instead of providing raw access
+ * for pin control. For E810 NIC with dpll there is additional MUX-related logic
+ * between SMA/U.FL pins/connectors and dpll device, best to give user access
+ * with series of wrapper functions as from user perspective they convey single
+ * functionality rather then separated pins.
+ *
+ * Return:
+ * * true - pin controlled by SW
+ * * false - pin not controlled by SW
+ */
+static bool ice_dpll_is_sw_pin(struct ice_pf *pf, u8 index, bool input)
+{
+	if (input && pf->hw.device_id == ICE_DEV_ID_E810C_QSFP)
+		index -= ICE_DPLL_SW_PIN_INPUT_BASE_QSFP -
+			 ICE_DPLL_SW_PIN_INPUT_BASE_SFP;
+
+	if ((input && (index == ICE_DPLL_PIN_SW_1_INPUT_ABS_IDX ||
+		       index == ICE_DPLL_PIN_SW_2_INPUT_ABS_IDX)) ||
+	    (!input && (index == ICE_DPLL_PIN_SW_1_OUTPUT_ABS_IDX ||
+			index == ICE_DPLL_PIN_SW_2_OUTPUT_ABS_IDX)))
+		return true;
+	return false;
+}
+
+/**
  * ice_dpll_is_reset - check if reset is in progress
  * @pf: private board structure
  * @extack: error reporting
@@ -95,9 +168,9 @@ ice_dpll_pin_freq_set(struct ice_pf *pf, struct ice_dpll_pin *pin,
 	}
 	if (ret) {
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to set pin freq:%u on pin:%u\n",
+				   "err:%d %s failed to set pin freq:%u on pin:%u",
 				   ret,
-				   ice_aq_str(pf->hw.adminq.sq_last_status),
+				   libie_aq_str(pf->hw.adminq.sq_last_status),
 				   freq, pin->idx);
 		return ret;
 	}
@@ -280,6 +353,87 @@ ice_dpll_output_frequency_get(const struct dpll_pin *pin, void *pin_priv,
 }
 
 /**
+ * ice_dpll_sw_pin_frequency_set - callback to set frequency of SW pin
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: pointer to dpll
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @frequency: on success holds pin's frequency
+ * @extack: error reporting
+ *
+ * Calls set frequency command for corresponding and active input/output pin.
+ *
+ * Context: Calls a function which acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error pin not active or couldn't get from hw
+ */
+static int
+ice_dpll_sw_pin_frequency_set(const struct dpll_pin *pin, void *pin_priv,
+			      const struct dpll_device *dpll, void *dpll_priv,
+			      u64 frequency, struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *sma = pin_priv;
+	int ret;
+
+	if (!sma->active) {
+		NL_SET_ERR_MSG(extack, "pin is not active");
+		return -EINVAL;
+	}
+	if (sma->direction == DPLL_PIN_DIRECTION_INPUT)
+		ret = ice_dpll_input_frequency_set(NULL, sma->input, dpll,
+						   dpll_priv, frequency,
+						   extack);
+	else
+		ret = ice_dpll_output_frequency_set(NULL, sma->output, dpll,
+						    dpll_priv, frequency,
+						    extack);
+
+	return ret;
+}
+
+/**
+ * ice_dpll_sw_pin_frequency_get - callback for get frequency of SW pin
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: pointer to dpll
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @frequency: on success holds pin's frequency
+ * @extack: error reporting
+ *
+ * Calls get frequency command for corresponding active input/output.
+ *
+ * Context: Calls a function which acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error pin not active or couldn't get from hw
+ */
+static int
+ice_dpll_sw_pin_frequency_get(const struct dpll_pin *pin, void *pin_priv,
+			      const struct dpll_device *dpll, void *dpll_priv,
+			      u64 *frequency, struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *sma = pin_priv;
+	int ret;
+
+	if (!sma->active) {
+		*frequency = 0;
+		return 0;
+	}
+	if (sma->direction == DPLL_PIN_DIRECTION_INPUT) {
+		ret = ice_dpll_input_frequency_get(NULL, sma->input, dpll,
+						   dpll_priv, frequency,
+						   extack);
+	} else {
+		ret = ice_dpll_output_frequency_get(NULL, sma->output, dpll,
+						    dpll_priv, frequency,
+						    extack);
+	}
+
+	return ret;
+}
+
+/**
  * ice_dpll_pin_enable - enable a pin on dplls
  * @hw: board private hw structure
  * @pin: pointer to a pin
@@ -322,8 +476,8 @@ ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin,
 	}
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to enable %s pin:%u\n",
-				   ret, ice_aq_str(hw->adminq.sq_last_status),
+				   "err:%d %s failed to enable %s pin:%u",
+				   ret, libie_aq_str(hw->adminq.sq_last_status),
 				   pin_type_name[pin_type], pin->idx);
 
 	return ret;
@@ -367,14 +521,75 @@ ice_dpll_pin_disable(struct ice_hw *hw, struct ice_dpll_pin *pin,
 	}
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to disable %s pin:%u\n",
-				   ret, ice_aq_str(hw->adminq.sq_last_status),
+				   "err:%d %s failed to disable %s pin:%u",
+				   ret, libie_aq_str(hw->adminq.sq_last_status),
 				   pin_type_name[pin_type], pin->idx);
 
 	return ret;
 }
 
 /**
+ * ice_dpll_sw_pins_update - update status of all SW pins
+ * @pf: private board struct
+ *
+ * Determine and update pin struct fields (direction/active) of their current
+ * values for all the SW controlled pins.
+ *
+ * Context: Call with pf->dplls.lock held
+ * Return:
+ * * 0 - OK
+ * * negative - error
+ */
+static int
+ice_dpll_sw_pins_update(struct ice_pf *pf)
+{
+	struct ice_dplls *d = &pf->dplls;
+	struct ice_dpll_pin *p;
+	u8 data = 0;
+	int ret;
+
+	ret = ice_read_sma_ctrl(&pf->hw, &data);
+	if (ret)
+		return ret;
+	/* no change since last check */
+	if (d->sma_data == data)
+		return 0;
+
+	/*
+	 * SMA1/U.FL1 vs SMA2/U.FL2 are using different bit scheme to decide
+	 * on their direction and if are active
+	 */
+	p = &d->sma[ICE_DPLL_PIN_SW_1_IDX];
+	p->active = true;
+	p->direction = DPLL_PIN_DIRECTION_INPUT;
+	if (data & ICE_SMA1_DIR_EN) {
+		p->direction = DPLL_PIN_DIRECTION_OUTPUT;
+		if (data & ICE_SMA1_TX_EN)
+			p->active = false;
+	}
+
+	p = &d->sma[ICE_DPLL_PIN_SW_2_IDX];
+	p->active = true;
+	p->direction = DPLL_PIN_DIRECTION_INPUT;
+	if ((data & ICE_SMA2_INACTIVE_MASK) == ICE_SMA2_INACTIVE_MASK)
+		p->active = false;
+	else if (data & ICE_SMA2_DIR_EN)
+		p->direction = DPLL_PIN_DIRECTION_OUTPUT;
+
+	p = &d->ufl[ICE_DPLL_PIN_SW_1_IDX];
+	if (!(data & (ICE_SMA1_DIR_EN | ICE_SMA1_TX_EN)))
+		p->active = true;
+	else
+		p->active = false;
+
+	p = &d->ufl[ICE_DPLL_PIN_SW_2_IDX];
+	p->active = (data & ICE_SMA2_DIR_EN) && !(data & ICE_SMA2_UFL2_RX_DIS);
+	d->sma_data = data;
+
+	return 0;
+}
+
+/**
  * ice_dpll_pin_state_update - update pin's state
  * @pf: private board struct
  * @pin: structure with pin attributes to be updated
@@ -471,6 +686,11 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin,
 					DPLL_PIN_STATE_DISCONNECTED;
 		}
 		break;
+	case ICE_DPLL_PIN_TYPE_SOFTWARE:
+		ret = ice_dpll_sw_pins_update(pf);
+		if (ret)
+			goto err;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -479,15 +699,15 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin,
 err:
 	if (extack)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to update %s pin:%u\n",
+				   "err:%d %s failed to update %s pin:%u",
 				   ret,
-				   ice_aq_str(pf->hw.adminq.sq_last_status),
+				   libie_aq_str(pf->hw.adminq.sq_last_status),
 				   pin_type_name[pin_type], pin->idx);
 	else
 		dev_err_ratelimited(ice_pf_to_dev(pf),
 				    "err:%d %s failed to update %s pin:%u\n",
 				    ret,
-				    ice_aq_str(pf->hw.adminq.sq_last_status),
+				    libie_aq_str(pf->hw.adminq.sq_last_status),
 				    pin_type_name[pin_type], pin->idx);
 	return ret;
 }
@@ -518,9 +738,9 @@ ice_dpll_hw_input_prio_set(struct ice_pf *pf, struct ice_dpll *dpll,
 				      (u8)prio);
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to set pin prio:%u on pin:%u\n",
+				   "err:%d %s failed to set pin prio:%u on pin:%u",
 				   ret,
-				   ice_aq_str(pf->hw.adminq.sq_last_status),
+				   libie_aq_str(pf->hw.adminq.sq_last_status),
 				   prio, pin->idx);
 	else
 		dpll->input_prio[pin->idx] = prio;
@@ -588,6 +808,67 @@ static int ice_dpll_mode_get(const struct dpll_device *dpll, void *dpll_priv,
 }
 
 /**
+ * ice_dpll_phase_offset_monitor_set - set phase offset monitor state
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @state: feature state to be set
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Enable/disable phase offset monitor feature of dpll.
+ *
+ * Context: Acquires and releases pf->dplls.lock
+ * Return: 0 - success
+ */
+static int ice_dpll_phase_offset_monitor_set(const struct dpll_device *dpll,
+					     void *dpll_priv,
+					     enum dpll_feature_state state,
+					     struct netlink_ext_ack *extack)
+{
+	struct ice_dpll *d = dpll_priv;
+	struct ice_pf *pf = d->pf;
+
+	mutex_lock(&pf->dplls.lock);
+	if (state == DPLL_FEATURE_STATE_ENABLE)
+		d->phase_offset_monitor_period = ICE_DPLL_PHASE_OFFSET_PERIOD;
+	else
+		d->phase_offset_monitor_period = 0;
+	mutex_unlock(&pf->dplls.lock);
+
+	return 0;
+}
+
+/**
+ * ice_dpll_phase_offset_monitor_get - get phase offset monitor state
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @state: on success holds current state of phase offset monitor
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Provides current state of phase offset monitor
+ * features on dpll device.
+ *
+ * Context: Acquires and releases pf->dplls.lock
+ * Return: 0 - success
+ */
+static int ice_dpll_phase_offset_monitor_get(const struct dpll_device *dpll,
+					     void *dpll_priv,
+					     enum dpll_feature_state *state,
+					     struct netlink_ext_ack *extack)
+{
+	struct ice_dpll *d = dpll_priv;
+	struct ice_pf *pf = d->pf;
+
+	mutex_lock(&pf->dplls.lock);
+	if (d->phase_offset_monitor_period)
+		*state = DPLL_FEATURE_STATE_ENABLE;
+	else
+		*state = DPLL_FEATURE_STATE_DISABLE;
+	mutex_unlock(&pf->dplls.lock);
+
+	return 0;
+}
+
+/**
  * ice_dpll_pin_state_set - set pin's state on dpll
  * @pin: pointer to a pin
  * @pin_priv: private data pointer passed on pin registration
@@ -793,6 +1074,270 @@ ice_dpll_input_state_get(const struct dpll_pin *pin, void *pin_priv,
 }
 
 /**
+ * ice_dpll_sma_direction_set - set direction of SMA pin
+ * @p: pointer to a pin
+ * @direction: requested direction of the pin
+ * @extack: error reporting
+ *
+ * Wrapper for dpll subsystem callback. Set direction of a SMA pin.
+ *
+ * Context: Call with pf->dplls.lock held
+ * Return:
+ * * 0 - success
+ * * negative - failed to get state
+ */
+static int ice_dpll_sma_direction_set(struct ice_dpll_pin *p,
+				      enum dpll_pin_direction direction,
+				      struct netlink_ext_ack *extack)
+{
+	u8 data;
+	int ret;
+
+	if (p->direction == direction && p->active)
+		return 0;
+	ret = ice_read_sma_ctrl(&p->pf->hw, &data);
+	if (ret)
+		return ret;
+
+	switch (p->idx) {
+	case ICE_DPLL_PIN_SW_1_IDX:
+		data &= ~ICE_SMA1_MASK;
+		if (direction == DPLL_PIN_DIRECTION_OUTPUT)
+			data |= ICE_SMA1_DIR_EN;
+		break;
+	case ICE_DPLL_PIN_SW_2_IDX:
+		if (direction == DPLL_PIN_DIRECTION_INPUT) {
+			data &= ~ICE_SMA2_DIR_EN;
+		} else {
+			data &= ~ICE_SMA2_TX_EN;
+			data |= ICE_SMA2_DIR_EN;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+	ret = ice_write_sma_ctrl(&p->pf->hw, data);
+	if (!ret)
+		ret = ice_dpll_pin_state_update(p->pf, p,
+						ICE_DPLL_PIN_TYPE_SOFTWARE,
+						extack);
+
+	return ret;
+}
+
+/**
+ * ice_dpll_ufl_pin_state_set - set U.FL pin state on dpll device
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @state: requested state of the pin
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Set the state of a pin.
+ *
+ * Context: Acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_ufl_pin_state_set(const struct dpll_pin *pin, void *pin_priv,
+			   const struct dpll_device *dpll, void *dpll_priv,
+			   enum dpll_pin_state state,
+			   struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv, *target;
+	struct ice_dpll *d = dpll_priv;
+	enum ice_dpll_pin_type type;
+	struct ice_pf *pf = p->pf;
+	struct ice_hw *hw;
+	bool enable;
+	u8 data;
+	int ret;
+
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
+	mutex_lock(&pf->dplls.lock);
+	hw = &pf->hw;
+	ret = ice_read_sma_ctrl(hw, &data);
+	if (ret)
+		goto unlock;
+
+	ret = -EINVAL;
+	switch (p->idx) {
+	case ICE_DPLL_PIN_SW_1_IDX:
+		if (state == DPLL_PIN_STATE_CONNECTED) {
+			data &= ~ICE_SMA1_MASK;
+			enable = true;
+		} else if (state == DPLL_PIN_STATE_DISCONNECTED) {
+			data |= ICE_SMA1_TX_EN;
+			enable = false;
+		} else {
+			goto unlock;
+		}
+		target = p->output;
+		type = ICE_DPLL_PIN_TYPE_OUTPUT;
+		break;
+	case ICE_DPLL_PIN_SW_2_IDX:
+		if (state == DPLL_PIN_STATE_SELECTABLE) {
+			data |= ICE_SMA2_DIR_EN;
+			data &= ~ICE_SMA2_UFL2_RX_DIS;
+			enable = true;
+		} else if (state == DPLL_PIN_STATE_DISCONNECTED) {
+			data |= ICE_SMA2_UFL2_RX_DIS;
+			enable = false;
+		} else {
+			goto unlock;
+		}
+		target = p->input;
+		type = ICE_DPLL_PIN_TYPE_INPUT;
+		break;
+	default:
+		goto unlock;
+	}
+
+	ret = ice_write_sma_ctrl(hw, data);
+	if (ret)
+		goto unlock;
+	ret = ice_dpll_pin_state_update(pf, p, ICE_DPLL_PIN_TYPE_SOFTWARE,
+					extack);
+	if (ret)
+		goto unlock;
+
+	if (enable)
+		ret = ice_dpll_pin_enable(hw, target, d->dpll_idx, type, extack);
+	else
+		ret = ice_dpll_pin_disable(hw, target, type, extack);
+	if (!ret)
+		ret = ice_dpll_pin_state_update(pf, target, type, extack);
+
+unlock:
+	mutex_unlock(&pf->dplls.lock);
+
+	return ret;
+}
+
+/**
+ * ice_dpll_sw_pin_state_get - get SW pin state
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @state: on success holds state of the pin
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Check state of a SW pin.
+ *
+ * Context: Acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_sw_pin_state_get(const struct dpll_pin *pin, void *pin_priv,
+			  const struct dpll_device *dpll, void *dpll_priv,
+			  enum dpll_pin_state *state,
+			  struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+	struct ice_dpll *d = dpll_priv;
+	struct ice_pf *pf = p->pf;
+	int ret = 0;
+
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+	mutex_lock(&pf->dplls.lock);
+	if (!p->active) {
+		*state = DPLL_PIN_STATE_DISCONNECTED;
+		goto unlock;
+	}
+
+	if (p->direction == DPLL_PIN_DIRECTION_INPUT) {
+		ret = ice_dpll_pin_state_update(pf, p->input,
+						ICE_DPLL_PIN_TYPE_INPUT,
+						extack);
+		if (ret)
+			goto unlock;
+		*state = p->input->state[d->dpll_idx];
+	} else {
+		ret = ice_dpll_pin_state_update(pf, p->output,
+						ICE_DPLL_PIN_TYPE_OUTPUT,
+						extack);
+		if (ret)
+			goto unlock;
+		*state = p->output->state[d->dpll_idx];
+	}
+unlock:
+	mutex_unlock(&pf->dplls.lock);
+
+	return ret;
+}
+
+/**
+ * ice_dpll_sma_pin_state_set - set SMA pin state on dpll device
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @state: requested state of the pin
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Set state of a pin.
+ *
+ * Context: Acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - failed to get state
+ */
+static int
+ice_dpll_sma_pin_state_set(const struct dpll_pin *pin, void *pin_priv,
+			   const struct dpll_device *dpll, void *dpll_priv,
+			   enum dpll_pin_state state,
+			   struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *sma = pin_priv, *target;
+	struct ice_dpll *d = dpll_priv;
+	struct ice_pf *pf = sma->pf;
+	enum ice_dpll_pin_type type;
+	bool enable;
+	int ret;
+
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
+	mutex_lock(&pf->dplls.lock);
+	if (!sma->active) {
+		ret = ice_dpll_sma_direction_set(sma, sma->direction, extack);
+		if (ret)
+			goto unlock;
+	}
+	if (sma->direction == DPLL_PIN_DIRECTION_INPUT) {
+		enable = state == DPLL_PIN_STATE_SELECTABLE;
+		target = sma->input;
+		type = ICE_DPLL_PIN_TYPE_INPUT;
+	} else {
+		enable = state == DPLL_PIN_STATE_CONNECTED;
+		target = sma->output;
+		type = ICE_DPLL_PIN_TYPE_OUTPUT;
+	}
+
+	if (enable)
+		ret = ice_dpll_pin_enable(&pf->hw, target, d->dpll_idx, type,
+					  extack);
+	else
+		ret = ice_dpll_pin_disable(&pf->hw, target, type, extack);
+	if (!ret)
+		ret = ice_dpll_pin_state_update(pf, target, type, extack);
+
+unlock:
+	mutex_unlock(&pf->dplls.lock);
+
+	return ret;
+}
+
+/**
  * ice_dpll_input_prio_get - get dpll's input prio
  * @pin: pointer to a pin
  * @pin_priv: private data pointer passed on pin registration
@@ -860,6 +1405,47 @@ ice_dpll_input_prio_set(const struct dpll_pin *pin, void *pin_priv,
 	return ret;
 }
 
+static int
+ice_dpll_sw_input_prio_get(const struct dpll_pin *pin, void *pin_priv,
+			   const struct dpll_device *dpll, void *dpll_priv,
+			   u32 *prio, struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+	struct ice_dpll *d = dpll_priv;
+	struct ice_pf *pf = d->pf;
+
+	mutex_lock(&pf->dplls.lock);
+	if (p->input && p->direction == DPLL_PIN_DIRECTION_INPUT)
+		*prio = d->input_prio[p->input->idx];
+	else
+		*prio = ICE_DPLL_PIN_PRIO_OUTPUT;
+	mutex_unlock(&pf->dplls.lock);
+
+	return 0;
+}
+
+static int
+ice_dpll_sw_input_prio_set(const struct dpll_pin *pin, void *pin_priv,
+			   const struct dpll_device *dpll, void *dpll_priv,
+			   u32 prio, struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+	struct ice_dpll *d = dpll_priv;
+	struct ice_pf *pf = d->pf;
+	int ret;
+
+	if (!p->input || p->direction != DPLL_PIN_DIRECTION_INPUT)
+		return -EINVAL;
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
+	mutex_lock(&pf->dplls.lock);
+	ret = ice_dpll_hw_input_prio_set(pf, d, p->input, prio, extack);
+	mutex_unlock(&pf->dplls.lock);
+
+	return ret;
+}
+
 /**
  * ice_dpll_input_direction - callback for get input pin direction
  * @pin: pointer to a pin
@@ -911,6 +1497,76 @@ ice_dpll_output_direction(const struct dpll_pin *pin, void *pin_priv,
 }
 
 /**
+ * ice_dpll_pin_sma_direction_set - callback for set SMA pin direction
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @direction: requested pin direction
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Handler for setting direction of a SMA pin.
+ *
+ * Context: Acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_pin_sma_direction_set(const struct dpll_pin *pin, void *pin_priv,
+			       const struct dpll_device *dpll, void *dpll_priv,
+			       enum dpll_pin_direction direction,
+			       struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+	struct ice_pf *pf = p->pf;
+	int ret;
+
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
+	mutex_lock(&pf->dplls.lock);
+	ret = ice_dpll_sma_direction_set(p, direction, extack);
+	mutex_unlock(&pf->dplls.lock);
+
+	return ret;
+}
+
+/**
+ * ice_dpll_pin_sw_direction_get - callback for get SW pin direction
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @direction: on success holds pin direction
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Handler for getting direction of a SMA pin.
+ *
+ * Context: Acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_pin_sw_direction_get(const struct dpll_pin *pin, void *pin_priv,
+			      const struct dpll_device *dpll, void *dpll_priv,
+			      enum dpll_pin_direction *direction,
+			      struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+	struct ice_pf *pf = p->pf;
+
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+	mutex_lock(&pf->dplls.lock);
+	*direction = p->direction;
+	mutex_unlock(&pf->dplls.lock);
+
+	return 0;
+}
+
+/**
  * ice_dpll_pin_phase_adjust_get - callback for get pin phase adjust value
  * @pin: pointer to a pin
  * @pin_priv: private data pointer passed on pin registration
@@ -1004,9 +1660,9 @@ ice_dpll_pin_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv,
 	mutex_unlock(&pf->dplls.lock);
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to set pin phase_adjust:%d for pin:%u on dpll:%u\n",
+				   "err:%d %s failed to set pin phase_adjust:%d for pin:%u on dpll:%u",
 				   ret,
-				   ice_aq_str(pf->hw.adminq.sq_last_status),
+				   libie_aq_str(pf->hw.adminq.sq_last_status),
 				   phase_adjust, p->idx, d->dpll_idx);
 
 	return ret;
@@ -1024,7 +1680,7 @@ ice_dpll_pin_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv,
  * Dpll subsystem callback. Wraps a handler for setting phase adjust on input
  * pin.
  *
- * Context: Calls a function which acquires pf->dplls.lock
+ * Context: Calls a function which acquires and releases pf->dplls.lock
  * Return:
  * * 0 - success
  * * negative - error
@@ -1068,6 +1724,82 @@ ice_dpll_output_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv,
 					     ICE_DPLL_PIN_TYPE_OUTPUT);
 }
 
+/**
+ * ice_dpll_sw_phase_adjust_get - callback for get SW pin phase adjust
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @phase_adjust: on success holds phase adjust value
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Wraps a handler for getting phase adjust on sw
+ * pin.
+ *
+ * Context: Calls a function which acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_sw_phase_adjust_get(const struct dpll_pin *pin, void *pin_priv,
+			     const struct dpll_device *dpll, void *dpll_priv,
+			     s32 *phase_adjust,
+			     struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+
+	if (p->direction == DPLL_PIN_DIRECTION_INPUT)
+		return ice_dpll_pin_phase_adjust_get(p->input->pin, p->input,
+						     dpll, dpll_priv,
+						     phase_adjust, extack);
+	else
+		return ice_dpll_pin_phase_adjust_get(p->output->pin, p->output,
+						     dpll, dpll_priv,
+						     phase_adjust, extack);
+}
+
+/**
+ * ice_dpll_sw_phase_adjust_set - callback for set SW pin phase adjust value
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @phase_adjust: phase_adjust to be set
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Wraps a handler for setting phase adjust on output
+ * pin.
+ *
+ * Context: Calls a function which acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_sw_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv,
+			     const struct dpll_device *dpll, void *dpll_priv,
+			     s32 phase_adjust,
+			     struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+
+	if (!p->active) {
+		NL_SET_ERR_MSG(extack, "pin is not active");
+		return -EINVAL;
+	}
+	if (p->direction == DPLL_PIN_DIRECTION_INPUT)
+		return ice_dpll_pin_phase_adjust_set(p->input->pin, p->input,
+						     dpll, dpll_priv,
+						     phase_adjust, extack,
+						     ICE_DPLL_PIN_TYPE_INPUT);
+	else
+		return ice_dpll_pin_phase_adjust_set(p->output->pin, p->output,
+						     dpll, dpll_priv,
+						     phase_adjust, extack,
+						     ICE_DPLL_PIN_TYPE_OUTPUT);
+}
+
 #define ICE_DPLL_PHASE_OFFSET_DIVIDER	100
 #define ICE_DPLL_PHASE_OFFSET_FACTOR		\
 	(DPLL_PHASE_OFFSET_DIVIDER / ICE_DPLL_PHASE_OFFSET_DIVIDER)
@@ -1093,12 +1825,16 @@ ice_dpll_phase_offset_get(const struct dpll_pin *pin, void *pin_priv,
 			  const struct dpll_device *dpll, void *dpll_priv,
 			  s64 *phase_offset, struct netlink_ext_ack *extack)
 {
+	struct ice_dpll_pin *p = pin_priv;
 	struct ice_dpll *d = dpll_priv;
 	struct ice_pf *pf = d->pf;
 
 	mutex_lock(&pf->dplls.lock);
-	if (d->active_input == pin)
+	if (d->active_input == pin || (p->input &&
+				       d->active_input == p->input->pin))
 		*phase_offset = d->phase_offset * ICE_DPLL_PHASE_OFFSET_FACTOR;
+	else if (d->phase_offset_monitor_period)
+		*phase_offset = p->phase_offset * ICE_DPLL_PHASE_OFFSET_FACTOR;
 	else
 		*phase_offset = 0;
 	mutex_unlock(&pf->dplls.lock);
@@ -1315,6 +2051,219 @@ ice_dpll_input_esync_get(const struct dpll_pin *pin, void *pin_priv,
 }
 
 /**
+ * ice_dpll_sw_esync_set - callback for setting embedded sync on SW pin
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @freq: requested embedded sync frequency
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Handler for setting embedded sync frequency value
+ * on SW pin.
+ *
+ * Context: Calls a function which acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_sw_esync_set(const struct dpll_pin *pin, void *pin_priv,
+		      const struct dpll_device *dpll, void *dpll_priv,
+		      u64 freq, struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+
+	if (!p->active) {
+		NL_SET_ERR_MSG(extack, "pin is not active");
+		return -EINVAL;
+	}
+	if (p->direction == DPLL_PIN_DIRECTION_INPUT)
+		return ice_dpll_input_esync_set(p->input->pin, p->input, dpll,
+						dpll_priv, freq, extack);
+	else
+		return ice_dpll_output_esync_set(p->output->pin, p->output,
+						 dpll, dpll_priv, freq, extack);
+}
+
+/**
+ * ice_dpll_sw_esync_get - callback for getting embedded sync on SW pin
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @esync: on success holds embedded sync frequency and properties
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Handler for getting embedded sync frequency value
+ * of SW pin.
+ *
+ * Context: Calls a function which acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_sw_esync_get(const struct dpll_pin *pin, void *pin_priv,
+		      const struct dpll_device *dpll, void *dpll_priv,
+		      struct dpll_pin_esync *esync,
+		      struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+
+	if (p->direction == DPLL_PIN_DIRECTION_INPUT)
+		return ice_dpll_input_esync_get(p->input->pin, p->input, dpll,
+						dpll_priv, esync, extack);
+	else
+		return ice_dpll_output_esync_get(p->output->pin, p->output,
+						 dpll, dpll_priv, esync,
+						 extack);
+}
+
+/*
+ * ice_dpll_input_ref_sync_set - callback for setting reference sync feature
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @ref_pin: pin pointer for reference sync pair
+ * @ref_pin_priv: private data pointer of ref_pin
+ * @state: requested state for reference sync for pin pair
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Handler for setting reference sync frequency
+ * feature for input pin.
+ *
+ * Context: Acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_input_ref_sync_set(const struct dpll_pin *pin, void *pin_priv,
+			    const struct dpll_pin *ref_pin, void *ref_pin_priv,
+			    const enum dpll_pin_state state,
+			    struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+	struct ice_pf *pf = p->pf;
+	u8 flags_en = 0;
+	int ret;
+
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+	mutex_lock(&pf->dplls.lock);
+
+	if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN)
+		flags_en = ICE_AQC_SET_CGU_IN_CFG_FLG2_INPUT_EN;
+	if (state == DPLL_PIN_STATE_CONNECTED)
+		flags_en |= ICE_AQC_CGU_IN_CFG_FLG2_REFSYNC_EN;
+	ret = ice_aq_set_input_pin_cfg(&pf->hw, p->idx, 0, flags_en, 0, 0);
+	if (!ret)
+		ret = ice_dpll_pin_state_update(pf, p, ICE_DPLL_PIN_TYPE_INPUT,
+						extack);
+	mutex_unlock(&pf->dplls.lock);
+
+	return ret;
+}
+
+/**
+ * ice_dpll_input_ref_sync_get - callback for getting reference sync config
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @ref_pin: pin pointer for reference sync pair
+ * @ref_pin_priv: private data pointer of ref_pin
+ * @state: on success holds reference sync state for pin pair
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Handler for setting reference sync frequency
+ * feature for input pin.
+ *
+ * Context: Acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_input_ref_sync_get(const struct dpll_pin *pin, void *pin_priv,
+			    const struct dpll_pin *ref_pin, void *ref_pin_priv,
+			    enum dpll_pin_state *state,
+			    struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+	struct ice_pf *pf = p->pf;
+
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+	mutex_lock(&pf->dplls.lock);
+	if (p->flags[0] & ICE_AQC_CGU_IN_CFG_FLG2_REFSYNC_EN)
+		*state = DPLL_PIN_STATE_CONNECTED;
+	else
+		*state = DPLL_PIN_STATE_DISCONNECTED;
+	mutex_unlock(&pf->dplls.lock);
+
+	return 0;
+}
+
+/*
+ * ice_dpll_sw_input_ref_sync_set - callback for setting reference sync feature
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @ref_pin: pin pointer for reference sync pair
+ * @ref_pin_priv: private data pointer of ref_pin
+ * @state: requested state for reference sync for pin pair
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Handler for setting reference sync
+ * feature for input pins.
+ *
+ * Context: Calls a function which acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_sw_input_ref_sync_set(const struct dpll_pin *pin, void *pin_priv,
+			       const struct dpll_pin *ref_pin,
+			       void *ref_pin_priv,
+			       const enum dpll_pin_state state,
+			       struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+
+	return ice_dpll_input_ref_sync_set(pin, p->input, ref_pin, ref_pin_priv,
+					   state, extack);
+}
+
+/**
+ * ice_dpll_sw_input_ref_sync_get - callback for getting reference sync config
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @ref_pin: pin pointer for reference sync pair
+ * @ref_pin_priv: private data pointer of ref_pin
+ * @state: on success holds reference sync state for pin pair
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Handler for setting reference sync feature for
+ * input pins.
+ *
+ * Context: Calls a function which acquires and releases pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_sw_input_ref_sync_get(const struct dpll_pin *pin, void *pin_priv,
+			       const struct dpll_pin *ref_pin,
+			       void *ref_pin_priv,
+			       enum dpll_pin_state *state,
+			       struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+
+	return ice_dpll_input_ref_sync_get(pin, p->input, ref_pin, ref_pin_priv,
+					   state, extack);
+}
+
+/**
  * ice_dpll_rclk_state_on_pin_set - set a state on rclk pin
  * @pin: pointer to a pin
  * @pin_priv: private data pointer passed on pin registration
@@ -1362,9 +2311,9 @@ ice_dpll_rclk_state_on_pin_set(const struct dpll_pin *pin, void *pin_priv,
 					 &p->freq);
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to set pin state:%u for pin:%u on parent:%u\n",
+				   "err:%d %s failed to set pin state:%u for pin:%u on parent:%u",
 				   ret,
-				   ice_aq_str(pf->hw.adminq.sq_last_status),
+				   libie_aq_str(pf->hw.adminq.sq_last_status),
 				   state, p->idx, parent->idx);
 unlock:
 	mutex_unlock(&pf->dplls.lock);
@@ -1427,6 +2376,37 @@ static const struct dpll_pin_ops ice_dpll_rclk_ops = {
 	.direction_get = ice_dpll_input_direction,
 };
 
+static const struct dpll_pin_ops ice_dpll_pin_sma_ops = {
+	.state_on_dpll_set = ice_dpll_sma_pin_state_set,
+	.state_on_dpll_get = ice_dpll_sw_pin_state_get,
+	.direction_get = ice_dpll_pin_sw_direction_get,
+	.direction_set = ice_dpll_pin_sma_direction_set,
+	.prio_get = ice_dpll_sw_input_prio_get,
+	.prio_set = ice_dpll_sw_input_prio_set,
+	.frequency_get = ice_dpll_sw_pin_frequency_get,
+	.frequency_set = ice_dpll_sw_pin_frequency_set,
+	.phase_adjust_get = ice_dpll_sw_phase_adjust_get,
+	.phase_adjust_set = ice_dpll_sw_phase_adjust_set,
+	.phase_offset_get = ice_dpll_phase_offset_get,
+	.esync_set = ice_dpll_sw_esync_set,
+	.esync_get = ice_dpll_sw_esync_get,
+	.ref_sync_set = ice_dpll_sw_input_ref_sync_set,
+	.ref_sync_get = ice_dpll_sw_input_ref_sync_get,
+};
+
+static const struct dpll_pin_ops ice_dpll_pin_ufl_ops = {
+	.state_on_dpll_set = ice_dpll_ufl_pin_state_set,
+	.state_on_dpll_get = ice_dpll_sw_pin_state_get,
+	.direction_get = ice_dpll_pin_sw_direction_get,
+	.frequency_get = ice_dpll_sw_pin_frequency_get,
+	.frequency_set = ice_dpll_sw_pin_frequency_set,
+	.esync_set = ice_dpll_sw_esync_set,
+	.esync_get = ice_dpll_sw_esync_get,
+	.phase_adjust_get = ice_dpll_sw_phase_adjust_get,
+	.phase_adjust_set = ice_dpll_sw_phase_adjust_set,
+	.phase_offset_get = ice_dpll_phase_offset_get,
+};
+
 static const struct dpll_pin_ops ice_dpll_input_ops = {
 	.frequency_get = ice_dpll_input_frequency_get,
 	.frequency_set = ice_dpll_input_frequency_set,
@@ -1440,6 +2420,8 @@ static const struct dpll_pin_ops ice_dpll_input_ops = {
 	.phase_offset_get = ice_dpll_phase_offset_get,
 	.esync_set = ice_dpll_input_esync_set,
 	.esync_get = ice_dpll_input_esync_get,
+	.ref_sync_set = ice_dpll_input_ref_sync_set,
+	.ref_sync_get = ice_dpll_input_ref_sync_get,
 };
 
 static const struct dpll_pin_ops ice_dpll_output_ops = {
@@ -1459,6 +2441,13 @@ static const struct dpll_device_ops ice_dpll_ops = {
 	.mode_get = ice_dpll_mode_get,
 };
 
+static const struct dpll_device_ops ice_dpll_pom_ops = {
+	.lock_status_get = ice_dpll_lock_status_get,
+	.mode_get = ice_dpll_mode_get,
+	.phase_offset_monitor_set = ice_dpll_phase_offset_monitor_set,
+	.phase_offset_monitor_get = ice_dpll_phase_offset_monitor_get,
+};
+
 /**
  * ice_generate_clock_id - generates unique clock_id for registering dpll.
  * @pf: board private structure
@@ -1504,6 +2493,110 @@ static void ice_dpll_notify_changes(struct ice_dpll *d)
 }
 
 /**
+ * ice_dpll_is_pps_phase_monitor - check if dpll capable of phase offset monitor
+ * @pf: pf private structure
+ *
+ * Check if firmware is capable of supporting admin command to provide
+ * phase offset monitoring on all the input pins on PPS dpll.
+ *
+ * Returns:
+ * * true - PPS dpll phase offset monitoring is supported
+ * * false - PPS dpll phase offset monitoring is not supported
+ */
+static bool ice_dpll_is_pps_phase_monitor(struct ice_pf *pf)
+{
+	struct ice_cgu_input_measure meas[ICE_DPLL_INPUT_REF_NUM];
+	int ret = ice_aq_get_cgu_input_pin_measure(&pf->hw, DPLL_TYPE_PPS, meas,
+						   ARRAY_SIZE(meas));
+
+	if (ret && pf->hw.adminq.sq_last_status == LIBIE_AQ_RC_ESRCH)
+		return false;
+
+	return true;
+}
+
+/**
+ * ice_dpll_pins_notify_mask - notify dpll subsystem about bulk pin changes
+ * @pins: array of ice_dpll_pin pointers registered within dpll subsystem
+ * @pin_num: number of pins
+ * @phase_offset_ntf_mask: bitmask of pin indexes to notify
+ *
+ * Iterate over array of pins and call dpll subsystem pin notify if
+ * corresponding pin index within bitmask is set.
+ *
+ * Context: Must be called while pf->dplls.lock is released.
+ */
+static void ice_dpll_pins_notify_mask(struct ice_dpll_pin *pins,
+				      u8 pin_num,
+				      u32 phase_offset_ntf_mask)
+{
+	int i = 0;
+
+	for (i = 0; i < pin_num; i++)
+		if (phase_offset_ntf_mask & (1 << i))
+			dpll_pin_change_ntf(pins[i].pin);
+}
+
+/**
+ * ice_dpll_pps_update_phase_offsets - update phase offset measurements
+ * @pf: pf private structure
+ * @phase_offset_pins_updated: returns mask of updated input pin indexes
+ *
+ * Read phase offset measurements for PPS dpll device and store values in
+ * input pins array. On success phase_offset_pins_updated - fills bitmask of
+ * updated input pin indexes, pins shall be notified.
+ *
+ * Context: Shall be called with pf->dplls.lock being locked.
+ * Returns:
+ * * 0 - success or no data available
+ * * negative - AQ failure
+ */
+static int ice_dpll_pps_update_phase_offsets(struct ice_pf *pf,
+					     u32 *phase_offset_pins_updated)
+{
+	struct ice_cgu_input_measure meas[ICE_DPLL_INPUT_REF_NUM];
+	struct ice_dpll_pin *p;
+	s64 phase_offset, tmp;
+	int i, j, ret;
+
+	*phase_offset_pins_updated = 0;
+	ret = ice_aq_get_cgu_input_pin_measure(&pf->hw, DPLL_TYPE_PPS, meas,
+					       ARRAY_SIZE(meas));
+	if (ret && pf->hw.adminq.sq_last_status == LIBIE_AQ_RC_EAGAIN) {
+		return 0;
+	} else if (ret) {
+		dev_err(ice_pf_to_dev(pf),
+			"failed to get input pin measurements dpll=%d, ret=%d %s\n",
+			DPLL_TYPE_PPS, ret,
+			libie_aq_str(pf->hw.adminq.sq_last_status));
+		return ret;
+	}
+	for (i = 0; i < pf->dplls.num_inputs; i++) {
+		p = &pf->dplls.inputs[i];
+		phase_offset = 0;
+		for (j = 0; j < ICE_CGU_INPUT_PHASE_OFFSET_BYTES; j++) {
+			tmp = meas[i].phase_offset[j];
+#ifdef __LITTLE_ENDIAN
+			phase_offset += tmp << 8 * j;
+#else
+			phase_offset += tmp << 8 *
+				(ICE_CGU_INPUT_PHASE_OFFSET_BYTES - 1 - j);
+#endif
+		}
+		phase_offset = sign_extend64(phase_offset, 47);
+		if (p->phase_offset != phase_offset) {
+			dev_dbg(ice_pf_to_dev(pf),
+				"phase offset changed for pin:%d old:%llx, new:%llx\n",
+				p->idx, p->phase_offset, phase_offset);
+			p->phase_offset = phase_offset;
+			*phase_offset_pins_updated |= (1 << i);
+		}
+	}
+
+	return 0;
+}
+
+/**
  * ice_dpll_update_state - update dpll state
  * @pf: pf private structure
  * @d: pointer to queried dpll device
@@ -1534,7 +2627,7 @@ ice_dpll_update_state(struct ice_pf *pf, struct ice_dpll *d, bool init)
 		dev_err(ice_pf_to_dev(pf),
 			"update dpll=%d state failed, ret=%d %s\n",
 			d->dpll_idx, ret,
-			ice_aq_str(pf->hw.adminq.sq_last_status));
+			libie_aq_str(pf->hw.adminq.sq_last_status));
 		return ret;
 	}
 	if (init) {
@@ -1589,14 +2682,19 @@ static void ice_dpll_periodic_work(struct kthread_work *work)
 	struct ice_pf *pf = container_of(d, struct ice_pf, dplls);
 	struct ice_dpll *de = &pf->dplls.eec;
 	struct ice_dpll *dp = &pf->dplls.pps;
+	u32 phase_offset_ntf = 0;
 	int ret = 0;
 
 	if (ice_is_reset_in_progress(pf->state))
 		goto resched;
 	mutex_lock(&pf->dplls.lock);
+	d->periodic_counter++;
 	ret = ice_dpll_update_state(pf, de, false);
 	if (!ret)
 		ret = ice_dpll_update_state(pf, dp, false);
+	if (!ret && dp->phase_offset_monitor_period &&
+	    d->periodic_counter % dp->phase_offset_monitor_period == 0)
+		ret = ice_dpll_pps_update_phase_offsets(pf, &phase_offset_ntf);
 	if (ret) {
 		d->cgu_state_acq_err_num++;
 		/* stop rescheduling this worker */
@@ -1611,6 +2709,9 @@ static void ice_dpll_periodic_work(struct kthread_work *work)
 	mutex_unlock(&pf->dplls.lock);
 	ice_dpll_notify_changes(de);
 	ice_dpll_notify_changes(dp);
+	if (phase_offset_ntf)
+		ice_dpll_pins_notify_mask(d->inputs, d->num_inputs,
+					  phase_offset_ntf);
 
 resched:
 	/* Run twice a second or reschedule if update failed */
@@ -1620,6 +2721,88 @@ resched:
 }
 
 /**
+ * ice_dpll_init_ref_sync_inputs - initialize reference sync pin pairs
+ * @pf: pf private structure
+ *
+ * Read DPLL TLV capabilities and initialize reference sync pin pairs in
+ * dpll subsystem.
+ *
+ * Return:
+ * * 0 - success or nothing to do (no ref-sync tlv are present)
+ * * negative - AQ failure
+ */
+static int ice_dpll_init_ref_sync_inputs(struct ice_pf *pf)
+{
+	struct ice_dpll_pin *inputs = pf->dplls.inputs;
+	struct ice_hw *hw = &pf->hw;
+	u16 addr, len, end, hdr;
+	int ret;
+
+	ret = ice_get_pfa_module_tlv(hw, &hdr, &len, ICE_SR_PFA_DPLL_DEFAULTS);
+	if (ret) {
+		dev_err(ice_pf_to_dev(pf),
+			"Failed to read PFA dpll defaults TLV ret=%d\n", ret);
+		return ret;
+	}
+	end = hdr + len;
+
+	for (addr = hdr + ICE_DPLL_PFA_HEADER_LEN; addr < end;
+	     addr += ICE_DPLL_PFA_ENTRY_LEN) {
+		unsigned long bit, ul_mask, offset;
+		u16 pin, mask, buf;
+		bool valid = false;
+
+		ret = ice_read_sr_word(hw, addr, &buf);
+		if (ret)
+			return ret;
+
+		switch (buf) {
+		case ICE_DPLL_PFA_REF_SYNC_TYPE:
+		case ICE_DPLL_PFA_REF_SYNC_TYPE2:
+		{
+			u16 mask_addr = addr + ICE_DPLL_PFA_MASK_OFFSET;
+			u16 val_addr = addr + ICE_DPLL_PFA_VALUE_OFFSET;
+
+			ret = ice_read_sr_word(hw, mask_addr, &mask);
+			if (ret)
+				return ret;
+			ret = ice_read_sr_word(hw, val_addr, &pin);
+			if (ret)
+				return ret;
+			if (buf == ICE_DPLL_PFA_REF_SYNC_TYPE)
+				pin >>= ICE_DPLL_PFA_MAILBOX_REF_SYNC_PIN_S;
+			valid = true;
+			break;
+		}
+		case ICE_DPLL_PFA_END:
+			addr = end;
+			break;
+		default:
+			continue;
+		}
+		if (!valid)
+			continue;
+
+		ul_mask = mask;
+		offset = 0;
+		for_each_set_bit(bit, &ul_mask, BITS_PER_TYPE(u16)) {
+			int i, j;
+
+			if (hw->device_id == ICE_DEV_ID_E810C_SFP &&
+			    pin > ICE_DPLL_E810C_SFP_NC_START)
+				offset = -ICE_DPLL_E810C_SFP_NC_PINS;
+			i = pin + offset;
+			j = bit + offset;
+			if (i < 0 || j < 0)
+				return -ERANGE;
+			inputs[i].ref_sync = j;
+		}
+	}
+
+	return 0;
+}
+
+/**
  * ice_dpll_release_pins - release pins resources from dpll subsystem
  * @pins: pointer to pins array
  * @count: number of pins
@@ -1689,7 +2872,38 @@ ice_dpll_unregister_pins(struct dpll_device *dpll, struct ice_dpll_pin *pins,
 	int i;
 
 	for (i = 0; i < count; i++)
-		dpll_pin_unregister(dpll, pins[i].pin, ops, &pins[i]);
+		if (!pins[i].hidden)
+			dpll_pin_unregister(dpll, pins[i].pin, ops, &pins[i]);
+}
+
+/**
+ * ice_dpll_pin_ref_sync_register - register reference sync pins
+ * @pins: pointer to pins array
+ * @count: number of pins
+ *
+ * Register reference sync pins in dpll subsystem.
+ *
+ * Return:
+ * * 0 - success
+ * * negative - registration failure reason
+ */
+static int
+ice_dpll_pin_ref_sync_register(struct ice_dpll_pin *pins, int count)
+{
+	int ret, i;
+
+	for (i = 0; i < count; i++) {
+		if (!pins[i].hidden && pins[i].ref_sync) {
+			int j = pins[i].ref_sync;
+
+			ret = dpll_pin_ref_sync_pair_add(pins[i].pin,
+							 pins[j].pin);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
 }
 
 /**
@@ -1712,16 +2926,19 @@ ice_dpll_register_pins(struct dpll_device *dpll, struct ice_dpll_pin *pins,
 	int ret, i;
 
 	for (i = 0; i < count; i++) {
-		ret = dpll_pin_register(dpll, pins[i].pin, ops, &pins[i]);
-		if (ret)
-			goto unregister_pins;
+		if (!pins[i].hidden) {
+			ret = dpll_pin_register(dpll, pins[i].pin, ops, &pins[i]);
+			if (ret)
+				goto unregister_pins;
+		}
 	}
 
 	return 0;
 
 unregister_pins:
 	while (--i >= 0)
-		dpll_pin_unregister(dpll, pins[i].pin, ops, &pins[i]);
+		if (!pins[i].hidden)
+			dpll_pin_unregister(dpll, pins[i].pin, ops, &pins[i]);
 	return ret;
 }
 
@@ -1909,6 +3126,18 @@ static void ice_dpll_deinit_pins(struct ice_pf *pf, bool cgu)
 		ice_dpll_unregister_pins(de->dpll, outputs,
 					 &ice_dpll_output_ops, num_outputs);
 		ice_dpll_release_pins(outputs, num_outputs);
+		if (!pf->dplls.generic) {
+			ice_dpll_deinit_direct_pins(cgu, pf->dplls.ufl,
+						    ICE_DPLL_PIN_SW_NUM,
+						    &ice_dpll_pin_ufl_ops,
+						    pf->dplls.pps.dpll,
+						    pf->dplls.eec.dpll);
+			ice_dpll_deinit_direct_pins(cgu, pf->dplls.sma,
+						    ICE_DPLL_PIN_SW_NUM,
+						    &ice_dpll_pin_sma_ops,
+						    pf->dplls.pps.dpll,
+						    pf->dplls.eec.dpll);
+		}
 	}
 }
 
@@ -1926,8 +3155,7 @@ static void ice_dpll_deinit_pins(struct ice_pf *pf, bool cgu)
  */
 static int ice_dpll_init_pins(struct ice_pf *pf, bool cgu)
 {
-	u32 rclk_idx;
-	int ret;
+	int ret, count;
 
 	ret = ice_dpll_init_direct_pins(pf, cgu, pf->dplls.inputs, 0,
 					pf->dplls.num_inputs,
@@ -1935,23 +3163,64 @@ static int ice_dpll_init_pins(struct ice_pf *pf, bool cgu)
 					pf->dplls.eec.dpll, pf->dplls.pps.dpll);
 	if (ret)
 		return ret;
+	count = pf->dplls.num_inputs;
 	if (cgu) {
 		ret = ice_dpll_init_direct_pins(pf, cgu, pf->dplls.outputs,
-						pf->dplls.num_inputs,
+						count,
 						pf->dplls.num_outputs,
 						&ice_dpll_output_ops,
 						pf->dplls.eec.dpll,
 						pf->dplls.pps.dpll);
 		if (ret)
 			goto deinit_inputs;
+		count += pf->dplls.num_outputs;
+		if (!pf->dplls.generic) {
+			ret = ice_dpll_init_direct_pins(pf, cgu, pf->dplls.sma,
+							count,
+							ICE_DPLL_PIN_SW_NUM,
+							&ice_dpll_pin_sma_ops,
+							pf->dplls.eec.dpll,
+							pf->dplls.pps.dpll);
+			if (ret)
+				goto deinit_outputs;
+			count += ICE_DPLL_PIN_SW_NUM;
+			ret = ice_dpll_init_direct_pins(pf, cgu, pf->dplls.ufl,
+							count,
+							ICE_DPLL_PIN_SW_NUM,
+							&ice_dpll_pin_ufl_ops,
+							pf->dplls.eec.dpll,
+							pf->dplls.pps.dpll);
+			if (ret)
+				goto deinit_sma;
+			count += ICE_DPLL_PIN_SW_NUM;
+		}
+		ret = ice_dpll_pin_ref_sync_register(pf->dplls.inputs,
+						     pf->dplls.num_inputs);
+		if (ret)
+			goto deinit_ufl;
+		ret = ice_dpll_pin_ref_sync_register(pf->dplls.sma,
+						     ICE_DPLL_PIN_SW_NUM);
+		if (ret)
+			goto deinit_ufl;
+	} else {
+		count += pf->dplls.num_outputs + 2 * ICE_DPLL_PIN_SW_NUM;
 	}
-	rclk_idx = pf->dplls.num_inputs + pf->dplls.num_outputs + pf->hw.pf_id;
-	ret = ice_dpll_init_rclk_pins(pf, &pf->dplls.rclk, rclk_idx,
+	ret = ice_dpll_init_rclk_pins(pf, &pf->dplls.rclk, count + pf->hw.pf_id,
 				      &ice_dpll_rclk_ops);
 	if (ret)
-		goto deinit_outputs;
+		goto deinit_ufl;
 
 	return 0;
+deinit_ufl:
+	ice_dpll_deinit_direct_pins(cgu, pf->dplls.ufl,
+				    ICE_DPLL_PIN_SW_NUM,
+				    &ice_dpll_pin_ufl_ops,
+				    pf->dplls.pps.dpll, pf->dplls.eec.dpll);
+deinit_sma:
+	ice_dpll_deinit_direct_pins(cgu, pf->dplls.sma,
+				    ICE_DPLL_PIN_SW_NUM,
+				    &ice_dpll_pin_sma_ops,
+				    pf->dplls.pps.dpll, pf->dplls.eec.dpll);
 deinit_outputs:
 	ice_dpll_deinit_direct_pins(cgu, pf->dplls.outputs,
 				    pf->dplls.num_outputs,
@@ -1977,7 +3246,7 @@ static void
 ice_dpll_deinit_dpll(struct ice_pf *pf, struct ice_dpll *d, bool cgu)
 {
 	if (cgu)
-		dpll_device_unregister(d->dpll, &ice_dpll_ops, d);
+		dpll_device_unregister(d->dpll, d->ops, d);
 	dpll_device_put(d->dpll);
 }
 
@@ -2011,12 +3280,17 @@ ice_dpll_init_dpll(struct ice_pf *pf, struct ice_dpll *d, bool cgu,
 	}
 	d->pf = pf;
 	if (cgu) {
+		const struct dpll_device_ops *ops = &ice_dpll_ops;
+
+		if (type == DPLL_TYPE_PPS && ice_dpll_is_pps_phase_monitor(pf))
+			ops =  &ice_dpll_pom_ops;
 		ice_dpll_update_state(pf, d, true);
-		ret = dpll_device_register(d->dpll, type, &ice_dpll_ops, d);
+		ret = dpll_device_register(d->dpll, type, ops, d);
 		if (ret) {
 			dpll_device_put(d->dpll);
 			return ret;
 		}
+		d->ops = ops;
 	}
 
 	return 0;
@@ -2053,7 +3327,7 @@ static int ice_dpll_init_worker(struct ice_pf *pf)
 	struct kthread_worker *kworker;
 
 	kthread_init_delayed_work(&d->work, ice_dpll_periodic_work);
-	kworker = kthread_create_worker(0, "ice-dplls-%s",
+	kworker = kthread_run_worker(0, "ice-dplls-%s",
 					dev_name(ice_pf_to_dev(pf)));
 	if (IS_ERR(kworker))
 		return PTR_ERR(kworker);
@@ -2065,6 +3339,18 @@ static int ice_dpll_init_worker(struct ice_pf *pf)
 }
 
 /**
+ * ice_dpll_phase_range_set - initialize phase adjust range helper
+ * @range: pointer to phase adjust range struct to be initialized
+ * @phase_adj: a value to be used as min(-)/max(+) boundary
+ */
+static void ice_dpll_phase_range_set(struct dpll_pin_phase_adjust_range *range,
+				     u32 phase_adj)
+{
+	range->min = -phase_adj;
+	range->max = phase_adj;
+}
+
+/**
  * ice_dpll_init_info_pins_generic - initializes generic pins info
  * @pf: board private structure
  * @input: if input pins initialized
@@ -2105,8 +3391,8 @@ static int ice_dpll_init_info_pins_generic(struct ice_pf *pf, bool input)
 	for (i = 0; i < pin_num; i++) {
 		pins[i].idx = i;
 		pins[i].prop.board_label = labels[i];
-		pins[i].prop.phase_range.min = phase_adj_max;
-		pins[i].prop.phase_range.max = -phase_adj_max;
+		ice_dpll_phase_range_set(&pins[i].prop.phase_range,
+					 phase_adj_max);
 		pins[i].prop.capabilities = cap;
 		pins[i].pf = pf;
 		ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL);
@@ -2152,6 +3438,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 	struct ice_hw *hw = &pf->hw;
 	struct ice_dpll_pin *pins;
 	unsigned long caps;
+	u32 phase_adj_max;
 	u8 freq_supp_num;
 	bool input;
 
@@ -2159,18 +3446,22 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 	case ICE_DPLL_PIN_TYPE_INPUT:
 		pins = pf->dplls.inputs;
 		num_pins = pf->dplls.num_inputs;
+		phase_adj_max = pf->dplls.input_phase_adj_max;
 		input = true;
 		break;
 	case ICE_DPLL_PIN_TYPE_OUTPUT:
 		pins = pf->dplls.outputs;
 		num_pins = pf->dplls.num_outputs;
+		phase_adj_max = pf->dplls.output_phase_adj_max;
 		input = false;
 		break;
 	default:
 		return -EINVAL;
 	}
-	if (num_pins != ice_cgu_get_num_pins(hw, input))
+	if (num_pins != ice_cgu_get_num_pins(hw, input)) {
+		pf->dplls.generic = true;
 		return ice_dpll_init_info_pins_generic(pf, input);
+	}
 
 	for (i = 0; i < num_pins; i++) {
 		caps = 0;
@@ -2188,19 +3479,17 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 				return ret;
 			caps |= (DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE |
 				 DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE);
-			pins[i].prop.phase_range.min =
-				pf->dplls.input_phase_adj_max;
-			pins[i].prop.phase_range.max =
-				-pf->dplls.input_phase_adj_max;
+			if (ice_dpll_is_sw_pin(pf, i, true))
+				pins[i].hidden = true;
 		} else {
-			pins[i].prop.phase_range.min =
-				pf->dplls.output_phase_adj_max;
-			pins[i].prop.phase_range.max =
-				-pf->dplls.output_phase_adj_max;
 			ret = ice_cgu_get_output_pin_state_caps(hw, i, &caps);
 			if (ret)
 				return ret;
+			if (ice_dpll_is_sw_pin(pf, i, false))
+				pins[i].hidden = true;
 		}
+		ice_dpll_phase_range_set(&pins[i].prop.phase_range,
+					 phase_adj_max);
 		pins[i].prop.capabilities = caps;
 		ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL);
 		if (ret)
@@ -2210,6 +3499,8 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 		pins[i].prop.freq_supported_num = freq_supp_num;
 		pins[i].pf = pf;
 	}
+	if (input)
+		ret = ice_dpll_init_ref_sync_inputs(pf);
 
 	return ret;
 }
@@ -2237,6 +3528,91 @@ static int ice_dpll_init_info_rclk_pin(struct ice_pf *pf)
 }
 
 /**
+ * ice_dpll_init_info_sw_pins - initializes software controlled pin information
+ * @pf: board private structure
+ *
+ * Init information for software controlled pins, cache them in
+ * pf->dplls.sma and pf->dplls.ufl.
+ *
+ * Return:
+ * * 0 - success
+ * * negative - init failure reason
+ */
+static int ice_dpll_init_info_sw_pins(struct ice_pf *pf)
+{
+	u8 freq_supp_num, pin_abs_idx, input_idx_offset = 0;
+	struct ice_dplls *d = &pf->dplls;
+	struct ice_dpll_pin *pin;
+	u32 phase_adj_max, caps;
+	int i, ret;
+
+	if (pf->hw.device_id == ICE_DEV_ID_E810C_QSFP)
+		input_idx_offset = ICE_E810_RCLK_PINS_NUM;
+	phase_adj_max = max(d->input_phase_adj_max, d->output_phase_adj_max);
+	caps = DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE;
+	for (i = 0; i < ICE_DPLL_PIN_SW_NUM; i++) {
+		pin = &d->sma[i];
+		pin->idx = i;
+		pin->prop.type = DPLL_PIN_TYPE_EXT;
+		pin_abs_idx = ICE_DPLL_PIN_SW_INPUT_ABS(i) + input_idx_offset;
+		pin->prop.freq_supported =
+			ice_cgu_get_pin_freq_supp(&pf->hw, pin_abs_idx,
+						  true, &freq_supp_num);
+		pin->prop.freq_supported_num = freq_supp_num;
+		pin->prop.capabilities =
+			(DPLL_PIN_CAPABILITIES_DIRECTION_CAN_CHANGE |
+			 DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE |
+			 caps);
+		pin->pf = pf;
+		pin->prop.board_label = ice_dpll_sw_pin_sma[i];
+		pin->input = &d->inputs[pin_abs_idx];
+		if (pin->input->ref_sync)
+			pin->ref_sync = pin->input->ref_sync - pin_abs_idx;
+		pin->output = &d->outputs[ICE_DPLL_PIN_SW_OUTPUT_ABS(i)];
+		ice_dpll_phase_range_set(&pin->prop.phase_range, phase_adj_max);
+	}
+	for (i = 0; i < ICE_DPLL_PIN_SW_NUM; i++) {
+		pin = &d->ufl[i];
+		pin->idx = i;
+		pin->prop.type = DPLL_PIN_TYPE_EXT;
+		pin->prop.capabilities = caps;
+		pin->pf = pf;
+		pin->prop.board_label = ice_dpll_sw_pin_ufl[i];
+		if (i == ICE_DPLL_PIN_SW_1_IDX) {
+			pin->direction = DPLL_PIN_DIRECTION_OUTPUT;
+			pin_abs_idx = ICE_DPLL_PIN_SW_OUTPUT_ABS(i);
+			pin->prop.freq_supported =
+				ice_cgu_get_pin_freq_supp(&pf->hw, pin_abs_idx,
+							  false,
+							  &freq_supp_num);
+			pin->prop.freq_supported_num = freq_supp_num;
+			pin->input = NULL;
+			pin->output = &d->outputs[pin_abs_idx];
+		} else if (i == ICE_DPLL_PIN_SW_2_IDX) {
+			pin->direction = DPLL_PIN_DIRECTION_INPUT;
+			pin_abs_idx = ICE_DPLL_PIN_SW_INPUT_ABS(i) +
+				      input_idx_offset;
+			pin->output = NULL;
+			pin->input = &d->inputs[pin_abs_idx];
+			pin->prop.freq_supported =
+				ice_cgu_get_pin_freq_supp(&pf->hw, pin_abs_idx,
+							  true, &freq_supp_num);
+			pin->prop.freq_supported_num = freq_supp_num;
+			pin->prop.capabilities =
+				(DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE |
+				 caps);
+		}
+		ice_dpll_phase_range_set(&pin->prop.phase_range, phase_adj_max);
+	}
+	ret = ice_dpll_pin_state_update(pf, pin, ICE_DPLL_PIN_TYPE_SOFTWARE,
+					NULL);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/**
  * ice_dpll_init_pins_info - init pins info wrapper
  * @pf: board private structure
  * @pin_type: type of pins being initialized
@@ -2256,6 +3632,8 @@ ice_dpll_init_pins_info(struct ice_pf *pf, enum ice_dpll_pin_type pin_type)
 		return ice_dpll_init_info_direct_pins(pf, pin_type);
 	case ICE_DPLL_PIN_TYPE_RCLK_INPUT:
 		return ice_dpll_init_info_rclk_pin(pf);
+	case ICE_DPLL_PIN_TYPE_SOFTWARE:
+		return ice_dpll_init_info_sw_pins(pf);
 	default:
 		return -EINVAL;
 	}
@@ -2300,7 +3678,7 @@ static int ice_dpll_init_info(struct ice_pf *pf, bool cgu)
 	if (ret) {
 		dev_err(ice_pf_to_dev(pf),
 			"err:%d %s failed to read cgu abilities\n",
-			ret, ice_aq_str(hw->adminq.sq_last_status));
+			ret, libie_aq_str(hw->adminq.sq_last_status));
 		return ret;
 	}
 
@@ -2308,8 +3686,10 @@ static int ice_dpll_init_info(struct ice_pf *pf, bool cgu)
 	dp->dpll_idx = abilities.pps_dpll_idx;
 	d->num_inputs = abilities.num_inputs;
 	d->num_outputs = abilities.num_outputs;
-	d->input_phase_adj_max = le32_to_cpu(abilities.max_in_phase_adj);
-	d->output_phase_adj_max = le32_to_cpu(abilities.max_out_phase_adj);
+	d->input_phase_adj_max = le32_to_cpu(abilities.max_in_phase_adj) &
+		ICE_AQC_GET_CGU_MAX_PHASE_ADJ;
+	d->output_phase_adj_max = le32_to_cpu(abilities.max_out_phase_adj) &
+		ICE_AQC_GET_CGU_MAX_PHASE_ADJ;
 
 	alloc_size = sizeof(*d->inputs) * d->num_inputs;
 	d->inputs = kzalloc(alloc_size, GFP_KERNEL);
@@ -2340,6 +3720,9 @@ static int ice_dpll_init_info(struct ice_pf *pf, bool cgu)
 		ret = ice_dpll_init_pins_info(pf, ICE_DPLL_PIN_TYPE_OUTPUT);
 		if (ret)
 			goto deinit_info;
+		ret = ice_dpll_init_pins_info(pf, ICE_DPLL_PIN_TYPE_SOFTWARE);
+		if (ret)
+			goto deinit_info;
 	}
 
 	ret = ice_get_cgu_rclk_pin_info(&pf->hw, &d->base_rclk_idx,
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h
index c320f1bf7d6d..c0da03384ce9 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.h
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.h
@@ -8,6 +8,18 @@
 
 #define ICE_DPLL_RCLK_NUM_MAX	4
 
+/**
+ * enum ice_dpll_pin_sw - enumerate ice software pin indices:
+ * @ICE_DPLL_PIN_SW_1_IDX: index of first SW pin
+ * @ICE_DPLL_PIN_SW_2_IDX: index of second SW pin
+ * @ICE_DPLL_PIN_SW_NUM: number of SW pins in pair
+ */
+enum ice_dpll_pin_sw {
+	ICE_DPLL_PIN_SW_1_IDX,
+	ICE_DPLL_PIN_SW_2_IDX,
+	ICE_DPLL_PIN_SW_NUM
+};
+
 /** ice_dpll_pin - store info about pins
  * @pin: dpll pin structure
  * @pf: pointer to pf, which has registered the dpll_pin
@@ -19,6 +31,8 @@
  * @prop: pin properties
  * @freq: current frequency of a pin
  * @phase_adjust: current phase adjust value
+ * @phase_offset: monitored phase offset value
+ * @ref_sync: store id of reference sync pin
  */
 struct ice_dpll_pin {
 	struct dpll_pin *pin;
@@ -31,7 +45,14 @@ struct ice_dpll_pin {
 	struct dpll_pin_properties prop;
 	u32 freq;
 	s32 phase_adjust;
+	struct ice_dpll_pin *input;
+	struct ice_dpll_pin *output;
+	enum dpll_pin_direction direction;
+	s64 phase_offset;
 	u8 status;
+	u8 ref_sync;
+	bool active;
+	bool hidden;
 };
 
 /** ice_dpll - store info required for DPLL control
@@ -47,8 +68,10 @@ struct ice_dpll_pin {
  * @input_prio: priorities of each input
  * @dpll_state: current dpll sync state
  * @prev_dpll_state: last dpll sync state
+ * @phase_offset_monitor_period: period for phase offset monitor read frequency
  * @active_input: pointer to active input pin
  * @prev_input: pointer to previous active input pin
+ * @ops: holds the registered ops
  */
 struct ice_dpll {
 	struct dpll_device *dpll;
@@ -64,8 +87,10 @@ struct ice_dpll {
 	enum dpll_lock_status dpll_state;
 	enum dpll_lock_status prev_dpll_state;
 	enum dpll_mode mode;
+	u32 phase_offset_monitor_period;
 	struct dpll_pin *active_input;
 	struct dpll_pin *prev_input;
+	const struct dpll_device_ops *ops;
 };
 
 /** ice_dplls - store info required for CCU (clock controlling unit)
@@ -84,6 +109,7 @@ struct ice_dpll {
  * @clock_id: clock_id of dplls
  * @input_phase_adj_max: max phase adjust value for an input pins
  * @output_phase_adj_max: max phase adjust value for an output pins
+ * @periodic_counter: counter of periodic work executions
  */
 struct ice_dplls {
 	struct kthread_worker *kworker;
@@ -93,14 +119,19 @@ struct ice_dplls {
 	struct ice_dpll pps;
 	struct ice_dpll_pin *inputs;
 	struct ice_dpll_pin *outputs;
+	struct ice_dpll_pin sma[ICE_DPLL_PIN_SW_NUM];
+	struct ice_dpll_pin ufl[ICE_DPLL_PIN_SW_NUM];
 	struct ice_dpll_pin rclk;
 	u8 num_inputs;
 	u8 num_outputs;
-	int cgu_state_acq_err_num;
+	u8 sma_data;
 	u8 base_rclk_idx;
+	int cgu_state_acq_err_num;
 	u64 clock_id;
 	s32 input_phase_adj_max;
 	s32 output_phase_adj_max;
+	u32 periodic_counter;
+	bool generic;
 };
 
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index fb527434b58b..2e4f0969035f 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -29,6 +29,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 			return -ENODEV;
 
 	ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx);
+	ice_vsi_cfg_sw_lldp(uplink_vsi, true, false);
 
 	netif_addr_lock_bh(netdev);
 	__dev_uc_unsync(netdev, NULL);
@@ -38,8 +39,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 	if (ice_vsi_add_vlan_zero(uplink_vsi))
 		goto err_vlan_zero;
 
-	if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,
-			     ICE_FLTR_RX))
+	if (ice_set_dflt_vsi(uplink_vsi))
 		goto err_def_rx;
 
 	if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,
@@ -50,9 +50,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 	if (vlan_ops->dis_rx_filtering(uplink_vsi))
 		goto err_vlan_filtering;
 
-	if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override))
-		goto err_override_uplink;
-
 	if (ice_vsi_update_local_lb(uplink_vsi, true))
 		goto err_override_local_lb;
 
@@ -64,8 +61,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 err_up:
 	ice_vsi_update_local_lb(uplink_vsi, false);
 err_override_local_lb:
-	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
-err_override_uplink:
 	vlan_ops->ena_rx_filtering(uplink_vsi);
 err_vlan_filtering:
 	ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
@@ -251,6 +246,10 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb,
 	u64 cd_cmd, dst_vsi;
 
 	if (!dst) {
+		struct ethhdr *eth = (struct ethhdr *)skb_mac_header(skb);
+
+		if (unlikely(eth->h_proto == htons(ETH_P_LLDP)))
+			return;
 		cd_cmd = ICE_TX_CTX_DESC_SWTCH_UPLINK << ICE_TXD_CTX_QW1_CMD_S;
 		off->cd_qw1 |= (cd_cmd | ICE_TX_DESC_DTYPE_CTX);
 	} else {
@@ -276,7 +275,6 @@ static void ice_eswitch_release_env(struct ice_pf *pf)
 	vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi);
 
 	ice_vsi_update_local_lb(uplink_vsi, false);
-	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
 	vlan_ops->ena_rx_filtering(uplink_vsi);
 	ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
 			 ICE_FLTR_TX);
@@ -285,6 +283,7 @@ static void ice_eswitch_release_env(struct ice_pf *pf)
 	ice_fltr_add_mac_and_broadcast(uplink_vsi,
 				       uplink_vsi->port_info->mac.perm_addr,
 				       ICE_FWD_TO_VSI);
+	ice_vsi_cfg_sw_lldp(uplink_vsi, true, true);
 }
 
 /**
@@ -509,10 +508,14 @@ err_create_repr:
  */
 int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf)
 {
-	struct ice_repr *repr = ice_repr_create_vf(vf);
 	struct devlink *devlink = priv_to_devlink(pf);
+	struct ice_repr *repr;
 	int err;
 
+	if (!ice_is_eswitch_mode_switchdev(pf))
+		return 0;
+
+	repr = ice_repr_create_vf(vf);
 	if (IS_ERR(repr))
 		return PTR_ERR(repr);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 3072634bf049..969d4f8f9c02 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -10,6 +10,7 @@
 #include "ice_lib.h"
 #include "ice_dcb_lib.h"
 #include <net/dcbnl.h>
+#include <net/libeth/rx.h>
 
 struct ice_stats {
 	char stat_string[ETH_GSTRING_LEN];
@@ -340,7 +341,6 @@ static const struct ice_priv_flag ice_gstrings_priv_flags[] = {
 		      ICE_FLAG_VF_TRUE_PROMISC_ENA),
 	ICE_PRIV_FLAG("mdd-auto-reset-vf", ICE_FLAG_MDD_AUTO_RESET_VF),
 	ICE_PRIV_FLAG("vf-vlan-pruning", ICE_FLAG_VF_VLAN_PRUNING),
-	ICE_PRIV_FLAG("legacy-rx", ICE_FLAG_LEGACY_RX),
 };
 
 #define ICE_PRIV_FLAG_ARRAY_SIZE	ARRAY_SIZE(ice_gstrings_priv_flags)
@@ -667,7 +667,8 @@ static int ice_get_port_topology(struct ice_hw *hw, u8 lport,
 
 		if (max_speed == ICE_AQC_PORT_OPT_MAX_LANE_100G)
 			port_topology->serdes_lane_count = 4;
-		else if (max_speed == ICE_AQC_PORT_OPT_MAX_LANE_50G)
+		else if (max_speed == ICE_AQC_PORT_OPT_MAX_LANE_50G ||
+			 max_speed == ICE_AQC_PORT_OPT_MAX_LANE_40G)
 			port_topology->serdes_lane_count = 2;
 		else
 			port_topology->serdes_lane_count = 1;
@@ -710,7 +711,6 @@ static int ice_get_tx_rx_equa(struct ice_hw *hw, u8 serdes_num,
 		{ ICE_AQC_RX_EQU_POST1, rx, &ptr->rx_equ_post1 },
 		{ ICE_AQC_RX_EQU_BFLF, rx, &ptr->rx_equ_bflf },
 		{ ICE_AQC_RX_EQU_BFHF, rx, &ptr->rx_equ_bfhf },
-		{ ICE_AQC_RX_EQU_DRATE, rx, &ptr->rx_equ_drate },
 		{ ICE_AQC_RX_EQU_CTLE_GAINHF, rx, &ptr->rx_equ_ctle_gainhf },
 		{ ICE_AQC_RX_EQU_CTLE_GAINLF, rx, &ptr->rx_equ_ctle_gainlf },
 		{ ICE_AQC_RX_EQU_CTLE_GAINDC, rx, &ptr->rx_equ_ctle_gaindc },
@@ -794,8 +794,7 @@ static int ice_get_extended_regs(struct net_device *netdev, void *p)
 static void
 ice_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_pf *pf = np->vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	struct ice_hw *hw = &pf->hw;
 	u32 *regs_buf = (u32 *)p;
 	unsigned int i;
@@ -810,8 +809,7 @@ ice_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 
 static u32 ice_get_msglevel(struct net_device *netdev)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_pf *pf = np->vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 
 #ifndef CONFIG_DYNAMIC_DEBUG
 	if (pf->hw.debug_mask)
@@ -824,8 +822,7 @@ static u32 ice_get_msglevel(struct net_device *netdev)
 
 static void ice_set_msglevel(struct net_device *netdev, u32 data)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_pf *pf = np->vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 
 #ifndef CONFIG_DYNAMIC_DEBUG
 	if (ICE_DBG_USER & data)
@@ -837,10 +834,17 @@ static void ice_set_msglevel(struct net_device *netdev, u32 data)
 #endif /* !CONFIG_DYNAMIC_DEBUG */
 }
 
+static void ice_get_link_ext_stats(struct net_device *netdev,
+				   struct ethtool_link_ext_stats *stats)
+{
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
+
+	stats->link_down_events = pf->link_down_events;
+}
+
 static int ice_get_eeprom_len(struct net_device *netdev)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_pf *pf = np->vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 
 	return (int)pf->hw.flash.flash_size;
 }
@@ -849,9 +853,7 @@ static int
 ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
 	       u8 *bytes)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_vsi *vsi = np->vsi;
-	struct ice_pf *pf = vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	struct ice_hw *hw = &pf->hw;
 	struct device *dev;
 	int ret;
@@ -870,7 +872,7 @@ ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
 	ret = ice_acquire_nvm(hw, ICE_RES_READ);
 	if (ret) {
 		dev_err(dev, "ice_acquire_nvm failed, err %d aq_err %s\n",
-			ret, ice_aq_str(hw->adminq.sq_last_status));
+			ret, libie_aq_str(hw->adminq.sq_last_status));
 		goto out;
 	}
 
@@ -878,7 +880,7 @@ ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
 				false);
 	if (ret) {
 		dev_err(dev, "ice_read_flat_nvm failed, err %d aq_err %s\n",
-			ret, ice_aq_str(hw->adminq.sq_last_status));
+			ret, libie_aq_str(hw->adminq.sq_last_status));
 		goto release;
 	}
 
@@ -950,8 +952,7 @@ static u64 ice_link_test(struct net_device *netdev)
  */
 static u64 ice_eeprom_test(struct net_device *netdev)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_pf *pf = np->vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 
 	netdev_info(netdev, "EEPROM test\n");
 	return !!(ice_nvm_validate_checksum(&pf->hw));
@@ -1230,8 +1231,9 @@ static int ice_diag_send(struct ice_tx_ring *tx_ring, u8 *data, u16 size)
  */
 static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring)
 {
-	struct ice_rx_buf *rx_buf;
+	struct libeth_fqe *rx_buf;
 	int valid_frames, i;
+	struct page *page;
 	u8 *received_buf;
 
 	valid_frames = 0;
@@ -1246,8 +1248,10 @@ static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring)
 		     cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S)))))
 			continue;
 
-		rx_buf = &rx_ring->rx_buf[i];
-		received_buf = page_address(rx_buf->page) + rx_buf->page_offset;
+		rx_buf = &rx_ring->rx_fqes[i];
+		page = __netmem_to_page(rx_buf->netmem);
+		received_buf = page_address(page) + rx_buf->offset +
+			       page->pp->p.offset;
 
 		if (ice_lbtest_check_frame(received_buf))
 			valid_frames++;
@@ -1265,9 +1269,8 @@ static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring)
  */
 static u64 ice_loopback_test(struct net_device *netdev)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_vsi *orig_vsi = np->vsi, *test_vsi;
-	struct ice_pf *pf = orig_vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
+	struct ice_vsi *test_vsi;
 	u8 *tx_frame __free(kfree) = NULL;
 	u8 broadcast[ETH_ALEN], ret = 0;
 	int num_frames, valid_frames;
@@ -1356,8 +1359,7 @@ lbtest_vsi_close:
  */
 static u64 ice_intr_test(struct net_device *netdev)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_pf *pf = np->vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	u16 swic_old = pf->sw_int_count;
 
 	netdev_info(netdev, "interrupt test\n");
@@ -1385,9 +1387,8 @@ static void
 ice_self_test(struct net_device *netdev, struct ethtool_test *eth_test,
 	      u64 *data)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	bool if_running = netif_running(netdev);
-	struct ice_pf *pf = np->vsi->back;
 	struct device *dev;
 
 	dev = ice_pf_to_dev(pf);
@@ -1711,9 +1712,7 @@ static int ice_nway_reset(struct net_device *netdev)
  */
 static u32 ice_get_priv_flags(struct net_device *netdev)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_vsi *vsi = np->vsi;
-	struct ice_pf *pf = vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	u32 i, ret_flags = 0;
 
 	for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) {
@@ -1819,7 +1818,7 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags)
 			/* Remove rule to direct LLDP packets to default VSI.
 			 * The FW LLDP engine will now be consuming them.
 			 */
-			ice_cfg_sw_lldp(vsi, false, false);
+			ice_cfg_sw_rx_lldp(vsi->back, false);
 
 			/* AQ command to start FW LLDP agent will return an
 			 * error if the agent is already started
@@ -1860,10 +1859,6 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags)
 			ice_nway_reset(netdev);
 		}
 	}
-	if (test_bit(ICE_FLAG_LEGACY_RX, change_flags)) {
-		/* down and up VSI so that changes of Rx cfg are reflected. */
-		ice_down_up(vsi);
-	}
 	/* don't allow modification of this flag when a single VF is in
 	 * promiscuous mode because it's not supported
 	 */
@@ -2789,14 +2784,7 @@ done:
 	return err;
 }
 
-/**
- * ice_parse_hdrs - parses headers from RSS hash input
- * @nfc: ethtool rxnfc command
- *
- * This function parses the rxnfc command and returns intended
- * header types for RSS configuration
- */
-static u32 ice_parse_hdrs(struct ethtool_rxnfc *nfc)
+static u32 ice_parse_hdrs(const struct ethtool_rxfh_fields *nfc)
 {
 	u32 hdrs = ICE_FLOW_SEG_HDR_NONE;
 
@@ -2861,15 +2849,7 @@ static u32 ice_parse_hdrs(struct ethtool_rxnfc *nfc)
 	return hdrs;
 }
 
-/**
- * ice_parse_hash_flds - parses hash fields from RSS hash input
- * @nfc: ethtool rxnfc command
- * @symm: true if Symmetric Topelitz is set
- *
- * This function parses the rxnfc command and returns intended
- * hash fields for RSS configuration
- */
-static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc, bool symm)
+static u64 ice_parse_hash_flds(const struct ethtool_rxfh_fields *nfc, bool symm)
 {
 	u64 hfld = ICE_HASH_INVALID;
 
@@ -2966,16 +2946,13 @@ static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc, bool symm)
 	return hfld;
 }
 
-/**
- * ice_set_rss_hash_opt - Enable/Disable flow types for RSS hash
- * @vsi: the VSI being configured
- * @nfc: ethtool rxnfc command
- *
- * Returns Success if the flow input set is supported.
- */
 static int
-ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
+ice_set_rxfh_fields(struct net_device *netdev,
+		    const struct ethtool_rxfh_fields *nfc,
+		    struct netlink_ext_ack *extack)
 {
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
 	struct ice_rss_hash_cfg cfg;
 	struct device *dev;
@@ -3021,14 +2998,11 @@ ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
 	return 0;
 }
 
-/**
- * ice_get_rss_hash_opt - Retrieve hash fields for a given flow-type
- * @vsi: the VSI being configured
- * @nfc: ethtool rxnfc command
- */
-static void
-ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
+static int
+ice_get_rxfh_fields(struct net_device *netdev, struct ethtool_rxfh_fields *nfc)
 {
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
 	struct device *dev;
 	u64 hash_flds;
@@ -3041,21 +3015,21 @@ ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
 	if (ice_is_safe_mode(pf)) {
 		dev_dbg(dev, "Advanced RSS disabled. Package download failed, vsi num = %d\n",
 			vsi->vsi_num);
-		return;
+		return 0;
 	}
 
 	hdrs = ice_parse_hdrs(nfc);
 	if (hdrs == ICE_FLOW_SEG_HDR_NONE) {
 		dev_dbg(dev, "Header type is not valid, vsi num = %d\n",
 			vsi->vsi_num);
-		return;
+		return 0;
 	}
 
 	hash_flds = ice_get_rss_cfg(&pf->hw, vsi->idx, hdrs, &symm);
 	if (hash_flds == ICE_HASH_INVALID) {
 		dev_dbg(dev, "No hash fields found for the given header type, vsi num = %d\n",
 			vsi->vsi_num);
-		return;
+		return 0;
 	}
 
 	if (hash_flds & ICE_FLOW_HASH_FLD_IPV4_SA ||
@@ -3082,6 +3056,8 @@ ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
 	    hash_flds & ICE_FLOW_HASH_FLD_GTPU_UP_TEID ||
 	    hash_flds & ICE_FLOW_HASH_FLD_GTPU_DWN_TEID)
 		nfc->data |= (u64)RXH_GTP_TEID;
+
+	return 0;
 }
 
 /**
@@ -3101,8 +3077,6 @@ static int ice_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 		return ice_add_fdir_ethtool(vsi, cmd);
 	case ETHTOOL_SRXCLSRLDEL:
 		return ice_del_fdir_ethtool(vsi, cmd);
-	case ETHTOOL_SRXFH:
-		return ice_set_rss_hash_opt(vsi, cmd);
 	default:
 		break;
 	}
@@ -3110,6 +3084,20 @@ static int ice_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 }
 
 /**
+ * ice_get_rx_ring_count - get RX ring count
+ * @netdev: network interface device structure
+ *
+ * Return: number of RX rings.
+ */
+static u32 ice_get_rx_ring_count(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+
+	return vsi->rss_size;
+}
+
+/**
  * ice_get_rxnfc - command to get Rx flow classification rules
  * @netdev: network interface device structure
  * @cmd: ethtool rxnfc command
@@ -3129,10 +3117,6 @@ ice_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 	hw = &vsi->back->hw;
 
 	switch (cmd->cmd) {
-	case ETHTOOL_GRXRINGS:
-		cmd->data = vsi->rss_size;
-		ret = 0;
-		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = hw->fdir_active_fltr;
 		/* report total rule count */
@@ -3145,10 +3129,6 @@ ice_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 	case ETHTOOL_GRXCLSRLALL:
 		ret = ice_get_fdir_fltr_ids(hw, cmd, (u32 *)rule_locs);
 		break;
-	case ETHTOOL_GRXFH:
-		ice_get_rss_hash_opt(vsi, cmd);
-		ret = 0;
-		break;
 	default:
 		break;
 	}
@@ -3163,9 +3143,11 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
+	struct ice_hw *hw;
 
-	ring->rx_max_pending = ICE_MAX_NUM_DESC;
-	ring->tx_max_pending = ICE_MAX_NUM_DESC;
+	hw = &vsi->back->hw;
+	ring->rx_max_pending = ICE_MAX_NUM_DESC_BY_MAC(hw);
+	ring->tx_max_pending = ICE_MAX_NUM_DESC_BY_MAC(hw);
 	if (vsi->tx_rings && vsi->rx_rings) {
 		ring->rx_pending = vsi->rx_rings[0]->count;
 		ring->tx_pending = vsi->tx_rings[0]->count;
@@ -3179,6 +3161,10 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 	ring->rx_jumbo_max_pending = 0;
 	ring->rx_mini_pending = 0;
 	ring->rx_jumbo_pending = 0;
+
+	kernel_ring->tcp_data_split = vsi->hsplit ?
+				      ETHTOOL_TCP_DATA_SPLIT_ENABLED :
+				      ETHTOOL_TCP_DATA_SPLIT_DISABLED;
 }
 
 static int
@@ -3193,15 +3179,17 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
 	int i, timeout = 50, err = 0;
+	struct ice_hw *hw = &pf->hw;
 	u16 new_rx_cnt, new_tx_cnt;
+	bool hsplit;
 
-	if (ring->tx_pending > ICE_MAX_NUM_DESC ||
+	if (ring->tx_pending > ICE_MAX_NUM_DESC_BY_MAC(hw) ||
 	    ring->tx_pending < ICE_MIN_NUM_DESC ||
-	    ring->rx_pending > ICE_MAX_NUM_DESC ||
+	    ring->rx_pending > ICE_MAX_NUM_DESC_BY_MAC(hw) ||
 	    ring->rx_pending < ICE_MIN_NUM_DESC) {
 		netdev_err(netdev, "Descriptors requested (Tx: %d / Rx: %d) out of range [%d-%d] (increment %d)\n",
 			   ring->tx_pending, ring->rx_pending,
-			   ICE_MIN_NUM_DESC, ICE_MAX_NUM_DESC,
+			   ICE_MIN_NUM_DESC, ICE_MAX_NUM_DESC_BY_MAC(hw),
 			   ICE_REQ_DESC_MULTIPLE);
 		return -EINVAL;
 	}
@@ -3219,9 +3207,12 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 		netdev_info(netdev, "Requested Rx descriptor count rounded up to %d\n",
 			    new_rx_cnt);
 
+	hsplit = kernel_ring->tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED;
+
 	/* if nothing to do return success */
 	if (new_tx_cnt == vsi->tx_rings[0]->count &&
-	    new_rx_cnt == vsi->rx_rings[0]->count) {
+	    new_rx_cnt == vsi->rx_rings[0]->count &&
+	    hsplit == vsi->hsplit) {
 		netdev_dbg(netdev, "Nothing to change, descriptor count is same as requested\n");
 		return 0;
 	}
@@ -3251,6 +3242,8 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 				vsi->xdp_rings[i]->count = new_tx_cnt;
 		vsi->num_tx_desc = (u16)new_tx_cnt;
 		vsi->num_rx_desc = (u16)new_rx_cnt;
+		vsi->hsplit = hsplit;
+
 		netdev_dbg(netdev, "Link is down, descriptor count change happens when link is brought up\n");
 		goto done;
 	}
@@ -3274,6 +3267,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 		tx_rings[i].count = new_tx_cnt;
 		tx_rings[i].desc = NULL;
 		tx_rings[i].tx_buf = NULL;
+		tx_rings[i].tstamp_ring = NULL;
 		tx_rings[i].tx_tstamps = &pf->ptp.port.tx;
 		err = ice_setup_tx_ring(&tx_rings[i]);
 		if (err) {
@@ -3333,7 +3327,8 @@ process_rx:
 		rx_rings[i].count = new_rx_cnt;
 		rx_rings[i].cached_phctime = pf->ptp.cached_phc_time;
 		rx_rings[i].desc = NULL;
-		rx_rings[i].rx_buf = NULL;
+		rx_rings[i].xdp_buf = NULL;
+
 		/* this is to allow wr32 to have something to write to
 		 * during early allocation of Rx buffers
 		 */
@@ -3342,10 +3337,6 @@ process_rx:
 		err = ice_setup_rx_ring(&rx_rings[i]);
 		if (err)
 			goto rx_unwind;
-
-		/* allocate Rx buffers */
-		err = ice_alloc_rx_bufs(&rx_rings[i],
-					ICE_RX_DESC_UNUSED(&rx_rings[i]));
 rx_unwind:
 		if (err) {
 			while (i) {
@@ -3359,6 +3350,8 @@ rx_unwind:
 	}
 
 process_link:
+	vsi->hsplit = hsplit;
+
 	/* Bring interface down, copy in the new ring info, then restore the
 	 * interface. if VSI is up, bring it down and then back up
 	 */
@@ -3558,15 +3551,15 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
 
 	if (aq_failures & ICE_SET_FC_AQ_FAIL_GET) {
 		netdev_info(netdev, "Set fc failed on the get_phy_capabilities call with err %d aq_err %s\n",
-			    err, ice_aq_str(hw->adminq.sq_last_status));
+			    err, libie_aq_str(hw->adminq.sq_last_status));
 		err = -EAGAIN;
 	} else if (aq_failures & ICE_SET_FC_AQ_FAIL_SET) {
 		netdev_info(netdev, "Set fc failed on the set_phy_config call with err %d aq_err %s\n",
-			    err, ice_aq_str(hw->adminq.sq_last_status));
+			    err, libie_aq_str(hw->adminq.sq_last_status));
 		err = -EAGAIN;
 	} else if (aq_failures & ICE_SET_FC_AQ_FAIL_UPDATE) {
 		netdev_info(netdev, "Set fc failed on the get_link_info call with err %d aq_err %s\n",
-			    err, ice_aq_str(hw->adminq.sq_last_status));
+			    err, libie_aq_str(hw->adminq.sq_last_status));
 		err = -EAGAIN;
 	}
 
@@ -3608,11 +3601,10 @@ static int
 ice_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
-	u32 rss_context = rxfh->rss_context;
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
 	u16 qcount, offset;
-	int err, num_tc, i;
+	int err, i;
 	u8 *lut;
 
 	if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
@@ -3620,24 +3612,8 @@ ice_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 		return -EOPNOTSUPP;
 	}
 
-	if (rss_context && !ice_is_adq_active(pf)) {
-		netdev_err(netdev, "RSS context cannot be non-zero when ADQ is not configured.\n");
-		return -EINVAL;
-	}
-
-	qcount = vsi->mqprio_qopt.qopt.count[rss_context];
-	offset = vsi->mqprio_qopt.qopt.offset[rss_context];
-
-	if (rss_context && ice_is_adq_active(pf)) {
-		num_tc = vsi->mqprio_qopt.qopt.num_tc;
-		if (rss_context >= num_tc) {
-			netdev_err(netdev, "RSS context:%d  > num_tc:%d\n",
-				   rss_context, num_tc);
-			return -EINVAL;
-		}
-		/* Use channel VSI of given TC */
-		vsi = vsi->tc_map_vsi[rss_context];
-	}
+	qcount = vsi->mqprio_qopt.qopt.count[0];
+	offset = vsi->mqprio_qopt.qopt.offset[0];
 
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
 	if (vsi->rss_hfunc == ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ)
@@ -3697,9 +3673,6 @@ ice_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
 	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (rxfh->rss_context)
-		return -EOPNOTSUPP;
-
 	if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
 		/* RSS not supported return error here */
 		netdev_warn(netdev, "RSS is not configured on this VSI!\n");
@@ -3789,8 +3762,7 @@ ice_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info)
  */
 static int ice_get_max_txq(struct ice_pf *pf)
 {
-	return min3(pf->num_lan_msix, (u16)num_online_cpus(),
-		    (u16)pf->hw.func_caps.common_cap.num_txq);
+	return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_txq);
 }
 
 /**
@@ -3799,8 +3771,7 @@ static int ice_get_max_txq(struct ice_pf *pf)
  */
 static int ice_get_max_rxq(struct ice_pf *pf)
 {
-	return min3(pf->num_lan_msix, (u16)num_online_cpus(),
-		    (u16)pf->hw.func_caps.common_cap.num_rxq);
+	return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_rxq);
 }
 
 /**
@@ -3818,8 +3789,7 @@ static u32 ice_get_combined_cnt(struct ice_vsi *vsi)
 	ice_for_each_q_vector(vsi, q_idx) {
 		struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
 
-		if (q_vector->rx.rx_ring && q_vector->tx.tx_ring)
-			combined++;
+		combined += min(q_vector->num_ring_tx, q_vector->num_ring_rx);
 	}
 
 	return combined;
@@ -3900,7 +3870,7 @@ static int ice_vsi_set_dflt_rss_lut(struct ice_vsi *vsi, int req_rss_size)
 	err = ice_set_rss_lut(vsi, lut, vsi->rss_table_size);
 	if (err)
 		dev_err(dev, "Cannot set RSS lut, err %d aq_err %s\n", err,
-			ice_aq_str(hw->adminq.sq_last_status));
+			libie_aq_str(hw->adminq.sq_last_status));
 
 	kfree(lut);
 	return err;
@@ -3968,11 +3938,11 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch)
 		return -EINVAL;
 	}
 
-	if (pf->adev) {
+	if (pf->cdev_info && pf->cdev_info->adev) {
 		mutex_lock(&pf->adev_mutex);
-		device_lock(&pf->adev->dev);
+		device_lock(&pf->cdev_info->adev->dev);
 		locked = true;
-		if (pf->adev->dev.driver) {
+		if (pf->cdev_info->adev->dev.driver) {
 			netdev_err(dev, "Cannot change channels when RDMA is active\n");
 			ret = -EBUSY;
 			goto adev_unlock;
@@ -3991,7 +3961,7 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch)
 
 adev_unlock:
 	if (locked) {
-		device_unlock(&pf->adev->dev);
+		device_unlock(&pf->cdev_info->adev->dev);
 		mutex_unlock(&pf->adev_mutex);
 	}
 	return ret;
@@ -4452,9 +4422,7 @@ static int
 ice_get_module_info(struct net_device *netdev,
 		    struct ethtool_modinfo *modinfo)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_vsi *vsi = np->vsi;
-	struct ice_pf *pf = vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	struct ice_hw *hw = &pf->hw;
 	u8 sff8472_comp = 0;
 	u8 sff8472_swap = 0;
@@ -4526,12 +4494,10 @@ static int
 ice_get_module_eeprom(struct net_device *netdev,
 		      struct ethtool_eeprom *ee, u8 *data)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 #define SFF_READ_BLOCK_SIZE 8
 	u8 value[SFF_READ_BLOCK_SIZE] = { 0 };
 	u8 addr = ICE_I2C_EEPROM_DEV_ADDR;
-	struct ice_vsi *vsi = np->vsi;
-	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
 	bool is_sfp = false;
 	unsigned int i, j;
@@ -4659,10 +4625,12 @@ static int ice_get_port_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port,
  * ice_get_fec_stats - returns FEC correctable, uncorrectable stats per netdev
  * @netdev: network interface device structure
  * @fec_stats: buffer to hold FEC statistics for given port
+ * @hist: buffer to put FEC histogram statistics for given port
  *
  */
 static void ice_get_fec_stats(struct net_device *netdev,
-			      struct ethtool_fec_stats *fec_stats)
+			      struct ethtool_fec_stats *fec_stats,
+			      struct ethtool_fec_hist *hist)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_port_topology port_topology;
@@ -4694,6 +4662,98 @@ static void ice_get_fec_stats(struct net_device *netdev,
 			    pi->lport, err);
 }
 
+static void ice_get_eth_mac_stats(struct net_device *netdev,
+				  struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
+	struct ice_hw_port_stats *ps = &pf->stats;
+
+	mac_stats->FramesTransmittedOK = ps->eth.tx_unicast +
+					 ps->eth.tx_multicast +
+					 ps->eth.tx_broadcast;
+	mac_stats->FramesReceivedOK = ps->eth.rx_unicast +
+				      ps->eth.rx_multicast +
+				      ps->eth.rx_broadcast;
+	mac_stats->FrameCheckSequenceErrors = ps->crc_errors;
+	mac_stats->OctetsTransmittedOK = ps->eth.tx_bytes;
+	mac_stats->OctetsReceivedOK = ps->eth.rx_bytes;
+	mac_stats->MulticastFramesXmittedOK = ps->eth.tx_multicast;
+	mac_stats->BroadcastFramesXmittedOK = ps->eth.tx_broadcast;
+	mac_stats->MulticastFramesReceivedOK = ps->eth.rx_multicast;
+	mac_stats->BroadcastFramesReceivedOK = ps->eth.rx_broadcast;
+	mac_stats->InRangeLengthErrors = ps->rx_len_errors;
+	mac_stats->FrameTooLongErrors = ps->rx_oversize;
+}
+
+static void ice_get_pause_stats(struct net_device *netdev,
+				struct ethtool_pause_stats *pause_stats)
+{
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
+	struct ice_hw_port_stats *ps = &pf->stats;
+
+	pause_stats->tx_pause_frames = ps->link_xon_tx + ps->link_xoff_tx;
+	pause_stats->rx_pause_frames = ps->link_xon_rx + ps->link_xoff_rx;
+}
+
+static const struct ethtool_rmon_hist_range ice_rmon_ranges[] = {
+	{    0,    64 },
+	{   65,   127 },
+	{  128,   255 },
+	{  256,   511 },
+	{  512,  1023 },
+	{ 1024,  1522 },
+	{ 1523,  9522 },
+	{}
+};
+
+static void ice_get_rmon_stats(struct net_device *netdev,
+			       struct ethtool_rmon_stats *rmon,
+			       const struct ethtool_rmon_hist_range **ranges)
+{
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
+	struct ice_hw_port_stats *ps = &pf->stats;
+
+	rmon->undersize_pkts	= ps->rx_undersize;
+	rmon->oversize_pkts	= ps->rx_oversize;
+	rmon->fragments		= ps->rx_fragments;
+	rmon->jabbers		= ps->rx_jabber;
+
+	rmon->hist[0]		= ps->rx_size_64;
+	rmon->hist[1]		= ps->rx_size_127;
+	rmon->hist[2]		= ps->rx_size_255;
+	rmon->hist[3]		= ps->rx_size_511;
+	rmon->hist[4]		= ps->rx_size_1023;
+	rmon->hist[5]		= ps->rx_size_1522;
+	rmon->hist[6]		= ps->rx_size_big;
+
+	rmon->hist_tx[0]	= ps->tx_size_64;
+	rmon->hist_tx[1]	= ps->tx_size_127;
+	rmon->hist_tx[2]	= ps->tx_size_255;
+	rmon->hist_tx[3]	= ps->tx_size_511;
+	rmon->hist_tx[4]	= ps->tx_size_1023;
+	rmon->hist_tx[5]	= ps->tx_size_1522;
+	rmon->hist_tx[6]	= ps->tx_size_big;
+
+	*ranges = ice_rmon_ranges;
+}
+
+/* ice_get_ts_stats - provide timestamping stats
+ * @netdev: the netdevice pointer from ethtool
+ * @ts_stats: the ethtool data structure to fill in
+ */
+static void ice_get_ts_stats(struct net_device *netdev,
+			     struct ethtool_ts_stats *ts_stats)
+{
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
+	struct ice_ptp *ptp = &pf->ptp;
+
+	ts_stats->pkts = ptp->tx_hwtstamp_good;
+	ts_stats->err = ptp->tx_hwtstamp_skipped +
+			ptp->tx_hwtstamp_flushed +
+			ptp->tx_hwtstamp_discarded;
+	ts_stats->lost = ptp->tx_hwtstamp_timeouts;
+}
+
 #define ICE_ETHTOOL_PFR (ETH_RESET_IRQ | ETH_RESET_DMA | \
 	ETH_RESET_FILTER | ETH_RESET_OFFLOAD)
 
@@ -4715,8 +4775,7 @@ static void ice_get_fec_stats(struct net_device *netdev,
  */
 static int ice_ethtool_reset(struct net_device *dev, u32 *flags)
 {
-	struct ice_netdev_priv *np = netdev_priv(dev);
-	struct ice_pf *pf = np->vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(dev);
 	enum ice_reset_req reset;
 
 	switch (*flags) {
@@ -4770,15 +4829,18 @@ static int ice_repr_ethtool_reset(struct net_device *dev, u32 *flags)
 }
 
 static const struct ethtool_ops ice_ethtool_ops = {
-	.cap_rss_ctx_supported  = true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
 				     ETHTOOL_COALESCE_RX_USECS_HIGH,
-	.cap_rss_sym_xor_supported = true,
-	.rxfh_per_ctx_key	= true,
+	.supported_input_xfrm	= RXH_XFRM_SYM_XOR,
+	.supported_ring_params	= ETHTOOL_RING_USE_TCP_DATA_SPLIT,
 	.get_link_ksettings	= ice_get_link_ksettings,
 	.set_link_ksettings	= ice_set_link_ksettings,
 	.get_fec_stats		= ice_get_fec_stats,
+	.get_eth_mac_stats	= ice_get_eth_mac_stats,
+	.get_pause_stats	= ice_get_pause_stats,
+	.get_rmon_stats		= ice_get_rmon_stats,
+	.get_ts_stats		= ice_get_ts_stats,
 	.get_drvinfo		= ice_get_drvinfo,
 	.get_regs_len		= ice_get_regs_len,
 	.get_regs		= ice_get_regs,
@@ -4788,6 +4850,7 @@ static const struct ethtool_ops ice_ethtool_ops = {
 	.set_msglevel		= ice_set_msglevel,
 	.self_test		= ice_self_test,
 	.get_link		= ethtool_op_get_link,
+	.get_link_ext_stats	= ice_get_link_ext_stats,
 	.get_eeprom_len		= ice_get_eeprom_len,
 	.get_eeprom		= ice_get_eeprom,
 	.get_coalesce		= ice_get_coalesce,
@@ -4800,6 +4863,7 @@ static const struct ethtool_ops ice_ethtool_ops = {
 	.get_sset_count		= ice_get_sset_count,
 	.get_rxnfc		= ice_get_rxnfc,
 	.set_rxnfc		= ice_set_rxnfc,
+	.get_rx_ring_count	= ice_get_rx_ring_count,
 	.get_ringparam		= ice_get_ringparam,
 	.set_ringparam		= ice_set_ringparam,
 	.nway_reset		= ice_nway_reset,
@@ -4810,6 +4874,8 @@ static const struct ethtool_ops ice_ethtool_ops = {
 	.get_rxfh_indir_size	= ice_get_rxfh_indir_size,
 	.get_rxfh		= ice_get_rxfh,
 	.set_rxfh		= ice_set_rxfh,
+	.get_rxfh_fields	= ice_get_rxfh_fields,
+	.set_rxfh_fields	= ice_set_rxfh_fields,
 	.get_channels		= ice_get_channels,
 	.set_channels		= ice_set_channels,
 	.get_ts_info		= ice_get_ts_info,
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.h b/drivers/net/ethernet/intel/ice/ice_ethtool.h
index 8f2ad1c172c0..23b2cfbc9684 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.h
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.h
@@ -15,7 +15,6 @@ struct ice_serdes_equalization_to_ethtool {
 	int rx_equ_post1;
 	int rx_equ_bflf;
 	int rx_equ_bfhf;
-	int rx_equ_drate;
 	int rx_equ_ctle_gainhf;
 	int rx_equ_ctle_gainlf;
 	int rx_equ_ctle_gaindc;
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index ee9862ddfe15..aceec184e89b 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -1605,22 +1605,19 @@ void ice_fdir_replay_fltrs(struct ice_pf *pf)
  */
 int ice_fdir_create_dflt_rules(struct ice_pf *pf)
 {
+	static const enum ice_fltr_ptype dflt_rules[] = {
+		ICE_FLTR_PTYPE_NONF_IPV4_TCP, ICE_FLTR_PTYPE_NONF_IPV4_UDP,
+		ICE_FLTR_PTYPE_NONF_IPV6_TCP, ICE_FLTR_PTYPE_NONF_IPV6_UDP,
+	};
 	int err;
 
 	/* Create perfect TCP and UDP rules in hardware. */
-	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_TCP);
-	if (err)
-		return err;
-
-	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_UDP);
-	if (err)
-		return err;
+	for (int i = 0; i < ARRAY_SIZE(dflt_rules); i++) {
+		err = ice_create_init_fdir_rule(pf, dflt_rules[i]);
 
-	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_TCP);
-	if (err)
-		return err;
-
-	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_UDP);
+		if (err)
+			break;
+	}
 
 	return err;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c
index 26b357c0ae15..b29fbdec9442 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.c
@@ -1121,7 +1121,7 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
  * ice_fdir_has_frag - does flow type have 2 ptypes
  * @flow: flow ptype
  *
- * returns true is there is a fragment packet for this ptype
+ * Return: true if there is a fragment packet for this ptype
  */
 bool ice_fdir_has_frag(enum ice_fltr_ptype flow)
 {
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index ed95072ca6e3..c0dbec369366 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -574,9 +574,7 @@ ice_destroy_tunnel_end:
 int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table,
 			    unsigned int idx, struct udp_tunnel_info *ti)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_vsi *vsi = np->vsi;
-	struct ice_pf *pf = vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	enum ice_tunnel_type tnl_type;
 	int status;
 	u16 index;
@@ -598,9 +596,7 @@ int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table,
 int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table,
 			      unsigned int idx, struct udp_tunnel_info *ti)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_vsi *vsi = np->vsi;
-	struct ice_pf *pf = vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	enum ice_tunnel_type tnl_type;
 	int status;
 
@@ -1479,7 +1475,7 @@ static void ice_init_prof_masks(struct ice_hw *hw, enum ice_block blk)
 	per_pf = ICE_PROF_MASK_COUNT / hw->dev_caps.num_funcs;
 
 	hw->blk[blk].masks.count = per_pf;
-	hw->blk[blk].masks.first = hw->pf_id * per_pf;
+	hw->blk[blk].masks.first = hw->logical_pf_id * per_pf;
 
 	memset(hw->blk[blk].masks.masks, 0, sizeof(hw->blk[blk].masks.masks));
 
@@ -3043,16 +3039,16 @@ ice_disable_fd_swap(struct ice_hw *hw, u8 prof_id)
  * the ID value used here.
  */
 int
-ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
-	     const struct ice_ptype_attributes *attr, u16 attr_cnt,
-	     struct ice_fv_word *es, u16 *masks, bool symm, bool fd_swap)
+ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id,
+	     unsigned long *ptypes, const struct ice_ptype_attributes *attr,
+	     u16 attr_cnt, struct ice_fv_word *es, u16 *masks, bool symm,
+	     bool fd_swap)
 {
-	u32 bytes = DIV_ROUND_UP(ICE_FLOW_PTYPE_MAX, BITS_PER_BYTE);
 	DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT);
 	struct ice_prof_map *prof;
-	u8 byte = 0;
-	u8 prof_id;
 	int status;
+	u8 prof_id;
+	u16 ptype;
 
 	bitmap_zero(ptgs_used, ICE_XLT1_CNT);
 
@@ -3102,57 +3098,35 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 	prof->context = 0;
 
 	/* build list of ptgs */
-	while (bytes && prof->ptg_cnt < ICE_MAX_PTG_PER_PROFILE) {
-		u8 bit;
+	for_each_set_bit(ptype, ptypes, ICE_FLOW_PTYPE_MAX) {
+		u8 ptg;
 
-		if (!ptypes[byte]) {
-			bytes--;
-			byte++;
+		/* The package should place all ptypes in a non-zero
+		 * PTG, so the following call should never fail.
+		 */
+		if (ice_ptg_find_ptype(hw, blk, ptype, &ptg))
 			continue;
-		}
-
-		/* Examine 8 bits per byte */
-		for_each_set_bit(bit, (unsigned long *)&ptypes[byte],
-				 BITS_PER_BYTE) {
-			u16 ptype;
-			u8 ptg;
 
-			ptype = byte * BITS_PER_BYTE + bit;
-
-			/* The package should place all ptypes in a non-zero
-			 * PTG, so the following call should never fail.
-			 */
-			if (ice_ptg_find_ptype(hw, blk, ptype, &ptg))
-				continue;
+		/* If PTG is already added, skip and continue */
+		if (test_bit(ptg, ptgs_used))
+			continue;
 
-			/* If PTG is already added, skip and continue */
-			if (test_bit(ptg, ptgs_used))
-				continue;
+		set_bit(ptg, ptgs_used);
+		/* Check to see there are any attributes for this ptype, and
+		 * add them if found.
+		 */
+		status = ice_add_prof_attrib(prof, ptg, ptype, attr, attr_cnt);
+		if (status == -ENOSPC)
+			break;
+		if (status) {
+			/* This is simple a ptype/PTG with no attribute */
+			prof->ptg[prof->ptg_cnt] = ptg;
+			prof->attr[prof->ptg_cnt].flags = 0;
+			prof->attr[prof->ptg_cnt].mask = 0;
 
-			__set_bit(ptg, ptgs_used);
-			/* Check to see there are any attributes for
-			 * this PTYPE, and add them if found.
-			 */
-			status = ice_add_prof_attrib(prof, ptg, ptype,
-						     attr, attr_cnt);
-			if (status == -ENOSPC)
+			if (++prof->ptg_cnt >= ICE_MAX_PTG_PER_PROFILE)
 				break;
-			if (status) {
-				/* This is simple a PTYPE/PTG with no
-				 * attribute
-				 */
-				prof->ptg[prof->ptg_cnt] = ptg;
-				prof->attr[prof->ptg_cnt].flags = 0;
-				prof->attr[prof->ptg_cnt].mask = 0;
-
-				if (++prof->ptg_cnt >=
-				    ICE_MAX_PTG_PER_PROFILE)
-					break;
-			}
 		}
-
-		bytes--;
-		byte++;
 	}
 
 	list_add(&prof->list, &hw->blk[blk].es.prof_map);
@@ -3604,6 +3578,19 @@ ice_move_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig,
 }
 
 /**
+ * ice_set_tcam_flags - set TCAM flag don't care mask
+ * @mask: mask for flags
+ * @dc_mask: pointer to the don't care mask
+ */
+static void ice_set_tcam_flags(u16 mask, u8 dc_mask[ICE_TCAM_KEY_VAL_SZ])
+{
+	u16 inverted_mask = ~mask;
+
+	/* flags are lowest u16 */
+	put_unaligned_le16(inverted_mask, dc_mask);
+}
+
+/**
  * ice_rem_chg_tcam_ent - remove a specific TCAM entry from change list
  * @hw: pointer to the HW struct
  * @idx: the index of the TCAM entry to remove
@@ -3673,6 +3660,9 @@ ice_prof_tcam_ena_dis(struct ice_hw *hw, enum ice_block blk, bool enable,
 	if (!p)
 		return -ENOMEM;
 
+	/* set don't care masks for TCAM flags */
+	ice_set_tcam_flags(tcam->attr.mask, dc_msk);
+
 	status = ice_tcam_write_entry(hw, blk, tcam->tcam_idx, tcam->prof_id,
 				      tcam->ptg, vsig, 0, tcam->attr.flags,
 				      vl_msk, dc_msk, nm_msk);
@@ -3699,6 +3689,34 @@ err_ice_prof_tcam_ena_dis:
 }
 
 /**
+ * ice_ptg_attr_in_use - determine if PTG and attribute pair is in use
+ * @ptg_attr: pointer to the PTG and attribute pair to check
+ * @ptgs_used: bitmap that denotes which PTGs are in use
+ * @attr_used: array of PTG and attributes pairs already used
+ * @attr_cnt: count of entries in the attr_used array
+ *
+ * Return: true if the PTG and attribute pair is in use, false otherwise.
+ */
+static bool
+ice_ptg_attr_in_use(struct ice_tcam_inf *ptg_attr, unsigned long *ptgs_used,
+		    struct ice_tcam_inf *attr_used[], u16 attr_cnt)
+{
+	u16 i;
+
+	if (!test_bit(ptg_attr->ptg, ptgs_used))
+		return false;
+
+	/* the PTG is used, so now look for correct attributes */
+	for (i = 0; i < attr_cnt; i++)
+		if (attr_used[i]->ptg == ptg_attr->ptg &&
+		    attr_used[i]->attr.flags == ptg_attr->attr.flags &&
+		    attr_used[i]->attr.mask == ptg_attr->attr.mask)
+			return true;
+
+	return false;
+}
+
+/**
  * ice_adj_prof_priorities - adjust profile based on priorities
  * @hw: pointer to the HW struct
  * @blk: hardware block
@@ -3710,10 +3728,16 @@ ice_adj_prof_priorities(struct ice_hw *hw, enum ice_block blk, u16 vsig,
 			struct list_head *chg)
 {
 	DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT);
+	struct ice_tcam_inf **attr_used;
 	struct ice_vsig_prof *t;
-	int status;
+	u16 attr_used_cnt = 0;
+	int status = 0;
 	u16 idx;
 
+	attr_used = kcalloc(ICE_MAX_PTG_ATTRS, sizeof(*attr_used), GFP_KERNEL);
+	if (!attr_used)
+		return -ENOMEM;
+
 	bitmap_zero(ptgs_used, ICE_XLT1_CNT);
 	idx = vsig & ICE_VSIG_IDX_M;
 
@@ -3731,11 +3755,15 @@ ice_adj_prof_priorities(struct ice_hw *hw, enum ice_block blk, u16 vsig,
 		u16 i;
 
 		for (i = 0; i < t->tcam_count; i++) {
+			bool used;
+
 			/* Scan the priorities from newest to oldest.
 			 * Make sure that the newest profiles take priority.
 			 */
-			if (test_bit(t->tcam[i].ptg, ptgs_used) &&
-			    t->tcam[i].in_use) {
+			used = ice_ptg_attr_in_use(&t->tcam[i], ptgs_used,
+						   attr_used, attr_used_cnt);
+
+			if (used && t->tcam[i].in_use) {
 				/* need to mark this PTG as never match, as it
 				 * was already in use and therefore duplicate
 				 * (and lower priority)
@@ -3745,9 +3773,8 @@ ice_adj_prof_priorities(struct ice_hw *hw, enum ice_block blk, u16 vsig,
 							       &t->tcam[i],
 							       chg);
 				if (status)
-					return status;
-			} else if (!test_bit(t->tcam[i].ptg, ptgs_used) &&
-				   !t->tcam[i].in_use) {
+					goto free_attr_used;
+			} else if (!used && !t->tcam[i].in_use) {
 				/* need to enable this PTG, as it in not in use
 				 * and not enabled (highest priority)
 				 */
@@ -3756,15 +3783,21 @@ ice_adj_prof_priorities(struct ice_hw *hw, enum ice_block blk, u16 vsig,
 							       &t->tcam[i],
 							       chg);
 				if (status)
-					return status;
+					goto free_attr_used;
 			}
 
 			/* keep track of used ptgs */
-			__set_bit(t->tcam[i].ptg, ptgs_used);
+			set_bit(t->tcam[i].ptg, ptgs_used);
+			if (attr_used_cnt < ICE_MAX_PTG_ATTRS)
+				attr_used[attr_used_cnt++] = &t->tcam[i];
+			else
+				ice_debug(hw, ICE_DBG_INIT, "Warn: ICE_MAX_PTG_ATTRS exceeded\n");
 		}
 	}
 
-	return 0;
+free_attr_used:
+	kfree(attr_used);
+	return status;
 }
 
 /**
@@ -3847,11 +3880,15 @@ ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl,
 		p->vsig = vsig;
 		p->tcam_idx = t->tcam[i].tcam_idx;
 
+		/* set don't care masks for TCAM flags */
+		ice_set_tcam_flags(t->tcam[i].attr.mask, dc_msk);
+
 		/* write the TCAM entry */
 		status = ice_tcam_write_entry(hw, blk, t->tcam[i].tcam_idx,
 					      t->tcam[i].prof_id,
-					      t->tcam[i].ptg, vsig, 0, 0,
-					      vl_msk, dc_msk, nm_msk);
+					      t->tcam[i].ptg, vsig, 0,
+					      t->tcam[i].attr.flags, vl_msk,
+					      dc_msk, nm_msk);
 		if (status) {
 			devm_kfree(ice_hw_to_dev(hw), p);
 			goto err_ice_add_prof_id_vsig;
@@ -4165,9 +4202,6 @@ ice_flow_assoc_fdir_prof(struct ice_hw *hw, enum ice_block blk,
 	u16 vsi_num;
 	int status;
 
-	if (blk != ICE_BLK_FD)
-		return -EINVAL;
-
 	vsi_num = ice_get_hw_vsi_num(hw, dest_vsi);
 	status = ice_add_prof_id_flow(hw, blk, vsi_num, hdl);
 	if (status) {
@@ -4176,6 +4210,9 @@ ice_flow_assoc_fdir_prof(struct ice_hw *hw, enum ice_block blk,
 		return status;
 	}
 
+	if (blk != ICE_BLK_FD)
+		return 0;
+
 	vsi_num = ice_get_hw_vsi_num(hw, fdir_vsi);
 	status = ice_add_prof_id_flow(hw, blk, vsi_num, hdl);
 	if (status) {
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
index 28b0897adf32..ee5d9f9c9d53 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
@@ -39,9 +39,10 @@ bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype);
 
 /* XLT2/VSI group functions */
 int
-ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
-	     const struct ice_ptype_attributes *attr, u16 attr_cnt,
-	     struct ice_fv_word *es, u16 *masks, bool symm, bool fd_swap);
+ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id,
+	     unsigned long *ptypes, const struct ice_ptype_attributes *attr,
+	     u16 attr_cnt, struct ice_fv_word *es, u16 *masks, bool symm,
+	     bool fd_swap);
 struct ice_prof_map *
 ice_search_prof_id(struct ice_hw *hw, enum ice_block blk, u64 id);
 int
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h
index 817beca591e0..80c9e7c749c2 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h
@@ -187,6 +187,7 @@ struct ice_prof_map {
 };
 
 #define ICE_INVALID_TCAM	0xFFFF
+#define ICE_MAX_PTG_ATTRS	1024
 
 struct ice_tcam_inf {
 	u16 tcam_idx;
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c
index d97b751052f2..c9b6d0a84bd1 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.c
+++ b/drivers/net/ethernet/intel/ice/ice_flow.c
@@ -5,6 +5,38 @@
 #include "ice_flow.h"
 #include <net/gre.h>
 
+/* Size of known protocol header fields */
+#define ICE_FLOW_FLD_SZ_ETH_TYPE	2
+#define ICE_FLOW_FLD_SZ_VLAN		2
+#define ICE_FLOW_FLD_SZ_IPV4_ADDR	4
+#define ICE_FLOW_FLD_SZ_IPV6_ADDR	16
+#define ICE_FLOW_FLD_SZ_IPV6_PRE32_ADDR	4
+#define ICE_FLOW_FLD_SZ_IPV6_PRE48_ADDR	6
+#define ICE_FLOW_FLD_SZ_IPV6_PRE64_ADDR	8
+#define ICE_FLOW_FLD_SZ_IPV4_ID		2
+#define ICE_FLOW_FLD_SZ_IPV6_ID		4
+#define ICE_FLOW_FLD_SZ_IP_CHKSUM	2
+#define ICE_FLOW_FLD_SZ_TCP_CHKSUM	2
+#define ICE_FLOW_FLD_SZ_UDP_CHKSUM	2
+#define ICE_FLOW_FLD_SZ_SCTP_CHKSUM	4
+#define ICE_FLOW_FLD_SZ_IP_DSCP		1
+#define ICE_FLOW_FLD_SZ_IP_TTL		1
+#define ICE_FLOW_FLD_SZ_IP_PROT		1
+#define ICE_FLOW_FLD_SZ_PORT		2
+#define ICE_FLOW_FLD_SZ_TCP_FLAGS	1
+#define ICE_FLOW_FLD_SZ_ICMP_TYPE	1
+#define ICE_FLOW_FLD_SZ_ICMP_CODE	1
+#define ICE_FLOW_FLD_SZ_ARP_OPER	2
+#define ICE_FLOW_FLD_SZ_GRE_KEYID	4
+#define ICE_FLOW_FLD_SZ_GTP_TEID	4
+#define ICE_FLOW_FLD_SZ_GTP_QFI		2
+#define ICE_FLOW_FLD_SZ_PFCP_SEID 8
+#define ICE_FLOW_FLD_SZ_ESP_SPI	4
+#define ICE_FLOW_FLD_SZ_AH_SPI	4
+#define ICE_FLOW_FLD_SZ_NAT_T_ESP_SPI	4
+#define ICE_FLOW_FLD_SZ_L2TPV2_SESS_ID	2
+#define ICE_FLOW_FLD_SZ_L2TPV2_LEN_SESS_ID	2
+
 /* Describe properties of a protocol header field */
 struct ice_flow_field_info {
 	enum ice_flow_seg_hdr hdr;
@@ -20,6 +52,7 @@ struct ice_flow_field_info {
 	.mask = 0, \
 }
 
+/* QFI: 6-bit field in GTP-U PDU Session Container (3GPP TS 38.415) */
 #define ICE_FLOW_FLD_INFO_MSK(_hdr, _offset_bytes, _size_bytes, _mask) { \
 	.hdr = _hdr, \
 	.off = (_offset_bytes) * BITS_PER_BYTE, \
@@ -61,7 +94,33 @@ struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = {
 	/* ICE_FLOW_FIELD_IDX_IPV6_SA */
 	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 8, sizeof(struct in6_addr)),
 	/* ICE_FLOW_FIELD_IDX_IPV6_DA */
-	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 24, sizeof(struct in6_addr)),
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 24, ICE_FLOW_FLD_SZ_IPV6_ADDR),
+	/* ICE_FLOW_FIELD_IDX_IPV4_CHKSUM */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV4, 10, ICE_FLOW_FLD_SZ_IP_CHKSUM),
+	/* ICE_FLOW_FIELD_IDX_IPV4_FRAG */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV_FRAG, 4,
+			  ICE_FLOW_FLD_SZ_IPV4_ID),
+	/* ICE_FLOW_FIELD_IDX_IPV6_FRAG */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV_FRAG, 4,
+			  ICE_FLOW_FLD_SZ_IPV6_ID),
+	/* ICE_FLOW_FIELD_IDX_IPV6_PRE32_SA */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 8,
+			  ICE_FLOW_FLD_SZ_IPV6_PRE32_ADDR),
+	/* ICE_FLOW_FIELD_IDX_IPV6_PRE32_DA */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 24,
+			  ICE_FLOW_FLD_SZ_IPV6_PRE32_ADDR),
+	/* ICE_FLOW_FIELD_IDX_IPV6_PRE48_SA */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 8,
+			  ICE_FLOW_FLD_SZ_IPV6_PRE48_ADDR),
+	/* ICE_FLOW_FIELD_IDX_IPV6_PRE48_DA */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 24,
+			  ICE_FLOW_FLD_SZ_IPV6_PRE48_ADDR),
+	/* ICE_FLOW_FIELD_IDX_IPV6_PRE64_SA */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 8,
+			  ICE_FLOW_FLD_SZ_IPV6_PRE64_ADDR),
+	/* ICE_FLOW_FIELD_IDX_IPV6_PRE64_DA */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 24,
+			  ICE_FLOW_FLD_SZ_IPV6_PRE64_ADDR),
 	/* Transport */
 	/* ICE_FLOW_FIELD_IDX_TCP_SRC_PORT */
 	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_TCP, 0, sizeof(__be16)),
@@ -76,7 +135,14 @@ struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = {
 	/* ICE_FLOW_FIELD_IDX_SCTP_DST_PORT */
 	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_SCTP, 2, sizeof(__be16)),
 	/* ICE_FLOW_FIELD_IDX_TCP_FLAGS */
-	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_TCP, 13, 1),
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_TCP, 13, ICE_FLOW_FLD_SZ_TCP_FLAGS),
+	/* ICE_FLOW_FIELD_IDX_TCP_CHKSUM */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_TCP, 16, ICE_FLOW_FLD_SZ_TCP_CHKSUM),
+	/* ICE_FLOW_FIELD_IDX_UDP_CHKSUM */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_UDP, 6, ICE_FLOW_FLD_SZ_UDP_CHKSUM),
+	/* ICE_FLOW_FIELD_IDX_SCTP_CHKSUM */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_SCTP, 8,
+			  ICE_FLOW_FLD_SZ_SCTP_CHKSUM),
 	/* ARP */
 	/* ICE_FLOW_FIELD_IDX_ARP_SIP */
 	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_ARP, 14, sizeof(struct in_addr)),
@@ -108,9 +174,17 @@ struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = {
 	ICE_FLOW_FLD_INFO_MSK(ICE_FLOW_SEG_HDR_GTPU_EH, 22, sizeof(__be16),
 			      0x3f00),
 	/* ICE_FLOW_FIELD_IDX_GTPU_UP_TEID */
-	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GTPU_UP, 12, sizeof(__be32)),
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GTPU_UP, 12,
+			  ICE_FLOW_FLD_SZ_GTP_TEID),
+	/* ICE_FLOW_FIELD_IDX_GTPU_UP_QFI */
+	ICE_FLOW_FLD_INFO_MSK(ICE_FLOW_SEG_HDR_GTPU_UP, 22,
+			      ICE_FLOW_FLD_SZ_GTP_QFI, 0x3f00),
 	/* ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID */
-	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GTPU_DWN, 12, sizeof(__be32)),
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GTPU_DWN, 12,
+			  ICE_FLOW_FLD_SZ_GTP_TEID),
+	/* ICE_FLOW_FIELD_IDX_GTPU_DWN_QFI */
+	ICE_FLOW_FLD_INFO_MSK(ICE_FLOW_SEG_HDR_GTPU_DWN, 22,
+			      ICE_FLOW_FLD_SZ_GTP_QFI, 0x3f00),
 	/* PPPoE */
 	/* ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID */
 	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_PPPOE, 2, sizeof(__be16)),
@@ -128,7 +202,16 @@ struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = {
 	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_AH, 4, sizeof(__be32)),
 	/* NAT_T_ESP */
 	/* ICE_FLOW_FIELD_IDX_NAT_T_ESP_SPI */
-	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_NAT_T_ESP, 8, sizeof(__be32)),
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_NAT_T_ESP, 8,
+			  ICE_FLOW_FLD_SZ_NAT_T_ESP_SPI),
+	/* L2TPV2 */
+	/* ICE_FLOW_FIELD_IDX_L2TPV2_SESS_ID */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_L2TPV2, 12,
+			  ICE_FLOW_FLD_SZ_L2TPV2_SESS_ID),
+	/* L2TPV2_LEN */
+	/* ICE_FLOW_FIELD_IDX_L2TPV2_LEN_SESS_ID */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_L2TPV2, 14,
+			  ICE_FLOW_FLD_SZ_L2TPV2_LEN_SESS_ID),
 };
 
 /* Bitmaps indicating relevant packet types for a particular protocol header
@@ -137,9 +220,9 @@ struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = {
  */
 static const u32 ice_ptypes_mac_ofos[] = {
 	0xFDC00846, 0xBFBF7F7E, 0xF70001DF, 0xFEFDFDFB,
-	0x0000077E, 0x00000000, 0x00000000, 0x00000000,
-	0x00400000, 0x03FFF000, 0x7FFFFFE0, 0x00000000,
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x0000077E, 0x000003FF, 0x00000000, 0x00000000,
+	0x00400000, 0x03FFF000, 0xFFFFFFE0, 0x00000707,
+	0xFFFFF000, 0x000003FF, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -162,10 +245,10 @@ static const u32 ice_ptypes_macvlan_il[] = {
  * include IPv4 other PTYPEs
  */
 static const u32 ice_ptypes_ipv4_ofos[] = {
-	0x1DC00000, 0x04000800, 0x00000000, 0x00000000,
+	0x1D800000, 0xBFBF7800, 0x000001DF, 0x00000000,
 	0x00000000, 0x00000155, 0x00000000, 0x00000000,
-	0x00000000, 0x000FC000, 0x00000000, 0x00000000,
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x000FC000, 0x000002A0, 0x00000000,
+	0x00015000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -176,10 +259,10 @@ static const u32 ice_ptypes_ipv4_ofos[] = {
  * IPv4 other PTYPEs
  */
 static const u32 ice_ptypes_ipv4_ofos_all[] = {
-	0x1DC00000, 0x04000800, 0x00000000, 0x00000000,
+	0x1D800000, 0x27BF7800, 0x00000000, 0x00000000,
 	0x00000000, 0x00000155, 0x00000000, 0x00000000,
-	0x00000000, 0x000FC000, 0x83E0F800, 0x00000101,
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x000FC000, 0x83E0FAA0, 0x00000101,
+	0x3FFD5000, 0x00000000, 0x02FBEFBC, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -191,7 +274,7 @@ static const u32 ice_ptypes_ipv4_il[] = {
 	0xE0000000, 0xB807700E, 0x80000003, 0xE01DC03B,
 	0x0000000E, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x001FF800, 0x00000000,
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0xC0FC0000, 0x0000000F, 0xBC0BC0BC, 0x00000BC0,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -202,10 +285,10 @@ static const u32 ice_ptypes_ipv4_il[] = {
  * include IPv6 other PTYPEs
  */
 static const u32 ice_ptypes_ipv6_ofos[] = {
-	0x00000000, 0x00000000, 0x77000000, 0x10002000,
+	0x00000000, 0x00000000, 0x76000000, 0x10002000,
 	0x00000000, 0x000002AA, 0x00000000, 0x00000000,
-	0x00000000, 0x03F00000, 0x00000000, 0x00000000,
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x03F00000, 0x00000540, 0x00000000,
+	0x0002A000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -216,10 +299,10 @@ static const u32 ice_ptypes_ipv6_ofos[] = {
  * IPv6 other PTYPEs
  */
 static const u32 ice_ptypes_ipv6_ofos_all[] = {
-	0x00000000, 0x00000000, 0x77000000, 0x10002000,
-	0x00000000, 0x000002AA, 0x00000000, 0x00000000,
-	0x00080F00, 0x03F00000, 0x7C1F0000, 0x00000206,
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x00000000, 0x76000000, 0xFEFDE000,
+	0x0000077E, 0x000002AA, 0x00000000, 0x00000000,
+	0x00000000, 0x03F00000, 0x7C1F0540, 0x00000206,
+	0xC002A000, 0x000003FF, 0xBC000000, 0x0002FBEF,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -231,7 +314,7 @@ static const u32 ice_ptypes_ipv6_il[] = {
 	0x00000000, 0x03B80770, 0x000001DC, 0x0EE00000,
 	0x00000770, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x7FE00000, 0x00000000,
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x3F000000, 0x000003F0, 0x02F02F00, 0x0002F02F,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -304,8 +387,8 @@ static const u32 ice_ptypes_ipv6_il_no_l4[] = {
 static const u32 ice_ptypes_udp_il[] = {
 	0x81000000, 0x20204040, 0x04000010, 0x80810102,
 	0x00000040, 0x00000000, 0x00000000, 0x00000000,
-	0x00000000, 0x00410000, 0x90842000, 0x00000007,
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x00410000, 0x908427E0, 0x00000007,
+	0x0413F000, 0x00000041, 0x10410410, 0x00004104,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -317,7 +400,7 @@ static const u32 ice_ptypes_tcp_il[] = {
 	0x04000000, 0x80810102, 0x10000040, 0x02040408,
 	0x00000102, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00820000, 0x21084000, 0x00000000,
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x08200000, 0x00000082, 0x20820820, 0x00008208,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -329,7 +412,7 @@ static const u32 ice_ptypes_sctp_il[] = {
 	0x08000000, 0x01020204, 0x20000081, 0x04080810,
 	0x00000204, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x01040000, 0x00000000, 0x00000000,
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x10400000, 0x00000104, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -353,7 +436,7 @@ static const u32 ice_ptypes_icmp_il[] = {
 	0x00000000, 0x02040408, 0x40000102, 0x08101020,
 	0x00000408, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x42108000, 0x00000000,
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x20800000, 0x00000208, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -365,7 +448,7 @@ static const u32 ice_ptypes_gre_of[] = {
 	0x00000000, 0xBFBF7800, 0x000001DF, 0xFEFDE000,
 	0x0000017E, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x00000000, 0xBEFBEFBC, 0x0002FBEF,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -374,7 +457,7 @@ static const u32 ice_ptypes_gre_of[] = {
 
 /* Packet types for packets with an Innermost/Last MAC header */
 static const u32 ice_ptypes_mac_il[] = {
-	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x20000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -388,7 +471,7 @@ static const u32 ice_ptypes_mac_il[] = {
 static const u32 ice_ptypes_gtpc[] = {
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
-	0x00000000, 0x00000000, 0x00000180, 0x00000000,
+	0x00000000, 0x00000000, 0x000001E0, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
@@ -1421,7 +1504,7 @@ ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk,
 	}
 
 	/* Add a HW profile for this flow profile */
-	status = ice_add_prof(hw, blk, prof_id, (u8 *)params->ptypes,
+	status = ice_add_prof(hw, blk, prof_id, params->ptypes,
 			      params->attr, params->attr_cnt, params->es,
 			      params->mask, symm, true);
 	if (status) {
@@ -1617,7 +1700,7 @@ ice_flow_set_parser_prof(struct ice_hw *hw, u16 dest_vsi, u16 fdir_vsi,
 		break;
 	}
 
-	status = ice_add_prof(hw, blk, id, (u8 *)prof->ptypes,
+	status = ice_add_prof(hw, blk, id, prof->ptypes,
 			      params->attr, params->attr_cnt,
 			      params->es, params->mask, false, false);
 	if (status)
@@ -2325,6 +2408,130 @@ static void ice_rss_set_symm(struct ice_hw *hw, struct ice_flow_prof *prof)
 }
 
 /**
+ * ice_rss_cfg_raw_symm - Configure symmetric RSS for a raw parser profile
+ * @hw:      device HW
+ * @prof:    parser profile describing extracted FV (field vector) entries
+ * @prof_id: RSS profile identifier used to program symmetry registers
+ *
+ * The routine scans the parser profile's FV entries and looks for
+ * direction-sensitive pairs (L3 src/dst, L4 src/dst). When a pair is found,
+ * it programs XOR-based symmetry so that flows hash identically regardless
+ * of packet direction. This preserves CPU affinity for the same 5-tuple.
+ *
+ * Notes:
+ * - The size of each logical field (IPv4/IPv6 address, L4 port) is expressed
+ *   in units of ICE_FLOW_FV_EXTRACT_SZ so we can step across fv[] correctly.
+ * - We guard against out-of-bounds access before looking at fv[i + len].
+ */
+static void ice_rss_cfg_raw_symm(struct ice_hw *hw,
+				 const struct ice_parser_profile *prof,
+				 u64 prof_id)
+{
+	for (size_t i = 0; i < prof->fv_num; i++) {
+		u8 proto_id = prof->fv[i].proto_id;
+		u16 src_off = 0, dst_off = 0;
+		size_t src_idx, dst_idx;
+		bool is_matched = false;
+		unsigned int len = 0;
+
+		switch (proto_id) {
+		/* IPv4 address pairs (outer/inner variants) */
+		case ICE_PROT_IPV4_OF_OR_S:
+		case ICE_PROT_IPV4_IL:
+		case ICE_PROT_IPV4_IL_IL:
+			len = ICE_FLOW_FLD_SZ_IPV4_ADDR /
+			      ICE_FLOW_FV_EXTRACT_SZ;
+			src_off = ICE_FLOW_FIELD_IPV4_SRC_OFFSET;
+			dst_off = ICE_FLOW_FIELD_IPV4_DST_OFFSET;
+			break;
+
+		/* IPv6 address pairs (outer/inner variants) */
+		case ICE_PROT_IPV6_OF_OR_S:
+		case ICE_PROT_IPV6_IL:
+		case ICE_PROT_IPV6_IL_IL:
+			len = ICE_FLOW_FLD_SZ_IPV6_ADDR /
+			      ICE_FLOW_FV_EXTRACT_SZ;
+			src_off = ICE_FLOW_FIELD_IPV6_SRC_OFFSET;
+			dst_off = ICE_FLOW_FIELD_IPV6_DST_OFFSET;
+			break;
+
+		/* L4 port pairs (TCP/UDP/SCTP) */
+		case ICE_PROT_TCP_IL:
+		case ICE_PROT_UDP_IL_OR_S:
+		case ICE_PROT_SCTP_IL:
+			len = ICE_FLOW_FLD_SZ_PORT / ICE_FLOW_FV_EXTRACT_SZ;
+			src_off = ICE_FLOW_FIELD_SRC_PORT_OFFSET;
+			dst_off = ICE_FLOW_FIELD_DST_PORT_OFFSET;
+			break;
+
+		default:
+			continue;
+		}
+
+		/* Bounds check before accessing fv[i + len]. */
+		if (i + len >= prof->fv_num)
+			continue;
+
+		/* Verify src/dst pairing for this protocol id. */
+		is_matched = prof->fv[i].offset == src_off &&
+			     prof->fv[i + len].proto_id == proto_id &&
+			     prof->fv[i + len].offset == dst_off;
+		if (!is_matched)
+			continue;
+
+		/* Program XOR symmetry for this field pair. */
+		src_idx = i;
+		dst_idx = i + len;
+
+		ice_rss_config_xor(hw, prof_id, src_idx, dst_idx, len);
+
+		/* Skip over the pair we just handled; the loop's ++i advances
+		 * one more element, hence the --i after the jump.
+		 */
+		i += (2 * len);
+		/* not strictly needed; keeps static analyzers happy */
+		if (i == 0)
+			break;
+		--i;
+	}
+}
+
+/* Max registers index per packet profile */
+#define ICE_SYMM_REG_INDEX_MAX 6
+
+/**
+ * ice_rss_update_raw_symm - update symmetric hash configuration
+ * for raw pattern
+ * @hw: pointer to the hardware structure
+ * @cfg: configure parameters for raw pattern
+ * @id: profile tracking ID
+ *
+ * Update symmetric hash configuration for raw pattern if required.
+ * Otherwise only clear to default.
+ */
+void
+ice_rss_update_raw_symm(struct ice_hw *hw,
+			struct ice_rss_raw_cfg *cfg, u64 id)
+{
+	struct ice_prof_map *map;
+	u8 prof_id, m;
+
+	mutex_lock(&hw->blk[ICE_BLK_RSS].es.prof_map_lock);
+	map = ice_search_prof_id(hw, ICE_BLK_RSS, id);
+	if (map)
+		prof_id = map->prof_id;
+	mutex_unlock(&hw->blk[ICE_BLK_RSS].es.prof_map_lock);
+	if (!map)
+		return;
+	/* clear to default */
+	for (m = 0; m < ICE_SYMM_REG_INDEX_MAX; m++)
+		wr32(hw, GLQF_HSYMM(prof_id, m), 0);
+
+	if (cfg->symm)
+		ice_rss_cfg_raw_symm(hw, &cfg->prof, prof_id);
+}
+
+/**
  * ice_add_rss_cfg_sync - add an RSS configuration
  * @hw: pointer to the hardware structure
  * @vsi_handle: software VSI handle
@@ -2573,38 +2780,38 @@ ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle,
  * convert its values to their appropriate flow L3, L4 values.
  */
 #define ICE_FLOW_AVF_RSS_IPV4_MASKS \
-	(BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_OTHER) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_FRAG_IPV4))
+	(BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV4))
 #define ICE_FLOW_AVF_RSS_TCP_IPV4_MASKS \
-	(BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_TCP_SYN_NO_ACK) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_TCP))
+	(BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP))
 #define ICE_FLOW_AVF_RSS_UDP_IPV4_MASKS \
-	(BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV4_UDP) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV4_UDP) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_UDP))
+	(BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP))
 #define ICE_FLOW_AVF_RSS_ALL_IPV4_MASKS \
 	(ICE_FLOW_AVF_RSS_TCP_IPV4_MASKS | ICE_FLOW_AVF_RSS_UDP_IPV4_MASKS | \
-	 ICE_FLOW_AVF_RSS_IPV4_MASKS | BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_SCTP))
+	 ICE_FLOW_AVF_RSS_IPV4_MASKS | BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP))
 
 #define ICE_FLOW_AVF_RSS_IPV6_MASKS \
-	(BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_OTHER) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_FRAG_IPV6))
+	(BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV6))
 #define ICE_FLOW_AVF_RSS_UDP_IPV6_MASKS \
-	(BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV6_UDP) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV6_UDP) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_UDP))
+	(BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP))
 #define ICE_FLOW_AVF_RSS_TCP_IPV6_MASKS \
-	(BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_TCP_SYN_NO_ACK) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_TCP))
+	(BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP))
 #define ICE_FLOW_AVF_RSS_ALL_IPV6_MASKS \
 	(ICE_FLOW_AVF_RSS_TCP_IPV6_MASKS | ICE_FLOW_AVF_RSS_UDP_IPV6_MASKS | \
-	 ICE_FLOW_AVF_RSS_IPV6_MASKS | BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_SCTP))
+	 ICE_FLOW_AVF_RSS_IPV6_MASKS | BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP))
 
 /**
  * ice_add_avf_rss_cfg - add an RSS configuration for AVF driver
  * @hw: pointer to the hardware structure
  * @vsi: VF's VSI
- * @avf_hash: hash bit fields (ICE_AVF_FLOW_FIELD_*) to configure
+ * @avf_hash: hash bit fields (LIBIE_FILTER_PCTYPE_*) to configure
  *
  * This function will take the hash bitmap provided by the AVF driver via a
  * message, convert it to ICE-compatible values, and configure RSS flow
@@ -2621,8 +2828,7 @@ int ice_add_avf_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi, u64 avf_hash)
 		return -EINVAL;
 
 	vsi_handle = vsi->idx;
-	if (avf_hash == ICE_AVF_FLOW_FIELD_INVALID ||
-	    !ice_is_vsi_valid(hw, vsi_handle))
+	if (!avf_hash || !ice_is_vsi_valid(hw, vsi_handle))
 		return -EINVAL;
 
 	/* Make sure no unsupported bits are specified */
@@ -2658,11 +2864,11 @@ int ice_add_avf_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi, u64 avf_hash)
 					ICE_FLOW_HASH_UDP_PORT;
 				hash_flds &= ~ICE_FLOW_AVF_RSS_UDP_IPV4_MASKS;
 			} else if (hash_flds &
-				   BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_SCTP)) {
+				   BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP)) {
 				rss_hash = ICE_FLOW_HASH_IPV4 |
 					ICE_FLOW_HASH_SCTP_PORT;
 				hash_flds &=
-					~BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_SCTP);
+					~BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP);
 			}
 		} else if (hash_flds & ICE_FLOW_AVF_RSS_ALL_IPV6_MASKS) {
 			if (hash_flds & ICE_FLOW_AVF_RSS_IPV6_MASKS) {
@@ -2679,11 +2885,11 @@ int ice_add_avf_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi, u64 avf_hash)
 					ICE_FLOW_HASH_UDP_PORT;
 				hash_flds &= ~ICE_FLOW_AVF_RSS_UDP_IPV6_MASKS;
 			} else if (hash_flds &
-				   BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_SCTP)) {
+				   BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP)) {
 				rss_hash = ICE_FLOW_HASH_IPV6 |
 					ICE_FLOW_HASH_SCTP_PORT;
 				hash_flds &=
-					~BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_SCTP);
+					~BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP);
 			}
 		}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h
index 6cb7bb879c98..6c6cdc8addb1 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.h
+++ b/drivers/net/ethernet/intel/ice/ice_flow.h
@@ -4,6 +4,8 @@
 #ifndef _ICE_FLOW_H_
 #define _ICE_FLOW_H_
 
+#include <linux/net/intel/libie/pctype.h>
+
 #include "ice_flex_type.h"
 #include "ice_parser.h"
 
@@ -20,6 +22,15 @@
 #define ICE_FLOW_HASH_IPV6	\
 	(BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA) | \
 	 BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA))
+#define ICE_FLOW_HASH_IPV6_PRE32	\
+	(BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE32_SA) | \
+	 BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE32_DA))
+#define ICE_FLOW_HASH_IPV6_PRE48	\
+	(BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE48_SA) | \
+	 BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE48_DA))
+#define ICE_FLOW_HASH_IPV6_PRE64	\
+	(BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE64_SA) | \
+	 BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE64_DA))
 #define ICE_FLOW_HASH_TCP_PORT	\
 	(BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT) | \
 	 BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT))
@@ -38,6 +49,33 @@
 #define ICE_HASH_SCTP_IPV4	(ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_SCTP_PORT)
 #define ICE_HASH_SCTP_IPV6	(ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_SCTP_PORT)
 
+#define ICE_HASH_TCP_IPV6_PRE32	 \
+	(ICE_FLOW_HASH_IPV6_PRE32 | ICE_FLOW_HASH_TCP_PORT)
+#define ICE_HASH_UDP_IPV6_PRE32	 \
+	(ICE_FLOW_HASH_IPV6_PRE32 | ICE_FLOW_HASH_UDP_PORT)
+#define ICE_HASH_SCTP_IPV6_PRE32 \
+	(ICE_FLOW_HASH_IPV6_PRE32 | ICE_FLOW_HASH_SCTP_PORT)
+#define ICE_HASH_TCP_IPV6_PRE48	 \
+	(ICE_FLOW_HASH_IPV6_PRE48 | ICE_FLOW_HASH_TCP_PORT)
+#define ICE_HASH_UDP_IPV6_PRE48	 \
+	(ICE_FLOW_HASH_IPV6_PRE48 | ICE_FLOW_HASH_UDP_PORT)
+#define ICE_HASH_SCTP_IPV6_PRE48 \
+	(ICE_FLOW_HASH_IPV6_PRE48 | ICE_FLOW_HASH_SCTP_PORT)
+#define ICE_HASH_TCP_IPV6_PRE64	 \
+	(ICE_FLOW_HASH_IPV6_PRE64 | ICE_FLOW_HASH_TCP_PORT)
+#define ICE_HASH_UDP_IPV6_PRE64	 \
+	(ICE_FLOW_HASH_IPV6_PRE64 | ICE_FLOW_HASH_UDP_PORT)
+#define ICE_HASH_SCTP_IPV6_PRE64 \
+	(ICE_FLOW_HASH_IPV6_PRE64 | ICE_FLOW_HASH_SCTP_PORT)
+
+#define ICE_FLOW_HASH_GTP_TEID \
+	(BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID))
+
+#define ICE_FLOW_HASH_GTP_IPV4_TEID \
+	(ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_TEID)
+#define ICE_FLOW_HASH_GTP_IPV6_TEID \
+	(ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_TEID)
+
 #define ICE_FLOW_HASH_GTP_C_TEID \
 	(BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID))
 
@@ -126,6 +164,23 @@
 #define ICE_FLOW_HASH_NAT_T_ESP_IPV6_SPI \
 	(ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_NAT_T_ESP_SPI)
 
+#define ICE_FLOW_HASH_L2TPV2_SESS_ID \
+	(BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV2_SESS_ID))
+#define ICE_FLOW_HASH_L2TPV2_SESS_ID_ETH \
+	(ICE_FLOW_HASH_ETH | ICE_FLOW_HASH_L2TPV2_SESS_ID)
+
+#define ICE_FLOW_HASH_L2TPV2_LEN_SESS_ID \
+	(BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV2_LEN_SESS_ID))
+#define ICE_FLOW_HASH_L2TPV2_LEN_SESS_ID_ETH \
+	(ICE_FLOW_HASH_ETH | ICE_FLOW_HASH_L2TPV2_LEN_SESS_ID)
+
+#define ICE_FLOW_FIELD_IPV4_SRC_OFFSET 12
+#define ICE_FLOW_FIELD_IPV4_DST_OFFSET 16
+#define ICE_FLOW_FIELD_IPV6_SRC_OFFSET 8
+#define ICE_FLOW_FIELD_IPV6_DST_OFFSET 24
+#define ICE_FLOW_FIELD_SRC_PORT_OFFSET 0
+#define ICE_FLOW_FIELD_DST_PORT_OFFSET 2
+
 /* Protocol header fields within a packet segment. A segment consists of one or
  * more protocol headers that make up a logical group of protocol headers. Each
  * logical group of protocol headers encapsulates or is encapsulated using/by
@@ -158,10 +213,13 @@ enum ice_flow_seg_hdr {
 	ICE_FLOW_SEG_HDR_AH		= 0x00200000,
 	ICE_FLOW_SEG_HDR_NAT_T_ESP	= 0x00400000,
 	ICE_FLOW_SEG_HDR_ETH_NON_IP	= 0x00800000,
+	ICE_FLOW_SEG_HDR_GTPU_NON_IP	= 0x01000000,
+	ICE_FLOW_SEG_HDR_L2TPV2		= 0x10000000,
 	/* The following is an additive bit for ICE_FLOW_SEG_HDR_IPV4 and
-	 * ICE_FLOW_SEG_HDR_IPV6 which include the IPV4 other PTYPEs
+	 * ICE_FLOW_SEG_HDR_IPV6.
 	 */
-	ICE_FLOW_SEG_HDR_IPV_OTHER      = 0x20000000,
+	ICE_FLOW_SEG_HDR_IPV_FRAG	= 0x40000000,
+	ICE_FLOW_SEG_HDR_IPV_OTHER	= 0x80000000,
 };
 
 /* These segments all have the same PTYPES, but are otherwise distinguished by
@@ -198,6 +256,15 @@ enum ice_flow_field {
 	ICE_FLOW_FIELD_IDX_IPV4_DA,
 	ICE_FLOW_FIELD_IDX_IPV6_SA,
 	ICE_FLOW_FIELD_IDX_IPV6_DA,
+	ICE_FLOW_FIELD_IDX_IPV4_CHKSUM,
+	ICE_FLOW_FIELD_IDX_IPV4_ID,
+	ICE_FLOW_FIELD_IDX_IPV6_ID,
+	ICE_FLOW_FIELD_IDX_IPV6_PRE32_SA,
+	ICE_FLOW_FIELD_IDX_IPV6_PRE32_DA,
+	ICE_FLOW_FIELD_IDX_IPV6_PRE48_SA,
+	ICE_FLOW_FIELD_IDX_IPV6_PRE48_DA,
+	ICE_FLOW_FIELD_IDX_IPV6_PRE64_SA,
+	ICE_FLOW_FIELD_IDX_IPV6_PRE64_DA,
 	/* L4 */
 	ICE_FLOW_FIELD_IDX_TCP_SRC_PORT,
 	ICE_FLOW_FIELD_IDX_TCP_DST_PORT,
@@ -206,6 +273,9 @@ enum ice_flow_field {
 	ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT,
 	ICE_FLOW_FIELD_IDX_SCTP_DST_PORT,
 	ICE_FLOW_FIELD_IDX_TCP_FLAGS,
+	ICE_FLOW_FIELD_IDX_TCP_CHKSUM,
+	ICE_FLOW_FIELD_IDX_UDP_CHKSUM,
+	ICE_FLOW_FIELD_IDX_SCTP_CHKSUM,
 	/* ARP */
 	ICE_FLOW_FIELD_IDX_ARP_SIP,
 	ICE_FLOW_FIELD_IDX_ARP_DIP,
@@ -226,13 +296,13 @@ enum ice_flow_field {
 	ICE_FLOW_FIELD_IDX_GTPU_EH_QFI,
 	/* GTPU_UP */
 	ICE_FLOW_FIELD_IDX_GTPU_UP_TEID,
+	ICE_FLOW_FIELD_IDX_GTPU_UP_QFI,
 	/* GTPU_DWN */
 	ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID,
-	/* PPPoE */
+	ICE_FLOW_FIELD_IDX_GTPU_DWN_QFI,
 	ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID,
 	/* PFCP */
 	ICE_FLOW_FIELD_IDX_PFCP_SEID,
-	/* L2TPv3 */
 	ICE_FLOW_FIELD_IDX_L2TPV3_SESS_ID,
 	/* ESP */
 	ICE_FLOW_FIELD_IDX_ESP_SPI,
@@ -240,10 +310,16 @@ enum ice_flow_field {
 	ICE_FLOW_FIELD_IDX_AH_SPI,
 	/* NAT_T ESP */
 	ICE_FLOW_FIELD_IDX_NAT_T_ESP_SPI,
+	/* L2TPV2 SESSION ID*/
+	ICE_FLOW_FIELD_IDX_L2TPV2_SESS_ID,
+	/* L2TPV2_LEN SESSION ID */
+	ICE_FLOW_FIELD_IDX_L2TPV2_LEN_SESS_ID,
 	 /* The total number of enums must not exceed 64 */
 	ICE_FLOW_FIELD_IDX_MAX
 };
 
+static_assert(ICE_FLOW_FIELD_IDX_MAX <= 64, "The total number of enums must not exceed 64");
+
 #define ICE_FLOW_HASH_FLD_IPV4_SA	BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA)
 #define ICE_FLOW_HASH_FLD_IPV6_SA	BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA)
 #define ICE_FLOW_HASH_FLD_IPV4_DA	BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)
@@ -264,57 +340,27 @@ enum ice_flow_field {
 #define ICE_FLOW_HASH_FLD_GTPU_DWN_TEID \
 	BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID)
 
-/* Flow headers and fields for AVF support */
-enum ice_flow_avf_hdr_field {
-	/* Values 0 - 28 are reserved for future use */
-	ICE_AVF_FLOW_FIELD_INVALID		= 0,
-	ICE_AVF_FLOW_FIELD_UNICAST_IPV4_UDP	= 29,
-	ICE_AVF_FLOW_FIELD_MULTICAST_IPV4_UDP,
-	ICE_AVF_FLOW_FIELD_IPV4_UDP,
-	ICE_AVF_FLOW_FIELD_IPV4_TCP_SYN_NO_ACK,
-	ICE_AVF_FLOW_FIELD_IPV4_TCP,
-	ICE_AVF_FLOW_FIELD_IPV4_SCTP,
-	ICE_AVF_FLOW_FIELD_IPV4_OTHER,
-	ICE_AVF_FLOW_FIELD_FRAG_IPV4,
-	/* Values 37-38 are reserved */
-	ICE_AVF_FLOW_FIELD_UNICAST_IPV6_UDP	= 39,
-	ICE_AVF_FLOW_FIELD_MULTICAST_IPV6_UDP,
-	ICE_AVF_FLOW_FIELD_IPV6_UDP,
-	ICE_AVF_FLOW_FIELD_IPV6_TCP_SYN_NO_ACK,
-	ICE_AVF_FLOW_FIELD_IPV6_TCP,
-	ICE_AVF_FLOW_FIELD_IPV6_SCTP,
-	ICE_AVF_FLOW_FIELD_IPV6_OTHER,
-	ICE_AVF_FLOW_FIELD_FRAG_IPV6,
-	ICE_AVF_FLOW_FIELD_RSVD47,
-	ICE_AVF_FLOW_FIELD_FCOE_OX,
-	ICE_AVF_FLOW_FIELD_FCOE_RX,
-	ICE_AVF_FLOW_FIELD_FCOE_OTHER,
-	/* Values 51-62 are reserved */
-	ICE_AVF_FLOW_FIELD_L2_PAYLOAD		= 63,
-	ICE_AVF_FLOW_FIELD_MAX
-};
-
 /* Supported RSS offloads  This macro is defined to support
- * VIRTCHNL_OP_GET_RSS_HENA_CAPS ops. PF driver sends the RSS hardware
+ * VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS ops. PF driver sends the RSS hardware
  * capabilities to the caller of this ops.
  */
-#define ICE_DEFAULT_RSS_HENA ( \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_UDP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_SCTP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_TCP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_OTHER) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_FRAG_IPV4) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_UDP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_TCP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_SCTP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_OTHER) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_FRAG_IPV6) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_TCP_SYN_NO_ACK) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV4_UDP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV4_UDP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_TCP_SYN_NO_ACK) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV6_UDP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV6_UDP))
+#define ICE_DEFAULT_RSS_HASHCFG ( \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV4) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV6) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
 enum ice_rss_cfg_hdr_type {
 	ICE_RSS_OUTER_HEADERS, /* take outer headers as inputset. */
@@ -324,6 +370,10 @@ enum ice_rss_cfg_hdr_type {
 	/* take inner headers as inputset for packet with outer ipv6. */
 	ICE_RSS_INNER_HEADERS_W_OUTER_IPV6,
 	/* take outer headers first then inner headers as inputset */
+	/* take inner as inputset for GTPoGRE with outer IPv4 + GRE. */
+	ICE_RSS_INNER_HEADERS_W_OUTER_IPV4_GRE,
+	/* take inner as inputset for GTPoGRE with outer IPv6 + GRE. */
+	ICE_RSS_INNER_HEADERS_W_OUTER_IPV6_GRE,
 	ICE_RSS_ANY_HEADERS
 };
 
@@ -434,6 +484,12 @@ struct ice_flow_prof {
 	bool symm; /* Symmetric Hash for RSS */
 };
 
+struct ice_rss_raw_cfg {
+	struct ice_parser_profile prof;
+	bool raw_ena;
+	bool symm;
+};
+
 struct ice_rss_cfg {
 	struct list_head l_entry;
 	/* bitmap of VSIs added to the RSS entry */
@@ -472,4 +528,6 @@ int ice_add_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi,
 int ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle,
 		    const struct ice_rss_hash_cfg *cfg);
 u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs, bool *symm);
+void ice_rss_update_raw_symm(struct ice_hw *hw,
+			     struct ice_rss_raw_cfg *cfg, u64 id);
 #endif /* _ICE_FLOW_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c
index 2702a0da5c3e..973a13d3d92a 100644
--- a/drivers/net/ethernet/intel/ice/ice_fw_update.c
+++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c
@@ -6,6 +6,7 @@
 #include <linux/crc32.h>
 #include <linux/pldmfw.h>
 #include "ice.h"
+#include "ice_lib.h"
 #include "ice_fw_update.h"
 
 struct ice_fwu_priv {
@@ -67,7 +68,7 @@ ice_send_package_data(struct pldmfw *context, const u8 *data, u16 length)
 
 	if (status) {
 		dev_err(dev, "Failed to send record package data to firmware, err %d aq_err %s\n",
-			status, ice_aq_str(hw->adminq.sq_last_status));
+			status, libie_aq_str(hw->adminq.sq_last_status));
 		NL_SET_ERR_MSG_MOD(extack, "Failed to record package data to firmware");
 		return -EIO;
 	}
@@ -125,6 +126,10 @@ ice_check_component_response(struct ice_pf *pf, u16 id, u8 response, u8 code,
 	case ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED:
 		dev_info(dev, "firmware has rejected updating %s\n", component);
 		break;
+	case ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK:
+		if (ice_is_recovery_mode(&pf->hw))
+			return 0;
+		break;
 	}
 
 	switch (code) {
@@ -252,7 +257,7 @@ ice_send_component_table(struct pldmfw *context, struct pldmfw_component *compon
 
 	if (status) {
 		dev_err(dev, "Failed to transfer component table to firmware, err %d aq_err %s\n",
-			status, ice_aq_str(hw->adminq.sq_last_status));
+			status, libie_aq_str(hw->adminq.sq_last_status));
 		NL_SET_ERR_MSG_MOD(extack, "Failed to transfer component table to firmware");
 		return -EIO;
 	}
@@ -294,7 +299,8 @@ int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_aq_task task = {};
 	struct ice_hw *hw = &pf->hw;
-	struct ice_aq_desc *desc;
+	struct libie_aq_desc *desc;
+	struct ice_aqc_nvm *cmd;
 	u32 completion_offset;
 	int err;
 
@@ -308,7 +314,7 @@ int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 	if (err) {
 		dev_err(dev, "Failed to flash module 0x%02x with block of size %u at offset %u, err %d aq_err %s\n",
 			module, block_size, offset, err,
-			ice_aq_str(hw->adminq.sq_last_status));
+			libie_aq_str(hw->adminq.sq_last_status));
 		NL_SET_ERR_MSG_MOD(extack, "Failed to program flash module");
 		return -EIO;
 	}
@@ -328,11 +334,12 @@ int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 	}
 
 	desc = &task.event.desc;
-	completion_module = le16_to_cpu(desc->params.nvm.module_typeid);
+	cmd = libie_aq_raw(desc);
+	completion_module = le16_to_cpu(cmd->module_typeid);
 	completion_retval = le16_to_cpu(desc->retval);
 
-	completion_offset = le16_to_cpu(desc->params.nvm.offset_low);
-	completion_offset |= desc->params.nvm.offset_high << 16;
+	completion_offset = le16_to_cpu(cmd->offset_low);
+	completion_offset |= cmd->offset_high << 16;
 
 	if (completion_module != module) {
 		dev_err(dev, "Unexpected module_typeid in write completion: got 0x%x, expected 0x%x\n",
@@ -351,7 +358,7 @@ int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 	if (completion_retval) {
 		dev_err(dev, "Firmware failed to flash module 0x%02x with block of size %u at offset %u, err %s\n",
 			module, block_size, offset,
-			ice_aq_str((enum ice_aq_err)completion_retval));
+			libie_aq_str((enum libie_aq_err)completion_retval));
 		NL_SET_ERR_MSG_MOD(extack, "Firmware failed to program flash module");
 		return -EIO;
 	}
@@ -364,7 +371,7 @@ int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 	 */
 	if (reset_level && last_cmd && module == ICE_SR_1ST_NVM_BANK_PTR) {
 		if (hw->dev_caps.common_cap.pcie_reset_avoidance) {
-			*reset_level = desc->params.nvm.cmd_flags &
+			*reset_level = cmd->cmd_flags &
 				       ICE_AQC_NVM_RESET_LVL_M;
 			dev_dbg(dev, "Firmware reported required reset level as %u\n",
 				*reset_level);
@@ -482,7 +489,8 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component,
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_aq_task task = {};
 	struct ice_hw *hw = &pf->hw;
-	struct ice_aq_desc *desc;
+	struct libie_aq_desc *desc;
+	struct ice_aqc_nvm *cmd;
 	struct devlink *devlink;
 	int err;
 
@@ -498,7 +506,7 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component,
 	if (err) {
 		dev_err(dev, "Failed to erase %s (module 0x%02x), err %d aq_err %s\n",
 			component, module, err,
-			ice_aq_str(hw->adminq.sq_last_status));
+			libie_aq_str(hw->adminq.sq_last_status));
 		NL_SET_ERR_MSG_MOD(extack, "Failed to erase flash module");
 		err = -EIO;
 		goto out_notify_devlink;
@@ -513,7 +521,8 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component,
 	}
 
 	desc = &task.event.desc;
-	completion_module = le16_to_cpu(desc->params.nvm.module_typeid);
+	cmd = libie_aq_raw(desc);
+	completion_module = le16_to_cpu(cmd->module_typeid);
 	completion_retval = le16_to_cpu(desc->retval);
 
 	if (completion_module != module) {
@@ -525,9 +534,9 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component,
 	}
 
 	if (completion_retval) {
-		dev_err(dev, "Firmware failed to erase %s (module 0x02%x), aq_err %s\n",
+		dev_err(dev, "Firmware failed to erase %s (module 0x%02x), aq_err %s\n",
 			component, module,
-			ice_aq_str((enum ice_aq_err)completion_retval));
+			libie_aq_str((enum libie_aq_err)completion_retval));
 		NL_SET_ERR_MSG_MOD(extack, "Firmware failed to erase flash");
 		err = -EIO;
 		goto out_notify_devlink;
@@ -574,7 +583,7 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags,
 	err = ice_nvm_write_activate(hw, activate_flags, &response_flags);
 	if (err) {
 		dev_err(dev, "Failed to switch active flash banks, err %d aq_err %s\n",
-			err, ice_aq_str(hw->adminq.sq_last_status));
+			err, libie_aq_str(hw->adminq.sq_last_status));
 		NL_SET_ERR_MSG_MOD(extack, "Failed to switch active flash banks");
 		return -EIO;
 	}
@@ -606,7 +615,7 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags,
 	completion_retval = le16_to_cpu(task.event.desc.retval);
 	if (completion_retval) {
 		dev_err(dev, "Firmware failed to switch active flash banks aq_err %s\n",
-			ice_aq_str((enum ice_aq_err)completion_retval));
+			libie_aq_str((enum libie_aq_err)completion_retval));
 		NL_SET_ERR_MSG_MOD(extack, "Firmware failed to switch active flash banks");
 		return -EIO;
 	}
@@ -944,7 +953,7 @@ ice_cancel_pending_update(struct ice_pf *pf, const char *component,
 	err = ice_acquire_nvm(hw, ICE_RES_WRITE);
 	if (err) {
 		dev_err(dev, "Failed to acquire device flash lock, err %d aq_err %s\n",
-			err, ice_aq_str(hw->adminq.sq_last_status));
+			err, libie_aq_str(hw->adminq.sq_last_status));
 		NL_SET_ERR_MSG_MOD(extack, "Failed to acquire device flash lock");
 		return err;
 	}
@@ -1004,13 +1013,20 @@ int ice_devlink_flash_update(struct devlink *devlink,
 		return -EOPNOTSUPP;
 	}
 
-	if (!hw->dev_caps.common_cap.nvm_unified_update) {
+	if (!hw->dev_caps.common_cap.nvm_unified_update && !ice_is_recovery_mode(hw)) {
 		NL_SET_ERR_MSG_MOD(extack, "Current firmware does not support unified update");
 		return -EOPNOTSUPP;
 	}
 
 	memset(&priv, 0, sizeof(priv));
 
+	if (params->component && strcmp(params->component, "fw.mgmt") == 0) {
+		priv.context.mode = PLDMFW_UPDATE_MODE_SINGLE_COMPONENT;
+		priv.context.component_identifier = NVM_COMP_ID_NVM;
+	} else if (params->component) {
+		return -EOPNOTSUPP;
+	}
+
 	/* the E822 device needs a slightly different ops */
 	if (hw->mac_type == ICE_MAC_GENERIC)
 		priv.context.ops = &ice_fwu_ops_e822;
@@ -1030,7 +1046,7 @@ int ice_devlink_flash_update(struct devlink *devlink,
 	err = ice_acquire_nvm(hw, ICE_RES_WRITE);
 	if (err) {
 		dev_err(dev, "Failed to acquire device flash lock, err %d aq_err %s\n",
-			err, ice_aq_str(hw->adminq.sq_last_status));
+			err, libie_aq_str(hw->adminq.sq_last_status));
 		NL_SET_ERR_MSG_MOD(extack, "Failed to acquire device flash lock");
 		return err;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_fwlog.c b/drivers/net/ethernet/intel/ice/ice_fwlog.c
deleted file mode 100644
index 4fd15387a7e5..000000000000
--- a/drivers/net/ethernet/intel/ice/ice_fwlog.c
+++ /dev/null
@@ -1,472 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2022, Intel Corporation. */
-
-#include <linux/vmalloc.h>
-#include "ice.h"
-#include "ice_common.h"
-#include "ice_fwlog.h"
-
-bool ice_fwlog_ring_full(struct ice_fwlog_ring *rings)
-{
-	u16 head, tail;
-
-	head = rings->head;
-	tail = rings->tail;
-
-	if (head < tail && (tail - head == (rings->size - 1)))
-		return true;
-	else if (head > tail && (tail == (head - 1)))
-		return true;
-
-	return false;
-}
-
-bool ice_fwlog_ring_empty(struct ice_fwlog_ring *rings)
-{
-	return rings->head == rings->tail;
-}
-
-void ice_fwlog_ring_increment(u16 *item, u16 size)
-{
-	*item = (*item + 1) & (size - 1);
-}
-
-static int ice_fwlog_alloc_ring_buffs(struct ice_fwlog_ring *rings)
-{
-	int i, nr_bytes;
-	u8 *mem;
-
-	nr_bytes = rings->size * ICE_AQ_MAX_BUF_LEN;
-	mem = vzalloc(nr_bytes);
-	if (!mem)
-		return -ENOMEM;
-
-	for (i = 0; i < rings->size; i++) {
-		struct ice_fwlog_data *ring = &rings->rings[i];
-
-		ring->data_size = ICE_AQ_MAX_BUF_LEN;
-		ring->data = mem;
-		mem += ICE_AQ_MAX_BUF_LEN;
-	}
-
-	return 0;
-}
-
-static void ice_fwlog_free_ring_buffs(struct ice_fwlog_ring *rings)
-{
-	int i;
-
-	for (i = 0; i < rings->size; i++) {
-		struct ice_fwlog_data *ring = &rings->rings[i];
-
-		/* the first ring is the base memory for the whole range so
-		 * free it
-		 */
-		if (!i)
-			vfree(ring->data);
-
-		ring->data = NULL;
-		ring->data_size = 0;
-	}
-}
-
-#define ICE_FWLOG_INDEX_TO_BYTES(n) ((128 * 1024) << (n))
-/**
- * ice_fwlog_realloc_rings - reallocate the FW log rings
- * @hw: pointer to the HW structure
- * @index: the new index to use to allocate memory for the log data
- *
- */
-void ice_fwlog_realloc_rings(struct ice_hw *hw, int index)
-{
-	struct ice_fwlog_ring ring;
-	int status, ring_size;
-
-	/* convert the number of bytes into a number of 4K buffers. externally
-	 * the driver presents the interface to the FW log data as a number of
-	 * bytes because that's easy for users to understand. internally the
-	 * driver uses a ring of buffers because the driver doesn't know where
-	 * the beginning and end of any line of log data is so the driver has
-	 * to overwrite data as complete blocks. when the data is returned to
-	 * the user the driver knows that the data is correct and the FW log
-	 * can be correctly parsed by the tools
-	 */
-	ring_size = ICE_FWLOG_INDEX_TO_BYTES(index) / ICE_AQ_MAX_BUF_LEN;
-	if (ring_size == hw->fwlog_ring.size)
-		return;
-
-	/* allocate space for the new rings and buffers then release the
-	 * old rings and buffers. that way if we don't have enough
-	 * memory then we at least have what we had before
-	 */
-	ring.rings = kcalloc(ring_size, sizeof(*ring.rings), GFP_KERNEL);
-	if (!ring.rings)
-		return;
-
-	ring.size = ring_size;
-
-	status = ice_fwlog_alloc_ring_buffs(&ring);
-	if (status) {
-		dev_warn(ice_hw_to_dev(hw), "Unable to allocate memory for FW log ring data buffers\n");
-		ice_fwlog_free_ring_buffs(&ring);
-		kfree(ring.rings);
-		return;
-	}
-
-	ice_fwlog_free_ring_buffs(&hw->fwlog_ring);
-	kfree(hw->fwlog_ring.rings);
-
-	hw->fwlog_ring.rings = ring.rings;
-	hw->fwlog_ring.size = ring.size;
-	hw->fwlog_ring.index = index;
-	hw->fwlog_ring.head = 0;
-	hw->fwlog_ring.tail = 0;
-}
-
-/**
- * ice_fwlog_init - Initialize FW logging configuration
- * @hw: pointer to the HW structure
- *
- * This function should be called on driver initialization during
- * ice_init_hw().
- */
-int ice_fwlog_init(struct ice_hw *hw)
-{
-	/* only support fw log commands on PF 0 */
-	if (hw->bus.func)
-		return -EINVAL;
-
-	ice_fwlog_set_supported(hw);
-
-	if (ice_fwlog_supported(hw)) {
-		int status;
-
-		/* read the current config from the FW and store it */
-		status = ice_fwlog_get(hw, &hw->fwlog_cfg);
-		if (status)
-			return status;
-
-		hw->fwlog_ring.rings = kcalloc(ICE_FWLOG_RING_SIZE_DFLT,
-					       sizeof(*hw->fwlog_ring.rings),
-					       GFP_KERNEL);
-		if (!hw->fwlog_ring.rings) {
-			dev_warn(ice_hw_to_dev(hw), "Unable to allocate memory for FW log rings\n");
-			return -ENOMEM;
-		}
-
-		hw->fwlog_ring.size = ICE_FWLOG_RING_SIZE_DFLT;
-		hw->fwlog_ring.index = ICE_FWLOG_RING_SIZE_INDEX_DFLT;
-
-		status = ice_fwlog_alloc_ring_buffs(&hw->fwlog_ring);
-		if (status) {
-			dev_warn(ice_hw_to_dev(hw), "Unable to allocate memory for FW log ring data buffers\n");
-			ice_fwlog_free_ring_buffs(&hw->fwlog_ring);
-			kfree(hw->fwlog_ring.rings);
-			return status;
-		}
-
-		ice_debugfs_fwlog_init(hw->back);
-	} else {
-		dev_warn(ice_hw_to_dev(hw), "FW logging is not supported in this NVM image. Please update the NVM to get FW log support\n");
-	}
-
-	return 0;
-}
-
-/**
- * ice_fwlog_deinit - unroll FW logging configuration
- * @hw: pointer to the HW structure
- *
- * This function should be called in ice_deinit_hw().
- */
-void ice_fwlog_deinit(struct ice_hw *hw)
-{
-	struct ice_pf *pf = hw->back;
-	int status;
-
-	/* only support fw log commands on PF 0 */
-	if (hw->bus.func)
-		return;
-
-	ice_debugfs_pf_deinit(hw->back);
-
-	/* make sure FW logging is disabled to not put the FW in a weird state
-	 * for the next driver load
-	 */
-	hw->fwlog_cfg.options &= ~ICE_FWLOG_OPTION_ARQ_ENA;
-	status = ice_fwlog_set(hw, &hw->fwlog_cfg);
-	if (status)
-		dev_warn(ice_hw_to_dev(hw), "Unable to turn off FW logging, status: %d\n",
-			 status);
-
-	kfree(pf->ice_debugfs_pf_fwlog_modules);
-
-	pf->ice_debugfs_pf_fwlog_modules = NULL;
-
-	status = ice_fwlog_unregister(hw);
-	if (status)
-		dev_warn(ice_hw_to_dev(hw), "Unable to unregister FW logging, status: %d\n",
-			 status);
-
-	if (hw->fwlog_ring.rings) {
-		ice_fwlog_free_ring_buffs(&hw->fwlog_ring);
-		kfree(hw->fwlog_ring.rings);
-	}
-}
-
-/**
- * ice_fwlog_supported - Cached for whether FW supports FW logging or not
- * @hw: pointer to the HW structure
- *
- * This will always return false if called before ice_init_hw(), so it must be
- * called after ice_init_hw().
- */
-bool ice_fwlog_supported(struct ice_hw *hw)
-{
-	return hw->fwlog_supported;
-}
-
-/**
- * ice_aq_fwlog_set - Set FW logging configuration AQ command (0xFF30)
- * @hw: pointer to the HW structure
- * @entries: entries to configure
- * @num_entries: number of @entries
- * @options: options from ice_fwlog_cfg->options structure
- * @log_resolution: logging resolution
- */
-static int
-ice_aq_fwlog_set(struct ice_hw *hw, struct ice_fwlog_module_entry *entries,
-		 u16 num_entries, u16 options, u16 log_resolution)
-{
-	struct ice_aqc_fw_log_cfg_resp *fw_modules;
-	struct ice_aqc_fw_log *cmd;
-	struct ice_aq_desc desc;
-	int status;
-	int i;
-
-	fw_modules = kcalloc(num_entries, sizeof(*fw_modules), GFP_KERNEL);
-	if (!fw_modules)
-		return -ENOMEM;
-
-	for (i = 0; i < num_entries; i++) {
-		fw_modules[i].module_identifier =
-			cpu_to_le16(entries[i].module_id);
-		fw_modules[i].log_level = entries[i].log_level;
-	}
-
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logs_config);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-
-	cmd = &desc.params.fw_log;
-
-	cmd->cmd_flags = ICE_AQC_FW_LOG_CONF_SET_VALID;
-	cmd->ops.cfg.log_resolution = cpu_to_le16(log_resolution);
-	cmd->ops.cfg.mdl_cnt = cpu_to_le16(num_entries);
-
-	if (options & ICE_FWLOG_OPTION_ARQ_ENA)
-		cmd->cmd_flags |= ICE_AQC_FW_LOG_CONF_AQ_EN;
-	if (options & ICE_FWLOG_OPTION_UART_ENA)
-		cmd->cmd_flags |= ICE_AQC_FW_LOG_CONF_UART_EN;
-
-	status = ice_aq_send_cmd(hw, &desc, fw_modules,
-				 sizeof(*fw_modules) * num_entries,
-				 NULL);
-
-	kfree(fw_modules);
-
-	return status;
-}
-
-/**
- * ice_fwlog_set - Set the firmware logging settings
- * @hw: pointer to the HW structure
- * @cfg: config used to set firmware logging
- *
- * This function should be called whenever the driver needs to set the firmware
- * logging configuration. It can be called on initialization, reset, or during
- * runtime.
- *
- * If the PF wishes to receive FW logging then it must register via
- * ice_fwlog_register. Note, that ice_fwlog_register does not need to be called
- * for init.
- */
-int ice_fwlog_set(struct ice_hw *hw, struct ice_fwlog_cfg *cfg)
-{
-	if (!ice_fwlog_supported(hw))
-		return -EOPNOTSUPP;
-
-	return ice_aq_fwlog_set(hw, cfg->module_entries,
-				ICE_AQC_FW_LOG_ID_MAX, cfg->options,
-				cfg->log_resolution);
-}
-
-/**
- * ice_aq_fwlog_get - Get the current firmware logging configuration (0xFF32)
- * @hw: pointer to the HW structure
- * @cfg: firmware logging configuration to populate
- */
-static int ice_aq_fwlog_get(struct ice_hw *hw, struct ice_fwlog_cfg *cfg)
-{
-	struct ice_aqc_fw_log_cfg_resp *fw_modules;
-	struct ice_aqc_fw_log *cmd;
-	struct ice_aq_desc desc;
-	u16 module_id_cnt;
-	int status;
-	void *buf;
-	int i;
-
-	memset(cfg, 0, sizeof(*cfg));
-
-	buf = kzalloc(ICE_AQ_MAX_BUF_LEN, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logs_query);
-	cmd = &desc.params.fw_log;
-
-	cmd->cmd_flags = ICE_AQC_FW_LOG_AQ_QUERY;
-
-	status = ice_aq_send_cmd(hw, &desc, buf, ICE_AQ_MAX_BUF_LEN, NULL);
-	if (status) {
-		ice_debug(hw, ICE_DBG_FW_LOG, "Failed to get FW log configuration\n");
-		goto status_out;
-	}
-
-	module_id_cnt = le16_to_cpu(cmd->ops.cfg.mdl_cnt);
-	if (module_id_cnt < ICE_AQC_FW_LOG_ID_MAX) {
-		ice_debug(hw, ICE_DBG_FW_LOG, "FW returned less than the expected number of FW log module IDs\n");
-	} else if (module_id_cnt > ICE_AQC_FW_LOG_ID_MAX) {
-		ice_debug(hw, ICE_DBG_FW_LOG, "FW returned more than expected number of FW log module IDs, setting module_id_cnt to software expected max %u\n",
-			  ICE_AQC_FW_LOG_ID_MAX);
-		module_id_cnt = ICE_AQC_FW_LOG_ID_MAX;
-	}
-
-	cfg->log_resolution = le16_to_cpu(cmd->ops.cfg.log_resolution);
-	if (cmd->cmd_flags & ICE_AQC_FW_LOG_CONF_AQ_EN)
-		cfg->options |= ICE_FWLOG_OPTION_ARQ_ENA;
-	if (cmd->cmd_flags & ICE_AQC_FW_LOG_CONF_UART_EN)
-		cfg->options |= ICE_FWLOG_OPTION_UART_ENA;
-	if (cmd->cmd_flags & ICE_AQC_FW_LOG_QUERY_REGISTERED)
-		cfg->options |= ICE_FWLOG_OPTION_IS_REGISTERED;
-
-	fw_modules = (struct ice_aqc_fw_log_cfg_resp *)buf;
-
-	for (i = 0; i < module_id_cnt; i++) {
-		struct ice_aqc_fw_log_cfg_resp *fw_module = &fw_modules[i];
-
-		cfg->module_entries[i].module_id =
-			le16_to_cpu(fw_module->module_identifier);
-		cfg->module_entries[i].log_level = fw_module->log_level;
-	}
-
-status_out:
-	kfree(buf);
-	return status;
-}
-
-/**
- * ice_fwlog_get - Get the firmware logging settings
- * @hw: pointer to the HW structure
- * @cfg: config to populate based on current firmware logging settings
- */
-int ice_fwlog_get(struct ice_hw *hw, struct ice_fwlog_cfg *cfg)
-{
-	if (!ice_fwlog_supported(hw))
-		return -EOPNOTSUPP;
-
-	return ice_aq_fwlog_get(hw, cfg);
-}
-
-/**
- * ice_aq_fwlog_register - Register PF for firmware logging events (0xFF31)
- * @hw: pointer to the HW structure
- * @reg: true to register and false to unregister
- */
-static int ice_aq_fwlog_register(struct ice_hw *hw, bool reg)
-{
-	struct ice_aq_desc desc;
-
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logs_register);
-
-	if (reg)
-		desc.params.fw_log.cmd_flags = ICE_AQC_FW_LOG_AQ_REGISTER;
-
-	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
-}
-
-/**
- * ice_fwlog_register - Register the PF for firmware logging
- * @hw: pointer to the HW structure
- *
- * After this call the PF will start to receive firmware logging based on the
- * configuration set in ice_fwlog_set.
- */
-int ice_fwlog_register(struct ice_hw *hw)
-{
-	int status;
-
-	if (!ice_fwlog_supported(hw))
-		return -EOPNOTSUPP;
-
-	status = ice_aq_fwlog_register(hw, true);
-	if (status)
-		ice_debug(hw, ICE_DBG_FW_LOG, "Failed to register for firmware logging events over ARQ\n");
-	else
-		hw->fwlog_cfg.options |= ICE_FWLOG_OPTION_IS_REGISTERED;
-
-	return status;
-}
-
-/**
- * ice_fwlog_unregister - Unregister the PF from firmware logging
- * @hw: pointer to the HW structure
- */
-int ice_fwlog_unregister(struct ice_hw *hw)
-{
-	int status;
-
-	if (!ice_fwlog_supported(hw))
-		return -EOPNOTSUPP;
-
-	status = ice_aq_fwlog_register(hw, false);
-	if (status)
-		ice_debug(hw, ICE_DBG_FW_LOG, "Failed to unregister from firmware logging events over ARQ\n");
-	else
-		hw->fwlog_cfg.options &= ~ICE_FWLOG_OPTION_IS_REGISTERED;
-
-	return status;
-}
-
-/**
- * ice_fwlog_set_supported - Set if FW logging is supported by FW
- * @hw: pointer to the HW struct
- *
- * If FW returns success to the ice_aq_fwlog_get call then it supports FW
- * logging, else it doesn't. Set the fwlog_supported flag accordingly.
- *
- * This function is only meant to be called during driver init to determine if
- * the FW support FW logging.
- */
-void ice_fwlog_set_supported(struct ice_hw *hw)
-{
-	struct ice_fwlog_cfg *cfg;
-	int status;
-
-	hw->fwlog_supported = false;
-
-	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
-	if (!cfg)
-		return;
-
-	/* don't call ice_fwlog_get() because that would check to see if FW
-	 * logging is supported which is what the driver is determining now
-	 */
-	status = ice_aq_fwlog_get(hw, cfg);
-	if (status)
-		ice_debug(hw, ICE_DBG_FW_LOG, "ice_aq_fwlog_get failed, FW logging is not supported on this version of FW, status %d\n",
-			  status);
-	else
-		hw->fwlog_supported = true;
-
-	kfree(cfg);
-}
diff --git a/drivers/net/ethernet/intel/ice/ice_fwlog.h b/drivers/net/ethernet/intel/ice/ice_fwlog.h
deleted file mode 100644
index 287e71fa4b86..000000000000
--- a/drivers/net/ethernet/intel/ice/ice_fwlog.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2022, Intel Corporation. */
-
-#ifndef _ICE_FWLOG_H_
-#define _ICE_FWLOG_H_
-#include "ice_adminq_cmd.h"
-
-struct ice_hw;
-
-/* Only a single log level should be set and all log levels under the set value
- * are enabled, e.g. if log level is set to ICE_FW_LOG_LEVEL_VERBOSE, then all
- * other log levels are included (except ICE_FW_LOG_LEVEL_NONE)
- */
-enum ice_fwlog_level {
-	ICE_FWLOG_LEVEL_NONE = 0,
-	ICE_FWLOG_LEVEL_ERROR = 1,
-	ICE_FWLOG_LEVEL_WARNING = 2,
-	ICE_FWLOG_LEVEL_NORMAL = 3,
-	ICE_FWLOG_LEVEL_VERBOSE = 4,
-	ICE_FWLOG_LEVEL_INVALID, /* all values >= this entry are invalid */
-};
-
-struct ice_fwlog_module_entry {
-	/* module ID for the corresponding firmware logging event */
-	u16 module_id;
-	/* verbosity level for the module_id */
-	u8 log_level;
-};
-
-struct ice_fwlog_cfg {
-	/* list of modules for configuring log level */
-	struct ice_fwlog_module_entry module_entries[ICE_AQC_FW_LOG_ID_MAX];
-	/* options used to configure firmware logging */
-	u16 options;
-#define ICE_FWLOG_OPTION_ARQ_ENA		BIT(0)
-#define ICE_FWLOG_OPTION_UART_ENA		BIT(1)
-	/* set before calling ice_fwlog_init() so the PF registers for firmware
-	 * logging on initialization
-	 */
-#define ICE_FWLOG_OPTION_REGISTER_ON_INIT	BIT(2)
-	/* set in the ice_fwlog_get() response if the PF is registered for FW
-	 * logging events over ARQ
-	 */
-#define ICE_FWLOG_OPTION_IS_REGISTERED		BIT(3)
-
-	/* minimum number of log events sent per Admin Receive Queue event */
-	u16 log_resolution;
-};
-
-struct ice_fwlog_data {
-	u16 data_size;
-	u8 *data;
-};
-
-struct ice_fwlog_ring {
-	struct ice_fwlog_data *rings;
-	u16 index;
-	u16 size;
-	u16 head;
-	u16 tail;
-};
-
-#define ICE_FWLOG_RING_SIZE_INDEX_DFLT 3
-#define ICE_FWLOG_RING_SIZE_DFLT 256
-#define ICE_FWLOG_RING_SIZE_MAX 512
-
-bool ice_fwlog_ring_full(struct ice_fwlog_ring *rings);
-bool ice_fwlog_ring_empty(struct ice_fwlog_ring *rings);
-void ice_fwlog_ring_increment(u16 *item, u16 size);
-void ice_fwlog_set_supported(struct ice_hw *hw);
-bool ice_fwlog_supported(struct ice_hw *hw);
-int ice_fwlog_init(struct ice_hw *hw);
-void ice_fwlog_deinit(struct ice_hw *hw);
-int ice_fwlog_set(struct ice_hw *hw, struct ice_fwlog_cfg *cfg);
-int ice_fwlog_get(struct ice_hw *hw, struct ice_fwlog_cfg *cfg);
-int ice_fwlog_register(struct ice_hw *hw);
-int ice_fwlog_unregister(struct ice_hw *hw);
-void ice_fwlog_realloc_rings(struct ice_hw *hw, int index);
-#endif /* _ICE_FWLOG_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c
index f02e8ca55375..6b26290452d4 100644
--- a/drivers/net/ethernet/intel/ice/ice_gnss.c
+++ b/drivers/net/ethernet/intel/ice/ice_gnss.c
@@ -182,7 +182,7 @@ static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf)
 	pf->gnss_serial = gnss;
 
 	kthread_init_delayed_work(&gnss->read_work, ice_gnss_read);
-	kworker = kthread_create_worker(0, "ice-gnss-%s", dev_name(dev));
+	kworker = kthread_run_worker(0, "ice-gnss-%s", dev_name(dev));
 	if (IS_ERR(kworker)) {
 		kfree(gnss);
 		return NULL;
@@ -381,32 +381,23 @@ void ice_gnss_exit(struct ice_pf *pf)
 }
 
 /**
- * ice_gnss_is_gps_present - Check if GPS HW is present
+ * ice_gnss_is_module_present - Check if GNSS HW is present
  * @hw: pointer to HW struct
+ *
+ * Return: true when GNSS is present, false otherwise.
  */
-bool ice_gnss_is_gps_present(struct ice_hw *hw)
+bool ice_gnss_is_module_present(struct ice_hw *hw)
 {
-	if (!hw->func_caps.ts_func_info.src_tmr_owned)
-		return false;
+	int err;
+	u8 data;
 
-	if (!ice_is_gps_in_netlist(hw))
+	if (!hw->func_caps.ts_func_info.src_tmr_owned ||
+	    !ice_is_gps_in_netlist(hw))
 		return false;
 
-#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
-	if (ice_is_e810t(hw)) {
-		int err;
-		u8 data;
-
-		err = ice_read_pca9575_reg(hw, ICE_PCA9575_P0_IN, &data);
-		if (err || !!(data & ICE_P0_GNSS_PRSNT_N))
-			return false;
-	} else {
-		return false;
-	}
-#else
-	if (!ice_is_e810t(hw))
+	err = ice_read_pca9575_reg(hw, ICE_PCA9575_P0_IN, &data);
+	if (err || !!(data & ICE_P0_GNSS_PRSNT_N))
 		return false;
-#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
 
 	return true;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.h b/drivers/net/ethernet/intel/ice/ice_gnss.h
index 75e567ad7059..15daf603ed7b 100644
--- a/drivers/net/ethernet/intel/ice/ice_gnss.h
+++ b/drivers/net/ethernet/intel/ice/ice_gnss.h
@@ -37,11 +37,11 @@ struct gnss_serial {
 #if IS_ENABLED(CONFIG_GNSS)
 void ice_gnss_init(struct ice_pf *pf);
 void ice_gnss_exit(struct ice_pf *pf);
-bool ice_gnss_is_gps_present(struct ice_hw *hw);
+bool ice_gnss_is_module_present(struct ice_hw *hw);
 #else
 static inline void ice_gnss_init(struct ice_pf *pf) { }
 static inline void ice_gnss_exit(struct ice_pf *pf) { }
-static inline bool ice_gnss_is_gps_present(struct ice_hw *hw)
+static inline bool ice_gnss_is_module_present(struct ice_hw *hw)
 {
 	return false;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index dc88aea9f473..082ad33c53dc 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -16,8 +16,10 @@
 #define GLCOMM_QUANTA_PROF_MAX_DESC_M		ICE_M(0x3F, 24)
 #define QTX_COMM_DBELL(_DBQM)			(0x002C0000 + ((_DBQM) * 4))
 #define QTX_COMM_HEAD(_DBQM)			(0x000E0000 + ((_DBQM) * 4))
+#define QTX_COMM_HEAD_MAX_INDEX			16383
 #define QTX_COMM_HEAD_HEAD_S			0
 #define QTX_COMM_HEAD_HEAD_M			ICE_M(0x1FFF, 0)
+#define E830_GLQTX_TXTIME_DBELL_LSB(_DBQM)	(0x002E0000 + ((_DBQM) * 8))
 #define PF_FW_ARQBAH				0x00080180
 #define PF_FW_ARQBAL				0x00080080
 #define PF_FW_ARQH				0x00080380
@@ -272,6 +274,8 @@
 #define VPINT_ALLOC_PCI_VALID_M			BIT(31)
 #define VPINT_MBX_CTL(_VSI)			(0x0016A000 + ((_VSI) * 4))
 #define VPINT_MBX_CTL_CAUSE_ENA_M		BIT(30)
+#define PFLAN_TX_QALLOC(_PF)			(0x001D2580 + ((_PF) * 4))
+#define PFLAN_TX_QALLOC_FIRSTQ_M		GENMASK(13, 0)
 #define GLLAN_RCTL_0				0x002941F8
 #define QRX_CONTEXT(_i, _QRX)			(0x00280000 + ((_i) * 8192 + (_QRX) * 4))
 #define QRX_CTRL(_QRX)				(0x00120000 + ((_QRX) * 4))
@@ -376,6 +380,15 @@
 #define GLNVM_ULD_POR_DONE_1_M			BIT(8)
 #define GLNVM_ULD_PCIER_DONE_2_M		BIT(9)
 #define GLNVM_ULD_PE_DONE_M			BIT(10)
+#define GLCOMM_QTX_CNTX_CTL			0x002D2DC8
+#define GLCOMM_QTX_CNTX_CTL_QUEUE_ID_M		GENMASK(13, 0)
+#define GLCOMM_QTX_CNTX_CTL_CMD_M		GENMASK(18, 16)
+#define GLCOMM_QTX_CNTX_CTL_CMD_READ		0
+#define GLCOMM_QTX_CNTX_CTL_CMD_WRITE		1
+#define GLCOMM_QTX_CNTX_CTL_CMD_RESET		3
+#define GLCOMM_QTX_CNTX_CTL_CMD_WRITE_NO_DYN	4
+#define GLCOMM_QTX_CNTX_CTL_CMD_EXEC_M		BIT(19)
+#define GLCOMM_QTX_CNTX_DATA(_i)		(0x002D2D40 + ((_i) * 4))
 #define GLPCI_CNF2				0x000BE004
 #define GLPCI_CNF2_CACHELINE_SIZE_M		BIT(1)
 #define PF_FUNC_RID				0x0009E880
@@ -541,12 +554,26 @@
 #define PFPM_WUS_MAG_M				BIT(1)
 #define PFPM_WUS_MNG_M				BIT(3)
 #define PFPM_WUS_FW_RST_WK_M			BIT(31)
+#define E830_PRTMAC_TS_TX_MEM_VALID_H		0x001E2020
+#define E830_PRTMAC_TS_TX_MEM_VALID_L		0x001E2000
 #define E830_PRTMAC_CL01_PS_QNT			0x001E32A0
 #define E830_PRTMAC_CL01_PS_QNT_CL0_M		GENMASK(15, 0)
 #define E830_PRTMAC_CL01_QNT_THR		0x001E3320
 #define E830_PRTMAC_CL01_QNT_THR_CL0_M		GENMASK(15, 0)
+#define E830_PRTTSYN_TXTIME_H(_i)		(0x001E5800 + ((_i) * 32))
+#define E830_PRTTSYN_TXTIME_L(_i)		(0x001E5000 + ((_i) * 32))
+#define E830_GLPTM_ART_CTL			0x00088B50
+#define E830_GLPTM_ART_CTL_ACTIVE_M		BIT(0)
+#define E830_GLPTM_ART_TIME_H			0x00088B54
+#define E830_GLPTM_ART_TIME_L			0x00088B58
+#define E830_GLTSYN_PTMTIME_H(_i)		(0x00088B48 + ((_i) * 4))
+#define E830_GLTSYN_PTMTIME_L(_i)		(0x00088B40 + ((_i) * 4))
+#define E830_PFPTM_SEM				0x00088B00
+#define E830_PFPTM_SEM_BUSY_M			BIT(0)
 #define VFINT_DYN_CTLN(_i)			(0x00003800 + ((_i) * 4))
 #define VFINT_DYN_CTLN_CLEARPBA_M		BIT(1)
+#define E830_GLTXTIME_FETCH_PROFILE(_i, _j)     (0x002D3500 + ((_i) * 4 + (_j) * 64))
+#define E830_GLTXTIME_FETCH_PROFILE_FETCH_TS_DESC_M ICE_M(0x1FF, 0)
 #define E830_MBX_PF_IN_FLIGHT_VF_MSGS_THRESH	0x00234000
 #define E830_MBX_VF_DEC_TRIG(_VF)		(0x00233800 + (_VF) * 4)
 #define E830_MBX_VF_IN_FLIGHT_MSGS_AT_PF_CNT(_VF)	(0x00233000 + (_VF) * 4)
diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c
index 145b27f2a4ce..420d45c2558b 100644
--- a/drivers/net/ethernet/intel/ice/ice_idc.c
+++ b/drivers/net/ethernet/intel/ice/ice_idc.c
@@ -9,22 +9,25 @@
 static DEFINE_XARRAY_ALLOC1(ice_aux_id);
 
 /**
- * ice_get_auxiliary_drv - retrieve iidc_auxiliary_drv struct
- * @pf: pointer to PF struct
+ * ice_get_auxiliary_drv - retrieve iidc_rdma_core_auxiliary_drv struct
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  *
  * This function has to be called with a device_lock on the
- * pf->adev.dev to avoid race conditions.
+ * cdev->adev.dev to avoid race conditions.
+ *
+ * Return: pointer to the matched auxiliary driver struct
  */
-static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf)
+static struct iidc_rdma_core_auxiliary_drv *
+ice_get_auxiliary_drv(struct iidc_rdma_core_dev_info *cdev)
 {
 	struct auxiliary_device *adev;
 
-	adev = pf->adev;
+	adev = cdev->adev;
 	if (!adev || !adev->dev.driver)
 		return NULL;
 
-	return container_of(adev->dev.driver, struct iidc_auxiliary_drv,
-			    adrv.driver);
+	return container_of(adev->dev.driver,
+			    struct iidc_rdma_core_auxiliary_drv, adrv.driver);
 }
 
 /**
@@ -32,44 +35,54 @@ static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf)
  * @pf: pointer to PF struct
  * @event: event struct
  */
-void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event)
+void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_rdma_event *event)
 {
-	struct iidc_auxiliary_drv *iadrv;
+	struct iidc_rdma_core_auxiliary_drv *iadrv;
+	struct iidc_rdma_core_dev_info *cdev;
 
 	if (WARN_ON_ONCE(!in_task()))
 		return;
 
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return;
+
 	mutex_lock(&pf->adev_mutex);
-	if (!pf->adev)
+	if (!cdev->adev)
 		goto finish;
 
-	device_lock(&pf->adev->dev);
-	iadrv = ice_get_auxiliary_drv(pf);
+	device_lock(&cdev->adev->dev);
+	iadrv = ice_get_auxiliary_drv(cdev);
 	if (iadrv && iadrv->event_handler)
-		iadrv->event_handler(pf, event);
-	device_unlock(&pf->adev->dev);
+		iadrv->event_handler(cdev, event);
+	device_unlock(&cdev->adev->dev);
 finish:
 	mutex_unlock(&pf->adev_mutex);
 }
 
 /**
  * ice_add_rdma_qset - Add Leaf Node for RDMA Qset
- * @pf: PF struct
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  * @qset: Resource to be allocated
+ *
+ * Return: Zero on success or error code encountered
  */
-int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
+int ice_add_rdma_qset(struct iidc_rdma_core_dev_info *cdev,
+		      struct iidc_rdma_qset_params *qset)
 {
 	u16 max_rdmaqs[ICE_MAX_TRAFFIC_CLASS];
 	struct ice_vsi *vsi;
 	struct device *dev;
+	struct ice_pf *pf;
 	u32 qset_teid;
 	u16 qs_handle;
 	int status;
 	int i;
 
-	if (WARN_ON(!pf || !qset))
+	if (WARN_ON(!cdev || !qset))
 		return -EINVAL;
 
+	pf = pci_get_drvdata(cdev->pdev);
 	dev = ice_pf_to_dev(pf);
 
 	if (!ice_is_rdma_ena(pf))
@@ -100,7 +113,6 @@ int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
 		dev_err(dev, "Failed VSI RDMA Qset enable\n");
 		return status;
 	}
-	vsi->qset_handle[qset->tc] = qset->qs_handle;
 	qset->teid = qset_teid;
 
 	return 0;
@@ -109,18 +121,23 @@ EXPORT_SYMBOL_GPL(ice_add_rdma_qset);
 
 /**
  * ice_del_rdma_qset - Delete leaf node for RDMA Qset
- * @pf: PF struct
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  * @qset: Resource to be freed
+ *
+ * Return: Zero on success, error code on failure
  */
-int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
+int ice_del_rdma_qset(struct iidc_rdma_core_dev_info *cdev,
+		      struct iidc_rdma_qset_params *qset)
 {
 	struct ice_vsi *vsi;
+	struct ice_pf *pf;
 	u32 teid;
 	u16 q_id;
 
-	if (WARN_ON(!pf || !qset))
+	if (WARN_ON(!cdev || !qset))
 		return -EINVAL;
 
+	pf = pci_get_drvdata(cdev->pdev);
 	vsi = ice_find_vsi(pf, qset->vport_id);
 	if (!vsi) {
 		dev_err(ice_pf_to_dev(pf), "RDMA Invalid VSI\n");
@@ -130,36 +147,36 @@ int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
 	q_id = qset->qs_handle;
 	teid = qset->teid;
 
-	vsi->qset_handle[qset->tc] = 0;
-
 	return ice_dis_vsi_rdma_qset(vsi->port_info, 1, &teid, &q_id);
 }
 EXPORT_SYMBOL_GPL(ice_del_rdma_qset);
 
 /**
  * ice_rdma_request_reset - accept request from RDMA to perform a reset
- * @pf: struct for PF
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  * @reset_type: type of reset
+ *
+ * Return: Zero on success, error code on failure
  */
-int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type)
+int ice_rdma_request_reset(struct iidc_rdma_core_dev_info *cdev,
+			   enum iidc_rdma_reset_type reset_type)
 {
 	enum ice_reset_req reset;
+	struct ice_pf *pf;
 
-	if (WARN_ON(!pf))
+	if (WARN_ON(!cdev))
 		return -EINVAL;
 
+	pf = pci_get_drvdata(cdev->pdev);
+
 	switch (reset_type) {
-	case IIDC_PFR:
+	case IIDC_FUNC_RESET:
 		reset = ICE_RESET_PFR;
 		break;
-	case IIDC_CORER:
+	case IIDC_DEV_RESET:
 		reset = ICE_RESET_CORER;
 		break;
-	case IIDC_GLOBR:
-		reset = ICE_RESET_GLOBR;
-		break;
 	default:
-		dev_err(ice_pf_to_dev(pf), "incorrect reset request\n");
 		return -EINVAL;
 	}
 
@@ -169,18 +186,23 @@ EXPORT_SYMBOL_GPL(ice_rdma_request_reset);
 
 /**
  * ice_rdma_update_vsi_filter - update main VSI filters for RDMA
- * @pf: pointer to struct for PF
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  * @vsi_id: VSI HW idx to update filter on
  * @enable: bool whether to enable or disable filters
+ *
+ * Return: Zero on success, error code on failure
  */
-int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable)
+int ice_rdma_update_vsi_filter(struct iidc_rdma_core_dev_info *cdev,
+			       u16 vsi_id, bool enable)
 {
 	struct ice_vsi *vsi;
+	struct ice_pf *pf;
 	int status;
 
-	if (WARN_ON(!pf))
+	if (WARN_ON(!cdev))
 		return -EINVAL;
 
+	pf = pci_get_drvdata(cdev->pdev);
 	vsi = ice_find_vsi(pf, vsi_id);
 	if (!vsi)
 		return -EINVAL;
@@ -201,88 +223,54 @@ int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable)
 EXPORT_SYMBOL_GPL(ice_rdma_update_vsi_filter);
 
 /**
- * ice_get_qos_params - parse QoS params for RDMA consumption
- * @pf: pointer to PF struct
- * @qos: set of QoS values
- */
-void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos)
-{
-	struct ice_dcbx_cfg *dcbx_cfg;
-	unsigned int i;
-	u32 up2tc;
-
-	dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
-	up2tc = rd32(&pf->hw, PRTDCB_TUP2TC);
-
-	qos->num_tc = ice_dcb_get_num_tc(dcbx_cfg);
-	for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++)
-		qos->up2tc[i] = (up2tc >> (i * 3)) & 0x7;
-
-	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
-		qos->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i];
-
-	qos->pfc_mode = dcbx_cfg->pfc_mode;
-	if (qos->pfc_mode == IIDC_DSCP_PFC_MODE)
-		for (i = 0; i < IIDC_MAX_DSCP_MAPPING; i++)
-			qos->dscp_map[i] = dcbx_cfg->dscp_map[i];
-}
-EXPORT_SYMBOL_GPL(ice_get_qos_params);
-
-/**
- * ice_alloc_rdma_qvectors - Allocate vector resources for RDMA driver
- * @pf: board private structure to initialize
+ * ice_alloc_rdma_qvector - alloc vector resources reserved for RDMA driver
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
+ * @entry: MSI-X entry to be removed
+ *
+ * Return: Zero on success, error code on failure
  */
-static int ice_alloc_rdma_qvectors(struct ice_pf *pf)
+int ice_alloc_rdma_qvector(struct iidc_rdma_core_dev_info *cdev,
+			   struct msix_entry *entry)
 {
-	if (ice_is_rdma_ena(pf)) {
-		int i;
-
-		pf->msix_entries = kcalloc(pf->num_rdma_msix,
-					   sizeof(*pf->msix_entries),
-						  GFP_KERNEL);
-		if (!pf->msix_entries)
-			return -ENOMEM;
+	struct msi_map map;
+	struct ice_pf *pf;
 
-		/* RDMA is the only user of pf->msix_entries array */
-		pf->rdma_base_vector = 0;
+	if (WARN_ON(!cdev))
+		return -EINVAL;
 
-		for (i = 0; i < pf->num_rdma_msix; i++) {
-			struct msix_entry *entry = &pf->msix_entries[i];
-			struct msi_map map;
+	pf = pci_get_drvdata(cdev->pdev);
+	map = ice_alloc_irq(pf, true);
+	if (map.index < 0)
+		return -ENOMEM;
 
-			map = ice_alloc_irq(pf, false);
-			if (map.index < 0)
-				break;
+	entry->entry = map.index;
+	entry->vector = map.virq;
 
-			entry->entry = map.index;
-			entry->vector = map.virq;
-		}
-	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ice_alloc_rdma_qvector);
 
 /**
  * ice_free_rdma_qvector - free vector resources reserved for RDMA driver
- * @pf: board private structure to initialize
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
+ * @entry: MSI-X entry to be removed
  */
-static void ice_free_rdma_qvector(struct ice_pf *pf)
+void ice_free_rdma_qvector(struct iidc_rdma_core_dev_info *cdev,
+			   struct msix_entry *entry)
 {
-	int i;
+	struct msi_map map;
+	struct ice_pf *pf;
 
-	if (!pf->msix_entries)
+	if (WARN_ON(!cdev || !entry))
 		return;
 
-	for (i = 0; i < pf->num_rdma_msix; i++) {
-		struct msi_map map;
-
-		map.index = pf->msix_entries[i].entry;
-		map.virq = pf->msix_entries[i].vector;
-		ice_free_irq(pf, map);
-	}
+	pf = pci_get_drvdata(cdev->pdev);
 
-	kfree(pf->msix_entries);
-	pf->msix_entries = NULL;
+	map.index = entry->entry;
+	map.virq = entry->vector;
+	ice_free_irq(pf, map);
 }
+EXPORT_SYMBOL_GPL(ice_free_rdma_qvector);
 
 /**
  * ice_adev_release - function to be mapped to AUX dev's release op
@@ -290,19 +278,23 @@ static void ice_free_rdma_qvector(struct ice_pf *pf)
  */
 static void ice_adev_release(struct device *dev)
 {
-	struct iidc_auxiliary_dev *iadev;
+	struct iidc_rdma_core_auxiliary_dev *iadev;
 
-	iadev = container_of(dev, struct iidc_auxiliary_dev, adev.dev);
+	iadev = container_of(dev, struct iidc_rdma_core_auxiliary_dev,
+			     adev.dev);
 	kfree(iadev);
 }
 
 /**
  * ice_plug_aux_dev - allocate and register AUX device
  * @pf: pointer to pf struct
+ *
+ * Return: Zero on success, error code on failure
  */
 int ice_plug_aux_dev(struct ice_pf *pf)
 {
-	struct iidc_auxiliary_dev *iadev;
+	struct iidc_rdma_core_auxiliary_dev *iadev;
+	struct iidc_rdma_core_dev_info *cdev;
 	struct auxiliary_device *adev;
 	int ret;
 
@@ -312,17 +304,22 @@ int ice_plug_aux_dev(struct ice_pf *pf)
 	if (!ice_is_rdma_ena(pf))
 		return 0;
 
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
+
 	iadev = kzalloc(sizeof(*iadev), GFP_KERNEL);
 	if (!iadev)
 		return -ENOMEM;
 
 	adev = &iadev->adev;
-	iadev->pf = pf;
+	iadev->cdev_info = cdev;
 
 	adev->id = pf->aux_idx;
 	adev->dev.release = ice_adev_release;
 	adev->dev.parent = &pf->pdev->dev;
-	adev->name = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ? "roce" : "iwarp";
+	adev->name = cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2 ?
+		"roce" : "iwarp";
 
 	ret = auxiliary_device_init(adev);
 	if (ret) {
@@ -337,8 +334,9 @@ int ice_plug_aux_dev(struct ice_pf *pf)
 	}
 
 	mutex_lock(&pf->adev_mutex);
-	pf->adev = adev;
+	cdev->adev = adev;
 	mutex_unlock(&pf->adev_mutex);
+	set_bit(ICE_FLAG_AUX_DEV_CREATED, pf->flags);
 
 	return 0;
 }
@@ -350,15 +348,16 @@ void ice_unplug_aux_dev(struct ice_pf *pf)
 {
 	struct auxiliary_device *adev;
 
+	if (!test_and_clear_bit(ICE_FLAG_AUX_DEV_CREATED, pf->flags))
+		return;
+
 	mutex_lock(&pf->adev_mutex);
-	adev = pf->adev;
-	pf->adev = NULL;
+	adev = pf->cdev_info->adev;
+	pf->cdev_info->adev = NULL;
 	mutex_unlock(&pf->adev_mutex);
 
-	if (adev) {
-		auxiliary_device_delete(adev);
-		auxiliary_device_uninit(adev);
-	}
+	auxiliary_device_delete(adev);
+	auxiliary_device_uninit(adev);
 }
 
 /**
@@ -367,7 +366,9 @@ void ice_unplug_aux_dev(struct ice_pf *pf)
  */
 int ice_init_rdma(struct ice_pf *pf)
 {
+	struct iidc_rdma_priv_dev_info *privd;
 	struct device *dev = &pf->pdev->dev;
+	struct iidc_rdma_core_dev_info *cdev;
 	int ret;
 
 	if (!ice_is_rdma_ena(pf)) {
@@ -375,30 +376,50 @@ int ice_init_rdma(struct ice_pf *pf)
 		return 0;
 	}
 
+	cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
+	if (!cdev)
+		return -ENOMEM;
+
+	pf->cdev_info = cdev;
+
+	privd = kzalloc(sizeof(*privd), GFP_KERNEL);
+	if (!privd) {
+		ret = -ENOMEM;
+		goto err_privd_alloc;
+	}
+
+	privd->pf_id = pf->hw.pf_id;
 	ret = xa_alloc(&ice_aux_id, &pf->aux_idx, NULL, XA_LIMIT(1, INT_MAX),
 		       GFP_KERNEL);
 	if (ret) {
 		dev_err(dev, "Failed to allocate device ID for AUX driver\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_alloc_xa;
 	}
 
-	/* Reserve vector resources */
-	ret = ice_alloc_rdma_qvectors(pf);
-	if (ret < 0) {
-		dev_err(dev, "failed to reserve vectors for RDMA\n");
-		goto err_reserve_rdma_qvector;
-	}
-	pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2;
+	cdev->iidc_priv = privd;
+	privd->netdev = pf->vsi[0]->netdev;
+
+	privd->hw_addr = (u8 __iomem *)pf->hw.hw_addr;
+	cdev->pdev = pf->pdev;
+	privd->vport_id = pf->vsi[0]->vsi_num;
+
+	pf->cdev_info->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2;
+	ice_setup_dcb_qos_info(pf, &privd->qos_info);
 	ret = ice_plug_aux_dev(pf);
 	if (ret)
 		goto err_plug_aux_dev;
 	return 0;
 
 err_plug_aux_dev:
-	ice_free_rdma_qvector(pf);
-err_reserve_rdma_qvector:
-	pf->adev = NULL;
+	pf->cdev_info->adev = NULL;
 	xa_erase(&ice_aux_id, pf->aux_idx);
+err_alloc_xa:
+	kfree(privd);
+err_privd_alloc:
+	kfree(cdev);
+	pf->cdev_info = NULL;
+
 	return ret;
 }
 
@@ -412,6 +433,8 @@ void ice_deinit_rdma(struct ice_pf *pf)
 		return;
 
 	ice_unplug_aux_dev(pf);
-	ice_free_rdma_qvector(pf);
 	xa_erase(&ice_aux_id, pf->aux_idx);
+	kfree(pf->cdev_info->iidc_priv);
+	kfree(pf->cdev_info);
+	pf->cdev_info = NULL;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_idc_int.h b/drivers/net/ethernet/intel/ice/ice_idc_int.h
index 4b0c86757df9..17dbfcfb6a2a 100644
--- a/drivers/net/ethernet/intel/ice/ice_idc_int.h
+++ b/drivers/net/ethernet/intel/ice/ice_idc_int.h
@@ -4,10 +4,11 @@
 #ifndef _ICE_IDC_INT_H_
 #define _ICE_IDC_INT_H_
 
-#include <linux/net/intel/iidc.h>
+#include <linux/net/intel/iidc_rdma.h>
+#include <linux/net/intel/iidc_rdma_ice.h>
 
 struct ice_pf;
 
-void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event);
+void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_rdma_event *event);
 
 #endif /* !_ICE_IDC_INT_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c
index ad82ff7d1995..30801fd375f0 100644
--- a/drivers/net/ethernet/intel/ice/ice_irq.c
+++ b/drivers/net/ethernet/intel/ice/ice_irq.c
@@ -20,6 +20,19 @@ ice_init_irq_tracker(struct ice_pf *pf, unsigned int max_vectors,
 	xa_init_flags(&pf->irq_tracker.entries, XA_FLAGS_ALLOC);
 }
 
+static int
+ice_init_virt_irq_tracker(struct ice_pf *pf, u32 base, u32 num_entries)
+{
+	pf->virt_irq_tracker.bm = bitmap_zalloc(num_entries, GFP_KERNEL);
+	if (!pf->virt_irq_tracker.bm)
+		return -ENOMEM;
+
+	pf->virt_irq_tracker.num_entries = num_entries;
+	pf->virt_irq_tracker.base = base;
+
+	return 0;
+}
+
 /**
  * ice_deinit_irq_tracker - free xarray tracker
  * @pf: board private structure
@@ -29,6 +42,11 @@ static void ice_deinit_irq_tracker(struct ice_pf *pf)
 	xa_destroy(&pf->irq_tracker.entries);
 }
 
+static void ice_deinit_virt_irq_tracker(struct ice_pf *pf)
+{
+	bitmap_free(pf->virt_irq_tracker.bm);
+}
+
 /**
  * ice_free_irq_res - free a block of resources
  * @pf: board private structure
@@ -45,7 +63,7 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index)
 /**
  * ice_get_irq_res - get an interrupt resource
  * @pf: board private structure
- * @dyn_only: force entry to be dynamically allocated
+ * @dyn_allowed: allow entry to be dynamically allocated
  *
  * Allocate new irq entry in the free slot of the tracker. Since xarray
  * is used, always allocate new entry at the lowest possible index. Set
@@ -53,11 +71,12 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index)
  *
  * Returns allocated irq entry or NULL on failure.
  */
-static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
+static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf,
+					     bool dyn_allowed)
 {
-	struct xa_limit limit = { .max = pf->irq_tracker.num_entries,
+	struct xa_limit limit = { .max = pf->irq_tracker.num_entries - 1,
 				  .min = 0 };
-	unsigned int num_static = pf->irq_tracker.num_static;
+	unsigned int num_static = pf->irq_tracker.num_static - 1;
 	struct ice_irq_entry *entry;
 	unsigned int index;
 	int ret;
@@ -66,9 +85,9 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
 	if (!entry)
 		return NULL;
 
-	/* skip preallocated entries if the caller says so */
-	if (dyn_only)
-		limit.min = num_static;
+	/* only already allocated if the caller says so */
+	if (!dyn_allowed)
+		limit.max = num_static;
 
 	ret = xa_alloc(&pf->irq_tracker.entries, &index, entry, limit,
 		       GFP_KERNEL);
@@ -78,161 +97,18 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
 		entry = NULL;
 	} else {
 		entry->index = index;
-		entry->dynamic = index >= num_static;
+		entry->dynamic = index > num_static;
 	}
 
 	return entry;
 }
 
-/**
- * ice_reduce_msix_usage - Reduce usage of MSI-X vectors
- * @pf: board private structure
- * @v_remain: number of remaining MSI-X vectors to be distributed
- *
- * Reduce the usage of MSI-X vectors when entire request cannot be fulfilled.
- * pf->num_lan_msix and pf->num_rdma_msix values are set based on number of
- * remaining vectors.
- */
-static void ice_reduce_msix_usage(struct ice_pf *pf, int v_remain)
-{
-	int v_rdma;
-
-	if (!ice_is_rdma_ena(pf)) {
-		pf->num_lan_msix = v_remain;
-		return;
-	}
-
-	/* RDMA needs at least 1 interrupt in addition to AEQ MSIX */
-	v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1;
-
-	if (v_remain < ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_RDMA_MSIX) {
-		dev_warn(ice_pf_to_dev(pf), "Not enough MSI-X vectors to support RDMA.\n");
-		clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
-
-		pf->num_rdma_msix = 0;
-		pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX;
-	} else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) ||
-		   (v_remain - v_rdma < v_rdma)) {
-		/* Support minimum RDMA and give remaining vectors to LAN MSIX
-		 */
-		pf->num_rdma_msix = ICE_MIN_RDMA_MSIX;
-		pf->num_lan_msix = v_remain - ICE_MIN_RDMA_MSIX;
-	} else {
-		/* Split remaining MSIX with RDMA after accounting for AEQ MSIX
-		 */
-		pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 +
-				    ICE_RDMA_NUM_AEQ_MSIX;
-		pf->num_lan_msix = v_remain - pf->num_rdma_msix;
-	}
-}
-
-/**
- * ice_ena_msix_range - Request a range of MSIX vectors from the OS
- * @pf: board private structure
- *
- * Compute the number of MSIX vectors wanted and request from the OS. Adjust
- * device usage if there are not enough vectors. Return the number of vectors
- * reserved or negative on failure.
- */
-static int ice_ena_msix_range(struct ice_pf *pf)
+#define ICE_RDMA_AEQ_MSIX 1
+static int ice_get_default_msix_amount(struct ice_pf *pf)
 {
-	int num_cpus, hw_num_msix, v_other, v_wanted, v_actual;
-	struct device *dev = ice_pf_to_dev(pf);
-	int err;
-
-	hw_num_msix = pf->hw.func_caps.common_cap.num_msix_vectors;
-	num_cpus = num_online_cpus();
-
-	/* LAN miscellaneous handler */
-	v_other = ICE_MIN_LAN_OICR_MSIX;
-
-	/* Flow Director */
-	if (test_bit(ICE_FLAG_FD_ENA, pf->flags))
-		v_other += ICE_FDIR_MSIX;
-
-	/* switchdev */
-	v_other += ICE_ESWITCH_MSIX;
-
-	v_wanted = v_other;
-
-	/* LAN traffic */
-	pf->num_lan_msix = num_cpus;
-	v_wanted += pf->num_lan_msix;
-
-	/* RDMA auxiliary driver */
-	if (ice_is_rdma_ena(pf)) {
-		pf->num_rdma_msix = num_cpus + ICE_RDMA_NUM_AEQ_MSIX;
-		v_wanted += pf->num_rdma_msix;
-	}
-
-	if (v_wanted > hw_num_msix) {
-		int v_remain;
-
-		dev_warn(dev, "not enough device MSI-X vectors. wanted = %d, available = %d\n",
-			 v_wanted, hw_num_msix);
-
-		if (hw_num_msix < ICE_MIN_MSIX) {
-			err = -ERANGE;
-			goto exit_err;
-		}
-
-		v_remain = hw_num_msix - v_other;
-		if (v_remain < ICE_MIN_LAN_TXRX_MSIX) {
-			v_other = ICE_MIN_MSIX - ICE_MIN_LAN_TXRX_MSIX;
-			v_remain = ICE_MIN_LAN_TXRX_MSIX;
-		}
-
-		ice_reduce_msix_usage(pf, v_remain);
-		v_wanted = pf->num_lan_msix + pf->num_rdma_msix + v_other;
-
-		dev_notice(dev, "Reducing request to %d MSI-X vectors for LAN traffic.\n",
-			   pf->num_lan_msix);
-		if (ice_is_rdma_ena(pf))
-			dev_notice(dev, "Reducing request to %d MSI-X vectors for RDMA.\n",
-				   pf->num_rdma_msix);
-	}
-
-	/* actually reserve the vectors */
-	v_actual = pci_alloc_irq_vectors(pf->pdev, ICE_MIN_MSIX, v_wanted,
-					 PCI_IRQ_MSIX);
-	if (v_actual < 0) {
-		dev_err(dev, "unable to reserve MSI-X vectors\n");
-		err = v_actual;
-		goto exit_err;
-	}
-
-	if (v_actual < v_wanted) {
-		dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n",
-			 v_wanted, v_actual);
-
-		if (v_actual < ICE_MIN_MSIX) {
-			/* error if we can't get minimum vectors */
-			pci_free_irq_vectors(pf->pdev);
-			err = -ERANGE;
-			goto exit_err;
-		} else {
-			int v_remain = v_actual - v_other;
-
-			if (v_remain < ICE_MIN_LAN_TXRX_MSIX)
-				v_remain = ICE_MIN_LAN_TXRX_MSIX;
-
-			ice_reduce_msix_usage(pf, v_remain);
-
-			dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n",
-				   pf->num_lan_msix);
-
-			if (ice_is_rdma_ena(pf))
-				dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n",
-					   pf->num_rdma_msix);
-		}
-	}
-
-	return v_actual;
-
-exit_err:
-	pf->num_rdma_msix = 0;
-	pf->num_lan_msix = 0;
-	return err;
+	return ICE_MIN_LAN_OICR_MSIX + num_online_cpus() +
+	       (test_bit(ICE_FLAG_FD_ENA, pf->flags) ? ICE_FDIR_MSIX : 0) +
+	       (ice_is_rdma_ena(pf) ? num_online_cpus() + ICE_RDMA_AEQ_MSIX : 0);
 }
 
 /**
@@ -243,6 +119,7 @@ void ice_clear_interrupt_scheme(struct ice_pf *pf)
 {
 	pci_free_irq_vectors(pf->pdev);
 	ice_deinit_irq_tracker(pf);
+	ice_deinit_virt_irq_tracker(pf);
 }
 
 /**
@@ -252,27 +129,38 @@ void ice_clear_interrupt_scheme(struct ice_pf *pf)
 int ice_init_interrupt_scheme(struct ice_pf *pf)
 {
 	int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
-	int vectors, max_vectors;
+	int vectors;
 
-	vectors = ice_ena_msix_range(pf);
+	/* load default PF MSI-X range */
+	if (!pf->msix.min)
+		pf->msix.min = ICE_MIN_MSIX;
 
-	if (vectors < 0)
-		return -ENOMEM;
+	if (!pf->msix.max)
+		pf->msix.max = min(total_vectors,
+				   ice_get_default_msix_amount(pf));
+
+	pf->msix.total = total_vectors;
+	pf->msix.rest = total_vectors - pf->msix.max;
 
 	if (pci_msix_can_alloc_dyn(pf->pdev))
-		max_vectors = total_vectors;
+		vectors = pf->msix.min;
 	else
-		max_vectors = vectors;
+		vectors = pf->msix.max;
+
+	vectors = pci_alloc_irq_vectors(pf->pdev, pf->msix.min, vectors,
+					PCI_IRQ_MSIX);
+	if (vectors < 0)
+		return vectors;
 
-	ice_init_irq_tracker(pf, max_vectors, vectors);
+	ice_init_irq_tracker(pf, pf->msix.max, vectors);
 
-	return 0;
+	return ice_init_virt_irq_tracker(pf, pf->msix.max, pf->msix.rest);
 }
 
 /**
  * ice_alloc_irq - Allocate new interrupt vector
  * @pf: board private structure
- * @dyn_only: force dynamic allocation of the interrupt
+ * @dyn_allowed: allow dynamic allocation of the interrupt
  *
  * Allocate new interrupt vector for a given owner id.
  * return struct msi_map with interrupt details and track
@@ -285,27 +173,22 @@ int ice_init_interrupt_scheme(struct ice_pf *pf)
  * interrupt will be allocated with pci_msix_alloc_irq_at.
  *
  * Some callers may only support dynamically allocated interrupts.
- * This is indicated with dyn_only flag.
+ * This is indicated with dyn_allowed flag.
  *
  * On failure, return map with negative .index. The caller
  * is expected to check returned map index.
  *
  */
-struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only)
+struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_allowed)
 {
-	int sriov_base_vector = pf->sriov_base_vector;
 	struct msi_map map = { .index = -ENOENT };
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_irq_entry *entry;
 
-	entry = ice_get_irq_res(pf, dyn_only);
+	entry = ice_get_irq_res(pf, dyn_allowed);
 	if (!entry)
 		return map;
 
-	/* fail if we're about to violate SRIOV vectors space */
-	if (sriov_base_vector && entry->index >= sriov_base_vector)
-		goto exit_free_res;
-
 	if (pci_msix_can_alloc_dyn(pf->pdev) && entry->dynamic) {
 		map = pci_msix_alloc_irq_at(pf->pdev, entry->index, NULL);
 		if (map.index < 0)
@@ -353,26 +236,40 @@ void ice_free_irq(struct ice_pf *pf, struct msi_map map)
 }
 
 /**
- * ice_get_max_used_msix_vector - Get the max used interrupt vector
- * @pf: board private structure
+ * ice_virt_get_irqs - get irqs for SR-IOV usacase
+ * @pf: pointer to PF structure
+ * @needed: number of irqs to get
  *
- * Return index of maximum used interrupt vectors with respect to the
- * beginning of the MSIX table. Take into account that some interrupts
- * may have been dynamically allocated after MSIX was initially enabled.
+ * This returns the first MSI-X vector index in PF space that is used by this
+ * VF. This index is used when accessing PF relative registers such as
+ * GLINT_VECT2FUNC and GLINT_DYN_CTL.
+ * This will always be the OICR index in the AVF driver so any functionality
+ * using vf->first_vector_idx for queue configuration_id: id of VF which will
+ * use this irqs
  */
-int ice_get_max_used_msix_vector(struct ice_pf *pf)
+int ice_virt_get_irqs(struct ice_pf *pf, u32 needed)
 {
-	unsigned long start, index, max_idx;
-	void *entry;
+	int res = bitmap_find_next_zero_area(pf->virt_irq_tracker.bm,
+					     pf->virt_irq_tracker.num_entries,
+					     0, needed, 0);
 
-	/* Treat all preallocated interrupts as used */
-	start = pf->irq_tracker.num_static;
-	max_idx = start - 1;
+	if (res >= pf->virt_irq_tracker.num_entries)
+		return -ENOENT;
 
-	xa_for_each_start(&pf->irq_tracker.entries, index, entry, start) {
-		if (index > max_idx)
-			max_idx = index;
-	}
+	bitmap_set(pf->virt_irq_tracker.bm, res, needed);
+
+	/* conversion from number in bitmap to global irq index */
+	return res + pf->virt_irq_tracker.base;
+}
 
-	return max_idx;
+/**
+ * ice_virt_free_irqs - free irqs used by the VF
+ * @pf: pointer to PF structure
+ * @index: first index to be free
+ * @irqs: number of irqs to free
+ */
+void ice_virt_free_irqs(struct ice_pf *pf, u32 index, u32 irqs)
+{
+	bitmap_clear(pf->virt_irq_tracker.bm, index - pf->virt_irq_tracker.base,
+		     irqs);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_irq.h b/drivers/net/ethernet/intel/ice/ice_irq.h
index f35efc08575e..b2f9dbafd57e 100644
--- a/drivers/net/ethernet/intel/ice/ice_irq.h
+++ b/drivers/net/ethernet/intel/ice/ice_irq.h
@@ -15,11 +15,22 @@ struct ice_irq_tracker {
 	u16 num_static;	/* preallocated entries */
 };
 
+struct ice_virt_irq_tracker {
+	unsigned long *bm;	/* bitmap to track irq usage */
+	u32 num_entries;
+	/* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the
+	 * number of MSIX vectors needed for all SR-IOV VFs from the number of
+	 * MSIX vectors allowed on this PF.
+	 */
+	u32 base;
+};
+
 int ice_init_interrupt_scheme(struct ice_pf *pf);
 void ice_clear_interrupt_scheme(struct ice_pf *pf);
 
 struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only);
 void ice_free_irq(struct ice_pf *pf, struct msi_map map);
-int ice_get_max_used_msix_vector(struct ice_pf *pf);
 
+int ice_virt_get_irqs(struct ice_pf *pf, u32 needed);
+void ice_virt_free_irqs(struct ice_pf *pf, u32 index, u32 irqs);
 #endif
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 1ccb572ce285..d2576d606e10 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -10,12 +10,17 @@
 #define ICE_LAG_RES_SHARED	BIT(14)
 #define ICE_LAG_RES_VALID	BIT(15)
 
-#define LACP_TRAIN_PKT_LEN		16
-static const u8 lacp_train_pkt[LACP_TRAIN_PKT_LEN] = { 0, 0, 0, 0, 0, 0,
-						       0, 0, 0, 0, 0, 0,
-						       0x88, 0x09, 0, 0 };
+#define ICE_TRAIN_PKT_LEN		16
+static const u8 lacp_train_pkt[ICE_TRAIN_PKT_LEN] = { 0, 0, 0, 0, 0, 0,
+						      0, 0, 0, 0, 0, 0,
+						      0x88, 0x09, 0, 0 };
+static const u8 act_act_train_pkt[ICE_TRAIN_PKT_LEN] = { 0, 0, 0, 0, 0, 0,
+							 0, 0, 0, 0, 0, 0,
+							 0, 0, 0, 0 };
 
 #define ICE_RECIPE_LEN			64
+#define ICE_LAG_SRIOV_CP_RECIPE		10
+
 static const u8 ice_dflt_vsi_rcp[ICE_RECIPE_LEN] = {
 	0x05, 0, 0, 0, 0x20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
 	0x85, 0, 0x01, 0, 0, 0, 0xff, 0xff, 0x08, 0, 0, 0, 0, 0, 0, 0,
@@ -46,10 +51,10 @@ static void ice_lag_set_primary(struct ice_lag *lag)
 }
 
 /**
- * ice_lag_set_backup - set PF LAG state to Backup
+ * ice_lag_set_bkup - set PF LAG state to Backup
  * @lag: LAG info struct
  */
-static void ice_lag_set_backup(struct ice_lag *lag)
+static void ice_lag_set_bkup(struct ice_lag *lag)
 {
 	struct ice_pf *pf = lag->pf;
 
@@ -99,6 +104,28 @@ static bool netif_is_same_ice(struct ice_pf *pf, struct net_device *netdev)
 }
 
 /**
+ * ice_lag_config_eswitch - configure eswitch to work with LAG
+ * @lag: lag info struct
+ * @netdev: active network interface device struct
+ *
+ * Updates all port representors in eswitch to use @netdev for Tx.
+ *
+ * Configures the netdev to keep dst metadata (also used in representor Tx).
+ * This is required for an uplink without switchdev mode configured.
+ */
+static void ice_lag_config_eswitch(struct ice_lag *lag,
+				   struct net_device *netdev)
+{
+	struct ice_repr *repr;
+	unsigned long id;
+
+	xa_for_each(&lag->pf->eswitch.reprs, id, repr)
+		repr->dst->u.port_info.lower_dev = netdev;
+
+	netif_keep_dst(netdev);
+}
+
+/**
  * ice_netdev_to_lag - return pointer to associated lag struct from netdev
  * @netdev: pointer to net_device struct to query
  */
@@ -210,13 +237,12 @@ ice_lag_cfg_fltr(struct ice_lag *lag, u32 act, u16 recipe_id, u16 *rule_idx,
 		 u8 direction, bool add)
 {
 	struct ice_sw_rule_lkup_rx_tx *s_rule;
+	struct ice_hw *hw = &lag->pf->hw;
 	u16 s_rule_sz, vsi_num;
-	struct ice_hw *hw;
 	u8 *eth_hdr;
 	u32 opc;
 	int err;
 
-	hw = &lag->pf->hw;
 	vsi_num = ice_get_hw_vsi_num(hw, 0);
 
 	s_rule_sz = ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s_rule);
@@ -314,26 +340,15 @@ ice_lag_cfg_drop_fltr(struct ice_lag *lag, bool add)
 }
 
 /**
- * ice_lag_cfg_pf_fltrs - set filters up for new active port
+ * ice_lag_cfg_pf_fltrs_act_bkup - set filters up for new active port
  * @lag: local interfaces lag struct
- * @ptr: opaque data containing notifier event
+ * @bonding_info: netdev event bonding info
  */
 static void
-ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr)
+ice_lag_cfg_pf_fltrs_act_bkup(struct ice_lag *lag,
+			      struct netdev_bonding_info *bonding_info)
 {
-	struct netdev_notifier_bonding_info *info;
-	struct netdev_bonding_info *bonding_info;
-	struct net_device *event_netdev;
-	struct device *dev;
-
-	event_netdev = netdev_notifier_info_to_dev(ptr);
-	/* not for this netdev */
-	if (event_netdev != lag->netdev)
-		return;
-
-	info = (struct netdev_notifier_bonding_info *)ptr;
-	bonding_info = &info->bonding_info;
-	dev = ice_pf_to_dev(lag->pf);
+	struct device *dev = ice_pf_to_dev(lag->pf);
 
 	/* interface not active - remove old default VSI rule */
 	if (bonding_info->slave.state && lag->pf_rx_rule_id) {
@@ -354,6 +369,105 @@ ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr)
 }
 
 /**
+ * ice_lag_cfg_lp_fltr - configure lport filters
+ * @lag: local interface's lag struct
+ * @add: add or remove rule
+ * @cp: control packet only or general PF lport rule
+ */
+static void
+ice_lag_cfg_lp_fltr(struct ice_lag *lag, bool add, bool cp)
+{
+	struct ice_sw_rule_lkup_rx_tx *s_rule;
+	struct ice_vsi *vsi = lag->pf->vsi[0];
+	u16 buf_len, opc;
+
+	buf_len = ICE_SW_RULE_RX_TX_HDR_SIZE(s_rule, ICE_TRAIN_PKT_LEN);
+	s_rule = kzalloc(buf_len, GFP_KERNEL);
+	if (!s_rule) {
+		netdev_warn(lag->netdev, "-ENOMEM error configuring CP filter\n");
+		return;
+	}
+
+	if (add) {
+		if (cp) {
+			s_rule->recipe_id =
+				cpu_to_le16(ICE_LAG_SRIOV_CP_RECIPE);
+			memcpy(s_rule->hdr_data, lacp_train_pkt,
+			       ICE_TRAIN_PKT_LEN);
+		} else {
+			s_rule->recipe_id = cpu_to_le16(lag->act_act_recipe);
+			memcpy(s_rule->hdr_data, act_act_train_pkt,
+			       ICE_TRAIN_PKT_LEN);
+		}
+
+		s_rule->src = cpu_to_le16(vsi->port_info->lport);
+		s_rule->act = cpu_to_le32(ICE_FWD_TO_VSI |
+					  ICE_SINGLE_ACT_LAN_ENABLE |
+					  ICE_SINGLE_ACT_VALID_BIT |
+					  FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M,
+						     vsi->vsi_num));
+		s_rule->hdr_len = cpu_to_le16(ICE_TRAIN_PKT_LEN);
+		s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX);
+		opc = ice_aqc_opc_add_sw_rules;
+	} else {
+		opc = ice_aqc_opc_remove_sw_rules;
+		if (cp)
+			s_rule->index = cpu_to_le16(lag->cp_rule_idx);
+		else
+			s_rule->index = cpu_to_le16(lag->act_act_rule_idx);
+	}
+	if (ice_aq_sw_rules(&lag->pf->hw, s_rule, buf_len, 1, opc, NULL)) {
+		netdev_warn(lag->netdev, "Error %s %s rule for aggregate\n",
+			    add ? "ADDING" : "REMOVING",
+			    cp ? "CONTROL PACKET" : "LPORT");
+		goto err_cp_free;
+	}
+
+	if (add) {
+		if (cp)
+			lag->cp_rule_idx = le16_to_cpu(s_rule->index);
+		else
+			lag->act_act_rule_idx = le16_to_cpu(s_rule->index);
+	} else {
+		if (cp)
+			lag->cp_rule_idx = 0;
+		else
+			lag->act_act_rule_idx = 0;
+	}
+
+err_cp_free:
+	kfree(s_rule);
+}
+
+/**
+ * ice_lag_cfg_pf_fltrs - set filters up for PF traffic
+ * @lag: local interfaces lag struct
+ * @ptr: opaque data containing notifier event
+ */
+static void
+ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr)
+{
+	struct netdev_notifier_bonding_info *info = ptr;
+	struct netdev_bonding_info *bonding_info;
+	struct net_device *event_netdev;
+
+	event_netdev = netdev_notifier_info_to_dev(ptr);
+	if (event_netdev != lag->netdev)
+		return;
+
+	bonding_info = &info->bonding_info;
+
+	if (lag->bond_aa) {
+		if (lag->need_fltr_cfg) {
+			ice_lag_cfg_lp_fltr(lag, true, false);
+			lag->need_fltr_cfg = false;
+		}
+	} else {
+		ice_lag_cfg_pf_fltrs_act_bkup(lag, bonding_info);
+	}
+}
+
+/**
  * ice_display_lag_info - print LAG info
  * @lag: LAG info struct
  */
@@ -402,12 +516,11 @@ static u16
 ice_lag_qbuf_recfg(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *qbuf,
 		   u16 vsi_num, u16 numq, u8 tc)
 {
+	struct ice_pf *pf = hw->back;
 	struct ice_q_ctx *q_ctx;
 	u16 qid, count = 0;
-	struct ice_pf *pf;
 	int i;
 
-	pf = hw->back;
 	for (i = 0; i < numq; i++) {
 		q_ctx = ice_get_lan_q_ctx(hw, vsi_num, tc, i);
 		if (!q_ctx) {
@@ -577,7 +690,7 @@ ice_lag_move_vf_node_tc(struct ice_lag *lag, u8 oldport, u8 newport,
 	}
 
 	if (ice_aq_cfg_lan_txq(&lag->pf->hw, qbuf, qbuf_size, valq, oldport,
-			       newport, NULL)) {
+			       newport, ICE_AQC_Q_CFG_TC_CHNG, NULL)) {
 		dev_warn(dev, "Failure to configure queues for LAG failover\n");
 		goto qbuf_err;
 	}
@@ -677,54 +790,6 @@ ice_lag_move_single_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport,
 }
 
 /**
- * ice_lag_move_new_vf_nodes - Move Tx scheduling nodes for a VF if required
- * @vf: the VF to move Tx nodes for
- *
- * Called just after configuring new VF queues. Check whether the VF Tx
- * scheduling nodes need to be updated to fail over to the active port. If so,
- * move them now.
- */
-void ice_lag_move_new_vf_nodes(struct ice_vf *vf)
-{
-	struct ice_lag_netdev_list ndlist;
-	u8 pri_port, act_port;
-	struct ice_lag *lag;
-	struct ice_vsi *vsi;
-	struct ice_pf *pf;
-
-	vsi = ice_get_vf_vsi(vf);
-
-	if (WARN_ON(!vsi))
-		return;
-
-	if (WARN_ON(vsi->type != ICE_VSI_VF))
-		return;
-
-	pf = vf->pf;
-	lag = pf->lag;
-
-	mutex_lock(&pf->lag_mutex);
-	if (!lag->bonded)
-		goto new_vf_unlock;
-
-	pri_port = pf->hw.port_info->lport;
-	act_port = lag->active_port;
-
-	if (lag->upper_netdev)
-		ice_lag_build_netdev_list(lag, &ndlist);
-
-	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) &&
-	    lag->bonded && lag->primary && pri_port != act_port &&
-	    !list_empty(lag->netdev_head))
-		ice_lag_move_single_vf_nodes(lag, pri_port, act_port, vsi->idx);
-
-	ice_lag_destroy_netdev_list(lag, &ndlist);
-
-new_vf_unlock:
-	mutex_unlock(&pf->lag_mutex);
-}
-
-/**
  * ice_lag_move_vf_nodes - move Tx scheduling nodes for all VFs to new port
  * @lag: lag info struct
  * @oldport: lport of previous interface
@@ -767,59 +832,60 @@ void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt)
 	ice_lag_destroy_netdev_list(lag, &ndlist);
 }
 
-#define ICE_LAG_SRIOV_CP_RECIPE		10
-#define ICE_LAG_SRIOV_TRAIN_PKT_LEN	16
-
 /**
- * ice_lag_cfg_cp_fltr - configure filter for control packets
- * @lag: local interface's lag struct
- * @add: add or remove rule
+ * ice_lag_prepare_vf_reset - helper to adjust vf lag for reset
+ * @lag: lag struct for interface that owns VF
+ *
+ * Context: must be called with the lag_mutex lock held.
+ *
+ * Return: active lport value or ICE_LAG_INVALID_PORT if nothing moved.
  */
-static void
-ice_lag_cfg_cp_fltr(struct ice_lag *lag, bool add)
+u8 ice_lag_prepare_vf_reset(struct ice_lag *lag)
 {
-	struct ice_sw_rule_lkup_rx_tx *s_rule = NULL;
-	struct ice_vsi *vsi;
-	u16 buf_len, opc;
-
-	vsi = lag->pf->vsi[0];
-
-	buf_len = ICE_SW_RULE_RX_TX_HDR_SIZE(s_rule,
-					     ICE_LAG_SRIOV_TRAIN_PKT_LEN);
-	s_rule = kzalloc(buf_len, GFP_KERNEL);
-	if (!s_rule) {
-		netdev_warn(lag->netdev, "-ENOMEM error configuring CP filter\n");
-		return;
-	}
-
-	if (add) {
-		s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX);
-		s_rule->recipe_id = cpu_to_le16(ICE_LAG_SRIOV_CP_RECIPE);
-		s_rule->src = cpu_to_le16(vsi->port_info->lport);
-		s_rule->act = cpu_to_le32(ICE_FWD_TO_VSI |
-					  ICE_SINGLE_ACT_LAN_ENABLE |
-					  ICE_SINGLE_ACT_VALID_BIT |
-					  FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, vsi->vsi_num));
-		s_rule->hdr_len = cpu_to_le16(ICE_LAG_SRIOV_TRAIN_PKT_LEN);
-		memcpy(s_rule->hdr_data, lacp_train_pkt, LACP_TRAIN_PKT_LEN);
-		opc = ice_aqc_opc_add_sw_rules;
-	} else {
-		opc = ice_aqc_opc_remove_sw_rules;
-		s_rule->index = cpu_to_le16(lag->cp_rule_idx);
-	}
-	if (ice_aq_sw_rules(&lag->pf->hw, s_rule, buf_len, 1, opc, NULL)) {
-		netdev_warn(lag->netdev, "Error %s CP rule for fail-over\n",
-			    add ? "ADDING" : "REMOVING");
-		goto cp_free;
+	u8 pri_prt, act_prt;
+
+	if (lag && lag->bonded && lag->primary && lag->upper_netdev) {
+		if (!lag->bond_aa) {
+			pri_prt = lag->pf->hw.port_info->lport;
+			act_prt = lag->active_port;
+			if (act_prt != pri_prt &&
+			    act_prt != ICE_LAG_INVALID_PORT) {
+				ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt);
+				return act_prt;
+			}
+		} else {
+			if (lag->port_bitmap & ICE_LAGS_M) {
+				lag->port_bitmap &= ~ICE_LAGS_M;
+				ice_lag_aa_failover(lag, ICE_LAGP_IDX, NULL);
+				lag->port_bitmap |= ICE_LAGS_M;
+			}
+		}
 	}
 
-	if (add)
-		lag->cp_rule_idx = le16_to_cpu(s_rule->index);
-	else
-		lag->cp_rule_idx = 0;
+	return ICE_LAG_INVALID_PORT;
+}
 
-cp_free:
-	kfree(s_rule);
+/**
+ * ice_lag_complete_vf_reset - helper for lag after reset
+ * @lag: lag struct for primary interface
+ * @act_prt: which port should be active for lag
+ *
+ * Context: must be called while holding the lag_mutex.
+ */
+void ice_lag_complete_vf_reset(struct ice_lag *lag, u8 act_prt)
+{
+	u8 pri_prt;
+
+	if (lag && lag->bonded && lag->primary) {
+		if (!lag->bond_aa) {
+			pri_prt = lag->pf->hw.port_info->lport;
+			if (act_prt != ICE_LAG_INVALID_PORT)
+				ice_lag_move_vf_nodes_cfg(lag, pri_prt,
+							  act_prt);
+		} else {
+			ice_lag_aa_failover(lag, ICE_LAGS_IDX, NULL);
+		}
+	}
 }
 
 /**
@@ -831,13 +897,12 @@ cp_free:
  */
 static void ice_lag_info_event(struct ice_lag *lag, void *ptr)
 {
-	struct netdev_notifier_bonding_info *info;
+	struct netdev_notifier_bonding_info *info = ptr;
 	struct netdev_bonding_info *bonding_info;
 	struct net_device *event_netdev;
 	const char *lag_netdev_name;
 
 	event_netdev = netdev_notifier_info_to_dev(ptr);
-	info = ptr;
 	lag_netdev_name = netdev_name(lag->netdev);
 	bonding_info = &info->bonding_info;
 
@@ -855,7 +920,7 @@ static void ice_lag_info_event(struct ice_lag *lag, void *ptr)
 	}
 
 	if (bonding_info->slave.state)
-		ice_lag_set_backup(lag);
+		ice_lag_set_bkup(lag);
 	else
 		ice_lag_set_primary(lag);
 
@@ -864,6 +929,295 @@ lag_out:
 }
 
 /**
+ * ice_lag_aa_qbuf_recfg - fill a single queue buffer for recfg cmd
+ * @hw: HW struct that contains the queue context
+ * @qbuf: pointer to single queue buffer
+ * @vsi_num: index of the VF VSI in PF space
+ * @qnum: queue index
+ *
+ * Return: Zero on success, error code on failure.
+ */
+static int
+ice_lag_aa_qbuf_recfg(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *qbuf,
+		      u16 vsi_num, int qnum)
+{
+	struct ice_pf *pf = hw->back;
+	struct ice_q_ctx *q_ctx;
+	u16 q_id;
+
+	q_ctx = ice_get_lan_q_ctx(hw, vsi_num, 0, qnum);
+	if (!q_ctx) {
+		dev_dbg(ice_hw_to_dev(hw), "LAG queue %d no Q context\n", qnum);
+		return -ENOENT;
+	}
+
+	if (q_ctx->q_teid == ICE_INVAL_TEID) {
+		dev_dbg(ice_hw_to_dev(hw), "LAG queue %d INVAL TEID\n", qnum);
+		return -EINVAL;
+	}
+
+	if (q_ctx->q_handle == ICE_INVAL_Q_HANDLE) {
+		dev_dbg(ice_hw_to_dev(hw), "LAG queue %d INVAL Q HANDLE\n", qnum);
+		return -EINVAL;
+	}
+
+	q_id = pf->vsi[vsi_num]->txq_map[q_ctx->q_handle];
+	qbuf->queue_info[0].q_handle = cpu_to_le16(q_id);
+	qbuf->queue_info[0].tc = 0;
+	qbuf->queue_info[0].q_teid = cpu_to_le32(q_ctx->q_teid);
+
+	return 0;
+}
+
+/**
+ * ice_lag_aa_move_vf_qs - Move some/all VF queues to destination
+ * @lag: primary interface's lag struct
+ * @dest: index of destination port
+ * @vsi_num: index of VF VSI in PF space
+ * @all: if true move all queues to destination
+ * @odd: VF wide q indicator for odd/even
+ * @e_pf: PF struct for the event interface
+ *
+ * the parameter "all" is to control whether we are splitting the queues
+ * between two interfaces or moving them all to the destination interface
+ */
+static void ice_lag_aa_move_vf_qs(struct ice_lag *lag, u8 dest, u16 vsi_num,
+				  bool all, bool *odd, struct ice_pf *e_pf)
+{
+	DEFINE_RAW_FLEX(struct ice_aqc_cfg_txqs_buf, qbuf, queue_info, 1);
+	struct ice_hw *old_hw, *new_hw, *pri_hw, *sec_hw;
+	struct device *dev = ice_pf_to_dev(lag->pf);
+	struct ice_vsi_ctx *pv_ctx, *sv_ctx;
+	struct ice_lag_netdev_list ndlist;
+	u16 num_q, qbuf_size, sec_vsi_num;
+	u8 pri_lport, sec_lport;
+	u32 pvf_teid, svf_teid;
+	u16 vf_id;
+
+	vf_id = lag->pf->vsi[vsi_num]->vf->vf_id;
+	/* If sec_vf[] not defined, then no second interface to share with */
+	if (lag->sec_vf[vf_id])
+		sec_vsi_num = lag->sec_vf[vf_id]->idx;
+	else
+		return;
+
+	pri_lport = lag->bond_lport_pri;
+	sec_lport = lag->bond_lport_sec;
+
+	if (pri_lport == ICE_LAG_INVALID_PORT ||
+	    sec_lport == ICE_LAG_INVALID_PORT)
+		return;
+
+	if (!e_pf)
+		ice_lag_build_netdev_list(lag, &ndlist);
+
+	pri_hw = &lag->pf->hw;
+	if (e_pf && lag->pf != e_pf)
+		sec_hw = &e_pf->hw;
+	else
+		sec_hw = ice_lag_find_hw_by_lport(lag, sec_lport);
+
+	if (!pri_hw || !sec_hw)
+		return;
+
+	if (dest == ICE_LAGP_IDX) {
+		struct ice_vsi *vsi;
+
+		vsi = ice_get_main_vsi(lag->pf);
+		if (!vsi)
+			return;
+
+		old_hw = sec_hw;
+		new_hw = pri_hw;
+		ice_lag_config_eswitch(lag, vsi->netdev);
+	} else {
+		struct ice_pf *sec_pf = sec_hw->back;
+		struct ice_vsi *vsi;
+
+		vsi = ice_get_main_vsi(sec_pf);
+		if (!vsi)
+			return;
+
+		old_hw = pri_hw;
+		new_hw = sec_hw;
+		ice_lag_config_eswitch(lag, vsi->netdev);
+	}
+
+	pv_ctx = ice_get_vsi_ctx(pri_hw, vsi_num);
+	if (!pv_ctx) {
+		dev_warn(dev, "Unable to locate primary VSI %d context for LAG failover\n",
+			 vsi_num);
+		return;
+	}
+
+	sv_ctx = ice_get_vsi_ctx(sec_hw, sec_vsi_num);
+	if (!sv_ctx) {
+		dev_warn(dev, "Unable to locate secondary VSI %d context for LAG failover\n",
+			 vsi_num);
+		return;
+	}
+
+	num_q = pv_ctx->num_lan_q_entries[0];
+	qbuf_size = __struct_size(qbuf);
+
+	/* Suspend traffic for primary VSI VF */
+	pvf_teid = le32_to_cpu(pv_ctx->sched.vsi_node[0]->info.node_teid);
+	ice_sched_suspend_resume_elems(pri_hw, 1, &pvf_teid, true);
+
+	/* Suspend traffic for secondary VSI VF */
+	svf_teid = le32_to_cpu(sv_ctx->sched.vsi_node[0]->info.node_teid);
+	ice_sched_suspend_resume_elems(sec_hw, 1, &svf_teid, true);
+
+	for (int i = 0; i < num_q; i++) {
+		struct ice_sched_node *n_prt, *q_node, *parent;
+		struct ice_port_info *pi, *new_pi;
+		struct ice_vsi_ctx *src_ctx;
+		struct ice_sched_node *p;
+		struct ice_q_ctx *q_ctx;
+		u16 dst_vsi_num;
+
+		pi = old_hw->port_info;
+		new_pi = new_hw->port_info;
+
+		*odd = !(*odd);
+		if ((dest == ICE_LAGP_IDX && *odd && !all) ||
+		    (dest == ICE_LAGS_IDX && !(*odd) && !all) ||
+		    lag->q_home[vf_id][i] == dest)
+			continue;
+
+		if (dest == ICE_LAGP_IDX)
+			dst_vsi_num = vsi_num;
+		else
+			dst_vsi_num = sec_vsi_num;
+
+		n_prt = ice_sched_get_free_qparent(new_hw->port_info,
+						   dst_vsi_num, 0,
+						   ICE_SCHED_NODE_OWNER_LAN);
+		if (!n_prt)
+			continue;
+
+		q_ctx = ice_get_lan_q_ctx(pri_hw, vsi_num, 0, i);
+		if (!q_ctx)
+			continue;
+
+		if (dest == ICE_LAGP_IDX)
+			src_ctx = sv_ctx;
+		else
+			src_ctx = pv_ctx;
+
+		q_node = ice_sched_find_node_by_teid(src_ctx->sched.vsi_node[0],
+						     q_ctx->q_teid);
+		if (!q_node)
+			continue;
+
+		qbuf->src_parent_teid = q_node->info.parent_teid;
+		qbuf->dst_parent_teid = n_prt->info.node_teid;
+
+		/* Move the node in the HW/FW */
+		if (ice_lag_aa_qbuf_recfg(pri_hw, qbuf, vsi_num, i))
+			continue;
+
+		if (dest == ICE_LAGP_IDX)
+			ice_aq_cfg_lan_txq(pri_hw, qbuf, qbuf_size, 1,
+					   sec_lport, pri_lport,
+					   ICE_AQC_Q_CFG_MOVE_TC_CHNG,
+					   NULL);
+		else
+			ice_aq_cfg_lan_txq(pri_hw, qbuf, qbuf_size, 1,
+					   pri_lport, sec_lport,
+					   ICE_AQC_Q_CFG_MOVE_TC_CHNG,
+					   NULL);
+
+		/* Move the node in the SW */
+		parent = q_node->parent;
+		if (!parent)
+			continue;
+
+		for (int n = 0; n < parent->num_children; n++) {
+			int j;
+
+			if (parent->children[n] != q_node)
+				continue;
+
+			for (j = n + 1; j < parent->num_children;
+			     j++) {
+				parent->children[j - 1] =
+					parent->children[j];
+			}
+			parent->children[j] = NULL;
+			parent->num_children--;
+			break;
+		}
+
+		p = pi->sib_head[0][q_node->tx_sched_layer];
+		while (p) {
+			if (p->sibling == q_node) {
+				p->sibling = q_node->sibling;
+				break;
+			}
+			p = p->sibling;
+		}
+
+		if (pi->sib_head[0][q_node->tx_sched_layer] == q_node)
+			pi->sib_head[0][q_node->tx_sched_layer] =
+				q_node->sibling;
+
+		q_node->parent = n_prt;
+		q_node->info.parent_teid = n_prt->info.node_teid;
+		q_node->sibling = NULL;
+		p = new_pi->sib_head[0][q_node->tx_sched_layer];
+		if (p) {
+			while (p) {
+				if (!p->sibling) {
+					p->sibling = q_node;
+					break;
+				}
+				p = p->sibling;
+			}
+		} else {
+			new_pi->sib_head[0][q_node->tx_sched_layer] =
+				q_node;
+		}
+
+		n_prt->children[n_prt->num_children++] = q_node;
+		lag->q_home[vf_id][i] = dest;
+	}
+
+	ice_sched_suspend_resume_elems(pri_hw, 1, &pvf_teid, false);
+	ice_sched_suspend_resume_elems(sec_hw, 1, &svf_teid, false);
+
+	if (!e_pf)
+		ice_lag_destroy_netdev_list(lag, &ndlist);
+}
+
+/**
+ * ice_lag_aa_failover - move VF queues in A/A mode
+ * @lag: primary lag struct
+ * @dest: index of destination port
+ * @e_pf: PF struct for event port
+ */
+void ice_lag_aa_failover(struct ice_lag *lag, u8 dest, struct ice_pf *e_pf)
+{
+	bool odd = true, all = false;
+	int i;
+
+	/* Primary can be a target if down (cleanup), but secondary can't */
+	if (dest == ICE_LAGS_IDX && !(lag->port_bitmap & ICE_LAGS_M))
+		return;
+
+	/* Move all queues to a destination if only one port is active,
+	 * or no ports are active and dest is primary.
+	 */
+	if ((lag->port_bitmap ^ (ICE_LAGP_M | ICE_LAGS_M)) ||
+	    (!lag->port_bitmap && dest == ICE_LAGP_IDX))
+		all = true;
+
+	ice_for_each_vsi(lag->pf, i)
+		if (lag->pf->vsi[i] && lag->pf->vsi[i]->type == ICE_VSI_VF)
+			ice_lag_aa_move_vf_qs(lag, dest, i, all, &odd, e_pf);
+}
+
+/**
  * ice_lag_reclaim_vf_tc - move scheduling nodes back to primary interface
  * @lag: primary interface lag struct
  * @src_hw: HW struct current node location
@@ -879,13 +1233,12 @@ ice_lag_reclaim_vf_tc(struct ice_lag *lag, struct ice_hw *src_hw, u16 vsi_num,
 	u16 numq, valq, num_moved, qbuf_size;
 	u16 buf_size = __struct_size(buf);
 	struct ice_aqc_cfg_txqs_buf *qbuf;
+	struct ice_hw *hw = &lag->pf->hw;
 	struct ice_sched_node *n_prt;
 	__le32 teid, parent_teid;
 	struct ice_vsi_ctx *ctx;
-	struct ice_hw *hw;
 	u32 tmp_teid;
 
-	hw = &lag->pf->hw;
 	ctx = ice_get_vsi_ctx(hw, vsi_num);
 	if (!ctx) {
 		dev_warn(dev, "Unable to locate VSI context for LAG reclaim\n");
@@ -926,7 +1279,7 @@ ice_lag_reclaim_vf_tc(struct ice_lag *lag, struct ice_hw *src_hw, u16 vsi_num,
 
 	if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq,
 			       src_hw->port_info->lport, hw->port_info->lport,
-			       NULL)) {
+			       ICE_AQC_Q_CFG_TC_CHNG, NULL)) {
 		dev_warn(dev, "Failure to configure queues for LAG failover\n");
 		goto reclaim_qerr;
 	}
@@ -997,14 +1350,15 @@ static void ice_lag_link(struct ice_lag *lag)
 
 	lag->bonded = true;
 	lag->role = ICE_LAG_UNSET;
+	lag->need_fltr_cfg = true;
 	netdev_info(lag->netdev, "Shared SR-IOV resources in bond are active\n");
 }
 
 /**
- * ice_lag_unlink - handle unlink event
+ * ice_lag_act_bkup_unlink - handle unlink event for A/B bond
  * @lag: LAG info struct
  */
-static void ice_lag_unlink(struct ice_lag *lag)
+static void ice_lag_act_bkup_unlink(struct ice_lag *lag)
 {
 	u8 pri_port, act_port, loc_port;
 	struct ice_pf *pf = lag->pf;
@@ -1021,6 +1375,9 @@ static void ice_lag_unlink(struct ice_lag *lag)
 			ice_lag_move_vf_nodes(lag, act_port, pri_port);
 		lag->primary = false;
 		lag->active_port = ICE_LAG_INVALID_PORT;
+
+		/* Config primary's eswitch back to normal operation. */
+		ice_lag_config_eswitch(lag, lag->netdev);
 	} else {
 		struct ice_lag *primary_lag;
 
@@ -1037,10 +1394,32 @@ static void ice_lag_unlink(struct ice_lag *lag)
 			}
 		}
 	}
+}
 
-	lag->bonded = false;
-	lag->role = ICE_LAG_NONE;
-	lag->upper_netdev = NULL;
+/**
+ * ice_lag_aa_unlink - handle unlink event for Active-Active bond
+ * @lag: LAG info struct
+ */
+static void ice_lag_aa_unlink(struct ice_lag *lag)
+{
+	struct ice_lag *pri_lag;
+
+	if (lag->primary) {
+		pri_lag = lag;
+		lag->port_bitmap &= ~ICE_LAGP_M;
+	} else {
+		pri_lag = ice_lag_find_primary(lag);
+		if (pri_lag)
+			pri_lag->port_bitmap &= ICE_LAGS_M;
+	}
+
+	if (pri_lag) {
+		ice_lag_aa_failover(pri_lag, ICE_LAGP_IDX, lag->pf);
+		if (lag->primary)
+			pri_lag->bond_lport_pri = ICE_LAG_INVALID_PORT;
+		else
+			pri_lag->bond_lport_sec = ICE_LAG_INVALID_PORT;
+	}
 }
 
 /**
@@ -1056,10 +1435,20 @@ static void ice_lag_link_unlink(struct ice_lag *lag, void *ptr)
 	if (netdev != lag->netdev)
 		return;
 
-	if (info->linking)
+	if (info->linking) {
 		ice_lag_link(lag);
-	else
-		ice_lag_unlink(lag);
+	} else {
+		if (lag->bond_aa)
+			ice_lag_aa_unlink(lag);
+		else
+			ice_lag_act_bkup_unlink(lag);
+
+		lag->bonded = false;
+		lag->role = ICE_LAG_NONE;
+		lag->upper_netdev = NULL;
+		lag->bond_aa = false;
+		lag->need_fltr_cfg = false;
+	}
 }
 
 /**
@@ -1077,7 +1466,7 @@ ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag,
 {
 	struct ice_aqc_alloc_free_res_elem *buf;
 	struct ice_aqc_set_port_params *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 buf_len, swid;
 	int status, i;
 
@@ -1125,7 +1514,7 @@ ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag,
 	else
 		swid = local_lag->pf->hw.port_info->sw_id;
 
-	cmd = &desc.params.set_port_params;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_params);
 
 	cmd->swid = cpu_to_le16(ICE_AQC_PORT_SWID_VALID | swid);
@@ -1157,11 +1546,8 @@ ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag,
  */
 static void ice_lag_primary_swid(struct ice_lag *lag, bool link)
 {
-	struct ice_hw *hw;
-	u16 swid;
-
-	hw = &lag->pf->hw;
-	swid = hw->port_info->sw_id;
+	struct ice_hw *hw = &lag->pf->hw;
+	u16 swid = hw->port_info->sw_id;
 
 	if (ice_share_res(hw, ICE_AQC_RES_TYPE_SWID, link, swid))
 		dev_warn(ice_pf_to_dev(lag->pf), "Failure to set primary interface shared status\n");
@@ -1174,12 +1560,10 @@ static void ice_lag_primary_swid(struct ice_lag *lag, bool link)
  */
 static void ice_lag_add_prune_list(struct ice_lag *lag, struct ice_pf *event_pf)
 {
-	u16 num_vsi, rule_buf_sz, vsi_list_id, event_vsi_num, prim_vsi_idx;
-	struct ice_sw_rule_vsi_list *s_rule = NULL;
+	u16 rule_buf_sz, vsi_list_id, event_vsi_num, prim_vsi_idx, num_vsi = 1;
+	struct ice_sw_rule_vsi_list *s_rule;
 	struct device *dev;
 
-	num_vsi = 1;
-
 	dev = ice_pf_to_dev(lag->pf);
 	event_vsi_num = event_pf->vsi[0]->vsi_num;
 	prim_vsi_idx = lag->pf->vsi[0]->idx;
@@ -1215,12 +1599,10 @@ static void ice_lag_add_prune_list(struct ice_lag *lag, struct ice_pf *event_pf)
  */
 static void ice_lag_del_prune_list(struct ice_lag *lag, struct ice_pf *event_pf)
 {
-	u16 num_vsi, vsi_num, vsi_idx, rule_buf_sz, vsi_list_id;
-	struct ice_sw_rule_vsi_list *s_rule = NULL;
+	u16 vsi_num, vsi_idx, rule_buf_sz, vsi_list_id, num_vsi = 1;
+	struct ice_sw_rule_vsi_list *s_rule;
 	struct device *dev;
 
-	num_vsi = 1;
-
 	dev = ice_pf_to_dev(lag->pf);
 	vsi_num = event_pf->vsi[0]->vsi_num;
 	vsi_idx = lag->pf->vsi[0]->idx;
@@ -1268,6 +1650,11 @@ static void ice_lag_init_feature_support_flag(struct ice_pf *pf)
 		ice_set_feature_support(pf, ICE_F_SRIOV_LAG);
 	else
 		ice_clear_feature_support(pf, ICE_F_SRIOV_LAG);
+
+	if (caps->sriov_aa_lag && ice_pkg_has_lport_extract(&pf->hw))
+		ice_set_feature_support(pf, ICE_F_SRIOV_AA_LAG);
+	else
+		ice_clear_feature_support(pf, ICE_F_SRIOV_AA_LAG);
 }
 
 /**
@@ -1277,11 +1664,10 @@ static void ice_lag_init_feature_support_flag(struct ice_pf *pf)
  */
 static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
 {
-	struct netdev_notifier_changeupper_info *info;
+	struct netdev_notifier_changeupper_info *info = ptr;
 	struct ice_lag *primary_lag;
 	struct net_device *netdev;
 
-	info = ptr;
 	netdev = netdev_notifier_info_to_dev(ptr);
 
 	/* not for this netdev */
@@ -1296,25 +1682,47 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
 		 */
 		if (!primary_lag) {
 			lag->primary = true;
+			if (!ice_is_switchdev_running(lag->pf))
+				return;
+
 			/* Configure primary's SWID to be shared */
 			ice_lag_primary_swid(lag, true);
 			primary_lag = lag;
+			lag->bond_lport_pri = lag->pf->hw.port_info->lport;
+			lag->bond_lport_sec = ICE_LAG_INVALID_PORT;
+			lag->port_bitmap = 0;
 		} else {
 			u16 swid;
 
+			if (!ice_is_switchdev_running(primary_lag->pf))
+				return;
+
 			swid = primary_lag->pf->hw.port_info->sw_id;
 			ice_lag_set_swid(swid, lag, true);
 			ice_lag_add_prune_list(primary_lag, lag->pf);
-			ice_lag_cfg_drop_fltr(lag, true);
+			primary_lag->bond_lport_sec =
+				lag->pf->hw.port_info->lport;
 		}
 		/* add filter for primary control packets */
-		ice_lag_cfg_cp_fltr(lag, true);
+		ice_lag_cfg_lp_fltr(lag, true, true);
 	} else {
 		if (!primary_lag && lag->primary)
 			primary_lag = lag;
 
+		if (primary_lag) {
+			for (int i = 0; i < ICE_MAX_SRIOV_VFS; i++) {
+				if (primary_lag->sec_vf[i]) {
+					ice_vsi_release(primary_lag->sec_vf[i]);
+					primary_lag->sec_vf[i] = NULL;
+				}
+			}
+		}
+
 		if (!lag->primary) {
 			ice_lag_set_swid(0, lag, false);
+			if (primary_lag)
+				primary_lag->bond_lport_sec =
+					ICE_LAG_INVALID_PORT;
 		} else {
 			if (primary_lag && lag->primary) {
 				ice_lag_primary_swid(lag, false);
@@ -1322,7 +1730,7 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
 			}
 		}
 		/* remove filter for control packets */
-		ice_lag_cfg_cp_fltr(lag, false);
+		ice_lag_cfg_lp_fltr(lag, false, !lag->bond_aa);
 	}
 }
 
@@ -1335,7 +1743,7 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
  */
 static void ice_lag_monitor_link(struct ice_lag *lag, void *ptr)
 {
-	struct netdev_notifier_changeupper_info *info;
+	struct netdev_notifier_changeupper_info *info = ptr;
 	struct ice_hw *prim_hw, *active_hw;
 	struct net_device *event_netdev;
 	struct ice_pf *pf;
@@ -1348,19 +1756,34 @@ static void ice_lag_monitor_link(struct ice_lag *lag, void *ptr)
 	if (!netif_is_same_ice(lag->pf, event_netdev))
 		return;
 
+	if (info->upper_dev != lag->upper_netdev)
+		return;
+
+	if (info->linking)
+		return;
+
 	pf = lag->pf;
 	prim_hw = &pf->hw;
 	prim_port = prim_hw->port_info->lport;
 
-	info = (struct netdev_notifier_changeupper_info *)ptr;
-	if (info->upper_dev != lag->upper_netdev)
-		return;
-
-	if (!info->linking) {
-		/* Since there are only two interfaces allowed in SRIOV+LAG, if
-		 * one port is leaving, then nodes need to be on primary
-		 * interface.
-		 */
+	/* Since there are only two interfaces allowed in SRIOV+LAG, if
+	 * one port is leaving, then nodes need to be on primary
+	 * interface.
+	 */
+	if (lag->bond_aa) {
+		struct ice_netdev_priv *e_ndp;
+		struct ice_pf *e_pf;
+
+		e_ndp = netdev_priv(event_netdev);
+		e_pf = e_ndp->vsi->back;
+
+		if (lag->bond_lport_pri != ICE_LAG_INVALID_PORT &&
+		    lag->port_bitmap & ICE_LAGS_M) {
+			lag->port_bitmap &= ~ICE_LAGS_M;
+			ice_lag_aa_failover(lag, ICE_LAGP_IDX, e_pf);
+			lag->bond_lport_sec = ICE_LAG_INVALID_PORT;
+		}
+	} else {
 		if (prim_port != lag->active_port &&
 		    lag->active_port != ICE_LAG_INVALID_PORT) {
 			active_hw = ice_lag_find_hw_by_lport(lag,
@@ -1372,45 +1795,32 @@ static void ice_lag_monitor_link(struct ice_lag *lag, void *ptr)
 }
 
 /**
- * ice_lag_monitor_active - main PF keep track of which port is active
+ * ice_lag_monitor_act_bkup - keep track of which port is active in A/B LAG
  * @lag: lag info struct
- * @ptr: opaque data containing notifier event
+ * @b_info: bonding info
+ * @event_netdev: net_device got target netdev
  *
  * This function is for the primary PF to monitor changes in which port is
  * active and handle changes for SRIOV VF functionality
  */
-static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
+static void ice_lag_monitor_act_bkup(struct ice_lag *lag,
+				     struct netdev_bonding_info *b_info,
+				     struct net_device *event_netdev)
 {
-	struct net_device *event_netdev, *event_upper;
-	struct netdev_notifier_bonding_info *info;
-	struct netdev_bonding_info *bonding_info;
 	struct ice_netdev_priv *event_np;
 	struct ice_pf *pf, *event_pf;
 	u8 prim_port, event_port;
 
-	if (!lag->primary)
-		return;
-
 	pf = lag->pf;
 	if (!pf)
 		return;
 
-	event_netdev = netdev_notifier_info_to_dev(ptr);
-	rcu_read_lock();
-	event_upper = netdev_master_upper_dev_get_rcu(event_netdev);
-	rcu_read_unlock();
-	if (!netif_is_ice(event_netdev) || event_upper != lag->upper_netdev)
-		return;
-
 	event_np = netdev_priv(event_netdev);
 	event_pf = event_np->vsi->back;
 	event_port = event_pf->hw.port_info->lport;
 	prim_port = pf->hw.port_info->lport;
 
-	info = (struct netdev_notifier_bonding_info *)ptr;
-	bonding_info = &info->bonding_info;
-
-	if (!bonding_info->slave.state) {
+	if (!b_info->slave.state) {
 		/* if no port is currently active, then nodes and filters exist
 		 * on primary port, check if we need to move them
 		 */
@@ -1419,6 +1829,7 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
 				ice_lag_move_vf_nodes(lag, prim_port,
 						      event_port);
 			lag->active_port = event_port;
+			ice_lag_config_eswitch(lag, event_netdev);
 			return;
 		}
 
@@ -1428,6 +1839,7 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
 		/* new active port */
 		ice_lag_move_vf_nodes(lag, lag->active_port, event_port);
 		lag->active_port = event_port;
+		ice_lag_config_eswitch(lag, event_netdev);
 	} else {
 		/* port not set as currently active (e.g. new active port
 		 * has already claimed the nodes and filters
@@ -1445,6 +1857,128 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
 }
 
 /**
+ * ice_lag_aa_clear_spoof - adjust the placeholder VSI spoofing for A/A LAG
+ * @vsi: placeholder VSI to adjust
+ */
+static void ice_lag_aa_clear_spoof(struct ice_vsi *vsi)
+{
+	ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof);
+}
+
+/**
+ * ice_lag_monitor_act_act - Keep track of active ports in A/A LAG
+ * @lag: lag struct for primary interface
+ * @b_info: bonding_info for event
+ * @event_netdev: net_device for target netdev
+ */
+static void ice_lag_monitor_act_act(struct ice_lag *lag,
+				    struct netdev_bonding_info *b_info,
+				    struct net_device *event_netdev)
+{
+	struct ice_netdev_priv *event_np;
+	u8 prim_port, event_port;
+	struct ice_pf *event_pf;
+
+	event_np = netdev_priv(event_netdev);
+	event_pf = event_np->vsi->back;
+	event_port = event_pf->hw.port_info->lport;
+	prim_port = lag->pf->hw.port_info->lport;
+
+	if (b_info->slave.link == BOND_LINK_UP) {
+		/* Port is coming up */
+		if (prim_port == event_port) {
+			/* Processing event for primary interface */
+			if (lag->bond_lport_pri == ICE_LAG_INVALID_PORT)
+				return;
+
+			if (!(lag->port_bitmap & ICE_LAGP_M)) {
+				/* Primary port was not marked up before, move
+				 * some|all VF queues to it and mark as up
+				 */
+				lag->port_bitmap |= ICE_LAGP_M;
+				ice_lag_aa_failover(lag, ICE_LAGP_IDX, event_pf);
+			}
+		} else {
+			if (lag->bond_lport_sec == ICE_LAG_INVALID_PORT)
+				return;
+
+			/* Create placeholder VSIs on secondary PF.
+			 * The placeholder is necessary so that we have
+			 * an element that represents the VF on the secondary
+			 * interface's scheduling tree.  This will be a tree
+			 * root for scheduling nodes when they are moved to
+			 * the secondary interface.
+			 */
+			if (!lag->sec_vf[0]) {
+				struct ice_vsi_cfg_params params = {};
+				struct ice_vsi *nvsi;
+				struct ice_vf *vf;
+				unsigned int bkt;
+
+				params.type = ICE_VSI_VF;
+				params.port_info = event_pf->hw.port_info;
+				params.flags = ICE_VSI_FLAG_INIT;
+
+				ice_for_each_vf(lag->pf, bkt, vf) {
+					params.vf = vf;
+					nvsi = ice_vsi_setup(event_pf,
+							     &params);
+					ice_lag_aa_clear_spoof(nvsi);
+					lag->sec_vf[vf->vf_id] = nvsi;
+				}
+			}
+
+			if (!(lag->port_bitmap & ICE_LAGS_M)) {
+				/* Secondary port was not marked up before,
+				 * move some|all VF queues to it and mark as up
+				 */
+				lag->port_bitmap |= ICE_LAGS_M;
+				ice_lag_aa_failover(lag, ICE_LAGS_IDX, event_pf);
+			}
+		}
+	} else {
+		/* Port is going down */
+		if (prim_port == event_port) {
+			lag->port_bitmap &= ~ICE_LAGP_M;
+			ice_lag_aa_failover(lag, ICE_LAGS_IDX, event_pf);
+		} else {
+			lag->port_bitmap &= ~ICE_LAGS_M;
+			ice_lag_aa_failover(lag, ICE_LAGP_IDX, event_pf);
+		}
+	}
+}
+
+/**
+ * ice_lag_monitor_info - Calls relevant A/A or A/B monitoring function
+ * @lag: lag info struct
+ * @ptr: opaque data containing notifier event
+ *
+ * This function is for the primary PF to monitor changes in which port is
+ * active and handle changes for SRIOV VF functionality
+ */
+static void ice_lag_monitor_info(struct ice_lag *lag, void *ptr)
+{
+	struct netdev_notifier_bonding_info *info = ptr;
+	struct net_device *event_netdev, *event_upper;
+	struct netdev_bonding_info *bonding_info;
+
+	if (!lag->primary)
+		return;
+
+	event_netdev = netdev_notifier_info_to_dev(ptr);
+	bonding_info = &info->bonding_info;
+	rcu_read_lock();
+	event_upper = netdev_master_upper_dev_get_rcu(event_netdev);
+	rcu_read_unlock();
+	if (!netif_is_ice(event_netdev) || event_upper != lag->upper_netdev)
+		return;
+
+	if (lag->bond_aa)
+		ice_lag_monitor_act_act(lag, bonding_info, event_netdev);
+	else
+		ice_lag_monitor_act_bkup(lag, bonding_info, event_netdev);
+}
+/**
  * ice_lag_chk_comp - evaluate bonded interface for feature support
  * @lag: lag info struct
  * @ptr: opaque data for netdev event info
@@ -1452,13 +1986,21 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
 static bool
 ice_lag_chk_comp(struct ice_lag *lag, void *ptr)
 {
+	struct netdev_notifier_bonding_info *info = ptr;
 	struct net_device *event_netdev, *event_upper;
-	struct netdev_notifier_bonding_info *info;
 	struct netdev_bonding_info *bonding_info;
 	struct list_head *tmp;
 	struct device *dev;
 	int count = 0;
 
+	/* All members need to know if bond A/A or A/B */
+	bonding_info = &info->bonding_info;
+	lag->bond_mode = bonding_info->master.bond_mode;
+	if (lag->bond_mode != BOND_MODE_ACTIVEBACKUP)
+		lag->bond_aa = true;
+	else
+		lag->bond_aa = false;
+
 	if (!lag->primary)
 		return true;
 
@@ -1479,13 +2021,9 @@ ice_lag_chk_comp(struct ice_lag *lag, void *ptr)
 		return false;
 	}
 
-	info = (struct netdev_notifier_bonding_info *)ptr;
-	bonding_info = &info->bonding_info;
-	lag->bond_mode = bonding_info->master.bond_mode;
-	if (lag->bond_mode != BOND_MODE_ACTIVEBACKUP) {
-		dev_info(dev, "Bond Mode not ACTIVE-BACKUP - VF LAG disabled\n");
+	if (lag->bond_aa && !ice_is_feature_supported(lag->pf,
+						      ICE_F_SRIOV_AA_LAG))
 		return false;
-	}
 
 	list_for_each(tmp, lag->netdev_head) {
 		struct ice_dcbx_cfg *dcb_cfg, *peer_dcb_cfg;
@@ -1589,10 +2127,9 @@ ice_lag_unregister(struct ice_lag *lag, struct net_device *event_netdev)
 static void
 ice_lag_monitor_rdma(struct ice_lag *lag, void *ptr)
 {
-	struct netdev_notifier_changeupper_info *info;
+	struct netdev_notifier_changeupper_info *info = ptr;
 	struct net_device *netdev;
 
-	info = ptr;
 	netdev = netdev_notifier_info_to_dev(ptr);
 
 	if (netdev != lag->netdev)
@@ -1640,12 +2177,29 @@ static void ice_lag_chk_disabled_bond(struct ice_lag *lag, void *ptr)
  */
 static void ice_lag_disable_sriov_bond(struct ice_lag *lag)
 {
-	struct ice_netdev_priv *np;
-	struct ice_pf *pf;
+	struct ice_pf *pf = ice_netdev_to_pf(lag->netdev);
 
-	np = netdev_priv(lag->netdev);
-	pf = np->vsi->back;
 	ice_clear_feature_support(pf, ICE_F_SRIOV_LAG);
+	ice_clear_feature_support(pf, ICE_F_SRIOV_AA_LAG);
+}
+
+/**
+ * ice_lag_preset_drop_fltr - preset drop filter for A/B bonds
+ * @lag: local lag struct
+ * @ptr: opaque data containing event
+ *
+ * Sets the initial drop filter for secondary interface in an
+ * active-backup bond
+ */
+static void ice_lag_preset_drop_fltr(struct ice_lag *lag, void *ptr)
+{
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+
+	if (netdev != lag->netdev || lag->primary || !lag->need_fltr_cfg)
+		return;
+
+	ice_lag_cfg_drop_fltr(lag, true);
+	lag->need_fltr_cfg = false;
 }
 
 /**
@@ -1686,10 +2240,12 @@ static void ice_lag_process_event(struct work_struct *work)
 				ice_lag_unregister(lag_work->lag, netdev);
 				goto lag_cleanup;
 			}
-			ice_lag_monitor_active(lag_work->lag,
-					       &lag_work->info.bonding_info);
 			ice_lag_cfg_pf_fltrs(lag_work->lag,
 					     &lag_work->info.bonding_info);
+			ice_lag_preset_drop_fltr(lag_work->lag,
+						 &lag_work->info.bonding_info);
+			ice_lag_monitor_info(lag_work->lag,
+					     &lag_work->info.bonding_info);
 		}
 		ice_lag_info_event(lag_work->lag, &lag_work->info.bonding_info);
 		break;
@@ -1762,9 +2318,8 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event,
 	lag_work->lag = lag;
 	lag_work->event = event;
 	if (event == NETDEV_CHANGEUPPER) {
-		struct netdev_notifier_changeupper_info *info;
+		struct netdev_notifier_changeupper_info *info = ptr;
 
-		info = ptr;
 		upper_netdev = info->upper_dev;
 	} else {
 		upper_netdev = netdev_master_upper_dev_get(netdev);
@@ -1814,10 +2369,8 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event,
  */
 static int ice_register_lag_handler(struct ice_lag *lag)
 {
+	struct notifier_block *notif_blk = &lag->notif_block;
 	struct device *dev = ice_pf_to_dev(lag->pf);
-	struct notifier_block *notif_blk;
-
-	notif_blk = &lag->notif_block;
 
 	if (!notif_blk->notifier_call) {
 		notif_blk->notifier_call = ice_lag_event_handler;
@@ -1837,10 +2390,9 @@ static int ice_register_lag_handler(struct ice_lag *lag)
  */
 static void ice_unregister_lag_handler(struct ice_lag *lag)
 {
+	struct notifier_block *notif_blk = &lag->notif_block;
 	struct device *dev = ice_pf_to_dev(lag->pf);
-	struct notifier_block *notif_blk;
 
-	notif_blk = &lag->notif_block;
 	if (notif_blk->notifier_call) {
 		unregister_netdevice_notifier(notif_blk);
 		dev_dbg(dev, "LAG event handler unregistered\n");
@@ -1902,13 +2454,12 @@ ice_lag_move_vf_nodes_tc_sync(struct ice_lag *lag, struct ice_hw *dest_hw,
 	u16 numq, valq, num_moved, qbuf_size;
 	u16 buf_size = __struct_size(buf);
 	struct ice_aqc_cfg_txqs_buf *qbuf;
+	struct ice_hw *hw = &lag->pf->hw;
 	struct ice_sched_node *n_prt;
 	__le32 teid, parent_teid;
 	struct ice_vsi_ctx *ctx;
-	struct ice_hw *hw;
 	u32 tmp_teid;
 
-	hw = &lag->pf->hw;
 	ctx = ice_get_vsi_ctx(hw, vsi_num);
 	if (!ctx) {
 		dev_warn(dev, "LAG rebuild failed after reset due to VSI Context failure\n");
@@ -1945,7 +2496,8 @@ ice_lag_move_vf_nodes_tc_sync(struct ice_lag *lag, struct ice_hw *dest_hw,
 	}
 
 	if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq, hw->port_info->lport,
-			       dest_hw->port_info->lport, NULL)) {
+			       dest_hw->port_info->lport,
+			       ICE_AQC_Q_CFG_TC_CHNG, NULL)) {
 		dev_warn(dev, "Failure to configure queues for LAG reset rebuild\n");
 		goto sync_qerr;
 	}
@@ -2041,9 +2593,13 @@ int ice_init_lag(struct ice_pf *pf)
 	lag->netdev = vsi->netdev;
 	lag->role = ICE_LAG_NONE;
 	lag->active_port = ICE_LAG_INVALID_PORT;
+	lag->port_bitmap = 0x0;
 	lag->bonded = false;
+	lag->bond_aa = false;
+	lag->need_fltr_cfg = false;
 	lag->upper_netdev = NULL;
 	lag->notif_block.notifier_call = NULL;
+	memset(lag->sec_vf, 0, sizeof(lag->sec_vf));
 
 	err = ice_register_lag_handler(lag);
 	if (err) {
@@ -2061,6 +2617,11 @@ int ice_init_lag(struct ice_pf *pf)
 	if (err)
 		goto free_rcp_res;
 
+	err = ice_create_lag_recipe(&pf->hw, &lag->act_act_recipe,
+				    ice_lport_rcp, 1);
+	if (err)
+		goto  free_lport_res;
+
 	/* associate recipes to profiles */
 	for (n = 0; n < ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER; n++) {
 		err = ice_aq_get_recipe_to_profile(&pf->hw, n,
@@ -2070,7 +2631,8 @@ int ice_init_lag(struct ice_pf *pf)
 
 		if (recipe_bits & BIT(ICE_SW_LKUP_DFLT)) {
 			recipe_bits |= BIT(lag->pf_recipe) |
-				       BIT(lag->lport_recipe);
+				       BIT(lag->lport_recipe) |
+				       BIT(lag->act_act_recipe);
 			ice_aq_map_recipe_to_profile(&pf->hw, n,
 						     recipe_bits, NULL);
 		}
@@ -2081,9 +2643,13 @@ int ice_init_lag(struct ice_pf *pf)
 	dev_dbg(dev, "INIT LAG complete\n");
 	return 0;
 
+free_lport_res:
+	ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1,
+			&lag->lport_recipe);
+
 free_rcp_res:
 	ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1,
-			&pf->lag->pf_recipe);
+			&lag->pf_recipe);
 lag_error:
 	kfree(lag);
 	pf->lag = NULL;
@@ -2099,9 +2665,7 @@ lag_error:
  */
 void ice_deinit_lag(struct ice_pf *pf)
 {
-	struct ice_lag *lag;
-
-	lag = pf->lag;
+	struct ice_lag *lag = pf->lag;
 
 	if (!lag)
 		return;
@@ -2170,11 +2734,15 @@ void ice_lag_rebuild(struct ice_pf *pf)
 			ice_lag_move_vf_nodes_sync(prim_lag, &pf->hw);
 	}
 
-	ice_lag_cfg_cp_fltr(lag, true);
+	if (!lag->bond_aa) {
+		ice_lag_cfg_lp_fltr(lag, true, true);
+		if (lag->pf_rx_rule_id)
+			if (ice_lag_cfg_dflt_fltr(lag, true))
+				dev_err(ice_pf_to_dev(pf), "Error adding default VSI rule in rebuild\n");
+	} else {
+		ice_lag_cfg_lp_fltr(lag, true, false);
+	}
 
-	if (lag->pf_rx_rule_id)
-		if (ice_lag_cfg_dflt_fltr(lag, true))
-			dev_err(ice_pf_to_dev(pf), "Error adding default VSI rule in rebuild\n");
 
 	ice_clear_rdma_cap(pf);
 lag_rebuild_out:
@@ -2193,7 +2761,8 @@ bool ice_lag_is_switchdev_running(struct ice_pf *pf)
 	struct ice_lag *lag = pf->lag;
 	struct net_device *tmp_nd;
 
-	if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) || !lag)
+	if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) ||
+	    !lag || !lag->upper_netdev)
 		return false;
 
 	rcu_read_lock();
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h
index bab2c83142a1..f77ebcd61042 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.h
+++ b/drivers/net/ethernet/intel/ice/ice_lag.h
@@ -14,7 +14,11 @@ enum ice_lag_role {
 	ICE_LAG_UNSET
 };
 
-#define ICE_LAG_INVALID_PORT 0xFF
+#define ICE_LAG_INVALID_PORT		0xFF
+#define ICE_LAGP_IDX			0
+#define ICE_LAGS_IDX			1
+#define ICE_LAGP_M			0x1
+#define ICE_LAGS_M			0x2
 
 #define ICE_LAG_RESET_RETRIES		5
 #define ICE_SW_DEFAULT_PROFILE		0
@@ -41,12 +45,26 @@ struct ice_lag {
 	u8 active_port; /* lport value for the current active port */
 	u8 bonded:1; /* currently bonded */
 	u8 primary:1; /* this is primary */
+	u8 bond_aa:1; /* is this bond active-active */
+	u8 need_fltr_cfg:1; /* fltrs for A/A bond still need to be make */
+	u8 port_bitmap:2; /* bitmap of active ports */
+	u8 bond_lport_pri; /* lport values for primary PF */
+	u8 bond_lport_sec; /* lport values for secondary PF */
+
+	/* q_home keeps track of which interface the q is currently on */
+	u8 q_home[ICE_MAX_SRIOV_VFS][ICE_MAX_RSS_QS_PER_VF];
+
+	/* placeholder VSI for hanging VF queues from on secondary interface */
+	struct ice_vsi *sec_vf[ICE_MAX_SRIOV_VFS];
+
 	u16 pf_recipe;
 	u16 lport_recipe;
+	u16 act_act_recipe;
 	u16 pf_rx_rule_id;
 	u16 pf_tx_rule_id;
 	u16 cp_rule_idx;
 	u16 lport_rule_idx;
+	u16 act_act_rule_idx;
 	u8 role;
 };
 
@@ -64,10 +82,12 @@ struct ice_lag_work {
 	} info;
 };
 
-void ice_lag_move_new_vf_nodes(struct ice_vf *vf);
+void ice_lag_aa_failover(struct ice_lag *lag, u8 dest, struct ice_pf *e_pf);
 int ice_init_lag(struct ice_pf *pf);
 void ice_deinit_lag(struct ice_pf *pf);
 void ice_lag_rebuild(struct ice_pf *pf);
 bool ice_lag_is_switchdev_running(struct ice_pf *pf);
 void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt);
+u8 ice_lag_prepare_vf_reset(struct ice_lag *lag);
+void ice_lag_complete_vf_reset(struct ice_lag *lag, u8 act_prt);
 #endif /* _ICE_LAG_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 1479b45738af..185672c7e17d 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -229,7 +229,7 @@ struct ice_32b_rx_flex_desc_nic {
 	__le16 status_error1;
 	u8 flexi_flags2;
 	u8 ts_low;
-	__le16 l2tag2_1st;
+	__le16 raw_csum;
 	__le16 l2tag2_2nd;
 
 	/* Qword 3 */
@@ -342,6 +342,9 @@ enum ice_flg64_bits {
 /* for ice_32byte_rx_flex_desc.pkt_length member */
 #define ICE_RX_FLX_DESC_PKT_LEN_M	(0x3FFF) /* 14-bits */
 
+/* ice_32byte_rx_flex_desc::hdr_len_sph_flex_flags1 */
+#define ICE_RX_FLEX_DESC_HDR_LEN_M	GENMASK(10, 0)
+
 enum ice_rx_flex_desc_status_error_0_bits {
 	/* Note: These are predefined bit offsets */
 	ICE_RX_FLEX_DESC_STATUS0_DD_S = 0,
@@ -478,10 +481,15 @@ enum ice_tx_desc_len_fields {
 struct ice_tx_ctx_desc {
 	__le32 tunneling_params;
 	__le16 l2tag2;
-	__le16 rsvd;
+	__le16 gcs;
 	__le64 qw1;
 };
 
+#define ICE_TX_GCS_DESC_START_M		GENMASK(7, 0)
+#define ICE_TX_GCS_DESC_OFFSET_M	GENMASK(11, 8)
+#define ICE_TX_GCS_DESC_TYPE_M		GENMASK(14, 12)
+#define ICE_TX_GCS_DESC_CSUM_PSH	1
+
 #define ICE_TXD_CTX_QW1_CMD_S	4
 #define ICE_TXD_CTX_QW1_CMD_M	(0x7FUL << ICE_TXD_CTX_QW1_CMD_S)
 
@@ -564,4 +572,45 @@ struct ice_tlan_ctx {
 	u8 pkt_shaper_prof_idx;
 };
 
+#define ICE_TXTIME_TX_DESC_IDX_M	GENMASK(12, 0)
+#define ICE_TXTIME_STAMP_M		GENMASK(31, 13)
+
+/* Tx time stamp descriptor */
+struct ice_ts_desc {
+	__le32 tx_desc_idx_tstamp;
+};
+
+#define ICE_TS_DESC(R, i) (&(((struct ice_ts_desc *)((R)->desc))[i]))
+
+#define ICE_TXTIME_MAX_QUEUE		2047
+#define ICE_SET_TXTIME_MAX_Q_AMOUNT	127
+#define ICE_TXTIME_FETCH_TS_DESC_DFLT	8
+#define ICE_TXTIME_FETCH_PROFILE_CNT	16
+
+/* Tx Time queue context data */
+struct ice_txtime_ctx {
+#define ICE_TXTIME_CTX_BASE_S		7
+	u64 base;			/* base is defined in 128-byte units */
+	u8 pf_num;
+	u16 vmvf_num;
+	u8 vmvf_type;
+	u16 src_vsi;
+	u8 cpuid;
+	u8 tphrd_desc;
+	u16 qlen;
+	u8 timer_num;
+	u8 txtime_ena_q;
+	u8 drbell_mode_32;
+#define ICE_TXTIME_CTX_DRBELL_MODE_32	1
+	u8 ts_res;
+#define ICE_TXTIME_CTX_RESOLUTION_128NS 7
+	u8 ts_round_type;
+	u8 ts_pacing_slot;
+#define ICE_TXTIME_CTX_FETCH_PROF_ID_0 0
+	u8 merging_ena;
+	u8 ts_fetch_prof_id;
+	u8 ts_fetch_cache_line_aln_thld;
+	u8 tx_pipe_delay_mode;
+};
+
 #endif /* _ICE_LAN_TX_RX_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index a7d45a8ce7ac..15621707fbf8 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -157,6 +157,16 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi)
 	}
 }
 
+static u16 ice_get_rxq_count(struct ice_pf *pf)
+{
+	return min(ice_get_avail_rxq_count(pf), num_online_cpus());
+}
+
+static u16 ice_get_txq_count(struct ice_pf *pf)
+{
+	return min(ice_get_avail_txq_count(pf), num_online_cpus());
+}
+
 /**
  * ice_vsi_set_num_qs - Set number of queues, descriptors and vectors for a VSI
  * @vsi: the VSI being configured
@@ -178,9 +188,7 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
 			vsi->alloc_txq = vsi->req_txq;
 			vsi->num_txq = vsi->req_txq;
 		} else {
-			vsi->alloc_txq = min3(pf->num_lan_msix,
-					      ice_get_avail_txq_count(pf),
-					      (u16)num_online_cpus());
+			vsi->alloc_txq = ice_get_txq_count(pf);
 		}
 
 		pf->num_lan_tx = vsi->alloc_txq;
@@ -193,17 +201,13 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
 				vsi->alloc_rxq = vsi->req_rxq;
 				vsi->num_rxq = vsi->req_rxq;
 			} else {
-				vsi->alloc_rxq = min3(pf->num_lan_msix,
-						      ice_get_avail_rxq_count(pf),
-						      (u16)num_online_cpus());
+				vsi->alloc_rxq = ice_get_rxq_count(pf);
 			}
 		}
 
 		pf->num_lan_rx = vsi->alloc_rxq;
 
-		vsi->num_q_vectors = min_t(int, pf->num_lan_msix,
-					   max_t(int, vsi->alloc_rxq,
-						 vsi->alloc_txq));
+		vsi->num_q_vectors = max(vsi->alloc_rxq, vsi->alloc_txq);
 		break;
 	case ICE_VSI_SF:
 		vsi->alloc_txq = 1;
@@ -480,8 +484,7 @@ static irqreturn_t ice_msix_clean_ctrl_vsi(int __always_unused irq, void *data)
 	if (!q_vector->tx.tx_ring)
 		return IRQ_HANDLED;
 
-#define FDIR_RX_DESC_CLEAN_BUDGET 64
-	ice_clean_rx_irq(q_vector->rx.rx_ring, FDIR_RX_DESC_CLEAN_BUDGET);
+	ice_clean_ctrl_rx_irq(q_vector->rx.rx_ring);
 	ice_clean_ctrl_tx_irq(q_vector->tx.tx_ring);
 
 	return IRQ_HANDLED;
@@ -567,6 +570,8 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch)
 			return -ENOMEM;
 	}
 
+	vsi->irq_dyn_alloc = pci_msix_can_alloc_dyn(vsi->back->pdev);
+
 	switch (vsi->type) {
 	case ICE_VSI_PF:
 	case ICE_VSI_SF:
@@ -827,7 +832,13 @@ bool ice_is_safe_mode(struct ice_pf *pf)
  */
 bool ice_is_rdma_ena(struct ice_pf *pf)
 {
-	return test_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+	union devlink_param_value value;
+	int err;
+
+	err = devl_param_driverinit_value_get(priv_to_devlink(pf),
+					      DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA,
+					      &value);
+	return err ? test_bit(ICE_FLAG_RDMA_ENA, pf->flags) : value.vbool;
 }
 
 /**
@@ -1173,12 +1184,11 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
 static void
 ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 {
-	struct ice_pf *pf = vsi->back;
 	u16 qcount, qmap;
 	u8 offset = 0;
 	int pow;
 
-	qcount = min_t(int, vsi->num_rxq, pf->num_lan_msix);
+	qcount = vsi->num_rxq;
 
 	pow = order_base_2(qcount);
 	qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset);
@@ -1417,9 +1427,12 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 		ring->reg_idx = vsi->rxq_map[i];
 		ring->vsi = vsi;
 		ring->netdev = vsi->netdev;
-		ring->dev = dev;
 		ring->count = vsi->num_rx_desc;
 		ring->cached_phctime = pf->ptp.cached_phc_time;
+
+		if (ice_is_feature_supported(pf, ICE_F_GCS))
+			ring->flags |= ICE_RX_FLAGS_RING_GCS;
+
 		WRITE_ONCE(vsi->rx_rings[i], ring);
 	}
 
@@ -1564,7 +1577,7 @@ static void ice_vsi_set_vf_rss_flow_fld(struct ice_vsi *vsi)
 		return;
 	}
 
-	status = ice_add_avf_rss_cfg(&pf->hw, vsi, ICE_DEFAULT_RSS_HENA);
+	status = ice_add_avf_rss_cfg(&pf->hw, vsi, ICE_DEFAULT_RSS_HASHCFG);
 	if (status)
 		dev_dbg(dev, "ice_add_avf_rss_cfg failed for vsi = %d, error = %d\n",
 			vsi->vsi_num, status);
@@ -1700,6 +1713,12 @@ bool ice_pf_state_is_nominal(struct ice_pf *pf)
 	return true;
 }
 
+#define ICE_FW_MODE_REC_M BIT(1)
+bool ice_is_recovery_mode(struct ice_hw *hw)
+{
+	return rd32(hw, GL_MNG_FWSM) & ICE_FW_MODE_REC_M;
+}
+
 /**
  * ice_update_eth_stats - Update VSI-specific ethernet statistics counters
  * @vsi: the VSI to be updated
@@ -1758,9 +1777,8 @@ void ice_update_eth_stats(struct ice_vsi *vsi)
  * @prio: priority for the RXDID for this queue
  * @ena_ts: true to enable timestamp and false to disable timestamp
  */
-void
-ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio,
-			bool ena_ts)
+void ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio,
+			     bool ena_ts)
 {
 	int regval = rd32(hw, QRXFLXP_CNTXT(pf_q));
 
@@ -2045,12 +2063,15 @@ static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi)
 }
 
 /**
- * ice_cfg_sw_lldp - Config switch rules for LLDP packet handling
+ * ice_vsi_cfg_sw_lldp - Config switch rules for LLDP packet handling
  * @vsi: the VSI being configured
  * @tx: bool to determine Tx or Rx rule
  * @create: bool to determine create or remove Rule
+ *
+ * Adding an ethtype Tx rule to the uplink VSI results in it being applied
+ * to the whole port, so LLDP transmission for VFs will be blocked too.
  */
-void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
+void ice_vsi_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
 {
 	int (*eth_fltr)(struct ice_vsi *v, u16 type, u16 flag,
 			enum ice_sw_fwd_act_type act);
@@ -2065,19 +2086,59 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
 		status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_TX,
 				  ICE_DROP_PACKET);
 	} else {
-		if (ice_fw_supports_lldp_fltr_ctrl(&pf->hw)) {
-			status = ice_lldp_fltr_add_remove(&pf->hw, vsi->vsi_num,
-							  create);
-		} else {
+		if (!test_bit(ICE_FLAG_LLDP_AQ_FLTR, pf->flags)) {
 			status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_RX,
 					  ICE_FWD_TO_VSI);
+			if (!status || !create)
+				goto report;
+
+			dev_info(dev,
+				 "Failed to add generic LLDP Rx filter on VSI %i error: %d, falling back to specialized AQ control\n",
+				 vsi->vsi_num, status);
 		}
+
+		status = ice_lldp_fltr_add_remove(&pf->hw, vsi, create);
+		if (!status)
+			set_bit(ICE_FLAG_LLDP_AQ_FLTR, pf->flags);
+
 	}
 
+report:
 	if (status)
-		dev_dbg(dev, "Fail %s %s LLDP rule on VSI %i error: %d\n",
-			create ? "adding" : "removing", tx ? "TX" : "RX",
-			vsi->vsi_num, status);
+		dev_warn(dev, "Failed to %s %s LLDP rule on VSI %i error: %d\n",
+			 create ? "add" : "remove", tx ? "Tx" : "Rx",
+			 vsi->vsi_num, status);
+}
+
+/**
+ * ice_cfg_sw_rx_lldp - Enable/disable software handling of LLDP
+ * @pf: the PF being configured
+ * @enable: enable or disable
+ *
+ * Configure switch rules to enable/disable LLDP handling by software
+ * across PF.
+ */
+void ice_cfg_sw_rx_lldp(struct ice_pf *pf, bool enable)
+{
+	struct ice_vsi *vsi;
+	struct ice_vf *vf;
+	unsigned int bkt;
+
+	vsi = ice_get_main_vsi(pf);
+	ice_vsi_cfg_sw_lldp(vsi, false, enable);
+
+	if (!test_bit(ICE_FLAG_SRIOV_ENA, pf->flags))
+		return;
+
+	ice_for_each_vf(pf, bkt, vf) {
+		vsi = ice_get_vf_vsi(vf);
+
+		if (WARN_ON(!vsi))
+			continue;
+
+		if (ice_vf_is_lldp_ena(vf))
+			ice_vsi_cfg_sw_lldp(vsi, false, enable);
+	}
 }
 
 /**
@@ -2508,7 +2569,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params)
 	if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF) {
 		ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX,
 				 ICE_DROP_PACKET);
-		ice_cfg_sw_lldp(vsi, true, true);
+		ice_vsi_cfg_sw_lldp(vsi, true, true);
 	}
 
 	if (!vsi->agg_node)
@@ -2576,7 +2637,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)
 		return;
 
 	vsi->irqs_ready = false;
-	ice_free_cpu_rx_rmap(vsi);
 
 	ice_for_each_q_vector(vsi, i) {
 		int irq_num;
@@ -2589,12 +2649,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)
 		      vsi->q_vectors[i]->num_ring_rx))
 			continue;
 
-		/* clear the affinity notifier in the IRQ descriptor */
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
-			irq_set_affinity_notifier(irq_num, NULL);
-
-		/* clear the affinity_hint in the IRQ descriptor */
-		irq_update_affinity_hint(irq_num, NULL);
 		synchronize_irq(irq_num);
 		devm_free_irq(ice_pf_to_dev(pf), irq_num, vsi->q_vectors[i]);
 	}
@@ -2714,7 +2768,6 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
  * @vsi: VSI pointer
  *
  * Associate queue[s] with napi for all vectors.
- * The caller must hold rtnl_lock.
  */
 void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
 {
@@ -2724,6 +2777,7 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
 	if (!netdev)
 		return;
 
+	ASSERT_RTNL();
 	ice_for_each_rxq(vsi, q_idx)
 		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX,
 				     &vsi->rx_rings[q_idx]->q_vector->napi);
@@ -2744,16 +2798,23 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
  * @vsi: VSI pointer
  *
  * Clear the association between all VSI queues queue[s] and napi.
- * The caller must hold rtnl_lock.
  */
 void ice_vsi_clear_napi_queues(struct ice_vsi *vsi)
 {
 	struct net_device *netdev = vsi->netdev;
-	int q_idx;
+	int q_idx, v_idx;
 
 	if (!netdev)
 		return;
 
+	ASSERT_RTNL();
+	/* Clear the NAPI's interrupt number */
+	ice_for_each_q_vector(vsi, v_idx) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
+
+		netif_napi_set_irq(&q_vector->napi, -1);
+	}
+
 	ice_for_each_txq(vsi, q_idx)
 		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL);
 
@@ -2805,9 +2866,11 @@ int ice_vsi_release(struct ice_vsi *vsi)
 	/* The Rx rule will only exist to remove if the LLDP FW
 	 * engine is currently stopped
 	 */
-	if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF &&
-	    !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
-		ice_cfg_sw_lldp(vsi, false, false);
+	if (!ice_is_safe_mode(pf) &&
+	    !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags) &&
+	    (vsi->type == ICE_VSI_PF || (vsi->type == ICE_VSI_VF &&
+	     ice_vf_is_lldp_ena(vsi->vf))))
+		ice_vsi_cfg_sw_lldp(vsi, false, false);
 
 	ice_vsi_decfg(vsi);
 
@@ -3135,7 +3198,7 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc)
 	if (!netdev)
 		return;
 
-	/* CHNL VSI doesn't have it's own netdev, hence, no netdev_tc */
+	/* CHNL VSI doesn't have its own netdev, hence, no netdev_tc */
 	if (vsi->type == ICE_VSI_CHNL)
 		return;
 
@@ -3672,20 +3735,20 @@ int ice_set_link(struct ice_vsi *vsi, bool ena)
 
 	status = ice_aq_set_link_restart_an(pi, ena, NULL);
 
-	/* if link is owned by manageability, FW will return ICE_AQ_RC_EMODE.
+	/* if link is owned by manageability, FW will return LIBIE_AQ_RC_EMODE.
 	 * this is not a fatal error, so print a warning message and return
 	 * a success code. Return an error if FW returns an error code other
-	 * than ICE_AQ_RC_EMODE
+	 * than LIBIE_AQ_RC_EMODE
 	 */
 	if (status == -EIO) {
-		if (hw->adminq.sq_last_status == ICE_AQ_RC_EMODE)
+		if (hw->adminq.sq_last_status == LIBIE_AQ_RC_EMODE)
 			dev_dbg(dev, "can't set link to %s, err %d aq_err %s. not fatal, continuing\n",
 				(ena ? "ON" : "OFF"), status,
-				ice_aq_str(hw->adminq.sq_last_status));
+				libie_aq_str(hw->adminq.sq_last_status));
 	} else if (status) {
 		dev_err(dev, "can't set link to %s, err %d aq_err %s\n",
 			(ena ? "ON" : "OFF"), status,
-			ice_aq_str(hw->adminq.sq_last_status));
+			libie_aq_str(hw->adminq.sq_last_status));
 		return status;
 	}
 
@@ -3876,15 +3939,18 @@ void ice_init_feature_support(struct ice_pf *pf)
 			ice_set_feature_support(pf, ICE_F_CGU);
 		if (ice_is_clock_mux_in_netlist(&pf->hw))
 			ice_set_feature_support(pf, ICE_F_SMA_CTRL);
-		if (ice_gnss_is_gps_present(&pf->hw))
+		if (ice_gnss_is_module_present(&pf->hw))
 			ice_set_feature_support(pf, ICE_F_GNSS);
 		break;
 	default:
 		break;
 	}
 
-	if (pf->hw.mac_type == ICE_MAC_E830)
+	if (pf->hw.mac_type == ICE_MAC_E830) {
 		ice_set_feature_support(pf, ICE_F_MBX_LIMIT);
+		ice_set_feature_support(pf, ICE_F_GCS);
+		ice_set_feature_support(pf, ICE_F_TXTIME);
+	}
 }
 
 /**
@@ -3931,24 +3997,6 @@ void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx)
 }
 
 /**
- * ice_vsi_ctx_set_allow_override - allow destination override on VSI
- * @ctx: pointer to VSI ctx structure
- */
-void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx)
-{
-	ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD;
-}
-
-/**
- * ice_vsi_ctx_clear_allow_override - turn off destination override on VSI
- * @ctx: pointer to VSI ctx structure
- */
-void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx)
-{
-	ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD;
-}
-
-/**
  * ice_vsi_update_local_lb - update sw block in VSI with local loopback bit
  * @vsi: pointer to VSI structure
  * @set: set or unset the bit
@@ -3972,3 +4020,38 @@ ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set)
 	vsi->info = ctx.info;
 	return 0;
 }
+
+/**
+ * ice_vsi_update_l2tsel - update l2tsel field for all Rx rings on this VSI
+ * @vsi: VSI used to update l2tsel on
+ * @l2tsel: l2tsel setting requested
+ *
+ * Use the l2tsel setting to update all of the Rx queue context bits for l2tsel.
+ * This will modify which descriptor field the first offloaded VLAN will be
+ * stripped into.
+ */
+void ice_vsi_update_l2tsel(struct ice_vsi *vsi, enum ice_l2tsel l2tsel)
+{
+	struct ice_hw *hw = &vsi->back->hw;
+	u32 l2tsel_bit;
+	int i;
+
+	if (l2tsel == ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG2_2ND)
+		l2tsel_bit = 0;
+	else
+		l2tsel_bit = BIT(ICE_L2TSEL_BIT_OFFSET);
+
+	for (i = 0; i < vsi->alloc_rxq; i++) {
+		u16 pfq = vsi->rxq_map[i];
+		u32 qrx_context_offset;
+		u32 regval;
+
+		qrx_context_offset =
+			QRX_CONTEXT(ICE_L2TSEL_QRX_CONTEXT_REG_IDX, pfq);
+
+		regval = rd32(hw, qrx_context_offset);
+		regval &= ~BIT(ICE_L2TSEL_BIT_OFFSET);
+		regval |= l2tsel_bit;
+		wr32(hw, qrx_context_offset, regval);
+	}
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 10d6fc479a32..2cb1eb98b9da 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -11,6 +11,13 @@
 #define ICE_VSI_FLAG_INIT	BIT(0)
 #define ICE_VSI_FLAG_NO_INIT	0
 
+#define ICE_L2TSEL_QRX_CONTEXT_REG_IDX	3
+#define ICE_L2TSEL_BIT_OFFSET		23
+enum ice_l2tsel {
+	ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG2_2ND,
+	ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG1,
+};
+
 const char *ice_vsi_type_str(enum ice_vsi_type vsi_type);
 
 bool ice_pf_state_is_nominal(struct ice_pf *pf);
@@ -29,7 +36,8 @@ ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 
 int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi);
 
-void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create);
+void ice_vsi_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create);
+void ice_cfg_sw_rx_lldp(struct ice_pf *pf, bool enable);
 
 int ice_set_link(struct ice_vsi *vsi, bool ena);
 
@@ -90,6 +98,7 @@ void ice_set_q_vector_intrl(struct ice_q_vector *q_vector);
 
 bool ice_is_safe_mode(struct ice_pf *pf);
 bool ice_is_rdma_ena(struct ice_pf *pf);
+bool ice_is_recovery_mode(struct ice_hw *hw);
 bool ice_is_dflt_vsi_in_use(struct ice_port_info *pi);
 bool ice_is_vsi_dflt_vsi(struct ice_vsi *vsi);
 int ice_set_dflt_vsi(struct ice_vsi *vsi);
@@ -104,10 +113,6 @@ ice_vsi_update_security(struct ice_vsi *vsi, void (*fill)(struct ice_vsi_ctx *))
 void ice_vsi_ctx_set_antispoof(struct ice_vsi_ctx *ctx);
 
 void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx);
-
-void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx);
-
-void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx);
 int ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set);
 int ice_vsi_add_vlan_zero(struct ice_vsi *vsi);
 int ice_vsi_del_vlan_zero(struct ice_vsi *vsi);
@@ -118,4 +123,5 @@ void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f);
 void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f);
 void ice_init_feature_support(struct ice_pf *pf);
 bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi);
+void ice_vsi_update_l2tsel(struct ice_vsi *vsi, enum ice_l2tsel l2tsel);
 #endif /* !_ICE_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 1701f7143f24..4bb68e7a00f5 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -37,7 +37,11 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation.";
 #define ICE_DDP_PKG_FILE	ICE_DDP_PKG_PATH "ice.pkg"
 
 MODULE_DESCRIPTION(DRV_SUMMARY);
+MODULE_IMPORT_NS("LIBETH");
+MODULE_IMPORT_NS("LIBETH_XDP");
 MODULE_IMPORT_NS("LIBIE");
+MODULE_IMPORT_NS("LIBIE_ADMINQ");
+MODULE_IMPORT_NS("LIBIE_FWLOG");
 MODULE_LICENSE("GPL v2");
 MODULE_FIRMWARE(ICE_DDP_PKG_FILE);
 
@@ -379,7 +383,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 		 * should go into promiscuous mode. There should be some
 		 * space reserved for promiscuous filters.
 		 */
-		if (hw->adminq.sq_last_status == ICE_AQ_RC_ENOSPC &&
+		if (hw->adminq.sq_last_status == LIBIE_AQ_RC_ENOSPC &&
 		    !test_and_set_bit(ICE_FLTR_OVERFLOW_PROMISC,
 				      vsi->state)) {
 			promisc_forced_on = true;
@@ -1119,7 +1123,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
 	if (status)
 		dev_dbg(dev, "Failed to update link status on port %d, err %d aq_err %s\n",
 			pi->lport, status,
-			ice_aq_str(pi->hw->adminq.sq_last_status));
+			libie_aq_str(pi->hw->adminq.sq_last_status));
 
 	ice_check_link_cfg_err(pf, pi->phy.link_info.link_cfg_err);
 
@@ -1144,7 +1148,10 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
 	if (link_up == old_link && link_speed == old_link_speed)
 		return 0;
 
-	ice_ptp_link_change(pf, pf->hw.pf_id, link_up);
+	if (!link_up && old_link)
+		pf->link_down_events++;
+
+	ice_ptp_link_change(pf, link_up);
 
 	if (ice_is_dcb_active(pf)) {
 		if (test_bit(ICE_FLAG_DCB_ENA, pf->flags))
@@ -1247,32 +1254,6 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event)
 }
 
 /**
- * ice_get_fwlog_data - copy the FW log data from ARQ event
- * @pf: PF that the FW log event is associated with
- * @event: event structure containing FW log data
- */
-static void
-ice_get_fwlog_data(struct ice_pf *pf, struct ice_rq_event_info *event)
-{
-	struct ice_fwlog_data *fwlog;
-	struct ice_hw *hw = &pf->hw;
-
-	fwlog = &hw->fwlog_ring.rings[hw->fwlog_ring.tail];
-
-	memset(fwlog->data, 0, PAGE_SIZE);
-	fwlog->data_size = le16_to_cpu(event->desc.datalen);
-
-	memcpy(fwlog->data, event->msg_buf, fwlog->data_size);
-	ice_fwlog_ring_increment(&hw->fwlog_ring.tail, hw->fwlog_ring.size);
-
-	if (ice_fwlog_ring_full(&hw->fwlog_ring)) {
-		/* the rings are full so bump the head to create room */
-		ice_fwlog_ring_increment(&hw->fwlog_ring.head,
-					 hw->fwlog_ring.size);
-	}
-}
-
-/**
  * ice_aq_prep_for_event - Prepare to wait for an AdminQ event from firmware
  * @pf: pointer to the PF private structure
  * @task: intermediate helper storage and identifier for waiting
@@ -1562,11 +1543,15 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 			}
 			break;
 		case ice_aqc_opc_fw_logs_event:
-			ice_get_fwlog_data(pf, &event);
+			libie_get_fwlog_data(&hw->fwlog, event.msg_buf,
+					     le16_to_cpu(event.desc.datalen));
 			break;
 		case ice_aqc_opc_lldp_set_mib_change:
 			ice_dcb_process_lldp_set_mib_change(pf, &event);
 			break;
+		case ice_aqc_opc_get_health_status:
+			ice_process_health_status_event(pf, &event);
+			break;
 		default:
 			dev_dbg(dev, "%s Receive Queue unknown event 0x%04x ignored\n",
 				qtype, opcode);
@@ -1714,7 +1699,7 @@ static int ice_service_task_stop(struct ice_pf *pf)
 	ret = test_and_set_bit(ICE_SERVICE_DIS, pf->state);
 
 	if (pf->serv_tmr.function)
-		del_timer_sync(&pf->serv_tmr);
+		timer_delete_sync(&pf->serv_tmr);
 	if (pf->serv_task.func)
 		cancel_work_sync(&pf->serv_task);
 
@@ -1740,7 +1725,7 @@ static void ice_service_task_restart(struct ice_pf *pf)
  */
 static void ice_service_timer(struct timer_list *t)
 {
-	struct ice_pf *pf = from_timer(pf, t, serv_tmr);
+	struct ice_pf *pf = timer_container_of(pf, t, serv_tmr);
 
 	mod_timer(&pf->serv_tmr, round_jiffies(pf->serv_tmr_period + jiffies));
 	ice_service_task_schedule(pf);
@@ -2361,6 +2346,18 @@ static void ice_check_media_subtask(struct ice_pf *pf)
 	}
 }
 
+static void ice_service_task_recovery_mode(struct work_struct *work)
+{
+	struct ice_pf *pf = container_of(work, struct ice_pf, serv_task);
+
+	set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state);
+	ice_clean_adminq_subtask(pf);
+
+	ice_service_task_complete(pf);
+
+	mod_timer(&pf->serv_tmr, jiffies + msecs_to_jiffies(100));
+}
+
 /**
  * ice_service_task - manage and run subtasks
  * @work: pointer to work_struct contained by the PF struct
@@ -2386,11 +2383,11 @@ static void ice_service_task(struct work_struct *work)
 	}
 
 	if (test_and_clear_bit(ICE_AUX_ERR_PENDING, pf->state)) {
-		struct iidc_event *event;
+		struct iidc_rdma_event *event;
 
 		event = kzalloc(sizeof(*event), GFP_KERNEL);
 		if (event) {
-			set_bit(IIDC_EVENT_CRIT_ERR, event->type);
+			set_bit(IIDC_RDMA_EVENT_CRIT_ERR, event->type);
 			/* report the entire OICR value to AUX driver */
 			swap(event->reg, pf->oicr_err_reg);
 			ice_send_event_to_aux(pf, event);
@@ -2409,11 +2406,11 @@ static void ice_service_task(struct work_struct *work)
 		ice_plug_aux_dev(pf);
 
 	if (test_and_clear_bit(ICE_FLAG_MTU_CHANGED, pf->flags)) {
-		struct iidc_event *event;
+		struct iidc_rdma_event *event;
 
 		event = kzalloc(sizeof(*event), GFP_KERNEL);
 		if (event) {
-			set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type);
+			set_bit(IIDC_RDMA_EVENT_AFTER_MTU_CHANGE, event->type);
 			ice_send_event_to_aux(pf, event);
 			kfree(event);
 		}
@@ -2513,34 +2510,6 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset)
 }
 
 /**
- * ice_irq_affinity_notify - Callback for affinity changes
- * @notify: context as to what irq was changed
- * @mask: the new affinity mask
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * so that we may register to receive changes to the irq affinity masks.
- */
-static void
-ice_irq_affinity_notify(struct irq_affinity_notify *notify,
-			const cpumask_t *mask)
-{
-	struct ice_q_vector *q_vector =
-		container_of(notify, struct ice_q_vector, affinity_notify);
-
-	cpumask_copy(&q_vector->affinity_mask, mask);
-}
-
-/**
- * ice_irq_affinity_release - Callback for affinity notifier release
- * @ref: internal core kernel usage
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * to inform the current notification subscriber that they will no longer
- * receive notifications.
- */
-static void ice_irq_affinity_release(struct kref __always_unused *ref) {}
-
-/**
  * ice_vsi_ena_irq - Enable IRQ for the given VSI
  * @vsi: the VSI being configured
  */
@@ -2603,19 +2572,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 				   err);
 			goto free_q_irqs;
 		}
-
-		/* register for affinity change notifications */
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL)) {
-			struct irq_affinity_notify *affinity_notify;
-
-			affinity_notify = &q_vector->affinity_notify;
-			affinity_notify->notify = ice_irq_affinity_notify;
-			affinity_notify->release = ice_irq_affinity_release;
-			irq_set_affinity_notifier(irq_num, affinity_notify);
-		}
-
-		/* assign the mask for this irq */
-		irq_update_affinity_hint(irq_num, &q_vector->affinity_mask);
 	}
 
 	err = ice_set_cpu_rx_rmap(vsi);
@@ -2631,9 +2587,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 free_q_irqs:
 	while (vector--) {
 		irq_num = vsi->q_vectors[vector]->irq.virq;
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
-			irq_set_affinity_notifier(irq_num, NULL);
-		irq_update_affinity_hint(irq_num, NULL);
 		devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]);
 	}
 	return err;
@@ -2770,6 +2723,27 @@ void ice_map_xdp_rings(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_unmap_xdp_rings - Unmap XDP rings from interrupt vectors
+ * @vsi: the VSI with XDP rings being unmapped
+ */
+static void ice_unmap_xdp_rings(struct ice_vsi *vsi)
+{
+	int v_idx;
+
+	ice_for_each_q_vector(vsi, v_idx) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
+		struct ice_tx_ring *ring;
+
+		ice_for_each_tx_ring(ring, q_vector->tx)
+			if (!ring->tx_buf || !ice_ring_is_xdp(ring))
+				break;
+
+		/* restore the value of last node prior to XDP setup */
+		q_vector->tx.tx_ring = ring;
+	}
+}
+
+/**
  * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP
  * @vsi: VSI to bring up Tx rings used by XDP
  * @prog: bpf program that will be assigned to VSI
@@ -2832,7 +2806,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
 	if (status) {
 		dev_err(dev, "Failed VSI LAN queue config for XDP, error: %d\n",
 			status);
-		goto clear_xdp_rings;
+		goto unmap_xdp_rings;
 	}
 
 	/* assign the prog only when it's not already present on VSI;
@@ -2848,6 +2822,8 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
 		ice_vsi_assign_bpf_prog(vsi, prog);
 
 	return 0;
+unmap_xdp_rings:
+	ice_unmap_xdp_rings(vsi);
 clear_xdp_rings:
 	ice_for_each_xdp_txq(vsi, i)
 		if (vsi->xdp_rings[i]) {
@@ -2864,6 +2840,8 @@ err_map_xdp:
 	mutex_unlock(&pf->avail_q_mutex);
 
 	devm_kfree(dev, vsi->xdp_rings);
+	vsi->xdp_rings = NULL;
+
 	return -ENOMEM;
 }
 
@@ -2879,7 +2857,7 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
 	struct ice_pf *pf = vsi->back;
-	int i, v_idx;
+	int i;
 
 	/* q_vectors are freed in reset path so there's no point in detaching
 	 * rings
@@ -2887,17 +2865,7 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type)
 	if (cfg_type == ICE_XDP_CFG_PART)
 		goto free_qmap;
 
-	ice_for_each_q_vector(vsi, v_idx) {
-		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
-		struct ice_tx_ring *ring;
-
-		ice_for_each_tx_ring(ring, q_vector->tx)
-			if (!ring->tx_buf || !ice_ring_is_xdp(ring))
-				break;
-
-		/* restore the value of last node prior to XDP setup */
-		q_vector->tx.tx_ring = ring;
-	}
+	ice_unmap_xdp_rings(vsi);
 
 free_qmap:
 	mutex_lock(&pf->avail_q_mutex);
@@ -2991,10 +2959,7 @@ int ice_vsi_determine_xdp_res(struct ice_vsi *vsi)
  */
 static int ice_max_xdp_frame_size(struct ice_vsi *vsi)
 {
-	if (test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags))
-		return ICE_RXBUF_1664;
-	else
-		return ICE_RXBUF_3072;
+	return ICE_RXBUF_3072;
 }
 
 /**
@@ -3042,28 +3007,24 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 		xdp_ring_err = ice_vsi_determine_xdp_res(vsi);
 		if (xdp_ring_err) {
 			NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP");
+			goto resume_if;
 		} else {
 			xdp_ring_err = ice_prepare_xdp_rings(vsi, prog,
 							     ICE_XDP_CFG_FULL);
-			if (xdp_ring_err)
+			if (xdp_ring_err) {
 				NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed");
+				goto resume_if;
+			}
 		}
 		xdp_features_set_redirect_target(vsi->netdev, true);
-		/* reallocate Rx queues that are used for zero-copy */
-		xdp_ring_err = ice_realloc_zc_buf(vsi, true);
-		if (xdp_ring_err)
-			NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed");
 	} else if (ice_is_xdp_ena_vsi(vsi) && !prog) {
 		xdp_features_clear_redirect_target(vsi->netdev);
 		xdp_ring_err = ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_FULL);
 		if (xdp_ring_err)
 			NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed");
-		/* reallocate Rx queues that were used for zero-copy */
-		xdp_ring_err = ice_realloc_zc_buf(vsi, false);
-		if (xdp_ring_err)
-			NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Rx resources failed");
 	}
 
+resume_if:
 	if (if_running)
 		ret = ice_up(vsi);
 
@@ -3182,12 +3143,14 @@ static irqreturn_t ice_ll_ts_intr(int __always_unused irq, void *data)
 	hw = &pf->hw;
 	tx = &pf->ptp.port.tx;
 	spin_lock_irqsave(&tx->lock, flags);
-	ice_ptp_complete_tx_single_tstamp(tx);
+	if (tx->init) {
+		ice_ptp_complete_tx_single_tstamp(tx);
 
-	idx = find_next_bit_wrap(tx->in_use, tx->len,
-				 tx->last_ll_ts_idx_read + 1);
-	if (idx != tx->len)
-		ice_ptp_req_tx_single_tstamp(tx, idx);
+		idx = find_next_bit_wrap(tx->in_use, tx->len,
+					 tx->last_ll_ts_idx_read + 1);
+		if (idx != tx->len)
+			ice_ptp_req_tx_single_tstamp(tx, idx);
+	}
 	spin_unlock_irqrestore(&tx->lock, flags);
 
 	val = GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M |
@@ -3289,22 +3252,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 
 	if (oicr & PFINT_OICR_TSYN_TX_M) {
 		ena_mask &= ~PFINT_OICR_TSYN_TX_M;
-		if (ice_pf_state_is_nominal(pf) &&
-		    pf->hw.dev_caps.ts_dev_info.ts_ll_int_read) {
-			struct ice_ptp_tx *tx = &pf->ptp.port.tx;
-			unsigned long flags;
-			u8 idx;
-
-			spin_lock_irqsave(&tx->lock, flags);
-			idx = find_next_bit_wrap(tx->in_use, tx->len,
-						 tx->last_ll_ts_idx_read + 1);
-			if (idx != tx->len)
-				ice_ptp_req_tx_single_tstamp(tx, idx);
-			spin_unlock_irqrestore(&tx->lock, flags);
-		} else if (ice_ptp_pf_handles_tx_interrupt(pf)) {
-			set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread);
-			ret = IRQ_WAKE_THREAD;
-		}
+
+		ret = ice_ptp_ts_irq(pf);
 	}
 
 	if (oicr & PFINT_OICR_TSYN_EVNT_M) {
@@ -3674,6 +3623,15 @@ void ice_set_netdev_features(struct net_device *netdev)
 	 */
 	netdev->hw_features |= NETIF_F_RXFCS;
 
+	/* Allow core to manage IRQs affinity */
+	netif_set_affinity_auto(netdev);
+
+	/* Mutual exclusivity for TSO and GCS is enforced by the set features
+	 * ndo callback.
+	 */
+	if (ice_is_feature_supported(pf, ICE_F_GCS))
+		netdev->hw_features |= NETIF_F_HW_CSUM;
+
 	netif_set_tso_max_size(netdev, ICE_MAX_TSO_SIZE);
 }
 
@@ -3982,9 +3940,10 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf)
  * ice_deinit_pf - Unrolls initialziations done by ice_init_pf
  * @pf: board private structure to initialize
  */
-static void ice_deinit_pf(struct ice_pf *pf)
+void ice_deinit_pf(struct ice_pf *pf)
 {
-	ice_service_task_stop(pf);
+	/* note that we unroll also on ice_init_pf() failure here */
+
 	mutex_destroy(&pf->lag_mutex);
 	mutex_destroy(&pf->adev_mutex);
 	mutex_destroy(&pf->sw_mutex);
@@ -4002,9 +3961,17 @@ static void ice_deinit_pf(struct ice_pf *pf)
 		pf->avail_rxqs = NULL;
 	}
 
+	if (pf->txtime_txqs) {
+		bitmap_free(pf->txtime_txqs);
+		pf->txtime_txqs = NULL;
+	}
+
 	if (pf->ptp.clock)
 		ptp_clock_unregister(pf->ptp.clock);
 
+	if (!xa_empty(&pf->irq_tracker.entries))
+		ice_free_irq_msix_misc(pf);
+
 	xa_destroy(&pf->dyn_ports);
 	xa_destroy(&pf->sf_nums);
 }
@@ -4051,21 +4018,32 @@ static void ice_set_pf_caps(struct ice_pf *pf)
 	}
 
 	clear_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
-	if (func_caps->common_cap.ieee_1588 &&
-	    !(pf->hw.mac_type == ICE_MAC_E830))
+	if (func_caps->common_cap.ieee_1588)
 		set_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
 
 	pf->max_pf_txqs = func_caps->common_cap.num_txq;
 	pf->max_pf_rxqs = func_caps->common_cap.num_rxq;
 }
 
+void ice_start_service_task(struct ice_pf *pf)
+{
+	timer_setup(&pf->serv_tmr, ice_service_timer, 0);
+	pf->serv_tmr_period = HZ;
+	INIT_WORK(&pf->serv_task, ice_service_task);
+	clear_bit(ICE_SERVICE_SCHED, pf->state);
+}
+
 /**
  * ice_init_pf - Initialize general software structures (struct ice_pf)
  * @pf: board private structure to initialize
+ * Return: 0 on success, negative errno otherwise.
  */
-static int ice_init_pf(struct ice_pf *pf)
+int ice_init_pf(struct ice_pf *pf)
 {
-	ice_set_pf_caps(pf);
+	struct udp_tunnel_nic_info *udp_tunnel_nic = &pf->hw.udp_tunnel_nic;
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_hw *hw = &pf->hw;
+	int err = -ENOMEM;
 
 	mutex_init(&pf->sw_mutex);
 	mutex_init(&pf->tc_mutex);
@@ -4078,23 +4056,7 @@ static int ice_init_pf(struct ice_pf *pf)
 
 	init_waitqueue_head(&pf->reset_wait_queue);
 
-	/* setup service timer and periodic service task */
-	timer_setup(&pf->serv_tmr, ice_service_timer, 0);
-	pf->serv_tmr_period = HZ;
-	INIT_WORK(&pf->serv_task, ice_service_task);
-	clear_bit(ICE_SERVICE_SCHED, pf->state);
-
 	mutex_init(&pf->avail_q_mutex);
-	pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL);
-	if (!pf->avail_txqs)
-		return -ENOMEM;
-
-	pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL);
-	if (!pf->avail_rxqs) {
-		bitmap_free(pf->avail_txqs);
-		pf->avail_txqs = NULL;
-		return -ENOMEM;
-	}
 
 	mutex_init(&pf->vfs.table_lock);
 	hash_init(pf->vfs.table);
@@ -4107,7 +4069,36 @@ static int ice_init_pf(struct ice_pf *pf)
 	xa_init(&pf->dyn_ports);
 	xa_init(&pf->sf_nums);
 
+	pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL);
+	pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL);
+	pf->txtime_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL);
+	if (!pf->avail_txqs || !pf->avail_rxqs || !pf->txtime_txqs)
+		goto undo_init;
+
+	udp_tunnel_nic->set_port = ice_udp_tunnel_set_port;
+	udp_tunnel_nic->unset_port = ice_udp_tunnel_unset_port;
+	udp_tunnel_nic->shared = &hw->udp_tunnel_shared;
+	udp_tunnel_nic->tables[0].n_entries = hw->tnl.valid_count[TNL_VXLAN];
+	udp_tunnel_nic->tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN;
+	udp_tunnel_nic->tables[1].n_entries = hw->tnl.valid_count[TNL_GENEVE];
+	udp_tunnel_nic->tables[1].tunnel_types = UDP_TUNNEL_TYPE_GENEVE;
+
+	/* In case of MSIX we are going to setup the misc vector right here
+	 * to handle admin queue events etc. In case of legacy and MSI
+	 * the misc functionality and queue processing is combined in
+	 * the same vector and that gets setup at open.
+	 */
+	err = ice_req_irq_msix_misc(pf);
+	if (err) {
+		dev_err(dev, "setup of misc vector failed: %d\n", err);
+		goto undo_init;
+	}
+
 	return 0;
+undo_init:
+	/* deinit handles half-initialized pf just fine */
+	ice_deinit_pf(pf);
+	return err;
 }
 
 /**
@@ -4237,7 +4228,7 @@ static void ice_set_safe_mode_vlan_cfg(struct ice_pf *pf)
 	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
 		dev_err(ice_pf_to_dev(vsi->back), "Failed to update VSI for safe mode VLANs, err %d aq_err %s\n",
-			status, ice_aq_str(hw->adminq.sq_last_status));
+			status, libie_aq_str(hw->adminq.sq_last_status));
 	} else {
 		vsi->info.sec_flags = ctxt->info.sec_flags;
 		vsi->info.sw_flags2 = ctxt->info.sw_flags2;
@@ -4548,17 +4539,23 @@ ice_init_tx_topology(struct ice_hw *hw, const struct firmware *firmware)
 			dev_info(dev, "Tx scheduling layers switching feature disabled\n");
 		else
 			dev_info(dev, "Tx scheduling layers switching feature enabled\n");
-		/* if there was a change in topology ice_cfg_tx_topo triggered
-		 * a CORER and we need to re-init hw
+		return 0;
+	} else if (err == -ENODEV) {
+		/* If we failed to re-initialize the device, we can no longer
+		 * continue loading.
 		 */
-		ice_deinit_hw(hw);
-		err = ice_init_hw(hw);
-
+		dev_warn(dev, "Failed to initialize hardware after applying Tx scheduling configuration.\n");
 		return err;
 	} else if (err == -EIO) {
 		dev_info(dev, "DDP package does not support Tx scheduling layers switching feature - please update to the latest DDP package and try again\n");
+		return 0;
+	} else if (err == -EEXIST) {
+		return 0;
 	}
 
+	/* Do not treat this as a fatal error. */
+	dev_info(dev, "Failed to apply Tx scheduling configuration, err %pe\n",
+		 ERR_PTR(err));
 	return 0;
 }
 
@@ -4658,19 +4655,6 @@ static void ice_print_wake_reason(struct ice_pf *pf)
 }
 
 /**
- * ice_pf_fwlog_update_module - update 1 module
- * @pf: pointer to the PF struct
- * @log_level: log_level to use for the @module
- * @module: module to update
- */
-void ice_pf_fwlog_update_module(struct ice_pf *pf, int log_level, int module)
-{
-	struct ice_hw *hw = &pf->hw;
-
-	hw->fwlog_cfg.module_entries[module].log_level = log_level;
-}
-
-/**
  * ice_register_netdev - register netdev
  * @vsi: pointer to the VSI struct
  */
@@ -4749,55 +4733,11 @@ static void ice_decfg_netdev(struct ice_vsi *vsi)
 	vsi->netdev = NULL;
 }
 
-/**
- * ice_wait_for_fw - wait for full FW readiness
- * @hw: pointer to the hardware structure
- * @timeout: milliseconds that can elapse before timing out
- */
-static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout)
-{
-	int fw_loading;
-	u32 elapsed = 0;
-
-	while (elapsed <= timeout) {
-		fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M;
-
-		/* firmware was not yet loaded, we have to wait more */
-		if (fw_loading) {
-			elapsed += 100;
-			msleep(100);
-			continue;
-		}
-		return 0;
-	}
-
-	return -ETIMEDOUT;
-}
-
-int ice_init_dev(struct ice_pf *pf)
+void ice_init_dev_hw(struct ice_pf *pf)
 {
-	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 	int err;
 
-	err = ice_init_hw(hw);
-	if (err) {
-		dev_err(dev, "ice_init_hw failed: %d\n", err);
-		return err;
-	}
-
-	/* Some cards require longer initialization times
-	 * due to necessity of loading FW from an external source.
-	 * This can take even half a minute.
-	 */
-	if (ice_is_pf_c827(hw)) {
-		err = ice_wait_for_fw(hw, 30000);
-		if (err) {
-			dev_err(dev, "ice_wait_for_fw timed out");
-			return err;
-		}
-	}
-
 	ice_init_feature_support(pf);
 
 	err = ice_init_ddp_config(hw, pf);
@@ -4814,64 +4754,28 @@ int ice_init_dev(struct ice_pf *pf)
 		 */
 		ice_set_safe_mode_caps(hw);
 	}
+}
 
-	err = ice_init_pf(pf);
-	if (err) {
-		dev_err(dev, "ice_init_pf failed: %d\n", err);
-		goto err_init_pf;
-	}
-
-	pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port;
-	pf->hw.udp_tunnel_nic.unset_port = ice_udp_tunnel_unset_port;
-	pf->hw.udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP;
-	pf->hw.udp_tunnel_nic.shared = &pf->hw.udp_tunnel_shared;
-	if (pf->hw.tnl.valid_count[TNL_VXLAN]) {
-		pf->hw.udp_tunnel_nic.tables[0].n_entries =
-			pf->hw.tnl.valid_count[TNL_VXLAN];
-		pf->hw.udp_tunnel_nic.tables[0].tunnel_types =
-			UDP_TUNNEL_TYPE_VXLAN;
-	}
-	if (pf->hw.tnl.valid_count[TNL_GENEVE]) {
-		pf->hw.udp_tunnel_nic.tables[1].n_entries =
-			pf->hw.tnl.valid_count[TNL_GENEVE];
-		pf->hw.udp_tunnel_nic.tables[1].tunnel_types =
-			UDP_TUNNEL_TYPE_GENEVE;
-	}
+int ice_init_dev(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	int err;
 
+	ice_set_pf_caps(pf);
 	err = ice_init_interrupt_scheme(pf);
 	if (err) {
 		dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err);
-		err = -EIO;
-		goto err_init_interrupt_scheme;
+		return -EIO;
 	}
 
-	/* In case of MSIX we are going to setup the misc vector right here
-	 * to handle admin queue events etc. In case of legacy and MSI
-	 * the misc functionality and queue processing is combined in
-	 * the same vector and that gets setup at open.
-	 */
-	err = ice_req_irq_msix_misc(pf);
-	if (err) {
-		dev_err(dev, "setup of misc vector failed: %d\n", err);
-		goto err_req_irq_msix_misc;
-	}
+	ice_start_service_task(pf);
 
 	return 0;
-
-err_req_irq_msix_misc:
-	ice_clear_interrupt_scheme(pf);
-err_init_interrupt_scheme:
-	ice_deinit_pf(pf);
-err_init_pf:
-	ice_deinit_hw(hw);
-	return err;
 }
 
 void ice_deinit_dev(struct ice_pf *pf)
 {
-	ice_free_irq_msix_misc(pf);
-	ice_deinit_pf(pf);
-	ice_deinit_hw(&pf->hw);
+	ice_service_task_stop(pf);
 
 	/* Service task is already stopped, so call reset directly. */
 	ice_reset(&pf->hw, ICE_RESET_PFR);
@@ -5095,31 +4999,40 @@ static int ice_init_devlink(struct ice_pf *pf)
 		return err;
 
 	ice_devlink_init_regions(pf);
-	ice_health_init(pf);
 	ice_devlink_register(pf);
+	ice_health_init(pf);
 
 	return 0;
 }
 
 static void ice_deinit_devlink(struct ice_pf *pf)
 {
-	ice_devlink_unregister(pf);
 	ice_health_deinit(pf);
+	ice_devlink_unregister(pf);
 	ice_devlink_destroy_regions(pf);
 	ice_devlink_unregister_params(pf);
 }
 
 static int ice_init(struct ice_pf *pf)
 {
+	struct device *dev = ice_pf_to_dev(pf);
 	int err;
 
-	err = ice_init_dev(pf);
-	if (err)
+	err = ice_init_pf(pf);
+	if (err) {
+		dev_err(dev, "ice_init_pf failed: %d\n", err);
 		return err;
+	}
+
+	if (pf->hw.mac_type == ICE_MAC_E830) {
+		err = pci_enable_ptm(pf->pdev, NULL);
+		if (err)
+			dev_dbg(dev, "PCIe PTM not supported by PCIe bus/controller\n");
+	}
 
 	err = ice_alloc_vsis(pf);
 	if (err)
-		goto err_alloc_vsis;
+		goto unroll_pf_init;
 
 	err = ice_init_pf_sw(pf);
 	if (err)
@@ -5156,8 +5069,8 @@ err_init_link:
 	ice_deinit_pf_sw(pf);
 err_init_pf_sw:
 	ice_dealloc_vsis(pf);
-err_alloc_vsis:
-	ice_deinit_dev(pf);
+unroll_pf_init:
+	ice_deinit_pf(pf);
 	return err;
 }
 
@@ -5168,7 +5081,7 @@ static void ice_deinit(struct ice_pf *pf)
 
 	ice_deinit_pf_sw(pf);
 	ice_dealloc_vsis(pf);
-	ice_deinit_dev(pf);
+	ice_deinit_pf(pf);
 }
 
 /**
@@ -5216,11 +5129,12 @@ int ice_load(struct ice_pf *pf)
 
 	ice_napi_add(vsi);
 
+	ice_init_features(pf);
+
 	err = ice_init_rdma(pf);
 	if (err)
 		goto err_init_rdma;
 
-	ice_init_features(pf);
 	ice_service_task_restart(pf);
 
 	clear_bit(ICE_DOWN, pf->state);
@@ -5228,6 +5142,7 @@ int ice_load(struct ice_pf *pf)
 	return 0;
 
 err_init_rdma:
+	ice_deinit_features(pf);
 	ice_tc_indir_block_unregister(vsi);
 err_tc_indir_block_register:
 	ice_unregister_netdev(vsi);
@@ -5251,14 +5166,44 @@ void ice_unload(struct ice_pf *pf)
 
 	devl_assert_locked(priv_to_devlink(pf));
 
-	ice_deinit_features(pf);
 	ice_deinit_rdma(pf);
+	ice_deinit_features(pf);
 	ice_tc_indir_block_unregister(vsi);
 	ice_unregister_netdev(vsi);
 	ice_devlink_destroy_pf_port(pf);
 	ice_decfg_netdev(vsi);
 }
 
+static int ice_probe_recovery_mode(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	int err;
+
+	dev_err(dev, "Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode\n");
+
+	INIT_HLIST_HEAD(&pf->aq_wait_list);
+	spin_lock_init(&pf->aq_wait_lock);
+	init_waitqueue_head(&pf->aq_wait_queue);
+
+	timer_setup(&pf->serv_tmr, ice_service_timer, 0);
+	pf->serv_tmr_period = HZ;
+	INIT_WORK(&pf->serv_task, ice_service_task_recovery_mode);
+	clear_bit(ICE_SERVICE_SCHED, pf->state);
+	err = ice_create_all_ctrlq(&pf->hw);
+	if (err)
+		return err;
+
+	scoped_guard(devl, priv_to_devlink(pf)) {
+		err = ice_init_devlink(pf);
+		if (err)
+			return err;
+	}
+
+	ice_service_task_restart(pf);
+
+	return 0;
+}
+
 /**
  * ice_probe - Device initialization routine
  * @pdev: PCI device information struct
@@ -5270,6 +5215,7 @@ static int
 ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 {
 	struct device *dev = &pdev->dev;
+	bool need_dev_deinit = false;
 	struct ice_adapter *adapter;
 	struct ice_pf *pf;
 	struct ice_hw *hw;
@@ -5322,13 +5268,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	}
 
 	pci_set_master(pdev);
-
-	adapter = ice_adapter_get(pdev);
-	if (IS_ERR(adapter))
-		return PTR_ERR(adapter);
-
 	pf->pdev = pdev;
-	pf->adapter = adapter;
 	pci_set_drvdata(pdev, pf);
 	set_bit(ICE_DOWN, pf->state);
 	/* Disable service task until DOWN bit is cleared */
@@ -5356,29 +5296,55 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 		hw->debug_mask = debug;
 #endif
 
+	if (ice_is_recovery_mode(hw))
+		return ice_probe_recovery_mode(pf);
+
+	err = ice_init_hw(hw);
+	if (err) {
+		dev_err(dev, "ice_init_hw failed: %d\n", err);
+		return err;
+	}
+
+	adapter = ice_adapter_get(pdev);
+	if (IS_ERR(adapter)) {
+		err = PTR_ERR(adapter);
+		goto unroll_hw_init;
+	}
+	pf->adapter = adapter;
+
+	err = ice_init_dev(pf);
+	if (err)
+		goto unroll_adapter;
+
 	err = ice_init(pf);
 	if (err)
-		goto err_init;
+		goto unroll_dev_init;
 
 	devl_lock(priv_to_devlink(pf));
 	err = ice_load(pf);
 	if (err)
-		goto err_load;
+		goto unroll_init;
 
 	err = ice_init_devlink(pf);
 	if (err)
-		goto err_init_devlink;
+		goto unroll_load;
 	devl_unlock(priv_to_devlink(pf));
 
 	return 0;
 
-err_init_devlink:
+unroll_load:
 	ice_unload(pf);
-err_load:
+unroll_init:
 	devl_unlock(priv_to_devlink(pf));
 	ice_deinit(pf);
-err_init:
+unroll_dev_init:
+	need_dev_deinit = true;
+unroll_adapter:
 	ice_adapter_put(pdev);
+unroll_hw_init:
+	ice_deinit_hw(hw);
+	if (need_dev_deinit)
+		ice_deinit_dev(pf);
 	return err;
 }
 
@@ -5440,7 +5406,7 @@ static void ice_setup_mc_magic_wake(struct ice_pf *pf)
 	status = ice_aq_manage_mac_write(hw, mac_addr, flags, NULL);
 	if (status)
 		dev_err(dev, "Failed to enable Multicast Magic Packet wake, err %d aq_err %s\n",
-			status, ice_aq_str(hw->adminq.sq_last_status));
+			status, libie_aq_str(hw->adminq.sq_last_status));
 }
 
 /**
@@ -5458,6 +5424,14 @@ static void ice_remove(struct pci_dev *pdev)
 		msleep(100);
 	}
 
+	if (ice_is_recovery_mode(&pf->hw)) {
+		ice_service_task_stop(pf);
+		scoped_guard(devl, priv_to_devlink(pf)) {
+			ice_deinit_devlink(pf);
+		}
+		return;
+	}
+
 	if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) {
 		set_bit(ICE_VF_RESETS_DISABLED, pf->state);
 		ice_free_vfs(pf);
@@ -5465,10 +5439,6 @@ static void ice_remove(struct pci_dev *pdev)
 
 	ice_hwmon_exit(pf);
 
-	ice_service_task_stop(pf);
-	ice_aq_cancel_waiting_tasks(pf);
-	set_bit(ICE_DOWN, pf->state);
-
 	if (!ice_is_safe_mode(pf))
 		ice_remove_arfs(pf);
 
@@ -5486,6 +5456,11 @@ static void ice_remove(struct pci_dev *pdev)
 	ice_set_wake(pf);
 
 	ice_adapter_put(pdev);
+	ice_deinit_hw(&pf->hw);
+
+	ice_deinit_dev(pf);
+	ice_aq_cancel_waiting_tasks(pf);
+	set_bit(ICE_DOWN, pf->state);
 }
 
 /**
@@ -5678,7 +5653,6 @@ static int ice_resume(struct device *dev)
 
 	pci_set_power_state(pdev, PCI_D0);
 	pci_restore_state(pdev);
-	pci_save_state(pdev);
 
 	if (!pci_device_is_present(pdev))
 		return -ENODEV;
@@ -5778,7 +5752,6 @@ static pci_ers_result_t ice_pci_err_slot_reset(struct pci_dev *pdev)
 	} else {
 		pci_set_master(pdev);
 		pci_restore_state(pdev);
-		pci_save_state(pdev);
 		pci_wake_from_d3(pdev, false);
 
 		/* Check for life */
@@ -5898,6 +5871,15 @@ static const struct pci_device_id ice_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_QSFP), },
 	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_SFP), },
 	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_SFP), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E835CC_BACKPLANE), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E835CC_QSFP56), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E835CC_SFP), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E835C_BACKPLANE), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E835C_QSFP), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E835C_SFP), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E835_L_BACKPLANE), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E835_L_QSFP), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E835_L_SFP), },
 	/* required last entry */
 	{}
 };
@@ -6577,6 +6559,18 @@ ice_set_features(struct net_device *netdev, netdev_features_t features)
 	if (changed & NETIF_F_LOOPBACK)
 		ret = ice_set_loopback(vsi, !!(features & NETIF_F_LOOPBACK));
 
+	/* Due to E830 hardware limitations, TSO (NETIF_F_ALL_TSO) with GCS
+	 * (NETIF_F_HW_CSUM) is not supported.
+	 */
+	if (ice_is_feature_supported(pf, ICE_F_GCS) &&
+	    ((features & NETIF_F_HW_CSUM) && (features & NETIF_F_ALL_TSO))) {
+		if (netdev->features & NETIF_F_HW_CSUM)
+			dev_err(ice_pf_to_dev(pf), "To enable TSO, you must first disable HW checksum.\n");
+		else
+			dev_err(ice_pf_to_dev(pf), "To enable HW checksum, you must first disable TSO.\n");
+		return -EIO;
+	}
+
 	return ret;
 }
 
@@ -6800,7 +6794,7 @@ static int ice_up_complete(struct ice_vsi *vsi)
 		ice_print_link_msg(vsi, true);
 		netif_tx_start_all_queues(vsi->netdev);
 		netif_carrier_on(vsi->netdev);
-		ice_ptp_link_change(pf, pf->hw.pf_id, true);
+		ice_ptp_link_change(pf, true);
 	}
 
 	/* Perform an initial read of the statistics registers now to
@@ -7132,6 +7126,9 @@ void ice_update_pf_stats(struct ice_pf *pf)
 			  &prev_ps->mac_remote_faults,
 			  &cur_ps->mac_remote_faults);
 
+	ice_stat_update32(hw, GLPRT_RLEC(port), pf->stat_prev_loaded,
+			  &prev_ps->rx_len_errors, &cur_ps->rx_len_errors);
+
 	ice_stat_update32(hw, GLPRT_RUC(port), pf->stat_prev_loaded,
 			  &prev_ps->rx_undersize, &cur_ps->rx_undersize);
 
@@ -7270,7 +7267,7 @@ int ice_down(struct ice_vsi *vsi)
 
 	if (vsi->netdev) {
 		vlan_err = ice_vsi_del_vlan_zero(vsi);
-		ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false);
+		ice_ptp_link_change(vsi->back, false);
 		netif_carrier_off(vsi->netdev);
 		netif_tx_disable(vsi->netdev);
 	}
@@ -7492,7 +7489,8 @@ int ice_vsi_open(struct ice_vsi *vsi)
 	if (err)
 		goto err_setup_rx;
 
-	ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc);
+	if (bitmap_empty(pf->txtime_txqs, pf->max_pf_txqs))
+		ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc);
 
 	if (vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_SF) {
 		/* Notify the stack of the actual queue counts. */
@@ -7855,12 +7853,6 @@ int ice_change_mtu(struct net_device *netdev, int new_mtu)
 				   frame_size - ICE_ETH_PKT_HDR_PAD);
 			return -EINVAL;
 		}
-	} else if (test_bit(ICE_FLAG_LEGACY_RX, pf->flags)) {
-		if (new_mtu + ICE_ETH_PKT_HDR_PAD > ICE_MAX_FRAME_LEGACY_RX) {
-			netdev_err(netdev, "Too big MTU for legacy-rx; Max is %d\n",
-				   ICE_MAX_FRAME_LEGACY_RX - ICE_ETH_PKT_HDR_PAD);
-			return -EINVAL;
-		}
 	}
 
 	/* if a reset is in progress, wait for some time for it to complete */
@@ -7891,69 +7883,6 @@ int ice_change_mtu(struct net_device *netdev, int new_mtu)
 }
 
 /**
- * ice_eth_ioctl - Access the hwtstamp interface
- * @netdev: network interface device structure
- * @ifr: interface request data
- * @cmd: ioctl command
- */
-static int ice_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
-{
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_pf *pf = np->vsi->back;
-
-	switch (cmd) {
-	case SIOCGHWTSTAMP:
-		return ice_ptp_get_ts_config(pf, ifr);
-	case SIOCSHWTSTAMP:
-		return ice_ptp_set_ts_config(pf, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-/**
- * ice_aq_str - convert AQ err code to a string
- * @aq_err: the AQ error code to convert
- */
-const char *ice_aq_str(enum ice_aq_err aq_err)
-{
-	switch (aq_err) {
-	case ICE_AQ_RC_OK:
-		return "OK";
-	case ICE_AQ_RC_EPERM:
-		return "ICE_AQ_RC_EPERM";
-	case ICE_AQ_RC_ENOENT:
-		return "ICE_AQ_RC_ENOENT";
-	case ICE_AQ_RC_ENOMEM:
-		return "ICE_AQ_RC_ENOMEM";
-	case ICE_AQ_RC_EBUSY:
-		return "ICE_AQ_RC_EBUSY";
-	case ICE_AQ_RC_EEXIST:
-		return "ICE_AQ_RC_EEXIST";
-	case ICE_AQ_RC_EINVAL:
-		return "ICE_AQ_RC_EINVAL";
-	case ICE_AQ_RC_ENOSPC:
-		return "ICE_AQ_RC_ENOSPC";
-	case ICE_AQ_RC_ENOSYS:
-		return "ICE_AQ_RC_ENOSYS";
-	case ICE_AQ_RC_EMODE:
-		return "ICE_AQ_RC_EMODE";
-	case ICE_AQ_RC_ENOSEC:
-		return "ICE_AQ_RC_ENOSEC";
-	case ICE_AQ_RC_EBADSIG:
-		return "ICE_AQ_RC_EBADSIG";
-	case ICE_AQ_RC_ESVN:
-		return "ICE_AQ_RC_ESVN";
-	case ICE_AQ_RC_EBADMAN:
-		return "ICE_AQ_RC_EBADMAN";
-	case ICE_AQ_RC_EBADBUF:
-		return "ICE_AQ_RC_EBADBUF";
-	}
-
-	return "ICE_AQ_RC_UNKNOWN";
-}
-
-/**
  * ice_set_rss_lut - Set RSS LUT
  * @vsi: Pointer to VSI structure
  * @lut: Lookup table
@@ -7978,7 +7907,7 @@ int ice_set_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size)
 	status = ice_aq_set_rss_lut(hw, &params);
 	if (status)
 		dev_err(ice_pf_to_dev(vsi->back), "Cannot set RSS lut, err %d aq_err %s\n",
-			status, ice_aq_str(hw->adminq.sq_last_status));
+			status, libie_aq_str(hw->adminq.sq_last_status));
 
 	return status;
 }
@@ -8001,7 +7930,7 @@ int ice_set_rss_key(struct ice_vsi *vsi, u8 *seed)
 	status = ice_aq_set_rss_key(hw, vsi->idx, (struct ice_aqc_get_set_rss_keys *)seed);
 	if (status)
 		dev_err(ice_pf_to_dev(vsi->back), "Cannot set RSS key, err %d aq_err %s\n",
-			status, ice_aq_str(hw->adminq.sq_last_status));
+			status, libie_aq_str(hw->adminq.sq_last_status));
 
 	return status;
 }
@@ -8031,7 +7960,7 @@ int ice_get_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size)
 	status = ice_aq_get_rss_lut(hw, &params);
 	if (status)
 		dev_err(ice_pf_to_dev(vsi->back), "Cannot get RSS lut, err %d aq_err %s\n",
-			status, ice_aq_str(hw->adminq.sq_last_status));
+			status, libie_aq_str(hw->adminq.sq_last_status));
 
 	return status;
 }
@@ -8054,7 +7983,7 @@ int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed)
 	status = ice_aq_get_rss_key(hw, vsi->idx, (struct ice_aqc_get_set_rss_keys *)seed);
 	if (status)
 		dev_err(ice_pf_to_dev(vsi->back), "Cannot get RSS key, err %d aq_err %s\n",
-			status, ice_aq_str(hw->adminq.sq_last_status));
+			status, libie_aq_str(hw->adminq.sq_last_status));
 
 	return status;
 }
@@ -8127,9 +8056,7 @@ static int
 ice_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 		   struct net_device *dev, u32 filter_mask, int nlflags)
 {
-	struct ice_netdev_priv *np = netdev_priv(dev);
-	struct ice_vsi *vsi = np->vsi;
-	struct ice_pf *pf = vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(dev);
 	u16 bmode;
 
 	bmode = pf->first_sw->bridge_mode;
@@ -8171,7 +8098,7 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
 	ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (ret) {
 		dev_err(ice_pf_to_dev(vsi->back), "update VSI for bridge mode failed, bmode = %d err %d aq_err %s\n",
-			bmode, ret, ice_aq_str(hw->adminq.sq_last_status));
+			bmode, ret, libie_aq_str(hw->adminq.sq_last_status));
 		goto out;
 	}
 	/* Update sw flags for book keeping */
@@ -8199,8 +8126,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 		   u16 __always_unused flags,
 		   struct netlink_ext_ack __always_unused *extack)
 {
-	struct ice_netdev_priv *np = netdev_priv(dev);
-	struct ice_pf *pf = np->vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(dev);
 	struct nlattr *attr, *br_spec;
 	struct ice_hw *hw = &pf->hw;
 	struct ice_sw *pf_sw;
@@ -8239,7 +8165,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 		if (err) {
 			netdev_err(dev, "switch rule update failed, mode = %d err %d aq_err %s\n",
 				   mode, err,
-				   ice_aq_str(hw->adminq.sq_last_status));
+				   libie_aq_str(hw->adminq.sq_last_status));
 			/* revert hw->evb_veb */
 			hw->evb_veb = (pf_sw->bridge_mode == BRIDGE_MODE_VEB);
 			return err;
@@ -8340,11 +8266,16 @@ void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
  * @np: net device to configure
  * @filter_dev: device on which filter is added
  * @cls_flower: offload data
+ * @ingress: if the rule is added to an ingress block
+ *
+ * Return: 0 if the flower was successfully added or deleted,
+ *	   negative error code otherwise.
  */
 static int
 ice_setup_tc_cls_flower(struct ice_netdev_priv *np,
 			struct net_device *filter_dev,
-			struct flow_cls_offload *cls_flower)
+			struct flow_cls_offload *cls_flower,
+			bool ingress)
 {
 	struct ice_vsi *vsi = np->vsi;
 
@@ -8353,7 +8284,7 @@ ice_setup_tc_cls_flower(struct ice_netdev_priv *np,
 
 	switch (cls_flower->command) {
 	case FLOW_CLS_REPLACE:
-		return ice_add_cls_flower(filter_dev, vsi, cls_flower);
+		return ice_add_cls_flower(filter_dev, vsi, cls_flower, ingress);
 	case FLOW_CLS_DESTROY:
 		return ice_del_cls_flower(vsi, cls_flower);
 	default:
@@ -8362,20 +8293,46 @@ ice_setup_tc_cls_flower(struct ice_netdev_priv *np,
 }
 
 /**
- * ice_setup_tc_block_cb - callback handler registered for TC block
+ * ice_setup_tc_block_cb_ingress - callback handler for ingress TC block
  * @type: TC SETUP type
  * @type_data: TC flower offload data that contains user input
  * @cb_priv: netdev private data
+ *
+ * Return: 0 if the setup was successful, negative error code otherwise.
  */
 static int
-ice_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
+ice_setup_tc_block_cb_ingress(enum tc_setup_type type, void *type_data,
+			      void *cb_priv)
 {
 	struct ice_netdev_priv *np = cb_priv;
 
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return ice_setup_tc_cls_flower(np, np->vsi->netdev,
-					       type_data);
+					       type_data, true);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+/**
+ * ice_setup_tc_block_cb_egress - callback handler for egress TC block
+ * @type: TC SETUP type
+ * @type_data: TC flower offload data that contains user input
+ * @cb_priv: netdev private data
+ *
+ * Return: 0 if the setup was successful, negative error code otherwise.
+ */
+static int
+ice_setup_tc_block_cb_egress(enum tc_setup_type type, void *type_data,
+			     void *cb_priv)
+{
+	struct ice_netdev_priv *np = cb_priv;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return ice_setup_tc_cls_flower(np, np->vsi->netdev,
+					       type_data, false);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -9128,7 +9085,7 @@ static int ice_create_q_channels(struct ice_vsi *vsi)
 		list_add_tail(&ch->list, &vsi->ch_list);
 		vsi->tc_map_vsi[i] = ch->ch_vsi;
 		dev_dbg(ice_pf_to_dev(pf),
-			"successfully created channel: VSI %pK\n", ch->ch_vsi);
+			"successfully created channel: VSI %p\n", ch->ch_vsi);
 	}
 	return 0;
 
@@ -9313,6 +9270,96 @@ exit:
 	return ret;
 }
 
+/**
+ * ice_cfg_txtime - configure Tx Time for the Tx ring
+ * @tx_ring: pointer to the Tx ring structure
+ *
+ * Return: 0 on success, negative value on failure.
+ */
+static int ice_cfg_txtime(struct ice_tx_ring *tx_ring)
+{
+	int err, timeout = 50;
+	struct ice_vsi *vsi;
+	struct device *dev;
+	struct ice_pf *pf;
+	u32 queue;
+
+	if (!tx_ring)
+		return -EINVAL;
+
+	vsi = tx_ring->vsi;
+	pf = vsi->back;
+	while (test_and_set_bit(ICE_CFG_BUSY, pf->state)) {
+		timeout--;
+		if (!timeout)
+			return -EBUSY;
+		usleep_range(1000, 2000);
+	}
+
+	queue = tx_ring->q_index;
+	dev = ice_pf_to_dev(pf);
+
+	/* Ignore return value, and always attempt to enable queue. */
+	ice_qp_dis(vsi, queue);
+
+	err = ice_qp_ena(vsi, queue);
+	if (err)
+		dev_err(dev, "Failed to enable Tx queue %d for TxTime configuration\n",
+			queue);
+
+	clear_bit(ICE_CFG_BUSY, pf->state);
+	return err;
+}
+
+/**
+ * ice_offload_txtime - set earliest TxTime first
+ * @netdev: network interface device structure
+ * @qopt_off: etf queue option offload from the skb to set
+ *
+ * Return: 0 on success, negative value on failure.
+ */
+static int ice_offload_txtime(struct net_device *netdev,
+			      void *qopt_off)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_pf *pf = np->vsi->back;
+	struct tc_etf_qopt_offload *qopt;
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_tx_ring *tx_ring;
+	int ret = 0;
+
+	if (!ice_is_feature_supported(pf, ICE_F_TXTIME))
+		return -EOPNOTSUPP;
+
+	qopt = qopt_off;
+	if (!qopt_off || qopt->queue < 0 || qopt->queue >= vsi->num_txq)
+		return -EINVAL;
+
+	if (qopt->enable)
+		set_bit(qopt->queue,  pf->txtime_txqs);
+	else
+		clear_bit(qopt->queue, pf->txtime_txqs);
+
+	if (netif_running(vsi->netdev)) {
+		tx_ring = vsi->tx_rings[qopt->queue];
+		ret = ice_cfg_txtime(tx_ring);
+		if (ret)
+			goto err;
+	}
+
+	netdev_info(netdev, "%s TxTime on queue: %i\n",
+		    str_enable_disable(qopt->enable), qopt->queue);
+	return 0;
+
+err:
+	netdev_err(netdev, "Failed to %s TxTime on queue: %i\n",
+		   str_enable_disable(qopt->enable), qopt->queue);
+
+	if (qopt->enable)
+		clear_bit(qopt->queue,  pf->txtime_txqs);
+	return ret;
+}
+
 static LIST_HEAD(ice_block_cb_list);
 
 static int
@@ -9320,27 +9367,45 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 	     void *type_data)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
+	enum flow_block_binder_type binder_type;
+	struct iidc_rdma_core_dev_info *cdev;
 	struct ice_pf *pf = np->vsi->back;
+	flow_setup_cb_t *flower_handler;
 	bool locked = false;
 	int err;
 
 	switch (type) {
 	case TC_SETUP_BLOCK:
+		binder_type =
+			((struct flow_block_offload *)type_data)->binder_type;
+
+		switch (binder_type) {
+		case FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS:
+			flower_handler = ice_setup_tc_block_cb_ingress;
+			break;
+		case FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS:
+			flower_handler = ice_setup_tc_block_cb_egress;
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+
 		return flow_block_cb_setup_simple(type_data,
 						  &ice_block_cb_list,
-						  ice_setup_tc_block_cb,
-						  np, np, true);
+						  flower_handler,
+						  np, np, false);
 	case TC_SETUP_QDISC_MQPRIO:
 		if (ice_is_eswitch_mode_switchdev(pf)) {
 			netdev_err(netdev, "TC MQPRIO offload not supported, switchdev is enabled\n");
 			return -EOPNOTSUPP;
 		}
 
-		if (pf->adev) {
+		cdev = pf->cdev_info;
+		if (cdev && cdev->adev) {
 			mutex_lock(&pf->adev_mutex);
-			device_lock(&pf->adev->dev);
+			device_lock(&cdev->adev->dev);
 			locked = true;
-			if (pf->adev->dev.driver) {
+			if (cdev->adev->dev.driver) {
 				netdev_err(netdev, "Cannot change qdisc when RDMA is active\n");
 				err = -EBUSY;
 				goto adev_unlock;
@@ -9354,10 +9419,12 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 
 adev_unlock:
 		if (locked) {
-			device_unlock(&pf->adev->dev);
+			device_unlock(&cdev->adev->dev);
 			mutex_unlock(&pf->adev_mutex);
 		}
 		return err;
+	case TC_SETUP_QDISC_ETF:
+		return ice_offload_txtime(netdev, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -9390,7 +9457,7 @@ ice_indr_setup_block_cb(enum tc_setup_type type, void *type_data,
 	case TC_SETUP_CLSFLOWER:
 		return ice_setup_tc_cls_flower(np, priv->netdev,
 					       (struct flow_cls_offload *)
-					       type_data);
+					       type_data, false);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -9493,8 +9560,7 @@ ice_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch,
  */
 int ice_open(struct net_device *netdev)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_pf *pf = np->vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 
 	if (ice_is_reset_in_progress(pf->state)) {
 		netdev_err(netdev, "can't open net device while reset is in progress");
@@ -9697,7 +9763,6 @@ static const struct net_device_ops ice_netdev_ops = {
 	.ndo_change_mtu = ice_change_mtu,
 	.ndo_get_stats64 = ice_get_stats64,
 	.ndo_set_tx_maxrate = ice_set_tx_maxrate,
-	.ndo_eth_ioctl = ice_eth_ioctl,
 	.ndo_set_vf_spoofchk = ice_set_vf_spoofchk,
 	.ndo_set_vf_mac = ice_set_vf_mac,
 	.ndo_get_vf_config = ice_get_vf_cfg,
@@ -9721,4 +9786,6 @@ static const struct net_device_ops ice_netdev_ops = {
 	.ndo_bpf = ice_xdp,
 	.ndo_xdp_xmit = ice_xdp_xmit,
 	.ndo_xsk_wakeup = ice_xsk_wakeup,
+	.ndo_hwtstamp_get = ice_ptp_hwtstamp_get,
+	.ndo_hwtstamp_set = ice_ptp_hwtstamp_set,
 };
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index 59e8879ac059..7e187a804dfa 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -22,10 +22,10 @@ int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
 		    u16 length, void *data, bool last_command,
 		    bool read_shadow_ram, struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	struct ice_aqc_nvm *cmd;
 
-	cmd = &desc.params.nvm;
+	cmd = libie_aq_raw(&desc);
 
 	if (offset > ICE_AQC_NVM_MAX_OFFSET)
 		return -EINVAL;
@@ -125,10 +125,10 @@ ice_aq_update_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
 		  u16 length, void *data, bool last_command, u8 command_flags,
 		  struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	struct ice_aqc_nvm *cmd;
 
-	cmd = &desc.params.nvm;
+	cmd = libie_aq_raw(&desc);
 
 	/* In offset the highest byte must be zeroed. */
 	if (offset & 0xFF000000)
@@ -146,7 +146,7 @@ ice_aq_update_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
 	cmd->offset_high = (offset >> 16) & 0xFF;
 	cmd->length = cpu_to_le16(length);
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	return ice_aq_send_cmd(hw, &desc, data, length, cd);
 }
@@ -161,10 +161,10 @@ ice_aq_update_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
  */
 int ice_aq_erase_nvm(struct ice_hw *hw, u16 module_typeid, struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	struct ice_aqc_nvm *cmd;
 
-	cmd = &desc.params.nvm;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_erase);
 
@@ -869,7 +869,7 @@ static int ice_discover_flash_size(struct ice_hw *hw)
 
 		status = ice_read_flat_nvm(hw, offset, &len, &data, false);
 		if (status == -EIO &&
-		    hw->adminq.sq_last_status == ICE_AQ_RC_EINVAL) {
+		    hw->adminq.sq_last_status == LIBIE_AQ_RC_EINVAL) {
 			ice_debug(hw, ICE_DBG_NVM, "%s: New upper bound of %u bytes\n",
 				  __func__, offset);
 			status = 0;
@@ -1182,14 +1182,14 @@ int ice_init_nvm(struct ice_hw *hw)
 int ice_nvm_validate_checksum(struct ice_hw *hw)
 {
 	struct ice_aqc_nvm_checksum *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	status = ice_acquire_nvm(hw, ICE_RES_READ);
 	if (status)
 		return status;
 
-	cmd = &desc.params.nvm_checksum;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_checksum);
 	cmd->flags = ICE_AQC_NVM_CHECKSUM_VERIFY;
@@ -1226,11 +1226,11 @@ int ice_nvm_validate_checksum(struct ice_hw *hw)
  */
 int ice_nvm_write_activate(struct ice_hw *hw, u16 cmd_flags, u8 *response_flags)
 {
+	struct libie_aq_desc desc;
 	struct ice_aqc_nvm *cmd;
-	struct ice_aq_desc desc;
 	int err;
 
-	cmd = &desc.params.nvm;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_write_activate);
 
 	cmd->cmd_flags = (u8)(cmd_flags & 0xFF);
@@ -1252,7 +1252,7 @@ int ice_nvm_write_activate(struct ice_hw *hw, u16 cmd_flags, u8 *response_flags)
  */
 int ice_aq_nvm_update_empr(struct ice_hw *hw)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_update_empr);
 
@@ -1278,15 +1278,15 @@ ice_nvm_set_pkg_data(struct ice_hw *hw, bool del_pkg_data_flag, u8 *data,
 		     u16 length, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_nvm_pkg_data *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	if (length != 0 && !data)
 		return -EINVAL;
 
-	cmd = &desc.params.pkg_data;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_pkg_data);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	if (del_pkg_data_flag)
 		cmd->cmd_flags |= ICE_AQC_NVM_PKG_DELETE;
@@ -1316,17 +1316,17 @@ ice_nvm_pass_component_tbl(struct ice_hw *hw, u8 *data, u16 length,
 			   u8 *comp_response_code, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_nvm_pass_comp_tbl *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!data || !comp_response || !comp_response_code)
 		return -EINVAL;
 
-	cmd = &desc.params.pass_comp_tbl;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc,
 				      ice_aqc_opc_nvm_pass_component_tbl);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	cmd->transfer_flag = transfer_flag;
 	status = ice_aq_send_cmd(hw, &desc, data, length, cd);
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h
index 6509d807627c..4f56d53d56b9 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.h
+++ b/drivers/net/ethernet/intel/ice/ice_parser.h
@@ -257,7 +257,6 @@ ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size,
 /*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/
 #define ICE_BST_TCAM_TABLE_SIZE		256
 #define ICE_BST_TCAM_KEY_SIZE		20
-#define ICE_BST_KEY_TCAM_SIZE		19
 
 /* Boost TCAM item */
 struct ice_bst_tcam_item {
@@ -401,7 +400,6 @@ u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag);
 #define ICE_PARSER_GPR_NUM	128
 #define ICE_PARSER_FLG_NUM	64
 #define ICE_PARSER_ERR_NUM	16
-#define ICE_BST_KEY_SIZE	10
 #define ICE_MARKER_ID_SIZE	9
 #define ICE_MARKER_MAX_SIZE	\
 		(ICE_MARKER_ID_SIZE * BITS_PER_BYTE - 1)
@@ -431,13 +429,13 @@ struct ice_parser_rt {
 	u8 pkt_buf[ICE_PARSER_MAX_PKT_LEN + ICE_PARSER_PKT_REV];
 	u16 pkt_len;
 	u16 po;
-	u8 bst_key[ICE_BST_KEY_SIZE];
+	u8 bst_key[ICE_BST_TCAM_KEY_SIZE];
 	struct ice_pg_cam_key pg_key;
+	u8 pg_prio;
 	struct ice_alu *alu0;
 	struct ice_alu *alu1;
 	struct ice_alu *alu2;
 	struct ice_pg_cam_action *action;
-	u8 pg_prio;
 	struct ice_gpr_pu pu;
 	u8 markers[ICE_MARKER_ID_SIZE];
 	bool protocols[ICE_PO_PAIR_SIZE];
diff --git a/drivers/net/ethernet/intel/ice/ice_parser_rt.c b/drivers/net/ethernet/intel/ice/ice_parser_rt.c
index dedf5e854e4b..3995d662e050 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser_rt.c
+++ b/drivers/net/ethernet/intel/ice/ice_parser_rt.c
@@ -125,22 +125,20 @@ static void ice_bst_key_init(struct ice_parser_rt *rt,
 	else
 		key[idd] = imem->b_kb.prio;
 
-	idd = ICE_BST_KEY_TCAM_SIZE - 1;
+	idd = ICE_BST_TCAM_KEY_SIZE - 2;
 	for (i = idd; i >= 0; i--) {
 		int j;
 
 		j = ho + idd - i;
 		if (j < ICE_PARSER_MAX_PKT_LEN)
-			key[i] = rt->pkt_buf[ho + idd - i];
+			key[i] = rt->pkt_buf[j];
 		else
 			key[i] = 0;
 	}
 
-	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generated Boost TCAM Key:\n");
-	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "%02X %02X %02X %02X %02X %02X %02X %02X %02X %02X\n",
-		  key[0], key[1], key[2], key[3], key[4],
-		  key[5], key[6], key[7], key[8], key[9]);
-	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "\n");
+	ice_debug_array_w_prefix(rt->psr->hw, ICE_DBG_PARSER,
+				 KBUILD_MODNAME ": Generated Boost TCAM Key",
+				 key, ICE_BST_TCAM_KEY_SIZE);
 }
 
 static u16 ice_bit_rev_u16(u16 v, int len)
diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
index 7c09ea0f03ba..725167d557a8 100644
--- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
@@ -82,26 +82,46 @@ enum ice_sw_tunnel_type {
 enum ice_prot_id {
 	ICE_PROT_ID_INVAL	= 0,
 	ICE_PROT_MAC_OF_OR_S	= 1,
+	ICE_PROT_MAC_O2		= 2,
 	ICE_PROT_MAC_IL		= 4,
+	ICE_PROT_MAC_IN_MAC	= 7,
 	ICE_PROT_ETYPE_OL	= 9,
 	ICE_PROT_ETYPE_IL	= 10,
+	ICE_PROT_PAY		= 15,
+	ICE_PROT_EVLAN_O	= 16,
+	ICE_PROT_VLAN_O		= 17,
+	ICE_PROT_VLAN_IF	= 18,
+	ICE_PROT_MPLS_OL_MINUS_1 = 27,
+	ICE_PROT_MPLS_OL_OR_OS	= 28,
+	ICE_PROT_MPLS_IL	= 29,
 	ICE_PROT_IPV4_OF_OR_S	= 32,
 	ICE_PROT_IPV4_IL	= 33,
+	ICE_PROT_IPV4_IL_IL	= 34,
 	ICE_PROT_IPV6_OF_OR_S	= 40,
 	ICE_PROT_IPV6_IL	= 41,
+	ICE_PROT_IPV6_IL_IL	= 42,
+	ICE_PROT_IPV6_NEXT_PROTO = 43,
+	ICE_PROT_IPV6_FRAG	= 47,
 	ICE_PROT_TCP_IL		= 49,
 	ICE_PROT_UDP_OF		= 52,
 	ICE_PROT_UDP_IL_OR_S	= 53,
 	ICE_PROT_GRE_OF		= 64,
+	ICE_PROT_NSH_F		= 84,
 	ICE_PROT_ESP_F		= 88,
 	ICE_PROT_ESP_2		= 89,
 	ICE_PROT_SCTP_IL	= 96,
 	ICE_PROT_ICMP_IL	= 98,
 	ICE_PROT_ICMPV6_IL	= 100,
+	ICE_PROT_VRRP_F		= 101,
+	ICE_PROT_OSPF		= 102,
 	ICE_PROT_PPPOE		= 103,
 	ICE_PROT_L2TPV3		= 104,
+	ICE_PROT_ATAOE_OF	= 114,
+	ICE_PROT_CTRL_OF	= 116,
+	ICE_PROT_LLDP_OF	= 117,
 	ICE_PROT_ARP_OF		= 118,
 	ICE_PROT_META_ID	= 255, /* when offset == metadata */
+	ICE_PROT_EAPOL_OF	= 120,
 	ICE_PROT_INVALID	= 255  /* when offset == ICE_FV_OFFSET_INVAL */
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index a999fface272..4c8d20f2d2c0 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -4,7 +4,6 @@
 #include "ice.h"
 #include "ice_lib.h"
 #include "ice_trace.h"
-#include "ice_cgu_regs.h"
 
 static const char ice_pin_names[][64] = {
 	"SDP0",
@@ -16,45 +15,43 @@ static const char ice_pin_names[][64] = {
 };
 
 static const struct ice_ptp_pin_desc ice_pin_desc_e82x[] = {
-	/* name,        gpio */
-	{  TIME_SYNC, {  4, -1 }},
-	{  ONE_PPS,   { -1,  5 }},
+	/* name,        gpio,       delay */
+	{  TIME_SYNC, {  4, -1 }, { 0,  0 }},
+	{  ONE_PPS,   { -1,  5 }, { 0, 11 }},
 };
 
 static const struct ice_ptp_pin_desc ice_pin_desc_e825c[] = {
-	/* name,        gpio */
-	{  SDP0,      {  0,  0 }},
-	{  SDP1,      {  1,  1 }},
-	{  SDP2,      {  2,  2 }},
-	{  SDP3,      {  3,  3 }},
-	{  TIME_SYNC, {  4, -1 }},
-	{  ONE_PPS,   { -1,  5 }},
+	/* name,        gpio,       delay */
+	{  SDP0,      {  0,  0 }, { 15, 14 }},
+	{  SDP1,      {  1,  1 }, { 15, 14 }},
+	{  SDP2,      {  2,  2 }, { 15, 14 }},
+	{  SDP3,      {  3,  3 }, { 15, 14 }},
+	{  TIME_SYNC, {  4, -1 }, { 11,  0 }},
+	{  ONE_PPS,   { -1,  5 }, {  0,  9 }},
 };
 
 static const struct ice_ptp_pin_desc ice_pin_desc_e810[] = {
-	/* name,      gpio */
-	{  SDP0,    {  0, 0 }},
-	{  SDP1,    {  1, 1 }},
-	{  SDP2,    {  2, 2 }},
-	{  SDP3,    {  3, 3 }},
-	{  ONE_PPS, { -1, 5 }},
+	/* name,        gpio,       delay */
+	{  SDP0,      {  0,  0 }, { 0, 1 }},
+	{  SDP1,      {  1,  1 }, { 0, 1 }},
+	{  SDP2,      {  2,  2 }, { 0, 1 }},
+	{  SDP3,      {  3,  3 }, { 0, 1 }},
+	{  ONE_PPS,   { -1,  5 }, { 0, 1 }},
 };
 
-static const char ice_pin_names_nvm[][64] = {
-	"GNSS",
-	"SMA1",
-	"U.FL1",
-	"SMA2",
-	"U.FL2",
+static const char ice_pin_names_dpll[][64] = {
+	"SDP20",
+	"SDP21",
+	"SDP22",
+	"SDP23",
 };
 
-static const struct ice_ptp_pin_desc ice_pin_desc_e810_sma[] = {
-	/* name,   gpio */
-	{  GNSS, {  1, -1 }},
-	{  SMA1, {  1,  0 }},
-	{  UFL1, { -1,  0 }},
-	{  SMA2, {  3,  2 }},
-	{  UFL2, {  3, -1 }},
+static const struct ice_ptp_pin_desc ice_pin_desc_dpll[] = {
+	/* name,   gpio,       delay */
+	{  SDP0, { -1,  0 }, { 0, 1 }},
+	{  SDP1, {  1, -1 }, { 0, 0 }},
+	{  SDP2, { -1,  2 }, { 0, 1 }},
+	{  SDP3, {  3, -1 }, { 0, 0 }},
 };
 
 static struct ice_pf *ice_get_ctrl_pf(struct ice_pf *pf)
@@ -93,101 +90,6 @@ static int ice_ptp_find_pin_idx(struct ice_pf *pf, enum ptp_pin_function func,
 }
 
 /**
- * ice_ptp_update_sma_data - update SMA pins data according to pins setup
- * @pf: Board private structure
- * @sma_pins: parsed SMA pins status
- * @data: SMA data to update
- */
-static void ice_ptp_update_sma_data(struct ice_pf *pf, unsigned int sma_pins[],
-				    u8 *data)
-{
-	const char *state1, *state2;
-
-	/* Set the right state based on the desired configuration.
-	 * When bit is set, functionality is disabled.
-	 */
-	*data &= ~ICE_ALL_SMA_MASK;
-	if (!sma_pins[UFL1 - 1]) {
-		if (sma_pins[SMA1 - 1] == PTP_PF_EXTTS) {
-			state1 = "SMA1 Rx, U.FL1 disabled";
-			*data |= ICE_SMA1_TX_EN;
-		} else if (sma_pins[SMA1 - 1] == PTP_PF_PEROUT) {
-			state1 = "SMA1 Tx U.FL1 disabled";
-			*data |= ICE_SMA1_DIR_EN;
-		} else {
-			state1 = "SMA1 disabled, U.FL1 disabled";
-			*data |= ICE_SMA1_MASK;
-		}
-	} else {
-		/* U.FL1 Tx will always enable SMA1 Rx */
-		state1 = "SMA1 Rx, U.FL1 Tx";
-	}
-
-	if (!sma_pins[UFL2 - 1]) {
-		if (sma_pins[SMA2 - 1] == PTP_PF_EXTTS) {
-			state2 = "SMA2 Rx, U.FL2 disabled";
-			*data |= ICE_SMA2_TX_EN | ICE_SMA2_UFL2_RX_DIS;
-		} else if (sma_pins[SMA2 - 1] == PTP_PF_PEROUT) {
-			state2 = "SMA2 Tx, U.FL2 disabled";
-			*data |= ICE_SMA2_DIR_EN | ICE_SMA2_UFL2_RX_DIS;
-		} else {
-			state2 = "SMA2 disabled, U.FL2 disabled";
-			*data |= ICE_SMA2_MASK;
-		}
-	} else {
-		if (!sma_pins[SMA2 - 1]) {
-			state2 = "SMA2 disabled, U.FL2 Rx";
-			*data |= ICE_SMA2_DIR_EN | ICE_SMA2_TX_EN;
-		} else {
-			state2 = "SMA2 Tx, U.FL2 Rx";
-			*data |= ICE_SMA2_DIR_EN;
-		}
-	}
-
-	dev_dbg(ice_pf_to_dev(pf), "%s, %s\n", state1, state2);
-}
-
-/**
- * ice_ptp_set_sma_cfg - set the configuration of the SMA control logic
- * @pf: Board private structure
- *
- * Return: 0 on success, negative error code otherwise
- */
-static int ice_ptp_set_sma_cfg(struct ice_pf *pf)
-{
-	const struct ice_ptp_pin_desc *ice_pins = pf->ptp.ice_pin_desc;
-	struct ptp_pin_desc *pins = pf->ptp.pin_desc;
-	unsigned int sma_pins[ICE_SMA_PINS_NUM] = {};
-	int err;
-	u8 data;
-
-	/* Read initial pin state value */
-	err = ice_read_sma_ctrl(&pf->hw, &data);
-	if (err)
-		return err;
-
-	/* Get SMA/U.FL pins states */
-	for (int i = 0; i < pf->ptp.info.n_pins; i++)
-		if (pins[i].func) {
-			int name_idx = ice_pins[i].name_idx;
-
-			switch (name_idx) {
-			case SMA1:
-			case UFL1:
-			case SMA2:
-			case UFL2:
-				sma_pins[name_idx - 1] = pins[i].func;
-				break;
-			default:
-				continue;
-			}
-		}
-
-	ice_ptp_update_sma_data(pf, sma_pins, &data);
-	return ice_write_sma_ctrl(&pf->hw, data);
-}
-
-/**
  * ice_ptp_cfg_tx_interrupt - Configure Tx timestamp interrupt for the device
  * @pf: Board private structure
  *
@@ -298,18 +200,30 @@ void ice_ptp_restore_timestamp_mode(struct ice_pf *pf)
  * @sts: Optional parameter for holding a pair of system timestamps from
  *       the system clock. Will be ignored if NULL is given.
  */
-static u64
-ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts)
+u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf,
+			     struct ptp_system_timestamp *sts)
 {
 	struct ice_hw *hw = &pf->hw;
 	u32 hi, lo, lo2;
 	u8 tmr_idx;
 
+	if (!ice_is_primary(hw))
+		hw = ice_get_primary_hw(pf);
+
 	tmr_idx = ice_get_ptp_src_clock_index(hw);
 	guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock);
 	/* Read the system timestamp pre PHC read */
 	ptp_read_system_prets(sts);
 
+	if (hw->mac_type == ICE_MAC_E830) {
+		u64 clk_time = rd64(hw, E830_GLTSYN_TIME_L(tmr_idx));
+
+		/* Read the system timestamp post PHC read */
+		ptp_read_system_postts(sts);
+
+		return clk_time;
+	}
+
 	lo = rd32(hw, GLTSYN_TIME_L(tmr_idx));
 
 	/* Read the system timestamp post PHC read */
@@ -464,7 +378,9 @@ ice_ptp_is_tx_tracker_up(struct ice_ptp_tx *tx)
  */
 void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx)
 {
+	struct ice_e810_params *params;
 	struct ice_ptp_port *ptp_port;
+	unsigned long flags;
 	struct sk_buff *skb;
 	struct ice_pf *pf;
 
@@ -473,6 +389,7 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx)
 
 	ptp_port = container_of(tx, struct ice_ptp_port, tx);
 	pf = ptp_port_to_pf(ptp_port);
+	params = &pf->hw.ptp.phy.e810;
 
 	/* Drop packets which have waited for more than 2 seconds */
 	if (time_is_before_jiffies(tx->tstamps[idx].start + 2 * HZ)) {
@@ -489,11 +406,17 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx)
 
 	ice_trace(tx_tstamp_fw_req, tx->tstamps[idx].skb, idx);
 
+	spin_lock_irqsave(&params->atqbal_wq.lock, flags);
+
+	params->atqbal_flags |= ATQBAL_FLAGS_INTR_IN_PROGRESS;
+
 	/* Write TS index to read to the PF register so the FW can read it */
-	wr32(&pf->hw, PF_SB_ATQBAL,
-	     TS_LL_READ_TS_INTR | FIELD_PREP(TS_LL_READ_TS_IDX, idx) |
-	     TS_LL_READ_TS);
+	wr32(&pf->hw, REG_LL_PROXY_H,
+	     REG_LL_PROXY_H_TS_INTR_ENA | FIELD_PREP(REG_LL_PROXY_H_TS_IDX, idx) |
+	     REG_LL_PROXY_H_EXEC);
 	tx->last_ll_ts_idx_read = idx;
+
+	spin_unlock_irqrestore(&params->atqbal_wq.lock, flags);
 }
 
 /**
@@ -504,35 +427,52 @@ void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx)
 {
 	struct skb_shared_hwtstamps shhwtstamps = {};
 	u8 idx = tx->last_ll_ts_idx_read;
+	struct ice_e810_params *params;
 	struct ice_ptp_port *ptp_port;
 	u64 raw_tstamp, tstamp;
 	bool drop_ts = false;
 	struct sk_buff *skb;
+	unsigned long flags;
+	struct device *dev;
 	struct ice_pf *pf;
-	u32 val;
+	u32 reg_ll_high;
 
 	if (!tx->init || tx->last_ll_ts_idx_read < 0)
 		return;
 
 	ptp_port = container_of(tx, struct ice_ptp_port, tx);
 	pf = ptp_port_to_pf(ptp_port);
+	dev = ice_pf_to_dev(pf);
+	params = &pf->hw.ptp.phy.e810;
 
 	ice_trace(tx_tstamp_fw_done, tx->tstamps[idx].skb, idx);
 
-	val = rd32(&pf->hw, PF_SB_ATQBAL);
+	spin_lock_irqsave(&params->atqbal_wq.lock, flags);
+
+	if (!(params->atqbal_flags & ATQBAL_FLAGS_INTR_IN_PROGRESS))
+		dev_dbg(dev, "%s: low latency interrupt request not in progress?\n",
+			__func__);
+
+	/* Read the low 32 bit value */
+	raw_tstamp = rd32(&pf->hw, REG_LL_PROXY_L);
+	/* Read the status together with high TS part */
+	reg_ll_high = rd32(&pf->hw, REG_LL_PROXY_H);
+
+	/* Wake up threads waiting on low latency interface */
+	params->atqbal_flags &= ~ATQBAL_FLAGS_INTR_IN_PROGRESS;
+
+	wake_up_locked(&params->atqbal_wq);
+
+	spin_unlock_irqrestore(&params->atqbal_wq.lock, flags);
 
 	/* When the bit is cleared, the TS is ready in the register */
-	if (val & TS_LL_READ_TS) {
+	if (reg_ll_high & REG_LL_PROXY_H_EXEC) {
 		dev_err(ice_pf_to_dev(pf), "Failed to get the Tx tstamp - FW not ready");
 		return;
 	}
 
 	/* High 8 bit value of the TS is on the bits 16:23 */
-	raw_tstamp = FIELD_GET(TS_LL_READ_TS_HIGH, val);
-	raw_tstamp <<= 32;
-
-	/* Read the low 32 bit value */
-	raw_tstamp |= (u64)rd32(&pf->hw, PF_SB_ATQBAH);
+	raw_tstamp |= ((u64)FIELD_GET(REG_LL_PROXY_H_TS_HIGH, reg_ll_high)) << 32;
 
 	/* Devices using this interface always verify the timestamp differs
 	 * relative to the last cached timestamp value.
@@ -560,6 +500,9 @@ void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx)
 	if (tstamp) {
 		shhwtstamps.hwtstamp = ns_to_ktime(tstamp);
 		ice_trace(tx_tstamp_complete, skb, idx);
+
+		/* Count the number of Tx timestamps that succeeded */
+		pf->ptp.tx_hwtstamp_good++;
 	}
 
 	skb_tstamp_tx(skb, &shhwtstamps);
@@ -618,6 +561,7 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx)
 {
 	struct ice_ptp_port *ptp_port;
 	unsigned long flags;
+	u32 tstamp_good = 0;
 	struct ice_pf *pf;
 	struct ice_hw *hw;
 	u64 tstamp_ready;
@@ -718,11 +662,16 @@ skip_ts_read:
 		if (tstamp) {
 			shhwtstamps.hwtstamp = ns_to_ktime(tstamp);
 			ice_trace(tx_tstamp_complete, skb, idx);
+
+			/* Count the number of Tx timestamps that succeeded */
+			tstamp_good++;
 		}
 
 		skb_tstamp_tx(skb, &shhwtstamps);
 		dev_kfree_skb_any(skb);
 	}
+
+	pf->ptp.tx_hwtstamp_good += tstamp_good;
 }
 
 /**
@@ -946,28 +895,6 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
 }
 
 /**
- * ice_ptp_init_tx_eth56g - Initialize tracking for Tx timestamps
- * @pf: Board private structure
- * @tx: the Tx tracking structure to initialize
- * @port: the port this structure tracks
- *
- * Initialize the Tx timestamp tracker for this port. ETH56G PHYs
- * have independent memory blocks for all ports.
- *
- * Return: 0 for success, -ENOMEM when failed to allocate Tx tracker
- */
-static int ice_ptp_init_tx_eth56g(struct ice_pf *pf, struct ice_ptp_tx *tx,
-				  u8 port)
-{
-	tx->block = port;
-	tx->offset = 0;
-	tx->len = INDEX_PER_PORT_ETH56G;
-	tx->has_ready_bitmap = 1;
-
-	return ice_ptp_alloc_tx_tracker(tx);
-}
-
-/**
  * ice_ptp_init_tx_e82x - Initialize tracking for Tx timestamps
  * @pf: Board private structure
  * @tx: the Tx tracking structure to initialize
@@ -977,9 +904,11 @@ static int ice_ptp_init_tx_eth56g(struct ice_pf *pf, struct ice_ptp_tx *tx,
  * the timestamp block is shared for all ports in the same quad. To avoid
  * ports using the same timestamp index, logically break the block of
  * registers into chunks based on the port number.
+ *
+ * Return: 0 on success, -ENOMEM when out of memory
  */
-static int
-ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port)
+static int ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx,
+				u8 port)
 {
 	tx->block = ICE_GET_QUAD_NUM(port);
 	tx->offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT_E82X;
@@ -990,24 +919,27 @@ ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port)
 }
 
 /**
- * ice_ptp_init_tx_e810 - Initialize tracking for Tx timestamps
+ * ice_ptp_init_tx - Initialize tracking for Tx timestamps
  * @pf: Board private structure
  * @tx: the Tx tracking structure to initialize
+ * @port: the port this structure tracks
  *
- * Initialize the Tx timestamp tracker for this PF. For E810 devices, each
- * port has its own block of timestamps, independent of the other ports.
+ * Initialize the Tx timestamp tracker for this PF. For all PHYs except E82X,
+ * each port has its own block of timestamps, independent of the other ports.
+ *
+ * Return: 0 on success, -ENOMEM when out of memory
  */
-static int
-ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx)
+static int ice_ptp_init_tx(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port)
 {
-	tx->block = pf->hw.port_info->lport;
+	tx->block = port;
 	tx->offset = 0;
-	tx->len = INDEX_PER_PORT_E810;
+	tx->len = INDEX_PER_PORT;
+
 	/* The E810 PHY does not provide a timestamp ready bitmap. Instead,
 	 * verify new timestamps against cached copy of the last read
 	 * timestamp.
 	 */
-	tx->has_ready_bitmap = 0;
+	tx->has_ready_bitmap = pf->hw.mac_type != ICE_MAC_E810;
 
 	return ice_ptp_alloc_tx_tracker(tx);
 }
@@ -1292,20 +1224,21 @@ ice_ptp_port_phy_stop(struct ice_ptp_port *ptp_port)
 	struct ice_hw *hw = &pf->hw;
 	int err;
 
-	if (ice_is_e810(hw))
-		return 0;
-
 	mutex_lock(&ptp_port->ps_lock);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_stop_phy_timer_eth56g(hw, port, true);
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
+		err = 0;
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		kthread_cancel_delayed_work_sync(&ptp_port->ov_work);
 
 		err = ice_stop_phy_timer_e82x(hw, port, true);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_stop_phy_timer_eth56g(hw, port, true);
+		break;
 	default:
 		err = -ENODEV;
 	}
@@ -1335,19 +1268,17 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 	unsigned long flags;
 	int err;
 
-	if (ice_is_e810(hw))
-		return 0;
-
 	if (!ptp_port->link_up)
 		return ice_ptp_port_phy_stop(ptp_port);
 
 	mutex_lock(&ptp_port->ps_lock);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_start_phy_timer_eth56g(hw, port);
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
+		err = 0;
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		/* Start the PHY timer in Vernier mode */
 		kthread_cancel_delayed_work_sync(&ptp_port->ov_work);
 
@@ -1372,6 +1303,9 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 		kthread_queue_delayed_work(pf->ptp.kworker, &ptp_port->ov_work,
 					   0);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_start_phy_timer_eth56g(hw, port);
+		break;
 	default:
 		err = -ENODEV;
 	}
@@ -1388,10 +1322,9 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 /**
  * ice_ptp_link_change - Reconfigure PTP after link status change
  * @pf: Board private structure
- * @port: Port for which the PHY start is set
  * @linkup: Link is up or down
  */
-void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
+void ice_ptp_link_change(struct ice_pf *pf, bool linkup)
 {
 	struct ice_ptp_port *ptp_port;
 	struct ice_hw *hw = &pf->hw;
@@ -1399,14 +1332,7 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
 	if (pf->ptp.state != ICE_PTP_READY)
 		return;
 
-	if (WARN_ON_ONCE(port >= hw->ptp.num_lports))
-		return;
-
 	ptp_port = &pf->ptp.port;
-	if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo)
-		port *= 2;
-	if (WARN_ON_ONCE(ptp_port->port_num != port))
-		return;
 
 	/* Update cached link status for this port immediately */
 	ptp_port->link_up = linkup;
@@ -1414,12 +1340,14 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
 	/* Skip HW writes if reset is in progress */
 	if (pf->hw.reset_ongoing)
 		return;
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_E810:
-		/* Do not reconfigure E810 PHY */
+
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
+		/* Do not reconfigure E810 or E830 PHY */
 		return;
-	case ICE_PHY_ETH56G:
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
+	case ICE_MAC_GENERIC_3K_E825:
 		ice_ptp_port_phy_restart(ptp_port);
 		return;
 	default:
@@ -1447,46 +1375,45 @@ static int ice_ptp_cfg_phy_interrupt(struct ice_pf *pf, bool ena, u32 threshold)
 
 	ice_ptp_reset_ts_memory(hw);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G: {
-		int port;
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
+		return 0;
+	case ICE_MAC_GENERIC: {
+		int quad;
 
-		for (port = 0; port < hw->ptp.num_lports; port++) {
+		for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports);
+		     quad++) {
 			int err;
 
-			err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold);
+			err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold);
 			if (err) {
-				dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n",
-					port, err);
+				dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n",
+					quad, err);
 				return err;
 			}
 		}
 
 		return 0;
 	}
-	case ICE_PHY_E82X: {
-		int quad;
+	case ICE_MAC_GENERIC_3K_E825: {
+		int port;
 
-		for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports);
-		     quad++) {
+		for (port = 0; port < hw->ptp.num_lports; port++) {
 			int err;
 
-			err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold);
+			err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold);
 			if (err) {
-				dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n",
-					quad, err);
+				dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n",
+					port, err);
 				return err;
 			}
 		}
 
 		return 0;
 	}
-	case ICE_PHY_E810:
-		return 0;
-	case ICE_PHY_UNSUP:
+	case ICE_MAC_UNKNOWN:
 	default:
-		dev_warn(dev, "%s: Unexpected PHY model %d\n", __func__,
-			 ice_get_phy_model(hw));
 		return -EOPNOTSUPP;
 	}
 }
@@ -1566,18 +1493,29 @@ void ice_ptp_extts_event(struct ice_pf *pf)
 	 * Event is defined in GLTSYN_EVNT_0 register
 	 */
 	for (chan = 0; chan < GLTSYN_EVNT_H_IDX_MAX; chan++) {
+		int pin_desc_idx;
+
 		/* Check if channel is enabled */
-		if (pf->ptp.ext_ts_irq & (1 << chan)) {
-			lo = rd32(hw, GLTSYN_EVNT_L(chan, tmr_idx));
-			hi = rd32(hw, GLTSYN_EVNT_H(chan, tmr_idx));
-			event.timestamp = (((u64)hi) << 32) | lo;
-			event.type = PTP_CLOCK_EXTTS;
-			event.index = chan;
-
-			/* Fire event */
-			ptp_clock_event(pf->ptp.clock, &event);
-			pf->ptp.ext_ts_irq &= ~(1 << chan);
+		if (!(pf->ptp.ext_ts_irq & (1 << chan)))
+			continue;
+
+		lo = rd32(hw, GLTSYN_EVNT_L(chan, tmr_idx));
+		hi = rd32(hw, GLTSYN_EVNT_H(chan, tmr_idx));
+		event.timestamp = (u64)hi << 32 | lo;
+
+		/* Add delay compensation */
+		pin_desc_idx = ice_ptp_find_pin_idx(pf, PTP_PF_EXTTS, chan);
+		if (pin_desc_idx >= 0) {
+			const struct ice_ptp_pin_desc *desc;
+
+			desc = &pf->ptp.ice_pin_desc[pin_desc_idx];
+			event.timestamp -= desc->delay[0];
 		}
+
+		event.type = PTP_CLOCK_EXTTS;
+		event.index = chan;
+		pf->ptp.ext_ts_irq &= ~(1 << chan);
+		ptp_clock_event(pf->ptp.clock, &event);
 	}
 }
 
@@ -1600,14 +1538,6 @@ static int ice_ptp_cfg_extts(struct ice_pf *pf, struct ptp_extts_request *rq,
 	int pin_desc_idx;
 	u8 tmr_idx;
 
-	/* Reject requests with unsupported flags */
-
-	if (rq->flags & ~(PTP_ENABLE_FEATURE |
-			  PTP_RISING_EDGE |
-			  PTP_FALLING_EDGE |
-			  PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 	chan = rq->index;
 
@@ -1711,11 +1641,11 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan,
 	/* 0. Reset mode & out_en in AUX_OUT */
 	wr32(hw, GLTSYN_AUX_OUT(chan, tmr_idx), 0);
 
-	if (ice_is_e825c(hw)) {
+	if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) {
 		int err;
 
 		/* Enable/disable CGU 1PPS output for E825C */
-		err = ice_cgu_cfg_pps_out(hw, !!period);
+		err = ice_tspll_cfg_pps_out_e825c(hw, !!period);
 		if (err)
 			return err;
 	}
@@ -1754,6 +1684,7 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan,
 				  8 + chan + (tmr_idx * 4));
 
 	wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val);
+	ice_flush(hw);
 
 	return 0;
 }
@@ -1772,19 +1703,17 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan,
 static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq,
 			      int on)
 {
+	unsigned int gpio_pin, prop_delay_ns;
 	u64 clk, period, start, phase;
 	struct ice_hw *hw = &pf->hw;
-	unsigned int gpio_pin;
 	int pin_desc_idx;
 
-	if (rq->flags & ~PTP_PEROUT_PHASE)
-		return -EOPNOTSUPP;
-
 	pin_desc_idx = ice_ptp_find_pin_idx(pf, PTP_PF_PEROUT, rq->index);
 	if (pin_desc_idx < 0)
 		return -EIO;
 
 	gpio_pin = pf->ptp.ice_pin_desc[pin_desc_idx].gpio[1];
+	prop_delay_ns = pf->ptp.ice_pin_desc[pin_desc_idx].delay[1];
 	period = rq->period.sec * NSEC_PER_SEC + rq->period.nsec;
 
 	/* If we're disabling the output or period is 0, clear out CLKO and TGT
@@ -1794,7 +1723,7 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq,
 		return ice_ptp_write_perout(hw, rq->index, gpio_pin, 0, 0);
 
 	if (strncmp(pf->ptp.pin_desc[pin_desc_idx].name, "1PPS", 64) == 0 &&
-	    period != NSEC_PER_SEC && hw->ptp.phy_model == ICE_PHY_E82X) {
+	    period != NSEC_PER_SEC && hw->mac_type == ICE_MAC_GENERIC) {
 		dev_err(ice_pf_to_dev(pf), "1PPS pin supports only 1 s period\n");
 		return -EOPNOTSUPP;
 	}
@@ -1813,14 +1742,15 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq,
 		div64_u64_rem(start, period, &phase);
 
 	/* If we have only phase or start time is in the past, start the timer
-	 * at the next multiple of period, maintaining phase.
+	 * at the next multiple of period, maintaining phase at least 0.5 second
+	 * from now, so we have time to write it to HW.
 	 */
-	clk = ice_ptp_read_src_clk_reg(pf, NULL);
-	if (rq->flags & PTP_PEROUT_PHASE || start <= clk - ice_prop_delay(hw))
+	clk = ice_ptp_read_src_clk_reg(pf, NULL) + NSEC_PER_MSEC * 500;
+	if (rq->flags & PTP_PEROUT_PHASE || start <= clk - prop_delay_ns)
 		start = div64_u64(clk + period - 1, period) * period + phase;
 
 	/* Compensate for propagation delay from the generator to the pin. */
-	start -= ice_prop_delay(hw);
+	start -= prop_delay_ns;
 
 	return ice_ptp_write_perout(hw, rq->index, gpio_pin, start, period);
 }
@@ -1860,63 +1790,6 @@ static void ice_ptp_enable_all_perout(struct ice_pf *pf)
 }
 
 /**
- * ice_ptp_disable_shared_pin - Disable enabled pin that shares GPIO
- * @pf: Board private structure
- * @pin: Pin index
- * @func: Assigned function
- *
- * Return: 0 on success, negative error code otherwise
- */
-static int ice_ptp_disable_shared_pin(struct ice_pf *pf, unsigned int pin,
-				      enum ptp_pin_function func)
-{
-	unsigned int gpio_pin;
-
-	switch (func) {
-	case PTP_PF_PEROUT:
-		gpio_pin = pf->ptp.ice_pin_desc[pin].gpio[1];
-		break;
-	case PTP_PF_EXTTS:
-		gpio_pin = pf->ptp.ice_pin_desc[pin].gpio[0];
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	for (unsigned int i = 0; i < pf->ptp.info.n_pins; i++) {
-		struct ptp_pin_desc *pin_desc = &pf->ptp.pin_desc[i];
-		unsigned int chan = pin_desc->chan;
-
-		/* Skip pin idx from the request */
-		if (i == pin)
-			continue;
-
-		if (pin_desc->func == PTP_PF_PEROUT &&
-		    pf->ptp.ice_pin_desc[i].gpio[1] == gpio_pin) {
-			pf->ptp.perout_rqs[chan].period.sec = 0;
-			pf->ptp.perout_rqs[chan].period.nsec = 0;
-			pin_desc->func = PTP_PF_NONE;
-			pin_desc->chan = 0;
-			dev_dbg(ice_pf_to_dev(pf), "Disabling pin %u with shared output GPIO pin %u\n",
-				i, gpio_pin);
-			return ice_ptp_cfg_perout(pf, &pf->ptp.perout_rqs[chan],
-						  false);
-		} else if (pf->ptp.pin_desc->func == PTP_PF_EXTTS &&
-			   pf->ptp.ice_pin_desc[i].gpio[0] == gpio_pin) {
-			pf->ptp.extts_rqs[chan].flags &= ~PTP_ENABLE_FEATURE;
-			pin_desc->func = PTP_PF_NONE;
-			pin_desc->chan = 0;
-			dev_dbg(ice_pf_to_dev(pf), "Disabling pin %u with shared input GPIO pin %u\n",
-				i, gpio_pin);
-			return ice_ptp_cfg_extts(pf, &pf->ptp.extts_rqs[chan],
-						 false);
-		}
-	}
-
-	return 0;
-}
-
-/**
  * ice_verify_pin - verify if pin supports requested pin function
  * @info: the driver's PTP info structure
  * @pin: Pin index
@@ -1950,14 +1823,6 @@ static int ice_verify_pin(struct ptp_clock_info *info, unsigned int pin,
 		return -EOPNOTSUPP;
 	}
 
-	/* On adapters with SMA_CTRL disable other pins that share same GPIO */
-	if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) {
-		ice_ptp_disable_shared_pin(pf, pin, func);
-		pf->ptp.pin_desc[pin].func = func;
-		pf->ptp.pin_desc[pin].chan = chan;
-		return ice_ptp_set_sma_cfg(pf);
-	}
-
 	return 0;
 }
 
@@ -2048,7 +1913,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts)
 	/* For Vernier mode on E82X, we need to recalibrate after new settime.
 	 * Start with marking timestamps as invalid.
 	 */
-	if (ice_get_phy_model(hw) == ICE_PHY_E82X) {
+	if (hw->mac_type == ICE_MAC_GENERIC) {
 		err = ice_ptp_clear_phy_offset_ready_e82x(hw);
 		if (err)
 			dev_warn(ice_pf_to_dev(pf), "Failed to mark timestamps as invalid before settime\n");
@@ -2072,7 +1937,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts)
 	ice_ptp_enable_all_perout(pf);
 
 	/* Recalibrate and re-enable timestamp blocks for E822/E823 */
-	if (ice_get_phy_model(hw) == ICE_PHY_E82X)
+	if (hw->mac_type == ICE_MAC_GENERIC)
 		ice_ptp_restart_all_phy(pf);
 exit:
 	if (err) {
@@ -2150,93 +2015,158 @@ static int ice_ptp_adjtime(struct ptp_clock_info *info, s64 delta)
 	return 0;
 }
 
+/**
+ * struct ice_crosststamp_cfg - Device cross timestamp configuration
+ * @lock_reg: The hardware semaphore lock to use
+ * @lock_busy: Bit in the semaphore lock indicating the lock is busy
+ * @ctl_reg: The hardware register to request cross timestamp
+ * @ctl_active: Bit in the control register to request cross timestamp
+ * @art_time_l: Lower 32-bits of ART system time
+ * @art_time_h: Upper 32-bits of ART system time
+ * @dev_time_l: Lower 32-bits of device time (per timer index)
+ * @dev_time_h: Upper 32-bits of device time (per timer index)
+ */
+struct ice_crosststamp_cfg {
+	/* HW semaphore lock register */
+	u32 lock_reg;
+	u32 lock_busy;
+
+	/* Capture control register */
+	u32 ctl_reg;
+	u32 ctl_active;
+
+	/* Time storage */
+	u32 art_time_l;
+	u32 art_time_h;
+	u32 dev_time_l[2];
+	u32 dev_time_h[2];
+};
+
+static const struct ice_crosststamp_cfg ice_crosststamp_cfg_e82x = {
+	.lock_reg = PFHH_SEM,
+	.lock_busy = PFHH_SEM_BUSY_M,
+	.ctl_reg = GLHH_ART_CTL,
+	.ctl_active = GLHH_ART_CTL_ACTIVE_M,
+	.art_time_l = GLHH_ART_TIME_L,
+	.art_time_h = GLHH_ART_TIME_H,
+	.dev_time_l[0] = GLTSYN_HHTIME_L(0),
+	.dev_time_h[0] = GLTSYN_HHTIME_H(0),
+	.dev_time_l[1] = GLTSYN_HHTIME_L(1),
+	.dev_time_h[1] = GLTSYN_HHTIME_H(1),
+};
+
 #ifdef CONFIG_ICE_HWTS
+static const struct ice_crosststamp_cfg ice_crosststamp_cfg_e830 = {
+	.lock_reg = E830_PFPTM_SEM,
+	.lock_busy = E830_PFPTM_SEM_BUSY_M,
+	.ctl_reg = E830_GLPTM_ART_CTL,
+	.ctl_active = E830_GLPTM_ART_CTL_ACTIVE_M,
+	.art_time_l = E830_GLPTM_ART_TIME_L,
+	.art_time_h = E830_GLPTM_ART_TIME_H,
+	.dev_time_l[0] = E830_GLTSYN_PTMTIME_L(0),
+	.dev_time_h[0] = E830_GLTSYN_PTMTIME_H(0),
+	.dev_time_l[1] = E830_GLTSYN_PTMTIME_L(1),
+	.dev_time_h[1] = E830_GLTSYN_PTMTIME_H(1),
+};
+
+#endif /* CONFIG_ICE_HWTS */
+/**
+ * struct ice_crosststamp_ctx - Device cross timestamp context
+ * @snapshot: snapshot of system clocks for historic interpolation
+ * @pf: pointer to the PF private structure
+ * @cfg: pointer to hardware configuration for cross timestamp
+ */
+struct ice_crosststamp_ctx {
+	struct system_time_snapshot snapshot;
+	struct ice_pf *pf;
+	const struct ice_crosststamp_cfg *cfg;
+};
+
 /**
- * ice_ptp_get_syncdevicetime - Get the cross time stamp info
+ * ice_capture_crosststamp - Capture a device/system cross timestamp
  * @device: Current device time
  * @system: System counter value read synchronously with device time
- * @ctx: Context provided by timekeeping code
+ * @__ctx: Context passed from ice_ptp_getcrosststamp
  *
  * Read device and system (ART) clock simultaneously and return the corrected
  * clock values in ns.
+ *
+ * Return: zero on success, or a negative error code on failure.
  */
-static int
-ice_ptp_get_syncdevicetime(ktime_t *device,
-			   struct system_counterval_t *system,
-			   void *ctx)
+static int ice_capture_crosststamp(ktime_t *device,
+				   struct system_counterval_t *system,
+				   void *__ctx)
 {
-	struct ice_pf *pf = (struct ice_pf *)ctx;
-	struct ice_hw *hw = &pf->hw;
-	u32 hh_lock, hh_art_ctl;
-	int i;
+	struct ice_crosststamp_ctx *ctx = __ctx;
+	const struct ice_crosststamp_cfg *cfg;
+	u32 lock, ctl, ts_lo, ts_hi, tmr_idx;
+	struct ice_pf *pf;
+	struct ice_hw *hw;
+	int err;
+	u64 ts;
 
-#define MAX_HH_HW_LOCK_TRIES	5
-#define MAX_HH_CTL_LOCK_TRIES	100
+	cfg = ctx->cfg;
+	pf = ctx->pf;
+	hw = &pf->hw;
 
-	for (i = 0; i < MAX_HH_HW_LOCK_TRIES; i++) {
-		/* Get the HW lock */
-		hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id));
-		if (hh_lock & PFHH_SEM_BUSY_M) {
-			usleep_range(10000, 15000);
-			continue;
-		}
-		break;
-	}
-	if (hh_lock & PFHH_SEM_BUSY_M) {
-		dev_err(ice_pf_to_dev(pf), "PTP failed to get hh lock\n");
+	tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc;
+	if (tmr_idx > 1)
+		return -EINVAL;
+
+	/* Poll until we obtain the cross-timestamp hardware semaphore */
+	err = rd32_poll_timeout(hw, cfg->lock_reg, lock,
+				!(lock & cfg->lock_busy),
+				10 * USEC_PER_MSEC, 50 * USEC_PER_MSEC);
+	if (err) {
+		dev_err(ice_pf_to_dev(pf), "PTP failed to get cross timestamp lock\n");
 		return -EBUSY;
 	}
 
+	/* Snapshot system time for historic interpolation */
+	ktime_get_snapshot(&ctx->snapshot);
+
 	/* Program cmd to master timer */
 	ice_ptp_src_cmd(hw, ICE_PTP_READ_TIME);
 
 	/* Start the ART and device clock sync sequence */
-	hh_art_ctl = rd32(hw, GLHH_ART_CTL);
-	hh_art_ctl = hh_art_ctl | GLHH_ART_CTL_ACTIVE_M;
-	wr32(hw, GLHH_ART_CTL, hh_art_ctl);
-
-	for (i = 0; i < MAX_HH_CTL_LOCK_TRIES; i++) {
-		/* Wait for sync to complete */
-		hh_art_ctl = rd32(hw, GLHH_ART_CTL);
-		if (hh_art_ctl & GLHH_ART_CTL_ACTIVE_M) {
-			udelay(1);
-			continue;
-		} else {
-			u32 hh_ts_lo, hh_ts_hi, tmr_idx;
-			u64 hh_ts;
-
-			tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc;
-			/* Read ART time */
-			hh_ts_lo = rd32(hw, GLHH_ART_TIME_L);
-			hh_ts_hi = rd32(hw, GLHH_ART_TIME_H);
-			hh_ts = ((u64)hh_ts_hi << 32) | hh_ts_lo;
-			system->cycles = hh_ts;
-			system->cs_id = CSID_X86_ART;
-			/* Read Device source clock time */
-			hh_ts_lo = rd32(hw, GLTSYN_HHTIME_L(tmr_idx));
-			hh_ts_hi = rd32(hw, GLTSYN_HHTIME_H(tmr_idx));
-			hh_ts = ((u64)hh_ts_hi << 32) | hh_ts_lo;
-			*device = ns_to_ktime(hh_ts);
-			break;
-		}
-	}
+	ctl = rd32(hw, cfg->ctl_reg);
+	ctl |= cfg->ctl_active;
+	wr32(hw, cfg->ctl_reg, ctl);
 
+	/* Poll until hardware completes the capture */
+	err = rd32_poll_timeout(hw, cfg->ctl_reg, ctl, !(ctl & cfg->ctl_active),
+				5, 20 * USEC_PER_MSEC);
+	if (err)
+		goto err_timeout;
+
+	/* Read ART system time */
+	ts_lo = rd32(hw, cfg->art_time_l);
+	ts_hi = rd32(hw, cfg->art_time_h);
+	ts = ((u64)ts_hi << 32) | ts_lo;
+	system->cycles = ts;
+	system->cs_id = CSID_X86_ART;
+	system->use_nsecs = true;
+
+	/* Read Device source clock time */
+	ts_lo = rd32(hw, cfg->dev_time_l[tmr_idx]);
+	ts_hi = rd32(hw, cfg->dev_time_h[tmr_idx]);
+	ts = ((u64)ts_hi << 32) | ts_lo;
+	*device = ns_to_ktime(ts);
+
+err_timeout:
 	/* Clear the master timer */
 	ice_ptp_src_cmd(hw, ICE_PTP_NOP);
 
 	/* Release HW lock */
-	hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id));
-	hh_lock = hh_lock & ~PFHH_SEM_BUSY_M;
-	wr32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id), hh_lock);
-
-	if (i == MAX_HH_CTL_LOCK_TRIES)
-		return -ETIMEDOUT;
+	lock = rd32(hw, cfg->lock_reg);
+	lock &= ~cfg->lock_busy;
+	wr32(hw, cfg->lock_reg, lock);
 
-	return 0;
+	return err;
 }
 
 /**
- * ice_ptp_getcrosststamp_e82x - Capture a device cross timestamp
+ * ice_ptp_getcrosststamp - Capture a device cross timestamp
  * @info: the driver's PTP info structure
  * @cts: The memory to fill the cross timestamp info
  *
@@ -2244,41 +2174,55 @@ ice_ptp_get_syncdevicetime(ktime_t *device,
  * clock. Fill the cross timestamp information and report it back to the
  * caller.
  *
- * This is only valid for E822 and E823 devices which have support for
- * generating the cross timestamp via PCIe PTM.
- *
  * In order to correctly correlate the ART timestamp back to the TSC time, the
  * CPU must have X86_FEATURE_TSC_KNOWN_FREQ.
+ *
+ * Return: zero on success, or a negative error code on failure.
  */
-static int
-ice_ptp_getcrosststamp_e82x(struct ptp_clock_info *info,
-			    struct system_device_crosststamp *cts)
+static int ice_ptp_getcrosststamp(struct ptp_clock_info *info,
+				  struct system_device_crosststamp *cts)
 {
 	struct ice_pf *pf = ptp_info_to_pf(info);
+	struct ice_crosststamp_ctx ctx = {
+		.pf = pf,
+	};
+
+	switch (pf->hw.mac_type) {
+	case ICE_MAC_GENERIC:
+	case ICE_MAC_GENERIC_3K_E825:
+		ctx.cfg = &ice_crosststamp_cfg_e82x;
+		break;
+#ifdef CONFIG_ICE_HWTS
+	case ICE_MAC_E830:
+		ctx.cfg = &ice_crosststamp_cfg_e830;
+		break;
+#endif /* CONFIG_ICE_HWTS */
+	default:
+		return -EOPNOTSUPP;
+	}
 
-	return get_device_system_crosststamp(ice_ptp_get_syncdevicetime,
-					     pf, NULL, cts);
+	return get_device_system_crosststamp(ice_capture_crosststamp, &ctx,
+					     &ctx.snapshot, cts);
 }
-#endif /* CONFIG_ICE_HWTS */
 
 /**
- * ice_ptp_get_ts_config - ioctl interface to read the timestamping config
- * @pf: Board private structure
- * @ifr: ioctl data
+ * ice_ptp_hwtstamp_get - interface to read the timestamping config
+ * @netdev: Pointer to network interface device structure
+ * @config: Timestamping configuration structure
  *
  * Copy the timestamping config to user buffer
  */
-int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr)
+int ice_ptp_hwtstamp_get(struct net_device *netdev,
+			 struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config *config;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 
 	if (pf->ptp.state != ICE_PTP_READY)
 		return -EIO;
 
-	config = &pf->ptp.tstamp_config;
+	*config = pf->ptp.tstamp_config;
 
-	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 /**
@@ -2286,8 +2230,8 @@ int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr)
  * @pf: Board private structure
  * @config: hwtstamp settings requested or saved
  */
-static int
-ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config)
+static int ice_ptp_set_timestamp_mode(struct ice_pf *pf,
+				      struct kernel_hwtstamp_config *config)
 {
 	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
@@ -2331,32 +2275,31 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config)
 }
 
 /**
- * ice_ptp_set_ts_config - ioctl interface to control the timestamping
- * @pf: Board private structure
- * @ifr: ioctl data
+ * ice_ptp_hwtstamp_set - interface to control the timestamping
+ * @netdev: Pointer to network interface device structure
+ * @config: Timestamping configuration structure
+ * @extack: Netlink extended ack structure for error reporting
  *
  * Get the user config and store it
  */
-int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr)
+int ice_ptp_hwtstamp_set(struct net_device *netdev,
+			 struct kernel_hwtstamp_config *config,
+			 struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	int err;
 
 	if (pf->ptp.state != ICE_PTP_READY)
 		return -EAGAIN;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	err = ice_ptp_set_timestamp_mode(pf, &config);
+	err = ice_ptp_set_timestamp_mode(pf, config);
 	if (err)
 		return err;
 
 	/* Return the actual configuration set */
-	config = pf->ptp.tstamp_config;
+	*config = pf->ptp.tstamp_config;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 /**
@@ -2402,14 +2345,14 @@ static void ice_ptp_setup_pin_cfg(struct ice_pf *pf)
 	for (unsigned int i = 0; i < pf->ptp.info.n_pins; i++) {
 		const struct ice_ptp_pin_desc *desc = &pf->ptp.ice_pin_desc[i];
 		struct ptp_pin_desc *pin = &pf->ptp.pin_desc[i];
-		const char *name = NULL;
+		const char *name;
 
 		if (!ice_is_feature_supported(pf, ICE_F_SMA_CTRL))
 			name = ice_pin_names[desc->name_idx];
-		else if (desc->name_idx != GPIO_NA)
-			name = ice_pin_names_nvm[desc->name_idx];
-		if (name)
-			strscpy(pin->name, name, sizeof(pin->name));
+		else
+			name = ice_pin_names_dpll[desc->name_idx];
+
+		strscpy(pin->name, name, sizeof(pin->name));
 
 		pin->index = i;
 	}
@@ -2421,8 +2364,8 @@ static void ice_ptp_setup_pin_cfg(struct ice_pf *pf)
  * ice_ptp_disable_pins - Disable PTP pins
  * @pf: pointer to the PF structure
  *
- * Disable the OS access to the SMA pins. Called to clear out the OS
- * indications of pin support when we fail to setup the SMA control register.
+ * Disable the OS access to the pins. Called to clear out the OS
+ * indications of pin support when we fail to setup pin array.
  */
 static void ice_ptp_disable_pins(struct ice_pf *pf)
 {
@@ -2463,40 +2406,30 @@ static int ice_ptp_parse_sdp_entries(struct ice_pf *pf, __le16 *entries,
 	for (i = 0; i < num_entries; i++) {
 		u16 entry = le16_to_cpu(entries[i]);
 		DECLARE_BITMAP(bitmap, GPIO_NA);
-		unsigned int bitmap_idx;
+		unsigned int idx;
 		bool dir;
 		u16 gpio;
 
 		*bitmap = FIELD_GET(ICE_AQC_NVM_SDP_AC_PIN_M, entry);
+
+		/* Check if entry's pin bitmap is valid. */
+		if (bitmap_empty(bitmap, GPIO_NA))
+			continue;
+
 		dir = !!FIELD_GET(ICE_AQC_NVM_SDP_AC_DIR_M, entry);
 		gpio = FIELD_GET(ICE_AQC_NVM_SDP_AC_SDP_NUM_M, entry);
-		for_each_set_bit(bitmap_idx, bitmap, GPIO_NA + 1) {
-			unsigned int idx;
-
-			/* Check if entry's pin bit is valid */
-			if (bitmap_idx >= NUM_PTP_PINS_NVM &&
-			    bitmap_idx != GPIO_NA)
-				continue;
 
-			/* Check if pin already exists */
-			for (idx = 0; idx < ICE_N_PINS_MAX; idx++)
-				if (pins[idx].name_idx == bitmap_idx)
-					break;
-
-			if (idx == ICE_N_PINS_MAX) {
-				/* Pin not found, setup its entry and name */
-				idx = n_pins++;
-				pins[idx].name_idx = bitmap_idx;
-				if (bitmap_idx == GPIO_NA)
-					strscpy(pf->ptp.pin_desc[idx].name,
-						ice_pin_names[gpio],
-						sizeof(pf->ptp.pin_desc[idx]
-							       .name));
-			}
+		for (idx = 0; idx < ICE_N_PINS_MAX; idx++) {
+			if (pins[idx].name_idx == gpio)
+				break;
+		}
 
-			/* Setup in/out GPIO number */
-			pins[idx].gpio[dir] = gpio;
+		if (idx == ICE_N_PINS_MAX) {
+			/* Pin not found, setup its entry and name */
+			idx = n_pins++;
+			pins[idx].name_idx = gpio;
 		}
+		pins[idx].gpio[dir] = gpio;
 	}
 
 	for (i = 0; i < n_pins; i++) {
@@ -2520,18 +2453,14 @@ static int ice_ptp_parse_sdp_entries(struct ice_pf *pf, __le16 *entries,
  */
 static void ice_ptp_set_funcs_e82x(struct ice_pf *pf)
 {
-#ifdef CONFIG_ICE_HWTS
-	if (boot_cpu_has(X86_FEATURE_ART) &&
-	    boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ))
-		pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp_e82x;
+	pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp;
 
-#endif /* CONFIG_ICE_HWTS */
-	if (ice_is_e825c(&pf->hw)) {
+	if (pf->hw.mac_type == ICE_MAC_GENERIC_3K_E825) {
 		pf->ptp.ice_pin_desc = ice_pin_desc_e825c;
-		pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e825c);
+		pf->ptp.info.n_pins = ARRAY_SIZE(ice_pin_desc_e825c);
 	} else {
 		pf->ptp.ice_pin_desc = ice_pin_desc_e82x;
-		pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e82x);
+		pf->ptp.info.n_pins = ARRAY_SIZE(ice_pin_desc_e82x);
 	}
 	ice_ptp_setup_pin_cfg(pf);
 }
@@ -2557,15 +2486,13 @@ static void ice_ptp_set_funcs_e810(struct ice_pf *pf)
 	if (err) {
 		/* SDP section does not exist in NVM or is corrupted */
 		if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) {
-			ptp->ice_pin_desc = ice_pin_desc_e810_sma;
-			ptp->info.n_pins =
-				ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e810_sma);
+			ptp->ice_pin_desc = ice_pin_desc_dpll;
+			ptp->info.n_pins = ARRAY_SIZE(ice_pin_desc_dpll);
 		} else {
 			pf->ptp.ice_pin_desc = ice_pin_desc_e810;
-			pf->ptp.info.n_pins =
-				ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e810);
-			err = 0;
+			pf->ptp.info.n_pins = ARRAY_SIZE(ice_pin_desc_e810);
 		}
+		err = 0;
 	} else {
 		desc = devm_kcalloc(ice_pf_to_dev(pf), ICE_N_PINS_MAX,
 				    sizeof(struct ice_ptp_pin_desc),
@@ -2583,8 +2510,6 @@ static void ice_ptp_set_funcs_e810(struct ice_pf *pf)
 	ptp->info.pin_config = ptp->pin_desc;
 	ice_ptp_setup_pin_cfg(pf);
 
-	if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL))
-		err = ice_ptp_set_sma_cfg(pf);
 err:
 	if (err) {
 		devm_kfree(ice_pf_to_dev(pf), desc);
@@ -2593,6 +2518,28 @@ err:
 }
 
 /**
+ * ice_ptp_set_funcs_e830 - Set specialized functions for E830 support
+ * @pf: Board private structure
+ *
+ * Assign functions to the PTP capabiltiies structure for E830 devices.
+ * Functions which operate across all device families should be set directly
+ * in ice_ptp_set_caps. Only add functions here which are distinct for E830
+ * devices.
+ */
+static void ice_ptp_set_funcs_e830(struct ice_pf *pf)
+{
+#ifdef CONFIG_ICE_HWTS
+	if (pcie_ptm_enabled(pf->pdev) && boot_cpu_has(X86_FEATURE_ART))
+		pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp;
+
+#endif /* CONFIG_ICE_HWTS */
+	/* Rest of the config is the same as base E810 */
+	pf->ptp.ice_pin_desc = ice_pin_desc_e810;
+	pf->ptp.info.n_pins = ARRAY_SIZE(ice_pin_desc_e810);
+	ice_ptp_setup_pin_cfg(pf);
+}
+
+/**
  * ice_ptp_set_caps - Set PTP capabilities
  * @pf: Board private structure
  */
@@ -2614,10 +2561,25 @@ static void ice_ptp_set_caps(struct ice_pf *pf)
 	info->enable = ice_ptp_gpio_enable;
 	info->verify = ice_verify_pin;
 
-	if (ice_is_e810(&pf->hw))
+	info->supported_extts_flags = PTP_RISING_EDGE |
+				      PTP_FALLING_EDGE |
+				      PTP_STRICT_FLAGS;
+	info->supported_perout_flags = PTP_PEROUT_PHASE;
+
+	switch (pf->hw.mac_type) {
+	case ICE_MAC_E810:
 		ice_ptp_set_funcs_e810(pf);
-	else
+		return;
+	case ICE_MAC_E830:
+		ice_ptp_set_funcs_e830(pf);
+		return;
+	case ICE_MAC_GENERIC:
+	case ICE_MAC_GENERIC_3K_E825:
 		ice_ptp_set_funcs_e82x(pf);
+		return;
+	default:
+		return;
+	}
 }
 
 /**
@@ -2728,6 +2690,68 @@ enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf)
 }
 
 /**
+ * ice_ptp_ts_irq - Process the PTP Tx timestamps in IRQ context
+ * @pf: Board private structure
+ *
+ * Return: IRQ_WAKE_THREAD if Tx timestamp read has to be handled in the bottom
+ *         half of the interrupt and IRQ_HANDLED otherwise.
+ */
+irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf)
+{
+	struct ice_hw *hw = &pf->hw;
+
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+		/* E810 capable of low latency timestamping with interrupt can
+		 * request a single timestamp in the top half and wait for
+		 * a second LL TS interrupt from the FW when it's ready.
+		 */
+		if (hw->dev_caps.ts_dev_info.ts_ll_int_read) {
+			struct ice_ptp_tx *tx = &pf->ptp.port.tx;
+			u8 idx, last;
+
+			if (!ice_pf_state_is_nominal(pf))
+				return IRQ_HANDLED;
+
+			spin_lock(&tx->lock);
+			if (tx->init) {
+				last = tx->last_ll_ts_idx_read + 1;
+				idx = find_next_bit_wrap(tx->in_use, tx->len,
+							 last);
+				if (idx != tx->len)
+					ice_ptp_req_tx_single_tstamp(tx, idx);
+			}
+			spin_unlock(&tx->lock);
+
+			return IRQ_HANDLED;
+		}
+		fallthrough; /* non-LL_TS E810 */
+	case ICE_MAC_GENERIC:
+	case ICE_MAC_GENERIC_3K_E825:
+		/* All other devices process timestamps in the bottom half due
+		 * to sleeping or polling.
+		 */
+		if (!ice_ptp_pf_handles_tx_interrupt(pf))
+			return IRQ_HANDLED;
+
+		set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread);
+		return IRQ_WAKE_THREAD;
+	case ICE_MAC_E830:
+		/* E830 can read timestamps in the top half using rd32() */
+		if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) {
+			/* Process outstanding Tx timestamps. If there
+			 * is more work, re-arm the interrupt to trigger again.
+			 */
+			wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M);
+			ice_flush(hw);
+		}
+		return IRQ_HANDLED;
+	default:
+		return IRQ_HANDLED;
+	}
+}
+
+/**
  * ice_ptp_maybe_trigger_tx_interrupt - Trigger Tx timstamp interrupt
  * @pf: Board private structure
  *
@@ -2747,7 +2771,7 @@ static void ice_ptp_maybe_trigger_tx_interrupt(struct ice_pf *pf)
 	bool trigger_oicr = false;
 	unsigned int i;
 
-	if (ice_is_e810(hw))
+	if (!pf->ptp.port.tx.has_ready_bitmap)
 		return;
 
 	if (!ice_pf_src_tmr_owned(pf))
@@ -2794,6 +2818,32 @@ static void ice_ptp_periodic_work(struct kthread_work *work)
 }
 
 /**
+ * ice_ptp_prepare_rebuild_sec - Prepare second NAC for PTP reset or rebuild
+ * @pf: Board private structure
+ * @rebuild: rebuild if true, prepare if false
+ * @reset_type: the reset type being performed
+ */
+static void ice_ptp_prepare_rebuild_sec(struct ice_pf *pf, bool rebuild,
+					enum ice_reset_req reset_type)
+{
+	struct list_head *entry;
+
+	list_for_each(entry, &pf->adapter->ports.ports) {
+		struct ice_ptp_port *port = list_entry(entry,
+						       struct ice_ptp_port,
+						       list_node);
+		struct ice_pf *peer_pf = ptp_port_to_pf(port);
+
+		if (!ice_is_primary(&peer_pf->hw)) {
+			if (rebuild)
+				ice_ptp_rebuild(peer_pf, reset_type);
+			else
+				ice_ptp_prepare_for_reset(peer_pf, reset_type);
+		}
+	}
+}
+
+/**
  * ice_ptp_prepare_for_reset - Prepare PTP for reset
  * @pf: Board private structure
  * @reset_type: the reset type being performed
@@ -2801,6 +2851,7 @@ static void ice_ptp_periodic_work(struct kthread_work *work)
 void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 {
 	struct ice_ptp *ptp = &pf->ptp;
+	struct ice_hw *hw = &pf->hw;
 	u8 src_tmr;
 
 	if (ptp->state != ICE_PTP_READY)
@@ -2816,6 +2867,9 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 	if (reset_type == ICE_RESET_PFR)
 		return;
 
+	if (ice_pf_src_tmr_owned(pf) && hw->mac_type == ICE_MAC_GENERIC_3K_E825)
+		ice_ptp_prepare_rebuild_sec(pf, false, reset_type);
+
 	ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx);
 
 	/* Disable periodic outputs */
@@ -2849,6 +2903,10 @@ static int ice_ptp_rebuild_owner(struct ice_pf *pf)
 	if (err)
 		return err;
 
+	err = ice_tspll_init(hw);
+	if (err)
+		return err;
+
 	/* Acquire the global hardware lock */
 	if (!ice_ptp_lock(hw)) {
 		err = -EBUSY;
@@ -2882,14 +2940,12 @@ static int ice_ptp_rebuild_owner(struct ice_pf *pf)
 	 */
 	ice_ptp_flush_all_tx_tracker(pf);
 
-	if (!ice_is_e810(hw)) {
-		/* Enable quad interrupts */
-		err = ice_ptp_cfg_phy_interrupt(pf, true, 1);
-		if (err)
-			return err;
+	/* Enable quad interrupts */
+	err = ice_ptp_cfg_phy_interrupt(pf, true, 1);
+	if (err)
+		return err;
 
-		ice_ptp_restart_all_phy(pf);
-	}
+	ice_ptp_restart_all_phy(pf);
 
 	/* Re-enable all periodic outputs and external timestamp events */
 	ice_ptp_enable_all_perout(pf);
@@ -2939,12 +2995,6 @@ err:
 	dev_err(ice_pf_to_dev(pf), "PTP reset failed %d\n", err);
 }
 
-static bool ice_is_primary(struct ice_hw *hw)
-{
-	return ice_is_e825c(hw) && ice_is_dual(hw) ?
-		!!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M) : true;
-}
-
 static int ice_ptp_setup_adapter(struct ice_pf *pf)
 {
 	if (!ice_pf_src_tmr_owned(pf) || !ice_is_primary(&pf->hw))
@@ -2960,7 +3010,7 @@ static int ice_ptp_setup_pf(struct ice_pf *pf)
 	struct ice_ptp *ctrl_ptp = ice_get_ctrl_ptp(pf);
 	struct ice_ptp *ptp = &pf->ptp;
 
-	if (WARN_ON(!ctrl_ptp) || ice_get_phy_model(&pf->hw) == ICE_PHY_UNSUP)
+	if (WARN_ON(!ctrl_ptp) || pf->hw.mac_type == ICE_MAC_UNKNOWN)
 		return -ENODEV;
 
 	INIT_LIST_HEAD(&ptp->port.list_node);
@@ -2977,7 +3027,7 @@ static void ice_ptp_cleanup_pf(struct ice_pf *pf)
 {
 	struct ice_ptp *ptp = &pf->ptp;
 
-	if (ice_get_phy_model(&pf->hw) != ICE_PHY_UNSUP) {
+	if (pf->hw.mac_type != ICE_MAC_UNKNOWN) {
 		mutex_lock(&pf->adapter->ports.lock);
 		list_del(&ptp->port.list_node);
 		mutex_unlock(&pf->adapter->ports.lock);
@@ -3024,6 +3074,13 @@ static int ice_ptp_init_owner(struct ice_pf *pf)
 		return err;
 	}
 
+	err = ice_tspll_init(hw);
+	if (err) {
+		dev_err(ice_pf_to_dev(pf), "Failed to initialize CGU, status %d\n",
+			err);
+		return err;
+	}
+
 	/* Acquire the global hardware lock */
 	if (!ice_ptp_lock(hw)) {
 		err = -EBUSY;
@@ -3080,7 +3137,7 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp)
 	/* Allocate a kworker for handling work required for the ports
 	 * connected to the PTP hardware clock.
 	 */
-	kworker = kthread_create_worker(0, "ice-ptp-%s",
+	kworker = kthread_run_worker(0, "ice-ptp-%s",
 					dev_name(ice_pf_to_dev(pf)));
 	if (IS_ERR(kworker))
 		return PTR_ERR(kworker);
@@ -3097,6 +3154,8 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp)
  * ice_ptp_init_port - Initialize PTP port structure
  * @pf: Board private structure
  * @ptp_port: PTP port structure
+ *
+ * Return: 0 on success, -ENODEV on invalid MAC type, -ENOMEM on failed alloc.
  */
 static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
 {
@@ -3104,16 +3163,14 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
 
 	mutex_init(&ptp_port->ps_lock);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_ptp_init_tx_eth56g(pf, &ptp_port->tx,
-					      ptp_port->port_num);
-	case ICE_PHY_E810:
-		return ice_ptp_init_tx_e810(pf, &ptp_port->tx);
-	case ICE_PHY_E82X:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_ptp_init_tx(pf, &ptp_port->tx, ptp_port->port_num);
+	case ICE_MAC_GENERIC:
 		kthread_init_delayed_work(&ptp_port->ov_work,
 					  ice_ptp_wait_for_offsets);
-
 		return ice_ptp_init_tx_e82x(pf, &ptp_port->tx,
 					    ptp_port->port_num);
 	default:
@@ -3132,8 +3189,8 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
  */
 static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf)
 {
-	switch (ice_get_phy_model(&pf->hw)) {
-	case ICE_PHY_E82X:
+	switch (pf->hw.mac_type) {
+	case ICE_MAC_GENERIC:
 		/* E822 based PHY has the clock owner process the interrupt
 		 * for all ports.
 		 */
@@ -3168,6 +3225,12 @@ void ice_ptp_init(struct ice_pf *pf)
 
 	ptp->state = ICE_PTP_INITIALIZING;
 
+	if (hw->lane_num < 0) {
+		err = hw->lane_num;
+		goto err_exit;
+	}
+	ptp->port.port_num = hw->lane_num;
+
 	ice_ptp_init_hw(hw);
 
 	ice_ptp_init_tx_interrupt_mode(pf);
@@ -3188,13 +3251,9 @@ void ice_ptp_init(struct ice_pf *pf)
 	if (err)
 		goto err_exit;
 
-	ptp->port.port_num = hw->pf_id;
-	if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo)
-		ptp->port.port_num = hw->pf_id * 2;
-
 	err = ice_ptp_init_port(pf, &ptp->port);
 	if (err)
-		goto err_exit;
+		goto err_clean_pf;
 
 	/* Start the PHY timestamping block */
 	ice_ptp_reset_phy_timestamping(pf);
@@ -3211,13 +3270,19 @@ void ice_ptp_init(struct ice_pf *pf)
 	dev_info(ice_pf_to_dev(pf), "PTP init successful\n");
 	return;
 
+err_clean_pf:
+	mutex_destroy(&ptp->port.ps_lock);
+	ice_ptp_cleanup_pf(pf);
 err_exit:
 	/* If we registered a PTP clock, release it */
 	if (pf->ptp.clock) {
 		ptp_clock_unregister(ptp->clock);
 		pf->ptp.clock = NULL;
 	}
-	ptp->state = ICE_PTP_ERROR;
+	/* Keep ICE_PTP_UNINIT state to avoid ambiguity at driver unload
+	 * and to avoid duplicated resources release.
+	 */
+	ptp->state = ICE_PTP_UNINIT;
 	dev_err(ice_pf_to_dev(pf), "PTP failed %d\n", err);
 }
 
@@ -3230,9 +3295,19 @@ err_exit:
  */
 void ice_ptp_release(struct ice_pf *pf)
 {
-	if (pf->ptp.state != ICE_PTP_READY)
+	if (pf->ptp.state == ICE_PTP_UNINIT)
 		return;
 
+	if (pf->ptp.state != ICE_PTP_READY) {
+		mutex_destroy(&pf->ptp.port.ps_lock);
+		ice_ptp_cleanup_pf(pf);
+		if (pf->ptp.clock) {
+			ptp_clock_unregister(pf->ptp.clock);
+			pf->ptp.clock = NULL;
+		}
+		return;
+	}
+
 	pf->ptp.state = ICE_PTP_UNINIT;
 
 	/* Disable timestamping for both Tx and Rx */
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
index 824e73b677a4..27016aac4f1e 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -128,8 +128,7 @@ struct ice_ptp_tx {
 /* Quad and port information for initializing timestamp blocks */
 #define INDEX_PER_QUAD			64
 #define INDEX_PER_PORT_E82X		16
-#define INDEX_PER_PORT_E810		64
-#define INDEX_PER_PORT_ETH56G		64
+#define INDEX_PER_PORT			64
 
 /**
  * struct ice_ptp_port - data used to initialize an external port for PTP
@@ -203,14 +202,12 @@ enum ice_ptp_pin_nvm {
 
 /* Pin definitions for PTP */
 #define ICE_N_PINS_MAX			6
-#define ICE_SMA_PINS_NUM		4
-#define ICE_PIN_DESC_ARR_LEN(_arr)	(sizeof(_arr) / \
-					 sizeof(struct ice_ptp_pin_desc))
 
 /**
  * struct ice_ptp_pin_desc - hardware pin description data
  * @name_idx: index of the name of pin in ice_pin_names
  * @gpio: the associated GPIO input and output pins
+ * @delay: input and output signal delays in nanoseconds
  *
  * Structure describing a PTP-capable GPIO pin that extends ptp_pin_desc array
  * for the device. Device families have separate sets of available pins with
@@ -219,6 +216,7 @@ enum ice_ptp_pin_nvm {
 struct ice_ptp_pin_desc {
 	int name_idx;
 	int gpio[2];
+	unsigned int delay[2];
 };
 
 /**
@@ -239,6 +237,7 @@ struct ice_ptp_pin_desc {
  * @clock: pointer to registered PTP clock device
  * @tstamp_config: hardware timestamping configuration
  * @reset_time: kernel time after clock stop on reset
+ * @tx_hwtstamp_good: number of completed Tx timestamp requests
  * @tx_hwtstamp_skipped: number of Tx time stamp requests skipped
  * @tx_hwtstamp_timeouts: number of Tx skbs discarded with no time stamp
  * @tx_hwtstamp_flushed: number of Tx skbs flushed due to interface closed
@@ -261,8 +260,9 @@ struct ice_ptp {
 	struct ptp_extts_request extts_rqs[GLTSYN_EVNT_H_IDX_MAX];
 	struct ptp_clock_info info;
 	struct ptp_clock *clock;
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 	u64 reset_time;
+	u64 tx_hwtstamp_good;
 	u32 tx_hwtstamp_skipped;
 	u32 tx_hwtstamp_timeouts;
 	u32 tx_hwtstamp_flushed;
@@ -293,8 +293,11 @@ struct ice_ptp {
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
 int ice_ptp_clock_index(struct ice_pf *pf);
 struct ice_pf;
-int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr);
-int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr);
+int ice_ptp_hwtstamp_get(struct net_device *netdev,
+			 struct kernel_hwtstamp_config *config);
+int ice_ptp_hwtstamp_set(struct net_device *netdev,
+			 struct kernel_hwtstamp_config *config,
+			 struct netlink_ext_ack *extack);
 void ice_ptp_restore_timestamp_mode(struct ice_pf *pf);
 
 void ice_ptp_extts_event(struct ice_pf *pf);
@@ -302,6 +305,9 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb);
 void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx);
 void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx);
 enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf);
+irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf);
+u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf,
+			     struct ptp_system_timestamp *sts);
 
 u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc,
 			const struct ice_pkt_ctx *pkt_ctx);
@@ -310,14 +316,18 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf,
 			       enum ice_reset_req reset_type);
 void ice_ptp_init(struct ice_pf *pf);
 void ice_ptp_release(struct ice_pf *pf);
-void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup);
+void ice_ptp_link_change(struct ice_pf *pf, bool linkup);
 #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
-static inline int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr)
+
+static inline int ice_ptp_hwtstamp_get(struct net_device *netdev,
+				       struct kernel_hwtstamp_config *config)
 {
 	return -EOPNOTSUPP;
 }
 
-static inline int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr)
+static inline int ice_ptp_hwtstamp_set(struct net_device *netdev,
+				       struct kernel_hwtstamp_config *config,
+				       struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
@@ -340,6 +350,17 @@ static inline bool ice_ptp_process_ts(struct ice_pf *pf)
 	return true;
 }
 
+static inline irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf)
+{
+	return IRQ_HANDLED;
+}
+
+static inline u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf,
+					   struct ptp_system_timestamp *sts)
+{
+	return 0;
+}
+
 static inline u64
 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc,
 		    const struct ice_pkt_ctx *pkt_ctx)
@@ -358,7 +379,7 @@ static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf,
 }
 static inline void ice_ptp_init(struct ice_pf *pf) { }
 static inline void ice_ptp_release(struct ice_pf *pf) { }
-static inline void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
+static inline void ice_ptp_link_change(struct ice_pf *pf, bool linkup)
 {
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
index 585ce200c60f..19dddd9b53dd 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
@@ -10,70 +10,25 @@
 /* Constants defined for the PTP 1588 clock hardware. */
 
 const struct ice_phy_reg_info_eth56g eth56g_phy_res[NUM_ETH56G_PHY_RES] = {
-	/* ETH56G_PHY_REG_PTP */
-	{
-		/* base_addr */
-		{
-			0x092000,
-			0x126000,
-			0x1BA000,
-			0x24E000,
-			0x2E2000,
-		},
-		/* step */
-		0x98,
+	[ETH56G_PHY_REG_PTP] = {
+		.base_addr = 0x092000,
+		.step = 0x98,
 	},
-	/* ETH56G_PHY_MEM_PTP */
-	{
-		/* base_addr */
-		{
-			0x093000,
-			0x127000,
-			0x1BB000,
-			0x24F000,
-			0x2E3000,
-		},
-		/* step */
-		0x200,
+	[ETH56G_PHY_MEM_PTP] = {
+		.base_addr = 0x093000,
+		.step = 0x200,
 	},
-	/* ETH56G_PHY_REG_XPCS */
-	{
-		/* base_addr */
-		{
-			0x000000,
-			0x009400,
-			0x128000,
-			0x1BC000,
-			0x250000,
-		},
-		/* step */
-		0x21000,
+	[ETH56G_PHY_REG_XPCS] = {
+		.base_addr = 0x000000,
+		.step = 0x21000,
 	},
-	/* ETH56G_PHY_REG_MAC */
-	{
-		/* base_addr */
-		{
-			0x085000,
-			0x119000,
-			0x1AD000,
-			0x241000,
-			0x2D5000,
-		},
-		/* step */
-		0x1000,
+	[ETH56G_PHY_REG_MAC] = {
+		.base_addr = 0x085000,
+		.step = 0x1000,
 	},
-	/* ETH56G_PHY_REG_GPCS */
-	{
-		/* base_addr */
-		{
-			0x084000,
-			0x118000,
-			0x1AC000,
-			0x240000,
-			0x2D4000,
-		},
-		/* step */
-		0x400,
+	[ETH56G_PHY_REG_GPCS] = {
+		.base_addr = 0x084000,
+		.step = 0x400,
 	},
 };
 
@@ -131,7 +86,7 @@ struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD] = {
 		.rx_offset = {
 			.serdes = 0xffffeb27, /* -10.42424 */
 			.no_fec = 0xffffcccd, /* -25.6 */
-			.fc = 0xfffe0014, /* -255.96 */
+			.fc = 0xfffc557b, /* -469.26 */
 			.sfd = 0x4a4, /* 2.32 */
 			.bs_ds = 0x32 /* 0.0969697 */
 		}
@@ -326,7 +281,7 @@ struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD] = {
 
 /* struct ice_time_ref_info_e82x
  *
- * E822 hardware can use different sources as the reference for the PTP
+ * E82X hardware can use different sources as the reference for the PTP
  * hardware clock. Each clock has different characteristics such as a slightly
  * different frequency, etc.
  *
@@ -334,226 +289,53 @@ struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD] = {
  * reference. See the struct ice_time_ref_info_e82x for information about the
  * meaning of each constant.
  */
-const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = {
-	/* ICE_TIME_REF_FREQ_25_000 -> 25 MHz */
+const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TSPLL_FREQ] = {
+	/* ICE_TSPLL_FREQ_25_000 -> 25 MHz */
 	{
 		/* pll_freq */
 		823437500, /* 823.4375 MHz PLL */
 		/* nominal_incval */
 		0x136e44fabULL,
-		/* pps_delay */
-		11,
 	},
 
-	/* ICE_TIME_REF_FREQ_122_880 -> 122.88 MHz */
+	/* ICE_TSPLL_FREQ_122_880 -> 122.88 MHz */
 	{
 		/* pll_freq */
 		783360000, /* 783.36 MHz */
 		/* nominal_incval */
 		0x146cc2177ULL,
-		/* pps_delay */
-		12,
 	},
 
-	/* ICE_TIME_REF_FREQ_125_000 -> 125 MHz */
+	/* ICE_TSPLL_FREQ_125_000 -> 125 MHz */
 	{
 		/* pll_freq */
 		796875000, /* 796.875 MHz */
 		/* nominal_incval */
 		0x141414141ULL,
-		/* pps_delay */
-		12,
 	},
 
-	/* ICE_TIME_REF_FREQ_153_600 -> 153.6 MHz */
+	/* ICE_TSPLL_FREQ_153_600 -> 153.6 MHz */
 	{
 		/* pll_freq */
 		816000000, /* 816 MHz */
 		/* nominal_incval */
 		0x139b9b9baULL,
-		/* pps_delay */
-		12,
 	},
 
-	/* ICE_TIME_REF_FREQ_156_250 -> 156.25 MHz */
+	/* ICE_TSPLL_FREQ_156_250 -> 156.25 MHz */
 	{
 		/* pll_freq */
 		830078125, /* 830.78125 MHz */
 		/* nominal_incval */
 		0x134679aceULL,
-		/* pps_delay */
-		11,
 	},
 
-	/* ICE_TIME_REF_FREQ_245_760 -> 245.76 MHz */
+	/* ICE_TSPLL_FREQ_245_760 -> 245.76 MHz */
 	{
 		/* pll_freq */
 		783360000, /* 783.36 MHz */
 		/* nominal_incval */
 		0x146cc2177ULL,
-		/* pps_delay */
-		12,
-	},
-};
-
-const struct ice_cgu_pll_params_e82x e822_cgu_params[NUM_ICE_TIME_REF_FREQ] = {
-	/* ICE_TIME_REF_FREQ_25_000 -> 25 MHz */
-	{
-		/* refclk_pre_div */
-		1,
-		/* feedback_div */
-		197,
-		/* frac_n_div */
-		2621440,
-		/* post_pll_div */
-		6,
-	},
-
-	/* ICE_TIME_REF_FREQ_122_880 -> 122.88 MHz */
-	{
-		/* refclk_pre_div */
-		5,
-		/* feedback_div */
-		223,
-		/* frac_n_div */
-		524288,
-		/* post_pll_div */
-		7,
-	},
-
-	/* ICE_TIME_REF_FREQ_125_000 -> 125 MHz */
-	{
-		/* refclk_pre_div */
-		5,
-		/* feedback_div */
-		223,
-		/* frac_n_div */
-		524288,
-		/* post_pll_div */
-		7,
-	},
-
-	/* ICE_TIME_REF_FREQ_153_600 -> 153.6 MHz */
-	{
-		/* refclk_pre_div */
-		5,
-		/* feedback_div */
-		159,
-		/* frac_n_div */
-		1572864,
-		/* post_pll_div */
-		6,
-	},
-
-	/* ICE_TIME_REF_FREQ_156_250 -> 156.25 MHz */
-	{
-		/* refclk_pre_div */
-		5,
-		/* feedback_div */
-		159,
-		/* frac_n_div */
-		1572864,
-		/* post_pll_div */
-		6,
-	},
-
-	/* ICE_TIME_REF_FREQ_245_760 -> 245.76 MHz */
-	{
-		/* refclk_pre_div */
-		10,
-		/* feedback_div */
-		223,
-		/* frac_n_div */
-		524288,
-		/* post_pll_div */
-		7,
-	},
-};
-
-const
-struct ice_cgu_pll_params_e825c e825c_cgu_params[NUM_ICE_TIME_REF_FREQ] = {
-	/* ICE_TIME_REF_FREQ_25_000 -> 25 MHz */
-	{
-		/* tspll_ck_refclkfreq */
-		0x19,
-		/* tspll_ndivratio */
-		1,
-		/* tspll_fbdiv_intgr */
-		320,
-		/* tspll_fbdiv_frac */
-		0,
-		/* ref1588_ck_div */
-		0,
-	},
-
-	/* ICE_TIME_REF_FREQ_122_880 -> 122.88 MHz */
-	{
-		/* tspll_ck_refclkfreq */
-		0x29,
-		/* tspll_ndivratio */
-		3,
-		/* tspll_fbdiv_intgr */
-		195,
-		/* tspll_fbdiv_frac */
-		1342177280UL,
-		/* ref1588_ck_div */
-		0,
-	},
-
-	/* ICE_TIME_REF_FREQ_125_000 -> 125 MHz */
-	{
-		/* tspll_ck_refclkfreq */
-		0x3E,
-		/* tspll_ndivratio */
-		2,
-		/* tspll_fbdiv_intgr */
-		128,
-		/* tspll_fbdiv_frac */
-		0,
-		/* ref1588_ck_div */
-		0,
-	},
-
-	/* ICE_TIME_REF_FREQ_153_600 -> 153.6 MHz */
-	{
-		/* tspll_ck_refclkfreq */
-		0x33,
-		/* tspll_ndivratio */
-		3,
-		/* tspll_fbdiv_intgr */
-		156,
-		/* tspll_fbdiv_frac */
-		1073741824UL,
-		/* ref1588_ck_div */
-		0,
-	},
-
-	/* ICE_TIME_REF_FREQ_156_250 -> 156.25 MHz */
-	{
-		/* tspll_ck_refclkfreq */
-		0x1F,
-		/* tspll_ndivratio */
-		5,
-		/* tspll_fbdiv_intgr */
-		256,
-		/* tspll_fbdiv_frac */
-		0,
-		/* ref1588_ck_div */
-		0,
-	},
-
-	/* ICE_TIME_REF_FREQ_245_760 -> 245.76 MHz */
-	{
-		/* tspll_ck_refclkfreq */
-		0x52,
-		/* tspll_ndivratio */
-		3,
-		/* tspll_fbdiv_intgr */
-		97,
-		/* tspll_fbdiv_frac */
-		2818572288UL,
-		/* ref1588_ck_div */
-		0,
 	},
 };
 
@@ -761,9 +543,9 @@ const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD] = {
 		/* rx_desk_rsgb_par */
 		644531250, /* 644.53125 MHz Reed Solomon gearbox */
 		/* tx_desk_rsgb_pcs */
-		644531250, /* 644.53125 MHz Reed Solomon gearbox */
+		390625000, /* 390.625 MHz Reed Solomon gearbox */
 		/* rx_desk_rsgb_pcs */
-		644531250, /* 644.53125 MHz Reed Solomon gearbox */
+		390625000, /* 390.625 MHz Reed Solomon gearbox */
 		/* tx_fixed_delay */
 		1620,
 		/* pmd_adj_divisor */
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 518893f23372..35680dbe4a7f 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -6,7 +6,6 @@
 #include "ice_common.h"
 #include "ice_ptp_hw.h"
 #include "ice_ptp_consts.h"
-#include "ice_cgu_regs.h"
 
 static struct dpll_pin_frequency ice_cgu_pin_freq_common[] = {
 	DPLL_PIN_FREQUENCY_1PPS,
@@ -150,7 +149,7 @@ static const struct ice_cgu_pin_desc ice_e823_zl_cgu_outputs[] = {
  *                    |    8 bit s    | |    32 bits    |
  *                    +---------------+ +---------------+
  *
- * The increment value is added to the GLSTYN_TIME_R and GLSTYN_TIME_L
+ * The increment value is added to the GLTSYN_TIME_R and GLTSYN_TIME_L
  * registers every clock source tick. Depending on the specific device
  * configuration, the clock source frequency could be one of a number of
  * values.
@@ -226,547 +225,6 @@ static u64 ice_ptp_read_src_incval(struct ice_hw *hw)
 }
 
 /**
- * ice_read_cgu_reg_e82x - Read a CGU register
- * @hw: pointer to the HW struct
- * @addr: Register address to read
- * @val: storage for register value read
- *
- * Read the contents of a register of the Clock Generation Unit. Only
- * applicable to E822 devices.
- *
- * Return: 0 on success, other error codes when failed to read from CGU
- */
-static int ice_read_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 *val)
-{
-	struct ice_sbq_msg_input cgu_msg = {
-		.opcode = ice_sbq_msg_rd,
-		.dest_dev = cgu,
-		.msg_addr_low = addr
-	};
-	int err;
-
-	err = ice_sbq_rw_reg(hw, &cgu_msg, ICE_AQ_FLAG_RD);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to read CGU register 0x%04x, err %d\n",
-			  addr, err);
-		return err;
-	}
-
-	*val = cgu_msg.data;
-
-	return 0;
-}
-
-/**
- * ice_write_cgu_reg_e82x - Write a CGU register
- * @hw: pointer to the HW struct
- * @addr: Register address to write
- * @val: value to write into the register
- *
- * Write the specified value to a register of the Clock Generation Unit. Only
- * applicable to E822 devices.
- *
- * Return: 0 on success, other error codes when failed to write to CGU
- */
-static int ice_write_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 val)
-{
-	struct ice_sbq_msg_input cgu_msg = {
-		.opcode = ice_sbq_msg_wr,
-		.dest_dev = cgu,
-		.msg_addr_low = addr,
-		.data = val
-	};
-	int err;
-
-	err = ice_sbq_rw_reg(hw, &cgu_msg, ICE_AQ_FLAG_RD);
-	if (err) {
-		ice_debug(hw, ICE_DBG_PTP, "Failed to write CGU register 0x%04x, err %d\n",
-			  addr, err);
-		return err;
-	}
-
-	return err;
-}
-
-/**
- * ice_clk_freq_str - Convert time_ref_freq to string
- * @clk_freq: Clock frequency
- *
- * Return: specified TIME_REF clock frequency converted to a string
- */
-static const char *ice_clk_freq_str(enum ice_time_ref_freq clk_freq)
-{
-	switch (clk_freq) {
-	case ICE_TIME_REF_FREQ_25_000:
-		return "25 MHz";
-	case ICE_TIME_REF_FREQ_122_880:
-		return "122.88 MHz";
-	case ICE_TIME_REF_FREQ_125_000:
-		return "125 MHz";
-	case ICE_TIME_REF_FREQ_153_600:
-		return "153.6 MHz";
-	case ICE_TIME_REF_FREQ_156_250:
-		return "156.25 MHz";
-	case ICE_TIME_REF_FREQ_245_760:
-		return "245.76 MHz";
-	default:
-		return "Unknown";
-	}
-}
-
-/**
- * ice_clk_src_str - Convert time_ref_src to string
- * @clk_src: Clock source
- *
- * Return: specified clock source converted to its string name
- */
-static const char *ice_clk_src_str(enum ice_clk_src clk_src)
-{
-	switch (clk_src) {
-	case ICE_CLK_SRC_TCXO:
-		return "TCXO";
-	case ICE_CLK_SRC_TIME_REF:
-		return "TIME_REF";
-	default:
-		return "Unknown";
-	}
-}
-
-/**
- * ice_cfg_cgu_pll_e82x - Configure the Clock Generation Unit
- * @hw: pointer to the HW struct
- * @clk_freq: Clock frequency to program
- * @clk_src: Clock source to select (TIME_REF, or TCXO)
- *
- * Configure the Clock Generation Unit with the desired clock frequency and
- * time reference, enabling the PLL which drives the PTP hardware clock.
- *
- * Return:
- * * %0       - success
- * * %-EINVAL - input parameters are incorrect
- * * %-EBUSY  - failed to lock TS PLL
- * * %other   - CGU read/write failure
- */
-static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw,
-				enum ice_time_ref_freq clk_freq,
-				enum ice_clk_src clk_src)
-{
-	union tspll_ro_bwm_lf bwm_lf;
-	union nac_cgu_dword19 dw19;
-	union nac_cgu_dword22 dw22;
-	union nac_cgu_dword24 dw24;
-	union nac_cgu_dword9 dw9;
-	int err;
-
-	if (clk_freq >= NUM_ICE_TIME_REF_FREQ) {
-		dev_warn(ice_hw_to_dev(hw), "Invalid TIME_REF frequency %u\n",
-			 clk_freq);
-		return -EINVAL;
-	}
-
-	if (clk_src >= NUM_ICE_CLK_SRC) {
-		dev_warn(ice_hw_to_dev(hw), "Invalid clock source %u\n",
-			 clk_src);
-		return -EINVAL;
-	}
-
-	if (clk_src == ICE_CLK_SRC_TCXO &&
-	    clk_freq != ICE_TIME_REF_FREQ_25_000) {
-		dev_warn(ice_hw_to_dev(hw),
-			 "TCXO only supports 25 MHz frequency\n");
-		return -EINVAL;
-	}
-
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD9, &dw9.val);
-	if (err)
-		return err;
-
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val);
-	if (err)
-		return err;
-
-	err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val);
-	if (err)
-		return err;
-
-	/* Log the current clock configuration */
-	ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
-		  dw24.ts_pll_enable ? "enabled" : "disabled",
-		  ice_clk_src_str(dw24.time_ref_sel),
-		  ice_clk_freq_str(dw9.time_ref_freq_sel),
-		  bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked");
-
-	/* Disable the PLL before changing the clock source or frequency */
-	if (dw24.ts_pll_enable) {
-		dw24.ts_pll_enable = 0;
-
-		err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
-		if (err)
-			return err;
-	}
-
-	/* Set the frequency */
-	dw9.time_ref_freq_sel = clk_freq;
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD9, dw9.val);
-	if (err)
-		return err;
-
-	/* Configure the TS PLL feedback divisor */
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD19, &dw19.val);
-	if (err)
-		return err;
-
-	dw19.tspll_fbdiv_intgr = e822_cgu_params[clk_freq].feedback_div;
-	dw19.tspll_ndivratio = 1;
-
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD19, dw19.val);
-	if (err)
-		return err;
-
-	/* Configure the TS PLL post divisor */
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD22, &dw22.val);
-	if (err)
-		return err;
-
-	dw22.time1588clk_div = e822_cgu_params[clk_freq].post_pll_div;
-	dw22.time1588clk_sel_div2 = 0;
-
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD22, dw22.val);
-	if (err)
-		return err;
-
-	/* Configure the TS PLL pre divisor and clock source */
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val);
-	if (err)
-		return err;
-
-	dw24.ref1588_ck_div = e822_cgu_params[clk_freq].refclk_pre_div;
-	dw24.tspll_fbdiv_frac = e822_cgu_params[clk_freq].frac_n_div;
-	dw24.time_ref_sel = clk_src;
-
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
-	if (err)
-		return err;
-
-	/* Finally, enable the PLL */
-	dw24.ts_pll_enable = 1;
-
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
-	if (err)
-		return err;
-
-	/* Wait to verify if the PLL locks */
-	usleep_range(1000, 5000);
-
-	err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val);
-	if (err)
-		return err;
-
-	if (!bwm_lf.plllock_true_lock_cri) {
-		dev_warn(ice_hw_to_dev(hw), "CGU PLL failed to lock\n");
-		return -EBUSY;
-	}
-
-	/* Log the current clock configuration */
-	ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
-		  dw24.ts_pll_enable ? "enabled" : "disabled",
-		  ice_clk_src_str(dw24.time_ref_sel),
-		  ice_clk_freq_str(dw9.time_ref_freq_sel),
-		  bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked");
-
-	return 0;
-}
-
-/**
- * ice_cfg_cgu_pll_e825c - Configure the Clock Generation Unit for E825-C
- * @hw: pointer to the HW struct
- * @clk_freq: Clock frequency to program
- * @clk_src: Clock source to select (TIME_REF, or TCXO)
- *
- * Configure the Clock Generation Unit with the desired clock frequency and
- * time reference, enabling the PLL which drives the PTP hardware clock.
- *
- * Return:
- * * %0       - success
- * * %-EINVAL - input parameters are incorrect
- * * %-EBUSY  - failed to lock TS PLL
- * * %other   - CGU read/write failure
- */
-static int ice_cfg_cgu_pll_e825c(struct ice_hw *hw,
-				 enum ice_time_ref_freq clk_freq,
-				 enum ice_clk_src clk_src)
-{
-	union tspll_ro_lock_e825c ro_lock;
-	union nac_cgu_dword16_e825c dw16;
-	union nac_cgu_dword23_e825c dw23;
-	union nac_cgu_dword19 dw19;
-	union nac_cgu_dword22 dw22;
-	union nac_cgu_dword24 dw24;
-	union nac_cgu_dword9 dw9;
-	int err;
-
-	if (clk_freq >= NUM_ICE_TIME_REF_FREQ) {
-		dev_warn(ice_hw_to_dev(hw), "Invalid TIME_REF frequency %u\n",
-			 clk_freq);
-		return -EINVAL;
-	}
-
-	if (clk_src >= NUM_ICE_CLK_SRC) {
-		dev_warn(ice_hw_to_dev(hw), "Invalid clock source %u\n",
-			 clk_src);
-		return -EINVAL;
-	}
-
-	if (clk_src == ICE_CLK_SRC_TCXO &&
-	    clk_freq != ICE_TIME_REF_FREQ_156_250) {
-		dev_warn(ice_hw_to_dev(hw),
-			 "TCXO only supports 156.25 MHz frequency\n");
-		return -EINVAL;
-	}
-
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD9, &dw9.val);
-	if (err)
-		return err;
-
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val);
-	if (err)
-		return err;
-
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD16_E825C, &dw16.val);
-	if (err)
-		return err;
-
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C, &dw23.val);
-	if (err)
-		return err;
-
-	err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_LOCK_E825C, &ro_lock.val);
-	if (err)
-		return err;
-
-	/* Log the current clock configuration */
-	ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
-		  dw24.ts_pll_enable ? "enabled" : "disabled",
-		  ice_clk_src_str(dw23.time_ref_sel),
-		  ice_clk_freq_str(dw9.time_ref_freq_sel),
-		  ro_lock.plllock_true_lock_cri ? "locked" : "unlocked");
-
-	/* Disable the PLL before changing the clock source or frequency */
-	if (dw23.ts_pll_enable) {
-		dw23.ts_pll_enable = 0;
-
-		err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C,
-					     dw23.val);
-		if (err)
-			return err;
-	}
-
-	/* Set the frequency */
-	dw9.time_ref_freq_sel = clk_freq;
-
-	/* Enable the correct receiver */
-	if (clk_src == ICE_CLK_SRC_TCXO) {
-		dw9.time_ref_en = 0;
-		dw9.clk_eref0_en = 1;
-	} else {
-		dw9.time_ref_en = 1;
-		dw9.clk_eref0_en = 0;
-	}
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD9, dw9.val);
-	if (err)
-		return err;
-
-	/* Choose the referenced frequency */
-	dw16.tspll_ck_refclkfreq =
-	e825c_cgu_params[clk_freq].tspll_ck_refclkfreq;
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD16_E825C, dw16.val);
-	if (err)
-		return err;
-
-	/* Configure the TS PLL feedback divisor */
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD19, &dw19.val);
-	if (err)
-		return err;
-
-	dw19.tspll_fbdiv_intgr =
-		e825c_cgu_params[clk_freq].tspll_fbdiv_intgr;
-	dw19.tspll_ndivratio =
-		e825c_cgu_params[clk_freq].tspll_ndivratio;
-
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD19, dw19.val);
-	if (err)
-		return err;
-
-	/* Configure the TS PLL post divisor */
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD22, &dw22.val);
-	if (err)
-		return err;
-
-	/* These two are constant for E825C */
-	dw22.time1588clk_div = 5;
-	dw22.time1588clk_sel_div2 = 0;
-
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD22, dw22.val);
-	if (err)
-		return err;
-
-	/* Configure the TS PLL pre divisor and clock source */
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C, &dw23.val);
-	if (err)
-		return err;
-
-	dw23.ref1588_ck_div =
-		e825c_cgu_params[clk_freq].ref1588_ck_div;
-	dw23.time_ref_sel = clk_src;
-
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C, dw23.val);
-	if (err)
-		return err;
-
-	dw24.tspll_fbdiv_frac =
-		e825c_cgu_params[clk_freq].tspll_fbdiv_frac;
-
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val);
-	if (err)
-		return err;
-
-	/* Finally, enable the PLL */
-	dw23.ts_pll_enable = 1;
-
-	err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C, dw23.val);
-	if (err)
-		return err;
-
-	/* Wait to verify if the PLL locks */
-	usleep_range(1000, 5000);
-
-	err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_LOCK_E825C, &ro_lock.val);
-	if (err)
-		return err;
-
-	if (!ro_lock.plllock_true_lock_cri) {
-		dev_warn(ice_hw_to_dev(hw), "CGU PLL failed to lock\n");
-		return -EBUSY;
-	}
-
-	/* Log the current clock configuration */
-	ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
-		  dw24.ts_pll_enable ? "enabled" : "disabled",
-		  ice_clk_src_str(dw23.time_ref_sel),
-		  ice_clk_freq_str(dw9.time_ref_freq_sel),
-		  ro_lock.plllock_true_lock_cri ? "locked" : "unlocked");
-
-	return 0;
-}
-
-#define ICE_ONE_PPS_OUT_AMP_MAX 3
-
-/**
- * ice_cgu_cfg_pps_out - Configure 1PPS output from CGU
- * @hw: pointer to the HW struct
- * @enable: true to enable 1PPS output, false to disable it
- *
- * Return: 0 on success, other negative error code when CGU read/write failed
- */
-int ice_cgu_cfg_pps_out(struct ice_hw *hw, bool enable)
-{
-	union nac_cgu_dword9 dw9;
-	int err;
-
-	err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD9, &dw9.val);
-	if (err)
-		return err;
-
-	dw9.one_pps_out_en = enable;
-	dw9.one_pps_out_amp = enable * ICE_ONE_PPS_OUT_AMP_MAX;
-	return ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD9, dw9.val);
-}
-
-/**
- * ice_cfg_cgu_pll_dis_sticky_bits_e82x - disable TS PLL sticky bits
- * @hw: pointer to the HW struct
- *
- * Configure the Clock Generation Unit TS PLL sticky bits so they don't latch on
- * losing TS PLL lock, but always show current state.
- *
- * Return: 0 on success, other error codes when failed to read/write CGU
- */
-static int ice_cfg_cgu_pll_dis_sticky_bits_e82x(struct ice_hw *hw)
-{
-	union tspll_cntr_bist_settings cntr_bist;
-	int err;
-
-	err = ice_read_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS,
-				    &cntr_bist.val);
-	if (err)
-		return err;
-
-	/* Disable sticky lock detection so lock err reported is accurate */
-	cntr_bist.i_plllock_sel_0 = 0;
-	cntr_bist.i_plllock_sel_1 = 0;
-
-	return ice_write_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS,
-				      cntr_bist.val);
-}
-
-/**
- * ice_cfg_cgu_pll_dis_sticky_bits_e825c - disable TS PLL sticky bits for E825-C
- * @hw: pointer to the HW struct
- *
- * Configure the Clock Generation Unit TS PLL sticky bits so they don't latch on
- * losing TS PLL lock, but always show current state.
- *
- * Return: 0 on success, other error codes when failed to read/write CGU
- */
-static int ice_cfg_cgu_pll_dis_sticky_bits_e825c(struct ice_hw *hw)
-{
-	union tspll_bw_tdc_e825c bw_tdc;
-	int err;
-
-	err = ice_read_cgu_reg_e82x(hw, TSPLL_BW_TDC_E825C, &bw_tdc.val);
-	if (err)
-		return err;
-
-	bw_tdc.i_plllock_sel_1_0 = 0;
-
-	return ice_write_cgu_reg_e82x(hw, TSPLL_BW_TDC_E825C, bw_tdc.val);
-}
-
-/**
- * ice_init_cgu_e82x - Initialize CGU with settings from firmware
- * @hw: pointer to the HW structure
- *
- * Initialize the Clock Generation Unit of the E822 device.
- *
- * Return: 0 on success, other error codes when failed to read/write/cfg CGU
- */
-static int ice_init_cgu_e82x(struct ice_hw *hw)
-{
-	struct ice_ts_func_info *ts_info = &hw->func_caps.ts_func_info;
-	int err;
-
-	/* Disable sticky lock detection so lock err reported is accurate */
-	if (ice_is_e825c(hw))
-		err = ice_cfg_cgu_pll_dis_sticky_bits_e825c(hw);
-	else
-		err = ice_cfg_cgu_pll_dis_sticky_bits_e82x(hw);
-	if (err)
-		return err;
-
-	/* Configure the CGU PLL using the parameters from the function
-	 * capabilities.
-	 */
-	if (ice_is_e825c(hw))
-		err = ice_cfg_cgu_pll_e825c(hw, ts_info->time_ref,
-					    (enum ice_clk_src)ts_info->clk_src);
-	else
-		err = ice_cfg_cgu_pll_e82x(hw, ts_info->time_ref,
-					   (enum ice_clk_src)ts_info->clk_src);
-
-	return err;
-}
-
-/**
  * ice_ptp_tmr_cmd_to_src_reg - Convert to source timer command value
  * @hw: pointer to HW struct
  * @cmd: Timer command
@@ -827,8 +285,9 @@ static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw,
 	/* Certain hardware families share the same register values for the
 	 * port register and source timer register.
 	 */
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
 		return ice_ptp_tmr_cmd_to_src_reg(hw, cmd) & TS_CMD_MASK_E810;
 	default:
 		break;
@@ -873,8 +332,12 @@ static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw,
  */
 void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 {
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
 	u32 cmd_val = ice_ptp_tmr_cmd_to_src_reg(hw, cmd);
 
+	if (!ice_is_primary(hw))
+		hw = ice_get_primary_hw(pf);
+
 	wr32(hw, GLTSYN_CMD, cmd_val);
 }
 
@@ -890,41 +353,78 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw)
 {
 	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
 
+	if (!ice_is_primary(hw))
+		hw = ice_get_primary_hw(pf);
+
 	guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock);
 	wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD);
 	ice_flush(hw);
 }
 
+/**
+ * ice_ptp_cfg_sync_delay - Configure PHC to PHY synchronization delay
+ * @hw: pointer to HW struct
+ * @delay: delay between PHC and PHY SYNC command execution in nanoseconds
+ */
+static void ice_ptp_cfg_sync_delay(const struct ice_hw *hw, u32 delay)
+{
+	wr32(hw, GLTSYN_SYNC_DLAY, delay);
+	ice_flush(hw);
+}
+
 /* 56G PHY device functions
  *
  * The following functions operate on devices with the ETH 56G PHY.
  */
 
 /**
+ * ice_ptp_get_dest_dev_e825 - get destination PHY for given port number
+ * @hw: pointer to the HW struct
+ * @port: destination port
+ *
+ * Return: destination sideband queue PHY device.
+ */
+static enum ice_sbq_dev_id ice_ptp_get_dest_dev_e825(struct ice_hw *hw,
+						     u8 port)
+{
+	u8 curr_phy, tgt_phy;
+
+	tgt_phy = port >= hw->ptp.ports_per_phy;
+	curr_phy = hw->lane_num >= hw->ptp.ports_per_phy;
+	/* In the driver, lanes 4..7 are in fact 0..3 on a second PHY.
+	 * On a single complex E825C, PHY 0 is always destination device phy_0
+	 * and PHY 1 is phy_0_peer.
+	 * On dual complex E825C, device phy_0 points to PHY on a current
+	 * complex and phy_0_peer to PHY on a different complex.
+	 */
+	if ((!ice_is_dual(hw) && tgt_phy == 1) ||
+	    (ice_is_dual(hw) && tgt_phy != curr_phy))
+		return ice_sbq_dev_phy_0_peer;
+	else
+		return ice_sbq_dev_phy_0;
+}
+
+/**
  * ice_write_phy_eth56g - Write a PHY port register
  * @hw: pointer to the HW struct
- * @phy_idx: PHY index
+ * @port: destination port
  * @addr: PHY register address
  * @val: Value to write
  *
  * Return: 0 on success, other error codes when failed to write to PHY
  */
-static int ice_write_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
-				u32 val)
+static int ice_write_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 val)
 {
-	struct ice_sbq_msg_input phy_msg;
+	struct ice_sbq_msg_input msg = {
+		.dest_dev = ice_ptp_get_dest_dev_e825(hw, port),
+		.opcode = ice_sbq_msg_wr,
+		.msg_addr_low = lower_16_bits(addr),
+		.msg_addr_high = upper_16_bits(addr),
+		.data = val
+	};
 	int err;
 
-	phy_msg.opcode = ice_sbq_msg_wr;
-
-	phy_msg.msg_addr_low = lower_16_bits(addr);
-	phy_msg.msg_addr_high = upper_16_bits(addr);
-
-	phy_msg.data = val;
-	phy_msg.dest_dev = hw->ptp.phy.eth56g.phy_addr[phy_idx];
-
-	err = ice_sbq_rw_reg(hw, &phy_msg, ICE_AQ_FLAG_RD);
-
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err)
 		ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n",
 			  err);
@@ -935,41 +435,36 @@ static int ice_write_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
 /**
  * ice_read_phy_eth56g - Read a PHY port register
  * @hw: pointer to the HW struct
- * @phy_idx: PHY index
+ * @port: destination port
  * @addr: PHY register address
  * @val: Value to write
  *
  * Return: 0 on success, other error codes when failed to read from PHY
  */
-static int ice_read_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
-			       u32 *val)
+static int ice_read_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 *val)
 {
-	struct ice_sbq_msg_input phy_msg;
+	struct ice_sbq_msg_input msg = {
+		.dest_dev = ice_ptp_get_dest_dev_e825(hw, port),
+		.opcode = ice_sbq_msg_rd,
+		.msg_addr_low = lower_16_bits(addr),
+		.msg_addr_high = upper_16_bits(addr)
+	};
 	int err;
 
-	phy_msg.opcode = ice_sbq_msg_rd;
-
-	phy_msg.msg_addr_low = lower_16_bits(addr);
-	phy_msg.msg_addr_high = upper_16_bits(addr);
-
-	phy_msg.data = 0;
-	phy_msg.dest_dev = hw->ptp.phy.eth56g.phy_addr[phy_idx];
-
-	err = ice_sbq_rw_reg(hw, &phy_msg, ICE_AQ_FLAG_RD);
-	if (err) {
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
+	if (err)
 		ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n",
 			  err);
-		return err;
-	}
-
-	*val = phy_msg.data;
+	else
+		*val = msg.data;
 
-	return 0;
+	return err;
 }
 
 /**
  * ice_phy_res_address_eth56g - Calculate a PHY port register address
- * @port: Port number to be written
+ * @hw: pointer to the HW struct
+ * @lane: Lane number to be written
  * @res_type: resource type (register/memory)
  * @offset: Offset from PHY port register base
  * @addr: The result address
@@ -978,17 +473,19 @@ static int ice_read_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
  * * %0      - success
  * * %EINVAL - invalid port number or resource type
  */
-static int ice_phy_res_address_eth56g(u8 port, enum eth56g_res_type res_type,
-				      u32 offset, u32 *addr)
+static int ice_phy_res_address_eth56g(struct ice_hw *hw, u8 lane,
+				      enum eth56g_res_type res_type,
+				      u32 offset,
+				      u32 *addr)
 {
-	u8 lane = port % ICE_PORTS_PER_QUAD;
-	u8 phy = ICE_GET_QUAD_NUM(port);
-
 	if (res_type >= NUM_ETH56G_PHY_RES)
 		return -EINVAL;
 
-	*addr = eth56g_phy_res[res_type].base[phy] +
+	/* Lanes 4..7 are in fact 0..3 on a second PHY */
+	lane %= hw->ptp.ports_per_phy;
+	*addr = eth56g_phy_res[res_type].base_addr +
 		lane * eth56g_phy_res[res_type].step + offset;
+
 	return 0;
 }
 
@@ -1008,19 +505,17 @@ static int ice_phy_res_address_eth56g(u8 port, enum eth56g_res_type res_type,
 static int ice_write_port_eth56g(struct ice_hw *hw, u8 port, u32 offset,
 				 u32 val, enum eth56g_res_type res_type)
 {
-	u8 phy_port = port % hw->ptp.ports_per_phy;
-	u8 phy_idx = port / hw->ptp.ports_per_phy;
 	u32 addr;
 	int err;
 
 	if (port >= hw->ptp.num_lports)
 		return -EINVAL;
 
-	err = ice_phy_res_address_eth56g(phy_port, res_type, offset, &addr);
+	err = ice_phy_res_address_eth56g(hw, port, res_type, offset, &addr);
 	if (err)
 		return err;
 
-	return ice_write_phy_eth56g(hw, phy_idx, addr, val);
+	return ice_write_phy_eth56g(hw, port, addr, val);
 }
 
 /**
@@ -1039,19 +534,17 @@ static int ice_write_port_eth56g(struct ice_hw *hw, u8 port, u32 offset,
 static int ice_read_port_eth56g(struct ice_hw *hw, u8 port, u32 offset,
 				u32 *val, enum eth56g_res_type res_type)
 {
-	u8 phy_port = port % hw->ptp.ports_per_phy;
-	u8 phy_idx = port / hw->ptp.ports_per_phy;
 	u32 addr;
 	int err;
 
 	if (port >= hw->ptp.num_lports)
 		return -EINVAL;
 
-	err = ice_phy_res_address_eth56g(phy_port, res_type, offset, &addr);
+	err = ice_phy_res_address_eth56g(hw, port, res_type, offset, &addr);
 	if (err)
 		return err;
 
-	return ice_read_phy_eth56g(hw, phy_idx, addr, val);
+	return ice_read_phy_eth56g(hw, port, addr, val);
 }
 
 /**
@@ -1201,6 +694,56 @@ static int ice_write_port_mem_eth56g(struct ice_hw *hw, u8 port, u16 offset,
 }
 
 /**
+ * ice_write_quad_ptp_reg_eth56g - Write a PHY quad register
+ * @hw: pointer to the HW struct
+ * @offset: PHY register offset
+ * @port: Port number
+ * @val: Value to write
+ *
+ * Return:
+ * * %0     - success
+ * * %EIO  - invalid port number or resource type
+ * * %other - failed to write to PHY
+ */
+static int ice_write_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port,
+					 u32 offset, u32 val)
+{
+	u32 addr;
+
+	if (port >= hw->ptp.num_lports)
+		return -EIO;
+
+	addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset;
+
+	return ice_write_phy_eth56g(hw, port, addr, val);
+}
+
+/**
+ * ice_read_quad_ptp_reg_eth56g - Read a PHY quad register
+ * @hw: pointer to the HW struct
+ * @offset: PHY register offset
+ * @port: Port number
+ * @val: Value to read
+ *
+ * Return:
+ * * %0     - success
+ * * %EIO  - invalid port number or resource type
+ * * %other - failed to read from PHY
+ */
+static int ice_read_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port,
+					u32 offset, u32 *val)
+{
+	u32 addr;
+
+	if (port >= hw->ptp.num_lports)
+		return -EIO;
+
+	addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset;
+
+	return ice_read_phy_eth56g(hw, port, addr, val);
+}
+
+/**
  * ice_is_64b_phy_reg_eth56g - Check if this is a 64bit PHY register
  * @low_addr: the low address to check
  * @high_addr: on return, contains the high address of the 64bit register
@@ -1518,9 +1061,8 @@ static int ice_read_ptp_tstamp_eth56g(struct ice_hw *hw, u8 port, u8 idx,
 	 * lower 8 bits in the low register, and the upper 32 bits in the high
 	 * register.
 	 */
-	*tstamp = FIELD_PREP(TS_PHY_HIGH_M, hi) |
-		  FIELD_PREP(TS_PHY_LOW_M, lo);
-
+	*tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) |
+		  FIELD_PREP(PHY_40B_LOW_M, lo);
 	return 0;
 }
 
@@ -1919,7 +1461,6 @@ ice_phy_get_speed_eth56g(struct ice_link_status *li)
  */
 static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port)
 {
-	u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1);
 	u32 val;
 	int err;
 
@@ -1934,8 +1475,8 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port)
 	switch (ice_phy_get_speed_eth56g(&hw->port_info->phy.link_info)) {
 	case ICE_ETH56G_LNK_SPD_1G:
 	case ICE_ETH56G_LNK_SPD_2_5G:
-		err = ice_read_ptp_reg_eth56g(hw, port_blk,
-					      PHY_GPCS_CONFIG_REG0, &val);
+		err = ice_read_quad_ptp_reg_eth56g(hw, port,
+						   PHY_GPCS_CONFIG_REG0, &val);
 		if (err) {
 			ice_debug(hw, ICE_DBG_PTP, "Failed to read PHY_GPCS_CONFIG_REG0, status: %d",
 				  err);
@@ -1946,8 +1487,8 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port)
 		val |= FIELD_PREP(PHY_GPCS_CONFIG_REG0_TX_THR_M,
 				  ICE_ETH56G_NOMINAL_TX_THRESH);
 
-		err = ice_write_ptp_reg_eth56g(hw, port_blk,
-					       PHY_GPCS_CONFIG_REG0, val);
+		err = ice_write_quad_ptp_reg_eth56g(hw, port,
+						    PHY_GPCS_CONFIG_REG0, val);
 		if (err) {
 			ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_GPCS_CONFIG_REG0, status: %d",
 				  err);
@@ -1988,50 +1529,47 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port)
  */
 int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port)
 {
-	u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1);
-	u8 blk_port = port & (ICE_PORTS_PER_QUAD - 1);
+	u8 quad_lane = port % ICE_PORTS_PER_QUAD;
+	u32 addr, val, peer_delay;
 	bool enable, sfd_ena;
-	u32 val, peer_delay;
 	int err;
 
 	enable = hw->ptp.phy.eth56g.onestep_ena;
 	peer_delay = hw->ptp.phy.eth56g.peer_delay;
 	sfd_ena = hw->ptp.phy.eth56g.sfd_ena;
 
-	/* PHY_PTP_1STEP_CONFIG */
-	err = ice_read_ptp_reg_eth56g(hw, port_blk, PHY_PTP_1STEP_CONFIG, &val);
+	addr = PHY_PTP_1STEP_CONFIG;
+	err = ice_read_quad_ptp_reg_eth56g(hw, port, addr, &val);
 	if (err)
 		return err;
 
 	if (enable)
-		val |= blk_port;
+		val |= BIT(quad_lane);
 	else
-		val &= ~blk_port;
+		val &= ~BIT(quad_lane);
 
 	val &= ~(PHY_PTP_1STEP_T1S_UP64_M | PHY_PTP_1STEP_T1S_DELTA_M);
 
-	err = ice_write_ptp_reg_eth56g(hw, port_blk, PHY_PTP_1STEP_CONFIG, val);
+	err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val);
 	if (err)
 		return err;
 
-	/* PHY_PTP_1STEP_PEER_DELAY */
+	addr = PHY_PTP_1STEP_PEER_DELAY(quad_lane);
 	val = FIELD_PREP(PHY_PTP_1STEP_PD_DELAY_M, peer_delay);
 	if (peer_delay)
 		val |= PHY_PTP_1STEP_PD_ADD_PD_M;
 	val |= PHY_PTP_1STEP_PD_DLY_V_M;
-	err = ice_write_ptp_reg_eth56g(hw, port_blk,
-				       PHY_PTP_1STEP_PEER_DELAY(blk_port), val);
+	err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val);
 	if (err)
 		return err;
 
 	val &= ~PHY_PTP_1STEP_PD_DLY_V_M;
-	err = ice_write_ptp_reg_eth56g(hw, port_blk,
-				       PHY_PTP_1STEP_PEER_DELAY(blk_port), val);
+	err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val);
 	if (err)
 		return err;
 
-	/* PHY_MAC_XIF_MODE */
-	err = ice_read_mac_reg_eth56g(hw, port, PHY_MAC_XIF_MODE, &val);
+	addr = PHY_MAC_XIF_MODE;
+	err = ice_read_mac_reg_eth56g(hw, port, addr, &val);
 	if (err)
 		return err;
 
@@ -2051,7 +1589,7 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port)
 	       FIELD_PREP(PHY_MAC_XIF_TS_BIN_MODE_M, enable) |
 	       FIELD_PREP(PHY_MAC_XIF_TS_SFD_ENA_M, sfd_ena);
 
-	return ice_write_mac_reg_eth56g(hw, port, PHY_MAC_XIF_MODE, val);
+	return ice_write_mac_reg_eth56g(hw, port, addr, val);
 }
 
 /**
@@ -2093,21 +1631,22 @@ static u32 ice_ptp_calc_bitslip_eth56g(struct ice_hw *hw, u8 port, u32 bs,
 				       bool fc, bool rs,
 				       enum ice_eth56g_link_spd spd)
 {
-	u8 port_offset = port & (ICE_PORTS_PER_QUAD - 1);
-	u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1);
 	u32 bitslip;
 	int err;
 
 	if (!bs || rs)
 		return 0;
 
-	if (spd == ICE_ETH56G_LNK_SPD_1G || spd == ICE_ETH56G_LNK_SPD_2_5G)
+	if (spd == ICE_ETH56G_LNK_SPD_1G || spd == ICE_ETH56G_LNK_SPD_2_5G) {
 		err = ice_read_gpcs_reg_eth56g(hw, port, PHY_GPCS_BITSLIP,
 					       &bitslip);
-	else
-		err = ice_read_ptp_reg_eth56g(hw, port_blk,
-					      PHY_REG_SD_BIT_SLIP(port_offset),
-					      &bitslip);
+	} else {
+		u8 quad_lane = port % ICE_PORTS_PER_QUAD;
+		u32 addr;
+
+		addr = PHY_REG_SD_BIT_SLIP(quad_lane);
+		err = ice_read_quad_ptp_reg_eth56g(hw, port, addr, &bitslip);
+	}
 	if (err)
 		return 0;
 
@@ -2351,6 +1890,7 @@ int ice_phy_cfg_intr_eth56g(struct ice_hw *hw, u8 port, bool ena, u8 threshold)
 static int ice_read_phy_and_phc_time_eth56g(struct ice_hw *hw, u8 port,
 					    u64 *phy_time, u64 *phc_time)
 {
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
 	u64 tx_time, rx_time;
 	u32 zo, lo;
 	u8 tmr_idx;
@@ -2370,8 +1910,13 @@ static int ice_read_phy_and_phc_time_eth56g(struct ice_hw *hw, u8 port,
 	ice_ptp_exec_tmr_cmd(hw);
 
 	/* Read the captured PHC time from the shadow time registers */
-	zo = rd32(hw, GLTSYN_SHTIME_0(tmr_idx));
-	lo = rd32(hw, GLTSYN_SHTIME_L(tmr_idx));
+	if (ice_is_primary(hw)) {
+		zo = rd32(hw, GLTSYN_SHTIME_0(tmr_idx));
+		lo = rd32(hw, GLTSYN_SHTIME_L(tmr_idx));
+	} else {
+		zo = rd32(ice_get_primary_hw(pf), GLTSYN_SHTIME_0(tmr_idx));
+		lo = rd32(ice_get_primary_hw(pf), GLTSYN_SHTIME_L(tmr_idx));
+	}
 	*phc_time = (u64)lo << 32 | zo;
 
 	/* Read the captured PHY time from the PHY shadow registers */
@@ -2508,6 +2053,7 @@ int ice_stop_phy_timer_eth56g(struct ice_hw *hw, u8 port, bool soft_reset)
  */
 int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port)
 {
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
 	u32 lo, hi;
 	u64 incval;
 	u8 tmr_idx;
@@ -2533,8 +2079,13 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port)
 	if (err)
 		return err;
 
-	lo = rd32(hw, GLTSYN_INCVAL_L(tmr_idx));
-	hi = rd32(hw, GLTSYN_INCVAL_H(tmr_idx));
+	if (ice_is_primary(hw)) {
+		lo = rd32(hw, GLTSYN_INCVAL_L(tmr_idx));
+		hi = rd32(hw, GLTSYN_INCVAL_H(tmr_idx));
+	} else {
+		lo = rd32(ice_get_primary_hw(pf), GLTSYN_INCVAL_L(tmr_idx));
+		hi = rd32(ice_get_primary_hw(pf), GLTSYN_INCVAL_H(tmr_idx));
+	}
 	incval = (u64)hi << 32 | lo;
 
 	err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_REG_TIMETUS_L, incval);
@@ -2565,42 +2116,6 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port)
 }
 
 /**
- * ice_sb_access_ena_eth56g - Enable SB devices (PHY and others) access
- * @hw: pointer to HW struct
- * @enable: Enable or disable access
- *
- * Enable sideband devices (PHY and others) access.
- */
-static void ice_sb_access_ena_eth56g(struct ice_hw *hw, bool enable)
-{
-	u32 val = rd32(hw, PF_SB_REM_DEV_CTL);
-
-	if (enable)
-		val |= BIT(eth56g_phy_0) | BIT(cgu) | BIT(eth56g_phy_1);
-	else
-		val &= ~(BIT(eth56g_phy_0) | BIT(cgu) | BIT(eth56g_phy_1));
-
-	wr32(hw, PF_SB_REM_DEV_CTL, val);
-}
-
-/**
- * ice_ptp_init_phc_eth56g - Perform E82X specific PHC initialization
- * @hw: pointer to HW struct
- *
- * Perform PHC initialization steps specific to E82X devices.
- *
- * Return:
- * * %0     - success
- * * %other - failed to initialize CGU
- */
-static int ice_ptp_init_phc_eth56g(struct ice_hw *hw)
-{
-	ice_sb_access_ena_eth56g(hw, true);
-	/* Initialize the Clock Generation Unit */
-	return ice_init_cgu_e82x(hw);
-}
-
-/**
  * ice_ptp_read_tx_hwtstamp_status_eth56g - Get TX timestamp status
  * @hw: pointer to the HW struct
  * @ts_status: the timestamp mask pointer
@@ -2667,59 +2182,21 @@ static int ice_get_phy_tx_tstamp_ready_eth56g(struct ice_hw *hw, u8 port,
 }
 
 /**
- * ice_is_muxed_topo - detect breakout 2x50G topology for E825C
- * @hw: pointer to the HW struct
- *
- * Return: true if it's 2x50 breakout topology, false otherwise
- */
-static bool ice_is_muxed_topo(struct ice_hw *hw)
-{
-	u8 link_topo;
-	bool mux;
-	u32 val;
-
-	val = rd32(hw, GLGEN_SWITCH_MODE_CONFIG);
-	mux = FIELD_GET(GLGEN_SWITCH_MODE_CONFIG_25X4_QUAD_M, val);
-	val = rd32(hw, GLGEN_MAC_LINK_TOPO);
-	link_topo = FIELD_GET(GLGEN_MAC_LINK_TOPO_LINK_TOPO_M, val);
-
-	return (mux && link_topo == ICE_LINK_TOPO_UP_TO_2_LINKS);
-}
-
-/**
- * ice_ptp_init_phy_e825c - initialize PHY parameters
+ * ice_ptp_init_phy_e825 - initialize PHY parameters
  * @hw: pointer to the HW struct
  */
-static void ice_ptp_init_phy_e825c(struct ice_hw *hw)
+static void ice_ptp_init_phy_e825(struct ice_hw *hw)
 {
 	struct ice_ptp_hw *ptp = &hw->ptp;
 	struct ice_eth56g_params *params;
-	u8 phy;
 
-	ptp->phy_model = ICE_PHY_ETH56G;
 	params = &ptp->phy.eth56g;
 	params->onestep_ena = false;
 	params->peer_delay = 0;
 	params->sfd_ena = false;
-	params->phy_addr[0] = eth56g_phy_0;
-	params->phy_addr[1] = eth56g_phy_1;
 	params->num_phys = 2;
 	ptp->ports_per_phy = 4;
 	ptp->num_lports = params->num_phys * ptp->ports_per_phy;
-
-	ice_sb_access_ena_eth56g(hw, true);
-	for (phy = 0; phy < params->num_phys; phy++) {
-		u32 phy_rev;
-		int err;
-
-		err = ice_read_phy_eth56g(hw, phy, PHY_REG_REVISION, &phy_rev);
-		if (err || phy_rev != PHY_REVISION_ETH56G) {
-			ptp->phy_model = ICE_PHY_UNSUP;
-			return;
-		}
-	}
-
-	ptp->is_2x50g_muxed_topo = ice_is_muxed_topo(hw);
 }
 
 /* E822 family functions
@@ -2738,10 +2215,9 @@ static void ice_fill_phy_msg_e82x(struct ice_hw *hw,
 				  struct ice_sbq_msg_input *msg, u8 port,
 				  u16 offset)
 {
-	int phy_port, phy, quadtype;
+	int phy_port, quadtype;
 
 	phy_port = port % hw->ptp.ports_per_phy;
-	phy = port / hw->ptp.ports_per_phy;
 	quadtype = ICE_GET_QUAD_NUM(port) %
 		   ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy);
 
@@ -2753,12 +2229,7 @@ static void ice_fill_phy_msg_e82x(struct ice_hw *hw,
 		msg->msg_addr_high = P_Q1_H(P_4_BASE + offset, phy_port);
 	}
 
-	if (phy == 0)
-		msg->dest_dev = rmn_0;
-	else if (phy == 1)
-		msg->dest_dev = rmn_1;
-	else
-		msg->dest_dev = rmn_2;
+	msg->dest_dev = ice_sbq_dev_phy_0;
 }
 
 /**
@@ -2877,7 +2348,7 @@ ice_read_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 *val)
 	ice_fill_phy_msg_e82x(hw, &msg, port, offset);
 	msg.opcode = ice_sbq_msg_rd;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
 			  err);
@@ -2955,7 +2426,7 @@ ice_write_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 val)
 	msg.opcode = ice_sbq_msg_wr;
 	msg.data = val;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
 			  err);
@@ -3081,7 +2552,7 @@ static int ice_fill_quad_msg_e82x(struct ice_hw *hw,
 	if (quad >= ICE_GET_QUAD_NUM(hw->ptp.num_lports))
 		return -EINVAL;
 
-	msg->dest_dev = rmn_0;
+	msg->dest_dev = ice_sbq_dev_phy_0;
 
 	if (!(quad % ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy)))
 		addr = Q_0_BASE + offset;
@@ -3116,7 +2587,7 @@ ice_read_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 *val)
 
 	msg.opcode = ice_sbq_msg_rd;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
 			  err);
@@ -3151,7 +2622,7 @@ ice_write_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 val)
 	msg.opcode = ice_sbq_msg_wr;
 	msg.data = val;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
 			  err);
@@ -3200,7 +2671,8 @@ ice_read_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp)
 	 * lower 8 bits in the low register, and the upper 32 bits in the high
 	 * register.
 	 */
-	*tstamp = FIELD_PREP(TS_PHY_HIGH_M, hi) | FIELD_PREP(TS_PHY_LOW_M, lo);
+	*tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) |
+		  FIELD_PREP(PHY_40B_LOW_M, lo);
 
 	return 0;
 }
@@ -3302,7 +2774,6 @@ static int ice_ptp_set_vernier_wl(struct ice_hw *hw)
  */
 static int ice_ptp_init_phc_e82x(struct ice_hw *hw)
 {
-	int err;
 	u32 val;
 
 	/* Enable reading switch and PHY registers over the sideband queue */
@@ -3312,11 +2783,6 @@ static int ice_ptp_init_phc_e82x(struct ice_hw *hw)
 	val |= (PF_SB_REM_DEV_CTL_SWITCH_READ | PF_SB_REM_DEV_CTL_PHY0);
 	wr32(hw, PF_SB_REM_DEV_CTL, val);
 
-	/* Initialize the Clock Generation Unit */
-	err = ice_init_cgu_e82x(hw);
-	if (err)
-		return err;
-
 	/* Set window length for all the ports */
 	return ice_ptp_set_vernier_wl(hw);
 }
@@ -4773,7 +4239,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold)
  */
 static void ice_ptp_init_phy_e82x(struct ice_ptp_hw *ptp)
 {
-	ptp->phy_model = ICE_PHY_E82X;
 	ptp->num_lports = 8;
 	ptp->ports_per_phy = 8;
 }
@@ -4800,9 +4265,9 @@ static int ice_read_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 *val)
 	msg.msg_addr_low = lower_16_bits(addr);
 	msg.msg_addr_high = upper_16_bits(addr);
 	msg.opcode = ice_sbq_msg_rd;
-	msg.dest_dev = rmn_0;
+	msg.dest_dev = ice_sbq_dev_phy_0;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
 			  err);
@@ -4830,10 +4295,10 @@ static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val)
 	msg.msg_addr_low = lower_16_bits(addr);
 	msg.msg_addr_high = upper_16_bits(addr);
 	msg.opcode = ice_sbq_msg_wr;
-	msg.dest_dev = rmn_0;
+	msg.dest_dev = ice_sbq_dev_phy_0;
 	msg.data = val;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
 			  err);
@@ -4857,33 +4322,46 @@ static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val)
 static int
 ice_read_phy_tstamp_ll_e810(struct ice_hw *hw, u8 idx, u8 *hi, u32 *lo)
 {
+	struct ice_e810_params *params = &hw->ptp.phy.e810;
+	unsigned long flags;
 	u32 val;
-	u8 i;
+	int err;
+
+	spin_lock_irqsave(&params->atqbal_wq.lock, flags);
+
+	/* Wait for any pending in-progress low latency interrupt */
+	err = wait_event_interruptible_locked_irq(params->atqbal_wq,
+						  !(params->atqbal_flags &
+						    ATQBAL_FLAGS_INTR_IN_PROGRESS));
+	if (err) {
+		spin_unlock_irqrestore(&params->atqbal_wq.lock, flags);
+		return err;
+	}
 
 	/* Write TS index to read to the PF register so the FW can read it */
-	val = FIELD_PREP(TS_LL_READ_TS_IDX, idx) | TS_LL_READ_TS;
-	wr32(hw, PF_SB_ATQBAL, val);
+	val = FIELD_PREP(REG_LL_PROXY_H_TS_IDX, idx) | REG_LL_PROXY_H_EXEC;
+	wr32(hw, REG_LL_PROXY_H, val);
 
 	/* Read the register repeatedly until the FW provides us the TS */
-	for (i = TS_LL_READ_RETRIES; i > 0; i--) {
-		val = rd32(hw, PF_SB_ATQBAL);
+	err = read_poll_timeout_atomic(rd32, val,
+				       !FIELD_GET(REG_LL_PROXY_H_EXEC, val), 10,
+				       REG_LL_PROXY_H_TIMEOUT_US, false, hw,
+				       REG_LL_PROXY_H);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n");
+		spin_unlock_irqrestore(&params->atqbal_wq.lock, flags);
+		return err;
+	}
 
-		/* When the bit is cleared, the TS is ready in the register */
-		if (!(FIELD_GET(TS_LL_READ_TS, val))) {
-			/* High 8 bit value of the TS is on the bits 16:23 */
-			*hi = FIELD_GET(TS_LL_READ_TS_HIGH, val);
+	/* High 8 bit value of the TS is on the bits 16:23 */
+	*hi = FIELD_GET(REG_LL_PROXY_H_TS_HIGH, val);
 
-			/* Read the low 32 bit value and set the TS valid bit */
-			*lo = rd32(hw, PF_SB_ATQBAH) | TS_VALID;
-			return 0;
-		}
+	/* Read the low 32 bit value and set the TS valid bit */
+	*lo = rd32(hw, REG_LL_PROXY_L) | TS_VALID;
 
-		udelay(10);
-	}
+	spin_unlock_irqrestore(&params->atqbal_wq.lock, flags);
 
-	/* FW failed to provide the TS in time */
-	ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n");
-	return -EINVAL;
+	return 0;
 }
 
 /**
@@ -4954,7 +4432,8 @@ ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp)
 	/* For E810 devices, the timestamp is reported with the lower 32 bits
 	 * in the low register, and the upper 8 bits in the high register.
 	 */
-	*tstamp = ((u64)hi) << TS_HIGH_S | ((u64)lo & TS_LOW_M);
+	*tstamp = FIELD_PREP(PHY_EXT_40B_HIGH_M, hi) |
+		  FIELD_PREP(PHY_EXT_40B_LOW_M, lo);
 
 	return 0;
 }
@@ -5017,8 +4496,7 @@ static int ice_ptp_init_phc_e810(struct ice_hw *hw)
 	u8 tmr_idx;
 	int err;
 
-	/* Ensure synchronization delay is zero */
-	wr32(hw, GLTSYN_SYNC_DLAY, 0);
+	ice_ptp_cfg_sync_delay(hw, ICE_E810_E830_SYNC_DELAY);
 
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 	err = ice_write_phy_reg_e810(hw, ETH_GLTSYN_ENA(tmr_idx),
@@ -5066,6 +4544,55 @@ static int ice_ptp_prep_phy_time_e810(struct ice_hw *hw, u32 time)
 }
 
 /**
+ * ice_ptp_prep_phy_adj_ll_e810 - Prep PHY ports for a time adjustment
+ * @hw: pointer to HW struct
+ * @adj: adjustment value to program
+ *
+ * Use the low latency firmware interface to program PHY time adjustment to
+ * all PHY ports.
+ *
+ * Return: 0 on success, -EBUSY on timeout
+ */
+static int ice_ptp_prep_phy_adj_ll_e810(struct ice_hw *hw, s32 adj)
+{
+	const u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+	struct ice_e810_params *params = &hw->ptp.phy.e810;
+	u32 val;
+	int err;
+
+	spin_lock_irq(&params->atqbal_wq.lock);
+
+	/* Wait for any pending in-progress low latency interrupt */
+	err = wait_event_interruptible_locked_irq(params->atqbal_wq,
+						  !(params->atqbal_flags &
+						    ATQBAL_FLAGS_INTR_IN_PROGRESS));
+	if (err) {
+		spin_unlock_irq(&params->atqbal_wq.lock);
+		return err;
+	}
+
+	wr32(hw, REG_LL_PROXY_L, adj);
+	val = FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_CMD_M, REG_LL_PROXY_H_PHY_TMR_CMD_ADJ) |
+	      FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_IDX_M, tmr_idx) | REG_LL_PROXY_H_EXEC;
+	wr32(hw, REG_LL_PROXY_H, val);
+
+	/* Read the register repeatedly until the FW indicates completion */
+	err = read_poll_timeout_atomic(rd32, val,
+				       !FIELD_GET(REG_LL_PROXY_H_EXEC, val),
+				       10, REG_LL_PROXY_H_TIMEOUT_US, false, hw,
+				       REG_LL_PROXY_H);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY timer adjustment using low latency interface\n");
+		spin_unlock_irq(&params->atqbal_wq.lock);
+		return err;
+	}
+
+	spin_unlock_irq(&params->atqbal_wq.lock);
+
+	return 0;
+}
+
+/**
  * ice_ptp_prep_phy_adj_e810 - Prep PHY port for a time adjustment
  * @hw: pointer to HW struct
  * @adj: adjustment value to program
@@ -5083,6 +4610,9 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj)
 	u8 tmr_idx;
 	int err;
 
+	if (hw->dev_caps.ts_dev_info.ll_phy_tmr_update)
+		return ice_ptp_prep_phy_adj_ll_e810(hw, adj);
+
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 
 	/* Adjustments are represented as signed 2's complement values in
@@ -5106,6 +4636,56 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj)
 }
 
 /**
+ * ice_ptp_prep_phy_incval_ll_e810 - Prep PHY ports increment value change
+ * @hw: pointer to HW struct
+ * @incval: The new 40bit increment value to prepare
+ *
+ * Use the low latency firmware interface to program PHY time increment value
+ * for all PHY ports.
+ *
+ * Return: 0 on success, -EBUSY on timeout
+ */
+static int ice_ptp_prep_phy_incval_ll_e810(struct ice_hw *hw, u64 incval)
+{
+	const u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+	struct ice_e810_params *params = &hw->ptp.phy.e810;
+	u32 val;
+	int err;
+
+	spin_lock_irq(&params->atqbal_wq.lock);
+
+	/* Wait for any pending in-progress low latency interrupt */
+	err = wait_event_interruptible_locked_irq(params->atqbal_wq,
+						  !(params->atqbal_flags &
+						    ATQBAL_FLAGS_INTR_IN_PROGRESS));
+	if (err) {
+		spin_unlock_irq(&params->atqbal_wq.lock);
+		return err;
+	}
+
+	wr32(hw, REG_LL_PROXY_L, lower_32_bits(incval));
+	val = FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_CMD_M, REG_LL_PROXY_H_PHY_TMR_CMD_FREQ) |
+	      FIELD_PREP(REG_LL_PROXY_H_TS_HIGH, (u8)upper_32_bits(incval)) |
+	      FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_IDX_M, tmr_idx) | REG_LL_PROXY_H_EXEC;
+	wr32(hw, REG_LL_PROXY_H, val);
+
+	/* Read the register repeatedly until the FW indicates completion */
+	err = read_poll_timeout_atomic(rd32, val,
+				       !FIELD_GET(REG_LL_PROXY_H_EXEC, val),
+				       10, REG_LL_PROXY_H_TIMEOUT_US, false, hw,
+				       REG_LL_PROXY_H);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY timer increment using low latency interface\n");
+		spin_unlock_irq(&params->atqbal_wq.lock);
+		return err;
+	}
+
+	spin_unlock_irq(&params->atqbal_wq.lock);
+
+	return 0;
+}
+
+/**
  * ice_ptp_prep_phy_incval_e810 - Prep PHY port increment value change
  * @hw: pointer to HW struct
  * @incval: The new 40bit increment value to prepare
@@ -5120,6 +4700,9 @@ static int ice_ptp_prep_phy_incval_e810(struct ice_hw *hw, u64 incval)
 	u8 tmr_idx;
 	int err;
 
+	if (hw->dev_caps.ts_dev_info.ll_phy_tmr_update)
+		return ice_ptp_prep_phy_incval_ll_e810(hw, incval);
+
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 	low = lower_32_bits(incval);
 	high = upper_32_bits(incval);
@@ -5179,68 +4762,6 @@ ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready)
  */
 
 /**
- * ice_get_pca9575_handle
- * @hw: pointer to the hw struct
- * @pca9575_handle: GPIO controller's handle
- *
- * Find and return the GPIO controller's handle in the netlist.
- * When found - the value will be cached in the hw structure and following calls
- * will return cached value
- */
-static int
-ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle)
-{
-	struct ice_aqc_get_link_topo *cmd;
-	struct ice_aq_desc desc;
-	int status;
-	u8 idx;
-
-	/* If handle was read previously return cached value */
-	if (hw->io_expander_handle) {
-		*pca9575_handle = hw->io_expander_handle;
-		return 0;
-	}
-
-	/* If handle was not detected read it from the netlist */
-	cmd = &desc.params.get_link_topo;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
-
-	/* Set node type to GPIO controller */
-	cmd->addr.topo_params.node_type_ctx =
-		(ICE_AQC_LINK_TOPO_NODE_TYPE_M &
-		 ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL);
-
-#define SW_PCA9575_SFP_TOPO_IDX		2
-#define SW_PCA9575_QSFP_TOPO_IDX	1
-
-	/* Check if the SW IO expander controlling SMA exists in the netlist. */
-	if (hw->device_id == ICE_DEV_ID_E810C_SFP)
-		idx = SW_PCA9575_SFP_TOPO_IDX;
-	else if (hw->device_id == ICE_DEV_ID_E810C_QSFP)
-		idx = SW_PCA9575_QSFP_TOPO_IDX;
-	else
-		return -EOPNOTSUPP;
-
-	cmd->addr.topo_params.index = idx;
-
-	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
-	if (status)
-		return -EOPNOTSUPP;
-
-	/* Verify if we found the right IO expander type */
-	if (desc.params.get_link_topo.node_part_num !=
-		ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575)
-		return -EOPNOTSUPP;
-
-	/* If present save the handle and return it */
-	hw->io_expander_handle =
-		le16_to_cpu(desc.params.get_link_topo.addr.handle);
-	*pca9575_handle = hw->io_expander_handle;
-
-	return 0;
-}
-
-/**
  * ice_read_sma_ctrl
  * @hw: pointer to the hw struct
  * @data: pointer to data to be read from the GPIO controller
@@ -5305,37 +4826,6 @@ int ice_write_sma_ctrl(struct ice_hw *hw, u8 data)
 }
 
 /**
- * ice_read_pca9575_reg
- * @hw: pointer to the hw struct
- * @offset: GPIO controller register offset
- * @data: pointer to data to be read from the GPIO controller
- *
- * Read the register from the GPIO controller
- */
-int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data)
-{
-	struct ice_aqc_link_topo_addr link_topo;
-	__le16 addr;
-	u16 handle;
-	int err;
-
-	memset(&link_topo, 0, sizeof(link_topo));
-
-	err = ice_get_pca9575_handle(hw, &handle);
-	if (err)
-		return err;
-
-	link_topo.handle = cpu_to_le16(handle);
-	link_topo.topo_params.node_type_ctx =
-		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M,
-			   ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED);
-
-	addr = cpu_to_le16((u16)offset);
-
-	return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL);
-}
-
-/**
  * ice_ptp_read_sdp_ac - read SDP available connections section from NVM
  * @hw: pointer to the HW struct
  * @entries: returns the SDP available connections section from NVM
@@ -5401,16 +4891,138 @@ exit:
  */
 static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp)
 {
-	ptp->phy_model = ICE_PHY_E810;
+	ptp->num_lports = 8;
+	ptp->ports_per_phy = 4;
+
+	init_waitqueue_head(&ptp->phy.e810.atqbal_wq);
+}
+
+/* E830 functions
+ *
+ * The following functions operate on the E830 series devices.
+ *
+ */
+
+/**
+ * ice_ptp_init_phc_e830 - Perform E830 specific PHC initialization
+ * @hw: pointer to HW struct
+ *
+ * Perform E830-specific PTP hardware clock initialization steps.
+ */
+static void ice_ptp_init_phc_e830(const struct ice_hw *hw)
+{
+	ice_ptp_cfg_sync_delay(hw, ICE_E810_E830_SYNC_DELAY);
+}
+
+/**
+ * ice_ptp_write_direct_incval_e830 - Prep PHY port increment value change
+ * @hw: pointer to HW struct
+ * @incval: The new 40bit increment value to prepare
+ *
+ * Prepare the PHY port for a new increment value by programming the PHC
+ * GLTSYN_INCVAL_L and GLTSYN_INCVAL_H registers. The actual change is
+ * completed by FW automatically.
+ */
+static void ice_ptp_write_direct_incval_e830(const struct ice_hw *hw,
+					     u64 incval)
+{
+	u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+
+	wr32(hw, GLTSYN_INCVAL_L(tmr_idx), lower_32_bits(incval));
+	wr32(hw, GLTSYN_INCVAL_H(tmr_idx), upper_32_bits(incval));
+}
+
+/**
+ * ice_ptp_write_direct_phc_time_e830 - Prepare PHY port with initial time
+ * @hw: Board private structure
+ * @time: Time to initialize the PHY port clock to
+ *
+ * Program the PHY port ETH_GLTSYN_SHTIME registers in preparation setting the
+ * initial clock time. The time will not actually be programmed until the
+ * driver issues an ICE_PTP_INIT_TIME command.
+ *
+ * The time value is the upper 32 bits of the PHY timer, usually in units of
+ * nominal nanoseconds.
+ */
+static void ice_ptp_write_direct_phc_time_e830(const struct ice_hw *hw,
+					       u64 time)
+{
+	u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+
+	wr32(hw, GLTSYN_TIME_0(tmr_idx), 0);
+	wr32(hw, GLTSYN_TIME_L(tmr_idx), lower_32_bits(time));
+	wr32(hw, GLTSYN_TIME_H(tmr_idx), upper_32_bits(time));
+}
+
+/**
+ * ice_ptp_port_cmd_e830 - Prepare all external PHYs for a timer command
+ * @hw: pointer to HW struct
+ * @cmd: Command to be sent to the port
+ *
+ * Prepare the external PHYs connected to this device for a timer sync
+ * command.
+ *
+ * Return: 0 on success, negative error code when PHY write failed
+ */
+static int ice_ptp_port_cmd_e830(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
+{
+	u32 val = ice_ptp_tmr_cmd_to_port_reg(hw, cmd);
+
+	return ice_write_phy_reg_e810(hw, E830_ETH_GLTSYN_CMD, val);
+}
+
+/**
+ * ice_read_phy_tstamp_e830 - Read a PHY timestamp out of the external PHY
+ * @hw: pointer to the HW struct
+ * @idx: the timestamp index to read
+ * @tstamp: on return, the 40bit timestamp value
+ *
+ * Read a 40bit timestamp value out of the timestamp block of the external PHY
+ * on the E830 device.
+ */
+static void ice_read_phy_tstamp_e830(const struct ice_hw *hw, u8 idx,
+				     u64 *tstamp)
+{
+	u32 hi, lo;
+
+	hi = rd32(hw, E830_PRTTSYN_TXTIME_H(idx));
+	lo = rd32(hw, E830_PRTTSYN_TXTIME_L(idx));
+
+	/* For E830 devices, the timestamp is reported with the lower 32 bits
+	 * in the low register, and the upper 8 bits in the high register.
+	 */
+	*tstamp = FIELD_PREP(PHY_EXT_40B_HIGH_M, hi) |
+		  FIELD_PREP(PHY_EXT_40B_LOW_M, lo);
+}
+
+/**
+ * ice_get_phy_tx_tstamp_ready_e830 - Read Tx memory status register
+ * @hw: pointer to the HW struct
+ * @port: the PHY port to read
+ * @tstamp_ready: contents of the Tx memory status register
+ */
+static void ice_get_phy_tx_tstamp_ready_e830(const struct ice_hw *hw, u8 port,
+					     u64 *tstamp_ready)
+{
+	*tstamp_ready = rd32(hw, E830_PRTMAC_TS_TX_MEM_VALID_H);
+	*tstamp_ready <<= 32;
+	*tstamp_ready |= rd32(hw, E830_PRTMAC_TS_TX_MEM_VALID_L);
+}
+
+/**
+ * ice_ptp_init_phy_e830 - initialize PHY parameters
+ * @ptp: pointer to the PTP HW struct
+ */
+static void ice_ptp_init_phy_e830(struct ice_ptp_hw *ptp)
+{
 	ptp->num_lports = 8;
 	ptp->ports_per_phy = 4;
 }
 
 /* Device agnostic functions
  *
- * The following functions implement shared behavior common to both E822 and
- * E810 devices, possibly calling a device specific implementation where
- * necessary.
+ * The following functions implement shared behavior common to all devices,
+ * possibly calling a device specific implementation where necessary.
  */
 
 /**
@@ -5473,14 +5085,22 @@ void ice_ptp_init_hw(struct ice_hw *hw)
 {
 	struct ice_ptp_hw *ptp = &hw->ptp;
 
-	if (ice_is_e822(hw) || ice_is_e823(hw))
-		ice_ptp_init_phy_e82x(ptp);
-	else if (ice_is_e810(hw))
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		ice_ptp_init_phy_e810(ptp);
-	else if (ice_is_e825c(hw))
-		ice_ptp_init_phy_e825c(hw);
-	else
-		ptp->phy_model = ICE_PHY_UNSUP;
+		break;
+	case ICE_MAC_E830:
+		ice_ptp_init_phy_e830(ptp);
+		break;
+	case ICE_MAC_GENERIC:
+		ice_ptp_init_phy_e82x(ptp);
+		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		ice_ptp_init_phy_e825(hw);
+		break;
+	default:
+		return;
+	}
 }
 
 /**
@@ -5501,11 +5121,11 @@ void ice_ptp_init_hw(struct ice_hw *hw)
 static int ice_ptp_write_port_cmd(struct ice_hw *hw, u8 port,
 				  enum ice_ptp_tmr_cmd cmd)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_ptp_write_port_cmd_eth56g(hw, port, cmd);
-	case ICE_PHY_E82X:
+	switch (hw->mac_type) {
+	case ICE_MAC_GENERIC:
 		return ice_ptp_write_port_cmd_e82x(hw, port, cmd);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_ptp_write_port_cmd_eth56g(hw, port, cmd);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5566,9 +5186,11 @@ static int ice_ptp_port_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 	u32 port;
 
 	/* PHY models which can program all ports simultaneously */
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_ptp_port_cmd_e810(hw, cmd);
+	case ICE_MAC_E830:
+		return ice_ptp_port_cmd_e830(hw, cmd);
 	default:
 		break;
 	}
@@ -5639,23 +5261,29 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time)
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 
 	/* Source timers */
+	/* For E830 we don't need to use shadow registers, its automatic */
+	if (hw->mac_type == ICE_MAC_E830) {
+		ice_ptp_write_direct_phc_time_e830(hw, time);
+		return 0;
+	}
+
 	wr32(hw, GLTSYN_SHTIME_L(tmr_idx), lower_32_bits(time));
 	wr32(hw, GLTSYN_SHTIME_H(tmr_idx), upper_32_bits(time));
 	wr32(hw, GLTSYN_SHTIME_0(tmr_idx), 0);
 
 	/* PHY timers */
 	/* Fill Rx and Tx ports and send msg to PHY */
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_ptp_prep_phy_time_eth56g(hw,
-						   (u32)(time & 0xFFFFFFFF));
-		break;
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		err = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF);
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		err = ice_ptp_prep_phy_time_e82x(hw, time & 0xFFFFFFFF);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_ptp_prep_phy_time_eth56g(hw,
+						   (u32)(time & 0xFFFFFFFF));
+		break;
 	default:
 		err = -EOPNOTSUPP;
 	}
@@ -5687,20 +5315,26 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval)
 
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 
+	/* For E830 we don't need to use shadow registers, its automatic */
+	if (hw->mac_type == ICE_MAC_E830) {
+		ice_ptp_write_direct_incval_e830(hw, incval);
+		return 0;
+	}
+
 	/* Shadow Adjust */
 	wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval));
 	wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval));
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_ptp_prep_phy_incval_eth56g(hw, incval);
-		break;
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		err = ice_ptp_prep_phy_incval_e810(hw, incval);
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		err = ice_ptp_prep_phy_incval_e82x(hw, incval);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_ptp_prep_phy_incval_eth56g(hw, incval);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 	}
@@ -5760,16 +5394,19 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj)
 	wr32(hw, GLTSYN_SHADJ_L(tmr_idx), 0);
 	wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_ptp_prep_phy_adj_eth56g(hw, adj);
-		break;
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		err = ice_ptp_prep_phy_adj_e810(hw, adj);
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_E830:
+		/* E830 sync PHYs automatically after setting GLTSYN_SHADJ */
+		return 0;
+	case ICE_MAC_GENERIC:
 		err = ice_ptp_prep_phy_adj_e82x(hw, adj);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_ptp_prep_phy_adj_eth56g(hw, adj);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 	}
@@ -5793,13 +5430,16 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj)
  */
 int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp);
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_read_phy_tstamp_e810(hw, block, idx, tstamp);
-	case ICE_PHY_E82X:
+	case ICE_MAC_E830:
+		ice_read_phy_tstamp_e830(hw, idx, tstamp);
+		return 0;
+	case ICE_MAC_GENERIC:
 		return ice_read_phy_tstamp_e82x(hw, block, idx, tstamp);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5823,13 +5463,13 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp)
  */
 int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_clear_ptp_tstamp_eth56g(hw, block, idx);
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_clear_phy_tstamp_e810(hw, block, idx);
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		return ice_clear_phy_tstamp_e82x(hw, block, idx);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_clear_ptp_tstamp_eth56g(hw, block, idx);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5886,14 +5526,14 @@ static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx)
  */
 void ice_ptp_reset_ts_memory(struct ice_hw *hw)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		ice_ptp_reset_ts_memory_eth56g(hw);
-		break;
-	case ICE_PHY_E82X:
+	switch (hw->mac_type) {
+	case ICE_MAC_GENERIC:
 		ice_ptp_reset_ts_memory_e82x(hw);
 		break;
-	case ICE_PHY_E810:
+	case ICE_MAC_GENERIC_3K_E825:
+		ice_ptp_reset_ts_memory_eth56g(hw);
+		break;
+	case ICE_MAC_E810:
 	default:
 		return;
 	}
@@ -5915,13 +5555,16 @@ int ice_ptp_init_phc(struct ice_hw *hw)
 	/* Clear event err indications for auxiliary pins */
 	(void)rd32(hw, GLTSYN_STAT(src_idx));
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_ptp_init_phc_eth56g(hw);
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_ptp_init_phc_e810(hw);
-	case ICE_PHY_E82X:
+	case ICE_MAC_E830:
+		ice_ptp_init_phc_e830(hw);
+		return 0;
+	case ICE_MAC_GENERIC:
 		return ice_ptp_init_phc_e82x(hw);
+	case ICE_MAC_GENERIC_3K_E825:
+		return 0;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5940,17 +5583,19 @@ int ice_ptp_init_phc(struct ice_hw *hw)
  */
 int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_get_phy_tx_tstamp_ready_eth56g(hw, block,
-							  tstamp_ready);
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_get_phy_tx_tstamp_ready_e810(hw, block,
 							tstamp_ready);
-	case ICE_PHY_E82X:
+	case ICE_MAC_E830:
+		ice_get_phy_tx_tstamp_ready_e830(hw, block, tstamp_ready);
+		return 0;
+	case ICE_MAC_GENERIC:
 		return ice_get_phy_tx_tstamp_ready_e82x(hw, block,
 							tstamp_ready);
-		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_get_phy_tx_tstamp_ready_eth56g(hw, block,
+							  tstamp_ready);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 1cee0f1bba2d..5896b346e579 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -65,14 +65,14 @@ enum ice_eth56g_link_spd {
 
 /**
  * struct ice_phy_reg_info_eth56g - ETH56G PHY register parameters
- * @base: base address for each PHY block
+ * @base_addr: base address for each PHY block
  * @step: step between PHY lanes
  *
  * Characteristic information for the various PHY register parameters in the
  * ETH56G devices
  */
 struct ice_phy_reg_info_eth56g {
-	u32 base[NUM_ETH56G_PHY_RES];
+	u32 base_addr;
 	u32 step;
 };
 
@@ -80,7 +80,6 @@ struct ice_phy_reg_info_eth56g {
  * struct ice_time_ref_info_e82x
  * @pll_freq: Frequency of PLL that drives timer ticks in Hz
  * @nominal_incval: increment to generate nanoseconds in GLTSYN_TIME_L
- * @pps_delay: propagation delay of the PPS output signal
  *
  * Characteristic information for the various TIME_REF sources possible in the
  * E822 devices
@@ -88,7 +87,6 @@ struct ice_phy_reg_info_eth56g {
 struct ice_time_ref_info_e82x {
 	u64 pll_freq;
 	u64 nominal_incval;
-	u8 pps_delay;
 };
 
 /**
@@ -196,23 +194,6 @@ struct ice_eth56g_mac_reg_cfg {
 extern
 const struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD];
 
-/**
- * struct ice_cgu_pll_params_e82x - E82X CGU parameters
- * @refclk_pre_div: Reference clock pre-divisor
- * @feedback_div: Feedback divisor
- * @frac_n_div: Fractional divisor
- * @post_pll_div: Post PLL divisor
- *
- * Clock Generation Unit parameters used to program the PLL based on the
- * selected TIME_REF frequency.
- */
-struct ice_cgu_pll_params_e82x {
-	u32 refclk_pre_div;
-	u32 feedback_div;
-	u32 frac_n_div;
-	u32 post_pll_div;
-};
-
 #define E810C_QSFP_C827_0_HANDLE	2
 #define E810C_QSFP_C827_1_HANDLE	3
 enum ice_e810_c827_idx {
@@ -284,31 +265,6 @@ struct ice_cgu_pin_desc {
 	struct dpll_pin_frequency *freq_supp;
 };
 
-extern const struct
-ice_cgu_pll_params_e82x e822_cgu_params[NUM_ICE_TIME_REF_FREQ];
-
-/**
- * struct ice_cgu_pll_params_e825c - E825C CGU parameters
- * @tspll_ck_refclkfreq: tspll_ck_refclkfreq selection
- * @tspll_ndivratio: ndiv ratio that goes directly to the pll
- * @tspll_fbdiv_intgr: TS PLL integer feedback divide
- * @tspll_fbdiv_frac:  TS PLL fractional feedback divide
- * @ref1588_ck_div: clock divider for tspll ref
- *
- * Clock Generation Unit parameters used to program the PLL based on the
- * selected TIME_REF/TCXO frequency.
- */
-struct ice_cgu_pll_params_e825c {
-	u32 tspll_ck_refclkfreq;
-	u32 tspll_ndivratio;
-	u32 tspll_fbdiv_intgr;
-	u32 tspll_fbdiv_frac;
-	u32 ref1588_ck_div;
-};
-
-extern const struct
-ice_cgu_pll_params_e825c e825c_cgu_params[NUM_ICE_TIME_REF_FREQ];
-
 #define E810C_QSFP_C827_0_HANDLE 2
 #define E810C_QSFP_C827_1_HANDLE 3
 
@@ -316,7 +272,7 @@ ice_cgu_pll_params_e825c e825c_cgu_params[NUM_ICE_TIME_REF_FREQ];
 extern const struct ice_phy_reg_info_eth56g eth56g_phy_res[NUM_ETH56G_PHY_RES];
 
 /* Table of constants related to possible TIME_REF sources */
-extern const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ];
+extern const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TSPLL_FREQ];
 
 /* Table of constants for Vernier calibration on E822 */
 extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD];
@@ -326,12 +282,10 @@ extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD];
  */
 #define ICE_E810_PLL_FREQ		812500000
 #define ICE_PTP_NOMINAL_INCVAL_E810	0x13b13b13bULL
-#define ICE_E810_OUT_PROP_DELAY_NS	1
-#define ICE_E825C_OUT_PROP_DELAY_NS	11
+#define ICE_E810_E830_SYNC_DELAY	0
 
 /* Device agnostic functions */
 u8 ice_get_ptp_src_clock_index(struct ice_hw *hw);
-int ice_cgu_cfg_pps_out(struct ice_hw *hw, bool enable);
 bool ice_ptp_lock(struct ice_hw *hw);
 void ice_ptp_unlock(struct ice_hw *hw);
 void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd);
@@ -360,7 +314,8 @@ void ice_ptp_reset_ts_memory_quad_e82x(struct ice_hw *hw, u8 quad);
  *
  * Returns the current TIME_REF from the capabilities structure.
  */
-static inline enum ice_time_ref_freq ice_e82x_time_ref(const struct ice_hw *hw)
+
+static inline enum ice_tspll_freq ice_e82x_time_ref(const struct ice_hw *hw)
 {
 	return hw->func_caps.ts_func_info.time_ref;
 }
@@ -374,26 +329,21 @@ static inline enum ice_time_ref_freq ice_e82x_time_ref(const struct ice_hw *hw)
  * change, such as an update to the CGU registers.
  */
 static inline void
-ice_set_e82x_time_ref(struct ice_hw *hw, enum ice_time_ref_freq time_ref)
+ice_set_e82x_time_ref(struct ice_hw *hw, enum ice_tspll_freq time_ref)
 {
 	hw->func_caps.ts_func_info.time_ref = time_ref;
 }
 
-static inline u64 ice_e82x_pll_freq(enum ice_time_ref_freq time_ref)
+static inline u64 ice_e82x_pll_freq(enum ice_tspll_freq time_ref)
 {
 	return e82x_time_ref[time_ref].pll_freq;
 }
 
-static inline u64 ice_e82x_nominal_incval(enum ice_time_ref_freq time_ref)
+static inline u64 ice_e82x_nominal_incval(enum ice_tspll_freq time_ref)
 {
 	return e82x_time_ref[time_ref].nominal_incval;
 }
 
-static inline u64 ice_e82x_pps_delay(enum ice_time_ref_freq time_ref)
-{
-	return e82x_time_ref[time_ref].pps_delay;
-}
-
 /* E822 Vernier calibration functions */
 int ice_stop_phy_timer_e82x(struct ice_hw *hw, u8 port, bool soft_reset);
 int ice_start_phy_timer_e82x(struct ice_hw *hw, u8 port);
@@ -404,7 +354,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold);
 /* E810 family functions */
 int ice_read_sma_ctrl(struct ice_hw *hw, u8 *data);
 int ice_write_sma_ctrl(struct ice_hw *hw, u8 data);
-int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data);
 int ice_ptp_read_sdp_ac(struct ice_hw *hw, __le16 *entries, uint *num_entries);
 int ice_cgu_get_num_pins(struct ice_hw *hw, bool input);
 enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input);
@@ -432,20 +381,6 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port);
 #define ICE_ETH56G_NOMINAL_THRESH4	0x7777
 #define ICE_ETH56G_NOMINAL_TX_THRESH	0x6
 
-static inline u64 ice_prop_delay(const struct ice_hw *hw)
-{
-	switch (hw->ptp.phy_model) {
-	case ICE_PHY_ETH56G:
-		return ICE_E825C_OUT_PROP_DELAY_NS;
-	case ICE_PHY_E810:
-		return ICE_E810_OUT_PROP_DELAY_NS;
-	case ICE_PHY_E82X:
-		return ice_e82x_pps_delay(ice_e82x_time_ref(hw));
-	default:
-		return 0;
-	}
-}
-
 /**
  * ice_get_base_incval - Get base clock increment value
  * @hw: pointer to the HW struct
@@ -454,23 +389,19 @@ static inline u64 ice_prop_delay(const struct ice_hw *hw)
  */
 static inline u64 ice_get_base_incval(struct ice_hw *hw)
 {
-	switch (hw->ptp.phy_model) {
-	case ICE_PHY_ETH56G:
-		return ICE_ETH56G_NOMINAL_INCVAL;
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
 		return ICE_PTP_NOMINAL_INCVAL_E810;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		return ice_e82x_nominal_incval(ice_e82x_time_ref(hw));
+	case ICE_MAC_GENERIC_3K_E825:
+		return ICE_ETH56G_NOMINAL_INCVAL;
 	default:
 		return 0;
 	}
 }
 
-static inline bool ice_is_dual(struct ice_hw *hw)
-{
-	return !!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_DUAL_M);
-}
-
 #define PFTSYN_SEM_BYTES	4
 
 #define ICE_PTP_CLOCK_INDEX_0	0x00
@@ -673,27 +604,41 @@ static inline bool ice_is_dual(struct ice_hw *hw)
 /* E810 timer command register */
 #define E810_ETH_GLTSYN_CMD		0x03000344
 
+/* E830 timer command register */
+#define E830_ETH_GLTSYN_CMD		0x00088814
+
+/* E810 PHC time register */
+#define E830_GLTSYN_TIME_L(_tmr_idx)	(0x0008A000 + 0x1000 * (_tmr_idx))
+
 /* Source timer incval macros */
 #define INCVAL_HIGH_M			0xFF
 
-/* Timestamp block macros */
+/* PHY 40b registers macros */
+#define PHY_EXT_40B_LOW_M		GENMASK(31, 0)
+#define PHY_EXT_40B_HIGH_M		GENMASK_ULL(39, 32)
+#define PHY_40B_LOW_M			GENMASK(7, 0)
+#define PHY_40B_HIGH_M			GENMASK_ULL(39, 8)
 #define TS_VALID			BIT(0)
 #define TS_LOW_M			0xFFFFFFFF
 #define TS_HIGH_M			0xFF
 #define TS_HIGH_S			32
 
-#define TS_PHY_LOW_M			GENMASK(7, 0)
-#define TS_PHY_HIGH_M			GENMASK_ULL(39, 8)
-
 #define BYTES_PER_IDX_ADDR_L_U		8
 #define BYTES_PER_IDX_ADDR_L		4
 
 /* Tx timestamp low latency read definitions */
-#define TS_LL_READ_RETRIES		200
-#define TS_LL_READ_TS_HIGH		GENMASK(23, 16)
-#define TS_LL_READ_TS_IDX		GENMASK(29, 24)
-#define TS_LL_READ_TS_INTR		BIT(30)
-#define TS_LL_READ_TS			BIT(31)
+#define REG_LL_PROXY_H_TIMEOUT_US	2000
+#define REG_LL_PROXY_H_PHY_TMR_CMD_M	GENMASK(7, 6)
+#define REG_LL_PROXY_H_PHY_TMR_CMD_ADJ	0x1
+#define REG_LL_PROXY_H_PHY_TMR_CMD_FREQ	0x2
+#define REG_LL_PROXY_H_TS_HIGH		GENMASK(23, 16)
+#define REG_LL_PROXY_H_PHY_TMR_IDX_M	BIT(24)
+#define REG_LL_PROXY_H_TS_IDX		GENMASK(29, 24)
+#define REG_LL_PROXY_H_TS_INTR_ENA	BIT(30)
+#define REG_LL_PROXY_H_EXEC		BIT(31)
+
+#define REG_LL_PROXY_L			PF_SB_ATQBAH
+#define REG_LL_PROXY_H			PF_SB_ATQBAL
 
 /* Internal PHY timestamp address */
 #define TS_L(a, idx) ((a) + ((idx) * BYTES_PER_IDX_ADDR_L_U))
@@ -717,6 +662,7 @@ static inline bool ice_is_dual(struct ice_hw *hw)
 #define ICE_SMA1_MASK		(ICE_SMA1_DIR_EN | ICE_SMA1_TX_EN)
 #define ICE_SMA2_MASK		(ICE_SMA2_UFL2_RX_DIS | ICE_SMA2_DIR_EN | \
 				 ICE_SMA2_TX_EN)
+#define ICE_SMA2_INACTIVE_MASK	(ICE_SMA2_DIR_EN | ICE_SMA2_TX_EN)
 #define ICE_ALL_SMA_MASK	(ICE_SMA1_MASK | ICE_SMA2_MASK)
 
 #define ICE_SMA_MIN_BIT		3
@@ -788,36 +734,19 @@ static inline bool ice_is_dual(struct ice_hw *hw)
 #define PHY_MAC_XIF_TS_SFD_ENA_M	ICE_M(0x1, 20)
 #define PHY_MAC_XIF_GMII_TS_SEL_M	ICE_M(0x1, 21)
 
-/* GPCS config register */
-#define PHY_GPCS_CONFIG_REG0		0x268
-#define PHY_GPCS_CONFIG_REG0_TX_THR_M	ICE_M(0xF, 24)
-#define PHY_GPCS_BITSLIP		0x5C
-
 #define PHY_TS_INT_CONFIG_THRESHOLD_M	ICE_M(0x3F, 0)
 #define PHY_TS_INT_CONFIG_ENA_M		BIT(6)
 
-/* 1-step PTP config */
-#define PHY_PTP_1STEP_CONFIG		0x270
-#define PHY_PTP_1STEP_T1S_UP64_M	ICE_M(0xF, 4)
-#define PHY_PTP_1STEP_T1S_DELTA_M	ICE_M(0xF, 8)
-#define PHY_PTP_1STEP_PEER_DELAY(_port)	(0x274 + 4 * (_port))
-#define PHY_PTP_1STEP_PD_ADD_PD_M	ICE_M(0x1, 0)
-#define PHY_PTP_1STEP_PD_DELAY_M	ICE_M(0x3fffffff, 1)
-#define PHY_PTP_1STEP_PD_DLY_V_M	ICE_M(0x1, 31)
-
 /* Macros to derive offsets for TimeStampLow and TimeStampHigh */
 #define PHY_TSTAMP_L(x) (((x) * 8) + 0)
 #define PHY_TSTAMP_U(x) (((x) * 8) + 4)
 
-#define PHY_REG_REVISION		0x85000
-
 #define PHY_REG_DESKEW_0		0x94
 #define PHY_REG_DESKEW_0_RLEVEL		GENMASK(6, 0)
 #define PHY_REG_DESKEW_0_RLEVEL_FRAC	GENMASK(9, 7)
 #define PHY_REG_DESKEW_0_RLEVEL_FRAC_W	3
 #define PHY_REG_DESKEW_0_VALID		GENMASK(10, 10)
 
-#define PHY_REG_GPCS_BITSLIP		0x5C
 #define PHY_REG_SD_BIT_SLIP(_port_offset)	(0x29C + 4 * (_port_offset))
 #define PHY_REVISION_ETH56G		0x10200
 #define PHY_VENDOR_TXLANE_THRESH	0x2000C
@@ -837,7 +766,21 @@ static inline bool ice_is_dual(struct ice_hw *hw)
 #define PHY_MAC_BLOCKTIME		0x50
 #define PHY_MAC_MARKERTIME		0x54
 #define PHY_MAC_TX_OFFSET		0x58
+#define PHY_GPCS_BITSLIP		0x5C
 
 #define PHY_PTP_INT_STATUS		0x7FD140
 
+/* ETH56G registers shared per quad */
+/* GPCS config register */
+#define PHY_GPCS_CONFIG_REG0		0x268
+#define PHY_GPCS_CONFIG_REG0_TX_THR_M	GENMASK(27, 24)
+/* 1-step PTP config */
+#define PHY_PTP_1STEP_CONFIG		0x270
+#define PHY_PTP_1STEP_T1S_UP64_M	GENMASK(7, 4)
+#define PHY_PTP_1STEP_T1S_DELTA_M	GENMASK(11, 8)
+#define PHY_PTP_1STEP_PEER_DELAY(_quad_lane)	(0x274 + 4 * (_quad_lane))
+#define PHY_PTP_1STEP_PD_ADD_PD_M	BIT(0)
+#define PHY_PTP_1STEP_PD_DELAY_M	GENMASK(30, 1)
+#define PHY_PTP_1STEP_PD_DLY_V_M	BIT(31)
+
 #endif /* _ICE_PTP_HW_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index fb7a1b9a4313..cb08746556a6 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -219,7 +219,8 @@ ice_repr_setup_tc_cls_flower(struct ice_repr *repr,
 {
 	switch (flower->command) {
 	case FLOW_CLS_REPLACE:
-		return ice_add_cls_flower(repr->netdev, repr->src_vsi, flower);
+		return ice_add_cls_flower(repr->netdev, repr->src_vsi, flower,
+					  true);
 	case FLOW_CLS_DESTROY:
 		return ice_del_cls_flower(repr->src_vsi, flower);
 	default:
@@ -336,6 +337,7 @@ void ice_repr_destroy(struct ice_repr *repr)
 static void ice_repr_rem_vf(struct ice_repr *repr)
 {
 	ice_eswitch_decfg_vsi(repr->src_vsi, repr->parent_mac);
+	ice_pass_vf_tx_lldp(repr->src_vsi, true);
 	unregister_netdev(repr->netdev);
 	ice_devlink_destroy_vf_port(repr->vf);
 	ice_virtchnl_set_dflt_ops(repr->vf);
@@ -417,6 +419,10 @@ static int ice_repr_add_vf(struct ice_repr *repr)
 	if (err)
 		goto err_netdev;
 
+	err = ice_drop_vf_tx_lldp(repr->src_vsi, true);
+	if (err)
+		goto err_drop_lldp;
+
 	err = ice_eswitch_cfg_vsi(repr->src_vsi, repr->parent_mac);
 	if (err)
 		goto err_cfg_vsi;
@@ -429,6 +435,8 @@ static int ice_repr_add_vf(struct ice_repr *repr)
 	return 0;
 
 err_cfg_vsi:
+	ice_pass_vf_tx_lldp(repr->src_vsi, true);
+err_drop_lldp:
 	unregister_netdev(repr->netdev);
 err_netdev:
 	ice_devlink_destroy_vf_port(vf);
diff --git a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
index 3b0054faf70c..21bb861febbf 100644
--- a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
@@ -46,13 +46,11 @@ struct ice_sbq_evt_desc {
 	u8 data[24];
 };
 
-enum ice_sbq_msg_dev {
-	eth56g_phy_0	= 0x02,
-	rmn_0		= 0x02,
-	rmn_1		= 0x03,
-	rmn_2		= 0x04,
-	cgu		= 0x06,
-	eth56g_phy_1	= 0x0D,
+enum ice_sbq_dev_id {
+	ice_sbq_dev_phy_0	= 0x02,
+	ice_sbq_dev_cgu		= 0x06,
+	ice_sbq_dev_phy_0_peer	= 0x0D,
+	ice_sbq_dev_cgu_peer	= 0x0F,
 };
 
 enum ice_sbq_msg_opcode {
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 6ca13c5dcb14..fff0c1afdb41 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -85,6 +85,27 @@ ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid)
 }
 
 /**
+ * ice_sched_find_next_vsi_node - find the next node for a given VSI
+ * @vsi_node: VSI support node to start search with
+ *
+ * Return: Next VSI support node, or NULL.
+ *
+ * The function returns a pointer to the next node from the VSI layer
+ * assigned to the given VSI, or NULL if there is no such a node.
+ */
+static struct ice_sched_node *
+ice_sched_find_next_vsi_node(struct ice_sched_node *vsi_node)
+{
+	unsigned int vsi_handle = vsi_node->vsi_handle;
+
+	while ((vsi_node = vsi_node->sibling) != NULL)
+		if (vsi_node->vsi_handle == vsi_handle)
+			break;
+
+	return vsi_node;
+}
+
+/**
  * ice_aqc_send_sched_elem_cmd - send scheduling elements cmd
  * @hw: pointer to the HW struct
  * @cmd_opc: cmd opcode
@@ -102,13 +123,13 @@ ice_aqc_send_sched_elem_cmd(struct ice_hw *hw, enum ice_adminq_opc cmd_opc,
 			    u16 *elems_resp, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_sched_elem_cmd *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.sched_elem_cmd;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, cmd_opc);
 	cmd->num_elem_req = cpu_to_le16(elems_req);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
 	if (!status && elems_resp)
 		*elems_resp = le16_to_cpu(cmd->num_elem_resp);
@@ -371,10 +392,10 @@ ice_aq_get_dflt_topo(struct ice_hw *hw, u8 lport,
 		     u8 *num_branches, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_get_topo *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.get_topo;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_dflt_topo);
 	cmd->port_num = lport;
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
@@ -497,7 +518,7 @@ ice_aq_query_sched_res(struct ice_hw *hw, u16 buf_size,
 		       struct ice_aqc_query_txsched_res_resp *buf,
 		       struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_query_sched_res);
 	return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
@@ -662,13 +683,13 @@ ice_aq_rl_profile(struct ice_hw *hw, enum ice_adminq_opc opcode,
 		  u16 buf_size, u16 *num_processed, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_rl_profile *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.rl_profile;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, opcode);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 	cmd->num_profiles = cpu_to_le16(num_profiles);
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
 	if (!status && num_processed)
@@ -1084,8 +1105,10 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi,
 		if (parent->num_children < max_child_nodes) {
 			new_num_nodes = max_child_nodes - parent->num_children;
 		} else {
-			/* This parent is full, try the next sibling */
-			parent = parent->sibling;
+			/* This parent is full,
+			 * try the next available sibling.
+			 */
+			parent = ice_sched_find_next_vsi_node(parent);
 			/* Don't modify the first node TEID memory if the
 			 * first node was added already in the above call.
 			 * Instead send some temp memory for all other
@@ -1528,12 +1551,23 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
 	/* get the first queue group node from VSI sub-tree */
 	qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer);
 	while (qgrp_node) {
+		struct ice_sched_node *next_vsi_node;
+
 		/* make sure the qgroup node is part of the VSI subtree */
 		if (ice_sched_find_node_in_subtree(pi->hw, vsi_node, qgrp_node))
 			if (qgrp_node->num_children < max_children &&
 			    qgrp_node->owner == owner)
 				break;
 		qgrp_node = qgrp_node->sibling;
+		if (qgrp_node)
+			continue;
+
+		next_vsi_node = ice_sched_find_next_vsi_node(vsi_node);
+		if (!next_vsi_node)
+			break;
+
+		vsi_node = next_vsi_node;
+		qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer);
 	}
 
 	/* Select the best queue group */
@@ -1604,16 +1638,16 @@ ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node,
 /**
  * ice_sched_calc_vsi_child_nodes - calculate number of VSI child nodes
  * @hw: pointer to the HW struct
- * @num_qs: number of queues
+ * @num_new_qs: number of new queues that will be added to the tree
  * @num_nodes: num nodes array
  *
  * This function calculates the number of VSI child nodes based on the
  * number of queues.
  */
 static void
-ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes)
+ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_new_qs, u16 *num_nodes)
 {
-	u16 num = num_qs;
+	u16 num = num_new_qs;
 	u8 i, qgl, vsil;
 
 	qgl = ice_sched_get_qgrp_layer(hw);
@@ -1779,7 +1813,11 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle,
 		if (!parent)
 			return -EIO;
 
-		if (i == vsil)
+		/* Do not modify the VSI handle for already existing VSI nodes,
+		 * (if no new VSI node was added to the tree).
+		 * Assign the VSI handle only to newly added VSI nodes.
+		 */
+		if (i == vsil && num_added)
 			parent->vsi_handle = vsi_handle;
 	}
 
@@ -1813,6 +1851,41 @@ ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_handle, u8 tc)
 }
 
 /**
+ * ice_sched_recalc_vsi_support_nodes - recalculate VSI support nodes count
+ * @hw: pointer to the HW struct
+ * @vsi_node: pointer to the leftmost VSI node that needs to be extended
+ * @new_numqs: new number of queues that has to be handled by the VSI
+ * @new_num_nodes: pointer to nodes count table to modify the VSI layer entry
+ *
+ * This function recalculates the number of supported nodes that need to
+ * be added after adding more Tx queues for a given VSI.
+ * The number of new VSI support nodes that shall be added will be saved
+ * to the @new_num_nodes table for the VSI layer.
+ */
+static void
+ice_sched_recalc_vsi_support_nodes(struct ice_hw *hw,
+				   struct ice_sched_node *vsi_node,
+				   unsigned int new_numqs, u16 *new_num_nodes)
+{
+	u32 vsi_nodes_cnt = 1;
+	u32 max_queue_cnt = 1;
+	u32 qgl, vsil;
+
+	qgl = ice_sched_get_qgrp_layer(hw);
+	vsil = ice_sched_get_vsi_layer(hw);
+
+	for (u32 i = vsil; i <= qgl; i++)
+		max_queue_cnt *= hw->max_children[i];
+
+	while ((vsi_node = ice_sched_find_next_vsi_node(vsi_node)) != NULL)
+		vsi_nodes_cnt++;
+
+	if (new_numqs > (max_queue_cnt * vsi_nodes_cnt))
+		new_num_nodes[vsil] = DIV_ROUND_UP(new_numqs, max_queue_cnt) -
+				      vsi_nodes_cnt;
+}
+
+/**
  * ice_sched_update_vsi_child_nodes - update VSI child nodes
  * @pi: port information structure
  * @vsi_handle: software VSI handle
@@ -1863,15 +1936,25 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
 			return status;
 	}
 
-	if (new_numqs)
-		ice_sched_calc_vsi_child_nodes(hw, new_numqs, new_num_nodes);
-	/* Keep the max number of queue configuration all the time. Update the
-	 * tree only if number of queues > previous number of queues. This may
+	ice_sched_recalc_vsi_support_nodes(hw, vsi_node,
+					   new_numqs, new_num_nodes);
+	ice_sched_calc_vsi_child_nodes(hw, new_numqs - prev_numqs,
+				       new_num_nodes);
+
+	/* Never decrease the number of queues in the tree. Update the tree
+	 * only if number of queues > previous number of queues. This may
 	 * leave some extra nodes in the tree if number of queues < previous
 	 * number but that wouldn't harm anything. Removing those extra nodes
 	 * may complicate the code if those nodes are part of SRL or
 	 * individually rate limited.
+	 * Also, add the required VSI support nodes if the existing ones cannot
+	 * handle the requested new number of queues.
 	 */
+	status = ice_sched_add_vsi_support_nodes(pi, vsi_handle, tc_node,
+						 new_num_nodes);
+	if (status)
+		return status;
+
 	status = ice_sched_add_vsi_child_nodes(pi, vsi_handle, tc_node,
 					       new_num_nodes, owner);
 	if (status)
@@ -2013,6 +2096,58 @@ static bool ice_sched_is_leaf_node_present(struct ice_sched_node *node)
 }
 
 /**
+ * ice_sched_rm_vsi_subtree - remove all nodes assigned to a given VSI
+ * @pi: port information structure
+ * @vsi_node: pointer to the leftmost node of the VSI to be removed
+ * @owner: LAN or RDMA
+ * @tc: TC number
+ *
+ * Return: Zero in case of success, or -EBUSY if the VSI has leaf nodes in TC.
+ *
+ * This function removes all the VSI support nodes associated with a given VSI
+ * and its LAN or RDMA children nodes from the scheduler tree.
+ */
+static int
+ice_sched_rm_vsi_subtree(struct ice_port_info *pi,
+			 struct ice_sched_node *vsi_node, u8 owner, u8 tc)
+{
+	u16 vsi_handle = vsi_node->vsi_handle;
+	bool all_vsi_nodes_removed = true;
+	int j = 0;
+
+	while (vsi_node) {
+		struct ice_sched_node *next_vsi_node;
+
+		if (ice_sched_is_leaf_node_present(vsi_node)) {
+			ice_debug(pi->hw, ICE_DBG_SCHED, "VSI has leaf nodes in TC %d\n", tc);
+			return -EBUSY;
+		}
+		while (j < vsi_node->num_children) {
+			if (vsi_node->children[j]->owner == owner)
+				ice_free_sched_node(pi, vsi_node->children[j]);
+			else
+				j++;
+		}
+
+		next_vsi_node = ice_sched_find_next_vsi_node(vsi_node);
+
+		/* remove the VSI if it has no children */
+		if (!vsi_node->num_children)
+			ice_free_sched_node(pi, vsi_node);
+		else
+			all_vsi_nodes_removed = false;
+
+		vsi_node = next_vsi_node;
+	}
+
+	/* clean up aggregator related VSI info if any */
+	if (all_vsi_nodes_removed)
+		ice_sched_rm_agg_vsi_info(pi, vsi_handle);
+
+	return 0;
+}
+
+/**
  * ice_sched_rm_vsi_cfg - remove the VSI and its children nodes
  * @pi: port information structure
  * @vsi_handle: software VSI handle
@@ -2038,7 +2173,6 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
 
 	ice_for_each_traffic_class(i) {
 		struct ice_sched_node *vsi_node, *tc_node;
-		u8 j = 0;
 
 		tc_node = ice_sched_get_tc_node(pi, i);
 		if (!tc_node)
@@ -2048,31 +2182,12 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
 		if (!vsi_node)
 			continue;
 
-		if (ice_sched_is_leaf_node_present(vsi_node)) {
-			ice_debug(pi->hw, ICE_DBG_SCHED, "VSI has leaf nodes in TC %d\n", i);
-			status = -EBUSY;
+		status = ice_sched_rm_vsi_subtree(pi, vsi_node, owner, i);
+		if (status)
 			goto exit_sched_rm_vsi_cfg;
-		}
-		while (j < vsi_node->num_children) {
-			if (vsi_node->children[j]->owner == owner) {
-				ice_free_sched_node(pi, vsi_node->children[j]);
 
-				/* reset the counter again since the num
-				 * children will be updated after node removal
-				 */
-				j = 0;
-			} else {
-				j++;
-			}
-		}
-		/* remove the VSI if it has no children */
-		if (!vsi_node->num_children) {
-			ice_free_sched_node(pi, vsi_node);
-			vsi_ctx->sched.vsi_node[i] = NULL;
+		vsi_ctx->sched.vsi_node[i] = NULL;
 
-			/* clean up aggregator related VSI info if any */
-			ice_sched_rm_agg_vsi_info(pi, vsi_handle);
-		}
 		if (owner == ICE_SCHED_NODE_OWNER_LAN)
 			vsi_ctx->sched.max_lanq[i] = 0;
 		else
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index b83f99c01d91..6b1126ddb561 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -9,7 +9,7 @@
 #include "ice_dcb_lib.h"
 #include "ice_flow.h"
 #include "ice_eswitch.h"
-#include "ice_virtchnl_allowlist.h"
+#include "virt/allowlist.h"
 #include "ice_flex_pipe.h"
 #include "ice_vf_vsi_vlan_ops.h"
 #include "ice_vlan.h"
@@ -36,6 +36,7 @@ static void ice_free_vf_entries(struct ice_pf *pf)
 
 	hash_for_each_safe(vfs->table, bkt, tmp, vf, entry) {
 		hash_del_rcu(&vf->entry);
+		ice_deinitialize_vf_entry(vf);
 		ice_put_vf(vf);
 	}
 }
@@ -62,6 +63,7 @@ static void ice_free_vf_res(struct ice_vf *vf)
 	if (vf->lan_vsi_idx != ICE_NO_VSI) {
 		ice_vf_vsi_release(vf);
 		vf->num_mac = 0;
+		vf->num_mac_lldp = 0;
 	}
 
 	last_vector_idx = vf->first_vector_idx + vf->num_msix - 1;
@@ -123,27 +125,6 @@ static void ice_dis_vf_mappings(struct ice_vf *vf)
 }
 
 /**
- * ice_sriov_free_msix_res - Reset/free any used MSIX resources
- * @pf: pointer to the PF structure
- *
- * Since no MSIX entries are taken from the pf->irq_tracker then just clear
- * the pf->sriov_base_vector.
- *
- * Returns 0 on success, and -EINVAL on error.
- */
-static int ice_sriov_free_msix_res(struct ice_pf *pf)
-{
-	if (!pf)
-		return -EINVAL;
-
-	bitmap_free(pf->sriov_irq_bm);
-	pf->sriov_irq_size = 0;
-	pf->sriov_base_vector = 0;
-
-	return 0;
-}
-
-/**
  * ice_free_vfs - Free all VFs
  * @pf: pointer to the PF structure
  */
@@ -177,6 +158,7 @@ void ice_free_vfs(struct ice_pf *pf)
 
 		ice_eswitch_detach_vf(pf, vf);
 		ice_dis_vf_qs(vf);
+		ice_virt_free_irqs(pf, vf->first_vector_idx, vf->num_msix);
 
 		if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
 			/* disable VF qp mappings and set VF disable state */
@@ -193,16 +175,9 @@ void ice_free_vfs(struct ice_pf *pf)
 			wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx));
 		}
 
-		/* clear malicious info since the VF is getting released */
-		if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
-			list_del(&vf->mbx_info.list_entry);
-
 		mutex_unlock(&vf->cfg_lock);
 	}
 
-	if (ice_sriov_free_msix_res(pf))
-		dev_err(dev, "Failed to free MSIX resources used by SR-IOV\n");
-
 	vfs->num_qps_per = 0;
 	ice_free_vf_entries(pf);
 
@@ -372,40 +347,6 @@ void ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector)
 }
 
 /**
- * ice_sriov_set_msix_res - Set any used MSIX resources
- * @pf: pointer to PF structure
- * @num_msix_needed: number of MSIX vectors needed for all SR-IOV VFs
- *
- * This function allows SR-IOV resources to be taken from the end of the PF's
- * allowed HW MSIX vectors so that the irq_tracker will not be affected. We
- * just set the pf->sriov_base_vector and return success.
- *
- * If there are not enough resources available, return an error. This should
- * always be caught by ice_set_per_vf_res().
- *
- * Return 0 on success, and -EINVAL when there are not enough MSIX vectors
- * in the PF's space available for SR-IOV.
- */
-static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed)
-{
-	u16 total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
-	int vectors_used = ice_get_max_used_msix_vector(pf);
-	int sriov_base_vector;
-
-	sriov_base_vector = total_vectors - num_msix_needed;
-
-	/* make sure we only grab irq_tracker entries from the list end and
-	 * that we have enough available MSIX vectors
-	 */
-	if (sriov_base_vector < vectors_used)
-		return -EINVAL;
-
-	pf->sriov_base_vector = sriov_base_vector;
-
-	return 0;
-}
-
-/**
  * ice_set_per_vf_res - check if vectors and queues are available
  * @pf: pointer to the PF structure
  * @num_vfs: the number of SR-IOV VFs being configured
@@ -429,11 +370,9 @@ static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed)
  */
 static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
 {
-	int vectors_used = ice_get_max_used_msix_vector(pf);
 	u16 num_msix_per_vf, num_txq, num_rxq, avail_qs;
 	int msix_avail_per_vf, msix_avail_for_sriov;
 	struct device *dev = ice_pf_to_dev(pf);
-	int err;
 
 	lockdep_assert_held(&pf->vfs.table_lock);
 
@@ -441,8 +380,7 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
 		return -EINVAL;
 
 	/* determine MSI-X resources per VF */
-	msix_avail_for_sriov = pf->hw.func_caps.common_cap.num_msix_vectors -
-		vectors_used;
+	msix_avail_for_sriov = pf->virt_irq_tracker.num_entries;
 	msix_avail_per_vf = msix_avail_for_sriov / num_vfs;
 	if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MED) {
 		num_msix_per_vf = ICE_NUM_VF_MSIX_MED;
@@ -481,13 +419,6 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
 		return -ENOSPC;
 	}
 
-	err = ice_sriov_set_msix_res(pf, num_msix_per_vf * num_vfs);
-	if (err) {
-		dev_err(dev, "Unable to set MSI-X resources for %d VFs, err %d\n",
-			num_vfs, err);
-		return err;
-	}
-
 	/* only allow equal Tx/Rx queue count (i.e. queue pairs) */
 	pf->vfs.num_qps_per = min_t(int, num_txq, num_rxq);
 	pf->vfs.num_msix_per = num_msix_per_vf;
@@ -498,52 +429,6 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
 }
 
 /**
- * ice_sriov_get_irqs - get irqs for SR-IOV usacase
- * @pf: pointer to PF structure
- * @needed: number of irqs to get
- *
- * This returns the first MSI-X vector index in PF space that is used by this
- * VF. This index is used when accessing PF relative registers such as
- * GLINT_VECT2FUNC and GLINT_DYN_CTL.
- * This will always be the OICR index in the AVF driver so any functionality
- * using vf->first_vector_idx for queue configuration_id: id of VF which will
- * use this irqs
- *
- * Only SRIOV specific vectors are tracked in sriov_irq_bm. SRIOV vectors are
- * allocated from the end of global irq index. First bit in sriov_irq_bm means
- * last irq index etc. It simplifies extension of SRIOV vectors.
- * They will be always located from sriov_base_vector to the last irq
- * index. While increasing/decreasing sriov_base_vector can be moved.
- */
-static int ice_sriov_get_irqs(struct ice_pf *pf, u16 needed)
-{
-	int res = bitmap_find_next_zero_area(pf->sriov_irq_bm,
-					     pf->sriov_irq_size, 0, needed, 0);
-	/* conversion from number in bitmap to global irq index */
-	int index = pf->sriov_irq_size - res - needed;
-
-	if (res >= pf->sriov_irq_size || index < pf->sriov_base_vector)
-		return -ENOENT;
-
-	bitmap_set(pf->sriov_irq_bm, res, needed);
-	return index;
-}
-
-/**
- * ice_sriov_free_irqs - free irqs used by the VF
- * @pf: pointer to PF structure
- * @vf: pointer to VF structure
- */
-static void ice_sriov_free_irqs(struct ice_pf *pf, struct ice_vf *vf)
-{
-	/* Move back from first vector index to first index in bitmap */
-	int bm_i = pf->sriov_irq_size - vf->first_vector_idx - vf->num_msix;
-
-	bitmap_clear(pf->sriov_irq_bm, bm_i, vf->num_msix);
-	vf->first_vector_idx = 0;
-}
-
-/**
  * ice_init_vf_vsi_res - initialize/setup VF VSI resources
  * @vf: VF to initialize/setup the VSI for
  *
@@ -556,7 +441,7 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf)
 	struct ice_vsi *vsi;
 	int err;
 
-	vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix);
+	vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix);
 	if (vf->first_vector_idx < 0)
 		return -ENOMEM;
 
@@ -856,16 +741,10 @@ err_free_entries:
  */
 static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs)
 {
-	int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 	int ret;
 
-	pf->sriov_irq_bm = bitmap_zalloc(total_vectors, GFP_KERNEL);
-	if (!pf->sriov_irq_bm)
-		return -ENOMEM;
-	pf->sriov_irq_size = total_vectors;
-
 	/* Disable global interrupt 0 so we don't try to handle the VFLR. */
 	wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index),
 	     ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S);
@@ -918,7 +797,6 @@ err_unroll_intr:
 	/* rearm interrupts here */
 	ice_irq_dynamic_ena(hw, NULL, NULL);
 	clear_bit(ICE_OICR_INTR_DIS, pf->state);
-	bitmap_free(pf->sriov_irq_bm);
 	return ret;
 }
 
@@ -992,16 +870,7 @@ u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev)
 {
 	struct ice_pf *pf = pci_get_drvdata(pdev);
 
-	return pf->sriov_irq_size - ice_get_max_used_msix_vector(pf);
-}
-
-static int ice_sriov_move_base_vector(struct ice_pf *pf, int move)
-{
-	if (pf->sriov_base_vector - move < ice_get_max_used_msix_vector(pf))
-		return -ENOMEM;
-
-	pf->sriov_base_vector -= move;
-	return 0;
+	return pf->virt_irq_tracker.num_entries;
 }
 
 static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id)
@@ -1020,7 +889,8 @@ static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id)
 			continue;
 
 		ice_dis_vf_mappings(tmp_vf);
-		ice_sriov_free_irqs(pf, tmp_vf);
+		ice_virt_free_irqs(pf, tmp_vf->first_vector_idx,
+				   tmp_vf->num_msix);
 
 		vf_ids[to_remap] = tmp_vf->vf_id;
 		to_remap += 1;
@@ -1032,7 +902,7 @@ static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id)
 			continue;
 
 		tmp_vf->first_vector_idx =
-			ice_sriov_get_irqs(pf, tmp_vf->num_msix);
+			ice_virt_get_irqs(pf, tmp_vf->num_msix);
 		/* there is no need to rebuild VSI as we are only changing the
 		 * vector indexes not amount of MSI-X or queues
 		 */
@@ -1063,7 +933,6 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 	bool needs_rebuild = false;
 	struct ice_vsi *vsi;
 	struct ice_vf *vf;
-	int id;
 
 	if (!ice_get_num_vfs(pf))
 		return -ENOENT;
@@ -1082,17 +951,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 	if (msix_vec_count < ICE_MIN_INTR_PER_VF)
 		return -EINVAL;
 
-	/* Transition of PCI VF function number to function_id */
-	for (id = 0; id < pci_num_vf(pdev); id++) {
-		if (vf_dev->devfn == pci_iov_virtfn_devfn(pdev, id))
-			break;
-	}
-
-	if (id == pci_num_vf(pdev))
-		return -ENOENT;
-
-	vf = ice_get_vf_by_id(pf, id);
-
+	vf = ice_get_vf_by_dev(pf, vf_dev);
 	if (!vf)
 		return -ENOENT;
 
@@ -1102,23 +961,24 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 		return -ENOENT;
 	}
 
-	prev_msix = vf->num_msix;
-	prev_queues = vf->num_vf_qs;
-
-	if (ice_sriov_move_base_vector(pf, msix_vec_count - prev_msix)) {
+	/* No need to rebuild if we're setting to the same value */
+	if (msix_vec_count == vf->num_msix) {
 		ice_put_vf(vf);
-		return -ENOSPC;
+		return 0;
 	}
 
+	prev_msix = vf->num_msix;
+	prev_queues = vf->num_vf_qs;
+
 	ice_dis_vf_mappings(vf);
-	ice_sriov_free_irqs(pf, vf);
+	ice_virt_free_irqs(pf, vf->first_vector_idx, vf->num_msix);
 
 	/* Remap all VFs beside the one is now configured */
 	ice_sriov_remap_vectors(pf, vf->vf_id);
 
 	vf->num_msix = msix_vec_count;
 	vf->num_vf_qs = queues;
-	vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix);
+	vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix);
 	if (vf->first_vector_idx < 0)
 		goto unroll;
 
@@ -1147,7 +1007,8 @@ unroll:
 
 	vf->num_msix = prev_msix;
 	vf->num_vf_qs = prev_queues;
-	vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix);
+
+	vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix);
 	if (vf->first_vector_idx < 0) {
 		ice_put_vf(vf);
 		return -EINVAL;
@@ -1300,10 +1161,12 @@ static u32 ice_globalq_to_pfq(struct ice_pf *pf, u32 globalq)
 void
 ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event)
 {
+	struct ice_aqc_event_lan_overflow *cmd;
 	u32 gldcb_rtctq, queue;
 	struct ice_vf *vf;
 
-	gldcb_rtctq = le32_to_cpu(event->desc.params.lan_overflow.prtdcb_ruptq);
+	cmd = libie_aq_raw(&event->desc);
+	gldcb_rtctq = le32_to_cpu(cmd->prtdcb_ruptq);
 	dev_dbg(ice_pf_to_dev(pf), "GLDCB_RTCTQ: 0x%08x\n", gldcb_rtctq);
 
 	/* event returns device global Rx queue number */
@@ -1327,8 +1190,7 @@ ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event)
  */
 int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_pf *pf = np->vsi->back;
+	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	struct ice_vsi *vf_vsi;
 	struct device *dev;
 	struct ice_vf *vf;
@@ -1537,6 +1399,9 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted)
 
 	mutex_lock(&vf->cfg_lock);
 
+	while (!trusted && vf->num_mac_lldp)
+		ice_vf_update_mac_lldp_num(vf, ice_get_vf_vsi(vf), false);
+
 	vf->trusted = trusted;
 	ice_reset_vf(vf, ICE_VF_RESET_NOTIFY);
 	dev_info(ice_pf_to_dev(pf), "VF %u is now %strusted\n",
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h
index 96549ca5c52c..6c4fad09a527 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.h
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.h
@@ -3,9 +3,9 @@
 
 #ifndef _ICE_SRIOV_H_
 #define _ICE_SRIOV_H_
-#include "ice_virtchnl_fdir.h"
+#include "virt/fdir.h"
 #include "ice_vf_lib.h"
-#include "ice_virtchnl.h"
+#include "virt/virtchnl.h"
 
 /* Static VF transaction/status register def */
 #define VF_DEVICE_STATUS		0xAA
@@ -64,6 +64,7 @@ bool
 ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto);
 u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev);
 int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count);
+int ice_vf_vsi_dis_single_txq(struct ice_vf *vf, struct ice_vsi *vsi, u16 q_id);
 #else /* CONFIG_PCI_IOV */
 static inline void ice_process_vflr_event(struct ice_pf *pf) { }
 static inline void ice_free_vfs(struct ice_pf *pf) { }
@@ -164,5 +165,11 @@ ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int ice_vf_vsi_dis_single_txq(struct ice_vf *vf,
+					    struct ice_vsi *vsi, u16 q_id)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_PCI_IOV */
 #endif /* _ICE_SRIOV_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 0e740342e294..84848f0123e7 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -1511,11 +1511,11 @@ ice_aq_get_sw_cfg(struct ice_hw *hw, struct ice_aqc_get_sw_cfg_resp_elem *buf,
 		  struct ice_sq_cd *cd)
 {
 	struct ice_aqc_get_sw_cfg *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_sw_cfg);
-	cmd = &desc.params.get_sw_conf;
+	cmd = libie_aq_raw(&desc);
 	cmd->element = cpu_to_le16(*req_desc);
 
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
@@ -1541,11 +1541,11 @@ ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
 {
 	struct ice_aqc_add_update_free_vsi_resp *res;
 	struct ice_aqc_add_get_update_free_vsi *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.vsi_cmd;
-	res = &desc.params.add_update_free_vsi_res;
+	cmd = libie_aq_raw(&desc);
+	res = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_vsi);
 
@@ -1556,7 +1556,7 @@ ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
 
 	cmd->vsi_flags = cpu_to_le16(vsi_ctx->flags);
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	status = ice_aq_send_cmd(hw, &desc, &vsi_ctx->info,
 				 sizeof(vsi_ctx->info), cd);
@@ -1585,11 +1585,11 @@ ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
 {
 	struct ice_aqc_add_update_free_vsi_resp *resp;
 	struct ice_aqc_add_get_update_free_vsi *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.vsi_cmd;
-	resp = &desc.params.add_update_free_vsi_res;
+	cmd = libie_aq_raw(&desc);
+	resp = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_free_vsi);
 
@@ -1620,17 +1620,17 @@ ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
 {
 	struct ice_aqc_add_update_free_vsi_resp *resp;
 	struct ice_aqc_add_get_update_free_vsi *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.vsi_cmd;
-	resp = &desc.params.add_update_free_vsi_res;
+	cmd = libie_aq_raw(&desc);
+	resp = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_vsi);
 
 	cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num | ICE_AQ_VSI_IS_VALID);
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	status = ice_aq_send_cmd(hw, &desc, &vsi_ctx->info,
 				 sizeof(vsi_ctx->info), cd);
@@ -1944,7 +1944,8 @@ int
 ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz,
 		u8 num_rules, enum ice_adminq_opc opc, struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct ice_aqc_sw_rules *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (opc != ice_aqc_opc_add_sw_rules &&
@@ -1953,13 +1954,13 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz,
 		return -EINVAL;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, opc);
+	cmd = libie_aq_raw(&desc);
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-	desc.params.sw_rules.num_rules_fltr_entry_index =
-		cpu_to_le16(num_rules);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
+	cmd->num_rules_fltr_entry_index = cpu_to_le16(num_rules);
 	status = ice_aq_send_cmd(hw, &desc, rule_list, rule_list_sz, cd);
 	if (opc != ice_aqc_opc_add_sw_rules &&
-	    hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT)
+	    hw->adminq.sq_last_status == LIBIE_AQ_RC_ENOENT)
 		status = -ENOENT;
 
 	if (!status) {
@@ -1989,14 +1990,14 @@ ice_aq_add_recipe(struct ice_hw *hw,
 		  u16 num_recipes, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_add_get_recipe *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 buf_size;
 
-	cmd = &desc.params.add_get_recipe;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_recipe);
 
 	cmd->num_sub_recipes = cpu_to_le16(num_recipes);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	buf_size = num_recipes * sizeof(*s_recipe_list);
 
@@ -2026,14 +2027,14 @@ ice_aq_get_recipe(struct ice_hw *hw,
 		  u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_add_get_recipe *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 buf_size;
 	int status;
 
 	if (*num_recipes != ICE_MAX_NUM_RECIPES)
 		return -EINVAL;
 
-	cmd = &desc.params.add_get_recipe;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_recipe);
 
 	cmd->return_index = cpu_to_le16(recipe_root);
@@ -2118,9 +2119,9 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 r_assoc,
 			     struct ice_sq_cd *cd)
 {
 	struct ice_aqc_recipe_to_profile *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.recipe_to_profile;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_recipe_to_profile);
 	cmd->profile_id = cpu_to_le16(profile_id);
 	/* Set the recipe ID bit in the bitmask to let the device know which
@@ -2144,10 +2145,10 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 *r_assoc,
 			     struct ice_sq_cd *cd)
 {
 	struct ice_aqc_recipe_to_profile *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.recipe_to_profile;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_recipe_to_profile);
 	cmd->profile_id = cpu_to_le16(profile_id);
 
@@ -3146,7 +3147,7 @@ ice_add_update_vsi_list(struct ice_hw *hw,
 		u16 vsi_handle_arr[2];
 
 		/* A rule already exists with the new VSI being added */
-		if (cur_fltr->fwd_id.hw_vsi_id == new_fltr->fwd_id.hw_vsi_id)
+		if (cur_fltr->vsi_handle == new_fltr->vsi_handle)
 			return -EEXIST;
 
 		vsi_handle_arr[0] = cur_fltr->vsi_handle;
@@ -4784,7 +4785,8 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts,
 			 */
 			if (found && recp[i].tun_type == rinfo->tun_type &&
 			    recp[i].need_pass_l2 == rinfo->need_pass_l2 &&
-			    recp[i].allow_pass_l2 == rinfo->allow_pass_l2)
+			    recp[i].allow_pass_l2 == rinfo->allow_pass_l2 &&
+			    recp[i].priority == rinfo->priority)
 				return i; /* Return the recipe ID */
 		}
 	}
@@ -5977,7 +5979,7 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw,
 
 		/* A rule already exists with the new VSI being added */
 		if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map))
-			return 0;
+			return -EEXIST;
 
 		/* Update the previously created VSI list set with
 		 * the new VSI ID passed in
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index ea39b999a0d0..fb9ea7f8ef44 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -12,14 +12,11 @@
 /**
  * ice_tc_count_lkups - determine lookup count for switch filter
  * @flags: TC-flower flags
- * @headers: Pointer to TC flower filter header structure
  * @fltr: Pointer to outer TC filter structure
  *
- * Determine lookup count based on TC flower input for switch filter.
+ * Return: lookup count based on TC flower input for a switch filter.
  */
-static int
-ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers,
-		   struct ice_tc_flower_fltr *fltr)
+static int ice_tc_count_lkups(u32 flags, struct ice_tc_flower_fltr *fltr)
 {
 	int lkups_cnt = 1; /* 0th lookup is metadata */
 
@@ -684,26 +681,26 @@ static int ice_tc_setup_action(struct net_device *filter_dev,
 	fltr->action.fltr_act = action;
 
 	if (ice_is_port_repr_netdev(filter_dev) &&
-	    ice_is_port_repr_netdev(target_dev)) {
+	    ice_is_port_repr_netdev(target_dev) &&
+	    fltr->direction == ICE_ESWITCH_FLTR_EGRESS) {
 		repr = ice_netdev_to_repr(target_dev);
 
 		fltr->dest_vsi = repr->src_vsi;
-		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
 	} else if (ice_is_port_repr_netdev(filter_dev) &&
-		   ice_tc_is_dev_uplink(target_dev)) {
+		   ice_tc_is_dev_uplink(target_dev) &&
+		   fltr->direction == ICE_ESWITCH_FLTR_EGRESS) {
 		repr = ice_netdev_to_repr(filter_dev);
 
 		fltr->dest_vsi = repr->src_vsi->back->eswitch.uplink_vsi;
-		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
 	} else if (ice_tc_is_dev_uplink(filter_dev) &&
-		   ice_is_port_repr_netdev(target_dev)) {
+		   ice_is_port_repr_netdev(target_dev) &&
+		   fltr->direction == ICE_ESWITCH_FLTR_INGRESS) {
 		repr = ice_netdev_to_repr(target_dev);
 
 		fltr->dest_vsi = repr->src_vsi;
-		fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
 	} else {
 		NL_SET_ERR_MSG_MOD(fltr->extack,
-				   "Unsupported netdevice in switchdev mode");
+				   "The action is not supported for this netdevice");
 		return -EINVAL;
 	}
 
@@ -716,13 +713,11 @@ ice_tc_setup_drop_action(struct net_device *filter_dev,
 {
 	fltr->action.fltr_act = ICE_DROP_PACKET;
 
-	if (ice_is_port_repr_netdev(filter_dev)) {
-		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
-	} else if (ice_tc_is_dev_uplink(filter_dev)) {
-		fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
-	} else {
+	if (!ice_tc_is_dev_uplink(filter_dev) &&
+	    !(ice_is_port_repr_netdev(filter_dev) &&
+	      fltr->direction == ICE_ESWITCH_FLTR_INGRESS)) {
 		NL_SET_ERR_MSG_MOD(fltr->extack,
-				   "Unsupported netdevice in switchdev mode");
+				   "The action is not supported for this netdevice");
 		return -EINVAL;
 	}
 
@@ -767,10 +762,157 @@ static int ice_eswitch_tc_parse_action(struct net_device *filter_dev,
 	return 0;
 }
 
+static bool ice_is_fltr_lldp(struct ice_tc_flower_fltr *fltr)
+{
+	return fltr->outer_headers.l2_key.n_proto == htons(ETH_P_LLDP);
+}
+
+static bool ice_is_fltr_pf_tx_lldp(struct ice_tc_flower_fltr *fltr)
+{
+	struct ice_vsi *vsi = fltr->src_vsi, *uplink;
+
+	if (!ice_is_switchdev_running(vsi->back))
+		return false;
+
+	uplink = vsi->back->eswitch.uplink_vsi;
+	return vsi == uplink && fltr->action.fltr_act == ICE_DROP_PACKET &&
+	       ice_is_fltr_lldp(fltr) &&
+	       fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
+	       fltr->flags == ICE_TC_FLWR_FIELD_ETH_TYPE_ID;
+}
+
+static bool ice_is_fltr_vf_tx_lldp(struct ice_tc_flower_fltr *fltr)
+{
+	struct ice_vsi *vsi = fltr->src_vsi, *uplink;
+
+	uplink = vsi->back->eswitch.uplink_vsi;
+	return fltr->src_vsi->type == ICE_VSI_VF && ice_is_fltr_lldp(fltr) &&
+	       fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
+	       fltr->dest_vsi == uplink;
+}
+
+static struct ice_tc_flower_fltr *
+ice_find_pf_tx_lldp_fltr(struct ice_pf *pf)
+{
+	struct ice_tc_flower_fltr *fltr;
+
+	hlist_for_each_entry(fltr, &pf->tc_flower_fltr_list, tc_flower_node)
+		if (ice_is_fltr_pf_tx_lldp(fltr))
+			return fltr;
+
+	return NULL;
+}
+
+static bool ice_any_vf_lldp_tx_ena(struct ice_pf *pf)
+{
+	struct ice_vf *vf;
+	unsigned int bkt;
+
+	ice_for_each_vf(pf, bkt, vf)
+		if (vf->lldp_tx_ena)
+			return true;
+
+	return false;
+}
+
+int ice_pass_vf_tx_lldp(struct ice_vsi *vsi, bool deinit)
+{
+	struct ice_rule_query_data remove_entry = {
+		.rid = vsi->vf->lldp_recipe_id,
+		.rule_id = vsi->vf->lldp_rule_id,
+		.vsi_handle = vsi->idx,
+	};
+	struct ice_pf *pf = vsi->back;
+	int err;
+
+	if (vsi->vf->lldp_tx_ena)
+		return 0;
+
+	if (!deinit && !ice_find_pf_tx_lldp_fltr(vsi->back))
+		return -EINVAL;
+
+	if (!deinit && ice_any_vf_lldp_tx_ena(pf))
+		return -EINVAL;
+
+	err = ice_rem_adv_rule_by_id(&pf->hw, &remove_entry);
+	if (!err)
+		vsi->vf->lldp_tx_ena = true;
+
+	return err;
+}
+
+int ice_drop_vf_tx_lldp(struct ice_vsi *vsi, bool init)
+{
+	struct ice_rule_query_data rule_added;
+	struct ice_adv_rule_info rinfo = {
+		.priority = 7,
+		.src_vsi = vsi->idx,
+		.sw_act = {
+			.src = vsi->idx,
+			.flag = ICE_FLTR_TX,
+			.fltr_act = ICE_DROP_PACKET,
+			.vsi_handle = vsi->idx,
+		},
+		.flags_info.act_valid = true,
+	};
+	struct ice_adv_lkup_elem list[3];
+	struct ice_pf *pf = vsi->back;
+	int err;
+
+	if (!init && !vsi->vf->lldp_tx_ena)
+		return 0;
+
+	memset(list, 0, sizeof(list));
+	ice_rule_add_direction_metadata(&list[0]);
+	ice_rule_add_src_vsi_metadata(&list[1]);
+	list[2].type = ICE_ETYPE_OL;
+	list[2].h_u.ethertype.ethtype_id = htons(ETH_P_LLDP);
+	list[2].m_u.ethertype.ethtype_id = htons(0xFFFF);
+
+	err = ice_add_adv_rule(&pf->hw, list, ARRAY_SIZE(list), &rinfo,
+			       &rule_added);
+	if (err) {
+		dev_err(&pf->pdev->dev,
+			"Failed to add an LLDP rule to VSI 0x%X: %d\n",
+			vsi->idx, err);
+	} else {
+		vsi->vf->lldp_recipe_id = rule_added.rid;
+		vsi->vf->lldp_rule_id = rule_added.rule_id;
+		vsi->vf->lldp_tx_ena = false;
+	}
+
+	return err;
+}
+
+static void ice_handle_add_pf_lldp_drop_rule(struct ice_vsi *vsi)
+{
+	struct ice_tc_flower_fltr *fltr;
+	struct ice_pf *pf = vsi->back;
+
+	hlist_for_each_entry(fltr, &pf->tc_flower_fltr_list, tc_flower_node) {
+		if (!ice_is_fltr_vf_tx_lldp(fltr))
+			continue;
+		ice_pass_vf_tx_lldp(fltr->src_vsi, true);
+		break;
+	}
+}
+
+static void ice_handle_del_pf_lldp_drop_rule(struct ice_pf *pf)
+{
+	int i;
+
+	/* Make the VF LLDP fwd to uplink rule dormant */
+	ice_for_each_vsi(pf, i) {
+		struct ice_vsi *vf_vsi = pf->vsi[i];
+
+		if (vf_vsi && vf_vsi->type == ICE_VSI_VF)
+			ice_drop_vf_tx_lldp(vf_vsi, false);
+	}
+}
+
 static int
 ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 {
-	struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers;
 	struct ice_adv_rule_info rule_info = { 0 };
 	struct ice_rule_query_data rule_added;
 	struct ice_hw *hw = &vsi->back->hw;
@@ -785,7 +927,10 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 		return -EOPNOTSUPP;
 	}
 
-	lkups_cnt = ice_tc_count_lkups(flags, headers, fltr);
+	if (ice_is_fltr_vf_tx_lldp(fltr))
+		return ice_pass_vf_tx_lldp(vsi, false);
+
+	lkups_cnt = ice_tc_count_lkups(flags, fltr);
 	list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC);
 	if (!list)
 		return -ENOMEM;
@@ -814,6 +959,11 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 		rule_info.sw_act.src = hw->pf_id;
 		rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE;
 	} else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
+		   !fltr->dest_vsi && vsi == vsi->back->eswitch.uplink_vsi) {
+		/* PF to Uplink */
+		rule_info.sw_act.flag |= ICE_FLTR_TX;
+		rule_info.sw_act.src = vsi->idx;
+	} else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
 		   fltr->dest_vsi == vsi->back->eswitch.uplink_vsi) {
 		/* VF to Uplink */
 		rule_info.sw_act.flag |= ICE_FLTR_TX;
@@ -846,11 +996,17 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 		NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because it already exist");
 		ret = -EINVAL;
 		goto exit;
+	} else if (ret == -ENOSPC) {
+		NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter: insufficient space available.");
+		goto exit;
 	} else if (ret) {
 		NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter due to error");
 		goto exit;
 	}
 
+	if (ice_is_fltr_pf_tx_lldp(fltr))
+		ice_handle_add_pf_lldp_drop_rule(vsi);
+
 	/* store the output params, which are needed later for removing
 	 * advanced switch filter
 	 */
@@ -985,7 +1141,6 @@ static int
 ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 			   struct ice_tc_flower_fltr *tc_fltr)
 {
-	struct ice_tc_flower_lyr_2_4_hdrs *headers = &tc_fltr->outer_headers;
 	struct ice_adv_rule_info rule_info = {0};
 	struct ice_rule_query_data rule_added;
 	struct ice_adv_lkup_elem *list;
@@ -1021,7 +1176,7 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 			return PTR_ERR(dest_vsi);
 	}
 
-	lkups_cnt = ice_tc_count_lkups(flags, headers, tc_fltr);
+	lkups_cnt = ice_tc_count_lkups(flags, tc_fltr);
 	list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC);
 	if (!list)
 		return -ENOMEM;
@@ -1056,8 +1211,13 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 			tc_fltr->action.fwd.q.hw_queue, lkups_cnt);
 		break;
 	case ICE_DROP_PACKET:
-		rule_info.sw_act.flag |= ICE_FLTR_RX;
-		rule_info.sw_act.src = hw->pf_id;
+		if (tc_fltr->direction == ICE_ESWITCH_FLTR_EGRESS) {
+			rule_info.sw_act.flag |= ICE_FLTR_TX;
+			rule_info.sw_act.src = vsi->idx;
+		} else {
+			rule_info.sw_act.flag |= ICE_FLTR_RX;
+			rule_info.sw_act.src = hw->pf_id;
+		}
 		rule_info.priority = ICE_SWITCH_FLTR_PRIO_VSI;
 		break;
 	default:
@@ -1071,6 +1231,10 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 				   "Unable to add filter because it already exist");
 		ret = -EINVAL;
 		goto exit;
+	} else if (ret == -ENOSPC) {
+		NL_SET_ERR_MSG_MOD(tc_fltr->extack,
+				   "Unable to add filter: insufficient space available.");
+		goto exit;
 	} else if (ret) {
 		NL_SET_ERR_MSG_MOD(tc_fltr->extack,
 				   "Unable to add filter due to error");
@@ -1463,11 +1627,16 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule,
  * @filter_dev: Pointer to device on which filter is being added
  * @f: Pointer to struct flow_cls_offload
  * @fltr: Pointer to filter structure
+ * @ingress: if the rule is added to an ingress block
+ *
+ * Return: 0 if the flower was parsed successfully, -EINVAL if the flower
+ *	   cannot be parsed, -EOPNOTSUPP if such filter cannot be configured
+ *	   for the given VSI.
  */
 static int
 ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 		     struct flow_cls_offload *f,
-		     struct ice_tc_flower_fltr *fltr)
+		     struct ice_tc_flower_fltr *fltr, bool ingress)
 {
 	struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers;
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
@@ -1551,6 +1720,20 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 			fltr->flags |= ICE_TC_FLWR_FIELD_ETH_TYPE_ID;
 		}
 
+		if (!ingress) {
+			bool switchdev =
+				ice_is_eswitch_mode_switchdev(vsi->back);
+
+			if (switchdev != (n_proto_key == ETH_P_LLDP)) {
+				NL_SET_ERR_MSG_FMT_MOD(fltr->extack,
+						       "%sLLDP filtering is not supported on egress in %s mode",
+						       switchdev ? "Non-" : "",
+						       switchdev ? "switchdev" :
+								   "legacy");
+				return -EOPNOTSUPP;
+			}
+		}
+
 		headers->l2_key.n_proto = cpu_to_be16(n_proto_key);
 		headers->l2_mask.n_proto = cpu_to_be16(n_proto_mask);
 		headers->l3_key.ip_proto = match.key->ip_proto;
@@ -1726,6 +1909,14 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 			return -EINVAL;
 		}
 	}
+
+	/* Ingress filter on representor results in an egress filter in HW
+	 * and vice versa
+	 */
+	ingress = ice_is_port_repr_netdev(filter_dev) ? !ingress : ingress;
+	fltr->direction = ingress ? ICE_ESWITCH_FLTR_INGRESS :
+				    ICE_ESWITCH_FLTR_EGRESS;
+
 	return 0;
 }
 
@@ -1939,6 +2130,12 @@ static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 	struct ice_pf *pf = vsi->back;
 	int err;
 
+	if (ice_is_fltr_pf_tx_lldp(fltr))
+		ice_handle_del_pf_lldp_drop_rule(pf);
+
+	if (ice_is_fltr_vf_tx_lldp(fltr))
+		return ice_drop_vf_tx_lldp(vsi, false);
+
 	rule_rem.rid = fltr->rid;
 	rule_rem.rule_id = fltr->rule_id;
 	rule_rem.vsi_handle = fltr->dest_vsi_handle;
@@ -1975,14 +2172,18 @@ static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
  * @vsi: Pointer to VSI
  * @f: Pointer to flower offload structure
  * @__fltr: Pointer to struct ice_tc_flower_fltr
+ * @ingress: if the rule is added to an ingress block
  *
  * This function parses TC-flower input fields, parses action,
  * and adds a filter.
+ *
+ * Return: 0 if the filter was successfully added,
+ *	   negative error code otherwise.
  */
 static int
 ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi,
 		struct flow_cls_offload *f,
-		struct ice_tc_flower_fltr **__fltr)
+		struct ice_tc_flower_fltr **__fltr, bool ingress)
 {
 	struct ice_tc_flower_fltr *fltr;
 	int err;
@@ -1999,7 +2200,7 @@ ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi,
 	fltr->src_vsi = vsi;
 	INIT_HLIST_NODE(&fltr->tc_flower_node);
 
-	err = ice_parse_cls_flower(netdev, vsi, f, fltr);
+	err = ice_parse_cls_flower(netdev, vsi, f, fltr, ingress);
 	if (err < 0)
 		goto err;
 
@@ -2042,10 +2243,13 @@ ice_find_tc_flower_fltr(struct ice_pf *pf, unsigned long cookie)
  * @netdev: Pointer to filter device
  * @vsi: Pointer to VSI
  * @cls_flower: Pointer to flower offload structure
+ * @ingress: if the rule is added to an ingress block
+ *
+ * Return: 0 if the flower was successfully added,
+ *	   negative error code otherwise.
  */
-int
-ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
-		   struct flow_cls_offload *cls_flower)
+int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
+		       struct flow_cls_offload *cls_flower, bool ingress)
 {
 	struct netlink_ext_ack *extack = cls_flower->common.extack;
 	struct net_device *vsi_netdev = vsi->netdev;
@@ -2080,7 +2284,7 @@ ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
 	}
 
 	/* prep and add TC-flower filter in HW */
-	err = ice_add_tc_fltr(netdev, vsi, cls_flower, &fltr);
+	err = ice_add_tc_fltr(netdev, vsi, cls_flower, &fltr, ingress);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
index d84f153517ec..8a3ab2f22af9 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
@@ -211,13 +211,14 @@ static inline int ice_chnl_dmac_fltr_cnt(struct ice_pf *pf)
 }
 
 struct ice_vsi *ice_locate_vsi_using_queue(struct ice_vsi *vsi, int queue);
-int
-ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
-		   struct flow_cls_offload *cls_flower);
-int
-ice_del_cls_flower(struct ice_vsi *vsi, struct flow_cls_offload *cls_flower);
+int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
+		       struct flow_cls_offload *cls_flower, bool ingress);
+int ice_del_cls_flower(struct ice_vsi *vsi,
+		       struct flow_cls_offload *cls_flower);
 void ice_replay_tc_fltrs(struct ice_pf *pf);
 bool ice_is_tunnel_supported(struct net_device *dev);
+int ice_drop_vf_tx_lldp(struct ice_vsi *vsi, bool init);
+int ice_pass_vf_tx_lldp(struct ice_vsi *vsi, bool deinit);
 
 static inline bool ice_is_forward_action(enum ice_sw_fwd_act_type fltr_act)
 {
diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h
index 07aab6e130cd..4f35ef8d6b29 100644
--- a/drivers/net/ethernet/intel/ice/ice_trace.h
+++ b/drivers/net/ethernet/intel/ice/ice_trace.h
@@ -130,7 +130,7 @@ DECLARE_EVENT_CLASS(ice_tx_template,
 				   __entry->buf = buf;
 				   __assign_str(devname);),
 
-		    TP_printk("netdev: %s ring: %pK desc: %pK buf %pK", __get_str(devname),
+		    TP_printk("netdev: %s ring: %p desc: %p buf %p", __get_str(devname),
 			      __entry->ring, __entry->desc, __entry->buf)
 );
 
@@ -158,7 +158,7 @@ DECLARE_EVENT_CLASS(ice_rx_template,
 				   __entry->desc = desc;
 				   __assign_str(devname);),
 
-		    TP_printk("netdev: %s ring: %pK desc: %pK", __get_str(devname),
+		    TP_printk("netdev: %s ring: %p desc: %p", __get_str(devname),
 			      __entry->ring, __entry->desc)
 );
 DEFINE_EVENT(ice_rx_template, ice_clean_rx_irq,
@@ -182,7 +182,7 @@ DECLARE_EVENT_CLASS(ice_rx_indicate_template,
 				   __entry->skb = skb;
 				   __assign_str(devname);),
 
-		    TP_printk("netdev: %s ring: %pK desc: %pK skb %pK", __get_str(devname),
+		    TP_printk("netdev: %s ring: %p desc: %p skb %p", __get_str(devname),
 			      __entry->ring, __entry->desc, __entry->skb)
 );
 
@@ -205,7 +205,7 @@ DECLARE_EVENT_CLASS(ice_xmit_template,
 				   __entry->skb = skb;
 				   __assign_str(devname);),
 
-		    TP_printk("netdev: %s skb: %pK ring: %pK", __get_str(devname),
+		    TP_printk("netdev: %s skb: %p ring: %p", __get_str(devname),
 			      __entry->skb, __entry->ring)
 );
 
@@ -228,7 +228,7 @@ DECLARE_EVENT_CLASS(ice_tx_tstamp_template,
 		    TP_fast_assign(__entry->skb = skb;
 				   __entry->idx = idx;),
 
-		    TP_printk("skb %pK idx %d",
+		    TP_printk("skb %p idx %d",
 			      __entry->skb, __entry->idx)
 );
 #define DEFINE_TX_TSTAMP_OP_EVENT(name) \
diff --git a/drivers/net/ethernet/intel/ice/ice_tspll.c b/drivers/net/ethernet/intel/ice/ice_tspll.c
new file mode 100644
index 000000000000..66320a4ab86f
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_tspll.c
@@ -0,0 +1,626 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025, Intel Corporation. */
+
+#include "ice.h"
+#include "ice_lib.h"
+#include "ice_ptp_hw.h"
+
+static const struct
+ice_tspll_params_e82x e82x_tspll_params[NUM_ICE_TSPLL_FREQ] = {
+	[ICE_TSPLL_FREQ_25_000] = {
+		.refclk_pre_div = 1,
+		.post_pll_div = 6,
+		.feedback_div = 197,
+		.frac_n_div = 2621440,
+	},
+	[ICE_TSPLL_FREQ_122_880] = {
+		.refclk_pre_div = 5,
+		.post_pll_div = 7,
+		.feedback_div = 223,
+		.frac_n_div = 524288
+	},
+	[ICE_TSPLL_FREQ_125_000] = {
+		.refclk_pre_div = 5,
+		.post_pll_div = 7,
+		.feedback_div = 223,
+		.frac_n_div = 524288
+	},
+	[ICE_TSPLL_FREQ_153_600] = {
+		.refclk_pre_div = 5,
+		.post_pll_div = 6,
+		.feedback_div = 159,
+		.frac_n_div = 1572864
+	},
+	[ICE_TSPLL_FREQ_156_250] = {
+		.refclk_pre_div = 5,
+		.post_pll_div = 6,
+		.feedback_div = 159,
+		.frac_n_div = 1572864
+	},
+	[ICE_TSPLL_FREQ_245_760] = {
+		.refclk_pre_div = 10,
+		.post_pll_div = 7,
+		.feedback_div = 223,
+		.frac_n_div = 524288
+	},
+};
+
+/**
+ * ice_tspll_clk_freq_str - Convert time_ref_freq to string
+ * @clk_freq: Clock frequency
+ *
+ * Return: specified TIME_REF clock frequency converted to a string.
+ */
+static const char *ice_tspll_clk_freq_str(enum ice_tspll_freq clk_freq)
+{
+	switch (clk_freq) {
+	case ICE_TSPLL_FREQ_25_000:
+		return "25 MHz";
+	case ICE_TSPLL_FREQ_122_880:
+		return "122.88 MHz";
+	case ICE_TSPLL_FREQ_125_000:
+		return "125 MHz";
+	case ICE_TSPLL_FREQ_153_600:
+		return "153.6 MHz";
+	case ICE_TSPLL_FREQ_156_250:
+		return "156.25 MHz";
+	case ICE_TSPLL_FREQ_245_760:
+		return "245.76 MHz";
+	default:
+		return "Unknown";
+	}
+}
+
+/**
+ * ice_tspll_default_freq - Return default frequency for a MAC type
+ * @mac_type: MAC type
+ *
+ * Return: default TSPLL frequency for a correct MAC type, -ERANGE otherwise.
+ */
+static enum ice_tspll_freq ice_tspll_default_freq(enum ice_mac_type mac_type)
+{
+	switch (mac_type) {
+	case ICE_MAC_GENERIC:
+		return ICE_TSPLL_FREQ_25_000;
+	case ICE_MAC_GENERIC_3K_E825:
+		return ICE_TSPLL_FREQ_156_250;
+	default:
+		return -ERANGE;
+	}
+}
+
+/**
+ * ice_tspll_check_params - Check if TSPLL params are correct
+ * @hw: Pointer to the HW struct
+ * @clk_freq: Clock frequency to program
+ * @clk_src: Clock source to select (TIME_REF or TCXO)
+ *
+ * Return: true if TSPLL params are correct, false otherwise.
+ */
+static bool ice_tspll_check_params(struct ice_hw *hw,
+				   enum ice_tspll_freq clk_freq,
+				   enum ice_clk_src clk_src)
+{
+	if (clk_freq >= NUM_ICE_TSPLL_FREQ) {
+		dev_warn(ice_hw_to_dev(hw), "Invalid TSPLL frequency %u\n",
+			 clk_freq);
+		return false;
+	}
+
+	if (clk_src >= NUM_ICE_CLK_SRC) {
+		dev_warn(ice_hw_to_dev(hw), "Invalid clock source %u\n",
+			 clk_src);
+		return false;
+	}
+
+	if ((hw->mac_type == ICE_MAC_GENERIC_3K_E825 ||
+	     clk_src == ICE_CLK_SRC_TCXO) &&
+	    clk_freq != ice_tspll_default_freq(hw->mac_type)) {
+		dev_warn(ice_hw_to_dev(hw), "Unsupported frequency for this clock source\n");
+		return false;
+	}
+
+	return true;
+}
+
+/**
+ * ice_tspll_clk_src_str - Convert time_ref_src to string
+ * @clk_src: Clock source
+ *
+ * Return: specified clock source converted to its string name
+ */
+static const char *ice_tspll_clk_src_str(enum ice_clk_src clk_src)
+{
+	switch (clk_src) {
+	case ICE_CLK_SRC_TCXO:
+		return "TCXO";
+	case ICE_CLK_SRC_TIME_REF:
+		return "TIME_REF";
+	default:
+		return "Unknown";
+	}
+}
+
+/**
+ * ice_tspll_log_cfg - Log current/new TSPLL configuration
+ * @hw: Pointer to the HW struct
+ * @enable: CGU enabled/disabled
+ * @clk_src: Current clock source
+ * @tspll_freq: Current clock frequency
+ * @lock: CGU lock status
+ * @new_cfg: true if this is a new config
+ */
+static void ice_tspll_log_cfg(struct ice_hw *hw, bool enable, u8 clk_src,
+			      u8 tspll_freq, bool lock, bool new_cfg)
+{
+	dev_dbg(ice_hw_to_dev(hw),
+		"%s TSPLL configuration -- %s, src %s, freq %s, PLL %s\n",
+		new_cfg ? "New" : "Current", str_enabled_disabled(enable),
+		ice_tspll_clk_src_str((enum ice_clk_src)clk_src),
+		ice_tspll_clk_freq_str((enum ice_tspll_freq)tspll_freq),
+		lock ? "locked" : "unlocked");
+}
+
+/**
+ * ice_tspll_cfg_e82x - Configure the Clock Generation Unit TSPLL
+ * @hw: Pointer to the HW struct
+ * @clk_freq: Clock frequency to program
+ * @clk_src: Clock source to select (TIME_REF, or TCXO)
+ *
+ * Configure the Clock Generation Unit with the desired clock frequency and
+ * time reference, enabling the PLL which drives the PTP hardware clock.
+ *
+ * Return:
+ * * %0       - success
+ * * %-EINVAL - input parameters are incorrect
+ * * %-EBUSY  - failed to lock TSPLL
+ * * %other   - CGU read/write failure
+ */
+static int ice_tspll_cfg_e82x(struct ice_hw *hw, enum ice_tspll_freq clk_freq,
+			      enum ice_clk_src clk_src)
+{
+	u32 val, r9, r24;
+	int err;
+
+	err = ice_read_cgu_reg(hw, ICE_CGU_R9, &r9);
+	if (err)
+		return err;
+
+	err = ice_read_cgu_reg(hw, ICE_CGU_R24, &r24);
+	if (err)
+		return err;
+
+	err = ice_read_cgu_reg(hw, ICE_CGU_RO_BWM_LF, &val);
+	if (err)
+		return err;
+
+	ice_tspll_log_cfg(hw, !!FIELD_GET(ICE_CGU_R23_R24_TSPLL_ENABLE, r24),
+			  FIELD_GET(ICE_CGU_R23_R24_TIME_REF_SEL, r24),
+			  FIELD_GET(ICE_CGU_R9_TIME_REF_FREQ_SEL, r9),
+			  !!FIELD_GET(ICE_CGU_RO_BWM_LF_TRUE_LOCK, val),
+			  false);
+
+	/* Disable the PLL before changing the clock source or frequency */
+	if (FIELD_GET(ICE_CGU_R23_R24_TSPLL_ENABLE, r24)) {
+		r24 &= ~ICE_CGU_R23_R24_TSPLL_ENABLE;
+
+		err = ice_write_cgu_reg(hw, ICE_CGU_R24, r24);
+		if (err)
+			return err;
+	}
+
+	/* Set the frequency */
+	r9 &= ~ICE_CGU_R9_TIME_REF_FREQ_SEL;
+	r9 |= FIELD_PREP(ICE_CGU_R9_TIME_REF_FREQ_SEL, clk_freq);
+	err = ice_write_cgu_reg(hw, ICE_CGU_R9, r9);
+	if (err)
+		return err;
+
+	/* Configure the TSPLL feedback divisor */
+	err = ice_read_cgu_reg(hw, ICE_CGU_R19, &val);
+	if (err)
+		return err;
+
+	val &= ~(ICE_CGU_R19_TSPLL_FBDIV_INTGR_E82X | ICE_CGU_R19_TSPLL_NDIVRATIO);
+	val |= FIELD_PREP(ICE_CGU_R19_TSPLL_FBDIV_INTGR_E82X,
+			  e82x_tspll_params[clk_freq].feedback_div);
+	val |= FIELD_PREP(ICE_CGU_R19_TSPLL_NDIVRATIO, 1);
+
+	err = ice_write_cgu_reg(hw, ICE_CGU_R19, val);
+	if (err)
+		return err;
+
+	/* Configure the TSPLL post divisor */
+	err = ice_read_cgu_reg(hw, ICE_CGU_R22, &val);
+	if (err)
+		return err;
+
+	val &= ~(ICE_CGU_R22_TIME1588CLK_DIV |
+		 ICE_CGU_R22_TIME1588CLK_DIV2);
+	val |= FIELD_PREP(ICE_CGU_R22_TIME1588CLK_DIV,
+			  e82x_tspll_params[clk_freq].post_pll_div);
+
+	err = ice_write_cgu_reg(hw, ICE_CGU_R22, val);
+	if (err)
+		return err;
+
+	/* Configure the TSPLL pre divisor and clock source */
+	err = ice_read_cgu_reg(hw, ICE_CGU_R24, &r24);
+	if (err)
+		return err;
+
+	r24 &= ~(ICE_CGU_R23_R24_REF1588_CK_DIV | ICE_CGU_R24_FBDIV_FRAC |
+		 ICE_CGU_R23_R24_TIME_REF_SEL);
+	r24 |= FIELD_PREP(ICE_CGU_R23_R24_REF1588_CK_DIV,
+			  e82x_tspll_params[clk_freq].refclk_pre_div);
+	r24 |= FIELD_PREP(ICE_CGU_R24_FBDIV_FRAC,
+			  e82x_tspll_params[clk_freq].frac_n_div);
+	r24 |= FIELD_PREP(ICE_CGU_R23_R24_TIME_REF_SEL, clk_src);
+
+	err = ice_write_cgu_reg(hw, ICE_CGU_R24, r24);
+	if (err)
+		return err;
+
+	/* Wait to ensure everything is stable */
+	usleep_range(10, 20);
+
+	/* Finally, enable the PLL */
+	r24 |= ICE_CGU_R23_R24_TSPLL_ENABLE;
+
+	err = ice_write_cgu_reg(hw, ICE_CGU_R24, r24);
+	if (err)
+		return err;
+
+	/* Wait at least 1 ms to verify if the PLL locks */
+	usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC);
+
+	err = ice_read_cgu_reg(hw, ICE_CGU_RO_BWM_LF, &val);
+	if (err)
+		return err;
+
+	if (!(val & ICE_CGU_RO_BWM_LF_TRUE_LOCK)) {
+		dev_warn(ice_hw_to_dev(hw), "CGU PLL failed to lock\n");
+		return -EBUSY;
+	}
+
+	err = ice_read_cgu_reg(hw, ICE_CGU_R9, &r9);
+	if (err)
+		return err;
+	err = ice_read_cgu_reg(hw, ICE_CGU_R24, &r24);
+	if (err)
+		return err;
+
+	ice_tspll_log_cfg(hw, !!FIELD_GET(ICE_CGU_R23_R24_TSPLL_ENABLE, r24),
+			  FIELD_GET(ICE_CGU_R23_R24_TIME_REF_SEL, r24),
+			  FIELD_GET(ICE_CGU_R9_TIME_REF_FREQ_SEL, r9),
+			  true, true);
+
+	return 0;
+}
+
+/**
+ * ice_tspll_dis_sticky_bits_e82x - disable TSPLL sticky bits
+ * @hw: Pointer to the HW struct
+ *
+ * Configure the Clock Generation Unit TSPLL sticky bits so they don't latch on
+ * losing TSPLL lock, but always show current state.
+ *
+ * Return: 0 on success, other error codes when failed to read/write CGU.
+ */
+static int ice_tspll_dis_sticky_bits_e82x(struct ice_hw *hw)
+{
+	u32 val;
+	int err;
+
+	err = ice_read_cgu_reg(hw, ICE_CGU_CNTR_BIST, &val);
+	if (err)
+		return err;
+
+	val &= ~(ICE_CGU_CNTR_BIST_PLLLOCK_SEL_0 |
+		 ICE_CGU_CNTR_BIST_PLLLOCK_SEL_1);
+
+	return ice_write_cgu_reg(hw, ICE_CGU_CNTR_BIST, val);
+}
+
+/**
+ * ice_tspll_cfg_e825c - Configure the TSPLL for E825-C
+ * @hw: Pointer to the HW struct
+ * @clk_freq: Clock frequency to program
+ * @clk_src: Clock source to select (TIME_REF, or TCXO)
+ *
+ * Configure the Clock Generation Unit with the desired clock frequency and
+ * time reference, enabling the PLL which drives the PTP hardware clock.
+ *
+ * Return:
+ * * %0       - success
+ * * %-EINVAL - input parameters are incorrect
+ * * %-EBUSY  - failed to lock TSPLL
+ * * %other   - CGU read/write failure
+ */
+static int ice_tspll_cfg_e825c(struct ice_hw *hw, enum ice_tspll_freq clk_freq,
+			       enum ice_clk_src clk_src)
+{
+	u32 val, r9, r23;
+	int err;
+
+	err = ice_read_cgu_reg(hw, ICE_CGU_R9, &r9);
+	if (err)
+		return err;
+
+	err = ice_read_cgu_reg(hw, ICE_CGU_R23, &r23);
+	if (err)
+		return err;
+
+	err = ice_read_cgu_reg(hw, ICE_CGU_RO_LOCK, &val);
+	if (err)
+		return err;
+
+	ice_tspll_log_cfg(hw, !!FIELD_GET(ICE_CGU_R23_R24_TSPLL_ENABLE, r23),
+			  FIELD_GET(ICE_CGU_R23_R24_TIME_REF_SEL, r23),
+			  FIELD_GET(ICE_CGU_R9_TIME_REF_FREQ_SEL, r9),
+			  !!FIELD_GET(ICE_CGU_RO_LOCK_TRUE_LOCK, val),
+			  false);
+
+	/* Disable the PLL before changing the clock source or frequency */
+	if (FIELD_GET(ICE_CGU_R23_R24_TSPLL_ENABLE, r23)) {
+		r23 &= ~ICE_CGU_R23_R24_TSPLL_ENABLE;
+
+		err = ice_write_cgu_reg(hw, ICE_CGU_R23, r23);
+		if (err)
+			return err;
+	}
+
+	if (FIELD_GET(ICE_CGU_R9_TIME_SYNC_EN, r9)) {
+		r9 &= ~ICE_CGU_R9_TIME_SYNC_EN;
+
+		err = ice_write_cgu_reg(hw, ICE_CGU_R9, r9);
+		if (err)
+			return err;
+	}
+
+	/* Set the frequency and enable the correct receiver */
+	r9 &= ~(ICE_CGU_R9_TIME_REF_FREQ_SEL | ICE_CGU_R9_CLK_EREF0_EN |
+		ICE_CGU_R9_TIME_REF_EN);
+	r9 |= FIELD_PREP(ICE_CGU_R9_TIME_REF_FREQ_SEL, clk_freq);
+	if (clk_src == ICE_CLK_SRC_TCXO)
+		r9 |= ICE_CGU_R9_CLK_EREF0_EN;
+	else
+		r9 |= ICE_CGU_R9_TIME_REF_EN;
+	r9 |= ICE_CGU_R9_TIME_SYNC_EN;
+	err = ice_write_cgu_reg(hw, ICE_CGU_R9, r9);
+	if (err)
+		return err;
+
+	/* Choose the referenced frequency */
+	err = ice_read_cgu_reg(hw, ICE_CGU_R16, &val);
+	if (err)
+		return err;
+	val &= ~ICE_CGU_R16_TSPLL_CK_REFCLKFREQ;
+	val |= FIELD_PREP(ICE_CGU_R16_TSPLL_CK_REFCLKFREQ,
+			  ICE_TSPLL_CK_REFCLKFREQ_E825);
+	err = ice_write_cgu_reg(hw, ICE_CGU_R16, val);
+	if (err)
+		return err;
+
+	/* Configure the TSPLL feedback divisor */
+	err = ice_read_cgu_reg(hw, ICE_CGU_R19, &val);
+	if (err)
+		return err;
+
+	val &= ~(ICE_CGU_R19_TSPLL_FBDIV_INTGR_E825 |
+		 ICE_CGU_R19_TSPLL_NDIVRATIO);
+	val |= FIELD_PREP(ICE_CGU_R19_TSPLL_FBDIV_INTGR_E825,
+			  ICE_TSPLL_FBDIV_INTGR_E825);
+	val |= FIELD_PREP(ICE_CGU_R19_TSPLL_NDIVRATIO,
+			  ICE_TSPLL_NDIVRATIO_E825);
+
+	err = ice_write_cgu_reg(hw, ICE_CGU_R19, val);
+	if (err)
+		return err;
+
+	/* Configure the TSPLL post divisor, these two are constant */
+	err = ice_read_cgu_reg(hw, ICE_CGU_R22, &val);
+	if (err)
+		return err;
+
+	val &= ~(ICE_CGU_R22_TIME1588CLK_DIV |
+		 ICE_CGU_R22_TIME1588CLK_DIV2);
+	val |= FIELD_PREP(ICE_CGU_R22_TIME1588CLK_DIV, 5);
+
+	err = ice_write_cgu_reg(hw, ICE_CGU_R22, val);
+	if (err)
+		return err;
+
+	/* Configure the TSPLL pre divisor (constant) and clock source */
+	err = ice_read_cgu_reg(hw, ICE_CGU_R23, &r23);
+	if (err)
+		return err;
+
+	r23 &= ~(ICE_CGU_R23_R24_REF1588_CK_DIV | ICE_CGU_R23_R24_TIME_REF_SEL);
+	r23 |= FIELD_PREP(ICE_CGU_R23_R24_TIME_REF_SEL, clk_src);
+
+	err = ice_write_cgu_reg(hw, ICE_CGU_R23, r23);
+	if (err)
+		return err;
+
+	/* Clear the R24 register. */
+	err = ice_write_cgu_reg(hw, ICE_CGU_R24, 0);
+	if (err)
+		return err;
+
+	/* Wait to ensure everything is stable */
+	usleep_range(10, 20);
+
+	/* Finally, enable the PLL */
+	r23 |= ICE_CGU_R23_R24_TSPLL_ENABLE;
+
+	err = ice_write_cgu_reg(hw, ICE_CGU_R23, r23);
+	if (err)
+		return err;
+
+	/* Wait at least 1 ms to verify if the PLL locks */
+	usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC);
+
+	err = ice_read_cgu_reg(hw, ICE_CGU_RO_LOCK, &val);
+	if (err)
+		return err;
+
+	if (!(val & ICE_CGU_RO_LOCK_TRUE_LOCK)) {
+		dev_warn(ice_hw_to_dev(hw), "CGU PLL failed to lock\n");
+		return -EBUSY;
+	}
+
+	err = ice_read_cgu_reg(hw, ICE_CGU_R9, &r9);
+	if (err)
+		return err;
+	err = ice_read_cgu_reg(hw, ICE_CGU_R23, &r23);
+	if (err)
+		return err;
+
+	ice_tspll_log_cfg(hw, !!FIELD_GET(ICE_CGU_R23_R24_TSPLL_ENABLE, r23),
+			  FIELD_GET(ICE_CGU_R23_R24_TIME_REF_SEL, r23),
+			  FIELD_GET(ICE_CGU_R9_TIME_REF_FREQ_SEL, r9),
+			  true, true);
+
+	return 0;
+}
+
+/**
+ * ice_tspll_dis_sticky_bits_e825c - disable TSPLL sticky bits for E825-C
+ * @hw: Pointer to the HW struct
+ *
+ * Configure the Clock Generation Unit TSPLL sticky bits so they don't latch on
+ * losing TSPLL lock, but always show current state.
+ *
+ * Return: 0 on success, other error codes when failed to read/write CGU.
+ */
+static int ice_tspll_dis_sticky_bits_e825c(struct ice_hw *hw)
+{
+	u32 val;
+	int err;
+
+	err = ice_read_cgu_reg(hw, ICE_CGU_BW_TDC, &val);
+	if (err)
+		return err;
+
+	val &= ~ICE_CGU_BW_TDC_PLLLOCK_SEL;
+
+	return ice_write_cgu_reg(hw, ICE_CGU_BW_TDC, val);
+}
+
+/**
+ * ice_tspll_cfg_pps_out_e825c - Enable/disable 1PPS output and set amplitude
+ * @hw: pointer to the HW struct
+ * @enable: true to enable 1PPS output, false to disable it
+ *
+ * Return: 0 on success, other negative error code when CGU read/write failed.
+ */
+int ice_tspll_cfg_pps_out_e825c(struct ice_hw *hw, bool enable)
+{
+	u32 val;
+	int err;
+
+	err = ice_read_cgu_reg(hw, ICE_CGU_R9, &val);
+	if (err)
+		return err;
+
+	val &= ~(ICE_CGU_R9_ONE_PPS_OUT_EN | ICE_CGU_R9_ONE_PPS_OUT_AMP);
+	val |= FIELD_PREP(ICE_CGU_R9_ONE_PPS_OUT_EN, enable) |
+	       ICE_CGU_R9_ONE_PPS_OUT_AMP;
+
+	return ice_write_cgu_reg(hw, ICE_CGU_R9, val);
+}
+
+/**
+ * ice_tspll_cfg - Configure the Clock Generation Unit TSPLL
+ * @hw: Pointer to the HW struct
+ * @clk_freq: Clock frequency to program
+ * @clk_src: Clock source to select (TIME_REF, or TCXO)
+ *
+ * Configure the Clock Generation Unit with the desired clock frequency and
+ * time reference, enabling the TSPLL which drives the PTP hardware clock.
+ *
+ * Return: 0 on success, -ERANGE on unsupported MAC type, other negative error
+ *         codes when failed to configure CGU.
+ */
+static int ice_tspll_cfg(struct ice_hw *hw, enum ice_tspll_freq clk_freq,
+			 enum ice_clk_src clk_src)
+{
+	switch (hw->mac_type) {
+	case ICE_MAC_GENERIC:
+		return ice_tspll_cfg_e82x(hw, clk_freq, clk_src);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_tspll_cfg_e825c(hw, clk_freq, clk_src);
+	default:
+		return -ERANGE;
+	}
+}
+
+/**
+ * ice_tspll_dis_sticky_bits - disable TSPLL sticky bits
+ * @hw: Pointer to the HW struct
+ *
+ * Configure the Clock Generation Unit TSPLL sticky bits so they don't latch on
+ * losing TSPLL lock, but always show current state.
+ *
+ * Return: 0 on success, -ERANGE on unsupported MAC type.
+ */
+static int ice_tspll_dis_sticky_bits(struct ice_hw *hw)
+{
+	switch (hw->mac_type) {
+	case ICE_MAC_GENERIC:
+		return ice_tspll_dis_sticky_bits_e82x(hw);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_tspll_dis_sticky_bits_e825c(hw);
+	default:
+		return -ERANGE;
+	}
+}
+
+/**
+ * ice_tspll_init - Initialize TSPLL with settings from firmware
+ * @hw: Pointer to the HW structure
+ *
+ * Initialize the Clock Generation Unit of the E82X/E825 device.
+ *
+ * Return: 0 on success, other error codes when failed to read/write/cfg CGU.
+ */
+int ice_tspll_init(struct ice_hw *hw)
+{
+	struct ice_ts_func_info *ts_info = &hw->func_caps.ts_func_info;
+	enum ice_tspll_freq tspll_freq;
+	enum ice_clk_src clk_src;
+	int err;
+
+	/* Only E822, E823 and E825 products support TSPLL */
+	if (hw->mac_type != ICE_MAC_GENERIC &&
+	    hw->mac_type != ICE_MAC_GENERIC_3K_E825)
+		return 0;
+
+	tspll_freq = (enum ice_tspll_freq)ts_info->time_ref;
+	clk_src = (enum ice_clk_src)ts_info->clk_src;
+	if (!ice_tspll_check_params(hw, tspll_freq, clk_src))
+		return -EINVAL;
+
+	/* Disable sticky lock detection so lock status reported is accurate */
+	err = ice_tspll_dis_sticky_bits(hw);
+	if (err)
+		return err;
+
+	/* Configure the TSPLL using the parameters from the function
+	 * capabilities.
+	 */
+	err = ice_tspll_cfg(hw, tspll_freq, clk_src);
+	if (err) {
+		dev_warn(ice_hw_to_dev(hw), "Failed to lock TSPLL to predefined frequency. Retrying with fallback frequency.\n");
+
+		/* Try to lock to internal TCXO as a fallback. */
+		tspll_freq = ice_tspll_default_freq(hw->mac_type);
+		clk_src = ICE_CLK_SRC_TCXO;
+		err = ice_tspll_cfg(hw, tspll_freq, clk_src);
+		if (err)
+			dev_warn(ice_hw_to_dev(hw), "Failed to lock TSPLL to fallback frequency.\n");
+	}
+
+	return err;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_tspll.h b/drivers/net/ethernet/intel/ice/ice_tspll.h
new file mode 100644
index 000000000000..c0b1232cc07c
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_tspll.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025, Intel Corporation. */
+
+#ifndef _ICE_TSPLL_H_
+#define _ICE_TSPLL_H_
+
+/**
+ * struct ice_tspll_params_e82x - E82X TSPLL parameters
+ * @refclk_pre_div: Reference clock pre-divisor
+ * @post_pll_div: Post PLL divisor
+ * @feedback_div: Feedback divisor
+ * @frac_n_div: Fractional divisor
+ *
+ * Clock Generation Unit parameters used to program the PLL based on the
+ * selected TIME_REF/TCXO frequency.
+ */
+struct ice_tspll_params_e82x {
+	u8 refclk_pre_div;
+	u8 post_pll_div;
+	u8 feedback_div;
+	u32 frac_n_div;
+};
+
+#define ICE_TSPLL_CK_REFCLKFREQ_E825		0x1F
+#define ICE_TSPLL_NDIVRATIO_E825		5
+#define ICE_TSPLL_FBDIV_INTGR_E825		256
+
+int ice_tspll_cfg_pps_out_e825c(struct ice_hw *hw, bool enable);
+int ice_tspll_init(struct ice_hw *hw);
+
+#endif /* _ICE_TSPLL_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 5d2d7736fd5f..ad76768a4232 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -7,6 +7,8 @@
 #include <linux/netdevice.h>
 #include <linux/prefetch.h>
 #include <linux/bpf_trace.h>
+#include <linux/net/intel/libie/rx.h>
+#include <net/libeth/xdp.h>
 #include <net/dsfield.h>
 #include <net/mpls.h>
 #include <net/xdp.h>
@@ -20,7 +22,6 @@
 
 #define ICE_RX_HDR_SIZE		256
 
-#define FDIR_DESC_RXDID 0x40
 #define ICE_FDIR_CLEAN_DELAY 10
 
 /**
@@ -112,7 +113,7 @@ ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc,
 static void
 ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf)
 {
-	if (dma_unmap_len(tx_buf, len))
+	if (tx_buf->type != ICE_TX_BUF_XDP_TX && dma_unmap_len(tx_buf, len))
 		dma_unmap_page(ring->dev,
 			       dma_unmap_addr(tx_buf, dma),
 			       dma_unmap_len(tx_buf, len),
@@ -126,7 +127,7 @@ ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf)
 		dev_kfree_skb_any(tx_buf->skb);
 		break;
 	case ICE_TX_BUF_XDP_TX:
-		page_frag_free(tx_buf->raw_buf);
+		libeth_xdp_return_va(tx_buf->raw_buf, false);
 		break;
 	case ICE_TX_BUF_XDP_XMIT:
 		xdp_return_frame(tx_buf->xdpf);
@@ -145,6 +146,56 @@ static struct netdev_queue *txring_txq(const struct ice_tx_ring *ring)
 }
 
 /**
+ * ice_clean_tstamp_ring - clean time stamp ring
+ * @tx_ring: Tx ring to clean the Time Stamp ring for
+ */
+static void ice_clean_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct ice_tstamp_ring *tstamp_ring = tx_ring->tstamp_ring;
+	u32 size;
+
+	if (!tstamp_ring->desc)
+		return;
+
+	size = ALIGN(tstamp_ring->count * sizeof(struct ice_ts_desc),
+		     PAGE_SIZE);
+	memset(tstamp_ring->desc, 0, size);
+	tstamp_ring->next_to_use = 0;
+}
+
+/**
+ * ice_free_tstamp_ring - free time stamp resources per queue
+ * @tx_ring: Tx ring to free the Time Stamp ring for
+ */
+void ice_free_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct ice_tstamp_ring *tstamp_ring = tx_ring->tstamp_ring;
+	u32 size;
+
+	if (!tstamp_ring->desc)
+		return;
+
+	ice_clean_tstamp_ring(tx_ring);
+	size = ALIGN(tstamp_ring->count * sizeof(struct ice_ts_desc),
+		     PAGE_SIZE);
+	dmam_free_coherent(tx_ring->dev, size, tstamp_ring->desc,
+			   tstamp_ring->dma);
+	tstamp_ring->desc = NULL;
+}
+
+/**
+ * ice_free_tx_tstamp_ring - free time stamp resources per Tx ring
+ * @tx_ring: Tx ring to free the Time Stamp ring for
+ */
+void ice_free_tx_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	ice_free_tstamp_ring(tx_ring);
+	kfree_rcu(tx_ring->tstamp_ring, rcu);
+	tx_ring->tstamp_ring = NULL;
+	tx_ring->flags &= ~ICE_TX_FLAGS_TXTIME;
+}
+
+/**
  * ice_clean_tx_ring - Free any empty Tx buffers
  * @tx_ring: ring to be cleaned
  */
@@ -182,6 +233,9 @@ tx_skip_free:
 
 	/* cleanup Tx queue statistics */
 	netdev_tx_reset_queue(txring_txq(tx_ring));
+
+	if (ice_is_txtime_cfg(tx_ring))
+		ice_free_tx_tstamp_ring(tx_ring);
 }
 
 /**
@@ -333,6 +387,84 @@ static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget)
 }
 
 /**
+ * ice_alloc_tstamp_ring - allocate the Time Stamp ring
+ * @tx_ring: Tx ring to allocate the Time Stamp ring for
+ *
+ * Return: 0 on success, negative on error
+ */
+static int ice_alloc_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct ice_tstamp_ring *tstamp_ring;
+
+	/* allocate with kzalloc(), free with kfree_rcu() */
+	tstamp_ring = kzalloc(sizeof(*tstamp_ring), GFP_KERNEL);
+	if (!tstamp_ring)
+		return -ENOMEM;
+
+	tstamp_ring->tx_ring = tx_ring;
+	tx_ring->tstamp_ring = tstamp_ring;
+	tstamp_ring->desc = NULL;
+	tstamp_ring->count = ice_calc_ts_ring_count(tx_ring);
+	tx_ring->flags |= ICE_TX_FLAGS_TXTIME;
+	return 0;
+}
+
+/**
+ * ice_setup_tstamp_ring - allocate the Time Stamp ring
+ * @tx_ring: Tx ring to set up the Time Stamp ring for
+ *
+ * Return: 0 on success, negative on error
+ */
+static int ice_setup_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct ice_tstamp_ring *tstamp_ring = tx_ring->tstamp_ring;
+	struct device *dev = tx_ring->dev;
+	u32 size;
+
+	/* round up to nearest page */
+	size = ALIGN(tstamp_ring->count * sizeof(struct ice_ts_desc),
+		     PAGE_SIZE);
+	tstamp_ring->desc = dmam_alloc_coherent(dev, size, &tstamp_ring->dma,
+						GFP_KERNEL);
+	if (!tstamp_ring->desc) {
+		dev_err(dev, "Unable to allocate memory for Time stamp Ring, size=%d\n",
+			size);
+		return -ENOMEM;
+	}
+
+	tstamp_ring->next_to_use = 0;
+	return 0;
+}
+
+/**
+ * ice_alloc_setup_tstamp_ring - Allocate and setup the Time Stamp ring
+ * @tx_ring: Tx ring to allocate and setup the Time Stamp ring for
+ *
+ * Return: 0 on success, negative on error
+ */
+int ice_alloc_setup_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct device *dev = tx_ring->dev;
+	int err;
+
+	err = ice_alloc_tstamp_ring(tx_ring);
+	if (err) {
+		dev_err(dev, "Unable to allocate Time stamp ring for Tx ring %d\n",
+			tx_ring->q_index);
+		return err;
+	}
+
+	err = ice_setup_tstamp_ring(tx_ring);
+	if (err) {
+		dev_err(dev, "Unable to setup Time stamp ring for Tx ring %d\n",
+			tx_ring->q_index);
+		ice_free_tx_tstamp_ring(tx_ring);
+		return err;
+	}
+	return 0;
+}
+
+/**
  * ice_setup_tx_ring - Allocate the Tx descriptors
  * @tx_ring: the Tx ring to set up
  *
@@ -376,61 +508,67 @@ err:
 	return -ENOMEM;
 }
 
+void ice_rxq_pp_destroy(struct ice_rx_ring *rq)
+{
+	struct libeth_fq fq = {
+		.fqes	= rq->rx_fqes,
+		.pp	= rq->pp,
+	};
+
+	libeth_rx_fq_destroy(&fq);
+	rq->rx_fqes = NULL;
+	rq->pp = NULL;
+
+	if (!rq->hdr_pp)
+		return;
+
+	fq.fqes = rq->hdr_fqes;
+	fq.pp = rq->hdr_pp;
+
+	libeth_rx_fq_destroy(&fq);
+	rq->hdr_fqes = NULL;
+	rq->hdr_pp = NULL;
+}
+
 /**
  * ice_clean_rx_ring - Free Rx buffers
  * @rx_ring: ring to be cleaned
  */
 void ice_clean_rx_ring(struct ice_rx_ring *rx_ring)
 {
-	struct xdp_buff *xdp = &rx_ring->xdp;
-	struct device *dev = rx_ring->dev;
 	u32 size;
-	u16 i;
-
-	/* ring already cleared, nothing to do */
-	if (!rx_ring->rx_buf)
-		return;
 
 	if (rx_ring->xsk_pool) {
 		ice_xsk_clean_rx_ring(rx_ring);
 		goto rx_skip_free;
 	}
 
-	if (xdp->data) {
-		xdp_return_buff(xdp);
-		xdp->data = NULL;
-	}
+	/* ring already cleared, nothing to do */
+	if (!rx_ring->rx_fqes)
+		return;
+
+	libeth_xdp_return_stash(&rx_ring->xdp);
 
 	/* Free all the Rx ring sk_buffs */
-	for (i = 0; i < rx_ring->count; i++) {
-		struct ice_rx_buf *rx_buf = &rx_ring->rx_buf[i];
+	for (u32 i = rx_ring->next_to_clean; i != rx_ring->next_to_use; ) {
+		libeth_rx_recycle_slow(rx_ring->rx_fqes[i].netmem);
 
-		if (!rx_buf->page)
-			continue;
+		if (rx_ring->hdr_pp)
+			libeth_rx_recycle_slow(rx_ring->hdr_fqes[i].netmem);
 
-		/* Invalidate cache lines that may have been written to by
-		 * device so that we avoid corrupting memory.
-		 */
-		dma_sync_single_range_for_cpu(dev, rx_buf->dma,
-					      rx_buf->page_offset,
-					      rx_ring->rx_buf_len,
-					      DMA_FROM_DEVICE);
-
-		/* free resources associated with mapping */
-		dma_unmap_page_attrs(dev, rx_buf->dma, ice_rx_pg_size(rx_ring),
-				     DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
-		__page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias);
-
-		rx_buf->page = NULL;
-		rx_buf->page_offset = 0;
+		if (unlikely(++i == rx_ring->count))
+			i = 0;
 	}
 
-rx_skip_free:
-	if (rx_ring->xsk_pool)
-		memset(rx_ring->xdp_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->xdp_buf)));
-	else
-		memset(rx_ring->rx_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->rx_buf)));
+	if (rx_ring->vsi->type == ICE_VSI_PF &&
+	    xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) {
+		xdp_rxq_info_detach_mem_model(&rx_ring->xdp_rxq);
+		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
+	}
 
+	ice_rxq_pp_destroy(rx_ring);
+
+rx_skip_free:
 	/* Zero out the descriptor ring */
 	size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
 		     PAGE_SIZE);
@@ -438,7 +576,6 @@ rx_skip_free:
 
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
-	rx_ring->first_desc = 0;
 	rx_ring->next_to_use = 0;
 }
 
@@ -450,26 +587,20 @@ rx_skip_free:
  */
 void ice_free_rx_ring(struct ice_rx_ring *rx_ring)
 {
+	struct device *dev = ice_pf_to_dev(rx_ring->vsi->back);
 	u32 size;
 
 	ice_clean_rx_ring(rx_ring);
-	if (rx_ring->vsi->type == ICE_VSI_PF)
-		if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
-			xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 	WRITE_ONCE(rx_ring->xdp_prog, NULL);
 	if (rx_ring->xsk_pool) {
 		kfree(rx_ring->xdp_buf);
 		rx_ring->xdp_buf = NULL;
-	} else {
-		kfree(rx_ring->rx_buf);
-		rx_ring->rx_buf = NULL;
 	}
 
 	if (rx_ring->desc) {
 		size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
 			     PAGE_SIZE);
-		dmam_free_coherent(rx_ring->dev, size,
-				   rx_ring->desc, rx_ring->dma);
+		dmam_free_coherent(dev, size, rx_ring->desc, rx_ring->dma);
 		rx_ring->desc = NULL;
 	}
 }
@@ -482,19 +613,9 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring)
  */
 int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 {
-	struct device *dev = rx_ring->dev;
+	struct device *dev = ice_pf_to_dev(rx_ring->vsi->back);
 	u32 size;
 
-	if (!dev)
-		return -ENOMEM;
-
-	/* warn if we are about to overwrite the pointer */
-	WARN_ON(rx_ring->rx_buf);
-	rx_ring->rx_buf =
-		kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL);
-	if (!rx_ring->rx_buf)
-		return -ENOMEM;
-
 	/* round up to nearest page */
 	size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
 		     PAGE_SIZE);
@@ -503,22 +624,16 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 	if (!rx_ring->desc) {
 		dev_err(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n",
 			size);
-		goto err;
+		return -ENOMEM;
 	}
 
 	rx_ring->next_to_use = 0;
 	rx_ring->next_to_clean = 0;
-	rx_ring->first_desc = 0;
 
 	if (ice_is_xdp_ena_vsi(rx_ring->vsi))
 		WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog);
 
 	return 0;
-
-err:
-	kfree(rx_ring->rx_buf);
-	rx_ring->rx_buf = NULL;
-	return -ENOMEM;
 }
 
 /**
@@ -527,15 +642,14 @@ err:
  * @xdp: xdp_buff used as input to the XDP program
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
- * @rx_buf: Rx buffer to store the XDP action
  * @eop_desc: Last descriptor in packet to read metadata from
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
-static void
-ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
+static u32
+ice_run_xdp(struct ice_rx_ring *rx_ring, struct libeth_xdp_buff *xdp,
 	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
-	    struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
+	    union ice_32b_rx_flex_desc *eop_desc)
 {
 	unsigned int ret = ICE_XDP_PASS;
 	u32 act;
@@ -543,23 +657,23 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	if (!xdp_prog)
 		goto exit;
 
-	ice_xdp_meta_set_desc(xdp, eop_desc);
+	xdp->desc = eop_desc;
 
-	act = bpf_prog_run_xdp(xdp_prog, xdp);
+	act = bpf_prog_run_xdp(xdp_prog, &xdp->base);
 	switch (act) {
 	case XDP_PASS:
 		break;
 	case XDP_TX:
 		if (static_branch_unlikely(&ice_xdp_locking_key))
 			spin_lock(&xdp_ring->tx_lock);
-		ret = __ice_xmit_xdp_ring(xdp, xdp_ring, false);
+		ret = __ice_xmit_xdp_ring(&xdp->base, xdp_ring, false);
 		if (static_branch_unlikely(&ice_xdp_locking_key))
 			spin_unlock(&xdp_ring->tx_lock);
 		if (ret == ICE_XDP_CONSUMED)
 			goto out_failure;
 		break;
 	case XDP_REDIRECT:
-		if (xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog))
+		if (xdp_do_redirect(rx_ring->netdev, &xdp->base, xdp_prog))
 			goto out_failure;
 		ret = ICE_XDP_REDIR;
 		break;
@@ -571,10 +685,12 @@ out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
 	case XDP_DROP:
+		libeth_xdp_return_buff(xdp);
 		ret = ICE_XDP_CONSUMED;
 	}
+
 exit:
-	ice_set_rx_bufs_act(xdp, rx_ring, ret);
+	return ret;
 }
 
 /**
@@ -661,50 +777,34 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 }
 
 /**
- * ice_alloc_mapped_page - recycle or make a new page
- * @rx_ring: ring to use
- * @bi: rx_buf struct to modify
- *
- * Returns true if the page was successfully allocated or
- * reused.
+ * ice_init_ctrl_rx_descs - Initialize Rx descriptors for control vsi.
+ * @rx_ring: ring to init descriptors on
+ * @count: number of descriptors to initialize
  */
-static bool
-ice_alloc_mapped_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *bi)
+void ice_init_ctrl_rx_descs(struct ice_rx_ring *rx_ring, u32 count)
 {
-	struct page *page = bi->page;
-	dma_addr_t dma;
-
-	/* since we are recycling buffers we should seldom need to alloc */
-	if (likely(page))
-		return true;
+	union ice_32b_rx_flex_desc *rx_desc;
+	u32 ntu = rx_ring->next_to_use;
 
-	/* alloc new page for storage */
-	page = dev_alloc_pages(ice_rx_pg_order(rx_ring));
-	if (unlikely(!page)) {
-		rx_ring->ring_stats->rx_stats.alloc_page_failed++;
-		return false;
-	}
+	if (!count)
+		return;
 
-	/* map page for use */
-	dma = dma_map_page_attrs(rx_ring->dev, page, 0, ice_rx_pg_size(rx_ring),
-				 DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
+	rx_desc = ICE_RX_DESC(rx_ring, ntu);
 
-	/* if mapping failed free memory back to system since
-	 * there isn't much point in holding memory we can't use
-	 */
-	if (dma_mapping_error(rx_ring->dev, dma)) {
-		__free_pages(page, ice_rx_pg_order(rx_ring));
-		rx_ring->ring_stats->rx_stats.alloc_page_failed++;
-		return false;
-	}
+	do {
+		rx_desc++;
+		ntu++;
+		if (unlikely(ntu == rx_ring->count)) {
+			rx_desc = ICE_RX_DESC(rx_ring, 0);
+			ntu = 0;
+		}
 
-	bi->dma = dma;
-	bi->page = page;
-	bi->page_offset = rx_ring->rx_offset;
-	page_ref_add(page, USHRT_MAX - 1);
-	bi->pagecnt_bias = USHRT_MAX;
+		rx_desc->wb.status_error0 = 0;
+		count--;
+	} while (count);
 
-	return true;
+	if (rx_ring->next_to_use != ntu)
+		ice_release_rx_desc(rx_ring, ntu);
 }
 
 /**
@@ -722,41 +822,60 @@ ice_alloc_mapped_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *bi)
  */
 bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, unsigned int cleaned_count)
 {
+	const struct libeth_fq_fp hdr_fq = {
+		.pp		= rx_ring->hdr_pp,
+		.fqes		= rx_ring->hdr_fqes,
+		.truesize	= rx_ring->hdr_truesize,
+		.count		= rx_ring->count,
+	};
+	const struct libeth_fq_fp fq = {
+		.pp		= rx_ring->pp,
+		.fqes		= rx_ring->rx_fqes,
+		.truesize	= rx_ring->truesize,
+		.count		= rx_ring->count,
+	};
 	union ice_32b_rx_flex_desc *rx_desc;
 	u16 ntu = rx_ring->next_to_use;
-	struct ice_rx_buf *bi;
 
 	/* do nothing if no valid netdev defined */
-	if ((!rx_ring->netdev && rx_ring->vsi->type != ICE_VSI_CTRL) ||
-	    !cleaned_count)
+	if (!rx_ring->netdev || !cleaned_count)
 		return false;
 
 	/* get the Rx descriptor and buffer based on next_to_use */
 	rx_desc = ICE_RX_DESC(rx_ring, ntu);
-	bi = &rx_ring->rx_buf[ntu];
 
 	do {
-		/* if we fail here, we have work remaining */
-		if (!ice_alloc_mapped_page(rx_ring, bi))
-			break;
+		dma_addr_t addr;
 
-		/* sync the buffer for use by the device */
-		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
-						 bi->page_offset,
-						 rx_ring->rx_buf_len,
-						 DMA_FROM_DEVICE);
+		addr = libeth_rx_alloc(&fq, ntu);
+		if (addr == DMA_MAPPING_ERROR) {
+			rx_ring->ring_stats->rx_stats.alloc_page_failed++;
+			break;
+		}
 
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
-		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
+		rx_desc->read.pkt_addr = cpu_to_le64(addr);
+
+		if (!hdr_fq.pp)
+			goto next;
+
+		addr = libeth_rx_alloc(&hdr_fq, ntu);
+		if (addr == DMA_MAPPING_ERROR) {
+			rx_ring->ring_stats->rx_stats.alloc_page_failed++;
+
+			libeth_rx_recycle_slow(fq.fqes[ntu].netmem);
+			break;
+		}
+
+		rx_desc->read.hdr_addr = cpu_to_le64(addr);
 
+next:
 		rx_desc++;
-		bi++;
 		ntu++;
 		if (unlikely(ntu == rx_ring->count)) {
 			rx_desc = ICE_RX_DESC(rx_ring, 0);
-			bi = rx_ring->rx_buf;
 			ntu = 0;
 		}
 
@@ -773,334 +892,41 @@ bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, unsigned int cleaned_count)
 }
 
 /**
- * ice_rx_buf_adjust_pg_offset - Prepare Rx buffer for reuse
- * @rx_buf: Rx buffer to adjust
- * @size: Size of adjustment
- *
- * Update the offset within page so that Rx buf will be ready to be reused.
- * For systems with PAGE_SIZE < 8192 this function will flip the page offset
- * so the second half of page assigned to Rx buffer will be used, otherwise
- * the offset is moved by "size" bytes
- */
-static void
-ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size)
-{
-#if (PAGE_SIZE < 8192)
-	/* flip page offset to other buffer */
-	rx_buf->page_offset ^= size;
-#else
-	/* move offset up to the next cache line */
-	rx_buf->page_offset += size;
-#endif
-}
-
-/**
- * ice_can_reuse_rx_page - Determine if page can be reused for another Rx
- * @rx_buf: buffer containing the page
- *
- * If page is reusable, we have a green light for calling ice_reuse_rx_page,
- * which will assign the current buffer to the buffer that next_to_alloc is
- * pointing to; otherwise, the DMA mapping needs to be destroyed and
- * page freed
- */
-static bool
-ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf)
-{
-	unsigned int pagecnt_bias = rx_buf->pagecnt_bias;
-	struct page *page = rx_buf->page;
-
-	/* avoid re-using remote and pfmemalloc pages */
-	if (!dev_page_is_reusable(page))
-		return false;
-
-	/* if we are only owner of page we can reuse it */
-	if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1))
-		return false;
-#if (PAGE_SIZE >= 8192)
-#define ICE_LAST_OFFSET \
-	(SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_3072)
-	if (rx_buf->page_offset > ICE_LAST_OFFSET)
-		return false;
-#endif /* PAGE_SIZE >= 8192) */
-
-	/* If we have drained the page fragment pool we need to update
-	 * the pagecnt_bias and page count so that we fully restock the
-	 * number of references the driver holds.
-	 */
-	if (unlikely(pagecnt_bias == 1)) {
-		page_ref_add(page, USHRT_MAX - 1);
-		rx_buf->pagecnt_bias = USHRT_MAX;
-	}
-
-	return true;
-}
-
-/**
- * ice_add_xdp_frag - Add contents of Rx buffer to xdp buf as a frag
- * @rx_ring: Rx descriptor ring to transact packets on
- * @xdp: xdp buff to place the data into
- * @rx_buf: buffer containing page to add
- * @size: packet length from rx_desc
- *
- * This function will add the data contained in rx_buf->page to the xdp buf.
- * It will just attach the page as a frag.
- */
-static int
-ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
-		 struct ice_rx_buf *rx_buf, const unsigned int size)
-{
-	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
-
-	if (!size)
-		return 0;
-
-	if (!xdp_buff_has_frags(xdp)) {
-		sinfo->nr_frags = 0;
-		sinfo->xdp_frags_size = 0;
-		xdp_buff_set_frags_flag(xdp);
-	}
-
-	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
-		ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED);
-		return -ENOMEM;
-	}
-
-	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page,
-				   rx_buf->page_offset, size);
-	sinfo->xdp_frags_size += size;
-	/* remember frag count before XDP prog execution; bpf_xdp_adjust_tail()
-	 * can pop off frags but driver has to handle it on its own
-	 */
-	rx_ring->nr_frags = sinfo->nr_frags;
-
-	if (page_is_pfmemalloc(rx_buf->page))
-		xdp_buff_set_frag_pfmemalloc(xdp);
-
-	return 0;
-}
-
-/**
- * ice_reuse_rx_page - page flip buffer and store it back on the ring
- * @rx_ring: Rx descriptor ring to store buffers on
- * @old_buf: donor buffer to have page reused
- *
- * Synchronizes page for reuse by the adapter
- */
-static void
-ice_reuse_rx_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *old_buf)
-{
-	u16 nta = rx_ring->next_to_alloc;
-	struct ice_rx_buf *new_buf;
-
-	new_buf = &rx_ring->rx_buf[nta];
-
-	/* update, and store next to alloc */
-	nta++;
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	/* Transfer page from old buffer to new buffer.
-	 * Move each member individually to avoid possible store
-	 * forwarding stalls and unnecessary copy of skb.
-	 */
-	new_buf->dma = old_buf->dma;
-	new_buf->page = old_buf->page;
-	new_buf->page_offset = old_buf->page_offset;
-	new_buf->pagecnt_bias = old_buf->pagecnt_bias;
-}
-
-/**
- * ice_get_rx_buf - Fetch Rx buffer and synchronize data for use
- * @rx_ring: Rx descriptor ring to transact packets on
- * @size: size of buffer to add to skb
- * @ntc: index of next to clean element
- *
- * This function will pull an Rx buffer from the ring and synchronize it
- * for use by the CPU.
- */
-static struct ice_rx_buf *
-ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
-	       const unsigned int ntc)
-{
-	struct ice_rx_buf *rx_buf;
-
-	rx_buf = &rx_ring->rx_buf[ntc];
-	rx_buf->pgcnt = page_count(rx_buf->page);
-	prefetchw(rx_buf->page);
-
-	if (!size)
-		return rx_buf;
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma,
-				      rx_buf->page_offset, size,
-				      DMA_FROM_DEVICE);
-
-	/* We have pulled a buffer for use, so decrement pagecnt_bias */
-	rx_buf->pagecnt_bias--;
-
-	return rx_buf;
-}
-
-/**
- * ice_build_skb - Build skb around an existing buffer
- * @rx_ring: Rx descriptor ring to transact packets on
- * @xdp: xdp_buff pointing to the data
- *
- * This function builds an skb around an existing XDP buffer, taking care
- * to set up the skb correctly and avoid any memcpy overhead. Driver has
- * already combined frags (if any) to skb_shared_info.
- */
-static struct sk_buff *
-ice_build_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
-{
-	u8 metasize = xdp->data - xdp->data_meta;
-	struct skb_shared_info *sinfo = NULL;
-	unsigned int nr_frags;
-	struct sk_buff *skb;
-
-	if (unlikely(xdp_buff_has_frags(xdp))) {
-		sinfo = xdp_get_shared_info_from_buff(xdp);
-		nr_frags = sinfo->nr_frags;
-	}
-
-	/* Prefetch first cache line of first page. If xdp->data_meta
-	 * is unused, this points exactly as xdp->data, otherwise we
-	 * likely have a consumer accessing first few bytes of meta
-	 * data, and then actual data.
-	 */
-	net_prefetch(xdp->data_meta);
-	/* build an skb around the page buffer */
-	skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz);
-	if (unlikely(!skb))
-		return NULL;
-
-	/* must to record Rx queue, otherwise OS features such as
-	 * symmetric queue won't work
-	 */
-	skb_record_rx_queue(skb, rx_ring->q_index);
-
-	/* update pointers within the skb to store the data */
-	skb_reserve(skb, xdp->data - xdp->data_hard_start);
-	__skb_put(skb, xdp->data_end - xdp->data);
-	if (metasize)
-		skb_metadata_set(skb, metasize);
-
-	if (unlikely(xdp_buff_has_frags(xdp)))
-		xdp_update_skb_shared_info(skb, nr_frags,
-					   sinfo->xdp_frags_size,
-					   nr_frags * xdp->frame_sz,
-					   xdp_buff_is_frag_pfmemalloc(xdp));
-
-	return skb;
-}
-
-/**
- * ice_construct_skb - Allocate skb and populate it
- * @rx_ring: Rx descriptor ring to transact packets on
- * @xdp: xdp_buff pointing to the data
+ * ice_clean_ctrl_rx_irq - Clean descriptors from flow director Rx ring
+ * @rx_ring: Rx descriptor ring for ctrl_vsi to transact packets on
  *
- * This function allocates an skb. It then populates it with the page
- * data from the current receive descriptor, taking care to set up the
- * skb correctly.
+ * This function cleans Rx descriptors from the ctrl_vsi Rx ring used
+ * to set flow director rules on VFs.
  */
-static struct sk_buff *
-ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
+void ice_clean_ctrl_rx_irq(struct ice_rx_ring *rx_ring)
 {
-	unsigned int size = xdp->data_end - xdp->data;
-	struct skb_shared_info *sinfo = NULL;
-	struct ice_rx_buf *rx_buf;
-	unsigned int nr_frags = 0;
-	unsigned int headlen;
-	struct sk_buff *skb;
-
-	/* prefetch first cache line of first page */
-	net_prefetch(xdp->data);
-
-	if (unlikely(xdp_buff_has_frags(xdp))) {
-		sinfo = xdp_get_shared_info_from_buff(xdp);
-		nr_frags = sinfo->nr_frags;
-	}
-
-	/* allocate a skb to store the frags */
-	skb = napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE);
-	if (unlikely(!skb))
-		return NULL;
-
-	rx_buf = &rx_ring->rx_buf[rx_ring->first_desc];
-	skb_record_rx_queue(skb, rx_ring->q_index);
-	/* Determine available headroom for copy */
-	headlen = size;
-	if (headlen > ICE_RX_HDR_SIZE)
-		headlen = eth_get_headlen(skb->dev, xdp->data, ICE_RX_HDR_SIZE);
-
-	/* align pull length to size of long to optimize memcpy performance */
-	memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen,
-							 sizeof(long)));
-
-	/* if we exhaust the linear part then add what is left as a frag */
-	size -= headlen;
-	if (size) {
-		/* besides adding here a partial frag, we are going to add
-		 * frags from xdp_buff, make sure there is enough space for
-		 * them
-		 */
-		if (unlikely(nr_frags >= MAX_SKB_FRAGS - 1)) {
-			dev_kfree_skb(skb);
-			return NULL;
-		}
-		skb_add_rx_frag(skb, 0, rx_buf->page,
-				rx_buf->page_offset + headlen, size,
-				xdp->frame_sz);
-	} else {
-		/* buffer is unused, change the act that should be taken later
-		 * on; data was copied onto skb's linear part so there's no
-		 * need for adjusting page offset and we can reuse this buffer
-		 * as-is
-		 */
-		rx_buf->act = ICE_SKB_CONSUMED;
-	}
+	u32 ntc = rx_ring->next_to_clean;
+	unsigned int total_rx_pkts = 0;
+	u32 cnt = rx_ring->count;
 
-	if (unlikely(xdp_buff_has_frags(xdp))) {
-		struct skb_shared_info *skinfo = skb_shinfo(skb);
+	while (likely(total_rx_pkts < ICE_DFLT_IRQ_WORK)) {
+		struct ice_vsi *ctrl_vsi = rx_ring->vsi;
+		union ice_32b_rx_flex_desc *rx_desc;
+		u16 stat_err_bits;
 
-		memcpy(&skinfo->frags[skinfo->nr_frags], &sinfo->frags[0],
-		       sizeof(skb_frag_t) * nr_frags);
+		rx_desc = ICE_RX_DESC(rx_ring, ntc);
 
-		xdp_update_skb_shared_info(skb, skinfo->nr_frags + nr_frags,
-					   sinfo->xdp_frags_size,
-					   nr_frags * xdp->frame_sz,
-					   xdp_buff_is_frag_pfmemalloc(xdp));
-	}
+		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S);
+		if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits))
+			break;
 
-	return skb;
-}
+		dma_rmb();
 
-/**
- * ice_put_rx_buf - Clean up used buffer and either recycle or free
- * @rx_ring: Rx descriptor ring to transact packets on
- * @rx_buf: Rx buffer to pull data from
- *
- * This function will clean up the contents of the rx_buf. It will either
- * recycle the buffer or unmap it and free the associated resources.
- */
-static void
-ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf)
-{
-	if (!rx_buf)
-		return;
+		if (ctrl_vsi->vf)
+			ice_vc_fdir_irq_handler(ctrl_vsi, rx_desc);
 
-	if (ice_can_reuse_rx_page(rx_buf)) {
-		/* hand second half of page back to the ring */
-		ice_reuse_rx_page(rx_ring, rx_buf);
-	} else {
-		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page_attrs(rx_ring->dev, rx_buf->dma,
-				     ice_rx_pg_size(rx_ring), DMA_FROM_DEVICE,
-				     ICE_RX_DMA_ATTR);
-		__page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias);
+		if (++ntc == cnt)
+			ntc = 0;
+		total_rx_pkts++;
 	}
 
-	/* clear contents of buffer_info */
-	rx_buf->page = NULL;
+	rx_ring->next_to_clean = ntc;
+	ice_init_ctrl_rx_descs(rx_ring, ICE_DESC_UNUSED(rx_ring));
 }
 
 /**
@@ -1115,20 +941,19 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf)
  *
  * Returns amount of work completed
  */
-int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
+static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
-	unsigned int offset = rx_ring->rx_offset;
-	struct xdp_buff *xdp = &rx_ring->xdp;
-	u32 cached_ntc = rx_ring->first_desc;
 	struct ice_tx_ring *xdp_ring = NULL;
 	struct bpf_prog *xdp_prog = NULL;
 	u32 ntc = rx_ring->next_to_clean;
+	LIBETH_XDP_ONSTACK_BUFF(xdp);
+	u32 cached_ntu, xdp_verdict;
 	u32 cnt = rx_ring->count;
 	u32 xdp_xmit = 0;
-	u32 cached_ntu;
 	bool failure;
-	u32 first;
+
+	libeth_xdp_init_buff(xdp, &rx_ring->xdp, &rx_ring->xdp_rxq);
 
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	if (xdp_prog) {
@@ -1139,19 +964,21 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 	/* start the loop to process Rx packets bounded by 'budget' */
 	while (likely(total_rx_pkts < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
-		struct ice_rx_buf *rx_buf;
+		struct libeth_fqe *rx_buf;
 		struct sk_buff *skb;
 		unsigned int size;
 		u16 stat_err_bits;
 		u16 vlan_tci;
+		bool rxe;
 
 		/* get the Rx desc from Rx ring based on 'next_to_clean' */
 		rx_desc = ICE_RX_DESC(rx_ring, ntc);
 
-		/* status_error_len will always be zero for unused descriptors
-		 * because it's cleared in cleanup, and overlaps with hdr_addr
-		 * which is always zero because packet split isn't used, if the
-		 * hardware wrote DD then it will be non-zero
+		/*
+		 * The DD bit will always be zero for unused descriptors
+		 * because it's cleared in cleanup or when setting the DMA
+		 * address of the header buffer, which never uses the DD bit.
+		 * If the hardware wrote the descriptor, it will be non-zero.
 		 */
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S);
 		if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits))
@@ -1164,85 +991,66 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		dma_rmb();
 
 		ice_trace(clean_rx_irq, rx_ring, rx_desc);
-		if (rx_desc->wb.rxdid == FDIR_DESC_RXDID || !rx_ring->netdev) {
-			struct ice_vsi *ctrl_vsi = rx_ring->vsi;
-
-			if (rx_desc->wb.rxdid == FDIR_DESC_RXDID &&
-			    ctrl_vsi->vf)
-				ice_vc_fdir_irq_handler(ctrl_vsi, rx_desc);
-			if (++ntc == cnt)
-				ntc = 0;
-			rx_ring->first_desc = ntc;
-			continue;
-		}
 
+		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_HBO_S) |
+				BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
+		rxe = ice_test_staterr(rx_desc->wb.status_error0,
+				       stat_err_bits);
+
+		if (!rx_ring->hdr_pp)
+			goto payload;
+
+		size = le16_get_bits(rx_desc->wb.hdr_len_sph_flex_flags1,
+				     ICE_RX_FLEX_DESC_HDR_LEN_M);
+		if (unlikely(rxe))
+			size = 0;
+
+		rx_buf = &rx_ring->hdr_fqes[ntc];
+		libeth_xdp_process_buff(xdp, rx_buf, size);
+		rx_buf->netmem = 0;
+
+payload:
 		size = le16_to_cpu(rx_desc->wb.pkt_len) &
 			ICE_RX_FLX_DESC_PKT_LEN_M;
+		if (unlikely(rxe))
+			size = 0;
 
 		/* retrieve a buffer from the ring */
-		rx_buf = ice_get_rx_buf(rx_ring, size, ntc);
-
-		if (!xdp->data) {
-			void *hard_start;
+		rx_buf = &rx_ring->rx_fqes[ntc];
+		libeth_xdp_process_buff(xdp, rx_buf, size);
 
-			hard_start = page_address(rx_buf->page) + rx_buf->page_offset -
-				     offset;
-			xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
-			xdp_buff_clear_frags_flag(xdp);
-		} else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
-			break;
-		}
 		if (++ntc == cnt)
 			ntc = 0;
 
 		/* skip if it is NOP desc */
-		if (ice_is_non_eop(rx_ring, rx_desc))
+		if (ice_is_non_eop(rx_ring, rx_desc) || unlikely(!xdp->data))
 			continue;
 
-		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
-		if (rx_buf->act == ICE_XDP_PASS)
+		xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc);
+		if (xdp_verdict == ICE_XDP_PASS)
 			goto construct_skb;
-		total_rx_bytes += xdp_get_buff_len(xdp);
+
+		if (xdp_verdict & (ICE_XDP_TX | ICE_XDP_REDIR))
+			xdp_xmit |= xdp_verdict;
+		total_rx_bytes += xdp_get_buff_len(&xdp->base);
 		total_rx_pkts++;
 
 		xdp->data = NULL;
-		rx_ring->first_desc = ntc;
-		rx_ring->nr_frags = 0;
 		continue;
+
 construct_skb:
-		if (likely(ice_ring_uses_build_skb(rx_ring)))
-			skb = ice_build_skb(rx_ring, xdp);
-		else
-			skb = ice_construct_skb(rx_ring, xdp);
-		/* exit if we failed to retrieve a buffer */
-		if (!skb) {
-			rx_ring->ring_stats->rx_stats.alloc_page_failed++;
-			rx_buf->act = ICE_XDP_CONSUMED;
-			if (unlikely(xdp_buff_has_frags(xdp)))
-				ice_set_rx_bufs_act(xdp, rx_ring,
-						    ICE_XDP_CONSUMED);
-			xdp->data = NULL;
-			rx_ring->first_desc = ntc;
-			rx_ring->nr_frags = 0;
-			break;
-		}
+		skb = xdp_build_skb_from_buff(&xdp->base);
 		xdp->data = NULL;
-		rx_ring->first_desc = ntc;
-		rx_ring->nr_frags = 0;
 
-		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
-		if (unlikely(ice_test_staterr(rx_desc->wb.status_error0,
-					      stat_err_bits))) {
-			dev_kfree_skb_any(skb);
+		/* exit if we failed to retrieve a buffer */
+		if (!skb) {
+			libeth_xdp_return_buff_slow(xdp);
+			rx_ring->ring_stats->rx_stats.alloc_buf_failed++;
 			continue;
 		}
 
 		vlan_tci = ice_get_vlan_tci(rx_desc);
 
-		/* pad the skb if needed, to make a valid ethernet frame */
-		if (eth_skb_pad(skb))
-			continue;
-
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 
@@ -1257,30 +1065,15 @@ construct_skb:
 		total_rx_pkts++;
 	}
 
-	first = rx_ring->first_desc;
-	while (cached_ntc != first) {
-		struct ice_rx_buf *buf = &rx_ring->rx_buf[cached_ntc];
-
-		if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) {
-			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-			xdp_xmit |= buf->act;
-		} else if (buf->act & ICE_XDP_CONSUMED) {
-			buf->pagecnt_bias++;
-		} else if (buf->act == ICE_XDP_PASS) {
-			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-		}
-
-		ice_put_rx_buf(rx_ring, buf);
-		if (++cached_ntc >= cnt)
-			cached_ntc = 0;
-	}
 	rx_ring->next_to_clean = ntc;
 	/* return up to cleaned_count buffers to hardware */
-	failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring));
+	failure = ice_alloc_rx_bufs(rx_ring, ICE_DESC_UNUSED(rx_ring));
 
 	if (xdp_xmit)
 		ice_finalize_xdp_rx(xdp_ring, xdp_xmit, cached_ntu);
 
+	libeth_xdp_save_buff(&rx_ring->xdp, xdp);
+
 	if (rx_ring->ring_stats)
 		ice_update_rx_ring_stats(rx_ring, total_rx_pkts,
 					 total_rx_bytes);
@@ -1722,10 +1515,46 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first,
 	/* notify HW of packet */
 	kick = __netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount,
 				      netdev_xmit_more());
-	if (kick)
-		/* notify HW of packet */
-		writel(i, tx_ring->tail);
+	if (!kick)
+		return;
 
+	if (ice_is_txtime_cfg(tx_ring)) {
+		struct ice_tstamp_ring *tstamp_ring = tx_ring->tstamp_ring;
+		u32 tstamp_count = tstamp_ring->count;
+		u32 j = tstamp_ring->next_to_use;
+		struct ice_ts_desc *ts_desc;
+		struct timespec64 ts;
+		u32 tstamp;
+
+		ts = ktime_to_timespec64(first->skb->tstamp);
+		tstamp = ts.tv_nsec >> ICE_TXTIME_CTX_RESOLUTION_128NS;
+
+		ts_desc = ICE_TS_DESC(tstamp_ring, j);
+		ts_desc->tx_desc_idx_tstamp = ice_build_tstamp_desc(i, tstamp);
+
+		j++;
+		if (j == tstamp_count) {
+			u32 fetch = tstamp_count - tx_ring->count;
+
+			j = 0;
+
+			/* To prevent an MDD, when wrapping the tstamp ring
+			 * create additional TS descriptors equal to the number
+			 * of the fetch TS descriptors value. HW will merge the
+			 * TS descriptors with the same timestamp value into a
+			 * single descriptor.
+			 */
+			for (; j < fetch; j++) {
+				ts_desc = ICE_TS_DESC(tstamp_ring, j);
+				ts_desc->tx_desc_idx_tstamp =
+				       ice_build_tstamp_desc(i, tstamp);
+			}
+		}
+		tstamp_ring->next_to_use = j;
+		writel_relaxed(j, tstamp_ring->tail);
+	} else {
+		writel_relaxed(i, tx_ring->tail);
+	}
 	return;
 
 dma_error:
@@ -1753,6 +1582,7 @@ dma_error:
 static
 int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 {
+	const struct ice_tx_ring *tx_ring = off->tx_ring;
 	u32 l4_len = 0, l3_len = 0, l2_len = 0;
 	struct sk_buff *skb = first->skb;
 	union {
@@ -1902,6 +1732,30 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 	l3_len = l4.hdr - ip.hdr;
 	offset |= (l3_len / 4) << ICE_TX_DESC_LEN_IPLEN_S;
 
+	if ((tx_ring->netdev->features & NETIF_F_HW_CSUM) &&
+	    !(first->tx_flags & ICE_TX_FLAGS_TSO) &&
+	    !skb_csum_is_sctp(skb)) {
+		/* Set GCS */
+		u16 csum_start = (skb->csum_start - skb->mac_header) / 2;
+		u16 csum_offset = skb->csum_offset / 2;
+		u16 gcs_params;
+
+		gcs_params = FIELD_PREP(ICE_TX_GCS_DESC_START_M, csum_start) |
+			     FIELD_PREP(ICE_TX_GCS_DESC_OFFSET_M, csum_offset) |
+			     FIELD_PREP(ICE_TX_GCS_DESC_TYPE_M,
+					ICE_TX_GCS_DESC_CSUM_PSH);
+
+		/* Unlike legacy HW checksums, GCS requires a context
+		 * descriptor.
+		 */
+		off->cd_qw1 |= ICE_TX_DESC_DTYPE_CTX;
+		off->cd_gcs_params = gcs_params;
+		/* Fill out CSO info in data descriptors */
+		off->td_offset |= offset;
+		off->td_cmd |= cmd;
+		return 1;
+	}
+
 	/* Enable L4 checksum offloads */
 	switch (l4_proto) {
 	case IPPROTO_TCP:
@@ -2359,17 +2213,20 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 
 	/* allow CONTROL frames egress from main VSI if FW LLDP disabled */
 	eth = (struct ethhdr *)skb_mac_header(skb);
-	if (unlikely((skb->priority == TC_PRIO_CONTROL ||
-		      eth->h_proto == htons(ETH_P_LLDP)) &&
-		     vsi->type == ICE_VSI_PF &&
-		     vsi->port_info->qos_cfg.is_sw_lldp))
+
+	if ((ice_is_switchdev_running(vsi->back) ||
+	     ice_lag_is_switchdev_running(vsi->back)) &&
+	    vsi->type != ICE_VSI_SF)
+		ice_eswitch_set_target_vsi(skb, &offload);
+	else if (unlikely((skb->priority == TC_PRIO_CONTROL ||
+			   eth->h_proto == htons(ETH_P_LLDP)) &&
+			   vsi->type == ICE_VSI_PF &&
+			   vsi->port_info->qos_cfg.is_sw_lldp))
 		offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
 					ICE_TX_CTX_DESC_SWTCH_UPLINK <<
 					ICE_TXD_CTX_QW1_CMD_S);
 
 	ice_tstamp(tx_ring, skb, first, &offload);
-	if (ice_is_switchdev_running(vsi->back) && vsi->type != ICE_VSI_SF)
-		ice_eswitch_set_target_vsi(skb, &offload);
 
 	if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) {
 		struct ice_tx_ctx_desc *cdesc;
@@ -2383,7 +2240,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 		/* setup context descriptor */
 		cdesc->tunneling_params = cpu_to_le32(offload.cd_tunnel_params);
 		cdesc->l2tag2 = cpu_to_le16(offload.cd_l2tag2);
-		cdesc->rsvd = cpu_to_le16(0);
+		cdesc->gcs = cpu_to_le16(offload.cd_gcs_params);
 		cdesc->qw1 = cpu_to_le64(offload.cd_qw1);
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index cb347c852ba9..e440c55d9e9f 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -4,6 +4,8 @@
 #ifndef _ICE_TXRX_H_
 #define _ICE_TXRX_H_
 
+#include <net/libeth/types.h>
+
 #include "ice_type.h"
 
 #define ICE_DFLT_IRQ_WORK	256
@@ -27,72 +29,6 @@
 
 #define ICE_MAX_TXQ_PER_TXQG	128
 
-/* Attempt to maximize the headroom available for incoming frames. We use a 2K
- * buffer for MTUs <= 1500 and need 1536/1534 to store the data for the frame.
- * This leaves us with 512 bytes of room.  From that we need to deduct the
- * space needed for the shared info and the padding needed to IP align the
- * frame.
- *
- * Note: For cache line sizes 256 or larger this value is going to end
- *	 up negative.  In these cases we should fall back to the legacy
- *	 receive path.
- */
-#if (PAGE_SIZE < 8192)
-#define ICE_2K_TOO_SMALL_WITH_PADDING \
-	((unsigned int)(NET_SKB_PAD + ICE_RXBUF_1536) > \
-			SKB_WITH_OVERHEAD(ICE_RXBUF_2048))
-
-/**
- * ice_compute_pad - compute the padding
- * @rx_buf_len: buffer length
- *
- * Figure out the size of half page based on given buffer length and
- * then subtract the skb_shared_info followed by subtraction of the
- * actual buffer length; this in turn results in the actual space that
- * is left for padding usage
- */
-static inline int ice_compute_pad(int rx_buf_len)
-{
-	int half_page_size;
-
-	half_page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2);
-	return SKB_WITH_OVERHEAD(half_page_size) - rx_buf_len;
-}
-
-/**
- * ice_skb_pad - determine the padding that we can supply
- *
- * Figure out the right Rx buffer size and based on that calculate the
- * padding
- */
-static inline int ice_skb_pad(void)
-{
-	int rx_buf_len;
-
-	/* If a 2K buffer cannot handle a standard Ethernet frame then
-	 * optimize padding for a 3K buffer instead of a 1.5K buffer.
-	 *
-	 * For a 3K buffer we need to add enough padding to allow for
-	 * tailroom due to NET_IP_ALIGN possibly shifting us out of
-	 * cache-line alignment.
-	 */
-	if (ICE_2K_TOO_SMALL_WITH_PADDING)
-		rx_buf_len = ICE_RXBUF_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN);
-	else
-		rx_buf_len = ICE_RXBUF_1536;
-
-	/* if needed make room for NET_IP_ALIGN */
-	rx_buf_len -= NET_IP_ALIGN;
-
-	return ice_compute_pad(rx_buf_len);
-}
-
-#define ICE_SKB_PAD ice_skb_pad()
-#else
-#define ICE_2K_TOO_SMALL_WITH_PADDING false
-#define ICE_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
-#endif
-
 /* We are assuming that the cache line is always 64 Bytes here for ice.
  * In order to make sure that is a correct assumption there is a check in probe
  * to print a warning if the read from GLPCI_CNF2 tells us that the cache line
@@ -112,10 +48,6 @@ static inline int ice_skb_pad(void)
 	(u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
 	      (R)->next_to_clean - (R)->next_to_use - 1)
 
-#define ICE_RX_DESC_UNUSED(R)	\
-	((((R)->first_desc > (R)->next_to_use) ? 0 : (R)->count) + \
-	      (R)->first_desc - (R)->next_to_use - 1)
-
 #define ICE_RING_QUARTER(R) ((R)->count >> 2)
 
 #define ICE_TX_FLAGS_TSO	BIT(0)
@@ -193,18 +125,10 @@ struct ice_tx_offload_params {
 	u32 td_l2tag1;
 	u32 cd_tunnel_params;
 	u16 cd_l2tag2;
+	u16 cd_gcs_params;
 	u8 header_len;
 };
 
-struct ice_rx_buf {
-	dma_addr_t dma;
-	struct page *page;
-	unsigned int page_offset;
-	unsigned int pgcnt;
-	unsigned int act;
-	unsigned int pagecnt_bias;
-};
-
 struct ice_q_stats {
 	u64 pkts;
 	u64 bytes;
@@ -262,15 +186,6 @@ struct ice_pkt_ctx {
 	__be16 vlan_proto;
 };
 
-struct ice_xdp_buff {
-	struct xdp_buff xdp_buff;
-	const union ice_32b_rx_flex_desc *eop_desc;
-	const struct ice_pkt_ctx *pkt_ctx;
-};
-
-/* Required for compatibility with xdp_buffs from xsk_pool */
-static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0);
-
 /* indices into GLINT_ITR registers */
 #define ICE_RX_ITR	ICE_IDX_ITR0
 #define ICE_TX_ITR	ICE_IDX_ITR1
@@ -310,10 +225,20 @@ enum ice_dynamic_itr {
 #define ICE_TX_LEGACY	1
 
 /* descriptor ring, associated with a VSI */
+struct ice_tstamp_ring {
+	struct ice_tx_ring *tx_ring;	/* Backreference to associated Tx ring */
+	dma_addr_t dma;			/* physical address of ring */
+	struct rcu_head rcu;            /* to avoid race on free */
+	u8 __iomem *tail;
+	void *desc;
+	u16 next_to_use;
+	u16 count;
+} ____cacheline_internodealigned_in_smp;
+
 struct ice_rx_ring {
 	/* CL1 - 1st cacheline starts here */
 	void *desc;			/* Descriptor ring memory */
-	struct device *dev;		/* Used for DMA mapping */
+	struct page_pool *pp;
 	struct net_device *netdev;	/* netdev ring maps to */
 	struct ice_vsi *vsi;		/* Backreference to associated VSI */
 	struct ice_q_vector *q_vector;	/* Backreference to associated vector */
@@ -325,14 +250,19 @@ struct ice_rx_ring {
 	u16 next_to_alloc;
 
 	union {
-		struct ice_rx_buf *rx_buf;
+		struct libeth_fqe *rx_fqes;
 		struct xdp_buff **xdp_buf;
 	};
+
 	/* CL2 - 2nd cacheline starts here */
+	struct libeth_fqe *hdr_fqes;
+	struct page_pool *hdr_pp;
+
 	union {
-		struct ice_xdp_buff xdp_ext;
-		struct xdp_buff xdp;
+		struct libeth_xdp_buff_stash xdp;
+		struct libeth_xdp_buff *xsk;
 	};
+
 	/* CL3 - 3rd cacheline starts here */
 	union {
 		struct ice_pkt_ctx pkt_ctx;
@@ -342,12 +272,13 @@ struct ice_rx_ring {
 		};
 	};
 	struct bpf_prog *xdp_prog;
-	u16 rx_offset;
 
 	/* used in interrupt processing */
 	u16 next_to_use;
 	u16 next_to_clean;
-	u16 first_desc;
+
+	u32 hdr_truesize;
+	u32 truesize;
 
 	/* stats structs */
 	struct ice_ring_stats *ring_stats;
@@ -358,15 +289,14 @@ struct ice_rx_ring {
 	struct ice_tx_ring *xdp_ring;
 	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
 	struct xsk_buff_pool *xsk_pool;
-	u32 nr_frags;
-	u16 max_frame;
+	u16 rx_hdr_len;
 	u16 rx_buf_len;
 	dma_addr_t dma;			/* physical address of ring */
 	u8 dcb_tc;			/* Traffic class of ring */
 	u8 ptp_rx;
-#define ICE_RX_FLAGS_RING_BUILD_SKB	BIT(1)
 #define ICE_RX_FLAGS_CRC_STRIP_DIS	BIT(2)
 #define ICE_RX_FLAGS_MULTIDEV		BIT(3)
+#define ICE_RX_FLAGS_RING_GCS		BIT(4)
 	u8 flags;
 	/* CL5 - 5th cacheline starts here */
 	struct xdp_rxq_info xdp_rxq;
@@ -402,29 +332,16 @@ struct ice_tx_ring {
 	spinlock_t tx_lock;
 	u32 txq_teid;			/* Added Tx queue TEID */
 	/* CL4 - 4th cacheline starts here */
+	struct ice_tstamp_ring *tstamp_ring;
 #define ICE_TX_FLAGS_RING_XDP		BIT(0)
 #define ICE_TX_FLAGS_RING_VLAN_L2TAG1	BIT(1)
 #define ICE_TX_FLAGS_RING_VLAN_L2TAG2	BIT(2)
+#define ICE_TX_FLAGS_TXTIME		BIT(3)
 	u8 flags;
 	u8 dcb_tc;			/* Traffic class of ring */
 	u16 quanta_prof_id;
 } ____cacheline_internodealigned_in_smp;
 
-static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring)
-{
-	return !!(ring->flags & ICE_RX_FLAGS_RING_BUILD_SKB);
-}
-
-static inline void ice_set_ring_build_skb_ena(struct ice_rx_ring *ring)
-{
-	ring->flags |= ICE_RX_FLAGS_RING_BUILD_SKB;
-}
-
-static inline void ice_clear_ring_build_skb_ena(struct ice_rx_ring *ring)
-{
-	ring->flags &= ~ICE_RX_FLAGS_RING_BUILD_SKB;
-}
-
 static inline bool ice_ring_ch_enabled(struct ice_tx_ring *ring)
 {
 	return !!ring->ch;
@@ -479,17 +396,13 @@ struct ice_coalesce_stored {
 
 static inline unsigned int ice_rx_pg_order(struct ice_rx_ring *ring)
 {
-#if (PAGE_SIZE < 8192)
-	if (ring->rx_buf_len > (PAGE_SIZE / 2))
-		return 1;
-#endif
 	return 0;
 }
 
-#define ice_rx_pg_size(_ring) (PAGE_SIZE << ice_rx_pg_order(_ring))
-
 union ice_32b_rx_flex_desc;
 
+void ice_init_ctrl_rx_descs(struct ice_rx_ring *rx_ring, u32 num_descs);
+void ice_rxq_pp_destroy(struct ice_rx_ring *rq);
 bool ice_alloc_rx_bufs(struct ice_rx_ring *rxr, unsigned int cleaned_count);
 netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev);
 u16
@@ -499,12 +412,15 @@ void ice_clean_tx_ring(struct ice_tx_ring *tx_ring);
 void ice_clean_rx_ring(struct ice_rx_ring *rx_ring);
 int ice_setup_tx_ring(struct ice_tx_ring *tx_ring);
 int ice_setup_rx_ring(struct ice_rx_ring *rx_ring);
+int ice_alloc_setup_tstamp_ring(struct ice_tx_ring *tx_ring);
 void ice_free_tx_ring(struct ice_tx_ring *tx_ring);
 void ice_free_rx_ring(struct ice_rx_ring *rx_ring);
 int ice_napi_poll(struct napi_struct *napi, int budget);
 int
 ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc,
 		   u8 *raw_packet);
-int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget);
 void ice_clean_ctrl_tx_irq(struct ice_tx_ring *tx_ring);
+void ice_clean_ctrl_rx_irq(struct ice_rx_ring *rx_ring);
+void ice_free_tx_tstamp_ring(struct ice_tx_ring *tx_ring);
+void ice_free_tstamp_ring(struct ice_tx_ring *tx_ring);
 #endif /* _ICE_TXRX_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 2719f0e20933..956da38d63b0 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -3,6 +3,7 @@
 
 #include <linux/filter.h>
 #include <linux/net/intel/libie/rx.h>
+#include <net/libeth/xdp.h>
 
 #include "ice_txrx_lib.h"
 #include "ice_eswitch.h"
@@ -81,6 +82,23 @@ ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring,
 }
 
 /**
+ * ice_rx_gcs - Set generic checksum in skb
+ * @skb: skb currently being received and modified
+ * @rx_desc: receive descriptor
+ */
+static void ice_rx_gcs(struct sk_buff *skb,
+		       const union ice_32b_rx_flex_desc *rx_desc)
+{
+	const struct ice_32b_rx_flex_desc_nic *desc;
+	u16 csum;
+
+	desc = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
+	skb->ip_summed = CHECKSUM_COMPLETE;
+	csum = (__force u16)desc->raw_csum;
+	skb->csum = csum_unfold((__force __sum16)swab16(csum));
+}
+
+/**
  * ice_rx_csum - Indicate in skb if checksum is good
  * @ring: the ring we care about
  * @skb: skb currently being received and modified
@@ -107,6 +125,15 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
 	rx_status0 = le16_to_cpu(rx_desc->wb.status_error0);
 	rx_status1 = le16_to_cpu(rx_desc->wb.status_error1);
 
+	if ((ring->flags & ICE_RX_FLAGS_RING_GCS) &&
+	    rx_desc->wb.rxdid == ICE_RXDID_FLEX_NIC &&
+	    (decoded.inner_prot == LIBETH_RX_PT_INNER_TCP ||
+	     decoded.inner_prot == LIBETH_RX_PT_INNER_UDP ||
+	     decoded.inner_prot == LIBETH_RX_PT_INNER_ICMP)) {
+		ice_rx_gcs(skb, rx_desc);
+		return;
+	}
+
 	/* check if HW has decoded the packet and checksum */
 	if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S)))
 		return;
@@ -204,9 +231,12 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 
 		if (ice_is_port_repr_netdev(netdev))
 			ice_repr_inc_rx_stats(netdev, skb->len);
+
+		/* __skb_push() is needed because xdp_build_skb_from_buff()
+		 * calls eth_type_trans()
+		 */
+		__skb_push(skb, ETH_HLEN);
 		skb->protocol = eth_type_trans(skb, netdev);
-	} else {
-		skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 	}
 
 	ice_rx_csum(rx_ring, skb, rx_desc, ptype);
@@ -244,19 +274,18 @@ static void
 ice_clean_xdp_tx_buf(struct device *dev, struct ice_tx_buf *tx_buf,
 		     struct xdp_frame_bulk *bq)
 {
-	dma_unmap_single(dev, dma_unmap_addr(tx_buf, dma),
-			 dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
-	dma_unmap_len_set(tx_buf, len, 0);
-
 	switch (tx_buf->type) {
 	case ICE_TX_BUF_XDP_TX:
-		page_frag_free(tx_buf->raw_buf);
+		libeth_xdp_return_va(tx_buf->raw_buf, true);
 		break;
 	case ICE_TX_BUF_XDP_XMIT:
+		dma_unmap_single(dev, dma_unmap_addr(tx_buf, dma),
+				 dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
 		xdp_return_frame_bulk(tx_buf->xdpf, bq);
 		break;
 	}
 
+	dma_unmap_len_set(tx_buf, len, 0);
 	tx_buf->type = ICE_TX_BUF_EMPTY;
 }
 
@@ -351,9 +380,11 @@ int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring,
 	struct ice_tx_buf *tx_buf;
 	u32 cnt = xdp_ring->count;
 	void *data = xdp->data;
+	struct page *page;
 	u32 nr_frags = 0;
 	u32 free_space;
 	u32 frag = 0;
+	u32 offset;
 
 	free_space = ICE_DESC_UNUSED(xdp_ring);
 	if (free_space < ICE_RING_QUARTER(xdp_ring))
@@ -373,24 +404,28 @@ int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring,
 	tx_head = &xdp_ring->tx_buf[ntu];
 	tx_buf = tx_head;
 
+	page = virt_to_page(data);
+	offset = offset_in_page(xdp->data);
+
 	for (;;) {
 		dma_addr_t dma;
 
-		dma = dma_map_single(dev, data, size, DMA_TO_DEVICE);
-		if (dma_mapping_error(dev, dma))
-			goto dma_unmap;
-
-		/* record length, and DMA address */
-		dma_unmap_len_set(tx_buf, len, size);
-		dma_unmap_addr_set(tx_buf, dma, dma);
-
 		if (frame) {
+			dma = dma_map_single(dev, data, size, DMA_TO_DEVICE);
+			if (dma_mapping_error(dev, dma))
+				goto dma_unmap;
 			tx_buf->type = ICE_TX_BUF_FRAG;
 		} else {
+			dma = page_pool_get_dma_addr(page) + offset;
+			dma_sync_single_for_device(dev, dma, size, DMA_BIDIRECTIONAL);
 			tx_buf->type = ICE_TX_BUF_XDP_TX;
 			tx_buf->raw_buf = data;
 		}
 
+		/* record length, and DMA address */
+		dma_unmap_len_set(tx_buf, len, size);
+		dma_unmap_addr_set(tx_buf, dma, dma);
+
 		tx_desc->buf_addr = cpu_to_le64(dma);
 		tx_desc->cmd_type_offset_bsz = ice_build_ctob(0, 0, size, 0);
 
@@ -404,6 +439,8 @@ int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring,
 		tx_desc = ICE_TX_DESC(xdp_ring, ntu);
 		tx_buf = &xdp_ring->tx_buf[ntu];
 
+		page = skb_frag_page(&sinfo->frags[frag]);
+		offset = skb_frag_off(&sinfo->frags[frag]);
 		data = skb_frag_address(&sinfo->frags[frag]);
 		size = skb_frag_size(&sinfo->frags[frag]);
 		frag++;
@@ -488,10 +525,13 @@ void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res,
  */
 static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns)
 {
-	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+	const struct libeth_xdp_buff *xdp_ext = (void *)ctx;
+	struct ice_rx_ring *rx_ring;
+
+	rx_ring = libeth_xdp_buff_to_rq(xdp_ext, typeof(*rx_ring), xdp_rxq);
 
-	*ts_ns = ice_ptp_get_rx_hwts(xdp_ext->eop_desc,
-				     xdp_ext->pkt_ctx);
+	*ts_ns = ice_ptp_get_rx_hwts(xdp_ext->desc,
+				     &rx_ring->pkt_ctx);
 	if (!*ts_ns)
 		return -ENODATA;
 
@@ -519,10 +559,10 @@ ice_xdp_rx_hash_type(const union ice_32b_rx_flex_desc *eop_desc)
 static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
 			   enum xdp_rss_hash_type *rss_type)
 {
-	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+	const struct libeth_xdp_buff *xdp_ext = (void *)ctx;
 
-	*hash = ice_get_rx_hash(xdp_ext->eop_desc);
-	*rss_type = ice_xdp_rx_hash_type(xdp_ext->eop_desc);
+	*hash = ice_get_rx_hash(xdp_ext->desc);
+	*rss_type = ice_xdp_rx_hash_type(xdp_ext->desc);
 	if (!likely(*hash))
 		return -ENODATA;
 
@@ -541,13 +581,16 @@ static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
 static int ice_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto,
 			       u16 *vlan_tci)
 {
-	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+	const struct libeth_xdp_buff *xdp_ext = (void *)ctx;
+	struct ice_rx_ring *rx_ring;
+
+	rx_ring = libeth_xdp_buff_to_rq(xdp_ext, typeof(*rx_ring), xdp_rxq);
 
-	*vlan_proto = xdp_ext->pkt_ctx->vlan_proto;
+	*vlan_proto = rx_ring->pkt_ctx.vlan_proto;
 	if (!*vlan_proto)
 		return -ENODATA;
 
-	*vlan_tci = ice_get_vlan_tci(xdp_ext->eop_desc);
+	*vlan_tci = ice_get_vlan_tci(xdp_ext->desc);
 	if (!*vlan_tci)
 		return -ENODATA;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index 79f960c6680d..6a3f10f7a53f 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -6,49 +6,6 @@
 #include "ice.h"
 
 /**
- * ice_set_rx_bufs_act - propagate Rx buffer action to frags
- * @xdp: XDP buffer representing frame (linear and frags part)
- * @rx_ring: Rx ring struct
- * act: action to store onto Rx buffers related to XDP buffer parts
- *
- * Set action that should be taken before putting Rx buffer from first frag
- * to the last.
- */
-static inline void
-ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring,
-		    const unsigned int act)
-{
-	u32 sinfo_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
-	u32 nr_frags = rx_ring->nr_frags + 1;
-	u32 idx = rx_ring->first_desc;
-	u32 cnt = rx_ring->count;
-	struct ice_rx_buf *buf;
-
-	for (int i = 0; i < nr_frags; i++) {
-		buf = &rx_ring->rx_buf[idx];
-		buf->act = act;
-
-		if (++idx == cnt)
-			idx = 0;
-	}
-
-	/* adjust pagecnt_bias on frags freed by XDP prog */
-	if (sinfo_frags < rx_ring->nr_frags && act == ICE_XDP_CONSUMED) {
-		u32 delta = rx_ring->nr_frags - sinfo_frags;
-
-		while (delta) {
-			if (idx == 0)
-				idx = cnt - 1;
-			else
-				idx--;
-			buf = &rx_ring->rx_buf[idx];
-			buf->pagecnt_bias--;
-			delta--;
-		}
-	}
-}
-
-/**
  * ice_test_staterr - tests bits in Rx descriptor status and error fields
  * @status_err_n: Rx descriptor status_error0 or status_error1 bits
  * @stat_err_bits: value to mask
@@ -97,6 +54,20 @@ ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag)
 }
 
 /**
+ * ice_build_tstamp_desc - build Tx time stamp descriptor
+ * @tx_desc: Tx LAN descriptor index
+ * @tstamp: time stamp
+ *
+ * Return: Tx time stamp descriptor
+ */
+static inline __le32
+ice_build_tstamp_desc(u16 tx_desc, u32 tstamp)
+{
+	return cpu_to_le32(FIELD_PREP(ICE_TXTIME_TX_DESC_IDX_M, tx_desc) |
+			   FIELD_PREP(ICE_TXTIME_STAMP_M, tstamp));
+}
+
+/**
  * ice_get_vlan_tci - get VLAN TCI from Rx flex descriptor
  * @rx_desc: Rx 32b flex descriptor with RXDID=2
  *
@@ -164,13 +135,4 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 void
 ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tci);
 
-static inline void
-ice_xdp_meta_set_desc(struct xdp_buff *xdp,
-		      union ice_32b_rx_flex_desc *eop_desc)
-{
-	struct ice_xdp_buff *xdp_ext = container_of(xdp, struct ice_xdp_buff,
-						    xdp_buff);
-
-	xdp_ext->eop_desc = eop_desc;
-}
 #endif /* !_ICE_TXRX_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index adb168860711..6a2ec8389a8f 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -17,7 +17,9 @@
 #include "ice_protocol_type.h"
 #include "ice_sbq_cmd.h"
 #include "ice_vlan_mode.h"
-#include "ice_fwlog.h"
+#include <linux/net/intel/libie/fwlog.h>
+#include <linux/wait.h>
+#include <net/dscp.h>
 
 static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc)
 {
@@ -291,8 +293,10 @@ struct ice_hw_common_caps {
 	u8 dcb;
 	u8 ieee_1588;
 	u8 rdma;
-	u8 roce_lag;
-	u8 sriov_lag;
+
+	bool roce_lag;
+	bool sriov_lag;
+	bool sriov_aa_lag;
 
 	bool nvm_update_pending_nvm;
 	bool nvm_update_pending_orom;
@@ -324,17 +328,17 @@ struct ice_hw_common_caps {
 #define ICE_TS_TMR_IDX_ASSOC_M		BIT(24)
 
 /* TIME_REF clock rate specification */
-enum ice_time_ref_freq {
-	ICE_TIME_REF_FREQ_25_000	= 0,
-	ICE_TIME_REF_FREQ_122_880	= 1,
-	ICE_TIME_REF_FREQ_125_000	= 2,
-	ICE_TIME_REF_FREQ_153_600	= 3,
-	ICE_TIME_REF_FREQ_156_250	= 4,
-	ICE_TIME_REF_FREQ_245_760	= 5,
+enum ice_tspll_freq {
+	ICE_TSPLL_FREQ_25_000	= 0,
+	ICE_TSPLL_FREQ_122_880	= 1,
+	ICE_TSPLL_FREQ_125_000	= 2,
+	ICE_TSPLL_FREQ_153_600	= 3,
+	ICE_TSPLL_FREQ_156_250	= 4,
+	ICE_TSPLL_FREQ_245_760	= 5,
 
-	NUM_ICE_TIME_REF_FREQ,
+	NUM_ICE_TSPLL_FREQ,
 
-	ICE_TIME_REF_FREQ_INVALID	= -1,
+	ICE_TSPLL_FREQ_INVALID	= -1,
 };
 
 /* Clock source specification */
@@ -347,7 +351,7 @@ enum ice_clk_src {
 
 struct ice_ts_func_info {
 	/* Function specific info */
-	enum ice_time_ref_freq time_ref;
+	enum ice_tspll_freq time_ref;
 	u8 clk_freq;
 	u8 clk_src;
 	u8 tmr_index_assoc;
@@ -368,6 +372,7 @@ struct ice_ts_func_info {
 #define ICE_TS_TMR1_ENA_M		BIT(26)
 #define ICE_TS_LL_TX_TS_READ_M		BIT(28)
 #define ICE_TS_LL_TX_TS_INT_READ_M	BIT(29)
+#define ICE_TS_LL_PHY_TMR_UPDATE_M	BIT(30)
 
 struct ice_ts_dev_info {
 	/* Device specific info */
@@ -382,6 +387,7 @@ struct ice_ts_dev_info {
 	u8 tmr1_ena;
 	u8 ts_ll_read;
 	u8 ts_ll_int_read;
+	u8 ll_phy_tmr_update;
 };
 
 #define ICE_NAC_TOPO_PRIMARY_M	BIT(0)
@@ -692,7 +698,6 @@ struct ice_dcb_app_priority_table {
 
 #define ICE_MAX_USER_PRIORITY	8
 #define ICE_DCBX_MAX_APPS	64
-#define ICE_DSCP_NUM_VAL	64
 #define ICE_LLDPDU_SIZE		1500
 #define ICE_TLV_STATUS_OPER	0x1
 #define ICE_TLV_STATUS_SYNC	0x2
@@ -715,9 +720,9 @@ struct ice_dcbx_cfg {
 	u8 pfc_mode;
 	struct ice_dcb_app_priority_table app[ICE_DCBX_MAX_APPS];
 	/* when DSCP mapping defined by user set its bit to 1 */
-	DECLARE_BITMAP(dscp_mapped, ICE_DSCP_NUM_VAL);
+	DECLARE_BITMAP(dscp_mapped, DSCP_MAX);
 	/* array holding DSCP -> UP/TC values for DSCP L3 QoS mode */
-	u8 dscp_map[ICE_DSCP_NUM_VAL];
+	u8 dscp_map[DSCP_MAX];
 	u8 dcbx_mode;
 #define ICE_DCBX_MODE_CEE	0x1
 #define ICE_DCBX_MODE_IEEE	0x2
@@ -848,26 +853,26 @@ struct ice_mbx_data {
 #define ICE_PORTS_PER_QUAD	4
 #define ICE_GET_QUAD_NUM(port) ((port) / ICE_PORTS_PER_QUAD)
 
+#define ATQBAL_FLAGS_INTR_IN_PROGRESS	BIT(0)
+
+struct ice_e810_params {
+	/* The wait queue lock also protects the low latency interface */
+	wait_queue_head_t atqbal_wq;
+	unsigned int atqbal_flags;
+};
+
 struct ice_eth56g_params {
 	u8 num_phys;
-	u8 phy_addr[2];
 	bool onestep_ena;
 	bool sfd_ena;
 	u32 peer_delay;
 };
 
 union ice_phy_params {
+	struct ice_e810_params e810;
 	struct ice_eth56g_params eth56g;
 };
 
-/* PHY model */
-enum ice_phy_model {
-	ICE_PHY_UNSUP = -1,
-	ICE_PHY_E810 = 1,
-	ICE_PHY_E82X,
-	ICE_PHY_ETH56G,
-};
-
 /* Global Link Topology */
 enum ice_global_link_topo {
 	ICE_LINK_TOPO_UP_TO_2_LINKS,
@@ -877,11 +882,9 @@ enum ice_global_link_topo {
 };
 
 struct ice_ptp_hw {
-	enum ice_phy_model phy_model;
 	union ice_phy_params phy;
 	u8 num_lports;
 	u8 ports_per_phy;
-	bool is_2x50g_muxed_topo;
 };
 
 /* Port hardware description */
@@ -945,9 +948,7 @@ struct ice_hw {
 	u8 fw_patch;		/* firmware patch version */
 	u32 fw_build;		/* firmware build number */
 
-	struct ice_fwlog_cfg fwlog_cfg;
-	bool fwlog_supported; /* does hardware support FW logging? */
-	struct ice_fwlog_ring fwlog_ring;
+	struct libie_fwlog fwlog;
 
 /* Device max aggregate bandwidths corresponding to the GL_PWR_MODE_CTL
  * register. Used for determining the ITR/INTRL granularity during
@@ -969,6 +970,7 @@ struct ice_hw {
 	u8 intrl_gran;
 
 	struct ice_ptp_hw ptp;
+	s8 lane_num;
 
 	/* Active package version (currently active) */
 	struct ice_pkg_ver active_pkg_ver;
@@ -1061,6 +1063,7 @@ struct ice_hw_port_stats {
 	u64 error_bytes;		/* errbc */
 	u64 mac_local_faults;		/* mlfc */
 	u64 mac_remote_faults;		/* mrfc */
+	u64 rx_len_errors;		/* rlec */
 	u64 link_xon_rx;		/* lxonrxc */
 	u64 link_xoff_rx;		/* lxoffrxc */
 	u64 link_xon_tx;		/* lxontxc */
@@ -1216,4 +1219,9 @@ struct ice_aq_get_set_rss_lut_params {
 #define ICE_FW_API_REPORT_DFLT_CFG_MIN		7
 #define ICE_FW_API_REPORT_DFLT_CFG_PATCH	3
 
+/* AQ API version for Health Status support */
+#define ICE_FW_API_HEALTH_REPORT_MAJ		1
+#define ICE_FW_API_HEALTH_REPORT_MIN		7
+#define ICE_FW_API_HEALTH_REPORT_PATCH		6
+
 #endif /* _ICE_TYPE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index c7c0c2f50c26..de9e81ccee66 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -5,7 +5,7 @@
 #include "ice.h"
 #include "ice_lib.h"
 #include "ice_fltr.h"
-#include "ice_virtchnl_allowlist.h"
+#include "virt/allowlist.h"
 
 /* Public functions which may be accessed by all driver files */
 
@@ -226,6 +226,7 @@ static void ice_vf_clear_counters(struct ice_vf *vf)
 		vsi->num_vlan = 0;
 
 	vf->num_mac = 0;
+	vf->num_mac_lldp = 0;
 	memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events));
 	memset(&vf->mdd_rx_events, 0, sizeof(vf->mdd_rx_events));
 }
@@ -858,16 +859,13 @@ static void ice_notify_vf_reset(struct ice_vf *vf)
 int ice_reset_vf(struct ice_vf *vf, u32 flags)
 {
 	struct ice_pf *pf = vf->pf;
-	struct ice_lag *lag;
 	struct ice_vsi *vsi;
-	u8 act_prt, pri_prt;
 	struct device *dev;
 	int err = 0;
+	u8 act_prt;
 	bool rsd;
 
 	dev = ice_pf_to_dev(pf);
-	act_prt = ICE_LAG_INVALID_PORT;
-	pri_prt = pf->hw.port_info->lport;
 
 	if (flags & ICE_VF_RESET_NOTIFY)
 		ice_notify_vf_reset(vf);
@@ -883,16 +881,8 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)
 	else
 		lockdep_assert_held(&vf->cfg_lock);
 
-	lag = pf->lag;
 	mutex_lock(&pf->lag_mutex);
-	if (lag && lag->bonded && lag->primary) {
-		act_prt = lag->active_port;
-		if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT &&
-		    lag->upper_netdev)
-			ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt);
-		else
-			act_prt = ICE_LAG_INVALID_PORT;
-	}
+	act_prt = ice_lag_prepare_vf_reset(pf->lag);
 
 	if (ice_is_vf_disabled(vf)) {
 		vsi = ice_get_vf_vsi(vf);
@@ -978,9 +968,7 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)
 	ice_reset_vf_mbx_cnt(vf);
 
 out_unlock:
-	if (lag && lag->bonded && lag->primary &&
-	    act_prt != ICE_LAG_INVALID_PORT)
-		ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt);
+	ice_lag_complete_vf_reset(pf->lag, act_prt);
 	mutex_unlock(&pf->lag_mutex);
 
 	if (flags & ICE_VF_RESET_LOCK)
@@ -1021,6 +1009,9 @@ void ice_initialize_vf_entry(struct ice_vf *vf)
 	vf->num_msix = vfs->num_msix_per;
 	vf->num_vf_qs = vfs->num_qps_per;
 
+	/* set default RSS hash configuration */
+	vf->rss_hashcfg = ICE_DEFAULT_RSS_HASHCFG;
+
 	/* ctrl_vsi_idx will be set to a valid value only when iAVF
 	 * creates its first fdir rule.
 	 */
@@ -1036,6 +1027,14 @@ void ice_initialize_vf_entry(struct ice_vf *vf)
 	mutex_init(&vf->cfg_lock);
 }
 
+void ice_deinitialize_vf_entry(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+
+	if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
+		list_del(&vf->mbx_info.list_entry);
+}
+
 /**
  * ice_dis_vf_qs - Disable the VF queues
  * @vf: pointer to the VF structure
@@ -1393,3 +1392,28 @@ struct ice_vsi *ice_get_vf_ctrl_vsi(struct ice_pf *pf, struct ice_vsi *vsi)
 	rcu_read_unlock();
 	return ctrl_vsi;
 }
+
+/**
+ * ice_vf_update_mac_lldp_num - update the VF's number of LLDP addresses
+ * @vf: a VF to add the address to
+ * @vsi: the corresponding VSI
+ * @incr: is the rule added or removed
+ */
+void ice_vf_update_mac_lldp_num(struct ice_vf *vf, struct ice_vsi *vsi,
+				bool incr)
+{
+	bool lldp_by_fw = test_bit(ICE_FLAG_FW_LLDP_AGENT, vsi->back->flags);
+	bool was_ena = ice_vf_is_lldp_ena(vf) && !lldp_by_fw;
+	bool is_ena;
+
+	if (WARN_ON(!vsi)) {
+		vf->num_mac_lldp = 0;
+		return;
+	}
+
+	vf->num_mac_lldp += incr ? 1 : -1;
+	is_ena = ice_vf_is_lldp_ena(vf) && !lldp_by_fw;
+
+	if (was_ena != is_ena)
+		ice_vsi_cfg_sw_lldp(vsi, false, is_ena);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
index 4261fe1c2bcd..7a9c75d1d07c 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
@@ -13,7 +13,7 @@
 #include <linux/avf/virtchnl.h>
 #include "ice_type.h"
 #include "ice_flow.h"
-#include "ice_virtchnl_fdir.h"
+#include "virt/fdir.h"
 #include "ice_vsi_vlan_ops.h"
 
 #define ICE_MAX_SRIOV_VFS		256
@@ -53,6 +53,46 @@ struct ice_mdd_vf_events {
 	u16 last_printed;
 };
 
+enum ice_hash_ip_ctx_type {
+	ICE_HASH_IP_CTX_IP = 0,
+	ICE_HASH_IP_CTX_IP_ESP,
+	ICE_HASH_IP_CTX_IP_UDP_ESP,
+	ICE_HASH_IP_CTX_IP_AH,
+	ICE_HASH_IP_CTX_IP_PFCP,
+	ICE_HASH_IP_CTX_IP_UDP,
+	ICE_HASH_IP_CTX_IP_TCP,
+	ICE_HASH_IP_CTX_IP_SCTP,
+	ICE_HASH_IP_CTX_MAX,
+};
+
+struct ice_vf_hash_ip_ctx {
+	struct ice_rss_hash_cfg ctx[ICE_HASH_IP_CTX_MAX];
+};
+
+enum ice_hash_gtpu_ctx_type {
+	ICE_HASH_GTPU_CTX_EH_IP = 0,
+	ICE_HASH_GTPU_CTX_EH_IP_UDP,
+	ICE_HASH_GTPU_CTX_EH_IP_TCP,
+	ICE_HASH_GTPU_CTX_UP_IP,
+	ICE_HASH_GTPU_CTX_UP_IP_UDP,
+	ICE_HASH_GTPU_CTX_UP_IP_TCP,
+	ICE_HASH_GTPU_CTX_DW_IP,
+	ICE_HASH_GTPU_CTX_DW_IP_UDP,
+	ICE_HASH_GTPU_CTX_DW_IP_TCP,
+	ICE_HASH_GTPU_CTX_MAX,
+};
+
+struct ice_vf_hash_gtpu_ctx {
+	struct ice_rss_hash_cfg ctx[ICE_HASH_GTPU_CTX_MAX];
+};
+
+struct ice_vf_hash_ctx {
+	struct ice_vf_hash_ip_ctx v4;
+	struct ice_vf_hash_ip_ctx v6;
+	struct ice_vf_hash_gtpu_ctx ipv4;
+	struct ice_vf_hash_gtpu_ctx ipv6;
+};
+
 /* Structure to store fdir fv entry */
 struct ice_fdir_prof_info {
 	struct ice_parser_profile prof;
@@ -66,6 +106,12 @@ struct ice_vf_qs_bw {
 	u8 tc;
 };
 
+/* Structure to store RSS field vector entry */
+struct ice_rss_prof_info {
+	struct ice_parser_profile prof;
+	bool symm;
+};
+
 /* VF operations */
 struct ice_vf_ops {
 	enum ice_disq_rst_src reset_type;
@@ -106,8 +152,9 @@ struct ice_vf {
 	u16 ctrl_vsi_idx;
 	struct ice_vf_fdir fdir;
 	struct ice_fdir_prof_info fdir_prof_info[ICE_MAX_PTGS];
-	/* first vector index of this VF in the PF space */
-	int first_vector_idx;
+	struct ice_rss_prof_info rss_prof_info[ICE_MAX_PTGS];
+	struct ice_vf_hash_ctx hash_ctx;
+	u64 rss_hashcfg;		/* RSS hash configuration */
 	struct ice_sw *vf_sw_id;	/* switch ID the VF VSIs connect to */
 	struct virtchnl_version_info vf_ver;
 	u32 driver_caps;		/* reported by VF driver */
@@ -124,13 +171,22 @@ struct ice_vf {
 	u8 spoofchk:1;
 	u8 link_forced:1;
 	u8 link_up:1;			/* only valid if VF link is forced */
+	u8 lldp_tx_ena:1;
+
+	u16 num_msix;			/* num of MSI-X configured on this VF */
+
+	u32 ptp_caps;
+
 	unsigned int min_tx_rate;	/* Minimum Tx bandwidth limit in Mbps */
 	unsigned int max_tx_rate;	/* Maximum Tx bandwidth limit in Mbps */
+	/* first vector index of this VF in the PF space */
+	int first_vector_idx;
 	DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS);	/* VF runtime states */
 
 	unsigned long vf_caps;		/* VF's adv. capabilities */
 	u8 num_req_qs;			/* num of queue pairs requested by VF */
 	u16 num_mac;
+	u16 num_mac_lldp;
 	u16 num_vf_qs;			/* num of queue configured per VF */
 	u8 vlan_strip_ena;		/* Outer and Inner VLAN strip enable */
 #define ICE_INNER_VLAN_STRIP_ENA	BIT(0)
@@ -146,7 +202,9 @@ struct ice_vf {
 	/* devlink port data */
 	struct devlink_port devlink_port;
 
-	u16 num_msix;			/* num of MSI-X configured on this VF */
+	u16 lldp_recipe_id;
+	u16 lldp_rule_id;
+
 	struct ice_vf_qs_bw qs_bw[ICE_MAX_RSS_QS_PER_VF];
 };
 
@@ -177,6 +235,11 @@ static inline u16 ice_vf_get_port_vlan_tpid(struct ice_vf *vf)
 	return vf->port_vlan_info.tpid;
 }
 
+static inline bool ice_vf_is_lldp_ena(struct ice_vf *vf)
+{
+	return vf->num_mac_lldp && vf->trusted;
+}
+
 /* VF Hash Table access functions
  *
  * These functions provide abstraction for interacting with the VF hash table.
@@ -224,6 +287,18 @@ static inline u16 ice_vf_get_port_vlan_tpid(struct ice_vf *vf)
 
 #ifdef CONFIG_PCI_IOV
 struct ice_vf *ice_get_vf_by_id(struct ice_pf *pf, u16 vf_id);
+
+static inline struct ice_vf *ice_get_vf_by_dev(struct ice_pf *pf,
+					       struct pci_dev *vf_dev)
+{
+	int vf_id = pci_iov_vf_id(vf_dev);
+
+	if (vf_id < 0)
+		return NULL;
+
+	return ice_get_vf_by_id(pf, pci_iov_vf_id(vf_dev));
+}
+
 void ice_put_vf(struct ice_vf *vf);
 bool ice_has_vfs(struct ice_pf *pf);
 u16 ice_get_num_vfs(struct ice_pf *pf);
@@ -242,12 +317,20 @@ ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m);
 int ice_reset_vf(struct ice_vf *vf, u32 flags);
 void ice_reset_all_vfs(struct ice_pf *pf);
 struct ice_vsi *ice_get_vf_ctrl_vsi(struct ice_pf *pf, struct ice_vsi *vsi);
+void ice_vf_update_mac_lldp_num(struct ice_vf *vf, struct ice_vsi *vsi,
+				bool incr);
 #else /* CONFIG_PCI_IOV */
 static inline struct ice_vf *ice_get_vf_by_id(struct ice_pf *pf, u16 vf_id)
 {
 	return NULL;
 }
 
+static inline struct ice_vf *ice_get_vf_by_dev(struct ice_pf *pf,
+					       struct pci_dev *vf_dev)
+{
+	return NULL;
+}
+
 static inline void ice_put_vf(struct ice_vf *vf)
 {
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
index 0c7e77c0a09f..5392b0404986 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
@@ -24,6 +24,7 @@
 #endif
 
 void ice_initialize_vf_entry(struct ice_vf *vf);
+void ice_deinitialize_vf_entry(struct ice_vf *vf);
 void ice_dis_vf_qs(struct ice_vf *vf);
 int ice_check_vf_init(struct ice_vf *vf);
 enum virtchnl_status_code ice_err_to_virt_err(int err);
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c
index 75c8113e58ee..7798a5d4bc9d 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c
@@ -23,18 +23,18 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval,
 		      u8 *msg, u16 msglen, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_pf_vf_msg *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_mbx_opc_send_msg_to_vf);
 
-	cmd = &desc.params.virt;
+	cmd = libie_aq_raw(&desc);
 	cmd->id = cpu_to_le32(vfid);
 
 	desc.cookie_high = cpu_to_le32(v_opcode);
 	desc.cookie_low = cpu_to_le32(v_retval);
 
 	if (msglen)
-		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+		desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_vlan_mode.c b/drivers/net/ethernet/intel/ice/ice_vlan_mode.c
index 1279c1ffe31c..fb526cb84776 100644
--- a/drivers/net/ethernet/intel/ice/ice_vlan_mode.c
+++ b/drivers/net/ethernet/intel/ice/ice_vlan_mode.c
@@ -63,7 +63,7 @@ static int
 ice_aq_get_vlan_mode(struct ice_hw *hw,
 		     struct ice_aqc_get_vlan_mode *get_params)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	if (!get_params)
 		return -EINVAL;
@@ -275,7 +275,7 @@ ice_aq_set_vlan_mode(struct ice_hw *hw,
 		     struct ice_aqc_set_vlan_mode *set_params)
 {
 	u8 rdma_packet, mng_vlan_prot_id;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	if (!set_params)
 		return -EINVAL;
@@ -295,7 +295,7 @@ ice_aq_set_vlan_mode(struct ice_hw *hw,
 
 	ice_fill_dflt_direct_cmd_desc(&desc,
 				      ice_aqc_opc_set_vlan_mode_parameters);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	return ice_aq_send_cmd(hw, &desc, set_params, sizeof(*set_params),
 			       NULL);
diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c
index 5291f2888ef8..ada78f83b3ac 100644
--- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c
@@ -113,7 +113,7 @@ static int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi)
 	err = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (err) {
 		dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN insert failed, err %d aq_err %s\n",
-			err, ice_aq_str(hw->adminq.sq_last_status));
+			err, libie_aq_str(hw->adminq.sq_last_status));
 		goto out;
 	}
 
@@ -169,7 +169,7 @@ static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena)
 	err = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (err) {
 		dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN strip failed, ena = %d err %d aq_err %s\n",
-			ena, err, ice_aq_str(hw->adminq.sq_last_status));
+			ena, err, libie_aq_str(hw->adminq.sq_last_status));
 		goto out;
 	}
 
@@ -258,7 +258,7 @@ static int __ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, u16 pvid_info)
 	ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (ret) {
 		dev_info(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %d aq_err %s\n",
-			 ret, ice_aq_str(hw->adminq.sq_last_status));
+			 ret, libie_aq_str(hw->adminq.sq_last_status));
 		goto out;
 	}
 
@@ -306,7 +306,7 @@ int ice_vsi_clear_inner_port_vlan(struct ice_vsi *vsi)
 	ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (ret)
 		dev_err(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %d aq_err %s\n",
-			ret, ice_aq_str(hw->adminq.sq_last_status));
+			ret, libie_aq_str(hw->adminq.sq_last_status));
 
 	kfree(ctxt);
 	return ret;
@@ -353,7 +353,7 @@ static int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena)
 	if (status) {
 		netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %s\n",
 			   ena ? "En" : "Dis", vsi->idx, vsi->vsi_num, status,
-			   ice_aq_str(pf->hw.adminq.sq_last_status));
+			   libie_aq_str(pf->hw.adminq.sq_last_status));
 		goto err_out;
 	}
 
@@ -497,7 +497,7 @@ int ice_vsi_ena_outer_stripping(struct ice_vsi *vsi, u16 tpid)
 	err = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (err)
 		dev_err(ice_pf_to_dev(vsi->back), "update VSI for enabling outer VLAN stripping failed, err %d aq_err %s\n",
-			err, ice_aq_str(hw->adminq.sq_last_status));
+			err, libie_aq_str(hw->adminq.sq_last_status));
 	else
 		vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags;
 
@@ -544,7 +544,7 @@ int ice_vsi_dis_outer_stripping(struct ice_vsi *vsi)
 	err = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (err)
 		dev_err(ice_pf_to_dev(vsi->back), "update VSI for disabling outer VLAN stripping failed, err %d aq_err %s\n",
-			err, ice_aq_str(hw->adminq.sq_last_status));
+			err, libie_aq_str(hw->adminq.sq_last_status));
 	else
 		vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags;
 
@@ -604,7 +604,7 @@ int ice_vsi_ena_outer_insertion(struct ice_vsi *vsi, u16 tpid)
 	err = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (err)
 		dev_err(ice_pf_to_dev(vsi->back), "update VSI for enabling outer VLAN insertion failed, err %d aq_err %s\n",
-			err, ice_aq_str(hw->adminq.sq_last_status));
+			err, libie_aq_str(hw->adminq.sq_last_status));
 	else
 		vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags;
 
@@ -654,7 +654,7 @@ int ice_vsi_dis_outer_insertion(struct ice_vsi *vsi)
 	err = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (err)
 		dev_err(ice_pf_to_dev(vsi->back), "update VSI for disabling outer VLAN insertion failed, err %d aq_err %s\n",
-			err, ice_aq_str(hw->adminq.sq_last_status));
+			err, libie_aq_str(hw->adminq.sq_last_status));
 	else
 		vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags;
 
@@ -720,7 +720,7 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid)
 	err = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (err) {
 		dev_err(ice_pf_to_dev(vsi->back), "update VSI for setting outer port based VLAN failed, err %d aq_err %s\n",
-			err, ice_aq_str(hw->adminq.sq_last_status));
+			err, libie_aq_str(hw->adminq.sq_last_status));
 	} else {
 		vsi->info.port_based_outer_vlan = ctxt->info.port_based_outer_vlan;
 		vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags;
@@ -782,7 +782,7 @@ int ice_vsi_clear_outer_port_vlan(struct ice_vsi *vsi)
 	err = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (err)
 		dev_err(ice_pf_to_dev(vsi->back), "update VSI for clearing outer port based VLAN failed, err %d aq_err %s\n",
-			err, ice_aq_str(hw->adminq.sq_last_status));
+			err, libie_aq_str(hw->adminq.sq_last_status));
 
 	kfree(ctxt);
 	return err;
@@ -830,7 +830,7 @@ int ice_vsi_clear_port_vlan(struct ice_vsi *vsi)
 	err = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (err) {
 		dev_err(ice_pf_to_dev(vsi->back), "update VSI for clearing port based VLAN failed, err %d aq_err %s\n",
-			err, ice_aq_str(hw->adminq.sq_last_status));
+			err, libie_aq_str(hw->adminq.sq_last_status));
 	} else {
 		vsi->info.port_based_outer_vlan =
 			ctxt->info.port_based_outer_vlan;
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 8975d2971bc3..989ff1fd9110 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -2,6 +2,8 @@
 /* Copyright (c) 2019, Intel Corporation. */
 
 #include <linux/bpf_trace.h>
+#include <linux/unroll.h>
+#include <net/libeth/xdp.h>
 #include <net/xdp_sock_drv.h>
 #include <net/xdp.h>
 #include "ice.h"
@@ -18,52 +20,12 @@ static struct xdp_buff **ice_xdp_buf(struct ice_rx_ring *rx_ring, u32 idx)
 }
 
 /**
- * ice_qp_reset_stats - Resets all stats for rings of given index
- * @vsi: VSI that contains rings of interest
- * @q_idx: ring index in array
- */
-static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
-{
-	struct ice_vsi_stats *vsi_stat;
-	struct ice_pf *pf;
-
-	pf = vsi->back;
-	if (!pf->vsi_stats)
-		return;
-
-	vsi_stat = pf->vsi_stats[vsi->idx];
-	if (!vsi_stat)
-		return;
-
-	memset(&vsi_stat->rx_ring_stats[q_idx]->rx_stats, 0,
-	       sizeof(vsi_stat->rx_ring_stats[q_idx]->rx_stats));
-	memset(&vsi_stat->tx_ring_stats[q_idx]->stats, 0,
-	       sizeof(vsi_stat->tx_ring_stats[q_idx]->stats));
-	if (vsi->xdp_rings)
-		memset(&vsi->xdp_rings[q_idx]->ring_stats->stats, 0,
-		       sizeof(vsi->xdp_rings[q_idx]->ring_stats->stats));
-}
-
-/**
- * ice_qp_clean_rings - Cleans all the rings of a given index
- * @vsi: VSI that contains rings of interest
- * @q_idx: ring index in array
- */
-static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
-{
-	ice_clean_tx_ring(vsi->tx_rings[q_idx]);
-	if (vsi->xdp_rings)
-		ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
-	ice_clean_rx_ring(vsi->rx_rings[q_idx]);
-}
-
-/**
  * ice_qvec_toggle_napi - Enables/disables NAPI for a given q_vector
  * @vsi: VSI that has netdev
  * @q_vector: q_vector that has NAPI context
  * @enable: true for enable, false for disable
  */
-static void
+void
 ice_qvec_toggle_napi(struct ice_vsi *vsi, struct ice_q_vector *q_vector,
 		     bool enable)
 {
@@ -82,7 +44,7 @@ ice_qvec_toggle_napi(struct ice_vsi *vsi, struct ice_q_vector *q_vector,
  * @rx_ring: Rx ring that will have its IRQ disabled
  * @q_vector: queue vector
  */
-static void
+void
 ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring,
 		 struct ice_q_vector *q_vector)
 {
@@ -112,7 +74,7 @@ ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring,
  * @q_vector: queue vector
  * @qid: queue index
  */
-static void
+void
 ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector, u16 qid)
 {
 	u16 reg_idx = q_vector->reg_idx;
@@ -142,7 +104,7 @@ ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector, u16 qid)
  * @vsi: the VSI that contains queue vector
  * @q_vector: queue vector
  */
-static void ice_qvec_ena_irq(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+void ice_qvec_ena_irq(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
 {
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
@@ -153,111 +115,6 @@ static void ice_qvec_ena_irq(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
 }
 
 /**
- * ice_qp_dis - Disables a queue pair
- * @vsi: VSI of interest
- * @q_idx: ring index in array
- *
- * Returns 0 on success, negative on failure.
- */
-static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
-{
-	struct ice_txq_meta txq_meta = { };
-	struct ice_q_vector *q_vector;
-	struct ice_tx_ring *tx_ring;
-	struct ice_rx_ring *rx_ring;
-	int fail = 0;
-	int err;
-
-	if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq)
-		return -EINVAL;
-
-	tx_ring = vsi->tx_rings[q_idx];
-	rx_ring = vsi->rx_rings[q_idx];
-	q_vector = rx_ring->q_vector;
-
-	synchronize_net();
-	netif_carrier_off(vsi->netdev);
-	netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
-
-	ice_qvec_dis_irq(vsi, rx_ring, q_vector);
-	ice_qvec_toggle_napi(vsi, q_vector, false);
-
-	ice_fill_txq_meta(vsi, tx_ring, &txq_meta);
-	err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta);
-	if (!fail)
-		fail = err;
-	if (vsi->xdp_rings) {
-		struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
-
-		memset(&txq_meta, 0, sizeof(txq_meta));
-		ice_fill_txq_meta(vsi, xdp_ring, &txq_meta);
-		err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, xdp_ring,
-					   &txq_meta);
-		if (!fail)
-			fail = err;
-	}
-
-	ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, false);
-	ice_qp_clean_rings(vsi, q_idx);
-	ice_qp_reset_stats(vsi, q_idx);
-
-	return fail;
-}
-
-/**
- * ice_qp_ena - Enables a queue pair
- * @vsi: VSI of interest
- * @q_idx: ring index in array
- *
- * Returns 0 on success, negative on failure.
- */
-static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
-{
-	struct ice_q_vector *q_vector;
-	int fail = 0;
-	bool link_up;
-	int err;
-
-	err = ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx);
-	if (!fail)
-		fail = err;
-
-	if (ice_is_xdp_ena_vsi(vsi)) {
-		struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
-
-		err = ice_vsi_cfg_single_txq(vsi, vsi->xdp_rings, q_idx);
-		if (!fail)
-			fail = err;
-		ice_set_ring_xdp(xdp_ring);
-		ice_tx_xsk_pool(vsi, q_idx);
-	}
-
-	err = ice_vsi_cfg_single_rxq(vsi, q_idx);
-	if (!fail)
-		fail = err;
-
-	q_vector = vsi->rx_rings[q_idx]->q_vector;
-	ice_qvec_cfg_msix(vsi, q_vector, q_idx);
-
-	err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true);
-	if (!fail)
-		fail = err;
-
-	ice_qvec_toggle_napi(vsi, q_vector, true);
-	ice_qvec_ena_irq(vsi, q_vector);
-
-	/* make sure NAPI sees updated ice_{t,x}_ring::xsk_pool */
-	synchronize_net();
-	ice_get_link_status(vsi->port_info, &link_up);
-	if (link_up) {
-		netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
-		netif_carrier_on(vsi->netdev);
-	}
-
-	return fail;
-}
-
-/**
  * ice_xsk_pool_disable - disable a buffer pool region
  * @vsi: Current VSI
  * @qid: queue ID
@@ -313,50 +170,18 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
  * If allocation was successful, substitute buffer with allocated one.
  * Returns 0 on success, negative on failure
  */
-static int
+int
 ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present)
 {
-	size_t elem_size = pool_present ? sizeof(*rx_ring->xdp_buf) :
-					  sizeof(*rx_ring->rx_buf);
-	void *sw_ring = kcalloc(rx_ring->count, elem_size, GFP_KERNEL);
-
-	if (!sw_ring)
-		return -ENOMEM;
-
 	if (pool_present) {
-		kfree(rx_ring->rx_buf);
-		rx_ring->rx_buf = NULL;
-		rx_ring->xdp_buf = sw_ring;
+		rx_ring->xdp_buf = kcalloc(rx_ring->count,
+					   sizeof(*rx_ring->xdp_buf),
+					   GFP_KERNEL);
+		if (!rx_ring->xdp_buf)
+			return -ENOMEM;
 	} else {
 		kfree(rx_ring->xdp_buf);
 		rx_ring->xdp_buf = NULL;
-		rx_ring->rx_buf = sw_ring;
-	}
-
-	return 0;
-}
-
-/**
- * ice_realloc_zc_buf - reallocate XDP ZC queue pairs
- * @vsi: Current VSI
- * @zc: is zero copy set
- *
- * Reallocate buffer for rx_rings that might be used by XSK.
- * XDP requires more memory, than rx_buf provides.
- * Returns 0 on success, negative on failure
- */
-int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc)
-{
-	struct ice_rx_ring *rx_ring;
-	uint i;
-
-	ice_for_each_rxq(vsi, i) {
-		rx_ring = vsi->rx_rings[i];
-		if (!rx_ring->xsk_pool)
-			continue;
-
-		if (ice_realloc_rx_xdp_bufs(rx_ring, zc))
-			return -ENOMEM;
 	}
 
 	return 0;
@@ -372,6 +197,7 @@ int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc)
  */
 int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 {
+	struct ice_rx_ring *rx_ring = vsi->rx_rings[qid];
 	bool if_running, pool_present = !!pool;
 	int ret = 0, pool_failure = 0;
 
@@ -385,8 +211,6 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 		     ice_is_xdp_ena_vsi(vsi);
 
 	if (if_running) {
-		struct ice_rx_ring *rx_ring = vsi->rx_rings[qid];
-
 		ret = ice_qp_dis(vsi, qid);
 		if (ret) {
 			netdev_err(vsi->netdev, "ice_qp_dis error = %d\n", ret);
@@ -447,11 +271,6 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
 		rx_desc->read.pkt_addr = cpu_to_le64(dma);
 		rx_desc->wb.status_error0 = 0;
 
-		/* Put private info that changes on a per-packet basis
-		 * into xdp_buff_xsk->cb.
-		 */
-		ice_xdp_meta_set_desc(*xdp, rx_desc);
-
 		rx_desc++;
 		xdp++;
 	}
@@ -537,69 +356,6 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
 }
 
 /**
- * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer
- * @rx_ring: Rx ring
- * @xdp: Pointer to XDP buffer
- *
- * This function allocates a new skb from a zero-copy Rx buffer.
- *
- * Returns the skb on success, NULL on failure.
- */
-static struct sk_buff *
-ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
-{
-	unsigned int totalsize = xdp->data_end - xdp->data_meta;
-	unsigned int metasize = xdp->data - xdp->data_meta;
-	struct skb_shared_info *sinfo = NULL;
-	struct sk_buff *skb;
-	u32 nr_frags = 0;
-
-	if (unlikely(xdp_buff_has_frags(xdp))) {
-		sinfo = xdp_get_shared_info_from_buff(xdp);
-		nr_frags = sinfo->nr_frags;
-	}
-	net_prefetch(xdp->data_meta);
-
-	skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize);
-	if (unlikely(!skb))
-		return NULL;
-
-	memcpy(__skb_put(skb, totalsize), xdp->data_meta,
-	       ALIGN(totalsize, sizeof(long)));
-
-	if (metasize) {
-		skb_metadata_set(skb, metasize);
-		__skb_pull(skb, metasize);
-	}
-
-	if (likely(!xdp_buff_has_frags(xdp)))
-		goto out;
-
-	for (int i = 0; i < nr_frags; i++) {
-		struct skb_shared_info *skinfo = skb_shinfo(skb);
-		skb_frag_t *frag = &sinfo->frags[i];
-		struct page *page;
-		void *addr;
-
-		page = dev_alloc_page();
-		if (!page) {
-			dev_kfree_skb(skb);
-			return NULL;
-		}
-		addr = page_to_virt(page);
-
-		memcpy(addr, skb_frag_page(frag), skb_frag_size(frag));
-
-		__skb_fill_page_desc_noacc(skinfo, skinfo->nr_frags++,
-					   addr, 0, skb_frag_size(frag));
-	}
-
-out:
-	xsk_buff_free(xdp);
-	return skb;
-}
-
-/**
  * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
  * @xdp_ring: XDP Tx ring
  * @xsk_pool: AF_XDP buffer pool pointer
@@ -813,10 +569,10 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
 			struct xsk_buff_pool *xsk_pool,
 			int budget)
 {
+	struct xdp_buff *first = (struct xdp_buff *)rx_ring->xsk;
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	u32 ntc = rx_ring->next_to_clean;
 	u32 ntu = rx_ring->next_to_use;
-	struct xdp_buff *first = NULL;
 	struct ice_tx_ring *xdp_ring;
 	unsigned int xdp_xmit = 0;
 	struct bpf_prog *xdp_prog;
@@ -830,9 +586,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	xdp_ring = rx_ring->xdp_ring;
 
-	if (ntc != rx_ring->first_desc)
-		first = *ice_xdp_buf(rx_ring, rx_ring->first_desc);
-
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
 		unsigned int size, xdp_res = 0;
@@ -868,15 +621,17 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
 			first = xdp;
 		} else if (likely(size) && !xsk_buff_add_frag(first, xdp)) {
 			xsk_buff_free(first);
-			break;
+			first = NULL;
 		}
 
 		if (++ntc == cnt)
 			ntc = 0;
 
-		if (ice_is_non_eop(rx_ring, rx_desc))
+		if (ice_is_non_eop(rx_ring, rx_desc) || unlikely(!first))
 			continue;
 
+		((struct libeth_xdp_buff *)first)->desc = rx_desc;
+
 		xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring,
 					 xsk_pool);
 		if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) {
@@ -884,7 +639,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
 		} else if (xdp_res == ICE_XDP_EXIT) {
 			failure = true;
 			first = NULL;
-			rx_ring->first_desc = ntc;
 			break;
 		} else if (xdp_res == ICE_XDP_CONSUMED) {
 			xsk_buff_free(first);
@@ -896,24 +650,20 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
 		total_rx_packets++;
 
 		first = NULL;
-		rx_ring->first_desc = ntc;
 		continue;
 
 construct_skb:
 		/* XDP_PASS path */
-		skb = ice_construct_skb_zc(rx_ring, first);
+		skb = xdp_build_skb_from_zc(first);
 		if (!skb) {
+			xsk_buff_free(first);
+			first = NULL;
+
 			rx_ring->ring_stats->rx_stats.alloc_buf_failed++;
-			break;
+			continue;
 		}
 
 		first = NULL;
-		rx_ring->first_desc = ntc;
-
-		if (eth_skb_pad(skb)) {
-			skb = NULL;
-			continue;
-		}
 
 		total_rx_bytes += skb->len;
 		total_rx_packets++;
@@ -925,7 +675,9 @@ construct_skb:
 	}
 
 	rx_ring->next_to_clean = ntc;
-	entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring);
+	rx_ring->xsk = (struct libeth_xdp_buff *)first;
+
+	entries_to_alloc = ICE_DESC_UNUSED(rx_ring);
 	if (entries_to_alloc > ICE_RING_QUARTER(rx_ring))
 		failure |= !ice_alloc_rx_bufs_zc(rx_ring, xsk_pool,
 						 entries_to_alloc);
@@ -989,7 +741,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring,
 	struct ice_tx_desc *tx_desc;
 	u32 i;
 
-	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+	unrolled_count(PKTS_PER_BATCH)
+	for (i = 0; i < PKTS_PER_BATCH; i++) {
 		dma_addr_t dma;
 
 		dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h
index 45adeb513253..5275fcedc9e1 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.h
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.h
@@ -7,14 +7,6 @@
 
 #define PKTS_PER_BATCH 8
 
-#ifdef __clang__
-#define loop_unrolled_for _Pragma("clang loop unroll_count(8)") for
-#elif __GNUC__ >= 8
-#define loop_unrolled_for _Pragma("GCC unroll 8") for
-#else
-#define loop_unrolled_for for
-#endif
-
 struct ice_vsi;
 
 #ifdef CONFIG_XDP_SOCKETS
@@ -30,7 +22,14 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi);
 void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring);
 void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring);
 bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool);
-int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc);
+int ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present);
+void ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector,
+		       u16 qid);
+void ice_qvec_toggle_napi(struct ice_vsi *vsi, struct ice_q_vector *q_vector,
+			  bool enable);
+void ice_qvec_ena_irq(struct ice_vsi *vsi, struct ice_q_vector *q_vector);
+void ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring,
+		      struct ice_q_vector *q_vector);
 #else
 static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring,
 			       struct xsk_buff_pool __always_unused *xsk_pool)
@@ -78,10 +77,25 @@ static inline void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { }
 static inline void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring) { }
 
 static inline int
-ice_realloc_zc_buf(struct ice_vsi __always_unused *vsi,
-		   bool __always_unused zc)
+ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring,
+			bool __always_unused pool_present)
 {
 	return 0;
 }
+
+static inline void
+ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector,
+		  u16 qid) { }
+
+static inline void
+ice_qvec_toggle_napi(struct ice_vsi *vsi, struct ice_q_vector *q_vector,
+		     bool enable) { }
+
+static inline void
+ice_qvec_ena_irq(struct ice_vsi *vsi, struct ice_q_vector *q_vector) { }
+
+static inline void
+ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring,
+		 struct ice_q_vector *q_vector) { }
 #endif /* CONFIG_XDP_SOCKETS */
 #endif /* !_ICE_XSK_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/virt/allowlist.c
index c105a82ee136..a07efec19c45 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
+++ b/drivers/net/ethernet/intel/ice/virt/allowlist.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (C) 2021, Intel Corporation. */
 
-#include "ice_virtchnl_allowlist.h"
+#include "allowlist.h"
 
 /* Purpose of this file is to share functionality to allowlist or denylist
  * opcodes used in PF <-> VF communication. Group of opcodes:
@@ -65,7 +65,7 @@ static const u32 vlan_v2_allowlist_opcodes[] = {
 /* VIRTCHNL_VF_OFFLOAD_RSS_PF */
 static const u32 rss_pf_allowlist_opcodes[] = {
 	VIRTCHNL_OP_CONFIG_RSS_KEY, VIRTCHNL_OP_CONFIG_RSS_LUT,
-	VIRTCHNL_OP_GET_RSS_HENA_CAPS, VIRTCHNL_OP_SET_RSS_HENA,
+	VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS, VIRTCHNL_OP_SET_RSS_HASHCFG,
 	VIRTCHNL_OP_CONFIG_RSS_HFUNC,
 };
 
@@ -84,6 +84,12 @@ static const u32 fdir_pf_allowlist_opcodes[] = {
 	VIRTCHNL_OP_ADD_FDIR_FILTER, VIRTCHNL_OP_DEL_FDIR_FILTER,
 };
 
+/* VIRTCHNL_VF_CAP_PTP */
+static const u32 ptp_allowlist_opcodes[] = {
+	VIRTCHNL_OP_1588_PTP_GET_CAPS,
+	VIRTCHNL_OP_1588_PTP_GET_TIME,
+};
+
 static const u32 tc_allowlist_opcodes[] = {
 	VIRTCHNL_OP_GET_QOS_CAPS, VIRTCHNL_OP_CONFIG_QUEUE_BW,
 	VIRTCHNL_OP_CONFIG_QUANTA,
@@ -110,6 +116,7 @@ static const struct allowlist_opcode_info allowlist_opcodes[] = {
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes),
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN_V2, vlan_v2_allowlist_opcodes),
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_QOS, tc_allowlist_opcodes),
+	ALLOW_ITEM(VIRTCHNL_VF_CAP_PTP, ptp_allowlist_opcodes),
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.h b/drivers/net/ethernet/intel/ice/virt/allowlist.h
index d3ae86ded219..d3ae86ded219 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.h
+++ b/drivers/net/ethernet/intel/ice/virt/allowlist.h
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/virt/fdir.c
index 14e3f0f89c78..ae83c3914e29 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/virt/fdir.c
@@ -832,21 +832,27 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf,
 		      struct virtchnl_proto_hdrs *proto,
 		      struct virtchnl_fdir_fltr_conf *conf)
 {
-	u8 *pkt_buf, *msk_buf __free(kfree);
+	u8 *pkt_buf, *msk_buf __free(kfree) = NULL;
 	struct ice_parser_result rslt;
 	struct ice_pf *pf = vf->pf;
+	u16 pkt_len, udp_port = 0;
 	struct ice_parser *psr;
 	int status = -ENOMEM;
 	struct ice_hw *hw;
-	u16 udp_port = 0;
 
-	pkt_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL);
-	msk_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL);
+	pkt_len = proto->raw.pkt_len;
+
+	if (!pkt_len || pkt_len > VIRTCHNL_MAX_SIZE_RAW_PACKET)
+		return -EINVAL;
+
+	pkt_buf = kzalloc(pkt_len, GFP_KERNEL);
+	msk_buf = kzalloc(pkt_len, GFP_KERNEL);
+
 	if (!pkt_buf || !msk_buf)
 		goto err_mem_alloc;
 
-	memcpy(pkt_buf, proto->raw.spec, proto->raw.pkt_len);
-	memcpy(msk_buf, proto->raw.mask, proto->raw.pkt_len);
+	memcpy(pkt_buf, proto->raw.spec, pkt_len);
+	memcpy(msk_buf, proto->raw.mask, pkt_len);
 
 	hw = &pf->hw;
 
@@ -862,7 +868,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf,
 	if (ice_get_open_tunnel_port(hw, &udp_port, TNL_VXLAN))
 		ice_parser_vxlan_tunnel_set(psr, udp_port, true);
 
-	status = ice_parser_run(psr, pkt_buf, proto->raw.pkt_len, &rslt);
+	status = ice_parser_run(psr, pkt_buf, pkt_len, &rslt);
 	if (status)
 		goto err_parser_destroy;
 
@@ -876,7 +882,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf,
 	}
 
 	status = ice_parser_profile_init(&rslt, pkt_buf, msk_buf,
-					 proto->raw.pkt_len, ICE_BLK_FD,
+					 pkt_len, ICE_BLK_FD,
 					 conf->prof);
 	if (status)
 		goto err_parser_profile_init;
@@ -885,7 +891,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf,
 		ice_parser_profile_dump(hw, conf->prof);
 
 	/* Store raw flow info into @conf */
-	conf->pkt_len = proto->raw.pkt_len;
+	conf->pkt_len = pkt_len;
 	conf->pkt_buf = pkt_buf;
 	conf->parser_ena = true;
 
@@ -1444,7 +1450,8 @@ err_free_pkt:
  */
 static void ice_vf_fdir_timer(struct timer_list *t)
 {
-	struct ice_vf_fdir_ctx *ctx_irq = from_timer(ctx_irq, t, rx_tmr);
+	struct ice_vf_fdir_ctx *ctx_irq = timer_container_of(ctx_irq, t,
+							     rx_tmr);
 	struct ice_vf_fdir_ctx *ctx_done;
 	struct ice_vf_fdir *fdir;
 	unsigned long flags;
@@ -1515,7 +1522,7 @@ ice_vc_fdir_irq_handler(struct ice_vsi *ctrl_vsi,
 	memcpy(&ctx_done->rx_desc, rx_desc, sizeof(*rx_desc));
 	spin_unlock_irqrestore(&fdir->ctx_lock, flags);
 
-	ret = del_timer(&ctx_irq->rx_tmr);
+	ret = timer_delete(&ctx_irq->rx_tmr);
 	if (!ret)
 		dev_err(dev, "VF %d: Unexpected inactive timer!\n", vf->vf_id);
 
@@ -1910,7 +1917,7 @@ static void ice_vc_fdir_clear_irq_ctx(struct ice_vf *vf)
 	struct ice_vf_fdir_ctx *ctx = &vf->fdir.ctx_irq;
 	unsigned long flags;
 
-	del_timer(&ctx->rx_tmr);
+	timer_delete(&ctx->rx_tmr);
 	spin_lock_irqsave(&vf->fdir.ctx_lock, flags);
 	ctx->flags &= ~ICE_VF_FDIR_CTX_VALID;
 	spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags);
@@ -2091,6 +2098,11 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
 	pf = vf->pf;
 	dev = ice_pf_to_dev(pf);
 	vf_vsi = ice_get_vf_vsi(vf);
+	if (!vf_vsi) {
+		dev_err(dev, "Can not get FDIR vf_vsi for VF %u\n", vf->vf_id);
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err_exit;
+	}
 
 #define ICE_VF_MAX_FDIR_FILTERS	128
 	if (!ice_fdir_num_avail_fltr(&pf->hw, vf_vsi) ||
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h b/drivers/net/ethernet/intel/ice/virt/fdir.h
index ac6dcab454b4..ac6dcab454b4 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h
+++ b/drivers/net/ethernet/intel/ice/virt/fdir.h
diff --git a/drivers/net/ethernet/intel/ice/virt/queues.c b/drivers/net/ethernet/intel/ice/virt/queues.c
new file mode 100644
index 000000000000..f73d5a3e83d4
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/virt/queues.c
@@ -0,0 +1,975 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2022, Intel Corporation. */
+
+#include "virtchnl.h"
+#include "queues.h"
+#include "ice_vf_lib_private.h"
+#include "ice.h"
+#include "ice_base.h"
+#include "ice_lib.h"
+
+/**
+ * ice_vc_get_max_frame_size - get max frame size allowed for VF
+ * @vf: VF used to determine max frame size
+ *
+ * Max frame size is determined based on the current port's max frame size and
+ * whether a port VLAN is configured on this VF. The VF is not aware whether
+ * it's in a port VLAN so the PF needs to account for this in max frame size
+ * checks and sending the max frame size to the VF.
+ */
+u16 ice_vc_get_max_frame_size(struct ice_vf *vf)
+{
+	struct ice_port_info *pi = ice_vf_get_port_info(vf);
+	u16 max_frame_size;
+
+	max_frame_size = pi->phy.link_info.max_frame_size;
+
+	if (ice_vf_is_port_vlan_ena(vf))
+		max_frame_size -= VLAN_HLEN;
+
+	return max_frame_size;
+}
+
+/**
+ * ice_vc_isvalid_q_id
+ * @vsi: VSI to check queue ID against
+ * @qid: VSI relative queue ID
+ *
+ * check for the valid queue ID
+ */
+static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u16 qid)
+{
+	/* allocated Tx and Rx queues should be always equal for VF VSI */
+	return qid < vsi->alloc_txq;
+}
+
+/**
+ * ice_vc_isvalid_ring_len
+ * @ring_len: length of ring
+ *
+ * check for the valid ring count, should be multiple of ICE_REQ_DESC_MULTIPLE
+ * or zero
+ */
+static bool ice_vc_isvalid_ring_len(u16 ring_len)
+{
+	return ring_len == 0 ||
+	       (ring_len >= ICE_MIN_NUM_DESC &&
+		ring_len <= ICE_MAX_NUM_DESC_E810 &&
+		!(ring_len % ICE_REQ_DESC_MULTIPLE));
+}
+
+/**
+ * ice_vf_cfg_qs_bw - Configure per queue bandwidth
+ * @vf: pointer to the VF info
+ * @num_queues: number of queues to be configured
+ *
+ * Configure per queue bandwidth.
+ *
+ * Return: 0 on success or negative error value.
+ */
+static int ice_vf_cfg_qs_bw(struct ice_vf *vf, u16 num_queues)
+{
+	struct ice_hw *hw = &vf->pf->hw;
+	struct ice_vsi *vsi;
+	int ret;
+	u16 i;
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi)
+		return -EINVAL;
+
+	for (i = 0; i < num_queues; i++) {
+		u32 p_rate, min_rate;
+		u8 tc;
+
+		p_rate = vf->qs_bw[i].peak;
+		min_rate = vf->qs_bw[i].committed;
+		tc = vf->qs_bw[i].tc;
+		if (p_rate)
+			ret = ice_cfg_q_bw_lmt(hw->port_info, vsi->idx, tc,
+					       vf->qs_bw[i].queue_id,
+					       ICE_MAX_BW, p_rate);
+		else
+			ret = ice_cfg_q_bw_dflt_lmt(hw->port_info, vsi->idx, tc,
+						    vf->qs_bw[i].queue_id,
+						    ICE_MAX_BW);
+		if (ret)
+			return ret;
+
+		if (min_rate)
+			ret = ice_cfg_q_bw_lmt(hw->port_info, vsi->idx, tc,
+					       vf->qs_bw[i].queue_id,
+					       ICE_MIN_BW, min_rate);
+		else
+			ret = ice_cfg_q_bw_dflt_lmt(hw->port_info, vsi->idx, tc,
+						    vf->qs_bw[i].queue_id,
+						    ICE_MIN_BW);
+
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_vf_cfg_q_quanta_profile - Configure quanta profile
+ * @vf: pointer to the VF info
+ * @quanta_prof_idx: pointer to the quanta profile index
+ * @quanta_size: quanta size to be set
+ *
+ * This function chooses available quanta profile and configures the register.
+ * The quanta profile is evenly divided by the number of device ports, and then
+ * available to the specific PF and VFs. The first profile for each PF is a
+ * reserved default profile. Only quanta size of the rest unused profile can be
+ * modified.
+ *
+ * Return: 0 on success or negative error value.
+ */
+static int ice_vf_cfg_q_quanta_profile(struct ice_vf *vf, u16 quanta_size,
+				       u16 *quanta_prof_idx)
+{
+	const u16 n_desc = calc_quanta_desc(quanta_size);
+	struct ice_hw *hw = &vf->pf->hw;
+	const u16 n_cmd = 2 * n_desc;
+	struct ice_pf *pf = vf->pf;
+	u16 per_pf, begin_id;
+	u8 n_used;
+	u32 reg;
+
+	begin_id = (GLCOMM_QUANTA_PROF_MAX_INDEX + 1) / hw->dev_caps.num_funcs *
+		   hw->logical_pf_id;
+
+	if (quanta_size == ICE_DFLT_QUANTA) {
+		*quanta_prof_idx = begin_id;
+	} else {
+		per_pf = (GLCOMM_QUANTA_PROF_MAX_INDEX + 1) /
+			 hw->dev_caps.num_funcs;
+		n_used = pf->num_quanta_prof_used;
+		if (n_used < per_pf) {
+			*quanta_prof_idx = begin_id + 1 + n_used;
+			pf->num_quanta_prof_used++;
+		} else {
+			return -EINVAL;
+		}
+	}
+
+	reg = FIELD_PREP(GLCOMM_QUANTA_PROF_QUANTA_SIZE_M, quanta_size) |
+	      FIELD_PREP(GLCOMM_QUANTA_PROF_MAX_CMD_M, n_cmd) |
+	      FIELD_PREP(GLCOMM_QUANTA_PROF_MAX_DESC_M, n_desc);
+	wr32(hw, GLCOMM_QUANTA_PROF(*quanta_prof_idx), reg);
+
+	return 0;
+}
+
+/**
+ * ice_vc_validate_vqs_bitmaps - validate Rx/Tx queue bitmaps from VIRTCHNL
+ * @vqs: virtchnl_queue_select structure containing bitmaps to validate
+ *
+ * Return true on successful validation, else false
+ */
+static bool ice_vc_validate_vqs_bitmaps(struct virtchnl_queue_select *vqs)
+{
+	if ((!vqs->rx_queues && !vqs->tx_queues) ||
+	    vqs->rx_queues >= BIT(ICE_MAX_RSS_QS_PER_VF) ||
+	    vqs->tx_queues >= BIT(ICE_MAX_RSS_QS_PER_VF))
+		return false;
+
+	return true;
+}
+
+/**
+ * ice_vf_ena_txq_interrupt - enable Tx queue interrupt via QINT_TQCTL
+ * @vsi: VSI of the VF to configure
+ * @q_idx: VF queue index used to determine the queue in the PF's space
+ */
+void ice_vf_ena_txq_interrupt(struct ice_vsi *vsi, u32 q_idx)
+{
+	struct ice_hw *hw = &vsi->back->hw;
+	u32 pfq = vsi->txq_map[q_idx];
+	u32 reg;
+
+	reg = rd32(hw, QINT_TQCTL(pfq));
+
+	/* MSI-X index 0 in the VF's space is always for the OICR, which means
+	 * this is most likely a poll mode VF driver, so don't enable an
+	 * interrupt that was never configured via VIRTCHNL_OP_CONFIG_IRQ_MAP
+	 */
+	if (!(reg & QINT_TQCTL_MSIX_INDX_M))
+		return;
+
+	wr32(hw, QINT_TQCTL(pfq), reg | QINT_TQCTL_CAUSE_ENA_M);
+}
+
+/**
+ * ice_vf_ena_rxq_interrupt - enable Tx queue interrupt via QINT_RQCTL
+ * @vsi: VSI of the VF to configure
+ * @q_idx: VF queue index used to determine the queue in the PF's space
+ */
+void ice_vf_ena_rxq_interrupt(struct ice_vsi *vsi, u32 q_idx)
+{
+	struct ice_hw *hw = &vsi->back->hw;
+	u32 pfq = vsi->rxq_map[q_idx];
+	u32 reg;
+
+	reg = rd32(hw, QINT_RQCTL(pfq));
+
+	/* MSI-X index 0 in the VF's space is always for the OICR, which means
+	 * this is most likely a poll mode VF driver, so don't enable an
+	 * interrupt that was never configured via VIRTCHNL_OP_CONFIG_IRQ_MAP
+	 */
+	if (!(reg & QINT_RQCTL_MSIX_INDX_M))
+		return;
+
+	wr32(hw, QINT_RQCTL(pfq), reg | QINT_RQCTL_CAUSE_ENA_M);
+}
+
+/**
+ * ice_vc_ena_qs_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * called from the VF to enable all or specific queue(s)
+ */
+int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct virtchnl_queue_select *vqs =
+	    (struct virtchnl_queue_select *)msg;
+	struct ice_vsi *vsi;
+	unsigned long q_map;
+	u16 vf_q_id;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!ice_vc_validate_vqs_bitmaps(vqs)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	/* Enable only Rx rings, Tx rings were enabled by the FW when the
+	 * Tx queue group list was configured and the context bits were
+	 * programmed using ice_vsi_cfg_txqs
+	 */
+	q_map = vqs->rx_queues;
+	for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) {
+		if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) {
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+
+		/* Skip queue if enabled */
+		if (test_bit(vf_q_id, vf->rxq_ena))
+			continue;
+
+		if (ice_vsi_ctrl_one_rx_ring(vsi, true, vf_q_id, true)) {
+			dev_err(ice_pf_to_dev(vsi->back), "Failed to enable Rx ring %d on VSI %d\n",
+				vf_q_id, vsi->vsi_num);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+
+		ice_vf_ena_rxq_interrupt(vsi, vf_q_id);
+		set_bit(vf_q_id, vf->rxq_ena);
+	}
+
+	q_map = vqs->tx_queues;
+	for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) {
+		if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) {
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+
+		/* Skip queue if enabled */
+		if (test_bit(vf_q_id, vf->txq_ena))
+			continue;
+
+		ice_vf_ena_txq_interrupt(vsi, vf_q_id);
+		set_bit(vf_q_id, vf->txq_ena);
+	}
+
+	/* Set flag to indicate that queues are enabled */
+	if (v_ret == VIRTCHNL_STATUS_SUCCESS)
+		set_bit(ICE_VF_STATE_QS_ENA, vf->vf_states);
+
+error_param:
+	/* send the response to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, v_ret,
+				     NULL, 0);
+}
+
+/**
+ * ice_vf_vsi_dis_single_txq - disable a single Tx queue
+ * @vf: VF to disable queue for
+ * @vsi: VSI for the VF
+ * @q_id: VF relative (0-based) queue ID
+ *
+ * Attempt to disable the Tx queue passed in. If the Tx queue was successfully
+ * disabled then clear q_id bit in the enabled queues bitmap and return
+ * success. Otherwise return error.
+ */
+int ice_vf_vsi_dis_single_txq(struct ice_vf *vf, struct ice_vsi *vsi, u16 q_id)
+{
+	struct ice_txq_meta txq_meta = { 0 };
+	struct ice_tx_ring *ring;
+	int err;
+
+	if (!test_bit(q_id, vf->txq_ena))
+		dev_dbg(ice_pf_to_dev(vsi->back), "Queue %u on VSI %u is not enabled, but stopping it anyway\n",
+			q_id, vsi->vsi_num);
+
+	ring = vsi->tx_rings[q_id];
+	if (!ring)
+		return -EINVAL;
+
+	ice_fill_txq_meta(vsi, ring, &txq_meta);
+
+	err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, vf->vf_id, ring, &txq_meta);
+	if (err) {
+		dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Tx ring %d on VSI %d\n",
+			q_id, vsi->vsi_num);
+		return err;
+	}
+
+	/* Clear enabled queues flag */
+	clear_bit(q_id, vf->txq_ena);
+
+	return 0;
+}
+
+/**
+ * ice_vc_dis_qs_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * called from the VF to disable all or specific queue(s)
+ */
+int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct virtchnl_queue_select *vqs =
+	    (struct virtchnl_queue_select *)msg;
+	struct ice_vsi *vsi;
+	unsigned long q_map;
+	u16 vf_q_id;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) &&
+	    !test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!ice_vc_validate_vqs_bitmaps(vqs)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (vqs->tx_queues) {
+		q_map = vqs->tx_queues;
+
+		for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) {
+			if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) {
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+				goto error_param;
+			}
+
+			if (ice_vf_vsi_dis_single_txq(vf, vsi, vf_q_id)) {
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+				goto error_param;
+			}
+		}
+	}
+
+	q_map = vqs->rx_queues;
+	/* speed up Rx queue disable by batching them if possible */
+	if (q_map &&
+	    bitmap_equal(&q_map, vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF)) {
+		if (ice_vsi_stop_all_rx_rings(vsi)) {
+			dev_err(ice_pf_to_dev(vsi->back), "Failed to stop all Rx rings on VSI %d\n",
+				vsi->vsi_num);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+
+		bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF);
+	} else if (q_map) {
+		for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) {
+			if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) {
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+				goto error_param;
+			}
+
+			/* Skip queue if not enabled */
+			if (!test_bit(vf_q_id, vf->rxq_ena))
+				continue;
+
+			if (ice_vsi_ctrl_one_rx_ring(vsi, false, vf_q_id,
+						     true)) {
+				dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Rx ring %d on VSI %d\n",
+					vf_q_id, vsi->vsi_num);
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+				goto error_param;
+			}
+
+			/* Clear enabled queues flag */
+			clear_bit(vf_q_id, vf->rxq_ena);
+		}
+	}
+
+	/* Clear enabled queues flag */
+	if (v_ret == VIRTCHNL_STATUS_SUCCESS && ice_vf_has_no_qs_ena(vf))
+		clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states);
+
+error_param:
+	/* send the response to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_QUEUES, v_ret,
+				     NULL, 0);
+}
+
+/**
+ * ice_cfg_interrupt
+ * @vf: pointer to the VF info
+ * @vsi: the VSI being configured
+ * @map: vector map for mapping vectors to queues
+ * @q_vector: structure for interrupt vector
+ * configure the IRQ to queue map
+ */
+static enum virtchnl_status_code
+ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi,
+		  struct virtchnl_vector_map *map,
+		  struct ice_q_vector *q_vector)
+{
+	u16 vsi_q_id, vsi_q_id_idx;
+	unsigned long qmap;
+
+	q_vector->num_ring_rx = 0;
+	q_vector->num_ring_tx = 0;
+
+	qmap = map->rxq_map;
+	for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) {
+		vsi_q_id = vsi_q_id_idx;
+
+		if (!ice_vc_isvalid_q_id(vsi, vsi_q_id))
+			return VIRTCHNL_STATUS_ERR_PARAM;
+
+		q_vector->num_ring_rx++;
+		q_vector->rx.itr_idx = map->rxitr_idx;
+		vsi->rx_rings[vsi_q_id]->q_vector = q_vector;
+		ice_cfg_rxq_interrupt(vsi, vsi_q_id,
+				      q_vector->vf_reg_idx,
+				      q_vector->rx.itr_idx);
+	}
+
+	qmap = map->txq_map;
+	for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) {
+		vsi_q_id = vsi_q_id_idx;
+
+		if (!ice_vc_isvalid_q_id(vsi, vsi_q_id))
+			return VIRTCHNL_STATUS_ERR_PARAM;
+
+		q_vector->num_ring_tx++;
+		q_vector->tx.itr_idx = map->txitr_idx;
+		vsi->tx_rings[vsi_q_id]->q_vector = q_vector;
+		ice_cfg_txq_interrupt(vsi, vsi_q_id,
+				      q_vector->vf_reg_idx,
+				      q_vector->tx.itr_idx);
+	}
+
+	return VIRTCHNL_STATUS_SUCCESS;
+}
+
+/**
+ * ice_vc_cfg_irq_map_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * called from the VF to configure the IRQ to queue map
+ */
+int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	u16 num_q_vectors_mapped, vsi_id, vector_id;
+	struct virtchnl_irq_map_info *irqmap_info;
+	struct virtchnl_vector_map *map;
+	struct ice_vsi *vsi;
+	int i;
+
+	irqmap_info = (struct virtchnl_irq_map_info *)msg;
+	num_q_vectors_mapped = irqmap_info->num_vectors;
+
+	/* Check to make sure number of VF vectors mapped is not greater than
+	 * number of VF vectors originally allocated, and check that
+	 * there is actually at least a single VF queue vector mapped
+	 */
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) ||
+	    vf->num_msix < num_q_vectors_mapped ||
+	    !num_q_vectors_mapped) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	for (i = 0; i < num_q_vectors_mapped; i++) {
+		struct ice_q_vector *q_vector;
+
+		map = &irqmap_info->vecmap[i];
+
+		vector_id = map->vector_id;
+		vsi_id = map->vsi_id;
+		/* vector_id is always 0-based for each VF, and can never be
+		 * larger than or equal to the max allowed interrupts per VF
+		 */
+		if (!(vector_id < vf->num_msix) ||
+		    !ice_vc_isvalid_vsi_id(vf, vsi_id) ||
+		    (!vector_id && (map->rxq_map || map->txq_map))) {
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+
+		/* No need to map VF miscellaneous or rogue vector */
+		if (!vector_id)
+			continue;
+
+		/* Subtract non queue vector from vector_id passed by VF
+		 * to get actual number of VSI queue vector array index
+		 */
+		q_vector = vsi->q_vectors[vector_id - ICE_NONQ_VECS_VF];
+		if (!q_vector) {
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+
+		/* lookout for the invalid queue index */
+		v_ret = ice_cfg_interrupt(vf, vsi, map, q_vector);
+		if (v_ret)
+			goto error_param;
+	}
+
+error_param:
+	/* send the response to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_IRQ_MAP, v_ret,
+				     NULL, 0);
+}
+
+/**
+ * ice_vc_cfg_q_bw - Configure per queue bandwidth
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer which holds the command descriptor
+ *
+ * Configure VF queues bandwidth.
+ *
+ * Return: 0 on success or negative error value.
+ */
+int ice_vc_cfg_q_bw(struct ice_vf *vf, u8 *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct virtchnl_queues_bw_cfg *qbw =
+		(struct virtchnl_queues_bw_cfg *)msg;
+	struct ice_vsi *vsi;
+	u16 i;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) ||
+	    !ice_vc_isvalid_vsi_id(vf, qbw->vsi_id)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	if (qbw->num_queues > ICE_MAX_RSS_QS_PER_VF ||
+	    qbw->num_queues > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
+		dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n",
+			vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq));
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	for (i = 0; i < qbw->num_queues; i++) {
+		if (qbw->cfg[i].shaper.peak != 0 && vf->max_tx_rate != 0 &&
+		    qbw->cfg[i].shaper.peak > vf->max_tx_rate) {
+			dev_warn(ice_pf_to_dev(vf->pf), "The maximum queue %d rate limit configuration may not take effect because the maximum TX rate for VF-%d is %d\n",
+				 qbw->cfg[i].queue_id, vf->vf_id,
+				 vf->max_tx_rate);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
+		if (qbw->cfg[i].shaper.committed != 0 && vf->min_tx_rate != 0 &&
+		    qbw->cfg[i].shaper.committed < vf->min_tx_rate) {
+			dev_warn(ice_pf_to_dev(vf->pf), "The minimum queue %d rate limit configuration may not take effect because the minimum TX rate for VF-%d is %d\n",
+				 qbw->cfg[i].queue_id, vf->vf_id,
+				 vf->min_tx_rate);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
+		if (qbw->cfg[i].queue_id > vf->num_vf_qs) {
+			dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure invalid queue_id\n",
+				 vf->vf_id);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
+		if (qbw->cfg[i].tc >= ICE_MAX_TRAFFIC_CLASS) {
+			dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure a traffic class higher than allowed\n",
+				 vf->vf_id);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
+	}
+
+	for (i = 0; i < qbw->num_queues; i++) {
+		vf->qs_bw[i].queue_id = qbw->cfg[i].queue_id;
+		vf->qs_bw[i].peak = qbw->cfg[i].shaper.peak;
+		vf->qs_bw[i].committed = qbw->cfg[i].shaper.committed;
+		vf->qs_bw[i].tc = qbw->cfg[i].tc;
+	}
+
+	if (ice_vf_cfg_qs_bw(vf, qbw->num_queues))
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+
+err:
+	/* send the response to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_QUEUE_BW,
+				    v_ret, NULL, 0);
+}
+
+/**
+ * ice_vc_cfg_q_quanta - Configure per queue quanta
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer which holds the command descriptor
+ *
+ * Configure VF queues quanta.
+ *
+ * Return: 0 on success or negative error value.
+ */
+int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg)
+{
+	u16 quanta_prof_id, quanta_size, start_qid, num_queues, end_qid, i;
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct virtchnl_quanta_cfg *qquanta =
+		(struct virtchnl_quanta_cfg *)msg;
+	struct ice_vsi *vsi;
+	int ret;
+
+	start_qid = qquanta->queue_select.start_queue_id;
+	num_queues = qquanta->queue_select.num_queues;
+
+	if (check_add_overflow(start_qid, num_queues, &end_qid)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	if (end_qid > ICE_MAX_RSS_QS_PER_VF ||
+	    end_qid > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
+		dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n",
+			vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq));
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	quanta_size = qquanta->quanta_size;
+	if (quanta_size > ICE_MAX_QUANTA_SIZE ||
+	    quanta_size < ICE_MIN_QUANTA_SIZE) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	if (quanta_size % 64) {
+		dev_err(ice_pf_to_dev(vf->pf), "quanta size should be the product of 64\n");
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	ret = ice_vf_cfg_q_quanta_profile(vf, quanta_size,
+					  &quanta_prof_id);
+	if (ret) {
+		v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED;
+		goto err;
+	}
+
+	for (i = start_qid; i < end_qid; i++)
+		vsi->tx_rings[i]->quanta_prof_id = quanta_prof_id;
+
+err:
+	/* send the response to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_QUANTA,
+				     v_ret, NULL, 0);
+}
+
+/**
+ * ice_vc_cfg_qs_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * called from the VF to configure the Rx/Tx queues
+ */
+int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
+{
+	struct virtchnl_vsi_queue_config_info *qci =
+	    (struct virtchnl_vsi_queue_config_info *)msg;
+	struct virtchnl_queue_pair_info *qpi;
+	struct ice_pf *pf = vf->pf;
+	struct ice_vsi *vsi;
+	int i = -1, q_idx;
+	bool ena_ts;
+	u8 act_prt;
+
+	mutex_lock(&pf->lag_mutex);
+	act_prt = ice_lag_prepare_vf_reset(pf->lag);
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+		goto error_param;
+
+	if (!ice_vc_isvalid_vsi_id(vf, qci->vsi_id))
+		goto error_param;
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi)
+		goto error_param;
+
+	if (qci->num_queue_pairs > ICE_MAX_RSS_QS_PER_VF ||
+	    qci->num_queue_pairs > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
+		dev_err(ice_pf_to_dev(pf), "VF-%d requesting more than supported number of queues: %d\n",
+			vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq));
+		goto error_param;
+	}
+
+	for (i = 0; i < qci->num_queue_pairs; i++) {
+		if (!qci->qpair[i].rxq.crc_disable)
+			continue;
+
+		if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_CRC) ||
+		    vf->vlan_strip_ena)
+			goto error_param;
+	}
+
+	for (i = 0; i < qci->num_queue_pairs; i++) {
+		qpi = &qci->qpair[i];
+		if (qpi->txq.vsi_id != qci->vsi_id ||
+		    qpi->rxq.vsi_id != qci->vsi_id ||
+		    qpi->rxq.queue_id != qpi->txq.queue_id ||
+		    qpi->txq.headwb_enabled ||
+		    !ice_vc_isvalid_ring_len(qpi->txq.ring_len) ||
+		    !ice_vc_isvalid_ring_len(qpi->rxq.ring_len) ||
+		    !ice_vc_isvalid_q_id(vsi, qpi->txq.queue_id)) {
+			goto error_param;
+		}
+
+		q_idx = qpi->rxq.queue_id;
+
+		/* make sure selected "q_idx" is in valid range of queues
+		 * for selected "vsi"
+		 */
+		if (q_idx >= vsi->alloc_txq || q_idx >= vsi->alloc_rxq) {
+			goto error_param;
+		}
+
+		/* copy Tx queue info from VF into VSI */
+		if (qpi->txq.ring_len > 0) {
+			vsi->tx_rings[q_idx]->dma = qpi->txq.dma_ring_addr;
+			vsi->tx_rings[q_idx]->count = qpi->txq.ring_len;
+
+			/* Disable any existing queue first */
+			if (ice_vf_vsi_dis_single_txq(vf, vsi, q_idx))
+				goto error_param;
+
+			/* Configure a queue with the requested settings */
+			if (ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx)) {
+				dev_warn(ice_pf_to_dev(pf), "VF-%d failed to configure TX queue %d\n",
+					 vf->vf_id, q_idx);
+				goto error_param;
+			}
+		}
+
+		/* copy Rx queue info from VF into VSI */
+		if (qpi->rxq.ring_len > 0) {
+			u16 max_frame_size = ice_vc_get_max_frame_size(vf);
+			struct ice_rx_ring *ring = vsi->rx_rings[q_idx];
+			u32 rxdid;
+
+			ring->dma = qpi->rxq.dma_ring_addr;
+			ring->count = qpi->rxq.ring_len;
+
+			if (qpi->rxq.crc_disable)
+				ring->flags |= ICE_RX_FLAGS_CRC_STRIP_DIS;
+			else
+				ring->flags &= ~ICE_RX_FLAGS_CRC_STRIP_DIS;
+
+			if (qpi->rxq.databuffer_size != 0 &&
+			    (qpi->rxq.databuffer_size > ((16 * 1024) - 128) ||
+			     qpi->rxq.databuffer_size < 1024))
+				goto error_param;
+
+			ring->rx_buf_len = qpi->rxq.databuffer_size;
+
+			if (qpi->rxq.max_pkt_size > max_frame_size ||
+			    qpi->rxq.max_pkt_size < 64)
+				goto error_param;
+
+			vsi->max_frame = qpi->rxq.max_pkt_size;
+			/* add space for the port VLAN since the VF driver is
+			 * not expected to account for it in the MTU
+			 * calculation
+			 */
+			if (ice_vf_is_port_vlan_ena(vf))
+				vsi->max_frame += VLAN_HLEN;
+
+			if (ice_vsi_cfg_single_rxq(vsi, q_idx)) {
+				dev_warn(ice_pf_to_dev(pf), "VF-%d failed to configure RX queue %d\n",
+					 vf->vf_id, q_idx);
+				goto error_param;
+			}
+
+			/* If Rx flex desc is supported, select RXDID for Rx
+			 * queues. Otherwise, use legacy 32byte descriptor
+			 * format. Legacy 16byte descriptor is not supported.
+			 * If this RXDID is selected, return error.
+			 */
+			if (vf->driver_caps &
+			    VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) {
+				rxdid = qpi->rxq.rxdid;
+				if (!(BIT(rxdid) & pf->supported_rxdids))
+					goto error_param;
+			} else {
+				rxdid = ICE_RXDID_LEGACY_1;
+			}
+
+			ena_ts = ((vf->driver_caps &
+				  VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) &&
+				  (vf->driver_caps & VIRTCHNL_VF_CAP_PTP) &&
+				  (qpi->rxq.flags & VIRTCHNL_PTP_RX_TSTAMP));
+
+			ice_write_qrxflxp_cntxt(&vsi->back->hw,
+						vsi->rxq_map[q_idx], rxdid,
+						ICE_RXDID_PRIO, ena_ts);
+		}
+	}
+
+	ice_lag_complete_vf_reset(pf->lag, act_prt);
+	mutex_unlock(&pf->lag_mutex);
+
+	/* send the response to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES,
+				     VIRTCHNL_STATUS_SUCCESS, NULL, 0);
+error_param:
+	/* disable whatever we can */
+	for (; i >= 0; i--) {
+		if (ice_vsi_ctrl_one_rx_ring(vsi, false, i, true))
+			dev_err(ice_pf_to_dev(pf), "VF-%d could not disable RX queue %d\n",
+				vf->vf_id, i);
+		if (ice_vf_vsi_dis_single_txq(vf, vsi, i))
+			dev_err(ice_pf_to_dev(pf), "VF-%d could not disable TX queue %d\n",
+				vf->vf_id, i);
+	}
+
+	ice_lag_complete_vf_reset(pf->lag, act_prt);
+	mutex_unlock(&pf->lag_mutex);
+
+	/* send the response to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES,
+				     VIRTCHNL_STATUS_ERR_PARAM, NULL, 0);
+}
+
+/**
+ * ice_vc_request_qs_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * VFs get a default number of queues but can use this message to request a
+ * different number. If the request is successful, PF will reset the VF and
+ * return 0. If unsuccessful, PF will send message informing VF of number of
+ * available queue pairs via virtchnl message response to VF.
+ */
+int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct virtchnl_vf_res_request *vfres =
+		(struct virtchnl_vf_res_request *)msg;
+	u16 req_queues = vfres->num_queue_pairs;
+	struct ice_pf *pf = vf->pf;
+	u16 max_allowed_vf_queues;
+	u16 tx_rx_queue_left;
+	struct device *dev;
+	u16 cur_queues;
+
+	dev = ice_pf_to_dev(pf);
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	cur_queues = vf->num_vf_qs;
+	tx_rx_queue_left = min_t(u16, ice_get_avail_txq_count(pf),
+				 ice_get_avail_rxq_count(pf));
+	max_allowed_vf_queues = tx_rx_queue_left + cur_queues;
+	if (!req_queues) {
+		dev_err(dev, "VF %d tried to request 0 queues. Ignoring.\n",
+			vf->vf_id);
+	} else if (req_queues > ICE_MAX_RSS_QS_PER_VF) {
+		dev_err(dev, "VF %d tried to request more than %d queues.\n",
+			vf->vf_id, ICE_MAX_RSS_QS_PER_VF);
+		vfres->num_queue_pairs = ICE_MAX_RSS_QS_PER_VF;
+	} else if (req_queues > cur_queues &&
+		   req_queues - cur_queues > tx_rx_queue_left) {
+		dev_warn(dev, "VF %d requested %u more queues, but only %u left.\n",
+			 vf->vf_id, req_queues - cur_queues, tx_rx_queue_left);
+		vfres->num_queue_pairs = min_t(u16, max_allowed_vf_queues,
+					       ICE_MAX_RSS_QS_PER_VF);
+	} else {
+		/* request is successful, then reset VF */
+		vf->num_req_qs = req_queues;
+		ice_reset_vf(vf, ICE_VF_RESET_NOTIFY);
+		dev_info(dev, "VF %d granted request of %u queues.\n",
+			 vf->vf_id, req_queues);
+		return 0;
+	}
+
+error_param:
+	/* send the response to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES,
+				     v_ret, (u8 *)vfres, sizeof(*vfres));
+}
+
diff --git a/drivers/net/ethernet/intel/ice/virt/queues.h b/drivers/net/ethernet/intel/ice/virt/queues.h
new file mode 100644
index 000000000000..c4a792cecea1
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/virt/queues.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2022, Intel Corporation. */
+
+#ifndef _ICE_VIRT_QUEUES_H_
+#define _ICE_VIRT_QUEUES_H_
+
+#include <linux/types.h>
+
+struct ice_vf;
+
+u16 ice_vc_get_max_frame_size(struct ice_vf *vf);
+int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg);
+int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg);
+int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg);
+int ice_vc_cfg_q_bw(struct ice_vf *vf, u8 *msg);
+int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg);
+int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg);
+int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg);
+
+#endif /* _ICE_VIRT_QUEUES_H_ */
diff --git a/drivers/net/ethernet/intel/ice/virt/rss.c b/drivers/net/ethernet/intel/ice/virt/rss.c
new file mode 100644
index 000000000000..085e69ec0cfc
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/virt/rss.c
@@ -0,0 +1,1922 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2022, Intel Corporation. */
+
+#include "rss.h"
+#include "ice_vf_lib_private.h"
+#include "ice.h"
+
+#define FIELD_SELECTOR(proto_hdr_field) \
+		BIT((proto_hdr_field) & PROTO_HDR_FIELD_MASK)
+
+struct ice_vc_hdr_match_type {
+	u32 vc_hdr;	/* virtchnl headers (VIRTCHNL_PROTO_HDR_XXX) */
+	u32 ice_hdr;	/* ice headers (ICE_FLOW_SEG_HDR_XXX) */
+};
+
+static const struct ice_vc_hdr_match_type ice_vc_hdr_list[] = {
+	{VIRTCHNL_PROTO_HDR_NONE,	ICE_FLOW_SEG_HDR_NONE},
+	{VIRTCHNL_PROTO_HDR_ETH,	ICE_FLOW_SEG_HDR_ETH},
+	{VIRTCHNL_PROTO_HDR_S_VLAN,	ICE_FLOW_SEG_HDR_VLAN},
+	{VIRTCHNL_PROTO_HDR_C_VLAN,	ICE_FLOW_SEG_HDR_VLAN},
+	{VIRTCHNL_PROTO_HDR_IPV4,	ICE_FLOW_SEG_HDR_IPV4 |
+					ICE_FLOW_SEG_HDR_IPV_OTHER},
+	{VIRTCHNL_PROTO_HDR_IPV6,	ICE_FLOW_SEG_HDR_IPV6 |
+					ICE_FLOW_SEG_HDR_IPV_OTHER},
+	{VIRTCHNL_PROTO_HDR_TCP,	ICE_FLOW_SEG_HDR_TCP},
+	{VIRTCHNL_PROTO_HDR_UDP,	ICE_FLOW_SEG_HDR_UDP},
+	{VIRTCHNL_PROTO_HDR_SCTP,	ICE_FLOW_SEG_HDR_SCTP},
+	{VIRTCHNL_PROTO_HDR_PPPOE,	ICE_FLOW_SEG_HDR_PPPOE},
+	{VIRTCHNL_PROTO_HDR_GTPU_IP,	ICE_FLOW_SEG_HDR_GTPU_IP},
+	{VIRTCHNL_PROTO_HDR_GTPU_EH,	ICE_FLOW_SEG_HDR_GTPU_EH},
+	{VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_DWN,
+					ICE_FLOW_SEG_HDR_GTPU_DWN},
+	{VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_UP,
+					ICE_FLOW_SEG_HDR_GTPU_UP},
+	{VIRTCHNL_PROTO_HDR_L2TPV3,	ICE_FLOW_SEG_HDR_L2TPV3},
+	{VIRTCHNL_PROTO_HDR_ESP,	ICE_FLOW_SEG_HDR_ESP},
+	{VIRTCHNL_PROTO_HDR_AH,		ICE_FLOW_SEG_HDR_AH},
+	{VIRTCHNL_PROTO_HDR_PFCP,	ICE_FLOW_SEG_HDR_PFCP_SESSION},
+	{VIRTCHNL_PROTO_HDR_GTPC,	ICE_FLOW_SEG_HDR_GTPC},
+	{VIRTCHNL_PROTO_HDR_L2TPV2,	ICE_FLOW_SEG_HDR_L2TPV2},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,	ICE_FLOW_SEG_HDR_IPV_FRAG},
+	{VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG,	ICE_FLOW_SEG_HDR_IPV_FRAG},
+	{VIRTCHNL_PROTO_HDR_GRE,        ICE_FLOW_SEG_HDR_GRE},
+};
+
+struct ice_vc_hash_field_match_type {
+	u32 vc_hdr;		/* virtchnl headers
+				 * (VIRTCHNL_PROTO_HDR_XXX)
+				 */
+	u32 vc_hash_field;	/* virtchnl hash fields selector
+				 * FIELD_SELECTOR((VIRTCHNL_PROTO_HDR_ETH_XXX))
+				 */
+	u64 ice_hash_field;	/* ice hash fields
+				 * (BIT_ULL(ICE_FLOW_FIELD_IDX_XXX))
+				 */
+};
+
+static const struct
+ice_vc_hash_field_match_type ice_vc_hash_field_list[] = {
+	{VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_SRC),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_SA)},
+	{VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_DST),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_DA)},
+	{VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_DST),
+		ICE_FLOW_HASH_ETH},
+	{VIRTCHNL_PROTO_HDR_ETH,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_ETHERTYPE),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_TYPE)},
+	{VIRTCHNL_PROTO_HDR_S_VLAN,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_S_VLAN_ID),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_S_VLAN)},
+	{VIRTCHNL_PROTO_HDR_C_VLAN,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_C_VLAN_ID),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_C_VLAN)},
+	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA)},
+	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)},
+	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST),
+		ICE_FLOW_HASH_IPV4},
+	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT),
+		ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV4,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_FRAG_PKID),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_ID)},
+	{VIRTCHNL_PROTO_HDR_IPV4,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST),
+		ICE_FLOW_HASH_IPV4},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT),
+		ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_FRAG_PKID),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_ID)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA)},
+	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA)},
+	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST),
+		ICE_FLOW_HASH_IPV6},
+	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT),
+		ICE_FLOW_HASH_IPV6 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG_PKID),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_ID)},
+	{VIRTCHNL_PROTO_HDR_IPV6,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_DST),
+		ICE_FLOW_HASH_IPV6_PRE64},
+	{VIRTCHNL_PROTO_HDR_IPV6,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_SRC),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE64_SA)},
+	{VIRTCHNL_PROTO_HDR_IPV6,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_DST),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE64_DA)},
+	{VIRTCHNL_PROTO_HDR_IPV6,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT),
+		ICE_FLOW_HASH_IPV6_PRE64 |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV6,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_SRC) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE64_SA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)},
+	{VIRTCHNL_PROTO_HDR_IPV6,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_DST) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE64_DA) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)},
+	{VIRTCHNL_PROTO_HDR_TCP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT)},
+	{VIRTCHNL_PROTO_HDR_TCP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT)},
+	{VIRTCHNL_PROTO_HDR_TCP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT),
+		ICE_FLOW_HASH_TCP_PORT},
+	{VIRTCHNL_PROTO_HDR_TCP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_TCP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_TCP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_TCP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_CHKSUM),
+		ICE_FLOW_HASH_TCP_PORT |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_UDP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT)},
+	{VIRTCHNL_PROTO_HDR_UDP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT)},
+	{VIRTCHNL_PROTO_HDR_UDP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT),
+		ICE_FLOW_HASH_UDP_PORT},
+	{VIRTCHNL_PROTO_HDR_UDP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_UDP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_UDP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_UDP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_CHKSUM),
+		ICE_FLOW_HASH_UDP_PORT |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_SCTP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT)},
+	{VIRTCHNL_PROTO_HDR_SCTP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT)},
+	{VIRTCHNL_PROTO_HDR_SCTP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT),
+		ICE_FLOW_HASH_SCTP_PORT},
+	{VIRTCHNL_PROTO_HDR_SCTP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_SCTP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_SCTP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_CHKSUM),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT) |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_SCTP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT) |
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_CHKSUM),
+		ICE_FLOW_HASH_SCTP_PORT |
+		BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_CHKSUM)},
+	{VIRTCHNL_PROTO_HDR_PPPOE,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_PPPOE_SESS_ID),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID)},
+	{VIRTCHNL_PROTO_HDR_GTPU_IP,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_GTPU_IP_TEID),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_IP_TEID)},
+	{VIRTCHNL_PROTO_HDR_L2TPV3,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_L2TPV3_SESS_ID),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV3_SESS_ID)},
+	{VIRTCHNL_PROTO_HDR_ESP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ESP_SPI),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_ESP_SPI)},
+	{VIRTCHNL_PROTO_HDR_AH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_AH_SPI),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_AH_SPI)},
+	{VIRTCHNL_PROTO_HDR_PFCP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_PFCP_SEID),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_PFCP_SEID)},
+	{VIRTCHNL_PROTO_HDR_GTPC,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_GTPC_TEID),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID)},
+	{VIRTCHNL_PROTO_HDR_L2TPV2,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_L2TPV2_SESS_ID),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV2_SESS_ID)},
+	{VIRTCHNL_PROTO_HDR_L2TPV2,
+		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_L2TPV2_LEN_SESS_ID),
+		BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV2_LEN_SESS_ID)},
+};
+
+static int
+ice_vc_rss_hash_update(struct ice_hw *hw, struct ice_vsi *vsi, u8 hash_type)
+{
+	struct ice_vsi_ctx *ctx;
+	int ret;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	/* clear previous hash_type */
+	ctx->info.q_opt_rss = vsi->info.q_opt_rss &
+		~ICE_AQ_VSI_Q_OPT_RSS_HASH_M;
+	/* hash_type is passed in as ICE_AQ_VSI_Q_OPT_RSS_<XOR|TPLZ|SYM_TPLZ */
+	ctx->info.q_opt_rss |= FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M,
+					  hash_type);
+
+	/* Preserve existing queueing option setting */
+	ctx->info.q_opt_tc = vsi->info.q_opt_tc;
+	ctx->info.q_opt_flags = vsi->info.q_opt_flags;
+
+	ctx->info.valid_sections =
+			cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID);
+
+	ret = ice_update_vsi(hw, vsi->idx, ctx, NULL);
+	if (ret) {
+		dev_err(ice_hw_to_dev(hw), "update VSI for RSS failed, err %d aq_err %s\n",
+			ret, libie_aq_str(hw->adminq.sq_last_status));
+	} else {
+		vsi->info.q_opt_rss = ctx->info.q_opt_rss;
+	}
+
+	kfree(ctx);
+
+	return ret;
+}
+
+/**
+ * ice_vc_validate_pattern
+ * @vf: pointer to the VF info
+ * @proto: virtchnl protocol headers
+ *
+ * validate the pattern is supported or not.
+ *
+ * Return: true on success, false on error.
+ */
+bool
+ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto)
+{
+	bool is_ipv4 = false;
+	bool is_ipv6 = false;
+	bool is_udp = false;
+	u16 ptype = -1;
+	int i = 0;
+
+	while (i < proto->count &&
+	       proto->proto_hdr[i].type != VIRTCHNL_PROTO_HDR_NONE) {
+		switch (proto->proto_hdr[i].type) {
+		case VIRTCHNL_PROTO_HDR_ETH:
+			ptype = ICE_PTYPE_MAC_PAY;
+			break;
+		case VIRTCHNL_PROTO_HDR_IPV4:
+			ptype = ICE_PTYPE_IPV4_PAY;
+			is_ipv4 = true;
+			break;
+		case VIRTCHNL_PROTO_HDR_IPV6:
+			ptype = ICE_PTYPE_IPV6_PAY;
+			is_ipv6 = true;
+			break;
+		case VIRTCHNL_PROTO_HDR_UDP:
+			if (is_ipv4)
+				ptype = ICE_PTYPE_IPV4_UDP_PAY;
+			else if (is_ipv6)
+				ptype = ICE_PTYPE_IPV6_UDP_PAY;
+			is_udp = true;
+			break;
+		case VIRTCHNL_PROTO_HDR_TCP:
+			if (is_ipv4)
+				ptype = ICE_PTYPE_IPV4_TCP_PAY;
+			else if (is_ipv6)
+				ptype = ICE_PTYPE_IPV6_TCP_PAY;
+			break;
+		case VIRTCHNL_PROTO_HDR_SCTP:
+			if (is_ipv4)
+				ptype = ICE_PTYPE_IPV4_SCTP_PAY;
+			else if (is_ipv6)
+				ptype = ICE_PTYPE_IPV6_SCTP_PAY;
+			break;
+		case VIRTCHNL_PROTO_HDR_GTPU_IP:
+		case VIRTCHNL_PROTO_HDR_GTPU_EH:
+			if (is_ipv4)
+				ptype = ICE_MAC_IPV4_GTPU;
+			else if (is_ipv6)
+				ptype = ICE_MAC_IPV6_GTPU;
+			goto out;
+		case VIRTCHNL_PROTO_HDR_L2TPV3:
+			if (is_ipv4)
+				ptype = ICE_MAC_IPV4_L2TPV3;
+			else if (is_ipv6)
+				ptype = ICE_MAC_IPV6_L2TPV3;
+			goto out;
+		case VIRTCHNL_PROTO_HDR_ESP:
+			if (is_ipv4)
+				ptype = is_udp ? ICE_MAC_IPV4_NAT_T_ESP :
+						ICE_MAC_IPV4_ESP;
+			else if (is_ipv6)
+				ptype = is_udp ? ICE_MAC_IPV6_NAT_T_ESP :
+						ICE_MAC_IPV6_ESP;
+			goto out;
+		case VIRTCHNL_PROTO_HDR_AH:
+			if (is_ipv4)
+				ptype = ICE_MAC_IPV4_AH;
+			else if (is_ipv6)
+				ptype = ICE_MAC_IPV6_AH;
+			goto out;
+		case VIRTCHNL_PROTO_HDR_PFCP:
+			if (is_ipv4)
+				ptype = ICE_MAC_IPV4_PFCP_SESSION;
+			else if (is_ipv6)
+				ptype = ICE_MAC_IPV6_PFCP_SESSION;
+			goto out;
+		default:
+			break;
+		}
+		i++;
+	}
+
+out:
+	return ice_hw_ptype_ena(&vf->pf->hw, ptype);
+}
+
+/**
+ * ice_vc_parse_rss_cfg - parses hash fields and headers from
+ * a specific virtchnl RSS cfg
+ * @hw: pointer to the hardware
+ * @rss_cfg: pointer to the virtchnl RSS cfg
+ * @hash_cfg: pointer to the HW hash configuration
+ *
+ * Return true if all the protocol header and hash fields in the RSS cfg could
+ * be parsed, else return false
+ *
+ * This function parses the virtchnl RSS cfg to be the intended
+ * hash fields and the intended header for RSS configuration
+ */
+static bool ice_vc_parse_rss_cfg(struct ice_hw *hw,
+				 struct virtchnl_rss_cfg *rss_cfg,
+				 struct ice_rss_hash_cfg *hash_cfg)
+{
+	const struct ice_vc_hash_field_match_type *hf_list;
+	const struct ice_vc_hdr_match_type *hdr_list;
+	int i, hf_list_len, hdr_list_len;
+	bool outer_ipv4 = false;
+	bool outer_ipv6 = false;
+	bool inner_hdr = false;
+	bool has_gre = false;
+
+	u32 *addl_hdrs = &hash_cfg->addl_hdrs;
+	u64 *hash_flds = &hash_cfg->hash_flds;
+
+	/* set outer layer RSS as default */
+	hash_cfg->hdr_type = ICE_RSS_OUTER_HEADERS;
+
+	if (rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC)
+		hash_cfg->symm = true;
+	else
+		hash_cfg->symm = false;
+
+	hf_list = ice_vc_hash_field_list;
+	hf_list_len = ARRAY_SIZE(ice_vc_hash_field_list);
+	hdr_list = ice_vc_hdr_list;
+	hdr_list_len = ARRAY_SIZE(ice_vc_hdr_list);
+
+	for (i = 0; i < rss_cfg->proto_hdrs.count; i++) {
+		struct virtchnl_proto_hdr *proto_hdr =
+					&rss_cfg->proto_hdrs.proto_hdr[i];
+		u32 hdr_found = 0;
+		int j;
+
+		/* Find matched ice headers according to virtchnl headers.
+		 * Also figure out the outer type of GTPU headers.
+		 */
+		for (j = 0; j < hdr_list_len; j++) {
+			struct ice_vc_hdr_match_type hdr_map = hdr_list[j];
+
+			if (proto_hdr->type == hdr_map.vc_hdr)
+				hdr_found = hdr_map.ice_hdr;
+		}
+
+		if (!hdr_found)
+			return false;
+
+		/* Find matched ice hash fields according to
+		 * virtchnl hash fields.
+		 */
+		for (j = 0; j < hf_list_len; j++) {
+			struct ice_vc_hash_field_match_type hf_map = hf_list[j];
+
+			if (proto_hdr->type == hf_map.vc_hdr &&
+			    proto_hdr->field_selector == hf_map.vc_hash_field) {
+				*hash_flds |= hf_map.ice_hash_field;
+				break;
+			}
+		}
+
+		if (proto_hdr->type == VIRTCHNL_PROTO_HDR_IPV4 && !inner_hdr)
+			outer_ipv4 = true;
+		else if (proto_hdr->type == VIRTCHNL_PROTO_HDR_IPV6 &&
+			 !inner_hdr)
+			outer_ipv6 = true;
+		/* for GRE and L2TPv2, take inner header as input set if no
+		 * any field is selected from outer headers.
+		 * for GTPU, take inner header and GTPU teid as input set.
+		 */
+		else if ((proto_hdr->type == VIRTCHNL_PROTO_HDR_GTPU_IP ||
+			  proto_hdr->type == VIRTCHNL_PROTO_HDR_GTPU_EH ||
+			  proto_hdr->type == VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_DWN ||
+			  proto_hdr->type ==
+				VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_UP) ||
+			 ((proto_hdr->type == VIRTCHNL_PROTO_HDR_L2TPV2 ||
+			   proto_hdr->type == VIRTCHNL_PROTO_HDR_GRE) &&
+			   *hash_flds == 0)) {
+			/* set inner_hdr flag, and clean up outer header */
+			inner_hdr = true;
+
+			/* clear outer headers */
+			*addl_hdrs = 0;
+
+			if (outer_ipv4 && outer_ipv6)
+				return false;
+
+			if (outer_ipv4)
+				hash_cfg->hdr_type = ICE_RSS_INNER_HEADERS_W_OUTER_IPV4;
+			else if (outer_ipv6)
+				hash_cfg->hdr_type = ICE_RSS_INNER_HEADERS_W_OUTER_IPV6;
+			else
+				hash_cfg->hdr_type = ICE_RSS_INNER_HEADERS;
+
+			if (has_gre && outer_ipv4)
+				hash_cfg->hdr_type =
+					ICE_RSS_INNER_HEADERS_W_OUTER_IPV4_GRE;
+			if (has_gre && outer_ipv6)
+				hash_cfg->hdr_type =
+					ICE_RSS_INNER_HEADERS_W_OUTER_IPV6_GRE;
+
+			if (proto_hdr->type == VIRTCHNL_PROTO_HDR_GRE)
+				has_gre = true;
+		}
+
+		*addl_hdrs |= hdr_found;
+
+		/* refine hash hdrs and fields for IP fragment */
+		if (VIRTCHNL_TEST_PROTO_HDR_FIELD(proto_hdr,
+						  VIRTCHNL_PROTO_HDR_IPV4_FRAG_PKID) &&
+		    proto_hdr->type == VIRTCHNL_PROTO_HDR_IPV4_FRAG) {
+			*addl_hdrs |= ICE_FLOW_SEG_HDR_IPV_FRAG;
+			*addl_hdrs &= ~(ICE_FLOW_SEG_HDR_IPV_OTHER);
+			*hash_flds |= BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_ID);
+			VIRTCHNL_DEL_PROTO_HDR_FIELD(proto_hdr,
+						     VIRTCHNL_PROTO_HDR_IPV4_FRAG_PKID);
+		}
+		if (VIRTCHNL_TEST_PROTO_HDR_FIELD(proto_hdr,
+						  VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG_PKID) &&
+		    proto_hdr->type == VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG) {
+			*addl_hdrs |= ICE_FLOW_SEG_HDR_IPV_FRAG;
+			*addl_hdrs &= ~(ICE_FLOW_SEG_HDR_IPV_OTHER);
+			*hash_flds |= BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_ID);
+			VIRTCHNL_DEL_PROTO_HDR_FIELD(proto_hdr,
+						     VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG_PKID);
+		}
+	}
+
+	/* refine gtpu header if we take outer as input set for a no inner
+	 * ip gtpu flow.
+	 */
+	if (hash_cfg->hdr_type == ICE_RSS_OUTER_HEADERS &&
+	    *addl_hdrs & ICE_FLOW_SEG_HDR_GTPU_IP) {
+		*addl_hdrs &= ~(ICE_FLOW_SEG_HDR_GTPU_IP);
+		*addl_hdrs |= ICE_FLOW_SEG_HDR_GTPU_NON_IP;
+	}
+
+	/* refine hash field for esp and nat-t-esp. */
+	if ((*addl_hdrs & ICE_FLOW_SEG_HDR_UDP) &&
+	    (*addl_hdrs & ICE_FLOW_SEG_HDR_ESP)) {
+		*addl_hdrs &= ~(ICE_FLOW_SEG_HDR_ESP | ICE_FLOW_SEG_HDR_UDP);
+		*addl_hdrs |= ICE_FLOW_SEG_HDR_NAT_T_ESP;
+		*hash_flds &= ~(BIT_ULL(ICE_FLOW_FIELD_IDX_ESP_SPI));
+		*hash_flds |= BIT_ULL(ICE_FLOW_FIELD_IDX_NAT_T_ESP_SPI);
+	}
+
+	/* refine hash hdrs for L4 udp/tcp/sctp. */
+	if (*addl_hdrs & (ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_UDP |
+			  ICE_FLOW_SEG_HDR_SCTP) &&
+	    *addl_hdrs & ICE_FLOW_SEG_HDR_IPV_OTHER)
+		*addl_hdrs &= ~ICE_FLOW_SEG_HDR_IPV_OTHER;
+
+	return true;
+}
+
+/**
+ * ice_vf_adv_rss_offload_ena - determine if capabilities support advanced
+ * RSS offloads
+ * @caps: VF driver negotiated capabilities
+ *
+ * Return true if VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability is set,
+ * else return false
+ */
+static bool ice_vf_adv_rss_offload_ena(u32 caps)
+{
+	return !!(caps & VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF);
+}
+
+/**
+ * ice_is_hash_cfg_valid - Check whether an RSS hash context is valid
+ * @cfg: RSS hash configuration to test
+ *
+ * Return: true if both @cfg->hash_flds and @cfg->addl_hdrs are non-zero; false otherwise.
+ */
+static bool ice_is_hash_cfg_valid(struct ice_rss_hash_cfg *cfg)
+{
+	return cfg->hash_flds && cfg->addl_hdrs;
+}
+
+/**
+ * ice_hash_cfg_reset - Reset an RSS hash context
+ * @cfg: RSS hash configuration to reset
+ *
+ * Reset fields of @cfg that store the active rule information.
+ */
+static void ice_hash_cfg_reset(struct ice_rss_hash_cfg *cfg)
+{
+	cfg->hash_flds = 0;
+	cfg->addl_hdrs = 0;
+	cfg->hdr_type = ICE_RSS_OUTER_HEADERS;
+	cfg->symm = 0;
+}
+
+/**
+ * ice_hash_cfg_record - Record an RSS hash context
+ * @ctx: destination (global) RSS hash configuration
+ * @cfg: source RSS hash configuration to record
+ *
+ * Copy the active rule information from @cfg into @ctx.
+ */
+static void ice_hash_cfg_record(struct ice_rss_hash_cfg *ctx,
+				struct ice_rss_hash_cfg *cfg)
+{
+	ctx->hash_flds = cfg->hash_flds;
+	ctx->addl_hdrs = cfg->addl_hdrs;
+	ctx->hdr_type = cfg->hdr_type;
+	ctx->symm = cfg->symm;
+}
+
+/**
+ * ice_hash_moveout - Delete an RSS configuration (keep context)
+ * @vf: VF pointer
+ * @cfg: RSS hash configuration
+ *
+ * Return: 0 on success (including when already absent); -ENOENT if @cfg is
+ * invalid or VSI is missing; -EBUSY on hardware removal failure.
+ */
+static int
+ice_hash_moveout(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg)
+{
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
+	struct ice_hw *hw = &vf->pf->hw;
+	int ret;
+
+	if (!ice_is_hash_cfg_valid(cfg) || !vsi)
+		return -ENOENT;
+
+	ret = ice_rem_rss_cfg(hw, vsi->idx, cfg);
+	if (ret && ret != -ENOENT) {
+		dev_err(dev, "ice_rem_rss_cfg failed for VF %d, VSI %d, error:%d\n",
+			vf->vf_id, vf->lan_vsi_idx, ret);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_hash_moveback - Add an RSS hash configuration for a VF
+ * @vf: VF pointer
+ * @cfg: RSS hash configuration to apply
+ *
+ * Add @cfg to @vf if the context is valid and VSI exists; programs HW.
+ *
+ * Return:
+ * * 0 on success
+ * * -ENOENT if @cfg is invalid or VSI is missing
+ * * -EBUSY if hardware programming fails
+ */
+static int
+ice_hash_moveback(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg)
+{
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
+	struct ice_hw *hw = &vf->pf->hw;
+	int ret;
+
+	if (!ice_is_hash_cfg_valid(cfg) || !vsi)
+		return -ENOENT;
+
+	ret = ice_add_rss_cfg(hw, vsi, cfg);
+	if (ret) {
+		dev_err(dev, "ice_add_rss_cfg failed for VF %d, VSI %d, error:%d\n",
+			vf->vf_id, vf->lan_vsi_idx, ret);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_hash_remove - remove a RSS configuration
+ * @vf: pointer to the VF info
+ * @cfg: pointer to the RSS hash configuration
+ *
+ * This function will delete a RSS hash configuration and also delete the
+ * hash context which stores the rule info.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int
+ice_hash_remove(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg)
+{
+	int ret;
+
+	ret = ice_hash_moveout(vf, cfg);
+	if (ret && ret != -ENOENT)
+		return ret;
+
+	ice_hash_cfg_reset(cfg);
+
+	return 0;
+}
+
+struct ice_gtpu_ctx_action {
+	u32 ctx_idx;
+	const u32 *remove_list;
+	int remove_count;
+	const u32 *moveout_list;
+	int moveout_count;
+};
+
+/**
+ * ice_add_rss_cfg_pre_gtpu - Pre-process the GTPU RSS configuration
+ * @vf: pointer to the VF info
+ * @ctx: pointer to the context of the GTPU hash
+ * @ctx_idx: index of the hash context
+ *
+ * Pre-processes the GTPU hash configuration before adding a new
+ * hash context. It removes or reorders existing hash configurations that may
+ * conflict with the new one. For example, if a GTPU_UP or GTPU_DWN rule is
+ * configured after a GTPU_EH rule, the GTPU_EH hash will be matched first due
+ * to TCAM write and match order (top-down). In such cases, the GTPU_EH rule
+ * must be moved after the GTPU_UP/DWN rule. Conversely, if a GTPU_EH rule is
+ * configured after a GTPU_UP/DWN rule, the UP/DWN rules should be removed to
+ * avoid conflict.
+ *
+ * Return: 0 on success or a negative error code on failure
+ */
+static int ice_add_rss_cfg_pre_gtpu(struct ice_vf *vf,
+				    struct ice_vf_hash_gtpu_ctx *ctx,
+				    u32 ctx_idx)
+{
+	int ret, i;
+
+	static const u32 remove_eh_ip[] = {
+		ICE_HASH_GTPU_CTX_EH_IP_UDP, ICE_HASH_GTPU_CTX_EH_IP_TCP,
+		ICE_HASH_GTPU_CTX_UP_IP,     ICE_HASH_GTPU_CTX_UP_IP_UDP,
+		ICE_HASH_GTPU_CTX_UP_IP_TCP, ICE_HASH_GTPU_CTX_DW_IP,
+		ICE_HASH_GTPU_CTX_DW_IP_UDP, ICE_HASH_GTPU_CTX_DW_IP_TCP,
+	};
+
+	static const u32 remove_eh_ip_udp[] = {
+		ICE_HASH_GTPU_CTX_UP_IP_UDP,
+		ICE_HASH_GTPU_CTX_DW_IP_UDP,
+	};
+	static const u32 moveout_eh_ip_udp[] = {
+		ICE_HASH_GTPU_CTX_UP_IP,
+		ICE_HASH_GTPU_CTX_UP_IP_TCP,
+		ICE_HASH_GTPU_CTX_DW_IP,
+		ICE_HASH_GTPU_CTX_DW_IP_TCP,
+	};
+
+	static const u32 remove_eh_ip_tcp[] = {
+		ICE_HASH_GTPU_CTX_UP_IP_TCP,
+		ICE_HASH_GTPU_CTX_DW_IP_TCP,
+	};
+	static const u32 moveout_eh_ip_tcp[] = {
+		ICE_HASH_GTPU_CTX_UP_IP,
+		ICE_HASH_GTPU_CTX_UP_IP_UDP,
+		ICE_HASH_GTPU_CTX_DW_IP,
+		ICE_HASH_GTPU_CTX_DW_IP_UDP,
+	};
+
+	static const u32 remove_up_ip[] = {
+		ICE_HASH_GTPU_CTX_UP_IP_UDP,
+		ICE_HASH_GTPU_CTX_UP_IP_TCP,
+	};
+	static const u32 moveout_up_ip[] = {
+		ICE_HASH_GTPU_CTX_EH_IP,
+		ICE_HASH_GTPU_CTX_EH_IP_UDP,
+		ICE_HASH_GTPU_CTX_EH_IP_TCP,
+	};
+
+	static const u32 moveout_up_ip_udp_tcp[] = {
+		ICE_HASH_GTPU_CTX_EH_IP,
+		ICE_HASH_GTPU_CTX_EH_IP_UDP,
+		ICE_HASH_GTPU_CTX_EH_IP_TCP,
+	};
+
+	static const u32 remove_dw_ip[] = {
+		ICE_HASH_GTPU_CTX_DW_IP_UDP,
+		ICE_HASH_GTPU_CTX_DW_IP_TCP,
+	};
+	static const u32 moveout_dw_ip[] = {
+		ICE_HASH_GTPU_CTX_EH_IP,
+		ICE_HASH_GTPU_CTX_EH_IP_UDP,
+		ICE_HASH_GTPU_CTX_EH_IP_TCP,
+	};
+
+	static const struct ice_gtpu_ctx_action actions[] = {
+		{ ICE_HASH_GTPU_CTX_EH_IP, remove_eh_ip,
+		  ARRAY_SIZE(remove_eh_ip), NULL, 0 },
+		{ ICE_HASH_GTPU_CTX_EH_IP_UDP, remove_eh_ip_udp,
+		  ARRAY_SIZE(remove_eh_ip_udp), moveout_eh_ip_udp,
+		  ARRAY_SIZE(moveout_eh_ip_udp) },
+		{ ICE_HASH_GTPU_CTX_EH_IP_TCP, remove_eh_ip_tcp,
+		  ARRAY_SIZE(remove_eh_ip_tcp), moveout_eh_ip_tcp,
+		  ARRAY_SIZE(moveout_eh_ip_tcp) },
+		{ ICE_HASH_GTPU_CTX_UP_IP, remove_up_ip,
+		  ARRAY_SIZE(remove_up_ip), moveout_up_ip,
+		  ARRAY_SIZE(moveout_up_ip) },
+		{ ICE_HASH_GTPU_CTX_UP_IP_UDP, NULL, 0, moveout_up_ip_udp_tcp,
+		  ARRAY_SIZE(moveout_up_ip_udp_tcp) },
+		{ ICE_HASH_GTPU_CTX_UP_IP_TCP, NULL, 0, moveout_up_ip_udp_tcp,
+		  ARRAY_SIZE(moveout_up_ip_udp_tcp) },
+		{ ICE_HASH_GTPU_CTX_DW_IP, remove_dw_ip,
+		  ARRAY_SIZE(remove_dw_ip), moveout_dw_ip,
+		  ARRAY_SIZE(moveout_dw_ip) },
+		{ ICE_HASH_GTPU_CTX_DW_IP_UDP, NULL, 0, moveout_dw_ip,
+		  ARRAY_SIZE(moveout_dw_ip) },
+		{ ICE_HASH_GTPU_CTX_DW_IP_TCP, NULL, 0, moveout_dw_ip,
+		  ARRAY_SIZE(moveout_dw_ip) },
+	};
+
+	for (i = 0; i < ARRAY_SIZE(actions); i++) {
+		if (actions[i].ctx_idx != ctx_idx)
+			continue;
+
+		if (actions[i].remove_list) {
+			for (int j = 0; j < actions[i].remove_count; j++) {
+				u16 rm = actions[i].remove_list[j];
+
+				ret = ice_hash_remove(vf, &ctx->ctx[rm]);
+				if (ret && ret != -ENOENT)
+					return ret;
+			}
+		}
+
+		if (actions[i].moveout_list) {
+			for (int j = 0; j < actions[i].moveout_count; j++) {
+				u16 mv = actions[i].moveout_list[j];
+
+				ret = ice_hash_moveout(vf, &ctx->ctx[mv]);
+				if (ret && ret != -ENOENT)
+					return ret;
+			}
+		}
+		break;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_add_rss_cfg_pre_ip - Pre-process IP-layer RSS configuration
+ * @vf: VF pointer
+ * @ctx: IP L4 hash context (ESP/UDP-ESP/AH/PFCP and UDP/TCP/SCTP)
+ *
+ * Remove covered/recorded IP RSS configurations prior to adding a new one.
+ *
+ * Return: 0 on success; negative error code on failure.
+ */
+static int
+ice_add_rss_cfg_pre_ip(struct ice_vf *vf, struct ice_vf_hash_ip_ctx *ctx)
+{
+	int i, ret;
+
+	for (i = 1; i < ICE_HASH_IP_CTX_MAX; i++)
+		if (ice_is_hash_cfg_valid(&ctx->ctx[i])) {
+			ret = ice_hash_remove(vf, &ctx->ctx[i]);
+			if (ret)
+				return ret;
+		}
+
+	return 0;
+}
+
+/**
+ * ice_calc_gtpu_ctx_idx - Calculate GTPU hash context index
+ * @hdrs: Bitmask of protocol headers prefixed with ICE_FLOW_SEG_HDR_*
+ *
+ * Determine the GTPU hash context index based on the combination of
+ * encapsulation headers (GTPU_EH, GTPU_UP, GTPU_DWN) and transport
+ * protocols (UDP, TCP) within IPv4 or IPv6 flows.
+ *
+ * Return: A valid context index (0-8) if the header combination is supported,
+ *         or ICE_HASH_GTPU_CTX_MAX if the combination is invalid.
+ */
+static enum ice_hash_gtpu_ctx_type ice_calc_gtpu_ctx_idx(u32 hdrs)
+{
+	u32 eh_idx, ip_idx;
+
+	if (hdrs & ICE_FLOW_SEG_HDR_GTPU_EH)
+		eh_idx = 0;
+	else if (hdrs & ICE_FLOW_SEG_HDR_GTPU_UP)
+		eh_idx = 1;
+	else if (hdrs & ICE_FLOW_SEG_HDR_GTPU_DWN)
+		eh_idx = 2;
+	else
+		return ICE_HASH_GTPU_CTX_MAX;
+
+	ip_idx = 0;
+	if (hdrs & ICE_FLOW_SEG_HDR_UDP)
+		ip_idx = 1;
+	else if (hdrs & ICE_FLOW_SEG_HDR_TCP)
+		ip_idx = 2;
+
+	if (hdrs & (ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV6))
+		return eh_idx * 3 + ip_idx;
+	else
+		return ICE_HASH_GTPU_CTX_MAX;
+}
+
+/**
+ * ice_map_ip_ctx_idx - map the index of the IP L4 hash context
+ * @hdrs: protocol headers prefix with ICE_FLOW_SEG_HDR_XXX.
+ *
+ * The IP L4 hash context use the index to classify for IPv4/IPv6 with
+ * ESP/UDP_ESP/AH/PFCP and non-tunnel UDP/TCP/SCTP
+ * this function map the index based on the protocol headers.
+ *
+ * Return: The mapped IP context index on success, or ICE_HASH_IP_CTX_MAX
+ *         if no matching context is found.
+ */
+static u8 ice_map_ip_ctx_idx(u32 hdrs)
+{
+	u8 i;
+
+	static struct {
+		u32 hdrs;
+		u8 ctx_idx;
+	} ip_ctx_idx_map[] = {
+		{ ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV_OTHER |
+			ICE_FLOW_SEG_HDR_ESP,
+			ICE_HASH_IP_CTX_IP_ESP },
+		{ ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV_OTHER |
+			ICE_FLOW_SEG_HDR_NAT_T_ESP,
+			ICE_HASH_IP_CTX_IP_UDP_ESP },
+		{ ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV_OTHER |
+			ICE_FLOW_SEG_HDR_AH,
+			ICE_HASH_IP_CTX_IP_AH },
+		{ ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV_OTHER |
+			ICE_FLOW_SEG_HDR_PFCP_SESSION,
+			ICE_HASH_IP_CTX_IP_PFCP },
+		{ ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN |
+			ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_UDP,
+			ICE_HASH_IP_CTX_IP_UDP },
+		{ ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN |
+			ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_TCP,
+			ICE_HASH_IP_CTX_IP_TCP },
+		{ ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN |
+			ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_SCTP,
+			ICE_HASH_IP_CTX_IP_SCTP },
+		{ ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN |
+			ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV_OTHER,
+			ICE_HASH_IP_CTX_IP },
+		{ ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_IPV_OTHER |
+			ICE_FLOW_SEG_HDR_ESP,
+			ICE_HASH_IP_CTX_IP_ESP },
+		{ ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_IPV_OTHER |
+			ICE_FLOW_SEG_HDR_NAT_T_ESP,
+			ICE_HASH_IP_CTX_IP_UDP_ESP },
+		{ ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_IPV_OTHER |
+			ICE_FLOW_SEG_HDR_AH,
+			ICE_HASH_IP_CTX_IP_AH },
+		{ ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_IPV_OTHER |
+			ICE_FLOW_SEG_HDR_PFCP_SESSION,
+			ICE_HASH_IP_CTX_IP_PFCP },
+		{ ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN |
+			ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_UDP,
+			ICE_HASH_IP_CTX_IP_UDP },
+		{ ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN |
+			ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_TCP,
+			ICE_HASH_IP_CTX_IP_TCP },
+		{ ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN |
+			ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_SCTP,
+			ICE_HASH_IP_CTX_IP_SCTP },
+		{ ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN |
+			ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_IPV_OTHER,
+			ICE_HASH_IP_CTX_IP },
+		/* the remaining mappings are used for default RSS */
+		{ ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_UDP,
+			ICE_HASH_IP_CTX_IP_UDP },
+		{ ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_TCP,
+			ICE_HASH_IP_CTX_IP_TCP },
+		{ ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_SCTP,
+			ICE_HASH_IP_CTX_IP_SCTP },
+		{ ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV_OTHER,
+			ICE_HASH_IP_CTX_IP },
+		{ ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_UDP,
+			ICE_HASH_IP_CTX_IP_UDP },
+		{ ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_TCP,
+			ICE_HASH_IP_CTX_IP_TCP },
+		{ ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_SCTP,
+			ICE_HASH_IP_CTX_IP_SCTP },
+		{ ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_IPV_OTHER,
+			ICE_HASH_IP_CTX_IP },
+	};
+
+	for (i = 0; i < ARRAY_SIZE(ip_ctx_idx_map); i++) {
+		if (hdrs == ip_ctx_idx_map[i].hdrs)
+			return ip_ctx_idx_map[i].ctx_idx;
+	}
+
+	return ICE_HASH_IP_CTX_MAX;
+}
+
+/**
+ * ice_add_rss_cfg_pre - Prepare RSS configuration context for a VF
+ * @vf: pointer to the VF structure
+ * @cfg: pointer to the RSS hash configuration
+ *
+ * Prepare the RSS hash context for a given VF based on the additional
+ * protocol headers specified in @cfg. This includes pre-configuration
+ * for IP and GTPU-based flows.
+ *
+ * If the configuration matches a known IP context, the function sets up
+ * the appropriate IP hash context. If the configuration includes GTPU
+ * headers, it prepares the GTPU-specific context accordingly.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int
+ice_add_rss_cfg_pre(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg)
+{
+	u32 ice_gtpu_ctx_idx = ice_calc_gtpu_ctx_idx(cfg->addl_hdrs);
+	u8 ip_ctx_idx = ice_map_ip_ctx_idx(cfg->addl_hdrs);
+
+	if (ip_ctx_idx == ICE_HASH_IP_CTX_IP) {
+		int ret = 0;
+
+		if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV4)
+			ret = ice_add_rss_cfg_pre_ip(vf, &vf->hash_ctx.v4);
+		else if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV6)
+			ret = ice_add_rss_cfg_pre_ip(vf, &vf->hash_ctx.v6);
+
+		if (ret)
+			return ret;
+	}
+
+	if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV4) {
+		return ice_add_rss_cfg_pre_gtpu(vf, &vf->hash_ctx.ipv4,
+						ice_gtpu_ctx_idx);
+	} else if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV6) {
+		return ice_add_rss_cfg_pre_gtpu(vf, &vf->hash_ctx.ipv6,
+						ice_gtpu_ctx_idx);
+	}
+
+	return 0;
+}
+
+/**
+ * ice_add_rss_cfg_post_gtpu - Post-process GTPU RSS configuration
+ * @vf: pointer to the VF info
+ * @ctx: pointer to the context of the GTPU hash
+ * @cfg: pointer to the RSS hash configuration
+ * @ctx_idx: index of the hash context
+ *
+ * Post-processes the GTPU hash configuration after a new hash
+ * context has been successfully added. It updates the context with the new
+ * configuration and restores any previously removed hash contexts that need
+ * to be re-applied. This ensures proper TCAM rule ordering and avoids
+ * conflicts between overlapping GTPU rules.
+ *
+ * Return: 0 on success or a negative error code on failure
+ */
+static int ice_add_rss_cfg_post_gtpu(struct ice_vf *vf,
+				     struct ice_vf_hash_gtpu_ctx *ctx,
+				     struct ice_rss_hash_cfg *cfg, u32 ctx_idx)
+{
+	/* GTPU hash moveback lookup table indexed by context ID.
+	 * Each entry is a bitmap indicating which contexts need moveback
+	 * operations when the corresponding context index is processed.
+	 */
+	static const unsigned long
+		ice_gtpu_moveback_tbl[ICE_HASH_GTPU_CTX_MAX] = {
+			[ICE_HASH_GTPU_CTX_EH_IP] = 0,
+			[ICE_HASH_GTPU_CTX_EH_IP_UDP] =
+				BIT(ICE_HASH_GTPU_CTX_UP_IP) |
+				BIT(ICE_HASH_GTPU_CTX_UP_IP_TCP) |
+				BIT(ICE_HASH_GTPU_CTX_DW_IP) |
+				BIT(ICE_HASH_GTPU_CTX_DW_IP_TCP),
+			[ICE_HASH_GTPU_CTX_EH_IP_TCP] =
+				BIT(ICE_HASH_GTPU_CTX_UP_IP) |
+				BIT(ICE_HASH_GTPU_CTX_UP_IP_UDP) |
+				BIT(ICE_HASH_GTPU_CTX_DW_IP) |
+				BIT(ICE_HASH_GTPU_CTX_DW_IP_UDP),
+			[ICE_HASH_GTPU_CTX_UP_IP] =
+				BIT(ICE_HASH_GTPU_CTX_EH_IP) |
+				BIT(ICE_HASH_GTPU_CTX_EH_IP_UDP) |
+				BIT(ICE_HASH_GTPU_CTX_EH_IP_TCP),
+			[ICE_HASH_GTPU_CTX_UP_IP_UDP] =
+				BIT(ICE_HASH_GTPU_CTX_EH_IP) |
+				BIT(ICE_HASH_GTPU_CTX_EH_IP_UDP) |
+				BIT(ICE_HASH_GTPU_CTX_EH_IP_TCP),
+			[ICE_HASH_GTPU_CTX_UP_IP_TCP] =
+				BIT(ICE_HASH_GTPU_CTX_EH_IP) |
+				BIT(ICE_HASH_GTPU_CTX_EH_IP_UDP) |
+				BIT(ICE_HASH_GTPU_CTX_EH_IP_TCP),
+			[ICE_HASH_GTPU_CTX_DW_IP] =
+				BIT(ICE_HASH_GTPU_CTX_EH_IP) |
+				BIT(ICE_HASH_GTPU_CTX_EH_IP_UDP) |
+				BIT(ICE_HASH_GTPU_CTX_EH_IP_TCP),
+			[ICE_HASH_GTPU_CTX_DW_IP_UDP] =
+				BIT(ICE_HASH_GTPU_CTX_EH_IP) |
+				BIT(ICE_HASH_GTPU_CTX_EH_IP_UDP) |
+				BIT(ICE_HASH_GTPU_CTX_EH_IP_TCP),
+			[ICE_HASH_GTPU_CTX_DW_IP_TCP] =
+				BIT(ICE_HASH_GTPU_CTX_EH_IP) |
+				BIT(ICE_HASH_GTPU_CTX_EH_IP_UDP) |
+				BIT(ICE_HASH_GTPU_CTX_EH_IP_TCP),
+		};
+	unsigned long moveback_mask;
+	int ret;
+	int i;
+
+	if (unlikely(ctx_idx >= ICE_HASH_GTPU_CTX_MAX))
+		return 0;
+
+	ctx->ctx[ctx_idx].addl_hdrs = cfg->addl_hdrs;
+	ctx->ctx[ctx_idx].hash_flds = cfg->hash_flds;
+	ctx->ctx[ctx_idx].hdr_type = cfg->hdr_type;
+	ctx->ctx[ctx_idx].symm = cfg->symm;
+
+	moveback_mask = ice_gtpu_moveback_tbl[ctx_idx];
+	for_each_set_bit(i, &moveback_mask, ICE_HASH_GTPU_CTX_MAX) {
+		ret = ice_hash_moveback(vf, &ctx->ctx[i]);
+		if (ret && ret != -ENOENT)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int
+ice_add_rss_cfg_post(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg)
+{
+	u32 ice_gtpu_ctx_idx = ice_calc_gtpu_ctx_idx(cfg->addl_hdrs);
+	u8 ip_ctx_idx = ice_map_ip_ctx_idx(cfg->addl_hdrs);
+
+	if (ip_ctx_idx && ip_ctx_idx < ICE_HASH_IP_CTX_MAX) {
+		if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV4)
+			ice_hash_cfg_record(&vf->hash_ctx.v4.ctx[ip_ctx_idx], cfg);
+		else if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV6)
+			ice_hash_cfg_record(&vf->hash_ctx.v6.ctx[ip_ctx_idx], cfg);
+	}
+
+	if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV4) {
+		return ice_add_rss_cfg_post_gtpu(vf, &vf->hash_ctx.ipv4,
+						 cfg, ice_gtpu_ctx_idx);
+	} else if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV6) {
+		return ice_add_rss_cfg_post_gtpu(vf, &vf->hash_ctx.ipv6,
+						 cfg, ice_gtpu_ctx_idx);
+	}
+
+	return 0;
+}
+
+/**
+ * ice_rem_rss_cfg_post - post-process the RSS configuration
+ * @vf: pointer to the VF info
+ * @cfg: pointer to the RSS hash configuration
+ *
+ * Post process the RSS hash configuration after deleting a hash
+ * config. Such as, it will reset the hash context for the GTPU hash.
+ */
+static void
+ice_rem_rss_cfg_post(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg)
+{
+	u32 ice_gtpu_ctx_idx = ice_calc_gtpu_ctx_idx(cfg->addl_hdrs);
+	u8 ip_ctx_idx = ice_map_ip_ctx_idx(cfg->addl_hdrs);
+
+	if (ip_ctx_idx && ip_ctx_idx < ICE_HASH_IP_CTX_MAX) {
+		if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV4)
+			ice_hash_cfg_reset(&vf->hash_ctx.v4.ctx[ip_ctx_idx]);
+		else if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV6)
+			ice_hash_cfg_reset(&vf->hash_ctx.v6.ctx[ip_ctx_idx]);
+	}
+
+	if (ice_gtpu_ctx_idx >= ICE_HASH_GTPU_CTX_MAX)
+		return;
+
+	if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV4)
+		ice_hash_cfg_reset(&vf->hash_ctx.ipv4.ctx[ice_gtpu_ctx_idx]);
+	else if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV6)
+		ice_hash_cfg_reset(&vf->hash_ctx.ipv6.ctx[ice_gtpu_ctx_idx]);
+}
+
+/**
+ * ice_rem_rss_cfg_wrap - Wrapper for deleting an RSS configuration
+ * @vf: pointer to the VF info
+ * @cfg: pointer to the RSS hash configuration
+ *
+ * Wrapper function to delete a flow profile base on an RSS configuration,
+ * and also post process the hash context base on the rollback mechanism
+ * which handle some rules conflict by ice_add_rss_cfg_wrap.
+ *
+ * Return: 0 on success; negative error code on failure.
+ */
+static int
+ice_rem_rss_cfg_wrap(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg)
+{
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
+	struct ice_hw *hw = &vf->pf->hw;
+	int ret;
+
+	ret = ice_rem_rss_cfg(hw, vsi->idx, cfg);
+	/* We just ignore -ENOENT, because if two configurations share the same
+	 * profile remove one of them actually removes both, since the
+	 * profile is deleted.
+	 */
+	if (ret && ret != -ENOENT) {
+		dev_err(dev, "ice_rem_rss_cfg failed for VF %d, VSI %d, error:%d\n",
+			vf->vf_id, vf->lan_vsi_idx, ret);
+		return ret;
+	}
+
+	ice_rem_rss_cfg_post(vf, cfg);
+
+	return 0;
+}
+
+/**
+ * ice_add_rss_cfg_wrap - Wrapper for adding an RSS configuration
+ * @vf: pointer to the VF info
+ * @cfg: pointer to the RSS hash configuration
+ *
+ * Add a flow profile based on an RSS configuration. Use a rollback
+ * mechanism to handle rule conflicts due to TCAM
+ * write sequence from top to down.
+ *
+ * Return: 0 on success; negative error code on failure.
+ */
+static int
+ice_add_rss_cfg_wrap(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg)
+{
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
+	struct ice_hw *hw = &vf->pf->hw;
+	int ret;
+
+	if (ice_add_rss_cfg_pre(vf, cfg))
+		return -EINVAL;
+
+	ret = ice_add_rss_cfg(hw, vsi, cfg);
+	if (ret) {
+		dev_err(dev, "ice_add_rss_cfg failed for VF %d, VSI %d, error:%d\n",
+			vf->vf_id, vf->lan_vsi_idx, ret);
+		return ret;
+	}
+
+	if (ice_add_rss_cfg_post(vf, cfg))
+		ret = -EINVAL;
+
+	return ret;
+}
+
+/**
+ * ice_parse_raw_rss_pattern - Parse raw pattern spec and mask for RSS
+ * @vf: pointer to the VF info
+ * @proto: pointer to the virtchnl protocol header
+ * @raw_cfg: pointer to the RSS raw pattern configuration
+ *
+ * Parser function to get spec and mask from virtchnl message, and parse
+ * them to get the corresponding profile and offset. The profile is used
+ * to add RSS configuration.
+ *
+ * Return: 0 on success; negative error code on failure.
+ */
+static int
+ice_parse_raw_rss_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto,
+			  struct ice_rss_raw_cfg *raw_cfg)
+{
+	struct ice_parser_result pkt_parsed;
+	struct ice_hw *hw = &vf->pf->hw;
+	struct ice_parser_profile prof;
+	struct ice_parser *psr;
+	u8 *pkt_buf, *msk_buf;
+	u16 pkt_len;
+	int ret = 0;
+
+	pkt_len = proto->raw.pkt_len;
+	if (!pkt_len)
+		return -EINVAL;
+	if (pkt_len > VIRTCHNL_MAX_SIZE_RAW_PACKET)
+		pkt_len = VIRTCHNL_MAX_SIZE_RAW_PACKET;
+
+	pkt_buf = kzalloc(pkt_len, GFP_KERNEL);
+	msk_buf = kzalloc(pkt_len, GFP_KERNEL);
+	if (!pkt_buf || !msk_buf) {
+		ret = -ENOMEM;
+		goto free_alloc;
+	}
+
+	memcpy(pkt_buf, proto->raw.spec, pkt_len);
+	memcpy(msk_buf, proto->raw.mask, pkt_len);
+
+	psr = ice_parser_create(hw);
+	if (IS_ERR(psr)) {
+		ret = PTR_ERR(psr);
+		goto free_alloc;
+	}
+
+	ret = ice_parser_run(psr, pkt_buf, pkt_len, &pkt_parsed);
+	if (ret)
+		goto parser_destroy;
+
+	ret = ice_parser_profile_init(&pkt_parsed, pkt_buf, msk_buf,
+				      pkt_len, ICE_BLK_RSS, &prof);
+	if (ret)
+		goto parser_destroy;
+
+	memcpy(&raw_cfg->prof, &prof, sizeof(prof));
+
+parser_destroy:
+	ice_parser_destroy(psr);
+free_alloc:
+	kfree(pkt_buf);
+	kfree(msk_buf);
+	return ret;
+}
+
+/**
+ * ice_add_raw_rss_cfg - add RSS configuration for raw pattern
+ * @vf: pointer to the VF info
+ * @cfg: pointer to the RSS raw pattern configuration
+ *
+ * This function adds the RSS configuration for raw pattern.
+ * Check if current profile is matched. If not, remove the old
+ * one and add the new profile to HW directly. Update the symmetric
+ * hash configuration as well.
+ *
+ * Return: 0 on success; negative error code on failure.
+ */
+static int
+ice_add_raw_rss_cfg(struct ice_vf *vf, struct ice_rss_raw_cfg *cfg)
+{
+	struct ice_parser_profile *prof = &cfg->prof;
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	struct ice_rss_prof_info *rss_prof;
+	struct ice_hw *hw = &vf->pf->hw;
+	int i, ptg, ret = 0;
+	u16 vsi_handle;
+	u64 id;
+
+	vsi_handle = vf->lan_vsi_idx;
+	id = find_first_bit(prof->ptypes, ICE_FLOW_PTYPE_MAX);
+
+	ptg = hw->blk[ICE_BLK_RSS].xlt1.t[id];
+	rss_prof = &vf->rss_prof_info[ptg];
+
+	/* check if ptg already has a profile */
+	if (rss_prof->prof.fv_num) {
+		for (i = 0; i < ICE_MAX_FV_WORDS; i++) {
+			if (rss_prof->prof.fv[i].proto_id !=
+			    prof->fv[i].proto_id ||
+			    rss_prof->prof.fv[i].offset !=
+			    prof->fv[i].offset)
+				break;
+		}
+
+		/* current profile is matched, check symmetric hash */
+		if (i == ICE_MAX_FV_WORDS) {
+			if (rss_prof->symm != cfg->symm)
+				goto update_symm;
+			return ret;
+		}
+
+		/* current profile is not matched, remove it */
+		ret =
+		ice_rem_prof_id_flow(hw, ICE_BLK_RSS,
+				     ice_get_hw_vsi_num(hw, vsi_handle),
+				     id);
+		if (ret) {
+			dev_err(dev, "remove RSS flow failed\n");
+			return ret;
+		}
+
+		ret = ice_rem_prof(hw, ICE_BLK_RSS, id);
+		if (ret) {
+			dev_err(dev, "remove RSS profile failed\n");
+			return ret;
+		}
+	}
+
+	/* add new profile */
+	ret = ice_flow_set_parser_prof(hw, vsi_handle, 0, prof, ICE_BLK_RSS);
+	if (ret) {
+		dev_err(dev, "HW profile add failed\n");
+		return ret;
+	}
+
+	memcpy(&rss_prof->prof, prof, sizeof(struct ice_parser_profile));
+
+update_symm:
+	rss_prof->symm = cfg->symm;
+	ice_rss_update_raw_symm(hw, cfg, id);
+	return ret;
+}
+
+/**
+ * ice_rem_raw_rss_cfg - remove RSS configuration for raw pattern
+ * @vf: pointer to the VF info
+ * @cfg: pointer to the RSS raw pattern configuration
+ *
+ * This function removes the RSS configuration for raw pattern.
+ * Check if vsi group is already removed first. If not, remove the
+ * profile.
+ *
+ * Return: 0 on success; negative error code on failure.
+ */
+static int
+ice_rem_raw_rss_cfg(struct ice_vf *vf, struct ice_rss_raw_cfg *cfg)
+{
+	struct ice_parser_profile *prof = &cfg->prof;
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	struct ice_hw *hw = &vf->pf->hw;
+	int ptg, ret = 0;
+	u16 vsig, vsi;
+	u64 id;
+
+	id = find_first_bit(prof->ptypes, ICE_FLOW_PTYPE_MAX);
+
+	ptg = hw->blk[ICE_BLK_RSS].xlt1.t[id];
+
+	memset(&vf->rss_prof_info[ptg], 0,
+	       sizeof(struct ice_rss_prof_info));
+
+	/* check if vsig is already removed */
+	vsi = ice_get_hw_vsi_num(hw, vf->lan_vsi_idx);
+	if (vsi >= ICE_MAX_VSI) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	vsig = hw->blk[ICE_BLK_RSS].xlt2.vsis[vsi].vsig;
+	if (vsig) {
+		ret = ice_rem_prof_id_flow(hw, ICE_BLK_RSS, vsi, id);
+		if (ret)
+			goto err;
+
+		ret = ice_rem_prof(hw, ICE_BLK_RSS, id);
+		if (ret)
+			goto err;
+	}
+
+	return ret;
+
+err:
+	dev_err(dev, "HW profile remove failed\n");
+	return ret;
+}
+
+/**
+ * ice_vc_handle_rss_cfg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the message buffer
+ * @add: add a RSS config if true, otherwise delete a RSS config
+ *
+ * This function adds/deletes a RSS config
+ */
+int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add)
+{
+	u32 v_opcode = add ? VIRTCHNL_OP_ADD_RSS_CFG : VIRTCHNL_OP_DEL_RSS_CFG;
+	struct virtchnl_rss_cfg *rss_cfg = (struct virtchnl_rss_cfg *)msg;
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	struct ice_hw *hw = &vf->pf->hw;
+	struct ice_vsi *vsi;
+	u8 hash_type;
+	bool symm;
+	int ret;
+
+	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
+		dev_dbg(dev, "VF %d attempting to configure RSS, but RSS is not supported by the PF\n",
+			vf->vf_id);
+		v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED;
+		goto error_param;
+	}
+
+	if (!ice_vf_adv_rss_offload_ena(vf->driver_caps)) {
+		dev_dbg(dev, "VF %d attempting to configure RSS, but Advanced RSS offload is not supported\n",
+			vf->vf_id);
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (rss_cfg->proto_hdrs.count > VIRTCHNL_MAX_NUM_PROTO_HDRS ||
+	    rss_cfg->rss_algorithm < VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC ||
+	    rss_cfg->rss_algorithm > VIRTCHNL_RSS_ALG_XOR_SYMMETRIC) {
+		dev_dbg(dev, "VF %d attempting to configure RSS, but RSS configuration is not valid\n",
+			vf->vf_id);
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_R_ASYMMETRIC) {
+		hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_HASH_XOR :
+				  ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ;
+
+		ret = ice_vc_rss_hash_update(hw, vsi, hash_type);
+		if (ret)
+			v_ret = ice_err_to_virt_err(ret);
+		goto error_param;
+	}
+
+	hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ :
+			  ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ;
+	ret = ice_vc_rss_hash_update(hw, vsi, hash_type);
+	if (ret) {
+		v_ret = ice_err_to_virt_err(ret);
+		goto error_param;
+	}
+
+	symm = rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC;
+	/* Configure RSS hash for raw pattern */
+	if (rss_cfg->proto_hdrs.tunnel_level == 0 &&
+	    rss_cfg->proto_hdrs.count == 0) {
+		struct ice_rss_raw_cfg raw_cfg;
+
+		if (ice_parse_raw_rss_pattern(vf, &rss_cfg->proto_hdrs,
+					      &raw_cfg)) {
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+
+		if (add) {
+			raw_cfg.symm = symm;
+			if (ice_add_raw_rss_cfg(vf, &raw_cfg))
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		} else {
+			if (ice_rem_raw_rss_cfg(vf, &raw_cfg))
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		}
+	} else {
+		struct ice_rss_hash_cfg cfg;
+
+		/* Only check for none raw pattern case */
+		if (!ice_vc_validate_pattern(vf, &rss_cfg->proto_hdrs)) {
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+		cfg.addl_hdrs = ICE_FLOW_SEG_HDR_NONE;
+		cfg.hash_flds = ICE_HASH_INVALID;
+		cfg.hdr_type = ICE_RSS_ANY_HEADERS;
+
+		if (!ice_vc_parse_rss_cfg(hw, rss_cfg, &cfg)) {
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+
+		if (add) {
+			cfg.symm = symm;
+			if (ice_add_rss_cfg_wrap(vf, &cfg))
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		} else {
+			if (ice_rem_rss_cfg_wrap(vf, &cfg))
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		}
+	}
+
+error_param:
+	return ice_vc_send_msg_to_vf(vf, v_opcode, v_ret, NULL, 0);
+}
+
+/**
+ * ice_vc_config_rss_key
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * Configure the VF's RSS key
+ */
+int ice_vc_config_rss_key(struct ice_vf *vf, u8 *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct virtchnl_rss_key *vrk =
+		(struct virtchnl_rss_key *)msg;
+	struct ice_vsi *vsi;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!ice_vc_isvalid_vsi_id(vf, vrk->vsi_id)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (ice_set_rss_key(vsi, vrk->key))
+		v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
+error_param:
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_KEY, v_ret,
+				     NULL, 0);
+}
+
+/**
+ * ice_vc_config_rss_lut
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * Configure the VF's RSS LUT
+ */
+int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg)
+{
+	struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg;
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct ice_vsi *vsi;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!ice_vc_isvalid_vsi_id(vf, vrl->vsi_id)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (vrl->lut_entries != ICE_LUT_VSI_SIZE) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (ice_set_rss_lut(vsi, vrl->lut, ICE_LUT_VSI_SIZE))
+		v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
+error_param:
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_LUT, v_ret,
+				     NULL, 0);
+}
+
+/**
+ * ice_vc_config_rss_hfunc
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * Configure the VF's RSS Hash function
+ */
+int ice_vc_config_rss_hfunc(struct ice_vf *vf, u8 *msg)
+{
+	struct virtchnl_rss_hfunc *vrh = (struct virtchnl_rss_hfunc *)msg;
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	u8 hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ;
+	struct ice_vsi *vsi;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!ice_vc_isvalid_vsi_id(vf, vrh->vsi_id)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (vrh->rss_algorithm == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC)
+		hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ;
+
+	if (ice_set_rss_hfunc(vsi, hfunc))
+		v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
+error_param:
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_HFUNC, v_ret,
+				     NULL, 0);
+}
+
+/**
+ * ice_vc_get_rss_hashcfg - return the RSS Hash configuration
+ * @vf: pointer to the VF info
+ */
+int ice_vc_get_rss_hashcfg(struct ice_vf *vf)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct virtchnl_rss_hashcfg *vrh = NULL;
+	int len = 0, ret;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
+		dev_err(ice_pf_to_dev(vf->pf), "RSS not supported by PF\n");
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	len = sizeof(struct virtchnl_rss_hashcfg);
+	vrh = kzalloc(len, GFP_KERNEL);
+	if (!vrh) {
+		v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
+		len = 0;
+		goto err;
+	}
+
+	vrh->hashcfg = ICE_DEFAULT_RSS_HASHCFG;
+err:
+	/* send the response back to the VF */
+	ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS, v_ret,
+				    (u8 *)vrh, len);
+	kfree(vrh);
+	return ret;
+}
+
+/**
+ * ice_vc_set_rss_hashcfg - set RSS Hash configuration bits for the VF
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ */
+int ice_vc_set_rss_hashcfg(struct ice_vf *vf, u8 *msg)
+{
+	struct virtchnl_rss_hashcfg *vrh = (struct virtchnl_rss_hashcfg *)msg;
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct ice_pf *pf = vf->pf;
+	struct ice_vsi *vsi;
+	struct device *dev;
+	int status;
+
+	dev = ice_pf_to_dev(pf);
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
+		dev_err(dev, "RSS not supported by PF\n");
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	/* clear all previously programmed RSS configuration to allow VF drivers
+	 * the ability to customize the RSS configuration and/or completely
+	 * disable RSS
+	 */
+	status = ice_rem_vsi_rss_cfg(&pf->hw, vsi->idx);
+	if (status && !vrh->hashcfg) {
+		/* only report failure to clear the current RSS configuration if
+		 * that was clearly the VF's intention (i.e. vrh->hashcfg = 0)
+		 */
+		v_ret = ice_err_to_virt_err(status);
+		goto err;
+	} else if (status) {
+		/* allow the VF to update the RSS configuration even on failure
+		 * to clear the current RSS confguration in an attempt to keep
+		 * RSS in a working state
+		 */
+		dev_warn(dev, "Failed to clear the RSS configuration for VF %u\n",
+			 vf->vf_id);
+	}
+
+	if (vrh->hashcfg) {
+		status = ice_add_avf_rss_cfg(&pf->hw, vsi, vrh->hashcfg);
+		v_ret = ice_err_to_virt_err(status);
+	}
+
+	/* save the requested VF configuration */
+	if (!v_ret)
+		vf->rss_hashcfg = vrh->hashcfg;
+
+	/* send the response to the VF */
+err:
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_SET_RSS_HASHCFG, v_ret,
+				     NULL, 0);
+}
+
diff --git a/drivers/net/ethernet/intel/ice/virt/rss.h b/drivers/net/ethernet/intel/ice/virt/rss.h
new file mode 100644
index 000000000000..784d4c43ce8b
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/virt/rss.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2022, Intel Corporation. */
+
+#ifndef _ICE_VIRT_RSS_H_
+#define _ICE_VIRT_RSS_H_
+
+#include <linux/types.h>
+
+struct ice_vf;
+
+int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add);
+int ice_vc_config_rss_key(struct ice_vf *vf, u8 *msg);
+int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg);
+int ice_vc_config_rss_hfunc(struct ice_vf *vf, u8 *msg);
+int ice_vc_get_rss_hashcfg(struct ice_vf *vf);
+int ice_vc_set_rss_hashcfg(struct ice_vf *vf, u8 *msg);
+
+#endif /* _ICE_VIRT_RSS_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/virt/virtchnl.c
index ff4ad788d96a..f3f921134379 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/virt/virtchnl.c
@@ -1,170 +1,20 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (C) 2022, Intel Corporation. */
 
-#include "ice_virtchnl.h"
+#include "virtchnl.h"
+#include "queues.h"
+#include "rss.h"
 #include "ice_vf_lib_private.h"
 #include "ice.h"
 #include "ice_base.h"
 #include "ice_lib.h"
 #include "ice_fltr.h"
-#include "ice_virtchnl_allowlist.h"
+#include "allowlist.h"
 #include "ice_vf_vsi_vlan_ops.h"
 #include "ice_vlan.h"
 #include "ice_flex_pipe.h"
 #include "ice_dcb_lib.h"
 
-#define FIELD_SELECTOR(proto_hdr_field) \
-		BIT((proto_hdr_field) & PROTO_HDR_FIELD_MASK)
-
-struct ice_vc_hdr_match_type {
-	u32 vc_hdr;	/* virtchnl headers (VIRTCHNL_PROTO_HDR_XXX) */
-	u32 ice_hdr;	/* ice headers (ICE_FLOW_SEG_HDR_XXX) */
-};
-
-static const struct ice_vc_hdr_match_type ice_vc_hdr_list[] = {
-	{VIRTCHNL_PROTO_HDR_NONE,	ICE_FLOW_SEG_HDR_NONE},
-	{VIRTCHNL_PROTO_HDR_ETH,	ICE_FLOW_SEG_HDR_ETH},
-	{VIRTCHNL_PROTO_HDR_S_VLAN,	ICE_FLOW_SEG_HDR_VLAN},
-	{VIRTCHNL_PROTO_HDR_C_VLAN,	ICE_FLOW_SEG_HDR_VLAN},
-	{VIRTCHNL_PROTO_HDR_IPV4,	ICE_FLOW_SEG_HDR_IPV4 |
-					ICE_FLOW_SEG_HDR_IPV_OTHER},
-	{VIRTCHNL_PROTO_HDR_IPV6,	ICE_FLOW_SEG_HDR_IPV6 |
-					ICE_FLOW_SEG_HDR_IPV_OTHER},
-	{VIRTCHNL_PROTO_HDR_TCP,	ICE_FLOW_SEG_HDR_TCP},
-	{VIRTCHNL_PROTO_HDR_UDP,	ICE_FLOW_SEG_HDR_UDP},
-	{VIRTCHNL_PROTO_HDR_SCTP,	ICE_FLOW_SEG_HDR_SCTP},
-	{VIRTCHNL_PROTO_HDR_PPPOE,	ICE_FLOW_SEG_HDR_PPPOE},
-	{VIRTCHNL_PROTO_HDR_GTPU_IP,	ICE_FLOW_SEG_HDR_GTPU_IP},
-	{VIRTCHNL_PROTO_HDR_GTPU_EH,	ICE_FLOW_SEG_HDR_GTPU_EH},
-	{VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_DWN,
-					ICE_FLOW_SEG_HDR_GTPU_DWN},
-	{VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_UP,
-					ICE_FLOW_SEG_HDR_GTPU_UP},
-	{VIRTCHNL_PROTO_HDR_L2TPV3,	ICE_FLOW_SEG_HDR_L2TPV3},
-	{VIRTCHNL_PROTO_HDR_ESP,	ICE_FLOW_SEG_HDR_ESP},
-	{VIRTCHNL_PROTO_HDR_AH,		ICE_FLOW_SEG_HDR_AH},
-	{VIRTCHNL_PROTO_HDR_PFCP,	ICE_FLOW_SEG_HDR_PFCP_SESSION},
-};
-
-struct ice_vc_hash_field_match_type {
-	u32 vc_hdr;		/* virtchnl headers
-				 * (VIRTCHNL_PROTO_HDR_XXX)
-				 */
-	u32 vc_hash_field;	/* virtchnl hash fields selector
-				 * FIELD_SELECTOR((VIRTCHNL_PROTO_HDR_ETH_XXX))
-				 */
-	u64 ice_hash_field;	/* ice hash fields
-				 * (BIT_ULL(ICE_FLOW_FIELD_IDX_XXX))
-				 */
-};
-
-static const struct
-ice_vc_hash_field_match_type ice_vc_hash_field_list[] = {
-	{VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_SRC),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_SA)},
-	{VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_DST),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_DA)},
-	{VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_SRC) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_DST),
-		ICE_FLOW_HASH_ETH},
-	{VIRTCHNL_PROTO_HDR_ETH,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_ETHERTYPE),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_TYPE)},
-	{VIRTCHNL_PROTO_HDR_S_VLAN,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_S_VLAN_ID),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_S_VLAN)},
-	{VIRTCHNL_PROTO_HDR_C_VLAN,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_C_VLAN_ID),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_C_VLAN)},
-	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA)},
-	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)},
-	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST),
-		ICE_FLOW_HASH_IPV4},
-	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) |
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)},
-	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) |
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)},
-	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT),
-		ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)},
-	{VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)},
-	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA)},
-	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA)},
-	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST),
-		ICE_FLOW_HASH_IPV6},
-	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA) |
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)},
-	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA) |
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)},
-	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT),
-		ICE_FLOW_HASH_IPV6 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)},
-	{VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)},
-	{VIRTCHNL_PROTO_HDR_TCP,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT)},
-	{VIRTCHNL_PROTO_HDR_TCP,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT)},
-	{VIRTCHNL_PROTO_HDR_TCP,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT),
-		ICE_FLOW_HASH_TCP_PORT},
-	{VIRTCHNL_PROTO_HDR_UDP,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT)},
-	{VIRTCHNL_PROTO_HDR_UDP,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT)},
-	{VIRTCHNL_PROTO_HDR_UDP,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT),
-		ICE_FLOW_HASH_UDP_PORT},
-	{VIRTCHNL_PROTO_HDR_SCTP,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT)},
-	{VIRTCHNL_PROTO_HDR_SCTP,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT)},
-	{VIRTCHNL_PROTO_HDR_SCTP,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT) |
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT),
-		ICE_FLOW_HASH_SCTP_PORT},
-	{VIRTCHNL_PROTO_HDR_PPPOE,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_PPPOE_SESS_ID),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID)},
-	{VIRTCHNL_PROTO_HDR_GTPU_IP,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_GTPU_IP_TEID),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_IP_TEID)},
-	{VIRTCHNL_PROTO_HDR_L2TPV3,
-		FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_L2TPV3_SESS_ID),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV3_SESS_ID)},
-	{VIRTCHNL_PROTO_HDR_ESP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ESP_SPI),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_ESP_SPI)},
-	{VIRTCHNL_PROTO_HDR_AH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_AH_SPI),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_AH_SPI)},
-	{VIRTCHNL_PROTO_HDR_PFCP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_PFCP_SEID),
-		BIT_ULL(ICE_FLOW_FIELD_IDX_PFCP_SEID)},
-};
-
 /**
  * ice_vc_vf_broadcast - Broadcast a message to all VFs on PF
  * @pf: pointer to the PF structure
@@ -304,10 +154,10 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode,
 
 	aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval,
 				       msg, msglen, NULL);
-	if (aq_ret && pf->hw.mailboxq.sq_last_status != ICE_AQ_RC_ENOSYS) {
+	if (aq_ret && pf->hw.mailboxq.sq_last_status != LIBIE_AQ_RC_ENOSYS) {
 		dev_info(dev, "Unable to send the message to VF %d ret %d aq_err %s\n",
 			 vf->vf_id, aq_ret,
-			 ice_aq_str(pf->hw.mailboxq.sq_last_status));
+			 libie_aq_str(pf->hw.mailboxq.sq_last_status));
 		return -EIO;
 	}
 
@@ -338,28 +188,6 @@ static int ice_vc_get_ver_msg(struct ice_vf *vf, u8 *msg)
 }
 
 /**
- * ice_vc_get_max_frame_size - get max frame size allowed for VF
- * @vf: VF used to determine max frame size
- *
- * Max frame size is determined based on the current port's max frame size and
- * whether a port VLAN is configured on this VF. The VF is not aware whether
- * it's in a port VLAN so the PF needs to account for this in max frame size
- * checks and sending the max frame size to the VF.
- */
-static u16 ice_vc_get_max_frame_size(struct ice_vf *vf)
-{
-	struct ice_port_info *pi = ice_vf_get_port_info(vf);
-	u16 max_frame_size;
-
-	max_frame_size = pi->phy.link_info.max_frame_size;
-
-	if (ice_vf_is_port_vlan_ena(vf))
-		max_frame_size -= VLAN_HLEN;
-
-	return max_frame_size;
-}
-
-/**
  * ice_vc_get_vlan_caps
  * @hw: pointer to the hw
  * @vf: pointer to the VF info
@@ -498,6 +326,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_QOS)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_QOS;
 
+	if (vf->driver_caps & VIRTCHNL_VF_CAP_PTP)
+		vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_PTP;
+
 	vfres->num_vsis = 1;
 	/* Tx and Rx queue are equal for VF */
 	vfres->num_queue_pairs = vsi->num_txq;
@@ -556,488 +387,6 @@ bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id)
 }
 
 /**
- * ice_vc_isvalid_q_id
- * @vsi: VSI to check queue ID against
- * @qid: VSI relative queue ID
- *
- * check for the valid queue ID
- */
-static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u8 qid)
-{
-	/* allocated Tx and Rx queues should be always equal for VF VSI */
-	return qid < vsi->alloc_txq;
-}
-
-/**
- * ice_vc_isvalid_ring_len
- * @ring_len: length of ring
- *
- * check for the valid ring count, should be multiple of ICE_REQ_DESC_MULTIPLE
- * or zero
- */
-static bool ice_vc_isvalid_ring_len(u16 ring_len)
-{
-	return ring_len == 0 ||
-	       (ring_len >= ICE_MIN_NUM_DESC &&
-		ring_len <= ICE_MAX_NUM_DESC &&
-		!(ring_len % ICE_REQ_DESC_MULTIPLE));
-}
-
-/**
- * ice_vc_validate_pattern
- * @vf: pointer to the VF info
- * @proto: virtchnl protocol headers
- *
- * validate the pattern is supported or not.
- *
- * Return: true on success, false on error.
- */
-bool
-ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto)
-{
-	bool is_ipv4 = false;
-	bool is_ipv6 = false;
-	bool is_udp = false;
-	u16 ptype = -1;
-	int i = 0;
-
-	while (i < proto->count &&
-	       proto->proto_hdr[i].type != VIRTCHNL_PROTO_HDR_NONE) {
-		switch (proto->proto_hdr[i].type) {
-		case VIRTCHNL_PROTO_HDR_ETH:
-			ptype = ICE_PTYPE_MAC_PAY;
-			break;
-		case VIRTCHNL_PROTO_HDR_IPV4:
-			ptype = ICE_PTYPE_IPV4_PAY;
-			is_ipv4 = true;
-			break;
-		case VIRTCHNL_PROTO_HDR_IPV6:
-			ptype = ICE_PTYPE_IPV6_PAY;
-			is_ipv6 = true;
-			break;
-		case VIRTCHNL_PROTO_HDR_UDP:
-			if (is_ipv4)
-				ptype = ICE_PTYPE_IPV4_UDP_PAY;
-			else if (is_ipv6)
-				ptype = ICE_PTYPE_IPV6_UDP_PAY;
-			is_udp = true;
-			break;
-		case VIRTCHNL_PROTO_HDR_TCP:
-			if (is_ipv4)
-				ptype = ICE_PTYPE_IPV4_TCP_PAY;
-			else if (is_ipv6)
-				ptype = ICE_PTYPE_IPV6_TCP_PAY;
-			break;
-		case VIRTCHNL_PROTO_HDR_SCTP:
-			if (is_ipv4)
-				ptype = ICE_PTYPE_IPV4_SCTP_PAY;
-			else if (is_ipv6)
-				ptype = ICE_PTYPE_IPV6_SCTP_PAY;
-			break;
-		case VIRTCHNL_PROTO_HDR_GTPU_IP:
-		case VIRTCHNL_PROTO_HDR_GTPU_EH:
-			if (is_ipv4)
-				ptype = ICE_MAC_IPV4_GTPU;
-			else if (is_ipv6)
-				ptype = ICE_MAC_IPV6_GTPU;
-			goto out;
-		case VIRTCHNL_PROTO_HDR_L2TPV3:
-			if (is_ipv4)
-				ptype = ICE_MAC_IPV4_L2TPV3;
-			else if (is_ipv6)
-				ptype = ICE_MAC_IPV6_L2TPV3;
-			goto out;
-		case VIRTCHNL_PROTO_HDR_ESP:
-			if (is_ipv4)
-				ptype = is_udp ? ICE_MAC_IPV4_NAT_T_ESP :
-						ICE_MAC_IPV4_ESP;
-			else if (is_ipv6)
-				ptype = is_udp ? ICE_MAC_IPV6_NAT_T_ESP :
-						ICE_MAC_IPV6_ESP;
-			goto out;
-		case VIRTCHNL_PROTO_HDR_AH:
-			if (is_ipv4)
-				ptype = ICE_MAC_IPV4_AH;
-			else if (is_ipv6)
-				ptype = ICE_MAC_IPV6_AH;
-			goto out;
-		case VIRTCHNL_PROTO_HDR_PFCP:
-			if (is_ipv4)
-				ptype = ICE_MAC_IPV4_PFCP_SESSION;
-			else if (is_ipv6)
-				ptype = ICE_MAC_IPV6_PFCP_SESSION;
-			goto out;
-		default:
-			break;
-		}
-		i++;
-	}
-
-out:
-	return ice_hw_ptype_ena(&vf->pf->hw, ptype);
-}
-
-/**
- * ice_vc_parse_rss_cfg - parses hash fields and headers from
- * a specific virtchnl RSS cfg
- * @hw: pointer to the hardware
- * @rss_cfg: pointer to the virtchnl RSS cfg
- * @hash_cfg: pointer to the HW hash configuration
- *
- * Return true if all the protocol header and hash fields in the RSS cfg could
- * be parsed, else return false
- *
- * This function parses the virtchnl RSS cfg to be the intended
- * hash fields and the intended header for RSS configuration
- */
-static bool ice_vc_parse_rss_cfg(struct ice_hw *hw,
-				 struct virtchnl_rss_cfg *rss_cfg,
-				 struct ice_rss_hash_cfg *hash_cfg)
-{
-	const struct ice_vc_hash_field_match_type *hf_list;
-	const struct ice_vc_hdr_match_type *hdr_list;
-	int i, hf_list_len, hdr_list_len;
-	u32 *addl_hdrs = &hash_cfg->addl_hdrs;
-	u64 *hash_flds = &hash_cfg->hash_flds;
-
-	/* set outer layer RSS as default */
-	hash_cfg->hdr_type = ICE_RSS_OUTER_HEADERS;
-
-	if (rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC)
-		hash_cfg->symm = true;
-	else
-		hash_cfg->symm = false;
-
-	hf_list = ice_vc_hash_field_list;
-	hf_list_len = ARRAY_SIZE(ice_vc_hash_field_list);
-	hdr_list = ice_vc_hdr_list;
-	hdr_list_len = ARRAY_SIZE(ice_vc_hdr_list);
-
-	for (i = 0; i < rss_cfg->proto_hdrs.count; i++) {
-		struct virtchnl_proto_hdr *proto_hdr =
-					&rss_cfg->proto_hdrs.proto_hdr[i];
-		bool hdr_found = false;
-		int j;
-
-		/* Find matched ice headers according to virtchnl headers. */
-		for (j = 0; j < hdr_list_len; j++) {
-			struct ice_vc_hdr_match_type hdr_map = hdr_list[j];
-
-			if (proto_hdr->type == hdr_map.vc_hdr) {
-				*addl_hdrs |= hdr_map.ice_hdr;
-				hdr_found = true;
-			}
-		}
-
-		if (!hdr_found)
-			return false;
-
-		/* Find matched ice hash fields according to
-		 * virtchnl hash fields.
-		 */
-		for (j = 0; j < hf_list_len; j++) {
-			struct ice_vc_hash_field_match_type hf_map = hf_list[j];
-
-			if (proto_hdr->type == hf_map.vc_hdr &&
-			    proto_hdr->field_selector == hf_map.vc_hash_field) {
-				*hash_flds |= hf_map.ice_hash_field;
-				break;
-			}
-		}
-	}
-
-	return true;
-}
-
-/**
- * ice_vf_adv_rss_offload_ena - determine if capabilities support advanced
- * RSS offloads
- * @caps: VF driver negotiated capabilities
- *
- * Return true if VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability is set,
- * else return false
- */
-static bool ice_vf_adv_rss_offload_ena(u32 caps)
-{
-	return !!(caps & VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF);
-}
-
-/**
- * ice_vc_handle_rss_cfg
- * @vf: pointer to the VF info
- * @msg: pointer to the message buffer
- * @add: add a RSS config if true, otherwise delete a RSS config
- *
- * This function adds/deletes a RSS config
- */
-static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add)
-{
-	u32 v_opcode = add ? VIRTCHNL_OP_ADD_RSS_CFG : VIRTCHNL_OP_DEL_RSS_CFG;
-	struct virtchnl_rss_cfg *rss_cfg = (struct virtchnl_rss_cfg *)msg;
-	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct device *dev = ice_pf_to_dev(vf->pf);
-	struct ice_hw *hw = &vf->pf->hw;
-	struct ice_vsi *vsi;
-
-	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
-		dev_dbg(dev, "VF %d attempting to configure RSS, but RSS is not supported by the PF\n",
-			vf->vf_id);
-		v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED;
-		goto error_param;
-	}
-
-	if (!ice_vf_adv_rss_offload_ena(vf->driver_caps)) {
-		dev_dbg(dev, "VF %d attempting to configure RSS, but Advanced RSS offload is not supported\n",
-			vf->vf_id);
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (rss_cfg->proto_hdrs.count > VIRTCHNL_MAX_NUM_PROTO_HDRS ||
-	    rss_cfg->rss_algorithm < VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC ||
-	    rss_cfg->rss_algorithm > VIRTCHNL_RSS_ALG_XOR_SYMMETRIC) {
-		dev_dbg(dev, "VF %d attempting to configure RSS, but RSS configuration is not valid\n",
-			vf->vf_id);
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (!ice_vc_validate_pattern(vf, &rss_cfg->proto_hdrs)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_R_ASYMMETRIC) {
-		struct ice_vsi_ctx *ctx;
-		u8 lut_type, hash_type;
-		int status;
-
-		lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI;
-		hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_HASH_XOR :
-				ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ;
-
-		ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
-		if (!ctx) {
-			v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
-			goto error_param;
-		}
-
-		ctx->info.q_opt_rss =
-			FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_LUT_M, lut_type) |
-			FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hash_type);
-
-		/* Preserve existing queueing option setting */
-		ctx->info.q_opt_rss |= (vsi->info.q_opt_rss &
-					  ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_M);
-		ctx->info.q_opt_tc = vsi->info.q_opt_tc;
-		ctx->info.q_opt_flags = vsi->info.q_opt_rss;
-
-		ctx->info.valid_sections =
-				cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID);
-
-		status = ice_update_vsi(hw, vsi->idx, ctx, NULL);
-		if (status) {
-			dev_err(dev, "update VSI for RSS failed, err %d aq_err %s\n",
-				status, ice_aq_str(hw->adminq.sq_last_status));
-			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		} else {
-			vsi->info.q_opt_rss = ctx->info.q_opt_rss;
-		}
-
-		kfree(ctx);
-	} else {
-		struct ice_rss_hash_cfg cfg;
-
-		/* Only check for none raw pattern case */
-		if (!ice_vc_validate_pattern(vf, &rss_cfg->proto_hdrs)) {
-			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-			goto error_param;
-		}
-		cfg.addl_hdrs = ICE_FLOW_SEG_HDR_NONE;
-		cfg.hash_flds = ICE_HASH_INVALID;
-		cfg.hdr_type = ICE_RSS_ANY_HEADERS;
-
-		if (!ice_vc_parse_rss_cfg(hw, rss_cfg, &cfg)) {
-			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-			goto error_param;
-		}
-
-		if (add) {
-			if (ice_add_rss_cfg(hw, vsi, &cfg)) {
-				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-				dev_err(dev, "ice_add_rss_cfg failed for vsi = %d, v_ret = %d\n",
-					vsi->vsi_num, v_ret);
-			}
-		} else {
-			int status;
-
-			status = ice_rem_rss_cfg(hw, vsi->idx, &cfg);
-			/* We just ignore -ENOENT, because if two configurations
-			 * share the same profile remove one of them actually
-			 * removes both, since the profile is deleted.
-			 */
-			if (status && status != -ENOENT) {
-				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-				dev_err(dev, "ice_rem_rss_cfg failed for VF ID:%d, error:%d\n",
-					vf->vf_id, status);
-			}
-		}
-	}
-
-error_param:
-	return ice_vc_send_msg_to_vf(vf, v_opcode, v_ret, NULL, 0);
-}
-
-/**
- * ice_vc_config_rss_key
- * @vf: pointer to the VF info
- * @msg: pointer to the msg buffer
- *
- * Configure the VF's RSS key
- */
-static int ice_vc_config_rss_key(struct ice_vf *vf, u8 *msg)
-{
-	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct virtchnl_rss_key *vrk =
-		(struct virtchnl_rss_key *)msg;
-	struct ice_vsi *vsi;
-
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (!ice_vc_isvalid_vsi_id(vf, vrk->vsi_id)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (ice_set_rss_key(vsi, vrk->key))
-		v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
-error_param:
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_KEY, v_ret,
-				     NULL, 0);
-}
-
-/**
- * ice_vc_config_rss_lut
- * @vf: pointer to the VF info
- * @msg: pointer to the msg buffer
- *
- * Configure the VF's RSS LUT
- */
-static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg)
-{
-	struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg;
-	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct ice_vsi *vsi;
-
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (!ice_vc_isvalid_vsi_id(vf, vrl->vsi_id)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (vrl->lut_entries != ICE_LUT_VSI_SIZE) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (ice_set_rss_lut(vsi, vrl->lut, ICE_LUT_VSI_SIZE))
-		v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
-error_param:
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_LUT, v_ret,
-				     NULL, 0);
-}
-
-/**
- * ice_vc_config_rss_hfunc
- * @vf: pointer to the VF info
- * @msg: pointer to the msg buffer
- *
- * Configure the VF's RSS Hash function
- */
-static int ice_vc_config_rss_hfunc(struct ice_vf *vf, u8 *msg)
-{
-	struct virtchnl_rss_hfunc *vrh = (struct virtchnl_rss_hfunc *)msg;
-	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	u8 hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ;
-	struct ice_vsi *vsi;
-
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (!ice_vc_isvalid_vsi_id(vf, vrh->vsi_id)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (vrh->rss_algorithm == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC)
-		hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ;
-
-	if (ice_set_rss_hfunc(vsi, hfunc))
-		v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
-error_param:
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_HFUNC, v_ret,
-				     NULL, 0);
-}
-
-/**
  * ice_vc_get_qos_caps - Get current QoS caps from PF
  * @vf: pointer to the VF info
  *
@@ -1119,110 +468,6 @@ err:
 }
 
 /**
- * ice_vf_cfg_qs_bw - Configure per queue bandwidth
- * @vf: pointer to the VF info
- * @num_queues: number of queues to be configured
- *
- * Configure per queue bandwidth.
- *
- * Return: 0 on success or negative error value.
- */
-static int ice_vf_cfg_qs_bw(struct ice_vf *vf, u16 num_queues)
-{
-	struct ice_hw *hw = &vf->pf->hw;
-	struct ice_vsi *vsi;
-	int ret;
-	u16 i;
-
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi)
-		return -EINVAL;
-
-	for (i = 0; i < num_queues; i++) {
-		u32 p_rate, min_rate;
-		u8 tc;
-
-		p_rate = vf->qs_bw[i].peak;
-		min_rate = vf->qs_bw[i].committed;
-		tc = vf->qs_bw[i].tc;
-		if (p_rate)
-			ret = ice_cfg_q_bw_lmt(hw->port_info, vsi->idx, tc,
-					       vf->qs_bw[i].queue_id,
-					       ICE_MAX_BW, p_rate);
-		else
-			ret = ice_cfg_q_bw_dflt_lmt(hw->port_info, vsi->idx, tc,
-						    vf->qs_bw[i].queue_id,
-						    ICE_MAX_BW);
-		if (ret)
-			return ret;
-
-		if (min_rate)
-			ret = ice_cfg_q_bw_lmt(hw->port_info, vsi->idx, tc,
-					       vf->qs_bw[i].queue_id,
-					       ICE_MIN_BW, min_rate);
-		else
-			ret = ice_cfg_q_bw_dflt_lmt(hw->port_info, vsi->idx, tc,
-						    vf->qs_bw[i].queue_id,
-						    ICE_MIN_BW);
-
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-/**
- * ice_vf_cfg_q_quanta_profile - Configure quanta profile
- * @vf: pointer to the VF info
- * @quanta_prof_idx: pointer to the quanta profile index
- * @quanta_size: quanta size to be set
- *
- * This function chooses available quanta profile and configures the register.
- * The quanta profile is evenly divided by the number of device ports, and then
- * available to the specific PF and VFs. The first profile for each PF is a
- * reserved default profile. Only quanta size of the rest unused profile can be
- * modified.
- *
- * Return: 0 on success or negative error value.
- */
-static int ice_vf_cfg_q_quanta_profile(struct ice_vf *vf, u16 quanta_size,
-				       u16 *quanta_prof_idx)
-{
-	const u16 n_desc = calc_quanta_desc(quanta_size);
-	struct ice_hw *hw = &vf->pf->hw;
-	const u16 n_cmd = 2 * n_desc;
-	struct ice_pf *pf = vf->pf;
-	u16 per_pf, begin_id;
-	u8 n_used;
-	u32 reg;
-
-	begin_id = (GLCOMM_QUANTA_PROF_MAX_INDEX + 1) / hw->dev_caps.num_funcs *
-		   hw->logical_pf_id;
-
-	if (quanta_size == ICE_DFLT_QUANTA) {
-		*quanta_prof_idx = begin_id;
-	} else {
-		per_pf = (GLCOMM_QUANTA_PROF_MAX_INDEX + 1) /
-			 hw->dev_caps.num_funcs;
-		n_used = pf->num_quanta_prof_used;
-		if (n_used < per_pf) {
-			*quanta_prof_idx = begin_id + 1 + n_used;
-			pf->num_quanta_prof_used++;
-		} else {
-			return -EINVAL;
-		}
-	}
-
-	reg = FIELD_PREP(GLCOMM_QUANTA_PROF_QUANTA_SIZE_M, quanta_size) |
-	      FIELD_PREP(GLCOMM_QUANTA_PROF_MAX_CMD_M, n_cmd) |
-	      FIELD_PREP(GLCOMM_QUANTA_PROF_MAX_DESC_M, n_desc);
-	wr32(hw, GLCOMM_QUANTA_PROF(*quanta_prof_idx), reg);
-
-	return 0;
-}
-
-/**
  * ice_vc_cfg_promiscuous_mode_msg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
@@ -1404,744 +649,6 @@ error_param:
 }
 
 /**
- * ice_vc_validate_vqs_bitmaps - validate Rx/Tx queue bitmaps from VIRTCHNL
- * @vqs: virtchnl_queue_select structure containing bitmaps to validate
- *
- * Return true on successful validation, else false
- */
-static bool ice_vc_validate_vqs_bitmaps(struct virtchnl_queue_select *vqs)
-{
-	if ((!vqs->rx_queues && !vqs->tx_queues) ||
-	    vqs->rx_queues >= BIT(ICE_MAX_RSS_QS_PER_VF) ||
-	    vqs->tx_queues >= BIT(ICE_MAX_RSS_QS_PER_VF))
-		return false;
-
-	return true;
-}
-
-/**
- * ice_vf_ena_txq_interrupt - enable Tx queue interrupt via QINT_TQCTL
- * @vsi: VSI of the VF to configure
- * @q_idx: VF queue index used to determine the queue in the PF's space
- */
-static void ice_vf_ena_txq_interrupt(struct ice_vsi *vsi, u32 q_idx)
-{
-	struct ice_hw *hw = &vsi->back->hw;
-	u32 pfq = vsi->txq_map[q_idx];
-	u32 reg;
-
-	reg = rd32(hw, QINT_TQCTL(pfq));
-
-	/* MSI-X index 0 in the VF's space is always for the OICR, which means
-	 * this is most likely a poll mode VF driver, so don't enable an
-	 * interrupt that was never configured via VIRTCHNL_OP_CONFIG_IRQ_MAP
-	 */
-	if (!(reg & QINT_TQCTL_MSIX_INDX_M))
-		return;
-
-	wr32(hw, QINT_TQCTL(pfq), reg | QINT_TQCTL_CAUSE_ENA_M);
-}
-
-/**
- * ice_vf_ena_rxq_interrupt - enable Tx queue interrupt via QINT_RQCTL
- * @vsi: VSI of the VF to configure
- * @q_idx: VF queue index used to determine the queue in the PF's space
- */
-static void ice_vf_ena_rxq_interrupt(struct ice_vsi *vsi, u32 q_idx)
-{
-	struct ice_hw *hw = &vsi->back->hw;
-	u32 pfq = vsi->rxq_map[q_idx];
-	u32 reg;
-
-	reg = rd32(hw, QINT_RQCTL(pfq));
-
-	/* MSI-X index 0 in the VF's space is always for the OICR, which means
-	 * this is most likely a poll mode VF driver, so don't enable an
-	 * interrupt that was never configured via VIRTCHNL_OP_CONFIG_IRQ_MAP
-	 */
-	if (!(reg & QINT_RQCTL_MSIX_INDX_M))
-		return;
-
-	wr32(hw, QINT_RQCTL(pfq), reg | QINT_RQCTL_CAUSE_ENA_M);
-}
-
-/**
- * ice_vc_ena_qs_msg
- * @vf: pointer to the VF info
- * @msg: pointer to the msg buffer
- *
- * called from the VF to enable all or specific queue(s)
- */
-static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg)
-{
-	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct virtchnl_queue_select *vqs =
-	    (struct virtchnl_queue_select *)msg;
-	struct ice_vsi *vsi;
-	unsigned long q_map;
-	u16 vf_q_id;
-
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (!ice_vc_validate_vqs_bitmaps(vqs)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	/* Enable only Rx rings, Tx rings were enabled by the FW when the
-	 * Tx queue group list was configured and the context bits were
-	 * programmed using ice_vsi_cfg_txqs
-	 */
-	q_map = vqs->rx_queues;
-	for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) {
-		if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) {
-			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-			goto error_param;
-		}
-
-		/* Skip queue if enabled */
-		if (test_bit(vf_q_id, vf->rxq_ena))
-			continue;
-
-		if (ice_vsi_ctrl_one_rx_ring(vsi, true, vf_q_id, true)) {
-			dev_err(ice_pf_to_dev(vsi->back), "Failed to enable Rx ring %d on VSI %d\n",
-				vf_q_id, vsi->vsi_num);
-			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-			goto error_param;
-		}
-
-		ice_vf_ena_rxq_interrupt(vsi, vf_q_id);
-		set_bit(vf_q_id, vf->rxq_ena);
-	}
-
-	q_map = vqs->tx_queues;
-	for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) {
-		if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) {
-			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-			goto error_param;
-		}
-
-		/* Skip queue if enabled */
-		if (test_bit(vf_q_id, vf->txq_ena))
-			continue;
-
-		ice_vf_ena_txq_interrupt(vsi, vf_q_id);
-		set_bit(vf_q_id, vf->txq_ena);
-	}
-
-	/* Set flag to indicate that queues are enabled */
-	if (v_ret == VIRTCHNL_STATUS_SUCCESS)
-		set_bit(ICE_VF_STATE_QS_ENA, vf->vf_states);
-
-error_param:
-	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, v_ret,
-				     NULL, 0);
-}
-
-/**
- * ice_vf_vsi_dis_single_txq - disable a single Tx queue
- * @vf: VF to disable queue for
- * @vsi: VSI for the VF
- * @q_id: VF relative (0-based) queue ID
- *
- * Attempt to disable the Tx queue passed in. If the Tx queue was successfully
- * disabled then clear q_id bit in the enabled queues bitmap and return
- * success. Otherwise return error.
- */
-static int
-ice_vf_vsi_dis_single_txq(struct ice_vf *vf, struct ice_vsi *vsi, u16 q_id)
-{
-	struct ice_txq_meta txq_meta = { 0 };
-	struct ice_tx_ring *ring;
-	int err;
-
-	if (!test_bit(q_id, vf->txq_ena))
-		dev_dbg(ice_pf_to_dev(vsi->back), "Queue %u on VSI %u is not enabled, but stopping it anyway\n",
-			q_id, vsi->vsi_num);
-
-	ring = vsi->tx_rings[q_id];
-	if (!ring)
-		return -EINVAL;
-
-	ice_fill_txq_meta(vsi, ring, &txq_meta);
-
-	err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, vf->vf_id, ring, &txq_meta);
-	if (err) {
-		dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Tx ring %d on VSI %d\n",
-			q_id, vsi->vsi_num);
-		return err;
-	}
-
-	/* Clear enabled queues flag */
-	clear_bit(q_id, vf->txq_ena);
-
-	return 0;
-}
-
-/**
- * ice_vc_dis_qs_msg
- * @vf: pointer to the VF info
- * @msg: pointer to the msg buffer
- *
- * called from the VF to disable all or specific queue(s)
- */
-static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg)
-{
-	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct virtchnl_queue_select *vqs =
-	    (struct virtchnl_queue_select *)msg;
-	struct ice_vsi *vsi;
-	unsigned long q_map;
-	u16 vf_q_id;
-
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) &&
-	    !test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (!ice_vc_validate_vqs_bitmaps(vqs)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	if (vqs->tx_queues) {
-		q_map = vqs->tx_queues;
-
-		for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) {
-			if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) {
-				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-				goto error_param;
-			}
-
-			if (ice_vf_vsi_dis_single_txq(vf, vsi, vf_q_id)) {
-				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-				goto error_param;
-			}
-		}
-	}
-
-	q_map = vqs->rx_queues;
-	/* speed up Rx queue disable by batching them if possible */
-	if (q_map &&
-	    bitmap_equal(&q_map, vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF)) {
-		if (ice_vsi_stop_all_rx_rings(vsi)) {
-			dev_err(ice_pf_to_dev(vsi->back), "Failed to stop all Rx rings on VSI %d\n",
-				vsi->vsi_num);
-			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-			goto error_param;
-		}
-
-		bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF);
-	} else if (q_map) {
-		for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) {
-			if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) {
-				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-				goto error_param;
-			}
-
-			/* Skip queue if not enabled */
-			if (!test_bit(vf_q_id, vf->rxq_ena))
-				continue;
-
-			if (ice_vsi_ctrl_one_rx_ring(vsi, false, vf_q_id,
-						     true)) {
-				dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Rx ring %d on VSI %d\n",
-					vf_q_id, vsi->vsi_num);
-				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-				goto error_param;
-			}
-
-			/* Clear enabled queues flag */
-			clear_bit(vf_q_id, vf->rxq_ena);
-		}
-	}
-
-	/* Clear enabled queues flag */
-	if (v_ret == VIRTCHNL_STATUS_SUCCESS && ice_vf_has_no_qs_ena(vf))
-		clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states);
-
-error_param:
-	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_QUEUES, v_ret,
-				     NULL, 0);
-}
-
-/**
- * ice_cfg_interrupt
- * @vf: pointer to the VF info
- * @vsi: the VSI being configured
- * @map: vector map for mapping vectors to queues
- * @q_vector: structure for interrupt vector
- * configure the IRQ to queue map
- */
-static enum virtchnl_status_code
-ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi,
-		  struct virtchnl_vector_map *map,
-		  struct ice_q_vector *q_vector)
-{
-	u16 vsi_q_id, vsi_q_id_idx;
-	unsigned long qmap;
-
-	q_vector->num_ring_rx = 0;
-	q_vector->num_ring_tx = 0;
-
-	qmap = map->rxq_map;
-	for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) {
-		vsi_q_id = vsi_q_id_idx;
-
-		if (!ice_vc_isvalid_q_id(vsi, vsi_q_id))
-			return VIRTCHNL_STATUS_ERR_PARAM;
-
-		q_vector->num_ring_rx++;
-		q_vector->rx.itr_idx = map->rxitr_idx;
-		vsi->rx_rings[vsi_q_id]->q_vector = q_vector;
-		ice_cfg_rxq_interrupt(vsi, vsi_q_id,
-				      q_vector->vf_reg_idx,
-				      q_vector->rx.itr_idx);
-	}
-
-	qmap = map->txq_map;
-	for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) {
-		vsi_q_id = vsi_q_id_idx;
-
-		if (!ice_vc_isvalid_q_id(vsi, vsi_q_id))
-			return VIRTCHNL_STATUS_ERR_PARAM;
-
-		q_vector->num_ring_tx++;
-		q_vector->tx.itr_idx = map->txitr_idx;
-		vsi->tx_rings[vsi_q_id]->q_vector = q_vector;
-		ice_cfg_txq_interrupt(vsi, vsi_q_id,
-				      q_vector->vf_reg_idx,
-				      q_vector->tx.itr_idx);
-	}
-
-	return VIRTCHNL_STATUS_SUCCESS;
-}
-
-/**
- * ice_vc_cfg_irq_map_msg
- * @vf: pointer to the VF info
- * @msg: pointer to the msg buffer
- *
- * called from the VF to configure the IRQ to queue map
- */
-static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg)
-{
-	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	u16 num_q_vectors_mapped, vsi_id, vector_id;
-	struct virtchnl_irq_map_info *irqmap_info;
-	struct virtchnl_vector_map *map;
-	struct ice_vsi *vsi;
-	int i;
-
-	irqmap_info = (struct virtchnl_irq_map_info *)msg;
-	num_q_vectors_mapped = irqmap_info->num_vectors;
-
-	/* Check to make sure number of VF vectors mapped is not greater than
-	 * number of VF vectors originally allocated, and check that
-	 * there is actually at least a single VF queue vector mapped
-	 */
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) ||
-	    vf->num_msix < num_q_vectors_mapped ||
-	    !num_q_vectors_mapped) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	for (i = 0; i < num_q_vectors_mapped; i++) {
-		struct ice_q_vector *q_vector;
-
-		map = &irqmap_info->vecmap[i];
-
-		vector_id = map->vector_id;
-		vsi_id = map->vsi_id;
-		/* vector_id is always 0-based for each VF, and can never be
-		 * larger than or equal to the max allowed interrupts per VF
-		 */
-		if (!(vector_id < vf->num_msix) ||
-		    !ice_vc_isvalid_vsi_id(vf, vsi_id) ||
-		    (!vector_id && (map->rxq_map || map->txq_map))) {
-			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-			goto error_param;
-		}
-
-		/* No need to map VF miscellaneous or rogue vector */
-		if (!vector_id)
-			continue;
-
-		/* Subtract non queue vector from vector_id passed by VF
-		 * to get actual number of VSI queue vector array index
-		 */
-		q_vector = vsi->q_vectors[vector_id - ICE_NONQ_VECS_VF];
-		if (!q_vector) {
-			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-			goto error_param;
-		}
-
-		/* lookout for the invalid queue index */
-		v_ret = ice_cfg_interrupt(vf, vsi, map, q_vector);
-		if (v_ret)
-			goto error_param;
-	}
-
-error_param:
-	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_IRQ_MAP, v_ret,
-				     NULL, 0);
-}
-
-/**
- * ice_vc_cfg_q_bw - Configure per queue bandwidth
- * @vf: pointer to the VF info
- * @msg: pointer to the msg buffer which holds the command descriptor
- *
- * Configure VF queues bandwidth.
- *
- * Return: 0 on success or negative error value.
- */
-static int ice_vc_cfg_q_bw(struct ice_vf *vf, u8 *msg)
-{
-	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct virtchnl_queues_bw_cfg *qbw =
-		(struct virtchnl_queues_bw_cfg *)msg;
-	struct ice_vsi *vsi;
-	u16 i;
-
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) ||
-	    !ice_vc_isvalid_vsi_id(vf, qbw->vsi_id)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto err;
-	}
-
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto err;
-	}
-
-	if (qbw->num_queues > ICE_MAX_RSS_QS_PER_VF ||
-	    qbw->num_queues > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
-		dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n",
-			vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq));
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto err;
-	}
-
-	for (i = 0; i < qbw->num_queues; i++) {
-		if (qbw->cfg[i].shaper.peak != 0 && vf->max_tx_rate != 0 &&
-		    qbw->cfg[i].shaper.peak > vf->max_tx_rate)
-			dev_warn(ice_pf_to_dev(vf->pf), "The maximum queue %d rate limit configuration may not take effect because the maximum TX rate for VF-%d is %d\n",
-				 qbw->cfg[i].queue_id, vf->vf_id,
-				 vf->max_tx_rate);
-		if (qbw->cfg[i].shaper.committed != 0 && vf->min_tx_rate != 0 &&
-		    qbw->cfg[i].shaper.committed < vf->min_tx_rate)
-			dev_warn(ice_pf_to_dev(vf->pf), "The minimum queue %d rate limit configuration may not take effect because the minimum TX rate for VF-%d is %d\n",
-				 qbw->cfg[i].queue_id, vf->vf_id,
-				 vf->max_tx_rate);
-	}
-
-	for (i = 0; i < qbw->num_queues; i++) {
-		vf->qs_bw[i].queue_id = qbw->cfg[i].queue_id;
-		vf->qs_bw[i].peak = qbw->cfg[i].shaper.peak;
-		vf->qs_bw[i].committed = qbw->cfg[i].shaper.committed;
-		vf->qs_bw[i].tc = qbw->cfg[i].tc;
-	}
-
-	if (ice_vf_cfg_qs_bw(vf, qbw->num_queues))
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-
-err:
-	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_QUEUE_BW,
-				    v_ret, NULL, 0);
-}
-
-/**
- * ice_vc_cfg_q_quanta - Configure per queue quanta
- * @vf: pointer to the VF info
- * @msg: pointer to the msg buffer which holds the command descriptor
- *
- * Configure VF queues quanta.
- *
- * Return: 0 on success or negative error value.
- */
-static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg)
-{
-	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	u16 quanta_prof_id, quanta_size, start_qid, end_qid, i;
-	struct virtchnl_quanta_cfg *qquanta =
-		(struct virtchnl_quanta_cfg *)msg;
-	struct ice_vsi *vsi;
-	int ret;
-
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto err;
-	}
-
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto err;
-	}
-
-	end_qid = qquanta->queue_select.start_queue_id +
-		  qquanta->queue_select.num_queues;
-	if (end_qid > ICE_MAX_RSS_QS_PER_VF ||
-	    end_qid > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
-		dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n",
-			vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq));
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto err;
-	}
-
-	quanta_size = qquanta->quanta_size;
-	if (quanta_size > ICE_MAX_QUANTA_SIZE ||
-	    quanta_size < ICE_MIN_QUANTA_SIZE) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto err;
-	}
-
-	if (quanta_size % 64) {
-		dev_err(ice_pf_to_dev(vf->pf), "quanta size should be the product of 64\n");
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto err;
-	}
-
-	ret = ice_vf_cfg_q_quanta_profile(vf, quanta_size,
-					  &quanta_prof_id);
-	if (ret) {
-		v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED;
-		goto err;
-	}
-
-	start_qid = qquanta->queue_select.start_queue_id;
-	for (i = start_qid; i < end_qid; i++)
-		vsi->tx_rings[i]->quanta_prof_id = quanta_prof_id;
-
-err:
-	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_QUANTA,
-				     v_ret, NULL, 0);
-}
-
-/**
- * ice_vc_cfg_qs_msg
- * @vf: pointer to the VF info
- * @msg: pointer to the msg buffer
- *
- * called from the VF to configure the Rx/Tx queues
- */
-static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
-{
-	struct virtchnl_vsi_queue_config_info *qci =
-	    (struct virtchnl_vsi_queue_config_info *)msg;
-	struct virtchnl_queue_pair_info *qpi;
-	struct ice_pf *pf = vf->pf;
-	struct ice_lag *lag;
-	struct ice_vsi *vsi;
-	u8 act_prt, pri_prt;
-	int i = -1, q_idx;
-
-	lag = pf->lag;
-	mutex_lock(&pf->lag_mutex);
-	act_prt = ICE_LAG_INVALID_PORT;
-	pri_prt = pf->hw.port_info->lport;
-	if (lag && lag->bonded && lag->primary) {
-		act_prt = lag->active_port;
-		if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT &&
-		    lag->upper_netdev)
-			ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt);
-		else
-			act_prt = ICE_LAG_INVALID_PORT;
-	}
-
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
-		goto error_param;
-
-	if (!ice_vc_isvalid_vsi_id(vf, qci->vsi_id))
-		goto error_param;
-
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi)
-		goto error_param;
-
-	if (qci->num_queue_pairs > ICE_MAX_RSS_QS_PER_VF ||
-	    qci->num_queue_pairs > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
-		dev_err(ice_pf_to_dev(pf), "VF-%d requesting more than supported number of queues: %d\n",
-			vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq));
-		goto error_param;
-	}
-
-	for (i = 0; i < qci->num_queue_pairs; i++) {
-		if (!qci->qpair[i].rxq.crc_disable)
-			continue;
-
-		if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_CRC) ||
-		    vf->vlan_strip_ena)
-			goto error_param;
-	}
-
-	for (i = 0; i < qci->num_queue_pairs; i++) {
-		qpi = &qci->qpair[i];
-		if (qpi->txq.vsi_id != qci->vsi_id ||
-		    qpi->rxq.vsi_id != qci->vsi_id ||
-		    qpi->rxq.queue_id != qpi->txq.queue_id ||
-		    qpi->txq.headwb_enabled ||
-		    !ice_vc_isvalid_ring_len(qpi->txq.ring_len) ||
-		    !ice_vc_isvalid_ring_len(qpi->rxq.ring_len) ||
-		    !ice_vc_isvalid_q_id(vsi, qpi->txq.queue_id)) {
-			goto error_param;
-		}
-
-		q_idx = qpi->rxq.queue_id;
-
-		/* make sure selected "q_idx" is in valid range of queues
-		 * for selected "vsi"
-		 */
-		if (q_idx >= vsi->alloc_txq || q_idx >= vsi->alloc_rxq) {
-			goto error_param;
-		}
-
-		/* copy Tx queue info from VF into VSI */
-		if (qpi->txq.ring_len > 0) {
-			vsi->tx_rings[q_idx]->dma = qpi->txq.dma_ring_addr;
-			vsi->tx_rings[q_idx]->count = qpi->txq.ring_len;
-
-			/* Disable any existing queue first */
-			if (ice_vf_vsi_dis_single_txq(vf, vsi, q_idx))
-				goto error_param;
-
-			/* Configure a queue with the requested settings */
-			if (ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx)) {
-				dev_warn(ice_pf_to_dev(pf), "VF-%d failed to configure TX queue %d\n",
-					 vf->vf_id, q_idx);
-				goto error_param;
-			}
-		}
-
-		/* copy Rx queue info from VF into VSI */
-		if (qpi->rxq.ring_len > 0) {
-			u16 max_frame_size = ice_vc_get_max_frame_size(vf);
-			struct ice_rx_ring *ring = vsi->rx_rings[q_idx];
-			u32 rxdid;
-
-			ring->dma = qpi->rxq.dma_ring_addr;
-			ring->count = qpi->rxq.ring_len;
-
-			if (qpi->rxq.crc_disable)
-				ring->flags |= ICE_RX_FLAGS_CRC_STRIP_DIS;
-			else
-				ring->flags &= ~ICE_RX_FLAGS_CRC_STRIP_DIS;
-
-			if (qpi->rxq.databuffer_size != 0 &&
-			    (qpi->rxq.databuffer_size > ((16 * 1024) - 128) ||
-			     qpi->rxq.databuffer_size < 1024))
-				goto error_param;
-			ring->rx_buf_len = qpi->rxq.databuffer_size;
-			if (qpi->rxq.max_pkt_size > max_frame_size ||
-			    qpi->rxq.max_pkt_size < 64)
-				goto error_param;
-
-			ring->max_frame = qpi->rxq.max_pkt_size;
-			/* add space for the port VLAN since the VF driver is
-			 * not expected to account for it in the MTU
-			 * calculation
-			 */
-			if (ice_vf_is_port_vlan_ena(vf))
-				ring->max_frame += VLAN_HLEN;
-
-			if (ice_vsi_cfg_single_rxq(vsi, q_idx)) {
-				dev_warn(ice_pf_to_dev(pf), "VF-%d failed to configure RX queue %d\n",
-					 vf->vf_id, q_idx);
-				goto error_param;
-			}
-
-			/* If Rx flex desc is supported, select RXDID for Rx
-			 * queues. Otherwise, use legacy 32byte descriptor
-			 * format. Legacy 16byte descriptor is not supported.
-			 * If this RXDID is selected, return error.
-			 */
-			if (vf->driver_caps &
-			    VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) {
-				rxdid = qpi->rxq.rxdid;
-				if (!(BIT(rxdid) & pf->supported_rxdids))
-					goto error_param;
-			} else {
-				rxdid = ICE_RXDID_LEGACY_1;
-			}
-
-			ice_write_qrxflxp_cntxt(&vsi->back->hw,
-						vsi->rxq_map[q_idx],
-						rxdid, 0x03, false);
-		}
-	}
-
-	if (lag && lag->bonded && lag->primary &&
-	    act_prt != ICE_LAG_INVALID_PORT)
-		ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt);
-	mutex_unlock(&pf->lag_mutex);
-
-	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES,
-				     VIRTCHNL_STATUS_SUCCESS, NULL, 0);
-error_param:
-	/* disable whatever we can */
-	for (; i >= 0; i--) {
-		if (ice_vsi_ctrl_one_rx_ring(vsi, false, i, true))
-			dev_err(ice_pf_to_dev(pf), "VF-%d could not disable RX queue %d\n",
-				vf->vf_id, i);
-		if (ice_vf_vsi_dis_single_txq(vf, vsi, i))
-			dev_err(ice_pf_to_dev(pf), "VF-%d could not disable TX queue %d\n",
-				vf->vf_id, i);
-	}
-
-	if (lag && lag->bonded && lag->primary &&
-	    act_prt != ICE_LAG_INVALID_PORT)
-		ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt);
-	mutex_unlock(&pf->lag_mutex);
-
-	ice_lag_move_new_vf_nodes(vf);
-
-	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES,
-				     VIRTCHNL_STATUS_ERR_PARAM, NULL, 0);
-}
-
-/**
  * ice_can_vf_change_mac
  * @vf: pointer to the VF info
  *
@@ -2234,6 +741,51 @@ ice_vfhw_mac_add(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr)
 }
 
 /**
+ * ice_is_mc_lldp_eth_addr - check if the given MAC is a multicast LLDP address
+ * @mac: address to check
+ *
+ * Return: true if the address is one of the three possible LLDP multicast
+ *	   addresses, false otherwise.
+ */
+static bool ice_is_mc_lldp_eth_addr(const u8 *mac)
+{
+	const u8 lldp_mac_base[] = {0x01, 0x80, 0xc2, 0x00, 0x00};
+
+	if (memcmp(mac, lldp_mac_base, sizeof(lldp_mac_base)))
+		return false;
+
+	return (mac[5] == 0x0e || mac[5] == 0x03 || mac[5] == 0x00);
+}
+
+/**
+ * ice_vc_can_add_mac - check if the VF is allowed to add a given MAC
+ * @vf: a VF to add the address to
+ * @mac: address to check
+ *
+ * Return: true if the VF is allowed to add such MAC address, false otherwise.
+ */
+static bool ice_vc_can_add_mac(const struct ice_vf *vf, const u8 *mac)
+{
+	struct device *dev = ice_pf_to_dev(vf->pf);
+
+	if (is_unicast_ether_addr(mac) &&
+	    !ice_can_vf_change_mac((struct ice_vf *)vf)) {
+		dev_err(dev,
+			"VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n");
+		return false;
+	}
+
+	if (!vf->trusted && ice_is_mc_lldp_eth_addr(mac)) {
+		dev_warn(dev,
+			 "An untrusted VF %u is attempting to configure an LLDP multicast address\n",
+			 vf->vf_id);
+		return false;
+	}
+
+	return true;
+}
+
+/**
  * ice_vc_add_mac_addr - attempt to add the MAC address passed in
  * @vf: pointer to the VF info
  * @vsi: pointer to the VF's VSI
@@ -2251,10 +803,8 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi,
 	if (ether_addr_equal(mac_addr, vf->dev_lan_addr))
 		return 0;
 
-	if (is_unicast_ether_addr(mac_addr) && !ice_can_vf_change_mac(vf)) {
-		dev_err(dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n");
+	if (!ice_vc_can_add_mac(vf, mac_addr))
 		return -EPERM;
-	}
 
 	ret = ice_fltr_add_mac(vsi, mac_addr, ICE_FWD_TO_VSI);
 	if (ret == -EEXIST) {
@@ -2269,6 +819,8 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi,
 		return ret;
 	} else {
 		vf->num_mac++;
+		if (ice_is_mc_lldp_eth_addr(mac_addr))
+			ice_vf_update_mac_lldp_num(vf, vsi, true);
 	}
 
 	ice_vfhw_mac_add(vf, vc_ether_addr);
@@ -2363,6 +915,8 @@ ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi,
 	ice_vfhw_mac_del(vf, vc_ether_addr);
 
 	vf->num_mac--;
+	if (ice_is_mc_lldp_eth_addr(mac_addr))
+		ice_vf_update_mac_lldp_num(vf, vsi, false);
 
 	return 0;
 }
@@ -2468,66 +1022,6 @@ static int ice_vc_del_mac_addr_msg(struct ice_vf *vf, u8 *msg)
 }
 
 /**
- * ice_vc_request_qs_msg
- * @vf: pointer to the VF info
- * @msg: pointer to the msg buffer
- *
- * VFs get a default number of queues but can use this message to request a
- * different number. If the request is successful, PF will reset the VF and
- * return 0. If unsuccessful, PF will send message informing VF of number of
- * available queue pairs via virtchnl message response to VF.
- */
-static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg)
-{
-	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct virtchnl_vf_res_request *vfres =
-		(struct virtchnl_vf_res_request *)msg;
-	u16 req_queues = vfres->num_queue_pairs;
-	struct ice_pf *pf = vf->pf;
-	u16 max_allowed_vf_queues;
-	u16 tx_rx_queue_left;
-	struct device *dev;
-	u16 cur_queues;
-
-	dev = ice_pf_to_dev(pf);
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto error_param;
-	}
-
-	cur_queues = vf->num_vf_qs;
-	tx_rx_queue_left = min_t(u16, ice_get_avail_txq_count(pf),
-				 ice_get_avail_rxq_count(pf));
-	max_allowed_vf_queues = tx_rx_queue_left + cur_queues;
-	if (!req_queues) {
-		dev_err(dev, "VF %d tried to request 0 queues. Ignoring.\n",
-			vf->vf_id);
-	} else if (req_queues > ICE_MAX_RSS_QS_PER_VF) {
-		dev_err(dev, "VF %d tried to request more than %d queues.\n",
-			vf->vf_id, ICE_MAX_RSS_QS_PER_VF);
-		vfres->num_queue_pairs = ICE_MAX_RSS_QS_PER_VF;
-	} else if (req_queues > cur_queues &&
-		   req_queues - cur_queues > tx_rx_queue_left) {
-		dev_warn(dev, "VF %d requested %u more queues, but only %u left.\n",
-			 vf->vf_id, req_queues - cur_queues, tx_rx_queue_left);
-		vfres->num_queue_pairs = min_t(u16, max_allowed_vf_queues,
-					       ICE_MAX_RSS_QS_PER_VF);
-	} else {
-		/* request is successful, then reset VF */
-		vf->num_req_qs = req_queues;
-		ice_reset_vf(vf, ICE_VF_RESET_NOTIFY);
-		dev_info(dev, "VF %d granted request of %u queues.\n",
-			 vf->vf_id, req_queues);
-		return 0;
-	}
-
-error_param:
-	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES,
-				     v_ret, (u8 *)vfres, sizeof(*vfres));
-}
-
-/**
  * ice_vf_vlan_offload_ena - determine if capabilities support VLAN offloads
  * @caps: VF driver negotiated capabilities
  *
@@ -2542,7 +1036,7 @@ static bool ice_vf_vlan_offload_ena(u32 caps)
  * ice_is_vlan_promisc_allowed - check if VLAN promiscuous config is allowed
  * @vf: VF used to determine if VLAN promiscuous config is allowed
  */
-static bool ice_is_vlan_promisc_allowed(struct ice_vf *vf)
+bool ice_is_vlan_promisc_allowed(struct ice_vf *vf)
 {
 	if ((test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) ||
 	     test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) &&
@@ -2561,8 +1055,8 @@ static bool ice_is_vlan_promisc_allowed(struct ice_vf *vf)
  * This function should only be called if VLAN promiscuous mode is allowed,
  * which can be determined via ice_is_vlan_promisc_allowed().
  */
-static int ice_vf_ena_vlan_promisc(struct ice_vf *vf, struct ice_vsi *vsi,
-				   struct ice_vlan *vlan)
+int ice_vf_ena_vlan_promisc(struct ice_vf *vf, struct ice_vsi *vsi,
+			    struct ice_vlan *vlan)
 {
 	u8 promisc_m = 0;
 	int status;
@@ -2920,108 +1414,6 @@ error_param:
 }
 
 /**
- * ice_vc_get_rss_hena - return the RSS HENA bits allowed by the hardware
- * @vf: pointer to the VF info
- */
-static int ice_vc_get_rss_hena(struct ice_vf *vf)
-{
-	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct virtchnl_rss_hena *vrh = NULL;
-	int len = 0, ret;
-
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto err;
-	}
-
-	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
-		dev_err(ice_pf_to_dev(vf->pf), "RSS not supported by PF\n");
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto err;
-	}
-
-	len = sizeof(struct virtchnl_rss_hena);
-	vrh = kzalloc(len, GFP_KERNEL);
-	if (!vrh) {
-		v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
-		len = 0;
-		goto err;
-	}
-
-	vrh->hena = ICE_DEFAULT_RSS_HENA;
-err:
-	/* send the response back to the VF */
-	ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_RSS_HENA_CAPS, v_ret,
-				    (u8 *)vrh, len);
-	kfree(vrh);
-	return ret;
-}
-
-/**
- * ice_vc_set_rss_hena - set RSS HENA bits for the VF
- * @vf: pointer to the VF info
- * @msg: pointer to the msg buffer
- */
-static int ice_vc_set_rss_hena(struct ice_vf *vf, u8 *msg)
-{
-	struct virtchnl_rss_hena *vrh = (struct virtchnl_rss_hena *)msg;
-	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct ice_pf *pf = vf->pf;
-	struct ice_vsi *vsi;
-	struct device *dev;
-	int status;
-
-	dev = ice_pf_to_dev(pf);
-
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto err;
-	}
-
-	if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
-		dev_err(dev, "RSS not supported by PF\n");
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto err;
-	}
-
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi) {
-		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-		goto err;
-	}
-
-	/* clear all previously programmed RSS configuration to allow VF drivers
-	 * the ability to customize the RSS configuration and/or completely
-	 * disable RSS
-	 */
-	status = ice_rem_vsi_rss_cfg(&pf->hw, vsi->idx);
-	if (status && !vrh->hena) {
-		/* only report failure to clear the current RSS configuration if
-		 * that was clearly the VF's intention (i.e. vrh->hena = 0)
-		 */
-		v_ret = ice_err_to_virt_err(status);
-		goto err;
-	} else if (status) {
-		/* allow the VF to update the RSS configuration even on failure
-		 * to clear the current RSS confguration in an attempt to keep
-		 * RSS in a working state
-		 */
-		dev_warn(dev, "Failed to clear the RSS configuration for VF %u\n",
-			 vf->vf_id);
-	}
-
-	if (vrh->hena) {
-		status = ice_add_avf_rss_cfg(&pf->hw, vsi, vrh->hena);
-		v_ret = ice_err_to_virt_err(status);
-	}
-
-	/* send the response to the VF */
-err:
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_SET_RSS_HENA, v_ret,
-				     NULL, 0);
-}
-
-/**
  * ice_vc_query_rxdid - query RXDID supported by DDP package
  * @vf: pointer to VF info
  *
@@ -3031,8 +1423,8 @@ err:
 static int ice_vc_query_rxdid(struct ice_vf *vf)
 {
 	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct virtchnl_supported_rxdids rxdid = {};
 	struct ice_pf *pf = vf->pf;
+	u64 rxdid;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
@@ -3044,7 +1436,7 @@ static int ice_vc_query_rxdid(struct ice_vf *vf)
 		goto err;
 	}
 
-	rxdid.supported_rxdids = pf->supported_rxdids;
+	rxdid = pf->supported_rxdids;
 
 err:
 	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS,
@@ -3777,48 +2169,6 @@ ice_vc_ena_vlan_offload(struct ice_vsi *vsi,
 	return 0;
 }
 
-#define ICE_L2TSEL_QRX_CONTEXT_REG_IDX	3
-#define ICE_L2TSEL_BIT_OFFSET		23
-enum ice_l2tsel {
-	ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG2_2ND,
-	ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG1,
-};
-
-/**
- * ice_vsi_update_l2tsel - update l2tsel field for all Rx rings on this VSI
- * @vsi: VSI used to update l2tsel on
- * @l2tsel: l2tsel setting requested
- *
- * Use the l2tsel setting to update all of the Rx queue context bits for l2tsel.
- * This will modify which descriptor field the first offloaded VLAN will be
- * stripped into.
- */
-static void ice_vsi_update_l2tsel(struct ice_vsi *vsi, enum ice_l2tsel l2tsel)
-{
-	struct ice_hw *hw = &vsi->back->hw;
-	u32 l2tsel_bit;
-	int i;
-
-	if (l2tsel == ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG2_2ND)
-		l2tsel_bit = 0;
-	else
-		l2tsel_bit = BIT(ICE_L2TSEL_BIT_OFFSET);
-
-	for (i = 0; i < vsi->alloc_rxq; i++) {
-		u16 pfq = vsi->rxq_map[i];
-		u32 qrx_context_offset;
-		u32 regval;
-
-		qrx_context_offset =
-			QRX_CONTEXT(ICE_L2TSEL_QRX_CONTEXT_REG_IDX, pfq);
-
-		regval = rd32(hw, qrx_context_offset);
-		regval &= ~BIT(ICE_L2TSEL_BIT_OFFSET);
-		regval |= l2tsel_bit;
-		wr32(hw, qrx_context_offset, regval);
-	}
-}
-
 /**
  * ice_vc_ena_vlan_stripping_v2_msg
  * @vf: VF the message was received from
@@ -4092,6 +2442,59 @@ out:
 				     v_ret, NULL, 0);
 }
 
+static int ice_vc_get_ptp_cap(struct ice_vf *vf,
+			      const struct virtchnl_ptp_caps *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+	u32 caps = VIRTCHNL_1588_PTP_CAP_RX_TSTAMP |
+		   VIRTCHNL_1588_PTP_CAP_READ_PHC;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+		goto err;
+
+	v_ret = VIRTCHNL_STATUS_SUCCESS;
+
+	if (msg->caps & caps)
+		vf->ptp_caps = caps;
+
+err:
+	/* send the response back to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_CAPS, v_ret,
+				     (u8 *)&vf->ptp_caps,
+				     sizeof(struct virtchnl_ptp_caps));
+}
+
+static int ice_vc_get_phc_time(struct ice_vf *vf)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+	struct virtchnl_phc_time *phc_time = NULL;
+	struct ice_pf *pf = vf->pf;
+	u32 len = 0;
+	int ret;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+		goto err;
+
+	v_ret = VIRTCHNL_STATUS_SUCCESS;
+
+	phc_time = kzalloc(sizeof(*phc_time), GFP_KERNEL);
+	if (!phc_time) {
+		v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
+		goto err;
+	}
+
+	len = sizeof(*phc_time);
+
+	phc_time->time = ice_ptp_read_src_clk_reg(pf, NULL);
+
+err:
+	/* send the response back to the VF */
+	ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_TIME, v_ret,
+				    (u8 *)phc_time, len);
+	kfree(phc_time);
+	return ret;
+}
+
 static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.get_ver_msg = ice_vc_get_ver_msg,
 	.get_vf_res_msg = ice_vc_get_vf_res_msg,
@@ -4111,8 +2514,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.add_vlan_msg = ice_vc_add_vlan_msg,
 	.remove_vlan_msg = ice_vc_remove_vlan_msg,
 	.query_rxdid = ice_vc_query_rxdid,
-	.get_rss_hena = ice_vc_get_rss_hena,
-	.set_rss_hena_msg = ice_vc_set_rss_hena,
+	.get_rss_hashcfg = ice_vc_get_rss_hashcfg,
+	.set_rss_hashcfg = ice_vc_set_rss_hashcfg,
 	.ena_vlan_stripping = ice_vc_ena_vlan_stripping,
 	.dis_vlan_stripping = ice_vc_dis_vlan_stripping,
 	.handle_rss_cfg_msg = ice_vc_handle_rss_cfg,
@@ -4128,6 +2531,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.get_qos_caps = ice_vc_get_qos_caps,
 	.cfg_q_bw = ice_vc_cfg_q_bw,
 	.cfg_q_quanta = ice_vc_cfg_q_quanta,
+	.get_ptp_cap = ice_vc_get_ptp_cap,
+	.get_phc_time = ice_vc_get_phc_time,
 	/* If you add a new op here please make sure to add it to
 	 * ice_virtchnl_repr_ops as well.
 	 */
@@ -4188,7 +2593,6 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg)
 		}
 
 		ice_vfhw_mac_add(vf, &al->list[i]);
-		vf->num_mac++;
 		break;
 	}
 
@@ -4247,8 +2651,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = {
 	.add_vlan_msg = ice_vc_add_vlan_msg,
 	.remove_vlan_msg = ice_vc_remove_vlan_msg,
 	.query_rxdid = ice_vc_query_rxdid,
-	.get_rss_hena = ice_vc_get_rss_hena,
-	.set_rss_hena_msg = ice_vc_set_rss_hena,
+	.get_rss_hashcfg = ice_vc_get_rss_hashcfg,
+	.set_rss_hashcfg = ice_vc_set_rss_hashcfg,
 	.ena_vlan_stripping = ice_vc_ena_vlan_stripping,
 	.dis_vlan_stripping = ice_vc_dis_vlan_stripping,
 	.handle_rss_cfg_msg = ice_vc_handle_rss_cfg,
@@ -4264,6 +2668,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = {
 	.get_qos_caps = ice_vc_get_qos_caps,
 	.cfg_q_bw = ice_vc_cfg_q_bw,
 	.cfg_q_quanta = ice_vc_cfg_q_quanta,
+	.get_ptp_cap = ice_vc_get_ptp_cap,
+	.get_phc_time = ice_vc_get_phc_time,
 };
 
 /**
@@ -4447,11 +2853,11 @@ error_handler:
 	case VIRTCHNL_OP_GET_SUPPORTED_RXDIDS:
 		err = ops->query_rxdid(vf);
 		break;
-	case VIRTCHNL_OP_GET_RSS_HENA_CAPS:
-		err = ops->get_rss_hena(vf);
+	case VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS:
+		err = ops->get_rss_hashcfg(vf);
 		break;
-	case VIRTCHNL_OP_SET_RSS_HENA:
-		err = ops->set_rss_hena_msg(vf, msg);
+	case VIRTCHNL_OP_SET_RSS_HASHCFG:
+		err = ops->set_rss_hashcfg(vf, msg);
 		break;
 	case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING:
 		err = ops->ena_vlan_stripping(vf);
@@ -4501,6 +2907,12 @@ error_handler:
 	case VIRTCHNL_OP_CONFIG_QUANTA:
 		err = ops->cfg_q_quanta(vf, msg);
 		break;
+	case VIRTCHNL_OP_1588_PTP_GET_CAPS:
+		err = ops->get_ptp_cap(vf, (const void *)msg);
+		break;
+	case VIRTCHNL_OP_1588_PTP_GET_TIME:
+		err = ops->get_phc_time(vf);
+		break;
 	case VIRTCHNL_OP_UNKNOWN:
 	default:
 		dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode,
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/virt/virtchnl.h
index 0c629aef9baf..71bb456e2d71 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h
+++ b/drivers/net/ethernet/intel/ice/virt/virtchnl.h
@@ -26,6 +26,9 @@
 #define ICE_MAX_MACADDR_PER_VF		18
 #define ICE_FLEX_DESC_RXDID_MAX_NUM	64
 
+/* Priority to be compared against previous priority from the pipe */
+#define ICE_RXDID_PRIO			0x03
+
 /* VFs only get a single VSI. For ice hardware, the VF does not need to know
  * its VSI index. However, the virtchnl interface requires a VSI number,
  * mainly due to legacy hardware.
@@ -54,8 +57,8 @@ struct ice_virtchnl_ops {
 	int (*add_vlan_msg)(struct ice_vf *vf, u8 *msg);
 	int (*remove_vlan_msg)(struct ice_vf *vf, u8 *msg);
 	int (*query_rxdid)(struct ice_vf *vf);
-	int (*get_rss_hena)(struct ice_vf *vf);
-	int (*set_rss_hena_msg)(struct ice_vf *vf, u8 *msg);
+	int (*get_rss_hashcfg)(struct ice_vf *vf);
+	int (*set_rss_hashcfg)(struct ice_vf *vf, u8 *msg);
 	int (*ena_vlan_stripping)(struct ice_vf *vf);
 	int (*dis_vlan_stripping)(struct ice_vf *vf);
 	int (*handle_rss_cfg_msg)(struct ice_vf *vf, u8 *msg, bool add);
@@ -72,6 +75,9 @@ struct ice_virtchnl_ops {
 	int (*cfg_q_tc_map)(struct ice_vf *vf, u8 *msg);
 	int (*cfg_q_bw)(struct ice_vf *vf, u8 *msg);
 	int (*cfg_q_quanta)(struct ice_vf *vf, u8 *msg);
+	int (*get_ptp_cap)(struct ice_vf *vf,
+			   const struct virtchnl_ptp_caps *msg);
+	int (*get_phc_time)(struct ice_vf *vf);
 };
 
 #ifdef CONFIG_PCI_IOV
@@ -86,12 +92,31 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode,
 bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id);
 void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event,
 			   struct ice_mbx_data *mbxdata);
+void ice_vf_ena_rxq_interrupt(struct ice_vsi *vsi, u32 q_idx);
+void ice_vf_ena_txq_interrupt(struct ice_vsi *vsi, u32 q_idx);
+int ice_vf_ena_vlan_promisc(struct ice_vf *vf, struct ice_vsi *vsi,
+			    struct ice_vlan *vlan);
+bool ice_is_vlan_promisc_allowed(struct ice_vf *vf);
 #else /* CONFIG_PCI_IOV */
 static inline void ice_virtchnl_set_dflt_ops(struct ice_vf *vf) { }
 static inline void ice_virtchnl_set_repr_ops(struct ice_vf *vf) { }
 static inline void ice_vc_notify_vf_link_state(struct ice_vf *vf) { }
 static inline void ice_vc_notify_link_state(struct ice_pf *pf) { }
 static inline void ice_vc_notify_reset(struct ice_pf *pf) { }
+static inline void ice_vf_ena_rxq_interrupt(struct ice_vsi *vsi, u32 q_idx) { }
+static inline void ice_vf_ena_txq_interrupt(struct ice_vsi *vsi, u32 q_idx) { }
+
+static inline int ice_vf_ena_vlan_promisc(struct ice_vf *vf,
+					  struct ice_vsi *vsi,
+					  struct ice_vlan *vlan)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline bool ice_is_vlan_promisc_allowed(struct ice_vf *vf)
+{
+	return false;
+}
 
 static inline int
 ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode,
diff --git a/drivers/net/ethernet/intel/idpf/Kconfig b/drivers/net/ethernet/intel/idpf/Kconfig
index 1addd663acad..adab2154125b 100644
--- a/drivers/net/ethernet/intel/idpf/Kconfig
+++ b/drivers/net/ethernet/intel/idpf/Kconfig
@@ -4,8 +4,9 @@
 config IDPF
 	tristate "Intel(R) Infrastructure Data Path Function Support"
 	depends on PCI_MSI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select DIMLIB
-	select LIBETH
+	select LIBETH_XDP
 	help
 	  This driver supports Intel(R) Infrastructure Data Path Function
 	  devices.
diff --git a/drivers/net/ethernet/intel/idpf/Makefile b/drivers/net/ethernet/intel/idpf/Makefile
index 2ce01a0b5898..651ddee942bd 100644
--- a/drivers/net/ethernet/intel/idpf/Makefile
+++ b/drivers/net/ethernet/intel/idpf/Makefile
@@ -10,6 +10,7 @@ idpf-y := \
 	idpf_controlq_setup.o	\
 	idpf_dev.o		\
 	idpf_ethtool.o		\
+	idpf_idc.o		\
 	idpf_lib.o		\
 	idpf_main.o		\
 	idpf_txrx.o		\
@@ -17,3 +18,9 @@ idpf-y := \
 	idpf_vf_dev.o
 
 idpf-$(CONFIG_IDPF_SINGLEQ)	+= idpf_singleq_txrx.o
+
+idpf-$(CONFIG_PTP_1588_CLOCK)	+= idpf_ptp.o
+idpf-$(CONFIG_PTP_1588_CLOCK)	+= idpf_virtchnl_ptp.o
+
+idpf-y				+= xdp.o
+idpf-y				+= xsk.o
diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index 66544faab710..8cfc68cbfa06 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -12,12 +12,16 @@ struct idpf_vport_max_q;
 #include <net/pkt_sched.h>
 #include <linux/aer.h>
 #include <linux/etherdevice.h>
+#include <linux/ioport.h>
 #include <linux/pci.h>
 #include <linux/bitfield.h>
 #include <linux/sctp.h>
 #include <linux/ethtool_netlink.h>
 #include <net/gro.h>
 
+#include <linux/net/intel/iidc_rdma.h>
+#include <linux/net/intel/iidc_rdma_idpf.h>
+
 #include "virtchnl2.h"
 #include "idpf_txrx.h"
 #include "idpf_controlq.h"
@@ -36,6 +40,7 @@ struct idpf_vport_max_q;
 #define IDPF_NUM_CHUNKS_PER_MSG(struct_sz, chunk_sz)	\
 	((IDPF_CTLQ_MAX_BUF_LEN - (struct_sz)) / (chunk_sz))
 
+#define IDPF_WAIT_FOR_MARKER_TIMEO	500
 #define IDPF_MAX_WAIT			500
 
 /* available message levels */
@@ -126,14 +131,12 @@ enum idpf_cap_field {
 
 /**
  * enum idpf_vport_state - Current vport state
- * @__IDPF_VPORT_DOWN: Vport is down
- * @__IDPF_VPORT_UP: Vport is up
- * @__IDPF_VPORT_STATE_LAST: Must be last, number of states
+ * @IDPF_VPORT_UP: Vport is up
+ * @IDPF_VPORT_STATE_NBITS: Must be last, number of states
  */
 enum idpf_vport_state {
-	__IDPF_VPORT_DOWN,
-	__IDPF_VPORT_UP,
-	__IDPF_VPORT_STATE_LAST,
+	IDPF_VPORT_UP,
+	IDPF_VPORT_STATE_NBITS
 };
 
 /**
@@ -143,6 +146,8 @@ enum idpf_vport_state {
  * @vport_id: Vport identifier
  * @link_speed_mbps: Link speed in mbps
  * @vport_idx: Relative vport index
+ * @max_tx_hdr_size: Max header length hardware can support
+ * @tx_max_bufs: Max buffers that can be transmitted with scatter-gather
  * @state: See enum idpf_vport_state
  * @netstats: Packet and byte stats
  * @stats_lock: Lock to protect stats update
@@ -153,7 +158,9 @@ struct idpf_netdev_priv {
 	u32 vport_id;
 	u32 link_speed_mbps;
 	u16 vport_idx;
-	enum idpf_vport_state state;
+	u16 max_tx_hdr_size;
+	u16 tx_max_bufs;
+	DECLARE_BITMAP(state, IDPF_VPORT_STATE_NBITS);
 	struct rtnl_link_stats64 netstats;
 	spinlock_t stats_lock;
 };
@@ -189,22 +196,38 @@ struct idpf_vport_max_q {
  * @mb_intr_reg_init: Mailbox interrupt register initialization
  * @reset_reg_init: Reset register initialization
  * @trigger_reset: Trigger a reset to occur
+ * @ptp_reg_init: PTP register initialization
  */
 struct idpf_reg_ops {
-	void (*ctlq_reg_init)(struct idpf_ctlq_create_info *cq);
+	void (*ctlq_reg_init)(struct idpf_adapter *adapter,
+			      struct idpf_ctlq_create_info *cq);
 	int (*intr_reg_init)(struct idpf_vport *vport);
 	void (*mb_intr_reg_init)(struct idpf_adapter *adapter);
 	void (*reset_reg_init)(struct idpf_adapter *adapter);
 	void (*trigger_reset)(struct idpf_adapter *adapter,
 			      enum idpf_flags trig_cause);
+	void (*ptp_reg_init)(const struct idpf_adapter *adapter);
 };
 
+#define IDPF_MMIO_REG_NUM_STATIC	2
+#define IDPF_PF_MBX_REGION_SZ		4096
+#define IDPF_PF_RSTAT_REGION_SZ		2048
+#define IDPF_VF_MBX_REGION_SZ		10240
+#define IDPF_VF_RSTAT_REGION_SZ		2048
+
 /**
  * struct idpf_dev_ops - Device specific operations
  * @reg_ops: Register operations
+ * @idc_init: IDC initialization
+ * @static_reg_info: array of mailbox and rstat register info
  */
 struct idpf_dev_ops {
 	struct idpf_reg_ops reg_ops;
+
+	int (*idc_init)(struct idpf_adapter *adapter);
+
+	/* static_reg_info[0] is mailbox region, static_reg_info[1] is rstat */
+	struct resource static_reg_info[IDPF_MMIO_REG_NUM_STATIC];
 };
 
 /**
@@ -224,16 +247,28 @@ enum idpf_vport_reset_cause {
 /**
  * enum idpf_vport_flags - Vport flags
  * @IDPF_VPORT_DEL_QUEUES: To send delete queues message
- * @IDPF_VPORT_SW_MARKER: Indicate TX pipe drain software marker packets
- *			  processing is done
  * @IDPF_VPORT_FLAGS_NBITS: Must be last
  */
 enum idpf_vport_flags {
 	IDPF_VPORT_DEL_QUEUES,
-	IDPF_VPORT_SW_MARKER,
 	IDPF_VPORT_FLAGS_NBITS,
 };
 
+/**
+ * struct idpf_tstamp_stats - Tx timestamp statistics
+ * @stats_sync: See struct u64_stats_sync
+ * @packets: Number of packets successfully timestamped by the hardware
+ * @discarded: Number of Tx skbs discarded due to cached PHC
+ *	       being too old to correctly extend timestamp
+ * @flushed: Number of Tx skbs flushed due to interface closed
+ */
+struct idpf_tstamp_stats {
+	struct u64_stats_sync stats_sync;
+	u64_stats_t packets;
+	u64_stats_t discarded;
+	u64_stats_t flushed;
+};
+
 struct idpf_port_stats {
 	struct u64_stats_sync stats_sync;
 	u64_stats_t rx_hw_csum_err;
@@ -247,6 +282,12 @@ struct idpf_port_stats {
 	struct virtchnl2_vport_stats vport_stats;
 };
 
+struct idpf_fsteer_fltr {
+	struct list_head list;
+	u32 loc;
+	u32 q_index;
+};
+
 /**
  * struct idpf_vport - Handle for netdevices and queue resources
  * @num_txq: Number of allocated TX queues
@@ -259,6 +300,10 @@ struct idpf_port_stats {
  * @txq_model: Split queue or single queue queuing model
  * @txqs: Used only in hotpath to get to the right queue very fast
  * @crc_enable: Enable CRC insertion offload
+ * @xdpsq_share: whether XDPSQ sharing is enabled
+ * @num_xdp_txq: number of XDPSQs
+ * @xdp_txq_offset: index of the first XDPSQ (== number of regular SQs)
+ * @xdp_prog: installed XDP program
  * @num_rxq: Number of allocated RX queues
  * @num_bufq: Number of allocated buffer queues
  * @rxq_desc_count: RX queue descriptor count. *MUST* have enough descriptors
@@ -271,6 +316,7 @@ struct idpf_port_stats {
  *	      group will yield total number of RX queues.
  * @rxq_model: Splitq queue or single queue queuing model
  * @rx_ptype_lkup: Lookup table for ptypes on RX
+ * @vdev_info: IDC vport device info pointer
  * @adapter: back pointer to associated adapter
  * @netdev: Associated net_device. Each vport should have one and only one
  *	    associated netdev.
@@ -283,13 +329,19 @@ struct idpf_port_stats {
  * @num_q_vectors: Number of IRQ vectors allocated
  * @q_vectors: Array of queue vectors
  * @q_vector_idxs: Starting index of queue vectors
+ * @noirq_dyn_ctl: register to enable/disable the vector for NOIRQ queues
+ * @noirq_dyn_ctl_ena: value to write to the above to enable it
+ * @noirq_v_idx: ID of the NOIRQ vector
  * @max_mtu: device given max possible MTU
  * @default_mac_addr: device will give a default MAC to use
  * @rx_itr_profile: RX profiles for Dynamic Interrupt Moderation
  * @tx_itr_profile: TX profiles for Dynamic Interrupt Moderation
  * @port_stats: per port csum, header split, and other offload stats
  * @link_up: True if link is up
- * @sw_marker_wq: workqueue for marker packets
+ * @tx_tstamp_caps: Capabilities negotiated for Tx timestamping
+ * @tstamp_config: The Tx tstamp config
+ * @tstamp_task: Tx timestamping task
+ * @tstamp_stats: Tx timestamping statistics
  */
 struct idpf_vport {
 	u16 num_txq;
@@ -303,6 +355,11 @@ struct idpf_vport {
 	struct idpf_tx_queue **txqs;
 	bool crc_enable;
 
+	bool xdpsq_share;
+	u16 num_xdp_txq;
+	u16 xdp_txq_offset;
+	struct bpf_prog *xdp_prog;
+
 	u16 num_rxq;
 	u16 num_bufq;
 	u32 rxq_desc_count;
@@ -313,6 +370,8 @@ struct idpf_vport {
 	u32 rxq_model;
 	struct libeth_rx_pt *rx_ptype_lkup;
 
+	struct iidc_rdma_vport_dev_info *vdev_info;
+
 	struct idpf_adapter *adapter;
 	struct net_device *netdev;
 	DECLARE_BITMAP(flags, IDPF_VPORT_FLAGS_NBITS);
@@ -325,6 +384,11 @@ struct idpf_vport {
 	u16 num_q_vectors;
 	struct idpf_q_vector *q_vectors;
 	u16 *q_vector_idxs;
+
+	void __iomem *noirq_dyn_ctl;
+	u32 noirq_dyn_ctl_ena;
+	u16 noirq_v_idx;
+
 	u16 max_mtu;
 	u8 default_mac_addr[ETH_ALEN];
 	u16 rx_itr_profile[IDPF_DIM_PROFILE_SLOTS];
@@ -333,7 +397,10 @@ struct idpf_vport {
 
 	bool link_up;
 
-	wait_queue_head_t sw_marker_wq;
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct kernel_hwtstamp_config tstamp_config;
+	struct work_struct tstamp_task;
+	struct idpf_tstamp_stats tstamp_stats;
 };
 
 /**
@@ -368,28 +435,53 @@ struct idpf_rss_data {
 };
 
 /**
+ * struct idpf_q_coalesce - User defined coalescing configuration values for
+ *			   a single queue.
+ * @tx_intr_mode: Dynamic TX ITR or not
+ * @rx_intr_mode: Dynamic RX ITR or not
+ * @tx_coalesce_usecs: TX interrupt throttling rate
+ * @rx_coalesce_usecs: RX interrupt throttling rate
+ *
+ * Used to restore user coalescing configuration after a reset.
+ */
+struct idpf_q_coalesce {
+	u32 tx_intr_mode;
+	u32 rx_intr_mode;
+	u32 tx_coalesce_usecs;
+	u32 rx_coalesce_usecs;
+};
+
+/**
  * struct idpf_vport_user_config_data - User defined configuration values for
  *					each vport.
  * @rss_data: See struct idpf_rss_data
+ * @q_coalesce: Array of per queue coalescing data
  * @num_req_tx_qs: Number of user requested TX queues through ethtool
  * @num_req_rx_qs: Number of user requested RX queues through ethtool
  * @num_req_txq_desc: Number of user requested TX queue descriptors through
  *		      ethtool
  * @num_req_rxq_desc: Number of user requested RX queue descriptors through
  *		      ethtool
+ * @xdp_prog: requested XDP program to install
  * @user_flags: User toggled config flags
  * @mac_filter_list: List of MAC filters
+ * @num_fsteer_fltrs: number of flow steering filters
+ * @flow_steer_list: list of flow steering filters
  *
  * Used to restore configuration after a reset as the vport will get wiped.
  */
 struct idpf_vport_user_config_data {
 	struct idpf_rss_data rss_data;
+	struct idpf_q_coalesce *q_coalesce;
 	u16 num_req_tx_qs;
 	u16 num_req_rx_qs;
 	u32 num_req_txq_desc;
 	u32 num_req_rxq_desc;
+	struct bpf_prog *xdp_prog;
 	DECLARE_BITMAP(user_flags, __IDPF_USER_FLAGS_NBITS);
 	struct list_head mac_filter_list;
+	u32 num_fsteer_fltrs;
+	struct list_head flow_steer_list;
 };
 
 /**
@@ -478,6 +570,13 @@ struct idpf_vport_config {
 
 struct idpf_vc_xn_manager;
 
+#define idpf_for_each_vport(adapter, iter) \
+	for (struct idpf_vport **__##iter = &(adapter)->vports[0], \
+	     *iter = (adapter)->max_vports ? *__##iter : NULL; \
+	     iter; \
+	     iter = (++__##iter) < &(adapter)->vports[(adapter)->max_vports] ? \
+	     *__##iter : NULL)
+
 /**
  * struct idpf_adapter - Device data struct generated on probe
  * @pdev: PCI device struct given on probe
@@ -489,10 +588,11 @@ struct idpf_vc_xn_manager;
  * @flags: See enum idpf_flags
  * @reset_reg: See struct idpf_reset_reg
  * @hw: Device access data
- * @num_req_msix: Requested number of MSIX vectors
  * @num_avail_msix: Available number of MSIX vectors
  * @num_msix_entries: Number of entries in MSIX table
  * @msix_entries: MSIX table
+ * @num_rdma_msix_entries: Available number of MSIX vectors for RDMA
+ * @rdma_msix_entries: RDMA MSIX table
  * @req_vec_chunks: Requested vector chunk data
  * @mb_vector: Mailbox vector data
  * @vector_stack: Stack to store the msix vector indexes
@@ -521,6 +621,7 @@ struct idpf_vc_xn_manager;
  * @caps: Negotiated capabilities with device
  * @vcxn_mngr: Virtchnl transaction manager
  * @dev_ops: See idpf_dev_ops
+ * @cdev_info: IDC core device info pointer
  * @num_vfs: Number of allocated VFs through sysfs. PF does not directly talk
  *	     to VFs but is used to initialize them
  * @crc_enable: Enable CRC insertion offload
@@ -530,6 +631,7 @@ struct idpf_vc_xn_manager;
  * @vector_lock: Lock to protect vector distribution
  * @queue_lock: Lock to protect queue distribution
  * @vc_buf_lock: Lock to protect virtchnl buffer
+ * @ptp: Storage for PTP-related data
  */
 struct idpf_adapter {
 	struct pci_dev *pdev;
@@ -542,10 +644,11 @@ struct idpf_adapter {
 	DECLARE_BITMAP(flags, IDPF_FLAGS_NBITS);
 	struct idpf_reset_reg reset_reg;
 	struct idpf_hw hw;
-	u16 num_req_msix;
 	u16 num_avail_msix;
 	u16 num_msix_entries;
 	struct msix_entry *msix_entries;
+	u16 num_rdma_msix_entries;
+	struct msix_entry *rdma_msix_entries;
 	struct virtchnl2_alloc_vectors *req_vec_chunks;
 	struct idpf_q_vector mb_vector;
 	struct idpf_vector_lifo vector_stack;
@@ -578,6 +681,7 @@ struct idpf_adapter {
 	struct idpf_vc_xn_manager *vcxn_mngr;
 
 	struct idpf_dev_ops dev_ops;
+	struct iidc_rdma_core_dev_info *cdev_info;
 	int num_vfs;
 	bool crc_enable;
 	bool req_tx_splitq;
@@ -587,6 +691,8 @@ struct idpf_adapter {
 	struct mutex vector_lock;
 	struct mutex queue_lock;
 	struct mutex vc_buf_lock;
+
+	struct idpf_ptp *ptp;
 };
 
 /**
@@ -601,6 +707,11 @@ static inline int idpf_is_queue_model_split(u16 q_model)
 	       q_model == VIRTCHNL2_QUEUE_MODEL_SPLIT;
 }
 
+static inline bool idpf_xdp_enabled(const struct idpf_vport *vport)
+{
+	return vport->adapter && vport->xdp_prog;
+}
+
 #define idpf_is_cap_ena(adapter, field, flag) \
 	idpf_is_capability_ena(adapter, false, field, flag)
 #define idpf_is_cap_ena_all(adapter, field, flag) \
@@ -609,17 +720,26 @@ static inline int idpf_is_queue_model_split(u16 q_model)
 bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
 			    enum idpf_cap_field field, u64 flag);
 
+/**
+ * idpf_is_rdma_cap_ena - Determine if RDMA is supported
+ * @adapter: private data struct
+ *
+ * Return: true if RDMA capability is enabled, false otherwise
+ */
+static inline bool idpf_is_rdma_cap_ena(struct idpf_adapter *adapter)
+{
+	return idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_RDMA);
+}
+
 #define IDPF_CAP_RSS (\
-	VIRTCHNL2_CAP_RSS_IPV4_TCP	|\
-	VIRTCHNL2_CAP_RSS_IPV4_TCP	|\
-	VIRTCHNL2_CAP_RSS_IPV4_UDP	|\
-	VIRTCHNL2_CAP_RSS_IPV4_SCTP	|\
-	VIRTCHNL2_CAP_RSS_IPV4_OTHER	|\
-	VIRTCHNL2_CAP_RSS_IPV6_TCP	|\
-	VIRTCHNL2_CAP_RSS_IPV6_TCP	|\
-	VIRTCHNL2_CAP_RSS_IPV6_UDP	|\
-	VIRTCHNL2_CAP_RSS_IPV6_SCTP	|\
-	VIRTCHNL2_CAP_RSS_IPV6_OTHER)
+	VIRTCHNL2_FLOW_IPV4_TCP		|\
+	VIRTCHNL2_FLOW_IPV4_UDP		|\
+	VIRTCHNL2_FLOW_IPV4_SCTP	|\
+	VIRTCHNL2_FLOW_IPV4_OTHER	|\
+	VIRTCHNL2_FLOW_IPV6_TCP		|\
+	VIRTCHNL2_FLOW_IPV6_UDP		|\
+	VIRTCHNL2_FLOW_IPV6_SCTP	|\
+	VIRTCHNL2_FLOW_IPV6_OTHER)
 
 #define IDPF_CAP_RSC (\
 	VIRTCHNL2_CAP_RSC_IPV4_TCP	|\
@@ -629,13 +749,13 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
 	VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V4	|\
 	VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V6)
 
-#define IDPF_CAP_RX_CSUM_L4V4 (\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_TCP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_UDP)
+#define IDPF_CAP_TX_CSUM_L4V4 (\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_TCP	|\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_UDP)
 
-#define IDPF_CAP_RX_CSUM_L4V6 (\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP)
+#define IDPF_CAP_TX_CSUM_L4V6 (\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_TCP	|\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_UDP)
 
 #define IDPF_CAP_RX_CSUM (\
 	VIRTCHNL2_CAP_RX_CSUM_L3_IPV4		|\
@@ -644,11 +764,9 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
 	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP	|\
 	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP)
 
-#define IDPF_CAP_SCTP_CSUM (\
+#define IDPF_CAP_TX_SCTP_CSUM (\
 	VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_SCTP	|\
-	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_SCTP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_SCTP)
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP)
 
 #define IDPF_CAP_TUNNEL_TX_CSUM (\
 	VIRTCHNL2_CAP_TX_CSUM_L3_SINGLE_TUNNEL	|\
@@ -664,6 +782,17 @@ static inline u16 idpf_get_reserved_vecs(struct idpf_adapter *adapter)
 }
 
 /**
+ * idpf_get_reserved_rdma_vecs - Get reserved RDMA vectors
+ * @adapter: private data struct
+ *
+ * Return: number of vectors reserved for RDMA
+ */
+static inline u16 idpf_get_reserved_rdma_vecs(struct idpf_adapter *adapter)
+{
+	return le16_to_cpu(adapter->caps.num_rdma_allocated_vectors);
+}
+
+/**
  * idpf_get_default_vports - Get default number of vports
  * @adapter: private data struct
  */
@@ -702,6 +831,34 @@ static inline u8 idpf_get_min_tx_pkt_len(struct idpf_adapter *adapter)
 }
 
 /**
+ * idpf_get_mbx_reg_addr - Get BAR0 mailbox register address
+ * @adapter: private data struct
+ * @reg_offset: register offset value
+ *
+ * Return: BAR0 mailbox register address based on register offset.
+ */
+static inline void __iomem *idpf_get_mbx_reg_addr(struct idpf_adapter *adapter,
+						  resource_size_t reg_offset)
+{
+	return adapter->hw.mbx.vaddr + reg_offset;
+}
+
+/**
+ * idpf_get_rstat_reg_addr - Get BAR0 rstat register address
+ * @adapter: private data struct
+ * @reg_offset: register offset value
+ *
+ * Return: BAR0 rstat register address based on register offset.
+ */
+static inline void __iomem *idpf_get_rstat_reg_addr(struct idpf_adapter *adapter,
+						    resource_size_t reg_offset)
+{
+	reg_offset -= adapter->dev_ops.static_reg_info[1].start;
+
+	return adapter->hw.rstat.vaddr + reg_offset;
+}
+
+/**
  * idpf_get_reg_addr - Get BAR0 register address
  * @adapter: private data struct
  * @reg_offset: register offset value
@@ -711,7 +868,30 @@ static inline u8 idpf_get_min_tx_pkt_len(struct idpf_adapter *adapter)
 static inline void __iomem *idpf_get_reg_addr(struct idpf_adapter *adapter,
 					      resource_size_t reg_offset)
 {
-	return (void __iomem *)(adapter->hw.hw_addr + reg_offset);
+	struct idpf_hw *hw = &adapter->hw;
+
+	for (int i = 0; i < hw->num_lan_regs; i++) {
+		struct idpf_mmio_reg *region = &hw->lan_regs[i];
+
+		if (reg_offset >= region->addr_start &&
+		    reg_offset < (region->addr_start + region->addr_len)) {
+			/* Convert the offset so that it is relative to the
+			 * start of the region.  Then add the base address of
+			 * the region to get the final address.
+			 */
+			reg_offset -= region->addr_start;
+
+			return region->vaddr + reg_offset;
+		}
+	}
+
+	/* It's impossible to hit this case with offsets from the CP. But if we
+	 * do for any other reason, the kernel will panic on that register
+	 * access. Might as well do it here to make it clear what's happening.
+	 */
+	BUG();
+
+	return NULL;
 }
 
 /**
@@ -725,7 +905,7 @@ static inline bool idpf_is_reset_detected(struct idpf_adapter *adapter)
 	if (!adapter->hw.arq)
 		return true;
 
-	return !(readl(idpf_get_reg_addr(adapter, adapter->hw.arq->reg.len)) &
+	return !(readl(idpf_get_mbx_reg_addr(adapter, adapter->hw.arq->reg.len)) &
 		 adapter->hw.arq->reg.len_mask);
 }
 
@@ -811,6 +991,13 @@ static inline void idpf_vport_ctrl_unlock(struct net_device *netdev)
 	mutex_unlock(&np->adapter->vport_ctrl_lock);
 }
 
+static inline bool idpf_vport_ctrl_is_locked(struct net_device *netdev)
+{
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+
+	return mutex_is_locked(&np->adapter->vport_ctrl_lock);
+}
+
 void idpf_statistics_task(struct work_struct *work);
 void idpf_init_task(struct work_struct *work);
 void idpf_service_task(struct work_struct *work);
@@ -834,5 +1021,16 @@ int idpf_sriov_configure(struct pci_dev *pdev, int num_vfs);
 
 u8 idpf_vport_get_hsplit(const struct idpf_vport *vport);
 bool idpf_vport_set_hsplit(const struct idpf_vport *vport, u8 val);
-
+int idpf_idc_init(struct idpf_adapter *adapter);
+int idpf_idc_init_aux_core_dev(struct idpf_adapter *adapter,
+			       enum iidc_function_type ftype);
+void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info);
+void idpf_idc_deinit_vport_aux_device(struct iidc_rdma_vport_dev_info *vdev_info);
+void idpf_idc_issue_reset_event(struct iidc_rdma_core_dev_info *cdev_info);
+void idpf_idc_vdev_mtu_event(struct iidc_rdma_vport_dev_info *vdev_info,
+			     enum iidc_rdma_event_type event_type);
+
+int idpf_add_del_fsteer_filters(struct idpf_adapter *adapter,
+				struct virtchnl2_flow_rule_add_del *rule,
+				enum virtchnl2_op opcode);
 #endif /* !_IDPF_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.c b/drivers/net/ethernet/intel/idpf/idpf_controlq.c
index 4849590a5591..67894eda2d29 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.c
@@ -36,19 +36,19 @@ static void idpf_ctlq_init_regs(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 {
 	/* Update tail to post pre-allocated buffers for rx queues */
 	if (is_rxq)
-		wr32(hw, cq->reg.tail, (u32)(cq->ring_size - 1));
+		idpf_mbx_wr32(hw, cq->reg.tail, (u32)(cq->ring_size - 1));
 
 	/* For non-Mailbox control queues only TAIL need to be set */
 	if (cq->q_id != -1)
 		return;
 
 	/* Clear Head for both send or receive */
-	wr32(hw, cq->reg.head, 0);
+	idpf_mbx_wr32(hw, cq->reg.head, 0);
 
 	/* set starting point */
-	wr32(hw, cq->reg.bal, lower_32_bits(cq->desc_ring.pa));
-	wr32(hw, cq->reg.bah, upper_32_bits(cq->desc_ring.pa));
-	wr32(hw, cq->reg.len, (cq->ring_size | cq->reg.len_ena_mask));
+	idpf_mbx_wr32(hw, cq->reg.bal, lower_32_bits(cq->desc_ring.pa));
+	idpf_mbx_wr32(hw, cq->reg.bah, upper_32_bits(cq->desc_ring.pa));
+	idpf_mbx_wr32(hw, cq->reg.len, (cq->ring_size | cq->reg.len_ena_mask));
 }
 
 /**
@@ -96,7 +96,7 @@ static void idpf_ctlq_init_rxq_bufs(struct idpf_ctlq_info *cq)
  */
 static void idpf_ctlq_shutdown(struct idpf_hw *hw, struct idpf_ctlq_info *cq)
 {
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	/* free ring buffers and the ring itself */
 	idpf_ctlq_dealloc_ring_res(hw, cq);
@@ -104,8 +104,7 @@ static void idpf_ctlq_shutdown(struct idpf_hw *hw, struct idpf_ctlq_info *cq)
 	/* Set ring_size to 0 to indicate uninitialized queue */
 	cq->ring_size = 0;
 
-	mutex_unlock(&cq->cq_lock);
-	mutex_destroy(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 }
 
 /**
@@ -173,7 +172,7 @@ int idpf_ctlq_add(struct idpf_hw *hw,
 
 	idpf_ctlq_init_regs(hw, cq, is_rxq);
 
-	mutex_init(&cq->cq_lock);
+	spin_lock_init(&cq->cq_lock);
 
 	list_add(&cq->cq_list, &hw->cq_list_head);
 
@@ -272,7 +271,7 @@ int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 	int err = 0;
 	int i;
 
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	/* Ensure there are enough descriptors to send all messages */
 	num_desc_avail = IDPF_CTLQ_DESC_UNUSED(cq);
@@ -329,10 +328,10 @@ int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 	 */
 	dma_wmb();
 
-	wr32(hw, cq->reg.tail, cq->next_to_use);
+	idpf_mbx_wr32(hw, cq->reg.tail, cq->next_to_use);
 
 err_unlock:
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	return err;
 }
@@ -364,7 +363,7 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count,
 	if (*clean_count > cq->ring_size)
 		return -EBADR;
 
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	ntc = cq->next_to_clean;
 
@@ -376,6 +375,9 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count,
 		if (!(le16_to_cpu(desc->flags) & IDPF_CTLQ_FLAG_DD))
 			break;
 
+		/* Ensure no other fields are read until DD flag is checked */
+		dma_rmb();
+
 		/* strip off FW internal code */
 		desc_err = le16_to_cpu(desc->ret_val) & 0xff;
 
@@ -394,7 +396,7 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count,
 
 	cq->next_to_clean = ntc;
 
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	/* Return number of descriptors actually cleaned */
 	*clean_count = i;
@@ -432,7 +434,7 @@ int idpf_ctlq_post_rx_buffs(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 	if (*buff_count > 0)
 		buffs_avail = true;
 
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	if (tbp >= cq->ring_size)
 		tbp = 0;
@@ -518,10 +520,10 @@ post_buffs_out:
 
 		dma_wmb();
 
-		wr32(hw, cq->reg.tail, cq->next_to_post);
+		idpf_mbx_wr32(hw, cq->reg.tail, cq->next_to_post);
 	}
 
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	/* return the number of buffers that were not posted */
 	*buff_count = *buff_count - i;
@@ -549,7 +551,7 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg,
 	u16 i;
 
 	/* take the lock before we start messing with the ring */
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	ntc = cq->next_to_clean;
 
@@ -563,6 +565,9 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg,
 		if (!(flags & IDPF_CTLQ_FLAG_DD))
 			break;
 
+		/* Ensure no other fields are read until DD flag is checked */
+		dma_rmb();
+
 		q_msg[i].vmvf_type = (flags &
 				      (IDPF_CTLQ_FLAG_FTYPE_VM |
 				       IDPF_CTLQ_FLAG_FTYPE_PF)) >>
@@ -608,7 +613,7 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg,
 
 	cq->next_to_clean = ntc;
 
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	*num_q_msg = i;
 	if (*num_q_msg == 0)
diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.h b/drivers/net/ethernet/intel/idpf/idpf_controlq.h
index c1aba09e9856..de4ece40c2ff 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.h
@@ -94,12 +94,26 @@ struct idpf_mbxq_desc {
 	u32 pf_vf_id;		/* used by CP when sending to PF */
 };
 
+/* Max number of MMIO regions not including the mailbox and rstat regions in
+ * the fallback case when the whole bar is mapped.
+ */
+#define IDPF_MMIO_MAP_FALLBACK_MAX_REMAINING		3
+
+struct idpf_mmio_reg {
+	void __iomem *vaddr;
+	resource_size_t addr_start;
+	resource_size_t addr_len;
+};
+
 /* Define the driver hardware struct to replace other control structs as needed
  * Align to ctlq_hw_info
  */
 struct idpf_hw {
-	void __iomem *hw_addr;
-	resource_size_t hw_addr_len;
+	struct idpf_mmio_reg mbx;
+	struct idpf_mmio_reg rstat;
+	/* Array of remaining LAN BAR regions */
+	int num_lan_regs;
+	struct idpf_mmio_reg *lan_regs;
 
 	struct idpf_adapter *back;
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
index e8e046ef2f0d..3414c5f9a831 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
@@ -99,7 +99,7 @@ struct idpf_ctlq_info {
 
 	enum idpf_ctlq_type cq_type;
 	int q_id;
-	struct mutex cq_lock;		/* control queue lock */
+	spinlock_t cq_lock;		/* control queue lock */
 	/* used for interrupt processing */
 	u16 next_to_use;
 	u16 next_to_clean;
@@ -123,9 +123,12 @@ struct idpf_ctlq_info {
 /**
  * enum idpf_mbx_opc - PF/VF mailbox commands
  * @idpf_mbq_opc_send_msg_to_cp: used by PF or VF to send a message to its CP
+ * @idpf_mbq_opc_send_msg_to_peer_drv: used by PF or VF to send a message to
+ *				       any peer driver
  */
 enum idpf_mbx_opc {
 	idpf_mbq_opc_send_msg_to_cp		= 0x0801,
+	idpf_mbq_opc_send_msg_to_peer_drv	= 0x0804,
 };
 
 /* API supported for control queue management */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c
index 41e4bd49402a..3a04a6bd0d7c 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_dev.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c
@@ -4,15 +4,19 @@
 #include "idpf.h"
 #include "idpf_lan_pf_regs.h"
 #include "idpf_virtchnl.h"
+#include "idpf_ptp.h"
 
 #define IDPF_PF_ITR_IDX_SPACING		0x4
 
 /**
  * idpf_ctlq_reg_init - initialize default mailbox registers
+ * @adapter: adapter structure
  * @cq: pointer to the array of create control queues
  */
-static void idpf_ctlq_reg_init(struct idpf_ctlq_create_info *cq)
+static void idpf_ctlq_reg_init(struct idpf_adapter *adapter,
+			       struct idpf_ctlq_create_info *cq)
 {
+	resource_size_t mbx_start = adapter->dev_ops.static_reg_info[0].start;
 	int i;
 
 	for (i = 0; i < IDPF_NUM_DFLT_MBX_Q; i++) {
@@ -21,22 +25,22 @@ static void idpf_ctlq_reg_init(struct idpf_ctlq_create_info *cq)
 		switch (ccq->type) {
 		case IDPF_CTLQ_TYPE_MAILBOX_TX:
 			/* set head and tail registers in our local struct */
-			ccq->reg.head = PF_FW_ATQH;
-			ccq->reg.tail = PF_FW_ATQT;
-			ccq->reg.len = PF_FW_ATQLEN;
-			ccq->reg.bah = PF_FW_ATQBAH;
-			ccq->reg.bal = PF_FW_ATQBAL;
+			ccq->reg.head = PF_FW_ATQH - mbx_start;
+			ccq->reg.tail = PF_FW_ATQT - mbx_start;
+			ccq->reg.len = PF_FW_ATQLEN - mbx_start;
+			ccq->reg.bah = PF_FW_ATQBAH - mbx_start;
+			ccq->reg.bal = PF_FW_ATQBAL - mbx_start;
 			ccq->reg.len_mask = PF_FW_ATQLEN_ATQLEN_M;
 			ccq->reg.len_ena_mask = PF_FW_ATQLEN_ATQENABLE_M;
 			ccq->reg.head_mask = PF_FW_ATQH_ATQH_M;
 			break;
 		case IDPF_CTLQ_TYPE_MAILBOX_RX:
 			/* set head and tail registers in our local struct */
-			ccq->reg.head = PF_FW_ARQH;
-			ccq->reg.tail = PF_FW_ARQT;
-			ccq->reg.len = PF_FW_ARQLEN;
-			ccq->reg.bah = PF_FW_ARQBAH;
-			ccq->reg.bal = PF_FW_ARQBAL;
+			ccq->reg.head = PF_FW_ARQH - mbx_start;
+			ccq->reg.tail = PF_FW_ARQT - mbx_start;
+			ccq->reg.len = PF_FW_ARQLEN - mbx_start;
+			ccq->reg.bah = PF_FW_ARQBAH - mbx_start;
+			ccq->reg.bal = PF_FW_ARQBAL - mbx_start;
 			ccq->reg.len_mask = PF_FW_ARQLEN_ARQLEN_M;
 			ccq->reg.len_ena_mask = PF_FW_ARQLEN_ARQENABLE_M;
 			ccq->reg.head_mask = PF_FW_ARQH_ARQH_M;
@@ -73,7 +77,7 @@ static int idpf_intr_reg_init(struct idpf_vport *vport)
 	int num_vecs = vport->num_q_vectors;
 	struct idpf_vec_regs *reg_vals;
 	int num_regs, i, err = 0;
-	u32 rx_itr, tx_itr;
+	u32 rx_itr, tx_itr, val;
 	u16 total_vecs;
 
 	total_vecs = idpf_get_reserved_vecs(vport->adapter);
@@ -117,6 +121,15 @@ static int idpf_intr_reg_init(struct idpf_vport *vport)
 		intr->tx_itr = idpf_get_reg_addr(adapter, tx_itr);
 	}
 
+	/* Data vector for NOIRQ queues */
+
+	val = reg_vals[vport->q_vector_idxs[i] - IDPF_MBX_Q_VEC].dyn_ctl_reg;
+	vport->noirq_dyn_ctl = idpf_get_reg_addr(adapter, val);
+
+	val = PF_GLINT_DYN_CTL_WB_ON_ITR_M | PF_GLINT_DYN_CTL_INTENA_MSK_M |
+	      FIELD_PREP(PF_GLINT_DYN_CTL_ITR_INDX_M, IDPF_NO_ITR_UPDATE_IDX);
+	vport->noirq_dyn_ctl_ena = val;
+
 free_reg_vals:
 	kfree(reg_vals);
 
@@ -129,7 +142,7 @@ free_reg_vals:
  */
 static void idpf_reset_reg_init(struct idpf_adapter *adapter)
 {
-	adapter->reset_reg.rstat = idpf_get_reg_addr(adapter, PFGEN_RSTAT);
+	adapter->reset_reg.rstat = idpf_get_rstat_reg_addr(adapter, PFGEN_RSTAT);
 	adapter->reset_reg.rstat_m = PFGEN_RSTAT_PFR_STATE_M;
 }
 
@@ -143,9 +156,32 @@ static void idpf_trigger_reset(struct idpf_adapter *adapter,
 {
 	u32 reset_reg;
 
-	reset_reg = readl(idpf_get_reg_addr(adapter, PFGEN_CTRL));
+	reset_reg = readl(idpf_get_rstat_reg_addr(adapter, PFGEN_CTRL));
 	writel(reset_reg | PFGEN_CTRL_PFSWR,
-	       idpf_get_reg_addr(adapter, PFGEN_CTRL));
+	       idpf_get_rstat_reg_addr(adapter, PFGEN_CTRL));
+}
+
+/**
+ * idpf_ptp_reg_init - Initialize required registers
+ * @adapter: Driver specific private structure
+ *
+ * Set the bits required for enabling shtime and cmd execution
+ */
+static void idpf_ptp_reg_init(const struct idpf_adapter *adapter)
+{
+	adapter->ptp->cmd.shtime_enable_mask = PF_GLTSYN_CMD_SYNC_SHTIME_EN_M;
+	adapter->ptp->cmd.exec_cmd_mask = PF_GLTSYN_CMD_SYNC_EXEC_CMD_M;
+}
+
+/**
+ * idpf_idc_register - register for IDC callbacks
+ * @adapter: Driver specific private structure
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_idc_register(struct idpf_adapter *adapter)
+{
+	return idpf_idc_init_aux_core_dev(adapter, IIDC_FUNCTION_TYPE_PF);
 }
 
 /**
@@ -159,6 +195,7 @@ static void idpf_reg_ops_init(struct idpf_adapter *adapter)
 	adapter->dev_ops.reg_ops.mb_intr_reg_init = idpf_mb_intr_reg_init;
 	adapter->dev_ops.reg_ops.reset_reg_init = idpf_reset_reg_init;
 	adapter->dev_ops.reg_ops.trigger_reset = idpf_trigger_reset;
+	adapter->dev_ops.reg_ops.ptp_reg_init = idpf_ptp_reg_init;
 }
 
 /**
@@ -168,4 +205,11 @@ static void idpf_reg_ops_init(struct idpf_adapter *adapter)
 void idpf_dev_ops_init(struct idpf_adapter *adapter)
 {
 	idpf_reg_ops_init(adapter);
+
+	adapter->dev_ops.idc_init = idpf_idc_register;
+
+	resource_set_range(&adapter->dev_ops.static_reg_info[0],
+			   PF_FW_BASE, IDPF_PF_MBX_REGION_SZ);
+	resource_set_range(&adapter->dev_ops.static_reg_info[1],
+			   PFGEN_RTRIG, IDPF_PF_RSTAT_REGION_SZ);
 }
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
index 59b1a1a09996..2589e124e41c 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
@@ -2,6 +2,27 @@
 /* Copyright (C) 2023 Intel Corporation */
 
 #include "idpf.h"
+#include "idpf_ptp.h"
+#include "idpf_virtchnl.h"
+
+/**
+ * idpf_get_rx_ring_count - get RX ring count
+ * @netdev: network interface device structure
+ *
+ * Return: number of RX rings.
+ */
+static u32 idpf_get_rx_ring_count(struct net_device *netdev)
+{
+	struct idpf_vport *vport;
+	u32 num_rxq;
+
+	idpf_vport_ctrl_lock(netdev);
+	vport = idpf_netdev_to_vport(netdev);
+	num_rxq = vport->num_rxq;
+	idpf_vport_ctrl_unlock(netdev);
+
+	return num_rxq;
+}
 
 /**
  * idpf_get_rxnfc - command to get RX flow classification rules
@@ -12,26 +33,309 @@
  * Returns Success if the command is supported.
  */
 static int idpf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
-			  u32 __always_unused *rule_locs)
+			  u32 *rule_locs)
 {
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	struct idpf_vport_user_config_data *user_config;
+	struct idpf_fsteer_fltr *f;
 	struct idpf_vport *vport;
+	unsigned int cnt = 0;
+	int err = 0;
 
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
+	user_config = &np->adapter->vport_config[np->vport_idx]->user_config;
 
 	switch (cmd->cmd) {
-	case ETHTOOL_GRXRINGS:
-		cmd->data = vport->num_rxq;
-		idpf_vport_ctrl_unlock(netdev);
-
-		return 0;
+	case ETHTOOL_GRXCLSRLCNT:
+		cmd->rule_cnt = user_config->num_fsteer_fltrs;
+		cmd->data = idpf_fsteer_max_rules(vport);
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		err = -EINVAL;
+		list_for_each_entry(f, &user_config->flow_steer_list, list)
+			if (f->loc == cmd->fs.location) {
+				cmd->fs.ring_cookie = f->q_index;
+				err = 0;
+				break;
+			}
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		cmd->data = idpf_fsteer_max_rules(vport);
+		list_for_each_entry(f, &user_config->flow_steer_list, list) {
+			if (cnt == cmd->rule_cnt) {
+				err = -EMSGSIZE;
+				break;
+			}
+			rule_locs[cnt] = f->loc;
+			cnt++;
+		}
+		if (!err)
+			cmd->rule_cnt = user_config->num_fsteer_fltrs;
+		break;
 	default:
 		break;
 	}
 
 	idpf_vport_ctrl_unlock(netdev);
 
-	return -EOPNOTSUPP;
+	return err;
+}
+
+static void idpf_fsteer_fill_ipv4(struct virtchnl2_proto_hdrs *hdrs,
+				  struct ethtool_rx_flow_spec *fsp)
+{
+	struct iphdr *iph;
+
+	hdrs->proto_hdr[0].hdr_type = cpu_to_le32(VIRTCHNL2_PROTO_HDR_IPV4);
+
+	iph = (struct iphdr *)hdrs->proto_hdr[0].buffer_spec;
+	iph->saddr = fsp->h_u.tcp_ip4_spec.ip4src;
+	iph->daddr = fsp->h_u.tcp_ip4_spec.ip4dst;
+
+	iph = (struct iphdr *)hdrs->proto_hdr[0].buffer_mask;
+	iph->saddr = fsp->m_u.tcp_ip4_spec.ip4src;
+	iph->daddr = fsp->m_u.tcp_ip4_spec.ip4dst;
+}
+
+static void idpf_fsteer_fill_udp(struct virtchnl2_proto_hdrs *hdrs,
+				 struct ethtool_rx_flow_spec *fsp,
+				 bool v4)
+{
+	struct udphdr *udph, *udpm;
+
+	hdrs->proto_hdr[1].hdr_type = cpu_to_le32(VIRTCHNL2_PROTO_HDR_UDP);
+
+	udph = (struct udphdr *)hdrs->proto_hdr[1].buffer_spec;
+	udpm = (struct udphdr *)hdrs->proto_hdr[1].buffer_mask;
+
+	if (v4) {
+		udph->source = fsp->h_u.udp_ip4_spec.psrc;
+		udph->dest = fsp->h_u.udp_ip4_spec.pdst;
+		udpm->source = fsp->m_u.udp_ip4_spec.psrc;
+		udpm->dest = fsp->m_u.udp_ip4_spec.pdst;
+	} else {
+		udph->source = fsp->h_u.udp_ip6_spec.psrc;
+		udph->dest = fsp->h_u.udp_ip6_spec.pdst;
+		udpm->source = fsp->m_u.udp_ip6_spec.psrc;
+		udpm->dest = fsp->m_u.udp_ip6_spec.pdst;
+	}
+}
+
+static void idpf_fsteer_fill_tcp(struct virtchnl2_proto_hdrs *hdrs,
+				 struct ethtool_rx_flow_spec *fsp,
+				 bool v4)
+{
+	struct tcphdr *tcph, *tcpm;
+
+	hdrs->proto_hdr[1].hdr_type = cpu_to_le32(VIRTCHNL2_PROTO_HDR_TCP);
+
+	tcph = (struct tcphdr *)hdrs->proto_hdr[1].buffer_spec;
+	tcpm = (struct tcphdr *)hdrs->proto_hdr[1].buffer_mask;
+
+	if (v4) {
+		tcph->source = fsp->h_u.tcp_ip4_spec.psrc;
+		tcph->dest = fsp->h_u.tcp_ip4_spec.pdst;
+		tcpm->source = fsp->m_u.tcp_ip4_spec.psrc;
+		tcpm->dest = fsp->m_u.tcp_ip4_spec.pdst;
+	} else {
+		tcph->source = fsp->h_u.tcp_ip6_spec.psrc;
+		tcph->dest = fsp->h_u.tcp_ip6_spec.pdst;
+		tcpm->source = fsp->m_u.tcp_ip6_spec.psrc;
+		tcpm->dest = fsp->m_u.tcp_ip6_spec.pdst;
+	}
+}
+
+/**
+ * idpf_add_flow_steer - add a Flow Steering filter
+ * @netdev: network interface device structure
+ * @cmd: command to add Flow Steering filter
+ *
+ * Return: 0 on success and negative values for failure
+ */
+static int idpf_add_flow_steer(struct net_device *netdev,
+			       struct ethtool_rxnfc *cmd)
+{
+	struct idpf_fsteer_fltr *fltr, *parent = NULL, *f;
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	struct idpf_vport_user_config_data *user_config;
+	struct ethtool_rx_flow_spec *fsp = &cmd->fs;
+	struct virtchnl2_flow_rule_add_del *rule;
+	struct idpf_vport_config *vport_config;
+	struct virtchnl2_rule_action_set *acts;
+	struct virtchnl2_flow_rule_info *info;
+	struct virtchnl2_proto_hdrs *hdrs;
+	struct idpf_vport *vport;
+	u32 flow_type, q_index;
+	u16 num_rxq;
+	int err;
+
+	vport = idpf_netdev_to_vport(netdev);
+	vport_config = vport->adapter->vport_config[np->vport_idx];
+	user_config = &vport_config->user_config;
+	num_rxq = user_config->num_req_rx_qs;
+
+	flow_type = fsp->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS);
+	if (flow_type != fsp->flow_type)
+		return -EINVAL;
+
+	if (!idpf_sideband_action_ena(vport, fsp) ||
+	    !idpf_sideband_flow_type_ena(vport, flow_type))
+		return -EOPNOTSUPP;
+
+	if (user_config->num_fsteer_fltrs > idpf_fsteer_max_rules(vport))
+		return -ENOSPC;
+
+	q_index = fsp->ring_cookie;
+	if (q_index >= num_rxq)
+		return -EINVAL;
+
+	rule = kzalloc(struct_size(rule, rule_info, 1), GFP_KERNEL);
+	if (!rule)
+		return -ENOMEM;
+
+	rule->vport_id = cpu_to_le32(vport->vport_id);
+	rule->count = cpu_to_le32(1);
+	info = &rule->rule_info[0];
+	info->rule_id = cpu_to_le32(fsp->location);
+
+	hdrs = &info->rule_cfg.proto_hdrs;
+	hdrs->tunnel_level = 0;
+	hdrs->count = cpu_to_le32(2);
+
+	acts = &info->rule_cfg.action_set;
+	acts->count = cpu_to_le32(1);
+	acts->actions[0].action_type = cpu_to_le32(VIRTCHNL2_ACTION_QUEUE);
+	acts->actions[0].act_conf.q_id = cpu_to_le32(q_index);
+
+	switch (flow_type) {
+	case UDP_V4_FLOW:
+		idpf_fsteer_fill_ipv4(hdrs, fsp);
+		idpf_fsteer_fill_udp(hdrs, fsp, true);
+		break;
+	case TCP_V4_FLOW:
+		idpf_fsteer_fill_ipv4(hdrs, fsp);
+		idpf_fsteer_fill_tcp(hdrs, fsp, true);
+		break;
+	default:
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = idpf_add_del_fsteer_filters(vport->adapter, rule,
+					  VIRTCHNL2_OP_ADD_FLOW_RULE);
+	if (err)
+		goto out;
+
+	if (info->status != cpu_to_le32(VIRTCHNL2_FLOW_RULE_SUCCESS)) {
+		err = -EIO;
+		goto out;
+	}
+
+	fltr = kzalloc(sizeof(*fltr), GFP_KERNEL);
+	if (!fltr) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	fltr->loc = fsp->location;
+	fltr->q_index = q_index;
+	list_for_each_entry(f, &user_config->flow_steer_list, list) {
+		if (f->loc >= fltr->loc)
+			break;
+		parent = f;
+	}
+
+	parent ? list_add(&fltr->list, &parent->list) :
+		 list_add(&fltr->list, &user_config->flow_steer_list);
+
+	user_config->num_fsteer_fltrs++;
+
+out:
+	kfree(rule);
+	return err;
+}
+
+/**
+ * idpf_del_flow_steer - delete a Flow Steering filter
+ * @netdev: network interface device structure
+ * @cmd: command to add Flow Steering filter
+ *
+ * Return: 0 on success and negative values for failure
+ */
+static int idpf_del_flow_steer(struct net_device *netdev,
+			       struct ethtool_rxnfc *cmd)
+{
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	struct idpf_vport_user_config_data *user_config;
+	struct ethtool_rx_flow_spec *fsp = &cmd->fs;
+	struct virtchnl2_flow_rule_add_del *rule;
+	struct idpf_vport_config *vport_config;
+	struct virtchnl2_flow_rule_info *info;
+	struct idpf_fsteer_fltr *f, *iter;
+	struct idpf_vport *vport;
+	int err;
+
+	vport = idpf_netdev_to_vport(netdev);
+	vport_config = vport->adapter->vport_config[np->vport_idx];
+	user_config = &vport_config->user_config;
+
+	if (!idpf_sideband_action_ena(vport, fsp))
+		return -EOPNOTSUPP;
+
+	rule = kzalloc(struct_size(rule, rule_info, 1), GFP_KERNEL);
+	if (!rule)
+		return -ENOMEM;
+
+	rule->vport_id = cpu_to_le32(vport->vport_id);
+	rule->count = cpu_to_le32(1);
+	info = &rule->rule_info[0];
+	info->rule_id = cpu_to_le32(fsp->location);
+
+	err = idpf_add_del_fsteer_filters(vport->adapter, rule,
+					  VIRTCHNL2_OP_DEL_FLOW_RULE);
+	if (err)
+		goto out;
+
+	if (info->status != cpu_to_le32(VIRTCHNL2_FLOW_RULE_SUCCESS)) {
+		err = -EIO;
+		goto out;
+	}
+
+	list_for_each_entry_safe(f, iter,
+				 &user_config->flow_steer_list, list) {
+		if (f->loc == fsp->location) {
+			list_del(&f->list);
+			kfree(f);
+			user_config->num_fsteer_fltrs--;
+			goto out;
+		}
+	}
+	err = -EINVAL;
+
+out:
+	kfree(rule);
+	return err;
+}
+
+static int idpf_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
+{
+	int ret = -EOPNOTSUPP;
+
+	idpf_vport_ctrl_lock(netdev);
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		ret = idpf_add_flow_steer(netdev, cmd);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		ret = idpf_del_flow_steer(netdev, cmd);
+		break;
+	default:
+		break;
+	}
+
+	idpf_vport_ctrl_unlock(netdev);
+	return ret;
 }
 
 /**
@@ -46,7 +350,7 @@ static u32 idpf_get_rxfh_key_size(struct net_device *netdev)
 	struct idpf_vport_user_config_data *user_config;
 
 	if (!idpf_is_cap_ena_all(np->adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
-		return -EOPNOTSUPP;
+		return 0;
 
 	user_config = &np->adapter->vport_config[np->vport_idx]->user_config;
 
@@ -65,7 +369,7 @@ static u32 idpf_get_rxfh_indir_size(struct net_device *netdev)
 	struct idpf_vport_user_config_data *user_config;
 
 	if (!idpf_is_cap_ena_all(np->adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
-		return -EOPNOTSUPP;
+		return 0;
 
 	user_config = &np->adapter->vport_config[np->vport_idx]->user_config;
 
@@ -98,7 +402,7 @@ static int idpf_get_rxfh(struct net_device *netdev,
 	}
 
 	rss_data = &adapter->vport_config[np->vport_idx]->user_config.rss_data;
-	if (np->state != __IDPF_VPORT_UP)
+	if (!test_bit(IDPF_VPORT_UP, np->state))
 		goto unlock_mutex;
 
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
@@ -148,7 +452,7 @@ static int idpf_set_rxfh(struct net_device *netdev,
 	}
 
 	rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data;
-	if (np->state != __IDPF_VPORT_UP)
+	if (!test_bit(IDPF_VPORT_UP, np->state))
 		goto unlock_mutex;
 
 	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
@@ -879,7 +1183,7 @@ static void idpf_get_ethtool_stats(struct net_device *netdev,
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
 
-	if (np->state != __IDPF_VPORT_UP) {
+	if (!test_bit(IDPF_VPORT_UP, np->state)) {
 		idpf_vport_ctrl_unlock(netdev);
 
 		return;
@@ -957,8 +1261,8 @@ static void idpf_get_ethtool_stats(struct net_device *netdev,
  *
  * returns pointer to rx vector
  */
-static struct idpf_q_vector *idpf_find_rxq_vec(const struct idpf_vport *vport,
-					       int q_num)
+struct idpf_q_vector *idpf_find_rxq_vec(const struct idpf_vport *vport,
+					u32 q_num)
 {
 	int q_grp, q_idx;
 
@@ -978,8 +1282,8 @@ static struct idpf_q_vector *idpf_find_rxq_vec(const struct idpf_vport *vport,
  *
  * returns pointer to tx vector
  */
-static struct idpf_q_vector *idpf_find_txq_vec(const struct idpf_vport *vport,
-					       int q_num)
+struct idpf_q_vector *idpf_find_txq_vec(const struct idpf_vport *vport,
+					u32 q_num)
 {
 	int q_grp;
 
@@ -1031,7 +1335,7 @@ static int idpf_get_q_coalesce(struct net_device *netdev,
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
 
-	if (np->state != __IDPF_VPORT_UP)
+	if (!test_bit(IDPF_VPORT_UP, np->state))
 		goto unlock_mutex;
 
 	if (q_num >= vport->num_rxq && q_num >= vport->num_txq) {
@@ -1089,12 +1393,14 @@ static int idpf_get_per_q_coalesce(struct net_device *netdev, u32 q_num,
 /**
  * __idpf_set_q_coalesce - set ITR values for specific queue
  * @ec: ethtool structure from user to update ITR settings
+ * @q_coal: per queue coalesce settings
  * @qv: queue vector for which itr values has to be set
  * @is_rxq: is queue type rx
  *
  * Returns 0 on success, negative otherwise.
  */
 static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec,
+				 struct idpf_q_coalesce *q_coal,
 				 struct idpf_q_vector *qv, bool is_rxq)
 {
 	u32 use_adaptive_coalesce, coalesce_usecs;
@@ -1138,20 +1444,25 @@ static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec,
 
 	if (is_rxq) {
 		qv->rx_itr_value = coalesce_usecs;
+		q_coal->rx_coalesce_usecs = coalesce_usecs;
 		if (use_adaptive_coalesce) {
 			qv->rx_intr_mode = IDPF_ITR_DYNAMIC;
+			q_coal->rx_intr_mode = IDPF_ITR_DYNAMIC;
 		} else {
 			qv->rx_intr_mode = !IDPF_ITR_DYNAMIC;
-			idpf_vport_intr_write_itr(qv, qv->rx_itr_value,
-						  false);
+			q_coal->rx_intr_mode = !IDPF_ITR_DYNAMIC;
+			idpf_vport_intr_write_itr(qv, coalesce_usecs, false);
 		}
 	} else {
 		qv->tx_itr_value = coalesce_usecs;
+		q_coal->tx_coalesce_usecs = coalesce_usecs;
 		if (use_adaptive_coalesce) {
 			qv->tx_intr_mode = IDPF_ITR_DYNAMIC;
+			q_coal->tx_intr_mode = IDPF_ITR_DYNAMIC;
 		} else {
 			qv->tx_intr_mode = !IDPF_ITR_DYNAMIC;
-			idpf_vport_intr_write_itr(qv, qv->tx_itr_value, true);
+			q_coal->tx_intr_mode = !IDPF_ITR_DYNAMIC;
+			idpf_vport_intr_write_itr(qv, coalesce_usecs, true);
 		}
 	}
 
@@ -1164,6 +1475,7 @@ static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec,
 /**
  * idpf_set_q_coalesce - set ITR values for specific queue
  * @vport: vport associated to the queue that need updating
+ * @q_coal: per queue coalesce settings
  * @ec: coalesce settings to program the device with
  * @q_num: update ITR/INTRL (coalesce) settings for this queue number/index
  * @is_rxq: is queue type rx
@@ -1171,6 +1483,7 @@ static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec,
  * Return 0 on success, and negative on failure
  */
 static int idpf_set_q_coalesce(const struct idpf_vport *vport,
+			       struct idpf_q_coalesce *q_coal,
 			       const struct ethtool_coalesce *ec,
 			       int q_num, bool is_rxq)
 {
@@ -1179,7 +1492,7 @@ static int idpf_set_q_coalesce(const struct idpf_vport *vport,
 	qv = is_rxq ? idpf_find_rxq_vec(vport, q_num) :
 		      idpf_find_txq_vec(vport, q_num);
 
-	if (qv && __idpf_set_q_coalesce(ec, qv, is_rxq))
+	if (qv && __idpf_set_q_coalesce(ec, q_coal, qv, is_rxq))
 		return -EINVAL;
 
 	return 0;
@@ -1200,23 +1513,29 @@ static int idpf_set_coalesce(struct net_device *netdev,
 			     struct netlink_ext_ack *extack)
 {
 	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	struct idpf_vport_user_config_data *user_config;
+	struct idpf_q_coalesce *q_coal;
 	struct idpf_vport *vport;
 	int i, err = 0;
 
+	user_config = &np->adapter->vport_config[np->vport_idx]->user_config;
+
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
 
-	if (np->state != __IDPF_VPORT_UP)
+	if (!test_bit(IDPF_VPORT_UP, np->state))
 		goto unlock_mutex;
 
 	for (i = 0; i < vport->num_txq; i++) {
-		err = idpf_set_q_coalesce(vport, ec, i, false);
+		q_coal = &user_config->q_coalesce[i];
+		err = idpf_set_q_coalesce(vport, q_coal, ec, i, false);
 		if (err)
 			goto unlock_mutex;
 	}
 
 	for (i = 0; i < vport->num_rxq; i++) {
-		err = idpf_set_q_coalesce(vport, ec, i, true);
+		q_coal = &user_config->q_coalesce[i];
+		err = idpf_set_q_coalesce(vport, q_coal, ec, i, true);
 		if (err)
 			goto unlock_mutex;
 	}
@@ -1238,20 +1557,25 @@ unlock_mutex:
 static int idpf_set_per_q_coalesce(struct net_device *netdev, u32 q_num,
 				   struct ethtool_coalesce *ec)
 {
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	struct idpf_vport_user_config_data *user_config;
+	struct idpf_q_coalesce *q_coal;
 	struct idpf_vport *vport;
 	int err;
 
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
+	user_config = &np->adapter->vport_config[np->vport_idx]->user_config;
+	q_coal = &user_config->q_coalesce[q_num];
 
-	err = idpf_set_q_coalesce(vport, ec, q_num, false);
+	err = idpf_set_q_coalesce(vport, q_coal, ec, q_num, false);
 	if (err) {
 		idpf_vport_ctrl_unlock(netdev);
 
 		return err;
 	}
 
-	err = idpf_set_q_coalesce(vport, ec, q_num, true);
+	err = idpf_set_q_coalesce(vport, q_coal, ec, q_num, true);
 
 	idpf_vport_ctrl_unlock(netdev);
 
@@ -1312,6 +1636,126 @@ static int idpf_get_link_ksettings(struct net_device *netdev,
 	return 0;
 }
 
+/**
+ * idpf_get_timestamp_filters - Get the supported timestamping mode
+ * @vport: Virtual port structure
+ * @info: ethtool timestamping info structure
+ *
+ * Get the Tx/Rx timestamp filters.
+ */
+static void idpf_get_timestamp_filters(const struct idpf_vport *vport,
+				       struct kernel_ethtool_ts_info *info)
+{
+	info->so_timestamping = SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	info->tx_types = BIT(HWTSTAMP_TX_OFF);
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL);
+
+	if (!vport->tx_tstamp_caps ||
+	    vport->adapter->ptp->tx_tstamp_access == IDPF_PTP_NONE)
+		return;
+
+	info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
+				 SOF_TIMESTAMPING_TX_HARDWARE;
+
+	info->tx_types |= BIT(HWTSTAMP_TX_ON);
+}
+
+/**
+ * idpf_get_ts_info - Get device PHC association
+ * @netdev: network interface device structure
+ * @info: ethtool timestamping info structure
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_get_ts_info(struct net_device *netdev,
+			    struct kernel_ethtool_ts_info *info)
+{
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	struct idpf_vport *vport;
+	int err = 0;
+
+	if (!mutex_trylock(&np->adapter->vport_ctrl_lock))
+		return -EBUSY;
+
+	vport = idpf_netdev_to_vport(netdev);
+
+	if (!vport->adapter->ptp) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	if (idpf_is_cap_ena(vport->adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_PTP) &&
+	    vport->adapter->ptp->clock) {
+		info->phc_index = ptp_clock_index(vport->adapter->ptp->clock);
+		idpf_get_timestamp_filters(vport, info);
+	} else {
+		pci_dbg(vport->adapter->pdev, "PTP clock not detected\n");
+		err = ethtool_op_get_ts_info(netdev, info);
+	}
+
+unlock:
+	mutex_unlock(&np->adapter->vport_ctrl_lock);
+
+	return err;
+}
+
+/**
+ * idpf_get_ts_stats - Collect HW tstamping statistics
+ * @netdev: network interface device structure
+ * @ts_stats: HW timestamping stats structure
+ *
+ * Collect HW timestamping statistics including successfully timestamped
+ * packets, discarded due to illegal values, flushed during releasing PTP and
+ * skipped due to lack of the free index.
+ */
+static void idpf_get_ts_stats(struct net_device *netdev,
+			      struct ethtool_ts_stats *ts_stats)
+{
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	struct idpf_vport *vport;
+	unsigned int start;
+
+	idpf_vport_ctrl_lock(netdev);
+	vport = idpf_netdev_to_vport(netdev);
+	do {
+		start = u64_stats_fetch_begin(&vport->tstamp_stats.stats_sync);
+		ts_stats->pkts = u64_stats_read(&vport->tstamp_stats.packets);
+		ts_stats->lost = u64_stats_read(&vport->tstamp_stats.flushed);
+		ts_stats->err = u64_stats_read(&vport->tstamp_stats.discarded);
+	} while (u64_stats_fetch_retry(&vport->tstamp_stats.stats_sync, start));
+
+	if (!test_bit(IDPF_VPORT_UP, np->state))
+		goto exit;
+
+	for (u16 i = 0; i < vport->num_txq_grp; i++) {
+		struct idpf_txq_group *txq_grp = &vport->txq_grps[i];
+
+		for (u16 j = 0; j < txq_grp->num_txq; j++) {
+			struct idpf_tx_queue *txq = txq_grp->txqs[j];
+			struct idpf_tx_queue_stats *stats;
+			u64 ts;
+
+			if (!txq)
+				continue;
+
+			stats = &txq->q_stats;
+			do {
+				start = u64_stats_fetch_begin(&txq->stats_sync);
+
+				ts = u64_stats_read(&stats->tstamp_skipped);
+			} while (u64_stats_fetch_retry(&txq->stats_sync,
+						       start));
+
+			ts_stats->lost += ts;
+		}
+	}
+
+exit:
+	idpf_vport_ctrl_unlock(netdev);
+}
+
 static const struct ethtool_ops idpf_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
@@ -1328,6 +1772,8 @@ static const struct ethtool_ops idpf_ethtool_ops = {
 	.get_sset_count		= idpf_get_sset_count,
 	.get_channels		= idpf_get_channels,
 	.get_rxnfc		= idpf_get_rxnfc,
+	.set_rxnfc		= idpf_set_rxnfc,
+	.get_rx_ring_count	= idpf_get_rx_ring_count,
 	.get_rxfh_key_size	= idpf_get_rxfh_key_size,
 	.get_rxfh_indir_size	= idpf_get_rxfh_indir_size,
 	.get_rxfh		= idpf_get_rxfh,
@@ -1336,6 +1782,8 @@ static const struct ethtool_ops idpf_ethtool_ops = {
 	.get_ringparam		= idpf_get_ringparam,
 	.set_ringparam		= idpf_set_ringparam,
 	.get_link_ksettings	= idpf_get_link_ksettings,
+	.get_ts_info		= idpf_get_ts_info,
+	.get_ts_stats		= idpf_get_ts_stats,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c
new file mode 100644
index 000000000000..7e20a07e98e5
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c
@@ -0,0 +1,503 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2025 Intel Corporation */
+
+#include <linux/export.h>
+
+#include "idpf.h"
+#include "idpf_virtchnl.h"
+
+static DEFINE_IDA(idpf_idc_ida);
+
+#define IDPF_IDC_MAX_ADEV_NAME_LEN	15
+
+/**
+ * idpf_idc_init - Called to initialize IDC
+ * @adapter: driver private data structure
+ *
+ * Return: 0 on success or cap not enabled, error code on failure.
+ */
+int idpf_idc_init(struct idpf_adapter *adapter)
+{
+	int err;
+
+	if (!idpf_is_rdma_cap_ena(adapter) ||
+	    !adapter->dev_ops.idc_init)
+		return 0;
+
+	err = adapter->dev_ops.idc_init(adapter);
+	if (err)
+		dev_err(&adapter->pdev->dev, "failed to initialize idc: %d\n",
+			err);
+
+	return err;
+}
+
+/**
+ * idpf_vport_adev_release - function to be mapped to aux dev's release op
+ * @dev: pointer to device to free
+ */
+static void idpf_vport_adev_release(struct device *dev)
+{
+	struct iidc_rdma_vport_auxiliary_dev *iadev;
+
+	iadev = container_of(dev, struct iidc_rdma_vport_auxiliary_dev, adev.dev);
+	kfree(iadev);
+	iadev = NULL;
+}
+
+/**
+ * idpf_plug_vport_aux_dev - allocate and register a vport Auxiliary device
+ * @cdev_info: IDC core device info pointer
+ * @vdev_info: IDC vport device info pointer
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_plug_vport_aux_dev(struct iidc_rdma_core_dev_info *cdev_info,
+				   struct iidc_rdma_vport_dev_info *vdev_info)
+{
+	struct iidc_rdma_vport_auxiliary_dev *iadev;
+	char name[IDPF_IDC_MAX_ADEV_NAME_LEN];
+	struct auxiliary_device *adev;
+	int ret;
+
+	iadev = kzalloc(sizeof(*iadev), GFP_KERNEL);
+	if (!iadev)
+		return -ENOMEM;
+
+	adev = &iadev->adev;
+	vdev_info->adev = &iadev->adev;
+	iadev->vdev_info = vdev_info;
+
+	ret = ida_alloc(&idpf_idc_ida, GFP_KERNEL);
+	if (ret < 0) {
+		pr_err("failed to allocate unique device ID for Auxiliary driver\n");
+		goto err_ida_alloc;
+	}
+	adev->id = ret;
+	adev->dev.release = idpf_vport_adev_release;
+	adev->dev.parent = &cdev_info->pdev->dev;
+	sprintf(name, "%04x.rdma.vdev", cdev_info->pdev->vendor);
+	adev->name = name;
+
+	ret = auxiliary_device_init(adev);
+	if (ret)
+		goto err_aux_dev_init;
+
+	ret = auxiliary_device_add(adev);
+	if (ret)
+		goto err_aux_dev_add;
+
+	return 0;
+
+err_aux_dev_add:
+	auxiliary_device_uninit(adev);
+err_aux_dev_init:
+	ida_free(&idpf_idc_ida, adev->id);
+err_ida_alloc:
+	vdev_info->adev = NULL;
+	kfree(iadev);
+
+	return ret;
+}
+
+/**
+ * idpf_idc_init_aux_vport_dev - initialize vport Auxiliary Device(s)
+ * @vport: virtual port data struct
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_idc_init_aux_vport_dev(struct idpf_vport *vport)
+{
+	struct idpf_adapter *adapter = vport->adapter;
+	struct iidc_rdma_vport_dev_info *vdev_info;
+	struct iidc_rdma_core_dev_info *cdev_info;
+	struct virtchnl2_create_vport *vport_msg;
+	int err;
+
+	vport_msg = (struct virtchnl2_create_vport *)
+			adapter->vport_params_recvd[vport->idx];
+
+	if (!(le16_to_cpu(vport_msg->vport_flags) & VIRTCHNL2_VPORT_ENABLE_RDMA))
+		return 0;
+
+	vport->vdev_info = kzalloc(sizeof(*vdev_info), GFP_KERNEL);
+	if (!vport->vdev_info)
+		return -ENOMEM;
+
+	cdev_info = vport->adapter->cdev_info;
+
+	vdev_info = vport->vdev_info;
+	vdev_info->vport_id = vport->vport_id;
+	vdev_info->netdev = vport->netdev;
+	vdev_info->core_adev = cdev_info->adev;
+
+	err = idpf_plug_vport_aux_dev(cdev_info, vdev_info);
+	if (err) {
+		vport->vdev_info = NULL;
+		kfree(vdev_info);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * idpf_idc_vdev_mtu_event - Function to handle IDC vport mtu change events
+ * @vdev_info: IDC vport device info pointer
+ * @event_type: type of event to pass to handler
+ */
+void idpf_idc_vdev_mtu_event(struct iidc_rdma_vport_dev_info *vdev_info,
+			     enum iidc_rdma_event_type event_type)
+{
+	struct iidc_rdma_vport_auxiliary_drv *iadrv;
+	struct iidc_rdma_event event = { };
+	struct auxiliary_device *adev;
+
+	if (!vdev_info)
+		/* RDMA is not enabled */
+		return;
+
+	set_bit(event_type, event.type);
+
+	device_lock(&vdev_info->adev->dev);
+	adev = vdev_info->adev;
+	if (!adev || !adev->dev.driver)
+		goto unlock;
+	iadrv = container_of(adev->dev.driver,
+			     struct iidc_rdma_vport_auxiliary_drv,
+			     adrv.driver);
+	if (iadrv->event_handler)
+		iadrv->event_handler(vdev_info, &event);
+unlock:
+	device_unlock(&vdev_info->adev->dev);
+}
+
+/**
+ * idpf_core_adev_release - function to be mapped to aux dev's release op
+ * @dev: pointer to device to free
+ */
+static void idpf_core_adev_release(struct device *dev)
+{
+	struct iidc_rdma_core_auxiliary_dev *iadev;
+
+	iadev = container_of(dev, struct iidc_rdma_core_auxiliary_dev, adev.dev);
+	kfree(iadev);
+	iadev = NULL;
+}
+
+/**
+ * idpf_plug_core_aux_dev - allocate and register an Auxiliary device
+ * @cdev_info: IDC core device info pointer
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_plug_core_aux_dev(struct iidc_rdma_core_dev_info *cdev_info)
+{
+	struct iidc_rdma_core_auxiliary_dev *iadev;
+	char name[IDPF_IDC_MAX_ADEV_NAME_LEN];
+	struct auxiliary_device *adev;
+	int ret;
+
+	iadev = kzalloc(sizeof(*iadev), GFP_KERNEL);
+	if (!iadev)
+		return -ENOMEM;
+
+	adev = &iadev->adev;
+	cdev_info->adev = adev;
+	iadev->cdev_info = cdev_info;
+
+	ret = ida_alloc(&idpf_idc_ida, GFP_KERNEL);
+	if (ret < 0) {
+		pr_err("failed to allocate unique device ID for Auxiliary driver\n");
+		goto err_ida_alloc;
+	}
+	adev->id = ret;
+	adev->dev.release = idpf_core_adev_release;
+	adev->dev.parent = &cdev_info->pdev->dev;
+	sprintf(name, "%04x.rdma.core", cdev_info->pdev->vendor);
+	adev->name = name;
+
+	ret = auxiliary_device_init(adev);
+	if (ret)
+		goto err_aux_dev_init;
+
+	ret = auxiliary_device_add(adev);
+	if (ret)
+		goto err_aux_dev_add;
+
+	return 0;
+
+err_aux_dev_add:
+	auxiliary_device_uninit(adev);
+err_aux_dev_init:
+	ida_free(&idpf_idc_ida, adev->id);
+err_ida_alloc:
+	cdev_info->adev = NULL;
+	kfree(iadev);
+
+	return ret;
+}
+
+/**
+ * idpf_unplug_aux_dev - unregister and free an Auxiliary device
+ * @adev: auxiliary device struct
+ */
+static void idpf_unplug_aux_dev(struct auxiliary_device *adev)
+{
+	if (!adev)
+		return;
+
+	ida_free(&idpf_idc_ida, adev->id);
+
+	auxiliary_device_delete(adev);
+	auxiliary_device_uninit(adev);
+}
+
+/**
+ * idpf_idc_issue_reset_event - Function to handle reset IDC event
+ * @cdev_info: IDC core device info pointer
+ */
+void idpf_idc_issue_reset_event(struct iidc_rdma_core_dev_info *cdev_info)
+{
+	enum iidc_rdma_event_type event_type = IIDC_RDMA_EVENT_WARN_RESET;
+	struct iidc_rdma_core_auxiliary_drv *iadrv;
+	struct iidc_rdma_event event = { };
+	struct auxiliary_device *adev;
+
+	if (!cdev_info)
+		/* RDMA is not enabled */
+		return;
+
+	set_bit(event_type, event.type);
+
+	device_lock(&cdev_info->adev->dev);
+
+	adev = cdev_info->adev;
+	if (!adev || !adev->dev.driver)
+		goto unlock;
+
+	iadrv = container_of(adev->dev.driver,
+			     struct iidc_rdma_core_auxiliary_drv,
+			     adrv.driver);
+	if (iadrv->event_handler)
+		iadrv->event_handler(cdev_info, &event);
+unlock:
+	device_unlock(&cdev_info->adev->dev);
+}
+
+/**
+ * idpf_idc_vport_dev_up - called when CORE is ready for vport aux devs
+ * @adapter: private data struct
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_idc_vport_dev_up(struct idpf_adapter *adapter)
+{
+	int i, err = 0;
+
+	for (i = 0; i < adapter->num_alloc_vports; i++) {
+		struct idpf_vport *vport = adapter->vports[i];
+
+		if (!vport)
+			continue;
+
+		if (!vport->vdev_info)
+			err = idpf_idc_init_aux_vport_dev(vport);
+		else
+			err = idpf_plug_vport_aux_dev(vport->adapter->cdev_info,
+						      vport->vdev_info);
+	}
+
+	return err;
+}
+
+/**
+ * idpf_idc_vport_dev_down - called CORE is leaving vport aux dev support state
+ * @adapter: private data struct
+ */
+static void idpf_idc_vport_dev_down(struct idpf_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_alloc_vports; i++) {
+		struct idpf_vport *vport = adapter->vports[i];
+
+		if (!vport)
+			continue;
+
+		idpf_unplug_aux_dev(vport->vdev_info->adev);
+		vport->vdev_info->adev = NULL;
+	}
+}
+
+/**
+ * idpf_idc_vport_dev_ctrl - Called by an Auxiliary Driver
+ * @cdev_info: IDC core device info pointer
+ * @up: RDMA core driver status
+ *
+ * This callback function is accessed by an Auxiliary Driver to indicate
+ * whether core driver is ready to support vport driver load or if vport
+ * drivers need to be taken down.
+ *
+ * Return: 0 on success or error code on failure.
+ */
+int idpf_idc_vport_dev_ctrl(struct iidc_rdma_core_dev_info *cdev_info, bool up)
+{
+	struct idpf_adapter *adapter = pci_get_drvdata(cdev_info->pdev);
+
+	if (up)
+		return idpf_idc_vport_dev_up(adapter);
+
+	idpf_idc_vport_dev_down(adapter);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(idpf_idc_vport_dev_ctrl);
+
+/**
+ * idpf_idc_request_reset - Called by an Auxiliary Driver
+ * @cdev_info: IDC core device info pointer
+ * @reset_type: function, core or other
+ *
+ * This callback function is accessed by an Auxiliary Driver to request a reset
+ * on the Auxiliary Device.
+ *
+ * Return: 0 on success or error code on failure.
+ */
+int idpf_idc_request_reset(struct iidc_rdma_core_dev_info *cdev_info,
+			   enum iidc_rdma_reset_type __always_unused reset_type)
+{
+	struct idpf_adapter *adapter = pci_get_drvdata(cdev_info->pdev);
+
+	if (!idpf_is_reset_in_prog(adapter)) {
+		set_bit(IDPF_HR_FUNC_RESET, adapter->flags);
+		queue_delayed_work(adapter->vc_event_wq,
+				   &adapter->vc_event_task,
+				   msecs_to_jiffies(10));
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(idpf_idc_request_reset);
+
+/**
+ * idpf_idc_init_msix_data - initialize MSIX data for the cdev_info structure
+ * @adapter: driver private data structure
+ */
+static void
+idpf_idc_init_msix_data(struct idpf_adapter *adapter)
+{
+	struct iidc_rdma_core_dev_info *cdev_info;
+	struct iidc_rdma_priv_dev_info *privd;
+
+	if (!adapter->rdma_msix_entries)
+		return;
+
+	cdev_info = adapter->cdev_info;
+	privd = cdev_info->iidc_priv;
+
+	privd->msix_entries = adapter->rdma_msix_entries;
+	privd->msix_count = adapter->num_rdma_msix_entries;
+}
+
+/**
+ * idpf_idc_init_aux_core_dev - initialize Auxiliary Device(s)
+ * @adapter: driver private data structure
+ * @ftype: PF or VF
+ *
+ * Return: 0 on success or error code on failure.
+ */
+int idpf_idc_init_aux_core_dev(struct idpf_adapter *adapter,
+			       enum iidc_function_type ftype)
+{
+	struct iidc_rdma_core_dev_info *cdev_info;
+	struct iidc_rdma_priv_dev_info *privd;
+	int err, i;
+
+	adapter->cdev_info = kzalloc(sizeof(*cdev_info), GFP_KERNEL);
+	if (!adapter->cdev_info)
+		return -ENOMEM;
+	cdev_info = adapter->cdev_info;
+
+	privd = kzalloc(sizeof(*privd), GFP_KERNEL);
+	if (!privd) {
+		err = -ENOMEM;
+		goto err_privd_alloc;
+	}
+
+	cdev_info->iidc_priv = privd;
+	cdev_info->pdev = adapter->pdev;
+	cdev_info->rdma_protocol = IIDC_RDMA_PROTOCOL_ROCEV2;
+	privd->ftype = ftype;
+
+	privd->mapped_mem_regions =
+		kcalloc(adapter->hw.num_lan_regs,
+			sizeof(struct iidc_rdma_lan_mapped_mem_region),
+			GFP_KERNEL);
+	if (!privd->mapped_mem_regions) {
+		err = -ENOMEM;
+		goto err_plug_aux_dev;
+	}
+
+	privd->num_memory_regions = cpu_to_le16(adapter->hw.num_lan_regs);
+	for (i = 0; i < adapter->hw.num_lan_regs; i++) {
+		privd->mapped_mem_regions[i].region_addr =
+			adapter->hw.lan_regs[i].vaddr;
+		privd->mapped_mem_regions[i].size =
+			cpu_to_le64(adapter->hw.lan_regs[i].addr_len);
+		privd->mapped_mem_regions[i].start_offset =
+			cpu_to_le64(adapter->hw.lan_regs[i].addr_start);
+	}
+
+	idpf_idc_init_msix_data(adapter);
+
+	err = idpf_plug_core_aux_dev(cdev_info);
+	if (err)
+		goto err_free_mem_regions;
+
+	return 0;
+
+err_free_mem_regions:
+	kfree(privd->mapped_mem_regions);
+	privd->mapped_mem_regions = NULL;
+err_plug_aux_dev:
+	kfree(privd);
+err_privd_alloc:
+	kfree(cdev_info);
+	adapter->cdev_info = NULL;
+
+	return err;
+}
+
+/**
+ * idpf_idc_deinit_core_aux_device - de-initialize Auxiliary Device(s)
+ * @cdev_info: IDC core device info pointer
+ */
+void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info)
+{
+	struct iidc_rdma_priv_dev_info *privd;
+
+	if (!cdev_info)
+		return;
+
+	idpf_unplug_aux_dev(cdev_info->adev);
+
+	privd = cdev_info->iidc_priv;
+	kfree(privd->mapped_mem_regions);
+	kfree(privd);
+	kfree(cdev_info);
+}
+
+/**
+ * idpf_idc_deinit_vport_aux_device - de-initialize Auxiliary Device(s)
+ * @vdev_info: IDC vport device info pointer
+ */
+void idpf_idc_deinit_vport_aux_device(struct iidc_rdma_vport_dev_info *vdev_info)
+{
+	if (!vdev_info)
+		return;
+
+	idpf_unplug_aux_dev(vdev_info->adev);
+
+	kfree(vdev_info);
+}
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h b/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h
index 24edb8a6ec2e..cc9aa2b6a14a 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h
@@ -53,6 +53,10 @@
 #define PF_FW_ATQH_ATQH_M		GENMASK(9, 0)
 #define PF_FW_ATQT			(PF_FW_BASE + 0x24)
 
+/* Timesync registers */
+#define PF_GLTSYN_CMD_SYNC_EXEC_CMD_M	GENMASK(1, 0)
+#define PF_GLTSYN_CMD_SYNC_SHTIME_EN_M	BIT(2)
+
 /* Interrupts */
 #define PF_GLINT_BASE			0x08900000
 #define PF_GLINT_DYN_CTL(_INT)		(PF_GLINT_BASE + ((_INT) * 0x1000))
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
index 8c7f8ef8f1a1..20d5af64e750 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
@@ -186,13 +186,17 @@ struct idpf_base_tx_desc {
 	__le64 qw1; /* type_cmd_offset_bsz_l2tag1 */
 }; /* read used with buffer queues */
 
-struct idpf_splitq_tx_compl_desc {
+struct idpf_splitq_4b_tx_compl_desc {
 	/* qid=[10:0] comptype=[13:11] rsvd=[14] gen=[15] */
 	__le16 qid_comptype_gen;
 	union {
 		__le16 q_head; /* Queue head */
 		__le16 compl_tag; /* Completion tag */
 	} q_head_compl_tag;
+}; /* writeback used with completion queues */
+
+struct idpf_splitq_tx_compl_desc {
+	struct idpf_splitq_4b_tx_compl_desc common;
 	u8 ts[3];
 	u8 rsvd; /* Reserved */
 }; /* writeback used with completion queues */
@@ -282,7 +286,18 @@ struct idpf_flex_tx_tso_ctx_qw {
 	u8 flex;
 };
 
-struct idpf_flex_tx_ctx_desc {
+union idpf_flex_tx_ctx_desc {
+	/* DTYPE = IDPF_TX_DESC_DTYPE_CTX (0x01) */
+	struct {
+		__le64 qw0;
+#define IDPF_TX_CTX_L2TAG2_M	GENMASK_ULL(47, 32)
+		__le64 qw1;
+#define IDPF_TX_CTX_DTYPE_M	GENMASK_ULL(3, 0)
+#define IDPF_TX_CTX_CMD_M	GENMASK_ULL(15, 4)
+#define IDPF_TX_CTX_TSYN_REG_M	GENMASK_ULL(47, 30)
+#define IDPF_TX_CTX_MSS_M	GENMASK_ULL(50, 63)
+	} tsyn;
+
 	/* DTYPE = IDPF_TX_DESC_DTYPE_FLEX_TSO_CTX (0x05) */
 	struct {
 		struct idpf_flex_tx_tso_ctx_qw qw0;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index b4fbb99bfad2..7a7e101afeb6 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -3,6 +3,9 @@
 
 #include "idpf.h"
 #include "idpf_virtchnl.h"
+#include "idpf_ptp.h"
+#include "xdp.h"
+#include "xsk.h"
 
 static const struct net_device_ops idpf_netdev_ops;
 
@@ -87,6 +90,8 @@ void idpf_intr_rel(struct idpf_adapter *adapter)
 	idpf_deinit_vector_stack(adapter);
 	kfree(adapter->msix_entries);
 	adapter->msix_entries = NULL;
+	kfree(adapter->rdma_msix_entries);
+	adapter->rdma_msix_entries = NULL;
 }
 
 /**
@@ -144,22 +149,6 @@ static int idpf_mb_intr_req_irq(struct idpf_adapter *adapter)
 }
 
 /**
- * idpf_set_mb_vec_id - Set vector index for mailbox
- * @adapter: adapter structure to access the vector chunks
- *
- * The first vector id in the requested vector chunks from the CP is for
- * the mailbox
- */
-static void idpf_set_mb_vec_id(struct idpf_adapter *adapter)
-{
-	if (adapter->req_vec_chunks)
-		adapter->mb_vector.v_idx =
-			le16_to_cpu(adapter->caps.mailbox_vector_id);
-	else
-		adapter->mb_vector.v_idx = 0;
-}
-
-/**
  * idpf_mb_intr_init - Initialize the mailbox interrupt
  * @adapter: adapter structure to store the mailbox vector
  */
@@ -314,13 +303,33 @@ rel_lock:
  */
 int idpf_intr_req(struct idpf_adapter *adapter)
 {
+	u16 num_lan_vecs, min_lan_vecs, num_rdma_vecs = 0, min_rdma_vecs = 0;
 	u16 default_vports = idpf_get_default_vports(adapter);
 	int num_q_vecs, total_vecs, num_vec_ids;
-	int min_vectors, v_actual, err;
+	int min_vectors, actual_vecs, err;
 	unsigned int vector;
 	u16 *vecids;
+	int i;
 
 	total_vecs = idpf_get_reserved_vecs(adapter);
+	num_lan_vecs = total_vecs;
+	if (idpf_is_rdma_cap_ena(adapter)) {
+		num_rdma_vecs = idpf_get_reserved_rdma_vecs(adapter);
+		min_rdma_vecs = IDPF_MIN_RDMA_VEC;
+
+		if (!num_rdma_vecs) {
+			/* If idpf_get_reserved_rdma_vecs is 0, vectors are
+			 * pulled from the LAN pool.
+			 */
+			num_rdma_vecs = min_rdma_vecs;
+		} else if (num_rdma_vecs < min_rdma_vecs) {
+			dev_err(&adapter->pdev->dev,
+				"Not enough vectors reserved for RDMA (min: %u, current: %u)\n",
+				min_rdma_vecs, num_rdma_vecs);
+			return -EINVAL;
+		}
+	}
+
 	num_q_vecs = total_vecs - IDPF_MBX_Q_VEC;
 
 	err = idpf_send_alloc_vectors_msg(adapter, num_q_vecs);
@@ -331,52 +340,76 @@ int idpf_intr_req(struct idpf_adapter *adapter)
 		return -EAGAIN;
 	}
 
-	min_vectors = IDPF_MBX_Q_VEC + IDPF_MIN_Q_VEC * default_vports;
-	v_actual = pci_alloc_irq_vectors(adapter->pdev, min_vectors,
-					 total_vecs, PCI_IRQ_MSIX);
-	if (v_actual < min_vectors) {
-		dev_err(&adapter->pdev->dev, "Failed to allocate MSIX vectors: %d\n",
-			v_actual);
-		err = -EAGAIN;
+	min_lan_vecs = IDPF_MBX_Q_VEC + IDPF_MIN_Q_VEC * default_vports;
+	min_vectors = min_lan_vecs + min_rdma_vecs;
+	actual_vecs = pci_alloc_irq_vectors(adapter->pdev, min_vectors,
+					    total_vecs, PCI_IRQ_MSIX);
+	if (actual_vecs < 0) {
+		dev_err(&adapter->pdev->dev, "Failed to allocate minimum MSIX vectors required: %d\n",
+			min_vectors);
+		err = actual_vecs;
 		goto send_dealloc_vecs;
 	}
 
-	adapter->msix_entries = kcalloc(v_actual, sizeof(struct msix_entry),
-					GFP_KERNEL);
+	if (idpf_is_rdma_cap_ena(adapter)) {
+		if (actual_vecs < total_vecs) {
+			dev_warn(&adapter->pdev->dev,
+				 "Warning: %d vectors requested, only %d available. Defaulting to minimum (%d) for RDMA and remaining for LAN.\n",
+				 total_vecs, actual_vecs, IDPF_MIN_RDMA_VEC);
+			num_rdma_vecs = IDPF_MIN_RDMA_VEC;
+		}
+
+		adapter->rdma_msix_entries = kcalloc(num_rdma_vecs,
+						     sizeof(struct msix_entry),
+						     GFP_KERNEL);
+		if (!adapter->rdma_msix_entries) {
+			err = -ENOMEM;
+			goto free_irq;
+		}
+	}
 
+	num_lan_vecs = actual_vecs - num_rdma_vecs;
+	adapter->msix_entries = kcalloc(num_lan_vecs, sizeof(struct msix_entry),
+					GFP_KERNEL);
 	if (!adapter->msix_entries) {
 		err = -ENOMEM;
-		goto free_irq;
+		goto free_rdma_msix;
 	}
 
-	idpf_set_mb_vec_id(adapter);
+	adapter->mb_vector.v_idx = le16_to_cpu(adapter->caps.mailbox_vector_id);
 
-	vecids = kcalloc(total_vecs, sizeof(u16), GFP_KERNEL);
+	vecids = kcalloc(actual_vecs, sizeof(u16), GFP_KERNEL);
 	if (!vecids) {
 		err = -ENOMEM;
 		goto free_msix;
 	}
 
-	num_vec_ids = idpf_get_vec_ids(adapter, vecids, total_vecs,
+	num_vec_ids = idpf_get_vec_ids(adapter, vecids, actual_vecs,
 				       &adapter->req_vec_chunks->vchunks);
-	if (num_vec_ids < v_actual) {
+	if (num_vec_ids < actual_vecs) {
 		err = -EINVAL;
 		goto free_vecids;
 	}
 
-	for (vector = 0; vector < v_actual; vector++) {
+	for (vector = 0; vector < num_lan_vecs; vector++) {
 		adapter->msix_entries[vector].entry = vecids[vector];
 		adapter->msix_entries[vector].vector =
 			pci_irq_vector(adapter->pdev, vector);
 	}
+	for (i = 0; i < num_rdma_vecs; vector++, i++) {
+		adapter->rdma_msix_entries[i].entry = vecids[vector];
+		adapter->rdma_msix_entries[i].vector =
+			pci_irq_vector(adapter->pdev, vector);
+	}
 
-	adapter->num_req_msix = total_vecs;
-	adapter->num_msix_entries = v_actual;
 	/* 'num_avail_msix' is used to distribute excess vectors to the vports
 	 * after considering the minimum vectors required per each default
 	 * vport
 	 */
-	adapter->num_avail_msix = v_actual - min_vectors;
+	adapter->num_avail_msix = num_lan_vecs - min_lan_vecs;
+	adapter->num_msix_entries = num_lan_vecs;
+	if (idpf_is_rdma_cap_ena(adapter))
+		adapter->num_rdma_msix_entries = num_rdma_vecs;
 
 	/* Fill MSIX vector lifo stack with vector indexes */
 	err = idpf_init_vector_stack(adapter);
@@ -398,6 +431,9 @@ free_vecids:
 free_msix:
 	kfree(adapter->msix_entries);
 	adapter->msix_entries = NULL;
+free_rdma_msix:
+	kfree(adapter->rdma_msix_entries);
+	adapter->rdma_msix_entries = NULL;
 free_irq:
 	pci_free_irq_vectors(adapter->pdev);
 send_dealloc_vecs:
@@ -483,7 +519,7 @@ static int idpf_del_mac_filter(struct idpf_vport *vport,
 	}
 	spin_unlock_bh(&vport_config->mac_filter_list_lock);
 
-	if (np->state == __IDPF_VPORT_UP) {
+	if (test_bit(IDPF_VPORT_UP, np->state)) {
 		int err;
 
 		err = idpf_add_del_mac_filters(vport, np, false, async);
@@ -554,7 +590,7 @@ static int idpf_add_mac_filter(struct idpf_vport *vport,
 	if (err)
 		return err;
 
-	if (np->state == __IDPF_VPORT_UP)
+	if (test_bit(IDPF_VPORT_UP, np->state))
 		err = idpf_add_del_mac_filters(vport, np, true, async);
 
 	return err;
@@ -703,8 +739,10 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 {
 	struct idpf_adapter *adapter = vport->adapter;
 	struct idpf_vport_config *vport_config;
+	netdev_features_t other_offloads = 0;
+	netdev_features_t csum_offloads = 0;
+	netdev_features_t tso_offloads = 0;
 	netdev_features_t dflt_features;
-	netdev_features_t offloads = 0;
 	struct idpf_netdev_priv *np;
 	struct net_device *netdev;
 	u16 idx = vport->idx;
@@ -721,6 +759,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 		np->vport = vport;
 		np->vport_idx = vport->idx;
 		np->vport_id = vport->vport_id;
+		np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter);
 		vport->netdev = netdev;
 
 		return idpf_init_mac_addr(vport, netdev);
@@ -738,6 +777,8 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 	np->adapter = adapter;
 	np->vport_idx = vport->idx;
 	np->vport_id = vport->vport_id;
+	np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter);
+	np->tx_max_bufs = idpf_get_max_tx_bufs(adapter);
 
 	spin_lock_init(&np->stats_lock);
 
@@ -766,54 +807,40 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 
 	if (idpf_is_cap_ena_all(adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
 		dflt_features |= NETIF_F_RXHASH;
-	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V4))
-		dflt_features |= NETIF_F_IP_CSUM;
-	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V6))
-		dflt_features |= NETIF_F_IPV6_CSUM;
+	if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS,
+			    VIRTCHNL2_CAP_FLOW_STEER) &&
+	    idpf_vport_is_cap_ena(vport, VIRTCHNL2_VPORT_SIDEBAND_FLOW_STEER))
+		dflt_features |= NETIF_F_NTUPLE;
+	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V4))
+		csum_offloads |= NETIF_F_IP_CSUM;
+	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V6))
+		csum_offloads |= NETIF_F_IPV6_CSUM;
 	if (idpf_is_cap_ena(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM))
-		dflt_features |= NETIF_F_RXCSUM;
-	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_SCTP_CSUM))
-		dflt_features |= NETIF_F_SCTP_CRC;
+		csum_offloads |= NETIF_F_RXCSUM;
+	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_SCTP_CSUM))
+		csum_offloads |= NETIF_F_SCTP_CRC;
 
 	if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV4_TCP))
-		dflt_features |= NETIF_F_TSO;
+		tso_offloads |= NETIF_F_TSO;
 	if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV6_TCP))
-		dflt_features |= NETIF_F_TSO6;
+		tso_offloads |= NETIF_F_TSO6;
 	if (idpf_is_cap_ena_all(adapter, IDPF_SEG_CAPS,
 				VIRTCHNL2_CAP_SEG_IPV4_UDP |
 				VIRTCHNL2_CAP_SEG_IPV6_UDP))
-		dflt_features |= NETIF_F_GSO_UDP_L4;
+		tso_offloads |= NETIF_F_GSO_UDP_L4;
 	if (idpf_is_cap_ena_all(adapter, IDPF_RSC_CAPS, IDPF_CAP_RSC))
-		offloads |= NETIF_F_GRO_HW;
-	/* advertise to stack only if offloads for encapsulated packets is
-	 * supported
-	 */
-	if (idpf_is_cap_ena(vport->adapter, IDPF_SEG_CAPS,
-			    VIRTCHNL2_CAP_SEG_TX_SINGLE_TUNNEL)) {
-		offloads |= NETIF_F_GSO_UDP_TUNNEL	|
-			    NETIF_F_GSO_GRE		|
-			    NETIF_F_GSO_GRE_CSUM	|
-			    NETIF_F_GSO_PARTIAL		|
-			    NETIF_F_GSO_UDP_TUNNEL_CSUM	|
-			    NETIF_F_GSO_IPXIP4		|
-			    NETIF_F_GSO_IPXIP6		|
-			    0;
-
-		if (!idpf_is_cap_ena_all(vport->adapter, IDPF_CSUM_CAPS,
-					 IDPF_CAP_TUNNEL_TX_CSUM))
-			netdev->gso_partial_features |=
-				NETIF_F_GSO_UDP_TUNNEL_CSUM;
-
-		netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
-		offloads |= NETIF_F_TSO_MANGLEID;
-	}
+		other_offloads |= NETIF_F_GRO_HW;
 	if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_LOOPBACK))
-		offloads |= NETIF_F_LOOPBACK;
+		other_offloads |= NETIF_F_LOOPBACK;
+
+	netdev->features |= dflt_features | csum_offloads | tso_offloads;
+	netdev->hw_features |=  netdev->features | other_offloads;
+	netdev->vlan_features |= netdev->features | other_offloads;
+	netdev->hw_enc_features |= dflt_features | other_offloads;
+	idpf_xdp_set_features(vport);
 
-	netdev->features |= dflt_features;
-	netdev->hw_features |= dflt_features | offloads;
-	netdev->hw_enc_features |= dflt_features | offloads;
 	idpf_set_ethtool_ops(netdev);
+	netif_set_affinity_auto(netdev);
 	SET_NETDEV_DEV(netdev, &adapter->pdev->dev);
 
 	/* carrier off on init to avoid Tx hangs */
@@ -861,14 +888,18 @@ static void idpf_remove_features(struct idpf_vport *vport)
 /**
  * idpf_vport_stop - Disable a vport
  * @vport: vport to disable
+ * @rtnl: whether to take RTNL lock
  */
-static void idpf_vport_stop(struct idpf_vport *vport)
+static void idpf_vport_stop(struct idpf_vport *vport, bool rtnl)
 {
 	struct idpf_netdev_priv *np = netdev_priv(vport->netdev);
 
-	if (np->state <= __IDPF_VPORT_DOWN)
+	if (!test_bit(IDPF_VPORT_UP, np->state))
 		return;
 
+	if (rtnl)
+		rtnl_lock();
+
 	netif_carrier_off(vport->netdev);
 	netif_tx_disable(vport->netdev);
 
@@ -887,9 +918,13 @@ static void idpf_vport_stop(struct idpf_vport *vport)
 
 	vport->link_up = false;
 	idpf_vport_intr_deinit(vport);
+	idpf_xdp_rxq_info_deinit_all(vport);
 	idpf_vport_queues_rel(vport);
 	idpf_vport_intr_rel(vport);
-	np->state = __IDPF_VPORT_DOWN;
+	clear_bit(IDPF_VPORT_UP, np->state);
+
+	if (rtnl)
+		rtnl_unlock();
 }
 
 /**
@@ -913,7 +948,7 @@ static int idpf_stop(struct net_device *netdev)
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
 
-	idpf_vport_stop(vport);
+	idpf_vport_stop(vport, false);
 
 	idpf_vport_ctrl_unlock(netdev);
 
@@ -927,15 +962,19 @@ static int idpf_stop(struct net_device *netdev)
 static void idpf_decfg_netdev(struct idpf_vport *vport)
 {
 	struct idpf_adapter *adapter = vport->adapter;
+	u16 idx = vport->idx;
 
 	kfree(vport->rx_ptype_lkup);
 	vport->rx_ptype_lkup = NULL;
 
-	unregister_netdev(vport->netdev);
-	free_netdev(vport->netdev);
+	if (test_and_clear_bit(IDPF_VPORT_REG_NETDEV,
+			       adapter->vport_config[idx]->flags)) {
+		unregister_netdev(vport->netdev);
+		free_netdev(vport->netdev);
+	}
 	vport->netdev = NULL;
 
-	adapter->netdevs[vport->idx] = NULL;
+	adapter->netdevs[idx] = NULL;
 }
 
 /**
@@ -999,8 +1038,10 @@ static void idpf_vport_dealloc(struct idpf_vport *vport)
 	struct idpf_adapter *adapter = vport->adapter;
 	unsigned int i = vport->idx;
 
+	idpf_idc_deinit_vport_aux_device(vport->vdev_info);
+
 	idpf_deinit_mac_addr(vport);
-	idpf_vport_stop(vport);
+	idpf_vport_stop(vport, true);
 
 	if (!test_bit(IDPF_HR_RESET_IN_PROG, adapter->flags))
 		idpf_decfg_netdev(vport);
@@ -1106,8 +1147,10 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 	if (!vport)
 		return vport;
 
+	num_max_q = max(max_q->max_txq, max_q->max_rxq) + IDPF_RESERVED_VECS;
 	if (!adapter->vport_config[idx]) {
 		struct idpf_vport_config *vport_config;
+		struct idpf_q_coalesce *q_coal;
 
 		vport_config = kzalloc(sizeof(*vport_config), GFP_KERNEL);
 		if (!vport_config) {
@@ -1116,6 +1159,21 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 			return NULL;
 		}
 
+		q_coal = kcalloc(num_max_q, sizeof(*q_coal), GFP_KERNEL);
+		if (!q_coal) {
+			kfree(vport_config);
+			kfree(vport);
+
+			return NULL;
+		}
+		for (int i = 0; i < num_max_q; i++) {
+			q_coal[i].tx_intr_mode = IDPF_ITR_DYNAMIC;
+			q_coal[i].tx_coalesce_usecs = IDPF_ITR_TX_DEF;
+			q_coal[i].rx_intr_mode = IDPF_ITR_DYNAMIC;
+			q_coal[i].rx_coalesce_usecs = IDPF_ITR_RX_DEF;
+		}
+		vport_config->user_config.q_coalesce = q_coal;
+
 		adapter->vport_config[idx] = vport_config;
 	}
 
@@ -1125,13 +1183,10 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 	vport->default_vport = adapter->num_alloc_vports <
 			       idpf_get_default_vports(adapter);
 
-	num_max_q = max(max_q->max_txq, max_q->max_rxq);
 	vport->q_vector_idxs = kcalloc(num_max_q, sizeof(u16), GFP_KERNEL);
-	if (!vport->q_vector_idxs) {
-		kfree(vport);
+	if (!vport->q_vector_idxs)
+		goto free_vport;
 
-		return NULL;
-	}
 	idpf_vport_init(vport, max_q);
 
 	/* This alloc is done separate from the LUT because it's not strictly
@@ -1141,11 +1196,9 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 	 */
 	rss_data = &adapter->vport_config[idx]->user_config.rss_data;
 	rss_data->rss_key = kzalloc(rss_data->rss_key_size, GFP_KERNEL);
-	if (!rss_data->rss_key) {
-		kfree(vport);
+	if (!rss_data->rss_key)
+		goto free_vector_idxs;
 
-		return NULL;
-	}
 	/* Initialize default rss key */
 	netdev_rss_key_fill((void *)rss_data->rss_key, rss_data->rss_key_size);
 
@@ -1158,6 +1211,13 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 	adapter->next_vport = idpf_get_free_slot(adapter);
 
 	return vport;
+
+free_vector_idxs:
+	kfree(vport->q_vector_idxs);
+free_vport:
+	kfree(vport);
+
+	return NULL;
 }
 
 /**
@@ -1261,13 +1321,13 @@ static void idpf_restore_features(struct idpf_vport *vport)
  */
 static int idpf_set_real_num_queues(struct idpf_vport *vport)
 {
-	int err;
+	int err, txq = vport->num_txq - vport->num_xdp_txq;
 
 	err = netif_set_real_num_rx_queues(vport->netdev, vport->num_rxq);
 	if (err)
 		return err;
 
-	return netif_set_real_num_tx_queues(vport->netdev, vport->num_txq);
+	return netif_set_real_num_tx_queues(vport->netdev, txq);
 }
 
 /**
@@ -1285,7 +1345,7 @@ static int idpf_up_complete(struct idpf_vport *vport)
 		netif_tx_start_all_queues(vport->netdev);
 	}
 
-	np->state = __IDPF_VPORT_UP;
+	set_bit(IDPF_VPORT_UP, np->state);
 
 	return 0;
 }
@@ -1322,17 +1382,21 @@ static void idpf_rx_init_buf_tail(struct idpf_vport *vport)
 /**
  * idpf_vport_open - Bring up a vport
  * @vport: vport to bring up
+ * @rtnl: whether to take RTNL lock
  */
-static int idpf_vport_open(struct idpf_vport *vport)
+static int idpf_vport_open(struct idpf_vport *vport, bool rtnl)
 {
 	struct idpf_netdev_priv *np = netdev_priv(vport->netdev);
 	struct idpf_adapter *adapter = vport->adapter;
 	struct idpf_vport_config *vport_config;
 	int err;
 
-	if (np->state != __IDPF_VPORT_DOWN)
+	if (test_bit(IDPF_VPORT_UP, np->state))
 		return -EBUSY;
 
+	if (rtnl)
+		rtnl_lock();
+
 	/* we do not allow interface up just yet */
 	netif_carrier_off(vport->netdev);
 
@@ -1340,7 +1404,7 @@ static int idpf_vport_open(struct idpf_vport *vport)
 	if (err) {
 		dev_err(&adapter->pdev->dev, "Failed to allocate interrupts for vport %u: %d\n",
 			vport->vport_id, err);
-		return err;
+		goto err_rtnl_unlock;
 	}
 
 	err = idpf_vport_queues_alloc(vport);
@@ -1361,35 +1425,44 @@ static int idpf_vport_open(struct idpf_vport *vport)
 		goto queues_rel;
 	}
 
-	err = idpf_rx_bufs_init_all(vport);
+	err = idpf_queue_reg_init(vport);
 	if (err) {
-		dev_err(&adapter->pdev->dev, "Failed to initialize RX buffers for vport %u: %d\n",
+		dev_err(&adapter->pdev->dev, "Failed to initialize queue registers for vport %u: %d\n",
 			vport->vport_id, err);
 		goto queues_rel;
 	}
 
-	err = idpf_queue_reg_init(vport);
+	err = idpf_rx_bufs_init_all(vport);
 	if (err) {
-		dev_err(&adapter->pdev->dev, "Failed to initialize queue registers for vport %u: %d\n",
+		dev_err(&adapter->pdev->dev, "Failed to initialize RX buffers for vport %u: %d\n",
 			vport->vport_id, err);
 		goto queues_rel;
 	}
 
 	idpf_rx_init_buf_tail(vport);
+
+	err = idpf_xdp_rxq_info_init_all(vport);
+	if (err) {
+		netdev_err(vport->netdev,
+			   "Failed to initialize XDP RxQ info for vport %u: %pe\n",
+			   vport->vport_id, ERR_PTR(err));
+		goto intr_deinit;
+	}
+
 	idpf_vport_intr_ena(vport);
 
 	err = idpf_send_config_queues_msg(vport);
 	if (err) {
 		dev_err(&adapter->pdev->dev, "Failed to configure queues for vport %u, %d\n",
 			vport->vport_id, err);
-		goto intr_deinit;
+		goto rxq_deinit;
 	}
 
 	err = idpf_send_map_unmap_queue_vector_msg(vport, true);
 	if (err) {
 		dev_err(&adapter->pdev->dev, "Failed to map queue vectors for vport %u: %d\n",
 			vport->vport_id, err);
-		goto intr_deinit;
+		goto rxq_deinit;
 	}
 
 	err = idpf_send_enable_queues_msg(vport);
@@ -1427,6 +1500,9 @@ static int idpf_vport_open(struct idpf_vport *vport)
 		goto deinit_rss;
 	}
 
+	if (rtnl)
+		rtnl_unlock();
+
 	return 0;
 
 deinit_rss:
@@ -1437,6 +1513,8 @@ disable_queues:
 	idpf_send_disable_queues_msg(vport);
 unmap_queue_vectors:
 	idpf_send_map_unmap_queue_vector_msg(vport, false);
+rxq_deinit:
+	idpf_xdp_rxq_info_deinit_all(vport);
 intr_deinit:
 	idpf_vport_intr_deinit(vport);
 queues_rel:
@@ -1444,6 +1522,10 @@ queues_rel:
 intr_rel:
 	idpf_vport_intr_rel(vport);
 
+err_rtnl_unlock:
+	if (rtnl)
+		rtnl_unlock();
+
 	return err;
 }
 
@@ -1500,11 +1582,10 @@ void idpf_init_task(struct work_struct *work)
 	index = vport->idx;
 	vport_config = adapter->vport_config[index];
 
-	init_waitqueue_head(&vport->sw_marker_wq);
-
 	spin_lock_init(&vport_config->mac_filter_list_lock);
 
 	INIT_LIST_HEAD(&vport_config->user_config.mac_filter_list);
+	INIT_LIST_HEAD(&vport_config->user_config.flow_steer_list);
 
 	err = idpf_check_supported_desc_ids(vport);
 	if (err) {
@@ -1521,9 +1602,9 @@ void idpf_init_task(struct work_struct *work)
 
 	/* Once state is put into DOWN, driver is ready for dev_open */
 	np = netdev_priv(vport->netdev);
-	np->state = __IDPF_VPORT_DOWN;
+	clear_bit(IDPF_VPORT_UP, np->state);
 	if (test_and_clear_bit(IDPF_VPORT_UP_REQUESTED, vport_config->flags))
-		idpf_vport_open(vport);
+		idpf_vport_open(vport, true);
 
 	/* Spawn and return 'idpf_init_task' work queue until all the
 	 * default vports are created
@@ -1536,13 +1617,22 @@ void idpf_init_task(struct work_struct *work)
 	}
 
 	for (index = 0; index < adapter->max_vports; index++) {
-		if (adapter->netdevs[index] &&
-		    !test_bit(IDPF_VPORT_REG_NETDEV,
-			      adapter->vport_config[index]->flags)) {
-			register_netdev(adapter->netdevs[index]);
-			set_bit(IDPF_VPORT_REG_NETDEV,
-				adapter->vport_config[index]->flags);
+		struct net_device *netdev = adapter->netdevs[index];
+		struct idpf_vport_config *vport_config;
+
+		vport_config = adapter->vport_config[index];
+
+		if (!netdev ||
+		    test_bit(IDPF_VPORT_REG_NETDEV, vport_config->flags))
+			continue;
+
+		err = register_netdev(netdev);
+		if (err) {
+			dev_err(&pdev->dev, "failed to register netdev for vport %d: %pe\n",
+				index, ERR_PTR(err));
+			continue;
 		}
+		set_bit(IDPF_VPORT_REG_NETDEV, vport_config->flags);
 	}
 
 	/* As all the required vports are created, clear the reset flag
@@ -1711,7 +1801,7 @@ static void idpf_set_vport_state(struct idpf_adapter *adapter)
 			continue;
 
 		np = netdev_priv(adapter->netdevs[i]);
-		if (np->state == __IDPF_VPORT_UP)
+		if (test_bit(IDPF_VPORT_UP, np->state))
 			set_bit(IDPF_VPORT_UP_REQUESTED,
 				adapter->vport_config[i]->flags);
 	}
@@ -1753,6 +1843,8 @@ static int idpf_init_hard_reset(struct idpf_adapter *adapter)
 	} else if (test_and_clear_bit(IDPF_HR_FUNC_RESET, adapter->flags)) {
 		bool is_reset = idpf_is_reset_detected(adapter);
 
+		idpf_idc_issue_reset_event(adapter->cdev_info);
+
 		idpf_set_vport_state(adapter);
 		idpf_vc_core_deinit(adapter);
 		if (!is_reset)
@@ -1800,6 +1892,10 @@ static int idpf_init_hard_reset(struct idpf_adapter *adapter)
 unlock_mutex:
 	mutex_unlock(&adapter->vport_ctrl_lock);
 
+	/* Wait until all vports are created to init RDMA CORE AUX */
+	if (!err)
+		err = idpf_idc_init(adapter);
+
 	return err;
 }
 
@@ -1816,11 +1912,19 @@ void idpf_vc_event_task(struct work_struct *work)
 	if (test_bit(IDPF_REMOVE_IN_PROG, adapter->flags))
 		return;
 
-	if (test_bit(IDPF_HR_FUNC_RESET, adapter->flags) ||
-	    test_bit(IDPF_HR_DRV_LOAD, adapter->flags)) {
-		set_bit(IDPF_HR_RESET_IN_PROG, adapter->flags);
-		idpf_init_hard_reset(adapter);
-	}
+	if (test_bit(IDPF_HR_FUNC_RESET, adapter->flags))
+		goto func_reset;
+
+	if (test_bit(IDPF_HR_DRV_LOAD, adapter->flags))
+		goto drv_load;
+
+	return;
+
+func_reset:
+	idpf_vc_xn_shutdown(adapter->vcxn_mngr);
+drv_load:
+	set_bit(IDPF_HR_RESET_IN_PROG, adapter->flags);
+	idpf_init_hard_reset(adapter);
 }
 
 /**
@@ -1835,7 +1939,7 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport,
 			     enum idpf_vport_reset_cause reset_cause)
 {
 	struct idpf_netdev_priv *np = netdev_priv(vport->netdev);
-	enum idpf_vport_state current_state = np->state;
+	bool vport_is_up = test_bit(IDPF_VPORT_UP, np->state);
 	struct idpf_adapter *adapter = vport->adapter;
 	struct idpf_vport *new_vport;
 	int err;
@@ -1875,6 +1979,9 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport,
 		idpf_vport_calc_num_q_desc(new_vport);
 		break;
 	case IDPF_SR_MTU_CHANGE:
+		idpf_idc_vdev_mtu_event(vport->vdev_info,
+					IIDC_RDMA_EVENT_BEFORE_MTU_CHANGE);
+		break;
 	case IDPF_SR_RSC_CHANGE:
 		break;
 	default:
@@ -1883,11 +1990,11 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport,
 		goto free_vport;
 	}
 
-	if (current_state <= __IDPF_VPORT_DOWN) {
+	if (!vport_is_up) {
 		idpf_send_delete_queues_msg(vport);
 	} else {
 		set_bit(IDPF_VPORT_DEL_QUEUES, vport->flags);
-		idpf_vport_stop(vport);
+		idpf_vport_stop(vport, false);
 	}
 
 	idpf_deinit_rss(vport);
@@ -1916,24 +2023,26 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport,
 	if (err)
 		goto err_open;
 
-	if (current_state == __IDPF_VPORT_UP)
-		err = idpf_vport_open(vport);
+	if (vport_is_up)
+		err = idpf_vport_open(vport, false);
 
-	kfree(new_vport);
-
-	return err;
+	goto free_vport;
 
 err_reset:
 	idpf_send_add_queues_msg(vport, vport->num_txq, vport->num_complq,
 				 vport->num_rxq, vport->num_bufq);
 
 err_open:
-	if (current_state == __IDPF_VPORT_UP)
-		idpf_vport_open(vport);
+	if (vport_is_up)
+		idpf_vport_open(vport, false);
 
 free_vport:
 	kfree(new_vport);
 
+	if (reset_cause == IDPF_SR_MTU_CHANGE)
+		idpf_idc_vdev_mtu_event(vport->vdev_info,
+					IIDC_RDMA_EVENT_AFTER_MTU_CHANGE);
+
 	return err;
 }
 
@@ -2159,8 +2268,13 @@ static int idpf_open(struct net_device *netdev)
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
 
-	err = idpf_vport_open(vport);
+	err = idpf_set_real_num_queues(vport);
+	if (err)
+		goto unlock;
 
+	err = idpf_vport_open(vport, false);
+
+unlock:
 	idpf_vport_ctrl_unlock(netdev);
 
 	return err;
@@ -2191,6 +2305,92 @@ static int idpf_change_mtu(struct net_device *netdev, int new_mtu)
 }
 
 /**
+ * idpf_chk_tso_segment - Check skb is not using too many buffers
+ * @skb: send buffer
+ * @max_bufs: maximum number of buffers
+ *
+ * For TSO we need to count the TSO header and segment payload separately.  As
+ * such we need to check cases where we have max_bufs-1 fragments or more as we
+ * can potentially require max_bufs+1 DMA transactions, 1 for the TSO header, 1
+ * for the segment payload in the first descriptor, and another max_buf-1 for
+ * the fragments.
+ *
+ * Returns true if the packet needs to be software segmented by core stack.
+ */
+static bool idpf_chk_tso_segment(const struct sk_buff *skb,
+				 unsigned int max_bufs)
+{
+	const struct skb_shared_info *shinfo = skb_shinfo(skb);
+	const skb_frag_t *frag, *stale;
+	int nr_frags, sum;
+
+	/* no need to check if number of frags is less than max_bufs - 1 */
+	nr_frags = shinfo->nr_frags;
+	if (nr_frags < (max_bufs - 1))
+		return false;
+
+	/* We need to walk through the list and validate that each group
+	 * of max_bufs-2 fragments totals at least gso_size.
+	 */
+	nr_frags -= max_bufs - 2;
+	frag = &shinfo->frags[0];
+
+	/* Initialize size to the negative value of gso_size minus 1.  We use
+	 * this as the worst case scenario in which the frag ahead of us only
+	 * provides one byte which is why we are limited to max_bufs-2
+	 * descriptors for a single transmit as the header and previous
+	 * fragment are already consuming 2 descriptors.
+	 */
+	sum = 1 - shinfo->gso_size;
+
+	/* Add size of frags 0 through 4 to create our initial sum */
+	sum += skb_frag_size(frag++);
+	sum += skb_frag_size(frag++);
+	sum += skb_frag_size(frag++);
+	sum += skb_frag_size(frag++);
+	sum += skb_frag_size(frag++);
+
+	/* Walk through fragments adding latest fragment, testing it, and
+	 * then removing stale fragments from the sum.
+	 */
+	for (stale = &shinfo->frags[0];; stale++) {
+		int stale_size = skb_frag_size(stale);
+
+		sum += skb_frag_size(frag++);
+
+		/* The stale fragment may present us with a smaller
+		 * descriptor than the actual fragment size. To account
+		 * for that we need to remove all the data on the front and
+		 * figure out what the remainder would be in the last
+		 * descriptor associated with the fragment.
+		 */
+		if (stale_size > IDPF_TX_MAX_DESC_DATA) {
+			int align_pad = -(skb_frag_off(stale)) &
+					(IDPF_TX_MAX_READ_REQ_SIZE - 1);
+
+			sum -= align_pad;
+			stale_size -= align_pad;
+
+			do {
+				sum -= IDPF_TX_MAX_DESC_DATA_ALIGNED;
+				stale_size -= IDPF_TX_MAX_DESC_DATA_ALIGNED;
+			} while (stale_size > IDPF_TX_MAX_DESC_DATA);
+		}
+
+		/* if sum is negative we failed to make sufficient progress */
+		if (sum < 0)
+			return true;
+
+		if (!nr_frags--)
+			break;
+
+		sum -= stale_size;
+	}
+
+	return false;
+}
+
+/**
  * idpf_features_check - Validate packet conforms to limits
  * @skb: skb buffer
  * @netdev: This port's netdev
@@ -2200,8 +2400,8 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
 					     struct net_device *netdev,
 					     netdev_features_t features)
 {
-	struct idpf_vport *vport = idpf_netdev_to_vport(netdev);
-	struct idpf_adapter *adapter = vport->adapter;
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	u16 max_tx_hdr_size = np->max_tx_hdr_size;
 	size_t len;
 
 	/* No point in doing any of this if neither checksum nor GSO are
@@ -2211,12 +2411,15 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
 		return features;
 
-	/* We cannot support GSO if the MSS is going to be less than
-	 * 88 bytes. If it is then we need to drop support for GSO.
-	 */
-	if (skb_is_gso(skb) &&
-	    (skb_shinfo(skb)->gso_size < IDPF_TX_TSO_MIN_MSS))
-		features &= ~NETIF_F_GSO_MASK;
+	if (skb_is_gso(skb)) {
+		/* We cannot support GSO if the MSS is going to be less than
+		 * 88 bytes. If it is then we need to drop support for GSO.
+		 */
+		if (skb_shinfo(skb)->gso_size < IDPF_TX_TSO_MIN_MSS)
+			features &= ~NETIF_F_GSO_MASK;
+		else if (idpf_chk_tso_segment(skb, np->tx_max_bufs))
+			features &= ~NETIF_F_GSO_MASK;
+	}
 
 	/* Ensure MACLEN is <= 126 bytes (63 words) and not an odd size */
 	len = skb_network_offset(skb);
@@ -2224,7 +2427,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
 		goto unsupported;
 
 	len = skb_network_header_len(skb);
-	if (unlikely(len > idpf_get_max_tx_hdr_size(adapter)))
+	if (unlikely(len > max_tx_hdr_size))
 		goto unsupported;
 
 	if (!skb->encapsulation)
@@ -2237,7 +2440,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
 
 	/* IPLEN can support at most 127 dwords */
 	len = skb_inner_network_header_len(skb);
-	if (unlikely(len > idpf_get_max_tx_hdr_size(adapter)))
+	if (unlikely(len > max_tx_hdr_size))
 		goto unsupported;
 
 	/* No need to validate L4LEN as TCP is the only protocol with a
@@ -2263,6 +2466,7 @@ static int idpf_set_mac(struct net_device *netdev, void *p)
 	struct idpf_netdev_priv *np = netdev_priv(netdev);
 	struct idpf_vport_config *vport_config;
 	struct sockaddr *addr = p;
+	u8 old_mac_addr[ETH_ALEN];
 	struct idpf_vport *vport;
 	int err = 0;
 
@@ -2286,17 +2490,19 @@ static int idpf_set_mac(struct net_device *netdev, void *p)
 	if (ether_addr_equal(netdev->dev_addr, addr->sa_data))
 		goto unlock_mutex;
 
+	ether_addr_copy(old_mac_addr, vport->default_mac_addr);
+	ether_addr_copy(vport->default_mac_addr, addr->sa_data);
 	vport_config = vport->adapter->vport_config[vport->idx];
 	err = idpf_add_mac_filter(vport, np, addr->sa_data, false);
 	if (err) {
 		__idpf_del_mac_filter(vport_config, addr->sa_data);
+		ether_addr_copy(vport->default_mac_addr, netdev->dev_addr);
 		goto unlock_mutex;
 	}
 
-	if (is_valid_ether_addr(vport->default_mac_addr))
-		idpf_del_mac_filter(vport, np, vport->default_mac_addr, false);
+	if (is_valid_ether_addr(old_mac_addr))
+		__idpf_del_mac_filter(vport_config, old_mac_addr);
 
-	ether_addr_copy(vport->default_mac_addr, addr->sa_data);
 	eth_hw_addr_set(netdev, addr->sa_data);
 
 unlock_mutex:
@@ -2316,8 +2522,12 @@ void *idpf_alloc_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem, u64 size)
 	struct idpf_adapter *adapter = hw->back;
 	size_t sz = ALIGN(size, 4096);
 
-	mem->va = dma_alloc_coherent(&adapter->pdev->dev, sz,
-				     &mem->pa, GFP_KERNEL);
+	/* The control queue resources are freed under a spinlock, contiguous
+	 * pages will avoid IOMMU remapping and the use vmap (and vunmap in
+	 * dma_free_*() path.
+	 */
+	mem->va = dma_alloc_attrs(&adapter->pdev->dev, sz, &mem->pa,
+				  GFP_KERNEL, DMA_ATTR_FORCE_CONTIGUOUS);
 	mem->size = sz;
 
 	return mem->va;
@@ -2332,13 +2542,67 @@ void idpf_free_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem)
 {
 	struct idpf_adapter *adapter = hw->back;
 
-	dma_free_coherent(&adapter->pdev->dev, mem->size,
-			  mem->va, mem->pa);
+	dma_free_attrs(&adapter->pdev->dev, mem->size,
+		       mem->va, mem->pa, DMA_ATTR_FORCE_CONTIGUOUS);
 	mem->size = 0;
 	mem->va = NULL;
 	mem->pa = 0;
 }
 
+static int idpf_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
+{
+	struct idpf_vport *vport;
+	int err;
+
+	idpf_vport_ctrl_lock(netdev);
+	vport = idpf_netdev_to_vport(netdev);
+
+	if (!vport->link_up) {
+		idpf_vport_ctrl_unlock(netdev);
+		return -EPERM;
+	}
+
+	if (!idpf_ptp_is_vport_tx_tstamp_ena(vport) &&
+	    !idpf_ptp_is_vport_rx_tstamp_ena(vport)) {
+		idpf_vport_ctrl_unlock(netdev);
+		return -EOPNOTSUPP;
+	}
+
+	err = idpf_ptp_set_timestamp_mode(vport, config);
+
+	idpf_vport_ctrl_unlock(netdev);
+
+	return err;
+}
+
+static int idpf_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config)
+{
+	struct idpf_vport *vport;
+
+	idpf_vport_ctrl_lock(netdev);
+	vport = idpf_netdev_to_vport(netdev);
+
+	if (!vport->link_up) {
+		idpf_vport_ctrl_unlock(netdev);
+		return -EPERM;
+	}
+
+	if (!idpf_ptp_is_vport_tx_tstamp_ena(vport) &&
+	    !idpf_ptp_is_vport_rx_tstamp_ena(vport)) {
+		idpf_vport_ctrl_unlock(netdev);
+		return 0;
+	}
+
+	*config = vport->tstamp_config;
+
+	idpf_vport_ctrl_unlock(netdev);
+
+	return 0;
+}
+
 static const struct net_device_ops idpf_netdev_ops = {
 	.ndo_open = idpf_open,
 	.ndo_stop = idpf_stop,
@@ -2351,4 +2615,9 @@ static const struct net_device_ops idpf_netdev_ops = {
 	.ndo_get_stats64 = idpf_get_stats64,
 	.ndo_set_features = idpf_set_features,
 	.ndo_tx_timeout = idpf_tx_timeout,
+	.ndo_hwtstamp_get = idpf_hwtstamp_get,
+	.ndo_hwtstamp_set = idpf_hwtstamp_set,
+	.ndo_bpf = idpf_xdp,
+	.ndo_xdp_xmit = idpf_xdp_xmit,
+	.ndo_xsk_wakeup = idpf_xsk_wakeup,
 };
diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c
index f71d3182580b..de5d722cc21d 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_main.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_main.c
@@ -3,15 +3,94 @@
 
 #include "idpf.h"
 #include "idpf_devids.h"
+#include "idpf_lan_vf_regs.h"
 #include "idpf_virtchnl.h"
 
 #define DRV_SUMMARY	"Intel(R) Infrastructure Data Path Function Linux Driver"
 
+#define IDPF_NETWORK_ETHERNET_PROGIF				0x01
+#define IDPF_CLASS_NETWORK_ETHERNET_PROGIF			\
+	(PCI_CLASS_NETWORK_ETHERNET << 8 | IDPF_NETWORK_ETHERNET_PROGIF)
+#define IDPF_VF_TEST_VAL		0xfeed0000u
+
 MODULE_DESCRIPTION(DRV_SUMMARY);
 MODULE_IMPORT_NS("LIBETH");
+MODULE_IMPORT_NS("LIBETH_XDP");
 MODULE_LICENSE("GPL");
 
 /**
+ * idpf_get_device_type - Helper to find if it is a VF or PF device
+ * @pdev: PCI device information struct
+ *
+ * Return: PF/VF device ID or -%errno on failure.
+ */
+static int idpf_get_device_type(struct pci_dev *pdev)
+{
+	void __iomem *addr;
+	int ret;
+
+	addr = ioremap(pci_resource_start(pdev, 0) + VF_ARQBAL, 4);
+	if (!addr) {
+		pci_err(pdev, "Failed to allocate BAR0 mbx region\n");
+		return -EIO;
+	}
+
+	writel(IDPF_VF_TEST_VAL, addr);
+	if (readl(addr) == IDPF_VF_TEST_VAL)
+		ret = IDPF_DEV_ID_VF;
+	else
+		ret = IDPF_DEV_ID_PF;
+
+	iounmap(addr);
+
+	return ret;
+}
+
+/**
+ * idpf_dev_init - Initialize device specific parameters
+ * @adapter: adapter to initialize
+ * @ent: entry in idpf_pci_tbl
+ *
+ * Return: %0 on success, -%errno on failure.
+ */
+static int idpf_dev_init(struct idpf_adapter *adapter,
+			 const struct pci_device_id *ent)
+{
+	int ret;
+
+	if (ent->class == IDPF_CLASS_NETWORK_ETHERNET_PROGIF) {
+		ret = idpf_get_device_type(adapter->pdev);
+		switch (ret) {
+		case IDPF_DEV_ID_VF:
+			idpf_vf_dev_ops_init(adapter);
+			adapter->crc_enable = true;
+			break;
+		case IDPF_DEV_ID_PF:
+			idpf_dev_ops_init(adapter);
+			break;
+		default:
+			return ret;
+		}
+
+		return 0;
+	}
+
+	switch (ent->device) {
+	case IDPF_DEV_ID_PF:
+		idpf_dev_ops_init(adapter);
+		break;
+	case IDPF_DEV_ID_VF:
+		idpf_vf_dev_ops_init(adapter);
+		adapter->crc_enable = true;
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+/**
  * idpf_remove - Device removal routine
  * @pdev: PCI device information struct
  */
@@ -62,6 +141,9 @@ destroy_wqs:
 	destroy_workqueue(adapter->vc_event_wq);
 
 	for (i = 0; i < adapter->max_vports; i++) {
+		if (!adapter->vport_config[i])
+			continue;
+		kfree(adapter->vport_config[i]->user_config.q_coalesce);
 		kfree(adapter->vport_config[i]);
 		adapter->vport_config[i] = NULL;
 	}
@@ -87,7 +169,12 @@ destroy_wqs:
  */
 static void idpf_shutdown(struct pci_dev *pdev)
 {
-	idpf_remove(pdev);
+	struct idpf_adapter *adapter = pci_get_drvdata(pdev);
+
+	cancel_delayed_work_sync(&adapter->serv_task);
+	cancel_delayed_work_sync(&adapter->vc_event_task);
+	idpf_vc_core_deinit(adapter);
+	idpf_deinit_dflt_mbx(adapter);
 
 	if (system_state == SYSTEM_POWER_OFF)
 		pci_set_power_state(pdev, PCI_D3hot);
@@ -101,15 +188,37 @@ static void idpf_shutdown(struct pci_dev *pdev)
  */
 static int idpf_cfg_hw(struct idpf_adapter *adapter)
 {
+	resource_size_t res_start, mbx_start, rstat_start;
 	struct pci_dev *pdev = adapter->pdev;
 	struct idpf_hw *hw = &adapter->hw;
+	struct device *dev = &pdev->dev;
+	long len;
 
-	hw->hw_addr = pcim_iomap_table(pdev)[0];
-	if (!hw->hw_addr) {
-		pci_err(pdev, "failed to allocate PCI iomap table\n");
+	res_start = pci_resource_start(pdev, 0);
+
+	/* Map mailbox space for virtchnl communication */
+	mbx_start = res_start + adapter->dev_ops.static_reg_info[0].start;
+	len = resource_size(&adapter->dev_ops.static_reg_info[0]);
+	hw->mbx.vaddr = devm_ioremap(dev, mbx_start, len);
+	if (!hw->mbx.vaddr) {
+		pci_err(pdev, "failed to allocate BAR0 mbx region\n");
 
 		return -ENOMEM;
 	}
+	hw->mbx.addr_start = adapter->dev_ops.static_reg_info[0].start;
+	hw->mbx.addr_len = len;
+
+	/* Map rstat space for resets */
+	rstat_start = res_start + adapter->dev_ops.static_reg_info[1].start;
+	len = resource_size(&adapter->dev_ops.static_reg_info[1]);
+	hw->rstat.vaddr = devm_ioremap(dev, rstat_start, len);
+	if (!hw->rstat.vaddr) {
+		pci_err(pdev, "failed to allocate BAR0 rstat region\n");
+
+		return -ENOMEM;
+	}
+	hw->rstat.addr_start = adapter->dev_ops.static_reg_info[1].start;
+	hw->rstat.addr_len = len;
 
 	hw->back = adapter;
 
@@ -136,33 +245,22 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	adapter->req_tx_splitq = true;
 	adapter->req_rx_splitq = true;
 
-	switch (ent->device) {
-	case IDPF_DEV_ID_PF:
-		idpf_dev_ops_init(adapter);
-		break;
-	case IDPF_DEV_ID_VF:
-		idpf_vf_dev_ops_init(adapter);
-		adapter->crc_enable = true;
-		break;
-	default:
-		err = -ENODEV;
-		dev_err(&pdev->dev, "Unexpected dev ID 0x%x in idpf probe\n",
-			ent->device);
-		goto err_free;
-	}
-
 	adapter->pdev = pdev;
 	err = pcim_enable_device(pdev);
 	if (err)
 		goto err_free;
 
-	err = pcim_iomap_regions(pdev, BIT(0), pci_name(pdev));
+	err = pcim_request_region(pdev, 0, pci_name(pdev));
 	if (err) {
-		pci_err(pdev, "pcim_iomap_regions failed %pe\n", ERR_PTR(err));
+		pci_err(pdev, "pcim_request_region failed %pe\n", ERR_PTR(err));
 
 		goto err_free;
 	}
 
+	err = pci_enable_ptm(pdev, NULL);
+	if (err)
+		pci_dbg(pdev, "PCIe PTM is not supported by PCIe bus/controller\n");
+
 	/* set up for high or low dma */
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (err) {
@@ -174,7 +272,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_set_master(pdev);
 	pci_set_drvdata(pdev, adapter);
 
-	adapter->init_wq = alloc_workqueue("%s-%s-init", 0, 0,
+	adapter->init_wq = alloc_workqueue("%s-%s-init",
+					   WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					   dev_driver_string(dev),
 					   dev_name(dev));
 	if (!adapter->init_wq) {
@@ -183,7 +282,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_free;
 	}
 
-	adapter->serv_wq = alloc_workqueue("%s-%s-service", 0, 0,
+	adapter->serv_wq = alloc_workqueue("%s-%s-service",
+					   WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					   dev_driver_string(dev),
 					   dev_name(dev));
 	if (!adapter->serv_wq) {
@@ -192,8 +292,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_serv_wq_alloc;
 	}
 
-	adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", 0, 0,
-					  dev_driver_string(dev),
+	adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", WQ_UNBOUND | WQ_HIGHPRI,
+					  0, dev_driver_string(dev),
 					  dev_name(dev));
 	if (!adapter->mbx_wq) {
 		dev_err(dev, "Failed to allocate mailbox workqueue\n");
@@ -201,7 +301,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_mbx_wq_alloc;
 	}
 
-	adapter->stats_wq = alloc_workqueue("%s-%s-stats", 0, 0,
+	adapter->stats_wq = alloc_workqueue("%s-%s-stats",
+					    WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					    dev_driver_string(dev),
 					    dev_name(dev));
 	if (!adapter->stats_wq) {
@@ -210,7 +311,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_stats_wq_alloc;
 	}
 
-	adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event", 0, 0,
+	adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event",
+					       WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					       dev_driver_string(dev),
 					       dev_name(dev));
 	if (!adapter->vc_event_wq) {
@@ -222,11 +324,18 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* setup msglvl */
 	adapter->msg_enable = netif_msg_init(-1, IDPF_AVAIL_NETIF_M);
 
+	err = idpf_dev_init(adapter, ent);
+	if (err) {
+		dev_err(&pdev->dev, "Unexpected dev ID 0x%x in idpf probe\n",
+			ent->device);
+		goto destroy_vc_event_wq;
+	}
+
 	err = idpf_cfg_hw(adapter);
 	if (err) {
 		dev_err(dev, "Failed to configure HW structure for adapter: %d\n",
 			err);
-		goto err_cfg_hw;
+		goto destroy_vc_event_wq;
 	}
 
 	mutex_init(&adapter->vport_ctrl_lock);
@@ -247,7 +356,7 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	return 0;
 
-err_cfg_hw:
+destroy_vc_event_wq:
 	destroy_workqueue(adapter->vc_event_wq);
 err_vc_event_wq_alloc:
 	destroy_workqueue(adapter->stats_wq);
@@ -267,6 +376,7 @@ err_free:
 static const struct pci_device_id idpf_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, IDPF_DEV_ID_PF)},
 	{ PCI_VDEVICE(INTEL, IDPF_DEV_ID_VF)},
+	{ PCI_DEVICE_CLASS(IDPF_CLASS_NETWORK_ETHERNET_PROGIF, ~0)},
 	{ /* Sentinel */ }
 };
 MODULE_DEVICE_TABLE(pci, idpf_pci_tbl);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_mem.h b/drivers/net/ethernet/intel/idpf/idpf_mem.h
index b21a04fccf0f..2aaabdc02dd2 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_mem.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_mem.h
@@ -12,9 +12,9 @@ struct idpf_dma_mem {
 	size_t size;
 };
 
-#define wr32(a, reg, value)	writel((value), ((a)->hw_addr + (reg)))
-#define rd32(a, reg)		readl((a)->hw_addr + (reg))
-#define wr64(a, reg, value)	writeq((value), ((a)->hw_addr + (reg)))
-#define rd64(a, reg)		readq((a)->hw_addr + (reg))
+#define idpf_mbx_wr32(a, reg, value)	writel((value), ((a)->mbx.vaddr + (reg)))
+#define idpf_mbx_rd32(a, reg)		readl((a)->mbx.vaddr + (reg))
+#define idpf_mbx_wr64(a, reg, value)	writeq((value), ((a)->mbx.vaddr + (reg)))
+#define idpf_mbx_rd64(a, reg)		readq((a)->mbx.vaddr + (reg))
 
 #endif /* _IDPF_MEM_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
new file mode 100644
index 000000000000..3e1052d070cf
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
@@ -0,0 +1,1021 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2024 Intel Corporation */
+
+#include "idpf.h"
+#include "idpf_ptp.h"
+
+/**
+ * idpf_ptp_get_access - Determine the access type of the PTP features
+ * @adapter: Driver specific private structure
+ * @direct: Capability that indicates the direct access
+ * @mailbox: Capability that indicates the mailbox access
+ *
+ * Return: the type of supported access for the PTP feature.
+ */
+static enum idpf_ptp_access
+idpf_ptp_get_access(const struct idpf_adapter *adapter, u32 direct, u32 mailbox)
+{
+	if (adapter->ptp->caps & direct)
+		return IDPF_PTP_DIRECT;
+	else if (adapter->ptp->caps & mailbox)
+		return IDPF_PTP_MAILBOX;
+	else
+		return IDPF_PTP_NONE;
+}
+
+/**
+ * idpf_ptp_get_features_access - Determine the access type of PTP features
+ * @adapter: Driver specific private structure
+ *
+ * Fulfill the adapter structure with type of the supported PTP features
+ * access.
+ */
+void idpf_ptp_get_features_access(const struct idpf_adapter *adapter)
+{
+	struct idpf_ptp *ptp = adapter->ptp;
+	u32 direct, mailbox;
+
+	/* Get the device clock time */
+	direct = VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME;
+	mailbox = VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB;
+	ptp->get_dev_clk_time_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
+
+	/* Get the cross timestamp */
+	direct = VIRTCHNL2_CAP_PTP_GET_CROSS_TIME;
+	mailbox = VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB;
+	ptp->get_cross_tstamp_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
+
+	/* Set the device clock time */
+	direct = VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME;
+	mailbox = VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME;
+	ptp->set_dev_clk_time_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
+
+	/* Adjust the device clock time */
+	direct = VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK;
+	mailbox = VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB;
+	ptp->adj_dev_clk_time_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
+
+	/* Tx timestamping */
+	direct = VIRTCHNL2_CAP_PTP_TX_TSTAMPS;
+	mailbox = VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB;
+	ptp->tx_tstamp_access = idpf_ptp_get_access(adapter,
+						    direct,
+						    mailbox);
+}
+
+/**
+ * idpf_ptp_enable_shtime - Enable shadow time and execute a command
+ * @adapter: Driver specific private structure
+ */
+static void idpf_ptp_enable_shtime(struct idpf_adapter *adapter)
+{
+	u32 shtime_enable, exec_cmd;
+
+	/* Get offsets */
+	shtime_enable = adapter->ptp->cmd.shtime_enable_mask;
+	exec_cmd = adapter->ptp->cmd.exec_cmd_mask;
+
+	/* Set the shtime en and the sync field */
+	writel(shtime_enable, adapter->ptp->dev_clk_regs.cmd_sync);
+	writel(exec_cmd | shtime_enable, adapter->ptp->dev_clk_regs.cmd_sync);
+}
+
+/**
+ * idpf_ptp_read_src_clk_reg_direct - Read directly the main timer value
+ * @adapter: Driver specific private structure
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored when NULL is given.
+ *
+ * Return: the device clock time.
+ */
+static u64 idpf_ptp_read_src_clk_reg_direct(struct idpf_adapter *adapter,
+					    struct ptp_system_timestamp *sts)
+{
+	struct idpf_ptp *ptp = adapter->ptp;
+	u32 hi, lo;
+
+	spin_lock(&ptp->read_dev_clk_lock);
+
+	/* Read the system timestamp pre PHC read */
+	ptp_read_system_prets(sts);
+
+	idpf_ptp_enable_shtime(adapter);
+
+	/* Read the system timestamp post PHC read */
+	ptp_read_system_postts(sts);
+
+	lo = readl(ptp->dev_clk_regs.dev_clk_ns_l);
+	hi = readl(ptp->dev_clk_regs.dev_clk_ns_h);
+
+	spin_unlock(&ptp->read_dev_clk_lock);
+
+	return ((u64)hi << 32) | lo;
+}
+
+/**
+ * idpf_ptp_read_src_clk_reg_mailbox - Read the main timer value through mailbox
+ * @adapter: Driver specific private structure
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored when NULL is given.
+ * @src_clk: Returned main timer value in nanoseconds unit
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_read_src_clk_reg_mailbox(struct idpf_adapter *adapter,
+					     struct ptp_system_timestamp *sts,
+					     u64 *src_clk)
+{
+	struct idpf_ptp_dev_timers clk_time;
+	int err;
+
+	/* Read the system timestamp pre PHC read */
+	ptp_read_system_prets(sts);
+
+	err = idpf_ptp_get_dev_clk_time(adapter, &clk_time);
+	if (err)
+		return err;
+
+	/* Read the system timestamp post PHC read */
+	ptp_read_system_postts(sts);
+
+	*src_clk = clk_time.dev_clk_time_ns;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_read_src_clk_reg - Read the main timer value
+ * @adapter: Driver specific private structure
+ * @src_clk: Returned main timer value in nanoseconds unit
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored if NULL is given.
+ *
+ * Return: the device clock time on success, -errno otherwise.
+ */
+static int idpf_ptp_read_src_clk_reg(struct idpf_adapter *adapter, u64 *src_clk,
+				     struct ptp_system_timestamp *sts)
+{
+	switch (adapter->ptp->get_dev_clk_time_access) {
+	case IDPF_PTP_NONE:
+		return -EOPNOTSUPP;
+	case IDPF_PTP_MAILBOX:
+		return idpf_ptp_read_src_clk_reg_mailbox(adapter, sts, src_clk);
+	case IDPF_PTP_DIRECT:
+		*src_clk = idpf_ptp_read_src_clk_reg_direct(adapter, sts);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_ARM_ARCH_TIMER) || IS_ENABLED(CONFIG_X86)
+/**
+ * idpf_ptp_get_sync_device_time_direct - Get the cross time stamp values
+ *					  directly
+ * @adapter: Driver specific private structure
+ * @dev_time: 64bit main timer value
+ * @sys_time: 64bit system time value
+ */
+static void idpf_ptp_get_sync_device_time_direct(struct idpf_adapter *adapter,
+						 u64 *dev_time, u64 *sys_time)
+{
+	u32 dev_time_lo, dev_time_hi, sys_time_lo, sys_time_hi;
+	struct idpf_ptp *ptp = adapter->ptp;
+
+	spin_lock(&ptp->read_dev_clk_lock);
+
+	idpf_ptp_enable_shtime(adapter);
+
+	dev_time_lo = readl(ptp->dev_clk_regs.dev_clk_ns_l);
+	dev_time_hi = readl(ptp->dev_clk_regs.dev_clk_ns_h);
+
+	sys_time_lo = readl(ptp->dev_clk_regs.sys_time_ns_l);
+	sys_time_hi = readl(ptp->dev_clk_regs.sys_time_ns_h);
+
+	spin_unlock(&ptp->read_dev_clk_lock);
+
+	*dev_time = (u64)dev_time_hi << 32 | dev_time_lo;
+	*sys_time = (u64)sys_time_hi << 32 | sys_time_lo;
+}
+
+/**
+ * idpf_ptp_get_sync_device_time_mailbox - Get the cross time stamp values
+ *					   through mailbox
+ * @adapter: Driver specific private structure
+ * @dev_time: 64bit main timer value expressed in nanoseconds
+ * @sys_time: 64bit system time value expressed in nanoseconds
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_get_sync_device_time_mailbox(struct idpf_adapter *adapter,
+						 u64 *dev_time, u64 *sys_time)
+{
+	struct idpf_ptp_dev_timers cross_time;
+	int err;
+
+	err = idpf_ptp_get_cross_time(adapter, &cross_time);
+	if (err)
+		return err;
+
+	*dev_time = cross_time.dev_clk_time_ns;
+	*sys_time = cross_time.sys_time_ns;
+
+	return err;
+}
+
+/**
+ * idpf_ptp_get_sync_device_time - Get the cross time stamp info
+ * @device: Current device time
+ * @system: System counter value read synchronously with device time
+ * @ctx: Context provided by timekeeping code
+ *
+ * The device and the system clocks time read simultaneously.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_get_sync_device_time(ktime_t *device,
+					 struct system_counterval_t *system,
+					 void *ctx)
+{
+	struct idpf_adapter *adapter = ctx;
+	u64 ns_time_dev, ns_time_sys;
+	int err;
+
+	switch (adapter->ptp->get_cross_tstamp_access) {
+	case IDPF_PTP_NONE:
+		return -EOPNOTSUPP;
+	case IDPF_PTP_DIRECT:
+		idpf_ptp_get_sync_device_time_direct(adapter, &ns_time_dev,
+						     &ns_time_sys);
+		break;
+	case IDPF_PTP_MAILBOX:
+		err = idpf_ptp_get_sync_device_time_mailbox(adapter,
+							    &ns_time_dev,
+							    &ns_time_sys);
+		if (err)
+			return err;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	*device = ns_to_ktime(ns_time_dev);
+
+	system->cs_id = IS_ENABLED(CONFIG_X86) ? CSID_X86_ART
+					       : CSID_ARM_ARCH_COUNTER;
+	system->cycles = ns_time_sys;
+	system->use_nsecs = true;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_crosststamp - Capture a device cross timestamp
+ * @info: the driver's PTP info structure
+ * @cts: The memory to fill the cross timestamp info
+ *
+ * Capture a cross timestamp between the system time and the device PTP hardware
+ * clock.
+ *
+ * Return: cross timestamp value on success, -errno on failure.
+ */
+static int idpf_ptp_get_crosststamp(struct ptp_clock_info *info,
+				    struct system_device_crosststamp *cts)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+
+	return get_device_system_crosststamp(idpf_ptp_get_sync_device_time,
+					     adapter, NULL, cts);
+}
+#endif /* CONFIG_ARM_ARCH_TIMER || CONFIG_X86 */
+
+/**
+ * idpf_ptp_gettimex64 - Get the time of the clock
+ * @info: the driver's PTP info structure
+ * @ts: timespec64 structure to hold the current time value
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored if NULL is given.
+ *
+ * Return: the device clock value in ns, after converting it into a timespec
+ * struct on success, -errno otherwise.
+ */
+static int idpf_ptp_gettimex64(struct ptp_clock_info *info,
+			       struct timespec64 *ts,
+			       struct ptp_system_timestamp *sts)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	u64 time_ns;
+	int err;
+
+	err = idpf_ptp_read_src_clk_reg(adapter, &time_ns, sts);
+	if (err)
+		return -EACCES;
+
+	*ts = ns_to_timespec64(time_ns);
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_update_phctime_rxq_grp - Update the cached PHC time for a given Rx
+ *				     queue group.
+ * @grp: receive queue group in which Rx timestamp is enabled
+ * @split: Indicates whether the queue model is split or single queue
+ * @systime: Cached system time
+ */
+static void
+idpf_ptp_update_phctime_rxq_grp(const struct idpf_rxq_group *grp, bool split,
+				u64 systime)
+{
+	struct idpf_rx_queue *rxq;
+	u16 i;
+
+	if (!split) {
+		for (i = 0; i < grp->singleq.num_rxq; i++) {
+			rxq = grp->singleq.rxqs[i];
+			if (rxq)
+				WRITE_ONCE(rxq->cached_phc_time, systime);
+		}
+	} else {
+		for (i = 0; i < grp->splitq.num_rxq_sets; i++) {
+			rxq = &grp->splitq.rxq_sets[i]->rxq;
+			if (rxq)
+				WRITE_ONCE(rxq->cached_phc_time, systime);
+		}
+	}
+}
+
+/**
+ * idpf_ptp_update_cached_phctime - Update the cached PHC time values
+ * @adapter: Driver specific private structure
+ *
+ * This function updates the system time values which are cached in the adapter
+ * structure and the Rx queues.
+ *
+ * This function must be called periodically to ensure that the cached value
+ * is never more than 2 seconds old.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_update_cached_phctime(struct idpf_adapter *adapter)
+{
+	u64 systime;
+	int err;
+
+	err = idpf_ptp_read_src_clk_reg(adapter, &systime, NULL);
+	if (err)
+		return -EACCES;
+
+	/* Update the cached PHC time stored in the adapter structure.
+	 * These values are used to extend Tx timestamp values to 64 bit
+	 * expected by the stack.
+	 */
+	WRITE_ONCE(adapter->ptp->cached_phc_time, systime);
+	WRITE_ONCE(adapter->ptp->cached_phc_jiffies, jiffies);
+
+	idpf_for_each_vport(adapter, vport) {
+		bool split;
+
+		if (!vport || !vport->rxq_grps)
+			continue;
+
+		split = idpf_is_queue_model_split(vport->rxq_model);
+
+		for (u16 i = 0; i < vport->num_rxq_grp; i++) {
+			struct idpf_rxq_group *grp = &vport->rxq_grps[i];
+
+			idpf_ptp_update_phctime_rxq_grp(grp, split, systime);
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_settime64 - Set the time of the clock
+ * @info: the driver's PTP info structure
+ * @ts: timespec64 structure that holds the new time value
+ *
+ * Set the device clock to the user input value. The conversion from timespec
+ * to ns happens in the write function.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_settime64(struct ptp_clock_info *info,
+			      const struct timespec64 *ts)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	enum idpf_ptp_access access;
+	int err;
+	u64 ns;
+
+	access = adapter->ptp->set_dev_clk_time_access;
+	if (access != IDPF_PTP_MAILBOX)
+		return -EOPNOTSUPP;
+
+	ns = timespec64_to_ns(ts);
+
+	err = idpf_ptp_set_dev_clk_time(adapter, ns);
+	if (err) {
+		pci_err(adapter->pdev, "Failed to set the time, err: %pe\n",
+			ERR_PTR(err));
+		return err;
+	}
+
+	err = idpf_ptp_update_cached_phctime(adapter);
+	if (err)
+		pci_warn(adapter->pdev,
+			 "Unable to immediately update cached PHC time\n");
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adjtime_nonatomic - Do a non-atomic clock adjustment
+ * @info: the driver's PTP info structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_adjtime_nonatomic(struct ptp_clock_info *info, s64 delta)
+{
+	struct timespec64 now, then;
+	int err;
+
+	err = idpf_ptp_gettimex64(info, &now, NULL);
+	if (err)
+		return err;
+
+	then = ns_to_timespec64(delta);
+	now = timespec64_add(now, then);
+
+	return idpf_ptp_settime64(info, &now);
+}
+
+/**
+ * idpf_ptp_adjtime - Adjust the time of the clock by the indicated delta
+ * @info: the driver's PTP info structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_adjtime(struct ptp_clock_info *info, s64 delta)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	enum idpf_ptp_access access;
+	int err;
+
+	access = adapter->ptp->adj_dev_clk_time_access;
+	if (access != IDPF_PTP_MAILBOX)
+		return -EOPNOTSUPP;
+
+	/* Hardware only supports atomic adjustments using signed 32-bit
+	 * integers. For any adjustment outside this range, perform
+	 * a non-atomic get->adjust->set flow.
+	 */
+	if (delta > S32_MAX || delta < S32_MIN)
+		return idpf_ptp_adjtime_nonatomic(info, delta);
+
+	err = idpf_ptp_adj_dev_clk_time(adapter, delta);
+	if (err) {
+		pci_err(adapter->pdev, "Failed to adjust the clock with delta %lld err: %pe\n",
+			delta, ERR_PTR(err));
+		return err;
+	}
+
+	err = idpf_ptp_update_cached_phctime(adapter);
+	if (err)
+		pci_warn(adapter->pdev,
+			 "Unable to immediately update cached PHC time\n");
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adjfine - Adjust clock increment rate
+ * @info: the driver's PTP info structure
+ * @scaled_ppm: Parts per million with 16-bit fractional field
+ *
+ * Adjust the frequency of the clock by the indicated scaled ppm from the
+ * base frequency.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	enum idpf_ptp_access access;
+	u64 incval, diff;
+	int err;
+
+	access = adapter->ptp->adj_dev_clk_time_access;
+	if (access != IDPF_PTP_MAILBOX)
+		return -EOPNOTSUPP;
+
+	incval = adapter->ptp->base_incval;
+
+	diff = adjust_by_scaled_ppm(incval, scaled_ppm);
+	err = idpf_ptp_adj_dev_clk_fine(adapter, diff);
+	if (err)
+		pci_err(adapter->pdev, "Failed to adjust clock increment rate for scaled ppm %ld %pe\n",
+			scaled_ppm, ERR_PTR(err));
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_verify_pin - Verify if pin supports requested pin function
+ * @info: the driver's PTP info structure
+ * @pin: Pin index
+ * @func: Assigned function
+ * @chan: Assigned channel
+ *
+ * Return: EOPNOTSUPP as not supported yet.
+ */
+static int idpf_ptp_verify_pin(struct ptp_clock_info *info, unsigned int pin,
+			       enum ptp_pin_function func, unsigned int chan)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * idpf_ptp_gpio_enable - Enable/disable ancillary features of PHC
+ * @info: the driver's PTP info structure
+ * @rq: The requested feature to change
+ * @on: Enable/disable flag
+ *
+ * Return: EOPNOTSUPP as not supported yet.
+ */
+static int idpf_ptp_gpio_enable(struct ptp_clock_info *info,
+				struct ptp_clock_request *rq, int on)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * idpf_ptp_tstamp_extend_32b_to_64b - Convert a 32b nanoseconds Tx or Rx
+ *				       timestamp value to 64b.
+ * @cached_phc_time: recently cached copy of PHC time
+ * @in_timestamp: Ingress/egress 32b nanoseconds timestamp value
+ *
+ * Hardware captures timestamps which contain only 32 bits of nominal
+ * nanoseconds, as opposed to the 64bit timestamps that the stack expects.
+ *
+ * Return: Tx timestamp value extended to 64 bits based on cached PHC time.
+ */
+u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time, u32 in_timestamp)
+{
+	u32 delta, phc_time_lo;
+	u64 ns;
+
+	/* Extract the lower 32 bits of the PHC time */
+	phc_time_lo = (u32)cached_phc_time;
+
+	/* Calculate the delta between the lower 32bits of the cached PHC
+	 * time and the in_timestamp value.
+	 */
+	delta = in_timestamp - phc_time_lo;
+
+	if (delta > U32_MAX / 2) {
+		/* Reverse the delta calculation here */
+		delta = phc_time_lo - in_timestamp;
+		ns = cached_phc_time - delta;
+	} else {
+		ns = cached_phc_time + delta;
+	}
+
+	return ns;
+}
+
+/**
+ * idpf_ptp_extend_ts - Convert a 40b timestamp to 64b nanoseconds
+ * @vport: Virtual port structure
+ * @in_tstamp: Ingress/egress timestamp value
+ *
+ * It is assumed that the caller verifies the timestamp is valid prior to
+ * calling this function.
+ *
+ * Extract the 32bit nominal nanoseconds and extend them. Use the cached PHC
+ * time stored in the device private PTP structure as the basis for timestamp
+ * extension.
+ *
+ * Return: Tx timestamp value extended to 64 bits.
+ */
+u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u64 in_tstamp)
+{
+	struct idpf_ptp *ptp = vport->adapter->ptp;
+	unsigned long discard_time;
+
+	discard_time = ptp->cached_phc_jiffies + 2 * HZ;
+
+	if (time_is_before_jiffies(discard_time)) {
+		u64_stats_update_begin(&vport->tstamp_stats.stats_sync);
+		u64_stats_inc(&vport->tstamp_stats.discarded);
+		u64_stats_update_end(&vport->tstamp_stats.stats_sync);
+
+		return 0;
+	}
+
+	return idpf_ptp_tstamp_extend_32b_to_64b(ptp->cached_phc_time,
+						 lower_32_bits(in_tstamp));
+}
+
+/**
+ * idpf_ptp_request_ts - Request an available Tx timestamp index
+ * @tx_q: Transmit queue on which the Tx timestamp is requested
+ * @skb: The SKB to associate with this timestamp request
+ * @idx: Index of the Tx timestamp latch
+ *
+ * Request tx timestamp index negotiated during PTP init that will be set into
+ * Tx descriptor.
+ *
+ * Return: 0 and the index that can be provided to Tx descriptor on success,
+ * -errno otherwise.
+ */
+int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			u32 *idx)
+{
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp;
+	struct list_head *head;
+
+	/* Get the index from the free latches list */
+	spin_lock(&tx_q->cached_tstamp_caps->latches_lock);
+
+	head = &tx_q->cached_tstamp_caps->latches_free;
+	if (list_empty(head)) {
+		spin_unlock(&tx_q->cached_tstamp_caps->latches_lock);
+		return -ENOBUFS;
+	}
+
+	ptp_tx_tstamp = list_first_entry(head, struct idpf_ptp_tx_tstamp,
+					 list_member);
+	list_del(&ptp_tx_tstamp->list_member);
+
+	ptp_tx_tstamp->skb = skb_get(skb);
+	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+
+	/* Move the element to the used latches list */
+	list_add(&ptp_tx_tstamp->list_member,
+		 &tx_q->cached_tstamp_caps->latches_in_use);
+	spin_unlock(&tx_q->cached_tstamp_caps->latches_lock);
+
+	*idx = ptp_tx_tstamp->idx;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_set_rx_tstamp - Enable or disable Rx timestamping
+ * @vport: Virtual port structure
+ * @rx_filter: Receive timestamp filter
+ */
+static void idpf_ptp_set_rx_tstamp(struct idpf_vport *vport, int rx_filter)
+{
+	bool enable = true, splitq;
+
+	splitq = idpf_is_queue_model_split(vport->rxq_model);
+
+	if (rx_filter == HWTSTAMP_FILTER_NONE) {
+		enable = false;
+		vport->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+	} else {
+		vport->tstamp_config.rx_filter = HWTSTAMP_FILTER_ALL;
+	}
+
+	for (u16 i = 0; i < vport->num_rxq_grp; i++) {
+		struct idpf_rxq_group *grp = &vport->rxq_grps[i];
+		struct idpf_rx_queue *rx_queue;
+		u16 j, num_rxq;
+
+		if (splitq)
+			num_rxq = grp->splitq.num_rxq_sets;
+		else
+			num_rxq = grp->singleq.num_rxq;
+
+		for (j = 0; j < num_rxq; j++) {
+			if (splitq)
+				rx_queue = &grp->splitq.rxq_sets[j]->rxq;
+			else
+				rx_queue = grp->singleq.rxqs[j];
+
+			if (enable)
+				idpf_queue_set(PTP, rx_queue);
+			else
+				idpf_queue_clear(PTP, rx_queue);
+		}
+	}
+}
+
+/**
+ * idpf_ptp_set_timestamp_mode - Setup driver for requested timestamp mode
+ * @vport: Virtual port structure
+ * @config: Hwtstamp settings requested or saved
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_set_timestamp_mode(struct idpf_vport *vport,
+				struct kernel_hwtstamp_config *config)
+{
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+		break;
+	case HWTSTAMP_TX_ON:
+		if (!idpf_ptp_is_vport_tx_tstamp_ena(vport))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	vport->tstamp_config.tx_type = config->tx_type;
+	idpf_ptp_set_rx_tstamp(vport, config->rx_filter);
+	*config = vport->tstamp_config;
+
+	return 0;
+}
+
+/**
+ * idpf_tstamp_task - Delayed task to handle Tx tstamps
+ * @work: work_struct handle
+ */
+void idpf_tstamp_task(struct work_struct *work)
+{
+	struct idpf_vport *vport;
+
+	vport = container_of(work, struct idpf_vport, tstamp_task);
+
+	idpf_ptp_get_tx_tstamp(vport);
+}
+
+/**
+ * idpf_ptp_do_aux_work - Do PTP periodic work
+ * @info: Driver's PTP info structure
+ *
+ * Return: Number of jiffies to periodic work.
+ */
+static long idpf_ptp_do_aux_work(struct ptp_clock_info *info)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+
+	idpf_ptp_update_cached_phctime(adapter);
+
+	return msecs_to_jiffies(500);
+}
+
+/**
+ * idpf_ptp_set_caps - Set PTP capabilities
+ * @adapter: Driver specific private structure
+ *
+ * This function sets the PTP functions.
+ */
+static void idpf_ptp_set_caps(const struct idpf_adapter *adapter)
+{
+	struct ptp_clock_info *info = &adapter->ptp->info;
+
+	snprintf(info->name, sizeof(info->name), "%s-%s-clk",
+		 KBUILD_MODNAME, pci_name(adapter->pdev));
+
+	info->owner = THIS_MODULE;
+	info->max_adj = adapter->ptp->max_adj;
+	info->gettimex64 = idpf_ptp_gettimex64;
+	info->settime64 = idpf_ptp_settime64;
+	info->adjfine = idpf_ptp_adjfine;
+	info->adjtime = idpf_ptp_adjtime;
+	info->verify = idpf_ptp_verify_pin;
+	info->enable = idpf_ptp_gpio_enable;
+	info->do_aux_work = idpf_ptp_do_aux_work;
+#if IS_ENABLED(CONFIG_ARM_ARCH_TIMER)
+	info->getcrosststamp = idpf_ptp_get_crosststamp;
+#elif IS_ENABLED(CONFIG_X86)
+	if (pcie_ptm_enabled(adapter->pdev) &&
+	    boot_cpu_has(X86_FEATURE_ART) &&
+	    boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ))
+		info->getcrosststamp = idpf_ptp_get_crosststamp;
+#endif /* CONFIG_ARM_ARCH_TIMER */
+}
+
+/**
+ * idpf_ptp_create_clock - Create PTP clock device for userspace
+ * @adapter: Driver specific private structure
+ *
+ * This function creates a new PTP clock device.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_create_clock(const struct idpf_adapter *adapter)
+{
+	struct ptp_clock *clock;
+
+	idpf_ptp_set_caps(adapter);
+
+	/* Attempt to register the clock before enabling the hardware. */
+	clock = ptp_clock_register(&adapter->ptp->info,
+				   &adapter->pdev->dev);
+	if (IS_ERR(clock)) {
+		pci_err(adapter->pdev, "PTP clock creation failed: %pe\n",
+			clock);
+		return PTR_ERR(clock);
+	}
+
+	adapter->ptp->clock = clock;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_release_vport_tstamp - Release the Tx timestamps trakcers for a
+ *				   given vport.
+ * @vport: Virtual port structure
+ *
+ * Remove the queues and delete lists that tracks Tx timestamp entries for a
+ * given vport.
+ */
+static void idpf_ptp_release_vport_tstamp(struct idpf_vport *vport)
+{
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp, *tmp;
+	struct list_head *head;
+
+	cancel_work_sync(&vport->tstamp_task);
+
+	/* Remove list with free latches */
+	spin_lock_bh(&vport->tx_tstamp_caps->latches_lock);
+
+	head = &vport->tx_tstamp_caps->latches_free;
+	list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) {
+		list_del(&ptp_tx_tstamp->list_member);
+		kfree(ptp_tx_tstamp);
+	}
+
+	/* Remove list with latches in use */
+	head = &vport->tx_tstamp_caps->latches_in_use;
+	u64_stats_update_begin(&vport->tstamp_stats.stats_sync);
+	list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) {
+		u64_stats_inc(&vport->tstamp_stats.flushed);
+
+		list_del(&ptp_tx_tstamp->list_member);
+		if (ptp_tx_tstamp->skb)
+			consume_skb(ptp_tx_tstamp->skb);
+
+		kfree(ptp_tx_tstamp);
+	}
+	u64_stats_update_end(&vport->tstamp_stats.stats_sync);
+
+	spin_unlock_bh(&vport->tx_tstamp_caps->latches_lock);
+
+	kfree(vport->tx_tstamp_caps);
+	vport->tx_tstamp_caps = NULL;
+}
+
+/**
+ * idpf_ptp_release_tstamp - Release the Tx timestamps trackers
+ * @adapter: Driver specific private structure
+ *
+ * Remove the queues and delete lists that tracks Tx timestamp entries.
+ */
+static void idpf_ptp_release_tstamp(struct idpf_adapter *adapter)
+{
+	idpf_for_each_vport(adapter, vport) {
+		if (!idpf_ptp_is_vport_tx_tstamp_ena(vport))
+			continue;
+
+		idpf_ptp_release_vport_tstamp(vport);
+	}
+}
+
+/**
+ * idpf_ptp_get_txq_tstamp_capability - Verify the timestamping capability
+ *					for a given tx queue.
+ * @txq: Transmit queue
+ *
+ * Since performing timestamp flows requires reading the device clock value and
+ * the support in the Control Plane, the function checks both factors and
+ * summarizes the support for the timestamping.
+ *
+ * Return: true if the timestamping is supported, false otherwise.
+ */
+bool idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq)
+{
+	if (!txq || !txq->cached_tstamp_caps)
+		return false;
+	else if (txq->cached_tstamp_caps->access)
+		return true;
+	else
+		return false;
+}
+
+/**
+ * idpf_ptp_init - Initialize PTP hardware clock support
+ * @adapter: Driver specific private structure
+ *
+ * Set up the device for interacting with the PTP hardware clock for all
+ * functions. Function will allocate and register a ptp_clock with the
+ * PTP_1588_CLOCK infrastructure.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_init(struct idpf_adapter *adapter)
+{
+	struct timespec64 ts;
+	int err;
+
+	if (!idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_PTP)) {
+		pci_dbg(adapter->pdev, "PTP capability is not detected\n");
+		return -EOPNOTSUPP;
+	}
+
+	adapter->ptp = kzalloc(sizeof(*adapter->ptp), GFP_KERNEL);
+	if (!adapter->ptp)
+		return -ENOMEM;
+
+	/* add a back pointer to adapter */
+	adapter->ptp->adapter = adapter;
+
+	if (adapter->dev_ops.reg_ops.ptp_reg_init)
+		adapter->dev_ops.reg_ops.ptp_reg_init(adapter);
+
+	err = idpf_ptp_get_caps(adapter);
+	if (err) {
+		pci_err(adapter->pdev, "Failed to get PTP caps err %d\n", err);
+		goto free_ptp;
+	}
+
+	err = idpf_ptp_create_clock(adapter);
+	if (err)
+		goto free_ptp;
+
+	if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+		ptp_schedule_worker(adapter->ptp->clock, 0);
+
+	/* Write the default increment time value if the clock adjustments
+	 * are enabled.
+	 */
+	if (adapter->ptp->adj_dev_clk_time_access != IDPF_PTP_NONE) {
+		err = idpf_ptp_adj_dev_clk_fine(adapter,
+						adapter->ptp->base_incval);
+		if (err)
+			goto remove_clock;
+	}
+
+	/* Write the initial time value if the set time operation is enabled */
+	if (adapter->ptp->set_dev_clk_time_access != IDPF_PTP_NONE) {
+		ts = ktime_to_timespec64(ktime_get_real());
+		err = idpf_ptp_settime64(&adapter->ptp->info, &ts);
+		if (err)
+			goto remove_clock;
+	}
+
+	spin_lock_init(&adapter->ptp->read_dev_clk_lock);
+
+	pci_dbg(adapter->pdev, "PTP init successful\n");
+
+	return 0;
+
+remove_clock:
+	if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+		ptp_cancel_worker_sync(adapter->ptp->clock);
+
+	ptp_clock_unregister(adapter->ptp->clock);
+	adapter->ptp->clock = NULL;
+
+free_ptp:
+	kfree(adapter->ptp);
+	adapter->ptp = NULL;
+
+	return err;
+}
+
+/**
+ * idpf_ptp_release - Clear PTP hardware clock support
+ * @adapter: Driver specific private structure
+ */
+void idpf_ptp_release(struct idpf_adapter *adapter)
+{
+	struct idpf_ptp *ptp = adapter->ptp;
+
+	if (!ptp)
+		return;
+
+	if (ptp->tx_tstamp_access != IDPF_PTP_NONE &&
+	    ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+		idpf_ptp_release_tstamp(adapter);
+
+	if (ptp->clock) {
+		if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+			ptp_cancel_worker_sync(adapter->ptp->clock);
+
+		ptp_clock_unregister(ptp->clock);
+	}
+
+	kfree(ptp);
+	adapter->ptp = NULL;
+}
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.h b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
new file mode 100644
index 000000000000..785da03e4cf5
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
@@ -0,0 +1,379 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2024 Intel Corporation */
+
+#ifndef _IDPF_PTP_H
+#define _IDPF_PTP_H
+
+#include <linux/ptp_clock_kernel.h>
+
+/**
+ * struct idpf_ptp_cmd - PTP command masks
+ * @exec_cmd_mask: mask to trigger command execution
+ * @shtime_enable_mask: mask to enable shadow time
+ */
+struct idpf_ptp_cmd {
+	u32 exec_cmd_mask;
+	u32 shtime_enable_mask;
+};
+
+/* struct idpf_ptp_dev_clk_regs - PTP device registers
+ * @dev_clk_ns_l: low part of the device clock register
+ * @dev_clk_ns_h: high part of the device clock register
+ * @phy_clk_ns_l: low part of the PHY clock register
+ * @phy_clk_ns_h: high part of the PHY clock register
+ * @sys_time_ns_l: low part of the system time register
+ * @sys_time_ns_h: high part of the system time register
+ * @incval_l: low part of the increment value register
+ * @incval_h: high part of the increment value register
+ * @shadj_l: low part of the shadow adjust register
+ * @shadj_h: high part of the shadow adjust register
+ * @phy_incval_l: low part of the PHY increment value register
+ * @phy_incval_h: high part of the PHY increment value register
+ * @phy_shadj_l: low part of the PHY shadow adjust register
+ * @phy_shadj_h: high part of the PHY shadow adjust register
+ * @cmd: PTP command register
+ * @phy_cmd: PHY command register
+ * @cmd_sync: PTP command synchronization register
+ */
+struct idpf_ptp_dev_clk_regs {
+	/* Main clock */
+	void __iomem *dev_clk_ns_l;
+	void __iomem *dev_clk_ns_h;
+
+	/* PHY timer */
+	void __iomem *phy_clk_ns_l;
+	void __iomem *phy_clk_ns_h;
+
+	/* System time */
+	void __iomem *sys_time_ns_l;
+	void __iomem *sys_time_ns_h;
+
+	/* Main timer adjustments */
+	void __iomem *incval_l;
+	void __iomem *incval_h;
+	void __iomem *shadj_l;
+	void __iomem *shadj_h;
+
+	/* PHY timer adjustments */
+	void __iomem *phy_incval_l;
+	void __iomem *phy_incval_h;
+	void __iomem *phy_shadj_l;
+	void __iomem *phy_shadj_h;
+
+	/* Command */
+	void __iomem *cmd;
+	void __iomem *phy_cmd;
+	void __iomem *cmd_sync;
+};
+
+/**
+ * enum idpf_ptp_access - the type of access to PTP operations
+ * @IDPF_PTP_NONE: no access
+ * @IDPF_PTP_DIRECT: direct access through BAR registers
+ * @IDPF_PTP_MAILBOX: access through mailbox messages
+ */
+enum idpf_ptp_access {
+	IDPF_PTP_NONE = 0,
+	IDPF_PTP_DIRECT,
+	IDPF_PTP_MAILBOX,
+};
+
+/**
+ * struct idpf_ptp_secondary_mbx - PTP secondary mailbox
+ * @peer_mbx_q_id: PTP mailbox queue ID
+ * @peer_id: Peer ID for PTP Device Control daemon
+ * @valid: indicates whether secondary mailblox is supported by the Control
+ *	   Plane
+ */
+struct idpf_ptp_secondary_mbx {
+	u16 peer_mbx_q_id;
+	u16 peer_id;
+	bool valid:1;
+};
+
+/**
+ * enum idpf_ptp_tx_tstamp_state - Tx timestamp states
+ * @IDPF_PTP_FREE: Tx timestamp index free to use
+ * @IDPF_PTP_REQUEST: Tx timestamp index set to the Tx descriptor
+ * @IDPF_PTP_READ_VALUE: Tx timestamp value ready to be read
+ */
+enum idpf_ptp_tx_tstamp_state {
+	IDPF_PTP_FREE,
+	IDPF_PTP_REQUEST,
+	IDPF_PTP_READ_VALUE,
+};
+
+/**
+ * struct idpf_ptp_tx_tstamp_status - Parameters to track Tx timestamp
+ * @skb: the pointer to the SKB that received the completion tag
+ * @state: the state of the Tx timestamp
+ */
+struct idpf_ptp_tx_tstamp_status {
+	struct sk_buff *skb;
+	enum idpf_ptp_tx_tstamp_state state;
+};
+
+/**
+ * struct idpf_ptp_tx_tstamp - Parameters for Tx timestamping
+ * @list_member: the list member structure
+ * @tx_latch_reg_offset_l: Tx tstamp latch low register offset
+ * @tx_latch_reg_offset_h: Tx tstamp latch high register offset
+ * @skb: the pointer to the SKB for this timestamp request
+ * @tstamp: the Tx tstamp value
+ * @idx: the index of the Tx tstamp
+ */
+struct idpf_ptp_tx_tstamp {
+	struct list_head list_member;
+	u32 tx_latch_reg_offset_l;
+	u32 tx_latch_reg_offset_h;
+	struct sk_buff *skb;
+	u64 tstamp;
+	u32 idx;
+};
+
+/**
+ * struct idpf_ptp_vport_tx_tstamp_caps - Tx timestamp capabilities
+ * @vport_id: the vport id
+ * @num_entries: the number of negotiated Tx timestamp entries
+ * @tstamp_ns_lo_bit: first bit for nanosecond part of the timestamp
+ * @latches_lock: the lock to the lists of free/used timestamp indexes
+ * @status_lock: the lock to the status tracker
+ * @access: indicates an access to Tx timestamp
+ * @latches_free: the list of the free Tx timestamps latches
+ * @latches_in_use: the list of the used Tx timestamps latches
+ * @tx_tstamp_status: Tx tstamp status tracker
+ */
+struct idpf_ptp_vport_tx_tstamp_caps {
+	u32 vport_id;
+	u16 num_entries;
+	u16 tstamp_ns_lo_bit;
+	spinlock_t latches_lock;
+	spinlock_t status_lock;
+	bool access:1;
+	struct list_head latches_free;
+	struct list_head latches_in_use;
+	struct idpf_ptp_tx_tstamp_status tx_tstamp_status[];
+};
+
+/**
+ * struct idpf_ptp - PTP parameters
+ * @info: structure defining PTP hardware capabilities
+ * @clock: pointer to registered PTP clock device
+ * @adapter: back pointer to the adapter
+ * @base_incval: base increment value of the PTP clock
+ * @max_adj: maximum adjustment of the PTP clock
+ * @cmd: HW specific command masks
+ * @cached_phc_time: a cached copy of the PHC time for timestamp extension
+ * @cached_phc_jiffies: jiffies when cached_phc_time was last updated
+ * @dev_clk_regs: the set of registers to access the device clock
+ * @caps: PTP capabilities negotiated with the Control Plane
+ * @get_dev_clk_time_access: access type for getting the device clock time
+ * @get_cross_tstamp_access: access type for the cross timestamping
+ * @set_dev_clk_time_access: access type for setting the device clock time
+ * @adj_dev_clk_time_access: access type for the adjusting the device clock
+ * @tx_tstamp_access: access type for the Tx timestamp value read
+ * @rsv: reserved bits
+ * @secondary_mbx: parameters for using dedicated PTP mailbox
+ * @read_dev_clk_lock: spinlock protecting access to the device clock read
+ *		       operation executed by the HW latch
+ */
+struct idpf_ptp {
+	struct ptp_clock_info info;
+	struct ptp_clock *clock;
+	struct idpf_adapter *adapter;
+	u64 base_incval;
+	u64 max_adj;
+	struct idpf_ptp_cmd cmd;
+	u64 cached_phc_time;
+	unsigned long cached_phc_jiffies;
+	struct idpf_ptp_dev_clk_regs dev_clk_regs;
+	u32 caps;
+	enum idpf_ptp_access get_dev_clk_time_access:2;
+	enum idpf_ptp_access get_cross_tstamp_access:2;
+	enum idpf_ptp_access set_dev_clk_time_access:2;
+	enum idpf_ptp_access adj_dev_clk_time_access:2;
+	enum idpf_ptp_access tx_tstamp_access:2;
+	u8 rsv;
+	struct idpf_ptp_secondary_mbx secondary_mbx;
+	spinlock_t read_dev_clk_lock;
+};
+
+/**
+ * idpf_ptp_info_to_adapter - get driver adapter struct from ptp_clock_info
+ * @info: pointer to ptp_clock_info struct
+ *
+ * Return: pointer to the corresponding adapter struct
+ */
+static inline struct idpf_adapter *
+idpf_ptp_info_to_adapter(const struct ptp_clock_info *info)
+{
+	const struct idpf_ptp *ptp = container_of_const(info, struct idpf_ptp,
+							info);
+	return ptp->adapter;
+}
+
+/**
+ * struct idpf_ptp_dev_timers - System time and device time values
+ * @sys_time_ns: system time value expressed in nanoseconds
+ * @dev_clk_time_ns: device clock time value expressed in nanoseconds
+ */
+struct idpf_ptp_dev_timers {
+	u64 sys_time_ns;
+	u64 dev_clk_time_ns;
+};
+
+/**
+ * idpf_ptp_is_vport_tx_tstamp_ena - Verify the Tx timestamping enablement for
+ *				     a given vport.
+ * @vport: Virtual port structure
+ *
+ * Tx timestamp capabilities are negotiated with the Control Plane only if the
+ * device clock value can be read, Tx timestamp access type is different than
+ * NONE, and the PTP clock for the adapter is created. When all those conditions
+ * are satisfied, Tx timestamp feature is enabled and tx_tstamp_caps is
+ * allocated and fulfilled.
+ *
+ * Return: true if the Tx timestamping is enabled, false otherwise.
+ */
+static inline bool idpf_ptp_is_vport_tx_tstamp_ena(struct idpf_vport *vport)
+{
+	if (!vport->tx_tstamp_caps)
+		return false;
+	else
+		return true;
+}
+
+/**
+ * idpf_ptp_is_vport_rx_tstamp_ena - Verify the Rx timestamping enablement for
+ *				     a given vport.
+ * @vport: Virtual port structure
+ *
+ * Rx timestamp feature is enabled if the PTP clock for the adapter is created
+ * and it is possible to read the value of the device clock. The second
+ * assumption comes from the need to extend the Rx timestamp value to 64 bit
+ * based on the current device clock time.
+ *
+ * Return: true if the Rx timestamping is enabled, false otherwise.
+ */
+static inline bool idpf_ptp_is_vport_rx_tstamp_ena(struct idpf_vport *vport)
+{
+	if (!vport->adapter->ptp ||
+	    vport->adapter->ptp->get_dev_clk_time_access == IDPF_PTP_NONE)
+		return false;
+	else
+		return true;
+}
+
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+int idpf_ptp_init(struct idpf_adapter *adapter);
+void idpf_ptp_release(struct idpf_adapter *adapter);
+int idpf_ptp_get_caps(struct idpf_adapter *adapter);
+void idpf_ptp_get_features_access(const struct idpf_adapter *adapter);
+bool idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq);
+int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
+			      struct idpf_ptp_dev_timers *dev_clk_time);
+int idpf_ptp_get_cross_time(struct idpf_adapter *adapter,
+			    struct idpf_ptp_dev_timers *cross_time);
+int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time);
+int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval);
+int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, s64 delta);
+int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport);
+int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport);
+int idpf_ptp_set_timestamp_mode(struct idpf_vport *vport,
+				struct kernel_hwtstamp_config *config);
+u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u64 in_tstamp);
+u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time, u32 in_timestamp);
+int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			u32 *idx);
+void idpf_tstamp_task(struct work_struct *work);
+#else /* CONFIG_PTP_1588_CLOCK */
+static inline int idpf_ptp_init(struct idpf_adapter *adapter)
+{
+	return 0;
+}
+
+static inline void idpf_ptp_release(struct idpf_adapter *adapter) { }
+
+static inline int idpf_ptp_get_caps(struct idpf_adapter *adapter)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void
+idpf_ptp_get_features_access(const struct idpf_adapter *adapter) { }
+
+static inline bool
+idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq)
+{
+	return false;
+}
+
+static inline int
+idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
+			  struct idpf_ptp_dev_timers *dev_clk_time)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+idpf_ptp_get_cross_time(struct idpf_adapter *adapter,
+			struct idpf_ptp_dev_timers *cross_time)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter,
+					    u64 time)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter,
+					    u64 incval)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter,
+					    s64 delta)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+idpf_ptp_set_timestamp_mode(struct idpf_vport *vport,
+			    struct kernel_hwtstamp_config *config)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u32 in_tstamp)
+{
+	return 0;
+}
+
+static inline u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time,
+						    u32 in_timestamp)
+{
+	return 0;
+}
+
+static inline int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q,
+				      struct sk_buff *skb, u32 *idx)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void idpf_tstamp_task(struct work_struct *work) { }
+#endif /* CONFIG_PTP_1588_CLOCK */
+#endif /* _IDPF_PTP_H */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index dfd7cf1d9aa0..e3ddf18dcbf5 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -1,8 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (C) 2023 Intel Corporation */
 
-#include <net/libeth/rx.h>
-#include <net/libeth/tx.h>
+#include <net/libeth/xdp.h>
 
 #include "idpf.h"
 
@@ -180,6 +179,58 @@ static int idpf_tx_singleq_csum(struct sk_buff *skb,
 }
 
 /**
+ * idpf_tx_singleq_dma_map_error - handle TX DMA map errors
+ * @txq: queue to send buffer on
+ * @skb: send buffer
+ * @first: original first buffer info buffer for packet
+ * @idx: starting point on ring to unwind
+ */
+static void idpf_tx_singleq_dma_map_error(struct idpf_tx_queue *txq,
+					  struct sk_buff *skb,
+					  struct idpf_tx_buf *first, u16 idx)
+{
+	struct libeth_sq_napi_stats ss = { };
+	struct libeth_cq_pp cp = {
+		.dev	= txq->dev,
+		.ss	= &ss,
+	};
+
+	u64_stats_update_begin(&txq->stats_sync);
+	u64_stats_inc(&txq->q_stats.dma_map_errs);
+	u64_stats_update_end(&txq->stats_sync);
+
+	/* clear dma mappings for failed tx_buf map */
+	for (;;) {
+		struct idpf_tx_buf *tx_buf;
+
+		tx_buf = &txq->tx_buf[idx];
+		libeth_tx_complete(tx_buf, &cp);
+		if (tx_buf == first)
+			break;
+		if (idx == 0)
+			idx = txq->desc_count;
+		idx--;
+	}
+
+	if (skb_is_gso(skb)) {
+		union idpf_tx_flex_desc *tx_desc;
+
+		/* If we failed a DMA mapping for a TSO packet, we will have
+		 * used one additional descriptor for a context
+		 * descriptor. Reset that here.
+		 */
+		tx_desc = &txq->flex_tx[idx];
+		memset(tx_desc, 0, sizeof(*tx_desc));
+		if (idx == 0)
+			idx = txq->desc_count;
+		idx--;
+	}
+
+	/* Update tail in case netdev_xmit_more was previously true */
+	idpf_tx_buf_hw_update(txq, idx, false);
+}
+
+/**
  * idpf_tx_singleq_map - Build the Tx base descriptor
  * @tx_q: queue to send buffer on
  * @first: first buffer info buffer to use
@@ -219,8 +270,9 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
 		unsigned int max_data = IDPF_TX_MAX_DESC_DATA_ALIGNED;
 
-		if (dma_mapping_error(tx_q->dev, dma))
-			return idpf_tx_dma_map_error(tx_q, skb, first, i);
+		if (unlikely(dma_mapping_error(tx_q->dev, dma)))
+			return idpf_tx_singleq_dma_map_error(tx_q, skb,
+							     first, i);
 
 		/* record length, and DMA address */
 		dma_unmap_len_set(tx_buf, len, size);
@@ -362,17 +414,18 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 {
 	struct idpf_tx_offload_params offload = { };
 	struct idpf_tx_buf *first;
-	unsigned int count;
+	u32 count, buf_count = 1;
+	int csum, tso, needed;
 	__be16 protocol;
-	int csum, tso;
 
-	count = idpf_tx_desc_count_required(tx_q, skb);
+	count = idpf_tx_res_count_required(tx_q, skb, &buf_count);
 	if (unlikely(!count))
 		return idpf_tx_drop_skb(tx_q, skb);
 
-	if (idpf_tx_maybe_stop_common(tx_q,
-				      count + IDPF_TX_DESCS_PER_CACHE_LINE +
-				      IDPF_TX_DESCS_FOR_CTX)) {
+	needed = count + IDPF_TX_DESCS_PER_CACHE_LINE + IDPF_TX_DESCS_FOR_CTX;
+	if (!netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
+				       IDPF_DESC_UNUSED(tx_q),
+				       needed, needed)) {
 		idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false);
 
 		u64_stats_update_begin(&tx_q->stats_sync);
@@ -517,7 +570,7 @@ fetch_next_txq_desc:
 	np = netdev_priv(tx_q->netdev);
 	nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
 
-	dont_wake = np->state != __IDPF_VPORT_UP ||
+	dont_wake = !test_bit(IDPF_VPORT_UP, np->state) ||
 		    !netif_carrier_ok(tx_q->netdev);
 	__netif_txq_completed_wake(nq, ss.packets, ss.bytes,
 				   IDPF_DESC_UNUSED(tx_q), IDPF_TX_WAKE_THRESH,
@@ -595,13 +648,13 @@ static bool idpf_rx_singleq_is_non_eop(const union virtchnl2_rx_desc *rx_desc)
  */
 static void idpf_rx_singleq_csum(struct idpf_rx_queue *rxq,
 				 struct sk_buff *skb,
-				 struct idpf_rx_csum_decoded csum_bits,
+				 struct libeth_rx_csum csum_bits,
 				 struct libeth_rx_pt decoded)
 {
 	bool ipv4, ipv6;
 
 	/* check if Rx checksum is enabled */
-	if (!libeth_rx_pt_has_checksum(rxq->netdev, decoded))
+	if (!libeth_rx_pt_has_checksum(rxq->xdp_rxq.dev, decoded))
 		return;
 
 	/* check if HW has decoded the packet and checksum */
@@ -661,10 +714,10 @@ checksum_fail:
  *
  * Return: parsed checksum status.
  **/
-static struct idpf_rx_csum_decoded
+static struct libeth_rx_csum
 idpf_rx_singleq_base_csum(const union virtchnl2_rx_desc *rx_desc)
 {
-	struct idpf_rx_csum_decoded csum_bits = { };
+	struct libeth_rx_csum csum_bits = { };
 	u32 rx_error, rx_status;
 	u64 qword;
 
@@ -696,10 +749,10 @@ idpf_rx_singleq_base_csum(const union virtchnl2_rx_desc *rx_desc)
  *
  * Return: parsed checksum status.
  **/
-static struct idpf_rx_csum_decoded
+static struct libeth_rx_csum
 idpf_rx_singleq_flex_csum(const union virtchnl2_rx_desc *rx_desc)
 {
-	struct idpf_rx_csum_decoded csum_bits = { };
+	struct libeth_rx_csum csum_bits = { };
 	u16 rx_status0, rx_status1;
 
 	rx_status0 = le16_to_cpu(rx_desc->flex_nic_wb.status_error0);
@@ -740,7 +793,7 @@ static void idpf_rx_singleq_base_hash(struct idpf_rx_queue *rx_q,
 {
 	u64 mask, qw1;
 
-	if (!libeth_rx_pt_has_hash(rx_q->netdev, decoded))
+	if (!libeth_rx_pt_has_hash(rx_q->xdp_rxq.dev, decoded))
 		return;
 
 	mask = VIRTCHNL2_RX_BASE_DESC_FLTSTAT_RSS_HASH_M;
@@ -768,7 +821,7 @@ static void idpf_rx_singleq_flex_hash(struct idpf_rx_queue *rx_q,
 				      const union virtchnl2_rx_desc *rx_desc,
 				      struct libeth_rx_pt decoded)
 {
-	if (!libeth_rx_pt_has_hash(rx_q->netdev, decoded))
+	if (!libeth_rx_pt_has_hash(rx_q->xdp_rxq.dev, decoded))
 		return;
 
 	if (FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_STATUS0_RSS_VALID_M,
@@ -780,7 +833,7 @@ static void idpf_rx_singleq_flex_hash(struct idpf_rx_queue *rx_q,
 }
 
 /**
- * idpf_rx_singleq_process_skb_fields - Populate skb header fields from Rx
+ * __idpf_rx_singleq_process_skb_fields - Populate skb header fields from Rx
  * descriptor
  * @rx_q: Rx ring being processed
  * @skb: pointer to current skb being populated
@@ -792,16 +845,13 @@ static void idpf_rx_singleq_flex_hash(struct idpf_rx_queue *rx_q,
  * other fields within the skb.
  */
 static void
-idpf_rx_singleq_process_skb_fields(struct idpf_rx_queue *rx_q,
-				   struct sk_buff *skb,
-				   const union virtchnl2_rx_desc *rx_desc,
-				   u16 ptype)
+__idpf_rx_singleq_process_skb_fields(struct idpf_rx_queue *rx_q,
+				     struct sk_buff *skb,
+				     const union virtchnl2_rx_desc *rx_desc,
+				     u16 ptype)
 {
 	struct libeth_rx_pt decoded = rx_q->rx_ptype_lkup[ptype];
-	struct idpf_rx_csum_decoded csum_bits;
-
-	/* modifies the skb - consumes the enet header */
-	skb->protocol = eth_type_trans(skb, rx_q->netdev);
+	struct libeth_rx_csum csum_bits;
 
 	/* Check if we're using base mode descriptor IDs */
 	if (rx_q->rxdids == VIRTCHNL2_RXDID_1_32B_BASE_M) {
@@ -813,7 +863,6 @@ idpf_rx_singleq_process_skb_fields(struct idpf_rx_queue *rx_q,
 	}
 
 	idpf_rx_singleq_csum(rx_q, skb, csum_bits, decoded);
-	skb_record_rx_queue(skb, rx_q->idx);
 }
 
 /**
@@ -900,14 +949,14 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rx_q,
  */
 static void
 idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc,
-				    struct idpf_rx_extracted *fields)
+				    struct libeth_rqe_info *fields)
 {
 	u64 qword;
 
 	qword = le64_to_cpu(rx_desc->base_wb.qword1.status_error_ptype_len);
 
-	fields->size = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M, qword);
-	fields->rx_ptype = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M, qword);
+	fields->len = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M, qword);
+	fields->ptype = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M, qword);
 }
 
 /**
@@ -923,12 +972,12 @@ idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc,
  */
 static void
 idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc,
-				    struct idpf_rx_extracted *fields)
+				    struct libeth_rqe_info *fields)
 {
-	fields->size = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M,
-				 le16_to_cpu(rx_desc->flex_nic_wb.pkt_len));
-	fields->rx_ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M,
-				     le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0));
+	fields->len = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M,
+				le16_to_cpu(rx_desc->flex_nic_wb.pkt_len));
+	fields->ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M,
+				  le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0));
 }
 
 /**
@@ -941,7 +990,7 @@ idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc,
 static void
 idpf_rx_singleq_extract_fields(const struct idpf_rx_queue *rx_q,
 			       const union virtchnl2_rx_desc *rx_desc,
-			       struct idpf_rx_extracted *fields)
+			       struct libeth_rqe_info *fields)
 {
 	if (rx_q->rxdids == VIRTCHNL2_RXDID_1_32B_BASE_M)
 		idpf_rx_singleq_extract_base_fields(rx_desc, fields);
@@ -949,6 +998,32 @@ idpf_rx_singleq_extract_fields(const struct idpf_rx_queue *rx_q,
 		idpf_rx_singleq_extract_flex_fields(rx_desc, fields);
 }
 
+static bool
+idpf_rx_singleq_process_skb_fields(struct sk_buff *skb,
+				   const struct libeth_xdp_buff *xdp,
+				   struct libeth_rq_napi_stats *rs)
+{
+	struct libeth_rqe_info fields;
+	struct idpf_rx_queue *rxq;
+
+	rxq = libeth_xdp_buff_to_rq(xdp, typeof(*rxq), xdp_rxq);
+
+	idpf_rx_singleq_extract_fields(rxq, xdp->desc, &fields);
+	__idpf_rx_singleq_process_skb_fields(rxq, skb, xdp->desc,
+					     fields.ptype);
+
+	return true;
+}
+
+static void idpf_xdp_run_pass(struct libeth_xdp_buff *xdp,
+			      struct napi_struct *napi,
+			      struct libeth_rq_napi_stats *rs,
+			      const union virtchnl2_rx_desc *desc)
+{
+	libeth_xdp_run_pass(xdp, NULL, napi, rs, desc, NULL,
+			    idpf_rx_singleq_process_skb_fields);
+}
+
 /**
  * idpf_rx_singleq_clean - Reclaim resources after receive completes
  * @rx_q: rx queue to clean
@@ -958,15 +1033,16 @@ idpf_rx_singleq_extract_fields(const struct idpf_rx_queue *rx_q,
  */
 static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget)
 {
-	unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
-	struct sk_buff *skb = rx_q->skb;
+	struct libeth_rq_napi_stats rs = { };
 	u16 ntc = rx_q->next_to_clean;
+	LIBETH_XDP_ONSTACK_BUFF(xdp);
 	u16 cleaned_count = 0;
-	bool failure = false;
+
+	libeth_xdp_init_buff(xdp, &rx_q->xdp, &rx_q->xdp_rxq);
 
 	/* Process Rx packets bounded by budget */
-	while (likely(total_rx_pkts < (unsigned int)budget)) {
-		struct idpf_rx_extracted fields = { };
+	while (likely(rs.packets < budget)) {
+		struct libeth_rqe_info fields = { };
 		union virtchnl2_rx_desc *rx_desc;
 		struct idpf_rx_buf *rx_buf;
 
@@ -992,73 +1068,41 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget)
 		idpf_rx_singleq_extract_fields(rx_q, rx_desc, &fields);
 
 		rx_buf = &rx_q->rx_buf[ntc];
-		if (!libeth_rx_sync_for_cpu(rx_buf, fields.size))
-			goto skip_data;
-
-		if (skb)
-			idpf_rx_add_frag(rx_buf, skb, fields.size);
-		else
-			skb = idpf_rx_build_skb(rx_buf, fields.size);
-
-		/* exit if we failed to retrieve a buffer */
-		if (!skb)
-			break;
-
-skip_data:
-		rx_buf->page = NULL;
+		libeth_xdp_process_buff(xdp, rx_buf, fields.len);
+		rx_buf->netmem = 0;
 
 		IDPF_SINGLEQ_BUMP_RING_IDX(rx_q, ntc);
 		cleaned_count++;
 
 		/* skip if it is non EOP desc */
-		if (idpf_rx_singleq_is_non_eop(rx_desc) || unlikely(!skb))
+		if (idpf_rx_singleq_is_non_eop(rx_desc) ||
+		    unlikely(!xdp->data))
 			continue;
 
 #define IDPF_RXD_ERR_S FIELD_PREP(VIRTCHNL2_RX_BASE_DESC_QW1_ERROR_M, \
 				  VIRTCHNL2_RX_BASE_DESC_ERROR_RXE_M)
 		if (unlikely(idpf_rx_singleq_test_staterr(rx_desc,
 							  IDPF_RXD_ERR_S))) {
-			dev_kfree_skb_any(skb);
-			skb = NULL;
+			libeth_xdp_return_buff_slow(xdp);
 			continue;
 		}
 
-		/* pad skb if needed (to make valid ethernet frame) */
-		if (eth_skb_pad(skb)) {
-			skb = NULL;
-			continue;
-		}
-
-		/* probably a little skewed due to removing CRC */
-		total_rx_bytes += skb->len;
-
-		/* protocol */
-		idpf_rx_singleq_process_skb_fields(rx_q, skb,
-						   rx_desc, fields.rx_ptype);
-
-		/* send completed skb up the stack */
-		napi_gro_receive(rx_q->pp->p.napi, skb);
-		skb = NULL;
-
-		/* update budget accounting */
-		total_rx_pkts++;
+		idpf_xdp_run_pass(xdp, rx_q->pp->p.napi, &rs, rx_desc);
 	}
 
-	rx_q->skb = skb;
-
 	rx_q->next_to_clean = ntc;
+	libeth_xdp_save_buff(&rx_q->xdp, xdp);
 
 	page_pool_nid_changed(rx_q->pp, numa_mem_id());
 	if (cleaned_count)
-		failure = idpf_rx_singleq_buf_hw_alloc_all(rx_q, cleaned_count);
+		idpf_rx_singleq_buf_hw_alloc_all(rx_q, cleaned_count);
 
 	u64_stats_update_begin(&rx_q->stats_sync);
-	u64_stats_add(&rx_q->q_stats.packets, total_rx_pkts);
-	u64_stats_add(&rx_q->q_stats.bytes, total_rx_bytes);
+	u64_stats_add(&rx_q->q_stats.packets, rs.packets);
+	u64_stats_add(&rx_q->q_stats.bytes, rs.bytes);
 	u64_stats_update_end(&rx_q->stats_sync);
 
-	/* guarantee a trip back through this routine if there was a failure */
-	return failure ? budget : (int)total_rx_pkts;
+	return rs.packets;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 2fa9c36e33c9..1d91c56f7469 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -1,51 +1,36 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (C) 2023 Intel Corporation */
 
-#include <net/libeth/rx.h>
-#include <net/libeth/tx.h>
-
 #include "idpf.h"
+#include "idpf_ptp.h"
 #include "idpf_virtchnl.h"
+#include "xdp.h"
+#include "xsk.h"
 
-struct idpf_tx_stash {
-	struct hlist_node hlist;
-	struct libeth_sqe buf;
-};
-
-#define idpf_tx_buf_compl_tag(buf)	(*(u32 *)&(buf)->priv)
+#define idpf_tx_buf_next(buf)		(*(u32 *)&(buf)->priv)
 LIBETH_SQE_CHECK_PRIV(u32);
 
-static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
-			       unsigned int count);
-
 /**
- * idpf_buf_lifo_push - push a buffer pointer onto stack
- * @stack: pointer to stack struct
- * @buf: pointer to buf to push
+ * idpf_chk_linearize - Check if skb exceeds max descriptors per packet
+ * @skb: send buffer
+ * @max_bufs: maximum scatter gather buffers for single packet
+ * @count: number of buffers this packet needs
  *
- * Returns 0 on success, negative on failure
- **/
-static int idpf_buf_lifo_push(struct idpf_buf_lifo *stack,
-			      struct idpf_tx_stash *buf)
+ * Make sure we don't exceed maximum scatter gather buffers for a single
+ * packet.
+ * TSO case has been handled earlier from idpf_features_check().
+ */
+static bool idpf_chk_linearize(const struct sk_buff *skb,
+			       unsigned int max_bufs,
+			       unsigned int count)
 {
-	if (unlikely(stack->top == stack->size))
-		return -ENOSPC;
-
-	stack->bufs[stack->top++] = buf;
-
-	return 0;
-}
+	if (likely(count <= max_bufs))
+		return false;
 
-/**
- * idpf_buf_lifo_pop - pop a buffer pointer from stack
- * @stack: pointer to stack struct
- **/
-static struct idpf_tx_stash *idpf_buf_lifo_pop(struct idpf_buf_lifo *stack)
-{
-	if (unlikely(!stack->top))
-		return NULL;
+	if (skb_is_gso(skb))
+		return false;
 
-	return stack->bufs[--stack->top];
+	return true;
 }
 
 /**
@@ -69,59 +54,42 @@ void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	}
 }
 
-/**
- * idpf_tx_buf_rel_all - Free any empty Tx buffers
- * @txq: queue to be cleaned
- */
-static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
+static void idpf_tx_buf_clean(struct idpf_tx_queue *txq)
 {
 	struct libeth_sq_napi_stats ss = { };
-	struct idpf_buf_lifo *buf_stack;
-	struct idpf_tx_stash *stash;
+	struct xdp_frame_bulk bq;
 	struct libeth_cq_pp cp = {
 		.dev	= txq->dev,
+		.bq	= &bq,
 		.ss	= &ss,
 	};
-	struct hlist_node *tmp;
-	u32 i, tag;
 
-	/* Buffers already cleared, nothing to do */
-	if (!txq->tx_buf)
-		return;
+	xdp_frame_bulk_init(&bq);
 
 	/* Free all the Tx buffer sk_buffs */
-	for (i = 0; i < txq->desc_count; i++)
-		libeth_tx_complete(&txq->tx_buf[i], &cp);
+	for (u32 i = 0; i < txq->buf_pool_size; i++)
+		libeth_tx_complete_any(&txq->tx_buf[i], &cp);
 
-	kfree(txq->tx_buf);
-	txq->tx_buf = NULL;
-
-	if (!idpf_queue_has(FLOW_SCH_EN, txq))
-		return;
+	xdp_flush_frame_bulk(&bq);
+}
 
-	buf_stack = &txq->stash->buf_stack;
-	if (!buf_stack->bufs)
+/**
+ * idpf_tx_buf_rel_all - Free any empty Tx buffers
+ * @txq: queue to be cleaned
+ */
+static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
+{
+	/* Buffers already cleared, nothing to do */
+	if (!txq->tx_buf)
 		return;
 
-	/*
-	 * If a Tx timeout occurred, there are potentially still bufs in the
-	 * hash table, free them here.
-	 */
-	hash_for_each_safe(txq->stash->sched_buf_hash, tag, tmp, stash,
-			   hlist) {
-		if (!stash)
-			continue;
-
-		libeth_tx_complete(&stash->buf, &cp);
-		hash_del(&stash->hlist);
-		idpf_buf_lifo_push(buf_stack, stash);
-	}
-
-	for (i = 0; i < buf_stack->size; i++)
-		kfree(buf_stack->bufs[i]);
+	if (idpf_queue_has(XSK, txq))
+		idpf_xsksq_clean(txq);
+	else
+		idpf_tx_buf_clean(txq);
 
-	kfree(buf_stack->bufs);
-	buf_stack->bufs = NULL;
+	kfree(txq->tx_buf);
+	txq->tx_buf = NULL;
 }
 
 /**
@@ -132,12 +100,24 @@ static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
  */
 static void idpf_tx_desc_rel(struct idpf_tx_queue *txq)
 {
+	bool xdp = idpf_queue_has(XDP, txq);
+
+	if (xdp)
+		libeth_xdpsq_deinit_timer(txq->timer);
+
 	idpf_tx_buf_rel_all(txq);
-	netdev_tx_reset_subqueue(txq->netdev, txq->idx);
+
+	if (!xdp)
+		netdev_tx_reset_subqueue(txq->netdev, txq->idx);
+
+	idpf_xsk_clear_queue(txq, VIRTCHNL2_QUEUE_TYPE_TX);
 
 	if (!txq->desc_ring)
 		return;
 
+	if (!xdp && txq->refillq)
+		kfree(txq->refillq->ring);
+
 	dmam_free_coherent(txq->dev, txq->size, txq->desc_ring, txq->dma);
 	txq->desc_ring = NULL;
 	txq->next_to_use = 0;
@@ -152,12 +132,14 @@ static void idpf_tx_desc_rel(struct idpf_tx_queue *txq)
  */
 static void idpf_compl_desc_rel(struct idpf_compl_queue *complq)
 {
-	if (!complq->comp)
+	idpf_xsk_clear_queue(complq, VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION);
+
+	if (!complq->desc_ring)
 		return;
 
 	dma_free_coherent(complq->netdev->dev.parent, complq->size,
-			  complq->comp, complq->dma);
-	complq->comp = NULL;
+			  complq->desc_ring, complq->dma);
+	complq->desc_ring = NULL;
 	complq->next_to_use = 0;
 	complq->next_to_clean = 0;
 }
@@ -194,41 +176,18 @@ static void idpf_tx_desc_rel_all(struct idpf_vport *vport)
  */
 static int idpf_tx_buf_alloc_all(struct idpf_tx_queue *tx_q)
 {
-	struct idpf_buf_lifo *buf_stack;
-	int buf_size;
-	int i;
-
 	/* Allocate book keeping buffers only. Buffers to be supplied to HW
 	 * are allocated by kernel network stack and received as part of skb
 	 */
-	buf_size = sizeof(struct idpf_tx_buf) * tx_q->desc_count;
-	tx_q->tx_buf = kzalloc(buf_size, GFP_KERNEL);
+	if (idpf_queue_has(FLOW_SCH_EN, tx_q))
+		tx_q->buf_pool_size = U16_MAX;
+	else
+		tx_q->buf_pool_size = tx_q->desc_count;
+	tx_q->tx_buf = kcalloc(tx_q->buf_pool_size, sizeof(*tx_q->tx_buf),
+			       GFP_KERNEL);
 	if (!tx_q->tx_buf)
 		return -ENOMEM;
 
-	if (!idpf_queue_has(FLOW_SCH_EN, tx_q))
-		return 0;
-
-	buf_stack = &tx_q->stash->buf_stack;
-
-	/* Initialize tx buf stack for out-of-order completions if
-	 * flow scheduling offload is enabled
-	 */
-	buf_stack->bufs = kcalloc(tx_q->desc_count, sizeof(*buf_stack->bufs),
-				  GFP_KERNEL);
-	if (!buf_stack->bufs)
-		return -ENOMEM;
-
-	buf_stack->size = tx_q->desc_count;
-	buf_stack->top = tx_q->desc_count;
-
-	for (i = 0; i < tx_q->desc_count; i++) {
-		buf_stack->bufs[i] = kzalloc(sizeof(*buf_stack->bufs[i]),
-					     GFP_KERNEL);
-		if (!buf_stack->bufs[i])
-			return -ENOMEM;
-	}
-
 	return 0;
 }
 
@@ -243,6 +202,7 @@ static int idpf_tx_desc_alloc(const struct idpf_vport *vport,
 			      struct idpf_tx_queue *tx_q)
 {
 	struct device *dev = tx_q->dev;
+	struct idpf_sw_queue *refillq;
 	int err;
 
 	err = idpf_tx_buf_alloc_all(tx_q);
@@ -266,6 +226,33 @@ static int idpf_tx_desc_alloc(const struct idpf_vport *vport,
 	tx_q->next_to_clean = 0;
 	idpf_queue_set(GEN_CHK, tx_q);
 
+	idpf_xsk_setup_queue(vport, tx_q, VIRTCHNL2_QUEUE_TYPE_TX);
+
+	if (!idpf_queue_has(FLOW_SCH_EN, tx_q))
+		return 0;
+
+	refillq = tx_q->refillq;
+	refillq->desc_count = tx_q->buf_pool_size;
+	refillq->ring = kcalloc(refillq->desc_count, sizeof(u32),
+				GFP_KERNEL);
+	if (!refillq->ring) {
+		err = -ENOMEM;
+		goto err_alloc;
+	}
+
+	for (unsigned int i = 0; i < refillq->desc_count; i++)
+		refillq->ring[i] =
+			FIELD_PREP(IDPF_RFL_BI_BUFID_M, i) |
+			FIELD_PREP(IDPF_RFL_BI_GEN_M,
+				   idpf_queue_has(GEN_CHK, refillq));
+
+	/* Go ahead and flip the GEN bit since this counts as filling
+	 * up the ring, i.e. we already ring wrapped.
+	 */
+	idpf_queue_change(GEN_CHK, refillq);
+
+	tx_q->last_re = tx_q->desc_count - IDPF_TX_SPLITQ_RE_MIN_GAP;
+
 	return 0;
 
 err_alloc:
@@ -284,18 +271,25 @@ err_alloc:
 static int idpf_compl_desc_alloc(const struct idpf_vport *vport,
 				 struct idpf_compl_queue *complq)
 {
-	complq->size = array_size(complq->desc_count, sizeof(*complq->comp));
+	u32 desc_size;
 
-	complq->comp = dma_alloc_coherent(complq->netdev->dev.parent,
-					  complq->size, &complq->dma,
-					  GFP_KERNEL);
-	if (!complq->comp)
+	desc_size = idpf_queue_has(FLOW_SCH_EN, complq) ?
+		    sizeof(*complq->comp) : sizeof(*complq->comp_4b);
+	complq->size = array_size(complq->desc_count, desc_size);
+
+	complq->desc_ring = dma_alloc_coherent(complq->netdev->dev.parent,
+					       complq->size, &complq->dma,
+					       GFP_KERNEL);
+	if (!complq->desc_ring)
 		return -ENOMEM;
 
 	complq->next_to_use = 0;
 	complq->next_to_clean = 0;
 	idpf_queue_set(GEN_CHK, complq);
 
+	idpf_xsk_setup_queue(vport, complq,
+			     VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION);
+
 	return 0;
 }
 
@@ -316,8 +310,6 @@ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport)
 	for (i = 0; i < vport->num_txq_grp; i++) {
 		for (j = 0; j < vport->txq_grps[i].num_txq; j++) {
 			struct idpf_tx_queue *txq = vport->txq_grps[i].txqs[j];
-			u8 gen_bits = 0;
-			u16 bufidx_mask;
 
 			err = idpf_tx_desc_alloc(vport, txq);
 			if (err) {
@@ -326,34 +318,6 @@ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport)
 					i);
 				goto err_out;
 			}
-
-			if (!idpf_is_queue_model_split(vport->txq_model))
-				continue;
-
-			txq->compl_tag_cur_gen = 0;
-
-			/* Determine the number of bits in the bufid
-			 * mask and add one to get the start of the
-			 * generation bits
-			 */
-			bufidx_mask = txq->desc_count - 1;
-			while (bufidx_mask >> 1) {
-				txq->compl_tag_gen_s++;
-				bufidx_mask = bufidx_mask >> 1;
-			}
-			txq->compl_tag_gen_s++;
-
-			gen_bits = IDPF_TX_SPLITQ_COMPL_TAG_WIDTH -
-							txq->compl_tag_gen_s;
-			txq->compl_tag_gen_max = GETMAXVAL(gen_bits);
-
-			/* Set bufid mask based on location of first
-			 * gen bit; it cannot simply be the descriptor
-			 * ring size-1 since we can have size values
-			 * where not all of those bits are set.
-			 */
-			txq->compl_tag_bufid_m =
-				GETMAXVAL(txq->compl_tag_gen_s);
 		}
 
 		if (!idpf_is_queue_model_split(vport->txq_model))
@@ -382,12 +346,12 @@ err_out:
  */
 static void idpf_rx_page_rel(struct libeth_fqe *rx_buf)
 {
-	if (unlikely(!rx_buf->page))
+	if (unlikely(!rx_buf->netmem))
 		return;
 
-	page_pool_put_full_page(rx_buf->page->pp, rx_buf->page, false);
+	libeth_rx_recycle_slow(rx_buf->netmem);
 
-	rx_buf->page = NULL;
+	rx_buf->netmem = 0;
 	rx_buf->offset = 0;
 }
 
@@ -425,6 +389,11 @@ static void idpf_rx_buf_rel_bufq(struct idpf_buf_queue *bufq)
 	if (!bufq->buf)
 		return;
 
+	if (idpf_queue_has(XSK, bufq)) {
+		idpf_xskfq_rel(bufq);
+		return;
+	}
+
 	/* Free all the bufs allocated and given to hw on Rx queue */
 	for (u32 i = 0; i < bufq->desc_count; i++)
 		idpf_rx_page_rel(&bufq->buf[i]);
@@ -473,14 +442,14 @@ static void idpf_rx_desc_rel(struct idpf_rx_queue *rxq, struct device *dev,
 	if (!rxq)
 		return;
 
-	if (rxq->skb) {
-		dev_kfree_skb_any(rxq->skb);
-		rxq->skb = NULL;
-	}
+	if (!idpf_queue_has(XSK, rxq))
+		libeth_xdp_return_stash(&rxq->xdp);
 
 	if (!idpf_is_queue_model_split(model))
 		idpf_rx_buf_rel_all(rxq);
 
+	idpf_xsk_clear_queue(rxq, VIRTCHNL2_QUEUE_TYPE_RX);
+
 	rxq->next_to_alloc = 0;
 	rxq->next_to_clean = 0;
 	rxq->next_to_use = 0;
@@ -503,6 +472,7 @@ static void idpf_rx_desc_rel_bufq(struct idpf_buf_queue *bufq,
 		return;
 
 	idpf_rx_buf_rel_bufq(bufq);
+	idpf_xsk_clear_queue(bufq, VIRTCHNL2_QUEUE_TYPE_RX_BUFFER);
 
 	bufq->next_to_alloc = 0;
 	bufq->next_to_clean = 0;
@@ -585,6 +555,7 @@ static int idpf_rx_hdr_buf_alloc_all(struct idpf_buf_queue *bufq)
 	struct libeth_fq fq = {
 		.count	= bufq->desc_count,
 		.type	= LIBETH_FQE_HDR,
+		.xdp	= idpf_xdp_enabled(bufq->q_vector->vport),
 		.nid	= idpf_q_vector_to_mem(bufq->q_vector),
 	};
 	int ret;
@@ -602,18 +573,18 @@ static int idpf_rx_hdr_buf_alloc_all(struct idpf_buf_queue *bufq)
 }
 
 /**
- * idpf_rx_post_buf_refill - Post buffer id to refill queue
+ * idpf_post_buf_refill - Post buffer id to refill queue
  * @refillq: refill queue to post to
  * @buf_id: buffer id to post
  */
-static void idpf_rx_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id)
+static void idpf_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id)
 {
 	u32 nta = refillq->next_to_use;
 
 	/* store the buffer ID and the SW maintained GEN bit to the refillq */
 	refillq->ring[nta] =
-		FIELD_PREP(IDPF_RX_BI_BUFID_M, buf_id) |
-		FIELD_PREP(IDPF_RX_BI_GEN_M,
+		FIELD_PREP(IDPF_RFL_BI_BUFID_M, buf_id) |
+		FIELD_PREP(IDPF_RFL_BI_GEN_M,
 			   idpf_queue_has(GEN_CHK, refillq));
 
 	if (unlikely(++nta == refillq->desc_count)) {
@@ -784,10 +755,14 @@ static int idpf_rx_bufs_init(struct idpf_buf_queue *bufq,
 		.count		= bufq->desc_count,
 		.type		= type,
 		.hsplit		= idpf_queue_has(HSPLIT_EN, bufq),
+		.xdp		= idpf_xdp_enabled(bufq->q_vector->vport),
 		.nid		= idpf_q_vector_to_mem(bufq->q_vector),
 	};
 	int ret;
 
+	if (idpf_queue_has(XSK, bufq))
+		return idpf_xskfq_init(bufq);
+
 	ret = libeth_rx_fq_create(&fq, &bufq->q_vector->napi);
 	if (ret)
 		return ret;
@@ -811,6 +786,8 @@ int idpf_rx_bufs_init_all(struct idpf_vport *vport)
 	bool split = idpf_is_queue_model_split(vport->rxq_model);
 	int i, j, err;
 
+	idpf_xdp_copy_prog_to_rqs(vport, vport->xdp_prog);
+
 	for (i = 0; i < vport->num_rxq_grp; i++) {
 		struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i];
 		u32 truesize = 0;
@@ -881,6 +858,8 @@ static int idpf_rx_desc_alloc(const struct idpf_vport *vport,
 	rxq->next_to_use = 0;
 	idpf_queue_set(GEN_CHK, rxq);
 
+	idpf_xsk_setup_queue(vport, rxq, VIRTCHNL2_QUEUE_TYPE_RX);
+
 	return 0;
 }
 
@@ -906,9 +885,10 @@ static int idpf_bufq_desc_alloc(const struct idpf_vport *vport,
 	bufq->next_to_alloc = 0;
 	bufq->next_to_clean = 0;
 	bufq->next_to_use = 0;
-
 	idpf_queue_set(GEN_CHK, bufq);
 
+	idpf_xsk_setup_queue(vport, bufq, VIRTCHNL2_QUEUE_TYPE_RX_BUFFER);
+
 	return 0;
 }
 
@@ -942,8 +922,8 @@ static int idpf_rx_desc_alloc_all(struct idpf_vport *vport)
 			err = idpf_rx_desc_alloc(vport, q);
 			if (err) {
 				pci_err(vport->adapter->pdev,
-					"Memory allocation for Rx Queue %u failed\n",
-					i);
+					"Memory allocation for Rx queue %u from queue group %u failed\n",
+					j, i);
 				goto err_out;
 			}
 		}
@@ -959,8 +939,8 @@ static int idpf_rx_desc_alloc_all(struct idpf_vport *vport)
 			err = idpf_bufq_desc_alloc(vport, q);
 			if (err) {
 				pci_err(vport->adapter->pdev,
-					"Memory allocation for Rx Buffer Queue %u failed\n",
-					i);
+					"Memory allocation for Rx Buffer Queue %u from queue group %u failed\n",
+					j, i);
 				goto err_out;
 			}
 		}
@@ -974,6 +954,341 @@ err_out:
 	return err;
 }
 
+static int idpf_init_queue_set(const struct idpf_queue_set *qs)
+{
+	const struct idpf_vport *vport = qs->vport;
+	bool splitq;
+	int err;
+
+	splitq = idpf_is_queue_model_split(vport->rxq_model);
+
+	for (u32 i = 0; i < qs->num; i++) {
+		const struct idpf_queue_ptr *q = &qs->qs[i];
+		struct idpf_buf_queue *bufq;
+
+		switch (q->type) {
+		case VIRTCHNL2_QUEUE_TYPE_RX:
+			err = idpf_rx_desc_alloc(vport, q->rxq);
+			if (err)
+				break;
+
+			err = idpf_xdp_rxq_info_init(q->rxq);
+			if (err)
+				break;
+
+			if (!splitq)
+				err = idpf_rx_bufs_init_singleq(q->rxq);
+
+			break;
+		case VIRTCHNL2_QUEUE_TYPE_RX_BUFFER:
+			bufq = q->bufq;
+
+			err = idpf_bufq_desc_alloc(vport, bufq);
+			if (err)
+				break;
+
+			for (u32 j = 0; j < bufq->q_vector->num_bufq; j++) {
+				struct idpf_buf_queue * const *bufqs;
+				enum libeth_fqe_type type;
+				u32 ts;
+
+				bufqs = bufq->q_vector->bufq;
+				if (bufqs[j] != bufq)
+					continue;
+
+				if (j) {
+					type = LIBETH_FQE_SHORT;
+					ts = bufqs[j - 1]->truesize >> 1;
+				} else {
+					type = LIBETH_FQE_MTU;
+					ts = 0;
+				}
+
+				bufq->truesize = ts;
+
+				err = idpf_rx_bufs_init(bufq, type);
+				break;
+			}
+
+			break;
+		case VIRTCHNL2_QUEUE_TYPE_TX:
+			err = idpf_tx_desc_alloc(vport, q->txq);
+			break;
+		case VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION:
+			err = idpf_compl_desc_alloc(vport, q->complq);
+			break;
+		default:
+			continue;
+		}
+
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void idpf_clean_queue_set(const struct idpf_queue_set *qs)
+{
+	const struct idpf_vport *vport = qs->vport;
+	struct device *dev = vport->netdev->dev.parent;
+
+	for (u32 i = 0; i < qs->num; i++) {
+		const struct idpf_queue_ptr *q = &qs->qs[i];
+
+		switch (q->type) {
+		case VIRTCHNL2_QUEUE_TYPE_RX:
+			idpf_xdp_rxq_info_deinit(q->rxq, vport->rxq_model);
+			idpf_rx_desc_rel(q->rxq, dev, vport->rxq_model);
+			break;
+		case VIRTCHNL2_QUEUE_TYPE_RX_BUFFER:
+			idpf_rx_desc_rel_bufq(q->bufq, dev);
+			break;
+		case VIRTCHNL2_QUEUE_TYPE_TX:
+			idpf_tx_desc_rel(q->txq);
+
+			if (idpf_queue_has(XDP, q->txq)) {
+				q->txq->pending = 0;
+				q->txq->xdp_tx = 0;
+			} else {
+				q->txq->txq_grp->num_completions_pending = 0;
+			}
+
+			writel(q->txq->next_to_use, q->txq->tail);
+			break;
+		case VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION:
+			idpf_compl_desc_rel(q->complq);
+			q->complq->num_completions = 0;
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+static void idpf_qvec_ena_irq(struct idpf_q_vector *qv)
+{
+	if (qv->num_txq) {
+		u32 itr;
+
+		if (IDPF_ITR_IS_DYNAMIC(qv->tx_intr_mode))
+			itr = qv->vport->tx_itr_profile[qv->tx_dim.profile_ix];
+		else
+			itr = qv->tx_itr_value;
+
+		idpf_vport_intr_write_itr(qv, itr, true);
+	}
+
+	if (qv->num_rxq) {
+		u32 itr;
+
+		if (IDPF_ITR_IS_DYNAMIC(qv->rx_intr_mode))
+			itr = qv->vport->rx_itr_profile[qv->rx_dim.profile_ix];
+		else
+			itr = qv->rx_itr_value;
+
+		idpf_vport_intr_write_itr(qv, itr, false);
+	}
+
+	if (qv->num_txq || qv->num_rxq)
+		idpf_vport_intr_update_itr_ena_irq(qv);
+}
+
+/**
+ * idpf_vector_to_queue_set - create a queue set associated with the given
+ *			      queue vector
+ * @qv: queue vector corresponding to the queue pair
+ *
+ * Returns a pointer to a dynamically allocated array of pointers to all
+ * queues associated with a given queue vector (@qv).
+ * Please note that the caller is responsible to free the memory allocated
+ * by this function using kfree().
+ *
+ * Return: &idpf_queue_set on success, %NULL in case of error.
+ */
+static struct idpf_queue_set *
+idpf_vector_to_queue_set(struct idpf_q_vector *qv)
+{
+	bool xdp = qv->vport->xdp_txq_offset && !qv->num_xsksq;
+	struct idpf_vport *vport = qv->vport;
+	struct idpf_queue_set *qs;
+	u32 num;
+
+	num = qv->num_rxq + qv->num_bufq + qv->num_txq + qv->num_complq;
+	num += xdp ? qv->num_rxq * 2 : qv->num_xsksq * 2;
+	if (!num)
+		return NULL;
+
+	qs = idpf_alloc_queue_set(vport, num);
+	if (!qs)
+		return NULL;
+
+	num = 0;
+
+	for (u32 i = 0; i < qv->num_bufq; i++) {
+		qs->qs[num].type = VIRTCHNL2_QUEUE_TYPE_RX_BUFFER;
+		qs->qs[num++].bufq = qv->bufq[i];
+	}
+
+	for (u32 i = 0; i < qv->num_rxq; i++) {
+		qs->qs[num].type = VIRTCHNL2_QUEUE_TYPE_RX;
+		qs->qs[num++].rxq = qv->rx[i];
+	}
+
+	for (u32 i = 0; i < qv->num_txq; i++) {
+		qs->qs[num].type = VIRTCHNL2_QUEUE_TYPE_TX;
+		qs->qs[num++].txq = qv->tx[i];
+	}
+
+	for (u32 i = 0; i < qv->num_complq; i++) {
+		qs->qs[num].type = VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION;
+		qs->qs[num++].complq = qv->complq[i];
+	}
+
+	if (!vport->xdp_txq_offset)
+		goto finalize;
+
+	if (xdp) {
+		for (u32 i = 0; i < qv->num_rxq; i++) {
+			u32 idx = vport->xdp_txq_offset + qv->rx[i]->idx;
+
+			qs->qs[num].type = VIRTCHNL2_QUEUE_TYPE_TX;
+			qs->qs[num++].txq = vport->txqs[idx];
+
+			qs->qs[num].type = VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION;
+			qs->qs[num++].complq = vport->txqs[idx]->complq;
+		}
+	} else {
+		for (u32 i = 0; i < qv->num_xsksq; i++) {
+			qs->qs[num].type = VIRTCHNL2_QUEUE_TYPE_TX;
+			qs->qs[num++].txq = qv->xsksq[i];
+
+			qs->qs[num].type = VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION;
+			qs->qs[num++].complq = qv->xsksq[i]->complq;
+		}
+	}
+
+finalize:
+	if (num != qs->num) {
+		kfree(qs);
+		return NULL;
+	}
+
+	return qs;
+}
+
+static int idpf_qp_enable(const struct idpf_queue_set *qs, u32 qid)
+{
+	struct idpf_vport *vport = qs->vport;
+	struct idpf_q_vector *q_vector;
+	int err;
+
+	q_vector = idpf_find_rxq_vec(vport, qid);
+
+	err = idpf_init_queue_set(qs);
+	if (err) {
+		netdev_err(vport->netdev, "Could not initialize queues in pair %u: %pe\n",
+			   qid, ERR_PTR(err));
+		return err;
+	}
+
+	if (!vport->xdp_txq_offset)
+		goto config;
+
+	q_vector->xsksq = kcalloc(DIV_ROUND_UP(vport->num_rxq_grp,
+					       vport->num_q_vectors),
+				  sizeof(*q_vector->xsksq), GFP_KERNEL);
+	if (!q_vector->xsksq)
+		return -ENOMEM;
+
+	for (u32 i = 0; i < qs->num; i++) {
+		const struct idpf_queue_ptr *q = &qs->qs[i];
+
+		if (q->type != VIRTCHNL2_QUEUE_TYPE_TX)
+			continue;
+
+		if (!idpf_queue_has(XSK, q->txq))
+			continue;
+
+		idpf_xsk_init_wakeup(q_vector);
+
+		q->txq->q_vector = q_vector;
+		q_vector->xsksq[q_vector->num_xsksq++] = q->txq;
+	}
+
+config:
+	err = idpf_send_config_queue_set_msg(qs);
+	if (err) {
+		netdev_err(vport->netdev, "Could not configure queues in pair %u: %pe\n",
+			   qid, ERR_PTR(err));
+		return err;
+	}
+
+	err = idpf_send_enable_queue_set_msg(qs);
+	if (err) {
+		netdev_err(vport->netdev, "Could not enable queues in pair %u: %pe\n",
+			   qid, ERR_PTR(err));
+		return err;
+	}
+
+	napi_enable(&q_vector->napi);
+	idpf_qvec_ena_irq(q_vector);
+
+	netif_start_subqueue(vport->netdev, qid);
+
+	return 0;
+}
+
+static int idpf_qp_disable(const struct idpf_queue_set *qs, u32 qid)
+{
+	struct idpf_vport *vport = qs->vport;
+	struct idpf_q_vector *q_vector;
+	int err;
+
+	q_vector = idpf_find_rxq_vec(vport, qid);
+	netif_stop_subqueue(vport->netdev, qid);
+
+	writel(0, q_vector->intr_reg.dyn_ctl);
+	napi_disable(&q_vector->napi);
+
+	err = idpf_send_disable_queue_set_msg(qs);
+	if (err) {
+		netdev_err(vport->netdev, "Could not disable queues in pair %u: %pe\n",
+			   qid, ERR_PTR(err));
+		return err;
+	}
+
+	idpf_clean_queue_set(qs);
+
+	kfree(q_vector->xsksq);
+	q_vector->num_xsksq = 0;
+
+	return 0;
+}
+
+/**
+ * idpf_qp_switch - enable or disable queues associated with queue pair
+ * @vport: vport to switch the pair for
+ * @qid: index of the queue pair to switch
+ * @en: whether to enable or disable the pair
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int idpf_qp_switch(struct idpf_vport *vport, u32 qid, bool en)
+{
+	struct idpf_q_vector *q_vector = idpf_find_rxq_vec(vport, qid);
+	struct idpf_queue_set *qs __free(kfree) = NULL;
+
+	if (idpf_find_txq_vec(vport, qid) != q_vector)
+		return -EINVAL;
+
+	qs = idpf_vector_to_queue_set(q_vector);
+	if (!qs)
+		return -ENOMEM;
+
+	return en ? idpf_qp_enable(qs, qid) : idpf_qp_disable(qs, qid);
+}
+
 /**
  * idpf_txq_group_rel - Release all resources for txq groups
  * @vport: vport to release txq groups on
@@ -994,6 +1309,11 @@ static void idpf_txq_group_rel(struct idpf_vport *vport)
 		struct idpf_txq_group *txq_grp = &vport->txq_grps[i];
 
 		for (j = 0; j < txq_grp->num_txq; j++) {
+			if (flow_sch_en) {
+				kfree(txq_grp->txqs[j]->refillq);
+				txq_grp->txqs[j]->refillq = NULL;
+			}
+
 			kfree(txq_grp->txqs[j]);
 			txq_grp->txqs[j] = NULL;
 		}
@@ -1003,9 +1323,6 @@ static void idpf_txq_group_rel(struct idpf_vport *vport)
 
 		kfree(txq_grp->complq);
 		txq_grp->complq = NULL;
-
-		if (flow_sch_en)
-			kfree(txq_grp->stashes);
 	}
 	kfree(vport->txq_grps);
 	vport->txq_grps = NULL;
@@ -1087,8 +1404,12 @@ static void idpf_vport_queue_grp_rel_all(struct idpf_vport *vport)
  */
 void idpf_vport_queues_rel(struct idpf_vport *vport)
 {
+	idpf_xdp_copy_prog_to_rqs(vport, NULL);
+
 	idpf_tx_desc_rel_all(vport);
 	idpf_rx_desc_rel_all(vport);
+
+	idpf_xdpsqs_put(vport);
 	idpf_vport_queue_grp_rel_all(vport);
 
 	kfree(vport->txqs);
@@ -1107,6 +1428,8 @@ void idpf_vport_queues_rel(struct idpf_vport *vport)
  */
 static int idpf_vport_init_fast_path_txqs(struct idpf_vport *vport)
 {
+	struct idpf_ptp_vport_tx_tstamp_caps *caps = vport->tx_tstamp_caps;
+	struct work_struct *tstamp_task = &vport->tstamp_task;
 	int i, j, k = 0;
 
 	vport->txqs = kcalloc(vport->num_txq, sizeof(*vport->txqs),
@@ -1121,6 +1444,12 @@ static int idpf_vport_init_fast_path_txqs(struct idpf_vport *vport)
 		for (j = 0; j < tx_grp->num_txq; j++, k++) {
 			vport->txqs[k] = tx_grp->txqs[j];
 			vport->txqs[k]->idx = k;
+
+			if (!caps)
+				continue;
+
+			vport->txqs[k]->cached_tstamp_caps = caps;
+			vport->txqs[k]->tstamp_task = tstamp_task;
 		}
 	}
 
@@ -1154,6 +1483,18 @@ void idpf_vport_init_num_qs(struct idpf_vport *vport,
 	if (idpf_is_queue_model_split(vport->rxq_model))
 		vport->num_bufq = le16_to_cpu(vport_msg->num_rx_bufq);
 
+	vport->xdp_prog = config_data->xdp_prog;
+	if (idpf_xdp_enabled(vport)) {
+		vport->xdp_txq_offset = config_data->num_req_tx_qs;
+		vport->num_xdp_txq = le16_to_cpu(vport_msg->num_tx_q) -
+				     vport->xdp_txq_offset;
+		vport->xdpsq_share = libeth_xdpsq_shared(vport->num_xdp_txq);
+	} else {
+		vport->xdp_txq_offset = 0;
+		vport->num_xdp_txq = 0;
+		vport->xdpsq_share = false;
+	}
+
 	/* Adjust number of buffer queues per Rx queue group. */
 	if (!idpf_is_queue_model_split(vport->rxq_model)) {
 		vport->num_bufqs_per_qgrp = 0;
@@ -1225,22 +1566,17 @@ int idpf_vport_calc_total_qs(struct idpf_adapter *adapter, u16 vport_idx,
 	int dflt_splitq_txq_grps = 0, dflt_singleq_txqs = 0;
 	int dflt_splitq_rxq_grps = 0, dflt_singleq_rxqs = 0;
 	u16 num_req_tx_qs = 0, num_req_rx_qs = 0;
+	struct idpf_vport_user_config_data *user;
 	struct idpf_vport_config *vport_config;
 	u16 num_txq_grps, num_rxq_grps;
-	u32 num_qs;
+	u32 num_qs, num_xdpsq;
 
 	vport_config = adapter->vport_config[vport_idx];
 	if (vport_config) {
 		num_req_tx_qs = vport_config->user_config.num_req_tx_qs;
 		num_req_rx_qs = vport_config->user_config.num_req_rx_qs;
 	} else {
-		int num_cpus;
-
-		/* Restrict num of queues to cpus online as a default
-		 * configuration to give best performance. User can always
-		 * override to a max number of queues via ethtool.
-		 */
-		num_cpus = num_online_cpus();
+		u32 num_cpus = netif_get_num_default_rss_queues();
 
 		dflt_splitq_txq_grps = min_t(int, max_q->max_txq, num_cpus);
 		dflt_singleq_txqs = min_t(int, max_q->max_txq, num_cpus);
@@ -1275,6 +1611,24 @@ int idpf_vport_calc_total_qs(struct idpf_adapter *adapter, u16 vport_idx,
 		vport_msg->num_rx_bufq = 0;
 	}
 
+	if (!vport_config)
+		return 0;
+
+	user = &vport_config->user_config;
+	user->num_req_rx_qs = le16_to_cpu(vport_msg->num_rx_q);
+	user->num_req_tx_qs = le16_to_cpu(vport_msg->num_tx_q);
+
+	if (vport_config->user_config.xdp_prog)
+		num_xdpsq = libeth_xdpsq_num(user->num_req_rx_qs,
+					     user->num_req_tx_qs,
+					     vport_config->max_q.max_txq);
+	else
+		num_xdpsq = 0;
+
+	vport_msg->num_tx_q = cpu_to_le16(user->num_req_tx_qs + num_xdpsq);
+	if (idpf_is_queue_model_split(le16_to_cpu(vport_msg->txq_model)))
+		vport_msg->num_tx_complq = vport_msg->num_tx_q;
+
 	return 0;
 }
 
@@ -1324,14 +1678,13 @@ static void idpf_vport_calc_numq_per_grp(struct idpf_vport *vport,
 static void idpf_rxq_set_descids(const struct idpf_vport *vport,
 				 struct idpf_rx_queue *q)
 {
-	if (idpf_is_queue_model_split(vport->rxq_model)) {
-		q->rxdids = VIRTCHNL2_RXDID_2_FLEX_SPLITQ_M;
-	} else {
-		if (vport->base_rxd)
-			q->rxdids = VIRTCHNL2_RXDID_1_32B_BASE_M;
-		else
-			q->rxdids = VIRTCHNL2_RXDID_2_FLEX_SQ_NIC_M;
-	}
+	if (idpf_is_queue_model_split(vport->rxq_model))
+		return;
+
+	if (vport->base_rxd)
+		q->rxdids = VIRTCHNL2_RXDID_1_32B_BASE_M;
+	else
+		q->rxdids = VIRTCHNL2_RXDID_2_FLEX_SQ_NIC_M;
 }
 
 /**
@@ -1358,7 +1711,6 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 	for (i = 0; i < vport->num_txq_grp; i++) {
 		struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
 		struct idpf_adapter *adapter = vport->adapter;
-		struct idpf_txq_stash *stashes;
 		int j;
 
 		tx_qgrp->vport = vport;
@@ -1371,15 +1723,6 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 				goto err_alloc;
 		}
 
-		if (split && flow_sch_en) {
-			stashes = kcalloc(num_txq, sizeof(*stashes),
-					  GFP_KERNEL);
-			if (!stashes)
-				goto err_alloc;
-
-			tx_qgrp->stashes = stashes;
-		}
-
 		for (j = 0; j < tx_qgrp->num_txq; j++) {
 			struct idpf_tx_queue *q = tx_qgrp->txqs[j];
 
@@ -1389,6 +1732,7 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 			q->tx_min_pkt_len = idpf_get_min_tx_pkt_len(adapter);
 			q->netdev = vport->netdev;
 			q->txq_grp = tx_qgrp;
+			q->rel_q_id = j;
 
 			if (!split) {
 				q->clean_budget = vport->compln_clean_budget;
@@ -1399,12 +1743,14 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 			if (!flow_sch_en)
 				continue;
 
-			if (split) {
-				q->stash = &stashes[j];
-				hash_init(q->stash->sched_buf_hash);
-			}
-
 			idpf_queue_set(FLOW_SCH_EN, q);
+
+			q->refillq = kzalloc(sizeof(*q->refillq), GFP_KERNEL);
+			if (!q->refillq)
+				goto err_alloc;
+
+			idpf_queue_set(GEN_CHK, q->refillq);
+			idpf_queue_set(RFL_GEN_CHK, q->refillq);
 		}
 
 		if (!split)
@@ -1547,7 +1893,6 @@ skip_splitq_rx_init:
 setup_rxq:
 			q->desc_count = vport->rxq_desc_count;
 			q->rx_ptype_lkup = vport->rx_ptype_lkup;
-			q->netdev = vport->netdev;
 			q->bufq_sets = rx_qgrp->splitq.bufq_sets;
 			q->idx = (i * num_rxq) + j;
 			q->rx_buffer_low_watermark = IDPF_LOW_WATERMARK;
@@ -1608,15 +1953,19 @@ int idpf_vport_queues_alloc(struct idpf_vport *vport)
 	if (err)
 		goto err_out;
 
-	err = idpf_tx_desc_alloc_all(vport);
+	err = idpf_vport_init_fast_path_txqs(vport);
 	if (err)
 		goto err_out;
 
-	err = idpf_rx_desc_alloc_all(vport);
+	err = idpf_xdpsqs_get(vport);
 	if (err)
 		goto err_out;
 
-	err = idpf_vport_init_fast_path_txqs(vport);
+	err = idpf_tx_desc_alloc_all(vport);
+	if (err)
+		goto err_out;
+
+	err = idpf_rx_desc_alloc_all(vport);
 	if (err)
 		goto err_out;
 
@@ -1629,105 +1978,37 @@ err_out:
 }
 
 /**
- * idpf_tx_handle_sw_marker - Handle queue marker packet
- * @tx_q: tx queue to handle software marker
+ * idpf_tx_read_tstamp - schedule a work to read Tx timestamp value
+ * @txq: queue to read the timestamp from
+ * @skb: socket buffer to provide Tx timestamp value
+ *
+ * Schedule a work to read Tx timestamp value generated once the packet is
+ * transmitted.
  */
-static void idpf_tx_handle_sw_marker(struct idpf_tx_queue *tx_q)
+static void idpf_tx_read_tstamp(struct idpf_tx_queue *txq, struct sk_buff *skb)
 {
-	struct idpf_netdev_priv *priv = netdev_priv(tx_q->netdev);
-	struct idpf_vport *vport = priv->vport;
-	int i;
-
-	idpf_queue_clear(SW_MARKER, tx_q);
-	/* Hardware must write marker packets to all queues associated with
-	 * completion queues. So check if all queues received marker packets
-	 */
-	for (i = 0; i < vport->num_txq; i++)
-		/* If we're still waiting on any other TXQ marker completions,
-		 * just return now since we cannot wake up the marker_wq yet.
-		 */
-		if (idpf_queue_has(SW_MARKER, vport->txqs[i]))
-			return;
-
-	/* Drain complete */
-	set_bit(IDPF_VPORT_SW_MARKER, vport->flags);
-	wake_up(&vport->sw_marker_wq);
-}
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct idpf_ptp_tx_tstamp_status *tx_tstamp_status;
 
-/**
- * idpf_tx_clean_stashed_bufs - clean bufs that were stored for
- * out of order completions
- * @txq: queue to clean
- * @compl_tag: completion tag of packet to clean (from completion descriptor)
- * @cleaned: pointer to stats struct to track cleaned packets/bytes
- * @budget: Used to determine if we are in netpoll
- */
-static void idpf_tx_clean_stashed_bufs(struct idpf_tx_queue *txq,
-				       u16 compl_tag,
-				       struct libeth_sq_napi_stats *cleaned,
-				       int budget)
-{
-	struct idpf_tx_stash *stash;
-	struct hlist_node *tmp_buf;
-	struct libeth_cq_pp cp = {
-		.dev	= txq->dev,
-		.ss	= cleaned,
-		.napi	= budget,
-	};
+	tx_tstamp_caps = txq->cached_tstamp_caps;
+	spin_lock_bh(&tx_tstamp_caps->status_lock);
 
-	/* Buffer completion */
-	hash_for_each_possible_safe(txq->stash->sched_buf_hash, stash, tmp_buf,
-				    hlist, compl_tag) {
-		if (unlikely(idpf_tx_buf_compl_tag(&stash->buf) != compl_tag))
+	for (u32 i = 0; i < tx_tstamp_caps->num_entries; i++) {
+		tx_tstamp_status = &tx_tstamp_caps->tx_tstamp_status[i];
+		if (tx_tstamp_status->state != IDPF_PTP_FREE)
 			continue;
 
-		hash_del(&stash->hlist);
-		libeth_tx_complete(&stash->buf, &cp);
+		tx_tstamp_status->skb = skb;
+		tx_tstamp_status->state = IDPF_PTP_REQUEST;
 
-		/* Push shadow buf back onto stack */
-		idpf_buf_lifo_push(&txq->stash->buf_stack, stash);
-	}
-}
-
-/**
- * idpf_stash_flow_sch_buffers - store buffer parameters info to be freed at a
- * later time (only relevant for flow scheduling mode)
- * @txq: Tx queue to clean
- * @tx_buf: buffer to store
- */
-static int idpf_stash_flow_sch_buffers(struct idpf_tx_queue *txq,
-				       struct idpf_tx_buf *tx_buf)
-{
-	struct idpf_tx_stash *stash;
-
-	if (unlikely(tx_buf->type <= LIBETH_SQE_CTX))
-		return 0;
-
-	stash = idpf_buf_lifo_pop(&txq->stash->buf_stack);
-	if (unlikely(!stash)) {
-		net_err_ratelimited("%s: No out-of-order TX buffers left!\n",
-				    netdev_name(txq->netdev));
-
-		return -ENOMEM;
+		/* Fetch timestamp from completion descriptor through
+		 * virtchnl msg to report to stack.
+		 */
+		queue_work(system_unbound_wq, txq->tstamp_task);
+		break;
 	}
 
-	/* Store buffer params in shadow buffer */
-	stash->buf.skb = tx_buf->skb;
-	stash->buf.bytes = tx_buf->bytes;
-	stash->buf.packets = tx_buf->packets;
-	stash->buf.type = tx_buf->type;
-	stash->buf.nr_frags = tx_buf->nr_frags;
-	dma_unmap_addr_set(&stash->buf, dma, dma_unmap_addr(tx_buf, dma));
-	dma_unmap_len_set(&stash->buf, len, dma_unmap_len(tx_buf, len));
-	idpf_tx_buf_compl_tag(&stash->buf) = idpf_tx_buf_compl_tag(tx_buf);
-
-	/* Add buffer to buf_hash table to be freed later */
-	hash_add(txq->stash->sched_buf_hash, &stash->hlist,
-		 idpf_tx_buf_compl_tag(&stash->buf));
-
-	tx_buf->type = LIBETH_SQE_EMPTY;
-
-	return 0;
+	spin_unlock_bh(&tx_tstamp_caps->status_lock);
 }
 
 #define idpf_tx_splitq_clean_bump_ntc(txq, ntc, desc, buf)	\
@@ -1757,14 +2038,8 @@ do {								\
  * Separate packet completion events will be reported on the completion queue,
  * and the buffers will be cleaned separately. The stats are not updated from
  * this function when using flow-based scheduling.
- *
- * Furthermore, in flow scheduling mode, check to make sure there are enough
- * reserve buffers to stash the packet. If there are not, return early, which
- * will leave next_to_clean pointing to the packet that failed to be stashed.
- *
- * Return: false in the scenario above, true otherwise.
  */
-static bool idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
+static void idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 				 int napi_budget,
 				 struct libeth_sq_napi_stats *cleaned,
 				 bool descs_only)
@@ -1778,7 +2053,12 @@ static bool idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 		.napi	= napi_budget,
 	};
 	struct idpf_tx_buf *tx_buf;
-	bool clean_complete = true;
+
+	if (descs_only) {
+		/* Bump ring index to mark as cleaned. */
+		tx_q->next_to_clean = end;
+		return;
+	}
 
 	tx_desc = &tx_q->flex_tx[ntc];
 	next_pending_desc = &tx_q->flex_tx[end];
@@ -1798,132 +2078,61 @@ static bool idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 			break;
 
 		eop_idx = tx_buf->rs_idx;
+		libeth_tx_complete(tx_buf, &cp);
 
-		if (descs_only) {
-			if (IDPF_TX_BUF_RSV_UNUSED(tx_q) < tx_buf->nr_frags) {
-				clean_complete = false;
-				goto tx_splitq_clean_out;
-			}
-
-			idpf_stash_flow_sch_buffers(tx_q, tx_buf);
+		/* unmap remaining buffers */
+		while (ntc != eop_idx) {
+			idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
+						      tx_desc, tx_buf);
 
-			while (ntc != eop_idx) {
-				idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
-							      tx_desc, tx_buf);
-				idpf_stash_flow_sch_buffers(tx_q, tx_buf);
-			}
-		} else {
+			/* unmap any remaining paged data */
 			libeth_tx_complete(tx_buf, &cp);
-
-			/* unmap remaining buffers */
-			while (ntc != eop_idx) {
-				idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
-							      tx_desc, tx_buf);
-
-				/* unmap any remaining paged data */
-				libeth_tx_complete(tx_buf, &cp);
-			}
 		}
 
 fetch_next_txq_desc:
 		idpf_tx_splitq_clean_bump_ntc(tx_q, ntc, tx_desc, tx_buf);
 	}
 
-tx_splitq_clean_out:
 	tx_q->next_to_clean = ntc;
-
-	return clean_complete;
 }
 
-#define idpf_tx_clean_buf_ring_bump_ntc(txq, ntc, buf)	\
-do {							\
-	(buf)++;					\
-	(ntc)++;					\
-	if (unlikely((ntc) == (txq)->desc_count)) {	\
-		buf = (txq)->tx_buf;			\
-		ntc = 0;				\
-	}						\
-} while (0)
-
 /**
- * idpf_tx_clean_buf_ring - clean flow scheduling TX queue buffers
+ * idpf_tx_clean_bufs - clean flow scheduling TX queue buffers
  * @txq: queue to clean
- * @compl_tag: completion tag of packet to clean (from completion descriptor)
+ * @buf_id: packet's starting buffer ID, from completion descriptor
  * @cleaned: pointer to stats struct to track cleaned packets/bytes
  * @budget: Used to determine if we are in netpoll
  *
- * Cleans all buffers associated with the input completion tag either from the
- * TX buffer ring or from the hash table if the buffers were previously
- * stashed. Returns the byte/segment count for the cleaned packet associated
- * this completion tag.
+ * Clean all buffers associated with the packet starting at buf_id. Returns the
+ * byte/segment count for the cleaned packet.
  */
-static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag,
-				   struct libeth_sq_napi_stats *cleaned,
-				   int budget)
+static void idpf_tx_clean_bufs(struct idpf_tx_queue *txq, u32 buf_id,
+			       struct libeth_sq_napi_stats *cleaned,
+			       int budget)
 {
-	u16 idx = compl_tag & txq->compl_tag_bufid_m;
 	struct idpf_tx_buf *tx_buf = NULL;
 	struct libeth_cq_pp cp = {
 		.dev	= txq->dev,
 		.ss	= cleaned,
 		.napi	= budget,
 	};
-	u16 ntc, orig_idx = idx;
-
-	tx_buf = &txq->tx_buf[idx];
 
-	if (unlikely(tx_buf->type <= LIBETH_SQE_CTX ||
-		     idpf_tx_buf_compl_tag(tx_buf) != compl_tag))
-		return false;
+	tx_buf = &txq->tx_buf[buf_id];
+	if (tx_buf->type == LIBETH_SQE_SKB) {
+		if (skb_shinfo(tx_buf->skb)->tx_flags & SKBTX_IN_PROGRESS)
+			idpf_tx_read_tstamp(txq, tx_buf->skb);
 
-	if (tx_buf->type == LIBETH_SQE_SKB)
 		libeth_tx_complete(tx_buf, &cp);
+		idpf_post_buf_refill(txq->refillq, buf_id);
+	}
 
-	idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
+	while (idpf_tx_buf_next(tx_buf) != IDPF_TXBUF_NULL) {
+		buf_id = idpf_tx_buf_next(tx_buf);
 
-	while (idpf_tx_buf_compl_tag(tx_buf) == compl_tag) {
+		tx_buf = &txq->tx_buf[buf_id];
 		libeth_tx_complete(tx_buf, &cp);
-		idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
+		idpf_post_buf_refill(txq->refillq, buf_id);
 	}
-
-	/*
-	 * It's possible the packet we just cleaned was an out of order
-	 * completion, which means we can stash the buffers starting from
-	 * the original next_to_clean and reuse the descriptors. We need
-	 * to compare the descriptor ring next_to_clean packet's "first" buffer
-	 * to the "first" buffer of the packet we just cleaned to determine if
-	 * this is the case. Howevever, next_to_clean can point to either a
-	 * reserved buffer that corresponds to a context descriptor used for the
-	 * next_to_clean packet (TSO packet) or the "first" buffer (single
-	 * packet). The orig_idx from the packet we just cleaned will always
-	 * point to the "first" buffer. If next_to_clean points to a reserved
-	 * buffer, let's bump ntc once and start the comparison from there.
-	 */
-	ntc = txq->next_to_clean;
-	tx_buf = &txq->tx_buf[ntc];
-
-	if (tx_buf->type == LIBETH_SQE_CTX)
-		idpf_tx_clean_buf_ring_bump_ntc(txq, ntc, tx_buf);
-
-	/*
-	 * If ntc still points to a different "first" buffer, clean the
-	 * descriptor ring and stash all of the buffers for later cleaning. If
-	 * we cannot stash all of the buffers, next_to_clean will point to the
-	 * "first" buffer of the packet that could not be stashed and cleaning
-	 * will start there next time.
-	 */
-	if (unlikely(tx_buf != &txq->tx_buf[orig_idx] &&
-		     !idpf_tx_splitq_clean(txq, orig_idx, budget, cleaned,
-					   true)))
-		return true;
-
-	/*
-	 * Otherwise, update next_to_clean to reflect the cleaning that was
-	 * done above.
-	 */
-	txq->next_to_clean = idx;
-
-	return true;
 }
 
 /**
@@ -1942,22 +2151,17 @@ static void idpf_tx_handle_rs_completion(struct idpf_tx_queue *txq,
 					 struct libeth_sq_napi_stats *cleaned,
 					 int budget)
 {
-	u16 compl_tag;
+	/* RS completion contains queue head for queue based scheduling or
+	 * completion tag for flow based scheduling.
+	 */
+	u16 rs_compl_val = le16_to_cpu(desc->common.q_head_compl_tag.q_head);
 
 	if (!idpf_queue_has(FLOW_SCH_EN, txq)) {
-		u16 head = le16_to_cpu(desc->q_head_compl_tag.q_head);
-
-		idpf_tx_splitq_clean(txq, head, budget, cleaned, false);
+		idpf_tx_splitq_clean(txq, rs_compl_val, budget, cleaned, false);
 		return;
 	}
 
-	compl_tag = le16_to_cpu(desc->q_head_compl_tag.compl_tag);
-
-	/* If we didn't clean anything on the ring, this packet must be
-	 * in the hash table. Go clean it there.
-	 */
-	if (!idpf_tx_clean_buf_ring(txq, compl_tag, cleaned, budget))
-		idpf_tx_clean_stashed_bufs(txq, compl_tag, cleaned, budget);
+	idpf_tx_clean_bufs(txq, rs_compl_val, cleaned, budget);
 }
 
 /**
@@ -1985,19 +2189,19 @@ static bool idpf_tx_clean_complq(struct idpf_compl_queue *complq, int budget,
 	do {
 		struct libeth_sq_napi_stats cleaned_stats = { };
 		struct idpf_tx_queue *tx_q;
+		__le16 hw_head;
 		int rel_tx_qid;
-		u16 hw_head;
 		u8 ctype;	/* completion type */
 		u16 gen;
 
 		/* if the descriptor isn't done, no work yet to do */
-		gen = le16_get_bits(tx_desc->qid_comptype_gen,
+		gen = le16_get_bits(tx_desc->common.qid_comptype_gen,
 				    IDPF_TXD_COMPLQ_GEN_M);
 		if (idpf_queue_has(GEN_CHK, complq) != gen)
 			break;
 
 		/* Find necessary info of TX queue to clean buffers */
-		rel_tx_qid = le16_get_bits(tx_desc->qid_comptype_gen,
+		rel_tx_qid = le16_get_bits(tx_desc->common.qid_comptype_gen,
 					   IDPF_TXD_COMPLQ_QID_M);
 		if (rel_tx_qid >= complq->txq_grp->num_txq ||
 		    !complq->txq_grp->txqs[rel_tx_qid]) {
@@ -2007,22 +2211,19 @@ static bool idpf_tx_clean_complq(struct idpf_compl_queue *complq, int budget,
 		tx_q = complq->txq_grp->txqs[rel_tx_qid];
 
 		/* Determine completion type */
-		ctype = le16_get_bits(tx_desc->qid_comptype_gen,
+		ctype = le16_get_bits(tx_desc->common.qid_comptype_gen,
 				      IDPF_TXD_COMPLQ_COMPL_TYPE_M);
 		switch (ctype) {
 		case IDPF_TXD_COMPLT_RE:
-			hw_head = le16_to_cpu(tx_desc->q_head_compl_tag.q_head);
+			hw_head = tx_desc->common.q_head_compl_tag.q_head;
 
-			idpf_tx_splitq_clean(tx_q, hw_head, budget,
-					     &cleaned_stats, true);
+			idpf_tx_splitq_clean(tx_q, le16_to_cpu(hw_head),
+					     budget, &cleaned_stats, true);
 			break;
 		case IDPF_TXD_COMPLT_RS:
 			idpf_tx_handle_rs_completion(tx_q, tx_desc,
 						     &cleaned_stats, budget);
 			break;
-		case IDPF_TXD_COMPLT_SW_MARKER:
-			idpf_tx_handle_sw_marker(tx_q);
-			break;
 		default:
 			netdev_err(tx_q->netdev,
 				   "Unknown TX completion type: %d\n", ctype);
@@ -2074,8 +2275,7 @@ fetch_next_desc:
 		/* Update BQL */
 		nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
 
-		dont_wake = !complq_ok || IDPF_TX_BUF_RSV_LOW(tx_q) ||
-			    np->state != __IDPF_VPORT_UP ||
+		dont_wake = !complq_ok || !test_bit(IDPF_VPORT_UP, np->state) ||
 			    !netif_carrier_ok(tx_q->netdev);
 		/* Check if the TXQ needs to and can be restarted */
 		__netif_txq_completed_wake(nq, tx_q->cleaned_pkts, tx_q->cleaned_bytes,
@@ -2096,6 +2296,69 @@ fetch_next_desc:
 }
 
 /**
+ * idpf_wait_for_sw_marker_completion - wait for SW marker of disabled Tx queue
+ * @txq: disabled Tx queue
+ *
+ * When Tx queue is requested for disabling, the CP sends a special completion
+ * descriptor called "SW marker", meaning the queue is ready to be destroyed.
+ * If, for some reason, the marker is not received within 500 ms, break the
+ * polling to not hang the driver.
+ */
+void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq)
+{
+	struct idpf_compl_queue *complq;
+	unsigned long timeout;
+	bool flow, gen_flag;
+	u32 ntc;
+
+	if (!idpf_queue_has(SW_MARKER, txq))
+		return;
+
+	complq = idpf_queue_has(XDP, txq) ? txq->complq : txq->txq_grp->complq;
+	ntc = complq->next_to_clean;
+
+	flow = idpf_queue_has(FLOW_SCH_EN, complq);
+	gen_flag = idpf_queue_has(GEN_CHK, complq);
+
+	timeout = jiffies + msecs_to_jiffies(IDPF_WAIT_FOR_MARKER_TIMEO);
+
+	do {
+		struct idpf_splitq_4b_tx_compl_desc *tx_desc;
+		struct idpf_tx_queue *target;
+		u32 ctype_gen, id;
+
+		tx_desc = flow ? &complq->comp[ntc].common :
+			  &complq->comp_4b[ntc];
+		ctype_gen = le16_to_cpu(tx_desc->qid_comptype_gen);
+
+		if (!!(ctype_gen & IDPF_TXD_COMPLQ_GEN_M) != gen_flag) {
+			usleep_range(500, 1000);
+			continue;
+		}
+
+		if (FIELD_GET(IDPF_TXD_COMPLQ_COMPL_TYPE_M, ctype_gen) !=
+		    IDPF_TXD_COMPLT_SW_MARKER)
+			goto next;
+
+		id = FIELD_GET(IDPF_TXD_COMPLQ_QID_M, ctype_gen);
+		target = complq->txq_grp->txqs[id];
+
+		idpf_queue_clear(SW_MARKER, target);
+		if (target == txq)
+			break;
+
+next:
+		if (unlikely(++ntc == complq->desc_count)) {
+			ntc = 0;
+			gen_flag = !gen_flag;
+		}
+	} while (time_before(jiffies, timeout));
+
+	idpf_queue_assign(GEN_CHK, complq, gen_flag);
+	complq->next_to_clean = ntc;
+}
+
+/**
  * idpf_tx_splitq_build_ctb - populate command tag and size for queue
  * based scheduling descriptors
  * @desc: descriptor to populate
@@ -2127,44 +2390,52 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
 				    struct idpf_tx_splitq_params *params,
 				    u16 td_cmd, u16 size)
 {
-	desc->flow.qw1.cmd_dtype = (u16)params->dtype | td_cmd;
+	*(u32 *)&desc->flow.qw1.cmd_dtype = (u8)(params->dtype | td_cmd);
 	desc->flow.qw1.rxr_bufsize = cpu_to_le16((u16)size);
 	desc->flow.qw1.compl_tag = cpu_to_le16(params->compl_tag);
 }
 
 /**
+ * idpf_tx_splitq_has_room - check if enough Tx splitq resources are available
+ * @tx_q: the queue to be checked
+ * @descs_needed: number of descriptors required for this packet
+ * @bufs_needed: number of Tx buffers required for this packet
+ *
+ * Return: 0 if no room available, 1 otherwise
+ */
+static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 descs_needed,
+			     u32 bufs_needed)
+{
+	if (IDPF_DESC_UNUSED(tx_q) < descs_needed ||
+	    IDPF_TX_COMPLQ_PENDING(tx_q->txq_grp) >
+		IDPF_TX_COMPLQ_OVERFLOW_THRESH(tx_q->txq_grp->complq) ||
+	    idpf_tx_splitq_get_free_bufs(tx_q->refillq) < bufs_needed)
+		return 0;
+	return 1;
+}
+
+/**
  * idpf_tx_maybe_stop_splitq - 1st level check for Tx splitq stop conditions
  * @tx_q: the queue to be checked
  * @descs_needed: number of descriptors required for this packet
+ * @bufs_needed: number of buffers needed for this packet
  *
- * Returns 0 if stop is not needed
+ * Return: 0 if stop is not needed
  */
 static int idpf_tx_maybe_stop_splitq(struct idpf_tx_queue *tx_q,
-				     unsigned int descs_needed)
+				     u32 descs_needed,
+				     u32 bufs_needed)
 {
-	if (idpf_tx_maybe_stop_common(tx_q, descs_needed))
-		goto out;
-
-	/* If there are too many outstanding completions expected on the
-	 * completion queue, stop the TX queue to give the device some time to
-	 * catch up
-	 */
-	if (unlikely(IDPF_TX_COMPLQ_PENDING(tx_q->txq_grp) >
-		     IDPF_TX_COMPLQ_OVERFLOW_THRESH(tx_q->txq_grp->complq)))
-		goto splitq_stop;
-
-	/* Also check for available book keeping buffers; if we are low, stop
-	 * the queue to wait for more completions
+	/* Since we have multiple resources to check for splitq, our
+	 * start,stop_thrs becomes a boolean check instead of a count
+	 * threshold.
 	 */
-	if (unlikely(IDPF_TX_BUF_RSV_LOW(tx_q)))
-		goto splitq_stop;
-
-	return 0;
-
-splitq_stop:
-	netif_stop_subqueue(tx_q->netdev, tx_q->idx);
+	if (netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
+				      idpf_txq_has_room(tx_q, descs_needed,
+							bufs_needed),
+				      1, 1))
+		return 0;
 
-out:
 	u64_stats_update_begin(&tx_q->stats_sync);
 	u64_stats_inc(&tx_q->q_stats.q_busy);
 	u64_stats_update_end(&tx_q->stats_sync);
@@ -2190,12 +2461,6 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 	nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
 	tx_q->next_to_use = val;
 
-	if (idpf_tx_maybe_stop_common(tx_q, IDPF_TX_DESC_NEEDED)) {
-		u64_stats_update_begin(&tx_q->stats_sync);
-		u64_stats_inc(&tx_q->q_stats.q_busy);
-		u64_stats_update_end(&tx_q->stats_sync);
-	}
-
 	/* Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.  (Only
 	 * applicable for weak-ordered memory model archs,
@@ -2209,14 +2474,16 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 }
 
 /**
- * idpf_tx_desc_count_required - calculate number of Tx descriptors needed
+ * idpf_tx_res_count_required - get number of Tx resources needed for this pkt
  * @txq: queue to send buffer on
  * @skb: send buffer
+ * @bufs_needed: (output) number of buffers needed for this skb.
  *
- * Returns number of data descriptors needed for this skb.
+ * Return: number of data descriptors and buffers needed for this skb.
  */
-unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
-					 struct sk_buff *skb)
+unsigned int idpf_tx_res_count_required(struct idpf_tx_queue *txq,
+					struct sk_buff *skb,
+					u32 *bufs_needed)
 {
 	const struct skb_shared_info *shinfo;
 	unsigned int count = 0, i;
@@ -2227,6 +2494,7 @@ unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
 		return count;
 
 	shinfo = skb_shinfo(skb);
+	*bufs_needed += shinfo->nr_frags;
 	for (i = 0; i < shinfo->nr_frags; i++) {
 		unsigned int size;
 
@@ -2256,71 +2524,89 @@ unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
 }
 
 /**
- * idpf_tx_dma_map_error - handle TX DMA map errors
- * @txq: queue to send buffer on
- * @skb: send buffer
- * @first: original first buffer info buffer for packet
- * @idx: starting point on ring to unwind
+ * idpf_tx_splitq_bump_ntu - adjust NTU and generation
+ * @txq: the tx ring to wrap
+ * @ntu: ring index to bump
  */
-void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
-			   struct idpf_tx_buf *first, u16 idx)
+static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_tx_queue *txq, u16 ntu)
 {
-	struct libeth_sq_napi_stats ss = { };
-	struct libeth_cq_pp cp = {
-		.dev	= txq->dev,
-		.ss	= &ss,
-	};
+	ntu++;
 
-	u64_stats_update_begin(&txq->stats_sync);
-	u64_stats_inc(&txq->q_stats.dma_map_errs);
-	u64_stats_update_end(&txq->stats_sync);
+	if (ntu == txq->desc_count)
+		ntu = 0;
 
-	/* clear dma mappings for failed tx_buf map */
-	for (;;) {
-		struct idpf_tx_buf *tx_buf;
+	return ntu;
+}
 
-		tx_buf = &txq->tx_buf[idx];
-		libeth_tx_complete(tx_buf, &cp);
-		if (tx_buf == first)
-			break;
-		if (idx == 0)
-			idx = txq->desc_count;
-		idx--;
-	}
+/**
+ * idpf_tx_get_free_buf_id - get a free buffer ID from the refill queue
+ * @refillq: refill queue to get buffer ID from
+ * @buf_id: return buffer ID
+ *
+ * Return: true if a buffer ID was found, false if not
+ */
+static bool idpf_tx_get_free_buf_id(struct idpf_sw_queue *refillq,
+				    u32 *buf_id)
+{
+	u32 ntc = refillq->next_to_clean;
+	u32 refill_desc;
 
-	if (skb_is_gso(skb)) {
-		union idpf_tx_flex_desc *tx_desc;
+	refill_desc = refillq->ring[ntc];
 
-		/* If we failed a DMA mapping for a TSO packet, we will have
-		 * used one additional descriptor for a context
-		 * descriptor. Reset that here.
-		 */
-		tx_desc = &txq->flex_tx[idx];
-		memset(tx_desc, 0, sizeof(struct idpf_flex_tx_ctx_desc));
-		if (idx == 0)
-			idx = txq->desc_count;
-		idx--;
+	if (unlikely(idpf_queue_has(RFL_GEN_CHK, refillq) !=
+		     !!(refill_desc & IDPF_RFL_BI_GEN_M)))
+		return false;
+
+	*buf_id = FIELD_GET(IDPF_RFL_BI_BUFID_M, refill_desc);
+
+	if (unlikely(++ntc == refillq->desc_count)) {
+		idpf_queue_change(RFL_GEN_CHK, refillq);
+		ntc = 0;
 	}
 
-	/* Update tail in case netdev_xmit_more was previously true */
-	idpf_tx_buf_hw_update(txq, idx, false);
+	refillq->next_to_clean = ntc;
+
+	return true;
 }
 
 /**
- * idpf_tx_splitq_bump_ntu - adjust NTU and generation
- * @txq: the tx ring to wrap
- * @ntu: ring index to bump
+ * idpf_tx_splitq_pkt_err_unmap - Unmap buffers and bump tail in case of error
+ * @txq: Tx queue to unwind
+ * @params: pointer to splitq params struct
+ * @first: starting buffer for packet to unmap
  */
-static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_tx_queue *txq, u16 ntu)
+static void idpf_tx_splitq_pkt_err_unmap(struct idpf_tx_queue *txq,
+					 struct idpf_tx_splitq_params *params,
+					 struct idpf_tx_buf *first)
 {
-	ntu++;
+	struct idpf_sw_queue *refillq = txq->refillq;
+	struct libeth_sq_napi_stats ss = { };
+	struct idpf_tx_buf *tx_buf = first;
+	struct libeth_cq_pp cp = {
+		.dev    = txq->dev,
+		.ss     = &ss,
+	};
 
-	if (ntu == txq->desc_count) {
-		ntu = 0;
-		txq->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(txq);
+	u64_stats_update_begin(&txq->stats_sync);
+	u64_stats_inc(&txq->q_stats.dma_map_errs);
+	u64_stats_update_end(&txq->stats_sync);
+
+	libeth_tx_complete(tx_buf, &cp);
+	while (idpf_tx_buf_next(tx_buf) != IDPF_TXBUF_NULL) {
+		tx_buf = &txq->tx_buf[idpf_tx_buf_next(tx_buf)];
+		libeth_tx_complete(tx_buf, &cp);
 	}
 
-	return ntu;
+	/* Update tail in case netdev_xmit_more was previously true. */
+	idpf_tx_buf_hw_update(txq, params->prev_ntu, false);
+
+	if (!refillq)
+		return;
+
+	/* Restore refillq state to avoid leaking tags. */
+	if (params->prev_refill_gen != idpf_queue_has(RFL_GEN_CHK, refillq))
+		idpf_queue_change(RFL_GEN_CHK, refillq);
+	refillq->next_to_clean = params->prev_refill_ntc;
 }
 
 /**
@@ -2344,6 +2630,7 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 	struct netdev_queue *nq;
 	struct sk_buff *skb;
 	skb_frag_t *frag;
+	u32 next_buf_id;
 	u16 td_cmd = 0;
 	dma_addr_t dma;
 
@@ -2361,17 +2648,16 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 	tx_buf = first;
 	first->nr_frags = 0;
 
-	params->compl_tag =
-		(tx_q->compl_tag_cur_gen << tx_q->compl_tag_gen_s) | i;
-
 	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
 		unsigned int max_data = IDPF_TX_MAX_DESC_DATA_ALIGNED;
 
-		if (dma_mapping_error(tx_q->dev, dma))
-			return idpf_tx_dma_map_error(tx_q, skb, first, i);
+		if (unlikely(dma_mapping_error(tx_q->dev, dma))) {
+			idpf_tx_buf_next(tx_buf) = IDPF_TXBUF_NULL;
+			return idpf_tx_splitq_pkt_err_unmap(tx_q, params,
+							    first);
+		}
 
 		first->nr_frags++;
-		idpf_tx_buf_compl_tag(tx_buf) = params->compl_tag;
 		tx_buf->type = LIBETH_SQE_FRAG;
 
 		/* record length, and DMA address */
@@ -2427,29 +2713,12 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 						  max_data);
 
 			if (unlikely(++i == tx_q->desc_count)) {
-				tx_buf = tx_q->tx_buf;
 				tx_desc = &tx_q->flex_tx[0];
 				i = 0;
-				tx_q->compl_tag_cur_gen =
-					IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
 			} else {
-				tx_buf++;
 				tx_desc++;
 			}
 
-			/* Since this packet has a buffer that is going to span
-			 * multiple descriptors, it's going to leave holes in
-			 * to the TX buffer ring. To ensure these holes do not
-			 * cause issues in the cleaning routines, we will clear
-			 * them of any stale data and assign them the same
-			 * completion tag as the current packet. Then when the
-			 * packet is being cleaned, the cleaning routines will
-			 * simply pass over these holes and finish cleaning the
-			 * rest of the packet.
-			 */
-			tx_buf->type = LIBETH_SQE_EMPTY;
-			idpf_tx_buf_compl_tag(tx_buf) = params->compl_tag;
-
 			/* Adjust the DMA offset and the remaining size of the
 			 * fragment.  On the first iteration of this loop,
 			 * max_data will be >= 12K and <= 16K-1.  On any
@@ -2474,15 +2743,25 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 		idpf_tx_splitq_build_desc(tx_desc, params, td_cmd, size);
 
 		if (unlikely(++i == tx_q->desc_count)) {
-			tx_buf = tx_q->tx_buf;
 			tx_desc = &tx_q->flex_tx[0];
 			i = 0;
-			tx_q->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
 		} else {
-			tx_buf++;
 			tx_desc++;
 		}
 
+		if (idpf_queue_has(FLOW_SCH_EN, tx_q)) {
+			if (unlikely(!idpf_tx_get_free_buf_id(tx_q->refillq,
+							      &next_buf_id))) {
+				idpf_tx_buf_next(tx_buf) = IDPF_TXBUF_NULL;
+				return idpf_tx_splitq_pkt_err_unmap(tx_q, params,
+								    first);
+			}
+		} else {
+			next_buf_id = i;
+		}
+		idpf_tx_buf_next(tx_buf) = next_buf_id;
+		tx_buf = &tx_q->tx_buf[next_buf_id];
+
 		size = skb_frag_size(frag);
 		data_len -= size;
 
@@ -2497,6 +2776,7 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 
 	/* write last descriptor with RS and EOP bits */
 	first->rs_idx = i;
+	idpf_tx_buf_next(tx_buf) = IDPF_TXBUF_NULL;
 	td_cmd |= params->eop_cmd;
 	idpf_tx_splitq_build_desc(tx_desc, params, td_cmd, size);
 	i = idpf_tx_splitq_bump_ntu(tx_q, i);
@@ -2586,111 +2866,6 @@ int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off)
 	return 1;
 }
 
-/**
- * __idpf_chk_linearize - Check skb is not using too many buffers
- * @skb: send buffer
- * @max_bufs: maximum number of buffers
- *
- * For TSO we need to count the TSO header and segment payload separately.  As
- * such we need to check cases where we have max_bufs-1 fragments or more as we
- * can potentially require max_bufs+1 DMA transactions, 1 for the TSO header, 1
- * for the segment payload in the first descriptor, and another max_buf-1 for
- * the fragments.
- */
-static bool __idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs)
-{
-	const struct skb_shared_info *shinfo = skb_shinfo(skb);
-	const skb_frag_t *frag, *stale;
-	int nr_frags, sum;
-
-	/* no need to check if number of frags is less than max_bufs - 1 */
-	nr_frags = shinfo->nr_frags;
-	if (nr_frags < (max_bufs - 1))
-		return false;
-
-	/* We need to walk through the list and validate that each group
-	 * of max_bufs-2 fragments totals at least gso_size.
-	 */
-	nr_frags -= max_bufs - 2;
-	frag = &shinfo->frags[0];
-
-	/* Initialize size to the negative value of gso_size minus 1.  We use
-	 * this as the worst case scenario in which the frag ahead of us only
-	 * provides one byte which is why we are limited to max_bufs-2
-	 * descriptors for a single transmit as the header and previous
-	 * fragment are already consuming 2 descriptors.
-	 */
-	sum = 1 - shinfo->gso_size;
-
-	/* Add size of frags 0 through 4 to create our initial sum */
-	sum += skb_frag_size(frag++);
-	sum += skb_frag_size(frag++);
-	sum += skb_frag_size(frag++);
-	sum += skb_frag_size(frag++);
-	sum += skb_frag_size(frag++);
-
-	/* Walk through fragments adding latest fragment, testing it, and
-	 * then removing stale fragments from the sum.
-	 */
-	for (stale = &shinfo->frags[0];; stale++) {
-		int stale_size = skb_frag_size(stale);
-
-		sum += skb_frag_size(frag++);
-
-		/* The stale fragment may present us with a smaller
-		 * descriptor than the actual fragment size. To account
-		 * for that we need to remove all the data on the front and
-		 * figure out what the remainder would be in the last
-		 * descriptor associated with the fragment.
-		 */
-		if (stale_size > IDPF_TX_MAX_DESC_DATA) {
-			int align_pad = -(skb_frag_off(stale)) &
-					(IDPF_TX_MAX_READ_REQ_SIZE - 1);
-
-			sum -= align_pad;
-			stale_size -= align_pad;
-
-			do {
-				sum -= IDPF_TX_MAX_DESC_DATA_ALIGNED;
-				stale_size -= IDPF_TX_MAX_DESC_DATA_ALIGNED;
-			} while (stale_size > IDPF_TX_MAX_DESC_DATA);
-		}
-
-		/* if sum is negative we failed to make sufficient progress */
-		if (sum < 0)
-			return true;
-
-		if (!nr_frags--)
-			break;
-
-		sum -= stale_size;
-	}
-
-	return false;
-}
-
-/**
- * idpf_chk_linearize - Check if skb exceeds max descriptors per packet
- * @skb: send buffer
- * @max_bufs: maximum scatter gather buffers for single packet
- * @count: number of buffers this packet needs
- *
- * Make sure we don't exceed maximum scatter gather buffers for a single
- * packet. We have to do some special checking around the boundary (max_bufs-1)
- * if TSO is on since we need count the TSO header and payload separately.
- * E.g.: a packet with 7 fragments can require 9 DMA transactions; 1 for TSO
- * header, 1 for segment payload, and then 7 for the fragments.
- */
-static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
-			       unsigned int count)
-{
-	if (likely(count < max_bufs))
-		return false;
-	if (skb_is_gso(skb))
-		return __idpf_chk_linearize(skb, max_bufs);
-
-	return count > max_bufs;
-}
 
 /**
  * idpf_tx_splitq_get_ctx_desc - grab next desc and update buffer ring
@@ -2699,14 +2874,12 @@ static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
  * Since the TX buffer rings mimics the descriptor ring, update the tx buffer
  * ring entry to reflect that this index is a context descriptor
  */
-static struct idpf_flex_tx_ctx_desc *
+static union idpf_flex_tx_ctx_desc *
 idpf_tx_splitq_get_ctx_desc(struct idpf_tx_queue *txq)
 {
-	struct idpf_flex_tx_ctx_desc *desc;
+	union idpf_flex_tx_ctx_desc *desc;
 	int i = txq->next_to_use;
 
-	txq->tx_buf[i].type = LIBETH_SQE_CTX;
-
 	/* grab the next descriptor */
 	desc = &txq->flex_ctx[i];
 	txq->next_to_use = idpf_tx_splitq_bump_ntu(txq, i);
@@ -2732,6 +2905,88 @@ netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb)
 	return NETDEV_TX_OK;
 }
 
+#if (IS_ENABLED(CONFIG_PTP_1588_CLOCK))
+/**
+ * idpf_tx_tstamp - set up context descriptor for hardware timestamp
+ * @tx_q: queue to send buffer on
+ * @skb: pointer to the SKB we're sending
+ * @off: pointer to the offload struct
+ *
+ * Return: Positive index number on success, negative otherwise.
+ */
+static int idpf_tx_tstamp(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			  struct idpf_tx_offload_params *off)
+{
+	int err, idx;
+
+	/* only timestamp the outbound packet if the user has requested it */
+	if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
+		return -1;
+
+	if (!idpf_ptp_get_txq_tstamp_capability(tx_q))
+		return -1;
+
+	/* Tx timestamps cannot be sampled when doing TSO */
+	if (off->tx_flags & IDPF_TX_FLAGS_TSO)
+		return -1;
+
+	/* Grab an open timestamp slot */
+	err = idpf_ptp_request_ts(tx_q, skb, &idx);
+	if (err) {
+		u64_stats_update_begin(&tx_q->stats_sync);
+		u64_stats_inc(&tx_q->q_stats.tstamp_skipped);
+		u64_stats_update_end(&tx_q->stats_sync);
+
+		return -1;
+	}
+
+	off->tx_flags |= IDPF_TX_FLAGS_TSYN;
+
+	return idx;
+}
+
+/**
+ * idpf_tx_set_tstamp_desc - Set the Tx descriptor fields needed to generate
+ *			     PHY Tx timestamp
+ * @ctx_desc: Context descriptor
+ * @idx: Index of the Tx timestamp latch
+ */
+static void idpf_tx_set_tstamp_desc(union idpf_flex_tx_ctx_desc *ctx_desc,
+				    u32 idx)
+{
+	ctx_desc->tsyn.qw1 = le64_encode_bits(IDPF_TX_DESC_DTYPE_CTX,
+					      IDPF_TX_CTX_DTYPE_M) |
+			     le64_encode_bits(IDPF_TX_CTX_DESC_TSYN,
+					      IDPF_TX_CTX_CMD_M) |
+			     le64_encode_bits(idx, IDPF_TX_CTX_TSYN_REG_M);
+}
+#else /* CONFIG_PTP_1588_CLOCK */
+static int idpf_tx_tstamp(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			  struct idpf_tx_offload_params *off)
+{
+	return -1;
+}
+
+static void idpf_tx_set_tstamp_desc(union idpf_flex_tx_ctx_desc *ctx_desc,
+				    u32 idx)
+{ }
+#endif /* CONFIG_PTP_1588_CLOCK */
+
+/**
+ * idpf_tx_splitq_need_re - check whether RE bit needs to be set
+ * @tx_q: pointer to Tx queue
+ *
+ * Return: true if RE bit needs to be set, false otherwise
+ */
+static bool idpf_tx_splitq_need_re(struct idpf_tx_queue *tx_q)
+{
+	int gap = tx_q->next_to_use - tx_q->last_re;
+
+	gap += (gap < 0) ? tx_q->desc_count : 0;
+
+	return gap >= IDPF_TX_SPLITQ_RE_MIN_GAP;
+}
+
 /**
  * idpf_tx_splitq_frame - Sends buffer on Tx ring using flex descriptors
  * @skb: send buffer
@@ -2742,12 +2997,16 @@ netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb)
 static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 					struct idpf_tx_queue *tx_q)
 {
-	struct idpf_tx_splitq_params tx_params = { };
+	struct idpf_tx_splitq_params tx_params = {
+		.prev_ntu = tx_q->next_to_use,
+	};
+	union idpf_flex_tx_ctx_desc *ctx_desc;
 	struct idpf_tx_buf *first;
-	unsigned int count;
-	int tso;
+	u32 count, buf_count = 1;
+	int tso, idx;
+	u32 buf_id;
 
-	count = idpf_tx_desc_count_required(tx_q, skb);
+	count = idpf_tx_res_count_required(tx_q, skb, &buf_count);
 	if (unlikely(!count))
 		return idpf_tx_drop_skb(tx_q, skb);
 
@@ -2757,7 +3016,7 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 
 	/* Check for splitq specific TX resources */
 	count += (IDPF_TX_DESCS_PER_CACHE_LINE + tso);
-	if (idpf_tx_maybe_stop_splitq(tx_q, count)) {
+	if (idpf_tx_maybe_stop_splitq(tx_q, count, buf_count)) {
 		idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false);
 
 		return NETDEV_TX_BUSY;
@@ -2765,8 +3024,7 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 
 	if (tso) {
 		/* If tso is needed, set up context desc */
-		struct idpf_flex_tx_ctx_desc *ctx_desc =
-			idpf_tx_splitq_get_ctx_desc(tx_q);
+		ctx_desc = idpf_tx_splitq_get_ctx_desc(tx_q);
 
 		ctx_desc->tso.qw1.cmd_dtype =
 				cpu_to_le16(IDPF_TX_DESC_DTYPE_FLEX_TSO_CTX |
@@ -2784,36 +3042,53 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 		u64_stats_update_end(&tx_q->stats_sync);
 	}
 
-	/* record the location of the first descriptor for this packet */
-	first = &tx_q->tx_buf[tx_q->next_to_use];
-	first->skb = skb;
-
-	if (tso) {
-		first->packets = tx_params.offload.tso_segs;
-		first->bytes = skb->len +
-			((first->packets - 1) * tx_params.offload.tso_hdr_len);
-	} else {
-		first->packets = 1;
-		first->bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
+	idx = idpf_tx_tstamp(tx_q, skb, &tx_params.offload);
+	if (idx != -1) {
+		ctx_desc = idpf_tx_splitq_get_ctx_desc(tx_q);
+		idpf_tx_set_tstamp_desc(ctx_desc, idx);
 	}
 
 	if (idpf_queue_has(FLOW_SCH_EN, tx_q)) {
+		struct idpf_sw_queue *refillq = tx_q->refillq;
+
+		/* Save refillq state in case of a packet rollback.  Otherwise,
+		 * the tags will be leaked since they will be popped from the
+		 * refillq but never reposted during cleaning.
+		 */
+		tx_params.prev_refill_gen =
+			idpf_queue_has(RFL_GEN_CHK, refillq);
+		tx_params.prev_refill_ntc = refillq->next_to_clean;
+
+		if (unlikely(!idpf_tx_get_free_buf_id(tx_q->refillq,
+						      &buf_id))) {
+			if (tx_params.prev_refill_gen !=
+			    idpf_queue_has(RFL_GEN_CHK, refillq))
+				idpf_queue_change(RFL_GEN_CHK, refillq);
+			refillq->next_to_clean = tx_params.prev_refill_ntc;
+
+			tx_q->next_to_use = tx_params.prev_ntu;
+			return idpf_tx_drop_skb(tx_q, skb);
+		}
+		tx_params.compl_tag = buf_id;
+
 		tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE;
 		tx_params.eop_cmd = IDPF_TXD_FLEX_FLOW_CMD_EOP;
-		/* Set the RE bit to catch any packets that may have not been
-		 * stashed during RS completion cleaning. MIN_GAP is set to
-		 * MIN_RING size to ensure it will be set at least once each
-		 * time around the ring.
+		/* Set the RE bit to periodically "clean" the descriptor ring.
+		 * MIN_GAP is set to MIN_RING size to ensure it will be set at
+		 * least once each time around the ring.
 		 */
-		if (!(tx_q->next_to_use % IDPF_TX_SPLITQ_RE_MIN_GAP)) {
+		if (idpf_tx_splitq_need_re(tx_q)) {
 			tx_params.eop_cmd |= IDPF_TXD_FLEX_FLOW_CMD_RE;
 			tx_q->txq_grp->num_completions_pending++;
+			tx_q->last_re = tx_q->next_to_use;
 		}
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			tx_params.offload.td_cmd |= IDPF_TXD_FLEX_FLOW_CMD_CS_EN;
 
 	} else {
+		buf_id = tx_q->next_to_use;
+
 		tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_L2TAG1_L2TAG2;
 		tx_params.eop_cmd = IDPF_TXD_LAST_DESC_CMD;
 
@@ -2821,6 +3096,18 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 			tx_params.offload.td_cmd |= IDPF_TX_FLEX_DESC_CMD_CS_EN;
 	}
 
+	first = &tx_q->tx_buf[buf_id];
+	first->skb = skb;
+
+	if (tso) {
+		first->packets = tx_params.offload.tso_segs;
+		first->bytes = skb->len +
+			((first->packets - 1) * tx_params.offload.tso_hdr_len);
+	} else {
+		first->packets = 1;
+		first->bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
+	}
+
 	idpf_tx_splitq_map(tx_q, &tx_params, first);
 
 	return NETDEV_TX_OK;
@@ -2835,10 +3122,11 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
  */
 netdev_tx_t idpf_tx_start(struct sk_buff *skb, struct net_device *netdev)
 {
-	struct idpf_vport *vport = idpf_netdev_to_vport(netdev);
+	const struct idpf_vport *vport = idpf_netdev_to_vport(netdev);
 	struct idpf_tx_queue *tx_q;
 
-	if (unlikely(skb_get_queue_mapping(skb) >= vport->num_txq)) {
+	if (unlikely(skb_get_queue_mapping(skb) >=
+		     vport->num_txq - vport->num_xdp_txq)) {
 		dev_kfree_skb_any(skb);
 
 		return NETDEV_TX_OK;
@@ -2875,7 +3163,7 @@ idpf_rx_hash(const struct idpf_rx_queue *rxq, struct sk_buff *skb,
 {
 	u32 hash;
 
-	if (!libeth_rx_pt_has_hash(rxq->netdev, decoded))
+	if (!libeth_rx_pt_has_hash(rxq->xdp_rxq.dev, decoded))
 		return;
 
 	hash = le16_to_cpu(rx_desc->hash1) |
@@ -2895,13 +3183,13 @@ idpf_rx_hash(const struct idpf_rx_queue *rxq, struct sk_buff *skb,
  * skb->protocol must be set before this function is called
  */
 static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb,
-			 struct idpf_rx_csum_decoded csum_bits,
+			 struct libeth_rx_csum csum_bits,
 			 struct libeth_rx_pt decoded)
 {
 	bool ipv4, ipv6;
 
 	/* check if Rx checksum is enabled */
-	if (!libeth_rx_pt_has_checksum(rxq->netdev, decoded))
+	if (!libeth_rx_pt_has_checksum(rxq->xdp_rxq.dev, decoded))
 		return;
 
 	/* check if HW has decoded the packet and checksum */
@@ -2923,7 +3211,7 @@ static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	if (unlikely(csum_bits.l4e))
 		goto checksum_fail;
 
-	if (csum_bits.raw_csum_inv ||
+	if (!csum_bits.raw_csum_valid ||
 	    decoded.inner_prot == LIBETH_RX_PT_INNER_SCTP) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 		return;
@@ -2946,10 +3234,10 @@ checksum_fail:
  *
  * Return: parsed checksum status.
  **/
-static struct idpf_rx_csum_decoded
+static struct libeth_rx_csum
 idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc)
 {
-	struct idpf_rx_csum_decoded csum = { };
+	struct libeth_rx_csum csum = { };
 	u8 qword0, qword1;
 
 	qword0 = rx_desc->status_err0_qw0;
@@ -2965,9 +3253,9 @@ idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 *
 			       qword1);
 	csum.ipv6exadd = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_IPV6EXADD_M,
 				   qword0);
-	csum.raw_csum_inv =
-		le16_get_bits(rx_desc->ptype_err_fflags0,
-			      VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M);
+	csum.raw_csum_valid =
+		!le16_get_bits(rx_desc->ptype_err_fflags0,
+			       VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M);
 	csum.raw_csum = le16_to_cpu(rx_desc->misc.raw_cs);
 
 	return csum;
@@ -3008,14 +3296,11 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 		return -EINVAL;
 
 	rsc_segments = DIV_ROUND_UP(skb->data_len, rsc_seg_len);
-	if (unlikely(rsc_segments == 1))
-		return 0;
 
 	NAPI_GRO_CB(skb)->count = rsc_segments;
 	skb_shinfo(skb)->gso_size = rsc_seg_len;
 
 	skb_reset_network_header(skb);
-	len = skb->len - skb_transport_offset(skb);
 
 	if (ipv4) {
 		struct iphdr *ipv4h = ip_hdr(skb);
@@ -3024,6 +3309,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 
 		/* Reset and set transport header offset in skb */
 		skb_set_transport_header(skb, sizeof(struct iphdr));
+		len = skb->len - skb_transport_offset(skb);
 
 		/* Compute the TCP pseudo header checksum*/
 		tcp_hdr(skb)->check =
@@ -3033,6 +3319,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 		skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+		len = skb->len - skb_transport_offset(skb);
 		tcp_hdr(skb)->check =
 			~tcp_v6_check(len, &ipv6h->saddr, &ipv6h->daddr, 0);
 	}
@@ -3047,7 +3334,34 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 }
 
 /**
- * idpf_rx_process_skb_fields - Populate skb header fields from Rx descriptor
+ * idpf_rx_hwtstamp - check for an RX timestamp and pass up the stack
+ * @rxq: pointer to the rx queue that receives the timestamp
+ * @rx_desc: pointer to rx descriptor containing timestamp
+ * @skb: skb to put timestamp in
+ */
+static void
+idpf_rx_hwtstamp(const struct idpf_rx_queue *rxq,
+		 const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc,
+		 struct sk_buff *skb)
+{
+	u64 cached_time, ts_ns;
+	u32 ts_high;
+
+	if (!(rx_desc->ts_low & VIRTCHNL2_RX_FLEX_TSTAMP_VALID))
+		return;
+
+	cached_time = READ_ONCE(rxq->cached_phc_time);
+
+	ts_high = le32_to_cpu(rx_desc->ts_high);
+	ts_ns = idpf_ptp_tstamp_extend_32b_to_64b(cached_time, ts_high);
+
+	*skb_hwtstamps(skb) = (struct skb_shared_hwtstamps) {
+		.hwtstamp = ns_to_ktime(ts_ns),
+	};
+}
+
+/**
+ * __idpf_rx_process_skb_fields - Populate skb header fields from Rx descriptor
  * @rxq: Rx descriptor ring packet is being transacted on
  * @skb: pointer to current skb being populated
  * @rx_desc: Receive descriptor
@@ -3057,10 +3371,10 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
  * other fields within the skb.
  */
 static int
-idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
-			   const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc)
+__idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
+			     const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc)
 {
-	struct idpf_rx_csum_decoded csum_bits;
+	struct libeth_rx_csum csum_bits;
 	struct libeth_rx_pt decoded;
 	u16 rx_ptype;
 
@@ -3071,7 +3385,8 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	/* process RSS/hash */
 	idpf_rx_hash(rxq, skb, rx_desc, decoded);
 
-	skb->protocol = eth_type_trans(skb, rxq->netdev);
+	if (idpf_queue_has(PTP, rxq))
+		idpf_rx_hwtstamp(rxq, rx_desc, skb);
 
 	if (le16_get_bits(rx_desc->hdrlen_flags,
 			  VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M))
@@ -3080,30 +3395,27 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	csum_bits = idpf_rx_splitq_extract_csum_bits(rx_desc);
 	idpf_rx_csum(rxq, skb, csum_bits, decoded);
 
-	skb_record_rx_queue(skb, rxq->idx);
-
 	return 0;
 }
 
-/**
- * idpf_rx_add_frag - Add contents of Rx buffer to sk_buff as a frag
- * @rx_buf: buffer containing page to add
- * @skb: sk_buff to place the data into
- * @size: packet length from rx_desc
- *
- * This function will add the data contained in rx_buf->page to the skb.
- * It will just attach the page as a frag to the skb.
- * The function will then update the page offset.
- */
-void idpf_rx_add_frag(struct idpf_rx_buf *rx_buf, struct sk_buff *skb,
-		      unsigned int size)
+bool idpf_rx_process_skb_fields(struct sk_buff *skb,
+				const struct libeth_xdp_buff *xdp,
+				struct libeth_rq_napi_stats *rs)
 {
-	u32 hr = rx_buf->page->pp->p.offset;
+	struct idpf_rx_queue *rxq;
+
+	rxq = libeth_xdp_buff_to_rq(xdp, typeof(*rxq), xdp_rxq);
 
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page,
-			rx_buf->offset + hr, size, rx_buf->truesize);
+	return !__idpf_rx_process_skb_fields(rxq, skb, xdp->desc);
 }
 
+LIBETH_XDP_DEFINE_START();
+LIBETH_XDP_DEFINE_RUN(static idpf_xdp_run_pass, idpf_xdp_run_prog,
+		      idpf_xdp_tx_flush_bulk, idpf_rx_process_skb_fields);
+LIBETH_XDP_DEFINE_FINALIZE(static idpf_xdp_finalize_rx, idpf_xdp_tx_flush_bulk,
+			   idpf_xdp_tx_finalize);
+LIBETH_XDP_DEFINE_END();
+
 /**
  * idpf_rx_hsplit_wa - handle header buffer overflows and split errors
  * @hdr: Rx buffer for the headers
@@ -3124,51 +3436,28 @@ static u32 idpf_rx_hsplit_wa(const struct libeth_fqe *hdr,
 			     struct libeth_fqe *buf, u32 data_len)
 {
 	u32 copy = data_len <= L1_CACHE_BYTES ? data_len : ETH_HLEN;
+	struct page *hdr_page, *buf_page;
 	const void *src;
 	void *dst;
 
-	if (!libeth_rx_sync_for_cpu(buf, copy))
+	if (unlikely(netmem_is_net_iov(buf->netmem)) ||
+	    !libeth_rx_sync_for_cpu(buf, copy))
 		return 0;
 
-	dst = page_address(hdr->page) + hdr->offset + hdr->page->pp->p.offset;
-	src = page_address(buf->page) + buf->offset + buf->page->pp->p.offset;
-	memcpy(dst, src, LARGEST_ALIGN(copy));
+	hdr_page = __netmem_to_page(hdr->netmem);
+	buf_page = __netmem_to_page(buf->netmem);
+	dst = page_address(hdr_page) + hdr->offset +
+		pp_page_to_nmdesc(hdr_page)->pp->p.offset;
+	src = page_address(buf_page) + buf->offset +
+		pp_page_to_nmdesc(buf_page)->pp->p.offset;
 
+	memcpy(dst, src, LARGEST_ALIGN(copy));
 	buf->offset += copy;
 
 	return copy;
 }
 
 /**
- * idpf_rx_build_skb - Allocate skb and populate it from header buffer
- * @buf: Rx buffer to pull data from
- * @size: the length of the packet
- *
- * This function allocates an skb. It then populates it with the page data from
- * the current receive descriptor, taking care to set up the skb correctly.
- */
-struct sk_buff *idpf_rx_build_skb(const struct libeth_fqe *buf, u32 size)
-{
-	u32 hr = buf->page->pp->p.offset;
-	struct sk_buff *skb;
-	void *va;
-
-	va = page_address(buf->page) + buf->offset;
-	prefetch(va + hr);
-
-	skb = napi_build_skb(va, buf->truesize);
-	if (unlikely(!skb))
-		return NULL;
-
-	skb_mark_for_recycle(skb);
-
-	skb_reserve(skb, hr);
-	__skb_put(skb, size);
-
-	return skb;
-}
-
-/**
  * idpf_rx_splitq_test_staterr - tests bits in Rx descriptor
  * status and error fields
  * @stat_err_field: field from descriptor to test bits in
@@ -3209,13 +3498,18 @@ static bool idpf_rx_splitq_is_eop(struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_de
  */
 static int idpf_rx_splitq_clean(struct idpf_rx_queue *rxq, int budget)
 {
-	int total_rx_bytes = 0, total_rx_pkts = 0;
 	struct idpf_buf_queue *rx_bufq = NULL;
-	struct sk_buff *skb = rxq->skb;
+	struct libeth_rq_napi_stats rs = { };
 	u16 ntc = rxq->next_to_clean;
+	LIBETH_XDP_ONSTACK_BUFF(xdp);
+	LIBETH_XDP_ONSTACK_BULK(bq);
+
+	libeth_xdp_tx_init_bulk(&bq, rxq->xdp_prog, rxq->xdp_rxq.dev,
+				rxq->xdpsqs, rxq->num_xdp_txq);
+	libeth_xdp_init_buff(xdp, &rxq->xdp, &rxq->xdp_rxq);
 
 	/* Process Rx packets bounded by budget */
-	while (likely(total_rx_pkts < budget)) {
+	while (likely(rs.packets < budget)) {
 		struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc;
 		struct libeth_fqe *hdr, *rx_buf = NULL;
 		struct idpf_sw_queue *refillq = NULL;
@@ -3229,18 +3523,14 @@ static int idpf_rx_splitq_clean(struct idpf_rx_queue *rxq, int budget)
 		/* get the Rx desc from Rx queue based on 'next_to_clean' */
 		rx_desc = &rxq->rx[ntc].flex_adv_nic_3_wb;
 
-		/* This memory barrier is needed to keep us from reading
-		 * any other fields out of the rx_desc
-		 */
-		dma_rmb();
-
 		/* if the descriptor isn't done, no work yet to do */
 		gen_id = le16_get_bits(rx_desc->pktlen_gen_bufq_id,
 				       VIRTCHNL2_RX_FLEX_DESC_ADV_GEN_M);
-
 		if (idpf_queue_has(GEN_CHK, rxq) != gen_id)
 			break;
 
+		dma_rmb();
+
 		rxdid = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_RXDID_M,
 				  rx_desc->rxdid_ucast);
 		if (rxdid != VIRTCHNL2_RXDID_2_FLEX_SPLITQ) {
@@ -3285,84 +3575,47 @@ static int idpf_rx_splitq_clean(struct idpf_rx_queue *rxq, int budget)
 
 		hdr = &rx_bufq->hdr_buf[buf_id];
 
-		if (unlikely(!hdr_len && !skb)) {
+		if (unlikely(!hdr_len && !xdp->data)) {
 			hdr_len = idpf_rx_hsplit_wa(hdr, rx_buf, pkt_len);
-			pkt_len -= hdr_len;
+			/* If failed, drop both buffers by setting len to 0 */
+			pkt_len -= hdr_len ? : pkt_len;
 
 			u64_stats_update_begin(&rxq->stats_sync);
 			u64_stats_inc(&rxq->q_stats.hsplit_buf_ovf);
 			u64_stats_update_end(&rxq->stats_sync);
 		}
 
-		if (libeth_rx_sync_for_cpu(hdr, hdr_len)) {
-			skb = idpf_rx_build_skb(hdr, hdr_len);
-			if (!skb)
-				break;
+		if (libeth_xdp_process_buff(xdp, hdr, hdr_len))
+			rs.hsplit++;
 
-			u64_stats_update_begin(&rxq->stats_sync);
-			u64_stats_inc(&rxq->q_stats.hsplit_pkts);
-			u64_stats_update_end(&rxq->stats_sync);
-		}
-
-		hdr->page = NULL;
+		hdr->netmem = 0;
 
 payload:
-		if (!libeth_rx_sync_for_cpu(rx_buf, pkt_len))
-			goto skip_data;
-
-		if (skb)
-			idpf_rx_add_frag(rx_buf, skb, pkt_len);
-		else
-			skb = idpf_rx_build_skb(rx_buf, pkt_len);
-
-		/* exit if we failed to retrieve a buffer */
-		if (!skb)
-			break;
+		libeth_xdp_process_buff(xdp, rx_buf, pkt_len);
+		rx_buf->netmem = 0;
 
-skip_data:
-		rx_buf->page = NULL;
-
-		idpf_rx_post_buf_refill(refillq, buf_id);
+		idpf_post_buf_refill(refillq, buf_id);
 		IDPF_RX_BUMP_NTC(rxq, ntc);
 
 		/* skip if it is non EOP desc */
-		if (!idpf_rx_splitq_is_eop(rx_desc) || unlikely(!skb))
+		if (!idpf_rx_splitq_is_eop(rx_desc) || unlikely(!xdp->data))
 			continue;
 
-		/* pad skb if needed (to make valid ethernet frame) */
-		if (eth_skb_pad(skb)) {
-			skb = NULL;
-			continue;
-		}
-
-		/* probably a little skewed due to removing CRC */
-		total_rx_bytes += skb->len;
-
-		/* protocol */
-		if (unlikely(idpf_rx_process_skb_fields(rxq, skb, rx_desc))) {
-			dev_kfree_skb_any(skb);
-			skb = NULL;
-			continue;
-		}
-
-		/* send completed skb up the stack */
-		napi_gro_receive(rxq->napi, skb);
-		skb = NULL;
-
-		/* update budget accounting */
-		total_rx_pkts++;
+		idpf_xdp_run_pass(xdp, &bq, rxq->napi, &rs, rx_desc);
 	}
 
+	idpf_xdp_finalize_rx(&bq);
+
 	rxq->next_to_clean = ntc;
+	libeth_xdp_save_buff(&rxq->xdp, xdp);
 
-	rxq->skb = skb;
 	u64_stats_update_begin(&rxq->stats_sync);
-	u64_stats_add(&rxq->q_stats.packets, total_rx_pkts);
-	u64_stats_add(&rxq->q_stats.bytes, total_rx_bytes);
+	u64_stats_add(&rxq->q_stats.packets, rs.packets);
+	u64_stats_add(&rxq->q_stats.bytes, rs.bytes);
+	u64_stats_add(&rxq->q_stats.hsplit_pkts, rs.hsplit);
 	u64_stats_update_end(&rxq->stats_sync);
 
-	/* guarantee a trip back through this routine if there was a failure */
-	return total_rx_pkts;
+	return rs.packets;
 }
 
 /**
@@ -3430,10 +3683,10 @@ static void idpf_rx_clean_refillq(struct idpf_buf_queue *bufq,
 		bool failure;
 
 		if (idpf_queue_has(RFL_GEN_CHK, refillq) !=
-		    !!(refill_desc & IDPF_RX_BI_GEN_M))
+		    !!(refill_desc & IDPF_RFL_BI_GEN_M))
 			break;
 
-		buf_id = FIELD_GET(IDPF_RX_BI_BUFID_M, refill_desc);
+		buf_id = FIELD_GET(IDPF_RFL_BI_BUFID_M, refill_desc);
 		failure = idpf_rx_update_bufq_desc(bufq, buf_id, buf_desc);
 		if (failure)
 			break;
@@ -3505,7 +3758,7 @@ static irqreturn_t idpf_vport_intr_clean_queues(int __always_unused irq,
 	struct idpf_q_vector *q_vector = (struct idpf_q_vector *)data;
 
 	q_vector->total_events++;
-	napi_schedule(&q_vector->napi);
+	napi_schedule_irqoff(&q_vector->napi);
 
 	return IRQ_HANDLED;
 }
@@ -3546,6 +3799,8 @@ void idpf_vport_intr_rel(struct idpf_vport *vport)
 	for (u32 v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) {
 		struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx];
 
+		kfree(q_vector->xsksq);
+		q_vector->xsksq = NULL;
 		kfree(q_vector->complq);
 		q_vector->complq = NULL;
 		kfree(q_vector->bufq);
@@ -3554,14 +3809,26 @@ void idpf_vport_intr_rel(struct idpf_vport *vport)
 		q_vector->tx = NULL;
 		kfree(q_vector->rx);
 		q_vector->rx = NULL;
-
-		free_cpumask_var(q_vector->affinity_mask);
 	}
 
 	kfree(vport->q_vectors);
 	vport->q_vectors = NULL;
 }
 
+static void idpf_q_vector_set_napi(struct idpf_q_vector *q_vector, bool link)
+{
+	struct napi_struct *napi = link ? &q_vector->napi : NULL;
+	struct net_device *dev = q_vector->vport->netdev;
+
+	for (u32 i = 0; i < q_vector->num_rxq; i++)
+		netif_queue_set_napi(dev, q_vector->rx[i]->idx,
+				     NETDEV_QUEUE_TYPE_RX, napi);
+
+	for (u32 i = 0; i < q_vector->num_txq; i++)
+		netif_queue_set_napi(dev, q_vector->tx[i]->idx,
+				     NETDEV_QUEUE_TYPE_TX, napi);
+}
+
 /**
  * idpf_vport_intr_rel_irq - Free the IRQ association with the OS
  * @vport: main vport structure
@@ -3582,8 +3849,7 @@ static void idpf_vport_intr_rel_irq(struct idpf_vport *vport)
 		vidx = vport->q_vector_idxs[vector];
 		irq_num = adapter->msix_entries[vidx].vector;
 
-		/* clear the affinity_mask in the IRQ descriptor */
-		irq_set_affinity_hint(irq_num, NULL);
+		idpf_q_vector_set_napi(q_vector, false);
 		kfree(free_irq(irq_num, q_vector));
 	}
 }
@@ -3597,6 +3863,8 @@ static void idpf_vport_intr_dis_irq_all(struct idpf_vport *vport)
 	struct idpf_q_vector *q_vector = vport->q_vectors;
 	int q_idx;
 
+	writel(0, vport->noirq_dyn_ctl);
+
 	for (q_idx = 0; q_idx < vport->num_q_vectors; q_idx++)
 		writel(0, q_vector[q_idx].intr_reg.dyn_ctl);
 }
@@ -3771,8 +4039,8 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport)
 				   "Request_irq failed, error: %d\n", err);
 			goto free_q_irqs;
 		}
-		/* assign the mask for this irq */
-		irq_set_affinity_hint(irq_num, q_vector->affinity_mask);
+
+		idpf_q_vector_set_napi(q_vector, true);
 	}
 
 	return 0;
@@ -3840,6 +4108,8 @@ static void idpf_vport_intr_ena_irq_all(struct idpf_vport *vport)
 		if (qv->num_txq || qv->num_rxq)
 			idpf_vport_intr_update_itr_ena_irq(qv);
 	}
+
+	writel(vport->noirq_dyn_ctl_ena, vport->noirq_dyn_ctl);
 }
 
 /**
@@ -3989,7 +4259,9 @@ static bool idpf_rx_splitq_clean_all(struct idpf_q_vector *q_vec, int budget,
 		struct idpf_rx_queue *rxq = q_vec->rx[i];
 		int pkts_cleaned_per_q;
 
-		pkts_cleaned_per_q = idpf_rx_splitq_clean(rxq, budget_per_q);
+		pkts_cleaned_per_q = idpf_queue_has(XSK, rxq) ?
+				     idpf_xskrq_poll(rxq, budget_per_q) :
+				     idpf_rx_splitq_clean(rxq, budget_per_q);
 		/* if we clean as many as budgeted, we must not be done */
 		if (pkts_cleaned_per_q >= budget_per_q)
 			clean_complete = false;
@@ -3999,8 +4271,10 @@ static bool idpf_rx_splitq_clean_all(struct idpf_q_vector *q_vec, int budget,
 
 	nid = numa_mem_id();
 
-	for (i = 0; i < q_vec->num_bufq; i++)
-		idpf_rx_clean_refillq_all(q_vec->bufq[i], nid);
+	for (i = 0; i < q_vec->num_bufq; i++) {
+		if (!idpf_queue_has(XSK, q_vec->bufq[i]))
+			idpf_rx_clean_refillq_all(q_vec->bufq[i], nid);
+	}
 
 	return clean_complete;
 }
@@ -4014,7 +4288,7 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct idpf_q_vector *q_vector =
 				container_of(napi, struct idpf_q_vector, napi);
-	bool clean_complete;
+	bool clean_complete = true;
 	int work_done = 0;
 
 	/* Handle case where we are called by netpoll with a budget of 0 */
@@ -4024,8 +4298,13 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
 		return 0;
 	}
 
-	clean_complete = idpf_rx_splitq_clean_all(q_vector, budget, &work_done);
-	clean_complete &= idpf_tx_splitq_clean_all(q_vector, budget, &work_done);
+	for (u32 i = 0; i < q_vector->num_xsksq; i++)
+		clean_complete &= idpf_xsk_xmit(q_vector->xsksq[i]);
+
+	clean_complete &= idpf_tx_splitq_clean_all(q_vector, budget,
+						   &work_done);
+	clean_complete &= idpf_rx_splitq_clean_all(q_vector, budget,
+						   &work_done);
 
 	/* If work not completed, return budget and polling will return */
 	if (!clean_complete) {
@@ -4038,20 +4317,12 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
 	/* Exit the polling mode, but don't re-enable interrupts if stack might
 	 * poll us due to busy-polling
 	 */
-	if (likely(napi_complete_done(napi, work_done)))
+	if (napi_complete_done(napi, work_done))
 		idpf_vport_intr_update_itr_ena_irq(q_vector);
 	else
 		idpf_vport_intr_set_wb_on_itr(q_vector);
 
-	/* Switch to poll mode in the tear-down path after sending disable
-	 * queues virtchnl message, as the interrupts will be disabled after
-	 * that
-	 */
-	if (unlikely(q_vector->num_txq && idpf_queue_has(POLL_MODE,
-							 q_vector->tx[0])))
-		return budget;
-	else
-		return work_done;
+	return work_done;
 }
 
 /**
@@ -4062,8 +4333,8 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
  */
 static void idpf_vport_intr_map_vector_to_qs(struct idpf_vport *vport)
 {
+	u16 num_txq_grp = vport->num_txq_grp - vport->num_xdp_txq;
 	bool split = idpf_is_queue_model_split(vport->rxq_model);
-	u16 num_txq_grp = vport->num_txq_grp;
 	struct idpf_rxq_group *rx_qgrp;
 	struct idpf_txq_group *tx_qgrp;
 	u32 i, qv_idx, q_index;
@@ -4139,6 +4410,21 @@ static void idpf_vport_intr_map_vector_to_qs(struct idpf_vport *vport)
 
 		qv_idx++;
 	}
+
+	for (i = 0; i < vport->num_xdp_txq; i++) {
+		struct idpf_tx_queue *xdpsq;
+		struct idpf_q_vector *qv;
+
+		xdpsq = vport->txqs[vport->xdp_txq_offset + i];
+		if (!idpf_queue_has(XSK, xdpsq))
+			continue;
+
+		qv = idpf_find_rxq_vec(vport, i);
+		idpf_xsk_init_wakeup(qv);
+
+		xdpsq->q_vector = qv;
+		qv->xsksq[qv->num_xsksq++] = xdpsq;
+	}
 }
 
 /**
@@ -4159,6 +4445,8 @@ static int idpf_vport_intr_init_vec_idx(struct idpf_vport *vport)
 		for (i = 0; i < vport->num_q_vectors; i++)
 			vport->q_vectors[i].v_idx = vport->q_vector_idxs[i];
 
+		vport->noirq_v_idx = vport->q_vector_idxs[i];
+
 		return 0;
 	}
 
@@ -4172,6 +4460,8 @@ static int idpf_vport_intr_init_vec_idx(struct idpf_vport *vport)
 	for (i = 0; i < vport->num_q_vectors; i++)
 		vport->q_vectors[i].v_idx = vecids[vport->q_vector_idxs[i]];
 
+	vport->noirq_v_idx = vecids[vport->q_vector_idxs[i]];
+
 	kfree(vecids);
 
 	return 0;
@@ -4184,7 +4474,8 @@ static int idpf_vport_intr_init_vec_idx(struct idpf_vport *vport)
 static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport)
 {
 	int (*napi_poll)(struct napi_struct *napi, int budget);
-	u16 v_idx;
+	u16 v_idx, qv_idx;
+	int irq_num;
 
 	if (idpf_is_queue_model_split(vport->txq_model))
 		napi_poll = idpf_vport_splitq_napi_poll;
@@ -4193,12 +4484,12 @@ static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport)
 
 	for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) {
 		struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx];
+		qv_idx = vport->q_vector_idxs[v_idx];
+		irq_num = vport->adapter->msix_entries[qv_idx].vector;
 
-		netif_napi_add(vport->netdev, &q_vector->napi, napi_poll);
-
-		/* only set affinity_mask if the CPU is online */
-		if (cpu_online(v_idx))
-			cpumask_set_cpu(v_idx, q_vector->affinity_mask);
+		netif_napi_add_config(vport->netdev, &q_vector->napi,
+				      napi_poll, v_idx);
+		netif_napi_set_irq(&q_vector->napi, irq_num);
 	}
 }
 
@@ -4212,9 +4503,13 @@ static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport)
 int idpf_vport_intr_alloc(struct idpf_vport *vport)
 {
 	u16 txqs_per_vector, rxqs_per_vector, bufqs_per_vector;
+	struct idpf_vport_user_config_data *user_config;
 	struct idpf_q_vector *q_vector;
+	struct idpf_q_coalesce *q_coal;
 	u32 complqs_per_vector, v_idx;
+	u16 idx = vport->idx;
 
+	user_config = &vport->adapter->vport_config[idx]->user_config;
 	vport->q_vectors = kcalloc(vport->num_q_vectors,
 				   sizeof(struct idpf_q_vector), GFP_KERNEL);
 	if (!vport->q_vectors)
@@ -4232,19 +4527,17 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport)
 
 	for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) {
 		q_vector = &vport->q_vectors[v_idx];
+		q_coal = &user_config->q_coalesce[v_idx];
 		q_vector->vport = vport;
 
-		q_vector->tx_itr_value = IDPF_ITR_TX_DEF;
-		q_vector->tx_intr_mode = IDPF_ITR_DYNAMIC;
+		q_vector->tx_itr_value = q_coal->tx_coalesce_usecs;
+		q_vector->tx_intr_mode = q_coal->tx_intr_mode;
 		q_vector->tx_itr_idx = VIRTCHNL2_ITR_IDX_1;
 
-		q_vector->rx_itr_value = IDPF_ITR_RX_DEF;
-		q_vector->rx_intr_mode = IDPF_ITR_DYNAMIC;
+		q_vector->rx_itr_value = q_coal->rx_coalesce_usecs;
+		q_vector->rx_intr_mode = q_coal->rx_intr_mode;
 		q_vector->rx_itr_idx = VIRTCHNL2_ITR_IDX_0;
 
-		if (!zalloc_cpumask_var(&q_vector->affinity_mask, GFP_KERNEL))
-			goto error;
-
 		q_vector->tx = kcalloc(txqs_per_vector, sizeof(*q_vector->tx),
 				       GFP_KERNEL);
 		if (!q_vector->tx)
@@ -4269,6 +4562,15 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport)
 					   GFP_KERNEL);
 		if (!q_vector->complq)
 			goto error;
+
+		if (!vport->xdp_txq_offset)
+			continue;
+
+		q_vector->xsksq = kcalloc(rxqs_per_vector,
+					  sizeof(*q_vector->xsksq),
+					  GFP_KERNEL);
+		if (!q_vector->xsksq)
+			goto error;
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 0f71a6f5557b..75b977094741 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -7,8 +7,10 @@
 #include <linux/dim.h>
 
 #include <net/libeth/cache.h>
-#include <net/tcp.h>
+#include <net/libeth/types.h>
 #include <net/netdev_queues.h>
+#include <net/tcp.h>
+#include <net/xdp.h>
 
 #include "idpf_lan_txrx.h"
 #include "virtchnl2_lan_desc.h"
@@ -57,6 +59,9 @@
 /* Default vector sharing */
 #define IDPF_MBX_Q_VEC		1
 #define IDPF_MIN_Q_VEC		1
+#define IDPF_MIN_RDMA_VEC	2
+/* Data vector for NOIRQ queues */
+#define IDPF_RESERVED_VECS			1
 
 #define IDPF_DFLT_TX_Q_DESC_COUNT		512
 #define IDPF_DFLT_TX_COMPLQ_DESC_COUNT		512
@@ -107,8 +112,8 @@ do {								\
  */
 #define IDPF_TX_SPLITQ_RE_MIN_GAP	64
 
-#define IDPF_RX_BI_GEN_M		BIT(16)
-#define IDPF_RX_BI_BUFID_M		GENMASK(15, 0)
+#define IDPF_RFL_BI_GEN_M		BIT(16)
+#define IDPF_RFL_BI_BUFID_M		GENMASK(15, 0)
 
 #define IDPF_RXD_EOF_SPLITQ		VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_EOF_M
 #define IDPF_RXD_EOF_SINGLEQ		VIRTCHNL2_RX_BASE_DESC_STATUS_EOF_M
@@ -117,10 +122,6 @@ do {								\
 	((((txq)->next_to_clean > (txq)->next_to_use) ? 0 : (txq)->desc_count) + \
 	(txq)->next_to_clean - (txq)->next_to_use - 1)
 
-#define IDPF_TX_BUF_RSV_UNUSED(txq)	((txq)->stash->buf_stack.top)
-#define IDPF_TX_BUF_RSV_LOW(txq)	(IDPF_TX_BUF_RSV_UNUSED(txq) < \
-					 (txq)->desc_count >> 2)
-
 #define IDPF_TX_COMPLQ_OVERFLOW_THRESH(txcq)	((txcq)->desc_count >> 1)
 /* Determine the absolute number of completions pending, i.e. the number of
  * completions that are expected to arrive on the TX completion queue.
@@ -130,11 +131,7 @@ do {								\
 	0 : U32_MAX) + \
 	(txq)->num_completions_pending - (txq)->complq->num_completions)
 
-#define IDPF_TX_SPLITQ_COMPL_TAG_WIDTH	16
-/* Adjust the generation for the completion tag and wrap if necessary */
-#define IDPF_TX_ADJ_COMPL_TAG_GEN(txq) \
-	((++(txq)->compl_tag_cur_gen) >= (txq)->compl_tag_gen_max ? \
-	0 : (txq)->compl_tag_cur_gen)
+#define IDPF_TXBUF_NULL			U32_MAX
 
 #define IDPF_TXD_LAST_DESC_CMD (IDPF_TX_DESC_CMD_EOP | IDPF_TX_DESC_CMD_RS)
 
@@ -142,6 +139,9 @@ do {								\
 #define IDPF_TX_FLAGS_IPV4		BIT(1)
 #define IDPF_TX_FLAGS_IPV6		BIT(2)
 #define IDPF_TX_FLAGS_TUNNEL		BIT(3)
+#define IDPF_TX_FLAGS_TSYN		BIT(4)
+
+struct libeth_rq_napi_stats;
 
 union idpf_tx_flex_desc {
 	struct idpf_flex_tx_desc q; /* queue based scheduling */
@@ -151,18 +151,6 @@ union idpf_tx_flex_desc {
 #define idpf_tx_buf libeth_sqe
 
 /**
- * struct idpf_buf_lifo - LIFO for managing OOO completions
- * @top: Used to know how many buffers are left
- * @size: Total size of LIFO
- * @bufs: Backing array
- */
-struct idpf_buf_lifo {
-	u16 top;
-	u16 size;
-	struct idpf_tx_stash **bufs;
-};
-
-/**
  * struct idpf_tx_offload_params - Offload parameters for a given packet
  * @tx_flags: Feature flags enabled for this packet
  * @hdr_offsets: Offset parameter for single queue model
@@ -194,6 +182,9 @@ struct idpf_tx_offload_params {
  * @compl_tag: Associated tag for completion
  * @td_tag: Descriptor tunneling tag
  * @offload: Offload parameters
+ * @prev_ntu: stored TxQ next_to_use in case of rollback
+ * @prev_refill_ntc: stored refillq next_to_clean in case of packet rollback
+ * @prev_refill_gen: stored refillq generation bit in case of packet rollback
  */
 struct idpf_tx_splitq_params {
 	enum idpf_tx_desc_dtype_value dtype;
@@ -204,6 +195,10 @@ struct idpf_tx_splitq_params {
 	};
 
 	struct idpf_tx_offload_params offload;
+
+	u16 prev_ntu;
+	u16 prev_refill_ntc;
+	bool prev_refill_gen;
 };
 
 enum idpf_tx_ctx_desc_eipt_offload {
@@ -213,25 +208,6 @@ enum idpf_tx_ctx_desc_eipt_offload {
 	IDPF_TX_CTX_EXT_IP_IPV4         = 0x3
 };
 
-/* Checksum offload bits decoded from the receive descriptor. */
-struct idpf_rx_csum_decoded {
-	u32 l3l4p : 1;
-	u32 ipe : 1;
-	u32 eipe : 1;
-	u32 eudpe : 1;
-	u32 ipv6exadd : 1;
-	u32 l4e : 1;
-	u32 pprs : 1;
-	u32 nat : 1;
-	u32 raw_csum_inv : 1;
-	u32 raw_csum : 16;
-};
-
-struct idpf_rx_extracted {
-	unsigned int size;
-	u16 rx_ptype;
-};
-
 #define IDPF_TX_COMPLQ_CLEAN_BUDGET	256
 #define IDPF_TX_MIN_PKT_LEN		17
 #define IDPF_TX_DESCS_FOR_SKB_DATA_PTR	1
@@ -305,9 +281,13 @@ struct idpf_ptype_state {
  *			  bit and Q_RFL_GEN is the SW bit.
  * @__IDPF_Q_FLOW_SCH_EN: Enable flow scheduling
  * @__IDPF_Q_SW_MARKER: Used to indicate TX queue marker completions
- * @__IDPF_Q_POLL_MODE: Enable poll mode
  * @__IDPF_Q_CRC_EN: enable CRC offload in singleq mode
  * @__IDPF_Q_HSPLIT_EN: enable header split on Rx (splitq)
+ * @__IDPF_Q_PTP: indicates whether the Rx timestamping is enabled for the
+ *		  queue
+ * @__IDPF_Q_NOIRQ: queue is polling-driven and has no interrupt
+ * @__IDPF_Q_XDP: this is an XDP queue
+ * @__IDPF_Q_XSK: the queue has an XSk pool installed
  * @__IDPF_Q_FLAGS_NBITS: Must be last
  */
 enum idpf_queue_flags_t {
@@ -315,9 +295,12 @@ enum idpf_queue_flags_t {
 	__IDPF_Q_RFL_GEN_CHK,
 	__IDPF_Q_FLOW_SCH_EN,
 	__IDPF_Q_SW_MARKER,
-	__IDPF_Q_POLL_MODE,
 	__IDPF_Q_CRC_EN,
 	__IDPF_Q_HSPLIT_EN,
+	__IDPF_Q_PTP,
+	__IDPF_Q_NOIRQ,
+	__IDPF_Q_XDP,
+	__IDPF_Q_XSK,
 
 	__IDPF_Q_FLAGS_NBITS,
 };
@@ -384,14 +367,17 @@ struct idpf_intr_reg {
  * @num_txq: Number of TX queues
  * @num_bufq: Number of buffer queues
  * @num_complq: number of completion queues
+ * @num_xsksq: number of XSk send queues
  * @rx: Array of RX queues to service
  * @tx: Array of TX queues to service
  * @bufq: Array of buffer queues to service
  * @complq: array of completion queues
+ * @xsksq: array of XSk send queues
  * @intr_reg: See struct idpf_intr_reg
- * @napi: napi handler
+ * @csd: XSk wakeup CSD
  * @total_events: Number of interrupts processed
  * @wb_on_itr: whether WB on ITR is enabled
+ * @napi: napi handler
  * @tx_dim: Data for TX net_dim algorithm
  * @tx_itr_value: TX interrupt throttling rate
  * @tx_intr_mode: Dynamic ITR or not
@@ -401,7 +387,6 @@ struct idpf_intr_reg {
  * @rx_intr_mode: Dynamic ITR or not
  * @rx_itr_idx: RX ITR index
  * @v_idx: Vector index
- * @affinity_mask: CPU affinity mask
  */
 struct idpf_q_vector {
 	__cacheline_group_begin_aligned(read_mostly);
@@ -411,19 +396,24 @@ struct idpf_q_vector {
 	u16 num_txq;
 	u16 num_bufq;
 	u16 num_complq;
+	u16 num_xsksq;
 	struct idpf_rx_queue **rx;
 	struct idpf_tx_queue **tx;
 	struct idpf_buf_queue **bufq;
 	struct idpf_compl_queue **complq;
+	struct idpf_tx_queue **xsksq;
 
 	struct idpf_intr_reg intr_reg;
 	__cacheline_group_end_aligned(read_mostly);
 
 	__cacheline_group_begin_aligned(read_write);
-	struct napi_struct napi;
+	call_single_data_t csd;
+
 	u16 total_events;
 	bool wb_on_itr;
 
+	struct napi_struct napi;
+
 	struct dim tx_dim;
 	u16 tx_itr_value;
 	bool tx_intr_mode;
@@ -438,13 +428,12 @@ struct idpf_q_vector {
 	__cacheline_group_begin_aligned(cold);
 	u16 v_idx;
 
-	cpumask_var_t affinity_mask;
 	__cacheline_group_end_aligned(cold);
 };
-libeth_cacheline_set_assert(struct idpf_q_vector, 120,
-			    24 + sizeof(struct napi_struct) +
+libeth_cacheline_set_assert(struct idpf_q_vector, 136,
+			    56 + sizeof(struct napi_struct) +
 			    2 * sizeof(struct dim),
-			    8 + sizeof(cpumask_var_t));
+			    8);
 
 struct idpf_rx_queue_stats {
 	u64_stats_t packets;
@@ -464,6 +453,7 @@ struct idpf_tx_queue_stats {
 	u64_stats_t q_busy;
 	u64_stats_t skb_drops;
 	u64_stats_t dma_map_errs;
+	u64_stats_t tstamp_skipped;
 };
 
 #define IDPF_ITR_DYNAMIC	1
@@ -483,38 +473,33 @@ struct idpf_tx_queue_stats {
 #define IDPF_DIM_DEFAULT_PROFILE_IX		1
 
 /**
- * struct idpf_txq_stash - Tx buffer stash for Flow-based scheduling mode
- * @buf_stack: Stack of empty buffers to store buffer info for out of order
- *	       buffer completions. See struct idpf_buf_lifo
- * @sched_buf_hash: Hash table to store buffers
- */
-struct idpf_txq_stash {
-	struct idpf_buf_lifo buf_stack;
-	DECLARE_HASHTABLE(sched_buf_hash, 12);
-} ____cacheline_aligned;
-
-/**
  * struct idpf_rx_queue - software structure representing a receive queue
  * @rx: universal receive descriptor array
  * @single_buf: buffer descriptor array in singleq
  * @desc_ring: virtual descriptor ring address
  * @bufq_sets: Pointer to the array of buffer queues in splitq mode
  * @napi: NAPI instance corresponding to this queue (splitq)
+ * @xdp_prog: attached XDP program
  * @rx_buf: See struct &libeth_fqe
  * @pp: Page pool pointer in singleq mode
- * @netdev: &net_device corresponding to this queue
  * @tail: Tail offset. Used for both queue models single and split.
  * @flags: See enum idpf_queue_flags_t
  * @idx: For RX queue, it is used to index to total RX queue across groups and
  *	 used for skb reporting.
  * @desc_count: Number of descriptors
+ * @num_xdp_txq: total number of XDP Tx queues
+ * @xdpsqs: shortcut for XDP Tx queues array
  * @rxdids: Supported RX descriptor ids
+ * @truesize: data buffer truesize in singleq
  * @rx_ptype_lkup: LUT of Rx ptypes
+ * @xdp_rxq: XDP queue info
  * @next_to_use: Next descriptor to use
  * @next_to_clean: Next descriptor to clean
  * @next_to_alloc: RX buffer to allocate at
- * @skb: Pointer to the skb
- * @truesize: data buffer truesize in singleq
+ * @xdp: XDP buffer with the current frame
+ * @xsk: current XDP buffer in XSk mode
+ * @pool: XSk pool if installed
+ * @cached_phc_time: Cached PHC time for the Rx queue
  * @stats_sync: See struct u64_stats_sync
  * @q_stats: See union idpf_rx_queue_stats
  * @q_id: Queue id
@@ -538,30 +523,45 @@ struct idpf_rx_queue {
 		struct {
 			struct idpf_bufq_set *bufq_sets;
 			struct napi_struct *napi;
+			struct bpf_prog __rcu *xdp_prog;
 		};
 		struct {
 			struct libeth_fqe *rx_buf;
 			struct page_pool *pp;
+			void __iomem *tail;
 		};
 	};
-	struct net_device *netdev;
-	void __iomem *tail;
 
 	DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS);
 	u16 idx;
 	u16 desc_count;
 
-	u32 rxdids;
+	u32 num_xdp_txq;
+	union {
+		struct idpf_tx_queue **xdpsqs;
+		struct {
+			u32 rxdids;
+			u32 truesize;
+		};
+	};
 	const struct libeth_rx_pt *rx_ptype_lkup;
+
+	struct xdp_rxq_info xdp_rxq;
 	__cacheline_group_end_aligned(read_mostly);
 
 	__cacheline_group_begin_aligned(read_write);
-	u16 next_to_use;
-	u16 next_to_clean;
-	u16 next_to_alloc;
+	u32 next_to_use;
+	u32 next_to_clean;
+	u32 next_to_alloc;
 
-	struct sk_buff *skb;
-	u32 truesize;
+	union {
+		struct libeth_xdp_buff_stash xdp;
+		struct {
+			struct libeth_xdp_buff *xsk;
+			struct xsk_buff_pool *pool;
+		};
+	};
+	u64 cached_phc_time;
 
 	struct u64_stats_sync stats_sync;
 	struct idpf_rx_queue_stats q_stats;
@@ -580,8 +580,11 @@ struct idpf_rx_queue {
 	u16 rx_max_pkt_size;
 	__cacheline_group_end_aligned(cold);
 };
-libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
-			    80 + sizeof(struct u64_stats_sync),
+libeth_cacheline_set_assert(struct idpf_rx_queue,
+			    ALIGN(64, __alignof(struct xdp_rxq_info)) +
+			    sizeof(struct xdp_rxq_info),
+			    96 + offsetof(struct idpf_rx_queue, q_stats) -
+			    offsetofend(struct idpf_rx_queue, cached_phc_time),
 			    32);
 
 /**
@@ -593,36 +596,21 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
  * @desc_ring: virtual descriptor ring address
  * @tx_buf: See struct idpf_tx_buf
  * @txq_grp: See struct idpf_txq_group
+ * @complq: corresponding completion queue in XDP mode
  * @dev: Device back pointer for DMA mapping
+ * @pool: corresponding XSk pool if installed
  * @tail: Tail offset. Used for both queue models single and split
  * @flags: See enum idpf_queue_flags_t
  * @idx: For TX queue, it is used as index to map between TX queue group and
  *	 hot path TX pointers stored in vport. Used in both singleq/splitq.
  * @desc_count: Number of descriptors
  * @tx_min_pkt_len: Min supported packet length
- * @compl_tag_gen_s: Completion tag generation bit
- *	The format of the completion tag will change based on the TXQ
- *	descriptor ring size so that we can maintain roughly the same level
- *	of "uniqueness" across all descriptor sizes. For example, if the
- *	TXQ descriptor ring size is 64 (the minimum size supported), the
- *	completion tag will be formatted as below:
- *	15                 6 5         0
- *	--------------------------------
- *	|    GEN=0-1023     |IDX = 0-63|
- *	--------------------------------
- *
- *	This gives us 64*1024 = 65536 possible unique values. Similarly, if
- *	the TXQ descriptor ring size is 8160 (the maximum size supported),
- *	the completion tag will be formatted as below:
- *	15 13 12                       0
- *	--------------------------------
- *	|GEN |       IDX = 0-8159      |
- *	--------------------------------
- *
- *	This gives us 8*8160 = 65280 possible unique values.
+ * @thresh: XDP queue cleaning threshold
  * @netdev: &net_device corresponding to this queue
  * @next_to_use: Next descriptor to use
  * @next_to_clean: Next descriptor to clean
+ * @last_re: last descriptor index that RE bit was set
+ * @tx_max_bufs: Max buffers that can be transmitted with scatter-gather
  * @cleaned_bytes: Splitq only, TXQ only: When a TX completion is received on
  *		   the TX completion queue, it can be for any TXQ associated
  *		   with that completion queue. This means we can clean up to
@@ -633,17 +621,21 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
  *		   only once at the end of the cleaning routine.
  * @clean_budget: singleq only, queue cleaning budget
  * @cleaned_pkts: Number of packets cleaned for the above said case
- * @tx_max_bufs: Max buffers that can be transmitted with scatter-gather
- * @stash: Tx buffer stash for Flow-based scheduling mode
- * @compl_tag_bufid_m: Completion tag buffer id mask
- * @compl_tag_cur_gen: Used to keep track of current completion tag generation
- * @compl_tag_gen_max: To determine when compl_tag_cur_gen should be reset
+ * @refillq: Pointer to refill queue
+ * @pending: number of pending descriptors to send in QB
+ * @xdp_tx: number of pending &xdp_buff or &xdp_frame buffers
+ * @timer: timer for XDP Tx queue cleanup
+ * @xdp_lock: lock for XDP Tx queues sharing
+ * @cached_tstamp_caps: Tx timestamp capabilities negotiated with the CP
+ * @tstamp_task: Work that handles Tx timestamp read
  * @stats_sync: See struct u64_stats_sync
  * @q_stats: See union idpf_tx_queue_stats
  * @q_id: Queue id
  * @size: Length of descriptor ring in bytes
  * @dma: Physical address of ring
  * @q_vector: Backreference to associated vector
+ * @buf_pool_size: Total number of idpf_tx_buf
+ * @rel_q_id: relative virtchnl queue index
  */
 struct idpf_tx_queue {
 	__cacheline_group_begin_aligned(read_mostly);
@@ -651,41 +643,61 @@ struct idpf_tx_queue {
 		struct idpf_base_tx_desc *base_tx;
 		struct idpf_base_tx_ctx_desc *base_ctx;
 		union idpf_tx_flex_desc *flex_tx;
-		struct idpf_flex_tx_ctx_desc *flex_ctx;
+		union idpf_flex_tx_ctx_desc *flex_ctx;
 
 		void *desc_ring;
 	};
 	struct libeth_sqe *tx_buf;
-	struct idpf_txq_group *txq_grp;
-	struct device *dev;
+	union {
+		struct idpf_txq_group *txq_grp;
+		struct idpf_compl_queue *complq;
+	};
+	union {
+		struct device *dev;
+		struct xsk_buff_pool *pool;
+	};
 	void __iomem *tail;
 
 	DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS);
 	u16 idx;
 	u16 desc_count;
 
-	u16 tx_min_pkt_len;
-	u16 compl_tag_gen_s;
+	union {
+		u16 tx_min_pkt_len;
+		u32 thresh;
+	};
 
 	struct net_device *netdev;
 	__cacheline_group_end_aligned(read_mostly);
 
 	__cacheline_group_begin_aligned(read_write);
-	u16 next_to_use;
-	u16 next_to_clean;
+	u32 next_to_use;
+	u32 next_to_clean;
 
 	union {
-		u32 cleaned_bytes;
-		u32 clean_budget;
-	};
-	u16 cleaned_pkts;
+		struct {
+			u16 last_re;
+			u16 tx_max_bufs;
+
+			union {
+				u32 cleaned_bytes;
+				u32 clean_budget;
+			};
+			u16 cleaned_pkts;
 
-	u16 tx_max_bufs;
-	struct idpf_txq_stash *stash;
+			struct idpf_sw_queue *refillq;
+		};
+		struct {
+			u32 pending;
+			u32 xdp_tx;
+
+			struct libeth_xdpsq_timer *timer;
+			struct libeth_xdpsq_lock xdp_lock;
+		};
+	};
 
-	u16 compl_tag_bufid_m;
-	u16 compl_tag_cur_gen;
-	u16 compl_tag_gen_max;
+	struct idpf_ptp_vport_tx_tstamp_caps *cached_tstamp_caps;
+	struct work_struct *tstamp_task;
 
 	struct u64_stats_sync stats_sync;
 	struct idpf_tx_queue_stats q_stats;
@@ -697,25 +709,36 @@ struct idpf_tx_queue {
 	dma_addr_t dma;
 
 	struct idpf_q_vector *q_vector;
+
+	u32 buf_pool_size;
+	u32 rel_q_id;
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_tx_queue, 64,
-			    88 + sizeof(struct u64_stats_sync),
-			    24);
+			    104 +
+			    offsetof(struct idpf_tx_queue, cached_tstamp_caps) -
+			    offsetofend(struct idpf_tx_queue, timer) +
+			    offsetof(struct idpf_tx_queue, q_stats) -
+			    offsetofend(struct idpf_tx_queue, tstamp_task),
+			    32);
 
 /**
  * struct idpf_buf_queue - software structure representing a buffer queue
  * @split_buf: buffer descriptor array
- * @hdr_buf: &libeth_fqe for header buffers
- * @hdr_pp: &page_pool for header buffers
  * @buf: &libeth_fqe for data buffers
  * @pp: &page_pool for data buffers
+ * @xsk_buf: &xdp_buff for XSk Rx buffers
+ * @pool: &xsk_buff_pool on XSk queues
+ * @hdr_buf: &libeth_fqe for header buffers
+ * @hdr_pp: &page_pool for header buffers
  * @tail: Tail offset
  * @flags: See enum idpf_queue_flags_t
  * @desc_count: Number of descriptors
+ * @thresh: refill threshold in XSk
  * @next_to_use: Next descriptor to use
  * @next_to_clean: Next descriptor to clean
  * @next_to_alloc: RX buffer to allocate at
+ * @pending: number of buffers to refill (Xsk)
  * @hdr_truesize: truesize for buffer headers
  * @truesize: truesize for data buffers
  * @q_id: Queue id
@@ -729,14 +752,24 @@ libeth_cacheline_set_assert(struct idpf_tx_queue, 64,
 struct idpf_buf_queue {
 	__cacheline_group_begin_aligned(read_mostly);
 	struct virtchnl2_splitq_rx_buf_desc *split_buf;
+	union {
+		struct {
+			struct libeth_fqe *buf;
+			struct page_pool *pp;
+		};
+		struct {
+			struct libeth_xdp_buff **xsk_buf;
+			struct xsk_buff_pool *pool;
+		};
+	};
 	struct libeth_fqe *hdr_buf;
 	struct page_pool *hdr_pp;
-	struct libeth_fqe *buf;
-	struct page_pool *pp;
 	void __iomem *tail;
 
 	DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS);
 	u32 desc_count;
+
+	u32 thresh;
 	__cacheline_group_end_aligned(read_mostly);
 
 	__cacheline_group_begin_aligned(read_write);
@@ -744,6 +777,7 @@ struct idpf_buf_queue {
 	u32 next_to_clean;
 	u32 next_to_alloc;
 
+	u32 pending;
 	u32 hdr_truesize;
 	u32 truesize;
 	__cacheline_group_end_aligned(read_write);
@@ -764,7 +798,9 @@ libeth_cacheline_set_assert(struct idpf_buf_queue, 64, 24, 32);
 
 /**
  * struct idpf_compl_queue - software structure representing a completion queue
- * @comp: completion descriptor array
+ * @comp: 8-byte completion descriptor array
+ * @comp_4b: 4-byte completion descriptor array
+ * @desc_ring: virtual descriptor ring address
  * @txq_grp: See struct idpf_txq_group
  * @flags: See enum idpf_queue_flags_t
  * @desc_count: Number of descriptors
@@ -784,7 +820,12 @@ libeth_cacheline_set_assert(struct idpf_buf_queue, 64, 24, 32);
  */
 struct idpf_compl_queue {
 	__cacheline_group_begin_aligned(read_mostly);
-	struct idpf_splitq_tx_compl_desc *comp;
+	union {
+		struct idpf_splitq_tx_compl_desc *comp;
+		struct idpf_splitq_4b_tx_compl_desc *comp_4b;
+
+		void *desc_ring;
+	};
 	struct idpf_txq_group *txq_grp;
 
 	DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS);
@@ -911,7 +952,6 @@ struct idpf_rxq_group {
  * @vport: Vport back pointer
  * @num_txq: Number of TX queues associated
  * @txqs: Array of TX queue pointers
- * @stashes: array of OOO stashes for the queues
  * @complq: Associated completion queue pointer, split queue only
  * @num_completions_pending: Total number of completions pending for the
  *			     completion queue, acculumated for all TX queues
@@ -926,7 +966,6 @@ struct idpf_txq_group {
 
 	u16 num_txq;
 	struct idpf_tx_queue *txqs[IDPF_LARGE_MAX_Q];
-	struct idpf_txq_stash *stashes;
 
 	struct idpf_compl_queue *complq;
 
@@ -940,7 +979,7 @@ static inline int idpf_q_vector_to_mem(const struct idpf_q_vector *q_vector)
 	if (!q_vector)
 		return NUMA_NO_NODE;
 
-	cpu = cpumask_first(q_vector->affinity_mask);
+	cpu = cpumask_first(&q_vector->napi.config->affinity_mask);
 
 	return cpu < nr_cpu_ids ? cpu_to_mem(cpu) : NUMA_NO_NODE;
 }
@@ -1019,6 +1058,17 @@ static inline void idpf_vport_intr_set_wb_on_itr(struct idpf_q_vector *q_vector)
 	       reg->dyn_ctl);
 }
 
+/**
+ * idpf_tx_splitq_get_free_bufs - get number of free buf_ids in refillq
+ * @refillq: pointer to refillq containing buf_ids
+ */
+static inline u32 idpf_tx_splitq_get_free_bufs(struct idpf_sw_queue *refillq)
+{
+	return (refillq->next_to_use > refillq->next_to_clean ?
+		0 : refillq->desc_count) +
+	       refillq->next_to_use - refillq->next_to_clean - 1;
+}
+
 int idpf_vport_singleq_napi_poll(struct napi_struct *napi, int budget);
 void idpf_vport_init_num_qs(struct idpf_vport *vport,
 			    struct virtchnl2_create_vport *vport_msg);
@@ -1039,31 +1089,30 @@ int idpf_config_rss(struct idpf_vport *vport);
 int idpf_init_rss(struct idpf_vport *vport);
 void idpf_deinit_rss(struct idpf_vport *vport);
 int idpf_rx_bufs_init_all(struct idpf_vport *vport);
-void idpf_rx_add_frag(struct idpf_rx_buf *rx_buf, struct sk_buff *skb,
-		      unsigned int size);
-struct sk_buff *idpf_rx_build_skb(const struct libeth_fqe *buf, u32 size);
+
+struct idpf_q_vector *idpf_find_rxq_vec(const struct idpf_vport *vport,
+					u32 q_num);
+struct idpf_q_vector *idpf_find_txq_vec(const struct idpf_vport *vport,
+					u32 q_num);
+int idpf_qp_switch(struct idpf_vport *vport, u32 qid, bool en);
+
 void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 			   bool xmit_more);
 unsigned int idpf_size_to_txd_count(unsigned int size);
 netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb);
-void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
-			   struct idpf_tx_buf *first, u16 ring_idx);
-unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
-					 struct sk_buff *skb);
+unsigned int idpf_tx_res_count_required(struct idpf_tx_queue *txq,
+					struct sk_buff *skb, u32 *buf_count);
 void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue);
 netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 				  struct idpf_tx_queue *tx_q);
 netdev_tx_t idpf_tx_start(struct sk_buff *skb, struct net_device *netdev);
 bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rxq,
 				      u16 cleaned_count);
+bool idpf_rx_process_skb_fields(struct sk_buff *skb,
+				const struct libeth_xdp_buff *xdp,
+				struct libeth_rq_napi_stats *rs);
 int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off);
 
-static inline bool idpf_tx_maybe_stop_common(struct idpf_tx_queue *tx_q,
-					     u32 needed)
-{
-	return !netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
-					  IDPF_DESC_UNUSED(tx_q),
-					  needed, needed);
-}
+void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq);
 
 #endif /* !_IDPF_TXRX_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
index aba828abcb17..4cc58c83688c 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
@@ -9,10 +9,13 @@
 
 /**
  * idpf_vf_ctlq_reg_init - initialize default mailbox registers
+ * @adapter: adapter structure
  * @cq: pointer to the array of create control queues
  */
-static void idpf_vf_ctlq_reg_init(struct idpf_ctlq_create_info *cq)
+static void idpf_vf_ctlq_reg_init(struct idpf_adapter *adapter,
+				  struct idpf_ctlq_create_info *cq)
 {
+	resource_size_t mbx_start = adapter->dev_ops.static_reg_info[0].start;
 	int i;
 
 	for (i = 0; i < IDPF_NUM_DFLT_MBX_Q; i++) {
@@ -21,22 +24,22 @@ static void idpf_vf_ctlq_reg_init(struct idpf_ctlq_create_info *cq)
 		switch (ccq->type) {
 		case IDPF_CTLQ_TYPE_MAILBOX_TX:
 			/* set head and tail registers in our local struct */
-			ccq->reg.head = VF_ATQH;
-			ccq->reg.tail = VF_ATQT;
-			ccq->reg.len = VF_ATQLEN;
-			ccq->reg.bah = VF_ATQBAH;
-			ccq->reg.bal = VF_ATQBAL;
+			ccq->reg.head = VF_ATQH - mbx_start;
+			ccq->reg.tail = VF_ATQT - mbx_start;
+			ccq->reg.len = VF_ATQLEN - mbx_start;
+			ccq->reg.bah = VF_ATQBAH - mbx_start;
+			ccq->reg.bal = VF_ATQBAL - mbx_start;
 			ccq->reg.len_mask = VF_ATQLEN_ATQLEN_M;
 			ccq->reg.len_ena_mask = VF_ATQLEN_ATQENABLE_M;
 			ccq->reg.head_mask = VF_ATQH_ATQH_M;
 			break;
 		case IDPF_CTLQ_TYPE_MAILBOX_RX:
 			/* set head and tail registers in our local struct */
-			ccq->reg.head = VF_ARQH;
-			ccq->reg.tail = VF_ARQT;
-			ccq->reg.len = VF_ARQLEN;
-			ccq->reg.bah = VF_ARQBAH;
-			ccq->reg.bal = VF_ARQBAL;
+			ccq->reg.head = VF_ARQH - mbx_start;
+			ccq->reg.tail = VF_ARQT - mbx_start;
+			ccq->reg.len = VF_ARQLEN - mbx_start;
+			ccq->reg.bah = VF_ARQBAH - mbx_start;
+			ccq->reg.bal = VF_ARQBAL - mbx_start;
 			ccq->reg.len_mask = VF_ARQLEN_ARQLEN_M;
 			ccq->reg.len_ena_mask = VF_ARQLEN_ARQENABLE_M;
 			ccq->reg.head_mask = VF_ARQH_ARQH_M;
@@ -73,7 +76,7 @@ static int idpf_vf_intr_reg_init(struct idpf_vport *vport)
 	int num_vecs = vport->num_q_vectors;
 	struct idpf_vec_regs *reg_vals;
 	int num_regs, i, err = 0;
-	u32 rx_itr, tx_itr;
+	u32 rx_itr, tx_itr, val;
 	u16 total_vecs;
 
 	total_vecs = idpf_get_reserved_vecs(vport->adapter);
@@ -117,6 +120,15 @@ static int idpf_vf_intr_reg_init(struct idpf_vport *vport)
 		intr->tx_itr = idpf_get_reg_addr(adapter, tx_itr);
 	}
 
+	/* Data vector for NOIRQ queues */
+
+	val = reg_vals[vport->q_vector_idxs[i] - IDPF_MBX_Q_VEC].dyn_ctl_reg;
+	vport->noirq_dyn_ctl = idpf_get_reg_addr(adapter, val);
+
+	val = VF_INT_DYN_CTLN_WB_ON_ITR_M | VF_INT_DYN_CTLN_INTENA_MSK_M |
+	      FIELD_PREP(VF_INT_DYN_CTLN_ITR_INDX_M, IDPF_NO_ITR_UPDATE_IDX);
+	vport->noirq_dyn_ctl_ena = val;
+
 free_reg_vals:
 	kfree(reg_vals);
 
@@ -129,7 +141,7 @@ free_reg_vals:
  */
 static void idpf_vf_reset_reg_init(struct idpf_adapter *adapter)
 {
-	adapter->reset_reg.rstat = idpf_get_reg_addr(adapter, VFGEN_RSTAT);
+	adapter->reset_reg.rstat = idpf_get_rstat_reg_addr(adapter, VFGEN_RSTAT);
 	adapter->reset_reg.rstat_m = VFGEN_RSTAT_VFR_STATE_M;
 }
 
@@ -148,6 +160,17 @@ static void idpf_vf_trigger_reset(struct idpf_adapter *adapter,
 }
 
 /**
+ * idpf_idc_vf_register - register for IDC callbacks
+ * @adapter: Driver specific private structure
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_idc_vf_register(struct idpf_adapter *adapter)
+{
+	return idpf_idc_init_aux_core_dev(adapter, IIDC_FUNCTION_TYPE_VF);
+}
+
+/**
  * idpf_vf_reg_ops_init - Initialize register API function pointers
  * @adapter: Driver specific private structure
  */
@@ -167,4 +190,11 @@ static void idpf_vf_reg_ops_init(struct idpf_adapter *adapter)
 void idpf_vf_dev_ops_init(struct idpf_adapter *adapter)
 {
 	idpf_vf_reg_ops_init(adapter);
+
+	adapter->dev_ops.idc_init = idpf_idc_vf_register;
+
+	resource_set_range(&adapter->dev_ops.static_reg_info[0],
+			   VF_BASE, IDPF_VF_MBX_REGION_SZ);
+	resource_set_range(&adapter->dev_ops.static_reg_info[1],
+			   VFGEN_RSTAT, IDPF_VF_RSTAT_REGION_SZ);
 }
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index d46c95f91b0d..44cd4b466c48 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -1,92 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (C) 2023 Intel Corporation */
 
+#include <linux/export.h>
 #include <net/libeth/rx.h>
 
 #include "idpf.h"
 #include "idpf_virtchnl.h"
-
-#define IDPF_VC_XN_MIN_TIMEOUT_MSEC	2000
-#define IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC	(60 * 1000)
-#define IDPF_VC_XN_IDX_M		GENMASK(7, 0)
-#define IDPF_VC_XN_SALT_M		GENMASK(15, 8)
-#define IDPF_VC_XN_RING_LEN		U8_MAX
-
-/**
- * enum idpf_vc_xn_state - Virtchnl transaction status
- * @IDPF_VC_XN_IDLE: not expecting a reply, ready to be used
- * @IDPF_VC_XN_WAITING: expecting a reply, not yet received
- * @IDPF_VC_XN_COMPLETED_SUCCESS: a reply was expected and received,
- *				  buffer updated
- * @IDPF_VC_XN_COMPLETED_FAILED: a reply was expected and received, but there
- *				 was an error, buffer not updated
- * @IDPF_VC_XN_SHUTDOWN: transaction object cannot be used, VC torn down
- * @IDPF_VC_XN_ASYNC: transaction sent asynchronously and doesn't have the
- *		      return context; a callback may be provided to handle
- *		      return
- */
-enum idpf_vc_xn_state {
-	IDPF_VC_XN_IDLE = 1,
-	IDPF_VC_XN_WAITING,
-	IDPF_VC_XN_COMPLETED_SUCCESS,
-	IDPF_VC_XN_COMPLETED_FAILED,
-	IDPF_VC_XN_SHUTDOWN,
-	IDPF_VC_XN_ASYNC,
-};
-
-struct idpf_vc_xn;
-/* Callback for asynchronous messages */
-typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *,
-			    const struct idpf_ctlq_msg *);
-
-/**
- * struct idpf_vc_xn - Data structure representing virtchnl transactions
- * @completed: virtchnl event loop uses that to signal when a reply is
- *	       available, uses kernel completion API
- * @state: virtchnl event loop stores the data below, protected by the
- *	   completion's lock.
- * @reply_sz: Original size of reply, may be > reply_buf.iov_len; it will be
- *	      truncated on its way to the receiver thread according to
- *	      reply_buf.iov_len.
- * @reply: Reference to the buffer(s) where the reply data should be written
- *	   to. May be 0-length (then NULL address permitted) if the reply data
- *	   should be ignored.
- * @async_handler: if sent asynchronously, a callback can be provided to handle
- *		   the reply when it's received
- * @vc_op: corresponding opcode sent with this transaction
- * @idx: index used as retrieval on reply receive, used for cookie
- * @salt: changed every message to make unique, used for cookie
- */
-struct idpf_vc_xn {
-	struct completion completed;
-	enum idpf_vc_xn_state state;
-	size_t reply_sz;
-	struct kvec reply;
-	async_vc_cb async_handler;
-	u32 vc_op;
-	u8 idx;
-	u8 salt;
-};
-
-/**
- * struct idpf_vc_xn_params - Parameters for executing transaction
- * @send_buf: kvec for send buffer
- * @recv_buf: kvec for recv buffer, may be NULL, must then have zero length
- * @timeout_ms: timeout to wait for reply
- * @async: send message asynchronously, will not wait on completion
- * @async_handler: If sent asynchronously, optional callback handler. The user
- *		   must be careful when using async handlers as the memory for
- *		   the recv_buf _cannot_ be on stack if this is async.
- * @vc_op: virtchnl op to send
- */
-struct idpf_vc_xn_params {
-	struct kvec send_buf;
-	struct kvec recv_buf;
-	int timeout_ms;
-	bool async;
-	async_vc_cb async_handler;
-	u32 vc_op;
-};
+#include "idpf_ptp.h"
 
 /**
  * struct idpf_vc_xn_manager - Manager for tracking transactions
@@ -148,7 +68,7 @@ static void idpf_handle_event_link(struct idpf_adapter *adapter,
 
 	vport->link_up = v2e->link_status;
 
-	if (np->state != __IDPF_VPORT_UP)
+	if (!test_bit(IDPF_VPORT_UP, np->state))
 		return;
 
 	if (vport->link_up) {
@@ -235,6 +155,55 @@ err_kfree:
 	return err;
 }
 
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+/**
+ * idpf_ptp_is_mb_msg - Check if the message is PTP-related
+ * @op: virtchnl opcode
+ *
+ * Return: true if msg is PTP-related, false otherwise.
+ */
+static bool idpf_ptp_is_mb_msg(u32 op)
+{
+	switch (op) {
+	case VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME:
+	case VIRTCHNL2_OP_PTP_GET_CROSS_TIME:
+	case VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME:
+	case VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE:
+	case VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME:
+	case VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS:
+	case VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
+ * idpf_prepare_ptp_mb_msg - Prepare PTP related message
+ *
+ * @adapter: Driver specific private structure
+ * @op: virtchnl opcode
+ * @ctlq_msg: Corresponding control queue message
+ */
+static void idpf_prepare_ptp_mb_msg(struct idpf_adapter *adapter, u32 op,
+				    struct idpf_ctlq_msg *ctlq_msg)
+{
+	/* If the message is PTP-related and the secondary mailbox is available,
+	 * send the message through the secondary mailbox.
+	 */
+	if (!idpf_ptp_is_mb_msg(op) || !adapter->ptp->secondary_mbx.valid)
+		return;
+
+	ctlq_msg->opcode = idpf_mbq_opc_send_msg_to_peer_drv;
+	ctlq_msg->func_id = adapter->ptp->secondary_mbx.peer_mbx_q_id;
+	ctlq_msg->host_id = adapter->ptp->secondary_mbx.peer_id;
+}
+#else /* !CONFIG_PTP_1588_CLOCK */
+static void idpf_prepare_ptp_mb_msg(struct idpf_adapter *adapter, u32 op,
+				    struct idpf_ctlq_msg *ctlq_msg)
+{ }
+#endif /* CONFIG_PTP_1588_CLOCK */
+
 /**
  * idpf_send_mb_msg - Send message over mailbox
  * @adapter: Driver specific private structure
@@ -278,6 +247,9 @@ int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op,
 
 	ctlq_msg->opcode = idpf_mbq_opc_send_msg_to_cp;
 	ctlq_msg->func_id = 0;
+
+	idpf_prepare_ptp_mb_msg(adapter, op, ctlq_msg);
+
 	ctlq_msg->data_len = msg_size;
 	ctlq_msg->cookie.mbx.chnl_opcode = op;
 	ctlq_msg->cookie.mbx.chnl_retval = 0;
@@ -376,7 +348,7 @@ static void idpf_vc_xn_init(struct idpf_vc_xn_manager *vcxn_mngr)
  * All waiting threads will be woken-up and their transaction aborted. Further
  * operations on that object will fail.
  */
-static void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr)
+void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr)
 {
 	int i;
 
@@ -449,8 +421,8 @@ static void idpf_vc_xn_push_free(struct idpf_vc_xn_manager *vcxn_mngr,
  * >= @recv_buf.iov_len, but we never overflow @@recv_buf_iov_base). < 0 for
  * error.
  */
-static ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
-			       const struct idpf_vc_xn_params *params)
+ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
+			const struct idpf_vc_xn_params *params)
 {
 	const struct kvec *send_buf = &params->send_buf;
 	struct idpf_vc_xn *xn;
@@ -517,8 +489,10 @@ static ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
 		retval = -ENXIO;
 		goto only_unlock;
 	case IDPF_VC_XN_WAITING:
-		dev_notice_ratelimited(&adapter->pdev->dev, "Transaction timed-out (op %d, %dms)\n",
-				       params->vc_op, params->timeout_ms);
+		dev_notice_ratelimited(&adapter->pdev->dev,
+				       "Transaction timed-out (op:%d cookie:%04x vc_op:%d salt:%02x timeout:%dms)\n",
+				       params->vc_op, cookie, xn->vc_op,
+				       xn->salt, params->timeout_ms);
 		retval = -ETIME;
 		break;
 	case IDPF_VC_XN_COMPLETED_SUCCESS:
@@ -612,14 +586,16 @@ idpf_vc_xn_forward_reply(struct idpf_adapter *adapter,
 		return -EINVAL;
 	}
 	xn = &adapter->vcxn_mngr->ring[xn_idx];
+	idpf_vc_xn_lock(xn);
 	salt = FIELD_GET(IDPF_VC_XN_SALT_M, msg_info);
 	if (xn->salt != salt) {
-		dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (%02x != %02x)\n",
-				    xn->salt, salt);
+		dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (exp:%d@%02x(%d) != got:%d@%02x)\n",
+				    xn->vc_op, xn->salt, xn->state,
+				    ctlq_msg->cookie.mbx.chnl_opcode, salt);
+		idpf_vc_xn_unlock(xn);
 		return -EINVAL;
 	}
 
-	idpf_vc_xn_lock(xn);
 	switch (xn->state) {
 	case IDPF_VC_XN_WAITING:
 		/* success */
@@ -726,9 +702,9 @@ int idpf_recv_mb_msg(struct idpf_adapter *adapter)
 		/* If post failed clear the only buffer we supplied */
 		if (post_err) {
 			if (dma_mem)
-				dmam_free_coherent(&adapter->pdev->dev,
-						   dma_mem->size, dma_mem->va,
-						   dma_mem->pa);
+				dma_free_coherent(&adapter->pdev->dev,
+						  dma_mem->size, dma_mem->va,
+						  dma_mem->pa);
 			break;
 		}
 
@@ -740,34 +716,145 @@ int idpf_recv_mb_msg(struct idpf_adapter *adapter)
 	return err;
 }
 
+struct idpf_chunked_msg_params {
+	u32			(*prepare_msg)(const struct idpf_vport *vport,
+					       void *buf, const void *pos,
+					       u32 num);
+
+	const void		*chunks;
+	u32			num_chunks;
+
+	u32			chunk_sz;
+	u32			config_sz;
+
+	u32			vc_op;
+};
+
+struct idpf_queue_set *idpf_alloc_queue_set(struct idpf_vport *vport, u32 num)
+{
+	struct idpf_queue_set *qp;
+
+	qp = kzalloc(struct_size(qp, qs, num), GFP_KERNEL);
+	if (!qp)
+		return NULL;
+
+	qp->vport = vport;
+	qp->num = num;
+
+	return qp;
+}
+
 /**
- * idpf_wait_for_marker_event - wait for software marker response
+ * idpf_send_chunked_msg - send VC message consisting of chunks
  * @vport: virtual port data structure
+ * @params: message params
  *
- * Returns 0 success, negative on failure.
- **/
-static int idpf_wait_for_marker_event(struct idpf_vport *vport)
+ * Helper function for preparing a message describing queues to be enabled
+ * or disabled.
+ *
+ * Return: the total size of the prepared message.
+ */
+static int idpf_send_chunked_msg(struct idpf_vport *vport,
+				 const struct idpf_chunked_msg_params *params)
 {
-	int event;
-	int i;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op		= params->vc_op,
+		.timeout_ms	= IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	const void *pos = params->chunks;
+	u32 num_chunks, num_msgs, buf_sz;
+	void *buf __free(kfree) = NULL;
+	u32 totqs = params->num_chunks;
+
+	num_chunks = min(IDPF_NUM_CHUNKS_PER_MSG(params->config_sz,
+						 params->chunk_sz), totqs);
+	num_msgs = DIV_ROUND_UP(totqs, num_chunks);
 
-	for (i = 0; i < vport->num_txq; i++)
-		idpf_queue_set(SW_MARKER, vport->txqs[i]);
+	buf_sz = params->config_sz + num_chunks * params->chunk_sz;
+	buf = kzalloc(buf_sz, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
 
-	event = wait_event_timeout(vport->sw_marker_wq,
-				   test_and_clear_bit(IDPF_VPORT_SW_MARKER,
-						      vport->flags),
-				   msecs_to_jiffies(500));
+	xn_params.send_buf.iov_base = buf;
 
-	for (i = 0; i < vport->num_txq; i++)
-		idpf_queue_clear(POLL_MODE, vport->txqs[i]);
+	for (u32 i = 0; i < num_msgs; i++) {
+		ssize_t reply_sz;
 
-	if (event)
-		return 0;
+		memset(buf, 0, buf_sz);
+		xn_params.send_buf.iov_len = buf_sz;
+
+		if (params->prepare_msg(vport, buf, pos, num_chunks) != buf_sz)
+			return -EINVAL;
+
+		reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
+		if (reply_sz < 0)
+			return reply_sz;
+
+		pos += num_chunks * params->chunk_sz;
+		totqs -= num_chunks;
+
+		num_chunks = min(num_chunks, totqs);
+		buf_sz = params->config_sz + num_chunks * params->chunk_sz;
+	}
+
+	return 0;
+}
+
+/**
+ * idpf_wait_for_marker_event_set - wait for software marker response for
+ *				    selected Tx queues
+ * @qs: set of the Tx queues
+ *
+ * Return: 0 success, -errno on failure.
+ */
+static int idpf_wait_for_marker_event_set(const struct idpf_queue_set *qs)
+{
+	struct idpf_tx_queue *txq;
+	bool markers_rcvd = true;
+
+	for (u32 i = 0; i < qs->num; i++) {
+		switch (qs->qs[i].type) {
+		case VIRTCHNL2_QUEUE_TYPE_TX:
+			txq = qs->qs[i].txq;
+
+			idpf_queue_set(SW_MARKER, txq);
+			idpf_wait_for_sw_marker_completion(txq);
+			markers_rcvd &= !idpf_queue_has(SW_MARKER, txq);
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (!markers_rcvd) {
+		netdev_warn(qs->vport->netdev,
+			    "Failed to receive marker packets\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+/**
+ * idpf_wait_for_marker_event - wait for software marker response
+ * @vport: virtual port data structure
+ *
+ * Return: 0 success, negative on failure.
+ **/
+static int idpf_wait_for_marker_event(struct idpf_vport *vport)
+{
+	struct idpf_queue_set *qs __free(kfree) = NULL;
+
+	qs = idpf_alloc_queue_set(vport, vport->num_txq);
+	if (!qs)
+		return -ENOMEM;
 
-	dev_warn(&vport->adapter->pdev->dev, "Failed to receive marker packets\n");
+	for (u32 i = 0; i < qs->num; i++) {
+		qs->qs[i].type = VIRTCHNL2_QUEUE_TYPE_TX;
+		qs->qs[i].txq = vport->txqs[i];
+	}
 
-	return -ETIMEDOUT;
+	return idpf_wait_for_marker_event_set(qs);
 }
 
 /**
@@ -874,14 +961,14 @@ static int idpf_send_get_caps_msg(struct idpf_adapter *adapter)
 			    VIRTCHNL2_CAP_SEG_TX_SINGLE_TUNNEL);
 
 	caps.rss_caps =
-		cpu_to_le64(VIRTCHNL2_CAP_RSS_IPV4_TCP		|
-			    VIRTCHNL2_CAP_RSS_IPV4_UDP		|
-			    VIRTCHNL2_CAP_RSS_IPV4_SCTP		|
-			    VIRTCHNL2_CAP_RSS_IPV4_OTHER	|
-			    VIRTCHNL2_CAP_RSS_IPV6_TCP		|
-			    VIRTCHNL2_CAP_RSS_IPV6_UDP		|
-			    VIRTCHNL2_CAP_RSS_IPV6_SCTP		|
-			    VIRTCHNL2_CAP_RSS_IPV6_OTHER);
+		cpu_to_le64(VIRTCHNL2_FLOW_IPV4_TCP		|
+			    VIRTCHNL2_FLOW_IPV4_UDP		|
+			    VIRTCHNL2_FLOW_IPV4_SCTP		|
+			    VIRTCHNL2_FLOW_IPV4_OTHER		|
+			    VIRTCHNL2_FLOW_IPV6_TCP		|
+			    VIRTCHNL2_FLOW_IPV6_UDP		|
+			    VIRTCHNL2_FLOW_IPV6_SCTP		|
+			    VIRTCHNL2_FLOW_IPV6_OTHER);
 
 	caps.hsplit_caps =
 		cpu_to_le32(VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V4	|
@@ -893,10 +980,13 @@ static int idpf_send_get_caps_msg(struct idpf_adapter *adapter)
 
 	caps.other_caps =
 		cpu_to_le64(VIRTCHNL2_CAP_SRIOV			|
+			    VIRTCHNL2_CAP_RDMA                  |
+			    VIRTCHNL2_CAP_LAN_MEMORY_REGIONS	|
 			    VIRTCHNL2_CAP_MACFILTER		|
 			    VIRTCHNL2_CAP_SPLITQ_QSCHED		|
 			    VIRTCHNL2_CAP_PROMISC		|
-			    VIRTCHNL2_CAP_LOOPBACK);
+			    VIRTCHNL2_CAP_LOOPBACK		|
+			    VIRTCHNL2_CAP_PTP);
 
 	xn_params.vc_op = VIRTCHNL2_OP_GET_CAPS;
 	xn_params.send_buf.iov_base = &caps;
@@ -915,6 +1005,163 @@ static int idpf_send_get_caps_msg(struct idpf_adapter *adapter)
 }
 
 /**
+ * idpf_send_get_lan_memory_regions - Send virtchnl get LAN memory regions msg
+ * @adapter: Driver specific private struct
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_send_get_lan_memory_regions(struct idpf_adapter *adapter)
+{
+	struct virtchnl2_get_lan_memory_regions *rcvd_regions __free(kfree);
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_GET_LAN_MEMORY_REGIONS,
+		.recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN,
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int num_regions, size;
+	struct idpf_hw *hw;
+	ssize_t reply_sz;
+	int err = 0;
+
+	rcvd_regions = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL);
+	if (!rcvd_regions)
+		return -ENOMEM;
+
+	xn_params.recv_buf.iov_base = rcvd_regions;
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+
+	num_regions = le16_to_cpu(rcvd_regions->num_memory_regions);
+	size = struct_size(rcvd_regions, mem_reg, num_regions);
+	if (reply_sz < size)
+		return -EIO;
+
+	if (size > IDPF_CTLQ_MAX_BUF_LEN)
+		return -EINVAL;
+
+	hw = &adapter->hw;
+	hw->lan_regs = kcalloc(num_regions, sizeof(*hw->lan_regs), GFP_KERNEL);
+	if (!hw->lan_regs)
+		return -ENOMEM;
+
+	for (int i = 0; i < num_regions; i++) {
+		hw->lan_regs[i].addr_len =
+			le64_to_cpu(rcvd_regions->mem_reg[i].size);
+		hw->lan_regs[i].addr_start =
+			le64_to_cpu(rcvd_regions->mem_reg[i].start_offset);
+	}
+	hw->num_lan_regs = num_regions;
+
+	return err;
+}
+
+/**
+ * idpf_calc_remaining_mmio_regs - calculate MMIO regions outside mbx and rstat
+ * @adapter: Driver specific private structure
+ *
+ * Called when idpf_send_get_lan_memory_regions is not supported. This will
+ * calculate the offsets and sizes for the regions before, in between, and
+ * after the mailbox and rstat MMIO mappings.
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_calc_remaining_mmio_regs(struct idpf_adapter *adapter)
+{
+	struct resource *rstat_reg = &adapter->dev_ops.static_reg_info[1];
+	struct resource *mbx_reg = &adapter->dev_ops.static_reg_info[0];
+	struct idpf_hw *hw = &adapter->hw;
+
+	hw->num_lan_regs = IDPF_MMIO_MAP_FALLBACK_MAX_REMAINING;
+	hw->lan_regs = kcalloc(hw->num_lan_regs, sizeof(*hw->lan_regs),
+			       GFP_KERNEL);
+	if (!hw->lan_regs)
+		return -ENOMEM;
+
+	/* Region preceding mailbox */
+	hw->lan_regs[0].addr_start = 0;
+	hw->lan_regs[0].addr_len = mbx_reg->start;
+	/* Region between mailbox and rstat */
+	hw->lan_regs[1].addr_start = mbx_reg->end + 1;
+	hw->lan_regs[1].addr_len = rstat_reg->start -
+					hw->lan_regs[1].addr_start;
+	/* Region after rstat */
+	hw->lan_regs[2].addr_start = rstat_reg->end + 1;
+	hw->lan_regs[2].addr_len = pci_resource_len(adapter->pdev, 0) -
+					hw->lan_regs[2].addr_start;
+
+	return 0;
+}
+
+/**
+ * idpf_map_lan_mmio_regs - map remaining LAN BAR regions
+ * @adapter: Driver specific private structure
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_map_lan_mmio_regs(struct idpf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct idpf_hw *hw = &adapter->hw;
+	resource_size_t res_start;
+
+	res_start = pci_resource_start(pdev, 0);
+
+	for (int i = 0; i < hw->num_lan_regs; i++) {
+		resource_size_t start;
+		long len;
+
+		len = hw->lan_regs[i].addr_len;
+		if (!len)
+			continue;
+		start = hw->lan_regs[i].addr_start + res_start;
+
+		hw->lan_regs[i].vaddr = devm_ioremap(&pdev->dev, start, len);
+		if (!hw->lan_regs[i].vaddr) {
+			pci_err(pdev, "failed to allocate BAR0 region\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * idpf_add_del_fsteer_filters - Send virtchnl add/del Flow Steering message
+ * @adapter: adapter info struct
+ * @rule: Flow steering rule to add/delete
+ * @opcode: VIRTCHNL2_OP_ADD_FLOW_RULE to add filter, or
+ *          VIRTCHNL2_OP_DEL_FLOW_RULE to delete. All other values are invalid.
+ *
+ * Send ADD/DELETE flow steering virtchnl message and receive the result.
+ *
+ * Return: 0 on success, negative on failure.
+ */
+int idpf_add_del_fsteer_filters(struct idpf_adapter *adapter,
+				struct virtchnl2_flow_rule_add_del *rule,
+				enum virtchnl2_op opcode)
+{
+	int rule_count = le32_to_cpu(rule->count);
+	struct idpf_vc_xn_params xn_params = {};
+	ssize_t reply_sz;
+
+	if (opcode != VIRTCHNL2_OP_ADD_FLOW_RULE &&
+	    opcode != VIRTCHNL2_OP_DEL_FLOW_RULE)
+		return -EINVAL;
+
+	xn_params.vc_op = opcode;
+	xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC;
+	xn_params.async = false;
+	xn_params.send_buf.iov_base = rule;
+	xn_params.send_buf.iov_len = struct_size(rule, rule_info, rule_count);
+	xn_params.recv_buf.iov_base = rule;
+	xn_params.recv_buf.iov_len = struct_size(rule, rule_info, rule_count);
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	return reply_sz < 0 ? reply_sz : 0;
+}
+
+/**
  * idpf_vport_alloc_max_qs - Allocate max queues for a vport
  * @adapter: Driver specific private structure
  * @max_q: vport max queue structure
@@ -925,21 +1172,35 @@ int idpf_vport_alloc_max_qs(struct idpf_adapter *adapter,
 	struct idpf_avail_queue_info *avail_queues = &adapter->avail_queues;
 	struct virtchnl2_get_capabilities *caps = &adapter->caps;
 	u16 default_vports = idpf_get_default_vports(adapter);
-	int max_rx_q, max_tx_q;
+	u32 max_rx_q, max_tx_q, max_buf_q, max_compl_q;
 
 	mutex_lock(&adapter->queue_lock);
 
+	/* Caps are device-wide. Give each vport an equal piece */
 	max_rx_q = le16_to_cpu(caps->max_rx_q) / default_vports;
 	max_tx_q = le16_to_cpu(caps->max_tx_q) / default_vports;
-	if (adapter->num_alloc_vports < default_vports) {
-		max_q->max_rxq = min_t(u16, max_rx_q, IDPF_MAX_Q);
-		max_q->max_txq = min_t(u16, max_tx_q, IDPF_MAX_Q);
-	} else {
-		max_q->max_rxq = IDPF_MIN_Q;
-		max_q->max_txq = IDPF_MIN_Q;
+	max_buf_q = le16_to_cpu(caps->max_rx_bufq) / default_vports;
+	max_compl_q = le16_to_cpu(caps->max_tx_complq) / default_vports;
+
+	if (adapter->num_alloc_vports >= default_vports) {
+		max_rx_q = IDPF_MIN_Q;
+		max_tx_q = IDPF_MIN_Q;
 	}
-	max_q->max_bufq = max_q->max_rxq * IDPF_MAX_BUFQS_PER_RXQ_GRP;
-	max_q->max_complq = max_q->max_txq;
+
+	/*
+	 * Harmonize the numbers. The current implementation always creates
+	 * `IDPF_MAX_BUFQS_PER_RXQ_GRP` buffer queues for each Rx queue and
+	 * one completion queue for each Tx queue for best performance.
+	 * If less buffer or completion queues is available, cap the number
+	 * of the corresponding Rx/Tx queues.
+	 */
+	max_rx_q = min(max_rx_q, max_buf_q / IDPF_MAX_BUFQS_PER_RXQ_GRP);
+	max_tx_q = min(max_tx_q, max_compl_q);
+
+	max_q->max_rxq = max_rx_q;
+	max_q->max_txq = max_tx_q;
+	max_q->max_bufq = max_rx_q * IDPF_MAX_BUFQS_PER_RXQ_GRP;
+	max_q->max_complq = max_tx_q;
 
 	if (avail_queues->avail_rxq < max_q->max_rxq ||
 	    avail_queues->avail_txq < max_q->max_txq ||
@@ -1370,7 +1631,7 @@ int idpf_send_destroy_vport_msg(struct idpf_vport *vport)
 	xn_params.vc_op = VIRTCHNL2_OP_DESTROY_VPORT;
 	xn_params.send_buf.iov_base = &v_id;
 	xn_params.send_buf.iov_len = sizeof(v_id);
-	xn_params.timeout_ms = IDPF_VC_XN_MIN_TIMEOUT_MSEC;
+	xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC;
 	reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
 
 	return reply_sz < 0 ? reply_sz : 0;
@@ -1418,236 +1679,368 @@ int idpf_send_disable_vport_msg(struct idpf_vport *vport)
 	xn_params.vc_op = VIRTCHNL2_OP_DISABLE_VPORT;
 	xn_params.send_buf.iov_base = &v_id;
 	xn_params.send_buf.iov_len = sizeof(v_id);
-	xn_params.timeout_ms = IDPF_VC_XN_MIN_TIMEOUT_MSEC;
+	xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC;
 	reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
 
 	return reply_sz < 0 ? reply_sz : 0;
 }
 
 /**
- * idpf_send_config_tx_queues_msg - Send virtchnl config tx queues message
+ * idpf_fill_txq_config_chunk - fill chunk describing the Tx queue
+ * @vport: virtual port data structure
+ * @q: Tx queue to be inserted into VC chunk
+ * @qi: pointer to the buffer containing the VC chunk
+ */
+static void idpf_fill_txq_config_chunk(const struct idpf_vport *vport,
+				       const struct idpf_tx_queue *q,
+				       struct virtchnl2_txq_info *qi)
+{
+	u32 val;
+
+	qi->queue_id = cpu_to_le32(q->q_id);
+	qi->model = cpu_to_le16(vport->txq_model);
+	qi->type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX);
+	qi->ring_len = cpu_to_le16(q->desc_count);
+	qi->dma_ring_addr = cpu_to_le64(q->dma);
+	qi->relative_queue_id = cpu_to_le16(q->rel_q_id);
+
+	if (!idpf_is_queue_model_split(vport->txq_model)) {
+		qi->sched_mode = cpu_to_le16(VIRTCHNL2_TXQ_SCHED_MODE_QUEUE);
+		return;
+	}
+
+	if (idpf_queue_has(XDP, q))
+		val = q->complq->q_id;
+	else
+		val = q->txq_grp->complq->q_id;
+
+	qi->tx_compl_queue_id = cpu_to_le16(val);
+
+	if (idpf_queue_has(FLOW_SCH_EN, q))
+		val = VIRTCHNL2_TXQ_SCHED_MODE_FLOW;
+	else
+		val = VIRTCHNL2_TXQ_SCHED_MODE_QUEUE;
+
+	qi->sched_mode = cpu_to_le16(val);
+}
+
+/**
+ * idpf_fill_complq_config_chunk - fill chunk describing the completion queue
  * @vport: virtual port data structure
+ * @q: completion queue to be inserted into VC chunk
+ * @qi: pointer to the buffer containing the VC chunk
+ */
+static void idpf_fill_complq_config_chunk(const struct idpf_vport *vport,
+					  const struct idpf_compl_queue *q,
+					  struct virtchnl2_txq_info *qi)
+{
+	u32 val;
+
+	qi->queue_id = cpu_to_le32(q->q_id);
+	qi->model = cpu_to_le16(vport->txq_model);
+	qi->type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION);
+	qi->ring_len = cpu_to_le16(q->desc_count);
+	qi->dma_ring_addr = cpu_to_le64(q->dma);
+
+	if (idpf_queue_has(FLOW_SCH_EN, q))
+		val = VIRTCHNL2_TXQ_SCHED_MODE_FLOW;
+	else
+		val = VIRTCHNL2_TXQ_SCHED_MODE_QUEUE;
+
+	qi->sched_mode = cpu_to_le16(val);
+}
+
+/**
+ * idpf_prepare_cfg_txqs_msg - prepare message to configure selected Tx queues
+ * @vport: virtual port data structure
+ * @buf: buffer containing the message
+ * @pos: pointer to the first chunk describing the tx queue
+ * @num_chunks: number of chunks in the message
  *
- * Send config tx queues virtchnl message. Returns 0 on success, negative on
- * failure.
+ * Helper function for preparing the message describing configuration of
+ * Tx queues.
+ *
+ * Return: the total size of the prepared message.
  */
-static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport)
+static u32 idpf_prepare_cfg_txqs_msg(const struct idpf_vport *vport,
+				     void *buf, const void *pos,
+				     u32 num_chunks)
+{
+	struct virtchnl2_config_tx_queues *ctq = buf;
+
+	ctq->vport_id = cpu_to_le32(vport->vport_id);
+	ctq->num_qinfo = cpu_to_le16(num_chunks);
+	memcpy(ctq->qinfo, pos, num_chunks * sizeof(*ctq->qinfo));
+
+	return struct_size(ctq, qinfo, num_chunks);
+}
+
+/**
+ * idpf_send_config_tx_queue_set_msg - send virtchnl config Tx queues
+ *				       message for selected queues
+ * @qs: set of the Tx queues to configure
+ *
+ * Send config queues virtchnl message for queues contained in the @qs array.
+ * The @qs array can contain Tx queues (or completion queues) only.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+static int idpf_send_config_tx_queue_set_msg(const struct idpf_queue_set *qs)
 {
-	struct virtchnl2_config_tx_queues *ctq __free(kfree) = NULL;
 	struct virtchnl2_txq_info *qi __free(kfree) = NULL;
-	struct idpf_vc_xn_params xn_params = {};
-	u32 config_sz, chunk_sz, buf_sz;
-	int totqs, num_msgs, num_chunks;
-	ssize_t reply_sz;
-	int i, k = 0;
+	struct idpf_chunked_msg_params params = {
+		.vc_op		= VIRTCHNL2_OP_CONFIG_TX_QUEUES,
+		.prepare_msg	= idpf_prepare_cfg_txqs_msg,
+		.config_sz	= sizeof(struct virtchnl2_config_tx_queues),
+		.chunk_sz	= sizeof(*qi),
+	};
 
-	totqs = vport->num_txq + vport->num_complq;
-	qi = kcalloc(totqs, sizeof(struct virtchnl2_txq_info), GFP_KERNEL);
+	qi = kcalloc(qs->num, sizeof(*qi), GFP_KERNEL);
 	if (!qi)
 		return -ENOMEM;
 
-	/* Populate the queue info buffer with all queue context info */
-	for (i = 0; i < vport->num_txq_grp; i++) {
-		struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
-		int j, sched_mode;
-
-		for (j = 0; j < tx_qgrp->num_txq; j++, k++) {
-			qi[k].queue_id =
-				cpu_to_le32(tx_qgrp->txqs[j]->q_id);
-			qi[k].model =
-				cpu_to_le16(vport->txq_model);
-			qi[k].type =
-				cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX);
-			qi[k].ring_len =
-				cpu_to_le16(tx_qgrp->txqs[j]->desc_count);
-			qi[k].dma_ring_addr =
-				cpu_to_le64(tx_qgrp->txqs[j]->dma);
-			if (idpf_is_queue_model_split(vport->txq_model)) {
-				struct idpf_tx_queue *q = tx_qgrp->txqs[j];
-
-				qi[k].tx_compl_queue_id =
-					cpu_to_le16(tx_qgrp->complq->q_id);
-				qi[k].relative_queue_id = cpu_to_le16(j);
-
-				if (idpf_queue_has(FLOW_SCH_EN, q))
-					qi[k].sched_mode =
-					cpu_to_le16(VIRTCHNL2_TXQ_SCHED_MODE_FLOW);
-				else
-					qi[k].sched_mode =
-					cpu_to_le16(VIRTCHNL2_TXQ_SCHED_MODE_QUEUE);
-			} else {
-				qi[k].sched_mode =
-					cpu_to_le16(VIRTCHNL2_TXQ_SCHED_MODE_QUEUE);
-			}
-		}
+	params.chunks = qi;
 
-		if (!idpf_is_queue_model_split(vport->txq_model))
-			continue;
+	for (u32 i = 0; i < qs->num; i++) {
+		if (qs->qs[i].type == VIRTCHNL2_QUEUE_TYPE_TX)
+			idpf_fill_txq_config_chunk(qs->vport, qs->qs[i].txq,
+						   &qi[params.num_chunks++]);
+		else if (qs->qs[i].type == VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION)
+			idpf_fill_complq_config_chunk(qs->vport,
+						      qs->qs[i].complq,
+						      &qi[params.num_chunks++]);
+	}
 
-		qi[k].queue_id = cpu_to_le32(tx_qgrp->complq->q_id);
-		qi[k].model = cpu_to_le16(vport->txq_model);
-		qi[k].type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION);
-		qi[k].ring_len = cpu_to_le16(tx_qgrp->complq->desc_count);
-		qi[k].dma_ring_addr = cpu_to_le64(tx_qgrp->complq->dma);
+	return idpf_send_chunked_msg(qs->vport, &params);
+}
 
-		if (idpf_queue_has(FLOW_SCH_EN, tx_qgrp->complq))
-			sched_mode = VIRTCHNL2_TXQ_SCHED_MODE_FLOW;
-		else
-			sched_mode = VIRTCHNL2_TXQ_SCHED_MODE_QUEUE;
-		qi[k].sched_mode = cpu_to_le16(sched_mode);
+/**
+ * idpf_send_config_tx_queues_msg - send virtchnl config Tx queues message
+ * @vport: virtual port data structure
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport)
+{
+	struct idpf_queue_set *qs __free(kfree) = NULL;
+	u32 totqs = vport->num_txq + vport->num_complq;
+	u32 k = 0;
+
+	qs = idpf_alloc_queue_set(vport, totqs);
+	if (!qs)
+		return -ENOMEM;
+
+	/* Populate the queue info buffer with all queue context info */
+	for (u32 i = 0; i < vport->num_txq_grp; i++) {
+		const struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
+
+		for (u32 j = 0; j < tx_qgrp->num_txq; j++) {
+			qs->qs[k].type = VIRTCHNL2_QUEUE_TYPE_TX;
+			qs->qs[k++].txq = tx_qgrp->txqs[j];
+		}
 
-		k++;
+		if (idpf_is_queue_model_split(vport->txq_model)) {
+			qs->qs[k].type = VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION;
+			qs->qs[k++].complq = tx_qgrp->complq;
+		}
 	}
 
 	/* Make sure accounting agrees */
 	if (k != totqs)
 		return -EINVAL;
 
-	/* Chunk up the queue contexts into multiple messages to avoid
-	 * sending a control queue message buffer that is too large
-	 */
-	config_sz = sizeof(struct virtchnl2_config_tx_queues);
-	chunk_sz = sizeof(struct virtchnl2_txq_info);
+	return idpf_send_config_tx_queue_set_msg(qs);
+}
 
-	num_chunks = min_t(u32, IDPF_NUM_CHUNKS_PER_MSG(config_sz, chunk_sz),
-			   totqs);
-	num_msgs = DIV_ROUND_UP(totqs, num_chunks);
+/**
+ * idpf_fill_rxq_config_chunk - fill chunk describing the Rx queue
+ * @vport: virtual port data structure
+ * @q: Rx queue to be inserted into VC chunk
+ * @qi: pointer to the buffer containing the VC chunk
+ */
+static void idpf_fill_rxq_config_chunk(const struct idpf_vport *vport,
+				       struct idpf_rx_queue *q,
+				       struct virtchnl2_rxq_info *qi)
+{
+	const struct idpf_bufq_set *sets;
+
+	qi->queue_id = cpu_to_le32(q->q_id);
+	qi->model = cpu_to_le16(vport->rxq_model);
+	qi->type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX);
+	qi->ring_len = cpu_to_le16(q->desc_count);
+	qi->dma_ring_addr = cpu_to_le64(q->dma);
+	qi->max_pkt_size = cpu_to_le32(q->rx_max_pkt_size);
+	qi->rx_buffer_low_watermark = cpu_to_le16(q->rx_buffer_low_watermark);
+	qi->qflags = cpu_to_le16(VIRTCHNL2_RX_DESC_SIZE_32BYTE);
+	if (idpf_is_feature_ena(vport, NETIF_F_GRO_HW))
+		qi->qflags |= cpu_to_le16(VIRTCHNL2_RXQ_RSC);
+
+	if (!idpf_is_queue_model_split(vport->rxq_model)) {
+		qi->data_buffer_size = cpu_to_le32(q->rx_buf_size);
+		qi->desc_ids = cpu_to_le64(q->rxdids);
 
-	buf_sz = struct_size(ctq, qinfo, num_chunks);
-	ctq = kzalloc(buf_sz, GFP_KERNEL);
-	if (!ctq)
-		return -ENOMEM;
+		return;
+	}
 
-	xn_params.vc_op = VIRTCHNL2_OP_CONFIG_TX_QUEUES;
-	xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC;
+	sets = q->bufq_sets;
 
-	for (i = 0, k = 0; i < num_msgs; i++) {
-		memset(ctq, 0, buf_sz);
-		ctq->vport_id = cpu_to_le32(vport->vport_id);
-		ctq->num_qinfo = cpu_to_le16(num_chunks);
-		memcpy(ctq->qinfo, &qi[k], chunk_sz * num_chunks);
+	/*
+	 * In splitq mode, RxQ buffer size should be set to that of the first
+	 * buffer queue associated with this RxQ.
+	 */
+	q->rx_buf_size = sets[0].bufq.rx_buf_size;
+	qi->data_buffer_size = cpu_to_le32(q->rx_buf_size);
 
-		xn_params.send_buf.iov_base = ctq;
-		xn_params.send_buf.iov_len = buf_sz;
-		reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
-		if (reply_sz < 0)
-			return reply_sz;
+	qi->rx_bufq1_id = cpu_to_le16(sets[0].bufq.q_id);
+	if (vport->num_bufqs_per_qgrp > IDPF_SINGLE_BUFQ_PER_RXQ_GRP) {
+		qi->bufq2_ena = IDPF_BUFQ2_ENA;
+		qi->rx_bufq2_id = cpu_to_le16(sets[1].bufq.q_id);
+	}
 
-		k += num_chunks;
-		totqs -= num_chunks;
-		num_chunks = min(num_chunks, totqs);
-		/* Recalculate buffer size */
-		buf_sz = struct_size(ctq, qinfo, num_chunks);
+	q->rx_hbuf_size = sets[0].bufq.rx_hbuf_size;
+
+	if (idpf_queue_has(HSPLIT_EN, q)) {
+		qi->qflags |= cpu_to_le16(VIRTCHNL2_RXQ_HDR_SPLIT);
+		qi->hdr_buffer_size = cpu_to_le16(q->rx_hbuf_size);
 	}
 
-	return 0;
+	qi->desc_ids = cpu_to_le64(VIRTCHNL2_RXDID_2_FLEX_SPLITQ_M);
 }
 
 /**
- * idpf_send_config_rx_queues_msg - Send virtchnl config rx queues message
+ * idpf_fill_bufq_config_chunk - fill chunk describing the buffer queue
  * @vport: virtual port data structure
+ * @q: buffer queue to be inserted into VC chunk
+ * @qi: pointer to the buffer containing the VC chunk
+ */
+static void idpf_fill_bufq_config_chunk(const struct idpf_vport *vport,
+					const struct idpf_buf_queue *q,
+					struct virtchnl2_rxq_info *qi)
+{
+	qi->queue_id = cpu_to_le32(q->q_id);
+	qi->model = cpu_to_le16(vport->rxq_model);
+	qi->type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX_BUFFER);
+	qi->ring_len = cpu_to_le16(q->desc_count);
+	qi->dma_ring_addr = cpu_to_le64(q->dma);
+	qi->data_buffer_size = cpu_to_le32(q->rx_buf_size);
+	qi->rx_buffer_low_watermark = cpu_to_le16(q->rx_buffer_low_watermark);
+	qi->desc_ids = cpu_to_le64(VIRTCHNL2_RXDID_2_FLEX_SPLITQ_M);
+	qi->buffer_notif_stride = IDPF_RX_BUF_STRIDE;
+	if (idpf_is_feature_ena(vport, NETIF_F_GRO_HW))
+		qi->qflags = cpu_to_le16(VIRTCHNL2_RXQ_RSC);
+
+	if (idpf_queue_has(HSPLIT_EN, q)) {
+		qi->qflags |= cpu_to_le16(VIRTCHNL2_RXQ_HDR_SPLIT);
+		qi->hdr_buffer_size = cpu_to_le16(q->rx_hbuf_size);
+	}
+}
+
+/**
+ * idpf_prepare_cfg_rxqs_msg - prepare message to configure selected Rx queues
+ * @vport: virtual port data structure
+ * @buf: buffer containing the message
+ * @pos: pointer to the first chunk describing the rx queue
+ * @num_chunks: number of chunks in the message
  *
- * Send config rx queues virtchnl message.  Returns 0 on success, negative on
- * failure.
+ * Helper function for preparing the message describing configuration of
+ * Rx queues.
+ *
+ * Return: the total size of the prepared message.
  */
-static int idpf_send_config_rx_queues_msg(struct idpf_vport *vport)
+static u32 idpf_prepare_cfg_rxqs_msg(const struct idpf_vport *vport,
+				     void *buf, const void *pos,
+				     u32 num_chunks)
+{
+	struct virtchnl2_config_rx_queues *crq = buf;
+
+	crq->vport_id = cpu_to_le32(vport->vport_id);
+	crq->num_qinfo = cpu_to_le16(num_chunks);
+	memcpy(crq->qinfo, pos, num_chunks * sizeof(*crq->qinfo));
+
+	return struct_size(crq, qinfo, num_chunks);
+}
+
+/**
+ * idpf_send_config_rx_queue_set_msg - send virtchnl config Rx queues message
+ *				       for selected queues.
+ * @qs: set of the Rx queues to configure
+ *
+ * Send config queues virtchnl message for queues contained in the @qs array.
+ * The @qs array can contain Rx queues (or buffer queues) only.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+static int idpf_send_config_rx_queue_set_msg(const struct idpf_queue_set *qs)
 {
-	struct virtchnl2_config_rx_queues *crq __free(kfree) = NULL;
 	struct virtchnl2_rxq_info *qi __free(kfree) = NULL;
-	struct idpf_vc_xn_params xn_params = {};
-	u32 config_sz, chunk_sz, buf_sz;
-	int totqs, num_msgs, num_chunks;
-	ssize_t reply_sz;
-	int i, k = 0;
+	struct idpf_chunked_msg_params params = {
+		.vc_op		= VIRTCHNL2_OP_CONFIG_RX_QUEUES,
+		.prepare_msg	= idpf_prepare_cfg_rxqs_msg,
+		.config_sz	= sizeof(struct virtchnl2_config_rx_queues),
+		.chunk_sz	= sizeof(*qi),
+	};
 
-	totqs = vport->num_rxq + vport->num_bufq;
-	qi = kcalloc(totqs, sizeof(struct virtchnl2_rxq_info), GFP_KERNEL);
+	qi = kcalloc(qs->num, sizeof(*qi), GFP_KERNEL);
 	if (!qi)
 		return -ENOMEM;
 
-	/* Populate the queue info buffer with all queue context info */
-	for (i = 0; i < vport->num_rxq_grp; i++) {
-		struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i];
-		u16 num_rxq;
-		int j;
-
-		if (!idpf_is_queue_model_split(vport->rxq_model))
-			goto setup_rxqs;
-
-		for (j = 0; j < vport->num_bufqs_per_qgrp; j++, k++) {
-			struct idpf_buf_queue *bufq =
-				&rx_qgrp->splitq.bufq_sets[j].bufq;
-
-			qi[k].queue_id = cpu_to_le32(bufq->q_id);
-			qi[k].model = cpu_to_le16(vport->rxq_model);
-			qi[k].type =
-				cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX_BUFFER);
-			qi[k].desc_ids = cpu_to_le64(VIRTCHNL2_RXDID_2_FLEX_SPLITQ_M);
-			qi[k].ring_len = cpu_to_le16(bufq->desc_count);
-			qi[k].dma_ring_addr = cpu_to_le64(bufq->dma);
-			qi[k].data_buffer_size = cpu_to_le32(bufq->rx_buf_size);
-			qi[k].buffer_notif_stride = IDPF_RX_BUF_STRIDE;
-			qi[k].rx_buffer_low_watermark =
-				cpu_to_le16(bufq->rx_buffer_low_watermark);
-			if (idpf_is_feature_ena(vport, NETIF_F_GRO_HW))
-				qi[k].qflags |= cpu_to_le16(VIRTCHNL2_RXQ_RSC);
-		}
+	params.chunks = qi;
 
-setup_rxqs:
-		if (idpf_is_queue_model_split(vport->rxq_model))
-			num_rxq = rx_qgrp->splitq.num_rxq_sets;
-		else
-			num_rxq = rx_qgrp->singleq.num_rxq;
+	for (u32 i = 0; i < qs->num; i++) {
+		if (qs->qs[i].type == VIRTCHNL2_QUEUE_TYPE_RX)
+			idpf_fill_rxq_config_chunk(qs->vport, qs->qs[i].rxq,
+						   &qi[params.num_chunks++]);
+		else if (qs->qs[i].type == VIRTCHNL2_QUEUE_TYPE_RX_BUFFER)
+			idpf_fill_bufq_config_chunk(qs->vport, qs->qs[i].bufq,
+						    &qi[params.num_chunks++]);
+	}
 
-		for (j = 0; j < num_rxq; j++, k++) {
-			const struct idpf_bufq_set *sets;
-			struct idpf_rx_queue *rxq;
+	return idpf_send_chunked_msg(qs->vport, &params);
+}
 
-			if (!idpf_is_queue_model_split(vport->rxq_model)) {
-				rxq = rx_qgrp->singleq.rxqs[j];
-				goto common_qi_fields;
-			}
+/**
+ * idpf_send_config_rx_queues_msg - send virtchnl config Rx queues message
+ * @vport: virtual port data structure
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+static int idpf_send_config_rx_queues_msg(struct idpf_vport *vport)
+{
+	bool splitq = idpf_is_queue_model_split(vport->rxq_model);
+	struct idpf_queue_set *qs __free(kfree) = NULL;
+	u32 totqs = vport->num_rxq + vport->num_bufq;
+	u32 k = 0;
 
-			rxq = &rx_qgrp->splitq.rxq_sets[j]->rxq;
-			sets = rxq->bufq_sets;
+	qs = idpf_alloc_queue_set(vport, totqs);
+	if (!qs)
+		return -ENOMEM;
 
-			/* In splitq mode, RXQ buffer size should be
-			 * set to that of the first buffer queue
-			 * associated with this RXQ.
-			 */
-			rxq->rx_buf_size = sets[0].bufq.rx_buf_size;
+	/* Populate the queue info buffer with all queue context info */
+	for (u32 i = 0; i < vport->num_rxq_grp; i++) {
+		const struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i];
+		u32 num_rxq;
 
-			qi[k].rx_bufq1_id = cpu_to_le16(sets[0].bufq.q_id);
-			if (vport->num_bufqs_per_qgrp > IDPF_SINGLE_BUFQ_PER_RXQ_GRP) {
-				qi[k].bufq2_ena = IDPF_BUFQ2_ENA;
-				qi[k].rx_bufq2_id =
-					cpu_to_le16(sets[1].bufq.q_id);
-			}
-			qi[k].rx_buffer_low_watermark =
-				cpu_to_le16(rxq->rx_buffer_low_watermark);
-			if (idpf_is_feature_ena(vport, NETIF_F_GRO_HW))
-				qi[k].qflags |= cpu_to_le16(VIRTCHNL2_RXQ_RSC);
-
-			rxq->rx_hbuf_size = sets[0].bufq.rx_hbuf_size;
-
-			if (idpf_queue_has(HSPLIT_EN, rxq)) {
-				qi[k].qflags |=
-					cpu_to_le16(VIRTCHNL2_RXQ_HDR_SPLIT);
-				qi[k].hdr_buffer_size =
-					cpu_to_le16(rxq->rx_hbuf_size);
-			}
+		if (!splitq) {
+			num_rxq = rx_qgrp->singleq.num_rxq;
+			goto rxq;
+		}
+
+		for (u32 j = 0; j < vport->num_bufqs_per_qgrp; j++) {
+			qs->qs[k].type = VIRTCHNL2_QUEUE_TYPE_RX_BUFFER;
+			qs->qs[k++].bufq = &rx_qgrp->splitq.bufq_sets[j].bufq;
+		}
+
+		num_rxq = rx_qgrp->splitq.num_rxq_sets;
 
-common_qi_fields:
-			qi[k].queue_id = cpu_to_le32(rxq->q_id);
-			qi[k].model = cpu_to_le16(vport->rxq_model);
-			qi[k].type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX);
-			qi[k].ring_len = cpu_to_le16(rxq->desc_count);
-			qi[k].dma_ring_addr = cpu_to_le64(rxq->dma);
-			qi[k].max_pkt_size = cpu_to_le32(rxq->rx_max_pkt_size);
-			qi[k].data_buffer_size = cpu_to_le32(rxq->rx_buf_size);
-			qi[k].qflags |=
-				cpu_to_le16(VIRTCHNL2_RX_DESC_SIZE_32BYTE);
-			qi[k].desc_ids = cpu_to_le64(rxq->rxdids);
+rxq:
+		for (u32 j = 0; j < num_rxq; j++) {
+			qs->qs[k].type = VIRTCHNL2_QUEUE_TYPE_RX;
+
+			if (splitq)
+				qs->qs[k++].rxq =
+					&rx_qgrp->splitq.rxq_sets[j]->rxq;
+			else
+				qs->qs[k++].rxq = rx_qgrp->singleq.rxqs[j];
 		}
 	}
 
@@ -1655,317 +2048,395 @@ common_qi_fields:
 	if (k != totqs)
 		return -EINVAL;
 
-	/* Chunk up the queue contexts into multiple messages to avoid
-	 * sending a control queue message buffer that is too large
-	 */
-	config_sz = sizeof(struct virtchnl2_config_rx_queues);
-	chunk_sz = sizeof(struct virtchnl2_rxq_info);
+	return idpf_send_config_rx_queue_set_msg(qs);
+}
 
-	num_chunks = min_t(u32, IDPF_NUM_CHUNKS_PER_MSG(config_sz, chunk_sz),
-			   totqs);
-	num_msgs = DIV_ROUND_UP(totqs, num_chunks);
+/**
+ * idpf_prepare_ena_dis_qs_msg - prepare message to enable/disable selected
+ *				 queues
+ * @vport: virtual port data structure
+ * @buf: buffer containing the message
+ * @pos: pointer to the first chunk describing the queue
+ * @num_chunks: number of chunks in the message
+ *
+ * Helper function for preparing the message describing queues to be enabled
+ * or disabled.
+ *
+ * Return: the total size of the prepared message.
+ */
+static u32 idpf_prepare_ena_dis_qs_msg(const struct idpf_vport *vport,
+				       void *buf, const void *pos,
+				       u32 num_chunks)
+{
+	struct virtchnl2_del_ena_dis_queues *eq = buf;
+
+	eq->vport_id = cpu_to_le32(vport->vport_id);
+	eq->chunks.num_chunks = cpu_to_le16(num_chunks);
+	memcpy(eq->chunks.chunks, pos,
+	       num_chunks * sizeof(*eq->chunks.chunks));
+
+	return struct_size(eq, chunks.chunks, num_chunks);
+}
+
+/**
+ * idpf_send_ena_dis_queue_set_msg - send virtchnl enable or disable queues
+ *				     message for selected queues
+ * @qs: set of the queues to enable or disable
+ * @en: whether to enable or disable queues
+ *
+ * Send enable or disable queues virtchnl message for queues contained
+ * in the @qs array.
+ * The @qs array can contain pointers to both Rx and Tx queues.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+static int idpf_send_ena_dis_queue_set_msg(const struct idpf_queue_set *qs,
+					   bool en)
+{
+	struct virtchnl2_queue_chunk *qc __free(kfree) = NULL;
+	struct idpf_chunked_msg_params params = {
+		.vc_op		= en ? VIRTCHNL2_OP_ENABLE_QUEUES :
+				       VIRTCHNL2_OP_DISABLE_QUEUES,
+		.prepare_msg	= idpf_prepare_ena_dis_qs_msg,
+		.config_sz	= sizeof(struct virtchnl2_del_ena_dis_queues),
+		.chunk_sz	= sizeof(*qc),
+		.num_chunks	= qs->num,
+	};
 
-	buf_sz = struct_size(crq, qinfo, num_chunks);
-	crq = kzalloc(buf_sz, GFP_KERNEL);
-	if (!crq)
+	qc = kcalloc(qs->num, sizeof(*qc), GFP_KERNEL);
+	if (!qc)
 		return -ENOMEM;
 
-	xn_params.vc_op = VIRTCHNL2_OP_CONFIG_RX_QUEUES;
-	xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC;
+	params.chunks = qc;
 
-	for (i = 0, k = 0; i < num_msgs; i++) {
-		memset(crq, 0, buf_sz);
-		crq->vport_id = cpu_to_le32(vport->vport_id);
-		crq->num_qinfo = cpu_to_le16(num_chunks);
-		memcpy(crq->qinfo, &qi[k], chunk_sz * num_chunks);
+	for (u32 i = 0; i < qs->num; i++) {
+		const struct idpf_queue_ptr *q = &qs->qs[i];
+		u32 qid;
 
-		xn_params.send_buf.iov_base = crq;
-		xn_params.send_buf.iov_len = buf_sz;
-		reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
-		if (reply_sz < 0)
-			return reply_sz;
+		qc[i].type = cpu_to_le32(q->type);
+		qc[i].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK);
 
-		k += num_chunks;
-		totqs -= num_chunks;
-		num_chunks = min(num_chunks, totqs);
-		/* Recalculate buffer size */
-		buf_sz = struct_size(crq, qinfo, num_chunks);
+		switch (q->type) {
+		case VIRTCHNL2_QUEUE_TYPE_RX:
+			qid = q->rxq->q_id;
+			break;
+		case VIRTCHNL2_QUEUE_TYPE_TX:
+			qid = q->txq->q_id;
+			break;
+		case VIRTCHNL2_QUEUE_TYPE_RX_BUFFER:
+			qid = q->bufq->q_id;
+			break;
+		case VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION:
+			qid = q->complq->q_id;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		qc[i].start_queue_id = cpu_to_le32(qid);
 	}
 
-	return 0;
+	return idpf_send_chunked_msg(qs->vport, &params);
 }
 
 /**
- * idpf_send_ena_dis_queues_msg - Send virtchnl enable or disable
- * queues message
+ * idpf_send_ena_dis_queues_msg - send virtchnl enable or disable queues
+ *				  message
  * @vport: virtual port data structure
- * @ena: if true enable, false disable
+ * @en: whether to enable or disable queues
  *
- * Send enable or disable queues virtchnl message. Returns 0 on success,
- * negative on failure.
+ * Return: 0 on success, -errno on failure.
  */
-static int idpf_send_ena_dis_queues_msg(struct idpf_vport *vport, bool ena)
+static int idpf_send_ena_dis_queues_msg(struct idpf_vport *vport, bool en)
 {
-	struct virtchnl2_del_ena_dis_queues *eq __free(kfree) = NULL;
-	struct virtchnl2_queue_chunk *qc __free(kfree) = NULL;
-	u32 num_msgs, num_chunks, num_txq, num_rxq, num_q;
-	struct idpf_vc_xn_params xn_params = {};
-	struct virtchnl2_queue_chunks *qcs;
-	u32 config_sz, chunk_sz, buf_sz;
-	ssize_t reply_sz;
-	int i, j, k = 0;
+	struct idpf_queue_set *qs __free(kfree) = NULL;
+	u32 num_txq, num_q, k = 0;
+	bool split;
 
 	num_txq = vport->num_txq + vport->num_complq;
-	num_rxq = vport->num_rxq + vport->num_bufq;
-	num_q = num_txq + num_rxq;
-	buf_sz = sizeof(struct virtchnl2_queue_chunk) * num_q;
-	qc = kzalloc(buf_sz, GFP_KERNEL);
-	if (!qc)
+	num_q = num_txq + vport->num_rxq + vport->num_bufq;
+
+	qs = idpf_alloc_queue_set(vport, num_q);
+	if (!qs)
 		return -ENOMEM;
 
-	for (i = 0; i < vport->num_txq_grp; i++) {
-		struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
+	split = idpf_is_queue_model_split(vport->txq_model);
 
-		for (j = 0; j < tx_qgrp->num_txq; j++, k++) {
-			qc[k].type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX);
-			qc[k].start_queue_id = cpu_to_le32(tx_qgrp->txqs[j]->q_id);
-			qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK);
-		}
-	}
-	if (vport->num_txq != k)
-		return -EINVAL;
+	for (u32 i = 0; i < vport->num_txq_grp; i++) {
+		const struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
 
-	if (!idpf_is_queue_model_split(vport->txq_model))
-		goto setup_rx;
+		for (u32 j = 0; j < tx_qgrp->num_txq; j++) {
+			qs->qs[k].type = VIRTCHNL2_QUEUE_TYPE_TX;
+			qs->qs[k++].txq = tx_qgrp->txqs[j];
+		}
 
-	for (i = 0; i < vport->num_txq_grp; i++, k++) {
-		struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
+		if (!split)
+			continue;
 
-		qc[k].type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION);
-		qc[k].start_queue_id = cpu_to_le32(tx_qgrp->complq->q_id);
-		qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK);
+		qs->qs[k].type = VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION;
+		qs->qs[k++].complq = tx_qgrp->complq;
 	}
-	if (vport->num_complq != (k - vport->num_txq))
+
+	if (k != num_txq)
 		return -EINVAL;
 
-setup_rx:
-	for (i = 0; i < vport->num_rxq_grp; i++) {
-		struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i];
+	split = idpf_is_queue_model_split(vport->rxq_model);
 
-		if (idpf_is_queue_model_split(vport->rxq_model))
+	for (u32 i = 0; i < vport->num_rxq_grp; i++) {
+		const struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i];
+		u32 num_rxq;
+
+		if (split)
 			num_rxq = rx_qgrp->splitq.num_rxq_sets;
 		else
 			num_rxq = rx_qgrp->singleq.num_rxq;
 
-		for (j = 0; j < num_rxq; j++, k++) {
-			if (idpf_is_queue_model_split(vport->rxq_model)) {
-				qc[k].start_queue_id =
-				cpu_to_le32(rx_qgrp->splitq.rxq_sets[j]->rxq.q_id);
-				qc[k].type =
-				cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX);
-			} else {
-				qc[k].start_queue_id =
-				cpu_to_le32(rx_qgrp->singleq.rxqs[j]->q_id);
-				qc[k].type =
-				cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX);
-			}
-			qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK);
-		}
-	}
-	if (vport->num_rxq != k - (vport->num_txq + vport->num_complq))
-		return -EINVAL;
-
-	if (!idpf_is_queue_model_split(vport->rxq_model))
-		goto send_msg;
+		for (u32 j = 0; j < num_rxq; j++) {
+			qs->qs[k].type = VIRTCHNL2_QUEUE_TYPE_RX;
 
-	for (i = 0; i < vport->num_rxq_grp; i++) {
-		struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i];
+			if (split)
+				qs->qs[k++].rxq =
+					&rx_qgrp->splitq.rxq_sets[j]->rxq;
+			else
+				qs->qs[k++].rxq = rx_qgrp->singleq.rxqs[j];
+		}
 
-		for (j = 0; j < vport->num_bufqs_per_qgrp; j++, k++) {
-			const struct idpf_buf_queue *q;
+		if (!split)
+			continue;
 
-			q = &rx_qgrp->splitq.bufq_sets[j].bufq;
-			qc[k].type =
-				cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX_BUFFER);
-			qc[k].start_queue_id = cpu_to_le32(q->q_id);
-			qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK);
+		for (u32 j = 0; j < vport->num_bufqs_per_qgrp; j++) {
+			qs->qs[k].type = VIRTCHNL2_QUEUE_TYPE_RX_BUFFER;
+			qs->qs[k++].bufq = &rx_qgrp->splitq.bufq_sets[j].bufq;
 		}
 	}
-	if (vport->num_bufq != k - (vport->num_txq +
-				    vport->num_complq +
-				    vport->num_rxq))
+
+	if (k != num_q)
 		return -EINVAL;
 
-send_msg:
-	/* Chunk up the queue info into multiple messages */
-	config_sz = sizeof(struct virtchnl2_del_ena_dis_queues);
-	chunk_sz = sizeof(struct virtchnl2_queue_chunk);
+	return idpf_send_ena_dis_queue_set_msg(qs, en);
+}
+
+/**
+ * idpf_prep_map_unmap_queue_set_vector_msg - prepare message to map or unmap
+ *					      queue set to the interrupt vector
+ * @vport: virtual port data structure
+ * @buf: buffer containing the message
+ * @pos: pointer to the first chunk describing the vector mapping
+ * @num_chunks: number of chunks in the message
+ *
+ * Helper function for preparing the message describing mapping queues to
+ * q_vectors.
+ *
+ * Return: the total size of the prepared message.
+ */
+static u32
+idpf_prep_map_unmap_queue_set_vector_msg(const struct idpf_vport *vport,
+					 void *buf, const void *pos,
+					 u32 num_chunks)
+{
+	struct virtchnl2_queue_vector_maps *vqvm = buf;
 
-	num_chunks = min_t(u32, IDPF_NUM_CHUNKS_PER_MSG(config_sz, chunk_sz),
-			   num_q);
-	num_msgs = DIV_ROUND_UP(num_q, num_chunks);
+	vqvm->vport_id = cpu_to_le32(vport->vport_id);
+	vqvm->num_qv_maps = cpu_to_le16(num_chunks);
+	memcpy(vqvm->qv_maps, pos, num_chunks * sizeof(*vqvm->qv_maps));
 
-	buf_sz = struct_size(eq, chunks.chunks, num_chunks);
-	eq = kzalloc(buf_sz, GFP_KERNEL);
-	if (!eq)
+	return struct_size(vqvm, qv_maps, num_chunks);
+}
+
+/**
+ * idpf_send_map_unmap_queue_set_vector_msg - send virtchnl map or unmap
+ *					      queue set vector message
+ * @qs: set of the queues to map or unmap
+ * @map: true for map and false for unmap
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+static int
+idpf_send_map_unmap_queue_set_vector_msg(const struct idpf_queue_set *qs,
+					 bool map)
+{
+	struct virtchnl2_queue_vector *vqv __free(kfree) = NULL;
+	struct idpf_chunked_msg_params params = {
+		.vc_op		= map ? VIRTCHNL2_OP_MAP_QUEUE_VECTOR :
+					VIRTCHNL2_OP_UNMAP_QUEUE_VECTOR,
+		.prepare_msg	= idpf_prep_map_unmap_queue_set_vector_msg,
+		.config_sz	= sizeof(struct virtchnl2_queue_vector_maps),
+		.chunk_sz	= sizeof(*vqv),
+		.num_chunks	= qs->num,
+	};
+	bool split;
+
+	vqv = kcalloc(qs->num, sizeof(*vqv), GFP_KERNEL);
+	if (!vqv)
 		return -ENOMEM;
 
-	if (ena) {
-		xn_params.vc_op = VIRTCHNL2_OP_ENABLE_QUEUES;
-		xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC;
-	} else {
-		xn_params.vc_op = VIRTCHNL2_OP_DISABLE_QUEUES;
-		xn_params.timeout_ms = IDPF_VC_XN_MIN_TIMEOUT_MSEC;
-	}
+	params.chunks = vqv;
 
-	for (i = 0, k = 0; i < num_msgs; i++) {
-		memset(eq, 0, buf_sz);
-		eq->vport_id = cpu_to_le32(vport->vport_id);
-		eq->chunks.num_chunks = cpu_to_le16(num_chunks);
-		qcs = &eq->chunks;
-		memcpy(qcs->chunks, &qc[k], chunk_sz * num_chunks);
+	split = idpf_is_queue_model_split(qs->vport->txq_model);
 
-		xn_params.send_buf.iov_base = eq;
-		xn_params.send_buf.iov_len = buf_sz;
-		reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
-		if (reply_sz < 0)
-			return reply_sz;
+	for (u32 i = 0; i < qs->num; i++) {
+		const struct idpf_queue_ptr *q = &qs->qs[i];
+		const struct idpf_q_vector *vec;
+		u32 qid, v_idx, itr_idx;
+
+		vqv[i].queue_type = cpu_to_le32(q->type);
 
-		k += num_chunks;
-		num_q -= num_chunks;
-		num_chunks = min(num_chunks, num_q);
-		/* Recalculate buffer size */
-		buf_sz = struct_size(eq, chunks.chunks, num_chunks);
+		switch (q->type) {
+		case VIRTCHNL2_QUEUE_TYPE_RX:
+			qid = q->rxq->q_id;
+
+			if (idpf_queue_has(NOIRQ, q->rxq))
+				vec = NULL;
+			else
+				vec = q->rxq->q_vector;
+
+			if (vec) {
+				v_idx = vec->v_idx;
+				itr_idx = vec->rx_itr_idx;
+			} else {
+				v_idx = qs->vport->noirq_v_idx;
+				itr_idx = VIRTCHNL2_ITR_IDX_0;
+			}
+			break;
+		case VIRTCHNL2_QUEUE_TYPE_TX:
+			qid = q->txq->q_id;
+
+			if (idpf_queue_has(NOIRQ, q->txq))
+				vec = NULL;
+			else if (idpf_queue_has(XDP, q->txq))
+				vec = q->txq->complq->q_vector;
+			else if (split)
+				vec = q->txq->txq_grp->complq->q_vector;
+			else
+				vec = q->txq->q_vector;
+
+			if (vec) {
+				v_idx = vec->v_idx;
+				itr_idx = vec->tx_itr_idx;
+			} else {
+				v_idx = qs->vport->noirq_v_idx;
+				itr_idx = VIRTCHNL2_ITR_IDX_1;
+			}
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		vqv[i].queue_id = cpu_to_le32(qid);
+		vqv[i].vector_id = cpu_to_le16(v_idx);
+		vqv[i].itr_idx = cpu_to_le32(itr_idx);
 	}
 
-	return 0;
+	return idpf_send_chunked_msg(qs->vport, &params);
 }
 
 /**
- * idpf_send_map_unmap_queue_vector_msg - Send virtchnl map or unmap queue
- * vector message
+ * idpf_send_map_unmap_queue_vector_msg - send virtchnl map or unmap queue
+ *					  vector message
  * @vport: virtual port data structure
  * @map: true for map and false for unmap
  *
- * Send map or unmap queue vector virtchnl message.  Returns 0 on success,
- * negative on failure.
+ * Return: 0 on success, -errno on failure.
  */
 int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map)
 {
-	struct virtchnl2_queue_vector_maps *vqvm __free(kfree) = NULL;
-	struct virtchnl2_queue_vector *vqv __free(kfree) = NULL;
-	struct idpf_vc_xn_params xn_params = {};
-	u32 config_sz, chunk_sz, buf_sz;
-	u32 num_msgs, num_chunks, num_q;
-	ssize_t reply_sz;
-	int i, j, k = 0;
+	struct idpf_queue_set *qs __free(kfree) = NULL;
+	u32 num_q = vport->num_txq + vport->num_rxq;
+	u32 k = 0;
 
-	num_q = vport->num_txq + vport->num_rxq;
-
-	buf_sz = sizeof(struct virtchnl2_queue_vector) * num_q;
-	vqv = kzalloc(buf_sz, GFP_KERNEL);
-	if (!vqv)
+	qs = idpf_alloc_queue_set(vport, num_q);
+	if (!qs)
 		return -ENOMEM;
 
-	for (i = 0; i < vport->num_txq_grp; i++) {
-		struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
+	for (u32 i = 0; i < vport->num_txq_grp; i++) {
+		const struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
 
-		for (j = 0; j < tx_qgrp->num_txq; j++, k++) {
-			vqv[k].queue_type =
-				cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX);
-			vqv[k].queue_id = cpu_to_le32(tx_qgrp->txqs[j]->q_id);
-
-			if (idpf_is_queue_model_split(vport->txq_model)) {
-				vqv[k].vector_id =
-				cpu_to_le16(tx_qgrp->complq->q_vector->v_idx);
-				vqv[k].itr_idx =
-				cpu_to_le32(tx_qgrp->complq->q_vector->tx_itr_idx);
-			} else {
-				vqv[k].vector_id =
-				cpu_to_le16(tx_qgrp->txqs[j]->q_vector->v_idx);
-				vqv[k].itr_idx =
-				cpu_to_le32(tx_qgrp->txqs[j]->q_vector->tx_itr_idx);
-			}
+		for (u32 j = 0; j < tx_qgrp->num_txq; j++) {
+			qs->qs[k].type = VIRTCHNL2_QUEUE_TYPE_TX;
+			qs->qs[k++].txq = tx_qgrp->txqs[j];
 		}
 	}
 
-	if (vport->num_txq != k)
+	if (k != vport->num_txq)
 		return -EINVAL;
 
-	for (i = 0; i < vport->num_rxq_grp; i++) {
-		struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i];
-		u16 num_rxq;
+	for (u32 i = 0; i < vport->num_rxq_grp; i++) {
+		const struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i];
+		u32 num_rxq;
 
 		if (idpf_is_queue_model_split(vport->rxq_model))
 			num_rxq = rx_qgrp->splitq.num_rxq_sets;
 		else
 			num_rxq = rx_qgrp->singleq.num_rxq;
 
-		for (j = 0; j < num_rxq; j++, k++) {
-			struct idpf_rx_queue *rxq;
+		for (u32 j = 0; j < num_rxq; j++) {
+			qs->qs[k].type = VIRTCHNL2_QUEUE_TYPE_RX;
 
 			if (idpf_is_queue_model_split(vport->rxq_model))
-				rxq = &rx_qgrp->splitq.rxq_sets[j]->rxq;
+				qs->qs[k++].rxq =
+					&rx_qgrp->splitq.rxq_sets[j]->rxq;
 			else
-				rxq = rx_qgrp->singleq.rxqs[j];
-
-			vqv[k].queue_type =
-				cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX);
-			vqv[k].queue_id = cpu_to_le32(rxq->q_id);
-			vqv[k].vector_id = cpu_to_le16(rxq->q_vector->v_idx);
-			vqv[k].itr_idx = cpu_to_le32(rxq->q_vector->rx_itr_idx);
+				qs->qs[k++].rxq = rx_qgrp->singleq.rxqs[j];
 		}
 	}
 
-	if (idpf_is_queue_model_split(vport->txq_model)) {
-		if (vport->num_rxq != k - vport->num_complq)
-			return -EINVAL;
-	} else {
-		if (vport->num_rxq != k - vport->num_txq)
-			return -EINVAL;
-	}
+	if (k != num_q)
+		return -EINVAL;
 
-	/* Chunk up the vector info into multiple messages */
-	config_sz = sizeof(struct virtchnl2_queue_vector_maps);
-	chunk_sz = sizeof(struct virtchnl2_queue_vector);
+	return idpf_send_map_unmap_queue_set_vector_msg(qs, map);
+}
 
-	num_chunks = min_t(u32, IDPF_NUM_CHUNKS_PER_MSG(config_sz, chunk_sz),
-			   num_q);
-	num_msgs = DIV_ROUND_UP(num_q, num_chunks);
+/**
+ * idpf_send_enable_queue_set_msg - send enable queues virtchnl message for
+ *				    selected queues
+ * @qs: set of the queues
+ *
+ * Send enable queues virtchnl message for queues contained in the @qs array.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int idpf_send_enable_queue_set_msg(const struct idpf_queue_set *qs)
+{
+	return idpf_send_ena_dis_queue_set_msg(qs, true);
+}
 
-	buf_sz = struct_size(vqvm, qv_maps, num_chunks);
-	vqvm = kzalloc(buf_sz, GFP_KERNEL);
-	if (!vqvm)
-		return -ENOMEM;
+/**
+ * idpf_send_disable_queue_set_msg - send disable queues virtchnl message for
+ *				     selected queues
+ * @qs: set of the queues
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int idpf_send_disable_queue_set_msg(const struct idpf_queue_set *qs)
+{
+	int err;
 
-	if (map) {
-		xn_params.vc_op = VIRTCHNL2_OP_MAP_QUEUE_VECTOR;
-		xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC;
-	} else {
-		xn_params.vc_op = VIRTCHNL2_OP_UNMAP_QUEUE_VECTOR;
-		xn_params.timeout_ms = IDPF_VC_XN_MIN_TIMEOUT_MSEC;
-	}
+	err = idpf_send_ena_dis_queue_set_msg(qs, false);
+	if (err)
+		return err;
 
-	for (i = 0, k = 0; i < num_msgs; i++) {
-		memset(vqvm, 0, buf_sz);
-		xn_params.send_buf.iov_base = vqvm;
-		xn_params.send_buf.iov_len = buf_sz;
-		vqvm->vport_id = cpu_to_le32(vport->vport_id);
-		vqvm->num_qv_maps = cpu_to_le16(num_chunks);
-		memcpy(vqvm->qv_maps, &vqv[k], chunk_sz * num_chunks);
+	return idpf_wait_for_marker_event_set(qs);
+}
 
-		reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
-		if (reply_sz < 0)
-			return reply_sz;
+/**
+ * idpf_send_config_queue_set_msg - send virtchnl config queues message for
+ *				    selected queues
+ * @qs: set of the queues
+ *
+ * Send config queues virtchnl message for queues contained in the @qs array.
+ * The @qs array can contain both Rx or Tx queues.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int idpf_send_config_queue_set_msg(const struct idpf_queue_set *qs)
+{
+	int err;
 
-		k += num_chunks;
-		num_q -= num_chunks;
-		num_chunks = min(num_chunks, num_q);
-		/* Recalculate buffer size */
-		buf_sz = struct_size(vqvm, qv_maps, num_chunks);
-	}
+	err = idpf_send_config_tx_queue_set_msg(qs);
+	if (err)
+		return err;
 
-	return 0;
+	return idpf_send_config_rx_queue_set_msg(qs);
 }
 
 /**
@@ -1989,24 +2460,12 @@ int idpf_send_enable_queues_msg(struct idpf_vport *vport)
  */
 int idpf_send_disable_queues_msg(struct idpf_vport *vport)
 {
-	int err, i;
+	int err;
 
 	err = idpf_send_ena_dis_queues_msg(vport, false);
 	if (err)
 		return err;
 
-	/* switch to poll mode as interrupts will be disabled after disable
-	 * queues virtchnl message is sent
-	 */
-	for (i = 0; i < vport->num_txq; i++)
-		idpf_queue_set(POLL_MODE, vport->txqs[i]);
-
-	/* schedule the napi to receive all the marker packets */
-	local_bh_disable();
-	for (i = 0; i < vport->num_q_vectors; i++)
-		napi_schedule(&vport->q_vectors[i].napi);
-	local_bh_enable();
-
 	return idpf_wait_for_marker_event(vport);
 }
 
@@ -2071,7 +2530,7 @@ int idpf_send_delete_queues_msg(struct idpf_vport *vport)
 					 num_chunks);
 
 	xn_params.vc_op = VIRTCHNL2_OP_DEL_QUEUES;
-	xn_params.timeout_ms = IDPF_VC_XN_MIN_TIMEOUT_MSEC;
+	xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC;
 	xn_params.send_buf.iov_base = eq;
 	xn_params.send_buf.iov_len = buf_size;
 	reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
@@ -2235,7 +2694,7 @@ int idpf_send_dealloc_vectors_msg(struct idpf_adapter *adapter)
 	xn_params.vc_op = VIRTCHNL2_OP_DEALLOC_VECTORS;
 	xn_params.send_buf.iov_base = vcs;
 	xn_params.send_buf.iov_len = buf_size;
-	xn_params.timeout_ms = IDPF_VC_XN_MIN_TIMEOUT_MSEC;
+	xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC;
 	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
 	if (reply_sz < 0)
 		return reply_sz;
@@ -2296,7 +2755,7 @@ int idpf_send_get_stats_msg(struct idpf_vport *vport)
 
 
 	/* Don't send get_stats message if the link is down */
-	if (np->state <= __IDPF_VPORT_DOWN)
+	if (!test_bit(IDPF_VPORT_UP, np->state))
 		return 0;
 
 	stats_msg.vport_id = cpu_to_le32(vport->vport_id);
@@ -2825,7 +3284,7 @@ int idpf_init_dflt_mbx(struct idpf_adapter *adapter)
 	struct idpf_hw *hw = &adapter->hw;
 	int err;
 
-	adapter->dev_ops.reg_ops.ctlq_reg_init(ctlq_info);
+	adapter->dev_ops.reg_ops.ctlq_reg_init(adapter, ctlq_info);
 
 	err = idpf_ctlq_init(hw, IDPF_NUM_DFLT_MBX_Q, ctlq_info);
 	if (err)
@@ -2985,6 +3444,30 @@ restart:
 		msleep(task_delay);
 	}
 
+	if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_LAN_MEMORY_REGIONS)) {
+		err = idpf_send_get_lan_memory_regions(adapter);
+		if (err) {
+			dev_err(&adapter->pdev->dev, "Failed to get LAN memory regions: %d\n",
+				err);
+			return -EINVAL;
+		}
+	} else {
+		/* Fallback to mapping the remaining regions of the entire BAR */
+		err = idpf_calc_remaining_mmio_regs(adapter);
+		if (err) {
+			dev_err(&adapter->pdev->dev, "Failed to allocate BAR0 region(s): %d\n",
+				err);
+			return -ENOMEM;
+		}
+	}
+
+	err = idpf_map_lan_mmio_regs(adapter);
+	if (err) {
+		dev_err(&adapter->pdev->dev, "Failed to map BAR0 region(s): %d\n",
+			err);
+		return -ENOMEM;
+	}
+
 	pci_sriov_set_totalvfs(adapter->pdev, idpf_get_max_vfs(adapter));
 	num_max_vports = idpf_get_max_vports(adapter);
 	adapter->max_vports = num_max_vports;
@@ -3025,6 +3508,11 @@ restart:
 		goto err_intr_req;
 	}
 
+	err = idpf_ptp_init(adapter);
+	if (err)
+		pci_err(adapter->pdev, "PTP init failed, err=%pe\n",
+			ERR_PTR(err));
+
 	idpf_init_avail_queues(adapter);
 
 	/* Skew the delay for init tasks for each function based on fn number
@@ -3077,12 +3565,23 @@ init_failed:
  */
 void idpf_vc_core_deinit(struct idpf_adapter *adapter)
 {
+	bool remove_in_prog;
+
 	if (!test_bit(IDPF_VC_CORE_INIT, adapter->flags))
 		return;
 
+	/* Avoid transaction timeouts when called during reset */
+	remove_in_prog = test_bit(IDPF_REMOVE_IN_PROG, adapter->flags);
+	if (!remove_in_prog)
+		idpf_vc_xn_shutdown(adapter->vcxn_mngr);
+
+	idpf_ptp_release(adapter);
 	idpf_deinit_task(adapter);
+	idpf_idc_deinit_core_aux_device(adapter->cdev_info);
 	idpf_intr_rel(adapter);
-	idpf_vc_xn_shutdown(adapter->vcxn_mngr);
+
+	if (remove_in_prog)
+		idpf_vc_xn_shutdown(adapter->vcxn_mngr);
 
 	cancel_delayed_work_sync(&adapter->serv_task);
 	cancel_delayed_work_sync(&adapter->mbx_task);
@@ -3109,9 +3608,17 @@ int idpf_vport_alloc_vec_indexes(struct idpf_vport *vport)
 {
 	struct idpf_vector_info vec_info;
 	int num_alloc_vecs;
+	u32 req;
 
 	vec_info.num_curr_vecs = vport->num_q_vectors;
-	vec_info.num_req_vecs = max(vport->num_txq, vport->num_rxq);
+	if (vec_info.num_curr_vecs)
+		vec_info.num_curr_vecs += IDPF_RESERVED_VECS;
+
+	/* XDPSQs are all bound to the NOIRQ vector from IDPF_RESERVED_VECS */
+	req = max(vport->num_txq - vport->num_xdp_txq, vport->num_rxq) +
+	      IDPF_RESERVED_VECS;
+	vec_info.num_req_vecs = req;
+
 	vec_info.default_vport = vport->default_vport;
 	vec_info.index = vport->idx;
 
@@ -3124,7 +3631,7 @@ int idpf_vport_alloc_vec_indexes(struct idpf_vport *vport)
 		return -EINVAL;
 	}
 
-	vport->num_q_vectors = num_alloc_vecs;
+	vport->num_q_vectors = num_alloc_vecs - IDPF_RESERVED_VECS;
 
 	return 0;
 }
@@ -3145,6 +3652,7 @@ void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q)
 	u16 rx_itr[] = {2, 8, 32, 96, 128};
 	struct idpf_rss_data *rss_data;
 	u16 idx = vport->idx;
+	int err;
 
 	vport_config = adapter->vport_config[idx];
 	rss_data = &vport_config->user_config.rss_data;
@@ -3179,6 +3687,18 @@ void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q)
 	idpf_vport_alloc_vec_indexes(vport);
 
 	vport->crc_enable = adapter->crc_enable;
+
+	if (!(vport_msg->vport_flags &
+	      cpu_to_le16(VIRTCHNL2_VPORT_UPLINK_PORT)))
+		return;
+
+	err = idpf_ptp_get_vport_tstamps_caps(vport);
+	if (err) {
+		pci_dbg(vport->adapter->pdev, "Tx timestamping not supported\n");
+		return;
+	}
+
+	INIT_WORK(&vport->tstamp_task, idpf_tstamp_task);
 }
 
 /**
@@ -3489,6 +4009,79 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
 }
 
 /**
+ * idpf_vport_is_cap_ena - Check if vport capability is enabled
+ * @vport: Private data struct
+ * @flag: flag(s) to check
+ *
+ * Return: true if the capability is supported, false otherwise
+ */
+bool idpf_vport_is_cap_ena(struct idpf_vport *vport, u16 flag)
+{
+	struct virtchnl2_create_vport *vport_msg;
+
+	vport_msg = vport->adapter->vport_params_recvd[vport->idx];
+
+	return !!(le16_to_cpu(vport_msg->vport_flags) & flag);
+}
+
+/**
+ * idpf_sideband_flow_type_ena - Check if steering is enabled for flow type
+ * @vport: Private data struct
+ * @flow_type: flow type to check (from ethtool.h)
+ *
+ * Return: true if sideband filters are allowed for @flow_type, false otherwise
+ */
+bool idpf_sideband_flow_type_ena(struct idpf_vport *vport, u32 flow_type)
+{
+	struct virtchnl2_create_vport *vport_msg;
+	__le64 caps;
+
+	vport_msg = vport->adapter->vport_params_recvd[vport->idx];
+	caps = vport_msg->sideband_flow_caps;
+
+	switch (flow_type) {
+	case TCP_V4_FLOW:
+		return !!(caps & cpu_to_le64(VIRTCHNL2_FLOW_IPV4_TCP));
+	case UDP_V4_FLOW:
+		return !!(caps & cpu_to_le64(VIRTCHNL2_FLOW_IPV4_UDP));
+	default:
+		return false;
+	}
+}
+
+/**
+ * idpf_sideband_action_ena - Check if steering is enabled for action
+ * @vport: Private data struct
+ * @fsp: flow spec
+ *
+ * Return: true if sideband filters are allowed for @fsp, false otherwise
+ */
+bool idpf_sideband_action_ena(struct idpf_vport *vport,
+			      struct ethtool_rx_flow_spec *fsp)
+{
+	struct virtchnl2_create_vport *vport_msg;
+	unsigned int supp_actions;
+
+	vport_msg = vport->adapter->vport_params_recvd[vport->idx];
+	supp_actions = le32_to_cpu(vport_msg->sideband_flow_actions);
+
+	/* Actions Drop/Wake are not supported */
+	if (fsp->ring_cookie == RX_CLS_FLOW_DISC ||
+	    fsp->ring_cookie == RX_CLS_FLOW_WAKE)
+		return false;
+
+	return !!(supp_actions & VIRTCHNL2_ACTION_QUEUE);
+}
+
+unsigned int idpf_fsteer_max_rules(struct idpf_vport *vport)
+{
+	struct virtchnl2_create_vport *vport_msg;
+
+	vport_msg = vport->adapter->vport_params_recvd[vport->idx];
+	return le32_to_cpu(vport_msg->flow_steer_max_rules);
+}
+
+/**
  * idpf_get_vport_id: Get vport id
  * @vport: virtual port structure
  *
@@ -3503,6 +4096,16 @@ u32 idpf_get_vport_id(struct idpf_vport *vport)
 	return le32_to_cpu(vport_msg->vport_id);
 }
 
+static void idpf_set_mac_type(struct idpf_vport *vport,
+			      struct virtchnl2_mac_addr *mac_addr)
+{
+	bool is_primary;
+
+	is_primary = ether_addr_equal(vport->default_mac_addr, mac_addr->addr);
+	mac_addr->type = is_primary ? VIRTCHNL2_MAC_ADDR_PRIMARY :
+				      VIRTCHNL2_MAC_ADDR_EXTRA;
+}
+
 /**
  * idpf_mac_filter_async_handler - Async callback for mac filters
  * @adapter: private data struct
@@ -3632,6 +4235,7 @@ int idpf_add_del_mac_filters(struct idpf_vport *vport,
 			    list) {
 		if (add && f->add) {
 			ether_addr_copy(mac_addr[i].addr, f->macaddr);
+			idpf_set_mac_type(vport, &mac_addr[i]);
 			i++;
 			f->add = false;
 			if (i == total_filters)
@@ -3639,6 +4243,7 @@ int idpf_add_del_mac_filters(struct idpf_vport *vport,
 		}
 		if (!add && f->remove) {
 			ether_addr_copy(mac_addr[i].addr, f->macaddr);
+			idpf_set_mac_type(vport, &mac_addr[i]);
 			i++;
 			f->remove = false;
 			if (i == total_filters)
@@ -3724,3 +4329,42 @@ int idpf_set_promiscuous(struct idpf_adapter *adapter,
 
 	return reply_sz < 0 ? reply_sz : 0;
 }
+
+/**
+ * idpf_idc_rdma_vc_send_sync - virtchnl send callback for IDC registered drivers
+ * @cdev_info: IDC core device info pointer
+ * @send_msg: message to send
+ * @msg_size: size of message to send
+ * @recv_msg: message to populate on reception of response
+ * @recv_len: length of message copied into recv_msg or 0 on error
+ *
+ * Return: 0 on success or error code on failure.
+ */
+int idpf_idc_rdma_vc_send_sync(struct iidc_rdma_core_dev_info *cdev_info,
+			       u8 *send_msg, u16 msg_size,
+			       u8 *recv_msg, u16 *recv_len)
+{
+	struct idpf_adapter *adapter = pci_get_drvdata(cdev_info->pdev);
+	struct idpf_vc_xn_params xn_params = { };
+	ssize_t reply_sz;
+	u16 recv_size;
+
+	if (!recv_msg || !recv_len || msg_size > IDPF_CTLQ_MAX_BUF_LEN)
+		return -EINVAL;
+
+	recv_size = min_t(u16, *recv_len, IDPF_CTLQ_MAX_BUF_LEN);
+	*recv_len = 0;
+	xn_params.vc_op = VIRTCHNL2_OP_RDMA;
+	xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC;
+	xn_params.send_buf.iov_base = send_msg;
+	xn_params.send_buf.iov_len = msg_size;
+	xn_params.recv_buf.iov_base = recv_msg;
+	xn_params.recv_buf.iov_len = recv_size;
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	*recv_len = reply_sz;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(idpf_idc_rdma_vc_send_sync);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
index 83da5d8da56b..eac3d15daa42 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
@@ -4,6 +4,89 @@
 #ifndef _IDPF_VIRTCHNL_H_
 #define _IDPF_VIRTCHNL_H_
 
+#include "virtchnl2.h"
+
+#define IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC	(60 * 1000)
+#define IDPF_VC_XN_IDX_M		GENMASK(7, 0)
+#define IDPF_VC_XN_SALT_M		GENMASK(15, 8)
+#define IDPF_VC_XN_RING_LEN		U8_MAX
+
+/**
+ * enum idpf_vc_xn_state - Virtchnl transaction status
+ * @IDPF_VC_XN_IDLE: not expecting a reply, ready to be used
+ * @IDPF_VC_XN_WAITING: expecting a reply, not yet received
+ * @IDPF_VC_XN_COMPLETED_SUCCESS: a reply was expected and received, buffer
+ *				  updated
+ * @IDPF_VC_XN_COMPLETED_FAILED: a reply was expected and received, but there
+ *				 was an error, buffer not updated
+ * @IDPF_VC_XN_SHUTDOWN: transaction object cannot be used, VC torn down
+ * @IDPF_VC_XN_ASYNC: transaction sent asynchronously and doesn't have the
+ *		      return context; a callback may be provided to handle
+ *		      return
+ */
+enum idpf_vc_xn_state {
+	IDPF_VC_XN_IDLE = 1,
+	IDPF_VC_XN_WAITING,
+	IDPF_VC_XN_COMPLETED_SUCCESS,
+	IDPF_VC_XN_COMPLETED_FAILED,
+	IDPF_VC_XN_SHUTDOWN,
+	IDPF_VC_XN_ASYNC,
+};
+
+struct idpf_vc_xn;
+/* Callback for asynchronous messages */
+typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *,
+			    const struct idpf_ctlq_msg *);
+
+/**
+ * struct idpf_vc_xn - Data structure representing virtchnl transactions
+ * @completed: virtchnl event loop uses that to signal when a reply is
+ *	       available, uses kernel completion API
+ * @state: virtchnl event loop stores the data below, protected by the
+ *	   completion's lock.
+ * @reply_sz: Original size of reply, may be > reply_buf.iov_len; it will be
+ *	      truncated on its way to the receiver thread according to
+ *	      reply_buf.iov_len.
+ * @reply: Reference to the buffer(s) where the reply data should be written
+ *	   to. May be 0-length (then NULL address permitted) if the reply data
+ *	   should be ignored.
+ * @async_handler: if sent asynchronously, a callback can be provided to handle
+ *		   the reply when it's received
+ * @vc_op: corresponding opcode sent with this transaction
+ * @idx: index used as retrieval on reply receive, used for cookie
+ * @salt: changed every message to make unique, used for cookie
+ */
+struct idpf_vc_xn {
+	struct completion completed;
+	enum idpf_vc_xn_state state;
+	size_t reply_sz;
+	struct kvec reply;
+	async_vc_cb async_handler;
+	u32 vc_op;
+	u8 idx;
+	u8 salt;
+};
+
+/**
+ * struct idpf_vc_xn_params - Parameters for executing transaction
+ * @send_buf: kvec for send buffer
+ * @recv_buf: kvec for recv buffer, may be NULL, must then have zero length
+ * @timeout_ms: timeout to wait for reply
+ * @async: send message asynchronously, will not wait on completion
+ * @async_handler: If sent asynchronously, optional callback handler. The user
+ *		   must be careful when using async handlers as the memory for
+ *		   the recv_buf _cannot_ be on stack if this is async.
+ * @vc_op: virtchnl op to send
+ */
+struct idpf_vc_xn_params {
+	struct kvec send_buf;
+	struct kvec recv_buf;
+	int timeout_ms;
+	bool async;
+	async_vc_cb async_handler;
+	u32 vc_op;
+};
+
 struct idpf_adapter;
 struct idpf_netdev_priv;
 struct idpf_vec_regs;
@@ -11,6 +94,8 @@ struct idpf_vport;
 struct idpf_vport_max_q;
 struct idpf_vport_user_config_data;
 
+ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
+			const struct idpf_vc_xn_params *params);
 int idpf_init_dflt_mbx(struct idpf_adapter *adapter);
 void idpf_deinit_dflt_mbx(struct idpf_adapter *adapter);
 int idpf_vc_core_init(struct idpf_adapter *adapter);
@@ -21,10 +106,43 @@ int idpf_get_reg_intr_vecs(struct idpf_vport *vport,
 int idpf_queue_reg_init(struct idpf_vport *vport);
 int idpf_vport_queue_ids_init(struct idpf_vport *vport);
 
+bool idpf_vport_is_cap_ena(struct idpf_vport *vport, u16 flag);
+bool idpf_sideband_flow_type_ena(struct idpf_vport *vport, u32 flow_type);
+bool idpf_sideband_action_ena(struct idpf_vport *vport,
+			      struct ethtool_rx_flow_spec *fsp);
+unsigned int idpf_fsteer_max_rules(struct idpf_vport *vport);
+
 int idpf_recv_mb_msg(struct idpf_adapter *adapter);
 int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op,
 		     u16 msg_size, u8 *msg, u16 cookie);
 
+struct idpf_queue_ptr {
+	enum virtchnl2_queue_type	type;
+	union {
+		struct idpf_rx_queue		*rxq;
+		struct idpf_tx_queue		*txq;
+		struct idpf_buf_queue		*bufq;
+		struct idpf_compl_queue		*complq;
+	};
+};
+
+struct idpf_queue_set {
+	struct idpf_vport		*vport;
+
+	u32				num;
+	struct idpf_queue_ptr		qs[] __counted_by(num);
+};
+
+struct idpf_queue_set *idpf_alloc_queue_set(struct idpf_vport *vport, u32 num);
+
+int idpf_send_enable_queue_set_msg(const struct idpf_queue_set *qs);
+int idpf_send_disable_queue_set_msg(const struct idpf_queue_set *qs);
+int idpf_send_config_queue_set_msg(const struct idpf_queue_set *qs);
+
+int idpf_send_disable_queues_msg(struct idpf_vport *vport);
+int idpf_send_config_queues_msg(struct idpf_vport *vport);
+int idpf_send_enable_queues_msg(struct idpf_vport *vport);
+
 void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q);
 u32 idpf_get_vport_id(struct idpf_vport *vport);
 int idpf_send_create_vport_msg(struct idpf_adapter *adapter,
@@ -41,9 +159,6 @@ void idpf_vport_dealloc_max_qs(struct idpf_adapter *adapter,
 int idpf_send_add_queues_msg(const struct idpf_vport *vport, u16 num_tx_q,
 			     u16 num_complq, u16 num_rx_q, u16 num_rx_bufq);
 int idpf_send_delete_queues_msg(struct idpf_vport *vport);
-int idpf_send_enable_queues_msg(struct idpf_vport *vport);
-int idpf_send_disable_queues_msg(struct idpf_vport *vport);
-int idpf_send_config_queues_msg(struct idpf_vport *vport);
 
 int idpf_vport_alloc_vec_indexes(struct idpf_vport *vport);
 int idpf_get_vec_ids(struct idpf_adapter *adapter,
@@ -66,5 +181,9 @@ int idpf_send_get_stats_msg(struct idpf_vport *vport);
 int idpf_send_set_sriov_vfs_msg(struct idpf_adapter *adapter, u16 num_vfs);
 int idpf_send_get_set_rss_key_msg(struct idpf_vport *vport, bool get);
 int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get);
+void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr);
+int idpf_idc_rdma_vc_send_sync(struct iidc_rdma_core_dev_info *cdev_info,
+			       u8 *send_msg, u16 msg_size,
+			       u8 *recv_msg, u16 *recv_len);
 
 #endif /* _IDPF_VIRTCHNL_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
new file mode 100644
index 000000000000..61cedb6f2854
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
@@ -0,0 +1,673 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2024 Intel Corporation */
+
+#include "idpf.h"
+#include "idpf_ptp.h"
+#include "idpf_virtchnl.h"
+
+/**
+ * idpf_ptp_get_caps - Send virtchnl get ptp capabilities message
+ * @adapter: Driver specific private structure
+ *
+ * Send virtchnl get PTP capabilities message.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int idpf_ptp_get_caps(struct idpf_adapter *adapter)
+{
+	struct virtchnl2_ptp_get_caps *recv_ptp_caps_msg __free(kfree) = NULL;
+	struct virtchnl2_ptp_get_caps send_ptp_caps_msg = {
+		.caps = cpu_to_le32(VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME |
+				    VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB |
+				    VIRTCHNL2_CAP_PTP_GET_CROSS_TIME |
+				    VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB |
+				    VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB |
+				    VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB)
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_CAPS,
+		.send_buf.iov_base = &send_ptp_caps_msg,
+		.send_buf.iov_len = sizeof(send_ptp_caps_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	struct virtchnl2_ptp_cross_time_reg_offsets cross_tstamp_offsets;
+	struct virtchnl2_ptp_clk_adj_reg_offsets clk_adj_offsets;
+	struct virtchnl2_ptp_clk_reg_offsets clock_offsets;
+	struct idpf_ptp_secondary_mbx *scnd_mbx;
+	struct idpf_ptp *ptp = adapter->ptp;
+	enum idpf_ptp_access access_type;
+	u32 temp_offset;
+	int reply_sz;
+
+	recv_ptp_caps_msg = kzalloc(sizeof(struct virtchnl2_ptp_get_caps),
+				    GFP_KERNEL);
+	if (!recv_ptp_caps_msg)
+		return -ENOMEM;
+
+	xn_params.recv_buf.iov_base = recv_ptp_caps_msg;
+	xn_params.recv_buf.iov_len = sizeof(*recv_ptp_caps_msg);
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	else if (reply_sz != sizeof(*recv_ptp_caps_msg))
+		return -EIO;
+
+	ptp->caps = le32_to_cpu(recv_ptp_caps_msg->caps);
+	ptp->base_incval = le64_to_cpu(recv_ptp_caps_msg->base_incval);
+	ptp->max_adj = le32_to_cpu(recv_ptp_caps_msg->max_adj);
+
+	scnd_mbx = &ptp->secondary_mbx;
+	scnd_mbx->peer_mbx_q_id = le16_to_cpu(recv_ptp_caps_msg->peer_mbx_q_id);
+
+	/* if the ptp_mb_q_id holds invalid value (0xffff), the secondary
+	 * mailbox is not supported.
+	 */
+	scnd_mbx->valid = scnd_mbx->peer_mbx_q_id != 0xffff;
+	if (scnd_mbx->valid)
+		scnd_mbx->peer_id = recv_ptp_caps_msg->peer_id;
+
+	/* Determine the access type for the PTP features */
+	idpf_ptp_get_features_access(adapter);
+
+	access_type = ptp->get_dev_clk_time_access;
+	if (access_type != IDPF_PTP_DIRECT)
+		goto cross_tstamp;
+
+	clock_offsets = recv_ptp_caps_msg->clk_offsets;
+
+	temp_offset = le32_to_cpu(clock_offsets.dev_clk_ns_l);
+	ptp->dev_clk_regs.dev_clk_ns_l = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.dev_clk_ns_h);
+	ptp->dev_clk_regs.dev_clk_ns_h = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.phy_clk_ns_l);
+	ptp->dev_clk_regs.phy_clk_ns_l = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.phy_clk_ns_h);
+	ptp->dev_clk_regs.phy_clk_ns_h = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.cmd_sync_trigger);
+	ptp->dev_clk_regs.cmd_sync = idpf_get_reg_addr(adapter, temp_offset);
+
+cross_tstamp:
+	access_type = ptp->get_cross_tstamp_access;
+	if (access_type != IDPF_PTP_DIRECT)
+		goto discipline_clock;
+
+	cross_tstamp_offsets = recv_ptp_caps_msg->cross_time_offsets;
+
+	temp_offset = le32_to_cpu(cross_tstamp_offsets.sys_time_ns_l);
+	ptp->dev_clk_regs.sys_time_ns_l = idpf_get_reg_addr(adapter,
+							    temp_offset);
+	temp_offset = le32_to_cpu(cross_tstamp_offsets.sys_time_ns_h);
+	ptp->dev_clk_regs.sys_time_ns_h = idpf_get_reg_addr(adapter,
+							    temp_offset);
+	temp_offset = le32_to_cpu(cross_tstamp_offsets.cmd_sync_trigger);
+	ptp->dev_clk_regs.cmd_sync = idpf_get_reg_addr(adapter, temp_offset);
+
+discipline_clock:
+	access_type = ptp->adj_dev_clk_time_access;
+	if (access_type != IDPF_PTP_DIRECT)
+		return 0;
+
+	clk_adj_offsets = recv_ptp_caps_msg->clk_adj_offsets;
+
+	/* Device clock offsets */
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_cmd_type);
+	ptp->dev_clk_regs.cmd = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_incval_l);
+	ptp->dev_clk_regs.incval_l = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_incval_h);
+	ptp->dev_clk_regs.incval_h = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_shadj_l);
+	ptp->dev_clk_regs.shadj_l = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_shadj_h);
+	ptp->dev_clk_regs.shadj_h = idpf_get_reg_addr(adapter, temp_offset);
+
+	/* PHY clock offsets */
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_cmd_type);
+	ptp->dev_clk_regs.phy_cmd = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_incval_l);
+	ptp->dev_clk_regs.phy_incval_l = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_incval_h);
+	ptp->dev_clk_regs.phy_incval_h = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_shadj_l);
+	ptp->dev_clk_regs.phy_shadj_l = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_shadj_h);
+	ptp->dev_clk_regs.phy_shadj_h = idpf_get_reg_addr(adapter, temp_offset);
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_dev_clk_time - Send virtchnl get device clk time message
+ * @adapter: Driver specific private structure
+ * @dev_clk_time: Pointer to the device clock structure where the value is set
+ *
+ * Send virtchnl get time message to get the time of the clock.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
+			      struct idpf_ptp_dev_timers *dev_clk_time)
+{
+	struct virtchnl2_ptp_get_dev_clk_time get_dev_clk_time_msg;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME,
+		.send_buf.iov_base = &get_dev_clk_time_msg,
+		.send_buf.iov_len = sizeof(get_dev_clk_time_msg),
+		.recv_buf.iov_base = &get_dev_clk_time_msg,
+		.recv_buf.iov_len = sizeof(get_dev_clk_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+	u64 dev_time;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(get_dev_clk_time_msg))
+		return -EIO;
+
+	dev_time = le64_to_cpu(get_dev_clk_time_msg.dev_time_ns);
+	dev_clk_time->dev_clk_time_ns = dev_time;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_cross_time - Send virtchnl get cross time message
+ * @adapter: Driver specific private structure
+ * @cross_time: Pointer to the device clock structure where the value is set
+ *
+ * Send virtchnl get cross time message to get the time of the clock and the
+ * system time.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_cross_time(struct idpf_adapter *adapter,
+			    struct idpf_ptp_dev_timers *cross_time)
+{
+	struct virtchnl2_ptp_get_cross_time cross_time_msg;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_CROSS_TIME,
+		.send_buf.iov_base = &cross_time_msg,
+		.send_buf.iov_len = sizeof(cross_time_msg),
+		.recv_buf.iov_base = &cross_time_msg,
+		.recv_buf.iov_len = sizeof(cross_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(cross_time_msg))
+		return -EIO;
+
+	cross_time->dev_clk_time_ns = le64_to_cpu(cross_time_msg.dev_time_ns);
+	cross_time->sys_time_ns = le64_to_cpu(cross_time_msg.sys_time_ns);
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_set_dev_clk_time - Send virtchnl set device time message
+ * @adapter: Driver specific private structure
+ * @time: New time value
+ *
+ * Send virtchnl set time message to set the time of the clock.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time)
+{
+	struct virtchnl2_ptp_set_dev_clk_time set_dev_clk_time_msg = {
+		.dev_time_ns = cpu_to_le64(time),
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME,
+		.send_buf.iov_base = &set_dev_clk_time_msg,
+		.send_buf.iov_len = sizeof(set_dev_clk_time_msg),
+		.recv_buf.iov_base = &set_dev_clk_time_msg,
+		.recv_buf.iov_len = sizeof(set_dev_clk_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(set_dev_clk_time_msg))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adj_dev_clk_time - Send virtchnl adj device clock time message
+ * @adapter: Driver specific private structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * Send virtchnl adj time message to adjust the clock by the indicated delta.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, s64 delta)
+{
+	struct virtchnl2_ptp_adj_dev_clk_time adj_dev_clk_time_msg = {
+		.delta = cpu_to_le64(delta),
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME,
+		.send_buf.iov_base = &adj_dev_clk_time_msg,
+		.send_buf.iov_len = sizeof(adj_dev_clk_time_msg),
+		.recv_buf.iov_base = &adj_dev_clk_time_msg,
+		.recv_buf.iov_len = sizeof(adj_dev_clk_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(adj_dev_clk_time_msg))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adj_dev_clk_fine - Send virtchnl adj time message
+ * @adapter: Driver specific private structure
+ * @incval: Source timer increment value per clock cycle
+ *
+ * Send virtchnl adj fine message to adjust the frequency of the clock by
+ * incval.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval)
+{
+	struct virtchnl2_ptp_adj_dev_clk_fine adj_dev_clk_fine_msg = {
+		.incval = cpu_to_le64(incval),
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE,
+		.send_buf.iov_base = &adj_dev_clk_fine_msg,
+		.send_buf.iov_len = sizeof(adj_dev_clk_fine_msg),
+		.recv_buf.iov_base = &adj_dev_clk_fine_msg,
+		.recv_buf.iov_len = sizeof(adj_dev_clk_fine_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(adj_dev_clk_fine_msg))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_vport_tstamps_caps - Send virtchnl to get tstamps caps for vport
+ * @vport: Virtual port structure
+ *
+ * Send virtchnl get vport tstamps caps message to receive the set of tstamp
+ * capabilities per vport.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport)
+{
+	struct virtchnl2_ptp_get_vport_tx_tstamp_caps send_tx_tstamp_caps;
+	struct virtchnl2_ptp_get_vport_tx_tstamp_caps *rcv_tx_tstamp_caps;
+	struct virtchnl2_ptp_tx_tstamp_latch_caps tx_tstamp_latch_caps;
+	struct idpf_ptp_vport_tx_tstamp_caps *tstamp_caps;
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp, *tmp;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS,
+		.send_buf.iov_base = &send_tx_tstamp_caps,
+		.send_buf.iov_len = sizeof(send_tx_tstamp_caps),
+		.recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN,
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	enum idpf_ptp_access tstamp_access, get_dev_clk_access;
+	struct idpf_ptp *ptp = vport->adapter->ptp;
+	struct list_head *head;
+	int err = 0, reply_sz;
+	u16 num_latches;
+	u32 size;
+
+	if (!ptp)
+		return -EOPNOTSUPP;
+
+	tstamp_access = ptp->tx_tstamp_access;
+	get_dev_clk_access = ptp->get_dev_clk_time_access;
+	if (tstamp_access == IDPF_PTP_NONE ||
+	    get_dev_clk_access == IDPF_PTP_NONE)
+		return -EOPNOTSUPP;
+
+	rcv_tx_tstamp_caps = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL);
+	if (!rcv_tx_tstamp_caps)
+		return -ENOMEM;
+
+	send_tx_tstamp_caps.vport_id = cpu_to_le32(vport->vport_id);
+	xn_params.recv_buf.iov_base = rcv_tx_tstamp_caps;
+
+	reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
+	if (reply_sz < 0) {
+		err = reply_sz;
+		goto get_tstamp_caps_out;
+	}
+
+	num_latches = le16_to_cpu(rcv_tx_tstamp_caps->num_latches);
+	size = struct_size(rcv_tx_tstamp_caps, tstamp_latches, num_latches);
+	if (reply_sz != size) {
+		err = -EIO;
+		goto get_tstamp_caps_out;
+	}
+
+	size = struct_size(tstamp_caps, tx_tstamp_status, num_latches);
+	tstamp_caps = kzalloc(size, GFP_KERNEL);
+	if (!tstamp_caps) {
+		err = -ENOMEM;
+		goto get_tstamp_caps_out;
+	}
+
+	tstamp_caps->access = true;
+	tstamp_caps->num_entries = num_latches;
+
+	INIT_LIST_HEAD(&tstamp_caps->latches_in_use);
+	INIT_LIST_HEAD(&tstamp_caps->latches_free);
+
+	spin_lock_init(&tstamp_caps->latches_lock);
+	spin_lock_init(&tstamp_caps->status_lock);
+
+	tstamp_caps->tstamp_ns_lo_bit = rcv_tx_tstamp_caps->tstamp_ns_lo_bit;
+
+	for (u16 i = 0; i < tstamp_caps->num_entries; i++) {
+		__le32 offset_l, offset_h;
+
+		ptp_tx_tstamp = kzalloc(sizeof(*ptp_tx_tstamp), GFP_KERNEL);
+		if (!ptp_tx_tstamp) {
+			err = -ENOMEM;
+			goto err_free_ptp_tx_stamp_list;
+		}
+
+		tx_tstamp_latch_caps = rcv_tx_tstamp_caps->tstamp_latches[i];
+
+		if (tstamp_access != IDPF_PTP_DIRECT)
+			goto skip_offsets;
+
+		offset_l = tx_tstamp_latch_caps.tx_latch_reg_offset_l;
+		offset_h = tx_tstamp_latch_caps.tx_latch_reg_offset_h;
+		ptp_tx_tstamp->tx_latch_reg_offset_l = le32_to_cpu(offset_l);
+		ptp_tx_tstamp->tx_latch_reg_offset_h = le32_to_cpu(offset_h);
+
+skip_offsets:
+		ptp_tx_tstamp->idx = tx_tstamp_latch_caps.index;
+
+		list_add(&ptp_tx_tstamp->list_member,
+			 &tstamp_caps->latches_free);
+
+		tstamp_caps->tx_tstamp_status[i].state = IDPF_PTP_FREE;
+	}
+
+	vport->tx_tstamp_caps = tstamp_caps;
+	kfree(rcv_tx_tstamp_caps);
+
+	return 0;
+
+err_free_ptp_tx_stamp_list:
+	head = &tstamp_caps->latches_free;
+	list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) {
+		list_del(&ptp_tx_tstamp->list_member);
+		kfree(ptp_tx_tstamp);
+	}
+
+	kfree(tstamp_caps);
+get_tstamp_caps_out:
+	kfree(rcv_tx_tstamp_caps);
+
+	return err;
+}
+
+/**
+ * idpf_ptp_update_tstamp_tracker - Update the Tx timestamp tracker based on
+ *				    the skb compatibility.
+ * @caps: Tx timestamp capabilities that monitor the latch status
+ * @skb: skb for which the tstamp value is returned through virtchnl message
+ * @current_state: Current state of the Tx timestamp latch
+ * @expected_state: Expected state of the Tx timestamp latch
+ *
+ * Find a proper skb tracker for which the Tx timestamp is received and change
+ * the state to expected value.
+ *
+ * Return: true if the tracker has been found and updated, false otherwise.
+ */
+static bool
+idpf_ptp_update_tstamp_tracker(struct idpf_ptp_vport_tx_tstamp_caps *caps,
+			       struct sk_buff *skb,
+			       enum idpf_ptp_tx_tstamp_state current_state,
+			       enum idpf_ptp_tx_tstamp_state expected_state)
+{
+	bool updated = false;
+
+	spin_lock(&caps->status_lock);
+	for (u16 i = 0; i < caps->num_entries; i++) {
+		struct idpf_ptp_tx_tstamp_status *status;
+
+		status = &caps->tx_tstamp_status[i];
+
+		if (skb == status->skb && status->state == current_state) {
+			status->state = expected_state;
+			updated = true;
+			break;
+		}
+	}
+	spin_unlock(&caps->status_lock);
+
+	return updated;
+}
+
+/**
+ * idpf_ptp_get_tstamp_value - Get the Tx timestamp value and provide it
+ *			       back to the skb.
+ * @vport: Virtual port structure
+ * @tstamp_latch: Tx timestamp latch structure fulfilled by the Control Plane
+ * @ptp_tx_tstamp: Tx timestamp latch to add to the free list
+ *
+ * Read the value of the Tx timestamp for a given latch received from the
+ * Control Plane, extend it to 64 bit and provide back to the skb.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int
+idpf_ptp_get_tstamp_value(struct idpf_vport *vport,
+			  struct virtchnl2_ptp_tx_tstamp_latch *tstamp_latch,
+			  struct idpf_ptp_tx_tstamp *ptp_tx_tstamp)
+{
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct skb_shared_hwtstamps shhwtstamps;
+	bool state_upd = false;
+	u8 tstamp_ns_lo_bit;
+	u64 tstamp;
+
+	tx_tstamp_caps = vport->tx_tstamp_caps;
+	tstamp_ns_lo_bit = tx_tstamp_caps->tstamp_ns_lo_bit;
+
+	ptp_tx_tstamp->tstamp = le64_to_cpu(tstamp_latch->tstamp);
+	ptp_tx_tstamp->tstamp >>= tstamp_ns_lo_bit;
+
+	state_upd = idpf_ptp_update_tstamp_tracker(tx_tstamp_caps,
+						   ptp_tx_tstamp->skb,
+						   IDPF_PTP_READ_VALUE,
+						   IDPF_PTP_FREE);
+	if (!state_upd)
+		return -EINVAL;
+
+	tstamp = idpf_ptp_extend_ts(vport, ptp_tx_tstamp->tstamp);
+	shhwtstamps.hwtstamp = ns_to_ktime(tstamp);
+	skb_tstamp_tx(ptp_tx_tstamp->skb, &shhwtstamps);
+	consume_skb(ptp_tx_tstamp->skb);
+	ptp_tx_tstamp->skb = NULL;
+
+	list_add(&ptp_tx_tstamp->list_member,
+		 &tx_tstamp_caps->latches_free);
+
+	u64_stats_update_begin(&vport->tstamp_stats.stats_sync);
+	u64_stats_inc(&vport->tstamp_stats.packets);
+	u64_stats_update_end(&vport->tstamp_stats.stats_sync);
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_tx_tstamp_async_handler - Async callback for getting Tx tstamps
+ * @adapter: Driver specific private structure
+ * @xn: transaction for message
+ * @ctlq_msg: received message
+ *
+ * Read the tstamps Tx tstamp values from a received message and put them
+ * directly to the skb. The number of timestamps to read is specified by
+ * the virtchnl message.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int
+idpf_ptp_get_tx_tstamp_async_handler(struct idpf_adapter *adapter,
+				     struct idpf_vc_xn *xn,
+				     const struct idpf_ctlq_msg *ctlq_msg)
+{
+	struct virtchnl2_ptp_get_vport_tx_tstamp_latches *recv_tx_tstamp_msg;
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct virtchnl2_ptp_tx_tstamp_latch tstamp_latch;
+	struct idpf_ptp_tx_tstamp *tx_tstamp, *tmp;
+	struct idpf_vport *tstamp_vport = NULL;
+	struct list_head *head;
+	u16 num_latches;
+	u32 vport_id;
+	int err = 0;
+
+	recv_tx_tstamp_msg = ctlq_msg->ctx.indirect.payload->va;
+	vport_id = le32_to_cpu(recv_tx_tstamp_msg->vport_id);
+
+	idpf_for_each_vport(adapter, vport) {
+		if (!vport)
+			continue;
+
+		if (vport->vport_id == vport_id) {
+			tstamp_vport = vport;
+			break;
+		}
+	}
+
+	if (!tstamp_vport || !tstamp_vport->tx_tstamp_caps)
+		return -EINVAL;
+
+	tx_tstamp_caps = tstamp_vport->tx_tstamp_caps;
+	num_latches = le16_to_cpu(recv_tx_tstamp_msg->num_latches);
+
+	spin_lock_bh(&tx_tstamp_caps->latches_lock);
+	head = &tx_tstamp_caps->latches_in_use;
+
+	for (u16 i = 0; i < num_latches; i++) {
+		tstamp_latch = recv_tx_tstamp_msg->tstamp_latches[i];
+
+		if (!tstamp_latch.valid)
+			continue;
+
+		if (list_empty(head)) {
+			err = -ENOBUFS;
+			goto unlock;
+		}
+
+		list_for_each_entry_safe(tx_tstamp, tmp, head, list_member) {
+			if (tstamp_latch.index == tx_tstamp->idx) {
+				list_del(&tx_tstamp->list_member);
+				err = idpf_ptp_get_tstamp_value(tstamp_vport,
+								&tstamp_latch,
+								tx_tstamp);
+				if (err)
+					goto unlock;
+
+				break;
+			}
+		}
+	}
+
+unlock:
+	spin_unlock_bh(&tx_tstamp_caps->latches_lock);
+
+	return err;
+}
+
+/**
+ * idpf_ptp_get_tx_tstamp - Send virtchnl get Tx timestamp latches message
+ * @vport: Virtual port structure
+ *
+ * Send virtchnl get Tx tstamp message to read the value of the HW timestamp.
+ * The message contains a list of indexes set in the Tx descriptors.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport)
+{
+	struct virtchnl2_ptp_get_vport_tx_tstamp_latches *send_tx_tstamp_msg;
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP,
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+		.async = true,
+		.async_handler = idpf_ptp_get_tx_tstamp_async_handler,
+	};
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp;
+	int reply_sz, size, msg_size;
+	struct list_head *head;
+	bool state_upd;
+	u16 id = 0;
+
+	tx_tstamp_caps = vport->tx_tstamp_caps;
+	head = &tx_tstamp_caps->latches_in_use;
+
+	size = struct_size(send_tx_tstamp_msg, tstamp_latches,
+			   tx_tstamp_caps->num_entries);
+	send_tx_tstamp_msg = kzalloc(size, GFP_KERNEL);
+	if (!send_tx_tstamp_msg)
+		return -ENOMEM;
+
+	spin_lock_bh(&tx_tstamp_caps->latches_lock);
+	list_for_each_entry(ptp_tx_tstamp, head, list_member) {
+		u8 idx;
+
+		state_upd = idpf_ptp_update_tstamp_tracker(tx_tstamp_caps,
+							   ptp_tx_tstamp->skb,
+							   IDPF_PTP_REQUEST,
+							   IDPF_PTP_READ_VALUE);
+		if (!state_upd)
+			continue;
+
+		idx = ptp_tx_tstamp->idx;
+		send_tx_tstamp_msg->tstamp_latches[id].index = idx;
+		id++;
+	}
+	spin_unlock_bh(&tx_tstamp_caps->latches_lock);
+
+	msg_size = struct_size(send_tx_tstamp_msg, tstamp_latches, id);
+	send_tx_tstamp_msg->vport_id = cpu_to_le32(vport->vport_id);
+	send_tx_tstamp_msg->num_latches = cpu_to_le16(id);
+	xn_params.send_buf.iov_base = send_tx_tstamp_msg;
+	xn_params.send_buf.iov_len = msg_size;
+
+	reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
+	kfree(send_tx_tstamp_msg);
+
+	return min(reply_sz, 0);
+}
diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h
index 63deb120359c..02ae447cc24a 100644
--- a/drivers/net/ethernet/intel/idpf/virtchnl2.h
+++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h
@@ -62,12 +62,28 @@ enum virtchnl2_op {
 	VIRTCHNL2_OP_GET_PTYPE_INFO		= 526,
 	/* Opcode 527 and 528 are reserved for VIRTCHNL2_OP_GET_PTYPE_ID and
 	 * VIRTCHNL2_OP_GET_PTYPE_INFO_RAW.
-	 * Opcodes 529, 530, 531, 532 and 533 are reserved.
 	 */
+	VIRTCHNL2_OP_RDMA			= 529,
+	/* Opcodes 530 through 533 are reserved. */
 	VIRTCHNL2_OP_LOOPBACK			= 534,
 	VIRTCHNL2_OP_ADD_MAC_ADDR		= 535,
 	VIRTCHNL2_OP_DEL_MAC_ADDR		= 536,
 	VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE	= 537,
+
+	/* TimeSync opcodes */
+	VIRTCHNL2_OP_PTP_GET_CAPS			= 541,
+	VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP		= 542,
+	VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME		= 543,
+	VIRTCHNL2_OP_PTP_GET_CROSS_TIME			= 544,
+	VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME		= 545,
+	VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE		= 546,
+	VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME		= 547,
+	VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS	= 548,
+	VIRTCHNL2_OP_GET_LAN_MEMORY_REGIONS		= 549,
+	/* Opcode 550 is reserved */
+	VIRTCHNL2_OP_ADD_FLOW_RULE			= 551,
+	VIRTCHNL2_OP_GET_FLOW_RULE			= 552,
+	VIRTCHNL2_OP_DEL_FLOW_RULE			= 553,
 };
 
 /**
@@ -141,22 +157,22 @@ enum virtchnl2_cap_seg {
 	VIRTCHNL2_CAP_SEG_TX_DOUBLE_TUNNEL	= BIT(8),
 };
 
-/* Receive Side Scaling Flow type capability flags */
-enum virtchnl2_cap_rss {
-	VIRTCHNL2_CAP_RSS_IPV4_TCP		= BIT(0),
-	VIRTCHNL2_CAP_RSS_IPV4_UDP		= BIT(1),
-	VIRTCHNL2_CAP_RSS_IPV4_SCTP		= BIT(2),
-	VIRTCHNL2_CAP_RSS_IPV4_OTHER		= BIT(3),
-	VIRTCHNL2_CAP_RSS_IPV6_TCP		= BIT(4),
-	VIRTCHNL2_CAP_RSS_IPV6_UDP		= BIT(5),
-	VIRTCHNL2_CAP_RSS_IPV6_SCTP		= BIT(6),
-	VIRTCHNL2_CAP_RSS_IPV6_OTHER		= BIT(7),
-	VIRTCHNL2_CAP_RSS_IPV4_AH		= BIT(8),
-	VIRTCHNL2_CAP_RSS_IPV4_ESP		= BIT(9),
-	VIRTCHNL2_CAP_RSS_IPV4_AH_ESP		= BIT(10),
-	VIRTCHNL2_CAP_RSS_IPV6_AH		= BIT(11),
-	VIRTCHNL2_CAP_RSS_IPV6_ESP		= BIT(12),
-	VIRTCHNL2_CAP_RSS_IPV6_AH_ESP		= BIT(13),
+/* Receive Side Scaling and Flow Steering Flow type capability flags */
+enum virtchnl2_flow_types {
+	VIRTCHNL2_FLOW_IPV4_TCP		= BIT(0),
+	VIRTCHNL2_FLOW_IPV4_UDP		= BIT(1),
+	VIRTCHNL2_FLOW_IPV4_SCTP	= BIT(2),
+	VIRTCHNL2_FLOW_IPV4_OTHER	= BIT(3),
+	VIRTCHNL2_FLOW_IPV6_TCP		= BIT(4),
+	VIRTCHNL2_FLOW_IPV6_UDP		= BIT(5),
+	VIRTCHNL2_FLOW_IPV6_SCTP	= BIT(6),
+	VIRTCHNL2_FLOW_IPV6_OTHER	= BIT(7),
+	VIRTCHNL2_FLOW_IPV4_AH		= BIT(8),
+	VIRTCHNL2_FLOW_IPV4_ESP		= BIT(9),
+	VIRTCHNL2_FLOW_IPV4_AH_ESP	= BIT(10),
+	VIRTCHNL2_FLOW_IPV6_AH		= BIT(11),
+	VIRTCHNL2_FLOW_IPV6_ESP		= BIT(12),
+	VIRTCHNL2_FLOW_IPV6_AH_ESP	= BIT(13),
 };
 
 /* Header split capability flags */
@@ -182,8 +198,9 @@ enum virtchnl2_cap_other {
 	VIRTCHNL2_CAP_RDMA			= BIT_ULL(0),
 	VIRTCHNL2_CAP_SRIOV			= BIT_ULL(1),
 	VIRTCHNL2_CAP_MACFILTER			= BIT_ULL(2),
-	VIRTCHNL2_CAP_FLOW_DIRECTOR		= BIT_ULL(3),
-	/* Queue based scheduling using split queue model */
+	/* Other capability 3 is available
+	 * Queue based scheduling using split queue model
+	 */
 	VIRTCHNL2_CAP_SPLITQ_QSCHED		= BIT_ULL(4),
 	VIRTCHNL2_CAP_CRC			= BIT_ULL(5),
 	VIRTCHNL2_CAP_ADQ			= BIT_ULL(6),
@@ -197,16 +214,37 @@ enum virtchnl2_cap_other {
 	/* EDT: Earliest Departure Time capability used for Timing Wheel */
 	VIRTCHNL2_CAP_EDT			= BIT_ULL(14),
 	VIRTCHNL2_CAP_ADV_RSS			= BIT_ULL(15),
-	VIRTCHNL2_CAP_FDIR			= BIT_ULL(16),
+	/* Other capability 16 is available */
 	VIRTCHNL2_CAP_RX_FLEX_DESC		= BIT_ULL(17),
 	VIRTCHNL2_CAP_PTYPE			= BIT_ULL(18),
 	VIRTCHNL2_CAP_LOOPBACK			= BIT_ULL(19),
 	/* Other capability 20 is reserved */
+	VIRTCHNL2_CAP_FLOW_STEER		= BIT_ULL(21),
+	VIRTCHNL2_CAP_LAN_MEMORY_REGIONS	= BIT_ULL(22),
 
 	/* this must be the last capability */
 	VIRTCHNL2_CAP_OEM			= BIT_ULL(63),
 };
 
+/**
+ * enum virtchnl2_action_types - Available actions for sideband flow steering
+ * @VIRTCHNL2_ACTION_DROP: Drop the packet
+ * @VIRTCHNL2_ACTION_PASSTHRU: Forward the packet to the next classifier/stage
+ * @VIRTCHNL2_ACTION_QUEUE: Forward the packet to a receive queue
+ * @VIRTCHNL2_ACTION_Q_GROUP: Forward the packet to a receive queue group
+ * @VIRTCHNL2_ACTION_MARK: Mark the packet with specific marker value
+ * @VIRTCHNL2_ACTION_COUNT: Increment the corresponding counter
+ */
+
+enum virtchnl2_action_types {
+	VIRTCHNL2_ACTION_DROP		= BIT(0),
+	VIRTCHNL2_ACTION_PASSTHRU	= BIT(1),
+	VIRTCHNL2_ACTION_QUEUE		= BIT(2),
+	VIRTCHNL2_ACTION_Q_GROUP	= BIT(3),
+	VIRTCHNL2_ACTION_MARK		= BIT(4),
+	VIRTCHNL2_ACTION_COUNT		= BIT(5),
+};
+
 /* underlying device type */
 enum virtchl2_device_type {
 	VIRTCHNL2_MEV_DEVICE			= 0,
@@ -448,7 +486,7 @@ VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_version_info);
  * @seg_caps: See enum virtchnl2_cap_seg.
  * @hsplit_caps: See enum virtchnl2_cap_rx_hsplit_at.
  * @rsc_caps: See enum virtchnl2_cap_rsc.
- * @rss_caps: See enum virtchnl2_cap_rss.
+ * @rss_caps: See enum virtchnl2_flow_types.
  * @other_caps: See enum virtchnl2_cap_other.
  * @mailbox_dyn_ctl: DYN_CTL register offset and vector id for mailbox
  *		     provided by CP.
@@ -473,6 +511,8 @@ VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_version_info);
  *			segment offload.
  * @max_hdr_buf_per_lso: Max number of header buffers that can be used for
  *			 an LSO.
+ * @num_rdma_allocated_vectors: Maximum number of allocated RDMA vectors for
+ *				the device.
  * @pad1: Padding for future extensions.
  *
  * Dataplane driver sends this message to CP to negotiate capabilities and
@@ -520,7 +560,8 @@ struct virtchnl2_get_capabilities {
 	__le32 device_type;
 	u8 min_sso_packet_len;
 	u8 max_hdr_buf_per_lso;
-	u8 pad1[10];
+	__le16 num_rdma_allocated_vectors;
+	u8 pad1[8];
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(80, virtchnl2_get_capabilities);
 
@@ -560,6 +601,23 @@ struct virtchnl2_queue_reg_chunks {
 VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks);
 
 /**
+ * enum virtchnl2_vport_flags - Vport flags that indicate vport capabilities.
+ * @VIRTCHNL2_VPORT_UPLINK_PORT: Representatives of underlying physical ports
+ * @VIRTCHNL2_VPORT_INLINE_FLOW_STEER: Inline flow steering enabled
+ * @VIRTCHNL2_VPORT_INLINE_FLOW_STEER_RXQ: Inline flow steering enabled
+ *  with explicit Rx queue action
+ * @VIRTCHNL2_VPORT_SIDEBAND_FLOW_STEER: Sideband flow steering enabled
+ * @VIRTCHNL2_VPORT_ENABLE_RDMA: RDMA is enabled for this vport
+ */
+enum virtchnl2_vport_flags {
+	VIRTCHNL2_VPORT_UPLINK_PORT		= BIT(0),
+	VIRTCHNL2_VPORT_INLINE_FLOW_STEER	= BIT(1),
+	VIRTCHNL2_VPORT_INLINE_FLOW_STEER_RXQ	= BIT(2),
+	VIRTCHNL2_VPORT_SIDEBAND_FLOW_STEER	= BIT(3),
+	VIRTCHNL2_VPORT_ENABLE_RDMA             = BIT(4),
+};
+
+/**
  * struct virtchnl2_create_vport - Create vport config info.
  * @vport_type: See enum virtchnl2_vport_type.
  * @txq_model: See virtchnl2_queue_model.
@@ -577,10 +635,18 @@ VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks);
  * @max_mtu: Max MTU. CP populates this field on response.
  * @vport_id: Vport id. CP populates this field on response.
  * @default_mac_addr: Default MAC address.
- * @pad: Padding.
+ * @vport_flags: See enum virtchnl2_vport_flags.
  * @rx_desc_ids: See VIRTCHNL2_RX_DESC_IDS definitions.
  * @tx_desc_ids: See VIRTCHNL2_TX_DESC_IDS definitions.
  * @pad1: Padding.
+ * @inline_flow_caps: Bit mask of supported inline-flow-steering
+ *  flow types (See enum virtchnl2_flow_types)
+ * @sideband_flow_caps: Bit mask of supported sideband-flow-steering
+ *  flow types (See enum virtchnl2_flow_types)
+ * @sideband_flow_actions: Bit mask of supported action types
+ *  for sideband flow steering (See enum virtchnl2_action_types)
+ * @flow_steer_max_rules: Max rules allowed for inline and sideband
+ *  flow steering combined
  * @rss_algorithm: RSS algorithm.
  * @rss_key_size: RSS key size.
  * @rss_lut_size: RSS LUT size.
@@ -610,10 +676,14 @@ struct virtchnl2_create_vport {
 	__le16 max_mtu;
 	__le32 vport_id;
 	u8 default_mac_addr[ETH_ALEN];
-	__le16 pad;
+	__le16 vport_flags;
 	__le64 rx_desc_ids;
 	__le64 tx_desc_ids;
-	u8 pad1[72];
+	u8 pad1[48];
+	__le64 inline_flow_caps;
+	__le64 sideband_flow_caps;
+	__le32 sideband_flow_actions;
+	__le32 flow_steer_max_rules;
 	__le32 rss_algorithm;
 	__le16 rss_key_size;
 	__le16 rss_lut_size;
@@ -1270,4 +1340,474 @@ struct virtchnl2_promisc_info {
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_promisc_info);
 
+/**
+ * enum virtchnl2_ptp_caps - PTP capabilities
+ * @VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME: direct access to get the time of
+ *					   device clock
+ * @VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB: mailbox access to get the time of
+ *					      device clock
+ * @VIRTCHNL2_CAP_PTP_GET_CROSS_TIME: direct access to cross timestamp
+ * @VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB: mailbox access to cross timestamp
+ * @VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME: direct access to set the time of
+ *					   device clock
+ * @VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB: mailbox access to set the time of
+ *					      device clock
+ * @VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK: direct access to adjust the time of device
+ *				      clock
+ * @VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB: mailbox access to adjust the time of
+ *					 device clock
+ * @VIRTCHNL2_CAP_PTP_TX_TSTAMPS: direct access to the Tx timestamping
+ * @VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB: mailbox access to the Tx timestamping
+ *
+ * PF/VF negotiates a set of supported PTP capabilities with the Control Plane.
+ * There are two access methods - mailbox (_MB) and direct.
+ * PTP capabilities enables Main Timer operations: get/set/adjust Main Timer,
+ * cross timestamping and the Tx timestamping.
+ */
+enum virtchnl2_ptp_caps {
+	VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME		= BIT(0),
+	VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB	= BIT(1),
+	VIRTCHNL2_CAP_PTP_GET_CROSS_TIME		= BIT(2),
+	VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB		= BIT(3),
+	VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME		= BIT(4),
+	VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB	= BIT(5),
+	VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK		= BIT(6),
+	VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB		= BIT(7),
+	VIRTCHNL2_CAP_PTP_TX_TSTAMPS			= BIT(8),
+	VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB			= BIT(9),
+};
+
+/**
+ * struct virtchnl2_ptp_clk_reg_offsets - Offsets of device and PHY clocks
+ *					  registers.
+ * @dev_clk_ns_l: Device clock low register offset
+ * @dev_clk_ns_h: Device clock high register offset
+ * @phy_clk_ns_l: PHY clock low register offset
+ * @phy_clk_ns_h: PHY clock high register offset
+ * @cmd_sync_trigger: The command sync trigger register offset
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_clk_reg_offsets {
+	__le32 dev_clk_ns_l;
+	__le32 dev_clk_ns_h;
+	__le32 phy_clk_ns_l;
+	__le32 phy_clk_ns_h;
+	__le32 cmd_sync_trigger;
+	u8 pad[4];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(24, virtchnl2_ptp_clk_reg_offsets);
+
+/**
+ * struct virtchnl2_ptp_cross_time_reg_offsets - Offsets of the device cross
+ *						 time registers.
+ * @sys_time_ns_l: System time low register offset
+ * @sys_time_ns_h: System time high register offset
+ * @cmd_sync_trigger: The command sync trigger register offset
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_cross_time_reg_offsets {
+	__le32 sys_time_ns_l;
+	__le32 sys_time_ns_h;
+	__le32 cmd_sync_trigger;
+	u8 pad[4];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_cross_time_reg_offsets);
+
+/**
+ * struct virtchnl2_ptp_clk_adj_reg_offsets - Offsets of device and PHY clocks
+ *					      adjustments registers.
+ * @dev_clk_cmd_type: Device clock command type register offset
+ * @dev_clk_incval_l: Device clock increment value low register offset
+ * @dev_clk_incval_h: Device clock increment value high registers offset
+ * @dev_clk_shadj_l: Device clock shadow adjust low register offset
+ * @dev_clk_shadj_h: Device clock shadow adjust high register offset
+ * @phy_clk_cmd_type: PHY timer command type register offset
+ * @phy_clk_incval_l: PHY timer increment value low register offset
+ * @phy_clk_incval_h: PHY timer increment value high register offset
+ * @phy_clk_shadj_l: PHY timer shadow adjust low register offset
+ * @phy_clk_shadj_h: PHY timer shadow adjust high register offset
+ */
+struct virtchnl2_ptp_clk_adj_reg_offsets {
+	__le32 dev_clk_cmd_type;
+	__le32 dev_clk_incval_l;
+	__le32 dev_clk_incval_h;
+	__le32 dev_clk_shadj_l;
+	__le32 dev_clk_shadj_h;
+	__le32 phy_clk_cmd_type;
+	__le32 phy_clk_incval_l;
+	__le32 phy_clk_incval_h;
+	__le32 phy_clk_shadj_l;
+	__le32 phy_clk_shadj_h;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(40, virtchnl2_ptp_clk_adj_reg_offsets);
+
+/**
+ * struct virtchnl2_ptp_tx_tstamp_latch_caps - PTP Tx timestamp latch
+ *					       capabilities.
+ * @tx_latch_reg_offset_l: Tx timestamp latch low register offset
+ * @tx_latch_reg_offset_h: Tx timestamp latch high register offset
+ * @index: Latch index provided to the Tx descriptor
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_tx_tstamp_latch_caps {
+	__le32 tx_latch_reg_offset_l;
+	__le32 tx_latch_reg_offset_h;
+	u8 index;
+	u8 pad[7];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_tx_tstamp_latch_caps);
+
+/**
+ * struct virtchnl2_ptp_get_vport_tx_tstamp_caps - Structure that defines Tx
+ *						   tstamp entries.
+ * @vport_id: Vport number
+ * @num_latches: Total number of latches
+ * @tstamp_ns_lo_bit: First bit for nanosecond part of the timestamp
+ * @tstamp_ns_hi_bit: Last bit for nanosecond part of the timestamp
+ * @pad: Padding for future tstamp granularity extensions
+ * @tstamp_latches: Capabilities of Tx timestamp entries
+ *
+ * PF/VF sends this message to negotiate the Tx timestamp latches for each
+ * Vport.
+ *
+ * Associated with VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS.
+ */
+struct virtchnl2_ptp_get_vport_tx_tstamp_caps {
+	__le32 vport_id;
+	__le16 num_latches;
+	u8 tstamp_ns_lo_bit;
+	u8 tstamp_ns_hi_bit;
+	u8 pad[8];
+
+	struct virtchnl2_ptp_tx_tstamp_latch_caps tstamp_latches[]
+						  __counted_by_le(num_latches);
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_vport_tx_tstamp_caps);
+
+/**
+ * struct virtchnl2_ptp_get_caps - Get PTP capabilities
+ * @caps: PTP capability bitmap. See enum virtchnl2_ptp_caps
+ * @max_adj: The maximum possible frequency adjustment
+ * @base_incval: The default timer increment value
+ * @peer_mbx_q_id: ID of the PTP Device Control daemon queue
+ * @peer_id: Peer ID for PTP Device Control daemon
+ * @secondary_mbx: Indicates to the driver that it should create a secondary
+ *		   mailbox to inetract with control plane for PTP
+ * @pad: Padding for future extensions
+ * @clk_offsets: Main timer and PHY registers offsets
+ * @cross_time_offsets: Cross time registers offsets
+ * @clk_adj_offsets: Offsets needed to adjust the PHY and the main timer
+ *
+ * PF/VF sends this message to negotiate PTP capabilities. CP updates bitmap
+ * with supported features and fulfills appropriate structures.
+ * If HW uses primary MBX for PTP: secondary_mbx is set to false.
+ * If HW uses secondary MBX for PTP: secondary_mbx is set to true.
+ *	Control plane has 2 MBX and the driver has 1 MBX, send to peer
+ *	driver may be used to send a message using valid ptp_peer_mb_q_id and
+ *	ptp_peer_id.
+ * If HW does not use send to peer driver: secondary_mbx is no care field and
+ * peer_mbx_q_id holds invalid value (0xFFFF).
+ *
+ * Associated with VIRTCHNL2_OP_PTP_GET_CAPS.
+ */
+struct virtchnl2_ptp_get_caps {
+	__le32 caps;
+	__le32 max_adj;
+	__le64 base_incval;
+	__le16 peer_mbx_q_id;
+	u8 peer_id;
+	u8 secondary_mbx;
+	u8 pad[4];
+
+	struct virtchnl2_ptp_clk_reg_offsets clk_offsets;
+	struct virtchnl2_ptp_cross_time_reg_offsets cross_time_offsets;
+	struct virtchnl2_ptp_clk_adj_reg_offsets clk_adj_offsets;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(104, virtchnl2_ptp_get_caps);
+
+/**
+ * struct virtchnl2_ptp_tx_tstamp_latch - Structure that describes tx tstamp
+ *					  values, index and validity.
+ * @tstamp: Timestamp value
+ * @index: Timestamp index from which the value is read
+ * @valid: Timestamp validity
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_tx_tstamp_latch {
+	__le64 tstamp;
+	u8 index;
+	u8 valid;
+	u8 pad[6];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_tx_tstamp_latch);
+
+/**
+ * struct virtchnl2_ptp_get_vport_tx_tstamp_latches - Tx timestamp latches
+ *						      associated with the vport.
+ * @vport_id: Number of vport that requests the timestamp
+ * @num_latches: Number of latches
+ * @get_devtime_with_txtstmp: Flag to request device time along with Tx timestamp
+ * @pad: Padding for future extensions
+ * @device_time: device time if get_devtime_with_txtstmp was set in request
+ * @tstamp_latches: PTP TX timestamp latch
+ *
+ * PF/VF sends this message to receive a specified number of timestamps
+ * entries.
+ *
+ * Associated with VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP.
+ */
+struct virtchnl2_ptp_get_vport_tx_tstamp_latches {
+	__le32 vport_id;
+	__le16 num_latches;
+	u8 get_devtime_with_txtstmp;
+	u8 pad[1];
+	__le64 device_time;
+
+	struct virtchnl2_ptp_tx_tstamp_latch tstamp_latches[]
+					     __counted_by_le(num_latches);
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_vport_tx_tstamp_latches);
+
+/**
+ * struct virtchnl2_ptp_get_dev_clk_time - Associated with message
+ *					   VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME.
+ * @dev_time_ns: Device clock time value in nanoseconds
+ *
+ * PF/VF sends this message to receive the time from the main timer.
+ */
+struct virtchnl2_ptp_get_dev_clk_time {
+	__le64 dev_time_ns;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_get_dev_clk_time);
+
+/**
+ * struct virtchnl2_ptp_get_cross_time: Associated with message
+ *					VIRTCHNL2_OP_PTP_GET_CROSS_TIME.
+ * @sys_time_ns: System counter value expressed in nanoseconds, read
+ *		 synchronously with device time
+ * @dev_time_ns: Device clock time value expressed in nanoseconds
+ *
+ * PF/VF sends this message to receive the cross time.
+ */
+struct virtchnl2_ptp_get_cross_time {
+	__le64 sys_time_ns;
+	__le64 dev_time_ns;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_cross_time);
+
+/**
+ * struct virtchnl2_ptp_set_dev_clk_time: Associated with message
+ *					  VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME.
+ * @dev_time_ns: Device time value expressed in nanoseconds to set
+ *
+ * PF/VF sends this message to set the time of the main timer.
+ */
+struct virtchnl2_ptp_set_dev_clk_time {
+	__le64 dev_time_ns;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_set_dev_clk_time);
+
+/**
+ * struct virtchnl2_ptp_adj_dev_clk_fine: Associated with message
+ *					  VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE.
+ * @incval: Source timer increment value per clock cycle
+ *
+ * PF/VF sends this message to adjust the frequency of the main timer by the
+ * indicated increment value.
+ */
+struct virtchnl2_ptp_adj_dev_clk_fine {
+	__le64 incval;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_adj_dev_clk_fine);
+
+/**
+ * struct virtchnl2_ptp_adj_dev_clk_time: Associated with message
+ *					  VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME.
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * PF/VF sends this message to adjust the time of the main timer by the delta.
+ */
+struct virtchnl2_ptp_adj_dev_clk_time {
+	__le64 delta;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_adj_dev_clk_time);
+
+/**
+ * struct virtchnl2_mem_region - MMIO memory region
+ * @start_offset: starting offset of the MMIO memory region
+ * @size: size of the MMIO memory region
+ */
+struct virtchnl2_mem_region {
+	__le64 start_offset;
+	__le64 size;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_mem_region);
+
+/**
+ * struct virtchnl2_get_lan_memory_regions - List of LAN MMIO memory regions
+ * @num_memory_regions: number of memory regions
+ * @pad: Padding
+ * @mem_reg: List with memory region info
+ *
+ * PF/VF sends this message to learn what LAN MMIO memory regions it should map.
+ */
+struct virtchnl2_get_lan_memory_regions {
+	__le16 num_memory_regions;
+	u8 pad[6];
+	struct virtchnl2_mem_region mem_reg[];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_get_lan_memory_regions);
+
+#define VIRTCHNL2_MAX_NUM_PROTO_HDRS	4
+#define VIRTCHNL2_MAX_SIZE_RAW_PACKET	256
+#define VIRTCHNL2_MAX_NUM_ACTIONS	8
+
+/**
+ * struct virtchnl2_proto_hdr - represent one protocol header
+ * @hdr_type: See enum virtchnl2_proto_hdr_type
+ * @pad: padding
+ * @buffer_spec: binary buffer based on header type.
+ * @buffer_mask: mask applied on buffer_spec.
+ *
+ * Structure to hold protocol headers based on hdr_type
+ */
+struct virtchnl2_proto_hdr {
+	__le32 hdr_type;
+	u8 pad[4];
+	u8 buffer_spec[64];
+	u8 buffer_mask[64];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(136, virtchnl2_proto_hdr);
+
+/**
+ * struct virtchnl2_proto_hdrs - struct to represent match criteria
+ * @tunnel_level: specify where protocol header(s) start from.
+ *                 must be 0 when sending a raw packet request.
+ *                 0 - from the outer layer
+ *                 1 - from the first inner layer
+ *                 2 - from the second inner layer
+ * @pad: Padding bytes
+ * @count: total number of protocol headers in proto_hdr. 0 for raw packet.
+ * @proto_hdr: Array of protocol headers
+ * @raw: struct holding raw packet buffer when count is 0
+ */
+struct virtchnl2_proto_hdrs {
+	u8 tunnel_level;
+	u8 pad[3];
+	__le32 count;
+	union {
+		struct virtchnl2_proto_hdr
+			proto_hdr[VIRTCHNL2_MAX_NUM_PROTO_HDRS];
+		struct {
+			__le16 pkt_len;
+			u8 spec[VIRTCHNL2_MAX_SIZE_RAW_PACKET];
+			u8 mask[VIRTCHNL2_MAX_SIZE_RAW_PACKET];
+		} raw;
+	};
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(552, virtchnl2_proto_hdrs);
+
+/**
+ * struct virtchnl2_rule_action - struct representing single action for a flow
+ * @action_type: see enum virtchnl2_action_types
+ * @act_conf: union representing action depending on action_type.
+ * @act_conf.q_id: queue id to redirect the packets to.
+ * @act_conf.q_grp_id: queue group id to redirect the packets to.
+ * @act_conf.ctr_id: used for count action. If input value 0xFFFFFFFF control
+ *                    plane assigns a new counter and returns the counter ID to
+ *                    the driver. If input value is not 0xFFFFFFFF then it must
+ *                    be an existing counter given to the driver for an earlier
+ *                    flow. Then this flow will share the counter.
+ * @act_conf.mark_id: Value used to mark the packets. Used for mark action.
+ * @act_conf.reserved: Reserved for future use.
+ */
+struct virtchnl2_rule_action {
+	__le32 action_type;
+	union {
+		__le32 q_id;
+		__le32 q_grp_id;
+		__le32 ctr_id;
+		__le32 mark_id;
+		u8 reserved[8];
+	} act_conf;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(12, virtchnl2_rule_action);
+
+/**
+ * struct virtchnl2_rule_action_set - struct representing multiple actions
+ * @count: number of valid actions in the action set of a rule
+ * @actions: array of struct virtchnl2_rule_action
+ */
+struct virtchnl2_rule_action_set {
+	/* action count must be less than VIRTCHNL2_MAX_NUM_ACTIONS */
+	__le32 count;
+	struct virtchnl2_rule_action actions[VIRTCHNL2_MAX_NUM_ACTIONS];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(100, virtchnl2_rule_action_set);
+
+/**
+ * struct virtchnl2_flow_rule - represent one flow steering rule
+ * @proto_hdrs: array of protocol header buffers representing match criteria
+ * @action_set: series of actions to be applied for given rule
+ * @priority: rule priority.
+ * @pad: padding for future extensions.
+ */
+struct virtchnl2_flow_rule {
+	struct virtchnl2_proto_hdrs proto_hdrs;
+	struct virtchnl2_rule_action_set action_set;
+	__le32 priority;
+	u8 pad[8];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(664, virtchnl2_flow_rule);
+
+enum virtchnl2_flow_rule_status {
+	VIRTCHNL2_FLOW_RULE_SUCCESS			= 1,
+	VIRTCHNL2_FLOW_RULE_NORESOURCE			= 2,
+	VIRTCHNL2_FLOW_RULE_EXIST			= 3,
+	VIRTCHNL2_FLOW_RULE_TIMEOUT			= 4,
+	VIRTCHNL2_FLOW_RULE_FLOW_TYPE_NOT_SUPPORTED	= 5,
+	VIRTCHNL2_FLOW_RULE_MATCH_KEY_NOT_SUPPORTED	= 6,
+	VIRTCHNL2_FLOW_RULE_ACTION_NOT_SUPPORTED	= 7,
+	VIRTCHNL2_FLOW_RULE_ACTION_COMBINATION_INVALID	= 8,
+	VIRTCHNL2_FLOW_RULE_ACTION_DATA_INVALID		= 9,
+	VIRTCHNL2_FLOW_RULE_NOT_ADDED			= 10,
+};
+
+/**
+ * struct virtchnl2_flow_rule_info: structure representing single flow rule
+ * @rule_id: rule_id associated with the flow_rule.
+ * @rule_cfg: structure representing rule.
+ * @status: status of rule programming. See enum virtchnl2_flow_rule_status.
+ */
+struct virtchnl2_flow_rule_info {
+	__le32 rule_id;
+	struct virtchnl2_flow_rule rule_cfg;
+	__le32 status;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(672, virtchnl2_flow_rule_info);
+
+/**
+ * struct virtchnl2_flow_rule_add_del - add/delete a flow steering rule
+ * @vport_id: vport id for which the rule is to be added or deleted.
+ * @count: Indicates number of rules to be added or deleted.
+ * @rule_info: Array of flow rules to be added or deleted.
+ *
+ * For VIRTCHNL2_OP_FLOW_RULE_ADD, rule_info contains list of rules to be
+ * added. If rule_id is 0xFFFFFFFF, then the rule is programmed and not cached.
+ *
+ * For VIRTCHNL2_OP_FLOW_RULE_DEL, there are two possibilities. The structure
+ * can contain either array of rule_ids or array of match keys to be deleted.
+ * When match keys are used the corresponding rule_ids must be 0xFFFFFFFF.
+ *
+ * status member of each rule indicates the result. Maximum of 6 rules can be
+ * added or deleted using this method. Driver has to retry in case of any
+ * failure of ADD or DEL opcode. CP doesn't retry in case of failure.
+ */
+struct virtchnl2_flow_rule_add_del {
+	__le32 vport_id;
+	__le32 count;
+	struct virtchnl2_flow_rule_info rule_info[] __counted_by_le(count);
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_flow_rule_add_del);
+
 #endif /* _VIRTCHNL_2_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/xdp.c b/drivers/net/ethernet/intel/idpf/xdp.c
new file mode 100644
index 000000000000..958d16f87424
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/xdp.c
@@ -0,0 +1,486 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2025 Intel Corporation */
+
+#include "idpf.h"
+#include "idpf_virtchnl.h"
+#include "xdp.h"
+#include "xsk.h"
+
+static int idpf_rxq_for_each(const struct idpf_vport *vport,
+			     int (*fn)(struct idpf_rx_queue *rxq, void *arg),
+			     void *arg)
+{
+	bool splitq = idpf_is_queue_model_split(vport->rxq_model);
+
+	if (!vport->rxq_grps)
+		return -ENETDOWN;
+
+	for (u32 i = 0; i < vport->num_rxq_grp; i++) {
+		const struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i];
+		u32 num_rxq;
+
+		if (splitq)
+			num_rxq = rx_qgrp->splitq.num_rxq_sets;
+		else
+			num_rxq = rx_qgrp->singleq.num_rxq;
+
+		for (u32 j = 0; j < num_rxq; j++) {
+			struct idpf_rx_queue *q;
+			int err;
+
+			if (splitq)
+				q = &rx_qgrp->splitq.rxq_sets[j]->rxq;
+			else
+				q = rx_qgrp->singleq.rxqs[j];
+
+			err = fn(q, arg);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static int __idpf_xdp_rxq_info_init(struct idpf_rx_queue *rxq, void *arg)
+{
+	const struct idpf_vport *vport = rxq->q_vector->vport;
+	bool split = idpf_is_queue_model_split(vport->rxq_model);
+	int err;
+
+	err = __xdp_rxq_info_reg(&rxq->xdp_rxq, vport->netdev, rxq->idx,
+				 rxq->q_vector->napi.napi_id,
+				 rxq->rx_buf_size);
+	if (err)
+		return err;
+
+	if (idpf_queue_has(XSK, rxq)) {
+		err = xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq,
+						 MEM_TYPE_XSK_BUFF_POOL,
+						 rxq->pool);
+		if (err)
+			goto unreg;
+	} else {
+		const struct page_pool *pp;
+
+		pp = split ? rxq->bufq_sets[0].bufq.pp : rxq->pp;
+		xdp_rxq_info_attach_page_pool(&rxq->xdp_rxq, pp);
+	}
+
+	if (!split)
+		return 0;
+
+	rxq->xdpsqs = &vport->txqs[vport->xdp_txq_offset];
+	rxq->num_xdp_txq = vport->num_xdp_txq;
+
+	return 0;
+
+unreg:
+	xdp_rxq_info_unreg(&rxq->xdp_rxq);
+
+	return err;
+}
+
+int idpf_xdp_rxq_info_init(struct idpf_rx_queue *rxq)
+{
+	return __idpf_xdp_rxq_info_init(rxq, NULL);
+}
+
+int idpf_xdp_rxq_info_init_all(const struct idpf_vport *vport)
+{
+	return idpf_rxq_for_each(vport, __idpf_xdp_rxq_info_init, NULL);
+}
+
+static int __idpf_xdp_rxq_info_deinit(struct idpf_rx_queue *rxq, void *arg)
+{
+	if (idpf_is_queue_model_split((size_t)arg)) {
+		rxq->xdpsqs = NULL;
+		rxq->num_xdp_txq = 0;
+	}
+
+	if (!idpf_queue_has(XSK, rxq))
+		xdp_rxq_info_detach_mem_model(&rxq->xdp_rxq);
+
+	xdp_rxq_info_unreg(&rxq->xdp_rxq);
+
+	return 0;
+}
+
+void idpf_xdp_rxq_info_deinit(struct idpf_rx_queue *rxq, u32 model)
+{
+	__idpf_xdp_rxq_info_deinit(rxq, (void *)(size_t)model);
+}
+
+void idpf_xdp_rxq_info_deinit_all(const struct idpf_vport *vport)
+{
+	idpf_rxq_for_each(vport, __idpf_xdp_rxq_info_deinit,
+			  (void *)(size_t)vport->rxq_model);
+}
+
+static int idpf_xdp_rxq_assign_prog(struct idpf_rx_queue *rxq, void *arg)
+{
+	struct bpf_prog *prog = arg;
+	struct bpf_prog *old;
+
+	if (prog)
+		bpf_prog_inc(prog);
+
+	old = rcu_replace_pointer(rxq->xdp_prog, prog, lockdep_rtnl_is_held());
+	if (old)
+		bpf_prog_put(old);
+
+	return 0;
+}
+
+void idpf_xdp_copy_prog_to_rqs(const struct idpf_vport *vport,
+			       struct bpf_prog *xdp_prog)
+{
+	idpf_rxq_for_each(vport, idpf_xdp_rxq_assign_prog, xdp_prog);
+}
+
+static void idpf_xdp_tx_timer(struct work_struct *work);
+
+int idpf_xdpsqs_get(const struct idpf_vport *vport)
+{
+	struct libeth_xdpsq_timer **timers __free(kvfree) = NULL;
+	struct net_device *dev;
+	u32 sqs;
+
+	if (!idpf_xdp_enabled(vport))
+		return 0;
+
+	timers = kvcalloc(vport->num_xdp_txq, sizeof(*timers), GFP_KERNEL);
+	if (!timers)
+		return -ENOMEM;
+
+	for (u32 i = 0; i < vport->num_xdp_txq; i++) {
+		timers[i] = kzalloc_node(sizeof(*timers[i]), GFP_KERNEL,
+					 cpu_to_mem(i));
+		if (!timers[i]) {
+			for (int j = i - 1; j >= 0; j--)
+				kfree(timers[j]);
+
+			return -ENOMEM;
+		}
+	}
+
+	dev = vport->netdev;
+	sqs = vport->xdp_txq_offset;
+
+	for (u32 i = sqs; i < vport->num_txq; i++) {
+		struct idpf_tx_queue *xdpsq = vport->txqs[i];
+
+		xdpsq->complq = xdpsq->txq_grp->complq;
+		kfree(xdpsq->refillq);
+		xdpsq->refillq = NULL;
+
+		idpf_queue_clear(FLOW_SCH_EN, xdpsq);
+		idpf_queue_clear(FLOW_SCH_EN, xdpsq->complq);
+		idpf_queue_set(NOIRQ, xdpsq);
+		idpf_queue_set(XDP, xdpsq);
+		idpf_queue_set(XDP, xdpsq->complq);
+
+		xdpsq->timer = timers[i - sqs];
+		libeth_xdpsq_get(&xdpsq->xdp_lock, dev, vport->xdpsq_share);
+		libeth_xdpsq_init_timer(xdpsq->timer, xdpsq, &xdpsq->xdp_lock,
+					idpf_xdp_tx_timer);
+
+		xdpsq->pending = 0;
+		xdpsq->xdp_tx = 0;
+		xdpsq->thresh = libeth_xdp_queue_threshold(xdpsq->desc_count);
+	}
+
+	return 0;
+}
+
+void idpf_xdpsqs_put(const struct idpf_vport *vport)
+{
+	struct net_device *dev;
+	u32 sqs;
+
+	if (!idpf_xdp_enabled(vport))
+		return;
+
+	dev = vport->netdev;
+	sqs = vport->xdp_txq_offset;
+
+	for (u32 i = sqs; i < vport->num_txq; i++) {
+		struct idpf_tx_queue *xdpsq = vport->txqs[i];
+
+		if (!idpf_queue_has_clear(XDP, xdpsq))
+			continue;
+
+		libeth_xdpsq_deinit_timer(xdpsq->timer);
+		libeth_xdpsq_put(&xdpsq->xdp_lock, dev);
+
+		kfree(xdpsq->timer);
+		xdpsq->refillq = NULL;
+		idpf_queue_clear(NOIRQ, xdpsq);
+	}
+}
+
+static int idpf_xdp_parse_cqe(const struct idpf_splitq_4b_tx_compl_desc *desc,
+			      bool gen)
+{
+	u32 val;
+
+#ifdef __LIBETH_WORD_ACCESS
+	val = *(const u32 *)desc;
+#else
+	val = ((u32)le16_to_cpu(desc->q_head_compl_tag.q_head) << 16) |
+	      le16_to_cpu(desc->qid_comptype_gen);
+#endif
+	if (!!(val & IDPF_TXD_COMPLQ_GEN_M) != gen)
+		return -ENODATA;
+
+	if (unlikely((val & GENMASK(IDPF_TXD_COMPLQ_GEN_S - 1, 0)) !=
+		     FIELD_PREP(IDPF_TXD_COMPLQ_COMPL_TYPE_M,
+				IDPF_TXD_COMPLT_RS)))
+		return -EINVAL;
+
+	return upper_16_bits(val);
+}
+
+u32 idpf_xdpsq_poll(struct idpf_tx_queue *xdpsq, u32 budget)
+{
+	struct idpf_compl_queue *cq = xdpsq->complq;
+	u32 tx_ntc = xdpsq->next_to_clean;
+	u32 tx_cnt = xdpsq->desc_count;
+	u32 ntc = cq->next_to_clean;
+	u32 cnt = cq->desc_count;
+	u32 done_frames;
+	bool gen;
+
+	gen = idpf_queue_has(GEN_CHK, cq);
+
+	for (done_frames = 0; done_frames < budget; ) {
+		int ret;
+
+		ret = idpf_xdp_parse_cqe(&cq->comp_4b[ntc], gen);
+		if (ret >= 0) {
+			done_frames = ret > tx_ntc ? ret - tx_ntc :
+						     ret + tx_cnt - tx_ntc;
+			goto next;
+		}
+
+		switch (ret) {
+		case -ENODATA:
+			goto out;
+		case -EINVAL:
+			break;
+		}
+
+next:
+		if (unlikely(++ntc == cnt)) {
+			ntc = 0;
+			gen = !gen;
+			idpf_queue_change(GEN_CHK, cq);
+		}
+	}
+
+out:
+	cq->next_to_clean = ntc;
+
+	return done_frames;
+}
+
+static u32 idpf_xdpsq_complete(void *_xdpsq, u32 budget)
+{
+	struct libeth_xdpsq_napi_stats ss = { };
+	struct idpf_tx_queue *xdpsq = _xdpsq;
+	u32 tx_ntc = xdpsq->next_to_clean;
+	u32 tx_cnt = xdpsq->desc_count;
+	struct xdp_frame_bulk bq;
+	struct libeth_cq_pp cp = {
+		.dev	= xdpsq->dev,
+		.bq	= &bq,
+		.xss	= &ss,
+		.napi	= true,
+	};
+	u32 done_frames;
+
+	done_frames = idpf_xdpsq_poll(xdpsq, budget);
+	if (unlikely(!done_frames))
+		return 0;
+
+	xdp_frame_bulk_init(&bq);
+
+	for (u32 i = 0; likely(i < done_frames); i++) {
+		libeth_xdp_complete_tx(&xdpsq->tx_buf[tx_ntc], &cp);
+
+		if (unlikely(++tx_ntc == tx_cnt))
+			tx_ntc = 0;
+	}
+
+	xdp_flush_frame_bulk(&bq);
+
+	xdpsq->next_to_clean = tx_ntc;
+	xdpsq->pending -= done_frames;
+	xdpsq->xdp_tx -= cp.xdp_tx;
+
+	return done_frames;
+}
+
+static u32 idpf_xdp_tx_prep(void *_xdpsq, struct libeth_xdpsq *sq)
+{
+	struct idpf_tx_queue *xdpsq = _xdpsq;
+	u32 free;
+
+	libeth_xdpsq_lock(&xdpsq->xdp_lock);
+
+	free = xdpsq->desc_count - xdpsq->pending;
+	if (free < xdpsq->thresh)
+		free += idpf_xdpsq_complete(xdpsq, xdpsq->thresh);
+
+	*sq = (struct libeth_xdpsq){
+		.sqes		= xdpsq->tx_buf,
+		.descs		= xdpsq->desc_ring,
+		.count		= xdpsq->desc_count,
+		.lock		= &xdpsq->xdp_lock,
+		.ntu		= &xdpsq->next_to_use,
+		.pending	= &xdpsq->pending,
+		.xdp_tx		= &xdpsq->xdp_tx,
+	};
+
+	return free;
+}
+
+LIBETH_XDP_DEFINE_START();
+LIBETH_XDP_DEFINE_TIMER(static idpf_xdp_tx_timer, idpf_xdpsq_complete);
+LIBETH_XDP_DEFINE_FLUSH_TX(idpf_xdp_tx_flush_bulk, idpf_xdp_tx_prep,
+			   idpf_xdp_tx_xmit);
+LIBETH_XDP_DEFINE_FLUSH_XMIT(static idpf_xdp_xmit_flush_bulk, idpf_xdp_tx_prep,
+			     idpf_xdp_tx_xmit);
+LIBETH_XDP_DEFINE_END();
+
+int idpf_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
+		  u32 flags)
+{
+	const struct idpf_netdev_priv *np = netdev_priv(dev);
+	const struct idpf_vport *vport = np->vport;
+
+	if (unlikely(!netif_carrier_ok(dev) || !vport->link_up))
+		return -ENETDOWN;
+
+	return libeth_xdp_xmit_do_bulk(dev, n, frames, flags,
+				       &vport->txqs[vport->xdp_txq_offset],
+				       vport->num_xdp_txq,
+				       idpf_xdp_xmit_flush_bulk,
+				       idpf_xdp_tx_finalize);
+}
+
+static int idpf_xdpmo_rx_hash(const struct xdp_md *ctx, u32 *hash,
+			      enum xdp_rss_hash_type *rss_type)
+{
+	const struct libeth_xdp_buff *xdp = (typeof(xdp))ctx;
+	struct idpf_xdp_rx_desc desc __uninitialized;
+	const struct idpf_rx_queue *rxq;
+	struct libeth_rx_pt pt;
+
+	rxq = libeth_xdp_buff_to_rq(xdp, typeof(*rxq), xdp_rxq);
+
+	idpf_xdp_get_qw0(&desc, xdp->desc);
+
+	pt = rxq->rx_ptype_lkup[idpf_xdp_rx_pt(&desc)];
+	if (!libeth_rx_pt_has_hash(rxq->xdp_rxq.dev, pt))
+		return -ENODATA;
+
+	idpf_xdp_get_qw2(&desc, xdp->desc);
+
+	return libeth_xdpmo_rx_hash(hash, rss_type, idpf_xdp_rx_hash(&desc),
+				    pt);
+}
+
+static const struct xdp_metadata_ops idpf_xdpmo = {
+	.xmo_rx_hash		= idpf_xdpmo_rx_hash,
+};
+
+void idpf_xdp_set_features(const struct idpf_vport *vport)
+{
+	if (!idpf_is_queue_model_split(vport->rxq_model))
+		return;
+
+	libeth_xdp_set_features_noredir(vport->netdev, &idpf_xdpmo,
+					idpf_get_max_tx_bufs(vport->adapter),
+					libeth_xsktmo);
+}
+
+static int idpf_xdp_setup_prog(struct idpf_vport *vport,
+			       const struct netdev_bpf *xdp)
+{
+	const struct idpf_netdev_priv *np = netdev_priv(vport->netdev);
+	struct bpf_prog *old, *prog = xdp->prog;
+	struct idpf_vport_config *cfg;
+	int ret;
+
+	cfg = vport->adapter->vport_config[vport->idx];
+
+	if (test_bit(IDPF_REMOVE_IN_PROG, vport->adapter->flags) ||
+	    !test_bit(IDPF_VPORT_REG_NETDEV, cfg->flags) ||
+	    !!vport->xdp_prog == !!prog) {
+		if (test_bit(IDPF_VPORT_UP, np->state))
+			idpf_xdp_copy_prog_to_rqs(vport, prog);
+
+		old = xchg(&vport->xdp_prog, prog);
+		if (old)
+			bpf_prog_put(old);
+
+		cfg->user_config.xdp_prog = prog;
+
+		return 0;
+	}
+
+	if (!vport->num_xdp_txq && vport->num_txq == cfg->max_q.max_txq) {
+		NL_SET_ERR_MSG_MOD(xdp->extack,
+				   "No Tx queues available for XDP, please decrease the number of regular SQs");
+		return -ENOSPC;
+	}
+
+	old = cfg->user_config.xdp_prog;
+	cfg->user_config.xdp_prog = prog;
+
+	ret = idpf_initiate_soft_reset(vport, IDPF_SR_Q_CHANGE);
+	if (ret) {
+		NL_SET_ERR_MSG_MOD(xdp->extack,
+				   "Could not reopen the vport after XDP setup");
+
+		cfg->user_config.xdp_prog = old;
+		old = prog;
+	}
+
+	if (old)
+		bpf_prog_put(old);
+
+	libeth_xdp_set_redirect(vport->netdev, vport->xdp_prog);
+
+	return ret;
+}
+
+int idpf_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+	struct idpf_vport *vport;
+	int ret;
+
+	idpf_vport_ctrl_lock(dev);
+	vport = idpf_netdev_to_vport(dev);
+
+	if (!idpf_is_queue_model_split(vport->txq_model))
+		goto notsupp;
+
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		ret = idpf_xdp_setup_prog(vport, xdp);
+		break;
+	case XDP_SETUP_XSK_POOL:
+		ret = idpf_xsk_pool_setup(vport, xdp);
+		break;
+	default:
+notsupp:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	idpf_vport_ctrl_unlock(dev);
+
+	return ret;
+}
diff --git a/drivers/net/ethernet/intel/idpf/xdp.h b/drivers/net/ethernet/intel/idpf/xdp.h
new file mode 100644
index 000000000000..479f5ef3c604
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/xdp.h
@@ -0,0 +1,175 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2025 Intel Corporation */
+
+#ifndef _IDPF_XDP_H_
+#define _IDPF_XDP_H_
+
+#include <net/libeth/xdp.h>
+
+#include "idpf_txrx.h"
+
+int idpf_xdp_rxq_info_init(struct idpf_rx_queue *rxq);
+int idpf_xdp_rxq_info_init_all(const struct idpf_vport *vport);
+void idpf_xdp_rxq_info_deinit(struct idpf_rx_queue *rxq, u32 model);
+void idpf_xdp_rxq_info_deinit_all(const struct idpf_vport *vport);
+void idpf_xdp_copy_prog_to_rqs(const struct idpf_vport *vport,
+			       struct bpf_prog *xdp_prog);
+
+int idpf_xdpsqs_get(const struct idpf_vport *vport);
+void idpf_xdpsqs_put(const struct idpf_vport *vport);
+
+u32 idpf_xdpsq_poll(struct idpf_tx_queue *xdpsq, u32 budget);
+bool idpf_xdp_tx_flush_bulk(struct libeth_xdp_tx_bulk *bq, u32 flags);
+
+/**
+ * idpf_xdp_tx_xmit - produce a single HW Tx descriptor out of XDP desc
+ * @desc: XDP descriptor to pull the DMA address and length from
+ * @i: descriptor index on the queue to fill
+ * @sq: XDP queue to produce the HW Tx descriptor on
+ * @priv: &xsk_tx_metadata_ops on XSk xmit or %NULL
+ */
+static inline void idpf_xdp_tx_xmit(struct libeth_xdp_tx_desc desc, u32 i,
+				    const struct libeth_xdpsq *sq, u64 priv)
+{
+	struct idpf_flex_tx_desc *tx_desc = sq->descs;
+	u32 cmd;
+
+	cmd = FIELD_PREP(IDPF_FLEX_TXD_QW1_DTYPE_M,
+			 IDPF_TX_DESC_DTYPE_FLEX_L2TAG1_L2TAG2);
+	if (desc.flags & LIBETH_XDP_TX_LAST)
+		cmd |= FIELD_PREP(IDPF_FLEX_TXD_QW1_CMD_M,
+				  IDPF_TX_DESC_CMD_EOP);
+	if (priv && (desc.flags & LIBETH_XDP_TX_CSUM))
+		cmd |= FIELD_PREP(IDPF_FLEX_TXD_QW1_CMD_M,
+				  IDPF_TX_FLEX_DESC_CMD_CS_EN);
+
+	tx_desc = &tx_desc[i];
+	tx_desc->buf_addr = cpu_to_le64(desc.addr);
+#ifdef __LIBETH_WORD_ACCESS
+	*(u64 *)&tx_desc->qw1 = ((u64)desc.len << 48) | cmd;
+#else
+	tx_desc->qw1.buf_size = cpu_to_le16(desc.len);
+	tx_desc->qw1.cmd_dtype = cpu_to_le16(cmd);
+#endif
+}
+
+static inline void idpf_xdpsq_set_rs(const struct idpf_tx_queue *xdpsq)
+{
+	u32 ntu, cmd;
+
+	ntu = xdpsq->next_to_use;
+	if (unlikely(!ntu))
+		ntu = xdpsq->desc_count;
+
+	cmd = FIELD_PREP(IDPF_FLEX_TXD_QW1_CMD_M, IDPF_TX_DESC_CMD_RS);
+#ifdef __LIBETH_WORD_ACCESS
+	*(u64 *)&xdpsq->flex_tx[ntu - 1].q.qw1 |= cmd;
+#else
+	xdpsq->flex_tx[ntu - 1].q.qw1.cmd_dtype |= cpu_to_le16(cmd);
+#endif
+}
+
+static inline void idpf_xdpsq_update_tail(const struct idpf_tx_queue *xdpsq)
+{
+	dma_wmb();
+	writel_relaxed(xdpsq->next_to_use, xdpsq->tail);
+}
+
+/**
+ * idpf_xdp_tx_finalize - finalize sending over XDPSQ
+ * @_xdpsq: XDP Tx queue
+ * @sent: whether any frames were sent
+ * @flush: whether to update RS bit and the tail register
+ *
+ * Set the RS bit ("end of batch"), bump the tail, and queue the cleanup timer.
+ * To be called after a NAPI polling loop, at the end of .ndo_xdp_xmit() etc.
+ */
+static inline void idpf_xdp_tx_finalize(void *_xdpsq, bool sent, bool flush)
+{
+	struct idpf_tx_queue *xdpsq = _xdpsq;
+
+	if ((!flush || unlikely(!sent)) &&
+	    likely(xdpsq->desc_count - 1 != xdpsq->pending))
+		return;
+
+	libeth_xdpsq_lock(&xdpsq->xdp_lock);
+
+	idpf_xdpsq_set_rs(xdpsq);
+	idpf_xdpsq_update_tail(xdpsq);
+
+	libeth_xdpsq_queue_timer(xdpsq->timer);
+
+	libeth_xdpsq_unlock(&xdpsq->xdp_lock);
+}
+
+struct idpf_xdp_rx_desc {
+	aligned_u64		qw0;
+#define IDPF_XDP_RX_BUFQ	BIT_ULL(47)
+#define IDPF_XDP_RX_GEN		BIT_ULL(46)
+#define IDPF_XDP_RX_LEN		GENMASK_ULL(45, 32)
+#define IDPF_XDP_RX_PT		GENMASK_ULL(25, 16)
+
+	aligned_u64		qw1;
+#define IDPF_XDP_RX_BUF		GENMASK_ULL(47, 32)
+#define IDPF_XDP_RX_EOP		BIT_ULL(1)
+
+	aligned_u64		qw2;
+#define IDPF_XDP_RX_HASH	GENMASK_ULL(31, 0)
+
+	aligned_u64		qw3;
+} __aligned(4 * sizeof(u64));
+static_assert(sizeof(struct idpf_xdp_rx_desc) ==
+	      sizeof(struct virtchnl2_rx_flex_desc_adv_nic_3));
+
+#define idpf_xdp_rx_bufq(desc)	!!((desc)->qw0 & IDPF_XDP_RX_BUFQ)
+#define idpf_xdp_rx_gen(desc)	!!((desc)->qw0 & IDPF_XDP_RX_GEN)
+#define idpf_xdp_rx_len(desc)	FIELD_GET(IDPF_XDP_RX_LEN, (desc)->qw0)
+#define idpf_xdp_rx_pt(desc)	FIELD_GET(IDPF_XDP_RX_PT, (desc)->qw0)
+#define idpf_xdp_rx_buf(desc)	FIELD_GET(IDPF_XDP_RX_BUF, (desc)->qw1)
+#define idpf_xdp_rx_eop(desc)	!!((desc)->qw1 & IDPF_XDP_RX_EOP)
+#define idpf_xdp_rx_hash(desc)	FIELD_GET(IDPF_XDP_RX_HASH, (desc)->qw2)
+
+static inline void
+idpf_xdp_get_qw0(struct idpf_xdp_rx_desc *desc,
+		 const struct virtchnl2_rx_flex_desc_adv_nic_3 *rxd)
+{
+#ifdef __LIBETH_WORD_ACCESS
+	desc->qw0 = ((const typeof(desc))rxd)->qw0;
+#else
+	desc->qw0 = ((u64)le16_to_cpu(rxd->pktlen_gen_bufq_id) << 32) |
+		    ((u64)le16_to_cpu(rxd->ptype_err_fflags0) << 16);
+#endif
+}
+
+static inline void
+idpf_xdp_get_qw1(struct idpf_xdp_rx_desc *desc,
+		 const struct virtchnl2_rx_flex_desc_adv_nic_3 *rxd)
+{
+#ifdef __LIBETH_WORD_ACCESS
+	desc->qw1 = ((const typeof(desc))rxd)->qw1;
+#else
+	desc->qw1 = ((u64)le16_to_cpu(rxd->buf_id) << 32) |
+		    rxd->status_err0_qw1;
+#endif
+}
+
+static inline void
+idpf_xdp_get_qw2(struct idpf_xdp_rx_desc *desc,
+		 const struct virtchnl2_rx_flex_desc_adv_nic_3 *rxd)
+{
+#ifdef __LIBETH_WORD_ACCESS
+	desc->qw2 = ((const typeof(desc))rxd)->qw2;
+#else
+	desc->qw2 = ((u64)rxd->hash3 << 24) |
+		    ((u64)rxd->ff2_mirrid_hash2.hash2 << 16) |
+		    le16_to_cpu(rxd->hash1);
+#endif
+}
+
+void idpf_xdp_set_features(const struct idpf_vport *vport);
+
+int idpf_xdp(struct net_device *dev, struct netdev_bpf *xdp);
+int idpf_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
+		  u32 flags);
+
+#endif /* _IDPF_XDP_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/xsk.c b/drivers/net/ethernet/intel/idpf/xsk.c
new file mode 100644
index 000000000000..fd2cc43ab43c
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/xsk.c
@@ -0,0 +1,633 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2025 Intel Corporation */
+
+#include <net/libeth/xsk.h>
+
+#include "idpf.h"
+#include "xdp.h"
+#include "xsk.h"
+
+static void idpf_xsk_tx_timer(struct work_struct *work);
+
+static void idpf_xsk_setup_rxq(const struct idpf_vport *vport,
+			       struct idpf_rx_queue *rxq)
+{
+	struct xsk_buff_pool *pool;
+
+	pool = xsk_get_pool_from_qid(vport->netdev, rxq->idx);
+	if (!pool || !pool->dev || !xsk_buff_can_alloc(pool, 1))
+		return;
+
+	rxq->pool = pool;
+
+	idpf_queue_set(XSK, rxq);
+}
+
+static void idpf_xsk_setup_bufq(const struct idpf_vport *vport,
+				struct idpf_buf_queue *bufq)
+{
+	struct xsk_buff_pool *pool;
+	u32 qid = U32_MAX;
+
+	for (u32 i = 0; i < vport->num_rxq_grp; i++) {
+		const struct idpf_rxq_group *grp = &vport->rxq_grps[i];
+
+		for (u32 j = 0; j < vport->num_bufqs_per_qgrp; j++) {
+			if (&grp->splitq.bufq_sets[j].bufq == bufq) {
+				qid = grp->splitq.rxq_sets[0]->rxq.idx;
+				goto setup;
+			}
+		}
+	}
+
+setup:
+	pool = xsk_get_pool_from_qid(vport->netdev, qid);
+	if (!pool || !pool->dev || !xsk_buff_can_alloc(pool, 1))
+		return;
+
+	bufq->pool = pool;
+
+	idpf_queue_set(XSK, bufq);
+}
+
+static void idpf_xsk_setup_txq(const struct idpf_vport *vport,
+			       struct idpf_tx_queue *txq)
+{
+	struct xsk_buff_pool *pool;
+	u32 qid;
+
+	idpf_queue_clear(XSK, txq);
+
+	if (!idpf_queue_has(XDP, txq))
+		return;
+
+	qid = txq->idx - vport->xdp_txq_offset;
+
+	pool = xsk_get_pool_from_qid(vport->netdev, qid);
+	if (!pool || !pool->dev)
+		return;
+
+	txq->pool = pool;
+	libeth_xdpsq_init_timer(txq->timer, txq, &txq->xdp_lock,
+				idpf_xsk_tx_timer);
+
+	idpf_queue_assign(NOIRQ, txq, xsk_uses_need_wakeup(pool));
+	idpf_queue_set(XSK, txq);
+}
+
+static void idpf_xsk_setup_complq(const struct idpf_vport *vport,
+				  struct idpf_compl_queue *complq)
+{
+	const struct xsk_buff_pool *pool;
+	u32 qid;
+
+	idpf_queue_clear(XSK, complq);
+
+	if (!idpf_queue_has(XDP, complq))
+		return;
+
+	qid = complq->txq_grp->txqs[0]->idx - vport->xdp_txq_offset;
+
+	pool = xsk_get_pool_from_qid(vport->netdev, qid);
+	if (!pool || !pool->dev)
+		return;
+
+	idpf_queue_set(XSK, complq);
+}
+
+void idpf_xsk_setup_queue(const struct idpf_vport *vport, void *q,
+			  enum virtchnl2_queue_type type)
+{
+	if (!idpf_xdp_enabled(vport))
+		return;
+
+	switch (type) {
+	case VIRTCHNL2_QUEUE_TYPE_RX:
+		idpf_xsk_setup_rxq(vport, q);
+		break;
+	case VIRTCHNL2_QUEUE_TYPE_RX_BUFFER:
+		idpf_xsk_setup_bufq(vport, q);
+		break;
+	case VIRTCHNL2_QUEUE_TYPE_TX:
+		idpf_xsk_setup_txq(vport, q);
+		break;
+	case VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION:
+		idpf_xsk_setup_complq(vport, q);
+		break;
+	default:
+		break;
+	}
+}
+
+void idpf_xsk_clear_queue(void *q, enum virtchnl2_queue_type type)
+{
+	struct idpf_compl_queue *complq;
+	struct idpf_buf_queue *bufq;
+	struct idpf_rx_queue *rxq;
+	struct idpf_tx_queue *txq;
+
+	switch (type) {
+	case VIRTCHNL2_QUEUE_TYPE_RX:
+		rxq = q;
+		if (!idpf_queue_has_clear(XSK, rxq))
+			return;
+
+		rxq->pool = NULL;
+		break;
+	case VIRTCHNL2_QUEUE_TYPE_RX_BUFFER:
+		bufq = q;
+		if (!idpf_queue_has_clear(XSK, bufq))
+			return;
+
+		bufq->pool = NULL;
+		break;
+	case VIRTCHNL2_QUEUE_TYPE_TX:
+		txq = q;
+		if (!idpf_queue_has_clear(XSK, txq))
+			return;
+
+		idpf_queue_set(NOIRQ, txq);
+		txq->dev = txq->netdev->dev.parent;
+		break;
+	case VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION:
+		complq = q;
+		idpf_queue_clear(XSK, complq);
+		break;
+	default:
+		break;
+	}
+}
+
+void idpf_xsk_init_wakeup(struct idpf_q_vector *qv)
+{
+	libeth_xsk_init_wakeup(&qv->csd, &qv->napi);
+}
+
+void idpf_xsksq_clean(struct idpf_tx_queue *xdpsq)
+{
+	struct libeth_xdpsq_napi_stats ss = { };
+	u32 ntc = xdpsq->next_to_clean;
+	struct xdp_frame_bulk bq;
+	struct libeth_cq_pp cp = {
+		.dev	= xdpsq->pool->dev,
+		.bq	= &bq,
+		.xss	= &ss,
+	};
+	u32 xsk_frames = 0;
+
+	xdp_frame_bulk_init(&bq);
+
+	while (ntc != xdpsq->next_to_use) {
+		struct libeth_sqe *sqe = &xdpsq->tx_buf[ntc];
+
+		if (sqe->type)
+			libeth_xdp_complete_tx(sqe, &cp);
+		else
+			xsk_frames++;
+
+		if (unlikely(++ntc == xdpsq->desc_count))
+			ntc = 0;
+	}
+
+	xdp_flush_frame_bulk(&bq);
+
+	if (xsk_frames)
+		xsk_tx_completed(xdpsq->pool, xsk_frames);
+}
+
+static noinline u32 idpf_xsksq_complete_slow(struct idpf_tx_queue *xdpsq,
+					     u32 done)
+{
+	struct libeth_xdpsq_napi_stats ss = { };
+	u32 ntc = xdpsq->next_to_clean;
+	u32 cnt = xdpsq->desc_count;
+	struct xdp_frame_bulk bq;
+	struct libeth_cq_pp cp = {
+		.dev	= xdpsq->pool->dev,
+		.bq	= &bq,
+		.xss	= &ss,
+		.napi	= true,
+	};
+	u32 xsk_frames = 0;
+
+	xdp_frame_bulk_init(&bq);
+
+	for (u32 i = 0; likely(i < done); i++) {
+		struct libeth_sqe *sqe = &xdpsq->tx_buf[ntc];
+
+		if (sqe->type)
+			libeth_xdp_complete_tx(sqe, &cp);
+		else
+			xsk_frames++;
+
+		if (unlikely(++ntc == cnt))
+			ntc = 0;
+	}
+
+	xdp_flush_frame_bulk(&bq);
+
+	xdpsq->next_to_clean = ntc;
+	xdpsq->xdp_tx -= cp.xdp_tx;
+
+	return xsk_frames;
+}
+
+static __always_inline u32 idpf_xsksq_complete(void *_xdpsq, u32 budget)
+{
+	struct idpf_tx_queue *xdpsq = _xdpsq;
+	u32 tx_ntc = xdpsq->next_to_clean;
+	u32 tx_cnt = xdpsq->desc_count;
+	u32 done_frames;
+	u32 xsk_frames;
+
+	done_frames = idpf_xdpsq_poll(xdpsq, budget);
+	if (unlikely(!done_frames))
+		return 0;
+
+	if (likely(!xdpsq->xdp_tx)) {
+		tx_ntc += done_frames;
+		if (tx_ntc >= tx_cnt)
+			tx_ntc -= tx_cnt;
+
+		xdpsq->next_to_clean = tx_ntc;
+		xsk_frames = done_frames;
+
+		goto finalize;
+	}
+
+	xsk_frames = idpf_xsksq_complete_slow(xdpsq, done_frames);
+	if (xsk_frames)
+finalize:
+		xsk_tx_completed(xdpsq->pool, xsk_frames);
+
+	xdpsq->pending -= done_frames;
+
+	return done_frames;
+}
+
+static u32 idpf_xsk_tx_prep(void *_xdpsq, struct libeth_xdpsq *sq)
+{
+	struct idpf_tx_queue *xdpsq = _xdpsq;
+	u32 free;
+
+	libeth_xdpsq_lock(&xdpsq->xdp_lock);
+
+	free = xdpsq->desc_count - xdpsq->pending;
+	if (free < xdpsq->thresh)
+		free += idpf_xsksq_complete(xdpsq, xdpsq->thresh);
+
+	*sq = (struct libeth_xdpsq){
+		.pool		= xdpsq->pool,
+		.sqes		= xdpsq->tx_buf,
+		.descs		= xdpsq->desc_ring,
+		.count		= xdpsq->desc_count,
+		.lock		= &xdpsq->xdp_lock,
+		.ntu		= &xdpsq->next_to_use,
+		.pending	= &xdpsq->pending,
+		.xdp_tx		= &xdpsq->xdp_tx,
+	};
+
+	return free;
+}
+
+static u32 idpf_xsk_xmit_prep(void *_xdpsq, struct libeth_xdpsq *sq)
+{
+	struct idpf_tx_queue *xdpsq = _xdpsq;
+
+	*sq = (struct libeth_xdpsq){
+		.pool		= xdpsq->pool,
+		.sqes		= xdpsq->tx_buf,
+		.descs		= xdpsq->desc_ring,
+		.count		= xdpsq->desc_count,
+		.lock		= &xdpsq->xdp_lock,
+		.ntu		= &xdpsq->next_to_use,
+		.pending	= &xdpsq->pending,
+	};
+
+	/*
+	 * The queue is cleaned, the budget is already known, optimize out
+	 * the second min() by passing the type limit.
+	 */
+	return U32_MAX;
+}
+
+bool idpf_xsk_xmit(struct idpf_tx_queue *xsksq)
+{
+	u32 free;
+
+	libeth_xdpsq_lock(&xsksq->xdp_lock);
+
+	free = xsksq->desc_count - xsksq->pending;
+	if (free < xsksq->thresh)
+		free += idpf_xsksq_complete(xsksq, xsksq->thresh);
+
+	return libeth_xsk_xmit_do_bulk(xsksq->pool, xsksq,
+				       min(free - 1, xsksq->thresh),
+				       libeth_xsktmo, idpf_xsk_xmit_prep,
+				       idpf_xdp_tx_xmit, idpf_xdp_tx_finalize);
+}
+
+LIBETH_XDP_DEFINE_START();
+LIBETH_XDP_DEFINE_TIMER(static idpf_xsk_tx_timer, idpf_xsksq_complete);
+LIBETH_XSK_DEFINE_FLUSH_TX(static idpf_xsk_tx_flush_bulk, idpf_xsk_tx_prep,
+			   idpf_xdp_tx_xmit);
+LIBETH_XSK_DEFINE_RUN(static idpf_xsk_run_pass, idpf_xsk_run_prog,
+		      idpf_xsk_tx_flush_bulk, idpf_rx_process_skb_fields);
+LIBETH_XSK_DEFINE_FINALIZE(static idpf_xsk_finalize_rx, idpf_xsk_tx_flush_bulk,
+			   idpf_xdp_tx_finalize);
+LIBETH_XDP_DEFINE_END();
+
+static void idpf_xskfqe_init(const struct libeth_xskfq_fp *fq, u32 i)
+{
+	struct virtchnl2_splitq_rx_buf_desc *desc = fq->descs;
+
+	desc = &desc[i];
+#ifdef __LIBETH_WORD_ACCESS
+	*(u64 *)&desc->qword0 = i;
+#else
+	desc->qword0.buf_id = cpu_to_le16(i);
+#endif
+	desc->pkt_addr = cpu_to_le64(libeth_xsk_buff_xdp_get_dma(fq->fqes[i]));
+}
+
+static bool idpf_xskfq_refill_thresh(struct idpf_buf_queue *bufq, u32 count)
+{
+	struct libeth_xskfq_fp fq = {
+		.pool	= bufq->pool,
+		.fqes	= bufq->xsk_buf,
+		.descs	= bufq->split_buf,
+		.ntu	= bufq->next_to_use,
+		.count	= bufq->desc_count,
+	};
+	u32 done;
+
+	done = libeth_xskfqe_alloc(&fq, count, idpf_xskfqe_init);
+	writel(fq.ntu, bufq->tail);
+
+	bufq->next_to_use = fq.ntu;
+	bufq->pending -= done;
+
+	return done == count;
+}
+
+static bool idpf_xskfq_refill(struct idpf_buf_queue *bufq)
+{
+	u32 count, rx_thresh = bufq->thresh;
+
+	count = ALIGN_DOWN(bufq->pending - 1, rx_thresh);
+
+	for (u32 i = 0; i < count; i += rx_thresh) {
+		if (unlikely(!idpf_xskfq_refill_thresh(bufq, rx_thresh)))
+			return false;
+	}
+
+	return true;
+}
+
+int idpf_xskfq_init(struct idpf_buf_queue *bufq)
+{
+	struct libeth_xskfq fq = {
+		.pool	= bufq->pool,
+		.count	= bufq->desc_count,
+		.nid	= idpf_q_vector_to_mem(bufq->q_vector),
+	};
+	int ret;
+
+	ret = libeth_xskfq_create(&fq);
+	if (ret)
+		return ret;
+
+	bufq->xsk_buf = fq.fqes;
+	bufq->pending = fq.pending;
+	bufq->thresh = fq.thresh;
+	bufq->rx_buf_size = fq.buf_len;
+
+	if (!idpf_xskfq_refill(bufq))
+		netdev_err(bufq->pool->netdev,
+			   "failed to allocate XSk buffers for qid %d\n",
+			   bufq->pool->queue_id);
+
+	bufq->next_to_alloc = bufq->next_to_use;
+
+	idpf_queue_clear(HSPLIT_EN, bufq);
+	bufq->rx_hbuf_size = 0;
+
+	return 0;
+}
+
+void idpf_xskfq_rel(struct idpf_buf_queue *bufq)
+{
+	struct libeth_xskfq fq = {
+		.fqes	= bufq->xsk_buf,
+	};
+
+	libeth_xskfq_destroy(&fq);
+
+	bufq->rx_buf_size = fq.buf_len;
+	bufq->thresh = fq.thresh;
+	bufq->pending = fq.pending;
+}
+
+struct idpf_xskfq_refill_set {
+	struct {
+		struct idpf_buf_queue	*q;
+		u32			buf_id;
+		u32			pending;
+	} bufqs[IDPF_MAX_BUFQS_PER_RXQ_GRP];
+};
+
+static bool idpf_xskfq_refill_set(const struct idpf_xskfq_refill_set *set)
+{
+	bool ret = true;
+
+	for (u32 i = 0; i < ARRAY_SIZE(set->bufqs); i++) {
+		struct idpf_buf_queue *bufq = set->bufqs[i].q;
+		u32 ntc;
+
+		if (!bufq)
+			continue;
+
+		ntc = set->bufqs[i].buf_id;
+		if (unlikely(++ntc == bufq->desc_count))
+			ntc = 0;
+
+		bufq->next_to_clean = ntc;
+		bufq->pending += set->bufqs[i].pending;
+
+		if (bufq->pending > bufq->thresh)
+			ret &= idpf_xskfq_refill(bufq);
+	}
+
+	return ret;
+}
+
+int idpf_xskrq_poll(struct idpf_rx_queue *rxq, u32 budget)
+{
+	struct idpf_xskfq_refill_set set = { };
+	struct libeth_rq_napi_stats rs = { };
+	bool wake, gen, fail = false;
+	u32 ntc = rxq->next_to_clean;
+	struct libeth_xdp_buff *xdp;
+	LIBETH_XDP_ONSTACK_BULK(bq);
+	u32 cnt = rxq->desc_count;
+
+	wake = xsk_uses_need_wakeup(rxq->pool);
+	if (wake)
+		xsk_clear_rx_need_wakeup(rxq->pool);
+
+	gen = idpf_queue_has(GEN_CHK, rxq);
+
+	libeth_xsk_tx_init_bulk(&bq, rxq->xdp_prog, rxq->xdp_rxq.dev,
+				rxq->xdpsqs, rxq->num_xdp_txq);
+	xdp = rxq->xsk;
+
+	while (likely(rs.packets < budget)) {
+		const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc;
+		struct idpf_xdp_rx_desc desc __uninitialized;
+		struct idpf_buf_queue *bufq;
+		u32 bufq_id, buf_id;
+
+		rx_desc = &rxq->rx[ntc].flex_adv_nic_3_wb;
+
+		idpf_xdp_get_qw0(&desc, rx_desc);
+		if (idpf_xdp_rx_gen(&desc) != gen)
+			break;
+
+		dma_rmb();
+
+		bufq_id = idpf_xdp_rx_bufq(&desc);
+		bufq = set.bufqs[bufq_id].q;
+		if (!bufq) {
+			bufq = &rxq->bufq_sets[bufq_id].bufq;
+			set.bufqs[bufq_id].q = bufq;
+		}
+
+		idpf_xdp_get_qw1(&desc, rx_desc);
+		buf_id = idpf_xdp_rx_buf(&desc);
+
+		set.bufqs[bufq_id].buf_id = buf_id;
+		set.bufqs[bufq_id].pending++;
+
+		xdp = libeth_xsk_process_buff(xdp, bufq->xsk_buf[buf_id],
+					      idpf_xdp_rx_len(&desc));
+
+		if (unlikely(++ntc == cnt)) {
+			ntc = 0;
+			gen = !gen;
+			idpf_queue_change(GEN_CHK, rxq);
+		}
+
+		if (!idpf_xdp_rx_eop(&desc) || unlikely(!xdp))
+			continue;
+
+		fail = !idpf_xsk_run_pass(xdp, &bq, rxq->napi, &rs, rx_desc);
+		xdp = NULL;
+
+		if (fail)
+			break;
+	}
+
+	idpf_xsk_finalize_rx(&bq);
+
+	rxq->next_to_clean = ntc;
+	rxq->xsk = xdp;
+
+	fail |= !idpf_xskfq_refill_set(&set);
+
+	u64_stats_update_begin(&rxq->stats_sync);
+	u64_stats_add(&rxq->q_stats.packets, rs.packets);
+	u64_stats_add(&rxq->q_stats.bytes, rs.bytes);
+	u64_stats_update_end(&rxq->stats_sync);
+
+	if (!wake)
+		return unlikely(fail) ? budget : rs.packets;
+
+	if (unlikely(fail))
+		xsk_set_rx_need_wakeup(rxq->pool);
+
+	return rs.packets;
+}
+
+int idpf_xsk_pool_setup(struct idpf_vport *vport, struct netdev_bpf *bpf)
+{
+	struct xsk_buff_pool *pool = bpf->xsk.pool;
+	u32 qid = bpf->xsk.queue_id;
+	bool restart;
+	int ret;
+
+	if (pool && !IS_ALIGNED(xsk_pool_get_rx_frame_size(pool),
+				LIBETH_RX_BUF_STRIDE)) {
+		NL_SET_ERR_MSG_FMT_MOD(bpf->extack,
+				       "%s: HW doesn't support frames sizes not aligned to %u (qid %u: %u)",
+				       netdev_name(vport->netdev),
+				       LIBETH_RX_BUF_STRIDE, qid,
+				       xsk_pool_get_rx_frame_size(pool));
+		return -EINVAL;
+	}
+
+	restart = idpf_xdp_enabled(vport) && netif_running(vport->netdev);
+	if (!restart)
+		goto pool;
+
+	ret = idpf_qp_switch(vport, qid, false);
+	if (ret) {
+		NL_SET_ERR_MSG_FMT_MOD(bpf->extack,
+				       "%s: failed to disable queue pair %u: %pe",
+				       netdev_name(vport->netdev), qid,
+				       ERR_PTR(ret));
+		return ret;
+	}
+
+pool:
+	ret = libeth_xsk_setup_pool(vport->netdev, qid, pool);
+	if (ret) {
+		NL_SET_ERR_MSG_FMT_MOD(bpf->extack,
+				       "%s: failed to configure XSk pool for pair %u: %pe",
+				       netdev_name(vport->netdev), qid,
+				       ERR_PTR(ret));
+		return ret;
+	}
+
+	if (!restart)
+		return 0;
+
+	ret = idpf_qp_switch(vport, qid, true);
+	if (ret) {
+		NL_SET_ERR_MSG_FMT_MOD(bpf->extack,
+				       "%s: failed to enable queue pair %u: %pe",
+				       netdev_name(vport->netdev), qid,
+				       ERR_PTR(ret));
+		goto err_dis;
+	}
+
+	return 0;
+
+err_dis:
+	libeth_xsk_setup_pool(vport->netdev, qid, false);
+
+	return ret;
+}
+
+int idpf_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
+{
+	const struct idpf_netdev_priv *np = netdev_priv(dev);
+	const struct idpf_vport *vport = np->vport;
+	struct idpf_q_vector *q_vector;
+
+	if (unlikely(idpf_vport_ctrl_is_locked(dev)))
+		return -EBUSY;
+
+	if (unlikely(!vport->link_up))
+		return -ENETDOWN;
+
+	if (unlikely(!vport->num_xdp_txq))
+		return -ENXIO;
+
+	q_vector = idpf_find_rxq_vec(vport, qid);
+	if (unlikely(!q_vector->xsksq))
+		return -ENXIO;
+
+	libeth_xsk_wakeup(&q_vector->csd, qid);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/idpf/xsk.h b/drivers/net/ethernet/intel/idpf/xsk.h
new file mode 100644
index 000000000000..b622d08c03e8
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/xsk.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2025 Intel Corporation */
+
+#ifndef _IDPF_XSK_H_
+#define _IDPF_XSK_H_
+
+#include <linux/types.h>
+
+enum virtchnl2_queue_type;
+struct idpf_buf_queue;
+struct idpf_q_vector;
+struct idpf_rx_queue;
+struct idpf_tx_queue;
+struct idpf_vport;
+struct net_device;
+struct netdev_bpf;
+
+void idpf_xsk_setup_queue(const struct idpf_vport *vport, void *q,
+			  enum virtchnl2_queue_type type);
+void idpf_xsk_clear_queue(void *q, enum virtchnl2_queue_type type);
+void idpf_xsk_init_wakeup(struct idpf_q_vector *qv);
+
+int idpf_xskfq_init(struct idpf_buf_queue *bufq);
+void idpf_xskfq_rel(struct idpf_buf_queue *bufq);
+void idpf_xsksq_clean(struct idpf_tx_queue *xdpq);
+
+int idpf_xskrq_poll(struct idpf_rx_queue *rxq, u32 budget);
+bool idpf_xsk_xmit(struct idpf_tx_queue *xsksq);
+
+int idpf_xsk_pool_setup(struct idpf_vport *vport, struct netdev_bpf *xdp);
+int idpf_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags);
+
+#endif /* !_IDPF_XSK_H_ */
diff --git a/drivers/net/ethernet/intel/igb/Makefile b/drivers/net/ethernet/intel/igb/Makefile
index 463c0d26b9d4..6c1b702fd992 100644
--- a/drivers/net/ethernet/intel/igb/Makefile
+++ b/drivers/net/ethernet/intel/igb/Makefile
@@ -8,4 +8,4 @@ obj-$(CONFIG_IGB) += igb.o
 
 igb-y := igb_main.o igb_ethtool.o e1000_82575.o \
 	 e1000_mac.o e1000_nvm.o e1000_phy.o e1000_mbx.o \
-	 e1000_i210.o igb_ptp.o igb_hwmon.o
+	 e1000_i210.o igb_ptp.o igb_hwmon.o igb_xsk.o
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 64dfc362d1dc..44a85ad749a4 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -2372,7 +2372,7 @@ static s32 igb_validate_nvm_checksum_with_offset(struct e1000_hw *hw,
 		checksum += nvm_data;
 	}
 
-	if (checksum != (u16) NVM_SUM) {
+	if (checksum != NVM_SUM) {
 		hw_dbg("NVM Checksum Invalid\n");
 		ret_val = -E1000_ERR_NVM;
 		goto out;
@@ -2406,7 +2406,7 @@ static s32 igb_update_nvm_checksum_with_offset(struct e1000_hw *hw, u16 offset)
 		}
 		checksum += nvm_data;
 	}
-	checksum = (u16) NVM_SUM - checksum;
+	checksum = NVM_SUM - checksum;
 	ret_val = hw->nvm.ops.write(hw, (NVM_CHECKSUM_REG + offset), 1,
 				&checksum);
 	if (ret_val)
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c
index 503b239868e8..9db29b231d6a 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.c
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.c
@@ -602,7 +602,7 @@ static s32 igb_update_nvm_checksum_i210(struct e1000_hw *hw)
 			}
 			checksum += nvm_data;
 		}
-		checksum = (u16) NVM_SUM - checksum;
+		checksum = NVM_SUM - checksum;
 		ret_val = igb_write_nvm_srwr(hw, NVM_CHECKSUM_REG, 1,
 						&checksum);
 		if (ret_val) {
diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.c b/drivers/net/ethernet/intel/igb/e1000_nvm.c
index 2dcd64d6dec3..c8638502c2be 100644
--- a/drivers/net/ethernet/intel/igb/e1000_nvm.c
+++ b/drivers/net/ethernet/intel/igb/e1000_nvm.c
@@ -636,7 +636,7 @@ s32 igb_validate_nvm_checksum(struct e1000_hw *hw)
 		checksum += nvm_data;
 	}
 
-	if (checksum != (u16) NVM_SUM) {
+	if (checksum != NVM_SUM) {
 		hw_dbg("NVM Checksum Invalid\n");
 		ret_val = -E1000_ERR_NVM;
 		goto out;
@@ -668,7 +668,7 @@ s32 igb_update_nvm_checksum(struct e1000_hw *hw)
 		}
 		checksum += nvm_data;
 	}
-	checksum = (u16) NVM_SUM - checksum;
+	checksum = NVM_SUM - checksum;
 	ret_val = hw->nvm.ops.write(hw, NVM_CHECKSUM_REG, 1, &checksum);
 	if (ret_val)
 		hw_dbg("NVM Write Error while updating checksum.\n");
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 3c2dc7bdebb5..0fff1df81b7b 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -18,8 +18,10 @@
 #include <linux/i2c-algo-bit.h>
 #include <linux/pci.h>
 #include <linux/mdio.h>
+#include <linux/lockdep.h>
 
 #include <net/xdp.h>
+#include <net/xdp_sock_drv.h>
 
 struct igb_adapter;
 
@@ -86,6 +88,7 @@ struct igb_adapter;
 #define IGB_XDP_CONSUMED	BIT(0)
 #define IGB_XDP_TX		BIT(1)
 #define IGB_XDP_REDIR		BIT(2)
+#define IGB_XDP_EXIT		BIT(3)
 
 struct vf_data_storage {
 	unsigned char vf_mac_addresses[ETH_ALEN];
@@ -214,7 +217,7 @@ static inline int igb_skb_pad(void)
 #define IGB_MASTER_SLAVE	e1000_ms_hw_default
 #endif
 
-#define IGB_MNG_VLAN_NONE	-1
+#define IGB_MNG_VLAN_NONE	0xFFFF
 
 enum igb_tx_flags {
 	/* cmd_type flags */
@@ -255,6 +258,7 @@ enum igb_tx_flags {
 enum igb_tx_buf_type {
 	IGB_TYPE_SKB = 0,
 	IGB_TYPE_XDP,
+	IGB_TYPE_XSK
 };
 
 /* wrapper around a pointer to a socket buffer,
@@ -320,6 +324,7 @@ struct igb_ring {
 	union {				/* array of buffer info structs */
 		struct igb_tx_buffer *tx_buffer_info;
 		struct igb_rx_buffer *rx_buffer_info;
+		struct xdp_buff **rx_buffer_info_zc;
 	};
 	void *desc;			/* descriptor ring memory */
 	unsigned long flags;		/* ring specific flags */
@@ -357,6 +362,7 @@ struct igb_ring {
 		};
 	};
 	struct xdp_rxq_info xdp_rxq;
+	struct xsk_buff_pool *xsk_pool;
 } ____cacheline_internodealigned_in_smp;
 
 struct igb_q_vector {
@@ -384,7 +390,9 @@ enum e1000_ring_flags_t {
 	IGB_RING_FLAG_RX_SCTP_CSUM,
 	IGB_RING_FLAG_RX_LB_VLAN_BSWAP,
 	IGB_RING_FLAG_TX_CTX_IDX,
-	IGB_RING_FLAG_TX_DETECT_HANG
+	IGB_RING_FLAG_TX_DETECT_HANG,
+	IGB_RING_FLAG_TX_DISABLED,
+	IGB_RING_FLAG_RX_ALLOC_FAILED,
 };
 
 #define ring_uses_large_buffer(ring) \
@@ -618,7 +626,7 @@ struct igb_adapter {
 	struct delayed_work ptp_overflow_work;
 	struct work_struct ptp_tx_work;
 	struct sk_buff *ptp_tx_skb;
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 	unsigned long ptp_tx_start;
 	unsigned long last_rx_ptp_check;
 	unsigned long last_rx_timestamp;
@@ -715,6 +723,8 @@ enum igb_boards {
 
 extern char igb_driver_name[];
 
+void igb_set_queue_napi(struct igb_adapter *adapter, int q_idx,
+			struct napi_struct *napi);
 int igb_xmit_xdp_ring(struct igb_adapter *adapter,
 		      struct igb_ring *ring,
 		      struct xdp_frame *xdpf);
@@ -731,12 +741,21 @@ int igb_setup_tx_resources(struct igb_ring *);
 int igb_setup_rx_resources(struct igb_ring *);
 void igb_free_tx_resources(struct igb_ring *);
 void igb_free_rx_resources(struct igb_ring *);
+void igb_clean_tx_ring(struct igb_ring *tx_ring);
+void igb_clean_rx_ring(struct igb_ring *rx_ring);
 void igb_configure_tx_ring(struct igb_adapter *, struct igb_ring *);
 void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *);
+void igb_finalize_xdp(struct igb_adapter *adapter, unsigned int status);
+void igb_update_rx_stats(struct igb_q_vector *q_vector, unsigned int packets,
+			 unsigned int bytes);
 void igb_setup_tctl(struct igb_adapter *);
 void igb_setup_rctl(struct igb_adapter *);
 void igb_setup_srrctl(struct igb_adapter *, struct igb_ring *);
 netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *);
+int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp);
+void igb_process_skb_fields(struct igb_ring *rx_ring,
+			    union e1000_adv_rx_desc *rx_desc,
+			    struct sk_buff *skb);
 void igb_alloc_rx_buffers(struct igb_ring *, u16);
 void igb_update_stats(struct igb_adapter *);
 bool igb_has_link(struct igb_adapter *adapter);
@@ -752,8 +771,11 @@ void igb_ptp_tx_hang(struct igb_adapter *adapter);
 void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb);
 int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 			ktime_t *timestamp);
-int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
-int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
+int igb_ptp_hwtstamp_get(struct net_device *netdev,
+			 struct kernel_hwtstamp_config *config);
+int igb_ptp_hwtstamp_set(struct net_device *netdev,
+			 struct kernel_hwtstamp_config *config,
+			 struct netlink_ext_ack *extack);
 void igb_set_flag_queue_pairs(struct igb_adapter *, const u32);
 unsigned int igb_get_max_rss_queues(struct igb_adapter *);
 #ifdef CONFIG_IGB_HWMON
@@ -797,6 +819,33 @@ static inline struct netdev_queue *txring_txq(const struct igb_ring *tx_ring)
 	return netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index);
 }
 
+/* This function assumes __netif_tx_lock is held by the caller. */
+static inline void igb_xdp_ring_update_tail(struct igb_ring *ring)
+{
+	lockdep_assert_held(&txring_txq(ring)->_xmit_lock);
+
+	/* Force memory writes to complete before letting h/w know there
+	 * are new descriptors to fetch.
+	 */
+	wmb();
+	writel(ring->next_to_use, ring->tail);
+}
+
+static inline struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter)
+{
+	unsigned int r_idx = smp_processor_id();
+
+	if (r_idx >= adapter->num_tx_queues)
+		r_idx = r_idx % adapter->num_tx_queues;
+
+	return adapter->tx_ring[r_idx];
+}
+
+static inline bool igb_xdp_is_enabled(struct igb_adapter *adapter)
+{
+	return !!READ_ONCE(adapter->xdp_prog);
+}
+
 int igb_add_filter(struct igb_adapter *adapter,
 		   struct igb_nfc_filter *input);
 int igb_erase_filter(struct igb_adapter *adapter,
@@ -807,4 +856,17 @@ int igb_add_mac_steering_filter(struct igb_adapter *adapter,
 int igb_del_mac_steering_filter(struct igb_adapter *adapter,
 				const u8 *addr, u8 queue, u8 flags);
 
+struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter,
+				   struct igb_ring *ring);
+int igb_xsk_pool_setup(struct igb_adapter *adapter,
+		       struct xsk_buff_pool *pool,
+		       u16 qid);
+bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring,
+			     struct xsk_buff_pool *xsk_pool, u16 count);
+void igb_clean_rx_ring_zc(struct igb_ring *rx_ring);
+int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector,
+			struct xsk_buff_pool *xsk_pool, const int budget);
+bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool);
+int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags);
+
 #endif /* _IGB_H_ */
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index ca6ccbc13954..b507576b28b2 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -920,11 +920,11 @@ static int igb_set_ringparam(struct net_device *netdev,
 	}
 
 	if (adapter->num_tx_queues > adapter->num_rx_queues)
-		temp_ring = vmalloc(array_size(sizeof(struct igb_ring),
-					       adapter->num_tx_queues));
+		temp_ring = vmalloc_array(adapter->num_tx_queues,
+					  sizeof(struct igb_ring));
 	else
-		temp_ring = vmalloc(array_size(sizeof(struct igb_ring),
-					       adapter->num_rx_queues));
+		temp_ring = vmalloc_array(adapter->num_rx_queues,
+					  sizeof(struct igb_ring));
 
 	if (!temp_ring) {
 		err = -ENOMEM;
@@ -2081,11 +2081,8 @@ static void igb_diag_test(struct net_device *netdev,
 	} else {
 		dev_info(&adapter->pdev->dev, "online testing starting\n");
 
-		/* PHY is powered down when interface is down */
-		if (if_running && igb_link_test(adapter, &data[TEST_LINK]))
+		if (igb_link_test(adapter, &data[TEST_LINK]))
 			eth_test->flags |= ETH_TEST_FL_FAILED;
-		else
-			data[TEST_LINK] = 0;
 
 		/* Online tests aren't run; pass by default */
 		data[TEST_REG] = 0;
@@ -2284,7 +2281,7 @@ static int igb_get_sset_count(struct net_device *netdev, int sset)
 	case ETH_SS_PRIV_FLAGS:
 		return IGB_PRIV_FLAGS_STR_LEN;
 	default:
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 }
 
@@ -2500,9 +2497,11 @@ static int igb_get_ethtool_nfc_all(struct igb_adapter *adapter,
 	return 0;
 }
 
-static int igb_get_rss_hash_opts(struct igb_adapter *adapter,
-				 struct ethtool_rxnfc *cmd)
+static int igb_get_rxfh_fields(struct net_device *dev,
+			       struct ethtool_rxfh_fields *cmd)
 {
+	struct igb_adapter *adapter = netdev_priv(dev);
+
 	cmd->data = 0;
 
 	/* Report default options for RSS on igb */
@@ -2542,6 +2541,13 @@ static int igb_get_rss_hash_opts(struct igb_adapter *adapter,
 	return 0;
 }
 
+static u32 igb_get_rx_ring_count(struct net_device *dev)
+{
+	struct igb_adapter *adapter = netdev_priv(dev);
+
+	return adapter->num_rx_queues;
+}
+
 static int igb_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 			 u32 *rule_locs)
 {
@@ -2549,10 +2555,6 @@ static int igb_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	int ret = -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
-	case ETHTOOL_GRXRINGS:
-		cmd->data = adapter->num_rx_queues;
-		ret = 0;
-		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = adapter->nfc_filter_count;
 		ret = 0;
@@ -2563,9 +2565,6 @@ static int igb_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	case ETHTOOL_GRXCLSRLALL:
 		ret = igb_get_ethtool_nfc_all(adapter, cmd, rule_locs);
 		break;
-	case ETHTOOL_GRXFH:
-		ret = igb_get_rss_hash_opts(adapter, cmd);
-		break;
 	default:
 		break;
 	}
@@ -2575,9 +2574,11 @@ static int igb_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 
 #define UDP_RSS_FLAGS (IGB_FLAG_RSS_FIELD_IPV4_UDP | \
 		       IGB_FLAG_RSS_FIELD_IPV6_UDP)
-static int igb_set_rss_hash_opt(struct igb_adapter *adapter,
-				struct ethtool_rxnfc *nfc)
+static int igb_set_rxfh_fields(struct net_device *dev,
+			       const struct ethtool_rxfh_fields *nfc,
+			       struct netlink_ext_ack *extack)
 {
+	struct igb_adapter *adapter = netdev_priv(dev);
 	u32 flags = adapter->flags;
 
 	/* RSS does not support anything other than hashing
@@ -3005,9 +3006,6 @@ static int igb_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	int ret = -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
-	case ETHTOOL_SRXFH:
-		ret = igb_set_rss_hash_opt(adapter, cmd);
-		break;
 	case ETHTOOL_SRXCLSRLINS:
 		ret = igb_add_ethtool_nfc_entry(adapter, cmd);
 		break;
@@ -3478,6 +3476,7 @@ static const struct ethtool_ops igb_ethtool_ops = {
 	.get_ts_info		= igb_get_ts_info,
 	.get_rxnfc		= igb_get_rxnfc,
 	.set_rxnfc		= igb_set_rxnfc,
+	.get_rx_ring_count	= igb_get_rx_ring_count,
 	.get_eee		= igb_get_eee,
 	.set_eee		= igb_set_eee,
 	.get_module_info	= igb_get_module_info,
@@ -3485,6 +3484,8 @@ static const struct ethtool_ops igb_ethtool_ops = {
 	.get_rxfh_indir_size	= igb_get_rxfh_indir_size,
 	.get_rxfh		= igb_get_rxfh,
 	.set_rxfh		= igb_set_rxfh,
+	.get_rxfh_fields	= igb_get_rxfh_fields,
+	.set_rxfh_fields	= igb_set_rxfh_fields,
 	.get_channels		= igb_get_channels,
 	.set_channels		= igb_set_channels,
 	.get_priv_flags		= igb_get_priv_flags,
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 288a4bb2683a..dbea37269d2c 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -33,7 +33,6 @@
 #include <linux/bpf_trace.h>
 #include <linux/pm_runtime.h>
 #include <linux/etherdevice.h>
-#include <linux/lockdep.h>
 #ifdef CONFIG_IGB_DCA
 #include <linux/dca.h>
 #endif
@@ -116,8 +115,6 @@ static void igb_configure_tx(struct igb_adapter *);
 static void igb_configure_rx(struct igb_adapter *);
 static void igb_clean_all_tx_rings(struct igb_adapter *);
 static void igb_clean_all_rx_rings(struct igb_adapter *);
-static void igb_clean_tx_ring(struct igb_ring *);
-static void igb_clean_rx_ring(struct igb_ring *);
 static void igb_set_rx_mode(struct net_device *);
 static void igb_update_phy_info(struct timer_list *);
 static void igb_watchdog(struct timer_list *);
@@ -475,12 +472,17 @@ rx_ring_summary:
 
 		for (i = 0; i < rx_ring->count; i++) {
 			const char *next_desc;
-			struct igb_rx_buffer *buffer_info;
-			buffer_info = &rx_ring->rx_buffer_info[i];
+			dma_addr_t dma = (dma_addr_t)0;
+			struct igb_rx_buffer *buffer_info = NULL;
 			rx_desc = IGB_RX_DESC(rx_ring, i);
 			u0 = (struct my_u0 *)rx_desc;
 			staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
 
+			if (!rx_ring->xsk_pool) {
+				buffer_info = &rx_ring->rx_buffer_info[i];
+				dma = buffer_info->dma;
+			}
+
 			if (i == rx_ring->next_to_use)
 				next_desc = " NTU";
 			else if (i == rx_ring->next_to_clean)
@@ -500,11 +502,11 @@ rx_ring_summary:
 					"R  ", i,
 					le64_to_cpu(u0->a),
 					le64_to_cpu(u0->b),
-					(u64)buffer_info->dma,
+					(u64)dma,
 					next_desc);
 
 				if (netif_msg_pktdata(adapter) &&
-				    buffer_info->dma && buffer_info->page) {
+				    buffer_info && dma && buffer_info->page) {
 					print_hex_dump(KERN_INFO, "",
 					  DUMP_PREFIX_ADDRESS,
 					  16, 1,
@@ -945,6 +947,9 @@ static int igb_request_msix(struct igb_adapter *adapter)
 				  q_vector);
 		if (err)
 			goto err_free;
+
+		netif_napi_set_irq(&q_vector->napi,
+				   adapter->msix_entries[vector].vector);
 	}
 
 	igb_configure_msix(adapter);
@@ -1192,7 +1197,8 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
 		return -ENOMEM;
 
 	/* initialize NAPI */
-	netif_napi_add(adapter->netdev, &q_vector->napi, igb_poll);
+	netif_napi_add_config(adapter->netdev, &q_vector->napi, igb_poll,
+			      v_idx);
 
 	/* tie q_vector and adapter together */
 	adapter->q_vector[v_idx] = q_vector;
@@ -1525,8 +1531,7 @@ static void igb_update_mng_vlan(struct igb_adapter *adapter)
 		adapter->mng_vlan_id = IGB_MNG_VLAN_NONE;
 	}
 
-	if ((old_vid != (u16)IGB_MNG_VLAN_NONE) &&
-	    (vid != old_vid) &&
+	if (old_vid != IGB_MNG_VLAN_NONE && vid != old_vid &&
 	    !test_bit(old_vid, adapter->active_vlans)) {
 		/* remove VID from filter table */
 		igb_vfta_set(hw, vid, pf_id, false, true);
@@ -1990,7 +1995,11 @@ static void igb_configure(struct igb_adapter *adapter)
 	 */
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		struct igb_ring *ring = adapter->rx_ring[i];
-		igb_alloc_rx_buffers(ring, igb_desc_unused(ring));
+		if (ring->xsk_pool)
+			igb_alloc_rx_buffers_zc(ring, ring->xsk_pool,
+						igb_desc_unused(ring));
+		else
+			igb_alloc_rx_buffers(ring, igb_desc_unused(ring));
 	}
 }
 
@@ -2090,6 +2099,22 @@ static void igb_check_swap_media(struct igb_adapter *adapter)
 	wr32(E1000_CTRL_EXT, ctrl_ext);
 }
 
+void igb_set_queue_napi(struct igb_adapter *adapter, int vector,
+			struct napi_struct *napi)
+{
+	struct igb_q_vector *q_vector = adapter->q_vector[vector];
+
+	if (q_vector->rx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->rx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_RX, napi);
+
+	if (q_vector->tx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->tx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_TX, napi);
+}
+
 /**
  *  igb_up - Open the interface and prepare it to handle traffic
  *  @adapter: board private structure
@@ -2097,6 +2122,7 @@ static void igb_check_swap_media(struct igb_adapter *adapter)
 int igb_up(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int i;
 
 	/* hardware has been reset, we need to reload some things */
@@ -2104,8 +2130,11 @@ int igb_up(struct igb_adapter *adapter)
 
 	clear_bit(__IGB_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&(adapter->q_vector[i]->napi));
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igb_set_queue_napi(adapter, i, napi);
+	}
 
 	if (adapter->flags & IGB_FLAG_HAS_MSIX)
 		igb_configure_msix(adapter);
@@ -2175,12 +2204,13 @@ void igb_down(struct igb_adapter *adapter)
 	for (i = 0; i < adapter->num_q_vectors; i++) {
 		if (adapter->q_vector[i]) {
 			napi_synchronize(&adapter->q_vector[i]->napi);
+			igb_set_queue_napi(adapter, i, NULL);
 			napi_disable(&adapter->q_vector[i]->napi);
 		}
 	}
 
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_info_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_info_timer);
 
 	/* record the stats before reset*/
 	spin_lock(&adapter->stats64_lock);
@@ -2911,37 +2941,20 @@ static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf)
 
 static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
+	struct igb_adapter *adapter = netdev_priv(dev);
+
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return igb_xdp_setup(dev, xdp);
+	case XDP_SETUP_XSK_POOL:
+		return igb_xsk_pool_setup(adapter, xdp->xsk.pool,
+					  xdp->xsk.queue_id);
 	default:
 		return -EINVAL;
 	}
 }
 
-/* This function assumes __netif_tx_lock is held by the caller. */
-static void igb_xdp_ring_update_tail(struct igb_ring *ring)
-{
-	lockdep_assert_held(&txring_txq(ring)->_xmit_lock);
-
-	/* Force memory writes to complete before letting h/w know there
-	 * are new descriptors to fetch.
-	 */
-	wmb();
-	writel(ring->next_to_use, ring->tail);
-}
-
-static struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter)
-{
-	unsigned int r_idx = smp_processor_id();
-
-	if (r_idx >= adapter->num_tx_queues)
-		r_idx = r_idx % adapter->num_tx_queues;
-
-	return adapter->tx_ring[r_idx];
-}
-
-static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp)
+int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp)
 {
 	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
 	int cpu = smp_processor_id();
@@ -2955,7 +2968,8 @@ static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp)
 	/* During program transitions its possible adapter->xdp_prog is assigned
 	 * but ring has not been configured yet. In this case simply abort xmit.
 	 */
-	tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL;
+	tx_ring = igb_xdp_is_enabled(adapter) ?
+		igb_xdp_tx_queue_mapping(adapter) : NULL;
 	if (unlikely(!tx_ring))
 		return IGB_XDP_CONSUMED;
 
@@ -2988,10 +3002,14 @@ static int igb_xdp_xmit(struct net_device *dev, int n,
 	/* During program transitions its possible adapter->xdp_prog is assigned
 	 * but ring has not been configured yet. In this case simply abort xmit.
 	 */
-	tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL;
+	tx_ring = igb_xdp_is_enabled(adapter) ?
+		igb_xdp_tx_queue_mapping(adapter) : NULL;
 	if (unlikely(!tx_ring))
 		return -ENXIO;
 
+	if (unlikely(test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags)))
+		return -ENXIO;
+
 	nq = txring_txq(tx_ring);
 	__netif_tx_lock(nq, cpu);
 
@@ -3042,6 +3060,9 @@ static const struct net_device_ops igb_netdev_ops = {
 	.ndo_setup_tc		= igb_setup_tc,
 	.ndo_bpf		= igb_xdp,
 	.ndo_xdp_xmit		= igb_xdp_xmit,
+	.ndo_xsk_wakeup         = igb_xsk_wakeup,
+	.ndo_hwtstamp_get	= igb_ptp_hwtstamp_get,
+	.ndo_hwtstamp_set	= igb_ptp_hwtstamp_set,
 };
 
 /**
@@ -3338,7 +3359,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	netdev->priv_flags |= IFF_SUPP_NOFCS;
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
-	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			       NETDEV_XDP_ACT_XSK_ZEROCOPY;
 
 	/* MTU range: 68 - 9216 */
 	netdev->min_mtu = ETH_MIN_MTU;
@@ -3864,8 +3886,8 @@ static void igb_remove(struct pci_dev *pdev)
 	 * disable watchdog from being rescheduled.
 	 */
 	set_bit(__IGB_DOWN, &adapter->state);
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_info_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_info_timer);
 
 	cancel_work_sync(&adapter->reset_task);
 	cancel_work_sync(&adapter->watchdog_task);
@@ -4117,8 +4139,9 @@ static int igb_sw_init(struct igb_adapter *adapter)
 static int __igb_open(struct net_device *netdev, bool resuming)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
-	struct e1000_hw *hw = &adapter->hw;
 	struct pci_dev *pdev = adapter->pdev;
+	struct e1000_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int err;
 	int i;
 
@@ -4170,8 +4193,11 @@ static int __igb_open(struct net_device *netdev, bool resuming)
 	/* From here on the code is the same as igb_up() */
 	clear_bit(__IGB_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&(adapter->q_vector[i]->napi));
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igb_set_queue_napi(adapter, i, napi);
+	}
 
 	/* Clear any pending interrupts. */
 	rd32(E1000_TSICR);
@@ -4364,6 +4390,8 @@ void igb_configure_tx_ring(struct igb_adapter *adapter,
 	u64 tdba = ring->dma;
 	int reg_idx = ring->reg_idx;
 
+	WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring));
+
 	wr32(E1000_TDLEN(reg_idx),
 	     ring->count * sizeof(union e1000_adv_tx_desc));
 	wr32(E1000_TDBAL(reg_idx),
@@ -4720,12 +4748,17 @@ void igb_setup_srrctl(struct igb_adapter *adapter, struct igb_ring *ring)
 	struct e1000_hw *hw = &adapter->hw;
 	int reg_idx = ring->reg_idx;
 	u32 srrctl = 0;
+	u32 buf_size;
 
-	srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
-	if (ring_uses_large_buffer(ring))
-		srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+	if (ring->xsk_pool)
+		buf_size = xsk_pool_get_rx_frame_size(ring->xsk_pool);
+	else if (ring_uses_large_buffer(ring))
+		buf_size = IGB_RXBUFFER_3072;
 	else
-		srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+		buf_size = IGB_RXBUFFER_2048;
+
+	srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
+	srrctl |= buf_size >> E1000_SRRCTL_BSIZEPKT_SHIFT;
 	srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF;
 	if (hw->mac.type >= e1000_82580)
 		srrctl |= E1000_SRRCTL_TIMESTAMP;
@@ -4757,8 +4790,17 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	u32 rxdctl = 0;
 
 	xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
-	WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-					   MEM_TYPE_PAGE_SHARED, NULL));
+	WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring));
+	if (ring->xsk_pool) {
+		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						   MEM_TYPE_XSK_BUFF_POOL,
+						   NULL));
+		xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
+	} else {
+		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						   MEM_TYPE_PAGE_SHARED,
+						   NULL));
+	}
 
 	/* disable the queue */
 	wr32(E1000_RXDCTL(reg_idx), 0);
@@ -4785,9 +4827,12 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	rxdctl |= IGB_RX_HTHRESH << 8;
 	rxdctl |= IGB_RX_WTHRESH << 16;
 
-	/* initialize rx_buffer_info */
-	memset(ring->rx_buffer_info, 0,
-	       sizeof(struct igb_rx_buffer) * ring->count);
+	if (ring->xsk_pool)
+		memset(ring->rx_buffer_info_zc, 0,
+		       sizeof(*ring->rx_buffer_info_zc) * ring->count);
+	else
+		memset(ring->rx_buffer_info, 0,
+		       sizeof(*ring->rx_buffer_info) * ring->count);
 
 	/* initialize Rx descriptor 0 */
 	rx_desc = IGB_RX_DESC(ring, 0);
@@ -4888,19 +4933,24 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter)
  *  igb_clean_tx_ring - Free Tx Buffers
  *  @tx_ring: ring to be cleaned
  **/
-static void igb_clean_tx_ring(struct igb_ring *tx_ring)
+void igb_clean_tx_ring(struct igb_ring *tx_ring)
 {
 	u16 i = tx_ring->next_to_clean;
 	struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i];
+	u32 xsk_frames = 0;
 
 	while (i != tx_ring->next_to_use) {
 		union e1000_adv_tx_desc *eop_desc, *tx_desc;
 
 		/* Free all the Tx ring sk_buffs or xdp frames */
-		if (tx_buffer->type == IGB_TYPE_SKB)
+		if (tx_buffer->type == IGB_TYPE_SKB) {
 			dev_kfree_skb_any(tx_buffer->skb);
-		else
+		} else if (tx_buffer->type == IGB_TYPE_XDP) {
 			xdp_return_frame(tx_buffer->xdpf);
+		} else if (tx_buffer->type == IGB_TYPE_XSK) {
+			xsk_frames++;
+			goto skip_for_xsk;
+		}
 
 		/* unmap skb header data */
 		dma_unmap_single(tx_ring->dev,
@@ -4931,6 +4981,7 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring)
 					       DMA_TO_DEVICE);
 		}
 
+skip_for_xsk:
 		tx_buffer->next_to_watch = NULL;
 
 		/* move us one more past the eop_desc for start of next pkt */
@@ -4945,6 +4996,9 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring)
 	/* reset BQL for queue */
 	netdev_tx_reset_queue(txring_txq(tx_ring));
 
+	if (tx_ring->xsk_pool && xsk_frames)
+		xsk_tx_completed(tx_ring->xsk_pool, xsk_frames);
+
 	/* reset next_to_use and next_to_clean */
 	tx_ring->next_to_use = 0;
 	tx_ring->next_to_clean = 0;
@@ -4975,8 +5029,13 @@ void igb_free_rx_resources(struct igb_ring *rx_ring)
 
 	rx_ring->xdp_prog = NULL;
 	xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
-	vfree(rx_ring->rx_buffer_info);
-	rx_ring->rx_buffer_info = NULL;
+	if (rx_ring->xsk_pool) {
+		vfree(rx_ring->rx_buffer_info_zc);
+		rx_ring->rx_buffer_info_zc = NULL;
+	} else {
+		vfree(rx_ring->rx_buffer_info);
+		rx_ring->rx_buffer_info = NULL;
+	}
 
 	/* if not set, then don't free */
 	if (!rx_ring->desc)
@@ -5007,13 +5066,18 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter)
  *  igb_clean_rx_ring - Free Rx Buffers per Queue
  *  @rx_ring: ring to free buffers from
  **/
-static void igb_clean_rx_ring(struct igb_ring *rx_ring)
+void igb_clean_rx_ring(struct igb_ring *rx_ring)
 {
 	u16 i = rx_ring->next_to_clean;
 
 	dev_kfree_skb(rx_ring->skb);
 	rx_ring->skb = NULL;
 
+	if (rx_ring->xsk_pool) {
+		igb_clean_rx_ring_zc(rx_ring);
+		goto skip_for_xsk;
+	}
+
 	/* Free all the Rx ring sk_buffs */
 	while (i != rx_ring->next_to_alloc) {
 		struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i];
@@ -5041,6 +5105,7 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring)
 			i = 0;
 	}
 
+skip_for_xsk:
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
@@ -5400,7 +5465,8 @@ static void igb_spoof_check(struct igb_adapter *adapter)
  */
 static void igb_update_phy_info(struct timer_list *t)
 {
-	struct igb_adapter *adapter = from_timer(adapter, t, phy_info_timer);
+	struct igb_adapter *adapter = timer_container_of(adapter, t,
+							 phy_info_timer);
 	igb_get_phy_info(&adapter->hw);
 }
 
@@ -5490,7 +5556,8 @@ static void igb_check_lvmmc(struct igb_adapter *adapter)
  **/
 static void igb_watchdog(struct timer_list *t)
 {
-	struct igb_adapter *adapter = from_timer(adapter, t, watchdog_timer);
+	struct igb_adapter *adapter = timer_container_of(adapter, t,
+							 watchdog_timer);
 	/* Do the rest outside of interrupt context */
 	schedule_work(&adapter->watchdog_task);
 }
@@ -5690,11 +5757,29 @@ no_wait:
 	if (adapter->flags & IGB_FLAG_HAS_MSIX) {
 		u32 eics = 0;
 
-		for (i = 0; i < adapter->num_q_vectors; i++)
-			eics |= adapter->q_vector[i]->eims_value;
-		wr32(E1000_EICS, eics);
+		for (i = 0; i < adapter->num_q_vectors; i++) {
+			struct igb_q_vector *q_vector = adapter->q_vector[i];
+			struct igb_ring *rx_ring;
+
+			if (!q_vector->rx.ring)
+				continue;
+
+			rx_ring = adapter->rx_ring[q_vector->rx.ring->queue_index];
+
+			if (test_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) {
+				eics |= q_vector->eims_value;
+				clear_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
+			}
+		}
+		if (eics)
+			wr32(E1000_EICS, eics);
 	} else {
-		wr32(E1000_ICS, E1000_ICS_RXDMT0);
+		struct igb_ring *rx_ring = adapter->rx_ring[0];
+
+		if (test_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) {
+			clear_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
+			wr32(E1000_ICS, E1000_ICS_RXDMT0);
+		}
 	}
 
 	igb_spoof_check(adapter);
@@ -6467,6 +6552,9 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 		return NETDEV_TX_BUSY;
 	}
 
+	if (unlikely(test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags)))
+		return NETDEV_TX_BUSY;
+
 	/* record the location of the first descriptor for this packet */
 	first = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
 	first->type = IGB_TYPE_SKB;
@@ -6622,7 +6710,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	int max_frame = new_mtu + IGB_ETH_PKT_HDR_PAD;
 
-	if (adapter->xdp_prog) {
+	if (igb_xdp_is_enabled(adapter)) {
 		int i;
 
 		for (i = 0; i < adapter->num_rx_queues; i++) {
@@ -8195,6 +8283,7 @@ static int igb_poll(struct napi_struct *napi, int budget)
 	struct igb_q_vector *q_vector = container_of(napi,
 						     struct igb_q_vector,
 						     napi);
+	struct xsk_buff_pool *xsk_pool;
 	bool clean_complete = true;
 	int work_done = 0;
 
@@ -8206,7 +8295,12 @@ static int igb_poll(struct napi_struct *napi, int budget)
 		clean_complete = igb_clean_tx_irq(q_vector, budget);
 
 	if (q_vector->rx.ring) {
-		int cleaned = igb_clean_rx_irq(q_vector, budget);
+		int cleaned;
+
+		xsk_pool = READ_ONCE(q_vector->rx.ring->xsk_pool);
+		cleaned = xsk_pool ?
+			igb_clean_rx_irq_zc(q_vector, xsk_pool, budget) :
+			igb_clean_rx_irq(q_vector, budget);
 
 		work_done += cleaned;
 		if (cleaned >= budget)
@@ -8235,13 +8329,18 @@ static int igb_poll(struct napi_struct *napi, int budget)
  **/
 static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 {
-	struct igb_adapter *adapter = q_vector->adapter;
-	struct igb_ring *tx_ring = q_vector->tx.ring;
-	struct igb_tx_buffer *tx_buffer;
-	union e1000_adv_tx_desc *tx_desc;
 	unsigned int total_bytes = 0, total_packets = 0;
+	struct igb_adapter *adapter = q_vector->adapter;
 	unsigned int budget = q_vector->tx.work_limit;
+	struct igb_ring *tx_ring = q_vector->tx.ring;
 	unsigned int i = tx_ring->next_to_clean;
+	union e1000_adv_tx_desc *tx_desc;
+	struct igb_tx_buffer *tx_buffer;
+	struct xsk_buff_pool *xsk_pool;
+	int cpu = smp_processor_id();
+	bool xsk_xmit_done = true;
+	struct netdev_queue *nq;
+	u32 xsk_frames = 0;
 
 	if (test_bit(__IGB_DOWN, &adapter->state))
 		return true;
@@ -8272,10 +8371,14 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 		total_packets += tx_buffer->gso_segs;
 
 		/* free the skb */
-		if (tx_buffer->type == IGB_TYPE_SKB)
+		if (tx_buffer->type == IGB_TYPE_SKB) {
 			napi_consume_skb(tx_buffer->skb, napi_budget);
-		else
+		} else if (tx_buffer->type == IGB_TYPE_XDP) {
 			xdp_return_frame(tx_buffer->xdpf);
+		} else if (tx_buffer->type == IGB_TYPE_XSK) {
+			xsk_frames++;
+			goto skip_for_xsk;
+		}
 
 		/* unmap skb header data */
 		dma_unmap_single(tx_ring->dev,
@@ -8307,6 +8410,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 			}
 		}
 
+skip_for_xsk:
 		/* move us one more past the eop_desc for start of next pkt */
 		tx_buffer++;
 		tx_desc++;
@@ -8335,6 +8439,21 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 	q_vector->tx.total_bytes += total_bytes;
 	q_vector->tx.total_packets += total_packets;
 
+	xsk_pool = READ_ONCE(tx_ring->xsk_pool);
+	if (xsk_pool) {
+		if (xsk_frames)
+			xsk_tx_completed(xsk_pool, xsk_frames);
+		if (xsk_uses_need_wakeup(xsk_pool))
+			xsk_set_tx_need_wakeup(xsk_pool);
+
+		nq = txring_txq(tx_ring);
+		__netif_tx_lock(nq, cpu);
+		/* Avoid transmit queue timeout since we share it with the slow path */
+		txq_trans_cond_update(nq);
+		xsk_xmit_done = igb_xmit_zc(tx_ring, xsk_pool);
+		__netif_tx_unlock(nq);
+	}
+
 	if (test_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) {
 		struct e1000_hw *hw = &adapter->hw;
 
@@ -8397,7 +8516,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 		}
 	}
 
-	return !!budget;
+	return !!budget && xsk_xmit_done;
 }
 
 /**
@@ -8588,9 +8707,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
 	return skb;
 }
 
-static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter,
-				   struct igb_ring *rx_ring,
-				   struct xdp_buff *xdp)
+static int igb_run_xdp(struct igb_adapter *adapter, struct igb_ring *rx_ring,
+		       struct xdp_buff *xdp)
 {
 	int err, result = IGB_XDP_PASS;
 	struct bpf_prog *xdp_prog;
@@ -8630,7 +8748,7 @@ out_failure:
 		break;
 	}
 xdp_out:
-	return ERR_PTR(-result);
+	return result;
 }
 
 static unsigned int igb_rx_frame_truesize(struct igb_ring *rx_ring,
@@ -8756,10 +8874,6 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring,
 				union e1000_adv_rx_desc *rx_desc,
 				struct sk_buff *skb)
 {
-	/* XDP packets use error pointer so abort at this point */
-	if (IS_ERR(skb))
-		return true;
-
 	if (unlikely((igb_test_staterr(rx_desc,
 				       E1000_RXDEXT_ERR_FRAME_ERR_MASK)))) {
 		struct net_device *netdev = rx_ring->netdev;
@@ -8786,9 +8900,9 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring,
  *  order to populate the hash, checksum, VLAN, timestamp, protocol, and
  *  other fields within the skb.
  **/
-static void igb_process_skb_fields(struct igb_ring *rx_ring,
-				   union e1000_adv_rx_desc *rx_desc,
-				   struct sk_buff *skb)
+void igb_process_skb_fields(struct igb_ring *rx_ring,
+			    union e1000_adv_rx_desc *rx_desc,
+			    struct sk_buff *skb)
 {
 	struct net_device *dev = rx_ring->netdev;
 
@@ -8870,6 +8984,38 @@ static void igb_put_rx_buffer(struct igb_ring *rx_ring,
 	rx_buffer->page = NULL;
 }
 
+void igb_finalize_xdp(struct igb_adapter *adapter, unsigned int status)
+{
+	int cpu = smp_processor_id();
+	struct netdev_queue *nq;
+
+	if (status & IGB_XDP_REDIR)
+		xdp_do_flush();
+
+	if (status & IGB_XDP_TX) {
+		struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter);
+
+		nq = txring_txq(tx_ring);
+		__netif_tx_lock(nq, cpu);
+		igb_xdp_ring_update_tail(tx_ring);
+		__netif_tx_unlock(nq);
+	}
+}
+
+void igb_update_rx_stats(struct igb_q_vector *q_vector, unsigned int packets,
+			 unsigned int bytes)
+{
+	struct igb_ring *ring = q_vector->rx.ring;
+
+	u64_stats_update_begin(&ring->rx_syncp);
+	ring->rx_stats.packets += packets;
+	ring->rx_stats.bytes += bytes;
+	u64_stats_update_end(&ring->rx_syncp);
+
+	q_vector->rx.total_packets += packets;
+	q_vector->rx.total_bytes += bytes;
+}
+
 static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 {
 	unsigned int total_bytes = 0, total_packets = 0;
@@ -8877,12 +9023,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	struct igb_ring *rx_ring = q_vector->rx.ring;
 	u16 cleaned_count = igb_desc_unused(rx_ring);
 	struct sk_buff *skb = rx_ring->skb;
-	int cpu = smp_processor_id();
 	unsigned int xdp_xmit = 0;
-	struct netdev_queue *nq;
 	struct xdp_buff xdp;
 	u32 frame_sz = 0;
 	int rx_buf_pgcnt;
+	int xdp_res = 0;
 
 	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
 #if (PAGE_SIZE < 8192)
@@ -8940,12 +9085,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 			/* At larger PAGE_SIZE, frame_sz depend on len size */
 			xdp.frame_sz = igb_rx_frame_truesize(rx_ring, size);
 #endif
-			skb = igb_run_xdp(adapter, rx_ring, &xdp);
+			xdp_res = igb_run_xdp(adapter, rx_ring, &xdp);
 		}
 
-		if (IS_ERR(skb)) {
-			unsigned int xdp_res = -PTR_ERR(skb);
-
+		if (xdp_res) {
 			if (xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR)) {
 				xdp_xmit |= xdp_res;
 				igb_rx_buffer_flip(rx_ring, rx_buffer, size);
@@ -8964,9 +9107,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 						&xdp, timestamp);
 
 		/* exit if we failed to retrieve a buffer */
-		if (!skb) {
+		if (!xdp_res && !skb) {
 			rx_ring->rx_stats.alloc_failed++;
 			rx_buffer->pagecnt_bias++;
+			set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
 			break;
 		}
 
@@ -8978,7 +9122,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 			continue;
 
 		/* verify the packet layout is correct */
-		if (igb_cleanup_headers(rx_ring, rx_desc, skb)) {
+		if (xdp_res || igb_cleanup_headers(rx_ring, rx_desc, skb)) {
 			skb = NULL;
 			continue;
 		}
@@ -9001,24 +9145,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	/* place incomplete frames back on ring for completion */
 	rx_ring->skb = skb;
 
-	if (xdp_xmit & IGB_XDP_REDIR)
-		xdp_do_flush();
-
-	if (xdp_xmit & IGB_XDP_TX) {
-		struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter);
-
-		nq = txring_txq(tx_ring);
-		__netif_tx_lock(nq, cpu);
-		igb_xdp_ring_update_tail(tx_ring);
-		__netif_tx_unlock(nq);
-	}
+	if (xdp_xmit)
+		igb_finalize_xdp(adapter, xdp_xmit);
 
-	u64_stats_update_begin(&rx_ring->rx_syncp);
-	rx_ring->rx_stats.packets += total_packets;
-	rx_ring->rx_stats.bytes += total_bytes;
-	u64_stats_update_end(&rx_ring->rx_syncp);
-	q_vector->rx.total_packets += total_packets;
-	q_vector->rx.total_bytes += total_bytes;
+	igb_update_rx_stats(q_vector, total_packets, total_bytes);
 
 	if (cleaned_count)
 		igb_alloc_rx_buffers(rx_ring, cleaned_count);
@@ -9040,6 +9170,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 	page = dev_alloc_pages(igb_rx_pg_order(rx_ring));
 	if (unlikely(!page)) {
 		rx_ring->rx_stats.alloc_failed++;
+		set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
 		return false;
 	}
 
@@ -9056,6 +9187,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 		__free_pages(page, igb_rx_pg_order(rx_ring));
 
 		rx_ring->rx_stats.alloc_failed++;
+		set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
 		return false;
 	}
 
@@ -9185,10 +9317,6 @@ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
 		return igb_mii_ioctl(netdev, ifr, cmd);
-	case SIOCGHWTSTAMP:
-		return igb_ptp_get_ts_config(netdev, ifr);
-	case SIOCSHWTSTAMP:
-		return igb_ptp_set_ts_config(netdev, ifr);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -9471,7 +9599,6 @@ static int __igb_resume(struct device *dev, bool rpm)
 
 	pci_set_power_state(pdev, PCI_D0);
 	pci_restore_state(pdev);
-	pci_save_state(pdev);
 
 	if (!pci_device_is_present(pdev))
 		return -ENODEV;
@@ -9594,8 +9721,11 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev,
 	if (state == pci_channel_io_perm_failure)
 		return PCI_ERS_RESULT_DISCONNECT;
 
+	rtnl_lock();
 	if (netif_running(netdev))
 		igb_down(adapter);
+	rtnl_unlock();
+
 	pci_disable_device(pdev);
 
 	/* Request a slot reset. */
@@ -9623,7 +9753,6 @@ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev)
 	} else {
 		pci_set_master(pdev);
 		pci_restore_state(pdev);
-		pci_save_state(pdev);
 
 		pci_enable_wake(pdev, PCI_D3hot, 0);
 		pci_enable_wake(pdev, PCI_D3cold, 0);
@@ -9654,16 +9783,21 @@ static void igb_io_resume(struct pci_dev *pdev)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igb_adapter *adapter = netdev_priv(netdev);
 
+	rtnl_lock();
 	if (netif_running(netdev)) {
 		if (!test_bit(__IGB_DOWN, &adapter->state)) {
 			dev_dbg(&pdev->dev, "Resuming from non-fatal error, do nothing.\n");
+			rtnl_unlock();
 			return;
 		}
+
 		if (igb_up(adapter)) {
 			dev_err(&pdev->dev, "igb_up failed after reset\n");
+			rtnl_unlock();
 			return;
 		}
 	}
+	rtnl_unlock();
 
 	netif_device_attach(netdev);
 
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index f94570556120..bd85d02ecadd 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -73,7 +73,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter);
 static void igb_ptp_sdp_init(struct igb_adapter *adapter);
 
 /* SYSTIM read access for the 82576 */
-static u64 igb_ptp_read_82576(const struct cyclecounter *cc)
+static u64 igb_ptp_read_82576(struct cyclecounter *cc)
 {
 	struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc);
 	struct e1000_hw *hw = &igb->hw;
@@ -90,7 +90,7 @@ static u64 igb_ptp_read_82576(const struct cyclecounter *cc)
 }
 
 /* SYSTIM read access for the 82580 */
-static u64 igb_ptp_read_82580(const struct cyclecounter *cc)
+static u64 igb_ptp_read_82580(struct cyclecounter *cc)
 {
 	struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc);
 	struct e1000_hw *hw = &igb->hw;
@@ -502,11 +502,10 @@ static int igb_ptp_feature_enable_82580(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_EXTTS:
-		/* Reject requests with unsupported flags */
-		if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-					PTP_RISING_EDGE |
-					PTP_FALLING_EDGE |
-					PTP_STRICT_FLAGS))
+		/* Both the rising and falling edge are timestamped */
+		if (rq->extts.flags & PTP_STRICT_FLAGS &&
+		    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
+		    (rq->extts.flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES)
 			return -EOPNOTSUPP;
 
 		if (on) {
@@ -652,13 +651,6 @@ static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_EXTTS:
-		/* Reject requests with unsupported flags */
-		if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-					PTP_RISING_EDGE |
-					PTP_FALLING_EDGE |
-					PTP_STRICT_FLAGS))
-			return -EOPNOTSUPP;
-
 		/* Reject requests failing to enable both edges. */
 		if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
 		    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
@@ -848,14 +840,11 @@ static void igb_ptp_overflow_check(struct work_struct *work)
 	struct igb_adapter *igb =
 		container_of(work, struct igb_adapter, ptp_overflow_work.work);
 	struct timespec64 ts;
-	u64 ns;
 
 	/* Update the timecounter */
-	ns = timecounter_read(&igb->tc);
+	ts = ns_to_timespec64(timecounter_read(&igb->tc));
 
-	ts = ns_to_timespec64(ns);
-	pr_debug("igb overflow check at %lld.%09lu\n",
-		 (long long) ts.tv_sec, ts.tv_nsec);
+	pr_debug("igb overflow check at %ptSp\n", &ts);
 
 	schedule_delayed_work(&igb->ptp_overflow_work,
 			      IGB_SYSTIM_OVERFLOW_PERIOD);
@@ -1102,21 +1091,22 @@ void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb)
 }
 
 /**
- * igb_ptp_get_ts_config - get hardware time stamping config
+ * igb_ptp_hwtstamp_get - get hardware time stamping config
  * @netdev: netdev struct
- * @ifr: interface struct
+ * @config: timestamping configuration structure
  *
  * Get the hwtstamp_config settings to return to the user. Rather than attempt
  * to deconstruct the settings from the registers, just return a shadow copy
  * of the last known settings.
  **/
-int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr)
+int igb_ptp_hwtstamp_get(struct net_device *netdev,
+			 struct kernel_hwtstamp_config *config)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
-	struct hwtstamp_config *config = &adapter->tstamp_config;
 
-	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
-		-EFAULT : 0;
+	*config = adapter->tstamp_config;
+
+	return 0;
 }
 
 /**
@@ -1137,7 +1127,7 @@ int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr)
  * level 2 or 4".
  */
 static int igb_ptp_set_timestamp_mode(struct igb_adapter *adapter,
-				      struct hwtstamp_config *config)
+				      struct kernel_hwtstamp_config *config)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED;
@@ -1283,30 +1273,26 @@ static int igb_ptp_set_timestamp_mode(struct igb_adapter *adapter,
 }
 
 /**
- * igb_ptp_set_ts_config - set hardware time stamping config
+ * igb_ptp_hwtstamp_set - set hardware time stamping config
  * @netdev: netdev struct
- * @ifr: interface struct
- *
+ * @config: timestamping configuration structure
+ * @extack: netlink extended ack structure for error reporting
  **/
-int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr)
+int igb_ptp_hwtstamp_set(struct net_device *netdev,
+			 struct kernel_hwtstamp_config *config,
+			 struct netlink_ext_ack *extack)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
-	struct hwtstamp_config config;
 	int err;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	err = igb_ptp_set_timestamp_mode(adapter, &config);
+	err = igb_ptp_set_timestamp_mode(adapter, config);
 	if (err)
 		return err;
 
 	/* save these settings for future reference */
-	memcpy(&adapter->tstamp_config, &config,
-	       sizeof(adapter->tstamp_config));
+	adapter->tstamp_config = *config;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 /**
@@ -1350,6 +1336,9 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.n_per_out = IGB_N_PEROUT;
 		adapter->ptp_caps.n_pins = IGB_N_SDP;
 		adapter->ptp_caps.pps = 0;
+		adapter->ptp_caps.supported_extts_flags = PTP_RISING_EDGE |
+							  PTP_FALLING_EDGE |
+							  PTP_STRICT_FLAGS;
 		adapter->ptp_caps.pin_config = adapter->sdp_config;
 		adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
 		adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
@@ -1372,6 +1361,9 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.n_ext_ts = IGB_N_EXTTS;
 		adapter->ptp_caps.n_per_out = IGB_N_PEROUT;
 		adapter->ptp_caps.n_pins = IGB_N_SDP;
+		adapter->ptp_caps.supported_extts_flags = PTP_RISING_EDGE |
+							  PTP_FALLING_EDGE |
+							  PTP_STRICT_FLAGS;
 		adapter->ptp_caps.pps = 1;
 		adapter->ptp_caps.pin_config = adapter->sdp_config;
 		adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c
new file mode 100644
index 000000000000..30ce5fbb5b77
--- /dev/null
+++ b/drivers/net/ethernet/intel/igb/igb_xsk.c
@@ -0,0 +1,562 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2018 Intel Corporation. */
+
+#include <linux/bpf_trace.h>
+#include <net/xdp_sock_drv.h>
+#include <net/xdp.h>
+
+#include "e1000_hw.h"
+#include "igb.h"
+
+static int igb_realloc_rx_buffer_info(struct igb_ring *ring, bool pool_present)
+{
+	int size = pool_present ?
+		sizeof(*ring->rx_buffer_info_zc) * ring->count :
+		sizeof(*ring->rx_buffer_info) * ring->count;
+	void *buff_info = vmalloc(size);
+
+	if (!buff_info)
+		return -ENOMEM;
+
+	if (pool_present) {
+		vfree(ring->rx_buffer_info);
+		ring->rx_buffer_info = NULL;
+		ring->rx_buffer_info_zc = buff_info;
+	} else {
+		vfree(ring->rx_buffer_info_zc);
+		ring->rx_buffer_info_zc = NULL;
+		ring->rx_buffer_info = buff_info;
+	}
+
+	return 0;
+}
+
+static void igb_txrx_ring_disable(struct igb_adapter *adapter, u16 qid)
+{
+	struct igb_ring *tx_ring = adapter->tx_ring[qid];
+	struct igb_ring *rx_ring = adapter->rx_ring[qid];
+	struct e1000_hw *hw = &adapter->hw;
+
+	set_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags);
+
+	wr32(E1000_TXDCTL(tx_ring->reg_idx), 0);
+	wr32(E1000_RXDCTL(rx_ring->reg_idx), 0);
+
+	synchronize_net();
+
+	/* Rx/Tx share the same napi context. */
+	napi_disable(&rx_ring->q_vector->napi);
+
+	igb_clean_tx_ring(tx_ring);
+	igb_clean_rx_ring(rx_ring);
+
+	memset(&rx_ring->rx_stats, 0, sizeof(rx_ring->rx_stats));
+	memset(&tx_ring->tx_stats, 0, sizeof(tx_ring->tx_stats));
+}
+
+static void igb_txrx_ring_enable(struct igb_adapter *adapter, u16 qid)
+{
+	struct igb_ring *tx_ring = adapter->tx_ring[qid];
+	struct igb_ring *rx_ring = adapter->rx_ring[qid];
+
+	igb_configure_tx_ring(adapter, tx_ring);
+	igb_configure_rx_ring(adapter, rx_ring);
+
+	synchronize_net();
+
+	clear_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags);
+
+	/* call igb_desc_unused which always leaves
+	 * at least 1 descriptor unused to make sure
+	 * next_to_use != next_to_clean
+	 */
+	if (rx_ring->xsk_pool)
+		igb_alloc_rx_buffers_zc(rx_ring, rx_ring->xsk_pool,
+					igb_desc_unused(rx_ring));
+	else
+		igb_alloc_rx_buffers(rx_ring, igb_desc_unused(rx_ring));
+
+	/* Rx/Tx share the same napi context. */
+	napi_enable(&rx_ring->q_vector->napi);
+}
+
+struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter,
+				   struct igb_ring *ring)
+{
+	int qid = ring->queue_index;
+	struct xsk_buff_pool *pool;
+
+	pool = xsk_get_pool_from_qid(adapter->netdev, qid);
+
+	if (!igb_xdp_is_enabled(adapter))
+		return NULL;
+
+	return (pool && pool->dev) ? pool : NULL;
+}
+
+static int igb_xsk_pool_enable(struct igb_adapter *adapter,
+			       struct xsk_buff_pool *pool,
+			       u16 qid)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct igb_ring *rx_ring;
+	bool if_running;
+	int err;
+
+	if (qid >= adapter->num_rx_queues)
+		return -EINVAL;
+
+	if (qid >= netdev->real_num_rx_queues ||
+	    qid >= netdev->real_num_tx_queues)
+		return -EINVAL;
+
+	err = xsk_pool_dma_map(pool, &adapter->pdev->dev, IGB_RX_DMA_ATTR);
+	if (err)
+		return err;
+
+	rx_ring = adapter->rx_ring[qid];
+	if_running = netif_running(adapter->netdev) && igb_xdp_is_enabled(adapter);
+	if (if_running)
+		igb_txrx_ring_disable(adapter, qid);
+
+	if (if_running) {
+		err = igb_realloc_rx_buffer_info(rx_ring, true);
+		if (!err) {
+			igb_txrx_ring_enable(adapter, qid);
+			/* Kick start the NAPI context so that receiving will start */
+			err = igb_xsk_wakeup(adapter->netdev, qid, XDP_WAKEUP_RX);
+		}
+
+		if (err) {
+			xsk_pool_dma_unmap(pool, IGB_RX_DMA_ATTR);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int igb_xsk_pool_disable(struct igb_adapter *adapter, u16 qid)
+{
+	struct xsk_buff_pool *pool;
+	struct igb_ring *rx_ring;
+	bool if_running;
+	int err;
+
+	pool = xsk_get_pool_from_qid(adapter->netdev, qid);
+	if (!pool)
+		return -EINVAL;
+
+	rx_ring = adapter->rx_ring[qid];
+	if_running = netif_running(adapter->netdev) && igb_xdp_is_enabled(adapter);
+	if (if_running)
+		igb_txrx_ring_disable(adapter, qid);
+
+	xsk_pool_dma_unmap(pool, IGB_RX_DMA_ATTR);
+
+	if (if_running) {
+		err = igb_realloc_rx_buffer_info(rx_ring, false);
+		if (err)
+			return err;
+
+		igb_txrx_ring_enable(adapter, qid);
+	}
+
+	return 0;
+}
+
+int igb_xsk_pool_setup(struct igb_adapter *adapter,
+		       struct xsk_buff_pool *pool,
+		       u16 qid)
+{
+	return pool ? igb_xsk_pool_enable(adapter, pool, qid) :
+		igb_xsk_pool_disable(adapter, qid);
+}
+
+static u16 igb_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
+			     union e1000_adv_rx_desc *rx_desc, u16 count)
+{
+	dma_addr_t dma;
+	u16 buffs;
+	int i;
+
+	/* nothing to do */
+	if (!count)
+		return 0;
+
+	buffs = xsk_buff_alloc_batch(pool, xdp, count);
+	for (i = 0; i < buffs; i++) {
+		dma = xsk_buff_xdp_get_dma(*xdp);
+		rx_desc->read.pkt_addr = cpu_to_le64(dma);
+		rx_desc->wb.upper.length = 0;
+
+		rx_desc++;
+		xdp++;
+	}
+
+	return buffs;
+}
+
+bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring,
+			     struct xsk_buff_pool *xsk_pool, u16 count)
+{
+	u32 nb_buffs_extra = 0, nb_buffs = 0;
+	union e1000_adv_rx_desc *rx_desc;
+	u16 ntu = rx_ring->next_to_use;
+	u16 total_count = count;
+	struct xdp_buff **xdp;
+
+	rx_desc = IGB_RX_DESC(rx_ring, ntu);
+	xdp = &rx_ring->rx_buffer_info_zc[ntu];
+
+	if (ntu + count >= rx_ring->count) {
+		nb_buffs_extra = igb_fill_rx_descs(xsk_pool, xdp, rx_desc,
+						   rx_ring->count - ntu);
+		if (nb_buffs_extra != rx_ring->count - ntu) {
+			ntu += nb_buffs_extra;
+			goto exit;
+		}
+		rx_desc = IGB_RX_DESC(rx_ring, 0);
+		xdp = rx_ring->rx_buffer_info_zc;
+		ntu = 0;
+		count -= nb_buffs_extra;
+	}
+
+	nb_buffs = igb_fill_rx_descs(xsk_pool, xdp, rx_desc, count);
+	ntu += nb_buffs;
+	if (ntu == rx_ring->count)
+		ntu = 0;
+
+	/* clear the length for the next_to_use descriptor */
+	rx_desc = IGB_RX_DESC(rx_ring, ntu);
+	rx_desc->wb.upper.length = 0;
+
+exit:
+	if (rx_ring->next_to_use != ntu) {
+		rx_ring->next_to_use = ntu;
+
+		/* Force memory writes to complete before letting h/w
+		 * know there are new descriptors to fetch.  (Only
+		 * applicable for weak-ordered memory model archs,
+		 * such as IA-64).
+		 */
+		wmb();
+		writel(ntu, rx_ring->tail);
+	}
+
+	return total_count == (nb_buffs + nb_buffs_extra);
+}
+
+void igb_clean_rx_ring_zc(struct igb_ring *rx_ring)
+{
+	u16 ntc = rx_ring->next_to_clean;
+	u16 ntu = rx_ring->next_to_use;
+
+	while (ntc != ntu) {
+		struct xdp_buff *xdp = rx_ring->rx_buffer_info_zc[ntc];
+
+		xsk_buff_free(xdp);
+		ntc++;
+		if (ntc >= rx_ring->count)
+			ntc = 0;
+	}
+}
+
+static struct sk_buff *igb_construct_skb_zc(struct igb_ring *rx_ring,
+					    struct xdp_buff *xdp,
+					    ktime_t timestamp)
+{
+	unsigned int totalsize = xdp->data_end - xdp->data_meta;
+	unsigned int metasize = xdp->data - xdp->data_meta;
+	struct sk_buff *skb;
+
+	net_prefetch(xdp->data_meta);
+
+	/* allocate a skb to store the frags */
+	skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize);
+	if (unlikely(!skb))
+		return NULL;
+
+	if (timestamp)
+		skb_hwtstamps(skb)->hwtstamp = timestamp;
+
+	memcpy(__skb_put(skb, totalsize), xdp->data_meta,
+	       ALIGN(totalsize, sizeof(long)));
+
+	if (metasize) {
+		skb_metadata_set(skb, metasize);
+		__skb_pull(skb, metasize);
+	}
+
+	return skb;
+}
+
+static int igb_run_xdp_zc(struct igb_adapter *adapter, struct igb_ring *rx_ring,
+			  struct xdp_buff *xdp, struct xsk_buff_pool *xsk_pool,
+			  struct bpf_prog *xdp_prog)
+{
+	int err, result = IGB_XDP_PASS;
+	u32 act;
+
+	prefetchw(xdp->data_hard_start); /* xdp_frame write */
+
+	act = bpf_prog_run_xdp(xdp_prog, xdp);
+
+	if (likely(act == XDP_REDIRECT)) {
+		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
+		if (!err)
+			return IGB_XDP_REDIR;
+
+		if (xsk_uses_need_wakeup(xsk_pool) &&
+		    err == -ENOBUFS)
+			result = IGB_XDP_EXIT;
+		else
+			result = IGB_XDP_CONSUMED;
+		goto out_failure;
+	}
+
+	switch (act) {
+	case XDP_PASS:
+		break;
+	case XDP_TX:
+		result = igb_xdp_xmit_back(adapter, xdp);
+		if (result == IGB_XDP_CONSUMED)
+			goto out_failure;
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(adapter->netdev, xdp_prog, act);
+		fallthrough;
+	case XDP_ABORTED:
+out_failure:
+		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
+		fallthrough;
+	case XDP_DROP:
+		result = IGB_XDP_CONSUMED;
+		break;
+	}
+
+	return result;
+}
+
+int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector,
+			struct xsk_buff_pool *xsk_pool, const int budget)
+{
+	struct igb_adapter *adapter = q_vector->adapter;
+	unsigned int total_bytes = 0, total_packets = 0;
+	struct igb_ring *rx_ring = q_vector->rx.ring;
+	u32 ntc = rx_ring->next_to_clean;
+	struct bpf_prog *xdp_prog;
+	unsigned int xdp_xmit = 0;
+	bool failure = false;
+	u16 entries_to_alloc;
+	struct sk_buff *skb;
+
+	/* xdp_prog cannot be NULL in the ZC path */
+	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
+
+	while (likely(total_packets < budget)) {
+		union e1000_adv_rx_desc *rx_desc;
+		ktime_t timestamp = 0;
+		struct xdp_buff *xdp;
+		unsigned int size;
+		int xdp_res = 0;
+
+		rx_desc = IGB_RX_DESC(rx_ring, ntc);
+		size = le16_to_cpu(rx_desc->wb.upper.length);
+		if (!size)
+			break;
+
+		/* This memory barrier is needed to keep us from reading
+		 * any other fields out of the rx_desc until we know the
+		 * descriptor has been written back
+		 */
+		dma_rmb();
+
+		xdp = rx_ring->rx_buffer_info_zc[ntc];
+		xsk_buff_set_size(xdp, size);
+		xsk_buff_dma_sync_for_cpu(xdp);
+
+		/* pull rx packet timestamp if available and valid */
+		if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
+			int ts_hdr_len;
+
+			ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector,
+							 xdp->data,
+							 &timestamp);
+
+			xdp->data += ts_hdr_len;
+			xdp->data_meta += ts_hdr_len;
+			size -= ts_hdr_len;
+		}
+
+		xdp_res = igb_run_xdp_zc(adapter, rx_ring, xdp, xsk_pool,
+					 xdp_prog);
+
+		if (xdp_res) {
+			if (likely(xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR))) {
+				xdp_xmit |= xdp_res;
+			} else if (xdp_res == IGB_XDP_EXIT) {
+				failure = true;
+				break;
+			} else if (xdp_res == IGB_XDP_CONSUMED) {
+				xsk_buff_free(xdp);
+			}
+
+			total_packets++;
+			total_bytes += size;
+			ntc++;
+			if (ntc == rx_ring->count)
+				ntc = 0;
+			continue;
+		}
+
+		skb = igb_construct_skb_zc(rx_ring, xdp, timestamp);
+
+		/* exit if we failed to retrieve a buffer */
+		if (!skb) {
+			rx_ring->rx_stats.alloc_failed++;
+			set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
+			break;
+		}
+
+		xsk_buff_free(xdp);
+		ntc++;
+		if (ntc == rx_ring->count)
+			ntc = 0;
+
+		if (eth_skb_pad(skb))
+			continue;
+
+		/* probably a little skewed due to removing CRC */
+		total_bytes += skb->len;
+
+		/* populate checksum, timestamp, VLAN, and protocol */
+		igb_process_skb_fields(rx_ring, rx_desc, skb);
+
+		napi_gro_receive(&q_vector->napi, skb);
+
+		/* update budget accounting */
+		total_packets++;
+	}
+
+	rx_ring->next_to_clean = ntc;
+
+	if (xdp_xmit)
+		igb_finalize_xdp(adapter, xdp_xmit);
+
+	igb_update_rx_stats(q_vector, total_packets, total_bytes);
+
+	entries_to_alloc = igb_desc_unused(rx_ring);
+	if (entries_to_alloc >= IGB_RX_BUFFER_WRITE)
+		failure |= !igb_alloc_rx_buffers_zc(rx_ring, xsk_pool,
+						    entries_to_alloc);
+
+	if (xsk_uses_need_wakeup(xsk_pool)) {
+		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
+			xsk_set_rx_need_wakeup(xsk_pool);
+		else
+			xsk_clear_rx_need_wakeup(xsk_pool);
+
+		return (int)total_packets;
+	}
+	return failure ? budget : (int)total_packets;
+}
+
+bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool)
+{
+	unsigned int budget = igb_desc_unused(tx_ring);
+	u32 cmd_type, olinfo_status, nb_pkts, i = 0;
+	struct xdp_desc *descs = xsk_pool->tx_descs;
+	union e1000_adv_tx_desc *tx_desc = NULL;
+	struct igb_tx_buffer *tx_buffer_info;
+	unsigned int total_bytes = 0;
+	dma_addr_t dma;
+
+	if (!netif_carrier_ok(tx_ring->netdev))
+		return true;
+
+	if (test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags))
+		return true;
+
+	nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget);
+	if (!nb_pkts)
+		return true;
+
+	for (; i < nb_pkts; i++) {
+		dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);
+		xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len);
+
+		tx_buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
+		tx_buffer_info->bytecount = descs[i].len;
+		tx_buffer_info->type = IGB_TYPE_XSK;
+		tx_buffer_info->xdpf = NULL;
+		tx_buffer_info->gso_segs = 1;
+		tx_buffer_info->time_stamp = jiffies;
+
+		tx_desc = IGB_TX_DESC(tx_ring, tx_ring->next_to_use);
+		tx_desc->read.buffer_addr = cpu_to_le64(dma);
+
+		/* put descriptor type bits */
+		cmd_type = E1000_ADVTXD_DTYP_DATA | E1000_ADVTXD_DCMD_DEXT |
+			   E1000_ADVTXD_DCMD_IFCS;
+		olinfo_status = descs[i].len << E1000_ADVTXD_PAYLEN_SHIFT;
+
+		/* FIXME: This sets the Report Status (RS) bit for every
+		 * descriptor. One nice to have optimization would be to set it
+		 * only for the last descriptor in the whole batch. See Intel
+		 * ice driver for an example on how to do it.
+		 */
+		cmd_type |= descs[i].len | IGB_TXD_DCMD;
+		tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
+		tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
+
+		total_bytes += descs[i].len;
+
+		tx_ring->next_to_use++;
+		tx_buffer_info->next_to_watch = tx_desc;
+		if (tx_ring->next_to_use == tx_ring->count)
+			tx_ring->next_to_use = 0;
+	}
+
+	netdev_tx_sent_queue(txring_txq(tx_ring), total_bytes);
+	igb_xdp_ring_update_tail(tx_ring);
+
+	return nb_pkts < budget;
+}
+
+int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
+{
+	struct igb_adapter *adapter = netdev_priv(dev);
+	struct e1000_hw *hw = &adapter->hw;
+	struct igb_ring *ring;
+	u32 eics = 0;
+
+	if (test_bit(__IGB_DOWN, &adapter->state))
+		return -ENETDOWN;
+
+	if (!igb_xdp_is_enabled(adapter))
+		return -EINVAL;
+
+	if (qid >= adapter->num_tx_queues)
+		return -EINVAL;
+
+	ring = adapter->tx_ring[qid];
+
+	if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags))
+		return -ENETDOWN;
+
+	if (!READ_ONCE(ring->xsk_pool))
+		return -EINVAL;
+
+	if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) {
+		/* Cause software interrupt */
+		if (adapter->flags & IGB_FLAG_HAS_MSIX) {
+			eics |= ring->q_vector->eims_value;
+			wr32(E1000_EICS, eics);
+		} else {
+			wr32(E1000_ICS, E1000_ICS_RXDMT0);
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c
index 83b97989a6bd..9c08ebfad804 100644
--- a/drivers/net/ethernet/intel/igbvf/ethtool.c
+++ b/drivers/net/ethernet/intel/igbvf/ethtool.c
@@ -30,10 +30,12 @@ static const struct igbvf_stats igbvf_gstrings_stats[] = {
 	{ "rx_bytes", IGBVF_STAT(stats.gorc, stats.base_gorc) },
 	{ "tx_bytes", IGBVF_STAT(stats.gotc, stats.base_gotc) },
 	{ "multicast", IGBVF_STAT(stats.mprc, stats.base_mprc) },
-	{ "lbrx_bytes", IGBVF_STAT(stats.gorlbc, stats.base_gorlbc) },
 	{ "lbrx_packets", IGBVF_STAT(stats.gprlbc, stats.base_gprlbc) },
+	{ "lbtx_packets", IGBVF_STAT(stats.gptlbc, stats.base_gptlbc) },
+	{ "lbrx_bytes", IGBVF_STAT(stats.gorlbc, stats.base_gorlbc) },
+	{ "lbtx_bytes", IGBVF_STAT(stats.gotlbc, stats.base_gotlbc) },
 	{ "tx_restart_queue", IGBVF_STAT(restart_queue, zero_base) },
-	{ "rx_long_byte_count", IGBVF_STAT(stats.gorc, stats.base_gorc) },
+	{ "tx_timeout_count", IGBVF_STAT(tx_timeout_count, zero_base) },
 	{ "rx_csum_offload_good", IGBVF_STAT(hw_csum_good, zero_base) },
 	{ "rx_csum_offload_errors", IGBVF_STAT(hw_csum_err, zero_base) },
 	{ "rx_header_split", IGBVF_STAT(rx_hdr_split, zero_base) },
diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h
index ca6e44245a7b..da8e1fd47301 100644
--- a/drivers/net/ethernet/intel/igbvf/igbvf.h
+++ b/drivers/net/ethernet/intel/igbvf/igbvf.h
@@ -154,7 +154,6 @@ struct igbvf_ring {
 /* board specific private data structure */
 struct igbvf_adapter {
 	struct timer_list watchdog_timer;
-	struct timer_list blink_timer;
 
 	struct work_struct reset_task;
 	struct work_struct watchdog_task;
@@ -162,10 +161,7 @@ struct igbvf_adapter {
 	const struct igbvf_info *ei;
 
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
-	u32 bd_number;
 	u32 rx_buffer_len;
-	u32 polling_interval;
-	u16 mng_vlan_id;
 	u16 link_speed;
 	u16 link_duplex;
 
@@ -183,9 +179,6 @@ struct igbvf_adapter {
 	unsigned int restart_queue;
 	u32 txd_cmd;
 
-	u32 tx_int_delay;
-	u32 tx_abs_int_delay;
-
 	unsigned int total_tx_bytes;
 	unsigned int total_tx_packets;
 	unsigned int total_rx_bytes;
@@ -193,23 +186,15 @@ struct igbvf_adapter {
 
 	/* Tx stats */
 	u32 tx_timeout_count;
-	u32 tx_fifo_head;
-	u32 tx_head_addr;
-	u32 tx_fifo_size;
-	u32 tx_dma_failed;
 
 	/* Rx */
 	struct igbvf_ring *rx_ring;
 
-	u32 rx_int_delay;
-	u32 rx_abs_int_delay;
-
 	/* Rx stats */
 	u64 hw_csum_err;
 	u64 hw_csum_good;
 	u64 rx_hdr_split;
 	u32 alloc_rx_buff_failed;
-	u32 rx_dma_failed;
 
 	unsigned int rx_ps_hdr_size;
 	u32 max_frame_size;
@@ -229,26 +214,14 @@ struct igbvf_adapter {
 	struct e1000_vf_stats stats;
 	u64 zero_base;
 
-	struct igbvf_ring test_tx_ring;
-	struct igbvf_ring test_rx_ring;
-	u32 test_icr;
-
 	u32 msg_enable;
 	struct msix_entry *msix_entries;
-	int int_mode;
 	u32 eims_enable_mask;
 	u32 eims_other;
-	u32 int_counter0;
-	u32 int_counter1;
 
-	u32 eeprom_wol;
 	u32 wol;
 	u32 pba;
 
-	bool fc_autoneg;
-
-	unsigned long led_status;
-
 	unsigned int flags;
 	unsigned long last_reset;
 };
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 02044aa2181b..ac57212ab02b 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -855,8 +855,6 @@ static irqreturn_t igbvf_msix_other(int irq, void *data)
 	struct igbvf_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 
-	adapter->int_counter1++;
-
 	hw->mac.get_link_status = 1;
 	if (!test_bit(__IGBVF_DOWN, &adapter->state))
 		mod_timer(&adapter->watchdog_timer, jiffies + 1);
@@ -899,8 +897,6 @@ static irqreturn_t igbvf_intr_msix_rx(int irq, void *data)
 	struct net_device *netdev = data;
 	struct igbvf_adapter *adapter = netdev_priv(netdev);
 
-	adapter->int_counter0++;
-
 	/* Write the ITR value calculated at the end of the
 	 * previous interrupt.
 	 */
@@ -1239,7 +1235,7 @@ static int igbvf_vlan_rx_add_vid(struct net_device *netdev,
 	spin_lock_bh(&hw->mbx_lock);
 
 	if (hw->mac.ops.set_vfta(hw, vid, true)) {
-		dev_warn(&adapter->pdev->dev, "Vlan id %d\n is not added", vid);
+		dev_warn(&adapter->pdev->dev, "Vlan id %d is not added\n", vid);
 		spin_unlock_bh(&hw->mbx_lock);
 		return -EINVAL;
 	}
@@ -1592,7 +1588,7 @@ void igbvf_down(struct igbvf_adapter *adapter)
 
 	igbvf_irq_disable(adapter);
 
-	del_timer_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
 
 	/* record the stats before reset*/
 	igbvf_update_stats(adapter);
@@ -1633,10 +1629,6 @@ static int igbvf_sw_init(struct igbvf_adapter *adapter)
 	adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
 	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
 
-	adapter->tx_int_delay = 8;
-	adapter->tx_abs_int_delay = 32;
-	adapter->rx_int_delay = 0;
-	adapter->rx_abs_int_delay = 8;
 	adapter->requested_itr = 3;
 	adapter->current_itr = IGBVF_START_ITR;
 
@@ -1900,7 +1892,8 @@ static bool igbvf_has_link(struct igbvf_adapter *adapter)
  **/
 static void igbvf_watchdog(struct timer_list *t)
 {
-	struct igbvf_adapter *adapter = from_timer(adapter, t, watchdog_timer);
+	struct igbvf_adapter *adapter = timer_container_of(adapter, t,
+							   watchdog_timer);
 
 	/* Do the rest outside of interrupt context */
 	schedule_work(&adapter->watchdog_task);
@@ -2711,7 +2704,6 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct igbvf_adapter *adapter;
 	struct e1000_hw *hw;
 	const struct igbvf_info *ei = igbvf_info_tbl[ent->driver_data];
-	static int cards_found;
 	int err;
 
 	err = pci_enable_device_mem(pdev);
@@ -2783,8 +2775,6 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	netdev->watchdog_timeo = 5 * HZ;
 	strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name));
 
-	adapter->bd_number = cards_found++;
-
 	netdev->hw_features = NETIF_F_SG |
 			      NETIF_F_TSO |
 			      NETIF_F_TSO6 |
@@ -2912,7 +2902,7 @@ static void igbvf_remove(struct pci_dev *pdev)
 	 * disable it from being rescheduled.
 	 */
 	set_bit(__IGBVF_DOWN, &adapter->state);
-	del_timer_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
 
 	cancel_work_sync(&adapter->reset_task);
 	cancel_work_sync(&adapter->watchdog_task);
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index eac0f966e0e4..a427f05814c1 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -40,6 +40,12 @@ void igc_ethtool_set_ops(struct net_device *);
 
 #define IGC_MAX_TX_TSTAMP_REGS		4
 
+struct igc_fpe_t {
+	struct ethtool_mmsv mmsv;
+	u32 tx_min_frag_size;
+	bool tx_enabled;
+};
+
 enum igc_mac_filter_type {
 	IGC_MAC_FILTER_TYPE_DST = 0,
 	IGC_MAC_FILTER_TYPE_SRC
@@ -158,6 +164,7 @@ struct igc_ring {
 	bool launchtime_enable;         /* true if LaunchTime is enabled */
 	ktime_t last_tx_cycle;          /* end of the cycle with a launchtime transmission */
 	ktime_t last_ff_cycle;          /* Last cycle with an active first flag */
+	bool preemptible;		/* True if preemptible queue, false if express queue */
 
 	u32 start_time;
 	u32 end_time;
@@ -308,7 +315,7 @@ struct igc_adapter {
 	 */
 	spinlock_t ptp_tx_lock;
 	struct igc_tx_timestamp_request tx_tstamp[IGC_MAX_TX_TSTAMP_REGS];
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 	unsigned int ptp_flags;
 	/* System time value lock */
 	spinlock_t tmreg_lock;
@@ -319,6 +326,7 @@ struct igc_adapter {
 	struct timespec64 prev_ptp_time; /* Pre-reset PTP clock */
 	ktime_t ptp_reset_start; /* Reset time in clock mono */
 	struct system_time_snapshot snapshot;
+	struct mutex ptm_lock; /* Only allow one PTM transaction at a time */
 
 	char fw_version[32];
 
@@ -332,9 +340,12 @@ struct igc_adapter {
 		struct timespec64 period;
 	} perout[IGC_N_PEROUT];
 
+	struct igc_fpe_t fpe;
+
 	/* LEDs */
 	struct mutex led_mutex;
 	struct igc_led_classdev *leds;
+	bool leds_available;
 };
 
 void igc_up(struct igc_adapter *adapter);
@@ -386,19 +397,16 @@ extern char igc_driver_name[];
 #define IGC_FLAG_RX_LEGACY		BIT(16)
 #define IGC_FLAG_TSN_QBV_ENABLED	BIT(17)
 #define IGC_FLAG_TSN_QAV_ENABLED	BIT(18)
-#define IGC_FLAG_TSN_LEGACY_ENABLED	BIT(19)
+#define IGC_FLAG_TSN_PREEMPT_ENABLED	BIT(19)
+#define IGC_FLAG_TSN_REVERSE_TXQ_PRIO	BIT(20)
 
 #define IGC_FLAG_TSN_ANY_ENABLED				\
 	(IGC_FLAG_TSN_QBV_ENABLED | IGC_FLAG_TSN_QAV_ENABLED |	\
-	 IGC_FLAG_TSN_LEGACY_ENABLED)
+	 IGC_FLAG_TSN_PREEMPT_ENABLED)
 
 #define IGC_FLAG_RSS_FIELD_IPV4_UDP	BIT(6)
 #define IGC_FLAG_RSS_FIELD_IPV6_UDP	BIT(7)
 
-#define IGC_MRQC_ENABLE_RSS_MQ		0x00000002
-#define IGC_MRQC_RSS_FIELD_IPV4_UDP	0x00400000
-#define IGC_MRQC_RSS_FIELD_IPV6_UDP	0x00800000
-
 /* RX-desc Write-Back format RSS Type's */
 enum igc_rss_type_num {
 	IGC_RSS_TYPE_NO_HASH		= 0,
@@ -477,12 +485,30 @@ static inline u32 igc_rss_type(const union igc_adv_rx_desc *rx_desc)
  *           descriptors until either it has this many to write back, or the
  *           ITR timer expires.
  */
-#define IGC_RX_PTHRESH			8
-#define IGC_RX_HTHRESH			8
-#define IGC_TX_PTHRESH			8
-#define IGC_TX_HTHRESH			1
-#define IGC_RX_WTHRESH			4
-#define IGC_TX_WTHRESH			16
+#define IGC_RXDCTL_PTHRESH		8
+#define IGC_RXDCTL_HTHRESH		8
+#define IGC_RXDCTL_WTHRESH		4
+/* Ena specific Rx Queue */
+#define IGC_RXDCTL_QUEUE_ENABLE		0x02000000
+/* Receive Software Flush */
+#define IGC_RXDCTL_SWFLUSH		0x04000000
+
+#define IGC_TXDCTL_PTHRESH_MASK		GENMASK(4, 0)
+#define IGC_TXDCTL_HTHRESH_MASK		GENMASK(12, 8)
+#define IGC_TXDCTL_WTHRESH_MASK		GENMASK(20, 16)
+#define IGC_TXDCTL_QUEUE_ENABLE_MASK	GENMASK(25, 25)
+#define IGC_TXDCTL_SWFLUSH_MASK		GENMASK(26, 26)
+#define IGC_TXDCTL_PRIORITY_MASK	GENMASK(27, 27)
+
+#define IGC_TXDCTL_PTHRESH(x)		FIELD_PREP(IGC_TXDCTL_PTHRESH_MASK, (x))
+#define IGC_TXDCTL_HTHRESH(x)		FIELD_PREP(IGC_TXDCTL_HTHRESH_MASK, (x))
+#define IGC_TXDCTL_WTHRESH(x)		FIELD_PREP(IGC_TXDCTL_WTHRESH_MASK, (x))
+/* Ena specific Tx Queue */
+#define IGC_TXDCTL_QUEUE_ENABLE		FIELD_PREP(IGC_TXDCTL_QUEUE_ENABLE_MASK, 1)
+/* Transmit Software Flush */
+#define IGC_TXDCTL_SWFLUSH		FIELD_PREP(IGC_TXDCTL_SWFLUSH_MASK, 1)
+#define IGC_TXDCTL_PRIORITY(x)		FIELD_PREP(IGC_TXDCTL_PRIORITY_MASK, (x))
+#define IGC_TXDCTL_PRIORITY_HIGH	IGC_TXDCTL_PRIORITY(1)
 
 #define IGC_RX_DMA_ATTR \
 	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
@@ -577,6 +603,7 @@ struct igc_metadata_request {
 	struct xsk_tx_metadata *meta;
 	struct igc_ring *tx_ring;
 	u32 cmd_type;
+	u16 used_desc;
 };
 
 struct igc_q_vector {
@@ -605,6 +632,7 @@ enum igc_filter_match_flags {
 	IGC_FILTER_FLAG_DST_MAC_ADDR =	BIT(3),
 	IGC_FILTER_FLAG_USER_DATA =	BIT(4),
 	IGC_FILTER_FLAG_VLAN_ETYPE =	BIT(5),
+	IGC_FILTER_FLAG_DEFAULT_QUEUE = BIT(6),
 };
 
 struct igc_nfc_filter {
@@ -632,10 +660,14 @@ struct igc_nfc_rule {
 	bool flex;
 };
 
-/* IGC supports a total of 32 NFC rules: 16 MAC address based, 8 VLAN priority
- * based, 8 ethertype based and 32 Flex filter based rules.
+/* IGC supports a total of 65 NFC rules, listed below in order of priority:
+ *  - 16 MAC address based filtering rules (highest priority)
+ *  - 8 ethertype based filtering rules
+ *  - 32 Flex filter based filtering rules
+ *  - 8 VLAN priority based filtering rules
+ *  - 1 default queue rule (lowest priority)
  */
-#define IGC_MAX_RXNFC_RULES		64
+#define IGC_MAX_RXNFC_RULES		65
 
 struct igc_flex_filter {
 	u8 index;
@@ -734,14 +766,20 @@ struct igc_nfc_rule *igc_get_nfc_rule(struct igc_adapter *adapter,
 				      u32 location);
 int igc_add_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule);
 void igc_del_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule);
-
+void igc_disable_empty_addr_recv(struct igc_adapter *adapter);
+int igc_enable_empty_addr_recv(struct igc_adapter *adapter);
+struct igc_ring *igc_get_tx_ring(struct igc_adapter *adapter, int cpu);
+void igc_flush_tx_descriptors(struct igc_ring *ring);
 void igc_ptp_init(struct igc_adapter *adapter);
 void igc_ptp_reset(struct igc_adapter *adapter);
 void igc_ptp_suspend(struct igc_adapter *adapter);
 void igc_ptp_stop(struct igc_adapter *adapter);
 ktime_t igc_ptp_rx_pktstamp(struct igc_adapter *adapter, __le32 *buf);
-int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
-int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
+int igc_ptp_hwtstamp_get(struct net_device *netdev,
+			 struct kernel_hwtstamp_config *config);
+int igc_ptp_hwtstamp_set(struct net_device *netdev,
+			 struct kernel_hwtstamp_config *config,
+			 struct netlink_ext_ack *extack);
 void igc_ptp_tx_hang(struct igc_adapter *adapter);
 void igc_ptp_read(struct igc_adapter *adapter, struct timespec64 *ts);
 void igc_ptp_tx_tstamp_event(struct igc_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
index 9fae8bdec2a7..1613b562d17c 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.c
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -68,6 +68,10 @@ static s32 igc_init_nvm_params_base(struct igc_hw *hw)
 	u32 eecd = rd32(IGC_EECD);
 	u16 size;
 
+	/* failed to read reg and got all F's */
+	if (!(~eecd))
+		return -ENXIO;
+
 	size = FIELD_GET(IGC_EECD_SIZE_EX_MASK, eecd);
 
 	/* Added to a constant, "size" becomes the left-shift value
@@ -221,6 +225,8 @@ static s32 igc_get_invariants_base(struct igc_hw *hw)
 
 	/* NVM initialization */
 	ret_val = igc_init_nvm_params_base(hw);
+	if (ret_val)
+		goto out;
 	switch (hw->mac.type) {
 	case igc_i225:
 		ret_val = igc_init_nvm_params_i225(hw);
diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h
index bf8cdfbba9ff..eaf17cd031c3 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.h
+++ b/drivers/net/ethernet/intel/igc/igc_base.h
@@ -49,6 +49,7 @@ struct igc_adv_tx_context_desc {
 #define IGC_ADVTXD_DCMD_DEXT	0x20000000 /* Descriptor extension (1=Adv) */
 #define IGC_ADVTXD_DCMD_VLE	0x40000000 /* VLAN pkt enable */
 #define IGC_ADVTXD_DCMD_TSE	0x80000000 /* TCP Seg enable */
+#define IGC_ADVTXD_PAYLEN_MASK	0XFFFFC000 /* Adv desc PAYLEN mask */
 #define IGC_ADVTXD_PAYLEN_SHIFT	14 /* Adv desc PAYLEN shift */
 
 #define IGC_RAR_ENTRIES		16
@@ -85,14 +86,6 @@ union igc_adv_rx_desc {
 	} wb;  /* writeback */
 };
 
-/* Additional Transmit Descriptor Control definitions */
-#define IGC_TXDCTL_QUEUE_ENABLE	0x02000000 /* Ena specific Tx Queue */
-#define IGC_TXDCTL_SWFLUSH	0x04000000 /* Transmit Software Flush */
-
-/* Additional Receive Descriptor Control definitions */
-#define IGC_RXDCTL_QUEUE_ENABLE	0x02000000 /* Ena specific Rx Queue */
-#define IGC_RXDCTL_SWFLUSH		0x04000000 /* Receive Software Flush */
-
 /* SRRCTL bit definitions */
 #define IGC_SRRCTL_BSIZEPKT_MASK	GENMASK(6, 0)
 #define IGC_SRRCTL_BSIZEPKT(x)		FIELD_PREP(IGC_SRRCTL_BSIZEPKT_MASK, \
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 8e449904aa7d..498ba1522ca4 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -308,6 +308,8 @@
 #define IGC_TXD_DTYP_C		0x00000000 /* Context Descriptor */
 #define IGC_TXD_POPTS_IXSM	0x01       /* Insert IP checksum */
 #define IGC_TXD_POPTS_TXSM	0x02       /* Insert TCP/UDP checksum */
+#define IGC_TXD_POPTS_SMD_MASK	0x3000     /* Indicates whether it's SMD-V or SMD-R */
+
 #define IGC_TXD_CMD_EOP		0x01000000 /* End of Packet */
 #define IGC_TXD_CMD_IC		0x04000000 /* Insert Checksum */
 #define IGC_TXD_CMD_DEXT	0x20000000 /* Desc extension (0 = legacy) */
@@ -363,6 +365,8 @@
 #define IGC_SRRCTL_TIMER0SEL(timer)	(((timer) & 0x3) << 17)
 
 /* Receive Descriptor bit definitions */
+#define IGC_RXD_STAT_SMD_TYPE_V	0x01	/* SMD-V Packet */
+#define IGC_RXD_STAT_SMD_TYPE_R	0x02	/* SMD-R Packet */
 #define IGC_RXD_STAT_EOP	0x02	/* End of Packet */
 #define IGC_RXD_STAT_IXSM	0x04	/* Ignore checksum */
 #define IGC_RXD_STAT_UDPCS	0x10	/* UDP xsum calculated */
@@ -372,17 +376,22 @@
 #define IGC_RXDEXT_STATERR_LB	0x00040000
 
 /* Advanced Receive Descriptor bit definitions */
-#define IGC_RXDADV_STAT_TSIP	0x08000 /* timestamp in packet */
+#define IGC_RXDADV_STAT_SMD_TYPE_MASK	0x06000
+#define IGC_RXDADV_STAT_TSIP		0x08000 /* timestamp in packet */
 
 #define IGC_RXDEXT_STATERR_L4E		0x20000000
 #define IGC_RXDEXT_STATERR_IPE		0x40000000
 #define IGC_RXDEXT_STATERR_RXE		0x80000000
 
+#define IGC_MRQC_ENABLE_RSS_MQ		0x00000002
 #define IGC_MRQC_RSS_FIELD_IPV4_TCP	0x00010000
 #define IGC_MRQC_RSS_FIELD_IPV4		0x00020000
 #define IGC_MRQC_RSS_FIELD_IPV6_TCP_EX	0x00040000
 #define IGC_MRQC_RSS_FIELD_IPV6		0x00100000
 #define IGC_MRQC_RSS_FIELD_IPV6_TCP	0x00200000
+#define IGC_MRQC_RSS_FIELD_IPV4_UDP	0x00400000
+#define IGC_MRQC_RSS_FIELD_IPV6_UDP	0x00800000
+#define IGC_MRQC_DEFAULT_QUEUE_MASK	GENMASK(5, 3)
 
 /* Header split receive */
 #define IGC_RFCTL_IPV6_EX_DIS	0x00010000
@@ -396,11 +405,47 @@
 #define IGC_RCTL_PMCF		0x00800000 /* pass MAC control frames */
 #define IGC_RCTL_SECRC		0x04000000 /* Strip Ethernet CRC */
 
-#define I225_RXPBSIZE_DEFAULT	0x000000A2 /* RXPBSIZE default */
-#define I225_TXPBSIZE_DEFAULT	0x04000014 /* TXPBSIZE default */
-#define IGC_RXPBS_CFG_TS_EN	0x80000000 /* Timestamp in Rx buffer */
-
-#define IGC_TXPBSIZE_TSN	0x04145145 /* 5k bytes buffer for each queue */
+/* Mask for RX packet buffer size */
+#define IGC_RXPBSIZE_EXP_MASK		GENMASK(5, 0)
+#define IGC_BMC2OSPBSIZE_MASK		GENMASK(11, 6)
+#define IGC_RXPBSIZE_BE_MASK		GENMASK(17, 12)
+/* Mask for timestamp in RX buffer */
+#define IGC_RXPBS_CFG_TS_EN_MASK	GENMASK(31, 31)
+/* High-priority RX packet buffer size (KB). Used for Express traffic when preemption is enabled */
+#define IGC_RXPBSIZE_EXP(x)		FIELD_PREP(IGC_RXPBSIZE_EXP_MASK, (x))
+/* BMC to OS packet buffer size in KB */
+#define IGC_BMC2OSPBSIZE(x)		FIELD_PREP(IGC_BMC2OSPBSIZE_MASK, (x))
+/* Low-priority RX packet buffer size (KB). Used for BE traffic when preemption is enabled */
+#define IGC_RXPBSIZE_BE(x)		FIELD_PREP(IGC_RXPBSIZE_BE_MASK, (x))
+/* Enable RX packet buffer for timestamp descriptor, saving 16 bytes per packet if set */
+#define IGC_RXPBS_CFG_TS_EN		FIELD_PREP(IGC_RXPBS_CFG_TS_EN_MASK, 1)
+/* Default value following I225/I226 SW User Manual Section 8.3.1 */
+#define IGC_RXPBSIZE_EXP_BMC_DEFAULT ( \
+	IGC_RXPBSIZE_EXP(34) | IGC_BMC2OSPBSIZE(2))
+#define IGC_RXPBSIZE_EXP_BMC_BE_TSN ( \
+	IGC_RXPBSIZE_EXP(15) | IGC_BMC2OSPBSIZE(2) | IGC_RXPBSIZE_BE(15))
+
+/* Mask for TX packet buffer size */
+#define IGC_TXPB0SIZE_MASK		GENMASK(5, 0)
+#define IGC_TXPB1SIZE_MASK		GENMASK(11, 6)
+#define IGC_TXPB2SIZE_MASK		GENMASK(17, 12)
+#define IGC_TXPB3SIZE_MASK		GENMASK(23, 18)
+/* Mask for OS to BMC packet buffer size */
+#define IGC_OS2BMCPBSIZE_MASK		GENMASK(29, 24)
+/* TX Packet buffer size in KB */
+#define IGC_TXPB0SIZE(x)		FIELD_PREP(IGC_TXPB0SIZE_MASK, (x))
+#define IGC_TXPB1SIZE(x)		FIELD_PREP(IGC_TXPB1SIZE_MASK, (x))
+#define IGC_TXPB2SIZE(x)		FIELD_PREP(IGC_TXPB2SIZE_MASK, (x))
+#define IGC_TXPB3SIZE(x)		FIELD_PREP(IGC_TXPB3SIZE_MASK, (x))
+/* OS to BMC packet buffer size in KB */
+#define IGC_OS2BMCPBSIZE(x)		FIELD_PREP(IGC_OS2BMCPBSIZE_MASK, (x))
+/* Default value following I225/I226 SW User Manual Section 8.3.2 */
+#define IGC_TXPBSIZE_DEFAULT ( \
+	IGC_TXPB0SIZE(20) | IGC_TXPB1SIZE(0) | IGC_TXPB2SIZE(0) | \
+	IGC_TXPB3SIZE(0) | IGC_OS2BMCPBSIZE(4))
+#define IGC_TXPBSIZE_TSN ( \
+	IGC_TXPB0SIZE(7) | IGC_TXPB1SIZE(7) | IGC_TXPB2SIZE(7) | \
+	IGC_TXPB3SIZE(7) | IGC_OS2BMCPBSIZE(4))
 
 #define IGC_DTXMXPKTSZ_TSN	0x19 /* 1600 bytes of max TX DMA packet size */
 #define IGC_DTXMXPKTSZ_DEFAULT	0x98 /* 9728-byte Jumbo frames */
@@ -539,12 +584,15 @@
 
 /* Transmit Scheduling */
 #define IGC_TQAVCTRL_TRANSMIT_MODE_TSN	0x00000001
+#define IGC_TQAVCTRL_PREEMPT_ENA	0x00000002
 #define IGC_TQAVCTRL_ENHANCED_QAV	0x00000008
 #define IGC_TQAVCTRL_FUTSCDDIS		0x00000080
+#define IGC_TQAVCTRL_MIN_FRAG_MASK	0x0000C000
 
 #define IGC_TXQCTL_QUEUE_MODE_LAUNCHT	0x00000001
 #define IGC_TXQCTL_STRICT_CYCLE		0x00000002
 #define IGC_TXQCTL_STRICT_END		0x00000004
+#define IGC_TXQCTL_PREEMPTIBLE		0x00000008
 #define IGC_TXQCTL_QAV_SEL_MASK		0x000000C0
 #define IGC_TXQCTL_QAV_SEL_CBS0		0x00000080
 #define IGC_TXQCTL_QAV_SEL_CBS1		0x000000C0
@@ -574,7 +622,10 @@
 #define IGC_PTM_CTRL_SHRT_CYC(usec)	(((usec) & 0x3f) << 2)
 #define IGC_PTM_CTRL_PTM_TO(usec)	(((usec) & 0xff) << 8)
 
-#define IGC_PTM_SHORT_CYC_DEFAULT	1   /* Default short cycle interval */
+/* A short cycle time of 1us theoretically should work, but appears to be too
+ * short in practice.
+ */
+#define IGC_PTM_SHORT_CYC_DEFAULT	4   /* Default short cycle interval */
 #define IGC_PTM_CYC_TIME_DEFAULT	5   /* Default PTM cycle time */
 #define IGC_PTM_TIMEOUT_DEFAULT		255 /* Default timeout for PTM errors */
 
@@ -593,6 +644,7 @@
 #define IGC_PTM_STAT_T4M1_OVFL		BIT(3) /* T4 minus T1 overflow */
 #define IGC_PTM_STAT_ADJUST_1ST		BIT(4) /* 1588 timer adjusted during 1st PTM cycle */
 #define IGC_PTM_STAT_ADJUST_CYC		BIT(5) /* 1588 timer adjusted during non-1st PTM cycle */
+#define IGC_PTM_STAT_ALL		GENMASK(5, 0) /* Used to clear all status */
 
 /* PCIe PTM Cycle Control */
 #define IGC_PTM_CYCLE_CTRL_CYC_TIME(msec)	((msec) & 0x3ff) /* PTM Cycle Time (msec) */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 817838677817..e94c1922b97a 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -8,6 +8,7 @@
 
 #include "igc.h"
 #include "igc_diag.h"
+#include "igc_tsn.h"
 
 /* forward declaration */
 struct igc_stats {
@@ -121,9 +122,11 @@ static const char igc_gstrings_test[][ETH_GSTRING_LEN] = {
 #define IGC_STATS_LEN \
 	(IGC_GLOBAL_STATS_LEN + IGC_NETDEV_STATS_LEN + IGC_QUEUE_STATS_LEN)
 
+#define IGC_PRIV_FLAGS_LEGACY_RX		BIT(0)
+#define IGC_PRIV_FLAGS_REVERSE_TSN_TXQ_PRIO	BIT(1)
 static const char igc_priv_flags_strings[][ETH_GSTRING_LEN] = {
-#define IGC_PRIV_FLAGS_LEGACY_RX	BIT(0)
 	"legacy-rx",
+	"reverse-tsn-txq-prio",
 };
 
 #define IGC_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igc_priv_flags_strings)
@@ -624,11 +627,11 @@ igc_ethtool_set_ringparam(struct net_device *netdev,
 	}
 
 	if (adapter->num_tx_queues > adapter->num_rx_queues)
-		temp_ring = vmalloc(array_size(sizeof(struct igc_ring),
-					       adapter->num_tx_queues));
+		temp_ring = vmalloc_array(adapter->num_tx_queues,
+					  sizeof(struct igc_ring));
 	else
-		temp_ring = vmalloc(array_size(sizeof(struct igc_ring),
-					       adapter->num_rx_queues));
+		temp_ring = vmalloc_array(adapter->num_rx_queues,
+					  sizeof(struct igc_ring));
 
 	if (!temp_ring) {
 		err = -ENOMEM;
@@ -807,7 +810,7 @@ static int igc_ethtool_get_sset_count(struct net_device *netdev, int sset)
 	case ETH_SS_PRIV_FLAGS:
 		return IGC_PRIV_FLAGS_STR_LEN;
 	default:
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 }
 
@@ -1044,9 +1047,11 @@ static int igc_ethtool_get_nfc_rules(struct igc_adapter *adapter,
 	return 0;
 }
 
-static int igc_ethtool_get_rss_hash_opts(struct igc_adapter *adapter,
-					 struct ethtool_rxnfc *cmd)
+static int igc_ethtool_get_rxfh_fields(struct net_device *dev,
+				       struct ethtool_rxfh_fields *cmd)
 {
+	struct igc_adapter *adapter = netdev_priv(dev);
+
 	cmd->data = 0;
 
 	/* Report default options for RSS on igc */
@@ -1086,15 +1091,19 @@ static int igc_ethtool_get_rss_hash_opts(struct igc_adapter *adapter,
 	return 0;
 }
 
+static u32 igc_ethtool_get_rx_ring_count(struct net_device *dev)
+{
+	struct igc_adapter *adapter = netdev_priv(dev);
+
+	return adapter->num_rx_queues;
+}
+
 static int igc_ethtool_get_rxnfc(struct net_device *dev,
 				 struct ethtool_rxnfc *cmd, u32 *rule_locs)
 {
 	struct igc_adapter *adapter = netdev_priv(dev);
 
 	switch (cmd->cmd) {
-	case ETHTOOL_GRXRINGS:
-		cmd->data = adapter->num_rx_queues;
-		return 0;
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = adapter->nfc_rule_count;
 		return 0;
@@ -1102,8 +1111,6 @@ static int igc_ethtool_get_rxnfc(struct net_device *dev,
 		return igc_ethtool_get_nfc_rule(adapter, cmd);
 	case ETHTOOL_GRXCLSRLALL:
 		return igc_ethtool_get_nfc_rules(adapter, cmd, rule_locs);
-	case ETHTOOL_GRXFH:
-		return igc_ethtool_get_rss_hash_opts(adapter, cmd);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1111,9 +1118,11 @@ static int igc_ethtool_get_rxnfc(struct net_device *dev,
 
 #define UDP_RSS_FLAGS (IGC_FLAG_RSS_FIELD_IPV4_UDP | \
 		       IGC_FLAG_RSS_FIELD_IPV6_UDP)
-static int igc_ethtool_set_rss_hash_opt(struct igc_adapter *adapter,
-					struct ethtool_rxnfc *nfc)
+static int igc_ethtool_set_rxfh_fields(struct net_device *dev,
+				       const struct ethtool_rxfh_fields *nfc,
+				       struct netlink_ext_ack *extack)
 {
+	struct igc_adapter *adapter = netdev_priv(dev);
 	u32 flags = adapter->flags;
 
 	/* RSS does not support anything other than hashing
@@ -1278,6 +1287,24 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule,
 		rule->flex = true;
 	else
 		rule->flex = false;
+
+	/* The wildcard rule is only applied if:
+	 *  a) None of the other filtering rules match (match_flags is zero)
+	 *  b) The flow type is ETHER_FLOW only (no additional fields set)
+	 *  c) Mask for Source MAC address is not specified (all zeros)
+	 *  d) Mask for Destination MAC address is not specified (all zeros)
+	 *  e) Mask for L2 EtherType is not specified (zero)
+	 *
+	 * If all these conditions are met, the rule is treated as a wildcard
+	 * rule. Default queue feature will be used, so that all packets that do
+	 * not match any other rule will be routed to the default queue.
+	 */
+	if (!rule->filter.match_flags &&
+	    fsp->flow_type == ETHER_FLOW &&
+	    is_zero_ether_addr(fsp->m_u.ether_spec.h_source) &&
+	    is_zero_ether_addr(fsp->m_u.ether_spec.h_dest) &&
+	    !fsp->m_u.ether_spec.h_proto)
+		rule->filter.match_flags = IGC_FILTER_FLAG_DEFAULT_QUEUE;
 }
 
 /**
@@ -1424,8 +1451,6 @@ static int igc_ethtool_set_rxnfc(struct net_device *dev,
 	struct igc_adapter *adapter = netdev_priv(dev);
 
 	switch (cmd->cmd) {
-	case ETHTOOL_SRXFH:
-		return igc_ethtool_set_rss_hash_opt(adapter, cmd);
 	case ETHTOOL_SRXCLSRLINS:
 		return igc_ethtool_add_nfc_rule(adapter, cmd);
 	case ETHTOOL_SRXCLSRLDEL:
@@ -1599,6 +1624,9 @@ static u32 igc_ethtool_get_priv_flags(struct net_device *netdev)
 	if (adapter->flags & IGC_FLAG_RX_LEGACY)
 		priv_flags |= IGC_PRIV_FLAGS_LEGACY_RX;
 
+	if (adapter->flags & IGC_FLAG_TSN_REVERSE_TXQ_PRIO)
+		priv_flags |= IGC_PRIV_FLAGS_REVERSE_TSN_TXQ_PRIO;
+
 	return priv_flags;
 }
 
@@ -1607,10 +1635,13 @@ static int igc_ethtool_set_priv_flags(struct net_device *netdev, u32 priv_flags)
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	unsigned int flags = adapter->flags;
 
-	flags &= ~IGC_FLAG_RX_LEGACY;
+	flags &= ~(IGC_FLAG_RX_LEGACY | IGC_FLAG_TSN_REVERSE_TXQ_PRIO);
 	if (priv_flags & IGC_PRIV_FLAGS_LEGACY_RX)
 		flags |= IGC_FLAG_RX_LEGACY;
 
+	if (priv_flags & IGC_PRIV_FLAGS_REVERSE_TSN_TXQ_PRIO)
+		flags |= IGC_FLAG_TSN_REVERSE_TXQ_PRIO;
+
 	if (flags != adapter->flags) {
 		adapter->flags = flags;
 
@@ -1781,6 +1812,83 @@ static int igc_ethtool_set_eee(struct net_device *netdev,
 	return 0;
 }
 
+static int igc_ethtool_get_mm(struct net_device *netdev,
+			      struct ethtool_mm_state *cmd)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_fpe_t *fpe = &adapter->fpe;
+
+	ethtool_mmsv_get_mm(&fpe->mmsv, cmd);
+	cmd->tx_min_frag_size = fpe->tx_min_frag_size;
+	cmd->rx_min_frag_size = IGC_RX_MIN_FRAG_SIZE;
+
+	return 0;
+}
+
+static int igc_ethtool_set_mm(struct net_device *netdev,
+			      struct ethtool_mm_cfg *cmd,
+			      struct netlink_ext_ack *extack)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_fpe_t *fpe = &adapter->fpe;
+
+	fpe->tx_min_frag_size = igc_fpe_get_supported_frag_size(cmd->tx_min_frag_size);
+	if (fpe->tx_min_frag_size != cmd->tx_min_frag_size)
+		NL_SET_ERR_MSG_MOD(extack,
+				   "tx-min-frag-size value set is unsupported. Rounded up to supported value (64, 128, 192, 256)");
+
+	if (fpe->mmsv.pmac_enabled != cmd->pmac_enabled) {
+		if (cmd->pmac_enabled)
+			static_branch_inc(&igc_fpe_enabled);
+		else
+			static_branch_dec(&igc_fpe_enabled);
+	}
+
+	ethtool_mmsv_set_mm(&fpe->mmsv, cmd);
+
+	return igc_tsn_offload_apply(adapter);
+}
+
+/**
+ * igc_ethtool_get_frame_ass_error - Get the frame assembly error count.
+ * @reg_value: Register value for IGC_PRMEXCPRCNT
+ * Return: The count of frame assembly errors.
+ */
+static u64 igc_ethtool_get_frame_ass_error(u32 reg_value)
+{
+	/* Out of order statistics */
+	u32 ooo_frame_cnt, ooo_frag_cnt;
+	u32 miss_frame_frag_cnt;
+
+	ooo_frame_cnt = FIELD_GET(IGC_PRMEXCPRCNT_OOO_FRAME_CNT, reg_value);
+	ooo_frag_cnt = FIELD_GET(IGC_PRMEXCPRCNT_OOO_FRAG_CNT, reg_value);
+	miss_frame_frag_cnt = FIELD_GET(IGC_PRMEXCPRCNT_MISS_FRAME_FRAG_CNT,
+					reg_value);
+
+	return ooo_frame_cnt + ooo_frag_cnt + miss_frame_frag_cnt;
+}
+
+static u64 igc_ethtool_get_frame_smd_error(u32 reg_value)
+{
+	return FIELD_GET(IGC_PRMEXCPRCNT_OOO_SMDC, reg_value);
+}
+
+static void igc_ethtool_get_mm_stats(struct net_device *dev,
+				     struct ethtool_mm_stats *stats)
+{
+	struct igc_adapter *adapter = netdev_priv(dev);
+	struct igc_hw *hw = &adapter->hw;
+	u32 reg_value;
+
+	reg_value = rd32(IGC_PRMEXCPRCNT);
+
+	stats->MACMergeFrameAssErrorCount = igc_ethtool_get_frame_ass_error(reg_value);
+	stats->MACMergeFrameSmdErrorCount = igc_ethtool_get_frame_smd_error(reg_value);
+	stats->MACMergeFrameAssOkCount = rd32(IGC_PRMPTDRCNT);
+	stats->MACMergeFragCountRx = rd32(IGC_PRMEVNTRCNT);
+	stats->MACMergeFragCountTx = rd32(IGC_PRMEVNTTCNT);
+}
+
 static int igc_ethtool_get_link_ksettings(struct net_device *netdev,
 					  struct ethtool_link_ksettings *cmd)
 {
@@ -1990,6 +2098,9 @@ static void igc_ethtool_diag_test(struct net_device *netdev,
 		netdev_info(adapter->netdev, "Offline testing starting");
 		set_bit(__IGC_TESTING, &adapter->state);
 
+		/* power up PHY for link test */
+		igc_power_up_phy_copper(&adapter->hw);
+
 		/* Link test performed before hardware reset so autoneg doesn't
 		 * interfere with test result
 		 */
@@ -2063,9 +2174,12 @@ static const struct ethtool_ops igc_ethtool_ops = {
 	.set_coalesce		= igc_ethtool_set_coalesce,
 	.get_rxnfc		= igc_ethtool_get_rxnfc,
 	.set_rxnfc		= igc_ethtool_set_rxnfc,
+	.get_rx_ring_count	= igc_ethtool_get_rx_ring_count,
 	.get_rxfh_indir_size	= igc_ethtool_get_rxfh_indir_size,
 	.get_rxfh		= igc_ethtool_get_rxfh,
 	.set_rxfh		= igc_ethtool_set_rxfh,
+	.get_rxfh_fields	= igc_ethtool_get_rxfh_fields,
+	.set_rxfh_fields	= igc_ethtool_set_rxfh_fields,
 	.get_ts_info		= igc_ethtool_get_ts_info,
 	.get_channels		= igc_ethtool_get_channels,
 	.set_channels		= igc_ethtool_set_channels,
@@ -2076,6 +2190,9 @@ static const struct ethtool_ops igc_ethtool_ops = {
 	.get_link_ksettings	= igc_ethtool_get_link_ksettings,
 	.set_link_ksettings	= igc_ethtool_set_link_ksettings,
 	.self_test		= igc_ethtool_diag_test,
+	.get_mm			= igc_ethtool_get_mm,
+	.get_mm_stats		= igc_ethtool_get_mm_stats,
+	.set_mm			= igc_ethtool_set_mm,
 };
 
 void igc_ethtool_set_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h
index d9d1a1a11daf..be8a49a86d09 100644
--- a/drivers/net/ethernet/intel/igc/igc_hw.h
+++ b/drivers/net/ethernet/intel/igc/igc_hw.h
@@ -279,9 +279,4 @@ struct net_device *igc_get_hw_dev(struct igc_hw *hw);
 #define hw_dbg(format, arg...) \
 	netdev_dbg(igc_get_hw_dev(hw), format, ##arg)
 
-s32  igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value);
-s32  igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value);
-void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value);
-void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value);
-
 #endif /* _IGC_HW_H_ */
diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c
index 0dd61719f1ed..5226d10cc95b 100644
--- a/drivers/net/ethernet/intel/igc/igc_i225.c
+++ b/drivers/net/ethernet/intel/igc/igc_i225.c
@@ -435,7 +435,7 @@ static s32 igc_update_nvm_checksum_i225(struct igc_hw *hw)
 		}
 		checksum += nvm_data;
 	}
-	checksum = (u16)NVM_SUM - checksum;
+	checksum = NVM_SUM - checksum;
 	ret_val = igc_write_nvm_srwr(hw, NVM_CHECKSUM_REG, 1,
 				     &checksum);
 	if (ret_val) {
diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c
index d344e0a1cd5e..7ac6637f8db7 100644
--- a/drivers/net/ethernet/intel/igc/igc_mac.c
+++ b/drivers/net/ethernet/intel/igc/igc_mac.c
@@ -127,7 +127,7 @@ s32 igc_setup_link(struct igc_hw *hw)
 		goto out;
 
 	/* If requested flow control is set to default, set flow control
-	 * to the both 'rx' and 'tx' pause frames.
+	 * to both 'rx' and 'tx' pause frames.
 	 */
 	if (hw->fc.requested_mode == igc_fc_default)
 		hw->fc.requested_mode = igc_fc_full;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 27872bdea9bd..7aafa60ba0c8 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -683,9 +683,9 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter,
 
 	wr32(IGC_SRRCTL(reg_idx), srrctl);
 
-	rxdctl |= IGC_RX_PTHRESH;
-	rxdctl |= IGC_RX_HTHRESH << 8;
-	rxdctl |= IGC_RX_WTHRESH << 16;
+	rxdctl |= IGC_RXDCTL_PTHRESH;
+	rxdctl |= IGC_RXDCTL_HTHRESH << 8;
+	rxdctl |= IGC_RXDCTL_WTHRESH << 16;
 
 	/* initialize rx_buffer_info */
 	memset(ring->rx_buffer_info, 0,
@@ -749,11 +749,9 @@ static void igc_configure_tx_ring(struct igc_adapter *adapter,
 	wr32(IGC_TDH(reg_idx), 0);
 	writel(0, ring->tail);
 
-	txdctl |= IGC_TX_PTHRESH;
-	txdctl |= IGC_TX_HTHRESH << 8;
-	txdctl |= IGC_TX_WTHRESH << 16;
+	txdctl |= IGC_TXDCTL_PTHRESH(8) | IGC_TXDCTL_HTHRESH(1) |
+		  IGC_TXDCTL_WTHRESH(16) | IGC_TXDCTL_QUEUE_ENABLE;
 
-	txdctl |= IGC_TXDCTL_QUEUE_ENABLE;
 	wr32(IGC_TXDCTL(reg_idx), txdctl);
 }
 
@@ -1092,10 +1090,12 @@ static int igc_init_empty_frame(struct igc_ring *ring,
 
 	dma = dma_map_single(ring->dev, skb->data, size, DMA_TO_DEVICE);
 	if (dma_mapping_error(ring->dev, dma)) {
-		netdev_err_once(ring->netdev, "Failed to map DMA for TX\n");
+		net_err_ratelimited("%s: DMA mapping error for empty frame\n",
+				    netdev_name(ring->netdev));
 		return -ENOMEM;
 	}
 
+	buffer->type = IGC_TX_BUFFER_TYPE_SKB;
 	buffer->skb = skb;
 	buffer->protocol = 0;
 	buffer->bytecount = skb->len;
@@ -1107,20 +1107,12 @@ static int igc_init_empty_frame(struct igc_ring *ring,
 	return 0;
 }
 
-static int igc_init_tx_empty_descriptor(struct igc_ring *ring,
-					struct sk_buff *skb,
-					struct igc_tx_buffer *first)
+static void igc_init_tx_empty_descriptor(struct igc_ring *ring,
+					 struct sk_buff *skb,
+					 struct igc_tx_buffer *first)
 {
 	union igc_adv_tx_desc *desc;
 	u32 cmd_type, olinfo_status;
-	int err;
-
-	if (!igc_desc_unused(ring))
-		return -EBUSY;
-
-	err = igc_init_empty_frame(ring, first, skb);
-	if (err)
-		return err;
 
 	cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT |
 		   IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD |
@@ -1139,8 +1131,6 @@ static int igc_init_tx_empty_descriptor(struct igc_ring *ring,
 	ring->next_to_use++;
 	if (ring->next_to_use == ring->count)
 		ring->next_to_use = 0;
-
-	return 0;
 }
 
 #define IGC_EMPTY_FRAME_SIZE 60
@@ -1566,6 +1556,40 @@ static bool igc_request_tx_tstamp(struct igc_adapter *adapter, struct sk_buff *s
 	return false;
 }
 
+static int igc_insert_empty_frame(struct igc_ring *tx_ring)
+{
+	struct igc_tx_buffer *empty_info;
+	struct sk_buff *empty_skb;
+	void *data;
+	int ret;
+
+	empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
+	empty_skb = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC);
+	if (unlikely(!empty_skb)) {
+		net_err_ratelimited("%s: skb alloc error for empty frame\n",
+				    netdev_name(tx_ring->netdev));
+		return -ENOMEM;
+	}
+
+	data = skb_put(empty_skb, IGC_EMPTY_FRAME_SIZE);
+	memset(data, 0, IGC_EMPTY_FRAME_SIZE);
+
+	/* Prepare DMA mapping and Tx buffer information */
+	ret = igc_init_empty_frame(tx_ring, empty_info, empty_skb);
+	if (unlikely(ret)) {
+		dev_kfree_skb_any(empty_skb);
+		return ret;
+	}
+
+	/* Prepare advanced context descriptor for empty packet */
+	igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0);
+
+	/* Prepare advanced data descriptor for empty packet */
+	igc_init_tx_empty_descriptor(tx_ring, empty_skb, empty_info);
+
+	return 0;
+}
+
 static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 				       struct igc_ring *tx_ring)
 {
@@ -1585,6 +1609,7 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 	 *	+ 1 desc for skb_headlen/IGC_MAX_DATA_PER_TXD,
 	 *	+ 2 desc gap to keep tail from touching head,
 	 *	+ 1 desc for context descriptor,
+	 *	+ 2 desc for inserting an empty packet for launch time,
 	 * otherwise try next time
 	 */
 	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
@@ -1604,24 +1629,16 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 	launch_time = igc_tx_launchtime(tx_ring, txtime, &first_flag, &insert_empty);
 
 	if (insert_empty) {
-		struct igc_tx_buffer *empty_info;
-		struct sk_buff *empty;
-		void *data;
-
-		empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
-		empty = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC);
-		if (!empty)
-			goto done;
-
-		data = skb_put(empty, IGC_EMPTY_FRAME_SIZE);
-		memset(data, 0, IGC_EMPTY_FRAME_SIZE);
-
-		igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0);
-
-		if (igc_init_tx_empty_descriptor(tx_ring,
-						 empty,
-						 empty_info) < 0)
-			dev_kfree_skb_any(empty);
+		/* Reset the launch time if the required empty frame fails to
+		 * be inserted. However, this packet is not dropped, so it
+		 * "dirties" the current Qbv cycle. This ensures that the
+		 * upcoming packet, which is scheduled in the next Qbv cycle,
+		 * does not require an empty frame. This way, the launch time
+		 * continues to function correctly despite the current failure
+		 * to insert the empty frame.
+		 */
+		if (igc_insert_empty_frame(tx_ring))
+			launch_time = 0;
 	}
 
 done:
@@ -1649,7 +1666,8 @@ done:
 		if (igc_request_tx_tstamp(adapter, skb, &tstamp_flags)) {
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 			tx_flags |= IGC_TX_FLAGS_TSTAMP | tstamp_flags;
-			if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_USE_CYCLES)
+			if (skb->sk &&
+			    READ_ONCE(skb->sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC)
 				tx_flags |= IGC_TX_FLAGS_TSTAMP_TIMER_1;
 		} else {
 			adapter->tx_hwtstamp_skipped++;
@@ -1667,6 +1685,15 @@ done:
 	first->tx_flags = tx_flags;
 	first->protocol = protocol;
 
+	/* For preemptible queue, manually pad the skb so that HW includes
+	 * padding bytes in mCRC calculation
+	 */
+	if (tx_ring->preemptible && skb->len < ETH_ZLEN) {
+		if (skb_padto(skb, ETH_ZLEN))
+			goto out_drop;
+		skb_put(skb, ETH_ZLEN - skb->len);
+	}
+
 	tso = igc_tso(tx_ring, first, launch_time, first_flag, &hdr_len);
 	if (tso < 0)
 		goto out_drop;
@@ -2123,10 +2150,6 @@ static bool igc_cleanup_headers(struct igc_ring *rx_ring,
 				union igc_adv_rx_desc *rx_desc,
 				struct sk_buff *skb)
 {
-	/* XDP packets use error pointer so abort at this point */
-	if (IS_ERR(skb))
-		return true;
-
 	if (unlikely(igc_test_staterr(rx_desc, IGC_RXDEXT_STATERR_RXE))) {
 		struct net_device *netdev = rx_ring->netdev;
 
@@ -2448,8 +2471,7 @@ unmap:
 	return -ENOMEM;
 }
 
-static struct igc_ring *igc_xdp_get_tx_ring(struct igc_adapter *adapter,
-					    int cpu)
+struct igc_ring *igc_get_tx_ring(struct igc_adapter *adapter, int cpu)
 {
 	int index = cpu;
 
@@ -2473,7 +2495,7 @@ static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp)
 	if (unlikely(!xdpf))
 		return -EFAULT;
 
-	ring = igc_xdp_get_tx_ring(adapter, cpu);
+	ring = igc_get_tx_ring(adapter, cpu);
 	nq = txring_txq(ring);
 
 	__netif_tx_lock(nq, cpu);
@@ -2515,8 +2537,7 @@ out_failure:
 	}
 }
 
-static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter,
-					struct xdp_buff *xdp)
+static int igc_xdp_run_prog(struct igc_adapter *adapter, struct xdp_buff *xdp)
 {
 	struct bpf_prog *prog;
 	int res;
@@ -2530,11 +2551,11 @@ static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter,
 	res = __igc_xdp_run_prog(adapter, prog, xdp);
 
 out:
-	return ERR_PTR(-res);
+	return res;
 }
 
 /* This function assumes __netif_tx_lock is held by the caller. */
-static void igc_flush_tx_descriptors(struct igc_ring *ring)
+void igc_flush_tx_descriptors(struct igc_ring *ring)
 {
 	/* Once tail pointer is updated, hardware can fetch the descriptors
 	 * any time so we issue a write membar here to ensure all memory
@@ -2551,7 +2572,7 @@ static void igc_finalize_xdp(struct igc_adapter *adapter, int status)
 	struct igc_ring *ring;
 
 	if (status & IGC_XDP_TX) {
-		ring = igc_xdp_get_tx_ring(adapter, cpu);
+		ring = igc_get_tx_ring(adapter, cpu);
 		nq = txring_txq(ring);
 
 		__netif_tx_lock(nq, cpu);
@@ -2585,6 +2606,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 	struct sk_buff *skb = rx_ring->skb;
 	u16 cleaned_count = igc_desc_unused(rx_ring);
 	int xdp_status = 0, rx_buffer_pgcnt;
+	int xdp_res = 0;
 
 	while (likely(total_packets < budget)) {
 		struct igc_xdp_buff ctx = { .rx_ts = NULL };
@@ -2622,6 +2644,14 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 			size -= IGC_TS_HDR_LEN;
 		}
 
+		if (igc_fpe_is_pmac_enabled(adapter) &&
+		    igc_fpe_handle_mpacket(adapter, rx_desc, size, pktbuf)) {
+			/* Advance the ring next-to-clean */
+			igc_is_non_eop(rx_ring, rx_desc);
+			cleaned_count++;
+			continue;
+		}
+
 		if (!skb) {
 			xdp_init_buff(&ctx.xdp, truesize, &rx_ring->xdp_rxq);
 			xdp_prepare_buff(&ctx.xdp, pktbuf - igc_rx_offset(rx_ring),
@@ -2630,12 +2660,10 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 			xdp_buff_clear_frags_flag(&ctx.xdp);
 			ctx.rx_desc = rx_desc;
 
-			skb = igc_xdp_run_prog(adapter, &ctx.xdp);
+			xdp_res = igc_xdp_run_prog(adapter, &ctx.xdp);
 		}
 
-		if (IS_ERR(skb)) {
-			unsigned int xdp_res = -PTR_ERR(skb);
-
+		if (xdp_res) {
 			switch (xdp_res) {
 			case IGC_XDP_CONSUMED:
 				rx_buffer->pagecnt_bias++;
@@ -2657,7 +2685,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 			skb = igc_construct_skb(rx_ring, rx_buffer, &ctx);
 
 		/* exit if we failed to retrieve a buffer */
-		if (!skb) {
+		if (!xdp_res && !skb) {
 			rx_ring->rx_stats.alloc_failed++;
 			rx_buffer->pagecnt_bias++;
 			set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
@@ -2672,7 +2700,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 			continue;
 
 		/* verify the packet layout is correct */
-		if (igc_cleanup_headers(rx_ring, rx_desc, skb)) {
+		if (xdp_res || igc_cleanup_headers(rx_ring, rx_desc, skb)) {
 			skb = NULL;
 			continue;
 		}
@@ -2707,8 +2735,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 }
 
 static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
-					    struct xdp_buff *xdp)
+					    struct igc_xdp_buff *ctx)
 {
+	struct xdp_buff *xdp = &ctx->xdp;
 	unsigned int totalsize = xdp->data_end - xdp->data_meta;
 	unsigned int metasize = xdp->data - xdp->data_meta;
 	struct sk_buff *skb;
@@ -2727,27 +2756,28 @@ static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
 		__skb_pull(skb, metasize);
 	}
 
+	if (ctx->rx_ts) {
+		skb_shinfo(skb)->tx_flags |= SKBTX_HW_TSTAMP_NETDEV;
+		skb_hwtstamps(skb)->netdev_data = ctx->rx_ts;
+	}
+
 	return skb;
 }
 
 static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector,
 				union igc_adv_rx_desc *desc,
-				struct xdp_buff *xdp,
-				ktime_t timestamp)
+				struct igc_xdp_buff *ctx)
 {
 	struct igc_ring *ring = q_vector->rx.ring;
 	struct sk_buff *skb;
 
-	skb = igc_construct_skb_zc(ring, xdp);
+	skb = igc_construct_skb_zc(ring, ctx);
 	if (!skb) {
 		ring->rx_stats.alloc_failed++;
 		set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &ring->flags);
 		return;
 	}
 
-	if (timestamp)
-		skb_hwtstamps(skb)->hwtstamp = timestamp;
-
 	if (igc_cleanup_headers(ring, desc, skb))
 		return;
 
@@ -2783,7 +2813,6 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 		union igc_adv_rx_desc *desc;
 		struct igc_rx_buffer *bi;
 		struct igc_xdp_buff *ctx;
-		ktime_t timestamp = 0;
 		unsigned int size;
 		int res;
 
@@ -2813,6 +2842,8 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 			 */
 			bi->xdp->data_meta += IGC_TS_HDR_LEN;
 			size -= IGC_TS_HDR_LEN;
+		} else {
+			ctx->rx_ts = NULL;
 		}
 
 		bi->xdp->data_end = bi->xdp->data + size;
@@ -2821,7 +2852,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 		res = __igc_xdp_run_prog(adapter, prog, bi->xdp);
 		switch (res) {
 		case IGC_XDP_PASS:
-			igc_dispatch_skb_zc(q_vector, desc, bi->xdp, timestamp);
+			igc_dispatch_skb_zc(q_vector, desc, ctx);
 			fallthrough;
 		case IGC_XDP_CONSUMED:
 			xsk_buff_free(bi->xdp);
@@ -2955,9 +2986,48 @@ static u64 igc_xsk_fill_timestamp(void *_priv)
 	return *(u64 *)_priv;
 }
 
+static void igc_xsk_request_launch_time(u64 launch_time, void *_priv)
+{
+	struct igc_metadata_request *meta_req = _priv;
+	struct igc_ring *tx_ring = meta_req->tx_ring;
+	__le32 launch_time_offset;
+	bool insert_empty = false;
+	bool first_flag = false;
+	u16 used_desc = 0;
+
+	if (!tx_ring->launchtime_enable)
+		return;
+
+	launch_time_offset = igc_tx_launchtime(tx_ring,
+					       ns_to_ktime(launch_time),
+					       &first_flag, &insert_empty);
+	if (insert_empty) {
+		/* Disregard the launch time request if the required empty frame
+		 * fails to be inserted.
+		 */
+		if (igc_insert_empty_frame(tx_ring))
+			return;
+
+		meta_req->tx_buffer =
+			&tx_ring->tx_buffer_info[tx_ring->next_to_use];
+		/* Inserting an empty packet requires two descriptors:
+		 * one data descriptor and one context descriptor.
+		 */
+		used_desc += 2;
+	}
+
+	/* Use one context descriptor to specify launch time and first flag. */
+	igc_tx_ctxtdesc(tx_ring, launch_time_offset, first_flag, 0, 0, 0);
+	used_desc += 1;
+
+	/* Update the number of used descriptors in this request */
+	meta_req->used_desc += used_desc;
+}
+
 const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops = {
 	.tmo_request_timestamp		= igc_xsk_request_timestamp,
 	.tmo_fill_timestamp		= igc_xsk_fill_timestamp,
+	.tmo_request_launch_time	= igc_xsk_request_launch_time,
 };
 
 static void igc_xdp_xmit_zc(struct igc_ring *ring)
@@ -2980,7 +3050,13 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 	ntu = ring->next_to_use;
 	budget = igc_desc_unused(ring);
 
-	while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) {
+	/* Packets with launch time require one data descriptor and one context
+	 * descriptor. When the launch time falls into the next Qbv cycle, we
+	 * may need to insert an empty packet, which requires two more
+	 * descriptors. Therefore, to be safe, we always ensure we have at least
+	 * 4 descriptors available.
+	 */
+	while (budget >= 4 && xsk_tx_peek_desc(pool, &xdp_desc)) {
 		struct igc_metadata_request meta_req;
 		struct xsk_tx_metadata *meta = NULL;
 		struct igc_tx_buffer *bi;
@@ -3001,9 +3077,19 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 		meta_req.tx_ring = ring;
 		meta_req.tx_buffer = bi;
 		meta_req.meta = meta;
+		meta_req.used_desc = 0;
 		xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops,
 					&meta_req);
 
+		/* xsk_tx_metadata_request() may have updated next_to_use */
+		ntu = ring->next_to_use;
+
+		/* xsk_tx_metadata_request() may have updated Tx buffer info */
+		bi = meta_req.tx_buffer;
+
+		/* xsk_tx_metadata_request() may use a few descriptors */
+		budget -= meta_req.used_desc;
+
 		tx_desc = IGC_TX_DESC(ring, ntu);
 		tx_desc->read.cmd_type_len = cpu_to_le32(meta_req.cmd_type);
 		tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
@@ -3021,9 +3107,11 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 		ntu++;
 		if (ntu == ring->count)
 			ntu = 0;
+
+		ring->next_to_use = ntu;
+		budget--;
 	}
 
-	ring->next_to_use = ntu;
 	if (tx_desc) {
 		igc_flush_tx_descriptors(ring);
 		xsk_tx_release(pool);
@@ -3071,6 +3159,11 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 		if (!(eop_desc->wb.status & cpu_to_le32(IGC_TXD_STAT_DD)))
 			break;
 
+		if (igc_fpe_is_pmac_enabled(adapter) &&
+		    igc_fpe_transmitted_smd_v(tx_desc))
+			ethtool_mmsv_event_handle(&adapter->fpe.mmsv,
+						  ETHTOOL_MMSV_LD_SENT_VERIFY_MPACKET);
+
 		/* Hold the completions while there's a pending tx hardware
 		 * timestamp request from XDP Tx metadata.
 		 */
@@ -3781,6 +3874,22 @@ static void igc_del_flex_filter(struct igc_adapter *adapter,
 	wr32(IGC_WUFC, wufc);
 }
 
+static void igc_set_default_queue_filter(struct igc_adapter *adapter, u32 queue)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 mrqc = rd32(IGC_MRQC);
+
+	mrqc &= ~IGC_MRQC_DEFAULT_QUEUE_MASK;
+	mrqc |= FIELD_PREP(IGC_MRQC_DEFAULT_QUEUE_MASK, queue);
+	wr32(IGC_MRQC, mrqc);
+}
+
+static void igc_reset_default_queue_filter(struct igc_adapter *adapter)
+{
+	/* Reset the default queue to its default value which is Queue 0 */
+	igc_set_default_queue_filter(adapter, 0);
+}
+
 static int igc_enable_nfc_rule(struct igc_adapter *adapter,
 			       struct igc_nfc_rule *rule)
 {
@@ -3819,6 +3928,9 @@ static int igc_enable_nfc_rule(struct igc_adapter *adapter,
 			return err;
 	}
 
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_DEFAULT_QUEUE)
+		igc_set_default_queue_filter(adapter, rule->action);
+
 	return 0;
 }
 
@@ -3846,6 +3958,9 @@ static void igc_disable_nfc_rule(struct igc_adapter *adapter,
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
 		igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST,
 				   rule->filter.dst_addr);
+
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_DEFAULT_QUEUE)
+		igc_reset_default_queue_filter(adapter);
 }
 
 /**
@@ -3963,6 +4078,30 @@ static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr)
 }
 
 /**
+ * igc_enable_empty_addr_recv - Enable Rx of packets with all-zeroes MAC address
+ * @adapter: Pointer to the igc_adapter structure.
+ *
+ * Frame preemption verification requires that packets with the all-zeroes
+ * MAC address are allowed to be received by the driver. This function adds the
+ * all-zeroes destination address to the list of acceptable addresses.
+ *
+ * Return: 0 on success, negative value otherwise.
+ */
+int igc_enable_empty_addr_recv(struct igc_adapter *adapter)
+{
+	u8 empty[ETH_ALEN] = {};
+
+	return igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, empty, -1);
+}
+
+void igc_disable_empty_addr_recv(struct igc_adapter *adapter)
+{
+	u8 empty[ETH_ALEN] = {};
+
+	igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, empty);
+}
+
+/**
  * igc_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set
  * @netdev: network interface device structure
  *
@@ -4948,6 +5087,22 @@ static int igc_sw_init(struct igc_adapter *adapter)
 	return 0;
 }
 
+static void igc_set_queue_napi(struct igc_adapter *adapter, int vector,
+			       struct napi_struct *napi)
+{
+	struct igc_q_vector *q_vector = adapter->q_vector[vector];
+
+	if (q_vector->rx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->rx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_RX, napi);
+
+	if (q_vector->tx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->tx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_TX, napi);
+}
+
 /**
  * igc_up - Open the interface and prepare it to handle traffic
  * @adapter: board private structure
@@ -4955,6 +5110,7 @@ static int igc_sw_init(struct igc_adapter *adapter)
 void igc_up(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int i = 0;
 
 	/* hardware has been reset, we need to reload some things */
@@ -4962,8 +5118,11 @@ void igc_up(struct igc_adapter *adapter)
 
 	clear_bit(__IGC_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&adapter->q_vector[i]->napi);
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igc_set_queue_napi(adapter, i, napi);
+	}
 
 	if (adapter->msix_entries)
 		igc_configure_msix(adapter);
@@ -5192,12 +5351,13 @@ void igc_down(struct igc_adapter *adapter)
 	for (i = 0; i < adapter->num_q_vectors; i++) {
 		if (adapter->q_vector[i]) {
 			napi_synchronize(&adapter->q_vector[i]->napi);
+			igc_set_queue_napi(adapter, i, NULL);
 			napi_disable(&adapter->q_vector[i]->napi);
 		}
 	}
 
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_info_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_info_timer);
 
 	/* record the stats before reset*/
 	spin_lock(&adapter->stats64_lock);
@@ -5216,6 +5376,9 @@ void igc_down(struct igc_adapter *adapter)
 	igc_disable_all_tx_rings_hw(adapter);
 	igc_clean_all_tx_rings(adapter);
 	igc_clean_all_rx_rings(adapter);
+
+	if (adapter->fpe.mmsv.pmac_enabled)
+		ethtool_mmsv_stop(&adapter->fpe.mmsv);
 }
 
 void igc_reinit_locked(struct igc_adapter *adapter)
@@ -5576,6 +5739,9 @@ static int igc_request_msix(struct igc_adapter *adapter)
 				  q_vector);
 		if (err)
 			goto err_free;
+
+		netif_napi_set_irq(&q_vector->napi,
+				   adapter->msix_entries[vector].vector);
 	}
 
 	igc_configure_msix(adapter);
@@ -5612,7 +5778,8 @@ static void igc_clear_interrupt_scheme(struct igc_adapter *adapter)
  */
 static void igc_update_phy_info(struct timer_list *t)
 {
-	struct igc_adapter *adapter = from_timer(adapter, t, phy_info_timer);
+	struct igc_adapter *adapter = timer_container_of(adapter, t,
+							 phy_info_timer);
 
 	igc_get_phy_info(&adapter->hw);
 }
@@ -5654,7 +5821,8 @@ bool igc_has_link(struct igc_adapter *adapter)
  */
 static void igc_watchdog(struct timer_list *t)
 {
-	struct igc_adapter *adapter = from_timer(adapter, t, watchdog_timer);
+	struct igc_adapter *adapter = timer_container_of(adapter, t,
+							 watchdog_timer);
 	/* Do the rest outside of interrupt context */
 	schedule_work(&adapter->watchdog_task);
 }
@@ -5737,6 +5905,10 @@ static void igc_watchdog_task(struct work_struct *work)
 			 */
 			igc_tsn_adjust_txtime_offset(adapter);
 
+			if (adapter->fpe.mmsv.pmac_enabled)
+				ethtool_mmsv_link_state_handle(&adapter->fpe.mmsv,
+							       true);
+
 			if (adapter->link_speed != SPEED_1000)
 				goto no_wait;
 
@@ -5772,6 +5944,10 @@ no_wait:
 			netdev_info(netdev, "NIC Link is Down\n");
 			netif_carrier_off(netdev);
 
+			if (adapter->fpe.mmsv.pmac_enabled)
+				ethtool_mmsv_link_state_handle(&adapter->fpe.mmsv,
+							       false);
+
 			/* link state has changed, schedule phy info update */
 			if (!test_bit(__IGC_DOWN, &adapter->state))
 				mod_timer(&adapter->phy_info_timer,
@@ -6018,6 +6194,7 @@ static int __igc_open(struct net_device *netdev, bool resuming)
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct pci_dev *pdev = adapter->pdev;
 	struct igc_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int err = 0;
 	int i = 0;
 
@@ -6053,8 +6230,11 @@ static int __igc_open(struct net_device *netdev, bool resuming)
 
 	clear_bit(__IGC_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&adapter->q_vector[i]->napi);
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igc_set_queue_napi(adapter, i, napi);
+	}
 
 	/* Clear any pending interrupts. */
 	rd32(IGC_ICR);
@@ -6145,24 +6325,6 @@ int igc_close(struct net_device *netdev)
 	return 0;
 }
 
-/**
- * igc_ioctl - Access the hwtstamp interface
- * @netdev: network interface device structure
- * @ifr: interface request data
- * @cmd: ioctl command
- **/
-static int igc_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
-{
-	switch (cmd) {
-	case SIOCGHWTSTAMP:
-		return igc_ptp_get_ts_config(netdev, ifr);
-	case SIOCSHWTSTAMP:
-		return igc_ptp_set_ts_config(netdev, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 static int igc_save_launchtime_params(struct igc_adapter *adapter, int queue,
 				      bool enable)
 {
@@ -6272,6 +6434,7 @@ static int igc_qbv_clear_schedule(struct igc_adapter *adapter)
 		ring->start_time = 0;
 		ring->end_time = NSEC_PER_SEC;
 		ring->max_sdu = 0;
+		ring->preemptible = false;
 	}
 
 	spin_lock_irqsave(&adapter->qbv_tx_lock, flags);
@@ -6337,6 +6500,13 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 	if (!validate_schedule(adapter, qopt))
 		return -EINVAL;
 
+	if (qopt->mqprio.preemptible_tcs &&
+	    !(adapter->flags & IGC_FLAG_TSN_REVERSE_TXQ_PRIO)) {
+		NL_SET_ERR_MSG_MOD(qopt->extack,
+				   "reverse-tsn-txq-prio private flag must be enabled before setting preemptible tc");
+		return -ENODEV;
+	}
+
 	igc_ptp_read(adapter, &now);
 
 	if (igc_tsn_is_taprio_activated_by_user(adapter) &&
@@ -6428,6 +6598,8 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 			ring->max_sdu = 0;
 	}
 
+	igc_fpe_save_preempt_queue(adapter, &qopt->mqprio);
+
 	return 0;
 }
 
@@ -6547,7 +6719,8 @@ static int igc_tc_query_caps(struct igc_adapter *adapter,
 	case TC_SETUP_QDISC_TAPRIO: {
 		struct tc_taprio_caps *caps = base->caps;
 
-		caps->broken_mqprio = true;
+		if (!(adapter->flags & IGC_FLAG_TSN_REVERSE_TXQ_PRIO))
+			caps->broken_mqprio = true;
 
 		if (hw->mac.type == igc_i225) {
 			caps->supports_queue_max_sdu = true;
@@ -6573,17 +6746,33 @@ static void igc_save_mqprio_params(struct igc_adapter *adapter, u8 num_tc,
 		adapter->queue_per_tc[i] = offset[i];
 }
 
+static bool
+igc_tsn_is_tc_to_queue_priority_ordered(struct tc_mqprio_qopt_offload *mqprio)
+{
+	int num_tc = mqprio->qopt.num_tc;
+	int i;
+
+	for (i = 1; i < num_tc; i++) {
+		if (mqprio->qopt.offset[i - 1] > mqprio->qopt.offset[i])
+			return false;
+	}
+
+	return true;
+}
+
 static int igc_tsn_enable_mqprio(struct igc_adapter *adapter,
 				 struct tc_mqprio_qopt_offload *mqprio)
 {
 	struct igc_hw *hw = &adapter->hw;
-	int i;
+	int err, i;
 
 	if (hw->mac.type != igc_i225)
 		return -EOPNOTSUPP;
 
 	if (!mqprio->qopt.num_tc) {
 		adapter->strict_priority_enable = false;
+		igc_fpe_clear_preempt_queue(adapter);
+		netdev_reset_tc(adapter->netdev);
 		goto apply;
 	}
 
@@ -6604,17 +6793,32 @@ static int igc_tsn_enable_mqprio(struct igc_adapter *adapter,
 		}
 	}
 
-	/* Preemption is not supported yet. */
-	if (mqprio->preemptible_tcs) {
+	if (!igc_tsn_is_tc_to_queue_priority_ordered(mqprio)) {
 		NL_SET_ERR_MSG_MOD(mqprio->extack,
-				   "Preemption is not supported yet");
+				   "tc to queue mapping must preserve increasing priority (higher tc -> higher queue)");
 		return -EOPNOTSUPP;
 	}
 
 	igc_save_mqprio_params(adapter, mqprio->qopt.num_tc,
 			       mqprio->qopt.offset);
 
+	err = netdev_set_num_tc(adapter->netdev, adapter->num_tc);
+	if (err)
+		return err;
+
+	for (i = 0; i < adapter->num_tc; i++) {
+		err = netdev_set_tc_queue(adapter->netdev, i, 1,
+					  adapter->queue_per_tc[i]);
+		if (err)
+			return err;
+	}
+
+	/* In case the card is configured with less than four queues. */
+	for (; i < IGC_MAX_TX_QUEUES; i++)
+		adapter->queue_per_tc[i] = i;
+
 	mqprio->qopt.hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	igc_fpe_save_preempt_queue(adapter, mqprio);
 
 apply:
 	return igc_tsn_offload_apply(adapter);
@@ -6677,7 +6881,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
 
-	ring = igc_xdp_get_tx_ring(adapter, cpu);
+	ring = igc_get_tx_ring(adapter, cpu);
 	nq = txring_txq(ring);
 
 	__netif_tx_lock(nq, cpu);
@@ -6771,53 +6975,15 @@ static const struct net_device_ops igc_netdev_ops = {
 	.ndo_fix_features	= igc_fix_features,
 	.ndo_set_features	= igc_set_features,
 	.ndo_features_check	= igc_features_check,
-	.ndo_eth_ioctl		= igc_ioctl,
 	.ndo_setup_tc		= igc_setup_tc,
 	.ndo_bpf		= igc_bpf,
 	.ndo_xdp_xmit		= igc_xdp_xmit,
 	.ndo_xsk_wakeup		= igc_xsk_wakeup,
 	.ndo_get_tstamp		= igc_get_tstamp,
+	.ndo_hwtstamp_get	= igc_ptp_hwtstamp_get,
+	.ndo_hwtstamp_set	= igc_ptp_hwtstamp_set,
 };
 
-/* PCIe configuration access */
-void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value)
-{
-	struct igc_adapter *adapter = hw->back;
-
-	pci_read_config_word(adapter->pdev, reg, value);
-}
-
-void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value)
-{
-	struct igc_adapter *adapter = hw->back;
-
-	pci_write_config_word(adapter->pdev, reg, *value);
-}
-
-s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value)
-{
-	struct igc_adapter *adapter = hw->back;
-
-	if (!pci_is_pcie(adapter->pdev))
-		return -IGC_ERR_CONFIG;
-
-	pcie_capability_read_word(adapter->pdev, reg, value);
-
-	return IGC_SUCCESS;
-}
-
-s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value)
-{
-	struct igc_adapter *adapter = hw->back;
-
-	if (!pci_is_pcie(adapter->pdev))
-		return -IGC_ERR_CONFIG;
-
-	pcie_capability_write_word(adapter->pdev, reg, *value);
-
-	return IGC_SUCCESS;
-}
-
 u32 igc_rd32(struct igc_hw *hw, u32 reg)
 {
 	struct igc_adapter *igc = container_of(hw, struct igc_adapter, hw);
@@ -6983,6 +7149,17 @@ static int igc_probe(struct pci_dev *pdev,
 	adapter->port_num = hw->bus.func;
 	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
+	/* PCI config space info */
+	hw->vendor_id = pdev->vendor;
+	hw->device_id = pdev->device;
+	hw->revision_id = pdev->revision;
+	hw->subsystem_vendor_id = pdev->subsystem_vendor;
+	hw->subsystem_device_id = pdev->subsystem_device;
+
+	/* Disable ASPM L1.2 on I226 devices to avoid packet loss */
+	if (igc_is_device_id_i226(hw))
+		pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
+
 	err = pci_save_state(pdev);
 	if (err)
 		goto err_ioremap;
@@ -7005,13 +7182,6 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->mem_start = pci_resource_start(pdev, 0);
 	netdev->mem_end = pci_resource_end(pdev, 0);
 
-	/* PCI config space info */
-	hw->vendor_id = pdev->vendor;
-	hw->device_id = pdev->device;
-	hw->revision_id = pdev->revision;
-	hw->subsystem_vendor_id = pdev->subsystem_vendor;
-	hw->subsystem_device_id = pdev->subsystem_device;
-
 	/* Copy the default MAC and PHY function pointers */
 	memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops));
 	memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops));
@@ -7062,6 +7232,9 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
 			       NETDEV_XDP_ACT_XSK_ZEROCOPY;
 
+	/* enable HW vlan tag insertion/stripping by default */
+	netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
+
 	/* MTU range: 68 - 9216 */
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE;
@@ -7094,8 +7267,8 @@ static int igc_probe(struct pci_dev *pdev,
 	}
 
 	/* configure RXPBSIZE and TXPBSIZE */
-	wr32(IGC_RXPBS, I225_RXPBSIZE_DEFAULT);
-	wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT);
+	wr32(IGC_RXPBS, IGC_RXPBSIZE_EXP_BMC_DEFAULT);
+	wr32(IGC_TXPBS, IGC_TXPBSIZE_DEFAULT);
 
 	timer_setup(&adapter->watchdog_timer, igc_watchdog, 0);
 	timer_setup(&adapter->phy_info_timer, igc_update_phy_info, 0);
@@ -7103,8 +7276,8 @@ static int igc_probe(struct pci_dev *pdev,
 	INIT_WORK(&adapter->reset_task, igc_reset_task);
 	INIT_WORK(&adapter->watchdog_task, igc_watchdog_task);
 
-	hrtimer_init(&adapter->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	adapter->hrtimer.function = &igc_qbv_scheduling_timer;
+	hrtimer_setup(&adapter->hrtimer, &igc_qbv_scheduling_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	/* Initialize link properties that are user-changeable */
 	adapter->fc_autoneg = true;
@@ -7127,6 +7300,8 @@ static int igc_probe(struct pci_dev *pdev,
 
 	igc_tsn_clear_schedule(adapter);
 
+	igc_fpe_init(adapter);
+
 	/* reset the hardware with the new settings */
 	igc_reset(adapter);
 
@@ -7160,14 +7335,21 @@ static int igc_probe(struct pci_dev *pdev,
 
 	if (IS_ENABLED(CONFIG_IGC_LEDS)) {
 		err = igc_led_setup(adapter);
-		if (err)
-			goto err_register;
+		if (err) {
+			netdev_warn_once(netdev,
+					 "LED init failed (%d); continuing without LED support\n",
+					 err);
+			adapter->leds_available = false;
+		} else {
+			adapter->leds_available = true;
+		}
 	}
 
 	return 0;
 
 err_register:
 	igc_release_hw_control(adapter);
+	igc_ptp_stop(adapter);
 err_eeprom:
 	if (!igc_check_reset_block(hw))
 		igc_reset_phy(hw);
@@ -7209,14 +7391,14 @@ static void igc_remove(struct pci_dev *pdev)
 
 	set_bit(__IGC_DOWN, &adapter->state);
 
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_info_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_info_timer);
 
 	cancel_work_sync(&adapter->reset_task);
 	cancel_work_sync(&adapter->watchdog_task);
 	hrtimer_cancel(&adapter->hrtimer);
 
-	if (IS_ENABLED(CONFIG_IGC_LEDS))
+	if (IS_ENABLED(CONFIG_IGC_LEDS) && adapter->leds_available)
 		igc_led_free(adapter);
 
 	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
@@ -7338,7 +7520,7 @@ static void igc_deliver_wake_packet(struct net_device *netdev)
 	netif_rx(skb);
 }
 
-static int igc_resume(struct device *dev)
+static int __igc_resume(struct device *dev, bool rpm)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -7348,7 +7530,6 @@ static int igc_resume(struct device *dev)
 
 	pci_set_power_state(pdev, PCI_D0);
 	pci_restore_state(pdev);
-	pci_save_state(pdev);
 
 	if (!pci_device_is_present(pdev))
 		return -ENODEV;
@@ -7362,6 +7543,9 @@ static int igc_resume(struct device *dev)
 	pci_enable_wake(pdev, PCI_D3hot, 0);
 	pci_enable_wake(pdev, PCI_D3cold, 0);
 
+	if (igc_is_device_id_i226(hw))
+		pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
+
 	if (igc_init_interrupt_scheme(adapter, true)) {
 		netdev_err(netdev, "Unable to allocate memory for queues\n");
 		return -ENOMEM;
@@ -7381,7 +7565,11 @@ static int igc_resume(struct device *dev)
 	wr32(IGC_WUS, ~0);
 
 	if (netif_running(netdev)) {
+		if (!rpm)
+			rtnl_lock();
 		err = __igc_open(netdev, true);
+		if (!rpm)
+			rtnl_unlock();
 		if (!err)
 			netif_device_attach(netdev);
 	}
@@ -7389,9 +7577,14 @@ static int igc_resume(struct device *dev)
 	return err;
 }
 
+static int igc_resume(struct device *dev)
+{
+	return __igc_resume(dev, false);
+}
+
 static int igc_runtime_resume(struct device *dev)
 {
-	return igc_resume(dev);
+	return __igc_resume(dev, true);
 }
 
 static int igc_suspend(struct device *dev)
@@ -7436,14 +7629,18 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev,
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
+	rtnl_lock();
 	netif_device_detach(netdev);
 
-	if (state == pci_channel_io_perm_failure)
+	if (state == pci_channel_io_perm_failure) {
+		rtnl_unlock();
 		return PCI_ERS_RESULT_DISCONNECT;
+	}
 
 	if (netif_running(netdev))
 		igc_down(adapter);
 	pci_disable_device(pdev);
+	rtnl_unlock();
 
 	/* Request a slot reset. */
 	return PCI_ERS_RESULT_NEED_RESET;
@@ -7454,7 +7651,7 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev,
  *  @pdev: Pointer to PCI device
  *
  *  Restart the card from scratch, as if from a cold-boot. Implementation
- *  resembles the first-half of the igc_resume routine.
+ *  resembles the first-half of the __igc_resume routine.
  **/
 static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
 {
@@ -7469,11 +7666,13 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
 	} else {
 		pci_set_master(pdev);
 		pci_restore_state(pdev);
-		pci_save_state(pdev);
 
 		pci_enable_wake(pdev, PCI_D3hot, 0);
 		pci_enable_wake(pdev, PCI_D3cold, 0);
 
+		if (igc_is_device_id_i226(hw))
+			pci_disable_link_state_locked(pdev, PCIE_LINK_STATE_L1_2);
+
 		/* In case of PCI error, adapter loses its HW address
 		 * so we should re-assign it here.
 		 */
@@ -7493,7 +7692,7 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
  *
  *  This callback is called when the error recovery driver tells us that
  *  its OK to resume normal operation. Implementation resembles the
- *  second-half of the igc_resume routine.
+ *  second-half of the __igc_resume routine.
  */
 static void igc_io_resume(struct pci_dev *pdev)
 {
diff --git a/drivers/net/ethernet/intel/igc/igc_nvm.c b/drivers/net/ethernet/intel/igc/igc_nvm.c
index 58f81aba0144..a47b8d39238c 100644
--- a/drivers/net/ethernet/intel/igc/igc_nvm.c
+++ b/drivers/net/ethernet/intel/igc/igc_nvm.c
@@ -36,56 +36,6 @@ static s32 igc_poll_eerd_eewr_done(struct igc_hw *hw, int ee_reg)
 }
 
 /**
- * igc_acquire_nvm - Generic request for access to EEPROM
- * @hw: pointer to the HW structure
- *
- * Set the EEPROM access request bit and wait for EEPROM access grant bit.
- * Return successful if access grant bit set, else clear the request for
- * EEPROM access and return -IGC_ERR_NVM (-1).
- */
-s32 igc_acquire_nvm(struct igc_hw *hw)
-{
-	s32 timeout = IGC_NVM_GRANT_ATTEMPTS;
-	u32 eecd = rd32(IGC_EECD);
-	s32 ret_val = 0;
-
-	wr32(IGC_EECD, eecd | IGC_EECD_REQ);
-	eecd = rd32(IGC_EECD);
-
-	while (timeout) {
-		if (eecd & IGC_EECD_GNT)
-			break;
-		udelay(5);
-		eecd = rd32(IGC_EECD);
-		timeout--;
-	}
-
-	if (!timeout) {
-		eecd &= ~IGC_EECD_REQ;
-		wr32(IGC_EECD, eecd);
-		hw_dbg("Could not acquire NVM grant\n");
-		ret_val = -IGC_ERR_NVM;
-	}
-
-	return ret_val;
-}
-
-/**
- * igc_release_nvm - Release exclusive access to EEPROM
- * @hw: pointer to the HW structure
- *
- * Stop any current commands to the EEPROM and clear the EEPROM request bit.
- */
-void igc_release_nvm(struct igc_hw *hw)
-{
-	u32 eecd;
-
-	eecd = rd32(IGC_EECD);
-	eecd &= ~IGC_EECD_REQ;
-	wr32(IGC_EECD, eecd);
-}
-
-/**
  * igc_read_nvm_eerd - Reads EEPROM using EERD register
  * @hw: pointer to the HW structure
  * @offset: offset of word in the EEPROM to read
@@ -173,7 +123,7 @@ s32 igc_validate_nvm_checksum(struct igc_hw *hw)
 		checksum += nvm_data;
 	}
 
-	if (checksum != (u16)NVM_SUM) {
+	if (checksum != NVM_SUM) {
 		hw_dbg("NVM Checksum Invalid\n");
 		ret_val = -IGC_ERR_NVM;
 		goto out;
@@ -205,7 +155,7 @@ s32 igc_update_nvm_checksum(struct igc_hw *hw)
 		}
 		checksum += nvm_data;
 	}
-	checksum = (u16)NVM_SUM - checksum;
+	checksum = NVM_SUM - checksum;
 	ret_val = hw->nvm.ops.write(hw, NVM_CHECKSUM_REG, 1, &checksum);
 	if (ret_val)
 		hw_dbg("NVM Write Error while updating checksum.\n");
diff --git a/drivers/net/ethernet/intel/igc/igc_nvm.h b/drivers/net/ethernet/intel/igc/igc_nvm.h
index f9fc2e9cfb03..ab78d0c64547 100644
--- a/drivers/net/ethernet/intel/igc/igc_nvm.h
+++ b/drivers/net/ethernet/intel/igc/igc_nvm.h
@@ -4,8 +4,6 @@
 #ifndef _IGC_NVM_H_
 #define _IGC_NVM_H_
 
-s32 igc_acquire_nvm(struct igc_hw *hw);
-void igc_release_nvm(struct igc_hw *hw);
 s32 igc_read_mac_addr(struct igc_hw *hw);
 s32 igc_read_nvm_eerd(struct igc_hw *hw, u16 offset, u16 words, u16 *data);
 s32 igc_validate_nvm_checksum(struct igc_hw *hw);
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 946edbad4302..b7b46d863bee 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -257,13 +257,6 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_EXTTS:
-		/* Reject requests with unsupported flags */
-		if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-					PTP_RISING_EDGE |
-					PTP_FALLING_EDGE |
-					PTP_STRICT_FLAGS))
-			return -EOPNOTSUPP;
-
 		/* Reject requests failing to enable both edges. */
 		if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
 		    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
@@ -300,10 +293,6 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp,
 		return 0;
 
 	case PTP_CLK_REQ_PEROUT:
-		/* Reject requests with unsupported flags */
-		if (rq->perout.flags)
-			return -EOPNOTSUPP;
-
 		if (on) {
 			pin = ptp_find_pin(igc->ptp_clock, PTP_PF_PEROUT,
 					   rq->perout.index);
@@ -637,7 +626,7 @@ static void igc_ptp_enable_tx_timestamp(struct igc_adapter *adapter)
  * Return: 0 in case of success, negative errno code otherwise.
  */
 static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter,
-				      struct hwtstamp_config *config)
+				      struct kernel_hwtstamp_config *config)
 {
 	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
@@ -864,48 +853,46 @@ void igc_ptp_tx_tstamp_event(struct igc_adapter *adapter)
 }
 
 /**
- * igc_ptp_set_ts_config - set hardware time stamping config
+ * igc_ptp_hwtstamp_set - set hardware time stamping config
  * @netdev: network interface device structure
- * @ifr: interface request data
+ * @config: timestamping configuration structure
+ * @extack: netlink extended ack structure for error reporting
  *
  **/
-int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr)
+int igc_ptp_hwtstamp_set(struct net_device *netdev,
+			 struct kernel_hwtstamp_config *config,
+			 struct netlink_ext_ack *extack)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
-	struct hwtstamp_config config;
 	int err;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	err = igc_ptp_set_timestamp_mode(adapter, &config);
+	err = igc_ptp_set_timestamp_mode(adapter, config);
 	if (err)
 		return err;
 
 	/* save these settings for future reference */
-	memcpy(&adapter->tstamp_config, &config,
-	       sizeof(adapter->tstamp_config));
+	adapter->tstamp_config = *config;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 /**
- * igc_ptp_get_ts_config - get hardware time stamping config
+ * igc_ptp_hwtstamp_get - get hardware time stamping config
  * @netdev: network interface device structure
- * @ifr: interface request data
+ * @config: timestamping configuration structure
  *
  * Get the hwtstamp_config settings to return to the user. Rather than attempt
  * to deconstruct the settings from the registers, just return a shadow copy
  * of the last known settings.
  **/
-int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr)
+int igc_ptp_hwtstamp_get(struct net_device *netdev,
+			 struct kernel_hwtstamp_config *config)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
-	struct hwtstamp_config *config = &adapter->tstamp_config;
 
-	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
-		-EFAULT : 0;
+	*config = adapter->tstamp_config;
+
+	return 0;
 }
 
 /* The two conditions below must be met for cross timestamping via
@@ -974,45 +961,62 @@ static void igc_ptm_log_error(struct igc_adapter *adapter, u32 ptm_stat)
 	}
 }
 
+/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_trigger() */
+static void igc_ptm_trigger(struct igc_hw *hw)
+{
+	u32 ctrl;
+
+	/* To "manually" start the PTM cycle we need to set the
+	 * trigger (TRIG) bit
+	 */
+	ctrl = rd32(IGC_PTM_CTRL);
+	ctrl |= IGC_PTM_CTRL_TRIG;
+	wr32(IGC_PTM_CTRL, ctrl);
+	/* Perform flush after write to CTRL register otherwise
+	 * transaction may not start
+	 */
+	wrfl();
+}
+
+/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_reset() */
+static void igc_ptm_reset(struct igc_hw *hw)
+{
+	u32 ctrl;
+
+	ctrl = rd32(IGC_PTM_CTRL);
+	ctrl &= ~IGC_PTM_CTRL_TRIG;
+	wr32(IGC_PTM_CTRL, ctrl);
+	/* Write to clear all status */
+	wr32(IGC_PTM_STAT, IGC_PTM_STAT_ALL);
+}
+
 static int igc_phc_get_syncdevicetime(ktime_t *device,
 				      struct system_counterval_t *system,
 				      void *ctx)
 {
-	u32 stat, t2_curr_h, t2_curr_l, ctrl;
 	struct igc_adapter *adapter = ctx;
 	struct igc_hw *hw = &adapter->hw;
+	u32 stat, t2_curr_h, t2_curr_l;
 	int err, count = 100;
 	ktime_t t1, t2_curr;
 
-	/* Get a snapshot of system clocks to use as historic value. */
-	ktime_get_snapshot(&adapter->snapshot);
-
+	/* Doing this in a loop because in the event of a
+	 * badly timed (ha!) system clock adjustment, we may
+	 * get PTM errors from the PCI root, but these errors
+	 * are transitory. Repeating the process returns valid
+	 * data eventually.
+	 */
 	do {
-		/* Doing this in a loop because in the event of a
-		 * badly timed (ha!) system clock adjustment, we may
-		 * get PTM errors from the PCI root, but these errors
-		 * are transitory. Repeating the process returns valid
-		 * data eventually.
-		 */
-
-		/* To "manually" start the PTM cycle we need to clear and
-		 * then set again the TRIG bit.
-		 */
-		ctrl = rd32(IGC_PTM_CTRL);
-		ctrl &= ~IGC_PTM_CTRL_TRIG;
-		wr32(IGC_PTM_CTRL, ctrl);
-		ctrl |= IGC_PTM_CTRL_TRIG;
-		wr32(IGC_PTM_CTRL, ctrl);
+		/* Get a snapshot of system clocks to use as historic value. */
+		ktime_get_snapshot(&adapter->snapshot);
 
-		/* The cycle only starts "for real" when software notifies
-		 * that it has read the registers, this is done by setting
-		 * VALID bit.
-		 */
-		wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID);
+		igc_ptm_trigger(hw);
 
 		err = readx_poll_timeout(rd32, IGC_PTM_STAT, stat,
 					 stat, IGC_PTM_STAT_SLEEP,
 					 IGC_PTM_STAT_TIMEOUT);
+		igc_ptm_reset(hw);
+
 		if (err < 0) {
 			netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n");
 			return err;
@@ -1021,15 +1025,7 @@ static int igc_phc_get_syncdevicetime(ktime_t *device,
 		if ((stat & IGC_PTM_STAT_VALID) == IGC_PTM_STAT_VALID)
 			break;
 
-		if (stat & ~IGC_PTM_STAT_VALID) {
-			/* An error occurred, log it. */
-			igc_ptm_log_error(adapter, stat);
-			/* The STAT register is write-1-to-clear (W1C),
-			 * so write the previous error status to clear it.
-			 */
-			wr32(IGC_PTM_STAT, stat);
-			continue;
-		}
+		igc_ptm_log_error(adapter, stat);
 	} while (--count);
 
 	if (!count) {
@@ -1061,9 +1057,16 @@ static int igc_ptp_getcrosststamp(struct ptp_clock_info *ptp,
 {
 	struct igc_adapter *adapter = container_of(ptp, struct igc_adapter,
 						   ptp_caps);
+	int ret;
 
-	return get_device_system_crosststamp(igc_phc_get_syncdevicetime,
-					     adapter, &adapter->snapshot, cts);
+	/* This blocks until any in progress PTM transactions complete */
+	mutex_lock(&adapter->ptm_lock);
+
+	ret = get_device_system_crosststamp(igc_phc_get_syncdevicetime,
+					    adapter, &adapter->snapshot, cts);
+	mutex_unlock(&adapter->ptm_lock);
+
+	return ret;
 }
 
 static int igc_ptp_getcyclesx64(struct ptp_clock_info *ptp,
@@ -1146,6 +1149,9 @@ void igc_ptp_init(struct igc_adapter *adapter)
 		adapter->ptp_caps.pin_config = adapter->sdp_config;
 		adapter->ptp_caps.n_ext_ts = IGC_N_EXTTS;
 		adapter->ptp_caps.n_per_out = IGC_N_PEROUT;
+		adapter->ptp_caps.supported_extts_flags = PTP_RISING_EDGE |
+							  PTP_FALLING_EDGE |
+							  PTP_STRICT_FLAGS;
 		adapter->ptp_caps.n_pins = IGC_N_SDP;
 		adapter->ptp_caps.verify = igc_ptp_verify_pin;
 
@@ -1162,6 +1168,7 @@ void igc_ptp_init(struct igc_adapter *adapter)
 	spin_lock_init(&adapter->ptp_tx_lock);
 	spin_lock_init(&adapter->free_timer_lock);
 	spin_lock_init(&adapter->tmreg_lock);
+	mutex_init(&adapter->ptm_lock);
 
 	adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
 	adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
@@ -1174,6 +1181,7 @@ void igc_ptp_init(struct igc_adapter *adapter)
 	if (IS_ERR(adapter->ptp_clock)) {
 		adapter->ptp_clock = NULL;
 		netdev_err(netdev, "ptp_clock_register failed\n");
+		mutex_destroy(&adapter->ptm_lock);
 	} else if (adapter->ptp_clock) {
 		netdev_info(netdev, "PHC added\n");
 		adapter->ptp_flags |= IGC_PTP_ENABLED;
@@ -1203,10 +1211,12 @@ static void igc_ptm_stop(struct igc_adapter *adapter)
 	struct igc_hw *hw = &adapter->hw;
 	u32 ctrl;
 
+	mutex_lock(&adapter->ptm_lock);
 	ctrl = rd32(IGC_PTM_CTRL);
 	ctrl &= ~IGC_PTM_CTRL_EN;
 
 	wr32(IGC_PTM_CTRL, ctrl);
+	mutex_unlock(&adapter->ptm_lock);
 }
 
 /**
@@ -1237,13 +1247,18 @@ void igc_ptp_suspend(struct igc_adapter *adapter)
  **/
 void igc_ptp_stop(struct igc_adapter *adapter)
 {
+	if (!(adapter->ptp_flags & IGC_PTP_ENABLED))
+		return;
+
 	igc_ptp_suspend(adapter);
 
+	adapter->ptp_flags &= ~IGC_PTP_ENABLED;
 	if (adapter->ptp_clock) {
 		ptp_clock_unregister(adapter->ptp_clock);
 		netdev_info(adapter->netdev, "PHC removed\n");
 		adapter->ptp_flags &= ~IGC_PTP_ENABLED;
 	}
+	mutex_destroy(&adapter->ptm_lock);
 }
 
 /**
@@ -1255,13 +1270,18 @@ void igc_ptp_stop(struct igc_adapter *adapter)
 void igc_ptp_reset(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
-	u32 cycle_ctrl, ctrl;
+	u32 cycle_ctrl, ctrl, stat;
 	unsigned long flags;
 	u32 timadj;
 
+	if (!(adapter->ptp_flags & IGC_PTP_ENABLED))
+		return;
+
 	/* reset the tstamp_config */
 	igc_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config);
 
+	mutex_lock(&adapter->ptm_lock);
+
 	spin_lock_irqsave(&adapter->tmreg_lock, flags);
 
 	switch (adapter->hw.mac.type) {
@@ -1290,14 +1310,19 @@ void igc_ptp_reset(struct igc_adapter *adapter)
 		ctrl = IGC_PTM_CTRL_EN |
 			IGC_PTM_CTRL_START_NOW |
 			IGC_PTM_CTRL_SHRT_CYC(IGC_PTM_SHORT_CYC_DEFAULT) |
-			IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT) |
-			IGC_PTM_CTRL_TRIG;
+			IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT);
 
 		wr32(IGC_PTM_CTRL, ctrl);
 
 		/* Force the first cycle to run. */
-		wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID);
+		igc_ptm_trigger(hw);
 
+		if (readx_poll_timeout_atomic(rd32, IGC_PTM_STAT, stat,
+					      stat, IGC_PTM_STAT_SLEEP,
+					      IGC_PTM_STAT_TIMEOUT))
+			netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n");
+
+		igc_ptm_reset(hw);
 		break;
 	default:
 		/* No work to do. */
@@ -1314,5 +1339,7 @@ void igc_ptp_reset(struct igc_adapter *adapter)
 out:
 	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
 
+	mutex_unlock(&adapter->ptm_lock);
+
 	wrfl();
 }
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 12ddc5793651..f343c6bfc6be 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -222,6 +222,22 @@
 
 #define IGC_FTQF(_n)	(0x059E0 + (4 * (_n)))  /* 5-tuple Queue Fltr */
 
+/* Time sync registers - preemption statistics */
+#define IGC_PRMPTDRCNT		0x04284	/* Good RX Preempted Packets */
+#define IGC_PRMEVNTTCNT		0x04298	/* TX Preemption event counter */
+#define IGC_PRMEVNTRCNT		0x0429C	/* RX Preemption event counter */
+
+ /* Preemption Exception Counter */
+ #define IGC_PRMEXCPRCNT				0x42A0
+/* Received out of order packets with SMD-C */
+#define IGC_PRMEXCPRCNT_OOO_SMDC			0x000000FF
+/* Received out of order packets with SMD-C and wrong Frame CNT */
+#define IGC_PRMEXCPRCNT_OOO_FRAME_CNT			0x0000FF00
+/* Received out of order packets with SMD-C and wrong Frag CNT */
+#define IGC_PRMEXCPRCNT_OOO_FRAG_CNT			0x00FF0000
+/* Received packets with SMD-S and wrong Frag CNT and Frame CNT */
+#define IGC_PRMEXCPRCNT_MISS_FRAME_FRAG_CNT		0xFF000000
+
 /* Transmit Scheduling Registers */
 #define IGC_TQAVCTRL		0x3570
 #define IGC_TXQCTL(_n)		(0x3344 + 0x4 * (_n))
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c
index 1e44374ca1ff..8a110145bfee 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.c
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.c
@@ -2,9 +2,206 @@
 /* Copyright (c)  2019 Intel Corporation */
 
 #include "igc.h"
+#include "igc_base.h"
 #include "igc_hw.h"
 #include "igc_tsn.h"
 
+#define MIN_MULTPLIER_TX_MIN_FRAG	0
+#define MAX_MULTPLIER_TX_MIN_FRAG	3
+/* Frag size is based on the Section 8.12.2 of the SW User Manual */
+#define TX_MIN_FRAG_SIZE		64
+#define TX_MAX_FRAG_SIZE	(TX_MIN_FRAG_SIZE * \
+				 (MAX_MULTPLIER_TX_MIN_FRAG + 1))
+
+enum tx_queue {
+	TX_QUEUE_0 = 0,
+	TX_QUEUE_1,
+	TX_QUEUE_2,
+	TX_QUEUE_3,
+};
+
+DEFINE_STATIC_KEY_FALSE(igc_fpe_enabled);
+
+static int igc_fpe_init_smd_frame(struct igc_ring *ring,
+				  struct igc_tx_buffer *buffer,
+				  struct sk_buff *skb)
+{
+	dma_addr_t dma = dma_map_single(ring->dev, skb->data, skb->len,
+					DMA_TO_DEVICE);
+
+	if (dma_mapping_error(ring->dev, dma)) {
+		netdev_err_once(ring->netdev, "Failed to map DMA for TX\n");
+		return -ENOMEM;
+	}
+
+	buffer->skb = skb;
+	buffer->protocol = 0;
+	buffer->bytecount = skb->len;
+	buffer->gso_segs = 1;
+	buffer->time_stamp = jiffies;
+	dma_unmap_len_set(buffer, len, skb->len);
+	dma_unmap_addr_set(buffer, dma, dma);
+
+	return 0;
+}
+
+static int igc_fpe_init_tx_descriptor(struct igc_ring *ring,
+				      struct sk_buff *skb,
+				      enum igc_txd_popts_type type)
+{
+	u32 cmd_type, olinfo_status = 0;
+	struct igc_tx_buffer *buffer;
+	union igc_adv_tx_desc *desc;
+	int err;
+
+	if (!igc_desc_unused(ring))
+		return -EBUSY;
+
+	buffer = &ring->tx_buffer_info[ring->next_to_use];
+	err = igc_fpe_init_smd_frame(ring, buffer, skb);
+	if (err)
+		return err;
+
+	cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT |
+		   IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD |
+		   buffer->bytecount;
+
+	olinfo_status |= FIELD_PREP(IGC_ADVTXD_PAYLEN_MASK, buffer->bytecount);
+
+	switch (type) {
+	case SMD_V:
+	case SMD_R:
+		olinfo_status |= FIELD_PREP(IGC_TXD_POPTS_SMD_MASK, type);
+		break;
+	}
+
+	desc = IGC_TX_DESC(ring, ring->next_to_use);
+	desc->read.cmd_type_len = cpu_to_le32(cmd_type);
+	desc->read.olinfo_status = cpu_to_le32(olinfo_status);
+	desc->read.buffer_addr = cpu_to_le64(dma_unmap_addr(buffer, dma));
+
+	netdev_tx_sent_queue(txring_txq(ring), skb->len);
+
+	buffer->next_to_watch = desc;
+	ring->next_to_use = (ring->next_to_use + 1) % ring->count;
+
+	return 0;
+}
+
+static int igc_fpe_xmit_smd_frame(struct igc_adapter *adapter,
+				  enum igc_txd_popts_type type)
+{
+	int cpu = smp_processor_id();
+	struct netdev_queue *nq;
+	struct igc_ring *ring;
+	struct sk_buff *skb;
+	int err;
+
+	ring = igc_get_tx_ring(adapter, cpu);
+	nq = txring_txq(ring);
+
+	skb = alloc_skb(SMD_FRAME_SIZE, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_put_zero(skb, SMD_FRAME_SIZE);
+
+	__netif_tx_lock(nq, cpu);
+
+	err = igc_fpe_init_tx_descriptor(ring, skb, type);
+	igc_flush_tx_descriptors(ring);
+
+	__netif_tx_unlock(nq);
+
+	return err;
+}
+
+static void igc_fpe_configure_tx(struct ethtool_mmsv *mmsv, bool tx_enable)
+{
+	struct igc_fpe_t *fpe = container_of(mmsv, struct igc_fpe_t, mmsv);
+	struct igc_adapter *adapter;
+
+	adapter = container_of(fpe, struct igc_adapter, fpe);
+	adapter->fpe.tx_enabled = tx_enable;
+
+	/* Update config since tx_enabled affects preemptible queue configuration */
+	igc_tsn_offload_apply(adapter);
+}
+
+static void igc_fpe_send_mpacket(struct ethtool_mmsv *mmsv,
+				 enum ethtool_mpacket type)
+{
+	struct igc_fpe_t *fpe = container_of(mmsv, struct igc_fpe_t, mmsv);
+	struct igc_adapter *adapter;
+	int err;
+
+	adapter = container_of(fpe, struct igc_adapter, fpe);
+
+	if (type == ETHTOOL_MPACKET_VERIFY) {
+		err = igc_fpe_xmit_smd_frame(adapter, SMD_V);
+		if (err && net_ratelimit())
+			netdev_err(adapter->netdev, "Error sending SMD-V\n");
+	} else if (type == ETHTOOL_MPACKET_RESPONSE) {
+		err = igc_fpe_xmit_smd_frame(adapter, SMD_R);
+		if (err && net_ratelimit())
+			netdev_err(adapter->netdev, "Error sending SMD-R frame\n");
+	}
+}
+
+static const struct ethtool_mmsv_ops igc_mmsv_ops = {
+	.configure_tx = igc_fpe_configure_tx,
+	.send_mpacket = igc_fpe_send_mpacket,
+};
+
+void igc_fpe_init(struct igc_adapter *adapter)
+{
+	adapter->fpe.tx_min_frag_size = TX_MIN_FRAG_SIZE;
+	adapter->fpe.tx_enabled = false;
+	ethtool_mmsv_init(&adapter->fpe.mmsv, adapter->netdev, &igc_mmsv_ops);
+}
+
+void igc_fpe_clear_preempt_queue(struct igc_adapter *adapter)
+{
+	for (int i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *tx_ring = adapter->tx_ring[i];
+
+		tx_ring->preemptible = false;
+	}
+}
+
+static u32 igc_fpe_map_preempt_tc_to_queue(const struct igc_adapter *adapter,
+					   unsigned long preemptible_tcs)
+{
+	struct net_device *dev = adapter->netdev;
+	u32 i, queue = 0;
+
+	for (i = 0; i < dev->num_tc; i++) {
+		u32 offset, count;
+
+		if (!(preemptible_tcs & BIT(i)))
+			continue;
+
+		offset = dev->tc_to_txq[i].offset;
+		count = dev->tc_to_txq[i].count;
+		queue |= GENMASK(offset + count - 1, offset);
+	}
+
+	return queue;
+}
+
+void igc_fpe_save_preempt_queue(struct igc_adapter *adapter,
+				const struct tc_mqprio_qopt_offload *mqprio)
+{
+	u32 preemptible_queue = igc_fpe_map_preempt_tc_to_queue(adapter,
+								mqprio->preemptible_tcs);
+
+	for (int i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *tx_ring = adapter->tx_ring[i];
+
+		tx_ring->preemptible = !!(preemptible_queue & BIT(i));
+	}
+}
+
 static bool is_any_launchtime(struct igc_adapter *adapter)
 {
 	int i;
@@ -37,17 +234,16 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter)
 {
 	unsigned int new_flags = adapter->flags & ~IGC_FLAG_TSN_ANY_ENABLED;
 
-	if (adapter->taprio_offload_enable)
-		new_flags |= IGC_FLAG_TSN_QBV_ENABLED;
 
-	if (is_any_launchtime(adapter))
+	if (adapter->taprio_offload_enable || is_any_launchtime(adapter) ||
+	    adapter->strict_priority_enable)
 		new_flags |= IGC_FLAG_TSN_QBV_ENABLED;
 
 	if (is_cbs_enabled(adapter))
 		new_flags |= IGC_FLAG_TSN_QAV_ENABLED;
 
-	if (adapter->strict_priority_enable)
-		new_flags |= IGC_FLAG_TSN_LEGACY_ENABLED;
+	if (adapter->fpe.mmsv.pmac_enabled)
+		new_flags |= IGC_FLAG_TSN_PREEMPT_ENABLED;
 
 	return new_flags;
 }
@@ -105,7 +301,7 @@ bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter)
 		adapter->taprio_offload_enable;
 }
 
-static void igc_tsn_tx_arb(struct igc_adapter *adapter, u16 *queue_per_tc)
+static void igc_tsn_tx_arb(struct igc_adapter *adapter, bool reverse_prio)
 {
 	struct igc_hw *hw = &adapter->hw;
 	u32 txarb;
@@ -117,56 +313,91 @@ static void igc_tsn_tx_arb(struct igc_adapter *adapter, u16 *queue_per_tc)
 		   IGC_TXARB_TXQ_PRIO_2_MASK |
 		   IGC_TXARB_TXQ_PRIO_3_MASK);
 
-	txarb |= IGC_TXARB_TXQ_PRIO_0(queue_per_tc[3]);
-	txarb |= IGC_TXARB_TXQ_PRIO_1(queue_per_tc[2]);
-	txarb |= IGC_TXARB_TXQ_PRIO_2(queue_per_tc[1]);
-	txarb |= IGC_TXARB_TXQ_PRIO_3(queue_per_tc[0]);
+	if (reverse_prio) {
+		txarb |= IGC_TXARB_TXQ_PRIO_0(TX_QUEUE_3);
+		txarb |= IGC_TXARB_TXQ_PRIO_1(TX_QUEUE_2);
+		txarb |= IGC_TXARB_TXQ_PRIO_2(TX_QUEUE_1);
+		txarb |= IGC_TXARB_TXQ_PRIO_3(TX_QUEUE_0);
+	} else {
+		txarb |= IGC_TXARB_TXQ_PRIO_0(TX_QUEUE_0);
+		txarb |= IGC_TXARB_TXQ_PRIO_1(TX_QUEUE_1);
+		txarb |= IGC_TXARB_TXQ_PRIO_2(TX_QUEUE_2);
+		txarb |= IGC_TXARB_TXQ_PRIO_3(TX_QUEUE_3);
+	}
 
 	wr32(IGC_TXARB, txarb);
 }
 
+/**
+ * igc_tsn_set_rxpbsize - Set the receive packet buffer size
+ * @adapter: Pointer to the igc_adapter structure
+ * @rxpbs_exp_bmc_be: Value to set the receive packet buffer size, including
+ *                    express buffer, BMC buffer, and Best Effort buffer
+ *
+ * The IGC_RXPBS register value may include allocations for the Express buffer,
+ * BMC buffer, Best Effort buffer, and the timestamp descriptor buffer
+ * (IGC_RXPBS_CFG_TS_EN).
+ */
+static void igc_tsn_set_rxpbsize(struct igc_adapter *adapter,
+				 u32 rxpbs_exp_bmc_be)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 rxpbs = rd32(IGC_RXPBS);
+
+	rxpbs &= ~(IGC_RXPBSIZE_EXP_MASK | IGC_BMC2OSPBSIZE_MASK |
+		   IGC_RXPBSIZE_BE_MASK);
+	rxpbs |= rxpbs_exp_bmc_be;
+
+	wr32(IGC_RXPBS, rxpbs);
+}
+
 /* Returns the TSN specific registers to their default values after
  * the adapter is reset.
  */
 static int igc_tsn_disable_offload(struct igc_adapter *adapter)
 {
-	u16 queue_per_tc[4] = { 3, 2, 1, 0 };
 	struct igc_hw *hw = &adapter->hw;
 	u32 tqavctrl;
 	int i;
 
 	wr32(IGC_GTXOFFSET, 0);
-	wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT);
+	wr32(IGC_TXPBS, IGC_TXPBSIZE_DEFAULT);
 	wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT);
 
+	igc_tsn_set_rxpbsize(adapter, IGC_RXPBSIZE_EXP_BMC_DEFAULT);
+
 	if (igc_is_device_id_i226(hw))
 		igc_tsn_restore_retx_default(adapter);
 
 	tqavctrl = rd32(IGC_TQAVCTRL);
 	tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN |
-		      IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS);
+		      IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS |
+		      IGC_TQAVCTRL_PREEMPT_ENA | IGC_TQAVCTRL_MIN_FRAG_MASK);
 
 	wr32(IGC_TQAVCTRL, tqavctrl);
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
+		int reg_idx = adapter->tx_ring[i]->reg_idx;
+		u32 txdctl;
+
 		wr32(IGC_TXQCTL(i), 0);
 		wr32(IGC_STQT(i), 0);
 		wr32(IGC_ENDQT(i), NSEC_PER_SEC);
+
+		txdctl = rd32(IGC_TXDCTL(reg_idx));
+		txdctl &= ~IGC_TXDCTL_PRIORITY_HIGH;
+		wr32(IGC_TXDCTL(reg_idx), txdctl);
 	}
 
 	wr32(IGC_QBVCYCLET_S, 0);
 	wr32(IGC_QBVCYCLET, NSEC_PER_SEC);
 
-	/* Reset mqprio TC configuration. */
-	netdev_reset_tc(adapter->netdev);
-
 	/* Restore the default Tx arbitration: Priority 0 has the highest
 	 * priority and is assigned to queue 0 and so on and so forth.
 	 */
-	igc_tsn_tx_arb(adapter, queue_per_tc);
+	igc_tsn_tx_arb(adapter, false);
 
 	adapter->flags &= ~IGC_FLAG_TSN_QBV_ENABLED;
-	adapter->flags &= ~IGC_FLAG_TSN_LEGACY_ENABLED;
 
 	return 0;
 }
@@ -190,57 +421,53 @@ static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter)
 	wr32(IGC_RETX_CTL, retxctl);
 }
 
+static u8 igc_fpe_get_frag_size_mult(const struct igc_fpe_t *fpe)
+{
+	u8 mult = (fpe->tx_min_frag_size / TX_MIN_FRAG_SIZE) - 1;
+
+	return clamp_t(u8, mult, MIN_MULTPLIER_TX_MIN_FRAG,
+		       MAX_MULTPLIER_TX_MIN_FRAG);
+}
+
+u32 igc_fpe_get_supported_frag_size(u32 frag_size)
+{
+	static const u32 supported_sizes[] = { 64, 128, 192, 256 };
+
+	/* Find the smallest supported size that is >= frag_size */
+	for (int i = 0; i < ARRAY_SIZE(supported_sizes); i++) {
+		if (frag_size <= supported_sizes[i])
+			return supported_sizes[i];
+	}
+
+	/* Should not happen */
+	return TX_MAX_FRAG_SIZE;
+}
+
 static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
 	u32 tqavctrl, baset_l, baset_h;
 	u32 sec, nsec, cycle;
 	ktime_t base_time, systim;
+	u32 frag_size_mult;
 	int i;
 
 	wr32(IGC_TSAUXC, 0);
 	wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN);
 	wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN);
 
+	igc_tsn_set_rxpbsize(adapter, IGC_RXPBSIZE_EXP_BMC_BE_TSN);
+
 	if (igc_is_device_id_i226(hw))
 		igc_tsn_set_retx_qbvfullthreshold(adapter);
 
-	if (adapter->strict_priority_enable) {
-		int err;
-
-		err = netdev_set_num_tc(adapter->netdev, adapter->num_tc);
-		if (err)
-			return err;
-
-		for (i = 0; i < adapter->num_tc; i++) {
-			err = netdev_set_tc_queue(adapter->netdev, i, 1,
-						  adapter->queue_per_tc[i]);
-			if (err)
-				return err;
-		}
-
-		/* In case the card is configured with less than four queues. */
-		for (; i < IGC_MAX_TX_QUEUES; i++)
-			adapter->queue_per_tc[i] = i;
-
-		/* Configure queue priorities according to the user provided
-		 * mapping.
-		 */
-		igc_tsn_tx_arb(adapter, adapter->queue_per_tc);
-
-		/* Enable legacy TSN mode which will do strict priority without
-		 * any other TSN features.
-		 */
-		tqavctrl = rd32(IGC_TQAVCTRL);
-		tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN;
-		tqavctrl &= ~IGC_TQAVCTRL_ENHANCED_QAV;
-		wr32(IGC_TQAVCTRL, tqavctrl);
-
-		return 0;
-	}
+	if (adapter->strict_priority_enable ||
+	    adapter->flags & IGC_FLAG_TSN_REVERSE_TXQ_PRIO)
+		igc_tsn_tx_arb(adapter, true);
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		struct igc_ring *ring = adapter->tx_ring[i];
+		u32 txdctl = rd32(IGC_TXDCTL(ring->reg_idx));
 		u32 txqctl = 0;
 		u16 cbs_value;
 		u32 tqavcc;
@@ -274,6 +501,22 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 		if (ring->launchtime_enable)
 			txqctl |= IGC_TXQCTL_QUEUE_MODE_LAUNCHT;
 
+		if (!adapter->fpe.tx_enabled) {
+			/* fpe inactive: clear both flags */
+			txqctl &= ~IGC_TXQCTL_PREEMPTIBLE;
+			txdctl &= ~IGC_TXDCTL_PRIORITY_HIGH;
+		} else if (ring->preemptible) {
+			/* fpe active + preemptible: enable preemptible queue + set low priority */
+			txqctl |= IGC_TXQCTL_PREEMPTIBLE;
+			txdctl &= ~IGC_TXDCTL_PRIORITY_HIGH;
+		} else {
+			/* fpe active + express: enable express queue + set high priority */
+			txqctl &= ~IGC_TXQCTL_PREEMPTIBLE;
+			txdctl |= IGC_TXDCTL_PRIORITY_HIGH;
+		}
+
+		wr32(IGC_TXDCTL(ring->reg_idx), txdctl);
+
 		/* Skip configuring CBS for Q2 and Q3 */
 		if (i > 1)
 			goto skip_cbs;
@@ -361,10 +604,16 @@ skip_cbs:
 		wr32(IGC_TXQCTL(i), txqctl);
 	}
 
-	tqavctrl = rd32(IGC_TQAVCTRL) & ~IGC_TQAVCTRL_FUTSCDDIS;
-
+	tqavctrl = rd32(IGC_TQAVCTRL) & ~(IGC_TQAVCTRL_FUTSCDDIS |
+		   IGC_TQAVCTRL_PREEMPT_ENA | IGC_TQAVCTRL_MIN_FRAG_MASK);
 	tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV;
 
+	if (adapter->fpe.mmsv.pmac_enabled)
+		tqavctrl |= IGC_TQAVCTRL_PREEMPT_ENA;
+
+	frag_size_mult = igc_fpe_get_frag_size_mult(&adapter->fpe);
+	tqavctrl |= FIELD_PREP(IGC_TQAVCTRL_MIN_FRAG_MASK, frag_size_mult);
+
 	adapter->qbv_count++;
 
 	cycle = adapter->cycle_time;
@@ -425,6 +674,14 @@ int igc_tsn_reset(struct igc_adapter *adapter)
 	unsigned int new_flags;
 	int err = 0;
 
+	if (adapter->fpe.mmsv.pmac_enabled) {
+		err = igc_enable_empty_addr_recv(adapter);
+		if (err && net_ratelimit())
+			netdev_err(adapter->netdev, "Error adding empty address to MAC filter\n");
+	} else {
+		igc_disable_empty_addr_recv(adapter);
+	}
+
 	new_flags = igc_tsn_new_flags(adapter);
 
 	if (!(new_flags & IGC_FLAG_TSN_ANY_ENABLED))
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h
index 98ec845a86bf..a95b893459d7 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.h
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.h
@@ -4,9 +4,66 @@
 #ifndef _IGC_TSN_H_
 #define _IGC_TSN_H_
 
+#include <net/pkt_sched.h>
+
+#define IGC_RX_MIN_FRAG_SIZE		60
+#define SMD_FRAME_SIZE			60
+
+enum igc_txd_popts_type {
+	SMD_V = 0x01,
+	SMD_R = 0x02,
+};
+
+DECLARE_STATIC_KEY_FALSE(igc_fpe_enabled);
+
+void igc_fpe_init(struct igc_adapter *adapter);
+void igc_fpe_clear_preempt_queue(struct igc_adapter *adapter);
+void igc_fpe_save_preempt_queue(struct igc_adapter *adapter,
+				const struct tc_mqprio_qopt_offload *mqprio);
+u32 igc_fpe_get_supported_frag_size(u32 frag_size);
 int igc_tsn_offload_apply(struct igc_adapter *adapter);
 int igc_tsn_reset(struct igc_adapter *adapter);
 void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter);
 bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter);
 
+static inline bool igc_fpe_is_pmac_enabled(struct igc_adapter *adapter)
+{
+	return static_branch_unlikely(&igc_fpe_enabled) &&
+	       adapter->fpe.mmsv.pmac_enabled;
+}
+
+static inline bool igc_fpe_handle_mpacket(struct igc_adapter *adapter,
+					  union igc_adv_rx_desc *rx_desc,
+					  unsigned int size, void *pktbuf)
+{
+	u32 status_error = le32_to_cpu(rx_desc->wb.upper.status_error);
+	int smd;
+
+	smd = FIELD_GET(IGC_RXDADV_STAT_SMD_TYPE_MASK, status_error);
+	if (smd != IGC_RXD_STAT_SMD_TYPE_V && smd != IGC_RXD_STAT_SMD_TYPE_R)
+		return false;
+
+	if (size == SMD_FRAME_SIZE && mem_is_zero(pktbuf, SMD_FRAME_SIZE)) {
+		struct ethtool_mmsv *mmsv = &adapter->fpe.mmsv;
+		enum ethtool_mmsv_event event;
+
+		if (smd == IGC_RXD_STAT_SMD_TYPE_V)
+			event = ETHTOOL_MMSV_LP_SENT_VERIFY_MPACKET;
+		else
+			event = ETHTOOL_MMSV_LP_SENT_RESPONSE_MPACKET;
+
+		ethtool_mmsv_event_handle(mmsv, event);
+	}
+
+	return true;
+}
+
+static inline bool igc_fpe_transmitted_smd_v(union igc_adv_tx_desc *tx_desc)
+{
+	u32 olinfo_status = le32_to_cpu(tx_desc->read.olinfo_status);
+	u8 smd = FIELD_GET(IGC_TXD_POPTS_SMD_MASK, olinfo_status);
+
+	return smd == SMD_V;
+}
+
 #endif /* _IGC_BASE_H */
diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c
index e27af72aada8..9eb47b4beb06 100644
--- a/drivers/net/ethernet/intel/igc/igc_xdp.c
+++ b/drivers/net/ethernet/intel/igc/igc_xdp.c
@@ -13,6 +13,8 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
 	struct net_device *dev = adapter->netdev;
 	bool if_running = netif_running(dev);
 	struct bpf_prog *old_prog;
+	bool need_update;
+	unsigned int i;
 
 	if (dev->mtu > ETH_DATA_LEN) {
 		/* For now, the driver doesn't support XDP functionality with
@@ -22,8 +24,14 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
 		return -EOPNOTSUPP;
 	}
 
-	if (if_running)
-		igc_close(dev);
+	need_update = !!adapter->xdp_prog != !!prog;
+	if (if_running && need_update) {
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			igc_disable_rx_ring(adapter->rx_ring[i]);
+			igc_disable_tx_ring(adapter->tx_ring[i]);
+			napi_disable(&adapter->rx_ring[i]->q_vector->napi);
+		}
+	}
 
 	old_prog = xchg(&adapter->xdp_prog, prog);
 	if (old_prog)
@@ -34,8 +42,13 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
 	else
 		xdp_features_clear_redirect_target(dev);
 
-	if (if_running)
-		igc_open(dev);
+	if (if_running && need_update) {
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			napi_enable(&adapter->rx_ring[i]->q_vector->napi);
+			igc_enable_tx_ring(adapter->tx_ring[i]);
+			igc_enable_rx_ring(adapter->rx_ring[i]);
+		}
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile
index 965e5ce1b326..2e7738f41c58 100644
--- a/drivers/net/ethernet/intel/ixgbe/Makefile
+++ b/drivers/net/ethernet/intel/ixgbe/Makefile
@@ -1,15 +1,17 @@
 # SPDX-License-Identifier: GPL-2.0
-# Copyright(c) 1999 - 2018 Intel Corporation.
+# Copyright(c) 1999 - 2024 Intel Corporation.
 #
 # Makefile for the Intel(R) 10GbE PCI Express ethernet driver
 #
 
+subdir-ccflags-y += -I$(src)
 obj-$(CONFIG_IXGBE) += ixgbe.o
 
 ixgbe-y := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
            ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
            ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \
-           ixgbe_xsk.o
+           ixgbe_xsk.o ixgbe_e610.o devlink/devlink.o ixgbe_fw_update.o \
+	   devlink/region.o
 
 ixgbe-$(CONFIG_IXGBE_DCB) +=  ixgbe_dcb.o ixgbe_dcb_82598.o \
                               ixgbe_dcb_82599.o ixgbe_dcb_nl.o
diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c
new file mode 100644
index 000000000000..d227f4d2a2d1
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c
@@ -0,0 +1,558 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025, Intel Corporation. */
+
+#include "ixgbe.h"
+#include "devlink.h"
+#include "ixgbe_fw_update.h"
+
+struct ixgbe_info_ctx {
+	char buf[128];
+	struct ixgbe_orom_info pending_orom;
+	struct ixgbe_nvm_info pending_nvm;
+	struct ixgbe_netlist_info pending_netlist;
+	struct ixgbe_hw_dev_caps dev_caps;
+};
+
+enum ixgbe_devlink_version_type {
+	IXGBE_DL_VERSION_RUNNING,
+	IXGBE_DL_VERSION_STORED
+};
+
+static void ixgbe_info_get_dsn(struct ixgbe_adapter *adapter,
+			       struct ixgbe_info_ctx *ctx)
+{
+	u8 dsn[8];
+
+	/* Copy the DSN into an array in Big Endian format */
+	put_unaligned_be64(pci_get_dsn(adapter->pdev), dsn);
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%8phD", dsn);
+}
+
+static void ixgbe_info_orom_ver(struct ixgbe_adapter *adapter,
+				struct ixgbe_info_ctx *ctx,
+				enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_nvm_version nvm_ver;
+
+	ctx->buf[0] = '\0';
+
+	if (hw->mac.type == ixgbe_mac_e610) {
+		struct ixgbe_orom_info *orom = &adapter->hw.flash.orom;
+
+		if (type == IXGBE_DL_VERSION_STORED &&
+		    ctx->dev_caps.common_cap.nvm_update_pending_orom)
+			orom = &ctx->pending_orom;
+
+		snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u",
+			 orom->major, orom->build, orom->patch);
+		return;
+	}
+
+	ixgbe_get_oem_prod_version(hw, &nvm_ver);
+	if (nvm_ver.oem_valid) {
+		snprintf(ctx->buf, sizeof(ctx->buf), "%x.%x.%x",
+			 nvm_ver.oem_major, nvm_ver.oem_minor,
+			 nvm_ver.oem_release);
+
+		return;
+	}
+
+	ixgbe_get_orom_version(hw, &nvm_ver);
+	if (nvm_ver.or_valid)
+		snprintf(ctx->buf, sizeof(ctx->buf), "%d.%d.%d",
+			 nvm_ver.or_major, nvm_ver.or_build, nvm_ver.or_patch);
+}
+
+static void ixgbe_info_eetrack(struct ixgbe_adapter *adapter,
+			       struct ixgbe_info_ctx *ctx,
+			       enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_nvm_version nvm_ver;
+
+	if (hw->mac.type == ixgbe_mac_e610) {
+		u32 eetrack = hw->flash.nvm.eetrack;
+
+		if (type == IXGBE_DL_VERSION_STORED &&
+		    ctx->dev_caps.common_cap.nvm_update_pending_nvm)
+			eetrack = ctx->pending_nvm.eetrack;
+
+		snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", eetrack);
+		return;
+	}
+
+	ixgbe_get_oem_prod_version(hw, &nvm_ver);
+
+	/* No ETRACK version for OEM */
+	if (nvm_ver.oem_valid) {
+		ctx->buf[0] = '\0';
+		return;
+	}
+
+	ixgbe_get_etk_id(hw, &nvm_ver);
+	snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", nvm_ver.etk_id);
+}
+
+static void ixgbe_info_fw_api(struct ixgbe_adapter *adapter,
+			      struct ixgbe_info_ctx *ctx)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u",
+		 hw->api_maj_ver, hw->api_min_ver, hw->api_patch);
+}
+
+static void ixgbe_info_fw_build(struct ixgbe_adapter *adapter,
+				struct ixgbe_info_ctx *ctx)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", hw->fw_build);
+}
+
+static void ixgbe_info_fw_srev(struct ixgbe_adapter *adapter,
+			       struct ixgbe_info_ctx *ctx,
+			       enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_nvm)
+		nvm = &ctx->pending_nvm;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%u", nvm->srev);
+}
+
+static void ixgbe_info_orom_srev(struct ixgbe_adapter *adapter,
+				 struct ixgbe_info_ctx *ctx,
+				 enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_orom_info *orom = &adapter->hw.flash.orom;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_orom)
+		orom = &ctx->pending_orom;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%u", orom->srev);
+}
+
+static void ixgbe_info_nvm_ver(struct ixgbe_adapter *adapter,
+			       struct ixgbe_info_ctx *ctx,
+			       enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_nvm)
+		nvm = &ctx->pending_nvm;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%x.%02x", nvm->major, nvm->minor);
+}
+
+static void ixgbe_info_netlist_ver(struct ixgbe_adapter *adapter,
+				   struct ixgbe_info_ctx *ctx,
+				   enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_netlist_info *netlist = &adapter->hw.flash.netlist;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_netlist)
+		netlist = &ctx->pending_netlist;
+
+	/* The netlist version fields are BCD formatted */
+	snprintf(ctx->buf, sizeof(ctx->buf), "%x.%x.%x-%x.%x.%x",
+		 netlist->major, netlist->minor,
+		 netlist->type >> 16, netlist->type & 0xFFFF,
+		 netlist->rev, netlist->cust_ver);
+}
+
+static void ixgbe_info_netlist_build(struct ixgbe_adapter *adapter,
+				     struct ixgbe_info_ctx *ctx,
+				     enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_netlist_info *netlist = &adapter->hw.flash.netlist;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_netlist)
+		netlist = &ctx->pending_netlist;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", netlist->hash);
+}
+
+static int ixgbe_set_ctx_dev_caps(struct ixgbe_hw *hw,
+				  struct ixgbe_info_ctx *ctx,
+				  struct netlink_ext_ack *extack)
+{
+	bool *pending_orom, *pending_nvm, *pending_netlist;
+	int err;
+
+	err = ixgbe_discover_dev_caps(hw, &ctx->dev_caps);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Unable to discover device capabilities");
+		return err;
+	}
+
+	pending_orom = &ctx->dev_caps.common_cap.nvm_update_pending_orom;
+	pending_nvm = &ctx->dev_caps.common_cap.nvm_update_pending_nvm;
+	pending_netlist = &ctx->dev_caps.common_cap.nvm_update_pending_netlist;
+
+	if (*pending_orom) {
+		err = ixgbe_get_inactive_orom_ver(hw, &ctx->pending_orom);
+		if (err)
+			*pending_orom = false;
+	}
+
+	if (*pending_nvm) {
+		err = ixgbe_get_inactive_nvm_ver(hw, &ctx->pending_nvm);
+		if (err)
+			*pending_nvm = false;
+	}
+
+	if (*pending_netlist) {
+		err = ixgbe_get_inactive_netlist_ver(hw, &ctx->pending_netlist);
+		if (err)
+			*pending_netlist = false;
+	}
+
+	return 0;
+}
+
+static int ixgbe_devlink_info_get_e610(struct ixgbe_adapter *adapter,
+				       struct devlink_info_req *req,
+				       struct ixgbe_info_ctx *ctx)
+{
+	int err;
+
+	ixgbe_info_fw_api(adapter, ctx);
+	err = devlink_info_version_running_put(req,
+					       DEVLINK_INFO_VERSION_GENERIC_FW_MGMT_API,
+					       ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_fw_build(adapter, ctx);
+	err = devlink_info_version_running_put(req, "fw.mgmt.build", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_fw_srev(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req, "fw.mgmt.srev", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_orom_srev(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req, "fw.undi.srev", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_nvm_ver(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req, "fw.psid.api", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_netlist_ver(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req, "fw.netlist", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_netlist_build(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	return devlink_info_version_running_put(req, "fw.netlist.build",
+						ctx->buf);
+}
+
+static int
+ixgbe_devlink_pending_info_get_e610(struct ixgbe_adapter *adapter,
+				    struct devlink_info_req *req,
+				    struct ixgbe_info_ctx *ctx)
+{
+	int err;
+
+	ixgbe_info_orom_ver(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req,
+					      DEVLINK_INFO_VERSION_GENERIC_FW_UNDI,
+					      ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_eetrack(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req,
+					      DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID,
+					      ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_fw_srev(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req, "fw.mgmt.srev", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_orom_srev(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req, "fw.undi.srev", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_nvm_ver(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req, "fw.psid.api", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_netlist_ver(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req, "fw.netlist", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_netlist_build(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	return devlink_info_version_stored_put(req, "fw.netlist.build",
+					       ctx->buf);
+}
+
+static int ixgbe_devlink_info_get(struct devlink *devlink,
+				  struct devlink_info_req *req,
+				  struct netlink_ext_ack *extack)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_info_ctx *ctx;
+	int err;
+
+	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	if (hw->mac.type == ixgbe_mac_e610)
+		ixgbe_refresh_fw_version(adapter);
+
+	ixgbe_info_get_dsn(adapter, ctx);
+	err = devlink_info_serial_number_put(req, ctx->buf);
+	if (err)
+		goto free_ctx;
+
+	err = hw->eeprom.ops.read_pba_string(hw, ctx->buf, sizeof(ctx->buf));
+	if (err)
+		goto free_ctx;
+
+	err = devlink_info_version_fixed_put(req,
+					     DEVLINK_INFO_VERSION_GENERIC_BOARD_ID,
+					     ctx->buf);
+	if (err)
+		goto free_ctx;
+
+	ixgbe_info_orom_ver(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req,
+					       DEVLINK_INFO_VERSION_GENERIC_FW_UNDI,
+					       ctx->buf);
+	if (err)
+		goto free_ctx;
+
+	ixgbe_info_eetrack(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req,
+					       DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID,
+					       ctx->buf);
+	if (err || hw->mac.type != ixgbe_mac_e610)
+		goto free_ctx;
+
+	err = ixgbe_set_ctx_dev_caps(hw, ctx, extack);
+	if (err)
+		goto free_ctx;
+
+	err = ixgbe_devlink_info_get_e610(adapter, req, ctx);
+	if (err)
+		goto free_ctx;
+
+	err = ixgbe_devlink_pending_info_get_e610(adapter, req, ctx);
+free_ctx:
+	kfree(ctx);
+	return err;
+}
+
+/**
+ * ixgbe_devlink_reload_empr_start - Start EMP reset to activate new firmware
+ * @devlink: pointer to the devlink instance to reload
+ * @netns_change: if true, the network namespace is changing
+ * @action: the action to perform. Must be DEVLINK_RELOAD_ACTION_FW_ACTIVATE
+ * @limit: limits on what reload should do, such as not resetting
+ * @extack: netlink extended ACK structure
+ *
+ * Allow user to activate new Embedded Management Processor firmware by
+ * issuing device specific EMP reset. Called in response to
+ * a DEVLINK_CMD_RELOAD with the DEVLINK_RELOAD_ACTION_FW_ACTIVATE.
+ *
+ * Note that teardown and rebuild of the driver state happens automatically as
+ * part of an interrupt and watchdog task. This is because all physical
+ * functions on the device must be able to reset when an EMP reset occurs from
+ * any source.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_devlink_reload_empr_start(struct devlink *devlink,
+					   bool netns_change,
+					   enum devlink_reload_action action,
+					   enum devlink_reload_limit limit,
+					   struct netlink_ext_ack *extack)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 pending;
+	int err;
+
+	if (hw->mac.type != ixgbe_mac_e610)
+		return -EOPNOTSUPP;
+
+	err = ixgbe_get_pending_updates(adapter, &pending, extack);
+	if (err)
+		return err;
+
+	/* Pending is a bitmask of which flash banks have a pending update,
+	 * including the main NVM bank, the Option ROM bank, and the netlist
+	 * bank. If any of these bits are set, then there is a pending update
+	 * waiting to be activated.
+	 */
+	if (!pending) {
+		NL_SET_ERR_MSG_MOD(extack, "No pending firmware update");
+		return -ECANCELED;
+	}
+
+	if (adapter->fw_emp_reset_disabled) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "EMP reset is not available. To activate firmware, a reboot or power cycle is needed");
+		return -ECANCELED;
+	}
+
+	err = ixgbe_aci_nvm_update_empr(hw);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to trigger EMP device reset to reload firmware");
+
+	return err;
+}
+
+/*Wait for 10 sec with 0.5 sec tic. EMPR takes no less than half of a sec */
+#define IXGBE_DEVLINK_RELOAD_TIMEOUT_SEC	20
+
+/**
+ * ixgbe_devlink_reload_empr_finish - finishes EMP reset
+ * @devlink: pointer to the devlink instance
+ * @action: the action to perform.
+ * @limit: limits on what reload should do
+ * @actions_performed: actions performed
+ * @extack: netlink extended ACK structure
+ *
+ * Wait for new NVM to be loaded during EMP reset.
+ *
+ * Return: -ETIME when timer is exceeded, 0 on success.
+ */
+static int ixgbe_devlink_reload_empr_finish(struct devlink *devlink,
+					    enum devlink_reload_action action,
+					    enum devlink_reload_limit limit,
+					    u32 *actions_performed,
+					    struct netlink_ext_ack *extack)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i = 0;
+	u32 fwsm;
+
+	do {
+		/* Just right away after triggering EMP reset the FWSM register
+		 * may be not cleared yet, so begin the loop with the delay
+		 * in order to not check the not updated register.
+		 */
+		mdelay(500);
+
+		fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
+
+		if (i++ >= IXGBE_DEVLINK_RELOAD_TIMEOUT_SEC)
+			return -ETIME;
+
+	} while (!(fwsm & IXGBE_FWSM_FW_VAL_BIT));
+
+	*actions_performed = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE);
+
+	adapter->flags2 &= ~(IXGBE_FLAG2_API_MISMATCH |
+			     IXGBE_FLAG2_FW_ROLLBACK);
+
+	return 0;
+}
+
+static const struct devlink_ops ixgbe_devlink_ops = {
+	.info_get = ixgbe_devlink_info_get,
+	.supported_flash_update_params =
+		DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK,
+	.flash_update = ixgbe_flash_pldm_image,
+	.reload_actions = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE),
+	.reload_down = ixgbe_devlink_reload_empr_start,
+	.reload_up = ixgbe_devlink_reload_empr_finish,
+};
+
+/**
+ * ixgbe_allocate_devlink - Allocate devlink instance
+ * @dev: device to allocate devlink for
+ *
+ * Allocate a devlink instance for this physical function.
+ *
+ * Return: pointer to the device adapter structure on success,
+ * ERR_PTR(-ENOMEM) when allocation failed.
+ */
+struct ixgbe_adapter *ixgbe_allocate_devlink(struct device *dev)
+{
+	struct ixgbe_adapter *adapter;
+	struct devlink *devlink;
+
+	devlink = devlink_alloc(&ixgbe_devlink_ops, sizeof(*adapter), dev);
+	if (!devlink)
+		return ERR_PTR(-ENOMEM);
+
+	adapter = devlink_priv(devlink);
+	adapter->devlink = devlink;
+
+	return adapter;
+}
+
+/**
+ * ixgbe_devlink_set_switch_id - Set unique switch ID based on PCI DSN
+ * @adapter: pointer to the device adapter structure
+ * @ppid: struct with switch id information
+ */
+static void ixgbe_devlink_set_switch_id(struct ixgbe_adapter *adapter,
+					struct netdev_phys_item_id *ppid)
+{
+	u64 id = pci_get_dsn(adapter->pdev);
+
+	ppid->id_len = sizeof(id);
+	put_unaligned_be64(id, &ppid->id);
+}
+
+/**
+ * ixgbe_devlink_register_port - Register devlink port
+ * @adapter: pointer to the device adapter structure
+ *
+ * Create and register a devlink_port for this physical function.
+ *
+ * Return: 0 on success, error code on failure.
+ */
+int ixgbe_devlink_register_port(struct ixgbe_adapter *adapter)
+{
+	struct devlink_port *devlink_port = &adapter->devlink_port;
+	struct devlink *devlink = adapter->devlink;
+	struct device *dev = &adapter->pdev->dev;
+	struct devlink_port_attrs attrs = {};
+	int err;
+
+	attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
+	attrs.phys.port_number = adapter->hw.bus.func;
+	attrs.no_phys_port_name = 1;
+	ixgbe_devlink_set_switch_id(adapter, &attrs.switch_id);
+
+	devlink_port_attrs_set(devlink_port, &attrs);
+
+	err = devl_port_register(devlink, devlink_port, 0);
+	if (err) {
+		dev_err(dev,
+			"devlink port registration failed, err %d\n", err);
+	}
+
+	return err;
+}
diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.h b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.h
new file mode 100644
index 000000000000..381558058048
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025, Intel Corporation. */
+
+#ifndef _IXGBE_DEVLINK_H_
+#define _IXGBE_DEVLINK_H_
+
+struct ixgbe_adapter *ixgbe_allocate_devlink(struct device *dev);
+int ixgbe_devlink_register_port(struct ixgbe_adapter *adapter);
+void ixgbe_devlink_init_regions(struct ixgbe_adapter *adapter);
+void ixgbe_devlink_destroy_regions(struct ixgbe_adapter *adapter);
+
+#endif /* _IXGBE_DEVLINK_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/region.c b/drivers/net/ethernet/intel/ixgbe/devlink/region.c
new file mode 100644
index 000000000000..478b4f435120
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/devlink/region.c
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025, Intel Corporation. */
+
+#include "ixgbe.h"
+#include "devlink.h"
+
+#define IXGBE_DEVLINK_READ_BLK_SIZE (1024 * 1024)
+
+static const struct devlink_region_ops ixgbe_nvm_region_ops;
+static const struct devlink_region_ops ixgbe_sram_region_ops;
+
+static int ixgbe_devlink_parse_region(struct ixgbe_hw *hw,
+				      const struct devlink_region_ops *ops,
+				      bool *read_shadow_ram, u32 *nvm_size)
+{
+	if (ops == &ixgbe_nvm_region_ops) {
+		*read_shadow_ram = false;
+		*nvm_size = hw->flash.flash_size;
+	} else if (ops == &ixgbe_sram_region_ops) {
+		*read_shadow_ram = true;
+		*nvm_size = hw->flash.sr_words * 2u;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_devlink_nvm_snapshot - Capture a snapshot of the NVM content
+ * @devlink: the devlink instance
+ * @ops: the devlink region being snapshotted
+ * @extack: extended ACK response structure
+ * @data: on exit points to snapshot data buffer
+ *
+ * This function is called in response to the DEVLINK_CMD_REGION_NEW cmd.
+ *
+ * Capture a snapshot of the whole requested NVM region.
+ *
+ * No need to worry with freeing @data, devlink core takes care if it.
+ *
+ * Return: 0 on success, -EOPNOTSUPP for unsupported regions, -EBUSY when
+ * cannot lock NVM, -ENOMEM when cannot alloc mem and -EIO when error
+ * occurs during reading.
+ */
+static int ixgbe_devlink_nvm_snapshot(struct devlink *devlink,
+				      const struct devlink_region_ops *ops,
+				      struct netlink_ext_ack *extack, u8 **data)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool read_shadow_ram;
+	u8 *nvm_data, *buf;
+	u32 nvm_size, left;
+	u8 num_blks;
+	int err;
+
+	err = ixgbe_devlink_parse_region(hw, ops, &read_shadow_ram, &nvm_size);
+	if (err)
+		return err;
+
+	nvm_data = kvzalloc(nvm_size, GFP_KERNEL);
+	if (!nvm_data)
+		return -ENOMEM;
+
+	num_blks = DIV_ROUND_UP(nvm_size, IXGBE_DEVLINK_READ_BLK_SIZE);
+	buf = nvm_data;
+	left = nvm_size;
+
+	for (int i = 0; i < num_blks; i++) {
+		u32 read_sz = min_t(u32, IXGBE_DEVLINK_READ_BLK_SIZE, left);
+
+		/* Need to acquire NVM lock during each loop run because the
+		 * total period of reading whole NVM is longer than the maximum
+		 * period the lock can be taken defined by the IXGBE_NVM_TIMEOUT.
+		 */
+		err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to acquire NVM semaphore");
+			kvfree(nvm_data);
+			return -EBUSY;
+		}
+
+		err = ixgbe_read_flat_nvm(hw, i * IXGBE_DEVLINK_READ_BLK_SIZE,
+					  &read_sz, buf, read_shadow_ram);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to read RAM content");
+			ixgbe_release_nvm(hw);
+			kvfree(nvm_data);
+			return -EIO;
+		}
+
+		ixgbe_release_nvm(hw);
+
+		buf += read_sz;
+		left -= read_sz;
+	}
+
+	*data = nvm_data;
+	return 0;
+}
+
+/**
+ * ixgbe_devlink_devcaps_snapshot - Capture a snapshot of device capabilities
+ * @devlink: the devlink instance
+ * @ops: the devlink region being snapshotted
+ * @extack: extended ACK response structure
+ * @data: on exit points to snapshot data buffer
+ *
+ * This function is called in response to the DEVLINK_CMD_REGION_NEW for
+ * the device-caps devlink region.
+ *
+ * Capture a snapshot of the device capabilities reported by firmware.
+ *
+ * No need to worry with freeing @data, devlink core takes care if it.
+ *
+ * Return: 0 on success, -ENOMEM when cannot alloc mem, or return code of
+ * the reading operation.
+ */
+static int ixgbe_devlink_devcaps_snapshot(struct devlink *devlink,
+					  const struct devlink_region_ops *ops,
+					  struct netlink_ext_ack *extack,
+					  u8 **data)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_aci_cmd_list_caps_elem *caps;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	caps = kvzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL);
+	if (!caps)
+		return -ENOMEM;
+
+	err = ixgbe_aci_list_caps(hw, caps, IXGBE_ACI_MAX_BUFFER_SIZE, NULL,
+				  ixgbe_aci_opc_list_dev_caps);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to read device capabilities");
+		kvfree(caps);
+		return err;
+	}
+
+	*data = (u8 *)caps;
+	return 0;
+}
+
+/**
+ * ixgbe_devlink_nvm_read - Read a portion of NVM flash content
+ * @devlink: the devlink instance
+ * @ops: the devlink region to snapshot
+ * @extack: extended ACK response structure
+ * @offset: the offset to start at
+ * @size: the amount to read
+ * @data: the data buffer to read into
+ *
+ * This function is called in response to DEVLINK_CMD_REGION_READ to directly
+ * read a section of the NVM contents.
+ *
+ * Read from either the nvm-flash region either shadow-ram region.
+ *
+ * Return: 0 on success, -EOPNOTSUPP for unsupported regions, -EBUSY when
+ * cannot lock NVM, -ERANGE when buffer limit exceeded and -EIO when error
+ * occurs during reading.
+ */
+static int ixgbe_devlink_nvm_read(struct devlink *devlink,
+				  const struct devlink_region_ops *ops,
+				  struct netlink_ext_ack *extack,
+				  u64 offset, u32 size, u8 *data)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool read_shadow_ram;
+	u32 nvm_size;
+	int err;
+
+	err = ixgbe_devlink_parse_region(hw, ops, &read_shadow_ram, &nvm_size);
+	if (err)
+		return err;
+
+	if (offset + size > nvm_size) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot read beyond the region size");
+		return -ERANGE;
+	}
+
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore");
+		return -EBUSY;
+	}
+
+	err = ixgbe_read_flat_nvm(hw, (u32)offset, &size, data, read_shadow_ram);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents");
+		ixgbe_release_nvm(hw);
+		return -EIO;
+	}
+
+	ixgbe_release_nvm(hw);
+	return 0;
+}
+
+static const struct devlink_region_ops ixgbe_nvm_region_ops = {
+	.name = "nvm-flash",
+	.destructor = kvfree,
+	.snapshot = ixgbe_devlink_nvm_snapshot,
+	.read = ixgbe_devlink_nvm_read,
+};
+
+static const struct devlink_region_ops ixgbe_sram_region_ops = {
+	.name = "shadow-ram",
+	.destructor = kvfree,
+	.snapshot = ixgbe_devlink_nvm_snapshot,
+	.read = ixgbe_devlink_nvm_read,
+};
+
+static const struct devlink_region_ops ixgbe_devcaps_region_ops = {
+	.name = "device-caps",
+	.destructor = kvfree,
+	.snapshot = ixgbe_devlink_devcaps_snapshot,
+};
+
+/**
+ * ixgbe_devlink_init_regions - Initialize devlink regions
+ * @adapter: adapter instance
+ *
+ * Create devlink regions used to enable access to dump the contents of the
+ * flash memory of the device.
+ */
+void ixgbe_devlink_init_regions(struct ixgbe_adapter *adapter)
+{
+	struct devlink *devlink = adapter->devlink;
+	struct device *dev = &adapter->pdev->dev;
+	u64 nvm_size, sram_size;
+
+	if (adapter->hw.mac.type != ixgbe_mac_e610)
+		return;
+
+	nvm_size = adapter->hw.flash.flash_size;
+	adapter->nvm_region = devl_region_create(devlink, &ixgbe_nvm_region_ops,
+						 1, nvm_size);
+	if (IS_ERR(adapter->nvm_region)) {
+		dev_err(dev,
+			"Failed to create NVM devlink region, err %ld\n",
+			PTR_ERR(adapter->nvm_region));
+		adapter->nvm_region = NULL;
+	}
+
+	sram_size = adapter->hw.flash.sr_words * 2u;
+	adapter->sram_region = devl_region_create(devlink, &ixgbe_sram_region_ops,
+						  1, sram_size);
+	if (IS_ERR(adapter->sram_region)) {
+		dev_err(dev,
+			"Failed to create shadow-ram devlink region, err %ld\n",
+			PTR_ERR(adapter->sram_region));
+		adapter->sram_region = NULL;
+	}
+
+	adapter->devcaps_region = devl_region_create(devlink,
+						     &ixgbe_devcaps_region_ops,
+						     10, IXGBE_ACI_MAX_BUFFER_SIZE);
+	if (IS_ERR(adapter->devcaps_region)) {
+		dev_err(dev,
+			"Failed to create device-caps devlink region, err %ld\n",
+			PTR_ERR(adapter->devcaps_region));
+		adapter->devcaps_region = NULL;
+	}
+}
+
+/**
+ * ixgbe_devlink_destroy_regions - Destroy devlink regions
+ * @adapter: adapter instance
+ *
+ * Remove previously created regions for this adapter instance.
+ */
+void ixgbe_devlink_destroy_regions(struct ixgbe_adapter *adapter)
+{
+	if (adapter->hw.mac.type != ixgbe_mac_e610)
+		return;
+
+	if (adapter->nvm_region)
+		devl_region_destroy(adapter->nvm_region);
+
+	if (adapter->sram_region)
+		devl_region_destroy(adapter->sram_region);
+
+	if (adapter->devcaps_region)
+		devl_region_destroy(adapter->devcaps_region);
+}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 559b443c409f..dce4936708eb 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #ifndef _IXGBE_H_
 #define _IXGBE_H_
@@ -17,9 +17,12 @@
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 
+#include <net/devlink.h>
+
 #include "ixgbe_type.h"
 #include "ixgbe_common.h"
 #include "ixgbe_dcb.h"
+#include "ixgbe_e610.h"
 #if IS_ENABLED(CONFIG_FCOE)
 #define IXGBE_FCOE
 #include "ixgbe_fcoe.h"
@@ -173,6 +176,7 @@ enum ixgbe_tx_flags {
 #define VMDQ_P(p)   ((p) + adapter->ring_feature[RING_F_VMDQ].offset)
 #define IXGBE_82599_VF_DEVICE_ID        0x10ED
 #define IXGBE_X540_VF_DEVICE_ID         0x1515
+#define IXGBE_E610_VF_DEVICE_ID		0x57AD
 
 #define UPDATE_VF_COUNTER_32bit(reg, last_counter, counter)	\
 	{							\
@@ -425,6 +429,10 @@ enum ixgbe_ring_f_enum {
 #define IXGBE_BAD_L2A_QUEUE		3
 #define IXGBE_MAX_MACVLANS		63
 
+#define IXGBE_MAX_TX_QUEUES		128
+#define IXGBE_MAX_TX_DESCRIPTORS	40
+#define IXGBE_MAX_TX_VF_HANGS		4
+
 DECLARE_STATIC_KEY_FALSE(ixgbe_xdp_locking_key);
 
 struct ixgbe_ring_feature {
@@ -503,9 +511,10 @@ struct ixgbe_q_vector {
 	struct ixgbe_ring_container rx, tx;
 
 	struct napi_struct napi;
+	struct rcu_head rcu;	/* to avoid race with update stats on free */
+
 	cpumask_t affinity_mask;
 	int numa_node;
-	struct rcu_head rcu;	/* to avoid race with update stats on free */
 	char name[IFNAMSIZ + 9];
 
 	/* for dynamic allocation of rings associated with this q_vector */
@@ -610,6 +619,11 @@ struct ixgbe_adapter {
 	struct bpf_prog *xdp_prog;
 	struct pci_dev *pdev;
 	struct mii_bus *mii_bus;
+	struct devlink *devlink;
+	struct devlink_port devlink_port;
+	struct devlink_region *nvm_region;
+	struct devlink_region *sram_region;
+	struct devlink_region *devcaps_region;
 
 	unsigned long state;
 
@@ -654,6 +668,7 @@ struct ixgbe_adapter {
 #define IXGBE_FLAG2_RSS_FIELD_IPV6_UDP		BIT(9)
 #define IXGBE_FLAG2_PTP_PPS_ENABLED		BIT(10)
 #define IXGBE_FLAG2_PHY_INTERRUPT		BIT(11)
+#define IXGBE_FLAG2_FW_ASYNC_EVENT		BIT(12)
 #define IXGBE_FLAG2_VLAN_PROMISC		BIT(13)
 #define IXGBE_FLAG2_EEE_CAPABLE			BIT(14)
 #define IXGBE_FLAG2_EEE_ENABLED			BIT(15)
@@ -661,6 +676,11 @@ struct ixgbe_adapter {
 #define IXGBE_FLAG2_IPSEC_ENABLED		BIT(17)
 #define IXGBE_FLAG2_VF_IPSEC_ENABLED		BIT(18)
 #define IXGBE_FLAG2_AUTO_DISABLE_VF		BIT(19)
+#define IXGBE_FLAG2_PHY_FW_LOAD_FAILED		BIT(20)
+#define IXGBE_FLAG2_NO_MEDIA			BIT(21)
+#define IXGBE_FLAG2_MOD_POWER_UNSUPPORTED	BIT(22)
+#define IXGBE_FLAG2_API_MISMATCH		BIT(23)
+#define IXGBE_FLAG2_FW_ROLLBACK			BIT(24)
 
 	/* Tx fast path data */
 	int num_tx_queues;
@@ -737,6 +757,7 @@ struct ixgbe_adapter {
 	bool link_up;
 	unsigned long sfp_poll_time;
 	unsigned long link_check_timeout;
+	u32 link_down_events;
 
 	struct timer_list service_timer;
 	struct work_struct service_task;
@@ -749,6 +770,8 @@ struct ixgbe_adapter {
 	u32 atr_sample_rate;
 	spinlock_t fdir_perfect_lock;
 
+	bool fw_emp_reset_disabled;
+
 #ifdef IXGBE_FCOE
 	struct ixgbe_fcoe fcoe;
 #endif /* IXGBE_FCOE */
@@ -767,7 +790,7 @@ struct ixgbe_adapter {
 	struct ptp_clock_info ptp_caps;
 	struct work_struct ptp_tx_work;
 	struct sk_buff *ptp_tx_skb;
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 	unsigned long ptp_tx_start;
 	unsigned long last_overflow_check;
 	unsigned long last_rx_ptp_check;
@@ -792,13 +815,13 @@ struct ixgbe_adapter {
 	u32 timer_event_accumulator;
 	u32 vferr_refcount;
 	struct ixgbe_mac_addr *mac_table;
+	u8 tx_hang_count[IXGBE_MAX_TX_QUEUES];
 	struct kobject *info_kobj;
+	u16 lse_mask;
 #ifdef CONFIG_IXGBE_HWMON
 	struct hwmon_buff *ixgbe_hwmon_buff;
 #endif /* CONFIG_IXGBE_HWMON */
-#ifdef CONFIG_DEBUG_FS
 	struct dentry *ixgbe_dbg_adapter;
-#endif /*CONFIG_DEBUG_FS*/
 
 	u8 default_up;
 	/* Bitmask indicating in use pools */
@@ -823,6 +846,17 @@ struct ixgbe_adapter {
 	spinlock_t vfs_lock;
 };
 
+struct ixgbe_netdevice_priv {
+	struct ixgbe_adapter *adapter;
+};
+
+static inline struct ixgbe_adapter *ixgbe_from_netdev(struct net_device *netdev)
+{
+	struct ixgbe_netdevice_priv *priv = netdev_priv(netdev);
+
+	return priv->adapter;
+}
+
 static inline int ixgbe_determine_xdp_q_idx(int cpu)
 {
 	if (static_key_enabled(&ixgbe_xdp_locking_key))
@@ -849,6 +883,7 @@ static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		return IXGBE_MAX_RSS_INDICES_X550;
 	default:
 		return 0;
@@ -874,6 +909,7 @@ enum ixgbe_state_t {
 	__IXGBE_PTP_RUNNING,
 	__IXGBE_PTP_TX_IN_PROGRESS,
 	__IXGBE_RESET_REQUESTED,
+	__IXGBE_PHY_INIT_COMPLETE,
 };
 
 struct ixgbe_cb {
@@ -896,6 +932,7 @@ enum ixgbe_boards {
 	board_x550em_x_fw,
 	board_x550em_a,
 	board_x550em_a_fw,
+	board_e610,
 };
 
 extern const struct ixgbe_info ixgbe_82598_info;
@@ -906,6 +943,7 @@ extern const struct ixgbe_info ixgbe_X550EM_x_info;
 extern const struct ixgbe_info ixgbe_x550em_x_fw_info;
 extern const struct ixgbe_info ixgbe_x550em_a_info;
 extern const struct ixgbe_info ixgbe_x550em_a_fw_info;
+extern const struct ixgbe_info ixgbe_e610_info;
 #ifdef CONFIG_IXGBE_DCB
 extern const struct dcbnl_rtnl_ops ixgbe_dcbnl_ops;
 #endif
@@ -934,6 +972,8 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter);
 int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter);
 bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id,
 			 u16 subdevice_id);
+void ixgbe_set_fw_version_e610(struct ixgbe_adapter *adapter);
+void ixgbe_refresh_fw_version(struct ixgbe_adapter *adapter);
 #ifdef CONFIG_PCI_IOV
 void ixgbe_full_sync_mac_table(struct ixgbe_adapter *adapter);
 #endif
@@ -1044,8 +1084,11 @@ static inline void ixgbe_ptp_rx_hwtstamp(struct ixgbe_ring *rx_ring,
 	rx_ring->last_rx_timestamp = jiffies;
 }
 
-int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr);
-int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr);
+int ixgbe_ptp_hwtstamp_get(struct net_device *netdev,
+			   struct kernel_hwtstamp_config *config);
+int ixgbe_ptp_hwtstamp_set(struct net_device *netdev,
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack);
 void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter);
 void ixgbe_ptp_reset(struct ixgbe_adapter *adapter);
 void ixgbe_ptp_check_pps_event(struct ixgbe_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
index 4aaaea3b5f8f..406c15f58034 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
@@ -45,7 +45,7 @@ static void ixgbe_set_pcie_completion_timeout(struct ixgbe_hw *hw)
 		goto out;
 
 	/*
-	 * if capababilities version is type 1 we can write the
+	 * if capabilities version is type 1 we can write the
 	 * timeout of 10ms to 250ms through the GCR register
 	 */
 	if (!(gcr & IXGBE_GCR_CAP_VER2)) {
@@ -751,7 +751,7 @@ mac_reset_top:
 	/*
 	 * Store the original AUTOC value if it has not been
 	 * stored off yet.  Otherwise restore the stored original
-	 * AUTOC value since the reset operation sets back to deaults.
+	 * AUTOC value since the reset operation sets back to defaults.
 	 */
 	autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC);
 	if (hw->mac.orig_link_settings_stored == false) {
@@ -1169,6 +1169,7 @@ static const struct ixgbe_eeprom_operations eeprom_ops_82598 = {
 	.calc_checksum          = &ixgbe_calc_eeprom_checksum_generic,
 	.validate_checksum	= &ixgbe_validate_eeprom_checksum_generic,
 	.update_checksum	= &ixgbe_update_eeprom_checksum_generic,
+	.read_pba_string        = &ixgbe_read_pba_string_generic,
 };
 
 static const struct ixgbe_phy_operations phy_ops_82598 = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index cdaf087b4e85..3069b583fd81 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include <linux/pci.h>
 #include <linux/delay.h>
@@ -198,7 +198,7 @@ static int prot_autoc_read_82599(struct ixgbe_hw *hw, bool *locked,
  * @hw: pointer to hardware structure
  * @autoc: value to write to AUTOC
  * @locked: bool to indicate whether the SW/FW lock was already taken by
- *	     previous proc_autoc_read_82599.
+ *	     previous prot_autoc_read_82599.
  *
  * This part (82599) may need to hold a the SW/FW lock around all writes to
  * AUTOC. Likewise after a write we need to do a pipeline reset.
@@ -1615,13 +1615,14 @@ int ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		IXGBE_WRITE_REG(hw, IXGBE_FDIRSCTPM, ~fdirtcpm);
 		break;
 	default:
 		break;
 	}
 
-	/* store source and destination IP masks (big-enian) */
+	/* store source and destination IP masks (big-endian) */
 	IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRSIP4M,
 			     ~input_mask->formatted.src_ip[0]);
 	IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRDIP4M,
@@ -2229,6 +2230,7 @@ static const struct ixgbe_eeprom_operations eeprom_ops_82599 = {
 	.calc_checksum		= &ixgbe_calc_eeprom_checksum_generic,
 	.validate_checksum	= &ixgbe_validate_eeprom_checksum_generic,
 	.update_checksum	= &ixgbe_update_eeprom_checksum_generic,
+	.read_pba_string        = &ixgbe_read_pba_string_generic,
 };
 
 static const struct ixgbe_phy_operations phy_ops_82599 = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 3be1bfb16498..3ea6765f9c5d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include <linux/pci.h>
 #include <linux/delay.h>
@@ -58,6 +58,7 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw)
 		switch (hw->device_id) {
 		case IXGBE_DEV_ID_X550EM_A_SFP:
 		case IXGBE_DEV_ID_X550EM_A_SFP_N:
+		case IXGBE_DEV_ID_E610_SFP:
 			supported = false;
 			break;
 		default:
@@ -88,6 +89,8 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw)
 		case IXGBE_DEV_ID_X550EM_A_10G_T:
 		case IXGBE_DEV_ID_X550EM_A_1G_T:
 		case IXGBE_DEV_ID_X550EM_A_1G_T_L:
+		case IXGBE_DEV_ID_E610_10G_T:
+		case IXGBE_DEV_ID_E610_2_5G_T:
 			supported = true;
 			break;
 		default:
@@ -241,7 +244,7 @@ int ixgbe_setup_fc_generic(struct ixgbe_hw *hw)
 	 */
 	if (hw->phy.media_type == ixgbe_media_type_backplane) {
 		/* Need the SW/FW semaphore around AUTOC writes if 82599 and
-		 * LESM is on, likewise reset_pipeline requries the lock as
+		 * LESM is on, likewise reset_pipeline requires the lock as
 		 * it also writes AUTOC.
 		 */
 		ret_val = hw->mac.ops.prot_autoc_write(hw, reg_bp, locked);
@@ -298,7 +301,7 @@ int ixgbe_start_hw_generic(struct ixgbe_hw *hw)
 			return ret_val;
 	}
 
-	/* Cashe bit indicating need for crosstalk fix */
+	/* Cache bit indicating need for crosstalk fix */
 	switch (hw->mac.type) {
 	case ixgbe_mac_82599EB:
 	case ixgbe_mac_X550EM_x:
@@ -329,6 +332,7 @@ int ixgbe_start_hw_generic(struct ixgbe_hw *hw)
  * Devices in the second generation:
  *     82599
  *     X540
+ *     E610
  **/
 int ixgbe_start_hw_gen2(struct ixgbe_hw *hw)
 {
@@ -469,9 +473,14 @@ int ixgbe_clear_hw_cntrs_generic(struct ixgbe_hw *hw)
 		}
 	}
 
-	if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_X540) {
+	if (hw->mac.type == ixgbe_mac_X550 ||
+	    hw->mac.type == ixgbe_mac_X540 ||
+	    hw->mac.type == ixgbe_mac_e610) {
 		if (hw->phy.id == 0)
 			hw->phy.ops.identify(hw);
+	}
+
+	if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_X540) {
 		hw->phy.ops.read_reg(hw, IXGBE_PCRC8ECL, MDIO_MMD_PCS, &i);
 		hw->phy.ops.read_reg(hw, IXGBE_PCRC8ECH, MDIO_MMD_PCS, &i);
 		hw->phy.ops.read_reg(hw, IXGBE_LDPCECL, MDIO_MMD_PCS, &i);
@@ -660,7 +669,11 @@ int ixgbe_get_bus_info_generic(struct ixgbe_hw *hw)
 	hw->bus.type = ixgbe_bus_type_pci_express;
 
 	/* Get the negotiated link width and speed from PCI config space */
-	link_status = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_LINK_STATUS);
+	if (hw->mac.type == ixgbe_mac_e610)
+		link_status = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_LINK_STATUS_E610);
+	else
+		link_status = ixgbe_read_pci_cfg_word(hw,
+						      IXGBE_PCI_LINK_STATUS);
 
 	hw->bus.width = ixgbe_convert_bus_width(link_status);
 	hw->bus.speed = ixgbe_convert_bus_speed(link_status);
@@ -1726,9 +1739,9 @@ int ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw)
 		}
 	}
 
-	checksum = (u16)IXGBE_EEPROM_SUM - checksum;
+	checksum = IXGBE_EEPROM_SUM - checksum;
 
-	return (int)checksum;
+	return checksum;
 }
 
 /**
@@ -2918,6 +2931,10 @@ u16 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw)
 		pcie_offset = IXGBE_PCIE_MSIX_82599_CAPS;
 		max_msix_count = IXGBE_MAX_MSIX_VECTORS_82599;
 		break;
+	case ixgbe_mac_e610:
+		pcie_offset = IXGBE_PCIE_MSIX_E610_CAPS;
+		max_msix_count = IXGBE_MAX_MSIX_VECTORS_82599;
+		break;
 	default:
 		return 1;
 	}
@@ -3366,7 +3383,8 @@ int ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
 		*speed = IXGBE_LINK_SPEED_1GB_FULL;
 		break;
 	case IXGBE_LINKS_SPEED_100_82599:
-		if ((hw->mac.type >= ixgbe_mac_X550) &&
+		if ((hw->mac.type >= ixgbe_mac_X550 ||
+		     hw->mac.type == ixgbe_mac_e610) &&
 		    (links_reg & IXGBE_LINKS_SPEED_NON_STD))
 			*speed = IXGBE_LINK_SPEED_5GB_FULL;
 		else
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
index f2709b10c2e5..3dd5a16a14df 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include "ixgbe.h"
 #include <linux/dcbnl.h>
@@ -118,14 +118,14 @@ static int ixgbe_copy_dcb_cfg(struct ixgbe_adapter *adapter, int tc_max)
 
 static u8 ixgbe_dcbnl_get_state(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	return !!(adapter->flags & IXGBE_FLAG_DCB_ENABLED);
 }
 
 static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* Fail command if not in CEE mode */
 	if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
@@ -142,7 +142,7 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
 static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev,
 					 u8 *perm_addr)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int i, j;
 
 	memset(perm_addr, 0xff, MAX_ADDR_LEN);
@@ -154,6 +154,7 @@ static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev,
 	case ixgbe_mac_82599EB:
 	case ixgbe_mac_X540:
 	case ixgbe_mac_X550:
+	case ixgbe_mac_e610:
 		for (j = 0; j < netdev->addr_len; j++, i++)
 			perm_addr[i] = adapter->hw.mac.san_addr[j];
 		break;
@@ -166,7 +167,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 					 u8 prio, u8 bwg_id, u8 bw_pct,
 					 u8 up_map)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (prio != DCB_ATTR_VALUE_UNDEFINED)
 		adapter->temp_dcb_cfg.tc_config[tc].path[0].prio_type = prio;
@@ -183,7 +184,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
 					  u8 bw_pct)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->temp_dcb_cfg.bw_percentage[0][bwg_id] = bw_pct;
 }
@@ -192,7 +193,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 					 u8 prio, u8 bwg_id, u8 bw_pct,
 					 u8 up_map)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (prio != DCB_ATTR_VALUE_UNDEFINED)
 		adapter->temp_dcb_cfg.tc_config[tc].path[1].prio_type = prio;
@@ -209,7 +210,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
 					  u8 bw_pct)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->temp_dcb_cfg.bw_percentage[1][bwg_id] = bw_pct;
 }
@@ -218,7 +219,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 					 u8 *prio, u8 *bwg_id, u8 *bw_pct,
 					 u8 *up_map)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*prio = adapter->dcb_cfg.tc_config[tc].path[0].prio_type;
 	*bwg_id = adapter->dcb_cfg.tc_config[tc].path[0].bwg_id;
@@ -229,7 +230,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 static void ixgbe_dcbnl_get_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
 					  u8 *bw_pct)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*bw_pct = adapter->dcb_cfg.bw_percentage[0][bwg_id];
 }
@@ -238,7 +239,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 					 u8 *prio, u8 *bwg_id, u8 *bw_pct,
 					 u8 *up_map)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*prio = adapter->dcb_cfg.tc_config[tc].path[1].prio_type;
 	*bwg_id = adapter->dcb_cfg.tc_config[tc].path[1].bwg_id;
@@ -249,7 +250,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 static void ixgbe_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
 					  u8 *bw_pct)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*bw_pct = adapter->dcb_cfg.bw_percentage[1][bwg_id];
 }
@@ -257,7 +258,7 @@ static void ixgbe_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
 static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
 				    u8 setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc = setting;
 	if (adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc !=
@@ -268,14 +269,14 @@ static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
 static void ixgbe_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
 				    u8 *setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*setting = adapter->dcb_cfg.tc_config[priority].dcb_pfc;
 }
 
 static void ixgbe_dcbnl_devreset(struct net_device *dev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state))
 		usleep_range(1000, 2000);
@@ -294,7 +295,7 @@ static void ixgbe_dcbnl_devreset(struct net_device *dev)
 
 static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_dcb_config *dcb_cfg = &adapter->dcb_cfg;
 	struct ixgbe_hw *hw = &adapter->hw;
 	int ret = DCB_NO_HW_CHG;
@@ -382,7 +383,7 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 
 static u8 ixgbe_dcbnl_getcap(struct net_device *netdev, int capid, u8 *cap)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	switch (capid) {
 	case DCB_CAP_ATTR_PG:
@@ -419,7 +420,7 @@ static u8 ixgbe_dcbnl_getcap(struct net_device *netdev, int capid, u8 *cap)
 
 static int ixgbe_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
 		switch (tcid) {
@@ -446,14 +447,14 @@ static int ixgbe_dcbnl_setnumtcs(struct net_device *netdev, int tcid, u8 num)
 
 static u8 ixgbe_dcbnl_getpfcstate(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	return adapter->dcb_cfg.pfc_mode_enable;
 }
 
 static void ixgbe_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->temp_dcb_cfg.pfc_mode_enable = state;
 }
@@ -470,7 +471,7 @@ static void ixgbe_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
  */
 static int ixgbe_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct dcb_app app = {
 				.selector = idtype,
 				.protocol = id,
@@ -485,7 +486,7 @@ static int ixgbe_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id)
 static int ixgbe_dcbnl_ieee_getets(struct net_device *dev,
 				   struct ieee_ets *ets)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ieee_ets *my_ets = adapter->ixgbe_ieee_ets;
 
 	ets->ets_cap = adapter->dcb_cfg.num_tcs.pg_tcs;
@@ -505,7 +506,7 @@ static int ixgbe_dcbnl_ieee_getets(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_setets(struct net_device *dev,
 				   struct ieee_ets *ets)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int max_frame = dev->mtu + ETH_HLEN + ETH_FCS_LEN;
 	int i, err;
 	__u8 max_tc = 0;
@@ -558,7 +559,7 @@ static int ixgbe_dcbnl_ieee_setets(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_getpfc(struct net_device *dev,
 				   struct ieee_pfc *pfc)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ieee_pfc *my_pfc = adapter->ixgbe_ieee_pfc;
 	int i;
 
@@ -583,7 +584,7 @@ static int ixgbe_dcbnl_ieee_getpfc(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev,
 				   struct ieee_pfc *pfc)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u8 *prio_tc;
 	int err;
@@ -615,7 +616,7 @@ static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev,
 				   struct dcb_app *app)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int err;
 
 	if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
@@ -660,7 +661,7 @@ static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_delapp(struct net_device *dev,
 				   struct dcb_app *app)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int err;
 
 	if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
@@ -704,13 +705,13 @@ static int ixgbe_dcbnl_ieee_delapp(struct net_device *dev,
 
 static u8 ixgbe_dcbnl_getdcbx(struct net_device *dev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	return adapter->dcbx_cap;
 }
 
 static u8 ixgbe_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ieee_ets ets = {0};
 	struct ieee_pfc pfc = {0};
 	int err = 0;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
new file mode 100644
index 000000000000..c2f8189a0738
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
@@ -0,0 +1,4043 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024 Intel Corporation. */
+
+#include "ixgbe_common.h"
+#include "ixgbe_e610.h"
+#include "ixgbe_x550.h"
+#include "ixgbe_type.h"
+#include "ixgbe_x540.h"
+#include "ixgbe_mbx.h"
+#include "ixgbe_phy.h"
+
+/**
+ * ixgbe_should_retry_aci_send_cmd_execute - decide if ACI command should
+ * be resent
+ * @opcode: ACI opcode
+ *
+ * Check if ACI command should be sent again depending on the provided opcode.
+ * It may happen when CSR is busy during link state changes.
+ *
+ * Return: true if the sending command routine should be repeated,
+ * otherwise false.
+ */
+static bool ixgbe_should_retry_aci_send_cmd_execute(u16 opcode)
+{
+	switch (opcode) {
+	case ixgbe_aci_opc_disable_rxen:
+	case ixgbe_aci_opc_get_phy_caps:
+	case ixgbe_aci_opc_get_link_status:
+	case ixgbe_aci_opc_get_link_topo:
+		return true;
+	}
+
+	return false;
+}
+
+/**
+ * ixgbe_aci_send_cmd_execute - execute sending FW Admin Command to FW Admin
+ * Command Interface
+ * @hw: pointer to the HW struct
+ * @desc: descriptor describing the command
+ * @buf: buffer to use for indirect commands (NULL for direct commands)
+ * @buf_size: size of buffer for indirect commands (0 for direct commands)
+ *
+ * Admin Command is sent using CSR by setting descriptor and buffer in specific
+ * registers.
+ *
+ * Return: the exit code of the operation.
+ * * - 0 - success.
+ * * - -EIO - CSR mechanism is not enabled.
+ * * - -EBUSY - CSR mechanism is busy.
+ * * - -EINVAL - buf_size is too big or
+ * invalid argument buf or buf_size.
+ * * - -ETIME - Admin Command X command timeout.
+ * * - -EIO - Admin Command X invalid state of HICR register or
+ * Admin Command failed because of bad opcode was returned or
+ * Admin Command failed with error Y.
+ */
+static int ixgbe_aci_send_cmd_execute(struct ixgbe_hw *hw,
+				      struct libie_aq_desc *desc,
+				      void *buf, u16 buf_size)
+{
+	u16 opcode, buf_tail_size = buf_size % 4;
+	u32 *raw_desc = (u32 *)desc;
+	u32 hicr, i, buf_tail = 0;
+	bool valid_buf = false;
+
+	hw->aci.last_status = LIBIE_AQ_RC_OK;
+
+	/* It's necessary to check if mechanism is enabled */
+	hicr = IXGBE_READ_REG(hw, IXGBE_PF_HICR);
+
+	if (!(hicr & IXGBE_PF_HICR_EN))
+		return -EIO;
+
+	if (hicr & IXGBE_PF_HICR_C) {
+		hw->aci.last_status = LIBIE_AQ_RC_EBUSY;
+		return -EBUSY;
+	}
+
+	opcode = le16_to_cpu(desc->opcode);
+
+	if (buf_size > IXGBE_ACI_MAX_BUFFER_SIZE)
+		return -EINVAL;
+
+	if (buf)
+		desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_BUF);
+
+	if (desc->flags & cpu_to_le16(LIBIE_AQ_FLAG_BUF)) {
+		if ((buf && !buf_size) ||
+		    (!buf && buf_size))
+			return -EINVAL;
+		if (buf && buf_size)
+			valid_buf = true;
+	}
+
+	if (valid_buf) {
+		if (buf_tail_size)
+			memcpy(&buf_tail, buf + buf_size - buf_tail_size,
+			       buf_tail_size);
+
+		if (((buf_size + 3) & ~0x3) > LIBIE_AQ_LG_BUF)
+			desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
+
+		desc->datalen = cpu_to_le16(buf_size);
+
+		if (desc->flags & cpu_to_le16(LIBIE_AQ_FLAG_RD)) {
+			for (i = 0; i < buf_size / 4; i++)
+				IXGBE_WRITE_REG(hw, IXGBE_PF_HIBA(i), ((u32 *)buf)[i]);
+			if (buf_tail_size)
+				IXGBE_WRITE_REG(hw, IXGBE_PF_HIBA(i), buf_tail);
+		}
+	}
+
+	/* Descriptor is written to specific registers */
+	for (i = 0; i < IXGBE_ACI_DESC_SIZE_IN_DWORDS; i++)
+		IXGBE_WRITE_REG(hw, IXGBE_PF_HIDA(i), raw_desc[i]);
+
+	/* SW has to set PF_HICR.C bit and clear PF_HICR.SV and
+	 * PF_HICR_EV
+	 */
+	hicr = (IXGBE_READ_REG(hw, IXGBE_PF_HICR) | IXGBE_PF_HICR_C) &
+	       ~(IXGBE_PF_HICR_SV | IXGBE_PF_HICR_EV);
+	IXGBE_WRITE_REG(hw, IXGBE_PF_HICR, hicr);
+
+#define MAX_SLEEP_RESP_US 1000
+#define MAX_TMOUT_RESP_SYNC_US 100000000
+
+	/* Wait for sync Admin Command response */
+	read_poll_timeout(IXGBE_READ_REG, hicr,
+			  (hicr & IXGBE_PF_HICR_SV) ||
+			  !(hicr & IXGBE_PF_HICR_C),
+			  MAX_SLEEP_RESP_US, MAX_TMOUT_RESP_SYNC_US, true, hw,
+			  IXGBE_PF_HICR);
+
+#define MAX_TMOUT_RESP_ASYNC_US 150000000
+
+	/* Wait for async Admin Command response */
+	read_poll_timeout(IXGBE_READ_REG, hicr,
+			  (hicr & IXGBE_PF_HICR_EV) ||
+			  !(hicr & IXGBE_PF_HICR_C),
+			  MAX_SLEEP_RESP_US, MAX_TMOUT_RESP_ASYNC_US, true, hw,
+			  IXGBE_PF_HICR);
+
+	/* Read sync Admin Command response */
+	if ((hicr & IXGBE_PF_HICR_SV)) {
+		for (i = 0; i < IXGBE_ACI_DESC_SIZE_IN_DWORDS; i++) {
+			raw_desc[i] = IXGBE_READ_REG(hw, IXGBE_PF_HIDA(i));
+			raw_desc[i] = raw_desc[i];
+		}
+	}
+
+	/* Read async Admin Command response */
+	if ((hicr & IXGBE_PF_HICR_EV) && !(hicr & IXGBE_PF_HICR_C)) {
+		for (i = 0; i < IXGBE_ACI_DESC_SIZE_IN_DWORDS; i++) {
+			raw_desc[i] = IXGBE_READ_REG(hw, IXGBE_PF_HIDA_2(i));
+			raw_desc[i] = raw_desc[i];
+		}
+	}
+
+	/* Handle timeout and invalid state of HICR register */
+	if (hicr & IXGBE_PF_HICR_C)
+		return -ETIME;
+
+	if (!(hicr & IXGBE_PF_HICR_SV) && !(hicr & IXGBE_PF_HICR_EV))
+		return -EIO;
+
+	/* For every command other than 0x0014 treat opcode mismatch
+	 * as an error. Response to 0x0014 command read from HIDA_2
+	 * is a descriptor of an event which is expected to contain
+	 * different opcode than the command.
+	 */
+	if (desc->opcode != cpu_to_le16(opcode) &&
+	    opcode != ixgbe_aci_opc_get_fw_event)
+		return -EIO;
+
+	if (desc->retval) {
+		hw->aci.last_status = (enum libie_aq_err)
+			le16_to_cpu(desc->retval);
+		return -EIO;
+	}
+
+	/* Write a response values to a buf */
+	if (valid_buf) {
+		for (i = 0; i < buf_size / 4; i++)
+			((u32 *)buf)[i] = IXGBE_READ_REG(hw, IXGBE_PF_HIBA(i));
+		if (buf_tail_size) {
+			buf_tail = IXGBE_READ_REG(hw, IXGBE_PF_HIBA(i));
+			memcpy(buf + buf_size - buf_tail_size, &buf_tail,
+			       buf_tail_size);
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_aci_send_cmd - send FW Admin Command to FW Admin Command Interface
+ * @hw: pointer to the HW struct
+ * @desc: descriptor describing the command
+ * @buf: buffer to use for indirect commands (NULL for direct commands)
+ * @buf_size: size of buffer for indirect commands (0 for direct commands)
+ *
+ * Helper function to send FW Admin Commands to the FW Admin Command Interface.
+ *
+ * Retry sending the FW Admin Command multiple times to the FW ACI
+ * if the EBUSY Admin Command error is returned.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_send_cmd(struct ixgbe_hw *hw, struct libie_aq_desc *desc,
+		       void *buf, u16 buf_size)
+{
+	u16 opcode = le16_to_cpu(desc->opcode);
+	struct libie_aq_desc desc_cpy;
+	enum libie_aq_err last_status;
+	u8 idx = 0, *buf_cpy = NULL;
+	bool is_cmd_for_retry;
+	unsigned long timeout;
+	int err;
+
+	is_cmd_for_retry = ixgbe_should_retry_aci_send_cmd_execute(opcode);
+	if (is_cmd_for_retry) {
+		if (buf) {
+			buf_cpy = kmalloc(buf_size, GFP_KERNEL);
+			if (!buf_cpy)
+				return -ENOMEM;
+			*buf_cpy = *(u8 *)buf;
+		}
+		desc_cpy = *desc;
+	}
+
+	timeout = jiffies + msecs_to_jiffies(IXGBE_ACI_SEND_TIMEOUT_MS);
+	do {
+		mutex_lock(&hw->aci.lock);
+		err = ixgbe_aci_send_cmd_execute(hw, desc, buf, buf_size);
+		last_status = hw->aci.last_status;
+		mutex_unlock(&hw->aci.lock);
+
+		if (!is_cmd_for_retry || !err ||
+		    last_status != LIBIE_AQ_RC_EBUSY)
+			break;
+
+		if (buf)
+			memcpy(buf, buf_cpy, buf_size);
+		*desc = desc_cpy;
+
+		msleep(IXGBE_ACI_SEND_DELAY_TIME_MS);
+	} while (++idx < IXGBE_ACI_SEND_MAX_EXECUTE &&
+		 time_before(jiffies, timeout));
+
+	kfree(buf_cpy);
+
+	return err;
+}
+
+/**
+ * ixgbe_aci_check_event_pending - check if there are any pending events
+ * @hw: pointer to the HW struct
+ *
+ * Determine if there are any pending events.
+ *
+ * Return: true if there are any currently pending events
+ * otherwise false.
+ */
+bool ixgbe_aci_check_event_pending(struct ixgbe_hw *hw)
+{
+	u32 ep_bit_mask = hw->bus.func ? GL_FWSTS_EP_PF1 : GL_FWSTS_EP_PF0;
+	u32 fwsts = IXGBE_READ_REG(hw, GL_FWSTS);
+
+	return (fwsts & ep_bit_mask) ? true : false;
+}
+
+/**
+ * ixgbe_aci_get_event - get an event from ACI
+ * @hw: pointer to the HW struct
+ * @e: event information structure
+ * @pending: optional flag signaling that there are more pending events
+ *
+ * Obtain an event from ACI and return its content
+ * through 'e' using ACI command (0x0014).
+ * Provide information if there are more events
+ * to retrieve through 'pending'.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_get_event(struct ixgbe_hw *hw, struct ixgbe_aci_event *e,
+			bool *pending)
+{
+	struct libie_aq_desc desc;
+	int err;
+
+	if (!e || (!e->msg_buf && e->buf_len))
+		return -EINVAL;
+
+	mutex_lock(&hw->aci.lock);
+
+	/* Check if there are any events pending */
+	if (!ixgbe_aci_check_event_pending(hw)) {
+		err = -ENOENT;
+		goto aci_get_event_exit;
+	}
+
+	/* Obtain pending event */
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_fw_event);
+	err = ixgbe_aci_send_cmd_execute(hw, &desc, e->msg_buf, e->buf_len);
+	if (err)
+		goto aci_get_event_exit;
+
+	/* Returned 0x0014 opcode indicates that no event was obtained */
+	if (desc.opcode == cpu_to_le16(ixgbe_aci_opc_get_fw_event)) {
+		err = -ENOENT;
+		goto aci_get_event_exit;
+	}
+
+	/* Determine size of event data */
+	e->msg_len = min_t(u16, le16_to_cpu(desc.datalen), e->buf_len);
+	/* Write event descriptor to event info structure */
+	memcpy(&e->desc, &desc, sizeof(e->desc));
+
+	/* Check if there are any further events pending */
+	if (pending)
+		*pending = ixgbe_aci_check_event_pending(hw);
+
+aci_get_event_exit:
+	mutex_unlock(&hw->aci.lock);
+
+	return err;
+}
+
+/**
+ * ixgbe_fill_dflt_direct_cmd_desc - fill ACI descriptor with default values.
+ * @desc: pointer to the temp descriptor (non DMA mem)
+ * @opcode: the opcode can be used to decide which flags to turn off or on
+ *
+ * Helper function to fill the descriptor desc with default values
+ * and the provided opcode.
+ */
+void ixgbe_fill_dflt_direct_cmd_desc(struct libie_aq_desc *desc, u16 opcode)
+{
+	/* Zero out the desc. */
+	memset(desc, 0, sizeof(*desc));
+	desc->opcode = cpu_to_le16(opcode);
+	desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_SI);
+}
+
+/**
+ * ixgbe_aci_get_fw_ver - Get the firmware version
+ * @hw: pointer to the HW struct
+ *
+ * Get the firmware version using ACI command (0x0001).
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_aci_get_fw_ver(struct ixgbe_hw *hw)
+{
+	struct libie_aqc_get_ver *resp;
+	struct libie_aq_desc desc;
+	int err;
+
+	resp = &desc.params.get_ver;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_ver);
+
+	err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+	if (!err) {
+		hw->fw_branch = resp->fw_branch;
+		hw->fw_maj_ver = resp->fw_major;
+		hw->fw_min_ver = resp->fw_minor;
+		hw->fw_patch = resp->fw_patch;
+		hw->fw_build = le32_to_cpu(resp->fw_build);
+		hw->api_branch = resp->api_branch;
+		hw->api_maj_ver = resp->api_major;
+		hw->api_min_ver = resp->api_minor;
+		hw->api_patch = resp->api_patch;
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_aci_req_res - request a common resource
+ * @hw: pointer to the HW struct
+ * @res: resource ID
+ * @access: access type
+ * @sdp_number: resource number
+ * @timeout: the maximum time in ms that the driver may hold the resource
+ *
+ * Requests a common resource using the ACI command (0x0008).
+ * Specifies the maximum time the driver may hold the resource.
+ * If the requested resource is currently occupied by some other driver,
+ * a busy return value is returned and the timeout field value indicates the
+ * maximum time the current owner has to free it.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_aci_req_res(struct ixgbe_hw *hw, enum libie_aq_res_id res,
+			     enum libie_aq_res_access_type access,
+			     u8 sdp_number, u32 *timeout)
+{
+	struct libie_aqc_req_res *cmd_resp;
+	struct libie_aq_desc desc;
+	int err;
+
+	cmd_resp = &desc.params.res_owner;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_req_res);
+
+	cmd_resp->res_id = cpu_to_le16(res);
+	cmd_resp->access_type = cpu_to_le16(access);
+	cmd_resp->res_number = cpu_to_le32(sdp_number);
+	cmd_resp->timeout = cpu_to_le32(*timeout);
+	*timeout = 0;
+
+	err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+
+	/* If the resource is held by some other driver, the command completes
+	 * with a busy return value and the timeout field indicates the maximum
+	 * time the current owner of the resource has to free it.
+	 */
+	if (!err || hw->aci.last_status == LIBIE_AQ_RC_EBUSY)
+		*timeout = le32_to_cpu(cmd_resp->timeout);
+
+	return err;
+}
+
+/**
+ * ixgbe_aci_release_res - release a common resource using ACI
+ * @hw: pointer to the HW struct
+ * @res: resource ID
+ * @sdp_number: resource number
+ *
+ * Release a common resource using ACI command (0x0009).
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_aci_release_res(struct ixgbe_hw *hw, enum libie_aq_res_id res,
+				 u8 sdp_number)
+{
+	struct libie_aqc_req_res *cmd;
+	struct libie_aq_desc desc;
+
+	cmd = &desc.params.res_owner;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_release_res);
+
+	cmd->res_id = cpu_to_le16(res);
+	cmd->res_number = cpu_to_le32(sdp_number);
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
+ * ixgbe_acquire_res - acquire the ownership of a resource
+ * @hw: pointer to the HW structure
+ * @res: resource ID
+ * @access: access type (read or write)
+ * @timeout: timeout in milliseconds
+ *
+ * Make an attempt to acquire the ownership of a resource using
+ * the ixgbe_aci_req_res to utilize ACI.
+ * In case if some other driver has previously acquired the resource and
+ * performed any necessary updates, the -EALREADY is returned,
+ * and the caller does not obtain the resource and has no further work to do.
+ * If needed, the function will poll until the current lock owner timeouts.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_acquire_res(struct ixgbe_hw *hw, enum libie_aq_res_id res,
+		      enum libie_aq_res_access_type access, u32 timeout)
+{
+#define IXGBE_RES_POLLING_DELAY_MS	10
+	u32 delay = IXGBE_RES_POLLING_DELAY_MS;
+	u32 res_timeout = timeout;
+	u32 retry_timeout;
+	int err;
+
+	err = ixgbe_aci_req_res(hw, res, access, 0, &res_timeout);
+
+	/* A return code of -EALREADY means that another driver has
+	 * previously acquired the resource and performed any necessary updates;
+	 * in this case the caller does not obtain the resource and has no
+	 * further work to do.
+	 */
+	if (err == -EALREADY)
+		return err;
+
+	/* If necessary, poll until the current lock owner timeouts.
+	 * Set retry_timeout to the timeout value reported by the FW in the
+	 * response to the "Request Resource Ownership" (0x0008) Admin Command
+	 * as it indicates the maximum time the current owner of the resource
+	 * is allowed to hold it.
+	 */
+	retry_timeout = res_timeout;
+	while (err && retry_timeout && res_timeout) {
+		msleep(delay);
+		retry_timeout = (retry_timeout > delay) ?
+			retry_timeout - delay : 0;
+		err = ixgbe_aci_req_res(hw, res, access, 0, &res_timeout);
+
+		/* Success - lock acquired.
+		 * -EALREADY - lock free, no work to do.
+		 */
+		if (!err || err == -EALREADY)
+			break;
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_release_res - release a common resource
+ * @hw: pointer to the HW structure
+ * @res: resource ID
+ *
+ * Release a common resource using ixgbe_aci_release_res.
+ */
+void ixgbe_release_res(struct ixgbe_hw *hw, enum libie_aq_res_id res)
+{
+	u32 total_delay = 0;
+	int err;
+
+	err = ixgbe_aci_release_res(hw, res, 0);
+
+	/* There are some rare cases when trying to release the resource
+	 * results in an admin command timeout, so handle them correctly.
+	 */
+	while (err == -ETIME &&
+	       total_delay < IXGBE_ACI_RELEASE_RES_TIMEOUT) {
+		usleep_range(1000, 1500);
+		err = ixgbe_aci_release_res(hw, res, 0);
+		total_delay++;
+	}
+}
+
+/**
+ * ixgbe_parse_e610_caps - Parse common device/function capabilities
+ * @hw: pointer to the HW struct
+ * @caps: pointer to common capabilities structure
+ * @elem: the capability element to parse
+ * @prefix: message prefix for tracing capabilities
+ *
+ * Given a capability element, extract relevant details into the common
+ * capability structure.
+ *
+ * Return: true if the capability matches one of the common capability ids,
+ * false otherwise.
+ */
+static bool ixgbe_parse_e610_caps(struct ixgbe_hw *hw,
+				  struct ixgbe_hw_caps *caps,
+				  struct libie_aqc_list_caps_elem *elem,
+				  const char *prefix)
+{
+	u32 logical_id = le32_to_cpu(elem->logical_id);
+	u32 phys_id = le32_to_cpu(elem->phys_id);
+	u32 number = le32_to_cpu(elem->number);
+	u16 cap = le16_to_cpu(elem->cap);
+
+	switch (cap) {
+	case LIBIE_AQC_CAPS_VALID_FUNCTIONS:
+		caps->valid_functions = number;
+		break;
+	case LIBIE_AQC_CAPS_SRIOV:
+		caps->sr_iov_1_1 = (number == 1);
+		break;
+	case LIBIE_AQC_CAPS_VMDQ:
+		caps->vmdq = (number == 1);
+		break;
+	case LIBIE_AQC_CAPS_DCB:
+		caps->dcb = (number == 1);
+		caps->active_tc_bitmap = logical_id;
+		caps->maxtc = phys_id;
+		break;
+	case LIBIE_AQC_CAPS_RSS:
+		caps->rss_table_size = number;
+		caps->rss_table_entry_width = logical_id;
+		break;
+	case LIBIE_AQC_CAPS_RXQS:
+		caps->num_rxq = number;
+		caps->rxq_first_id = phys_id;
+		break;
+	case LIBIE_AQC_CAPS_TXQS:
+		caps->num_txq = number;
+		caps->txq_first_id = phys_id;
+		break;
+	case LIBIE_AQC_CAPS_MSIX:
+		caps->num_msix_vectors = number;
+		caps->msix_vector_first_id = phys_id;
+		break;
+	case LIBIE_AQC_CAPS_NVM_VER:
+		break;
+	case LIBIE_AQC_CAPS_PENDING_NVM_VER:
+		caps->nvm_update_pending_nvm = true;
+		break;
+	case LIBIE_AQC_CAPS_PENDING_OROM_VER:
+		caps->nvm_update_pending_orom = true;
+		break;
+	case LIBIE_AQC_CAPS_PENDING_NET_VER:
+		caps->nvm_update_pending_netlist = true;
+		break;
+	case LIBIE_AQC_CAPS_NVM_MGMT:
+		caps->nvm_unified_update =
+			(number & IXGBE_NVM_MGMT_UNIFIED_UPD_SUPPORT) ?
+			true : false;
+		break;
+	case LIBIE_AQC_CAPS_MAX_MTU:
+		caps->max_mtu = number;
+		break;
+	case LIBIE_AQC_CAPS_PCIE_RESET_AVOIDANCE:
+		caps->pcie_reset_avoidance = (number > 0);
+		break;
+	case LIBIE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT:
+		caps->reset_restrict_support = (number == 1);
+		break;
+	case LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG0:
+	case LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG1:
+	case LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG2:
+	case LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG3:
+	{
+		u8 index = cap - LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG0;
+
+		caps->ext_topo_dev_img_ver_high[index] = number;
+		caps->ext_topo_dev_img_ver_low[index] = logical_id;
+		caps->ext_topo_dev_img_part_num[index] =
+			FIELD_GET(IXGBE_EXT_TOPO_DEV_IMG_PART_NUM_M, phys_id);
+		caps->ext_topo_dev_img_load_en[index] =
+			(phys_id & IXGBE_EXT_TOPO_DEV_IMG_LOAD_EN) != 0;
+		caps->ext_topo_dev_img_prog_en[index] =
+			(phys_id & IXGBE_EXT_TOPO_DEV_IMG_PROG_EN) != 0;
+		break;
+	}
+	default:
+		/* Not one of the recognized common capabilities */
+		return false;
+	}
+
+	return true;
+}
+
+/**
+ * ixgbe_parse_valid_functions_cap - Parse LIBIE_AQC_CAPS_VALID_FUNCTIONS caps
+ * @hw: pointer to the HW struct
+ * @dev_p: pointer to device capabilities structure
+ * @cap: capability element to parse
+ *
+ * Parse LIBIE_AQC_CAPS_VALID_FUNCTIONS for device capabilities.
+ */
+static void
+ixgbe_parse_valid_functions_cap(struct ixgbe_hw *hw,
+				struct ixgbe_hw_dev_caps *dev_p,
+				struct libie_aqc_list_caps_elem *cap)
+{
+	dev_p->num_funcs = hweight32(le32_to_cpu(cap->number));
+}
+
+/**
+ * ixgbe_parse_vf_dev_caps - Parse LIBIE_AQC_CAPS_VF device caps
+ * @hw: pointer to the HW struct
+ * @dev_p: pointer to device capabilities structure
+ * @cap: capability element to parse
+ *
+ * Parse LIBIE_AQC_CAPS_VF for device capabilities.
+ */
+static void ixgbe_parse_vf_dev_caps(struct ixgbe_hw *hw,
+				    struct ixgbe_hw_dev_caps *dev_p,
+				    struct libie_aqc_list_caps_elem *cap)
+{
+	dev_p->num_vfs_exposed = le32_to_cpu(cap->number);
+}
+
+/**
+ * ixgbe_parse_vsi_dev_caps - Parse LIBIE_AQC_CAPS_VSI device caps
+ * @hw: pointer to the HW struct
+ * @dev_p: pointer to device capabilities structure
+ * @cap: capability element to parse
+ *
+ * Parse LIBIE_AQC_CAPS_VSI for device capabilities.
+ */
+static void ixgbe_parse_vsi_dev_caps(struct ixgbe_hw *hw,
+				     struct ixgbe_hw_dev_caps *dev_p,
+				     struct libie_aqc_list_caps_elem *cap)
+{
+	dev_p->num_vsi_allocd_to_host = le32_to_cpu(cap->number);
+}
+
+/**
+ * ixgbe_parse_fdir_dev_caps - Parse LIBIE_AQC_CAPS_FD device caps
+ * @hw: pointer to the HW struct
+ * @dev_p: pointer to device capabilities structure
+ * @cap: capability element to parse
+ *
+ * Parse LIBIE_AQC_CAPS_FD for device capabilities.
+ */
+static void ixgbe_parse_fdir_dev_caps(struct ixgbe_hw *hw,
+				      struct ixgbe_hw_dev_caps *dev_p,
+				      struct libie_aqc_list_caps_elem *cap)
+{
+	dev_p->num_flow_director_fltr = le32_to_cpu(cap->number);
+}
+
+/**
+ * ixgbe_parse_dev_caps - Parse device capabilities
+ * @hw: pointer to the HW struct
+ * @dev_p: pointer to device capabilities structure
+ * @buf: buffer containing the device capability records
+ * @cap_count: the number of capabilities
+ *
+ * Helper device to parse device (0x000B) capabilities list. For
+ * capabilities shared between device and function, this relies on
+ * ixgbe_parse_e610_caps.
+ *
+ * Loop through the list of provided capabilities and extract the relevant
+ * data into the device capabilities structured.
+ */
+static void ixgbe_parse_dev_caps(struct ixgbe_hw *hw,
+				 struct ixgbe_hw_dev_caps *dev_p,
+				 void *buf, u32 cap_count)
+{
+	struct libie_aqc_list_caps_elem *cap_resp;
+	u32 i;
+
+	cap_resp = (struct libie_aqc_list_caps_elem *)buf;
+
+	memset(dev_p, 0, sizeof(*dev_p));
+
+	for (i = 0; i < cap_count; i++) {
+		u16 cap = le16_to_cpu(cap_resp[i].cap);
+
+		ixgbe_parse_e610_caps(hw, &dev_p->common_cap, &cap_resp[i],
+				      "dev caps");
+
+		switch (cap) {
+		case LIBIE_AQC_CAPS_VALID_FUNCTIONS:
+			ixgbe_parse_valid_functions_cap(hw, dev_p,
+							&cap_resp[i]);
+			break;
+		case LIBIE_AQC_CAPS_VF:
+			ixgbe_parse_vf_dev_caps(hw, dev_p, &cap_resp[i]);
+			break;
+		case LIBIE_AQC_CAPS_VSI:
+			ixgbe_parse_vsi_dev_caps(hw, dev_p, &cap_resp[i]);
+			break;
+		case  LIBIE_AQC_CAPS_FD:
+			ixgbe_parse_fdir_dev_caps(hw, dev_p, &cap_resp[i]);
+			break;
+		default:
+			/* Don't list common capabilities as unknown */
+			break;
+		}
+	}
+}
+
+/**
+ * ixgbe_parse_vf_func_caps - Parse LIBIE_AQC_CAPS_VF function caps
+ * @hw: pointer to the HW struct
+ * @func_p: pointer to function capabilities structure
+ * @cap: pointer to the capability element to parse
+ *
+ * Extract function capabilities for LIBIE_AQC_CAPS_VF.
+ */
+static void ixgbe_parse_vf_func_caps(struct ixgbe_hw *hw,
+				     struct ixgbe_hw_func_caps *func_p,
+				     struct libie_aqc_list_caps_elem *cap)
+{
+	func_p->num_allocd_vfs = le32_to_cpu(cap->number);
+	func_p->vf_base_id = le32_to_cpu(cap->logical_id);
+}
+
+/**
+ * ixgbe_get_num_per_func - determine number of resources per PF
+ * @hw: pointer to the HW structure
+ * @max: value to be evenly split between each PF
+ *
+ * Determine the number of valid functions by going through the bitmap returned
+ * from parsing capabilities and use this to calculate the number of resources
+ * per PF based on the max value passed in.
+ *
+ * Return: the number of resources per PF or 0, if no PFs are available.
+ */
+static u32 ixgbe_get_num_per_func(struct ixgbe_hw *hw, u32 max)
+{
+#define IXGBE_CAPS_VALID_FUNCS_M	GENMASK(7, 0)
+	u8 funcs = hweight8(hw->dev_caps.common_cap.valid_functions &
+			    IXGBE_CAPS_VALID_FUNCS_M);
+
+	return funcs ? (max / funcs) : 0;
+}
+
+/**
+ * ixgbe_parse_vsi_func_caps - Parse LIBIE_AQC_CAPS_VSI function caps
+ * @hw: pointer to the HW struct
+ * @func_p: pointer to function capabilities structure
+ * @cap: pointer to the capability element to parse
+ *
+ * Extract function capabilities for LIBIE_AQC_CAPS_VSI.
+ */
+static void ixgbe_parse_vsi_func_caps(struct ixgbe_hw *hw,
+				      struct ixgbe_hw_func_caps *func_p,
+				      struct libie_aqc_list_caps_elem *cap)
+{
+	func_p->guar_num_vsi = ixgbe_get_num_per_func(hw, IXGBE_MAX_VSI);
+}
+
+/**
+ * ixgbe_parse_func_caps - Parse function capabilities
+ * @hw: pointer to the HW struct
+ * @func_p: pointer to function capabilities structure
+ * @buf: buffer containing the function capability records
+ * @cap_count: the number of capabilities
+ *
+ * Helper function to parse function (0x000A) capabilities list. For
+ * capabilities shared between device and function, this relies on
+ * ixgbe_parse_e610_caps.
+ *
+ * Loop through the list of provided capabilities and extract the relevant
+ * data into the function capabilities structured.
+ */
+static void ixgbe_parse_func_caps(struct ixgbe_hw *hw,
+				  struct ixgbe_hw_func_caps *func_p,
+				  void *buf, u32 cap_count)
+{
+	struct libie_aqc_list_caps_elem *cap_resp;
+	u32 i;
+
+	cap_resp = (struct libie_aqc_list_caps_elem *)buf;
+
+	memset(func_p, 0, sizeof(*func_p));
+
+	for (i = 0; i < cap_count; i++) {
+		u16 cap = le16_to_cpu(cap_resp[i].cap);
+
+		ixgbe_parse_e610_caps(hw, &func_p->common_cap,
+				      &cap_resp[i], "func caps");
+
+		switch (cap) {
+		case LIBIE_AQC_CAPS_VF:
+			ixgbe_parse_vf_func_caps(hw, func_p, &cap_resp[i]);
+			break;
+		case LIBIE_AQC_CAPS_VSI:
+			ixgbe_parse_vsi_func_caps(hw, func_p, &cap_resp[i]);
+			break;
+		default:
+			/* Don't list common capabilities as unknown */
+			break;
+		}
+	}
+}
+
+/**
+ * ixgbe_aci_list_caps - query function/device capabilities
+ * @hw: pointer to the HW struct
+ * @buf: a buffer to hold the capabilities
+ * @buf_size: size of the buffer
+ * @cap_count: if not NULL, set to the number of capabilities reported
+ * @opc: capabilities type to discover, device or function
+ *
+ * Get the function (0x000A) or device (0x000B) capabilities description from
+ * firmware and store it in the buffer.
+ *
+ * If the cap_count pointer is not NULL, then it is set to the number of
+ * capabilities firmware will report. Note that if the buffer size is too
+ * small, it is possible the command will return -ENOMEM. The
+ * cap_count will still be updated in this case. It is recommended that the
+ * buffer size be set to IXGBE_ACI_MAX_BUFFER_SIZE (the largest possible
+ * buffer that firmware could return) to avoid this.
+ *
+ * Return: the exit code of the operation.
+ * Exit code of -ENOMEM means the buffer size is too small.
+ */
+int ixgbe_aci_list_caps(struct ixgbe_hw *hw, void *buf, u16 buf_size,
+			u32 *cap_count, enum ixgbe_aci_opc opc)
+{
+	struct libie_aqc_list_caps *cmd;
+	struct libie_aq_desc desc;
+	int err;
+
+	cmd = &desc.params.get_cap;
+
+	if (opc != ixgbe_aci_opc_list_func_caps &&
+	    opc != ixgbe_aci_opc_list_dev_caps)
+		return -EINVAL;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, opc);
+	err = ixgbe_aci_send_cmd(hw, &desc, buf, buf_size);
+
+	if (cap_count)
+		*cap_count = le32_to_cpu(cmd->count);
+
+	return err;
+}
+
+/**
+ * ixgbe_discover_dev_caps - Read and extract device capabilities
+ * @hw: pointer to the hardware structure
+ * @dev_caps: pointer to device capabilities structure
+ *
+ * Read the device capabilities and extract them into the dev_caps structure
+ * for later use.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_discover_dev_caps(struct ixgbe_hw *hw,
+			    struct ixgbe_hw_dev_caps *dev_caps)
+{
+	u32 cap_count;
+	u8 *cbuf;
+	int err;
+
+	cbuf = kzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL);
+	if (!cbuf)
+		return -ENOMEM;
+
+	/* Although the driver doesn't know the number of capabilities the
+	 * device will return, we can simply send a 4KB buffer, the maximum
+	 * possible size that firmware can return.
+	 */
+	cap_count = IXGBE_ACI_MAX_BUFFER_SIZE /
+		    sizeof(struct libie_aqc_list_caps_elem);
+
+	err = ixgbe_aci_list_caps(hw, cbuf, IXGBE_ACI_MAX_BUFFER_SIZE,
+				  &cap_count,
+				  ixgbe_aci_opc_list_dev_caps);
+	if (!err)
+		ixgbe_parse_dev_caps(hw, dev_caps, cbuf, cap_count);
+
+	kfree(cbuf);
+
+	return 0;
+}
+
+/**
+ * ixgbe_discover_func_caps - Read and extract function capabilities
+ * @hw: pointer to the hardware structure
+ * @func_caps: pointer to function capabilities structure
+ *
+ * Read the function capabilities and extract them into the func_caps structure
+ * for later use.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_discover_func_caps(struct ixgbe_hw *hw,
+			     struct ixgbe_hw_func_caps *func_caps)
+{
+	u32 cap_count;
+	u8 *cbuf;
+	int err;
+
+	cbuf = kzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL);
+	if (!cbuf)
+		return -ENOMEM;
+
+	/* Although the driver doesn't know the number of capabilities the
+	 * device will return, we can simply send a 4KB buffer, the maximum
+	 * possible size that firmware can return.
+	 */
+	cap_count = IXGBE_ACI_MAX_BUFFER_SIZE /
+		    sizeof(struct libie_aqc_list_caps_elem);
+
+	err = ixgbe_aci_list_caps(hw, cbuf, IXGBE_ACI_MAX_BUFFER_SIZE,
+				  &cap_count,
+				  ixgbe_aci_opc_list_func_caps);
+	if (!err)
+		ixgbe_parse_func_caps(hw, func_caps, cbuf, cap_count);
+
+	kfree(cbuf);
+
+	return 0;
+}
+
+/**
+ * ixgbe_get_caps - get info about the HW
+ * @hw: pointer to the hardware structure
+ *
+ * Retrieve both device and function capabilities.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_caps(struct ixgbe_hw *hw)
+{
+	int err;
+
+	err = ixgbe_discover_dev_caps(hw, &hw->dev_caps);
+	if (err)
+		return err;
+
+	return ixgbe_discover_func_caps(hw, &hw->func_caps);
+}
+
+/**
+ * ixgbe_aci_disable_rxen - disable RX
+ * @hw: pointer to the HW struct
+ *
+ * Request a safe disable of Receive Enable using ACI command (0x000C).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_disable_rxen(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_disable_rxen *cmd;
+	struct libie_aq_desc desc;
+
+	cmd = libie_aq_raw(&desc);
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_disable_rxen);
+
+	cmd->lport_num = hw->bus.func;
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
+ * ixgbe_aci_get_phy_caps - returns PHY capabilities
+ * @hw: pointer to the HW struct
+ * @qual_mods: report qualified modules
+ * @report_mode: report mode capabilities
+ * @pcaps: structure for PHY capabilities to be filled
+ *
+ * Returns the various PHY capabilities supported on the Port
+ * using ACI command (0x0600).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_get_phy_caps(struct ixgbe_hw *hw, bool qual_mods, u8 report_mode,
+			   struct ixgbe_aci_cmd_get_phy_caps_data *pcaps)
+{
+	struct ixgbe_aci_cmd_get_phy_caps *cmd;
+	u16 pcaps_size = sizeof(*pcaps);
+	struct libie_aq_desc desc;
+	int err;
+
+	cmd = libie_aq_raw(&desc);
+
+	if (!pcaps || (report_mode & ~IXGBE_ACI_REPORT_MODE_M))
+		return -EINVAL;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_phy_caps);
+
+	if (qual_mods)
+		cmd->param0 |= cpu_to_le16(IXGBE_ACI_GET_PHY_RQM);
+
+	cmd->param0 |= cpu_to_le16(report_mode);
+	err = ixgbe_aci_send_cmd(hw, &desc, pcaps, pcaps_size);
+	if (!err && report_mode == IXGBE_ACI_REPORT_TOPO_CAP_MEDIA) {
+		hw->phy.phy_type_low = le64_to_cpu(pcaps->phy_type_low);
+		hw->phy.phy_type_high = le64_to_cpu(pcaps->phy_type_high);
+		memcpy(hw->link.link_info.module_type, &pcaps->module_type,
+		       sizeof(hw->link.link_info.module_type));
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_copy_phy_caps_to_cfg - Copy PHY ability data to configuration data
+ * @caps: PHY ability structure to copy data from
+ * @cfg: PHY configuration structure to copy data to
+ *
+ * Helper function to copy data from PHY capabilities data structure
+ * to PHY configuration data structure
+ */
+void ixgbe_copy_phy_caps_to_cfg(struct ixgbe_aci_cmd_get_phy_caps_data *caps,
+				struct ixgbe_aci_cmd_set_phy_cfg_data *cfg)
+{
+	if (!caps || !cfg)
+		return;
+
+	memset(cfg, 0, sizeof(*cfg));
+	cfg->phy_type_low = caps->phy_type_low;
+	cfg->phy_type_high = caps->phy_type_high;
+	cfg->caps = caps->caps;
+	cfg->low_power_ctrl_an = caps->low_power_ctrl_an;
+	cfg->eee_cap = caps->eee_cap;
+	cfg->eeer_value = caps->eeer_value;
+	cfg->link_fec_opt = caps->link_fec_options;
+	cfg->module_compliance_enforcement =
+		caps->module_compliance_enforcement;
+}
+
+/**
+ * ixgbe_aci_set_phy_cfg - set PHY configuration
+ * @hw: pointer to the HW struct
+ * @cfg: structure with PHY configuration data to be set
+ *
+ * Set the various PHY configuration parameters supported on the Port
+ * using ACI command (0x0601).
+ * One or more of the Set PHY config parameters may be ignored in an MFP
+ * mode as the PF may not have the privilege to set some of the PHY Config
+ * parameters.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_set_phy_cfg(struct ixgbe_hw *hw,
+			  struct ixgbe_aci_cmd_set_phy_cfg_data *cfg)
+{
+	struct ixgbe_aci_cmd_set_phy_cfg *cmd;
+	struct libie_aq_desc desc;
+	int err;
+
+	if (!cfg)
+		return -EINVAL;
+
+	cmd = libie_aq_raw(&desc);
+	/* Ensure that only valid bits of cfg->caps can be turned on. */
+	cfg->caps &= IXGBE_ACI_PHY_ENA_VALID_MASK;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_phy_cfg);
+	cmd->lport_num = hw->bus.func;
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
+
+	err = ixgbe_aci_send_cmd(hw, &desc, cfg, sizeof(*cfg));
+	if (!err)
+		hw->phy.curr_user_phy_cfg = *cfg;
+
+	return err;
+}
+
+/**
+ * ixgbe_aci_set_link_restart_an - set up link and restart AN
+ * @hw: pointer to the HW struct
+ * @ena_link: if true: enable link, if false: disable link
+ *
+ * Function sets up the link and restarts the Auto-Negotiation over the link.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_set_link_restart_an(struct ixgbe_hw *hw, bool ena_link)
+{
+	struct ixgbe_aci_cmd_restart_an *cmd;
+	struct libie_aq_desc desc;
+
+	cmd = libie_aq_raw(&desc);
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_restart_an);
+
+	cmd->cmd_flags = IXGBE_ACI_RESTART_AN_LINK_RESTART;
+	cmd->lport_num = hw->bus.func;
+	if (ena_link)
+		cmd->cmd_flags |= IXGBE_ACI_RESTART_AN_LINK_ENABLE;
+	else
+		cmd->cmd_flags &= ~IXGBE_ACI_RESTART_AN_LINK_ENABLE;
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
+ * ixgbe_is_media_cage_present - check if media cage is present
+ * @hw: pointer to the HW struct
+ *
+ * Identify presence of media cage using the ACI command (0x06E0).
+ *
+ * Return: true if media cage is present, else false. If no cage, then
+ * media type is backplane or BASE-T.
+ */
+static bool ixgbe_is_media_cage_present(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_link_topo *cmd;
+	struct libie_aq_desc desc;
+
+	cmd = libie_aq_raw(&desc);
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_topo);
+
+	cmd->addr.topo_params.node_type_ctx =
+		FIELD_PREP(IXGBE_ACI_LINK_TOPO_NODE_CTX_M,
+			   IXGBE_ACI_LINK_TOPO_NODE_CTX_PORT);
+
+	/* Set node type. */
+	cmd->addr.topo_params.node_type_ctx |=
+		FIELD_PREP(IXGBE_ACI_LINK_TOPO_NODE_TYPE_M,
+			   IXGBE_ACI_LINK_TOPO_NODE_TYPE_CAGE);
+
+	/* Node type cage can be used to determine if cage is present. If AQC
+	 * returns error (ENOENT), then no cage present. If no cage present then
+	 * connection type is backplane or BASE-T.
+	 */
+	return !ixgbe_aci_get_netlist_node(hw, cmd, NULL, NULL);
+}
+
+/**
+ * ixgbe_get_media_type_from_phy_type - Gets media type based on phy type
+ * @hw: pointer to the HW struct
+ *
+ * Try to identify the media type based on the phy type.
+ * If more than one media type, the ixgbe_media_type_unknown is returned.
+ * First, phy_type_low is checked, then phy_type_high.
+ * If none are identified, the ixgbe_media_type_unknown is returned
+ *
+ * Return: type of a media based on phy type in form of enum.
+ */
+static enum ixgbe_media_type
+ixgbe_get_media_type_from_phy_type(struct ixgbe_hw *hw)
+{
+	struct ixgbe_link_status *hw_link_info;
+
+	if (!hw)
+		return ixgbe_media_type_unknown;
+
+	hw_link_info = &hw->link.link_info;
+	if (hw_link_info->phy_type_low && hw_link_info->phy_type_high)
+		/* If more than one media type is selected, report unknown */
+		return ixgbe_media_type_unknown;
+
+	if (hw_link_info->phy_type_low) {
+		/* 1G SGMII is a special case where some DA cable PHYs
+		 * may show this as an option when it really shouldn't
+		 * be since SGMII is meant to be between a MAC and a PHY
+		 * in a backplane. Try to detect this case and handle it
+		 */
+		if (hw_link_info->phy_type_low == IXGBE_PHY_TYPE_LOW_1G_SGMII &&
+		    (hw_link_info->module_type[IXGBE_ACI_MOD_TYPE_IDENT] ==
+		    IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_ACTIVE ||
+		    hw_link_info->module_type[IXGBE_ACI_MOD_TYPE_IDENT] ==
+		    IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_PASSIVE))
+			return ixgbe_media_type_da;
+
+		switch (hw_link_info->phy_type_low) {
+		case IXGBE_PHY_TYPE_LOW_1000BASE_SX:
+		case IXGBE_PHY_TYPE_LOW_1000BASE_LX:
+		case IXGBE_PHY_TYPE_LOW_10GBASE_SR:
+		case IXGBE_PHY_TYPE_LOW_10GBASE_LR:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_SR:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_LR:
+			return ixgbe_media_type_fiber;
+		case IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC:
+		case IXGBE_PHY_TYPE_LOW_25G_AUI_AOC_ACC:
+			return ixgbe_media_type_fiber;
+		case IXGBE_PHY_TYPE_LOW_100BASE_TX:
+		case IXGBE_PHY_TYPE_LOW_1000BASE_T:
+		case IXGBE_PHY_TYPE_LOW_2500BASE_T:
+		case IXGBE_PHY_TYPE_LOW_5GBASE_T:
+		case IXGBE_PHY_TYPE_LOW_10GBASE_T:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_T:
+			return ixgbe_media_type_copper;
+		case IXGBE_PHY_TYPE_LOW_10G_SFI_DA:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_CR:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_CR_S:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_CR1:
+			return ixgbe_media_type_da;
+		case IXGBE_PHY_TYPE_LOW_25G_AUI_C2C:
+			if (ixgbe_is_media_cage_present(hw))
+				return ixgbe_media_type_aui;
+			fallthrough;
+		case IXGBE_PHY_TYPE_LOW_1000BASE_KX:
+		case IXGBE_PHY_TYPE_LOW_2500BASE_KX:
+		case IXGBE_PHY_TYPE_LOW_2500BASE_X:
+		case IXGBE_PHY_TYPE_LOW_5GBASE_KR:
+		case IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1:
+		case IXGBE_PHY_TYPE_LOW_10G_SFI_C2C:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_KR:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_KR1:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_KR_S:
+			return ixgbe_media_type_backplane;
+		}
+	} else {
+		switch (hw_link_info->phy_type_high) {
+		case IXGBE_PHY_TYPE_HIGH_10BASE_T:
+			return ixgbe_media_type_copper;
+		}
+	}
+	return ixgbe_media_type_unknown;
+}
+
+/**
+ * ixgbe_update_link_info - update status of the HW network link
+ * @hw: pointer to the HW struct
+ *
+ * Update the status of the HW network link.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_update_link_info(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data *pcaps;
+	struct ixgbe_link_status *li;
+	int err;
+
+	if (!hw)
+		return -EINVAL;
+
+	li = &hw->link.link_info;
+
+	err = ixgbe_aci_get_link_info(hw, true, NULL);
+	if (err)
+		return err;
+
+	if (!(li->link_info & IXGBE_ACI_MEDIA_AVAILABLE))
+		return 0;
+
+	pcaps =	kzalloc(sizeof(*pcaps), GFP_KERNEL);
+	if (!pcaps)
+		return -ENOMEM;
+
+	err = ixgbe_aci_get_phy_caps(hw, false, IXGBE_ACI_REPORT_TOPO_CAP_MEDIA,
+				     pcaps);
+
+	if (!err)
+		memcpy(li->module_type, &pcaps->module_type,
+		       sizeof(li->module_type));
+
+	kfree(pcaps);
+
+	return err;
+}
+
+/**
+ * ixgbe_get_link_status - get status of the HW network link
+ * @hw: pointer to the HW struct
+ * @link_up: pointer to bool (true/false = linkup/linkdown)
+ *
+ * Variable link_up is true if link is up, false if link is down.
+ * The variable link_up is invalid if status is non zero. As a
+ * result of this call, link status reporting becomes enabled
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_link_status(struct ixgbe_hw *hw, bool *link_up)
+{
+	if (!hw || !link_up)
+		return -EINVAL;
+
+	if (hw->link.get_link_info) {
+		int err = ixgbe_update_link_info(hw);
+
+		if (err)
+			return err;
+	}
+
+	*link_up = hw->link.link_info.link_info & IXGBE_ACI_LINK_UP;
+
+	return 0;
+}
+
+/**
+ * ixgbe_aci_get_link_info - get the link status
+ * @hw: pointer to the HW struct
+ * @ena_lse: enable/disable LinkStatusEvent reporting
+ * @link: pointer to link status structure - optional
+ *
+ * Get the current Link Status using ACI command (0x607).
+ * The current link can be optionally provided to update
+ * the status.
+ *
+ * Return: the link status of the adapter.
+ */
+int ixgbe_aci_get_link_info(struct ixgbe_hw *hw, bool ena_lse,
+			    struct ixgbe_link_status *link)
+{
+	struct ixgbe_aci_cmd_get_link_status_data link_data = {};
+	struct ixgbe_aci_cmd_get_link_status *resp;
+	struct ixgbe_link_status *li_old, *li;
+	struct ixgbe_fc_info *hw_fc_info;
+	struct libie_aq_desc desc;
+	bool tx_pause, rx_pause;
+	u8 cmd_flags;
+	int err;
+
+	if (!hw)
+		return -EINVAL;
+
+	li_old = &hw->link.link_info_old;
+	li = &hw->link.link_info;
+	hw_fc_info = &hw->fc;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_status);
+	cmd_flags = (ena_lse) ? IXGBE_ACI_LSE_ENA : IXGBE_ACI_LSE_DIS;
+	resp = libie_aq_raw(&desc);
+	resp->cmd_flags = cpu_to_le16(cmd_flags);
+	resp->lport_num = hw->bus.func;
+
+	err = ixgbe_aci_send_cmd(hw, &desc, &link_data, sizeof(link_data));
+	if (err)
+		return err;
+
+	/* Save off old link status information. */
+	*li_old = *li;
+
+	/* Update current link status information. */
+	li->link_speed = le16_to_cpu(link_data.link_speed);
+	li->phy_type_low = le64_to_cpu(link_data.phy_type_low);
+	li->phy_type_high = le64_to_cpu(link_data.phy_type_high);
+	li->link_info = link_data.link_info;
+	li->link_cfg_err = link_data.link_cfg_err;
+	li->an_info = link_data.an_info;
+	li->ext_info = link_data.ext_info;
+	li->max_frame_size = le16_to_cpu(link_data.max_frame_size);
+	li->fec_info = link_data.cfg & IXGBE_ACI_FEC_MASK;
+	li->topo_media_conflict = link_data.topo_media_conflict;
+	li->pacing = link_data.cfg & (IXGBE_ACI_CFG_PACING_M |
+				      IXGBE_ACI_CFG_PACING_TYPE_M);
+
+	/* Update fc info. */
+	tx_pause = !!(link_data.an_info & IXGBE_ACI_LINK_PAUSE_TX);
+	rx_pause = !!(link_data.an_info & IXGBE_ACI_LINK_PAUSE_RX);
+	if (tx_pause && rx_pause)
+		hw_fc_info->current_mode = ixgbe_fc_full;
+	else if (tx_pause)
+		hw_fc_info->current_mode = ixgbe_fc_tx_pause;
+	else if (rx_pause)
+		hw_fc_info->current_mode = ixgbe_fc_rx_pause;
+	else
+		hw_fc_info->current_mode = ixgbe_fc_none;
+
+	li->lse_ena = !!(le16_to_cpu(resp->cmd_flags) &
+			 IXGBE_ACI_LSE_IS_ENABLED);
+
+	/* Save link status information. */
+	if (link)
+		*link = *li;
+
+	/* Flag cleared so calling functions don't call AQ again. */
+	hw->link.get_link_info = false;
+
+	return 0;
+}
+
+/**
+ * ixgbe_aci_set_event_mask - set event mask
+ * @hw: pointer to the HW struct
+ * @port_num: port number of the physical function
+ * @mask: event mask to be set
+ *
+ * Set the event mask using ACI command (0x0613).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_set_event_mask(struct ixgbe_hw *hw, u8 port_num, u16 mask)
+{
+	struct ixgbe_aci_cmd_set_event_mask *cmd;
+	struct libie_aq_desc desc;
+
+	cmd = libie_aq_raw(&desc);
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_event_mask);
+
+	cmd->lport_num = port_num;
+
+	cmd->event_mask = cpu_to_le16(mask);
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
+ * ixgbe_configure_lse - enable/disable link status events
+ * @hw: pointer to the HW struct
+ * @activate: true for enable lse, false otherwise
+ * @mask: event mask to be set; a set bit means deactivation of the
+ * corresponding event
+ *
+ * Set the event mask and then enable or disable link status events
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_configure_lse(struct ixgbe_hw *hw, bool activate, u16 mask)
+{
+	int err;
+
+	err = ixgbe_aci_set_event_mask(hw, (u8)hw->bus.func, mask);
+	if (err)
+		return err;
+
+	/* Enabling link status events generation by fw. */
+	return ixgbe_aci_get_link_info(hw, activate, NULL);
+}
+
+/**
+ * ixgbe_start_hw_e610 - Prepare hardware for Tx/Rx
+ * @hw: pointer to hardware structure
+ *
+ * Get firmware version and start the hardware using the generic
+ * start_hw() and ixgbe_start_hw_gen2() functions.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_start_hw_e610(struct ixgbe_hw *hw)
+{
+	int err;
+
+	err = ixgbe_aci_get_fw_ver(hw);
+	if (err)
+		return err;
+
+	err = ixgbe_start_hw_generic(hw);
+	if (err)
+		return err;
+
+	ixgbe_start_hw_gen2(hw);
+
+	return 0;
+}
+
+/**
+ * ixgbe_aci_set_port_id_led - set LED value for the given port
+ * @hw: pointer to the HW struct
+ * @orig_mode: set LED original mode
+ *
+ * Set LED value for the given port (0x06E9)
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_set_port_id_led(struct ixgbe_hw *hw, bool orig_mode)
+{
+	struct ixgbe_aci_cmd_set_port_id_led *cmd;
+	struct libie_aq_desc desc;
+
+	cmd = libie_aq_raw(&desc);
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_port_id_led);
+
+	cmd->lport_num = (u8)hw->bus.func;
+	cmd->lport_num_valid = IXGBE_ACI_PORT_ID_PORT_NUM_VALID;
+
+	if (orig_mode)
+		cmd->ident_mode = IXGBE_ACI_PORT_IDENT_LED_ORIG;
+	else
+		cmd->ident_mode = IXGBE_ACI_PORT_IDENT_LED_BLINK;
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
+ * ixgbe_get_media_type_e610 - Gets media type
+ * @hw: pointer to the HW struct
+ *
+ * In order to get the media type, the function gets PHY
+ * capabilities and later on use them to identify the PHY type
+ * checking phy_type_high and phy_type_low.
+ *
+ * Return: the type of media in form of ixgbe_media_type enum
+ * or ixgbe_media_type_unknown in case of an error.
+ */
+enum ixgbe_media_type ixgbe_get_media_type_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data pcaps;
+	int rc;
+
+	rc = ixgbe_update_link_info(hw);
+	if (rc)
+		return ixgbe_media_type_unknown;
+
+	/* If there is no link but PHY (dongle) is available SW should use
+	 * Get PHY Caps admin command instead of Get Link Status, find most
+	 * significant bit that is set in PHY types reported by the command
+	 * and use it to discover media type.
+	 */
+	if (!(hw->link.link_info.link_info & IXGBE_ACI_LINK_UP) &&
+	    (hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE)) {
+		int highest_bit;
+
+		/* Get PHY Capabilities */
+		rc = ixgbe_aci_get_phy_caps(hw, false,
+					    IXGBE_ACI_REPORT_TOPO_CAP_MEDIA,
+					    &pcaps);
+		if (rc)
+			return ixgbe_media_type_unknown;
+
+		highest_bit = fls64(le64_to_cpu(pcaps.phy_type_high));
+		if (highest_bit) {
+			hw->link.link_info.phy_type_high =
+				BIT_ULL(highest_bit - 1);
+			hw->link.link_info.phy_type_low = 0;
+		} else {
+			highest_bit = fls64(le64_to_cpu(pcaps.phy_type_low));
+			if (highest_bit) {
+				hw->link.link_info.phy_type_low =
+					BIT_ULL(highest_bit - 1);
+				hw->link.link_info.phy_type_high = 0;
+			}
+		}
+	}
+
+	/* Based on link status or search above try to discover media type. */
+	hw->phy.media_type = ixgbe_get_media_type_from_phy_type(hw);
+
+	return hw->phy.media_type;
+}
+
+/**
+ * ixgbe_setup_link_e610 - Set up link
+ * @hw: pointer to hardware structure
+ * @speed: new link speed
+ * @autoneg_wait: true when waiting for completion is needed
+ *
+ * Set up the link with the specified speed.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_setup_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed speed,
+			  bool autoneg_wait)
+{
+	/* Simply request FW to perform proper PHY setup */
+	return hw->phy.ops.setup_link_speed(hw, speed, autoneg_wait);
+}
+
+/**
+ * ixgbe_check_link_e610 - Determine link and speed status
+ * @hw: pointer to hardware structure
+ * @speed: pointer to link speed
+ * @link_up: true when link is up
+ * @link_up_wait_to_complete: bool used to wait for link up or not
+ *
+ * Determine if the link is up and the current link speed
+ * using ACI command (0x0607).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_check_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
+			  bool *link_up, bool link_up_wait_to_complete)
+{
+	int err;
+	u32 i;
+
+	if (!speed || !link_up)
+		return -EINVAL;
+
+	/* Set get_link_info flag to ensure that fresh
+	 * link information will be obtained from FW
+	 * by sending Get Link Status admin command.
+	 */
+	hw->link.get_link_info = true;
+
+	/* Update link information in adapter context. */
+	err = ixgbe_get_link_status(hw, link_up);
+	if (err)
+		return err;
+
+	/* Wait for link up if it was requested. */
+	if (link_up_wait_to_complete && !(*link_up)) {
+		for (i = 0; i < hw->mac.max_link_up_time; i++) {
+			msleep(100);
+			hw->link.get_link_info = true;
+			err = ixgbe_get_link_status(hw, link_up);
+			if (err)
+				return err;
+			if (*link_up)
+				break;
+		}
+	}
+
+	/* Use link information in adapter context updated by the call
+	 * to ixgbe_get_link_status() to determine current link speed.
+	 * Link speed information is valid only when link up was
+	 * reported by FW.
+	 */
+	if (*link_up) {
+		switch (hw->link.link_info.link_speed) {
+		case IXGBE_ACI_LINK_SPEED_10MB:
+			*speed = IXGBE_LINK_SPEED_10_FULL;
+			break;
+		case IXGBE_ACI_LINK_SPEED_100MB:
+			*speed = IXGBE_LINK_SPEED_100_FULL;
+			break;
+		case IXGBE_ACI_LINK_SPEED_1000MB:
+			*speed = IXGBE_LINK_SPEED_1GB_FULL;
+			break;
+		case IXGBE_ACI_LINK_SPEED_2500MB:
+			*speed = IXGBE_LINK_SPEED_2_5GB_FULL;
+			break;
+		case IXGBE_ACI_LINK_SPEED_5GB:
+			*speed = IXGBE_LINK_SPEED_5GB_FULL;
+			break;
+		case IXGBE_ACI_LINK_SPEED_10GB:
+			*speed = IXGBE_LINK_SPEED_10GB_FULL;
+			break;
+		default:
+			*speed = IXGBE_LINK_SPEED_UNKNOWN;
+			break;
+		}
+	} else {
+		*speed = IXGBE_LINK_SPEED_UNKNOWN;
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_get_link_capabilities_e610 - Determine link capabilities
+ * @hw: pointer to hardware structure
+ * @speed: pointer to link speed
+ * @autoneg: true when autoneg or autotry is enabled
+ *
+ * Determine speed and AN parameters of a link.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_link_capabilities_e610(struct ixgbe_hw *hw,
+				     ixgbe_link_speed *speed,
+				     bool *autoneg)
+{
+	if (!speed || !autoneg)
+		return -EINVAL;
+
+	*autoneg = true;
+	*speed = hw->phy.speeds_supported;
+
+	return 0;
+}
+
+/**
+ * ixgbe_cfg_phy_fc - Configure PHY Flow Control (FC) data based on FC mode
+ * @hw: pointer to hardware structure
+ * @cfg: PHY configuration data to set FC mode
+ * @req_mode: FC mode to configure
+ *
+ * Configures PHY Flow Control according to the provided configuration.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_cfg_phy_fc(struct ixgbe_hw *hw,
+		     struct ixgbe_aci_cmd_set_phy_cfg_data *cfg,
+		     enum ixgbe_fc_mode req_mode)
+{
+	u8 pause_mask = 0x0;
+
+	if (!cfg)
+		return -EINVAL;
+
+	switch (req_mode) {
+	case ixgbe_fc_full:
+		pause_mask |= IXGBE_ACI_PHY_EN_TX_LINK_PAUSE;
+		pause_mask |= IXGBE_ACI_PHY_EN_RX_LINK_PAUSE;
+		break;
+	case ixgbe_fc_rx_pause:
+		pause_mask |= IXGBE_ACI_PHY_EN_RX_LINK_PAUSE;
+		break;
+	case ixgbe_fc_tx_pause:
+		pause_mask |= IXGBE_ACI_PHY_EN_TX_LINK_PAUSE;
+		break;
+	default:
+		break;
+	}
+
+	/* Clear the old pause settings. */
+	cfg->caps &= ~(IXGBE_ACI_PHY_EN_TX_LINK_PAUSE |
+		IXGBE_ACI_PHY_EN_RX_LINK_PAUSE);
+
+	/* Set the new capabilities. */
+	cfg->caps |= pause_mask;
+
+	return 0;
+}
+
+/**
+ * ixgbe_setup_fc_e610 - Set up flow control
+ * @hw: pointer to hardware structure
+ *
+ * Set up flow control. This has to be done during init time.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_setup_fc_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data pcaps = {};
+	struct ixgbe_aci_cmd_set_phy_cfg_data cfg = {};
+	int err;
+
+	/* Get the current PHY config */
+	err = ixgbe_aci_get_phy_caps(hw, false,
+				     IXGBE_ACI_REPORT_ACTIVE_CFG, &pcaps);
+	if (err)
+		return err;
+
+	ixgbe_copy_phy_caps_to_cfg(&pcaps, &cfg);
+
+	/* Configure the set PHY data */
+	err = ixgbe_cfg_phy_fc(hw, &cfg, hw->fc.requested_mode);
+	if (err)
+		return err;
+
+	/* If the capabilities have changed, then set the new config */
+	if (cfg.caps != pcaps.caps) {
+		cfg.caps |= IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT;
+
+		err = ixgbe_aci_set_phy_cfg(hw, &cfg);
+		if (err)
+			return err;
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_fc_autoneg_e610 - Configure flow control
+ * @hw: pointer to hardware structure
+ *
+ * Configure Flow Control.
+ */
+void ixgbe_fc_autoneg_e610(struct ixgbe_hw *hw)
+{
+	int err;
+
+	/* Get current link err.
+	 * Current FC mode will be stored in the hw context.
+	 */
+	err = ixgbe_aci_get_link_info(hw, false, NULL);
+	if (err)
+		goto no_autoneg;
+
+	/* Check if the link is up */
+	if (!(hw->link.link_info.link_info & IXGBE_ACI_LINK_UP))
+		goto no_autoneg;
+
+	/* Check if auto-negotiation has completed */
+	if (!(hw->link.link_info.an_info & IXGBE_ACI_AN_COMPLETED))
+		goto no_autoneg;
+
+	hw->fc.fc_was_autonegged = true;
+	return;
+
+no_autoneg:
+	hw->fc.fc_was_autonegged = false;
+	hw->fc.current_mode = hw->fc.requested_mode;
+}
+
+/**
+ * ixgbe_disable_rx_e610 - Disable RX unit
+ * @hw: pointer to hardware structure
+ *
+ * Disable RX DMA unit on E610 with use of ACI command (0x000C).
+ *
+ * Return: the exit code of the operation.
+ */
+void ixgbe_disable_rx_e610(struct ixgbe_hw *hw)
+{
+	u32 rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL);
+	u32 pfdtxgswc;
+	int err;
+
+	if (!(rxctrl & IXGBE_RXCTRL_RXEN))
+		return;
+
+	pfdtxgswc = IXGBE_READ_REG(hw, IXGBE_PFDTXGSWC);
+	if (pfdtxgswc & IXGBE_PFDTXGSWC_VT_LBEN) {
+		pfdtxgswc &= ~IXGBE_PFDTXGSWC_VT_LBEN;
+		IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, pfdtxgswc);
+		hw->mac.set_lben = true;
+	} else {
+		hw->mac.set_lben = false;
+	}
+
+	err = ixgbe_aci_disable_rxen(hw);
+
+	/* If we fail - disable RX using register write */
+	if (err) {
+		rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL);
+		if (rxctrl & IXGBE_RXCTRL_RXEN) {
+			rxctrl &= ~IXGBE_RXCTRL_RXEN;
+			IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, rxctrl);
+		}
+	}
+}
+
+/**
+ * ixgbe_fw_recovery_mode_e610 - Check FW NVM recovery mode
+ * @hw: pointer to hardware structure
+ *
+ * Check FW NVM recovery mode by reading the value of
+ * the dedicated register.
+ *
+ * Return: true if FW is in recovery mode, otherwise false.
+ */
+static bool ixgbe_fw_recovery_mode_e610(struct ixgbe_hw *hw)
+{
+	u32 fwsm = IXGBE_READ_REG(hw, IXGBE_GL_MNG_FWSM);
+
+	return !!(fwsm & IXGBE_GL_MNG_FWSM_RECOVERY_M);
+}
+
+/**
+ * ixgbe_fw_rollback_mode_e610 - Check FW NVM rollback mode
+ * @hw: pointer to hardware structure
+ *
+ * Check FW NVM rollback mode by reading the value of
+ * the dedicated register.
+ *
+ * Return: true if FW is in rollback mode, otherwise false.
+ */
+static bool ixgbe_fw_rollback_mode_e610(struct ixgbe_hw *hw)
+{
+	u32 fwsm = IXGBE_READ_REG(hw, IXGBE_GL_MNG_FWSM);
+
+	return !!(fwsm & IXGBE_GL_MNG_FWSM_ROLLBACK_M);
+}
+
+/**
+ * ixgbe_init_phy_ops_e610 - PHY specific init
+ * @hw: pointer to hardware structure
+ *
+ * Initialize any function pointers that were not able to be
+ * set during init_shared_code because the PHY type was not known.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_init_phy_ops_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_mac_info *mac = &hw->mac;
+	struct ixgbe_phy_info *phy = &hw->phy;
+
+	if (mac->ops.get_media_type(hw) == ixgbe_media_type_copper)
+		phy->ops.set_phy_power = ixgbe_set_phy_power_e610;
+	else
+		phy->ops.set_phy_power = NULL;
+
+	/* Identify the PHY */
+	return phy->ops.identify(hw);
+}
+
+/**
+ * ixgbe_identify_phy_e610 - Identify PHY
+ * @hw: pointer to hardware structure
+ *
+ * Determine PHY type, supported speeds and PHY ID.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_identify_phy_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data pcaps;
+	u64 phy_type_low, phy_type_high;
+	int err;
+
+	/* Set PHY type */
+	hw->phy.type = ixgbe_phy_fw;
+
+	err = ixgbe_aci_get_phy_caps(hw, false,
+				     IXGBE_ACI_REPORT_TOPO_CAP_MEDIA, &pcaps);
+	if (err)
+		return err;
+
+	if (!(pcaps.module_compliance_enforcement &
+	      IXGBE_ACI_MOD_ENFORCE_STRICT_MODE)) {
+		/* Handle lenient mode */
+		err = ixgbe_aci_get_phy_caps(hw, false,
+					     IXGBE_ACI_REPORT_TOPO_CAP_NO_MEDIA,
+					     &pcaps);
+		if (err)
+			return err;
+	}
+
+	/* Determine supported speeds */
+	hw->phy.speeds_supported = IXGBE_LINK_SPEED_UNKNOWN;
+	phy_type_high = le64_to_cpu(pcaps.phy_type_high);
+	phy_type_low = le64_to_cpu(pcaps.phy_type_low);
+
+	if (phy_type_high & IXGBE_PHY_TYPE_HIGH_10BASE_T ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_10M_SGMII)
+		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_10_FULL;
+	if (phy_type_low  & IXGBE_PHY_TYPE_LOW_100BASE_TX ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_100M_SGMII ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_100M_USXGMII)
+		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_100_FULL;
+	if (phy_type_low  & IXGBE_PHY_TYPE_LOW_1000BASE_T  ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_1000BASE_SX ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_1000BASE_LX ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_1000BASE_KX ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_1G_SGMII    ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_1G_USXGMII)
+		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_1GB_FULL;
+	if (phy_type_low  & IXGBE_PHY_TYPE_LOW_2500BASE_T   ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_2500BASE_X   ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_2500BASE_KX  ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_2500M_SGMII ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_2500M_USXGMII)
+		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_2_5GB_FULL;
+	if (phy_type_low  & IXGBE_PHY_TYPE_LOW_5GBASE_T  ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_5GBASE_KR ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_5G_USXGMII)
+		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_5GB_FULL;
+	if (phy_type_low  & IXGBE_PHY_TYPE_LOW_10GBASE_T       ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_10G_SFI_DA      ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_10GBASE_SR      ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_10GBASE_LR      ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1  ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_10G_SFI_C2C     ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_10G_USXGMII)
+		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_10GB_FULL;
+
+	/* Initialize autoneg speeds */
+	if (!hw->phy.autoneg_advertised)
+		hw->phy.autoneg_advertised = hw->phy.speeds_supported;
+
+	/* Set PHY ID */
+	memcpy(&hw->phy.id, pcaps.phy_id_oui, sizeof(u32));
+
+	hw->phy.eee_speeds_supported = IXGBE_LINK_SPEED_10_FULL |
+				       IXGBE_LINK_SPEED_100_FULL |
+				       IXGBE_LINK_SPEED_1GB_FULL;
+	hw->phy.eee_speeds_advertised = hw->phy.eee_speeds_supported;
+
+	return 0;
+}
+
+/**
+ * ixgbe_identify_module_e610 - Identify SFP module type
+ * @hw: pointer to hardware structure
+ *
+ * Identify the SFP module type.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_identify_module_e610(struct ixgbe_hw *hw)
+{
+	bool media_available;
+	u8 module_type;
+	int err;
+
+	err = ixgbe_update_link_info(hw);
+	if (err)
+		return err;
+
+	media_available =
+		(hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE);
+
+	if (media_available) {
+		hw->phy.sfp_type = ixgbe_sfp_type_unknown;
+
+		/* Get module type from hw context updated by
+		 * ixgbe_update_link_info()
+		 */
+		module_type = hw->link.link_info.module_type[IXGBE_ACI_MOD_TYPE_IDENT];
+
+		if ((module_type & IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_PASSIVE) ||
+		    (module_type & IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_ACTIVE)) {
+			hw->phy.sfp_type = ixgbe_sfp_type_da_cu;
+		} else if (module_type & IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_SR) {
+			hw->phy.sfp_type = ixgbe_sfp_type_sr;
+		} else if ((module_type & IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LR) ||
+			   (module_type & IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LRM)) {
+			hw->phy.sfp_type = ixgbe_sfp_type_lr;
+		}
+	} else {
+		hw->phy.sfp_type = ixgbe_sfp_type_not_present;
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_setup_phy_link_e610 - Sets up firmware-controlled PHYs
+ * @hw: pointer to hardware structure
+ *
+ * Set the parameters for the firmware-controlled PHYs.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_setup_phy_link_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data pcaps;
+	struct ixgbe_aci_cmd_set_phy_cfg_data pcfg;
+	u8 rmode = IXGBE_ACI_REPORT_TOPO_CAP_MEDIA;
+	u64 sup_phy_type_low, sup_phy_type_high;
+	u64 phy_type_low = 0, phy_type_high = 0;
+	int err;
+
+	err = ixgbe_aci_get_link_info(hw, false, NULL);
+	if (err)
+		return err;
+
+	/* If media is not available get default config. */
+	if (!(hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE))
+		rmode = IXGBE_ACI_REPORT_DFLT_CFG;
+
+	err = ixgbe_aci_get_phy_caps(hw, false, rmode, &pcaps);
+	if (err)
+		return err;
+
+	sup_phy_type_low = le64_to_cpu(pcaps.phy_type_low);
+	sup_phy_type_high = le64_to_cpu(pcaps.phy_type_high);
+
+	/* Get Active configuration to avoid unintended changes. */
+	err = ixgbe_aci_get_phy_caps(hw, false, IXGBE_ACI_REPORT_ACTIVE_CFG,
+				     &pcaps);
+	if (err)
+		return err;
+
+	ixgbe_copy_phy_caps_to_cfg(&pcaps, &pcfg);
+
+	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10_FULL) {
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_10BASE_T;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_10M_SGMII;
+	}
+	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) {
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_100BASE_TX;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_100M_SGMII;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_100M_USXGMII;
+	}
+	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) {
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_1000BASE_T;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_1000BASE_SX;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_1000BASE_LX;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_1000BASE_KX;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_1G_SGMII;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_1G_USXGMII;
+	}
+	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_2_5GB_FULL) {
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_2500BASE_T;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_2500BASE_X;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_2500BASE_KX;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_2500M_SGMII;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_2500M_USXGMII;
+	}
+	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_5GB_FULL) {
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_5GBASE_T;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_5GBASE_KR;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_5G_USXGMII;
+	}
+	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) {
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10GBASE_T;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10G_SFI_DA;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10GBASE_SR;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10GBASE_LR;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10G_SFI_C2C;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_10G_USXGMII;
+	}
+
+	/* Mask the set values to avoid requesting unsupported link types. */
+	phy_type_low &= sup_phy_type_low;
+	pcfg.phy_type_low = cpu_to_le64(phy_type_low);
+	phy_type_high &= sup_phy_type_high;
+	pcfg.phy_type_high = cpu_to_le64(phy_type_high);
+
+	if (pcfg.phy_type_high != pcaps.phy_type_high ||
+	    pcfg.phy_type_low != pcaps.phy_type_low ||
+	    pcfg.caps != pcaps.caps) {
+		pcfg.caps |= IXGBE_ACI_PHY_ENA_LINK;
+		pcfg.caps |= IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT;
+
+		err = ixgbe_aci_set_phy_cfg(hw, &pcfg);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_set_phy_power_e610 - Control power for copper PHY
+ * @hw: pointer to hardware structure
+ * @on: true for on, false for off
+ *
+ * Set the power on/off of the PHY
+ * by getting its capabilities and setting the appropriate
+ * configuration parameters.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_set_phy_power_e610(struct ixgbe_hw *hw, bool on)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data phy_caps = {};
+	struct ixgbe_aci_cmd_set_phy_cfg_data phy_cfg = {};
+	int err;
+
+	err = ixgbe_aci_get_phy_caps(hw, false,
+				     IXGBE_ACI_REPORT_ACTIVE_CFG,
+				     &phy_caps);
+	if (err)
+		return err;
+
+	ixgbe_copy_phy_caps_to_cfg(&phy_caps, &phy_cfg);
+
+	if (on)
+		phy_cfg.caps &= ~IXGBE_ACI_PHY_ENA_LOW_POWER;
+	else
+		phy_cfg.caps |= IXGBE_ACI_PHY_ENA_LOW_POWER;
+
+	/* PHY is already in requested power mode. */
+	if (phy_caps.caps == phy_cfg.caps)
+		return 0;
+
+	phy_cfg.caps |= IXGBE_ACI_PHY_ENA_LINK;
+	phy_cfg.caps |= IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT;
+
+	return ixgbe_aci_set_phy_cfg(hw, &phy_cfg);
+}
+
+/**
+ * ixgbe_enter_lplu_e610 - Transition to low power states
+ * @hw: pointer to hardware structure
+ *
+ * Configures Low Power Link Up on transition to low power states
+ * (from D0 to non-D0). Link is required to enter LPLU so avoid resetting the
+ * X557 PHY immediately prior to entering LPLU.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_enter_lplu_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data phy_caps = {};
+	struct ixgbe_aci_cmd_set_phy_cfg_data phy_cfg = {};
+	int err;
+
+	err = ixgbe_aci_get_phy_caps(hw, false,
+				     IXGBE_ACI_REPORT_ACTIVE_CFG,
+				     &phy_caps);
+	if (err)
+		return err;
+
+	ixgbe_copy_phy_caps_to_cfg(&phy_caps, &phy_cfg);
+
+	phy_cfg.low_power_ctrl_an |= IXGBE_ACI_PHY_EN_D3COLD_LOW_POWER_AUTONEG;
+
+	return ixgbe_aci_set_phy_cfg(hw, &phy_cfg);
+}
+
+/**
+ * ixgbe_init_eeprom_params_e610 - Initialize EEPROM params
+ * @hw: pointer to hardware structure
+ *
+ * Initialize the EEPROM parameters ixgbe_eeprom_info within the ixgbe_hw
+ * struct in order to set up EEPROM access.
+ *
+ * Return: the operation exit code.
+ */
+int ixgbe_init_eeprom_params_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_eeprom_info *eeprom = &hw->eeprom;
+	u32 gens_stat;
+	u8 sr_size;
+
+	if (eeprom->type != ixgbe_eeprom_uninitialized)
+		return 0;
+
+	eeprom->type = ixgbe_flash;
+
+	gens_stat = IXGBE_READ_REG(hw, GLNVM_GENS);
+	sr_size = FIELD_GET(GLNVM_GENS_SR_SIZE_M, gens_stat);
+
+	/* Switching to words (sr_size contains power of 2). */
+	eeprom->word_size = BIT(sr_size) * IXGBE_SR_WORDS_IN_1KB;
+
+	hw_dbg(hw, "Eeprom params: type = %d, size = %d\n", eeprom->type,
+	       eeprom->word_size);
+
+	return 0;
+}
+
+/**
+ * ixgbe_aci_get_netlist_node - get a node handle
+ * @hw: pointer to the hw struct
+ * @cmd: get_link_topo AQ structure
+ * @node_part_number: output node part number if node found
+ * @node_handle: output node handle parameter if node found
+ *
+ * Get the netlist node and assigns it to
+ * the provided handle using ACI command (0x06E0).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_get_netlist_node(struct ixgbe_hw *hw,
+			       struct ixgbe_aci_cmd_get_link_topo *cmd,
+			       u8 *node_part_number, u16 *node_handle)
+{
+	struct ixgbe_aci_cmd_get_link_topo *resp;
+	struct libie_aq_desc desc;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_topo);
+	resp = libie_aq_raw(&desc);
+	*resp = *cmd;
+
+	if (ixgbe_aci_send_cmd(hw, &desc, NULL, 0))
+		return -EOPNOTSUPP;
+
+	if (node_handle)
+		*node_handle = le16_to_cpu(resp->addr.handle);
+	if (node_part_number)
+		*node_part_number = resp->node_part_num;
+
+	return 0;
+}
+
+/**
+ * ixgbe_acquire_nvm - Generic request for acquiring the NVM ownership
+ * @hw: pointer to the HW structure
+ * @access: NVM access type (read or write)
+ *
+ * Request NVM ownership.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_acquire_nvm(struct ixgbe_hw *hw, enum libie_aq_res_access_type access)
+{
+	u32 fla;
+
+	/* Skip if we are in blank NVM programming mode */
+	fla = IXGBE_READ_REG(hw, IXGBE_GLNVM_FLA);
+	if ((fla & IXGBE_GLNVM_FLA_LOCKED_M) == 0)
+		return 0;
+
+	return ixgbe_acquire_res(hw, LIBIE_AQC_RES_ID_NVM, access,
+				 IXGBE_NVM_TIMEOUT);
+}
+
+/**
+ * ixgbe_release_nvm - Generic request for releasing the NVM ownership
+ * @hw: pointer to the HW structure
+ *
+ * Release NVM ownership.
+ */
+void ixgbe_release_nvm(struct ixgbe_hw *hw)
+{
+	u32 fla;
+
+	/* Skip if we are in blank NVM programming mode */
+	fla = IXGBE_READ_REG(hw, IXGBE_GLNVM_FLA);
+	if ((fla & IXGBE_GLNVM_FLA_LOCKED_M) == 0)
+		return;
+
+	ixgbe_release_res(hw, LIBIE_AQC_RES_ID_NVM);
+}
+
+/**
+ * ixgbe_aci_read_nvm - read NVM
+ * @hw: pointer to the HW struct
+ * @module_typeid: module pointer location in words from the NVM beginning
+ * @offset: byte offset from the module beginning
+ * @length: length of the section to be read (in bytes from the offset)
+ * @data: command buffer (size [bytes] = length)
+ * @last_command: tells if this is the last command in a series
+ * @read_shadow_ram: tell if this is a shadow RAM read
+ *
+ * Read the NVM using ACI command (0x0701).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset,
+		       u16 length, void *data, bool last_command,
+		       bool read_shadow_ram)
+{
+	struct ixgbe_aci_cmd_nvm *cmd;
+	struct libie_aq_desc desc;
+
+	if (offset > IXGBE_ACI_NVM_MAX_OFFSET)
+		return -EINVAL;
+
+	cmd = libie_aq_raw(&desc);
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_read);
+
+	if (!read_shadow_ram && module_typeid == IXGBE_ACI_NVM_START_POINT)
+		cmd->cmd_flags |= IXGBE_ACI_NVM_FLASH_ONLY;
+
+	/* If this is the last command in a series, set the proper flag. */
+	if (last_command)
+		cmd->cmd_flags |= IXGBE_ACI_NVM_LAST_CMD;
+	cmd->module_typeid = cpu_to_le16(module_typeid);
+	cmd->offset_low = cpu_to_le16(offset & 0xFFFF);
+	cmd->offset_high = (offset >> 16) & 0xFF;
+	cmd->length = cpu_to_le16(length);
+
+	return ixgbe_aci_send_cmd(hw, &desc, data, length);
+}
+
+/**
+ * ixgbe_aci_erase_nvm - erase NVM sector
+ * @hw: pointer to the HW struct
+ * @module_typeid: module pointer location in words from the NVM beginning
+ *
+ * Erase the NVM sector using the ACI command (0x0702).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_erase_nvm(struct ixgbe_hw *hw, u16 module_typeid)
+{
+	struct ixgbe_aci_cmd_nvm *cmd;
+	struct libie_aq_desc desc;
+	__le16 len;
+	int err;
+
+	/* Read a length value from SR, so module_typeid is equal to 0,
+	 * calculate offset where module size is placed from bytes to words
+	 * set last command and read from SR values to true.
+	 */
+	err = ixgbe_aci_read_nvm(hw, 0, 2 * module_typeid + 2, 2, &len, true,
+				 true);
+	if (err)
+		return err;
+
+	cmd = libie_aq_raw(&desc);
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_erase);
+
+	cmd->module_typeid = cpu_to_le16(module_typeid);
+	cmd->length = len;
+	cmd->offset_low = 0;
+	cmd->offset_high = 0;
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
+ * ixgbe_aci_update_nvm - update NVM
+ * @hw: pointer to the HW struct
+ * @module_typeid: module pointer location in words from the NVM beginning
+ * @offset: byte offset from the module beginning
+ * @length: length of the section to be written (in bytes from the offset)
+ * @data: command buffer (size [bytes] = length)
+ * @last_command: tells if this is the last command in a series
+ * @command_flags: command parameters
+ *
+ * Update the NVM using the ACI command (0x0703).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_update_nvm(struct ixgbe_hw *hw, u16 module_typeid,
+			 u32 offset, u16 length, void *data,
+			 bool last_command, u8 command_flags)
+{
+	struct ixgbe_aci_cmd_nvm *cmd;
+	struct libie_aq_desc desc;
+
+	cmd = libie_aq_raw(&desc);
+
+	/* In offset the highest byte must be zeroed. */
+	if (offset & 0xFF000000)
+		return -EINVAL;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_write);
+
+	cmd->cmd_flags |= command_flags;
+
+	/* If this is the last command in a series, set the proper flag. */
+	if (last_command)
+		cmd->cmd_flags |= IXGBE_ACI_NVM_LAST_CMD;
+	cmd->module_typeid = cpu_to_le16(module_typeid);
+	cmd->offset_low = cpu_to_le16(offset & 0xFFFF);
+	cmd->offset_high = FIELD_GET(IXGBE_ACI_NVM_OFFSET_HI_U_MASK, offset);
+	cmd->length = cpu_to_le16(length);
+
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
+
+	return ixgbe_aci_send_cmd(hw, &desc, data, length);
+}
+
+/**
+ * ixgbe_nvm_write_activate - NVM activate write
+ * @hw: pointer to the HW struct
+ * @cmd_flags: flags for write activate command
+ * @response_flags: response indicators from firmware
+ *
+ * Update the control word with the required banks' validity bits
+ * and dumps the Shadow RAM to flash using ACI command (0x0707).
+ *
+ * cmd_flags controls which banks to activate, the preservation level to use
+ * when activating the NVM bank, and whether an EMP reset is required for
+ * activation.
+ *
+ * Note that the 16bit cmd_flags value is split between two separate 1 byte
+ * flag values in the descriptor.
+ *
+ * On successful return of the firmware command, the response_flags variable
+ * is updated with the flags reported by firmware indicating certain status,
+ * such as whether EMP reset is enabled.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_nvm_write_activate(struct ixgbe_hw *hw, u16 cmd_flags,
+			     u8 *response_flags)
+{
+	struct ixgbe_aci_cmd_nvm *cmd;
+	struct libie_aq_desc desc;
+	s32 err;
+
+	cmd = libie_aq_raw(&desc);
+	ixgbe_fill_dflt_direct_cmd_desc(&desc,
+					ixgbe_aci_opc_nvm_write_activate);
+
+	cmd->cmd_flags = (u8)(cmd_flags & 0xFF);
+	cmd->offset_high = (u8)FIELD_GET(IXGBE_ACI_NVM_OFFSET_HI_A_MASK,
+					 cmd_flags);
+
+	err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+	if (!err && response_flags)
+		*response_flags = cmd->cmd_flags;
+
+	return err;
+}
+
+/**
+ * ixgbe_nvm_validate_checksum - validate checksum
+ * @hw: pointer to the HW struct
+ *
+ * Verify NVM PFA checksum validity using ACI command (0x0706).
+ * If the checksum verification failed, IXGBE_ERR_NVM_CHECKSUM is returned.
+ * The function acquires and then releases the NVM ownership.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_nvm_validate_checksum(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_nvm_checksum *cmd;
+	struct libie_aq_desc desc;
+	int err;
+
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
+	if (err)
+		return err;
+
+	cmd = libie_aq_raw(&desc);
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_checksum);
+	cmd->flags = IXGBE_ACI_NVM_CHECKSUM_VERIFY;
+
+	err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+
+	ixgbe_release_nvm(hw);
+
+	if (!err && cmd->checksum !=
+		cpu_to_le16(IXGBE_ACI_NVM_CHECKSUM_CORRECT)) {
+		struct ixgbe_adapter *adapter = container_of(hw, struct ixgbe_adapter,
+							     hw);
+
+		err = -EIO;
+		netdev_err(adapter->netdev, "Invalid Shadow Ram checksum");
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_discover_flash_size - Discover the available flash size
+ * @hw: pointer to the HW struct
+ *
+ * The device flash could be up to 16MB in size. However, it is possible that
+ * the actual size is smaller. Use bisection to determine the accessible size
+ * of flash memory.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_discover_flash_size(struct ixgbe_hw *hw)
+{
+	u32 min_size = 0, max_size = IXGBE_ACI_NVM_MAX_OFFSET + 1;
+	int err;
+
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
+	if (err)
+		return err;
+
+	while ((max_size - min_size) > 1) {
+		u32 offset = (max_size + min_size) / 2;
+		u32 len = 1;
+		u8 data;
+
+		err = ixgbe_read_flat_nvm(hw, offset, &len, &data, false);
+		if (err == -EIO &&
+		    hw->aci.last_status == LIBIE_AQ_RC_EINVAL) {
+			err = 0;
+			max_size = offset;
+		} else if (!err) {
+			min_size = offset;
+		} else {
+			/* an unexpected error occurred */
+			goto err_read_flat_nvm;
+		}
+	}
+
+	hw->flash.flash_size = max_size;
+
+err_read_flat_nvm:
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_sr_base_address - Read the value of a Shadow RAM pointer word
+ * @hw: pointer to the HW structure
+ * @offset: the word offset of the Shadow RAM word to read
+ * @pointer: pointer value read from Shadow RAM
+ *
+ * Read the given Shadow RAM word, and convert it to a pointer value specified
+ * in bytes. This function assumes the specified offset is a valid pointer
+ * word.
+ *
+ * Each pointer word specifies whether it is stored in word size or 4KB
+ * sector size by using the highest bit. The reported pointer value will be in
+ * bytes, intended for flat NVM reads.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_sr_base_address(struct ixgbe_hw *hw, u16 offset,
+				      u32 *pointer)
+{
+	u16 value;
+	int err;
+
+	err = ixgbe_read_ee_aci_e610(hw, offset, &value);
+	if (err)
+		return err;
+
+	/* Determine if the pointer is in 4KB or word units */
+	if (value & IXGBE_SR_NVM_PTR_4KB_UNITS)
+		*pointer = (value & ~IXGBE_SR_NVM_PTR_4KB_UNITS) * SZ_4K;
+	else
+		*pointer = value * sizeof(u16);
+
+	return 0;
+}
+
+/**
+ * ixgbe_read_sr_area_size - Read an area size from a Shadow RAM word
+ * @hw: pointer to the HW structure
+ * @offset: the word offset of the Shadow RAM to read
+ * @size: size value read from the Shadow RAM
+ *
+ * Read the given Shadow RAM word, and convert it to an area size value
+ * specified in bytes. This function assumes the specified offset is a valid
+ * area size word.
+ *
+ * Each area size word is specified in 4KB sector units. This function reports
+ * the size in bytes, intended for flat NVM reads.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_sr_area_size(struct ixgbe_hw *hw, u16 offset, u32 *size)
+{
+	u16 value;
+	int err;
+
+	err = ixgbe_read_ee_aci_e610(hw, offset, &value);
+	if (err)
+		return err;
+
+	/* Area sizes are always specified in 4KB units */
+	*size = value * SZ_4K;
+
+	return 0;
+}
+
+/**
+ * ixgbe_determine_active_flash_banks - Discover active bank for each module
+ * @hw: pointer to the HW struct
+ *
+ * Read the Shadow RAM control word and determine which banks are active for
+ * the NVM, OROM, and Netlist modules. Also read and calculate the associated
+ * pointer and size. These values are then cached into the ixgbe_flash_info
+ * structure for later use in order to calculate the correct offset to read
+ * from the active module.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_determine_active_flash_banks(struct ixgbe_hw *hw)
+{
+	struct ixgbe_bank_info *banks = &hw->flash.banks;
+	u16 ctrl_word;
+	int err;
+
+	err = ixgbe_read_ee_aci_e610(hw, IXGBE_E610_SR_NVM_CTRL_WORD,
+				     &ctrl_word);
+	if (err)
+		return err;
+
+	if (FIELD_GET(IXGBE_SR_CTRL_WORD_1_M, ctrl_word) !=
+	    IXGBE_SR_CTRL_WORD_VALID)
+		return -ENODATA;
+
+	if (!(ctrl_word & IXGBE_SR_CTRL_WORD_NVM_BANK))
+		banks->nvm_bank = IXGBE_1ST_FLASH_BANK;
+	else
+		banks->nvm_bank = IXGBE_2ND_FLASH_BANK;
+
+	if (!(ctrl_word & IXGBE_SR_CTRL_WORD_OROM_BANK))
+		banks->orom_bank = IXGBE_1ST_FLASH_BANK;
+	else
+		banks->orom_bank = IXGBE_2ND_FLASH_BANK;
+
+	if (!(ctrl_word & IXGBE_SR_CTRL_WORD_NETLIST_BANK))
+		banks->netlist_bank = IXGBE_1ST_FLASH_BANK;
+	else
+		banks->netlist_bank = IXGBE_2ND_FLASH_BANK;
+
+	err = ixgbe_read_sr_base_address(hw, IXGBE_E610_SR_1ST_NVM_BANK_PTR,
+					 &banks->nvm_ptr);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_area_size(hw, IXGBE_E610_SR_NVM_BANK_SIZE,
+				      &banks->nvm_size);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_base_address(hw, IXGBE_E610_SR_1ST_OROM_BANK_PTR,
+					 &banks->orom_ptr);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_area_size(hw, IXGBE_E610_SR_OROM_BANK_SIZE,
+				      &banks->orom_size);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_base_address(hw, IXGBE_E610_SR_NETLIST_BANK_PTR,
+					 &banks->netlist_ptr);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_area_size(hw, IXGBE_E610_SR_NETLIST_BANK_SIZE,
+				      &banks->netlist_size);
+
+	return err;
+}
+
+/**
+ * ixgbe_get_flash_bank_offset - Get offset into requested flash bank
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from the active or inactive flash bank
+ * @module: the module to read from
+ *
+ * Based on the module, lookup the module offset from the beginning of the
+ * flash.
+ *
+ * Return: the flash offset. Note that a value of zero is invalid and must be
+ * treated as an error.
+ */
+static int ixgbe_get_flash_bank_offset(struct ixgbe_hw *hw,
+				       enum ixgbe_bank_select bank,
+				       u16 module)
+{
+	struct ixgbe_bank_info *banks = &hw->flash.banks;
+	enum ixgbe_flash_bank active_bank;
+	bool second_bank_active;
+	u32 offset, size;
+
+	switch (module) {
+	case IXGBE_E610_SR_1ST_NVM_BANK_PTR:
+		offset = banks->nvm_ptr;
+		size = banks->nvm_size;
+		active_bank = banks->nvm_bank;
+		break;
+	case IXGBE_E610_SR_1ST_OROM_BANK_PTR:
+		offset = banks->orom_ptr;
+		size = banks->orom_size;
+		active_bank = banks->orom_bank;
+		break;
+	case IXGBE_E610_SR_NETLIST_BANK_PTR:
+		offset = banks->netlist_ptr;
+		size = banks->netlist_size;
+		active_bank = banks->netlist_bank;
+		break;
+	default:
+		return 0;
+	}
+
+	switch (active_bank) {
+	case IXGBE_1ST_FLASH_BANK:
+		second_bank_active = false;
+		break;
+	case IXGBE_2ND_FLASH_BANK:
+		second_bank_active = true;
+		break;
+	default:
+		return 0;
+	}
+
+	/* The second flash bank is stored immediately following the first
+	 * bank. Based on whether the 1st or 2nd bank is active, and whether
+	 * we want the active or inactive bank, calculate the desired offset.
+	 */
+	switch (bank) {
+	case IXGBE_ACTIVE_FLASH_BANK:
+		return offset + (second_bank_active ? size : 0);
+	case IXGBE_INACTIVE_FLASH_BANK:
+		return offset + (second_bank_active ? 0 : size);
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_read_flash_module - Read a word from one of the main NVM modules
+ * @hw: pointer to the HW structure
+ * @bank: which bank of the module to read
+ * @module: the module to read
+ * @offset: the offset into the module in bytes
+ * @data: storage for the word read from the flash
+ * @length: bytes of data to read
+ *
+ * Read data from the specified flash module. The bank parameter indicates
+ * whether or not to read from the active bank or the inactive bank of that
+ * module.
+ *
+ * The word will be read using flat NVM access, and relies on the
+ * hw->flash.banks data being setup by ixgbe_determine_active_flash_banks()
+ * during initialization.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_flash_module(struct ixgbe_hw *hw,
+				   enum ixgbe_bank_select bank,
+				   u16 module, u32 offset, u8 *data, u32 length)
+{
+	u32 start;
+	int err;
+
+	start = ixgbe_get_flash_bank_offset(hw, bank, module);
+	if (!start)
+		return -EINVAL;
+
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
+	if (err)
+		return err;
+
+	err = ixgbe_read_flat_nvm(hw, start + offset, &length, data, false);
+
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_nvm_module - Read from the active main NVM module
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from active or inactive NVM module
+ * @offset: offset into the NVM module to read, in words
+ * @data: storage for returned word value
+ *
+ * Read the specified word from the active NVM module. This includes the CSS
+ * header at the start of the NVM module.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_nvm_module(struct ixgbe_hw *hw,
+				 enum ixgbe_bank_select bank,
+				 u32 offset, u16 *data)
+{
+	__le16 data_local;
+	int err;
+
+	err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_1ST_NVM_BANK_PTR,
+				      offset * sizeof(data_local),
+				      (u8 *)&data_local,
+				      sizeof(data_local));
+	if (!err)
+		*data = le16_to_cpu(data_local);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_netlist_module - Read data from the netlist module area
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from the active or inactive module
+ * @offset: offset into the netlist to read from
+ * @data: storage for returned word value
+ *
+ * Read a word from the specified netlist bank.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_netlist_module(struct ixgbe_hw *hw,
+				     enum ixgbe_bank_select bank,
+				     u32 offset, u16 *data)
+{
+	__le16 data_local;
+	int err;
+
+	err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_NETLIST_BANK_PTR,
+				      offset * sizeof(data_local),
+				      (u8 *)&data_local, sizeof(data_local));
+	if (!err)
+		*data = le16_to_cpu(data_local);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_orom_module - Read from the active Option ROM module
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from active or inactive OROM module
+ * @offset: offset into the OROM module to read, in words
+ * @data: storage for returned word value
+ *
+ * Read the specified word from the active Option ROM module of the flash.
+ * Note that unlike the NVM module, the CSS data is stored at the end of the
+ * module instead of at the beginning.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_orom_module(struct ixgbe_hw *hw,
+				  enum ixgbe_bank_select bank,
+				  u32 offset, u16 *data)
+{
+	__le16 data_local;
+	int err;
+
+	err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_1ST_OROM_BANK_PTR,
+				      offset * sizeof(data_local),
+				      (u8 *)&data_local, sizeof(data_local));
+	if (!err)
+		*data = le16_to_cpu(data_local);
+
+	return err;
+}
+
+/**
+ * ixgbe_get_nvm_css_hdr_len - Read the CSS header length
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @hdr_len: storage for header length in words
+ *
+ * Read the CSS header length from the NVM CSS header and add the
+ * Authentication header size, and then convert to words.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_nvm_css_hdr_len(struct ixgbe_hw *hw,
+				     enum ixgbe_bank_select bank,
+				     u32 *hdr_len)
+{
+	u16 hdr_len_l, hdr_len_h;
+	u32 hdr_len_dword;
+	int err;
+
+	err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_HDR_LEN_L,
+				    &hdr_len_l);
+	if (err)
+		return err;
+
+	err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_HDR_LEN_H,
+				    &hdr_len_h);
+	if (err)
+		return err;
+
+	/* CSS header length is in DWORD, so convert to words and add
+	 * authentication header size.
+	 */
+	hdr_len_dword = (hdr_len_h << 16) | hdr_len_l;
+	*hdr_len = hdr_len_dword * 2 + IXGBE_NVM_AUTH_HEADER_LEN;
+
+	return 0;
+}
+
+/**
+ * ixgbe_read_nvm_sr_copy - Read a word from the Shadow RAM copy
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from the active or inactive NVM module
+ * @offset: offset into the Shadow RAM copy to read, in words
+ * @data: storage for returned word value
+ *
+ * Read the specified word from the copy of the Shadow RAM found in the
+ * specified NVM module.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_nvm_sr_copy(struct ixgbe_hw *hw,
+				  enum ixgbe_bank_select bank,
+				  u32 offset, u16 *data)
+{
+	u32 hdr_len;
+	int err;
+
+	err = ixgbe_get_nvm_css_hdr_len(hw, bank, &hdr_len);
+	if (err)
+		return err;
+
+	hdr_len = round_up(hdr_len, IXGBE_HDR_LEN_ROUNDUP);
+
+	return ixgbe_read_nvm_module(hw, bank, hdr_len + offset, data);
+}
+
+/**
+ * ixgbe_get_nvm_srev - Read the security revision from the NVM CSS header
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @srev: storage for security revision
+ *
+ * Read the security revision out of the CSS header of the active NVM module
+ * bank.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_nvm_srev(struct ixgbe_hw *hw,
+			      enum ixgbe_bank_select bank, u32 *srev)
+{
+	u16 srev_l, srev_h;
+	int err;
+
+	err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_SREV_L, &srev_l);
+	if (err)
+		return err;
+
+	err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_SREV_H, &srev_h);
+	if (err)
+		return err;
+
+	*srev = (srev_h << 16) | srev_l;
+
+	return 0;
+}
+
+/**
+ * ixgbe_get_orom_civd_data - Get the combo version information from Option ROM
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash module
+ * @civd: storage for the Option ROM CIVD data.
+ *
+ * Searches through the Option ROM flash contents to locate the CIVD data for
+ * the image.
+ *
+ * Return: -ENOMEM when cannot allocate memory, -EDOM for checksum violation,
+ *	   -ENODATA when cannot find proper data, -EIO for faulty read or
+ *	   0 on success.
+ *
+ *	   On success @civd stores collected data.
+ */
+static int
+ixgbe_get_orom_civd_data(struct ixgbe_hw *hw, enum ixgbe_bank_select bank,
+			 struct ixgbe_orom_civd_info *civd)
+{
+	u32 orom_size = hw->flash.banks.orom_size;
+	u8 *orom_data;
+	u32 offset;
+	int err;
+
+	orom_data = kzalloc(orom_size, GFP_KERNEL);
+	if (!orom_data)
+		return -ENOMEM;
+
+	err = ixgbe_read_flash_module(hw, bank,
+				      IXGBE_E610_SR_1ST_OROM_BANK_PTR, 0,
+				      orom_data, orom_size);
+	if (err) {
+		err = -EIO;
+		goto cleanup;
+	}
+
+	/* The CIVD section is located in the Option ROM aligned to 512 bytes.
+	 * The first 4 bytes must contain the ASCII characters "$CIV".
+	 * A simple modulo 256 sum of all of the bytes of the structure must
+	 * equal 0.
+	 */
+	for (offset = 0; offset + SZ_512 <= orom_size; offset += SZ_512) {
+		struct ixgbe_orom_civd_info *tmp;
+		u8 sum = 0;
+		u32 i;
+
+		BUILD_BUG_ON(sizeof(*tmp) > SZ_512);
+
+		tmp = (struct ixgbe_orom_civd_info *)&orom_data[offset];
+
+		/* Skip forward until we find a matching signature */
+		if (memcmp(IXGBE_OROM_CIV_SIGNATURE, tmp->signature,
+			   sizeof(tmp->signature)))
+			continue;
+
+		/* Verify that the simple checksum is zero */
+		for (i = 0; i < sizeof(*tmp); i++)
+			sum += ((u8 *)tmp)[i];
+
+		if (sum) {
+			err = -EDOM;
+			goto cleanup;
+		}
+
+		*civd = *tmp;
+		err = 0;
+
+		goto cleanup;
+	}
+
+	err = -ENODATA;
+cleanup:
+	kfree(orom_data);
+	return err;
+}
+
+/**
+ * ixgbe_get_orom_srev - Read the security revision from the OROM CSS header
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from active or inactive flash module
+ * @srev: storage for security revision
+ *
+ * Read the security revision out of the CSS header of the active OROM module
+ * bank.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_orom_srev(struct ixgbe_hw *hw,
+			       enum ixgbe_bank_select bank,
+			       u32 *srev)
+{
+	u32 orom_size_word = hw->flash.banks.orom_size / 2;
+	u32 css_start, hdr_len;
+	u16 srev_l, srev_h;
+	int err;
+
+	err = ixgbe_get_nvm_css_hdr_len(hw, bank, &hdr_len);
+	if (err)
+		return err;
+
+	if (orom_size_word < hdr_len)
+		return -EINVAL;
+
+	/* Calculate how far into the Option ROM the CSS header starts. Note
+	 * that ixgbe_read_orom_module takes a word offset.
+	 */
+	css_start = orom_size_word - hdr_len;
+	err = ixgbe_read_orom_module(hw, bank,
+				     css_start + IXGBE_NVM_CSS_SREV_L,
+				     &srev_l);
+	if (err)
+		return err;
+
+	err = ixgbe_read_orom_module(hw, bank,
+				     css_start + IXGBE_NVM_CSS_SREV_H,
+				     &srev_h);
+	if (err)
+		return err;
+
+	*srev = srev_h << 16 | srev_l;
+
+	return 0;
+}
+
+/**
+ * ixgbe_get_orom_ver_info - Read Option ROM version information
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash module
+ * @orom: pointer to Option ROM info structure
+ *
+ * Read Option ROM version and security revision from the Option ROM flash
+ * section.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_orom_ver_info(struct ixgbe_hw *hw,
+				   enum ixgbe_bank_select bank,
+				   struct ixgbe_orom_info *orom)
+{
+	struct ixgbe_orom_civd_info civd;
+	u32 combo_ver;
+	int err;
+
+	err = ixgbe_get_orom_civd_data(hw, bank, &civd);
+	if (err)
+		return err;
+
+	combo_ver = get_unaligned_le32(&civd.combo_ver);
+
+	orom->major = (u8)FIELD_GET(IXGBE_OROM_VER_MASK, combo_ver);
+	orom->patch = (u8)FIELD_GET(IXGBE_OROM_VER_PATCH_MASK, combo_ver);
+	orom->build = (u16)FIELD_GET(IXGBE_OROM_VER_BUILD_MASK, combo_ver);
+
+	return ixgbe_get_orom_srev(hw, bank, &orom->srev);
+}
+
+/**
+ * ixgbe_get_inactive_orom_ver - Read Option ROM version from the inactive bank
+ * @hw: pointer to the HW structure
+ * @orom: storage for Option ROM version information
+ *
+ * Read the Option ROM version and security revision data for the inactive
+ * section of flash. Used to access version data for a pending update that has
+ * not yet been activated.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_inactive_orom_ver(struct ixgbe_hw *hw,
+				struct ixgbe_orom_info *orom)
+{
+	return ixgbe_get_orom_ver_info(hw, IXGBE_INACTIVE_FLASH_BANK, orom);
+}
+
+/**
+ * ixgbe_get_nvm_ver_info - Read NVM version information
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @nvm: pointer to NVM info structure
+ *
+ * Read the NVM EETRACK ID and map version of the main NVM image bank, filling
+ * in the nvm info structure.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_nvm_ver_info(struct ixgbe_hw *hw,
+				  enum ixgbe_bank_select bank,
+				  struct ixgbe_nvm_info *nvm)
+{
+	u16 eetrack_lo, eetrack_hi, ver;
+	int err;
+
+	err = ixgbe_read_nvm_sr_copy(hw, bank,
+				     IXGBE_E610_SR_NVM_DEV_STARTER_VER, &ver);
+	if (err)
+		return err;
+
+	nvm->major = FIELD_GET(IXGBE_E610_NVM_VER_HI_MASK, ver);
+	nvm->minor = FIELD_GET(IXGBE_E610_NVM_VER_LO_MASK, ver);
+
+	err = ixgbe_read_nvm_sr_copy(hw, bank, IXGBE_E610_SR_NVM_EETRACK_LO,
+				     &eetrack_lo);
+	if (err)
+		return err;
+
+	err = ixgbe_read_nvm_sr_copy(hw, bank, IXGBE_E610_SR_NVM_EETRACK_HI,
+				     &eetrack_hi);
+	if (err)
+		return err;
+
+	nvm->eetrack = (eetrack_hi << 16) | eetrack_lo;
+
+	ixgbe_get_nvm_srev(hw, bank, &nvm->srev);
+
+	return 0;
+}
+
+/**
+ * ixgbe_get_inactive_nvm_ver - Read Option ROM version from the inactive bank
+ * @hw: pointer to the HW structure
+ * @nvm: storage for Option ROM version information
+ *
+ * Read the NVM EETRACK ID, Map version, and security revision of the
+ * inactive NVM bank. Used to access version data for a pending update that
+ * has not yet been activated.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_inactive_nvm_ver(struct ixgbe_hw *hw, struct ixgbe_nvm_info *nvm)
+{
+	return ixgbe_get_nvm_ver_info(hw, IXGBE_INACTIVE_FLASH_BANK, nvm);
+}
+
+/**
+ * ixgbe_get_active_nvm_ver - Read Option ROM version from the active bank
+ * @hw: pointer to the HW structure
+ * @nvm: storage for Option ROM version information
+ *
+ * Reads the NVM EETRACK ID, Map version, and security revision of the
+ * active NVM bank.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_active_nvm_ver(struct ixgbe_hw *hw,
+				    struct ixgbe_nvm_info *nvm)
+{
+	return ixgbe_get_nvm_ver_info(hw, IXGBE_ACTIVE_FLASH_BANK, nvm);
+}
+
+/**
+ * ixgbe_get_netlist_info - Read the netlist version information
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @netlist: pointer to netlist version info structure
+ *
+ * Get the netlist version information from the requested bank. Reads the Link
+ * Topology section to find the Netlist ID block and extract the relevant
+ * information into the netlist version structure.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_netlist_info(struct ixgbe_hw *hw,
+				  enum ixgbe_bank_select bank,
+				  struct ixgbe_netlist_info *netlist)
+{
+	u16 module_id, length, node_count, i;
+	u16 *id_blk;
+	int err;
+
+	err = ixgbe_read_netlist_module(hw, bank, IXGBE_NETLIST_TYPE_OFFSET,
+					&module_id);
+	if (err)
+		return err;
+
+	if (module_id != IXGBE_NETLIST_LINK_TOPO_MOD_ID)
+		return -EIO;
+
+	err = ixgbe_read_netlist_module(hw, bank, IXGBE_LINK_TOPO_MODULE_LEN,
+					&length);
+	if (err)
+		return err;
+
+	/* Sanity check that we have at least enough words to store the
+	 * netlist ID block.
+	 */
+	if (length < IXGBE_NETLIST_ID_BLK_SIZE)
+		return -EIO;
+
+	err = ixgbe_read_netlist_module(hw, bank, IXGBE_LINK_TOPO_NODE_COUNT,
+					&node_count);
+	if (err)
+		return err;
+
+	node_count &= IXGBE_LINK_TOPO_NODE_COUNT_M;
+
+	id_blk = kcalloc(IXGBE_NETLIST_ID_BLK_SIZE, sizeof(*id_blk), GFP_KERNEL);
+	if (!id_blk)
+		return -ENOMEM;
+
+	/* Read out the entire Netlist ID Block at once. */
+	err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_NETLIST_BANK_PTR,
+				      IXGBE_NETLIST_ID_BLK_OFFSET(node_count) *
+				      sizeof(*id_blk), (u8 *)id_blk,
+				      IXGBE_NETLIST_ID_BLK_SIZE *
+				      sizeof(*id_blk));
+	if (err)
+		goto free_id_blk;
+
+	for (i = 0; i < IXGBE_NETLIST_ID_BLK_SIZE; i++)
+		id_blk[i] = le16_to_cpu(((__le16 *)id_blk)[i]);
+
+	netlist->major = id_blk[IXGBE_NETLIST_ID_BLK_MAJOR_VER_HIGH] << 16 |
+			 id_blk[IXGBE_NETLIST_ID_BLK_MAJOR_VER_LOW];
+	netlist->minor = id_blk[IXGBE_NETLIST_ID_BLK_MINOR_VER_HIGH] << 16 |
+			 id_blk[IXGBE_NETLIST_ID_BLK_MINOR_VER_LOW];
+	netlist->type = id_blk[IXGBE_NETLIST_ID_BLK_TYPE_HIGH] << 16 |
+			id_blk[IXGBE_NETLIST_ID_BLK_TYPE_LOW];
+	netlist->rev = id_blk[IXGBE_NETLIST_ID_BLK_REV_HIGH] << 16 |
+		       id_blk[IXGBE_NETLIST_ID_BLK_REV_LOW];
+	netlist->cust_ver = id_blk[IXGBE_NETLIST_ID_BLK_CUST_VER];
+	/* Read the left most 4 bytes of SHA */
+	netlist->hash = id_blk[IXGBE_NETLIST_ID_BLK_SHA_HASH_WORD(15)] << 16 |
+			id_blk[IXGBE_NETLIST_ID_BLK_SHA_HASH_WORD(14)];
+
+free_id_blk:
+	kfree(id_blk);
+	return err;
+}
+
+/**
+ * ixgbe_get_inactive_netlist_ver - Read netlist version from the inactive bank
+ * @hw: pointer to the HW struct
+ * @netlist: pointer to netlist version info structure
+ *
+ * Read the netlist version data from the inactive netlist bank. Used to
+ * extract version data of a pending flash update in order to display the
+ * version data.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_inactive_netlist_ver(struct ixgbe_hw *hw,
+				   struct ixgbe_netlist_info *netlist)
+{
+	return ixgbe_get_netlist_info(hw, IXGBE_INACTIVE_FLASH_BANK, netlist);
+}
+
+/**
+ * ixgbe_get_flash_data - get flash data
+ * @hw: pointer to the HW struct
+ *
+ * Read and populate flash data such as Shadow RAM size,
+ * max_timeout and blank_nvm_mode
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_flash_data(struct ixgbe_hw *hw)
+{
+	struct ixgbe_flash_info *flash = &hw->flash;
+	u32 fla, gens_stat;
+	u8 sr_size;
+	int err;
+
+	/* The SR size is stored regardless of the NVM programming mode
+	 * as the blank mode may be used in the factory line.
+	 */
+	gens_stat = IXGBE_READ_REG(hw, GLNVM_GENS);
+	sr_size = FIELD_GET(GLNVM_GENS_SR_SIZE_M, gens_stat);
+
+	/* Switching to words (sr_size contains power of 2) */
+	flash->sr_words = BIT(sr_size) * (SZ_1K / sizeof(u16));
+
+	/* Check if we are in the normal or blank NVM programming mode */
+	fla = IXGBE_READ_REG(hw, IXGBE_GLNVM_FLA);
+	if (fla & IXGBE_GLNVM_FLA_LOCKED_M) {
+		flash->blank_nvm_mode = false;
+	} else {
+		flash->blank_nvm_mode = true;
+		return -EIO;
+	}
+
+	err = ixgbe_discover_flash_size(hw);
+	if (err)
+		return err;
+
+	err = ixgbe_determine_active_flash_banks(hw);
+	if (err)
+		return err;
+
+	err = ixgbe_get_nvm_ver_info(hw, IXGBE_ACTIVE_FLASH_BANK,
+				     &flash->nvm);
+	if (err)
+		return err;
+
+	err = ixgbe_get_orom_ver_info(hw, IXGBE_ACTIVE_FLASH_BANK,
+				      &flash->orom);
+	if (err)
+		return err;
+
+	err = ixgbe_get_netlist_info(hw, IXGBE_ACTIVE_FLASH_BANK,
+				     &flash->netlist);
+	return err;
+}
+
+/**
+ * ixgbe_aci_nvm_update_empr - update NVM using EMPR
+ * @hw: pointer to the HW struct
+ *
+ * Force EMP reset using ACI command (0x0709). This command allows SW to
+ * request an EMPR to activate new FW.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_nvm_update_empr(struct ixgbe_hw *hw)
+{
+	struct libie_aq_desc desc;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_update_empr);
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/* ixgbe_nvm_set_pkg_data - NVM set package data
+ * @hw: pointer to the HW struct
+ * @del_pkg_data_flag: If is set then the current pkg_data store by FW
+ *		       is deleted.
+ *		       If bit is set to 1, then buffer should be size 0.
+ * @data: pointer to buffer
+ * @length: length of the buffer
+ *
+ * Set package data using ACI command (0x070A).
+ * This command is equivalent to the reception of
+ * a PLDM FW Update GetPackageData cmd. This command should be sent
+ * as part of the NVM update as the first cmd in the flow.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_nvm_set_pkg_data(struct ixgbe_hw *hw, bool del_pkg_data_flag,
+			   u8 *data, u16 length)
+{
+	struct ixgbe_aci_cmd_nvm_pkg_data *cmd;
+	struct libie_aq_desc desc;
+
+	if (length != 0 && !data)
+		return -EINVAL;
+
+	cmd = libie_aq_raw(&desc);
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_pkg_data);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
+
+	if (del_pkg_data_flag)
+		cmd->cmd_flags |= IXGBE_ACI_NVM_PKG_DELETE;
+
+	return ixgbe_aci_send_cmd(hw, &desc, data, length);
+}
+
+/* ixgbe_nvm_pass_component_tbl - NVM pass component table
+ * @hw: pointer to the HW struct
+ * @data: pointer to buffer
+ * @length: length of the buffer
+ * @transfer_flag: parameter for determining stage of the update
+ * @comp_response: a pointer to the response from the 0x070B ACI.
+ * @comp_response_code: a pointer to the response code from the 0x070B ACI.
+ *
+ * Pass component table using ACI command (0x070B). This command is equivalent
+ * to the reception of a PLDM FW Update PassComponentTable cmd.
+ * This command should be sent once per component. It can be only sent after
+ * Set Package Data cmd and before actual update. FW will assume these
+ * commands are going to be sent until the TransferFlag is set to End or
+ * StartAndEnd.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_nvm_pass_component_tbl(struct ixgbe_hw *hw, u8 *data, u16 length,
+				 u8 transfer_flag, u8 *comp_response,
+				 u8 *comp_response_code)
+{
+	struct ixgbe_aci_cmd_nvm_pass_comp_tbl *cmd;
+	struct libie_aq_desc desc;
+	int err;
+
+	if (!data || !comp_response || !comp_response_code)
+		return -EINVAL;
+
+	cmd = libie_aq_raw(&desc);
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc,
+					ixgbe_aci_opc_nvm_pass_component_tbl);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
+
+	cmd->transfer_flag = transfer_flag;
+	err = ixgbe_aci_send_cmd(hw, &desc, data, length);
+	if (!err) {
+		*comp_response = cmd->component_response;
+		*comp_response_code = cmd->component_response_code;
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_read_sr_word_aci - Reads Shadow RAM via ACI
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
+ * @data: word read from the Shadow RAM
+ *
+ * Reads one 16 bit word from the Shadow RAM using ixgbe_read_flat_nvm.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_read_sr_word_aci(struct ixgbe_hw  *hw, u16 offset, u16 *data)
+{
+	u32 bytes = sizeof(u16);
+	u16 data_local;
+	int err;
+
+	err = ixgbe_read_flat_nvm(hw, offset * sizeof(u16), &bytes,
+				  (u8 *)&data_local, true);
+	if (err)
+		return err;
+
+	*data = data_local;
+	return 0;
+}
+
+/**
+ * ixgbe_read_flat_nvm - Read portion of NVM by flat offset
+ * @hw: pointer to the HW struct
+ * @offset: offset from beginning of NVM
+ * @length: (in) number of bytes to read; (out) number of bytes actually read
+ * @data: buffer to return data in (sized to fit the specified length)
+ * @read_shadow_ram: if true, read from shadow RAM instead of NVM
+ *
+ * Reads a portion of the NVM, as a flat memory space. This function correctly
+ * breaks read requests across Shadow RAM sectors, prevents Shadow RAM size
+ * from being exceeded in case of Shadow RAM read requests and ensures that no
+ * single read request exceeds the maximum 4KB read for a single admin command.
+ *
+ * Returns an error code on failure. Note that the data pointer may be
+ * partially updated if some reads succeed before a failure.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_read_flat_nvm(struct ixgbe_hw  *hw, u32 offset, u32 *length,
+			u8 *data, bool read_shadow_ram)
+{
+	u32 inlen = *length;
+	u32 bytes_read = 0;
+	bool last_cmd;
+	int err;
+
+	/* Verify the length of the read if this is for the Shadow RAM */
+	if (read_shadow_ram && ((offset + inlen) >
+				(hw->eeprom.word_size * 2u)))
+		return -EINVAL;
+
+	do {
+		u32 read_size, sector_offset;
+
+		/* ixgbe_aci_read_nvm cannot read more than 4KB at a time.
+		 * Additionally, a read from the Shadow RAM may not cross over
+		 * a sector boundary. Conveniently, the sector size is also 4KB.
+		 */
+		sector_offset = offset % IXGBE_ACI_MAX_BUFFER_SIZE;
+		read_size = min_t(u32,
+				  IXGBE_ACI_MAX_BUFFER_SIZE - sector_offset,
+				  inlen - bytes_read);
+
+		last_cmd = !(bytes_read + read_size < inlen);
+
+		/* ixgbe_aci_read_nvm takes the length as a u16. Our read_size
+		 * is calculated using a u32, but the IXGBE_ACI_MAX_BUFFER_SIZE
+		 * maximum size guarantees that it will fit within the 2 bytes.
+		 */
+		err = ixgbe_aci_read_nvm(hw, IXGBE_ACI_NVM_START_POINT,
+					 offset, (u16)read_size,
+					 data + bytes_read, last_cmd,
+					 read_shadow_ram);
+		if (err)
+			break;
+
+		bytes_read += read_size;
+		offset += read_size;
+	} while (!last_cmd);
+
+	*length = bytes_read;
+	return err;
+}
+
+/**
+ * ixgbe_read_sr_buf_aci - Read Shadow RAM buffer via ACI
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM words to read (0x000000 - 0x001FFF)
+ * @words: (in) number of words to read; (out) number of words actually read
+ * @data: words read from the Shadow RAM
+ *
+ * Read 16 bit words (data buf) from the Shadow RAM. Acquire/release the NVM
+ * ownership.
+ *
+ * Return: the operation exit code.
+ */
+int ixgbe_read_sr_buf_aci(struct ixgbe_hw *hw, u16 offset, u16 *words,
+			  u16 *data)
+{
+	u32 bytes = *words * 2;
+	int err;
+
+	err = ixgbe_read_flat_nvm(hw, offset * 2, &bytes, (u8 *)data, true);
+	if (err)
+		return err;
+
+	*words = bytes / 2;
+
+	for (int i = 0; i < *words; i++)
+		data[i] = le16_to_cpu(((__le16 *)data)[i]);
+
+	return 0;
+}
+
+/**
+ * ixgbe_read_ee_aci_e610 - Read EEPROM word using the admin command.
+ * @hw: pointer to hardware structure
+ * @offset: offset of  word in the EEPROM to read
+ * @data: word read from the EEPROM
+ *
+ * Reads a 16 bit word from the EEPROM using the ACI.
+ * If the EEPROM params are not initialized, the function
+ * initialize them before proceeding with reading.
+ * The function acquires and then releases the NVM ownership.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_read_ee_aci_e610(struct ixgbe_hw *hw, u16 offset, u16 *data)
+{
+	int err;
+
+	if (hw->eeprom.type == ixgbe_eeprom_uninitialized) {
+		err = hw->eeprom.ops.init_params(hw);
+		if (err)
+			return err;
+	}
+
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_word_aci(hw, offset, data);
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_ee_aci_buffer_e610 - Read EEPROM words via ACI
+ * @hw: pointer to hardware structure
+ * @offset: offset of words in the EEPROM to read
+ * @words: number of words to read
+ * @data: words to read from the EEPROM
+ *
+ * Read 16 bit words from the EEPROM via the ACI. Initialize the EEPROM params
+ * prior to the read. Acquire/release the NVM ownership.
+ *
+ * Return: the operation exit code.
+ */
+int ixgbe_read_ee_aci_buffer_e610(struct ixgbe_hw *hw, u16 offset,
+				  u16 words, u16 *data)
+{
+	int err;
+
+	if (hw->eeprom.type == ixgbe_eeprom_uninitialized) {
+		err = hw->eeprom.ops.init_params(hw);
+		if (err)
+			return err;
+	}
+
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_buf_aci(hw, offset, &words, data);
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ixgbe_validate_eeprom_checksum_e610 - Validate EEPROM checksum
+ * @hw: pointer to hardware structure
+ * @checksum_val: calculated checksum
+ *
+ * Performs checksum calculation and validates the EEPROM checksum. If the
+ * caller does not need checksum_val, the value can be NULL.
+ * If the EEPROM params are not initialized, the function
+ * initialize them before proceeding.
+ * The function acquires and then releases the NVM ownership.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_validate_eeprom_checksum_e610(struct ixgbe_hw *hw, u16 *checksum_val)
+{
+	int err;
+
+	if (hw->eeprom.type == ixgbe_eeprom_uninitialized) {
+		err = hw->eeprom.ops.init_params(hw);
+		if (err)
+			return err;
+	}
+
+	err = ixgbe_nvm_validate_checksum(hw);
+	if (err)
+		return err;
+
+	if (checksum_val) {
+		u16 tmp_checksum;
+
+		err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
+		if (err)
+			return err;
+
+		err = ixgbe_read_sr_word_aci(hw, IXGBE_E610_SR_SW_CHECKSUM_WORD,
+					     &tmp_checksum);
+		ixgbe_release_nvm(hw);
+
+		if (!err)
+			*checksum_val = tmp_checksum;
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_reset_hw_e610 - Perform hardware reset
+ * @hw: pointer to hardware structure
+ *
+ * Resets the hardware by resetting the transmit and receive units, masks
+ * and clears all interrupts, and performs a reset.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_reset_hw_e610(struct ixgbe_hw *hw)
+{
+	u32 swfw_mask = hw->phy.phy_semaphore_mask;
+	u32 ctrl, i;
+	int err;
+
+	/* Call adapter stop to disable tx/rx and clear interrupts */
+	err = hw->mac.ops.stop_adapter(hw);
+	if (err)
+		goto reset_hw_out;
+
+	/* Flush pending Tx transactions. */
+	ixgbe_clear_tx_pending(hw);
+
+	hw->phy.ops.init(hw);
+mac_reset_top:
+	err = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask);
+	if (err)
+		return -EBUSY;
+	ctrl = IXGBE_CTRL_RST;
+	ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL);
+	IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl);
+	IXGBE_WRITE_FLUSH(hw);
+	hw->mac.ops.release_swfw_sync(hw, swfw_mask);
+
+	/* Poll for reset bit to self-clear indicating reset is complete */
+	for (i = 0; i < 10; i++) {
+		udelay(1);
+		ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL);
+		if (!(ctrl & IXGBE_CTRL_RST_MASK))
+			break;
+	}
+
+	if (ctrl & IXGBE_CTRL_RST_MASK) {
+		struct ixgbe_adapter *adapter = container_of(hw, struct ixgbe_adapter,
+							     hw);
+
+		err = -EIO;
+		netdev_err(adapter->netdev, "Reset polling failed to complete.");
+	}
+
+	/* Double resets are required for recovery from certain error
+	 * conditions. Between resets, it is necessary to stall to allow time
+	 * for any pending HW events to complete.
+	 */
+	msleep(100);
+	if (hw->mac.flags & IXGBE_FLAGS_DOUBLE_RESET_REQUIRED) {
+		hw->mac.flags &= ~IXGBE_FLAGS_DOUBLE_RESET_REQUIRED;
+		goto mac_reset_top;
+	}
+
+	/* Set the Rx packet buffer size. */
+	IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(0), GENMASK(18, 17));
+
+	/* Store the permanent mac address */
+	hw->mac.ops.get_mac_addr(hw, hw->mac.perm_addr);
+
+	/* Maximum number of Receive Address Registers. */
+#define IXGBE_MAX_NUM_RAR		128
+
+	/* Store MAC address from RAR0, clear receive address registers, and
+	 * clear the multicast table.  Also reset num_rar_entries to the
+	 * maximum number of Receive Address Registers, since we modify this
+	 * value when programming the SAN MAC address.
+	 */
+	hw->mac.num_rar_entries = IXGBE_MAX_NUM_RAR;
+	hw->mac.ops.init_rx_addrs(hw);
+
+	/* Initialize bus function number */
+	hw->mac.ops.set_lan_id(hw);
+
+reset_hw_out:
+	return err;
+}
+
+/**
+ * ixgbe_get_pfa_module_tlv - Read sub module TLV from NVM PFA
+ * @hw: pointer to hardware structure
+ * @module_tlv: pointer to module TLV to return
+ * @module_tlv_len: pointer to module TLV length to return
+ * @module_type: module type requested
+ *
+ * Find the requested sub module TLV type from the Preserved Field
+ * Area (PFA) and returns the TLV pointer and length. The caller can
+ * use these to read the variable length TLV value.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_pfa_module_tlv(struct ixgbe_hw *hw, u16 *module_tlv,
+				    u16 *module_tlv_len, u16 module_type)
+{
+	u16 pfa_len, pfa_ptr, pfa_end_ptr;
+	u16 next_tlv;
+	int err;
+
+	err = ixgbe_read_ee_aci_e610(hw, IXGBE_E610_SR_PFA_PTR, &pfa_ptr);
+	if (err)
+		return err;
+
+	err = ixgbe_read_ee_aci_e610(hw, pfa_ptr, &pfa_len);
+	if (err)
+		return err;
+
+	/* Starting with first TLV after PFA length, iterate through the list
+	 * of TLVs to find the requested one.
+	 */
+	next_tlv = pfa_ptr + 1;
+	pfa_end_ptr = pfa_ptr + pfa_len;
+	while (next_tlv < pfa_end_ptr) {
+		u16 tlv_sub_module_type, tlv_len;
+
+		/* Read TLV type */
+		err = ixgbe_read_ee_aci_e610(hw, next_tlv,
+					     &tlv_sub_module_type);
+		if (err)
+			break;
+
+		/* Read TLV length */
+		err = ixgbe_read_ee_aci_e610(hw, next_tlv + 1, &tlv_len);
+		if (err)
+			break;
+
+		if (tlv_sub_module_type == module_type) {
+			if (tlv_len) {
+				*module_tlv = next_tlv;
+				*module_tlv_len = tlv_len;
+				return 0;
+			}
+			return -EIO;
+		}
+		/* Check next TLV, i.e. current TLV pointer + length + 2 words
+		 * (for current TLV's type and length).
+		 */
+		next_tlv = next_tlv + tlv_len + 2;
+	}
+	/* Module does not exist */
+	return -ENODATA;
+}
+
+/**
+ * ixgbe_read_pba_string_e610 - Read PBA string from NVM
+ * @hw: pointer to hardware structure
+ * @pba_num: stores the part number string from the NVM
+ * @pba_num_size: part number string buffer length
+ *
+ * Read the part number string from the NVM.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_pba_string_e610(struct ixgbe_hw *hw, u8 *pba_num,
+				      u32 pba_num_size)
+{
+	u16 pba_tlv, pba_tlv_len;
+	u16 pba_word, pba_size;
+	int err;
+
+	*pba_num = '\0';
+
+	err = ixgbe_get_pfa_module_tlv(hw, &pba_tlv, &pba_tlv_len,
+				       IXGBE_E610_SR_PBA_BLOCK_PTR);
+	if (err)
+		return err;
+
+	/* pba_size is the next word */
+	err = ixgbe_read_ee_aci_e610(hw, (pba_tlv + 2), &pba_size);
+	if (err)
+		return err;
+
+	if (pba_tlv_len < pba_size)
+		return -EINVAL;
+
+	/* Subtract one to get PBA word count (PBA Size word is included in
+	 * total size).
+	 */
+	pba_size--;
+
+	if (pba_num_size < (((u32)pba_size * 2) + 1))
+		return -EINVAL;
+
+	for (u16 i = 0; i < pba_size; i++) {
+		err = ixgbe_read_ee_aci_e610(hw, (pba_tlv + 2 + 1) + i,
+					     &pba_word);
+		if (err)
+			return err;
+
+		pba_num[(i * 2)] = FIELD_GET(IXGBE_E610_SR_PBA_BLOCK_MASK,
+					     pba_word);
+		pba_num[(i * 2) + 1] = pba_word & 0xFF;
+	}
+
+	pba_num[(pba_size * 2)] = '\0';
+
+	return err;
+}
+
+static int __fwlog_send_cmd(void *priv, struct libie_aq_desc *desc, void *buf,
+			    u16 size)
+{
+	struct ixgbe_hw *hw = priv;
+
+	return ixgbe_aci_send_cmd(hw, desc, buf, size);
+}
+
+int ixgbe_fwlog_init(struct ixgbe_hw *hw)
+{
+	struct ixgbe_adapter *adapter = hw->back;
+	struct libie_fwlog_api api = {
+		.pdev = adapter->pdev,
+		.send_cmd = __fwlog_send_cmd,
+		.debugfs_root = adapter->ixgbe_dbg_adapter,
+		.priv = hw,
+	};
+
+	if (hw->mac.type != ixgbe_mac_e610)
+		return -EOPNOTSUPP;
+
+	return libie_fwlog_init(&hw->fwlog, &api);
+}
+
+void ixgbe_fwlog_deinit(struct ixgbe_hw *hw)
+{
+	if (hw->mac.type != ixgbe_mac_e610)
+		return;
+
+	libie_fwlog_deinit(&hw->fwlog);
+}
+
+static const struct ixgbe_mac_operations mac_ops_e610 = {
+	.init_hw			= ixgbe_init_hw_generic,
+	.start_hw			= ixgbe_start_hw_e610,
+	.clear_hw_cntrs			= ixgbe_clear_hw_cntrs_generic,
+	.enable_rx_dma			= ixgbe_enable_rx_dma_generic,
+	.get_mac_addr			= ixgbe_get_mac_addr_generic,
+	.get_device_caps		= ixgbe_get_device_caps_generic,
+	.stop_adapter			= ixgbe_stop_adapter_generic,
+	.set_lan_id			= ixgbe_set_lan_id_multi_port_pcie,
+	.set_rxpba			= ixgbe_set_rxpba_generic,
+	.check_link			= ixgbe_check_link_e610,
+	.blink_led_start		= ixgbe_blink_led_start_X540,
+	.blink_led_stop			= ixgbe_blink_led_stop_X540,
+	.set_rar			= ixgbe_set_rar_generic,
+	.clear_rar			= ixgbe_clear_rar_generic,
+	.set_vmdq			= ixgbe_set_vmdq_generic,
+	.set_vmdq_san_mac		= ixgbe_set_vmdq_san_mac_generic,
+	.clear_vmdq			= ixgbe_clear_vmdq_generic,
+	.init_rx_addrs			= ixgbe_init_rx_addrs_generic,
+	.update_mc_addr_list		= ixgbe_update_mc_addr_list_generic,
+	.enable_mc			= ixgbe_enable_mc_generic,
+	.disable_mc			= ixgbe_disable_mc_generic,
+	.clear_vfta			= ixgbe_clear_vfta_generic,
+	.set_vfta			= ixgbe_set_vfta_generic,
+	.fc_enable			= ixgbe_fc_enable_generic,
+	.set_fw_drv_ver			= ixgbe_set_fw_drv_ver_x550,
+	.init_uta_tables		= ixgbe_init_uta_tables_generic,
+	.set_mac_anti_spoofing		= ixgbe_set_mac_anti_spoofing,
+	.set_vlan_anti_spoofing		= ixgbe_set_vlan_anti_spoofing,
+	.set_source_address_pruning	=
+				ixgbe_set_source_address_pruning_x550,
+	.set_ethertype_anti_spoofing	=
+				ixgbe_set_ethertype_anti_spoofing_x550,
+	.disable_rx_buff		= ixgbe_disable_rx_buff_generic,
+	.enable_rx_buff			= ixgbe_enable_rx_buff_generic,
+	.enable_rx			= ixgbe_enable_rx_generic,
+	.disable_rx			= ixgbe_disable_rx_e610,
+	.led_on				= ixgbe_led_on_generic,
+	.led_off			= ixgbe_led_off_generic,
+	.init_led_link_act		= ixgbe_init_led_link_act_generic,
+	.reset_hw			= ixgbe_reset_hw_e610,
+	.get_fw_ver                     = ixgbe_aci_get_fw_ver,
+	.get_media_type			= ixgbe_get_media_type_e610,
+	.setup_link			= ixgbe_setup_link_e610,
+	.fw_recovery_mode		= ixgbe_fw_recovery_mode_e610,
+	.fw_rollback_mode		= ixgbe_fw_rollback_mode_e610,
+	.get_nvm_ver			= ixgbe_get_active_nvm_ver,
+	.get_link_capabilities		= ixgbe_get_link_capabilities_e610,
+	.get_bus_info			= ixgbe_get_bus_info_generic,
+	.acquire_swfw_sync		= ixgbe_acquire_swfw_sync_X540,
+	.release_swfw_sync		= ixgbe_release_swfw_sync_X540,
+	.init_swfw_sync			= ixgbe_init_swfw_sync_X540,
+	.prot_autoc_read		= prot_autoc_read_generic,
+	.prot_autoc_write		= prot_autoc_write_generic,
+	.setup_fc			= ixgbe_setup_fc_e610,
+	.fc_autoneg			= ixgbe_fc_autoneg_e610,
+	.enable_mdd			= ixgbe_enable_mdd_x550,
+	.disable_mdd			= ixgbe_disable_mdd_x550,
+	.restore_mdd_vf			= ixgbe_restore_mdd_vf_x550,
+	.handle_mdd			= ixgbe_handle_mdd_x550,
+};
+
+static const struct ixgbe_phy_operations phy_ops_e610 = {
+	.init				= ixgbe_init_phy_ops_e610,
+	.identify			= ixgbe_identify_phy_e610,
+	.identify_sfp			= ixgbe_identify_module_e610,
+	.setup_link_speed		= ixgbe_setup_phy_link_speed_generic,
+	.setup_link			= ixgbe_setup_phy_link_e610,
+	.enter_lplu			= ixgbe_enter_lplu_e610,
+};
+
+static const struct ixgbe_eeprom_operations eeprom_ops_e610 = {
+	.read				= ixgbe_read_ee_aci_e610,
+	.read_buffer			= ixgbe_read_ee_aci_buffer_e610,
+	.validate_checksum		= ixgbe_validate_eeprom_checksum_e610,
+	.read_pba_string		= ixgbe_read_pba_string_e610,
+	.init_params			= ixgbe_init_eeprom_params_e610,
+};
+
+const struct ixgbe_info ixgbe_e610_info = {
+	.mac			= ixgbe_mac_e610,
+	.get_invariants		= ixgbe_get_invariants_X540,
+	.mac_ops		= &mac_ops_e610,
+	.eeprom_ops		= &eeprom_ops_e610,
+	.phy_ops		= &phy_ops_e610,
+	.mbx_ops		= &mbx_ops_generic,
+	.mvals			= ixgbe_mvals_x550em_a,
+};
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h
new file mode 100644
index 000000000000..11916b979d28
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IXGBE_E610_H_
+#define _IXGBE_E610_H_
+
+#include "ixgbe_type.h"
+
+int ixgbe_aci_send_cmd(struct ixgbe_hw *hw, struct libie_aq_desc *desc,
+		       void *buf, u16 buf_size);
+bool ixgbe_aci_check_event_pending(struct ixgbe_hw *hw);
+int ixgbe_aci_get_event(struct ixgbe_hw *hw, struct ixgbe_aci_event *e,
+			bool *pending);
+void ixgbe_fill_dflt_direct_cmd_desc(struct libie_aq_desc *desc, u16 opcode);
+int ixgbe_acquire_res(struct ixgbe_hw *hw, enum libie_aq_res_id res,
+		      enum libie_aq_res_access_type access, u32 timeout);
+void ixgbe_release_res(struct ixgbe_hw *hw, enum libie_aq_res_id res);
+int ixgbe_aci_list_caps(struct ixgbe_hw *hw, void *buf, u16 buf_size,
+			u32 *cap_count, enum ixgbe_aci_opc opc);
+int ixgbe_discover_dev_caps(struct ixgbe_hw *hw,
+			    struct ixgbe_hw_dev_caps *dev_caps);
+int ixgbe_discover_func_caps(struct ixgbe_hw *hw,
+			     struct ixgbe_hw_func_caps *func_caps);
+int ixgbe_get_caps(struct ixgbe_hw *hw);
+int ixgbe_aci_disable_rxen(struct ixgbe_hw *hw);
+int ixgbe_aci_get_phy_caps(struct ixgbe_hw *hw, bool qual_mods, u8 report_mode,
+			   struct ixgbe_aci_cmd_get_phy_caps_data *pcaps);
+void ixgbe_copy_phy_caps_to_cfg(struct ixgbe_aci_cmd_get_phy_caps_data *caps,
+				struct ixgbe_aci_cmd_set_phy_cfg_data *cfg);
+int ixgbe_aci_set_phy_cfg(struct ixgbe_hw *hw,
+			  struct ixgbe_aci_cmd_set_phy_cfg_data *cfg);
+int ixgbe_aci_set_link_restart_an(struct ixgbe_hw *hw, bool ena_link);
+int ixgbe_update_link_info(struct ixgbe_hw *hw);
+int ixgbe_get_link_status(struct ixgbe_hw *hw, bool *link_up);
+int ixgbe_aci_get_link_info(struct ixgbe_hw *hw, bool ena_lse,
+			    struct ixgbe_link_status *link);
+int ixgbe_aci_set_event_mask(struct ixgbe_hw *hw, u8 port_num, u16 mask);
+int ixgbe_configure_lse(struct ixgbe_hw *hw, bool activate, u16 mask);
+int ixgbe_aci_set_port_id_led(struct ixgbe_hw *hw, bool orig_mode);
+enum ixgbe_media_type ixgbe_get_media_type_e610(struct ixgbe_hw *hw);
+int ixgbe_setup_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed speed,
+			  bool autoneg_wait);
+int ixgbe_check_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
+			  bool *link_up, bool link_up_wait_to_complete);
+int ixgbe_get_link_capabilities_e610(struct ixgbe_hw *hw,
+				     ixgbe_link_speed *speed,
+				     bool *autoneg);
+int ixgbe_cfg_phy_fc(struct ixgbe_hw *hw,
+		     struct ixgbe_aci_cmd_set_phy_cfg_data *cfg,
+		     enum ixgbe_fc_mode req_mode);
+int ixgbe_setup_fc_e610(struct ixgbe_hw *hw);
+void ixgbe_fc_autoneg_e610(struct ixgbe_hw *hw);
+void ixgbe_disable_rx_e610(struct ixgbe_hw *hw);
+int ixgbe_init_phy_ops_e610(struct ixgbe_hw *hw);
+int ixgbe_identify_phy_e610(struct ixgbe_hw *hw);
+int ixgbe_identify_module_e610(struct ixgbe_hw *hw);
+int ixgbe_setup_phy_link_e610(struct ixgbe_hw *hw);
+int ixgbe_set_phy_power_e610(struct ixgbe_hw *hw, bool on);
+int ixgbe_enter_lplu_e610(struct ixgbe_hw *hw);
+int ixgbe_init_eeprom_params_e610(struct ixgbe_hw *hw);
+int ixgbe_aci_get_netlist_node(struct ixgbe_hw *hw,
+			       struct ixgbe_aci_cmd_get_link_topo *cmd,
+			       u8 *node_part_number, u16 *node_handle);
+int ixgbe_acquire_nvm(struct ixgbe_hw *hw,
+		      enum libie_aq_res_access_type access);
+void ixgbe_release_nvm(struct ixgbe_hw *hw);
+int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset,
+		       u16 length, void *data, bool last_command,
+		       bool read_shadow_ram);
+int ixgbe_nvm_validate_checksum(struct ixgbe_hw *hw);
+int ixgbe_get_inactive_orom_ver(struct ixgbe_hw *hw,
+				struct ixgbe_orom_info *orom);
+int ixgbe_get_inactive_nvm_ver(struct ixgbe_hw *hw, struct ixgbe_nvm_info *nvm);
+int ixgbe_get_inactive_netlist_ver(struct ixgbe_hw *hw,
+				   struct ixgbe_netlist_info *netlist);
+int ixgbe_read_sr_word_aci(struct ixgbe_hw  *hw, u16 offset, u16 *data);
+int ixgbe_read_flat_nvm(struct ixgbe_hw  *hw, u32 offset, u32 *length,
+			u8 *data, bool read_shadow_ram);
+int ixgbe_read_sr_buf_aci(struct ixgbe_hw *hw, u16 offset, u16 *words,
+			  u16 *data);
+int ixgbe_read_ee_aci_e610(struct ixgbe_hw *hw, u16 offset, u16 *data);
+int ixgbe_read_ee_aci_buffer_e610(struct ixgbe_hw *hw, u16 offset,
+				  u16 words, u16 *data);
+int ixgbe_validate_eeprom_checksum_e610(struct ixgbe_hw *hw, u16 *checksum_val);
+int ixgbe_reset_hw_e610(struct ixgbe_hw *hw);
+int ixgbe_get_flash_data(struct ixgbe_hw *hw);
+int ixgbe_aci_nvm_update_empr(struct ixgbe_hw *hw);
+int ixgbe_nvm_set_pkg_data(struct ixgbe_hw *hw, bool del_pkg_data_flag,
+			   u8 *data, u16 length);
+int ixgbe_nvm_pass_component_tbl(struct ixgbe_hw *hw, u8 *data, u16 length,
+				 u8 transfer_flag, u8 *comp_response,
+				 u8 *comp_response_code);
+int ixgbe_aci_erase_nvm(struct ixgbe_hw *hw, u16 module_typeid);
+int ixgbe_aci_update_nvm(struct ixgbe_hw *hw, u16 module_typeid,
+			 u32 offset, u16 length, void *data,
+			 bool last_command, u8 command_flags);
+int ixgbe_nvm_write_activate(struct ixgbe_hw *hw, u16 cmd_flags,
+			     u8 *response_flags);
+int ixgbe_fwlog_init(struct ixgbe_hw *hw);
+void ixgbe_fwlog_deinit(struct ixgbe_hw *hw);
+
+#endif /* _IXGBE_E610_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 9482e0cca8b7..2ad81f687a84 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 /* ethtool support for ixgbe */
 
@@ -213,7 +213,7 @@ static void ixgbe_set_advertising_10gtypes(struct ixgbe_hw *hw,
 static int ixgbe_get_link_ksettings(struct net_device *netdev,
 				    struct ethtool_link_ksettings *cmd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	ixgbe_link_speed supported_link;
 	bool autoneg = false;
@@ -458,7 +458,7 @@ static int ixgbe_get_link_ksettings(struct net_device *netdev,
 static int ixgbe_set_link_ksettings(struct net_device *netdev,
 				    const struct ethtool_link_ksettings *cmd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 advertised, old;
 	int err = 0;
@@ -535,7 +535,7 @@ static int ixgbe_set_link_ksettings(struct net_device *netdev,
 static void ixgbe_get_pause_stats(struct net_device *netdev,
 				  struct ethtool_pause_stats *stats)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw_stats *hwstats = &adapter->stats;
 
 	stats->tx_pause_frames = hwstats->lxontxc + hwstats->lxofftxc;
@@ -545,7 +545,7 @@ static void ixgbe_get_pause_stats(struct net_device *netdev,
 static void ixgbe_get_pauseparam(struct net_device *netdev,
 				 struct ethtool_pauseparam *pause)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (ixgbe_device_supports_autoneg_fc(hw) &&
@@ -564,10 +564,26 @@ static void ixgbe_get_pauseparam(struct net_device *netdev,
 	}
 }
 
+static void ixgbe_set_pauseparam_finalize(struct net_device *netdev,
+					  struct ixgbe_fc_info *fc)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	/* If the thing changed then we'll update and use new autoneg. */
+	if (memcmp(fc, &hw->fc, sizeof(*fc))) {
+		hw->fc = *fc;
+		if (netif_running(netdev))
+			ixgbe_reinit_locked(adapter);
+		else
+			ixgbe_reset(adapter);
+	}
+}
+
 static int ixgbe_set_pauseparam(struct net_device *netdev,
 				struct ethtool_pauseparam *pause)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct ixgbe_fc_info fc = hw->fc;
 
@@ -592,27 +608,52 @@ static int ixgbe_set_pauseparam(struct net_device *netdev,
 	else
 		fc.requested_mode = ixgbe_fc_none;
 
-	/* if the thing changed then we'll update and use new autoneg */
-	if (memcmp(&fc, &hw->fc, sizeof(struct ixgbe_fc_info))) {
-		hw->fc = fc;
-		if (netif_running(netdev))
-			ixgbe_reinit_locked(adapter);
-		else
-			ixgbe_reset(adapter);
+	ixgbe_set_pauseparam_finalize(netdev, &fc);
+
+	return 0;
+}
+
+static int ixgbe_set_pauseparam_e610(struct net_device *netdev,
+				     struct ethtool_pauseparam *pause)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_fc_info fc = hw->fc;
+
+	if (!ixgbe_device_supports_autoneg_fc(hw))
+		return -EOPNOTSUPP;
+
+	if (pause->autoneg == AUTONEG_DISABLE) {
+		netdev_info(netdev,
+			    "Cannot disable autonegotiation on this device.\n");
+		return -EOPNOTSUPP;
 	}
 
+	fc.disable_fc_autoneg = false;
+
+	if (pause->rx_pause && pause->tx_pause)
+		fc.requested_mode = ixgbe_fc_full;
+	else if (pause->rx_pause)
+		fc.requested_mode = ixgbe_fc_rx_pause;
+	else if (pause->tx_pause)
+		fc.requested_mode = ixgbe_fc_tx_pause;
+	else
+		fc.requested_mode = ixgbe_fc_none;
+
+	ixgbe_set_pauseparam_finalize(netdev, &fc);
+
 	return 0;
 }
 
 static u32 ixgbe_get_msglevel(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	return adapter->msg_enable;
 }
 
 static void ixgbe_set_msglevel(struct net_device *netdev, u32 data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	adapter->msg_enable = data;
 }
 
@@ -627,7 +668,7 @@ static int ixgbe_get_regs_len(struct net_device *netdev)
 static void ixgbe_get_regs(struct net_device *netdev,
 			   struct ethtool_regs *regs, void *p)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 *regs_buff = p;
 	u8 i;
@@ -690,6 +731,7 @@ static void ixgbe_get_regs(struct net_device *netdev,
 		case ixgbe_mac_X550:
 		case ixgbe_mac_X550EM_x:
 		case ixgbe_mac_x550em_a:
+		case ixgbe_mac_e610:
 			regs_buff[35 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTL_82599(i));
 			regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTH_82599(i));
 			break;
@@ -991,16 +1033,24 @@ static void ixgbe_get_regs(struct net_device *netdev,
 	regs_buff[1144] = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT);
 }
 
+static void ixgbe_get_link_ext_stats(struct net_device *netdev,
+				     struct ethtool_link_ext_stats *stats)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+
+	stats->link_down_events = adapter->link_down_events;
+}
+
 static int ixgbe_get_eeprom_len(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	return adapter->hw.eeprom.word_size * 2;
 }
 
 static int ixgbe_get_eeprom(struct net_device *netdev,
 			    struct ethtool_eeprom *eeprom, u8 *bytes)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u16 *eeprom_buff;
 	int first_word, last_word, eeprom_len;
@@ -1036,7 +1086,7 @@ static int ixgbe_get_eeprom(struct net_device *netdev,
 static int ixgbe_set_eeprom(struct net_device *netdev,
 			    struct ethtool_eeprom *eeprom, u8 *bytes)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u16 *eeprom_buff;
 	void *ptr;
@@ -1103,10 +1153,22 @@ err:
 	return ret_val;
 }
 
+void ixgbe_refresh_fw_version(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	ixgbe_get_flash_data(hw);
+	ixgbe_set_fw_version_e610(adapter);
+}
+
 static void ixgbe_get_drvinfo(struct net_device *netdev,
 			      struct ethtool_drvinfo *drvinfo)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+
+	/* need to refresh info for e610 in case fw reloads in runtime */
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		ixgbe_refresh_fw_version(adapter);
 
 	strscpy(drvinfo->driver, ixgbe_driver_name, sizeof(drvinfo->driver));
 
@@ -1160,7 +1222,7 @@ static void ixgbe_get_ringparam(struct net_device *netdev,
 				struct kernel_ethtool_ringparam *kernel_ring,
 				struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_ring *tx_ring = adapter->tx_ring[0];
 	struct ixgbe_ring *rx_ring = adapter->rx_ring[0];
 
@@ -1175,7 +1237,7 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
 			       struct kernel_ethtool_ringparam *kernel_ring,
 			       struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_ring *temp_ring;
 	int i, j, err = 0;
 	u32 new_rx_count, new_tx_count;
@@ -1216,7 +1278,7 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
 	/* allocate temporary buffer to store rings in */
 	i = max_t(int, adapter->num_tx_queues + adapter->num_xdp_queues,
 		  adapter->num_rx_queues);
-	temp_ring = vmalloc(array_size(i, sizeof(struct ixgbe_ring)));
+	temp_ring = vmalloc_array(i, sizeof(struct ixgbe_ring));
 
 	if (!temp_ring) {
 		err = -ENOMEM;
@@ -1335,7 +1397,7 @@ static int ixgbe_get_sset_count(struct net_device *netdev, int sset)
 static void ixgbe_get_ethtool_stats(struct net_device *netdev,
 				    struct ethtool_stats *stats, u64 *data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct rtnl_link_stats64 temp;
 	const struct rtnl_link_stats64 *net_stats;
 	unsigned int start;
@@ -1613,6 +1675,7 @@ static int ixgbe_reg_test(struct ixgbe_adapter *adapter, u64 *data)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		toggle = 0x7FFFF30F;
 		test = reg_test_82599;
 		break;
@@ -1708,7 +1771,7 @@ static int ixgbe_eeprom_test(struct ixgbe_adapter *adapter, u64 *data)
 static irqreturn_t ixgbe_test_intr(int irq, void *data)
 {
 	struct net_device *netdev = (struct net_device *) data;
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->test_icr |= IXGBE_READ_REG(&adapter->hw, IXGBE_EICR);
 
@@ -1874,6 +1937,7 @@ static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_DMATXCTL);
 		reg_data |= IXGBE_DMATXCTL_TE;
 		IXGBE_WRITE_REG(&adapter->hw, IXGBE_DMATXCTL, reg_data);
@@ -1935,6 +1999,7 @@ static int ixgbe_setup_loopback_test(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		reg_data = IXGBE_READ_REG(hw, IXGBE_MACC);
 		reg_data |= IXGBE_MACC_FLU;
 		IXGBE_WRITE_REG(hw, IXGBE_MACC, reg_data);
@@ -2179,7 +2244,7 @@ out:
 static void ixgbe_diag_test(struct net_device *netdev,
 			    struct ethtool_test *eth_test, u64 *data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	bool if_running = netif_running(netdev);
 
 	if (ixgbe_removed(adapter->hw.hw_addr)) {
@@ -2302,7 +2367,7 @@ static int ixgbe_wol_exclusion(struct ixgbe_adapter *adapter,
 static void ixgbe_get_wol(struct net_device *netdev,
 			  struct ethtool_wolinfo *wol)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	wol->supported = WAKE_UCAST | WAKE_MCAST |
 			 WAKE_BCAST | WAKE_MAGIC;
@@ -2324,7 +2389,7 @@ static void ixgbe_get_wol(struct net_device *netdev,
 
 static int ixgbe_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (wol->wolopts & (WAKE_PHY | WAKE_ARP | WAKE_MAGICSECURE |
 			    WAKE_FILTER))
@@ -2349,9 +2414,53 @@ static int ixgbe_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 	return 0;
 }
 
+static int ixgbe_set_wol_acpi(struct net_device *netdev,
+			      struct ethtool_wolinfo *wol)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 grc;
+
+	if (ixgbe_wol_exclusion(adapter, wol))
+		return wol->wolopts ? -EOPNOTSUPP : 0;
+
+	/* disable APM wakeup */
+	grc = IXGBE_READ_REG(hw, IXGBE_GRC_X550EM_a);
+	grc &= ~IXGBE_GRC_APME;
+	IXGBE_WRITE_REG(hw, IXGBE_GRC_X550EM_a, grc);
+
+	/* erase existing filters */
+	IXGBE_WRITE_REG(hw, IXGBE_WUFC, 0);
+	adapter->wol = 0;
+
+	if (wol->wolopts & WAKE_UCAST)
+		adapter->wol |= IXGBE_WUFC_EX;
+	if (wol->wolopts & WAKE_MCAST)
+		adapter->wol |= IXGBE_WUFC_MC;
+	if (wol->wolopts & WAKE_BCAST)
+		adapter->wol |= IXGBE_WUFC_BC;
+
+	IXGBE_WRITE_REG(hw, IXGBE_WUC, IXGBE_WUC_PME_EN);
+	IXGBE_WRITE_REG(hw, IXGBE_WUFC, adapter->wol);
+
+	hw->wol_enabled = adapter->wol;
+	device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol);
+
+	return 0;
+}
+
+static int ixgbe_set_wol_e610(struct net_device *netdev,
+			      struct ethtool_wolinfo *wol)
+{
+	if (wol->wolopts & (WAKE_UCAST | WAKE_MCAST | WAKE_BCAST))
+		return ixgbe_set_wol_acpi(netdev, wol);
+	else
+		return ixgbe_set_wol(netdev, wol);
+}
+
 static int ixgbe_nway_reset(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (netif_running(netdev))
 		ixgbe_reinit_locked(adapter);
@@ -2362,7 +2471,7 @@ static int ixgbe_nway_reset(struct net_device *netdev)
 static int ixgbe_set_phys_id(struct net_device *netdev,
 			     enum ethtool_phys_id_state state)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (!hw->mac.ops.led_on || !hw->mac.ops.led_off)
@@ -2390,12 +2499,32 @@ static int ixgbe_set_phys_id(struct net_device *netdev,
 	return 0;
 }
 
+static int ixgbe_set_phys_id_e610(struct net_device *netdev,
+				  enum ethtool_phys_id_state state)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+	bool led_active;
+
+	switch (state) {
+	case ETHTOOL_ID_ACTIVE:
+		led_active = true;
+		break;
+	case ETHTOOL_ID_INACTIVE:
+		led_active = false;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return ixgbe_aci_set_port_id_led(&adapter->hw, !led_active);
+}
+
 static int ixgbe_get_coalesce(struct net_device *netdev,
 			      struct ethtool_coalesce *ec,
 			      struct kernel_ethtool_coalesce *kernel_coal,
 			      struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* only valid if in constant ITR mode */
 	if (adapter->rx_itr_setting <= 1)
@@ -2451,7 +2580,7 @@ static int ixgbe_set_coalesce(struct net_device *netdev,
 			      struct kernel_ethtool_coalesce *kernel_coal,
 			      struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_q_vector *q_vector;
 	int i;
 	u16 tx_itr_param, rx_itr_param, tx_itr_prev;
@@ -2624,9 +2753,11 @@ static int ixgbe_get_ethtool_fdir_all(struct ixgbe_adapter *adapter,
 	return 0;
 }
 
-static int ixgbe_get_rss_hash_opts(struct ixgbe_adapter *adapter,
-				   struct ethtool_rxnfc *cmd)
+static int ixgbe_get_rxfh_fields(struct net_device *dev,
+				 struct ethtool_rxfh_fields *cmd)
 {
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
+
 	cmd->data = 0;
 
 	/* Report default options for RSS on ixgbe */
@@ -2674,18 +2805,21 @@ static int ixgbe_rss_indir_tbl_max(struct ixgbe_adapter *adapter)
 		return 64;
 }
 
+static u32 ixgbe_get_rx_ring_count(struct net_device *dev)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
+
+	return min_t(u32, adapter->num_rx_queues,
+		     ixgbe_rss_indir_tbl_max(adapter));
+}
+
 static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 			   u32 *rule_locs)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int ret = -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
-	case ETHTOOL_GRXRINGS:
-		cmd->data = min_t(int, adapter->num_rx_queues,
-				  ixgbe_rss_indir_tbl_max(adapter));
-		ret = 0;
-		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = adapter->fdir_filter_count;
 		ret = 0;
@@ -2696,9 +2830,6 @@ static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	case ETHTOOL_GRXCLSRLALL:
 		ret = ixgbe_get_ethtool_fdir_all(adapter, cmd, rule_locs);
 		break;
-	case ETHTOOL_GRXFH:
-		ret = ixgbe_get_rss_hash_opts(adapter, cmd);
-		break;
 	default:
 		break;
 	}
@@ -2950,9 +3081,11 @@ static int ixgbe_del_ethtool_fdir_entry(struct ixgbe_adapter *adapter,
 
 #define UDP_RSS_FLAGS (IXGBE_FLAG2_RSS_FIELD_IPV4_UDP | \
 		       IXGBE_FLAG2_RSS_FIELD_IPV6_UDP)
-static int ixgbe_set_rss_hash_opt(struct ixgbe_adapter *adapter,
-				  struct ethtool_rxnfc *nfc)
+static int ixgbe_set_rxfh_fields(struct net_device *dev,
+				 const struct ethtool_rxfh_fields *nfc,
+				 struct netlink_ext_ack *extack)
 {
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	u32 flags2 = adapter->flags2;
 
 	/*
@@ -3065,7 +3198,7 @@ static int ixgbe_set_rss_hash_opt(struct ixgbe_adapter *adapter,
 
 static int ixgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int ret = -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
@@ -3075,9 +3208,6 @@ static int ixgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	case ETHTOOL_SRXCLSRLDEL:
 		ret = ixgbe_del_ethtool_fdir_entry(adapter, cmd);
 		break;
-	case ETHTOOL_SRXFH:
-		ret = ixgbe_set_rss_hash_opt(adapter, cmd);
-		break;
 	default:
 		break;
 	}
@@ -3092,7 +3222,7 @@ static u32 ixgbe_get_rxfh_key_size(struct net_device *netdev)
 
 static u32 ixgbe_rss_indir_size(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	return ixgbe_rss_indir_tbl_entries(adapter);
 }
@@ -3112,7 +3242,7 @@ static void ixgbe_get_reta(struct ixgbe_adapter *adapter, u32 *indir)
 static int ixgbe_get_rxfh(struct net_device *netdev,
 			  struct ethtool_rxfh_param *rxfh)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
@@ -3130,7 +3260,7 @@ static int ixgbe_set_rxfh(struct net_device *netdev,
 			  struct ethtool_rxfh_param *rxfh,
 			  struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int i;
 	u32 reta_entries = ixgbe_rss_indir_tbl_entries(adapter);
 
@@ -3172,7 +3302,7 @@ static int ixgbe_set_rxfh(struct net_device *netdev,
 static int ixgbe_get_ts_info(struct net_device *dev,
 			     struct kernel_ethtool_ts_info *info)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	/* we always support timestamping disabled */
 	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE);
@@ -3181,6 +3311,7 @@ static int ixgbe_get_ts_info(struct net_device *dev,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		info->rx_filters |= BIT(HWTSTAMP_FILTER_ALL);
 		break;
 	case ixgbe_mac_X540:
@@ -3247,7 +3378,7 @@ static unsigned int ixgbe_max_channels(struct ixgbe_adapter *adapter)
 static void ixgbe_get_channels(struct net_device *dev,
 			       struct ethtool_channels *ch)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	/* report maximum channels */
 	ch->max_combined = ixgbe_max_channels(adapter);
@@ -3284,7 +3415,7 @@ static void ixgbe_get_channels(struct net_device *dev,
 static int ixgbe_set_channels(struct net_device *dev,
 			      struct ethtool_channels *ch)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	unsigned int count = ch->combined_count;
 	u8 max_rss_indices = ixgbe_max_rss_indices(adapter);
 
@@ -3322,7 +3453,7 @@ static int ixgbe_set_channels(struct net_device *dev,
 static int ixgbe_get_module_info(struct net_device *dev,
 				       struct ethtool_modinfo *modinfo)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u8 sff8472_rev, addr_mode;
 	bool page_swap = false;
@@ -3368,7 +3499,7 @@ static int ixgbe_get_module_eeprom(struct net_device *dev,
 					 struct ethtool_eeprom *ee,
 					 u8 *data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	int status = -EFAULT;
 	u8 databyte = 0xFF;
@@ -3443,13 +3574,13 @@ ixgbe_get_eee_fw(struct ixgbe_adapter *adapter, struct ethtool_keee *edata)
 
 	for (i = 0; i < ARRAY_SIZE(ixgbe_ls_map); ++i) {
 		if (hw->phy.eee_speeds_supported & ixgbe_ls_map[i].mac_speed)
-			linkmode_set_bit(ixgbe_lp_map[i].link_mode,
+			linkmode_set_bit(ixgbe_ls_map[i].link_mode,
 					 edata->supported);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(ixgbe_ls_map); ++i) {
 		if (hw->phy.eee_speeds_advertised & ixgbe_ls_map[i].mac_speed)
-			linkmode_set_bit(ixgbe_lp_map[i].link_mode,
+			linkmode_set_bit(ixgbe_ls_map[i].link_mode,
 					 edata->advertised);
 	}
 
@@ -3464,7 +3595,7 @@ ixgbe_get_eee_fw(struct ixgbe_adapter *adapter, struct ethtool_keee *edata)
 
 static int ixgbe_get_eee(struct net_device *netdev, struct ethtool_keee *edata)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (!(adapter->flags2 & IXGBE_FLAG2_EEE_CAPABLE))
@@ -3478,7 +3609,7 @@ static int ixgbe_get_eee(struct net_device *netdev, struct ethtool_keee *edata)
 
 static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_keee *edata)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct ethtool_keee eee_data;
 	int ret_val;
@@ -3533,7 +3664,7 @@ static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_keee *edata)
 
 static u32 ixgbe_get_priv_flags(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	u32 priv_flags = 0;
 
 	if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
@@ -3550,7 +3681,7 @@ static u32 ixgbe_get_priv_flags(struct net_device *netdev)
 
 static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	unsigned int flags2 = adapter->flags2;
 	unsigned int i;
 
@@ -3597,6 +3728,7 @@ static const struct ethtool_ops ixgbe_ethtool_ops = {
 	.set_wol                = ixgbe_set_wol,
 	.nway_reset             = ixgbe_nway_reset,
 	.get_link               = ethtool_op_get_link,
+	.get_link_ext_stats	= ixgbe_get_link_ext_stats,
 	.get_eeprom_len         = ixgbe_get_eeprom_len,
 	.get_eeprom             = ixgbe_get_eeprom,
 	.set_eeprom             = ixgbe_set_eeprom,
@@ -3614,12 +3746,64 @@ static const struct ethtool_ops ixgbe_ethtool_ops = {
 	.get_ethtool_stats      = ixgbe_get_ethtool_stats,
 	.get_coalesce           = ixgbe_get_coalesce,
 	.set_coalesce           = ixgbe_set_coalesce,
+	.get_rx_ring_count	= ixgbe_get_rx_ring_count,
+	.get_rxnfc		= ixgbe_get_rxnfc,
+	.set_rxnfc		= ixgbe_set_rxnfc,
+	.get_rxfh_indir_size	= ixgbe_rss_indir_size,
+	.get_rxfh_key_size	= ixgbe_get_rxfh_key_size,
+	.get_rxfh		= ixgbe_get_rxfh,
+	.set_rxfh		= ixgbe_set_rxfh,
+	.get_rxfh_fields	= ixgbe_get_rxfh_fields,
+	.set_rxfh_fields	= ixgbe_set_rxfh_fields,
+	.get_eee		= ixgbe_get_eee,
+	.set_eee		= ixgbe_set_eee,
+	.get_channels		= ixgbe_get_channels,
+	.set_channels		= ixgbe_set_channels,
+	.get_priv_flags		= ixgbe_get_priv_flags,
+	.set_priv_flags		= ixgbe_set_priv_flags,
+	.get_ts_info		= ixgbe_get_ts_info,
+	.get_module_info	= ixgbe_get_module_info,
+	.get_module_eeprom	= ixgbe_get_module_eeprom,
+	.get_link_ksettings     = ixgbe_get_link_ksettings,
+	.set_link_ksettings     = ixgbe_set_link_ksettings,
+};
+
+static const struct ethtool_ops ixgbe_ethtool_ops_e610 = {
+	.supported_coalesce_params = ETHTOOL_COALESCE_USECS,
+	.get_drvinfo            = ixgbe_get_drvinfo,
+	.get_regs_len           = ixgbe_get_regs_len,
+	.get_regs               = ixgbe_get_regs,
+	.get_wol                = ixgbe_get_wol,
+	.set_wol                = ixgbe_set_wol_e610,
+	.nway_reset             = ixgbe_nway_reset,
+	.get_link               = ethtool_op_get_link,
+	.get_link_ext_stats	= ixgbe_get_link_ext_stats,
+	.get_eeprom_len         = ixgbe_get_eeprom_len,
+	.get_eeprom             = ixgbe_get_eeprom,
+	.set_eeprom             = ixgbe_set_eeprom,
+	.get_ringparam          = ixgbe_get_ringparam,
+	.set_ringparam          = ixgbe_set_ringparam,
+	.get_pause_stats	= ixgbe_get_pause_stats,
+	.get_pauseparam         = ixgbe_get_pauseparam,
+	.set_pauseparam         = ixgbe_set_pauseparam_e610,
+	.get_msglevel           = ixgbe_get_msglevel,
+	.set_msglevel           = ixgbe_set_msglevel,
+	.self_test              = ixgbe_diag_test,
+	.get_strings            = ixgbe_get_strings,
+	.set_phys_id            = ixgbe_set_phys_id_e610,
+	.get_sset_count         = ixgbe_get_sset_count,
+	.get_ethtool_stats      = ixgbe_get_ethtool_stats,
+	.get_coalesce           = ixgbe_get_coalesce,
+	.set_coalesce           = ixgbe_set_coalesce,
+	.get_rx_ring_count	= ixgbe_get_rx_ring_count,
 	.get_rxnfc		= ixgbe_get_rxnfc,
 	.set_rxnfc		= ixgbe_set_rxnfc,
 	.get_rxfh_indir_size	= ixgbe_rss_indir_size,
 	.get_rxfh_key_size	= ixgbe_get_rxfh_key_size,
 	.get_rxfh		= ixgbe_get_rxfh,
 	.set_rxfh		= ixgbe_set_rxfh,
+	.get_rxfh_fields	= ixgbe_get_rxfh_fields,
+	.set_rxfh_fields	= ixgbe_set_rxfh_fields,
 	.get_eee		= ixgbe_get_eee,
 	.set_eee		= ixgbe_set_eee,
 	.get_channels		= ixgbe_get_channels,
@@ -3635,5 +3819,10 @@ static const struct ethtool_ops ixgbe_ethtool_ops = {
 
 void ixgbe_set_ethtool_ops(struct net_device *netdev)
 {
-	netdev->ethtool_ops = &ixgbe_ethtool_ops;
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		netdev->ethtool_ops = &ixgbe_ethtool_ops_e610;
+	else
+		netdev->ethtool_ops = &ixgbe_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
index 955dced844a9..011fda9c6193 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
@@ -56,7 +56,7 @@ int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid)
 	if (xid >= netdev->fcoe_ddp_xid)
 		return 0;
 
-	adapter = netdev_priv(netdev);
+	adapter = ixgbe_from_netdev(netdev);
 	fcoe = &adapter->fcoe;
 	ddp = &fcoe->ddp[xid];
 	if (!ddp->udl)
@@ -153,7 +153,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid,
 	if (!netdev || !sgl)
 		return 0;
 
-	adapter = netdev_priv(netdev);
+	adapter = ixgbe_from_netdev(netdev);
 	if (xid >= netdev->fcoe_ddp_xid) {
 		e_warn(drv, "xid=0x%x out-of-range\n", xid);
 		return 0;
@@ -744,7 +744,7 @@ void ixgbe_free_fcoe_ddp_resources(struct ixgbe_adapter *adapter)
  * ixgbe_setup_fcoe_ddp_resources - setup all fcoe ddp context resources
  * @adapter: ixgbe adapter
  *
- * Sets up ddp context resouces
+ * Sets up ddp context resources
  *
  * Returns : 0 indicates success or -EINVAL on failure
  */
@@ -834,7 +834,7 @@ static void ixgbe_fcoe_ddp_disable(struct ixgbe_adapter *adapter)
  */
 int ixgbe_fcoe_enable(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_fcoe *fcoe = &adapter->fcoe;
 
 	atomic_inc(&fcoe->refcnt);
@@ -881,7 +881,7 @@ int ixgbe_fcoe_enable(struct net_device *netdev)
  */
 int ixgbe_fcoe_disable(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (!atomic_dec_and_test(&adapter->fcoe.refcnt))
 		return -EINVAL;
@@ -927,7 +927,7 @@ int ixgbe_fcoe_disable(struct net_device *netdev)
 int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type)
 {
 	u16 prefix = 0xffff;
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_mac_info *mac = &adapter->hw.mac;
 
 	switch (type) {
@@ -967,7 +967,7 @@ int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type)
 int ixgbe_fcoe_get_hbainfo(struct net_device *netdev,
 			   struct netdev_fcoe_hbainfo *info)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u64 dsn;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c
new file mode 100644
index 000000000000..e5479fc07a07
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c
@@ -0,0 +1,707 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2025 Intel Corporation. */
+
+#include <linux/crc32.h>
+#include <linux/pldmfw.h>
+#include <linux/uuid.h>
+
+#include "ixgbe.h"
+#include "ixgbe_fw_update.h"
+
+struct ixgbe_fwu_priv {
+	struct pldmfw context;
+
+	struct ixgbe_adapter *adapter;
+	struct netlink_ext_ack *extack;
+
+	/* Track which NVM banks to activate at the end of the update */
+	u8 activate_flags;
+	bool emp_reset_available;
+};
+
+/**
+ * ixgbe_send_package_data - Send record package data to firmware
+ * @context: PLDM fw update structure
+ * @data: pointer to the package data
+ * @length: length of the package data
+ *
+ * Send a copy of the package data associated with the PLDM record matching
+ * this device to the firmware.
+ *
+ * Note that this function sends an AdminQ command that will fail unless the
+ * NVM resource has been acquired.
+ *
+ * Return: zero on success, or a negative error code on failure.
+ */
+static int ixgbe_send_package_data(struct pldmfw *context,
+				   const u8 *data, u16 length)
+{
+	struct ixgbe_fwu_priv *priv = container_of(context,
+						   struct ixgbe_fwu_priv,
+						   context);
+	struct ixgbe_adapter *adapter = priv->adapter;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 *package_data;
+	int err;
+
+	package_data = kmemdup(data, length, GFP_KERNEL);
+	if (!package_data)
+		return -ENOMEM;
+
+	err = ixgbe_nvm_set_pkg_data(hw, false, package_data, length);
+
+	kfree(package_data);
+
+	return err;
+}
+
+/**
+ * ixgbe_check_component_response - Report firmware response to a component
+ * @adapter: device private data structure
+ * @response: indicates whether this component can be updated
+ * @code: code indicating reason for response
+ * @extack: netlink extended ACK structure
+ *
+ * Check whether firmware indicates if this component can be updated. Report
+ * a suitable error message over the netlink extended ACK if the component
+ * cannot be updated.
+ *
+ * Return: 0 if the component can be updated, or -ECANCELED if the
+ * firmware indicates the component cannot be updated.
+ */
+static int ixgbe_check_component_response(struct ixgbe_adapter *adapter,
+					  u8 response, u8 code,
+					  struct netlink_ext_ack *extack)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	switch (response) {
+	case IXGBE_ACI_NVM_PASS_COMP_CAN_BE_UPDATED:
+		/* Firmware indicated this update is good to proceed. */
+		return 0;
+	case IXGBE_ACI_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Firmware recommends not updating, as it may result in a downgrade. Continuing anyways");
+		return 0;
+	case IXGBE_ACI_NVM_PASS_COMP_CAN_NOT_BE_UPDATED:
+		NL_SET_ERR_MSG_MOD(extack, "Firmware has rejected updating.");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_PARTIAL_CHECK:
+		if (hw->mac.ops.fw_recovery_mode &&
+		    hw->mac.ops.fw_recovery_mode(hw))
+			return 0;
+		break;
+	}
+
+	switch (code) {
+	case IXGBE_ACI_NVM_PASS_COMP_STAMP_IDENTICAL_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component comparison stamp is identical to running image");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_STAMP_LOWER:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component comparison stamp is lower than running image");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_INVALID_STAMP_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component comparison stamp is invalid");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_CONFLICT_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component table conflict occurred");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_PRE_REQ_NOT_MET_CODE:
+		NL_SET_ERR_MSG_MOD(extack, "Component pre-requisites not met");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_NOT_SUPPORTED_CODE:
+		NL_SET_ERR_MSG_MOD(extack, "Component not supported");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_CANNOT_DOWNGRADE_CODE:
+		NL_SET_ERR_MSG_MOD(extack, "Component cannot be downgraded");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_INCOMPLETE_IMAGE_CODE:
+		NL_SET_ERR_MSG_MOD(extack, "Incomplete component image");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_VER_STR_IDENTICAL_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component version is identical to running image");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_VER_STR_LOWER_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component version is lower than the running image");
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Received unexpected response code from firmware");
+		break;
+	}
+
+	return -ECANCELED;
+}
+
+/**
+ * ixgbe_send_component_table - Send PLDM component table to firmware
+ * @context: PLDM fw update structure
+ * @component: the component to process
+ * @transfer_flag: relative transfer order of this component
+ *
+ * Read relevant data from the component and forward it to the device
+ * firmware. Check the response to determine if the firmware indicates that
+ * the update can proceed.
+ *
+ * This function sends ACI commands related to the NVM, and assumes that
+ * the NVM resource has been acquired.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_send_component_table(struct pldmfw *context,
+				      struct pldmfw_component *component,
+				      u8 transfer_flag)
+{
+	struct ixgbe_fwu_priv *priv = container_of(context,
+						   struct ixgbe_fwu_priv,
+						   context);
+	struct ixgbe_adapter *adapter = priv->adapter;
+	struct netlink_ext_ack *extack = priv->extack;
+	struct ixgbe_aci_cmd_nvm_comp_tbl *comp_tbl;
+	u8 comp_response, comp_response_code;
+	struct ixgbe_hw *hw = &adapter->hw;
+	size_t length;
+	int err;
+
+	switch (component->identifier) {
+	case NVM_COMP_ID_OROM:
+	case NVM_COMP_ID_NVM:
+	case NVM_COMP_ID_NETLIST:
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Unable to update due to unknown firmware component");
+		return -EOPNOTSUPP;
+	}
+
+	length = struct_size(comp_tbl, cvs, component->version_len);
+	comp_tbl = kzalloc(length, GFP_KERNEL);
+	if (!comp_tbl)
+		return -ENOMEM;
+
+	comp_tbl->comp_class = cpu_to_le16(component->classification);
+	comp_tbl->comp_id = cpu_to_le16(component->identifier);
+	comp_tbl->comp_class_idx = FWU_COMP_CLASS_IDX_NOT_USE;
+	comp_tbl->comp_cmp_stamp = cpu_to_le32(component->comparison_stamp);
+	comp_tbl->cvs_type = component->version_type;
+	comp_tbl->cvs_len = component->version_len;
+
+	memcpy(comp_tbl->cvs, component->version_string,
+	       component->version_len);
+
+	err = ixgbe_nvm_pass_component_tbl(hw, (u8 *)comp_tbl, length,
+					   transfer_flag, &comp_response,
+					   &comp_response_code);
+
+	kfree(comp_tbl);
+
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to transfer component table to firmware");
+		return -EIO;
+	}
+
+	return ixgbe_check_component_response(adapter,
+					      comp_response,
+					      comp_response_code, extack);
+}
+
+/**
+ * ixgbe_write_one_nvm_block - Write an NVM block and await completion response
+ * @adapter: the PF data structure
+ * @module: the module to write to
+ * @offset: offset in bytes
+ * @block_size: size of the block to write, up to 4k
+ * @block: pointer to block of data to write
+ * @last_cmd: whether this is the last command
+ * @extack: netlink extended ACK structure
+ *
+ * Write a block of data to a flash module, and await for the completion
+ * response message from firmware.
+ *
+ * Note this function assumes the caller has acquired the NVM resource.
+ *
+ * On successful return, reset level indicates the device reset required to
+ * complete the update.
+ *
+ *   0 - IXGBE_ACI_NVM_POR_FLAG - A full power on is required
+ *   1 - IXGBE_ACI_NVM_PERST_FLAG - A cold PCIe reset is required
+ *   2 - IXGBE_ACI_NVM_EMPR_FLAG - An EMP reset is required
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_write_one_nvm_block(struct ixgbe_adapter *adapter,
+				     u16 module, u32 offset,
+				     u16 block_size, u8 *block, bool last_cmd,
+				     struct netlink_ext_ack *extack)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	return ixgbe_aci_update_nvm(hw, module, offset, block_size, block,
+				    last_cmd, 0);
+}
+
+/**
+ * ixgbe_write_nvm_module - Write data to an NVM module
+ * @adapter: the PF driver structure
+ * @module: the module id to program
+ * @component: the name of the component being updated
+ * @image: buffer of image data to write to the NVM
+ * @length: length of the buffer
+ * @extack: netlink extended ACK structure
+ *
+ * Loop over the data for a given NVM module and program it in 4 Kb
+ * blocks. Notify devlink core of progress after each block is programmed.
+ * Loops over a block of data and programs the NVM in 4k block chunks.
+ *
+ * Note this function assumes the caller has acquired the NVM resource.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_write_nvm_module(struct ixgbe_adapter *adapter, u16 module,
+				  const char *component, const u8 *image,
+				  u32 length,
+				  struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = adapter->devlink;
+	u32 offset = 0;
+	bool last_cmd;
+	u8 *block;
+	int err;
+
+	devlink_flash_update_status_notify(devlink, "Flashing",
+					   component, 0, length);
+
+	block = kzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL);
+	if (!block)
+		return -ENOMEM;
+
+	do {
+		u32 block_size;
+
+		block_size = min_t(u32, IXGBE_ACI_MAX_BUFFER_SIZE,
+				   length - offset);
+		last_cmd = !(offset + block_size < length);
+
+		memcpy(block, image + offset, block_size);
+
+		err = ixgbe_write_one_nvm_block(adapter, module, offset,
+						block_size, block, last_cmd,
+						extack);
+		if (err)
+			break;
+
+		offset += block_size;
+
+		devlink_flash_update_status_notify(devlink, "Flashing",
+						   component, offset, length);
+	} while (!last_cmd);
+
+	if (err)
+		devlink_flash_update_status_notify(devlink, "Flashing failed",
+						   component, length, length);
+	else
+		devlink_flash_update_status_notify(devlink, "Flashing done",
+						   component, length, length);
+
+	kfree(block);
+
+	return err;
+}
+
+/* Length in seconds to wait before timing out when erasing a flash module.
+ * Yes, erasing really can take minutes to complete.
+ */
+#define IXGBE_FW_ERASE_TIMEOUT 300
+
+/**
+ * ixgbe_erase_nvm_module - Erase an NVM module and await firmware completion
+ * @adapter: the PF data structure
+ * @module: the module to erase
+ * @component: name of the component being updated
+ * @extack: netlink extended ACK structure
+ *
+ * Erase the inactive NVM bank associated with this module, and await for
+ * a completion response message from firmware.
+ *
+ * Note this function assumes the caller has acquired the NVM resource.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_erase_nvm_module(struct ixgbe_adapter *adapter, u16 module,
+				  const char *component,
+				  struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = adapter->devlink;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	devlink_flash_update_timeout_notify(devlink, "Erasing", component,
+					    IXGBE_FW_ERASE_TIMEOUT);
+
+	err = ixgbe_aci_erase_nvm(hw, module);
+	if (err)
+		devlink_flash_update_status_notify(devlink, "Erasing failed",
+						   component, 0, 0);
+	else
+		devlink_flash_update_status_notify(devlink, "Erasing done",
+						   component, 0, 0);
+
+	return err;
+}
+
+/**
+ * ixgbe_switch_flash_banks - Tell firmware to switch NVM banks
+ * @adapter: Pointer to the PF data structure
+ * @activate_flags: flags used for the activation command
+ * @emp_reset_available: on return, indicates if EMP reset is available
+ * @extack: netlink extended ACK structure
+ *
+ * Notify firmware to activate the newly written flash banks, and wait for the
+ * firmware response.
+ *
+ * Return: 0 on success or an error code on failure.
+ */
+static int ixgbe_switch_flash_banks(struct ixgbe_adapter *adapter,
+				    u8 activate_flags,
+				    bool *emp_reset_available,
+				    struct netlink_ext_ack *extack)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 response_flags;
+	int err;
+
+	err = ixgbe_nvm_write_activate(hw, activate_flags, &response_flags);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to switch active flash banks");
+		return err;
+	}
+
+	if (emp_reset_available) {
+		if (hw->dev_caps.common_cap.reset_restrict_support)
+			*emp_reset_available =
+				response_flags & IXGBE_ACI_NVM_EMPR_ENA;
+		else
+			*emp_reset_available = true;
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_flash_component - Flash a component of the NVM
+ * @context: PLDM fw update structure
+ * @component: the component table to program
+ *
+ * Program the flash contents for a given component. First, determine the
+ * module id. Then, erase the secondary bank for this module. Finally, write
+ * the contents of the component to the NVM.
+ *
+ * Note this function assumes the caller has acquired the NVM resource.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_flash_component(struct pldmfw *context,
+				 struct pldmfw_component *component)
+{
+	struct ixgbe_fwu_priv *priv = container_of(context,
+						   struct ixgbe_fwu_priv,
+						   context);
+	struct netlink_ext_ack *extack = priv->extack;
+	struct ixgbe_adapter *adapter = priv->adapter;
+	const char *name;
+	u16 module;
+	int err;
+	u8 flag;
+
+	switch (component->identifier) {
+	case NVM_COMP_ID_OROM:
+		module = IXGBE_E610_SR_1ST_OROM_BANK_PTR;
+		flag = IXGBE_ACI_NVM_ACTIV_SEL_OROM;
+		name = "fw.undi";
+		break;
+	case NVM_COMP_ID_NVM:
+		module = IXGBE_E610_SR_1ST_NVM_BANK_PTR;
+		flag = IXGBE_ACI_NVM_ACTIV_SEL_NVM;
+		name = "fw.mgmt";
+		break;
+	case NVM_COMP_ID_NETLIST:
+		module = IXGBE_E610_SR_NETLIST_BANK_PTR;
+		flag = IXGBE_ACI_NVM_ACTIV_SEL_NETLIST;
+		name = "fw.netlist";
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/* Mark this component for activating at the end. */
+	priv->activate_flags |= flag;
+
+	err = ixgbe_erase_nvm_module(adapter, module, name, extack);
+	if (err)
+		return err;
+
+	return ixgbe_write_nvm_module(adapter, module, name,
+				      component->component_data,
+				      component->component_size, extack);
+}
+
+/**
+ * ixgbe_finalize_update - Perform last steps to complete device update
+ * @context: PLDM fw update structure
+ *
+ * Called as the last step of the update process. Complete the update by
+ * telling the firmware to switch active banks, and perform a reset of
+ * configured.
+ *
+ * Return: 0 on success, or an error code on failure.
+ */
+static int ixgbe_finalize_update(struct pldmfw *context)
+{
+	struct ixgbe_fwu_priv *priv = container_of(context,
+						   struct ixgbe_fwu_priv,
+						   context);
+	struct ixgbe_adapter *adapter = priv->adapter;
+	struct netlink_ext_ack *extack = priv->extack;
+	struct devlink *devlink = adapter->devlink;
+	int err;
+
+	/* Finally, notify firmware to activate the written NVM banks */
+	err = ixgbe_switch_flash_banks(adapter, priv->activate_flags,
+				       &priv->emp_reset_available, extack);
+	if (err)
+		return err;
+
+	adapter->fw_emp_reset_disabled = !priv->emp_reset_available;
+
+	if (!adapter->fw_emp_reset_disabled)
+		devlink_flash_update_status_notify(devlink,
+						   "Suggested is to activate new firmware by devlink reload, if it doesn't work then a power cycle is required",
+						   NULL, 0, 0);
+
+	return 0;
+}
+
+static const struct pldmfw_ops ixgbe_fwu_ops_e610 = {
+	.match_record = &pldmfw_op_pci_match_record,
+	.send_package_data = &ixgbe_send_package_data,
+	.send_component_table = &ixgbe_send_component_table,
+	.flash_component = &ixgbe_flash_component,
+	.finalize_update = &ixgbe_finalize_update,
+};
+
+/**
+ * ixgbe_get_pending_updates - Check if the component has a pending update
+ * @adapter: the PF driver structure
+ * @pending: on return, bitmap of updates pending
+ * @extack: Netlink extended ACK
+ *
+ * Check if the device has any pending updates on any flash components.
+ *
+ * Return: 0 on success, or a negative error code on failure. Update
+ * pending with the bitmap of pending updates.
+ */
+int ixgbe_get_pending_updates(struct ixgbe_adapter *adapter, u8 *pending,
+			      struct netlink_ext_ack *extack)
+{
+	struct ixgbe_hw_dev_caps *dev_caps;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	dev_caps = kzalloc(sizeof(*dev_caps), GFP_KERNEL);
+	if (!dev_caps)
+		return -ENOMEM;
+
+	err = ixgbe_discover_dev_caps(hw, dev_caps);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Unable to read device capabilities");
+		kfree(dev_caps);
+		return -EIO;
+	}
+
+	*pending = 0;
+
+	if (dev_caps->common_cap.nvm_update_pending_nvm)
+		*pending |= IXGBE_ACI_NVM_ACTIV_SEL_NVM;
+
+	if (dev_caps->common_cap.nvm_update_pending_orom)
+		*pending |= IXGBE_ACI_NVM_ACTIV_SEL_OROM;
+
+	if (dev_caps->common_cap.nvm_update_pending_netlist)
+		*pending |= IXGBE_ACI_NVM_ACTIV_SEL_NETLIST;
+
+	kfree(dev_caps);
+
+	return 0;
+}
+
+/**
+ * ixgbe_cancel_pending_update - Cancel any pending update for a component
+ * @adapter: the PF driver structure
+ * @component: if not NULL, the name of the component being updated
+ * @extack: Netlink extended ACK structure
+ *
+ * Cancel any pending update for the specified component. If component is
+ * NULL, all device updates will be canceled.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_cancel_pending_update(struct ixgbe_adapter *adapter,
+				       const char *component,
+				       struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = adapter->devlink;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 pending;
+	int err;
+
+	err = ixgbe_get_pending_updates(adapter, &pending, extack);
+	if (err)
+		return err;
+
+	/* If the flash_update request is for a specific component, ignore all
+	 * of the other components.
+	 */
+	if (component) {
+		if (strcmp(component, "fw.mgmt") == 0)
+			pending &= IXGBE_ACI_NVM_ACTIV_SEL_NVM;
+		else if (strcmp(component, "fw.undi") == 0)
+			pending &= IXGBE_ACI_NVM_ACTIV_SEL_OROM;
+		else if (strcmp(component, "fw.netlist") == 0)
+			pending &= IXGBE_ACI_NVM_ACTIV_SEL_NETLIST;
+		else
+			return -EINVAL;
+	}
+
+	/* There is no previous pending update, so this request may continue */
+	if (!pending)
+		return 0;
+
+	/* In order to allow overwriting a previous pending update, notify
+	 * firmware to cancel that update by issuing the appropriate command.
+	 */
+	devlink_flash_update_status_notify(devlink,
+					   "Canceling previous pending update",
+					   component, 0, 0);
+
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_WRITE);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to acquire device flash lock");
+		return -EIO;
+	}
+
+	pending |= IXGBE_ACI_NVM_REVERT_LAST_ACTIV;
+	err = ixgbe_switch_flash_banks(adapter, pending, NULL, extack);
+
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ixgbe_flash_pldm_image - Write a PLDM-formatted firmware image to the device
+ * @devlink: pointer to devlink associated with the device to update
+ * @params: devlink flash update parameters
+ * @extack: netlink extended ACK structure
+ *
+ * Parse the data for a given firmware file, verifying that it is a valid PLDM
+ * formatted image that matches this device.
+ *
+ * Extract the device record Package Data and Component Tables and send them
+ * to the firmware. Extract and write the flash data for each of the three
+ * main flash components, "fw.mgmt", "fw.undi", and "fw.netlist". Notify
+ * firmware once the data is written to the inactive banks.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int ixgbe_flash_pldm_image(struct devlink *devlink,
+			   struct devlink_flash_update_params *params,
+			   struct netlink_ext_ack *extack)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct device *dev = &adapter->pdev->dev;
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_fwu_priv priv;
+	u8 preservation;
+	int err;
+
+	if (hw->mac.type != ixgbe_mac_e610)
+		return -EOPNOTSUPP;
+
+	switch (params->overwrite_mask) {
+	case 0:
+		/* preserve all settings and identifiers */
+		preservation = IXGBE_ACI_NVM_PRESERVE_ALL;
+		break;
+	case DEVLINK_FLASH_OVERWRITE_SETTINGS:
+		/* Overwrite settings, but preserve vital information such as
+		 * device identifiers.
+		 */
+		preservation = IXGBE_ACI_NVM_PRESERVE_SELECTED;
+		break;
+	case (DEVLINK_FLASH_OVERWRITE_SETTINGS |
+	      DEVLINK_FLASH_OVERWRITE_IDENTIFIERS):
+		/* overwrite both settings and identifiers, preserve nothing */
+		preservation = IXGBE_ACI_NVM_NO_PRESERVATION;
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Requested overwrite mask is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	/* Cannot get caps in recovery mode, so lack of nvm_unified_update bit
+	 * cannot lead to error
+	 */
+	if (!hw->dev_caps.common_cap.nvm_unified_update &&
+	    (hw->mac.ops.fw_recovery_mode &&
+	     !hw->mac.ops.fw_recovery_mode(hw))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Current firmware does not support unified update");
+		return -EOPNOTSUPP;
+	}
+
+	memset(&priv, 0, sizeof(priv));
+
+	priv.context.ops = &ixgbe_fwu_ops_e610;
+	priv.context.dev = dev;
+	priv.extack = extack;
+	priv.adapter = adapter;
+	priv.activate_flags = preservation;
+
+	devlink_flash_update_status_notify(devlink,
+					   "Preparing to flash", NULL, 0, 0);
+
+	err = ixgbe_cancel_pending_update(adapter, NULL, extack);
+	if (err)
+		return err;
+
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_WRITE);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to acquire device flash lock");
+		return -EIO;
+	}
+
+	err = pldmfw_flash_image(&priv.context, params->fw);
+	if (err == -ENOENT) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Firmware image has no record matching this device");
+	} else if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to flash PLDM image");
+	}
+
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.h
new file mode 100644
index 000000000000..abdd708c93df
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2025 Intel Corporation. */
+
+#ifndef _IXGBE_FW_UPDATE_H_
+#define _IXGBE_FW_UPDATE_H_
+
+int ixgbe_flash_pldm_image(struct devlink *devlink,
+			   struct devlink_flash_update_params *params,
+			   struct netlink_ext_ack *extack);
+int ixgbe_get_pending_updates(struct ixgbe_adapter *adapter, u8 *pending,
+			      struct netlink_ext_ack *extack);
+#endif
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 866024f2b9ee..d1f4073b36f9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -9,7 +9,7 @@
 #define IXGBE_IPSEC_KEY_BITS  160
 static const char aes_gcm_name[] = "rfc4106(gcm(aes))";
 
-static void ixgbe_ipsec_del_sa(struct xfrm_state *xs);
+static void ixgbe_ipsec_del_sa(struct net_device *dev, struct xfrm_state *xs);
 
 /**
  * ixgbe_ipsec_set_tx_sa - set the Tx SA registers
@@ -321,7 +321,7 @@ void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter)
 
 		if (r->used) {
 			if (r->mode & IXGBE_RXTXMOD_VF)
-				ixgbe_ipsec_del_sa(r->xs);
+				ixgbe_ipsec_del_sa(adapter->netdev, r->xs);
 			else
 				ixgbe_ipsec_set_rx_sa(hw, i, r->xs->id.spi,
 						      r->key, r->salt,
@@ -330,7 +330,7 @@ void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter)
 
 		if (t->used) {
 			if (t->mode & IXGBE_RXTXMOD_VF)
-				ixgbe_ipsec_del_sa(t->xs);
+				ixgbe_ipsec_del_sa(adapter->netdev, t->xs);
 			else
 				ixgbe_ipsec_set_tx_sa(hw, i, t->key, t->salt);
 		}
@@ -417,6 +417,7 @@ static struct xfrm_state *ixgbe_ipsec_find_rx_state(struct ixgbe_ipsec *ipsec,
 
 /**
  * ixgbe_ipsec_parse_proto_keys - find the key and salt based on the protocol
+ * @dev: pointer to net device
  * @xs: pointer to xfrm_state struct
  * @mykey: pointer to key array to populate
  * @mysalt: pointer to salt value to populate
@@ -424,10 +425,10 @@ static struct xfrm_state *ixgbe_ipsec_find_rx_state(struct ixgbe_ipsec *ipsec,
  * This copies the protocol keys and salt to our own data tables.  The
  * 82599 family only supports the one algorithm.
  **/
-static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs,
+static int ixgbe_ipsec_parse_proto_keys(struct net_device *dev,
+					struct xfrm_state *xs,
 					u32 *mykey, u32 *mysalt)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	unsigned char *key_data;
 	char *alg_name = NULL;
 	int key_len;
@@ -473,12 +474,13 @@ static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs,
 
 /**
  * ixgbe_ipsec_check_mgmt_ip - make sure there is no clash with mgmt IP filters
+ * @dev: pointer to net device
  * @xs: pointer to transformer state struct
  **/
-static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs)
+static int ixgbe_ipsec_check_mgmt_ip(struct net_device *dev,
+				     struct xfrm_state *xs)
 {
-	struct net_device *dev = xs->xso.real_dev;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 mfval, manc, reg;
 	int num_filters = 4;
@@ -556,14 +558,15 @@ static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs)
 
 /**
  * ixgbe_ipsec_add_sa - program device with a security association
+ * @dev: pointer to device to program
  * @xs: pointer to transformer state struct
  * @extack: extack point to fill failure reason
  **/
-static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
+static int ixgbe_ipsec_add_sa(struct net_device *dev,
+			      struct xfrm_state *xs,
 			      struct netlink_ext_ack *extack)
 {
-	struct net_device *dev = xs->xso.real_dev;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct ixgbe_hw *hw = &adapter->hw;
 	int checked, match, first;
@@ -581,7 +584,7 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
 		return -EINVAL;
 	}
 
-	if (ixgbe_ipsec_check_mgmt_ip(xs)) {
+	if (ixgbe_ipsec_check_mgmt_ip(dev, xs)) {
 		NL_SET_ERR_MSG_MOD(extack, "IPsec IP addr clash with mgmt filters");
 		return -EINVAL;
 	}
@@ -615,7 +618,7 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
 			rsa.decrypt = xs->ealg || xs->aead;
 
 		/* get the key and salt */
-		ret = ixgbe_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt);
+		ret = ixgbe_ipsec_parse_proto_keys(dev, xs, rsa.key, &rsa.salt);
 		if (ret) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Rx SA table");
 			return ret;
@@ -724,7 +727,7 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
 		if (xs->id.proto & IPPROTO_ESP)
 			tsa.encrypt = xs->ealg || xs->aead;
 
-		ret = ixgbe_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt);
+		ret = ixgbe_ipsec_parse_proto_keys(dev, xs, tsa.key, &tsa.salt);
 		if (ret) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Tx SA table");
 			memset(&tsa, 0, sizeof(tsa));
@@ -752,12 +755,12 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
 
 /**
  * ixgbe_ipsec_del_sa - clear out this specific SA
+ * @dev: pointer to device to program
  * @xs: pointer to transformer state struct
  **/
-static void ixgbe_ipsec_del_sa(struct xfrm_state *xs)
+static void ixgbe_ipsec_del_sa(struct net_device *dev, struct xfrm_state *xs)
 {
-	struct net_device *dev = xs->xso.real_dev;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 zerobuf[4] = {0, 0, 0, 0};
@@ -817,30 +820,9 @@ static void ixgbe_ipsec_del_sa(struct xfrm_state *xs)
 	}
 }
 
-/**
- * ixgbe_ipsec_offload_ok - can this packet use the xfrm hw offload
- * @skb: current data packet
- * @xs: pointer to transformer state struct
- **/
-static bool ixgbe_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
-{
-	if (xs->props.family == AF_INET) {
-		/* Offload with IPv4 options is not supported yet */
-		if (ip_hdr(skb)->ihl != 5)
-			return false;
-	} else {
-		/* Offload with IPv6 extension headers is not support yet */
-		if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr))
-			return false;
-	}
-
-	return true;
-}
-
 static const struct xfrmdev_ops ixgbe_xfrmdev_ops = {
 	.xdo_dev_state_add = ixgbe_ipsec_add_sa,
 	.xdo_dev_state_delete = ixgbe_ipsec_del_sa,
-	.xdo_dev_offload_ok = ixgbe_ipsec_offload_ok,
 };
 
 /**
@@ -862,7 +844,8 @@ void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf)
 			continue;
 		if (ipsec->rx_tbl[i].mode & IXGBE_RXTXMOD_VF &&
 		    ipsec->rx_tbl[i].vf == vf)
-			ixgbe_ipsec_del_sa(ipsec->rx_tbl[i].xs);
+			ixgbe_ipsec_del_sa(adapter->netdev,
+					   ipsec->rx_tbl[i].xs);
 	}
 
 	/* search tx sa table */
@@ -871,7 +854,8 @@ void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf)
 			continue;
 		if (ipsec->tx_tbl[i].mode & IXGBE_RXTXMOD_VF &&
 		    ipsec->tx_tbl[i].vf == vf)
-			ixgbe_ipsec_del_sa(ipsec->tx_tbl[i].xs);
+			ixgbe_ipsec_del_sa(adapter->netdev,
+					   ipsec->tx_tbl[i].xs);
 	}
 }
 
@@ -951,7 +935,7 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 	memcpy(xs->aead->alg_name, aes_gcm_name, sizeof(aes_gcm_name));
 
 	/* set up the HW offload */
-	err = ixgbe_ipsec_add_sa(xs, NULL);
+	err = ixgbe_ipsec_add_sa(adapter->netdev, xs, NULL);
 	if (err)
 		goto err_aead;
 
@@ -1055,7 +1039,7 @@ int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 		xs = ipsec->tx_tbl[sa_idx].xs;
 	}
 
-	ixgbe_ipsec_del_sa(xs);
+	ixgbe_ipsec_del_sa(adapter->netdev, xs);
 
 	/* remove the xs that was made-up in the add request */
 	kfree_sensitive(xs);
@@ -1073,7 +1057,7 @@ int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring,
 		   struct ixgbe_tx_buffer *first,
 		   struct ixgbe_ipsec_tx_data *itd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(tx_ring->netdev);
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct xfrm_state *xs;
 	struct sec_path *sp;
@@ -1163,7 +1147,7 @@ void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring,
 		    union ixgbe_adv_rx_desc *rx_desc,
 		    struct sk_buff *skb)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(rx_ring->netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(rx_ring->netdev);
 	__le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
 	__le16 ipsec_pkt_types = cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH |
 					     IXGBE_RXDADV_PKTTYPE_IPSEC_ESP);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index 16fa621ce0ff..a1d04914fbbc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include "ixgbe.h"
 #include "ixgbe_sriov.h"
@@ -107,6 +107,7 @@ static void ixgbe_get_first_reg_idx(struct ixgbe_adapter *adapter, u8 tc,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		if (num_tcs > 4) {
 			/*
 			 * TCs    : TC0/1 TC2/3 TC4-7
@@ -317,7 +318,7 @@ static int ixgbe_xdp_queues(struct ixgbe_adapter *adapter)
  * ixgbe_set_dcb_sriov_queues: Allocate queues for SR-IOV devices w/ DCB
  * @adapter: board private structure to initialize
  *
- * When SR-IOV (Single Root IO Virtualiztion) is enabled, allocate queues
+ * When SR-IOV (Single Root IO Virtualization) is enabled, allocate queues
  * and VM pools where appropriate.  Also assign queues based on DCB
  * priorities and map accordingly..
  *
@@ -491,7 +492,7 @@ static bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter)
  * ixgbe_set_sriov_queues - Allocate queues for SR-IOV devices
  * @adapter: board private structure to initialize
  *
- * When SR-IOV (Single Root IO Virtualiztion) is enabled, allocate queues
+ * When SR-IOV (Single Root IO Virtualization) is enabled, allocate queues
  * and VM pools where appropriate.  If RSS is available, then also try and
  * enable RSS and map accordingly.
  *
@@ -890,7 +891,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 	q_vector->rx.itr = IXGBE_ITR_ADAPTIVE_MAX_USECS |
 			   IXGBE_ITR_ADAPTIVE_LATENCY;
 
-	/* intialize ITR */
+	/* initialize ITR */
 	if (txr_count && !rxr_count) {
 		/* tx only vector */
 		if (adapter->tx_itr_setting == 1)
@@ -1292,7 +1293,8 @@ void ixgbe_tx_ctxtdesc(struct ixgbe_ring *tx_ring, u32 vlan_macip_lens,
 	tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;
 
 	/* set bits to identify this as an advanced context descriptor */
-	type_tucmd |= IXGBE_TXD_CMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT;
+	type_tucmd |= IXGBE_TXD_CMD_DEXT |
+		FIELD_PREP(IXGBE_ADVTXD_DTYP_MASK, IXGBE_ADVTXD_DTYP_CTXT);
 
 	context_desc->vlan_macip_lens	= cpu_to_le32(vlan_macip_lens);
 	context_desc->fceof_saidx	= cpu_to_le32(fceof_saidx);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2e38e8f6fac1..034618e79169 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include <linux/types.h>
 #include <linux/module.h>
@@ -9,6 +9,7 @@
 #include <linux/string.h>
 #include <linux/in.h>
 #include <linux/interrupt.h>
+#include <linux/iopoll.h>
 #include <linux/ip.h>
 #include <linux/tcp.h>
 #include <linux/sctp.h>
@@ -42,12 +43,14 @@
 
 #include "ixgbe.h"
 #include "ixgbe_common.h"
+#include "ixgbe_e610.h"
 #include "ixgbe_dcb_82599.h"
 #include "ixgbe_mbx.h"
 #include "ixgbe_phy.h"
 #include "ixgbe_sriov.h"
 #include "ixgbe_model.h"
 #include "ixgbe_txrx_common.h"
+#include "devlink/devlink.h"
 
 char ixgbe_driver_name[] = "ixgbe";
 static const char ixgbe_driver_string[] =
@@ -73,6 +76,7 @@ static const struct ixgbe_info *ixgbe_info_tbl[] = {
 	[board_x550em_x_fw]	= &ixgbe_x550em_x_fw_info,
 	[board_x550em_a]	= &ixgbe_x550em_a_info,
 	[board_x550em_a_fw]	= &ixgbe_x550em_a_fw_info,
+	[board_e610]		= &ixgbe_e610_info,
 };
 
 /* ixgbe_pci_tbl - PCI Device ID Table
@@ -131,6 +135,11 @@ static const struct pci_device_id ixgbe_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP), board_x550em_a },
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T), board_x550em_a_fw },
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T_L), board_x550em_a_fw },
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_BACKPLANE), board_e610},
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_SFP), board_e610},
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_10G_T), board_e610},
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_2_5G_T), board_e610},
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_SGMII), board_e610},
 	/* required last entry */
 	{0, }
 };
@@ -163,6 +172,7 @@ static int debug = -1;
 module_param(debug, int, 0);
 MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
 
+MODULE_IMPORT_NS("LIBIE_FWLOG");
 MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver");
 MODULE_LICENSE("GPL v2");
 
@@ -173,6 +183,8 @@ static struct workqueue_struct *ixgbe_wq;
 
 static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev);
 static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *);
+static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *);
+static void ixgbe_watchdog_update_link(struct ixgbe_adapter *);
 
 static const struct net_device_ops ixgbe_netdev_ops;
 
@@ -236,8 +248,11 @@ static int ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter)
  * bandwidth details should be gathered from the parent bus instead of from the
  * device. Used to ensure that various locations all have the correct device ID
  * checks.
+ *
+ * Return: true if information should be collected from the parent bus, false
+ *         otherwise
  */
-static inline bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw)
+static bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw)
 {
 	switch (hw->device_id) {
 	case IXGBE_DEV_ID_82599_SFP_SF_QP:
@@ -876,6 +891,7 @@ static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		if (direction == -1) {
 			/* other causes */
 			msix_vector |= IXGBE_IVAR_ALLOC_VAL;
@@ -915,6 +931,7 @@ void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		mask = (qmask & 0xFFFFFFFF);
 		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(0), mask);
 		mask = (qmask >> 32);
@@ -952,10 +969,6 @@ static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter)
 	for (i = 0; i < adapter->num_tx_queues; i++)
 		clear_bit(__IXGBE_HANG_CHECK_ARMED,
 			  &adapter->tx_ring[i]->state);
-
-	for (i = 0; i < adapter->num_xdp_queues; i++)
-		clear_bit(__IXGBE_HANG_CHECK_ARMED,
-			  &adapter->xdp_ring[i]->state);
 }
 
 static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter)
@@ -1025,7 +1038,49 @@ static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring)
 	return ((head <= tail) ? tail : tail + ring->count) - head;
 }
 
-static inline bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring)
+/**
+ * ixgbe_get_vf_idx - provide VF index number based on queue index
+ * @adapter: pointer to the adapter struct
+ * @queue: Tx queue identifier
+ * @vf: output VF index
+ *
+ * Provide VF index number associated to the input queue.
+ *
+ * Returns: 0 if VF provided or error number.
+ */
+static int ixgbe_get_vf_idx(struct ixgbe_adapter *adapter, u16 queue, u16 *vf)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 queue_count;
+	u32 reg;
+
+	if (queue >= adapter->num_tx_queues)
+		return -EINVAL;
+
+	/* Determine number of queues by checking
+	 * number of virtual functions
+	 */
+	reg = IXGBE_READ_REG(hw, IXGBE_GCR_EXT);
+	switch (reg & IXGBE_GCR_EXT_VT_MODE_MASK) {
+	case IXGBE_GCR_EXT_VT_MODE_64:
+		queue_count = IXGBE_64VFS_QUEUES;
+		break;
+	case IXGBE_GCR_EXT_VT_MODE_32:
+		queue_count = IXGBE_32VFS_QUEUES;
+		break;
+	case IXGBE_GCR_EXT_VT_MODE_16:
+		queue_count = IXGBE_16VFS_QUEUES;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*vf = queue / queue_count;
+
+	return 0;
+}
+
+static bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring)
 {
 	u32 tx_done = ixgbe_get_tx_completed(tx_ring);
 	u32 tx_done_old = tx_ring->tx_stats.tx_done_old;
@@ -1081,7 +1136,7 @@ static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter)
 static int ixgbe_tx_maxrate(struct net_device *netdev,
 			    int queue_index, u32 maxrate)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 bcnrc_val = ixgbe_link_mbps(adapter);
 
@@ -1144,6 +1199,148 @@ void ixgbe_update_rx_ring_stats(struct ixgbe_ring *rx_ring,
 }
 
 /**
+ * ixgbe_pf_handle_tx_hang - handle Tx hang on PF
+ * @tx_ring: tx ring number
+ * @next: next ring
+ *
+ * Prints a message containing details about the tx hang.
+ */
+static void ixgbe_pf_handle_tx_hang(struct ixgbe_ring *tx_ring,
+				    unsigned int next)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	e_err(drv, "Detected Tx Unit Hang\n"
+		   "  Tx Queue             <%d>\n"
+		   "  TDH, TDT             <%x>, <%x>\n"
+		   "  next_to_use          <%x>\n"
+		   "  next_to_clean        <%x>\n"
+		   "tx_buffer_info[next_to_clean]\n"
+		   "  time_stamp           <%lx>\n"
+		   "  jiffies              <%lx>\n",
+	      tx_ring->queue_index,
+	      IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)),
+	      IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)),
+	      tx_ring->next_to_use, next,
+	      tx_ring->tx_buffer_info[next].time_stamp, jiffies);
+
+	netif_stop_subqueue(tx_ring->netdev,
+			    tx_ring->queue_index);
+}
+
+/**
+ * ixgbe_vf_handle_tx_hang - handle Tx hang on VF
+ * @adapter: structure containing ring specific data
+ * @vf: VF index
+ *
+ * Print a message containing details about malicious driver detection.
+ * Set malicious VF link down if the detection happened several times.
+ */
+static void ixgbe_vf_handle_tx_hang(struct ixgbe_adapter *adapter, u16 vf)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	if (adapter->hw.mac.type != ixgbe_mac_e610)
+		return;
+
+	e_warn(drv,
+	       "Malicious Driver Detection tx hang detected on PF %d VF %d MAC: %pM",
+	       hw->bus.func, vf, adapter->vfinfo[vf].vf_mac_addresses);
+
+	adapter->tx_hang_count[vf]++;
+	if (adapter->tx_hang_count[vf] == IXGBE_MAX_TX_VF_HANGS) {
+		ixgbe_set_vf_link_state(adapter, vf,
+					IFLA_VF_LINK_STATE_DISABLE);
+		adapter->tx_hang_count[vf] = 0;
+	}
+}
+
+static u32 ixgbe_poll_tx_icache(struct ixgbe_hw *hw, u16 queue, u16 idx)
+{
+	IXGBE_WRITE_REG(hw, IXGBE_TXDESCIC, queue * idx);
+	return IXGBE_READ_REG(hw, IXGBE_TXDESCIC);
+}
+
+/**
+ * ixgbe_check_illegal_queue - search for queue with illegal packet
+ * @adapter: structure containing ring specific data
+ * @queue: queue index
+ *
+ * Check if tx descriptor connected with input queue
+ * contains illegal packet.
+ *
+ * Returns: true if queue contain illegal packet.
+ */
+static bool ixgbe_check_illegal_queue(struct ixgbe_adapter *adapter,
+				      u16 queue)
+{
+	u32 hdr_len_reg, mss_len_reg, type_reg;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 mss_len, header_len, reg;
+
+	for (u16 i = 0; i < IXGBE_MAX_TX_DESCRIPTORS; i++) {
+		/* HW will clear bit IXGBE_TXDESCIC_READY when address
+		 * is written to address field. HW will set this bit
+		 * when iCache read is done, and data is ready at TIC_DWx.
+		 * Set descriptor address.
+		 */
+		read_poll_timeout(ixgbe_poll_tx_icache, reg,
+				  !(reg & IXGBE_TXDESCIC_READY), 0, 0, false,
+				  hw, queue, i);
+
+		/* read tx descriptor access registers */
+		hdr_len_reg = IXGBE_READ_REG(hw, IXGBE_TIC_DW2(IXGBE_VLAN_MACIP_LENS_REG));
+		type_reg = IXGBE_READ_REG(hw, IXGBE_TIC_DW2(IXGBE_TYPE_TUCMD_MLHL));
+		mss_len_reg = IXGBE_READ_REG(hw, IXGBE_TIC_DW2(IXGBE_MSS_L4LEN_IDX));
+
+		/* check if Advanced Context Descriptor */
+		if (FIELD_GET(IXGBE_ADVTXD_DTYP_MASK, type_reg) !=
+		    IXGBE_ADVTXD_DTYP_CTXT)
+			continue;
+
+		/* check for illegal MSS and Header length */
+		mss_len = FIELD_GET(IXGBE_ADVTXD_MSS_MASK, mss_len_reg);
+		header_len = FIELD_GET(IXGBE_ADVTXD_HEADER_LEN_MASK,
+				       hdr_len_reg);
+		if ((mss_len + header_len) > SZ_16K) {
+			e_warn(probe, "mss len + header len too long\n");
+			return true;
+		}
+	}
+
+	return false;
+}
+
+/**
+ * ixgbe_handle_mdd_event - handle mdd event
+ * @adapter: structure containing ring specific data
+ * @tx_ring: tx descriptor ring to handle
+ *
+ * Reset VF driver if malicious vf detected or
+ * illegal packet in an any queue detected.
+ */
+static void ixgbe_handle_mdd_event(struct ixgbe_adapter *adapter,
+				   struct ixgbe_ring *tx_ring)
+{
+	u16 vf, q;
+
+	if (adapter->vfinfo && ixgbe_check_mdd_event(adapter)) {
+		/* vf mdd info and malicious vf detected */
+		if (!ixgbe_get_vf_idx(adapter, tx_ring->queue_index, &vf))
+			ixgbe_vf_handle_tx_hang(adapter, vf);
+	} else {
+		/* malicious vf not detected */
+		for (q = 0; q < IXGBE_MAX_TX_QUEUES; q++) {
+			if (ixgbe_check_illegal_queue(adapter, q) &&
+			    !ixgbe_get_vf_idx(adapter, q, &vf))
+				/* illegal queue detected */
+				ixgbe_vf_handle_tx_hang(adapter, vf);
+		}
+	}
+}
+
+/**
  * ixgbe_clean_tx_irq - Reclaim resources after transmit completes
  * @q_vector: structure containing interrupt and ring information
  * @tx_ring: tx ring to clean
@@ -1249,27 +1446,14 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 				   total_bytes);
 	adapter->tx_ipsec += total_ipsec;
 
+	if (ring_is_xdp(tx_ring))
+		return !!budget;
+
 	if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) {
-		/* schedule immediate reset if we believe we hung */
-		struct ixgbe_hw *hw = &adapter->hw;
-		e_err(drv, "Detected Tx Unit Hang %s\n"
-			"  Tx Queue             <%d>\n"
-			"  TDH, TDT             <%x>, <%x>\n"
-			"  next_to_use          <%x>\n"
-			"  next_to_clean        <%x>\n"
-			"tx_buffer_info[next_to_clean]\n"
-			"  time_stamp           <%lx>\n"
-			"  jiffies              <%lx>\n",
-			ring_is_xdp(tx_ring) ? "(XDP)" : "",
-			tx_ring->queue_index,
-			IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)),
-			IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)),
-			tx_ring->next_to_use, i,
-			tx_ring->tx_buffer_info[i].time_stamp, jiffies);
-
-		if (!ring_is_xdp(tx_ring))
-			netif_stop_subqueue(tx_ring->netdev,
-					    tx_ring->queue_index);
+		if (adapter->hw.mac.type == ixgbe_mac_e610)
+			ixgbe_handle_mdd_event(adapter, tx_ring);
+
+		ixgbe_pf_handle_tx_hang(tx_ring, i);
 
 		e_info(probe,
 		       "tx hang %d detected on queue %d, resetting adapter\n",
@@ -1282,9 +1466,6 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 		return true;
 	}
 
-	if (ring_is_xdp(tx_ring))
-		return !!budget;
-
 #define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
 	txq = netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index);
 	if (!__netif_txq_completed_wake(txq, total_packets, total_bytes,
@@ -1909,10 +2090,6 @@ bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
 {
 	struct net_device *netdev = rx_ring->netdev;
 
-	/* XDP packets use error pointer so abort at this point */
-	if (IS_ERR(skb))
-		return true;
-
 	/* Verify netdev is present, and that packet does not have any
 	 * errors that would be unacceptable to the netdev.
 	 */
@@ -2095,7 +2272,7 @@ static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring,
 		/* hand second half of page back to the ring */
 		ixgbe_reuse_rx_page(rx_ring, rx_buffer);
 	} else {
-		if (!IS_ERR(skb) && IXGBE_CB(skb)->dma == rx_buffer->dma) {
+		if (skb && IXGBE_CB(skb)->dma == rx_buffer->dma) {
 			/* the page has been released from the ring */
 			IXGBE_CB(skb)->page_released = true;
 		} else {
@@ -2189,7 +2366,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 	struct sk_buff *skb;
 
 	/* Prefetch first cache line of first page. If xdp->data_meta
-	 * is unused, this points extactly as xdp->data, otherwise we
+	 * is unused, this points exactly as xdp->data, otherwise we
 	 * likely have a consumer accessing first few bytes of meta
 	 * data, and then actual data.
 	 */
@@ -2220,9 +2397,9 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 	return skb;
 }
 
-static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
-				     struct ixgbe_ring *rx_ring,
-				     struct xdp_buff *xdp)
+static int ixgbe_run_xdp(struct ixgbe_adapter *adapter,
+			 struct ixgbe_ring *rx_ring,
+			 struct xdp_buff *xdp)
 {
 	int err, result = IXGBE_XDP_PASS;
 	struct bpf_prog *xdp_prog;
@@ -2272,7 +2449,7 @@ out_failure:
 		break;
 	}
 xdp_out:
-	return ERR_PTR(-result);
+	return result;
 }
 
 static unsigned int ixgbe_rx_frame_truesize(struct ixgbe_ring *rx_ring,
@@ -2312,7 +2489,7 @@ static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring,
  * This function provides a "bounce buffer" approach to Rx interrupt
  * processing.  The advantage to this is that on systems that have
  * expensive overhead for IOMMU access this provides a means of avoiding
- * it by maintaining the mapping of the page to the syste.
+ * it by maintaining the mapping of the page to the system.
  *
  * Returns amount of work completed
  **/
@@ -2330,6 +2507,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 	unsigned int offset = rx_ring->rx_offset;
 	unsigned int xdp_xmit = 0;
 	struct xdp_buff xdp;
+	int xdp_res = 0;
 
 	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
 #if (PAGE_SIZE < 8192)
@@ -2375,12 +2553,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 			/* At larger PAGE_SIZE, frame_sz depend on len size */
 			xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, size);
 #endif
-			skb = ixgbe_run_xdp(adapter, rx_ring, &xdp);
+			xdp_res = ixgbe_run_xdp(adapter, rx_ring, &xdp);
 		}
 
-		if (IS_ERR(skb)) {
-			unsigned int xdp_res = -PTR_ERR(skb);
-
+		if (xdp_res) {
 			if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
 				xdp_xmit |= xdp_res;
 				ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size);
@@ -2400,7 +2576,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		}
 
 		/* exit if we failed to retrieve a buffer */
-		if (!skb) {
+		if (!xdp_res && !skb) {
 			rx_ring->rx_stats.alloc_rx_buff_failed++;
 			rx_buffer->pagecnt_bias++;
 			break;
@@ -2414,7 +2590,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 			continue;
 
 		/* verify the packet layout is correct */
-		if (ixgbe_cleanup_headers(rx_ring, rx_desc, skb))
+		if (xdp_res || ixgbe_cleanup_headers(rx_ring, rx_desc, skb))
 			continue;
 
 		/* probably a little skewed due to removing CRC */
@@ -2515,6 +2691,7 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		ixgbe_set_ivar(adapter, -1, 1, v_idx);
 		break;
 	default:
@@ -2528,6 +2705,9 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
 		  IXGBE_EIMS_MAILBOX |
 		  IXGBE_EIMS_LSC);
 
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		mask &= ~IXGBE_EIMS_FW_EVENT;
+
 	IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIAC, mask);
 }
 
@@ -2744,6 +2924,7 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		/*
 		 * set the WDIS bit to not clear the timer bits and cause an
 		 * immediate assertion of the interrupt
@@ -2966,6 +3147,226 @@ static void ixgbe_check_lsc(struct ixgbe_adapter *adapter)
 	}
 }
 
+/**
+ * ixgbe_check_phy_fw_load - check if PHY FW load failed
+ * @adapter: pointer to adapter structure
+ * @link_cfg_err: bitmap from the link info structure
+ *
+ * Check if external PHY FW load failed and print an error message if it did.
+ */
+static void ixgbe_check_phy_fw_load(struct ixgbe_adapter *adapter,
+				    u8 link_cfg_err)
+{
+	if (!(link_cfg_err & IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE)) {
+		adapter->flags2 &= ~IXGBE_FLAG2_PHY_FW_LOAD_FAILED;
+		return;
+	}
+
+	if (adapter->flags2 & IXGBE_FLAG2_PHY_FW_LOAD_FAILED)
+		return;
+
+	if (link_cfg_err & IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE) {
+		netdev_err(adapter->netdev, "Device failed to load the FW for the external PHY. Please download and install the latest NVM for your device and try again\n");
+		adapter->flags2 |= IXGBE_FLAG2_PHY_FW_LOAD_FAILED;
+	}
+}
+
+/**
+ * ixgbe_check_module_power - check module power level
+ * @adapter: pointer to adapter structure
+ * @link_cfg_err: bitmap from the link info structure
+ *
+ * Check module power level returned by a previous call to aci_get_link_info
+ * and print error messages if module power level is not supported.
+ */
+static void ixgbe_check_module_power(struct ixgbe_adapter *adapter,
+				     u8 link_cfg_err)
+{
+	/* If module power level is supported, clear the flag. */
+	if (!(link_cfg_err & (IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT |
+			      IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED))) {
+		adapter->flags2 &= ~IXGBE_FLAG2_MOD_POWER_UNSUPPORTED;
+		return;
+	}
+
+	/* If IXGBE_FLAG2_MOD_POWER_UNSUPPORTED was previously set and the
+	 * above block didn't clear this bit, there's nothing to do.
+	 */
+	if (adapter->flags2 & IXGBE_FLAG2_MOD_POWER_UNSUPPORTED)
+		return;
+
+	if (link_cfg_err & IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT) {
+		netdev_err(adapter->netdev, "The installed module is incompatible with the device's NVM image. Cannot start link.\n");
+		adapter->flags2 |= IXGBE_FLAG2_MOD_POWER_UNSUPPORTED;
+	} else if (link_cfg_err & IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED) {
+		netdev_err(adapter->netdev, "The module's power requirements exceed the device's power supply. Cannot start link.\n");
+		adapter->flags2 |= IXGBE_FLAG2_MOD_POWER_UNSUPPORTED;
+	}
+}
+
+/**
+ * ixgbe_check_link_cfg_err - check if link configuration failed
+ * @adapter: pointer to adapter structure
+ * @link_cfg_err: bitmap from the link info structure
+ *
+ * Print if any link configuration failure happens due to the value in the
+ * link_cfg_err parameter in the link info structure.
+ */
+static void ixgbe_check_link_cfg_err(struct ixgbe_adapter *adapter,
+				     u8 link_cfg_err)
+{
+	ixgbe_check_module_power(adapter, link_cfg_err);
+	ixgbe_check_phy_fw_load(adapter, link_cfg_err);
+}
+
+/**
+ * ixgbe_process_link_status_event - process the link event
+ * @adapter: pointer to adapter structure
+ * @link_up: true if the physical link is up and false if it is down
+ * @link_speed: current link speed received from the link event
+ *
+ * Return: 0 on success or negative value on failure.
+ */
+static int
+ixgbe_process_link_status_event(struct ixgbe_adapter *adapter, bool link_up,
+				u16 link_speed)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int status;
+
+	/* Update the link info structures and re-enable link events,
+	 * don't bail on failure due to other book keeping needed.
+	 */
+	status = ixgbe_update_link_info(hw);
+	if (status)
+		e_dev_err("Failed to update link status, err %d aq_err %d\n",
+			  status, hw->aci.last_status);
+
+	ixgbe_check_link_cfg_err(adapter, hw->link.link_info.link_cfg_err);
+
+	/* Check if the link state is up after updating link info, and treat
+	 * this event as an UP event since the link is actually UP now.
+	 */
+	if (hw->link.link_info.link_info & IXGBE_ACI_LINK_UP)
+		link_up = true;
+
+	/* Turn off PHY if media was removed. */
+	if (!(adapter->flags2 & IXGBE_FLAG2_NO_MEDIA) &&
+	    !(hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE))
+		adapter->flags2 |= IXGBE_FLAG2_NO_MEDIA;
+
+	if (link_up == adapter->link_up &&
+	    link_up == netif_carrier_ok(adapter->netdev) &&
+	    link_speed == adapter->link_speed)
+		return 0;
+
+	adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
+	adapter->link_check_timeout = jiffies;
+	ixgbe_watchdog_update_link(adapter);
+
+	if (link_up)
+		ixgbe_watchdog_link_is_up(adapter);
+	else
+		ixgbe_watchdog_link_is_down(adapter);
+
+	return 0;
+}
+
+/**
+ * ixgbe_handle_link_status_event - handle link status event via ACI
+ * @adapter: pointer to adapter structure
+ * @e: event structure containing link status info
+ */
+static void
+ixgbe_handle_link_status_event(struct ixgbe_adapter *adapter,
+			       struct ixgbe_aci_event *e)
+{
+	struct ixgbe_aci_cmd_get_link_status_data *link_data;
+	u16 link_speed;
+	bool link_up;
+
+	link_data = (struct ixgbe_aci_cmd_get_link_status_data *)e->msg_buf;
+
+	link_up = !!(link_data->link_info & IXGBE_ACI_LINK_UP);
+	link_speed = le16_to_cpu(link_data->link_speed);
+
+	if (ixgbe_process_link_status_event(adapter, link_up, link_speed))
+		e_dev_warn("Could not process link status event");
+}
+
+/**
+ * ixgbe_schedule_fw_event - schedule Firmware event
+ * @adapter: pointer to the adapter structure
+ *
+ * If the adapter is not in down, removing or resetting state,
+ * an event is scheduled.
+ */
+static void ixgbe_schedule_fw_event(struct ixgbe_adapter *adapter)
+{
+	if (!test_bit(__IXGBE_DOWN, &adapter->state) &&
+	    !test_bit(__IXGBE_REMOVING, &adapter->state) &&
+	    !test_bit(__IXGBE_RESETTING, &adapter->state)) {
+		adapter->flags2 |= IXGBE_FLAG2_FW_ASYNC_EVENT;
+		ixgbe_service_event_schedule(adapter);
+	}
+}
+
+/**
+ * ixgbe_aci_event_cleanup - release msg_buf memory
+ * @event: pointer to the event holding msg_buf to be released
+ *
+ * Clean memory allocated for event's msg_buf. Implements auto memory cleanup.
+ */
+static void ixgbe_aci_event_cleanup(struct ixgbe_aci_event *event)
+{
+	kfree(event->msg_buf);
+}
+
+/**
+ * ixgbe_handle_fw_event - handle Firmware event
+ * @adapter: pointer to the adapter structure
+ *
+ * Obtain an event from the ACI and then and then process it according to the
+ * type of the event and the opcode.
+ */
+static void ixgbe_handle_fw_event(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_aci_event event __cleanup(ixgbe_aci_event_cleanup);
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool pending = false;
+	int err;
+
+	if (adapter->flags2 & IXGBE_FLAG2_FW_ASYNC_EVENT)
+		adapter->flags2 &= ~IXGBE_FLAG2_FW_ASYNC_EVENT;
+	event.buf_len = IXGBE_ACI_MAX_BUFFER_SIZE;
+	event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
+	if (!event.msg_buf)
+		return;
+
+	do {
+		err = ixgbe_aci_get_event(hw, &event, &pending);
+		if (err)
+			break;
+
+		switch (le16_to_cpu(event.desc.opcode)) {
+		case ixgbe_aci_opc_get_link_status:
+			ixgbe_handle_link_status_event(adapter, &event);
+			break;
+		case ixgbe_aci_opc_temp_tca_event:
+			e_crit(drv, "%s\n", ixgbe_overheat_msg);
+			ixgbe_down(adapter);
+			break;
+		case libie_aqc_opc_fw_logs_event:
+			libie_get_fwlog_data(&hw->fwlog, event.msg_buf,
+					     le16_to_cpu(event.desc.datalen));
+			break;
+		default:
+			e_warn(hw, "unknown FW async event captured\n");
+			break;
+		}
+	} while (pending);
+}
+
 static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter,
 					   u64 qmask)
 {
@@ -2982,6 +3383,7 @@ static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		mask = (qmask & 0xFFFFFFFF);
 		if (mask)
 			IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask);
@@ -3035,6 +3437,9 @@ static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues,
 	case ixgbe_mac_X540:
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
+	case ixgbe_mac_e610:
+		mask |= IXGBE_EIMS_FW_EVENT;
+		fallthrough;
 	case ixgbe_mac_x550em_a:
 		if (adapter->hw.device_id == IXGBE_DEV_ID_X550EM_X_SFP ||
 		    adapter->hw.device_id == IXGBE_DEV_ID_X550EM_A_SFP ||
@@ -3091,12 +3496,16 @@ static irqreturn_t ixgbe_msix_other(int irq, void *data)
 	if (eicr & IXGBE_EICR_MAILBOX)
 		ixgbe_msg_task(adapter);
 
+	if (eicr & IXGBE_EICR_FW_EVENT)
+		ixgbe_schedule_fw_event(adapter);
+
 	switch (hw->mac.type) {
 	case ixgbe_mac_82599EB:
 	case ixgbe_mac_X540:
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		if (hw->phy.type == ixgbe_phy_x550em_ext_t &&
 		    (eicr & IXGBE_EICR_GPI_SDP0_X540)) {
 			adapter->flags2 |= IXGBE_FLAG2_PHY_INTERRUPT;
@@ -3334,6 +3743,9 @@ static irqreturn_t ixgbe_intr(int irq, void *data)
 	if (eicr & IXGBE_EICR_LSC)
 		ixgbe_check_lsc(adapter);
 
+	if (eicr & IXGBE_EICR_FW_EVENT)
+		ixgbe_schedule_fw_event(adapter);
+
 	switch (hw->mac.type) {
 	case ixgbe_mac_82599EB:
 		ixgbe_check_sfp_event(adapter, eicr);
@@ -3342,6 +3754,7 @@ static irqreturn_t ixgbe_intr(int irq, void *data)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		if (eicr & IXGBE_EICR_ECC) {
 			e_info(link, "Received ECC Err, initiating reset\n");
 			set_bit(__IXGBE_RESET_REQUESTED, &adapter->state);
@@ -3442,6 +3855,7 @@ static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, 0xFFFF0000);
 		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(0), ~0);
 		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(1), ~0);
@@ -3689,8 +4103,12 @@ void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter)
 static void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter)
 #endif
 {
-	int i;
 	bool pfc_en = adapter->dcb_cfg.pfc_mode_enable;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i;
+
+	if (hw->mac.ops.disable_mdd)
+		hw->mac.ops.disable_mdd(hw);
 
 	if (adapter->ixgbe_ieee_pfc)
 		pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en);
@@ -3712,6 +4130,9 @@ static void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter)
 		for (i = 0; i < adapter->num_rx_queues; i++)
 			ixgbe_disable_rx_drop(adapter, adapter->rx_ring[i]);
 	}
+
+	if (hw->mac.ops.enable_mdd)
+		hw->mac.ops.enable_mdd(hw);
 }
 
 #define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT 2
@@ -4359,6 +4780,7 @@ static void ixgbe_setup_rdrxctl(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		if (adapter->num_vfs)
 			rdrxctl |= IXGBE_RDRXCTL_PSP;
 		fallthrough;
@@ -4434,7 +4856,7 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter)
 static int ixgbe_vlan_rx_add_vid(struct net_device *netdev,
 				 __be16 proto, u16 vid)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	/* add VID to filter table */
@@ -4493,7 +4915,7 @@ void ixgbe_update_pf_promisc_vlvf(struct ixgbe_adapter *adapter, u32 vid)
 static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev,
 				  __be16 proto, u16 vid)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	/* remove VID from filter table */
@@ -4526,6 +4948,7 @@ static void ixgbe_vlan_strip_disable(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		for (i = 0; i < adapter->num_rx_queues; i++) {
 			struct ixgbe_ring *ring = adapter->rx_ring[i];
 
@@ -4564,6 +4987,7 @@ static void ixgbe_vlan_strip_enable(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		for (i = 0; i < adapter->num_rx_queues; i++) {
 			struct ixgbe_ring *ring = adapter->rx_ring[i];
 
@@ -4638,7 +5062,7 @@ static void ixgbe_scrub_vfta(struct ixgbe_adapter *adapter, u32 vfta_offset)
 		/* pull VLAN ID from VLVF */
 		vid = vlvf & VLAN_VID_MASK;
 
-		/* only concern outselves with a certain range */
+		/* only concern ourselves with a certain range */
 		if (vid < vid_start || vid >= vid_end)
 			continue;
 
@@ -4716,7 +5140,7 @@ static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter)
  **/
 static int ixgbe_write_mc_addr_list(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (!netif_running(netdev))
@@ -4892,7 +5316,7 @@ int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter,
 
 static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int ret;
 
 	ret = ixgbe_add_mac_filter(adapter, addr, VMDQ_P(0));
@@ -4902,7 +5326,7 @@ static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr)
 
 static int ixgbe_uc_unsync(struct net_device *netdev, const unsigned char *addr)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	ixgbe_del_mac_filter(adapter, addr, VMDQ_P(0));
 
@@ -4920,7 +5344,7 @@ static int ixgbe_uc_unsync(struct net_device *netdev, const unsigned char *addr)
  **/
 void ixgbe_set_rx_mode(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 fctrl, vmolr = IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE;
 	netdev_features_t features = netdev->features;
@@ -5022,7 +5446,7 @@ static void ixgbe_napi_disable_all(struct ixgbe_adapter *adapter)
 
 static int ixgbe_udp_tunnel_sync(struct net_device *dev, unsigned int table)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct udp_tunnel_info ti;
 
@@ -5148,6 +5572,7 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		dv_id = IXGBE_DV_X540(link, tc);
 		break;
 	default:
@@ -5208,6 +5633,7 @@ static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		dv_id = IXGBE_LOW_DV_X540(tc);
 		break;
 	default:
@@ -5510,6 +5936,48 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter)
 }
 
 /**
+ * ixgbe_enable_link_status_events - enable link status events
+ * @adapter: pointer to the adapter structure
+ * @mask: event mask to be set
+ *
+ * Enables link status events by invoking ixgbe_configure_lse()
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_enable_link_status_events(struct ixgbe_adapter *adapter,
+					   u16 mask)
+{
+	int err;
+
+	err = ixgbe_configure_lse(&adapter->hw, true, mask);
+	if (err)
+		return err;
+
+	adapter->lse_mask = mask;
+	return 0;
+}
+
+/**
+ * ixgbe_disable_link_status_events - disable link status events
+ * @adapter: pointer to the adapter structure
+ *
+ * Disables link status events by invoking ixgbe_configure_lse()
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_disable_link_status_events(struct ixgbe_adapter *adapter)
+{
+	int err;
+
+	err = ixgbe_configure_lse(&adapter->hw, false, adapter->lse_mask);
+	if (err)
+		return err;
+
+	adapter->lse_mask = 0;
+	return 0;
+}
+
+/**
  * ixgbe_sfp_link_config - set up SFP+ link
  * @adapter: pointer to private adapter struct
  **/
@@ -5532,13 +6000,21 @@ static void ixgbe_sfp_link_config(struct ixgbe_adapter *adapter)
  * ixgbe_non_sfp_link_config - set up non-SFP+ link
  * @hw: pointer to private hardware struct
  *
- * Returns 0 on success, negative on failure
+ * Configure non-SFP link.
+ *
+ * Return: 0 on success, negative on failure
  **/
 static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw)
 {
-	u32 speed;
+	struct ixgbe_adapter *adapter = container_of(hw, struct ixgbe_adapter,
+						     hw);
+	u16 mask = ~((u16)(IXGBE_ACI_LINK_EVENT_UPDOWN |
+			   IXGBE_ACI_LINK_EVENT_MEDIA_NA |
+			   IXGBE_ACI_LINK_EVENT_MODULE_QUAL_FAIL |
+			   IXGBE_ACI_LINK_EVENT_PHY_FW_LOAD_FAIL));
 	bool autoneg, link_up = false;
 	int ret = -EIO;
+	u32 speed;
 
 	if (hw->mac.ops.check_link)
 		ret = hw->mac.ops.check_link(hw, &speed, &link_up, false);
@@ -5561,13 +6037,53 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw)
 	if (ret)
 		return ret;
 
-	if (hw->mac.ops.setup_link)
+	if (hw->mac.ops.setup_link) {
+		if (adapter->hw.mac.type == ixgbe_mac_e610) {
+			ret = ixgbe_enable_link_status_events(adapter, mask);
+			if (ret)
+				return ret;
+		}
 		ret = hw->mac.ops.setup_link(hw, speed, link_up);
+	}
 
 	return ret;
 }
 
 /**
+ * ixgbe_check_media_subtask - check for media
+ * @adapter: pointer to adapter structure
+ *
+ * If media is available then initialize PHY user configuration. Configure the
+ * PHY if the interface is up.
+ */
+static void ixgbe_check_media_subtask(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	/* No need to check for media if it's already present */
+	if (!(adapter->flags2 & IXGBE_FLAG2_NO_MEDIA))
+		return;
+
+	/* Refresh link info and check if media is present */
+	if (ixgbe_update_link_info(hw))
+		return;
+
+	ixgbe_check_link_cfg_err(adapter, hw->link.link_info.link_cfg_err);
+
+	if (hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE) {
+		/* PHY settings are reset on media insertion, reconfigure
+		 * PHY to preserve settings.
+		 */
+		if (!(ixgbe_non_sfp_link_config(&adapter->hw)))
+			adapter->flags2 &= ~IXGBE_FLAG2_NO_MEDIA;
+
+		/* A Link Status Event will be generated; the event handler
+		 * will complete bringing the interface up
+		 */
+	}
+}
+
+/**
  * ixgbe_clear_vf_stats_counters - Clear out VF stats after reset
  * @adapter: board private structure
  *
@@ -5630,6 +6146,7 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter)
 		case ixgbe_mac_X550:
 		case ixgbe_mac_X550EM_x:
 		case ixgbe_mac_x550em_a:
+		case ixgbe_mac_e610:
 		default:
 			IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(0), 0xFFFFFFFF);
 			IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(1), 0xFFFFFFFF);
@@ -5980,6 +6497,7 @@ dma_engine_disable:
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL,
 				(IXGBE_READ_REG(hw, IXGBE_DMATXCTL) &
 				 ~IXGBE_DMATXCTL_TE));
@@ -6198,7 +6716,7 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 	adapter->flags2 &= ~IXGBE_FLAG2_FDIR_REQUIRES_REINIT;
 	adapter->flags &= ~IXGBE_FLAG_NEED_LINK_UPDATE;
 
-	del_timer_sync(&adapter->service_timer);
+	timer_delete_sync(&adapter->service_timer);
 
 	if (adapter->num_vfs) {
 		/* Clear EITR Select mapping */
@@ -6224,6 +6742,8 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 
 	ixgbe_clean_all_tx_rings(adapter);
 	ixgbe_clean_all_rx_rings(adapter);
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		ixgbe_disable_link_status_events(adapter);
 }
 
 /**
@@ -6258,7 +6778,7 @@ static void ixgbe_set_eee_capable(struct ixgbe_adapter *adapter)
  **/
 static void ixgbe_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* Do the reset outside of interrupt context */
 	ixgbe_tx_timeout_reset(adapter);
@@ -6279,6 +6799,7 @@ static void ixgbe_init_dcb(struct ixgbe_adapter *adapter)
 		break;
 	case ixgbe_mac_X540:
 	case ixgbe_mac_X550:
+	case ixgbe_mac_e610:
 		adapter->dcb_cfg.num_tcs.pg_tcs = X540_TRAFFIC_CLASS;
 		adapter->dcb_cfg.num_tcs.pfc_tcs = X540_TRAFFIC_CLASS;
 		break;
@@ -6342,6 +6863,8 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
 	hw->subsystem_vendor_id = pdev->subsystem_vendor;
 	hw->subsystem_device_id = pdev->subsystem_device;
 
+	hw->mac.max_link_up_time = IXGBE_LINK_UP_TIME;
+
 	/* get_invariants needs the device IDs */
 	ii->get_invariants(hw);
 
@@ -6455,6 +6978,13 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
 		break;
 	}
 
+	/* Make sure the SWFW semaphore is in a valid state */
+	if (hw->mac.ops.init_swfw_sync)
+		hw->mac.ops.init_swfw_sync(hw);
+
+	if (hw->mac.type == ixgbe_mac_e610)
+		mutex_init(&hw->aci.lock);
+
 #ifdef IXGBE_FCOE
 	/* FCoE support exists, always init the FCoE lock */
 	spin_lock_init(&adapter->fcoe.lock);
@@ -6504,7 +7034,7 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
 	adapter->tx_work_limit = IXGBE_DEFAULT_TX_WORK;
 
 	/* initialize eeprom parameters */
-	if (ixgbe_init_eeprom_params_generic(hw)) {
+	if (hw->eeprom.ops.init_params(hw)) {
 		e_dev_err("EEPROM initialization failed\n");
 		return -EIO;
 	}
@@ -6820,7 +7350,7 @@ static int ixgbe_max_xdp_frame_size(struct ixgbe_adapter *adapter)
  **/
 static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (ixgbe_enabled_xdp_adapter(adapter)) {
 		int new_frame_size = new_mtu + IXGBE_PKT_HDR_PAD;
@@ -6867,7 +7397,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
  **/
 int ixgbe_open(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	int err, queues;
 
@@ -6909,6 +7439,19 @@ int ixgbe_open(struct net_device *netdev)
 	ixgbe_up_complete(adapter);
 
 	udp_tunnel_nic_reset_ntf(netdev);
+	if (adapter->hw.mac.type == ixgbe_mac_e610) {
+		int err = ixgbe_update_link_info(&adapter->hw);
+
+		if (err)
+			e_dev_err("Failed to update link info, err %d.\n", err);
+
+		ixgbe_check_link_cfg_err(adapter,
+					 adapter->hw.link.link_info.link_cfg_err);
+
+		err = ixgbe_non_sfp_link_config(&adapter->hw);
+		if (err)
+			e_dev_err("Link setup failed, err %d.\n", err);
+	}
 
 	return 0;
 
@@ -6958,7 +7501,7 @@ static void ixgbe_close_suspend(struct ixgbe_adapter *adapter)
  **/
 int ixgbe_close(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	ixgbe_ptp_stop(adapter);
 
@@ -7062,6 +7605,7 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		pci_wake_from_d3(pdev, !!wufc);
 		break;
 	default:
@@ -7209,6 +7753,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 		case ixgbe_mac_X550:
 		case ixgbe_mac_X550EM_x:
 		case ixgbe_mac_x550em_a:
+		case ixgbe_mac_e610:
 			hwstats->pxonrxc[i] +=
 				IXGBE_READ_REG(hw, IXGBE_PXONRXCNT(i));
 			break;
@@ -7221,11 +7766,12 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	for (i = 0; i < 16; i++) {
 		hwstats->qptc[i] += IXGBE_READ_REG(hw, IXGBE_QPTC(i));
 		hwstats->qprc[i] += IXGBE_READ_REG(hw, IXGBE_QPRC(i));
-		if ((hw->mac.type == ixgbe_mac_82599EB) ||
-		    (hw->mac.type == ixgbe_mac_X540) ||
-		    (hw->mac.type == ixgbe_mac_X550) ||
-		    (hw->mac.type == ixgbe_mac_X550EM_x) ||
-		    (hw->mac.type == ixgbe_mac_x550em_a)) {
+		if (hw->mac.type == ixgbe_mac_82599EB ||
+		    hw->mac.type == ixgbe_mac_X540 ||
+		    hw->mac.type == ixgbe_mac_X550 ||
+		    hw->mac.type == ixgbe_mac_X550EM_x ||
+		    hw->mac.type == ixgbe_mac_x550em_a ||
+		    hw->mac.type == ixgbe_mac_e610) {
 			hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC_L(i));
 			IXGBE_READ_REG(hw, IXGBE_QBTC_H(i)); /* to clear */
 			hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC_L(i));
@@ -7251,6 +7797,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		/* OS2BMC stats are X540 and later */
 		hwstats->o2bgptc += IXGBE_READ_REG(hw, IXGBE_O2BGPTC);
 		hwstats->o2bspc += IXGBE_READ_REG(hw, IXGBE_O2BSPC);
@@ -7433,12 +7980,9 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter)
 		return;
 
 	/* Force detection of hung controller */
-	if (netif_carrier_ok(adapter->netdev)) {
+	if (netif_carrier_ok(adapter->netdev))
 		for (i = 0; i < adapter->num_tx_queues; i++)
 			set_check_for_tx_hang(adapter->tx_ring[i]);
-		for (i = 0; i < adapter->num_xdp_queues; i++)
-			set_check_for_tx_hang(adapter->xdp_ring[i]);
-	}
 
 	if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) {
 		/*
@@ -7551,6 +8095,7 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 	case ixgbe_mac_82599EB: {
 		u32 mflcn = IXGBE_READ_REG(hw, IXGBE_MFLCN);
 		u32 fccfg = IXGBE_READ_REG(hw, IXGBE_FCCFG);
@@ -7600,6 +8145,9 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter)
 	netif_carrier_on(netdev);
 	ixgbe_check_vf_rate_limit(adapter);
 
+	if (adapter->num_vfs && hw->mac.ops.enable_mdd)
+		hw->mac.ops.enable_mdd(hw);
+
 	/* enable transmits */
 	netif_tx_wake_all_queues(adapter->netdev);
 
@@ -7627,6 +8175,8 @@ static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *adapter)
 	if (!netif_carrier_ok(netdev))
 		return;
 
+	adapter->link_down_events++;
+
 	/* poll for SFP+ cable when link is down */
 	if (ixgbe_is_sfp(hw) && hw->mac.type == ixgbe_mac_82598EB)
 		adapter->flags2 |= IXGBE_FLAG2_SEARCH_FOR_SFP;
@@ -7652,13 +8202,6 @@ static bool ixgbe_ring_tx_pending(struct ixgbe_adapter *adapter)
 			return true;
 	}
 
-	for (i = 0; i < adapter->num_xdp_queues; i++) {
-		struct ixgbe_ring *ring = adapter->xdp_ring[i];
-
-		if (ring->next_to_use != ring->next_to_clean)
-			return true;
-	}
-
 	return false;
 }
 
@@ -7946,7 +8489,8 @@ static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter)
  **/
 static void ixgbe_service_timer(struct timer_list *t)
 {
-	struct ixgbe_adapter *adapter = from_timer(adapter, t, service_timer);
+	struct ixgbe_adapter *adapter = timer_container_of(adapter, t,
+							   service_timer);
 	unsigned long next_event_offset;
 
 	/* poll faster when waiting for link */
@@ -8001,6 +8545,34 @@ static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter)
 	rtnl_unlock();
 }
 
+static int ixgbe_check_fw_api_mismatch(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	if (hw->mac.type != ixgbe_mac_e610)
+		return 0;
+
+	if (hw->mac.ops.get_fw_ver && hw->mac.ops.get_fw_ver(hw))
+		return 0;
+
+	if (hw->api_maj_ver > IXGBE_FW_API_VER_MAJOR) {
+		e_dev_err("The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n");
+
+		adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH;
+		return -EOPNOTSUPP;
+	} else if (hw->api_maj_ver == IXGBE_FW_API_VER_MAJOR &&
+		   hw->api_min_ver > IXGBE_FW_API_VER_MINOR + IXGBE_FW_API_VER_DIFF_ALLOWED) {
+		e_dev_info("The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n");
+		adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH;
+	} else if (hw->api_maj_ver < IXGBE_FW_API_VER_MAJOR ||
+		   hw->api_min_ver < IXGBE_FW_API_VER_MINOR - IXGBE_FW_API_VER_DIFF_ALLOWED) {
+		e_dev_info("The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n");
+		adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH;
+	}
+
+	return 0;
+}
+
 /**
  * ixgbe_check_fw_error - Check firmware for errors
  * @adapter: the adapter private structure
@@ -8011,12 +8583,14 @@ static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 fwsm;
+	int err;
 
 	/* read fwsm.ext_err_ind register and log errors */
 	fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
 
+	/* skip if E610's FW is reloading, warning in that case may be misleading */
 	if (fwsm & IXGBE_FWSM_EXT_ERR_IND_MASK ||
-	    !(fwsm & IXGBE_FWSM_FW_VAL_BIT))
+	    (!(fwsm & IXGBE_FWSM_FW_VAL_BIT) && !(hw->mac.type == ixgbe_mac_e610)))
 		e_dev_warn("Warning firmware error detected FWSM: 0x%08X\n",
 			   fwsm);
 
@@ -8024,10 +8598,53 @@ static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter)
 		e_dev_err("Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n");
 		return true;
 	}
+	if (!(adapter->flags2 & IXGBE_FLAG2_API_MISMATCH)) {
+		err = ixgbe_check_fw_api_mismatch(adapter);
+		if (err)
+			return true;
+	}
+
+	/* return here if FW rollback mode has been already detected */
+	if (adapter->flags2 & IXGBE_FLAG2_FW_ROLLBACK)
+		return false;
+
+	if (hw->mac.ops.fw_rollback_mode && hw->mac.ops.fw_rollback_mode(hw)) {
+		struct ixgbe_nvm_info *nvm_info = &adapter->hw.flash.nvm;
+		char ver_buff[64] = "";
+
+		if (hw->mac.ops.get_fw_ver && hw->mac.ops.get_fw_ver(hw))
+			goto no_version;
+
+		if (hw->mac.ops.get_nvm_ver &&
+		    hw->mac.ops.get_nvm_ver(hw, nvm_info))
+			goto no_version;
+
+		snprintf(ver_buff, sizeof(ver_buff),
+			 "Current version is NVM:%x.%x.%x, FW:%d.%d. ",
+			 nvm_info->major, nvm_info->minor, nvm_info->eetrack,
+			 hw->fw_maj_ver, hw->fw_maj_ver);
+no_version:
+		e_dev_warn("Firmware rollback mode detected. %sDevice may exhibit limited functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware rollback mode.",
+			   ver_buff);
+
+		adapter->flags2 |= IXGBE_FLAG2_FW_ROLLBACK;
+	}
 
 	return false;
 }
 
+static void ixgbe_recovery_service_task(struct work_struct *work)
+{
+	struct ixgbe_adapter *adapter = container_of(work,
+						     struct ixgbe_adapter,
+						     service_task);
+
+	ixgbe_handle_fw_event(adapter);
+	ixgbe_service_event_complete(adapter);
+
+	mod_timer(&adapter->service_timer, jiffies + msecs_to_jiffies(100));
+}
+
 /**
  * ixgbe_service_task - manages and runs subtasks
  * @work: pointer to work_struct containing our data
@@ -8047,11 +8664,21 @@ static void ixgbe_service_task(struct work_struct *work)
 		return;
 	}
 	if (ixgbe_check_fw_error(adapter)) {
-		if (!test_bit(__IXGBE_DOWN, &adapter->state))
+		if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
+			if (adapter->mii_bus) {
+				mdiobus_unregister(adapter->mii_bus);
+				adapter->mii_bus = NULL;
+			}
 			unregister_netdev(adapter->netdev);
+		}
 		ixgbe_service_event_complete(adapter);
 		return;
 	}
+	if (adapter->hw.mac.type == ixgbe_mac_e610) {
+		if (adapter->flags2 & IXGBE_FLAG2_FW_ASYNC_EVENT)
+			ixgbe_handle_fw_event(adapter);
+		ixgbe_check_media_subtask(adapter);
+	}
 	ixgbe_reset_subtask(adapter);
 	ixgbe_phy_interrupt_subtask(adapter);
 	ixgbe_sfp_detection_subtask(adapter);
@@ -8633,7 +9260,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 	switch (vlan_get_protocol(skb)) {
 	case htons(ETH_P_FCOE):
 	case htons(ETH_P_FIP):
-		adapter = netdev_priv(dev);
+		adapter = ixgbe_from_netdev(dev);
 
 		if (!sb_dev && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED))
 			break;
@@ -8892,7 +9519,7 @@ static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb,
 				      struct net_device *netdev,
 				      struct ixgbe_ring *ring)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_ring *tx_ring;
 
 	/*
@@ -8924,7 +9551,7 @@ static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb,
  **/
 static int ixgbe_set_mac(struct net_device *netdev, void *p)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct sockaddr *addr = p;
 
@@ -8942,7 +9569,7 @@ static int ixgbe_set_mac(struct net_device *netdev, void *p)
 static int
 ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u16 value;
 	int rc;
@@ -8968,7 +9595,7 @@ ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr)
 static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad,
 			    u16 addr, u16 value)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (adapter->mii_bus) {
@@ -8988,13 +9615,9 @@ static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad,
 
 static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return ixgbe_ptp_set_ts_config(adapter, req);
-	case SIOCGHWTSTAMP:
-		return ixgbe_ptp_get_ts_config(adapter, req);
 	case SIOCGMIIPHY:
 		if (!adapter->hw.phy.ops.read_reg)
 			return -EOPNOTSUPP;
@@ -9014,7 +9637,7 @@ static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd)
 static int ixgbe_add_sanmac_netdev(struct net_device *dev)
 {
 	int err = 0;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (is_valid_ether_addr(hw->mac.san_addr)) {
@@ -9038,7 +9661,7 @@ static int ixgbe_add_sanmac_netdev(struct net_device *dev)
 static int ixgbe_del_sanmac_netdev(struct net_device *dev)
 {
 	int err = 0;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_mac_info *mac = &adapter->hw.mac;
 
 	if (is_valid_ether_addr(mac->san_addr)) {
@@ -9069,7 +9692,7 @@ static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats,
 static void ixgbe_get_stats64(struct net_device *netdev,
 			      struct rtnl_link_stats64 *stats)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int i;
 
 	rcu_read_lock();
@@ -9112,7 +9735,7 @@ static void ixgbe_get_stats64(struct net_device *netdev,
 static int ixgbe_ndo_get_vf_stats(struct net_device *netdev, int vf,
 				  struct ifla_vf_stats *vf_stats)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (vf < 0 || vf >= adapter->num_vfs)
 		return -EINVAL;
@@ -9229,7 +9852,7 @@ static int ixgbe_reassign_macvlan_pool(struct net_device *vdev,
 
 static void ixgbe_defrag_macvlan_pools(struct net_device *dev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct netdev_nested_priv priv = {
 		.data = (void *)adapter,
 	};
@@ -9250,7 +9873,7 @@ static void ixgbe_defrag_macvlan_pools(struct net_device *dev)
  */
 int ixgbe_setup_tc(struct net_device *dev, u8 tc)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	/* Hardware supports up to 8 traffic classes */
@@ -9808,7 +10431,7 @@ static LIST_HEAD(ixgbe_block_cb_list);
 static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			    void *type_data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	switch (type) {
 	case TC_SETUP_BLOCK:
@@ -9836,7 +10459,7 @@ void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter)
 #endif
 void ixgbe_do_reset(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (netif_running(netdev))
 		ixgbe_reinit_locked(adapter);
@@ -9847,7 +10470,7 @@ void ixgbe_do_reset(struct net_device *netdev)
 static netdev_features_t ixgbe_fix_features(struct net_device *netdev,
 					    netdev_features_t features)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* If Rx checksum is disabled, then RSC/LRO should also be disabled */
 	if (!(features & NETIF_F_RXCSUM))
@@ -9884,7 +10507,7 @@ static void ixgbe_reset_l2fw_offload(struct ixgbe_adapter *adapter)
 static int ixgbe_set_features(struct net_device *netdev,
 			      netdev_features_t features)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	netdev_features_t changed = netdev->features ^ features;
 	bool need_reset = false;
 
@@ -9960,7 +10583,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 {
 	/* guarantee we can provide a unique filter for the unicast address */
 	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
-		struct ixgbe_adapter *adapter = netdev_priv(dev);
+		struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 		u16 pool = VMDQ_P(0);
 
 		if (netdev_uc_count(dev) >= ixgbe_available_rars(adapter, pool))
@@ -10048,7 +10671,7 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
 				    struct nlmsghdr *nlh, u16 flags,
 				    struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct nlattr *attr, *br_spec;
 	int rem;
 
@@ -10076,7 +10699,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 				    struct net_device *dev,
 				    u32 filter_mask, int nlflags)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
 		return 0;
@@ -10088,7 +10711,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 
 static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(pdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(pdev);
 	struct ixgbe_fwd_adapter *accel;
 	int tcs = adapter->hw_tcs ? : 1;
 	int pool, err;
@@ -10185,7 +10808,7 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
 {
 	struct ixgbe_fwd_adapter *accel = priv;
-	struct ixgbe_adapter *adapter = netdev_priv(pdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(pdev);
 	unsigned int rxbase = accel->rx_base_queue;
 	unsigned int i;
 
@@ -10263,7 +10886,7 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev,
 static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 {
 	int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct bpf_prog *old_prog;
 	bool need_reset;
 	int num_queues;
@@ -10335,7 +10958,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 
 static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
@@ -10370,7 +10993,7 @@ void ixgbe_xdp_ring_update_tail_locked(struct ixgbe_ring *ring)
 static int ixgbe_xdp_xmit(struct net_device *dev, int n,
 			  struct xdp_frame **frames, u32 flags)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ring *ring;
 	int nxmit = 0;
 	int i;
@@ -10378,6 +11001,10 @@ static int ixgbe_xdp_xmit(struct net_device *dev, int n,
 	if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state)))
 		return -ENETDOWN;
 
+	if (!netif_carrier_ok(adapter->netdev) ||
+	    !netif_running(adapter->netdev))
+		return -ENETDOWN;
+
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
 
@@ -10458,6 +11085,8 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_bpf		= ixgbe_xdp,
 	.ndo_xdp_xmit		= ixgbe_xdp_xmit,
 	.ndo_xsk_wakeup         = ixgbe_xsk_wakeup,
+	.ndo_hwtstamp_get	= ixgbe_ptp_hwtstamp_get,
+	.ndo_hwtstamp_set	= ixgbe_ptp_hwtstamp_set,
 };
 
 static void ixgbe_disable_txr_hw(struct ixgbe_adapter *adapter,
@@ -10660,7 +11289,7 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring)
  * ixgbe_enumerate_functions - Get the number of ports this device has
  * @adapter: adapter structure
  *
- * This function enumerates the phsyical functions co-located on a single slot,
+ * This function enumerates the physical functions co-located on a single slot,
  * in order to determine how many ports a device has. This is most useful in
  * determining the required GT/s of PCIe bandwidth necessary for optimal
  * performance.
@@ -10771,6 +11400,24 @@ bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id,
 }
 
 /**
+ * ixgbe_set_fw_version_e610 - Set FW version specifically on E610 adapters
+ * @adapter: the adapter private structure
+ *
+ * This function is used by probe and ethtool to determine the FW version to
+ * format to display. The FW version is taken from the EEPROM/NVM.
+ *
+ */
+void ixgbe_set_fw_version_e610(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_orom_info *orom = &adapter->hw.flash.orom;
+	struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm;
+
+	snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id),
+		 "%x.%02x 0x%x %d.%d.%d", nvm->major, nvm->minor,
+		 nvm->eetrack, orom->major, orom->build, orom->patch);
+}
+
+/**
  * ixgbe_set_fw_version - Set FW version
  * @adapter: the adapter private structure
  *
@@ -10782,6 +11429,11 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter)
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct ixgbe_nvm_version nvm_ver;
 
+	if (adapter->hw.mac.type == ixgbe_mac_e610) {
+		ixgbe_set_fw_version_e610(adapter);
+		return;
+	}
+
 	ixgbe_get_oem_prod_version(hw, &nvm_ver);
 	if (nvm_ver.oem_valid) {
 		snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id),
@@ -10806,6 +11458,66 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter)
 }
 
 /**
+ * ixgbe_recovery_probe - Handle FW recovery mode during probe
+ * @adapter: the adapter private structure
+ *
+ * Perform limited driver initialization when FW error is detected.
+ *
+ * Return: 0 on successful probe for E610, -EIO if recovery mode is detected
+ * for non-E610 adapter, error status code on any other case.
+ */
+static int ixgbe_recovery_probe(struct ixgbe_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct pci_dev *pdev = adapter->pdev;
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool disable_dev;
+	int err = -EIO;
+
+	if (hw->mac.type != ixgbe_mac_e610)
+		goto clean_up_probe;
+
+	ixgbe_get_hw_control(adapter);
+	mutex_init(&hw->aci.lock);
+	err = ixgbe_get_flash_data(&adapter->hw);
+	if (err)
+		goto shutdown_aci;
+
+	timer_setup(&adapter->service_timer, ixgbe_service_timer, 0);
+	INIT_WORK(&adapter->service_task, ixgbe_recovery_service_task);
+	set_bit(__IXGBE_SERVICE_INITED, &adapter->state);
+	clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state);
+
+	if (hw->mac.ops.get_bus_info)
+		hw->mac.ops.get_bus_info(hw);
+
+	pci_set_drvdata(pdev, adapter);
+	/* We are creating devlink interface so NIC can be managed,
+	 * e.g. new NVM image loaded
+	 */
+	devl_lock(adapter->devlink);
+	ixgbe_devlink_register_port(adapter);
+	SET_NETDEV_DEVLINK_PORT(adapter->netdev,
+				&adapter->devlink_port);
+	ixgbe_devlink_init_regions(adapter);
+	devl_register(adapter->devlink);
+	devl_unlock(adapter->devlink);
+
+	return 0;
+shutdown_aci:
+	mutex_destroy(&adapter->hw.aci.lock);
+	ixgbe_release_hw_control(adapter);
+clean_up_probe:
+	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
+	free_netdev(netdev);
+	devlink_free(adapter->devlink);
+	pci_release_mem_regions(pdev);
+	if (disable_dev)
+		pci_disable_device(pdev);
+	return err;
+}
+
+/**
  * ixgbe_probe - Device Initialization Routine
  * @pdev: PCI device information struct
  * @ent: entry in ixgbe_pci_tbl
@@ -10819,6 +11531,7 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter)
 static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct net_device *netdev;
+	struct ixgbe_netdevice_priv *netdev_priv_wrapper;
 	struct ixgbe_adapter *adapter = NULL;
 	struct ixgbe_hw *hw;
 	const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data];
@@ -10868,9 +11581,17 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 #else
 		indices = IXGBE_MAX_RSS_INDICES;
 #endif
+	} else if (ii->mac == ixgbe_mac_e610) {
+		indices = IXGBE_MAX_RSS_INDICES_X550;
+	}
+
+	adapter = ixgbe_allocate_devlink(&pdev->dev);
+	if (IS_ERR(adapter)) {
+		err = PTR_ERR(adapter);
+		goto err_devlink;
 	}
 
-	netdev = alloc_etherdev_mq(sizeof(struct ixgbe_adapter), indices);
+	netdev = alloc_etherdev_mq(sizeof(*netdev_priv_wrapper), indices);
 	if (!netdev) {
 		err = -ENOMEM;
 		goto err_alloc_etherdev;
@@ -10878,7 +11599,8 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	SET_NETDEV_DEV(netdev, &pdev->dev);
 
-	adapter = netdev_priv(netdev);
+	netdev_priv_wrapper = netdev_priv(netdev);
+	netdev_priv_wrapper->adapter = adapter;
 
 	adapter->netdev = netdev;
 	adapter->pdev = pdev;
@@ -10894,11 +11616,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_ioremap;
 	}
 
-	netdev->netdev_ops = &ixgbe_netdev_ops;
-	ixgbe_set_ethtool_ops(netdev);
-	netdev->watchdog_timeo = 5 * HZ;
-	strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name));
-
 	/* Setup hw api */
 	hw->mac.ops   = *ii->mac_ops;
 	hw->mac.type  = ii->mac;
@@ -10928,17 +11645,36 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hw->phy.mdio.mdio_read = ixgbe_mdio_read;
 	hw->phy.mdio.mdio_write = ixgbe_mdio_write;
 
+	netdev->netdev_ops = &ixgbe_netdev_ops;
+	ixgbe_set_ethtool_ops(netdev);
+	netdev->watchdog_timeo = 5 * HZ;
+	strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name));
+
 	/* setup the private structure */
 	err = ixgbe_sw_init(adapter, ii);
 	if (err)
 		goto err_sw_init;
 
+	if (ixgbe_check_fw_error(adapter))
+		return ixgbe_recovery_probe(adapter);
+
+	if (adapter->hw.mac.type == ixgbe_mac_e610) {
+		err = ixgbe_get_caps(&adapter->hw);
+		if (err)
+			dev_err(&pdev->dev, "ixgbe_get_caps failed %d\n", err);
+
+		err = ixgbe_get_flash_data(&adapter->hw);
+		if (err)
+			goto err_sw_init;
+	}
+
 	if (adapter->hw.mac.type == ixgbe_mac_82599EB)
 		adapter->flags2 |= IXGBE_FLAG2_AUTO_DISABLE_VF;
 
 	switch (adapter->hw.mac.type) {
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
+	case ixgbe_mac_e610:
 		netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550;
 		break;
 	case ixgbe_mac_x550em_a:
@@ -10948,10 +11684,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		break;
 	}
 
-	/* Make sure the SWFW semaphore is in a valid state */
-	if (hw->mac.ops.init_swfw_sync)
-		hw->mac.ops.init_swfw_sync(hw);
-
 	/* Make it possible the adapter to be woken up via WOL */
 	switch (adapter->hw.mac.type) {
 	case ixgbe_mac_82599EB:
@@ -10959,6 +11691,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0);
 		break;
 	default:
@@ -11103,11 +11836,6 @@ skip_sriov:
 	if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
 		netdev->features |= NETIF_F_LRO;
 
-	if (ixgbe_check_fw_error(adapter)) {
-		err = -EIO;
-		goto err_sw_init;
-	}
-
 	/* make sure the EEPROM is good */
 	if (hw->eeprom.ops.validate_checksum(hw, NULL) < 0) {
 		e_dev_err("The EEPROM Checksum Is Not Valid\n");
@@ -11188,7 +11916,7 @@ skip_sriov:
 	if (expected_gts > 0)
 		ixgbe_check_minimum_link(adapter, expected_gts);
 
-	err = ixgbe_read_pba_string_generic(hw, part_str, sizeof(part_str));
+	err = hw->eeprom.ops.read_pba_string(hw, part_str, sizeof(part_str));
 	if (err)
 		strscpy(part_str, "Unknown", sizeof(part_str));
 	if (ixgbe_is_sfp(hw) && hw->phy.sfp_type != ixgbe_sfp_type_not_present)
@@ -11214,6 +11942,11 @@ skip_sriov:
 	}
 	strcpy(netdev->name, "eth%d");
 	pci_set_drvdata(pdev, adapter);
+
+	devl_lock(adapter->devlink);
+	ixgbe_devlink_register_port(adapter);
+	SET_NETDEV_DEVLINK_PORT(adapter->netdev, &adapter->devlink_port);
+
 	err = register_netdev(netdev);
 	if (err)
 		goto err_register;
@@ -11268,14 +12001,25 @@ skip_sriov:
 	if (err)
 		goto err_netdev;
 
+	ixgbe_devlink_init_regions(adapter);
+	devl_register(adapter->devlink);
+	devl_unlock(adapter->devlink);
+
+	if (ixgbe_fwlog_init(hw))
+		e_dev_info("Firmware logging not supported\n");
+
 	return 0;
 
 err_netdev:
 	unregister_netdev(netdev);
 err_register:
+	devl_port_unregister(&adapter->devlink_port);
+	devl_unlock(adapter->devlink);
 	ixgbe_release_hw_control(adapter);
 	ixgbe_clear_interrupt_scheme(adapter);
 err_sw_init:
+	if (hw->mac.type == ixgbe_mac_e610)
+		mutex_destroy(&adapter->hw.aci.lock);
 	ixgbe_disable_sriov(adapter);
 	adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP;
 	iounmap(adapter->io_addr);
@@ -11287,7 +12031,9 @@ err_ioremap:
 	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
 	free_netdev(netdev);
 err_alloc_etherdev:
+	devlink_free(adapter->devlink);
 	pci_release_mem_regions(pdev);
+err_devlink:
 err_pci_reg:
 err_dma:
 	if (!adapter || disable_dev)
@@ -11300,7 +12046,7 @@ err_dma:
  * @pdev: PCI device information struct
  *
  * ixgbe_remove is called by the PCI subsystem to alert the driver
- * that it should release a PCI device.  The could be caused by a
+ * that it should release a PCI device.  This could be caused by a
  * Hot-Plug event, or because the driver is going to be removed from
  * memory.
  **/
@@ -11316,11 +12062,18 @@ static void ixgbe_remove(struct pci_dev *pdev)
 		return;
 
 	netdev  = adapter->netdev;
+	devl_lock(adapter->devlink);
+	devl_unregister(adapter->devlink);
+	ixgbe_devlink_destroy_regions(adapter);
+	ixgbe_fwlog_deinit(&adapter->hw);
 	ixgbe_dbg_adapter_exit(adapter);
 
 	set_bit(__IXGBE_REMOVING, &adapter->state);
 	cancel_work_sync(&adapter->service_task);
 
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		ixgbe_disable_link_status_events(adapter);
+
 	if (adapter->mii_bus)
 		mdiobus_unregister(adapter->mii_bus);
 
@@ -11346,6 +12099,9 @@ static void ixgbe_remove(struct pci_dev *pdev)
 	if (netdev->reg_state == NETREG_REGISTERED)
 		unregister_netdev(netdev);
 
+	devl_port_unregister(&adapter->devlink_port);
+	devl_unlock(adapter->devlink);
+
 	ixgbe_stop_ipsec_offload(adapter);
 	ixgbe_clear_interrupt_scheme(adapter);
 
@@ -11375,8 +12131,13 @@ static void ixgbe_remove(struct pci_dev *pdev)
 	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
 	free_netdev(netdev);
 
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		mutex_destroy(&adapter->hw.aci.lock);
+
 	if (disable_dev)
 		pci_disable_device(pdev);
+
+	devlink_free(adapter->devlink);
 }
 
 /**
@@ -11452,6 +12213,9 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev,
 		case ixgbe_mac_x550em_a:
 			device_id = IXGBE_DEV_ID_X550EM_A_VF;
 			break;
+		case ixgbe_mac_e610:
+			device_id = IXGBE_DEV_ID_E610_VF;
+			break;
 		default:
 			device_id = 0;
 			break;
@@ -11534,7 +12298,6 @@ static pci_ers_result_t ixgbe_io_slot_reset(struct pci_dev *pdev)
 		adapter->hw.hw_addr = adapter->io_addr;
 		pci_set_master(pdev);
 		pci_restore_state(pdev);
-		pci_save_state(pdev);
 
 		pci_wake_from_d3(pdev, false);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
index d67d77e5dacc..788b5af07c70 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include <linux/pci.h>
 #include <linux/delay.h>
@@ -283,6 +283,7 @@ static int ixgbe_check_for_rst_pf(struct ixgbe_hw *hw, u16 vf_number)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		vflre = IXGBE_READ_REG(hw, IXGBE_VFLREC(reg_offset));
 		break;
 	default:
@@ -407,6 +408,7 @@ void ixgbe_init_mbx_params_pf(struct ixgbe_hw *hw)
 	    hw->mac.type != ixgbe_mac_X550 &&
 	    hw->mac.type != ixgbe_mac_X550EM_x &&
 	    hw->mac.type != ixgbe_mac_x550em_a &&
+	    hw->mac.type != ixgbe_mac_e610 &&
 	    hw->mac.type != ixgbe_mac_X540)
 		return;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
index bf65e82b4c61..0334ed4b8fa3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
@@ -34,7 +34,7 @@
 #define IXGBE_VT_MSGTYPE_CTS      0x20000000  /* Indicates that VF is still
 						 clear to send requests */
 #define IXGBE_VT_MSGINFO_SHIFT    16
-/* bits 23:16 are used for exra info for certain messages */
+/* bits 23:16 are used for extra info for certain messages */
 #define IXGBE_VT_MSGINFO_MASK     (0xFF << IXGBE_VT_MSGINFO_SHIFT)
 
 /* definitions to support mailbox API version negotiation */
@@ -50,6 +50,9 @@ enum ixgbe_pfvf_api_rev {
 	ixgbe_mbox_api_12,	/* API version 1.2, linux/freebsd VF driver */
 	ixgbe_mbox_api_13,	/* API version 1.3, linux/freebsd VF driver */
 	ixgbe_mbox_api_14,	/* API version 1.4, linux/freebsd VF driver */
+	ixgbe_mbox_api_15,	/* API version 1.5, linux/freebsd VF driver */
+	ixgbe_mbox_api_16,	/* API version 1.6, linux/freebsd VF driver */
+	ixgbe_mbox_api_17,	/* API version 1.7, linux/freebsd VF driver */
 	/* This value should always be last */
 	ixgbe_mbox_api_unknown,	/* indicates that API version is not known */
 };
@@ -86,6 +89,12 @@ enum ixgbe_pfvf_api_rev {
 
 #define IXGBE_VF_GET_LINK_STATE 0x10 /* get vf link state */
 
+/* mailbox API, version 1.6 VF requests */
+#define IXGBE_VF_GET_PF_LINK_STATE	0x11 /* request PF to send link info */
+
+/* mailbox API, version 1.7 VF requests */
+#define IXGBE_VF_FEATURES_NEGOTIATE	0x12 /* get features supported by PF */
+
 /* length of permanent address message returned from PF */
 #define IXGBE_VF_PERMADDR_MSG_LEN 4
 /* word in permanent address message with the current multicast type */
@@ -96,6 +105,12 @@ enum ixgbe_pfvf_api_rev {
 #define IXGBE_VF_MBX_INIT_TIMEOUT 2000 /* number of retries on mailbox */
 #define IXGBE_VF_MBX_INIT_DELAY   500  /* microseconds between retries */
 
+/* features negotiated between PF/VF */
+#define IXGBEVF_PF_SUP_IPSEC		BIT(0)
+#define IXGBEVF_PF_SUP_ESX_MBX		BIT(1)
+
+#define IXGBE_SUPPORTED_FEATURES	IXGBEVF_PF_SUP_IPSEC
+
 struct ixgbe_hw;
 
 int ixgbe_read_mbx(struct ixgbe_hw *, u32 *, u16, u16);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 07eaa3c3f4d3..2449e4cf2679 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include <linux/pci.h>
 #include <linux/delay.h>
@@ -167,7 +167,7 @@ int ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr,
 					 u16 reg, u16 val, bool lock)
 {
 	u32 swfw_mask = hw->phy.phy_semaphore_mask;
-	int max_retry = 1;
+	int max_retry = 3;
 	int retry = 0;
 	u8 reg_high;
 	u8 csum;
@@ -1117,7 +1117,7 @@ int ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw)
 	hw->phy.ops.read_reg(hw, IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG,
 			     MDIO_MMD_AN, &autoneg_reg);
 
-	if (hw->mac.type == ixgbe_mac_X550) {
+	if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_e610) {
 		/* Set or unset auto-negotiation 5G advertisement */
 		autoneg_reg &= ~IXGBE_MII_5GBASE_T_ADVERTISE;
 		if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_5GB_FULL) &&
@@ -1233,6 +1233,7 @@ static int ixgbe_get_copper_speeds_supported(struct ixgbe_hw *hw)
 
 	switch (hw->mac.type) {
 	case ixgbe_mac_X550:
+	case ixgbe_mac_e610:
 		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_2_5GB_FULL;
 		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_5GB_FULL;
 		break;
@@ -1322,7 +1323,7 @@ int ixgbe_check_phy_link_tnx(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
  *	@hw: pointer to hardware structure
  *
  *	Restart autonegotiation and PHY and waits for completion.
- *      This function always returns success, this is nessary since
+ *	This function always returns success, this is necessary since
  *	it is called via a function pointer that could call other
  *	functions that could return an error.
  **/
@@ -2284,7 +2285,7 @@ static int ixgbe_write_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset,
 					    u8 dev_addr, u8 data, bool lock)
 {
 	u32 swfw_mask = hw->phy.phy_semaphore_mask;
-	u32 max_retry = 1;
+	u32 max_retry = 3;
 	u32 retry = 0;
 	int status;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index 9339edbd9082..6885d2343c48 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -140,6 +140,7 @@
  * proper mult and shift to convert the cycles into nanoseconds of time.
  */
 #define IXGBE_X550_BASE_PERIOD 0xC80000000ULL
+#define IXGBE_E610_BASE_PERIOD 0x333333333ULL
 #define INCVALUE_MASK	0x7FFFFFFF
 #define ISGN		0x80000000
 
@@ -326,7 +327,7 @@ static void ixgbe_ptp_setup_sdp_X550(struct ixgbe_adapter *adapter)
  * result of SYSTIME is 32bits of "billions of cycles" and 32 bits of
  * "cycles", rather than seconds and nanoseconds.
  */
-static u64 ixgbe_ptp_read_X550(const struct cyclecounter *cc)
+static u64 ixgbe_ptp_read_X550(struct cyclecounter *cc)
 {
 	struct ixgbe_adapter *adapter =
 		container_of(cc, struct ixgbe_adapter, hw_cc);
@@ -363,7 +364,7 @@ static u64 ixgbe_ptp_read_X550(const struct cyclecounter *cc)
  * cyclecounter structure used to construct a ns counter from the
  * arbitrary fixed point registers
  */
-static u64 ixgbe_ptp_read_82599(const struct cyclecounter *cc)
+static u64 ixgbe_ptp_read_82599(struct cyclecounter *cc)
 {
 	struct ixgbe_adapter *adapter =
 		container_of(cc, struct ixgbe_adapter, hw_cc);
@@ -415,6 +416,7 @@ static void ixgbe_ptp_convert_to_hwtstamp(struct ixgbe_adapter *adapter,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		/* Upper 32 bits represent billions of cycles, lower 32 bits
 		 * represent cycles. However, we use timespec64_to_ns for the
 		 * correct math even though the units haven't been corrected
@@ -492,11 +494,13 @@ static int ixgbe_ptp_adjfine_X550(struct ptp_clock_info *ptp, long scaled_ppm)
 	struct ixgbe_adapter *adapter =
 			container_of(ptp, struct ixgbe_adapter, ptp_caps);
 	struct ixgbe_hw *hw = &adapter->hw;
+	u64 rate, base;
 	bool neg_adj;
-	u64 rate;
 	u32 inca;
 
-	neg_adj = diff_by_scaled_ppm(IXGBE_X550_BASE_PERIOD, scaled_ppm, &rate);
+	base = hw->mac.type == ixgbe_mac_e610 ? IXGBE_E610_BASE_PERIOD :
+						IXGBE_X550_BASE_PERIOD;
+	neg_adj = diff_by_scaled_ppm(base, scaled_ppm, &rate);
 
 	/* warn if rate is too large */
 	if (rate >= INCVALUE_MASK)
@@ -559,6 +563,7 @@ static int ixgbe_ptp_gettimex(struct ptp_clock_info *ptp,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		/* Upper 32 bits represent billions of cycles, lower 32 bits
 		 * represent cycles. However, we use timespec64_to_ns for the
 		 * correct math even though the units haven't been corrected
@@ -636,7 +641,7 @@ static int ixgbe_ptp_feature_enable(struct ptp_clock_info *ptp,
 	 * disabled
 	 */
 	if (rq->type != PTP_CLK_REQ_PPS || !adapter->ptp_setup_sdp)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (on)
 		adapter->flags2 |= IXGBE_FLAG2_PTP_PPS_ENABLED;
@@ -931,20 +936,22 @@ void ixgbe_ptp_rx_rgtstamp(struct ixgbe_q_vector *q_vector,
 }
 
 /**
- * ixgbe_ptp_get_ts_config - get current hardware timestamping configuration
- * @adapter: pointer to adapter structure
- * @ifr: ioctl data
+ * ixgbe_ptp_hwtstamp_get - get current hardware timestamping configuration
+ * @netdev: pointer to net device structure
+ * @config: timestamping configuration structure
  *
  * This function returns the current timestamping settings. Rather than
  * attempt to deconstruct registers to fill in the values, simply keep a copy
  * of the old settings around, and return a copy when requested.
  */
-int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
+int ixgbe_ptp_hwtstamp_get(struct net_device *netdev,
+			   struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config *config = &adapter->tstamp_config;
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+
+	*config = adapter->tstamp_config;
 
-	return copy_to_user(ifr->ifr_data, config,
-			    sizeof(*config)) ? -EFAULT : 0;
+	return 0;
 }
 
 /**
@@ -973,7 +980,7 @@ int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
  * mode, if required to support the specifically requested mode.
  */
 static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
-				 struct hwtstamp_config *config)
+					struct kernel_hwtstamp_config *config)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 tsync_tx_ctl = IXGBE_TSYNCTXCTL_ENABLED;
@@ -1067,6 +1074,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		/* enable timestamping all packets only if at least some
 		 * packets were requested. Otherwise, play nice and disable
 		 * timestamping
@@ -1123,31 +1131,29 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
 }
 
 /**
- * ixgbe_ptp_set_ts_config - user entry point for timestamp mode
- * @adapter: pointer to adapter struct
- * @ifr: ioctl data
+ * ixgbe_ptp_hwtstamp_set - user entry point for timestamp mode
+ * @netdev: pointer to net device structure
+ * @config: timestamping configuration structure
+ * @extack: netlink extended ack structure for error reporting
  *
  * Set hardware to requested mode. If unsupported, return an error with no
  * changes. Otherwise, store the mode for future reference.
  */
-int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
+int ixgbe_ptp_hwtstamp_set(struct net_device *netdev,
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int err;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	err = ixgbe_ptp_set_timestamp_mode(adapter, &config);
+	err = ixgbe_ptp_set_timestamp_mode(adapter, config);
 	if (err)
 		return err;
 
 	/* save these settings for future reference */
-	memcpy(&adapter->tstamp_config, &config,
-	       sizeof(adapter->tstamp_config));
+	adapter->tstamp_config = *config;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 static void ixgbe_ptp_link_speed_adjust(struct ixgbe_adapter *adapter,
@@ -1233,6 +1239,7 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
 		fallthrough;
 	case ixgbe_mac_x550em_a:
 	case ixgbe_mac_X550:
+	case ixgbe_mac_e610:
 		cc.read = ixgbe_ptp_read_X550;
 		break;
 	case ixgbe_mac_X540:
@@ -1280,6 +1287,7 @@ static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
 	case ixgbe_mac_X550:
+	case ixgbe_mac_e610:
 		tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC);
 
 		/* Reset SYSTIME registers to 0 */
@@ -1407,6 +1415,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		snprintf(adapter->ptp_caps.name, 16, "%s", netdev->name);
 		adapter->ptp_caps.owner = THIS_MODULE;
 		adapter->ptp_caps.max_adj = 30000000;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index ccdce80edd14..ee133d6749b3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -207,6 +207,7 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, unsigned int max_vfs)
 int ixgbe_disable_sriov(struct ixgbe_adapter *adapter)
 {
 	unsigned int num_vfs = adapter->num_vfs, vf;
+	struct ixgbe_hw *hw = &adapter->hw;
 	unsigned long flags;
 	int rss;
 
@@ -237,6 +238,9 @@ int ixgbe_disable_sriov(struct ixgbe_adapter *adapter)
 	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
 		return 0;
 
+	if (hw->mac.ops.disable_mdd)
+		hw->mac.ops.disable_mdd(hw);
+
 #ifdef CONFIG_PCI_IOV
 	/*
 	 * If our VFs are assigned we cannot shut down SR-IOV
@@ -506,6 +510,8 @@ static int ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 max_frame, u32 vf
 		case ixgbe_mbox_api_12:
 		case ixgbe_mbox_api_13:
 		case ixgbe_mbox_api_14:
+		case ixgbe_mbox_api_16:
+		case ixgbe_mbox_api_17:
 			/* Version 1.1 supports jumbo frames on VFs if PF has
 			 * jumbo frames enabled which means legacy VFs are
 			 * disabled
@@ -702,7 +708,7 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf)
 	u32 reg_val;
 	u32 queue;
 
-	/* remove VLAN filters beloning to this VF */
+	/* remove VLAN filters belonging to this VF */
 	ixgbe_clear_vf_vlans(adapter, vf);
 
 	/* add back PF assigned VLAN or VLAN 0 */
@@ -1042,6 +1048,8 @@ static int ixgbe_negotiate_vf_api(struct ixgbe_adapter *adapter,
 	case ixgbe_mbox_api_12:
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
+	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		adapter->vfinfo[vf].vf_api = api;
 		return 0;
 	default:
@@ -1068,6 +1076,8 @@ static int ixgbe_get_vf_queues(struct ixgbe_adapter *adapter,
 	case ixgbe_mbox_api_12:
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
+	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		break;
 	default:
 		return -1;
@@ -1108,6 +1118,8 @@ static int ixgbe_get_vf_reta(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 
 	/* verify the PF is supporting the correct API */
 	switch (adapter->vfinfo[vf].vf_api) {
+	case ixgbe_mbox_api_17:
+	case ixgbe_mbox_api_16:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_12:
@@ -1141,6 +1153,8 @@ static int ixgbe_get_vf_rss_key(struct ixgbe_adapter *adapter,
 
 	/* verify the PF is supporting the correct API */
 	switch (adapter->vfinfo[vf].vf_api) {
+	case ixgbe_mbox_api_17:
+	case ixgbe_mbox_api_16:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_12:
@@ -1170,6 +1184,8 @@ static int ixgbe_update_vf_xcast_mode(struct ixgbe_adapter *adapter,
 		fallthrough;
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
+	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -1240,6 +1256,8 @@ static int ixgbe_get_vf_link_state(struct ixgbe_adapter *adapter,
 	case ixgbe_mbox_api_12:
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
+	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -1250,6 +1268,65 @@ static int ixgbe_get_vf_link_state(struct ixgbe_adapter *adapter,
 	return 0;
 }
 
+/**
+ * ixgbe_send_vf_link_status - send link status data to VF
+ * @adapter: pointer to adapter struct
+ * @msgbuf: pointer to message buffers
+ * @vf: VF identifier
+ *
+ * Reply for IXGBE_VF_GET_PF_LINK_STATE mbox command sending link status data.
+ *
+ * Return: 0 on success or -EOPNOTSUPP when operation is not supported.
+ */
+static int ixgbe_send_vf_link_status(struct ixgbe_adapter *adapter,
+				     u32 *msgbuf, u32 vf)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	switch (adapter->vfinfo[vf].vf_api) {
+	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
+		if (hw->mac.type != ixgbe_mac_e610)
+			return -EOPNOTSUPP;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	/* Simply provide stored values as watchdog & link status events take
+	 * care of its freshness.
+	 */
+	msgbuf[1] = adapter->link_speed;
+	msgbuf[2] = adapter->link_up;
+
+	return 0;
+}
+
+/**
+ * ixgbe_negotiate_vf_features -  negotiate supported features with VF driver
+ * @adapter: pointer to adapter struct
+ * @msgbuf: pointer to message buffers
+ * @vf: VF identifier
+ *
+ * Return: 0 on success or -EOPNOTSUPP when operation is not supported.
+ */
+static int ixgbe_negotiate_vf_features(struct ixgbe_adapter *adapter,
+				       u32 *msgbuf, u32 vf)
+{
+	u32 features = msgbuf[1];
+
+	switch (adapter->vfinfo[vf].vf_api) {
+	case ixgbe_mbox_api_17:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	features &= IXGBE_SUPPORTED_FEATURES;
+	msgbuf[1] = features;
+
+	return 0;
+}
+
 static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 {
 	u32 mbx_size = IXGBE_VFMAILBOX_SIZE;
@@ -1324,6 +1401,12 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 	case IXGBE_VF_IPSEC_DEL:
 		retval = ixgbe_ipsec_vf_del_sa(adapter, msgbuf, vf);
 		break;
+	case IXGBE_VF_GET_PF_LINK_STATE:
+		retval = ixgbe_send_vf_link_status(adapter, msgbuf, vf);
+		break;
+	case IXGBE_VF_FEATURES_NEGOTIATE:
+		retval = ixgbe_negotiate_vf_features(adapter, msgbuf, vf);
+		break;
 	default:
 		e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]);
 		retval = -EIO;
@@ -1353,12 +1436,59 @@ static void ixgbe_rcv_ack_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 		ixgbe_write_mbx(hw, &msg, 1, vf);
 }
 
+/**
+ * ixgbe_check_mdd_event - check for MDD event on all VFs
+ * @adapter: pointer to ixgbe adapter
+ *
+ * Return: true if there is a VF on which MDD event occurred, false otherwise.
+ */
+bool ixgbe_check_mdd_event(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	DECLARE_BITMAP(vf_bitmap, 64);
+	bool ret = false;
+	int i;
+
+	if (!hw->mac.ops.handle_mdd)
+		return false;
+
+	/* Did we have a malicious event */
+	bitmap_zero(vf_bitmap, 64);
+	hw->mac.ops.handle_mdd(hw, vf_bitmap);
+
+	/* Log any blocked queues and release lock */
+	for_each_set_bit(i, vf_bitmap, 64) {
+		dev_warn(&adapter->pdev->dev,
+			 "Malicious event on VF %d tx:%x rx:%x\n", i,
+			 IXGBE_READ_REG(hw, IXGBE_LVMMC_TX),
+			 IXGBE_READ_REG(hw, IXGBE_LVMMC_RX));
+
+		if (hw->mac.ops.restore_mdd_vf) {
+			u32 ping;
+
+			hw->mac.ops.restore_mdd_vf(hw, i);
+
+			/* get the VF to rebuild its queues */
+			adapter->vfinfo[i].clear_to_send = 0;
+			ping = IXGBE_PF_CONTROL_MSG |
+			       IXGBE_VT_MSGTYPE_CTS;
+			ixgbe_write_mbx(hw, &ping, 1, i);
+		}
+
+		ret = true;
+	}
+
+	return ret;
+}
+
 void ixgbe_msg_task(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	unsigned long flags;
 	u32 vf;
 
+	ixgbe_check_mdd_event(adapter);
+
 	spin_lock_irqsave(&adapter->vfs_lock, flags);
 	for (vf = 0; vf < adapter->num_vfs; vf++) {
 		/* process any reset requests */
@@ -1418,7 +1548,7 @@ void ixgbe_set_all_vfs(struct ixgbe_adapter *adapter)
 
 int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int retval;
 
 	if (vf >= adapter->num_vfs)
@@ -1526,7 +1656,7 @@ int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan,
 			  u8 qos, __be16 vlan_proto)
 {
 	int err = 0;
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7))
 		return -EINVAL;
@@ -1644,7 +1774,7 @@ void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter)
 int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate,
 			int max_tx_rate)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int link_speed;
 
 	/* verify VF is active */
@@ -1679,7 +1809,7 @@ int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate,
 
 int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (vf >= adapter->num_vfs)
@@ -1757,7 +1887,7 @@ void ixgbe_set_vf_link_state(struct ixgbe_adapter *adapter, int vf, int state)
  **/
 int ixgbe_ndo_set_vf_link_state(struct net_device *netdev, int vf, int state)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int ret = 0;
 
 	if (vf < 0 || vf >= adapter->num_vfs) {
@@ -1794,7 +1924,7 @@ int ixgbe_ndo_set_vf_link_state(struct net_device *netdev, int vf, int state)
 int ixgbe_ndo_set_vf_rss_query_en(struct net_device *netdev, int vf,
 				  bool setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* This operation is currently supported only for 82599 and x540
 	 * devices.
@@ -1813,7 +1943,7 @@ int ixgbe_ndo_set_vf_rss_query_en(struct net_device *netdev, int vf,
 
 int ixgbe_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (vf >= adapter->num_vfs)
 		return -EINVAL;
@@ -1836,7 +1966,7 @@ int ixgbe_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting)
 int ixgbe_ndo_get_vf_config(struct net_device *netdev,
 			    int vf, struct ifla_vf_info *ivi)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	if (vf >= adapter->num_vfs)
 		return -EINVAL;
 	ivi->vf = vf;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
index 0690ecb8dfa3..bc4cab976bf9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
@@ -15,6 +15,7 @@
 #ifdef CONFIG_PCI_IOV
 void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter);
 #endif
+bool ixgbe_check_mdd_event(struct ixgbe_adapter *adapter);
 void ixgbe_msg_task(struct ixgbe_adapter *adapter);
 int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask);
 void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 9baccacd02a1..b1bfeb21537a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #ifndef _IXGBE_TYPE_H_
 #define _IXGBE_TYPE_H_
@@ -7,6 +7,8 @@
 #include <linux/types.h>
 #include <linux/mdio.h>
 #include <linux/netdevice.h>
+#include <linux/net/intel/libie/fwlog.h>
+#include "ixgbe_type_e610.h"
 
 /* Device IDs */
 #define IXGBE_DEV_ID_82598               0x10B6
@@ -71,12 +73,19 @@
 #define IXGBE_DEV_ID_X550EM_A_1G_T	0x15E4
 #define IXGBE_DEV_ID_X550EM_A_1G_T_L	0x15E5
 
+#define IXGBE_DEV_ID_E610_BACKPLANE	0x57AE
+#define IXGBE_DEV_ID_E610_SFP		0x57AF
+#define IXGBE_DEV_ID_E610_10G_T		0x57B0
+#define IXGBE_DEV_ID_E610_2_5G_T	0x57B1
+#define IXGBE_DEV_ID_E610_SGMII		0x57B2
+
 /* VF Device IDs */
 #define IXGBE_DEV_ID_82599_VF		0x10ED
 #define IXGBE_DEV_ID_X540_VF		0x1515
 #define IXGBE_DEV_ID_X550_VF		0x1565
 #define IXGBE_DEV_ID_X550EM_X_VF	0x15A8
 #define IXGBE_DEV_ID_X550EM_A_VF	0x15C5
+#define IXGBE_DEV_ID_E610_VF		0x57AD
 
 #define IXGBE_CAT(r, m)	IXGBE_##r##_##m
 
@@ -230,7 +239,7 @@ struct ixgbe_thermal_sensor_data {
 #define NVM_VER_INVALID		0xFFFF
 #define NVM_ETK_VALID		0x8000
 #define NVM_INVALID_PTR		0xFFFF
-#define NVM_VER_SIZE		32   /* version sting size */
+#define NVM_VER_SIZE		32   /* version string size */
 
 struct ixgbe_nvm_version {
 	u32 etk_id;
@@ -394,6 +403,8 @@ struct ixgbe_nvm_version {
 #define IXGBE_MRCTL(_i)      (0x0F600 + ((_i) * 4))
 #define IXGBE_VMRVLAN(_i)    (0x0F610 + ((_i) * 4))
 #define IXGBE_VMRVM(_i)      (0x0F630 + ((_i) * 4))
+#define IXGBE_LVMMC_RX	     0x2FA8
+#define IXGBE_LVMMC_TX	     0x8108
 #define IXGBE_WQBR_RX(_i)    (0x2FB0 + ((_i) * 4)) /* 4 total */
 #define IXGBE_WQBR_TX(_i)    (0x8130 + ((_i) * 4)) /* 4 total */
 #define IXGBE_L34T_IMIR(_i)  (0x0E800 + ((_i) * 4)) /*128 of these (0-127)*/
@@ -1034,6 +1045,7 @@ struct ixgbe_nvm_version {
 #define IXGBE_GCR_EXT_VT_MODE_16        0x00000001
 #define IXGBE_GCR_EXT_VT_MODE_32        0x00000002
 #define IXGBE_GCR_EXT_VT_MODE_64        0x00000003
+#define IXGBE_GCR_EXT_VT_MODE_MASK      0x00000003
 #define IXGBE_GCR_EXT_SRIOV             (IXGBE_GCR_EXT_MSIX_EN | \
 					 IXGBE_GCR_EXT_VT_MODE_64)
 
@@ -1600,7 +1612,7 @@ enum {
 #define IXGBE_EICR_PCI          0x00040000 /* PCI Exception */
 #define IXGBE_EICR_MAILBOX      0x00080000 /* VF to PF Mailbox Interrupt */
 #define IXGBE_EICR_LSC          0x00100000 /* Link Status Change */
-#define IXGBE_EICR_LINKSEC      0x00200000 /* PN Threshold */
+#define IXGBE_EICR_FW_EVENT	0x00200000 /* Async FW event */
 #define IXGBE_EICR_MNG          0x00400000 /* Manageability Event Interrupt */
 #define IXGBE_EICR_TS           0x00800000 /* Thermal Sensor Event */
 #define IXGBE_EICR_TIMESYNC     0x01000000 /* Timesync Event */
@@ -1636,6 +1648,7 @@ enum {
 #define IXGBE_EICS_PCI          IXGBE_EICR_PCI       /* PCI Exception */
 #define IXGBE_EICS_MAILBOX      IXGBE_EICR_MAILBOX   /* VF to PF Mailbox Int */
 #define IXGBE_EICS_LSC          IXGBE_EICR_LSC       /* Link Status Change */
+#define IXGBE_EICS_FW_EVENT	IXGBE_EICR_FW_EVENT  /* Async FW event */
 #define IXGBE_EICS_MNG          IXGBE_EICR_MNG       /* MNG Event Interrupt */
 #define IXGBE_EICS_TIMESYNC     IXGBE_EICR_TIMESYNC  /* Timesync Event */
 #define IXGBE_EICS_GPI_SDP0(_hw)	IXGBE_EICR_GPI_SDP0(_hw)
@@ -1654,6 +1667,7 @@ enum {
 #define IXGBE_EIMS_PCI          IXGBE_EICR_PCI       /* PCI Exception */
 #define IXGBE_EIMS_MAILBOX      IXGBE_EICR_MAILBOX   /* VF to PF Mailbox Int */
 #define IXGBE_EIMS_LSC          IXGBE_EICR_LSC       /* Link Status Change */
+#define IXGBE_EIMS_FW_EVENT	IXGBE_EICR_FW_EVENT  /* Async FW event */
 #define IXGBE_EIMS_MNG          IXGBE_EICR_MNG       /* MNG Event Interrupt */
 #define IXGBE_EIMS_TS           IXGBE_EICR_TS        /* Thermel Sensor Event */
 #define IXGBE_EIMS_TIMESYNC     IXGBE_EICR_TIMESYNC  /* Timesync Event */
@@ -1673,6 +1687,7 @@ enum {
 #define IXGBE_EIMC_PCI          IXGBE_EICR_PCI       /* PCI Exception */
 #define IXGBE_EIMC_MAILBOX      IXGBE_EICR_MAILBOX   /* VF to PF Mailbox Int */
 #define IXGBE_EIMC_LSC          IXGBE_EICR_LSC       /* Link Status Change */
+#define IXGBE_EIMC_FW_EVENT	IXGBE_EICR_FW_EVENT  /* Async FW event */
 #define IXGBE_EIMC_MNG          IXGBE_EICR_MNG       /* MNG Event Interrupt */
 #define IXGBE_EIMC_TIMESYNC     IXGBE_EICR_TIMESYNC  /* Timesync Event */
 #define IXGBE_EIMC_GPI_SDP0(_hw)	IXGBE_EICR_GPI_SDP0(_hw)
@@ -2010,7 +2025,7 @@ enum {
 /* EEPROM Addressing bits based on type (0-small, 1-large) */
 #define IXGBE_EEC_ADDR_SIZE 0x00000400
 #define IXGBE_EEC_SIZE      0x00007800 /* EEPROM Size */
-#define IXGBE_EERD_MAX_ADDR 0x00003FFF /* EERD alows 14 bits for addr. */
+#define IXGBE_EERD_MAX_ADDR 0x00003FFF /* EERD allows 14 bits for addr. */
 
 #define IXGBE_EEC_SIZE_SHIFT          11
 #define IXGBE_EEPROM_WORD_SIZE_SHIFT  6
@@ -2068,6 +2083,7 @@ enum {
 #define IXGBE_SAN_MAC_ADDR_PTR  0x28
 #define IXGBE_DEVICE_CAPS       0x2C
 #define IXGBE_SERIAL_NUMBER_MAC_ADDR 0x11
+#define IXGBE_PCIE_MSIX_E610_CAPS	0xB2
 #define IXGBE_PCIE_MSIX_82599_CAPS  0x72
 #define IXGBE_MAX_MSIX_VECTORS_82599	0x40
 #define IXGBE_PCIE_MSIX_82598_CAPS  0x62
@@ -2168,6 +2184,7 @@ enum {
 #define IXGBE_PCI_DEVICE_STATUS   0xAA
 #define IXGBE_PCI_DEVICE_STATUS_TRANSACTION_PENDING   0x0020
 #define IXGBE_PCI_LINK_STATUS     0xB2
+#define IXGBE_PCI_LINK_STATUS_E610	0x82
 #define IXGBE_PCI_DEVICE_CONTROL2 0xC8
 #define IXGBE_PCI_LINK_WIDTH      0x3F0
 #define IXGBE_PCI_LINK_WIDTH_1    0x10
@@ -2288,6 +2305,7 @@ enum {
 #define IXGBE_RXMTRL_V2_MGMT_MSG		0x0D00
 
 #define IXGBE_FCTRL_SBP 0x00000002 /* Store Bad Packet */
+#define IXGBE_FCTRL_TPE 0x00000080 /* Tag Promiscuous Ena*/
 #define IXGBE_FCTRL_MPE 0x00000100 /* Multicast Promiscuous Ena*/
 #define IXGBE_FCTRL_UPE 0x00000200 /* Unicast Promiscuous Ena */
 #define IXGBE_FCTRL_BAM 0x00000400 /* Broadcast Accept Mode */
@@ -2351,6 +2369,7 @@ enum {
 /* Multiple Transmit Queue Command Register */
 #define IXGBE_MTQC_RT_ENA       0x1 /* DCB Enable */
 #define IXGBE_MTQC_VT_ENA       0x2 /* VMDQ2 Enable */
+#define IXGBE_MTQC_NUM_TC_OR_Q  0xC /* Number of TCs or TxQs per pool */
 #define IXGBE_MTQC_64Q_1PB      0x0 /* 64 queues 1 pack buffer */
 #define IXGBE_MTQC_32VF         0x8 /* 4 TX Queues per pool w/32VF's */
 #define IXGBE_MTQC_64VF         0x4 /* 2 TX Queues per pool w/64VF's */
@@ -2731,6 +2750,28 @@ enum ixgbe_fdir_pballoc_type {
 #define FW_PHY_INFO_ID_HI_MASK		0xFFFF0000u
 #define FW_PHY_INFO_ID_LO_MASK		0x0000FFFFu
 
+/* There are only 3 options for VFs creation on this device:
+ * 16 VFs pool with 8 queues each
+ * 32 VFs pool with 4 queues each
+ * 64 VFs pool with 2 queues each
+ *
+ * That means reading some VF registers that map VF to queue depending on
+ * chosen option. Define values that help dealing with each scenario.
+ */
+/* Number of queues based on VFs pool */
+#define IXGBE_16VFS_QUEUES		8
+#define IXGBE_32VFS_QUEUES		4
+#define IXGBE_64VFS_QUEUES		2
+/* Mask for getting queues bits based on VFs pool */
+#define IXGBE_16VFS_BITMASK		GENMASK(IXGBE_16VFS_QUEUES - 1, 0)
+#define IXGBE_32VFS_BITMASK		GENMASK(IXGBE_32VFS_QUEUES - 1, 0)
+#define IXGBE_64VFS_BITMASK		GENMASK(IXGBE_64VFS_QUEUES - 1, 0)
+/* Convert queue index to register number.
+ * We have 4 registers with 32 queues in each.
+ */
+#define IXGBE_QUEUES_PER_REG		32
+#define IXGBE_QUEUES_REG_AMOUNT		4
+
 /* Host Interface Command Structures */
 struct ixgbe_hic_hdr {
 	u8 cmd;
@@ -2896,6 +2937,13 @@ struct ixgbe_adv_tx_context_desc {
 	__le32 mss_l4len_idx;
 };
 
+enum {
+	IXGBE_VLAN_MACIP_LENS_REG	= 0,
+	IXGBE_FCEOF_SAIDX_REG		= 1,
+	IXGBE_TYPE_TUCMD_MLHL		= 2,
+	IXGBE_MSS_L4LEN_IDX		= 3,
+};
+
 /* Adv Transmit Descriptor Config Masks */
 #define IXGBE_ADVTXD_DTALEN_MASK      0x0000FFFF /* Data buf length(bytes) */
 #define IXGBE_ADVTXD_MAC_LINKSEC      0x00040000 /* Insert LinkSec */
@@ -2903,7 +2951,7 @@ struct ixgbe_adv_tx_context_desc {
 #define IXGBE_ADVTXD_IPSEC_SA_INDEX_MASK   0x000003FF /* IPSec SA index */
 #define IXGBE_ADVTXD_IPSEC_ESP_LEN_MASK    0x000001FF /* IPSec ESP length */
 #define IXGBE_ADVTXD_DTYP_MASK  0x00F00000 /* DTYP mask */
-#define IXGBE_ADVTXD_DTYP_CTXT  0x00200000 /* Advanced Context Desc */
+#define IXGBE_ADVTXD_DTYP_CTXT	0x2 /* Advanced Context Desc */
 #define IXGBE_ADVTXD_DTYP_DATA  0x00300000 /* Advanced Data Descriptor */
 #define IXGBE_ADVTXD_DCMD_EOP   IXGBE_TXD_CMD_EOP  /* End of Packet */
 #define IXGBE_ADVTXD_DCMD_IFCS  IXGBE_TXD_CMD_IFCS /* Insert FCS */
@@ -2952,6 +3000,8 @@ struct ixgbe_adv_tx_context_desc {
 #define IXGBE_ADVTXD_FCOEF_EOF_MASK  (3u << 10)  /* FC EOF index */
 #define IXGBE_ADVTXD_L4LEN_SHIFT     8  /* Adv ctxt L4LEN shift */
 #define IXGBE_ADVTXD_MSS_SHIFT       16  /* Adv ctxt MSS shift */
+#define IXGBE_ADVTXD_MSS_MASK		GENMASK(31, IXGBE_ADVTXD_MSS_SHIFT)
+#define IXGBE_ADVTXD_HEADER_LEN_MASK	GENMASK(8, 0)
 
 /* Autonegotiation advertised speeds */
 typedef u32 ixgbe_autoneg_advertised;
@@ -2970,6 +3020,29 @@ typedef u32 ixgbe_link_speed;
 					IXGBE_LINK_SPEED_1GB_FULL | \
 					IXGBE_LINK_SPEED_10GB_FULL)
 
+/* Physical layer type */
+typedef u64 ixgbe_physical_layer;
+#define IXGBE_PHYSICAL_LAYER_UNKNOWN		0
+#define IXGBE_PHYSICAL_LAYER_10GBASE_T		0x00001
+#define IXGBE_PHYSICAL_LAYER_1000BASE_T		0x00002
+#define IXGBE_PHYSICAL_LAYER_100BASE_TX		0x00004
+#define IXGBE_PHYSICAL_LAYER_SFP_PLUS_CU	0x00008
+#define IXGBE_PHYSICAL_LAYER_10GBASE_LR		0x00010
+#define IXGBE_PHYSICAL_LAYER_10GBASE_LRM	0x00020
+#define IXGBE_PHYSICAL_LAYER_10GBASE_SR		0x00040
+#define IXGBE_PHYSICAL_LAYER_10GBASE_KX4	0x00080
+#define IXGBE_PHYSICAL_LAYER_10GBASE_CX4	0x00100
+#define IXGBE_PHYSICAL_LAYER_1000BASE_KX	0x00200
+#define IXGBE_PHYSICAL_LAYER_1000BASE_BX	0x00400
+#define IXGBE_PHYSICAL_LAYER_10GBASE_KR		0x00800
+#define IXGBE_PHYSICAL_LAYER_10GBASE_XAUI	0x01000
+#define IXGBE_PHYSICAL_LAYER_SFP_ACTIVE_DA	0x02000
+#define IXGBE_PHYSICAL_LAYER_1000BASE_SX	0x04000
+#define IXGBE_PHYSICAL_LAYER_10BASE_T		0x08000
+#define IXGBE_PHYSICAL_LAYER_2500BASE_KX	0x10000
+#define IXGBE_PHYSICAL_LAYER_2500BASE_T		0x20000
+#define IXGBE_PHYSICAL_LAYER_5000BASE_T		0x40000
+
 /* Flow Control Data Sheet defined values
  * Calculation and defines taken from 802.1bb Annex O
  */
@@ -3145,6 +3218,8 @@ enum ixgbe_mac_type {
 	ixgbe_mac_X550,
 	ixgbe_mac_X550EM_x,
 	ixgbe_mac_x550em_a,
+	ixgbe_mac_e610,
+	ixgbe_mac_e610_vf,
 	ixgbe_num_macs
 };
 
@@ -3224,7 +3299,9 @@ enum ixgbe_media_type {
 	ixgbe_media_type_copper,
 	ixgbe_media_type_backplane,
 	ixgbe_media_type_cx4,
-	ixgbe_media_type_virtual
+	ixgbe_media_type_virtual,
+	ixgbe_media_type_da,
+	ixgbe_media_type_aui,
 };
 
 /* Flow Control Settings */
@@ -3233,7 +3310,8 @@ enum ixgbe_fc_mode {
 	ixgbe_fc_rx_pause,
 	ixgbe_fc_tx_pause,
 	ixgbe_fc_full,
-	ixgbe_fc_default
+	ixgbe_fc_default,
+	ixgbe_fc_pfc,
 };
 
 /* Smart Speed Settings */
@@ -3403,6 +3481,8 @@ struct ixgbe_eeprom_operations {
 	int (*validate_checksum)(struct ixgbe_hw *, u16 *);
 	int (*update_checksum)(struct ixgbe_hw *);
 	int (*calc_checksum)(struct ixgbe_hw *);
+	int (*read_pba_string)(struct ixgbe_hw *hw, u8 *pba_num,
+			       u32 pba_num_size);
 };
 
 struct ixgbe_mac_operations {
@@ -3411,6 +3491,7 @@ struct ixgbe_mac_operations {
 	int (*start_hw)(struct ixgbe_hw *);
 	int (*clear_hw_cntrs)(struct ixgbe_hw *);
 	enum ixgbe_media_type (*get_media_type)(struct ixgbe_hw *);
+	int (*get_fw_ver)(struct ixgbe_hw *hw);
 	int (*get_mac_addr)(struct ixgbe_hw *, u8 *);
 	int (*get_san_mac_addr)(struct ixgbe_hw *, u8 *);
 	int (*get_device_caps)(struct ixgbe_hw *, u16 *);
@@ -3479,6 +3560,8 @@ struct ixgbe_mac_operations {
 	int (*get_thermal_sensor_data)(struct ixgbe_hw *);
 	int (*init_thermal_sensor_thresh)(struct ixgbe_hw *hw);
 	bool (*fw_recovery_mode)(struct ixgbe_hw *hw);
+	bool (*fw_rollback_mode)(struct ixgbe_hw *hw);
+	int (*get_nvm_ver)(struct ixgbe_hw *hw, struct ixgbe_nvm_info *nvm);
 	void (*disable_rx)(struct ixgbe_hw *hw);
 	void (*enable_rx)(struct ixgbe_hw *hw);
 	void (*set_source_address_pruning)(struct ixgbe_hw *, bool,
@@ -3491,6 +3574,12 @@ struct ixgbe_mac_operations {
 	int (*dmac_config_tcs)(struct ixgbe_hw *hw);
 	int (*read_iosf_sb_reg)(struct ixgbe_hw *, u32, u32, u32 *);
 	int (*write_iosf_sb_reg)(struct ixgbe_hw *, u32, u32, u32);
+
+	/* MDD events */
+	void (*enable_mdd)(struct ixgbe_hw *hw);
+	void (*disable_mdd)(struct ixgbe_hw *hw);
+	void (*restore_mdd_vf)(struct ixgbe_hw *hw, u32 vf);
+	void (*handle_mdd)(struct ixgbe_hw *hw, unsigned long *vf_bitmap);
 };
 
 struct ixgbe_phy_operations {
@@ -3533,6 +3622,9 @@ struct ixgbe_link_operations {
 struct ixgbe_link_info {
 	struct ixgbe_link_operations ops;
 	u8 addr;
+	struct ixgbe_link_status link_info;
+	struct ixgbe_link_status link_info_old;
+	u8 get_link_info;
 };
 
 struct ixgbe_eeprom_info {
@@ -3575,6 +3667,7 @@ struct ixgbe_mac_info {
 	u8				san_mac_rar_index;
 	struct ixgbe_thermal_sensor_data  thermal_sensor_data;
 	bool				set_lben;
+	u32				max_link_up_time;
 	u8				led_link_act;
 };
 
@@ -3599,6 +3692,10 @@ struct ixgbe_phy_info {
 	bool                            reset_if_overtemp;
 	bool                            qsfp_shared_i2c_bus;
 	u32				nw_mng_if_sel;
+	u64				phy_type_low;
+	u64				phy_type_high;
+	u16				curr_user_speed_req;
+	struct ixgbe_aci_cmd_set_phy_cfg_data curr_user_phy_cfg;
 };
 
 struct ixgbe_mbx_stats {
@@ -3643,6 +3740,20 @@ struct ixgbe_hw {
 	bool				allow_unsupported_sfp;
 	bool				wol_enabled;
 	bool				need_crosstalk_fix;
+	u8				api_branch;
+	u8				api_maj_ver;
+	u8				api_min_ver;
+	u8				api_patch;
+	u8				fw_branch;
+	u8				fw_maj_ver;
+	u8				fw_min_ver;
+	u8				fw_patch;
+	u32				fw_build;
+	struct ixgbe_aci_info		aci;
+	struct ixgbe_flash_info		flash;
+	struct ixgbe_hw_dev_caps	dev_caps;
+	struct ixgbe_hw_func_caps	func_caps;
+	struct libie_fwlog		fwlog;
 };
 
 struct ixgbe_info {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
new file mode 100644
index 000000000000..ff8d640a50b1
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
@@ -0,0 +1,1032 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IXGBE_TYPE_E610_H_
+#define _IXGBE_TYPE_E610_H_
+
+#include <linux/net/intel/libie/adminq.h>
+
+#define BYTES_PER_DWORD	4
+
+/* General E610 defines */
+#define IXGBE_MAX_VSI			768
+
+/* Checksum and Shadow RAM pointers */
+#define IXGBE_E610_SR_NVM_CTRL_WORD		0x00
+#define IXGBE_E610_SR_PBA_BLOCK_PTR		0x16
+#define IXGBE_E610_SR_PBA_BLOCK_MASK		GENMASK(15, 8)
+#define IXGBE_E610_SR_NVM_DEV_STARTER_VER	0x18
+#define IXGBE_E610_SR_NVM_EETRACK_LO		0x2D
+#define IXGBE_E610_SR_NVM_EETRACK_HI		0x2E
+#define IXGBE_E610_NVM_VER_LO_MASK		GENMASK(7, 0)
+#define IXGBE_E610_NVM_VER_HI_MASK		GENMASK(15, 12)
+#define IXGBE_E610_SR_SW_CHECKSUM_WORD		0x3F
+#define IXGBE_E610_SR_PFA_PTR			0x40
+#define IXGBE_E610_SR_1ST_NVM_BANK_PTR		0x42
+#define IXGBE_E610_SR_NVM_BANK_SIZE		0x43
+#define IXGBE_E610_SR_1ST_OROM_BANK_PTR		0x44
+#define IXGBE_E610_SR_OROM_BANK_SIZE		0x45
+#define IXGBE_E610_SR_NETLIST_BANK_PTR		0x46
+#define IXGBE_E610_SR_NETLIST_BANK_SIZE		0x47
+
+/* The OROM version topology */
+#define IXGBE_OROM_VER_PATCH_MASK		GENMASK_ULL(7, 0)
+#define IXGBE_OROM_VER_BUILD_MASK		GENMASK_ULL(23, 8)
+#define IXGBE_OROM_VER_MASK			GENMASK_ULL(31, 24)
+
+/* CSS Header words */
+#define IXGBE_NVM_CSS_HDR_LEN_L			0x02
+#define IXGBE_NVM_CSS_HDR_LEN_H			0x03
+#define IXGBE_NVM_CSS_SREV_L			0x14
+#define IXGBE_NVM_CSS_SREV_H			0x15
+
+#define IXGBE_HDR_LEN_ROUNDUP			32
+
+/* Length of Authentication header section in words */
+#define IXGBE_NVM_AUTH_HEADER_LEN		0x08
+
+/* Shadow RAM related */
+#define IXGBE_SR_WORDS_IN_1KB	512
+
+/* The Netlist ID Block is located after all of the Link Topology nodes. */
+#define IXGBE_NETLIST_ID_BLK_SIZE		0x30
+#define IXGBE_NETLIST_ID_BLK_OFFSET(n)		IXGBE_NETLIST_LINK_TOPO_OFFSET(0x0004 + 2 * (n))
+
+/* netlist ID block field offsets (word offsets) */
+#define IXGBE_NETLIST_ID_BLK_MAJOR_VER_LOW	0x02
+#define IXGBE_NETLIST_ID_BLK_MAJOR_VER_HIGH	0x03
+#define IXGBE_NETLIST_ID_BLK_MINOR_VER_LOW	0x04
+#define IXGBE_NETLIST_ID_BLK_MINOR_VER_HIGH	0x05
+#define IXGBE_NETLIST_ID_BLK_TYPE_LOW		0x06
+#define IXGBE_NETLIST_ID_BLK_TYPE_HIGH		0x07
+#define IXGBE_NETLIST_ID_BLK_REV_LOW		0x08
+#define IXGBE_NETLIST_ID_BLK_REV_HIGH		0x09
+#define IXGBE_NETLIST_ID_BLK_SHA_HASH_WORD(n)	(0x0A + (n))
+#define IXGBE_NETLIST_ID_BLK_CUST_VER		0x2F
+
+/* The Link Topology Netlist section is stored as a series of words. It is
+ * stored in the NVM as a TLV, with the first two words containing the type
+ * and length.
+ */
+#define IXGBE_NETLIST_LINK_TOPO_MOD_ID		0x011B
+#define IXGBE_NETLIST_TYPE_OFFSET		0x0000
+#define IXGBE_NETLIST_LEN_OFFSET		0x0001
+
+/* The Link Topology section follows the TLV header. When reading the netlist
+ * using ixgbe_read_netlist_module, we need to account for the 2-word TLV
+ * header.
+ */
+#define IXGBE_NETLIST_LINK_TOPO_OFFSET(n)	((n) + 2)
+#define IXGBE_LINK_TOPO_MODULE_LEN	IXGBE_NETLIST_LINK_TOPO_OFFSET(0x0000)
+#define IXGBE_LINK_TOPO_NODE_COUNT	IXGBE_NETLIST_LINK_TOPO_OFFSET(0x0001)
+#define IXGBE_LINK_TOPO_NODE_COUNT_M		GENMASK_ULL(9, 0)
+
+/* Firmware Status Register (GL_FWSTS) */
+#define GL_FWSTS		0x00083048 /* Reset Source: POR */
+#define GL_FWSTS_EP_PF0		BIT(24)
+#define GL_FWSTS_EP_PF1		BIT(25)
+
+/* Global NVM General Status Register */
+#define GLNVM_GENS		0x000B6100 /* Reset Source: POR */
+#define GLNVM_GENS_SR_SIZE_M	GENMASK(7, 5)
+
+#define IXGBE_GL_MNG_FWSM		0x000B6134 /* Reset Source: POR */
+#define IXGBE_GL_MNG_FWSM_RECOVERY_M	BIT(1)
+#define IXGBE_GL_MNG_FWSM_ROLLBACK_M    BIT(2)
+
+/* Flash Access Register */
+#define IXGBE_GLNVM_FLA			0x000B6108 /* Reset Source: POR */
+#define IXGBE_GLNVM_FLA_LOCKED_S	6
+#define IXGBE_GLNVM_FLA_LOCKED_M	BIT(6)
+
+/* Auxiliary field, mask and shift definition for Shadow RAM and NVM Flash */
+#define IXGBE_SR_CTRL_WORD_1_M		GENMASK(7, 6)
+#define IXGBE_SR_CTRL_WORD_VALID	BIT(0)
+#define IXGBE_SR_CTRL_WORD_OROM_BANK	BIT(3)
+#define IXGBE_SR_CTRL_WORD_NETLIST_BANK	BIT(4)
+#define IXGBE_SR_CTRL_WORD_NVM_BANK	BIT(5)
+#define IXGBE_SR_NVM_PTR_4KB_UNITS	BIT(15)
+
+/* Admin Command Interface (ACI) registers */
+#define IXGBE_PF_HIDA(_i)			(0x00085000 + ((_i) * 4))
+#define IXGBE_PF_HIDA_2(_i)			(0x00085020 + ((_i) * 4))
+#define IXGBE_PF_HIBA(_i)			(0x00084000 + ((_i) * 4))
+#define IXGBE_PF_HICR				0x00082048
+
+#define IXGBE_PF_HICR_EN			BIT(0)
+#define IXGBE_PF_HICR_C				BIT(1)
+#define IXGBE_PF_HICR_SV			BIT(2)
+#define IXGBE_PF_HICR_EV			BIT(3)
+
+#define IXGBE_FW_API_VER_MAJOR		0x01
+#define IXGBE_FW_API_VER_MINOR		0x07
+#define IXGBE_FW_API_VER_DIFF_ALLOWED	0x02
+
+#define IXGBE_ACI_DESC_SIZE		32
+#define IXGBE_ACI_DESC_SIZE_IN_DWORDS	(IXGBE_ACI_DESC_SIZE / BYTES_PER_DWORD)
+
+#define IXGBE_ACI_MAX_BUFFER_SIZE		4096    /* Size in bytes */
+#define IXGBE_ACI_SEND_DELAY_TIME_MS		10
+#define IXGBE_ACI_SEND_MAX_EXECUTE		3
+#define IXGBE_ACI_SEND_TIMEOUT_MS		\
+		(IXGBE_ACI_SEND_MAX_EXECUTE * IXGBE_ACI_SEND_DELAY_TIME_MS)
+/* [ms] timeout of waiting for sync response */
+#define IXGBE_ACI_SYNC_RESPONSE_TIMEOUT		100000
+/* [ms] timeout of waiting for async response */
+#define IXGBE_ACI_ASYNC_RESPONSE_TIMEOUT	150000
+/* [ms] timeout of waiting for resource release */
+#define IXGBE_ACI_RELEASE_RES_TIMEOUT		10000
+
+/* Admin Command Interface (ACI) opcodes */
+enum ixgbe_aci_opc {
+	ixgbe_aci_opc_get_ver				= 0x0001,
+	ixgbe_aci_opc_driver_ver			= 0x0002,
+	ixgbe_aci_opc_get_exp_err			= 0x0005,
+
+	/* resource ownership */
+	ixgbe_aci_opc_req_res				= 0x0008,
+	ixgbe_aci_opc_release_res			= 0x0009,
+
+	/* device/function capabilities */
+	ixgbe_aci_opc_list_func_caps			= 0x000A,
+	ixgbe_aci_opc_list_dev_caps			= 0x000B,
+
+	/* safe disable of RXEN */
+	ixgbe_aci_opc_disable_rxen			= 0x000C,
+
+	/* FW events */
+	ixgbe_aci_opc_get_fw_event			= 0x0014,
+
+	/* PHY commands */
+	ixgbe_aci_opc_get_phy_caps			= 0x0600,
+	ixgbe_aci_opc_set_phy_cfg			= 0x0601,
+	ixgbe_aci_opc_restart_an			= 0x0605,
+	ixgbe_aci_opc_get_link_status			= 0x0607,
+	ixgbe_aci_opc_set_event_mask			= 0x0613,
+	ixgbe_aci_opc_get_link_topo			= 0x06E0,
+	ixgbe_aci_opc_get_link_topo_pin			= 0x06E1,
+	ixgbe_aci_opc_read_i2c				= 0x06E2,
+	ixgbe_aci_opc_write_i2c				= 0x06E3,
+	ixgbe_aci_opc_read_mdio				= 0x06E4,
+	ixgbe_aci_opc_write_mdio			= 0x06E5,
+	ixgbe_aci_opc_set_gpio_by_func			= 0x06E6,
+	ixgbe_aci_opc_get_gpio_by_func			= 0x06E7,
+	ixgbe_aci_opc_set_port_id_led			= 0x06E9,
+	ixgbe_aci_opc_set_gpio				= 0x06EC,
+	ixgbe_aci_opc_get_gpio				= 0x06ED,
+	ixgbe_aci_opc_sff_eeprom			= 0x06EE,
+	ixgbe_aci_opc_prog_topo_dev_nvm			= 0x06F2,
+	ixgbe_aci_opc_read_topo_dev_nvm			= 0x06F3,
+
+	/* NVM commands */
+	ixgbe_aci_opc_nvm_read				= 0x0701,
+	ixgbe_aci_opc_nvm_erase				= 0x0702,
+	ixgbe_aci_opc_nvm_write				= 0x0703,
+	ixgbe_aci_opc_nvm_cfg_read			= 0x0704,
+	ixgbe_aci_opc_nvm_cfg_write			= 0x0705,
+	ixgbe_aci_opc_nvm_checksum			= 0x0706,
+	ixgbe_aci_opc_nvm_write_activate		= 0x0707,
+	ixgbe_aci_opc_nvm_sr_dump			= 0x0707,
+	ixgbe_aci_opc_nvm_save_factory_settings		= 0x0708,
+	ixgbe_aci_opc_nvm_update_empr			= 0x0709,
+	ixgbe_aci_opc_nvm_pkg_data			= 0x070A,
+	ixgbe_aci_opc_nvm_pass_component_tbl		= 0x070B,
+
+	/* Alternate Structure Commands */
+	ixgbe_aci_opc_write_alt_direct			= 0x0900,
+	ixgbe_aci_opc_write_alt_indirect		= 0x0901,
+	ixgbe_aci_opc_read_alt_direct			= 0x0902,
+	ixgbe_aci_opc_read_alt_indirect			= 0x0903,
+	ixgbe_aci_opc_done_alt_write			= 0x0904,
+	ixgbe_aci_opc_clear_port_alt_write		= 0x0906,
+
+	/* TCA Events */
+	ixgbe_aci_opc_temp_tca_event                    = 0x0C94,
+
+	/* debug commands */
+	ixgbe_aci_opc_debug_dump_internals		= 0xFF08,
+
+	/* SystemDiagnostic commands */
+	ixgbe_aci_opc_set_health_status_config		= 0xFF20,
+	ixgbe_aci_opc_get_supported_health_status_codes	= 0xFF21,
+	ixgbe_aci_opc_get_health_status			= 0xFF22,
+	ixgbe_aci_opc_clear_health_status		= 0xFF23,
+};
+
+#define IXGBE_DRV_VER_STR_LEN_E610	32
+
+/* Get Expanded Error Code (0x0005, direct) */
+struct ixgbe_aci_cmd_get_exp_err {
+	__le32 reason;
+#define IXGBE_ACI_EXPANDED_ERROR_NOT_PROVIDED	0xFFFFFFFF
+	__le32 identifier;
+	u8 rsvd[8];
+};
+
+/* FW update timeout definitions are in milliseconds */
+#define IXGBE_NVM_TIMEOUT		180000
+
+/* Disable RXEN (direct 0x000C) */
+struct ixgbe_aci_cmd_disable_rxen {
+	u8 lport_num;
+	u8 reserved[15];
+};
+
+/* Get PHY capabilities (indirect 0x0600) */
+struct ixgbe_aci_cmd_get_phy_caps {
+	u8 lport_num;
+	u8 reserved;
+	__le16 param0;
+	/* 18.0 - Report qualified modules */
+#define IXGBE_ACI_GET_PHY_RQM		BIT(0)
+	/* 18.1 - 18.3 : Report mode
+	 * 000b - Report topology capabilities, without media
+	 * 001b - Report topology capabilities, with media
+	 * 010b - Report Active configuration
+	 * 011b - Report PHY Type and FEC mode capabilities
+	 * 100b - Report Default capabilities
+	 */
+#define IXGBE_ACI_REPORT_MODE_M			GENMASK(3, 1)
+#define IXGBE_ACI_REPORT_TOPO_CAP_NO_MEDIA	0
+#define IXGBE_ACI_REPORT_TOPO_CAP_MEDIA		BIT(1)
+#define IXGBE_ACI_REPORT_ACTIVE_CFG		BIT(2)
+#define IXGBE_ACI_REPORT_DFLT_CFG		BIT(3)
+	__le32 reserved1;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* This is #define of PHY type (Extended):
+ * The first set of defines is for phy_type_low.
+ */
+#define IXGBE_PHY_TYPE_LOW_100BASE_TX		BIT_ULL(0)
+#define IXGBE_PHY_TYPE_LOW_100M_SGMII		BIT_ULL(1)
+#define IXGBE_PHY_TYPE_LOW_1000BASE_T		BIT_ULL(2)
+#define IXGBE_PHY_TYPE_LOW_1000BASE_SX		BIT_ULL(3)
+#define IXGBE_PHY_TYPE_LOW_1000BASE_LX		BIT_ULL(4)
+#define IXGBE_PHY_TYPE_LOW_1000BASE_KX		BIT_ULL(5)
+#define IXGBE_PHY_TYPE_LOW_1G_SGMII		BIT_ULL(6)
+#define IXGBE_PHY_TYPE_LOW_2500BASE_T		BIT_ULL(7)
+#define IXGBE_PHY_TYPE_LOW_2500BASE_X		BIT_ULL(8)
+#define IXGBE_PHY_TYPE_LOW_2500BASE_KX		BIT_ULL(9)
+#define IXGBE_PHY_TYPE_LOW_5GBASE_T		BIT_ULL(10)
+#define IXGBE_PHY_TYPE_LOW_5GBASE_KR		BIT_ULL(11)
+#define IXGBE_PHY_TYPE_LOW_10GBASE_T		BIT_ULL(12)
+#define IXGBE_PHY_TYPE_LOW_10G_SFI_DA		BIT_ULL(13)
+#define IXGBE_PHY_TYPE_LOW_10GBASE_SR		BIT_ULL(14)
+#define IXGBE_PHY_TYPE_LOW_10GBASE_LR		BIT_ULL(15)
+#define IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1	BIT_ULL(16)
+#define IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC	BIT_ULL(17)
+#define IXGBE_PHY_TYPE_LOW_10G_SFI_C2C		BIT_ULL(18)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_T		BIT_ULL(19)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_CR		BIT_ULL(20)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_CR_S		BIT_ULL(21)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_CR1		BIT_ULL(22)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_SR		BIT_ULL(23)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_LR		BIT_ULL(24)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_KR		BIT_ULL(25)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_KR_S		BIT_ULL(26)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_KR1		BIT_ULL(27)
+#define IXGBE_PHY_TYPE_LOW_25G_AUI_AOC_ACC	BIT_ULL(28)
+#define IXGBE_PHY_TYPE_LOW_25G_AUI_C2C		BIT_ULL(29)
+#define IXGBE_PHY_TYPE_LOW_MAX_INDEX		29
+/* The second set of defines is for phy_type_high. */
+#define IXGBE_PHY_TYPE_HIGH_10BASE_T		BIT_ULL(1)
+#define IXGBE_PHY_TYPE_HIGH_10M_SGMII		BIT_ULL(2)
+#define IXGBE_PHY_TYPE_HIGH_2500M_SGMII		BIT_ULL(56)
+#define IXGBE_PHY_TYPE_HIGH_100M_USXGMII	BIT_ULL(57)
+#define IXGBE_PHY_TYPE_HIGH_1G_USXGMII		BIT_ULL(58)
+#define IXGBE_PHY_TYPE_HIGH_2500M_USXGMII	BIT_ULL(59)
+#define IXGBE_PHY_TYPE_HIGH_5G_USXGMII		BIT_ULL(60)
+#define IXGBE_PHY_TYPE_HIGH_10G_USXGMII		BIT_ULL(61)
+#define IXGBE_PHY_TYPE_HIGH_MAX_INDEX		61
+
+struct ixgbe_aci_cmd_get_phy_caps_data {
+	__le64 phy_type_low; /* Use values from IXGBE_PHY_TYPE_LOW_* */
+	__le64 phy_type_high; /* Use values from IXGBE_PHY_TYPE_HIGH_* */
+	u8 caps;
+#define IXGBE_ACI_PHY_EN_TX_LINK_PAUSE			BIT(0)
+#define IXGBE_ACI_PHY_EN_RX_LINK_PAUSE			BIT(1)
+#define IXGBE_ACI_PHY_LOW_POWER_MODE			BIT(2)
+#define IXGBE_ACI_PHY_EN_LINK				BIT(3)
+#define IXGBE_ACI_PHY_AN_MODE				BIT(4)
+#define IXGBE_ACI_PHY_EN_MOD_QUAL			BIT(5)
+#define IXGBE_ACI_PHY_EN_LESM				BIT(6)
+#define IXGBE_ACI_PHY_EN_AUTO_FEC			BIT(7)
+#define IXGBE_ACI_PHY_CAPS_MASK				GENMASK(7, 0)
+	u8 low_power_ctrl_an;
+#define IXGBE_ACI_PHY_EN_D3COLD_LOW_POWER_AUTONEG	BIT(0)
+#define IXGBE_ACI_PHY_AN_EN_CLAUSE28			BIT(1)
+#define IXGBE_ACI_PHY_AN_EN_CLAUSE73			BIT(2)
+#define IXGBE_ACI_PHY_AN_EN_CLAUSE37			BIT(3)
+	__le16 eee_cap;
+#define IXGBE_ACI_PHY_EEE_EN_100BASE_TX			BIT(0)
+#define IXGBE_ACI_PHY_EEE_EN_1000BASE_T			BIT(1)
+#define IXGBE_ACI_PHY_EEE_EN_10GBASE_T			BIT(2)
+#define IXGBE_ACI_PHY_EEE_EN_1000BASE_KX		BIT(3)
+#define IXGBE_ACI_PHY_EEE_EN_10GBASE_KR			BIT(4)
+#define IXGBE_ACI_PHY_EEE_EN_25GBASE_KR			BIT(5)
+#define IXGBE_ACI_PHY_EEE_EN_10BASE_T			BIT(11)
+	__le16 eeer_value;
+	u8 phy_id_oui[4]; /* PHY/Module ID connected on the port */
+	u8 phy_fw_ver[8];
+	u8 link_fec_options;
+#define IXGBE_ACI_PHY_FEC_10G_KR_40G_KR4_EN		BIT(0)
+#define IXGBE_ACI_PHY_FEC_10G_KR_40G_KR4_REQ		BIT(1)
+#define IXGBE_ACI_PHY_FEC_25G_RS_528_REQ		BIT(2)
+#define IXGBE_ACI_PHY_FEC_25G_KR_REQ			BIT(3)
+#define IXGBE_ACI_PHY_FEC_25G_RS_544_REQ		BIT(4)
+#define IXGBE_ACI_PHY_FEC_25G_RS_CLAUSE91_EN		BIT(6)
+#define IXGBE_ACI_PHY_FEC_25G_KR_CLAUSE74_EN		BIT(7)
+#define IXGBE_ACI_PHY_FEC_MASK				0xdf
+	u8 module_compliance_enforcement;
+#define IXGBE_ACI_MOD_ENFORCE_STRICT_MODE		BIT(0)
+	u8 extended_compliance_code;
+#define IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE		3
+	u8 module_type[IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE];
+#define IXGBE_ACI_MOD_TYPE_BYTE0_SFP_PLUS		0xA0
+#define IXGBE_ACI_MOD_TYPE_BYTE0_QSFP_PLUS		0x80
+#define IXGBE_ACI_MOD_TYPE_IDENT			1
+#define IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_PASSIVE	BIT(0)
+#define IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_ACTIVE	BIT(1)
+#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_SR		BIT(4)
+#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LR		BIT(5)
+#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LRM		BIT(6)
+#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_ER		BIT(7)
+#define IXGBE_ACI_MOD_TYPE_BYTE2_SFP_PLUS		0xA0
+#define IXGBE_ACI_MOD_TYPE_BYTE2_QSFP_PLUS		0x86
+	u8 qualified_module_count;
+	u8 rsvd2[7];	/* Bytes 47:41 reserved */
+#define IXGBE_ACI_QUAL_MOD_COUNT_MAX			16
+	struct {
+		u8 v_oui[3];
+		u8 rsvd3;
+		u8 v_part[16];
+		__le32 v_rev;
+		__le64 rsvd4;
+	} qual_modules[IXGBE_ACI_QUAL_MOD_COUNT_MAX];
+};
+
+/* Set PHY capabilities (direct 0x0601)
+ * NOTE: This command must be followed by setup link and restart auto-neg
+ */
+struct ixgbe_aci_cmd_set_phy_cfg {
+	u8 lport_num;
+	u8 reserved[7];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Set PHY config command data structure */
+struct ixgbe_aci_cmd_set_phy_cfg_data {
+	__le64 phy_type_low; /* Use values from IXGBE_PHY_TYPE_LOW_* */
+	__le64 phy_type_high; /* Use values from IXGBE_PHY_TYPE_HIGH_* */
+	u8 caps;
+#define IXGBE_ACI_PHY_ENA_VALID_MASK		0xef
+#define IXGBE_ACI_PHY_ENA_TX_PAUSE_ABILITY	BIT(0)
+#define IXGBE_ACI_PHY_ENA_RX_PAUSE_ABILITY	BIT(1)
+#define IXGBE_ACI_PHY_ENA_LOW_POWER		BIT(2)
+#define IXGBE_ACI_PHY_ENA_LINK			BIT(3)
+#define IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT	BIT(5)
+#define IXGBE_ACI_PHY_ENA_LESM			BIT(6)
+#define IXGBE_ACI_PHY_ENA_AUTO_FEC		BIT(7)
+	u8 low_power_ctrl_an;
+	__le16 eee_cap; /* Value from ixgbe_aci_get_phy_caps */
+	__le16 eeer_value; /* Use defines from ixgbe_aci_get_phy_caps */
+	u8 link_fec_opt; /* Use defines from ixgbe_aci_get_phy_caps */
+	u8 module_compliance_enforcement;
+};
+
+/* Restart AN command data structure (direct 0x0605)
+ * Also used for response, with only the lport_num field present.
+ */
+struct ixgbe_aci_cmd_restart_an {
+	u8 lport_num;
+	u8 reserved;
+	u8 cmd_flags;
+#define IXGBE_ACI_RESTART_AN_LINK_RESTART	BIT(1)
+#define IXGBE_ACI_RESTART_AN_LINK_ENABLE	BIT(2)
+	u8 reserved2[13];
+};
+
+/* Get link status (indirect 0x0607), also used for Link Status Event */
+struct ixgbe_aci_cmd_get_link_status {
+	u8 lport_num;
+	u8 reserved;
+	__le16 cmd_flags;
+#define IXGBE_ACI_LSE_M				GENMASK(1, 0)
+#define IXGBE_ACI_LSE_NOP			0x0
+#define IXGBE_ACI_LSE_DIS			0x2
+#define IXGBE_ACI_LSE_ENA			0x3
+	/* only response uses this flag */
+#define IXGBE_ACI_LSE_IS_ENABLED		0x1
+	__le32 reserved2;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Get link status response data structure, also used for Link Status Event */
+struct ixgbe_aci_cmd_get_link_status_data {
+	u8 topo_media_conflict;
+#define IXGBE_ACI_LINK_TOPO_CONFLICT		BIT(0)
+#define IXGBE_ACI_LINK_MEDIA_CONFLICT		BIT(1)
+#define IXGBE_ACI_LINK_TOPO_CORRUPT		BIT(2)
+#define IXGBE_ACI_LINK_TOPO_UNREACH_PRT		BIT(4)
+#define IXGBE_ACI_LINK_TOPO_UNDRUTIL_PRT	BIT(5)
+#define IXGBE_ACI_LINK_TOPO_UNDRUTIL_MEDIA	BIT(6)
+#define IXGBE_ACI_LINK_TOPO_UNSUPP_MEDIA	BIT(7)
+	u8 link_cfg_err;
+#define IXGBE_ACI_LINK_CFG_ERR				BIT(0)
+#define IXGBE_ACI_LINK_CFG_COMPLETED			BIT(1)
+#define IXGBE_ACI_LINK_ACT_PORT_OPT_INVAL		BIT(2)
+#define IXGBE_ACI_LINK_FEAT_ID_OR_CONFIG_ID_INVAL	BIT(3)
+#define IXGBE_ACI_LINK_TOPO_CRITICAL_SDP_ERR		BIT(4)
+#define IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED		BIT(5)
+#define IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE	BIT(6)
+#define IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT		BIT(7)
+	u8 link_info;
+#define IXGBE_ACI_LINK_UP		BIT(0)	/* Link Status */
+#define IXGBE_ACI_LINK_FAULT		BIT(1)
+#define IXGBE_ACI_LINK_FAULT_TX		BIT(2)
+#define IXGBE_ACI_LINK_FAULT_RX		BIT(3)
+#define IXGBE_ACI_LINK_FAULT_REMOTE	BIT(4)
+#define IXGBE_ACI_LINK_UP_PORT		BIT(5)	/* External Port Link Status */
+#define IXGBE_ACI_MEDIA_AVAILABLE	BIT(6)
+#define IXGBE_ACI_SIGNAL_DETECT		BIT(7)
+	u8 an_info;
+#define IXGBE_ACI_AN_COMPLETED		BIT(0)
+#define IXGBE_ACI_LP_AN_ABILITY		BIT(1)
+#define IXGBE_ACI_PD_FAULT		BIT(2)	/* Parallel Detection Fault */
+#define IXGBE_ACI_FEC_EN		BIT(3)
+#define IXGBE_ACI_PHY_LOW_POWER		BIT(4)	/* Low Power State */
+#define IXGBE_ACI_LINK_PAUSE_TX		BIT(5)
+#define IXGBE_ACI_LINK_PAUSE_RX		BIT(6)
+#define IXGBE_ACI_QUALIFIED_MODULE	BIT(7)
+	u8 ext_info;
+#define IXGBE_ACI_LINK_PHY_TEMP_ALARM	BIT(0)
+#define IXGBE_ACI_LINK_EXCESSIVE_ERRORS	BIT(1)	/* Excessive Link Errors */
+	/* Port Tx Suspended */
+#define IXGBE_ACI_LINK_TX_ACTIVE	0
+#define IXGBE_ACI_LINK_TX_DRAINED	1
+#define IXGBE_ACI_LINK_TX_FLUSHED	3
+	u8 lb_status;
+#define IXGBE_ACI_LINK_LB_PHY_LCL	BIT(0)
+#define IXGBE_ACI_LINK_LB_PHY_RMT	BIT(1)
+#define IXGBE_ACI_LINK_LB_MAC_LCL	BIT(2)
+	__le16 max_frame_size;
+	u8 cfg;
+#define IXGBE_ACI_LINK_25G_KR_FEC_EN		BIT(0)
+#define IXGBE_ACI_LINK_25G_RS_528_FEC_EN	BIT(1)
+#define IXGBE_ACI_LINK_25G_RS_544_FEC_EN	BIT(2)
+#define IXGBE_ACI_FEC_MASK			GENMASK(2, 0)
+	/* Pacing Config */
+#define IXGBE_ACI_CFG_PACING_M		GENMASK(6, 3)
+#define IXGBE_ACI_CFG_PACING_TYPE_M	BIT(7)
+#define IXGBE_ACI_CFG_PACING_TYPE_AVG	0
+#define IXGBE_ACI_CFG_PACING_TYPE_FIXED	IXGBE_ACI_CFG_PACING_TYPE_M
+	/* External Device Power Ability */
+	u8 power_desc;
+#define IXGBE_ACI_PWR_CLASS_M			GENMASK(5, 0)
+#define IXGBE_ACI_LINK_PWR_BASET_LOW_HIGH	0
+#define IXGBE_ACI_LINK_PWR_BASET_HIGH		1
+#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_1		0
+#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_2		1
+#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_3		2
+#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_4		3
+	__le16 link_speed;
+#define IXGBE_ACI_LINK_SPEED_M			GENMASK(10, 0)
+#define IXGBE_ACI_LINK_SPEED_10MB		BIT(0)
+#define IXGBE_ACI_LINK_SPEED_100MB		BIT(1)
+#define IXGBE_ACI_LINK_SPEED_1000MB		BIT(2)
+#define IXGBE_ACI_LINK_SPEED_2500MB		BIT(3)
+#define IXGBE_ACI_LINK_SPEED_5GB		BIT(4)
+#define IXGBE_ACI_LINK_SPEED_10GB		BIT(5)
+#define IXGBE_ACI_LINK_SPEED_20GB		BIT(6)
+#define IXGBE_ACI_LINK_SPEED_25GB		BIT(7)
+#define IXGBE_ACI_LINK_SPEED_40GB		BIT(8)
+#define IXGBE_ACI_LINK_SPEED_50GB		BIT(9)
+#define IXGBE_ACI_LINK_SPEED_100GB		BIT(10)
+#define IXGBE_ACI_LINK_SPEED_200GB		BIT(11)
+#define IXGBE_ACI_LINK_SPEED_UNKNOWN		BIT(15)
+	__le16 reserved3;
+	u8 ext_fec_status;
+#define IXGBE_ACI_LINK_RS_272_FEC_EN	BIT(0) /* RS 272 FEC enabled */
+	u8 reserved4;
+	__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
+	__le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
+	/* Get link status version 2 link partner data */
+	__le64 lp_phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
+	__le64 lp_phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
+	u8 lp_fec_adv;
+#define IXGBE_ACI_LINK_LP_10G_KR_FEC_CAP	BIT(0)
+#define IXGBE_ACI_LINK_LP_25G_KR_FEC_CAP	BIT(1)
+#define IXGBE_ACI_LINK_LP_RS_528_FEC_CAP	BIT(2)
+#define IXGBE_ACI_LINK_LP_50G_KR_272_FEC_CAP	BIT(3)
+#define IXGBE_ACI_LINK_LP_100G_KR_272_FEC_CAP	BIT(4)
+#define IXGBE_ACI_LINK_LP_200G_KR_272_FEC_CAP	BIT(5)
+	u8 lp_fec_req;
+#define IXGBE_ACI_LINK_LP_10G_KR_FEC_REQ	BIT(0)
+#define IXGBE_ACI_LINK_LP_25G_KR_FEC_REQ	BIT(1)
+#define IXGBE_ACI_LINK_LP_RS_528_FEC_REQ	BIT(2)
+#define IXGBE_ACI_LINK_LP_KR_272_FEC_REQ	BIT(3)
+	u8 lp_flowcontrol;
+#define IXGBE_ACI_LINK_LP_PAUSE_ADV		BIT(0)
+#define IXGBE_ACI_LINK_LP_ASM_DIR_ADV		BIT(1)
+	u8 reserved5[5];
+} __packed;
+
+/* Set event mask command (direct 0x0613) */
+struct ixgbe_aci_cmd_set_event_mask {
+	u8	lport_num;
+	u8	reserved[7];
+	__le16	event_mask;
+#define IXGBE_ACI_LINK_EVENT_UPDOWN		BIT(1)
+#define IXGBE_ACI_LINK_EVENT_MEDIA_NA		BIT(2)
+#define IXGBE_ACI_LINK_EVENT_LINK_FAULT		BIT(3)
+#define IXGBE_ACI_LINK_EVENT_PHY_TEMP_ALARM	BIT(4)
+#define IXGBE_ACI_LINK_EVENT_EXCESSIVE_ERRORS	BIT(5)
+#define IXGBE_ACI_LINK_EVENT_SIGNAL_DETECT	BIT(6)
+#define IXGBE_ACI_LINK_EVENT_AN_COMPLETED	BIT(7)
+#define IXGBE_ACI_LINK_EVENT_MODULE_QUAL_FAIL	BIT(8)
+#define IXGBE_ACI_LINK_EVENT_PORT_TX_SUSPENDED	BIT(9)
+#define IXGBE_ACI_LINK_EVENT_TOPO_CONFLICT	BIT(10)
+#define IXGBE_ACI_LINK_EVENT_MEDIA_CONFLICT	BIT(11)
+#define IXGBE_ACI_LINK_EVENT_PHY_FW_LOAD_FAIL	BIT(12)
+	u8	reserved1[6];
+};
+
+struct ixgbe_aci_cmd_link_topo_params {
+	u8 lport_num;
+	u8 lport_num_valid;
+#define IXGBE_ACI_LINK_TOPO_PORT_NUM_VALID	BIT(0)
+	u8 node_type_ctx;
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_M		GENMASK(3, 0)
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_PHY	0
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_GPIO_CTRL	1
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_MUX_CTRL	2
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_LED_CTRL	3
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_LED	4
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_THERMAL	5
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_CAGE	6
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_MEZZ	7
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_ID_EEPROM	8
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_CLK_CTRL	9
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_CLK_MUX	10
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_GPS	11
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_S		4
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_M		GENMASK(7, 4)
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_GLOBAL			0
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_BOARD			1
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_PORT			2
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_NODE			3
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_NODE_HANDLE		4
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_DIRECT_BUS_ACCESS		5
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_NODE_HANDLE_BUS_ADDRESS	6
+	u8 index;
+};
+
+struct ixgbe_aci_cmd_link_topo_addr {
+	struct ixgbe_aci_cmd_link_topo_params topo_params;
+	__le16 handle;
+/* Used to decode the handle field */
+#define IXGBE_ACI_LINK_TOPO_HANDLE_BRD_TYPE_M		BIT(9)
+#define IXGBE_ACI_LINK_TOPO_HANDLE_BRD_TYPE_LOM		BIT(9)
+#define IXGBE_ACI_LINK_TOPO_HANDLE_BRD_TYPE_MEZZ	0
+};
+
+/* Get Link Topology Handle (direct, 0x06E0) */
+struct ixgbe_aci_cmd_get_link_topo {
+	struct ixgbe_aci_cmd_link_topo_addr addr;
+	u8 node_part_num;
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_PCA9575		0x21
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_ZL30632_80032	0x24
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_SI5384		0x25
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_C827		0x31
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_GEN_CLK_MUX	0x47
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_GEN_GPS		0x48
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_E610_PTC	0x49
+	u8 rsvd[9];
+};
+
+/* Get Link Topology Pin (direct, 0x06E1) */
+struct ixgbe_aci_cmd_get_link_topo_pin {
+	struct ixgbe_aci_cmd_link_topo_addr addr;
+	u8 input_io_params;
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_GPIO	0
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RESET_N	1
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_INT_N	2
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_PRESENT_N	3
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_TX_DIS	4
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_MODSEL_N	5
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_LPMODE	6
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_TX_FAULT	7
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RX_LOSS	8
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RS0		9
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RS1		10
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_EEPROM_WP	11
+/* 12 repeats intentionally due to two different uses depending on context */
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_LED		12
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RED_LED	12
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_GREEN_LED	13
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_BLUE_LED	14
+#define IXGBE_ACI_LINK_TOPO_INPUT_IO_TYPE_GPIO	3
+/* Use IXGBE_ACI_LINK_TOPO_NODE_TYPE_* for the type values */
+	u8 output_io_params;
+/* Use IXGBE_ACI_LINK_TOPO_NODE_TYPE_* for the type values */
+	u8 output_io_flags;
+#define IXGBE_ACI_LINK_TOPO_OUTPUT_POLARITY	BIT(5)
+#define IXGBE_ACI_LINK_TOPO_OUTPUT_VALUE	BIT(6)
+#define IXGBE_ACI_LINK_TOPO_OUTPUT_DRIVEN	BIT(7)
+	u8 rsvd[7];
+};
+
+/* Set Port Identification LED (direct, 0x06E9) */
+struct ixgbe_aci_cmd_set_port_id_led {
+	u8 lport_num;
+	u8 lport_num_valid;
+	u8 ident_mode;
+	u8 rsvd[13];
+};
+
+#define IXGBE_ACI_PORT_ID_PORT_NUM_VALID	BIT(0)
+#define IXGBE_ACI_PORT_IDENT_LED_ORIG		0
+#define IXGBE_ACI_PORT_IDENT_LED_BLINK		BIT(0)
+
+/* Read/Write SFF EEPROM command (indirect 0x06EE) */
+struct ixgbe_aci_cmd_sff_eeprom {
+	u8 lport_num;
+	u8 lport_num_valid;
+#define IXGBE_ACI_SFF_PORT_NUM_VALID		BIT(0)
+	__le16 i2c_bus_addr;
+#define IXGBE_ACI_SFF_I2CBUS_7BIT_M		GENMASK(6, 0)
+#define IXGBE_ACI_SFF_I2CBUS_10BIT_M		GENMASK(9, 0)
+#define IXGBE_ACI_SFF_I2CBUS_TYPE_M		BIT(10)
+#define IXGBE_ACI_SFF_I2CBUS_TYPE_7BIT		0
+#define IXGBE_ACI_SFF_I2CBUS_TYPE_10BIT		IXGBE_ACI_SFF_I2CBUS_TYPE_M
+#define IXGBE_ACI_SFF_NO_PAGE_BANK_UPDATE	0
+#define IXGBE_ACI_SFF_UPDATE_PAGE		1
+#define IXGBE_ACI_SFF_UPDATE_BANK		2
+#define IXGBE_ACI_SFF_UPDATE_PAGE_BANK		3
+#define IXGBE_ACI_SFF_IS_WRITE			BIT(15)
+	__le16 i2c_offset;
+	u8 module_bank;
+	u8 module_page;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* NVM Read command (indirect 0x0701)
+ * NVM Erase commands (direct 0x0702)
+ * NVM Write commands (indirect 0x0703)
+ * NVM Write Activate commands (direct 0x0707)
+ * NVM Shadow RAM Dump commands (direct 0x0707)
+ */
+struct ixgbe_aci_cmd_nvm {
+#define IXGBE_ACI_NVM_MAX_OFFSET	0xFFFFFF
+	__le16 offset_low;
+	u8 offset_high; /* For Write Activate offset_high is used as flags2 */
+#define IXGBE_ACI_NVM_OFFSET_HI_A_MASK  GENMASK(15, 8)
+#define IXGBE_ACI_NVM_OFFSET_HI_U_MASK	GENMASK(23, 16)
+	u8 cmd_flags;
+#define IXGBE_ACI_NVM_LAST_CMD		BIT(0)
+#define IXGBE_ACI_NVM_PCIR_REQ		BIT(0) /* Used by NVM Write reply */
+#define IXGBE_ACI_NVM_PRESERVE_ALL	BIT(1)
+#define IXGBE_ACI_NVM_ACTIV_SEL_NVM	BIT(3) /* Write Activate/SR Dump only */
+#define IXGBE_ACI_NVM_ACTIV_SEL_OROM	BIT(4)
+#define IXGBE_ACI_NVM_ACTIV_SEL_NETLIST	BIT(5)
+#define IXGBE_ACI_NVM_SPECIAL_UPDATE	BIT(6)
+#define IXGBE_ACI_NVM_REVERT_LAST_ACTIV	BIT(6) /* Write Activate only */
+#define IXGBE_ACI_NVM_FLASH_ONLY	BIT(7)
+#define IXGBE_ACI_NVM_RESET_LVL_M	GENMASK(1, 0) /* Write reply only */
+#define IXGBE_ACI_NVM_POR_FLAG		0
+#define IXGBE_ACI_NVM_PERST_FLAG	1
+#define IXGBE_ACI_NVM_EMPR_FLAG		2
+#define IXGBE_ACI_NVM_EMPR_ENA		BIT(0) /* Write Activate reply only */
+#define IXGBE_ACI_NVM_NO_PRESERVATION	0x0
+#define IXGBE_ACI_NVM_PRESERVE_SELECTED	0x6
+
+	/* For Write Activate, several flags are sent as part of a separate
+	 * flags2 field using a separate byte. For simplicity of the software
+	 * interface, we pass the flags as a 16 bit value so these flags are
+	 * all offset by 8 bits
+	 */
+#define IXGBE_ACI_NVM_ACTIV_REQ_EMPR	BIT(8) /* NVM Write Activate only */
+	__le16 module_typeid;
+	__le16 length;
+#define IXGBE_ACI_NVM_ERASE_LEN	0xFFFF
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* NVM Module_Type ID, needed offset and read_len for
+ * struct ixgbe_aci_cmd_nvm.
+ */
+#define IXGBE_ACI_NVM_START_POINT		0
+
+/* NVM Checksum Command (direct, 0x0706) */
+struct ixgbe_aci_cmd_nvm_checksum {
+	u8 flags;
+#define IXGBE_ACI_NVM_CHECKSUM_VERIFY	BIT(0)
+#define IXGBE_ACI_NVM_CHECKSUM_RECALC	BIT(1)
+	u8 rsvd;
+	__le16 checksum; /* Used only by response */
+#define IXGBE_ACI_NVM_CHECKSUM_CORRECT	0xBABA
+	u8 rsvd2[12];
+};
+
+/* Used for NVM Set Package Data command - 0x070A */
+struct ixgbe_aci_cmd_nvm_pkg_data {
+	u8 reserved[3];
+	u8 cmd_flags;
+#define IXGBE_ACI_NVM_PKG_DELETE	BIT(0) /* used for command call */
+
+	u32 reserved1;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Used for Pass Component Table command - 0x070B */
+struct ixgbe_aci_cmd_nvm_pass_comp_tbl {
+	u8 component_response; /* Response only */
+#define IXGBE_ACI_NVM_PASS_COMP_CAN_BE_UPDATED		0x0
+#define IXGBE_ACI_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE	0x1
+#define IXGBE_ACI_NVM_PASS_COMP_CAN_NOT_BE_UPDATED	0x2
+#define IXGBE_ACI_NVM_PASS_COMP_PARTIAL_CHECK		0x3
+	u8 component_response_code; /* Response only */
+#define IXGBE_ACI_NVM_PASS_COMP_CAN_BE_UPDATED_CODE	0x0
+#define IXGBE_ACI_NVM_PASS_COMP_STAMP_IDENTICAL_CODE	0x1
+#define IXGBE_ACI_NVM_PASS_COMP_STAMP_LOWER		0x2
+#define IXGBE_ACI_NVM_PASS_COMP_INVALID_STAMP_CODE	0x3
+#define IXGBE_ACI_NVM_PASS_COMP_CONFLICT_CODE		0x4
+#define IXGBE_ACI_NVM_PASS_COMP_PRE_REQ_NOT_MET_CODE	0x5
+#define IXGBE_ACI_NVM_PASS_COMP_NOT_SUPPORTED_CODE	0x6
+#define IXGBE_ACI_NVM_PASS_COMP_CANNOT_DOWNGRADE_CODE	0x7
+#define IXGBE_ACI_NVM_PASS_COMP_INCOMPLETE_IMAGE_CODE	0x8
+#define IXGBE_ACI_NVM_PASS_COMP_VER_STR_IDENTICAL_CODE	0xA
+#define IXGBE_ACI_NVM_PASS_COMP_VER_STR_LOWER_CODE	0xB
+	u8 reserved;
+	u8 transfer_flag;
+	__le32 reserved1;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+struct ixgbe_aci_cmd_nvm_comp_tbl {
+	__le16 comp_class;
+#define NVM_COMP_CLASS_ALL_FW		0x000A
+
+	__le16 comp_id;
+#define NVM_COMP_ID_OROM		0x5
+#define NVM_COMP_ID_NVM			0x6
+#define NVM_COMP_ID_NETLIST		0x8
+
+	u8 comp_class_idx;
+#define FWU_COMP_CLASS_IDX_NOT_USE	0x0
+
+	__le32 comp_cmp_stamp;
+	u8 cvs_type;
+#define NVM_CVS_TYPE_ASCII		0x1
+
+	u8 cvs_len;
+	u8 cvs[]; /* Component Version String */
+} __packed;
+
+/* E610-specific adapter context structures */
+
+struct ixgbe_link_status {
+	/* Refer to ixgbe_aci_phy_type for bits definition */
+	u64 phy_type_low;
+	u64 phy_type_high;
+	u16 max_frame_size;
+	u16 link_speed;
+	u16 req_speeds;
+	u8 topo_media_conflict;
+	u8 link_cfg_err;
+	u8 lse_ena;	/* Link Status Event notification */
+	u8 link_info;
+	u8 an_info;
+	u8 ext_info;
+	u8 fec_info;
+	u8 pacing;
+	/* Refer to #define from module_type[IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE]
+	 * of ixgbe_aci_get_phy_caps structure
+	 */
+	u8 module_type[IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE];
+};
+
+/* Common HW capabilities for SW use */
+struct ixgbe_hw_caps {
+	/* Write CSR protection */
+	u64 wr_csr_prot;
+	u32 switching_mode;
+	/* switching mode supported - EVB switching (including cloud) */
+#define IXGBE_NVM_IMAGE_TYPE_EVB		0x0
+
+	/* Manageability mode & supported protocols over MCTP */
+	u32 mgmt_mode;
+#define IXGBE_MGMT_MODE_PASS_THRU_MODE_M	GENMASK(3, 0)
+#define IXGBE_MGMT_MODE_CTL_INTERFACE_M		GENMASK(7, 4)
+#define IXGBE_MGMT_MODE_REDIR_SB_INTERFACE_M	GENMASK(11, 8)
+
+	u32 mgmt_protocols_mctp;
+#define IXGBE_MGMT_MODE_PROTO_RSVD	BIT(0)
+#define IXGBE_MGMT_MODE_PROTO_PLDM	BIT(1)
+#define IXGBE_MGMT_MODE_PROTO_OEM	BIT(2)
+#define IXGBE_MGMT_MODE_PROTO_NC_SI	BIT(3)
+
+	u32 os2bmc;
+	u32 valid_functions;
+	/* DCB capabilities */
+	u32 active_tc_bitmap;
+	u32 maxtc;
+
+	/* RSS related capabilities */
+	u32 rss_table_size;		/* 512 for PFs and 64 for VFs */
+	u32 rss_table_entry_width;	/* RSS Entry width in bits */
+
+	/* Tx/Rx queues */
+	u32 num_rxq;			/* Number/Total Rx queues */
+	u32 rxq_first_id;		/* First queue ID for Rx queues */
+	u32 num_txq;			/* Number/Total Tx queues */
+	u32 txq_first_id;		/* First queue ID for Tx queues */
+
+	/* MSI-X vectors */
+	u32 num_msix_vectors;
+	u32 msix_vector_first_id;
+
+	/* Max MTU for function or device */
+	u32 max_mtu;
+
+	/* WOL related */
+	u32 num_wol_proxy_fltr;
+	u32 wol_proxy_vsi_seid;
+
+	/* LED/SDP pin count */
+	u32 led_pin_num;
+	u32 sdp_pin_num;
+
+	/* LED/SDP - Supports up to 12 LED pins and 8 SDP signals */
+#define IXGBE_MAX_SUPPORTED_GPIO_LED	12
+#define IXGBE_MAX_SUPPORTED_GPIO_SDP	8
+	u8 led[IXGBE_MAX_SUPPORTED_GPIO_LED];
+	u8 sdp[IXGBE_MAX_SUPPORTED_GPIO_SDP];
+	/* SR-IOV virtualization */
+	u8 sr_iov_1_1;			/* SR-IOV enabled */
+	/* VMDQ */
+	u8 vmdq;			/* VMDQ supported */
+
+	/* EVB capabilities */
+	u8 evb_802_1_qbg;		/* Edge Virtual Bridging */
+	u8 evb_802_1_qbh;		/* Bridge Port Extension */
+
+	u8 dcb;
+	u8 iscsi;
+	u8 ieee_1588;
+	u8 mgmt_cem;
+
+	/* WoL and APM support */
+#define IXGBE_WOL_SUPPORT_M		BIT(0)
+#define IXGBE_ACPI_PROG_MTHD_M		BIT(1)
+#define IXGBE_PROXY_SUPPORT_M		BIT(2)
+	u8 apm_wol_support;
+	u8 acpi_prog_mthd;
+	u8 proxy_support;
+	bool nvm_update_pending_nvm;
+	bool nvm_update_pending_orom;
+	bool nvm_update_pending_netlist;
+#define IXGBE_NVM_PENDING_NVM_IMAGE		BIT(0)
+#define IXGBE_NVM_PENDING_OROM			BIT(1)
+#define IXGBE_NVM_PENDING_NETLIST		BIT(2)
+	bool sec_rev_disabled;
+	bool update_disabled;
+	bool nvm_unified_update;
+	bool netlist_auth;
+#define IXGBE_NVM_MGMT_SEC_REV_DISABLED		BIT(0)
+#define IXGBE_NVM_MGMT_UPDATE_DISABLED		BIT(1)
+#define IXGBE_NVM_MGMT_UNIFIED_UPD_SUPPORT	BIT(3)
+#define IXGBE_NVM_MGMT_NETLIST_AUTH_SUPPORT	BIT(5)
+	bool no_drop_policy_support;
+	/* PCIe reset avoidance */
+	bool pcie_reset_avoidance; /* false: not supported, true: supported */
+	/* Post update reset restriction */
+	bool reset_restrict_support; /* false: not supported, true: supported */
+
+	/* External topology device images within the NVM */
+#define IXGBE_EXT_TOPO_DEV_IMG_COUNT	4
+	u32 ext_topo_dev_img_ver_high[IXGBE_EXT_TOPO_DEV_IMG_COUNT];
+	u32 ext_topo_dev_img_ver_low[IXGBE_EXT_TOPO_DEV_IMG_COUNT];
+	u8 ext_topo_dev_img_part_num[IXGBE_EXT_TOPO_DEV_IMG_COUNT];
+#define IXGBE_EXT_TOPO_DEV_IMG_PART_NUM_S	8
+#define IXGBE_EXT_TOPO_DEV_IMG_PART_NUM_M	GENMASK(15, 8)
+	bool ext_topo_dev_img_load_en[IXGBE_EXT_TOPO_DEV_IMG_COUNT];
+#define IXGBE_EXT_TOPO_DEV_IMG_LOAD_EN	BIT(0)
+	bool ext_topo_dev_img_prog_en[IXGBE_EXT_TOPO_DEV_IMG_COUNT];
+#define IXGBE_EXT_TOPO_DEV_IMG_PROG_EN	BIT(1)
+} __packed;
+
+#define IXGBE_OROM_CIV_SIGNATURE	"$CIV"
+
+struct ixgbe_orom_civd_info {
+	u8 signature[4];	/* Must match ASCII '$CIV' characters */
+	u8 checksum;		/* Simple modulo 256 sum of all structure bytes must equal 0 */
+	__le32 combo_ver;	/* Combo Image Version number */
+	u8 combo_name_len;	/* Length of the unicode combo image version string, max of 32 */
+	__le16 combo_name[32];	/* Unicode string representing the Combo Image version */
+} __packed;
+
+/* Function specific capabilities */
+struct ixgbe_hw_func_caps {
+	u32 num_allocd_vfs;		/* Number of allocated VFs */
+	u32 vf_base_id;			/* Logical ID of the first VF */
+	u32 guar_num_vsi;
+	struct ixgbe_hw_caps common_cap;
+	bool no_drop_policy_ena;
+};
+
+/* Device wide capabilities */
+struct ixgbe_hw_dev_caps {
+	struct ixgbe_hw_caps common_cap;
+	u32 num_vfs_exposed;		/* Total number of VFs exposed */
+	u32 num_vsi_allocd_to_host;	/* Excluding EMP VSI */
+	u32 num_flow_director_fltr;	/* Number of FD filters available */
+	u32 num_funcs;
+};
+
+/* ACI event information */
+struct ixgbe_aci_event {
+	struct libie_aq_desc desc;
+	u8 *msg_buf;
+	u16 msg_len;
+	u16 buf_len;
+};
+
+struct ixgbe_aci_info {
+	struct mutex lock;		/* admin command interface lock */
+	enum libie_aq_err last_status;	/* last status of sent admin command */
+};
+
+enum ixgbe_bank_select {
+	IXGBE_ACTIVE_FLASH_BANK,
+	IXGBE_INACTIVE_FLASH_BANK,
+};
+
+/* Option ROM version information */
+struct ixgbe_orom_info {
+	u8 major;			/* Major version of OROM */
+	u8 patch;			/* Patch version of OROM */
+	u16 build;			/* Build version of OROM */
+	u32 srev;			/* Security revision */
+};
+
+/* NVM version information */
+struct ixgbe_nvm_info {
+	u32 eetrack;
+	u32 srev;
+	u8 major;
+	u8 minor;
+} __packed;
+
+/* netlist version information */
+struct ixgbe_netlist_info {
+	u32 major;			/* major high/low */
+	u32 minor;			/* minor high/low */
+	u32 type;			/* type high/low */
+	u32 rev;			/* revision high/low */
+	u32 hash;			/* SHA-1 hash word */
+	u16 cust_ver;			/* customer version */
+} __packed;
+
+/* Enumeration of possible flash banks for the NVM, OROM, and Netlist modules
+ * of the flash image.
+ */
+enum ixgbe_flash_bank {
+	IXGBE_INVALID_FLASH_BANK,
+	IXGBE_1ST_FLASH_BANK,
+	IXGBE_2ND_FLASH_BANK,
+};
+
+/* information for accessing NVM, OROM, and Netlist flash banks */
+struct ixgbe_bank_info {
+	u32 nvm_ptr;				/* Pointer to 1st NVM bank */
+	u32 nvm_size;				/* Size of NVM bank */
+	u32 orom_ptr;				/* Pointer to 1st OROM bank */
+	u32 orom_size;				/* Size of OROM bank */
+	u32 netlist_ptr;			/* Ptr to 1st Netlist bank */
+	u32 netlist_size;			/* Size of Netlist bank */
+	enum ixgbe_flash_bank nvm_bank;		/* Active NVM bank */
+	enum ixgbe_flash_bank orom_bank;	/* Active OROM bank */
+	enum ixgbe_flash_bank netlist_bank;	/* Active Netlist bank */
+};
+
+/* Flash Chip Information */
+struct ixgbe_flash_info {
+	struct ixgbe_orom_info orom;	/* Option ROM version info */
+	u32 flash_size;			/* Available flash size in bytes */
+	struct ixgbe_nvm_info nvm;	/* NVM version information */
+	struct ixgbe_netlist_info netlist;	/* Netlist version info */
+	struct ixgbe_bank_info banks;	/* Flash Bank information */
+	u16 sr_words;			/* Shadow RAM size in words */
+	u8 blank_nvm_mode;		/* is NVM empty (no FW present) */
+};
+
+#endif /* _IXGBE_TYPE_E610_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
index 81e1df83f136..e67e2feb045b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include <linux/pci.h>
 #include <linux/delay.h>
@@ -47,7 +47,7 @@ int ixgbe_get_invariants_X540(struct ixgbe_hw *hw)
 }
 
 /**
- *  ixgbe_setup_mac_link_X540 - Set the auto advertised capabilitires
+ *  ixgbe_setup_mac_link_X540 - Set the auto advertised capabilities
  *  @hw: pointer to hardware structure
  *  @speed: new link speed
  *  @autoneg_wait_to_complete: true when waiting for completion is needed
@@ -66,7 +66,9 @@ int ixgbe_setup_mac_link_X540(struct ixgbe_hw *hw, ixgbe_link_speed speed,
  *  Resets the hardware by resetting the transmit and receive units, masks
  *  and clears all interrupts, perform a PHY reset, and perform a link (MAC)
  *  reset.
- **/
+ *
+ *  Return: 0 on success or negative value on failure
+ */
 int ixgbe_reset_hw_X540(struct ixgbe_hw *hw)
 {
 	u32 swfw_mask = hw->phy.phy_semaphore_mask;
@@ -133,10 +135,14 @@ mac_reset_top:
 	hw->mac.num_rar_entries = IXGBE_X540_MAX_TX_QUEUES;
 	hw->mac.ops.init_rx_addrs(hw);
 
+	/* The following is not supported by E610. */
+	if (hw->mac.type == ixgbe_mac_e610)
+		return status;
+
 	/* Store the permanent SAN mac address */
 	hw->mac.ops.get_san_mac_addr(hw, hw->mac.san_addr);
 
-	/* Add the SAN MAC address to the RAR only if it's a valid address */
+	/* Add the SAN MAC address to RAR if it's a valid address */
 	if (is_valid_ether_addr(hw->mac.san_addr)) {
 		/* Save the SAN MAC RAR index */
 		hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1;
@@ -367,9 +373,9 @@ static int ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw)
 		}
 	}
 
-	checksum = (u16)IXGBE_EEPROM_SUM - checksum;
+	checksum = IXGBE_EEPROM_SUM - checksum;
 
-	return (int)checksum;
+	return checksum;
 }
 
 /**
@@ -888,6 +894,7 @@ static const struct ixgbe_eeprom_operations eeprom_ops_X540 = {
 	.calc_checksum		= &ixgbe_calc_eeprom_checksum_X540,
 	.validate_checksum      = &ixgbe_validate_eeprom_checksum_X540,
 	.update_checksum        = &ixgbe_update_eeprom_checksum_X540,
+	.read_pba_string        = &ixgbe_read_pba_string_generic,
 };
 
 static const struct ixgbe_phy_operations phy_ops_X540 = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h
index b69a680d3ab5..6ed360c5b605 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h
@@ -1,5 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
+
+#ifndef _IXGBE_X540_H_
+#define _IXGBE_X540_H_
 
 #include "ixgbe_type.h"
 
@@ -17,3 +20,5 @@ int ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask);
 void ixgbe_release_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask);
 void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw);
 int ixgbe_init_eeprom_params_X540(struct ixgbe_hw *hw);
+
+#endif /* _IXGBE_X540_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index d9a8cf018d3b..76d2fa3ef518 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include "ixgbe_x540.h"
+#include "ixgbe_x550.h"
 #include "ixgbe_type.h"
 #include "ixgbe_common.h"
 #include "ixgbe_mbx.h"
@@ -19,7 +20,7 @@ static int ixgbe_get_invariants_X550_x(struct ixgbe_hw *hw)
 	struct ixgbe_phy_info *phy = &hw->phy;
 	struct ixgbe_link_info *link = &hw->link;
 
-	/* Start with X540 invariants, since so simular */
+	/* Start with X540 invariants, since so similar */
 	ixgbe_get_invariants_X540(hw);
 
 	if (mac->ops.get_media_type(hw) != ixgbe_media_type_copper)
@@ -47,7 +48,7 @@ static int ixgbe_get_invariants_X550_a(struct ixgbe_hw *hw)
 	struct ixgbe_mac_info *mac = &hw->mac;
 	struct ixgbe_phy_info *phy = &hw->phy;
 
-	/* Start with X540 invariants, since so simular */
+	/* Start with X540 invariants, since so similar */
 	ixgbe_get_invariants_X540(hw);
 
 	if (mac->ops.get_media_type(hw) != ixgbe_media_type_copper)
@@ -684,7 +685,7 @@ static int ixgbe_iosf_wait(struct ixgbe_hw *hw, u32 *ctrl)
 	return 0;
 }
 
-/** ixgbe_read_iosf_sb_reg_x550 - Writes a value to specified register of the
+/** ixgbe_read_iosf_sb_reg_x550 - Reads a value to specified register of the
  *  IOSF device
  *  @hw: pointer to hardware structure
  *  @reg_addr: 32 bit PHY register to write
@@ -846,7 +847,7 @@ static int ixgbe_read_iosf_sb_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr,
 
 /** ixgbe_read_ee_hostif_buffer_X550- Read EEPROM word(s) using hostif
  *  @hw: pointer to hardware structure
- *  @offset: offset of  word in the EEPROM to read
+ *  @offset: offset of word in the EEPROM to read
  *  @words: number of words
  *  @data: word(s) read from the EEPROM
  *
@@ -1059,9 +1060,9 @@ static int ixgbe_calc_checksum_X550(struct ixgbe_hw *hw, u16 *buffer,
 			return status;
 	}
 
-	checksum = (u16)IXGBE_EEPROM_SUM - checksum;
+	checksum = IXGBE_EEPROM_SUM - checksum;
 
-	return (int)checksum;
+	return checksum;
 }
 
 /** ixgbe_calc_eeprom_checksum_X550 - Calculates and returns the checksum
@@ -1162,7 +1163,7 @@ static int ixgbe_validate_eeprom_checksum_X550(struct ixgbe_hw *hw,
 	return status;
 }
 
-/** ixgbe_write_ee_hostif_X550 - Write EEPROM word using hostif
+/** ixgbe_write_ee_hostif_data_X550 - Write EEPROM word using hostif
  *  @hw: pointer to hardware structure
  *  @offset: offset of  word in the EEPROM to write
  *  @data: word write to the EEPROM
@@ -1252,7 +1253,7 @@ static int ixgbe_get_bus_info_X550em(struct ixgbe_hw *hw)
 
 /**
  * ixgbe_fw_recovery_mode_X550 - Check FW NVM recovery mode
- * @hw: pointer t hardware structure
+ * @hw: pointer to hardware structure
  *
  * Returns true if in FW NVM recovery mode.
  */
@@ -1266,7 +1267,7 @@ static bool ixgbe_fw_recovery_mode_X550(struct ixgbe_hw *hw)
 
 /** ixgbe_disable_rx_x550 - Disable RX unit
  *
- *  Enables the Rx DMA unit for x550
+ *  Disables the Rx DMA unit for x550
  **/
 static void ixgbe_disable_rx_x550(struct ixgbe_hw *hw)
 {
@@ -1753,7 +1754,7 @@ ixgbe_setup_mac_link_sfp_n(struct ixgbe_hw *hw, ixgbe_link_speed speed,
 	ret_val = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear);
 
 	/* If no SFP module present, then return success. Return success since
-	 * SFP not present error is not excepted in the setup MAC link flow.
+	 * SFP not present error is not accepted in the setup MAC link flow.
 	 */
 	if (ret_val == -ENOENT)
 		return 0;
@@ -1803,7 +1804,7 @@ ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed,
 	ret_val = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear);
 
 	/* If no SFP module present, then return success. Return success since
-	 * SFP not present error is not excepted in the setup MAC link flow.
+	 * SFP not present error is not accepted in the setup MAC link flow.
 	 */
 	if (ret_val == -ENOENT)
 		return 0;
@@ -2317,13 +2318,13 @@ static int ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw,
 }
 
 /**
- * ixgbe_get_lasi_ext_t_x550em - Determime external Base T PHY interrupt cause
+ * ixgbe_get_lasi_ext_t_x550em - Determine external Base T PHY interrupt cause
  * @hw: pointer to hardware structure
  * @lsc: pointer to boolean flag which indicates whether external Base T
  *	 PHY interrupt is lsc
  * @is_overtemp: indicate whether an overtemp event encountered
  *
- * Determime if external Base T PHY interrupt cause is high temperature
+ * Determine if external Base T PHY interrupt cause is high temperature
  * failure alarm or link status change.
  **/
 static int ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc,
@@ -2627,7 +2628,7 @@ static int ixgbe_ext_phy_t_x550em_get_link(struct ixgbe_hw *hw, bool *link_up)
 }
 
 /** ixgbe_setup_internal_phy_t_x550em - Configure KR PHY to X557 link
- *  @hw: point to hardware structure
+ *  @hw: pointer to hardware structure
  *
  *  Configures the link between the integrated KR PHY and the external X557 PHY
  *  The driver will call this function when it gets a link status change
@@ -2668,7 +2669,7 @@ static int ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw)
 	if (status)
 		return status;
 
-	/* If link is not still up, then no setup is necessary so return */
+	/* If the link is still not up, no setup is necessary */
 	status = ixgbe_ext_phy_t_x550em_get_link(hw, &link_up);
 	if (status)
 		return status;
@@ -2744,7 +2745,7 @@ static int ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx)
 	if (led_idx >= IXGBE_X557_MAX_LED_INDEX)
 		return -EINVAL;
 
-	/* To turn on the LED, set mode to ON. */
+	/* To turn off the LED, set mode to OFF. */
 	hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx,
 			     MDIO_MMD_VEND1, &phy_data);
 	phy_data &= ~IXGBE_X557_LED_MANUAL_SET_MASK;
@@ -2767,12 +2768,12 @@ static int ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx)
  *  Sends driver version number to firmware through the manageability
  *  block.  On success return 0
  *  else returns -EBUSY when encountering an error acquiring
- *  semaphore, -EIO when command fails or -ENIVAL when incorrect
+ *  semaphore, -EIO when command fails or -EINVAL when incorrect
  *  params passed.
  **/
-static int ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min,
-				     u8 build, u8 sub, u16 len,
-				     const char *driver_ver)
+int ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min,
+			      u8 build, u8 sub, u16 len,
+			      const char *driver_ver)
 {
 	struct ixgbe_hic_drv_info2 fw_cmd;
 	int ret_val;
@@ -2811,7 +2812,7 @@ static int ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min,
 	return ret_val;
 }
 
-/** ixgbe_get_lcd_x550em - Determine lowest common denominator
+/** ixgbe_get_lcd_t_x550em - Determine lowest common denominator
  *  @hw: pointer to hardware structure
  *  @lcd_speed: pointer to lowest common link speed
  *
@@ -3174,7 +3175,7 @@ static void ixgbe_read_mng_if_sel_x550em(struct ixgbe_hw *hw)
 	hw->phy.nw_mng_if_sel = IXGBE_READ_REG(hw, IXGBE_NW_MNG_IF_SEL);
 
 	/* If X552 (X550EM_a) and MDIO is connected to external PHY, then set
-	 * PHY address. This register field was has only been used for X552.
+	 * PHY address. This register field has only been used for X552.
 	 */
 	if (hw->mac.type == ixgbe_mac_x550em_a &&
 	    hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_MDIO_ACT) {
@@ -3315,7 +3316,7 @@ static enum ixgbe_media_type ixgbe_get_media_type_X550em(struct ixgbe_hw *hw)
 	return media_type;
 }
 
-/** ixgbe_init_ext_t_x550em - Start (unstall) the external Base T PHY.
+/** ixgbe_init_ext_t_x550em - Start (uninstall) the external Base T PHY.
  ** @hw: pointer to hardware structure
  **/
 static int ixgbe_init_ext_t_x550em(struct ixgbe_hw *hw)
@@ -3505,14 +3506,14 @@ mac_reset_top:
 	return status;
 }
 
-/** ixgbe_set_ethertype_anti_spoofing_X550 - Enable/Disable Ethertype
+/** ixgbe_set_ethertype_anti_spoofing_x550 - Enable/Disable Ethertype
  *	anti-spoofing
  *  @hw:  pointer to hardware structure
  *  @enable: enable or disable switch for Ethertype anti-spoofing
  *  @vf: Virtual Function pool - VF Pool to set for Ethertype anti-spoofing
  **/
-static void ixgbe_set_ethertype_anti_spoofing_X550(struct ixgbe_hw *hw,
-						   bool enable, int vf)
+void ixgbe_set_ethertype_anti_spoofing_x550(struct ixgbe_hw *hw,
+					    bool enable, int vf)
 {
 	int vf_target_reg = vf >> 3;
 	int vf_target_shift = vf % 8 + IXGBE_SPOOF_ETHERTYPEAS_SHIFT;
@@ -3527,14 +3528,14 @@ static void ixgbe_set_ethertype_anti_spoofing_X550(struct ixgbe_hw *hw,
 	IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg), pfvfspoof);
 }
 
-/** ixgbe_set_source_address_pruning_X550 - Enable/Disbale src address pruning
+/** ixgbe_set_source_address_pruning_x550 - Enable/Disable src address pruning
  *  @hw: pointer to hardware structure
  *  @enable: enable or disable source address pruning
  *  @pool: Rx pool to set source address pruning for
  **/
-static void ixgbe_set_source_address_pruning_X550(struct ixgbe_hw *hw,
-						  bool enable,
-						  unsigned int pool)
+void ixgbe_set_source_address_pruning_x550(struct ixgbe_hw *hw,
+					   bool enable,
+					   unsigned int pool)
 {
 	u64 pfflp;
 
@@ -3734,7 +3735,7 @@ static int ixgbe_acquire_swfw_sync_x550em_a(struct ixgbe_hw *hw, u32 mask)
  * @hw: pointer to hardware structure
  * @mask: Mask to specify which semaphore to release
  *
- * Release the SWFW semaphore and puts the shared PHY token as needed
+ * Release the SWFW semaphore and puts back the shared PHY token as needed
  */
 static void ixgbe_release_swfw_sync_x550em_a(struct ixgbe_hw *hw, u32 mask)
 {
@@ -3755,7 +3756,7 @@ static void ixgbe_release_swfw_sync_x550em_a(struct ixgbe_hw *hw, u32 mask)
  * @phy_data: Pointer to read data from PHY register
  *
  * Reads a value from a specified PHY register using the SWFW lock and PHY
- * Token. The PHY Token is needed since the MDIO is shared between to MAC
+ * Token. The PHY Token is needed since the MDIO is shared between two MAC
  * instances.
  */
 static int ixgbe_read_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr,
@@ -3799,6 +3800,122 @@ static int ixgbe_write_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr,
 	return status;
 }
 
+static void ixgbe_set_mdd_x550(struct ixgbe_hw *hw, bool ena)
+{
+	u32 reg_dma, reg_rdr;
+
+	reg_dma = IXGBE_READ_REG(hw, IXGBE_DMATXCTL);
+	reg_rdr = IXGBE_READ_REG(hw, IXGBE_RDRXCTL);
+
+	if (ena) {
+		reg_dma |= (IXGBE_DMATXCTL_MDP_EN | IXGBE_DMATXCTL_MBINTEN);
+		reg_rdr |= (IXGBE_RDRXCTL_MDP_EN | IXGBE_RDRXCTL_MBINTEN);
+	} else {
+		reg_dma &= ~(IXGBE_DMATXCTL_MDP_EN | IXGBE_DMATXCTL_MBINTEN);
+		reg_rdr &= ~(IXGBE_RDRXCTL_MDP_EN | IXGBE_RDRXCTL_MBINTEN);
+	}
+
+	IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, reg_dma);
+	IXGBE_WRITE_REG(hw, IXGBE_RDRXCTL, reg_rdr);
+}
+
+/**
+ * ixgbe_enable_mdd_x550 - enable malicious driver detection
+ * @hw: pointer to hardware structure
+ */
+void ixgbe_enable_mdd_x550(struct ixgbe_hw *hw)
+{
+	ixgbe_set_mdd_x550(hw, true);
+}
+
+/**
+ * ixgbe_disable_mdd_x550 - disable malicious driver detection
+ * @hw: pointer to hardware structure
+ */
+void ixgbe_disable_mdd_x550(struct ixgbe_hw *hw)
+{
+	ixgbe_set_mdd_x550(hw, false);
+}
+
+/**
+ * ixgbe_restore_mdd_vf_x550 - restore VF that was disabled during MDD event
+ * @hw: pointer to hardware structure
+ * @vf: vf index
+ */
+void ixgbe_restore_mdd_vf_x550(struct ixgbe_hw *hw, u32 vf)
+{
+	u32 idx, reg, val, num_qs, start_q, bitmask;
+
+	/* Map VF to queues */
+	reg = IXGBE_READ_REG(hw, IXGBE_MRQC);
+	switch (reg & IXGBE_MRQC_MRQE_MASK) {
+	case IXGBE_MRQC_VMDQRT8TCEN:
+		num_qs = IXGBE_16VFS_QUEUES;
+		bitmask = IXGBE_16VFS_BITMASK;
+		break;
+	case IXGBE_MRQC_VMDQRSS32EN:
+	case IXGBE_MRQC_VMDQRT4TCEN:
+		num_qs = IXGBE_32VFS_QUEUES;
+		bitmask = IXGBE_32VFS_BITMASK;
+		break;
+	default:
+		num_qs = IXGBE_64VFS_QUEUES;
+		bitmask = IXGBE_64VFS_BITMASK;
+		break;
+	}
+	start_q = vf * num_qs;
+
+	/* Release vf's queues by clearing WQBR_TX and WQBR_RX (RW1C) */
+	idx = start_q / IXGBE_QUEUES_PER_REG;
+	val = bitmask << (start_q % IXGBE_QUEUES_PER_REG);
+	IXGBE_WRITE_REG(hw, IXGBE_WQBR_TX(idx), val);
+	IXGBE_WRITE_REG(hw, IXGBE_WQBR_RX(idx), val);
+}
+
+/**
+ * ixgbe_handle_mdd_x550 - handle malicious driver detection event
+ * @hw: pointer to hardware structure
+ * @vf_bitmap: output vf bitmap of malicious vfs
+ */
+void ixgbe_handle_mdd_x550(struct ixgbe_hw *hw, unsigned long *vf_bitmap)
+{
+	u32 i, j, reg, q, div, vf;
+	unsigned long wqbr;
+
+	/* figure out pool size for mapping to vf's */
+	reg = IXGBE_READ_REG(hw, IXGBE_MRQC);
+	switch (reg & IXGBE_MRQC_MRQE_MASK) {
+	case IXGBE_MRQC_VMDQRT8TCEN:
+		div = IXGBE_16VFS_QUEUES;
+		break;
+	case IXGBE_MRQC_VMDQRSS32EN:
+	case IXGBE_MRQC_VMDQRT4TCEN:
+		div = IXGBE_32VFS_QUEUES;
+		break;
+	default:
+		div = IXGBE_64VFS_QUEUES;
+		break;
+	}
+
+	/* Read WQBR_TX and WQBR_RX and check for malicious queues */
+	for (i = 0; i < IXGBE_QUEUES_REG_AMOUNT; i++) {
+		wqbr = IXGBE_READ_REG(hw, IXGBE_WQBR_TX(i)) |
+		       IXGBE_READ_REG(hw, IXGBE_WQBR_RX(i));
+		if (!wqbr)
+			continue;
+
+		/* Get malicious queue */
+		for_each_set_bit(j, (unsigned long *)&wqbr,
+				 IXGBE_QUEUES_PER_REG) {
+			/* Get queue from bitmask */
+			q = j + (i * IXGBE_QUEUES_PER_REG);
+			/* Map queue to vf */
+			vf = q / div;
+			set_bit(vf, vf_bitmap);
+		}
+	}
+}
+
 #define X550_COMMON_MAC \
 	.init_hw			= &ixgbe_init_hw_generic, \
 	.start_hw			= &ixgbe_start_hw_X540, \
@@ -3831,9 +3948,9 @@ static int ixgbe_write_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr,
 	.set_mac_anti_spoofing		= &ixgbe_set_mac_anti_spoofing, \
 	.set_vlan_anti_spoofing		= &ixgbe_set_vlan_anti_spoofing, \
 	.set_source_address_pruning	= \
-				&ixgbe_set_source_address_pruning_X550, \
+				&ixgbe_set_source_address_pruning_x550, \
 	.set_ethertype_anti_spoofing	= \
-				&ixgbe_set_ethertype_anti_spoofing_X550, \
+				&ixgbe_set_ethertype_anti_spoofing_x550, \
 	.disable_rx_buff		= &ixgbe_disable_rx_buff_generic, \
 	.enable_rx_buff			= &ixgbe_enable_rx_buff_generic, \
 	.get_thermal_sensor_data	= NULL, \
@@ -3862,6 +3979,10 @@ static const struct ixgbe_mac_operations mac_ops_X550 = {
 	.prot_autoc_write	= prot_autoc_write_generic,
 	.setup_fc		= ixgbe_setup_fc_generic,
 	.fc_autoneg		= ixgbe_fc_autoneg,
+	.enable_mdd		= ixgbe_enable_mdd_x550,
+	.disable_mdd		= ixgbe_disable_mdd_x550,
+	.restore_mdd_vf		= ixgbe_restore_mdd_vf_x550,
+	.handle_mdd		= ixgbe_handle_mdd_x550,
 };
 
 static const struct ixgbe_mac_operations mac_ops_X550EM_x = {
@@ -3958,6 +4079,7 @@ static const struct ixgbe_mac_operations mac_ops_x550em_a_fw = {
 	.validate_checksum	= &ixgbe_validate_eeprom_checksum_X550, \
 	.update_checksum	= &ixgbe_update_eeprom_checksum_X550, \
 	.calc_checksum		= &ixgbe_calc_eeprom_checksum_X550, \
+	.read_pba_string        = &ixgbe_read_pba_string_generic, \
 
 static const struct ixgbe_eeprom_operations eeprom_ops_X550 = {
 	X550_COMMON_EEP
@@ -4047,7 +4169,7 @@ static const u32 ixgbe_mvals_X550EM_x[IXGBE_MVALS_IDX_LIMIT] = {
 	IXGBE_MVALS_INIT(X550EM_x)
 };
 
-static const u32 ixgbe_mvals_x550em_a[IXGBE_MVALS_IDX_LIMIT] = {
+const u32 ixgbe_mvals_x550em_a[IXGBE_MVALS_IDX_LIMIT] = {
 	IXGBE_MVALS_INIT(X550EM_a)
 };
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.h
new file mode 100644
index 000000000000..2a11147fb1bc
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IXGBE_X550_H_
+#define _IXGBE_X550_H_
+
+#include "ixgbe_type.h"
+
+extern const u32 ixgbe_mvals_x550em_a[IXGBE_MVALS_IDX_LIMIT];
+
+int ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min,
+			      u8 build, u8 sub, u16 len,
+			      const char *driver_ver);
+void ixgbe_set_source_address_pruning_x550(struct ixgbe_hw *hw,
+					   bool enable,
+					   unsigned int pool);
+void ixgbe_set_ethertype_anti_spoofing_x550(struct ixgbe_hw *hw,
+					    bool enable, int vf);
+
+void ixgbe_enable_mdd_x550(struct ixgbe_hw *hw);
+void ixgbe_disable_mdd_x550(struct ixgbe_hw *hw);
+void ixgbe_restore_mdd_vf_x550(struct ixgbe_hw *hw, u32 vf);
+void ixgbe_handle_mdd_x550(struct ixgbe_hw *hw, unsigned long *vf_bitmap);
+
+#endif /* _IXGBE_X550_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 3e3b471e53f0..7b941505a9d0 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -398,7 +398,7 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 	dma_addr_t dma;
 	u32 cmd_type;
 
-	while (budget-- > 0) {
+	while (likely(budget)) {
 		if (unlikely(!ixgbe_desc_unused(xdp_ring))) {
 			work_done = false;
 			break;
@@ -433,6 +433,8 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 		xdp_ring->next_to_use++;
 		if (xdp_ring->next_to_use == xdp_ring->count)
 			xdp_ring->next_to_use = 0;
+
+		budget--;
 	}
 
 	if (tx_desc) {
@@ -508,7 +510,7 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
 
 int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ring *ring;
 
 	if (test_bit(__IXGBE_DOWN, &adapter->state))
diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h
index 5f08779c0e4e..e177d1d58696 100644
--- a/drivers/net/ethernet/intel/ixgbevf/defines.h
+++ b/drivers/net/ethernet/intel/ixgbevf/defines.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #ifndef _IXGBEVF_DEFINES_H_
 #define _IXGBEVF_DEFINES_H_
@@ -16,6 +16,9 @@
 #define IXGBE_DEV_ID_X550_VF_HV		0x1564
 #define IXGBE_DEV_ID_X550EM_X_VF_HV	0x15A9
 
+#define IXGBE_DEV_ID_E610_VF		0x57AD
+#define IXGBE_SUBDEV_ID_E610_VF_HV	0x00FF
+
 #define IXGBE_VF_IRQ_CLEAR_MASK		7
 #define IXGBE_VF_MAX_TX_QUEUES		8
 #define IXGBE_VF_MAX_RX_QUEUES		8
@@ -25,6 +28,7 @@
 
 /* Link speed */
 typedef u32 ixgbe_link_speed;
+#define IXGBE_LINK_SPEED_UNKNOWN	0
 #define IXGBE_LINK_SPEED_1GB_FULL	0x0020
 #define IXGBE_LINK_SPEED_10GB_FULL	0x0080
 #define IXGBE_LINK_SPEED_100_FULL	0x0008
diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
index 7ac53171b041..537a60d5276f 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
@@ -276,9 +276,9 @@ static int ixgbevf_set_ringparam(struct net_device *netdev,
 	}
 
 	if (new_tx_count != adapter->tx_ring_count) {
-		tx_ring = vmalloc(array_size(sizeof(*tx_ring),
-					     adapter->num_tx_queues +
-						adapter->num_xdp_queues));
+		tx_ring = vmalloc_array(adapter->num_tx_queues +
+					adapter->num_xdp_queues,
+					sizeof(*tx_ring));
 		if (!tx_ring) {
 			err = -ENOMEM;
 			goto clear_reset;
@@ -867,19 +867,11 @@ static int ixgbevf_set_coalesce(struct net_device *netdev,
 	return 0;
 }
 
-static int ixgbevf_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
-			     u32 *rules __always_unused)
+static u32 ixgbevf_get_rx_ring_count(struct net_device *dev)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(dev);
 
-	switch (info->cmd) {
-	case ETHTOOL_GRXRINGS:
-		info->data = adapter->num_rx_queues;
-		return 0;
-	default:
-		hw_dbg(&adapter->hw, "Command parameters not supported\n");
-		return -EOPNOTSUPP;
-	}
+	return adapter->num_rx_queues;
 }
 
 static u32 ixgbevf_get_rxfh_indir_size(struct net_device *netdev)
@@ -987,7 +979,7 @@ static const struct ethtool_ops ixgbevf_ethtool_ops = {
 	.get_ethtool_stats	= ixgbevf_get_ethtool_stats,
 	.get_coalesce		= ixgbevf_get_coalesce,
 	.set_coalesce		= ixgbevf_set_coalesce,
-	.get_rxnfc		= ixgbevf_get_rxnfc,
+	.get_rx_ring_count	= ixgbevf_get_rx_ring_count,
 	.get_rxfh_indir_size	= ixgbevf_get_rxfh_indir_size,
 	.get_rxfh_key_size	= ixgbevf_get_rxfh_key_size,
 	.get_rxfh		= ixgbevf_get_rxfh,
diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
index f804b35d79c7..fce35924ff8b 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
@@ -201,6 +201,7 @@ struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec,
 
 /**
  * ixgbevf_ipsec_parse_proto_keys - find the key and salt based on the protocol
+ * @dev: pointer to net device to program
  * @xs: pointer to xfrm_state struct
  * @mykey: pointer to key array to populate
  * @mysalt: pointer to salt value to populate
@@ -208,10 +209,10 @@ struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec,
  * This copies the protocol keys and salt to our own data tables.  The
  * 82599 family only supports the one algorithm.
  **/
-static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs,
+static int ixgbevf_ipsec_parse_proto_keys(struct net_device *dev,
+					  struct xfrm_state *xs,
 					  u32 *mykey, u32 *mysalt)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	unsigned char *key_data;
 	char *alg_name = NULL;
 	int key_len;
@@ -256,13 +257,14 @@ static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs,
 
 /**
  * ixgbevf_ipsec_add_sa - program device with a security association
+ * @dev: pointer to net device to program
  * @xs: pointer to transformer state struct
  * @extack: extack point to fill failure reason
  **/
-static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs,
+static int ixgbevf_ipsec_add_sa(struct net_device *dev,
+				struct xfrm_state *xs,
 				struct netlink_ext_ack *extack)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	struct ixgbevf_adapter *adapter;
 	struct ixgbevf_ipsec *ipsec;
 	u16 sa_idx;
@@ -271,6 +273,9 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs,
 	adapter = netdev_priv(dev);
 	ipsec = adapter->ipsec;
 
+	if (!(adapter->pf_features & IXGBEVF_PF_SUP_IPSEC))
+		return -EOPNOTSUPP;
+
 	if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
 		NL_SET_ERR_MSG_MOD(extack, "Unsupported protocol for IPsec offload");
 		return -EINVAL;
@@ -310,7 +315,8 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs,
 			rsa.decrypt = xs->ealg || xs->aead;
 
 		/* get the key and salt */
-		ret = ixgbevf_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt);
+		ret = ixgbevf_ipsec_parse_proto_keys(dev, xs, rsa.key,
+						     &rsa.salt);
 		if (ret) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Rx SA table");
 			return ret;
@@ -363,7 +369,8 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs,
 		if (xs->id.proto & IPPROTO_ESP)
 			tsa.encrypt = xs->ealg || xs->aead;
 
-		ret = ixgbevf_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt);
+		ret = ixgbevf_ipsec_parse_proto_keys(dev, xs, tsa.key,
+						     &tsa.salt);
 		if (ret) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Tx SA table");
 			memset(&tsa, 0, sizeof(tsa));
@@ -388,11 +395,12 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs,
 
 /**
  * ixgbevf_ipsec_del_sa - clear out this specific SA
+ * @dev: pointer to net device to program
  * @xs: pointer to transformer state struct
  **/
-static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs)
+static void ixgbevf_ipsec_del_sa(struct net_device *dev,
+				 struct xfrm_state *xs)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	struct ixgbevf_adapter *adapter;
 	struct ixgbevf_ipsec *ipsec;
 	u16 sa_idx;
@@ -400,6 +408,9 @@ static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs)
 	adapter = netdev_priv(dev);
 	ipsec = adapter->ipsec;
 
+	if (!(adapter->pf_features & IXGBEVF_PF_SUP_IPSEC))
+		return;
+
 	if (xs->xso.dir == XFRM_DEV_OFFLOAD_IN) {
 		sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_RX_INDEX;
 
@@ -428,30 +439,9 @@ static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs)
 	}
 }
 
-/**
- * ixgbevf_ipsec_offload_ok - can this packet use the xfrm hw offload
- * @skb: current data packet
- * @xs: pointer to transformer state struct
- **/
-static bool ixgbevf_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
-{
-	if (xs->props.family == AF_INET) {
-		/* Offload with IPv4 options is not supported yet */
-		if (ip_hdr(skb)->ihl != 5)
-			return false;
-	} else {
-		/* Offload with IPv6 extension headers is not support yet */
-		if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr))
-			return false;
-	}
-
-	return true;
-}
-
 static const struct xfrmdev_ops ixgbevf_xfrmdev_ops = {
 	.xdo_dev_state_add = ixgbevf_ipsec_add_sa,
 	.xdo_dev_state_delete = ixgbevf_ipsec_del_sa,
-	.xdo_dev_offload_ok = ixgbevf_ipsec_offload_ok,
 };
 
 /**
@@ -628,6 +618,10 @@ void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter)
 	size_t size;
 
 	switch (adapter->hw.api_version) {
+	case ixgbe_mbox_api_17:
+		if (!(adapter->pf_features & IXGBEVF_PF_SUP_IPSEC))
+			return;
+		break;
 	case ixgbe_mbox_api_14:
 		break;
 	default:
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index 130cb868774c..516a6fdd23d0 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #ifndef _IXGBEVF_H_
 #define _IXGBEVF_H_
@@ -241,23 +241,7 @@ struct ixgbevf_q_vector {
 	char name[IFNAMSIZ + 9];
 
 	/* for dynamic allocation of rings associated with this q_vector */
-	struct ixgbevf_ring ring[0] ____cacheline_internodealigned_in_smp;
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	unsigned int state;
-#define IXGBEVF_QV_STATE_IDLE		0
-#define IXGBEVF_QV_STATE_NAPI		1    /* NAPI owns this QV */
-#define IXGBEVF_QV_STATE_POLL		2    /* poll owns this QV */
-#define IXGBEVF_QV_STATE_DISABLED	4    /* QV is disabled */
-#define IXGBEVF_QV_OWNED	(IXGBEVF_QV_STATE_NAPI | IXGBEVF_QV_STATE_POLL)
-#define IXGBEVF_QV_LOCKED	(IXGBEVF_QV_OWNED | IXGBEVF_QV_STATE_DISABLED)
-#define IXGBEVF_QV_STATE_NAPI_YIELD	8    /* NAPI yielded this QV */
-#define IXGBEVF_QV_STATE_POLL_YIELD	16   /* poll yielded this QV */
-#define IXGBEVF_QV_YIELD	(IXGBEVF_QV_STATE_NAPI_YIELD | \
-				 IXGBEVF_QV_STATE_POLL_YIELD)
-#define IXGBEVF_QV_USER_PEND	(IXGBEVF_QV_STATE_POLL | \
-				 IXGBEVF_QV_STATE_POLL_YIELD)
-	spinlock_t lock;
-#endif /* CONFIG_NET_RX_BUSY_POLL */
+	struct ixgbevf_ring ring[] ____cacheline_internodealigned_in_smp;
 };
 
 /* microsecond values for various ITR rates shifted by 2 to fit itr register
@@ -346,7 +330,6 @@ struct ixgbevf_adapter {
 	int num_rx_queues;
 	struct ixgbevf_ring *rx_ring[MAX_TX_QUEUES]; /* One per active queue */
 	u64 hw_csum_rx_error;
-	u64 hw_rx_no_dma_resources;
 	int num_msix_vectors;
 	u64 alloc_rx_page_failed;
 	u64 alloc_rx_buff_failed;
@@ -363,8 +346,13 @@ struct ixgbevf_adapter {
 	/* structs defined in ixgbe_vf.h */
 	struct ixgbe_hw hw;
 	u16 msg_enable;
-	/* Interrupt Throttle Rate */
-	u32 eitr_param;
+
+	u32 pf_features;
+#define IXGBEVF_PF_SUP_IPSEC		BIT(0)
+#define IXGBEVF_PF_SUP_ESX_MBX		BIT(1)
+
+#define IXGBEVF_SUPPORTED_FEATURES	(IXGBEVF_PF_SUP_IPSEC | \
+					IXGBEVF_PF_SUP_ESX_MBX)
 
 	struct ixgbevf_hw_stats stats;
 
@@ -418,6 +406,8 @@ enum ixgbevf_boards {
 	board_X550EM_x_vf,
 	board_X550EM_x_vf_hv,
 	board_x550em_a_vf,
+	board_e610_vf,
+	board_e610_vf_hv,
 };
 
 enum ixgbevf_xcast_modes {
@@ -434,12 +424,13 @@ extern const struct ixgbevf_info ixgbevf_X550EM_x_vf_info;
 extern const struct ixgbe_mbx_operations ixgbevf_mbx_ops;
 extern const struct ixgbe_mbx_operations ixgbevf_mbx_ops_legacy;
 extern const struct ixgbevf_info ixgbevf_x550em_a_vf_info;
+extern const struct ixgbevf_info ixgbevf_e610_vf_info;
 
 extern const struct ixgbevf_info ixgbevf_82599_vf_hv_info;
 extern const struct ixgbevf_info ixgbevf_X540_vf_hv_info;
 extern const struct ixgbevf_info ixgbevf_X550_vf_hv_info;
 extern const struct ixgbevf_info ixgbevf_X550EM_x_vf_hv_info;
-extern const struct ixgbe_mbx_operations ixgbevf_hv_mbx_ops;
+extern const struct ixgbevf_info ixgbevf_e610_vf_hv_info;
 
 /* needed by ethtool.c */
 extern const char ixgbevf_driver_name[];
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 149911e3002a..d5ce20f47def 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 /******************************************************************************
  Copyright (c)2006 - 2007 Myricom, Inc. for some LRO specific code
@@ -39,7 +39,7 @@ static const char ixgbevf_driver_string[] =
 	"Intel(R) 10 Gigabit PCI Express Virtual Function Network Driver";
 
 static char ixgbevf_copyright[] =
-	"Copyright (c) 2009 - 2018 Intel Corporation.";
+	"Copyright (c) 2009 - 2024 Intel Corporation.";
 
 static const struct ixgbevf_info *ixgbevf_info_tbl[] = {
 	[board_82599_vf]	= &ixgbevf_82599_vf_info,
@@ -51,6 +51,8 @@ static const struct ixgbevf_info *ixgbevf_info_tbl[] = {
 	[board_X550EM_x_vf]	= &ixgbevf_X550EM_x_vf_info,
 	[board_X550EM_x_vf_hv]	= &ixgbevf_X550EM_x_vf_hv_info,
 	[board_x550em_a_vf]	= &ixgbevf_x550em_a_vf_info,
+	[board_e610_vf]         = &ixgbevf_e610_vf_info,
+	[board_e610_vf_hv]      = &ixgbevf_e610_vf_hv_info,
 };
 
 /* ixgbevf_pci_tbl - PCI Device ID Table
@@ -71,6 +73,9 @@ static const struct pci_device_id ixgbevf_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_VF), board_X550EM_x_vf },
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_VF_HV), board_X550EM_x_vf_hv},
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_VF), board_x550em_a_vf },
+	{PCI_VDEVICE_SUB(INTEL, IXGBE_DEV_ID_E610_VF, PCI_ANY_ID,
+			 IXGBE_SUBDEV_ID_E610_VF_HV), board_e610_vf_hv},
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_VF), board_e610_vf},
 	/* required last entry */
 	{0, }
 };
@@ -732,10 +737,6 @@ static bool ixgbevf_cleanup_headers(struct ixgbevf_ring *rx_ring,
 				    union ixgbe_adv_rx_desc *rx_desc,
 				    struct sk_buff *skb)
 {
-	/* XDP packets use error pointer so abort at this point */
-	if (IS_ERR(skb))
-		return true;
-
 	/* verify that the packet does not have any known errors */
 	if (unlikely(ixgbevf_test_staterr(rx_desc,
 					  IXGBE_RXDADV_ERR_FRAME_ERR_MASK))) {
@@ -1044,9 +1045,9 @@ static int ixgbevf_xmit_xdp_ring(struct ixgbevf_ring *ring,
 	return IXGBEVF_XDP_TX;
 }
 
-static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter,
-				       struct ixgbevf_ring  *rx_ring,
-				       struct xdp_buff *xdp)
+static int ixgbevf_run_xdp(struct ixgbevf_adapter *adapter,
+			   struct ixgbevf_ring *rx_ring,
+			   struct xdp_buff *xdp)
 {
 	int result = IXGBEVF_XDP_PASS;
 	struct ixgbevf_ring *xdp_ring;
@@ -1080,7 +1081,7 @@ out_failure:
 		break;
 	}
 xdp_out:
-	return ERR_PTR(-result);
+	return result;
 }
 
 static unsigned int ixgbevf_rx_frame_truesize(struct ixgbevf_ring *rx_ring,
@@ -1122,6 +1123,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 	struct sk_buff *skb = rx_ring->skb;
 	bool xdp_xmit = false;
 	struct xdp_buff xdp;
+	int xdp_res = 0;
 
 	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
 #if (PAGE_SIZE < 8192)
@@ -1165,11 +1167,11 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 			/* At larger PAGE_SIZE, frame_sz depend on len size */
 			xdp.frame_sz = ixgbevf_rx_frame_truesize(rx_ring, size);
 #endif
-			skb = ixgbevf_run_xdp(adapter, rx_ring, &xdp);
+			xdp_res = ixgbevf_run_xdp(adapter, rx_ring, &xdp);
 		}
 
-		if (IS_ERR(skb)) {
-			if (PTR_ERR(skb) == -IXGBEVF_XDP_TX) {
+		if (xdp_res) {
+			if (xdp_res == IXGBEVF_XDP_TX) {
 				xdp_xmit = true;
 				ixgbevf_rx_buffer_flip(rx_ring, rx_buffer,
 						       size);
@@ -1189,7 +1191,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 		}
 
 		/* exit if we failed to retrieve a buffer */
-		if (!skb) {
+		if (!xdp_res && !skb) {
 			rx_ring->rx_stats.alloc_rx_buff_failed++;
 			rx_buffer->pagecnt_bias++;
 			break;
@@ -1203,7 +1205,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 			continue;
 
 		/* verify the packet layout is correct */
-		if (ixgbevf_cleanup_headers(rx_ring, rx_desc, skb)) {
+		if (xdp_res || ixgbevf_cleanup_headers(rx_ring, rx_desc, skb)) {
 			skb = NULL;
 			continue;
 		}
@@ -2269,10 +2271,36 @@ static void ixgbevf_init_last_counter_stats(struct ixgbevf_adapter *adapter)
 	adapter->stats.base_vfmprc = adapter->stats.last_vfmprc;
 }
 
+/**
+ * ixgbevf_set_features - Set features supported by PF
+ * @adapter: pointer to the adapter struct
+ *
+ * Negotiate with PF supported features and then set pf_features accordingly.
+ */
+static void ixgbevf_set_features(struct ixgbevf_adapter *adapter)
+{
+	u32 *pf_features = &adapter->pf_features;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	err = hw->mac.ops.negotiate_features(hw, pf_features);
+	if (err && err != -EOPNOTSUPP)
+		netdev_dbg(adapter->netdev,
+			   "PF feature negotiation failed.\n");
+
+	/* Address also pre API 1.7 cases */
+	if (hw->api_version == ixgbe_mbox_api_14)
+		*pf_features |= IXGBEVF_PF_SUP_IPSEC;
+	else if (hw->api_version == ixgbe_mbox_api_15)
+		*pf_features |= IXGBEVF_PF_SUP_ESX_MBX;
+}
+
 static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	static const int api[] = {
+		ixgbe_mbox_api_17,
+		ixgbe_mbox_api_16,
 		ixgbe_mbox_api_15,
 		ixgbe_mbox_api_14,
 		ixgbe_mbox_api_13,
@@ -2292,7 +2320,9 @@ static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter)
 		idx++;
 	}
 
-	if (hw->api_version >= ixgbe_mbox_api_15) {
+	ixgbevf_set_features(adapter);
+
+	if (adapter->pf_features & IXGBEVF_PF_SUP_ESX_MBX) {
 		hw->mbx.ops.init_params(hw);
 		memcpy(&hw->mbx.ops, &ixgbevf_mbx_ops,
 		       sizeof(struct ixgbe_mbx_operations));
@@ -2512,7 +2542,7 @@ void ixgbevf_down(struct ixgbevf_adapter *adapter)
 
 	ixgbevf_napi_disable_all(adapter);
 
-	del_timer_sync(&adapter->service_timer);
+	timer_delete_sync(&adapter->service_timer);
 
 	/* disable transmits in the hardware now that interrupts are off */
 	for (i = 0; i < adapter->num_tx_queues; i++) {
@@ -2649,6 +2679,8 @@ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter)
 		case ixgbe_mbox_api_13:
 		case ixgbe_mbox_api_14:
 		case ixgbe_mbox_api_15:
+		case ixgbe_mbox_api_16:
+		case ixgbe_mbox_api_17:
 			if (adapter->xdp_prog &&
 			    hw->mac.max_tx_queues == rss)
 				rss = rss > 3 ? 2 : 1;
@@ -3174,8 +3206,8 @@ void ixgbevf_update_stats(struct ixgbevf_adapter *adapter)
  **/
 static void ixgbevf_service_timer(struct timer_list *t)
 {
-	struct ixgbevf_adapter *adapter = from_timer(adapter, t,
-						     service_timer);
+	struct ixgbevf_adapter *adapter = timer_container_of(adapter, t,
+							     service_timer);
 
 	/* Reset the timer */
 	mod_timer(&adapter->service_timer, (HZ * 2) + jiffies);
@@ -4321,7 +4353,7 @@ static int ixgbevf_resume(struct device *dev_d)
 	struct pci_dev *pdev = to_pci_dev(dev_d);
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
-	u32 err;
+	int err;
 
 	adapter->hw.hw_addr = adapter->io_addr;
 	smp_mb__before_atomic();
@@ -4643,6 +4675,8 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_15:
+	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE -
 				  (ETH_HLEN + ETH_FCS_LEN);
 		break;
@@ -4693,6 +4727,9 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	case ixgbe_mac_X540_vf:
 		dev_info(&pdev->dev, "Intel(R) X540 Virtual Function\n");
 		break;
+	case ixgbe_mac_e610_vf:
+		dev_info(&pdev->dev, "Intel(R) E610 Virtual Function\n");
+		break;
 	case ixgbe_mac_82599_vf:
 	default:
 		dev_info(&pdev->dev, "Intel(R) 82599 Virtual Function\n");
diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.c b/drivers/net/ethernet/intel/ixgbevf/mbx.c
index a55dd978f7ca..24d0237e7a99 100644
--- a/drivers/net/ethernet/intel/ixgbevf/mbx.c
+++ b/drivers/net/ethernet/intel/ixgbevf/mbx.c
@@ -505,15 +505,3 @@ const struct ixgbe_mbx_operations ixgbevf_mbx_ops_legacy = {
 	.check_for_ack	= ixgbevf_check_for_ack_vf,
 	.check_for_rst	= ixgbevf_check_for_rst_vf,
 };
-
-/* Mailbox operations when running on Hyper-V.
- * On Hyper-V, PF/VF communication is not through the
- * hardware mailbox; this communication is through
- * a software mediated path.
- * Most mail box operations are noop while running on
- * Hyper-V.
- */
-const struct ixgbe_mbx_operations ixgbevf_hv_mbx_ops = {
-	.init_params	= ixgbevf_init_mbx_params_vf,
-	.check_for_rst	= ixgbevf_check_for_rst_vf,
-};
diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.h b/drivers/net/ethernet/intel/ixgbevf/mbx.h
index 835bbcc5cc8e..a8ed23ee66aa 100644
--- a/drivers/net/ethernet/intel/ixgbevf/mbx.h
+++ b/drivers/net/ethernet/intel/ixgbevf/mbx.h
@@ -66,6 +66,8 @@ enum ixgbe_pfvf_api_rev {
 	ixgbe_mbox_api_13,	/* API version 1.3, linux/freebsd VF driver */
 	ixgbe_mbox_api_14,	/* API version 1.4, linux/freebsd VF driver */
 	ixgbe_mbox_api_15,	/* API version 1.5, linux/freebsd VF driver */
+	ixgbe_mbox_api_16,      /* API version 1.6, linux/freebsd VF driver */
+	ixgbe_mbox_api_17,	/* API version 1.7, linux/freebsd VF driver */
 	/* This value should always be last */
 	ixgbe_mbox_api_unknown,	/* indicates that API version is not known */
 };
@@ -102,6 +104,12 @@ enum ixgbe_pfvf_api_rev {
 
 #define IXGBE_VF_GET_LINK_STATE 0x10 /* get vf link state */
 
+/* mailbox API, version 1.6 VF requests */
+#define IXGBE_VF_GET_PF_LINK_STATE	0x11 /* request PF to send link info */
+
+/* mailbox API, version 1.7 VF requests */
+#define IXGBE_VF_FEATURES_NEGOTIATE	0x12 /* get features supported by PF*/
+
 /* length of permanent address message returned from PF */
 #define IXGBE_VF_PERMADDR_MSG_LEN	4
 /* word in permanent address message with the current multicast type */
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index 1641d00d8ed3..74d320879513 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include "vf.h"
 #include "ixgbevf.h"
@@ -255,7 +255,7 @@ static s32 ixgbevf_set_uc_addr_vf(struct ixgbe_hw *hw, u32 index, u8 *addr)
 
 	memset(msgbuf, 0, sizeof(msgbuf));
 	/* If index is one then this is the start of a new list and needs
-	 * indication to the PF so it can do it's own list management.
+	 * indication to the PF so it can do its own list management.
 	 * If it is zero then that tells the PF to just clear all of
 	 * this VF's macvlans and there is no new list.
 	 */
@@ -313,6 +313,8 @@ int ixgbevf_get_reta_locked(struct ixgbe_hw *hw, u32 *reta, int num_rx_queues)
 	 * is not supported for this device type.
 	 */
 	switch (hw->api_version) {
+	case ixgbe_mbox_api_17:
+	case ixgbe_mbox_api_16:
 	case ixgbe_mbox_api_15:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_13:
@@ -382,6 +384,8 @@ int ixgbevf_get_rss_key_locked(struct ixgbe_hw *hw, u8 *rss_key)
 	 * or if the operation is not supported for this device type.
 	 */
 	switch (hw->api_version) {
+	case ixgbe_mbox_api_17:
+	case ixgbe_mbox_api_16:
 	case ixgbe_mbox_api_15:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_13:
@@ -552,6 +556,8 @@ static s32 ixgbevf_update_xcast_mode(struct ixgbe_hw *hw, int xcast_mode)
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_15:
+	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -625,6 +631,85 @@ static s32 ixgbevf_hv_get_link_state_vf(struct ixgbe_hw *hw, bool *link_state)
 }
 
 /**
+ * ixgbevf_get_pf_link_state - Get PF's link status
+ * @hw: pointer to the HW structure
+ * @speed: link speed
+ * @link_up: indicate if link is up/down
+ *
+ * Ask PF to provide link_up state and speed of the link.
+ *
+ * Return: IXGBE_ERR_MBX in the case of mailbox error,
+ * -EOPNOTSUPP if the op is not supported or 0 on success.
+ */
+static int ixgbevf_get_pf_link_state(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
+				     bool *link_up)
+{
+	u32 msgbuf[3] = {};
+	int err;
+
+	switch (hw->api_version) {
+	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	msgbuf[0] = IXGBE_VF_GET_PF_LINK_STATE;
+
+	err = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf,
+					 ARRAY_SIZE(msgbuf));
+	if (err || (msgbuf[0] & IXGBE_VT_MSGTYPE_FAILURE)) {
+		err = IXGBE_ERR_MBX;
+		*speed = IXGBE_LINK_SPEED_UNKNOWN;
+		/* No need to set @link_up to false as it will be done by
+		 * ixgbe_check_mac_link_vf().
+		 */
+	} else {
+		*speed = msgbuf[1];
+		*link_up = msgbuf[2];
+	}
+
+	return err;
+}
+
+/**
+ * ixgbevf_negotiate_features_vf - negotiate supported features with PF driver
+ * @hw: pointer to the HW structure
+ * @pf_features: bitmask of features supported by PF
+ *
+ * Return: IXGBE_ERR_MBX in the  case of mailbox error,
+ * -EOPNOTSUPP if the op is not supported or 0 on success.
+ */
+static int ixgbevf_negotiate_features_vf(struct ixgbe_hw *hw, u32 *pf_features)
+{
+	u32 msgbuf[2] = {};
+	int err;
+
+	switch (hw->api_version) {
+	case ixgbe_mbox_api_17:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	msgbuf[0] = IXGBE_VF_FEATURES_NEGOTIATE;
+	msgbuf[1] = IXGBEVF_SUPPORTED_FEATURES;
+
+	err = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf,
+					 ARRAY_SIZE(msgbuf));
+
+	if (err || (msgbuf[0] & IXGBE_VT_MSGTYPE_FAILURE)) {
+		err = IXGBE_ERR_MBX;
+		*pf_features = 0x0;
+	} else {
+		*pf_features = msgbuf[1];
+	}
+
+	return err;
+}
+
+/**
  *  ixgbevf_set_vfta_vf - Set/Unset VLAN filter table address
  *  @hw: pointer to the HW structure
  *  @vlan: 12 bit VLAN ID
@@ -659,6 +744,58 @@ mbx_err:
 }
 
 /**
+ * ixgbe_read_vflinks - Read VFLINKS register
+ * @hw: pointer to the HW structure
+ * @speed: link speed
+ * @link_up: indicate if link is up/down
+ *
+ * Get linkup status and link speed from the VFLINKS register.
+ */
+static void ixgbe_read_vflinks(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
+			       bool *link_up)
+{
+	u32 vflinks = IXGBE_READ_REG(hw, IXGBE_VFLINKS);
+
+	/* if link status is down no point in checking to see if PF is up */
+	if (!(vflinks & IXGBE_LINKS_UP)) {
+		*link_up = false;
+		return;
+	}
+
+	/* for SFP+ modules and DA cables on 82599 it can take up to 500usecs
+	 * before the link status is correct
+	 */
+	if (hw->mac.type == ixgbe_mac_82599_vf) {
+		for (int i = 0; i < 5; i++) {
+			udelay(100);
+			vflinks = IXGBE_READ_REG(hw, IXGBE_VFLINKS);
+
+			if (!(vflinks & IXGBE_LINKS_UP)) {
+				*link_up = false;
+				return;
+			}
+		}
+	}
+
+	/* We reached this point so there's link */
+	*link_up = true;
+
+	switch (vflinks & IXGBE_LINKS_SPEED_82599) {
+	case IXGBE_LINKS_SPEED_10G_82599:
+		*speed = IXGBE_LINK_SPEED_10GB_FULL;
+		break;
+	case IXGBE_LINKS_SPEED_1G_82599:
+		*speed = IXGBE_LINK_SPEED_1GB_FULL;
+		break;
+	case IXGBE_LINKS_SPEED_100_82599:
+		*speed = IXGBE_LINK_SPEED_100_FULL;
+		break;
+	default:
+		*speed = IXGBE_LINK_SPEED_UNKNOWN;
+	}
+}
+
+/**
  * ixgbevf_hv_set_vfta_vf - * Hyper-V variant - just a stub.
  * @hw: unused
  * @vlan: unused
@@ -702,10 +839,10 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
 				     bool *link_up,
 				     bool autoneg_wait_to_complete)
 {
+	struct ixgbevf_adapter *adapter = hw->back;
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
 	struct ixgbe_mac_info *mac = &hw->mac;
 	s32 ret_val = 0;
-	u32 links_reg;
 	u32 in_msg = 0;
 
 	/* If we were hit with a reset drop the link */
@@ -715,43 +852,21 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
 	if (!mac->get_link_status)
 		goto out;
 
-	/* if link status is down no point in checking to see if pf is up */
-	links_reg = IXGBE_READ_REG(hw, IXGBE_VFLINKS);
-	if (!(links_reg & IXGBE_LINKS_UP))
-		goto out;
-
-	/* for SFP+ modules and DA cables on 82599 it can take up to 500usecs
-	 * before the link status is correct
-	 */
-	if (mac->type == ixgbe_mac_82599_vf) {
-		int i;
-
-		for (i = 0; i < 5; i++) {
-			udelay(100);
-			links_reg = IXGBE_READ_REG(hw, IXGBE_VFLINKS);
-
-			if (!(links_reg & IXGBE_LINKS_UP))
-				goto out;
-		}
-	}
-
-	switch (links_reg & IXGBE_LINKS_SPEED_82599) {
-	case IXGBE_LINKS_SPEED_10G_82599:
-		*speed = IXGBE_LINK_SPEED_10GB_FULL;
-		break;
-	case IXGBE_LINKS_SPEED_1G_82599:
-		*speed = IXGBE_LINK_SPEED_1GB_FULL;
-		break;
-	case IXGBE_LINKS_SPEED_100_82599:
-		*speed = IXGBE_LINK_SPEED_100_FULL;
-		break;
+	if (hw->mac.type == ixgbe_mac_e610_vf) {
+		ret_val = ixgbevf_get_pf_link_state(hw, speed, link_up);
+		if (ret_val)
+			goto out;
+	} else {
+		ixgbe_read_vflinks(hw, speed, link_up);
+		if (*link_up == false)
+			goto out;
 	}
 
 	/* if the read failed it could just be a mailbox collision, best wait
 	 * until we are called again and don't report an error
 	 */
 	if (mbx->ops.read(hw, &in_msg, 1)) {
-		if (hw->api_version >= ixgbe_mbox_api_15)
+		if (adapter->pf_features & IXGBEVF_PF_SUP_ESX_MBX)
 			mac->get_link_status = false;
 		goto out;
 	}
@@ -951,6 +1066,8 @@ int ixgbevf_get_queues(struct ixgbe_hw *hw, unsigned int *num_tcs,
 	case ixgbe_mbox_api_13:
 	case ixgbe_mbox_api_14:
 	case ixgbe_mbox_api_15:
+	case ixgbe_mbox_api_16:
+	case ixgbe_mbox_api_17:
 		break;
 	default:
 		return 0;
@@ -1005,6 +1122,7 @@ static const struct ixgbe_mac_operations ixgbevf_mac_ops = {
 	.setup_link		= ixgbevf_setup_mac_link_vf,
 	.check_link		= ixgbevf_check_mac_link_vf,
 	.negotiate_api_version	= ixgbevf_negotiate_api_version_vf,
+	.negotiate_features	= ixgbevf_negotiate_features_vf,
 	.set_rar		= ixgbevf_set_rar_vf,
 	.update_mc_addr_list	= ixgbevf_update_mc_addr_list_vf,
 	.update_xcast_mode	= ixgbevf_update_xcast_mode,
@@ -1076,3 +1194,13 @@ const struct ixgbevf_info ixgbevf_x550em_a_vf_info = {
 	.mac = ixgbe_mac_x550em_a_vf,
 	.mac_ops = &ixgbevf_mac_ops,
 };
+
+const struct ixgbevf_info ixgbevf_e610_vf_info = {
+	.mac                    = ixgbe_mac_e610_vf,
+	.mac_ops                = &ixgbevf_mac_ops,
+};
+
+const struct ixgbevf_info ixgbevf_e610_vf_hv_info = {
+	.mac            = ixgbe_mac_e610_vf,
+	.mac_ops        = &ixgbevf_hv_mac_ops,
+};
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h
index b4eef5b6c172..4f19b8900c29 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #ifndef __IXGBE_VF_H__
 #define __IXGBE_VF_H__
@@ -26,6 +26,7 @@ struct ixgbe_mac_operations {
 	s32 (*stop_adapter)(struct ixgbe_hw *);
 	s32 (*get_bus_info)(struct ixgbe_hw *);
 	s32 (*negotiate_api_version)(struct ixgbe_hw *hw, int api);
+	int (*negotiate_features)(struct ixgbe_hw *hw, u32 *pf_features);
 
 	/* Link */
 	s32 (*setup_link)(struct ixgbe_hw *, ixgbe_link_speed, bool, bool);
@@ -54,6 +55,8 @@ enum ixgbe_mac_type {
 	ixgbe_mac_X550_vf,
 	ixgbe_mac_X550EM_x_vf,
 	ixgbe_mac_x550em_a_vf,
+	ixgbe_mac_e610,
+	ixgbe_mac_e610_vf,
 	ixgbe_num_macs
 };
 
diff --git a/drivers/net/ethernet/intel/libeth/Kconfig b/drivers/net/ethernet/intel/libeth/Kconfig
index 480293b71dbc..2445b979c499 100644
--- a/drivers/net/ethernet/intel/libeth/Kconfig
+++ b/drivers/net/ethernet/intel/libeth/Kconfig
@@ -1,9 +1,15 @@
 # SPDX-License-Identifier: GPL-2.0-only
-# Copyright (C) 2024 Intel Corporation
+# Copyright (C) 2024-2025 Intel Corporation
 
 config LIBETH
-	tristate
+	tristate "Common Ethernet library (libeth)" if COMPILE_TEST
 	select PAGE_POOL
 	help
 	  libeth is a common library containing routines shared between several
 	  drivers, but not yet promoted to the generic kernel API.
+
+config LIBETH_XDP
+	tristate "Common XDP library (libeth_xdp)" if COMPILE_TEST
+	select LIBETH
+	help
+	  XDP and XSk helpers based on libeth hotpath management.
diff --git a/drivers/net/ethernet/intel/libeth/Makefile b/drivers/net/ethernet/intel/libeth/Makefile
index 52492b081132..350bc0b38bad 100644
--- a/drivers/net/ethernet/intel/libeth/Makefile
+++ b/drivers/net/ethernet/intel/libeth/Makefile
@@ -1,6 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0-only
-# Copyright (C) 2024 Intel Corporation
+# Copyright (C) 2024-2025 Intel Corporation
 
 obj-$(CONFIG_LIBETH)		+= libeth.o
 
 libeth-y			:= rx.o
+libeth-y			+= tx.o
+
+obj-$(CONFIG_LIBETH_XDP)	+= libeth_xdp.o
+
+libeth_xdp-y			+= xdp.o
+libeth_xdp-y			+= xsk.o
diff --git a/drivers/net/ethernet/intel/libeth/priv.h b/drivers/net/ethernet/intel/libeth/priv.h
new file mode 100644
index 000000000000..9b811d31015c
--- /dev/null
+++ b/drivers/net/ethernet/intel/libeth/priv.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2025 Intel Corporation */
+
+#ifndef __LIBETH_PRIV_H
+#define __LIBETH_PRIV_H
+
+#include <linux/types.h>
+
+/* XDP */
+
+enum xdp_action;
+struct libeth_xdp_buff;
+struct libeth_xdp_tx_frame;
+struct skb_shared_info;
+struct xdp_frame_bulk;
+
+extern const struct xsk_tx_metadata_ops libeth_xsktmo_slow;
+
+void libeth_xsk_tx_return_bulk(const struct libeth_xdp_tx_frame *bq,
+			       u32 count);
+u32 libeth_xsk_prog_exception(struct libeth_xdp_buff *xdp, enum xdp_action act,
+			      int ret);
+
+struct libeth_xdp_ops {
+	void	(*bulk)(const struct skb_shared_info *sinfo,
+			struct xdp_frame_bulk *bq, bool frags);
+	void	(*xsk)(struct libeth_xdp_buff *xdp);
+};
+
+void libeth_attach_xdp(const struct libeth_xdp_ops *ops);
+
+static inline void libeth_detach_xdp(void)
+{
+	libeth_attach_xdp(NULL);
+}
+
+#endif /* __LIBETH_PRIV_H */
diff --git a/drivers/net/ethernet/intel/libeth/rx.c b/drivers/net/ethernet/intel/libeth/rx.c
index 66d1d23b8ad2..62521a1f4ec9 100644
--- a/drivers/net/ethernet/intel/libeth/rx.c
+++ b/drivers/net/ethernet/intel/libeth/rx.c
@@ -1,5 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/* Copyright (C) 2024 Intel Corporation */
+/* Copyright (C) 2024-2025 Intel Corporation */
+
+#define DEFAULT_SYMBOL_NAMESPACE	"LIBETH"
+
+#include <linux/export.h>
 
 #include <net/libeth/rx.h>
 
@@ -68,7 +72,7 @@ static u32 libeth_rx_hw_len_truesize(const struct page_pool_params *pp,
 static bool libeth_rx_page_pool_params(struct libeth_fq *fq,
 				       struct page_pool_params *pp)
 {
-	pp->offset = LIBETH_SKB_HEADROOM;
+	pp->offset = fq->xdp ? LIBETH_XDP_HEADROOM : LIBETH_SKB_HEADROOM;
 	/* HW-writeable / syncable length per one page */
 	pp->max_len = LIBETH_RX_PAGE_LEN(pp->offset);
 
@@ -155,11 +159,12 @@ int libeth_rx_fq_create(struct libeth_fq *fq, struct napi_struct *napi)
 		.dev		= napi->dev->dev.parent,
 		.netdev		= napi->dev,
 		.napi		= napi,
-		.dma_dir	= DMA_FROM_DEVICE,
 	};
 	struct libeth_fqe *fqes;
 	struct page_pool *pool;
-	bool ret;
+	int ret;
+
+	pp.dma_dir = fq->xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
 
 	if (!fq->hsplit)
 		ret = libeth_rx_page_pool_params(fq, &pp);
@@ -173,20 +178,28 @@ int libeth_rx_fq_create(struct libeth_fq *fq, struct napi_struct *napi)
 		return PTR_ERR(pool);
 
 	fqes = kvcalloc_node(fq->count, sizeof(*fqes), GFP_KERNEL, fq->nid);
-	if (!fqes)
+	if (!fqes) {
+		ret = -ENOMEM;
 		goto err_buf;
+	}
+
+	ret = xdp_reg_page_pool(pool);
+	if (ret)
+		goto err_mem;
 
 	fq->fqes = fqes;
 	fq->pp = pool;
 
 	return 0;
 
+err_mem:
+	kvfree(fqes);
 err_buf:
 	page_pool_destroy(pool);
 
-	return -ENOMEM;
+	return ret;
 }
-EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_create, "LIBETH");
+EXPORT_SYMBOL_GPL(libeth_rx_fq_create);
 
 /**
  * libeth_rx_fq_destroy - destroy a &page_pool created by libeth
@@ -194,22 +207,23 @@ EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_create, "LIBETH");
  */
 void libeth_rx_fq_destroy(struct libeth_fq *fq)
 {
+	xdp_unreg_page_pool(fq->pp);
 	kvfree(fq->fqes);
 	page_pool_destroy(fq->pp);
 }
-EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_destroy, "LIBETH");
+EXPORT_SYMBOL_GPL(libeth_rx_fq_destroy);
 
 /**
- * libeth_rx_recycle_slow - recycle a libeth page from the NAPI context
- * @page: page to recycle
+ * libeth_rx_recycle_slow - recycle libeth netmem
+ * @netmem: network memory to recycle
  *
  * To be used on exceptions or rare cases not requiring fast inline recycling.
  */
-void libeth_rx_recycle_slow(struct page *page)
+void __cold libeth_rx_recycle_slow(netmem_ref netmem)
 {
-	page_pool_recycle_direct(page->pp, page);
+	page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false);
 }
-EXPORT_SYMBOL_NS_GPL(libeth_rx_recycle_slow, "LIBETH");
+EXPORT_SYMBOL_GPL(libeth_rx_recycle_slow);
 
 /* Converting abstract packet type numbers into a software structure with
  * the packet parameters to do O(1) lookup on Rx.
@@ -251,7 +265,7 @@ void libeth_rx_pt_gen_hash_type(struct libeth_rx_pt *pt)
 	pt->hash_type |= libeth_rx_pt_xdp_iprot[pt->inner_prot];
 	pt->hash_type |= libeth_rx_pt_xdp_pl[pt->payload_layer];
 }
-EXPORT_SYMBOL_NS_GPL(libeth_rx_pt_gen_hash_type, "LIBETH");
+EXPORT_SYMBOL_GPL(libeth_rx_pt_gen_hash_type);
 
 /* Module */
 
diff --git a/drivers/net/ethernet/intel/libeth/tx.c b/drivers/net/ethernet/intel/libeth/tx.c
new file mode 100644
index 000000000000..e0167f43d2a8
--- /dev/null
+++ b/drivers/net/ethernet/intel/libeth/tx.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2025 Intel Corporation */
+
+#define DEFAULT_SYMBOL_NAMESPACE	"LIBETH"
+
+#include <net/libeth/xdp.h>
+
+#include "priv.h"
+
+/* Tx buffer completion */
+
+DEFINE_STATIC_CALL_NULL(bulk, libeth_xdp_return_buff_bulk);
+DEFINE_STATIC_CALL_NULL(xsk, libeth_xsk_buff_free_slow);
+
+/**
+ * libeth_tx_complete_any - perform Tx completion for one SQE of any type
+ * @sqe: Tx buffer to complete
+ * @cp: polling params
+ *
+ * Can be used to complete both regular and XDP SQEs, for example when
+ * destroying queues.
+ * When libeth_xdp is not loaded, XDPSQEs won't be handled.
+ */
+void libeth_tx_complete_any(struct libeth_sqe *sqe, struct libeth_cq_pp *cp)
+{
+	if (sqe->type >= __LIBETH_SQE_XDP_START)
+		__libeth_xdp_complete_tx(sqe, cp, static_call(bulk),
+					 static_call(xsk));
+	else
+		libeth_tx_complete(sqe, cp);
+}
+EXPORT_SYMBOL_GPL(libeth_tx_complete_any);
+
+/* Module */
+
+void libeth_attach_xdp(const struct libeth_xdp_ops *ops)
+{
+	static_call_update(bulk, ops ? ops->bulk : NULL);
+	static_call_update(xsk, ops ? ops->xsk : NULL);
+}
+EXPORT_SYMBOL_GPL(libeth_attach_xdp);
diff --git a/drivers/net/ethernet/intel/libeth/xdp.c b/drivers/net/ethernet/intel/libeth/xdp.c
new file mode 100644
index 000000000000..d4ac027d9584
--- /dev/null
+++ b/drivers/net/ethernet/intel/libeth/xdp.c
@@ -0,0 +1,451 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2025 Intel Corporation */
+
+#define DEFAULT_SYMBOL_NAMESPACE	"LIBETH_XDP"
+
+#include <linux/export.h>
+
+#include <net/libeth/xdp.h>
+
+#include "priv.h"
+
+/* XDPSQ sharing */
+
+DEFINE_STATIC_KEY_FALSE(libeth_xdpsq_share);
+EXPORT_SYMBOL_GPL(libeth_xdpsq_share);
+
+void __libeth_xdpsq_get(struct libeth_xdpsq_lock *lock,
+			const struct net_device *dev)
+{
+	bool warn;
+
+	spin_lock_init(&lock->lock);
+	lock->share = true;
+
+	warn = !static_key_enabled(&libeth_xdpsq_share);
+	static_branch_inc(&libeth_xdpsq_share);
+
+	if (warn && net_ratelimit())
+		netdev_warn(dev, "XDPSQ sharing enabled, possible XDP Tx slowdown\n");
+}
+EXPORT_SYMBOL_GPL(__libeth_xdpsq_get);
+
+void __libeth_xdpsq_put(struct libeth_xdpsq_lock *lock,
+			const struct net_device *dev)
+{
+	static_branch_dec(&libeth_xdpsq_share);
+
+	if (!static_key_enabled(&libeth_xdpsq_share) && net_ratelimit())
+		netdev_notice(dev, "XDPSQ sharing disabled\n");
+
+	lock->share = false;
+}
+EXPORT_SYMBOL_GPL(__libeth_xdpsq_put);
+
+void __acquires(&lock->lock)
+__libeth_xdpsq_lock(struct libeth_xdpsq_lock *lock)
+{
+	spin_lock(&lock->lock);
+}
+EXPORT_SYMBOL_GPL(__libeth_xdpsq_lock);
+
+void __releases(&lock->lock)
+__libeth_xdpsq_unlock(struct libeth_xdpsq_lock *lock)
+{
+	spin_unlock(&lock->lock);
+}
+EXPORT_SYMBOL_GPL(__libeth_xdpsq_unlock);
+
+/* XDPSQ clean-up timers */
+
+/**
+ * libeth_xdpsq_init_timer - initialize an XDPSQ clean-up timer
+ * @timer: timer to initialize
+ * @xdpsq: queue this timer belongs to
+ * @lock: corresponding XDPSQ lock
+ * @poll: queue polling/completion function
+ *
+ * XDPSQ clean-up timers must be set up before using at the queue configuration
+ * time. Set the required pointers and the cleaning callback.
+ */
+void libeth_xdpsq_init_timer(struct libeth_xdpsq_timer *timer, void *xdpsq,
+			     struct libeth_xdpsq_lock *lock,
+			     void (*poll)(struct work_struct *work))
+{
+	timer->xdpsq = xdpsq;
+	timer->lock = lock;
+
+	INIT_DELAYED_WORK(&timer->dwork, poll);
+}
+EXPORT_SYMBOL_GPL(libeth_xdpsq_init_timer);
+
+/* ``XDP_TX`` bulking */
+
+static void __cold
+libeth_xdp_tx_return_one(const struct libeth_xdp_tx_frame *frm)
+{
+	if (frm->len_fl & LIBETH_XDP_TX_MULTI)
+		libeth_xdp_return_frags(frm->data + frm->soff, true);
+
+	libeth_xdp_return_va(frm->data, true);
+}
+
+static void __cold
+libeth_xdp_tx_return_bulk(const struct libeth_xdp_tx_frame *bq, u32 count)
+{
+	for (u32 i = 0; i < count; i++) {
+		const struct libeth_xdp_tx_frame *frm = &bq[i];
+
+		if (!(frm->len_fl & LIBETH_XDP_TX_FIRST))
+			continue;
+
+		libeth_xdp_tx_return_one(frm);
+	}
+}
+
+static void __cold libeth_trace_xdp_exception(const struct net_device *dev,
+					      const struct bpf_prog *prog,
+					      u32 act)
+{
+	trace_xdp_exception(dev, prog, act);
+}
+
+/**
+ * libeth_xdp_tx_exception - handle Tx exceptions of XDP frames
+ * @bq: XDP Tx frame bulk
+ * @sent: number of frames sent successfully (from this bulk)
+ * @flags: internal libeth_xdp flags (XSk, .ndo_xdp_xmit etc.)
+ *
+ * Cold helper used by __libeth_xdp_tx_flush_bulk(), do not call directly.
+ * Reports XDP Tx exceptions, frees the frames that won't be sent or adjust
+ * the Tx bulk to try again later.
+ */
+void __cold libeth_xdp_tx_exception(struct libeth_xdp_tx_bulk *bq, u32 sent,
+				    u32 flags)
+{
+	const struct libeth_xdp_tx_frame *pos = &bq->bulk[sent];
+	u32 left = bq->count - sent;
+
+	if (!(flags & LIBETH_XDP_TX_NDO))
+		libeth_trace_xdp_exception(bq->dev, bq->prog, XDP_TX);
+
+	if (!(flags & LIBETH_XDP_TX_DROP)) {
+		memmove(bq->bulk, pos, left * sizeof(*bq->bulk));
+		bq->count = left;
+
+		return;
+	}
+
+	if (flags & LIBETH_XDP_TX_XSK)
+		libeth_xsk_tx_return_bulk(pos, left);
+	else if (!(flags & LIBETH_XDP_TX_NDO))
+		libeth_xdp_tx_return_bulk(pos, left);
+	else
+		libeth_xdp_xmit_return_bulk(pos, left, bq->dev);
+
+	bq->count = 0;
+}
+EXPORT_SYMBOL_GPL(libeth_xdp_tx_exception);
+
+/* .ndo_xdp_xmit() implementation */
+
+u32 __cold libeth_xdp_xmit_return_bulk(const struct libeth_xdp_tx_frame *bq,
+				       u32 count, const struct net_device *dev)
+{
+	u32 n = 0;
+
+	for (u32 i = 0; i < count; i++) {
+		const struct libeth_xdp_tx_frame *frm = &bq[i];
+		dma_addr_t dma;
+
+		if (frm->flags & LIBETH_XDP_TX_FIRST)
+			dma = *libeth_xdp_xmit_frame_dma(frm->xdpf);
+		else
+			dma = dma_unmap_addr(frm, dma);
+
+		dma_unmap_page(dev->dev.parent, dma, dma_unmap_len(frm, len),
+			       DMA_TO_DEVICE);
+
+		/* Actual xdp_frames are freed by the core */
+		n += !!(frm->flags & LIBETH_XDP_TX_FIRST);
+	}
+
+	return n;
+}
+EXPORT_SYMBOL_GPL(libeth_xdp_xmit_return_bulk);
+
+/* Rx polling path */
+
+/**
+ * libeth_xdp_load_stash - recreate an &xdp_buff from libeth_xdp buffer stash
+ * @dst: target &libeth_xdp_buff to initialize
+ * @src: source stash
+ *
+ * External helper used by libeth_xdp_init_buff(), do not call directly.
+ * Recreate an onstack &libeth_xdp_buff using the stash saved earlier.
+ * The only field untouched (rxq) is initialized later in the
+ * abovementioned function.
+ */
+void libeth_xdp_load_stash(struct libeth_xdp_buff *dst,
+			   const struct libeth_xdp_buff_stash *src)
+{
+	dst->data = src->data;
+	dst->base.data_end = src->data + src->len;
+	dst->base.data_meta = src->data;
+	dst->base.data_hard_start = src->data - src->headroom;
+
+	dst->base.frame_sz = src->frame_sz;
+	dst->base.flags = src->flags;
+}
+EXPORT_SYMBOL_GPL(libeth_xdp_load_stash);
+
+/**
+ * libeth_xdp_save_stash - convert &xdp_buff to a libeth_xdp buffer stash
+ * @dst: target &libeth_xdp_buff_stash to initialize
+ * @src: source XDP buffer
+ *
+ * External helper used by libeth_xdp_save_buff(), do not call directly.
+ * Use the fields from the passed XDP buffer to initialize the stash on the
+ * queue, so that a partially received frame can be finished later during
+ * the next NAPI poll.
+ */
+void libeth_xdp_save_stash(struct libeth_xdp_buff_stash *dst,
+			   const struct libeth_xdp_buff *src)
+{
+	dst->data = src->data;
+	dst->headroom = src->data - src->base.data_hard_start;
+	dst->len = src->base.data_end - src->data;
+
+	dst->frame_sz = src->base.frame_sz;
+	dst->flags = src->base.flags;
+
+	WARN_ON_ONCE(dst->flags != src->base.flags);
+}
+EXPORT_SYMBOL_GPL(libeth_xdp_save_stash);
+
+void __libeth_xdp_return_stash(struct libeth_xdp_buff_stash *stash)
+{
+	LIBETH_XDP_ONSTACK_BUFF(xdp);
+
+	libeth_xdp_load_stash(xdp, stash);
+	libeth_xdp_return_buff_slow(xdp);
+
+	stash->data = NULL;
+}
+EXPORT_SYMBOL_GPL(__libeth_xdp_return_stash);
+
+/**
+ * libeth_xdp_return_buff_slow - free &libeth_xdp_buff
+ * @xdp: buffer to free/return
+ *
+ * Slowpath version of libeth_xdp_return_buff() to be called on exceptions,
+ * queue clean-ups etc., without unwanted inlining.
+ */
+void __cold libeth_xdp_return_buff_slow(struct libeth_xdp_buff *xdp)
+{
+	__libeth_xdp_return_buff(xdp, false);
+}
+EXPORT_SYMBOL_GPL(libeth_xdp_return_buff_slow);
+
+/**
+ * libeth_xdp_buff_add_frag - add frag to XDP buffer
+ * @xdp: head XDP buffer
+ * @fqe: Rx buffer containing the frag
+ * @len: frag length reported by HW
+ *
+ * External helper used by libeth_xdp_process_buff(), do not call directly.
+ * Frees both head and frag buffers on error.
+ *
+ * Return: true success, false on error (no space for a new frag).
+ */
+bool libeth_xdp_buff_add_frag(struct libeth_xdp_buff *xdp,
+			      const struct libeth_fqe *fqe,
+			      u32 len)
+{
+	netmem_ref netmem = fqe->netmem;
+
+	if (!xdp_buff_add_frag(&xdp->base, netmem,
+			       fqe->offset + netmem_get_pp(netmem)->p.offset,
+			       len, fqe->truesize))
+		goto recycle;
+
+	return true;
+
+recycle:
+	libeth_rx_recycle_slow(netmem);
+	libeth_xdp_return_buff_slow(xdp);
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(libeth_xdp_buff_add_frag);
+
+/**
+ * libeth_xdp_prog_exception - handle XDP prog exceptions
+ * @bq: XDP Tx bulk
+ * @xdp: buffer to process
+ * @act: original XDP prog verdict
+ * @ret: error code if redirect failed
+ *
+ * External helper used by __libeth_xdp_run_prog() and
+ * __libeth_xsk_run_prog_slow(), do not call directly.
+ * Reports invalid @act, XDP exception trace event and frees the buffer.
+ *
+ * Return: libeth_xdp XDP prog verdict.
+ */
+u32 __cold libeth_xdp_prog_exception(const struct libeth_xdp_tx_bulk *bq,
+				     struct libeth_xdp_buff *xdp,
+				     enum xdp_action act, int ret)
+{
+	if (act > XDP_REDIRECT)
+		bpf_warn_invalid_xdp_action(bq->dev, bq->prog, act);
+
+	libeth_trace_xdp_exception(bq->dev, bq->prog, act);
+
+	if (xdp->base.rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL)
+		return libeth_xsk_prog_exception(xdp, act, ret);
+
+	libeth_xdp_return_buff_slow(xdp);
+
+	return LIBETH_XDP_DROP;
+}
+EXPORT_SYMBOL_GPL(libeth_xdp_prog_exception);
+
+/* Tx buffer completion */
+
+static void libeth_xdp_put_netmem_bulk(netmem_ref netmem,
+				       struct xdp_frame_bulk *bq)
+{
+	if (unlikely(bq->count == XDP_BULK_QUEUE_SIZE))
+		xdp_flush_frame_bulk(bq);
+
+	bq->q[bq->count++] = netmem;
+}
+
+/**
+ * libeth_xdp_return_buff_bulk - free &xdp_buff as part of a bulk
+ * @sinfo: shared info corresponding to the buffer
+ * @bq: XDP frame bulk to store the buffer
+ * @frags: whether the buffer has frags
+ *
+ * Same as xdp_return_frame_bulk(), but for &libeth_xdp_buff, speeds up Tx
+ * completion of ``XDP_TX`` buffers and allows to free them in same bulks
+ * with &xdp_frame buffers.
+ */
+void libeth_xdp_return_buff_bulk(const struct skb_shared_info *sinfo,
+				 struct xdp_frame_bulk *bq, bool frags)
+{
+	if (!frags)
+		goto head;
+
+	for (u32 i = 0; i < sinfo->nr_frags; i++)
+		libeth_xdp_put_netmem_bulk(skb_frag_netmem(&sinfo->frags[i]),
+					   bq);
+
+head:
+	libeth_xdp_put_netmem_bulk(virt_to_netmem(sinfo), bq);
+}
+EXPORT_SYMBOL_GPL(libeth_xdp_return_buff_bulk);
+
+/* Misc */
+
+/**
+ * libeth_xdp_queue_threshold - calculate XDP queue clean/refill threshold
+ * @count: number of descriptors in the queue
+ *
+ * The threshold is the limit at which RQs start to refill (when the number of
+ * empty buffers exceeds it) and SQs get cleaned up (when the number of free
+ * descriptors goes below it). To speed up hotpath processing, threshold is
+ * always pow-2, closest to 1/4 of the queue length.
+ * Don't call it on hotpath, calculate and cache the threshold during the
+ * queue initialization.
+ *
+ * Return: the calculated threshold.
+ */
+u32 libeth_xdp_queue_threshold(u32 count)
+{
+	u32 quarter, low, high;
+
+	if (likely(is_power_of_2(count)))
+		return count >> 2;
+
+	quarter = DIV_ROUND_CLOSEST(count, 4);
+	low = rounddown_pow_of_two(quarter);
+	high = roundup_pow_of_two(quarter);
+
+	return high - quarter <= quarter - low ? high : low;
+}
+EXPORT_SYMBOL_GPL(libeth_xdp_queue_threshold);
+
+/**
+ * __libeth_xdp_set_features - set XDP features for netdev
+ * @dev: &net_device to configure
+ * @xmo: XDP metadata ops (Rx hints)
+ * @zc_segs: maximum number of S/G frags the HW can transmit
+ * @tmo: XSk Tx metadata ops (Tx hints)
+ *
+ * Set all the features libeth_xdp supports. Only the first argument is
+ * necessary; without the third one (zero), XSk support won't be advertised.
+ * Use the non-underscored versions in drivers instead.
+ */
+void __libeth_xdp_set_features(struct net_device *dev,
+			       const struct xdp_metadata_ops *xmo,
+			       u32 zc_segs,
+			       const struct xsk_tx_metadata_ops *tmo)
+{
+	xdp_set_features_flag(dev,
+			      NETDEV_XDP_ACT_BASIC |
+			      NETDEV_XDP_ACT_REDIRECT |
+			      NETDEV_XDP_ACT_NDO_XMIT |
+			      (zc_segs ? NETDEV_XDP_ACT_XSK_ZEROCOPY : 0) |
+			      NETDEV_XDP_ACT_RX_SG |
+			      NETDEV_XDP_ACT_NDO_XMIT_SG);
+	dev->xdp_metadata_ops = xmo;
+
+	tmo = tmo == libeth_xsktmo ? &libeth_xsktmo_slow : tmo;
+
+	dev->xdp_zc_max_segs = zc_segs ? : 1;
+	dev->xsk_tx_metadata_ops = zc_segs ? tmo : NULL;
+}
+EXPORT_SYMBOL_GPL(__libeth_xdp_set_features);
+
+/**
+ * libeth_xdp_set_redirect - toggle the XDP redirect feature
+ * @dev: &net_device to configure
+ * @enable: whether XDP is enabled
+ *
+ * Use this when XDPSQs are not always available to dynamically enable
+ * and disable redirect feature.
+ */
+void libeth_xdp_set_redirect(struct net_device *dev, bool enable)
+{
+	if (enable)
+		xdp_features_set_redirect_target(dev, true);
+	else
+		xdp_features_clear_redirect_target(dev);
+}
+EXPORT_SYMBOL_GPL(libeth_xdp_set_redirect);
+
+/* Module */
+
+static const struct libeth_xdp_ops xdp_ops __initconst = {
+	.bulk	= libeth_xdp_return_buff_bulk,
+	.xsk	= libeth_xsk_buff_free_slow,
+};
+
+static int __init libeth_xdp_module_init(void)
+{
+	libeth_attach_xdp(&xdp_ops);
+
+	return 0;
+}
+module_init(libeth_xdp_module_init);
+
+static void __exit libeth_xdp_module_exit(void)
+{
+	libeth_detach_xdp();
+}
+module_exit(libeth_xdp_module_exit);
+
+MODULE_DESCRIPTION("Common Ethernet library - XDP infra");
+MODULE_IMPORT_NS("LIBETH");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/intel/libeth/xsk.c b/drivers/net/ethernet/intel/libeth/xsk.c
new file mode 100644
index 000000000000..846e902e31b6
--- /dev/null
+++ b/drivers/net/ethernet/intel/libeth/xsk.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2025 Intel Corporation */
+
+#define DEFAULT_SYMBOL_NAMESPACE	"LIBETH_XDP"
+
+#include <linux/export.h>
+
+#include <net/libeth/xsk.h>
+
+#include "priv.h"
+
+/* ``XDP_TX`` bulking */
+
+void __cold libeth_xsk_tx_return_bulk(const struct libeth_xdp_tx_frame *bq,
+				      u32 count)
+{
+	for (u32 i = 0; i < count; i++)
+		libeth_xsk_buff_free_slow(bq[i].xsk);
+}
+
+/* XSk TMO */
+
+const struct xsk_tx_metadata_ops libeth_xsktmo_slow = {
+	.tmo_request_checksum		= libeth_xsktmo_req_csum,
+};
+
+/* Rx polling path */
+
+/**
+ * libeth_xsk_buff_free_slow - free an XSk Rx buffer
+ * @xdp: buffer to free
+ *
+ * Slowpath version of xsk_buff_free() to be used on exceptions, cleanups etc.
+ * to avoid unwanted inlining.
+ */
+void libeth_xsk_buff_free_slow(struct libeth_xdp_buff *xdp)
+{
+	xsk_buff_free(&xdp->base);
+}
+EXPORT_SYMBOL_GPL(libeth_xsk_buff_free_slow);
+
+/**
+ * libeth_xsk_buff_add_frag - add frag to XSk Rx buffer
+ * @head: head buffer
+ * @xdp: frag buffer
+ *
+ * External helper used by libeth_xsk_process_buff(), do not call directly.
+ * Frees both main and frag buffers on error.
+ *
+ * Return: main buffer with attached frag on success, %NULL on error (no space
+ * for a new frag).
+ */
+struct libeth_xdp_buff *libeth_xsk_buff_add_frag(struct libeth_xdp_buff *head,
+						 struct libeth_xdp_buff *xdp)
+{
+	if (!xsk_buff_add_frag(&head->base, &xdp->base))
+		goto free;
+
+	return head;
+
+free:
+	libeth_xsk_buff_free_slow(xdp);
+	libeth_xsk_buff_free_slow(head);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(libeth_xsk_buff_add_frag);
+
+/**
+ * libeth_xsk_buff_stats_frags - update onstack RQ stats with XSk frags info
+ * @rs: onstack stats to update
+ * @xdp: buffer to account
+ *
+ * External helper used by __libeth_xsk_run_pass(), do not call directly.
+ * Adds buffer's frags count and total len to the onstack stats.
+ */
+void libeth_xsk_buff_stats_frags(struct libeth_rq_napi_stats *rs,
+				 const struct libeth_xdp_buff *xdp)
+{
+	libeth_xdp_buff_stats_frags(rs, xdp);
+}
+EXPORT_SYMBOL_GPL(libeth_xsk_buff_stats_frags);
+
+/**
+ * __libeth_xsk_run_prog_slow - process the non-``XDP_REDIRECT`` verdicts
+ * @xdp: buffer to process
+ * @bq: Tx bulk for queueing on ``XDP_TX``
+ * @act: verdict to process
+ * @ret: error code if ``XDP_REDIRECT`` failed
+ *
+ * External helper used by __libeth_xsk_run_prog(), do not call directly.
+ * ``XDP_REDIRECT`` is the most common and hottest verdict on XSk, thus
+ * it is processed inline. The rest goes here for out-of-line processing,
+ * together with redirect errors.
+ *
+ * Return: libeth_xdp XDP prog verdict.
+ */
+u32 __libeth_xsk_run_prog_slow(struct libeth_xdp_buff *xdp,
+			       const struct libeth_xdp_tx_bulk *bq,
+			       enum xdp_action act, int ret)
+{
+	switch (act) {
+	case XDP_DROP:
+		xsk_buff_free(&xdp->base);
+
+		return LIBETH_XDP_DROP;
+	case XDP_TX:
+		return LIBETH_XDP_TX;
+	case XDP_PASS:
+		return LIBETH_XDP_PASS;
+	default:
+		break;
+	}
+
+	return libeth_xdp_prog_exception(bq, xdp, act, ret);
+}
+EXPORT_SYMBOL_GPL(__libeth_xsk_run_prog_slow);
+
+/**
+ * libeth_xsk_prog_exception - handle XDP prog exceptions on XSk
+ * @xdp: buffer to process
+ * @act: verdict returned by the prog
+ * @ret: error code if ``XDP_REDIRECT`` failed
+ *
+ * Internal. Frees the buffer and, if the queue uses XSk wakeups, stop the
+ * current NAPI poll when there are no free buffers left.
+ *
+ * Return: libeth_xdp's XDP prog verdict.
+ */
+u32 __cold libeth_xsk_prog_exception(struct libeth_xdp_buff *xdp,
+				     enum xdp_action act, int ret)
+{
+	const struct xdp_buff_xsk *xsk;
+	u32 __ret = LIBETH_XDP_DROP;
+
+	if (act != XDP_REDIRECT)
+		goto drop;
+
+	xsk = container_of(&xdp->base, typeof(*xsk), xdp);
+	if (xsk_uses_need_wakeup(xsk->pool) && ret == -ENOBUFS)
+		__ret = LIBETH_XDP_ABORTED;
+
+drop:
+	libeth_xsk_buff_free_slow(xdp);
+
+	return __ret;
+}
+
+/* Refill */
+
+/**
+ * libeth_xskfq_create - create an XSkFQ
+ * @fq: fill queue to initialize
+ *
+ * Allocates the FQEs and initializes the fields used by libeth_xdp: number
+ * of buffers to refill, refill threshold and buffer len.
+ *
+ * Return: %0 on success, -errno otherwise.
+ */
+int libeth_xskfq_create(struct libeth_xskfq *fq)
+{
+	fq->fqes = kvcalloc_node(fq->count, sizeof(*fq->fqes), GFP_KERNEL,
+				 fq->nid);
+	if (!fq->fqes)
+		return -ENOMEM;
+
+	fq->pending = fq->count;
+	fq->thresh = libeth_xdp_queue_threshold(fq->count);
+	fq->buf_len = xsk_pool_get_rx_frame_size(fq->pool);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(libeth_xskfq_create);
+
+/**
+ * libeth_xskfq_destroy - destroy an XSkFQ
+ * @fq: fill queue to destroy
+ *
+ * Zeroes the used fields and frees the FQEs array.
+ */
+void libeth_xskfq_destroy(struct libeth_xskfq *fq)
+{
+	fq->buf_len = 0;
+	fq->thresh = 0;
+	fq->pending = 0;
+
+	kvfree(fq->fqes);
+}
+EXPORT_SYMBOL_GPL(libeth_xskfq_destroy);
+
+/* .ndo_xsk_wakeup */
+
+static void libeth_xsk_napi_sched(void *info)
+{
+	__napi_schedule_irqoff(info);
+}
+
+/**
+ * libeth_xsk_init_wakeup - initialize libeth XSk wakeup structure
+ * @csd: struct to initialize
+ * @napi: NAPI corresponding to this queue
+ *
+ * libeth_xdp uses inter-processor interrupts to perform XSk wakeups. In order
+ * to do that, the corresponding CSDs must be initialized when creating the
+ * queues.
+ */
+void libeth_xsk_init_wakeup(call_single_data_t *csd, struct napi_struct *napi)
+{
+	INIT_CSD(csd, libeth_xsk_napi_sched, napi);
+}
+EXPORT_SYMBOL_GPL(libeth_xsk_init_wakeup);
+
+/**
+ * libeth_xsk_wakeup - perform an XSk wakeup
+ * @csd: CSD corresponding to the queue
+ * @qid: the stack queue index
+ *
+ * Try to mark the NAPI as missed first, so that it could be rescheduled.
+ * If it's not, schedule it on the corresponding CPU using IPIs (or directly
+ * if already running on it).
+ */
+void libeth_xsk_wakeup(call_single_data_t *csd, u32 qid)
+{
+	struct napi_struct *napi = csd->info;
+
+	if (napi_if_scheduled_mark_missed(napi) ||
+	    unlikely(!napi_schedule_prep(napi)))
+		return;
+
+	if (unlikely(qid >= nr_cpu_ids))
+		qid %= nr_cpu_ids;
+
+	if (qid != raw_smp_processor_id() && cpu_online(qid))
+		smp_call_function_single_async(qid, csd);
+	else
+		__napi_schedule(napi);
+}
+EXPORT_SYMBOL_GPL(libeth_xsk_wakeup);
+
+/* Pool setup */
+
+#define LIBETH_XSK_DMA_ATTR					\
+	(DMA_ATTR_WEAK_ORDERING | DMA_ATTR_SKIP_CPU_SYNC)
+
+/**
+ * libeth_xsk_setup_pool - setup or destroy an XSk pool for a queue
+ * @dev: target &net_device
+ * @qid: stack queue index to configure
+ * @enable: whether to enable or disable the pool
+ *
+ * Check that @qid is valid and then map or unmap the pool.
+ *
+ * Return: %0 on success, -errno otherwise.
+ */
+int libeth_xsk_setup_pool(struct net_device *dev, u32 qid, bool enable)
+{
+	struct xsk_buff_pool *pool;
+
+	pool = xsk_get_pool_from_qid(dev, qid);
+	if (!pool)
+		return -EINVAL;
+
+	if (enable)
+		return xsk_pool_dma_map(pool, dev->dev.parent,
+					LIBETH_XSK_DMA_ATTR);
+	else
+		xsk_pool_dma_unmap(pool, LIBETH_XSK_DMA_ATTR);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(libeth_xsk_setup_pool);
diff --git a/drivers/net/ethernet/intel/libie/Kconfig b/drivers/net/ethernet/intel/libie/Kconfig
index 33aff6bc8f81..70831c7e336e 100644
--- a/drivers/net/ethernet/intel/libie/Kconfig
+++ b/drivers/net/ethernet/intel/libie/Kconfig
@@ -8,3 +8,18 @@ config LIBIE
 	  libie (Intel Ethernet library) is a common library built on top of
 	  libeth and containing vendor-specific routines shared between several
 	  Intel Ethernet drivers.
+
+config LIBIE_ADMINQ
+	tristate
+	help
+	  Helper functions used by Intel Ethernet drivers for administration
+	  queue command interface (aka adminq).
+
+config LIBIE_FWLOG
+	tristate
+	select LIBIE_ADMINQ
+	help
+	  Library to support firmware logging on device that have support
+	  for it. Firmware logging is using admin queue interface to communicate
+	  with the device. Debugfs is a user interface used to config logging
+	  and dump all collected logs.
diff --git a/drivers/net/ethernet/intel/libie/Makefile b/drivers/net/ethernet/intel/libie/Makefile
index ffd27fab916a..db57fc6780ea 100644
--- a/drivers/net/ethernet/intel/libie/Makefile
+++ b/drivers/net/ethernet/intel/libie/Makefile
@@ -4,3 +4,11 @@
 obj-$(CONFIG_LIBIE)	+= libie.o
 
 libie-y			:= rx.o
+
+obj-$(CONFIG_LIBIE_ADMINQ) 	+= libie_adminq.o
+
+libie_adminq-y			:= adminq.o
+
+obj-$(CONFIG_LIBIE_FWLOG) 	+= libie_fwlog.o
+
+libie_fwlog-y			:= fwlog.o
diff --git a/drivers/net/ethernet/intel/libie/adminq.c b/drivers/net/ethernet/intel/libie/adminq.c
new file mode 100644
index 000000000000..7b4ff479e7e5
--- /dev/null
+++ b/drivers/net/ethernet/intel/libie/adminq.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2025 Intel Corporation */
+
+#include <linux/module.h>
+#include <linux/net/intel/libie/adminq.h>
+
+static const char * const libie_aq_str_arr[] = {
+#define LIBIE_AQ_STR(x)					\
+	[LIBIE_AQ_RC_##x]	= "LIBIE_AQ_RC_" #x
+	LIBIE_AQ_STR(OK),
+	LIBIE_AQ_STR(EPERM),
+	LIBIE_AQ_STR(ENOENT),
+	LIBIE_AQ_STR(ESRCH),
+	LIBIE_AQ_STR(EIO),
+	LIBIE_AQ_STR(EAGAIN),
+	LIBIE_AQ_STR(ENOMEM),
+	LIBIE_AQ_STR(EACCES),
+	LIBIE_AQ_STR(EBUSY),
+	LIBIE_AQ_STR(EEXIST),
+	LIBIE_AQ_STR(EINVAL),
+	LIBIE_AQ_STR(ENOSPC),
+	LIBIE_AQ_STR(ENOSYS),
+	LIBIE_AQ_STR(EMODE),
+	LIBIE_AQ_STR(ENOSEC),
+	LIBIE_AQ_STR(EBADSIG),
+	LIBIE_AQ_STR(ESVN),
+	LIBIE_AQ_STR(EBADMAN),
+	LIBIE_AQ_STR(EBADBUF),
+#undef LIBIE_AQ_STR
+	"LIBIE_AQ_RC_UNKNOWN",
+};
+
+#define __LIBIE_AQ_STR_NUM (ARRAY_SIZE(libie_aq_str_arr) - 1)
+
+/**
+ * libie_aq_str - get error string based on aq error
+ * @err: admin queue error type
+ *
+ * Return: error string for passed error code
+ */
+const char *libie_aq_str(enum libie_aq_err err)
+{
+	if (err >= ARRAY_SIZE(libie_aq_str_arr) ||
+	    !libie_aq_str_arr[err])
+		err = __LIBIE_AQ_STR_NUM;
+
+	return libie_aq_str_arr[err];
+}
+EXPORT_SYMBOL_NS_GPL(libie_aq_str, "LIBIE_ADMINQ");
+
+MODULE_DESCRIPTION("Intel(R) Ethernet common library - adminq helpers");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/intel/libie/fwlog.c b/drivers/net/ethernet/intel/libie/fwlog.c
new file mode 100644
index 000000000000..f39cc11cb7c5
--- /dev/null
+++ b/drivers/net/ethernet/intel/libie/fwlog.c
@@ -0,0 +1,1115 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022, Intel Corporation. */
+
+#include <linux/debugfs.h>
+#include <linux/export.h>
+#include <linux/fs.h>
+#include <linux/net/intel/libie/fwlog.h>
+#include <linux/pci.h>
+#include <linux/random.h>
+#include <linux/vmalloc.h>
+
+#define DEFAULT_SYMBOL_NAMESPACE	"LIBIE_FWLOG"
+
+/* create a define that has an extra module that doesn't really exist. this
+ * is so we can add a module 'all' to easily enable/disable all the modules
+ */
+#define LIBIE_NR_FW_LOG_MODULES (LIBIE_AQC_FW_LOG_ID_MAX + 1)
+
+/* the ordering in this array is important. it matches the ordering of the
+ * values in the FW so the index is the same value as in
+ * libie_aqc_fw_logging_mod
+ */
+static const char * const libie_fwlog_module_string[] = {
+	"general",
+	"ctrl",
+	"link",
+	"link_topo",
+	"dnl",
+	"i2c",
+	"sdp",
+	"mdio",
+	"adminq",
+	"hdma",
+	"lldp",
+	"dcbx",
+	"dcb",
+	"xlr",
+	"nvm",
+	"auth",
+	"vpd",
+	"iosf",
+	"parser",
+	"sw",
+	"scheduler",
+	"txq",
+	"rsvd",
+	"post",
+	"watchdog",
+	"task_dispatch",
+	"mng",
+	"synce",
+	"health",
+	"tsdrv",
+	"pfreg",
+	"mdlver",
+	"all",
+};
+
+/* the ordering in this array is important. it matches the ordering of the
+ * values in the FW so the index is the same value as in libie_fwlog_level
+ */
+static const char * const libie_fwlog_level_string[] = {
+	"none",
+	"error",
+	"warning",
+	"normal",
+	"verbose",
+};
+
+static const char * const libie_fwlog_log_size[] = {
+	"128K",
+	"256K",
+	"512K",
+	"1M",
+	"2M",
+};
+
+static bool libie_fwlog_ring_empty(struct libie_fwlog_ring *rings)
+{
+	return rings->head == rings->tail;
+}
+
+static void libie_fwlog_ring_increment(u16 *item, u16 size)
+{
+	*item = (*item + 1) & (size - 1);
+}
+
+static int libie_fwlog_alloc_ring_buffs(struct libie_fwlog_ring *rings)
+{
+	int i, nr_bytes;
+	u8 *mem;
+
+	nr_bytes = rings->size * LIBIE_AQ_MAX_BUF_LEN;
+	mem = vzalloc(nr_bytes);
+	if (!mem)
+		return -ENOMEM;
+
+	for (i = 0; i < rings->size; i++) {
+		struct libie_fwlog_data *ring = &rings->rings[i];
+
+		ring->data_size = LIBIE_AQ_MAX_BUF_LEN;
+		ring->data = mem;
+		mem += LIBIE_AQ_MAX_BUF_LEN;
+	}
+
+	return 0;
+}
+
+static void libie_fwlog_free_ring_buffs(struct libie_fwlog_ring *rings)
+{
+	int i;
+
+	for (i = 0; i < rings->size; i++) {
+		struct libie_fwlog_data *ring = &rings->rings[i];
+
+		/* the first ring is the base memory for the whole range so
+		 * free it
+		 */
+		if (!i)
+			vfree(ring->data);
+
+		ring->data = NULL;
+		ring->data_size = 0;
+	}
+}
+
+#define LIBIE_FWLOG_INDEX_TO_BYTES(n) ((128 * 1024) << (n))
+/**
+ * libie_fwlog_realloc_rings - reallocate the FW log rings
+ * @fwlog: pointer to the fwlog structure
+ * @index: the new index to use to allocate memory for the log data
+ *
+ */
+static void libie_fwlog_realloc_rings(struct libie_fwlog *fwlog, int index)
+{
+	struct libie_fwlog_ring ring;
+	int status, ring_size;
+
+	/* convert the number of bytes into a number of 4K buffers. externally
+	 * the driver presents the interface to the FW log data as a number of
+	 * bytes because that's easy for users to understand. internally the
+	 * driver uses a ring of buffers because the driver doesn't know where
+	 * the beginning and end of any line of log data is so the driver has
+	 * to overwrite data as complete blocks. when the data is returned to
+	 * the user the driver knows that the data is correct and the FW log
+	 * can be correctly parsed by the tools
+	 */
+	ring_size = LIBIE_FWLOG_INDEX_TO_BYTES(index) / LIBIE_AQ_MAX_BUF_LEN;
+	if (ring_size == fwlog->ring.size)
+		return;
+
+	/* allocate space for the new rings and buffers then release the
+	 * old rings and buffers. that way if we don't have enough
+	 * memory then we at least have what we had before
+	 */
+	ring.rings = kcalloc(ring_size, sizeof(*ring.rings), GFP_KERNEL);
+	if (!ring.rings)
+		return;
+
+	ring.size = ring_size;
+
+	status = libie_fwlog_alloc_ring_buffs(&ring);
+	if (status) {
+		dev_warn(&fwlog->pdev->dev, "Unable to allocate memory for FW log ring data buffers\n");
+		libie_fwlog_free_ring_buffs(&ring);
+		kfree(ring.rings);
+		return;
+	}
+
+	libie_fwlog_free_ring_buffs(&fwlog->ring);
+	kfree(fwlog->ring.rings);
+
+	fwlog->ring.rings = ring.rings;
+	fwlog->ring.size = ring.size;
+	fwlog->ring.index = index;
+	fwlog->ring.head = 0;
+	fwlog->ring.tail = 0;
+}
+
+/**
+ * libie_fwlog_supported - Cached for whether FW supports FW logging or not
+ * @fwlog: pointer to the fwlog structure
+ *
+ * This will always return false if called before libie_init_hw(), so it must be
+ * called after libie_init_hw().
+ */
+static bool libie_fwlog_supported(struct libie_fwlog *fwlog)
+{
+	return fwlog->supported;
+}
+
+/**
+ * libie_aq_fwlog_set - Set FW logging configuration AQ command (0xFF30)
+ * @fwlog: pointer to the fwlog structure
+ * @entries: entries to configure
+ * @num_entries: number of @entries
+ * @options: options from libie_fwlog_cfg->options structure
+ * @log_resolution: logging resolution
+ */
+static int
+libie_aq_fwlog_set(struct libie_fwlog *fwlog,
+		   struct libie_fwlog_module_entry *entries, u16 num_entries,
+		   u16 options, u16 log_resolution)
+{
+	struct libie_aqc_fw_log_cfg_resp *fw_modules;
+	struct libie_aq_desc desc = {0};
+	struct libie_aqc_fw_log *cmd;
+	int status;
+	int i;
+
+	fw_modules = kcalloc(num_entries, sizeof(*fw_modules), GFP_KERNEL);
+	if (!fw_modules)
+		return -ENOMEM;
+
+	for (i = 0; i < num_entries; i++) {
+		fw_modules[i].module_identifier =
+			cpu_to_le16(entries[i].module_id);
+		fw_modules[i].log_level = entries[i].log_level;
+	}
+
+	desc.opcode = cpu_to_le16(libie_aqc_opc_fw_logs_config);
+	desc.flags = cpu_to_le16(LIBIE_AQ_FLAG_SI) |
+		     cpu_to_le16(LIBIE_AQ_FLAG_RD);
+
+	cmd = libie_aq_raw(&desc);
+
+	cmd->cmd_flags = LIBIE_AQC_FW_LOG_CONF_SET_VALID;
+	cmd->ops.cfg.log_resolution = cpu_to_le16(log_resolution);
+	cmd->ops.cfg.mdl_cnt = cpu_to_le16(num_entries);
+
+	if (options & LIBIE_FWLOG_OPTION_ARQ_ENA)
+		cmd->cmd_flags |= LIBIE_AQC_FW_LOG_CONF_AQ_EN;
+	if (options & LIBIE_FWLOG_OPTION_UART_ENA)
+		cmd->cmd_flags |= LIBIE_AQC_FW_LOG_CONF_UART_EN;
+
+	status = fwlog->send_cmd(fwlog->priv, &desc, fw_modules,
+				 sizeof(*fw_modules) * num_entries);
+
+	kfree(fw_modules);
+
+	return status;
+}
+
+/**
+ * libie_fwlog_set - Set the firmware logging settings
+ * @fwlog: pointer to the fwlog structure
+ * @cfg: config used to set firmware logging
+ *
+ * This function should be called whenever the driver needs to set the firmware
+ * logging configuration. It can be called on initialization, reset, or during
+ * runtime.
+ *
+ * If the PF wishes to receive FW logging then it must register via
+ * libie_fwlog_register. Note, that libie_fwlog_register does not need to be called
+ * for init.
+ */
+static int libie_fwlog_set(struct libie_fwlog *fwlog,
+			   struct libie_fwlog_cfg *cfg)
+{
+	if (!libie_fwlog_supported(fwlog))
+		return -EOPNOTSUPP;
+
+	return libie_aq_fwlog_set(fwlog, cfg->module_entries,
+				LIBIE_AQC_FW_LOG_ID_MAX, cfg->options,
+				cfg->log_resolution);
+}
+
+/**
+ * libie_aq_fwlog_register - Register PF for firmware logging events (0xFF31)
+ * @fwlog: pointer to the fwlog structure
+ * @reg: true to register and false to unregister
+ */
+static int libie_aq_fwlog_register(struct libie_fwlog *fwlog, bool reg)
+{
+	struct libie_aq_desc desc = {0};
+	struct libie_aqc_fw_log *cmd;
+
+	desc.opcode = cpu_to_le16(libie_aqc_opc_fw_logs_register);
+	desc.flags = cpu_to_le16(LIBIE_AQ_FLAG_SI);
+	cmd = libie_aq_raw(&desc);
+
+	if (reg)
+		cmd->cmd_flags = LIBIE_AQC_FW_LOG_AQ_REGISTER;
+
+	return fwlog->send_cmd(fwlog->priv, &desc, NULL, 0);
+}
+
+/**
+ * libie_fwlog_register - Register the PF for firmware logging
+ * @fwlog: pointer to the fwlog structure
+ *
+ * After this call the PF will start to receive firmware logging based on the
+ * configuration set in libie_fwlog_set.
+ */
+static int libie_fwlog_register(struct libie_fwlog *fwlog)
+{
+	int status;
+
+	if (!libie_fwlog_supported(fwlog))
+		return -EOPNOTSUPP;
+
+	status = libie_aq_fwlog_register(fwlog, true);
+	if (status)
+		dev_dbg(&fwlog->pdev->dev, "Failed to register for firmware logging events over ARQ\n");
+	else
+		fwlog->cfg.options |= LIBIE_FWLOG_OPTION_IS_REGISTERED;
+
+	return status;
+}
+
+/**
+ * libie_fwlog_unregister - Unregister the PF from firmware logging
+ * @fwlog: pointer to the fwlog structure
+ */
+static int libie_fwlog_unregister(struct libie_fwlog *fwlog)
+{
+	int status;
+
+	if (!libie_fwlog_supported(fwlog))
+		return -EOPNOTSUPP;
+
+	status = libie_aq_fwlog_register(fwlog, false);
+	if (status)
+		dev_dbg(&fwlog->pdev->dev, "Failed to unregister from firmware logging events over ARQ\n");
+	else
+		fwlog->cfg.options &= ~LIBIE_FWLOG_OPTION_IS_REGISTERED;
+
+	return status;
+}
+
+/**
+ * libie_fwlog_print_module_cfg - print current FW logging module configuration
+ * @cfg: pointer to the fwlog cfg structure
+ * @module: module to print
+ * @s: the seq file to put data into
+ */
+static void
+libie_fwlog_print_module_cfg(struct libie_fwlog_cfg *cfg, int module,
+			     struct seq_file *s)
+{
+	struct libie_fwlog_module_entry *entry;
+
+	if (module != LIBIE_AQC_FW_LOG_ID_MAX) {
+		entry =	&cfg->module_entries[module];
+
+		seq_printf(s, "\tModule: %s, Log Level: %s\n",
+			   libie_fwlog_module_string[entry->module_id],
+			   libie_fwlog_level_string[entry->log_level]);
+	} else {
+		int i;
+
+		for (i = 0; i < LIBIE_AQC_FW_LOG_ID_MAX; i++) {
+			entry =	&cfg->module_entries[i];
+
+			seq_printf(s, "\tModule: %s, Log Level: %s\n",
+				   libie_fwlog_module_string[entry->module_id],
+				   libie_fwlog_level_string[entry->log_level]);
+		}
+	}
+}
+
+static int libie_find_module_by_dentry(struct dentry **modules, struct dentry *d)
+{
+	int i, module;
+
+	module = -1;
+	/* find the module based on the dentry */
+	for (i = 0; i < LIBIE_NR_FW_LOG_MODULES; i++) {
+		if (d == modules[i]) {
+			module = i;
+			break;
+		}
+	}
+
+	return module;
+}
+
+/**
+ * libie_debugfs_module_show - read from 'module' file
+ * @s: the opened file
+ * @v: pointer to the offset
+ */
+static int libie_debugfs_module_show(struct seq_file *s, void *v)
+{
+	struct libie_fwlog *fwlog = s->private;
+	const struct file *filp = s->file;
+	struct dentry *dentry;
+	int module;
+
+	dentry = file_dentry(filp);
+
+	module = libie_find_module_by_dentry(fwlog->debugfs_modules, dentry);
+	if (module < 0) {
+		dev_info(&fwlog->pdev->dev, "unknown module\n");
+		return -EINVAL;
+	}
+
+	libie_fwlog_print_module_cfg(&fwlog->cfg, module, s);
+
+	return 0;
+}
+
+static int libie_debugfs_module_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, libie_debugfs_module_show, inode->i_private);
+}
+
+/**
+ * libie_debugfs_module_write - write into 'module' file
+ * @filp: the opened file
+ * @buf: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ */
+static ssize_t
+libie_debugfs_module_write(struct file *filp, const char __user *buf,
+			   size_t count, loff_t *ppos)
+{
+	struct libie_fwlog *fwlog = file_inode(filp)->i_private;
+	struct dentry *dentry = file_dentry(filp);
+	struct device *dev = &fwlog->pdev->dev;
+	char user_val[16], *cmd_buf;
+	int module, log_level, cnt;
+
+	/* don't allow partial writes or invalid input */
+	if (*ppos != 0 || count > 8)
+		return -EINVAL;
+
+	cmd_buf = memdup_user_nul(buf, count);
+	if (IS_ERR(cmd_buf))
+		return PTR_ERR(cmd_buf);
+
+	module = libie_find_module_by_dentry(fwlog->debugfs_modules, dentry);
+	if (module < 0) {
+		dev_info(dev, "unknown module\n");
+		return -EINVAL;
+	}
+
+	cnt = sscanf(cmd_buf, "%s", user_val);
+	if (cnt != 1)
+		return -EINVAL;
+
+	log_level = sysfs_match_string(libie_fwlog_level_string, user_val);
+	if (log_level < 0) {
+		dev_info(dev, "unknown log level '%s'\n", user_val);
+		return -EINVAL;
+	}
+
+	if (module != LIBIE_AQC_FW_LOG_ID_MAX) {
+		fwlog->cfg.module_entries[module].log_level = log_level;
+	} else {
+		/* the module 'all' is a shortcut so that we can set
+		 * all of the modules to the same level quickly
+		 */
+		int i;
+
+		for (i = 0; i < LIBIE_AQC_FW_LOG_ID_MAX; i++)
+			fwlog->cfg.module_entries[i].log_level = log_level;
+	}
+
+	return count;
+}
+
+static const struct file_operations libie_debugfs_module_fops = {
+	.owner = THIS_MODULE,
+	.open  = libie_debugfs_module_open,
+	.read = seq_read,
+	.release = single_release,
+	.write = libie_debugfs_module_write,
+};
+
+/**
+ * libie_debugfs_nr_messages_read - read from 'nr_messages' file
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ */
+static ssize_t libie_debugfs_nr_messages_read(struct file *filp,
+					      char __user *buffer, size_t count,
+					      loff_t *ppos)
+{
+	struct libie_fwlog *fwlog = filp->private_data;
+	char buff[32] = {};
+
+	snprintf(buff, sizeof(buff), "%d\n",
+		 fwlog->cfg.log_resolution);
+
+	return simple_read_from_buffer(buffer, count, ppos, buff, strlen(buff));
+}
+
+/**
+ * libie_debugfs_nr_messages_write - write into 'nr_messages' file
+ * @filp: the opened file
+ * @buf: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ */
+static ssize_t
+libie_debugfs_nr_messages_write(struct file *filp, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct libie_fwlog *fwlog = filp->private_data;
+	struct device *dev = &fwlog->pdev->dev;
+	char user_val[8], *cmd_buf;
+	s16 nr_messages;
+	ssize_t ret;
+
+	/* don't allow partial writes or invalid input */
+	if (*ppos != 0 || count > 4)
+		return -EINVAL;
+
+	cmd_buf = memdup_user_nul(buf, count);
+	if (IS_ERR(cmd_buf))
+		return PTR_ERR(cmd_buf);
+
+	ret = sscanf(cmd_buf, "%s", user_val);
+	if (ret != 1)
+		return -EINVAL;
+
+	ret = kstrtos16(user_val, 0, &nr_messages);
+	if (ret)
+		return ret;
+
+	if (nr_messages < LIBIE_AQC_FW_LOG_MIN_RESOLUTION ||
+	    nr_messages > LIBIE_AQC_FW_LOG_MAX_RESOLUTION) {
+		dev_err(dev, "Invalid FW log number of messages %d, value must be between %d - %d\n",
+			nr_messages, LIBIE_AQC_FW_LOG_MIN_RESOLUTION,
+			LIBIE_AQC_FW_LOG_MAX_RESOLUTION);
+		return -EINVAL;
+	}
+
+	fwlog->cfg.log_resolution = nr_messages;
+
+	return count;
+}
+
+static const struct file_operations libie_debugfs_nr_messages_fops = {
+	.owner = THIS_MODULE,
+	.open  = simple_open,
+	.read = libie_debugfs_nr_messages_read,
+	.write = libie_debugfs_nr_messages_write,
+};
+
+/**
+ * libie_debugfs_enable_read - read from 'enable' file
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ */
+static ssize_t libie_debugfs_enable_read(struct file *filp,
+					 char __user *buffer, size_t count,
+					 loff_t *ppos)
+{
+	struct libie_fwlog *fwlog = filp->private_data;
+	char buff[32] = {};
+
+	snprintf(buff, sizeof(buff), "%u\n",
+		 (u16)(fwlog->cfg.options &
+		 LIBIE_FWLOG_OPTION_IS_REGISTERED) >> 3);
+
+	return simple_read_from_buffer(buffer, count, ppos, buff, strlen(buff));
+}
+
+/**
+ * libie_debugfs_enable_write - write into 'enable' file
+ * @filp: the opened file
+ * @buf: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ */
+static ssize_t
+libie_debugfs_enable_write(struct file *filp, const char __user *buf,
+			   size_t count, loff_t *ppos)
+{
+	struct libie_fwlog *fwlog = filp->private_data;
+	char user_val[8], *cmd_buf;
+	bool enable;
+	ssize_t ret;
+
+	/* don't allow partial writes or invalid input */
+	if (*ppos != 0 || count > 2)
+		return -EINVAL;
+
+	cmd_buf = memdup_user_nul(buf, count);
+	if (IS_ERR(cmd_buf))
+		return PTR_ERR(cmd_buf);
+
+	ret = sscanf(cmd_buf, "%s", user_val);
+	if (ret != 1)
+		return -EINVAL;
+
+	ret = kstrtobool(user_val, &enable);
+	if (ret)
+		goto enable_write_error;
+
+	if (enable)
+		fwlog->cfg.options |= LIBIE_FWLOG_OPTION_ARQ_ENA;
+	else
+		fwlog->cfg.options &= ~LIBIE_FWLOG_OPTION_ARQ_ENA;
+
+	ret = libie_fwlog_set(fwlog, &fwlog->cfg);
+	if (ret)
+		goto enable_write_error;
+
+	if (enable)
+		ret = libie_fwlog_register(fwlog);
+	else
+		ret = libie_fwlog_unregister(fwlog);
+
+	if (ret)
+		goto enable_write_error;
+
+	/* if we get here, nothing went wrong; return count since we didn't
+	 * really write anything
+	 */
+	ret = (ssize_t)count;
+
+enable_write_error:
+	/* This function always consumes all of the written input, or produces
+	 * an error. Check and enforce this. Otherwise, the write operation
+	 * won't complete properly.
+	 */
+	if (WARN_ON(ret != (ssize_t)count && ret >= 0))
+		ret = -EIO;
+
+	return ret;
+}
+
+static const struct file_operations libie_debugfs_enable_fops = {
+	.owner = THIS_MODULE,
+	.open  = simple_open,
+	.read = libie_debugfs_enable_read,
+	.write = libie_debugfs_enable_write,
+};
+
+/**
+ * libie_debugfs_log_size_read - read from 'log_size' file
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ */
+static ssize_t libie_debugfs_log_size_read(struct file *filp,
+					   char __user *buffer, size_t count,
+					   loff_t *ppos)
+{
+	struct libie_fwlog *fwlog = filp->private_data;
+	char buff[32] = {};
+	int index;
+
+	index = fwlog->ring.index;
+	snprintf(buff, sizeof(buff), "%s\n", libie_fwlog_log_size[index]);
+
+	return simple_read_from_buffer(buffer, count, ppos, buff, strlen(buff));
+}
+
+/**
+ * libie_debugfs_log_size_write - write into 'log_size' file
+ * @filp: the opened file
+ * @buf: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ */
+static ssize_t
+libie_debugfs_log_size_write(struct file *filp, const char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	struct libie_fwlog *fwlog = filp->private_data;
+	struct device *dev = &fwlog->pdev->dev;
+	char user_val[8], *cmd_buf;
+	ssize_t ret;
+	int index;
+
+	/* don't allow partial writes or invalid input */
+	if (*ppos != 0 || count > 5)
+		return -EINVAL;
+
+	cmd_buf = memdup_user_nul(buf, count);
+	if (IS_ERR(cmd_buf))
+		return PTR_ERR(cmd_buf);
+
+	ret = sscanf(cmd_buf, "%s", user_val);
+	if (ret != 1)
+		return -EINVAL;
+
+	index = sysfs_match_string(libie_fwlog_log_size, user_val);
+	if (index < 0) {
+		dev_info(dev, "Invalid log size '%s'. The value must be one of 128K, 256K, 512K, 1M, 2M\n",
+			 user_val);
+		ret = -EINVAL;
+		goto log_size_write_error;
+	} else if (fwlog->cfg.options & LIBIE_FWLOG_OPTION_IS_REGISTERED) {
+		dev_info(dev, "FW logging is currently running. Please disable FW logging to change log_size\n");
+		ret = -EINVAL;
+		goto log_size_write_error;
+	}
+
+	/* free all the buffers and the tracking info and resize */
+	libie_fwlog_realloc_rings(fwlog, index);
+
+	/* if we get here, nothing went wrong; return count since we didn't
+	 * really write anything
+	 */
+	ret = (ssize_t)count;
+
+log_size_write_error:
+	/* This function always consumes all of the written input, or produces
+	 * an error. Check and enforce this. Otherwise, the write operation
+	 * won't complete properly.
+	 */
+	if (WARN_ON(ret != (ssize_t)count && ret >= 0))
+		ret = -EIO;
+
+	return ret;
+}
+
+static const struct file_operations libie_debugfs_log_size_fops = {
+	.owner = THIS_MODULE,
+	.open  = simple_open,
+	.read = libie_debugfs_log_size_read,
+	.write = libie_debugfs_log_size_write,
+};
+
+/**
+ * libie_debugfs_data_read - read from 'data' file
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ */
+static ssize_t libie_debugfs_data_read(struct file *filp, char __user *buffer,
+				       size_t count, loff_t *ppos)
+{
+	struct libie_fwlog *fwlog = filp->private_data;
+	int data_copied = 0;
+	bool done = false;
+
+	if (libie_fwlog_ring_empty(&fwlog->ring))
+		return 0;
+
+	while (!libie_fwlog_ring_empty(&fwlog->ring) && !done) {
+		struct libie_fwlog_data *log;
+		u16 cur_buf_len;
+
+		log = &fwlog->ring.rings[fwlog->ring.head];
+		cur_buf_len = log->data_size;
+		if (cur_buf_len >= count) {
+			done = true;
+			continue;
+		}
+
+		if (copy_to_user(buffer, log->data, cur_buf_len)) {
+			/* if there is an error then bail and return whatever
+			 * the driver has copied so far
+			 */
+			done = true;
+			continue;
+		}
+
+		data_copied += cur_buf_len;
+		buffer += cur_buf_len;
+		count -= cur_buf_len;
+		*ppos += cur_buf_len;
+		libie_fwlog_ring_increment(&fwlog->ring.head, fwlog->ring.size);
+	}
+
+	return data_copied;
+}
+
+/**
+ * libie_debugfs_data_write - write into 'data' file
+ * @filp: the opened file
+ * @buf: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ */
+static ssize_t
+libie_debugfs_data_write(struct file *filp, const char __user *buf, size_t count,
+			 loff_t *ppos)
+{
+	struct libie_fwlog *fwlog = filp->private_data;
+	struct device *dev = &fwlog->pdev->dev;
+	ssize_t ret;
+
+	/* don't allow partial writes */
+	if (*ppos != 0)
+		return 0;
+
+	/* any value is allowed to clear the buffer so no need to even look at
+	 * what the value is
+	 */
+	if (!(fwlog->cfg.options & LIBIE_FWLOG_OPTION_IS_REGISTERED)) {
+		fwlog->ring.head = 0;
+		fwlog->ring.tail = 0;
+	} else {
+		dev_info(dev, "Can't clear FW log data while FW log running\n");
+		ret = -EINVAL;
+		goto nr_buffs_write_error;
+	}
+
+	/* if we get here, nothing went wrong; return count since we didn't
+	 * really write anything
+	 */
+	ret = (ssize_t)count;
+
+nr_buffs_write_error:
+	/* This function always consumes all of the written input, or produces
+	 * an error. Check and enforce this. Otherwise, the write operation
+	 * won't complete properly.
+	 */
+	if (WARN_ON(ret != (ssize_t)count && ret >= 0))
+		ret = -EIO;
+
+	return ret;
+}
+
+static const struct file_operations libie_debugfs_data_fops = {
+	.owner = THIS_MODULE,
+	.open  = simple_open,
+	.read = libie_debugfs_data_read,
+	.write = libie_debugfs_data_write,
+};
+
+/**
+ * libie_debugfs_fwlog_init - setup the debugfs directory
+ * @fwlog: pointer to the fwlog structure
+ * @root: debugfs root entry on which fwlog director will be registered
+ */
+static void libie_debugfs_fwlog_init(struct libie_fwlog *fwlog,
+				     struct dentry *root)
+{
+	struct dentry *fw_modules_dir;
+	struct dentry **fw_modules;
+	int i;
+
+	/* allocate space for this first because if it fails then we don't
+	 * need to unwind
+	 */
+	fw_modules = kcalloc(LIBIE_NR_FW_LOG_MODULES, sizeof(*fw_modules),
+			     GFP_KERNEL);
+	if (!fw_modules)
+		return;
+
+	fwlog->debugfs = debugfs_create_dir("fwlog", root);
+	if (IS_ERR(fwlog->debugfs))
+		goto err_create_module_files;
+
+	fw_modules_dir = debugfs_create_dir("modules", fwlog->debugfs);
+	if (IS_ERR(fw_modules_dir))
+		goto err_create_module_files;
+
+	for (i = 0; i < LIBIE_NR_FW_LOG_MODULES; i++) {
+		fw_modules[i] = debugfs_create_file(libie_fwlog_module_string[i],
+						    0600, fw_modules_dir, fwlog,
+						    &libie_debugfs_module_fops);
+		if (IS_ERR(fw_modules[i]))
+			goto err_create_module_files;
+	}
+
+	debugfs_create_file("nr_messages", 0600, fwlog->debugfs, fwlog,
+			    &libie_debugfs_nr_messages_fops);
+
+	fwlog->debugfs_modules = fw_modules;
+
+	debugfs_create_file("enable", 0600, fwlog->debugfs, fwlog,
+			    &libie_debugfs_enable_fops);
+
+	debugfs_create_file("log_size", 0600, fwlog->debugfs, fwlog,
+			    &libie_debugfs_log_size_fops);
+
+	debugfs_create_file("data", 0600, fwlog->debugfs, fwlog,
+			    &libie_debugfs_data_fops);
+
+	return;
+
+err_create_module_files:
+	debugfs_remove_recursive(fwlog->debugfs);
+	kfree(fw_modules);
+}
+
+static bool libie_fwlog_ring_full(struct libie_fwlog_ring *rings)
+{
+	u16 head, tail;
+
+	head = rings->head;
+	tail = rings->tail;
+
+	if (head < tail && (tail - head == (rings->size - 1)))
+		return true;
+	else if (head > tail && (tail == (head - 1)))
+		return true;
+
+	return false;
+}
+
+/**
+ * libie_aq_fwlog_get - Get the current firmware logging configuration (0xFF32)
+ * @fwlog: pointer to the fwlog structure
+ * @cfg: firmware logging configuration to populate
+ */
+static int libie_aq_fwlog_get(struct libie_fwlog *fwlog,
+			      struct libie_fwlog_cfg *cfg)
+{
+	struct libie_aqc_fw_log_cfg_resp *fw_modules;
+	struct libie_aq_desc desc = {0};
+	struct libie_aqc_fw_log *cmd;
+	u16 module_id_cnt;
+	int status;
+	void *buf;
+	int i;
+
+	memset(cfg, 0, sizeof(*cfg));
+
+	buf = kzalloc(LIBIE_AQ_MAX_BUF_LEN, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	desc.opcode = cpu_to_le16(libie_aqc_opc_fw_logs_query);
+	desc.flags = cpu_to_le16(LIBIE_AQ_FLAG_SI);
+	cmd = libie_aq_raw(&desc);
+
+	cmd->cmd_flags = LIBIE_AQC_FW_LOG_AQ_QUERY;
+
+	status = fwlog->send_cmd(fwlog->priv, &desc, buf, LIBIE_AQ_MAX_BUF_LEN);
+	if (status) {
+		dev_dbg(&fwlog->pdev->dev, "Failed to get FW log configuration\n");
+		goto status_out;
+	}
+
+	module_id_cnt = le16_to_cpu(cmd->ops.cfg.mdl_cnt);
+	if (module_id_cnt < LIBIE_AQC_FW_LOG_ID_MAX) {
+		dev_dbg(&fwlog->pdev->dev, "FW returned less than the expected number of FW log module IDs\n");
+	} else if (module_id_cnt > LIBIE_AQC_FW_LOG_ID_MAX) {
+		dev_dbg(&fwlog->pdev->dev, "FW returned more than expected number of FW log module IDs, setting module_id_cnt to software expected max %u\n",
+			LIBIE_AQC_FW_LOG_ID_MAX);
+		module_id_cnt = LIBIE_AQC_FW_LOG_ID_MAX;
+	}
+
+	cfg->log_resolution = le16_to_cpu(cmd->ops.cfg.log_resolution);
+	if (cmd->cmd_flags & LIBIE_AQC_FW_LOG_CONF_AQ_EN)
+		cfg->options |= LIBIE_FWLOG_OPTION_ARQ_ENA;
+	if (cmd->cmd_flags & LIBIE_AQC_FW_LOG_CONF_UART_EN)
+		cfg->options |= LIBIE_FWLOG_OPTION_UART_ENA;
+	if (cmd->cmd_flags & LIBIE_AQC_FW_LOG_QUERY_REGISTERED)
+		cfg->options |= LIBIE_FWLOG_OPTION_IS_REGISTERED;
+
+	fw_modules = (struct libie_aqc_fw_log_cfg_resp *)buf;
+
+	for (i = 0; i < module_id_cnt; i++) {
+		struct libie_aqc_fw_log_cfg_resp *fw_module = &fw_modules[i];
+
+		cfg->module_entries[i].module_id =
+			le16_to_cpu(fw_module->module_identifier);
+		cfg->module_entries[i].log_level = fw_module->log_level;
+	}
+
+status_out:
+	kfree(buf);
+	return status;
+}
+
+/**
+ * libie_fwlog_set_supported - Set if FW logging is supported by FW
+ * @fwlog: pointer to the fwlog structure
+ *
+ * If FW returns success to the libie_aq_fwlog_get call then it supports FW
+ * logging, else it doesn't. Set the fwlog_supported flag accordingly.
+ *
+ * This function is only meant to be called during driver init to determine if
+ * the FW support FW logging.
+ */
+static void libie_fwlog_set_supported(struct libie_fwlog *fwlog)
+{
+	struct libie_fwlog_cfg *cfg;
+	int status;
+
+	fwlog->supported = false;
+
+	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg)
+		return;
+
+	status = libie_aq_fwlog_get(fwlog, cfg);
+	if (status)
+		dev_dbg(&fwlog->pdev->dev, "libie_aq_fwlog_get failed, FW logging is not supported on this version of FW, status %d\n",
+			status);
+	else
+		fwlog->supported = true;
+
+	kfree(cfg);
+}
+
+/**
+ * libie_fwlog_init - Initialize FW logging configuration
+ * @fwlog: pointer to the fwlog structure
+ * @api: api structure to init fwlog
+ *
+ * This function should be called on driver initialization during
+ * libie_init_hw().
+ */
+int libie_fwlog_init(struct libie_fwlog *fwlog, struct libie_fwlog_api *api)
+{
+	fwlog->api = *api;
+	libie_fwlog_set_supported(fwlog);
+
+	if (libie_fwlog_supported(fwlog)) {
+		int status;
+
+		/* read the current config from the FW and store it */
+		status = libie_aq_fwlog_get(fwlog, &fwlog->cfg);
+		if (status)
+			return status;
+
+		fwlog->ring.rings = kcalloc(LIBIE_FWLOG_RING_SIZE_DFLT,
+					    sizeof(*fwlog->ring.rings),
+					    GFP_KERNEL);
+		if (!fwlog->ring.rings) {
+			dev_warn(&fwlog->pdev->dev, "Unable to allocate memory for FW log rings\n");
+			return -ENOMEM;
+		}
+
+		fwlog->ring.size = LIBIE_FWLOG_RING_SIZE_DFLT;
+		fwlog->ring.index = LIBIE_FWLOG_RING_SIZE_INDEX_DFLT;
+
+		status = libie_fwlog_alloc_ring_buffs(&fwlog->ring);
+		if (status) {
+			dev_warn(&fwlog->pdev->dev, "Unable to allocate memory for FW log ring data buffers\n");
+			libie_fwlog_free_ring_buffs(&fwlog->ring);
+			kfree(fwlog->ring.rings);
+			return status;
+		}
+
+		libie_debugfs_fwlog_init(fwlog, api->debugfs_root);
+	} else {
+		dev_warn(&fwlog->pdev->dev, "FW logging is not supported in this NVM image. Please update the NVM to get FW log support\n");
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(libie_fwlog_init);
+
+/**
+ * libie_fwlog_deinit - unroll FW logging configuration
+ * @fwlog: pointer to the fwlog structure
+ *
+ * This function should be called in libie_deinit_hw().
+ */
+void libie_fwlog_deinit(struct libie_fwlog *fwlog)
+{
+	int status;
+
+	/* make sure FW logging is disabled to not put the FW in a weird state
+	 * for the next driver load
+	 */
+	fwlog->cfg.options &= ~LIBIE_FWLOG_OPTION_ARQ_ENA;
+	status = libie_fwlog_set(fwlog, &fwlog->cfg);
+	if (status)
+		dev_warn(&fwlog->pdev->dev, "Unable to turn off FW logging, status: %d\n",
+			 status);
+
+	kfree(fwlog->debugfs_modules);
+
+	fwlog->debugfs_modules = NULL;
+
+	status = libie_fwlog_unregister(fwlog);
+	if (status)
+		dev_warn(&fwlog->pdev->dev, "Unable to unregister FW logging, status: %d\n",
+			 status);
+
+	if (fwlog->ring.rings) {
+		libie_fwlog_free_ring_buffs(&fwlog->ring);
+		kfree(fwlog->ring.rings);
+	}
+}
+EXPORT_SYMBOL_GPL(libie_fwlog_deinit);
+
+/**
+ * libie_get_fwlog_data - copy the FW log data from ARQ event
+ * @fwlog: fwlog that the FW log event is associated with
+ * @buf: event buffer pointer
+ * @len: len of event descriptor
+ */
+void libie_get_fwlog_data(struct libie_fwlog *fwlog, u8 *buf, u16 len)
+{
+	struct libie_fwlog_data *log;
+
+	log = &fwlog->ring.rings[fwlog->ring.tail];
+
+	memset(log->data, 0, PAGE_SIZE);
+	log->data_size = len;
+
+	memcpy(log->data, buf, log->data_size);
+	libie_fwlog_ring_increment(&fwlog->ring.tail, fwlog->ring.size);
+
+	if (libie_fwlog_ring_full(&fwlog->ring)) {
+		/* the rings are full so bump the head to create room */
+		libie_fwlog_ring_increment(&fwlog->ring.head, fwlog->ring.size);
+	}
+}
+EXPORT_SYMBOL_GPL(libie_get_fwlog_data);
+
+void libie_fwlog_reregister(struct libie_fwlog *fwlog)
+{
+	if (!(fwlog->cfg.options & LIBIE_FWLOG_OPTION_IS_REGISTERED))
+		return;
+
+	if (libie_fwlog_register(fwlog))
+		fwlog->cfg.options &= ~LIBIE_FWLOG_OPTION_IS_REGISTERED;
+}
+EXPORT_SYMBOL_GPL(libie_fwlog_reregister);
+
+MODULE_DESCRIPTION("Intel(R) Ethernet common library");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/intel/libie/rx.c b/drivers/net/ethernet/intel/libie/rx.c
index 66a9825fe11f..6fda656afa9c 100644
--- a/drivers/net/ethernet/intel/libie/rx.c
+++ b/drivers/net/ethernet/intel/libie/rx.c
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/* Copyright (C) 2024 Intel Corporation */
+/* Copyright (C) 2024-2025 Intel Corporation */
 
+#define DEFAULT_SYMBOL_NAMESPACE	"LIBIE"
+
+#include <linux/export.h>
 #include <linux/net/intel/libie/rx.h>
 
 /* O(1) converting i40e/ice/iavf's 8/10-bit hardware packet type to a parsed
@@ -116,7 +119,7 @@ const struct libeth_rx_pt libie_rx_pt_lut[LIBIE_RX_PT_NUM] = {
 	LIBIE_RX_PT_IP(4),
 	LIBIE_RX_PT_IP(6),
 };
-EXPORT_SYMBOL_NS_GPL(libie_rx_pt_lut, "LIBIE");
+EXPORT_SYMBOL_GPL(libie_rx_pt_lut);
 
 MODULE_DESCRIPTION("Intel(R) Ethernet common library");
 MODULE_IMPORT_NS("LIBETH");
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index 87c7e6251a4f..891a94d89f4b 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -900,7 +900,8 @@ static void korina_check_media(struct net_device *dev, unsigned int init_media)
 
 static void korina_poll_media(struct timer_list *t)
 {
-	struct korina_private *lp = from_timer(lp, t, media_check_timer);
+	struct korina_private *lp = timer_container_of(lp, t,
+						       media_check_timer);
 	struct net_device *dev = lp->dev;
 
 	korina_check_media(dev, 0);
@@ -1239,7 +1240,7 @@ static int korina_close(struct net_device *dev)
 	struct korina_private *lp = netdev_priv(dev);
 	u32 tmp;
 
-	del_timer(&lp->media_check_timer);
+	timer_delete(&lp->media_check_timer);
 
 	/* Disable interrupts */
 	disable_irq(lp->rx_irq);
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index 837295fecd17..50f7c59e8a04 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -34,7 +34,6 @@ config MV643XX_ETH
 config MVMDIO
 	tristate "Marvell MDIO interface support"
 	depends on HAS_IOMEM
-	select MDIO_DEVRES
 	select PHYLIB
 	help
 	  This driver supports the MDIO interface found in the network
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index a06048719e84..0ab52c57c648 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -1333,7 +1333,8 @@ static void mib_counters_update(struct mv643xx_eth_private *mp)
 
 static void mib_counters_timer_wrapper(struct timer_list *t)
 {
-	struct mv643xx_eth_private *mp = from_timer(mp, t, mib_counters_timer);
+	struct mv643xx_eth_private *mp = timer_container_of(mp, t,
+							    mib_counters_timer);
 	mib_counters_update(mp);
 	mod_timer(&mp->mib_counters_timer, jiffies + 30 * HZ);
 }
@@ -2247,7 +2248,7 @@ static int mv643xx_eth_poll(struct napi_struct *napi, int budget)
 
 	if (unlikely(mp->oom)) {
 		mp->oom = 0;
-		del_timer(&mp->rx_oom);
+		timer_delete(&mp->rx_oom);
 	}
 
 	work_done = 0;
@@ -2306,7 +2307,7 @@ static int mv643xx_eth_poll(struct napi_struct *napi, int budget)
 
 static inline void oom_timer_wrapper(struct timer_list *t)
 {
-	struct mv643xx_eth_private *mp = from_timer(mp, t, rx_oom);
+	struct mv643xx_eth_private *mp = timer_container_of(mp, t, rx_oom);
 
 	napi_schedule(&mp->napi);
 }
@@ -2521,7 +2522,7 @@ static int mv643xx_eth_stop(struct net_device *dev)
 
 	napi_disable(&mp->napi);
 
-	del_timer_sync(&mp->rx_oom);
+	timer_delete_sync(&mp->rx_oom);
 
 	netif_carrier_off(dev);
 	if (dev->phydev)
@@ -2531,7 +2532,7 @@ static int mv643xx_eth_stop(struct net_device *dev)
 	port_reset(mp);
 	mv643xx_eth_get_stats(dev);
 	mib_counters_update(mp);
-	del_timer_sync(&mp->mib_counters_timer);
+	timer_delete_sync(&mp->mib_counters_timer);
 
 	for (i = 0; i < mp->rxq_count; i++)
 		rxq_deinit(mp->rxq + i);
@@ -2704,9 +2705,15 @@ static struct platform_device *port_platdev[3];
 
 static void mv643xx_eth_shared_of_remove(void)
 {
+	struct mv643xx_eth_platform_data *pd;
 	int n;
 
 	for (n = 0; n < 3; n++) {
+		if (!port_platdev[n])
+			continue;
+		pd = dev_get_platdata(&port_platdev[n]->dev);
+		if (pd)
+			of_node_put(pd->phy_node);
 		platform_device_del(port_platdev[n]);
 		port_platdev[n] = NULL;
 	}
@@ -2769,8 +2776,10 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev,
 	}
 
 	ppdev = platform_device_alloc(MV643XX_ETH_NAME, dev_num);
-	if (!ppdev)
-		return -ENOMEM;
+	if (!ppdev) {
+		ret = -ENOMEM;
+		goto put_err;
+	}
 	ppdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
 	ppdev->dev.of_node = pnp;
 
@@ -2792,6 +2801,8 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev,
 
 port_err:
 	platform_device_put(ppdev);
+put_err:
+	of_node_put(ppd.phy_node);
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index fe6261b81540..7af44f858fa3 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -284,8 +284,12 @@
 					  MVNETA_TXQ_BUCKET_REFILL_PERIOD))
 
 #define MVNETA_LPI_CTRL_0                        0x2cc0
+#define      MVNETA_LPI_CTRL_0_TS                (0xff << 8)
 #define MVNETA_LPI_CTRL_1                        0x2cc4
-#define      MVNETA_LPI_REQUEST_ENABLE           BIT(0)
+#define      MVNETA_LPI_CTRL_1_REQUEST_ENABLE    BIT(0)
+#define      MVNETA_LPI_CTRL_1_REQUEST_FORCE     BIT(1)
+#define      MVNETA_LPI_CTRL_1_MANUAL_MODE       BIT(2)
+#define      MVNETA_LPI_CTRL_1_TW                (0xfff << 4)
 #define MVNETA_LPI_CTRL_2                        0x2cc8
 #define MVNETA_LPI_STATUS                        0x2ccc
 
@@ -541,10 +545,6 @@ struct mvneta_port {
 	struct mvneta_bm_pool *pool_short;
 	int bm_win_id;
 
-	bool eee_enabled;
-	bool eee_active;
-	bool tx_lpi_enabled;
-
 	u64 ethtool_stats[ARRAY_SIZE(mvneta_statistics)];
 
 	u32 indir[MVNETA_RSS_LU_TABLE_SIZE];
@@ -2342,7 +2342,7 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp,
 	prefetch(data);
 	xdp_buff_clear_frags_flag(xdp);
 	xdp_prepare_buff(xdp, data, pp->rx_offset_correction + MVNETA_MH_SIZE,
-			 data_len, false);
+			 data_len, true);
 }
 
 static void
@@ -2396,6 +2396,7 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 		      struct xdp_buff *xdp, u32 desc_status)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	u32 metasize = xdp->data - xdp->data_meta;
 	struct sk_buff *skb;
 	u8 num_frags;
 
@@ -2410,13 +2411,14 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	skb_put(skb, xdp->data_end - xdp->data);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 	skb->ip_summed = mvneta_rx_csum(pp, desc_status);
 
 	if (unlikely(xdp_buff_has_frags(xdp)))
-		xdp_update_skb_shared_info(skb, num_frags,
-					   sinfo->xdp_frags_size,
-					   num_frags * xdp->frame_sz,
-					   xdp_buff_is_frag_pfmemalloc(xdp));
+		xdp_update_skb_frags_info(skb, num_frags, sinfo->xdp_frags_size,
+					  num_frags * xdp->frame_sz,
+					  xdp_buff_get_skb_flags(xdp));
 
 	return skb;
 }
@@ -2982,6 +2984,13 @@ out:
 		if (txq->count >= txq->tx_stop_threshold)
 			netif_tx_stop_queue(nq);
 
+		/* This is not really the true transmit point, since we batch
+		 * up several before hitting the hardware, but is the best we
+		 * can do without more complexity to walk the packets in the
+		 * pending section of the transmit queue.
+		 */
+		skb_tx_timestamp(skb);
+
 		if (!netdev_xmit_more() || netif_xmit_stopped(nq) ||
 		    txq->pending + frags > MVNETA_TXQ_DEC_SENT_MASK)
 			mvneta_txq_pend_desc_add(pp, txq, frags);
@@ -3983,7 +3992,7 @@ static unsigned int mvneta_pcs_inband_caps(struct phylink_pcs *pcs,
 	return LINK_INBAND_DISABLE;
 }
 
-static void mvneta_pcs_get_state(struct phylink_pcs *pcs,
+static void mvneta_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode,
 				 struct phylink_link_state *state)
 {
 	struct mvneta_port *pp = mvneta_pcs_to_port(pcs);
@@ -4213,18 +4222,6 @@ static int mvneta_mac_finish(struct phylink_config *config, unsigned int mode,
 	return 0;
 }
 
-static void mvneta_set_eee(struct mvneta_port *pp, bool enable)
-{
-	u32 lpi_ctl1;
-
-	lpi_ctl1 = mvreg_read(pp, MVNETA_LPI_CTRL_1);
-	if (enable)
-		lpi_ctl1 |= MVNETA_LPI_REQUEST_ENABLE;
-	else
-		lpi_ctl1 &= ~MVNETA_LPI_REQUEST_ENABLE;
-	mvreg_write(pp, MVNETA_LPI_CTRL_1, lpi_ctl1);
-}
-
 static void mvneta_mac_link_down(struct phylink_config *config,
 				 unsigned int mode, phy_interface_t interface)
 {
@@ -4240,9 +4237,6 @@ static void mvneta_mac_link_down(struct phylink_config *config,
 		val |= MVNETA_GMAC_FORCE_LINK_DOWN;
 		mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
 	}
-
-	pp->eee_active = false;
-	mvneta_set_eee(pp, false);
 }
 
 static void mvneta_mac_link_up(struct phylink_config *config,
@@ -4291,11 +4285,56 @@ static void mvneta_mac_link_up(struct phylink_config *config,
 	}
 
 	mvneta_port_up(pp);
+}
 
-	if (phy && pp->eee_enabled) {
-		pp->eee_active = phy_init_eee(phy, false) >= 0;
-		mvneta_set_eee(pp, pp->eee_active && pp->tx_lpi_enabled);
+static void mvneta_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct mvneta_port *pp = netdev_priv(to_net_dev(config->dev));
+	u32 lpi1;
+
+	lpi1 = mvreg_read(pp, MVNETA_LPI_CTRL_1);
+	lpi1 &= ~(MVNETA_LPI_CTRL_1_REQUEST_ENABLE |
+		  MVNETA_LPI_CTRL_1_REQUEST_FORCE |
+		  MVNETA_LPI_CTRL_1_MANUAL_MODE);
+	mvreg_write(pp, MVNETA_LPI_CTRL_1, lpi1);
+}
+
+static int mvneta_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
+				    bool tx_clk_stop)
+{
+	struct mvneta_port *pp = netdev_priv(to_net_dev(config->dev));
+	u32 ts, tw, lpi0, lpi1, status;
+
+	status = mvreg_read(pp, MVNETA_GMAC_STATUS);
+	if (status & MVNETA_GMAC_SPEED_1000) {
+		/* At 1G speeds, the timer resolution are 1us, and
+		 * 802.3 says tw is 16.5us. Round up to 17us.
+		 */
+		tw = 17;
+		ts = timer;
+	} else {
+		/* At 100M speeds, the timer resolutions are 10us, and
+		 * 802.3 says tw is 30us.
+		 */
+		tw = 3;
+		ts = DIV_ROUND_UP(timer, 10);
 	}
+
+	if (ts > 255)
+		ts = 255;
+
+	/* Configure ts */
+	lpi0 = mvreg_read(pp, MVNETA_LPI_CTRL_0);
+	lpi0 = u32_replace_bits(lpi0, ts, MVNETA_LPI_CTRL_0_TS);
+	mvreg_write(pp, MVNETA_LPI_CTRL_0, lpi0);
+
+	/* Configure tw and enable LPI generation */
+	lpi1 = mvreg_read(pp, MVNETA_LPI_CTRL_1);
+	lpi1 = u32_replace_bits(lpi1, tw, MVNETA_LPI_CTRL_1_TW);
+	lpi1 |= MVNETA_LPI_CTRL_1_REQUEST_ENABLE;
+	mvreg_write(pp, MVNETA_LPI_CTRL_1, lpi1);
+
+	return 0;
 }
 
 static const struct phylink_mac_ops mvneta_phylink_ops = {
@@ -4305,6 +4344,8 @@ static const struct phylink_mac_ops mvneta_phylink_ops = {
 	.mac_finish = mvneta_mac_finish,
 	.mac_link_down = mvneta_mac_link_down,
 	.mac_link_up = mvneta_mac_link_up,
+	.mac_disable_tx_lpi = mvneta_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = mvneta_mac_enable_tx_lpi,
 };
 
 static int mvneta_mdio_probe(struct mvneta_port *pp)
@@ -4392,6 +4433,7 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node)
 	if (pp->neta_armada3700)
 		return 0;
 
+	netdev_lock(port->napi.dev);
 	spin_lock(&pp->lock);
 	/*
 	 * Configuring the driver for a new CPU while the driver is
@@ -4399,6 +4441,7 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node)
 	 */
 	if (pp->is_stopped) {
 		spin_unlock(&pp->lock);
+		netdev_unlock(port->napi.dev);
 		return 0;
 	}
 	netif_tx_stop_all_queues(pp->dev);
@@ -4418,7 +4461,7 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node)
 
 	/* Mask all ethernet port interrupts */
 	on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
-	napi_enable(&port->napi);
+	napi_enable_locked(&port->napi);
 
 	/*
 	 * Enable per-CPU interrupts on the CPU that is
@@ -4439,6 +4482,8 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node)
 		    MVNETA_CAUSE_LINK_CHANGE);
 	netif_tx_start_all_queues(pp->dev);
 	spin_unlock(&pp->lock);
+	netdev_unlock(port->napi.dev);
+
 	return 0;
 }
 
@@ -4571,7 +4616,7 @@ static int mvneta_stop(struct net_device *dev)
 		/* Inform that we are stopping so we don't want to setup the
 		 * driver for new CPUs in the notifiers. The code of the
 		 * notifier for CPU online is protected by the same spinlock,
-		 * so when we get the lock, the notifer work is done.
+		 * so when we get the lock, the notifier work is done.
 		 */
 		spin_lock(&pp->lock);
 		pp->is_stopped = true;
@@ -4967,19 +5012,9 @@ static u32 mvneta_ethtool_get_rxfh_indir_size(struct net_device *dev)
 	return MVNETA_RSS_LU_TABLE_SIZE;
 }
 
-static int mvneta_ethtool_get_rxnfc(struct net_device *dev,
-				    struct ethtool_rxnfc *info,
-				    u32 *rules __always_unused)
+static u32 mvneta_ethtool_get_rx_ring_count(struct net_device *dev)
 {
-	switch (info->cmd) {
-	case ETHTOOL_GRXRINGS:
-		info->data =  rxq_number;
-		return 0;
-	case ETHTOOL_GRXFH:
-		return -EOPNOTSUPP;
-	default:
-		return -EOPNOTSUPP;
-	}
+	return rxq_number;
 }
 
 static int  mvneta_config_rss(struct mvneta_port *pp)
@@ -5106,14 +5141,6 @@ static int mvneta_ethtool_get_eee(struct net_device *dev,
 				  struct ethtool_keee *eee)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
-	u32 lpi_ctl0;
-
-	lpi_ctl0 = mvreg_read(pp, MVNETA_LPI_CTRL_0);
-
-	eee->eee_enabled = pp->eee_enabled;
-	eee->eee_active = pp->eee_active;
-	eee->tx_lpi_enabled = pp->tx_lpi_enabled;
-	eee->tx_lpi_timer = (lpi_ctl0) >> 8; // * scale;
 
 	return phylink_ethtool_get_eee(pp->phylink, eee);
 }
@@ -5122,7 +5149,6 @@ static int mvneta_ethtool_set_eee(struct net_device *dev,
 				  struct ethtool_keee *eee)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
-	u32 lpi_ctl0;
 
 	/* The Armada 37x documents do not give limits for this other than
 	 * it being an 8-bit register.
@@ -5130,16 +5156,6 @@ static int mvneta_ethtool_set_eee(struct net_device *dev,
 	if (eee->tx_lpi_enabled && eee->tx_lpi_timer > 255)
 		return -EINVAL;
 
-	lpi_ctl0 = mvreg_read(pp, MVNETA_LPI_CTRL_0);
-	lpi_ctl0 &= ~(0xff << 8);
-	lpi_ctl0 |= eee->tx_lpi_timer << 8;
-	mvreg_write(pp, MVNETA_LPI_CTRL_0, lpi_ctl0);
-
-	pp->eee_enabled = eee->eee_enabled;
-	pp->tx_lpi_enabled = eee->tx_lpi_enabled;
-
-	mvneta_set_eee(pp, eee->tx_lpi_enabled && eee->eee_enabled);
-
 	return phylink_ethtool_set_eee(pp->phylink, eee);
 }
 
@@ -5332,13 +5348,14 @@ static const struct ethtool_ops mvneta_eth_tool_ops = {
 	.get_ethtool_stats = mvneta_ethtool_get_stats,
 	.get_sset_count	= mvneta_ethtool_get_sset_count,
 	.get_rxfh_indir_size = mvneta_ethtool_get_rxfh_indir_size,
-	.get_rxnfc	= mvneta_ethtool_get_rxnfc,
+	.get_rx_ring_count = mvneta_ethtool_get_rx_ring_count,
 	.get_rxfh	= mvneta_ethtool_get_rxfh,
 	.set_rxfh	= mvneta_ethtool_set_rxfh,
 	.get_link_ksettings = mvneta_ethtool_get_link_ksettings,
 	.set_link_ksettings = mvneta_ethtool_set_link_ksettings,
 	.get_wol        = mvneta_ethtool_get_wol,
 	.set_wol        = mvneta_ethtool_set_wol,
+	.get_ts_info	= ethtool_op_get_ts_info,
 	.get_eee	= mvneta_ethtool_get_eee,
 	.set_eee	= mvneta_ethtool_set_eee,
 };
@@ -5453,6 +5470,9 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 	    !phy_interface_mode_is_rgmii(phy_mode))
 		return -EINVAL;
 
+	/* Ensure LPI is disabled */
+	mvneta_mac_disable_tx_lpi(&pp->phylink_config);
+
 	return 0;
 }
 
@@ -5537,13 +5557,19 @@ static int mvneta_probe(struct platform_device *pdev)
 		clk_prepare_enable(pp->clk_bus);
 
 	pp->phylink_pcs.ops = &mvneta_phylink_pcs_ops;
-	pp->phylink_pcs.neg_mode = true;
 
 	pp->phylink_config.dev = &dev->dev;
 	pp->phylink_config.type = PHYLINK_NETDEV;
 	pp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_10 |
 		MAC_100 | MAC_1000FD | MAC_2500FD;
 
+	/* Setup EEE. Choose 250us idle. Only supported in SGMII modes. */
+	__set_bit(PHY_INTERFACE_MODE_QSGMII, pp->phylink_config.lpi_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_SGMII, pp->phylink_config.lpi_interfaces);
+	pp->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD;
+	pp->phylink_config.lpi_timer_default = 250;
+	pp->phylink_config.eee_enabled_default = true;
+
 	phy_interface_set_rgmii(pp->phylink_config.supported_interfaces);
 	__set_bit(PHY_INTERFACE_MODE_QSGMII,
 		  pp->phylink_config.supported_interfaces);
diff --git a/drivers/net/ethernet/marvell/mvneta_bm.h b/drivers/net/ethernet/marvell/mvneta_bm.h
index e47783ce77e0..57ac039df6f7 100644
--- a/drivers/net/ethernet/marvell/mvneta_bm.h
+++ b/drivers/net/ethernet/marvell/mvneta_bm.h
@@ -115,7 +115,7 @@ struct mvneta_bm_pool {
 
 	/* Packet size */
 	int pkt_size;
-	/* Size of the buffer acces through DMA*/
+	/* Size of the buffer access through DMA */
 	u32 buf_size;
 
 	/* BPPE virtual base address */
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 9e02e4367bec..061fcd444d50 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -481,6 +481,11 @@
 #define MVPP22_GMAC_INT_SUM_MASK		0xa4
 #define     MVPP22_GMAC_INT_SUM_MASK_LINK_STAT	BIT(1)
 #define	    MVPP22_GMAC_INT_SUM_MASK_PTP	BIT(2)
+#define MVPP2_GMAC_LPI_CTRL0			0xc0
+#define     MVPP2_GMAC_LPI_CTRL0_TS_MASK	GENMASK(15, 8)
+#define MVPP2_GMAC_LPI_CTRL1			0xc4
+#define     MVPP2_GMAC_LPI_CTRL1_REQ_EN		BIT(0)
+#define     MVPP2_GMAC_LPI_CTRL1_TW_MASK	GENMASK(15, 4)
 
 /* Per-port XGMAC registers. PPv2.2 and PPv2.3, only for GOP port 0,
  * relative to port->base.
@@ -1108,6 +1113,9 @@ struct mvpp2 {
 
 	/* Spinlocks for CM3 shared memory configuration */
 	spinlock_t mss_spinlock;
+
+	/* Spinlock for shared PRS parser memory and shadow table */
+	spinlock_t prs_spinlock;
 };
 
 struct mvpp2_pcpu_stats {
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 1641791a2d5b..44b201817d94 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -324,7 +324,7 @@ static const struct mvpp2_cls_flow cls_flows[MVPP2_N_PRS_FLOWS] = {
 		       MVPP2_PRS_RI_VLAN_MASK),
 	/* Non IP flow, with vlan tag */
 	MVPP2_DEF_FLOW(MVPP22_FLOW_ETHERNET, MVPP2_FL_NON_IP_TAG,
-		       MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP22_CLS_HEK_TAGGED,
 		       0, 0),
 };
 
@@ -1618,7 +1618,8 @@ int mvpp22_port_rss_ctx_indir_get(struct mvpp2_port *port, u32 port_ctx,
 	return 0;
 }
 
-int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info)
+int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port,
+			   const struct ethtool_rxfh_fields *info)
 {
 	u16 hash_opts = 0;
 	u32 flow_type;
@@ -1656,7 +1657,8 @@ int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info)
 	return mvpp2_port_rss_hash_opts_set(port, flow_type, hash_opts);
 }
 
-int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info)
+int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port,
+			   struct ethtool_rxfh_fields *info)
 {
 	unsigned long hash_opts;
 	u32 flow_type;
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index 85c9c6e80678..caadf3aea95d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -272,8 +272,10 @@ int mvpp22_port_rss_ctx_indir_set(struct mvpp2_port *port, u32 rss_ctx,
 int mvpp22_port_rss_ctx_indir_get(struct mvpp2_port *port, u32 rss_ctx,
 				  u32 *indir);
 
-int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info);
-int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info);
+int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port,
+			   struct ethtool_rxfh_fields *info);
+int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port,
+			   const struct ethtool_rxfh_fields *info);
 
 void mvpp2_cls_init(struct mvpp2 *priv);
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index f85229a30844..33426fded919 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3915,13 +3915,13 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 
 	while (rx_done < rx_todo) {
 		struct mvpp2_rx_desc *rx_desc = mvpp2_rxq_next_desc_get(rxq);
+		u32 rx_status, timestamp, metasize = 0;
 		struct mvpp2_bm_pool *bm_pool;
 		struct page_pool *pp = NULL;
 		struct sk_buff *skb;
 		unsigned int frag_size;
 		dma_addr_t dma_addr;
 		phys_addr_t phys_addr;
-		u32 rx_status, timestamp;
 		int pool, rx_bytes, err, ret;
 		struct page *page;
 		void *data;
@@ -3983,7 +3983,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 			xdp_init_buff(&xdp, PAGE_SIZE, xdp_rxq);
 			xdp_prepare_buff(&xdp, data,
 					 MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM,
-					 rx_bytes, false);
+					 rx_bytes, true);
 
 			ret = mvpp2_run_xdp(port, xdp_prog, &xdp, pp, &ps);
 
@@ -3999,6 +3999,8 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 				ps.rx_bytes += rx_bytes;
 				continue;
 			}
+
+			metasize = xdp.data - xdp.data_meta;
 		}
 
 		if (frag_size)
@@ -4038,6 +4040,8 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 
 		skb_reserve(skb, MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM);
 		skb_put(skb, rx_bytes);
+		if (metasize)
+			skb_metadata_set(skb, metasize);
 		skb->ip_summed = mvpp2_rx_csum(port, rx_status);
 		skb->protocol = eth_type_trans(skb, dev);
 
@@ -4435,6 +4439,8 @@ out:
 		txq_pcpu->count += frags;
 		aggr_txq->count += frags;
 
+		skb_tx_timestamp(skb);
+
 		/* Enable transmit */
 		wmb();
 		mvpp2_aggr_txq_pend_desc_add(port, frags);
@@ -5169,38 +5175,40 @@ mvpp2_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	stats->tx_dropped	= dev->stats.tx_dropped;
 }
 
-static int mvpp2_set_ts_config(struct mvpp2_port *port, struct ifreq *ifr)
+static int mvpp2_hwtstamp_set(struct net_device *dev,
+			      struct kernel_hwtstamp_config *config,
+			      struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
+	struct mvpp2_port *port = netdev_priv(dev);
 	void __iomem *ptp;
 	u32 gcr, int_mask;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	if (!port->hwtstamp)
+		return -EOPNOTSUPP;
 
-	if (config.tx_type != HWTSTAMP_TX_OFF &&
-	    config.tx_type != HWTSTAMP_TX_ON)
+	if (config->tx_type != HWTSTAMP_TX_OFF &&
+	    config->tx_type != HWTSTAMP_TX_ON)
 		return -ERANGE;
 
 	ptp = port->priv->iface_base + MVPP22_PTP_BASE(port->gop_id);
 
 	int_mask = gcr = 0;
-	if (config.tx_type != HWTSTAMP_TX_OFF) {
+	if (config->tx_type != HWTSTAMP_TX_OFF) {
 		gcr |= MVPP22_PTP_GCR_TSU_ENABLE | MVPP22_PTP_GCR_TX_RESET;
 		int_mask |= MVPP22_PTP_INT_MASK_QUEUE1 |
 			    MVPP22_PTP_INT_MASK_QUEUE0;
 	}
 
 	/* It seems we must also release the TX reset when enabling the TSU */
-	if (config.rx_filter != HWTSTAMP_FILTER_NONE)
+	if (config->rx_filter != HWTSTAMP_FILTER_NONE)
 		gcr |= MVPP22_PTP_GCR_TSU_ENABLE | MVPP22_PTP_GCR_RX_RESET |
 		       MVPP22_PTP_GCR_TX_RESET;
 
 	if (gcr & MVPP22_PTP_GCR_TSU_ENABLE)
 		mvpp22_tai_start(port->priv->tai);
 
-	if (config.rx_filter != HWTSTAMP_FILTER_NONE) {
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+	if (config->rx_filter != HWTSTAMP_FILTER_NONE) {
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		mvpp2_modify(ptp + MVPP22_PTP_GCR,
 			     MVPP22_PTP_GCR_RX_RESET |
 			     MVPP22_PTP_GCR_TX_RESET |
@@ -5221,26 +5229,22 @@ static int mvpp2_set_ts_config(struct mvpp2_port *port, struct ifreq *ifr)
 	if (!(gcr & MVPP22_PTP_GCR_TSU_ENABLE))
 		mvpp22_tai_stop(port->priv->tai);
 
-	port->tx_hwtstamp_type = config.tx_type;
-
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	port->tx_hwtstamp_type = config->tx_type;
 
 	return 0;
 }
 
-static int mvpp2_get_ts_config(struct mvpp2_port *port, struct ifreq *ifr)
+static int mvpp2_hwtstamp_get(struct net_device *dev,
+			      struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config config;
-
-	memset(&config, 0, sizeof(config));
+	struct mvpp2_port *port = netdev_priv(dev);
 
-	config.tx_type = port->tx_hwtstamp_type;
-	config.rx_filter = port->rx_hwtstamp ?
-		HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
+	if (!port->hwtstamp)
+		return -EOPNOTSUPP;
 
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	config->tx_type = port->tx_hwtstamp_type;
+	config->rx_filter = port->rx_hwtstamp ? HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
 
 	return 0;
 }
@@ -5250,14 +5254,14 @@ static int mvpp2_ethtool_get_ts_info(struct net_device *dev,
 {
 	struct mvpp2_port *port = netdev_priv(dev);
 
+	ethtool_op_get_ts_info(dev, info);
 	if (!port->hwtstamp)
-		return -EOPNOTSUPP;
+		return 0;
 
 	info->phc_index = mvpp22_tai_ptp_clock_index(port->priv->tai);
-	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_TX_HARDWARE |
-				SOF_TIMESTAMPING_RX_HARDWARE |
-				SOF_TIMESTAMPING_RAW_HARDWARE;
+	info->so_timestamping |= SOF_TIMESTAMPING_TX_HARDWARE |
+				 SOF_TIMESTAMPING_RX_HARDWARE |
+				 SOF_TIMESTAMPING_RAW_HARDWARE;
 	info->tx_types = BIT(HWTSTAMP_TX_OFF) |
 			 BIT(HWTSTAMP_TX_ON);
 	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
@@ -5270,18 +5274,6 @@ static int mvpp2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
 
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		if (port->hwtstamp)
-			return mvpp2_set_ts_config(port, ifr);
-		break;
-
-	case SIOCGHWTSTAMP:
-		if (port->hwtstamp)
-			return mvpp2_get_ts_config(port, ifr);
-		break;
-	}
-
 	if (!port->phylink)
 		return -ENOTSUPP;
 
@@ -5588,6 +5580,13 @@ static int mvpp2_ethtool_set_link_ksettings(struct net_device *dev,
 	return phylink_ethtool_ksettings_set(port->phylink, cmd);
 }
 
+static u32 mvpp2_ethtool_get_rx_ring_count(struct net_device *dev)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	return port->nrxqs;
+}
+
 static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
 				   struct ethtool_rxnfc *info, u32 *rules)
 {
@@ -5598,12 +5597,6 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
 		return -EOPNOTSUPP;
 
 	switch (info->cmd) {
-	case ETHTOOL_GRXFH:
-		ret = mvpp2_ethtool_rxfh_get(port, info);
-		break;
-	case ETHTOOL_GRXRINGS:
-		info->data = port->nrxqs;
-		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		info->rule_cnt = port->n_rfs_rules;
 		break;
@@ -5638,9 +5631,6 @@ static int mvpp2_ethtool_set_rxnfc(struct net_device *dev,
 		return -EOPNOTSUPP;
 
 	switch (info->cmd) {
-	case ETHTOOL_SRXFH:
-		ret = mvpp2_ethtool_rxfh_set(port, info);
-		break;
 	case ETHTOOL_SRXCLSRLINS:
 		ret = mvpp2_ethtool_cls_rule_ins(port, info);
 		break;
@@ -5757,6 +5747,51 @@ static int mvpp2_ethtool_set_rxfh(struct net_device *dev,
 	return mvpp2_modify_rxfh_context(dev, NULL, rxfh, extack);
 }
 
+static int mvpp2_ethtool_get_rxfh_fields(struct net_device *dev,
+					 struct ethtool_rxfh_fields *info)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	if (!mvpp22_rss_is_supported(port))
+		return -EOPNOTSUPP;
+
+	return mvpp2_ethtool_rxfh_get(port, info);
+}
+
+static int mvpp2_ethtool_set_rxfh_fields(struct net_device *dev,
+					 const struct ethtool_rxfh_fields *info,
+					 struct netlink_ext_ack *extack)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	if (!mvpp22_rss_is_supported(port))
+		return -EOPNOTSUPP;
+
+	return mvpp2_ethtool_rxfh_set(port, info);
+}
+
+static int mvpp2_ethtool_get_eee(struct net_device *dev,
+				 struct ethtool_keee *eee)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	if (!port->phylink)
+		return -EOPNOTSUPP;
+
+	return phylink_ethtool_get_eee(port->phylink, eee);
+}
+
+static int mvpp2_ethtool_set_eee(struct net_device *dev,
+				 struct ethtool_keee *eee)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	if (!port->phylink)
+		return -EOPNOTSUPP;
+
+	return phylink_ethtool_set_eee(port->phylink, eee);
+}
+
 /* Device ops */
 
 static const struct net_device_ops mvpp2_netdev_ops = {
@@ -5773,6 +5808,8 @@ static const struct net_device_ops mvpp2_netdev_ops = {
 	.ndo_set_features	= mvpp2_set_features,
 	.ndo_bpf		= mvpp2_xdp,
 	.ndo_xdp_xmit		= mvpp2_xdp_xmit,
+	.ndo_hwtstamp_get	= mvpp2_hwtstamp_get,
+	.ndo_hwtstamp_set	= mvpp2_hwtstamp_set,
 };
 
 static const struct ethtool_ops mvpp2_eth_tool_ops = {
@@ -5794,14 +5831,19 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.set_pauseparam		= mvpp2_ethtool_set_pause_param,
 	.get_link_ksettings	= mvpp2_ethtool_get_link_ksettings,
 	.set_link_ksettings	= mvpp2_ethtool_set_link_ksettings,
+	.get_rx_ring_count	= mvpp2_ethtool_get_rx_ring_count,
 	.get_rxnfc		= mvpp2_ethtool_get_rxnfc,
 	.set_rxnfc		= mvpp2_ethtool_set_rxnfc,
 	.get_rxfh_indir_size	= mvpp2_ethtool_get_rxfh_indir_size,
 	.get_rxfh		= mvpp2_ethtool_get_rxfh,
 	.set_rxfh		= mvpp2_ethtool_set_rxfh,
+	.get_rxfh_fields	= mvpp2_ethtool_get_rxfh_fields,
+	.set_rxfh_fields	= mvpp2_ethtool_set_rxfh_fields,
 	.create_rxfh_context	= mvpp2_create_rxfh_context,
 	.modify_rxfh_context	= mvpp2_modify_rxfh_context,
 	.remove_rxfh_context	= mvpp2_remove_rxfh_context,
+	.get_eee		= mvpp2_ethtool_get_eee,
+	.set_eee		= mvpp2_ethtool_set_eee,
 };
 
 /* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that
@@ -6187,7 +6229,14 @@ static struct mvpp2_port *mvpp2_pcs_gmac_to_port(struct phylink_pcs *pcs)
 	return container_of(pcs, struct mvpp2_port, pcs_gmac);
 }
 
+static unsigned int mvpp2_xjg_pcs_inband_caps(struct phylink_pcs *pcs,
+					      phy_interface_t interface)
+{
+	return LINK_INBAND_DISABLE;
+}
+
 static void mvpp2_xlg_pcs_get_state(struct phylink_pcs *pcs,
+				    unsigned int neg_mode,
 				    struct phylink_link_state *state)
 {
 	struct mvpp2_port *port = mvpp2_pcs_xlg_to_port(pcs);
@@ -6220,6 +6269,7 @@ static int mvpp2_xlg_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode,
 }
 
 static const struct phylink_pcs_ops mvpp2_phylink_xlg_pcs_ops = {
+	.pcs_inband_caps = mvpp2_xjg_pcs_inband_caps,
 	.pcs_get_state = mvpp2_xlg_pcs_get_state,
 	.pcs_config = mvpp2_xlg_pcs_config,
 };
@@ -6247,6 +6297,7 @@ static unsigned int mvpp2_gmac_pcs_inband_caps(struct phylink_pcs *pcs,
 }
 
 static void mvpp2_gmac_pcs_get_state(struct phylink_pcs *pcs,
+				     unsigned int neg_mode,
 				     struct phylink_link_state *state)
 {
 	struct mvpp2_port *port = mvpp2_pcs_gmac_to_port(pcs);
@@ -6672,6 +6723,55 @@ static void mvpp2_mac_link_down(struct phylink_config *config,
 	mvpp2_port_disable(port);
 }
 
+static void mvpp2_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct mvpp2_port *port = mvpp2_phylink_to_port(config);
+
+	mvpp2_modify(port->base + MVPP2_GMAC_LPI_CTRL1,
+		     MVPP2_GMAC_LPI_CTRL1_REQ_EN, 0);
+}
+
+static int mvpp2_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
+				   bool tx_clk_stop)
+{
+	struct mvpp2_port *port = mvpp2_phylink_to_port(config);
+	u32 ts, tw, lpi1, status;
+
+	status = readl(port->base + MVPP2_GMAC_STATUS0);
+	if (status & MVPP2_GMAC_STATUS0_GMII_SPEED) {
+		/* At 1G speeds, the timer resolution are 1us, and
+		 * 802.3 says tw is 16.5us. Round up to 17us.
+		 */
+		tw = 17;
+		ts = timer;
+	} else {
+		/* At 100M speeds, the timer resolutions are 10us, and
+		 * 802.3 says tw is 30us.
+		 */
+		tw = 3;
+		ts = DIV_ROUND_UP(timer, 10);
+	}
+
+	if (ts > 255)
+		ts = 255;
+
+	/* Configure ts */
+	mvpp2_modify(port->base + MVPP2_GMAC_LPI_CTRL0,
+		     MVPP2_GMAC_LPI_CTRL0_TS_MASK,
+		     FIELD_PREP(MVPP2_GMAC_LPI_CTRL0_TS_MASK, ts));
+
+	lpi1 = readl(port->base + MVPP2_GMAC_LPI_CTRL1);
+
+	/* Configure tw */
+	lpi1 = u32_replace_bits(lpi1, tw, MVPP2_GMAC_LPI_CTRL1_TW_MASK);
+
+	/* Enable LPI generation */
+	writel(lpi1 | MVPP2_GMAC_LPI_CTRL1_REQ_EN,
+	       port->base + MVPP2_GMAC_LPI_CTRL1);
+
+	return 0;
+}
+
 static const struct phylink_mac_ops mvpp2_phylink_ops = {
 	.mac_select_pcs = mvpp2_select_pcs,
 	.mac_prepare = mvpp2_mac_prepare,
@@ -6679,6 +6779,8 @@ static const struct phylink_mac_ops mvpp2_phylink_ops = {
 	.mac_finish = mvpp2_mac_finish,
 	.mac_link_up = mvpp2_mac_link_up,
 	.mac_link_down = mvpp2_mac_link_down,
+	.mac_enable_tx_lpi = mvpp2_mac_enable_tx_lpi,
+	.mac_disable_tx_lpi = mvpp2_mac_disable_tx_lpi,
 };
 
 /* Work-around for ACPI */
@@ -6908,9 +7010,8 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 		for (thread = 0; thread < priv->nthreads; thread++) {
 			port_pcpu = per_cpu_ptr(port->pcpu, thread);
 
-			hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC,
-				     HRTIMER_MODE_REL_PINNED_SOFT);
-			port_pcpu->tx_done_timer.function = mvpp2_hr_timer_cb;
+			hrtimer_setup(&port_pcpu->tx_done_timer, mvpp2_hr_timer_cb, CLOCK_MONOTONIC,
+				      HRTIMER_MODE_REL_PINNED_SOFT);
 			port_pcpu->timer_scheduled = false;
 			port_pcpu->dev = dev;
 		}
@@ -6947,9 +7048,7 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	dev->dev_port = port->id;
 
 	port->pcs_gmac.ops = &mvpp2_phylink_gmac_pcs_ops;
-	port->pcs_gmac.neg_mode = true;
 	port->pcs_xlg.ops = &mvpp2_phylink_xlg_pcs_ops;
-	port->pcs_xlg.neg_mode = true;
 
 	if (!mvpp2_use_acpi_compat_mode(port_fwnode)) {
 		port->phylink_config.dev = &dev->dev;
@@ -6957,6 +7056,15 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 		port->phylink_config.mac_capabilities =
 			MAC_2500FD | MAC_1000FD | MAC_100 | MAC_10;
 
+		__set_bit(PHY_INTERFACE_MODE_SGMII,
+			  port->phylink_config.lpi_interfaces);
+
+		port->phylink_config.lpi_capabilities = MAC_1000FD | MAC_100FD;
+
+		/* Setup EEE.  Choose 250us idle. */
+		port->phylink_config.lpi_timer_default = 250;
+		port->phylink_config.eee_enabled_default = true;
+
 		if (port->priv->global_tx_fc)
 			port->phylink_config.mac_capabilities |=
 				MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
@@ -7031,6 +7139,8 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 			goto err_free_port_pcpu;
 		}
 		port->phylink = phylink;
+
+		mvpp2_mac_disable_tx_lpi(&port->phylink_config);
 	} else {
 		dev_warn(&pdev->dev, "Use link irqs for port#%d. FW update required\n", port->id);
 		port->phylink = NULL;
@@ -7634,8 +7744,9 @@ static int mvpp2_probe(struct platform_device *pdev)
 	if (mvpp2_read(priv, MVPP2_VER_ID_REG) == MVPP2_VER_PP23)
 		priv->hw_version = MVPP23;
 
-	/* Init mss lock */
+	/* Init locks for shared packet processor resources */
 	spin_lock_init(&priv->mss_spinlock);
+	spin_lock_init(&priv->prs_spinlock);
 
 	/* Initialize network controller */
 	err = mvpp2_init(pdev, priv);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index 9af22f497a40..93e978bdf303 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -23,6 +23,8 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe)
 {
 	int i;
 
+	lockdep_assert_held(&priv->prs_spinlock);
+
 	if (pe->index > MVPP2_PRS_TCAM_SRAM_SIZE - 1)
 		return -EINVAL;
 
@@ -43,11 +45,13 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe)
 }
 
 /* Initialize tcam entry from hw */
-int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
-			   int tid)
+static int __mvpp2_prs_init_from_hw(struct mvpp2 *priv,
+				    struct mvpp2_prs_entry *pe, int tid)
 {
 	int i;
 
+	lockdep_assert_held(&priv->prs_spinlock);
+
 	if (tid > MVPP2_PRS_TCAM_SRAM_SIZE - 1)
 		return -EINVAL;
 
@@ -73,6 +77,18 @@ int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
 	return 0;
 }
 
+int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
+			   int tid)
+{
+	int err;
+
+	spin_lock_bh(&priv->prs_spinlock);
+	err = __mvpp2_prs_init_from_hw(priv, pe, tid);
+	spin_unlock_bh(&priv->prs_spinlock);
+
+	return err;
+}
+
 /* Invalidate tcam hw entry */
 static void mvpp2_prs_hw_inv(struct mvpp2 *priv, int index)
 {
@@ -374,7 +390,7 @@ static int mvpp2_prs_flow_find(struct mvpp2 *priv, int flow)
 		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_FLOWS)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 		bits = mvpp2_prs_sram_ai_get(&pe);
 
 		/* Sram store classification lookup ID in AI bits [5:0] */
@@ -441,7 +457,7 @@ static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add)
 
 	if (priv->prs_shadow[MVPP2_PE_DROP_ALL].valid) {
 		/* Entry exist - update port only */
-		mvpp2_prs_init_from_hw(priv, &pe, MVPP2_PE_DROP_ALL);
+		__mvpp2_prs_init_from_hw(priv, &pe, MVPP2_PE_DROP_ALL);
 	} else {
 		/* Entry doesn't exist - create new */
 		memset(&pe, 0, sizeof(pe));
@@ -469,14 +485,17 @@ static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add)
 }
 
 /* Set port to unicast or multicast promiscuous mode */
-void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
-			       enum mvpp2_prs_l2_cast l2_cast, bool add)
+static void __mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
+					enum mvpp2_prs_l2_cast l2_cast,
+					bool add)
 {
 	struct mvpp2_prs_entry pe;
 	unsigned char cast_match;
 	unsigned int ri;
 	int tid;
 
+	lockdep_assert_held(&priv->prs_spinlock);
+
 	if (l2_cast == MVPP2_PRS_L2_UNI_CAST) {
 		cast_match = MVPP2_PRS_UCAST_VAL;
 		tid = MVPP2_PE_MAC_UC_PROMISCUOUS;
@@ -489,7 +508,7 @@ void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
 
 	/* promiscuous mode - Accept unknown unicast or multicast packets */
 	if (priv->prs_shadow[tid].valid) {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	} else {
 		memset(&pe, 0, sizeof(pe));
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC);
@@ -522,6 +541,14 @@ void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
 	mvpp2_prs_hw_write(priv, &pe);
 }
 
+void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
+			       enum mvpp2_prs_l2_cast l2_cast, bool add)
+{
+	spin_lock_bh(&priv->prs_spinlock);
+	__mvpp2_prs_mac_promisc_set(priv, port, l2_cast, add);
+	spin_unlock_bh(&priv->prs_spinlock);
+}
+
 /* Set entry for dsa packets */
 static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add,
 				  bool tagged, bool extend)
@@ -539,7 +566,7 @@ static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add,
 
 	if (priv->prs_shadow[tid].valid) {
 		/* Entry exist - update port only */
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	} else {
 		/* Entry doesn't exist - create new */
 		memset(&pe, 0, sizeof(pe));
@@ -610,7 +637,7 @@ static void mvpp2_prs_dsa_tag_ethertype_set(struct mvpp2 *priv, int port,
 
 	if (priv->prs_shadow[tid].valid) {
 		/* Entry exist - update port only */
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	} else {
 		/* Entry doesn't exist - create new */
 		memset(&pe, 0, sizeof(pe));
@@ -673,7 +700,7 @@ static int mvpp2_prs_vlan_find(struct mvpp2 *priv, unsigned short tpid, int ai)
 		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VLAN)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 		match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid);
 		if (!match)
 			continue;
@@ -726,7 +753,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai,
 			    priv->prs_shadow[tid_aux].lu != MVPP2_PRS_LU_VLAN)
 				continue;
 
-			mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
+			__mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
 			ri_bits = mvpp2_prs_sram_ri_get(&pe);
 			if ((ri_bits & MVPP2_PRS_RI_VLAN_MASK) ==
 			    MVPP2_PRS_RI_VLAN_DOUBLE)
@@ -760,7 +787,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai,
 
 		mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VLAN);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	}
 	/* Update ports' mask */
 	mvpp2_prs_tcam_port_map_set(&pe, port_map);
@@ -800,7 +827,7 @@ static int mvpp2_prs_double_vlan_find(struct mvpp2 *priv, unsigned short tpid1,
 		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VLAN)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 
 		match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid1) &&
 			mvpp2_prs_tcam_data_cmp(&pe, 4, tpid2);
@@ -849,7 +876,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1,
 			    priv->prs_shadow[tid_aux].lu != MVPP2_PRS_LU_VLAN)
 				continue;
 
-			mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
+			__mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
 			ri_bits = mvpp2_prs_sram_ri_get(&pe);
 			ri_bits &= MVPP2_PRS_RI_VLAN_MASK;
 			if (ri_bits == MVPP2_PRS_RI_VLAN_SINGLE ||
@@ -880,7 +907,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1,
 
 		mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VLAN);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	}
 
 	/* Update ports' mask */
@@ -1213,8 +1240,8 @@ static void mvpp2_prs_mac_init(struct mvpp2 *priv)
 	/* Create dummy entries for drop all and promiscuous modes */
 	mvpp2_prs_drop_fc(priv);
 	mvpp2_prs_mac_drop_all_set(priv, 0, false);
-	mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_UNI_CAST, false);
-	mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_MULTI_CAST, false);
+	__mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_UNI_CAST, false);
+	__mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_MULTI_CAST, false);
 }
 
 /* Set default entries for various types of dsa packets */
@@ -1533,12 +1560,6 @@ static int mvpp2_prs_vlan_init(struct platform_device *pdev, struct mvpp2 *priv)
 	struct mvpp2_prs_entry pe;
 	int err;
 
-	priv->prs_double_vlans = devm_kcalloc(&pdev->dev, sizeof(bool),
-					      MVPP2_PRS_DBL_VLANS_MAX,
-					      GFP_KERNEL);
-	if (!priv->prs_double_vlans)
-		return -ENOMEM;
-
 	/* Double VLAN: 0x88A8, 0x8100 */
 	err = mvpp2_prs_double_vlan_add(priv, ETH_P_8021AD, ETH_P_8021Q,
 					MVPP2_PRS_PORT_MASK);
@@ -1941,7 +1962,7 @@ static int mvpp2_prs_vid_range_find(struct mvpp2_port *port, u16 vid, u16 mask)
 		    port->priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VID)
 			continue;
 
-		mvpp2_prs_init_from_hw(port->priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(port->priv, &pe, tid);
 
 		mvpp2_prs_tcam_data_byte_get(&pe, 2, &byte[0], &enable[0]);
 		mvpp2_prs_tcam_data_byte_get(&pe, 3, &byte[1], &enable[1]);
@@ -1970,6 +1991,8 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	/* Scan TCAM and see if entry with this <vid,port> already exist */
 	tid = mvpp2_prs_vid_range_find(port, vid, mask);
 
@@ -1988,8 +2011,10 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 						MVPP2_PRS_VLAN_FILT_MAX_ENTRY);
 
 		/* There isn't room for a new VID filter */
-		if (tid < 0)
+		if (tid < 0) {
+			spin_unlock_bh(&priv->prs_spinlock);
 			return tid;
+		}
 
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VID);
 		pe.index = tid;
@@ -1997,7 +2022,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 		/* Mask all ports */
 		mvpp2_prs_tcam_port_map_set(&pe, 0);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	}
 
 	/* Enable the current port */
@@ -2019,6 +2044,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID);
 	mvpp2_prs_hw_write(priv, &pe);
 
+	spin_unlock_bh(&priv->prs_spinlock);
 	return 0;
 }
 
@@ -2028,15 +2054,16 @@ void mvpp2_prs_vid_entry_remove(struct mvpp2_port *port, u16 vid)
 	struct mvpp2 *priv = port->priv;
 	int tid;
 
-	/* Scan TCAM and see if entry with this <vid,port> already exist */
-	tid = mvpp2_prs_vid_range_find(port, vid, 0xfff);
+	spin_lock_bh(&priv->prs_spinlock);
 
-	/* No such entry */
-	if (tid < 0)
-		return;
+	/* Invalidate TCAM entry with this <vid,port>, if it exists */
+	tid = mvpp2_prs_vid_range_find(port, vid, 0xfff);
+	if (tid >= 0) {
+		mvpp2_prs_hw_inv(priv, tid);
+		priv->prs_shadow[tid].valid = false;
+	}
 
-	mvpp2_prs_hw_inv(priv, tid);
-	priv->prs_shadow[tid].valid = false;
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Remove all existing VID filters on this port */
@@ -2045,6 +2072,8 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port)
 	struct mvpp2 *priv = port->priv;
 	int tid;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id);
 	     tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) {
 		if (priv->prs_shadow[tid].valid) {
@@ -2052,6 +2081,8 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port)
 			priv->prs_shadow[tid].valid = false;
 		}
 	}
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Remove VID filering entry for this port */
@@ -2060,10 +2091,14 @@ void mvpp2_prs_vid_disable_filtering(struct mvpp2_port *port)
 	unsigned int tid = MVPP2_PRS_VID_PORT_DFLT(port->id);
 	struct mvpp2 *priv = port->priv;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	/* Invalidate the guard entry */
 	mvpp2_prs_hw_inv(priv, tid);
 
 	priv->prs_shadow[tid].valid = false;
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Add guard entry that drops packets when no VID is matched on this port */
@@ -2079,6 +2114,8 @@ void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	pe.index = tid;
 
 	reg_val = mvpp2_read(priv, MVPP2_MH_REG(port->id));
@@ -2111,6 +2148,8 @@ void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port)
 	/* Update shadow table */
 	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID);
 	mvpp2_prs_hw_write(priv, &pe);
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Parser default initialization */
@@ -2118,6 +2157,20 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv)
 {
 	int err, index, i;
 
+	priv->prs_shadow = devm_kcalloc(&pdev->dev, MVPP2_PRS_TCAM_SRAM_SIZE,
+					sizeof(*priv->prs_shadow),
+					GFP_KERNEL);
+	if (!priv->prs_shadow)
+		return -ENOMEM;
+
+	priv->prs_double_vlans = devm_kcalloc(&pdev->dev, sizeof(bool),
+					      MVPP2_PRS_DBL_VLANS_MAX,
+					      GFP_KERNEL);
+	if (!priv->prs_double_vlans)
+		return -ENOMEM;
+
+	spin_lock_bh(&priv->prs_spinlock);
+
 	/* Enable tcam table */
 	mvpp2_write(priv, MVPP2_PRS_TCAM_CTRL_REG, MVPP2_PRS_TCAM_EN_MASK);
 
@@ -2136,12 +2189,6 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv)
 	for (index = 0; index < MVPP2_PRS_TCAM_SRAM_SIZE; index++)
 		mvpp2_prs_hw_inv(priv, index);
 
-	priv->prs_shadow = devm_kcalloc(&pdev->dev, MVPP2_PRS_TCAM_SRAM_SIZE,
-					sizeof(*priv->prs_shadow),
-					GFP_KERNEL);
-	if (!priv->prs_shadow)
-		return -ENOMEM;
-
 	/* Always start from lookup = 0 */
 	for (index = 0; index < MVPP2_MAX_PORTS; index++)
 		mvpp2_prs_hw_port_init(priv, index, MVPP2_PRS_LU_MH,
@@ -2158,26 +2205,13 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv)
 	mvpp2_prs_vid_init(priv);
 
 	err = mvpp2_prs_etype_init(priv);
-	if (err)
-		return err;
-
-	err = mvpp2_prs_vlan_init(pdev, priv);
-	if (err)
-		return err;
-
-	err = mvpp2_prs_pppoe_init(priv);
-	if (err)
-		return err;
-
-	err = mvpp2_prs_ip6_init(priv);
-	if (err)
-		return err;
-
-	err = mvpp2_prs_ip4_init(priv);
-	if (err)
-		return err;
+	err = err ? : mvpp2_prs_vlan_init(pdev, priv);
+	err = err ? : mvpp2_prs_pppoe_init(priv);
+	err = err ? : mvpp2_prs_ip6_init(priv);
+	err = err ? : mvpp2_prs_ip4_init(priv);
 
-	return 0;
+	spin_unlock_bh(&priv->prs_spinlock);
+	return err;
 }
 
 /* Compare MAC DA with tcam entry data */
@@ -2217,7 +2251,7 @@ mvpp2_prs_mac_da_range_find(struct mvpp2 *priv, int pmap, const u8 *da,
 		    (priv->prs_shadow[tid].udf != udf_type))
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 		entry_pmap = mvpp2_prs_tcam_port_map_get(&pe);
 
 		if (mvpp2_prs_mac_range_equals(&pe, da, mask) &&
@@ -2229,7 +2263,8 @@ mvpp2_prs_mac_da_range_find(struct mvpp2 *priv, int pmap, const u8 *da,
 }
 
 /* Update parser's mac da entry */
-int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
+static int __mvpp2_prs_mac_da_accept(struct mvpp2_port *port,
+				     const u8 *da, bool add)
 {
 	unsigned char mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
 	struct mvpp2 *priv = port->priv;
@@ -2261,7 +2296,7 @@ int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
 		/* Mask all ports */
 		mvpp2_prs_tcam_port_map_set(&pe, 0);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	}
 
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC);
@@ -2317,6 +2352,17 @@ int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
 	return 0;
 }
 
+int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
+{
+	int err;
+
+	spin_lock_bh(&port->priv->prs_spinlock);
+	err = __mvpp2_prs_mac_da_accept(port, da, add);
+	spin_unlock_bh(&port->priv->prs_spinlock);
+
+	return err;
+}
+
 int mvpp2_prs_update_mac_da(struct net_device *dev, const u8 *da)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
@@ -2345,6 +2391,8 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port)
 	unsigned long pmap;
 	int index, tid;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	for (tid = MVPP2_PE_MAC_RANGE_START;
 	     tid <= MVPP2_PE_MAC_RANGE_END; tid++) {
 		unsigned char da[ETH_ALEN], da_mask[ETH_ALEN];
@@ -2354,7 +2402,7 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port)
 		    (priv->prs_shadow[tid].udf != MVPP2_PRS_UDF_MAC_DEF))
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 
 		pmap = mvpp2_prs_tcam_port_map_get(&pe);
 
@@ -2375,14 +2423,17 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port)
 			continue;
 
 		/* Remove entry from TCAM */
-		mvpp2_prs_mac_da_accept(port, da, false);
+		__mvpp2_prs_mac_da_accept(port, da, false);
 	}
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 {
 	switch (type) {
 	case MVPP2_TAG_TYPE_EDSA:
+		spin_lock_bh(&priv->prs_spinlock);
 		/* Add port to EDSA entries */
 		mvpp2_prs_dsa_tag_set(priv, port, true,
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA);
@@ -2393,9 +2444,11 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_DSA);
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_UNTAGGED, MVPP2_PRS_DSA);
+		spin_unlock_bh(&priv->prs_spinlock);
 		break;
 
 	case MVPP2_TAG_TYPE_DSA:
+		spin_lock_bh(&priv->prs_spinlock);
 		/* Add port to DSA entries */
 		mvpp2_prs_dsa_tag_set(priv, port, true,
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_DSA);
@@ -2406,10 +2459,12 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA);
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_UNTAGGED, MVPP2_PRS_EDSA);
+		spin_unlock_bh(&priv->prs_spinlock);
 		break;
 
 	case MVPP2_TAG_TYPE_MH:
 	case MVPP2_TAG_TYPE_NONE:
+		spin_lock_bh(&priv->prs_spinlock);
 		/* Remove port form EDSA and DSA entries */
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_DSA);
@@ -2419,6 +2474,7 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA);
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_UNTAGGED, MVPP2_PRS_EDSA);
+		spin_unlock_bh(&priv->prs_spinlock);
 		break;
 
 	default:
@@ -2437,11 +2493,15 @@ int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	tid = mvpp2_prs_tcam_first_free(priv,
 					MVPP2_PE_LAST_FREE_TID,
 					MVPP2_PE_FIRST_FREE_TID);
-	if (tid < 0)
+	if (tid < 0) {
+		spin_unlock_bh(&priv->prs_spinlock);
 		return tid;
+	}
 
 	pe.index = tid;
 
@@ -2461,6 +2521,7 @@ int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask)
 	mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK);
 	mvpp2_prs_hw_write(priv, &pe);
 
+	spin_unlock_bh(&priv->prs_spinlock);
 	return 0;
 }
 
@@ -2472,6 +2533,8 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&port->priv->prs_spinlock);
+
 	tid = mvpp2_prs_flow_find(port->priv, port->id);
 
 	/* Such entry not exist */
@@ -2480,8 +2543,10 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 		tid = mvpp2_prs_tcam_first_free(port->priv,
 						MVPP2_PE_LAST_FREE_TID,
 					       MVPP2_PE_FIRST_FREE_TID);
-		if (tid < 0)
+		if (tid < 0) {
+			spin_unlock_bh(&port->priv->prs_spinlock);
 			return tid;
+		}
 
 		pe.index = tid;
 
@@ -2492,13 +2557,14 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 		/* Update shadow table */
 		mvpp2_prs_shadow_set(port->priv, pe.index, MVPP2_PRS_LU_FLOWS);
 	} else {
-		mvpp2_prs_init_from_hw(port->priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(port->priv, &pe, tid);
 	}
 
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
 	mvpp2_prs_tcam_port_map_set(&pe, (1 << port->id));
 	mvpp2_prs_hw_write(port->priv, &pe);
 
+	spin_unlock_bh(&port->priv->prs_spinlock);
 	return 0;
 }
 
@@ -2509,11 +2575,14 @@ int mvpp2_prs_hits(struct mvpp2 *priv, int index)
 	if (index > MVPP2_PRS_TCAM_SRAM_SIZE)
 		return -EINVAL;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	mvpp2_write(priv, MVPP2_PRS_TCAM_HIT_IDX_REG, index);
 
 	val = mvpp2_read(priv, MVPP2_PRS_TCAM_HIT_CNT_REG);
 
 	val &= MVPP2_PRS_TCAM_HIT_CNT_MASK;
 
+	spin_unlock_bh(&priv->prs_spinlock);
 	return val;
 }
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c b/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c
index 4f4d58189118..01c6c0a2f283 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c
@@ -150,17 +150,14 @@ octep_get_ethtool_stats(struct net_device *netdev,
 				    iface_rx_stats,
 				    iface_tx_stats);
 
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_iq *iq = oct->iq[q];
-		struct octep_oq *oq = oct->oq[q];
-
-		tx_packets += iq->stats.instr_completed;
-		tx_bytes += iq->stats.bytes_sent;
-		tx_busy_errors += iq->stats.tx_busy;
-
-		rx_packets += oq->stats.packets;
-		rx_bytes += oq->stats.bytes;
-		rx_alloc_errors += oq->stats.alloc_failures;
+	for (q = 0; q < OCTEP_MAX_QUEUES; q++) {
+		tx_packets += oct->stats_iq[q].instr_completed;
+		tx_bytes += oct->stats_iq[q].bytes_sent;
+		tx_busy_errors += oct->stats_iq[q].tx_busy;
+
+		rx_packets += oct->stats_oq[q].packets;
+		rx_bytes += oct->stats_oq[q].bytes;
+		rx_alloc_errors += oct->stats_oq[q].alloc_failures;
 	}
 	i = 0;
 	data[i++] = rx_packets;
@@ -198,22 +195,18 @@ octep_get_ethtool_stats(struct net_device *netdev,
 	data[i++] = iface_rx_stats->err_pkts;
 
 	/* Per Tx Queue stats */
-	for (q = 0; q < oct->num_iqs; q++) {
-		struct octep_iq *iq = oct->iq[q];
-
-		data[i++] = iq->stats.instr_posted;
-		data[i++] = iq->stats.instr_completed;
-		data[i++] = iq->stats.bytes_sent;
-		data[i++] = iq->stats.tx_busy;
+	for (q = 0; q < OCTEP_MAX_QUEUES; q++) {
+		data[i++] = oct->stats_iq[q].instr_posted;
+		data[i++] = oct->stats_iq[q].instr_completed;
+		data[i++] = oct->stats_iq[q].bytes_sent;
+		data[i++] = oct->stats_iq[q].tx_busy;
 	}
 
 	/* Per Rx Queue stats */
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_oq *oq = oct->oq[q];
-
-		data[i++] = oq->stats.packets;
-		data[i++] = oq->stats.bytes;
-		data[i++] = oq->stats.alloc_failures;
+	for (q = 0; q < OCTEP_MAX_QUEUES; q++) {
+		data[i++] = oct->stats_oq[q].packets;
+		data[i++] = oct->stats_oq[q].bytes;
+		data[i++] = oct->stats_oq[q].alloc_failures;
 	}
 }
 
@@ -444,6 +437,15 @@ static int octep_set_link_ksettings(struct net_device *netdev,
 	return 0;
 }
 
+static void octep_get_channels(struct net_device *dev,
+			       struct ethtool_channels *channel)
+{
+	struct octep_device *oct = netdev_priv(dev);
+
+	channel->max_combined = CFG_GET_PORTS_MAX_IO_RINGS(oct->conf);
+	channel->combined_count = CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf);
+}
+
 static const struct ethtool_ops octep_ethtool_ops = {
 	.get_drvinfo = octep_get_drvinfo,
 	.get_link = ethtool_op_get_link,
@@ -452,6 +454,7 @@ static const struct ethtool_ops octep_ethtool_ops = {
 	.get_ethtool_stats = octep_get_ethtool_stats,
 	.get_link_ksettings = octep_get_link_ksettings,
 	.set_link_ksettings = octep_set_link_ksettings,
+	.get_channels = octep_get_channels,
 };
 
 void octep_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index 3a9825883d79..bcea3fc26a8c 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -822,7 +822,7 @@ static inline int octep_iq_full_check(struct octep_iq *iq)
 	if (unlikely(IQ_INSTR_SPACE(iq) >
 		     OCTEP_WAKE_QUEUE_THRESHOLD)) {
 		netif_start_subqueue(iq->netdev, iq->q_no);
-		iq->stats.restart_cnt++;
+		iq->stats->restart_cnt++;
 		return 0;
 	}
 
@@ -960,7 +960,7 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 	wmb();
 	/* Ring Doorbell to notify the NIC of new packets */
 	writel(iq->fill_cnt, iq->doorbell_reg);
-	iq->stats.instr_posted += iq->fill_cnt;
+	iq->stats->instr_posted += iq->fill_cnt;
 	iq->fill_cnt = 0;
 	return NETDEV_TX_OK;
 
@@ -991,37 +991,24 @@ dma_map_err:
 static void octep_get_stats64(struct net_device *netdev,
 			      struct rtnl_link_stats64 *stats)
 {
-	u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
 	struct octep_device *oct = netdev_priv(netdev);
+	u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
 	int q;
 
-	if (netif_running(netdev))
-		octep_ctrl_net_get_if_stats(oct,
-					    OCTEP_CTRL_NET_INVALID_VFID,
-					    &oct->iface_rx_stats,
-					    &oct->iface_tx_stats);
-
 	tx_packets = 0;
 	tx_bytes = 0;
 	rx_packets = 0;
 	rx_bytes = 0;
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_iq *iq = oct->iq[q];
-		struct octep_oq *oq = oct->oq[q];
-
-		tx_packets += iq->stats.instr_completed;
-		tx_bytes += iq->stats.bytes_sent;
-		rx_packets += oq->stats.packets;
-		rx_bytes += oq->stats.bytes;
+	for (q = 0; q < OCTEP_MAX_QUEUES; q++) {
+		tx_packets += oct->stats_iq[q].instr_completed;
+		tx_bytes += oct->stats_iq[q].bytes_sent;
+		rx_packets += oct->stats_oq[q].packets;
+		rx_bytes += oct->stats_oq[q].bytes;
 	}
 	stats->tx_packets = tx_packets;
 	stats->tx_bytes = tx_bytes;
 	stats->rx_packets = rx_packets;
 	stats->rx_bytes = rx_bytes;
-	stats->multicast = oct->iface_rx_stats.mcast_pkts;
-	stats->rx_errors = oct->iface_rx_stats.err_pkts;
-	stats->collisions = oct->iface_tx_stats.xscol;
-	stats->tx_fifo_errors = oct->iface_tx_stats.undflw;
 }
 
 /**
@@ -1137,11 +1124,24 @@ static int octep_set_features(struct net_device *dev, netdev_features_t features
 	return err;
 }
 
+static bool octep_is_vf_valid(struct octep_device *oct, int vf)
+{
+	if (vf >= CFG_GET_ACTIVE_VFS(oct->conf)) {
+		netdev_err(oct->netdev, "Invalid VF ID %d\n", vf);
+		return false;
+	}
+
+	return true;
+}
+
 static int octep_get_vf_config(struct net_device *dev, int vf,
 			       struct ifla_vf_info *ivi)
 {
 	struct octep_device *oct = netdev_priv(dev);
 
+	if (!octep_is_vf_valid(oct, vf))
+		return -EINVAL;
+
 	ivi->vf = vf;
 	ether_addr_copy(ivi->mac, oct->vf_info[vf].mac_addr);
 	ivi->spoofchk = true;
@@ -1156,6 +1156,9 @@ static int octep_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
 	struct octep_device *oct = netdev_priv(dev);
 	int err;
 
+	if (!octep_is_vf_valid(oct, vf))
+		return -EINVAL;
+
 	if (!is_valid_ether_addr(mac)) {
 		dev_err(&oct->pdev->dev, "Invalid  MAC Address %pM\n", mac);
 		return -EADDRNOTAVAIL;
@@ -1236,7 +1239,7 @@ static void octep_hb_timeout_task(struct work_struct *work)
 		miss_cnt);
 	rtnl_lock();
 	if (netif_running(oct->netdev))
-		octep_stop(oct->netdev);
+		dev_close(oct->netdev);
 	rtnl_unlock();
 }
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h
index 3b56916af468..81ac4267811c 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h
@@ -258,11 +258,17 @@ struct octep_device {
 	/* Pointers to Octeon Tx queues */
 	struct octep_iq *iq[OCTEP_MAX_IQ];
 
+	/* Per iq stats */
+	struct octep_iq_stats stats_iq[OCTEP_MAX_IQ];
+
 	/* Rx queues (OQ: Output Queue) */
 	u16 num_oqs;
 	/* Pointers to Octeon Rx queues */
 	struct octep_oq *oq[OCTEP_MAX_OQ];
 
+	/* Per oq stats */
+	struct octep_oq_stats stats_oq[OCTEP_MAX_OQ];
+
 	/* Hardware port number of the PCIe interface */
 	u16 pcie_port;
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c
index ebecdd29f3bd..0867fab61b19 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c
@@ -196,6 +196,7 @@ static void octep_pfvf_get_mac_addr(struct octep_device *oct,  u32 vf_id,
 			vf_id);
 		return;
 	}
+	ether_addr_copy(oct->vf_info[vf_id].mac_addr, rsp->s_set_mac.mac_addr);
 	rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
 }
 
@@ -205,6 +206,8 @@ static void octep_pfvf_dev_remove(struct octep_device *oct,  u32 vf_id,
 {
 	int err;
 
+	/* Reset VF-specific information maintained by the PF */
+	memset(&oct->vf_info[vf_id], 0, sizeof(struct octep_pfvf_info));
 	err = octep_ctrl_net_dev_remove(oct, vf_id);
 	if (err) {
 		rsp->s.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
index 8af75cb37c3e..82b6b19e76b4 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
@@ -87,7 +87,7 @@ static int octep_oq_refill(struct octep_device *oct, struct octep_oq *oq)
 		page = dev_alloc_page();
 		if (unlikely(!page)) {
 			dev_err(oq->dev, "refill: rx buffer alloc failed\n");
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			break;
 		}
 
@@ -98,7 +98,7 @@ static int octep_oq_refill(struct octep_device *oct, struct octep_oq *oq)
 				"OQ-%d buffer refill: DMA mapping error!\n",
 				oq->q_no);
 			put_page(page);
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			break;
 		}
 		oq->buff_info[refill_idx].page = page;
@@ -134,6 +134,7 @@ static int octep_setup_oq(struct octep_device *oct, int q_no)
 	oq->netdev = oct->netdev;
 	oq->dev = &oct->pdev->dev;
 	oq->q_no = q_no;
+	oq->stats = &oct->stats_oq[q_no];
 	oq->max_count = CFG_GET_OQ_NUM_DESC(oct->conf);
 	oq->ring_size_mask = oq->max_count - 1;
 	oq->buffer_size = CFG_GET_OQ_BUF_SIZE(oct->conf);
@@ -443,7 +444,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 		if (!skb) {
 			octep_oq_drop_rx(oq, buff_info,
 					 &read_idx, &desc_used);
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			continue;
 		}
 		skb_reserve(skb, data_offset);
@@ -494,8 +495,8 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 
 	oq->host_read_idx = read_idx;
 	oq->refill_count += desc_used;
-	oq->stats.packets += pkt;
-	oq->stats.bytes += rx_bytes;
+	oq->stats->packets += pkt;
+	oq->stats->bytes += rx_bytes;
 
 	return pkt;
 }
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h
index 3b08e2d560dc..b4696c93d0e6 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h
@@ -186,8 +186,8 @@ struct octep_oq {
 	 */
 	u8 __iomem *pkts_sent_reg;
 
-	/* Statistics for this OQ. */
-	struct octep_oq_stats stats;
+	/* Pointer to statistics for this OQ. */
+	struct octep_oq_stats *stats;
 
 	/* Packets pending to be processed */
 	u32 pkts_pending;
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c
index 06851b78aa28..08ee90013fef 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c
@@ -81,9 +81,9 @@ int octep_iq_process_completions(struct octep_iq *iq, u16 budget)
 	}
 
 	iq->pkts_processed += compl_pkts;
-	iq->stats.instr_completed += compl_pkts;
-	iq->stats.bytes_sent += compl_bytes;
-	iq->stats.sgentry_sent += compl_sg;
+	iq->stats->instr_completed += compl_pkts;
+	iq->stats->bytes_sent += compl_bytes;
+	iq->stats->sgentry_sent += compl_sg;
 	iq->flush_index = fi;
 
 	netdev_tx_completed_queue(iq->netdev_q, compl_pkts, compl_bytes);
@@ -187,6 +187,7 @@ static int octep_setup_iq(struct octep_device *oct, int q_no)
 	iq->netdev = oct->netdev;
 	iq->dev = &oct->pdev->dev;
 	iq->q_no = q_no;
+	iq->stats = &oct->stats_iq[q_no];
 	iq->max_count = CFG_GET_IQ_NUM_DESC(oct->conf);
 	iq->ring_size_mask = iq->max_count - 1;
 	iq->fill_threshold = CFG_GET_IQ_DB_MIN(oct->conf);
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h
index 875a2c34091f..58fb39dda977 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h
@@ -170,8 +170,8 @@ struct octep_iq {
 	 */
 	u16 flush_index;
 
-	/* Statistics for this input queue. */
-	struct octep_iq_stats stats;
+	/* Pointer to statistics for this input queue. */
+	struct octep_iq_stats *stats;
 
 	/* Pointer to the Virtual Base addr of the input ring. */
 	struct octep_tx_desc_hw *desc_ring;
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c
index 7b21439a315f..241a7e7c7ad2 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c
@@ -114,12 +114,9 @@ static void octep_vf_get_ethtool_stats(struct net_device *netdev,
 	iface_tx_stats = &oct->iface_tx_stats;
 	iface_rx_stats = &oct->iface_rx_stats;
 
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_vf_iq *iq = oct->iq[q];
-		struct octep_vf_oq *oq = oct->oq[q];
-
-		tx_busy_errors += iq->stats.tx_busy;
-		rx_alloc_errors += oq->stats.alloc_failures;
+	for (q = 0; q < OCTEP_VF_MAX_QUEUES; q++) {
+		tx_busy_errors += oct->stats_iq[q].tx_busy;
+		rx_alloc_errors += oct->stats_oq[q].alloc_failures;
 	}
 	i = 0;
 	data[i++] = rx_alloc_errors;
@@ -134,22 +131,18 @@ static void octep_vf_get_ethtool_stats(struct net_device *netdev,
 	data[i++] = iface_rx_stats->dropped_octets_fifo_full;
 
 	/* Per Tx Queue stats */
-	for (q = 0; q < oct->num_iqs; q++) {
-		struct octep_vf_iq *iq = oct->iq[q];
-
-		data[i++] = iq->stats.instr_posted;
-		data[i++] = iq->stats.instr_completed;
-		data[i++] = iq->stats.bytes_sent;
-		data[i++] = iq->stats.tx_busy;
+	for (q = 0; q < OCTEP_VF_MAX_QUEUES; q++) {
+		data[i++] = oct->stats_iq[q].instr_posted;
+		data[i++] = oct->stats_iq[q].instr_completed;
+		data[i++] = oct->stats_iq[q].bytes_sent;
+		data[i++] = oct->stats_iq[q].tx_busy;
 	}
 
 	/* Per Rx Queue stats */
 	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_vf_oq *oq = oct->oq[q];
-
-		data[i++] = oq->stats.packets;
-		data[i++] = oq->stats.bytes;
-		data[i++] = oq->stats.alloc_failures;
+		data[i++] = oct->stats_oq[q].packets;
+		data[i++] = oct->stats_oq[q].bytes;
+		data[i++] = oct->stats_oq[q].alloc_failures;
 	}
 }
 
@@ -251,6 +244,15 @@ static int octep_vf_get_link_ksettings(struct net_device *netdev,
 	return 0;
 }
 
+static void octep_vf_get_channels(struct net_device *dev,
+				  struct ethtool_channels *channel)
+{
+	struct octep_vf_device *oct = netdev_priv(dev);
+
+	channel->max_combined = CFG_GET_PORTS_MAX_IO_RINGS(oct->conf);
+	channel->combined_count = CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf);
+}
+
 static const struct ethtool_ops octep_vf_ethtool_ops = {
 	.get_drvinfo = octep_vf_get_drvinfo,
 	.get_link = ethtool_op_get_link,
@@ -258,6 +260,7 @@ static const struct ethtool_ops octep_vf_ethtool_ops = {
 	.get_sset_count = octep_vf_get_sset_count,
 	.get_ethtool_stats = octep_vf_get_ethtool_stats,
 	.get_link_ksettings = octep_vf_get_link_ksettings,
+	.get_channels = octep_vf_get_channels,
 };
 
 void octep_vf_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
index 7e6771c9cdbb..420c3f4cf741 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
@@ -18,8 +18,6 @@
 #include "octep_vf_config.h"
 #include "octep_vf_main.h"
 
-struct workqueue_struct *octep_vf_wq;
-
 /* Supported Devices */
 static const struct pci_device_id octep_vf_pci_id_tbl[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CN93_VF)},
@@ -574,7 +572,7 @@ static int octep_vf_iq_full_check(struct octep_vf_iq *iq)
 		  * caused queues to get re-enabled after
 		  * being stopped
 		  */
-		iq->stats.restart_cnt++;
+		iq->stats->restart_cnt++;
 		fallthrough;
 	case 1: /* Queue left enabled, since IQ is not yet full*/
 		return 0;
@@ -731,7 +729,7 @@ ring_dbell:
 	/* Flush the hw descriptors before writing to doorbell */
 	smp_wmb();
 	writel(iq->fill_cnt, iq->doorbell_reg);
-	iq->stats.instr_posted += iq->fill_cnt;
+	iq->stats->instr_posted += iq->fill_cnt;
 	iq->fill_cnt = 0;
 	return NETDEV_TX_OK;
 }
@@ -786,27 +784,16 @@ static void octep_vf_get_stats64(struct net_device *netdev,
 	tx_bytes = 0;
 	rx_packets = 0;
 	rx_bytes = 0;
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_vf_iq *iq = oct->iq[q];
-		struct octep_vf_oq *oq = oct->oq[q];
-
-		tx_packets += iq->stats.instr_completed;
-		tx_bytes += iq->stats.bytes_sent;
-		rx_packets += oq->stats.packets;
-		rx_bytes += oq->stats.bytes;
+	for (q = 0; q < OCTEP_VF_MAX_QUEUES; q++) {
+		tx_packets += oct->stats_iq[q].instr_completed;
+		tx_bytes += oct->stats_iq[q].bytes_sent;
+		rx_packets += oct->stats_oq[q].packets;
+		rx_bytes += oct->stats_oq[q].bytes;
 	}
 	stats->tx_packets = tx_packets;
 	stats->tx_bytes = tx_bytes;
 	stats->rx_packets = rx_packets;
 	stats->rx_bytes = rx_bytes;
-	if (!octep_vf_get_if_stats(oct)) {
-		stats->multicast = oct->iface_rx_stats.mcast_pkts;
-		stats->rx_errors = oct->iface_rx_stats.err_pkts;
-		stats->rx_dropped = oct->iface_rx_stats.dropped_pkts_fifo_full +
-				    oct->iface_rx_stats.err_pkts;
-		stats->rx_missed_errors = oct->iface_rx_stats.dropped_pkts_fifo_full;
-		stats->tx_dropped = oct->iface_tx_stats.dropped;
-	}
 }
 
 /**
@@ -846,7 +833,9 @@ static void octep_vf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	struct octep_vf_device *oct = netdev_priv(netdev);
 
 	netdev_hold(netdev, NULL, GFP_ATOMIC);
-	schedule_work(&oct->tx_timeout_task);
+	if (!schedule_work(&oct->tx_timeout_task))
+		netdev_put(netdev, NULL);
+
 }
 
 static int octep_vf_set_mac(struct net_device *netdev, void *p)
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h
index 5769f62545cd..b9f13506f462 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h
@@ -246,11 +246,17 @@ struct octep_vf_device {
 	/* Pointers to Octeon Tx queues */
 	struct octep_vf_iq *iq[OCTEP_VF_MAX_IQ];
 
+	/* Per iq stats */
+	struct octep_vf_iq_stats stats_iq[OCTEP_VF_MAX_IQ];
+
 	/* Rx queues (OQ: Output Queue) */
 	u16 num_oqs;
 	/* Pointers to Octeon Rx queues */
 	struct octep_vf_oq *oq[OCTEP_VF_MAX_OQ];
 
+	/* Per oq stats */
+	struct octep_vf_oq_stats stats_oq[OCTEP_VF_MAX_OQ];
+
 	/* Hardware port number of the PCIe interface */
 	u16 pcie_port;
 
@@ -314,8 +320,6 @@ static inline u16 OCTEP_VF_MINOR_REV(struct octep_vf_device *oct)
 #define octep_vf_read_csr64(octep_vf_dev, reg_off)         \
 	readq((octep_vf_dev)->mmio.hw_addr + (reg_off))
 
-extern struct workqueue_struct *octep_vf_wq;
-
 int octep_vf_device_setup(struct octep_vf_device *oct);
 int octep_vf_setup_iqs(struct octep_vf_device *oct);
 void octep_vf_free_iqs(struct octep_vf_device *oct);
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
index 82821bc28634..d70c8be3cfc4 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
@@ -87,7 +87,7 @@ static int octep_vf_oq_refill(struct octep_vf_device *oct, struct octep_vf_oq *o
 		page = dev_alloc_page();
 		if (unlikely(!page)) {
 			dev_err(oq->dev, "refill: rx buffer alloc failed\n");
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			break;
 		}
 
@@ -98,7 +98,7 @@ static int octep_vf_oq_refill(struct octep_vf_device *oct, struct octep_vf_oq *o
 				"OQ-%d buffer refill: DMA mapping error!\n",
 				oq->q_no);
 			put_page(page);
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			break;
 		}
 		oq->buff_info[refill_idx].page = page;
@@ -134,6 +134,7 @@ static int octep_vf_setup_oq(struct octep_vf_device *oct, int q_no)
 	oq->netdev = oct->netdev;
 	oq->dev = &oct->pdev->dev;
 	oq->q_no = q_no;
+	oq->stats = &oct->stats_oq[q_no];
 	oq->max_count = CFG_GET_OQ_NUM_DESC(oct->conf);
 	oq->ring_size_mask = oq->max_count - 1;
 	oq->buffer_size = CFG_GET_OQ_BUF_SIZE(oct->conf);
@@ -458,8 +459,8 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct,
 
 	oq->host_read_idx = read_idx;
 	oq->refill_count += desc_used;
-	oq->stats.packets += pkt;
-	oq->stats.bytes += rx_bytes;
+	oq->stats->packets += pkt;
+	oq->stats->bytes += rx_bytes;
 
 	return pkt;
 }
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h
index fe46838b5200..9e296b7d7e34 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h
@@ -187,7 +187,7 @@ struct octep_vf_oq {
 	u8 __iomem *pkts_sent_reg;
 
 	/* Statistics for this OQ. */
-	struct octep_vf_oq_stats stats;
+	struct octep_vf_oq_stats *stats;
 
 	/* Packets pending to be processed */
 	u32 pkts_pending;
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c
index 47a5c054fdb6..8180e5ce3d7e 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c
@@ -82,9 +82,9 @@ int octep_vf_iq_process_completions(struct octep_vf_iq *iq, u16 budget)
 	}
 
 	iq->pkts_processed += compl_pkts;
-	iq->stats.instr_completed += compl_pkts;
-	iq->stats.bytes_sent += compl_bytes;
-	iq->stats.sgentry_sent += compl_sg;
+	iq->stats->instr_completed += compl_pkts;
+	iq->stats->bytes_sent += compl_bytes;
+	iq->stats->sgentry_sent += compl_sg;
 	iq->flush_index = fi;
 
 	netif_subqueue_completed_wake(iq->netdev, iq->q_no, compl_pkts,
@@ -186,6 +186,7 @@ static int octep_vf_setup_iq(struct octep_vf_device *oct, int q_no)
 	iq->netdev = oct->netdev;
 	iq->dev = &oct->pdev->dev;
 	iq->q_no = q_no;
+	iq->stats = &oct->stats_iq[q_no];
 	iq->max_count = CFG_GET_IQ_NUM_DESC(oct->conf);
 	iq->ring_size_mask = iq->max_count - 1;
 	iq->fill_threshold = CFG_GET_IQ_DB_MIN(oct->conf);
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h
index f338b975103c..1cede90e3a5f 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h
@@ -129,7 +129,7 @@ struct octep_vf_iq {
 	u16 flush_index;
 
 	/* Statistics for this input queue. */
-	struct octep_vf_iq_stats stats;
+	struct octep_vf_iq_stats *stats;
 
 	/* Pointer to the Virtual Base addr of the input ring. */
 	struct octep_vf_tx_desc_hw *desc_ring;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/Makefile b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
index ccea37847df8..244de500963e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
@@ -12,4 +12,5 @@ rvu_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \
 		  rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o rvu_npc_fs.o \
 		  rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o rvu_switch.o \
 		  rvu_sdp.o rvu_npc_hash.o mcs.o mcs_rvu_if.o mcs_cnf10kb.o \
-		  rvu_rep.o
+		  rvu_rep.o cn20k/mbox_init.o cn20k/nix.o cn20k/debugfs.o \
+		  cn20k/npa.o
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 8216f843a7cd..42044cd810b1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -21,8 +21,7 @@
 #include "rvu.h"
 #include "lmac_common.h"
 
-#define DRV_NAME	"Marvell-CGX/RPM"
-#define DRV_STRING      "Marvell CGX/RPM Driver"
+#define DRV_NAME	"Marvell-CGX-RPM"
 
 #define CGX_RX_STAT_GLOBAL_INDEX	9
 
@@ -66,8 +65,18 @@ static int cgx_fwi_link_change(struct cgx *cgx, int lmac_id, bool en);
 /* Supported devices */
 static const struct pci_device_id cgx_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_CGX) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CN10K_A) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CNF10K_A) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CNF10K_B) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CN10K_B) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CN20KA) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CNF20KA) },
 	{ 0, }  /* end of table */
 };
 
@@ -707,6 +716,11 @@ int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat)
 
 	if (!is_lmac_valid(cgx, lmac_id))
 		return -ENODEV;
+
+	/* pass lmac as 0 for CGX_CMR_RX_STAT9-12 */
+	if (idx >= CGX_RX_STAT_GLOBAL_INDEX)
+		lmac_id = 0;
+
 	*rx_stat =  cgx_read(cgx, lmac_id, CGXX_CMRX_RX_STAT0 + (idx * 8));
 	return 0;
 }
@@ -1167,17 +1181,25 @@ static int cgx_link_usertable_index_map(int speed)
 static void set_mod_args(struct cgx_set_link_mode_args *args,
 			 u32 speed, u8 duplex, u8 autoneg, u64 mode)
 {
-	/* Fill default values incase of user did not pass
-	 * valid parameters
+	int mode_baseidx;
+	u8 cgx_mode;
+
+	if (args->multimode) {
+		args->mode |= mode;
+		return;
+	}
+
+	/* Derive mode_base_idx and mode fields based
+	 * on cgx_mode value
 	 */
-	if (args->duplex == DUPLEX_UNKNOWN)
-		args->duplex = duplex;
-	if (args->speed == SPEED_UNKNOWN)
-		args->speed = speed;
-	if (args->an == AUTONEG_UNKNOWN)
-		args->an = autoneg;
+	cgx_mode = find_first_bit((unsigned long *)&mode,
+				  CGX_MODE_MAX);
 	args->mode = mode;
-	args->ports = 0;
+	mode_baseidx = cgx_mode - 41;
+	if (mode_baseidx > 0) {
+		args->mode_baseidx = 1;
+		args->mode = BIT_ULL(mode_baseidx);
+	}
 }
 
 static void otx2_map_ethtool_link_modes(u64 bitmask,
@@ -1185,16 +1207,16 @@ static void otx2_map_ethtool_link_modes(u64 bitmask,
 {
 	switch (bitmask) {
 	case ETHTOOL_LINK_MODE_10baseT_Half_BIT:
-		set_mod_args(args, 10, 1, 1, BIT_ULL(CGX_MODE_SGMII));
+		set_mod_args(args, 10, 1, 1, BIT_ULL(CGX_MODE_SGMII_10M_BIT));
 		break;
 	case  ETHTOOL_LINK_MODE_10baseT_Full_BIT:
-		set_mod_args(args, 10, 0, 1, BIT_ULL(CGX_MODE_SGMII));
+		set_mod_args(args, 10, 0, 1, BIT_ULL(CGX_MODE_SGMII_10M_BIT));
 		break;
 	case  ETHTOOL_LINK_MODE_100baseT_Half_BIT:
-		set_mod_args(args, 100, 1, 1, BIT_ULL(CGX_MODE_SGMII));
+		set_mod_args(args, 100, 1, 1, BIT_ULL(CGX_MODE_SGMII_100M_BIT));
 		break;
 	case  ETHTOOL_LINK_MODE_100baseT_Full_BIT:
-		set_mod_args(args, 100, 0, 1, BIT_ULL(CGX_MODE_SGMII));
+		set_mod_args(args, 100, 0, 1, BIT_ULL(CGX_MODE_SGMII_100M_BIT));
 		break;
 	case  ETHTOOL_LINK_MODE_1000baseT_Half_BIT:
 		set_mod_args(args, 1000, 1, 1, BIT_ULL(CGX_MODE_SGMII));
@@ -1466,25 +1488,36 @@ int cgx_get_fwdata_base(u64 *base)
 }
 
 int cgx_set_link_mode(void *cgxd, struct cgx_set_link_mode_args args,
+		      struct cgx_lmac_fwdata_s *linkmodes,
 		      int cgx_id, int lmac_id)
 {
 	struct cgx *cgx = cgxd;
 	u64 req = 0, resp;
+	u8 bit;
 
 	if (!cgx)
 		return -ENODEV;
 
-	if (args.mode)
-		otx2_map_ethtool_link_modes(args.mode, &args);
-	if (!args.speed && args.duplex && !args.an)
-		return -EINVAL;
+	for_each_set_bit(bit, args.advertising,
+			 __ETHTOOL_LINK_MODE_MASK_NBITS)
+		otx2_map_ethtool_link_modes(bit, &args);
+
+	if (args.multimode) {
+		if (linkmodes->advertised_link_modes_own != CGX_CMD_OWN_NS)
+			return -EBUSY;
+
+		linkmodes->advertised_link_modes = args.mode;
+		/* Update ownership */
+		linkmodes->advertised_link_modes_own = CGX_CMD_OWN_FIRMWARE;
+		args.mode = GENMASK_ULL(41, 0);
+	}
 
 	req = FIELD_SET(CMDREG_ID, CGX_CMD_MODE_CHANGE, req);
 	req = FIELD_SET(CMDMODECHANGE_SPEED,
 			cgx_link_usertable_index_map(args.speed), req);
 	req = FIELD_SET(CMDMODECHANGE_DUPLEX, args.duplex, req);
 	req = FIELD_SET(CMDMODECHANGE_AN, args.an, req);
-	req = FIELD_SET(CMDMODECHANGE_PORT, args.ports, req);
+	req = FIELD_SET(CMDMODECHANGE_MODE_BASEIDX, args.mode_baseidx, req);
 	req = FIELD_SET(CMDMODECHANGE_FLAGS, args.mode, req);
 
 	return cgx_fwi_cmd_generic(req, &resp, cgx, lmac_id);
@@ -1670,9 +1703,11 @@ unsigned long cgx_get_lmac_bmap(void *cgxd)
 
 static int cgx_lmac_init(struct cgx *cgx)
 {
+	u8 max_dmac_filters;
 	struct lmac *lmac;
+	int err, filter;
+	unsigned int i;
 	u64 lmac_list;
-	int i, err;
 
 	/* lmac_list specifies which lmacs are enabled
 	 * when bit n is set to 1, LMAC[n] is enabled
@@ -1698,7 +1733,7 @@ static int cgx_lmac_init(struct cgx *cgx)
 			err = -ENOMEM;
 			goto err_lmac_free;
 		}
-		sprintf(lmac->name, "cgx_fwi_%d_%d", cgx->cgx_id, i);
+		sprintf(lmac->name, "cgx_fwi_%u_%u", cgx->cgx_id, i);
 		if (cgx->mac_ops->non_contiguous_serdes_lane) {
 			lmac->lmac_id = __ffs64(lmac_list);
 			lmac_list   &= ~BIT_ULL(lmac->lmac_id);
@@ -1711,6 +1746,8 @@ static int cgx_lmac_init(struct cgx *cgx)
 				cgx->mac_ops->dmac_filter_count /
 				cgx->lmac_count;
 
+		max_dmac_filters = lmac->mac_to_index_bmap.max;
+
 		err = rvu_alloc_bitmap(&lmac->mac_to_index_bmap);
 		if (err)
 			goto err_name_free;
@@ -1740,6 +1777,15 @@ static int cgx_lmac_init(struct cgx *cgx)
 		set_bit(lmac->lmac_id, &cgx->lmac_bmap);
 		cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, true);
 		lmac->lmac_type = cgx->mac_ops->get_lmac_type(cgx, lmac->lmac_id);
+
+		/* Disable stale DMAC filters for sane state */
+		for (filter = 0; filter < max_dmac_filters; filter++)
+			cgx_lmac_addr_del(cgx->cgx_id, lmac->lmac_id, filter);
+
+		/* As cgx_lmac_addr_del does not clear entry for index 0
+		 * so it needs to be done explicitly
+		 */
+		cgx_lmac_addr_reset(cgx->cgx_id, lmac->lmac_id);
 	}
 
 	/* Start X2P reset on given MAC block */
@@ -1917,6 +1963,12 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_disable_device;
 	}
 
+	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
+	if (err) {
+		dev_err(dev, "DMA mask config failed, abort\n");
+		goto err_release_regions;
+	}
+
 	/* MAP configuration registers */
 	cgx->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0);
 	if (!cgx->reg_base) {
@@ -1925,6 +1977,14 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_release_regions;
 	}
 
+	if (!is_cn20k(pdev) &&
+	    !is_cgx_mapped_to_nix(pdev->subsystem_device, cgx->cgx_id)) {
+		dev_notice(dev, "CGX %d not mapped to NIX, skipping probe\n",
+			   cgx->cgx_id);
+		err = -ENODEV;
+		goto err_release_regions;
+	}
+
 	cgx->lmac_count = cgx->mac_ops->get_nr_lmacs(cgx);
 	if (!cgx->lmac_count) {
 		dev_notice(dev, "CGX %d LMAC count is zero, skipping probe\n", cgx->cgx_id);
@@ -1934,7 +1994,7 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	nvec = pci_msix_vec_count(cgx->pdev);
 	err = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_MSIX);
-	if (err < 0 || err != nvec) {
+	if (err < 0) {
 		dev_err(dev, "Request for %d msix vectors failed, err %d\n",
 			nvec, err);
 		goto err_release_regions;
@@ -1945,7 +2005,7 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	/* init wq for processing linkup requests */
 	INIT_WORK(&cgx->cgx_cmd_work, cgx_lmac_linkup_work);
-	cgx->cgx_cmd_workq = alloc_workqueue("cgx_cmd_workq", 0, 0);
+	cgx->cgx_cmd_workq = alloc_workqueue("cgx_cmd_workq", WQ_PERCPU, 0);
 	if (!cgx->cgx_cmd_workq) {
 		dev_err(dev, "alloc workqueue failed for cgx cmd");
 		err = -ENOMEM;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index 1cf12e5c7da8..92ccf343dfe0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -161,16 +161,13 @@ int cgx_get_link_info(void *cgxd, int lmac_id,
 		      struct cgx_link_user_info *linfo);
 int cgx_lmac_linkup_start(void *cgxd);
 int cgx_get_fwdata_base(u64 *base);
-int cgx_lmac_get_pause_frm(void *cgxd, int lmac_id,
-			   u8 *tx_pause, u8 *rx_pause);
-int cgx_lmac_set_pause_frm(void *cgxd, int lmac_id,
-			   u8 tx_pause, u8 rx_pause);
 void cgx_lmac_ptp_config(void *cgxd, int lmac_id, bool enable);
 u8 cgx_lmac_get_p2x(int cgx_id, int lmac_id);
 int cgx_set_fec(u64 fec, int cgx_id, int lmac_id);
 int cgx_get_fec_stats(void *cgxd, int lmac_id, struct cgx_fec_stats_rsp *rsp);
 int cgx_get_phy_fec_stats(void *cgxd, int lmac_id);
 int cgx_set_link_mode(void *cgxd, struct cgx_set_link_mode_args args,
+		      struct cgx_lmac_fwdata_s *linkmodes,
 		      int cgx_id, int lmac_id);
 u64 cgx_features_get(void *cgxd);
 struct mac_ops *get_mac_ops(void *cgxd);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
index d4a27c882a5b..39352d451cc3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
@@ -95,7 +95,31 @@ enum CGX_MODE_ {
 	CGX_MODE_100G_C2M,
 	CGX_MODE_100G_CR4,
 	CGX_MODE_100G_KR4,
-	CGX_MODE_MAX /* = 29 */
+	CGX_MODE_LAUI_2_C2C_BIT,
+	CGX_MODE_LAUI_2_C2M_BIT,
+	CGX_MODE_50GBASE_CR2_C_BIT,
+	CGX_MODE_50GBASE_KR2_C_BIT,     /* = 30 */
+	CGX_MODE_100GAUI_2_C2C_BIT,
+	CGX_MODE_100GAUI_2_C2M_BIT,
+	CGX_MODE_100GBASE_CR2_BIT,
+	CGX_MODE_100GBASE_KR2_BIT,
+	CGX_MODE_SFI_1G_BIT,
+	CGX_MODE_25GBASE_CR_C_BIT,
+	CGX_MODE_25GBASE_KR_C_BIT,
+	CGX_MODE_SGMII_10M_BIT,
+	CGX_MODE_SGMII_100M_BIT,        /* = 39 */
+	CGX_MODE_2500_BASEX_BIT = 42, /* Mode group 1 */
+	CGX_MODE_5000_BASEX_BIT,
+	CGX_MODE_O_USGMII_BIT,
+	CGX_MODE_Q_USGMII_BIT,
+	CGX_MODE_2_5G_USXGMII_BIT,
+	CGX_MODE_5G_USXGMII_BIT,
+	CGX_MODE_10G_SXGMII_BIT,
+	CGX_MODE_10G_DXGMII_BIT,
+	CGX_MODE_10G_QXGMII_BIT,
+	CGX_MODE_TP_BIT,
+	CGX_MODE_FIBER_BIT,
+	CGX_MODE_MAX /* = 53 */
 };
 /* REQUEST ID types. Input to firmware */
 enum cgx_cmd_id {
@@ -258,7 +282,12 @@ struct cgx_lnk_sts {
 #define CMDMODECHANGE_SPEED		GENMASK_ULL(11, 8)
 #define CMDMODECHANGE_DUPLEX		GENMASK_ULL(12, 12)
 #define CMDMODECHANGE_AN		GENMASK_ULL(13, 13)
-#define CMDMODECHANGE_PORT		GENMASK_ULL(21, 14)
+/* this field categorize the mode ID(FLAGS) range to accommodate
+ * more modes.
+ * To specify mode ID range of 0 - 41, this field will be 0.
+ * To specify mode ID range of 42 - 83, this field will be 1.
+ */
+#define CMDMODECHANGE_MODE_BASEIDX	GENMASK_ULL(21, 20)
 #define CMDMODECHANGE_FLAGS		GENMASK_ULL(63, 22)
 
 /* LINK_BRING_UP command timeout */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/api.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/api.h
new file mode 100644
index 000000000000..4285b5d6a6a2
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/api.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell RVU Admin Function driver
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#ifndef CN20K_API_H
+#define CN20K_API_H
+
+#include "../rvu.h"
+
+struct ng_rvu {
+	struct mbox_ops         *rvu_mbox_ops;
+	struct qmem             *pf_mbox_addr;
+	struct qmem             *vf_mbox_addr;
+};
+
+/* Mbox related APIs */
+int cn20k_rvu_mbox_init(struct rvu *rvu, int type, int num);
+int cn20k_rvu_get_mbox_regions(struct rvu *rvu, void **mbox_addr,
+			       int num, int type, unsigned long *pf_bmap);
+void cn20k_free_mbox_memory(struct rvu *rvu);
+int cn20k_register_afpf_mbox_intr(struct rvu *rvu);
+int cn20k_register_afvf_mbox_intr(struct rvu *rvu, int pf_vec_start);
+void cn20k_rvu_enable_mbox_intr(struct rvu *rvu);
+void cn20k_rvu_unregister_interrupts(struct rvu *rvu);
+int cn20k_mbox_setup(struct otx2_mbox *mbox, struct pci_dev *pdev,
+		     void *reg_base, int direction, int ndevs);
+void cn20k_rvu_enable_afvf_intr(struct rvu *rvu, int vfs);
+void cn20k_rvu_disable_afvf_intr(struct rvu *rvu, int vfs);
+#endif /* CN20K_API_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c
new file mode 100644
index 000000000000..498968bf4cf5
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell RVU Admin Function driver
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include "struct.h"
+#include "debugfs.h"
+
+void print_nix_cn20k_sq_ctx(struct seq_file *m,
+			    struct nix_cn20k_sq_ctx_s *sq_ctx)
+{
+	seq_printf(m, "W0: ena \t\t\t%d\nW0: qint_idx \t\t\t%d\n",
+		   sq_ctx->ena, sq_ctx->qint_idx);
+	seq_printf(m, "W0: substream \t\t\t0x%03x\nW0: sdp_mcast \t\t\t%d\n",
+		   sq_ctx->substream, sq_ctx->sdp_mcast);
+	seq_printf(m, "W0: cq \t\t\t\t%d\nW0: sqe_way_mask \t\t%d\n\n",
+		   sq_ctx->cq, sq_ctx->sqe_way_mask);
+
+	seq_printf(m, "W1: smq \t\t\t%d\nW1: cq_ena \t\t\t%d\nW1: xoff\t\t\t%d\n",
+		   sq_ctx->smq, sq_ctx->cq_ena, sq_ctx->xoff);
+	seq_printf(m, "W1: sso_ena \t\t\t%d\nW1: smq_rr_weight\t\t%d\n",
+		   sq_ctx->sso_ena, sq_ctx->smq_rr_weight);
+	seq_printf(m, "W1: default_chan\t\t%d\nW1: sqb_count\t\t\t%d\n\n",
+		   sq_ctx->default_chan, sq_ctx->sqb_count);
+
+	seq_printf(m, "W1: smq_rr_count_lb \t\t%d\n", sq_ctx->smq_rr_count_lb);
+	seq_printf(m, "W2: smq_rr_count_ub \t\t%d\n", sq_ctx->smq_rr_count_ub);
+	seq_printf(m, "W2: sqb_aura \t\t\t%d\nW2: sq_int \t\t\t%d\n",
+		   sq_ctx->sqb_aura, sq_ctx->sq_int);
+	seq_printf(m, "W2: sq_int_ena \t\t\t%d\nW2: sqe_stype \t\t\t%d\n",
+		   sq_ctx->sq_int_ena, sq_ctx->sqe_stype);
+
+	seq_printf(m, "W3: max_sqe_size\t\t%d\nW3: cq_limit\t\t\t%d\n",
+		   sq_ctx->max_sqe_size, sq_ctx->cq_limit);
+	seq_printf(m, "W3: lmt_dis \t\t\t%d\nW3: mnq_dis \t\t\t%d\n",
+		   sq_ctx->lmt_dis, sq_ctx->mnq_dis);
+	seq_printf(m, "W3: smq_next_sq\t\t\t%d\nW3: smq_lso_segnum\t\t%d\n",
+		   sq_ctx->smq_next_sq, sq_ctx->smq_lso_segnum);
+	seq_printf(m, "W3: tail_offset \t\t%d\nW3: smenq_offset\t\t%d\n",
+		   sq_ctx->tail_offset, sq_ctx->smenq_offset);
+	seq_printf(m, "W3: head_offset\t\t\t%d\nW3: smenq_next_sqb_vld\t\t%d\n\n",
+		   sq_ctx->head_offset, sq_ctx->smenq_next_sqb_vld);
+
+	seq_printf(m, "W3: smq_next_sq_vld\t\t%d\nW3: smq_pend\t\t\t%d\n",
+		   sq_ctx->smq_next_sq_vld, sq_ctx->smq_pend);
+	seq_printf(m, "W4: next_sqb \t\t\t%llx\n\n", sq_ctx->next_sqb);
+	seq_printf(m, "W5: tail_sqb \t\t\t%llx\n\n", sq_ctx->tail_sqb);
+	seq_printf(m, "W6: smenq_sqb \t\t\t%llx\n\n", sq_ctx->smenq_sqb);
+	seq_printf(m, "W7: smenq_next_sqb \t\t%llx\n\n",
+		   sq_ctx->smenq_next_sqb);
+
+	seq_printf(m, "W8: head_sqb\t\t\t%llx\n\n", sq_ctx->head_sqb);
+
+	seq_printf(m, "W9: vfi_lso_total\t\t%d\n", sq_ctx->vfi_lso_total);
+	seq_printf(m, "W9: vfi_lso_sizem1\t\t%d\nW9: vfi_lso_sb\t\t\t%d\n",
+		   sq_ctx->vfi_lso_sizem1, sq_ctx->vfi_lso_sb);
+	seq_printf(m, "W9: vfi_lso_mps\t\t\t%d\nW9: vfi_lso_vlan0_ins_ena\t%d\n",
+		   sq_ctx->vfi_lso_mps, sq_ctx->vfi_lso_vlan0_ins_ena);
+	seq_printf(m, "W9: vfi_lso_vlan1_ins_ena\t%d\nW9: vfi_lso_vld \t\t%d\n\n",
+		   sq_ctx->vfi_lso_vld, sq_ctx->vfi_lso_vlan1_ins_ena);
+
+	seq_printf(m, "W10: scm_lso_rem \t\t%llu\n\n",
+		   (u64)sq_ctx->scm_lso_rem);
+	seq_printf(m, "W11: octs \t\t\t%llu\n\n", (u64)sq_ctx->octs);
+	seq_printf(m, "W12: pkts \t\t\t%llu\n\n", (u64)sq_ctx->pkts);
+	seq_printf(m, "W13: aged_drop_octs \t\t\t%llu\n\n",
+		   (u64)sq_ctx->aged_drop_octs);
+	seq_printf(m, "W13: aged_drop_pkts \t\t\t%llu\n\n",
+		   (u64)sq_ctx->aged_drop_pkts);
+	seq_printf(m, "W14: dropped_octs \t\t%llu\n\n",
+		   (u64)sq_ctx->dropped_octs);
+	seq_printf(m, "W15: dropped_pkts \t\t%llu\n\n",
+		   (u64)sq_ctx->dropped_pkts);
+}
+
+void print_nix_cn20k_cq_ctx(struct seq_file *m,
+			    struct nix_cn20k_aq_enq_rsp *rsp)
+{
+	struct nix_cn20k_cq_ctx_s *cq_ctx = &rsp->cq;
+
+	seq_printf(m, "W0: base \t\t\t%llx\n\n", cq_ctx->base);
+
+	seq_printf(m, "W1: wrptr \t\t\t%llx\n", (u64)cq_ctx->wrptr);
+	seq_printf(m, "W1: avg_con \t\t\t%d\nW1: cint_idx \t\t\t%d\n",
+		   cq_ctx->avg_con, cq_ctx->cint_idx);
+	seq_printf(m, "W1: cq_err \t\t\t%d\nW1: qint_idx \t\t\t%d\n",
+		   cq_ctx->cq_err, cq_ctx->qint_idx);
+	seq_printf(m, "W1: bpid \t\t\t%d\nW1: bp_ena \t\t\t%d\n\n",
+		   cq_ctx->bpid, cq_ctx->bp_ena);
+
+	seq_printf(m, "W1: lbpid_high \t\t\t0x%03x\n", cq_ctx->lbpid_high);
+	seq_printf(m, "W1: lbpid_med \t\t\t0x%03x\n", cq_ctx->lbpid_med);
+	seq_printf(m, "W1: lbpid_low \t\t\t0x%03x\n", cq_ctx->lbpid_low);
+	seq_printf(m, "(W1: lbpid) \t\t\t0x%03x\n",
+		   cq_ctx->lbpid_high << 6 | cq_ctx->lbpid_med << 3 |
+		   cq_ctx->lbpid_low);
+	seq_printf(m, "W1: lbp_ena \t\t\t\t%d\n\n", cq_ctx->lbp_ena);
+
+	seq_printf(m, "W2: update_time \t\t%d\nW2:avg_level \t\t\t%d\n",
+		   cq_ctx->update_time, cq_ctx->avg_level);
+	seq_printf(m, "W2: head \t\t\t%d\nW2:tail \t\t\t%d\n\n",
+		   cq_ctx->head, cq_ctx->tail);
+
+	seq_printf(m, "W3: cq_err_int_ena \t\t%d\nW3:cq_err_int \t\t\t%d\n",
+		   cq_ctx->cq_err_int_ena, cq_ctx->cq_err_int);
+	seq_printf(m, "W3: qsize \t\t\t%d\nW3:stashing \t\t\t%d\n",
+		   cq_ctx->qsize, cq_ctx->stashing);
+
+	seq_printf(m, "W3: caching \t\t\t%d\n", cq_ctx->caching);
+	seq_printf(m, "W3: lbp_frac \t\t\t%d\n", cq_ctx->lbp_frac);
+	seq_printf(m, "W3: stash_thresh \t\t\t%d\n",
+		   cq_ctx->stash_thresh);
+
+	seq_printf(m, "W3: msh_valid \t\t\t%d\nW3:msh_dst \t\t\t%d\n",
+		   cq_ctx->msh_valid, cq_ctx->msh_dst);
+
+	seq_printf(m, "W3: cpt_drop_err_en \t\t\t%d\n",
+		   cq_ctx->cpt_drop_err_en);
+	seq_printf(m, "W3: ena \t\t\t%d\n",
+		   cq_ctx->ena);
+	seq_printf(m, "W3: drop_ena \t\t\t%d\nW3: drop \t\t\t%d\n",
+		   cq_ctx->drop_ena, cq_ctx->drop);
+	seq_printf(m, "W3: bp \t\t\t\t%d\n\n", cq_ctx->bp);
+
+	seq_printf(m, "W4: lbpid_ext \t\t\t\t%d\n\n", cq_ctx->lbpid_ext);
+	seq_printf(m, "W4: bpid_ext \t\t\t\t%d\n\n", cq_ctx->bpid_ext);
+}
+
+void print_npa_cn20k_aura_ctx(struct seq_file *m,
+			      struct npa_cn20k_aq_enq_rsp *rsp)
+{
+	struct npa_cn20k_aura_s *aura = &rsp->aura;
+
+	seq_printf(m, "W0: Pool addr\t\t%llx\n", aura->pool_addr);
+
+	seq_printf(m, "W1: ena\t\t\t%d\nW1: pool caching\t%d\n",
+		   aura->ena, aura->pool_caching);
+	seq_printf(m, "W1: avg con\t\t%d\n", aura->avg_con);
+	seq_printf(m, "W1: pool drop ena\t%d\nW1: aura drop ena\t%d\n",
+		   aura->pool_drop_ena, aura->aura_drop_ena);
+	seq_printf(m, "W1: bp_ena\t\t%d\nW1: aura drop\t\t%d\n",
+		   aura->bp_ena, aura->aura_drop);
+	seq_printf(m, "W1: aura shift\t\t%d\nW1: avg_level\t\t%d\n",
+		   aura->shift, aura->avg_level);
+
+	seq_printf(m, "W2: count\t\t%llu\nW2: nix_bpid\t\t%d\n",
+		   (u64)aura->count, aura->bpid);
+
+	seq_printf(m, "W3: limit\t\t%llu\nW3: bp\t\t\t%d\nW3: fc_ena\t\t%d\n",
+		   (u64)aura->limit, aura->bp, aura->fc_ena);
+
+	seq_printf(m, "W3: fc_up_crossing\t%d\nW3: fc_stype\t\t%d\n",
+		   aura->fc_up_crossing, aura->fc_stype);
+	seq_printf(m, "W3: fc_hyst_bits\t%d\n", aura->fc_hyst_bits);
+
+	seq_printf(m, "W4: fc_addr\t\t%llx\n", aura->fc_addr);
+
+	seq_printf(m, "W5: pool_drop\t\t%d\nW5: update_time\t\t%d\n",
+		   aura->pool_drop, aura->update_time);
+	seq_printf(m, "W5: err_int \t\t%d\nW5: err_int_ena\t\t%d\n",
+		   aura->err_int, aura->err_int_ena);
+	seq_printf(m, "W5: thresh_int\t\t%d\nW5: thresh_int_ena \t%d\n",
+		   aura->thresh_int, aura->thresh_int_ena);
+	seq_printf(m, "W5: thresh_up\t\t%d\nW5: thresh_qint_idx\t%d\n",
+		   aura->thresh_up, aura->thresh_qint_idx);
+	seq_printf(m, "W5: err_qint_idx \t%d\n", aura->err_qint_idx);
+
+	seq_printf(m, "W6: thresh\t\t%llu\n", (u64)aura->thresh);
+	seq_printf(m, "W6: fc_msh_dst\t\t%d\n", aura->fc_msh_dst);
+}
+
+void print_npa_cn20k_pool_ctx(struct seq_file *m,
+			      struct npa_cn20k_aq_enq_rsp *rsp)
+{
+	struct npa_cn20k_pool_s *pool = &rsp->pool;
+
+	seq_printf(m, "W0: Stack base\t\t%llx\n", pool->stack_base);
+
+	seq_printf(m, "W1: ena \t\t%d\nW1: nat_align \t\t%d\n",
+		   pool->ena, pool->nat_align);
+	seq_printf(m, "W1: stack_caching\t%d\n",
+		   pool->stack_caching);
+	seq_printf(m, "W1: buf_offset\t\t%d\nW1: buf_size\t\t%d\n",
+		   pool->buf_offset, pool->buf_size);
+
+	seq_printf(m, "W2: stack_max_pages \t%d\nW2: stack_pages\t\t%d\n",
+		   pool->stack_max_pages, pool->stack_pages);
+
+	seq_printf(m, "W4: stack_offset\t%d\nW4: shift\t\t%d\nW4: avg_level\t\t%d\n",
+		   pool->stack_offset, pool->shift, pool->avg_level);
+	seq_printf(m, "W4: avg_con \t\t%d\nW4: fc_ena\t\t%d\nW4: fc_stype\t\t%d\n",
+		   pool->avg_con, pool->fc_ena, pool->fc_stype);
+	seq_printf(m, "W4: fc_hyst_bits\t%d\nW4: fc_up_crossing\t%d\n",
+		   pool->fc_hyst_bits, pool->fc_up_crossing);
+	seq_printf(m, "W4: update_time\t\t%d\n", pool->update_time);
+
+	seq_printf(m, "W5: fc_addr\t\t%llx\n", pool->fc_addr);
+
+	seq_printf(m, "W6: ptr_start\t\t%llx\n", pool->ptr_start);
+
+	seq_printf(m, "W7: ptr_end\t\t%llx\n", pool->ptr_end);
+
+	seq_printf(m, "W8: err_int\t\t%d\nW8: err_int_ena\t\t%d\n",
+		   pool->err_int, pool->err_int_ena);
+	seq_printf(m, "W8: thresh_int\t\t%d\n", pool->thresh_int);
+	seq_printf(m, "W8: thresh_int_ena\t%d\nW8: thresh_up\t\t%d\n",
+		   pool->thresh_int_ena, pool->thresh_up);
+	seq_printf(m, "W8: thresh_qint_idx\t%d\nW8: err_qint_idx\t%d\n",
+		   pool->thresh_qint_idx, pool->err_qint_idx);
+	seq_printf(m, "W8: fc_msh_dst\t\t%d\n", pool->fc_msh_dst);
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.h
new file mode 100644
index 000000000000..a2e3a2cd6edb
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell OcteonTx2 CGX driver
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#ifndef DEBUFS_H
+#define DEBUFS_H
+
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include "struct.h"
+#include "../mbox.h"
+
+void print_nix_cn20k_sq_ctx(struct seq_file *m,
+			    struct nix_cn20k_sq_ctx_s *sq_ctx);
+void print_nix_cn20k_cq_ctx(struct seq_file *m,
+			    struct nix_cn20k_aq_enq_rsp *rsp);
+void print_npa_cn20k_aura_ctx(struct seq_file *m,
+			      struct npa_cn20k_aq_enq_rsp *rsp);
+void print_npa_cn20k_pool_ctx(struct seq_file *m,
+			      struct npa_cn20k_aq_enq_rsp *rsp);
+
+#endif
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/mbox_init.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/mbox_init.c
new file mode 100644
index 000000000000..bd3aab7770dd
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/mbox_init.c
@@ -0,0 +1,424 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell RVU Admin Function driver
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+
+#include "rvu_trace.h"
+#include "mbox.h"
+#include "reg.h"
+#include "api.h"
+
+static irqreturn_t cn20k_afvf_mbox_intr_handler(int irq, void *rvu_irq)
+{
+	struct rvu_irq_data *rvu_irq_data = rvu_irq;
+	struct rvu *rvu = rvu_irq_data->rvu;
+	u64 intr;
+
+	/* Sync with mbox memory region */
+	rmb();
+
+	/* Clear interrupts */
+	intr = rvupf_read64(rvu, rvu_irq_data->intr_status);
+	rvupf_write64(rvu, rvu_irq_data->intr_status, intr);
+
+	if (intr)
+		trace_otx2_msg_interrupt(rvu->pdev, "VF(s) to AF", intr);
+
+	rvu_irq_data->afvf_queue_work_hdlr(&rvu->afvf_wq_info, rvu_irq_data->start,
+					   rvu_irq_data->mdevs, intr);
+
+	return IRQ_HANDLED;
+}
+
+int cn20k_register_afvf_mbox_intr(struct rvu *rvu, int pf_vec_start)
+{
+	struct rvu_irq_data *irq_data;
+	int intr_vec, offset, vec = 0;
+	int err;
+
+	/* irq data for 4 VFPF intr vectors */
+	irq_data = devm_kcalloc(rvu->dev, 4,
+				sizeof(struct rvu_irq_data), GFP_KERNEL);
+	if (!irq_data)
+		return -ENOMEM;
+
+	for (intr_vec = RVU_MBOX_PF_INT_VEC_VFPF_MBOX0; intr_vec <=
+					RVU_MBOX_PF_INT_VEC_VFPF1_MBOX1;
+					intr_vec++, vec++) {
+		switch (intr_vec) {
+		case RVU_MBOX_PF_INT_VEC_VFPF_MBOX0:
+			irq_data[vec].intr_status =
+						RVU_MBOX_PF_VFPF_INTX(0);
+			irq_data[vec].start = 0;
+			irq_data[vec].mdevs = 64;
+			break;
+		case RVU_MBOX_PF_INT_VEC_VFPF_MBOX1:
+			irq_data[vec].intr_status =
+						RVU_MBOX_PF_VFPF_INTX(1);
+			irq_data[vec].start = 64;
+			irq_data[vec].mdevs = 64;
+			break;
+		case RVU_MBOX_PF_INT_VEC_VFPF1_MBOX0:
+			irq_data[vec].intr_status =
+						RVU_MBOX_PF_VFPF1_INTX(0);
+			irq_data[vec].start = 0;
+			irq_data[vec].mdevs = 64;
+			break;
+		case RVU_MBOX_PF_INT_VEC_VFPF1_MBOX1:
+			irq_data[vec].intr_status = RVU_MBOX_PF_VFPF1_INTX(1);
+			irq_data[vec].start = 64;
+			irq_data[vec].mdevs = 64;
+			break;
+		}
+		irq_data[vec].afvf_queue_work_hdlr =
+						rvu_queue_work;
+		offset = pf_vec_start + intr_vec;
+		irq_data[vec].vec_num = offset;
+		irq_data[vec].rvu = rvu;
+
+		sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAF VFAF%d Mbox%d",
+			vec / 2, vec % 2);
+		err = request_irq(pci_irq_vector(rvu->pdev, offset),
+				  rvu->ng_rvu->rvu_mbox_ops->afvf_intr_handler, 0,
+				  &rvu->irq_name[offset * NAME_SIZE],
+				  &irq_data[vec]);
+		if (err) {
+			dev_err(rvu->dev,
+				"RVUAF: IRQ registration failed for AFVF mbox irq\n");
+			return err;
+		}
+		rvu->irq_allocated[offset] = true;
+	}
+
+	return 0;
+}
+
+/* CN20K mbox PFx => AF irq handler */
+static irqreturn_t cn20k_mbox_pf_common_intr_handler(int irq, void *rvu_irq)
+{
+	struct rvu_irq_data *rvu_irq_data = rvu_irq;
+	struct rvu *rvu = rvu_irq_data->rvu;
+	u64 intr;
+
+	/* Clear interrupts */
+	intr = rvu_read64(rvu, BLKADDR_RVUM, rvu_irq_data->intr_status);
+	rvu_write64(rvu, BLKADDR_RVUM, rvu_irq_data->intr_status, intr);
+
+	if (intr)
+		trace_otx2_msg_interrupt(rvu->pdev, "PF(s) to AF", intr);
+
+	/* Sync with mbox memory region */
+	rmb();
+
+	rvu_irq_data->rvu_queue_work_hdlr(&rvu->afpf_wq_info,
+					  rvu_irq_data->start,
+					  rvu_irq_data->mdevs, intr);
+
+	return IRQ_HANDLED;
+}
+
+void cn20k_rvu_enable_mbox_intr(struct rvu *rvu)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+
+	/* Clear spurious irqs, if any */
+	rvu_write64(rvu, BLKADDR_RVUM,
+		    RVU_MBOX_AF_PFAF_INT(0), INTR_MASK(hw->total_pfs));
+
+	rvu_write64(rvu, BLKADDR_RVUM,
+		    RVU_MBOX_AF_PFAF_INT(1), INTR_MASK(hw->total_pfs - 64));
+
+	rvu_write64(rvu, BLKADDR_RVUM,
+		    RVU_MBOX_AF_PFAF1_INT(0), INTR_MASK(hw->total_pfs));
+
+	rvu_write64(rvu, BLKADDR_RVUM,
+		    RVU_MBOX_AF_PFAF1_INT(1), INTR_MASK(hw->total_pfs - 64));
+
+	/* Enable mailbox interrupt for all PFs except PF0 i.e AF itself */
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF_INT_ENA_W1S(0),
+		    INTR_MASK(hw->total_pfs) & ~1ULL);
+
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF_INT_ENA_W1S(1),
+		    INTR_MASK(hw->total_pfs - 64));
+
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF1_INT_ENA_W1S(0),
+		    INTR_MASK(hw->total_pfs) & ~1ULL);
+
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF1_INT_ENA_W1S(1),
+		    INTR_MASK(hw->total_pfs - 64));
+}
+
+void cn20k_rvu_unregister_interrupts(struct rvu *rvu)
+{
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF_INT_ENA_W1C(0),
+		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
+
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF_INT_ENA_W1C(1),
+		    INTR_MASK(rvu->hw->total_pfs - 64));
+
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF1_INT_ENA_W1C(0),
+		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
+
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF1_INT_ENA_W1C(1),
+		    INTR_MASK(rvu->hw->total_pfs - 64));
+}
+
+int cn20k_register_afpf_mbox_intr(struct rvu *rvu)
+{
+	struct rvu_irq_data *irq_data;
+	int intr_vec, ret, vec = 0;
+
+	/* irq data for 4 PF intr vectors */
+	irq_data = devm_kcalloc(rvu->dev, 4,
+				sizeof(struct rvu_irq_data), GFP_KERNEL);
+	if (!irq_data)
+		return -ENOMEM;
+
+	for (intr_vec = RVU_AF_CN20K_INT_VEC_PFAF_MBOX0; intr_vec <=
+				RVU_AF_CN20K_INT_VEC_PFAF1_MBOX1; intr_vec++,
+				vec++) {
+		switch (intr_vec) {
+		case RVU_AF_CN20K_INT_VEC_PFAF_MBOX0:
+			irq_data[vec].intr_status =
+						RVU_MBOX_AF_PFAF_INT(0);
+			irq_data[vec].start = 0;
+			irq_data[vec].mdevs = 64;
+			break;
+		case RVU_AF_CN20K_INT_VEC_PFAF_MBOX1:
+			irq_data[vec].intr_status =
+						RVU_MBOX_AF_PFAF_INT(1);
+			irq_data[vec].start = 64;
+			irq_data[vec].mdevs = 96;
+			break;
+		case RVU_AF_CN20K_INT_VEC_PFAF1_MBOX0:
+			irq_data[vec].intr_status =
+						RVU_MBOX_AF_PFAF1_INT(0);
+			irq_data[vec].start = 0;
+			irq_data[vec].mdevs = 64;
+			break;
+		case RVU_AF_CN20K_INT_VEC_PFAF1_MBOX1:
+			irq_data[vec].intr_status =
+						RVU_MBOX_AF_PFAF1_INT(1);
+			irq_data[vec].start = 64;
+			irq_data[vec].mdevs = 96;
+			break;
+		}
+		irq_data[vec].rvu_queue_work_hdlr = rvu_queue_work;
+		irq_data[vec].vec_num = intr_vec;
+		irq_data[vec].rvu = rvu;
+
+		/* Register mailbox interrupt handler */
+		sprintf(&rvu->irq_name[intr_vec * NAME_SIZE],
+			"RVUAF PFAF%d Mbox%d",
+			vec / 2, vec % 2);
+		ret = request_irq(pci_irq_vector(rvu->pdev, intr_vec),
+				  rvu->ng_rvu->rvu_mbox_ops->pf_intr_handler, 0,
+				  &rvu->irq_name[intr_vec * NAME_SIZE],
+				  &irq_data[vec]);
+		if (ret)
+			return ret;
+
+		rvu->irq_allocated[intr_vec] = true;
+	}
+
+	return 0;
+}
+
+int cn20k_rvu_get_mbox_regions(struct rvu *rvu, void **mbox_addr,
+			       int num, int type, unsigned long *pf_bmap)
+{
+	int region;
+	u64 bar;
+
+	if (type == TYPE_AFVF) {
+		for (region = 0; region < num; region++) {
+			if (!test_bit(region, pf_bmap))
+				continue;
+
+			bar = (u64)phys_to_virt((u64)rvu->ng_rvu->vf_mbox_addr->base);
+			bar += region * MBOX_SIZE;
+			mbox_addr[region] = (void *)bar;
+
+			if (!mbox_addr[region])
+				return -ENOMEM;
+		}
+		return 0;
+	}
+
+	for (region = 0; region < num; region++) {
+		if (!test_bit(region, pf_bmap))
+			continue;
+
+		bar = (u64)phys_to_virt((u64)rvu->ng_rvu->pf_mbox_addr->base);
+		bar += region * MBOX_SIZE;
+
+		mbox_addr[region] = (void *)bar;
+
+		if (!mbox_addr[region])
+			return -ENOMEM;
+	}
+	return 0;
+}
+
+static int rvu_alloc_mbox_memory(struct rvu *rvu, int type,
+				 int ndevs, int mbox_size)
+{
+	struct qmem *mbox_addr;
+	dma_addr_t iova;
+	int pf, err;
+
+	/* Allocate contiguous memory for mailbox communication.
+	 * eg: AF <=> PFx mbox memory
+	 * This allocated memory is split into chunks of MBOX_SIZE
+	 * and setup into each of the RVU PFs. In HW this memory will
+	 * get aliased to an offset within BAR2 of those PFs.
+	 *
+	 * AF will access mbox memory using direct physical addresses
+	 * and PFs will access the same shared memory from BAR2.
+	 *
+	 * PF <=> VF mbox memory also works in the same fashion.
+	 * AFPF, PFVF requires IOVA to be used to maintain the mailbox msgs
+	 */
+
+	err = qmem_alloc(rvu->dev, &mbox_addr, ndevs, mbox_size);
+	if (err)
+		return -ENOMEM;
+
+	switch (type) {
+	case TYPE_AFPF:
+		rvu->ng_rvu->pf_mbox_addr = mbox_addr;
+		iova = (u64)mbox_addr->iova;
+		for (pf = 0; pf < ndevs; pf++) {
+			rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFX_ADDR(pf),
+				    (u64)iova);
+			iova += mbox_size;
+		}
+		break;
+	case TYPE_AFVF:
+		rvu->ng_rvu->vf_mbox_addr = mbox_addr;
+		rvupf_write64(rvu, RVU_PF_VF_MBOX_ADDR, (u64)mbox_addr->iova);
+		break;
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+static struct mbox_ops cn20k_mbox_ops = {
+	.pf_intr_handler = cn20k_mbox_pf_common_intr_handler,
+	.afvf_intr_handler = cn20k_afvf_mbox_intr_handler,
+};
+
+int cn20k_rvu_mbox_init(struct rvu *rvu, int type, int ndevs)
+{
+	int dev;
+
+	if (!is_cn20k(rvu->pdev))
+		return 0;
+
+	rvu->ng_rvu->rvu_mbox_ops = &cn20k_mbox_ops;
+
+	if (type == TYPE_AFVF) {
+		rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_PF_VF_CFG, ilog2(MBOX_SIZE));
+	} else {
+		for (dev = 0; dev < ndevs; dev++)
+			rvu_write64(rvu, BLKADDR_RVUM,
+				    RVU_MBOX_AF_PFX_CFG(dev), ilog2(MBOX_SIZE));
+	}
+
+	return rvu_alloc_mbox_memory(rvu, type, ndevs, MBOX_SIZE);
+}
+
+void cn20k_free_mbox_memory(struct rvu *rvu)
+{
+	if (!is_cn20k(rvu->pdev))
+		return;
+
+	qmem_free(rvu->dev, rvu->ng_rvu->pf_mbox_addr);
+	qmem_free(rvu->dev, rvu->ng_rvu->vf_mbox_addr);
+}
+
+void cn20k_rvu_disable_afvf_intr(struct rvu *rvu, int vfs)
+{
+	rvupf_write64(rvu, RVU_MBOX_PF_VFPF_INT_ENA_W1CX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_MBOX_PF_VFPF1_INT_ENA_W1CX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1CX(0), INTR_MASK(vfs));
+
+	if (vfs <= 64)
+		return;
+
+	rvupf_write64(rvu, RVU_MBOX_PF_VFPF_INT_ENA_W1CX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_MBOX_PF_VFPF1_INT_ENA_W1CX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1CX(1), INTR_MASK(vfs - 64));
+}
+
+void cn20k_rvu_enable_afvf_intr(struct rvu *rvu, int vfs)
+{
+	/* Clear any pending interrupts and enable AF VF interrupts for
+	 * the first 64 VFs.
+	 */
+	rvupf_write64(rvu, RVU_MBOX_PF_VFPF_INTX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_MBOX_PF_VFPF_INT_ENA_W1SX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_MBOX_PF_VFPF1_INTX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_MBOX_PF_VFPF1_INT_ENA_W1SX(0), INTR_MASK(vfs));
+
+	/* FLR */
+	rvupf_write64(rvu, RVU_PF_VFFLR_INTX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1SX(0), INTR_MASK(vfs));
+
+	/* Same for remaining VFs, if any. */
+	if (vfs <= 64)
+		return;
+
+	rvupf_write64(rvu, RVU_MBOX_PF_VFPF_INTX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_MBOX_PF_VFPF_INT_ENA_W1SX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_MBOX_PF_VFPF1_INTX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_MBOX_PF_VFPF1_INT_ENA_W1SX(1), INTR_MASK(vfs - 64));
+
+	rvupf_write64(rvu, RVU_PF_VFFLR_INTX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1SX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1SX(1), INTR_MASK(vfs - 64));
+}
+
+int rvu_alloc_cint_qint_mem(struct rvu *rvu, struct rvu_pfvf *pfvf,
+			    int blkaddr, int nixlf)
+{
+	int qints, hwctx_size, err;
+	u64 cfg, ctx_cfg;
+
+	if (is_rvu_otx2(rvu) || is_cn20k(rvu->pdev))
+		return 0;
+
+	ctx_cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST3);
+	/* Alloc memory for CQINT's HW contexts */
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST2);
+	qints = (cfg >> 24) & 0xFFF;
+	hwctx_size = 1UL << ((ctx_cfg >> 24) & 0xF);
+	err = qmem_alloc(rvu->dev, &pfvf->cq_ints_ctx, qints, hwctx_size);
+	if (err)
+		return -ENOMEM;
+
+	rvu_write64(rvu, blkaddr, NIX_AF_LFX_CINTS_BASE(nixlf),
+		    (u64)pfvf->cq_ints_ctx->iova);
+
+	/* Alloc memory for QINT's HW contexts */
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST2);
+	qints = (cfg >> 12) & 0xFFF;
+	hwctx_size = 1UL << ((ctx_cfg >> 20) & 0xF);
+	err = qmem_alloc(rvu->dev, &pfvf->nix_qints_ctx, qints, hwctx_size);
+	if (err)
+		return -ENOMEM;
+
+	rvu_write64(rvu, blkaddr, NIX_AF_LFX_QINTS_BASE(nixlf),
+		    (u64)pfvf->nix_qints_ctx->iova);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/nix.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/nix.c
new file mode 100644
index 000000000000..aa2016fd1bba
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/nix.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell RVU Admin Function driver
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include "struct.h"
+#include "../rvu.h"
+
+int rvu_mbox_handler_nix_cn20k_aq_enq(struct rvu *rvu,
+				      struct nix_cn20k_aq_enq_req *req,
+				      struct nix_cn20k_aq_enq_rsp *rsp)
+{
+	return rvu_nix_aq_enq_inst(rvu, (struct nix_aq_enq_req *)req,
+				  (struct nix_aq_enq_rsp *)rsp);
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c
new file mode 100644
index 000000000000..fe8f926c8b75
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell RVU Admin Function driver
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include "struct.h"
+#include "../rvu.h"
+
+int rvu_mbox_handler_npa_cn20k_aq_enq(struct rvu *rvu,
+				      struct npa_cn20k_aq_enq_req *req,
+				      struct npa_cn20k_aq_enq_rsp *rsp)
+{
+	return rvu_npa_aq_enq_inst(rvu, (struct npa_aq_enq_req *)req,
+				   (struct npa_aq_enq_rsp *)rsp);
+}
+EXPORT_SYMBOL(rvu_mbox_handler_npa_cn20k_aq_enq);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/reg.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/reg.h
new file mode 100644
index 000000000000..affb39803120
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/reg.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell RVU Admin Function driver
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#ifndef RVU_MBOX_REG_H
+#define RVU_MBOX_REG_H
+#include "../rvu.h"
+#include "../rvu_reg.h"
+
+/* RVUM block registers */
+#define RVU_PF_DISC				(0x0)
+#define RVU_PRIV_PFX_DISC(a)			(0x8000208 | (a) << 16)
+#define RVU_PRIV_HWVFX_DISC(a)			(0xD000000 | (a) << 12)
+
+/* Mbox Registers */
+/* RVU AF BAR0 Mbox registers for AF => PFx */
+#define RVU_MBOX_AF_PFX_ADDR(a)			(0x5000 | (a) << 4)
+#define RVU_MBOX_AF_PFX_CFG(a)			(0x6000 | (a) << 4)
+#define RVU_MBOX_AF_AFPFX_TRIGX(a)		(0x9000 | (a) << 3)
+#define RVU_MBOX_AF_PFAF_INT(a)			(0x2980 | (a) << 6)
+#define RVU_MBOX_AF_PFAF_INT_W1S(a)		(0x2988 | (a) << 6)
+#define RVU_MBOX_AF_PFAF_INT_ENA_W1S(a)		(0x2990 | (a) << 6)
+#define RVU_MBOX_AF_PFAF_INT_ENA_W1C(a)		(0x2998 | (a) << 6)
+#define RVU_MBOX_AF_PFAF1_INT(a)		(0x29A0 | (a) << 6)
+#define RVU_MBOX_AF_PFAF1_INT_W1S(a)		(0x29A8 | (a) << 6)
+#define RVU_MBOX_AF_PFAF1_INT_ENA_W1S(a)	(0x29B0 | (a) << 6)
+#define RVU_MBOX_AF_PFAF1_INT_ENA_W1C(a)	(0x29B8 | (a) << 6)
+
+/* RVU PF => AF mbox registers */
+#define RVU_MBOX_PF_PFAF_TRIGX(a)		(0xC00 | (a) << 3)
+#define RVU_MBOX_PF_INT				(0xC20)
+#define RVU_MBOX_PF_INT_W1S			(0xC28)
+#define RVU_MBOX_PF_INT_ENA_W1S			(0xC30)
+#define RVU_MBOX_PF_INT_ENA_W1C			(0xC38)
+
+#define RVU_AF_BAR2_SEL				(0x9000000)
+#define RVU_AF_BAR2_PFID			(0x16400)
+#define NIX_CINTX_INT_W1S(a)			(0xd30 | (a) << 12)
+#define NIX_QINTX_CNT(a)			(0xc00 | (a) << 12)
+
+#define RVU_MBOX_AF_VFAF_INT(a)			(0x3000 | (a) << 6)
+#define RVU_MBOX_AF_VFAF_INT_W1S(a)		(0x3008 | (a) << 6)
+#define RVU_MBOX_AF_VFAF_INT_ENA_W1S(a)		(0x3010 | (a) << 6)
+#define RVU_MBOX_AF_VFAF_INT_ENA_W1C(a)		(0x3018 | (a) << 6)
+#define RVU_MBOX_AF_VFAF_INT_ENA_W1C(a)		(0x3018 | (a) << 6)
+#define RVU_MBOX_AF_VFAF1_INT(a)		(0x3020 | (a) << 6)
+#define RVU_MBOX_AF_VFAF1_INT_W1S(a)		(0x3028 | (a) << 6)
+#define RVU_MBOX_AF_VFAF1_IN_ENA_W1S(a)		(0x3030 | (a) << 6)
+#define RVU_MBOX_AF_VFAF1_IN_ENA_W1C(a)		(0x3038 | (a) << 6)
+
+#define RVU_MBOX_AF_AFVFX_TRIG(a, b)		(0x10000 | (a) << 4 | (b) << 3)
+#define RVU_MBOX_AF_VFX_ADDR(a)			(0x20000 | (a) << 4)
+#define RVU_MBOX_AF_VFX_CFG(a)			(0x28000 | (a) << 4)
+
+#define RVU_MBOX_PF_VFX_PFVF_TRIGX(a)		(0x2000 | (a) << 3)
+
+#define RVU_MBOX_PF_VFPF_INTX(a)		(0x1000 | (a) << 3)
+#define RVU_MBOX_PF_VFPF_INT_W1SX(a)		(0x1020 | (a) << 3)
+#define RVU_MBOX_PF_VFPF_INT_ENA_W1SX(a)	(0x1040 | (a) << 3)
+#define RVU_MBOX_PF_VFPF_INT_ENA_W1CX(a)	(0x1060 | (a) << 3)
+
+#define RVU_MBOX_PF_VFPF1_INTX(a)		(0x1080 | (a) << 3)
+#define RVU_MBOX_PF_VFPF1_INT_W1SX(a)		(0x10a0 | (a) << 3)
+#define RVU_MBOX_PF_VFPF1_INT_ENA_W1SX(a)	(0x10c0 | (a) << 3)
+#define RVU_MBOX_PF_VFPF1_INT_ENA_W1CX(a)	(0x10e0 | (a) << 3)
+
+#define RVU_MBOX_PF_VF_ADDR			(0xC40)
+#define RVU_MBOX_PF_LMTLINE_ADDR		(0xC48)
+#define RVU_MBOX_PF_VF_CFG			(0xC60)
+
+#define RVU_MBOX_VF_VFPF_TRIGX(a)		(0x3000 | (a) << 3)
+#define RVU_MBOX_VF_INT				(0x20)
+#define RVU_MBOX_VF_INT_W1S			(0x28)
+#define RVU_MBOX_VF_INT_ENA_W1S			(0x30)
+#define RVU_MBOX_VF_INT_ENA_W1C			(0x38)
+
+#define RVU_MBOX_VF_VFAF_TRIGX(a)		(0x2000 | (a) << 3)
+#endif /* RVU_MBOX_REG_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h
new file mode 100644
index 000000000000..763f6cabd7c2
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h
@@ -0,0 +1,380 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell RVU Admin Function driver
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#ifndef STRUCT_H
+#define STRUCT_H
+
+#define NIX_MAX_CTX_SIZE		128
+
+/*
+ * CN20k RVU PF MBOX Interrupt Vector Enumeration
+ *
+ * Vectors 0 - 3 are compatible with pre cn20k and hence
+ * existing macros are being reused.
+ */
+enum rvu_mbox_pf_int_vec_e {
+	RVU_MBOX_PF_INT_VEC_VFPF_MBOX0	= 0x4,
+	RVU_MBOX_PF_INT_VEC_VFPF_MBOX1	= 0x5,
+	RVU_MBOX_PF_INT_VEC_VFPF1_MBOX0	= 0x6,
+	RVU_MBOX_PF_INT_VEC_VFPF1_MBOX1	= 0x7,
+	RVU_MBOX_PF_INT_VEC_AFPF_MBOX	= 0x8,
+	RVU_MBOX_PF_INT_VEC_CNT		= 0x9,
+};
+
+/* RVU Admin function Interrupt Vector Enumeration */
+enum rvu_af_cn20k_int_vec_e {
+	RVU_AF_CN20K_INT_VEC_POISON		= 0x0,
+	RVU_AF_CN20K_INT_VEC_PFFLR0		= 0x1,
+	RVU_AF_CN20K_INT_VEC_PFFLR1		= 0x2,
+	RVU_AF_CN20K_INT_VEC_PFME0		= 0x3,
+	RVU_AF_CN20K_INT_VEC_PFME1		= 0x4,
+	RVU_AF_CN20K_INT_VEC_GEN		= 0x5,
+	RVU_AF_CN20K_INT_VEC_PFAF_MBOX0		= 0x6,
+	RVU_AF_CN20K_INT_VEC_PFAF_MBOX1		= 0x7,
+	RVU_AF_CN20K_INT_VEC_PFAF1_MBOX0	= 0x8,
+	RVU_AF_CN20K_INT_VEC_PFAF1_MBOX1	= 0x9,
+	RVU_AF_CN20K_INT_VEC_CNT		= 0xa,
+};
+
+struct nix_cn20k_sq_ctx_s {
+	u64 ena                         :  1; /* W0 */
+	u64 qint_idx                    :  6;
+	u64 substream                   : 20;
+	u64 sdp_mcast                   :  1;
+	u64 cq                          : 20;
+	u64 sqe_way_mask                : 16;
+	u64 smq                         : 11; /* W1 */
+	u64 cq_ena                      :  1;
+	u64 xoff                        :  1;
+	u64 sso_ena                     :  1;
+	u64 smq_rr_weight               : 14;
+	u64 default_chan                : 12;
+	u64 sqb_count                   : 16;
+	u64 reserved_120_120            :  1;
+	u64 smq_rr_count_lb             :  7;
+	u64 smq_rr_count_ub             : 25; /* W2 */
+	u64 sqb_aura                    : 20;
+	u64 sq_int                      :  8;
+	u64 sq_int_ena                  :  8;
+	u64 sqe_stype                   :  2;
+	u64 reserved_191_191            :  1;
+	u64 max_sqe_size                :  2; /* W3 */
+	u64 cq_limit                    :  8;
+	u64 lmt_dis                     :  1;
+	u64 mnq_dis                     :  1;
+	u64 smq_next_sq                 : 20;
+	u64 smq_lso_segnum              :  8;
+	u64 tail_offset                 :  6;
+	u64 smenq_offset                :  6;
+	u64 head_offset                 :  6;
+	u64 smenq_next_sqb_vld          :  1;
+	u64 smq_pend                    :  1;
+	u64 smq_next_sq_vld             :  1;
+	u64 reserved_253_255            :  3;
+	u64 next_sqb                    : 64; /* W4 */
+	u64 tail_sqb                    : 64; /* W5 */
+	u64 smenq_sqb                   : 64; /* W6 */
+	u64 smenq_next_sqb              : 64; /* W7 */
+	u64 head_sqb                    : 64; /* W8 */
+	u64 reserved_576_583            :  8; /* W9 */
+	u64 vfi_lso_total               : 18;
+	u64 vfi_lso_sizem1              :  3;
+	u64 vfi_lso_sb                  :  8;
+	u64 vfi_lso_mps                 : 14;
+	u64 vfi_lso_vlan0_ins_ena       :  1;
+	u64 vfi_lso_vlan1_ins_ena       :  1;
+	u64 vfi_lso_vld                 :  1;
+	u64 reserved_630_639            : 10;
+	u64 scm_lso_rem                 : 18; /* W10 */
+	u64 reserved_658_703            : 46;
+	u64 octs                        : 48; /* W11 */
+	u64 reserved_752_767            : 16;
+	u64 pkts                        : 48; /* W12 */
+	u64 reserved_816_831            : 16;
+	u64 aged_drop_octs              : 32; /* W13 */
+	u64 aged_drop_pkts              : 32;
+	u64 dropped_octs                : 48; /* W14 */
+	u64 reserved_944_959            : 16;
+	u64 dropped_pkts                : 48; /* W15 */
+	u64 reserved_1008_1023          : 16;
+};
+
+static_assert(sizeof(struct nix_cn20k_sq_ctx_s) == NIX_MAX_CTX_SIZE);
+
+struct nix_cn20k_cq_ctx_s {
+	u64 base                        : 64; /* W0 */
+	u64 lbp_ena                     :  1; /* W1 */
+	u64 lbpid_low                   :  3;
+	u64 bp_ena                      :  1;
+	u64 lbpid_med                   :  3;
+	u64 bpid                        :  9;
+	u64 lbpid_high                  :  3;
+	u64 qint_idx                    :  7;
+	u64 cq_err                      :  1;
+	u64 cint_idx                    :  7;
+	u64 avg_con                     :  9;
+	u64 wrptr                       : 20;
+	u64 tail                        : 20; /* W2 */
+	u64 head                        : 20;
+	u64 avg_level                   :  8;
+	u64 update_time                 : 16;
+	u64 bp                          :  8; /* W3 */
+	u64 drop                        :  8;
+	u64 drop_ena                    :  1;
+	u64 ena                         :  1;
+	u64 cpt_drop_err_en             :  1;
+	u64 reserved_211_211            :  1;
+	u64 msh_dst                     : 11;
+	u64 msh_valid                   :  1;
+	u64 stash_thresh                :  4;
+	u64 lbp_frac                    :  4;
+	u64 caching                     :  1;
+	u64 stashing                    :  1;
+	u64 reserved_234_235            :  2;
+	u64 qsize                       :  4;
+	u64 cq_err_int                  :  8;
+	u64 cq_err_int_ena              :  8;
+	u64 bpid_ext                    :  2; /* W4 */
+	u64 reserved_258_259            :  2;
+	u64 lbpid_ext                   :  2;
+	u64 reserved_262_319            : 58;
+	u64 reserved_320_383            : 64; /* W5 */
+	u64 reserved_384_447            : 64; /* W6 */
+	u64 reserved_448_511            : 64; /* W7 */
+	u64 padding[8];
+};
+
+static_assert(sizeof(struct nix_cn20k_sq_ctx_s) == NIX_MAX_CTX_SIZE);
+
+struct nix_cn20k_rq_ctx_s {
+	u64 ena                         :  1;
+	u64 sso_ena                     :  1;
+	u64 ipsech_ena                  :  1;
+	u64 ena_wqwd                    :  1;
+	u64 cq                          : 20;
+	u64 reserved_24_34              : 11;
+	u64 port_il4_dis                :  1;
+	u64 port_ol4_dis                :  1;
+	u64 lenerr_dis                  :  1;
+	u64 csum_il4_dis                :  1;
+	u64 csum_ol4_dis                :  1;
+	u64 len_il4_dis                 :  1;
+	u64 len_il3_dis                 :  1;
+	u64 len_ol4_dis                 :  1;
+	u64 len_ol3_dis                 :  1;
+	u64 wqe_aura                    : 20;
+	u64 spb_aura                    : 20;
+	u64 lpb_aura                    : 20;
+	u64 sso_grp                     : 10;
+	u64 sso_tt                      :  2;
+	u64 pb_caching                  :  2;
+	u64 wqe_caching                 :  1;
+	u64 xqe_drop_ena                :  1;
+	u64 spb_drop_ena                :  1;
+	u64 lpb_drop_ena                :  1;
+	u64 pb_stashing                 :  1;
+	u64 ipsecd_drop_en              :  1;
+	u64 chi_ena                     :  1;
+	u64 reserved_125_127            :  3;
+	u64 band_prof_id_l              : 10;
+	u64 sso_fc_ena                  :  1;
+	u64 policer_ena                 :  1;
+	u64 spb_sizem1                  :  6;
+	u64 wqe_skip                    :  2;
+	u64 spb_high_sizem1             :  3;
+	u64 spb_ena                     :  1;
+	u64 lpb_sizem1                  : 12;
+	u64 first_skip                  :  7;
+	u64 reserved_171_171            :  1;
+	u64 later_skip                  :  6;
+	u64 xqe_imm_size                :  6;
+	u64 band_prof_id_h              :  4;
+	u64 reserved_188_189            :  2;
+	u64 xqe_imm_copy                :  1;
+	u64 xqe_hdr_split               :  1;
+	u64 xqe_drop                    :  8;
+	u64 xqe_pass                    :  8;
+	u64 wqe_pool_drop               :  8;
+	u64 wqe_pool_pass               :  8;
+	u64 spb_aura_drop               :  8;
+	u64 spb_aura_pass               :  8;
+	u64 spb_pool_drop               :  8;
+	u64 spb_pool_pass               :  8;
+	u64 lpb_aura_drop               :  8;
+	u64 lpb_aura_pass               :  8;
+	u64 lpb_pool_drop               :  8;
+	u64 lpb_pool_pass               :  8;
+	u64 reserved_288_291            :  4;
+	u64 rq_int                      :  8;
+	u64 rq_int_ena                  :  8;
+	u64 qint_idx                    :  7;
+	u64 reserved_315_319            :  5;
+	u64 ltag                        : 24;
+	u64 good_utag                   :  8;
+	u64 bad_utag                    :  8;
+	u64 flow_tagw                   :  6;
+	u64 ipsec_vwqe                  :  1;
+	u64 vwqe_ena                    :  1;
+	u64 vtime_wait                  :  8;
+	u64 max_vsize_exp               :  4;
+	u64 vwqe_skip                   :  2;
+	u64 reserved_382_383            :  2;
+	u64 octs                        : 48;
+	u64 reserved_432_447            : 16;
+	u64 pkts                        : 48;
+	u64 reserved_496_511            : 16;
+	u64 drop_octs                   : 48;
+	u64 reserved_560_575            : 16;
+	u64 drop_pkts                   : 48;
+	u64 reserved_624_639            : 16;
+	u64 re_pkts                     : 48;
+	u64 reserved_688_703            : 16;
+	u64 reserved_704_767            : 64;
+	u64 reserved_768_831            : 64;
+	u64 reserved_832_895            : 64;
+	u64 reserved_896_959            : 64;
+	u64 reserved_960_1023           : 64;
+};
+
+static_assert(sizeof(struct nix_cn20k_rq_ctx_s) == NIX_MAX_CTX_SIZE);
+
+struct npa_cn20k_aura_s {
+	u64 pool_addr;			/* W0 */
+	u64 ena                   : 1;  /* W1 */
+	u64 reserved_65           : 2;
+	u64 pool_caching          : 1;
+	u64 reserved_68           : 16;
+	u64 avg_con               : 9;
+	u64 reserved_93           : 1;
+	u64 pool_drop_ena         : 1;
+	u64 aura_drop_ena         : 1;
+	u64 bp_ena                : 1;
+	u64 reserved_97_103       : 7;
+	u64 aura_drop             : 8;
+	u64 shift                 : 6;
+	u64 reserved_118_119      : 2;
+	u64 avg_level             : 8;
+	u64 count                 : 36; /* W2 */
+	u64 reserved_164_167      : 4;
+	u64 bpid                  : 12;
+	u64 reserved_180_191      : 12;
+	u64 limit                 : 36; /* W3 */
+	u64 reserved_228_231      : 4;
+	u64 bp                    : 7;
+	u64 reserved_239_243      : 5;
+	u64 fc_ena                : 1;
+	u64 fc_up_crossing        : 1;
+	u64 fc_stype              : 2;
+	u64 fc_hyst_bits          : 4;
+	u64 reserved_252_255      : 4;
+	u64 fc_addr;			/* W4 */
+	u64 pool_drop             : 8;  /* W5 */
+	u64 update_time           : 16;
+	u64 err_int               : 8;
+	u64 err_int_ena           : 8;
+	u64 thresh_int            : 1;
+	u64 thresh_int_ena        : 1;
+	u64 thresh_up             : 1;
+	u64 reserved_363          : 1;
+	u64 thresh_qint_idx       : 7;
+	u64 reserved_371          : 1;
+	u64 err_qint_idx          : 7;
+	u64 reserved_379_383      : 5;
+	u64 thresh                : 36; /* W6*/
+	u64 rsvd_423_420          : 4;
+	u64 fc_msh_dst            : 11;
+	u64 reserved_435_438      : 4;
+	u64 op_dpc_ena            : 1;
+	u64 op_dpc_set            : 5;
+	u64 reserved_445_445      : 1;
+	u64 stream_ctx            : 1;
+	u64 unified_ctx           : 1;
+	u64 reserved_448_511;		/* W7 */
+	u64 padding[8];
+};
+
+static_assert(sizeof(struct npa_cn20k_aura_s) == NIX_MAX_CTX_SIZE);
+
+struct npa_cn20k_pool_s {
+	u64 stack_base;			/* W0 */
+	u64 ena                   : 1;
+	u64 nat_align             : 1;
+	u64 reserved_66_67        : 2;
+	u64 stack_caching         : 1;
+	u64 reserved_69_87        : 19;
+	u64 buf_offset            : 12;
+	u64 reserved_100_103      : 4;
+	u64 buf_size              : 12;
+	u64 reserved_116_119      : 4;
+	u64 ref_cnt_prof          : 3;
+	u64 reserved_123_127      : 5;
+	u64 stack_max_pages       : 32;
+	u64 stack_pages           : 32;
+	uint64_t bp_0             : 7;
+	uint64_t bp_1             : 7;
+	uint64_t bp_2             : 7;
+	uint64_t bp_3             : 7;
+	uint64_t bp_4             : 7;
+	uint64_t bp_5             : 7;
+	uint64_t bp_6             : 7;
+	uint64_t bp_7             : 7;
+	uint64_t bp_ena_0         : 1;
+	uint64_t bp_ena_1         : 1;
+	uint64_t bp_ena_2         : 1;
+	uint64_t bp_ena_3         : 1;
+	uint64_t bp_ena_4         : 1;
+	uint64_t bp_ena_5         : 1;
+	uint64_t bp_ena_6         : 1;
+	uint64_t bp_ena_7         : 1;
+	u64 stack_offset          : 4;
+	u64 reserved_260_263      : 4;
+	u64 shift                 : 6;
+	u64 reserved_270_271      : 2;
+	u64 avg_level             : 8;
+	u64 avg_con               : 9;
+	u64 fc_ena                : 1;
+	u64 fc_stype              : 2;
+	u64 fc_hyst_bits          : 4;
+	u64 fc_up_crossing        : 1;
+	u64 reserved_297_299      : 3;
+	u64 update_time           : 16;
+	u64 reserved_316_319      : 4;
+	u64 fc_addr;			/* W5 */
+	u64 ptr_start;			/* W6 */
+	u64 ptr_end;			/* W7 */
+	u64 bpid_0                : 12;
+	u64 reserved_524_535      : 12;
+	u64 err_int               : 8;
+	u64 err_int_ena           : 8;
+	u64 thresh_int            : 1;
+	u64 thresh_int_ena        : 1;
+	u64 thresh_up             : 1;
+	u64 reserved_555          : 1;
+	u64 thresh_qint_idx       : 7;
+	u64 reserved_563          : 1;
+	u64 err_qint_idx          : 7;
+	u64 reserved_571_575      : 5;
+	u64 thresh                : 36;
+	u64 rsvd_612_615	  : 4;
+	u64 fc_msh_dst		  : 11;
+	u64 reserved_627_630      : 4;
+	u64 op_dpc_ena            : 1;
+	u64 op_dpc_set            : 5;
+	u64 reserved_637_637      : 1;
+	u64 stream_ctx            : 1;
+	u64 reserved_639          : 1;
+	u64 reserved_640_703;		/* W10 */
+	u64 reserved_704_767;		/* W11 */
+	u64 reserved_768_831;		/* W12 */
+	u64 reserved_832_895;		/* W13 */
+	u64 reserved_896_959;		/* W14 */
+	u64 reserved_960_1023;		/* W15 */
+};
+
+static_assert(sizeof(struct npa_cn20k_pool_s) == NIX_MAX_CTX_SIZE);
+
+#endif
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index 406c59100a35..8a08bebf08c2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -39,7 +39,7 @@ struct qmem {
 	void            *base;
 	dma_addr_t	iova;
 	int		alloc_sz;
-	u16		entry_sz;
+	u32		entry_sz;
 	u8		align;
 	u32		qsize;
 };
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
index 1e5aa5397504..75872d257eca 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
@@ -10,8 +10,11 @@
 #include <linux/pci.h>
 
 #include "rvu_reg.h"
+#include "cn20k/reg.h"
+#include "cn20k/api.h"
 #include "mbox.h"
 #include "rvu_trace.h"
+#include "rvu.h"
 
 static const u16 msgs_offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
 
@@ -28,8 +31,10 @@ void __otx2_mbox_reset(struct otx2_mbox *mbox, int devid)
 	mdev->rsp_size = 0;
 	tx_hdr->num_msgs = 0;
 	tx_hdr->msg_size = 0;
+	tx_hdr->sig = 0;
 	rx_hdr->num_msgs = 0;
 	rx_hdr->msg_size = 0;
+	rx_hdr->sig = 0;
 }
 EXPORT_SYMBOL(__otx2_mbox_reset);
 
@@ -53,9 +58,98 @@ void otx2_mbox_destroy(struct otx2_mbox *mbox)
 }
 EXPORT_SYMBOL(otx2_mbox_destroy);
 
+int cn20k_mbox_setup(struct otx2_mbox *mbox, struct pci_dev *pdev,
+		     void *reg_base, int direction, int ndevs)
+{
+	switch (direction) {
+	case MBOX_DIR_AFPF:
+	case MBOX_DIR_PFVF:
+		mbox->tx_start = MBOX_DOWN_TX_START;
+		mbox->rx_start = MBOX_DOWN_RX_START;
+		mbox->tx_size  = MBOX_DOWN_TX_SIZE;
+		mbox->rx_size  = MBOX_DOWN_RX_SIZE;
+		break;
+	case MBOX_DIR_PFAF:
+	case MBOX_DIR_VFPF:
+		mbox->tx_start = MBOX_DOWN_RX_START;
+		mbox->rx_start = MBOX_DOWN_TX_START;
+		mbox->tx_size  = MBOX_DOWN_RX_SIZE;
+		mbox->rx_size  = MBOX_DOWN_TX_SIZE;
+		break;
+	case MBOX_DIR_AFPF_UP:
+	case MBOX_DIR_PFVF_UP:
+		mbox->tx_start = MBOX_UP_TX_START;
+		mbox->rx_start = MBOX_UP_RX_START;
+		mbox->tx_size  = MBOX_UP_TX_SIZE;
+		mbox->rx_size  = MBOX_UP_RX_SIZE;
+		break;
+	case MBOX_DIR_PFAF_UP:
+	case MBOX_DIR_VFPF_UP:
+		mbox->tx_start = MBOX_UP_RX_START;
+		mbox->rx_start = MBOX_UP_TX_START;
+		mbox->tx_size  = MBOX_UP_RX_SIZE;
+		mbox->rx_size  = MBOX_UP_TX_SIZE;
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	switch (direction) {
+	case MBOX_DIR_AFPF:
+		mbox->trigger = RVU_MBOX_AF_AFPFX_TRIGX(1);
+		mbox->tr_shift = 4;
+		break;
+	case MBOX_DIR_AFPF_UP:
+		mbox->trigger = RVU_MBOX_AF_AFPFX_TRIGX(0);
+		mbox->tr_shift = 4;
+		break;
+	case MBOX_DIR_PFAF:
+		mbox->trigger = RVU_MBOX_PF_PFAF_TRIGX(0);
+		mbox->tr_shift = 0;
+		break;
+	case MBOX_DIR_PFAF_UP:
+		mbox->trigger = RVU_MBOX_PF_PFAF_TRIGX(1);
+		mbox->tr_shift = 0;
+		break;
+	case MBOX_DIR_PFVF:
+		mbox->trigger = RVU_MBOX_PF_VFX_PFVF_TRIGX(1);
+		mbox->tr_shift = 4;
+		break;
+	case MBOX_DIR_PFVF_UP:
+		mbox->trigger = RVU_MBOX_PF_VFX_PFVF_TRIGX(0);
+		mbox->tr_shift = 4;
+		break;
+	case MBOX_DIR_VFPF:
+		mbox->trigger = RVU_MBOX_VF_VFPF_TRIGX(0);
+		mbox->tr_shift = 0;
+		break;
+	case MBOX_DIR_VFPF_UP:
+		mbox->trigger = RVU_MBOX_VF_VFPF_TRIGX(1);
+		mbox->tr_shift = 0;
+		break;
+	default:
+		return -ENODEV;
+	}
+	mbox->reg_base = reg_base;
+	mbox->pdev = pdev;
+
+	mbox->dev = kcalloc(ndevs, sizeof(struct otx2_mbox_dev), GFP_KERNEL);
+	if (!mbox->dev) {
+		otx2_mbox_destroy(mbox);
+		return -ENOMEM;
+	}
+	mbox->ndevs = ndevs;
+
+	return 0;
+}
+
 static int otx2_mbox_setup(struct otx2_mbox *mbox, struct pci_dev *pdev,
 			   void *reg_base, int direction, int ndevs)
 {
+	if (is_cn20k(pdev))
+		return cn20k_mbox_setup(mbox, pdev, reg_base,
+							direction, ndevs);
+
 	switch (direction) {
 	case MBOX_DIR_AFPF:
 	case MBOX_DIR_PFVF:
@@ -188,14 +282,13 @@ int otx2_mbox_wait_for_rsp(struct otx2_mbox *mbox, int devid)
 {
 	unsigned long timeout = jiffies + msecs_to_jiffies(MBOX_RSP_TIMEOUT);
 	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
-	struct device *sender = &mbox->pdev->dev;
 
 	while (!time_after(jiffies, timeout)) {
 		if (mdev->num_msgs == mdev->msgs_acked)
 			return 0;
 		usleep_range(800, 1000);
 	}
-	dev_dbg(sender, "timed out while waiting for rsp\n");
+	trace_otx2_msg_wait_rsp(mbox->pdev);
 	return -EIO;
 }
 EXPORT_SYMBOL(otx2_mbox_wait_for_rsp);
@@ -219,6 +312,7 @@ static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data)
 	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
 	struct mbox_hdr *tx_hdr, *rx_hdr;
 	void *hw_mbase = mdev->hwbase;
+	struct mbox_msghdr *msg;
 	u64 intr_val;
 
 	tx_hdr = hw_mbase + mbox->tx_start;
@@ -234,7 +328,10 @@ static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data)
 
 	spin_lock(&mdev->mbox_lock);
 
-	tx_hdr->msg_size = mdev->msg_size;
+	if (!tx_hdr->sig) {
+		tx_hdr->msg_size = mdev->msg_size;
+		tx_hdr->num_msgs = mdev->num_msgs;
+	}
 
 	/* Reset header for next messages */
 	mdev->msg_size = 0;
@@ -248,10 +345,12 @@ static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data)
 	 * messages.  So this should be written after writing all the messages
 	 * to the shared memory.
 	 */
-	tx_hdr->num_msgs = mdev->num_msgs;
 	rx_hdr->num_msgs = 0;
 
-	trace_otx2_msg_send(mbox->pdev, tx_hdr->num_msgs, tx_hdr->msg_size);
+	msg = (struct mbox_msghdr *)(hw_mbase + mbox->tx_start + msgs_offset);
+
+	trace_otx2_msg_send(mbox->pdev, tx_hdr->num_msgs, tx_hdr->msg_size,
+			    msg->id, msg->pcifunc);
 
 	spin_unlock(&mdev->mbox_lock);
 
@@ -306,6 +405,7 @@ struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid,
 {
 	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
 	struct mbox_msghdr *msghdr = NULL;
+	struct mbox_hdr *mboxhdr = NULL;
 
 	spin_lock(&mdev->mbox_lock);
 	size = ALIGN(size, MBOX_MSG_ALIGN);
@@ -329,6 +429,11 @@ struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid,
 	mdev->msg_size += size;
 	mdev->rsp_size += size_rsp;
 	msghdr->next_msgoff = mdev->msg_size + msgs_offset;
+
+	mboxhdr = mdev->mbase + mbox->tx_start;
+	/* Clear the msg header region */
+	memset(mboxhdr, 0, msgs_offset);
+
 exit:
 	spin_unlock(&mdev->mbox_lock);
 
@@ -445,6 +550,14 @@ const char *otx2_mbox_id2name(u16 id)
 #define M(_name, _id, _1, _2, _3) case _id: return # _name;
 	MBOX_MESSAGES
 #undef M
+
+#define M(_name, _id, _1, _2, _3) case _id: return # _name;
+	MBOX_UP_CGX_MESSAGES
+#undef M
+
+#define M(_name, _id, _1, _2, _3) case _id: return # _name;
+	MBOX_UP_CPT_MESSAGES
+#undef M
 	default:
 		return "INVALID ID";
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 005ca8a056c0..a3e273126e4e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -10,9 +10,11 @@
 
 #include <linux/etherdevice.h>
 #include <linux/sizes.h>
+#include <linux/ethtool.h>
 
 #include "rvu_struct.h"
 #include "common.h"
+#include "cn20k/struct.h"
 
 #define MBOX_SIZE		SZ_64K
 
@@ -50,6 +52,11 @@
 #define MBOX_DIR_PFVF_UP	6  /* PF sends messages to VF */
 #define MBOX_DIR_VFPF_UP	7  /* VF replies to PF */
 
+enum {
+	TYPE_AFVF,
+	TYPE_AFPF,
+};
+
 struct otx2_mbox_dev {
 	void	    *mbase;   /* This dev's mbox region */
 	void	    *hwbase;
@@ -78,6 +85,8 @@ struct otx2_mbox {
 struct mbox_hdr {
 	u64 msg_size;	/* Total msgs size embedded */
 	u16  num_msgs;   /* No of msgs embedded */
+	u16 opt_msg;
+	u8 sig;
 };
 
 /* Header which precedes every msg and is also part of it */
@@ -194,6 +203,8 @@ M(NPA_LF_ALLOC,		0x400, npa_lf_alloc,				\
 M(NPA_LF_FREE,		0x401, npa_lf_free, msg_req, msg_rsp)		\
 M(NPA_AQ_ENQ,		0x402, npa_aq_enq, npa_aq_enq_req, npa_aq_enq_rsp)   \
 M(NPA_HWCTX_DISABLE,	0x403, npa_hwctx_disable, hwctx_disable_req, msg_rsp)\
+M(NPA_CN20K_AQ_ENQ,	0x404, npa_cn20k_aq_enq, npa_cn20k_aq_enq_req,	\
+				npa_cn20k_aq_enq_rsp)			\
 /* SSO/SSOW mbox IDs (range 0x600 - 0x7FF) */				\
 /* TIM mbox IDs (range 0x800 - 0x9FF) */				\
 /* CPT mbox IDs (range 0xA00 - 0xBFF) */				\
@@ -327,6 +338,8 @@ M(NIX_MCAST_GRP_UPDATE, 0x802d, nix_mcast_grp_update,				\
 				nix_mcast_grp_update_req,			\
 				nix_mcast_grp_update_rsp)			\
 M(NIX_LF_STATS, 0x802e, nix_lf_stats, nix_stats_req, nix_stats_rsp)	\
+M(NIX_CN20K_AQ_ENQ,	0x802f, nix_cn20k_aq_enq, nix_cn20k_aq_enq_req,		\
+				nix_cn20k_aq_enq_rsp)				\
 /* MCS mbox IDs (range 0xA000 - 0xBFFF) */					\
 M(MCS_ALLOC_RESOURCES,	0xa000, mcs_alloc_resources, mcs_alloc_rsrc_req,	\
 				mcs_alloc_rsrc_rsp)				\
@@ -524,6 +537,8 @@ struct get_hw_cap_rsp {
 	u8 nix_fixed_txschq_mapping; /* Schq mapping fixed or flexible */
 	u8 nix_shaping;		     /* Is shaping and coloring supported */
 	u8 npc_hash_extract;	/* Is hash extract supported */
+#define HW_CAP_MACSEC		BIT_ULL(1)
+	u64 hw_caps;
 };
 
 /* CGX mbox message formats */
@@ -648,11 +663,17 @@ struct cgx_lmac_fwdata_s {
 	u64 supported_link_modes;
 	/* only applicable if AN is supported */
 	u64 advertised_fec;
-	u64 advertised_link_modes;
+	u64 advertised_link_modes_own:1; /* CGX_CMD_OWN */
+	u64 advertised_link_modes:63;
 	/* Only applicable if SFP/QSFP slot is present */
 	struct sfp_eeprom_s sfp_eeprom;
 	struct phy_s phy;
-#define LMAC_FWDATA_RESERVED_MEM 1021
+	u32 lmac_type;
+	u32 portm_idx;
+	u64 mgmt_port:1;
+	u64 advertised_an:1;
+	u64 port;
+#define LMAC_FWDATA_RESERVED_MEM 1018
 	u64 reserved[LMAC_FWDATA_RESERVED_MEM];
 };
 
@@ -665,12 +686,13 @@ struct cgx_set_link_mode_args {
 	u32 speed;
 	u8 duplex;
 	u8 an;
-	u8 ports;
+	u8 mode_baseidx;
+	u8 multimode;
 	u64 mode;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
 };
 
 struct cgx_set_link_mode_req {
-#define AUTONEG_UNKNOWN		0xff
 	struct mbox_msghdr hdr;
 	struct cgx_set_link_mode_args args;
 };
@@ -814,6 +836,39 @@ struct npa_aq_enq_rsp {
 	};
 };
 
+struct npa_cn20k_aq_enq_req {
+	struct mbox_msghdr hdr;
+	u32 aura_id;
+	u8 ctype;
+	u8 op;
+	union {
+		/* Valid when op == WRITE/INIT and ctype == AURA.
+		 * LF fills the pool_id in aura.pool_addr. AF will translate
+		 * the pool_id to pool context pointer.
+		 */
+		struct npa_cn20k_aura_s aura;
+		/* Valid when op == WRITE/INIT and ctype == POOL */
+		struct npa_cn20k_pool_s pool;
+	};
+	/* Mask data when op == WRITE (1=write, 0=don't write) */
+	union {
+		/* Valid when op == WRITE and ctype == AURA */
+		struct npa_cn20k_aura_s aura_mask;
+		/* Valid when op == WRITE and ctype == POOL */
+		struct npa_cn20k_pool_s pool_mask;
+	};
+};
+
+struct npa_cn20k_aq_enq_rsp {
+	struct mbox_msghdr hdr;
+	union {
+		/* Valid when op == READ and ctype == AURA */
+		struct npa_cn20k_aura_s aura;
+		/* Valid when op == READ and ctype == POOL */
+		struct npa_cn20k_pool_s pool;
+	};
+};
+
 /* Disable all contexts of type 'ctype' */
 struct hwctx_disable_req {
 	struct mbox_msghdr hdr;
@@ -922,6 +977,42 @@ struct nix_lf_free_req {
 	u64 flags;
 };
 
+/* CN20K NIX AQ enqueue msg */
+struct nix_cn20k_aq_enq_req {
+	struct mbox_msghdr hdr;
+	u32  qidx;
+	u8 ctype;
+	u8 op;
+	union {
+		struct nix_cn20k_rq_ctx_s rq;
+		struct nix_cn20k_sq_ctx_s sq;
+		struct nix_cn20k_cq_ctx_s cq;
+		struct nix_rsse_s   rss;
+		struct nix_rx_mce_s mce;
+		struct nix_bandprof_s prof;
+	};
+	union {
+		struct nix_cn20k_rq_ctx_s rq_mask;
+		struct nix_cn20k_sq_ctx_s sq_mask;
+		struct nix_cn20k_cq_ctx_s cq_mask;
+		struct nix_rsse_s   rss_mask;
+		struct nix_rx_mce_s mce_mask;
+		struct nix_bandprof_s prof_mask;
+	};
+};
+
+struct nix_cn20k_aq_enq_rsp {
+	struct mbox_msghdr hdr;
+	union {
+		struct nix_cn20k_rq_ctx_s rq;
+		struct nix_cn20k_sq_ctx_s sq;
+		struct nix_cn20k_cq_ctx_s cq;
+		struct nix_rsse_s   rss;
+		struct nix_rx_mce_s mce;
+		struct nix_bandprof_s prof;
+	};
+};
+
 /* CN10K NIX AQ enqueue msg */
 struct nix_cn10k_aq_enq_req {
 	struct mbox_msghdr hdr;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
index d39d86e694cc..a80c8e7c94f2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
@@ -97,7 +97,7 @@ int mcs_add_intr_wq_entry(struct mcs *mcs, struct mcs_intr_event *event)
 	if (pcifunc & RVU_PFVF_FUNC_MASK)
 		pfvf = &mcs->vf[rvu_get_hwvf(rvu, pcifunc)];
 	else
-		pfvf = &mcs->pf[rvu_get_pf(pcifunc)];
+		pfvf = &mcs->pf[rvu_get_pf(rvu->pdev, pcifunc)];
 
 	event->intr_mask &= pfvf->intr_mask;
 
@@ -123,7 +123,7 @@ static int mcs_notify_pfvf(struct mcs_intr_event *event, struct rvu *rvu)
 	struct mcs_intr_info *req;
 	int pf;
 
-	pf = rvu_get_pf(event->pcifunc);
+	pf = rvu_get_pf(rvu->pdev, event->pcifunc);
 
 	mutex_lock(&rvu->mbox_lock);
 
@@ -143,6 +143,8 @@ static int mcs_notify_pfvf(struct mcs_intr_event *event, struct rvu *rvu)
 
 	otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pf);
 
+	otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pf);
+
 	mutex_unlock(&rvu->mbox_lock);
 
 	return 0;
@@ -191,7 +193,7 @@ int rvu_mbox_handler_mcs_intr_cfg(struct rvu *rvu,
 	if (pcifunc & RVU_PFVF_FUNC_MASK)
 		pfvf = &mcs->vf[rvu_get_hwvf(rvu, pcifunc)];
 	else
-		pfvf = &mcs->pf[rvu_get_pf(pcifunc)];
+		pfvf = &mcs->pf[rvu_get_pf(rvu->pdev, pcifunc)];
 
 	mcs->pf_map[0] = pcifunc;
 	pfvf->intr_mask = req->intr_mask;
@@ -911,7 +913,7 @@ int rvu_mcs_init(struct rvu *rvu)
 	/* Initialize the wq for handling mcs interrupts */
 	INIT_LIST_HEAD(&rvu->mcs_intrq_head);
 	INIT_WORK(&rvu->mcs_intr_work, mcs_intr_handler_task);
-	rvu->mcs_intr_wq = alloc_workqueue("mcs_intr_wq", 0, 0);
+	rvu->mcs_intr_wq = alloc_workqueue("mcs_intr_wq", WQ_PERCPU, 0);
 	if (!rvu->mcs_intr_wq) {
 		dev_err(rvu->dev, "mcs alloc workqueue failed\n");
 		return -ENOMEM;
@@ -925,7 +927,6 @@ void rvu_mcs_exit(struct rvu *rvu)
 	if (!rvu->mcs_intr_wq)
 		return;
 
-	flush_workqueue(rvu->mcs_intr_wq);
 	destroy_workqueue(rvu->mcs_intr_wq);
 	rvu->mcs_intr_wq = NULL;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
index bcc96eed2481..66749b3649c1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
@@ -545,8 +545,7 @@ static int ptp_probe(struct pci_dev *pdev,
 	spin_lock_init(&ptp->ptp_lock);
 	if (cn10k_ptp_errata(ptp)) {
 		ptp->read_ptp_tstmp = &read_ptp_tstmp_sec_nsec;
-		hrtimer_init(&ptp->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		ptp->hrtimer.function = ptp_reset_thresh;
+		hrtimer_setup(&ptp->hrtimer, ptp_reset_thresh, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	} else {
 		ptp->read_ptp_tstmp = &read_ptp_tstmp_nsec;
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index cd0d7b7774f1..2d78e08f985f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -20,6 +20,8 @@
 
 #include "rvu_trace.h"
 #include "rvu_npc_hash.h"
+#include "cn20k/reg.h"
+#include "cn20k/api.h"
 
 #define DRV_NAME	"rvu_af"
 #define DRV_STRING      "Marvell OcteonTX2 RVU Admin Function Driver"
@@ -34,10 +36,8 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
 			 int type, int num,
 			 void (mbox_handler)(struct work_struct *),
 			 void (mbox_up_handler)(struct work_struct *));
-enum {
-	TYPE_AFVF,
-	TYPE_AFPF,
-};
+static irqreturn_t rvu_mbox_pf_intr_handler(int irq, void *rvu_irq);
+static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq);
 
 /* Supported devices */
 static const struct pci_device_id rvu_id_table[] = {
@@ -294,7 +294,7 @@ int rvu_get_blkaddr(struct rvu *rvu, int blktype, u16 pcifunc)
 		devnum = rvu_get_hwvf(rvu, pcifunc);
 	} else {
 		is_pf = true;
-		devnum = rvu_get_pf(pcifunc);
+		devnum = rvu_get_pf(rvu->pdev, pcifunc);
 	}
 
 	/* Check if the 'pcifunc' has a NIX LF from 'BLKADDR_NIX0' or
@@ -359,7 +359,7 @@ static void rvu_update_rsrc_map(struct rvu *rvu, struct rvu_pfvf *pfvf,
 		devnum = rvu_get_hwvf(rvu, pcifunc);
 	} else {
 		is_pf = true;
-		devnum = rvu_get_pf(pcifunc);
+		devnum = rvu_get_pf(rvu->pdev, pcifunc);
 	}
 
 	block->fn_map[lf] = attach ? pcifunc : 0;
@@ -400,11 +400,6 @@ static void rvu_update_rsrc_map(struct rvu *rvu, struct rvu_pfvf *pfvf,
 	rvu_write64(rvu, BLKADDR_RVUM, reg | (devnum << 16), num_lfs);
 }
 
-inline int rvu_get_pf(u16 pcifunc)
-{
-	return (pcifunc >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK;
-}
-
 void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf)
 {
 	u64 cfg;
@@ -422,7 +417,7 @@ int rvu_get_hwvf(struct rvu *rvu, int pcifunc)
 	int pf, func;
 	u64 cfg;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	func = pcifunc & RVU_PFVF_FUNC_MASK;
 
 	/* Get first HWVF attached to this PF */
@@ -437,7 +432,7 @@ struct rvu_pfvf *rvu_get_pfvf(struct rvu *rvu, int pcifunc)
 	if (pcifunc & RVU_PFVF_FUNC_MASK)
 		return &rvu->hwvf[rvu_get_hwvf(rvu, pcifunc)];
 	else
-		return &rvu->pf[rvu_get_pf(pcifunc)];
+		return &rvu->pf[rvu_get_pf(rvu->pdev, pcifunc)];
 }
 
 static bool is_pf_func_valid(struct rvu *rvu, u16 pcifunc)
@@ -445,7 +440,7 @@ static bool is_pf_func_valid(struct rvu *rvu, u16 pcifunc)
 	int pf, vf, nvfs;
 	u64 cfg;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	if (pf >= rvu->hw->total_pfs)
 		return false;
 
@@ -760,6 +755,11 @@ static void rvu_free_hw_resources(struct rvu *rvu)
 
 	rvu_reset_msix(rvu);
 	mutex_destroy(&rvu->rsrc_lock);
+
+	/* Free the QINT/CINT memory */
+	pfvf = &rvu->pf[RVU_AFPF];
+	qmem_free(rvu->dev, pfvf->nix_qints_ctx);
+	qmem_free(rvu->dev, pfvf->cq_ints_ctx);
 }
 
 static void rvu_setup_pfvf_macaddress(struct rvu *rvu)
@@ -1164,6 +1164,9 @@ cpt:
 	rvu_program_channels(rvu);
 	cgx_start_linkup(rvu);
 
+	rvu_block_bcast_xon(rvu, BLKADDR_NIX0);
+	rvu_block_bcast_xon(rvu, BLKADDR_NIX1);
+
 	err = rvu_mcs_init(rvu);
 	if (err) {
 		dev_err(rvu->dev, "%s: Failed to initialize mcs\n", __func__);
@@ -1393,8 +1396,6 @@ static void rvu_detach_block(struct rvu *rvu, int pcifunc, int blktype)
 	if (blkaddr < 0)
 		return;
 
-	if (blktype == BLKTYPE_NIX)
-		rvu_nix_reset_mac(pfvf, pcifunc);
 
 	block = &hw->block[blkaddr];
 
@@ -1407,6 +1408,10 @@ static void rvu_detach_block(struct rvu *rvu, int pcifunc, int blktype)
 		if (lf < 0) /* This should never happen */
 			continue;
 
+		if (blktype == BLKTYPE_NIX) {
+			rvu_nix_reset_mac(pfvf, pcifunc);
+			rvu_npc_clear_ucast_entry(rvu, pcifunc, lf);
+		}
 		/* Disable the LF */
 		rvu_write64(rvu, blkaddr, block->lfcfg_reg |
 			    (lf << block->lfshift), 0x00ULL);
@@ -1485,7 +1490,7 @@ int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc)
 	pf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK);
 
 	/* All CGX mapped PFs are set with assigned NIX block during init */
-	if (is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) {
+	if (is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc))) {
 		blkaddr = pf->nix_blkaddr;
 	} else if (is_lbk_vf(rvu, pcifunc)) {
 		vf = pcifunc - 1;
@@ -1499,7 +1504,7 @@ int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc)
 	}
 
 	/* if SDP1 then the blkaddr is NIX1 */
-	if (is_sdp_pfvf(pcifunc) && pf->sdp_info->node_id == 1)
+	if (is_sdp_pfvf(rvu, pcifunc) && pf->sdp_info->node_id == 1)
 		blkaddr = BLKADDR_NIX1;
 
 	switch (blkaddr) {
@@ -2004,7 +2009,7 @@ int rvu_mbox_handler_vf_flr(struct rvu *rvu, struct msg_req *req,
 
 	vf = pcifunc & RVU_PFVF_FUNC_MASK;
 	cfg = rvu_read64(rvu, BLKADDR_RVUM,
-			 RVU_PRIV_PFX_CFG(rvu_get_pf(pcifunc)));
+			 RVU_PRIV_PFX_CFG(rvu_get_pf(rvu->pdev, pcifunc)));
 	numvfs = (cfg >> 12) & 0xFF;
 
 	if (vf && vf <= numvfs)
@@ -2031,6 +2036,9 @@ int rvu_mbox_handler_get_hw_cap(struct rvu *rvu, struct msg_req *req,
 	rsp->nix_shaping = hw->cap.nix_shaping;
 	rsp->npc_hash_extract = hw->cap.npc_hash_extract;
 
+	if (rvu->mcs_blk_cnt)
+		rsp->hw_caps = HW_CAP_MACSEC;
+
 	return 0;
 }
 
@@ -2173,7 +2181,7 @@ static int rvu_process_mbox_msg(struct otx2_mbox *mbox, int devid,
 		if (rsp && err)						\
 			rsp->hdr.rc = err;				\
 									\
-		trace_otx2_msg_process(mbox->pdev, _id, err);		\
+		trace_otx2_msg_process(mbox->pdev, _id, err, req->pcifunc); \
 		return rsp ? err : -ENOMEM;				\
 	}
 MBOX_MESSAGES
@@ -2218,15 +2226,30 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type, bool poll)
 
 	offset = mbox->rx_start + ALIGN(sizeof(*req_hdr), MBOX_MSG_ALIGN);
 
+	if (req_hdr->sig && !(is_rvu_otx2(rvu) || is_cn20k(rvu->pdev))) {
+		req_hdr->opt_msg = mw->mbox_wrk[devid].num_msgs;
+		rvu_write64(rvu, BLKADDR_NIX0, RVU_AF_BAR2_SEL,
+			    RVU_AF_BAR2_PFID);
+		if (type == TYPE_AFPF)
+			rvu_write64(rvu, BLKADDR_NIX0,
+				    AF_BAR2_ALIASX(0, NIX_CINTX_INT_W1S(devid)),
+				    0x1);
+		else
+			rvu_write64(rvu, BLKADDR_NIX0,
+				    AF_BAR2_ALIASX(0, NIX_QINTX_CNT(devid)),
+				    0x1);
+		usleep_range(5000, 6000);
+		goto done;
+	}
+
 	for (id = 0; id < mw->mbox_wrk[devid].num_msgs; id++) {
 		msg = mdev->mbase + offset;
 
 		/* Set which PF/VF sent this message based on mbox IRQ */
 		switch (type) {
 		case TYPE_AFPF:
-			msg->pcifunc &=
-				~(RVU_PFVF_PF_MASK << RVU_PFVF_PF_SHIFT);
-			msg->pcifunc |= (devid << RVU_PFVF_PF_SHIFT);
+			msg->pcifunc &= rvu_pcifunc_pf_mask(rvu->pdev);
+			msg->pcifunc |= rvu_make_pcifunc(rvu->pdev, devid, 0);
 			break;
 		case TYPE_AFVF:
 			msg->pcifunc &=
@@ -2244,16 +2267,17 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type, bool poll)
 		if (msg->pcifunc & RVU_PFVF_FUNC_MASK)
 			dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d:VF%d\n",
 				 err, otx2_mbox_id2name(msg->id),
-				 msg->id, rvu_get_pf(msg->pcifunc),
+				 msg->id, rvu_get_pf(rvu->pdev, msg->pcifunc),
 				 (msg->pcifunc & RVU_PFVF_FUNC_MASK) - 1);
 		else
 			dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d\n",
 				 err, otx2_mbox_id2name(msg->id),
 				 msg->id, devid);
 	}
+done:
 	mw->mbox_wrk[devid].num_msgs = 0;
 
-	if (poll)
+	if (!is_cn20k(mbox->pdev) && poll)
 		otx2_mbox_wait_for_zero(mbox, devid);
 
 	/* Send mbox responses to VF/PF */
@@ -2359,13 +2383,21 @@ static inline void rvu_afvf_mbox_up_handler(struct work_struct *work)
 	__rvu_mbox_up_handler(mwork, TYPE_AFVF);
 }
 
-static int rvu_get_mbox_regions(struct rvu *rvu, void **mbox_addr,
+static int rvu_get_mbox_regions(struct rvu *rvu, void __iomem **mbox_addr,
 				int num, int type, unsigned long *pf_bmap)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
 	int region;
 	u64 bar4;
 
+	/* For cn20k platform AF mailbox region is allocated by software
+	 * and the corresponding IOVA is programmed in hardware unlike earlier
+	 * silicons where software uses the hardware region after ioremap.
+	 */
+	if (is_cn20k(rvu->pdev))
+		return cn20k_rvu_get_mbox_regions(rvu, (void *)mbox_addr,
+						  num, type, pf_bmap);
+
 	/* For cn10k platform VF mailbox regions of a PF follows after the
 	 * PF <-> AF mailbox region. Whereas for Octeontx2 it is read from
 	 * RVU_PF_VF_BAR4_ADDR register.
@@ -2384,7 +2416,7 @@ static int rvu_get_mbox_regions(struct rvu *rvu, void **mbox_addr,
 				bar4 = rvupf_read64(rvu, RVU_PF_VF_BAR4_ADDR);
 				bar4 += region * MBOX_SIZE;
 			}
-			mbox_addr[region] = (void *)ioremap_wc(bar4, MBOX_SIZE);
+			mbox_addr[region] = ioremap_wc(bar4, MBOX_SIZE);
 			if (!mbox_addr[region])
 				goto error;
 		}
@@ -2407,7 +2439,7 @@ static int rvu_get_mbox_regions(struct rvu *rvu, void **mbox_addr,
 					  RVU_AF_PF_BAR4_ADDR);
 			bar4 += region * MBOX_SIZE;
 		}
-		mbox_addr[region] = (void *)ioremap_wc(bar4, MBOX_SIZE);
+		mbox_addr[region] = ioremap_wc(bar4, MBOX_SIZE);
 		if (!mbox_addr[region])
 			goto error;
 	}
@@ -2415,20 +2447,26 @@ static int rvu_get_mbox_regions(struct rvu *rvu, void **mbox_addr,
 
 error:
 	while (region--)
-		iounmap((void __iomem *)mbox_addr[region]);
+		iounmap(mbox_addr[region]);
 	return -ENOMEM;
 }
 
+static struct mbox_ops rvu_mbox_ops = {
+	.pf_intr_handler = rvu_mbox_pf_intr_handler,
+	.afvf_intr_handler = rvu_mbox_intr_handler,
+};
+
 static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
 			 int type, int num,
 			 void (mbox_handler)(struct work_struct *),
 			 void (mbox_up_handler)(struct work_struct *))
 {
-	int err = -EINVAL, i, dir, dir_up;
+	void __iomem **mbox_regions;
+	struct ng_rvu *ng_rvu_mbox;
+	int err, i, dir, dir_up;
 	void __iomem *reg_base;
 	struct rvu_work *mwork;
 	unsigned long *pf_bmap;
-	void **mbox_regions;
 	const char *name;
 	u64 cfg;
 
@@ -2436,6 +2474,12 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
 	if (!pf_bmap)
 		return -ENOMEM;
 
+	ng_rvu_mbox = kzalloc(sizeof(*ng_rvu_mbox), GFP_KERNEL);
+	if (!ng_rvu_mbox) {
+		err = -ENOMEM;
+		goto free_bitmap;
+	}
+
 	/* RVU VFs */
 	if (type == TYPE_AFVF)
 		bitmap_set(pf_bmap, 0, num);
@@ -2449,12 +2493,20 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
 		}
 	}
 
+	rvu->ng_rvu = ng_rvu_mbox;
+
+	rvu->ng_rvu->rvu_mbox_ops = &rvu_mbox_ops;
+
+	err = cn20k_rvu_mbox_init(rvu, type, num);
+	if (err)
+		goto free_mem;
+
 	mutex_init(&rvu->mbox_lock);
 
-	mbox_regions = kcalloc(num, sizeof(void *), GFP_KERNEL);
+	mbox_regions = kcalloc(num, sizeof(void __iomem *), GFP_KERNEL);
 	if (!mbox_regions) {
 		err = -ENOMEM;
-		goto free_bitmap;
+		goto free_qmem;
 	}
 
 	switch (type) {
@@ -2477,11 +2529,12 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
 			goto free_regions;
 		break;
 	default:
+		err = -EINVAL;
 		goto free_regions;
 	}
 
 	mw->mbox_wq = alloc_workqueue("%s",
-				      WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM,
+				      WQ_HIGHPRI | WQ_MEM_RECLAIM,
 				      num, name);
 	if (!mw->mbox_wq) {
 		err = -ENOMEM;
@@ -2524,7 +2577,11 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
 		mwork->rvu = rvu;
 		INIT_WORK(&mwork->work, mbox_up_handler);
 	}
-	goto free_regions;
+
+	kfree(mbox_regions);
+	bitmap_free(pf_bmap);
+
+	return 0;
 
 exit:
 	destroy_workqueue(mw->mbox_wq);
@@ -2533,6 +2590,10 @@ unmap_regions:
 		iounmap((void __iomem *)mbox_regions[num]);
 free_regions:
 	kfree(mbox_regions);
+free_qmem:
+	cn20k_free_mbox_memory(rvu);
+free_mem:
+	kfree(rvu->ng_rvu);
 free_bitmap:
 	bitmap_free(pf_bmap);
 	return err;
@@ -2559,8 +2620,8 @@ static void rvu_mbox_destroy(struct mbox_wq_info *mw)
 	otx2_mbox_destroy(&mw->mbox_up);
 }
 
-static void rvu_queue_work(struct mbox_wq_info *mw, int first,
-			   int mdevs, u64 intr)
+void rvu_queue_work(struct mbox_wq_info *mw, int first,
+		    int mdevs, u64 intr)
 {
 	struct otx2_mbox_dev *mdev;
 	struct otx2_mbox *mbox;
@@ -2634,7 +2695,7 @@ static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
 		rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(1), intr);
 
 		rvu_queue_work(&rvu->afvf_wq_info, 64, vfs, intr);
-		vfs -= 64;
+		vfs = 64;
 	}
 
 	intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(0));
@@ -2651,6 +2712,11 @@ static void rvu_enable_mbox_intr(struct rvu *rvu)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
 
+	if (is_cn20k(rvu->pdev)) {
+		cn20k_rvu_enable_mbox_intr(rvu);
+		return;
+	}
+
 	/* Clear spurious irqs, if any */
 	rvu_write64(rvu, BLKADDR_RVUM,
 		    RVU_AF_PFAF_MBOX_INT, INTR_MASK(hw->total_pfs));
@@ -2768,7 +2834,7 @@ static void rvu_flr_handler(struct work_struct *work)
 
 	cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
 	numvfs = (cfg >> 12) & 0xFF;
-	pcifunc  = pf << RVU_PFVF_PF_SHIFT;
+	pcifunc  = rvu_make_pcifunc(rvu->pdev, pf, 0);
 
 	for (vf = 0; vf < numvfs; vf++)
 		__rvu_flr_handler(rvu, (pcifunc | (vf + 1)));
@@ -2904,9 +2970,12 @@ static void rvu_unregister_interrupts(struct rvu *rvu)
 
 	rvu_cpt_unregister_interrupts(rvu);
 
-	/* Disable the Mbox interrupt */
-	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT_ENA_W1C,
-		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
+	if (!is_cn20k(rvu->pdev))
+		/* Disable the Mbox interrupt */
+		rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT_ENA_W1C,
+			    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
+	else
+		cn20k_rvu_unregister_interrupts(rvu);
 
 	/* Disable the PF FLR interrupt */
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1C,
@@ -2939,6 +3008,10 @@ static int rvu_afvf_msix_vectors_num_ok(struct rvu *rvu)
 	 * VF interrupts can be handled. Offset equal to zero means
 	 * that PF vectors are not configured and overlapping AF vectors.
 	 */
+	if (is_cn20k(rvu->pdev))
+		return (pfvf->msix.max >= RVU_AF_CN20K_INT_VEC_CNT +
+			RVU_MBOX_PF_INT_VEC_CNT) && offset;
+
 	return (pfvf->msix.max >= RVU_AF_INT_VEC_CNT + RVU_PF_INT_VEC_CNT) &&
 	       offset;
 }
@@ -2969,18 +3042,30 @@ static int rvu_register_interrupts(struct rvu *rvu)
 		return ret;
 	}
 
-	/* Register mailbox interrupt handler */
-	sprintf(&rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], "RVUAF Mbox");
-	ret = request_irq(pci_irq_vector(rvu->pdev, RVU_AF_INT_VEC_MBOX),
-			  rvu_mbox_pf_intr_handler, 0,
-			  &rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], rvu);
-	if (ret) {
-		dev_err(rvu->dev,
-			"RVUAF: IRQ registration failed for mbox irq\n");
-		goto fail;
-	}
+	if (!is_cn20k(rvu->pdev)) {
+		/* Register mailbox interrupt handler */
+		sprintf(&rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE],
+			"RVUAF Mbox");
+		ret = request_irq(pci_irq_vector
+				  (rvu->pdev, RVU_AF_INT_VEC_MBOX),
+				  rvu->ng_rvu->rvu_mbox_ops->pf_intr_handler, 0,
+				  &rvu->irq_name[RVU_AF_INT_VEC_MBOX *
+				  NAME_SIZE], rvu);
+		if (ret) {
+			dev_err(rvu->dev,
+				"RVUAF: IRQ registration failed for mbox\n");
+			goto fail;
+		}
 
-	rvu->irq_allocated[RVU_AF_INT_VEC_MBOX] = true;
+		rvu->irq_allocated[RVU_AF_INT_VEC_MBOX] = true;
+	} else {
+		ret = cn20k_register_afpf_mbox_intr(rvu);
+		if (ret) {
+			dev_err(rvu->dev,
+				"RVUAF: IRQ registration failed for mbox\n");
+			goto fail;
+		}
+	}
 
 	/* Enable mailbox interrupts from all PFs */
 	rvu_enable_mbox_intr(rvu);
@@ -3035,34 +3120,40 @@ static int rvu_register_interrupts(struct rvu *rvu)
 	/* Get PF MSIX vectors offset. */
 	pf_vec_start = rvu_read64(rvu, BLKADDR_RVUM,
 				  RVU_PRIV_PFX_INT_CFG(0)) & 0x3ff;
+	if (!is_cn20k(rvu->pdev)) {
+		/* Register MBOX0 interrupt. */
+		offset = pf_vec_start + RVU_PF_INT_VEC_VFPF_MBOX0;
+		sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox0");
+		ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+				  rvu->ng_rvu->rvu_mbox_ops->afvf_intr_handler, 0,
+				  &rvu->irq_name[offset * NAME_SIZE],
+				  rvu);
+		if (ret)
+			dev_err(rvu->dev,
+				"RVUAF: IRQ registration failed for Mbox0\n");
 
-	/* Register MBOX0 interrupt. */
-	offset = pf_vec_start + RVU_PF_INT_VEC_VFPF_MBOX0;
-	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox0");
-	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
-			  rvu_mbox_intr_handler, 0,
-			  &rvu->irq_name[offset * NAME_SIZE],
-			  rvu);
-	if (ret)
-		dev_err(rvu->dev,
-			"RVUAF: IRQ registration failed for Mbox0\n");
-
-	rvu->irq_allocated[offset] = true;
+		rvu->irq_allocated[offset] = true;
 
-	/* Register MBOX1 interrupt. MBOX1 IRQ number follows MBOX0 so
-	 * simply increment current offset by 1.
-	 */
-	offset = pf_vec_start + RVU_PF_INT_VEC_VFPF_MBOX1;
-	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox1");
-	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
-			  rvu_mbox_intr_handler, 0,
-			  &rvu->irq_name[offset * NAME_SIZE],
-			  rvu);
-	if (ret)
-		dev_err(rvu->dev,
-			"RVUAF: IRQ registration failed for Mbox1\n");
+		/* Register MBOX1 interrupt. MBOX1 IRQ number follows MBOX0 so
+		 * simply increment current offset by 1.
+		 */
+		offset = pf_vec_start + RVU_PF_INT_VEC_VFPF_MBOX1;
+		sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox1");
+		ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+				  rvu->ng_rvu->rvu_mbox_ops->afvf_intr_handler, 0,
+				  &rvu->irq_name[offset * NAME_SIZE],
+				  rvu);
+		if (ret)
+			dev_err(rvu->dev,
+				"RVUAF: IRQ registration failed for Mbox1\n");
 
-	rvu->irq_allocated[offset] = true;
+		rvu->irq_allocated[offset] = true;
+	} else {
+		ret = cn20k_register_afvf_mbox_intr(rvu, pf_vec_start);
+		if (ret)
+			dev_err(rvu->dev,
+				"RVUAF: IRQ registration failed for Mbox\n");
+	}
 
 	/* Register FLR interrupt handler for AF's VFs */
 	offset = pf_vec_start + RVU_PF_INT_VEC_VFFLR0;
@@ -3173,6 +3264,9 @@ static void rvu_disable_afvf_intr(struct rvu *rvu)
 {
 	int vfs = rvu->vfs;
 
+	if (is_cn20k(rvu->pdev))
+		return cn20k_rvu_disable_afvf_intr(rvu, vfs);
+
 	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(0), INTR_MASK(vfs));
 	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(0), INTR_MASK(vfs));
 	rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1CX(0), INTR_MASK(vfs));
@@ -3189,6 +3283,9 @@ static void rvu_enable_afvf_intr(struct rvu *rvu)
 {
 	int vfs = rvu->vfs;
 
+	if (is_cn20k(rvu->pdev))
+		return cn20k_rvu_enable_afvf_intr(rvu, vfs);
+
 	/* Clear any pending interrupts and enable AF VF interrupts for
 	 * the first 64 VFs.
 	 */
@@ -3433,6 +3530,9 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		ptp_start(rvu, rvu->fwdata->sclk, rvu->fwdata->ptp_ext_clk_rate,
 			  rvu->fwdata->ptp_ext_tstamp);
 
+	/* Alloc CINT and QINT memory */
+	rvu_alloc_cint_qint_mem(rvu, &rvu->pf[RVU_AFPF], BLKADDR_NIX0,
+				(rvu->hw->block[BLKADDR_NIX0].lf.max));
 	return 0;
 err_dl:
 	rvu_unregister_dl(rvu);
@@ -3484,6 +3584,9 @@ static void rvu_remove(struct pci_dev *pdev)
 	pci_set_drvdata(pdev, NULL);
 
 	devm_kfree(&pdev->dev, rvu->hw);
+	if (is_cn20k(rvu->pdev))
+		cn20k_free_mbox_memory(rvu);
+	kfree(rvu->ng_rvu);
 	devm_kfree(&pdev->dev, rvu);
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index a383b5ef5b2d..e85dac2c806d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -10,6 +10,7 @@
 
 #include <linux/pci.h>
 #include <net/devlink.h>
+#include <linux/soc/marvell/silicons.h>
 
 #include "rvu_struct.h"
 #include "rvu_devlink.h"
@@ -30,6 +31,8 @@
 #define PCI_SUBSYS_DEVID_CNF10K_A	       0xBA00
 #define PCI_SUBSYS_DEVID_CNF10K_B              0xBC00
 #define PCI_SUBSYS_DEVID_CN10K_B               0xBD00
+#define PCI_SUBSYS_DEVID_CN20KA                0xC220
+#define PCI_SUBSYS_DEVID_CNF20KA               0xC320
 
 /* PCI BAR nos */
 #define	PCI_AF_REG_BAR_NUM			0
@@ -41,12 +44,39 @@
 #define MAX_CPT_BLKS				2
 
 /* PF_FUNC */
-#define RVU_PFVF_PF_SHIFT	10
-#define RVU_PFVF_PF_MASK	0x3F
-#define RVU_PFVF_FUNC_SHIFT	0
-#define RVU_PFVF_FUNC_MASK	0x3FF
+#define RVU_OTX2_PFVF_PF_SHIFT			10
+#define RVU_OTX2_PFVF_PF_MASK			0x3F
+#define RVU_PFVF_FUNC_SHIFT			0
+#define RVU_PFVF_FUNC_MASK			0x3FF
+#define RVU_CN20K_PFVF_PF_SHIFT			9
+#define RVU_CN20K_PFVF_PF_MASK			0x7F
+
+static inline u16 rvu_make_pcifunc(struct pci_dev *pdev, int pf, int func)
+{
+	if (is_cn20k(pdev))
+		return ((pf & RVU_CN20K_PFVF_PF_MASK) <<
+			RVU_CN20K_PFVF_PF_SHIFT) |
+			((func & RVU_PFVF_FUNC_MASK) <<
+			RVU_PFVF_FUNC_SHIFT);
+	else
+		return ((pf & RVU_OTX2_PFVF_PF_MASK) <<
+			RVU_OTX2_PFVF_PF_SHIFT) |
+			((func & RVU_PFVF_FUNC_MASK) <<
+			RVU_PFVF_FUNC_SHIFT);
+}
+
+static inline int rvu_pcifunc_pf_mask(struct pci_dev *pdev)
+{
+	if (is_cn20k(pdev))
+		return ~(RVU_CN20K_PFVF_PF_MASK << RVU_CN20K_PFVF_PF_SHIFT);
+	else
+		return ~(RVU_OTX2_PFVF_PF_MASK << RVU_OTX2_PFVF_PF_SHIFT);
+}
+
+#define RVU_AFPF           25
 
 #ifdef CONFIG_DEBUG_FS
+
 struct dump_ctx {
 	int	lf;
 	int	id;
@@ -444,6 +474,23 @@ struct mbox_wq_info {
 	struct workqueue_struct *mbox_wq;
 };
 
+struct rvu_irq_data {
+	u64 intr_status;
+	void (*rvu_queue_work_hdlr)(struct mbox_wq_info *mw, int first,
+				    int mdevs, u64 intr);
+	void (*afvf_queue_work_hdlr)(struct mbox_wq_info *mw, int first,
+				     int mdevs, u64 intr);
+	struct	rvu *rvu;
+	int vec_num;
+	int start;
+	int mdevs;
+};
+
+struct mbox_ops {
+	irqreturn_t (*pf_intr_handler)(int irq, void *rvu_irq);
+	irqreturn_t (*afvf_intr_handler)(int irq, void *rvu_irq);
+};
+
 struct channel_fwdata {
 	struct sdp_node_info info;
 	u8 valid;
@@ -451,6 +498,14 @@ struct channel_fwdata {
 	u8 reserved[RVU_CHANL_INFO_RESERVED];
 };
 
+struct altaf_intr_notify {
+	unsigned long flr_pf_bmap[2];
+	unsigned long flr_vf_bmap[2];
+	unsigned long gint_paddr;
+	unsigned long gint_iova_addr;
+	unsigned long reserved[6];
+};
+
 struct rvu_fwdata {
 #define RVU_FWDATA_HEADER_MAGIC	0xCFDA	/* Custom Firmware Data*/
 #define RVU_FWDATA_VERSION	0x0001
@@ -470,7 +525,8 @@ struct rvu_fwdata {
 	u32 ptp_ext_clk_rate;
 	u32 ptp_ext_tstamp;
 	struct channel_fwdata channel_data;
-#define FWDATA_RESERVED_MEM 958
+	struct altaf_intr_notify altaf_intr_info;
+#define FWDATA_RESERVED_MEM 946
 	u64 reserved[FWDATA_RESERVED_MEM];
 #define CGX_MAX         9
 #define CGX_LMACS_MAX   4
@@ -601,6 +657,7 @@ struct rvu {
 
 	struct mutex		mbox_lock; /* Serialize mbox up and down msgs */
 	u16			rep_pcifunc;
+	bool			altaf_ready;
 	int			rep_cnt;
 	u16			*rep2pfvf_map;
 	u8			rep_mode;
@@ -609,6 +666,8 @@ struct rvu {
 	struct list_head	rep_evtq_head;
 	/* Representor event lock */
 	spinlock_t		rep_evtq_lock;
+
+	struct ng_rvu           *ng_rvu;
 };
 
 static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)
@@ -734,6 +793,20 @@ static inline bool is_cn10kb(struct rvu *rvu)
 	return false;
 }
 
+static inline bool is_cgx_mapped_to_nix(unsigned short id, u8 cgx_id)
+{
+	/* On CNF10KA and CNF10KB silicons only two CGX blocks are connected
+	 * to NIX.
+	 */
+	if (id == PCI_SUBSYS_DEVID_CNF10K_A || id == PCI_SUBSYS_DEVID_CNF10K_B)
+		return cgx_id <= 1;
+
+	return !(cgx_id && !(id == PCI_SUBSYS_DEVID_96XX ||
+			     id == PCI_SUBSYS_DEVID_98XX ||
+			     id == PCI_SUBSYS_DEVID_CN10K_A ||
+			     id == PCI_SUBSYS_DEVID_CN10K_B));
+}
+
 static inline bool is_rvu_npc_hash_extract_en(struct rvu *rvu)
 {
 	u64 npc_const3;
@@ -834,7 +907,6 @@ int rvu_alloc_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc);
 void rvu_free_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc, int start);
 bool rvu_rsrc_check_contig(struct rsrc_bmap *rsrc, int nrsrc);
 u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blkaddr);
-int rvu_get_pf(u16 pcifunc);
 struct rvu_pfvf *rvu_get_pfvf(struct rvu *rvu, int pcifunc);
 void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf);
 bool is_block_implemented(struct rvu_hwinfo *hw, int blkaddr);
@@ -863,8 +935,8 @@ void rvu_aq_free(struct rvu *rvu, struct admin_queue *aq);
 
 /* SDP APIs */
 int rvu_sdp_init(struct rvu *rvu);
-bool is_sdp_pfvf(u16 pcifunc);
-bool is_sdp_pf(u16 pcifunc);
+bool is_sdp_pfvf(struct rvu *rvu, u16 pcifunc);
+bool is_sdp_pf(struct rvu *rvu, u16 pcifunc);
 bool is_sdp_vf(struct rvu *rvu, u16 pcifunc);
 
 static inline bool is_rep_dev(struct rvu *rvu, u16 pcifunc)
@@ -875,11 +947,21 @@ static inline bool is_rep_dev(struct rvu *rvu, u16 pcifunc)
 	return false;
 }
 
+static inline int rvu_get_pf(struct pci_dev *pdev, u16 pcifunc)
+{
+	if (is_cn20k(pdev))
+		return (pcifunc >> RVU_CN20K_PFVF_PF_SHIFT) &
+			RVU_CN20K_PFVF_PF_MASK;
+	else
+		return (pcifunc >> RVU_OTX2_PFVF_PF_SHIFT) &
+			RVU_OTX2_PFVF_PF_MASK;
+}
+
 /* CGX APIs */
 static inline bool is_pf_cgxmapped(struct rvu *rvu, u8 pf)
 {
 	return (pf >= PF_CGXMAP_BASE && pf <= rvu->cgx_mapped_pfs) &&
-		!is_sdp_pf(pf << RVU_PFVF_PF_SHIFT);
+		!is_sdp_pf(rvu, rvu_make_pcifunc(rvu->pdev, pf, 0));
 }
 
 static inline void rvu_get_cgx_lmac_id(u8 map, u8 *cgx_id, u8 *lmac_id)
@@ -891,7 +973,7 @@ static inline void rvu_get_cgx_lmac_id(u8 map, u8 *cgx_id, u8 *lmac_id)
 static inline bool is_cgx_vf(struct rvu *rvu, u16 pcifunc)
 {
 	return ((pcifunc & RVU_PFVF_FUNC_MASK) &&
-		is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc)));
+		is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc)));
 }
 
 #define M(_name, _id, fn_name, req, rsp)				\
@@ -899,6 +981,10 @@ int rvu_mbox_handler_ ## fn_name(struct rvu *, struct req *, struct rsp *);
 MBOX_MESSAGES
 #undef M
 
+/* Mbox APIs */
+void rvu_queue_work(struct mbox_wq_info *mw, int first,
+		    int mdevs, u64 intr);
+
 int rvu_cgx_init(struct rvu *rvu);
 int rvu_cgx_exit(struct rvu *rvu);
 void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu);
@@ -953,6 +1039,11 @@ int rvu_nix_mcast_get_mce_index(struct rvu *rvu, u16 pcifunc,
 int rvu_nix_mcast_update_mcam_entry(struct rvu *rvu, u16 pcifunc,
 				    u32 mcast_grp_idx, u16 mcam_index);
 void rvu_nix_flr_free_bpids(struct rvu *rvu, u16 pcifunc);
+int rvu_alloc_cint_qint_mem(struct rvu *rvu, struct rvu_pfvf *pfvf,
+			    int blkaddr, int nixlf);
+void rvu_block_bcast_xon(struct rvu *rvu, int blkaddr);
+int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
+			struct nix_aq_enq_rsp *rsp);
 
 /* NPC APIs */
 void rvu_npc_freemem(struct rvu *rvu);
@@ -967,8 +1058,6 @@ void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 				  bool enable);
 void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 				       int nixlf, u64 chan);
-void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
-				bool enable);
 void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    u64 chan);
 void rvu_npc_enable_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
@@ -994,6 +1083,8 @@ void rvu_npc_get_mcam_entry_alloc_info(struct rvu *rvu, u16 pcifunc,
 void rvu_npc_get_mcam_counter_alloc_info(struct rvu *rvu, u16 pcifunc,
 					 int blkaddr, int *alloc_cnt,
 					 int *enable_cnt);
+void rvu_npc_clear_ucast_entry(struct rvu *rvu, int pcifunc, int nixlf);
+
 bool is_npc_intf_tx(u8 intf);
 bool is_npc_intf_rx(u8 intf);
 bool is_npc_interface_valid(struct rvu *rvu, u8 intf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 992fa0b82e8d..3abd750a4bd7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -34,7 +34,7 @@ static struct _req_type __maybe_unused					\
 		return NULL;						\
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;				\
 	req->hdr.id = _id;						\
-	trace_otx2_msg_alloc(rvu->pdev, _id, sizeof(*req));		\
+	trace_otx2_msg_alloc(rvu->pdev, _id, sizeof(*req), 0);		\
 	return req;							\
 }
 
@@ -272,6 +272,8 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu)
 
 		otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pfid);
 
+		otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pfid);
+
 		mutex_unlock(&rvu->mbox_lock);
 	} while (pfmap);
 }
@@ -313,7 +315,7 @@ static int cgx_lmac_event_handler_init(struct rvu *rvu)
 	spin_lock_init(&rvu->cgx_evq_lock);
 	INIT_LIST_HEAD(&rvu->cgx_evq_head);
 	INIT_WORK(&rvu->cgx_evh_work, cgx_evhandler_task);
-	rvu->cgx_evh_wq = alloc_workqueue("rvu_evh_wq", 0, 0);
+	rvu->cgx_evh_wq = alloc_workqueue("rvu_evh_wq", WQ_PERCPU, 0);
 	if (!rvu->cgx_evh_wq) {
 		dev_err(rvu->dev, "alloc workqueue failed");
 		return -ENOMEM;
@@ -455,7 +457,7 @@ int rvu_cgx_exit(struct rvu *rvu)
 inline bool is_cgx_config_permitted(struct rvu *rvu, u16 pcifunc)
 {
 	if ((pcifunc & RVU_PFVF_FUNC_MASK) ||
-	    !is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc)))
+	    !is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc)))
 		return false;
 	return true;
 }
@@ -482,7 +484,7 @@ void rvu_cgx_enadis_rx_bp(struct rvu *rvu, int pf, bool enable)
 
 int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 	void *cgxd;
@@ -499,7 +501,7 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start)
 
 int rvu_cgx_tx_enable(struct rvu *rvu, u16 pcifunc, bool enable)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 	void *cgxd;
@@ -524,7 +526,7 @@ int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable)
 
 void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	int i = 0, lmac_count = 0;
 	struct mac_ops *mac_ops;
 	u8 max_dmac_filters;
@@ -575,7 +577,7 @@ int rvu_mbox_handler_cgx_stop_rxtx(struct rvu *rvu, struct msg_req *req,
 static int rvu_lmac_get_stats(struct rvu *rvu, struct msg_req *req,
 			      void *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct mac_ops *mac_ops;
 	int stat = 0, err = 0;
 	u64 tx_stat, rx_stat;
@@ -631,7 +633,7 @@ int rvu_mbox_handler_rpm_stats(struct rvu *rvu, struct msg_req *req,
 int rvu_mbox_handler_cgx_stats_rst(struct rvu *rvu, struct msg_req *req,
 				   struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct rvu_pfvf	*parent_pf;
 	struct mac_ops *mac_ops;
 	u8 cgx_idx, lmac;
@@ -661,7 +663,7 @@ int rvu_mbox_handler_cgx_fec_stats(struct rvu *rvu,
 				   struct msg_req *req,
 				   struct cgx_fec_stats_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_idx, lmac;
 	void *cgxd;
@@ -679,17 +681,20 @@ int rvu_mbox_handler_cgx_mac_addr_set(struct rvu *rvu,
 				      struct cgx_mac_addr_set_or_get *req,
 				      struct cgx_mac_addr_set_or_get *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
+	struct rvu_pfvf *pfvf;
 	u8 cgx_id, lmac_id;
 
-	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
-		return -EPERM;
+	if (!is_pf_cgxmapped(rvu, pf))
+		return LMAC_AF_ERR_PF_NOT_MAPPED;
 
 	if (rvu_npc_exact_has_match_table(rvu))
 		return rvu_npc_exact_mac_addr_set(rvu, req, rsp);
 
 	rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
 
+	pfvf = &rvu->pf[pf];
+	ether_addr_copy(pfvf->mac_addr, req->mac_addr);
 	cgx_lmac_addr_set(cgx_id, lmac_id, req->mac_addr);
 
 	return 0;
@@ -699,7 +704,7 @@ int rvu_mbox_handler_cgx_mac_addr_add(struct rvu *rvu,
 				      struct cgx_mac_addr_add_req *req,
 				      struct cgx_mac_addr_add_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 	int rc = 0;
 
@@ -723,7 +728,7 @@ int rvu_mbox_handler_cgx_mac_addr_del(struct rvu *rvu,
 				      struct cgx_mac_addr_del_req *req,
 				      struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
@@ -741,7 +746,7 @@ int rvu_mbox_handler_cgx_mac_max_entries_get(struct rvu *rvu,
 					     struct cgx_max_dmac_entries_get_rsp
 					     *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	/* If msg is received from PFs(which are not mapped to CGX LMACs)
@@ -767,20 +772,12 @@ int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu,
 				      struct cgx_mac_addr_set_or_get *req,
 				      struct cgx_mac_addr_set_or_get *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
-	u8 cgx_id, lmac_id;
-	int rc = 0;
-	u64 cfg;
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc);
 
-	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
-		return -EPERM;
-
-	rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+	if (!is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, req->hdr.pcifunc)))
+		return LMAC_AF_ERR_PF_NOT_MAPPED;
 
-	rsp->hdr.rc = rc;
-	cfg = cgx_lmac_addr_get(cgx_id, lmac_id);
-	/* copy 48 bit mac address to req->mac_addr */
-	u64_to_ether_addr(cfg, rsp->mac_addr);
+	ether_addr_copy(rsp->mac_addr, pfvf->mac_addr);
 	return 0;
 }
 
@@ -788,7 +785,7 @@ int rvu_mbox_handler_cgx_promisc_enable(struct rvu *rvu, struct msg_req *req,
 					struct msg_rsp *rsp)
 {
 	u16 pcifunc = req->hdr.pcifunc;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
@@ -807,7 +804,7 @@ int rvu_mbox_handler_cgx_promisc_enable(struct rvu *rvu, struct msg_req *req,
 int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req,
 					 struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
@@ -826,7 +823,7 @@ int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req,
 static int rvu_cgx_ptp_rx_cfg(struct rvu *rvu, u16 pcifunc, bool enable)
 {
 	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 	void *cgxd;
@@ -862,7 +859,7 @@ static int rvu_cgx_ptp_rx_cfg(struct rvu *rvu, u16 pcifunc, bool enable)
 int rvu_mbox_handler_cgx_ptp_rx_enable(struct rvu *rvu, struct msg_req *req,
 				       struct msg_rsp *rsp)
 {
-	if (!is_pf_cgxmapped(rvu, rvu_get_pf(req->hdr.pcifunc)))
+	if (!is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, req->hdr.pcifunc)))
 		return -EPERM;
 
 	return rvu_cgx_ptp_rx_cfg(rvu, req->hdr.pcifunc, true);
@@ -876,7 +873,7 @@ int rvu_mbox_handler_cgx_ptp_rx_disable(struct rvu *rvu, struct msg_req *req,
 
 static int rvu_cgx_config_linkevents(struct rvu *rvu, u16 pcifunc, bool en)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, pcifunc))
@@ -915,7 +912,7 @@ int rvu_mbox_handler_cgx_get_linkinfo(struct rvu *rvu, struct msg_req *req,
 	u8 cgx_id, lmac_id;
 	int pf, err;
 
-	pf = rvu_get_pf(req->hdr.pcifunc);
+	pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 
 	if (!is_pf_cgxmapped(rvu, pf))
 		return -ENODEV;
@@ -931,7 +928,7 @@ int rvu_mbox_handler_cgx_features_get(struct rvu *rvu,
 				      struct msg_req *req,
 				      struct cgx_features_info_msg *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_idx, lmac;
 	void *cgxd;
 
@@ -973,7 +970,7 @@ u32 rvu_cgx_get_lmac_fifolen(struct rvu *rvu, int cgx, int lmac)
 
 static int rvu_cgx_config_intlbk(struct rvu *rvu, u16 pcifunc, bool en)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 
@@ -1003,7 +1000,7 @@ int rvu_mbox_handler_cgx_intlbk_disable(struct rvu *rvu, struct msg_req *req,
 
 int rvu_cgx_cfg_pause_frm(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 rx_pfc = 0, tx_pfc = 0;
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
@@ -1044,7 +1041,7 @@ int rvu_mbox_handler_cgx_cfg_pause_frm(struct rvu *rvu,
 				       struct cgx_pause_frm_cfg *req,
 				       struct cgx_pause_frm_cfg *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 	int err = 0;
@@ -1071,7 +1068,7 @@ int rvu_mbox_handler_cgx_cfg_pause_frm(struct rvu *rvu,
 int rvu_mbox_handler_cgx_get_phy_fec_stats(struct rvu *rvu, struct msg_req *req,
 					   struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_pf_cgxmapped(rvu, pf))
@@ -1104,7 +1101,7 @@ int rvu_cgx_nix_cuml_stats(struct rvu *rvu, void *cgxd, int lmac_id,
 	/* Assumes LF of a PF and all of its VF belongs to the same
 	 * NIX block
 	 */
-	pcifunc = pf << RVU_PFVF_PF_SHIFT;
+	pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
 	if (blkaddr < 0)
 		return 0;
@@ -1131,10 +1128,10 @@ int rvu_cgx_start_stop_io(struct rvu *rvu, u16 pcifunc, bool start)
 	struct rvu_pfvf *parent_pf, *pfvf;
 	int cgx_users, err = 0;
 
-	if (!is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc)))
+	if (!is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc)))
 		return 0;
 
-	parent_pf = &rvu->pf[rvu_get_pf(pcifunc)];
+	parent_pf = &rvu->pf[rvu_get_pf(rvu->pdev, pcifunc)];
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
 
 	mutex_lock(&rvu->cgx_cfg_lock);
@@ -1177,7 +1174,7 @@ int rvu_mbox_handler_cgx_set_fec_param(struct rvu *rvu,
 				       struct fec_mode *req,
 				       struct fec_mode *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_pf_cgxmapped(rvu, pf))
@@ -1193,7 +1190,7 @@ int rvu_mbox_handler_cgx_set_fec_param(struct rvu *rvu,
 int rvu_mbox_handler_cgx_get_aux_link_info(struct rvu *rvu, struct msg_req *req,
 					   struct cgx_fw_data *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!rvu->fwdata)
@@ -1220,7 +1217,8 @@ int rvu_mbox_handler_cgx_set_link_mode(struct rvu *rvu,
 				       struct cgx_set_link_mode_req *req,
 				       struct cgx_set_link_mode_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
+	struct cgx_lmac_fwdata_s *linkmodes;
 	u8 cgx_idx, lmac;
 	void *cgxd;
 
@@ -1229,14 +1227,20 @@ int rvu_mbox_handler_cgx_set_link_mode(struct rvu *rvu,
 
 	rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_idx, &lmac);
 	cgxd = rvu_cgx_pdata(cgx_idx, rvu);
-	rsp->status = cgx_set_link_mode(cgxd, req->args, cgx_idx, lmac);
+	if (rvu->hw->lmac_per_cgx == CGX_LMACS_USX)
+		linkmodes = &rvu->fwdata->cgx_fw_data_usx[cgx_idx][lmac];
+	else
+		linkmodes = &rvu->fwdata->cgx_fw_data[cgx_idx][lmac];
+
+	rsp->status = cgx_set_link_mode(cgxd, req->args, linkmodes,
+					cgx_idx, lmac);
 	return 0;
 }
 
 int rvu_mbox_handler_cgx_mac_addr_reset(struct rvu *rvu, struct cgx_mac_addr_reset_req *req,
 					struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
@@ -1254,7 +1258,7 @@ int rvu_mbox_handler_cgx_mac_addr_update(struct rvu *rvu,
 					 struct cgx_mac_addr_update_req *req,
 					 struct cgx_mac_addr_update_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
@@ -1270,7 +1274,7 @@ int rvu_mbox_handler_cgx_mac_addr_update(struct rvu *rvu,
 int rvu_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, u16 pcifunc, u8 tx_pause,
 			       u8 rx_pause, u16 pfc_en)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 rx_8023 = 0, tx_8023 = 0;
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
@@ -1308,7 +1312,7 @@ int rvu_mbox_handler_cgx_prio_flow_ctrl_cfg(struct rvu *rvu,
 					    struct cgx_pfc_cfg *req,
 					    struct cgx_pfc_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 	void *cgxd;
@@ -1333,7 +1337,7 @@ int rvu_mbox_handler_cgx_prio_flow_ctrl_cfg(struct rvu *rvu,
 
 void rvu_mac_reset(struct rvu *rvu, u16 pcifunc)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct mac_ops *mac_ops;
 	struct cgx *cgxd;
 	u8 cgx, lmac;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
index 7fa98aeb3663..d2163da28d18 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
@@ -13,19 +13,26 @@
 /* RVU LMTST */
 #define LMT_TBL_OP_READ		0
 #define LMT_TBL_OP_WRITE	1
-#define LMT_MAP_TABLE_SIZE	(128 * 1024)
 #define LMT_MAPTBL_ENTRY_SIZE	16
+#define LMT_MAX_VFS		256
+
+#define LMT_MAP_ENTRY_ENA      BIT_ULL(20)
+#define LMT_MAP_ENTRY_LINES    GENMASK_ULL(18, 16)
 
 /* Function to perform operations (read/write) on lmtst map table */
 static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 			       int lmt_tbl_op)
 {
 	void __iomem *lmt_map_base;
-	u64 tbl_base;
+	u64 tbl_base, cfg;
+	int pfs, vfs;
 
 	tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE);
+	cfg  = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG);
+	vfs = 1 << (cfg & 0xF);
+	pfs = 1 << ((cfg >> 4) & 0x7);
 
-	lmt_map_base = ioremap_wc(tbl_base, LMT_MAP_TABLE_SIZE);
+	lmt_map_base = ioremap_wc(tbl_base, pfs * vfs * LMT_MAPTBL_ENTRY_SIZE);
 	if (!lmt_map_base) {
 		dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n");
 		return -ENOMEM;
@@ -35,6 +42,13 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 		*val = readq(lmt_map_base + index);
 	} else {
 		writeq((*val), (lmt_map_base + index));
+
+		cfg = FIELD_PREP(LMT_MAP_ENTRY_ENA, 0x1);
+		/* 2048 LMTLINES */
+		cfg |= FIELD_PREP(LMT_MAP_ENTRY_LINES, 0x6);
+
+		writeq(cfg, (lmt_map_base + (index + 8)));
+
 		/* Flushing the AP interceptor cache to make APR_LMT_MAP_ENTRY_S
 		 * changes effective. Write 1 for flush and read is being used as a
 		 * barrier and sets up a data dependency. Write to 0 after a write
@@ -52,7 +66,7 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 #define LMT_MAP_TBL_W1_OFF  8
 static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc)
 {
-	return ((rvu_get_pf(pcifunc) * rvu->hw->total_vfs) +
+	return ((rvu_get_pf(rvu->pdev, pcifunc) * LMT_MAX_VFS) +
 		(pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE;
 }
 
@@ -69,7 +83,7 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc,
 
 	mutex_lock(&rvu->rsrc_lock);
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova);
-	pf = rvu_get_pf(pcifunc) & 0x1F;
+	pf = rvu_get_pf(rvu->pdev, pcifunc) & RVU_OTX2_PFVF_PF_MASK;
 	val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 |
 	      ((pcifunc & RVU_PFVF_FUNC_MASK) & 0xFF);
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TXN_REQ, val);
@@ -141,7 +155,7 @@ int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu,
 	int err = 0;
 	u64 val;
 
-	/* Check if PF_FUNC wants to use it's own local memory as LMTLINE
+	/* Check if PF_FUNC wants to use its own local memory as LMTLINE
 	 * region, if so, convert that IOVA to physical address and
 	 * populate LMT table with that address
 	 */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index 3c5bbaf12e59..f404117bf6c8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -410,7 +410,7 @@ static bool is_cpt_pf(struct rvu *rvu, u16 pcifunc)
 {
 	int cpt_pf_num = rvu->cpt_pf_num;
 
-	if (rvu_get_pf(pcifunc) != cpt_pf_num)
+	if (rvu_get_pf(rvu->pdev, pcifunc) != cpt_pf_num)
 		return false;
 	if (pcifunc & RVU_PFVF_FUNC_MASK)
 		return false;
@@ -422,7 +422,7 @@ static bool is_cpt_vf(struct rvu *rvu, u16 pcifunc)
 {
 	int cpt_pf_num = rvu->cpt_pf_num;
 
-	if (rvu_get_pf(pcifunc) != cpt_pf_num)
+	if (rvu_get_pf(rvu->pdev, pcifunc) != cpt_pf_num)
 		return false;
 	if (!(pcifunc & RVU_PFVF_FUNC_MASK))
 		return false;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 148144f5b61d..15d3cb0b9da6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -21,6 +21,8 @@
 #include "rvu_npc_hash.h"
 #include "mcs.h"
 
+#include "cn20k/debugfs.h"
+
 #define DEBUGFS_DIR_NAME "octeontx2"
 
 enum {
@@ -553,6 +555,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 	u64 lmt_addr, val, tbl_base;
 	int pf, vf, num_vfs, hw_vfs;
 	void __iomem *lmt_map_base;
+	int apr_pfs, apr_vfs;
 	int buf_size = 10240;
 	size_t off = 0;
 	int index = 0;
@@ -568,8 +571,12 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 		return -ENOMEM;
 
 	tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE);
+	val  = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG);
+	apr_vfs = 1 << (val & 0xF);
+	apr_pfs = 1 << ((val >> 4) & 0x7);
 
-	lmt_map_base = ioremap_wc(tbl_base, 128 * 1024);
+	lmt_map_base = ioremap_wc(tbl_base, apr_pfs * apr_vfs *
+				  LMT_MAPTBL_ENTRY_SIZE);
 	if (!lmt_map_base) {
 		dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n");
 		kfree(buf);
@@ -591,7 +598,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 		off += scnprintf(&buf[off], buf_size - 1 - off, "PF%d  \t\t\t",
 				    pf);
 
-		index = pf * rvu->hw->total_vfs * LMT_MAPTBL_ENTRY_SIZE;
+		index = pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE;
 		off += scnprintf(&buf[off], buf_size - 1 - off, " 0x%llx\t\t",
 				 (tbl_base + index));
 		lmt_addr = readq(lmt_map_base + index);
@@ -604,7 +611,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 		/* Reading num of VFs per PF */
 		rvu_get_pf_numvfs(rvu, pf, &num_vfs, &hw_vfs);
 		for (vf = 0; vf < num_vfs; vf++) {
-			index = (pf * rvu->hw->total_vfs * 16) +
+			index = (pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE) +
 				((vf + 1)  * LMT_MAPTBL_ENTRY_SIZE);
 			off += scnprintf(&buf[off], buf_size - 1 - off,
 					    "PF%d:VF%d  \t\t", pf, vf);
@@ -683,7 +690,7 @@ static int get_max_column_width(struct rvu *rvu)
 
 	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
 		for (vf = 0; vf <= rvu->hw->total_vfs; vf++) {
-			pcifunc = pf << 10 | vf;
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, vf);
 			if (!pcifunc)
 				continue;
 
@@ -754,7 +761,7 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
 		for (vf = 0; vf <= rvu->hw->total_vfs; vf++) {
 			off = 0;
 			flag = 0;
-			pcifunc = pf << 10 | vf;
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, vf);
 			if (!pcifunc)
 				continue;
 
@@ -837,7 +844,7 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused)
 
 		cgx[0] = 0;
 		lmac[0] = 0;
-		pcifunc = pf << 10;
+		pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 		pfvf = rvu_get_pfvf(rvu, pcifunc);
 
 		if (pfvf->nix_blkaddr == BLKADDR_NIX0)
@@ -862,6 +869,71 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused)
 
 RVU_DEBUG_SEQ_FOPS(rvu_pf_cgx_map, rvu_pf_cgx_map_display, NULL);
 
+static int rvu_dbg_rvu_fwdata_display(struct seq_file *s, void *unused)
+{
+	struct rvu *rvu = s->private;
+	struct rvu_fwdata *fwdata;
+	u8 mac[ETH_ALEN];
+	int count = 0, i;
+
+	if (!rvu->fwdata)
+		return -EAGAIN;
+
+	fwdata = rvu->fwdata;
+	seq_puts(s, "\nRVU Firmware Data:\n");
+	seq_puts(s, "\n\t\tPTP INFORMATION\n");
+	seq_puts(s, "\t\t===============\n");
+	seq_printf(s, "\t\texternal clockrate \t :%x\n",
+		   fwdata->ptp_ext_clk_rate);
+	seq_printf(s, "\t\texternal timestamp \t :%x\n",
+		   fwdata->ptp_ext_tstamp);
+	seq_puts(s, "\n");
+
+	seq_puts(s, "\n\t\tSDP CHANNEL INFORMATION\n");
+	seq_puts(s, "\t\t=======================\n");
+	seq_printf(s, "\t\tValid \t\t\t :%x\n", fwdata->channel_data.valid);
+	seq_printf(s, "\t\tNode ID \t\t :%x\n",
+		   fwdata->channel_data.info.node_id);
+	seq_printf(s, "\t\tNumber of VFs  \t\t :%x\n",
+		   fwdata->channel_data.info.max_vfs);
+	seq_printf(s, "\t\tNumber of PF-Rings \t :%x\n",
+		   fwdata->channel_data.info.num_pf_rings);
+	seq_printf(s, "\t\tPF SRN \t\t\t :%x\n",
+		   fwdata->channel_data.info.pf_srn);
+	seq_puts(s, "\n");
+
+	seq_puts(s, "\n\t\tPF-INDEX  MACADDRESS\n");
+	seq_puts(s, "\t\t====================\n");
+	for (i = 0; i < PF_MACNUM_MAX; i++) {
+		u64_to_ether_addr(fwdata->pf_macs[i], mac);
+		if (!is_zero_ether_addr(mac)) {
+			seq_printf(s, "\t\t  %d       %pM\n", i, mac);
+			count++;
+		}
+	}
+
+	if (!count)
+		seq_puts(s, "\t\tNo valid address found\n");
+
+	seq_puts(s, "\n\t\tVF-INDEX  MACADDRESS\n");
+	seq_puts(s, "\t\t====================\n");
+	count = 0;
+	for (i = 0; i < VF_MACNUM_MAX; i++) {
+		u64_to_ether_addr(fwdata->vf_macs[i], mac);
+		if (!is_zero_ether_addr(mac)) {
+			seq_printf(s, "\t\t  %d       %pM\n", i, mac);
+			count++;
+		}
+	}
+
+	if (!count)
+		seq_puts(s, "\t\tNo valid address found\n");
+
+	return 0;
+}
+
+RVU_DEBUG_SEQ_FOPS(rvu_fwdata, rvu_fwdata_display, NULL);
+
 static bool rvu_dbg_is_valid_lf(struct rvu *rvu, int blkaddr, int lf,
 				u16 *pcifunc)
 {
@@ -917,19 +989,18 @@ static void print_npa_qsize(struct seq_file *m, struct rvu_pfvf *pfvf)
 /* The 'qsize' entry dumps current Aura/Pool context Qsize
  * and each context's current enable/disable status in a bitmap.
  */
-static int rvu_dbg_qsize_display(struct seq_file *filp, void *unsused,
+static int rvu_dbg_qsize_display(struct seq_file *s, void *unsused,
 				 int blktype)
 {
-	void (*print_qsize)(struct seq_file *filp,
+	void (*print_qsize)(struct seq_file *s,
 			    struct rvu_pfvf *pfvf) = NULL;
-	struct dentry *current_dir;
 	struct rvu_pfvf *pfvf;
 	struct rvu *rvu;
 	int qsize_id;
 	u16 pcifunc;
 	int blkaddr;
 
-	rvu = filp->private;
+	rvu = s->private;
 	switch (blktype) {
 	case BLKTYPE_NPA:
 		qsize_id = rvu->rvu_dbg.npa_qsize_id;
@@ -945,32 +1016,28 @@ static int rvu_dbg_qsize_display(struct seq_file *filp, void *unsused,
 		return -EINVAL;
 	}
 
-	if (blktype == BLKTYPE_NPA) {
+	if (blktype == BLKTYPE_NPA)
 		blkaddr = BLKADDR_NPA;
-	} else {
-		current_dir = filp->file->f_path.dentry->d_parent;
-		blkaddr = (!strcmp(current_dir->d_name.name, "nix1") ?
-				   BLKADDR_NIX1 : BLKADDR_NIX0);
-	}
+	else
+		blkaddr = debugfs_get_aux_num(s->file);
 
 	if (!rvu_dbg_is_valid_lf(rvu, blkaddr, qsize_id, &pcifunc))
 		return -EINVAL;
 
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
-	print_qsize(filp, pfvf);
+	print_qsize(s, pfvf);
 
 	return 0;
 }
 
-static ssize_t rvu_dbg_qsize_write(struct file *filp,
+static ssize_t rvu_dbg_qsize_write(struct file *file,
 				   const char __user *buffer, size_t count,
 				   loff_t *ppos, int blktype)
 {
 	char *blk_string = (blktype == BLKTYPE_NPA) ? "npa" : "nix";
-	struct seq_file *seqfile = filp->private_data;
+	struct seq_file *seqfile = file->private_data;
 	char *cmd_buf, *cmd_buf_tmp, *subtoken;
 	struct rvu *rvu = seqfile->private;
-	struct dentry *current_dir;
 	int blkaddr;
 	u16 pcifunc;
 	int ret, lf;
@@ -996,13 +1063,10 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp,
 		goto qsize_write_done;
 	}
 
-	if (blktype == BLKTYPE_NPA) {
+	if (blktype == BLKTYPE_NPA)
 		blkaddr = BLKADDR_NPA;
-	} else {
-		current_dir = filp->f_path.dentry->d_parent;
-		blkaddr = (!strcmp(current_dir->d_name.name, "nix1") ?
-				   BLKADDR_NIX1 : BLKADDR_NIX0);
-	}
+	else
+		blkaddr = debugfs_get_aux_num(file);
 
 	if (!rvu_dbg_is_valid_lf(rvu, blkaddr, lf, &pcifunc)) {
 		ret = -EINVAL;
@@ -1039,6 +1103,11 @@ static void print_npa_aura_ctx(struct seq_file *m, struct npa_aq_enq_rsp *rsp)
 	struct npa_aura_s *aura = &rsp->aura;
 	struct rvu *rvu = m->private;
 
+	if (is_cn20k(rvu->pdev)) {
+		print_npa_cn20k_aura_ctx(m, (struct npa_cn20k_aq_enq_rsp *)rsp);
+		return;
+	}
+
 	seq_printf(m, "W0: Pool addr\t\t%llx\n", aura->pool_addr);
 
 	seq_printf(m, "W1: ena\t\t\t%d\nW1: pool caching\t%d\n",
@@ -1087,6 +1156,11 @@ static void print_npa_pool_ctx(struct seq_file *m, struct npa_aq_enq_rsp *rsp)
 	struct npa_pool_s *pool = &rsp->pool;
 	struct rvu *rvu = m->private;
 
+	if (is_cn20k(rvu->pdev)) {
+		print_npa_cn20k_pool_ctx(m, (struct npa_cn20k_aq_enq_rsp *)rsp);
+		return;
+	}
+
 	seq_printf(m, "W0: Stack base\t\t%llx\n", pool->stack_base);
 
 	seq_printf(m, "W1: ena \t\t%d\nW1: nat_align \t\t%d\n",
@@ -1589,6 +1663,9 @@ static void print_tm_tree(struct seq_file *m,
 	int blkaddr;
 	u64 cfg;
 
+	if (!sq_ctx->ena)
+		return;
+
 	blkaddr = nix_hw->blkaddr;
 	schq = sq_ctx->smq;
 
@@ -1947,10 +2024,16 @@ static void print_nix_sq_ctx(struct seq_file *m, struct nix_aq_enq_rsp *rsp)
 	struct nix_hw *nix_hw = m->private;
 	struct rvu *rvu = nix_hw->rvu;
 
+	if (is_cn20k(rvu->pdev)) {
+		print_nix_cn20k_sq_ctx(m, (struct nix_cn20k_sq_ctx_s *)sq_ctx);
+		return;
+	}
+
 	if (!is_rvu_otx2(rvu)) {
 		print_nix_cn10k_sq_ctx(m, (struct nix_cn10k_sq_ctx_s *)sq_ctx);
 		return;
 	}
+
 	seq_printf(m, "W0: sqe_way_mask \t\t%d\nW0: cq \t\t\t\t%d\n",
 		   sq_ctx->sqe_way_mask, sq_ctx->cq);
 	seq_printf(m, "W0: sdp_mcast \t\t\t%d\nW0: substream \t\t\t0x%03x\n",
@@ -2041,7 +2124,9 @@ static void print_nix_cn10k_rq_ctx(struct seq_file *m,
 	seq_printf(m, "W1: ipsecd_drop_ena \t\t%d\nW1: chi_ena \t\t\t%d\n\n",
 		   rq_ctx->ipsecd_drop_ena, rq_ctx->chi_ena);
 
-	seq_printf(m, "W2: band_prof_id \t\t%d\n", rq_ctx->band_prof_id);
+	seq_printf(m, "W2: band_prof_id \t\t%d\n",
+		   (u16)rq_ctx->band_prof_id_h << 10 | rq_ctx->band_prof_id);
+
 	seq_printf(m, "W2: policer_ena \t\t%d\n", rq_ctx->policer_ena);
 	seq_printf(m, "W2: spb_sizem1 \t\t\t%d\n", rq_ctx->spb_sizem1);
 	seq_printf(m, "W2: wqe_skip \t\t\t%d\nW2: sqb_ena \t\t\t%d\n",
@@ -2163,6 +2248,11 @@ static void print_nix_cq_ctx(struct seq_file *m, struct nix_aq_enq_rsp *rsp)
 	struct nix_hw *nix_hw = m->private;
 	struct rvu *rvu = nix_hw->rvu;
 
+	if (is_cn20k(rvu->pdev)) {
+		print_nix_cn20k_cq_ctx(m, (struct nix_cn20k_aq_enq_rsp *)rsp);
+		return;
+	}
+
 	seq_printf(m, "W0: base \t\t\t%llx\n\n", cq_ctx->base);
 
 	seq_printf(m, "W1: wrptr \t\t\t%llx\n", (u64)cq_ctx->wrptr);
@@ -2192,6 +2282,7 @@ static void print_nix_cq_ctx(struct seq_file *m, struct nix_aq_enq_rsp *rsp)
 		   cq_ctx->cq_err_int_ena, cq_ctx->cq_err_int);
 	seq_printf(m, "W3: qsize \t\t\t%d\nW3:caching \t\t\t%d\n",
 		   cq_ctx->qsize, cq_ctx->caching);
+
 	seq_printf(m, "W3: substream \t\t\t0x%03x\nW3: ena \t\t\t%d\n",
 		   cq_ctx->substream, cq_ctx->ena);
 	if (!is_rvu_otx2(rvu)) {
@@ -2553,7 +2644,10 @@ static void print_band_prof_ctx(struct seq_file *m,
 		(prof->rc_action == 1) ? "DROP" : "RED";
 	seq_printf(m, "W1: rc_action\t\t%s\n", str);
 	seq_printf(m, "W1: meter_algo\t\t%d\n", prof->meter_algo);
-	seq_printf(m, "W1: band_prof_id\t%d\n", prof->band_prof_id);
+
+	seq_printf(m, "W1: band_prof_id\t%d\n",
+		   (u16)prof->band_prof_id_h << 7 | prof->band_prof_id);
+
 	seq_printf(m, "W1: hl_en\t\t%d\n", prof->hl_en);
 
 	seq_printf(m, "W2: ts\t\t\t%lld\n", (u64)prof->ts);
@@ -2626,10 +2720,10 @@ static int rvu_dbg_nix_band_prof_ctx_display(struct seq_file *m, void *unused)
 			pcifunc = ipolicer->pfvf_map[idx];
 			if (!(pcifunc & RVU_PFVF_FUNC_MASK))
 				seq_printf(m, "Allocated to :: PF %d\n",
-					   rvu_get_pf(pcifunc));
+					   rvu_get_pf(rvu->pdev, pcifunc));
 			else
 				seq_printf(m, "Allocated to :: PF %d VF %d\n",
-					   rvu_get_pf(pcifunc),
+					   rvu_get_pf(rvu->pdev, pcifunc),
 					   (pcifunc & RVU_PFVF_FUNC_MASK) - 1);
 			print_band_prof_ctx(m, &aq_rsp.prof);
 		}
@@ -2704,8 +2798,8 @@ static void rvu_dbg_nix_init(struct rvu *rvu, int blkaddr)
 			    &rvu_dbg_nix_ndc_tx_hits_miss_fops);
 	debugfs_create_file("ndc_rx_hits_miss", 0600, rvu->rvu_dbg.nix, nix_hw,
 			    &rvu_dbg_nix_ndc_rx_hits_miss_fops);
-	debugfs_create_file("qsize", 0600, rvu->rvu_dbg.nix, rvu,
-			    &rvu_dbg_nix_qsize_fops);
+	debugfs_create_file_aux_num("qsize", 0600, rvu->rvu_dbg.nix, rvu,
+			    blkaddr, &rvu_dbg_nix_qsize_fops);
 	debugfs_create_file("ingress_policer_ctx", 0600, rvu->rvu_dbg.nix, nix_hw,
 			    &rvu_dbg_nix_band_prof_ctx_fops);
 	debugfs_create_file("ingress_policer_rsrc", 0600, rvu->rvu_dbg.nix, nix_hw,
@@ -2722,6 +2816,9 @@ static void rvu_dbg_npa_init(struct rvu *rvu)
 			    &rvu_dbg_npa_aura_ctx_fops);
 	debugfs_create_file("pool_ctx", 0600, rvu->rvu_dbg.npa, rvu,
 			    &rvu_dbg_npa_pool_ctx_fops);
+
+	if (is_cn20k(rvu->pdev)) /* NDC not appliable for cn20k */
+		return;
 	debugfs_create_file("ndc_cache", 0600, rvu->rvu_dbg.npa, rvu,
 			    &rvu_dbg_npa_ndc_cache_fops);
 	debugfs_create_file("ndc_hits_miss", 0600, rvu->rvu_dbg.npa, rvu,
@@ -2854,28 +2951,14 @@ static int cgx_print_stats(struct seq_file *s, int lmac_id)
 	return err;
 }
 
-static int rvu_dbg_derive_lmacid(struct seq_file *filp, int *lmac_id)
+static int rvu_dbg_derive_lmacid(struct seq_file *s)
 {
-	struct dentry *current_dir;
-	char *buf;
-
-	current_dir = filp->file->f_path.dentry->d_parent;
-	buf = strrchr(current_dir->d_name.name, 'c');
-	if (!buf)
-		return -EINVAL;
-
-	return kstrtoint(buf + 1, 10, lmac_id);
+	return debugfs_get_aux_num(s->file);
 }
 
-static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused)
+static int rvu_dbg_cgx_stat_display(struct seq_file *s, void *unused)
 {
-	int lmac_id, err;
-
-	err = rvu_dbg_derive_lmacid(filp, &lmac_id);
-	if (!err)
-		return cgx_print_stats(filp, lmac_id);
-
-	return err;
+	return cgx_print_stats(s, rvu_dbg_derive_lmacid(s));
 }
 
 RVU_DEBUG_SEQ_FOPS(cgx_stat, cgx_stat_display, NULL);
@@ -2933,18 +3016,103 @@ static int cgx_print_dmac_flt(struct seq_file *s, int lmac_id)
 	return 0;
 }
 
-static int rvu_dbg_cgx_dmac_flt_display(struct seq_file *filp, void *unused)
+static int rvu_dbg_cgx_dmac_flt_display(struct seq_file *s, void *unused)
 {
-	int err, lmac_id;
+	return cgx_print_dmac_flt(s, rvu_dbg_derive_lmacid(s));
+}
 
-	err = rvu_dbg_derive_lmacid(filp, &lmac_id);
-	if (!err)
-		return cgx_print_dmac_flt(filp, lmac_id);
+RVU_DEBUG_SEQ_FOPS(cgx_dmac_flt, cgx_dmac_flt_display, NULL);
 
-	return err;
+static int cgx_print_fwdata(struct seq_file *s, int lmac_id)
+{
+	struct cgx_lmac_fwdata_s *fwdata;
+	void *cgxd = s->private;
+	struct phy_s *phy;
+	struct rvu *rvu;
+	int cgx_id, i;
+
+	rvu = pci_get_drvdata(pci_get_device(PCI_VENDOR_ID_CAVIUM,
+					     PCI_DEVID_OCTEONTX2_RVU_AF, NULL));
+	if (!rvu)
+		return -ENODEV;
+
+	if (!rvu->fwdata)
+		return -EAGAIN;
+
+	cgx_id = cgx_get_cgxid(cgxd);
+
+	if (rvu->hw->lmac_per_cgx == CGX_LMACS_USX)
+		fwdata =  &rvu->fwdata->cgx_fw_data_usx[cgx_id][lmac_id];
+	else
+		fwdata =  &rvu->fwdata->cgx_fw_data[cgx_id][lmac_id];
+
+	seq_puts(s, "\nFIRMWARE SHARED:\n");
+	seq_puts(s, "\t\tSUPPORTED LINK INFORMATION\t\t\n");
+	seq_puts(s, "\t\t==========================\n");
+	seq_printf(s, "\t\t Link modes \t\t :%llx\n",
+		   fwdata->supported_link_modes);
+	seq_printf(s, "\t\t Autoneg \t\t :%llx\n", fwdata->supported_an);
+	seq_printf(s, "\t\t FEC \t\t\t :%llx\n", fwdata->supported_fec);
+	seq_puts(s, "\n");
+
+	seq_puts(s, "\t\tADVERTISED LINK INFORMATION\t\t\n");
+	seq_puts(s, "\t\t==========================\n");
+	seq_printf(s, "\t\t Link modes \t\t :%llx\n",
+		   (u64)fwdata->advertised_link_modes);
+	seq_printf(s, "\t\t Autoneg \t\t :%x\n", fwdata->advertised_an);
+	seq_printf(s, "\t\t FEC \t\t\t :%llx\n", fwdata->advertised_fec);
+	seq_puts(s, "\n");
+
+	seq_puts(s, "\t\tLMAC CONFIG\t\t\n");
+	seq_puts(s, "\t\t============\n");
+	seq_printf(s, "\t\t rw_valid  \t\t :%x\n",  fwdata->rw_valid);
+	seq_printf(s, "\t\t lmac_type \t\t :%x\n", fwdata->lmac_type);
+	seq_printf(s, "\t\t portm_idx \t\t :%x\n", fwdata->portm_idx);
+	seq_printf(s, "\t\t mgmt_port \t\t :%x\n", fwdata->mgmt_port);
+	seq_printf(s, "\t\t Link modes own \t :%llx\n",
+		   (u64)fwdata->advertised_link_modes_own);
+	seq_puts(s, "\n");
+
+	seq_puts(s, "\n\t\tEEPROM DATA\n");
+	seq_puts(s, "\t\t===========\n");
+	seq_printf(s, "\t\t sff_id \t\t :%x\n", fwdata->sfp_eeprom.sff_id);
+	seq_puts(s, "\t\t data \t\t\t :\n");
+	seq_puts(s, "\t\t");
+	for (i = 0; i < SFP_EEPROM_SIZE; i++) {
+		seq_printf(s, "%x", fwdata->sfp_eeprom.buf[i]);
+		if ((i + 1) % 16 == 0) {
+			seq_puts(s, "\n");
+			seq_puts(s, "\t\t");
+		}
+	}
+	seq_puts(s, "\n");
+
+	phy = &fwdata->phy;
+	seq_puts(s, "\n\t\tPHY INFORMATION\n");
+	seq_puts(s, "\t\t===============\n");
+	seq_printf(s, "\t\t Mod type configurable \t\t :%x\n",
+		   phy->misc.can_change_mod_type);
+	seq_printf(s, "\t\t Mod type \t\t\t :%x\n", phy->misc.mod_type);
+	seq_printf(s, "\t\t Support FEC \t\t\t :%x\n", phy->misc.has_fec_stats);
+	seq_printf(s, "\t\t RSFEC corrected words \t\t :%x\n",
+		   phy->fec_stats.rsfec_corr_cws);
+	seq_printf(s, "\t\t RSFEC uncorrected words \t :%x\n",
+		   phy->fec_stats.rsfec_uncorr_cws);
+	seq_printf(s, "\t\t BRFEC corrected words \t\t :%x\n",
+		   phy->fec_stats.brfec_corr_blks);
+	seq_printf(s, "\t\t BRFEC uncorrected words \t :%x\n",
+		   phy->fec_stats.brfec_uncorr_blks);
+	seq_puts(s, "\n");
+
+	return 0;
 }
 
-RVU_DEBUG_SEQ_FOPS(cgx_dmac_flt, cgx_dmac_flt_display, NULL);
+static int rvu_dbg_cgx_fwdata_display(struct seq_file *s, void *unused)
+{
+	return cgx_print_fwdata(s, rvu_dbg_derive_lmacid(s));
+}
+
+RVU_DEBUG_SEQ_FOPS(cgx_fwdata, cgx_fwdata_display, NULL);
 
 static void rvu_dbg_cgx_init(struct rvu *rvu)
 {
@@ -2980,11 +3148,14 @@ static void rvu_dbg_cgx_init(struct rvu *rvu)
 			rvu->rvu_dbg.lmac =
 				debugfs_create_dir(dname, rvu->rvu_dbg.cgx);
 
-			debugfs_create_file("stats", 0600, rvu->rvu_dbg.lmac,
-					    cgx, &rvu_dbg_cgx_stat_fops);
-			debugfs_create_file("mac_filter", 0600,
-					    rvu->rvu_dbg.lmac, cgx,
+			debugfs_create_file_aux_num("stats", 0600, rvu->rvu_dbg.lmac,
+					    cgx, lmac_id, &rvu_dbg_cgx_stat_fops);
+			debugfs_create_file_aux_num("mac_filter", 0600,
+					    rvu->rvu_dbg.lmac, cgx, lmac_id,
 					    &rvu_dbg_cgx_dmac_flt_fops);
+			debugfs_create_file("fwdata", 0600,
+					    rvu->rvu_dbg.lmac, cgx,
+					    &rvu_dbg_cgx_fwdata_fops);
 		}
 	}
 }
@@ -3006,10 +3177,10 @@ static void rvu_print_npc_mcam_info(struct seq_file *s,
 
 	if (!(pcifunc & RVU_PFVF_FUNC_MASK))
 		seq_printf(s, "\n\t\t Device \t\t: PF%d\n",
-			   rvu_get_pf(pcifunc));
+			   rvu_get_pf(rvu->pdev, pcifunc));
 	else
 		seq_printf(s, "\n\t\t Device \t\t: PF%d VF%d\n",
-			   rvu_get_pf(pcifunc),
+			   rvu_get_pf(rvu->pdev, pcifunc),
 			   (pcifunc & RVU_PFVF_FUNC_MASK) - 1);
 
 	if (entry_acnt) {
@@ -3072,13 +3243,13 @@ static int rvu_dbg_npc_mcam_info_display(struct seq_file *filp, void *unsued)
 	seq_puts(filp, "\n\t\t Current allocation\n");
 	seq_puts(filp, "\t\t====================\n");
 	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
-		pcifunc = (pf << RVU_PFVF_PF_SHIFT);
+		pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 		rvu_print_npc_mcam_info(filp, pcifunc, blkaddr);
 
 		cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
 		numvfs = (cfg >> 12) & 0xFF;
 		for (vf = 0; vf < numvfs; vf++) {
-			pcifunc = (pf << RVU_PFVF_PF_SHIFT) | (vf + 1);
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, (vf + 1));
 			rvu_print_npc_mcam_info(filp, pcifunc, blkaddr);
 		}
 	}
@@ -3349,7 +3520,7 @@ static int rvu_dbg_npc_mcam_show_rules(struct seq_file *s, void *unused)
 
 	mutex_lock(&mcam->lock);
 	list_for_each_entry(iter, &mcam->mcam_rules, list) {
-		pf = (iter->owner >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK;
+		pf = rvu_get_pf(rvu->pdev, iter->owner);
 		seq_printf(s, "\n\tInstalled by: PF%d ", pf);
 
 		if (iter->owner & RVU_PFVF_FUNC_MASK) {
@@ -3367,7 +3538,7 @@ static int rvu_dbg_npc_mcam_show_rules(struct seq_file *s, void *unused)
 		rvu_dbg_npc_mcam_show_flows(s, iter);
 		if (is_npc_intf_rx(iter->intf)) {
 			target = iter->rx_action.pf_func;
-			pf = (target >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK;
+			pf = rvu_get_pf(rvu->pdev, target);
 			seq_printf(s, "\tForward to: PF%d ", pf);
 
 			if (target & RVU_PFVF_FUNC_MASK) {
@@ -3814,6 +3985,9 @@ static void rvu_dbg_cpt_init(struct rvu *rvu, int blkaddr)
 
 static const char *rvu_get_dbg_dir_name(struct rvu *rvu)
 {
+	if (is_cn20k(rvu->pdev))
+		return "cn20k";
+
 	if (!is_rvu_otx2(rvu))
 		return "cn10k";
 	else
@@ -3831,6 +4005,9 @@ void rvu_dbg_init(struct rvu *rvu)
 		debugfs_create_file("lmtst_map_table", 0444, rvu->rvu_dbg.root,
 				    rvu, &rvu_dbg_lmtst_map_table_fops);
 
+	debugfs_create_file("rvu_fwdata", 0444, rvu->rvu_dbg.root, rvu,
+			    &rvu_dbg_rvu_fwdata_fops);
+
 	if (!cgx_get_cgxcnt_max())
 		goto create;
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index dab4deca893f..0f9953eaf1b0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -207,7 +207,7 @@ static void rvu_nix_unregister_interrupts(struct rvu *rvu)
 		rvu->irq_allocated[offs + NIX_AF_INT_VEC_RVU] = false;
 	}
 
-	for (i = NIX_AF_INT_VEC_AF_ERR; i < NIX_AF_INT_VEC_CNT; i++)
+	for (i = NIX_AF_INT_VEC_GEN; i < NIX_AF_INT_VEC_CNT; i++)
 		if (rvu->irq_allocated[offs + i]) {
 			free_irq(pci_irq_vector(rvu->pdev, offs + i), rvu_dl);
 			rvu->irq_allocated[offs + i] = false;
@@ -505,7 +505,9 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl)
 
 	rvu_reporters->nix_event_ctx = nix_event_context;
 	rvu_reporters->rvu_hw_nix_intr_reporter =
-		devlink_health_reporter_create(rvu_dl->dl, &rvu_hw_nix_intr_reporter_ops, 0, rvu);
+		devlink_health_reporter_create(rvu_dl->dl,
+					       &rvu_hw_nix_intr_reporter_ops,
+					       rvu);
 	if (IS_ERR(rvu_reporters->rvu_hw_nix_intr_reporter)) {
 		dev_warn(rvu->dev, "Failed to create hw_nix_intr reporter, err=%ld\n",
 			 PTR_ERR(rvu_reporters->rvu_hw_nix_intr_reporter));
@@ -513,7 +515,9 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl)
 	}
 
 	rvu_reporters->rvu_hw_nix_gen_reporter =
-		devlink_health_reporter_create(rvu_dl->dl, &rvu_hw_nix_gen_reporter_ops, 0, rvu);
+		devlink_health_reporter_create(rvu_dl->dl,
+					       &rvu_hw_nix_gen_reporter_ops,
+					       rvu);
 	if (IS_ERR(rvu_reporters->rvu_hw_nix_gen_reporter)) {
 		dev_warn(rvu->dev, "Failed to create hw_nix_gen reporter, err=%ld\n",
 			 PTR_ERR(rvu_reporters->rvu_hw_nix_gen_reporter));
@@ -521,7 +525,9 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl)
 	}
 
 	rvu_reporters->rvu_hw_nix_err_reporter =
-		devlink_health_reporter_create(rvu_dl->dl, &rvu_hw_nix_err_reporter_ops, 0, rvu);
+		devlink_health_reporter_create(rvu_dl->dl,
+					       &rvu_hw_nix_err_reporter_ops,
+					       rvu);
 	if (IS_ERR(rvu_reporters->rvu_hw_nix_err_reporter)) {
 		dev_warn(rvu->dev, "Failed to create hw_nix_err reporter, err=%ld\n",
 			 PTR_ERR(rvu_reporters->rvu_hw_nix_err_reporter));
@@ -529,7 +535,9 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl)
 	}
 
 	rvu_reporters->rvu_hw_nix_ras_reporter =
-		devlink_health_reporter_create(rvu_dl->dl, &rvu_hw_nix_ras_reporter_ops, 0, rvu);
+		devlink_health_reporter_create(rvu_dl->dl,
+					       &rvu_hw_nix_ras_reporter_ops,
+					       rvu);
 	if (IS_ERR(rvu_reporters->rvu_hw_nix_ras_reporter)) {
 		dev_warn(rvu->dev, "Failed to create hw_nix_ras reporter, err=%ld\n",
 			 PTR_ERR(rvu_reporters->rvu_hw_nix_ras_reporter));
@@ -1051,7 +1059,9 @@ static int rvu_npa_register_reporters(struct rvu_devlink *rvu_dl)
 
 	rvu_reporters->npa_event_ctx = npa_event_context;
 	rvu_reporters->rvu_hw_npa_intr_reporter =
-		devlink_health_reporter_create(rvu_dl->dl, &rvu_hw_npa_intr_reporter_ops, 0, rvu);
+		devlink_health_reporter_create(rvu_dl->dl,
+					       &rvu_hw_npa_intr_reporter_ops,
+					       rvu);
 	if (IS_ERR(rvu_reporters->rvu_hw_npa_intr_reporter)) {
 		dev_warn(rvu->dev, "Failed to create hw_npa_intr reporter, err=%ld\n",
 			 PTR_ERR(rvu_reporters->rvu_hw_npa_intr_reporter));
@@ -1059,7 +1069,9 @@ static int rvu_npa_register_reporters(struct rvu_devlink *rvu_dl)
 	}
 
 	rvu_reporters->rvu_hw_npa_gen_reporter =
-		devlink_health_reporter_create(rvu_dl->dl, &rvu_hw_npa_gen_reporter_ops, 0, rvu);
+		devlink_health_reporter_create(rvu_dl->dl,
+					       &rvu_hw_npa_gen_reporter_ops,
+					       rvu);
 	if (IS_ERR(rvu_reporters->rvu_hw_npa_gen_reporter)) {
 		dev_warn(rvu->dev, "Failed to create hw_npa_gen reporter, err=%ld\n",
 			 PTR_ERR(rvu_reporters->rvu_hw_npa_gen_reporter));
@@ -1067,7 +1079,9 @@ static int rvu_npa_register_reporters(struct rvu_devlink *rvu_dl)
 	}
 
 	rvu_reporters->rvu_hw_npa_err_reporter =
-		devlink_health_reporter_create(rvu_dl->dl, &rvu_hw_npa_err_reporter_ops, 0, rvu);
+		devlink_health_reporter_create(rvu_dl->dl,
+					       &rvu_hw_npa_err_reporter_ops,
+					       rvu);
 	if (IS_ERR(rvu_reporters->rvu_hw_npa_err_reporter)) {
 		dev_warn(rvu->dev, "Failed to create hw_npa_err reporter, err=%ld\n",
 			 PTR_ERR(rvu_reporters->rvu_hw_npa_err_reporter));
@@ -1075,7 +1089,9 @@ static int rvu_npa_register_reporters(struct rvu_devlink *rvu_dl)
 	}
 
 	rvu_reporters->rvu_hw_npa_ras_reporter =
-		devlink_health_reporter_create(rvu_dl->dl, &rvu_hw_npa_ras_reporter_ops, 0, rvu);
+		devlink_health_reporter_create(rvu_dl->dl,
+					       &rvu_hw_npa_ras_reporter_ops,
+					       rvu);
 	if (IS_ERR(rvu_reporters->rvu_hw_npa_ras_reporter)) {
 		dev_warn(rvu->dev, "Failed to create hw_npa_ras reporter, err=%ld\n",
 			 PTR_ERR(rvu_reporters->rvu_hw_npa_ras_reporter));
@@ -1217,7 +1233,8 @@ static int rvu_af_dl_dwrr_mtu_set(struct devlink *devlink, u32 id,
 }
 
 static int rvu_af_dl_dwrr_mtu_get(struct devlink *devlink, u32 id,
-				  struct devlink_param_gset_ctx *ctx)
+				  struct devlink_param_gset_ctx *ctx,
+				  struct netlink_ext_ack *extack)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
 	struct rvu *rvu = rvu_dl->rvu;
@@ -1243,7 +1260,8 @@ enum rvu_af_dl_param_id {
 };
 
 static int rvu_af_npc_exact_feature_get(struct devlink *devlink, u32 id,
-					struct devlink_param_gset_ctx *ctx)
+					struct devlink_param_gset_ctx *ctx,
+					struct netlink_ext_ack *extack)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
 	struct rvu *rvu = rvu_dl->rvu;
@@ -1298,7 +1316,8 @@ static int rvu_af_npc_exact_feature_validate(struct devlink *devlink, u32 id,
 }
 
 static int rvu_af_dl_npc_mcam_high_zone_percent_get(struct devlink *devlink, u32 id,
-						    struct devlink_param_gset_ctx *ctx)
+						    struct devlink_param_gset_ctx *ctx,
+						    struct netlink_ext_ack *extack)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
 	struct rvu *rvu = rvu_dl->rvu;
@@ -1360,7 +1379,8 @@ static int rvu_af_dl_npc_mcam_high_zone_percent_validate(struct devlink *devlink
 }
 
 static int rvu_af_dl_npc_def_rule_cntr_get(struct devlink *devlink, u32 id,
-					   struct devlink_param_gset_ctx *ctx)
+					   struct devlink_param_gset_ctx *ctx,
+					   struct netlink_ext_ack *extack)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
 	struct rvu *rvu = rvu_dl->rvu;
@@ -1386,7 +1406,8 @@ static int rvu_af_dl_npc_def_rule_cntr_set(struct devlink *devlink, u32 id,
 }
 
 static int rvu_af_dl_nix_maxlf_get(struct devlink *devlink, u32 id,
-				   struct devlink_param_gset_ctx *ctx)
+				   struct devlink_param_gset_ctx *ctx,
+				   struct netlink_ext_ack *extack)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
 	struct rvu *rvu = rvu_dl->rvu;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 613655fcd34f..2f485a930edd 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -315,7 +315,8 @@ static bool is_valid_txschq(struct rvu *rvu, int blkaddr,
 	if (lvl >= hw->cap.nix_tx_aggr_lvl) {
 		if ((nix_get_tx_link(rvu, map_func) !=
 		     nix_get_tx_link(rvu, pcifunc)) &&
-		     (rvu_get_pf(map_func) != rvu_get_pf(pcifunc)))
+		     (rvu_get_pf(rvu->pdev, map_func) !=
+				rvu_get_pf(rvu->pdev, pcifunc)))
 			return false;
 		else
 			return true;
@@ -339,7 +340,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf,
 	bool from_vf;
 	int err;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	if (!is_pf_cgxmapped(rvu, pf) && type != NIX_INTF_TYPE_LBK &&
 	    type != NIX_INTF_TYPE_SDP)
 		return 0;
@@ -416,7 +417,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf,
 		break;
 	case NIX_INTF_TYPE_SDP:
 		from_vf = !!(pcifunc & RVU_PFVF_FUNC_MASK);
-		parent_pf = &rvu->pf[rvu_get_pf(pcifunc)];
+		parent_pf = &rvu->pf[rvu_get_pf(rvu->pdev, pcifunc)];
 		sdp_info = parent_pf->sdp_info;
 		if (!sdp_info) {
 			dev_err(rvu->dev, "Invalid sdp_info pointer\n");
@@ -590,12 +591,12 @@ static int nix_bp_disable(struct rvu *rvu,
 	u16 chan_v;
 	u64 cfg;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	type = is_lbk_vf(rvu, pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX;
 	if (!is_pf_cgxmapped(rvu, pf) && type != NIX_INTF_TYPE_LBK)
 		return 0;
 
-	if (is_sdp_pfvf(pcifunc))
+	if (is_sdp_pfvf(rvu, pcifunc))
 		type = NIX_INTF_TYPE_SDP;
 
 	if (cpt_link && !rvu->hw->cpt_links)
@@ -736,9 +737,9 @@ static int nix_bp_enable(struct rvu *rvu,
 	u16 chan_v;
 	u64 cfg;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	type = is_lbk_vf(rvu, pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX;
-	if (is_sdp_pfvf(pcifunc))
+	if (is_sdp_pfvf(rvu, pcifunc))
 		type = NIX_INTF_TYPE_SDP;
 
 	/* Enable backpressure only for CGX mapped PFs and LBK/SDP interface */
@@ -1018,6 +1019,12 @@ static void nix_get_aq_req_smq(struct rvu *rvu, struct nix_aq_enq_req *req,
 {
 	struct nix_cn10k_aq_enq_req *aq_req;
 
+	if (is_cn20k(rvu->pdev)) {
+		*smq = ((struct nix_cn20k_aq_enq_req *)req)->sq.smq;
+		*smq_mask = ((struct nix_cn20k_aq_enq_req *)req)->sq_mask.smq;
+		return;
+	}
+
 	if (!is_rvu_otx2(rvu)) {
 		aq_req = (struct nix_cn10k_aq_enq_req *)req;
 		*smq = aq_req->sq.smq;
@@ -1148,36 +1155,36 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
 	case NIX_AQ_INSTOP_WRITE:
 		if (req->ctype == NIX_AQ_CTYPE_RQ)
 			memcpy(mask, &req->rq_mask,
-			       sizeof(struct nix_rq_ctx_s));
+			       NIX_MAX_CTX_SIZE);
 		else if (req->ctype == NIX_AQ_CTYPE_SQ)
 			memcpy(mask, &req->sq_mask,
-			       sizeof(struct nix_sq_ctx_s));
+			       NIX_MAX_CTX_SIZE);
 		else if (req->ctype == NIX_AQ_CTYPE_CQ)
 			memcpy(mask, &req->cq_mask,
-			       sizeof(struct nix_cq_ctx_s));
+			       NIX_MAX_CTX_SIZE);
 		else if (req->ctype == NIX_AQ_CTYPE_RSS)
 			memcpy(mask, &req->rss_mask,
-			       sizeof(struct nix_rsse_s));
+			       NIX_MAX_CTX_SIZE);
 		else if (req->ctype == NIX_AQ_CTYPE_MCE)
 			memcpy(mask, &req->mce_mask,
-			       sizeof(struct nix_rx_mce_s));
+			       NIX_MAX_CTX_SIZE);
 		else if (req->ctype == NIX_AQ_CTYPE_BANDPROF)
 			memcpy(mask, &req->prof_mask,
-			       sizeof(struct nix_bandprof_s));
+			       NIX_MAX_CTX_SIZE);
 		fallthrough;
 	case NIX_AQ_INSTOP_INIT:
 		if (req->ctype == NIX_AQ_CTYPE_RQ)
-			memcpy(ctx, &req->rq, sizeof(struct nix_rq_ctx_s));
+			memcpy(ctx, &req->rq, NIX_MAX_CTX_SIZE);
 		else if (req->ctype == NIX_AQ_CTYPE_SQ)
-			memcpy(ctx, &req->sq, sizeof(struct nix_sq_ctx_s));
+			memcpy(ctx, &req->sq, NIX_MAX_CTX_SIZE);
 		else if (req->ctype == NIX_AQ_CTYPE_CQ)
-			memcpy(ctx, &req->cq, sizeof(struct nix_cq_ctx_s));
+			memcpy(ctx, &req->cq, NIX_MAX_CTX_SIZE);
 		else if (req->ctype == NIX_AQ_CTYPE_RSS)
-			memcpy(ctx, &req->rss, sizeof(struct nix_rsse_s));
+			memcpy(ctx, &req->rss, NIX_MAX_CTX_SIZE);
 		else if (req->ctype == NIX_AQ_CTYPE_MCE)
-			memcpy(ctx, &req->mce, sizeof(struct nix_rx_mce_s));
+			memcpy(ctx, &req->mce, NIX_MAX_CTX_SIZE);
 		else if (req->ctype == NIX_AQ_CTYPE_BANDPROF)
-			memcpy(ctx, &req->prof, sizeof(struct nix_bandprof_s));
+			memcpy(ctx, &req->prof, NIX_MAX_CTX_SIZE);
 		break;
 	case NIX_AQ_INSTOP_NOP:
 	case NIX_AQ_INSTOP_READ:
@@ -1242,22 +1249,22 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
 		if (req->op == NIX_AQ_INSTOP_READ) {
 			if (req->ctype == NIX_AQ_CTYPE_RQ)
 				memcpy(&rsp->rq, ctx,
-				       sizeof(struct nix_rq_ctx_s));
+				       NIX_MAX_CTX_SIZE);
 			else if (req->ctype == NIX_AQ_CTYPE_SQ)
 				memcpy(&rsp->sq, ctx,
-				       sizeof(struct nix_sq_ctx_s));
+				       NIX_MAX_CTX_SIZE);
 			else if (req->ctype == NIX_AQ_CTYPE_CQ)
 				memcpy(&rsp->cq, ctx,
-				       sizeof(struct nix_cq_ctx_s));
+				       NIX_MAX_CTX_SIZE);
 			else if (req->ctype == NIX_AQ_CTYPE_RSS)
 				memcpy(&rsp->rss, ctx,
-				       sizeof(struct nix_rsse_s));
+				       NIX_MAX_CTX_SIZE);
 			else if (req->ctype == NIX_AQ_CTYPE_MCE)
 				memcpy(&rsp->mce, ctx,
-				       sizeof(struct nix_rx_mce_s));
+				       NIX_MAX_CTX_SIZE);
 			else if (req->ctype == NIX_AQ_CTYPE_BANDPROF)
 				memcpy(&rsp->prof, ctx,
-				       sizeof(struct nix_bandprof_s));
+				       NIX_MAX_CTX_SIZE);
 		}
 	}
 
@@ -1288,8 +1295,8 @@ static int rvu_nix_verify_aq_ctx(struct rvu *rvu, struct nix_hw *nix_hw,
 	/* Make copy of original context & mask which are required
 	 * for resubmission
 	 */
-	memcpy(&aq_req.cq_mask, &req->cq_mask, sizeof(struct nix_cq_ctx_s));
-	memcpy(&aq_req.cq, &req->cq, sizeof(struct nix_cq_ctx_s));
+	memcpy(&aq_req.cq_mask, &req->cq_mask, NIX_MAX_CTX_SIZE);
+	memcpy(&aq_req.cq, &req->cq, NIX_MAX_CTX_SIZE);
 
 	/* exclude fields which HW can update */
 	aq_req.cq_mask.cq_err       = 0;
@@ -1308,7 +1315,7 @@ static int rvu_nix_verify_aq_ctx(struct rvu *rvu, struct nix_hw *nix_hw,
 	 * updated fields are masked out for request and response
 	 * comparison
 	 */
-	for (word = 0; word < sizeof(struct nix_cq_ctx_s) / sizeof(u64);
+	for (word = 0; word < NIX_MAX_CTX_SIZE / sizeof(u64);
 	     word++) {
 		*(u64 *)((u8 *)&aq_rsp.cq + word * 8) &=
 			(*(u64 *)((u8 *)&aq_req.cq_mask + word * 8));
@@ -1316,14 +1323,14 @@ static int rvu_nix_verify_aq_ctx(struct rvu *rvu, struct nix_hw *nix_hw,
 			(*(u64 *)((u8 *)&aq_req.cq_mask + word * 8));
 	}
 
-	if (memcmp(&aq_req.cq, &aq_rsp.cq, sizeof(struct nix_cq_ctx_s)))
+	if (memcmp(&aq_req.cq, &aq_rsp.cq, NIX_MAX_CTX_SIZE))
 		return NIX_AF_ERR_AQ_CTX_RETRY_WRITE;
 
 	return 0;
 }
 
-static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
-			       struct nix_aq_enq_rsp *rsp)
+int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
+			struct nix_aq_enq_rsp *rsp)
 {
 	struct nix_hw *nix_hw;
 	int err, retries = 5;
@@ -1674,7 +1681,7 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 	}
 
 	intf = is_lbk_vf(rvu, pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX;
-	if (is_sdp_pfvf(pcifunc))
+	if (is_sdp_pfvf(rvu, pcifunc))
 		intf = NIX_INTF_TYPE_SDP;
 
 	err = nix_interface_init(rvu, pcifunc, intf, nixlf, rsp,
@@ -1798,7 +1805,8 @@ int rvu_mbox_handler_nix_mark_format_cfg(struct rvu *rvu,
 	rc = rvu_nix_reserve_mark_format(rvu, nix_hw, blkaddr, cfg);
 	if (rc < 0) {
 		dev_err(rvu->dev, "No mark_format_ctl for (pf:%d, vf:%d)",
-			rvu_get_pf(pcifunc), pcifunc & RVU_PFVF_FUNC_MASK);
+			rvu_get_pf(rvu->pdev,  pcifunc),
+				   pcifunc & RVU_PFVF_FUNC_MASK);
 		return NIX_AF_ERR_MARK_CFG_FAIL;
 	}
 
@@ -2050,7 +2058,7 @@ static void nix_clear_tx_xoff(struct rvu *rvu, int blkaddr,
 static int nix_get_tx_link(struct rvu *rvu, u16 pcifunc)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 cgx_id = 0, lmac_id = 0;
 
 	if (is_lbk_vf(rvu, pcifunc)) {/* LBK links */
@@ -2068,7 +2076,7 @@ static void nix_get_txschq_range(struct rvu *rvu, u16 pcifunc,
 				 int link, int *start, int *end)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 
 	/* LBK links */
 	if (is_lbk_vf(rvu, pcifunc) || is_rep_dev(rvu, pcifunc)) {
@@ -2426,7 +2434,7 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr,
 {
 	struct nix_smq_flush_ctx *smq_flush_ctx;
 	int err, restore_tx_en = 0, i;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 cgx_id = 0, lmac_id = 0;
 	u16 tl2_tl3_link_schq;
 	u8 link, link_level;
@@ -2820,7 +2828,7 @@ void rvu_nix_tx_tl2_cfg(struct rvu *rvu, int blkaddr, u16 pcifunc,
 {
 	struct rvu_hwinfo *hw = rvu->hw;
 	int lbk_link_start, lbk_links;
-	u8 pf = rvu_get_pf(pcifunc);
+	u8 pf = rvu_get_pf(rvu->pdev, pcifunc);
 	int schq;
 	u64 cfg;
 
@@ -3190,7 +3198,8 @@ static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw,
 	err = rvu_nix_blk_aq_enq_inst(rvu, nix_hw, &aq_req, NULL);
 	if (err) {
 		dev_err(rvu->dev, "Failed to setup Bcast MCE for PF%d:VF%d\n",
-			rvu_get_pf(pcifunc), pcifunc & RVU_PFVF_FUNC_MASK);
+			rvu_get_pf(rvu->pdev, pcifunc),
+				pcifunc & RVU_PFVF_FUNC_MASK);
 		return err;
 	}
 	return 0;
@@ -3458,7 +3467,7 @@ int nix_update_mce_list(struct rvu *rvu, u16 pcifunc,
 		dev_err(rvu->dev,
 			"%s: Idx %d > max MCE idx %d, for PF%d bcast list\n",
 			__func__, idx, mce_list->max,
-			pcifunc >> RVU_PFVF_PF_SHIFT);
+			rvu_get_pf(rvu->pdev, pcifunc));
 		return -EINVAL;
 	}
 
@@ -3510,7 +3519,8 @@ void nix_get_mce_list(struct rvu *rvu, u16 pcifunc, int type,
 	struct rvu_pfvf *pfvf;
 
 	if (!hw->cap.nix_rx_multicast ||
-	    !is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc & ~RVU_PFVF_FUNC_MASK))) {
+	    !is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev,
+			     pcifunc & ~RVU_PFVF_FUNC_MASK))) {
 		*mce_list = NULL;
 		*mce_idx = 0;
 		return;
@@ -3544,13 +3554,13 @@ static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc,
 	int pf;
 
 	/* skip multicast pkt replication for AF's VFs & SDP links */
-	if (is_lbk_vf(rvu, pcifunc) || is_sdp_pfvf(pcifunc))
+	if (is_lbk_vf(rvu, pcifunc) || is_sdp_pfvf(rvu, pcifunc))
 		return 0;
 
 	if (!hw->cap.nix_rx_multicast)
 		return 0;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	if (!is_pf_cgxmapped(rvu, pf))
 		return 0;
 
@@ -3619,7 +3629,7 @@ static int nix_setup_mce_tables(struct rvu *rvu, struct nix_hw *nix_hw)
 
 		for (idx = 0; idx < (numvfs + 1); idx++) {
 			/* idx-0 is for PF, followed by VFs */
-			pcifunc = (pf << RVU_PFVF_PF_SHIFT);
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 			pcifunc |= idx;
 			/* Add dummy entries now, so that we don't have to check
 			 * for whether AQ_OP should be INIT/WRITE later on.
@@ -4554,7 +4564,7 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 static void nix_find_link_frs(struct rvu *rvu,
 			      struct nix_frs_cfg *req, u16 pcifunc)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct rvu_pfvf *pfvf;
 	int maxlen, minlen;
 	int numvfs, hwvf;
@@ -4601,7 +4611,7 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
 {
 	struct rvu_hwinfo *hw = rvu->hw;
 	u16 pcifunc = req->hdr.pcifunc;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	int blkaddr, link = -1;
 	struct nix_hw *nix_hw;
 	struct rvu_pfvf *pfvf;
@@ -5046,7 +5056,7 @@ static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw)
 				    (ltdefs->rx_apad1.ltype_match << 4) |
 				    ltdefs->rx_apad1.ltype_mask);
 
-			/* Receive ethertype defination register defines layer
+			/* Receive ethertype definition register defines layer
 			 * information in NPC_RESULT_S to identify the Ethertype
 			 * location in L2 header. Used for Ethertype overwriting
 			 * in inline IPsec flow.
@@ -5251,7 +5261,7 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
 
 	rvu_switch_update_rules(rvu, pcifunc, true);
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	if (is_pf_cgxmapped(rvu, pf) && rvu->rep_mode)
 		rvu_rep_notify_pfvf_state(rvu, pcifunc, true);
 
@@ -5284,7 +5294,7 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req,
 	rvu_switch_update_rules(rvu, pcifunc, false);
 	rvu_cgx_tx_enable(rvu, pcifunc, true);
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	if (is_pf_cgxmapped(rvu, pf) && rvu->rep_mode)
 		rvu_rep_notify_pfvf_state(rvu, pcifunc, false);
 	return 0;
@@ -5296,7 +5306,7 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf)
 {
 	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	struct hwctx_disable_req ctx_req;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 	u64 sa_base;
@@ -5385,7 +5395,7 @@ static int rvu_nix_lf_ptp_tx_cfg(struct rvu *rvu, u16 pcifunc, bool enable)
 	int nixlf;
 	u64 cfg;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	if (!is_mac_feature_supported(rvu, pf, RVU_LMAC_FEAT_PTP))
 		return 0;
 
@@ -5808,6 +5818,8 @@ static void nix_ipolicer_freemem(struct rvu *rvu, struct nix_hw *nix_hw)
 	}
 }
 
+#define NIX_BW_PROF_HI_MASK	GENMASK(10, 7)
+
 static int nix_verify_bandprof(struct nix_cn10k_aq_enq_req *req,
 			       struct nix_hw *nix_hw, u16 pcifunc)
 {
@@ -5846,7 +5858,8 @@ static int nix_verify_bandprof(struct nix_cn10k_aq_enq_req *req,
 		return -EINVAL;
 
 	ipolicer = &nix_hw->ipolicer[hi_layer];
-	prof_idx = req->prof.band_prof_id;
+	prof_idx = FIELD_PREP(NIX_BW_PROF_HI_MASK, req->prof.band_prof_id_h);
+	prof_idx |= req->prof.band_prof_id;
 	if (prof_idx >= ipolicer->band_prof.max ||
 	    ipolicer->pfvf_map[prof_idx] != pcifunc)
 		return -EINVAL;
@@ -6011,8 +6024,10 @@ static int nix_ipolicer_map_leaf_midprofs(struct rvu *rvu,
 	aq_req->op = NIX_AQ_INSTOP_WRITE;
 	aq_req->qidx = leaf_prof;
 
-	aq_req->prof.band_prof_id = mid_prof;
+	aq_req->prof.band_prof_id = mid_prof & 0x7F;
 	aq_req->prof_mask.band_prof_id = GENMASK(6, 0);
+	aq_req->prof.band_prof_id_h = FIELD_GET(NIX_BW_PROF_HI_MASK, mid_prof);
+	aq_req->prof_mask.band_prof_id_h = GENMASK(3, 0);
 	aq_req->prof.hl_en = 1;
 	aq_req->prof_mask.hl_en = 1;
 
@@ -6021,6 +6036,8 @@ static int nix_ipolicer_map_leaf_midprofs(struct rvu *rvu,
 				       (struct nix_aq_enq_rsp *)aq_rsp);
 }
 
+#define NIX_RQ_PROF_HI_MASK	GENMASK(13, 10)
+
 int rvu_nix_setup_ratelimit_aggr(struct rvu *rvu, u16 pcifunc,
 				 u16 rq_idx, u16 match_id)
 {
@@ -6052,7 +6069,8 @@ int rvu_nix_setup_ratelimit_aggr(struct rvu *rvu, u16 pcifunc,
 		return 0;
 
 	/* Get the bandwidth profile ID mapped to this RQ */
-	leaf_prof = aq_rsp.rq.band_prof_id;
+	leaf_prof = FIELD_PREP(NIX_RQ_PROF_HI_MASK, aq_rsp.rq.band_prof_id_h);
+	leaf_prof |= aq_rsp.rq.band_prof_id;
 
 	ipolicer = &nix_hw->ipolicer[BAND_PROF_LEAF_LAYER];
 	ipolicer->match_id[leaf_prof] = match_id;
@@ -6090,7 +6108,10 @@ int rvu_nix_setup_ratelimit_aggr(struct rvu *rvu, u16 pcifunc,
 		 * to different RQs and marked with same match_id
 		 * are rate limited in a aggregate fashion
 		 */
-		mid_prof = aq_rsp.prof.band_prof_id;
+		mid_prof = FIELD_PREP(NIX_BW_PROF_HI_MASK,
+				      aq_rsp.prof.band_prof_id_h);
+		mid_prof |= aq_rsp.prof.band_prof_id;
+
 		rc = nix_ipolicer_map_leaf_midprofs(rvu, nix_hw,
 						    &aq_req, &aq_rsp,
 						    leaf_prof, mid_prof);
@@ -6212,7 +6233,8 @@ static void nix_clear_ratelimit_aggr(struct rvu *rvu, struct nix_hw *nix_hw,
 	if (!aq_rsp.prof.hl_en)
 		return;
 
-	mid_prof = aq_rsp.prof.band_prof_id;
+	mid_prof = FIELD_PREP(NIX_BW_PROF_HI_MASK, aq_rsp.prof.band_prof_id_h);
+	mid_prof |= aq_rsp.prof.band_prof_id;
 	ipolicer = &nix_hw->ipolicer[BAND_PROF_MID_LAYER];
 	ipolicer->ref_count[mid_prof]--;
 	/* If ref_count is zero, free mid layer profile */
@@ -6612,3 +6634,19 @@ unlock_grp:
 
 	return ret;
 }
+
+/* On CN10k and older series of silicons, hardware may incorrectly
+ * assert XOFF on certain channels. Issue a write on NIX_AF_RX_CHANX_CFG
+ * to broadcacst XON on the same.
+ */
+void rvu_block_bcast_xon(struct rvu *rvu, int blkaddr)
+{
+	struct rvu_block *block = &rvu->hw->block[blkaddr];
+	u64 cfg;
+
+	if (!block->implemented || is_cn20k(rvu->pdev))
+		return;
+
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(0));
+	rvu_write64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(0), cfg);
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
index 4f5ca5ab13a4..e2a33e46b48a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
@@ -464,6 +464,23 @@ int rvu_mbox_handler_npa_lf_free(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
+static void npa_aq_ndc_config(struct rvu *rvu, struct rvu_block *block)
+{
+	u64 cfg;
+
+	if (is_cn20k(rvu->pdev)) /* NDC not applicable to cn20k */
+		return;
+
+	/* Do not bypass NDC cache */
+	cfg = rvu_read64(rvu, block->addr, NPA_AF_NDC_CFG);
+	cfg &= ~0x03DULL;
+#ifdef CONFIG_NDC_DIS_DYNAMIC_CACHING
+	/* Disable caching of stack pages */
+	cfg |= 0x10ULL;
+#endif
+	rvu_write64(rvu, block->addr, NPA_AF_NDC_CFG, cfg);
+}
+
 static int npa_aq_init(struct rvu *rvu, struct rvu_block *block)
 {
 	u64 cfg;
@@ -479,14 +496,7 @@ static int npa_aq_init(struct rvu *rvu, struct rvu_block *block)
 	rvu_write64(rvu, block->addr, NPA_AF_GEN_CFG, cfg);
 #endif
 
-	/* Do not bypass NDC cache */
-	cfg = rvu_read64(rvu, block->addr, NPA_AF_NDC_CFG);
-	cfg &= ~0x03DULL;
-#ifdef CONFIG_NDC_DIS_DYNAMIC_CACHING
-	/* Disable caching of stack pages */
-	cfg |= 0x10ULL;
-#endif
-	rvu_write64(rvu, block->addr, NPA_AF_NDC_CFG, cfg);
+	npa_aq_ndc_config(rvu, block);
 
 	/* For CN10K NPA BATCH DMA set 35 cache lines */
 	if (!is_rvu_otx2(rvu)) {
@@ -567,6 +577,9 @@ int rvu_ndc_fix_locked_cacheline(struct rvu *rvu, int blkaddr)
 	int bank, max_bank, line, max_line, err;
 	u64 reg, ndc_af_const;
 
+	if (is_cn20k(rvu->pdev)) /* NDC not applicable to cn20k */
+		return 0;
+
 	/* Set the ENABLE bit(63) to '0' */
 	reg = rvu_read64(rvu, blkaddr, NDC_AF_CAMS_RD_INTERVAL);
 	rvu_write64(rvu, blkaddr, NDC_AF_CAMS_RD_INTERVAL, reg & GENMASK_ULL(62, 0));
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 821fe242f821..c7c70429eb6c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -147,7 +147,9 @@ static int npc_get_ucast_mcam_index(struct npc_mcam *mcam, u16 pcifunc,
 int npc_get_nixlf_mcam_index(struct npc_mcam *mcam,
 			     u16 pcifunc, int nixlf, int type)
 {
-	int pf = rvu_get_pf(pcifunc);
+	struct rvu_hwinfo *hw = container_of(mcam, struct rvu_hwinfo, mcam);
+	struct rvu *rvu = hw->rvu;
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	int index;
 
 	/* Check if this is for a PF */
@@ -698,7 +700,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 
 	/* RX_ACTION set to MCAST for CGX PF's */
 	if (hw->cap.nix_rx_multicast && pfvf->use_mce_list &&
-	    is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) {
+	    is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc))) {
 		*(u64 *)&action = 0;
 		action.op = NIX_RX_ACTIONOP_MCAST;
 		pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK);
@@ -820,24 +822,6 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 	rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
 }
 
-void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
-				bool enable)
-{
-	struct npc_mcam *mcam = &rvu->hw->mcam;
-	int blkaddr, index;
-
-	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
-	if (blkaddr < 0)
-		return;
-
-	/* Get 'pcifunc' of PF device */
-	pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK;
-
-	index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf,
-					 NIXLF_BCAST_ENTRY);
-	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
-}
-
 void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    u64 chan)
 {
@@ -1125,6 +1109,7 @@ void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc,
 static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
 				       int nixlf, bool enable)
 {
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	int index, blkaddr;
 
@@ -1133,9 +1118,12 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
 		return;
 
 	/* Ucast MCAM match entry of this PF/VF */
-	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
-					 nixlf, NIXLF_UCAST_ENTRY);
-	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
+	if (npc_is_feature_supported(rvu, BIT_ULL(NPC_DMAC),
+				     pfvf->nix_rx_intf)) {
+		index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+						 nixlf, NIXLF_UCAST_ENTRY);
+		npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
+	}
 
 	/* Nothing to do for VFs, on platforms where pkt replication
 	 * is not supported
@@ -3448,7 +3436,7 @@ int rvu_npc_set_parse_mode(struct rvu *rvu, u16 pcifunc, u64 mode, u8 dir,
 {
 	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	int blkaddr, nixlf, rc, intf_mode;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u64 rxpkind, txpkind;
 	u8 cgx_id, lmac_id;
 
@@ -3588,3 +3576,33 @@ int rvu_mbox_handler_npc_mcam_entry_stats(struct rvu *rvu,
 
 	return 0;
 }
+
+void rvu_npc_clear_ucast_entry(struct rvu *rvu, int pcifunc, int nixlf)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	struct rvu_npc_mcam_rule *rule;
+	int ucast_idx, blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return;
+
+	ucast_idx = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					     nixlf, NIXLF_UCAST_ENTRY);
+
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, ucast_idx, false);
+
+	npc_set_mcam_action(rvu, mcam, blkaddr, ucast_idx, 0);
+
+	npc_clear_mcam_entry(rvu, mcam, blkaddr, ucast_idx);
+
+	mutex_lock(&mcam->lock);
+	list_for_each_entry(rule, &mcam->mcam_rules, list) {
+		if (rule->entry == ucast_idx) {
+			list_del(&rule->list);
+			kfree(rule);
+			break;
+		}
+	}
+	mutex_unlock(&mcam->lock);
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
index 1b765045aa63..b56395ac5a74 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -606,8 +606,8 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf)
 		if (!npc_check_field(rvu, blkaddr, NPC_LB, intf))
 			*features &= ~BIT_ULL(NPC_OUTER_VID);
 
-	/* Set SPI flag only if AH/ESP and IPSEC_SPI are in the key */
-	if (npc_check_field(rvu, blkaddr, NPC_IPSEC_SPI, intf) &&
+	/* Allow extracting SPI field from AH and ESP headers at same offset */
+	if (npc_is_field_present(rvu, NPC_IPSEC_SPI, intf) &&
 	    (*features & (BIT_ULL(NPC_IPPROTO_ESP) | BIT_ULL(NPC_IPPROTO_AH))))
 		*features |= BIT_ULL(NPC_IPSEC_SPI);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
index d2661e7fabdb..999f6d93c7fe 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
@@ -1465,7 +1465,7 @@ static int rvu_npc_exact_update_table_entry(struct rvu *rvu, u8 cgx_id, u8 lmac_
 int rvu_npc_exact_promisc_disable(struct rvu *rvu, u16 pcifunc)
 {
 	struct npc_exact_table *table;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 cgx_id, lmac_id;
 	u32 drop_mcam_idx;
 	bool *promisc;
@@ -1512,7 +1512,7 @@ int rvu_npc_exact_promisc_disable(struct rvu *rvu, u16 pcifunc)
 int rvu_npc_exact_promisc_enable(struct rvu *rvu, u16 pcifunc)
 {
 	struct npc_exact_table *table;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 cgx_id, lmac_id;
 	u32 drop_mcam_idx;
 	bool *promisc;
@@ -1560,7 +1560,7 @@ int rvu_npc_exact_promisc_enable(struct rvu *rvu, u16 pcifunc)
 int rvu_npc_exact_mac_addr_reset(struct rvu *rvu, struct cgx_mac_addr_reset_req *req,
 				 struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u32 seq_id = req->index;
 	struct rvu_pfvf *pfvf;
 	u8 cgx_id, lmac_id;
@@ -1593,7 +1593,7 @@ int rvu_npc_exact_mac_addr_update(struct rvu *rvu,
 				  struct cgx_mac_addr_update_req *req,
 				  struct cgx_mac_addr_update_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct npc_exact_table_entry *entry;
 	struct npc_exact_table *table;
 	struct rvu_pfvf *pfvf;
@@ -1675,7 +1675,7 @@ int rvu_npc_exact_mac_addr_add(struct rvu *rvu,
 			       struct cgx_mac_addr_add_req *req,
 			       struct cgx_mac_addr_add_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct rvu_pfvf *pfvf;
 	u8 cgx_id, lmac_id;
 	int rc = 0;
@@ -1711,7 +1711,7 @@ int rvu_npc_exact_mac_addr_del(struct rvu *rvu,
 			       struct cgx_mac_addr_del_req *req,
 			       struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	int rc;
 
 	rc = rvu_npc_exact_del_table_entry_by_id(rvu, req->index);
@@ -1736,7 +1736,7 @@ int rvu_npc_exact_mac_addr_del(struct rvu *rvu,
 int rvu_npc_exact_mac_addr_set(struct rvu *rvu, struct cgx_mac_addr_set_or_get *req,
 			       struct cgx_mac_addr_set_or_get *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u32 seq_id = req->index;
 	struct rvu_pfvf *pfvf;
 	u8 cgx_id, lmac_id;
@@ -2001,7 +2001,7 @@ int rvu_npc_exact_init(struct rvu *rvu)
 		}
 
 		/* Filter rules are only for PF */
-		pcifunc = RVU_PFFUNC(i, 0);
+		pcifunc = RVU_PFFUNC(rvu->pdev, i, 0);
 
 		dev_dbg(rvu->dev,
 			"%s:Drop rule cgx=%d lmac=%d chan(val=0x%llx, mask=0x%llx\n",
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h
index 57a09328d46b..cb25cf478f1f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h
@@ -139,9 +139,7 @@ static struct npc_mcam_kex_hash npc_mkex_hash_default __maybe_unused = {
 #define NPC_MCAM_DROP_RULE_MAX 30
 #define NPC_MCAM_SDP_DROP_RULE_IDX 0
 
-#define RVU_PFFUNC(pf, func)	\
-	((((pf) & RVU_PFVF_PF_MASK) << RVU_PFVF_PF_SHIFT) | \
-	(((func) & RVU_PFVF_FUNC_MASK) << RVU_PFVF_FUNC_SHIFT))
+#define RVU_PFFUNC(pdev, pf, func) rvu_make_pcifunc(pdev, pf, func)
 
 enum npc_exact_opc_type {
 	NPC_EXACT_OPC_MEM,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c
index 052ae5923e3a..4415d0ce9aef 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c
@@ -39,7 +39,7 @@ static int rvu_rep_up_notify(struct rvu *rvu, struct rep_event *event)
 	struct rep_event *msg;
 	int pf;
 
-	pf = rvu_get_pf(event->pcifunc);
+	pf = rvu_get_pf(rvu->pdev, event->pcifunc);
 
 	if (event->event & RVU_EVENT_MAC_ADDR_CHANGE)
 		ether_addr_copy(pfvf->mac_addr, event->evt_data.mac);
@@ -60,6 +60,8 @@ static int rvu_rep_up_notify(struct rvu *rvu, struct rep_event *event)
 
 	otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pf);
 
+	otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pf);
+
 	mutex_unlock(&rvu->mbox_lock);
 	return 0;
 }
@@ -112,10 +114,10 @@ int rvu_rep_notify_pfvf_state(struct rvu *rvu, u16 pcifunc, bool enable)
 	struct rep_event *req;
 	int pf;
 
-	if (!is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc)))
+	if (!is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc)))
 		return 0;
 
-	pf = rvu_get_pf(rvu->rep_pcifunc);
+	pf = rvu_get_pf(rvu->pdev, rvu->rep_pcifunc);
 
 	mutex_lock(&rvu->mbox_lock);
 	req = otx2_mbox_alloc_msg_rep_event_up_notify(rvu, pf);
@@ -323,7 +325,7 @@ int rvu_rep_install_mcam_rules(struct rvu *rvu)
 		if (!is_pf_cgxmapped(rvu, pf))
 			continue;
 
-		pcifunc = pf << RVU_PFVF_PF_SHIFT;
+		pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 		rvu_get_nix_blkaddr(rvu, pcifunc);
 		rep = true;
 		for (i = 0; i < 2; i++) {
@@ -343,8 +345,7 @@ int rvu_rep_install_mcam_rules(struct rvu *rvu)
 
 		rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL);
 		for (vf = 0; vf < numvfs; vf++) {
-			pcifunc = pf << RVU_PFVF_PF_SHIFT |
-				  ((vf + 1) & RVU_PFVF_FUNC_MASK);
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, vf + 1);
 			rvu_get_nix_blkaddr(rvu, pcifunc);
 
 			/* Skip installimg rules if nixlf is not attached */
@@ -375,7 +376,7 @@ int rvu_rep_install_mcam_rules(struct rvu *rvu)
 	spin_lock_init(&rvu->rep_evtq_lock);
 	INIT_LIST_HEAD(&rvu->rep_evtq_head);
 	INIT_WORK(&rvu->rep_evt_work, rvu_rep_wq_handler);
-	rvu->rep_evt_wq = alloc_workqueue("rep_evt_wq", 0, 0);
+	rvu->rep_evt_wq = alloc_workqueue("rep_evt_wq", WQ_PERCPU, 0);
 	if (!rvu->rep_evt_wq) {
 		dev_err(rvu->dev, "REP workqueue allocation failed\n");
 		return -ENOMEM;
@@ -452,7 +453,7 @@ int rvu_mbox_handler_get_rep_cnt(struct rvu *rvu, struct msg_req *req,
 	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
 		if (!is_pf_cgxmapped(rvu, pf))
 			continue;
-		pcifunc = pf << RVU_PFVF_PF_SHIFT;
+		pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 		rvu->rep2pfvf_map[rep] = pcifunc;
 		rsp->rep_pf_map[rep] = pcifunc;
 		rep++;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c
index 38cfe148f4b7..e4a5f9fa6fd4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c
@@ -17,9 +17,9 @@
 /* SDP PF number */
 static int sdp_pf_num[MAX_SDP] = {-1, -1};
 
-bool is_sdp_pfvf(u16 pcifunc)
+bool is_sdp_pfvf(struct rvu *rvu, u16 pcifunc)
 {
-	u16 pf = rvu_get_pf(pcifunc);
+	u16 pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u32 found = 0, i = 0;
 
 	while (i < MAX_SDP) {
@@ -34,9 +34,9 @@ bool is_sdp_pfvf(u16 pcifunc)
 	return true;
 }
 
-bool is_sdp_pf(u16 pcifunc)
+bool is_sdp_pf(struct rvu *rvu, u16 pcifunc)
 {
-	return (is_sdp_pfvf(pcifunc) &&
+	return (is_sdp_pfvf(rvu, pcifunc) &&
 		!(pcifunc & RVU_PFVF_FUNC_MASK));
 }
 
@@ -46,7 +46,7 @@ bool is_sdp_vf(struct rvu *rvu, u16 pcifunc)
 	if (!(pcifunc & ~RVU_PFVF_FUNC_MASK))
 		return (rvu->vf_devid == RVU_SDP_VF_DEVID);
 
-	return (is_sdp_pfvf(pcifunc) &&
+	return (is_sdp_pfvf(rvu, pcifunc) &&
 		!!(pcifunc & RVU_PFVF_FUNC_MASK));
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
index 77ac94cb2ec4..8e868f815de1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
@@ -13,6 +13,8 @@
 
 #define RVU_MULTI_BLK_VER		0x7ULL
 
+#define NIX_MAX_CTX_SIZE		128
+
 /* RVU Block Address Enumeration */
 enum rvu_block_addr_e {
 	BLKADDR_RVUM		= 0x0ULL,
@@ -33,7 +35,8 @@ enum rvu_block_addr_e {
 	BLKADDR_NDC_NIX1_RX	= 0x10ULL,
 	BLKADDR_NDC_NIX1_TX	= 0x11ULL,
 	BLKADDR_APR		= 0x16ULL,
-	BLK_COUNT		= 0x17ULL,
+	BLKADDR_MBOX		= 0x1bULL,
+	BLK_COUNT		= 0x1cULL,
 };
 
 /* RVU Block Type Enumeration */
@@ -49,7 +52,8 @@ enum rvu_block_type_e {
 	BLKTYPE_TIM  = 0x8,
 	BLKTYPE_CPT  = 0x9,
 	BLKTYPE_NDC  = 0xa,
-	BLKTYPE_MAX  = 0xa,
+	BLKTYPE_MBOX = 0x13,
+	BLKTYPE_MAX  = 0x13,
 };
 
 /* RVU Admin function Interrupt Vector Enumeration */
@@ -368,8 +372,12 @@ struct nix_cq_ctx_s {
 	u64 qsize		: 4;
 	u64 cq_err_int		: 8;
 	u64 cq_err_int_ena	: 8;
+	/* Ensure all context sizes are 128 bytes */
+	u64 padding[12];
 };
 
+static_assert(sizeof(struct nix_cq_ctx_s) == NIX_MAX_CTX_SIZE);
+
 /* CN10K NIX Receive queue context structure */
 struct nix_cn10k_rq_ctx_s {
 	u64 ena			: 1;
@@ -411,7 +419,8 @@ struct nix_cn10k_rq_ctx_s {
 	u64 rsvd_171		: 1;
 	u64 later_skip		: 6;
 	u64 xqe_imm_size	: 6;
-	u64 rsvd_189_184	: 6;
+	u64 band_prof_id_h	: 4;
+	u64 rsvd_189_188	: 2;
 	u64 xqe_imm_copy	: 1;
 	u64 xqe_hdr_split	: 1;
 	u64 xqe_drop		: 8; /* W3 */
@@ -458,6 +467,8 @@ struct nix_cn10k_rq_ctx_s {
 	u64 rsvd_1023_960;		/* W15 */
 };
 
+static_assert(sizeof(struct nix_cn10k_rq_ctx_s) == NIX_MAX_CTX_SIZE);
+
 /* CN10K NIX Send queue context structure */
 struct nix_cn10k_sq_ctx_s {
 	u64 ena                   : 1;
@@ -521,6 +532,8 @@ struct nix_cn10k_sq_ctx_s {
 	u64 rsvd_1023_1008        : 16;
 };
 
+static_assert(sizeof(struct nix_cn10k_sq_ctx_s) == NIX_MAX_CTX_SIZE);
+
 /* NIX Receive queue context structure */
 struct nix_rq_ctx_s {
 	u64 ena           : 1;
@@ -592,6 +605,8 @@ struct nix_rq_ctx_s {
 	u64 rsvd_1023_960;		/* W15 */
 };
 
+static_assert(sizeof(struct nix_rq_ctx_s) == NIX_MAX_CTX_SIZE);
+
 /* NIX sqe sizes */
 enum nix_maxsqesz {
 	NIX_MAXSQESZ_W16 = 0x0,
@@ -666,13 +681,18 @@ struct nix_sq_ctx_s {
 	u64 rsvd_1023_1008        : 16;
 };
 
+static_assert(sizeof(struct nix_sq_ctx_s) == NIX_MAX_CTX_SIZE);
+
 /* NIX Receive side scaling entry structure*/
 struct nix_rsse_s {
 	uint32_t rq			: 20;
 	uint32_t reserved_20_31		: 12;
-
+	/* Ensure all context sizes are minimum 128 bytes */
+	u64 padding[15];
 };
 
+static_assert(sizeof(struct nix_rsse_s) == NIX_MAX_CTX_SIZE);
+
 /* NIX receive multicast/mirror entry structure */
 struct nix_rx_mce_s {
 	uint64_t op         : 2;
@@ -682,8 +702,12 @@ struct nix_rx_mce_s {
 	uint64_t rsvd_31_24 : 8;
 	uint64_t pf_func    : 16;
 	uint64_t next       : 16;
+	/* Ensure all context sizes are minimum 128 bytes */
+	u64 padding[15];
 };
 
+static_assert(sizeof(struct nix_rx_mce_s) == NIX_MAX_CTX_SIZE);
+
 enum nix_band_prof_layers {
 	BAND_PROF_LEAF_LAYER = 0,
 	BAND_PROF_INVAL_LAYER = 1,
@@ -734,7 +758,8 @@ struct nix_bandprof_s {
 	uint64_t rc_action                   :  2;
 	uint64_t meter_algo                  :  2;
 	uint64_t band_prof_id                :  7;
-	uint64_t reserved_111_118            :  8;
+	uint64_t band_prof_id_h              :  4;
+	uint64_t reserved_115_118            :  4;
 	uint64_t hl_en                       :  1;
 	uint64_t reserved_120_127            :  8;
 	uint64_t ts                          : 48; /* W2 */
@@ -767,6 +792,8 @@ struct nix_bandprof_s {
 	uint64_t reserved_1008_1023          : 16;
 };
 
+static_assert(sizeof(struct nix_bandprof_s) == NIX_MAX_CTX_SIZE);
+
 enum nix_lsoalg {
 	NIX_LSOALG_NOP,
 	NIX_LSOALG_ADD_SEGNUM,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
index 268efb7c1c15..49ce38685a7e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
@@ -93,7 +93,7 @@ static int rvu_switch_install_rules(struct rvu *rvu)
 		if (!is_pf_cgxmapped(rvu, pf))
 			continue;
 
-		pcifunc = pf << 10;
+		pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 		/* rvu_get_nix_blkaddr sets up the corresponding NIX block
 		 * address and NIX RX and TX interfaces for a pcifunc.
 		 * Generally it is called during attach call of a pcifunc but it
@@ -126,7 +126,7 @@ static int rvu_switch_install_rules(struct rvu *rvu)
 
 		rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL);
 		for (vf = 0; vf < numvfs; vf++) {
-			pcifunc = pf << 10 | ((vf + 1) & 0x3FF);
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, (vf + 1));
 			rvu_get_nix_blkaddr(rvu, pcifunc);
 
 			err = rvu_switch_install_rx_rule(rvu, pcifunc, 0x0);
@@ -236,7 +236,7 @@ void rvu_switch_disable(struct rvu *rvu)
 		if (!is_pf_cgxmapped(rvu, pf))
 			continue;
 
-		pcifunc = pf << 10;
+		pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 		err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF);
 		if (err)
 			dev_err(rvu->dev,
@@ -248,7 +248,7 @@ void rvu_switch_disable(struct rvu *rvu)
 
 		rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL);
 		for (vf = 0; vf < numvfs; vf++) {
-			pcifunc = pf << 10 | ((vf + 1) & 0x3FF);
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, (vf + 1));
 			err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF);
 			if (err)
 				dev_err(rvu->dev,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
index 775fd4c35794..19e0d16b12f6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
@@ -11,3 +11,5 @@
 EXPORT_TRACEPOINT_SYMBOL(otx2_msg_alloc);
 EXPORT_TRACEPOINT_SYMBOL(otx2_msg_interrupt);
 EXPORT_TRACEPOINT_SYMBOL(otx2_msg_process);
+EXPORT_TRACEPOINT_SYMBOL(otx2_msg_status);
+EXPORT_TRACEPOINT_SYMBOL(otx2_parse_dump);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
index 5704520f9b02..4cd0fc4b0d20 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
@@ -18,33 +18,42 @@
 #include "mbox.h"
 
 TRACE_EVENT(otx2_msg_alloc,
-	    TP_PROTO(const struct pci_dev *pdev, u16 id, u64 size),
-	    TP_ARGS(pdev, id, size),
+	    TP_PROTO(const struct pci_dev *pdev, u16 id, u64 size, u16 pcifunc),
+	    TP_ARGS(pdev, id, size, pcifunc),
 	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
 			     __field(u16, id)
 			     __field(u64, size)
+			     __field(u16, pcifunc)
 	    ),
 	    TP_fast_assign(__assign_str(dev);
 			   __entry->id = id;
 			   __entry->size = size;
+			   __entry->pcifunc = pcifunc;
 	    ),
-	    TP_printk("[%s] msg:(%s) size:%lld\n", __get_str(dev),
-		      otx2_mbox_id2name(__entry->id), __entry->size)
+	    TP_printk("[%s] msg:(%s) size:%lld pcifunc:0x%x\n", __get_str(dev),
+		      otx2_mbox_id2name(__entry->id), __entry->size,
+		      __entry->pcifunc)
 );
 
 TRACE_EVENT(otx2_msg_send,
-	    TP_PROTO(const struct pci_dev *pdev, u16 num_msgs, u64 msg_size),
-	    TP_ARGS(pdev, num_msgs, msg_size),
+	    TP_PROTO(const struct pci_dev *pdev, u16 num_msgs, u64 msg_size,
+		     u16 id, u16 pcifunc),
+	    TP_ARGS(pdev, num_msgs, msg_size, id, pcifunc),
 	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
 			     __field(u16, num_msgs)
 			     __field(u64, msg_size)
+			     __field(u16, id)
+			     __field(u16, pcifunc)
 	    ),
 	    TP_fast_assign(__assign_str(dev);
 			   __entry->num_msgs = num_msgs;
 			   __entry->msg_size = msg_size;
+			   __entry->id = id;
+			   __entry->pcifunc = pcifunc;
 	    ),
-	    TP_printk("[%s] sent %d msg(s) of size:%lld\n", __get_str(dev),
-		      __entry->num_msgs, __entry->msg_size)
+	    TP_printk("[%s] sent %d msg(s) of size:%lld msg:(%s) pcifunc:0x%x\n",
+		      __get_str(dev), __entry->num_msgs, __entry->msg_size,
+		      otx2_mbox_id2name(__entry->id), __entry->pcifunc)
 );
 
 TRACE_EVENT(otx2_msg_check,
@@ -81,18 +90,73 @@ TRACE_EVENT(otx2_msg_interrupt,
 );
 
 TRACE_EVENT(otx2_msg_process,
-	    TP_PROTO(const struct pci_dev *pdev, u16 id, int err),
-	    TP_ARGS(pdev, id, err),
+	    TP_PROTO(const struct pci_dev *pdev, u16 id, int err, u16 pcifunc),
+	    TP_ARGS(pdev, id, err, pcifunc),
 	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
 			     __field(u16, id)
 			     __field(int, err)
+			     __field(u16, pcifunc)
 	    ),
 	    TP_fast_assign(__assign_str(dev);
 			   __entry->id = id;
 			   __entry->err = err;
+			   __entry->pcifunc = pcifunc;
+	    ),
+	    TP_printk("[%s] msg:(%s) error:%d pcifunc:0x%x\n", __get_str(dev),
+		      otx2_mbox_id2name(__entry->id),
+		      __entry->err, __entry->pcifunc)
+);
+
+TRACE_EVENT(otx2_msg_wait_rsp,
+	    TP_PROTO(const struct pci_dev *pdev),
+	    TP_ARGS(pdev),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+	    ),
+	    TP_fast_assign(__assign_str(dev)
+	    ),
+	    TP_printk("[%s] timed out while waiting for response\n",
+		      __get_str(dev))
+);
+
+TRACE_EVENT(otx2_msg_status,
+	    TP_PROTO(const struct pci_dev *pdev, const char *msg, u16 num_msgs),
+	    TP_ARGS(pdev, msg, num_msgs),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+			     __string(str, msg)
+			     __field(u16, num_msgs)
+	    ),
+	    TP_fast_assign(__assign_str(dev);
+			   __assign_str(str);
+			   __entry->num_msgs = num_msgs;
+	    ),
+	    TP_printk("[%s] %s num_msgs:%d\n", __get_str(dev),
+		      __get_str(str), __entry->num_msgs)
+);
+
+TRACE_EVENT(otx2_parse_dump,
+	    TP_PROTO(const struct pci_dev *pdev, char *msg, u64 *word),
+	    TP_ARGS(pdev, msg, word),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+			     __string(str, msg)
+			     __field(u64, w0)
+			     __field(u64, w1)
+			     __field(u64, w2)
+			     __field(u64, w3)
+			     __field(u64, w4)
+			     __field(u64, w5)
+	    ),
+	    TP_fast_assign(__assign_str(dev);
+			   __assign_str(str);
+			   __entry->w0 = *(word + 0);
+			   __entry->w1 = *(word + 1);
+			   __entry->w2 = *(word + 2);
+			   __entry->w3 = *(word + 3);
+			   __entry->w4 = *(word + 4);
+			   __entry->w5 = *(word + 5);
 	    ),
-	    TP_printk("[%s] msg:(%s) error:%d\n", __get_str(dev),
-		      otx2_mbox_id2name(__entry->id), __entry->err)
+	    TP_printk("[%s] nix parse %s W0:%#llx W1:%#llx W2:%#llx W3:%#llx W4:%#llx W5:%#llx\n",
+		      __get_str(dev), __get_str(str), __entry->w0, __entry->w1, __entry->w2,
+		      __entry->w3, __entry->w4, __entry->w5)
 );
 
 #endif /* __RVU_TRACE_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
index cb6513ab35e7..883e9f4d601c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
@@ -8,8 +8,8 @@ obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o
 obj-$(CONFIG_RVU_ESWITCH) += rvu_rep.o
 
 rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \
-               otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \
-               otx2_devlink.o qos_sq.o qos.o
+               otx2_flows.o otx2_tc.o cn10k.o cn20k.o otx2_dmac_flt.o \
+               otx2_devlink.o qos_sq.o qos.o otx2_xsk.o
 rvu_nicvf-y := otx2_vf.o
 rvu_rep-y := rep.o
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
index a15cc86635d6..3e1bf22cba69 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
@@ -14,6 +14,9 @@ static struct dev_hw_ops	otx2_hw_ops = {
 	.sqe_flush = otx2_sqe_flush,
 	.aura_freeptr = otx2_aura_freeptr,
 	.refill_pool_ptrs = otx2_refill_pool_ptrs,
+	.pfaf_mbox_intr_handler = otx2_pfaf_mbox_intr_handler,
+	.aura_aq_init = otx2_aura_aq_init,
+	.pool_aq_init = otx2_pool_aq_init,
 };
 
 static struct dev_hw_ops cn10k_hw_ops = {
@@ -21,8 +24,22 @@ static struct dev_hw_ops cn10k_hw_ops = {
 	.sqe_flush = cn10k_sqe_flush,
 	.aura_freeptr = cn10k_aura_freeptr,
 	.refill_pool_ptrs = cn10k_refill_pool_ptrs,
+	.pfaf_mbox_intr_handler = otx2_pfaf_mbox_intr_handler,
+	.aura_aq_init = otx2_aura_aq_init,
+	.pool_aq_init = otx2_pool_aq_init,
 };
 
+void otx2_init_hw_ops(struct otx2_nic *pfvf)
+{
+	if (!test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) {
+		pfvf->hw_ops = &otx2_hw_ops;
+		return;
+	}
+
+	pfvf->hw_ops = &cn10k_hw_ops;
+}
+EXPORT_SYMBOL(otx2_init_hw_ops);
+
 int cn10k_lmtst_init(struct otx2_nic *pfvf)
 {
 
@@ -30,12 +47,9 @@ int cn10k_lmtst_init(struct otx2_nic *pfvf)
 	struct otx2_lmt_info *lmt_info;
 	int err, cpu;
 
-	if (!test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) {
-		pfvf->hw_ops = &otx2_hw_ops;
+	if (!test_bit(CN10K_LMTST, &pfvf->hw.cap_flag))
 		return 0;
-	}
 
-	pfvf->hw_ops = &cn10k_hw_ops;
 	/* Total LMTLINES = num_online_cpus() * 32 (For Burst flush).*/
 	pfvf->tot_lmt_lines = (num_online_cpus() * LMT_BURST_SIZE);
 	pfvf->hw.lmt_info = alloc_percpu(struct otx2_lmt_info);
@@ -112,9 +126,12 @@ int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 	struct otx2_nic *pfvf = dev;
 	int cnt = cq->pool_ptrs;
 	u64 ptrs[NPA_MAX_BURST];
+	struct otx2_pool *pool;
 	dma_addr_t bufptr;
 	int num_ptrs = 1;
 
+	pool = &pfvf->qset.pool[cq->cq_idx];
+
 	/* Refill pool with new buffers */
 	while (cq->pool_ptrs) {
 		if (otx2_alloc_buffer(pfvf, cq, &bufptr)) {
@@ -124,7 +141,9 @@ int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 			break;
 		}
 		cq->pool_ptrs--;
-		ptrs[num_ptrs] = (u64)bufptr + OTX2_HEAD_ROOM;
+		ptrs[num_ptrs] = pool->xsk_pool ?
+				 (u64)bufptr : (u64)bufptr + OTX2_HEAD_ROOM;
+
 		num_ptrs++;
 		if (num_ptrs == NPA_MAX_BURST || cq->pool_ptrs == 0) {
 			__cn10k_aura_freeptr(pfvf, cq->cq_idx, ptrs,
@@ -322,6 +341,12 @@ int cn10k_map_unmap_rq_policer(struct otx2_nic *pfvf, int rq_idx,
 	aq->rq.band_prof_id = policer;
 	aq->rq_mask.band_prof_id = GENMASK(9, 0);
 
+	/* If policer id is greater than 1023 then it implies hardware supports
+	 * more leaf profiles. In that case use band_prof_id_h for 4 MSBs.
+	 */
+	aq->rq.band_prof_id_h = policer >> 10;
+	aq->rq_mask.band_prof_id_h = GENMASK(3, 0);
+
 	/* Fill AQ info */
 	aq->qidx = rq_idx;
 	aq->ctype = NIX_AQ_CTYPE_RQ;
@@ -352,9 +377,12 @@ int cn10k_free_matchall_ipolicer(struct otx2_nic *pfvf)
 	mutex_lock(&pfvf->mbox.lock);
 
 	/* Remove RQ's policer mapping */
-	for (qidx = 0; qidx < hw->rx_queues; qidx++)
-		cn10k_map_unmap_rq_policer(pfvf, qidx,
-					   hw->matchall_ipolicer, false);
+	for (qidx = 0; qidx < hw->rx_queues; qidx++) {
+		rc = cn10k_map_unmap_rq_policer(pfvf, qidx, hw->matchall_ipolicer, false);
+		if (rc)
+			dev_warn(pfvf->dev, "Failed to unmap RQ %d's policer (error %d).",
+				 qidx, rc);
+	}
 
 	rc = cn10k_free_leaf_profile(pfvf, hw->matchall_ipolicer);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
index e3f0bce9908f..945ab10bd4ed 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
@@ -39,4 +39,5 @@ int cn10k_alloc_leaf_profile(struct otx2_nic *pfvf, u16 *leaf);
 int cn10k_set_ipolicer_rate(struct otx2_nic *pfvf, u16 profile,
 			    u32 burst, u64 rate, bool pps);
 int cn10k_free_leaf_profile(struct otx2_nic *pfvf, u16 leaf);
+void otx2_init_hw_ops(struct otx2_nic *pfvf);
 #endif /* CN10K_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c
index 09a5b5268205..77543d472345 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c
@@ -481,7 +481,7 @@ static int cn10k_outb_write_sa(struct otx2_nic *pf, struct qmem *sa_info)
 		goto set_available;
 
 	/* Trigger CTX flush to write dirty data back to DRAM */
-	reg_val = FIELD_PREP(CPT_LF_CTX_FLUSH, sa_iova >> 7);
+	reg_val = FIELD_PREP(CPT_LF_CTX_FLUSH_CPTR, sa_iova >> 7);
 	otx2_write64(pf, CN10K_CPT_LF_CTX_FLUSH, reg_val);
 
 set_available:
@@ -663,10 +663,10 @@ static int cn10k_ipsec_inb_add_state(struct xfrm_state *x,
 	return -EOPNOTSUPP;
 }
 
-static int cn10k_ipsec_outb_add_state(struct xfrm_state *x,
+static int cn10k_ipsec_outb_add_state(struct net_device *dev,
+				      struct xfrm_state *x,
 				      struct netlink_ext_ack *extack)
 {
-	struct net_device *netdev = x->xso.dev;
 	struct cn10k_tx_sa_s *sa_entry;
 	struct qmem *sa_info;
 	struct otx2_nic *pf;
@@ -676,7 +676,7 @@ static int cn10k_ipsec_outb_add_state(struct xfrm_state *x,
 	if (err)
 		return err;
 
-	pf = netdev_priv(netdev);
+	pf = netdev_priv(dev);
 
 	err = qmem_alloc(pf->dev, &sa_info, pf->ipsec.sa_size, OTX2_ALIGN);
 	if (err)
@@ -700,18 +700,18 @@ static int cn10k_ipsec_outb_add_state(struct xfrm_state *x,
 	return 0;
 }
 
-static int cn10k_ipsec_add_state(struct xfrm_state *x,
+static int cn10k_ipsec_add_state(struct net_device *dev,
+				 struct xfrm_state *x,
 				 struct netlink_ext_ack *extack)
 {
 	if (x->xso.dir == XFRM_DEV_OFFLOAD_IN)
 		return cn10k_ipsec_inb_add_state(x, extack);
 	else
-		return cn10k_ipsec_outb_add_state(x, extack);
+		return cn10k_ipsec_outb_add_state(dev, x, extack);
 }
 
-static void cn10k_ipsec_del_state(struct xfrm_state *x)
+static void cn10k_ipsec_del_state(struct net_device *dev, struct xfrm_state *x)
 {
-	struct net_device *netdev = x->xso.dev;
 	struct cn10k_tx_sa_s *sa_entry;
 	struct qmem *sa_info;
 	struct otx2_nic *pf;
@@ -720,7 +720,7 @@ static void cn10k_ipsec_del_state(struct xfrm_state *x)
 	if (x->xso.dir == XFRM_DEV_OFFLOAD_IN)
 		return;
 
-	pf = netdev_priv(netdev);
+	pf = netdev_priv(dev);
 
 	sa_info = (struct qmem *)x->xso.offload_handle;
 	sa_entry = (struct cn10k_tx_sa_s *)sa_info->base;
@@ -732,7 +732,7 @@ static void cn10k_ipsec_del_state(struct xfrm_state *x)
 
 	err = cn10k_outb_write_sa(pf, sa_info);
 	if (err)
-		netdev_err(netdev, "Error (%d) deleting SA\n", err);
+		netdev_err(dev, "Error (%d) deleting SA\n", err);
 
 	x->xso.offload_handle = 0;
 	qmem_free(pf->dev, sa_info);
@@ -744,24 +744,9 @@ static void cn10k_ipsec_del_state(struct xfrm_state *x)
 		queue_work(pf->ipsec.sa_workq, &pf->ipsec.sa_work);
 }
 
-static bool cn10k_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
-{
-	if (x->props.family == AF_INET) {
-		/* Offload with IPv4 options is not supported yet */
-		if (ip_hdr(skb)->ihl > 5)
-			return false;
-	} else {
-		/* Offload with IPv6 extension headers is not support yet */
-		if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr))
-			return false;
-	}
-	return true;
-}
-
 static const struct xfrmdev_ops cn10k_ipsec_xfrmdev_ops = {
 	.xdo_dev_state_add	= cn10k_ipsec_add_state,
 	.xdo_dev_state_delete	= cn10k_ipsec_del_state,
-	.xdo_dev_offload_ok	= cn10k_ipsec_offload_ok,
 };
 
 static void cn10k_ipsec_sa_wq_handler(struct work_struct *work)
@@ -813,7 +798,8 @@ int cn10k_ipsec_init(struct net_device *netdev)
 	pf->ipsec.sa_size = sa_size;
 
 	INIT_WORK(&pf->ipsec.sa_work, cn10k_ipsec_sa_wq_handler);
-	pf->ipsec.sa_workq = alloc_workqueue("cn10k_ipsec_sa_workq", 0, 0);
+	pf->ipsec.sa_workq = alloc_workqueue("cn10k_ipsec_sa_workq",
+					     WQ_PERCPU, 0);
 	if (!pf->ipsec.sa_workq) {
 		netdev_err(pf->netdev, "SA alloc workqueue failed\n");
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h
index 9965df0faa3e..43fbce0d6039 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h
@@ -220,7 +220,7 @@ struct cpt_sg_s {
 #define CPT_LF_Q_SIZE_DIV40 GENMASK_ULL(14, 0)
 
 /* CPT LF CTX Flush Register */
-#define CPT_LF_CTX_FLUSH GENMASK_ULL(45, 0)
+#define CPT_LF_CTX_FLUSH_CPTR GENMASK_ULL(45, 0)
 
 #ifdef CONFIG_XFRM_OFFLOAD
 int cn10k_ipsec_init(struct net_device *netdev);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
index 6cc7a78968fc..4c7e0f345cb5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
@@ -133,9 +133,7 @@ static const char *rsrc_name(enum mcs_rsrc_type rsrc_type)
 		return "SA";
 	default:
 		return "Unknown";
-	};
-
-	return "Unknown";
+	}
 }
 
 static int cn10k_mcs_alloc_rsrc(struct otx2_nic *pfvf, enum mcs_direction dir,
@@ -533,7 +531,8 @@ static int cn10k_mcs_write_tx_secy(struct otx2_nic *pfvf,
 	if (sw_tx_sc->encrypt)
 		sectag_tci |= (MCS_TCI_E | MCS_TCI_C);
 
-	policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU, secy->netdev->mtu);
+	policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU,
+			    pfvf->netdev->mtu + OTX2_ETH_HLEN);
 	/* Write SecTag excluding AN bits(1..0) */
 	policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_TCI, sectag_tci >> 2);
 	policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_OFFSET, tag_offset);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c
new file mode 100644
index 000000000000..a60f8cf53feb
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c
@@ -0,0 +1,450 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell RVU Ethernet driver
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#include "otx2_common.h"
+#include "otx2_reg.h"
+#include "otx2_struct.h"
+#include "cn10k.h"
+
+/* CN20K mbox AF => PFx irq handler */
+irqreturn_t cn20k_pfaf_mbox_intr_handler(int irq, void *pf_irq)
+{
+	struct otx2_nic *pf = pf_irq;
+	struct mbox *mw = &pf->mbox;
+	struct otx2_mbox_dev *mdev;
+	struct otx2_mbox *mbox;
+	struct mbox_hdr *hdr;
+	u64 pf_trig_val;
+
+	pf_trig_val = otx2_read64(pf, RVU_PF_INT) & 0x3ULL;
+
+	/* Clear the IRQ */
+	otx2_write64(pf, RVU_PF_INT, pf_trig_val);
+
+	if (pf_trig_val & BIT_ULL(0)) {
+		mbox = &mw->mbox_up;
+		mdev = &mbox->dev[0];
+		otx2_sync_mbox_bbuf(mbox, 0);
+
+		hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+		if (hdr->num_msgs)
+			queue_work(pf->mbox_wq, &mw->mbox_up_wrk);
+
+		trace_otx2_msg_interrupt(pf->pdev, "UP message from AF to PF",
+					 BIT_ULL(0));
+	}
+
+	if (pf_trig_val & BIT_ULL(1)) {
+		mbox = &mw->mbox;
+		mdev = &mbox->dev[0];
+		otx2_sync_mbox_bbuf(mbox, 0);
+
+		hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+		if (hdr->num_msgs)
+			queue_work(pf->mbox_wq, &mw->mbox_wrk);
+		trace_otx2_msg_interrupt(pf->pdev, "DOWN reply from AF to PF",
+					 BIT_ULL(1));
+	}
+
+	return IRQ_HANDLED;
+}
+
+irqreturn_t cn20k_vfaf_mbox_intr_handler(int irq, void *vf_irq)
+{
+	struct otx2_nic *vf = vf_irq;
+	struct otx2_mbox_dev *mdev;
+	struct otx2_mbox *mbox;
+	struct mbox_hdr *hdr;
+	u64 vf_trig_val;
+
+	vf_trig_val = otx2_read64(vf, RVU_VF_INT) & 0x3ULL;
+	/* Clear the IRQ */
+	otx2_write64(vf, RVU_VF_INT, vf_trig_val);
+
+	/* Read latest mbox data */
+	smp_rmb();
+
+	if (vf_trig_val & BIT_ULL(1)) {
+		/* Check for PF => VF response messages */
+		mbox = &vf->mbox.mbox;
+		mdev = &mbox->dev[0];
+		otx2_sync_mbox_bbuf(mbox, 0);
+
+		hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+		if (hdr->num_msgs)
+			queue_work(vf->mbox_wq, &vf->mbox.mbox_wrk);
+
+		trace_otx2_msg_interrupt(mbox->pdev, "DOWN reply from PF0 to VF",
+					 BIT_ULL(1));
+	}
+
+	if (vf_trig_val & BIT_ULL(0)) {
+		/* Check for PF => VF notification messages */
+		mbox = &vf->mbox.mbox_up;
+		mdev = &mbox->dev[0];
+		otx2_sync_mbox_bbuf(mbox, 0);
+
+		hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+		if (hdr->num_msgs)
+			queue_work(vf->mbox_wq, &vf->mbox.mbox_up_wrk);
+
+		trace_otx2_msg_interrupt(mbox->pdev, "UP message from PF0 to VF",
+					 BIT_ULL(0));
+	}
+
+	return IRQ_HANDLED;
+}
+
+void cn20k_enable_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs)
+{
+	/* Clear PF <=> VF mailbox IRQ */
+	otx2_write64(pf, RVU_MBOX_PF_VFPF_INTX(0), ~0ull);
+	otx2_write64(pf, RVU_MBOX_PF_VFPF_INTX(1), ~0ull);
+	otx2_write64(pf, RVU_MBOX_PF_VFPF1_INTX(0), ~0ull);
+	otx2_write64(pf, RVU_MBOX_PF_VFPF1_INTX(1), ~0ull);
+
+	/* Enable PF <=> VF mailbox IRQ */
+	otx2_write64(pf, RVU_MBOX_PF_VFPF_INT_ENA_W1SX(0), INTR_MASK(numvfs));
+	otx2_write64(pf, RVU_MBOX_PF_VFPF1_INT_ENA_W1SX(0), INTR_MASK(numvfs));
+	if (numvfs > 64) {
+		numvfs -= 64;
+		otx2_write64(pf, RVU_MBOX_PF_VFPF_INT_ENA_W1SX(1),
+			     INTR_MASK(numvfs));
+		otx2_write64(pf, RVU_MBOX_PF_VFPF1_INT_ENA_W1SX(1),
+			     INTR_MASK(numvfs));
+	}
+}
+
+void cn20k_disable_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs)
+{
+	int vector, intr_vec, vec = 0;
+
+	/* Disable PF <=> VF mailbox IRQ */
+	otx2_write64(pf, RVU_MBOX_PF_VFPF_INT_ENA_W1CX(0), ~0ull);
+	otx2_write64(pf, RVU_MBOX_PF_VFPF_INT_ENA_W1CX(1), ~0ull);
+	otx2_write64(pf, RVU_MBOX_PF_VFPF1_INT_ENA_W1CX(0), ~0ull);
+	otx2_write64(pf, RVU_MBOX_PF_VFPF1_INT_ENA_W1CX(1), ~0ull);
+
+	otx2_write64(pf, RVU_MBOX_PF_VFPF_INTX(0), ~0ull);
+	otx2_write64(pf, RVU_MBOX_PF_VFPF1_INTX(0), ~0ull);
+
+	if (numvfs > 64) {
+		otx2_write64(pf, RVU_MBOX_PF_VFPF_INTX(1), ~0ull);
+		otx2_write64(pf, RVU_MBOX_PF_VFPF1_INTX(1), ~0ull);
+	}
+
+	for (intr_vec = RVU_MBOX_PF_INT_VEC_VFPF_MBOX0; intr_vec <=
+			RVU_MBOX_PF_INT_VEC_VFPF1_MBOX1; intr_vec++, vec++) {
+		vector = pci_irq_vector(pf->pdev, intr_vec);
+		free_irq(vector, pf->hw.pfvf_irq_devid[vec]);
+	}
+}
+
+irqreturn_t cn20k_pfvf_mbox_intr_handler(int irq, void *pf_irq)
+{
+	struct pf_irq_data *irq_data = pf_irq;
+	struct otx2_nic *pf = irq_data->pf;
+	struct mbox *mbox;
+	u64 intr;
+
+	/* Sync with mbox memory region */
+	rmb();
+
+	/* Clear interrupts */
+	intr = otx2_read64(pf, irq_data->intr_status);
+	otx2_write64(pf, irq_data->intr_status, intr);
+	mbox = pf->mbox_pfvf;
+
+	if (intr)
+		trace_otx2_msg_interrupt(pf->pdev, "VF(s) to PF", intr);
+
+	irq_data->pf_queue_work_hdlr(mbox, pf->mbox_pfvf_wq, irq_data->start,
+				     irq_data->mdevs, intr);
+
+	return IRQ_HANDLED;
+}
+
+int cn20k_register_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs)
+{
+	struct otx2_hw *hw = &pf->hw;
+	struct pf_irq_data *irq_data;
+	int intr_vec, ret, vec = 0;
+	char *irq_name;
+
+	/* irq data for 4 PF intr vectors */
+	irq_data = devm_kcalloc(pf->dev, 4,
+				sizeof(struct pf_irq_data), GFP_KERNEL);
+	if (!irq_data)
+		return -ENOMEM;
+
+	for (intr_vec = RVU_MBOX_PF_INT_VEC_VFPF_MBOX0; intr_vec <=
+			RVU_MBOX_PF_INT_VEC_VFPF1_MBOX1; intr_vec++, vec++) {
+		switch (intr_vec) {
+		case RVU_MBOX_PF_INT_VEC_VFPF_MBOX0:
+			irq_data[vec].intr_status =
+						RVU_MBOX_PF_VFPF_INTX(0);
+			irq_data[vec].start = 0;
+			irq_data[vec].mdevs = 64;
+			break;
+		case RVU_MBOX_PF_INT_VEC_VFPF_MBOX1:
+			irq_data[vec].intr_status =
+						RVU_MBOX_PF_VFPF_INTX(1);
+			irq_data[vec].start = 64;
+			irq_data[vec].mdevs = 96;
+			break;
+		case RVU_MBOX_PF_INT_VEC_VFPF1_MBOX0:
+			irq_data[vec].intr_status =
+						RVU_MBOX_PF_VFPF1_INTX(0);
+			irq_data[vec].start = 0;
+			irq_data[vec].mdevs = 64;
+			break;
+		case RVU_MBOX_PF_INT_VEC_VFPF1_MBOX1:
+			irq_data[vec].intr_status =
+						RVU_MBOX_PF_VFPF1_INTX(1);
+			irq_data[vec].start = 64;
+			irq_data[vec].mdevs = 96;
+			break;
+		}
+		irq_data[vec].pf_queue_work_hdlr = otx2_queue_vf_work;
+		irq_data[vec].vec_num = intr_vec;
+		irq_data[vec].pf = pf;
+
+		/* Register mailbox interrupt handler */
+		irq_name = &hw->irq_name[intr_vec * NAME_SIZE];
+		if (pf->pcifunc)
+			snprintf(irq_name, NAME_SIZE,
+				 "RVUPF%d_VF%d Mbox%d", rvu_get_pf(pf->pdev,
+				 pf->pcifunc), vec / 2, vec % 2);
+		else
+			snprintf(irq_name, NAME_SIZE, "RVUPF_VF%d Mbox%d",
+				 vec / 2, vec % 2);
+
+		hw->pfvf_irq_devid[vec] = &irq_data[vec];
+		ret = request_irq(pci_irq_vector(pf->pdev, intr_vec),
+				  pf->hw_ops->pfvf_mbox_intr_handler, 0,
+				  irq_name,
+				  &irq_data[vec]);
+		if (ret) {
+			dev_err(pf->dev,
+				"RVUPF: IRQ registration failed for PFVF mbox0 irq\n");
+			return ret;
+		}
+	}
+
+	cn20k_enable_pfvf_mbox_intr(pf, numvfs);
+
+	return 0;
+}
+
+#define RQ_BP_LVL_AURA   (255 - ((85 * 256) / 100)) /* BP when 85% is full */
+
+static u8 cn20k_aura_bpid_idx(struct otx2_nic *pfvf, int aura_id)
+{
+#ifdef CONFIG_DCB
+	return pfvf->queue_to_pfc_map[aura_id];
+#else
+	return 0;
+#endif
+}
+
+static int cn20k_aura_aq_init(struct otx2_nic *pfvf, int aura_id,
+			      int pool_id, int numptrs)
+{
+	struct npa_cn20k_aq_enq_req *aq;
+	struct otx2_pool *pool;
+	u8 bpid_idx;
+	int err;
+
+	pool = &pfvf->qset.pool[pool_id];
+
+	/* Allocate memory for HW to update Aura count.
+	 * Alloc one cache line, so that it fits all FC_STYPE modes.
+	 */
+	if (!pool->fc_addr) {
+		err = qmem_alloc(pfvf->dev, &pool->fc_addr, 1, OTX2_ALIGN);
+		if (err)
+			return err;
+	}
+
+	/* Initialize this aura's context via AF */
+	aq = otx2_mbox_alloc_msg_npa_cn20k_aq_enq(&pfvf->mbox);
+	if (!aq) {
+		/* Shared mbox memory buffer is full, flush it and retry */
+		err = otx2_sync_mbox_msg(&pfvf->mbox);
+		if (err)
+			return err;
+		aq = otx2_mbox_alloc_msg_npa_cn20k_aq_enq(&pfvf->mbox);
+		if (!aq)
+			return -ENOMEM;
+	}
+
+	aq->aura_id = aura_id;
+
+	/* Will be filled by AF with correct pool context address */
+	aq->aura.pool_addr = pool_id;
+	aq->aura.pool_caching = 1;
+	aq->aura.shift = ilog2(numptrs) - 8;
+	aq->aura.count = numptrs;
+	aq->aura.limit = numptrs;
+	aq->aura.avg_level = 255;
+	aq->aura.ena = 1;
+	aq->aura.fc_ena = 1;
+	aq->aura.fc_addr = pool->fc_addr->iova;
+	aq->aura.fc_hyst_bits = 0; /* Store count on all updates */
+
+	/* Enable backpressure for RQ aura */
+	if (aura_id < pfvf->hw.rqpool_cnt && !is_otx2_lbkvf(pfvf->pdev)) {
+		aq->aura.bp_ena = 0;
+		/* If NIX1 LF is attached then specify NIX1_RX.
+		 *
+		 * Below NPA_AURA_S[BP_ENA] is set according to the
+		 * NPA_BPINTF_E enumeration given as:
+		 * 0x0 + a*0x1 where 'a' is 0 for NIX0_RX and 1 for NIX1_RX so
+		 * NIX0_RX is 0x0 + 0*0x1 = 0
+		 * NIX1_RX is 0x0 + 1*0x1 = 1
+		 * But in HRM it is given that
+		 * "NPA_AURA_S[BP_ENA](w1[33:32]) - Enable aura backpressure to
+		 * NIX-RX based on [BP] level. One bit per NIX-RX; index
+		 * enumerated by NPA_BPINTF_E."
+		 */
+		if (pfvf->nix_blkaddr == BLKADDR_NIX1)
+			aq->aura.bp_ena = 1;
+
+		bpid_idx = cn20k_aura_bpid_idx(pfvf, aura_id);
+		aq->aura.bpid = pfvf->bpid[bpid_idx];
+
+		/* Set backpressure level for RQ's Aura */
+		aq->aura.bp = RQ_BP_LVL_AURA;
+	}
+
+	/* Fill AQ info */
+	aq->ctype = NPA_AQ_CTYPE_AURA;
+	aq->op = NPA_AQ_INSTOP_INIT;
+
+	return 0;
+}
+
+static int cn20k_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id,
+			      int stack_pages, int numptrs, int buf_size,
+			      int type)
+{
+	struct page_pool_params pp_params = { 0 };
+	struct npa_cn20k_aq_enq_req *aq;
+	struct otx2_pool *pool;
+	int err, sz;
+
+	pool = &pfvf->qset.pool[pool_id];
+	/* Alloc memory for stack which is used to store buffer pointers */
+	err = qmem_alloc(pfvf->dev, &pool->stack,
+			 stack_pages, pfvf->hw.stack_pg_bytes);
+	if (err)
+		return err;
+
+	pool->rbsize = buf_size;
+
+	/* Initialize this pool's context via AF */
+	aq = otx2_mbox_alloc_msg_npa_cn20k_aq_enq(&pfvf->mbox);
+	if (!aq) {
+		/* Shared mbox memory buffer is full, flush it and retry */
+		err = otx2_sync_mbox_msg(&pfvf->mbox);
+		if (err) {
+			qmem_free(pfvf->dev, pool->stack);
+			return err;
+		}
+		aq = otx2_mbox_alloc_msg_npa_cn20k_aq_enq(&pfvf->mbox);
+		if (!aq) {
+			qmem_free(pfvf->dev, pool->stack);
+			return -ENOMEM;
+		}
+	}
+
+	aq->aura_id = pool_id;
+	aq->pool.stack_base = pool->stack->iova;
+	aq->pool.stack_caching = 1;
+	aq->pool.ena = 1;
+	aq->pool.buf_size = buf_size / 128;
+	aq->pool.stack_max_pages = stack_pages;
+	aq->pool.shift = ilog2(numptrs) - 8;
+	aq->pool.ptr_start = 0;
+	aq->pool.ptr_end = ~0ULL;
+
+	/* Fill AQ info */
+	aq->ctype = NPA_AQ_CTYPE_POOL;
+	aq->op = NPA_AQ_INSTOP_INIT;
+
+	if (type != AURA_NIX_RQ) {
+		pool->page_pool = NULL;
+		return 0;
+	}
+
+	sz = ALIGN(ALIGN(SKB_DATA_ALIGN(buf_size), OTX2_ALIGN), PAGE_SIZE);
+	pp_params.order = get_order(sz);
+	pp_params.flags = PP_FLAG_DMA_MAP;
+	pp_params.pool_size = min(OTX2_PAGE_POOL_SZ, numptrs);
+	pp_params.nid = NUMA_NO_NODE;
+	pp_params.dev = pfvf->dev;
+	pp_params.dma_dir = DMA_FROM_DEVICE;
+	pool->page_pool = page_pool_create(&pp_params);
+	if (IS_ERR(pool->page_pool)) {
+		netdev_err(pfvf->netdev, "Creation of page pool failed\n");
+		return PTR_ERR(pool->page_pool);
+	}
+
+	return 0;
+}
+
+static int cn20k_sq_aq_init(void *dev, u16 qidx, u8 chan_offset, u16 sqb_aura)
+{
+	struct nix_cn20k_aq_enq_req *aq;
+	struct otx2_nic *pfvf = dev;
+
+	/* Get memory to put this msg */
+	aq = otx2_mbox_alloc_msg_nix_cn20k_aq_enq(&pfvf->mbox);
+	if (!aq)
+		return -ENOMEM;
+
+	aq->sq.cq = pfvf->hw.rx_queues + qidx;
+	aq->sq.max_sqe_size = NIX_MAXSQESZ_W16; /* 128 byte */
+	aq->sq.cq_ena = 1;
+	aq->sq.ena = 1;
+	aq->sq.smq = otx2_get_smq_idx(pfvf, qidx);
+	aq->sq.smq_rr_weight = mtu_to_dwrr_weight(pfvf, pfvf->tx_max_pktlen);
+	aq->sq.default_chan = pfvf->hw.tx_chan_base + chan_offset;
+	aq->sq.sqe_stype = NIX_STYPE_STF; /* Cache SQB */
+	aq->sq.sqb_aura = sqb_aura;
+	aq->sq.sq_int_ena = NIX_SQINT_BITS;
+	aq->sq.qint_idx = 0;
+	/* Due pipelining impact minimum 2000 unused SQ CQE's
+	 * need to maintain to avoid CQ overflow.
+	 */
+	aq->sq.cq_limit = (SEND_CQ_SKID * 256) / (pfvf->qset.sqe_cnt);
+
+	/* Fill AQ info */
+	aq->qidx = qidx;
+	aq->ctype = NIX_AQ_CTYPE_SQ;
+	aq->op = NIX_AQ_INSTOP_INIT;
+
+	return otx2_sync_mbox_msg(&pfvf->mbox);
+}
+
+static struct dev_hw_ops cn20k_hw_ops = {
+	.pfaf_mbox_intr_handler = cn20k_pfaf_mbox_intr_handler,
+	.vfaf_mbox_intr_handler = cn20k_vfaf_mbox_intr_handler,
+	.pfvf_mbox_intr_handler = cn20k_pfvf_mbox_intr_handler,
+	.sq_aq_init = cn20k_sq_aq_init,
+	.sqe_flush = cn10k_sqe_flush,
+	.aura_freeptr = cn10k_aura_freeptr,
+	.refill_pool_ptrs = cn10k_refill_pool_ptrs,
+	.aura_aq_init = cn20k_aura_aq_init,
+	.pool_aq_init = cn20k_pool_aq_init,
+};
+
+void cn20k_init(struct otx2_nic *pfvf)
+{
+	pfvf->hw_ops = &cn20k_hw_ops;
+}
+EXPORT_SYMBOL(cn20k_init);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.h
new file mode 100644
index 000000000000..832adaf8c57f
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell RVU Ethernet driver
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#ifndef CN20K_H
+#define CN20K_H
+
+#include "otx2_common.h"
+
+void cn20k_init(struct otx2_nic *pfvf);
+int cn20k_register_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs);
+void cn20k_disable_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs);
+void cn20k_enable_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs);
+#endif /* CN20K_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 2b49bfec7869..75ebb17419c4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -17,6 +17,7 @@
 #include "otx2_common.h"
 #include "otx2_struct.h"
 #include "cn10k.h"
+#include "otx2_xsk.h"
 
 static bool otx2_is_pfc_enabled(struct otx2_nic *pfvf)
 {
@@ -27,12 +28,12 @@ static void otx2_nix_rq_op_stats(struct queue_stats *stats,
 				 struct otx2_nic *pfvf, int qidx)
 {
 	u64 incr = (u64)qidx << 32;
-	u64 *ptr;
+	void __iomem *ptr;
 
-	ptr = (u64 *)otx2_get_regaddr(pfvf, NIX_LF_RQ_OP_OCTS);
+	ptr = otx2_get_regaddr(pfvf, NIX_LF_RQ_OP_OCTS);
 	stats->bytes = otx2_atomic64_add(incr, ptr);
 
-	ptr = (u64 *)otx2_get_regaddr(pfvf, NIX_LF_RQ_OP_PKTS);
+	ptr = otx2_get_regaddr(pfvf, NIX_LF_RQ_OP_PKTS);
 	stats->pkts = otx2_atomic64_add(incr, ptr);
 }
 
@@ -40,12 +41,12 @@ static void otx2_nix_sq_op_stats(struct queue_stats *stats,
 				 struct otx2_nic *pfvf, int qidx)
 {
 	u64 incr = (u64)qidx << 32;
-	u64 *ptr;
+	void __iomem *ptr;
 
-	ptr = (u64 *)otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_OCTS);
+	ptr = otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_OCTS);
 	stats->bytes = otx2_atomic64_add(incr, ptr);
 
-	ptr = (u64 *)otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_PKTS);
+	ptr = otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_PKTS);
 	stats->pkts = otx2_atomic64_add(incr, ptr);
 }
 
@@ -123,7 +124,9 @@ void otx2_get_dev_stats(struct otx2_nic *pfvf)
 			       dev_stats->rx_ucast_frames;
 
 	dev_stats->tx_bytes = OTX2_GET_TX_STATS(TX_OCTS);
-	dev_stats->tx_drops = OTX2_GET_TX_STATS(TX_DROP);
+	dev_stats->tx_drops = OTX2_GET_TX_STATS(TX_DROP) +
+			       (unsigned long)atomic_long_read(&dev_stats->tx_discards);
+
 	dev_stats->tx_bcast_frames = OTX2_GET_TX_STATS(TX_BCAST);
 	dev_stats->tx_mcast_frames = OTX2_GET_TX_STATS(TX_MCAST);
 	dev_stats->tx_ucast_frames = OTX2_GET_TX_STATS(TX_UCAST);
@@ -317,19 +320,22 @@ fail:
 	return err;
 }
 
-int otx2_set_rss_table(struct otx2_nic *pfvf, int ctx_id)
+int otx2_set_rss_table(struct otx2_nic *pfvf, int ctx_id, const u32 *ind_tbl)
 {
 	struct otx2_rss_info *rss = &pfvf->hw.rss_info;
 	const int index = rss->rss_size * ctx_id;
 	struct mbox *mbox = &pfvf->mbox;
-	struct otx2_rss_ctx *rss_ctx;
 	struct nix_aq_enq_req *aq;
 	int idx, err;
 
 	mutex_lock(&mbox->lock);
-	rss_ctx = rss->rss_ctx[ctx_id];
+	ind_tbl = ind_tbl ?: rss->ind_tbl;
 	/* Get memory to put this msg */
 	for (idx = 0; idx < rss->rss_size; idx++) {
+		/* Ignore the queue if AF_XDP zero copy is enabled */
+		if (test_bit(ind_tbl[idx], pfvf->af_xdp_zc_qidx))
+			continue;
+
 		aq = otx2_mbox_alloc_msg_nix_aq_enq(mbox);
 		if (!aq) {
 			/* The shared memory buffer can be full.
@@ -347,7 +353,7 @@ int otx2_set_rss_table(struct otx2_nic *pfvf, int ctx_id)
 			}
 		}
 
-		aq->rss.rq = rss_ctx->ind_tbl[idx];
+		aq->rss.rq = ind_tbl[idx];
 
 		/* Fill AQ info */
 		aq->qidx = index + idx;
@@ -385,30 +391,22 @@ void otx2_set_rss_key(struct otx2_nic *pfvf)
 int otx2_rss_init(struct otx2_nic *pfvf)
 {
 	struct otx2_rss_info *rss = &pfvf->hw.rss_info;
-	struct otx2_rss_ctx *rss_ctx;
 	int idx, ret = 0;
 
-	rss->rss_size = sizeof(*rss->rss_ctx[DEFAULT_RSS_CONTEXT_GROUP]);
+	rss->rss_size = sizeof(*rss->ind_tbl);
 
 	/* Init RSS key if it is not setup already */
 	if (!rss->enable)
 		netdev_rss_key_fill(rss->key, sizeof(rss->key));
 	otx2_set_rss_key(pfvf);
 
-	if (!netif_is_rxfh_configured(pfvf->netdev)) {
-		/* Set RSS group 0 as default indirection table */
-		rss->rss_ctx[DEFAULT_RSS_CONTEXT_GROUP] = kzalloc(rss->rss_size,
-								  GFP_KERNEL);
-		if (!rss->rss_ctx[DEFAULT_RSS_CONTEXT_GROUP])
-			return -ENOMEM;
-
-		rss_ctx = rss->rss_ctx[DEFAULT_RSS_CONTEXT_GROUP];
+	if (!netif_is_rxfh_configured(pfvf->netdev))
 		for (idx = 0; idx < rss->rss_size; idx++)
-			rss_ctx->ind_tbl[idx] =
+			rss->ind_tbl[idx] =
 				ethtool_rxfh_indir_default(idx,
 							   pfvf->hw.rx_queues);
-	}
-	ret = otx2_set_rss_table(pfvf, DEFAULT_RSS_CONTEXT_GROUP);
+
+	ret = otx2_set_rss_table(pfvf, DEFAULT_RSS_CONTEXT_GROUP, NULL);
 	if (ret)
 		return ret;
 
@@ -549,10 +547,13 @@ static int otx2_alloc_pool_buf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 }
 
 static int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-			     dma_addr_t *dma)
+			     dma_addr_t *dma, int qidx, int idx)
 {
 	u8 *buf;
 
+	if (pool->xsk_pool)
+		return otx2_xsk_pool_alloc_buf(pfvf, pool, dma, idx);
+
 	if (pool->page_pool)
 		return otx2_alloc_pool_buf(pfvf, pool, dma);
 
@@ -571,12 +572,12 @@ static int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 }
 
 int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-		    dma_addr_t *dma)
+		    dma_addr_t *dma, int qidx, int idx)
 {
 	int ret;
 
 	local_bh_disable();
-	ret = __otx2_alloc_rbuf(pfvf, pool, dma);
+	ret = __otx2_alloc_rbuf(pfvf, pool, dma, qidx, idx);
 	local_bh_enable();
 	return ret;
 }
@@ -584,7 +585,8 @@ int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 int otx2_alloc_buffer(struct otx2_nic *pfvf, struct otx2_cq_queue *cq,
 		      dma_addr_t *dma)
 {
-	if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma)))
+	if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma,
+				       cq->cq_idx, cq->pool_ptrs - 1)))
 		return -ENOMEM;
 	return 0;
 }
@@ -851,9 +853,10 @@ void otx2_sqb_flush(struct otx2_nic *pfvf)
 {
 	int qidx, sqe_tail, sqe_head;
 	struct otx2_snd_queue *sq;
-	u64 incr, *ptr, val;
+	void __iomem *ptr;
+	u64 incr, val;
 
-	ptr = (u64 *)otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_STATUS);
+	ptr = otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_STATUS);
 	for (qidx = 0; qidx < otx2_get_total_tx_queues(pfvf); qidx++) {
 		sq = &pfvf->qset.sq[qidx];
 		if (!sq->sqb_ptrs)
@@ -884,7 +887,7 @@ void otx2_sqb_flush(struct otx2_nic *pfvf)
 #define RQ_PASS_LVL_AURA (255 - ((95 * 256) / 100)) /* RED when 95% is full */
 #define RQ_DROP_LVL_AURA (255 - ((99 * 256) / 100)) /* Drop when 99% is full */
 
-static int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura)
+int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura)
 {
 	struct otx2_qset *qset = &pfvf->qset;
 	struct nix_aq_enq_req *aq;
@@ -1028,6 +1031,10 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 
 	sq->stats.bytes = 0;
 	sq->stats.pkts = 0;
+	/* Attach XSK_BUFF_POOL to XDP queue */
+	if (qidx > pfvf->hw.xdp_queues)
+		otx2_attach_xsk_buff(pfvf, sq, (qidx - pfvf->hw.xdp_queues));
+
 
 	chan_offset = qidx % pfvf->hw.tx_chan_cnt;
 	err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, chan_offset, sqb_aura);
@@ -1041,12 +1048,13 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 
 }
 
-static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
+int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
 {
 	struct otx2_qset *qset = &pfvf->qset;
 	int err, pool_id, non_xdp_queues;
 	struct nix_aq_enq_req *aq;
 	struct otx2_cq_queue *cq;
+	struct otx2_pool *pool;
 
 	cq = &qset->cq[qidx];
 	cq->cq_idx = qidx;
@@ -1055,8 +1063,20 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
 		cq->cq_type = CQ_RX;
 		cq->cint_idx = qidx;
 		cq->cqe_cnt = qset->rqe_cnt;
-		if (pfvf->xdp_prog)
+		if (pfvf->xdp_prog) {
 			xdp_rxq_info_reg(&cq->xdp_rxq, pfvf->netdev, qidx, 0);
+			pool = &qset->pool[qidx];
+			if (pool->xsk_pool) {
+				xdp_rxq_info_reg_mem_model(&cq->xdp_rxq,
+							   MEM_TYPE_XSK_BUFF_POOL,
+							   NULL);
+				xsk_pool_set_rxq_info(pool->xsk_pool, &cq->xdp_rxq);
+			} else if (pool->page_pool) {
+				xdp_rxq_info_reg_mem_model(&cq->xdp_rxq,
+							   MEM_TYPE_PAGE_POOL,
+							   pool->page_pool);
+			}
+		}
 	} else if (qidx < non_xdp_queues) {
 		cq->cq_type = CQ_TX;
 		cq->cint_idx = qidx - pfvf->hw.rx_queues;
@@ -1275,9 +1295,10 @@ void otx2_free_bufs(struct otx2_nic *pfvf, struct otx2_pool *pool,
 
 	pa = otx2_iova_to_phys(pfvf->iommu_domain, iova);
 	page = virt_to_head_page(phys_to_virt(pa));
-
 	if (pool->page_pool) {
 		page_pool_put_full_page(pool->page_pool, page, true);
+	} else if (pool->xsk_pool) {
+		/* Note: No way of identifying xdp_buff */
 	} else {
 		dma_unmap_page_attrs(pfvf->dev, iova, size,
 				     DMA_FROM_DEVICE,
@@ -1292,6 +1313,7 @@ void otx2_free_aura_ptr(struct otx2_nic *pfvf, int type)
 	int pool_id, pool_start = 0, pool_end = 0, size = 0;
 	struct otx2_pool *pool;
 	u64 iova;
+	int idx;
 
 	if (type == AURA_NIX_SQ) {
 		pool_start = otx2_get_pool_idx(pfvf, type, 0);
@@ -1306,16 +1328,21 @@ void otx2_free_aura_ptr(struct otx2_nic *pfvf, int type)
 
 	/* Free SQB and RQB pointers from the aura pool */
 	for (pool_id = pool_start; pool_id < pool_end; pool_id++) {
-		iova = otx2_aura_allocptr(pfvf, pool_id);
 		pool = &pfvf->qset.pool[pool_id];
+		iova = otx2_aura_allocptr(pfvf, pool_id);
 		while (iova) {
 			if (type == AURA_NIX_RQ)
 				iova -= OTX2_HEAD_ROOM;
-
 			otx2_free_bufs(pfvf, pool, iova, size);
-
 			iova = otx2_aura_allocptr(pfvf, pool_id);
 		}
+
+		for (idx = 0 ; idx < pool->xdp_cnt; idx++) {
+			if (!pool->xdp[idx])
+				continue;
+
+			xsk_buff_free(pool->xdp[idx]);
+		}
 	}
 }
 
@@ -1332,7 +1359,8 @@ void otx2_aura_pool_free(struct otx2_nic *pfvf)
 		qmem_free(pfvf->dev, pool->stack);
 		qmem_free(pfvf->dev, pool->fc_addr);
 		page_pool_destroy(pool->page_pool);
-		pool->page_pool = NULL;
+		devm_kfree(pfvf->dev, pool->xdp);
+		pool->xsk_pool = NULL;
 	}
 	devm_kfree(pfvf->dev, pfvf->qset.pool);
 	pfvf->qset.pool = NULL;
@@ -1341,6 +1369,13 @@ void otx2_aura_pool_free(struct otx2_nic *pfvf)
 int otx2_aura_init(struct otx2_nic *pfvf, int aura_id,
 		   int pool_id, int numptrs)
 {
+	return pfvf->hw_ops->aura_aq_init(pfvf, aura_id, pool_id,
+					  numptrs);
+}
+
+int otx2_aura_aq_init(struct otx2_nic *pfvf, int aura_id,
+		      int pool_id, int numptrs)
+{
 	struct npa_aq_enq_req *aq;
 	struct otx2_pool *pool;
 	int err;
@@ -1418,7 +1453,15 @@ int otx2_aura_init(struct otx2_nic *pfvf, int aura_id,
 int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id,
 		   int stack_pages, int numptrs, int buf_size, int type)
 {
+	return pfvf->hw_ops->pool_aq_init(pfvf, pool_id, stack_pages, numptrs,
+					  buf_size, type);
+}
+
+int otx2_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id,
+		      int stack_pages, int numptrs, int buf_size, int type)
+{
 	struct page_pool_params pp_params = { 0 };
+	struct xsk_buff_pool *xsk_pool;
 	struct npa_aq_enq_req *aq;
 	struct otx2_pool *pool;
 	int err;
@@ -1462,21 +1505,33 @@ int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id,
 	aq->ctype = NPA_AQ_CTYPE_POOL;
 	aq->op = NPA_AQ_INSTOP_INIT;
 
-	if (type != AURA_NIX_RQ) {
-		pool->page_pool = NULL;
+	if (type != AURA_NIX_RQ)
+		return 0;
+
+	if (!test_bit(pool_id, pfvf->af_xdp_zc_qidx)) {
+		pp_params.order = get_order(buf_size);
+		pp_params.flags = PP_FLAG_DMA_MAP;
+		pp_params.pool_size = min(OTX2_PAGE_POOL_SZ, numptrs);
+		pp_params.nid = NUMA_NO_NODE;
+		pp_params.dev = pfvf->dev;
+		pp_params.dma_dir = DMA_FROM_DEVICE;
+		pool->page_pool = page_pool_create(&pp_params);
+		if (IS_ERR(pool->page_pool)) {
+			netdev_err(pfvf->netdev, "Creation of page pool failed\n");
+			return PTR_ERR(pool->page_pool);
+		}
 		return 0;
 	}
 
-	pp_params.order = get_order(buf_size);
-	pp_params.flags = PP_FLAG_DMA_MAP;
-	pp_params.pool_size = min(OTX2_PAGE_POOL_SZ, numptrs);
-	pp_params.nid = NUMA_NO_NODE;
-	pp_params.dev = pfvf->dev;
-	pp_params.dma_dir = DMA_FROM_DEVICE;
-	pool->page_pool = page_pool_create(&pp_params);
-	if (IS_ERR(pool->page_pool)) {
-		netdev_err(pfvf->netdev, "Creation of page pool failed\n");
-		return PTR_ERR(pool->page_pool);
+	/* Set XSK pool to support AF_XDP zero-copy */
+	xsk_pool = xsk_get_pool_from_qid(pfvf->netdev, pool_id);
+	if (xsk_pool) {
+		pool->xsk_pool = xsk_pool;
+		pool->xdp_cnt = numptrs;
+		pool->xdp = devm_kcalloc(pfvf->dev,
+					 numptrs, sizeof(struct xdp_buff *), GFP_KERNEL);
+		if (!pool->xdp)
+			return -ENOMEM;
 	}
 
 	return 0;
@@ -1537,9 +1592,18 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf)
 		}
 
 		for (ptr = 0; ptr < num_sqbs; ptr++) {
-			err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
-			if (err)
+			err = otx2_alloc_rbuf(pfvf, pool, &bufptr, pool_id, ptr);
+			if (err) {
+				if (pool->xsk_pool) {
+					ptr--;
+					while (ptr >= 0) {
+						xsk_buff_free(pool->xdp[ptr]);
+						ptr--;
+					}
+				}
 				goto err_mem;
+			}
+
 			pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);
 			sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr;
 		}
@@ -1589,11 +1653,19 @@ int otx2_rq_aura_pool_init(struct otx2_nic *pfvf)
 	/* Allocate pointers and free them to aura/pool */
 	for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) {
 		pool = &pfvf->qset.pool[pool_id];
+
 		for (ptr = 0; ptr < num_ptrs; ptr++) {
-			err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
-			if (err)
+			err = otx2_alloc_rbuf(pfvf, pool, &bufptr, pool_id, ptr);
+			if (err) {
+				if (pool->xsk_pool) {
+					while (ptr)
+						xsk_buff_free(pool->xdp[--ptr]);
+				}
 				return -ENOMEM;
+			}
+
 			pfvf->hw_ops->aura_freeptr(pfvf, pool_id,
+						   pool->xsk_pool ? bufptr :
 						   bufptr + OTX2_HEAD_ROOM);
 		}
 	}
@@ -1756,7 +1828,7 @@ int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable)
 		req->chan_cnt = IEEE_8021QAZ_MAX_TCS;
 		req->bpid_per_chan = 1;
 	} else {
-		req->chan_cnt = 1;
+		req->chan_cnt = pfvf->hw.rx_chan_cnt;
 		req->bpid_per_chan = 0;
 	}
 
@@ -1781,7 +1853,7 @@ int otx2_nix_cpt_config_bp(struct otx2_nic *pfvf, bool enable)
 		req->chan_cnt = IEEE_8021QAZ_MAX_TCS;
 		req->bpid_per_chan = 1;
 	} else {
-		req->chan_cnt = 1;
+		req->chan_cnt = pfvf->hw.rx_chan_cnt;
 		req->bpid_per_chan = 0;
 	}
 
@@ -1989,6 +2061,43 @@ int otx2_handle_ntuple_tc_features(struct net_device *netdev, netdev_features_t
 }
 EXPORT_SYMBOL(otx2_handle_ntuple_tc_features);
 
+int otx2_set_hw_capabilities(struct otx2_nic *pfvf)
+{
+	struct mbox *mbox = &pfvf->mbox;
+	struct otx2_hw *hw = &pfvf->hw;
+	struct get_hw_cap_rsp *rsp;
+	struct msg_req *req;
+	int ret = -ENOMEM;
+
+	mutex_lock(&mbox->lock);
+
+	req = otx2_mbox_alloc_msg_get_hw_cap(mbox);
+	if (!req)
+		goto fail;
+
+	ret = otx2_sync_mbox_msg(mbox);
+	if (ret)
+		goto fail;
+
+	rsp = (struct get_hw_cap_rsp *)otx2_mbox_get_rsp(&pfvf->mbox.mbox,
+							 0, &req->hdr);
+	if (IS_ERR(rsp)) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	if (rsp->hw_caps & HW_CAP_MACSEC)
+		__set_bit(CN10K_HW_MACSEC, &hw->cap_flag);
+
+	mutex_unlock(&mbox->lock);
+
+	return 0;
+fail:
+	dev_err(pfvf->dev, "Cannot get MACSEC capability from AF\n");
+	mutex_unlock(&mbox->lock);
+	return ret;
+}
+
 #define M(_name, _id, _fn_name, _req_type, _rsp_type)			\
 int __weak								\
 otx2_mbox_up_handler_ ## _fn_name(struct otx2_nic *pfvf,		\
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 65814e3dc93f..e616a727a3a9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -14,6 +14,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/timecounter.h>
+#include <linux/soc/marvell/silicons.h>
 #include <linux/soc/marvell/octeontx2/asm.h>
 #include <net/macsec.h>
 #include <net/pkt_cls.h>
@@ -21,16 +22,19 @@
 #include <linux/time64.h>
 #include <linux/dim.h>
 #include <uapi/linux/if_macsec.h>
+#include <net/page_pool/helpers.h>
 
 #include <mbox.h>
 #include <npc.h>
 #include "otx2_reg.h"
 #include "otx2_txrx.h"
 #include "otx2_devlink.h"
+#include <rvu.h>
 #include <rvu_trace.h>
 #include "qos.h"
 #include "rep.h"
 #include "cn10k_ipsec.h"
+#include "cn20k.h"
 
 /* IPv4 flag more fragment bit */
 #define IPV4_FLAG_MORE				0x20
@@ -60,6 +64,12 @@
 /* Number of segments per SG structure */
 #define MAX_SEGS_PER_SG 3
 
+irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq);
+irqreturn_t cn20k_pfaf_mbox_intr_handler(int irq, void *pf_irq);
+irqreturn_t cn20k_vfaf_mbox_intr_handler(int irq, void *vf_irq);
+irqreturn_t cn20k_pfvf_mbox_intr_handler(int irq, void *pf_irq);
+irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq);
+
 enum arua_mapped_qtypes {
 	AURA_NIX_RQ,
 	AURA_NIX_SQ,
@@ -84,10 +94,6 @@ struct otx2_lmt_info {
 	u64 lmt_addr;
 	u16 lmt_id;
 };
-/* RSS configuration */
-struct otx2_rss_ctx {
-	u8  ind_tbl[MAX_RSS_INDIR_TBL_SIZE];
-};
 
 struct otx2_rss_info {
 	u8 enable;
@@ -95,7 +101,7 @@ struct otx2_rss_info {
 	u16 rss_size;
 #define RSS_HASH_KEY_SIZE	44   /* 352 bit key */
 	u8  key[RSS_HASH_KEY_SIZE];
-	struct otx2_rss_ctx	*rss_ctx[MAX_RSS_GROUPS];
+	u32 ind_tbl[MAX_RSS_INDIR_TBL_SIZE];
 };
 
 /* NIX (or NPC) RX errors */
@@ -128,6 +134,12 @@ enum otx2_errcodes_re {
 	ERRCODE_IL4_CSUM = 0x22,
 };
 
+enum otx2_xdp_action {
+	OTX2_XDP_TX	  = BIT(0),
+	OTX2_XDP_REDIRECT = BIT(1),
+	OTX2_AF_XDP_FRAME = BIT(2),
+};
+
 struct otx2_dev_stats {
 	u64 rx_bytes;
 	u64 rx_frames;
@@ -142,6 +154,7 @@ struct otx2_dev_stats {
 	u64 tx_bcast_frames;
 	u64 tx_mcast_frames;
 	u64 tx_drops;
+	atomic_long_t tx_discards;
 };
 
 /* Driver counted stats */
@@ -238,6 +251,7 @@ struct otx2_hw {
 	u16			nix_msixoff; /* Offset of NIX vectors */
 	char			*irq_name;
 	cpumask_var_t           *affinity_mask;
+	struct pf_irq_data	*pfvf_irq_devid[4];
 
 	/* Stats */
 	struct otx2_dev_stats	dev_stats;
@@ -349,6 +363,7 @@ struct otx2_flow_config {
 	struct list_head	flow_list_tc;
 	u8			ucast_flt_cnt;
 	bool			ntuple;
+	u16			ntuple_cnt;
 };
 
 struct dev_hw_ops {
@@ -358,6 +373,14 @@ struct dev_hw_ops {
 			     int size, int qidx);
 	int	(*refill_pool_ptrs)(void *dev, struct otx2_cq_queue *cq);
 	void	(*aura_freeptr)(void *dev, int aura, u64 buf);
+	irqreturn_t (*pfaf_mbox_intr_handler)(int irq, void *pf_irq);
+	irqreturn_t (*vfaf_mbox_intr_handler)(int irq, void *pf_irq);
+	irqreturn_t (*pfvf_mbox_intr_handler)(int irq, void *pf_irq);
+	int	(*aura_aq_init)(struct otx2_nic *pfvf, int aura_id,
+				int pool_id, int numptrs);
+	int	(*pool_aq_init)(struct otx2_nic *pfvf, u16 pool_id,
+				int stack_pages, int numptrs, int buf_size,
+				int type);
 };
 
 #define CN10K_MCS_SA_PER_SC	4
@@ -425,6 +448,16 @@ struct cn10k_mcs_cfg {
 	struct list_head rxsc_list;
 };
 
+struct pf_irq_data {
+	u64 intr_status;
+	void (*pf_queue_work_hdlr)(struct mbox *mb, struct workqueue_struct *mw,
+				   int first, int mdevs, u64 intr);
+	struct otx2_nic *pf;
+	int vec_num;
+	int start;
+	int mdevs;
+};
+
 struct otx2_nic {
 	void __iomem		*reg_base;
 	struct net_device	*netdev;
@@ -468,6 +501,7 @@ struct otx2_nic {
 	struct mbox		*mbox_pfvf;
 	struct workqueue_struct *mbox_wq;
 	struct workqueue_struct *mbox_pfvf_wq;
+	struct qmem		*pfvf_mbox_addr;
 
 	u8			total_vfs;
 	u16			pcifunc; /* RVU PF_FUNC */
@@ -499,7 +533,7 @@ struct otx2_nic {
 	u32			nix_lmt_size;
 
 	struct otx2_ptp		*ptp;
-	struct hwtstamp_config	tstamp;
+	struct kernel_hwtstamp_config tstamp;
 
 	unsigned long		rq_bmap;
 
@@ -531,6 +565,8 @@ struct otx2_nic {
 
 	/* Inline ipsec */
 	struct cn10k_ipsec	ipsec;
+	/* af_xdp zero-copy */
+	unsigned long		*af_xdp_zc_qidx;
 };
 
 static inline bool is_otx2_lbkvf(struct pci_dev *pdev)
@@ -622,9 +658,6 @@ static inline void otx2_setup_dev_hw_settings(struct otx2_nic *pfvf)
 		__set_bit(CN10K_PTP_ONESTEP, &hw->cap_flag);
 		__set_bit(QOS_CIR_PIR_SUPPORT, &hw->cap_flag);
 	}
-
-	if (is_dev_cn10kb(pfvf->pdev))
-		__set_bit(CN10K_HW_MACSEC, &hw->cap_flag);
 }
 
 /* Register read/write APIs */
@@ -723,8 +756,9 @@ static inline void otx2_write128(u64 lo, u64 hi, void __iomem *addr)
 			 ::[x0]"r"(lo), [x1]"r"(hi), [p1]"r"(addr));
 }
 
-static inline u64 otx2_atomic64_add(u64 incr, u64 *ptr)
+static inline u64 otx2_atomic64_add(u64 incr, void __iomem *addr)
 {
+	u64 __iomem *ptr = addr;
 	u64 result;
 
 	__asm__ volatile(".cpu   generic+lse\n"
@@ -737,7 +771,11 @@ static inline u64 otx2_atomic64_add(u64 incr, u64 *ptr)
 
 #else
 #define otx2_write128(lo, hi, addr)		writeq((hi) | (lo), addr)
-#define otx2_atomic64_add(incr, ptr)		({ *ptr += incr; })
+
+static inline u64 otx2_atomic64_add(u64 incr, void __iomem *addr)
+{
+	return 0;
+}
 #endif
 
 static inline void __cn10k_aura_freeptr(struct otx2_nic *pfvf, u64 aura,
@@ -787,7 +825,7 @@ static inline void cn10k_aura_freeptr(void *dev, int aura, u64 buf)
 /* Alloc pointer from pool/aura */
 static inline u64 otx2_aura_allocptr(struct otx2_nic *pfvf, int aura)
 {
-	u64 *ptr = (__force u64 *)otx2_get_regaddr(pfvf, NPA_LF_AURA_OP_ALLOCX(0));
+	void __iomem *ptr = otx2_get_regaddr(pfvf, NPA_LF_AURA_OP_ALLOCX(0));
 	u64 incr = (u64)aura | BIT_ULL(63);
 
 	return otx2_atomic64_add(incr, ptr);
@@ -862,6 +900,7 @@ static struct _req_type __maybe_unused					\
 *otx2_mbox_alloc_msg_ ## _fn_name(struct mbox *mbox)                    \
 {									\
 	struct _req_type *req;						\
+	u16 pcifunc = mbox->pfvf->pcifunc;				\
 									\
 	req = (struct _req_type *)otx2_mbox_alloc_msg_rsp(		\
 		&mbox->mbox, 0, sizeof(struct _req_type),		\
@@ -870,7 +909,8 @@ static struct _req_type __maybe_unused					\
 		return NULL;						\
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;				\
 	req->hdr.id = _id;						\
-	trace_otx2_msg_alloc(mbox->mbox.pdev, _id, sizeof(*req));	\
+	req->hdr.pcifunc = pcifunc;					\
+	trace_otx2_msg_alloc(mbox->mbox.pdev, _id, sizeof(*req), pcifunc); \
 	return req;							\
 }
 
@@ -890,21 +930,11 @@ MBOX_UP_MCS_MESSAGES
 /* Time to wait before watchdog kicks off */
 #define OTX2_TX_TIMEOUT		(100 * HZ)
 
-#define	RVU_PFVF_PF_SHIFT	10
-#define	RVU_PFVF_PF_MASK	0x3F
-#define	RVU_PFVF_FUNC_SHIFT	0
-#define	RVU_PFVF_FUNC_MASK	0x3FF
-
 static inline bool is_otx2_vf(u16 pcifunc)
 {
 	return !!(pcifunc & RVU_PFVF_FUNC_MASK);
 }
 
-static inline int rvu_get_pf(u16 pcifunc)
-{
-	return (pcifunc >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK;
-}
-
 static inline dma_addr_t otx2_dma_map_page(struct otx2_nic *pfvf,
 					   struct page *page,
 					   size_t offset, size_t size,
@@ -1002,7 +1032,7 @@ void otx2_txschq_free_one(struct otx2_nic *pfvf, u16 lvl, u16 schq);
 void otx2_free_pending_sqe(struct otx2_nic *pfvf);
 void otx2_sqb_flush(struct otx2_nic *pfvf);
 int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-		    dma_addr_t *dma);
+		    dma_addr_t *dma, int qidx, int idx);
 int otx2_rxtx_enable(struct otx2_nic *pfvf, bool enable);
 void otx2_ctx_disable(struct mbox *mbox, int type, bool npa);
 int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable);
@@ -1032,12 +1062,19 @@ void otx2_pfaf_mbox_destroy(struct otx2_nic *pf);
 void otx2_disable_mbox_intr(struct otx2_nic *pf);
 void otx2_disable_napi(struct otx2_nic *pf);
 irqreturn_t otx2_cq_intr_handler(int irq, void *cq_irq);
+int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura);
+int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx);
+int otx2_set_hw_capabilities(struct otx2_nic *pfvf);
+int otx2_aura_aq_init(struct otx2_nic *pfvf, int aura_id,
+		      int pool_id, int numptrs);
+int otx2_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id,
+		      int stack_pages, int numptrs, int buf_size, int type);
 
 /* RSS configuration APIs*/
 int otx2_rss_init(struct otx2_nic *pfvf);
 int otx2_set_flowkey_cfg(struct otx2_nic *pfvf);
 void otx2_set_rss_key(struct otx2_nic *pfvf);
-int otx2_set_rss_table(struct otx2_nic *pfvf, int ctx_id);
+int otx2_set_rss_table(struct otx2_nic *pfvf, int ctx_id, const u32 *ind_tbl);
 
 /* Mbox handlers */
 void mbox_handler_msix_offset(struct otx2_nic *pfvf,
@@ -1071,8 +1108,11 @@ int otx2_open(struct net_device *netdev);
 int otx2_stop(struct net_device *netdev);
 int otx2_set_real_num_queues(struct net_device *netdev,
 			     int tx_queues, int rx_queues);
-int otx2_ioctl(struct net_device *netdev, struct ifreq *req, int cmd);
-int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr);
+int otx2_config_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config);
+int otx2_config_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack);
 
 /* MCAM filter related APIs */
 int otx2_mcam_flow_init(struct otx2_nic *pf);
@@ -1094,7 +1134,10 @@ int otx2_del_macfilter(struct net_device *netdev, const u8 *mac);
 int otx2_add_macfilter(struct net_device *netdev, const u8 *mac);
 int otx2_enable_rxvlan(struct otx2_nic *pf, bool enable);
 int otx2_install_rxvlan_offload_flow(struct otx2_nic *pfvf);
-bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx);
+bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, struct xdp_frame *xdpf,
+			    u64 iova, int len, u16 qidx, u16 flags);
+void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, struct xdp_frame *xdpf,
+			 u64 dma_addr, int len, int *offset, u16 flags);
 u16 otx2_get_max_mtu(struct otx2_nic *pfvf);
 int otx2_handle_ntuple_tc_features(struct net_device *netdev,
 				   netdev_features_t features);
@@ -1175,4 +1218,7 @@ static inline int mcam_entry_cmp(const void *a, const void *b)
 dma_addr_t otx2_dma_map_skb_frag(struct otx2_nic *pfvf,
 				 struct sk_buff *skb, int seg, int *len);
 void otx2_dma_unmap_skb_frags(struct otx2_nic *pfvf, struct sg_list *sg);
+int otx2_read_free_sqe(struct otx2_nic *pfvf, u16 qidx);
+void otx2_queue_vf_work(struct mbox *mw, struct workqueue_struct *mbox_wq,
+			int first, int mdevs, u64 intr);
 #endif /* OTX2_COMMON_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
index 33ec9a7f7c03..a72694219df4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
@@ -41,13 +41,15 @@ static int otx2_dl_mcam_count_set(struct devlink *devlink, u32 id,
 	if (!pfvf->flow_cfg)
 		return 0;
 
+	pfvf->flow_cfg->ntuple_cnt = ctx->val.vu16;
 	otx2_alloc_mcam_entries(pfvf, ctx->val.vu16);
 
 	return 0;
 }
 
 static int otx2_dl_mcam_count_get(struct devlink *devlink, u32 id,
-				  struct devlink_param_gset_ctx *ctx)
+				  struct devlink_param_gset_ctx *ctx,
+				  struct netlink_ext_ack *extack)
 {
 	struct otx2_devlink *otx2_dl = devlink_priv(devlink);
 	struct otx2_nic *pfvf = otx2_dl->pfvf;
@@ -83,7 +85,8 @@ static int otx2_dl_ucast_flt_cnt_set(struct devlink *devlink, u32 id,
 }
 
 static int otx2_dl_ucast_flt_cnt_get(struct devlink *devlink, u32 id,
-				     struct devlink_param_gset_ctx *ctx)
+				     struct devlink_param_gset_ctx *ctx,
+				     struct netlink_ext_ack *extack)
 {
 	struct otx2_devlink *otx2_dl = devlink_priv(devlink);
 	struct otx2_nic *pfvf = otx2_dl->pfvf;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 2d53dc77ef1e..b90e23dc49de 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -15,6 +15,7 @@
 
 #include "otx2_common.h"
 #include "otx2_ptp.h"
+#include <cgx_fw_if.h>
 
 #define DRV_NAME	"rvu-nicpf"
 #define DRV_VF_NAME	"rvu-nicvf"
@@ -315,7 +316,7 @@ static void otx2_get_pauseparam(struct net_device *netdev,
 	struct otx2_nic *pfvf = netdev_priv(netdev);
 	struct cgx_pause_frm_cfg *req, *rsp;
 
-	if (is_otx2_lbkvf(pfvf->pdev))
+	if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev))
 		return;
 
 	mutex_lock(&pfvf->mbox.lock);
@@ -347,7 +348,7 @@ static int otx2_set_pauseparam(struct net_device *netdev,
 	if (pause->autoneg)
 		return -EOPNOTSUPP;
 
-	if (is_otx2_lbkvf(pfvf->pdev))
+	if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev))
 		return -EOPNOTSUPP;
 
 	if (pause->rx_pause)
@@ -559,10 +560,13 @@ static int otx2_set_coalesce(struct net_device *netdev,
 	return 0;
 }
 
-static int otx2_get_rss_hash_opts(struct otx2_nic *pfvf,
-				  struct ethtool_rxnfc *nfc)
+static int otx2_get_rss_hash_opts(struct net_device *dev,
+				  struct ethtool_rxfh_fields *nfc)
 {
-	struct otx2_rss_info *rss = &pfvf->hw.rss_info;
+	struct otx2_nic *pfvf = netdev_priv(dev);
+	struct otx2_rss_info *rss;
+
+	rss = &pfvf->hw.rss_info;
 
 	if (!(rss->flowkey_cfg &
 	    (NIX_FLOW_KEY_TYPE_IPV4 | NIX_FLOW_KEY_TYPE_IPV6)))
@@ -609,12 +613,17 @@ static int otx2_get_rss_hash_opts(struct otx2_nic *pfvf,
 	return 0;
 }
 
-static int otx2_set_rss_hash_opts(struct otx2_nic *pfvf,
-				  struct ethtool_rxnfc *nfc)
+static int otx2_set_rss_hash_opts(struct net_device *dev,
+				  const struct ethtool_rxfh_fields *nfc,
+				  struct netlink_ext_ack *extack)
 {
-	struct otx2_rss_info *rss = &pfvf->hw.rss_info;
+	struct otx2_nic *pfvf = netdev_priv(dev);
 	u32 rxh_l4 = RXH_L4_B_0_1 | RXH_L4_B_2_3;
-	u32 rss_cfg = rss->flowkey_cfg;
+	struct otx2_rss_info *rss;
+	u32 rss_cfg;
+
+	rss = &pfvf->hw.rss_info;
+	rss_cfg = rss->flowkey_cfg;
 
 	if (!rss->enable) {
 		netdev_err(pfvf->netdev,
@@ -743,8 +752,6 @@ static int otx2_get_rxnfc(struct net_device *dev,
 		if (netif_running(dev) && ntuple)
 			ret = otx2_get_all_flows(pfvf, nfc, rules);
 		break;
-	case ETHTOOL_GRXFH:
-		return otx2_get_rss_hash_opts(pfvf, nfc);
 	default:
 		break;
 	}
@@ -759,9 +766,6 @@ static int otx2_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc)
 
 	pfvf->flow_cfg->ntuple = ntuple;
 	switch (nfc->cmd) {
-	case ETHTOOL_SRXFH:
-		ret = otx2_set_rss_hash_opts(pfvf, nfc);
-		break;
 	case ETHTOOL_SRXCLSRLINS:
 		if (netif_running(dev) && ntuple)
 			ret = otx2_add_flow(pfvf, nfc);
@@ -792,60 +796,91 @@ static u32 otx2_get_rxfh_indir_size(struct net_device *dev)
 	return  MAX_RSS_INDIR_TBL_SIZE;
 }
 
-static int otx2_rss_ctx_delete(struct otx2_nic *pfvf, int ctx_id)
+static int otx2_create_rxfh(struct net_device *dev,
+			    struct ethtool_rxfh_context *ctx,
+			    const struct ethtool_rxfh_param *rxfh,
+			    struct netlink_ext_ack *extack)
 {
-	struct otx2_rss_info *rss = &pfvf->hw.rss_info;
+	struct otx2_nic *pfvf = netdev_priv(dev);
+	struct otx2_rss_info *rss;
+	unsigned int queues;
+	u32 *ind_tbl;
+	int idx;
+
+	rss = &pfvf->hw.rss_info;
+	queues = pfvf->hw.rx_queues;
 
-	otx2_rss_ctx_flow_del(pfvf, ctx_id);
-	kfree(rss->rss_ctx[ctx_id]);
-	rss->rss_ctx[ctx_id] = NULL;
+	if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+	ctx->hfunc = ETH_RSS_HASH_TOP;
 
+	if (!rss->enable) {
+		netdev_err(dev, "RSS is disabled, cannot change settings\n");
+		return -EIO;
+	}
+
+	ind_tbl = rxfh->indir;
+	if (!ind_tbl) {
+		ind_tbl = ethtool_rxfh_context_indir(ctx);
+		for (idx = 0; idx < rss->rss_size; idx++)
+			ind_tbl[idx] = ethtool_rxfh_indir_default(idx, queues);
+	}
+
+	otx2_set_rss_table(pfvf, rxfh->rss_context, ind_tbl);
 	return 0;
 }
 
-static int otx2_rss_ctx_create(struct otx2_nic *pfvf,
-			       u32 *rss_context)
+static int otx2_modify_rxfh(struct net_device *dev,
+			    struct ethtool_rxfh_context *ctx,
+			    const struct ethtool_rxfh_param *rxfh,
+			    struct netlink_ext_ack *extack)
 {
-	struct otx2_rss_info *rss = &pfvf->hw.rss_info;
-	u8 ctx;
+	struct otx2_nic *pfvf = netdev_priv(dev);
 
-	for (ctx = 0; ctx < MAX_RSS_GROUPS; ctx++) {
-		if (!rss->rss_ctx[ctx])
-			break;
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
+	if (!pfvf->hw.rss_info.enable) {
+		netdev_err(dev, "RSS is disabled, cannot change settings\n");
+		return -EIO;
 	}
-	if (ctx == MAX_RSS_GROUPS)
-		return -EINVAL;
 
-	rss->rss_ctx[ctx] = kzalloc(sizeof(*rss->rss_ctx[ctx]), GFP_KERNEL);
-	if (!rss->rss_ctx[ctx])
-		return -ENOMEM;
-	*rss_context = ctx;
+	if (rxfh->indir)
+		otx2_set_rss_table(pfvf, rxfh->rss_context, rxfh->indir);
 
 	return 0;
 }
 
+static int otx2_remove_rxfh(struct net_device *dev,
+			    struct ethtool_rxfh_context *ctx,
+			    u32 rss_context,
+			    struct netlink_ext_ack *extack)
+{
+	struct otx2_nic *pfvf = netdev_priv(dev);
+
+	if (!pfvf->hw.rss_info.enable) {
+		netdev_err(dev, "RSS is disabled, cannot change settings\n");
+		return -EIO;
+	}
+
+	otx2_rss_ctx_flow_del(pfvf, rss_context);
+	return 0;
+}
+
 /* Configure RSS table and hash key */
 static int otx2_set_rxfh(struct net_device *dev,
 			 struct ethtool_rxfh_param *rxfh,
 			 struct netlink_ext_ack *extack)
 {
-	u32 rss_context = DEFAULT_RSS_CONTEXT_GROUP;
 	struct otx2_nic *pfvf = netdev_priv(dev);
-	struct otx2_rss_ctx *rss_ctx;
 	struct otx2_rss_info *rss;
-	int ret, idx;
+	int idx;
 
 	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
 	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (rxfh->rss_context)
-		rss_context = rxfh->rss_context;
-
-	if (rss_context != ETH_RXFH_CONTEXT_ALLOC &&
-	    rss_context >= MAX_RSS_GROUPS)
-		return -EINVAL;
-
 	rss = &pfvf->hw.rss_info;
 
 	if (!rss->enable) {
@@ -857,21 +892,12 @@ static int otx2_set_rxfh(struct net_device *dev,
 		memcpy(rss->key, rxfh->key, sizeof(rss->key));
 		otx2_set_rss_key(pfvf);
 	}
-	if (rxfh->rss_delete)
-		return otx2_rss_ctx_delete(pfvf, rss_context);
-
-	if (rss_context == ETH_RXFH_CONTEXT_ALLOC) {
-		ret = otx2_rss_ctx_create(pfvf, &rss_context);
-		rxfh->rss_context = rss_context;
-		if (ret)
-			return ret;
-	}
+
 	if (rxfh->indir) {
-		rss_ctx = rss->rss_ctx[rss_context];
 		for (idx = 0; idx < rss->rss_size; idx++)
-			rss_ctx->ind_tbl[idx] = rxfh->indir[idx];
+			rss->ind_tbl[idx] = rxfh->indir[idx];
 	}
-	otx2_set_rss_table(pfvf, rss_context);
+	otx2_set_rss_table(pfvf, DEFAULT_RSS_CONTEXT_GROUP, NULL);
 
 	return 0;
 }
@@ -880,9 +906,7 @@ static int otx2_set_rxfh(struct net_device *dev,
 static int otx2_get_rxfh(struct net_device *dev,
 			 struct ethtool_rxfh_param *rxfh)
 {
-	u32 rss_context = DEFAULT_RSS_CONTEXT_GROUP;
 	struct otx2_nic *pfvf = netdev_priv(dev);
-	struct otx2_rss_ctx *rss_ctx;
 	struct otx2_rss_info *rss;
 	u32 *indir = rxfh->indir;
 	int idx, rx_queues;
@@ -890,28 +914,21 @@ static int otx2_get_rxfh(struct net_device *dev,
 	rss = &pfvf->hw.rss_info;
 
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
-	if (rxfh->rss_context)
-		rss_context = rxfh->rss_context;
-
 	if (!indir)
 		return 0;
 
-	if (!rss->enable && rss_context == DEFAULT_RSS_CONTEXT_GROUP) {
+	if (!rss->enable) {
 		rx_queues = pfvf->hw.rx_queues;
 		for (idx = 0; idx < MAX_RSS_INDIR_TBL_SIZE; idx++)
 			indir[idx] = ethtool_rxfh_indir_default(idx, rx_queues);
 		return 0;
 	}
-	if (rss_context >= MAX_RSS_GROUPS)
-		return -ENOENT;
 
-	rss_ctx = rss->rss_ctx[rss_context];
-	if (!rss_ctx)
-		return -ENOENT;
-
-	if (indir) {
-		for (idx = 0; idx < rss->rss_size; idx++)
-			indir[idx] = rss_ctx->ind_tbl[idx];
+	for (idx = 0; idx < rss->rss_size; idx++) {
+		/* Ignore if the rx queue is AF_XDP zero copy enabled */
+		if (test_bit(rss->ind_tbl[idx], pfvf->af_xdp_zc_qidx))
+			continue;
+		indir[idx] = rss->ind_tbl[idx];
 	}
 	if (rxfh->key)
 		memcpy(rxfh->key, rss->key, sizeof(rss->key));
@@ -937,8 +954,8 @@ static u32 otx2_get_link(struct net_device *netdev)
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
 
-	/* LBK link is internal and always UP */
-	if (is_otx2_lbkvf(pfvf->pdev))
+	/* LBK and SDP links are internal and always UP */
+	if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev))
 		return 1;
 	return pfvf->linfo.link_up;
 }
@@ -1119,17 +1136,9 @@ static void otx2_get_link_mode_info(u64 link_mode_bmap,
 				    *link_ksettings)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(otx2_link_modes) = { 0, };
-	const int otx2_sgmii_features[6] = {
-		ETHTOOL_LINK_MODE_10baseT_Half_BIT,
-		ETHTOOL_LINK_MODE_10baseT_Full_BIT,
-		ETHTOOL_LINK_MODE_100baseT_Half_BIT,
-		ETHTOOL_LINK_MODE_100baseT_Full_BIT,
-		ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
-		ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
-	};
 	/* CGX link modes to Ethtool link mode mapping */
-	const int cgx_link_mode[27] = {
-		0, /* SGMII  Mode */
+	const int cgx_link_mode[CGX_MODE_MAX] = {
+		0, /* SGMII  1000baseT */
 		ETHTOOL_LINK_MODE_1000baseX_Full_BIT,
 		ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
 		ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
@@ -1159,14 +1168,19 @@ static void otx2_get_link_mode_info(u64 link_mode_bmap,
 	};
 	u8 bit;
 
-	for_each_set_bit(bit, (unsigned long *)&link_mode_bmap, 27) {
-		/* SGMII mode is set */
-		if (bit == 0)
-			linkmode_set_bit_array(otx2_sgmii_features,
-					       ARRAY_SIZE(otx2_sgmii_features),
-					       otx2_link_modes);
-		else
+	for_each_set_bit(bit, (unsigned long *)&link_mode_bmap, ARRAY_SIZE(cgx_link_mode)) {
+		if (bit == CGX_MODE_SGMII_10M_BIT) {
+			linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, otx2_link_modes);
+			linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, otx2_link_modes);
+		} else if (bit == CGX_MODE_SGMII_100M_BIT) {
+			linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, otx2_link_modes);
+			linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, otx2_link_modes);
+		} else if (bit == CGX_MODE_SGMII) {
+			linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, otx2_link_modes);
+			linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, otx2_link_modes);
+		} else {
 			linkmode_set_bit(cgx_link_mode[bit], otx2_link_modes);
+		}
 	}
 
 	if (req_mode == OTX2_MODE_ADVERTISED)
@@ -1207,23 +1221,10 @@ static int otx2_get_link_ksettings(struct net_device *netdev,
 	return 0;
 }
 
-static void otx2_get_advertised_mode(const struct ethtool_link_ksettings *cmd,
-				     u64 *mode)
-{
-	u32 bit_pos;
-
-	/* Firmware does not support requesting multiple advertised modes
-	 * return first set bit
-	 */
-	bit_pos = find_first_bit(cmd->link_modes.advertising,
-				 __ETHTOOL_LINK_MODE_MASK_NBITS);
-	if (bit_pos != __ETHTOOL_LINK_MODE_MASK_NBITS)
-		*mode = bit_pos;
-}
-
 static int otx2_set_link_ksettings(struct net_device *netdev,
 				   const struct ethtool_link_ksettings *cmd)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct otx2_nic *pf = netdev_priv(netdev);
 	struct ethtool_link_ksettings cur_ks;
 	struct cgx_set_link_mode_req *req;
@@ -1260,7 +1261,20 @@ static int otx2_set_link_ksettings(struct net_device *netdev,
 	 */
 	req->args.duplex = cmd->base.duplex ^ 0x1;
 	req->args.an = cmd->base.autoneg;
-	otx2_get_advertised_mode(cmd, &req->args.mode);
+	/* Mask unsupported modes and send message to AF */
+	linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT, mask);
+
+	linkmode_copy(req->args.advertising,
+		      cmd->link_modes.advertising);
+	linkmode_andnot(req->args.advertising,
+			req->args.advertising, mask);
+
+	/* inform AF that we need parse this differently */
+	if (bitmap_weight(req->args.advertising,
+			  __ETHTOOL_LINK_MODE_MASK_NBITS) >= 2)
+		req->args.multimode = true;
 
 	err = otx2_sync_mbox_msg(&pf->mbox);
 end:
@@ -1269,7 +1283,8 @@ end:
 }
 
 static void otx2_get_fec_stats(struct net_device *netdev,
-			       struct ethtool_fec_stats *fec_stats)
+			       struct ethtool_fec_stats *fec_stats,
+			       struct ethtool_fec_hist *hist)
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
 	struct cgx_fw_data *rsp;
@@ -1302,12 +1317,12 @@ static void otx2_get_fec_stats(struct net_device *netdev,
 }
 
 static const struct ethtool_ops otx2_ethtool_ops = {
-	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
 	.supported_ring_params  = ETHTOOL_RING_USE_RX_BUF_LEN |
 				  ETHTOOL_RING_USE_CQE_SIZE,
+	.rxfh_max_num_contexts	= MAX_RSS_GROUPS,
 	.get_link		= otx2_get_link,
 	.get_drvinfo		= otx2_get_drvinfo,
 	.get_strings		= otx2_get_strings,
@@ -1325,6 +1340,11 @@ static const struct ethtool_ops otx2_ethtool_ops = {
 	.get_rxfh_indir_size	= otx2_get_rxfh_indir_size,
 	.get_rxfh		= otx2_get_rxfh,
 	.set_rxfh		= otx2_set_rxfh,
+	.get_rxfh_fields	= otx2_get_rss_hash_opts,
+	.set_rxfh_fields	= otx2_set_rss_hash_opts,
+	.create_rxfh_context	= otx2_create_rxfh,
+	.modify_rxfh_context	= otx2_modify_rxfh,
+	.remove_rxfh_context	= otx2_remove_rxfh,
 	.get_msglevel		= otx2_get_msglevel,
 	.set_msglevel		= otx2_set_msglevel,
 	.get_pauseparam		= otx2_get_pauseparam,
@@ -1409,7 +1429,7 @@ static int otx2vf_get_link_ksettings(struct net_device *netdev,
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
 
-	if (is_otx2_lbkvf(pfvf->pdev)) {
+	if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev)) {
 		cmd->base.duplex = DUPLEX_FULL;
 		cmd->base.speed = SPEED_100000;
 	} else {
@@ -1419,12 +1439,12 @@ static int otx2vf_get_link_ksettings(struct net_device *netdev,
 }
 
 static const struct ethtool_ops otx2vf_ethtool_ops = {
-	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
 	.supported_ring_params  = ETHTOOL_RING_USE_RX_BUF_LEN |
 				  ETHTOOL_RING_USE_CQE_SIZE,
+	.rxfh_max_num_contexts	= MAX_RSS_GROUPS,
 	.get_link		= otx2_get_link,
 	.get_drvinfo		= otx2vf_get_drvinfo,
 	.get_strings		= otx2vf_get_strings,
@@ -1438,6 +1458,11 @@ static const struct ethtool_ops otx2vf_ethtool_ops = {
 	.get_rxfh_indir_size	= otx2_get_rxfh_indir_size,
 	.get_rxfh		= otx2_get_rxfh,
 	.set_rxfh		= otx2_set_rxfh,
+	.get_rxfh_fields	= otx2_get_rss_hash_opts,
+	.set_rxfh_fields	= otx2_set_rss_hash_opts,
+	.create_rxfh_context	= otx2_create_rxfh,
+	.modify_rxfh_context	= otx2_modify_rxfh,
+	.remove_rxfh_context	= otx2_remove_rxfh,
 	.get_ringparam		= otx2_get_ringparam,
 	.set_ringparam		= otx2_set_ringparam,
 	.get_coalesce		= otx2_get_coalesce,
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 47bfd1fb37d4..64c6d9162ef6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -247,7 +247,7 @@ int otx2_mcam_entry_init(struct otx2_nic *pfvf)
 	mutex_unlock(&pfvf->mbox.lock);
 
 	/* Allocate entries for Ntuple filters */
-	count = otx2_alloc_mcam_entries(pfvf, OTX2_DEFAULT_FLOWCOUNT);
+	count = otx2_alloc_mcam_entries(pfvf, flow_cfg->ntuple_cnt);
 	if (count <= 0) {
 		otx2_clear_ntuple_flow_info(pfvf, flow_cfg);
 		return 0;
@@ -307,6 +307,7 @@ int otx2_mcam_flow_init(struct otx2_nic *pf)
 	INIT_LIST_HEAD(&pf->flow_cfg->flow_list_tc);
 
 	pf->flow_cfg->ucast_flt_cnt = OTX2_DEFAULT_UNICAST_FLOWS;
+	pf->flow_cfg->ntuple_cnt = OTX2_DEFAULT_FLOWCOUNT;
 
 	/* Allocate bare minimum number of MCAM entries needed for
 	 * unicast and ntuple filters.
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index e1dde93e8af8..a7feb4c392b3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -27,6 +27,7 @@
 #include "qos.h"
 #include <rvu_trace.h>
 #include "cn10k_ipsec.h"
+#include "otx2_xsk.h"
 
 #define DRV_NAME	"rvu_nicpf"
 #define DRV_STRING	"Marvell RVU NIC Physical Function Driver"
@@ -205,7 +206,8 @@ static int otx2_register_flr_me_intr(struct otx2_nic *pf, int numvfs)
 
 	/* Register ME interrupt handler*/
 	irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFME0 * NAME_SIZE];
-	snprintf(irq_name, NAME_SIZE, "RVUPF%d_ME0", rvu_get_pf(pf->pcifunc));
+	snprintf(irq_name, NAME_SIZE, "RVUPF%d_ME0",
+		 rvu_get_pf(pf->pdev, pf->pcifunc));
 	ret = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFME0),
 			  otx2_pf_me_intr_handler, 0, irq_name, pf);
 	if (ret) {
@@ -215,7 +217,8 @@ static int otx2_register_flr_me_intr(struct otx2_nic *pf, int numvfs)
 
 	/* Register FLR interrupt handler */
 	irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFFLR0 * NAME_SIZE];
-	snprintf(irq_name, NAME_SIZE, "RVUPF%d_FLR0", rvu_get_pf(pf->pcifunc));
+	snprintf(irq_name, NAME_SIZE, "RVUPF%d_FLR0",
+		 rvu_get_pf(pf->pdev, pf->pcifunc));
 	ret = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFFLR0),
 			  otx2_pf_flr_intr_handler, 0, irq_name, pf);
 	if (ret) {
@@ -227,7 +230,7 @@ static int otx2_register_flr_me_intr(struct otx2_nic *pf, int numvfs)
 	if (numvfs > 64) {
 		irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFME1 * NAME_SIZE];
 		snprintf(irq_name, NAME_SIZE, "RVUPF%d_ME1",
-			 rvu_get_pf(pf->pcifunc));
+			 rvu_get_pf(pf->pdev, pf->pcifunc));
 		ret = request_irq(pci_irq_vector
 				  (pf->pdev, RVU_PF_INT_VEC_VFME1),
 				  otx2_pf_me_intr_handler, 0, irq_name, pf);
@@ -237,7 +240,7 @@ static int otx2_register_flr_me_intr(struct otx2_nic *pf, int numvfs)
 		}
 		irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFFLR1 * NAME_SIZE];
 		snprintf(irq_name, NAME_SIZE, "RVUPF%d_FLR1",
-			 rvu_get_pf(pf->pcifunc));
+			 rvu_get_pf(pf->pdev, pf->pcifunc));
 		ret = request_irq(pci_irq_vector
 				  (pf->pdev, RVU_PF_INT_VEC_VFFLR1),
 				  otx2_pf_flr_intr_handler, 0, irq_name, pf);
@@ -293,8 +296,8 @@ static int otx2_pf_flr_init(struct otx2_nic *pf, int num_vfs)
 	return 0;
 }
 
-static void otx2_queue_vf_work(struct mbox *mw, struct workqueue_struct *mbox_wq,
-			       int first, int mdevs, u64 intr)
+void otx2_queue_vf_work(struct mbox *mw, struct workqueue_struct *mbox_wq,
+			int first, int mdevs, u64 intr)
 {
 	struct otx2_mbox_dev *mdev;
 	struct otx2_mbox *mbox;
@@ -464,6 +467,9 @@ static void otx2_pfvf_mbox_handler(struct work_struct *work)
 
 	offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
 
+	trace_otx2_msg_status(pf->pdev, "PF-VF down queue handler(forwarding)",
+			      vf_mbox->num_msgs);
+
 	for (id = 0; id < vf_mbox->num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + mbox->rx_start +
 					     offset);
@@ -472,7 +478,7 @@ static void otx2_pfvf_mbox_handler(struct work_struct *work)
 			goto inval_msg;
 
 		/* Set VF's number in each of the msg */
-		msg->pcifunc &= RVU_PFVF_FUNC_MASK;
+		msg->pcifunc &= ~RVU_PFVF_FUNC_MASK;
 		msg->pcifunc |= (vf_idx + 1) & RVU_PFVF_FUNC_MASK;
 		offset = msg->next_msgoff;
 	}
@@ -502,6 +508,9 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work)
 
 	offset = mbox->rx_start + ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
 
+	trace_otx2_msg_status(pf->pdev, "PF-VF up queue handler(response)",
+			      vf_mbox->up_num_msgs);
+
 	for (id = 0; id < vf_mbox->up_num_msgs; id++) {
 		msg = mdev->mbase + offset;
 
@@ -538,7 +547,7 @@ end:
 	}
 }
 
-static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
+irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
 {
 	struct otx2_nic *pf = (struct otx2_nic *)(pf_irq);
 	int vfs = pf->total_vfs;
@@ -567,6 +576,23 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
 	return IRQ_HANDLED;
 }
 
+static void *cn20k_pfvf_mbox_alloc(struct otx2_nic *pf, int numvfs)
+{
+	struct qmem *mbox_addr;
+	int err;
+
+	err = qmem_alloc(&pf->pdev->dev, &mbox_addr, numvfs, MBOX_SIZE);
+	if (err) {
+		dev_err(pf->dev, "qmem alloc fail\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	otx2_write64(pf, RVU_PF_VF_MBOX_ADDR, (u64)mbox_addr->iova);
+	pf->pfvf_mbox_addr = mbox_addr;
+
+	return mbox_addr->base;
+}
+
 static int otx2_pfvf_mbox_init(struct otx2_nic *pf, int numvfs)
 {
 	void __iomem *hwbase;
@@ -588,20 +614,27 @@ static int otx2_pfvf_mbox_init(struct otx2_nic *pf, int numvfs)
 	if (!pf->mbox_pfvf_wq)
 		return -ENOMEM;
 
-	/* On CN10K platform, PF <-> VF mailbox region follows after
-	 * PF <-> AF mailbox region.
+	/* For CN20K, PF allocates mbox memory in DRAM and writes PF/VF
+	 * regions/offsets in RVU_PF_VF_MBOX_ADDR, the RVU_PFX_FUNC_PFAF_MBOX
+	 * gives the aliased address to access PF/VF mailbox regions.
 	 */
-	if (test_bit(CN10K_MBOX, &pf->hw.cap_flag))
-		base = pci_resource_start(pf->pdev, PCI_MBOX_BAR_NUM) +
-		       MBOX_SIZE;
-	else
-		base = readq((void __iomem *)((u64)pf->reg_base +
-					      RVU_PF_VF_BAR4_ADDR));
+	if (is_cn20k(pf->pdev)) {
+		hwbase = (void __iomem *)cn20k_pfvf_mbox_alloc(pf, numvfs);
+	} else {
+		/* On CN10K platform, PF <-> VF mailbox region follows after
+		 * PF <-> AF mailbox region.
+		 */
+		if (test_bit(CN10K_MBOX, &pf->hw.cap_flag))
+			base = pci_resource_start(pf->pdev, PCI_MBOX_BAR_NUM) +
+						  MBOX_SIZE;
+		else
+			base = readq(pf->reg_base + RVU_PF_VF_BAR4_ADDR);
 
-	hwbase = ioremap_wc(base, MBOX_SIZE * pf->total_vfs);
-	if (!hwbase) {
-		err = -ENOMEM;
-		goto free_wq;
+		hwbase = ioremap_wc(base, MBOX_SIZE * pf->total_vfs);
+		if (!hwbase) {
+			err = -ENOMEM;
+			goto free_wq;
+		}
 	}
 
 	mbox = &pf->mbox_pfvf[0];
@@ -625,7 +658,7 @@ static int otx2_pfvf_mbox_init(struct otx2_nic *pf, int numvfs)
 	return 0;
 
 free_iomem:
-	if (hwbase)
+	if (hwbase && !(is_cn20k(pf->pdev)))
 		iounmap(hwbase);
 free_wq:
 	destroy_workqueue(pf->mbox_pfvf_wq);
@@ -644,8 +677,10 @@ static void otx2_pfvf_mbox_destroy(struct otx2_nic *pf)
 		pf->mbox_pfvf_wq = NULL;
 	}
 
-	if (mbox->mbox.hwbase)
+	if (mbox->mbox.hwbase && !is_cn20k(pf->pdev))
 		iounmap(mbox->mbox.hwbase);
+	else
+		qmem_free(&pf->pdev->dev, pf->pfvf_mbox_addr);
 
 	otx2_mbox_destroy(&mbox->mbox);
 }
@@ -669,6 +704,9 @@ static void otx2_disable_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs)
 {
 	int vector;
 
+	if (is_cn20k(pf->pdev))
+		return cn20k_disable_pfvf_mbox_intr(pf, numvfs);
+
 	/* Disable PF <=> VF mailbox IRQ */
 	otx2_write64(pf, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(0), ~0ull);
 	otx2_write64(pf, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(1), ~0ull);
@@ -690,11 +728,14 @@ static int otx2_register_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs)
 	char *irq_name;
 	int err;
 
+	if (is_cn20k(pf->pdev))
+		return cn20k_register_pfvf_mbox_intr(pf, numvfs);
+
 	/* Register MBOX0 interrupt handler */
 	irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFPF_MBOX0 * NAME_SIZE];
 	if (pf->pcifunc)
 		snprintf(irq_name, NAME_SIZE,
-			 "RVUPF%d_VF Mbox0", rvu_get_pf(pf->pcifunc));
+			 "RVUPF%d_VF Mbox0", rvu_get_pf(pf->pdev, pf->pcifunc));
 	else
 		snprintf(irq_name, NAME_SIZE, "RVUPF_VF Mbox0");
 	err = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFPF_MBOX0),
@@ -710,7 +751,8 @@ static int otx2_register_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs)
 		irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFPF_MBOX1 * NAME_SIZE];
 		if (pf->pcifunc)
 			snprintf(irq_name, NAME_SIZE,
-				 "RVUPF%d_VF Mbox1", rvu_get_pf(pf->pcifunc));
+				 "RVUPF%d_VF Mbox1",
+				 rvu_get_pf(pf->pdev, pf->pcifunc));
 		else
 			snprintf(irq_name, NAME_SIZE, "RVUPF_VF Mbox1");
 		err = request_irq(pci_irq_vector(pf->pdev,
@@ -818,6 +860,9 @@ static void otx2_pfaf_mbox_handler(struct work_struct *work)
 	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
 	pf = af_mbox->pfvf;
 
+	trace_otx2_msg_status(pf->pdev, "PF-AF down queue handler(response)",
+			      num_msgs);
+
 	for (id = 0; id < num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
 		otx2_process_pfaf_mbox_msg(pf, msg);
@@ -973,6 +1018,9 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work)
 
 	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
 
+	trace_otx2_msg_status(pf->pdev, "PF-AF up queue handler(notification)",
+			      num_msgs);
+
 	for (id = 0; id < num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
 
@@ -993,7 +1041,7 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work)
 	otx2_mbox_msg_send(mbox, 0);
 }
 
-static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq)
+irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq)
 {
 	struct otx2_nic *pf = (struct otx2_nic *)pf_irq;
 	struct mbox *mw = &pf->mbox;
@@ -1022,6 +1070,9 @@ static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq)
 
 		trace_otx2_msg_interrupt(pf->pdev, "UP message from AF to PF",
 					 BIT_ULL(0));
+
+		trace_otx2_msg_status(pf->pdev, "PF-AF up work queued(interrupt)",
+				      hdr->num_msgs);
 	}
 
 	if (mbox_data & MBOX_DOWN_MSG) {
@@ -1038,6 +1089,9 @@ static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq)
 
 		trace_otx2_msg_interrupt(pf->pdev, "DOWN reply from AF to PF",
 					 BIT_ULL(0));
+
+		trace_otx2_msg_status(pf->pdev, "PF-AF down work queued(interrupt)",
+				      hdr->num_msgs);
 	}
 
 	return IRQ_HANDLED;
@@ -1045,10 +1099,18 @@ static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq)
 
 void otx2_disable_mbox_intr(struct otx2_nic *pf)
 {
-	int vector = pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_AFPF_MBOX);
+	int vector;
 
 	/* Disable AF => PF mailbox IRQ */
-	otx2_write64(pf, RVU_PF_INT_ENA_W1C, BIT_ULL(0));
+	if (!is_cn20k(pf->pdev)) {
+		vector = pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_AFPF_MBOX);
+		otx2_write64(pf, RVU_PF_INT_ENA_W1C, BIT_ULL(0));
+	} else {
+		vector = pci_irq_vector(pf->pdev,
+					RVU_MBOX_PF_INT_VEC_AFPF_MBOX);
+		otx2_write64(pf, RVU_PF_INT_ENA_W1C,
+			     BIT_ULL(0) | BIT_ULL(1));
+	}
 	free_irq(vector, pf);
 }
 EXPORT_SYMBOL(otx2_disable_mbox_intr);
@@ -1061,10 +1123,24 @@ int otx2_register_mbox_intr(struct otx2_nic *pf, bool probe_af)
 	int err;
 
 	/* Register mailbox interrupt handler */
-	irq_name = &hw->irq_name[RVU_PF_INT_VEC_AFPF_MBOX * NAME_SIZE];
-	snprintf(irq_name, NAME_SIZE, "RVUPFAF Mbox");
-	err = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_AFPF_MBOX),
-			  otx2_pfaf_mbox_intr_handler, 0, irq_name, pf);
+	if (!is_cn20k(pf->pdev)) {
+		irq_name = &hw->irq_name[RVU_PF_INT_VEC_AFPF_MBOX * NAME_SIZE];
+		snprintf(irq_name, NAME_SIZE, "RVUPF%d AFPF Mbox",
+			 rvu_get_pf(pf->pdev, pf->pcifunc));
+		err = request_irq(pci_irq_vector
+				  (pf->pdev, RVU_PF_INT_VEC_AFPF_MBOX),
+				  pf->hw_ops->pfaf_mbox_intr_handler,
+				  0, irq_name, pf);
+	} else {
+		irq_name = &hw->irq_name[RVU_MBOX_PF_INT_VEC_AFPF_MBOX *
+						NAME_SIZE];
+		snprintf(irq_name, NAME_SIZE, "RVUPF%d AFPF Mbox",
+			 rvu_get_pf(pf->pdev, pf->pcifunc));
+		err = request_irq(pci_irq_vector
+				  (pf->pdev, RVU_MBOX_PF_INT_VEC_AFPF_MBOX),
+				  pf->hw_ops->pfaf_mbox_intr_handler,
+				  0, irq_name, pf);
+	}
 	if (err) {
 		dev_err(pf->dev,
 			"RVUPF: IRQ registration failed for PFAF mbox irq\n");
@@ -1074,8 +1150,14 @@ int otx2_register_mbox_intr(struct otx2_nic *pf, bool probe_af)
 	/* Enable mailbox interrupt for msgs coming from AF.
 	 * First clear to avoid spurious interrupts, if any.
 	 */
-	otx2_write64(pf, RVU_PF_INT, BIT_ULL(0));
-	otx2_write64(pf, RVU_PF_INT_ENA_W1S, BIT_ULL(0));
+	if (!is_cn20k(pf->pdev)) {
+		otx2_write64(pf, RVU_PF_INT, BIT_ULL(0));
+		otx2_write64(pf, RVU_PF_INT_ENA_W1S, BIT_ULL(0));
+	} else {
+		otx2_write64(pf, RVU_PF_INT, BIT_ULL(0) | BIT_ULL(1));
+		otx2_write64(pf, RVU_PF_INT_ENA_W1S, BIT_ULL(0) |
+			     BIT_ULL(1));
+	}
 
 	if (!probe_af)
 		return 0;
@@ -1106,7 +1188,7 @@ void otx2_pfaf_mbox_destroy(struct otx2_nic *pf)
 		pf->mbox_wq = NULL;
 	}
 
-	if (mbox->mbox.hwbase)
+	if (mbox->mbox.hwbase && !is_cn20k(pf->pdev))
 		iounmap((void __iomem *)mbox->mbox.hwbase);
 
 	otx2_mbox_destroy(&mbox->mbox);
@@ -1126,12 +1208,20 @@ int otx2_pfaf_mbox_init(struct otx2_nic *pf)
 	if (!pf->mbox_wq)
 		return -ENOMEM;
 
-	/* Mailbox is a reserved memory (in RAM) region shared between
-	 * admin function (i.e AF) and this PF, shouldn't be mapped as
-	 * device memory to allow unaligned accesses.
+	/* For CN20K, AF allocates mbox memory in DRAM and writes PF
+	 * regions/offsets in RVU_MBOX_AF_PFX_ADDR, the RVU_PFX_FUNC_PFAF_MBOX
+	 * gives the aliased address to access AF/PF mailbox regions.
 	 */
-	hwbase = ioremap_wc(pci_resource_start(pf->pdev, PCI_MBOX_BAR_NUM),
-			    MBOX_SIZE);
+	if (is_cn20k(pf->pdev))
+		hwbase = pf->reg_base + RVU_PFX_FUNC_PFAF_MBOX +
+			((u64)BLKADDR_MBOX << RVU_FUNC_BLKADDR_SHIFT);
+	else
+		/* Mailbox is a reserved memory (in RAM) region shared between
+		 * admin function (i.e AF) and this PF, shouldn't be mapped as
+		 * device memory to allow unaligned accesses.
+		 */
+		hwbase = ioremap_wc(pci_resource_start
+				    (pf->pdev, PCI_MBOX_BAR_NUM), MBOX_SIZE);
 	if (!hwbase) {
 		dev_err(pf->dev, "Unable to map PFAF mailbox region\n");
 		err = -ENOMEM;
@@ -1304,8 +1394,8 @@ static irqreturn_t otx2_q_intr_handler(int irq, void *data)
 {
 	struct otx2_nic *pf = data;
 	struct otx2_snd_queue *sq;
-	u64 val, *ptr;
-	u64 qidx = 0;
+	void __iomem *ptr;
+	u64 val, qidx = 0;
 
 	/* CQ */
 	for (qidx = 0; qidx < pf->qset.cq_cnt; qidx++) {
@@ -1662,9 +1752,7 @@ void otx2_free_hw_resources(struct otx2_nic *pf)
 	struct nix_lf_free_req *free_req;
 	struct mbox *mbox = &pf->mbox;
 	struct otx2_cq_queue *cq;
-	struct otx2_pool *pool;
 	struct msg_req *req;
-	int pool_id;
 	int qidx;
 
 	/* Ensure all SQE are processed */
@@ -1705,13 +1793,6 @@ void otx2_free_hw_resources(struct otx2_nic *pf)
 	/* Free RQ buffer pointers*/
 	otx2_free_aura_ptr(pf, AURA_NIX_RQ);
 
-	for (qidx = 0; qidx < pf->hw.rx_queues; qidx++) {
-		pool_id = otx2_get_pool_idx(pf, AURA_NIX_RQ, qidx);
-		pool = &pf->qset.pool[pool_id];
-		page_pool_destroy(pool->page_pool);
-		pool->page_pool = NULL;
-	}
-
 	otx2_free_cq_res(pf);
 
 	/* Free all ingress bandwidth profiles allocated */
@@ -1962,7 +2043,7 @@ int otx2_open(struct net_device *netdev)
 	if (err) {
 		dev_err(pf->dev,
 			"RVUPF%d: IRQ registration failed for QERR\n",
-			rvu_get_pf(pf->pcifunc));
+			rvu_get_pf(pf->pdev, pf->pcifunc));
 		goto err_disable_napi;
 	}
 
@@ -1980,7 +2061,7 @@ int otx2_open(struct net_device *netdev)
 		if (name_len >= NAME_SIZE) {
 			dev_err(pf->dev,
 				"RVUPF%d: IRQ registration failed for CQ%d, irq name is too long\n",
-				rvu_get_pf(pf->pcifunc), qidx);
+				rvu_get_pf(pf->pdev, pf->pcifunc), qidx);
 			err = -EINVAL;
 			goto err_free_cints;
 		}
@@ -1991,7 +2072,7 @@ int otx2_open(struct net_device *netdev)
 		if (err) {
 			dev_err(pf->dev,
 				"RVUPF%d: IRQ registration failed for CQ%d\n",
-				rvu_get_pf(pf->pcifunc), qidx);
+				rvu_get_pf(pf->pdev, pf->pcifunc), qidx);
 			goto err_free_cints;
 		}
 		vec++;
@@ -2077,7 +2158,6 @@ int otx2_stop(struct net_device *netdev)
 	struct otx2_nic *pf = netdev_priv(netdev);
 	struct otx2_cq_poll *cq_poll = NULL;
 	struct otx2_qset *qset = &pf->qset;
-	struct otx2_rss_info *rss;
 	int qidx, vec, wrk;
 
 	/* If the DOWN flag is set resources are already freed */
@@ -2095,10 +2175,7 @@ int otx2_stop(struct net_device *netdev)
 	otx2_rxtx_enable(pf, false);
 
 	/* Clear RSS enable flag */
-	rss = &pf->hw.rss_info;
-	rss->enable = false;
-	if (!netif_is_rxfh_configured(netdev))
-		kfree(rss->rss_ctx[DEFAULT_RSS_CONTEXT_GROUP]);
+	pf->hw.rss_info.enable = false;
 
 	/* Cleanup Queue IRQ */
 	vec = pci_irq_vector(pf->pdev,
@@ -2143,6 +2220,7 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct otx2_nic *pf = netdev_priv(netdev);
 	int qidx = skb_get_queue_mapping(skb);
+	struct otx2_dev_stats *dev_stats;
 	struct otx2_snd_queue *sq;
 	struct netdev_queue *txq;
 	int sq_idx;
@@ -2155,6 +2233,8 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev)
 	/* Check for minimum and maximum packet length */
 	if (skb->len <= ETH_HLEN ||
 	    (!skb_shinfo(skb)->gso_size && skb->len > pf->tx_max_pktlen)) {
+		dev_stats = &pf->hw.dev_stats;
+		atomic_long_inc(&dev_stats->tx_discards);
 		dev_kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}
@@ -2365,18 +2445,26 @@ static int otx2_config_hw_tx_tstamp(struct otx2_nic *pfvf, bool enable)
 	return 0;
 }
 
-int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr)
+int otx2_config_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config)
+{
+	struct otx2_nic *pfvf = netdev_priv(netdev);
+
+	*config = pfvf->tstamp;
+	return 0;
+}
+EXPORT_SYMBOL(otx2_config_hwtstamp_get);
+
+int otx2_config_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
-	struct hwtstamp_config config;
 
 	if (!pfvf->ptp)
 		return -ENODEV;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		if (pfvf->flags & OTX2_FLAG_PTP_ONESTEP_SYNC)
 			pfvf->flags &= ~OTX2_FLAG_PTP_ONESTEP_SYNC;
@@ -2385,8 +2473,11 @@ int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr)
 		otx2_config_hw_tx_tstamp(pfvf, false);
 		break;
 	case HWTSTAMP_TX_ONESTEP_SYNC:
-		if (!test_bit(CN10K_PTP_ONESTEP, &pfvf->hw.cap_flag))
+		if (!test_bit(CN10K_PTP_ONESTEP, &pfvf->hw.cap_flag)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "One-step time stamping is not supported");
 			return -ERANGE;
+		}
 		pfvf->flags |= OTX2_FLAG_PTP_ONESTEP_SYNC;
 		schedule_delayed_work(&pfvf->ptp->synctstamp_work,
 				      msecs_to_jiffies(500));
@@ -2398,7 +2489,7 @@ int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		otx2_config_hw_rx_tstamp(pfvf, false);
 		break;
@@ -2417,35 +2508,17 @@ int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 		otx2_config_hw_rx_tstamp(pfvf, true);
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	memcpy(&pfvf->tstamp, &config, sizeof(config));
-
-	return copy_to_user(ifr->ifr_data, &config,
-			    sizeof(config)) ? -EFAULT : 0;
-}
-EXPORT_SYMBOL(otx2_config_hwtstamp);
+	pfvf->tstamp = *config;
 
-int otx2_ioctl(struct net_device *netdev, struct ifreq *req, int cmd)
-{
-	struct otx2_nic *pfvf = netdev_priv(netdev);
-	struct hwtstamp_config *cfg = &pfvf->tstamp;
-
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return otx2_config_hwtstamp(netdev, req);
-	case SIOCGHWTSTAMP:
-		return copy_to_user(req->ifr_data, cfg,
-				    sizeof(*cfg)) ? -EFAULT : 0;
-	default:
-		return -EOPNOTSUPP;
-	}
+	return 0;
 }
-EXPORT_SYMBOL(otx2_ioctl);
+EXPORT_SYMBOL(otx2_config_hwtstamp_set);
 
 static int otx2_do_set_vf_mac(struct otx2_nic *pf, int vf, const u8 *mac)
 {
@@ -2691,7 +2764,6 @@ static int otx2_get_vf_config(struct net_device *netdev, int vf,
 static int otx2_xdp_xmit_tx(struct otx2_nic *pf, struct xdp_frame *xdpf,
 			    int qidx)
 {
-	struct page *page;
 	u64 dma_addr;
 	int err = 0;
 
@@ -2701,11 +2773,11 @@ static int otx2_xdp_xmit_tx(struct otx2_nic *pf, struct xdp_frame *xdpf,
 	if (dma_mapping_error(pf->dev, dma_addr))
 		return -ENOMEM;
 
-	err = otx2_xdp_sq_append_pkt(pf, dma_addr, xdpf->len, qidx);
+	err = otx2_xdp_sq_append_pkt(pf, xdpf, dma_addr, xdpf->len,
+				     qidx, OTX2_XDP_REDIRECT);
 	if (!err) {
 		otx2_dma_unmap_page(pf, dma_addr, xdpf->len, DMA_TO_DEVICE);
-		page = virt_to_page(xdpf->data);
-		put_page(page);
+		xdp_return_frame(xdpf);
 		return -ENOMEM;
 	}
 	return 0;
@@ -2789,6 +2861,8 @@ static int otx2_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return otx2_xdp_setup(pf, xdp->prog);
+	case XDP_SETUP_XSK_POOL:
+		return otx2_xsk_pool_setup(pf, xdp->xsk.pool, xdp->xsk.queue_id);
 	default:
 		return -EINVAL;
 	}
@@ -2861,14 +2935,16 @@ static const struct net_device_ops otx2_netdev_ops = {
 	.ndo_set_features	= otx2_set_features,
 	.ndo_tx_timeout		= otx2_tx_timeout,
 	.ndo_get_stats64	= otx2_get_stats64,
-	.ndo_eth_ioctl		= otx2_ioctl,
 	.ndo_set_vf_mac		= otx2_set_vf_mac,
 	.ndo_set_vf_vlan	= otx2_set_vf_vlan,
 	.ndo_get_vf_config	= otx2_get_vf_config,
 	.ndo_bpf		= otx2_xdp,
+	.ndo_xsk_wakeup		= otx2_xsk_wakeup,
 	.ndo_xdp_xmit           = otx2_xdp_xmit,
 	.ndo_setup_tc		= otx2_setup_tc,
 	.ndo_set_vf_trust	= otx2_ndo_set_vf_trust,
+	.ndo_hwtstamp_get	= otx2_config_hwtstamp_get,
+	.ndo_hwtstamp_set	= otx2_config_hwtstamp_set,
 };
 
 int otx2_wq_init(struct otx2_nic *pf)
@@ -2986,8 +3062,13 @@ int otx2_init_rsrc(struct pci_dev *pdev, struct otx2_nic *pf)
 	if (err)
 		return err;
 
-	err = pci_alloc_irq_vectors(hw->pdev, RVU_PF_INT_VEC_CNT,
-				    RVU_PF_INT_VEC_CNT, PCI_IRQ_MSIX);
+	if (!is_cn20k(pf->pdev))
+		err = pci_alloc_irq_vectors(hw->pdev, RVU_PF_INT_VEC_CNT,
+					    RVU_PF_INT_VEC_CNT, PCI_IRQ_MSIX);
+	else
+		err = pci_alloc_irq_vectors(hw->pdev, RVU_MBOX_PF_INT_VEC_CNT,
+					    RVU_MBOX_PF_INT_VEC_CNT,
+					    PCI_IRQ_MSIX);
 	if (err < 0) {
 		dev_err(dev, "%s: Failed to alloc %d IRQ vectors\n",
 			__func__, num_vec);
@@ -2996,6 +3077,11 @@ int otx2_init_rsrc(struct pci_dev *pdev, struct otx2_nic *pf)
 
 	otx2_setup_dev_hw_settings(pf);
 
+	if (is_cn20k(pf->pdev))
+		cn20k_init(pf);
+	else
+		otx2_init_hw_ops(pf);
+
 	/* Init PF <=> AF mailbox stuff */
 	err = otx2_pfaf_mbox_init(pf);
 	if (err)
@@ -3054,7 +3140,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return err;
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
+	err = pcim_request_all_regions(pdev, DRV_NAME);
 	if (err) {
 		dev_err(dev, "PCI request regions failed 0x%x\n", err);
 		return err;
@@ -3063,7 +3149,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
 	if (err) {
 		dev_err(dev, "DMA mask config failed, abort\n");
-		goto err_release_regions;
+		return err;
 	}
 
 	pci_set_master(pdev);
@@ -3073,10 +3159,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	qos_txqs = min_t(int, qcount, OTX2_QOS_MAX_LEAF_NODES);
 
 	netdev = alloc_etherdev_mqs(sizeof(*pf), qcount + qos_txqs, qcount);
-	if (!netdev) {
-		err = -ENOMEM;
-		goto err_release_regions;
-	}
+	if (!netdev)
+		return -ENOMEM;
 
 	pci_set_drvdata(pdev, netdev);
 	SET_NETDEV_DEV(netdev, &pdev->dev);
@@ -3134,6 +3218,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_ptp_destroy;
 
+	otx2_set_hw_capabilities(pf);
+
 	err = cn10k_mcs_init(pf);
 	if (err)
 		goto err_del_mcam_entries;
@@ -3204,16 +3290,28 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* Enable link notifications */
 	otx2_cgx_config_linkevents(pf, true);
 
+	pf->af_xdp_zc_qidx = bitmap_zalloc(qcount, GFP_KERNEL);
+	if (!pf->af_xdp_zc_qidx) {
+		err = -ENOMEM;
+		goto err_sriov_cleannup;
+	}
+
 #ifdef CONFIG_DCB
 	err = otx2_dcbnl_set_ops(netdev);
 	if (err)
-		goto err_pf_sriov_init;
+		goto err_free_zc_bmap;
 #endif
 
 	otx2_qos_init(pf, qos_txqs);
 
 	return 0;
 
+#ifdef CONFIG_DCB
+err_free_zc_bmap:
+	bitmap_free(pf->af_xdp_zc_qidx);
+#endif
+err_sriov_cleannup:
+	otx2_sriov_vfcfg_cleanup(pf);
 err_pf_sriov_init:
 	otx2_shutdown_tc(pf);
 err_mcam_flow_del:
@@ -3240,8 +3338,6 @@ err_detach_rsrc:
 err_free_netdev:
 	pci_set_drvdata(pdev, NULL);
 	free_netdev(netdev);
-err_release_regions:
-	pci_release_regions(pdev);
 	return err;
 }
 
@@ -3283,6 +3379,7 @@ static void otx2_vf_link_event_task(struct work_struct *work)
 	req = (struct cgx_link_info_msg *)msghdr;
 	req->hdr.id = MBOX_MSG_CGX_LINK_EVENT;
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	req->hdr.pcifunc = pf->pcifunc;
 	memcpy(&req->link_info, &pf->linfo, sizeof(req->link_info));
 
 	otx2_mbox_wait_for_zero(&pf->mbox_pfvf[0].mbox_up, vf_idx);
@@ -3439,10 +3536,9 @@ static void otx2_remove(struct pci_dev *pdev)
 	otx2_disable_mbox_intr(pf);
 	otx2_pfaf_mbox_destroy(pf);
 	pci_free_irq_vectors(pf->pdev);
+	bitmap_free(pf->af_xdp_zc_qidx);
 	pci_set_drvdata(pdev, NULL);
 	free_netdev(netdev);
-
-	pci_release_regions(pdev);
 }
 
 static struct pci_driver otx2_pf_driver = {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
index 63130ba37e9d..dedd586ed310 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
@@ -193,7 +193,7 @@ static int ptp_pps_on(struct otx2_ptp *ptp, int on, u64 period)
 	return otx2_sync_mbox_msg(&ptp->nic->mbox);
 }
 
-static u64 ptp_cc_read(const struct cyclecounter *cc)
+static u64 ptp_cc_read(struct cyclecounter *cc)
 {
 	struct otx2_ptp *ptp = container_of(cc, struct otx2_ptp, cycle_counter);
 
@@ -491,7 +491,7 @@ void otx2_ptp_destroy(struct otx2_nic *pfvf)
 	if (!ptp)
 		return;
 
-	cancel_delayed_work(&pfvf->ptp->synctstamp_work);
+	cancel_delayed_work_sync(&pfvf->ptp->synctstamp_work);
 
 	ptp_clock_unregister(ptp->ptp_clock);
 	kfree(ptp);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h
index e3aee6e36215..1cd576fd09c5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h
@@ -44,6 +44,17 @@
 #define RVU_PF_VF_MBOX_ADDR                 (0xC40)
 #define RVU_PF_LMTLINE_ADDR                 (0xC48)
 
+#define RVU_MBOX_PF_VFX_PFVF_TRIGX(a)		(0x2000 | (a) << 3)
+#define RVU_MBOX_PF_VFPF_INTX(a)		(0x1000 | (a) << 3)
+#define RVU_MBOX_PF_VFPF_INT_W1SX(a)		(0x1020 | (a) << 3)
+#define RVU_MBOX_PF_VFPF_INT_ENA_W1SX(a)	(0x1040 | (a) << 3)
+#define RVU_MBOX_PF_VFPF_INT_ENA_W1CX(a)	(0x1060 | (a) << 3)
+
+#define RVU_MBOX_PF_VFPF1_INTX(a)		(0x1080 | (a) << 3)
+#define RVU_MBOX_PF_VFPF1_INT_W1SX(a)		(0x10a0 | (a) << 3)
+#define RVU_MBOX_PF_VFPF1_INT_ENA_W1SX(a)	(0x10c0 | (a) << 3)
+#define RVU_MBOX_PF_VFPF1_INT_ENA_W1CX(a)	(0x10e0 | (a) << 3)
+
 /* RVU VF registers */
 #define	RVU_VF_VFPF_MBOX0		    (0x00000)
 #define	RVU_VF_VFPF_MBOX1		    (0x00008)
@@ -58,6 +69,11 @@
 #define	RVU_VF_MSIX_PBAX(a)		    (0xF0000 | (a) << 3)
 #define RVU_VF_MBOX_REGION                  (0xC0000)
 
+/* CN20K RVU_MBOX_E: RVU PF/VF MBOX Address Range Enumeration */
+#define RVU_MBOX_AF_PFX_ADDR(a)             (0x5000 | (a) << 4)
+#define RVU_PFX_FUNC_PFAF_MBOX		    (0x80000)
+#define RVU_PFX_FUNCX_VFAF_MBOX		    (0x40000)
+
 #define RVU_FUNC_BLKADDR_SHIFT		20
 #define RVU_FUNC_BLKADDR_MASK		0x1FULL
 
@@ -138,39 +154,12 @@
 #define	NIX_LF_CINTX_ENA_W1S(a)		(NIX_LFBASE | 0xD40 | (a) << 12)
 #define	NIX_LF_CINTX_ENA_W1C(a)		(NIX_LFBASE | 0xD50 | (a) << 12)
 
-/* NIX AF transmit scheduler registers */
-#define NIX_AF_SMQX_CFG(a)		(0x700 | (u64)(a) << 16)
-#define NIX_AF_TL4X_SDP_LINK_CFG(a)	(0xB10 | (u64)(a) << 16)
-#define NIX_AF_TL1X_SCHEDULE(a)		(0xC00 | (u64)(a) << 16)
-#define NIX_AF_TL1X_CIR(a)		(0xC20 | (u64)(a) << 16)
-#define NIX_AF_TL1X_TOPOLOGY(a)		(0xC80 | (u64)(a) << 16)
-#define NIX_AF_TL2X_PARENT(a)		(0xE88 | (u64)(a) << 16)
-#define NIX_AF_TL2X_SCHEDULE(a)		(0xE00 | (u64)(a) << 16)
-#define NIX_AF_TL2X_TOPOLOGY(a)		(0xE80 | (u64)(a) << 16)
-#define NIX_AF_TL2X_CIR(a)		(0xE20 | (u64)(a) << 16)
-#define NIX_AF_TL2X_PIR(a)		(0xE30 | (u64)(a) << 16)
-#define NIX_AF_TL3X_PARENT(a)		(0x1088 | (u64)(a) << 16)
-#define NIX_AF_TL3X_SCHEDULE(a)		(0x1000 | (u64)(a) << 16)
-#define NIX_AF_TL3X_SHAPE(a)		(0x1010 | (u64)(a) << 16)
-#define NIX_AF_TL3X_CIR(a)		(0x1020 | (u64)(a) << 16)
-#define NIX_AF_TL3X_PIR(a)		(0x1030 | (u64)(a) << 16)
-#define NIX_AF_TL3X_TOPOLOGY(a)		(0x1080 | (u64)(a) << 16)
-#define NIX_AF_TL4X_PARENT(a)		(0x1288 | (u64)(a) << 16)
-#define NIX_AF_TL4X_SCHEDULE(a)		(0x1200 | (u64)(a) << 16)
-#define NIX_AF_TL4X_SHAPE(a)		(0x1210 | (u64)(a) << 16)
-#define NIX_AF_TL4X_CIR(a)		(0x1220 | (u64)(a) << 16)
-#define NIX_AF_TL4X_PIR(a)		(0x1230 | (u64)(a) << 16)
-#define NIX_AF_TL4X_TOPOLOGY(a)		(0x1280 | (u64)(a) << 16)
-#define NIX_AF_MDQX_SCHEDULE(a)		(0x1400 | (u64)(a) << 16)
-#define NIX_AF_MDQX_SHAPE(a)		(0x1410 | (u64)(a) << 16)
-#define NIX_AF_MDQX_CIR(a)		(0x1420 | (u64)(a) << 16)
-#define NIX_AF_MDQX_PIR(a)		(0x1430 | (u64)(a) << 16)
-#define NIX_AF_MDQX_PARENT(a)		(0x1480 | (u64)(a) << 16)
-#define NIX_AF_TL3_TL2X_LINKX_CFG(a, b)	(0x1700 | (u64)(a) << 16 | (b) << 3)
-
 /* LMT LF registers */
 #define LMT_LFBASE			BIT_ULL(RVU_FUNC_BLKADDR_SHIFT)
 #define LMT_LF_LMTLINEX(a)		(LMT_LFBASE | 0x000 | (a) << 12)
 #define LMT_LF_LMTCANCEL		(LMT_LFBASE | 0x400)
 
+/* CN20K registers */
+#define RVU_PF_DISC			(0x0)
+
 #endif /* OTX2_REG_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 9a226ca74425..26a08d2cfbb1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -467,7 +467,8 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic,
 			target = act->dev;
 			if (target->dev.parent) {
 				priv = netdev_priv(target);
-				if (rvu_get_pf(nic->pcifunc) != rvu_get_pf(priv->pcifunc)) {
+				if (rvu_get_pf(nic->pdev, nic->pcifunc) !=
+					rvu_get_pf(nic->pdev, priv->pcifunc)) {
 					NL_SET_ERR_MSG_MOD(extack,
 							   "can't redirect to other pf/vf");
 					return -EOPNOTSUPP;
@@ -1325,7 +1326,6 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 
 free_leaf:
 	otx2_tc_del_from_flow_list(flow_cfg, new_node);
-	kfree_rcu(new_node, rcu);
 	if (new_node->is_act_police) {
 		mutex_lock(&nic->mbox.lock);
 
@@ -1345,6 +1345,7 @@ free_leaf:
 
 		mutex_unlock(&nic->mbox.lock);
 	}
+	kfree_rcu(new_node, rcu);
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 224cef938927..625bb5a05344 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -12,6 +12,7 @@
 #include <linux/bpf_trace.h>
 #include <net/ip6_checksum.h>
 #include <net/xfrm.h>
+#include <net/xdp.h>
 
 #include "otx2_reg.h"
 #include "otx2_common.h"
@@ -19,6 +20,7 @@
 #include "otx2_txrx.h"
 #include "otx2_ptp.h"
 #include "cn10k.h"
+#include "otx2_xsk.h"
 
 #define CQE_ADDR(CQ, idx) ((CQ)->cqe_base + ((CQ)->cqe_size * (idx)))
 #define PTP_PORT	        0x13F
@@ -29,11 +31,17 @@
 
 DEFINE_STATIC_KEY_FALSE(cn10k_ipsec_sa_enabled);
 
+static int otx2_get_free_sqe(struct otx2_snd_queue *sq)
+{
+	return (sq->cons_head - sq->head - 1 + sq->sqe_cnt)
+		& (sq->sqe_cnt - 1);
+}
+
 static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct bpf_prog *prog,
 				     struct nix_cqe_rx_s *cqe,
 				     struct otx2_cq_queue *cq,
-				     bool *need_xdp_flush);
+				     u32 *metasize, bool *need_xdp_flush);
 
 static void otx2_sq_set_sqe_base(struct otx2_snd_queue *sq,
 				 struct sk_buff *skb)
@@ -96,20 +104,22 @@ static unsigned int frag_num(unsigned int i)
 
 static void otx2_xdp_snd_pkt_handler(struct otx2_nic *pfvf,
 				     struct otx2_snd_queue *sq,
-				 struct nix_cqe_tx_s *cqe)
+				     struct nix_cqe_tx_s *cqe,
+				     int *xsk_frames)
 {
 	struct nix_send_comp_s *snd_comp = &cqe->comp;
 	struct sg_list *sg;
-	struct page *page;
-	u64 pa;
 
 	sg = &sq->sg[snd_comp->sqe_id];
+	if (sg->flags & OTX2_AF_XDP_FRAME) {
+		(*xsk_frames)++;
+		return;
+	}
 
-	pa = otx2_iova_to_phys(pfvf->iommu_domain, sg->dma_addr[0]);
-	otx2_dma_unmap_page(pfvf, sg->dma_addr[0],
-			    sg->size[0], DMA_TO_DEVICE);
-	page = virt_to_page(phys_to_virt(pa));
-	put_page(page);
+	if (sg->flags & OTX2_XDP_REDIRECT)
+		otx2_dma_unmap_page(pfvf, sg->dma_addr[0], sg->size[0], DMA_TO_DEVICE);
+	xdp_return_frame((struct xdp_frame *)sg->skb);
+	sg->skb = (u64)NULL;
 }
 
 static void otx2_snd_pkt_handler(struct otx2_nic *pfvf,
@@ -325,18 +335,24 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf,
 	struct nix_rx_parse_s *parse = &cqe->parse;
 	struct nix_rx_sg_s *sg = &cqe->sg;
 	struct sk_buff *skb = NULL;
+	u64 *word = (u64 *)parse;
 	void *end, *start;
+	u32 metasize = 0;
 	u64 *seg_addr;
 	u16 *seg_size;
 	int seg;
 
 	if (unlikely(parse->errlev || parse->errcode)) {
-		if (otx2_check_rcv_errors(pfvf, cqe, cq->cq_idx))
+		if (otx2_check_rcv_errors(pfvf, cqe, cq->cq_idx)) {
+			trace_otx2_parse_dump(pfvf->pdev, "Err:", word);
 			return;
+		}
 	}
+	trace_otx2_parse_dump(pfvf->pdev, "", word);
 
 	if (pfvf->xdp_prog)
-		if (otx2_xdp_rcv_pkt_handler(pfvf, pfvf->xdp_prog, cqe, cq, need_xdp_flush))
+		if (otx2_xdp_rcv_pkt_handler(pfvf, pfvf->xdp_prog, cqe, cq,
+					     &metasize, need_xdp_flush))
 			return;
 
 	skb = napi_get_frags(napi);
@@ -368,6 +384,8 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf,
 		skb->mark = parse->match_id;
 
 	skb_mark_for_recycle(skb);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 
 	napi_gro_frags(napi);
 }
@@ -431,6 +449,18 @@ int otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 	return cnt - cq->pool_ptrs;
 }
 
+static void otx2_zc_submit_pkts(struct otx2_nic *pfvf, struct xsk_buff_pool *xsk_pool,
+				int *xsk_frames, int qidx, int budget)
+{
+	if (*xsk_frames)
+		xsk_tx_completed(xsk_pool, *xsk_frames);
+
+	if (xsk_uses_need_wakeup(xsk_pool))
+		xsk_set_tx_need_wakeup(xsk_pool);
+
+	otx2_zc_napi_handler(pfvf, xsk_pool, qidx, budget);
+}
+
 static int otx2_tx_napi_handler(struct otx2_nic *pfvf,
 				struct otx2_cq_queue *cq, int budget)
 {
@@ -439,16 +469,22 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf,
 	struct nix_cqe_tx_s *cqe;
 	struct net_device *ndev;
 	int processed_cqe = 0;
+	int xsk_frames = 0;
+
+	qidx = cq->cq_idx - pfvf->hw.rx_queues;
+	sq = &pfvf->qset.sq[qidx];
 
 	if (cq->pend_cqe >= budget)
 		goto process_cqe;
 
-	if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe)
+	if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) {
+		if (sq->xsk_pool)
+			otx2_zc_submit_pkts(pfvf, sq->xsk_pool, &xsk_frames,
+					    qidx, budget);
 		return 0;
+	}
 
 process_cqe:
-	qidx = cq->cq_idx - pfvf->hw.rx_queues;
-	sq = &pfvf->qset.sq[qidx];
 
 	while (likely(processed_cqe < budget) && cq->pend_cqe) {
 		cqe = (struct nix_cqe_tx_s *)otx2_get_next_cqe(cq);
@@ -458,10 +494,8 @@ process_cqe:
 			break;
 		}
 
-		qidx = cq->cq_idx - pfvf->hw.rx_queues;
-
 		if (cq->cq_type == CQ_XDP)
-			otx2_xdp_snd_pkt_handler(pfvf, sq, cqe);
+			otx2_xdp_snd_pkt_handler(pfvf, sq, cqe, &xsk_frames);
 		else
 			otx2_snd_pkt_handler(pfvf, cq, &pfvf->qset.sq[qidx],
 					     cqe, budget, &tx_pkts, &tx_bytes);
@@ -502,6 +536,10 @@ process_cqe:
 		    netif_carrier_ok(ndev))
 			netif_tx_wake_queue(txq);
 	}
+
+	if (sq->xsk_pool)
+		otx2_zc_submit_pkts(pfvf, sq->xsk_pool, &xsk_frames, qidx, budget);
+
 	return 0;
 }
 
@@ -527,9 +565,10 @@ static void otx2_adjust_adaptive_coalese(struct otx2_nic *pfvf, struct otx2_cq_p
 int otx2_napi_handler(struct napi_struct *napi, int budget)
 {
 	struct otx2_cq_queue *rx_cq = NULL;
+	struct otx2_cq_queue *cq = NULL;
+	struct otx2_pool *pool = NULL;
 	struct otx2_cq_poll *cq_poll;
 	int workdone = 0, cq_idx, i;
-	struct otx2_cq_queue *cq;
 	struct otx2_qset *qset;
 	struct otx2_nic *pfvf;
 	int filled_cnt = -1;
@@ -554,6 +593,7 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 
 	if (rx_cq && rx_cq->pool_ptrs)
 		filled_cnt = pfvf->hw_ops->refill_pool_ptrs(pfvf, rx_cq);
+
 	/* Clear the IRQ */
 	otx2_write64(pfvf, NIX_LF_CINTX_INT(cq_poll->cint_idx), BIT_ULL(0));
 
@@ -566,20 +606,31 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 		if (pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED)
 			otx2_adjust_adaptive_coalese(pfvf, cq_poll);
 
+		if (likely(cq))
+			pool = &pfvf->qset.pool[cq->cq_idx];
+
 		if (unlikely(!filled_cnt)) {
 			struct refill_work *work;
 			struct delayed_work *dwork;
 
-			work = &pfvf->refill_wrk[cq->cq_idx];
-			dwork = &work->pool_refill_work;
-			/* Schedule a task if no other task is running */
-			if (!cq->refill_task_sched) {
-				work->napi = napi;
-				cq->refill_task_sched = true;
-				schedule_delayed_work(dwork,
-						      msecs_to_jiffies(100));
+			if (likely(cq)) {
+				work = &pfvf->refill_wrk[cq->cq_idx];
+				dwork = &work->pool_refill_work;
+				/* Schedule a task if no other task is running */
+				if (!cq->refill_task_sched) {
+					work->napi = napi;
+					cq->refill_task_sched = true;
+					schedule_delayed_work(dwork,
+							      msecs_to_jiffies(100));
+				}
+				/* Call wake-up for not able to fill buffers */
+				if (pool->xsk_pool)
+					xsk_set_rx_need_wakeup(pool->xsk_pool);
 			}
 		} else {
+			/* Clear wake-up, since buffers are filled successfully */
+			if (pool && pool->xsk_pool)
+				xsk_clear_rx_need_wakeup(pool->xsk_pool);
 			/* Re-enable interrupts */
 			otx2_write64(pfvf,
 				     NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx),
@@ -1147,7 +1198,7 @@ bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq,
 	/* Check if there is enough room between producer
 	 * and consumer index.
 	 */
-	free_desc = (sq->cons_head - sq->head - 1 + sq->sqe_cnt) & (sq->sqe_cnt - 1);
+	free_desc = otx2_get_free_sqe(sq);
 	if (free_desc < sq->sqe_thresh)
 		return false;
 
@@ -1230,15 +1281,19 @@ void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int q
 	u16 pool_id;
 	u64 iova;
 
-	if (pfvf->xdp_prog)
+	pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_RQ, qidx);
+	pool = &pfvf->qset.pool[pool_id];
+
+	if (pfvf->xdp_prog) {
+		if (pool->page_pool)
+			xdp_rxq_info_unreg_mem_model(&cq->xdp_rxq);
+
 		xdp_rxq_info_unreg(&cq->xdp_rxq);
+	}
 
 	if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe)
 		return;
 
-	pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_RQ, qidx);
-	pool = &pfvf->qset.pool[pool_id];
-
 	while (cq->pend_cqe) {
 		cqe = (struct nix_cqe_rx_s *)otx2_get_next_cqe(cq);
 		processed_cqe++;
@@ -1359,8 +1414,8 @@ void otx2_free_pending_sqe(struct otx2_nic *pfvf)
 	}
 }
 
-static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, u64 dma_addr,
-				int len, int *offset)
+void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, struct xdp_frame *xdpf,
+			 u64 dma_addr, int len, int *offset, u16 flags)
 {
 	struct nix_sqe_sg_s *sg = NULL;
 	u64 *iova = NULL;
@@ -1377,16 +1432,34 @@ static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, u64 dma_addr,
 	sq->sg[sq->head].dma_addr[0] = dma_addr;
 	sq->sg[sq->head].size[0] = len;
 	sq->sg[sq->head].num_segs = 1;
+	sq->sg[sq->head].flags = flags;
+	sq->sg[sq->head].skb = (u64)xdpf;
+}
+
+int otx2_read_free_sqe(struct otx2_nic *pfvf, u16 qidx)
+{
+	struct otx2_snd_queue *sq;
+	int free_sqe;
+
+	sq = &pfvf->qset.sq[qidx];
+	free_sqe = otx2_get_free_sqe(sq);
+	if (free_sqe < sq->sqe_thresh) {
+		netdev_warn(pfvf->netdev, "No free sqe for Send queue%d\n", qidx);
+		return 0;
+	}
+
+	return free_sqe - sq->sqe_thresh;
 }
 
-bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx)
+bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, struct xdp_frame *xdpf,
+			    u64 iova, int len, u16 qidx, u16 flags)
 {
 	struct nix_sqe_hdr_s *sqe_hdr;
 	struct otx2_snd_queue *sq;
 	int offset, free_sqe;
 
 	sq = &pfvf->qset.sq[qidx];
-	free_sqe = (sq->num_sqbs - *sq->aura_fc_addr) * sq->sqe_per_sqb;
+	free_sqe = otx2_get_free_sqe(sq);
 	if (free_sqe < sq->sqe_thresh)
 		return false;
 
@@ -1405,7 +1478,7 @@ bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx)
 
 	offset = sizeof(*sqe_hdr);
 
-	otx2_xdp_sqe_add_sg(sq, iova, len, &offset);
+	otx2_xdp_sqe_add_sg(sq, xdpf, iova, len, &offset, flags);
 	sqe_hdr->sizem1 = (offset / 16) - 1;
 	pfvf->hw_ops->sqe_flush(pfvf, sq, offset, qidx);
 
@@ -1416,16 +1489,30 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct bpf_prog *prog,
 				     struct nix_cqe_rx_s *cqe,
 				     struct otx2_cq_queue *cq,
-				     bool *need_xdp_flush)
+				     u32 *metasize, bool *need_xdp_flush)
 {
+	struct xdp_buff xdp, *xsk_buff = NULL;
 	unsigned char *hard_start;
+	struct otx2_pool *pool;
+	struct xdp_frame *xdpf;
 	int qidx = cq->cq_idx;
-	struct xdp_buff xdp;
 	struct page *page;
 	u64 iova, pa;
 	u32 act;
 	int err;
 
+	pool = &pfvf->qset.pool[qidx];
+
+	if (pool->xsk_pool) {
+		xsk_buff = pool->xdp[--cq->rbpool->xdp_top];
+		if (!xsk_buff)
+			return false;
+
+		xsk_buff->data_end = xsk_buff->data + cqe->sg.seg_size;
+		act = bpf_prog_run_xdp(prog, xsk_buff);
+		goto handle_xdp_verdict;
+	}
+
 	iova = cqe->sg.seg_addr - OTX2_HEAD_ROOM;
 	pa = otx2_iova_to_phys(pfvf->iommu_domain, iova);
 	page = virt_to_page(phys_to_virt(pa));
@@ -1434,41 +1521,63 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 
 	hard_start = (unsigned char *)phys_to_virt(pa);
 	xdp_prepare_buff(&xdp, hard_start, OTX2_HEAD_ROOM,
-			 cqe->sg.seg_size, false);
+			 cqe->sg.seg_size, true);
 
 	act = bpf_prog_run_xdp(prog, &xdp);
 
+handle_xdp_verdict:
 	switch (act) {
 	case XDP_PASS:
+		*metasize = xdp.data - xdp.data_meta;
 		break;
 	case XDP_TX:
 		qidx += pfvf->hw.tx_queues;
 		cq->pool_ptrs++;
-		return otx2_xdp_sq_append_pkt(pfvf, iova,
-					      cqe->sg.seg_size, qidx);
+		xdpf = xdp_convert_buff_to_frame(&xdp);
+		return otx2_xdp_sq_append_pkt(pfvf, xdpf,
+					      cqe->sg.seg_addr,
+					      cqe->sg.seg_size,
+					      qidx, OTX2_XDP_TX);
 	case XDP_REDIRECT:
 		cq->pool_ptrs++;
-		err = xdp_do_redirect(pfvf->netdev, &xdp, prog);
+		if (xsk_buff) {
+			err = xdp_do_redirect(pfvf->netdev, xsk_buff, prog);
+			if (!err) {
+				*need_xdp_flush = true;
+				return true;
+			}
+			return false;
+		}
 
-		otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
-				    DMA_FROM_DEVICE);
+		err = xdp_do_redirect(pfvf->netdev, &xdp, prog);
 		if (!err) {
 			*need_xdp_flush = true;
 			return true;
 		}
-		put_page(page);
+
+		otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
+				    DMA_FROM_DEVICE);
+		xdpf = xdp_convert_buff_to_frame(&xdp);
+		xdp_return_frame(xdpf);
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(pfvf->netdev, prog, act);
-		break;
+		fallthrough;
 	case XDP_ABORTED:
-		trace_xdp_exception(pfvf->netdev, prog, act);
-		break;
+		if (act == XDP_ABORTED)
+			trace_xdp_exception(pfvf->netdev, prog, act);
+		fallthrough;
 	case XDP_DROP:
-		otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
-				    DMA_FROM_DEVICE);
-		put_page(page);
 		cq->pool_ptrs++;
+		if (xsk_buff) {
+			xsk_buff_free(xsk_buff);
+		} else if (pp_page_to_nmdesc(page)->pp) {
+			page_pool_recycle_direct(pool->page_pool, page);
+		} else {
+			otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
+					    DMA_FROM_DEVICE);
+			put_page(page);
+		}
 		return true;
 	}
 	return false;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
index d23810963fdb..acf259d72008 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
@@ -12,6 +12,7 @@
 #include <linux/iommu.h>
 #include <linux/if_vlan.h>
 #include <net/xdp.h>
+#include <net/xdp_sock_drv.h>
 
 #define LBK_CHAN_BASE	0x000
 #define SDP_CHAN_BASE	0x700
@@ -76,6 +77,7 @@ struct otx2_rcv_queue {
 
 struct sg_list {
 	u16	num_segs;
+	u16	flags;
 	u64	skb;
 	u64	size[OTX2_MAX_FRAGS_IN_SQE];
 	u64	dma_addr[OTX2_MAX_FRAGS_IN_SQE];
@@ -104,6 +106,8 @@ struct otx2_snd_queue {
 	/* SQE ring and CPT response queue for Inline IPSEC */
 	struct qmem		*sqe_ring;
 	struct qmem		*cpt_resp;
+	/* Buffer pool for af_xdp zero-copy */
+	struct xsk_buff_pool    *xsk_pool;
 } ____cacheline_aligned_in_smp;
 
 enum cq_type {
@@ -127,7 +131,11 @@ struct otx2_pool {
 	struct qmem		*stack;
 	struct qmem		*fc_addr;
 	struct page_pool	*page_pool;
+	struct xsk_buff_pool	*xsk_pool;
+	struct xdp_buff		**xdp;
+	u16			xdp_cnt;
 	u16			rbsize;
+	u16			xdp_top;
 };
 
 struct otx2_cq_queue {
@@ -144,6 +152,7 @@ struct otx2_cq_queue {
 	void			*cqe_base;
 	struct qmem		*cqe;
 	struct otx2_pool	*rbpool;
+	bool			xsk_zc_en;
 	struct xdp_rxq_info xdp_rxq;
 } ____cacheline_aligned_in_smp;
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index e926c6ce96cf..f4fdbfba8667 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -136,7 +136,7 @@ static int otx2vf_process_mbox_msg_up(struct otx2_nic *vf,
 
 		rsp->hdr.id = MBOX_MSG_CGX_LINK_EVENT;
 		rsp->hdr.sig = OTX2_MBOX_RSP_SIG;
-		rsp->hdr.pcifunc = 0;
+		rsp->hdr.pcifunc = req->pcifunc;
 		rsp->hdr.rc = 0;
 		err = otx2_mbox_up_handler_cgx_link_event(
 				vf, (struct cgx_link_info_msg *)req, rsp);
@@ -240,6 +240,10 @@ static void otx2vf_disable_mbox_intr(struct otx2_nic *vf)
 
 	/* Disable VF => PF mailbox IRQ */
 	otx2_write64(vf, RVU_VF_INT_ENA_W1C, BIT_ULL(0));
+
+	if (is_cn20k(vf->pdev))
+		otx2_write64(vf, RVU_VF_INT_ENA_W1C, BIT_ULL(0) | BIT_ULL(1));
+
 	free_irq(vector, vf);
 }
 
@@ -252,9 +256,18 @@ static int otx2vf_register_mbox_intr(struct otx2_nic *vf, bool probe_pf)
 
 	/* Register mailbox interrupt handler */
 	irq_name = &hw->irq_name[RVU_VF_INT_VEC_MBOX * NAME_SIZE];
-	snprintf(irq_name, NAME_SIZE, "RVUVFAF Mbox");
-	err = request_irq(pci_irq_vector(vf->pdev, RVU_VF_INT_VEC_MBOX),
-			  otx2vf_vfaf_mbox_intr_handler, 0, irq_name, vf);
+	snprintf(irq_name, NAME_SIZE, "RVUVF%d AFVF Mbox", ((vf->pcifunc &
+		 RVU_PFVF_FUNC_MASK) - 1));
+
+	if (!is_cn20k(vf->pdev)) {
+		err = request_irq(pci_irq_vector(vf->pdev, RVU_VF_INT_VEC_MBOX),
+				  otx2vf_vfaf_mbox_intr_handler, 0, irq_name, vf);
+	} else {
+		err = request_irq(pci_irq_vector(vf->pdev, RVU_VF_INT_VEC_MBOX),
+				  vf->hw_ops->vfaf_mbox_intr_handler, 0, irq_name,
+				  vf);
+	}
+
 	if (err) {
 		dev_err(vf->dev,
 			"RVUPF: IRQ registration failed for VFAF mbox irq\n");
@@ -264,8 +277,15 @@ static int otx2vf_register_mbox_intr(struct otx2_nic *vf, bool probe_pf)
 	/* Enable mailbox interrupt for msgs coming from PF.
 	 * First clear to avoid spurious interrupts, if any.
 	 */
-	otx2_write64(vf, RVU_VF_INT, BIT_ULL(0));
-	otx2_write64(vf, RVU_VF_INT_ENA_W1S, BIT_ULL(0));
+	if (!is_cn20k(vf->pdev)) {
+		otx2_write64(vf, RVU_VF_INT, BIT_ULL(0));
+		otx2_write64(vf, RVU_VF_INT_ENA_W1S, BIT_ULL(0));
+	} else {
+		otx2_write64(vf, RVU_VF_INT, BIT_ULL(0) | BIT_ULL(1) |
+			     BIT_ULL(2) | BIT_ULL(3));
+		otx2_write64(vf, RVU_VF_INT_ENA_W1S, BIT_ULL(0) |
+			     BIT_ULL(1) | BIT_ULL(2) | BIT_ULL(3));
+	}
 
 	if (!probe_pf)
 		return 0;
@@ -315,7 +335,13 @@ static int otx2vf_vfaf_mbox_init(struct otx2_nic *vf)
 	if (!vf->mbox_wq)
 		return -ENOMEM;
 
-	if (test_bit(CN10K_MBOX, &vf->hw.cap_flag)) {
+	/* For cn20k platform, VF mailbox region is in dram aliased from AF
+	 * VF MBOX ADDR, MBOX is a separate RVU block.
+	 */
+	if (is_cn20k(vf->pdev)) {
+		hwbase = vf->reg_base + RVU_VF_MBOX_REGION + ((u64)BLKADDR_MBOX <<
+			RVU_FUNC_BLKADDR_SHIFT);
+	} else if (test_bit(CN10K_MBOX, &vf->hw.cap_flag)) {
 		/* For cn10k platform, VF mailbox region is in its BAR2
 		 * register space
 		 */
@@ -391,9 +417,19 @@ static netdev_tx_t otx2vf_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct otx2_nic *vf = netdev_priv(netdev);
 	int qidx = skb_get_queue_mapping(skb);
+	struct otx2_dev_stats *dev_stats;
 	struct otx2_snd_queue *sq;
 	struct netdev_queue *txq;
 
+	/* Check for minimum and maximum packet length */
+	if (skb->len <= ETH_HLEN ||
+	    (!skb_shinfo(skb)->gso_size && skb->len > vf->tx_max_pktlen)) {
+		dev_stats = &vf->hw.dev_stats;
+		atomic_long_inc(&dev_stats->tx_discards);
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
 	sq = &vf->qset.sq[qidx];
 	txq = netdev_get_tx_queue(netdev, qidx);
 
@@ -498,8 +534,9 @@ static const struct net_device_ops otx2vf_netdev_ops = {
 	.ndo_set_features = otx2vf_set_features,
 	.ndo_get_stats64 = otx2_get_stats64,
 	.ndo_tx_timeout = otx2_tx_timeout,
-	.ndo_eth_ioctl	= otx2_ioctl,
 	.ndo_setup_tc = otx2_setup_tc,
+	.ndo_hwtstamp_get = otx2_config_hwtstamp_get,
+	.ndo_hwtstamp_set = otx2_config_hwtstamp_set,
 };
 
 static int otx2_vf_wq_init(struct otx2_nic *vf)
@@ -548,7 +585,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return err;
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
+	err = pcim_request_all_regions(pdev, DRV_NAME);
 	if (err) {
 		dev_err(dev, "PCI request regions failed 0x%x\n", err);
 		return err;
@@ -557,7 +594,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
 	if (err) {
 		dev_err(dev, "DMA mask config failed, abort\n");
-		goto err_release_regions;
+		return err;
 	}
 
 	pci_set_master(pdev);
@@ -565,10 +602,8 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	qcount = num_online_cpus();
 	qos_txqs = min_t(int, qcount, OTX2_QOS_MAX_LEAF_NODES);
 	netdev = alloc_etherdev_mqs(sizeof(*vf), qcount + qos_txqs, qcount);
-	if (!netdev) {
-		err = -ENOMEM;
-		goto err_release_regions;
-	}
+	if (!netdev)
+		return -ENOMEM;
 
 	pci_set_drvdata(pdev, netdev);
 	SET_NETDEV_DEV(netdev, &pdev->dev);
@@ -618,6 +653,12 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	otx2_setup_dev_hw_settings(vf);
+
+	if (is_cn20k(vf->pdev))
+		cn20k_init(vf);
+	else
+		otx2_init_hw_ops(vf);
+
 	/* Init VF <=> PF mailbox stuff */
 	err = otx2vf_vfaf_mbox_init(vf);
 	if (err)
@@ -722,15 +763,30 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_shutdown_tc;
 
+	vf->af_xdp_zc_qidx = bitmap_zalloc(qcount, GFP_KERNEL);
+	if (!vf->af_xdp_zc_qidx) {
+		err = -ENOMEM;
+		goto err_unreg_devlink;
+	}
+
 #ifdef CONFIG_DCB
-	err = otx2_dcbnl_set_ops(netdev);
-	if (err)
-		goto err_shutdown_tc;
+	/* Priority flow control is not supported for LBK and SDP vf(s) */
+	if (!(is_otx2_lbkvf(vf->pdev) || is_otx2_sdp_rep(vf->pdev))) {
+		err = otx2_dcbnl_set_ops(netdev);
+		if (err)
+			goto err_free_zc_bmap;
+	}
 #endif
 	otx2_qos_init(vf, qos_txqs);
 
 	return 0;
 
+#ifdef CONFIG_DCB
+err_free_zc_bmap:
+	bitmap_free(vf->af_xdp_zc_qidx);
+#endif
+err_unreg_devlink:
+	otx2_unregister_dl(vf);
 err_shutdown_tc:
 	otx2_shutdown_tc(vf);
 err_unreg_netdev:
@@ -753,8 +809,6 @@ err_free_irq_vectors:
 err_free_netdev:
 	pci_set_drvdata(pdev, NULL);
 	free_netdev(netdev);
-err_release_regions:
-	pci_release_regions(pdev);
 	return err;
 }
 
@@ -801,10 +855,9 @@ static void otx2vf_remove(struct pci_dev *pdev)
 		qmem_free(vf->dev, vf->dync_lmt);
 	otx2vf_vfaf_mbox_destroy(vf);
 	pci_free_irq_vectors(vf->pdev);
+	bitmap_free(vf->af_xdp_zc_qidx);
 	pci_set_drvdata(pdev, NULL);
 	free_netdev(netdev);
-
-	pci_release_regions(pdev);
 }
 
 static struct pci_driver otx2vf_driver = {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
new file mode 100644
index 000000000000..7d67b4cbaf71
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell RVU Ethernet driver
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#include <linux/bpf_trace.h>
+#include <linux/stringify.h>
+#include <net/xdp_sock_drv.h>
+#include <net/xdp.h>
+
+#include "otx2_common.h"
+#include "otx2_struct.h"
+#include "otx2_xsk.h"
+
+int otx2_xsk_pool_alloc_buf(struct otx2_nic *pfvf, struct otx2_pool *pool,
+			    dma_addr_t *dma, int idx)
+{
+	struct xdp_buff *xdp;
+	int delta;
+
+	xdp = xsk_buff_alloc(pool->xsk_pool);
+	if (!xdp)
+		return -ENOMEM;
+
+	pool->xdp[pool->xdp_top++] = xdp;
+	*dma = OTX2_DATA_ALIGN(xsk_buff_xdp_get_dma(xdp));
+	/* Adjust xdp->data for unaligned addresses */
+	delta = *dma - xsk_buff_xdp_get_dma(xdp);
+	xdp->data += delta;
+
+	return 0;
+}
+
+static int otx2_xsk_ctx_disable(struct otx2_nic *pfvf, u16 qidx, int aura_id)
+{
+	struct nix_cn10k_aq_enq_req *cn10k_rq_aq;
+	struct npa_aq_enq_req *aura_aq;
+	struct npa_aq_enq_req *pool_aq;
+	struct nix_aq_enq_req *rq_aq;
+
+	if (test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) {
+		cn10k_rq_aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox);
+		if (!cn10k_rq_aq)
+			return -ENOMEM;
+		cn10k_rq_aq->qidx = qidx;
+		cn10k_rq_aq->rq.ena = 0;
+		cn10k_rq_aq->rq_mask.ena = 1;
+		cn10k_rq_aq->ctype = NIX_AQ_CTYPE_RQ;
+		cn10k_rq_aq->op = NIX_AQ_INSTOP_WRITE;
+	} else {
+		rq_aq = otx2_mbox_alloc_msg_nix_aq_enq(&pfvf->mbox);
+		if (!rq_aq)
+			return -ENOMEM;
+		rq_aq->qidx = qidx;
+		rq_aq->sq.ena = 0;
+		rq_aq->sq_mask.ena = 1;
+		rq_aq->ctype = NIX_AQ_CTYPE_RQ;
+		rq_aq->op = NIX_AQ_INSTOP_WRITE;
+	}
+
+	aura_aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox);
+	if (!aura_aq)
+		goto fail;
+
+	aura_aq->aura_id = aura_id;
+	aura_aq->aura.ena = 0;
+	aura_aq->aura_mask.ena = 1;
+	aura_aq->ctype = NPA_AQ_CTYPE_AURA;
+	aura_aq->op = NPA_AQ_INSTOP_WRITE;
+
+	pool_aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox);
+	if (!pool_aq)
+		goto fail;
+
+	pool_aq->aura_id = aura_id;
+	pool_aq->pool.ena = 0;
+	pool_aq->pool_mask.ena = 1;
+
+	pool_aq->ctype = NPA_AQ_CTYPE_POOL;
+	pool_aq->op = NPA_AQ_INSTOP_WRITE;
+
+	return otx2_sync_mbox_msg(&pfvf->mbox);
+
+fail:
+	otx2_mbox_reset(&pfvf->mbox.mbox, 0);
+	return -ENOMEM;
+}
+
+static void otx2_clean_up_rq(struct otx2_nic *pfvf, int qidx)
+{
+	struct otx2_qset *qset = &pfvf->qset;
+	struct otx2_cq_queue *cq;
+	struct otx2_pool *pool;
+	u64 iova;
+
+	/* If the DOWN flag is set SQs are already freed */
+	if (pfvf->flags & OTX2_FLAG_INTF_DOWN)
+		return;
+
+	cq = &qset->cq[qidx];
+	if (cq)
+		otx2_cleanup_rx_cqes(pfvf, cq, qidx);
+
+	pool = &pfvf->qset.pool[qidx];
+	iova = otx2_aura_allocptr(pfvf, qidx);
+	while (iova) {
+		iova -= OTX2_HEAD_ROOM;
+		otx2_free_bufs(pfvf, pool, iova, pfvf->rbsize);
+		iova = otx2_aura_allocptr(pfvf, qidx);
+	}
+
+	mutex_lock(&pfvf->mbox.lock);
+	otx2_xsk_ctx_disable(pfvf, qidx, qidx);
+	mutex_unlock(&pfvf->mbox.lock);
+}
+
+int otx2_xsk_pool_enable(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qidx)
+{
+	u16 rx_queues = pf->hw.rx_queues;
+	u16 tx_queues = pf->hw.tx_queues;
+	int err;
+
+	if (qidx >= rx_queues || qidx >= tx_queues)
+		return -EINVAL;
+
+	err = xsk_pool_dma_map(pool, pf->dev, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
+	if (err)
+		return err;
+
+	set_bit(qidx, pf->af_xdp_zc_qidx);
+	otx2_clean_up_rq(pf, qidx);
+	/* Reconfigure RSS table as 'qidx' cannot be part of RSS now */
+	otx2_set_rss_table(pf, DEFAULT_RSS_CONTEXT_GROUP, NULL);
+	/* Kick start the NAPI context so that receiving will start */
+	return otx2_xsk_wakeup(pf->netdev, qidx, XDP_WAKEUP_RX);
+}
+
+int otx2_xsk_pool_disable(struct otx2_nic *pf, u16 qidx)
+{
+	struct net_device *netdev = pf->netdev;
+	struct xsk_buff_pool *pool;
+	struct otx2_snd_queue *sq;
+
+	pool = xsk_get_pool_from_qid(netdev, qidx);
+	if (!pool)
+		return -EINVAL;
+
+	sq = &pf->qset.sq[qidx + pf->hw.tx_queues];
+	sq->xsk_pool = NULL;
+	otx2_clean_up_rq(pf, qidx);
+	clear_bit(qidx, pf->af_xdp_zc_qidx);
+	xsk_pool_dma_unmap(pool, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
+	/* Reconfigure RSS table as 'qidx' now need to be part of RSS now */
+	otx2_set_rss_table(pf, DEFAULT_RSS_CONTEXT_GROUP, NULL);
+
+	return 0;
+}
+
+int otx2_xsk_pool_setup(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qidx)
+{
+	if (pool)
+		return otx2_xsk_pool_enable(pf, pool, qidx);
+
+	return otx2_xsk_pool_disable(pf, qidx);
+}
+
+int otx2_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
+{
+	struct otx2_nic *pf = netdev_priv(dev);
+	struct otx2_cq_poll *cq_poll = NULL;
+	struct otx2_qset *qset = &pf->qset;
+
+	if (pf->flags & OTX2_FLAG_INTF_DOWN)
+		return -ENETDOWN;
+
+	if (queue_id >= pf->hw.rx_queues || queue_id >= pf->hw.tx_queues)
+		return -EINVAL;
+
+	cq_poll = &qset->napi[queue_id];
+	if (!cq_poll)
+		return -EINVAL;
+
+	/* Trigger interrupt */
+	if (!napi_if_scheduled_mark_missed(&cq_poll->napi)) {
+		otx2_write64(pf, NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx), BIT_ULL(0));
+		otx2_write64(pf, NIX_LF_CINTX_INT_W1S(cq_poll->cint_idx), BIT_ULL(0));
+	}
+
+	return 0;
+}
+
+void otx2_attach_xsk_buff(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, int qidx)
+{
+	if (test_bit(qidx, pfvf->af_xdp_zc_qidx))
+		sq->xsk_pool = xsk_get_pool_from_qid(pfvf->netdev, qidx);
+}
+
+static void otx2_xsk_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len,
+				   u16 qidx)
+{
+	struct nix_sqe_hdr_s *sqe_hdr;
+	struct otx2_snd_queue *sq;
+	int offset;
+
+	sq = &pfvf->qset.sq[qidx];
+	memset(sq->sqe_base + 8, 0, sq->sqe_size - 8);
+
+	sqe_hdr = (struct nix_sqe_hdr_s *)(sq->sqe_base);
+
+	if (!sqe_hdr->total) {
+		sqe_hdr->aura = sq->aura_id;
+		sqe_hdr->df = 1;
+		sqe_hdr->sq = qidx;
+		sqe_hdr->pnc = 1;
+	}
+	sqe_hdr->total = len;
+	sqe_hdr->sqe_id = sq->head;
+
+	offset = sizeof(*sqe_hdr);
+
+	otx2_xdp_sqe_add_sg(sq, NULL, iova, len, &offset, OTX2_AF_XDP_FRAME);
+	sqe_hdr->sizem1 = (offset / 16) - 1;
+	pfvf->hw_ops->sqe_flush(pfvf, sq, offset, qidx);
+}
+
+void otx2_zc_napi_handler(struct otx2_nic *pfvf, struct xsk_buff_pool *pool,
+			  int queue, int budget)
+{
+	struct xdp_desc *xdp_desc = pool->tx_descs;
+	int  i, batch;
+
+	budget = min(budget, otx2_read_free_sqe(pfvf, queue));
+	batch = xsk_tx_peek_release_desc_batch(pool, budget);
+	if (!batch)
+		return;
+
+	for (i = 0; i < batch; i++) {
+		dma_addr_t dma_addr;
+
+		dma_addr = xsk_buff_raw_get_dma(pool, xdp_desc[i].addr);
+		otx2_xsk_sq_append_pkt(pfvf, dma_addr, xdp_desc[i].len, queue);
+	}
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h
new file mode 100644
index 000000000000..8047fafee8fe
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell RVU PF/VF Netdev Devlink
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#ifndef	OTX2_XSK_H
+#define	OTX2_XSK_H
+
+struct otx2_nic;
+struct xsk_buff_pool;
+
+int otx2_xsk_pool_setup(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qid);
+int otx2_xsk_pool_enable(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qid);
+int otx2_xsk_pool_disable(struct otx2_nic *pf, u16 qid);
+int otx2_xsk_pool_alloc_buf(struct otx2_nic *pfvf, struct otx2_pool *pool,
+			    dma_addr_t *dma, int idx);
+int otx2_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags);
+void otx2_zc_napi_handler(struct otx2_nic *pfvf, struct xsk_buff_pool *pool,
+			  int queue, int budget);
+void otx2_attach_xsk_buff(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, int qidx);
+
+#endif /* OTX2_XSK_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
index 0f844c14485a..5765bac119f0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
@@ -165,6 +165,11 @@ static void __otx2_qos_txschq_cfg(struct otx2_nic *pfvf,
 
 		otx2_config_sched_shaping(pfvf, node, cfg, &num_regs);
 	} else if (level == NIX_TXSCH_LVL_TL2) {
+		/* configure parent txschq */
+		cfg->reg[num_regs] = NIX_AF_TL2X_PARENT(node->schq);
+		cfg->regval[num_regs] = (u64)hw->tx_link << 16;
+		num_regs++;
+
 		/* configure link cfg */
 		if (level == pfvf->qos.link_cfg_lvl) {
 			cfg->reg[num_regs] = NIX_AF_TL3_TL2X_LINKX_CFG(node->schq, hw->tx_link);
@@ -1633,6 +1638,7 @@ static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force
 	if (!node->is_static)
 		dwrr_del_node = true;
 
+	WRITE_ONCE(node->qid, OTX2_QOS_QID_INNER);
 	/* destroy the leaf node */
 	otx2_qos_disable_sq(pfvf, qid);
 	otx2_qos_destroy_node(pfvf, node);
@@ -1677,9 +1683,6 @@ static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force
 	}
 	kfree(new_cfg);
 
-	/* update tx_real_queues */
-	otx2_qos_update_tx_netdev_queues(pfvf);
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
index 9d887bfc3108..2872adabc830 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
@@ -82,7 +82,7 @@ static int otx2_qos_sq_aura_pool_init(struct otx2_nic *pfvf, int qidx)
 	}
 
 	for (ptr = 0; ptr < num_sqbs; ptr++) {
-		err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
+		err = otx2_alloc_rbuf(pfvf, pool, &bufptr, pool_id, ptr);
 		if (err)
 			goto sqb_free;
 		pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);
@@ -151,9 +151,10 @@ static void otx2_qos_sq_free_sqbs(struct otx2_nic *pfvf, int qidx)
 static void otx2_qos_sqb_flush(struct otx2_nic *pfvf, int qidx)
 {
 	int sqe_tail, sqe_head;
-	u64 incr, *ptr, val;
+	void __iomem *ptr;
+	u64 incr, val;
 
-	ptr = (__force u64 *)otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_STATUS);
+	ptr = otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_STATUS);
 	incr = (u64)qidx << 32;
 	val = otx2_atomic64_add(incr, ptr);
 	sqe_head = (val >> 20) & 0x3F;
@@ -256,6 +257,26 @@ out:
 	return err;
 }
 
+static int otx2_qos_nix_npa_ndc_sync(struct otx2_nic *pfvf)
+{
+	struct ndc_sync_op *req;
+	int rc;
+
+	mutex_lock(&pfvf->mbox.lock);
+
+	req = otx2_mbox_alloc_msg_ndc_sync_op(&pfvf->mbox);
+	if (!req) {
+		mutex_unlock(&pfvf->mbox.lock);
+		return -ENOMEM;
+	}
+
+	req->nix_lf_tx_sync = true;
+	req->npa_lf_sync = true;
+	rc = otx2_sync_mbox_msg(&pfvf->mbox);
+	mutex_unlock(&pfvf->mbox.lock);
+	return rc;
+}
+
 void otx2_qos_disable_sq(struct otx2_nic *pfvf, int qidx)
 {
 	struct otx2_qset *qset = &pfvf->qset;
@@ -285,6 +306,8 @@ void otx2_qos_disable_sq(struct otx2_nic *pfvf, int qidx)
 
 	otx2_qos_sqb_flush(pfvf, sq_idx);
 	otx2_smq_flush(pfvf, otx2_get_smq_idx(pfvf, sq_idx));
+	/* NIX/NPA NDC sync */
+	otx2_qos_nix_npa_ndc_sync(pfvf);
 	otx2_cleanup_tx_cqes(pfvf, cq);
 
 	mutex_lock(&pfvf->mbox.lock);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
index 04e08e06f30f..b476733a0234 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
@@ -67,6 +67,8 @@ static int rvu_rep_mcam_flow_init(struct rep_dev *rep)
 
 		rsp = (struct npc_mcam_alloc_entry_rsp *)otx2_mbox_get_rsp
 			(&priv->mbox.mbox, 0, &req->hdr);
+		if (IS_ERR(rsp))
+			goto exit;
 
 		for (ent = 0; ent < rsp->count; ent++)
 			rep->flow_cfg->flow_ent[ent + allocated] = rsp->entry_list[ent];
@@ -242,10 +244,10 @@ static int rvu_rep_devlink_port_register(struct rep_dev *rep)
 
 	if (!(rep->pcifunc & RVU_PFVF_FUNC_MASK)) {
 		attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
-		attrs.phys.port_number = rvu_get_pf(rep->pcifunc);
+		attrs.phys.port_number = rvu_get_pf(priv->pdev, rep->pcifunc);
 	} else {
 		attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF;
-		attrs.pci_vf.pf = rvu_get_pf(rep->pcifunc);
+		attrs.pci_vf.pf = rvu_get_pf(priv->pdev, rep->pcifunc);
 		attrs.pci_vf.vf = rep->pcifunc & RVU_PFVF_FUNC_MASK;
 	}
 
@@ -369,7 +371,8 @@ static void rvu_rep_get_stats(struct work_struct *work)
 	stats->rx_mcast_frames = rsp->rx.mcast;
 	stats->tx_bytes = rsp->tx.octs;
 	stats->tx_frames = rsp->tx.ucast + rsp->tx.bcast + rsp->tx.mcast;
-	stats->tx_drops = rsp->tx.drop;
+	stats->tx_drops = rsp->tx.drop +
+			  (unsigned long)atomic_long_read(&stats->tx_discards);
 exit:
 	mutex_unlock(&priv->mbox.lock);
 }
@@ -416,6 +419,16 @@ static netdev_tx_t rvu_rep_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct otx2_nic *pf = rep->mdev;
 	struct otx2_snd_queue *sq;
 	struct netdev_queue *txq;
+	struct rep_stats *stats;
+
+	/* Check for minimum and maximum packet length */
+	if (skb->len <= ETH_HLEN ||
+	    (!skb_shinfo(skb)->gso_size && skb->len > pf->tx_max_pktlen)) {
+		stats = &rep->stats;
+		atomic_long_inc(&stats->tx_discards);
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
 
 	sq = &pf->qset.sq[rep->rep_id];
 	txq = netdev_get_tx_queue(dev, 0);
@@ -670,7 +683,8 @@ int rvu_rep_create(struct otx2_nic *priv, struct netlink_ext_ack *extack)
 		rep->pcifunc = pcifunc;
 
 		snprintf(ndev->name, sizeof(ndev->name), "Rpf%dvf%d",
-			 rvu_get_pf(pcifunc), (pcifunc & RVU_PFVF_FUNC_MASK));
+			 rvu_get_pf(priv->pdev, pcifunc),
+			 (pcifunc & RVU_PFVF_FUNC_MASK));
 
 		ndev->hw_features = (NETIF_F_RXCSUM | NETIF_F_IP_CSUM |
 			       NETIF_F_IPV6_CSUM | NETIF_F_RXHASH |
@@ -763,7 +777,7 @@ static int rvu_rep_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return err;
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
+	err = pcim_request_all_regions(pdev, DRV_NAME);
 	if (err) {
 		dev_err(dev, "PCI request regions failed 0x%x\n", err);
 		return err;
@@ -772,7 +786,7 @@ static int rvu_rep_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
 	if (err) {
 		dev_err(dev, "DMA mask config failed, abort\n");
-		goto err_release_regions;
+		goto err_set_drv_data;
 	}
 
 	pci_set_master(pdev);
@@ -780,7 +794,7 @@ static int rvu_rep_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
 		err = -ENOMEM;
-		goto err_release_regions;
+		goto err_set_drv_data;
 	}
 
 	pci_set_drvdata(pdev, priv);
@@ -797,7 +811,7 @@ static int rvu_rep_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	err = otx2_init_rsrc(pdev, priv);
 	if (err)
-		goto err_release_regions;
+		goto err_set_drv_data;
 
 	priv->iommu_domain = iommu_get_domain_for_dev(dev);
 
@@ -820,9 +834,8 @@ err_detach_rsrc:
 	otx2_disable_mbox_intr(priv);
 	otx2_pfaf_mbox_destroy(priv);
 	pci_free_irq_vectors(pdev);
-err_release_regions:
+err_set_drv_data:
 	pci_set_drvdata(pdev, NULL);
-	pci_release_regions(pdev);
 	return err;
 }
 
@@ -842,7 +855,6 @@ static void rvu_rep_remove(struct pci_dev *pdev)
 	otx2_pfaf_mbox_destroy(priv);
 	pci_free_irq_vectors(priv->pdev);
 	pci_set_drvdata(pdev, NULL);
-	pci_release_regions(pdev);
 }
 
 static struct pci_driver rvu_rep_driver = {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.h b/drivers/net/ethernet/marvell/octeontx2/nic/rep.h
index 38446b3e4f13..5bc9e2c7d800 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.h
@@ -27,6 +27,7 @@ struct rep_stats {
 	u64 tx_bytes;
 	u64 tx_frames;
 	u64 tx_drops;
+	atomic_long_t tx_discards;
 };
 
 struct rep_dev {
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_counter.c b/drivers/net/ethernet/marvell/prestera/prestera_counter.c
index 4cd53a2dae46..634f4543c1d7 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_counter.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_counter.c
@@ -336,8 +336,7 @@ prestera_counter_block_get_by_idx(struct prestera_counter *counter, u32 idx)
 
 static void prestera_counter_stats_work(struct work_struct *work)
 {
-	struct delayed_work *dl_work =
-		container_of(work, struct delayed_work, work);
+	struct delayed_work *dl_work = to_delayed_work(work);
 	struct prestera_counter *counter =
 		container_of(dl_work, struct prestera_counter, stats_dw);
 	struct prestera_counter_block *block;
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c
index 22ca6ee9665e..65e7ef033bde 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_main.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c
@@ -280,6 +280,7 @@ prestera_mac_select_pcs(struct phylink_config *config,
 }
 
 static void prestera_pcs_get_state(struct phylink_pcs *pcs,
+				   unsigned int neg_mode,
 				   struct phylink_link_state *state)
 {
 	struct prestera_port *port = container_of(pcs, struct prestera_port,
@@ -395,7 +396,6 @@ static int prestera_port_sfp_bind(struct prestera_port *port)
 			continue;
 
 		port->phylink_pcs.ops = &prestera_pcs_ops;
-		port->phylink_pcs.neg_mode = true;
 
 		port->phy_config.dev = &port->dev->dev;
 		port->phy_config.type = PHYLINK_NETDEV;
@@ -634,7 +634,7 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id)
 		goto err_dl_port_register;
 
 	dev->features |= NETIF_F_HW_TC;
-	dev->netns_local = true;
+	dev->netns_immutable = true;
 	dev->netdev_ops = &prestera_netdev_ops;
 	dev->ethtool_ops = &prestera_ethtool_ops;
 	SET_NETDEV_DEV(dev, sw->dev->dev);
@@ -1500,7 +1500,7 @@ EXPORT_SYMBOL(prestera_device_unregister);
 
 static int __init prestera_module_init(void)
 {
-	prestera_wq = alloc_workqueue("prestera", 0, 0);
+	prestera_wq = alloc_workqueue("prestera", WQ_PERCPU, 0);
 	if (!prestera_wq)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
index 35857dc19542..3e13322470da 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
@@ -845,9 +845,9 @@ static int prestera_pci_probe(struct pci_dev *pdev,
 		goto err_pci_enable_device;
 	}
 
-	err = pci_request_regions(pdev, driver_name);
+	err = pcim_request_all_regions(pdev, driver_name);
 	if (err) {
-		dev_err(&pdev->dev, "pci_request_regions failed\n");
+		dev_err(&pdev->dev, "pcim_request_all_regions failed\n");
 		goto err_pci_request_regions;
 	}
 
@@ -898,7 +898,7 @@ static int prestera_pci_probe(struct pci_dev *pdev,
 
 	dev_info(fw->dev.dev, "Prestera FW is ready\n");
 
-	fw->wq = alloc_workqueue("prestera_fw_wq", WQ_HIGHPRI, 1);
+	fw->wq = alloc_workqueue("prestera_fw_wq", WQ_HIGHPRI | WQ_PERCPU, 1);
 	if (!fw->wq) {
 		err = -ENOMEM;
 		goto err_wq_alloc;
@@ -938,7 +938,6 @@ err_pci_dev_alloc:
 err_pp_ioremap:
 err_mem_ioremap:
 err_dma_mask:
-	pci_release_regions(pdev);
 err_pci_request_regions:
 err_pci_enable_device:
 	return err;
@@ -953,7 +952,6 @@ static void prestera_pci_remove(struct pci_dev *pdev)
 	pci_free_irq_vectors(pdev);
 	destroy_workqueue(fw->wq);
 	prestera_fw_uninit(fw);
-	pci_release_regions(pdev);
 }
 
 static const struct pci_device_id prestera_pci_devices[] = {
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index 2bf426cea6dd..68f8a1e36aa6 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -353,7 +353,7 @@ static void rxq_refill(struct net_device *dev)
 
 static inline void rxq_refill_timer_wrapper(struct timer_list *t)
 {
-	struct pxa168_eth_private *pep = from_timer(pep, t, timeout);
+	struct pxa168_eth_private *pep = timer_container_of(pep, t, timeout);
 	napi_schedule(&pep->napi);
 }
 
@@ -1175,7 +1175,7 @@ static int pxa168_eth_stop(struct net_device *dev)
 	/* Write to ICR to clear interrupts. */
 	wrl(pep, INT_W_CLEAR, 0);
 	napi_disable(&pep->napi);
-	del_timer_sync(&pep->timeout);
+	timer_delete_sync(&pep->timeout);
 	netif_carrier_off(dev);
 	free_irq(dev->irq, dev);
 	rxq_deinit(dev);
@@ -1229,9 +1229,9 @@ static int pxa168_rx_poll(struct napi_struct *napi, int budget)
 	int work_done = 0;
 
 	/*
-	 * We call txq_reclaim every time since in NAPI interupts are disabled
-	 * and due to this we miss the TX_DONE interrupt,which is not updated in
-	 * interrupt status register.
+	 * We call txq_reclaim every time since in NAPI interrupts are disabled
+	 * and due to this we miss the TX_DONE interrupt, which is not updated
+	 * in interrupt status register.
 	 */
 	txq_reclaim(dev, 0);
 	if (netif_queue_stopped(dev)
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 25bf6ec44289..05349a0b2db1 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -1494,7 +1494,7 @@ static int xm_check_link(struct net_device *dev)
  */
 static void xm_link_timer(struct timer_list *t)
 {
-	struct skge_port *skge = from_timer(skge, t, link_timer);
+	struct skge_port *skge = timer_container_of(skge, t, link_timer);
 	struct net_device *dev = skge->netdev;
 	struct skge_hw *hw = skge->hw;
 	int port = skge->port;
@@ -2662,7 +2662,7 @@ static int skge_down(struct net_device *dev)
 	netif_tx_disable(dev);
 
 	if (is_genesis(hw) && hw->phy_type == SK_PHY_XMAC)
-		del_timer_sync(&skge->link_timer);
+		timer_delete_sync(&skge->link_timer);
 
 	napi_disable(&skge->napi);
 	netif_carrier_off(dev);
@@ -3742,10 +3742,7 @@ static int skge_device_event(struct notifier_block *unused,
 	skge = netdev_priv(dev);
 	switch (event) {
 	case NETDEV_CHANGENAME:
-		if (skge->debugfs)
-			skge->debugfs = debugfs_rename(skge_debug,
-						       skge->debugfs,
-						       skge_debug, dev->name);
+		debugfs_change_name(skge->debugfs, "%s", dev->name);
 		break;
 
 	case NETDEV_GOING_DOWN:
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 3914cd9210d4..3831f533b9db 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -130,6 +130,7 @@ static const struct pci_device_id sky2_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x436C) }, /* 88E8072 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x436D) }, /* 88E8055 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4370) }, /* 88E8075 */
+	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4373) }, /* 88E8075 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4380) }, /* 88E8057 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4381) }, /* 88E8059 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4382) }, /* 88E8079 */
@@ -2960,7 +2961,7 @@ static int sky2_rx_hung(struct net_device *dev)
 
 static void sky2_watchdog(struct timer_list *t)
 {
-	struct sky2_hw *hw = from_timer(hw, t, watchdog_timer);
+	struct sky2_hw *hw = timer_container_of(hw, t, watchdog_timer);
 
 	/* Check for lost IRQ once a second */
 	if (sky2_read32(hw, B0_ISRC)) {
@@ -4493,10 +4494,7 @@ static int sky2_device_event(struct notifier_block *unused,
 
 	switch (event) {
 	case NETDEV_CHANGENAME:
-		if (sky2->debugfs) {
-			sky2->debugfs = debugfs_rename(sky2_debug, sky2->debugfs,
-						       sky2_debug, dev->name);
-		}
+		debugfs_change_name(sky2->debugfs, "%s", dev->name);
 		break;
 
 	case NETDEV_GOING_DOWN:
@@ -5054,7 +5052,7 @@ static int sky2_suspend(struct device *dev)
 	if (!hw)
 		return 0;
 
-	del_timer_sync(&hw->watchdog_timer);
+	timer_delete_sync(&hw->watchdog_timer);
 	cancel_work_sync(&hw->restart_work);
 
 	rtnl_lock();
diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig
index 95c4405b7d7b..2ba361f8ce7d 100644
--- a/drivers/net/ethernet/mediatek/Kconfig
+++ b/drivers/net/ethernet/mediatek/Kconfig
@@ -7,14 +7,6 @@ config NET_VENDOR_MEDIATEK
 
 if NET_VENDOR_MEDIATEK
 
-config NET_AIROHA
-	tristate "Airoha SoC Gigabit Ethernet support"
-	depends on NET_DSA || !NET_DSA
-	select PAGE_POOL
-	help
-	  This driver supports the gigabit ethernet MACs in the
-	  Airoha SoC family.
-
 config NET_MEDIATEK_SOC_WED
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	def_bool NET_MEDIATEK_SOC != n
@@ -25,6 +17,7 @@ config NET_MEDIATEK_SOC
 	select PINCTRL
 	select PHYLINK
 	select DIMLIB
+	select GENERIC_ALLOCATOR
 	select PAGE_POOL
 	select PAGE_POOL_STATS
 	select PCS_MTK_LYNXI
diff --git a/drivers/net/ethernet/mediatek/Makefile b/drivers/net/ethernet/mediatek/Makefile
index ddbb7f4a516c..03e008fbc859 100644
--- a/drivers/net/ethernet/mediatek/Makefile
+++ b/drivers/net/ethernet/mediatek/Makefile
@@ -11,4 +11,3 @@ mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed_debugfs.o
 endif
 obj-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed_ops.o
 obj-$(CONFIG_NET_MEDIATEK_STAR_EMAC) += mtk_star_emac.o
-obj-$(CONFIG_NET_AIROHA) += airoha_eth.o
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_path.c b/drivers/net/ethernet/mediatek/mtk_eth_path.c
index 7c27a19c4d8f..b4c01e2878f6 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_path.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_path.c
@@ -14,7 +14,7 @@
 
 struct mtk_eth_muxc {
 	const char	*name;
-	int		cap_bit;
+	u64		cap_bit;
 	int		(*set_path)(struct mtk_eth *eth, u64 path);
 };
 
@@ -31,6 +31,8 @@ static const char *mtk_eth_path_name(u64 path)
 		return "gmac2_rgmii";
 	case MTK_ETH_PATH_GMAC2_SGMII:
 		return "gmac2_sgmii";
+	case MTK_ETH_PATH_GMAC2_2P5GPHY:
+		return "gmac2_2p5gphy";
 	case MTK_ETH_PATH_GMAC2_GEPHY:
 		return "gmac2_gephy";
 	case MTK_ETH_PATH_GDM1_ESW:
@@ -127,6 +129,29 @@ static int set_mux_u3_gmac2_to_qphy(struct mtk_eth *eth, u64 path)
 	return 0;
 }
 
+static int set_mux_gmac2_to_2p5gphy(struct mtk_eth *eth, u64 path)
+{
+	int ret;
+
+	if (path == MTK_ETH_PATH_GMAC2_2P5GPHY) {
+		ret = regmap_clear_bits(eth->ethsys, ETHSYS_SYSCFG0,
+					SYSCFG0_SGMII_GMAC2_V2);
+		if (ret)
+			return ret;
+
+		/* Setup mux to 2p5g PHY */
+		ret = regmap_clear_bits(eth->infra, TOP_MISC_NETSYS_PCS_MUX,
+					MUX_G2_USXGMII_SEL);
+		if (ret)
+			return ret;
+
+		dev_dbg(eth->dev, "path %s in %s updated\n",
+			mtk_eth_path_name(path), __func__);
+	}
+
+	return 0;
+}
+
 static int set_mux_gmac1_gmac2_to_sgmii_rgmii(struct mtk_eth *eth, u64 path)
 {
 	unsigned int val = 0;
@@ -210,6 +235,10 @@ static const struct mtk_eth_muxc mtk_eth_muxc[] = {
 		.cap_bit = MTK_ETH_MUX_U3_GMAC2_TO_QPHY,
 		.set_path = set_mux_u3_gmac2_to_qphy,
 	}, {
+		.name = "mux_gmac2_to_2p5gphy",
+		.cap_bit = MTK_ETH_MUX_GMAC2_TO_2P5GPHY,
+		.set_path = set_mux_gmac2_to_2p5gphy,
+	}, {
 		.name = "mux_gmac1_gmac2_to_sgmii_rgmii",
 		.cap_bit = MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII,
 		.set_path = set_mux_gmac1_gmac2_to_sgmii_rgmii,
@@ -260,6 +289,20 @@ int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id)
 	return mtk_eth_mux_setup(eth, path);
 }
 
+int mtk_gmac_2p5gphy_path_setup(struct mtk_eth *eth, int mac_id)
+{
+	u64 path = 0;
+
+	if (mac_id == MTK_GMAC2_ID)
+		path = MTK_ETH_PATH_GMAC2_2P5GPHY;
+
+	if (!path)
+		return -EINVAL;
+
+	/* Setup proper MUXes along the path */
+	return mtk_eth_mux_setup(eth, path);
+}
+
 int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id)
 {
 	u64 path = 0;
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 53485142938c..e68997a29191 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -27,6 +27,7 @@
 #include <net/dsa.h>
 #include <net/dst_metadata.h>
 #include <net/page_pool/helpers.h>
+#include <linux/genalloc.h>
 
 #include "mtk_eth_soc.h"
 #include "mtk_wed.h"
@@ -269,12 +270,8 @@ static const char * const mtk_clks_source_name[] = {
 	"ethwarp_wocpu2",
 	"ethwarp_wocpu1",
 	"ethwarp_wocpu0",
-	"top_usxgmii0_sel",
-	"top_usxgmii1_sel",
 	"top_sgm0_sel",
 	"top_sgm1_sel",
-	"top_xfi_phy0_xtal_sel",
-	"top_xfi_phy1_xtal_sel",
 	"top_eth_gmii_sel",
 	"top_eth_refck_50m_sel",
 	"top_eth_sys_200m_sel",
@@ -507,7 +504,7 @@ static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth,
 static void mtk_setup_bridge_switch(struct mtk_eth *eth)
 {
 	/* Force Port1 XGMAC Link Up */
-	mtk_m32(eth, 0, MTK_XGMAC_FORCE_LINK(MTK_GMAC1_ID),
+	mtk_m32(eth, 0, MTK_XGMAC_FORCE_MODE(MTK_GMAC1_ID),
 		MTK_XGMAC_STS(MTK_GMAC1_ID));
 
 	/* Adjust GSW bridge IPG to 11 */
@@ -536,6 +533,26 @@ static struct phylink_pcs *mtk_mac_select_pcs(struct phylink_config *config,
 	return NULL;
 }
 
+static int mtk_mac_prepare(struct phylink_config *config, unsigned int mode,
+			   phy_interface_t iface)
+{
+	struct mtk_mac *mac = container_of(config, struct mtk_mac,
+					   phylink_config);
+	struct mtk_eth *eth = mac->hw;
+
+	if (mtk_interface_mode_is_xgmii(eth, iface) &&
+	    mac->id != MTK_GMAC1_ID) {
+		mtk_m32(mac->hw, XMAC_MCR_TRX_DISABLE,
+			XMAC_MCR_TRX_DISABLE, MTK_XMAC_MCR(mac->id));
+
+		mtk_m32(mac->hw, MTK_XGMAC_FORCE_MODE(mac->id) |
+				 MTK_XGMAC_FORCE_LINK(mac->id),
+			MTK_XGMAC_FORCE_MODE(mac->id), MTK_XGMAC_STS(mac->id));
+	}
+
+	return 0;
+}
+
 static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 			   const struct phylink_link_state *state)
 {
@@ -577,6 +594,12 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 			}
 			break;
 		case PHY_INTERFACE_MODE_INTERNAL:
+			if (mac->id == MTK_GMAC2_ID &&
+			    MTK_HAS_CAPS(eth->soc->caps, MTK_2P5GPHY)) {
+				err = mtk_gmac_2p5gphy_path_setup(eth, mac->id);
+				if (err)
+					goto init_err;
+			}
 			break;
 		default:
 			goto err_phy;
@@ -648,12 +671,12 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 	}
 
 	/* Setup gmac */
-	if (mtk_is_netsys_v3_or_greater(eth) &&
-	    mac->interface == PHY_INTERFACE_MODE_INTERNAL) {
+	if (mtk_interface_mode_is_xgmii(eth, state->interface)) {
 		mtk_w32(mac->hw, MTK_GDMA_XGDM_SEL, MTK_GDMA_EG_CTRL(mac->id));
 		mtk_w32(mac->hw, MAC_MCR_FORCE_LINK_DOWN, MTK_MAC_MCR(mac->id));
 
-		mtk_setup_bridge_switch(eth);
+		if (mac->id == MTK_GMAC1_ID)
+			mtk_setup_bridge_switch(eth);
 	}
 
 	return;
@@ -700,10 +723,19 @@ static void mtk_mac_link_down(struct phylink_config *config, unsigned int mode,
 {
 	struct mtk_mac *mac = container_of(config, struct mtk_mac,
 					   phylink_config);
-	u32 mcr = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id));
 
-	mcr &= ~(MAC_MCR_TX_EN | MAC_MCR_RX_EN | MAC_MCR_FORCE_LINK);
-	mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id));
+	if (!mtk_interface_mode_is_xgmii(mac->hw, interface)) {
+		/* GMAC modes */
+		mtk_m32(mac->hw,
+			MAC_MCR_TX_EN | MAC_MCR_RX_EN | MAC_MCR_FORCE_LINK, 0,
+			MTK_MAC_MCR(mac->id));
+	} else if (mac->id != MTK_GMAC1_ID) {
+		/* XGMAC except for built-in switch */
+		mtk_m32(mac->hw, XMAC_MCR_TRX_DISABLE, XMAC_MCR_TRX_DISABLE,
+			MTK_XMAC_MCR(mac->id));
+		mtk_m32(mac->hw, MTK_XGMAC_FORCE_LINK(mac->id), 0,
+			MTK_XGMAC_STS(mac->id));
+	}
 }
 
 static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
@@ -734,7 +766,7 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
 		case SPEED_100:
 			val |= MTK_QTX_SCH_MAX_RATE_EN |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 103) |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 3);
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 3) |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1);
 			break;
 		case SPEED_1000:
@@ -757,13 +789,13 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
 		case SPEED_100:
 			val |= MTK_QTX_SCH_MAX_RATE_EN |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 1) |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5);
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5) |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1);
 			break;
 		case SPEED_1000:
 			val |= MTK_QTX_SCH_MAX_RATE_EN |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 10) |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5) |
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 1) |
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 6) |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 10);
 			break;
 		default:
@@ -775,13 +807,12 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
 	mtk_w32(eth, val, soc->reg_map->qdma.qtx_sch + ofs);
 }
 
-static void mtk_mac_link_up(struct phylink_config *config,
-			    struct phy_device *phy,
-			    unsigned int mode, phy_interface_t interface,
-			    int speed, int duplex, bool tx_pause, bool rx_pause)
+static void mtk_gdm_mac_link_up(struct mtk_mac *mac,
+				struct phy_device *phy,
+				unsigned int mode, phy_interface_t interface,
+				int speed, int duplex, bool tx_pause,
+				bool rx_pause)
 {
-	struct mtk_mac *mac = container_of(config, struct mtk_mac,
-					   phylink_config);
 	u32 mcr;
 
 	mcr = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id));
@@ -815,32 +846,145 @@ static void mtk_mac_link_up(struct phylink_config *config,
 	mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id));
 }
 
+static void mtk_xgdm_mac_link_up(struct mtk_mac *mac,
+				 struct phy_device *phy,
+				 unsigned int mode, phy_interface_t interface,
+				 int speed, int duplex, bool tx_pause,
+				 bool rx_pause)
+{
+	u32 mcr;
+
+	if (mac->id == MTK_GMAC1_ID)
+		return;
+
+	/* Eliminate the interference(before link-up) caused by PHY noise */
+	mtk_m32(mac->hw, XMAC_LOGIC_RST, 0, MTK_XMAC_LOGIC_RST(mac->id));
+	mdelay(20);
+	mtk_m32(mac->hw, XMAC_GLB_CNTCLR, XMAC_GLB_CNTCLR,
+		MTK_XMAC_CNT_CTRL(mac->id));
+
+	mtk_m32(mac->hw, MTK_XGMAC_FORCE_LINK(mac->id),
+		MTK_XGMAC_FORCE_LINK(mac->id), MTK_XGMAC_STS(mac->id));
+
+	mcr = mtk_r32(mac->hw, MTK_XMAC_MCR(mac->id));
+	mcr &= ~(XMAC_MCR_FORCE_TX_FC | XMAC_MCR_FORCE_RX_FC |
+		 XMAC_MCR_TRX_DISABLE);
+	/* Configure pause modes -
+	 * phylink will avoid these for half duplex
+	 */
+	if (tx_pause)
+		mcr |= XMAC_MCR_FORCE_TX_FC;
+	if (rx_pause)
+		mcr |= XMAC_MCR_FORCE_RX_FC;
+
+	mtk_w32(mac->hw, mcr, MTK_XMAC_MCR(mac->id));
+}
+
+static void mtk_mac_link_up(struct phylink_config *config,
+			    struct phy_device *phy,
+			    unsigned int mode, phy_interface_t interface,
+			    int speed, int duplex, bool tx_pause, bool rx_pause)
+{
+	struct mtk_mac *mac = container_of(config, struct mtk_mac,
+					   phylink_config);
+
+	if (mtk_interface_mode_is_xgmii(mac->hw, interface))
+		mtk_xgdm_mac_link_up(mac, phy, mode, interface, speed, duplex,
+				     tx_pause, rx_pause);
+	else
+		mtk_gdm_mac_link_up(mac, phy, mode, interface, speed, duplex,
+				    tx_pause, rx_pause);
+}
+
+static void mtk_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct mtk_mac *mac = container_of(config, struct mtk_mac,
+					   phylink_config);
+	struct mtk_eth *eth = mac->hw;
+
+	mtk_m32(eth, MAC_MCR_EEE100M | MAC_MCR_EEE1G, 0, MTK_MAC_MCR(mac->id));
+}
+
+static int mtk_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
+				 bool tx_clk_stop)
+{
+	struct mtk_mac *mac = container_of(config, struct mtk_mac,
+					   phylink_config);
+	struct mtk_eth *eth = mac->hw;
+	u32 val;
+
+	if (mtk_interface_mode_is_xgmii(eth, mac->interface))
+		return -EOPNOTSUPP;
+
+	/* Tx idle timer in ms */
+	timer = DIV_ROUND_UP(timer, 1000);
+
+	/* If the timer is zero, then set LPI_MODE, which allows the
+	 * system to enter LPI mode immediately rather than waiting for
+	 * the LPI threshold.
+	 */
+	if (!timer)
+		val = MAC_EEE_LPI_MODE;
+	else if (FIELD_FIT(MAC_EEE_LPI_TXIDLE_THD, timer))
+		val = FIELD_PREP(MAC_EEE_LPI_TXIDLE_THD, timer);
+	else
+		val = MAC_EEE_LPI_TXIDLE_THD;
+
+	if (tx_clk_stop)
+		val |= MAC_EEE_CKG_TXIDLE;
+
+	/* PHY Wake-up time, this field does not have a reset value, so use the
+	 * reset value from MT7531 (36us for 100M and 17us for 1000M).
+	 */
+	val |= FIELD_PREP(MAC_EEE_WAKEUP_TIME_1000, 17) |
+	       FIELD_PREP(MAC_EEE_WAKEUP_TIME_100, 36);
+
+	mtk_w32(eth, val, MTK_MAC_EEECR(mac->id));
+	mtk_m32(eth, 0, MAC_MCR_EEE100M | MAC_MCR_EEE1G, MTK_MAC_MCR(mac->id));
+
+	return 0;
+}
+
 static const struct phylink_mac_ops mtk_phylink_ops = {
+	.mac_prepare = mtk_mac_prepare,
 	.mac_select_pcs = mtk_mac_select_pcs,
 	.mac_config = mtk_mac_config,
 	.mac_finish = mtk_mac_finish,
 	.mac_link_down = mtk_mac_link_down,
 	.mac_link_up = mtk_mac_link_up,
+	.mac_disable_tx_lpi = mtk_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = mtk_mac_enable_tx_lpi,
 };
 
+static void mtk_mdio_config(struct mtk_eth *eth)
+{
+	u32 val;
+
+	/* Configure MDC Divider */
+	val = FIELD_PREP(PPSC_MDC_CFG, eth->mdc_divider);
+
+	/* Configure MDC Turbo Mode */
+	if (mtk_is_netsys_v3_or_greater(eth))
+		mtk_m32(eth, 0, MISC_MDC_TURBO, MTK_MAC_MISC_V3);
+	else
+		val |= PPSC_MDC_TURBO;
+
+	mtk_m32(eth, PPSC_MDC_CFG, val, MTK_PPSC);
+}
+
 static int mtk_mdio_init(struct mtk_eth *eth)
 {
-	unsigned int max_clk = 2500000, divider;
+	unsigned int max_clk = 2500000;
 	struct device_node *mii_np;
 	int ret;
 	u32 val;
 
-	mii_np = of_get_child_by_name(eth->dev->of_node, "mdio-bus");
+	mii_np = of_get_available_child_by_name(eth->dev->of_node, "mdio-bus");
 	if (!mii_np) {
 		dev_err(eth->dev, "no %s child node found", "mdio-bus");
 		return -ENODEV;
 	}
 
-	if (!of_device_is_available(mii_np)) {
-		ret = -ENODEV;
-		goto err_put_node;
-	}
-
 	eth->mii_bus = devm_mdiobus_alloc(eth->dev);
 	if (!eth->mii_bus) {
 		ret = -ENOMEM;
@@ -865,20 +1009,9 @@ static int mtk_mdio_init(struct mtk_eth *eth)
 		}
 		max_clk = val;
 	}
-	divider = min_t(unsigned int, DIV_ROUND_UP(MDC_MAX_FREQ, max_clk), 63);
-
-	/* Configure MDC Turbo Mode */
-	if (mtk_is_netsys_v3_or_greater(eth))
-		mtk_m32(eth, 0, MISC_MDC_TURBO, MTK_MAC_MISC_V3);
-
-	/* Configure MDC Divider */
-	val = FIELD_PREP(PPSC_MDC_CFG, divider);
-	if (!mtk_is_netsys_v3_or_greater(eth))
-		val |= PPSC_MDC_TURBO;
-	mtk_m32(eth, PPSC_MDC_CFG, val, MTK_PPSC);
-
-	dev_dbg(eth->dev, "MDC is running on %d Hz\n", MDC_MAX_FREQ / divider);
-
+	eth->mdc_divider = min_t(unsigned int, DIV_ROUND_UP(MDC_MAX_FREQ, max_clk), 63);
+	mtk_mdio_config(eth);
+	dev_dbg(eth->dev, "MDC is running on %d Hz\n", MDC_MAX_FREQ / eth->mdc_divider);
 	ret = of_mdiobus_register(eth->mii_bus, mii_np);
 
 err_put_node:
@@ -1135,6 +1268,34 @@ static void *mtk_max_lro_buf_alloc(gfp_t gfp_mask)
 	return (void *)data;
 }
 
+static void *mtk_dma_ring_alloc(struct mtk_eth *eth, size_t size,
+				dma_addr_t *dma_handle, bool use_sram)
+{
+	void *dma_ring;
+
+	if (use_sram && eth->sram_pool) {
+		dma_ring = (void *)gen_pool_alloc(eth->sram_pool, size);
+		if (!dma_ring)
+			return dma_ring;
+		*dma_handle = gen_pool_virt_to_phys(eth->sram_pool,
+						    (unsigned long)dma_ring);
+	} else {
+		dma_ring = dma_alloc_coherent(eth->dma_dev, size, dma_handle,
+					      GFP_KERNEL);
+	}
+
+	return dma_ring;
+}
+
+static void mtk_dma_ring_free(struct mtk_eth *eth, size_t size, void *dma_ring,
+			      dma_addr_t dma_handle, bool in_sram)
+{
+	if (in_sram && eth->sram_pool)
+		gen_pool_free(eth->sram_pool, (unsigned long)dma_ring, size);
+	else
+		dma_free_coherent(eth->dma_dev, size, dma_ring, dma_handle);
+}
+
 /* the qdma core needs scratch memory to be setup */
 static int mtk_init_fq_dma(struct mtk_eth *eth)
 {
@@ -1144,13 +1305,8 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 	dma_addr_t dma_addr;
 	int i, j, len;
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SRAM))
-		eth->scratch_ring = eth->sram_base;
-	else
-		eth->scratch_ring = dma_alloc_coherent(eth->dma_dev,
-						       cnt * soc->tx.desc_size,
-						       &eth->phy_scratch_ring,
-						       GFP_KERNEL);
+	eth->scratch_ring = mtk_dma_ring_alloc(eth, cnt * soc->tx.desc_size,
+					       &eth->phy_scratch_ring, true);
 
 	if (unlikely(!eth->scratch_ring))
 		return -ENOMEM;
@@ -1605,6 +1761,13 @@ static netdev_tx_t mtk_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool gso = false;
 	int tx_num;
 
+	if (skb_vlan_tag_present(skb) &&
+	    !eth_proto_is_802_3(eth_hdr(skb)->h_proto)) {
+		skb = __vlan_hwaccel_push_inside(skb);
+		if (!skb)
+			goto dropped;
+	}
+
 	/* normally we can rely on the stack not calling this more than once,
 	 * however we have 2 queues running on the same ring so we need to lock
 	 * the ring access
@@ -1650,8 +1813,9 @@ static netdev_tx_t mtk_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 drop:
 	spin_unlock(&eth->page_lock);
-	stats->tx_dropped++;
 	dev_kfree_skb_any(skb);
+dropped:
+	stats->tx_dropped++;
 	return NETDEV_TX_OK;
 }
 
@@ -2079,7 +2243,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 		if (ring->page_pool) {
 			struct page *page = virt_to_head_page(data);
 			struct xdp_buff xdp;
-			u32 ret;
+			u32 ret, metasize;
 
 			new_data = mtk_page_pool_get_buff(ring->page_pool,
 							  &dma_addr,
@@ -2095,7 +2259,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 
 			xdp_init_buff(&xdp, PAGE_SIZE, &ring->xdp_q);
 			xdp_prepare_buff(&xdp, data, MTK_PP_HEADROOM, pktlen,
-					 false);
+					 true);
 			xdp_buff_clear_frags_flag(&xdp);
 
 			ret = mtk_xdp_run(eth, ring, &xdp, netdev);
@@ -2115,6 +2279,9 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 
 			skb_reserve(skb, xdp.data - xdp.data_hard_start);
 			skb_put(skb, xdp.data_end - xdp.data);
+			metasize = xdp.data - xdp.data_meta;
+			if (metasize)
+				skb_metadata_set(skb, metasize);
 			skb_mark_for_recycle(skb);
 		} else {
 			if (ring->frag_size <= PAGE_SIZE)
@@ -2201,14 +2368,18 @@ skip_rx:
 		ring->data[idx] = new_data;
 		rxd->rxd1 = (unsigned int)dma_addr;
 release_desc:
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) {
+			if (unlikely(dma_addr == DMA_MAPPING_ERROR))
+				addr64 = FIELD_GET(RX_DMA_ADDR64_MASK,
+						   rxd->rxd2);
+			else
+				addr64 = RX_DMA_PREP_ADDR64(dma_addr);
+		}
+
 		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
 			rxd->rxd2 = RX_DMA_LSO;
 		else
-			rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size);
-
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA) &&
-		    likely(dma_addr != DMA_MAPPING_ERROR))
-			rxd->rxd2 |= RX_DMA_PREP_ADDR64(dma_addr);
+			rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size) | addr64;
 
 		ring->calc_idx = idx;
 		done++;
@@ -2481,14 +2652,7 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
 	if (!ring->buf)
 		goto no_tx_mem;
 
-	if (MTK_HAS_CAPS(soc->caps, MTK_SRAM)) {
-		ring->dma = eth->sram_base + soc->tx.fq_dma_size * sz;
-		ring->phys = eth->phy_scratch_ring + soc->tx.fq_dma_size * (dma_addr_t)sz;
-	} else {
-		ring->dma = dma_alloc_coherent(eth->dma_dev, ring_size * sz,
-					       &ring->phys, GFP_KERNEL);
-	}
-
+	ring->dma = mtk_dma_ring_alloc(eth, ring_size * sz, &ring->phys, true);
 	if (!ring->dma)
 		goto no_tx_mem;
 
@@ -2587,10 +2751,10 @@ static void mtk_tx_clean(struct mtk_eth *eth)
 		kfree(ring->buf);
 		ring->buf = NULL;
 	}
-	if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && ring->dma) {
-		dma_free_coherent(eth->dma_dev,
-				  ring->dma_size * soc->tx.desc_size,
-				  ring->dma, ring->phys);
+
+	if (ring->dma) {
+		mtk_dma_ring_free(eth, ring->dma_size * soc->tx.desc_size,
+				  ring->dma, ring->phys, true);
 		ring->dma = NULL;
 	}
 
@@ -2607,14 +2771,9 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 	const struct mtk_reg_map *reg_map = eth->soc->reg_map;
 	const struct mtk_soc_data *soc = eth->soc;
 	struct mtk_rx_ring *ring;
-	int rx_data_len, rx_dma_size, tx_ring_size;
+	int rx_data_len, rx_dma_size;
 	int i;
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA))
-		tx_ring_size = MTK_QDMA_RING_SIZE;
-	else
-		tx_ring_size = soc->tx.dma_size;
-
 	if (rx_flag == MTK_RX_FLAGS_QDMA) {
 		if (ring_no)
 			return -EINVAL;
@@ -2649,20 +2808,10 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 		ring->page_pool = pp;
 	}
 
-	if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SRAM) ||
-	    rx_flag != MTK_RX_FLAGS_NORMAL) {
-		ring->dma = dma_alloc_coherent(eth->dma_dev,
-				rx_dma_size * eth->soc->rx.desc_size,
-				&ring->phys, GFP_KERNEL);
-	} else {
-		struct mtk_tx_ring *tx_ring = &eth->tx_ring;
-
-		ring->dma = tx_ring->dma + tx_ring_size *
-			    eth->soc->tx.desc_size * (ring_no + 1);
-		ring->phys = tx_ring->phys + tx_ring_size *
-			     eth->soc->tx.desc_size * (ring_no + 1);
-	}
-
+	ring->dma = mtk_dma_ring_alloc(eth,
+				       rx_dma_size * eth->soc->rx.desc_size,
+				       &ring->phys,
+				       rx_flag == MTK_RX_FLAGS_NORMAL);
 	if (!ring->dma)
 		return -ENOMEM;
 
@@ -2777,10 +2926,9 @@ static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring, bool in_
 		ring->data = NULL;
 	}
 
-	if (!in_sram && ring->dma) {
-		dma_free_coherent(eth->dma_dev,
-				  ring->dma_size * eth->soc->rx.desc_size,
-				  ring->dma, ring->phys);
+	if (ring->dma) {
+		mtk_dma_ring_free(eth, ring->dma_size * eth->soc->rx.desc_size,
+				  ring->dma, ring->phys, in_sram);
 		ring->dma = NULL;
 	}
 
@@ -3135,20 +3283,29 @@ static int mtk_dma_init(struct mtk_eth *eth)
 static void mtk_dma_free(struct mtk_eth *eth)
 {
 	const struct mtk_soc_data *soc = eth->soc;
-	int i;
+	int i, j, txqs = 1;
 
-	for (i = 0; i < MTK_MAX_DEVS; i++)
-		if (eth->netdev[i])
-			netdev_reset_queue(eth->netdev[i]);
-	if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && eth->scratch_ring) {
-		dma_free_coherent(eth->dma_dev,
-				  MTK_QDMA_RING_SIZE * soc->tx.desc_size,
-				  eth->scratch_ring, eth->phy_scratch_ring);
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA))
+		txqs = MTK_QDMA_NUM_QUEUES;
+
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
+		if (!eth->netdev[i])
+			continue;
+
+		for (j = 0; j < txqs; j++)
+			netdev_tx_reset_subqueue(eth->netdev[i], j);
+	}
+
+	if (eth->scratch_ring) {
+		mtk_dma_ring_free(eth, soc->tx.fq_dma_size * soc->tx.desc_size,
+				  eth->scratch_ring, eth->phy_scratch_ring,
+				  true);
 		eth->scratch_ring = NULL;
 		eth->phy_scratch_ring = 0;
 	}
+
 	mtk_tx_clean(eth);
-	mtk_rx_clean(eth, &eth->rx_ring[0], MTK_HAS_CAPS(soc->caps, MTK_SRAM));
+	mtk_rx_clean(eth, &eth->rx_ring[0], true);
 	mtk_rx_clean(eth, &eth->rx_ring_qdma, false);
 
 	if (eth->hwlro) {
@@ -3189,6 +3346,53 @@ static void mtk_tx_timeout(struct net_device *dev, unsigned int txqueue)
 	schedule_work(&eth->pending_work);
 }
 
+static int mtk_get_irqs(struct platform_device *pdev, struct mtk_eth *eth)
+{
+	int i;
+
+	/* future SoCs beginning with MT7988 should use named IRQs in dts */
+	eth->irq[MTK_FE_IRQ_TX] = platform_get_irq_byname_optional(pdev, "fe1");
+	eth->irq[MTK_FE_IRQ_RX] = platform_get_irq_byname_optional(pdev, "fe2");
+	if (eth->irq[MTK_FE_IRQ_TX] >= 0 && eth->irq[MTK_FE_IRQ_RX] >= 0)
+		return 0;
+
+	/* only use legacy mode if platform_get_irq_byname_optional returned -ENXIO */
+	if (eth->irq[MTK_FE_IRQ_TX] != -ENXIO)
+		return dev_err_probe(&pdev->dev, eth->irq[MTK_FE_IRQ_TX],
+				     "Error requesting FE TX IRQ\n");
+
+	if (eth->irq[MTK_FE_IRQ_RX] != -ENXIO)
+		return dev_err_probe(&pdev->dev, eth->irq[MTK_FE_IRQ_RX],
+				     "Error requesting FE RX IRQ\n");
+
+	if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_INT))
+		dev_warn(&pdev->dev, "legacy DT: missing interrupt-names.");
+
+	/* legacy way:
+	 * On MTK_SHARED_INT SoCs (MT7621 + MT7628) the first IRQ is taken
+	 * from devicetree and used for both RX and TX - it is shared.
+	 * On SoCs with non-shared IRQs the first entry is not used,
+	 * the second is for TX, and the third is for RX.
+	 */
+	for (i = 0; i < MTK_FE_IRQ_NUM; i++) {
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_INT)) {
+			if (i == MTK_FE_IRQ_SHARED)
+				eth->irq[MTK_FE_IRQ_SHARED] = platform_get_irq(pdev, i);
+			else
+				eth->irq[i] = eth->irq[MTK_FE_IRQ_SHARED];
+		} else {
+			eth->irq[i] = platform_get_irq(pdev, i + 1);
+		}
+
+		if (eth->irq[i] < 0) {
+			dev_err(&pdev->dev, "no IRQ%d resource found\n", i);
+			return -ENXIO;
+		}
+	}
+
+	return 0;
+}
+
 static irqreturn_t mtk_handle_irq_rx(int irq, void *_eth)
 {
 	struct mtk_eth *eth = _eth;
@@ -3242,7 +3446,7 @@ static void mtk_poll_controller(struct net_device *dev)
 
 	mtk_tx_irq_disable(eth, MTK_TX_DONE_INT);
 	mtk_rx_irq_disable(eth, eth->soc->rx.irq_done_mask);
-	mtk_handle_irq_rx(eth->irq[2], dev);
+	mtk_handle_irq_rx(eth->irq[MTK_FE_IRQ_RX], dev);
 	mtk_tx_irq_enable(eth, MTK_TX_DONE_INT);
 	mtk_rx_irq_enable(eth, eth->soc->rx.irq_done_mask);
 }
@@ -3269,7 +3473,7 @@ static int mtk_start_dma(struct mtk_eth *eth)
 		if (mtk_is_netsys_v2_or_greater(eth))
 			val |= MTK_MUTLI_CNT | MTK_RESV_BUF |
 			       MTK_WCOMP_EN | MTK_DMAD_WR_WDONE |
-			       MTK_CHK_DDONE_EN | MTK_LEAKY_BUCKET_EN;
+			       MTK_CHK_DDONE_EN;
 		else
 			val |= MTK_RX_BT_32DWORDS;
 		mtk_w32(eth, val, reg_map->qdma.glo_cfg);
@@ -3414,9 +3618,6 @@ static int mtk_open(struct net_device *dev)
 			}
 			mtk_gdm_config(eth, target_mac->id, gdm_config);
 		}
-		/* Reset and enable PSE */
-		mtk_w32(eth, RST_GL_PSE, MTK_RST_GL);
-		mtk_w32(eth, 0, MTK_RST_GL);
 
 		napi_enable(&eth->tx_napi);
 		napi_enable(&eth->rx_napi);
@@ -3928,6 +4129,10 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	else
 		mtk_hw_reset(eth);
 
+	/* No MT7628/88 support yet */
+	if (reset && !MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
+		mtk_mdio_config(eth);
+
 	if (mtk_is_netsys_v3_or_greater(eth)) {
 		/* Set FE to PDMAv2 if necessary */
 		val = mtk_r32(eth, MTK_FE_GLO_MISC);
@@ -3988,11 +4193,27 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP);
 
 	if (mtk_is_netsys_v3_or_greater(eth)) {
-		/* PSE should not drop port1, port8 and port9 packets */
-		mtk_w32(eth, 0x00000302, PSE_DROP_CFG);
+		/* PSE dummy page mechanism */
+		mtk_w32(eth, PSE_DUMMY_WORK_GDM(1) | PSE_DUMMY_WORK_GDM(2) |
+			PSE_DUMMY_WORK_GDM(3) | DUMMY_PAGE_THR, PSE_DUMY_REQ);
+
+		/* PSE free buffer drop threshold */
+		mtk_w32(eth, 0x00600009, PSE_IQ_REV(8));
+
+		/* PSE should not drop port8, port9 and port13 packets from
+		 * WDMA Tx
+		 */
+		mtk_w32(eth, 0x00002300, PSE_DROP_CFG);
+
+		/* PSE should drop packets to port8, port9 and port13 on WDMA Rx
+		 * ring full
+		 */
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(0));
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(1));
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(2));
 
 		/* GDM and CDM Threshold */
-		mtk_w32(eth, 0x00000707, MTK_CDMW0_THRES);
+		mtk_w32(eth, 0x08000707, MTK_CDMW0_THRES);
 		mtk_w32(eth, 0x00000077, MTK_CDMW1_THRES);
 
 		/* Disable GDM1 RX CRC stripping */
@@ -4009,7 +4230,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 		mtk_w32(eth, 0x00000300, PSE_DROP_CFG);
 
 		/* PSE should drop packets to port 8/9 on WDMA Rx ring full */
-		mtk_w32(eth, 0x00000300, PSE_PPE0_DROP);
+		mtk_w32(eth, 0x00000300, PSE_PPE_DROP(0));
 
 		/* PSE Free Queue Flow Control  */
 		mtk_w32(eth, 0x01fa01f4, PSE_FQFC_CFG2);
@@ -4474,6 +4695,20 @@ static int mtk_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 	return phylink_ethtool_set_pauseparam(mac->phylink, pause);
 }
 
+static int mtk_get_eee(struct net_device *dev, struct ethtool_keee *eee)
+{
+	struct mtk_mac *mac = netdev_priv(dev);
+
+	return phylink_ethtool_get_eee(mac->phylink, eee);
+}
+
+static int mtk_set_eee(struct net_device *dev, struct ethtool_keee *eee)
+{
+	struct mtk_mac *mac = netdev_priv(dev);
+
+	return phylink_ethtool_set_eee(mac->phylink, eee);
+}
+
 static u16 mtk_select_queue(struct net_device *dev, struct sk_buff *skb,
 			    struct net_device *sb_dev)
 {
@@ -4506,6 +4741,8 @@ static const struct ethtool_ops mtk_ethtool_ops = {
 	.set_pauseparam		= mtk_set_pauseparam,
 	.get_rxnfc		= mtk_get_rxnfc,
 	.set_rxnfc		= mtk_set_rxnfc,
+	.get_eee		= mtk_get_eee,
+	.set_eee		= mtk_set_eee,
 };
 
 static const struct net_device_ops mtk_netdev_ops = {
@@ -4615,6 +4852,9 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	mac->phylink_config.type = PHYLINK_NETDEV;
 	mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 		MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD;
+	mac->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD |
+		MAC_2500FD;
+	mac->phylink_config.lpi_timer_default = 1000;
 
 	/* MT7623 gmac0 is now missing its speed-specific PLL configuration
 	 * in its .mac_config method (since state->speed is not valid there.
@@ -4653,7 +4893,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	}
 
 	if (mtk_is_netsys_v3_or_greater(mac->hw) &&
-	    MTK_HAS_CAPS(mac->hw->soc->caps, MTK_ESW_BIT) &&
+	    MTK_HAS_CAPS(mac->hw->soc->caps, MTK_ESW) &&
 	    id == MTK_GMAC1_ID) {
 		mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE |
 						       MAC_SYM_PAUSE |
@@ -4673,6 +4913,11 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 
 	mac->phylink = phylink;
 
+	if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_2P5GPHY) &&
+	    id == MTK_GMAC2_ID)
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  mac->phylink_config.supported_interfaces);
+
 	SET_NETDEV_DEV(eth->netdev[id], eth->dev);
 	eth->netdev[id]->watchdog_timeo = 5 * HZ;
 	eth->netdev[id]->netdev_ops = &mtk_netdev_ops;
@@ -4687,7 +4932,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	eth->netdev[id]->features |= eth->soc->hw_features;
 	eth->netdev[id]->ethtool_ops = &mtk_ethtool_ops;
 
-	eth->netdev[id]->irq = eth->irq[0];
+	eth->netdev[id]->irq = eth->irq[MTK_FE_IRQ_SHARED];
 	eth->netdev[id]->dev.of_node = np;
 
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
@@ -4730,7 +4975,7 @@ void mtk_eth_set_dma_device(struct mtk_eth *eth, struct device *dma_dev)
 		list_add_tail(&dev->close_list, &dev_list);
 	}
 
-	dev_close_many(&dev_list, false);
+	netif_close_many(&dev_list, false);
 
 	eth->dma_dev = dma_dev;
 
@@ -4772,9 +5017,30 @@ static int mtk_sgmii_init(struct mtk_eth *eth)
 	return 0;
 }
 
+static int mtk_setup_legacy_sram(struct mtk_eth *eth, struct resource *res)
+{
+	dev_warn(eth->dev, "legacy DT: using hard-coded SRAM offset.\n");
+
+	if (res->start + MTK_ETH_SRAM_OFFSET + MTK_ETH_NETSYS_V2_SRAM_SIZE - 1 >
+	    res->end)
+		return -EINVAL;
+
+	eth->sram_pool = devm_gen_pool_create(eth->dev,
+					      const_ilog2(MTK_ETH_SRAM_GRANULARITY),
+					      NUMA_NO_NODE, dev_name(eth->dev));
+
+	if (IS_ERR(eth->sram_pool))
+		return PTR_ERR(eth->sram_pool);
+
+	return gen_pool_add_virt(eth->sram_pool,
+				 (unsigned long)eth->base + MTK_ETH_SRAM_OFFSET,
+				 res->start + MTK_ETH_SRAM_OFFSET,
+				 MTK_ETH_NETSYS_V2_SRAM_SIZE, NUMA_NO_NODE);
+}
+
 static int mtk_probe(struct platform_device *pdev)
 {
-	struct resource *res = NULL, *res_sram;
+	struct resource *res = NULL;
 	struct device_node *mac_np;
 	struct mtk_eth *eth;
 	int err, i;
@@ -4794,20 +5060,6 @@ static int mtk_probe(struct platform_device *pdev)
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
 		eth->ip_align = NET_IP_ALIGN;
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SRAM)) {
-		/* SRAM is actual memory and supports transparent access just like DRAM.
-		 * Hence we don't require __iomem being set and don't need to use accessor
-		 * functions to read from or write to SRAM.
-		 */
-		if (mtk_is_netsys_v3_or_greater(eth)) {
-			eth->sram_base = (void __force *)devm_platform_ioremap_resource(pdev, 1);
-			if (IS_ERR(eth->sram_base))
-				return PTR_ERR(eth->sram_base);
-		} else {
-			eth->sram_base = (void __force *)eth->base + MTK_ETH_SRAM_OFFSET;
-		}
-	}
-
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) {
 		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(36));
 		if (!err)
@@ -4882,16 +5134,21 @@ static int mtk_probe(struct platform_device *pdev)
 			err = -EINVAL;
 			goto err_destroy_sgmii;
 		}
+
 		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SRAM)) {
-			if (mtk_is_netsys_v3_or_greater(eth)) {
-				res_sram = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-				if (!res_sram) {
+			eth->sram_pool = of_gen_pool_get(pdev->dev.of_node,
+							 "sram", 0);
+			if (!eth->sram_pool) {
+				if (!mtk_is_netsys_v3_or_greater(eth)) {
+					err = mtk_setup_legacy_sram(eth, res);
+					if (err)
+						goto err_destroy_sgmii;
+				} else {
+					dev_err(&pdev->dev,
+						"Could not get SRAM pool\n");
 					err = -EINVAL;
 					goto err_destroy_sgmii;
 				}
-				eth->phy_scratch_ring = res_sram->start;
-			} else {
-				eth->phy_scratch_ring = res->start + MTK_ETH_SRAM_OFFSET;
 			}
 		}
 	}
@@ -4917,17 +5174,10 @@ static int mtk_probe(struct platform_device *pdev)
 		}
 	}
 
-	for (i = 0; i < 3; i++) {
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_INT) && i > 0)
-			eth->irq[i] = eth->irq[0];
-		else
-			eth->irq[i] = platform_get_irq(pdev, i);
-		if (eth->irq[i] < 0) {
-			dev_err(&pdev->dev, "no IRQ%d resource found\n", i);
-			err = -ENXIO;
-			goto err_wed_exit;
-		}
-	}
+	err = mtk_get_irqs(pdev, eth);
+	if (err)
+		goto err_wed_exit;
+
 	for (i = 0; i < ARRAY_SIZE(eth->clks); i++) {
 		eth->clks[i] = devm_clk_get(eth->dev,
 					    mtk_clks_source_name[i]);
@@ -4971,17 +5221,17 @@ static int mtk_probe(struct platform_device *pdev)
 	}
 
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_INT)) {
-		err = devm_request_irq(eth->dev, eth->irq[0],
+		err = devm_request_irq(eth->dev, eth->irq[MTK_FE_IRQ_SHARED],
 				       mtk_handle_irq, 0,
 				       dev_name(eth->dev), eth);
 	} else {
-		err = devm_request_irq(eth->dev, eth->irq[1],
+		err = devm_request_irq(eth->dev, eth->irq[MTK_FE_IRQ_TX],
 				       mtk_handle_irq_tx, 0,
 				       dev_name(eth->dev), eth);
 		if (err)
 			goto err_free_dev;
 
-		err = devm_request_irq(eth->dev, eth->irq[2],
+		err = devm_request_irq(eth->dev, eth->irq[MTK_FE_IRQ_RX],
 				       mtk_handle_irq_rx, 0,
 				       dev_name(eth->dev), eth);
 	}
@@ -5027,7 +5277,7 @@ static int mtk_probe(struct platform_device *pdev)
 		} else
 			netif_info(eth, probe, eth->netdev[i],
 				   "mediatek frame engine at 0x%08lx, irq %d\n",
-				   eth->netdev[i]->base_addr, eth->irq[0]);
+				   eth->netdev[i]->base_addr, eth->irq[MTK_FE_IRQ_SHARED]);
 	}
 
 	/* we run 2 devices on the same DMA ring so we need a dummy device
@@ -5368,3 +5618,4 @@ module_platform_driver(mtk_driver);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
 MODULE_DESCRIPTION("Ethernet driver for MediaTek SoC");
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 0d5225f1d3ee..0168e2fbc619 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -141,8 +141,10 @@
 #define MTK_GDMA_MAC_ADRH(x)	({ typeof(x) _x = (x); (_x == MTK_GMAC3_ID) ?	\
 				   0x54C : 0x50C + (_x * 0x1000); })
 
-/* Internal SRAM offset */
-#define MTK_ETH_SRAM_OFFSET	0x40000
+/* legacy DT support for internal SRAM */
+#define MTK_ETH_SRAM_OFFSET		0x40000
+#define MTK_ETH_SRAM_GRANULARITY	32
+#define MTK_ETH_NETSYS_V2_SRAM_SIZE	0x40000
 
 /* FE global misc reg*/
 #define MTK_FE_GLO_MISC         0x124
@@ -151,7 +153,15 @@
 #define PSE_FQFC_CFG1		0x100
 #define PSE_FQFC_CFG2		0x104
 #define PSE_DROP_CFG		0x108
-#define PSE_PPE0_DROP		0x110
+#define PSE_PPE_DROP(x)		(0x110 + ((x) * 0x4))
+
+/* PSE Last FreeQ Page Request Control */
+#define PSE_DUMY_REQ		0x10C
+/* PSE_DUMY_REQ is not a typo but actually called like that also in
+ * MediaTek's datasheet
+ */
+#define PSE_DUMMY_WORK_GDM(x)	BIT(16 + (x))
+#define DUMMY_PAGE_THR		0x1
 
 /* PSE Input Queue Reservation Register*/
 #define PSE_IQ_REV(x)		(0x140 + (((x) - 1) << 2))
@@ -423,7 +433,8 @@
 
 /* XMAC status registers */
 #define MTK_XGMAC_STS(x)	(((x) == MTK_GMAC3_ID) ? 0x1001C : 0x1000C)
-#define MTK_XGMAC_FORCE_LINK(x)	(((x) == MTK_GMAC2_ID) ? BIT(31) : BIT(15))
+#define MTK_XGMAC_FORCE_MODE(x)	(((x) == MTK_GMAC2_ID) ? BIT(31) : BIT(15))
+#define MTK_XGMAC_FORCE_LINK(x)	(((x) == MTK_GMAC2_ID) ? BIT(27) : BIT(11))
 #define MTK_USXGMII_PCS_LINK	BIT(8)
 #define MTK_XGMAC_RX_FC		BIT(5)
 #define MTK_XGMAC_TX_FC		BIT(4)
@@ -453,6 +464,8 @@
 #define MAC_MCR_RX_FIFO_CLR_DIS	BIT(12)
 #define MAC_MCR_BACKOFF_EN	BIT(9)
 #define MAC_MCR_BACKPR_EN	BIT(8)
+#define MAC_MCR_EEE1G		BIT(7)
+#define MAC_MCR_EEE100M		BIT(6)
 #define MAC_MCR_FORCE_RX_FC	BIT(5)
 #define MAC_MCR_FORCE_TX_FC	BIT(4)
 #define MAC_MCR_SPEED_1000	BIT(3)
@@ -461,6 +474,15 @@
 #define MAC_MCR_FORCE_LINK	BIT(0)
 #define MAC_MCR_FORCE_LINK_DOWN	(MAC_MCR_FORCE_MODE)
 
+/* Mac EEE control registers */
+#define MTK_MAC_EEECR(x)		(0x10104 + (x * 0x100))
+#define MAC_EEE_WAKEUP_TIME_1000	GENMASK(31, 24)
+#define MAC_EEE_WAKEUP_TIME_100		GENMASK(23, 16)
+#define MAC_EEE_LPI_TXIDLE_THD		GENMASK(15, 8)
+#define MAC_EEE_CKG_TXIDLE		BIT(3)
+#define MAC_EEE_CKG_RXLPI		BIT(2)
+#define MAC_EEE_LPI_MODE		BIT(0)
+
 /* Mac status registers */
 #define MTK_MAC_MSR(x)		(0x10108 + (x * 0x100))
 #define MAC_MSR_EEE1G		BIT(7)
@@ -505,6 +527,21 @@
 #define INTF_MODE_RGMII_1000    (TRGMII_MODE | TRGMII_CENTRAL_ALIGNED)
 #define INTF_MODE_RGMII_10_100  0
 
+/* XFI Mac control registers */
+#define MTK_XMAC_BASE(x)	(0x12000 + (((x) - 1) * 0x1000))
+#define MTK_XMAC_MCR(x)		(MTK_XMAC_BASE(x))
+#define XMAC_MCR_TRX_DISABLE	0xf
+#define XMAC_MCR_FORCE_TX_FC	BIT(5)
+#define XMAC_MCR_FORCE_RX_FC	BIT(4)
+
+/* XFI Mac logic reset registers */
+#define MTK_XMAC_LOGIC_RST(x)	(MTK_XMAC_BASE(x) + 0x10)
+#define XMAC_LOGIC_RST		BIT(0)
+
+/* XFI Mac count global control */
+#define MTK_XMAC_CNT_CTRL(x)	(MTK_XMAC_BASE(x) + 0x100)
+#define XMAC_GLB_CNTCLR		BIT(0)
+
 /* GPIO port control registers for GMAC 2*/
 #define GPIO_OD33_CTRL8		0x4c0
 #define GPIO_BIAS_CTRL		0xed0
@@ -568,6 +605,10 @@
 #define GEPHY_MAC_SEL          BIT(1)
 
 /* Top misc registers */
+#define TOP_MISC_NETSYS_PCS_MUX	0x0
+#define NETSYS_PCS_MUX_MASK	GENMASK(1, 0)
+#define MUX_G2_USXGMII_SEL	BIT(1)
+
 #define USB_PHY_SWITCH_REG	0x218
 #define QPHY_SEL_MASK		GENMASK(1, 0)
 #define SGMII_QPHY_SEL		0x2
@@ -603,6 +644,11 @@
 
 #define MTK_MAC_FSM(x)		(0x1010C + ((x) * 0x100))
 
+#define MTK_FE_IRQ_SHARED	0
+#define MTK_FE_IRQ_TX		0
+#define MTK_FE_IRQ_RX		1
+#define MTK_FE_IRQ_NUM		(MTK_FE_IRQ_RX + 1)
+
 struct mtk_rx_dma {
 	unsigned int rxd1;
 	unsigned int rxd2;
@@ -932,6 +978,7 @@ enum mkt_eth_capabilities {
 	MTK_RGMII_BIT = 0,
 	MTK_TRGMII_BIT,
 	MTK_SGMII_BIT,
+	MTK_2P5GPHY_BIT,
 	MTK_ESW_BIT,
 	MTK_GEPHY_BIT,
 	MTK_MUX_BIT,
@@ -952,6 +999,7 @@ enum mkt_eth_capabilities {
 	MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT,
 	MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY_BIT,
 	MTK_ETH_MUX_U3_GMAC2_TO_QPHY_BIT,
+	MTK_ETH_MUX_GMAC2_TO_2P5GPHY_BIT,
 	MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII_BIT,
 	MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII_BIT,
 
@@ -961,6 +1009,7 @@ enum mkt_eth_capabilities {
 	MTK_ETH_PATH_GMAC1_SGMII_BIT,
 	MTK_ETH_PATH_GMAC2_RGMII_BIT,
 	MTK_ETH_PATH_GMAC2_SGMII_BIT,
+	MTK_ETH_PATH_GMAC2_2P5GPHY_BIT,
 	MTK_ETH_PATH_GMAC2_GEPHY_BIT,
 	MTK_ETH_PATH_GDM1_ESW_BIT,
 };
@@ -969,6 +1018,7 @@ enum mkt_eth_capabilities {
 #define MTK_RGMII		BIT_ULL(MTK_RGMII_BIT)
 #define MTK_TRGMII		BIT_ULL(MTK_TRGMII_BIT)
 #define MTK_SGMII		BIT_ULL(MTK_SGMII_BIT)
+#define MTK_2P5GPHY		BIT_ULL(MTK_2P5GPHY_BIT)
 #define MTK_ESW			BIT_ULL(MTK_ESW_BIT)
 #define MTK_GEPHY		BIT_ULL(MTK_GEPHY_BIT)
 #define MTK_MUX			BIT_ULL(MTK_MUX_BIT)
@@ -991,6 +1041,8 @@ enum mkt_eth_capabilities {
 	BIT_ULL(MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY_BIT)
 #define MTK_ETH_MUX_U3_GMAC2_TO_QPHY		\
 	BIT_ULL(MTK_ETH_MUX_U3_GMAC2_TO_QPHY_BIT)
+#define MTK_ETH_MUX_GMAC2_TO_2P5GPHY		\
+	BIT_ULL(MTK_ETH_MUX_GMAC2_TO_2P5GPHY_BIT)
 #define MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII	\
 	BIT_ULL(MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII_BIT)
 #define MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII	\
@@ -1002,6 +1054,7 @@ enum mkt_eth_capabilities {
 #define MTK_ETH_PATH_GMAC1_SGMII	BIT_ULL(MTK_ETH_PATH_GMAC1_SGMII_BIT)
 #define MTK_ETH_PATH_GMAC2_RGMII	BIT_ULL(MTK_ETH_PATH_GMAC2_RGMII_BIT)
 #define MTK_ETH_PATH_GMAC2_SGMII	BIT_ULL(MTK_ETH_PATH_GMAC2_SGMII_BIT)
+#define MTK_ETH_PATH_GMAC2_2P5GPHY	BIT_ULL(MTK_ETH_PATH_GMAC2_2P5GPHY_BIT)
 #define MTK_ETH_PATH_GMAC2_GEPHY	BIT_ULL(MTK_ETH_PATH_GMAC2_GEPHY_BIT)
 #define MTK_ETH_PATH_GDM1_ESW		BIT_ULL(MTK_ETH_PATH_GDM1_ESW_BIT)
 
@@ -1011,6 +1064,7 @@ enum mkt_eth_capabilities {
 #define MTK_GMAC2_RGMII		(MTK_ETH_PATH_GMAC2_RGMII | MTK_RGMII)
 #define MTK_GMAC2_SGMII		(MTK_ETH_PATH_GMAC2_SGMII | MTK_SGMII)
 #define MTK_GMAC2_GEPHY		(MTK_ETH_PATH_GMAC2_GEPHY | MTK_GEPHY)
+#define MTK_GMAC2_2P5GPHY	(MTK_ETH_PATH_GMAC2_2P5GPHY | MTK_2P5GPHY)
 #define MTK_GDM1_ESW		(MTK_ETH_PATH_GDM1_ESW | MTK_ESW)
 
 /* MUXes present on SoCs */
@@ -1030,6 +1084,10 @@ enum mkt_eth_capabilities {
 	(MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII | MTK_MUX | \
 	MTK_SHARED_SGMII)
 
+/* 2: GMAC2 -> 2P5GPHY */
+#define MTK_MUX_GMAC2_TO_2P5GPHY      \
+	(MTK_ETH_MUX_GMAC2_TO_2P5GPHY | MTK_MUX | MTK_INFRA)
+
 /* 0: GMACx -> GEPHY, 1: GMACx -> SGMII where x is 1 or 2 */
 #define MTK_MUX_GMAC12_TO_GEPHY_SGMII   \
 	(MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII | MTK_MUX)
@@ -1065,8 +1123,9 @@ enum mkt_eth_capabilities {
 		      MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \
 		      MTK_RSTCTRL_PPE1 | MTK_SRAM)
 
-#define MT7988_CAPS  (MTK_36BIT_DMA | MTK_GDM1_ESW | MTK_QDMA | \
-		      MTK_RSTCTRL_PPE1 | MTK_RSTCTRL_PPE2 | MTK_SRAM)
+#define MT7988_CAPS  (MTK_36BIT_DMA | MTK_GDM1_ESW | MTK_GMAC2_2P5GPHY | \
+		      MTK_MUX_GMAC2_TO_2P5GPHY | MTK_QDMA | MTK_RSTCTRL_PPE1 | \
+		      MTK_RSTCTRL_PPE2 | MTK_SRAM)
 
 struct mtk_tx_dma_desc_info {
 	dma_addr_t	addr;
@@ -1126,7 +1185,7 @@ struct mtk_reg_map {
 };
 
 /* struct mtk_eth_data -	This is the structure holding all differences
- *				among various plaforms
+ *				among various platforms
  * @reg_map			Soc register map.
  * @ana_rgc3:                   The offset for register ANA_RGC3 related to
  *				sgmiisys syscon
@@ -1186,8 +1245,9 @@ struct mtk_soc_data {
 /* struct mtk_eth -	This is the main datasructure for holding the state
  *			of the driver
  * @dev:		The device pointer
- * @dev:		The device pointer used for dma mapping/alloc
+ * @dma_dev:		The device pointer used for dma mapping/alloc
  * @base:		The mapped register i/o base
+ * @sram_pool:		Pointer to SRAM pool used for DMA descriptor rings
  * @page_lock:		Make sure that register operations are atomic
  * @tx_irq__lock:	Make sure that IRQ register operations are atomic
  * @rx_irq__lock:	Make sure that IRQ register operations are atomic
@@ -1226,21 +1286,21 @@ struct mtk_soc_data {
  * @mii_bus:		If there is a bus we need to create an instance for it
  * @pending_work:	The workqueue used to reset the dma ring
  * @state:		Initialization and runtime state of the device
- * @soc:		Holding specific data among vaious SoCs
+ * @soc:		Holding specific data among various SoCs
  */
 
 struct mtk_eth {
 	struct device			*dev;
 	struct device			*dma_dev;
 	void __iomem			*base;
-	void				*sram_base;
+	struct gen_pool			*sram_pool;
 	spinlock_t			page_lock;
 	spinlock_t			tx_irq_lock;
 	spinlock_t			rx_irq_lock;
 	struct net_device		*dummy_dev;
 	struct net_device		*netdev[MTK_MAX_DEVS];
 	struct mtk_mac			*mac[MTK_MAX_DEVS];
-	int				irq[3];
+	int				irq[MTK_FE_IRQ_NUM];
 	u32				msg_enable;
 	unsigned long			sysclk;
 	struct regmap			*ethsys;
@@ -1260,6 +1320,7 @@ struct mtk_eth {
 	struct clk			*clks[MTK_CLK_MAX];
 
 	struct mii_bus			*mii_bus;
+	unsigned int			mdc_divider;
 	struct work_struct		pending_work;
 	unsigned long			state;
 
@@ -1417,6 +1478,23 @@ static inline u32 mtk_get_ib2_multicast_mask(struct mtk_eth *eth)
 	return MTK_FOE_IB2_MULTICAST;
 }
 
+static inline bool mtk_interface_mode_is_xgmii(struct mtk_eth *eth,
+					       phy_interface_t interface)
+{
+	if (!mtk_is_netsys_v3_or_greater(eth))
+		return false;
+
+	switch (interface) {
+	case PHY_INTERFACE_MODE_INTERNAL:
+	case PHY_INTERFACE_MODE_USXGMII:
+	case PHY_INTERFACE_MODE_10GBASER:
+	case PHY_INTERFACE_MODE_5GBASER:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /* read the hardware status register */
 void mtk_stats_update_mac(struct mtk_mac *mac);
 
@@ -1425,6 +1503,7 @@ u32 mtk_r32(struct mtk_eth *eth, unsigned reg);
 u32 mtk_m32(struct mtk_eth *eth, u32 mask, u32 set, unsigned int reg);
 
 int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id);
+int mtk_gmac_2p5gphy_path_setup(struct mtk_eth *eth, int mac_id);
 int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id);
 int mtk_gmac_rgmii_path_setup(struct mtk_eth *eth, int mac_id);
 
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
index f20bb390df3a..e9bd32741983 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -34,8 +34,10 @@ struct mtk_flow_data {
 	u16 vlan_in;
 
 	struct {
-		u16 id;
-		__be16 proto;
+		struct {
+			u16 id;
+			__be16 proto;
+		} vlans[2];
 		u8 num;
 	} vlan;
 	struct {
@@ -99,7 +101,9 @@ mtk_flow_get_wdma_info(struct net_device *dev, const u8 *addr, struct mtk_wdma_i
 	if (!IS_ENABLED(CONFIG_NET_MEDIATEK_SOC_WED))
 		return -1;
 
+	rcu_read_lock();
 	err = dev_fill_forward_path(dev, addr, &stack);
+	rcu_read_unlock();
 	if (err)
 		return err;
 
@@ -349,18 +353,19 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 		case FLOW_ACTION_CSUM:
 			break;
 		case FLOW_ACTION_VLAN_PUSH:
-			if (data.vlan.num == 1 ||
+			if (data.vlan.num + data.pppoe.num == 2 ||
 			    act->vlan.proto != htons(ETH_P_8021Q))
 				return -EOPNOTSUPP;
 
-			data.vlan.id = act->vlan.vid;
-			data.vlan.proto = act->vlan.proto;
+			data.vlan.vlans[data.vlan.num].id = act->vlan.vid;
+			data.vlan.vlans[data.vlan.num].proto = act->vlan.proto;
 			data.vlan.num++;
 			break;
 		case FLOW_ACTION_VLAN_POP:
 			break;
 		case FLOW_ACTION_PPPOE_PUSH:
-			if (data.pppoe.num == 1)
+			if (data.pppoe.num == 1 ||
+			    data.vlan.num == 2)
 				return -EOPNOTSUPP;
 
 			data.pppoe.sid = act->pppoe.sid;
@@ -450,12 +455,9 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 	if (offload_type == MTK_PPE_PKT_TYPE_BRIDGE)
 		foe.bridge.vlan = data.vlan_in;
 
-	if (data.vlan.num == 1) {
-		if (data.vlan.proto != htons(ETH_P_8021Q))
-			return -EOPNOTSUPP;
+	for (i = 0; i < data.vlan.num; i++)
+		mtk_foe_entry_set_vlan(eth, &foe, data.vlan.vlans[i].id);
 
-		mtk_foe_entry_set_vlan(eth, &foe, data.vlan.id);
-	}
 	if (data.pppoe.num == 1)
 		mtk_foe_entry_set_pppoe(eth, &foe, data.pppoe.sid);
 
diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 25989c79c92e..b83886a41121 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -1163,6 +1163,7 @@ static int mtk_star_tx_poll(struct napi_struct *napi, int budget)
 	struct net_device *ndev = priv->ndev;
 	unsigned int head = ring->head;
 	unsigned int entry = ring->tail;
+	unsigned long flags;
 
 	while (entry != head && count < (MTK_STAR_RING_NUM_DESCS - 1)) {
 		ret = mtk_star_tx_complete_one(priv);
@@ -1182,9 +1183,9 @@ static int mtk_star_tx_poll(struct napi_struct *napi, int budget)
 		netif_wake_queue(ndev);
 
 	if (napi_complete(napi)) {
-		spin_lock(&priv->lock);
+		spin_lock_irqsave(&priv->lock, flags);
 		mtk_star_enable_dma_irq(priv, false, true);
-		spin_unlock(&priv->lock);
+		spin_unlock_irqrestore(&priv->lock, flags);
 	}
 
 	return 0;
@@ -1341,16 +1342,16 @@ push_new_skb:
 static int mtk_star_rx_poll(struct napi_struct *napi, int budget)
 {
 	struct mtk_star_priv *priv;
+	unsigned long flags;
 	int work_done = 0;
 
 	priv = container_of(napi, struct mtk_star_priv, rx_napi);
 
 	work_done = mtk_star_rx(priv, budget);
-	if (work_done < budget) {
-		napi_complete_done(napi, work_done);
-		spin_lock(&priv->lock);
+	if (work_done < budget && napi_complete_done(napi, work_done)) {
+		spin_lock_irqsave(&priv->lock, flags);
 		mtk_star_enable_dma_irq(priv, true, false);
-		spin_unlock(&priv->lock);
+		spin_unlock_irqrestore(&priv->lock, flags);
 	}
 
 	return work_done;
@@ -1427,15 +1428,10 @@ static int mtk_star_mdio_init(struct net_device *ndev)
 
 	of_node = dev->of_node;
 
-	mdio_node = of_get_child_by_name(of_node, "mdio");
+	mdio_node = of_get_available_child_by_name(of_node, "mdio");
 	if (!mdio_node)
 		return -ENODEV;
 
-	if (!of_device_is_available(mdio_node)) {
-		ret = -ENODEV;
-		goto out_put_node;
-	}
-
 	priv->mii = devm_mdiobus_alloc(dev);
 	if (!priv->mii) {
 		ret = -ENOMEM;
@@ -1467,6 +1463,8 @@ static __maybe_unused int mtk_star_suspend(struct device *dev)
 	if (netif_running(ndev))
 		mtk_star_disable(ndev);
 
+	netif_device_detach(ndev);
+
 	clk_bulk_disable_unprepare(MTK_STAR_NCLKS, priv->clks);
 
 	return 0;
@@ -1491,6 +1489,8 @@ static __maybe_unused int mtk_star_resume(struct device *dev)
 			clk_bulk_disable_unprepare(MTK_STAR_NCLKS, priv->clks);
 	}
 
+	netif_device_attach(ndev);
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
index e212a4ba9275..1ed1f88dd7f8 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed.c
@@ -59,7 +59,9 @@ struct mtk_wed_flow_block_priv {
 static const struct mtk_wed_soc_data mt7622_data = {
 	.regmap = {
 		.tx_bm_tkid		= 0x088,
-		.wpdma_rx_ring0		= 0x770,
+		.wpdma_rx_ring = {
+			0x770,
+		},
 		.reset_idx_tx_mask	= GENMASK(3, 0),
 		.reset_idx_rx_mask	= GENMASK(17, 16),
 	},
@@ -70,7 +72,9 @@ static const struct mtk_wed_soc_data mt7622_data = {
 static const struct mtk_wed_soc_data mt7986_data = {
 	.regmap = {
 		.tx_bm_tkid		= 0x0c8,
-		.wpdma_rx_ring0		= 0x770,
+		.wpdma_rx_ring = {
+			0x770,
+		},
 		.reset_idx_tx_mask	= GENMASK(1, 0),
 		.reset_idx_rx_mask	= GENMASK(7, 6),
 	},
@@ -81,7 +85,10 @@ static const struct mtk_wed_soc_data mt7986_data = {
 static const struct mtk_wed_soc_data mt7988_data = {
 	.regmap = {
 		.tx_bm_tkid		= 0x0c8,
-		.wpdma_rx_ring0		= 0x7d0,
+		.wpdma_rx_ring = {
+			0x7d0,
+			0x7d8,
+		},
 		.reset_idx_tx_mask	= GENMASK(1, 0),
 		.reset_idx_rx_mask	= GENMASK(7, 6),
 	},
@@ -621,8 +628,8 @@ mtk_wed_amsdu_init(struct mtk_wed_device *dev)
 		return ret;
 	}
 
-	/* eagle E1 PCIE1 tx ring 22 flow control issue */
-	if (dev->wlan.id == 0x7991)
+	/* Kite and Eagle E1 PCIE1 tx ring 22 flow control issue */
+	if (dev->wlan.id == 0x7991 || dev->wlan.id == 0x7992)
 		wed_clr(dev, MTK_WED_AMSDU_FIFO, MTK_WED_AMSDU_IS_PRIOR0_RING);
 
 	wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_TX_AMSDU_EN);
@@ -670,7 +677,7 @@ mtk_wed_tx_buffer_alloc(struct mtk_wed_device *dev)
 		void *buf;
 		int s;
 
-		page = __dev_alloc_page(GFP_KERNEL);
+		page = __dev_alloc_page(GFP_KERNEL | GFP_DMA32);
 		if (!page)
 			return -ENOMEM;
 
@@ -793,7 +800,7 @@ mtk_wed_hwrro_buffer_alloc(struct mtk_wed_device *dev)
 		struct page *page;
 		int s;
 
-		page = __dev_alloc_page(GFP_KERNEL);
+		page = __dev_alloc_page(GFP_KERNEL | GFP_DMA32);
 		if (!page)
 			return -ENOMEM;
 
@@ -1239,7 +1246,11 @@ mtk_wed_set_wpdma(struct mtk_wed_device *dev)
 		return;
 
 	wed_w32(dev, MTK_WED_WPDMA_RX_GLO_CFG, dev->wlan.wpdma_rx_glo);
-	wed_w32(dev, dev->hw->soc->regmap.wpdma_rx_ring0, dev->wlan.wpdma_rx);
+	wed_w32(dev, dev->hw->soc->regmap.wpdma_rx_ring[0],
+		dev->wlan.wpdma_rx[0]);
+	if (mtk_wed_is_v3_or_greater(dev->hw))
+		wed_w32(dev, dev->hw->soc->regmap.wpdma_rx_ring[1],
+			dev->wlan.wpdma_rx[1]);
 
 	if (!dev->wlan.hw_rro)
 		return;
@@ -1318,26 +1329,14 @@ mtk_wed_rro_ring_alloc(struct mtk_wed_device *dev, struct mtk_wed_ring *ring,
 static int
 mtk_wed_rro_alloc(struct mtk_wed_device *dev)
 {
-	struct reserved_mem *rmem;
-	struct device_node *np;
-	int index;
-
-	index = of_property_match_string(dev->hw->node, "memory-region-names",
-					 "wo-dlm");
-	if (index < 0)
-		return index;
+	struct resource res;
+	int ret;
 
-	np = of_parse_phandle(dev->hw->node, "memory-region", index);
-	if (!np)
-		return -ENODEV;
-
-	rmem = of_reserved_mem_lookup(np);
-	of_node_put(np);
-
-	if (!rmem)
-		return -ENODEV;
+	ret = of_reserved_mem_region_to_resource_byname(dev->hw->node, "wo-dlm", &res);
+	if (ret)
+		return ret;
 
-	dev->rro.miod_phys = rmem->base;
+	dev->rro.miod_phys = res.start;
 	dev->rro.fdbk_phys = MTK_WED_MIOD_COUNT + dev->rro.miod_phys;
 
 	return mtk_wed_rro_ring_alloc(dev, &dev->rro.ring,
@@ -2000,7 +1999,7 @@ mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask)
 		if (mtk_wed_is_v3_or_greater(dev->hw))
 			wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_TX_TKID_ALI_EN);
 
-		/* initail tx interrupt trigger */
+		/* initial tx interrupt trigger */
 		wed_w32(dev, MTK_WED_WPDMA_INT_CTRL_TX,
 			MTK_WED_WPDMA_INT_CTRL_TX0_DONE_EN |
 			MTK_WED_WPDMA_INT_CTRL_TX0_DONE_CLR |
@@ -2011,7 +2010,7 @@ mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask)
 			FIELD_PREP(MTK_WED_WPDMA_INT_CTRL_TX1_DONE_TRIG,
 				   dev->wlan.tx_tbit[1]));
 
-		/* initail txfree interrupt trigger */
+		/* initial txfree interrupt trigger */
 		wed_w32(dev, MTK_WED_WPDMA_INT_CTRL_TX_FREE,
 			MTK_WED_WPDMA_INT_CTRL_TX_FREE_DONE_EN |
 			MTK_WED_WPDMA_INT_CTRL_TX_FREE_DONE_CLR |
@@ -2335,6 +2334,16 @@ mtk_wed_start(struct mtk_wed_device *dev, u32 irq_mask)
 		if (!dev->rx_wdma[i].desc)
 			mtk_wed_wdma_rx_ring_setup(dev, i, 16, false);
 
+	if (dev->wlan.hw_rro) {
+		for (i = 0; i < MTK_WED_RX_PAGE_QUEUES; i++) {
+			u32 addr = MTK_WED_RRO_MSDU_PG_CTRL0(i) +
+				   MTK_WED_RING_OFS_COUNT;
+
+			if (!wed_r32(dev, addr))
+				wed_w32(dev, addr, 1);
+		}
+	}
+
 	mtk_wed_hw_init(dev);
 	mtk_wed_configure_irq(dev, irq_mask);
 
@@ -2417,6 +2426,10 @@ mtk_wed_attach(struct mtk_wed_device *dev)
 	dev->version = hw->version;
 	dev->hw->pcie_base = mtk_wed_get_pcie_base(dev);
 
+	ret = dma_set_mask_and_coherent(hw->dev, DMA_BIT_MASK(32));
+	if (ret)
+		goto out;
+
 	if (hw->eth->dma_dev == hw->eth->dev &&
 	    of_dma_is_coherent(hw->eth->dev->of_node))
 		mtk_eth_set_dma_device(hw->eth, hw->dev);
@@ -2794,7 +2807,6 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth,
 	if (!pdev)
 		goto err_of_node_put;
 
-	get_device(&pdev->dev);
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
 		goto err_put_device;
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.h b/drivers/net/ethernet/mediatek/mtk_wed.h
index c1f0479d7a71..b49aee9a8b65 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.h
+++ b/drivers/net/ethernet/mediatek/mtk_wed.h
@@ -17,7 +17,7 @@ struct mtk_wed_wo;
 struct mtk_wed_soc_data {
 	struct {
 		u32 tx_bm_tkid;
-		u32 wpdma_rx_ring0;
+		u32 wpdma_rx_ring[MTK_WED_RX_QUEUES];
 		u32 reset_idx_tx_mask;
 		u32 reset_idx_rx_mask;
 	} regmap;
diff --git a/drivers/net/ethernet/mediatek/mtk_wed_mcu.c b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c
index c06e5ad18b01..fa6b21603416 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed_mcu.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c
@@ -234,27 +234,23 @@ int mtk_wed_mcu_msg_update(struct mtk_wed_device *dev, int id, void *data,
 }
 
 static int
-mtk_wed_get_memory_region(struct mtk_wed_hw *hw, int index,
+mtk_wed_get_memory_region(struct mtk_wed_hw *hw, const char *name,
 			  struct mtk_wed_wo_memory_region *region)
 {
-	struct reserved_mem *rmem;
-	struct device_node *np;
-
-	np = of_parse_phandle(hw->node, "memory-region", index);
-	if (!np)
-		return -ENODEV;
-
-	rmem = of_reserved_mem_lookup(np);
-	of_node_put(np);
+	struct resource res;
+	int ret;
 
-	if (!rmem)
-		return -ENODEV;
+	ret = of_reserved_mem_region_to_resource_byname(hw->node, name, &res);
+	if (ret)
+		return 0;
 
-	region->phy_addr = rmem->base;
-	region->size = rmem->size;
-	region->addr = devm_ioremap(hw->dev, region->phy_addr, region->size);
+	region->phy_addr = res.start;
+	region->size = resource_size(&res);
+	region->addr = devm_ioremap_resource(hw->dev, &res);
+	if (IS_ERR(region->addr))
+		return PTR_ERR(region->addr);
 
-	return !region->addr ? -EINVAL : 0;
+	return 0;
 }
 
 static int
@@ -319,13 +315,7 @@ mtk_wed_mcu_load_firmware(struct mtk_wed_wo *wo)
 
 	/* load firmware region metadata */
 	for (i = 0; i < ARRAY_SIZE(mem_region); i++) {
-		int index = of_property_match_string(wo->hw->node,
-						     "memory-region-names",
-						     mem_region[i].name);
-		if (index < 0)
-			continue;
-
-		ret = mtk_wed_get_memory_region(wo->hw, index, &mem_region[i]);
+		ret = mtk_wed_get_memory_region(wo->hw, mem_region[i].name, &mem_region[i]);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig
index 825e05fb8607..0b1cb340206f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig
@@ -7,6 +7,7 @@ config MLX4_EN
 	tristate "Mellanox Technologies 1/10/40Gbit Ethernet support"
 	depends on PCI && NETDEVICES && ETHERNET && INET
 	depends on PTP_1588_CLOCK_OPTIONAL
+	select PAGE_POOL
 	select MLX4_CORE
 	help
 	  This driver supports Mellanox Technologies ConnectX Ethernet
diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index b330020dc0d6..07b061a97a6e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -526,28 +526,6 @@ out:
 	return res;
 }
 
-u32 mlx4_zone_free_entries(struct mlx4_zone_allocator *zones, u32 uid, u32 obj, u32 count)
-{
-	struct mlx4_zone_entry *zone;
-	int res = 0;
-
-	spin_lock(&zones->lock);
-
-	zone = __mlx4_find_zone_by_uid(zones, uid);
-
-	if (NULL == zone) {
-		res = -1;
-		goto out;
-	}
-
-	__mlx4_free_from_zone(zone, obj, count);
-
-out:
-	spin_unlock(&zones->lock);
-
-	return res;
-}
-
 u32 mlx4_zone_free_entries_unique(struct mlx4_zone_allocator *zones, u32 obj, u32 count)
 {
 	struct mlx4_zone_entry *zone;
@@ -682,9 +660,9 @@ static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device)
 }
 
 static int mlx4_alloc_db_from_pgdir(struct mlx4_db_pgdir *pgdir,
-				    struct mlx4_db *db, int order)
+				    struct mlx4_db *db, unsigned int order)
 {
-	int o;
+	unsigned int o;
 	int i;
 
 	for (o = order; o <= 1; ++o) {
@@ -712,7 +690,7 @@ found:
 	return 0;
 }
 
-int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order)
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, unsigned int order)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_db_pgdir *pgdir;
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 0d8a362c2673..edcc6f662618 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -236,7 +236,7 @@ static void dump_err_buf(struct mlx4_dev *dev)
 
 static void poll_catas(struct timer_list *t)
 {
-	struct mlx4_priv *priv = from_timer(priv, t, catas_err.timer);
+	struct mlx4_priv *priv = timer_container_of(priv, t, catas_err.timer);
 	struct mlx4_dev *dev = &priv->dev;
 	u32 slave_read;
 
@@ -305,7 +305,7 @@ void mlx4_stop_catas_poll(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
-	del_timer_sync(&priv->catas_err.timer);
+	timer_delete_sync(&priv->catas_err.timer);
 
 	if (priv->catas_err.map) {
 		iounmap(priv->catas_err.map);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index cd754cd76bde..2aeaafcfb993 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -38,7 +38,7 @@
 
 /* mlx4_en_read_clock - read raw cycle counter (to be used by time counter)
  */
-static u64 mlx4_en_read_clock(const struct cyclecounter *tc)
+static u64 mlx4_en_read_clock(struct cyclecounter *tc)
 {
 	struct mlx4_en_dev *mdev =
 		container_of(tc, struct mlx4_en_dev, cycles);
@@ -249,7 +249,7 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = {
 static u32 freq_to_shift(u16 freq)
 {
 	u32 freq_khz = freq * 1000;
-	u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
+	u64 max_val_cycles = freq_khz * 1000ULL * MLX4_EN_WRAP_AROUND_SEC;
 	u64 max_val_cycles_rounded = 1ULL << fls64(max_val_cycles - 1);
 	/* calculate max possible multiplier in order to fit in 64bit */
 	u64 max_mul = div64_u64(ULLONG_MAX, max_val_cycles_rounded);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
index 752a72499b4f..be80da03a594 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
@@ -290,9 +290,6 @@ static int mlx4_en_dcbnl_ieee_getets(struct net_device *dev,
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct ieee_ets *my_ets = &priv->ets;
 
-	if (!my_ets)
-		return -EINVAL;
-
 	ets->ets_cap = IEEE_8021QAZ_MAX_TCS;
 	ets->cbs = my_ets->cbs;
 	memcpy(ets->tc_tx_bw, my_ets->tc_tx_bw, sizeof(ets->tc_tx_bw));
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index cd17a3f4faf8..ad6298456639 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1727,6 +1727,13 @@ static int mlx4_en_get_num_flows(struct mlx4_en_priv *priv)
 
 }
 
+static u32 mlx4_en_get_rx_ring_count(struct net_device *dev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	return priv->rx_ring_num;
+}
+
 static int mlx4_en_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 			     u32 *rule_locs)
 {
@@ -1743,9 +1750,6 @@ static int mlx4_en_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 		return -EINVAL;
 
 	switch (cmd->cmd) {
-	case ETHTOOL_GRXRINGS:
-		cmd->data = priv->rx_ring_num;
-		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = mlx4_en_get_num_flows(priv);
 		break;
@@ -1897,6 +1901,7 @@ static int mlx4_en_get_ts_info(struct net_device *dev,
 	if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) {
 		info->so_timestamping |=
 			SOF_TIMESTAMPING_TX_HARDWARE |
+			SOF_TIMESTAMPING_TX_SOFTWARE |
 			SOF_TIMESTAMPING_RX_HARDWARE |
 			SOF_TIMESTAMPING_RAW_HARDWARE;
 
@@ -2153,6 +2158,7 @@ const struct ethtool_ops mlx4_en_ethtool_ops = {
 	.set_ringparam = mlx4_en_set_ringparam,
 	.get_rxnfc = mlx4_en_get_rxnfc,
 	.set_rxnfc = mlx4_en_set_rxnfc,
+	.get_rx_ring_count = mlx4_en_get_rx_ring_count,
 	.get_rxfh_indir_size = mlx4_en_get_rxfh_indir_size,
 	.get_rxfh_key_size = mlx4_en_get_rxfh_key_size,
 	.get_rxfh = mlx4_en_get_rxfh,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 281b34af0bb4..81bf8908b897 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1180,9 +1180,9 @@ static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv,
 				mlx4_unregister_mac(mdev->dev, priv->port, mac);
 
 				hlist_del_rcu(&entry->hlist);
-				kfree_rcu(entry, rcu);
 				en_dbg(DRV, priv, "Removed MAC %pM on port:%d\n",
 				       entry->mac, priv->port);
+				kfree_rcu(entry, rcu);
 				++removed;
 			}
 		}
@@ -2420,21 +2420,22 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
-static int mlx4_en_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
+static int mlx4_en_hwtstamp_set(struct net_device *dev,
+				struct kernel_hwtstamp_config *config,
+				struct netlink_ext_ack *extack)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
-	struct hwtstamp_config config;
-
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
 
 	/* device doesn't support time stamping */
-	if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS))
+	if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "device doesn't support time stamping");
 		return -EINVAL;
+	}
 
 	/* TX HW timestamp */
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 	case HWTSTAMP_TX_ON:
 		break;
@@ -2443,7 +2444,7 @@ static int mlx4_en_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	}
 
 	/* RX HW timestamp */
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		break;
 	case HWTSTAMP_FILTER_ALL:
@@ -2461,39 +2462,27 @@ static int mlx4_en_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 	case HWTSTAMP_FILTER_NTP_ALL:
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
 		return -ERANGE;
 	}
 
 	if (mlx4_en_reset_config(dev, config, dev->features)) {
-		config.tx_type = HWTSTAMP_TX_OFF;
-		config.rx_filter = HWTSTAMP_FILTER_NONE;
+		config->tx_type = HWTSTAMP_TX_OFF;
+		config->rx_filter = HWTSTAMP_FILTER_NONE;
 	}
 
-	return copy_to_user(ifr->ifr_data, &config,
-			    sizeof(config)) ? -EFAULT : 0;
+	return 0;
 }
 
-static int mlx4_en_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
+static int mlx4_en_hwtstamp_get(struct net_device *dev,
+				struct kernel_hwtstamp_config *config)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
-	return copy_to_user(ifr->ifr_data, &priv->hwtstamp_config,
-			    sizeof(priv->hwtstamp_config)) ? -EFAULT : 0;
-}
-
-static int mlx4_en_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return mlx4_en_hwtstamp_set(dev, ifr);
-	case SIOCGHWTSTAMP:
-		return mlx4_en_hwtstamp_get(dev, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
+	*config = priv->hwtstamp_config;
+	return 0;
 }
 
 static netdev_features_t mlx4_en_fix_features(struct net_device *netdev,
@@ -2560,7 +2549,7 @@ static int mlx4_en_set_features(struct net_device *netdev,
 	}
 
 	if (reset) {
-		ret = mlx4_en_reset_config(netdev, priv->hwtstamp_config,
+		ret = mlx4_en_reset_config(netdev, &priv->hwtstamp_config,
 					   features);
 		if (ret)
 			return ret;
@@ -2670,8 +2659,7 @@ static int mlx4_udp_tunnel_sync(struct net_device *dev, unsigned int table)
 
 static const struct udp_tunnel_nic_info mlx4_udp_tunnels = {
 	.sync_table	= mlx4_udp_tunnel_sync,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-			  UDP_TUNNEL_NIC_INFO_IPV4_ONLY,
+	.flags		= UDP_TUNNEL_NIC_INFO_IPV4_ONLY,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, },
 	},
@@ -2845,7 +2833,6 @@ static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_set_mac_address	= mlx4_en_set_mac,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= mlx4_en_change_mtu,
-	.ndo_eth_ioctl		= mlx4_en_ioctl,
 	.ndo_tx_timeout		= mlx4_en_tx_timeout,
 	.ndo_vlan_rx_add_vid	= mlx4_en_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= mlx4_en_vlan_rx_kill_vid,
@@ -2859,6 +2846,8 @@ static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_features_check	= mlx4_en_features_check,
 	.ndo_set_tx_maxrate	= mlx4_en_set_tx_maxrate,
 	.ndo_bpf		= mlx4_xdp,
+	.ndo_hwtstamp_get	= mlx4_en_hwtstamp_get,
+	.ndo_hwtstamp_set	= mlx4_en_hwtstamp_set,
 };
 
 static const struct net_device_ops mlx4_netdev_ops_master = {
@@ -3513,7 +3502,7 @@ out:
 }
 
 int mlx4_en_reset_config(struct net_device *dev,
-			 struct hwtstamp_config ts_config,
+			 struct kernel_hwtstamp_config *ts_config,
 			 netdev_features_t features)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -3523,8 +3512,8 @@ int mlx4_en_reset_config(struct net_device *dev,
 	int port_up = 0;
 	int err = 0;
 
-	if (priv->hwtstamp_config.tx_type == ts_config.tx_type &&
-	    priv->hwtstamp_config.rx_filter == ts_config.rx_filter &&
+	if (priv->hwtstamp_config.tx_type == ts_config->tx_type &&
+	    priv->hwtstamp_config.rx_filter == ts_config->rx_filter &&
 	    !DEV_FEATURE_CHANGED(dev, features, NETIF_F_HW_VLAN_CTAG_RX) &&
 	    !DEV_FEATURE_CHANGED(dev, features, NETIF_F_RXFCS))
 		return 0; /* Nothing to change */
@@ -3543,7 +3532,7 @@ int mlx4_en_reset_config(struct net_device *dev,
 	mutex_lock(&mdev->state_lock);
 
 	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
-	memcpy(&new_prof.hwtstamp_config, &ts_config, sizeof(ts_config));
+	memcpy(&new_prof.hwtstamp_config, ts_config, sizeof(*ts_config));
 
 	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true);
 	if (err)
@@ -3561,7 +3550,7 @@ int mlx4_en_reset_config(struct net_device *dev,
 			dev->features |= NETIF_F_HW_VLAN_CTAG_RX;
 		else
 			dev->features &= ~NETIF_F_HW_VLAN_CTAG_RX;
-	} else if (ts_config.rx_filter == HWTSTAMP_FILTER_NONE) {
+	} else if (ts_config->rx_filter == HWTSTAMP_FILTER_NONE) {
 		/* RX time-stamping is OFF, update the RX vlan offload
 		 * to the latest wanted state
 		 */
@@ -3582,7 +3571,7 @@ int mlx4_en_reset_config(struct net_device *dev,
 	 * Regardless of the caller's choice,
 	 * Turn Off RX vlan offload in case of time-stamping is ON
 	 */
-	if (ts_config.rx_filter != HWTSTAMP_FILTER_NONE) {
+	if (ts_config->rx_filter != HWTSTAMP_FILTER_NONE) {
 		if (dev->features & NETIF_F_HW_VLAN_CTAG_RX)
 			en_warn(priv, "Turning off RX vlan offload since RX time-stamping is ON\n");
 		dev->features &= ~NETIF_F_HW_VLAN_CTAG_RX;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 15c57e9517e9..13666d50b90f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -48,60 +48,43 @@
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ip6_checksum.h>
 #endif
+#include <net/page_pool/helpers.h>
 
 #include "mlx4_en.h"
 
-static int mlx4_alloc_page(struct mlx4_en_priv *priv,
-			   struct mlx4_en_rx_alloc *frag,
-			   gfp_t gfp)
-{
-	struct page *page;
-	dma_addr_t dma;
-
-	page = alloc_page(gfp);
-	if (unlikely(!page))
-		return -ENOMEM;
-	dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE, priv->dma_dir);
-	if (unlikely(dma_mapping_error(priv->ddev, dma))) {
-		__free_page(page);
-		return -ENOMEM;
-	}
-	frag->page = page;
-	frag->dma = dma;
-	frag->page_offset = priv->rx_headroom;
-	return 0;
-}
-
 static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
 			       struct mlx4_en_rx_ring *ring,
 			       struct mlx4_en_rx_desc *rx_desc,
 			       struct mlx4_en_rx_alloc *frags,
 			       gfp_t gfp)
 {
+	dma_addr_t dma;
 	int i;
 
 	for (i = 0; i < priv->num_frags; i++, frags++) {
 		if (!frags->page) {
-			if (mlx4_alloc_page(priv, frags, gfp)) {
+			frags->page = page_pool_alloc_pages(ring->pp, gfp);
+			if (!frags->page) {
 				ring->alloc_fail++;
 				return -ENOMEM;
 			}
+			page_pool_fragment_page(frags->page, 1);
+			frags->page_offset = priv->rx_headroom;
+
 			ring->rx_alloc_pages++;
 		}
-		rx_desc->data[i].addr = cpu_to_be64(frags->dma +
-						    frags->page_offset);
+		dma = page_pool_get_dma_addr(frags->page);
+		rx_desc->data[i].addr = cpu_to_be64(dma + frags->page_offset);
 	}
 	return 0;
 }
 
 static void mlx4_en_free_frag(const struct mlx4_en_priv *priv,
+			      struct mlx4_en_rx_ring *ring,
 			      struct mlx4_en_rx_alloc *frag)
 {
-	if (frag->page) {
-		dma_unmap_page(priv->ddev, frag->dma,
-			       PAGE_SIZE, priv->dma_dir);
-		__free_page(frag->page);
-	}
+	if (frag->page)
+		page_pool_put_full_page(ring->pp, frag->page, false);
 	/* We need to clear all fields, otherwise a change of priv->log_rx_info
 	 * could lead to see garbage later in frag->page.
 	 */
@@ -141,18 +124,6 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 		(index << ring->log_stride);
 	struct mlx4_en_rx_alloc *frags = ring->rx_info +
 					(index << priv->log_rx_info);
-	if (likely(ring->page_cache.index > 0)) {
-		/* XDP uses a single page per frame */
-		if (!frags->page) {
-			ring->page_cache.index--;
-			frags->page = ring->page_cache.buf[ring->page_cache.index].page;
-			frags->dma  = ring->page_cache.buf[ring->page_cache.index].dma;
-		}
-		frags->page_offset = XDP_PACKET_HEADROOM;
-		rx_desc->data[0].addr = cpu_to_be64(frags->dma +
-						    XDP_PACKET_HEADROOM);
-		return 0;
-	}
 
 	return mlx4_en_alloc_frags(priv, ring, rx_desc, frags, gfp);
 }
@@ -178,7 +149,7 @@ static void mlx4_en_free_rx_desc(const struct mlx4_en_priv *priv,
 	frags = ring->rx_info + (index << priv->log_rx_info);
 	for (nr = 0; nr < priv->num_frags; nr++) {
 		en_dbg(DRV, priv, "Freeing fragment:%d\n", nr);
-		mlx4_en_free_frag(priv, frags + nr);
+		mlx4_en_free_frag(priv, ring, frags + nr);
 	}
 }
 
@@ -268,6 +239,7 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 			   u32 size, u16 stride, int node, int queue_index)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct page_pool_params pp = {};
 	struct mlx4_en_rx_ring *ring;
 	int err = -ENOMEM;
 	int tmp;
@@ -286,8 +258,27 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 	ring->log_stride = ffs(ring->stride) - 1;
 	ring->buf_size = ring->size * ring->stride + TXBB_SIZE;
 
-	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0)
+	pp.flags = PP_FLAG_DMA_MAP;
+	pp.pool_size = size * DIV_ROUND_UP(priv->rx_skb_size, PAGE_SIZE);
+	pp.nid = node;
+	pp.napi = &priv->rx_cq[queue_index]->napi;
+	pp.netdev = priv->dev;
+	pp.dev = &mdev->dev->persist->pdev->dev;
+	pp.dma_dir = priv->dma_dir;
+
+	ring->pp = page_pool_create(&pp);
+	if (IS_ERR(ring->pp)) {
+		err = PTR_ERR(ring->pp);
 		goto err_ring;
+	}
+
+	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0)
+		goto err_pp;
+
+	err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_POOL,
+					 ring->pp);
+	if (err)
+		goto err_xdp_info;
 
 	tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
 					sizeof(struct mlx4_en_rx_alloc));
@@ -319,6 +310,8 @@ err_info:
 	ring->rx_info = NULL;
 err_xdp_info:
 	xdp_rxq_info_unreg(&ring->xdp_rxq);
+err_pp:
+	page_pool_destroy(ring->pp);
 err_ring:
 	kfree(ring);
 	*pring = NULL;
@@ -409,26 +402,6 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
 	}
 }
 
-/* When the rx ring is running in page-per-packet mode, a released frame can go
- * directly into a small cache, to avoid unmapping or touching the page
- * allocator. In bpf prog performance scenarios, buffers are either forwarded
- * or dropped, never converted to skbs, so every page can come directly from
- * this cache when it is sized to be a multiple of the napi budget.
- */
-bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
-			struct mlx4_en_rx_alloc *frame)
-{
-	struct mlx4_en_page_cache *cache = &ring->page_cache;
-
-	if (cache->index >= MLX4_EN_CACHE_SIZE)
-		return false;
-
-	cache->buf[cache->index].page = frame->page;
-	cache->buf[cache->index].dma = frame->dma;
-	cache->index++;
-	return true;
-}
-
 void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_rx_ring **pring,
 			     u32 size, u16 stride)
@@ -445,6 +418,7 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 	xdp_rxq_info_unreg(&ring->xdp_rxq);
 	mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE);
 	kvfree(ring->rx_info);
+	page_pool_destroy(ring->pp);
 	ring->rx_info = NULL;
 	kfree(ring);
 	*pring = NULL;
@@ -453,14 +427,6 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
 				struct mlx4_en_rx_ring *ring)
 {
-	int i;
-
-	for (i = 0; i < ring->page_cache.index; i++) {
-		dma_unmap_page(priv->ddev, ring->page_cache.buf[i].dma,
-			       PAGE_SIZE, priv->dma_dir);
-		put_page(ring->page_cache.buf[i].page);
-	}
-	ring->page_cache.index = 0;
 	mlx4_en_free_rx_buf(priv, ring);
 	if (ring->stride <= TXBB_SIZE)
 		ring->buf -= TXBB_SIZE;
@@ -487,7 +453,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 		if (unlikely(!page))
 			goto fail;
 
-		dma = frags->dma;
+		dma = page_pool_get_dma_addr(page);
 		dma_sync_single_range_for_cpu(priv->ddev, dma, frags->page_offset,
 					      frag_size, priv->dma_dir);
 
@@ -496,8 +462,11 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 
 		truesize += frag_info->frag_stride;
 		if (frag_info->frag_stride == PAGE_SIZE / 2) {
+			struct netmem_desc *desc = pp_page_to_nmdesc(page);
+
 			frags->page_offset ^= PAGE_SIZE / 2;
 			release = page_count(page) != 1 ||
+				  atomic_long_read(&desc->pp_ref_count) != 1 ||
 				  page_is_pfmemalloc(page) ||
 				  page_to_nid(page) != numa_mem_id();
 		} else if (!priv->rx_headroom) {
@@ -511,10 +480,9 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 			release = frags->page_offset + frag_info->frag_size > PAGE_SIZE;
 		}
 		if (release) {
-			dma_unmap_page(priv->ddev, dma, PAGE_SIZE, priv->dma_dir);
 			frags->page = NULL;
 		} else {
-			page_ref_inc(page);
+			page_pool_ref_page(page);
 		}
 
 		nr++;
@@ -784,7 +752,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			/* Get pointer to first fragment since we haven't
 			 * skb yet and cast it to ethhdr struct
 			 */
-			dma = frags[0].dma + frags[0].page_offset;
+			dma = page_pool_get_dma_addr(frags[0].page);
+			dma += frags[0].page_offset;
 			dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh),
 						DMA_FROM_DEVICE);
 
@@ -823,7 +792,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			void *orig_data;
 			u32 act;
 
-			dma = frags[0].dma + frags[0].page_offset;
+			dma = page_pool_get_dma_addr(frags[0].page);
+			dma += frags[0].page_offset;
 			dma_sync_single_for_cpu(priv->ddev, dma,
 						priv->frag_info[0].frag_size,
 						DMA_FROM_DEVICE);
@@ -886,6 +856,7 @@ xdp_drop_no_cnt:
 		skb = napi_get_frags(&cq->napi);
 		if (unlikely(!skb))
 			goto next;
+		skb_mark_for_recycle(skb);
 
 		if (unlikely(ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL)) {
 			u64 timestamp = mlx4_en_get_cqe_ts(cqe);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 1ddb11cb25f9..87f35bcbeff8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -44,6 +44,7 @@
 #include <linux/ipv6.h>
 #include <linux/indirect_call_wrapper.h>
 #include <net/ipv6.h>
+#include <net/page_pool/helpers.h>
 
 #include "mlx4_en.h"
 
@@ -350,16 +351,10 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
 			    int napi_mode)
 {
 	struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
-	struct mlx4_en_rx_alloc frame = {
-		.page = tx_info->page,
-		.dma = tx_info->map0_dma,
-	};
-
-	if (!napi_mode || !mlx4_en_rx_recycle(ring->recycle_ring, &frame)) {
-		dma_unmap_page(priv->ddev, tx_info->map0_dma,
-			       PAGE_SIZE, priv->dma_dir);
-		put_page(tx_info->page);
-	}
+	struct page_pool *pool = ring->recycle_ring->pp;
+
+	/* Note that napi_mode = 0 means ndo_close() path, not budget = 0 */
+	page_pool_put_full_page(pool, tx_info->page, !!napi_mode);
 
 	return tx_info->nr_txbb;
 }
@@ -450,6 +445,8 @@ int mlx4_en_process_tx_cq(struct net_device *dev,
 
 	if (unlikely(!priv->port_up))
 		return 0;
+	if (unlikely(!napi_budget) && cq->type == TX_XDP)
+		return 0;
 
 	netdev_txq_bql_complete_prefetchw(ring->tx_queue);
 
@@ -1194,7 +1191,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 	tx_desc = ring->buf + (index << LOG_TXBB_SIZE);
 	data = &tx_desc->data;
 
-	dma = frame->dma;
+	dma = page_pool_get_dma_addr(frame->page);
 
 	tx_info->page = frame->page;
 	frame->page = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index febeadfdd5a5..4293f8e33f44 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -49,6 +49,8 @@
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
 
+#include <rdma/ib_verbs.h>
+
 #include "mlx4.h"
 #include "fw.h"
 #include "icm.h"
@@ -172,7 +174,8 @@ MODULE_PARM_DESC(port_type_array, "Array of port types: HW_DEFAULT (0) is defaul
 static atomic_t pf_loading = ATOMIC_INIT(0);
 
 static int mlx4_devlink_ierr_reset_get(struct devlink *devlink, u32 id,
-				       struct devlink_param_gset_ctx *ctx)
+				       struct devlink_param_gset_ctx *ctx,
+				       struct netlink_ext_ack *extack)
 {
 	ctx->val.vbool = !!mlx4_internal_err_reset;
 	return 0;
@@ -187,7 +190,8 @@ static int mlx4_devlink_ierr_reset_set(struct devlink *devlink, u32 id,
 }
 
 static int mlx4_devlink_crdump_snapshot_get(struct devlink *devlink, u32 id,
-					    struct devlink_param_gset_ctx *ctx)
+					    struct devlink_param_gset_ctx *ctx,
+					    struct netlink_ext_ack *extack)
 {
 	struct mlx4_priv *priv = devlink_priv(devlink);
 	struct mlx4_dev *dev = &priv->dev;
@@ -1246,14 +1250,6 @@ err_out:
 	return err ? err : count;
 }
 
-enum ibta_mtu {
-	IB_MTU_256  = 1,
-	IB_MTU_512  = 2,
-	IB_MTU_1024 = 3,
-	IB_MTU_2048 = 4,
-	IB_MTU_4096 = 5
-};
-
 static inline int int_to_ibta_mtu(int mtu)
 {
 	switch (mtu) {
@@ -1266,7 +1262,7 @@ static inline int int_to_ibta_mtu(int mtu)
 	}
 }
 
-static inline int ibta_mtu_to_int(enum ibta_mtu mtu)
+static inline int ibta_mtu_to_int(enum ib_mtu mtu)
 {
 	switch (mtu) {
 	case IB_MTU_256:  return  256;
@@ -4372,7 +4368,6 @@ static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
 
 	pci_set_master(pdev);
 	pci_restore_state(pdev);
-	pci_save_state(pdev);
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index d7d856d1758a..b213094ea30f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1478,12 +1478,6 @@ void mlx4_zone_allocator_destroy(struct mlx4_zone_allocator *zone_alloc);
 u32 mlx4_zone_alloc_entries(struct mlx4_zone_allocator *zones, u32 uid, int count,
 			    int align, u32 skip_mask, u32 *puid);
 
-/* Free <count> objects, start from <obj> of the uid <uid> from zone_allocator
- * <zones>.
- */
-u32 mlx4_zone_free_entries(struct mlx4_zone_allocator *zones,
-			   u32 uid, u32 obj, u32 count);
-
 /* If <zones> was allocated with MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP, instead of
  * specifying the uid when freeing an object, zone allocator could figure it by
  * itself. Other parameters are similar to mlx4_zone_free.
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 28b70dcc652e..aab97694f86b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -247,20 +247,11 @@ struct mlx4_en_tx_desc {
 
 struct mlx4_en_rx_alloc {
 	struct page	*page;
-	dma_addr_t	dma;
 	u32		page_offset;
 };
 
 #define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT)
 
-struct mlx4_en_page_cache {
-	u32 index;
-	struct {
-		struct page	*page;
-		dma_addr_t	dma;
-	} buf[MLX4_EN_CACHE_SIZE];
-};
-
 enum {
 	MLX4_EN_TX_RING_STATE_RECOVERING,
 };
@@ -335,14 +326,14 @@ struct mlx4_en_rx_ring {
 	u16 stride;
 	u16 log_stride;
 	u16 cqn;	/* index of port CQ associated with this ring */
+	u8  fcs_del;
 	u32 prod;
 	u32 cons;
 	u32 buf_size;
-	u8  fcs_del;
+	struct page_pool *pp;
 	void *buf;
 	void *rx_info;
 	struct bpf_prog __rcu *xdp_prog;
-	struct mlx4_en_page_cache page_cache;
 	unsigned long bytes;
 	unsigned long packets;
 	unsigned long csum_ok;
@@ -397,7 +388,7 @@ struct mlx4_en_port_profile {
 	u8 num_up;
 	int rss_rings;
 	int inline_thold;
-	struct hwtstamp_config hwtstamp_config;
+	struct kernel_hwtstamp_config hwtstamp_config;
 };
 
 struct mlx4_en_profile {
@@ -621,7 +612,7 @@ struct mlx4_en_priv {
 	bool wol;
 	struct device *ddev;
 	struct hlist_head mac_hash[MLX4_EN_MAC_HASH_SIZE];
-	struct hwtstamp_config hwtstamp_config;
+	struct kernel_hwtstamp_config hwtstamp_config;
 	u32 counter_index;
 
 #ifdef CONFIG_MLX4_EN_DCB
@@ -707,8 +698,6 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_priv *priv, unsigned int length,
 			       int tx_ind, bool *doorbell_pending);
 void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring);
-bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
-			struct mlx4_en_rx_alloc *frame);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_tx_ring **pring,
@@ -791,7 +780,7 @@ void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev);
 
 int mlx4_en_moderation_update(struct mlx4_en_priv *priv);
 int mlx4_en_reset_config(struct net_device *dev,
-			 struct hwtstamp_config ts_config,
+			 struct kernel_hwtstamp_config *ts_config,
 			 netdev_features_t new_features);
 void mlx4_en_update_pfc_stats_bitmap(struct mlx4_dev *dev,
 				     struct mlx4_en_stats_bitmap *stats_bitmap,
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index d7444782bfdd..698a5d1f0d7e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -106,7 +106,7 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
 	buddy->max_order = max_order;
 	spin_lock_init(&buddy->lock);
 
-	buddy->bits = kcalloc(buddy->max_order + 1, sizeof(long *),
+	buddy->bits = kcalloc(buddy->max_order + 1, sizeof(*buddy->bits),
 			      GFP_KERNEL);
 	buddy->num_free = kcalloc(buddy->max_order + 1, sizeof(*buddy->num_free),
 				  GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 4e43f4a7d246..e3d0b13c1610 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -147,26 +147,6 @@ static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
 	return err;
 }
 
-int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx)
-{
-	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
-	struct mlx4_mac_table *table = &info->mac_table;
-	int i;
-
-	for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
-		if (!table->refs[i])
-			continue;
-
-		if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i]))) {
-			*idx = i;
-			return 0;
-		}
-	}
-
-	return -ENOENT;
-}
-EXPORT_SYMBOL_GPL(mlx4_find_cached_mac);
-
 static bool mlx4_need_mf_bond(struct mlx4_dev *dev)
 {
 	int i, num_eth_ports = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index ea6070180c96..3c3e84100d5a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -8,7 +8,6 @@ config MLX5_CORE
 	depends on PCI
 	select AUXILIARY_BUS
 	select NET_DEVLINK
-	depends on VXLAN || !VXLAN
 	depends on MLXFW || !MLXFW
 	depends on PTP_1588_CLOCK_OPTIONAL
 	depends on PCI_HYPERV_INTERFACE || !PCI_HYPERV_INTERFACE
@@ -31,6 +30,7 @@ config MLX5_CORE_EN
 	bool "Mellanox 5th generation network adapters (ConnectX series) Ethernet support"
 	depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE
 	select PAGE_POOL
+	select PAGE_POOL_STATS
 	select DIMLIB
 	help
 	  Ethernet support in Mellanox Technologies ConnectX-4 NIC.
@@ -80,8 +80,8 @@ config MLX5_BRIDGE
 	default y
 	help
 	  mlx5 ConnectX offloads support for Ethernet Bridging (BRIDGE).
-	  Enable adding representors of mlx5 uplink and VF ports to Bridge and
-	  offloading rules for traffic between such ports. Supports VLANs (trunk and
+	  Enable offloading FDB rules from a bridge device containing
+	  representors of mlx5 uplink and VF ports. Supports VLANs (trunk and
 	  access modes).
 
 config MLX5_CLS_ACT
@@ -207,3 +207,14 @@ config MLX5_DPLL
 	help
 	  DPLL support in Mellanox Technologies ConnectX NICs.
 
+config MLX5_EN_PSP
+	bool "Mellanox Technologies support for PSP cryptography-offload acceleration"
+	depends on INET_PSP
+	depends on MLX5_CORE_EN
+	default y
+	help
+	  mlx5 device offload support for Google PSP Security Protocol offload.
+	  Adds support for PSP encryption offload and for SPI and key generation
+	  interfaces to PSP Stack which supports PSP crypto offload.
+
+	  If unsure, say Y.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 79fe09de0a9f..8ffa286a18f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -17,7 +17,7 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		fs_counters.o fs_ft_pool.o rl.o lag/debugfs.o lag/lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \
 		diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o diag/reporter_vnic.o \
-		fw_reset.o qos.o lib/tout.o lib/aso.o wc.o fs_pool.o
+		fw_reset.o qos.o lib/tout.o lib/aso.o wc.o fs_pool.o lib/nv_param.o
 
 #
 # Netdev basic
@@ -29,7 +29,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en/rqt.o en/tir.o en/rss.o en/rx_res.o \
 		en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \
 		en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o en/ptp.o \
 		en/qos.o en/htb.o en/trap.o en/fs_tt_redirect.o en/selq.o \
-		lib/crypto.o lib/sd.o
+		lib/crypto.o lib/sd.o en/pcie_cong_event.o
 
 #
 # Netdev extra
@@ -60,6 +60,7 @@ mlx5_core-$(CONFIG_MLX5_CLS_ACT)     += en/tc/act/act.o en/tc/act/drop.o en/tc/a
 ifneq ($(CONFIG_MLX5_TC_CT),)
 	mlx5_core-y			     += en/tc_ct.o en/tc/ct_fs_dmfs.o
 	mlx5_core-$(CONFIG_MLX5_SW_STEERING) += en/tc/ct_fs_smfs.o
+	mlx5_core-$(CONFIG_MLX5_HW_STEERING) += en/tc/ct_fs_hmfs.o
 endif
 
 mlx5_core-$(CONFIG_MLX5_TC_SAMPLE)   += en/tc/sample.o
@@ -68,7 +69,7 @@ mlx5_core-$(CONFIG_MLX5_TC_SAMPLE)   += en/tc/sample.o
 # Core extra
 #
 mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o eswitch_offloads_termtbl.o \
-				      ecpf.o rdma.o esw/legacy.o \
+				      ecpf.o rdma.o esw/legacy.o esw/adj_vport.o \
 				      esw/devlink_port.o esw/vporttbl.o esw/qos.o esw/ipsec.o
 
 mlx5_core-$(CONFIG_MLX5_ESWITCH)   += esw/acl/helper.o \
@@ -84,7 +85,9 @@ mlx5_core-$(CONFIG_MLX5_BRIDGE)    += esw/bridge.o esw/bridge_mcast.o esw/bridge
 
 mlx5_core-$(CONFIG_HWMON)          += hwmon.o
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
-mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
+ifneq ($(CONFIG_VXLAN),)
+	mlx5_core-y		   += lib/vxlan.o
+endif
 mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
 mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += lib/hv.o lib/hv_vhca.o
 
@@ -109,6 +112,8 @@ mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/ktls_stats.o \
 				   en_accel/fs_tcp.o en_accel/ktls.o en_accel/ktls_txrx.o \
 				   en_accel/ktls_tx.o en_accel/ktls_rx.o
 
+mlx5_core-$(CONFIG_MLX5_EN_PSP) += en_accel/psp.o en_accel/psp_rxtx.o
+
 #
 # SW Steering
 #
@@ -123,6 +128,7 @@ mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/sws/dr_domain.o \
 					steering/sws/dr_ste_v0.o \
 					steering/sws/dr_ste_v1.o \
 					steering/sws/dr_ste_v2.o \
+					steering/sws/dr_ste_v3.o \
 					steering/sws/dr_cmd.o \
 					steering/sws/dr_fw.o \
 					steering/sws/dr_action.o \
@@ -150,8 +156,10 @@ mlx5_core-$(CONFIG_MLX5_HW_STEERING) += steering/hws/cmd.o \
 					steering/hws/bwc.o \
 					steering/hws/debug.o \
 					steering/hws/vport.o \
-					steering/hws/bwc_complex.o
-
+					steering/hws/bwc_complex.o \
+					steering/hws/fs_hws_pools.o \
+					steering/hws/fs_hws.o \
+					steering/hws/action_ste_pool.o
 
 #
 # SF device
@@ -163,5 +171,10 @@ mlx5_core-$(CONFIG_MLX5_SF) += sf/vhca_event.o sf/dev/dev.o sf/dev/driver.o irq_
 #
 mlx5_core-$(CONFIG_MLX5_SF_MANAGER) += sf/cmd.o sf/hw_table.o sf/devlink.o
 
+#
+# TPH support
+#
+mlx5_core-$(CONFIG_PCIE_TPH) += lib/st.o
+
 obj-$(CONFIG_MLX5_DPLL) += mlx5_dpll.o
 mlx5_dpll-y :=	dpll.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 6bd8a18e3af3..5b08e5ffe0e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -94,6 +94,11 @@ static u16 in_to_opcode(void *in)
 	return MLX5_GET(mbox_in, in, opcode);
 }
 
+static u16 in_to_uid(void *in)
+{
+	return MLX5_GET(mbox_in, in, uid);
+}
+
 /* Returns true for opcodes that might be triggered very frequently and throttle
  * the command interface. Limit their command slots usage.
  */
@@ -176,6 +181,7 @@ static int cmd_alloc_index(struct mlx5_cmd *cmd, struct mlx5_cmd_work_ent *ent)
 static void cmd_free_index(struct mlx5_cmd *cmd, int idx)
 {
 	lockdep_assert_held(&cmd->alloc_lock);
+	cmd->ent_arr[idx] = NULL;
 	set_bit(idx, &cmd->vars.bitmask);
 }
 
@@ -289,6 +295,10 @@ static void poll_timeout(struct mlx5_cmd_work_ent *ent)
 			return;
 		}
 		cond_resched();
+		if (mlx5_cmd_is_down(dev)) {
+			ent->ret = -ENXIO;
+			return;
+		}
 	} while (time_before(jiffies, poll_end));
 
 	ent->ret = -ETIMEDOUT;
@@ -823,7 +833,7 @@ static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out)
 
 	opcode = in_to_opcode(in);
 	op_mod = MLX5_GET(mbox_in, in, op_mod);
-	uid    = MLX5_GET(mbox_in, in, uid);
+	uid    = in_to_uid(in);
 	status = MLX5_GET(mbox_out, out, status);
 
 	if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY &&
@@ -922,8 +932,7 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force
 
 static void cb_timeout_handler(struct work_struct *work)
 {
-	struct delayed_work *dwork = container_of(work, struct delayed_work,
-						  work);
+	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5_cmd_work_ent *ent = container_of(dwork,
 						     struct mlx5_cmd_work_ent,
 						     cb_timeout_work);
@@ -1013,6 +1022,7 @@ static void cmd_work_handler(struct work_struct *work)
 				complete(&ent->done);
 			}
 			up(&cmd->vars.sem);
+			complete(&ent->slotted);
 			return;
 		}
 	} else {
@@ -1065,7 +1075,7 @@ static void cmd_work_handler(struct work_struct *work)
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();
-		mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, (ent->ret == -ETIMEDOUT));
+		mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, !!ent->ret);
 	}
 }
 
@@ -1191,6 +1201,44 @@ out_err:
 	return err;
 }
 
+/* Check if all command slots are stalled (timed out and not recovered).
+ * returns true if all slots timed out on a recent command and have not been
+ * completed by FW yet. (stalled state)
+ * false otherwise (at least one slot is not stalled).
+ *
+ * In such odd situation "all_stalled", this serves as a protection mechanism
+ * to avoid blocking the kernel for long periods of time in case FW is not
+ * responding to commands.
+ */
+static bool mlx5_cmd_all_stalled(struct mlx5_core_dev *dev)
+{
+	struct mlx5_cmd *cmd = &dev->cmd;
+	bool all_stalled = true;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&cmd->alloc_lock, flags);
+
+	/* at least one command slot is free */
+	if (bitmap_weight(&cmd->vars.bitmask, cmd->vars.max_reg_cmds) > 0) {
+		all_stalled = false;
+		goto out;
+	}
+
+	for_each_clear_bit(i, &cmd->vars.bitmask, cmd->vars.max_reg_cmds) {
+		struct mlx5_cmd_work_ent *ent = dev->cmd.ent_arr[i];
+
+		if (!test_bit(MLX5_CMD_ENT_STATE_TIMEDOUT, &ent->state)) {
+			all_stalled = false;
+			break;
+		}
+	}
+out:
+	spin_unlock_irqrestore(&cmd->alloc_lock, flags);
+
+	return all_stalled;
+}
+
 /*  Notes:
  *    1. Callback functions may not sleep
  *    2. page queue commands do not support asynchrous completion
@@ -1221,6 +1269,15 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	if (callback && page_queue)
 		return -EINVAL;
 
+	if (!page_queue && mlx5_cmd_all_stalled(dev)) {
+		mlx5_core_err_rl(dev,
+				 "All CMD slots are stalled, aborting command\n");
+		/* there's no reason to wait and block the whole kernel if FW
+		 * isn't currently responding to all slots, fail immediately
+		 */
+		return -EAGAIN;
+	}
+
 	ent = cmd_alloc_ent(cmd, in, out, uout, uout_size,
 			    callback, context, page_queue);
 	if (IS_ERR(ent))
@@ -1691,6 +1748,13 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force
 		if (test_bit(i, &vector)) {
 			ent = cmd->ent_arr[i];
 
+			if (forced && ent->ret == -ETIMEDOUT)
+				set_bit(MLX5_CMD_ENT_STATE_TIMEDOUT,
+					&ent->state);
+			else if (!forced) /* real FW completion */
+				clear_bit(MLX5_CMD_ENT_STATE_TIMEDOUT,
+					  &ent->state);
+
 			/* if we already completed the command, ignore it */
 			if (!test_and_clear_bit(MLX5_CMD_ENT_STATE_PENDING_COMP,
 						&ent->state)) {
@@ -1870,6 +1934,17 @@ static int is_manage_pages(void *in)
 	return in_to_opcode(in) == MLX5_CMD_OP_MANAGE_PAGES;
 }
 
+static bool mlx5_has_privileged_uid(struct mlx5_core_dev *dev)
+{
+	return !xa_empty(&dev->cmd.vars.privileged_uids);
+}
+
+static bool mlx5_cmd_is_privileged_uid(struct mlx5_core_dev *dev,
+				       u16 uid)
+{
+	return !!xa_load(&dev->cmd.vars.privileged_uids, uid);
+}
+
 /*  Notes:
  *    1. Callback functions may not sleep
  *    2. Page queue commands do not support asynchrous completion
@@ -1880,7 +1955,9 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 {
 	struct mlx5_cmd_msg *inb, *outb;
 	u16 opcode = in_to_opcode(in);
-	bool throttle_op;
+	bool throttle_locked = false;
+	bool unpriv_locked = false;
+	u16 uid = in_to_uid(in);
 	int pages_queue;
 	gfp_t gfp;
 	u8 token;
@@ -1889,12 +1966,17 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, opcode))
 		return -ENXIO;
 
-	throttle_op = mlx5_cmd_is_throttle_opcode(opcode);
-	if (throttle_op) {
-		if (callback) {
-			if (down_trylock(&dev->cmd.vars.throttle_sem))
-				return -EBUSY;
-		} else {
+	if (!callback) {
+		/* The semaphore is already held for callback commands. It was
+		 * acquired in mlx5_cmd_exec_cb()
+		 */
+		if (uid && mlx5_has_privileged_uid(dev)) {
+			if (!mlx5_cmd_is_privileged_uid(dev, uid)) {
+				unpriv_locked = true;
+				down(&dev->cmd.vars.unprivileged_sem);
+			}
+		} else if (mlx5_cmd_is_throttle_opcode(opcode)) {
+			throttle_locked = true;
 			down(&dev->cmd.vars.throttle_sem);
 		}
 	}
@@ -1924,8 +2006,8 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 
 	err = mlx5_cmd_invoke(dev, inb, outb, out, out_size, callback, context,
 			      pages_queue, token, force_polling);
-	if (callback)
-		return err;
+	if (callback && !err)
+		return 0;
 
 	if (err > 0) /* Failed in FW, command didn't execute */
 		err = deliv_status_to_err(err);
@@ -1940,8 +2022,11 @@ out_out:
 out_in:
 	free_msg(dev, inb);
 out_up:
-	if (throttle_op)
+	if (throttle_locked)
 		up(&dev->cmd.vars.throttle_sem);
+	if (unpriv_locked)
+		up(&dev->cmd.vars.unprivileged_sem);
+
 	return err;
 }
 
@@ -2103,18 +2188,22 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work)
 	struct mlx5_async_work *work = _work;
 	struct mlx5_async_ctx *ctx;
 	struct mlx5_core_dev *dev;
-	u16 opcode;
+	bool throttle_locked;
+	bool unpriv_locked;
 
 	ctx = work->ctx;
 	dev = ctx->dev;
-	opcode = work->opcode;
+	throttle_locked = work->throttle_locked;
+	unpriv_locked = work->unpriv_locked;
 	status = cmd_status_err(dev, status, work->opcode, work->op_mod, work->out);
 	work->user_callback(status, work);
 	/* Can't access "work" from this point on. It could have been freed in
 	 * the callback.
 	 */
-	if (mlx5_cmd_is_throttle_opcode(opcode))
+	if (throttle_locked)
 		up(&dev->cmd.vars.throttle_sem);
+	if (unpriv_locked)
+		up(&dev->cmd.vars.unprivileged_sem);
 	if (atomic_dec_and_test(&ctx->num_inflight))
 		complete(&ctx->inflight_done);
 }
@@ -2123,6 +2212,8 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 		     void *out, int out_size, mlx5_async_cbk_t callback,
 		     struct mlx5_async_work *work)
 {
+	struct mlx5_core_dev *dev = ctx->dev;
+	u16 uid;
 	int ret;
 
 	work->ctx = ctx;
@@ -2130,11 +2221,43 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 	work->opcode = in_to_opcode(in);
 	work->op_mod = MLX5_GET(mbox_in, in, op_mod);
 	work->out = out;
+	work->throttle_locked = false;
+	work->unpriv_locked = false;
+	uid = in_to_uid(in);
+
 	if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight)))
 		return -EIO;
-	ret = cmd_exec(ctx->dev, in, in_size, out, out_size,
+
+	if (uid && mlx5_has_privileged_uid(dev)) {
+		if (!mlx5_cmd_is_privileged_uid(dev, uid)) {
+			if (down_trylock(&dev->cmd.vars.unprivileged_sem)) {
+				ret = -EBUSY;
+				goto dec_num_inflight;
+			}
+			work->unpriv_locked = true;
+		}
+	} else if (mlx5_cmd_is_throttle_opcode(in_to_opcode(in))) {
+		if (down_trylock(&dev->cmd.vars.throttle_sem)) {
+			ret = -EBUSY;
+			goto dec_num_inflight;
+		}
+		work->throttle_locked = true;
+	}
+
+	ret = cmd_exec(dev, in, in_size, out, out_size,
 		       mlx5_cmd_exec_cb_handler, work, false);
-	if (ret && atomic_dec_and_test(&ctx->num_inflight))
+	if (ret)
+		goto sem_up;
+
+	return 0;
+
+sem_up:
+	if (work->throttle_locked)
+		up(&dev->cmd.vars.throttle_sem);
+	if (work->unpriv_locked)
+		up(&dev->cmd.vars.unprivileged_sem);
+dec_num_inflight:
+	if (atomic_dec_and_test(&ctx->num_inflight))
 		complete(&ctx->inflight_done);
 
 	return ret;
@@ -2370,10 +2493,16 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev)
 	sema_init(&cmd->vars.sem, cmd->vars.max_reg_cmds);
 	sema_init(&cmd->vars.pages_sem, 1);
 	sema_init(&cmd->vars.throttle_sem, DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2));
+	sema_init(&cmd->vars.unprivileged_sem,
+		  DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2));
+
+	xa_init(&cmd->vars.privileged_uids);
 
 	cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
-	if (!cmd->pool)
-		return -ENOMEM;
+	if (!cmd->pool) {
+		err = -ENOMEM;
+		goto err_destroy_xa;
+	}
 
 	err = alloc_cmd_page(dev, cmd);
 	if (err)
@@ -2407,6 +2536,8 @@ err_cmd_page:
 	free_cmd_page(dev, cmd);
 err_free_pool:
 	dma_pool_destroy(cmd->pool);
+err_destroy_xa:
+	xa_destroy(&dev->cmd.vars.privileged_uids);
 	return err;
 }
 
@@ -2419,6 +2550,7 @@ void mlx5_cmd_disable(struct mlx5_core_dev *dev)
 	destroy_msg_cache(dev);
 	free_cmd_page(dev, cmd);
 	dma_pool_destroy(cmd->pool);
+	xa_destroy(&dev->cmd.vars.privileged_uids);
 }
 
 void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
@@ -2426,3 +2558,18 @@ void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
 {
 	dev->cmd.state = cmdif_state;
 }
+
+int mlx5_cmd_add_privileged_uid(struct mlx5_core_dev *dev, u16 uid)
+{
+	return xa_insert(&dev->cmd.vars.privileged_uids, uid,
+			 xa_mk_value(uid), GFP_KERNEL);
+}
+EXPORT_SYMBOL(mlx5_cmd_add_privileged_uid);
+
+void mlx5_cmd_remove_privileged_uid(struct mlx5_core_dev *dev, u16 uid)
+{
+	void *data = xa_erase(&dev->cmd.vars.privileged_uids, uid);
+
+	WARN(!data, "Privileged UID %u does not exist\n", uid);
+}
+EXPORT_SYMBOL(mlx5_cmd_remove_privileged_uid);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index 1fd403713baf..60f7ab1d72e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -66,8 +66,8 @@ void mlx5_cq_tasklet_cb(struct tasklet_struct *t)
 		tasklet_schedule(&ctx->task);
 }
 
-static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq,
-				   struct mlx5_eqe *eqe)
+void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq,
+			    struct mlx5_eqe *eqe)
 {
 	unsigned long flags;
 	struct mlx5_eq_tasklet *tasklet_ctx = cq->tasklet_ctx.priv;
@@ -95,7 +95,15 @@ static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq,
 	if (schedule_tasklet)
 		tasklet_schedule(&tasklet_ctx->task);
 }
+EXPORT_SYMBOL(mlx5_add_cq_to_tasklet);
 
+static void mlx5_core_cq_dummy_cb(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe)
+{
+	mlx5_core_err(cq->eq->core.dev,
+		      "CQ default completion callback, CQ #%u\n", cq->cqn);
+}
+
+#define MLX5_CQ_INIT_CMD_SN cpu_to_be32(2 << 28)
 /* Callers must verify outbox status in case of err */
 int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 		   u32 *in, int inlen, u32 *out, int outlen)
@@ -121,10 +129,19 @@ int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	cq->arm_sn     = 0;
 	cq->eq         = eq;
 	cq->uid = MLX5_GET(create_cq_in, in, uid);
+
+	/* Kernel CQs must set the arm_db address prior to calling
+	 * this function, allowing for the proper value to be
+	 * initialized. User CQs are responsible for their own
+	 * initialization since they do not use the arm_db field.
+	 */
+	if (cq->arm_db)
+		*cq->arm_db = MLX5_CQ_INIT_CMD_SN;
+
 	refcount_set(&cq->refcount, 1);
 	init_completion(&cq->free);
 	if (!cq->comp)
-		cq->comp = mlx5_add_cq_to_tasklet;
+		cq->comp = mlx5_core_cq_dummy_cb;
 	/* assuming CQ will be deleted before the EQ */
 	cq->tasklet_ctx.priv = &eq->tasklet_ctx;
 	INIT_LIST_HEAD(&cq->tasklet_ctx.list);
@@ -145,7 +162,6 @@ int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 		mlx5_core_dbg(dev, "failed adding CP 0x%x to debug file system\n",
 			      cq->cqn);
 
-	cq->uar = dev->priv.uar;
 	cq->irqn = eq->core.irqn;
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 9a79674d27f1..64c04f52990f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -228,8 +228,15 @@ enum {
 	MLX5_INTERFACE_PROTOCOL_VNET,
 
 	MLX5_INTERFACE_PROTOCOL_DPLL,
+	MLX5_INTERFACE_PROTOCOL_FWCTL,
 };
 
+static bool is_fwctl_supported(struct mlx5_core_dev *dev)
+{
+	/* fwctl is most useful on PFs, prevent fwctl on SFs for now */
+	return MLX5_CAP_GEN(dev, uctx_cap) && !mlx5_core_is_sf(dev);
+}
+
 static const struct mlx5_adev_device {
 	const char *suffix;
 	bool (*is_supported)(struct mlx5_core_dev *dev);
@@ -252,6 +259,8 @@ static const struct mlx5_adev_device {
 					   .is_supported = &is_mp_supported },
 	[MLX5_INTERFACE_PROTOCOL_DPLL] = { .suffix = "dpll",
 					   .is_supported = &is_dpll_supported },
+	[MLX5_INTERFACE_PROTOCOL_FWCTL] = { .suffix = "fwctl",
+					    .is_supported = &is_fwctl_supported },
 };
 
 int mlx5_adev_idx_alloc(void)
@@ -555,10 +564,14 @@ int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev)
 
 bool mlx5_same_hw_devs(struct mlx5_core_dev *dev, struct mlx5_core_dev *peer_dev)
 {
-	u64 fsystem_guid, psystem_guid;
+	u8 fsystem_guid[MLX5_SW_IMAGE_GUID_MAX_BYTES];
+	u8 psystem_guid[MLX5_SW_IMAGE_GUID_MAX_BYTES];
+	u8 flen;
+	u8 plen;
 
-	fsystem_guid = mlx5_query_nic_system_image_guid(dev);
-	psystem_guid = mlx5_query_nic_system_image_guid(peer_dev);
+	mlx5_query_nic_sw_system_image_guid(dev, fsystem_guid, &flen);
+	mlx5_query_nic_sw_system_image_guid(peer_dev, psystem_guid, &plen);
 
-	return (fsystem_guid && psystem_guid && fsystem_guid == psystem_guid);
+	return plen && flen && flen == plen &&
+		!memcmp(fsystem_guid, psystem_guid, flen);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 98d4306929f3..887adf4807d1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -10,6 +10,7 @@
 #include "esw/qos.h"
 #include "sf/dev/dev.h"
 #include "sf/sf.h"
+#include "lib/nv_param.h"
 
 static int mlx5_devlink_flash_update(struct devlink *devlink,
 				     struct devlink_flash_update_params *params,
@@ -35,6 +36,55 @@ static u16 mlx5_fw_ver_subminor(u32 version)
 	return version & 0xffff;
 }
 
+static int mlx5_devlink_serial_numbers_put(struct mlx5_core_dev *dev,
+					   struct devlink_info_req *req,
+					   struct netlink_ext_ack *extack)
+{
+	struct pci_dev *pdev = dev->pdev;
+	unsigned int vpd_size, kw_len;
+	char *str, *end;
+	u8 *vpd_data;
+	int err = 0;
+	int start;
+
+	vpd_data = pci_vpd_alloc(pdev, &vpd_size);
+	if (IS_ERR(vpd_data))
+		return 0;
+
+	start = pci_vpd_find_ro_info_keyword(vpd_data, vpd_size,
+					     PCI_VPD_RO_KEYWORD_SERIALNO, &kw_len);
+	if (start >= 0) {
+		str = kstrndup(vpd_data + start, kw_len, GFP_KERNEL);
+		if (!str) {
+			err = -ENOMEM;
+			goto end;
+		}
+		end = strchrnul(str, ' ');
+		*end = '\0';
+		err = devlink_info_board_serial_number_put(req, str);
+		kfree(str);
+		if (err)
+			goto end;
+	}
+
+	start = pci_vpd_find_ro_info_keyword(vpd_data, vpd_size, "V3", &kw_len);
+	if (start >= 0) {
+		str = kstrndup(vpd_data + start, kw_len, GFP_KERNEL);
+		if (!str) {
+			err = -ENOMEM;
+			goto end;
+		}
+		err = devlink_info_serial_number_put(req, str);
+		kfree(str);
+		if (err)
+			goto end;
+	}
+
+end:
+	kfree(vpd_data);
+	return err;
+}
+
 #define DEVLINK_FW_STRING_LEN 32
 
 static int
@@ -46,6 +96,13 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 	u32 running_fw, stored_fw;
 	int err;
 
+	if (!mlx5_core_is_pf(dev))
+		return 0;
+
+	err = mlx5_devlink_serial_numbers_put(dev, req, extack);
+	if (err)
+		return err;
+
 	err = devlink_info_version_fixed_put(req, "fw.psid", dev->board_id);
 	if (err)
 		return err;
@@ -104,7 +161,7 @@ static int mlx5_devlink_reload_fw_activate(struct devlink *devlink, struct netli
 	if (err)
 		return err;
 
-	mlx5_unload_one_devl_locked(dev, true);
+	mlx5_sync_reset_unload_flow(dev, true);
 	err = mlx5_health_wait_pci_up(dev);
 	if (err)
 		NL_SET_ERR_MSG_MOD(extack, "FW activate aborted, PCI reads fail after reset");
@@ -147,11 +204,6 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
 		return 0;
 	}
 
-	if (mlx5_lag_is_active(dev)) {
-		NL_SET_ERR_MSG_MOD(extack, "reload is unsupported in Lag mode");
-		return -EOPNOTSUPP;
-	}
-
 	if (mlx5_core_is_mp_slave(dev)) {
 		NL_SET_ERR_MSG_MOD(extack, "reload is unsupported for multi port slave");
 		return -EOPNOTSUPP;
@@ -320,11 +372,14 @@ static const struct devlink_ops mlx5_devlink_ops = {
 	.eswitch_encap_mode_get = mlx5_devlink_eswitch_encap_mode_get,
 	.rate_leaf_tx_share_set = mlx5_esw_devlink_rate_leaf_tx_share_set,
 	.rate_leaf_tx_max_set = mlx5_esw_devlink_rate_leaf_tx_max_set,
+	.rate_leaf_tc_bw_set = mlx5_esw_devlink_rate_leaf_tc_bw_set,
+	.rate_node_tc_bw_set = mlx5_esw_devlink_rate_node_tc_bw_set,
 	.rate_node_tx_share_set = mlx5_esw_devlink_rate_node_tx_share_set,
 	.rate_node_tx_max_set = mlx5_esw_devlink_rate_node_tx_max_set,
 	.rate_node_new = mlx5_esw_devlink_rate_node_new,
 	.rate_node_del = mlx5_esw_devlink_rate_node_del,
-	.rate_leaf_parent_set = mlx5_esw_devlink_rate_parent_set,
+	.rate_leaf_parent_set = mlx5_esw_devlink_rate_leaf_parent_set,
+	.rate_node_parent_set = mlx5_esw_devlink_rate_node_parent_set,
 #endif
 #ifdef CONFIG_MLX5_SF_MANAGER
 	.port_new = mlx5_devlink_sf_port_new,
@@ -475,6 +530,25 @@ mlx5_devlink_hairpin_queue_size_validate(struct devlink *devlink, u32 id,
 	return 0;
 }
 
+static int mlx5_devlink_num_doorbells_validate(struct devlink *devlink, u32 id,
+					       union devlink_param_value val,
+					       struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *mdev = devlink_priv(devlink);
+	u32 val32 = val.vu32;
+	u32 max_num_channels;
+
+	max_num_channels = mlx5e_get_max_num_channels(mdev);
+	if (val32 > max_num_channels) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Requested num_doorbells (%u) exceeds max number of channels (%u)",
+				       val32, max_num_channels);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static void mlx5_devlink_hairpin_params_init_values(struct devlink *devlink)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
@@ -554,6 +628,9 @@ static const struct devlink_param mlx5_devlink_eth_params[] = {
 			     "hairpin_queue_size", DEVLINK_PARAM_TYPE_U32,
 			     BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), NULL, NULL,
 			     mlx5_devlink_hairpin_queue_size_validate),
+	DEVLINK_PARAM_GENERIC(NUM_DOORBELLS,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), NULL, NULL,
+			      mlx5_devlink_num_doorbells_validate),
 };
 
 static int mlx5_devlink_eth_params_register(struct devlink *devlink)
@@ -577,6 +654,10 @@ static int mlx5_devlink_eth_params_register(struct devlink *devlink)
 
 	mlx5_devlink_hairpin_params_init_values(devlink);
 
+	value.vu32 = MLX5_DEFAULT_NUM_DOORBELLS;
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_NUM_DOORBELLS,
+					value);
 	return 0;
 }
 
@@ -591,6 +672,105 @@ static void mlx5_devlink_eth_params_unregister(struct devlink *devlink)
 			       ARRAY_SIZE(mlx5_devlink_eth_params));
 }
 
+#define MLX5_PCIE_CONG_THRESH_MAX	10000
+#define MLX5_PCIE_CONG_THRESH_DEF_LOW	7500
+#define MLX5_PCIE_CONG_THRESH_DEF_HIGH	9000
+
+static int
+mlx5_devlink_pcie_cong_thresh_validate(struct devlink *devl, u32 id,
+				       union devlink_param_value val,
+				       struct netlink_ext_ack *extack)
+{
+	if (val.vu16 > MLX5_PCIE_CONG_THRESH_MAX) {
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Value %u > max supported (%u)",
+				       val.vu16, MLX5_PCIE_CONG_THRESH_MAX);
+
+		return -EINVAL;
+	}
+
+	switch (id) {
+	case MLX5_DEVLINK_PARAM_ID_PCIE_CONG_IN_LOW:
+	case MLX5_DEVLINK_PARAM_ID_PCIE_CONG_IN_HIGH:
+	case MLX5_DEVLINK_PARAM_ID_PCIE_CONG_OUT_LOW:
+	case MLX5_DEVLINK_PARAM_ID_PCIE_CONG_OUT_HIGH:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static void mlx5_devlink_pcie_cong_init_values(struct devlink *devlink)
+{
+	union devlink_param_value value;
+	u32 id;
+
+	value.vu16 = MLX5_PCIE_CONG_THRESH_DEF_LOW;
+	id = MLX5_DEVLINK_PARAM_ID_PCIE_CONG_IN_LOW;
+	devl_param_driverinit_value_set(devlink, id, value);
+
+	value.vu16 = MLX5_PCIE_CONG_THRESH_DEF_HIGH;
+	id = MLX5_DEVLINK_PARAM_ID_PCIE_CONG_IN_HIGH;
+	devl_param_driverinit_value_set(devlink, id, value);
+
+	value.vu16 = MLX5_PCIE_CONG_THRESH_DEF_LOW;
+	id = MLX5_DEVLINK_PARAM_ID_PCIE_CONG_OUT_LOW;
+	devl_param_driverinit_value_set(devlink, id, value);
+
+	value.vu16 = MLX5_PCIE_CONG_THRESH_DEF_HIGH;
+	id = MLX5_DEVLINK_PARAM_ID_PCIE_CONG_OUT_HIGH;
+	devl_param_driverinit_value_set(devlink, id, value);
+}
+
+static const struct devlink_param mlx5_devlink_pcie_cong_params[] = {
+	DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_PCIE_CONG_IN_LOW,
+			     "pcie_cong_inbound_low", DEVLINK_PARAM_TYPE_U16,
+			     BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), NULL, NULL,
+			     mlx5_devlink_pcie_cong_thresh_validate),
+	DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_PCIE_CONG_IN_HIGH,
+			     "pcie_cong_inbound_high", DEVLINK_PARAM_TYPE_U16,
+			     BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), NULL, NULL,
+			     mlx5_devlink_pcie_cong_thresh_validate),
+	DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_PCIE_CONG_OUT_LOW,
+			     "pcie_cong_outbound_low", DEVLINK_PARAM_TYPE_U16,
+			     BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), NULL, NULL,
+			     mlx5_devlink_pcie_cong_thresh_validate),
+	DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_PCIE_CONG_OUT_HIGH,
+			     "pcie_cong_outbound_high", DEVLINK_PARAM_TYPE_U16,
+			     BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), NULL, NULL,
+			     mlx5_devlink_pcie_cong_thresh_validate),
+};
+
+static int mlx5_devlink_pcie_cong_params_register(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	int err;
+
+	if (!mlx5_pcie_cong_event_supported(dev))
+		return 0;
+
+	err = devl_params_register(devlink, mlx5_devlink_pcie_cong_params,
+				   ARRAY_SIZE(mlx5_devlink_pcie_cong_params));
+	if (err)
+		return err;
+
+	mlx5_devlink_pcie_cong_init_values(devlink);
+
+	return 0;
+}
+
+static void mlx5_devlink_pcie_cong_params_unregister(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	if (!mlx5_pcie_cong_event_supported(dev))
+		return;
+
+	devl_params_unregister(devlink, mlx5_devlink_pcie_cong_params,
+			       ARRAY_SIZE(mlx5_devlink_pcie_cong_params));
+}
+
 static int mlx5_devlink_enable_rdma_validate(struct devlink *devlink, u32 id,
 					     union devlink_param_value val,
 					     struct netlink_ext_ack *extack)
@@ -836,8 +1016,20 @@ int mlx5_devlink_params_register(struct devlink *devlink)
 	if (err)
 		goto max_uc_list_err;
 
+	err = mlx5_devlink_pcie_cong_params_register(devlink);
+	if (err)
+		goto pcie_cong_err;
+
+	err = mlx5_nv_param_register_dl_params(devlink);
+	if (err)
+		goto nv_param_err;
+
 	return 0;
 
+nv_param_err:
+	mlx5_devlink_pcie_cong_params_unregister(devlink);
+pcie_cong_err:
+	mlx5_devlink_max_uc_list_params_unregister(devlink);
 max_uc_list_err:
 	mlx5_devlink_auxdev_params_unregister(devlink);
 auxdev_reg_err:
@@ -848,6 +1040,8 @@ auxdev_reg_err:
 
 void mlx5_devlink_params_unregister(struct devlink *devlink)
 {
+	mlx5_nv_param_unregister_dl_params(devlink);
+	mlx5_devlink_pcie_cong_params_unregister(devlink);
 	mlx5_devlink_max_uc_list_params_unregister(devlink);
 	mlx5_devlink_auxdev_params_unregister(devlink);
 	devl_params_unregister(devlink, mlx5_devlink_params,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
index 961f75da6227..43b9bf8829cf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
@@ -22,6 +22,12 @@ enum mlx5_devlink_param_id {
 	MLX5_DEVLINK_PARAM_ID_ESW_MULTIPORT,
 	MLX5_DEVLINK_PARAM_ID_HAIRPIN_NUM_QUEUES,
 	MLX5_DEVLINK_PARAM_ID_HAIRPIN_QUEUE_SIZE,
+	MLX5_DEVLINK_PARAM_ID_PCIE_CONG_IN_LOW,
+	MLX5_DEVLINK_PARAM_ID_PCIE_CONG_IN_HIGH,
+	MLX5_DEVLINK_PARAM_ID_PCIE_CONG_OUT_LOW,
+	MLX5_DEVLINK_PARAM_ID_PCIE_CONG_OUT_HIGH,
+	MLX5_DEVLINK_PARAM_ID_CQE_COMPRESSION_TYPE,
+	MLX5_DEVLINK_PARAM_ID_SWP_L4_CSUM_MODE,
 };
 
 struct mlx5_trap_ctx {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index 080e7eab52c7..7bcf822a89f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -54,7 +54,7 @@ static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer)
 
 	if (!MLX5_GET(mtrc_cap, out, trace_to_memory)) {
 		mlx5_core_dbg(dev, "FWTracer: Device does not support logging traces to memory\n");
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	tracer->trc_ver = MLX5_GET(mtrc_cap, out, trc_ver);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c
index c7216e84ef8c..7cae0c6e5e8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. */
 
+#include <linux/mlx5/vport.h>
+
 #include "reporter_vnic.h"
 #include "en_stats.h"
 #include "devlink.h"
@@ -13,6 +15,50 @@ struct mlx5_vnic_diag_stats {
 	__be64 query_vnic_env_out[MLX5_ST_SZ_QW(query_vnic_env_out)];
 };
 
+static void mlx5_reporter_vnic_diagnose_counter_icm(struct mlx5_core_dev *dev,
+						    struct devlink_fmsg *fmsg,
+						    u16 vport_num, bool other_vport)
+{
+	u32 out_icm_reg[MLX5_ST_SZ_DW(vhca_icm_ctrl_reg)] = {};
+	u32 in_icm_reg[MLX5_ST_SZ_DW(vhca_icm_ctrl_reg)] = {};
+	u32 out_reg[MLX5_ST_SZ_DW(nic_cap_reg)] = {};
+	u32 in_reg[MLX5_ST_SZ_DW(nic_cap_reg)] = {};
+	u32 cur_alloc_icm;
+	int vhca_icm_ctrl;
+	u16 vhca_id;
+	int err;
+
+	err = mlx5_core_access_reg(dev, in_reg, sizeof(in_reg), out_reg,
+				   sizeof(out_reg), MLX5_REG_NIC_CAP, 0, 0);
+	if (err) {
+		mlx5_core_warn(dev, "Reading nic_cap_reg failed. err = %d\n", err);
+		return;
+	}
+	vhca_icm_ctrl = MLX5_GET(nic_cap_reg, out_reg, vhca_icm_ctrl);
+	if (!vhca_icm_ctrl)
+		return;
+
+	MLX5_SET(vhca_icm_ctrl_reg, in_icm_reg, vhca_id_valid, other_vport);
+	if (other_vport) {
+		err = mlx5_vport_get_vhca_id(dev, vport_num, &vhca_id);
+		if (err) {
+			mlx5_core_warn(dev, "vport to vhca_id failed. vport_num = %d, err = %d\n",
+				       vport_num, err);
+			return;
+		}
+		MLX5_SET(vhca_icm_ctrl_reg, in_icm_reg, vhca_id, vhca_id);
+	}
+	err = mlx5_core_access_reg(dev, in_icm_reg, sizeof(in_icm_reg),
+				   out_icm_reg, sizeof(out_icm_reg),
+				   MLX5_REG_VHCA_ICM_CTRL, 0, 0);
+	if (err) {
+		mlx5_core_warn(dev, "Reading vhca_icm_ctrl failed. err = %d\n", err);
+		return;
+	}
+	cur_alloc_icm = MLX5_GET(vhca_icm_ctrl_reg, out_icm_reg, cur_alloc_icm);
+	devlink_fmsg_u32_pair_put(fmsg, "icm_consumption", cur_alloc_icm);
+}
+
 void mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev,
 					  struct devlink_fmsg *fmsg,
 					  u16 vport_num, bool other_vport)
@@ -59,6 +105,17 @@ void mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev,
 		devlink_fmsg_u64_pair_put(fmsg, "handled_pkt_steering_fail",
 					  VNIC_ENV_GET64(&vnic, handled_pkt_steering_fail));
 	}
+	if (MLX5_CAP_GEN(dev, nic_cap_reg))
+		mlx5_reporter_vnic_diagnose_counter_icm(dev, fmsg, vport_num, other_vport);
+	if (MLX5_CAP_GEN(dev, vnic_env_cnt_bar_uar_access))
+		devlink_fmsg_u32_pair_put(fmsg, "bar_uar_access",
+					  VNIC_ENV_GET(&vnic, bar_uar_access));
+	if (MLX5_CAP_GEN(dev, vnic_env_cnt_odp_page_fault)) {
+		devlink_fmsg_u32_pair_put(fmsg, "odp_local_triggered_page_fault",
+					  VNIC_ENV_GET(&vnic, odp_local_triggered_page_fault));
+		devlink_fmsg_u32_pair_put(fmsg, "odp_remote_triggered_page_fault",
+					  VNIC_ENV_GET(&vnic, odp_remote_triggered_page_fault));
+	}
 
 	devlink_fmsg_obj_nest_end(fmsg);
 	devlink_fmsg_pair_nest_end(fmsg);
@@ -87,11 +144,11 @@ void mlx5_reporter_vnic_create(struct mlx5_core_dev *dev)
 	health->vnic_reporter =
 		devlink_health_reporter_create(devlink,
 					       &mlx5_reporter_vnic_ops,
-					       0, dev);
+					       dev);
 	if (IS_ERR(health->vnic_reporter))
 		mlx5_core_warn(dev,
-			       "Failed to create vnic reporter, err = %ld\n",
-			       PTR_ERR(health->vnic_reporter));
+			       "Failed to create vnic reporter, err = %pe\n",
+			       health->vnic_reporter);
 }
 
 void mlx5_reporter_vnic_destroy(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
index 31142f6cc372..1e5522a19483 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
@@ -242,7 +242,7 @@ static int mlx5_dpll_clock_quality_level_get(const struct dpll_device *dpll,
 		return 0;
 	}
 errout:
-	NL_SET_ERR_MSG_MOD(extack, "Invalid clock quality level obtained from firmware\n");
+	NL_SET_ERR_MSG_MOD(extack, "Invalid clock quality level obtained from firmware");
 	return -EINVAL;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 979fc56205e1..811178d8976c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -47,6 +47,7 @@
 #include <linux/rhashtable.h>
 #include <net/udp_tunnel.h>
 #include <net/switchdev.h>
+#include <net/psp/types.h>
 #include <net/xdp.h>
 #include <linux/dim.h>
 #include <linux/bits.h>
@@ -68,7 +69,7 @@ struct page_pool;
 #define MLX5E_METADATA_ETHER_TYPE (0x8CE4)
 #define MLX5E_METADATA_ETHER_LEN 8
 
-#define MLX5E_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
+#define MLX5E_ETH_HARD_MTU (ETH_HLEN + PSP_ENCAP_HLEN + PSP_TRL_SIZE + VLAN_HLEN + ETH_FCS_LEN)
 
 #define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu))
 #define MLX5E_SW2HW_MTU(params, swmtu) ((swmtu) + ((params)->hard_mtu))
@@ -84,9 +85,10 @@ struct page_pool;
 #define MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE (9)
 #define MLX5E_SHAMPO_WQ_HEADER_PER_PAGE (PAGE_SIZE >> MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE)
 #define MLX5E_SHAMPO_LOG_WQ_HEADER_PER_PAGE (PAGE_SHIFT - MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE)
-#define MLX5E_SHAMPO_WQ_BASE_HEAD_ENTRY_SIZE (64)
-#define MLX5E_SHAMPO_WQ_RESRV_SIZE (64 * 1024)
-#define MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE (4096)
+#define MLX5E_SHAMPO_WQ_BASE_HEAD_ENTRY_SIZE_SHIFT (6)
+#define MLX5E_SHAMPO_WQ_RESRV_SIZE_BASE_SHIFT (12)
+#define MLX5E_SHAMPO_WQ_LOG_RESRV_SIZE (16)
+#define MLX5E_SHAMPO_WQ_RESRV_SIZE BIT(MLX5E_SHAMPO_WQ_LOG_RESRV_SIZE)
 
 #define MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev) \
 	(6 + MLX5_CAP_GEN(mdev, cache_line_128byte)) /* HW restriction */
@@ -95,8 +97,6 @@ struct page_pool;
 #define MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev) \
 	MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, order_base_2(MLX5E_RX_MAX_HEAD))
 
-#define MLX5_MPWRQ_MAX_LOG_WQE_SZ 18
-
 /* Keep in sync with mlx5e_mpwrq_log_wqe_sz.
  * These are theoretical maximums, which can be further restricted by
  * capabilities. These values are used for static resource allocations and
@@ -232,16 +232,22 @@ struct mlx5e_rx_wqe_cyc {
 	DECLARE_FLEX_ARRAY(struct mlx5_wqe_data_seg, data);
 };
 
-struct mlx5e_umr_wqe {
+struct mlx5e_umr_wqe_hdr {
 	struct mlx5_wqe_ctrl_seg       ctrl;
 	struct mlx5_wqe_umr_ctrl_seg   uctrl;
 	struct mlx5_mkey_seg           mkc;
+};
+
+struct mlx5e_umr_wqe {
+	struct mlx5e_umr_wqe_hdr hdr;
 	union {
 		DECLARE_FLEX_ARRAY(struct mlx5_mtt, inline_mtts);
 		DECLARE_FLEX_ARRAY(struct mlx5_klm, inline_klms);
 		DECLARE_FLEX_ARRAY(struct mlx5_ksm, inline_ksms);
 	};
 };
+static_assert(offsetof(struct mlx5e_umr_wqe, inline_mtts) == sizeof(struct mlx5e_umr_wqe_hdr),
+	      "struct members should be included in struct mlx5e_umr_wqe_hdr, not in struct mlx5e_umr_wqe");
 
 enum mlx5e_priv_flag {
 	MLX5E_PFLAG_RX_CQE_BASED_MODER,
@@ -274,10 +280,6 @@ enum packet_merge {
 struct mlx5e_packet_merge_param {
 	enum packet_merge type;
 	u32 timeout;
-	struct {
-		u8 match_criteria_type;
-		u8 alignment_granularity;
-	} shampo;
 };
 
 struct mlx5e_params {
@@ -343,6 +345,7 @@ struct mlx5e_cq {
 	/* data path - accessed per napi poll */
 	u16                        event_ctr;
 	struct napi_struct        *napi;
+	struct mlx5_uars_page     *uar;
 	struct mlx5_core_cq        mcq;
 	struct mlx5e_ch_stats     *ch_stats;
 
@@ -374,7 +377,7 @@ struct mlx5e_sq_dma {
 	enum mlx5e_dma_map_type type;
 };
 
-/* Keep this enum consistent with with the corresponding strings array
+/* Keep this enum consistent with the corresponding strings array
  * declared in en/reporter_tx.c
  */
 enum {
@@ -383,10 +386,8 @@ enum {
 	MLX5E_SQ_STATE_RECOVERING,
 	MLX5E_SQ_STATE_IPSEC,
 	MLX5E_SQ_STATE_DIM,
-	MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE,
 	MLX5E_SQ_STATE_PENDING_XSK_TX,
 	MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC,
-	MLX5E_SQ_STATE_XDP_MULTIBUF,
 	MLX5E_NUM_SQ_STATES, /* Must be kept last */
 };
 
@@ -395,6 +396,7 @@ struct mlx5e_tx_mpwqe {
 	struct mlx5e_tx_wqe *wqe;
 	u32 bytes_count;
 	u8 ds_count;
+	u8 ds_count_max;
 	u8 pkt_count;
 	u8 inline_on;
 };
@@ -516,6 +518,12 @@ struct mlx5e_xdpsq {
 	struct mlx5e_channel      *channel;
 } ____cacheline_aligned_in_smp;
 
+struct mlx5e_xdp_buff {
+	struct xdp_buff xdp;
+	struct mlx5_cqe64 *cqe;
+	struct mlx5e_rq *rq;
+};
+
 struct mlx5e_ktls_resync_resp;
 
 struct mlx5e_icosq {
@@ -547,7 +555,7 @@ struct mlx5e_icosq {
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_frag_page {
-	struct page *page;
+	netmem_ref netmem;
 	u16 frags;
 };
 
@@ -624,15 +632,16 @@ struct mlx5e_dma_info {
 };
 
 struct mlx5e_shampo_hd {
-	u32 mkey;
 	struct mlx5e_frag_page *pages;
 	u32 hd_per_wq;
+	u32 hd_per_page;
 	u16 hd_per_wqe;
-	u16 pages_per_wq;
+	u8 log_hd_per_page;
+	u8 log_hd_entry_size;
 	unsigned long *bitmap;
 	u16 pi;
 	u16 ci;
-	__be32 key;
+	__be32 mkey_be;
 };
 
 struct mlx5e_hw_gro_data {
@@ -660,7 +669,7 @@ struct mlx5e_rq {
 		} wqe;
 		struct {
 			struct mlx5_wq_ll      wq;
-			struct mlx5e_umr_wqe   umr_wqe;
+			struct mlx5e_umr_wqe_hdr umr_wqe;
 			struct mlx5e_mpw_info *info;
 			mlx5e_fp_skb_from_cqe_mpwrq skb_from_cqe_mpwrq;
 			__be32                 umr_mkey_be;
@@ -690,7 +699,7 @@ struct mlx5e_rq {
 	struct mlx5e_rq_stats *stats;
 	struct mlx5e_cq        cq;
 	struct mlx5e_cq_decomp cqd;
-	struct hwtstamp_config *tstamp;
+	struct kernel_hwtstamp_config *hwtstamp_config;
 	struct mlx5_clock      *clock;
 	struct mlx5e_icosq    *icosq;
 	struct mlx5e_priv     *priv;
@@ -711,12 +720,18 @@ struct mlx5e_rq {
 	struct bpf_prog __rcu *xdp_prog;
 	struct mlx5e_xdpsq    *xdpsq;
 	DECLARE_BITMAP(flags, 8);
+
+	/* page pools */
 	struct page_pool      *page_pool;
+	struct page_pool      *hd_page_pool;
+
+	struct mlx5e_xdp_buff mxbuf;
 
 	/* AF_XDP zero-copy */
 	struct xsk_buff_pool  *xsk_pool;
 
 	struct work_struct     recover_work;
+	struct work_struct     rx_timeout_work;
 
 	/* control */
 	struct mlx5_wq_ctrl    wq_ctrl;
@@ -772,12 +787,12 @@ struct mlx5e_channel {
 	/* control */
 	struct mlx5e_priv         *priv;
 	struct mlx5_core_dev      *mdev;
-	struct hwtstamp_config    *tstamp;
 	DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES);
 	int                        ix;
 	int                        vec_ix;
 	int                        sd_ix;
 	int                        cpu;
+	struct mlx5_sq_bfreg      *bfreg;
 	/* Sync between icosq recovery and XSK enable/disable. */
 	struct mutex               icosq_recovery_lock;
 
@@ -905,12 +920,14 @@ struct mlx5e_priv {
 	u8                         max_opened_tc;
 	bool                       tx_ptp_opened;
 	bool                       rx_ptp_opened;
-	struct hwtstamp_config     tstamp;
+	struct kernel_hwtstamp_config hwtstamp_config;
 	u16                        q_counter[MLX5_SD_MAX_GROUP_SZ];
 	u16                        drop_rq_q_counter;
 	struct notifier_block      events_nb;
 	struct notifier_block      blocking_events_nb;
 
+	struct mlx5e_pcie_cong_event *cong_event;
+
 	struct udp_tunnel_nic_info nic_info;
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	struct mlx5e_dcbx          dcbx;
@@ -924,6 +941,9 @@ struct mlx5e_priv {
 #ifdef CONFIG_MLX5_EN_IPSEC
 	struct mlx5e_ipsec        *ipsec;
 #endif
+#ifdef CONFIG_MLX5_EN_PSP
+	struct mlx5e_psp          *psp;
+#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	struct mlx5e_tls          *tls;
 #endif
@@ -938,6 +958,7 @@ struct mlx5e_priv {
 	struct mlx5e_mqprio_rl    *mqprio_rl;
 	struct dentry             *dfs_root;
 	struct mlx5_devcom_comp_dev *devcom;
+	struct ethtool_fec_hist_range *fec_ranges;
 };
 
 struct mlx5e_dev {
@@ -1008,8 +1029,11 @@ void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest,
 		     u64 *buf);
 void mlx5e_set_rx_mode_work(struct work_struct *work);
 
-int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr);
-int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr);
+int mlx5e_hwtstamp_set(struct mlx5e_priv *priv,
+		       struct kernel_hwtstamp_config *config,
+		       struct netlink_ext_ack *extack);
+int mlx5e_hwtstamp_get(struct mlx5e_priv *priv,
+		       struct kernel_hwtstamp_config *config);
 int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val, bool rx_filter);
 
 int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
@@ -1048,6 +1072,7 @@ struct mlx5e_create_cq_param {
 	struct mlx5e_ch_stats *ch_stats;
 	int node;
 	int ix;
+	struct mlx5_uars_page *uar;
 };
 
 struct mlx5e_cq_param;
@@ -1134,7 +1159,9 @@ extern const struct ethtool_ops mlx5e_ethtool_ops;
 int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey);
 int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
-int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
+int mlx5e_modify_tirs_lb(struct mlx5_core_dev *mdev, bool enable_uc_lb,
+			 bool enable_mc_lb);
+int mlx5e_refresh_tirs(struct mlx5_core_dev *mdev, bool enable_uc_lb,
 		       bool enable_mc_lb);
 void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc);
 
@@ -1222,7 +1249,7 @@ void mlx5e_netdev_attach_nic_profile(struct mlx5e_priv *priv);
 void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv);
 void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu);
 
-void mlx5e_set_xdp_feature(struct net_device *netdev);
+void mlx5e_set_xdp_feature(struct mlx5e_priv *priv);
 netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 				       struct net_device *netdev,
 				       netdev_features_t features);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h
index b59aee75de94..2c98a5299df3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h
@@ -26,7 +26,6 @@ struct mlx5e_dcbx {
 	u8                         cap;
 
 	/* Buffer configuration */
-	bool                       manual_buffer;
 	u32                        cable_len;
 	u32                        xoff;
 	u16                        port_buff_cell_sz;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
index 0b1ac6e5c890..8818f65d1fbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
@@ -40,11 +40,8 @@ void mlx5e_destroy_devlink(struct mlx5e_dev *mlx5e_dev)
 static void
 mlx5e_devlink_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_item_id *ppid)
 {
-	u64 parent_id;
-
-	parent_id = mlx5_query_nic_system_image_guid(dev);
-	ppid->id_len = sizeof(parent_id);
-	memcpy(ppid->id, &parent_id, sizeof(parent_id));
+	BUILD_BUG_ON(MLX5_SW_IMAGE_GUID_MAX_BYTES > MAX_PHYS_ITEM_ID_LEN);
+	mlx5_query_nic_sw_system_image_guid(dev, ppid->id, &ppid->id_len);
 }
 
 int mlx5e_devlink_port_register(struct mlx5e_dev *mlx5e_dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 1e8b7d330701..c3408b3f7010 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -18,7 +18,8 @@ enum {
 
 enum {
 	MLX5E_TC_PRIO = 0,
-	MLX5E_NIC_PRIO
+	MLX5E_PROMISC_PRIO,
+	MLX5E_NIC_PRIO,
 };
 
 struct mlx5e_flow_table {
@@ -56,7 +57,7 @@ struct mlx5e_l2_table {
 	bool                       promisc_enabled;
 };
 
-#define MLX5E_NUM_INDIR_TIRS (MLX5_NUM_TT - 1)
+#define MLX5E_NUM_INDIR_TIRS (MLX5_NUM_INDIR_TIRS)
 
 #define MLX5_HASH_IP		(MLX5_HASH_FIELD_SEL_SRC_IP   |\
 				 MLX5_HASH_FIELD_SEL_DST_IP)
@@ -68,9 +69,13 @@ struct mlx5e_l2_table {
 				 MLX5_HASH_FIELD_SEL_DST_IP   |\
 				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
 
-/* NIC prio FTS */
+/* NIC promisc FT level */
 enum {
 	MLX5E_PROMISC_FT_LEVEL,
+};
+
+/* NIC prio FTS */
+enum {
 	MLX5E_VLAN_FT_LEVEL,
 	MLX5E_L2_FT_LEVEL,
 	MLX5E_TTC_FT_LEVEL,
@@ -83,10 +88,11 @@ enum {
 #ifdef CONFIG_MLX5_EN_ARFS
 	MLX5E_ARFS_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
 #endif
-#ifdef CONFIG_MLX5_EN_IPSEC
-	MLX5E_ACCEL_FS_POL_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
-	MLX5E_ACCEL_FS_ESP_FT_LEVEL,
+#if defined(CONFIG_MLX5_EN_IPSEC) || defined(CONFIG_MLX5_EN_PSP)
+	MLX5E_ACCEL_FS_ESP_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
 	MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL,
+	MLX5E_ACCEL_FS_POL_FT_LEVEL,
+	MLX5E_ACCEL_FS_POL_MISS_FT_LEVEL,
 	MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL,
 #endif
 };
@@ -126,7 +132,8 @@ struct mlx5e_ptp_fs;
 
 void mlx5e_set_ttc_params(struct mlx5e_flow_steering *fs,
 			  struct mlx5e_rx_res *rx_res,
-			  struct ttc_params *ttc_params, bool tunnel);
+			  struct ttc_params *ttc_params, bool tunnel,
+			  bool ipsec_rss);
 
 void mlx5e_destroy_ttc_table(struct mlx5e_flow_steering *fs);
 int mlx5e_create_ttc_table(struct mlx5e_flow_steering  *fs,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_ethtool.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_ethtool.h
index 9e276fd3c0cf..c21fe36527a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_ethtool.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_ethtool.h
@@ -11,6 +11,11 @@ int mlx5e_ethtool_alloc(struct mlx5e_ethtool_steering **ethtool);
 void mlx5e_ethtool_free(struct mlx5e_ethtool_steering *ethtool);
 void mlx5e_ethtool_init_steering(struct mlx5e_flow_steering *fs);
 void mlx5e_ethtool_cleanup_steering(struct mlx5e_flow_steering *fs);
+int mlx5e_ethtool_set_rxfh_fields(struct mlx5e_priv *priv,
+				  const struct ethtool_rxfh_fields *nfc,
+				  struct netlink_ext_ack *extack);
+int mlx5e_ethtool_get_rxfh_fields(struct mlx5e_priv *priv,
+				  struct ethtool_rxfh_fields *nfc);
 int mlx5e_ethtool_set_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *cmd);
 int mlx5e_ethtool_get_rxnfc(struct mlx5e_priv *priv,
 			    struct ethtool_rxnfc *info, u32 *rule_locs);
@@ -20,6 +25,15 @@ static inline int mlx5e_ethtool_alloc(struct mlx5e_ethtool_steering **ethtool)
 static inline void mlx5e_ethtool_free(struct mlx5e_ethtool_steering *ethtool) { }
 static inline void mlx5e_ethtool_init_steering(struct mlx5e_flow_steering *fs) { }
 static inline void mlx5e_ethtool_cleanup_steering(struct mlx5e_flow_steering *fs) { }
+static inline int
+mlx5e_ethtool_set_rxfh_fields(struct mlx5e_priv *priv,
+			      const struct ethtool_rxfh_fields *nfc,
+			      struct netlink_ext_ack *extack)
+{ return -EOPNOTSUPP; }
+static inline int
+mlx5e_ethtool_get_rxfh_fields(struct mlx5e_priv *priv,
+			      struct ethtool_rxfh_fields *nfc)
+{ return -EOPNOTSUPP; }
 static inline int mlx5e_ethtool_set_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *cmd)
 { return -EOPNOTSUPP; }
 static inline int mlx5e_ethtool_get_rxnfc(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
index 81523825faa2..cb972b2d46e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
@@ -114,6 +114,7 @@ int mlx5e_health_recover_channels(struct mlx5e_priv *priv)
 	int err = 0;
 
 	rtnl_lock();
+	netdev_lock(priv->netdev);
 	mutex_lock(&priv->state_lock);
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
@@ -123,6 +124,7 @@ int mlx5e_health_recover_channels(struct mlx5e_priv *priv)
 
 out:
 	mutex_unlock(&priv->state_lock);
+	netdev_unlock(priv->netdev);
 	rtnl_unlock();
 
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
index b4f3bd7d346e..195863b2c013 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
@@ -138,8 +138,8 @@ void mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv)
 	if (IS_ERR_OR_NULL(agent)) {
 		if (IS_ERR(agent))
 			netdev_warn(priv->netdev,
-				    "Failed to create hv vhca stats agent, err = %ld\n",
-				    PTR_ERR(agent));
+				    "Failed to create hv vhca stats agent, err = %pe\n",
+				    agent);
 
 		kvfree(priv->stats_agent.buf);
 		return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c
index 4e72ca8070e2..1de18c7e96ec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c
@@ -6,6 +6,7 @@
 #include <linux/xarray.h>
 #include <linux/hashtable.h>
 #include <linux/refcount.h>
+#include <linux/mlx5/driver.h>
 
 #include "mapping.h"
 
@@ -24,7 +25,8 @@ struct mapping_ctx {
 	struct delayed_work dwork;
 	struct list_head pending_list;
 	spinlock_t pending_list_lock; /* Guards pending list */
-	u64 id;
+	u8 id[MLX5_SW_IMAGE_GUID_MAX_BYTES];
+	u8 id_len;
 	u8 type;
 	struct list_head list;
 	refcount_t refcount;
@@ -220,13 +222,15 @@ mapping_create(size_t data_size, u32 max_id, bool delayed_removal)
 }
 
 struct mapping_ctx *
-mapping_create_for_id(u64 id, u8 type, size_t data_size, u32 max_id, bool delayed_removal)
+mapping_create_for_id(u8 *id, u8 id_len, u8 type, size_t data_size, u32 max_id,
+		      bool delayed_removal)
 {
 	struct mapping_ctx *ctx;
 
 	mutex_lock(&shared_ctx_lock);
 	list_for_each_entry(ctx, &shared_ctx_list, list) {
-		if (ctx->id == id && ctx->type == type) {
+		if (ctx->type == type && ctx->id_len == id_len &&
+		    !memcmp(id, ctx->id, id_len)) {
 			if (refcount_inc_not_zero(&ctx->refcount))
 				goto unlock;
 			break;
@@ -237,7 +241,8 @@ mapping_create_for_id(u64 id, u8 type, size_t data_size, u32 max_id, bool delaye
 	if (IS_ERR(ctx))
 		goto unlock;
 
-	ctx->id = id;
+	memcpy(ctx->id, id, id_len);
+	ctx->id_len = id_len;
 	ctx->type = type;
 	list_add(&ctx->list, &shared_ctx_list);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h
index 4e2119f0f4c1..e86a103d58b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h
@@ -27,6 +27,7 @@ void mapping_destroy(struct mapping_ctx *ctx);
 /* adds mapping with an id or get an existing mapping with the same id
  */
 struct mapping_ctx *
-mapping_create_for_id(u64 id, u8 type, size_t data_size, u32 max_id, bool delayed_removal);
+mapping_create_for_id(u8 *id, u8 id_len, u8 type, size_t data_size, u32 max_id,
+		      bool delayed_removal);
 
 #endif /* __MLX5_MAPPING_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 64b62ed17b07..c9bdee9a8b30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -6,10 +6,14 @@
 #include "en/port.h"
 #include "en_accel/en_accel.h"
 #include "en_accel/ipsec.h"
+#include "en_accel/psp.h"
 #include <linux/dim.h>
 #include <net/page_pool/types.h>
 #include <net/xdp_sock_drv.h>
 
+#define MLX5_MPWRQ_MAX_LOG_WQE_SZ 18
+#define MLX5_REP_MPWRQ_MAX_LOG_WQE_SZ 17
+
 static u8 mlx5e_mpwrq_min_page_shift(struct mlx5_core_dev *mdev)
 {
 	u8 min_page_shift = MLX5_CAP_GEN_2(mdev, log_min_mkey_entity_size);
@@ -96,25 +100,29 @@ u8 mlx5e_mpwrq_umr_entry_size(enum mlx5e_mpwrq_umr_mode mode)
 		return sizeof(struct mlx5_ksm) * 4;
 	}
 	WARN_ONCE(1, "MPWRQ UMR mode %d is not known\n", mode);
-	return 0;
+	return 1;
 }
 
 u8 mlx5e_mpwrq_log_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift,
 			  enum mlx5e_mpwrq_umr_mode umr_mode)
 {
 	u8 umr_entry_size = mlx5e_mpwrq_umr_entry_size(umr_mode);
-	u8 max_pages_per_wqe, max_log_mpwqe_size;
+	u8 max_pages_per_wqe, max_log_wqe_size_calc;
+	u8 max_log_wqe_size_cap;
 	u16 max_wqe_size;
 
 	/* Keep in sync with MLX5_MPWRQ_MAX_PAGES_PER_WQE. */
 	max_wqe_size = mlx5e_get_max_sq_aligned_wqebbs(mdev) * MLX5_SEND_WQE_BB;
 	max_pages_per_wqe = ALIGN_DOWN(max_wqe_size - sizeof(struct mlx5e_umr_wqe),
 				       MLX5_UMR_FLEX_ALIGNMENT) / umr_entry_size;
-	max_log_mpwqe_size = ilog2(max_pages_per_wqe) + page_shift;
+	max_log_wqe_size_calc = ilog2(max_pages_per_wqe) + page_shift;
 
-	WARN_ON_ONCE(max_log_mpwqe_size < MLX5E_ORDER2_MAX_PACKET_MTU);
+	WARN_ON_ONCE(max_log_wqe_size_calc < MLX5E_ORDER2_MAX_PACKET_MTU);
 
-	return min_t(u8, max_log_mpwqe_size, MLX5_MPWRQ_MAX_LOG_WQE_SZ);
+	max_log_wqe_size_cap = mlx5_core_is_ecpf(mdev) ?
+			   MLX5_REP_MPWRQ_MAX_LOG_WQE_SZ : MLX5_MPWRQ_MAX_LOG_WQE_SZ;
+
+	return min_t(u8, max_log_wqe_size_calc, max_log_wqe_size_cap);
 }
 
 u8 mlx5e_mpwrq_pages_per_wqe(struct mlx5_core_dev *mdev, u8 page_shift,
@@ -407,25 +415,10 @@ u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5_core_dev *mdev,
 	return params->log_rq_mtu_frames - log_pkts_per_wqe;
 }
 
-u8 mlx5e_shampo_get_log_hd_entry_size(struct mlx5_core_dev *mdev,
-				      struct mlx5e_params *params)
+static u8 mlx5e_shampo_get_log_pkt_per_rsrv(struct mlx5e_params *params)
 {
-	return order_base_2(DIV_ROUND_UP(MLX5E_RX_MAX_HEAD, MLX5E_SHAMPO_WQ_BASE_HEAD_ENTRY_SIZE));
-}
-
-u8 mlx5e_shampo_get_log_rsrv_size(struct mlx5_core_dev *mdev,
-				  struct mlx5e_params *params)
-{
-	return order_base_2(MLX5E_SHAMPO_WQ_RESRV_SIZE / MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE);
-}
-
-u8 mlx5e_shampo_get_log_pkt_per_rsrv(struct mlx5_core_dev *mdev,
-				     struct mlx5e_params *params)
-{
-	u32 resrv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) *
-			 PAGE_SIZE;
-
-	return order_base_2(DIV_ROUND_UP(resrv_size, params->sw_mtu));
+	return order_base_2(DIV_ROUND_UP(MLX5E_SHAMPO_WQ_RESRV_SIZE,
+					 params->sw_mtu));
 }
 
 u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
@@ -619,6 +612,7 @@ void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e
 		.ch_stats = c->stats,
 		.node = cpu_to_node(c->cpu),
 		.ix = c->vec_ix,
+		.uar = c->bfreg->up,
 	};
 }
 
@@ -818,7 +812,7 @@ static void mlx5e_build_common_cq_param(struct mlx5_core_dev *mdev,
 {
 	void *cqc = param->cqc;
 
-	MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index);
+	MLX5_SET(cqc, cqc, uar_page, mdev->priv.bfreg.up->index);
 	if (MLX5_CAP_GEN(mdev, cqe_128_always) && cache_line_size() >= 128)
 		MLX5_SET(cqc, cqc, cqe_sz, CQE_STRIDE_128_PAD);
 }
@@ -827,12 +821,12 @@ static u32 mlx5e_shampo_get_log_cq_size(struct mlx5_core_dev *mdev,
 					struct mlx5e_params *params,
 					struct mlx5e_xsk_param *xsk)
 {
-	int rsrv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) * PAGE_SIZE;
 	u16 num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk));
-	int pkt_per_rsrv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params));
 	u8 log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk);
+	int pkt_per_rsrv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(params));
 	int wq_size = BIT(mlx5e_mpwqe_get_log_rq_size(mdev, params, xsk));
 	int wqe_size = BIT(log_stride_sz) * num_strides;
+	int rsrv_size = MLX5E_SHAMPO_WQ_RESRV_SIZE;
 
 	/* +1 is for the case that the pkt_per_rsrv dont consume the reservation
 	 * so we get a filler cqe for the rest of the reservation.
@@ -893,6 +887,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 {
 	void *rqc = param->rqc;
 	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
+	u32 lro_timeout;
 	int ndsegs = 1;
 	int err;
 
@@ -918,22 +913,27 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 		MLX5_SET(wq, wq, log_wqe_stride_size,
 			 log_wqe_stride_size - MLX5_MPWQE_LOG_STRIDE_SZ_BASE);
 		MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(mdev, params, xsk));
-		if (params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) {
-			MLX5_SET(wq, wq, shampo_enable, true);
-			MLX5_SET(wq, wq, log_reservation_size,
-				 mlx5e_shampo_get_log_rsrv_size(mdev, params));
-			MLX5_SET(wq, wq,
-				 log_max_num_of_packets_per_reservation,
-				 mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params));
-			MLX5_SET(wq, wq, log_headers_entry_size,
-				 mlx5e_shampo_get_log_hd_entry_size(mdev, params));
-			MLX5_SET(rqc, rqc, reservation_timeout,
-				 mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_SHAMPO_TIMEOUT));
-			MLX5_SET(rqc, rqc, shampo_match_criteria_type,
-				 params->packet_merge.shampo.match_criteria_type);
-			MLX5_SET(rqc, rqc, shampo_no_match_alignment_granularity,
-				 params->packet_merge.shampo.alignment_granularity);
-		}
+		if (params->packet_merge.type != MLX5E_PACKET_MERGE_SHAMPO)
+			break;
+
+		MLX5_SET(wq, wq, shampo_enable, true);
+		MLX5_SET(wq, wq, log_reservation_size,
+			 MLX5E_SHAMPO_WQ_LOG_RESRV_SIZE -
+			 MLX5E_SHAMPO_WQ_RESRV_SIZE_BASE_SHIFT);
+		MLX5_SET(wq, wq,
+			 log_max_num_of_packets_per_reservation,
+			 mlx5e_shampo_get_log_pkt_per_rsrv(params));
+		MLX5_SET(wq, wq, log_headers_entry_size,
+			 MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE -
+			 MLX5E_SHAMPO_WQ_BASE_HEAD_ENTRY_SIZE_SHIFT);
+		lro_timeout =
+			mlx5e_choose_lro_timeout(mdev,
+						 MLX5E_DEFAULT_SHAMPO_TIMEOUT);
+		MLX5_SET(rqc, rqc, reservation_timeout, lro_timeout);
+		MLX5_SET(rqc, rqc, shampo_match_criteria_type,
+			 MLX5_RQC_SHAMPO_MATCH_CRITERIA_TYPE_EXTENDED);
+		MLX5_SET(rqc, rqc, shampo_no_match_alignment_granularity,
+			 MLX5_RQC_SHAMPO_NO_MATCH_ALIGNMENT_GRANULARITY_STRIDE);
 		break;
 	}
 	default: /* MLX5_WQ_TYPE_CYCLIC */
@@ -1005,7 +1005,8 @@ void mlx5e_build_sq_param(struct mlx5_core_dev *mdev,
 	bool allow_swp;
 
 	allow_swp = mlx5_geneve_tx_allowed(mdev) ||
-		    (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_CRYPTO);
+		    (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_CRYPTO) ||
+		    mlx5_is_psp_device(mdev);
 	mlx5e_build_sq_param_common(mdev, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 	MLX5_SET(sqc, sqc, allow_swp, allow_swp);
@@ -1036,17 +1037,17 @@ u32 mlx5e_shampo_hd_per_wqe(struct mlx5_core_dev *mdev,
 			    struct mlx5e_params *params,
 			    struct mlx5e_rq_param *rq_param)
 {
-	int resv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) * PAGE_SIZE;
 	u16 num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, NULL));
-	int pkt_per_resv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params));
 	u8 log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, NULL);
+	int pkt_per_rsrv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(params));
 	int wqe_size = BIT(log_stride_sz) * num_strides;
+	int rsrv_size = MLX5E_SHAMPO_WQ_RESRV_SIZE;
 	u32 hd_per_wqe;
 
 	/* Assumption: hd_per_wqe % 8 == 0. */
-	hd_per_wqe = (wqe_size / resv_size) * pkt_per_resv;
-	mlx5_core_dbg(mdev, "%s hd_per_wqe = %d rsrv_size = %d wqe_size = %d pkt_per_resv = %d\n",
-		      __func__, hd_per_wqe, resv_size, wqe_size, pkt_per_resv);
+	hd_per_wqe = (wqe_size / rsrv_size) * pkt_per_rsrv;
+	mlx5_core_dbg(mdev, "%s hd_per_wqe = %d rsrv_size = %d wqe_size = %d pkt_per_rsrv = %d\n",
+		      __func__, hd_per_wqe, rsrv_size, wqe_size, pkt_per_rsrv);
 	return hd_per_wqe;
 }
 
@@ -1231,7 +1232,6 @@ static void mlx5e_build_async_icosq_param(struct mlx5_core_dev *mdev,
 
 void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev,
 			     struct mlx5e_params *params,
-			     struct mlx5e_xsk_param *xsk,
 			     struct mlx5e_sq_param *param)
 {
 	void *sqc = param->sqc;
@@ -1240,7 +1240,6 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev,
 	mlx5e_build_sq_param_common(mdev, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 	param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE);
-	param->is_xdp_mb = !mlx5e_rx_is_linear_skb(mdev, params, xsk);
 	mlx5e_build_tx_cq_param(mdev, params, &param->cqp);
 }
 
@@ -1259,7 +1258,7 @@ int mlx5e_build_channel_param(struct mlx5_core_dev *mdev,
 	async_icosq_log_wq_sz = mlx5e_build_async_icosq_log_wq_sz(mdev);
 
 	mlx5e_build_sq_param(mdev, params, &cparam->txq_sq);
-	mlx5e_build_xdpsq_param(mdev, params, NULL, &cparam->xdp_sq);
+	mlx5e_build_xdpsq_param(mdev, params, &cparam->xdp_sq);
 	mlx5e_build_icosq_param(mdev, icosq_log_wq_sz, &cparam->icosq);
 	mlx5e_build_async_icosq_param(mdev, async_icosq_log_wq_sz, &cparam->async_icosq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
index 3f8986f9d862..00617c65fe3c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -33,7 +33,6 @@ struct mlx5e_sq_param {
 	struct mlx5_wq_param       wq;
 	bool                       is_mpw;
 	bool                       is_tls;
-	bool                       is_xdp_mb;
 	u16                        stop_room;
 };
 
@@ -52,6 +51,7 @@ struct mlx5e_create_sq_param {
 	u32                         tisn;
 	u8                          tis_lst_sz;
 	u8                          min_inline_mode;
+	u32                         uar_page;
 };
 
 /* Striding RQ dynamic parameters */
@@ -96,12 +96,6 @@ bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
 u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5_core_dev *mdev,
 			       struct mlx5e_params *params,
 			       struct mlx5e_xsk_param *xsk);
-u8 mlx5e_shampo_get_log_hd_entry_size(struct mlx5_core_dev *mdev,
-				      struct mlx5e_params *params);
-u8 mlx5e_shampo_get_log_rsrv_size(struct mlx5_core_dev *mdev,
-				  struct mlx5e_params *params);
-u8 mlx5e_shampo_get_log_pkt_per_rsrv(struct mlx5_core_dev *mdev,
-				     struct mlx5e_params *params);
 u32 mlx5e_shampo_hd_per_wqe(struct mlx5_core_dev *mdev,
 			    struct mlx5e_params *params,
 			    struct mlx5e_rq_param *rq_param);
@@ -139,7 +133,6 @@ void mlx5e_build_tx_cq_param(struct mlx5_core_dev *mdev,
 			     struct mlx5e_cq_param *param);
 void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev,
 			     struct mlx5e_params *params,
-			     struct mlx5e_xsk_param *xsk,
 			     struct mlx5e_sq_param *param);
 int mlx5e_build_channel_param(struct mlx5_core_dev *mdev,
 			      struct mlx5e_params *params,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.c b/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.c
new file mode 100644
index 000000000000..2eb666a46f39
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.c
@@ -0,0 +1,376 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES.
+
+#include "../devlink.h"
+#include "en.h"
+#include "pcie_cong_event.h"
+
+#define MLX5E_CONG_HIGH_STATE 0x7
+
+enum {
+	MLX5E_INBOUND_CONG  = BIT(0),
+	MLX5E_OUTBOUND_CONG = BIT(1),
+};
+
+struct mlx5e_pcie_cong_thresh {
+	u16 inbound_high;
+	u16 inbound_low;
+	u16 outbound_high;
+	u16 outbound_low;
+};
+
+struct mlx5e_pcie_cong_stats {
+	u32 pci_bw_inbound_high;
+	u32 pci_bw_inbound_low;
+	u32 pci_bw_outbound_high;
+	u32 pci_bw_outbound_low;
+	u32 pci_bw_stale_event;
+};
+
+struct mlx5e_pcie_cong_event {
+	u64 obj_id;
+
+	struct mlx5e_priv *priv;
+
+	/* For event notifier and workqueue. */
+	struct work_struct work;
+	struct mlx5_nb nb;
+
+	/* Stores last read state. */
+	u8 state;
+
+	/* For ethtool stats group. */
+	struct mlx5e_pcie_cong_stats stats;
+};
+
+
+static const struct counter_desc mlx5e_pcie_cong_stats_desc[] = {
+	{ MLX5E_DECLARE_STAT(struct mlx5e_pcie_cong_stats,
+			     pci_bw_inbound_high) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_pcie_cong_stats,
+			     pci_bw_inbound_low) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_pcie_cong_stats,
+			     pci_bw_outbound_high) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_pcie_cong_stats,
+			     pci_bw_outbound_low) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_pcie_cong_stats,
+			     pci_bw_stale_event) },
+};
+
+#define NUM_PCIE_CONG_COUNTERS ARRAY_SIZE(mlx5e_pcie_cong_stats_desc)
+
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(pcie_cong)
+{
+	return priv->cong_event ? NUM_PCIE_CONG_COUNTERS : 0;
+}
+
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(pcie_cong) {}
+
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(pcie_cong)
+{
+	if (!priv->cong_event)
+		return;
+
+	for (int i = 0; i < NUM_PCIE_CONG_COUNTERS; i++)
+		ethtool_puts(data, mlx5e_pcie_cong_stats_desc[i].format);
+}
+
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(pcie_cong)
+{
+	if (!priv->cong_event)
+		return;
+
+	for (int i = 0; i < NUM_PCIE_CONG_COUNTERS; i++) {
+		u32 ctr = MLX5E_READ_CTR32_CPU(&priv->cong_event->stats,
+					       mlx5e_pcie_cong_stats_desc,
+					       i);
+
+		mlx5e_ethtool_put_stat(data, ctr);
+	}
+}
+
+MLX5E_DEFINE_STATS_GRP(pcie_cong, 0);
+
+static int
+mlx5_cmd_pcie_cong_event_set(struct mlx5_core_dev *dev,
+			     const struct mlx5e_pcie_cong_thresh *config,
+			     u64 *obj_id)
+{
+	u32 in[MLX5_ST_SZ_DW(pcie_cong_event_cmd_in)] = {};
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)];
+	void *cong_obj;
+	void *hdr;
+	int err;
+
+	hdr = MLX5_ADDR_OF(pcie_cong_event_cmd_in, in, hdr);
+	cong_obj = MLX5_ADDR_OF(pcie_cong_event_cmd_in, in, cong_obj);
+
+	MLX5_SET(general_obj_in_cmd_hdr, hdr, opcode,
+		 MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+
+	MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_type,
+		 MLX5_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT);
+
+	MLX5_SET(pcie_cong_event_obj, cong_obj, inbound_event_en, 1);
+	MLX5_SET(pcie_cong_event_obj, cong_obj, outbound_event_en, 1);
+
+	MLX5_SET(pcie_cong_event_obj, cong_obj,
+		 inbound_cong_high_threshold, config->inbound_high);
+	MLX5_SET(pcie_cong_event_obj, cong_obj,
+		 inbound_cong_low_threshold, config->inbound_low);
+
+	MLX5_SET(pcie_cong_event_obj, cong_obj,
+		 outbound_cong_high_threshold, config->outbound_high);
+	MLX5_SET(pcie_cong_event_obj, cong_obj,
+		 outbound_cong_low_threshold, config->outbound_low);
+
+	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return err;
+
+	*obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+
+	mlx5_core_dbg(dev, "PCIe congestion event (obj_id=%llu) created. Config: in: [%u, %u], out: [%u, %u]\n",
+		      *obj_id,
+		      config->inbound_high, config->inbound_low,
+		      config->outbound_high, config->outbound_low);
+
+	return 0;
+}
+
+static int mlx5_cmd_pcie_cong_event_destroy(struct mlx5_core_dev *dev,
+					    u64 obj_id)
+{
+	u32 in[MLX5_ST_SZ_DW(pcie_cong_event_cmd_in)] = {};
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)];
+	void *hdr;
+
+	hdr = MLX5_ADDR_OF(pcie_cong_event_cmd_in, in, hdr);
+	MLX5_SET(general_obj_in_cmd_hdr, hdr, opcode,
+		 MLX5_CMD_OP_DESTROY_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_type,
+		 MLX5_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT);
+	MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_id, obj_id);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_cmd_pcie_cong_event_query(struct mlx5_core_dev *dev,
+					  u64 obj_id,
+					  u32 *state)
+{
+	u32 in[MLX5_ST_SZ_DW(pcie_cong_event_cmd_in)] = {};
+	u32 out[MLX5_ST_SZ_DW(pcie_cong_event_cmd_out)];
+	void *obj;
+	void *hdr;
+	u8 cong;
+	int err;
+
+	hdr = MLX5_ADDR_OF(pcie_cong_event_cmd_in, in, hdr);
+
+	MLX5_SET(general_obj_in_cmd_hdr, hdr, opcode,
+		 MLX5_CMD_OP_QUERY_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_type,
+		 MLX5_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT);
+	MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_id, obj_id);
+
+	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return err;
+
+	obj = MLX5_ADDR_OF(pcie_cong_event_cmd_out, out, cong_obj);
+
+	if (state) {
+		cong = MLX5_GET(pcie_cong_event_obj, obj, inbound_cong_state);
+		if (cong == MLX5E_CONG_HIGH_STATE)
+			*state |= MLX5E_INBOUND_CONG;
+
+		cong = MLX5_GET(pcie_cong_event_obj, obj, outbound_cong_state);
+		if (cong == MLX5E_CONG_HIGH_STATE)
+			*state |= MLX5E_OUTBOUND_CONG;
+	}
+
+	return 0;
+}
+
+static void mlx5e_pcie_cong_event_work(struct work_struct *work)
+{
+	struct mlx5e_pcie_cong_event *cong_event;
+	struct mlx5_core_dev *dev;
+	struct mlx5e_priv *priv;
+	u32 new_cong_state = 0;
+	u32 changes;
+	int err;
+
+	cong_event = container_of(work, struct mlx5e_pcie_cong_event, work);
+	priv = cong_event->priv;
+	dev = priv->mdev;
+
+	err = mlx5_cmd_pcie_cong_event_query(dev, cong_event->obj_id,
+					     &new_cong_state);
+	if (err) {
+		mlx5_core_warn(dev, "Error %d when querying PCIe cong event object (obj_id=%llu).\n",
+			       err, cong_event->obj_id);
+		return;
+	}
+
+	changes = cong_event->state ^ new_cong_state;
+	if (!changes) {
+		cong_event->stats.pci_bw_stale_event++;
+		return;
+	}
+
+	cong_event->state = new_cong_state;
+
+	if (changes & MLX5E_INBOUND_CONG) {
+		if (new_cong_state & MLX5E_INBOUND_CONG)
+			cong_event->stats.pci_bw_inbound_high++;
+		else
+			cong_event->stats.pci_bw_inbound_low++;
+	}
+
+	if (changes & MLX5E_OUTBOUND_CONG) {
+		if (new_cong_state & MLX5E_OUTBOUND_CONG)
+			cong_event->stats.pci_bw_outbound_high++;
+		else
+			cong_event->stats.pci_bw_outbound_low++;
+	}
+}
+
+static int mlx5e_pcie_cong_event_handler(struct notifier_block *nb,
+					 unsigned long event, void *eqe)
+{
+	struct mlx5e_pcie_cong_event *cong_event;
+
+	cong_event = mlx5_nb_cof(nb, struct mlx5e_pcie_cong_event, nb);
+	queue_work(cong_event->priv->wq, &cong_event->work);
+
+	return NOTIFY_OK;
+}
+
+static int
+mlx5e_pcie_cong_get_thresh_config(struct mlx5_core_dev *dev,
+				  struct mlx5e_pcie_cong_thresh *config)
+{
+	u32 ids[4] = {
+		MLX5_DEVLINK_PARAM_ID_PCIE_CONG_IN_LOW,
+		MLX5_DEVLINK_PARAM_ID_PCIE_CONG_IN_HIGH,
+		MLX5_DEVLINK_PARAM_ID_PCIE_CONG_OUT_LOW,
+		MLX5_DEVLINK_PARAM_ID_PCIE_CONG_OUT_HIGH,
+	};
+	struct devlink *devlink = priv_to_devlink(dev);
+	union devlink_param_value val[4];
+
+	for (int i = 0; i < 4; i++) {
+		u32 id = ids[i];
+		int err;
+
+		err = devl_param_driverinit_value_get(devlink, id, &val[i]);
+		if (err)
+			return err;
+	}
+
+	config->inbound_low = val[0].vu16;
+	config->inbound_high = val[1].vu16;
+	config->outbound_low = val[2].vu16;
+	config->outbound_high = val[3].vu16;
+
+	return 0;
+}
+
+static int
+mlx5e_thresh_config_validate(struct mlx5_core_dev *mdev,
+			     const struct mlx5e_pcie_cong_thresh *config)
+{
+	int err = 0;
+
+	if (config->inbound_low >= config->inbound_high) {
+		err = -EINVAL;
+		mlx5_core_err(mdev, "PCIe inbound congestion threshold configuration invalid: low (%u) >= high (%u).\n",
+			      config->inbound_low, config->inbound_high);
+	}
+
+	if (config->outbound_low >= config->outbound_high) {
+		err = -EINVAL;
+		mlx5_core_err(mdev, "PCIe outbound congestion threshold configuration invalid: low (%u) >= high (%u).\n",
+			      config->outbound_low, config->outbound_high);
+	}
+
+	return err;
+}
+
+int mlx5e_pcie_cong_event_init(struct mlx5e_priv *priv)
+{
+	struct mlx5e_pcie_cong_thresh thresh_config = {};
+	struct mlx5e_pcie_cong_event *cong_event;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int err;
+
+	if (!mlx5_pcie_cong_event_supported(mdev))
+		return 0;
+
+	err = mlx5e_pcie_cong_get_thresh_config(mdev, &thresh_config);
+	if (WARN_ON(err))
+		return err;
+
+	err = mlx5e_thresh_config_validate(mdev, &thresh_config);
+	if (err) {
+		mlx5_core_err(mdev, "PCIe congestion event feature disabled\n");
+		return err;
+	}
+
+	cong_event = kvzalloc_node(sizeof(*cong_event), GFP_KERNEL,
+				   mdev->priv.numa_node);
+	if (!cong_event)
+		return -ENOMEM;
+
+	INIT_WORK(&cong_event->work, mlx5e_pcie_cong_event_work);
+	MLX5_NB_INIT(&cong_event->nb, mlx5e_pcie_cong_event_handler,
+		     OBJECT_CHANGE);
+
+	cong_event->priv = priv;
+
+	err = mlx5_cmd_pcie_cong_event_set(mdev, &thresh_config,
+					   &cong_event->obj_id);
+	if (err) {
+		mlx5_core_warn(mdev, "Error creating a PCIe congestion event object\n");
+		goto err_free;
+	}
+
+	err = mlx5_eq_notifier_register(mdev, &cong_event->nb);
+	if (err) {
+		mlx5_core_warn(mdev, "Error registering notifier for the PCIe congestion event\n");
+		goto err_obj_destroy;
+	}
+
+	priv->cong_event = cong_event;
+
+	return 0;
+
+err_obj_destroy:
+	mlx5_cmd_pcie_cong_event_destroy(mdev, cong_event->obj_id);
+err_free:
+	kvfree(cong_event);
+
+	return err;
+}
+
+void mlx5e_pcie_cong_event_cleanup(struct mlx5e_priv *priv)
+{
+	struct mlx5e_pcie_cong_event *cong_event = priv->cong_event;
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	if (!cong_event)
+		return;
+
+	priv->cong_event = NULL;
+
+	mlx5_eq_notifier_unregister(mdev, &cong_event->nb);
+	cancel_work_sync(&cong_event->work);
+
+	if (mlx5_cmd_pcie_cong_event_destroy(mdev, cong_event->obj_id))
+		mlx5_core_warn(mdev, "Error destroying PCIe congestion event (obj_id=%llu)\n",
+			       cong_event->obj_id);
+
+	kvfree(cong_event);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.h b/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.h
new file mode 100644
index 000000000000..b1ea46bf648a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. */
+
+#ifndef __MLX5_PCIE_CONG_EVENT_H__
+#define __MLX5_PCIE_CONG_EVENT_H__
+
+int mlx5e_pcie_cong_event_init(struct mlx5e_priv *priv);
+void mlx5e_pcie_cong_event_cleanup(struct mlx5e_priv *priv);
+
+#endif /* __MLX5_PCIE_CONG_EVENT_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 5f6a0605e4ae..6049ccf475bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -80,6 +80,7 @@ int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
 int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 {
 	struct mlx5_port_eth_proto eproto;
+	const struct mlx5_link_info *info;
 	bool force_legacy = false;
 	bool ext;
 	int err;
@@ -94,9 +95,13 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 		if (err)
 			goto out;
 	}
-	*speed = mlx5_port_ptys2speed(mdev, eproto.oper, force_legacy);
-	if (!(*speed))
+	info = mlx5_port_ptys2info(mdev, eproto.oper, force_legacy);
+	if (!info) {
+		*speed = SPEED_UNKNOWN;
 		err = -EINVAL;
+		goto out;
+	}
+	*speed = info->speed;
 
 out:
 	return err;
@@ -296,11 +301,16 @@ enum mlx5e_fec_supported_link_mode {
 	MLX5E_FEC_SUPPORTED_LINK_MODE_200G_2X,
 	MLX5E_FEC_SUPPORTED_LINK_MODE_400G_4X,
 	MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_400G_2X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_800G_4X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_1600G_8X,
 	MLX5E_MAX_FEC_SUPPORTED_LINK_MODE,
 };
 
 #define MLX5E_FEC_FIRST_50G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_50G_1X
 #define MLX5E_FEC_FIRST_100G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_100G_1X
+#define MLX5E_FEC_FIRST_200G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X
 
 #define MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, policy, write, link)			\
 	do {										\
@@ -320,8 +330,10 @@ static bool mlx5e_is_fec_supported_link_mode(struct mlx5_core_dev *dev,
 	return link_mode < MLX5E_FEC_FIRST_50G_PER_LANE_MODE ||
 	       (link_mode < MLX5E_FEC_FIRST_100G_PER_LANE_MODE &&
 		MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm)) ||
-	       (link_mode >= MLX5E_FEC_FIRST_100G_PER_LANE_MODE &&
-		MLX5_CAP_PCAM_FEATURE(dev, fec_100G_per_lane_in_pplm));
+	       (link_mode < MLX5E_FEC_FIRST_200G_PER_LANE_MODE &&
+		MLX5_CAP_PCAM_FEATURE(dev, fec_100G_per_lane_in_pplm)) ||
+	       (link_mode >= MLX5E_FEC_FIRST_200G_PER_LANE_MODE &&
+		MLX5_CAP_PCAM_FEATURE(dev, fec_200G_per_lane_in_pplm));
 }
 
 /* get/set FEC admin field for a given speed */
@@ -368,6 +380,18 @@ static int mlx5e_fec_admin_field(u32 *pplm, u16 *fec_policy, bool write,
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X:
 		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 800g_8x);
 		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 200g_1x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_2X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 400g_2x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_4X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 800g_4x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_1600G_8X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 1600g_8x);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -421,6 +445,18 @@ static int mlx5e_get_fec_cap_field(u32 *pplm, u16 *fec_cap,
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X:
 		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 800g_8x);
 		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 200g_1x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_2X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 400g_2x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_4X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 800g_4x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_1600G_8X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 1600g_8x);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -494,6 +530,26 @@ out:
 	return 0;
 }
 
+static u16 mlx5e_remap_fec_conf_mode(enum mlx5e_fec_supported_link_mode link_mode,
+				     u16 conf_fec)
+{
+	/* RS fec in ethtool is originally mapped to MLX5E_FEC_RS_528_514.
+	 * For link modes up to 25G per lane, the value is kept.
+	 * For 50G or 100G per lane, it's remapped to MLX5E_FEC_RS_544_514.
+	 * For 200G per lane, remapped to MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD.
+	 */
+	if (conf_fec != BIT(MLX5E_FEC_RS_528_514))
+		return conf_fec;
+
+	if (link_mode >= MLX5E_FEC_FIRST_200G_PER_LANE_MODE)
+		return BIT(MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD);
+
+	if (link_mode >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE)
+		return BIT(MLX5E_FEC_RS_544_514);
+
+	return conf_fec;
+}
+
 int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy)
 {
 	bool fec_50g_per_lane = MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm);
@@ -530,14 +586,7 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy)
 		if (!mlx5e_is_fec_supported_link_mode(dev, i))
 			break;
 
-		/* RS fec in ethtool is mapped to MLX5E_FEC_RS_528_514
-		 * to link modes up to 25G per lane and to
-		 * MLX5E_FEC_RS_544_514 in the new link modes based on
-		 * 50G or 100G per lane
-		 */
-		if (conf_fec == (1 << MLX5E_FEC_RS_528_514) &&
-		    i >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE)
-			conf_fec = (1 << MLX5E_FEC_RS_544_514);
+		conf_fec = mlx5e_remap_fec_conf_mode(i, conf_fec);
 
 		mlx5e_get_fec_cap_field(out, &fec_caps, i);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index d1da225f35da..fa2283dd383b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -61,6 +61,7 @@ enum {
 	MLX5E_FEC_NOFEC,
 	MLX5E_FEC_FIRECODE,
 	MLX5E_FEC_RS_528_514,
+	MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD = 4,
 	MLX5E_FEC_RS_544_514 = 7,
 	MLX5E_FEC_LLRS_272_257_1 = 9,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index 8e25f4ef5ccc..4720523813b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -272,8 +272,8 @@ static int port_update_shared_buffer(struct mlx5_core_dev *mdev,
 	/* Total shared buffer size is split in a ratio of 3:1 between
 	 * lossy and lossless pools respectively.
 	 */
-	lossy_epool_size = (shared_buffer_size / 4) * 3;
 	lossless_ipool_size = shared_buffer_size / 4;
+	lossy_epool_size    = shared_buffer_size - lossless_ipool_size;
 
 	mlx5e_port_set_sbpr(mdev, 0, MLX5_EGRESS_DIR, MLX5_LOSSY_POOL, 0,
 			    lossy_epool_size);
@@ -288,14 +288,12 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 	u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int sz = MLX5_ST_SZ_BYTES(pbmc_reg);
-	u32 new_headroom_size = 0;
-	u32 current_headroom_size;
+	u32 current_headroom_cells = 0;
+	u32 new_headroom_cells = 0;
 	void *in;
 	int err;
 	int i;
 
-	current_headroom_size = port_buffer->headroom_size;
-
 	in = kzalloc(sz, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -306,12 +304,14 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 
 	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]);
+		current_headroom_cells += MLX5_GET(bufferx_reg, buffer, size);
+
 		u64 size = port_buffer->buffer[i].size;
 		u64 xoff = port_buffer->buffer[i].xoff;
 		u64 xon = port_buffer->buffer[i].xon;
 
-		new_headroom_size += size;
 		do_div(size, port_buff_cell_sz);
+		new_headroom_cells += size;
 		do_div(xoff, port_buff_cell_sz);
 		do_div(xon, port_buff_cell_sz);
 		MLX5_SET(bufferx_reg, buffer, size, size);
@@ -320,10 +320,8 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 		MLX5_SET(bufferx_reg, buffer, xon_threshold, xon);
 	}
 
-	new_headroom_size /= port_buff_cell_sz;
-	current_headroom_size /= port_buff_cell_sz;
-	err = port_update_shared_buffer(priv->mdev, current_headroom_size,
-					new_headroom_size);
+	err = port_update_shared_buffer(priv->mdev, current_headroom_cells,
+					new_headroom_cells);
 	if (err)
 		goto out;
 
@@ -331,6 +329,9 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 	if (err)
 		goto out;
 
+	/* RO bits should be set to 0 on write */
+	MLX5_SET(pbmc_reg, in, port_buffer_size, 0);
+
 	err = mlx5e_port_set_pbmc(mdev, in);
 out:
 	kfree(in);
@@ -574,7 +575,6 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 	}
-	priv->dcbx.xoff = xoff;
 
 	/* Apply the settings */
 	if (update_buffer) {
@@ -583,6 +583,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 			return err;
 	}
 
+	priv->dcbx.xoff = xoff;
+
 	if (update_prio2buffer)
 		err = mlx5e_port_set_priority2buffer(priv->mdev, prio2buffer);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index afd654583b6b..424f8a2728a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -8,6 +8,7 @@
 #include "en/fs_tt_redirect.h"
 #include <linux/list.h>
 #include <linux/spinlock.h>
+#include <net/netdev_lock.h>
 
 struct mlx5e_ptp_fs {
 	struct mlx5_flow_handle *l2_rule;
@@ -81,7 +82,7 @@ static struct mlx5e_skb_cb_hwtstamp *mlx5e_skb_cb_get_hwts(struct sk_buff *skb)
 }
 
 static void mlx5e_skb_cb_hwtstamp_tx(struct sk_buff *skb,
-				     struct mlx5e_ptp_cq_stats *cq_stats)
+				     struct mlx5e_ptpsq *ptpsq)
 {
 	struct skb_shared_hwtstamps hwts = {};
 	ktime_t diff;
@@ -91,8 +92,17 @@ static void mlx5e_skb_cb_hwtstamp_tx(struct sk_buff *skb,
 
 	/* Maximal allowed diff is 1 / 128 second */
 	if (diff > (NSEC_PER_SEC >> 7)) {
-		cq_stats->abort++;
-		cq_stats->abort_abs_diff_ns += diff;
+		struct mlx5e_txqsq *sq = &ptpsq->txqsq;
+
+		ptpsq->cq_stats->abort++;
+		ptpsq->cq_stats->abort_abs_diff_ns += diff;
+		if (diff > (NSEC_PER_SEC >> 1) &&
+		    !test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) {
+			netdev_warn(sq->channel->netdev,
+				    "PTP TX timestamp difference between CQE and port exceeds threshold: %lld ns, recovering SQ %u\n",
+				    (s64)diff, sq->sqn);
+			queue_work(sq->priv->wq, &ptpsq->report_unhealthy_work);
+		}
 		return;
 	}
 
@@ -102,7 +112,7 @@ static void mlx5e_skb_cb_hwtstamp_tx(struct sk_buff *skb,
 
 void mlx5e_skb_cb_hwtstamp_handler(struct sk_buff *skb, int hwtstamp_type,
 				   ktime_t hwtstamp,
-				   struct mlx5e_ptp_cq_stats *cq_stats)
+				   struct mlx5e_ptpsq *ptpsq)
 {
 	switch (hwtstamp_type) {
 	case (MLX5E_SKB_CB_CQE_HWTSTAMP):
@@ -120,7 +130,7 @@ void mlx5e_skb_cb_hwtstamp_handler(struct sk_buff *skb, int hwtstamp_type,
 	    !mlx5e_skb_cb_get_hwts(skb)->port_hwtstamp)
 		return;
 
-	mlx5e_skb_cb_hwtstamp_tx(skb, cq_stats);
+	mlx5e_skb_cb_hwtstamp_tx(skb, ptpsq);
 	memset(skb->cb, 0, sizeof(struct mlx5e_skb_cb_hwtstamp));
 }
 
@@ -208,7 +218,7 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq,
 
 	hwtstamp = mlx5e_cqe_ts_to_ns(sq->ptp_cyc2time, sq->clock, get_cqe_ts(cqe));
 	mlx5e_skb_cb_hwtstamp_handler(skb, MLX5E_SKB_CB_PORT_HWTSTAMP,
-				      hwtstamp, ptpsq->cq_stats);
+				      hwtstamp, ptpsq);
 	ptpsq->cq_stats->cqe++;
 
 	mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp);
@@ -326,21 +336,19 @@ static int mlx5e_ptp_alloc_txqsq(struct mlx5e_ptp *c, int txq_ix,
 	int node;
 
 	sq->pdev      = c->pdev;
-	sq->clock     = &mdev->clock;
+	sq->clock     = mdev->clock;
 	sq->mkey_be   = c->mkey_be;
 	sq->netdev    = c->netdev;
 	sq->priv      = c->priv;
 	sq->mdev      = mdev;
 	sq->ch_ix     = MLX5E_PTP_CHANNEL_IX;
 	sq->txq_ix    = txq_ix;
-	sq->uar_map   = mdev->mlx5e_res.hw_objs.bfreg.map;
+	sq->uar_map   = c->bfreg->map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	sq->stats     = &c->priv->ptp_stats.sq[tc];
 	sq->ptpsq     = ptpsq;
 	INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work);
-	if (!MLX5_CAP_ETH(mdev, wqe_vlan_insert))
-		set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state);
 	sq->stop_room = param->stop_room;
 	sq->ptp_cyc2time = mlx5_sq_ts_translator(mdev);
 
@@ -449,8 +457,22 @@ static void mlx5e_ptpsq_unhealthy_work(struct work_struct *work)
 {
 	struct mlx5e_ptpsq *ptpsq =
 		container_of(work, struct mlx5e_ptpsq, report_unhealthy_work);
+	struct mlx5e_txqsq *sq = &ptpsq->txqsq;
+
+	/* Recovering the PTP SQ means re-enabling NAPI, which requires the
+	 * netdev instance lock. However, SQ closing has to wait for this work
+	 * task to finish while also holding the same lock. So either get the
+	 * lock or find that the SQ is no longer enabled and thus this work is
+	 * not relevant anymore.
+	 */
+	while (!netdev_trylock(sq->netdev)) {
+		if (!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))
+			return;
+		msleep(20);
+	}
 
 	mlx5e_reporter_tx_ptpsq_unhealthy(ptpsq);
+	netdev_unlock(sq->netdev);
 }
 
 static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn,
@@ -473,6 +495,7 @@ static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn,
 	csp.wq_ctrl         = &txqsq->wq_ctrl;
 	csp.min_inline_mode = txqsq->min_inline_mode;
 	csp.ts_cqe_to_dest_cqn = ptpsq->ts_cq.mcq.cqn;
+	csp.uar_page = c->bfreg->index;
 
 	err = mlx5e_create_sq_rdy(c->mdev, sqp, &csp, 0, &txqsq->sqn);
 	if (err)
@@ -564,6 +587,7 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c,
 	ccp.ch_stats = c->stats;
 	ccp.napi     = &c->napi;
 	ccp.ix       = MLX5E_PTP_CHANNEL_IX;
+	ccp.uar      = c->bfreg->up;
 
 	cq_param = &cparams->txq_sq_param.cqp;
 
@@ -613,6 +637,7 @@ static int mlx5e_ptp_open_rx_cq(struct mlx5e_ptp *c,
 	ccp.ch_stats = c->stats;
 	ccp.napi     = &c->napi;
 	ccp.ix       = MLX5E_PTP_CHANNEL_IX;
+	ccp.uar      = c->bfreg->up;
 
 	cq_param = &cparams->rq_param.cqp;
 
@@ -696,8 +721,8 @@ static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params,
 	rq->pdev         = c->pdev;
 	rq->netdev       = priv->netdev;
 	rq->priv         = priv;
-	rq->clock        = &mdev->clock;
-	rq->tstamp       = &priv->tstamp;
+	rq->clock        = mdev->clock;
+	rq->hwtstamp_config = &priv->hwtstamp_config;
 	rq->mdev         = mdev;
 	rq->hw_mtu       = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->stats        = &c->priv->ptp_stats.rq;
@@ -880,19 +905,19 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 
 	c->priv     = priv;
 	c->mdev     = priv->mdev;
-	c->tstamp   = &priv->tstamp;
 	c->pdev     = mlx5_core_dma_dev(priv->mdev);
 	c->netdev   = priv->netdev;
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey);
 	c->num_tc   = mlx5e_get_dcb_num_tc(params);
 	c->stats    = &priv->ptp_stats.ch;
 	c->lag_port = lag_port;
+	c->bfreg    = &mdev->priv.bfreg;
 
 	err = mlx5e_ptp_set_state(c, params);
 	if (err)
 		goto err_free;
 
-	netif_napi_add(netdev, &c->napi, mlx5e_ptp_napi_poll);
+	netif_napi_add_locked(netdev, &c->napi, mlx5e_ptp_napi_poll);
 
 	mlx5e_ptp_build_params(c, cparams, params);
 
@@ -910,7 +935,7 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	return 0;
 
 err_napi_del:
-	netif_napi_del(&c->napi);
+	netif_napi_del_locked(&c->napi);
 err_free:
 	kvfree(cparams);
 	kvfree(c);
@@ -920,7 +945,7 @@ err_free:
 void mlx5e_ptp_close(struct mlx5e_ptp *c)
 {
 	mlx5e_ptp_close_queues(c);
-	netif_napi_del(&c->napi);
+	netif_napi_del_locked(&c->napi);
 
 	kvfree(c);
 }
@@ -929,7 +954,7 @@ void mlx5e_ptp_activate_channel(struct mlx5e_ptp *c)
 {
 	int tc;
 
-	napi_enable(&c->napi);
+	napi_enable_locked(&c->napi);
 
 	if (test_bit(MLX5E_PTP_STATE_TX, c->state)) {
 		for (tc = 0; tc < c->num_tc; tc++)
@@ -957,7 +982,7 @@ void mlx5e_ptp_deactivate_channel(struct mlx5e_ptp *c)
 			mlx5e_deactivate_txqsq(&c->ptpsq[tc].txqsq);
 	}
 
-	napi_disable(&c->napi);
+	napi_disable_locked(&c->napi);
 }
 
 int mlx5e_ptp_get_rqn(struct mlx5e_ptp *c, u32 *rqn)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
index 883c044852f1..2a457a2ed707 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -64,8 +64,8 @@ struct mlx5e_ptp {
 	/* control */
 	struct mlx5e_priv         *priv;
 	struct mlx5_core_dev      *mdev;
-	struct hwtstamp_config    *tstamp;
 	DECLARE_BITMAP(state, MLX5E_PTP_STATE_NUM_STATES);
+	struct mlx5_sq_bfreg      *bfreg;
 };
 
 static inline bool mlx5e_use_ptpsq(struct sk_buff *skb)
@@ -147,7 +147,7 @@ enum {
 
 void mlx5e_skb_cb_hwtstamp_handler(struct sk_buff *skb, int hwtstamp_type,
 				   ktime_t hwtstamp,
-				   struct mlx5e_ptp_cq_stats *cq_stats);
+				   struct mlx5e_ptpsq *ptpsq);
 
 void mlx5e_skb_cb_hwtstamp_init(struct sk_buff *skb);
 #endif /* __MLX5_EN_PTP_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
index f0744a45db92..4e461cb03b83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
@@ -374,7 +374,7 @@ void mlx5e_reactivate_qos_sq(struct mlx5e_priv *priv, u16 qid, struct netdev_que
 void mlx5e_reset_qdisc(struct net_device *dev, u16 qid)
 {
 	struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, qid);
-	struct Qdisc *qdisc = dev_queue->qdisc_sleeping;
+	struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping);
 
 	if (!qdisc)
 		return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
index 5d128c5b4529..87a2ad69526d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
@@ -30,15 +30,11 @@ static bool mlx5_esw_bridge_dev_same_hw(struct net_device *dev, struct mlx5_eswi
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev, *esw_mdev;
-	u64 system_guid, esw_system_guid;
 
 	mdev = priv->mdev;
 	esw_mdev = esw->dev;
 
-	system_guid = mlx5_query_nic_system_image_guid(mdev);
-	esw_system_guid = mlx5_query_nic_system_image_guid(esw_mdev);
-
-	return system_guid == esw_system_guid;
+	return mlx5_same_hw_devs(mdev, esw_mdev);
 }
 
 static struct net_device *
@@ -48,15 +44,10 @@ mlx5_esw_bridge_lag_rep_get(struct net_device *dev, struct mlx5_eswitch *esw)
 	struct list_head *iter;
 
 	netdev_for_each_lower_dev(dev, lower, iter) {
-		struct mlx5_core_dev *mdev;
-		struct mlx5e_priv *priv;
-
 		if (!mlx5e_eswitch_rep(lower))
 			continue;
 
-		priv = netdev_priv(lower);
-		mdev = priv->mdev;
-		if (mlx5_lag_is_shared_fdb(mdev) && mlx5_esw_bridge_dev_same_esw(lower, esw))
+		if (mlx5_esw_bridge_dev_same_esw(lower, esw))
 			return lower;
 	}
 
@@ -125,7 +116,7 @@ static bool mlx5_esw_bridge_is_local(struct net_device *dev, struct net_device *
 	priv = netdev_priv(rep);
 	mdev = priv->mdev;
 	if (netif_is_lag_master(dev))
-		return mlx5_lag_is_shared_fdb(mdev) && mlx5_lag_is_master(mdev);
+		return mlx5_lag_is_master(mdev);
 	return true;
 }
 
@@ -455,6 +446,9 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb,
 	if (!rep)
 		return NOTIFY_DONE;
 
+	if (netif_is_lag_master(dev) && !mlx5_lag_is_shared_fdb(esw->dev))
+		return NOTIFY_DONE;
+
 	switch (event) {
 	case SWITCHDEV_FDB_ADD_TO_BRIDGE:
 		fdb_info = container_of(info,
@@ -490,8 +484,8 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb,
 							       fdb_info,
 							       br_offloads);
 		if (IS_ERR(work)) {
-			WARN_ONCE(1, "Failed to init switchdev work, err=%ld",
-				  PTR_ERR(work));
+			WARN_ONCE(1, "Failed to init switchdev work, err=%pe",
+				  work);
 			return notifier_from_errno(PTR_ERR(work));
 		}
 
@@ -529,7 +523,8 @@ void mlx5e_rep_bridge_init(struct mlx5e_priv *priv)
 	br_offloads = mlx5_esw_bridge_init(esw);
 	rtnl_unlock();
 	if (IS_ERR(br_offloads)) {
-		esw_warn(mdev, "Failed to init esw bridge (err=%ld)\n", PTR_ERR(br_offloads));
+		esw_warn(mdev, "Failed to init esw bridge (err=%pe)\n",
+			 br_offloads);
 		return;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index 25d751eba99b..0686fbdd5a05 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -170,16 +170,23 @@ static int mlx5e_rx_reporter_err_rq_cqe_recover(void *ctx)
 static int mlx5e_rx_reporter_timeout_recover(void *ctx)
 {
 	struct mlx5_eq_comp *eq;
+	struct mlx5e_priv *priv;
 	struct mlx5e_rq *rq;
 	int err;
 
 	rq = ctx;
+	priv = rq->priv;
+
+	mutex_lock(&priv->state_lock);
+
 	eq = rq->cq.mcq.eq;
 
 	err = mlx5e_health_channel_eq_recover(rq->netdev, eq, rq->cq.ch_stats);
 	if (err && rq->icosq)
 		clear_bit(MLX5E_SQ_STATE_ENABLED, &rq->icosq->state);
 
+	mutex_unlock(&priv->state_lock);
+
 	return err;
 }
 
@@ -311,16 +318,15 @@ mlx5e_rx_reporter_diagnose_common_ptp_config(struct mlx5e_priv *priv, struct mlx
 					     struct devlink_fmsg *fmsg)
 {
 	mlx5e_health_fmsg_named_obj_nest_start(fmsg, "PTP");
-	devlink_fmsg_u32_pair_put(fmsg, "filter_type", priv->tstamp.rx_filter);
+	devlink_fmsg_u32_pair_put(fmsg, "filter_type",
+				  priv->hwtstamp_config.rx_filter);
 	mlx5e_rx_reporter_diagnose_generic_rq(&ptp_ch->rq, fmsg);
 	mlx5e_health_fmsg_named_obj_nest_end(fmsg);
 }
 
 static void
-mlx5e_rx_reporter_diagnose_common_config(struct devlink_health_reporter *reporter,
-					 struct devlink_fmsg *fmsg)
+mlx5e_rx_reporter_diagnose_common_config(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg)
 {
-	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
 	struct mlx5e_rq *generic_rq = &priv->channels.c[0]->rq;
 	struct mlx5e_ptp *ptp_ch = priv->channels.ptp;
 
@@ -340,20 +346,100 @@ static void mlx5e_rx_reporter_build_diagnose_output_ptp_rq(struct mlx5e_rq *rq,
 	devlink_fmsg_obj_nest_end(fmsg);
 }
 
-static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
-				      struct devlink_fmsg *fmsg,
-				      struct netlink_ext_ack *extack)
+static void mlx5e_rx_reporter_diagnose_rx_res_dir_tirns(struct mlx5e_rx_res *rx_res,
+							struct devlink_fmsg *fmsg)
 {
-	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
-	struct mlx5e_ptp *ptp_ch = priv->channels.ptp;
+	unsigned int max_nch = mlx5e_rx_res_get_max_nch(rx_res);
 	int i;
 
-	mutex_lock(&priv->state_lock);
+	devlink_fmsg_arr_pair_nest_start(fmsg, "Direct TIRs");
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		goto unlock;
+	for (i = 0; i < max_nch; i++) {
+		devlink_fmsg_obj_nest_start(fmsg);
+
+		devlink_fmsg_u32_pair_put(fmsg, "ix", i);
+		devlink_fmsg_u32_pair_put(fmsg, "tirn", mlx5e_rx_res_get_tirn_direct(rx_res, i));
+		devlink_fmsg_u32_pair_put(fmsg, "rqtn", mlx5e_rx_res_get_rqtn_direct(rx_res, i));
+
+		devlink_fmsg_obj_nest_end(fmsg);
+	}
+
+	devlink_fmsg_arr_pair_nest_end(fmsg);
+}
+
+static void mlx5e_rx_reporter_diagnose_rx_res_rss_tirn(struct mlx5e_rss *rss, bool inner,
+						       struct devlink_fmsg *fmsg)
+{
+	bool found_valid_tir = false;
+	int tt;
+
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		if (!mlx5e_rss_valid_tir(rss, tt, inner))
+			continue;
+
+		if (!found_valid_tir) {
+			char *tir_msg = inner ? "Inner TIRs Numbers" : "TIRs Numbers";
+
+			found_valid_tir = true;
+			devlink_fmsg_arr_pair_nest_start(fmsg, tir_msg);
+		}
+
+		devlink_fmsg_obj_nest_start(fmsg);
+		devlink_fmsg_string_pair_put(fmsg, "tt", mlx5_ttc_get_name(tt));
+		devlink_fmsg_u32_pair_put(fmsg, "tirn", mlx5e_rss_get_tirn(rss, tt, inner));
+		devlink_fmsg_obj_nest_end(fmsg);
+	}
+
+	if (found_valid_tir)
+		devlink_fmsg_arr_pair_nest_end(fmsg);
+}
+
+static void mlx5e_rx_reporter_diagnose_rx_res_rss_ix(struct mlx5e_rx_res *rx_res, u32 rss_idx,
+						     struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_rss *rss = mlx5e_rx_res_rss_get(rx_res, rss_idx);
+
+	if (!rss)
+		return;
+
+	devlink_fmsg_obj_nest_start(fmsg);
+
+	devlink_fmsg_u32_pair_put(fmsg, "Index", rss_idx);
+	devlink_fmsg_u32_pair_put(fmsg, "rqtn", mlx5e_rss_get_rqtn(rss));
+	mlx5e_rx_reporter_diagnose_rx_res_rss_tirn(rss, false, fmsg);
+	if (mlx5e_rss_get_inner_ft_support(rss))
+		mlx5e_rx_reporter_diagnose_rx_res_rss_tirn(rss, true, fmsg);
+
+	devlink_fmsg_obj_nest_end(fmsg);
+}
+
+static void mlx5e_rx_reporter_diagnose_rx_res_rss(struct mlx5e_rx_res *rx_res,
+						  struct devlink_fmsg *fmsg)
+{
+	int rss_ix;
+
+	devlink_fmsg_arr_pair_nest_start(fmsg, "RSS");
+	for (rss_ix = 0; rss_ix < MLX5E_MAX_NUM_RSS; rss_ix++)
+		mlx5e_rx_reporter_diagnose_rx_res_rss_ix(rx_res, rss_ix, fmsg);
+	devlink_fmsg_arr_pair_nest_end(fmsg);
+}
+
+static void mlx5e_rx_reporter_diagnose_rx_res(struct mlx5e_priv *priv,
+					      struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_rx_res *rx_res = priv->rx_res;
+
+	mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RX resources");
+	mlx5e_rx_reporter_diagnose_rx_res_dir_tirns(rx_res, fmsg);
+	mlx5e_rx_reporter_diagnose_rx_res_rss(rx_res, fmsg);
+	mlx5e_health_fmsg_named_obj_nest_end(fmsg);
+}
+
+static void mlx5e_rx_reporter_diagnose_rqs(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_ptp *ptp_ch = priv->channels.ptp;
+	int i;
 
-	mlx5e_rx_reporter_diagnose_common_config(reporter, fmsg);
 	devlink_fmsg_arr_pair_nest_start(fmsg, "RQs");
 
 	for (i = 0; i < priv->channels.num; i++) {
@@ -367,7 +453,24 @@ static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
 	}
 	if (ptp_ch && test_bit(MLX5E_PTP_STATE_RX, ptp_ch->state))
 		mlx5e_rx_reporter_build_diagnose_output_ptp_rq(&ptp_ch->rq, fmsg);
+
 	devlink_fmsg_arr_pair_nest_end(fmsg);
+}
+
+static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
+				      struct devlink_fmsg *fmsg,
+				      struct netlink_ext_ack *extack)
+{
+	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+
+	mlx5e_rx_reporter_diagnose_common_config(priv, fmsg);
+	mlx5e_rx_reporter_diagnose_rqs(priv, fmsg);
+	mlx5e_rx_reporter_diagnose_rx_res(priv, fmsg);
 unlock:
 	mutex_unlock(&priv->state_lock);
 	return 0;
@@ -549,25 +652,29 @@ void mlx5e_reporter_icosq_resume_recovery(struct mlx5e_channel *c)
 	mutex_unlock(&c->icosq_recovery_lock);
 }
 
+#define MLX5E_REPORTER_RX_GRACEFUL_PERIOD 500
+#define MLX5E_REPORTER_RX_BURST_PERIOD 500
+
 static const struct devlink_health_reporter_ops mlx5_rx_reporter_ops = {
 	.name = "rx",
 	.recover = mlx5e_rx_reporter_recover,
 	.diagnose = mlx5e_rx_reporter_diagnose,
 	.dump = mlx5e_rx_reporter_dump,
+	.default_graceful_period = MLX5E_REPORTER_RX_GRACEFUL_PERIOD,
+	.default_burst_period = MLX5E_REPORTER_RX_BURST_PERIOD,
 };
 
-#define MLX5E_REPORTER_RX_GRACEFUL_PERIOD 500
-
 void mlx5e_reporter_rx_create(struct mlx5e_priv *priv)
 {
+	struct devlink_port *port = priv->netdev->devlink_port;
 	struct devlink_health_reporter *reporter;
 
-	reporter = devlink_port_health_reporter_create(priv->netdev->devlink_port,
+	reporter = devlink_port_health_reporter_create(port,
 						       &mlx5_rx_reporter_ops,
-						       MLX5E_REPORTER_RX_GRACEFUL_PERIOD, priv);
+						       priv);
 	if (IS_ERR(reporter)) {
-		netdev_warn(priv->netdev, "Failed to create rx reporter, err = %ld\n",
-			    PTR_ERR(reporter));
+		netdev_warn(priv->netdev, "Failed to create rx reporter, err = %pe\n",
+			    reporter);
 		return;
 	}
 	priv->rx_reporter = reporter;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 09433b91be17..9e2cf191ed30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -13,10 +13,8 @@ static const char * const sq_sw_state_type_name[] = {
 	[MLX5E_SQ_STATE_RECOVERING] = "recovering",
 	[MLX5E_SQ_STATE_IPSEC] = "ipsec",
 	[MLX5E_SQ_STATE_DIM] = "dim",
-	[MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE] = "vlan_need_l2_inline",
 	[MLX5E_SQ_STATE_PENDING_XSK_TX] = "pending_xsk_tx",
 	[MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC] = "pending_tls_rx_resync",
-	[MLX5E_SQ_STATE_XDP_MULTIBUF] = "xdp_multibuf",
 };
 
 static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
@@ -108,9 +106,7 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx)
 	mlx5e_reset_txqsq_cc_pc(sq);
 	sq->stats->recover++;
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
-	rtnl_lock();
 	mlx5e_activate_txqsq(sq);
-	rtnl_unlock();
 
 	if (sq->channel)
 		mlx5e_trigger_napi_icosq(sq->channel);
@@ -184,16 +180,12 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx)
 	carrier_ok = netif_carrier_ok(netdev);
 	netif_carrier_off(netdev);
 
-	rtnl_lock();
 	mlx5e_deactivate_priv_channels(priv);
-	rtnl_unlock();
 
 	mlx5e_ptp_close(chs->ptp);
 	err = mlx5e_ptp_open(priv, &chs->params, chs->c[0]->lag_port, &chs->ptp);
 
-	rtnl_lock();
 	mlx5e_activate_priv_channels(priv);
-	rtnl_unlock();
 
 	/* return carrier back if needed */
 	if (carrier_ok)
@@ -319,6 +311,30 @@ out:
 	mlx5e_health_fmsg_named_obj_nest_end(fmsg);
 }
 
+static void
+mlx5e_tx_reporter_diagnose_tis_config(struct devlink_health_reporter *reporter,
+				      struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+	u8 num_tc = mlx5e_get_dcb_num_tc(&priv->channels.params);
+	u32 tc, i, tisn;
+
+	devlink_fmsg_arr_pair_nest_start(fmsg, "TIS Config");
+	for (i = 0; i < mlx5e_get_num_lag_ports(priv->mdev); i++) {
+		for (tc = 0; tc < num_tc; tc++) {
+			tisn = mlx5e_profile_get_tisn(priv->mdev, priv,
+						      priv->profile, i, tc);
+
+			devlink_fmsg_obj_nest_start(fmsg);
+			devlink_fmsg_u32_pair_put(fmsg, "lag port", i);
+			devlink_fmsg_u32_pair_put(fmsg, "tc", tc);
+			devlink_fmsg_u32_pair_put(fmsg, "tisn", tisn);
+			devlink_fmsg_obj_nest_end(fmsg);
+		}
+	}
+	devlink_fmsg_arr_pair_nest_end(fmsg);
+}
+
 static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
 				      struct devlink_fmsg *fmsg,
 				      struct netlink_ext_ack *extack)
@@ -334,6 +350,7 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
 		goto unlock;
 
 	mlx5e_tx_reporter_diagnose_common_config(reporter, fmsg);
+	mlx5e_tx_reporter_diagnose_tis_config(reporter, fmsg);
 	devlink_fmsg_arr_pair_nest_start(fmsg, "SQs");
 
 	for (i = 0; i < priv->channels.num; i++) {
@@ -522,26 +539,30 @@ void mlx5e_reporter_tx_ptpsq_unhealthy(struct mlx5e_ptpsq *ptpsq)
 	mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx);
 }
 
+#define MLX5E_REPORTER_TX_GRACEFUL_PERIOD 500
+#define MLX5E_REPORTER_TX_BURST_PERIOD 500
+
 static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = {
 		.name = "tx",
 		.recover = mlx5e_tx_reporter_recover,
 		.diagnose = mlx5e_tx_reporter_diagnose,
 		.dump = mlx5e_tx_reporter_dump,
+		.default_graceful_period = MLX5E_REPORTER_TX_GRACEFUL_PERIOD,
+		.default_burst_period = MLX5E_REPORTER_TX_BURST_PERIOD,
 };
 
-#define MLX5_REPORTER_TX_GRACEFUL_PERIOD 500
-
 void mlx5e_reporter_tx_create(struct mlx5e_priv *priv)
 {
+	struct devlink_port *port = priv->netdev->devlink_port;
 	struct devlink_health_reporter *reporter;
 
-	reporter = devlink_port_health_reporter_create(priv->netdev->devlink_port,
+	reporter = devlink_port_health_reporter_create(port,
 						       &mlx5_tx_reporter_ops,
-						       MLX5_REPORTER_TX_GRACEFUL_PERIOD, priv);
+						       priv);
 	if (IS_ERR(reporter)) {
 		netdev_warn(priv->netdev,
-			    "Failed to create tx reporter, err = %ld\n",
-			    PTR_ERR(reporter));
+			    "Failed to create tx reporter, err = %pe\n",
+			    reporter);
 		return;
 	}
 	priv->tx_reporter = reporter;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
index 5f742f896600..88b0e1050d1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
@@ -75,18 +75,22 @@ struct mlx5e_rss {
 	struct mlx5e_tir *inner_tir[MLX5E_NUM_INDIR_TIRS];
 	struct mlx5e_rqt rqt;
 	struct mlx5_core_dev *mdev; /* primary */
-	u32 drop_rqn;
-	bool inner_ft_support;
+	struct mlx5e_rss_params params;
 	bool enabled;
 	refcount_t refcnt;
 };
 
+bool mlx5e_rss_get_inner_ft_support(struct mlx5e_rss *rss)
+{
+	return rss->params.inner_ft_support;
+}
+
 void mlx5e_rss_params_indir_modify_actual_size(struct mlx5e_rss *rss, u32 num_channels)
 {
 	rss->indir.actual_table_size = mlx5e_rqt_size(rss->mdev, num_channels);
 }
 
-int mlx5e_rss_params_indir_init(struct mlx5e_rss_params_indir *indir, struct mlx5_core_dev *mdev,
+int mlx5e_rss_params_indir_init(struct mlx5e_rss_params_indir *indir,
 				u32 actual_table_size, u32 max_table_size)
 {
 	indir->table = kvmalloc_array(max_table_size, sizeof(*indir->table), GFP_KERNEL);
@@ -134,7 +138,8 @@ static struct mlx5e_rss *mlx5e_rss_init_copy(const struct mlx5e_rss *from)
 	if (!rss)
 		return ERR_PTR(-ENOMEM);
 
-	err = mlx5e_rss_params_indir_init(&rss->indir, from->mdev, from->indir.actual_table_size,
+	err = mlx5e_rss_params_indir_init(&rss->indir,
+					  from->indir.actual_table_size,
 					  from->indir.max_table_size);
 	if (err)
 		goto err_free_rss;
@@ -156,6 +161,7 @@ static void mlx5e_rss_params_init(struct mlx5e_rss *rss)
 {
 	enum mlx5_traffic_types tt;
 
+	rss->hash.symmetric = true;
 	rss->hash.hfunc = ETH_RSS_HASH_TOP;
 	netdev_rss_key_fill(rss->hash.toeplitz_hash_key,
 			    sizeof(rss->hash.toeplitz_hash_key));
@@ -186,11 +192,12 @@ mlx5e_rss_get_tt_config(struct mlx5e_rss *rss, enum mlx5_traffic_types tt)
 	return rss_tt;
 }
 
-static int mlx5e_rss_create_tir(struct mlx5e_rss *rss,
-				enum mlx5_traffic_types tt,
-				const struct mlx5e_packet_merge_param *init_pkt_merge_param,
-				bool inner)
+static int
+mlx5e_rss_create_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
+		     const struct mlx5e_packet_merge_param *pkt_merge_param,
+		     bool inner)
 {
+	bool rss_inner = rss->params.inner_ft_support;
 	struct mlx5e_rss_params_traffic_type rss_tt;
 	struct mlx5e_tir_builder *builder;
 	struct mlx5e_tir **tir_p;
@@ -198,7 +205,7 @@ static int mlx5e_rss_create_tir(struct mlx5e_rss *rss,
 	u32 rqtn;
 	int err;
 
-	if (inner && !rss->inner_ft_support) {
+	if (inner && !rss_inner) {
 		mlx5e_rss_warn(rss->mdev,
 			       "Cannot create inner indirect TIR[%d], RSS inner FT is not supported.\n",
 			       tt);
@@ -221,9 +228,11 @@ static int mlx5e_rss_create_tir(struct mlx5e_rss *rss,
 
 	rqtn = mlx5e_rqt_get_rqtn(&rss->rqt);
 	mlx5e_tir_builder_build_rqt(builder, rss->mdev->mlx5e_res.hw_objs.td.tdn,
-				    rqtn, rss->inner_ft_support);
-	mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param);
+				    rqtn, rss_inner);
+	mlx5e_tir_builder_build_packet_merge(builder, pkt_merge_param);
 	rss_tt = mlx5e_rss_get_tt_config(rss, tt);
+	mlx5e_tir_builder_build_self_lb_block(builder, rss->params.self_lb_blk,
+					      rss->params.self_lb_blk);
 	mlx5e_tir_builder_build_rss(builder, &rss->hash, &rss_tt, inner);
 
 	err = mlx5e_tir_init(tir, builder, rss->mdev, true);
@@ -258,15 +267,16 @@ static void mlx5e_rss_destroy_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types
 	*tir_p = NULL;
 }
 
-static int mlx5e_rss_create_tirs(struct mlx5e_rss *rss,
-				 const struct mlx5e_packet_merge_param *init_pkt_merge_param,
-				 bool inner)
+static int
+mlx5e_rss_create_tirs(struct mlx5e_rss *rss,
+		      const struct mlx5e_packet_merge_param *pkt_merge_param,
+		      bool inner)
 {
 	enum mlx5_traffic_types tt, max_tt;
 	int err;
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		err = mlx5e_rss_create_tir(rss, tt, init_pkt_merge_param, inner);
+		err = mlx5e_rss_create_tir(rss, tt, pkt_merge_param, inner);
 		if (err)
 			goto err_destroy_tirs;
 	}
@@ -329,7 +339,7 @@ static int mlx5e_rss_update_tirs(struct mlx5e_rss *rss)
 				       tt, err);
 		}
 
-		if (!rss->inner_ft_support)
+		if (!rss->params.inner_ft_support)
 			continue;
 
 		err = mlx5e_rss_update_tir(rss, tt, true);
@@ -349,14 +359,16 @@ static int mlx5e_rss_init_no_tirs(struct mlx5e_rss *rss)
 	refcount_set(&rss->refcnt, 1);
 
 	return mlx5e_rqt_init_direct(&rss->rqt, rss->mdev, true,
-				     rss->drop_rqn, rss->indir.max_table_size);
+				     rss->params.drop_rqn,
+				     rss->indir.max_table_size);
 }
 
-struct mlx5e_rss *mlx5e_rss_init(struct mlx5_core_dev *mdev, bool inner_ft_support, u32 drop_rqn,
-				 const struct mlx5e_packet_merge_param *init_pkt_merge_param,
-				 enum mlx5e_rss_init_type type, unsigned int nch,
-				 unsigned int max_nch)
+struct mlx5e_rss *
+mlx5e_rss_init(struct mlx5_core_dev *mdev,
+	       const struct mlx5e_rss_params *params,
+	       const struct mlx5e_rss_init_params *init_params)
 {
+	u32 rqt_max_size, rqt_size;
 	struct mlx5e_rss *rss;
 	int err;
 
@@ -364,29 +376,31 @@ struct mlx5e_rss *mlx5e_rss_init(struct mlx5_core_dev *mdev, bool inner_ft_suppo
 	if (!rss)
 		return ERR_PTR(-ENOMEM);
 
-	err = mlx5e_rss_params_indir_init(&rss->indir, mdev,
-					  mlx5e_rqt_size(mdev, nch),
-					  mlx5e_rqt_size(mdev, max_nch));
+	rqt_size = mlx5e_rqt_size(mdev, init_params->nch);
+	rqt_max_size = mlx5e_rqt_size(mdev, init_params->max_nch);
+	err = mlx5e_rss_params_indir_init(&rss->indir, rqt_size, rqt_max_size);
 	if (err)
 		goto err_free_rss;
 
 	rss->mdev = mdev;
-	rss->inner_ft_support = inner_ft_support;
-	rss->drop_rqn = drop_rqn;
+	rss->params = *params;
 
 	err = mlx5e_rss_init_no_tirs(rss);
 	if (err)
 		goto err_free_indir;
 
-	if (type == MLX5E_RSS_INIT_NO_TIRS)
+	if (init_params->type == MLX5E_RSS_INIT_NO_TIRS)
 		goto out;
 
-	err = mlx5e_rss_create_tirs(rss, init_pkt_merge_param, false);
+	err = mlx5e_rss_create_tirs(rss, init_params->pkt_merge_param,
+				    false);
 	if (err)
 		goto err_destroy_rqt;
 
-	if (inner_ft_support) {
-		err = mlx5e_rss_create_tirs(rss, init_pkt_merge_param, true);
+	if (params->inner_ft_support) {
+		err = mlx5e_rss_create_tirs(rss,
+					    init_params->pkt_merge_param,
+					    true);
 		if (err)
 			goto err_destroy_tirs;
 	}
@@ -412,7 +426,7 @@ int mlx5e_rss_cleanup(struct mlx5e_rss *rss)
 
 	mlx5e_rss_destroy_tirs(rss, false);
 
-	if (rss->inner_ft_support)
+	if (rss->params.inner_ft_support)
 		mlx5e_rss_destroy_tirs(rss, true);
 
 	mlx5e_rqt_destroy(&rss->rqt);
@@ -442,20 +456,30 @@ u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
 {
 	struct mlx5e_tir *tir;
 
-	WARN_ON(inner && !rss->inner_ft_support);
+	WARN_ON(inner && !rss->params.inner_ft_support);
 	tir = rss_get_tir(rss, tt, inner);
 	WARN_ON(!tir);
 
 	return mlx5e_tir_get_tirn(tir);
 }
 
+u32 mlx5e_rss_get_rqtn(struct mlx5e_rss *rss)
+{
+	return mlx5e_rqt_get_rqtn(&rss->rqt);
+}
+
+bool mlx5e_rss_valid_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, bool inner)
+{
+	return !!rss_get_tir(rss, tt, inner);
+}
+
 /* Fill the "tirn" output parameter.
  * Create the requested TIR if it's its first usage.
  */
-int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
-			  enum mlx5_traffic_types tt,
-			  const struct mlx5e_packet_merge_param *init_pkt_merge_param,
-			  bool inner, u32 *tirn)
+int
+mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
+		      const struct mlx5e_packet_merge_param *pkt_merge_param,
+		      bool inner, u32 *tirn)
 {
 	struct mlx5e_tir *tir;
 
@@ -463,7 +487,7 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
 	if (!tir) { /* TIR doesn't exist, create one */
 		int err;
 
-		err = mlx5e_rss_create_tir(rss, tt, init_pkt_merge_param, inner);
+		err = mlx5e_rss_create_tir(rss, tt, pkt_merge_param, inner);
 		if (err)
 			return err;
 		tir = rss_get_tir(rss, tt, inner);
@@ -496,10 +520,11 @@ void mlx5e_rss_disable(struct mlx5e_rss *rss)
 	int err;
 
 	rss->enabled = false;
-	err = mlx5e_rqt_redirect_direct(&rss->rqt, rss->drop_rqn, NULL);
+	err = mlx5e_rqt_redirect_direct(&rss->rqt, rss->params.drop_rqn, NULL);
 	if (err)
 		mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to drop RQ %#x: err = %d\n",
-			       mlx5e_rqt_get_rqtn(&rss->rqt), rss->drop_rqn, err);
+			       mlx5e_rqt_get_rqtn(&rss->rqt),
+			       rss->params.drop_rqn, err);
 }
 
 int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss,
@@ -532,7 +557,7 @@ int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss,
 		}
 
 inner_tir:
-		if (!rss->inner_ft_support)
+		if (!rss->params.inner_ft_support)
 			continue;
 
 		tir = rss_get_tir(rss, tt, true);
@@ -551,7 +576,8 @@ inner_tir:
 	return final_err;
 }
 
-int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc)
+void mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc,
+			bool *symmetric)
 {
 	if (indir)
 		memcpy(indir, rss->indir.table,
@@ -564,11 +590,12 @@ int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc)
 	if (hfunc)
 		*hfunc = rss->hash.hfunc;
 
-	return 0;
+	if (symmetric)
+		*symmetric = rss->hash.symmetric;
 }
 
 int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
-		       const u8 *key, const u8 *hfunc,
+		       const u8 *key, const u8 *hfunc, const bool *symmetric,
 		       u32 *rqns, u32 *vhca_ids, unsigned int num_rqns)
 {
 	bool changed_indir = false;
@@ -608,6 +635,11 @@ int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
 		       rss->indir.actual_table_size * sizeof(*rss->indir.table));
 	}
 
+	if (symmetric) {
+		rss->hash.symmetric = *symmetric;
+		changed_hash = true;
+	}
+
 	if (changed_indir && rss->enabled) {
 		err = mlx5e_rss_apply(rss, rqns, vhca_ids, num_rqns);
 		if (err) {
@@ -658,7 +690,7 @@ int mlx5e_rss_set_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
 		return err;
 	}
 
-	if (!(rss->inner_ft_support))
+	if (!(rss->params.inner_ft_support))
 		return 0;
 
 	err = mlx5e_rss_update_tir(rss, tt, true);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
index d0df98963c8d..17664757a561 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
@@ -13,40 +13,57 @@ enum mlx5e_rss_init_type {
 	MLX5E_RSS_INIT_TIRS
 };
 
+struct mlx5e_rss_init_params {
+	enum mlx5e_rss_init_type type;
+	const struct mlx5e_packet_merge_param *pkt_merge_param;
+	unsigned int nch;
+	unsigned int max_nch;
+};
+
+struct mlx5e_rss_params {
+	bool inner_ft_support;
+	u32 drop_rqn;
+	bool self_lb_blk;
+};
+
 struct mlx5e_rss_params_traffic_type
 mlx5e_rss_get_default_tt_config(enum mlx5_traffic_types tt);
 
 struct mlx5e_rss;
 
-int mlx5e_rss_params_indir_init(struct mlx5e_rss_params_indir *indir, struct mlx5_core_dev *mdev,
+int mlx5e_rss_params_indir_init(struct mlx5e_rss_params_indir *indir,
 				u32 actual_table_size, u32 max_table_size);
 void mlx5e_rss_params_indir_cleanup(struct mlx5e_rss_params_indir *indir);
 void mlx5e_rss_params_indir_modify_actual_size(struct mlx5e_rss *rss, u32 num_channels);
-struct mlx5e_rss *mlx5e_rss_init(struct mlx5_core_dev *mdev, bool inner_ft_support, u32 drop_rqn,
-				 const struct mlx5e_packet_merge_param *init_pkt_merge_param,
-				 enum mlx5e_rss_init_type type, unsigned int nch,
-				 unsigned int max_nch);
+struct mlx5e_rss *
+mlx5e_rss_init(struct mlx5_core_dev *mdev,
+	       const struct mlx5e_rss_params *params,
+	       const struct mlx5e_rss_init_params *init_params);
 int mlx5e_rss_cleanup(struct mlx5e_rss *rss);
 
 void mlx5e_rss_refcnt_inc(struct mlx5e_rss *rss);
 void mlx5e_rss_refcnt_dec(struct mlx5e_rss *rss);
 unsigned int mlx5e_rss_refcnt_read(struct mlx5e_rss *rss);
 
+bool mlx5e_rss_get_inner_ft_support(struct mlx5e_rss *rss);
 u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
 		       bool inner);
-int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
-			  enum mlx5_traffic_types tt,
-			  const struct mlx5e_packet_merge_param *init_pkt_merge_param,
-			  bool inner, u32 *tirn);
+bool mlx5e_rss_valid_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, bool inner);
+u32 mlx5e_rss_get_rqtn(struct mlx5e_rss *rss);
+int
+mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
+		      const struct mlx5e_packet_merge_param *pkt_merge_param,
+		      bool inner, u32 *tirn);
 
 void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns);
 void mlx5e_rss_disable(struct mlx5e_rss *rss);
 
 int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss,
 				     struct mlx5e_packet_merge_param *pkt_merge_param);
-int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc);
+void mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc,
+			bool *symmetric);
 int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
-		       const u8 *key, const u8 *hfunc,
+		       const u8 *key, const u8 *hfunc, const bool *symmetric,
 		       u32 *rqns, u32 *vhca_ids, unsigned int num_rqns);
 struct mlx5e_rss_params_hash mlx5e_rss_get_hash(struct mlx5e_rss *rss);
 u8 mlx5e_rss_get_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
index a86eade9a9e0..55c117b7d8c4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
@@ -5,8 +5,6 @@
 #include "channels.h"
 #include "params.h"
 
-#define MLX5E_MAX_NUM_RSS 16
-
 struct mlx5e_rx_res {
 	struct mlx5_core_dev *mdev; /* primary */
 	enum mlx5e_rx_res_features features;
@@ -56,51 +54,74 @@ static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res,
 				     unsigned int init_nch)
 {
 	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
+	struct mlx5e_rss_init_params init_params;
+	struct mlx5e_rss_params rss_params;
 	struct mlx5e_rss *rss;
 
 	if (WARN_ON(res->rss[0]))
 		return -EINVAL;
 
-	rss = mlx5e_rss_init(res->mdev, inner_ft_support, res->drop_rqn,
-			     &res->pkt_merge_param, MLX5E_RSS_INIT_TIRS, init_nch, res->max_nch);
+	init_params = (struct mlx5e_rss_init_params) {
+		.type = MLX5E_RSS_INIT_TIRS,
+		.pkt_merge_param = &res->pkt_merge_param,
+		.nch = init_nch,
+		.max_nch = res->max_nch,
+	};
+
+	rss_params = (struct mlx5e_rss_params) {
+		.inner_ft_support = inner_ft_support,
+		.drop_rqn = res->drop_rqn,
+		.self_lb_blk =
+			res->features & MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK,
+	};
+
+	rss = mlx5e_rss_init(res->mdev, &rss_params, &init_params);
 	if (IS_ERR(rss))
 		return PTR_ERR(rss);
 
-	mlx5e_rss_set_indir_uniform(rss, init_nch);
+	mlx5e_rss_set_indir_uniform(rss, init_params.nch);
 
 	res->rss[0] = rss;
 
 	return 0;
 }
 
-int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int init_nch)
+int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 rss_idx, unsigned int init_nch)
 {
 	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
+	struct mlx5e_rss_init_params init_params;
+	struct mlx5e_rss_params rss_params;
 	struct mlx5e_rss *rss;
-	int i;
 
-	for (i = 1; i < MLX5E_MAX_NUM_RSS; i++)
-		if (!res->rss[i])
-			break;
-
-	if (i == MLX5E_MAX_NUM_RSS)
+	if (WARN_ON_ONCE(res->rss[rss_idx]))
 		return -ENOSPC;
 
-	rss = mlx5e_rss_init(res->mdev, inner_ft_support, res->drop_rqn,
-			     &res->pkt_merge_param, MLX5E_RSS_INIT_NO_TIRS, init_nch,
-			     res->max_nch);
+	init_params = (struct mlx5e_rss_init_params) {
+		.type = MLX5E_RSS_INIT_NO_TIRS,
+		.pkt_merge_param = &res->pkt_merge_param,
+		.nch = init_nch,
+		.max_nch = res->max_nch,
+	};
+
+	rss_params = (struct mlx5e_rss_params) {
+		.inner_ft_support = inner_ft_support,
+		.drop_rqn = res->drop_rqn,
+		.self_lb_blk =
+			res->features & MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK,
+	};
+
+	rss = mlx5e_rss_init(res->mdev, &rss_params, &init_params);
 	if (IS_ERR(rss))
 		return PTR_ERR(rss);
 
-	mlx5e_rss_set_indir_uniform(rss, init_nch);
+	mlx5e_rss_set_indir_uniform(rss, init_params.nch);
 	if (res->rss_active) {
 		u32 *vhca_ids = get_vhca_ids(res, 0);
 
 		mlx5e_rss_enable(rss, res->rss_rqns, vhca_ids, res->rss_nch);
 	}
 
-	res->rss[i] = rss;
-	*rss_idx = i;
+	res->rss[rss_idx] = rss;
 
 	return 0;
 }
@@ -195,23 +216,22 @@ void mlx5e_rx_res_rss_set_indir_uniform(struct mlx5e_rx_res *res, unsigned int n
 	mlx5e_rss_set_indir_uniform(res->rss[0], nch);
 }
 
-int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
-			      u32 *indir, u8 *key, u8 *hfunc)
+void mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
+			       u32 *indir, u8 *key, u8 *hfunc, bool *symmetric)
 {
-	struct mlx5e_rss *rss;
+	struct mlx5e_rss *rss = NULL;
 
-	if (rss_idx >= MLX5E_MAX_NUM_RSS)
-		return -EINVAL;
+	if (rss_idx < MLX5E_MAX_NUM_RSS)
+		rss = res->rss[rss_idx];
+	if (WARN_ON_ONCE(!rss))
+		return;
 
-	rss = res->rss[rss_idx];
-	if (!rss)
-		return -ENOENT;
-
-	return mlx5e_rss_get_rxfh(rss, indir, key, hfunc);
+	mlx5e_rss_get_rxfh(rss, indir, key, hfunc, symmetric);
 }
 
 int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
-			      const u32 *indir, const u8 *key, const u8 *hfunc)
+			      const u32 *indir, const u8 *key, const u8 *hfunc,
+			      const bool *symmetric)
 {
 	u32 *vhca_ids = get_vhca_ids(res, 0);
 	struct mlx5e_rss *rss;
@@ -223,8 +243,8 @@ int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
 	if (!rss)
 		return -ENOENT;
 
-	return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, vhca_ids,
-				  res->rss_nch);
+	return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, symmetric,
+				  res->rss_rqns, vhca_ids, res->rss_nch);
 }
 
 int mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx,
@@ -330,6 +350,7 @@ static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsig
 static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res)
 {
 	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
+	bool self_lb_blk = res->features & MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK;
 	struct mlx5e_tir_builder *builder;
 	int err = 0;
 	int ix;
@@ -360,6 +381,8 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res)
 					    mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt),
 					    inner_ft_support);
 		mlx5e_tir_builder_build_packet_merge(builder, &res->pkt_merge_param);
+		mlx5e_tir_builder_build_self_lb_block(builder, self_lb_blk,
+						      self_lb_blk);
 		mlx5e_tir_builder_build_direct(builder);
 
 		err = mlx5e_tir_init(&res->channels[ix].direct_tir, builder, res->mdev, true);
@@ -447,7 +470,7 @@ static void mlx5e_rx_res_ptp_destroy(struct mlx5e_rx_res *res)
 struct mlx5e_rx_res *
 mlx5e_rx_res_create(struct mlx5_core_dev *mdev, enum mlx5e_rx_res_features features,
 		    unsigned int max_nch, u32 drop_rqn,
-		    const struct mlx5e_packet_merge_param *init_pkt_merge_param,
+		    const struct mlx5e_packet_merge_param *pkt_merge_param,
 		    unsigned int init_nch)
 {
 	bool multi_vhca = features & MLX5E_RX_RES_FEATURE_MULTI_VHCA;
@@ -463,7 +486,7 @@ mlx5e_rx_res_create(struct mlx5_core_dev *mdev, enum mlx5e_rx_res_features featu
 	res->max_nch = max_nch;
 	res->drop_rqn = drop_rqn;
 
-	res->pkt_merge_param = *init_pkt_merge_param;
+	res->pkt_merge_param = *pkt_merge_param;
 	init_rwsem(&res->pkt_merge_param_sem);
 
 	err = mlx5e_rx_res_rss_init_def(res, init_nch);
@@ -497,6 +520,11 @@ void mlx5e_rx_res_destroy(struct mlx5e_rx_res *res)
 	mlx5e_rx_res_free(res);
 }
 
+unsigned int mlx5e_rx_res_get_max_nch(struct mlx5e_rx_res *res)
+{
+	return res->max_nch;
+}
+
 u32 mlx5e_rx_res_get_tirn_direct(struct mlx5e_rx_res *res, unsigned int ix)
 {
 	return mlx5e_tir_get_tirn(&res->channels[ix].direct_tir);
@@ -522,7 +550,7 @@ u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res)
 	return mlx5e_tir_get_tirn(&res->ptp.tir);
 }
 
-static u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix)
+u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix)
 {
 	return mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt);
 }
@@ -575,8 +603,6 @@ void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_chann
 
 	for (ix = 0; ix < nch; ix++)
 		mlx5e_rx_res_channel_activate_direct(res, chs, ix);
-	for (ix = nch; ix < res->max_nch; ix++)
-		mlx5e_rx_res_channel_deactivate_direct(res, ix);
 
 	if (res->features & MLX5E_RX_RES_FEATURE_PTP) {
 		u32 rqn;
@@ -599,7 +625,7 @@ void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res)
 
 	mlx5e_rx_res_rss_disable(res);
 
-	for (ix = 0; ix < res->max_nch; ix++)
+	for (ix = 0; ix < res->rss_nch; ix++)
 		mlx5e_rx_res_channel_deactivate_direct(res, ix);
 
 	if (res->features & MLX5E_RX_RES_FEATURE_PTP) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
index 7b1a9f0f1874..675780120a20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
@@ -10,6 +10,8 @@
 #include "fs.h"
 #include "rss.h"
 
+#define MLX5E_MAX_NUM_RSS 16
+
 struct mlx5e_rx_res;
 
 struct mlx5e_channels;
@@ -19,13 +21,14 @@ enum mlx5e_rx_res_features {
 	MLX5E_RX_RES_FEATURE_INNER_FT = BIT(0),
 	MLX5E_RX_RES_FEATURE_PTP = BIT(1),
 	MLX5E_RX_RES_FEATURE_MULTI_VHCA = BIT(2),
+	MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK = BIT(3),
 };
 
 /* Setup */
 struct mlx5e_rx_res *
 mlx5e_rx_res_create(struct mlx5_core_dev *mdev, enum mlx5e_rx_res_features features,
 		    unsigned int max_nch, u32 drop_rqn,
-		    const struct mlx5e_packet_merge_param *init_pkt_merge_param,
+		    const struct mlx5e_packet_merge_param *pkt_merge_param,
 		    unsigned int init_nch);
 void mlx5e_rx_res_destroy(struct mlx5e_rx_res *res);
 
@@ -34,6 +37,9 @@ u32 mlx5e_rx_res_get_tirn_direct(struct mlx5e_rx_res *res, unsigned int ix);
 u32 mlx5e_rx_res_get_tirn_rss(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
 u32 mlx5e_rx_res_get_tirn_rss_inner(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
 u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res);
+u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix);
+unsigned int mlx5e_rx_res_get_max_nch(struct mlx5e_rx_res *res);
+bool mlx5_rx_res_rss_inner_ft_support(struct mlx5e_rx_res *res);
 
 /* Activate/deactivate API */
 void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs);
@@ -43,10 +49,12 @@ void mlx5e_rx_res_xsk_update(struct mlx5e_rx_res *res, struct mlx5e_channels *ch
 
 /* Configuration API */
 void mlx5e_rx_res_rss_set_indir_uniform(struct mlx5e_rx_res *res, unsigned int nch);
-int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
-			      u32 *indir, u8 *key, u8 *hfunc);
+void mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
+			       u32 *indir, u8 *key, u8 *hfunc,
+			       bool *symmetric);
 int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
-			      const u32 *indir, const u8 *key, const u8 *hfunc);
+			      const u32 *indir, const u8 *key, const u8 *hfunc,
+			      const bool *symmetric);
 
 int mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx,
 				     enum mlx5_traffic_types tt);
@@ -55,7 +63,7 @@ int mlx5e_rx_res_rss_set_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx,
 int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res,
 					struct mlx5e_packet_merge_param *pkt_merge_param);
 
-int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int init_nch);
+int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 rss_idx, unsigned int init_nch);
 int mlx5e_rx_res_rss_destroy(struct mlx5e_rx_res *res, u32 rss_idx);
 int mlx5e_rx_res_rss_cnt(struct mlx5e_rx_res *res);
 int mlx5e_rx_res_rss_index(struct mlx5e_rx_res *res, struct mlx5e_rss *rss);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
index d6c12d0ea55b..2e528b2c34d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
@@ -73,11 +73,6 @@ struct mlx5e_tc_act {
 	bool is_terminating_action;
 };
 
-struct mlx5e_tc_flow_action {
-	unsigned int num_entries;
-	struct flow_action_entry **entries;
-};
-
 extern struct mlx5e_tc_act mlx5e_tc_act_drop;
 extern struct mlx5e_tc_act mlx5e_tc_act_trap;
 extern struct mlx5e_tc_act mlx5e_tc_act_accept;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
index feeb41693c17..b6cabe829f19 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
@@ -5,6 +5,16 @@
 #include "en/tc_priv.h"
 #include "en/tc_ct.h"
 
+static bool
+tc_act_can_offload_ct(struct mlx5e_tc_act_parse_state *parse_state,
+		      const struct flow_action_entry *act,
+		      int act_index,
+		      struct mlx5_flow_attr *attr)
+{
+	return !((act->ct.action & TCA_CT_ACT_COMMIT) &&
+		 flow_action_is_last_entry(parse_state->flow_action, act));
+}
+
 static int
 tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state,
 		const struct flow_action_entry *act,
@@ -56,6 +66,7 @@ tc_act_is_missable_ct(const struct flow_action_entry *act)
 }
 
 struct mlx5e_tc_act mlx5e_tc_act_ct = {
+	.can_offload = tc_act_can_offload_ct,
 	.parse_action = tc_act_parse_ct,
 	.post_parse = tc_act_post_parse_ct,
 	.is_multi_table_act = tc_act_is_multi_table_act_ct,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c
index a13c5e707b83..9bdb5820c553 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c
@@ -94,29 +94,30 @@ mlx5e_tc_act_vlan_add_push_action(struct mlx5e_priv *priv,
 				  struct net_device **out_dev,
 				  struct netlink_ext_ack *extack)
 {
-	struct net_device *vlan_dev = *out_dev;
-	struct flow_action_entry vlan_act = {
-		.id = FLOW_ACTION_VLAN_PUSH,
-		.vlan.vid = vlan_dev_vlan_id(vlan_dev),
-		.vlan.proto = vlan_dev_vlan_proto(vlan_dev),
-		.vlan.prio = 0,
-	};
-	int err;
-
-	err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, &attr->action, extack, NULL);
-	if (err)
-		return err;
-
-	rcu_read_lock();
-	*out_dev = dev_get_by_index_rcu(dev_net(vlan_dev), dev_get_iflink(vlan_dev));
-	rcu_read_unlock();
-	if (!*out_dev)
-		return -ENODEV;
+	do {
+		struct net_device *vlan_dev = *out_dev;
+		struct flow_action_entry vlan_act = {
+			.id = FLOW_ACTION_VLAN_PUSH,
+			.vlan.vid = vlan_dev_vlan_id(vlan_dev),
+			.vlan.proto = vlan_dev_vlan_proto(vlan_dev),
+			.vlan.prio = 0,
+		};
+		int err;
+
+		err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr,
+					   &attr->action, extack, NULL);
+		if (err)
+			return err;
 
-	if (is_vlan_dev(*out_dev))
-		err = mlx5e_tc_act_vlan_add_push_action(priv, attr, out_dev, extack);
+		rcu_read_lock();
+		*out_dev = dev_get_by_index_rcu(dev_net(vlan_dev),
+						dev_get_iflink(vlan_dev));
+		rcu_read_unlock();
+		if (!*out_dev)
+			return -ENODEV;
+	} while (is_vlan_dev(*out_dev));
 
-	return err;
+	return 0;
 }
 
 int
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h
index 62b3f7ff5562..e5b30801314b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h
@@ -48,4 +48,14 @@ mlx5_ct_fs_smfs_ops_get(void)
 }
 #endif /* IS_ENABLED(CONFIG_MLX5_SW_STEERING) */
 
+#if IS_ENABLED(CONFIG_MLX5_HW_STEERING)
+struct mlx5_ct_fs_ops *mlx5_ct_fs_hmfs_ops_get(void);
+#else
+static inline struct mlx5_ct_fs_ops *
+mlx5_ct_fs_hmfs_ops_get(void)
+{
+	return NULL;
+}
+#endif /* IS_ENABLED(CONFIG_MLX5_SW_STEERING) */
+
 #endif /* __MLX5_EN_TC_CT_FS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c
new file mode 100644
index 000000000000..d3db6146fcad
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c
@@ -0,0 +1,294 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. */
+
+#include "en_tc.h"
+#include "en/tc_ct.h"
+#include "en/tc_priv.h"
+#include "en/tc/ct_fs.h"
+#include "fs_core.h"
+#include "steering/hws/fs_hws_pools.h"
+#include "steering/hws/mlx5hws.h"
+#include "steering/hws/table.h"
+
+struct mlx5_ct_fs_hmfs_matcher {
+	struct mlx5hws_bwc_matcher *hws_bwc_matcher;
+	refcount_t ref;
+};
+
+/* We need {ipv4, ipv6} x {tcp, udp, gre}  matchers. */
+#define NUM_MATCHERS (2 * 3)
+
+struct mlx5_ct_fs_hmfs {
+	struct mlx5hws_table *ct_tbl;
+	struct mlx5hws_table *ct_nat_tbl;
+	struct mlx5_flow_table *ct_nat;
+	struct mlx5hws_action *fwd_action;
+	struct mlx5hws_action *last_action;
+	struct mlx5hws_context *ctx;
+	struct mutex lock;   /* Guards matchers */
+	struct mlx5_ct_fs_hmfs_matcher matchers[NUM_MATCHERS];
+	struct mlx5_ct_fs_hmfs_matcher matchers_nat[NUM_MATCHERS];
+};
+
+struct mlx5_ct_fs_hmfs_rule {
+	struct mlx5_ct_fs_rule fs_rule;
+	struct mlx5hws_bwc_rule *hws_bwc_rule;
+	struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher;
+	struct mlx5_fc *counter;
+};
+
+static u32 get_matcher_idx(bool ipv4, bool tcp, bool gre)
+{
+	return ipv4 * 3 + tcp * 2 + gre;
+}
+
+static int mlx5_ct_fs_hmfs_init(struct mlx5_ct_fs *fs, struct mlx5_flow_table *ct,
+				struct mlx5_flow_table *ct_nat, struct mlx5_flow_table *post_ct)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5hws_table *ct_tbl, *ct_nat_tbl, *post_ct_tbl;
+	struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs);
+
+	ct_tbl = ct->fs_hws_table.hws_table;
+	ct_nat_tbl = ct_nat->fs_hws_table.hws_table;
+	post_ct_tbl = post_ct->fs_hws_table.hws_table;
+	fs_hmfs->ct_nat = ct_nat;
+
+	if (!ct_tbl || !ct_nat_tbl || !post_ct_tbl) {
+		netdev_warn(fs->netdev, "ct_fs_hmfs: failed to init, missing backing hws tables");
+		return -EOPNOTSUPP;
+	}
+
+	netdev_dbg(fs->netdev, "using hmfs steering");
+
+	fs_hmfs->ct_tbl = ct_tbl;
+	fs_hmfs->ct_nat_tbl = ct_nat_tbl;
+	fs_hmfs->ctx = ct_tbl->ctx;
+	mutex_init(&fs_hmfs->lock);
+
+	fs_hmfs->fwd_action = mlx5hws_action_create_dest_table(ct_tbl->ctx, post_ct_tbl, flags);
+	if (!fs_hmfs->fwd_action) {
+		netdev_warn(fs->netdev, "ct_fs_hmfs: failed to create fwd action\n");
+		return -EINVAL;
+	}
+	fs_hmfs->last_action = mlx5hws_action_create_last(ct_tbl->ctx, flags);
+	if (!fs_hmfs->last_action) {
+		netdev_warn(fs->netdev, "ct_fs_hmfs: failed to create last action\n");
+		mlx5hws_action_destroy(fs_hmfs->fwd_action);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void mlx5_ct_fs_hmfs_destroy(struct mlx5_ct_fs *fs)
+{
+	struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs);
+
+	mlx5hws_action_destroy(fs_hmfs->last_action);
+	mlx5hws_action_destroy(fs_hmfs->fwd_action);
+}
+
+static struct mlx5hws_bwc_matcher *
+mlx5_ct_fs_hmfs_matcher_create(struct mlx5_ct_fs *fs, struct mlx5hws_table *tbl,
+			       struct mlx5_flow_spec *spec, bool ipv4, bool tcp, bool gre)
+{
+	u8 match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2 | MLX5_MATCH_OUTER_HEADERS;
+	struct mlx5hws_match_parameters mask = {
+		.match_buf = spec->match_criteria,
+		.match_sz = sizeof(spec->match_criteria),
+	};
+	u32 priority = get_matcher_idx(ipv4, tcp, gre);  /* Static priority based on params. */
+	struct mlx5hws_bwc_matcher *hws_bwc_matcher;
+
+	hws_bwc_matcher = mlx5hws_bwc_matcher_create(tbl, priority, match_criteria_enable, &mask);
+	if (!hws_bwc_matcher)
+		return ERR_PTR(-EINVAL);
+
+	return hws_bwc_matcher;
+}
+
+static struct mlx5_ct_fs_hmfs_matcher *
+mlx5_ct_fs_hmfs_matcher_get(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec,
+			    bool nat, bool ipv4, bool tcp, bool gre)
+{
+	struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs);
+	u32 matcher_idx = get_matcher_idx(ipv4, tcp, gre);
+	struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher;
+	struct mlx5hws_bwc_matcher *hws_bwc_matcher;
+	struct mlx5hws_table *tbl;
+
+	hmfs_matcher = nat ?
+		(fs_hmfs->matchers_nat + matcher_idx) :
+		(fs_hmfs->matchers + matcher_idx);
+
+	if (refcount_inc_not_zero(&hmfs_matcher->ref))
+		return hmfs_matcher;
+
+	mutex_lock(&fs_hmfs->lock);
+
+	/* Retry with lock, as the matcher might be already created by another cpu. */
+	if (refcount_inc_not_zero(&hmfs_matcher->ref))
+		goto out_unlock;
+
+	tbl = nat ? fs_hmfs->ct_nat_tbl : fs_hmfs->ct_tbl;
+
+	hws_bwc_matcher = mlx5_ct_fs_hmfs_matcher_create(fs, tbl, spec, ipv4, tcp, gre);
+	if (IS_ERR(hws_bwc_matcher)) {
+		netdev_warn(fs->netdev,
+			    "ct_fs_hmfs: failed to create bwc matcher (nat %d, ipv4 %d, tcp %d, gre %d), err: %pe\n",
+			    nat, ipv4, tcp, gre, hws_bwc_matcher);
+
+		hmfs_matcher = ERR_CAST(hws_bwc_matcher);
+		goto out_unlock;
+	}
+
+	hmfs_matcher->hws_bwc_matcher = hws_bwc_matcher;
+	refcount_set(&hmfs_matcher->ref, 1);
+
+out_unlock:
+	mutex_unlock(&fs_hmfs->lock);
+	return hmfs_matcher;
+}
+
+static void
+mlx5_ct_fs_hmfs_matcher_put(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher)
+{
+	struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs);
+
+	if (!refcount_dec_and_mutex_lock(&hmfs_matcher->ref, &fs_hmfs->lock))
+		return;
+
+	mlx5hws_bwc_matcher_destroy(hmfs_matcher->hws_bwc_matcher);
+	mutex_unlock(&fs_hmfs->lock);
+}
+
+#define NUM_CT_HMFS_RULES 4
+
+static void mlx5_ct_fs_hmfs_fill_rule_actions(struct mlx5_ct_fs_hmfs *fs_hmfs,
+					      struct mlx5_flow_attr *attr,
+					      struct mlx5hws_rule_action *rule_actions)
+{
+	struct mlx5_fs_hws_action *mh_action = &attr->modify_hdr->fs_hws_action;
+
+	memset(rule_actions, 0, NUM_CT_HMFS_RULES * sizeof(*rule_actions));
+	rule_actions[0].action = mlx5_fc_get_hws_action(fs_hmfs->ctx, attr->counter);
+	rule_actions[0].counter.offset =
+		attr->counter->id - attr->counter->bulk->base_id;
+	/* Modify header is special, it may require extra arguments outside the action itself. */
+	if (mh_action->mh_data) {
+		rule_actions[1].modify_header.offset = mh_action->mh_data->offset;
+		rule_actions[1].modify_header.data = mh_action->mh_data->data;
+	}
+	rule_actions[1].action = mh_action->hws_action;
+	rule_actions[2].action = fs_hmfs->fwd_action;
+	rule_actions[3].action = fs_hmfs->last_action;
+}
+
+static struct mlx5_ct_fs_rule *
+mlx5_ct_fs_hmfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec,
+			    struct mlx5_flow_attr *attr, struct flow_rule *flow_rule)
+{
+	struct mlx5hws_rule_action rule_actions[NUM_CT_HMFS_RULES];
+	struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs);
+	struct mlx5hws_match_parameters match_params = {
+		.match_buf = spec->match_value,
+		.match_sz = ARRAY_SIZE(spec->match_value),
+	};
+	struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher;
+	struct mlx5_ct_fs_hmfs_rule *hmfs_rule;
+	bool nat, tcp, ipv4, gre;
+	int err;
+
+	if (!mlx5e_tc_ct_is_valid_flow_rule(fs->netdev, flow_rule))
+		return ERR_PTR(-EOPNOTSUPP);
+
+	hmfs_rule = kzalloc(sizeof(*hmfs_rule), GFP_KERNEL);
+	if (!hmfs_rule)
+		return ERR_PTR(-ENOMEM);
+
+	nat = (attr->ft == fs_hmfs->ct_nat);
+	ipv4 = mlx5e_tc_get_ip_version(spec, true) == 4;
+	tcp = MLX5_GET(fte_match_param, spec->match_value,
+		       outer_headers.ip_protocol) == IPPROTO_TCP;
+	gre = MLX5_GET(fte_match_param, spec->match_value,
+		       outer_headers.ip_protocol) == IPPROTO_GRE;
+
+	hmfs_matcher = mlx5_ct_fs_hmfs_matcher_get(fs, spec, nat, ipv4, tcp, gre);
+	if (IS_ERR(hmfs_matcher)) {
+		err = PTR_ERR(hmfs_matcher);
+		goto err_free_rule;
+	}
+	hmfs_rule->hmfs_matcher = hmfs_matcher;
+
+	mlx5_ct_fs_hmfs_fill_rule_actions(fs_hmfs, attr, rule_actions);
+	hmfs_rule->counter = attr->counter;
+
+	hmfs_rule->hws_bwc_rule =
+		mlx5hws_bwc_rule_create(hmfs_matcher->hws_bwc_matcher, &match_params,
+					spec->flow_context.flow_source, rule_actions);
+	if (!hmfs_rule->hws_bwc_rule) {
+		err = -EINVAL;
+		goto err_put_matcher;
+	}
+
+	return &hmfs_rule->fs_rule;
+
+err_put_matcher:
+	mlx5_fc_put_hws_action(hmfs_rule->counter);
+	mlx5_ct_fs_hmfs_matcher_put(fs, hmfs_matcher);
+err_free_rule:
+	kfree(hmfs_rule);
+	return ERR_PTR(err);
+}
+
+static void mlx5_ct_fs_hmfs_ct_rule_del(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule)
+{
+	struct mlx5_ct_fs_hmfs_rule *hmfs_rule = container_of(fs_rule,
+							      struct mlx5_ct_fs_hmfs_rule,
+							      fs_rule);
+	mlx5hws_bwc_rule_destroy(hmfs_rule->hws_bwc_rule);
+	mlx5_fc_put_hws_action(hmfs_rule->counter);
+	mlx5_ct_fs_hmfs_matcher_put(fs, hmfs_rule->hmfs_matcher);
+	kfree(hmfs_rule);
+}
+
+static int mlx5_ct_fs_hmfs_ct_rule_update(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule,
+					  struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr)
+{
+	struct mlx5_ct_fs_hmfs_rule *hmfs_rule = container_of(fs_rule,
+							      struct mlx5_ct_fs_hmfs_rule,
+							      fs_rule);
+	struct mlx5hws_rule_action rule_actions[NUM_CT_HMFS_RULES];
+	struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs);
+	int err;
+
+	mlx5_ct_fs_hmfs_fill_rule_actions(fs_hmfs, attr, rule_actions);
+
+	err = mlx5hws_bwc_rule_action_update(hmfs_rule->hws_bwc_rule, rule_actions);
+	if (err) {
+		mlx5_fc_put_hws_action(attr->counter);
+		return err;
+	}
+
+	mlx5_fc_put_hws_action(hmfs_rule->counter);
+	hmfs_rule->counter = attr->counter;
+
+	return 0;
+}
+
+static struct mlx5_ct_fs_ops hmfs_ops = {
+	.ct_rule_add = mlx5_ct_fs_hmfs_ct_rule_add,
+	.ct_rule_del = mlx5_ct_fs_hmfs_ct_rule_del,
+	.ct_rule_update = mlx5_ct_fs_hmfs_ct_rule_update,
+
+	.init = mlx5_ct_fs_hmfs_init,
+	.destroy = mlx5_ct_fs_hmfs_destroy,
+
+	.priv_size = sizeof(struct mlx5_ct_fs_hmfs),
+};
+
+struct mlx5_ct_fs_ops *mlx5_ct_fs_hmfs_ops_get(void)
+{
+	return &hmfs_ops;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c
index 45737d039252..4d6924b644c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c
@@ -13,7 +13,6 @@
 #define INIT_ERR_PREFIX "ct_fs_smfs init failed"
 #define ct_dbg(fmt, args...)\
 	netdev_dbg(fs->netdev, "ct_fs_smfs debug: " fmt "\n", ##args)
-#define MLX5_CT_TCP_FLAGS_MASK cpu_to_be16(be32_to_cpu(TCP_FLAG_RST | TCP_FLAG_FIN) >> 16)
 
 struct mlx5_ct_fs_smfs_matcher {
 	struct mlx5dr_matcher *dr_matcher;
@@ -149,8 +148,8 @@ mlx5_ct_fs_smfs_matcher_get(struct mlx5_ct_fs *fs, bool nat, bool ipv4, bool tcp
 	dr_matcher = mlx5_ct_fs_smfs_matcher_create(fs, tbl, ipv4, tcp, gre, prio);
 	if (IS_ERR(dr_matcher)) {
 		netdev_warn(fs->netdev,
-			    "ct_fs_smfs: failed to create matcher (nat %d, ipv4 %d, tcp %d, gre %d), err: %ld\n",
-			    nat, ipv4, tcp, gre, PTR_ERR(dr_matcher));
+			    "ct_fs_smfs: failed to create matcher (nat %d, ipv4 %d, tcp %d, gre %d), err: %pe\n",
+			    nat, ipv4, tcp, gre, dr_matcher);
 
 		smfs_matcher = ERR_CAST(dr_matcher);
 		goto out_unlock;
@@ -220,78 +219,6 @@ mlx5_ct_fs_smfs_destroy(struct mlx5_ct_fs *fs)
 	mlx5_smfs_action_destroy(fs_smfs->fwd_action);
 }
 
-static inline bool
-mlx5_tc_ct_valid_used_dissector_keys(const u64 used_keys)
-{
-#define DISS_BIT(name) BIT_ULL(FLOW_DISSECTOR_KEY_ ## name)
-	const u64 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) |
-				DISS_BIT(META);
-	const u64 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) |
-				DISS_BIT(PORTS) | DISS_BIT(TCP);
-	const u64 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) |
-				DISS_BIT(PORTS) | DISS_BIT(TCP);
-	const u64 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) |
-				DISS_BIT(PORTS);
-	const u64 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) |
-				 DISS_BIT(PORTS);
-	const u64 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS);
-	const u64 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS);
-
-	return (used_keys == ipv4_tcp || used_keys == ipv4_udp || used_keys == ipv6_tcp ||
-		used_keys == ipv6_udp || used_keys == ipv4_gre || used_keys == ipv6_gre);
-}
-
-static bool
-mlx5_ct_fs_smfs_ct_validate_flow_rule(struct mlx5_ct_fs *fs, struct flow_rule *flow_rule)
-{
-	struct flow_match_ipv4_addrs ipv4_addrs;
-	struct flow_match_ipv6_addrs ipv6_addrs;
-	struct flow_match_control control;
-	struct flow_match_basic basic;
-	struct flow_match_ports ports;
-	struct flow_match_tcp tcp;
-
-	if (!mlx5_tc_ct_valid_used_dissector_keys(flow_rule->match.dissector->used_keys)) {
-		ct_dbg("rule uses unexpected dissectors (0x%016llx)",
-		       flow_rule->match.dissector->used_keys);
-		return false;
-	}
-
-	flow_rule_match_basic(flow_rule, &basic);
-	flow_rule_match_control(flow_rule, &control);
-	flow_rule_match_ipv4_addrs(flow_rule, &ipv4_addrs);
-	flow_rule_match_ipv6_addrs(flow_rule, &ipv6_addrs);
-	if (basic.key->ip_proto != IPPROTO_GRE)
-		flow_rule_match_ports(flow_rule, &ports);
-	if (basic.key->ip_proto == IPPROTO_TCP)
-		flow_rule_match_tcp(flow_rule, &tcp);
-
-	if (basic.mask->n_proto != htons(0xFFFF) ||
-	    (basic.key->n_proto != htons(ETH_P_IP) && basic.key->n_proto != htons(ETH_P_IPV6)) ||
-	    basic.mask->ip_proto != 0xFF ||
-	    (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP &&
-	     basic.key->ip_proto != IPPROTO_GRE)) {
-		ct_dbg("rule uses unexpected basic match (n_proto 0x%04x/0x%04x, ip_proto 0x%02x/0x%02x)",
-		       ntohs(basic.key->n_proto), ntohs(basic.mask->n_proto),
-		       basic.key->ip_proto, basic.mask->ip_proto);
-		return false;
-	}
-
-	if (basic.key->ip_proto != IPPROTO_GRE &&
-	    (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF))) {
-		ct_dbg("rule uses ports match (src 0x%04x, dst 0x%04x)",
-		       ports.mask->src, ports.mask->dst);
-		return false;
-	}
-
-	if (basic.key->ip_proto == IPPROTO_TCP && tcp.mask->flags != MLX5_CT_TCP_FLAGS_MASK) {
-		ct_dbg("rule uses unexpected tcp match (flags 0x%02x)", tcp.mask->flags);
-		return false;
-	}
-
-	return true;
-}
-
 static struct mlx5_ct_fs_rule *
 mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec,
 			    struct mlx5_flow_attr *attr, struct flow_rule *flow_rule)
@@ -304,7 +231,7 @@ mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec,
 	int num_actions = 0, err;
 	bool nat, tcp, ipv4, gre;
 
-	if (!mlx5_ct_fs_smfs_ct_validate_flow_rule(fs, flow_rule))
+	if (!mlx5e_tc_ct_is_valid_flow_rule(fs->netdev, flow_rule))
 		return ERR_PTR(-EOPNOTSUPP);
 
 	smfs_rule = kzalloc(sizeof(*smfs_rule), GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c
index 8afcec0c5d3c..991f47050643 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c
@@ -93,8 +93,8 @@ mlx5e_int_port_create_rx_rule(struct mlx5_eswitch *esw,
 	flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec,
 					&flow_act, dest, 1);
 	if (IS_ERR(flow_rule))
-		mlx5_core_warn(esw->dev, "ft offloads: Failed to add internal vport rx rule err %ld\n",
-			       PTR_ERR(flow_rule));
+		mlx5_core_warn(esw->dev, "ft offloads: Failed to add internal vport rx rule err %pe\n",
+			       flow_rule);
 
 	kvfree(spec);
 
@@ -307,7 +307,8 @@ mlx5e_tc_int_port_init(struct mlx5e_priv *priv)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_tc_int_port_priv *int_port_priv;
-	u64 mapping_id;
+	u8 mapping_id[MLX5_SW_IMAGE_GUID_MAX_BYTES];
+	u8 id_len;
 
 	if (!mlx5e_tc_int_port_supported(esw))
 		return NULL;
@@ -316,14 +317,15 @@ mlx5e_tc_int_port_init(struct mlx5e_priv *priv)
 	if (!int_port_priv)
 		return NULL;
 
-	mapping_id = mlx5_query_nic_system_image_guid(priv->mdev);
+	mlx5_query_nic_sw_system_image_guid(priv->mdev, mapping_id, &id_len);
 
-	int_port_priv->metadata_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_INT_PORT,
+	int_port_priv->metadata_mapping = mapping_create_for_id(mapping_id, id_len,
+								MAPPING_TYPE_INT_PORT,
 								sizeof(u32) * 2,
 								(1 << ESW_VPORT_BITS) - 1, true);
 	if (IS_ERR(int_port_priv->metadata_mapping)) {
-		mlx5_core_warn(priv->mdev, "Can't allocate metadata mapping of int port offload, err=%ld\n",
-			       PTR_ERR(int_port_priv->metadata_mapping));
+		mlx5_core_warn(priv->mdev, "Can't allocate metadata mapping of int port offload, err=%pe\n",
+			       int_port_priv->metadata_mapping);
 		goto err_mapping;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c
index 8218c892b161..7819fb297280 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c
@@ -593,3 +593,8 @@ mlx5e_tc_meter_get_stats(struct mlx5e_flow_meter_handle *meter,
 	*drops = packets2;
 	*lastuse = max_t(u64, lastuse1, lastuse2);
 }
+
+int mlx5e_flow_meter_get_base_id(struct mlx5e_flow_meter_handle *meter)
+{
+	return meter->meters_obj->base_id;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h
index 9b795cd106bb..d6afb6556875 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h
@@ -72,4 +72,17 @@ void
 mlx5e_tc_meter_get_stats(struct mlx5e_flow_meter_handle *meter,
 			 u64 *bytes, u64 *packets, u64 *drops, u64 *lastuse);
 
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+
+int mlx5e_flow_meter_get_base_id(struct mlx5e_flow_meter_handle *meter);
+
+#else /* CONFIG_MLX5_CLS_ACT */
+
+static inline int
+mlx5e_flow_meter_get_base_id(struct mlx5e_flow_meter_handle *meter)
+{
+	return 0;
+}
+#endif /* CONFIG_MLX5_CLS_ACT */
+
 #endif /* __MLX5_EN_FLOW_METER_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index a84ebac2f011..fc0e57403d25 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -1195,6 +1195,7 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft,
 	struct flow_action_entry *meta_action;
 	unsigned long cookie = flow->cookie;
 	struct mlx5_ct_entry *entry;
+	bool has_nat;
 	int err;
 
 	meta_action = mlx5_tc_ct_get_ct_metadata_action(flow_rule);
@@ -1236,6 +1237,8 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft,
 	err = mlx5_tc_ct_rule_to_tuple_nat(&entry->tuple_nat, flow_rule);
 	if (err)
 		goto err_set;
+	has_nat = memcmp(&entry->tuple, &entry->tuple_nat,
+			 sizeof(entry->tuple));
 
 	spin_lock_bh(&ct_priv->ht_lock);
 
@@ -1244,7 +1247,7 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft,
 	if (err)
 		goto err_entries;
 
-	if (memcmp(&entry->tuple, &entry->tuple_nat, sizeof(entry->tuple))) {
+	if (has_nat) {
 		err = rhashtable_lookup_insert_fast(&ct_priv->ct_tuples_nat_ht,
 						    &entry->tuple_nat_node,
 						    tuples_nat_ht_params);
@@ -1349,6 +1352,32 @@ mlx5_tc_ct_block_flow_offload_stats(struct mlx5_ct_ft *ft,
 	return 0;
 }
 
+static bool
+mlx5_tc_ct_filter_legacy_non_nic_flows(struct mlx5_ct_ft *ft,
+				       struct flow_cls_offload *flow)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+	struct mlx5_tc_ct_priv *ct_priv = ft->ct_priv;
+	struct flow_match_meta match;
+	struct net_device *netdev;
+	bool same_dev = false;
+
+	if (!is_mdev_legacy_mode(ct_priv->dev) ||
+	    !flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META))
+		return true;
+
+	flow_rule_match_meta(rule, &match);
+
+	if (!(match.key->ingress_ifindex & match.mask->ingress_ifindex))
+		return true;
+
+	netdev = dev_get_by_index(&init_net, match.key->ingress_ifindex);
+	same_dev = ct_priv->netdev == netdev;
+	dev_put(netdev);
+
+	return same_dev;
+}
+
 static int
 mlx5_tc_ct_block_flow_offload(enum tc_setup_type type, void *type_data,
 			      void *cb_priv)
@@ -1361,6 +1390,9 @@ mlx5_tc_ct_block_flow_offload(enum tc_setup_type type, void *type_data,
 
 	switch (f->command) {
 	case FLOW_CLS_REPLACE:
+		if (!mlx5_tc_ct_filter_legacy_non_nic_flows(ft, f))
+			return -EOPNOTSUPP;
+
 		return mlx5_tc_ct_block_flow_offload_add(ft, f);
 	case FLOW_CLS_DESTROY:
 		return mlx5_tc_ct_block_flow_offload_del(ft, f);
@@ -2065,10 +2097,19 @@ mlx5_tc_ct_fs_init(struct mlx5_tc_ct_priv *ct_priv)
 	struct mlx5_ct_fs_ops *fs_ops = mlx5_ct_fs_dmfs_ops_get();
 	int err;
 
-	if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB &&
-	    ct_priv->dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) {
-		ct_dbg("Using SMFS ct flow steering provider");
-		fs_ops = mlx5_ct_fs_smfs_ops_get();
+	if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB) {
+		if (ct_priv->dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_HMFS) {
+			ct_dbg("Using HMFS ct flow steering provider");
+			fs_ops = mlx5_ct_fs_hmfs_ops_get();
+		} else if (ct_priv->dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) {
+			ct_dbg("Using SMFS ct flow steering provider");
+			fs_ops = mlx5_ct_fs_smfs_ops_get();
+		}
+
+		if (!fs_ops) {
+			ct_dbg("Requested flow steering mode is not enabled.");
+			return -EOPNOTSUPP;
+		}
 	}
 
 	ct_priv->fs = kzalloc(sizeof(*ct_priv->fs) + fs_ops->priv_size, GFP_KERNEL);
@@ -2246,9 +2287,10 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
 		enum mlx5_flow_namespace_type ns_type,
 		struct mlx5e_post_act *post_act)
 {
+	u8 mapping_id[MLX5_SW_IMAGE_GUID_MAX_BYTES];
 	struct mlx5_tc_ct_priv *ct_priv;
 	struct mlx5_core_dev *dev;
-	u64 mapping_id;
+	u8 id_len;
 	int err;
 
 	dev = priv->mdev;
@@ -2260,16 +2302,18 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
 	if (!ct_priv)
 		goto err_alloc;
 
-	mapping_id = mlx5_query_nic_system_image_guid(dev);
+	mlx5_query_nic_sw_system_image_guid(dev, mapping_id, &id_len);
 
-	ct_priv->zone_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_ZONE,
+	ct_priv->zone_mapping = mapping_create_for_id(mapping_id, id_len,
+						      MAPPING_TYPE_ZONE,
 						      sizeof(u16), 0, true);
 	if (IS_ERR(ct_priv->zone_mapping)) {
 		err = PTR_ERR(ct_priv->zone_mapping);
 		goto err_mapping_zone;
 	}
 
-	ct_priv->labels_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_LABELS,
+	ct_priv->labels_mapping = mapping_create_for_id(mapping_id, id_len,
+							MAPPING_TYPE_LABELS,
 							sizeof(u32) * 4, 0, true);
 	if (IS_ERR(ct_priv->labels_mapping)) {
 		err = PTR_ERR(ct_priv->labels_mapping);
@@ -2421,3 +2465,74 @@ out_inc_drop:
 	atomic_inc(&ct_priv->debugfs.stats.rx_dropped);
 	return false;
 }
+
+static bool mlx5e_tc_ct_valid_used_dissector_keys(const u64 used_keys)
+{
+#define DISS_BIT(name) BIT_ULL(FLOW_DISSECTOR_KEY_ ## name)
+	const u64 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) |
+				DISS_BIT(META);
+	const u64 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) |
+				DISS_BIT(PORTS) | DISS_BIT(TCP);
+	const u64 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) |
+				DISS_BIT(PORTS) | DISS_BIT(TCP);
+	const u64 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) |
+				DISS_BIT(PORTS);
+	const u64 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) |
+				 DISS_BIT(PORTS);
+	const u64 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS);
+	const u64 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS);
+
+	return (used_keys == ipv4_tcp || used_keys == ipv4_udp || used_keys == ipv6_tcp ||
+		used_keys == ipv6_udp || used_keys == ipv4_gre || used_keys == ipv6_gre);
+}
+
+bool mlx5e_tc_ct_is_valid_flow_rule(const struct net_device *dev, struct flow_rule *flow_rule)
+{
+	struct flow_match_ipv4_addrs ipv4_addrs;
+	struct flow_match_ipv6_addrs ipv6_addrs;
+	struct flow_match_control control;
+	struct flow_match_basic basic;
+	struct flow_match_ports ports;
+	struct flow_match_tcp tcp;
+
+	if (!mlx5e_tc_ct_valid_used_dissector_keys(flow_rule->match.dissector->used_keys)) {
+		netdev_dbg(dev, "ct_debug: rule uses unexpected dissectors (0x%016llx)",
+			   flow_rule->match.dissector->used_keys);
+		return false;
+	}
+
+	flow_rule_match_basic(flow_rule, &basic);
+	flow_rule_match_control(flow_rule, &control);
+	flow_rule_match_ipv4_addrs(flow_rule, &ipv4_addrs);
+	flow_rule_match_ipv6_addrs(flow_rule, &ipv6_addrs);
+	if (basic.key->ip_proto != IPPROTO_GRE)
+		flow_rule_match_ports(flow_rule, &ports);
+	if (basic.key->ip_proto == IPPROTO_TCP)
+		flow_rule_match_tcp(flow_rule, &tcp);
+
+	if (basic.mask->n_proto != htons(0xFFFF) ||
+	    (basic.key->n_proto != htons(ETH_P_IP) && basic.key->n_proto != htons(ETH_P_IPV6)) ||
+	    basic.mask->ip_proto != 0xFF ||
+	    (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP &&
+	     basic.key->ip_proto != IPPROTO_GRE)) {
+		netdev_dbg(dev, "ct_debug: rule uses unexpected basic match (n_proto 0x%04x/0x%04x, ip_proto 0x%02x/0x%02x)",
+			   ntohs(basic.key->n_proto), ntohs(basic.mask->n_proto),
+			   basic.key->ip_proto, basic.mask->ip_proto);
+		return false;
+	}
+
+	if (basic.key->ip_proto != IPPROTO_GRE &&
+	    (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF))) {
+		netdev_dbg(dev, "ct_debug: rule uses ports match (src 0x%04x, dst 0x%04x)",
+			   ports.mask->src, ports.mask->dst);
+		return false;
+	}
+
+	if (basic.key->ip_proto == IPPROTO_TCP && tcp.mask->flags != MLX5_CT_TCP_FLAGS_MASK) {
+		netdev_dbg(dev, "ct_debug: rule uses unexpected tcp match (flags 0x%02x)",
+			   tcp.mask->flags);
+		return false;
+	}
+
+	return true;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
index b66c5f98067f..5e9dbdd4a5e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
@@ -128,6 +128,9 @@ bool
 mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv,
 			 struct sk_buff *skb, u8 zone_restore_id);
 
+#define MLX5_CT_TCP_FLAGS_MASK cpu_to_be16(be32_to_cpu(TCP_FLAG_RST | TCP_FLAG_FIN) >> 16)
+bool mlx5e_tc_ct_is_valid_flow_rule(const struct net_device *dev, struct flow_rule *flow_rule);
+
 #else /* CONFIG_MLX5_TC_CT */
 
 static inline struct mlx5_tc_ct_priv *
@@ -202,5 +205,12 @@ mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv,
 	return false;
 }
 
+static inline bool
+mlx5e_tc_ct_is_valid_flow_rule(const struct net_device *dev,
+			       struct flow_rule *flow_rule)
+{
+	return false;
+}
+
 #endif /* !IS_ENABLED(CONFIG_MLX5_TC_CT) */
 #endif /* __MLX5_EN_TC_CT_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 721f35e59757..a14f216048cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -1,7 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
 /* Copyright (c) 2018 Mellanox Technologies. */
 
-#include <net/inet_ecn.h>
+#include <net/flow.h>
+#include <net/inet_dscp.h>
 #include <net/vxlan.h>
 #include <net/gre.h>
 #include <net/geneve.h>
@@ -31,8 +32,7 @@ static void mlx5e_tc_tun_route_attr_cleanup(struct mlx5e_tc_tun_route_attr *attr
 {
 	if (attr->n)
 		neigh_release(attr->n);
-	if (attr->route_dev)
-		dev_put(attr->route_dev);
+	dev_put(attr->route_dev);
 }
 
 struct mlx5e_tc_tunnel *mlx5e_get_tc_tun(struct net_device *tunnel_dev)
@@ -68,16 +68,14 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv,
 	 * while holding rcu read lock. Take the net_device for correctness
 	 * sake.
 	 */
-	if (uplink_upper)
-		dev_hold(uplink_upper);
+	dev_hold(uplink_upper);
 	rcu_read_unlock();
 
 	dst_is_lag_dev = (uplink_upper &&
 			  netif_is_lag_master(uplink_upper) &&
 			  real_dev == uplink_upper &&
 			  mlx5_lag_is_sriov(priv->mdev));
-	if (uplink_upper)
-		dev_put(uplink_upper);
+	dev_put(uplink_upper);
 
 	/* if the egress device isn't on the same HW e-switch or
 	 * it's a LAG device, use the uplink
@@ -236,7 +234,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	int err;
 
 	/* add the IP fields */
-	attr.fl.fl4.flowi4_tos = tun_key->tos & ~INET_ECN_MASK;
+	attr.fl.fl4.flowi4_dscp = inet_dsfield_to_dscp(tun_key->tos);
 	attr.fl.fl4.daddr = tun_key->u.ipv4.dst;
 	attr.fl.fl4.saddr = tun_key->u.ipv4.src;
 	attr.ttl = tun_key->ttl;
@@ -352,7 +350,7 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv,
 	int err;
 
 	/* add the IP fields */
-	attr.fl.fl4.flowi4_tos = tun_key->tos & ~INET_ECN_MASK;
+	attr.fl.fl4.flowi4_dscp = inet_dsfield_to_dscp(tun_key->tos);
 	attr.fl.fl4.daddr = tun_key->u.ipv4.dst;
 	attr.fl.fl4.saddr = tun_key->u.ipv4.src;
 	attr.ttl = tun_key->ttl;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index e7e01f3298ef..0735d10f2bac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -42,8 +42,7 @@ static int mlx5e_set_int_port_tunnel(struct mlx5e_priv *priv,
 						&attr->action, out_index);
 
 out:
-	if (route_dev)
-		dev_put(route_dev);
+	dev_put(route_dev);
 
 	return err;
 }
@@ -173,8 +172,8 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 						     &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
-		mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %lu\n",
-			       PTR_ERR(e->pkt_reformat));
+		mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %pe\n",
+			       e->pkt_reformat);
 		return;
 	}
 	e->flags |= MLX5_ENCAP_ENTRY_VALID;
@@ -753,8 +752,7 @@ static int mlx5e_set_vf_tunnel(struct mlx5_eswitch *esw,
 	}
 
 out:
-	if (route_dev)
-		dev_put(route_dev);
+	dev_put(route_dev);
 	return err;
 }
 
@@ -788,8 +786,7 @@ static int mlx5e_update_vf_tunnel(struct mlx5_eswitch *esw,
 	mlx5e_tc_match_to_reg_mod_hdr_change(esw->dev, mod_hdr_acts, VPORT_TO_REG, act_id, data);
 
 out:
-	if (route_dev)
-		dev_put(route_dev);
+	dev_put(route_dev);
 	return err;
 }
 
@@ -1848,8 +1845,8 @@ static int mlx5e_tc_tun_fib_event(struct notifier_block *nb, unsigned long event
 			queue_work(priv->wq, &fib_work->work);
 		} else if (IS_ERR(fib_work)) {
 			NL_SET_ERR_MSG_MOD(info->extack, "Failed to init fib work");
-			mlx5_core_warn(priv->mdev, "Failed to init fib work, %ld\n",
-				       PTR_ERR(fib_work));
+			mlx5_core_warn(priv->mdev, "Failed to init fib work, %pe\n",
+				       fib_work);
 		}
 
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
index e4e487c8431b..7a18a469961d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
@@ -140,7 +140,7 @@ static int mlx5e_tc_tun_parse_vxlan_gbp_option(struct mlx5e_priv *priv,
 	gbp_mask = (u32 *)&enc_opts.mask->data[0];
 
 	if (*gbp_mask & ~VXLAN_GBP_MASK) {
-		NL_SET_ERR_MSG_FMT_MOD(extack, "Wrong VxLAN GBP mask(0x%08X)\n", *gbp_mask);
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Wrong VxLAN GBP mask(0x%08X)", *gbp_mask);
 		return -EINVAL;
 	}
 
@@ -165,9 +165,6 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 	struct flow_match_enc_keyid enc_keyid;
 	void *misc_c, *misc_v;
 
-	misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
-	misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
-
 	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID))
 		return 0;
 
@@ -182,6 +179,30 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 		err = mlx5e_tc_tun_parse_vxlan_gbp_option(priv, spec, f);
 		if (err)
 			return err;
+
+		/* We can't mix custom tunnel headers with symbolic ones and we
+		 * don't have a symbolic field name for GBP, so we use custom
+		 * tunnel headers in this case. We need hardware support to
+		 * match on custom tunnel headers, but we already know it's
+		 * supported because the previous call successfully checked for
+		 * that.
+		 */
+		misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				      misc_parameters_5);
+		misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				      misc_parameters_5);
+
+		/* Shift by 8 to account for the reserved bits in the vxlan
+		 * header after the VNI.
+		 */
+		MLX5_SET(fte_match_set_misc5, misc_c, tunnel_header_1,
+			 be32_to_cpu(enc_keyid.mask->keyid) << 8);
+		MLX5_SET(fte_match_set_misc5, misc_v, tunnel_header_1,
+			 be32_to_cpu(enc_keyid.key->keyid) << 8);
+
+		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_5;
+
+		return 0;
 	}
 
 	/* match on VNI is required */
@@ -195,6 +216,11 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
+	misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			      misc_parameters);
+	misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			      misc_parameters);
+
 	MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
 		 be32_to_cpu(enc_keyid.mask->keyid));
 	MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
index 11f724ad90db..0b55e77f19c8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
@@ -124,7 +124,7 @@ void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder,
 		const size_t len = MLX5_FLD_SZ_BYTES(tirc, rx_hash_toeplitz_key);
 		void *rss_key = MLX5_ADDR_OF(tirc, tirc, rx_hash_toeplitz_key);
 
-		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
+		MLX5_SET(tirc, tirc, rx_hash_symmetric, rss_hash->symmetric);
 		memcpy(rss_key, rss_hash->toeplitz_hash_key, len);
 	}
 
@@ -146,6 +146,31 @@ void mlx5e_tir_builder_build_direct(struct mlx5e_tir_builder *builder)
 	MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8);
 }
 
+static void mlx5e_tir_context_self_lb_block(void *tirc, bool enable_uc_lb,
+					    bool enable_mc_lb)
+{
+	u8 lb_flags = 0;
+
+	if (enable_uc_lb)
+		lb_flags = MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
+	if (enable_mc_lb)
+		lb_flags |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST;
+
+	MLX5_SET(tirc, tirc, self_lb_block, lb_flags);
+}
+
+void mlx5e_tir_builder_build_self_lb_block(struct mlx5e_tir_builder *builder,
+					   bool enable_uc_lb,
+					   bool enable_mc_lb)
+{
+	void *tirc = mlx5e_tir_builder_get_tirc(builder);
+
+	if (builder->modify)
+		MLX5_SET(modify_tir_in, builder->in, bitmask.self_lb_en, 1);
+
+	mlx5e_tir_context_self_lb_block(tirc, enable_uc_lb, enable_mc_lb);
+}
+
 void mlx5e_tir_builder_build_tls(struct mlx5e_tir_builder *builder)
 {
 	void *tirc = mlx5e_tir_builder_get_tirc(builder);
@@ -153,9 +178,7 @@ void mlx5e_tir_builder_build_tls(struct mlx5e_tir_builder *builder)
 	WARN_ON(builder->modify);
 
 	MLX5_SET(tirc, tirc, tls_en, 1);
-	MLX5_SET(tirc, tirc, self_lb_block,
-		 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST |
-		 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST);
+	mlx5e_tir_context_self_lb_block(tirc, true, true);
 }
 
 int mlx5e_tir_init(struct mlx5e_tir *tir, struct mlx5e_tir_builder *builder,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
index 857a84bcd53a..958eeb959a19 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
@@ -9,6 +9,7 @@
 struct mlx5e_rss_params_hash {
 	u8 hfunc;
 	u8 toeplitz_hash_key[40];
+	bool symmetric;
 };
 
 struct mlx5e_rss_params_traffic_type {
@@ -34,6 +35,9 @@ void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder,
 				 const struct mlx5e_rss_params_traffic_type *rss_tt,
 				 bool inner);
 void mlx5e_tir_builder_build_direct(struct mlx5e_tir_builder *builder);
+void mlx5e_tir_builder_build_self_lb_block(struct mlx5e_tir_builder *builder,
+					   bool enable_uc_lb,
+					   bool enable_mc_lb);
 void mlx5e_tir_builder_build_tls(struct mlx5e_tir_builder *builder);
 
 struct mlx5_core_dev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
index 53ca16cb9c41..da8c44f46edb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
@@ -46,8 +46,8 @@ static void mlx5e_init_trap_rq(struct mlx5e_trap *t, struct mlx5e_params *params
 	rq->pdev         = t->pdev;
 	rq->netdev       = priv->netdev;
 	rq->priv         = priv;
-	rq->clock        = &mdev->clock;
-	rq->tstamp       = &priv->tstamp;
+	rq->clock        = mdev->clock;
+	rq->hwtstamp_config = &priv->hwtstamp_config;
 	rq->mdev         = mdev;
 	rq->hw_mtu       = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->stats        = &priv->trap_stats.rq;
@@ -76,6 +76,7 @@ static int mlx5e_open_trap_rq(struct mlx5e_priv *priv, struct mlx5e_trap *t)
 	ccp.ch_stats = t->stats;
 	ccp.napi     = &t->napi;
 	ccp.ix       = 0;
+	ccp.uar      = mdev->priv.bfreg.up;
 	err = mlx5e_open_cq(priv->mdev, trap_moder, &rq_param->cqp, &ccp, &rq->cq);
 	if (err)
 		return err;
@@ -143,13 +144,12 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv)
 
 	t->priv     = priv;
 	t->mdev     = priv->mdev;
-	t->tstamp   = &priv->tstamp;
 	t->pdev     = mlx5_core_dma_dev(priv->mdev);
 	t->netdev   = priv->netdev;
 	t->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey);
 	t->stats    = &priv->trap_stats.ch;
 
-	netif_napi_add(netdev, &t->napi, mlx5e_trap_napi_poll);
+	netif_napi_add_locked(netdev, &t->napi, mlx5e_trap_napi_poll);
 
 	err = mlx5e_open_trap_rq(priv, t);
 	if (unlikely(err))
@@ -164,7 +164,7 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv)
 err_close_trap_rq:
 	mlx5e_close_trap_rq(&t->rq);
 err_napi_del:
-	netif_napi_del(&t->napi);
+	netif_napi_del_locked(&t->napi);
 	kvfree(t);
 	return ERR_PTR(err);
 }
@@ -173,13 +173,13 @@ void mlx5e_close_trap(struct mlx5e_trap *trap)
 {
 	mlx5e_tir_destroy(&trap->tir);
 	mlx5e_close_trap_rq(&trap->rq);
-	netif_napi_del(&trap->napi);
+	netif_napi_del_locked(&trap->napi);
 	kvfree(trap);
 }
 
 static void mlx5e_activate_trap(struct mlx5e_trap *trap)
 {
-	napi_enable(&trap->napi);
+	napi_enable_locked(&trap->napi);
 	mlx5e_activate_rq(&trap->rq);
 	mlx5e_trigger_napi_sched(&trap->napi);
 }
@@ -189,7 +189,7 @@ void mlx5e_deactivate_trap(struct mlx5e_priv *priv)
 	struct mlx5e_trap *trap = priv->en_trap;
 
 	mlx5e_deactivate_rq(&trap->rq);
-	napi_disable(&trap->napi);
+	napi_disable_locked(&trap->napi);
 }
 
 static struct mlx5e_trap *mlx5e_add_trap_queue(struct mlx5e_priv *priv)
@@ -285,6 +285,7 @@ int mlx5e_handle_trap_event(struct mlx5e_priv *priv, struct mlx5_trap_ctx *trap_
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
 		return 0;
 
+	netdev_lock(priv->netdev);
 	switch (trap_ctx->action) {
 	case DEVLINK_TRAP_ACTION_TRAP:
 		err = mlx5e_handle_action_trap(priv, trap_ctx->id);
@@ -297,6 +298,7 @@ int mlx5e_handle_trap_event(struct mlx5e_priv *priv, struct mlx5_trap_ctx *trap_
 			    trap_ctx->action);
 		err = -EINVAL;
 	}
+	netdev_unlock(priv->netdev);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.h b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.h
index aa3f17658c6d..394e917ea2b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.h
@@ -22,7 +22,6 @@ struct mlx5e_trap {
 	/* control */
 	struct mlx5e_priv         *priv;
 	struct mlx5_core_dev      *mdev;
-	struct hwtstamp_config    *tstamp;
 	DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES);
 
 	struct mlx5e_params        params;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 5ec468268d1a..7e191e1569e8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -92,7 +92,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
 void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
 void mlx5e_free_rx_missing_descs(struct mlx5e_rq *rq);
 
-static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
+static inline bool mlx5e_rx_hw_stamp(struct kernel_hwtstamp_config *config)
 {
 	return config->rx_filter == HWTSTAMP_FILTER_ALL;
 }
@@ -214,6 +214,19 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size)
 	return pi;
 }
 
+static inline u16 mlx5e_txqsq_get_next_pi_anysize(struct mlx5e_txqsq *sq,
+						  u16 *size)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u16 pi, contig_wqebbs;
+
+	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+	*size = min_t(u16, contig_wqebbs, sq->max_sq_mpw_wqebbs);
+
+	return pi;
+}
+
 void mlx5e_txqsq_wake(struct mlx5e_txqsq *sq);
 
 static inline u16 mlx5e_shampo_get_cqe_header_index(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
@@ -296,10 +309,7 @@ mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map,
 
 static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
 {
-	struct mlx5_core_cq *mcq;
-
-	mcq = &cq->mcq;
-	mlx5_cq_arm(mcq, MLX5_CQ_DB_REQ_NOT, mcq->uar->map, cq->wq.cc);
+	mlx5_cq_arm(&cq->mcq, MLX5_CQ_DB_REQ_NOT, cq->uar->map, cq->wq.cc);
 }
 
 static inline struct mlx5e_sq_dma *
@@ -309,14 +319,24 @@ mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i)
 }
 
 static inline void
-mlx5e_dma_push(struct mlx5e_txqsq *sq, dma_addr_t addr, u32 size,
-	       enum mlx5e_dma_map_type map_type)
+mlx5e_dma_push_single(struct mlx5e_txqsq *sq, dma_addr_t addr, u32 size)
 {
 	struct mlx5e_sq_dma *dma = mlx5e_dma_get(sq, sq->dma_fifo_pc++);
 
 	dma->addr = addr;
 	dma->size = size;
-	dma->type = map_type;
+	dma->type = MLX5E_DMA_MAP_SINGLE;
+}
+
+static inline void
+mlx5e_dma_push_netmem(struct mlx5e_txqsq *sq, netmem_ref netmem,
+		      dma_addr_t addr, u32 size)
+{
+	struct mlx5e_sq_dma *dma = mlx5e_dma_get(sq, sq->dma_fifo_pc++);
+
+	netmem_dma_unmap_addr_set(netmem, dma, addr, addr);
+	dma->size = size;
+	dma->type = MLX5E_DMA_MAP_PAGE;
 }
 
 static inline
@@ -349,7 +369,8 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma)
 		dma_unmap_single(pdev, dma->addr, dma->size, DMA_TO_DEVICE);
 		break;
 	case MLX5E_DMA_MAP_PAGE:
-		dma_unmap_page(pdev, dma->addr, dma->size, DMA_TO_DEVICE);
+		netmem_dma_unmap_page_attrs(pdev, dma->addr, dma->size,
+					    DMA_TO_DEVICE, 0);
 		break;
 	default:
 		WARN_ONCE(true, "mlx5e_tx_dma_unmap unknown DMA type!\n");
@@ -358,9 +379,9 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma)
 
 void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq);
 
-static inline bool mlx5e_tx_mpwqe_is_full(struct mlx5e_tx_mpwqe *session, u8 max_sq_mpw_wqebbs)
+static inline bool mlx5e_tx_mpwqe_is_full(struct mlx5e_tx_mpwqe *session)
 {
-	return session->ds_count == max_sq_mpw_wqebbs * MLX5_SEND_WQEBB_NUM_DS;
+	return session->ds_count == session->ds_count_max;
 }
 
 static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 94b291662087..80f9fc10877a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -179,7 +179,7 @@ static int mlx5e_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
 {
 	const struct mlx5e_xdp_buff *_ctx = (void *)ctx;
 
-	if (unlikely(!mlx5e_rx_hw_stamp(_ctx->rq->tstamp)))
+	if (unlikely(!mlx5e_rx_hw_stamp(_ctx->rq->hwtstamp_config)))
 		return -ENODATA;
 
 	*timestamp =  mlx5e_cqe_ts_to_ns(_ctx->rq->ptp_cyc2time,
@@ -289,9 +289,9 @@ static u64 mlx5e_xsk_fill_timestamp(void *_priv)
 	ts = get_cqe_ts(priv->cqe);
 
 	if (mlx5_is_real_time_rq(priv->cq->mdev) || mlx5_is_real_time_sq(priv->cq->mdev))
-		return mlx5_real_time_cyc2time(&priv->cq->mdev->clock, ts);
+		return mlx5_real_time_cyc2time(priv->cq->mdev->clock, ts);
 
-	return  mlx5_timecounter_cyc2time(&priv->cq->mdev->clock, ts);
+	return  mlx5_timecounter_cyc2time(priv->cq->mdev->clock, ts);
 }
 
 static void mlx5e_xsk_request_checksum(u16 csum_start, u16 csum_offset, void *priv)
@@ -390,6 +390,7 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 		.wqe = wqe,
 		.bytes_count = 0,
 		.ds_count = MLX5E_TX_WQE_EMPTY_DS_COUNT,
+		.ds_count_max = sq->max_sq_mpw_wqebbs * MLX5_SEND_WQEBB_NUM_DS,
 		.pkt_count = 0,
 		.inline_on = mlx5e_xdp_get_inline_state(sq, session->inline_on),
 	};
@@ -501,7 +502,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx
 
 	mlx5e_xdp_mpwqe_add_dseg(sq, p, stats);
 
-	if (unlikely(mlx5e_xdp_mpwqe_is_full(session, sq->max_sq_mpw_wqebbs)))
+	if (unlikely(mlx5e_xdp_mpwqe_is_full(session)))
 		mlx5e_xdp_mpwqe_complete(sq);
 
 	stats->xmit++;
@@ -546,6 +547,7 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 	bool inline_ok;
 	bool linear;
 	u16 pi;
+	int i;
 
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
 
@@ -612,41 +614,33 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
 
-	if (test_bit(MLX5E_SQ_STATE_XDP_MULTIBUF, &sq->state)) {
-		int i;
-
-		memset(&cseg->trailer, 0, sizeof(cseg->trailer));
-		memset(eseg, 0, sizeof(*eseg) - sizeof(eseg->trailer));
-
-		eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
+	memset(&cseg->trailer, 0, sizeof(cseg->trailer));
+	memset(eseg, 0, sizeof(*eseg) - sizeof(eseg->trailer));
 
-		for (i = 0; i < num_frags; i++) {
-			skb_frag_t *frag = &xdptxdf->sinfo->frags[i];
-			dma_addr_t addr;
+	eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
 
-			addr = xdptxdf->dma_arr ? xdptxdf->dma_arr[i] :
-				page_pool_get_dma_addr(skb_frag_page(frag)) +
-				skb_frag_off(frag);
+	for (i = 0; i < num_frags; i++) {
+		skb_frag_t *frag = &xdptxdf->sinfo->frags[i];
+		dma_addr_t addr;
 
-			dseg->addr = cpu_to_be64(addr);
-			dseg->byte_count = cpu_to_be32(skb_frag_size(frag));
-			dseg->lkey = sq->mkey_be;
-			dseg++;
-		}
+		addr = xdptxdf->dma_arr ? xdptxdf->dma_arr[i] :
+			page_pool_get_dma_addr(skb_frag_page(frag)) +
+			skb_frag_off(frag);
 
-		cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+		dseg->addr = cpu_to_be64(addr);
+		dseg->byte_count = cpu_to_be32(skb_frag_size(frag));
+		dseg->lkey = sq->mkey_be;
+		dseg++;
+	}
 
-		sq->db.wqe_info[pi] = (struct mlx5e_xdp_wqe_info) {
-			.num_wqebbs = num_wqebbs,
-			.num_pkts = 1,
-		};
+	cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
 
-		sq->pc += num_wqebbs;
-	} else {
-		cseg->fm_ce_se = 0;
+	sq->db.wqe_info[pi] = (struct mlx5e_xdp_wqe_info) {
+		.num_wqebbs = num_wqebbs,
+		.num_pkts = 1,
+	};
 
-		sq->pc++;
-	}
+	sq->pc += num_wqebbs;
 
 	xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, eseg);
 
@@ -713,10 +707,11 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 				xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
 				page = xdpi.page.page;
 
-				/* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
-				 * as we know this is a page_pool page.
+				/* No need to check page_pool_page_is_pp() as we
+				 * know this is a page_pool page.
 				 */
-				page_pool_recycle_direct(page->pp, page);
+				page_pool_recycle_direct(pp_page_to_nmdesc(page)->pp,
+							 page);
 			} while (++n < num);
 
 			break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index e054db1e10f8..46ab0a9e8cdd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -45,12 +45,6 @@
 	(MLX5E_XDP_INLINE_WQE_MAX_DS_CNT * MLX5_SEND_WQE_DS - \
 	 sizeof(struct mlx5_wqe_inline_seg))
 
-struct mlx5e_xdp_buff {
-	struct xdp_buff xdp;
-	struct mlx5_cqe64 *cqe;
-	struct mlx5e_rq *rq;
-};
-
 /* XDP packets can be transmitted in different ways. On completion, we need to
  * distinguish between them to clean up things in a proper way.
  */
@@ -182,13 +176,13 @@ static inline bool mlx5e_xdp_get_inline_state(struct mlx5e_xdpsq *sq, bool cur)
 	return cur;
 }
 
-static inline bool mlx5e_xdp_mpwqe_is_full(struct mlx5e_tx_mpwqe *session, u8 max_sq_mpw_wqebbs)
+static inline bool mlx5e_xdp_mpwqe_is_full(struct mlx5e_tx_mpwqe *session)
 {
 	if (session->inline_on)
 		return session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT >
-		       max_sq_mpw_wqebbs * MLX5_SEND_WQEBB_NUM_DS;
+		       session->ds_count_max;
 
-	return mlx5e_tx_mpwqe_is_full(session, max_sq_mpw_wqebbs);
+	return mlx5e_tx_mpwqe_is_full(session);
 }
 
 struct mlx5e_xdp_wqe_info {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
index 1b7132fa70de..2b05536d564a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
@@ -123,7 +123,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	bitmap_zero(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
 	wi->consumed_strides = 0;
 
-	umr_wqe->ctrl.opmod_idx_opcode =
+	umr_wqe->hdr.ctrl.opmod_idx_opcode =
 		cpu_to_be32((icosq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) | MLX5_OPCODE_UMR);
 
 	/* Optimized for speed: keep in sync with mlx5e_mpwrq_umr_entry_size. */
@@ -134,7 +134,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 		offset = offset * sizeof(struct mlx5_klm) * 2 / MLX5_OCTWORD;
 	else if (unlikely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_TRIPLE))
 		offset = offset * sizeof(struct mlx5_ksm) * 4 / MLX5_OCTWORD;
-	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
+	umr_wqe->hdr.uctrl.xlt_offset = cpu_to_be16(offset);
 
 	icosq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
 		.wqe_type = MLX5E_ICOSQ_WQE_UMR_RX,
@@ -144,7 +144,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 
 	icosq->pc += rq->mpwqe.umr_wqebbs;
 
-	icosq->doorbell_cseg = &umr_wqe->ctrl;
+	icosq->doorbell_cseg = &umr_wqe->hdr.ctrl;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 9240cfe25d10..5981c71cae2d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -54,7 +54,7 @@ static void mlx5e_build_xsk_cparam(struct mlx5_core_dev *mdev,
 				   struct mlx5e_channel_param *cparam)
 {
 	mlx5e_build_rq_param(mdev, params, xsk, &cparam->rq);
-	mlx5e_build_xdpsq_param(mdev, params, xsk, &cparam->xdp_sq);
+	mlx5e_build_xdpsq_param(mdev, params, &cparam->xdp_sq);
 }
 
 static int mlx5e_init_xsk_rq(struct mlx5e_channel *c,
@@ -71,8 +71,8 @@ static int mlx5e_init_xsk_rq(struct mlx5e_channel *c,
 	rq->pdev         = c->pdev;
 	rq->netdev       = c->netdev;
 	rq->priv         = c->priv;
-	rq->tstamp       = c->tstamp;
-	rq->clock        = &mdev->clock;
+	rq->hwtstamp_config = &c->priv->hwtstamp_config;
+	rq->clock        = mdev->clock;
 	rq->icosq        = &c->icosq;
 	rq->ix           = c->ix;
 	rq->channel      = c;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index 33e32584b07f..8bef99e8367e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -42,6 +42,8 @@
 #include <en_accel/macsec.h>
 #include "en.h"
 #include "en/txrx.h"
+#include "en_accel/psp.h"
+#include "en_accel/psp_rxtx.h"
 
 #if IS_ENABLED(CONFIG_GENEVE)
 #include <net/geneve.h>
@@ -119,6 +121,9 @@ struct mlx5e_accel_tx_state {
 #ifdef CONFIG_MLX5_EN_IPSEC
 	struct mlx5e_accel_tx_ipsec_state ipsec;
 #endif
+#ifdef CONFIG_MLX5_EN_PSP
+	struct mlx5e_accel_tx_psp_state psp_st;
+#endif
 };
 
 static inline bool mlx5e_accel_tx_begin(struct net_device *dev,
@@ -137,6 +142,13 @@ static inline bool mlx5e_accel_tx_begin(struct net_device *dev,
 			return false;
 #endif
 
+#ifdef CONFIG_MLX5_EN_PSP
+	if (mlx5e_psp_is_offload(skb, dev)) {
+		if (unlikely(!mlx5e_psp_handle_tx_skb(dev, skb, &state->psp_st)))
+			return false;
+	}
+#endif
+
 #ifdef CONFIG_MLX5_EN_IPSEC
 	if (test_bit(MLX5E_SQ_STATE_IPSEC, &sq->state) && xfrm_offload(skb)) {
 		if (unlikely(!mlx5e_ipsec_handle_tx_skb(dev, skb, &state->ipsec)))
@@ -157,8 +169,14 @@ static inline bool mlx5e_accel_tx_begin(struct net_device *dev,
 }
 
 static inline unsigned int mlx5e_accel_tx_ids_len(struct mlx5e_txqsq *sq,
+						  struct sk_buff *skb,
 						  struct mlx5e_accel_tx_state *state)
 {
+#ifdef CONFIG_MLX5_EN_PSP
+	if (mlx5e_psp_is_offload_state(&state->psp_st))
+		return mlx5e_psp_tx_ids_len(&state->psp_st);
+#endif
+
 #ifdef CONFIG_MLX5_EN_IPSEC
 	if (test_bit(MLX5E_SQ_STATE_IPSEC, &sq->state))
 		return mlx5e_ipsec_tx_ids_len(&state->ipsec);
@@ -172,8 +190,14 @@ static inline unsigned int mlx5e_accel_tx_ids_len(struct mlx5e_txqsq *sq,
 
 static inline void mlx5e_accel_tx_eseg(struct mlx5e_priv *priv,
 				       struct sk_buff *skb,
+				       struct mlx5e_accel_tx_state *accel,
 				       struct mlx5_wqe_eth_seg *eseg, u16 ihs)
 {
+#ifdef CONFIG_MLX5_EN_PSP
+	if (mlx5e_psp_is_offload_state(&accel->psp_st))
+		mlx5e_psp_tx_build_eseg(priv, skb, &accel->psp_st, eseg);
+#endif
+
 #ifdef CONFIG_MLX5_EN_IPSEC
 	if (xfrm_offload(skb))
 		mlx5e_ipsec_tx_build_eseg(priv, skb, eseg);
@@ -199,6 +223,11 @@ static inline void mlx5e_accel_tx_finish(struct mlx5e_txqsq *sq,
 	mlx5e_ktls_handle_tx_wqe(&wqe->ctrl, &state->tls);
 #endif
 
+#ifdef CONFIG_MLX5_EN_PSP
+	if (mlx5e_psp_is_offload_state(&state->psp_st))
+		mlx5e_psp_handle_tx_wqe(wqe, &state->psp_st, inlseg);
+#endif
+
 #ifdef CONFIG_MLX5_EN_IPSEC
 	if (test_bit(MLX5E_SQ_STATE_IPSEC, &sq->state) &&
 	    state->ipsec.xo && state->ipsec.tailen)
@@ -208,21 +237,40 @@ static inline void mlx5e_accel_tx_finish(struct mlx5e_txqsq *sq,
 
 static inline int mlx5e_accel_init_rx(struct mlx5e_priv *priv)
 {
-	return mlx5e_ktls_init_rx(priv);
+	int err;
+
+	err = mlx5_accel_psp_fs_init_rx_tables(priv);
+	if (err)
+		goto out;
+
+	err = mlx5e_ktls_init_rx(priv);
+	if (err)
+		mlx5_accel_psp_fs_cleanup_rx_tables(priv);
+
+out:
+	return err;
 }
 
 static inline void mlx5e_accel_cleanup_rx(struct mlx5e_priv *priv)
 {
 	mlx5e_ktls_cleanup_rx(priv);
+	mlx5_accel_psp_fs_cleanup_rx_tables(priv);
 }
 
 static inline int mlx5e_accel_init_tx(struct mlx5e_priv *priv)
 {
+	int err;
+
+	err = mlx5_accel_psp_fs_init_tx_tables(priv);
+	if (err)
+		return err;
+
 	return mlx5e_ktls_init_tx(priv);
 }
 
 static inline void mlx5e_accel_cleanup_tx(struct mlx5e_priv *priv)
 {
 	mlx5e_ktls_cleanup_tx(priv);
+	mlx5_accel_psp_fs_cleanup_tx_tables(priv);
 }
 #endif /* __MLX5E_EN_ACCEL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
index 4f83e3172767..1febdc5b81f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
@@ -138,7 +138,7 @@ struct mlx5_flow_handle *mlx5e_accel_fs_add_sk(struct mlx5e_flow_steering *fs,
 	flow = mlx5_add_flow_rules(ft->t, spec, &flow_act, &dest, 1);
 
 	if (IS_ERR(flow))
-		fs_err(fs, "mlx5_add_flow_rules() failed, flow is %ld\n", PTR_ERR(flow));
+		fs_err(fs, "mlx5_add_flow_rules() failed, flow is %pe\n", flow);
 
 out:
 	kvfree(spec);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index ca92e518be76..35d9530037a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -36,6 +36,7 @@
 #include <linux/inetdevice.h>
 #include <linux/netdevice.h>
 #include <net/netevent.h>
+#include <net/ipv6_stubs.h>
 
 #include "en.h"
 #include "eswitch.h"
@@ -94,25 +95,14 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry)
 	u32 esn, esn_msb;
 	u8 overlap;
 
-	switch (x->xso.type) {
-	case XFRM_DEV_OFFLOAD_PACKET:
-		switch (x->xso.dir) {
-		case XFRM_DEV_OFFLOAD_IN:
-			esn = x->replay_esn->seq;
-			esn_msb = x->replay_esn->seq_hi;
-			break;
-		case XFRM_DEV_OFFLOAD_OUT:
-			esn = x->replay_esn->oseq;
-			esn_msb = x->replay_esn->oseq_hi;
-			break;
-		default:
-			WARN_ON(true);
-			return false;
-		}
-		break;
-	case XFRM_DEV_OFFLOAD_CRYPTO:
-		/* Already parsed by XFRM core */
+	switch (x->xso.dir) {
+	case XFRM_DEV_OFFLOAD_IN:
 		esn = x->replay_esn->seq;
+		esn_msb = x->replay_esn->seq_hi;
+		break;
+	case XFRM_DEV_OFFLOAD_OUT:
+		esn = x->replay_esn->oseq;
+		esn_msb = x->replay_esn->oseq_hi;
 		break;
 	default:
 		WARN_ON(true);
@@ -121,11 +111,15 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 	overlap = sa_entry->esn_state.overlap;
 
-	if (esn >= x->replay_esn->replay_window)
-		seq_bottom = esn - x->replay_esn->replay_window + 1;
+	if (!x->replay_esn->replay_window) {
+		seq_bottom = esn;
+	} else {
+		if (esn >= x->replay_esn->replay_window)
+			seq_bottom = esn - x->replay_esn->replay_window + 1;
 
-	if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO)
-		esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom));
+		if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO)
+			esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom));
+	}
 
 	if (sa_entry->esn_state.esn_msb)
 		sa_entry->esn_state.esn = esn;
@@ -266,10 +260,15 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 				  struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
 	struct mlx5_core_dev *mdev = mlx5e_ipsec_sa2dev(sa_entry);
+	struct mlx5e_ipsec_addr *addrs = &attrs->addrs;
+	struct net_device *netdev = sa_entry->dev;
 	struct xfrm_state *x = sa_entry->x;
-	struct net_device *netdev;
+	struct dst_entry *rt_dst_entry;
+	struct flowi4 fl4 = {};
+	struct flowi6 fl6 = {};
 	struct neighbour *n;
 	u8 addr[ETH_ALEN];
+	struct rtable *rt;
 	const void *pkey;
 	u8 *dst, *src;
 
@@ -277,25 +276,94 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	    attrs->type != XFRM_DEV_OFFLOAD_PACKET)
 		return;
 
-	netdev = x->xso.real_dev;
-
 	mlx5_query_mac_address(mdev, addr);
 	switch (attrs->dir) {
 	case XFRM_DEV_OFFLOAD_IN:
 		src = attrs->dmac;
 		dst = attrs->smac;
-		pkey = &attrs->saddr.a4;
+
+		switch (addrs->family) {
+		case AF_INET:
+			fl4.flowi4_proto = x->sel.proto;
+			fl4.daddr = addrs->saddr.a4;
+			fl4.saddr = addrs->daddr.a4;
+			pkey = &addrs->saddr.a4;
+			break;
+		case AF_INET6:
+			fl6.flowi6_proto = x->sel.proto;
+			memcpy(fl6.daddr.s6_addr32, addrs->saddr.a6, 16);
+			memcpy(fl6.saddr.s6_addr32, addrs->daddr.a6, 16);
+			pkey = &addrs->saddr.a6;
+			break;
+		default:
+			return;
+		}
 		break;
 	case XFRM_DEV_OFFLOAD_OUT:
 		src = attrs->smac;
 		dst = attrs->dmac;
-		pkey = &attrs->daddr.a4;
+		switch (addrs->family) {
+		case AF_INET:
+			fl4.flowi4_proto = x->sel.proto;
+			fl4.daddr = addrs->daddr.a4;
+			fl4.saddr = addrs->saddr.a4;
+			pkey = &addrs->daddr.a4;
+			break;
+		case AF_INET6:
+			fl6.flowi6_proto = x->sel.proto;
+			memcpy(fl6.daddr.s6_addr32, addrs->daddr.a6, 16);
+			memcpy(fl6.saddr.s6_addr32, addrs->saddr.a6, 16);
+			pkey = &addrs->daddr.a6;
+			break;
+		default:
+			return;
+		}
 		break;
 	default:
 		return;
 	}
 
 	ether_addr_copy(src, addr);
+
+	/* Destination can refer to a routed network, so perform FIB lookup
+	 * to resolve nexthop and get its MAC. Neighbour resolution is used as
+	 * fallback.
+	 */
+	switch (addrs->family) {
+	case AF_INET:
+		rt = ip_route_output_key(dev_net(netdev), &fl4);
+		if (IS_ERR(rt))
+			goto neigh;
+
+		if (rt->rt_type != RTN_UNICAST) {
+			ip_rt_put(rt);
+			goto neigh;
+		}
+		rt_dst_entry = &rt->dst;
+		break;
+	case AF_INET6:
+		rt_dst_entry = ipv6_stub->ipv6_dst_lookup_flow(
+			dev_net(netdev), NULL, &fl6, NULL);
+		if (IS_ERR(rt_dst_entry))
+			goto neigh;
+		break;
+	default:
+		return;
+	}
+
+	n = dst_neigh_lookup(rt_dst_entry, pkey);
+	if (!n) {
+		dst_release(rt_dst_entry);
+		goto neigh;
+	}
+
+	neigh_ha_snapshot(addr, n, netdev);
+	ether_addr_copy(dst, addr);
+	dst_release(rt_dst_entry);
+	neigh_release(n);
+	return;
+
+neigh:
 	n = neigh_lookup(&arp_tbl, pkey, netdev);
 	if (!n) {
 		n = neigh_create(&arp_tbl, pkey, netdev);
@@ -310,6 +378,16 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	neigh_release(n);
 }
 
+static void mlx5e_ipsec_state_mask(struct mlx5e_ipsec_addr *addrs)
+{
+	/*
+	 * State doesn't have subnet prefixes in outer headers.
+	 * The match is performed for exaxt source/destination addresses.
+	 */
+	memset(addrs->smask.m6, 0xFF, sizeof(__be32) * 4);
+	memset(addrs->dmask.m6, 0xFF, sizeof(__be32) * 4);
+}
+
 void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 					struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
@@ -381,9 +459,11 @@ skip_replay_window:
 	attrs->spi = be32_to_cpu(x->id.spi);
 
 	/* source , destination ips */
-	memcpy(&attrs->saddr, x->props.saddr.a6, sizeof(attrs->saddr));
-	memcpy(&attrs->daddr, x->id.daddr.a6, sizeof(attrs->daddr));
-	attrs->family = x->props.family;
+	memcpy(&attrs->addrs.saddr, x->props.saddr.a6,
+	       sizeof(attrs->addrs.saddr));
+	memcpy(&attrs->addrs.daddr, x->id.daddr.a6, sizeof(attrs->addrs.daddr));
+	attrs->addrs.family = x->props.family;
+	mlx5e_ipsec_state_mask(&attrs->addrs);
 	attrs->type = x->xso.type;
 	attrs->reqid = x->props.reqid;
 	attrs->upspec.dport = ntohs(x->sel.dport);
@@ -435,7 +515,8 @@ static int mlx5e_xfrm_validate_state(struct mlx5_core_dev *mdev,
 	}
 	if (x->encap) {
 		if (!(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ESPINUDP)) {
-			NL_SET_ERR_MSG_MOD(extack, "Encapsulation is not supported");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Encapsulation is not supported");
 			return -EINVAL;
 		}
 
@@ -686,17 +767,18 @@ static int mlx5e_ipsec_create_dwork(struct mlx5e_ipsec_sa_entry *sa_entry)
 	return 0;
 }
 
-static int mlx5e_xfrm_add_state(struct xfrm_state *x,
+static int mlx5e_xfrm_add_state(struct net_device *dev,
+				struct xfrm_state *x,
 				struct netlink_ext_ack *extack)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = NULL;
-	struct net_device *netdev = x->xso.real_dev;
+	bool allow_tunnel_mode = false;
 	struct mlx5e_ipsec *ipsec;
 	struct mlx5e_priv *priv;
 	gfp_t gfp;
 	int err;
 
-	priv = netdev_priv(netdev);
+	priv = netdev_priv(dev);
 	if (!priv->ipsec)
 		return -EOPNOTSUPP;
 
@@ -707,6 +789,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x,
 		return -ENOMEM;
 
 	sa_entry->x = x;
+	sa_entry->dev = dev;
 	sa_entry->ipsec = ipsec;
 	/* Check if this SA is originated from acquire flow temporary SA */
 	if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ)
@@ -721,15 +804,36 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x,
 		goto err_xfrm;
 	}
 
+	err = mlx5_eswitch_block_mode(priv->mdev);
+	if (err)
+		goto unblock_ipsec;
+
+	if (x->props.mode == XFRM_MODE_TUNNEL &&
+	    x->xso.type == XFRM_DEV_OFFLOAD_PACKET) {
+		allow_tunnel_mode = mlx5e_ipsec_fs_tunnel_allowed(sa_entry);
+		if (!allow_tunnel_mode) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Packet offload tunnel mode is disabled due to encap settings");
+			err = -EINVAL;
+			goto unblock_mode;
+		}
+	}
+
 	/* check esn */
 	if (x->props.flags & XFRM_STATE_ESN)
 		mlx5e_ipsec_update_esn_state(sa_entry);
+	else
+		/* According to RFC4303, section "3.3.3. Sequence Number Generation",
+		 * the first packet sent using a given SA will contain a sequence
+		 * number of 1.
+		 */
+		sa_entry->esn_state.esn = 1;
 
 	mlx5e_ipsec_build_accel_xfrm_attrs(sa_entry, &sa_entry->attrs);
 
 	err = mlx5_ipsec_create_work(sa_entry);
 	if (err)
-		goto unblock_ipsec;
+		goto unblock_encap;
 
 	err = mlx5e_ipsec_create_dwork(sa_entry);
 	if (err)
@@ -744,14 +848,6 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x,
 	if (err)
 		goto err_hw_ctx;
 
-	if (x->props.mode == XFRM_MODE_TUNNEL &&
-	    x->xso.type == XFRM_DEV_OFFLOAD_PACKET &&
-	    !mlx5e_ipsec_fs_tunnel_enabled(sa_entry)) {
-		NL_SET_ERR_MSG_MOD(extack, "Packet offload tunnel mode is disabled due to encap settings");
-		err = -EINVAL;
-		goto err_add_rule;
-	}
-
 	/* We use *_bh() variant because xfrm_timer_handler(), which runs
 	 * in softirq context, can reach our state delete logic and we need
 	 * xa_erase_bh() there.
@@ -767,13 +863,20 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x,
 		queue_delayed_work(ipsec->wq, &sa_entry->dwork->dwork,
 				   MLX5_IPSEC_RESCHED);
 
-	if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET &&
-	    x->props.mode == XFRM_MODE_TUNNEL)
-		xa_set_mark(&ipsec->sadb, sa_entry->ipsec_obj_id,
-			    MLX5E_IPSEC_TUNNEL_SA);
+	if (allow_tunnel_mode) {
+		xa_lock_bh(&ipsec->sadb);
+		__xa_set_mark(&ipsec->sadb, sa_entry->ipsec_obj_id,
+			      MLX5E_IPSEC_TUNNEL_SA);
+		xa_unlock_bh(&ipsec->sadb);
+	}
 
 out:
 	x->xso.offload_handle = (unsigned long)sa_entry;
+	if (allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(priv->mdev);
+
+	mlx5_eswitch_unblock_mode(priv->mdev);
+
 	return 0;
 
 err_add_rule:
@@ -786,6 +889,11 @@ release_work:
 	if (sa_entry->work)
 		kfree(sa_entry->work->data);
 	kfree(sa_entry->work);
+unblock_encap:
+	if (allow_tunnel_mode)
+		mlx5_eswitch_unblock_encap(priv->mdev);
+unblock_mode:
+	mlx5_eswitch_unblock_mode(priv->mdev);
 unblock_ipsec:
 	mlx5_eswitch_unblock_ipsec(priv->mdev);
 err_xfrm:
@@ -794,10 +902,9 @@ err_xfrm:
 	return err;
 }
 
-static void mlx5e_xfrm_del_state(struct xfrm_state *x)
+static void mlx5e_xfrm_del_state(struct net_device *dev, struct xfrm_state *x)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x);
-	struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs;
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
 	struct mlx5e_ipsec_sa_entry *old;
 
@@ -806,15 +913,9 @@ static void mlx5e_xfrm_del_state(struct xfrm_state *x)
 
 	old = xa_erase_bh(&ipsec->sadb, sa_entry->ipsec_obj_id);
 	WARN_ON(old != sa_entry);
-
-	if (attrs->mode == XFRM_MODE_TUNNEL &&
-	    attrs->type == XFRM_DEV_OFFLOAD_PACKET)
-		/* Make sure that no ARP requests are running in parallel */
-		flush_workqueue(ipsec->wq);
-
 }
 
-static void mlx5e_xfrm_free_state(struct xfrm_state *x)
+static void mlx5e_xfrm_free_state(struct net_device *dev, struct xfrm_state *x)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x);
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
@@ -847,8 +948,6 @@ static int mlx5e_ipsec_netevent_event(struct notifier_block *nb,
 	struct mlx5e_ipsec_sa_entry *sa_entry;
 	struct mlx5e_ipsec *ipsec;
 	struct neighbour *n = ptr;
-	struct net_device *netdev;
-	struct xfrm_state *x;
 	unsigned long idx;
 
 	if (event != NETEVENT_NEIGH_UPDATE || !(n->nud_state & NUD_VALID))
@@ -858,21 +957,19 @@ static int mlx5e_ipsec_netevent_event(struct notifier_block *nb,
 	xa_for_each_marked(&ipsec->sadb, idx, sa_entry, MLX5E_IPSEC_TUNNEL_SA) {
 		attrs = &sa_entry->attrs;
 
-		if (attrs->family == AF_INET) {
-			if (!neigh_key_eq32(n, &attrs->saddr.a4) &&
-			    !neigh_key_eq32(n, &attrs->daddr.a4))
+		if (attrs->addrs.family == AF_INET) {
+			if (!neigh_key_eq32(n, &attrs->addrs.saddr.a4) &&
+			    !neigh_key_eq32(n, &attrs->addrs.daddr.a4))
 				continue;
 		} else {
-			if (!neigh_key_eq128(n, &attrs->saddr.a4) &&
-			    !neigh_key_eq128(n, &attrs->daddr.a4))
+			if (!neigh_key_eq128(n, &attrs->addrs.saddr.a4) &&
+			    !neigh_key_eq128(n, &attrs->addrs.daddr.a4))
 				continue;
 		}
 
-		x = sa_entry->x;
-		netdev = x->xso.real_dev;
 		data = sa_entry->work->data;
 
-		neigh_ha_snapshot(data->addr, n, netdev);
+		neigh_ha_snapshot(data->addr, n, sa_entry->dev);
 		queue_work(ipsec->wq, &sa_entry->work->work);
 	}
 
@@ -958,21 +1055,6 @@ void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv)
 	priv->ipsec = NULL;
 }
 
-static bool mlx5e_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
-{
-	if (x->props.family == AF_INET) {
-		/* Offload with IPv4 options is not supported yet */
-		if (ip_hdr(skb)->ihl > 5)
-			return false;
-	} else {
-		/* Offload with IPv6 extension headers is not support yet */
-		if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr))
-			return false;
-	}
-
-	return true;
-}
-
 static void mlx5e_xfrm_advance_esn_state(struct xfrm_state *x)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x);
@@ -1003,8 +1085,8 @@ static void mlx5e_xfrm_update_stats(struct xfrm_state *x)
 	size_t headers;
 
 	lockdep_assert(lockdep_is_held(&x->lock) ||
-		       lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_cfg_mutex) ||
-		       lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_state_lock));
+		       lockdep_is_held(&net->xfrm.xfrm_cfg_mutex) ||
+		       lockdep_is_held(&net->xfrm.xfrm_state_lock));
 
 	if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ)
 		return;
@@ -1040,7 +1122,7 @@ static void mlx5e_xfrm_update_stats(struct xfrm_state *x)
 	 * by removing always available headers.
 	 */
 	headers = sizeof(struct ethhdr);
-	if (sa_entry->attrs.family == AF_INET)
+	if (sa_entry->attrs.addrs.family == AF_INET)
 		headers += sizeof(struct iphdr);
 	else
 		headers += sizeof(struct ipv6hdr);
@@ -1049,6 +1131,43 @@ static void mlx5e_xfrm_update_stats(struct xfrm_state *x)
 	x->curlft.bytes += success_bytes - headers * success_packets;
 }
 
+static __be32 word_to_mask(int prefix)
+{
+	if (prefix < 0)
+		return 0;
+
+	if (!prefix || prefix > 31)
+		return cpu_to_be32(0xFFFFFFFF);
+
+	return cpu_to_be32(((1U << prefix) - 1) << (32 - prefix));
+}
+
+static void mlx5e_ipsec_policy_mask(struct mlx5e_ipsec_addr *addrs,
+				    struct xfrm_selector *sel)
+{
+	int i;
+
+	if (addrs->family == AF_INET) {
+		addrs->smask.m4 = word_to_mask(sel->prefixlen_s);
+		addrs->saddr.a4 &= addrs->smask.m4;
+		addrs->dmask.m4 = word_to_mask(sel->prefixlen_d);
+		addrs->daddr.a4 &= addrs->dmask.m4;
+		return;
+	}
+
+	for (i = 0; i < 4; i++) {
+		if (sel->prefixlen_s != 32 * i)
+			addrs->smask.m6[i] =
+				word_to_mask(sel->prefixlen_s - 32 * i);
+		addrs->saddr.a6[i] &= addrs->smask.m6[i];
+
+		if (sel->prefixlen_d != 32 * i)
+			addrs->dmask.m6[i] =
+				word_to_mask(sel->prefixlen_d - 32 * i);
+		addrs->daddr.a6[i] &= addrs->dmask.m6[i];
+	}
+}
+
 static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev,
 				      struct xfrm_policy *x,
 				      struct netlink_ext_ack *extack)
@@ -1121,9 +1240,10 @@ mlx5e_ipsec_build_accel_pol_attrs(struct mlx5e_ipsec_pol_entry *pol_entry,
 	sel = &x->selector;
 	memset(attrs, 0, sizeof(*attrs));
 
-	memcpy(&attrs->saddr, sel->saddr.a6, sizeof(attrs->saddr));
-	memcpy(&attrs->daddr, sel->daddr.a6, sizeof(attrs->daddr));
-	attrs->family = sel->family;
+	memcpy(&attrs->addrs.saddr, sel->saddr.a6, sizeof(attrs->addrs.saddr));
+	memcpy(&attrs->addrs.daddr, sel->daddr.a6, sizeof(attrs->addrs.daddr));
+	attrs->addrs.family = sel->family;
+	mlx5e_ipsec_policy_mask(&attrs->addrs, sel);
 	attrs->dir = x->xdo.dir;
 	attrs->action = x->action;
 	attrs->type = XFRM_DEV_OFFLOAD_PACKET;
@@ -1139,7 +1259,7 @@ mlx5e_ipsec_build_accel_pol_attrs(struct mlx5e_ipsec_pol_entry *pol_entry,
 static int mlx5e_xfrm_add_policy(struct xfrm_policy *x,
 				 struct netlink_ext_ack *extack)
 {
-	struct net_device *netdev = x->xdo.real_dev;
+	struct net_device *netdev = x->xdo.dev;
 	struct mlx5e_ipsec_pol_entry *pol_entry;
 	struct mlx5e_priv *priv;
 	int err;
@@ -1201,7 +1321,6 @@ static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = {
 	.xdo_dev_state_add	= mlx5e_xfrm_add_state,
 	.xdo_dev_state_delete	= mlx5e_xfrm_del_state,
 	.xdo_dev_state_free	= mlx5e_xfrm_free_state,
-	.xdo_dev_offload_ok	= mlx5e_ipsec_offload_ok,
 	.xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state,
 
 	.xdo_dev_state_update_stats = mlx5e_xfrm_update_stats,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 7d943e93cf6d..f8eaaf37963b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -76,27 +76,36 @@ struct mlx5_replay_esn {
 	u8 trigger : 1;
 };
 
-struct mlx5_accel_esp_xfrm_attrs {
-	u32   spi;
-	u32   mode;
-	struct aes_gcm_keymat aes_gcm;
-
+struct mlx5e_ipsec_addr {
 	union {
 		__be32 a4;
 		__be32 a6[4];
 	} saddr;
-
+	union {
+		__be32 m4;
+		__be32 m6[4];
+	} smask;
 	union {
 		__be32 a4;
 		__be32 a6[4];
 	} daddr;
+	union {
+		__be32 m4;
+		__be32 m6[4];
+	} dmask;
+	u8 family;
+};
 
+struct mlx5_accel_esp_xfrm_attrs {
+	u32   spi;
+	u32   mode;
+	struct aes_gcm_keymat aes_gcm;
+	struct mlx5e_ipsec_addr addrs;
 	struct upspec upspec;
 	u8 dir : 2;
 	u8 type : 2;
 	u8 drop : 1;
 	u8 encap : 1;
-	u8 family;
 	struct mlx5_replay_esn replay_esn;
 	u32 authsize;
 	u32 reqid;
@@ -128,6 +137,7 @@ struct mlx5e_ipsec_hw_stats {
 	u64 ipsec_rx_bytes;
 	u64 ipsec_rx_drop_pkts;
 	u64 ipsec_rx_drop_bytes;
+	u64 ipsec_rx_drop_mismatch_sa_sel;
 	u64 ipsec_tx_pkts;
 	u64 ipsec_tx_bytes;
 	u64 ipsec_tx_drop_pkts;
@@ -175,6 +185,7 @@ struct mlx5e_ipsec_rx_create_attr {
 	u32 family;
 	int prio;
 	int pol_level;
+	int pol_miss_level;
 	int sa_level;
 	int status_level;
 	enum mlx5_flow_namespace_type chains_ns;
@@ -184,6 +195,7 @@ struct mlx5e_ipsec_ft {
 	struct mutex mutex; /* Protect changes to this struct */
 	struct mlx5_flow_table *pol;
 	struct mlx5_flow_table *sa;
+	struct mlx5_flow_table *sa_sel;
 	struct mlx5_flow_table *status;
 	u32 refcnt;
 };
@@ -195,6 +207,8 @@ struct mlx5e_ipsec_drop {
 
 struct mlx5e_ipsec_rule {
 	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_handle *status_pass;
+	struct mlx5_flow_handle *sa_sel;
 	struct mlx5_modify_hdr *modify_hdr;
 	struct mlx5_pkt_reformat *pkt_reformat;
 	struct mlx5_fc *fc;
@@ -206,6 +220,7 @@ struct mlx5e_ipsec_rule {
 struct mlx5e_ipsec_miss {
 	struct mlx5_flow_group *group;
 	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *fc;
 };
 
 struct mlx5e_ipsec_tx_create_attr {
@@ -260,6 +275,7 @@ struct mlx5e_ipsec_limits {
 struct mlx5e_ipsec_sa_entry {
 	struct mlx5e_ipsec_esn_state esn_state;
 	struct xfrm_state *x;
+	struct net_device *dev;
 	struct mlx5e_ipsec *ipsec;
 	struct mlx5_accel_esp_xfrm_attrs attrs;
 	void (*set_iv_op)(struct sk_buff *skb, struct xfrm_state *x,
@@ -274,18 +290,8 @@ struct mlx5e_ipsec_sa_entry {
 };
 
 struct mlx5_accel_pol_xfrm_attrs {
-	union {
-		__be32 a4;
-		__be32 a6[4];
-	} saddr;
-
-	union {
-		__be32 a4;
-		__be32 a6[4];
-	} daddr;
-
+	struct mlx5e_ipsec_addr addrs;
 	struct upspec upspec;
-	u8 family;
 	u8 action;
 	u8 type : 2;
 	u8 dir : 2;
@@ -313,7 +319,7 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry);
 int mlx5e_accel_ipsec_fs_add_pol(struct mlx5e_ipsec_pol_entry *pol_entry);
 void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry);
 void mlx5e_accel_ipsec_fs_modify(struct mlx5e_ipsec_sa_entry *sa_entry);
-bool mlx5e_ipsec_fs_tunnel_enabled(struct mlx5e_ipsec_sa_entry *sa_entry);
+bool mlx5e_ipsec_fs_tunnel_allowed(struct mlx5e_ipsec_sa_entry *sa_entry);
 
 int mlx5_ipsec_create_sa_ctx(struct mlx5e_ipsec_sa_entry *sa_entry);
 void mlx5_ipsec_free_sa_ctx(struct mlx5e_ipsec_sa_entry *sa_entry);
@@ -336,6 +342,7 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 void mlx5e_ipsec_handle_mpv_event(int event, struct mlx5e_priv *slave_priv,
 				  struct mlx5e_priv *master_priv);
 void mlx5e_ipsec_send_event(struct mlx5e_priv *priv, int event);
+void mlx5e_ipsec_disable_events(struct mlx5e_priv *priv);
 
 static inline struct mlx5_core_dev *
 mlx5e_ipsec_sa2dev(struct mlx5e_ipsec_sa_entry *sa_entry)
@@ -381,6 +388,10 @@ static inline void mlx5e_ipsec_handle_mpv_event(int event, struct mlx5e_priv *sl
 static inline void mlx5e_ipsec_send_event(struct mlx5e_priv *priv, int event)
 {
 }
+
+static inline void mlx5e_ipsec_disable_events(struct mlx5e_priv *priv)
+{
+}
 #endif
 
 #endif	/* __MLX5E_IPSEC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 687bd95d2c3e..feef86fff4bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -16,6 +16,16 @@
 #define MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE 16
 #define IPSEC_TUNNEL_DEFAULT_TTL 0x40
 
+#define MLX5_IPSEC_FS_SA_SELECTOR_MAX_NUM_GROUPS 16
+
+enum {
+	MLX5_IPSEC_ASO_OK,
+	MLX5_IPSEC_ASO_BAD_REPLY,
+
+	/* For crypto offload, set by driver */
+	MLX5_IPSEC_ASO_SW_CRYPTO_OFFLOAD = 0xAA,
+};
+
 struct mlx5e_ipsec_fc {
 	struct mlx5_fc *cnt;
 	struct mlx5_fc *drop;
@@ -33,6 +43,9 @@ struct mlx5e_ipsec_tx {
 };
 
 struct mlx5e_ipsec_status_checks {
+	struct mlx5_flow_group *pass_group;
+	struct mlx5_flow_handle *packet_offload_pass_rule;
+	struct mlx5_flow_handle *crypto_offload_pass_rule;
 	struct mlx5_flow_group *drop_all_group;
 	struct mlx5e_ipsec_drop all;
 };
@@ -41,11 +54,14 @@ struct mlx5e_ipsec_rx {
 	struct mlx5e_ipsec_ft ft;
 	struct mlx5e_ipsec_miss pol;
 	struct mlx5e_ipsec_miss sa;
-	struct mlx5e_ipsec_rule status;
-	struct mlx5e_ipsec_status_checks status_drops;
+	struct mlx5e_ipsec_miss sa_sel;
+	struct mlx5e_ipsec_status_checks status_checks;
 	struct mlx5e_ipsec_fc *fc;
 	struct mlx5_fs_chains *chains;
+	struct mlx5_flow_table *pol_miss_ft;
+	struct mlx5_flow_handle *pol_miss_rule;
 	u8 allow_tunnel_mode : 1;
+	u8 ttc_rules_added : 1;
 };
 
 /* IPsec RX flow steering */
@@ -130,11 +146,12 @@ static void ipsec_chains_put_table(struct mlx5_fs_chains *chains, u32 prio)
 
 static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns,
 					       int level, int prio,
+					       int num_reserved_entries,
 					       int max_num_groups, u32 flags)
 {
 	struct mlx5_flow_table_attr ft_attr = {};
 
-	ft_attr.autogroup.num_reserved_entries = 1;
+	ft_attr.autogroup.num_reserved_entries = num_reserved_entries;
 	ft_attr.autogroup.max_num_groups = max_num_groups;
 	ft_attr.max_fte = NUM_IPSEC_FTE;
 	ft_attr.level = level;
@@ -147,22 +164,35 @@ static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns,
 static void ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
 					 struct mlx5e_ipsec_rx *rx)
 {
-	mlx5_del_flow_rules(rx->status_drops.all.rule);
-	mlx5_fc_destroy(ipsec->mdev, rx->status_drops.all.fc);
-	mlx5_destroy_flow_group(rx->status_drops.drop_all_group);
+	mlx5_del_flow_rules(rx->status_checks.all.rule);
+	mlx5_fc_destroy(ipsec->mdev, rx->status_checks.all.fc);
+	mlx5_destroy_flow_group(rx->status_checks.drop_all_group);
 }
 
 static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
 					 struct mlx5e_ipsec_rx *rx)
 {
-	mlx5_del_flow_rules(rx->status.rule);
+	mlx5_del_flow_rules(rx->status_checks.packet_offload_pass_rule);
+	mlx5_del_flow_rules(rx->status_checks.crypto_offload_pass_rule);
+}
 
-	if (rx != ipsec->rx_esw)
-		return;
+static void ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+					struct mlx5e_ipsec_rx *rx,
+					struct mlx5_flow_spec *spec)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
 
-#ifdef CONFIG_MLX5_ESWITCH
-	mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0);
-#endif
+	if (rx == ipsec->rx_esw) {
+		mlx5_esw_ipsec_rx_rule_add_match_obj(sa_entry, spec);
+	} else {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 misc_parameters_2.metadata_reg_c_2);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 misc_parameters_2.metadata_reg_c_2,
+			 sa_entry->ipsec_obj_id | BIT(31));
+
+		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+	}
 }
 
 static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry,
@@ -200,11 +230,8 @@ static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry,
 
 	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.ipsec_syndrome);
 	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 1);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
-	MLX5_SET(fte_match_param, spec->match_value,
-		 misc_parameters_2.metadata_reg_c_2,
-		 sa_entry->ipsec_obj_id | BIT(31));
 	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	ipsec_rx_rule_add_match_obj(sa_entry, rx, spec);
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -281,10 +308,8 @@ static int rx_add_rule_drop_replay(struct mlx5e_ipsec_sa_entry *sa_entry, struct
 
 	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_4);
 	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_4, 1);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
-	MLX5_SET(fte_match_param, spec->match_value,  misc_parameters_2.metadata_reg_c_2,
-		 sa_entry->ipsec_obj_id | BIT(31));
 	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	ipsec_rx_rule_add_match_obj(sa_entry, rx, spec);
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -359,9 +384,9 @@ static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec,
 		goto err_rule;
 	}
 
-	rx->status_drops.drop_all_group = g;
-	rx->status_drops.all.rule = rule;
-	rx->status_drops.all.fc = flow_counter;
+	rx->status_checks.drop_all_group = g;
+	rx->status_checks.all.rule = rule;
+	rx->status_checks.all.fc = flow_counter;
 
 	kvfree(flow_group_in);
 	kvfree(spec);
@@ -377,9 +402,52 @@ err_out:
 	return err;
 }
 
-static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
-				       struct mlx5e_ipsec_rx *rx,
-				       struct mlx5_flow_destination *dest)
+static int ipsec_rx_status_pass_group_create(struct mlx5e_ipsec *ipsec,
+					     struct mlx5e_ipsec_rx *rx)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_table *ft = rx->ft.status;
+	struct mlx5_flow_group *fg;
+	void *match_criteria;
+	u32 *flow_group_in;
+	int err = 0;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_MISC_PARAMETERS_2);
+	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
+				      match_criteria);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters_2.ipsec_syndrome);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters_2.metadata_reg_c_4);
+
+	MLX5_SET(create_flow_group_in, flow_group_in,
+		 start_flow_index, ft->max_fte - 3);
+	MLX5_SET(create_flow_group_in, flow_group_in,
+		 end_flow_index, ft->max_fte - 2);
+
+	fg = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(fg)) {
+		err = PTR_ERR(fg);
+		mlx5_core_warn(ipsec->mdev,
+			       "Failed to create rx status pass flow group, err=%d\n",
+			       err);
+	}
+	rx->status_checks.pass_group = fg;
+
+	kvfree(flow_group_in);
+	return err;
+}
+
+static struct mlx5_flow_handle *
+ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
+			    struct mlx5e_ipsec_rx *rx,
+			    struct mlx5_flow_destination *dest,
+			    u8 aso_ok)
 {
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_handle *rule;
@@ -388,7 +456,7 @@ static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
 			 misc_parameters_2.ipsec_syndrome);
@@ -397,11 +465,11 @@ static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
 	MLX5_SET(fte_match_param, spec->match_value,
 		 misc_parameters_2.ipsec_syndrome, 0);
 	MLX5_SET(fte_match_param, spec->match_value,
-		 misc_parameters_2.metadata_reg_c_4, 0);
+		 misc_parameters_2.metadata_reg_c_4, aso_ok);
 	if (rx == ipsec->rx_esw)
 		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
 	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
-	flow_act.flags = FLOW_ACT_NO_APPEND;
+	flow_act.flags = FLOW_ACT_NO_APPEND | FLOW_ACT_IGNORE_FLOW_LEVEL;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
@@ -412,19 +480,19 @@ static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
 		goto err_rule;
 	}
 
-	rx->status.rule = rule;
 	kvfree(spec);
-	return 0;
+	return rule;
 
 err_rule:
 	kvfree(spec);
-	return err;
+	return ERR_PTR(err);
 }
 
 static void mlx5_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
 					 struct mlx5e_ipsec_rx *rx)
 {
 	ipsec_rx_status_pass_destroy(ipsec, rx);
+	mlx5_destroy_flow_group(rx->status_checks.pass_group);
 	ipsec_rx_status_drop_destroy(ipsec, rx);
 }
 
@@ -432,19 +500,44 @@ static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_rx *rx,
 				       struct mlx5_flow_destination *dest)
 {
+	struct mlx5_flow_destination pol_dest[2];
+	struct mlx5_flow_handle *rule;
 	int err;
 
 	err = ipsec_rx_status_drop_all_create(ipsec, rx);
 	if (err)
 		return err;
 
-	err = ipsec_rx_status_pass_create(ipsec, rx, dest);
+	err = ipsec_rx_status_pass_group_create(ipsec, rx);
 	if (err)
-		goto err_pass_create;
+		goto err_pass_group_create;
+
+	rule = ipsec_rx_status_pass_create(ipsec, rx, dest,
+					   MLX5_IPSEC_ASO_SW_CRYPTO_OFFLOAD);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		goto err_crypto_offload_pass_create;
+	}
+	rx->status_checks.crypto_offload_pass_rule = rule;
+
+	pol_dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	pol_dest[0].ft = rx->ft.pol;
+	pol_dest[1] = dest[1];
+	rule = ipsec_rx_status_pass_create(ipsec, rx, pol_dest,
+					   MLX5_IPSEC_ASO_OK);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		goto err_packet_offload_pass_create;
+	}
+	rx->status_checks.packet_offload_pass_rule = rule;
 
 	return 0;
 
-err_pass_create:
+err_packet_offload_pass_create:
+	mlx5_del_flow_rules(rx->status_checks.crypto_offload_pass_rule);
+err_crypto_offload_pass_create:
+	mlx5_destroy_flow_group(rx->status_checks.pass_group);
+err_pass_group_create:
 	ipsec_rx_status_drop_destroy(ipsec, rx);
 	return err;
 }
@@ -493,35 +586,56 @@ out:
 	return err;
 }
 
+static struct mlx5_flow_destination
+ipsec_rx_decrypted_pkt_def_dest(struct mlx5_ttc_table *ttc, u32 family)
+{
+	struct mlx5_flow_destination dest;
+
+	if (!mlx5_ttc_has_esp_flow_group(ttc))
+		return mlx5_ttc_get_default_dest(ttc, family2tt(family));
+
+	dest.ft = mlx5_get_ttc_flow_table(ttc);
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+
+	return dest;
+}
+
+static void ipsec_rx_update_default_dest(struct mlx5e_ipsec_rx *rx,
+					 struct mlx5_flow_destination *old_dest,
+					 struct mlx5_flow_destination *new_dest)
+{
+	mlx5_modify_rule_destination(rx->pol_miss_rule, new_dest, old_dest);
+	mlx5_modify_rule_destination(rx->status_checks.crypto_offload_pass_rule,
+				     new_dest, old_dest);
+}
+
 static void handle_ipsec_rx_bringup(struct mlx5e_ipsec *ipsec, u32 family)
 {
 	struct mlx5e_ipsec_rx *rx = ipsec_rx(ipsec, family, XFRM_DEV_OFFLOAD_PACKET);
 	struct mlx5_flow_namespace *ns = mlx5e_fs_get_ns(ipsec->fs, false);
+	struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(ipsec->fs, false);
 	struct mlx5_flow_destination old_dest, new_dest;
 
-	old_dest = mlx5_ttc_get_default_dest(mlx5e_fs_get_ttc(ipsec->fs, false),
-					     family2tt(family));
+	old_dest = ipsec_rx_decrypted_pkt_def_dest(ttc, family);
 
 	mlx5_ipsec_fs_roce_rx_create(ipsec->mdev, ipsec->roce, ns, &old_dest, family,
 				     MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL, MLX5E_NIC_PRIO);
 
 	new_dest.ft = mlx5_ipsec_fs_roce_ft_get(ipsec->roce, family);
 	new_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	mlx5_modify_rule_destination(rx->status.rule, &new_dest, &old_dest);
-	mlx5_modify_rule_destination(rx->sa.rule, &new_dest, &old_dest);
+	ipsec_rx_update_default_dest(rx, &old_dest, &new_dest);
 }
 
 static void handle_ipsec_rx_cleanup(struct mlx5e_ipsec *ipsec, u32 family)
 {
 	struct mlx5e_ipsec_rx *rx = ipsec_rx(ipsec, family, XFRM_DEV_OFFLOAD_PACKET);
+	struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(ipsec->fs, false);
 	struct mlx5_flow_destination old_dest, new_dest;
 
 	old_dest.ft = mlx5_ipsec_fs_roce_ft_get(ipsec->roce, family);
 	old_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	new_dest = mlx5_ttc_get_default_dest(mlx5e_fs_get_ttc(ipsec->fs, false),
-					     family2tt(family));
-	mlx5_modify_rule_destination(rx->sa.rule, &new_dest, &old_dest);
-	mlx5_modify_rule_destination(rx->status.rule, &new_dest, &old_dest);
+	new_dest = ipsec_rx_decrypted_pkt_def_dest(ttc, family);
+	ipsec_rx_update_default_dest(rx, &old_dest, &new_dest);
 
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, ipsec->mdev);
 }
@@ -570,20 +684,18 @@ static void ipsec_mpv_work_handler(struct work_struct *_work)
 	complete(&work->master_priv->ipsec->comp);
 }
 
-static void ipsec_rx_ft_disconnect(struct mlx5e_ipsec *ipsec, u32 family)
+static void ipsec_rx_ft_disconnect(struct mlx5e_ipsec *ipsec,
+				   struct mlx5e_ipsec_rx *rx, u32 family)
 {
 	struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(ipsec->fs, false);
 
+	if (rx->ttc_rules_added)
+		mlx5_ttc_destroy_ipsec_rules(ttc);
 	mlx5_ttc_fwd_default_dest(ttc, family2tt(family));
 }
 
-static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
-		       struct mlx5e_ipsec_rx *rx, u32 family)
+static void ipsec_rx_policy_destroy(struct mlx5e_ipsec_rx *rx)
 {
-	/* disconnect */
-	if (rx != ipsec->rx_esw)
-		ipsec_rx_ft_disconnect(ipsec, family);
-
 	if (rx->chains) {
 		ipsec_chains_destroy(rx->chains);
 	} else {
@@ -592,6 +704,29 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		mlx5_destroy_flow_table(rx->ft.pol);
 	}
 
+	if (rx->pol_miss_rule) {
+		mlx5_del_flow_rules(rx->pol_miss_rule);
+		mlx5_destroy_flow_table(rx->pol_miss_ft);
+	}
+}
+
+static void ipsec_rx_sa_selector_destroy(struct mlx5_core_dev *mdev,
+					 struct mlx5e_ipsec_rx *rx)
+{
+	mlx5_del_flow_rules(rx->sa_sel.rule);
+	mlx5_fc_destroy(mdev, rx->sa_sel.fc);
+	rx->sa_sel.fc = NULL;
+	mlx5_destroy_flow_group(rx->sa_sel.group);
+	mlx5_destroy_flow_table(rx->ft.sa_sel);
+}
+
+static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
+		       struct mlx5e_ipsec_rx *rx, u32 family)
+{
+	/* disconnect */
+	if (rx != ipsec->rx_esw)
+		ipsec_rx_ft_disconnect(ipsec, rx, family);
+
 	mlx5_del_flow_rules(rx->sa.rule);
 	mlx5_destroy_flow_group(rx->sa.group);
 	mlx5_destroy_flow_table(rx->ft.sa);
@@ -600,7 +735,17 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_ipsec_rx_status_destroy(ipsec, rx);
 	mlx5_destroy_flow_table(rx->ft.status);
 
+	ipsec_rx_sa_selector_destroy(mdev, rx);
+
+	ipsec_rx_policy_destroy(rx);
+
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev);
+
+#ifdef CONFIG_MLX5_ESWITCH
+	if (rx == ipsec->rx_esw)
+		mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch),
+				      0, 1, 0);
+#endif
 }
 
 static void ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
@@ -620,6 +765,7 @@ static void ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 	attr->family = family;
 	attr->prio = MLX5E_NIC_PRIO;
 	attr->pol_level = MLX5E_ACCEL_FS_POL_FT_LEVEL;
+	attr->pol_miss_level = MLX5E_ACCEL_FS_POL_MISS_FT_LEVEL;
 	attr->sa_level = MLX5E_ACCEL_FS_ESP_FT_LEVEL;
 	attr->status_level = MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL;
 	attr->chains_ns = MLX5_FLOW_NAMESPACE_KERNEL;
@@ -636,7 +782,7 @@ static int ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
 	if (rx == ipsec->rx_esw)
 		return mlx5_esw_ipsec_rx_status_pass_dest_get(ipsec, dest);
 
-	*dest = mlx5_ttc_get_default_dest(attr->ttc, family2tt(attr->family));
+	*dest = ipsec_rx_decrypted_pkt_def_dest(attr->ttc, attr->family);
 	err = mlx5_ipsec_fs_roce_rx_create(ipsec->mdev, ipsec->roce, attr->ns, dest,
 					   attr->family, MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL,
 					   attr->prio);
@@ -652,22 +798,254 @@ static int ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
 	return 0;
 }
 
+static void ipsec_rx_sa_miss_dest_get(struct mlx5e_ipsec *ipsec,
+				      struct mlx5e_ipsec_rx *rx,
+				      struct mlx5e_ipsec_rx_create_attr *attr,
+				      struct mlx5_flow_destination *dest,
+				      struct mlx5_flow_destination *miss_dest)
+{
+	if (rx == ipsec->rx_esw)
+		*miss_dest = *dest;
+	else
+		*miss_dest =
+			mlx5_ttc_get_default_dest(attr->ttc,
+						  family2tt(attr->family));
+}
+
+static void ipsec_rx_default_dest_get(struct mlx5e_ipsec *ipsec,
+				      struct mlx5e_ipsec_rx *rx,
+				      struct mlx5_flow_destination *dest)
+{
+	dest->type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest->ft = rx->pol_miss_ft;
+}
+
 static void ipsec_rx_ft_connect(struct mlx5e_ipsec *ipsec,
 				struct mlx5e_ipsec_rx *rx,
 				struct mlx5e_ipsec_rx_create_attr *attr)
 {
 	struct mlx5_flow_destination dest = {};
+	struct mlx5_ttc_table *ttc, *inner_ttc;
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest.ft = rx->ft.pol;
-	mlx5_ttc_fwd_dest(attr->ttc, family2tt(attr->family), &dest);
+	dest.ft = rx->ft.sa;
+	if (mlx5_ttc_fwd_dest(attr->ttc, family2tt(attr->family), &dest))
+		return;
+
+	ttc = mlx5e_fs_get_ttc(ipsec->fs, false);
+	inner_ttc = mlx5e_fs_get_ttc(ipsec->fs, true);
+	rx->ttc_rules_added = !mlx5_ttc_create_ipsec_rules(ttc, inner_ttc);
+}
+
+static int ipsec_rx_chains_create_miss(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx *rx,
+				       struct mlx5e_ipsec_rx_create_attr *attr,
+				       struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_table_attr ft_attr = {};
+	MLX5_DECLARE_FLOW_ACT(flow_act);
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_table *ft;
+	int err;
+
+	if (rx == ipsec->rx_esw) {
+		/* No need to create miss table for switchdev mode,
+		 * just set it to the root chain table.
+		 */
+		rx->pol_miss_ft = dest->ft;
+		return 0;
+	}
+
+	ft_attr.max_fte = 1;
+	ft_attr.autogroup.max_num_groups = 1;
+	ft_attr.level = attr->pol_miss_level;
+	ft_attr.prio = attr->prio;
+
+	ft = mlx5_create_auto_grouped_flow_table(attr->ns, &ft_attr);
+	if (IS_ERR(ft))
+		return PTR_ERR(ft);
+
+	rule = mlx5_add_flow_rules(ft, NULL, &flow_act, dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		goto err_rule;
+	}
+
+	rx->pol_miss_ft = ft;
+	rx->pol_miss_rule = rule;
+
+	return 0;
+
+err_rule:
+	mlx5_destroy_flow_table(ft);
+	return err;
 }
 
+static int ipsec_rx_policy_create(struct mlx5e_ipsec *ipsec,
+				  struct mlx5e_ipsec_rx *rx,
+				  struct mlx5e_ipsec_rx_create_attr *attr,
+				  struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_destination default_dest;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_table *ft;
+	int err;
+
+	err = ipsec_rx_chains_create_miss(ipsec, rx, attr, dest);
+	if (err)
+		return err;
+
+	ipsec_rx_default_dest_get(ipsec, rx, &default_dest);
+
+	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PRIO) {
+		rx->chains = ipsec_chains_create(mdev,
+						 default_dest.ft,
+						 attr->chains_ns,
+						 attr->prio,
+						 attr->sa_level,
+						 &rx->ft.pol);
+		if (IS_ERR(rx->chains))
+			err = PTR_ERR(rx->chains);
+	} else {
+		ft = ipsec_ft_create(attr->ns, attr->pol_level,
+				     attr->prio, 1, 2, 0);
+		if (IS_ERR(ft)) {
+			err = PTR_ERR(ft);
+			goto err_out;
+		}
+		rx->ft.pol = ft;
+
+		err = ipsec_miss_create(mdev, rx->ft.pol, &rx->pol,
+					&default_dest);
+		if (err)
+			mlx5_destroy_flow_table(rx->ft.pol);
+	}
+
+	if (!err)
+		return 0;
+
+err_out:
+	if (rx->pol_miss_rule) {
+		mlx5_del_flow_rules(rx->pol_miss_rule);
+		mlx5_destroy_flow_table(rx->pol_miss_ft);
+	}
+	return err;
+}
+
+static int ipsec_rx_sa_selector_create(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx *rx,
+				       struct mlx5e_ipsec_rx_create_attr *attr)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_destination dest;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *fg;
+	u32 *flow_group_in;
+	struct mlx5_fc *fc;
+	int err;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	ft = ipsec_ft_create(attr->ns, attr->status_level, attr->prio, 1,
+			     MLX5_IPSEC_FS_SA_SELECTOR_MAX_NUM_GROUPS, 0);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		mlx5_core_err(mdev, "Failed to create RX SA selector flow table, err=%d\n",
+			      err);
+		goto err_ft;
+	}
+
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index,
+		 ft->max_fte - 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+		 ft->max_fte - 1);
+	fg = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(fg)) {
+		err = PTR_ERR(fg);
+		mlx5_core_err(mdev, "Failed to create RX SA selector miss group, err=%d\n",
+			      err);
+		goto err_fg;
+	}
+
+	fc = mlx5_fc_create(mdev, false);
+	if (IS_ERR(fc)) {
+		err = PTR_ERR(fc);
+		mlx5_core_err(mdev,
+			      "Failed to create ipsec RX SA selector miss rule counter, err=%d\n",
+			      err);
+		goto err_cnt;
+	}
+
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter = fc;
+	flow_act.action =
+		MLX5_FLOW_CONTEXT_ACTION_COUNT | MLX5_FLOW_CONTEXT_ACTION_DROP;
+
+	rule = mlx5_add_flow_rules(ft, NULL, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev, "Failed to create RX SA selector miss drop rule, err=%d\n",
+			      err);
+		goto err_rule;
+	}
+
+	rx->ft.sa_sel = ft;
+	rx->sa_sel.group = fg;
+	rx->sa_sel.fc = fc;
+	rx->sa_sel.rule = rule;
+
+	kvfree(flow_group_in);
+
+	return 0;
+
+err_rule:
+	mlx5_fc_destroy(mdev, fc);
+err_cnt:
+	mlx5_destroy_flow_group(fg);
+err_fg:
+	mlx5_destroy_flow_table(ft);
+err_ft:
+	kvfree(flow_group_in);
+	return err;
+}
+
+/* The decryption processing is as follows:
+ *
+ *   +----------+                         +-------------+
+ *   |          |                         |             |
+ *   |  Kernel  <--------------+----------+ policy miss <------------+
+ *   |          |              ^          |             |            ^
+ *   +----^-----+              |          +-------------+            |
+ *        |                  crypto                                  |
+ *      miss                offload ok                         allow/default
+ *        ^                    ^                                     ^
+ *        |                    |                  packet             |
+ *   +----+---------+     +----+-------------+   offload ok   +------+---+
+ *   |              |     |                  |   (no UPSPEC)  |          |
+ *   | SA (decrypt) +----->      status      +--->------->----+  policy  |
+ *   |              |     |                  |                |          |
+ *   +--------------+     ++---------+-------+                +-^----+---+
+ *                         |         |                          |    |
+ *                         v        packet             +-->->---+    v
+ *                         |       offload ok        match           |
+ *                       fails    (with UPSPEC)        |           block
+ *                         |         |   +-------------+-+           |
+ *                         v         v   |               |  miss     v
+ *                        drop       +--->    SA sel     +--------->drop
+ *                                       |               |
+ *                                       +---------------+
+ */
+
 static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		     struct mlx5e_ipsec_rx *rx, u32 family)
 {
+	struct mlx5_flow_destination dest[2], miss_dest;
 	struct mlx5e_ipsec_rx_create_attr attr;
-	struct mlx5_flow_destination dest[2];
 	struct mlx5_flow_table *ft;
 	u32 flags = 0;
 	int err;
@@ -678,80 +1056,63 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (err)
 		return err;
 
-	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 0);
+	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 4, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_fs_ft_status;
 	}
 	rx->ft.status = ft;
 
-	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest[1].counter = rx->fc->cnt;
-	err = mlx5_ipsec_rx_status_create(ipsec, rx, dest);
+	err = ipsec_rx_sa_selector_create(ipsec, rx, &attr);
 	if (err)
-		goto err_add;
+		goto err_fs_ft_sa_sel;
 
 	/* Create FT */
 	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
-		rx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
+		rx->allow_tunnel_mode =
+			mlx5_eswitch_block_encap(mdev, rx == ipsec->rx_esw);
+
 	if (rx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
-	ft = ipsec_ft_create(attr.ns, attr.sa_level, attr.prio, 2, flags);
+	ft = ipsec_ft_create(attr.ns, attr.sa_level, attr.prio, 1, 2, flags);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_fs_ft;
 	}
 	rx->ft.sa = ft;
 
-	err = ipsec_miss_create(mdev, rx->ft.sa, &rx->sa, dest);
+	ipsec_rx_sa_miss_dest_get(ipsec, rx, &attr, &dest[0], &miss_dest);
+	err = ipsec_miss_create(mdev, rx->ft.sa, &rx->sa, &miss_dest);
 	if (err)
 		goto err_fs;
 
-	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PRIO) {
-		rx->chains = ipsec_chains_create(mdev, rx->ft.sa,
-						 attr.chains_ns,
-						 attr.prio,
-						 attr.pol_level,
-						 &rx->ft.pol);
-		if (IS_ERR(rx->chains)) {
-			err = PTR_ERR(rx->chains);
-			goto err_pol_ft;
-		}
-
-		goto connect;
-	}
+	err = ipsec_rx_policy_create(ipsec, rx, &attr, &dest[0]);
+	if (err)
+		goto err_policy;
 
-	ft = ipsec_ft_create(attr.ns, attr.pol_level, attr.prio, 2, 0);
-	if (IS_ERR(ft)) {
-		err = PTR_ERR(ft);
-		goto err_pol_ft;
-	}
-	rx->ft.pol = ft;
-	memset(dest, 0x00, 2 * sizeof(*dest));
-	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest[0].ft = rx->ft.sa;
-	err = ipsec_miss_create(mdev, rx->ft.pol, &rx->pol, dest);
+	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest[1].counter = rx->fc->cnt;
+	err = mlx5_ipsec_rx_status_create(ipsec, rx, dest);
 	if (err)
-		goto err_pol_miss;
+		goto err_add;
 
-connect:
 	/* connect */
 	if (rx != ipsec->rx_esw)
 		ipsec_rx_ft_connect(ipsec, rx, &attr);
 	return 0;
 
-err_pol_miss:
-	mlx5_destroy_flow_table(rx->ft.pol);
-err_pol_ft:
+err_add:
+	ipsec_rx_policy_destroy(rx);
+err_policy:
 	mlx5_del_flow_rules(rx->sa.rule);
 	mlx5_destroy_flow_group(rx->sa.group);
 err_fs:
 	mlx5_destroy_flow_table(rx->ft.sa);
-err_fs_ft:
 	if (rx->allow_tunnel_mode)
 		mlx5_eswitch_unblock_encap(mdev);
-	mlx5_ipsec_rx_status_destroy(ipsec, rx);
-err_add:
+err_fs_ft:
+	ipsec_rx_sa_selector_destroy(mdev, rx);
+err_fs_ft_sa_sel:
 	mlx5_destroy_flow_table(rx->ft.status);
 err_fs_ft_status:
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev);
@@ -941,7 +1302,7 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 	int err;
 
 	ipsec_tx_create_attr_set(ipsec, tx, &attr);
-	ft = ipsec_ft_create(tx->ns, attr.cnt_level, attr.prio, 1, 0);
+	ft = ipsec_ft_create(tx->ns, attr.cnt_level, attr.prio, 1, 1, 0);
 	if (IS_ERR(ft))
 		return PTR_ERR(ft);
 	tx->ft.status = ft;
@@ -951,10 +1312,12 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		goto err_status_rule;
 
 	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
-		tx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
+		tx->allow_tunnel_mode =
+			mlx5_eswitch_block_encap(mdev, tx == ipsec->tx_esw);
+
 	if (tx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
-	ft = ipsec_ft_create(tx->ns, attr.sa_level, attr.prio, 4, flags);
+	ft = ipsec_ft_create(tx->ns, attr.sa_level, attr.prio, 1, 4, flags);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_sa_ft;
@@ -982,7 +1345,7 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		goto connect_roce;
 	}
 
-	ft = ipsec_ft_create(tx->ns, attr.pol_level, attr.prio, 2, 0);
+	ft = ipsec_ft_create(tx->ns, attr.pol_level, attr.prio, 1, 2, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_pol_ft;
@@ -1150,9 +1513,14 @@ static void tx_ft_put_policy(struct mlx5e_ipsec *ipsec, u32 prio, int type)
 	mutex_unlock(&tx->ft.mutex);
 }
 
-static void setup_fte_addr4(struct mlx5_flow_spec *spec, __be32 *saddr,
-			    __be32 *daddr)
+static void setup_fte_addr4(struct mlx5_flow_spec *spec,
+			    struct mlx5e_ipsec_addr *addrs)
 {
+	__be32 *saddr = &addrs->saddr.a4;
+	__be32 *smask = &addrs->smask.m4;
+	__be32 *daddr = &addrs->daddr.a4;
+	__be32 *dmask = &addrs->dmask.m4;
+
 	if (!*saddr && !*daddr)
 		return;
 
@@ -1164,21 +1532,26 @@ static void setup_fte_addr4(struct mlx5_flow_spec *spec, __be32 *saddr,
 	if (*saddr) {
 		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4), saddr, 4);
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
-				 outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4), smask, 4);
 	}
 
 	if (*daddr) {
 		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4), daddr, 4);
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
-				 outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4), dmask, 4);
 	}
 }
 
-static void setup_fte_addr6(struct mlx5_flow_spec *spec, __be32 *saddr,
-			    __be32 *daddr)
+static void setup_fte_addr6(struct mlx5_flow_spec *spec,
+			    struct mlx5e_ipsec_addr *addrs)
 {
+	__be32 *saddr = addrs->saddr.a6;
+	__be32 *smask = addrs->smask.m6;
+	__be32 *daddr = addrs->daddr.a6;
+	__be32 *dmask = addrs->dmask.m6;
+
 	if (addr6_all_zero(saddr) && addr6_all_zero(daddr))
 		return;
 
@@ -1190,15 +1563,15 @@ static void setup_fte_addr6(struct mlx5_flow_spec *spec, __be32 *saddr,
 	if (!addr6_all_zero(saddr)) {
 		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), saddr, 16);
-		memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), 0xff, 16);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), dmask, 16);
 	}
 
 	if (!addr6_all_zero(daddr)) {
 		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), daddr, 16);
-		memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), 0xff, 16);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), smask, 16);
 	}
 }
 
@@ -1340,7 +1713,8 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8
 				 MLX5_ACTION_TYPE_SET);
 			MLX5_SET(set_action_in, action[2], field,
 				 MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
-			MLX5_SET(set_action_in, action[2], data, 0);
+			MLX5_SET(set_action_in, action[2], data,
+				 MLX5_IPSEC_ASO_SW_CRYPTO_OFFLOAD);
 			MLX5_SET(set_action_in, action[2], offset, 0);
 			MLX5_SET(set_action_in, action[2], length, 32);
 		}
@@ -1359,8 +1733,8 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8
 
 	modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, num_of_actions, action);
 	if (IS_ERR(modify_hdr)) {
-		mlx5_core_err(mdev, "Failed to allocate modify_header %ld\n",
-			      PTR_ERR(modify_hdr));
+		mlx5_core_err(mdev, "Failed to allocate modify_header %pe\n",
+			      modify_hdr);
 		return PTR_ERR(modify_hdr);
 	}
 
@@ -1387,7 +1761,7 @@ setup_pkt_tunnel_reformat(struct mlx5_core_dev *mdev,
 	if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) {
 		bfflen += sizeof(*esp_hdr) + 8;
 
-		switch (attrs->family) {
+		switch (attrs->addrs.family) {
 		case AF_INET:
 			bfflen += sizeof(*iphdr);
 			break;
@@ -1404,7 +1778,7 @@ setup_pkt_tunnel_reformat(struct mlx5_core_dev *mdev,
 		return -ENOMEM;
 
 	eth_hdr = (struct ethhdr *)reformatbf;
-	switch (attrs->family) {
+	switch (attrs->addrs.family) {
 	case AF_INET:
 		eth_hdr->h_proto = htons(ETH_P_IP);
 		break;
@@ -1427,11 +1801,11 @@ setup_pkt_tunnel_reformat(struct mlx5_core_dev *mdev,
 		reformat_params->param_0 = attrs->authsize;
 
 		hdr = reformatbf + sizeof(*eth_hdr);
-		switch (attrs->family) {
+		switch (attrs->addrs.family) {
 		case AF_INET:
 			iphdr = (struct iphdr *)hdr;
-			memcpy(&iphdr->saddr, &attrs->saddr.a4, 4);
-			memcpy(&iphdr->daddr, &attrs->daddr.a4, 4);
+			memcpy(&iphdr->saddr, &attrs->addrs.saddr.a4, 4);
+			memcpy(&iphdr->daddr, &attrs->addrs.daddr.a4, 4);
 			iphdr->version = 4;
 			iphdr->ihl = 5;
 			iphdr->ttl = IPSEC_TUNNEL_DEFAULT_TTL;
@@ -1440,8 +1814,8 @@ setup_pkt_tunnel_reformat(struct mlx5_core_dev *mdev,
 			break;
 		case AF_INET6:
 			ipv6hdr = (struct ipv6hdr *)hdr;
-			memcpy(&ipv6hdr->saddr, &attrs->saddr.a6, 16);
-			memcpy(&ipv6hdr->daddr, &attrs->daddr.a6, 16);
+			memcpy(&ipv6hdr->saddr, &attrs->addrs.saddr.a6, 16);
+			memcpy(&ipv6hdr->daddr, &attrs->addrs.daddr.a6, 16);
 			ipv6hdr->nexthdr = IPPROTO_ESP;
 			ipv6hdr->version = 6;
 			ipv6hdr->hop_limit = IPSEC_TUNNEL_DEFAULT_TTL;
@@ -1475,7 +1849,7 @@ static int get_reformat_type(struct mlx5_accel_esp_xfrm_attrs *attrs)
 			return MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT_OVER_UDP;
 		return MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT;
 	case XFRM_DEV_OFFLOAD_OUT:
-		if (attrs->family == AF_INET) {
+		if (attrs->addrs.family == AF_INET) {
 			if (attrs->encap)
 				return MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV4;
 			return MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4;
@@ -1576,6 +1950,85 @@ static int setup_pkt_reformat(struct mlx5e_ipsec *ipsec,
 	return 0;
 }
 
+static int rx_add_rule_sa_selector(struct mlx5e_ipsec_sa_entry *sa_entry,
+				   struct mlx5e_ipsec_rx *rx,
+				   struct upspec *upspec)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_destination dest[2];
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.ipsec_syndrome);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.metadata_reg_c_4);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.ipsec_syndrome, 0);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.metadata_reg_c_4, 0);
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+
+	ipsec_rx_rule_add_match_obj(sa_entry, rx, spec);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL;
+	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest[0].ft = rx->ft.sa_sel;
+	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest[1].counter = rx->fc->cnt;
+
+	rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx pass rule, err=%d\n",
+			      err);
+		goto err_add_status_pass_rule;
+	}
+
+	sa_entry->ipsec_rule.status_pass = rule;
+
+	MLX5_SET(fte_match_param, spec->match_criteria,
+		 misc_parameters_2.ipsec_syndrome, 0);
+	MLX5_SET(fte_match_param, spec->match_criteria,
+		 misc_parameters_2.metadata_reg_c_4, 0);
+
+	setup_fte_upper_proto_match(spec, upspec);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest[0].ft = rx->ft.pol;
+
+	rule = mlx5_add_flow_rules(rx->ft.sa_sel, spec, &flow_act, &dest[0], 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx sa selector rule, err=%d\n",
+			      err);
+		goto err_add_sa_sel_rule;
+	}
+
+	sa_entry->ipsec_rule.sa_sel = rule;
+
+	kvfree(spec);
+	return 0;
+
+err_add_sa_sel_rule:
+	mlx5_del_flow_rules(sa_entry->ipsec_rule.status_pass);
+err_add_status_pass_rule:
+	kvfree(spec);
+	return err;
+}
+
 static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 {
 	struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs;
@@ -1589,7 +2042,7 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	struct mlx5_fc *counter;
 	int err = 0;
 
-	rx = rx_ft_get(mdev, ipsec, attrs->family, attrs->type);
+	rx = rx_ft_get(mdev, ipsec, attrs->addrs.family, attrs->type);
 	if (IS_ERR(rx))
 		return PTR_ERR(rx);
 
@@ -1599,16 +2052,15 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		goto err_alloc;
 	}
 
-	if (attrs->family == AF_INET)
-		setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
+	if (attrs->addrs.family == AF_INET)
+		setup_fte_addr4(spec, &attrs->addrs);
 	else
-		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
+		setup_fte_addr6(spec, &attrs->addrs);
 
 	setup_fte_spi(spec, attrs->spi, attrs->encap);
 	if (!attrs->encap)
 		setup_fte_esp(spec);
 	setup_fte_no_frags(spec);
-	setup_fte_upper_proto_match(spec, &attrs->upspec);
 
 	if (!attrs->drop) {
 		if (rx != ipsec->rx_esw)
@@ -1656,6 +2108,13 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		mlx5_core_err(mdev, "fail to add RX ipsec rule err=%d\n", err);
 		goto err_add_flow;
 	}
+
+	if (attrs->upspec.proto && attrs->type == XFRM_DEV_OFFLOAD_PACKET) {
+		err = rx_add_rule_sa_selector(sa_entry, rx, &attrs->upspec);
+		if (err)
+			goto err_add_sa_sel;
+	}
+
 	if (attrs->type == XFRM_DEV_OFFLOAD_PACKET)
 		err = rx_add_rule_drop_replay(sa_entry, rx);
 	if (err)
@@ -1679,6 +2138,11 @@ err_drop_reason:
 		mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.replay.fc);
 	}
 err_add_replay:
+	if (sa_entry->ipsec_rule.sa_sel) {
+		mlx5_del_flow_rules(sa_entry->ipsec_rule.sa_sel);
+		mlx5_del_flow_rules(sa_entry->ipsec_rule.status_pass);
+	}
+err_add_sa_sel:
 	mlx5_del_flow_rules(rule);
 err_add_flow:
 	mlx5_fc_destroy(mdev, counter);
@@ -1691,7 +2155,7 @@ err_pkt_reformat:
 err_mod_header:
 	kvfree(spec);
 err_alloc:
-	rx_ft_put(ipsec, attrs->family, attrs->type);
+	rx_ft_put(ipsec, attrs->addrs.family, attrs->type);
 	return err;
 }
 
@@ -1718,23 +2182,21 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		goto err_alloc;
 	}
 
-	if (attrs->family == AF_INET)
-		setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
-	else
-		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
-
 	setup_fte_no_frags(spec);
 	setup_fte_upper_proto_match(spec, &attrs->upspec);
 
 	switch (attrs->type) {
 	case XFRM_DEV_OFFLOAD_CRYPTO:
+		if (attrs->addrs.family == AF_INET)
+			setup_fte_addr4(spec, &attrs->addrs);
+		else
+			setup_fte_addr6(spec, &attrs->addrs);
 		setup_fte_spi(spec, attrs->spi, false);
 		setup_fte_esp(spec);
 		setup_fte_reg_a(spec);
 		break;
 	case XFRM_DEV_OFFLOAD_PACKET:
-		if (attrs->reqid)
-			setup_fte_reg_c4(spec, attrs->reqid);
+		setup_fte_reg_c4(spec, attrs->reqid);
 		err = setup_pkt_reformat(ipsec, attrs, &flow_act);
 		if (err)
 			goto err_pkt_reformat;
@@ -1812,10 +2274,10 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	}
 
 	tx = ipsec_tx(ipsec, attrs->type);
-	if (attrs->family == AF_INET)
-		setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
+	if (attrs->addrs.family == AF_INET)
+		setup_fte_addr4(spec, &attrs->addrs);
 	else
-		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
+		setup_fte_addr6(spec, &attrs->addrs);
 
 	setup_fte_no_frags(spec);
 	setup_fte_upper_proto_match(spec, &attrs->upspec);
@@ -1885,12 +2347,12 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	struct mlx5e_ipsec_rx *rx;
 	int err, dstn = 0;
 
-	ft = rx_ft_get_policy(mdev, pol_entry->ipsec, attrs->family, attrs->prio,
-			      attrs->type);
+	ft = rx_ft_get_policy(mdev, pol_entry->ipsec, attrs->addrs.family,
+			      attrs->prio, attrs->type);
 	if (IS_ERR(ft))
 		return PTR_ERR(ft);
 
-	rx = ipsec_rx(pol_entry->ipsec, attrs->family, attrs->type);
+	rx = ipsec_rx(pol_entry->ipsec, attrs->addrs.family, attrs->type);
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec) {
@@ -1898,10 +2360,10 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 		goto err_alloc;
 	}
 
-	if (attrs->family == AF_INET)
-		setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
+	if (attrs->addrs.family == AF_INET)
+		setup_fte_addr4(spec, &attrs->addrs);
 	else
-		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
+		setup_fte_addr6(spec, &attrs->addrs);
 
 	setup_fte_no_frags(spec);
 	setup_fte_upper_proto_match(spec, &attrs->upspec);
@@ -1925,8 +2387,7 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	flow_act.flags |= FLOW_ACT_NO_APPEND;
 	if (rx == ipsec->rx_esw && rx->chains)
 		flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
-	dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest[dstn].ft = rx->ft.sa;
+	ipsec_rx_default_dest_get(ipsec, rx, &dest[dstn]);
 	dstn++;
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, dstn);
 	if (IS_ERR(rule)) {
@@ -1942,7 +2403,8 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 err_action:
 	kvfree(spec);
 err_alloc:
-	rx_ft_put_policy(pol_entry->ipsec, attrs->family, attrs->prio, attrs->type);
+	rx_ft_put_policy(pol_entry->ipsec, attrs->addrs.family, attrs->prio,
+			 attrs->type);
 	return err;
 }
 
@@ -2063,6 +2525,7 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats)
 	stats->ipsec_rx_bytes = 0;
 	stats->ipsec_rx_drop_pkts = 0;
 	stats->ipsec_rx_drop_bytes = 0;
+	stats->ipsec_rx_drop_mismatch_sa_sel = 0;
 	stats->ipsec_tx_pkts = 0;
 	stats->ipsec_tx_bytes = 0;
 	stats->ipsec_tx_drop_pkts = 0;
@@ -2072,6 +2535,9 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats)
 	mlx5_fc_query(mdev, fc->cnt, &stats->ipsec_rx_pkts, &stats->ipsec_rx_bytes);
 	mlx5_fc_query(mdev, fc->drop, &stats->ipsec_rx_drop_pkts,
 		      &stats->ipsec_rx_drop_bytes);
+	if (ipsec->rx_ipv4->sa_sel.fc)
+		mlx5_fc_query(mdev, ipsec->rx_ipv4->sa_sel.fc,
+			      &stats->ipsec_rx_drop_mismatch_sa_sel, &bytes);
 
 	fc = ipsec->tx->fc;
 	mlx5_fc_query(mdev, fc->cnt, &stats->ipsec_tx_pkts, &stats->ipsec_tx_bytes);
@@ -2100,6 +2566,11 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats)
 			stats->ipsec_tx_drop_pkts += packets;
 			stats->ipsec_tx_drop_bytes += bytes;
 		}
+
+		if (ipsec->rx_esw->sa_sel.fc &&
+		    !mlx5_fc_query(mdev, ipsec->rx_esw->sa_sel.fc,
+				   &packets, &bytes))
+			stats->ipsec_rx_drop_mismatch_sa_sel += packets;
 	}
 }
 
@@ -2197,12 +2668,18 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	mlx5_del_flow_rules(ipsec_rule->auth.rule);
 	mlx5_fc_destroy(mdev, ipsec_rule->auth.fc);
 
+	if (ipsec_rule->sa_sel) {
+		mlx5_del_flow_rules(ipsec_rule->sa_sel);
+		mlx5_del_flow_rules(ipsec_rule->status_pass);
+	}
+
 	if (ipsec_rule->replay.rule) {
 		mlx5_del_flow_rules(ipsec_rule->replay.rule);
 		mlx5_fc_destroy(mdev, ipsec_rule->replay.fc);
 	}
 	mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry);
-	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type);
+	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.addrs.family,
+		  sa_entry->attrs.type);
 }
 
 int mlx5e_accel_ipsec_fs_add_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
@@ -2238,7 +2715,8 @@ void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
 	mlx5e_ipsec_unblock_tc_offload(pol_entry->ipsec->mdev);
 
 	if (pol_entry->attrs.dir == XFRM_DEV_OFFLOAD_IN) {
-		rx_ft_put_policy(pol_entry->ipsec, pol_entry->attrs.family,
+		rx_ft_put_policy(pol_entry->ipsec,
+				 pol_entry->attrs.addrs.family,
 				 pol_entry->attrs.prio, pol_entry->attrs.type);
 		return;
 	}
@@ -2372,18 +2850,24 @@ void mlx5e_accel_ipsec_fs_modify(struct mlx5e_ipsec_sa_entry *sa_entry)
 	memcpy(sa_entry, &sa_entry_shadow, sizeof(*sa_entry));
 }
 
-bool mlx5e_ipsec_fs_tunnel_enabled(struct mlx5e_ipsec_sa_entry *sa_entry)
+bool mlx5e_ipsec_fs_tunnel_allowed(struct mlx5e_ipsec_sa_entry *sa_entry)
 {
-	struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs;
-	struct mlx5e_ipsec_rx *rx;
-	struct mlx5e_ipsec_tx *tx;
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct xfrm_state *x = sa_entry->x;
+	bool from_fdb;
 
-	rx = ipsec_rx(sa_entry->ipsec, attrs->family, attrs->type);
-	tx = ipsec_tx(sa_entry->ipsec, attrs->type);
-	if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT)
-		return tx->allow_tunnel_mode;
+	if (x->xso.dir == XFRM_DEV_OFFLOAD_OUT) {
+		struct mlx5e_ipsec_tx *tx = ipsec_tx(ipsec, x->xso.type);
+
+		from_fdb = (tx == ipsec->tx_esw);
+	} else {
+		struct mlx5e_ipsec_rx *rx = ipsec_rx(ipsec, x->props.family,
+						     x->xso.type);
+
+		from_fdb = (rx == ipsec->rx_esw);
+	}
 
-	return rx->allow_tunnel_mode;
+	return mlx5_eswitch_block_encap(ipsec->mdev, from_fdb);
 }
 
 void mlx5e_ipsec_handle_mpv_event(int event, struct mlx5e_priv *slave_priv,
@@ -2409,9 +2893,30 @@ void mlx5e_ipsec_handle_mpv_event(int event, struct mlx5e_priv *slave_priv,
 
 void mlx5e_ipsec_send_event(struct mlx5e_priv *priv, int event)
 {
-	if (!priv->ipsec)
-		return; /* IPsec not supported */
+	if (!priv->ipsec || mlx5_devcom_comp_get_size(priv->devcom) < 2)
+		return; /* IPsec not supported or no peers */
 
 	mlx5_devcom_send_event(priv->devcom, event, event, priv);
 	wait_for_completion(&priv->ipsec->comp);
 }
+
+void mlx5e_ipsec_disable_events(struct mlx5e_priv *priv)
+{
+	struct mlx5_devcom_comp_dev *tmp = NULL;
+	struct mlx5e_priv *peer_priv;
+
+	if (!priv->devcom)
+		return;
+
+	if (!mlx5_devcom_for_each_peer_begin(priv->devcom))
+		goto out;
+
+	peer_priv = mlx5_devcom_get_next_peer_data(priv->devcom, &tmp);
+	if (peer_priv)
+		complete_all(&peer_priv->ipsec->comp);
+
+	mlx5_devcom_for_each_peer_end(priv->devcom);
+out:
+	mlx5_devcom_unregister_component(priv->devcom);
+	priv->devcom = NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 53cfa39188cb..ef7322d381af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -42,8 +42,7 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 
 	if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload) &&
 	    (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS ||
-	     (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS &&
-	     is_mdev_legacy_mode(mdev)))) {
+	     is_mdev_legacy_mode(mdev))) {
 		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,
 					      reformat_add_esp_trasport) &&
 		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
@@ -91,8 +90,9 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 EXPORT_SYMBOL_GPL(mlx5_ipsec_device_caps);
 
 static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn,
-				     struct mlx5_accel_esp_xfrm_attrs *attrs)
+				     struct mlx5e_ipsec_sa_entry *sa_entry)
 {
+	struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs;
 	void *aso_ctx;
 
 	aso_ctx = MLX5_ADDR_OF(ipsec_obj, obj, ipsec_aso);
@@ -120,8 +120,12 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn,
 	 * active.
 	 */
 	MLX5_SET(ipsec_obj, obj, aso_return_reg, MLX5_IPSEC_ASO_REG_C_4_5);
-	if (attrs->dir == XFRM_DEV_OFFLOAD_OUT)
+	if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) {
 		MLX5_SET(ipsec_aso, aso_ctx, mode, MLX5_IPSEC_ASO_INC_SN);
+		if (!attrs->replay_esn.trigger)
+			MLX5_SET(ipsec_aso, aso_ctx, mode_parameter,
+				 sa_entry->esn_state.esn);
+	}
 
 	if (attrs->lft.hard_packet_limit != XFRM_INF) {
 		MLX5_SET(ipsec_aso, aso_ctx, remove_flow_pkt_cnt,
@@ -175,7 +179,7 @@ static int mlx5_create_ipsec_obj(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 	res = &mdev->mlx5e_res.hw_objs;
 	if (attrs->type == XFRM_DEV_OFFLOAD_PACKET)
-		mlx5e_ipsec_packet_setup(obj, res->pdn, attrs);
+		mlx5e_ipsec_packet_setup(obj, res->pdn, sa_entry);
 
 	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 	if (!err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 727fa7c18523..6056106edcc6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -327,6 +327,10 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 	if (unlikely(!sa_entry)) {
 		rcu_read_unlock();
 		atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_sadb_miss);
+		/* Clear secpath to prevent invalid dereference
+		 * in downstream XFRM policy checks.
+		 */
+		secpath_reset(skb);
 		return;
 	}
 	xfrm_state_hold(sa_entry->x);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index 3cc640669247..45b0d19e735c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -40,7 +40,7 @@
 #include "en/txrx.h"
 
 /* Bit31: IPsec marker, Bit30: reserved, Bit29-24: IPsec syndrome, Bit23-0: IPsec obj id */
-#define MLX5_IPSEC_METADATA_MARKER(metadata)  (((metadata) >> 31) & 0x1)
+#define MLX5_IPSEC_METADATA_MARKER(metadata)  ((((metadata) >> 30) & 0x3) == 0x2)
 #define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(5, 0))
 #define MLX5_IPSEC_METADATA_HANDLE(metadata)  ((metadata) & GENMASK(23, 0))
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
index 92bf3fa44a3b..93be388068f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
@@ -42,6 +42,7 @@ static const struct counter_desc mlx5e_ipsec_hw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_drop_pkts) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_drop_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_drop_mismatch_sa_sel) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_tx_pkts) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_tx_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_tx_drop_pkts) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index 65ccb33edafb..da2d1eb52c13 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -320,7 +320,6 @@ err_dma_unmap:
 err_free:
 	kfree(buf);
 err_out:
-	priv_rx->rq_stats->tls_resync_req_skip++;
 	return err;
 }
 
@@ -339,14 +338,19 @@ static void resync_handle_work(struct work_struct *work)
 
 	if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags))) {
 		mlx5e_ktls_priv_rx_put(priv_rx);
+		priv_rx->rq_stats->tls_resync_req_skip++;
+		tls_offload_rx_resync_async_request_cancel(&resync->core);
 		return;
 	}
 
 	c = resync->priv->channels.c[priv_rx->rxq];
 	sq = &c->async_icosq;
 
-	if (resync_post_get_progress_params(sq, priv_rx))
+	if (resync_post_get_progress_params(sq, priv_rx)) {
+		priv_rx->rq_stats->tls_resync_req_skip++;
+		tls_offload_rx_resync_async_request_cancel(&resync->core);
 		mlx5e_ktls_priv_rx_put(priv_rx);
+	}
 }
 
 static void resync_init(struct mlx5e_ktls_rx_resync_ctx *resync,
@@ -425,14 +429,21 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 {
 	struct mlx5e_ktls_rx_resync_buf *buf = wi->tls_get_params.buf;
 	struct mlx5e_ktls_offload_context_rx *priv_rx;
+	struct tls_offload_resync_async *async_resync;
+	struct tls_offload_context_rx *rx_ctx;
 	u8 tracker_state, auth_state, *ctx;
 	struct device *dev;
 	u32 hw_seq;
 
 	priv_rx = buf->priv_rx;
 	dev = mlx5_core_dma_dev(sq->channel->mdev);
-	if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags)))
+	rx_ctx = tls_offload_ctx_rx(tls_get_ctx(priv_rx->sk));
+	async_resync = rx_ctx->resync_async;
+	if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags))) {
+		priv_rx->rq_stats->tls_resync_req_skip++;
+		tls_offload_rx_resync_async_request_cancel(async_resync);
 		goto out;
+	}
 
 	dma_sync_single_for_cpu(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE,
 				DMA_FROM_DEVICE);
@@ -443,11 +454,13 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 	if (tracker_state != MLX5E_TLS_PROGRESS_PARAMS_RECORD_TRACKER_STATE_TRACKING ||
 	    auth_state != MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_NO_OFFLOAD) {
 		priv_rx->rq_stats->tls_resync_req_skip++;
+		tls_offload_rx_resync_async_request_cancel(async_resync);
 		goto out;
 	}
 
 	hw_seq = MLX5_GET(tls_progress_params, ctx, hw_resync_tcp_sn);
-	tls_offload_rx_resync_async_request_end(priv_rx->sk, cpu_to_be32(hw_seq));
+	tls_offload_rx_resync_async_request_end(async_resync,
+						cpu_to_be32(hw_seq));
 	priv_rx->rq_stats->tls_resync_req_end++;
 out:
 	mlx5e_ktls_priv_rx_put(priv_rx);
@@ -472,8 +485,10 @@ static bool resync_queue_get_psv(struct sock *sk)
 
 	resync = &priv_rx->resync;
 	mlx5e_ktls_priv_rx_get(priv_rx);
-	if (unlikely(!queue_work(resync->priv->tls->rx_wq, &resync->work)))
+	if (unlikely(!queue_work(resync->priv->tls->rx_wq, &resync->work))) {
 		mlx5e_ktls_priv_rx_put(priv_rx);
+		return false;
+	}
 
 	return true;
 }
@@ -482,6 +497,7 @@ static bool resync_queue_get_psv(struct sock *sk)
 static void resync_update_sn(struct mlx5e_rq *rq, struct sk_buff *skb)
 {
 	struct ethhdr *eth = (struct ethhdr *)(skb->data);
+	struct tls_offload_resync_async *resync_async;
 	struct net_device *netdev = rq->netdev;
 	struct net *net = dev_net(netdev);
 	struct sock *sk = NULL;
@@ -498,9 +514,9 @@ static void resync_update_sn(struct mlx5e_rq *rq, struct sk_buff *skb)
 		depth += sizeof(struct iphdr);
 		th = (void *)iph + sizeof(struct iphdr);
 
-		sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
-					     iph->saddr, th->source, iph->daddr,
-					     th->dest, netdev->ifindex);
+		sk = inet_lookup_established(net, iph->saddr, th->source,
+					     iph->daddr, th->dest,
+					     netdev->ifindex);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
 		struct ipv6hdr *ipv6h = (struct ipv6hdr *)iph;
@@ -508,8 +524,7 @@ static void resync_update_sn(struct mlx5e_rq *rq, struct sk_buff *skb)
 		depth += sizeof(struct ipv6hdr);
 		th = (void *)ipv6h + sizeof(struct ipv6hdr);
 
-		sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
-						&ipv6h->saddr, th->source,
+		sk = __inet6_lookup_established(net, &ipv6h->saddr, th->source,
 						&ipv6h->daddr, ntohs(th->dest),
 						netdev->ifindex, 0);
 #endif
@@ -528,7 +543,8 @@ static void resync_update_sn(struct mlx5e_rq *rq, struct sk_buff *skb)
 
 	seq = th->seq;
 	datalen = skb->len - depth;
-	tls_offload_rx_resync_async_request_start(sk, seq, datalen);
+	resync_async = tls_offload_ctx_rx(tls_get_ctx(sk))->resync_async;
+	tls_offload_rx_resync_async_request_start(resync_async, seq, datalen);
 	rq->stats->tls_resync_req_start++;
 
 unref:
@@ -557,6 +573,18 @@ void mlx5e_ktls_rx_resync(struct net_device *netdev, struct sock *sk,
 	resync_handle_seq_match(priv_rx, c);
 }
 
+void
+mlx5e_ktls_rx_resync_async_request_cancel(struct mlx5e_icosq_wqe_info *wi)
+{
+	struct mlx5e_ktls_offload_context_rx *priv_rx;
+	struct mlx5e_ktls_rx_resync_buf *buf;
+
+	buf = wi->tls_get_params.buf;
+	priv_rx = buf->priv_rx;
+	priv_rx->rq_stats->tls_resync_req_skip++;
+	tls_offload_rx_resync_async_request_cancel(&priv_rx->resync.core);
+}
+
 /* End of resync section */
 
 void mlx5e_ktls_handle_rx_skb(struct mlx5e_rq *rq, struct sk_buff *skb,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 3db31cc10719..08f06984407b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -744,7 +744,7 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn)
 	dseg->addr       = cpu_to_be64(dma_addr);
 	dseg->lkey       = sq->mkey_be;
 	dseg->byte_count = cpu_to_be32(fsz);
-	mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE);
+	mlx5e_dma_push_netmem(sq, skb_frag_netmem(frag), dma_addr, fsz);
 
 	tx_fill_wi(sq, pi, MLX5E_KTLS_DUMP_WQEBBS, fsz, skb_frag_page(frag));
 	sq->pc += MLX5E_KTLS_DUMP_WQEBBS;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h
index f87b65c560ea..cb08799769ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h
@@ -29,6 +29,10 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 					   struct mlx5e_tx_wqe_info *wi,
 					   u32 *dma_fifo_cc);
+
+void
+mlx5e_ktls_rx_resync_async_request_cancel(struct mlx5e_icosq_wqe_info *wi);
+
 static inline bool
 mlx5e_ktls_tx_try_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 					  struct mlx5e_tx_wqe_info *wi,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index cc9bcc420032..528b04d4de41 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -339,9 +339,13 @@ static int mlx5e_macsec_init_sa_fs(struct macsec_context *ctx,
 {
 	struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev);
 	struct mlx5_macsec_fs *macsec_fs = priv->mdev->macsec_fs;
+	const struct macsec_tx_sc *tx_sc = &ctx->secy->tx_sc;
 	struct mlx5_macsec_rule_attrs rule_attrs;
 	union mlx5_macsec_rule *macsec_rule;
 
+	if (is_tx && tx_sc->encoding_sa != sa->assoc_num)
+		return 0;
+
 	rule_attrs.macsec_obj_id = sa->macsec_obj_id;
 	rule_attrs.sci = sa->sci;
 	rule_attrs.assoc_num = sa->assoc_num;
@@ -1672,7 +1676,7 @@ void mlx5e_macsec_tx_build_eseg(struct mlx5e_macsec *macsec,
 	if (!fs_id)
 		return;
 
-	eseg->flow_table_metadata = cpu_to_be32(MLX5_ETH_WQE_FT_META_MACSEC | fs_id << 2);
+	eseg->flow_table_metadata = cpu_to_be32(MLX5_MACSEC_TX_METADATA(fs_id));
 }
 
 void mlx5e_macsec_offload_handle_rx_skb(struct net_device *netdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c
new file mode 100644
index 000000000000..38e7c77cc851
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c
@@ -0,0 +1,1155 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+#include <linux/mlx5/device.h>
+#include <net/psp.h>
+#include <linux/psp.h>
+#include "mlx5_core.h"
+#include "psp.h"
+#include "lib/crypto.h"
+#include "en_accel/psp.h"
+#include "fs_core.h"
+
+enum accel_fs_psp_type {
+	ACCEL_FS_PSP4,
+	ACCEL_FS_PSP6,
+	ACCEL_FS_PSP_NUM_TYPES,
+};
+
+enum accel_psp_syndrome {
+	PSP_OK = 0,
+	PSP_ICV_FAIL,
+	PSP_BAD_TRAILER,
+};
+
+struct mlx5e_psp_tx {
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *fg;
+	struct mlx5_flow_handle *rule;
+	struct mutex mutex; /* Protect PSP TX steering */
+	u32 refcnt;
+	struct mlx5_fc *tx_counter;
+};
+
+struct mlx5e_psp_rx_err {
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_handle *auth_fail_rule;
+	struct mlx5_flow_handle *err_rule;
+	struct mlx5_flow_handle *bad_rule;
+	struct mlx5_modify_hdr *copy_modify_hdr;
+};
+
+struct mlx5e_accel_fs_psp_prot {
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *miss_group;
+	struct mlx5_flow_handle *miss_rule;
+	struct mlx5_flow_destination default_dest;
+	struct mlx5e_psp_rx_err rx_err;
+	u32 refcnt;
+	struct mutex prot_mutex; /* protect ESP4/ESP6 protocol */
+	struct mlx5_flow_handle *def_rule;
+};
+
+struct mlx5e_accel_fs_psp {
+	struct mlx5e_accel_fs_psp_prot fs_prot[ACCEL_FS_PSP_NUM_TYPES];
+	struct mlx5_fc *rx_counter;
+	struct mlx5_fc *rx_auth_fail_counter;
+	struct mlx5_fc *rx_err_counter;
+	struct mlx5_fc *rx_bad_counter;
+};
+
+struct mlx5e_psp_fs {
+	struct mlx5_core_dev *mdev;
+	struct mlx5e_psp_tx *tx_fs;
+	/* Rx manage */
+	struct mlx5e_flow_steering *fs;
+	struct mlx5e_accel_fs_psp *rx_fs;
+};
+
+/* PSP RX flow steering */
+static enum mlx5_traffic_types fs_psp2tt(enum accel_fs_psp_type i)
+{
+	if (i == ACCEL_FS_PSP4)
+		return MLX5_TT_IPV4_UDP;
+
+	return MLX5_TT_IPV6_UDP;
+}
+
+static void accel_psp_fs_rx_err_del_rules(struct mlx5e_psp_fs *fs,
+					  struct mlx5e_psp_rx_err *rx_err)
+{
+	if (rx_err->bad_rule) {
+		mlx5_del_flow_rules(rx_err->bad_rule);
+		rx_err->bad_rule = NULL;
+	}
+
+	if (rx_err->err_rule) {
+		mlx5_del_flow_rules(rx_err->err_rule);
+		rx_err->err_rule = NULL;
+	}
+
+	if (rx_err->auth_fail_rule) {
+		mlx5_del_flow_rules(rx_err->auth_fail_rule);
+		rx_err->auth_fail_rule = NULL;
+	}
+
+	if (rx_err->rule) {
+		mlx5_del_flow_rules(rx_err->rule);
+		rx_err->rule = NULL;
+	}
+
+	if (rx_err->copy_modify_hdr) {
+		mlx5_modify_header_dealloc(fs->mdev, rx_err->copy_modify_hdr);
+		rx_err->copy_modify_hdr = NULL;
+	}
+}
+
+static void accel_psp_fs_rx_err_destroy_ft(struct mlx5e_psp_fs *fs,
+					   struct mlx5e_psp_rx_err *rx_err)
+{
+	accel_psp_fs_rx_err_del_rules(fs, rx_err);
+
+	if (rx_err->ft) {
+		mlx5_destroy_flow_table(rx_err->ft);
+		rx_err->ft = NULL;
+	}
+}
+
+static void accel_psp_setup_syndrome_match(struct mlx5_flow_spec *spec,
+					   enum accel_psp_syndrome syndrome)
+{
+	void *misc_params_2;
+
+	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+	misc_params_2 = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2);
+	MLX5_SET_TO_ONES(fte_match_set_misc2, misc_params_2, psp_syndrome);
+	misc_params_2 = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2);
+	MLX5_SET(fte_match_set_misc2, misc_params_2, psp_syndrome, syndrome);
+}
+
+static int accel_psp_fs_rx_err_add_rule(struct mlx5e_psp_fs *fs,
+					struct mlx5e_accel_fs_psp_prot *fs_prot,
+					struct mlx5e_psp_rx_err *rx_err)
+{
+	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	struct mlx5_core_dev *mdev = fs->mdev;
+	struct mlx5_flow_destination dest[2];
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_modify_hdr *modify_hdr;
+	struct mlx5_flow_handle *fte;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	spec = kzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	/* Action to copy 7 bit psp_syndrome to regB[23:29] */
+	MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY);
+	MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_PSP_SYNDROME);
+	MLX5_SET(copy_action_in, action, src_offset, 0);
+	MLX5_SET(copy_action_in, action, length, 7);
+	MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
+	MLX5_SET(copy_action_in, action, dst_offset, 23);
+
+	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL,
+					      1, action);
+	if (IS_ERR(modify_hdr)) {
+		err = PTR_ERR(modify_hdr);
+		mlx5_core_err(mdev,
+			      "fail to alloc psp copy modify_header_id err=%d\n", err);
+		goto out_spec;
+	}
+
+	accel_psp_setup_syndrome_match(spec, PSP_OK);
+	/* create fte */
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
+			  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	flow_act.modify_hdr = modify_hdr;
+	dest[0].type = fs_prot->default_dest.type;
+	dest[0].ft = fs_prot->default_dest.ft;
+	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest[1].counter = fs->rx_fs->rx_counter;
+	fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, dest, 2);
+	if (IS_ERR(fte)) {
+		err = PTR_ERR(fte);
+		mlx5_core_err(mdev, "fail to add psp rx err copy rule err=%d\n", err);
+		goto out;
+	}
+	rx_err->rule = fte;
+
+	/* add auth fail drop rule */
+	memset(spec, 0, sizeof(*spec));
+	memset(&flow_act, 0, sizeof(flow_act));
+	accel_psp_setup_syndrome_match(spec, PSP_ICV_FAIL);
+	/* create fte */
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP |
+			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest[0].counter = fs->rx_fs->rx_auth_fail_counter;
+	fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, dest, 1);
+	if (IS_ERR(fte)) {
+		err = PTR_ERR(fte);
+		mlx5_core_err(mdev, "fail to add psp rx auth fail drop rule err=%d\n",
+			      err);
+		goto out_drop_rule;
+	}
+	rx_err->auth_fail_rule = fte;
+
+	/* add framing drop rule */
+	memset(spec, 0, sizeof(*spec));
+	memset(&flow_act, 0, sizeof(flow_act));
+	accel_psp_setup_syndrome_match(spec, PSP_BAD_TRAILER);
+	/* create fte */
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP |
+			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest[0].counter = fs->rx_fs->rx_err_counter;
+	fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, dest, 1);
+	if (IS_ERR(fte)) {
+		err = PTR_ERR(fte);
+		mlx5_core_err(mdev, "fail to add psp rx framing err drop rule err=%d\n",
+			      err);
+		goto out_drop_auth_fail_rule;
+	}
+	rx_err->err_rule = fte;
+
+	/* add misc. errors drop rule */
+	memset(spec, 0, sizeof(*spec));
+	memset(&flow_act, 0, sizeof(flow_act));
+	/* create fte */
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP |
+			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest[0].counter = fs->rx_fs->rx_bad_counter;
+	fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, dest, 1);
+	if (IS_ERR(fte)) {
+		err = PTR_ERR(fte);
+		mlx5_core_err(mdev, "fail to add psp rx misc. err drop rule err=%d\n",
+			      err);
+		goto out_drop_error_rule;
+	}
+	rx_err->bad_rule = fte;
+
+	rx_err->copy_modify_hdr = modify_hdr;
+
+	goto out_spec;
+
+out_drop_error_rule:
+	mlx5_del_flow_rules(rx_err->err_rule);
+	rx_err->err_rule = NULL;
+out_drop_auth_fail_rule:
+	mlx5_del_flow_rules(rx_err->auth_fail_rule);
+	rx_err->auth_fail_rule = NULL;
+out_drop_rule:
+	mlx5_del_flow_rules(rx_err->rule);
+	rx_err->rule = NULL;
+out:
+	mlx5_modify_header_dealloc(mdev, modify_hdr);
+out_spec:
+	kfree(spec);
+	return err;
+}
+
+static int accel_psp_fs_rx_err_create_ft(struct mlx5e_psp_fs *fs,
+					 struct mlx5e_accel_fs_psp_prot *fs_prot,
+					 struct mlx5e_psp_rx_err *rx_err)
+{
+	struct mlx5_flow_namespace *ns = mlx5e_fs_get_ns(fs->fs, false);
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_flow_table *ft;
+	int err;
+
+	ft_attr.max_fte = 2;
+	ft_attr.autogroup.max_num_groups = 2;
+	ft_attr.level = MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL; // MLX5E_ACCEL_FS_TCP_FT_LEVEL
+	ft_attr.prio = MLX5E_NIC_PRIO;
+	ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		mlx5_core_err(fs->mdev, "fail to create psp rx inline ft err=%d\n", err);
+		return err;
+	}
+
+	rx_err->ft = ft;
+	err = accel_psp_fs_rx_err_add_rule(fs, fs_prot, rx_err);
+	if (err)
+		goto out_err;
+
+	return 0;
+
+out_err:
+	mlx5_destroy_flow_table(ft);
+	rx_err->ft = NULL;
+	return err;
+}
+
+static void accel_psp_fs_rx_fs_destroy(struct mlx5e_accel_fs_psp_prot *fs_prot)
+{
+	if (fs_prot->def_rule) {
+		mlx5_del_flow_rules(fs_prot->def_rule);
+		fs_prot->def_rule = NULL;
+	}
+
+	if (fs_prot->miss_rule) {
+		mlx5_del_flow_rules(fs_prot->miss_rule);
+		fs_prot->miss_rule = NULL;
+	}
+
+	if (fs_prot->miss_group) {
+		mlx5_destroy_flow_group(fs_prot->miss_group);
+		fs_prot->miss_group = NULL;
+	}
+
+	if (fs_prot->ft) {
+		mlx5_destroy_flow_table(fs_prot->ft);
+		fs_prot->ft = NULL;
+	}
+}
+
+static void setup_fte_udp_psp(struct mlx5_flow_spec *spec, u16 udp_port)
+{
+	spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
+	MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria, udp_dport, 0xffff);
+	MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, udp_dport, udp_port);
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, spec->match_criteria, ip_protocol);
+	MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, ip_protocol, IPPROTO_UDP);
+}
+
+static int accel_psp_fs_rx_create_ft(struct mlx5e_psp_fs *fs,
+				     struct mlx5e_accel_fs_psp_prot *fs_prot)
+{
+	struct mlx5_flow_namespace *ns = mlx5e_fs_get_ns(fs->fs, false);
+	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_modify_hdr *modify_hdr = NULL;
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_core_dev *mdev = fs->mdev;
+	struct mlx5_flow_group *miss_group;
+	MLX5_DECLARE_FLOW_ACT(flow_act);
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	struct mlx5_flow_table *ft;
+	u32 *flow_group_in;
+	int err = 0;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!flow_group_in || !spec) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	/* Create FT */
+	ft_attr.max_fte = 2;
+	ft_attr.level = MLX5E_ACCEL_FS_ESP_FT_LEVEL;
+	ft_attr.prio = MLX5E_NIC_PRIO;
+	ft_attr.autogroup.num_reserved_entries = 1;
+	ft_attr.autogroup.max_num_groups = 1;
+	ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		mlx5_core_err(mdev, "fail to create psp rx ft err=%d\n", err);
+		goto out_err;
+	}
+	fs_prot->ft = ft;
+
+	/* Create miss_group */
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1);
+	miss_group = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(miss_group)) {
+		err = PTR_ERR(miss_group);
+		mlx5_core_err(mdev, "fail to create psp rx miss_group err=%d\n", err);
+		goto out_err;
+	}
+	fs_prot->miss_group = miss_group;
+
+	/* Create miss rule */
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &fs_prot->default_dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev, "fail to create psp rx miss_rule err=%d\n", err);
+		goto out_err;
+	}
+	fs_prot->miss_rule = rule;
+
+	/* Add default Rx psp rule */
+	setup_fte_udp_psp(spec, PSP_DEFAULT_UDP_PORT);
+	flow_act.crypto.type = MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_PSP;
+	/* Set bit[31, 30] PSP marker */
+	/* Set bit[29-23] psp_syndrome is set in error FT */
+#define MLX5E_PSP_MARKER_BIT (BIT(30) | BIT(31))
+	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
+	MLX5_SET(set_action_in, action, data, MLX5E_PSP_MARKER_BIT);
+	MLX5_SET(set_action_in, action, offset, 0);
+	MLX5_SET(set_action_in, action, length, 32);
+
+	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL, 1, action);
+	if (IS_ERR(modify_hdr)) {
+		err = PTR_ERR(modify_hdr);
+		mlx5_core_err(mdev, "fail to alloc psp set modify_header_id err=%d\n", err);
+		modify_hdr = NULL;
+		goto out_err;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+			  MLX5_FLOW_CONTEXT_ACTION_CRYPTO_DECRYPT |
+			  MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+	flow_act.modify_hdr = modify_hdr;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest.ft = fs_prot->rx_err.ft;
+	rule = mlx5_add_flow_rules(fs_prot->ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "fail to add psp rule Rx decryption, err=%d, flow_act.action = %#04X\n",
+			      err, flow_act.action);
+		goto out_err;
+	}
+
+	fs_prot->def_rule = rule;
+	goto out;
+
+out_err:
+	accel_psp_fs_rx_fs_destroy(fs_prot);
+out:
+	kvfree(flow_group_in);
+	kvfree(spec);
+	return err;
+}
+
+static int accel_psp_fs_rx_destroy(struct mlx5e_psp_fs *fs, enum accel_fs_psp_type type)
+{
+	struct mlx5e_accel_fs_psp_prot *fs_prot;
+	struct mlx5e_accel_fs_psp *accel_psp;
+
+	accel_psp = fs->rx_fs;
+
+	/* The netdev unreg already happened, so all offloaded rule are already removed */
+	fs_prot = &accel_psp->fs_prot[type];
+
+	accel_psp_fs_rx_fs_destroy(fs_prot);
+
+	accel_psp_fs_rx_err_destroy_ft(fs, &fs_prot->rx_err);
+
+	return 0;
+}
+
+static int accel_psp_fs_rx_create(struct mlx5e_psp_fs *fs, enum accel_fs_psp_type type)
+{
+	struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(fs->fs, false);
+	struct mlx5e_accel_fs_psp_prot *fs_prot;
+	struct mlx5e_accel_fs_psp *accel_psp;
+	int err;
+
+	accel_psp = fs->rx_fs;
+	fs_prot = &accel_psp->fs_prot[type];
+
+	fs_prot->default_dest = mlx5_ttc_get_default_dest(ttc, fs_psp2tt(type));
+
+	err = accel_psp_fs_rx_err_create_ft(fs, fs_prot, &fs_prot->rx_err);
+	if (err)
+		return err;
+
+	err = accel_psp_fs_rx_create_ft(fs, fs_prot);
+	if (err)
+		accel_psp_fs_rx_err_destroy_ft(fs, &fs_prot->rx_err);
+
+	return err;
+}
+
+static int accel_psp_fs_rx_ft_get(struct mlx5e_psp_fs *fs, enum accel_fs_psp_type type)
+{
+	struct mlx5e_accel_fs_psp_prot *fs_prot;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5e_accel_fs_psp *accel_psp;
+	struct mlx5_ttc_table *ttc;
+	int err = 0;
+
+	if (!fs || !fs->rx_fs)
+		return -EINVAL;
+
+	ttc = mlx5e_fs_get_ttc(fs->fs, false);
+	accel_psp = fs->rx_fs;
+	fs_prot = &accel_psp->fs_prot[type];
+	mutex_lock(&fs_prot->prot_mutex);
+	if (fs_prot->refcnt++)
+		goto out;
+
+	/* create FT */
+	err = accel_psp_fs_rx_create(fs, type);
+	if (err) {
+		fs_prot->refcnt--;
+		goto out;
+	}
+
+	/* connect */
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest.ft = fs_prot->ft;
+	mlx5_ttc_fwd_dest(ttc, fs_psp2tt(type), &dest);
+
+out:
+	mutex_unlock(&fs_prot->prot_mutex);
+	return err;
+}
+
+static void accel_psp_fs_rx_ft_put(struct mlx5e_psp_fs *fs, enum accel_fs_psp_type type)
+{
+	struct mlx5_ttc_table *ttc = mlx5e_fs_get_ttc(fs->fs, false);
+	struct mlx5e_accel_fs_psp_prot *fs_prot;
+	struct mlx5e_accel_fs_psp *accel_psp;
+
+	accel_psp = fs->rx_fs;
+	fs_prot = &accel_psp->fs_prot[type];
+	mutex_lock(&fs_prot->prot_mutex);
+	if (--fs_prot->refcnt)
+		goto out;
+
+	/* disconnect */
+	mlx5_ttc_fwd_default_dest(ttc, fs_psp2tt(type));
+
+	/* remove FT */
+	accel_psp_fs_rx_destroy(fs, type);
+
+out:
+	mutex_unlock(&fs_prot->prot_mutex);
+}
+
+static void accel_psp_fs_cleanup_rx(struct mlx5e_psp_fs *fs)
+{
+	struct mlx5e_accel_fs_psp_prot *fs_prot;
+	struct mlx5e_accel_fs_psp *accel_psp;
+	enum accel_fs_psp_type i;
+
+	if (!fs->rx_fs)
+		return;
+
+	accel_psp = fs->rx_fs;
+	mlx5_fc_destroy(fs->mdev, accel_psp->rx_bad_counter);
+	mlx5_fc_destroy(fs->mdev, accel_psp->rx_err_counter);
+	mlx5_fc_destroy(fs->mdev, accel_psp->rx_auth_fail_counter);
+	mlx5_fc_destroy(fs->mdev, accel_psp->rx_counter);
+	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++) {
+		fs_prot = &accel_psp->fs_prot[i];
+		mutex_destroy(&fs_prot->prot_mutex);
+		WARN_ON(fs_prot->refcnt);
+	}
+	kfree(fs->rx_fs);
+	fs->rx_fs = NULL;
+}
+
+static int accel_psp_fs_init_rx(struct mlx5e_psp_fs *fs)
+{
+	struct mlx5e_accel_fs_psp_prot *fs_prot;
+	struct mlx5e_accel_fs_psp *accel_psp;
+	struct mlx5_core_dev *mdev = fs->mdev;
+	struct mlx5_fc *flow_counter;
+	enum accel_fs_psp_type i;
+	int err;
+
+	accel_psp = kzalloc(sizeof(*accel_psp), GFP_KERNEL);
+	if (!accel_psp)
+		return -ENOMEM;
+
+	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++) {
+		fs_prot = &accel_psp->fs_prot[i];
+		mutex_init(&fs_prot->prot_mutex);
+	}
+
+	flow_counter = mlx5_fc_create(mdev, false);
+	if (IS_ERR(flow_counter)) {
+		mlx5_core_warn(mdev,
+			       "fail to create psp rx flow counter err=%pe\n",
+			       flow_counter);
+		err = PTR_ERR(flow_counter);
+		goto out_err;
+	}
+	accel_psp->rx_counter = flow_counter;
+
+	flow_counter = mlx5_fc_create(mdev, false);
+	if (IS_ERR(flow_counter)) {
+		mlx5_core_warn(mdev,
+			       "fail to create psp rx auth fail flow counter err=%pe\n",
+			       flow_counter);
+		err = PTR_ERR(flow_counter);
+		goto out_counter_err;
+	}
+	accel_psp->rx_auth_fail_counter = flow_counter;
+
+	flow_counter = mlx5_fc_create(mdev, false);
+	if (IS_ERR(flow_counter)) {
+		mlx5_core_warn(mdev,
+			       "fail to create psp rx error flow counter err=%pe\n",
+			       flow_counter);
+		err = PTR_ERR(flow_counter);
+		goto out_auth_fail_counter_err;
+	}
+	accel_psp->rx_err_counter = flow_counter;
+
+	flow_counter = mlx5_fc_create(mdev, false);
+	if (IS_ERR(flow_counter)) {
+		mlx5_core_warn(mdev,
+			       "fail to create psp rx bad flow counter err=%pe\n",
+			       flow_counter);
+		err = PTR_ERR(flow_counter);
+		goto out_err_counter_err;
+	}
+	accel_psp->rx_bad_counter = flow_counter;
+
+	fs->rx_fs = accel_psp;
+
+	return 0;
+
+out_err_counter_err:
+	mlx5_fc_destroy(mdev, accel_psp->rx_err_counter);
+	accel_psp->rx_err_counter = NULL;
+out_auth_fail_counter_err:
+	mlx5_fc_destroy(mdev, accel_psp->rx_auth_fail_counter);
+	accel_psp->rx_auth_fail_counter = NULL;
+out_counter_err:
+	mlx5_fc_destroy(mdev, accel_psp->rx_counter);
+	accel_psp->rx_counter = NULL;
+out_err:
+	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++) {
+		fs_prot = &accel_psp->fs_prot[i];
+		mutex_destroy(&fs_prot->prot_mutex);
+	}
+	kfree(accel_psp);
+	fs->rx_fs = NULL;
+
+	return err;
+}
+
+void mlx5_accel_psp_fs_cleanup_rx_tables(struct mlx5e_priv *priv)
+{
+	int i;
+
+	if (!priv->psp)
+		return;
+
+	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++)
+		accel_psp_fs_rx_ft_put(priv->psp->fs, i);
+}
+
+int mlx5_accel_psp_fs_init_rx_tables(struct mlx5e_priv *priv)
+{
+	struct mlx5e_psp_fs *fs;
+	int err, i;
+
+	if (!priv->psp)
+		return 0;
+
+	fs = priv->psp->fs;
+	for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++) {
+		err = accel_psp_fs_rx_ft_get(fs, i);
+		if (err)
+			goto out_err;
+	}
+
+	return 0;
+
+out_err:
+	i--;
+	while (i >= 0) {
+		accel_psp_fs_rx_ft_put(fs, i);
+		--i;
+	}
+
+	return err;
+}
+
+static int accel_psp_fs_tx_create_ft_table(struct mlx5e_psp_fs *fs)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_core_dev *mdev = fs->mdev;
+	struct mlx5_flow_act flow_act = {};
+	u32 *in, *mc, *outer_headers_c;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	struct mlx5e_psp_tx *tx_fs;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *fg;
+	int err = 0;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!spec || !in) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	ft_attr.max_fte = 1;
+#define MLX5E_PSP_PRIO 0
+	ft_attr.prio = MLX5E_PSP_PRIO;
+#define MLX5E_PSP_LEVEL 0
+	ft_attr.level = MLX5E_PSP_LEVEL;
+	ft_attr.autogroup.max_num_groups = 1;
+
+	tx_fs = fs->tx_fs;
+	ft = mlx5_create_flow_table(tx_fs->ns, &ft_attr);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		mlx5_core_err(mdev, "PSP: fail to add psp tx flow table, err = %d\n", err);
+		goto out;
+	}
+
+	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+	outer_headers_c = MLX5_ADDR_OF(fte_match_param, mc, outer_headers);
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol);
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, outer_headers_c, udp_dport);
+	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
+	fg = mlx5_create_flow_group(ft, in);
+	if (IS_ERR(fg)) {
+		err = PTR_ERR(fg);
+		mlx5_core_err(mdev, "PSP: fail to add psp tx flow group, err = %d\n", err);
+		goto err_create_fg;
+	}
+
+	setup_fte_udp_psp(spec, PSP_DEFAULT_UDP_PORT);
+	flow_act.crypto.type = MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_PSP;
+	flow_act.flags |= FLOW_ACT_NO_APPEND;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW |
+			  MLX5_FLOW_CONTEXT_ACTION_CRYPTO_ENCRYPT |
+			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter = tx_fs->tx_counter;
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev, "PSP: fail to add psp tx flow rule, err = %d\n", err);
+		goto err_add_flow_rule;
+	}
+
+	tx_fs->ft = ft;
+	tx_fs->fg = fg;
+	tx_fs->rule = rule;
+	goto out;
+
+err_add_flow_rule:
+	mlx5_destroy_flow_group(fg);
+err_create_fg:
+	mlx5_destroy_flow_table(ft);
+out:
+	kvfree(in);
+	kvfree(spec);
+	return err;
+}
+
+static void accel_psp_fs_tx_destroy(struct mlx5e_psp_tx *tx_fs)
+{
+	if (!tx_fs->ft)
+		return;
+
+	mlx5_del_flow_rules(tx_fs->rule);
+	mlx5_destroy_flow_group(tx_fs->fg);
+	mlx5_destroy_flow_table(tx_fs->ft);
+}
+
+static int accel_psp_fs_tx_ft_get(struct mlx5e_psp_fs *fs)
+{
+	struct mlx5e_psp_tx *tx_fs = fs->tx_fs;
+	int err = 0;
+
+	mutex_lock(&tx_fs->mutex);
+	if (tx_fs->refcnt++)
+		goto out;
+
+	err = accel_psp_fs_tx_create_ft_table(fs);
+	if (err)
+		tx_fs->refcnt--;
+out:
+	mutex_unlock(&tx_fs->mutex);
+	return err;
+}
+
+static void accel_psp_fs_tx_ft_put(struct mlx5e_psp_fs *fs)
+{
+	struct mlx5e_psp_tx *tx_fs = fs->tx_fs;
+
+	mutex_lock(&tx_fs->mutex);
+	if (--tx_fs->refcnt)
+		goto out;
+
+	accel_psp_fs_tx_destroy(tx_fs);
+out:
+	mutex_unlock(&tx_fs->mutex);
+}
+
+static void accel_psp_fs_cleanup_tx(struct mlx5e_psp_fs *fs)
+{
+	struct mlx5e_psp_tx *tx_fs = fs->tx_fs;
+
+	if (!tx_fs)
+		return;
+
+	mlx5_fc_destroy(fs->mdev, tx_fs->tx_counter);
+	mutex_destroy(&tx_fs->mutex);
+	WARN_ON(tx_fs->refcnt);
+	kfree(tx_fs);
+	fs->tx_fs = NULL;
+}
+
+static int accel_psp_fs_init_tx(struct mlx5e_psp_fs *fs)
+{
+	struct mlx5_core_dev *mdev = fs->mdev;
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_fc *flow_counter;
+	struct mlx5e_psp_tx *tx_fs;
+
+	ns = mlx5_get_flow_namespace(mdev, MLX5_FLOW_NAMESPACE_EGRESS_IPSEC);
+	if (!ns)
+		return -EOPNOTSUPP;
+
+	tx_fs = kzalloc(sizeof(*tx_fs), GFP_KERNEL);
+	if (!tx_fs)
+		return -ENOMEM;
+
+	flow_counter = mlx5_fc_create(mdev, false);
+	if (IS_ERR(flow_counter)) {
+		mlx5_core_warn(mdev,
+			       "fail to create psp tx flow counter err=%pe\n",
+			       flow_counter);
+		kfree(tx_fs);
+		return PTR_ERR(flow_counter);
+	}
+	tx_fs->tx_counter = flow_counter;
+	mutex_init(&tx_fs->mutex);
+	tx_fs->ns = ns;
+	fs->tx_fs = tx_fs;
+	return 0;
+}
+
+static void
+mlx5e_accel_psp_fs_get_stats_fill(struct mlx5e_priv *priv,
+				  struct mlx5e_psp_stats *stats)
+{
+	struct mlx5e_psp_tx *tx_fs = priv->psp->fs->tx_fs;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_accel_fs_psp *accel_psp;
+
+	accel_psp = (struct mlx5e_accel_fs_psp *)priv->psp->fs->rx_fs;
+
+	if (tx_fs->tx_counter)
+		mlx5_fc_query(mdev, tx_fs->tx_counter, &stats->psp_tx_pkts,
+			      &stats->psp_tx_bytes);
+
+	if (accel_psp->rx_counter)
+		mlx5_fc_query(mdev, accel_psp->rx_counter, &stats->psp_rx_pkts,
+			      &stats->psp_rx_bytes);
+
+	if (accel_psp->rx_auth_fail_counter)
+		mlx5_fc_query(mdev, accel_psp->rx_auth_fail_counter,
+			      &stats->psp_rx_pkts_auth_fail,
+			      &stats->psp_rx_bytes_auth_fail);
+
+	if (accel_psp->rx_err_counter)
+		mlx5_fc_query(mdev, accel_psp->rx_err_counter,
+			      &stats->psp_rx_pkts_frame_err,
+			      &stats->psp_rx_bytes_frame_err);
+
+	if (accel_psp->rx_bad_counter)
+		mlx5_fc_query(mdev, accel_psp->rx_bad_counter,
+			      &stats->psp_rx_pkts_drop,
+			      &stats->psp_rx_bytes_drop);
+}
+
+void mlx5_accel_psp_fs_cleanup_tx_tables(struct mlx5e_priv *priv)
+{
+	if (!priv->psp)
+		return;
+
+	accel_psp_fs_tx_ft_put(priv->psp->fs);
+}
+
+int mlx5_accel_psp_fs_init_tx_tables(struct mlx5e_priv *priv)
+{
+	if (!priv->psp)
+		return 0;
+
+	return accel_psp_fs_tx_ft_get(priv->psp->fs);
+}
+
+static void mlx5e_accel_psp_fs_cleanup(struct mlx5e_psp_fs *fs)
+{
+	accel_psp_fs_cleanup_rx(fs);
+	accel_psp_fs_cleanup_tx(fs);
+	kfree(fs);
+}
+
+static struct mlx5e_psp_fs *mlx5e_accel_psp_fs_init(struct mlx5e_priv *priv)
+{
+	struct mlx5e_psp_fs *fs;
+	int err = 0;
+
+	fs = kzalloc(sizeof(*fs), GFP_KERNEL);
+	if (!fs)
+		return ERR_PTR(-ENOMEM);
+
+	fs->mdev = priv->mdev;
+	err = accel_psp_fs_init_tx(fs);
+	if (err)
+		goto err_tx;
+
+	fs->fs = priv->fs;
+	err = accel_psp_fs_init_rx(fs);
+	if (err)
+		goto err_rx;
+
+	return fs;
+
+err_rx:
+	accel_psp_fs_cleanup_tx(fs);
+err_tx:
+	kfree(fs);
+	return ERR_PTR(err);
+}
+
+static int
+mlx5e_psp_set_config(struct psp_dev *psd, struct psp_dev_config *conf,
+		     struct netlink_ext_ack *extack)
+{
+	return 0; /* TODO: this should actually do things to the device */
+}
+
+static int
+mlx5e_psp_generate_key_spi(struct mlx5_core_dev *mdev,
+			   enum mlx5_psp_gen_spi_in_key_size keysz,
+			   unsigned int keysz_bytes,
+			   struct psp_key_parsed *key)
+{
+	u32 out[MLX5_ST_SZ_DW(psp_gen_spi_out) + MLX5_ST_SZ_DW(key_spi)] = {};
+	u32 in[MLX5_ST_SZ_DW(psp_gen_spi_in)] = {};
+	void *outkey;
+	int err;
+
+	WARN_ON_ONCE(keysz_bytes > PSP_MAX_KEY);
+
+	MLX5_SET(psp_gen_spi_in, in, opcode, MLX5_CMD_OP_PSP_GEN_SPI);
+	MLX5_SET(psp_gen_spi_in, in, key_size, keysz);
+	MLX5_SET(psp_gen_spi_in, in, num_of_spi, 1);
+	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return err;
+
+	outkey = MLX5_ADDR_OF(psp_gen_spi_out, out, key_spi);
+	key->spi = cpu_to_be32(MLX5_GET(key_spi, outkey, spi));
+	memcpy(key->key, MLX5_ADDR_OF(key_spi, outkey, key) + 32 - keysz_bytes,
+	       keysz_bytes);
+
+	return 0;
+}
+
+static int
+mlx5e_psp_rx_spi_alloc(struct psp_dev *psd, u32 version,
+		       struct psp_key_parsed *assoc,
+		       struct netlink_ext_ack *extack)
+{
+	struct mlx5e_priv *priv = netdev_priv(psd->main_netdev);
+	enum mlx5_psp_gen_spi_in_key_size keysz;
+	u8 keysz_bytes;
+
+	switch (version) {
+	case PSP_VERSION_HDR0_AES_GCM_128:
+		keysz = MLX5_PSP_GEN_SPI_IN_KEY_SIZE_128;
+		keysz_bytes = 16;
+		break;
+	case PSP_VERSION_HDR0_AES_GCM_256:
+		keysz = MLX5_PSP_GEN_SPI_IN_KEY_SIZE_256;
+		keysz_bytes = 32;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return mlx5e_psp_generate_key_spi(priv->mdev, keysz, keysz_bytes, assoc);
+}
+
+struct psp_key {
+	u32 id;
+};
+
+static int mlx5e_psp_assoc_add(struct psp_dev *psd, struct psp_assoc *pas,
+			       struct netlink_ext_ack *extack)
+{
+	struct mlx5e_priv *priv = netdev_priv(psd->main_netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct psp_key_parsed *tx = &pas->tx;
+	struct mlx5e_psp *psp = priv->psp;
+	struct psp_key *nkey;
+	int err;
+
+	mdev = priv->mdev;
+	nkey = (struct psp_key *)pas->drv_data;
+
+	err = mlx5_create_encryption_key(mdev, tx->key,
+					 psp_key_size(pas->version),
+					 MLX5_ACCEL_OBJ_PSP_KEY,
+					 &nkey->id);
+	if (err) {
+		mlx5_core_err(mdev, "Failed to create encryption key (err = %d)\n", err);
+		return err;
+	}
+
+	atomic_inc(&psp->tx_key_cnt);
+	return 0;
+}
+
+static void mlx5e_psp_assoc_del(struct psp_dev *psd, struct psp_assoc *pas)
+{
+	struct mlx5e_priv *priv = netdev_priv(psd->main_netdev);
+	struct mlx5e_psp *psp = priv->psp;
+	struct psp_key *nkey;
+
+	nkey = (struct psp_key *)pas->drv_data;
+	mlx5_destroy_encryption_key(priv->mdev, nkey->id);
+	atomic_dec(&psp->tx_key_cnt);
+}
+
+static int mlx5e_psp_rotate_key(struct mlx5_core_dev *mdev)
+{
+	u32 in[MLX5_ST_SZ_DW(psp_rotate_key_in)] = {};
+	u32 out[MLX5_ST_SZ_DW(psp_rotate_key_out)];
+
+	MLX5_SET(psp_rotate_key_in, in, opcode,
+		 MLX5_CMD_OP_PSP_ROTATE_KEY);
+
+	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+static int
+mlx5e_psp_key_rotate(struct psp_dev *psd, struct netlink_ext_ack *exack)
+{
+	struct mlx5e_priv *priv = netdev_priv(psd->main_netdev);
+
+	/* no support for protecting against external rotations */
+	psd->generation = 0;
+
+	return mlx5e_psp_rotate_key(priv->mdev);
+}
+
+static void
+mlx5e_psp_get_stats(struct psp_dev *psd, struct psp_dev_stats *stats)
+{
+	struct mlx5e_priv *priv = netdev_priv(psd->main_netdev);
+	struct mlx5e_psp_stats nstats;
+
+	mlx5e_accel_psp_fs_get_stats_fill(priv, &nstats);
+	stats->rx_packets = nstats.psp_rx_pkts;
+	stats->rx_bytes = nstats.psp_rx_bytes;
+	stats->rx_auth_fail = nstats.psp_rx_pkts_auth_fail;
+	stats->rx_error = nstats.psp_rx_pkts_frame_err;
+	stats->rx_bad = nstats.psp_rx_pkts_drop;
+	stats->tx_packets = nstats.psp_tx_pkts;
+	stats->tx_bytes = nstats.psp_tx_bytes;
+	stats->tx_error = atomic_read(&priv->psp->tx_drop);
+}
+
+static struct psp_dev_ops mlx5_psp_ops = {
+	.set_config   = mlx5e_psp_set_config,
+	.rx_spi_alloc = mlx5e_psp_rx_spi_alloc,
+	.tx_key_add   = mlx5e_psp_assoc_add,
+	.tx_key_del   = mlx5e_psp_assoc_del,
+	.key_rotate   = mlx5e_psp_key_rotate,
+	.get_stats    = mlx5e_psp_get_stats,
+};
+
+void mlx5e_psp_unregister(struct mlx5e_priv *priv)
+{
+	if (!priv->psp || !priv->psp->psp)
+		return;
+
+	psp_dev_unregister(priv->psp->psp);
+}
+
+void mlx5e_psp_register(struct mlx5e_priv *priv)
+{
+	/* FW Caps missing */
+	if (!priv->psp)
+		return;
+
+	priv->psp->caps.assoc_drv_spc = sizeof(u32);
+	priv->psp->caps.versions = 1 << PSP_VERSION_HDR0_AES_GCM_128;
+	if (MLX5_CAP_PSP(priv->mdev, psp_crypto_esp_aes_gcm_256_encrypt) &&
+	    MLX5_CAP_PSP(priv->mdev, psp_crypto_esp_aes_gcm_256_decrypt))
+		priv->psp->caps.versions |= 1 << PSP_VERSION_HDR0_AES_GCM_256;
+
+	priv->psp->psp = psp_dev_create(priv->netdev, &mlx5_psp_ops,
+					&priv->psp->caps, NULL);
+	if (IS_ERR(priv->psp->psp))
+		mlx5_core_err(priv->mdev, "PSP failed to register due to %pe\n",
+			      priv->psp->psp);
+}
+
+int mlx5e_psp_init(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_psp_fs *fs;
+	struct mlx5e_psp *psp;
+	int err;
+
+	if (!mlx5_is_psp_device(mdev)) {
+		mlx5_core_dbg(mdev, "PSP offload not supported\n");
+		return 0;
+	}
+
+	if (!MLX5_CAP_ETH(mdev, swp)) {
+		mlx5_core_dbg(mdev, "SWP not supported\n");
+		return 0;
+	}
+
+	if (!MLX5_CAP_ETH(mdev, swp_csum)) {
+		mlx5_core_dbg(mdev, "SWP checksum not supported\n");
+		return 0;
+	}
+
+	if (!MLX5_CAP_ETH(mdev, swp_csum_l4_partial)) {
+		mlx5_core_dbg(mdev, "SWP L4 partial checksum not supported\n");
+		return 0;
+	}
+
+	if (!MLX5_CAP_ETH(mdev, swp_lso)) {
+		mlx5_core_dbg(mdev, "PSP LSO not supported\n");
+		return 0;
+	}
+
+	psp = kzalloc(sizeof(*psp), GFP_KERNEL);
+	if (!psp)
+		return -ENOMEM;
+
+	priv->psp = psp;
+	fs = mlx5e_accel_psp_fs_init(priv);
+	if (IS_ERR(fs)) {
+		err = PTR_ERR(fs);
+		goto out_err;
+	}
+
+	psp->fs = fs;
+
+	mlx5_core_dbg(priv->mdev, "PSP attached to netdevice\n");
+	return 0;
+
+out_err:
+	priv->psp = NULL;
+	kfree(psp);
+	return err;
+}
+
+void mlx5e_psp_cleanup(struct mlx5e_priv *priv)
+{
+	struct mlx5e_psp *psp = priv->psp;
+
+	if (!psp)
+		return;
+
+	WARN_ON(atomic_read(&psp->tx_key_cnt));
+	mlx5e_accel_psp_fs_cleanup(psp->fs);
+	priv->psp = NULL;
+	kfree(psp);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h
new file mode 100644
index 000000000000..6b62fef0d9a7
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef __MLX5E_ACCEL_PSP_H__
+#define __MLX5E_ACCEL_PSP_H__
+#if IS_ENABLED(CONFIG_MLX5_EN_PSP)
+#include <net/psp/types.h>
+#include "en.h"
+
+struct mlx5e_psp_stats {
+	u64 psp_rx_pkts;
+	u64 psp_rx_bytes;
+	u64 psp_rx_pkts_auth_fail;
+	u64 psp_rx_bytes_auth_fail;
+	u64 psp_rx_pkts_frame_err;
+	u64 psp_rx_bytes_frame_err;
+	u64 psp_rx_pkts_drop;
+	u64 psp_rx_bytes_drop;
+	u64 psp_tx_pkts;
+	u64 psp_tx_bytes;
+	u64 psp_tx_pkts_drop;
+	u64 psp_tx_bytes_drop;
+};
+
+struct mlx5e_psp {
+	struct psp_dev *psp;
+	struct psp_dev_caps caps;
+	struct mlx5e_psp_fs *fs;
+	atomic_t tx_key_cnt;
+	atomic_t tx_drop;
+};
+
+static inline bool mlx5_is_psp_device(struct mlx5_core_dev *mdev)
+{
+	if (!MLX5_CAP_GEN(mdev, psp))
+		return false;
+
+	if (!MLX5_CAP_PSP(mdev, psp_crypto_offload) ||
+	    !MLX5_CAP_PSP(mdev, psp_crypto_esp_aes_gcm_128_encrypt) ||
+	    !MLX5_CAP_PSP(mdev, psp_crypto_esp_aes_gcm_128_decrypt))
+		return false;
+
+	return true;
+}
+
+int mlx5_accel_psp_fs_init_rx_tables(struct mlx5e_priv *priv);
+void mlx5_accel_psp_fs_cleanup_rx_tables(struct mlx5e_priv *priv);
+int mlx5_accel_psp_fs_init_tx_tables(struct mlx5e_priv *priv);
+void mlx5_accel_psp_fs_cleanup_tx_tables(struct mlx5e_priv *priv);
+void mlx5e_psp_register(struct mlx5e_priv *priv);
+void mlx5e_psp_unregister(struct mlx5e_priv *priv);
+int mlx5e_psp_init(struct mlx5e_priv *priv);
+void mlx5e_psp_cleanup(struct mlx5e_priv *priv);
+#else
+static inline int mlx5_accel_psp_fs_init_rx_tables(struct mlx5e_priv *priv)
+{
+	return 0;
+}
+
+static inline void mlx5_accel_psp_fs_cleanup_rx_tables(struct mlx5e_priv *priv) { }
+static inline int mlx5_accel_psp_fs_init_tx_tables(struct mlx5e_priv *priv)
+{
+	return 0;
+}
+
+static inline void mlx5_accel_psp_fs_cleanup_tx_tables(struct mlx5e_priv *priv) { }
+static inline bool mlx5_is_psp_device(struct mlx5_core_dev *mdev)
+{
+	return false;
+}
+
+static inline void mlx5e_psp_register(struct mlx5e_priv *priv) { }
+static inline void mlx5e_psp_unregister(struct mlx5e_priv *priv) { }
+static inline int mlx5e_psp_init(struct mlx5e_priv *priv) { return 0; }
+static inline void mlx5e_psp_cleanup(struct mlx5e_priv *priv) { }
+#endif /* CONFIG_MLX5_EN_PSP */
+#endif /* __MLX5E_ACCEL_PSP_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c
new file mode 100644
index 000000000000..c17ea0fcd8ef
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <net/protocol.h>
+#include <net/udp.h>
+#include <net/ip6_checksum.h>
+#include <net/psp/types.h>
+
+#include "en.h"
+#include "psp.h"
+#include "en_accel/psp_rxtx.h"
+#include "en_accel/psp.h"
+
+enum {
+	MLX5E_PSP_OFFLOAD_RX_SYNDROME_DECRYPTED,
+	MLX5E_PSP_OFFLOAD_RX_SYNDROME_AUTH_FAILED,
+	MLX5E_PSP_OFFLOAD_RX_SYNDROME_BAD_TRAILER,
+};
+
+static void mlx5e_psp_set_swp(struct sk_buff *skb,
+			      struct mlx5e_accel_tx_psp_state *psp_st,
+			      struct mlx5_wqe_eth_seg *eseg)
+{
+	/* Tunnel Mode:
+	 * SWP:      OutL3       InL3  InL4
+	 * Pkt: MAC  IP     ESP  IP    L4
+	 *
+	 * Transport Mode:
+	 * SWP:      OutL3       OutL4
+	 * Pkt: MAC  IP     ESP  L4
+	 *
+	 * Tunnel(VXLAN TCP/UDP) over Transport Mode
+	 * SWP:      OutL3                   InL3  InL4
+	 * Pkt: MAC  IP     ESP  UDP  VXLAN  IP    L4
+	 */
+	u8 inner_ipproto = 0;
+	struct ethhdr *eth;
+
+	/* Shared settings */
+	eseg->swp_outer_l3_offset = skb_network_offset(skb) / 2;
+	if (skb->protocol == htons(ETH_P_IPV6))
+		eseg->swp_flags |= MLX5_ETH_WQE_SWP_OUTER_L3_IPV6;
+
+	if (skb->inner_protocol_type == ENCAP_TYPE_IPPROTO) {
+		inner_ipproto = skb->inner_ipproto;
+		/* Set SWP additional flags for packet of type IP|UDP|PSP|[ TCP | UDP ] */
+		switch (inner_ipproto) {
+		case IPPROTO_UDP:
+			eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP;
+			fallthrough;
+		case IPPROTO_TCP:
+			eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2;
+			break;
+		default:
+			break;
+		}
+	} else {
+		/* IP in IP tunneling like vxlan*/
+		if (skb->inner_protocol_type != ENCAP_TYPE_ETHER)
+			return;
+
+		eth = (struct ethhdr *)skb_inner_mac_header(skb);
+		switch (ntohs(eth->h_proto)) {
+		case ETH_P_IP:
+			inner_ipproto = ((struct iphdr *)((char *)skb->data +
+					 skb_inner_network_offset(skb)))->protocol;
+			break;
+		case ETH_P_IPV6:
+			inner_ipproto = ((struct ipv6hdr *)((char *)skb->data +
+					 skb_inner_network_offset(skb)))->nexthdr;
+			break;
+		default:
+			break;
+		}
+
+		/* Tunnel(VXLAN TCP/UDP) over Transport Mode PSP i.e. PSP payload is vxlan tunnel */
+		switch (inner_ipproto) {
+		case IPPROTO_UDP:
+			eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP;
+			fallthrough;
+		case IPPROTO_TCP:
+			eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2;
+			eseg->swp_inner_l4_offset =
+				(skb->csum_start + skb->head - skb->data) / 2;
+			if (skb->protocol == htons(ETH_P_IPV6))
+				eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
+			break;
+		default:
+			break;
+		}
+
+		psp_st->inner_ipproto = inner_ipproto;
+	}
+}
+
+static bool mlx5e_psp_set_state(struct mlx5e_priv *priv,
+				struct sk_buff *skb,
+				struct mlx5e_accel_tx_psp_state *psp_st)
+{
+	struct psp_assoc *pas;
+	bool ret = false;
+
+	rcu_read_lock();
+	pas = psp_skb_get_assoc_rcu(skb);
+	if (!pas)
+		goto out;
+
+	ret = true;
+	psp_st->tailen = PSP_TRL_SIZE;
+	psp_st->spi = pas->tx.spi;
+	psp_st->ver = pas->version;
+	psp_st->keyid = *(u32 *)pas->drv_data;
+
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
+bool mlx5e_psp_offload_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+				     struct mlx5_cqe64 *cqe)
+{
+	u32 psp_meta_data = be32_to_cpu(cqe->ft_metadata);
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	u16 dev_id = priv->psp->psp->id;
+	bool strip_icv = true;
+	u8 generation = 0;
+
+	/* TBD: report errors as SW counters to ethtool, any further handling ? */
+	if (MLX5_PSP_METADATA_SYNDROME(psp_meta_data) != MLX5E_PSP_OFFLOAD_RX_SYNDROME_DECRYPTED)
+		goto drop;
+
+	if (psp_dev_rcv(skb, dev_id, generation, strip_icv))
+		goto drop;
+
+	skb->decrypted = 1;
+	return false;
+
+drop:
+	kfree_skb(skb);
+	return true;
+}
+
+void mlx5e_psp_tx_build_eseg(struct mlx5e_priv *priv, struct sk_buff *skb,
+			     struct mlx5e_accel_tx_psp_state *psp_st,
+			     struct mlx5_wqe_eth_seg *eseg)
+{
+	if (!mlx5_is_psp_device(priv->mdev))
+		return;
+
+	if (unlikely(skb->protocol != htons(ETH_P_IP) &&
+		     skb->protocol != htons(ETH_P_IPV6)))
+		return;
+
+	mlx5e_psp_set_swp(skb, psp_st, eseg);
+	/* Special WA for PSP LSO in ConnectX7 */
+	eseg->swp_outer_l3_offset = 0;
+	eseg->swp_inner_l3_offset = 0;
+
+	eseg->flow_table_metadata |= cpu_to_be32(psp_st->keyid);
+	eseg->trailer |= cpu_to_be32(MLX5_ETH_WQE_INSERT_TRAILER) |
+			 cpu_to_be32(MLX5_ETH_WQE_TRAILER_HDR_OUTER_L4_ASSOC);
+}
+
+void mlx5e_psp_handle_tx_wqe(struct mlx5e_tx_wqe *wqe,
+			     struct mlx5e_accel_tx_psp_state *psp_st,
+			     struct mlx5_wqe_inline_seg *inlseg)
+{
+	inlseg->byte_count = cpu_to_be32(psp_st->tailen | MLX5_INLINE_SEG);
+}
+
+bool mlx5e_psp_handle_tx_skb(struct net_device *netdev,
+			     struct sk_buff *skb,
+			     struct mlx5e_accel_tx_psp_state *psp_st)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct net *net = sock_net(skb->sk);
+	const struct ipv6hdr *ip6;
+	struct tcphdr *th;
+
+	if (!mlx5e_psp_set_state(priv, skb, psp_st))
+		return true;
+
+	/* psp_encap of the packet */
+	if (!psp_dev_encapsulate(net, skb, psp_st->spi, psp_st->ver, 0)) {
+		kfree_skb_reason(skb, SKB_DROP_REASON_PSP_OUTPUT);
+		atomic_inc(&priv->psp->tx_drop);
+		return false;
+	}
+	if (skb_is_gso(skb)) {
+		ip6 = ipv6_hdr(skb);
+		th = inner_tcp_hdr(skb);
+
+		th->check = ~tcp_v6_check(skb_shinfo(skb)->gso_size + inner_tcp_hdrlen(skb), &ip6->saddr,
+					  &ip6->daddr, 0);
+	}
+
+	return true;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.h
new file mode 100644
index 000000000000..70289c921bd6
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.h
@@ -0,0 +1,121 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef __MLX5E_PSP_RXTX_H__
+#define __MLX5E_PSP_RXTX_H__
+
+#include <linux/skbuff.h>
+#include <net/xfrm.h>
+#include <net/psp.h>
+#include "en.h"
+#include "en/txrx.h"
+
+/* Bit30: PSP marker, Bit29-23: PSP syndrome, Bit22-0: PSP obj id */
+#define MLX5_PSP_METADATA_MARKER(metadata)  ((((metadata) >> 30) & 0x3) == 0x3)
+#define MLX5_PSP_METADATA_SYNDROME(metadata) (((metadata) >> 23) & GENMASK(6, 0))
+#define MLX5_PSP_METADATA_HANDLE(metadata)  ((metadata) & GENMASK(22, 0))
+
+struct mlx5e_accel_tx_psp_state {
+	u32 tailen;
+	u32 keyid;
+	__be32 spi;
+	u8 inner_ipproto;
+	u8 ver;
+};
+
+#ifdef CONFIG_MLX5_EN_PSP
+static inline bool mlx5e_psp_is_offload_state(struct mlx5e_accel_tx_psp_state *psp_state)
+{
+	return (psp_state->tailen != 0);
+}
+
+static inline bool mlx5e_psp_is_offload(struct sk_buff *skb, struct net_device *netdev)
+{
+	bool ret;
+
+	rcu_read_lock();
+	ret = !!psp_skb_get_assoc_rcu(skb);
+	rcu_read_unlock();
+	return ret;
+}
+
+bool mlx5e_psp_handle_tx_skb(struct net_device *netdev,
+			     struct sk_buff *skb,
+			     struct mlx5e_accel_tx_psp_state *psp_st);
+
+void mlx5e_psp_tx_build_eseg(struct mlx5e_priv *priv, struct sk_buff *skb,
+			     struct mlx5e_accel_tx_psp_state *psp_st,
+			     struct mlx5_wqe_eth_seg *eseg);
+
+void mlx5e_psp_handle_tx_wqe(struct mlx5e_tx_wqe *wqe,
+			     struct mlx5e_accel_tx_psp_state *psp_st,
+			     struct mlx5_wqe_inline_seg *inlseg);
+
+static inline bool mlx5e_psp_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+						   struct mlx5e_accel_tx_psp_state *psp_st,
+						   struct mlx5_wqe_eth_seg *eseg)
+{
+	u8 inner_ipproto;
+
+	if (!mlx5e_psp_is_offload_state(psp_st))
+		return false;
+
+	inner_ipproto = psp_st->inner_ipproto;
+	eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM;
+	if (inner_ipproto) {
+		eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM;
+		if (inner_ipproto == IPPROTO_TCP || inner_ipproto == IPPROTO_UDP)
+			eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM;
+		if (likely(skb->ip_summed == CHECKSUM_PARTIAL))
+			sq->stats->csum_partial_inner++;
+	} else if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
+		eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM;
+		sq->stats->csum_partial_inner++;
+	}
+
+	return true;
+}
+
+static inline unsigned int mlx5e_psp_tx_ids_len(struct mlx5e_accel_tx_psp_state *psp_st)
+{
+	return psp_st->tailen;
+}
+
+static inline bool mlx5e_psp_is_rx_flow(struct mlx5_cqe64 *cqe)
+{
+	return MLX5_PSP_METADATA_MARKER(be32_to_cpu(cqe->ft_metadata));
+}
+
+bool mlx5e_psp_offload_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+				     struct mlx5_cqe64 *cqe);
+#else
+static inline bool mlx5e_psp_is_offload_state(struct mlx5e_accel_tx_psp_state *psp_state)
+{
+	return false;
+}
+
+static inline bool mlx5e_psp_is_offload(struct sk_buff *skb, struct net_device *netdev)
+{
+	return false;
+}
+
+static inline bool mlx5e_psp_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+						   struct mlx5e_accel_tx_psp_state *psp_st,
+						   struct mlx5_wqe_eth_seg *eseg)
+{
+	return false;
+}
+
+static inline bool mlx5e_psp_is_rx_flow(struct mlx5_cqe64 *cqe)
+{
+	return false;
+}
+
+static inline bool mlx5e_psp_offload_handle_rx_skb(struct net_device *netdev,
+						   struct sk_buff *skb,
+						   struct mlx5_cqe64 *cqe)
+{
+	return false;
+}
+#endif /* CONFIG_MLX5_EN_PSP */
+#endif /* __MLX5E_PSP_RXTX_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 6ed3a32b7e22..5a2ac7b6f260 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 
+#include "devlink.h"
 #include "en.h"
 #include "lib/crypto.h"
 
@@ -140,9 +141,22 @@ err_close_tises:
 	return err;
 }
 
+static unsigned int
+mlx5e_get_devlink_param_num_doorbells(struct mlx5_core_dev *dev)
+{
+	const u32 param_id = DEVLINK_PARAM_GENERIC_ID_NUM_DOORBELLS;
+	struct devlink *devlink = priv_to_devlink(dev);
+	union devlink_param_value val;
+	int err;
+
+	err = devl_param_driverinit_value_get(devlink, param_id, &val);
+	return err ? MLX5_DEFAULT_NUM_DOORBELLS : val.vu32;
+}
+
 int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises)
 {
 	struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs;
+	unsigned int num_doorbells, i;
 	int err;
 
 	err = mlx5_core_alloc_pd(mdev, &res->pdn);
@@ -163,17 +177,30 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises)
 		goto err_dealloc_transport_domain;
 	}
 
-	err = mlx5_alloc_bfreg(mdev, &res->bfreg, false, false);
-	if (err) {
-		mlx5_core_err(mdev, "alloc bfreg failed, %d\n", err);
+	num_doorbells = min(mlx5e_get_devlink_param_num_doorbells(mdev),
+			    mlx5e_get_max_num_channels(mdev));
+	res->bfregs = kcalloc(num_doorbells, sizeof(*res->bfregs), GFP_KERNEL);
+	if (!res->bfregs) {
+		err = -ENOMEM;
 		goto err_destroy_mkey;
 	}
 
+	for (i = 0; i < num_doorbells; i++) {
+		err = mlx5_alloc_bfreg(mdev, res->bfregs + i, false, false);
+		if (err) {
+			mlx5_core_warn(mdev,
+				       "could only allocate %d/%d doorbells, err %d.\n",
+				       i, num_doorbells, err);
+			break;
+		}
+	}
+	res->num_bfregs = i;
+
 	if (create_tises) {
 		err = mlx5e_create_tises(mdev, res->tisn);
 		if (err) {
 			mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
-			goto err_destroy_bfreg;
+			goto err_destroy_bfregs;
 		}
 		res->tisn_valid = true;
 	}
@@ -183,15 +210,17 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises)
 
 	mdev->mlx5e_res.dek_priv = mlx5_crypto_dek_init(mdev);
 	if (IS_ERR(mdev->mlx5e_res.dek_priv)) {
-		mlx5_core_err(mdev, "crypto dek init failed, %ld\n",
-			      PTR_ERR(mdev->mlx5e_res.dek_priv));
+		mlx5_core_err(mdev, "crypto dek init failed, %pe\n",
+			      mdev->mlx5e_res.dek_priv);
 		mdev->mlx5e_res.dek_priv = NULL;
 	}
 
 	return 0;
 
-err_destroy_bfreg:
-	mlx5_free_bfreg(mdev, &res->bfreg);
+err_destroy_bfregs:
+	for (i = 0; i < res->num_bfregs; i++)
+		mlx5_free_bfreg(mdev, res->bfregs + i);
+	kfree(res->bfregs);
 err_destroy_mkey:
 	mlx5_core_destroy_mkey(mdev, res->mkey);
 err_dealloc_transport_domain:
@@ -209,52 +238,52 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 	mdev->mlx5e_res.dek_priv = NULL;
 	if (res->tisn_valid)
 		mlx5e_destroy_tises(mdev, res->tisn);
-	mlx5_free_bfreg(mdev, &res->bfreg);
+	for (unsigned int i = 0; i < res->num_bfregs; i++)
+		mlx5_free_bfreg(mdev, res->bfregs + i);
+	kfree(res->bfregs);
 	mlx5_core_destroy_mkey(mdev, res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
 	mlx5_core_dealloc_pd(mdev, res->pdn);
 	memset(res, 0, sizeof(*res));
 }
 
-int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
-		       bool enable_mc_lb)
+int mlx5e_modify_tirs_lb(struct mlx5_core_dev *mdev, bool enable_uc_lb,
+			 bool enable_mc_lb)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_tir_builder *builder;
 	struct mlx5e_tir *tir;
-	u8 lb_flags = 0;
-	int err  = 0;
-	u32 tirn = 0;
-	int inlen;
-	void *in;
+	int err = 0;
 
-	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
+	builder = mlx5e_tir_builder_alloc(true);
+	if (!builder)
 		return -ENOMEM;
 
-	if (enable_uc_lb)
-		lb_flags = MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
-
-	if (enable_mc_lb)
-		lb_flags |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST;
-
-	if (lb_flags)
-		MLX5_SET(modify_tir_in, in, ctx.self_lb_block, lb_flags);
-
-	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
+	mlx5e_tir_builder_build_self_lb_block(builder, enable_uc_lb,
+					      enable_mc_lb);
 
 	mutex_lock(&mdev->mlx5e_res.hw_objs.td.list_lock);
 	list_for_each_entry(tir, &mdev->mlx5e_res.hw_objs.td.tirs_list, list) {
-		tirn = tir->tirn;
-		err = mlx5_core_modify_tir(mdev, tirn, in);
-		if (err)
+		err = mlx5e_tir_modify(tir, builder);
+		if (err) {
+			mlx5_core_err(mdev,
+				      "modify tir(0x%x) enable_lb uc(%d) mc(%d) failed, %d\n",
+				      mlx5e_tir_get_tirn(tir),
+				      enable_uc_lb, enable_mc_lb, err);
 			break;
+		}
 	}
 	mutex_unlock(&mdev->mlx5e_res.hw_objs.td.list_lock);
 
-	kvfree(in);
-	if (err)
-		netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
+	mlx5e_tir_builder_free(builder);
 
 	return err;
 }
+
+int mlx5e_refresh_tirs(struct mlx5_core_dev *mdev, bool enable_uc_lb,
+		       bool enable_mc_lb)
+{
+	if (MLX5_CAP_GEN(mdev, tis_tir_td_order))
+		return 0; /* refresh not needed */
+
+	return mlx5e_modify_tirs_lb(mdev, enable_uc_lb, enable_mc_lb);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 8705cffc747f..fddf7c207f8e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -31,14 +31,15 @@
  */
 #include <linux/device.h>
 #include <linux/netdevice.h>
+#include <linux/units.h>
 #include "en.h"
 #include "en/port.h"
 #include "en/port_buffer.h"
 
 #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
 
-#define MLX5E_100MB (100000)
-#define MLX5E_1GB   (1000000)
+#define MLX5E_100MB_TO_KB (100 * MEGA / KILO)
+#define MLX5E_1GB_TO_KB   (GIGA / KILO)
 
 #define MLX5E_CEE_STATE_UP    1
 #define MLX5E_CEE_STATE_DOWN  0
@@ -362,6 +363,7 @@ static int mlx5e_dcbnl_ieee_getpfc(struct net_device *dev,
 static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev,
 				   struct ieee_pfc *pfc)
 {
+	u8 buffer_ownership = MLX5_BUF_OWNERSHIP_UNKNOWN;
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u32 old_cable_len = priv->dcbx.cable_len;
@@ -389,7 +391,14 @@ static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev,
 
 	if (MLX5_BUFFER_SUPPORTED(mdev)) {
 		pfc_new.pfc_en = (changed & MLX5E_PORT_BUFFER_PFC) ? pfc->pfc_en : curr_pfc_en;
-		if (priv->dcbx.manual_buffer)
+		ret = mlx5_query_port_buffer_ownership(mdev,
+						       &buffer_ownership);
+		if (ret)
+			netdev_err(dev,
+				   "%s, Failed to get buffer ownership: %d\n",
+				   __func__, ret);
+
+		if (buffer_ownership == MLX5_BUF_OWNERSHIP_SW_OWNED)
 			ret = mlx5e_port_manual_buffer_config(priv, changed,
 							      dev->mtu, &pfc_new,
 							      NULL, NULL);
@@ -564,10 +573,10 @@ static int mlx5e_dcbnl_ieee_getmaxrate(struct net_device *netdev,
 	for (i = 0; i <= mlx5_max_tc(mdev); i++) {
 		switch (max_bw_unit[i]) {
 		case MLX5_100_MBPS_UNIT:
-			maxrate->tc_maxrate[i] = max_bw_value[i] * MLX5E_100MB;
+			maxrate->tc_maxrate[i] = max_bw_value[i] * MLX5E_100MB_TO_KB;
 			break;
 		case MLX5_GBPS_UNIT:
-			maxrate->tc_maxrate[i] = max_bw_value[i] * MLX5E_1GB;
+			maxrate->tc_maxrate[i] = max_bw_value[i] * MLX5E_1GB_TO_KB;
 			break;
 		case MLX5_BW_NO_LIMIT:
 			break;
@@ -587,32 +596,55 @@ static int mlx5e_dcbnl_ieee_setmaxrate(struct net_device *netdev,
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 max_bw_value[IEEE_8021QAZ_MAX_TCS];
 	u8 max_bw_unit[IEEE_8021QAZ_MAX_TCS];
-	__u64 upper_limit_mbps = roundup(255 * MLX5E_100MB, MLX5E_1GB);
+	u64 upper_limit_100mbps;
+	u64 upper_limit_gbps;
 	int i;
+	struct {
+		int scale;
+		const char *units_str;
+	} units[] = {
+		[MLX5_100_MBPS_UNIT] = {
+			.scale = 100,
+			.units_str = "Mbps",
+		},
+		[MLX5_GBPS_UNIT] = {
+			.scale = 1,
+			.units_str = "Gbps",
+		},
+	};
 
 	memset(max_bw_value, 0, sizeof(max_bw_value));
 	memset(max_bw_unit, 0, sizeof(max_bw_unit));
+	upper_limit_100mbps = U8_MAX * MLX5E_100MB_TO_KB;
+	upper_limit_gbps = U8_MAX * MLX5E_1GB_TO_KB;
 
 	for (i = 0; i <= mlx5_max_tc(mdev); i++) {
 		if (!maxrate->tc_maxrate[i]) {
 			max_bw_unit[i]  = MLX5_BW_NO_LIMIT;
 			continue;
 		}
-		if (maxrate->tc_maxrate[i] < upper_limit_mbps) {
+		if (maxrate->tc_maxrate[i] <= upper_limit_100mbps) {
 			max_bw_value[i] = div_u64(maxrate->tc_maxrate[i],
-						  MLX5E_100MB);
+						  MLX5E_100MB_TO_KB);
 			max_bw_value[i] = max_bw_value[i] ? max_bw_value[i] : 1;
 			max_bw_unit[i]  = MLX5_100_MBPS_UNIT;
-		} else {
+		} else if (maxrate->tc_maxrate[i] <= upper_limit_gbps) {
 			max_bw_value[i] = div_u64(maxrate->tc_maxrate[i],
-						  MLX5E_1GB);
+						  MLX5E_1GB_TO_KB);
 			max_bw_unit[i]  = MLX5_GBPS_UNIT;
+		} else {
+			netdev_err(netdev,
+				   "tc_%d maxrate %llu Kbps exceeds limit %llu\n",
+				   i, maxrate->tc_maxrate[i],
+				   upper_limit_gbps);
+			return -EINVAL;
 		}
 	}
 
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
-		netdev_dbg(netdev, "%s: tc_%d <=> max_bw %d Gbps\n",
-			   __func__, i, max_bw_value[i]);
+		netdev_dbg(netdev, "%s: tc_%d <=> max_bw %u %s\n", __func__, i,
+			   max_bw_value[i] * units[max_bw_unit[i]].scale,
+			   units[max_bw_unit[i]].units_str);
 	}
 
 	return mlx5_modify_port_ets_rate_limit(mdev, max_bw_value, max_bw_unit);
@@ -982,7 +1014,6 @@ static int mlx5e_dcbnl_setbuffer(struct net_device *dev,
 	if (!changed)
 		return 0;
 
-	priv->dcbx.manual_buffer = true;
 	err = mlx5e_port_manual_buffer_config(priv, changed, dev->mtu, NULL,
 					      buffer_size, prio2buffer);
 	return err;
@@ -1147,6 +1178,7 @@ static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state)
 	bool reset = true;
 	int err;
 
+	netdev_lock(priv->netdev);
 	mutex_lock(&priv->state_lock);
 
 	new_params = priv->channels.params;
@@ -1162,6 +1194,7 @@ static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state)
 				       &trust_state, reset);
 
 	mutex_unlock(&priv->state_lock);
+	netdev_unlock(priv->netdev);
 
 	return err;
 }
@@ -1250,7 +1283,6 @@ void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv)
 		priv->dcbx.cap |= DCB_CAP_DCBX_HOST;
 
 	priv->dcbx.port_buff_cell_sz = mlx5e_query_port_buffers_cell_size(priv);
-	priv->dcbx.manual_buffer = false;
 	priv->dcbx.cable_len = MLX5E_DEFAULT_CABLE_LEN;
 
 	mlx5e_ets_init(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
index 298bb74ec5e9..d1d629697e28 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
@@ -113,7 +113,7 @@ int mlx5e_dim_rx_change(struct mlx5e_rq *rq, bool enable)
 		__set_bit(MLX5E_RQ_STATE_DIM, &rq->state);
 	} else {
 		__clear_bit(MLX5E_RQ_STATE_DIM, &rq->state);
-
+		synchronize_net();
 		mlx5e_dim_disable(rq->dim);
 		rq->dim = NULL;
 	}
@@ -140,7 +140,7 @@ int mlx5e_dim_tx_change(struct mlx5e_txqsq *sq, bool enable)
 		__set_bit(MLX5E_SQ_STATE_DIM, &sq->state);
 	} else {
 		__clear_bit(MLX5E_SQ_STATE_DIM, &sq->state);
-
+		synchronize_net();
 		mlx5e_dim_disable(sq->dim);
 		sq->dim = NULL;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index cae39198b4db..d3fef1e7e2f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -32,6 +32,7 @@
 
 #include <linux/dim.h>
 #include <linux/ethtool_netlink.h>
+#include <net/netdev_queues.h>
 
 #include "en.h"
 #include "en/channels.h"
@@ -42,6 +43,8 @@
 #include "lib/clock.h"
 #include "en/fs_ethtool.h"
 
+#define LANES_UNKNOWN		 0
+
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo)
 {
@@ -237,14 +240,38 @@ void mlx5e_build_ptys2ethtool_map(void)
 				       ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT,
 				       ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT,
 				       ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT);
-}
-
-static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_200GAUI_1_200GBASE_CR1_KR1, ext,
+				       ETHTOOL_LINK_MODE_200000baseCR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseKR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseDR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseDR_2_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseSR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseVR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_400GAUI_2_400GBASE_CR2_KR2, ext,
+				       ETHTOOL_LINK_MODE_400000baseCR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseKR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseDR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseDR2_2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseSR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseVR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_800GAUI_4_800GBASE_CR4_KR4, ext,
+				       ETHTOOL_LINK_MODE_800000baseCR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseKR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseDR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseDR4_2_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseSR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1600TAUI_8_1600TBASE_CR8_KR8, ext,
+				       ETHTOOL_LINK_MODE_1600000baseCR8_Full_BIT,
+				       ETHTOOL_LINK_MODE_1600000baseKR8_Full_BIT,
+				       ETHTOOL_LINK_MODE_1600000baseDR8_Full_BIT,
+				       ETHTOOL_LINK_MODE_1600000baseDR8_2_Full_BIT);
+}
+
+static void mlx5e_ethtool_get_speed_arr(bool ext,
 					struct ptys2ethtool_config **arr,
 					u32 *size)
 {
-	bool ext = mlx5_ptys_ext_supported(mdev);
-
 	*arr = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
 	*size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
 		      ARRAY_SIZE(ptys2legacy_ethtool_table);
@@ -344,11 +371,6 @@ void mlx5e_ethtool_get_ringparam(struct mlx5e_priv *priv,
 	param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE;
 	param->rx_pending     = 1 << priv->channels.params.log_rq_mtu_frames;
 	param->tx_pending     = 1 << priv->channels.params.log_sq_size;
-
-	kernel_param->tcp_data_split =
-		(priv->channels.params.packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) ?
-		ETHTOOL_TCP_DATA_SPLIT_ENABLED :
-		ETHTOOL_TCP_DATA_SPLIT_DISABLED;
 }
 
 static void mlx5e_get_ringparam(struct net_device *dev,
@@ -361,6 +383,27 @@ static void mlx5e_get_ringparam(struct net_device *dev,
 	mlx5e_ethtool_get_ringparam(priv, param, kernel_param);
 }
 
+static bool mlx5e_ethtool_set_tcp_data_split(struct mlx5e_priv *priv,
+					     u8 tcp_data_split,
+					     struct netlink_ext_ack *extack)
+{
+	struct net_device *dev = priv->netdev;
+
+	if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED &&
+	    !(dev->features & NETIF_F_GRO_HW)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "TCP-data-split is not supported when GRO HW is disabled");
+		return false;
+	}
+
+	/* Might need to disable HW-GRO if it was kept on due to hds. */
+	if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_DISABLED &&
+	    dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED)
+		netdev_update_features(priv->netdev);
+
+	return true;
+}
+
 int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
 				struct ethtool_ringparam *param,
 				struct netlink_ext_ack *extack)
@@ -419,6 +462,11 @@ static int mlx5e_set_ringparam(struct net_device *dev,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
+	if (!mlx5e_ethtool_set_tcp_data_split(priv,
+					      kernel_param->tcp_data_split,
+					      extack))
+		return -EINVAL;
+
 	return mlx5e_ethtool_set_ringparam(priv, param, extack);
 }
 
@@ -891,37 +939,19 @@ int mlx5e_set_per_queue_coalesce(struct net_device *dev, u32 queue,
 	return mlx5e_ethtool_set_per_queue_coalesce(priv, queue, coal);
 }
 
-static void ptys2ethtool_supported_link(struct mlx5_core_dev *mdev,
-					unsigned long *supported_modes,
-					u32 eth_proto_cap)
-{
-	unsigned long proto_cap = eth_proto_cap;
-	struct ptys2ethtool_config *table;
-	u32 max_size;
-	int proto;
-
-	mlx5e_ethtool_get_speed_arr(mdev, &table, &max_size);
-	for_each_set_bit(proto, &proto_cap, max_size)
-		bitmap_or(supported_modes, supported_modes,
-			  table[proto].supported,
-			  __ETHTOOL_LINK_MODE_MASK_NBITS);
-}
-
-static void ptys2ethtool_adver_link(unsigned long *advertising_modes,
-				    u32 eth_proto_cap, bool ext)
+static void ptys2ethtool_process_link(u32 eth_eproto, bool ext, bool advertised,
+				      unsigned long *modes)
 {
-	unsigned long proto_cap = eth_proto_cap;
+	unsigned long eproto = eth_eproto;
 	struct ptys2ethtool_config *table;
 	u32 max_size;
 	int proto;
 
-	table = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
-	max_size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
-			 ARRAY_SIZE(ptys2legacy_ethtool_table);
-
-	for_each_set_bit(proto, &proto_cap, max_size)
-		bitmap_or(advertising_modes, advertising_modes,
-			  table[proto].advertised,
+	mlx5e_ethtool_get_speed_arr(ext, &table, &max_size);
+	for_each_set_bit(proto, &eproto, max_size)
+		bitmap_or(modes, modes,
+			  advertised ?
+			  table[proto].advertised : table[proto].supported,
 			  __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
@@ -931,6 +961,7 @@ static const u32 pplm_fec_2_ethtool[] = {
 	[MLX5E_FEC_RS_528_514] = ETHTOOL_FEC_RS,
 	[MLX5E_FEC_RS_544_514] = ETHTOOL_FEC_RS,
 	[MLX5E_FEC_LLRS_272_257_1] = ETHTOOL_FEC_LLRS,
+	[MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD] = ETHTOOL_FEC_RS,
 };
 
 static u32 pplm2ethtool_fec(u_long fec_mode, unsigned long size)
@@ -1074,50 +1105,51 @@ static void ptys2ethtool_supported_advertised_port(struct mlx5_core_dev *mdev,
 	}
 }
 
-static void get_speed_duplex(struct net_device *netdev,
-			     u32 eth_proto_oper, bool force_legacy,
-			     u16 data_rate_oper,
-			     struct ethtool_link_ksettings *link_ksettings)
+static void get_link_properties(struct net_device *netdev,
+				u32 eth_proto_oper, bool force_legacy,
+				u16 data_rate_oper,
+				struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	u32 speed = SPEED_UNKNOWN;
+	const struct mlx5_link_info *info;
 	u8 duplex = DUPLEX_UNKNOWN;
+	u32 speed = SPEED_UNKNOWN;
+	u32 lanes = LANES_UNKNOWN;
 
 	if (!netif_carrier_ok(netdev))
 		goto out;
 
-	speed = mlx5_port_ptys2speed(priv->mdev, eth_proto_oper, force_legacy);
-	if (!speed) {
-		if (data_rate_oper)
-			speed = 100 * data_rate_oper;
-		else
-			speed = SPEED_UNKNOWN;
-		goto out;
-	}
-
-	duplex = DUPLEX_FULL;
+	info = mlx5_port_ptys2info(priv->mdev, eth_proto_oper, force_legacy);
+	if (info) {
+		speed = info->speed;
+		lanes = info->lanes;
+		duplex = DUPLEX_FULL;
+	} else if (data_rate_oper)
+		speed = 100 * data_rate_oper;
 
 out:
-	link_ksettings->base.speed = speed;
 	link_ksettings->base.duplex = duplex;
+	link_ksettings->base.speed = speed;
+	link_ksettings->lanes = lanes;
 }
 
 static void get_supported(struct mlx5_core_dev *mdev, u32 eth_proto_cap,
 			  struct ethtool_link_ksettings *link_ksettings)
 {
 	unsigned long *supported = link_ksettings->link_modes.supported;
-	ptys2ethtool_supported_link(mdev, supported, eth_proto_cap);
+	bool ext = mlx5_ptys_ext_supported(mdev);
+
+	ptys2ethtool_process_link(eth_proto_cap, ext, false, supported);
 
 	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
 }
 
-static void get_advertising(u32 eth_proto_cap, u8 tx_pause, u8 rx_pause,
+static void get_advertising(u32 eth_proto_admin, u8 tx_pause, u8 rx_pause,
 			    struct ethtool_link_ksettings *link_ksettings,
 			    bool ext)
 {
 	unsigned long *advertising = link_ksettings->link_modes.advertising;
-	ptys2ethtool_adver_link(advertising, eth_proto_cap, ext);
-
+	ptys2ethtool_process_link(eth_proto_admin, ext, true, advertising);
 	if (rx_pause)
 		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
 	if (tx_pause ^ rx_pause)
@@ -1173,7 +1205,7 @@ static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp,
 	unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising;
 	bool ext = mlx5_ptys_ext_supported(mdev);
 
-	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext);
+	ptys2ethtool_process_link(eth_proto_lp, ext, true, lp_advertising);
 }
 
 static int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
@@ -1235,8 +1267,8 @@ static int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 	get_supported(mdev, eth_proto_cap, link_ksettings);
 	get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings,
 			admin_ext);
-	get_speed_duplex(priv->netdev, eth_proto_oper, !admin_ext,
-			 data_rate_oper, link_ksettings);
+	get_link_properties(priv->netdev, eth_proto_oper, !admin_ext,
+			    data_rate_oper, link_ksettings);
 
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
 	connector_type = connector_type < MLX5E_CONNECTOR_TYPE_NUMBER ?
@@ -1341,28 +1373,22 @@ static bool ext_link_mode_requested(const unsigned long *adver)
 	return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static bool ext_requested(u8 autoneg, const unsigned long *adver, bool ext_supported)
-{
-	bool ext_link_mode = ext_link_mode_requested(adver);
-
-	return  autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_supported;
-}
-
 static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 					    const struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_port_eth_proto eproto;
+	struct mlx5_link_info info = {};
 	const unsigned long *adver;
 	bool an_changes = false;
 	u8 an_disable_admin;
 	bool ext_supported;
+	bool ext_requested;
 	u8 an_disable_cap;
 	bool an_disable;
 	u32 link_modes;
 	u8 an_status;
 	u8 autoneg;
-	u32 speed;
 	bool ext;
 	int err;
 
@@ -1370,13 +1396,15 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 
 	adver = link_ksettings->link_modes.advertising;
 	autoneg = link_ksettings->base.autoneg;
-	speed = link_ksettings->base.speed;
+	info.speed = link_ksettings->base.speed;
+	info.lanes = link_ksettings->lanes;
 
 	ext_supported = mlx5_ptys_ext_supported(mdev);
-	ext = ext_requested(autoneg, adver, ext_supported);
-	if (!ext_supported && ext)
+	ext_requested = ext_link_mode_requested(adver);
+	if (!ext_supported && ext_requested)
 		return -EOPNOTSUPP;
 
+	ext = autoneg == AUTONEG_ENABLE ? ext_requested : ext_supported;
 	ethtool2ptys_adver_func = ext ? mlx5e_ethtool2ptys_ext_adver_link :
 				  mlx5e_ethtool2ptys_adver_link;
 	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
@@ -1386,7 +1414,7 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 		goto out;
 	}
 	link_modes = autoneg == AUTONEG_ENABLE ? ethtool2ptys_adver_func(adver) :
-		mlx5_port_speed2linkmodes(mdev, speed, !ext);
+		mlx5_port_info2linkmodes(mdev, &info, !ext);
 
 	err = mlx5e_speed_validate(priv->netdev, ext, link_modes, autoneg);
 	if (err)
@@ -1457,60 +1485,147 @@ static u32 mlx5e_get_rxfh_indir_size(struct net_device *netdev)
 static int mlx5e_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	u32 rss_context = rxfh->rss_context;
-	int err;
+	bool symmetric;
 
 	mutex_lock(&priv->state_lock);
-	err = mlx5e_rx_res_rss_get_rxfh(priv->rx_res, rss_context,
-					rxfh->indir, rxfh->key, &rxfh->hfunc);
+	mlx5e_rx_res_rss_get_rxfh(priv->rx_res, 0, rxfh->indir, rxfh->key,
+				  &rxfh->hfunc, &symmetric);
 	mutex_unlock(&priv->state_lock);
-	return err;
+
+	if (symmetric)
+		rxfh->input_xfrm = RXH_XFRM_SYM_OR_XOR;
+
+	return 0;
 }
 
-static int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
-			  struct netlink_ext_ack *extack)
+static int mlx5e_rxfh_hfunc_check(struct mlx5e_priv *priv,
+				  const struct ethtool_rxfh_param *rxfh,
+				  struct netlink_ext_ack *extack)
 {
-	struct mlx5e_priv *priv = netdev_priv(dev);
-	u32 *rss_context = &rxfh->rss_context;
-	u8 hfunc = rxfh->hfunc;
 	unsigned int count;
-	int err;
-
-	mutex_lock(&priv->state_lock);
 
 	count = priv->channels.params.num_channels;
 
-	if (hfunc == ETH_RSS_HASH_XOR) {
+	if (rxfh->hfunc == ETH_RSS_HASH_XOR) {
 		unsigned int xor8_max_channels = mlx5e_rqt_max_num_channels_allowed_for_xor8();
 
 		if (count > xor8_max_channels) {
-			err = -EINVAL;
-			netdev_err(priv->netdev, "%s: Cannot set RSS hash function to XOR, current number of channels (%d) exceeds the maximum allowed for XOR8 RSS hfunc (%d)\n",
-				   __func__, count, xor8_max_channels);
-			goto unlock;
+			NL_SET_ERR_MSG_FMT_MOD(
+				extack,
+				"Number of channels (%u) exceeds the max for XOR8 RSS (%u)",
+				count, xor8_max_channels);
+			return -EINVAL;
 		}
 	}
 
-	if (*rss_context && rxfh->rss_delete) {
-		err = mlx5e_rx_res_rss_destroy(priv->rx_res, *rss_context);
+	return 0;
+}
+
+static int mlx5e_set_rxfh(struct net_device *dev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
+{
+	bool symmetric = rxfh->input_xfrm == RXH_XFRM_SYM_OR_XOR;
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	u8 hfunc = rxfh->hfunc;
+	int err;
+
+	mutex_lock(&priv->state_lock);
+
+	err = mlx5e_rxfh_hfunc_check(priv, rxfh, extack);
+	if (err)
 		goto unlock;
-	}
 
-	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
-		err = mlx5e_rx_res_rss_init(priv->rx_res, rss_context, count);
-		if (err)
-			goto unlock;
-	}
+	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, rxfh->rss_context,
+					rxfh->indir, rxfh->key,
+					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc,
+					rxfh->input_xfrm == RXH_XFRM_NO_CHANGE ? NULL : &symmetric);
+
+unlock:
+	mutex_unlock(&priv->state_lock);
+	return err;
+}
+
+static int mlx5e_create_rxfh_context(struct net_device *dev,
+				     struct ethtool_rxfh_context *ctx,
+				     const struct ethtool_rxfh_param *rxfh,
+				     struct netlink_ext_ack *extack)
+{
+	bool symmetric = rxfh->input_xfrm == RXH_XFRM_SYM_OR_XOR;
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	u8 hfunc = rxfh->hfunc;
+	int err;
+
+	mutex_lock(&priv->state_lock);
+
+	err = mlx5e_rxfh_hfunc_check(priv, rxfh, extack);
+	if (err)
+		goto unlock;
+
+	err = mlx5e_rx_res_rss_init(priv->rx_res, rxfh->rss_context,
+				    priv->channels.params.num_channels);
+	if (err)
+		goto unlock;
+
+	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, rxfh->rss_context,
+					rxfh->indir, rxfh->key,
+					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc,
+					rxfh->input_xfrm == RXH_XFRM_NO_CHANGE ? NULL : &symmetric);
+	if (err)
+		goto unlock;
 
-	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, *rss_context,
+	mlx5e_rx_res_rss_get_rxfh(priv->rx_res, rxfh->rss_context,
+				  ethtool_rxfh_context_indir(ctx),
+				  ethtool_rxfh_context_key(ctx),
+				  &ctx->hfunc, &symmetric);
+	if (symmetric)
+		ctx->input_xfrm = RXH_XFRM_SYM_OR_XOR;
+
+unlock:
+	mutex_unlock(&priv->state_lock);
+	return err;
+}
+
+static int mlx5e_modify_rxfh_context(struct net_device *dev,
+				     struct ethtool_rxfh_context *ctx,
+				     const struct ethtool_rxfh_param *rxfh,
+				     struct netlink_ext_ack *extack)
+{
+	bool symmetric = rxfh->input_xfrm == RXH_XFRM_SYM_OR_XOR;
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	u8 hfunc = rxfh->hfunc;
+	int err;
+
+	mutex_lock(&priv->state_lock);
+
+	err = mlx5e_rxfh_hfunc_check(priv, rxfh, extack);
+	if (err)
+		goto unlock;
+
+	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, rxfh->rss_context,
 					rxfh->indir, rxfh->key,
-					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc);
+					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc,
+					rxfh->input_xfrm == RXH_XFRM_NO_CHANGE ? NULL : &symmetric);
 
 unlock:
 	mutex_unlock(&priv->state_lock);
 	return err;
 }
 
+static int mlx5e_remove_rxfh_context(struct net_device *dev,
+				     struct ethtool_rxfh_context *ctx,
+				     u32 rss_context,
+				     struct netlink_ext_ack *extack)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	int err;
+
+	mutex_lock(&priv->state_lock);
+	err = mlx5e_rx_res_rss_destroy(priv->rx_res, rss_context);
+	mutex_unlock(&priv->state_lock);
+	return err;
+}
+
 #define MLX5E_PFC_PREVEN_AUTO_TOUT_MSEC		100
 #define MLX5E_PFC_PREVEN_TOUT_MAX_MSEC		8000
 #define MLX5E_PFC_PREVEN_MINOR_PRECENT		85
@@ -1675,6 +1790,7 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 		return 0;
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+				SOF_TIMESTAMPING_TX_SOFTWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
 
@@ -1819,11 +1935,12 @@ static int mlx5e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 }
 
 static void mlx5e_get_fec_stats(struct net_device *netdev,
-				struct ethtool_fec_stats *fec_stats)
+				struct ethtool_fec_stats *fec_stats,
+				struct ethtool_fec_hist *hist)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	mlx5e_stats_fec_get(priv, fec_stats);
+	mlx5e_stats_fec_get(priv, fec_stats, hist);
 }
 
 static int mlx5e_get_fecparam(struct net_device *netdev,
@@ -1915,7 +2032,7 @@ static int mlx5e_get_module_info(struct net_device *netdev,
 	int size_read = 0;
 	u8 data[4] = {0};
 
-	size_read = mlx5_query_module_eeprom(dev, 0, 2, data);
+	size_read = mlx5_query_module_eeprom(dev, 0, 2, data, NULL);
 	if (size_read < 2)
 		return -EIO;
 
@@ -1957,6 +2074,7 @@ static int mlx5e_get_module_eeprom(struct net_device *netdev,
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int offset = ee->offset;
 	int size_read;
+	u8 status = 0;
 	int i = 0;
 
 	if (!ee->len)
@@ -1966,15 +2084,15 @@ static int mlx5e_get_module_eeprom(struct net_device *netdev,
 
 	while (i < ee->len) {
 		size_read = mlx5_query_module_eeprom(mdev, offset, ee->len - i,
-						     data + i);
-
+						     data + i, &status);
 		if (!size_read)
 			/* Done reading */
 			return 0;
 
 		if (size_read < 0) {
-			netdev_err(priv->netdev, "%s: mlx5_query_eeprom failed:0x%x\n",
-				   __func__, size_read);
+			netdev_err(netdev,
+				   "%s: mlx5_query_eeprom failed:0x%x, status %u\n",
+				   __func__, size_read, status);
 			return size_read;
 		}
 
@@ -1994,6 +2112,7 @@ static int mlx5e_get_module_eeprom_by_page(struct net_device *netdev,
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 *data = page_data->data;
 	int size_read;
+	u8 status = 0;
 	int i = 0;
 
 	if (!page_data->length)
@@ -2007,20 +2126,19 @@ static int mlx5e_get_module_eeprom_by_page(struct net_device *netdev,
 	query.page = page_data->page;
 	while (i < page_data->length) {
 		query.size = page_data->length - i;
-		size_read = mlx5_query_module_eeprom_by_page(mdev, &query, data + i);
+		size_read = mlx5_query_module_eeprom_by_page(mdev, &query,
+							     data + i, &status);
 
 		/* Done reading, return how many bytes was read */
 		if (!size_read)
 			return i;
 
-		if (size_read == -EINVAL)
-			return -EINVAL;
 		if (size_read < 0) {
 			NL_SET_ERR_MSG_FMT_MOD(
 				extack,
-				"Query module eeprom by page failed, read %u bytes, err %d\n",
-				i, size_read);
-			return i;
+				"Query module eeprom by page failed, read %u bytes, err %d, status %u",
+				i, size_read, status);
+			return size_read;
 		}
 
 		i += size_read;
@@ -2045,14 +2163,9 @@ int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
 	if (err)
 		return err;
 
-	dev_hold(dev);
-	rtnl_unlock();
-
 	err = mlx5_firmware_flash(mdev, fw, NULL);
 	release_firmware(fw);
 
-	rtnl_lock();
-	dev_put(dev);
 	return err;
 }
 
@@ -2166,7 +2279,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev,
 	if (!MLX5_CAP_GEN(mdev, cqe_compression))
 		return -EOPNOTSUPP;
 
-	rx_filter = priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE;
+	rx_filter = priv->hwtstamp_config.rx_filter != HWTSTAMP_FILTER_NONE;
 	err = mlx5e_modify_rx_cqe_compression_locked(priv, enable, rx_filter);
 	if (err)
 		return err;
@@ -2181,7 +2294,6 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable)
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_params new_params;
-	int err;
 
 	if (enable) {
 		/* Checking the regular RQ here; mlx5e_validate_xsk_param called
@@ -2202,14 +2314,7 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable)
 	MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_RX_STRIDING_RQ, enable);
 	mlx5e_set_rq_type(mdev, &new_params);
 
-	err = mlx5e_safe_switch_params(priv, &new_params, NULL, NULL, true);
-	if (err)
-		return err;
-
-	/* update XDP supported features */
-	mlx5e_set_xdp_feature(netdev);
-
-	return 0;
+	return mlx5e_safe_switch_params(priv, &new_params, NULL, NULL, true);
 }
 
 static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable)
@@ -2370,21 +2475,35 @@ static u32 mlx5e_get_priv_flags(struct net_device *netdev)
 	return priv->channels.params.pflags;
 }
 
+static int mlx5e_get_rxfh_fields(struct net_device *dev,
+				 struct ethtool_rxfh_fields *info)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	return mlx5e_ethtool_get_rxfh_fields(priv, info);
+}
+
+static int mlx5e_set_rxfh_fields(struct net_device *dev,
+				 const struct ethtool_rxfh_fields *cmd,
+				 struct netlink_ext_ack *extack)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	return mlx5e_ethtool_set_rxfh_fields(priv, cmd, extack);
+}
+
+static u32 mlx5e_get_rx_ring_count(struct net_device *dev)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	return priv->channels.params.num_channels;
+}
+
 static int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
 			   u32 *rule_locs)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
-	/* ETHTOOL_GRXRINGS is needed by ethtool -x which is not part
-	 * of rxnfc. We keep this logic out of mlx5e_ethtool_get_rxnfc,
-	 * to avoid breaking "ethtool -x" when mlx5e_ethtool_get_rxnfc
-	 * is compiled out via CONFIG_MLX5_EN_RXNFC=n.
-	 */
-	if (info->cmd == ETHTOOL_GRXRINGS) {
-		info->data = priv->channels.params.num_channels;
-		return 0;
-	}
-
 	return mlx5e_ethtool_get_rxnfc(priv, info, rule_locs);
 }
 
@@ -2607,12 +2726,16 @@ static void mlx5e_get_ts_stats(struct net_device *netdev,
 }
 
 const struct ethtool_ops mlx5e_ethtool_ops = {
-	.cap_rss_ctx_supported	= true,
+	.cap_link_lanes_supported = true,
+	.rxfh_per_ctx_fields	= true,
 	.rxfh_per_ctx_key	= true,
+	.rxfh_max_num_contexts	= MLX5E_MAX_NUM_RSS,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
 				     ETHTOOL_COALESCE_USE_CQE,
+	.supported_input_xfrm = RXH_XFRM_SYM_OR_XOR,
+	.supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT,
 	.get_drvinfo       = mlx5e_get_drvinfo,
 	.get_link          = ethtool_op_get_link,
 	.get_link_ext_state  = mlx5e_get_link_ext_state,
@@ -2633,8 +2756,14 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_rxfh_indir_size = mlx5e_get_rxfh_indir_size,
 	.get_rxfh          = mlx5e_get_rxfh,
 	.set_rxfh          = mlx5e_set_rxfh,
+	.get_rxfh_fields   = mlx5e_get_rxfh_fields,
+	.set_rxfh_fields   = mlx5e_set_rxfh_fields,
+	.create_rxfh_context	= mlx5e_create_rxfh_context,
+	.modify_rxfh_context	= mlx5e_modify_rxfh_context,
+	.remove_rxfh_context	= mlx5e_remove_rxfh_context,
 	.get_rxnfc         = mlx5e_get_rxnfc,
 	.set_rxnfc         = mlx5e_set_rxnfc,
+	.get_rx_ring_count = mlx5e_get_rx_ring_count,
 	.get_tunable       = mlx5e_get_tunable,
 	.set_tunable       = mlx5e_set_tunable,
 	.get_pause_stats   = mlx5e_get_pause_stats,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 05058710d2c7..8928d2dcd43f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -484,7 +484,9 @@ static int mlx5e_vlan_rx_add_svid(struct mlx5e_flow_steering *fs,
 	}
 
 	/* Need to fix some features.. */
+	netdev_lock(netdev);
 	netdev_update_features(netdev);
+	netdev_unlock(netdev);
 	return err;
 }
 
@@ -521,7 +523,9 @@ int mlx5e_fs_vlan_rx_kill_vid(struct mlx5e_flow_steering *fs,
 	} else if (be16_to_cpu(proto) == ETH_P_8021AD) {
 		clear_bit(vid, fs->vlan->active_svlans);
 		mlx5e_fs_del_vlan_rule(fs, MLX5E_VLAN_RULE_TYPE_MATCH_STAG_VID, vid);
+		netdev_lock(netdev);
 		netdev_update_features(netdev);
+		netdev_unlock(netdev);
 	}
 
 	return 0;
@@ -776,7 +780,7 @@ static int mlx5e_create_promisc_table(struct mlx5e_flow_steering *fs)
 	ft_attr.max_fte = MLX5E_PROMISC_TABLE_SIZE;
 	ft_attr.autogroup.max_num_groups = 1;
 	ft_attr.level = MLX5E_PROMISC_FT_LEVEL;
-	ft_attr.prio = MLX5E_NIC_PRIO;
+	ft_attr.prio = MLX5E_PROMISC_PRIO;
 
 	ft->t = mlx5_create_auto_grouped_flow_table(fs->ns, &ft_attr);
 	if (IS_ERR(ft->t)) {
@@ -901,6 +905,9 @@ static void mlx5e_set_inner_ttc_params(struct mlx5e_flow_steering *fs,
 	ft_attr->prio = MLX5E_NIC_PRIO;
 
 	for (tt = 0; tt < MLX5_NUM_TT; tt++) {
+		if (mlx5_ttc_is_decrypted_esp_tt(tt))
+			continue;
+
 		ttc_params->dests[tt].type = MLX5_FLOW_DESTINATION_TYPE_TIR;
 		ttc_params->dests[tt].tir_num =
 			tt == MLX5_TT_ANY ?
@@ -910,9 +917,17 @@ static void mlx5e_set_inner_ttc_params(struct mlx5e_flow_steering *fs,
 	}
 }
 
+static bool mlx5e_ipsec_rss_supported(struct mlx5_core_dev *mdev)
+{
+	return MLX5_CAP_NIC_RX_FT_FIELD_SUPPORT_2(mdev, ipsec_next_header) &&
+	       MLX5_CAP_NIC_RX_FT_FIELD_SUPPORT_2(mdev, outer_l4_type_ext) &&
+	       MLX5_CAP_NIC_RX_FT_FIELD_SUPPORT_2(mdev, inner_l4_type_ext);
+}
+
 void mlx5e_set_ttc_params(struct mlx5e_flow_steering *fs,
 			  struct mlx5e_rx_res *rx_res,
-			  struct ttc_params *ttc_params, bool tunnel)
+			  struct ttc_params *ttc_params, bool tunnel,
+			  bool ipsec_rss)
 
 {
 	struct mlx5_flow_table_attr *ft_attr = &ttc_params->ft_attr;
@@ -923,7 +938,13 @@ void mlx5e_set_ttc_params(struct mlx5e_flow_steering *fs,
 	ft_attr->level = MLX5E_TTC_FT_LEVEL;
 	ft_attr->prio = MLX5E_NIC_PRIO;
 
+	ttc_params->ipsec_rss = ipsec_rss &&
+				mlx5e_ipsec_rss_supported(fs->mdev);
+
 	for (tt = 0; tt < MLX5_NUM_TT; tt++) {
+		if (mlx5_ttc_is_decrypted_esp_tt(tt))
+			continue;
+
 		ttc_params->dests[tt].type = MLX5_FLOW_DESTINATION_TYPE_TIR;
 		ttc_params->dests[tt].tir_num =
 			tt == MLX5_TT_ANY ?
@@ -1289,7 +1310,7 @@ int mlx5e_create_ttc_table(struct mlx5e_flow_steering *fs,
 {
 	struct ttc_params ttc_params = {};
 
-	mlx5e_set_ttc_params(fs, rx_res, &ttc_params, true);
+	mlx5e_set_ttc_params(fs, rx_res, &ttc_params, true, true);
 	fs->ttc = mlx5_create_ttc_table(fs->mdev, &ttc_params);
 	return PTR_ERR_OR_ZERO(fs->ttc);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 773624bb2c5d..63bdef5b4ba5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -704,7 +704,7 @@ static int validate_flow(struct mlx5e_priv *priv,
 		num_tuples += ret;
 		break;
 	default:
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 	if ((fs->flow_type & FLOW_EXT)) {
 		ret = validate_vlan(fs);
@@ -884,25 +884,27 @@ static int flow_type_to_traffic_type(u32 flow_type)
 	case ESP_V6_FLOW:
 		return MLX5_TT_IPV6_IPSEC_ESP;
 	case IPV4_FLOW:
+	case IP_USER_FLOW:
 		return MLX5_TT_IPV4;
 	case IPV6_FLOW:
+	case IPV6_USER_FLOW:
 		return MLX5_TT_IPV6;
 	default:
 		return -EINVAL;
 	}
 }
 
-static int mlx5e_set_rss_hash_opt(struct mlx5e_priv *priv,
-				  struct ethtool_rxnfc *nfc)
+int mlx5e_ethtool_set_rxfh_fields(struct mlx5e_priv *priv,
+				  const struct ethtool_rxfh_fields *nfc,
+				  struct netlink_ext_ack *extack)
 {
 	u8 rx_hash_field = 0;
 	u32 flow_type = 0;
-	u32 rss_idx = 0;
+	u32 rss_idx;
 	int err;
 	int tt;
 
-	if (nfc->flow_type & FLOW_RSS)
-		rss_idx = nfc->rss_context;
+	rss_idx = nfc->rss_context;
 
 	flow_type = flow_type_mask(nfc->flow_type);
 	tt = flow_type_to_traffic_type(flow_type);
@@ -939,16 +941,15 @@ static int mlx5e_set_rss_hash_opt(struct mlx5e_priv *priv,
 	return err;
 }
 
-static int mlx5e_get_rss_hash_opt(struct mlx5e_priv *priv,
-				  struct ethtool_rxnfc *nfc)
+int mlx5e_ethtool_get_rxfh_fields(struct mlx5e_priv *priv,
+				  struct ethtool_rxfh_fields *nfc)
 {
 	int hash_field = 0;
 	u32 flow_type = 0;
-	u32 rss_idx = 0;
+	u32 rss_idx;
 	int tt;
 
-	if (nfc->flow_type & FLOW_RSS)
-		rss_idx = nfc->rss_context;
+	rss_idx = nfc->rss_context;
 
 	flow_type = flow_type_mask(nfc->flow_type);
 	tt = flow_type_to_traffic_type(flow_type);
@@ -984,9 +985,6 @@ int mlx5e_ethtool_set_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *cmd)
 	case ETHTOOL_SRXCLSRLDEL:
 		err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location);
 		break;
-	case ETHTOOL_SRXFH:
-		err = mlx5e_set_rss_hash_opt(priv, cmd);
-		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;
@@ -1011,9 +1009,6 @@ int mlx5e_ethtool_get_rxnfc(struct mlx5e_priv *priv,
 	case ETHTOOL_GRXCLSRLALL:
 		err = mlx5e_ethtool_get_all_flows(priv, info, rule_locs);
 		break;
-	case ETHTOOL_GRXFH:
-		err =  mlx5e_get_rss_hash_opt(priv, info);
-		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 15e765a41d72..6168f0814414 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -39,7 +39,9 @@
 #include <linux/debugfs.h>
 #include <linux/if_bridge.h>
 #include <linux/filter.h>
+#include <net/netdev_lock.h>
 #include <net/netdev_queues.h>
+#include <net/netdev_rx_queue.h>
 #include <net/page_pool/types.h>
 #include <net/pkt_sched.h>
 #include <net/xdp_sock_drv.h>
@@ -50,6 +52,7 @@
 #include "en_tc.h"
 #include "en_rep.h"
 #include "en_accel/ipsec.h"
+#include "en_accel/psp.h"
 #include "en_accel/macsec.h"
 #include "en_accel/en_accel.h"
 #include "en_accel/ktls.h"
@@ -74,10 +77,12 @@
 #include "en/trap.h"
 #include "lib/devcom.h"
 #include "lib/sd.h"
+#include "en/pcie_cong_event.h"
 
 static bool mlx5e_hw_gro_supported(struct mlx5_core_dev *mdev)
 {
-	if (!MLX5_CAP_GEN(mdev, shampo))
+	if (!MLX5_CAP_GEN(mdev, shampo) ||
+	    !MLX5_CAP_SHAMPO(mdev, shampo_header_split_data_merge))
 		return false;
 
 	/* Our HW-GRO implementation relies on "KSM Mkey" for
@@ -228,13 +233,17 @@ static int mlx5e_devcom_event_mpv(int event, void *my_data, void *event_data)
 
 static int mlx5e_devcom_init_mpv(struct mlx5e_priv *priv, u64 *data)
 {
+	struct mlx5_devcom_match_attr attr = {
+		.key.val = *data,
+	};
+
 	priv->devcom = mlx5_devcom_register_component(priv->mdev->priv.devc,
 						      MLX5_DEVCOM_MPV,
-						      *data,
+						      &attr,
 						      mlx5e_devcom_event_mpv,
 						      priv);
-	if (IS_ERR(priv->devcom))
-		return PTR_ERR(priv->devcom);
+	if (!priv->devcom)
+		return -EINVAL;
 
 	if (mlx5_core_is_mp_master(priv->mdev)) {
 		mlx5_devcom_send_event(priv->devcom, MPV_DEVCOM_MASTER_UP,
@@ -247,7 +256,7 @@ static int mlx5e_devcom_init_mpv(struct mlx5e_priv *priv, u64 *data)
 
 static void mlx5e_devcom_cleanup_mpv(struct mlx5e_priv *priv)
 {
-	if (IS_ERR_OR_NULL(priv->devcom))
+	if (!priv->devcom)
 		return;
 
 	if (mlx5_core_is_mp_master(priv->mdev)) {
@@ -257,6 +266,7 @@ static void mlx5e_devcom_cleanup_mpv(struct mlx5e_priv *priv)
 	}
 
 	mlx5_devcom_unregister_component(priv->devcom);
+	priv->devcom = NULL;
 }
 
 static int blocking_event(struct notifier_block *nb, unsigned long event, void *data)
@@ -311,8 +321,8 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
 				       struct mlx5e_icosq *sq,
 				       struct mlx5e_umr_wqe *wqe)
 {
-	struct mlx5_wqe_ctrl_seg      *cseg = &wqe->ctrl;
-	struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->uctrl;
+	struct mlx5_wqe_ctrl_seg      *cseg = &wqe->hdr.ctrl;
+	struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->hdr.uctrl;
 	u16 octowords;
 	u8 ds_cnt;
 
@@ -330,47 +340,6 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
 	ucseg->mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
 }
 
-static int mlx5e_rq_shampo_hd_alloc(struct mlx5e_rq *rq, int node)
-{
-	rq->mpwqe.shampo = kvzalloc_node(sizeof(*rq->mpwqe.shampo),
-					 GFP_KERNEL, node);
-	if (!rq->mpwqe.shampo)
-		return -ENOMEM;
-	return 0;
-}
-
-static void mlx5e_rq_shampo_hd_free(struct mlx5e_rq *rq)
-{
-	kvfree(rq->mpwqe.shampo);
-}
-
-static int mlx5e_rq_shampo_hd_info_alloc(struct mlx5e_rq *rq, int node)
-{
-	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
-
-	shampo->bitmap = bitmap_zalloc_node(shampo->hd_per_wq, GFP_KERNEL,
-					    node);
-	shampo->pages = kvzalloc_node(array_size(shampo->hd_per_wq,
-						 sizeof(*shampo->pages)),
-				     GFP_KERNEL, node);
-	if (!shampo->bitmap || !shampo->pages)
-		goto err_nomem;
-
-	return 0;
-
-err_nomem:
-	kvfree(shampo->bitmap);
-	kvfree(shampo->pages);
-
-	return -ENOMEM;
-}
-
-static void mlx5e_rq_shampo_hd_info_free(struct mlx5e_rq *rq)
-{
-	kvfree(rq->mpwqe.shampo->bitmap);
-	kvfree(rq->mpwqe.shampo->pages);
-}
-
 static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int node)
 {
 	int wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
@@ -393,7 +362,9 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int node)
 		bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
 	}
 
-	mlx5e_build_umr_wqe(rq, rq->icosq, &rq->mpwqe.umr_wqe);
+	mlx5e_build_umr_wqe(rq, rq->icosq,
+			    container_of(&rq->mpwqe.umr_wqe,
+					 struct mlx5e_umr_wqe, hdr));
 
 	return 0;
 }
@@ -581,19 +552,26 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq
 }
 
 static int mlx5e_create_rq_hd_umr_mkey(struct mlx5_core_dev *mdev,
-				       struct mlx5e_rq *rq)
+				       u16 hd_per_wq, __be32 *umr_mkey)
 {
 	u32 max_ksm_size = BIT(MLX5_CAP_GEN(mdev, log_max_klm_list_size));
+	u32 mkey;
+	int err;
 
-	if (max_ksm_size < rq->mpwqe.shampo->hd_per_wq) {
+	if (max_ksm_size < hd_per_wq) {
 		mlx5_core_err(mdev, "max ksm list size 0x%x is smaller than shampo header buffer list size 0x%x\n",
-			      max_ksm_size, rq->mpwqe.shampo->hd_per_wq);
+			      max_ksm_size, hd_per_wq);
 		return -EINVAL;
 	}
 
-	return mlx5e_create_umr_ksm_mkey(mdev, rq->mpwqe.shampo->hd_per_wq,
-					 MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE,
-					 &rq->mpwqe.shampo->mkey);
+	err = mlx5e_create_umr_ksm_mkey(mdev, hd_per_wq,
+					MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE,
+					&mkey);
+	if (err)
+		return err;
+
+	*umr_mkey = cpu_to_be32(mkey);
+	return 0;
 }
 
 static void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
@@ -704,6 +682,27 @@ static void mlx5e_rq_err_cqe_work(struct work_struct *recover_work)
 	mlx5e_reporter_rq_cqe_err(rq);
 }
 
+static void mlx5e_rq_timeout_work(struct work_struct *timeout_work)
+{
+	struct mlx5e_rq *rq = container_of(timeout_work,
+					   struct mlx5e_rq,
+					   rx_timeout_work);
+
+	/* Acquire netdev instance lock to synchronize with channel close and
+	 * reopen flows. Either successfully obtain the lock, or detect that
+	 * channels are closing for another reason, making this work no longer
+	 * necessary.
+	 */
+	while (!netdev_trylock(rq->netdev)) {
+		if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &rq->priv->state))
+			return;
+		msleep(20);
+	}
+
+	mlx5e_reporter_rx_timeout(rq);
+	netdev_unlock(rq->netdev);
+}
+
 static int mlx5e_alloc_mpwqe_rq_drop_page(struct mlx5e_rq *rq)
 {
 	rq->wqe_overflow.page = alloc_page(GFP_KERNEL);
@@ -736,8 +735,8 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param
 	rq->pdev         = c->pdev;
 	rq->netdev       = c->netdev;
 	rq->priv         = c->priv;
-	rq->tstamp       = c->tstamp;
-	rq->clock        = &mdev->clock;
+	rq->hwtstamp_config = &c->priv->hwtstamp_config;
+	rq->clock        = mdev->clock;
 	rq->icosq        = &c->icosq;
 	rq->ix           = c->ix;
 	rq->channel      = c;
@@ -755,6 +754,35 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param
 				  xdp_frag_size);
 }
 
+static int mlx5e_rq_shampo_hd_info_alloc(struct mlx5e_rq *rq, u16 hd_per_wq,
+					 int node)
+{
+	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
+
+	shampo->hd_per_wq = hd_per_wq;
+
+	shampo->bitmap = bitmap_zalloc_node(hd_per_wq, GFP_KERNEL, node);
+	shampo->pages = kvzalloc_node(array_size(hd_per_wq,
+						 sizeof(*shampo->pages)),
+				      GFP_KERNEL, node);
+	if (!shampo->bitmap || !shampo->pages)
+		goto err_nomem;
+
+	return 0;
+
+err_nomem:
+	kvfree(shampo->pages);
+	bitmap_free(shampo->bitmap);
+
+	return -ENOMEM;
+}
+
+static void mlx5e_rq_shampo_hd_info_free(struct mlx5e_rq *rq)
+{
+	kvfree(rq->mpwqe.shampo->pages);
+	bitmap_free(rq->mpwqe.shampo->bitmap);
+}
+
 static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev,
 				struct mlx5e_params *params,
 				struct mlx5e_rq_param *rqp,
@@ -762,42 +790,94 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev,
 				u32 *pool_size,
 				int node)
 {
+	void *wqc = MLX5_ADDR_OF(rqc, rqp->rqc, wq);
+	u8 log_hd_per_page, log_hd_entry_size;
+	u16 hd_per_wq, hd_per_wqe;
+	u32 hd_pool_size;
+	int wq_size;
 	int err;
 
 	if (!test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state))
 		return 0;
-	err = mlx5e_rq_shampo_hd_alloc(rq, node);
-	if (err)
-		goto out;
-	rq->mpwqe.shampo->hd_per_wq =
-		mlx5e_shampo_hd_per_wq(mdev, params, rqp);
-	err = mlx5e_create_rq_hd_umr_mkey(mdev, rq);
+
+	rq->mpwqe.shampo = kvzalloc_node(sizeof(*rq->mpwqe.shampo),
+					 GFP_KERNEL, node);
+	if (!rq->mpwqe.shampo)
+		return -ENOMEM;
+
+	/* split headers data structures */
+	hd_per_wq = mlx5e_shampo_hd_per_wq(mdev, params, rqp);
+	err = mlx5e_rq_shampo_hd_info_alloc(rq, hd_per_wq, node);
 	if (err)
-		goto err_shampo_hd;
-	err = mlx5e_rq_shampo_hd_info_alloc(rq, node);
+		goto err_shampo_hd_info_alloc;
+
+	err = mlx5e_create_rq_hd_umr_mkey(mdev, hd_per_wq,
+					  &rq->mpwqe.shampo->mkey_be);
 	if (err)
-		goto err_shampo_info;
+		goto err_umr_mkey;
+
+	hd_per_wqe = mlx5e_shampo_hd_per_wqe(mdev, params, rqp);
+	wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz));
+
+	BUILD_BUG_ON(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE > PAGE_SHIFT);
+	if (hd_per_wqe >= MLX5E_SHAMPO_WQ_HEADER_PER_PAGE) {
+		log_hd_per_page = MLX5E_SHAMPO_LOG_WQ_HEADER_PER_PAGE;
+		log_hd_entry_size = MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE;
+	} else {
+		log_hd_per_page = order_base_2(hd_per_wqe);
+		log_hd_entry_size = order_base_2(PAGE_SIZE / hd_per_wqe);
+	}
+
+	rq->mpwqe.shampo->hd_per_wqe = hd_per_wqe;
+	rq->mpwqe.shampo->hd_per_page = BIT(log_hd_per_page);
+	rq->mpwqe.shampo->log_hd_per_page = log_hd_per_page;
+	rq->mpwqe.shampo->log_hd_entry_size = log_hd_entry_size;
+
+	hd_pool_size = (hd_per_wqe * wq_size) >> log_hd_per_page;
+
+	if (netif_rxq_has_unreadable_mp(rq->netdev, rq->ix)) {
+		/* Separate page pool for shampo headers */
+		struct page_pool_params pp_params = { };
+
+		pp_params.order     = 0;
+		pp_params.flags     = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+		pp_params.pool_size = hd_pool_size;
+		pp_params.nid       = node;
+		pp_params.dev       = rq->pdev;
+		pp_params.napi      = rq->cq.napi;
+		pp_params.netdev    = rq->netdev;
+		pp_params.dma_dir   = rq->buff.map_dir;
+		pp_params.max_len   = PAGE_SIZE;
+
+		rq->hd_page_pool = page_pool_create(&pp_params);
+		if (IS_ERR(rq->hd_page_pool)) {
+			err = PTR_ERR(rq->hd_page_pool);
+			rq->hd_page_pool = NULL;
+			goto err_hds_page_pool;
+		}
+	} else {
+		/* Common page pool, reserve space for headers. */
+		*pool_size += hd_pool_size;
+		rq->hd_page_pool = NULL;
+	}
+
+	/* gro only data structures */
 	rq->hw_gro_data = kvzalloc_node(sizeof(*rq->hw_gro_data), GFP_KERNEL, node);
 	if (!rq->hw_gro_data) {
 		err = -ENOMEM;
 		goto err_hw_gro_data;
 	}
-	rq->mpwqe.shampo->key =
-		cpu_to_be32(rq->mpwqe.shampo->mkey);
-	rq->mpwqe.shampo->hd_per_wqe =
-		mlx5e_shampo_hd_per_wqe(mdev, params, rqp);
-	rq->mpwqe.shampo->pages_per_wq =
-		rq->mpwqe.shampo->hd_per_wq / MLX5E_SHAMPO_WQ_HEADER_PER_PAGE;
-	*pool_size += rq->mpwqe.shampo->pages_per_wq;
+
 	return 0;
 
 err_hw_gro_data:
+	page_pool_destroy(rq->hd_page_pool);
+err_hds_page_pool:
+	mlx5_core_destroy_mkey(mdev, be32_to_cpu(rq->mpwqe.shampo->mkey_be));
+err_umr_mkey:
 	mlx5e_rq_shampo_hd_info_free(rq);
-err_shampo_info:
-	mlx5_core_destroy_mkey(mdev, rq->mpwqe.shampo->mkey);
-err_shampo_hd:
-	mlx5e_rq_shampo_hd_free(rq);
-out:
+err_shampo_hd_info_alloc:
+	kvfree(rq->mpwqe.shampo);
 	return err;
 }
 
@@ -807,9 +887,12 @@ static void mlx5e_rq_free_shampo(struct mlx5e_rq *rq)
 		return;
 
 	kvfree(rq->hw_gro_data);
+	if (rq->hd_page_pool != rq->page_pool)
+		page_pool_destroy(rq->hd_page_pool);
 	mlx5e_rq_shampo_hd_info_free(rq);
-	mlx5_core_destroy_mkey(rq->mdev, rq->mpwqe.shampo->mkey);
-	mlx5e_rq_shampo_hd_free(rq);
+	mlx5_core_destroy_mkey(rq->mdev,
+			       be32_to_cpu(rq->mpwqe.shampo->mkey_be));
+	kvfree(rq->mpwqe.shampo);
 }
 
 static int mlx5e_alloc_rq(struct mlx5e_params *params,
@@ -827,6 +910,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 
 	rqp->wq.db_numa_node = node;
 	INIT_WORK(&rq->recover_work, mlx5e_rq_err_cqe_work);
+	INIT_WORK(&rq->rx_timeout_work, mlx5e_rq_timeout_work);
 
 	if (params->xdp_prog)
 		bpf_prog_inc(params->xdp_prog);
@@ -912,6 +996,8 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 	if (xsk) {
 		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
 						 MEM_TYPE_XSK_BUFF_POOL, NULL);
+		if (err)
+			goto err_free_by_rq_type;
 		xsk_pool_set_rxq_info(rq->xsk_pool, &rq->xdp_rxq);
 	} else {
 		/* Create a page_pool and register it with rxq */
@@ -926,6 +1012,11 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 		pp_params.netdev    = rq->netdev;
 		pp_params.dma_dir   = rq->buff.map_dir;
 		pp_params.max_len   = PAGE_SIZE;
+		pp_params.queue_idx = rq->ix;
+
+		/* Shampo header data split allow for unreadable netmem */
+		if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state))
+			pp_params.flags |= PP_FLAG_ALLOW_UNREADABLE_NETMEM;
 
 		/* page_pool can be used even when there is no rq->xdp_prog,
 		 * given page_pool does not handle DMA mapping there is no
@@ -938,12 +1029,15 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 			rq->page_pool = NULL;
 			goto err_free_by_rq_type;
 		}
-		if (xdp_rxq_info_is_reg(&rq->xdp_rxq))
+		if (!rq->hd_page_pool)
+			rq->hd_page_pool = rq->page_pool;
+		if (xdp_rxq_info_is_reg(&rq->xdp_rxq)) {
 			err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
 							 MEM_TYPE_PAGE_POOL, rq->page_pool);
+			if (err)
+				goto err_destroy_page_pool;
+		}
 	}
-	if (err)
-		goto err_destroy_page_pool;
 
 	for (i = 0; i < wq_sz; i++) {
 		if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
@@ -1071,7 +1165,8 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_cou
 	if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) {
 		MLX5_SET(wq, wq, log_headers_buffer_entry_num,
 			 order_base_2(rq->mpwqe.shampo->hd_per_wq));
-		MLX5_SET(wq, wq, headers_mkey, rq->mpwqe.shampo->mkey);
+		MLX5_SET(wq, wq, headers_mkey,
+			 be32_to_cpu(rq->mpwqe.shampo->mkey_be));
 	}
 
 	mlx5_fill_page_frag_array(&rq->wq_ctrl.buf,
@@ -1201,7 +1296,8 @@ int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
 	netdev_warn(rq->netdev, "Failed to get min RX wqes on Channel[%d] RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n",
 		    rq->ix, rq->rqn, mlx5e_rqwq_get_cur_sz(rq), min_wqes);
 
-	mlx5e_reporter_rx_timeout(rq);
+	queue_work(rq->priv->wq, &rq->rx_timeout_work);
+
 	return -ETIMEDOUT;
 }
 
@@ -1372,6 +1468,7 @@ void mlx5e_close_rq(struct mlx5e_rq *rq)
 	if (rq->dim)
 		cancel_work_sync(&rq->dim->work);
 	cancel_work_sync(&rq->recover_work);
+	cancel_work_sync(&rq->rx_timeout_work);
 	mlx5e_destroy_rq(rq);
 	mlx5e_free_rx_descs(rq);
 	mlx5e_free_rq(rq);
@@ -1452,7 +1549,7 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->pdev      = c->pdev;
 	sq->mkey_be   = c->mkey_be;
 	sq->channel   = c;
-	sq->uar_map   = mdev->mlx5e_res.hw_objs.bfreg.map;
+	sq->uar_map   = c->bfreg->map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN;
 	sq->xsk_pool  = xsk_pool;
@@ -1537,7 +1634,7 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 	int err;
 
 	sq->channel   = c;
-	sq->uar_map   = mdev->mlx5e_res.hw_objs.bfreg.map;
+	sq->uar_map   = c->bfreg->map;
 	sq->reserved_room = param->stop_room;
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
@@ -1614,7 +1711,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	int err;
 
 	sq->pdev      = c->pdev;
-	sq->clock     = &mdev->clock;
+	sq->clock     = mdev->clock;
 	sq->mkey_be   = c->mkey_be;
 	sq->netdev    = c->netdev;
 	sq->mdev      = c->mdev;
@@ -1622,13 +1719,11 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	sq->priv      = c->priv;
 	sq->ch_ix     = c->ix;
 	sq->txq_ix    = txq_ix;
-	sq->uar_map   = mdev->mlx5e_res.hw_objs.bfreg.map;
+	sq->uar_map   = c->bfreg->map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	sq->max_sq_mpw_wqebbs = mlx5e_get_max_sq_aligned_wqebbs(mdev);
 	INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work);
-	if (!MLX5_CAP_ETH(mdev, wqe_vlan_insert))
-		set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state);
 	if (mlx5_ipsec_device_caps(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
 	if (param->is_mpw)
@@ -1700,7 +1795,7 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev,
 	MLX5_SET(sqc,  sqc, flush_in_error_en, 1);
 
 	MLX5_SET(wq,   wq, wq_type,       MLX5_WQ_TYPE_CYCLIC);
-	MLX5_SET(wq,   wq, uar_page,      mdev->mlx5e_res.hw_objs.bfreg.index);
+	MLX5_SET(wq,   wq, uar_page,      csp->uar_page);
 	MLX5_SET(wq,   wq, log_wq_pg_sz,  csp->wq_ctrl->buf.page_shift -
 					  MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(wq, wq, dbr_addr,      csp->wq_ctrl->db.dma);
@@ -1804,6 +1899,7 @@ int mlx5e_open_txqsq(struct mlx5e_channel *c, u32 tisn, int txq_ix,
 	csp.cqn             = sq->cq.mcq.cqn;
 	csp.wq_ctrl         = &sq->wq_ctrl;
 	csp.min_inline_mode = sq->min_inline_mode;
+	csp.uar_page        = c->bfreg->index;
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, qos_queue_group_id, &sq->sqn);
 	if (err)
 		goto err_free_txqsq;
@@ -1901,7 +1997,20 @@ void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
 	struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq,
 					      recover_work);
 
+	/* Recovering queues means re-enabling NAPI, which requires the netdev
+	 * instance lock. However, SQ closing flows have to wait for work tasks
+	 * to finish while also holding the netdev instance lock. So either get
+	 * the lock or find that the SQ is no longer enabled and thus this work
+	 * is not relevant anymore.
+	 */
+	while (!netdev_trylock(sq->netdev)) {
+		if (!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))
+			return;
+		msleep(20);
+	}
+
 	mlx5e_reporter_tx_err_cqe(sq);
+	netdev_unlock(sq->netdev);
 }
 
 static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
@@ -1961,6 +2070,7 @@ static int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params
 	csp.cqn             = sq->cq.mcq.cqn;
 	csp.wq_ctrl         = &sq->wq_ctrl;
 	csp.min_inline_mode = params->tx_min_inline_mode;
+	csp.uar_page        = c->bfreg->index;
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, 0, &sq->sqn);
 	if (err)
 		goto err_free_icosq;
@@ -2021,43 +2131,15 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
 	csp.cqn             = sq->cq.mcq.cqn;
 	csp.wq_ctrl         = &sq->wq_ctrl;
 	csp.min_inline_mode = sq->min_inline_mode;
+	csp.uar_page        = c->bfreg->index;
 	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 
-	if (param->is_xdp_mb)
-		set_bit(MLX5E_SQ_STATE_XDP_MULTIBUF, &sq->state);
-
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, 0, &sq->sqn);
 	if (err)
 		goto err_free_xdpsq;
 
 	mlx5e_set_xmit_fp(sq, param->is_mpw);
 
-	if (!param->is_mpw && !test_bit(MLX5E_SQ_STATE_XDP_MULTIBUF, &sq->state)) {
-		unsigned int ds_cnt = MLX5E_TX_WQE_EMPTY_DS_COUNT + 1;
-		unsigned int inline_hdr_sz = 0;
-		int i;
-
-		if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
-			inline_hdr_sz = MLX5E_XDP_MIN_INLINE;
-			ds_cnt++;
-		}
-
-		/* Pre initialize fixed WQE fields */
-		for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
-			struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
-			struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
-			struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
-
-			sq->db.wqe_info[i] = (struct mlx5e_xdp_wqe_info) {
-				.num_wqebbs = 1,
-				.num_pkts   = 1,
-			};
-
-			cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
-			eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
-		}
-	}
-
 	return 0;
 
 err_free_xdpsq:
@@ -2087,7 +2169,7 @@ static struct mlx5e_xdpsq *mlx5e_open_xdpredirect_sq(struct mlx5e_channel *c,
 	struct mlx5e_xdpsq *xdpsq;
 	int err;
 
-	xdpsq = kvzalloc_node(sizeof(*xdpsq), GFP_KERNEL, c->cpu);
+	xdpsq = kvzalloc_node(sizeof(*xdpsq), GFP_KERNEL, cpu_to_node(c->cpu));
 	if (!xdpsq)
 		return ERR_PTR(-ENOMEM);
 
@@ -2120,6 +2202,7 @@ static void mlx5e_close_xdpredirect_sq(struct mlx5e_xdpsq *xdpsq)
 static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev,
 				 struct net_device *netdev,
 				 struct workqueue_struct *workqueue,
+				 struct mlx5_uars_page *uar,
 				 struct mlx5e_cq_param *param,
 				 struct mlx5e_cq *cq)
 {
@@ -2136,7 +2219,6 @@ static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev,
 	mcq->set_ci_db  = cq->wq_ctrl.db.db;
 	mcq->arm_db     = cq->wq_ctrl.db.db + 1;
 	*mcq->set_ci_db = 0;
-	*mcq->arm_db    = 0;
 	mcq->vector     = param->eq_ix;
 	mcq->comp       = mlx5e_completion_event;
 	mcq->event      = mlx5e_cq_error_event;
@@ -2151,6 +2233,7 @@ static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev,
 	cq->mdev = mdev;
 	cq->netdev = netdev;
 	cq->workqueue = workqueue;
+	cq->uar = uar;
 
 	return 0;
 }
@@ -2166,7 +2249,8 @@ static int mlx5e_alloc_cq(struct mlx5_core_dev *mdev,
 	param->wq.db_numa_node  = ccp->node;
 	param->eq_ix            = ccp->ix;
 
-	err = mlx5e_alloc_cq_common(mdev, ccp->netdev, ccp->wq, param, cq);
+	err = mlx5e_alloc_cq_common(mdev, ccp->netdev, ccp->wq,
+				    ccp->uar, param, cq);
 
 	cq->napi     = ccp->napi;
 	cq->ch_stats = ccp->ch_stats;
@@ -2211,7 +2295,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 	MLX5_SET(cqc, cqc, cq_period_mode, mlx5e_cq_period_mode(param->cq_period_mode));
 
 	MLX5_SET(cqc,   cqc, c_eqn_or_apu_element, eqn);
-	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.uar->index);
+	MLX5_SET(cqc,   cqc, uar_page,      cq->uar->index);
 	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
 					    MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(cqc, cqc, dbr_addr,      cq->wq_ctrl.db.dma);
@@ -2528,7 +2612,7 @@ static int mlx5e_open_queues(struct mlx5e_channel *c,
 	if (err)
 		goto err_close_icosq_cq;
 
-	if (netdev_ops->ndo_xdp_xmit) {
+	if (netdev_ops->ndo_xdp_xmit && c->xdp) {
 		c->xdpsq = mlx5e_open_xdpredirect_sq(c, params, cparam, &ccp);
 		if (IS_ERR(c->xdpsq)) {
 			err = PTR_ERR(c->xdpsq);
@@ -2678,6 +2762,20 @@ void mlx5e_trigger_napi_sched(struct napi_struct *napi)
 	local_bh_enable();
 }
 
+static void mlx5e_channel_pick_doorbell(struct mlx5e_channel *c)
+{
+	struct mlx5e_hw_objs *hw_objs = &c->mdev->mlx5e_res.hw_objs;
+
+	/* No dedicated Ethernet doorbells, use the global one. */
+	if (hw_objs->num_bfregs == 0) {
+		c->bfreg = &c->mdev->priv.bfreg;
+		return;
+	}
+
+	/* Round-robin between doorbells. */
+	c->bfreg = hw_objs->bfregs + c->vec_ix % hw_objs->num_bfregs;
+}
+
 static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 			      struct mlx5e_params *params,
 			      struct xsk_buff_pool *xsk_pool,
@@ -2718,7 +2816,6 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 
 	c->priv     = priv;
 	c->mdev     = mdev;
-	c->tstamp   = &priv->tstamp;
 	c->ix       = ix;
 	c->vec_ix   = vec_ix;
 	c->sd_ix    = mlx5_sd_ch_ix_get_dev_ix(mdev, ix);
@@ -2732,8 +2829,10 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->aff_mask = irq_get_effective_affinity_mask(irq);
 	c->lag_port = mlx5e_enumerate_lag_port(mdev, ix);
 
-	netif_napi_add_config(netdev, &c->napi, mlx5e_napi_poll, ix);
-	netif_napi_set_irq(&c->napi, irq);
+	mlx5e_channel_pick_doorbell(c);
+
+	netif_napi_add_config_locked(netdev, &c->napi, mlx5e_napi_poll, ix);
+	netif_napi_set_irq_locked(&c->napi, irq);
 
 	err = mlx5e_open_queues(c, params, cparam);
 	if (unlikely(err))
@@ -2755,7 +2854,7 @@ err_close_queues:
 	mlx5e_close_queues(c);
 
 err_napi_del:
-	netif_napi_del(&c->napi);
+	netif_napi_del_locked(&c->napi);
 
 err_free:
 	kvfree(cparam);
@@ -2768,7 +2867,7 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
 {
 	int tc;
 
-	napi_enable(&c->napi);
+	napi_enable_locked(&c->napi);
 
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_activate_txqsq(&c->sq[tc]);
@@ -2800,7 +2899,7 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
 		mlx5e_deactivate_txqsq(&c->sq[tc]);
 	mlx5e_qos_deactivate_queues(c);
 
-	napi_disable(&c->napi);
+	napi_disable_locked(&c->napi);
 }
 
 static void mlx5e_close_channel(struct mlx5e_channel *c)
@@ -2809,7 +2908,7 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 		mlx5e_close_xsk(c);
 	mlx5e_close_queues(c);
 	mlx5e_qos_close_queues(c);
-	netif_napi_del(&c->napi);
+	netif_napi_del_locked(&c->napi);
 
 	kvfree(c);
 }
@@ -3266,16 +3365,17 @@ static int mlx5e_switch_priv_params(struct mlx5e_priv *priv,
 		}
 	}
 
+	mlx5e_set_xdp_feature(priv);
 	return 0;
 }
 
 static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
+				      struct mlx5e_channels *old_chs,
 				      struct mlx5e_channels *new_chs,
 				      mlx5e_fp_preactivate preactivate,
 				      void *context)
 {
 	struct net_device *netdev = priv->netdev;
-	struct mlx5e_channels old_chs;
 	int carrier_ok;
 	int err = 0;
 
@@ -3284,7 +3384,6 @@ static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
 
 	mlx5e_deactivate_priv_channels(priv);
 
-	old_chs = priv->channels;
 	priv->channels = *new_chs;
 
 	/* New channels are ready to roll, call the preactivate hook if needed
@@ -3293,12 +3392,14 @@ static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
 	if (preactivate) {
 		err = preactivate(priv, context);
 		if (err) {
-			priv->channels = old_chs;
+			priv->channels = *old_chs;
 			goto out;
 		}
 	}
 
-	mlx5e_close_channels(&old_chs);
+	mlx5e_set_xdp_feature(priv);
+	if (!MLX5_CAP_GEN(priv->mdev, tis_tir_td_order))
+		mlx5e_close_channels(old_chs);
 	priv->profile->update_rx(priv);
 
 	mlx5e_selq_apply(&priv->selq);
@@ -3317,16 +3418,20 @@ int mlx5e_safe_switch_params(struct mlx5e_priv *priv,
 			     mlx5e_fp_preactivate preactivate,
 			     void *context, bool reset)
 {
-	struct mlx5e_channels *new_chs;
+	struct mlx5e_channels *old_chs, *new_chs;
 	int err;
 
 	reset &= test_bit(MLX5E_STATE_OPENED, &priv->state);
 	if (!reset)
 		return mlx5e_switch_priv_params(priv, params, preactivate, context);
 
+	old_chs = kzalloc(sizeof(*old_chs), GFP_KERNEL);
 	new_chs = kzalloc(sizeof(*new_chs), GFP_KERNEL);
-	if (!new_chs)
-		return -ENOMEM;
+	if (!old_chs || !new_chs) {
+		err = -ENOMEM;
+		goto err_free_chs;
+	}
+
 	new_chs->params = *params;
 
 	mlx5e_selq_prepare_params(&priv->selq, &new_chs->params);
@@ -3335,11 +3440,18 @@ int mlx5e_safe_switch_params(struct mlx5e_priv *priv,
 	if (err)
 		goto err_cancel_selq;
 
-	err = mlx5e_switch_priv_channels(priv, new_chs, preactivate, context);
+	*old_chs = priv->channels;
+
+	err = mlx5e_switch_priv_channels(priv, old_chs, new_chs,
+					 preactivate, context);
 	if (err)
 		goto err_close;
 
+	if (MLX5_CAP_GEN(priv->mdev, tis_tir_td_order))
+		mlx5e_close_channels(old_chs);
+
 	kfree(new_chs);
+	kfree(old_chs);
 	return 0;
 
 err_close:
@@ -3347,7 +3459,9 @@ err_close:
 
 err_cancel_selq:
 	mlx5e_selq_cancel(&priv->selq);
+err_free_chs:
 	kfree(new_chs);
+	kfree(old_chs);
 	return err;
 }
 
@@ -3358,8 +3472,8 @@ int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv)
 
 void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 {
-	priv->tstamp.tx_type   = HWTSTAMP_TX_OFF;
-	priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE;
+	priv->hwtstamp_config.tx_type   = HWTSTAMP_TX_OFF;
+	priv->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
 }
 
 static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev,
@@ -3503,7 +3617,8 @@ static int mlx5e_alloc_drop_cq(struct mlx5e_priv *priv,
 	param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev));
 	param->wq.db_numa_node  = dev_to_node(mlx5_core_dma_dev(mdev));
 
-	return mlx5e_alloc_cq_common(priv->mdev, priv->netdev, priv->wq, param, cq);
+	return mlx5e_alloc_cq_common(priv->mdev, priv->netdev, priv->wq,
+				     mdev->priv.bfreg.up, param, cq);
 }
 
 int mlx5e_open_drop_rq(struct mlx5e_priv *priv,
@@ -3816,8 +3931,11 @@ static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
 	/* MQPRIO is another toplevel qdisc that can't be attached
 	 * simultaneously with the offloaded HTB.
 	 */
-	if (WARN_ON(mlx5e_selq_is_htb_enabled(&priv->selq)))
-		return -EINVAL;
+	if (mlx5e_selq_is_htb_enabled(&priv->selq)) {
+		NL_SET_ERR_MSG_MOD(mqprio->extack,
+				   "MQPRIO cannot be configured when HTB offload is enabled.");
+		return -EOPNOTSUPP;
+	}
 
 	switch (mqprio->mode) {
 	case TC_MQPRIO_MODE_DCB:
@@ -3908,6 +4026,11 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s)
 		s->rx_bytes     += rq_stats->bytes;
 		s->multicast    += rq_stats->mcast_packets;
 	}
+
+#ifdef CONFIG_MLX5_EN_PSP
+	if (priv->psp)
+		s->tx_dropped	+= atomic_read(&priv->psp->tx_drop);
+#endif
 }
 
 void
@@ -4053,10 +4176,6 @@ static int set_feature_hw_gro(struct net_device *netdev, bool enable)
 
 	if (enable) {
 		new_params.packet_merge.type = MLX5E_PACKET_MERGE_SHAMPO;
-		new_params.packet_merge.shampo.match_criteria_type =
-			MLX5_RQC_SHAMPO_MATCH_CRITERIA_TYPE_EXTENDED;
-		new_params.packet_merge.shampo.alignment_granularity =
-			MLX5_RQC_SHAMPO_NO_MATCH_ALIGNMENT_GRANULARITY_STRIDE;
 	} else if (new_params.packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) {
 		new_params.packet_merge.type = MLX5E_PACKET_MERGE_NONE;
 	} else {
@@ -4292,24 +4411,23 @@ static int mlx5e_handle_feature(struct net_device *netdev,
 	return 0;
 }
 
-void mlx5e_set_xdp_feature(struct net_device *netdev)
+void mlx5e_set_xdp_feature(struct mlx5e_priv *priv)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_params *params = &priv->channels.params;
-	xdp_features_t val;
+	struct net_device *netdev = priv->netdev;
+	xdp_features_t val = 0;
 
-	if (!netdev->netdev_ops->ndo_bpf ||
-	    params->packet_merge.type != MLX5E_PACKET_MERGE_NONE) {
-		xdp_clear_features_flag(netdev);
-		return;
-	}
+	if (netdev->netdev_ops->ndo_bpf &&
+	    params->packet_merge.type == MLX5E_PACKET_MERGE_NONE)
+		val = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+		      NETDEV_XDP_ACT_XSK_ZEROCOPY |
+		      NETDEV_XDP_ACT_RX_SG;
+
+	if (netdev->netdev_ops->ndo_xdp_xmit && params->xdp_prog)
+		val |= NETDEV_XDP_ACT_NDO_XMIT |
+			NETDEV_XDP_ACT_NDO_XMIT_SG;
 
-	val = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
-	      NETDEV_XDP_ACT_XSK_ZEROCOPY |
-	      NETDEV_XDP_ACT_RX_SG |
-	      NETDEV_XDP_ACT_NDO_XMIT |
-	      NETDEV_XDP_ACT_NDO_XMIT_SG;
-	xdp_set_features_flag(netdev, val);
+	xdp_set_features_flag_locked(netdev, val);
 }
 
 int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
@@ -4344,9 +4462,6 @@ int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
 		return -EINVAL;
 	}
 
-	/* update XDP supported features */
-	mlx5e_set_xdp_feature(netdev);
-
 	return 0;
 }
 
@@ -4373,12 +4488,17 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev
 	if (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
 		netdev_warn(netdev, "Disabling HW_VLAN CTAG FILTERING, not supported in switchdev mode\n");
 
+	features &= ~NETIF_F_HW_MACSEC;
+	if (netdev->features & NETIF_F_HW_MACSEC)
+		netdev_warn(netdev, "Disabling HW MACsec offload, not supported in switchdev mode\n");
+
 	return features;
 }
 
 static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
 					    netdev_features_t features)
 {
+	struct netdev_config *cfg = netdev->cfg_pending;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_vlan_table *vlan;
 	struct mlx5e_params *params;
@@ -4445,11 +4565,18 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
 		}
 	}
 
+	/* The header-data split ring param requires HW GRO to stay enabled. */
+	if (cfg && cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED &&
+	    !(features & NETIF_F_GRO_HW)) {
+		netdev_warn(netdev, "Keeping HW-GRO enabled, TCP header-data split depends on it\n");
+		features |= NETIF_F_GRO_HW;
+	}
+
 	if (mlx5e_is_uplink_rep(priv)) {
 		features = mlx5e_fix_uplink_rep_features(netdev, features);
-		netdev->netns_local = true;
+		netdev->netns_immutable = true;
 	} else {
-		netdev->netns_local = false;
+		netdev->netns_immutable = false;
 	}
 
 	mutex_unlock(&priv->state_lock);
@@ -4642,22 +4769,23 @@ static int mlx5e_hwstamp_config_ptp_rx(struct mlx5e_priv *priv, bool ptp_rx)
 					&new_params.ptp_rx, true);
 }
 
-int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
+int mlx5e_hwtstamp_set(struct mlx5e_priv *priv,
+		       struct kernel_hwtstamp_config *config,
+		       struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
 	bool rx_cqe_compress_def;
 	bool ptp_rx;
 	int err;
 
 	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz) ||
-	    (mlx5_clock_get_ptp_index(priv->mdev) == -1))
+	    (mlx5_clock_get_ptp_index(priv->mdev) == -1)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Timestamps are not supported on this device");
 		return -EOPNOTSUPP;
-
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	}
 
 	/* TX HW timestamp */
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 	case HWTSTAMP_TX_ON:
 		break;
@@ -4669,7 +4797,7 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
 	rx_cqe_compress_def = priv->channels.params.rx_cqe_compress_def;
 
 	/* RX HW timestamp */
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		ptp_rx = false;
 		break;
@@ -4688,7 +4816,7 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 	case HWTSTAMP_FILTER_NTP_ALL:
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		/* ptp_rx is set if both HW TS is set and CQE
 		 * compression is set
 		 */
@@ -4701,47 +4829,50 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
 
 	if (!mlx5e_profile_feature_cap(priv->profile, PTP_RX))
 		err = mlx5e_hwstamp_config_no_ptp_rx(priv,
-						     config.rx_filter != HWTSTAMP_FILTER_NONE);
+						     config->rx_filter != HWTSTAMP_FILTER_NONE);
 	else
 		err = mlx5e_hwstamp_config_ptp_rx(priv, ptp_rx);
 	if (err)
 		goto err_unlock;
 
-	memcpy(&priv->tstamp, &config, sizeof(config));
+	priv->hwtstamp_config = *config;
 	mutex_unlock(&priv->state_lock);
 
 	/* might need to fix some features */
 	netdev_update_features(priv->netdev);
 
-	return copy_to_user(ifr->ifr_data, &config,
-			    sizeof(config)) ? -EFAULT : 0;
+	return 0;
 err_unlock:
 	mutex_unlock(&priv->state_lock);
 	return err;
 }
 
-int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr)
+static int mlx5e_hwtstamp_set_ndo(struct net_device *netdev,
+				  struct kernel_hwtstamp_config *config,
+				  struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config *cfg = &priv->tstamp;
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_hwtstamp_set(priv, config, extack);
+}
 
+int mlx5e_hwtstamp_get(struct mlx5e_priv *priv,
+		       struct kernel_hwtstamp_config *config)
+{
 	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
 		return -EOPNOTSUPP;
 
-	return copy_to_user(ifr->ifr_data, cfg, sizeof(*cfg)) ? -EFAULT : 0;
+	*config = priv->hwtstamp_config;
+
+	return 0;
 }
 
-static int mlx5e_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int mlx5e_hwtstamp_get_ndo(struct net_device *dev,
+				  struct kernel_hwtstamp_config *config)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return mlx5e_hwstamp_set(priv, ifr);
-	case SIOCGHWTSTAMP:
-		return mlx5e_hwstamp_get(priv, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
+	return mlx5e_hwtstamp_get(priv, config);
 }
 
 #ifdef CONFIG_MLX5_ESWITCH
@@ -4988,21 +5119,19 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 	struct net_device *netdev = priv->netdev;
 	int i;
 
-	/* Take rtnl_lock to ensure no change in netdev->real_num_tx_queues
-	 * through this flow. However, channel closing flows have to wait for
-	 * this work to finish while holding rtnl lock too. So either get the
-	 * lock or find that channels are being closed for other reason and
-	 * this work is not relevant anymore.
+	/* Recovering the TX queues implies re-enabling NAPI, which requires
+	 * the netdev instance lock.
+	 * However, channel closing flows have to wait for this work to finish
+	 * while holding the same lock. So either get the lock or find that
+	 * channels are being closed for other reason and this work is not
+	 * relevant anymore.
 	 */
-	while (!rtnl_trylock()) {
+	while (!netdev_trylock(netdev)) {
 		if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state))
 			return;
 		msleep(20);
 	}
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		goto unlock;
-
 	for (i = 0; i < netdev->real_num_tx_queues; i++) {
 		struct netdev_queue *dev_queue =
 			netdev_get_tx_queue(netdev, i);
@@ -5016,8 +5145,7 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 			break;
 	}
 
-unlock:
-	rtnl_unlock();
+	netdev_unlock(netdev);
 }
 
 static void mlx5e_tx_timeout(struct net_device *dev, unsigned int txqueue)
@@ -5132,11 +5260,9 @@ static int mlx5e_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 mode, setting;
-	int err;
 
-	err = mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting);
-	if (err)
-		return err;
+	if (mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting))
+		return -EOPNOTSUPP;
 	mode = setting ? BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB;
 	return ndo_dflt_bridge_getlink(skb, pid, seq, dev,
 				       mode,
@@ -5187,13 +5313,14 @@ const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_set_features        = mlx5e_set_features,
 	.ndo_fix_features        = mlx5e_fix_features,
 	.ndo_change_mtu          = mlx5e_change_nic_mtu,
-	.ndo_eth_ioctl            = mlx5e_ioctl,
 	.ndo_set_tx_maxrate      = mlx5e_set_tx_maxrate,
 	.ndo_features_check      = mlx5e_features_check,
 	.ndo_tx_timeout          = mlx5e_tx_timeout,
 	.ndo_bpf		 = mlx5e_xdp,
 	.ndo_xdp_xmit            = mlx5e_xdp_xmit,
 	.ndo_xsk_wakeup          = mlx5e_xsk_wakeup,
+	.ndo_hwtstamp_get        = mlx5e_hwtstamp_get_ndo,
+	.ndo_hwtstamp_set        = mlx5e_hwtstamp_set_ndo,
 #ifdef CONFIG_MLX5_EN_ARFS
 	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
 #endif
@@ -5314,8 +5441,7 @@ void mlx5e_vxlan_set_netdev_info(struct mlx5e_priv *priv)
 
 	priv->nic_info.set_port = mlx5e_vxlan_set_port;
 	priv->nic_info.unset_port = mlx5e_vxlan_unset_port;
-	priv->nic_info.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-				UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN;
+	priv->nic_info.flags = UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN;
 	priv->nic_info.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN;
 	/* Don't count the space hard-coded to the IANA port */
 	priv->nic_info.tables[0].n_entries =
@@ -5343,7 +5469,6 @@ static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i,
 	struct mlx5e_rq_stats *xskrq_stats;
 	struct mlx5e_rq_stats *rq_stats;
 
-	ASSERT_RTNL();
 	if (mlx5e_is_uplink_rep(priv) || !priv->stats_nch)
 		return;
 
@@ -5363,7 +5488,6 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i,
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_sq_stats *sq_stats;
 
-	ASSERT_RTNL();
 	if (!priv->stats_nch)
 		return;
 
@@ -5384,7 +5508,6 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 	struct mlx5e_ptp *ptp_channel;
 	int i, tc;
 
-	ASSERT_RTNL();
 	if (!mlx5e_is_uplink_rep(priv)) {
 		rx->packets = 0;
 		rx->bytes = 0;
@@ -5468,6 +5591,127 @@ static const struct netdev_stat_ops mlx5e_stat_ops = {
 	.get_base_stats      = mlx5e_get_base_stats,
 };
 
+struct mlx5_qmgmt_data {
+	struct mlx5e_channel *c;
+	struct mlx5e_channel_param cparam;
+};
+
+static int mlx5e_queue_mem_alloc(struct net_device *dev, void *newq,
+				 int queue_index)
+{
+	struct mlx5_qmgmt_data *new = (struct mlx5_qmgmt_data *)newq;
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_channels *chs = &priv->channels;
+	struct mlx5e_params params = chs->params;
+	struct mlx5_core_dev *mdev;
+	int err;
+
+	mutex_lock(&priv->state_lock);
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		err = -ENODEV;
+		goto unlock;
+	}
+
+	if (queue_index >= chs->num) {
+		err = -ERANGE;
+		goto unlock;
+	}
+
+	if (MLX5E_GET_PFLAG(&chs->params, MLX5E_PFLAG_TX_PORT_TS) ||
+	    chs->params.ptp_rx   ||
+	    chs->params.xdp_prog ||
+	    priv->htb) {
+		netdev_err(priv->netdev,
+			   "Cloning channels with Port/rx PTP, XDP or HTB is not supported\n");
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, queue_index);
+	err = mlx5e_build_channel_param(mdev, &params, &new->cparam);
+	if (err)
+		goto unlock;
+
+	err = mlx5e_open_channel(priv, queue_index, &params, NULL, &new->c);
+unlock:
+	mutex_unlock(&priv->state_lock);
+	return err;
+}
+
+static void mlx5e_queue_mem_free(struct net_device *dev, void *mem)
+{
+	struct mlx5_qmgmt_data *data = (struct mlx5_qmgmt_data *)mem;
+
+	/* not supposed to happen since mlx5e_queue_start never fails
+	 * but this is how this should be implemented just in case
+	 */
+	if (data->c)
+		mlx5e_close_channel(data->c);
+}
+
+static int mlx5e_queue_stop(struct net_device *dev, void *oldq, int queue_index)
+{
+	/* In mlx5 a txq cannot be simply stopped in isolation, only restarted.
+	 * mlx5e_queue_start does not fail, we stop the old queue there.
+	 * TODO: Improve this.
+	 */
+	return 0;
+}
+
+static int mlx5e_queue_start(struct net_device *dev, void *newq,
+			     int queue_index)
+{
+	struct mlx5_qmgmt_data *new = (struct mlx5_qmgmt_data *)newq;
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_channel *old;
+
+	mutex_lock(&priv->state_lock);
+
+	/* stop and close the old */
+	old = priv->channels.c[queue_index];
+	mlx5e_deactivate_priv_channels(priv);
+	/* close old before activating new, to avoid napi conflict */
+	mlx5e_close_channel(old);
+
+	/* start the new */
+	priv->channels.c[queue_index] = new->c;
+	mlx5e_activate_priv_channels(priv);
+	mutex_unlock(&priv->state_lock);
+	return 0;
+}
+
+static struct device *mlx5e_queue_get_dma_dev(struct net_device *dev,
+					      int queue_index)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_channels *channels;
+	struct device *pdev = NULL;
+	struct mlx5e_channel *ch;
+
+	channels = &priv->channels;
+
+	mutex_lock(&priv->state_lock);
+
+	if (queue_index >= channels->num)
+		goto out;
+
+	ch = channels->c[queue_index];
+	pdev = ch->pdev;
+out:
+	mutex_unlock(&priv->state_lock);
+
+	return pdev;
+}
+
+static const struct netdev_queue_mgmt_ops mlx5e_queue_mgmt_ops = {
+	.ndo_queue_mem_size	=	sizeof(struct mlx5_qmgmt_data),
+	.ndo_queue_mem_alloc	=	mlx5e_queue_mem_alloc,
+	.ndo_queue_mem_free	=	mlx5e_queue_mem_free,
+	.ndo_queue_start	=	mlx5e_queue_start,
+	.ndo_queue_stop		=	mlx5e_queue_stop,
+	.ndo_queue_get_dma_dev	=	mlx5e_queue_get_dma_dev,
+};
+
 static void mlx5e_build_nic_netdev(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -5478,8 +5722,11 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	SET_NETDEV_DEV(netdev, mdev->device);
 
 	netdev->netdev_ops = &mlx5e_netdev_ops;
+	netdev->queue_mgmt_ops = &mlx5e_queue_mgmt_ops;
 	netdev->xdp_metadata_ops = &mlx5e_xdp_metadata_ops;
 	netdev->xsk_tx_metadata_ops = &mlx5e_xsk_tx_metadata_ops;
+	netdev->request_ops_lock = true;
+	netdev_lockdep_set_classes(netdev);
 
 	mlx5e_dcbnl_build_netdev(netdev);
 
@@ -5518,17 +5765,17 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 						   MLX5E_MPWRQ_UMR_MODE_ALIGNED))
 		netdev->vlan_features    |= NETIF_F_LRO;
 
+	if (mlx5e_hw_gro_supported(mdev) &&
+	    mlx5e_check_fragmented_striding_rq_cap(mdev, PAGE_SHIFT,
+						   MLX5E_MPWRQ_UMR_MODE_ALIGNED))
+		netdev->vlan_features |= NETIF_F_GRO_HW;
+
 	netdev->hw_features       = netdev->vlan_features;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_TX;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_RX;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_STAG_TX;
 
-	if (mlx5e_hw_gro_supported(mdev) &&
-	    mlx5e_check_fragmented_striding_rq_cap(mdev, PAGE_SHIFT,
-						   MLX5E_MPWRQ_UMR_MODE_ALIGNED))
-		netdev->hw_features    |= NETIF_F_GRO_HW;
-
 	if (mlx5e_tunnel_any_tx_proto_supported(mdev)) {
 		netdev->hw_enc_features |= NETIF_F_HW_CSUM;
 		netdev->hw_enc_features |= NETIF_F_TSO;
@@ -5607,8 +5854,10 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 
 	netdev->priv_flags       |= IFF_UNICAST_FLT;
 
+	netdev->netmem_tx = true;
+
 	netif_set_tso_max_size(netdev, GSO_MAX_SIZE);
-	mlx5e_set_xdp_feature(netdev);
+	mlx5e_set_xdp_feature(priv);
 	mlx5e_set_netdev_dev_addr(netdev);
 	mlx5e_macsec_build_netdev(priv);
 	mlx5e_ipsec_build_netdev(priv);
@@ -5688,6 +5937,10 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 	}
 	priv->fs = fs;
 
+	err = mlx5e_psp_init(priv);
+	if (err)
+		mlx5_core_err(mdev, "PSP initialization failed, %d\n", err);
+
 	err = mlx5e_ktls_init(priv);
 	if (err)
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
@@ -5700,8 +5953,9 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 	if (take_rtnl)
 		rtnl_lock();
 
+	mlx5e_psp_register(priv);
 	/* update XDP supported features */
-	mlx5e_set_xdp_feature(netdev);
+	mlx5e_set_xdp_feature(priv);
 
 	if (take_rtnl)
 		rtnl_unlock();
@@ -5712,7 +5966,9 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
 	mlx5e_health_destroy_reporters(priv);
+	mlx5e_psp_unregister(priv);
 	mlx5e_ktls_cleanup(priv);
+	mlx5e_psp_cleanup(priv);
 	mlx5e_fs_cleanup(priv->fs);
 	debugfs_remove_recursive(priv->dfs_root);
 	priv->fs = NULL;
@@ -5853,6 +6109,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	if (mlx5e_monitor_counter_supported(priv))
 		mlx5e_monitor_counter_init(priv);
 
+	mlx5e_pcie_cong_event_init(priv);
 	mlx5e_hv_vhca_stats_create(priv);
 	if (netdev->reg_state != NETREG_REGISTERED)
 		return;
@@ -5861,9 +6118,11 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	mlx5e_nic_set_rx_mode(priv);
 
 	rtnl_lock();
+	netdev_lock(netdev);
 	if (netif_running(netdev))
 		mlx5e_open(netdev);
 	udp_tunnel_nic_reset_ntf(priv->netdev);
+	netdev_unlock(netdev);
 	netif_device_attach(netdev);
 	rtnl_unlock();
 }
@@ -5876,23 +6135,27 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 		mlx5e_dcbnl_delete_app(priv);
 
 	rtnl_lock();
+	netdev_lock(priv->netdev);
 	if (netif_running(priv->netdev))
 		mlx5e_close(priv->netdev);
 	netif_device_detach(priv->netdev);
+	if (priv->en_trap) {
+		mlx5e_deactivate_trap(priv);
+		mlx5e_close_trap(priv->en_trap);
+		priv->en_trap = NULL;
+	}
+	netdev_unlock(priv->netdev);
 	rtnl_unlock();
 
 	mlx5e_nic_set_rx_mode(priv);
 
+	mlx5e_pcie_cong_event_cleanup(priv);
 	mlx5e_hv_vhca_stats_destroy(priv);
 	if (mlx5e_monitor_counter_supported(priv))
 		mlx5e_monitor_counter_cleanup(priv);
 
+	mlx5e_ipsec_disable_events(priv);
 	mlx5e_disable_blocking_events(priv);
-	if (priv->en_trap) {
-		mlx5e_deactivate_trap(priv);
-		mlx5e_close_trap(priv->en_trap);
-		priv->en_trap = NULL;
-	}
 	mlx5e_disable_async_events(priv);
 	mlx5_lag_remove_netdev(mdev, priv->netdev);
 	mlx5_vxlan_reset_to_default(mdev->vxlan);
@@ -5902,7 +6165,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 
 static int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
 {
-	return mlx5e_refresh_tirs(priv, false, false);
+	return mlx5e_refresh_tirs(priv->mdev, false, false);
 }
 
 static const struct mlx5e_profile mlx5e_nic_profile = {
@@ -6036,8 +6299,15 @@ int mlx5e_priv_init(struct mlx5e_priv *priv,
 	if (!priv->channel_stats)
 		goto err_free_tx_rates;
 
+	priv->fec_ranges = kcalloc(ETHTOOL_FEC_HIST_MAX,
+				   sizeof(*priv->fec_ranges), GFP_KERNEL);
+	if (!priv->fec_ranges)
+		goto err_free_channel_stats;
+
 	return 0;
 
+err_free_channel_stats:
+	kfree(priv->channel_stats);
 err_free_tx_rates:
 	kfree(priv->tx_rates);
 err_free_txq2sq_stats:
@@ -6061,6 +6331,7 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv)
 	if (!priv->mdev)
 		return;
 
+	kfree(priv->fec_ranges);
 	for (i = 0; i < priv->stats_nch; i++)
 		kvfree(priv->channel_stats[i]);
 	kfree(priv->channel_stats);
@@ -6147,7 +6418,9 @@ static void mlx5e_update_features(struct net_device *netdev)
 		return; /* features will be updated on netdev registration */
 
 	rtnl_lock();
+	netdev_lock(netdev);
 	netdev_update_features(netdev);
+	netdev_unlock(netdev);
 	rtnl_unlock();
 }
 
@@ -6158,7 +6431,7 @@ static void mlx5e_reset_channels(struct net_device *netdev)
 
 int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 {
-	const bool take_rtnl = priv->netdev->reg_state == NETREG_REGISTERED;
+	const bool need_lock = priv->netdev->reg_state == NETREG_REGISTERED;
 	const struct mlx5e_profile *profile = priv->profile;
 	int max_nch;
 	int err;
@@ -6200,15 +6473,19 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 	 * 2. Set our default XPS cpumask.
 	 * 3. Build the RQT.
 	 *
-	 * rtnl_lock is required by netif_set_real_num_*_queues in case the
+	 * Locking is required by netif_set_real_num_*_queues in case the
 	 * netdev has been registered by this point (if this function was called
 	 * in the reload or resume flow).
 	 */
-	if (take_rtnl)
+	if (need_lock) {
 		rtnl_lock();
+		netdev_lock(priv->netdev);
+	}
 	err = mlx5e_num_channels_changed(priv);
-	if (take_rtnl)
+	if (need_lock) {
+		netdev_unlock(priv->netdev);
 		rtnl_unlock();
+	}
 	if (err)
 		goto out;
 
@@ -6543,8 +6820,24 @@ static void _mlx5e_remove(struct auxiliary_device *adev)
 
 	mlx5_core_uplink_netdev_set(mdev, NULL);
 	mlx5e_dcbnl_delete_app(priv);
-	unregister_netdev(priv->netdev);
-	_mlx5e_suspend(adev, false);
+	/* When unload driver, the netdev is in registered state
+	 * if it's from legacy mode. If from switchdev mode, it
+	 * is already unregistered before changing to NIC profile.
+	 */
+	if (priv->netdev->reg_state == NETREG_REGISTERED) {
+		mlx5e_psp_unregister(priv);
+		unregister_netdev(priv->netdev);
+		_mlx5e_suspend(adev, false);
+	} else {
+		struct mlx5_core_dev *pos;
+		int i;
+
+		if (test_bit(MLX5E_STATE_DESTROYING, &priv->state))
+			mlx5_sd_for_each_dev(i, mdev, pos)
+				mlx5e_destroy_mdev_resources(pos);
+		else
+			_mlx5e_suspend(adev, true);
+	}
 	/* Avoid cleanup if profile rollback failed. */
 	if (priv->profile)
 		priv->profile->cleanup(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 554f9cb5b53f..ee9595109649 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -33,6 +33,7 @@
 #include <linux/dim.h>
 #include <linux/debugfs.h>
 #include <linux/mlx5/fs.h>
+#include <net/netdev_lock.h>
 #include <net/switchdev.h>
 #include <net/pkt_cls.h>
 #include <net/act_api.h>
@@ -65,6 +66,7 @@
 #define MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE \
 	max(0x7, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)
 #define MLX5E_REP_PARAMS_DEF_NUM_CHANNELS 1
+#define MLX5E_REP_PARAMS_DEF_LOG_RQ_SIZE 0x8
 
 static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
 
@@ -802,6 +804,7 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
 	.ndo_stop                = mlx5e_rep_close,
 	.ndo_start_xmit          = mlx5e_xmit,
 	.ndo_setup_tc            = mlx5e_rep_setup_tc,
+	.ndo_set_mac_address	 = eth_mac_addr,
 	.ndo_get_stats64         = mlx5e_rep_get_stats,
 	.ndo_has_offload_stats	 = mlx5e_rep_has_offload_stats,
 	.ndo_get_offload_stats	 = mlx5e_rep_get_offload_stats,
@@ -855,6 +858,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
+	if (!mlx5e_is_uplink_rep(priv) && mlx5_core_is_ecpf(mdev))
+		params->log_rq_mtu_frames = MLX5E_REP_PARAMS_DEF_LOG_RQ_SIZE;
 
 	/* If netdev is already registered (e.g. move from nic profile to uplink,
 	 * RTNL lock must be held before triggering netdev notifiers.
@@ -862,7 +867,7 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 	if (take_rtnl)
 		rtnl_lock();
 	/* update XDP supported features */
-	mlx5e_set_xdp_feature(netdev);
+	mlx5e_set_xdp_feature(priv);
 	if (take_rtnl)
 		rtnl_unlock();
 
@@ -882,10 +887,14 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev,
 {
 	SET_NETDEV_DEV(netdev, mdev->device);
 	netdev->netdev_ops = &mlx5e_netdev_ops_rep;
+	netdev->request_ops_lock = true;
+	netdev_lockdep_set_classes(netdev);
 	eth_hw_addr_random(netdev);
 	netdev->ethtool_ops = &mlx5e_rep_ethtool_ops;
 
 	netdev->watchdog_timeo    = 15 * HZ;
+	if (mlx5_core_is_ecpf(mdev))
+		netdev->tx_queue_len = 1 << MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE;
 
 #if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 	netdev->hw_features    |= NETIF_F_HW_TC;
@@ -900,7 +909,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev,
 
 	netdev->features |= netdev->hw_features;
 
-	netdev->netns_local = true;
+	netdev->netns_immutable = true;
 }
 
 static int mlx5e_init_rep(struct mlx5_core_dev *mdev,
@@ -965,7 +974,7 @@ static int mlx5e_create_rep_ttc_table(struct mlx5e_priv *priv)
 						MLX5_FLOW_NAMESPACE_KERNEL), false);
 
 	/* The inner_ttc in the ttc params is intentionally not set */
-	mlx5e_set_ttc_params(priv->fs, priv->rx_res, &ttc_params, false);
+	mlx5e_set_ttc_params(priv->fs, priv->rx_res, &ttc_params, false, false);
 
 	if (rep->vport != MLX5_VPORT_UPLINK)
 		/* To give uplik rep TTC a lower level for chaining from root ft */
@@ -1339,9 +1348,11 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 	netdev->wanted_features |= NETIF_F_HW_TC;
 
 	rtnl_lock();
+	netdev_lock(netdev);
 	if (netif_running(netdev))
 		mlx5e_open(netdev);
 	udp_tunnel_nic_reset_ntf(priv->netdev);
+	netdev_unlock(netdev);
 	netif_device_attach(netdev);
 	rtnl_unlock();
 }
@@ -1351,9 +1362,11 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
 	struct mlx5_core_dev *mdev = priv->mdev;
 
 	rtnl_lock();
+	netdev_lock(priv->netdev);
 	if (netif_running(priv->netdev))
 		mlx5e_close(priv->netdev);
 	netif_device_detach(priv->netdev);
+	netdev_unlock(priv->netdev);
 	rtnl_unlock();
 
 	mlx5e_rep_bridge_cleanup(priv);
@@ -1434,11 +1447,11 @@ static void mlx5e_rep_vnic_reporter_create(struct mlx5e_priv *priv,
 
 	reporter = devl_port_health_reporter_create(dl_port,
 						    &mlx5_rep_vnic_reporter_ops,
-						    0, rpriv);
+						    rpriv);
 	if (IS_ERR(reporter)) {
 		mlx5_core_err(priv->mdev,
-			      "Failed to create representor vnic reporter, err = %ld\n",
-			      PTR_ERR(reporter));
+			      "Failed to create representor vnic reporter, err = %pe\n",
+			      reporter);
 		return;
 	}
 
@@ -1493,12 +1506,21 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
 static int
 mlx5e_vport_uplink_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
-	struct mlx5e_priv *priv = netdev_priv(mlx5_uplink_netdev_get(dev));
 	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
+	struct net_device *netdev;
+	struct mlx5e_priv *priv;
+	int err;
+
+	netdev = mlx5_uplink_netdev_get(dev);
+	if (!netdev)
+		return 0;
 
+	priv = netdev_priv(netdev);
 	rpriv->netdev = priv->netdev;
-	return mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile,
-					   rpriv);
+	err = mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile,
+					  rpriv);
+	mlx5_uplink_netdev_put(dev, netdev);
+	return err;
 }
 
 static void
@@ -1509,6 +1531,21 @@ mlx5e_vport_uplink_rep_unload(struct mlx5e_rep_priv *rpriv)
 
 	priv = netdev_priv(netdev);
 
+	/* This bit is set when using devlink to change eswitch mode from
+	 * switchdev to legacy. As need to keep uplink netdev ifindex, we
+	 * detach uplink representor profile and attach NIC profile only.
+	 * The netdev will be unregistered later when unload NIC auxiliary
+	 * driver for this case.
+	 * We explicitly block devlink eswitch mode change if any IPSec rules
+	 * offloaded, but can't block other cases, such as driver unload
+	 * and devlink reload. We have to unregister netdev before profile
+	 * change for those cases. This is to avoid resource leak because
+	 * the offloaded rules don't have the chance to be unoffloaded before
+	 * cleanup which is triggered by detach uplink representor profile.
+	 */
+	if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_SWITCH_LEGACY))
+		unregister_netdev(netdev);
+
 	mlx5e_netdev_attach_nic_profile(priv);
 }
 
@@ -1610,8 +1647,16 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 {
 	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
 	struct net_device *netdev = rpriv->netdev;
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	void *ppriv = priv->ppriv;
+	struct mlx5e_priv *priv;
+	void *ppriv;
+
+	if (!netdev) {
+		ppriv = rpriv;
+		goto free_ppriv;
+	}
+
+	priv = netdev_priv(netdev);
+	ppriv = priv->ppriv;
 
 	if (rep->vport == MLX5_VPORT_UPLINK) {
 		mlx5e_vport_uplink_rep_unload(rpriv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 1963bc5adb18..1f6930c77437 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -51,6 +51,7 @@
 #include "ipoib/ipoib.h"
 #include "en_accel/ipsec.h"
 #include "en_accel/macsec.h"
+#include "en_accel/psp_rxtx.h"
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/ktls_txrx.h"
 #include "en/xdp.h"
@@ -273,33 +274,32 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq,
 
 #define MLX5E_PAGECNT_BIAS_MAX (PAGE_SIZE / 64)
 
-static int mlx5e_page_alloc_fragmented(struct mlx5e_rq *rq,
+static int mlx5e_page_alloc_fragmented(struct page_pool *pp,
 				       struct mlx5e_frag_page *frag_page)
 {
-	struct page *page;
+	netmem_ref netmem = page_pool_dev_alloc_netmems(pp);
 
-	page = page_pool_dev_alloc_pages(rq->page_pool);
-	if (unlikely(!page))
+	if (unlikely(!netmem))
 		return -ENOMEM;
 
-	page_pool_fragment_page(page, MLX5E_PAGECNT_BIAS_MAX);
+	page_pool_fragment_netmem(netmem, MLX5E_PAGECNT_BIAS_MAX);
 
 	*frag_page = (struct mlx5e_frag_page) {
-		.page	= page,
+		.netmem	= netmem,
 		.frags	= 0,
 	};
 
 	return 0;
 }
 
-static void mlx5e_page_release_fragmented(struct mlx5e_rq *rq,
+static void mlx5e_page_release_fragmented(struct page_pool *pp,
 					  struct mlx5e_frag_page *frag_page)
 {
 	u16 drain_count = MLX5E_PAGECNT_BIAS_MAX - frag_page->frags;
-	struct page *page = frag_page->page;
+	netmem_ref netmem = frag_page->netmem;
 
-	if (page_pool_unref_page(page, drain_count) == 0)
-		page_pool_put_unrefed_page(rq->page_pool, page, -1, true);
+	if (page_pool_unref_netmem(netmem, drain_count) == 0)
+		page_pool_put_unrefed_netmem(pp, netmem, -1, true);
 }
 
 static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
@@ -313,7 +313,8 @@ static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
 		 * offset) should just use the new one without replenishing again
 		 * by themselves.
 		 */
-		err = mlx5e_page_alloc_fragmented(rq, frag->frag_page);
+		err = mlx5e_page_alloc_fragmented(rq->page_pool,
+						  frag->frag_page);
 
 	return err;
 }
@@ -332,7 +333,7 @@ static inline void mlx5e_put_rx_frag(struct mlx5e_rq *rq,
 				     struct mlx5e_wqe_frag_info *frag)
 {
 	if (mlx5e_frag_can_release(frag))
-		mlx5e_page_release_fragmented(rq, frag->frag_page);
+		mlx5e_page_release_fragmented(rq->page_pool, frag->frag_page);
 }
 
 static inline struct mlx5e_wqe_frag_info *get_frag(struct mlx5e_rq *rq, u16 ix)
@@ -358,7 +359,7 @@ static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe_cyc *wqe,
 		frag->flags &= ~BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
 
 		headroom = i == 0 ? rq->buff.headroom : 0;
-		addr = page_pool_get_dma_addr(frag->frag_page->page);
+		addr = page_pool_get_dma_addr_netmem(frag->frag_page->netmem);
 		wqe->data[i].addr = cpu_to_be64(addr + frag->offset + headroom);
 	}
 
@@ -499,9 +500,10 @@ mlx5e_add_skb_shared_info_frag(struct mlx5e_rq *rq, struct skb_shared_info *sinf
 			       struct xdp_buff *xdp, struct mlx5e_frag_page *frag_page,
 			       u32 frag_offset, u32 len)
 {
+	netmem_ref netmem = frag_page->netmem;
 	skb_frag_t *frag;
 
-	dma_addr_t addr = page_pool_get_dma_addr(frag_page->page);
+	dma_addr_t addr = page_pool_get_dma_addr_netmem(netmem);
 
 	dma_sync_single_for_cpu(rq->pdev, addr + frag_offset, len, rq->buff.map_dir);
 	if (!xdp_buff_has_frags(xdp)) {
@@ -514,9 +516,9 @@ mlx5e_add_skb_shared_info_frag(struct mlx5e_rq *rq, struct skb_shared_info *sinf
 	}
 
 	frag = &sinfo->frags[sinfo->nr_frags++];
-	skb_frag_fill_page_desc(frag, frag_page->page, frag_offset, len);
+	skb_frag_fill_netmem_desc(frag, netmem, frag_offset, len);
 
-	if (page_is_pfmemalloc(frag_page->page))
+	if (netmem_is_pfmemalloc(netmem))
 		xdp_buff_set_frag_pfmemalloc(xdp);
 	sinfo->xdp_frags_size += len;
 }
@@ -527,27 +529,29 @@ mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb,
 		   u32 frag_offset, u32 len,
 		   unsigned int truesize)
 {
-	dma_addr_t addr = page_pool_get_dma_addr(frag_page->page);
+	dma_addr_t addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
 	u8 next_frag = skb_shinfo(skb)->nr_frags;
+	netmem_ref netmem = frag_page->netmem;
 
 	dma_sync_single_for_cpu(rq->pdev, addr + frag_offset, len,
 				rq->buff.map_dir);
 
-	if (skb_can_coalesce(skb, next_frag, frag_page->page, frag_offset)) {
+	if (skb_can_coalesce_netmem(skb, next_frag, netmem, frag_offset)) {
 		skb_coalesce_rx_frag(skb, next_frag - 1, len, truesize);
-	} else {
-		frag_page->frags++;
-		skb_add_rx_frag(skb, next_frag, frag_page->page,
-				frag_offset, len, truesize);
+		return;
 	}
+
+	frag_page->frags++;
+	skb_add_rx_frag_netmem(skb, next_frag, netmem,
+			       frag_offset, len, truesize);
 }
 
 static inline void
 mlx5e_copy_skb_header(struct mlx5e_rq *rq, struct sk_buff *skb,
-		      struct page *page, dma_addr_t addr,
+		      netmem_ref netmem, dma_addr_t addr,
 		      int offset_from, int dma_offset, u32 headlen)
 {
-	const void *from = page_address(page) + offset_from;
+	const void *from = netmem_address(netmem) + offset_from;
 	/* Aligning len to sizeof(long) optimizes memcpy performance */
 	unsigned int len = ALIGN(headlen, sizeof(long));
 
@@ -584,7 +588,8 @@ mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
 				struct mlx5e_frag_page *frag_page;
 
 				frag_page = &wi->alloc_units.frag_pages[i];
-				mlx5e_page_release_fragmented(rq, frag_page);
+				mlx5e_page_release_fragmented(rq->page_pool,
+							      frag_page);
 			}
 		}
 	}
@@ -631,29 +636,32 @@ static void build_ksm_umr(struct mlx5e_icosq *sq, struct mlx5e_umr_wqe *umr_wqe,
 			  __be32 key, u16 offset, u16 ksm_len)
 {
 	memset(umr_wqe, 0, offsetof(struct mlx5e_umr_wqe, inline_ksms));
-	umr_wqe->ctrl.opmod_idx_opcode =
+	umr_wqe->hdr.ctrl.opmod_idx_opcode =
 		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
 			     MLX5_OPCODE_UMR);
-	umr_wqe->ctrl.umr_mkey = key;
-	umr_wqe->ctrl.qpn_ds = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT)
+	umr_wqe->hdr.ctrl.umr_mkey = key;
+	umr_wqe->hdr.ctrl.qpn_ds = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT)
 					    | MLX5E_KSM_UMR_DS_CNT(ksm_len));
-	umr_wqe->uctrl.flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
-	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
-	umr_wqe->uctrl.xlt_octowords = cpu_to_be16(ksm_len);
-	umr_wqe->uctrl.mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
+	umr_wqe->hdr.uctrl.flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
+	umr_wqe->hdr.uctrl.xlt_offset = cpu_to_be16(offset);
+	umr_wqe->hdr.uctrl.xlt_octowords = cpu_to_be16(ksm_len);
+	umr_wqe->hdr.uctrl.mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
 }
 
-static struct mlx5e_frag_page *mlx5e_shampo_hd_to_frag_page(struct mlx5e_rq *rq, int header_index)
+static struct mlx5e_frag_page *mlx5e_shampo_hd_to_frag_page(struct mlx5e_rq *rq,
+							    int header_index)
 {
-	BUILD_BUG_ON(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE > PAGE_SHIFT);
+	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
 
-	return &rq->mpwqe.shampo->pages[header_index >> MLX5E_SHAMPO_LOG_WQ_HEADER_PER_PAGE];
+	return &shampo->pages[header_index >> shampo->log_hd_per_page];
 }
 
-static u64 mlx5e_shampo_hd_offset(int header_index)
+static u64 mlx5e_shampo_hd_offset(struct mlx5e_rq *rq, int header_index)
 {
-	return (header_index & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) <<
-		MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE;
+	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
+	u32 hd_per_page = shampo->hd_per_page;
+
+	return (header_index & (hd_per_page - 1)) << shampo->log_hd_entry_size;
 }
 
 static void mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index);
@@ -666,34 +674,32 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 	u16 pi, header_offset, err, wqe_bbs;
 	u32 lkey = rq->mdev->mlx5e_res.hw_objs.mkey;
 	struct mlx5e_umr_wqe *umr_wqe;
-	int headroom, i = 0;
+	int headroom, i;
 
 	headroom = rq->buff.headroom;
 	wqe_bbs = MLX5E_KSM_UMR_WQEBBS(ksm_entries);
 	pi = mlx5e_icosq_get_next_pi(sq, wqe_bbs);
 	umr_wqe = mlx5_wq_cyc_get_wqe(&sq->wq, pi);
-	build_ksm_umr(sq, umr_wqe, shampo->key, index, ksm_entries);
+	build_ksm_umr(sq, umr_wqe, shampo->mkey_be, index, ksm_entries);
 
-	WARN_ON_ONCE(ksm_entries & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1));
-	while (i < ksm_entries) {
-		struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, index);
+	for (i = 0; i < ksm_entries; i++, index++) {
+		struct mlx5e_frag_page *frag_page;
 		u64 addr;
 
-		err = mlx5e_page_alloc_fragmented(rq, frag_page);
-		if (unlikely(err))
-			goto err_unmap;
-
-
-		addr = page_pool_get_dma_addr(frag_page->page);
-
-		for (int j = 0; j < MLX5E_SHAMPO_WQ_HEADER_PER_PAGE; j++) {
-			header_offset = mlx5e_shampo_hd_offset(index++);
-
-			umr_wqe->inline_ksms[i++] = (struct mlx5_ksm) {
-				.key = cpu_to_be32(lkey),
-				.va  = cpu_to_be64(addr + header_offset + headroom),
-			};
+		frag_page = mlx5e_shampo_hd_to_frag_page(rq, index);
+		header_offset = mlx5e_shampo_hd_offset(rq, index);
+		if (!header_offset) {
+			err = mlx5e_page_alloc_fragmented(rq->hd_page_pool,
+							  frag_page);
+			if (err)
+				goto err_unmap;
 		}
+
+		addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
+		umr_wqe->inline_ksms[i] = (struct mlx5_ksm) {
+			.key = cpu_to_be32(lkey),
+			.va  = cpu_to_be64(addr + header_offset + headroom),
+		};
 	}
 
 	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
@@ -704,18 +710,19 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 
 	shampo->pi = (shampo->pi + ksm_entries) & (shampo->hd_per_wq - 1);
 	sq->pc += wqe_bbs;
-	sq->doorbell_cseg = &umr_wqe->ctrl;
+	sq->doorbell_cseg = &umr_wqe->hdr.ctrl;
 
 	return 0;
 
 err_unmap:
-	while (--i) {
+	while (--i >= 0) {
 		--index;
-		header_offset = mlx5e_shampo_hd_offset(index);
+		header_offset = mlx5e_shampo_hd_offset(rq, index);
 		if (!header_offset) {
 			struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, index);
 
-			mlx5e_page_release_fragmented(rq, frag_page);
+			mlx5e_page_release_fragmented(rq->hd_page_pool,
+						      frag_page);
 		}
 	}
 
@@ -730,12 +737,11 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq)
 	struct mlx5e_icosq *sq = rq->icosq;
 	int i, err, max_ksm_entries, len;
 
-	max_ksm_entries = ALIGN_DOWN(MLX5E_MAX_KSM_PER_WQE(rq->mdev),
-				     MLX5E_SHAMPO_WQ_HEADER_PER_PAGE);
+	max_ksm_entries = MLX5E_MAX_KSM_PER_WQE(rq->mdev);
 	ksm_entries = bitmap_find_window(shampo->bitmap,
 					 shampo->hd_per_wqe,
 					 shampo->hd_per_wq, shampo->pi);
-	ksm_entries = ALIGN_DOWN(ksm_entries, MLX5E_SHAMPO_WQ_HEADER_PER_PAGE);
+	ksm_entries = ALIGN_DOWN(ksm_entries, shampo->hd_per_page);
 	if (!ksm_entries)
 		return 0;
 
@@ -791,10 +797,11 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	for (i = 0; i < rq->mpwqe.pages_per_wqe; i++, frag_page++) {
 		dma_addr_t addr;
 
-		err = mlx5e_page_alloc_fragmented(rq, frag_page);
+		err = mlx5e_page_alloc_fragmented(rq->page_pool, frag_page);
 		if (unlikely(err))
 			goto err_unmap;
-		addr = page_pool_get_dma_addr(frag_page->page);
+
+		addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
 		umr_wqe->inline_mtts[i] = (struct mlx5_mtt) {
 			.ptag = cpu_to_be64(addr | MLX5_EN_WR),
 		};
@@ -814,12 +821,12 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	bitmap_zero(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
 	wi->consumed_strides = 0;
 
-	umr_wqe->ctrl.opmod_idx_opcode =
+	umr_wqe->hdr.ctrl.opmod_idx_opcode =
 		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
 			    MLX5_OPCODE_UMR);
 
 	offset = (ix * rq->mpwqe.mtts_per_wqe) * sizeof(struct mlx5_mtt) / MLX5_OCTWORD;
-	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
+	umr_wqe->hdr.uctrl.xlt_offset = cpu_to_be16(offset);
 
 	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
 		.wqe_type   = MLX5E_ICOSQ_WQE_UMR_RX,
@@ -829,14 +836,14 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 
 	sq->pc += rq->mpwqe.umr_wqebbs;
 
-	sq->doorbell_cseg = &umr_wqe->ctrl;
+	sq->doorbell_cseg = &umr_wqe->hdr.ctrl;
 
 	return 0;
 
 err_unmap:
 	while (--i >= 0) {
 		frag_page--;
-		mlx5e_page_release_fragmented(rq, frag_page);
+		mlx5e_page_release_fragmented(rq->page_pool, frag_page);
 	}
 
 	bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
@@ -852,10 +859,10 @@ mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index)
 {
 	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
 
-	if (((header_index + 1) & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) == 0) {
+	if (((header_index + 1) & (shampo->hd_per_page - 1)) == 0) {
 		struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index);
 
-		mlx5e_page_release_fragmented(rq, frag_page);
+		mlx5e_page_release_fragmented(rq->hd_page_pool, frag_page);
 	}
 	clear_bit(header_index, shampo->bitmap);
 }
@@ -1030,6 +1037,10 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 				netdev_WARN_ONCE(cq->netdev,
 						 "Bad OP in ICOSQ CQE: 0x%x\n",
 						 get_cqe_opcode(cqe));
+#ifdef CONFIG_MLX5_EN_TLS
+				if (wi->wqe_type == MLX5E_ICOSQ_WQE_GET_PSV_TLS)
+					mlx5e_ktls_rx_resync_async_request_cancel(wi);
+#endif
 				mlx5e_dump_error_cqe(&sq->cq, sq->sqn,
 						     (struct mlx5_err_cqe *)cqe);
 				mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs);
@@ -1100,6 +1111,8 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 
 	if (rq->page_pool)
 		page_pool_nid_changed(rq->page_pool, numa_mem_id());
+	if (rq->hd_page_pool)
+		page_pool_nid_changed(rq->hd_page_pool, numa_mem_id());
 
 	head = rq->mpwqe.actual_wq_head;
 	i = missing;
@@ -1154,8 +1167,9 @@ static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp)
 	}
 }
 
-static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
-				 u32 cqe_bcnt)
+static unsigned int mlx5e_lro_update_hdr(struct sk_buff *skb,
+					 struct mlx5_cqe64 *cqe,
+					 u32 cqe_bcnt)
 {
 	struct ethhdr	*eth = (struct ethhdr *)(skb->data);
 	struct tcphdr	*tcp;
@@ -1205,14 +1219,17 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
 		tcp->check = tcp_v6_check(payload_len, &ipv6->saddr,
 					  &ipv6->daddr, check);
 	}
+
+	return (unsigned int)((unsigned char *)tcp + tcp->doff * 4 - skb->data);
 }
 
 static void *mlx5e_shampo_get_packet_hd(struct mlx5e_rq *rq, u16 header_index)
 {
 	struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index);
-	u16 head_offset = mlx5e_shampo_hd_offset(header_index) + rq->buff.headroom;
+	u16 head_offset = mlx5e_shampo_hd_offset(rq, header_index);
+	void *addr = netmem_address(frag_page->netmem);
 
-	return page_address(frag_page->page) + head_offset;
+	return addr + head_offset + rq->buff.headroom;
 }
 
 static void mlx5e_shampo_update_ipv4_udp_hdr(struct mlx5e_rq *rq, struct iphdr *ipv4)
@@ -1279,8 +1296,12 @@ static void mlx5e_shampo_update_ipv4_tcp_hdr(struct mlx5e_rq *rq, struct iphdr *
 	tcp->check = ~tcp_v4_check(skb->len - tcp_off, ipv4->saddr,
 				   ipv4->daddr, 0);
 	skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
-	if (ntohs(ipv4->id) == rq->hw_gro_data->second_ip_id)
-		skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID;
+	if (ntohs(ipv4->id) == rq->hw_gro_data->second_ip_id) {
+		bool encap = rq->hw_gro_data->fk.control.flags & FLOW_DIS_ENCAPSULATION;
+
+		skb_shinfo(skb)->gso_type |= encap ? SKB_GSO_TCP_FIXEDID_INNER :
+						     SKB_GSO_TCP_FIXEDID;
+	}
 
 	skb->csum_start = (unsigned char *)tcp - skb->head;
 	skb->csum_offset = offsetof(struct tcphdr, check);
@@ -1511,6 +1532,11 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
 
+		if (unlikely(mlx5e_psp_is_rx_flow(cqe))) {
+			/* TBD: PSP csum complete corrections for now chose csum_unnecessary path */
+			goto csum_unnecessary;
+		}
+
 		if (test_bit(MLX5E_RQ_STATE_CSUM_FULL, &rq->state))
 			return; /* CQE csum covers all received bytes */
 
@@ -1539,7 +1565,7 @@ csum_none:
 
 #define MLX5E_CE_BIT_MASK 0x80
 
-static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
+static inline bool mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 				      u32 cqe_bcnt,
 				      struct mlx5e_rq *rq,
 				      struct sk_buff *skb)
@@ -1553,6 +1579,11 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 	if (unlikely(get_cqe_tls_offload(cqe)))
 		mlx5e_ktls_handle_rx_skb(rq, skb, cqe, &cqe_bcnt);
 
+	if (unlikely(mlx5e_psp_is_rx_flow(cqe))) {
+		if (mlx5e_psp_offload_handle_rx_skb(netdev, skb, cqe))
+			return true;
+	}
+
 	if (unlikely(mlx5_ipsec_is_rx_flow(cqe)))
 		mlx5e_ipsec_offload_handle_rx_skb(netdev, skb,
 						  be32_to_cpu(cqe->ft_metadata));
@@ -1561,8 +1592,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 		mlx5e_macsec_offload_handle_rx_skb(netdev, skb, cqe);
 
 	if (lro_num_seg > 1) {
-		mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
-		skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
+		unsigned int hdrlen = mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
+
+		skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt - hdrlen, lro_num_seg);
+		skb_shinfo(skb)->gso_segs = lro_num_seg;
 		/* Subtract one since we already counted this as one
 		 * "regular" packet in mlx5e_complete_rx_cqe()
 		 */
@@ -1571,7 +1604,7 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 		stats->lro_bytes += cqe_bcnt;
 	}
 
-	if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp)))
+	if (unlikely(mlx5e_rx_hw_stamp(rq->hwtstamp_config)))
 		skb_hwtstamps(skb)->hwtstamp = mlx5e_cqe_ts_to_ns(rq->ptp_cyc2time,
 								  rq->clock, get_cqe_ts(cqe));
 	skb_record_rx_queue(skb, rq->ix);
@@ -1596,9 +1629,11 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 
 	if (unlikely(mlx5e_skb_is_multicast(skb)))
 		stats->mcast_packets++;
+
+	return false;
 }
 
-static void mlx5e_shampo_complete_rx_cqe(struct mlx5e_rq *rq,
+static bool mlx5e_shampo_complete_rx_cqe(struct mlx5e_rq *rq,
 					 struct mlx5_cqe64 *cqe,
 					 u32 cqe_bcnt,
 					 struct sk_buff *skb)
@@ -1608,16 +1643,20 @@ static void mlx5e_shampo_complete_rx_cqe(struct mlx5e_rq *rq,
 	stats->packets++;
 	stats->bytes += cqe_bcnt;
 	if (NAPI_GRO_CB(skb)->count != 1)
-		return;
-	mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
+		return false;
+
+	if (mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb))
+		return true;
+
 	skb_reset_network_header(skb);
 	if (!skb_flow_dissect_flow_keys(skb, &rq->hw_gro_data->fk, 0)) {
 		napi_gro_receive(rq->cq.napi, skb);
 		rq->hw_gro_data->skb = NULL;
 	}
+	return false;
 }
 
-static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
+static inline bool mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
 					 struct mlx5_cqe64 *cqe,
 					 u32 cqe_bcnt,
 					 struct sk_buff *skb)
@@ -1626,7 +1665,7 @@ static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
 
 	stats->packets++;
 	stats->bytes += cqe_bcnt;
-	mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
+	return mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
 }
 
 static inline
@@ -1673,28 +1712,28 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi,
 	dma_addr_t addr;
 	u32 frag_size;
 
-	va             = page_address(frag_page->page) + wi->offset;
+	va             = netmem_address(frag_page->netmem) + wi->offset;
 	data           = va + rx_headroom;
 	frag_size      = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
 
-	addr = page_pool_get_dma_addr(frag_page->page);
+	addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
 	dma_sync_single_range_for_cpu(rq->pdev, addr, wi->offset,
 				      frag_size, rq->buff.map_dir);
 	net_prefetch(data);
 
 	prog = rcu_dereference(rq->xdp_prog);
 	if (prog) {
-		struct mlx5e_xdp_buff mxbuf;
+		struct mlx5e_xdp_buff *mxbuf = &rq->mxbuf;
 
 		net_prefetchw(va); /* xdp_frame data area */
 		mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, rq->buff.frame0_sz,
-				 cqe_bcnt, &mxbuf);
-		if (mlx5e_xdp_handle(rq, prog, &mxbuf))
+				 cqe_bcnt, mxbuf);
+		if (mlx5e_xdp_handle(rq, prog, mxbuf))
 			return NULL; /* page/packet was consumed by XDP */
 
-		rx_headroom = mxbuf.xdp.data - mxbuf.xdp.data_hard_start;
-		metasize = mxbuf.xdp.data - mxbuf.xdp.data_meta;
-		cqe_bcnt = mxbuf.xdp.data_end - mxbuf.xdp.data;
+		rx_headroom = mxbuf->xdp.data - mxbuf->xdp.data_hard_start;
+		metasize = mxbuf->xdp.data - mxbuf->xdp.data_meta;
+		cqe_bcnt = mxbuf->xdp.data_end - mxbuf->xdp.data;
 	}
 	frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
 	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt, metasize);
@@ -1713,11 +1752,11 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 			     struct mlx5_cqe64 *cqe, u32 cqe_bcnt)
 {
 	struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0];
+	struct mlx5e_xdp_buff *mxbuf = &rq->mxbuf;
 	struct mlx5e_wqe_frag_info *head_wi = wi;
 	u16 rx_headroom = rq->buff.headroom;
 	struct mlx5e_frag_page *frag_page;
 	struct skb_shared_info *sinfo;
-	struct mlx5e_xdp_buff mxbuf;
 	u32 frag_consumed_bytes;
 	struct bpf_prog *prog;
 	struct sk_buff *skb;
@@ -1727,18 +1766,18 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 
 	frag_page = wi->frag_page;
 
-	va = page_address(frag_page->page) + wi->offset;
+	va = netmem_address(frag_page->netmem) + wi->offset;
 	frag_consumed_bytes = min_t(u32, frag_info->frag_size, cqe_bcnt);
 
-	addr = page_pool_get_dma_addr(frag_page->page);
+	addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
 	dma_sync_single_range_for_cpu(rq->pdev, addr, wi->offset,
 				      rq->buff.frame0_sz, rq->buff.map_dir);
 	net_prefetchw(va); /* xdp_frame data area */
 	net_prefetch(va + rx_headroom);
 
 	mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, rq->buff.frame0_sz,
-			 frag_consumed_bytes, &mxbuf);
-	sinfo = xdp_get_shared_info_from_buff(&mxbuf.xdp);
+			 frag_consumed_bytes, mxbuf);
+	sinfo = xdp_get_shared_info_from_buff(&mxbuf->xdp);
 	truesize = 0;
 
 	cqe_bcnt -= frag_consumed_bytes;
@@ -1750,8 +1789,9 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 
 		frag_consumed_bytes = min_t(u32, frag_info->frag_size, cqe_bcnt);
 
-		mlx5e_add_skb_shared_info_frag(rq, sinfo, &mxbuf.xdp, frag_page,
-					       wi->offset, frag_consumed_bytes);
+		mlx5e_add_skb_shared_info_frag(rq, sinfo, &mxbuf->xdp,
+					       frag_page, wi->offset,
+					       frag_consumed_bytes);
 		truesize += frag_info->frag_stride;
 
 		cqe_bcnt -= frag_consumed_bytes;
@@ -1760,31 +1800,45 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 	}
 
 	prog = rcu_dereference(rq->xdp_prog);
-	if (prog && mlx5e_xdp_handle(rq, prog, &mxbuf)) {
-		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
-			struct mlx5e_wqe_frag_info *pwi;
+	if (prog) {
+		u8 nr_frags_free, old_nr_frags = sinfo->nr_frags;
 
-			for (pwi = head_wi; pwi < wi; pwi++)
-				pwi->frag_page->frags++;
+		if (mlx5e_xdp_handle(rq, prog, mxbuf)) {
+			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT,
+						 rq->flags)) {
+				struct mlx5e_wqe_frag_info *pwi;
+
+				wi -= old_nr_frags - sinfo->nr_frags;
+
+				for (pwi = head_wi; pwi < wi; pwi++)
+					pwi->frag_page->frags++;
+			}
+			return NULL; /* page/packet was consumed by XDP */
+		}
+
+		nr_frags_free = old_nr_frags - sinfo->nr_frags;
+		if (unlikely(nr_frags_free)) {
+			wi -= nr_frags_free;
+			truesize -= nr_frags_free * frag_info->frag_stride;
 		}
-		return NULL; /* page/packet was consumed by XDP */
 	}
 
-	skb = mlx5e_build_linear_skb(rq, mxbuf.xdp.data_hard_start, rq->buff.frame0_sz,
-				     mxbuf.xdp.data - mxbuf.xdp.data_hard_start,
-				     mxbuf.xdp.data_end - mxbuf.xdp.data,
-				     mxbuf.xdp.data - mxbuf.xdp.data_meta);
+	skb = mlx5e_build_linear_skb(
+		rq, mxbuf->xdp.data_hard_start, rq->buff.frame0_sz,
+		mxbuf->xdp.data - mxbuf->xdp.data_hard_start,
+		mxbuf->xdp.data_end - mxbuf->xdp.data,
+		mxbuf->xdp.data - mxbuf->xdp.data_meta);
 	if (unlikely(!skb))
 		return NULL;
 
 	skb_mark_for_recycle(skb);
 	head_wi->frag_page->frags++;
 
-	if (xdp_buff_has_frags(&mxbuf.xdp)) {
+	if (xdp_buff_has_frags(&mxbuf->xdp)) {
 		/* sinfo->nr_frags is reset by build_skb, calculate again. */
-		xdp_update_skb_shared_info(skb, wi - head_wi - 1,
-					   sinfo->xdp_frags_size, truesize,
-					   xdp_buff_is_frag_pfmemalloc(&mxbuf.xdp));
+		xdp_update_skb_frags_info(skb, wi - head_wi - 1,
+					  sinfo->xdp_frags_size, truesize,
+					  xdp_buff_get_skb_flags(&mxbuf->xdp));
 
 		for (struct mlx5e_wqe_frag_info *pwi = head_wi + 1; pwi < wi; pwi++)
 			pwi->frag_page->frags++;
@@ -1840,7 +1894,8 @@ static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 		goto wq_cyc_pop;
 	}
 
-	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	if (mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb))
+		goto wq_cyc_pop;
 
 	if (mlx5e_cqe_regb_chain(cqe))
 		if (!mlx5e_tc_update_skb_nic(cqe, skb)) {
@@ -1887,7 +1942,8 @@ static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 		goto wq_cyc_pop;
 	}
 
-	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	if (mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb))
+		goto wq_cyc_pop;
 
 	if (rep->vlan && skb_vlan_tag_present(skb))
 		skb_vlan_pop(skb);
@@ -1936,7 +1992,8 @@ static void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, struct mlx5_cqe64
 	if (!skb)
 		goto mpwrq_cqe_out;
 
-	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	if (mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb))
+		goto mpwrq_cqe_out;
 
 	mlx5e_rep_tc_receive(cqe, rq, skb);
 
@@ -1984,11 +2041,12 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	struct mlx5e_frag_page *frag_page = &wi->alloc_units.frag_pages[page_idx];
 	u16 headlen = min_t(u16, MLX5E_RX_MAX_HEAD, cqe_bcnt);
 	struct mlx5e_frag_page *head_page = frag_page;
+	struct mlx5e_xdp_buff *mxbuf = &rq->mxbuf;
 	u32 frag_offset    = head_offset;
 	u32 byte_cnt       = cqe_bcnt;
 	struct skb_shared_info *sinfo;
-	struct mlx5e_xdp_buff mxbuf;
 	unsigned int truesize = 0;
+	u32 pg_consumed_bytes;
 	struct bpf_prog *prog;
 	struct sk_buff *skb;
 	u32 linear_frame_sz;
@@ -2000,12 +2058,14 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 
 	if (prog) {
 		/* area for bpf_xdp_[store|load]_bytes */
-		net_prefetchw(page_address(frag_page->page) + frag_offset);
-		if (unlikely(mlx5e_page_alloc_fragmented(rq, &wi->linear_page))) {
+		net_prefetchw(netmem_address(frag_page->netmem) + frag_offset);
+		if (unlikely(mlx5e_page_alloc_fragmented(rq->page_pool,
+							 &wi->linear_page))) {
 			rq->stats->buff_alloc_err++;
 			return NULL;
 		}
-		va = page_address(wi->linear_page.page);
+
+		va = netmem_address(wi->linear_page.netmem);
 		net_prefetchw(va); /* xdp_frame data area */
 		linear_hr = XDP_PACKET_HEADROOM;
 		linear_data_len = 0;
@@ -2033,20 +2093,23 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 		}
 	}
 
-	mlx5e_fill_mxbuf(rq, cqe, va, linear_hr, linear_frame_sz, linear_data_len, &mxbuf);
+	mlx5e_fill_mxbuf(rq, cqe, va, linear_hr, linear_frame_sz,
+			 linear_data_len, mxbuf);
 
-	sinfo = xdp_get_shared_info_from_buff(&mxbuf.xdp);
+	sinfo = xdp_get_shared_info_from_buff(&mxbuf->xdp);
 
 	while (byte_cnt) {
 		/* Non-linear mode, hence non-XSK, which always uses PAGE_SIZE. */
-		u32 pg_consumed_bytes = min_t(u32, PAGE_SIZE - frag_offset, byte_cnt);
+		pg_consumed_bytes =
+			min_t(u32, PAGE_SIZE - frag_offset, byte_cnt);
 
 		if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state))
 			truesize += pg_consumed_bytes;
 		else
 			truesize += ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz));
 
-		mlx5e_add_skb_shared_info_frag(rq, sinfo, &mxbuf.xdp, frag_page, frag_offset,
+		mlx5e_add_skb_shared_info_frag(rq, sinfo, &mxbuf->xdp,
+					       frag_page, frag_offset,
 					       pg_consumed_bytes);
 		byte_cnt -= pg_consumed_bytes;
 		frag_offset = 0;
@@ -2054,55 +2117,77 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	}
 
 	if (prog) {
-		if (mlx5e_xdp_handle(rq, prog, &mxbuf)) {
+		u8 nr_frags_free, old_nr_frags = sinfo->nr_frags;
+		u32 len;
+
+		if (mlx5e_xdp_handle(rq, prog, mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 				struct mlx5e_frag_page *pfp;
 
+				frag_page -= old_nr_frags - sinfo->nr_frags;
+
 				for (pfp = head_page; pfp < frag_page; pfp++)
 					pfp->frags++;
 
 				wi->linear_page.frags++;
 			}
-			mlx5e_page_release_fragmented(rq, &wi->linear_page);
+			mlx5e_page_release_fragmented(rq->page_pool,
+						      &wi->linear_page);
 			return NULL; /* page/packet was consumed by XDP */
 		}
 
-		skb = mlx5e_build_linear_skb(rq, mxbuf.xdp.data_hard_start,
-					     linear_frame_sz,
-					     mxbuf.xdp.data - mxbuf.xdp.data_hard_start, 0,
-					     mxbuf.xdp.data - mxbuf.xdp.data_meta);
+		nr_frags_free = old_nr_frags - sinfo->nr_frags;
+		if (unlikely(nr_frags_free)) {
+			frag_page -= nr_frags_free;
+			truesize -= (nr_frags_free - 1) * PAGE_SIZE +
+				ALIGN(pg_consumed_bytes,
+				      BIT(rq->mpwqe.log_stride_sz));
+		}
+
+		len = mxbuf->xdp.data_end - mxbuf->xdp.data;
+
+		skb = mlx5e_build_linear_skb(
+			rq, mxbuf->xdp.data_hard_start, linear_frame_sz,
+			mxbuf->xdp.data - mxbuf->xdp.data_hard_start, len,
+			mxbuf->xdp.data - mxbuf->xdp.data_meta);
 		if (unlikely(!skb)) {
-			mlx5e_page_release_fragmented(rq, &wi->linear_page);
+			mlx5e_page_release_fragmented(rq->page_pool,
+						      &wi->linear_page);
 			return NULL;
 		}
 
 		skb_mark_for_recycle(skb);
 		wi->linear_page.frags++;
-		mlx5e_page_release_fragmented(rq, &wi->linear_page);
+		mlx5e_page_release_fragmented(rq->page_pool, &wi->linear_page);
 
-		if (xdp_buff_has_frags(&mxbuf.xdp)) {
+		if (xdp_buff_has_frags(&mxbuf->xdp)) {
 			struct mlx5e_frag_page *pagep;
 
 			/* sinfo->nr_frags is reset by build_skb, calculate again. */
-			xdp_update_skb_shared_info(skb, frag_page - head_page,
-						   sinfo->xdp_frags_size, truesize,
-						   xdp_buff_is_frag_pfmemalloc(&mxbuf.xdp));
+			xdp_update_skb_frags_info(skb, frag_page - head_page,
+						  sinfo->xdp_frags_size,
+						  truesize,
+						  xdp_buff_get_skb_flags(&mxbuf->xdp));
 
 			pagep = head_page;
 			do
 				pagep->frags++;
 			while (++pagep < frag_page);
+
+			headlen = min_t(u16, MLX5E_RX_MAX_HEAD - len,
+					skb->data_len);
+			__pskb_pull_tail(skb, headlen);
 		}
-		__pskb_pull_tail(skb, headlen);
 	} else {
 		dma_addr_t addr;
 
-		if (xdp_buff_has_frags(&mxbuf.xdp)) {
+		if (xdp_buff_has_frags(&mxbuf->xdp)) {
 			struct mlx5e_frag_page *pagep;
 
-			xdp_update_skb_shared_info(skb, sinfo->nr_frags,
-						   sinfo->xdp_frags_size, truesize,
-						   xdp_buff_is_frag_pfmemalloc(&mxbuf.xdp));
+			xdp_update_skb_frags_info(skb, sinfo->nr_frags,
+						  sinfo->xdp_frags_size,
+						  truesize,
+						  xdp_buff_get_skb_flags(&mxbuf->xdp));
 
 			pagep = frag_page - sinfo->nr_frags;
 			do
@@ -2110,8 +2195,8 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 			while (++pagep < frag_page);
 		}
 		/* copy header */
-		addr = page_pool_get_dma_addr(head_page->page);
-		mlx5e_copy_skb_header(rq, skb, head_page->page, addr,
+		addr = page_pool_get_dma_addr_netmem(head_page->netmem);
+		mlx5e_copy_skb_header(rq, skb, head_page->netmem, addr,
 				      head_offset, head_offset, headlen);
 		/* skb linear part was allocated with headlen and aligned to long */
 		skb->tail += headlen;
@@ -2141,31 +2226,31 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 		return NULL;
 	}
 
-	va             = page_address(frag_page->page) + head_offset;
+	va             = netmem_address(frag_page->netmem) + head_offset;
 	data           = va + rx_headroom;
 	frag_size      = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
 
-	addr = page_pool_get_dma_addr(frag_page->page);
+	addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
 	dma_sync_single_range_for_cpu(rq->pdev, addr, head_offset,
 				      frag_size, rq->buff.map_dir);
 	net_prefetch(data);
 
 	prog = rcu_dereference(rq->xdp_prog);
 	if (prog) {
-		struct mlx5e_xdp_buff mxbuf;
+		struct mlx5e_xdp_buff *mxbuf = &rq->mxbuf;
 
 		net_prefetchw(va); /* xdp_frame data area */
 		mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, rq->buff.frame0_sz,
-				 cqe_bcnt, &mxbuf);
-		if (mlx5e_xdp_handle(rq, prog, &mxbuf)) {
+				 cqe_bcnt, mxbuf);
+		if (mlx5e_xdp_handle(rq, prog, mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
 				frag_page->frags++;
 			return NULL; /* page/packet was consumed by XDP */
 		}
 
-		rx_headroom = mxbuf.xdp.data - mxbuf.xdp.data_hard_start;
-		metasize = mxbuf.xdp.data - mxbuf.xdp.data_meta;
-		cqe_bcnt = mxbuf.xdp.data_end - mxbuf.xdp.data;
+		rx_headroom = mxbuf->xdp.data - mxbuf->xdp.data_hard_start;
+		metasize =  mxbuf->xdp.data -  mxbuf->xdp.data_meta;
+		cqe_bcnt =  mxbuf->xdp.data_end -  mxbuf->xdp.data;
 	}
 	frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
 	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt, metasize);
@@ -2184,20 +2269,24 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 			  struct mlx5_cqe64 *cqe, u16 header_index)
 {
 	struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index);
-	dma_addr_t page_dma_addr = page_pool_get_dma_addr(frag_page->page);
-	u16 head_offset = mlx5e_shampo_hd_offset(header_index);
-	dma_addr_t dma_addr = page_dma_addr + head_offset;
+	u16 head_offset = mlx5e_shampo_hd_offset(rq, header_index);
+	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
 	u16 head_size = cqe->shampo.header_size;
 	u16 rx_headroom = rq->buff.headroom;
 	struct sk_buff *skb = NULL;
+	dma_addr_t page_dma_addr;
+	dma_addr_t dma_addr;
 	void *hdr, *data;
 	u32 frag_size;
 
-	hdr		= page_address(frag_page->page) + head_offset;
+	page_dma_addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
+	dma_addr = page_dma_addr + head_offset;
+
+	hdr		= netmem_address(frag_page->netmem) + head_offset;
 	data		= hdr + rx_headroom;
 	frag_size	= MLX5_SKB_FRAG_SZ(rx_headroom + head_size);
 
-	if (likely(frag_size <= BIT(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE))) {
+	if (likely(frag_size <= BIT(shampo->log_hd_entry_size))) {
 		/* build SKB around header */
 		dma_sync_single_range_for_cpu(rq->pdev, dma_addr, 0, frag_size, rq->buff.map_dir);
 		net_prefetchw(hdr);
@@ -2218,7 +2307,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 		}
 
 		net_prefetchw(skb->data);
-		mlx5e_copy_skb_header(rq, skb, frag_page->page, dma_addr,
+		mlx5e_copy_skb_header(rq, skb, frag_page->netmem, dma_addr,
 				      head_offset + rx_headroom,
 				      rx_headroom, head_size);
 		/* skb linear part was allocated with headlen and aligned to long */
@@ -2270,7 +2359,10 @@ mlx5e_hw_gro_skb_has_enough_space(struct sk_buff *skb, u16 data_bcnt)
 {
 	int nr_frags = skb_shinfo(skb)->nr_frags;
 
-	return PAGE_SIZE * nr_frags + data_bcnt <= GRO_LEGACY_MAX_SIZE;
+	if (PAGE_SIZE >= GRO_LEGACY_MAX_SIZE)
+		return skb->len + data_bcnt <= GRO_LEGACY_MAX_SIZE;
+	else
+		return PAGE_SIZE * nr_frags + data_bcnt <= GRO_LEGACY_MAX_SIZE;
 }
 
 static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
@@ -2312,11 +2404,23 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 	}
 
 	if (!*skb) {
-		if (likely(head_size))
+		if (likely(head_size)) {
 			*skb = mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index);
-		else
-			*skb = mlx5e_skb_from_cqe_mpwrq_nonlinear(rq, wi, cqe, cqe_bcnt,
-								  data_offset, page_idx);
+		} else {
+			struct mlx5e_frag_page *frag_page;
+
+			frag_page = &wi->alloc_units.frag_pages[page_idx];
+			/* Drop packets with header in unreadable data area to
+			 * prevent the kernel from touching it.
+			 */
+			if (unlikely(netmem_is_net_iov(frag_page->netmem)))
+				goto free_hd_entry;
+			*skb = mlx5e_skb_from_cqe_mpwrq_nonlinear(rq, wi, cqe,
+								  cqe_bcnt,
+								  data_offset,
+								  page_idx);
+		}
+
 		if (unlikely(!*skb))
 			goto free_hd_entry;
 
@@ -2350,7 +2454,10 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 		stats->hds_nosplit_bytes += data_bcnt;
 	}
 
-	mlx5e_shampo_complete_rx_cqe(rq, cqe, cqe_bcnt, *skb);
+	if (mlx5e_shampo_complete_rx_cqe(rq, cqe, cqe_bcnt, *skb)) {
+		*skb = NULL;
+		goto free_hd_entry;
+	}
 	if (flush && rq->hw_gro_data->skb)
 		mlx5e_shampo_flush_skb(rq, cqe, match);
 free_hd_entry:
@@ -2408,7 +2515,8 @@ static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cq
 	if (!skb)
 		goto mpwrq_cqe_out;
 
-	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	if (mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb))
+		goto mpwrq_cqe_out;
 
 	if (mlx5e_cqe_regb_chain(cqe))
 		if (!mlx5e_tc_update_skb_nic(cqe, skb)) {
@@ -2548,7 +2656,6 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 					 u32 cqe_bcnt,
 					 struct sk_buff *skb)
 {
-	struct hwtstamp_config *tstamp;
 	struct mlx5e_rq_stats *stats;
 	struct net_device *netdev;
 	struct mlx5e_priv *priv;
@@ -2572,7 +2679,6 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 	}
 
 	priv = mlx5i_epriv(netdev);
-	tstamp = &priv->tstamp;
 	stats = &priv->channel_stats[rq->ix]->rq;
 
 	flags_rqpn = be32_to_cpu(cqe->flags_rqpn);
@@ -2608,7 +2714,7 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 		stats->csum_none++;
 	}
 
-	if (unlikely(mlx5e_rx_hw_stamp(tstamp)))
+	if (unlikely(mlx5e_rx_hw_stamp(&priv->hwtstamp_config)))
 		skb_hwtstamps(skb)->hwtstamp = mlx5e_cqe_ts_to_ns(rq->ptp_cyc2time,
 								  rq->clock, get_cqe_ts(cqe));
 	skb_record_rx_queue(skb, rq->ix);
@@ -2741,7 +2847,8 @@ static void mlx5e_trap_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe
 	if (!skb)
 		goto wq_cyc_pop;
 
-	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	if (mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb))
+		goto wq_cyc_pop;
 	skb_push(skb, ETH_HLEN);
 
 	mlx5_devlink_trap_report(rq->mdev, trap_id, skb,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 1d60465cc2ca..fcad464bc4d5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -166,6 +166,9 @@ mlx5e_test_loopback_validate(struct sk_buff *skb,
 	struct udphdr *udph;
 	struct iphdr *iph;
 
+	if (skb_linearize(skb))
+		goto out;
+
 	/* We are only going to peek, no need to clone the SKB */
 	if (MLX5E_TEST_PKT_SIZE - ETH_HLEN > skb_headlen(skb))
 		goto out;
@@ -211,7 +214,7 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv,
 			return err;
 	}
 
-	err = mlx5e_refresh_tirs(priv, true, false);
+	err = mlx5e_modify_tirs_lb(priv->mdev, true, false);
 	if (err)
 		goto out;
 
@@ -240,7 +243,7 @@ static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv,
 		mlx5_nic_vport_update_local_lb(priv->mdev, false);
 
 	dev_remove_pack(&lbtp->pt);
-	mlx5e_refresh_tirs(priv, false, false);
+	mlx5e_modify_tirs_lb(priv->mdev, false, false);
 }
 
 static int mlx5e_cond_loopback(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 611ec4b6f370..a2802cfc9b98 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -37,9 +37,7 @@
 #include "en/ptp.h"
 #include "en/port.h"
 
-#ifdef CONFIG_PAGE_POOL_STATS
 #include <net/page_pool/helpers.h>
-#endif
 
 void mlx5e_ethtool_put_stat(u64 **data, u64 val)
 {
@@ -196,7 +194,6 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_err) },
 #endif
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_recover) },
-#ifdef CONFIG_PAGE_POOL_STATS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_alloc_fast) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_alloc_slow) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_alloc_slow_high_order) },
@@ -208,7 +205,6 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_recycle_ring) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_recycle_ring_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_recycle_released_ref) },
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_bytes) },
@@ -377,7 +373,6 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s,
 	s->rx_arfs_err                += rq_stats->arfs_err;
 #endif
 	s->rx_recover                 += rq_stats->recover;
-#ifdef CONFIG_PAGE_POOL_STATS
 	s->rx_pp_alloc_fast          += rq_stats->pp_alloc_fast;
 	s->rx_pp_alloc_slow          += rq_stats->pp_alloc_slow;
 	s->rx_pp_alloc_empty         += rq_stats->pp_alloc_empty;
@@ -389,7 +384,6 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s,
 	s->rx_pp_recycle_ring			+= rq_stats->pp_recycle_ring;
 	s->rx_pp_recycle_ring_full		+= rq_stats->pp_recycle_ring_full;
 	s->rx_pp_recycle_released_ref		+= rq_stats->pp_recycle_released_ref;
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	s->rx_tls_decrypted_packets   += rq_stats->tls_decrypted_packets;
 	s->rx_tls_decrypted_bytes     += rq_stats->tls_decrypted_bytes;
@@ -496,7 +490,6 @@ static void mlx5e_stats_grp_sw_update_stats_qos(struct mlx5e_priv *priv,
 	}
 }
 
-#ifdef CONFIG_PAGE_POOL_STATS
 static void mlx5e_stats_update_stats_rq_page_pool(struct mlx5e_channel *c)
 {
 	struct mlx5e_rq_stats *rq_stats = c->rq.stats;
@@ -519,11 +512,6 @@ static void mlx5e_stats_update_stats_rq_page_pool(struct mlx5e_channel *c)
 	rq_stats->pp_recycle_ring_full = stats.recycle_stats.ring_full;
 	rq_stats->pp_recycle_released_ref = stats.recycle_stats.released_refcnt;
 }
-#else
-static void mlx5e_stats_update_stats_rq_page_pool(struct mlx5e_channel *c)
-{
-}
-#endif
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw)
 {
@@ -1227,6 +1215,13 @@ out:
 	mutex_unlock(&priv->state_lock);
 }
 
+#define PPORT_PHY_LAYER_OFF(c) \
+	MLX5_BYTE_OFF(ppcnt_reg, \
+		      counter_set.phys_layer_cntrs.c)
+static const struct counter_desc pport_phy_layer_cntrs_stats_desc[] = {
+	{ "link_down_events_phy", PPORT_PHY_LAYER_OFF(link_down_events) }
+};
+
 #define PPORT_PHY_STATISTICAL_OFF(c) \
 	MLX5_BYTE_OFF(ppcnt_reg, \
 		      counter_set.phys_layer_statistical_cntrs.c##_high)
@@ -1243,25 +1238,45 @@ pport_phy_statistical_err_lanes_stats_desc[] = {
 	{ "rx_err_lane_3_phy", PPORT_PHY_STATISTICAL_OFF(phy_corrected_bits_lane3) },
 };
 
+#define PPORT_PHY_RECOVERY_OFF(c) \
+	MLX5_BYTE_OFF(ppcnt_reg, counter_set.phys_layer_recovery_cntrs.c)
+static const struct counter_desc
+pport_phy_recovery_cntrs_stats_desc[] = {
+	{ "total_success_recovery_phy",
+	  PPORT_PHY_RECOVERY_OFF(total_successful_recovery_events) }
+};
+
+#define NUM_PPORT_PHY_LAYER_COUNTERS \
+	ARRAY_SIZE(pport_phy_layer_cntrs_stats_desc)
 #define NUM_PPORT_PHY_STATISTICAL_COUNTERS \
 	ARRAY_SIZE(pport_phy_statistical_stats_desc)
 #define NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS \
 	ARRAY_SIZE(pport_phy_statistical_err_lanes_stats_desc)
+#define NUM_PPORT_PHY_RECOVERY_COUNTERS \
+	ARRAY_SIZE(pport_phy_recovery_cntrs_stats_desc)
+
+#define NUM_PPORT_PHY_STATISTICAL_LOOPBACK_COUNTERS(dev) \
+	(MLX5_CAP_PCAM_FEATURE(dev, ppcnt_statistical_group) ? \
+	NUM_PPORT_PHY_STATISTICAL_COUNTERS : 0)
+#define NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(dev) \
+	(MLX5_CAP_PCAM_FEATURE(dev, per_lane_error_counters) ? \
+	NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS : 0)
+#define NUM_PPORT_PHY_RECOVERY_LOOPBACK_COUNTERS(dev) \
+	(MLX5_CAP_PCAM_FEATURE(dev, ppcnt_recovery_counters) ? \
+	NUM_PPORT_PHY_RECOVERY_COUNTERS : 0)
 
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(phy)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int num_stats;
 
-	/* "1" for link_down_events special counter */
-	num_stats = 1;
+	num_stats = NUM_PPORT_PHY_LAYER_COUNTERS;
 
-	num_stats += MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group) ?
-		     NUM_PPORT_PHY_STATISTICAL_COUNTERS : 0;
+	num_stats += NUM_PPORT_PHY_STATISTICAL_LOOPBACK_COUNTERS(mdev);
 
-	num_stats += MLX5_CAP_PCAM_FEATURE(mdev, per_lane_error_counters) ?
-		     NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS : 0;
+	num_stats += NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(mdev);
 
+	num_stats += NUM_PPORT_PHY_RECOVERY_LOOPBACK_COUNTERS(mdev);
 	return num_stats;
 }
 
@@ -1270,18 +1285,22 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(phy)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int i;
 
-	ethtool_puts(data, "link_down_events_phy");
-
-	if (!MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
-		return;
+	for (i = 0; i < NUM_PPORT_PHY_LAYER_COUNTERS; i++)
+		ethtool_puts(data, pport_phy_layer_cntrs_stats_desc[i].format);
 
-	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)
+	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_LOOPBACK_COUNTERS(mdev); i++)
 		ethtool_puts(data, pport_phy_statistical_stats_desc[i].format);
 
-	if (MLX5_CAP_PCAM_FEATURE(mdev, per_lane_error_counters))
-		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS; i++)
-			ethtool_puts(data,
-				     pport_phy_statistical_err_lanes_stats_desc[i].format);
+	for (i = 0;
+	     i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(mdev);
+	     i++)
+		ethtool_puts(data,
+			     pport_phy_statistical_err_lanes_stats_desc[i]
+			     .format);
+
+	for (i = 0; i < NUM_PPORT_PHY_RECOVERY_LOOPBACK_COUNTERS(mdev); i++)
+		ethtool_puts(data,
+			     pport_phy_recovery_cntrs_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(phy)
@@ -1289,30 +1308,35 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(phy)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int i;
 
-	/* link_down_events_phy has special handling since it is not stored in __be64 format */
-	mlx5e_ethtool_put_stat(
-		data, MLX5_GET(ppcnt_reg, priv->stats.pport.phy_counters,
-			       counter_set.phys_layer_cntrs.link_down_events));
-
-	if (!MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
-		return;
+	for (i = 0; i < NUM_PPORT_PHY_LAYER_COUNTERS; i++)
+		mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR32_BE(&priv->stats.pport
+					.phy_counters,
+					pport_phy_layer_cntrs_stats_desc, i));
 
-	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)
+	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_LOOPBACK_COUNTERS(mdev); i++)
 		mlx5e_ethtool_put_stat(
 			data,
 			MLX5E_READ_CTR64_BE(
 				&priv->stats.pport.phy_statistical_counters,
 				pport_phy_statistical_stats_desc, i));
 
-	if (MLX5_CAP_PCAM_FEATURE(mdev, per_lane_error_counters))
-		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS; i++)
-			mlx5e_ethtool_put_stat(
-				data,
-				MLX5E_READ_CTR64_BE(
-					&priv->stats.pport
-						 .phy_statistical_counters,
-					pport_phy_statistical_err_lanes_stats_desc,
-					i));
+	for (i = 0;
+	     i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(mdev);
+	     i++)
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR64_BE(
+				&priv->stats.pport.phy_statistical_counters,
+				pport_phy_statistical_err_lanes_stats_desc, i));
+
+	for (i = 0; i < NUM_PPORT_PHY_RECOVERY_LOOPBACK_COUNTERS(mdev); i++)
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR32_BE(
+				&priv->stats.pport.phy_recovery_counters,
+				pport_phy_recovery_cntrs_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(phy)
@@ -1328,12 +1352,21 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(phy)
 	MLX5_SET(ppcnt_reg, in, grp, MLX5_PHYSICAL_LAYER_COUNTERS_GROUP);
 	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
 
-	if (!MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
-		return;
+	if (MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group)) {
+		out = pstats->phy_statistical_counters;
+		MLX5_SET(ppcnt_reg, in, grp,
+			 MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP);
+		mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0,
+				     0);
+	}
 
-	out = pstats->phy_statistical_counters;
-	MLX5_SET(ppcnt_reg, in, grp, MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP);
-	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
+	if (MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_recovery_counters)) {
+		out = pstats->phy_recovery_counters;
+		MLX5_SET(ppcnt_reg, in, grp,
+			 MLX5_PHYSICAL_LAYER_RECOVERY_GROUP);
+		mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0,
+				     0);
+	}
 }
 
 void mlx5e_get_link_ext_stats(struct net_device *dev,
@@ -1413,16 +1446,13 @@ static void fec_set_rs_stats(struct ethtool_fec_stats *fec_stats, u32 *ppcnt)
 }
 
 static void fec_set_block_stats(struct mlx5e_priv *priv,
+				int mode,
 				struct ethtool_fec_stats *fec_stats)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u32 out[MLX5_ST_SZ_DW(ppcnt_reg)] = {};
 	u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {};
 	int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
-	int mode = fec_active_mode(mdev);
-
-	if (mode == MLX5E_FEC_NOFEC)
-		return;
 
 	MLX5_SET(ppcnt_reg, in, local_port, 1);
 	MLX5_SET(ppcnt_reg, in, grp, MLX5_PHYSICAL_LAYER_COUNTERS_GROUP);
@@ -1433,6 +1463,7 @@ static void fec_set_block_stats(struct mlx5e_priv *priv,
 	case MLX5E_FEC_RS_528_514:
 	case MLX5E_FEC_RS_544_514:
 	case MLX5E_FEC_LLRS_272_257_1:
+	case MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD:
 		fec_set_rs_stats(fec_stats, out);
 		return;
 	case MLX5E_FEC_FIRECODE:
@@ -1460,14 +1491,132 @@ static void fec_set_corrected_bits_total(struct mlx5e_priv *priv,
 				      phy_corrected_bits);
 }
 
+#define MLX5_RS_HISTOGRAM_ENTRIES \
+	(MLX5_FLD_SZ_BYTES(rs_histogram_cntrs, hist) / \
+	 MLX5_FLD_SZ_BYTES(rs_histogram_cntrs, hist[0]))
+
+enum {
+	MLX5E_HISTOGRAM_FEC_RS_544_514 = 1,
+	MLX5E_HISTOGRAM_FEC_LLRS = 2,
+	MLX5E_HISTOGRAM_FEC_RS_528_514 = 3,
+};
+
+static bool fec_rs_validate_hist_type(int mode, int hist_type)
+{
+	switch (mode) {
+	case MLX5E_FEC_RS_528_514:
+		return hist_type == MLX5E_HISTOGRAM_FEC_RS_528_514;
+	case MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD:
+	case MLX5E_FEC_RS_544_514:
+		return hist_type == MLX5E_HISTOGRAM_FEC_RS_544_514;
+	case MLX5E_FEC_LLRS_272_257_1:
+		return hist_type == MLX5E_HISTOGRAM_FEC_LLRS;
+	default:
+		break;
+	}
+
+	return false;
+}
+
+static u8
+fec_rs_histogram_fill_ranges(struct mlx5e_priv *priv, int mode,
+			     const struct ethtool_fec_hist_range **ranges)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 out[MLX5_ST_SZ_DW(pphcr_reg)] = {0};
+	u32 in[MLX5_ST_SZ_DW(pphcr_reg)] = {0};
+	int sz = MLX5_ST_SZ_BYTES(pphcr_reg);
+	u8 hist_type, num_of_bins;
+
+	memset(priv->fec_ranges, 0,
+	       ETHTOOL_FEC_HIST_MAX * sizeof(*priv->fec_ranges));
+	MLX5_SET(pphcr_reg, in, local_port, 1);
+	if (mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPHCR, 0, 0))
+		return 0;
+
+	hist_type = MLX5_GET(pphcr_reg, out, active_hist_type);
+	if (!fec_rs_validate_hist_type(mode, hist_type))
+		return 0;
+
+	num_of_bins = MLX5_GET(pphcr_reg, out, num_of_bins);
+	if (WARN_ON_ONCE(num_of_bins > MLX5_RS_HISTOGRAM_ENTRIES))
+		return 0;
+
+	for (int i = 0; i < num_of_bins; i++) {
+		void *bin_range = MLX5_ADDR_OF(pphcr_reg, out, bin_range[i]);
+
+		priv->fec_ranges[i].high = MLX5_GET(bin_range_layout, bin_range,
+						    high_val);
+		priv->fec_ranges[i].low = MLX5_GET(bin_range_layout, bin_range,
+						   low_val);
+	}
+	*ranges = priv->fec_ranges;
+
+	return num_of_bins;
+}
+
+static void fec_rs_histogram_fill_stats(struct mlx5e_priv *priv,
+					u8 num_of_bins,
+					struct ethtool_fec_hist *hist)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 out[MLX5_ST_SZ_DW(ppcnt_reg)] = {0};
+	u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {0};
+	int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
+	void *rs_histogram_cntrs;
+
+	MLX5_SET(ppcnt_reg, in, local_port, 1);
+	MLX5_SET(ppcnt_reg, in, grp, MLX5_RS_FEC_HISTOGRAM_GROUP);
+	if (mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0))
+		return;
+
+	rs_histogram_cntrs = MLX5_ADDR_OF(ppcnt_reg, out,
+					  counter_set.rs_histogram_cntrs);
+	/* Guaranteed that num_of_bins is less than MLX5E_FEC_RS_HIST_MAX
+	 * by fec_rs_histogram_fill_ranges().
+	 */
+	for (int i = 0; i < num_of_bins; i++)
+		hist->values[i].sum = MLX5_GET64(rs_histogram_cntrs,
+						 rs_histogram_cntrs,
+						 hist[i]);
+}
+
+static void fec_set_histograms_stats(struct mlx5e_priv *priv, int mode,
+				     struct ethtool_fec_hist *hist)
+{
+	u8 num_of_bins;
+
+	switch (mode) {
+	case MLX5E_FEC_RS_528_514:
+	case MLX5E_FEC_RS_544_514:
+	case MLX5E_FEC_LLRS_272_257_1:
+	case MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD:
+		num_of_bins =
+			fec_rs_histogram_fill_ranges(priv, mode, &hist->ranges);
+		if (num_of_bins)
+			return fec_rs_histogram_fill_stats(priv, num_of_bins,
+							   hist);
+		break;
+	default:
+		return;
+	}
+}
+
 void mlx5e_stats_fec_get(struct mlx5e_priv *priv,
-			 struct ethtool_fec_stats *fec_stats)
+			 struct ethtool_fec_stats *fec_stats,
+			 struct ethtool_fec_hist *hist)
 {
-	if (!MLX5_CAP_PCAM_FEATURE(priv->mdev, ppcnt_statistical_group))
+	int mode = fec_active_mode(priv->mdev);
+
+	if (mode == MLX5E_FEC_NOFEC ||
+	    !MLX5_CAP_PCAM_FEATURE(priv->mdev, ppcnt_statistical_group))
 		return;
 
 	fec_set_corrected_bits_total(priv, fec_stats);
-	fec_set_block_stats(priv, fec_stats);
+	fec_set_block_stats(priv, mode, fec_stats);
+
+	if (MLX5_CAP_PCAM_REG(priv->mdev, pphcr))
+		fec_set_histograms_stats(priv, mode, hist);
 }
 
 #define PPORT_ETH_EXT_OFF(c) \
@@ -2086,7 +2235,6 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_err) },
 #endif
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, recover) },
-#ifdef CONFIG_PAGE_POOL_STATS
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_alloc_fast) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_alloc_slow) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_alloc_slow_high_order) },
@@ -2098,7 +2246,6 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_recycle_ring) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_recycle_ring_full) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_recycle_released_ref) },
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_bytes) },
@@ -2393,8 +2540,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ptp)
 	}
 	if (priv->rx_ptp_opened) {
 		for (i = 0; i < NUM_PTP_RQ_STATS; i++)
-			ethtool_sprintf(data, ptp_rq_stats_desc[i].format,
-					MLX5E_PTP_CHANNEL_IX);
+			ethtool_puts(data, ptp_rq_stats_desc[i].format);
 	}
 }
 
@@ -2582,6 +2728,7 @@ mlx5e_stats_grp_t mlx5e_nic_stats_grps[] = {
 #ifdef CONFIG_MLX5_MACSEC
 	&MLX5E_STATS_GRP(macsec_hw),
 #endif
+	&MLX5E_STATS_GRP(pcie_cong),
 };
 
 unsigned int mlx5e_nic_stats_grps_num(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 5961c569cfe0..09f155acb461 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -54,7 +54,7 @@
 #define MLX5E_DECLARE_PTP_TX_STAT(type, fld) "ptp_tx%d_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_PTP_CH_STAT(type, fld) "ptp_ch_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_PTP_CQ_STAT(type, fld) "ptp_cq%d_"#fld, offsetof(type, fld)
-#define MLX5E_DECLARE_PTP_RQ_STAT(type, fld) "ptp_rq%d_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_PTP_RQ_STAT(type, fld) "ptp_rq0_"#fld, offsetof(type, fld)
 
 #define MLX5E_DECLARE_QOS_TX_STAT(type, fld) "qos_tx%d_"#fld, offsetof(type, fld)
 
@@ -117,7 +117,8 @@ void mlx5e_stats_update_ndo_stats(struct mlx5e_priv *priv);
 void mlx5e_stats_pause_get(struct mlx5e_priv *priv,
 			   struct ethtool_pause_stats *pause_stats);
 void mlx5e_stats_fec_get(struct mlx5e_priv *priv,
-			 struct ethtool_fec_stats *fec_stats);
+			 struct ethtool_fec_stats *fec_stats,
+			 struct ethtool_fec_hist *hist);
 
 void mlx5e_stats_eth_phy_get(struct mlx5e_priv *priv,
 			     struct ethtool_eth_phy_stats *phy_stats);
@@ -215,7 +216,6 @@ struct mlx5e_sw_stats {
 	u64 ch_aff_change;
 	u64 ch_force_irq;
 	u64 ch_eq_rearm;
-#ifdef CONFIG_PAGE_POOL_STATS
 	u64 rx_pp_alloc_fast;
 	u64 rx_pp_alloc_slow;
 	u64 rx_pp_alloc_slow_high_order;
@@ -227,7 +227,6 @@ struct mlx5e_sw_stats {
 	u64 rx_pp_recycle_ring;
 	u64 rx_pp_recycle_ring_full;
 	u64 rx_pp_recycle_released_ref;
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tx_tls_encrypted_packets;
 	u64 tx_tls_encrypted_bytes;
@@ -309,6 +308,9 @@ struct mlx5e_vport_stats {
 #define PPORT_PHY_STATISTICAL_GET(pstats, c) \
 	MLX5_GET64(ppcnt_reg, (pstats)->phy_statistical_counters, \
 		   counter_set.phys_layer_statistical_cntrs.c##_high)
+#define PPORT_PHY_RECOVERY_GET(pstats, c) \
+	MLX5_GET64(ppcnt_reg, (pstats)->phy_recovery_counters, \
+		   counter_set.phys_layer_recovery_cntrs.c)
 #define PPORT_PER_PRIO_GET(pstats, prio, c) \
 	MLX5_GET64(ppcnt_reg, pstats->per_prio_counters[prio], \
 		   counter_set.eth_per_prio_grp_data_layout.c##_high)
@@ -324,6 +326,7 @@ struct mlx5e_pport_stats {
 	__be64 per_prio_counters[NUM_PPORT_PRIO][MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 phy_counters[MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 phy_statistical_counters[MLX5_ST_SZ_QW(ppcnt_reg)];
+	__be64 phy_recovery_counters[MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 eth_ext_counters[MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 per_tc_prio_counters[NUM_PPORT_PRIO][MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 per_tc_congest_prio_counters[NUM_PPORT_PRIO][MLX5_ST_SZ_QW(ppcnt_reg)];
@@ -381,7 +384,6 @@ struct mlx5e_rq_stats {
 	u64 arfs_err;
 #endif
 	u64 recover;
-#ifdef CONFIG_PAGE_POOL_STATS
 	u64 pp_alloc_fast;
 	u64 pp_alloc_slow;
 	u64 pp_alloc_slow_high_order;
@@ -393,7 +395,6 @@ struct mlx5e_rq_stats {
 	u64 pp_recycle_ring;
 	u64 pp_recycle_ring_full;
 	u64 pp_recycle_released_ref;
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tls_decrypted_packets;
 	u64 tls_decrypted_bytes;
@@ -535,5 +536,6 @@ extern MLX5E_DECLARE_STATS_GRP(ipsec_hw);
 extern MLX5E_DECLARE_STATS_GRP(ipsec_sw);
 extern MLX5E_DECLARE_STATS_GRP(ptp);
 extern MLX5E_DECLARE_STATS_GRP(macsec_hw);
+extern MLX5E_DECLARE_STATS_GRP(pcie_cong);
 
 #endif /* __MLX5_EN_STATS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9ba99609999f..a8773b2342c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -66,6 +66,7 @@
 #include "lib/devcom.h"
 #include "lib/geneve.h"
 #include "lib/fs_chains.h"
+#include "lib/mlx5.h"
 #include "diag/en_tc_tracepoint.h"
 #include <asm/div64.h>
 #include "lag/lag.h"
@@ -757,11 +758,11 @@ static int mlx5e_hairpin_create_indirect_rqt(struct mlx5e_hairpin *hp)
 	struct mlx5e_priv *priv = hp->func_priv;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_rss_params_indir indir;
+	u32 rqt_size;
 	int err;
 
-	err = mlx5e_rss_params_indir_init(&indir, mdev,
-					  mlx5e_rqt_size(mdev, hp->num_channels),
-					  mlx5e_rqt_size(mdev, hp->num_channels));
+	rqt_size = mlx5e_rqt_size(mdev, hp->num_channels);
+	err = mlx5e_rss_params_indir_init(&indir, rqt_size, rqt_size);
 	if (err)
 		return err;
 
@@ -837,6 +838,9 @@ static void mlx5e_hairpin_set_ttc_params(struct mlx5e_hairpin *hp,
 
 	ttc_params->ns_type = MLX5_FLOW_NAMESPACE_KERNEL;
 	for (tt = 0; tt < MLX5_NUM_TT; tt++) {
+		if (mlx5_ttc_is_decrypted_esp_tt(tt))
+			continue;
+
 		ttc_params->dests[tt].type = MLX5_FLOW_DESTINATION_TYPE_TIR;
 		ttc_params->dests[tt].tir_num =
 			tt == MLX5_TT_ANY ?
@@ -1750,9 +1754,6 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr
 	    !list_is_first(&attr->list, &flow->attrs))
 		return 0;
 
-	if (flow_flag_test(flow, SLOW))
-		return 0;
-
 	esw_attr = attr->esw_attr;
 	if (!esw_attr->split_count ||
 	    esw_attr->split_count == esw_attr->out_count - 1)
@@ -1766,7 +1767,7 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr
 	for (i = esw_attr->split_count; i < esw_attr->out_count; i++) {
 		/* external dest with encap is considered as internal by firmware */
 		if (esw_attr->dests[i].vport == MLX5_VPORT_UPLINK &&
-		    !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP_VALID))
+		    !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP))
 			ext_dest = true;
 		else
 			int_dest = true;
@@ -2031,9 +2032,8 @@ err_out:
 	return err;
 }
 
-static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow)
+static bool mlx5_flow_has_geneve_opt(struct mlx5_flow_spec *spec)
 {
-	struct mlx5_flow_spec *spec = &flow->attr->parse_attr->spec;
 	void *headers_v = MLX5_ADDR_OF(fte_match_param,
 				       spec->match_value,
 				       misc_parameters_3);
@@ -2072,7 +2072,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	}
 	complete_all(&flow->del_hw_done);
 
-	if (mlx5_flow_has_geneve_opt(flow))
+	if (mlx5_flow_has_geneve_opt(&attr->parse_attr->spec))
 		mlx5_geneve_tlv_option_del(priv->mdev->geneve);
 
 	if (flow->decap_route)
@@ -2577,12 +2577,13 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 
 		err = mlx5e_tc_tun_parse(filter_dev, priv, tmp_spec, f, match_level);
 		if (err) {
-			kvfree(tmp_spec);
 			NL_SET_ERR_MSG_MOD(extack, "Failed to parse tunnel attributes");
 			netdev_warn(priv->netdev, "Failed to parse tunnel attributes");
-			return err;
+		} else {
+			err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
 		}
-		err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
+		if (mlx5_flow_has_geneve_opt(tmp_spec))
+			mlx5_geneve_tlv_option_del(priv->mdev->geneve);
 		kvfree(tmp_spec);
 		if (err)
 			return err;
@@ -3613,15 +3614,11 @@ static bool same_port_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv
 bool mlx5e_same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv)
 {
 	struct mlx5_core_dev *fmdev, *pmdev;
-	u64 fsystem_guid, psystem_guid;
 
 	fmdev = priv->mdev;
 	pmdev = peer_priv->mdev;
 
-	fsystem_guid = mlx5_query_nic_system_image_guid(fmdev);
-	psystem_guid = mlx5_query_nic_system_image_guid(pmdev);
-
-	return (fsystem_guid == psystem_guid);
+	return mlx5_same_hw_devs(fmdev, pmdev);
 }
 
 static int
@@ -5236,10 +5233,11 @@ static void mlx5e_tc_nic_destroy_miss_table(struct mlx5e_priv *priv)
 int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 {
 	struct mlx5e_tc_table *tc = mlx5e_fs_get_tc(priv->fs);
+	u8 mapping_id[MLX5_SW_IMAGE_GUID_MAX_BYTES];
 	struct mlx5_core_dev *dev = priv->mdev;
 	struct mapping_ctx *chains_mapping;
 	struct mlx5_chains_attr attr = {};
-	u64 mapping_id;
+	u8 id_len;
 	int err;
 
 	mlx5e_mod_hdr_tbl_init(&tc->mod_hdr);
@@ -5255,11 +5253,13 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 	lockdep_set_class(&tc->ht.mutex, &tc_ht_lock_key);
 	lockdep_init_map(&tc->ht.run_work.lockdep_map, "tc_ht_wq_key", &tc_ht_wq_key, 0);
 
-	mapping_id = mlx5_query_nic_system_image_guid(dev);
+	mlx5_query_nic_sw_system_image_guid(dev, mapping_id, &id_len);
 
-	chains_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_CHAIN,
+	chains_mapping = mapping_create_for_id(mapping_id, id_len,
+					       MAPPING_TYPE_CHAIN,
 					       sizeof(struct mlx5_mapped_obj),
-					       MLX5E_TC_TABLE_CHAIN_TAG_MASK, true);
+					       MLX5E_TC_TABLE_CHAIN_TAG_MASK,
+					       true);
 
 	if (IS_ERR(chains_mapping)) {
 		err = PTR_ERR(chains_mapping);
@@ -5390,13 +5390,15 @@ void mlx5e_tc_ht_cleanup(struct rhashtable *tc_ht)
 int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv)
 {
 	const size_t sz_enc_opts = sizeof(struct tunnel_match_enc_opts);
+	u8 mapping_id[MLX5_SW_IMAGE_GUID_MAX_BYTES];
+	struct mlx5_devcom_match_attr attr = {};
 	struct netdev_phys_item_id ppid;
 	struct mlx5e_rep_priv *rpriv;
 	struct mapping_ctx *mapping;
 	struct mlx5_eswitch *esw;
 	struct mlx5e_priv *priv;
-	u64 mapping_id, key;
 	int err = 0;
+	u8 id_len;
 
 	rpriv = container_of(uplink_priv, struct mlx5e_rep_priv, uplink_priv);
 	priv = netdev_priv(rpriv->netdev);
@@ -5414,9 +5416,9 @@ int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv)
 
 	uplink_priv->tc_psample = mlx5e_tc_sample_init(esw, uplink_priv->post_act);
 
-	mapping_id = mlx5_query_nic_system_image_guid(esw->dev);
+	mlx5_query_nic_sw_system_image_guid(esw->dev, mapping_id, &id_len);
 
-	mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_TUNNEL,
+	mapping = mapping_create_for_id(mapping_id, id_len, MAPPING_TYPE_TUNNEL,
 					sizeof(struct tunnel_match_key),
 					TUNNEL_INFO_BITS_MASK, true);
 
@@ -5429,8 +5431,10 @@ int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv)
 	/* Two last values are reserved for stack devices slow path table mark
 	 * and bridge ingress push mark.
 	 */
-	mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_TUNNEL_ENC_OPTS,
-					sz_enc_opts, ENC_OPTS_BITS_MASK - 2, true);
+	mapping = mapping_create_for_id(mapping_id, id_len,
+					MAPPING_TYPE_TUNNEL_ENC_OPTS,
+					sz_enc_opts, ENC_OPTS_BITS_MASK - 2,
+					true);
 	if (IS_ERR(mapping)) {
 		err = PTR_ERR(mapping);
 		goto err_enc_opts_mapping;
@@ -5449,10 +5453,12 @@ int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv)
 		goto err_action_counter;
 	}
 
-	err = dev_get_port_parent_id(priv->netdev, &ppid, false);
+	err = netif_get_port_parent_id(priv->netdev, &ppid, false);
 	if (!err) {
-		memcpy(&key, &ppid.id, sizeof(key));
-		mlx5_esw_offloads_devcom_init(esw, key);
+		memcpy(&attr.key.buf, &ppid.id, ppid.id_len);
+		attr.flags = MLX5_DEVCOM_MATCH_FLAGS_NS;
+		attr.net = mlx5_core_net(esw->dev);
+		mlx5_esw_offloads_devcom_init(esw, &attr);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f8c7912abe0e..14884b9ea7f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -39,6 +39,7 @@
 #include "ipoib/ipoib.h"
 #include "en_accel/en_accel.h"
 #include "en_accel/ipsec_rxtx.h"
+#include "en_accel/psp_rxtx.h"
 #include "en_accel/macsec.h"
 #include "en/ptp.h"
 #include <net/ipv6.h>
@@ -120,6 +121,11 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			    struct mlx5e_accel_tx_state *accel,
 			    struct mlx5_wqe_eth_seg *eseg)
 {
+#ifdef CONFIG_MLX5_EN_PSP
+	if (unlikely(mlx5e_psp_txwqe_build_eseg_csum(sq, skb, &accel->psp_st, eseg)))
+		return;
+#endif
+
 	if (unlikely(mlx5e_ipsec_txwqe_build_eseg_csum(sq, skb, eseg)))
 		return;
 
@@ -196,7 +202,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		dseg->lkey       = sq->mkey_be;
 		dseg->byte_count = cpu_to_be32(headlen);
 
-		mlx5e_dma_push(sq, dma_addr, headlen, MLX5E_DMA_MAP_SINGLE);
+		mlx5e_dma_push_single(sq, dma_addr, headlen);
 		num_dma++;
 		dseg++;
 	}
@@ -214,7 +220,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		dseg->lkey       = sq->mkey_be;
 		dseg->byte_count = cpu_to_be32(fsz);
 
-		mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE);
+		mlx5e_dma_push_netmem(sq, skb_frag_netmem(frag), dma_addr, fsz);
 		num_dma++;
 		dseg++;
 	}
@@ -250,14 +256,13 @@ mlx5e_tx_wqe_inline_mode(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	u8 mode;
 
 #ifdef CONFIG_MLX5_EN_TLS
-	if (accel && accel->tls.tls_tisn)
+	if (accel->tls.tls_tisn)
 		return MLX5_INLINE_MODE_TCP_UDP;
 #endif
 
 	mode = sq->min_inline_mode;
 
-	if (skb_vlan_tag_present(skb) &&
-	    test_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state))
+	if (skb_vlan_tag_present(skb))
 		mode = max_t(u8, MLX5_INLINE_MODE_L2, mode);
 
 	return mode;
@@ -298,7 +303,7 @@ static void mlx5e_sq_xmit_prepare(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		stats->packets++;
 	}
 
-	attr->insz = mlx5e_accel_tx_ids_len(sq, accel);
+	attr->insz = mlx5e_accel_tx_ids_len(sq, skb, accel);
 	stats->bytes += attr->num_bytes;
 }
 
@@ -337,10 +342,11 @@ static void mlx5e_sq_calc_wqe_attr(struct sk_buff *skb, const struct mlx5e_tx_at
 	};
 }
 
-static void mlx5e_tx_skb_update_hwts_flags(struct sk_buff *skb)
+static void mlx5e_tx_skb_update_ts_flags(struct sk_buff *skb)
 {
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+	skb_tx_timestamp(skb);
 }
 
 static void mlx5e_tx_check_stop(struct mlx5e_txqsq *sq)
@@ -392,7 +398,7 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | attr->opcode);
 	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | wqe_attr->ds_cnt);
 
-	mlx5e_tx_skb_update_hwts_flags(skb);
+	mlx5e_tx_skb_update_ts_flags(skb);
 
 	sq->pc += wi->num_wqebbs;
 
@@ -482,12 +488,6 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		}
 		eseg->inline_hdr.sz |= cpu_to_be16(ihs);
 		dseg += wqe_attr->ds_cnt_inl;
-	} else if (skb_vlan_tag_present(skb)) {
-		eseg->insert.type = cpu_to_be16(MLX5_ETH_WQE_INSERT_VLAN);
-		if (skb->vlan_proto == cpu_to_be16(ETH_P_8021AD))
-			eseg->insert.type |= cpu_to_be16(MLX5_ETH_WQE_SVLAN);
-		eseg->insert.vlan_tci = cpu_to_be16(skb_vlan_tag_get(skb));
-		stats->added_vlan_packets++;
 	}
 
 	dseg += wqe_attr->ds_cnt_ids;
@@ -525,9 +525,9 @@ static void mlx5e_tx_mpwqe_session_start(struct mlx5e_txqsq *sq,
 {
 	struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
 	struct mlx5e_tx_wqe *wqe;
-	u16 pi;
+	u16 pi, num_wqebbs;
 
-	pi = mlx5e_txqsq_get_next_pi(sq, sq->max_sq_mpw_wqebbs);
+	pi = mlx5e_txqsq_get_next_pi_anysize(sq, &num_wqebbs);
 	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
 	net_prefetchw(wqe->data);
 
@@ -535,6 +535,7 @@ static void mlx5e_tx_mpwqe_session_start(struct mlx5e_txqsq *sq,
 		.wqe = wqe,
 		.bytes_count = 0,
 		.ds_count = MLX5E_TX_WQE_EMPTY_DS_COUNT,
+		.ds_count_max = num_wqebbs * MLX5_SEND_WQEBB_NUM_DS,
 		.pkt_count = 0,
 		.inline_on = 0,
 	};
@@ -621,12 +622,12 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 
 	sq->stats->xmit_more += xmit_more;
 
-	mlx5e_dma_push(sq, txd.dma_addr, txd.len, MLX5E_DMA_MAP_SINGLE);
+	mlx5e_dma_push_single(sq, txd.dma_addr, txd.len);
 	mlx5e_skb_fifo_push(&sq->db.skb_fifo, skb);
 	mlx5e_tx_mpwqe_add_dseg(sq, &txd);
-	mlx5e_tx_skb_update_hwts_flags(skb);
+	mlx5e_tx_skb_update_ts_flags(skb);
 
-	if (unlikely(mlx5e_tx_mpwqe_is_full(&sq->mpwqe, sq->max_sq_mpw_wqebbs))) {
+	if (unlikely(mlx5e_tx_mpwqe_is_full(&sq->mpwqe))) {
 		/* Might stop the queue and affect the retval of __netdev_tx_sent_queue. */
 		cseg = mlx5e_tx_mpwqe_session_complete(sq);
 
@@ -658,7 +659,7 @@ static void mlx5e_cqe_ts_id_eseg(struct mlx5e_ptpsq *ptpsq, struct sk_buff *skb,
 				 struct mlx5_wqe_eth_seg *eseg)
 {
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
-		eseg->flow_table_metadata =
+		eseg->flow_table_metadata |=
 			cpu_to_be32(mlx5e_ptp_metadata_fifo_peek(&ptpsq->metadata_freelist));
 }
 
@@ -666,7 +667,7 @@ static void mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *
 				   struct sk_buff *skb, struct mlx5e_accel_tx_state *accel,
 				   struct mlx5_wqe_eth_seg *eseg, u16 ihs)
 {
-	mlx5e_accel_tx_eseg(priv, skb, eseg, ihs);
+	mlx5e_accel_tx_eseg(priv, skb, accel, eseg, ihs);
 	mlx5e_txwqe_build_eseg_csum(sq, skb, accel, eseg);
 	if (unlikely(sq->ptpsq))
 		mlx5e_cqe_ts_id_eseg(sq->ptpsq, skb, eseg);
@@ -754,7 +755,7 @@ static void mlx5e_consume_skb(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		hwts.hwtstamp = mlx5e_cqe_ts_to_ns(sq->ptp_cyc2time, sq->clock, ts);
 		if (sq->ptpsq) {
 			mlx5e_skb_cb_hwtstamp_handler(skb, MLX5E_SKB_CB_CQE_HWTSTAMP,
-						      hwts.hwtstamp, sq->ptpsq->cq_stats);
+						      hwts.hwtstamp, sq->ptpsq);
 		} else {
 			skb_tstamp_tx(skb, &hwts);
 			sq->stats->timestamps++;
@@ -981,6 +982,7 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	struct mlx5e_tx_attr attr;
 	struct mlx5i_tx_wqe *wqe;
 
+	struct mlx5e_accel_tx_state accel = {};
 	struct mlx5_wqe_datagram_seg *datagram;
 	struct mlx5_wqe_ctrl_seg *cseg;
 	struct mlx5_wqe_eth_seg  *eseg;
@@ -991,7 +993,7 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	int num_dma;
 	u16 pi;
 
-	mlx5e_sq_xmit_prepare(sq, skb, NULL, &attr);
+	mlx5e_sq_xmit_prepare(sq, skb, &accel, &attr);
 	mlx5i_sq_calc_wqe_attr(skb, &attr, &wqe_attr);
 
 	pi = mlx5e_txqsq_get_next_pi(sq, wqe_attr.num_wqebbs);
@@ -1008,7 +1010,7 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 
 	mlx5i_txwqe_build_datagram(av, dqpn, dqkey, datagram);
 
-	mlx5e_txwqe_build_eseg_csum(sq, skb, NULL, eseg);
+	mlx5e_txwqe_build_eseg_csum(sq, skb, &accel, eseg);
 
 	eseg->mss = attr.mss;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 2b229b6226c6..25499da177bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -32,9 +32,7 @@ enum {
 	MLX5_EQ_STATE_ALWAYS_ARMED	= 0xb,
 };
 
-enum {
-	MLX5_EQ_DOORBEL_OFFSET	= 0x40,
-};
+#define MLX5_EQ_DOORBELL_OFFSET 0x40
 
 /* budget must be smaller than MLX5_NUM_SPARE_EQE to guarantee that we update
  * the ci before we polled all the entries in the EQ. MLX5_NUM_SPARE_EQE is
@@ -309,7 +307,7 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 
 	eqc = MLX5_ADDR_OF(create_eq_in, in, eq_context_entry);
 	MLX5_SET(eqc, eqc, log_eq_size, eq->fbc.log_sz);
-	MLX5_SET(eqc, eqc, uar_page, priv->uar->index);
+	MLX5_SET(eqc, eqc, uar_page, priv->bfreg.up->index);
 	MLX5_SET(eqc, eqc, intr, vecidx);
 	MLX5_SET(eqc, eqc, log_page_size,
 		 eq->frag_buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
@@ -322,7 +320,7 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 	eq->eqn = MLX5_GET(create_eq_out, out, eq_number);
 	eq->irqn = pci_irq_vector(dev->pdev, vecidx);
 	eq->dev = dev;
-	eq->doorbell = priv->uar->map + MLX5_EQ_DOORBEL_OFFSET;
+	eq->doorbell = priv->bfreg.up->map + MLX5_EQ_DOORBELL_OFFSET;
 
 	err = mlx5_debug_eq_add(dev, eq);
 	if (err)
@@ -585,6 +583,9 @@ static void gather_async_events_mask(struct mlx5_core_dev *dev, u64 mask[4])
 		async_event_mask |=
 			(1ull << MLX5_EVENT_TYPE_OBJECT_CHANGE);
 
+	if (mlx5_pcie_cong_event_supported(dev))
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_OBJECT_CHANGE);
+
 	mask[0] = async_event_mask;
 
 	if (MLX5_CAP_GEN(dev, event_cap))
@@ -871,21 +872,27 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx)
 
 static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx)
 {
+	struct mlx5_irq_pool *pool = mlx5_irq_table_get_comp_irq_pool(dev);
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
-	struct irq_affinity_desc af_desc = {};
+	struct irq_affinity_desc *af_desc;
 	struct mlx5_irq *irq;
 
-	/* In case SF irq pool does not exist, fallback to the PF irqs*/
+	/* In case SF irq pool does not exist, fallback to the PF irqs */
 	if (!mlx5_irq_pool_is_sf_pool(pool))
 		return comp_irq_request_pci(dev, vecidx);
 
-	af_desc.is_managed = false;
-	cpumask_copy(&af_desc.mask, cpu_online_mask);
-	cpumask_andnot(&af_desc.mask, &af_desc.mask, &table->used_cpus);
-	irq = mlx5_irq_affinity_request(dev, pool, &af_desc);
-	if (IS_ERR(irq))
+	af_desc = kvzalloc(sizeof(*af_desc), GFP_KERNEL);
+	if (!af_desc)
+		return -ENOMEM;
+
+	af_desc->is_managed = false;
+	cpumask_copy(&af_desc->mask, cpu_online_mask);
+	cpumask_andnot(&af_desc->mask, &af_desc->mask, &table->used_cpus);
+	irq = mlx5_irq_affinity_request(dev, pool, af_desc);
+	if (IS_ERR(irq)) {
+		kvfree(af_desc);
 		return PTR_ERR(irq);
+	}
 
 	cpumask_or(&table->used_cpus, &table->used_cpus, mlx5_irq_get_affinity_mask(irq));
 	mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n",
@@ -893,6 +900,8 @@ static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx)
 		      cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)),
 		      mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ);
 
+	kvfree(af_desc);
+
 	return xa_err(xa_store(&table->comp_irqs, vecidx, irq, GFP_KERNEL));
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
index 7dd1dc3f77c7..c9a1654d83a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
@@ -87,8 +87,8 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
 		drop_counter = mlx5_fc_create(esw->dev, false);
 		if (IS_ERR(drop_counter)) {
 			esw_warn(esw->dev,
-				 "vport[%d] configure egress drop rule counter err(%ld)\n",
-				 vport->vport, PTR_ERR(drop_counter));
+				 "vport[%d] configure egress drop rule counter err(%pe)\n",
+				 vport->vport, drop_counter);
 			drop_counter = NULL;
 		}
 		vport->egress.legacy.drop_counter = drop_counter;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
index d599e50af346..3ce455c2535c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
@@ -27,7 +27,7 @@ esw_acl_table_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport, int ns,
 	esw_debug(dev, "Create vport[%d] %s ACL table\n", vport_num,
 		  ns == MLX5_FLOW_NAMESPACE_ESW_INGRESS ? "ingress" : "egress");
 
-	root_ns = mlx5_get_flow_vport_acl_namespace(dev, ns, vport->index);
+	root_ns = mlx5_get_flow_vport_namespace(dev, ns, vport->index);
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get E-Switch root namespace for vport (%d)\n",
 			 vport_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/adj_vport.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/adj_vport.c
new file mode 100644
index 000000000000..250af09b5af2
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/adj_vport.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+#include "fs_core.h"
+#include "eswitch.h"
+
+int mlx5_esw_adj_vport_modify(struct mlx5_core_dev *dev, u16 vport,
+			      bool connect)
+{
+	u32 in[MLX5_ST_SZ_DW(modify_vport_state_in)] = {};
+
+	MLX5_SET(modify_vport_state_in, in, opcode,
+		 MLX5_CMD_OP_MODIFY_VPORT_STATE);
+	MLX5_SET(modify_vport_state_in, in, op_mod,
+		 MLX5_VPORT_STATE_OP_MOD_ESW_VPORT);
+	MLX5_SET(modify_vport_state_in, in, other_vport, 1);
+	MLX5_SET(modify_vport_state_in, in, vport_number, vport);
+	MLX5_SET(modify_vport_state_in, in, ingress_connect_valid, 1);
+	MLX5_SET(modify_vport_state_in, in, egress_connect_valid, 1);
+	MLX5_SET(modify_vport_state_in, in, ingress_connect, connect);
+	MLX5_SET(modify_vport_state_in, in, egress_connect, connect);
+	MLX5_SET(modify_vport_state_in, in, admin_state, connect);
+	return mlx5_cmd_exec_in(dev, modify_vport_state, in);
+}
+
+static void mlx5_esw_destroy_esw_vport(struct mlx5_core_dev *dev, u16 vport)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_esw_vport_in)] = {};
+
+	MLX5_SET(destroy_esw_vport_in, in, opcode,
+		 MLX5_CMD_OPCODE_DESTROY_ESW_VPORT);
+	MLX5_SET(destroy_esw_vport_in, in, vport_num, vport);
+
+	mlx5_cmd_exec_in(dev, destroy_esw_vport, in);
+}
+
+static int mlx5_esw_create_esw_vport(struct mlx5_core_dev *dev, u16 vhca_id,
+				     u16 *vport_num)
+{
+	u32 out[MLX5_ST_SZ_DW(create_esw_vport_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(create_esw_vport_in)] = {};
+	int err;
+
+	MLX5_SET(create_esw_vport_in, in, opcode,
+		 MLX5_CMD_OPCODE_CREATE_ESW_VPORT);
+	MLX5_SET(create_esw_vport_in, in, managed_vhca_id, vhca_id);
+
+	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	if (!err)
+		*vport_num = MLX5_GET(create_esw_vport_out, out, vport_num);
+
+	return err;
+}
+
+static int mlx5_esw_adj_vport_create(struct mlx5_eswitch *esw, u16 vhca_id,
+				     const void *rid_info_reg)
+{
+	struct mlx5_vport *vport;
+	u16 vport_num;
+	int err;
+
+	err = mlx5_esw_create_esw_vport(esw->dev, vhca_id, &vport_num);
+	if (err) {
+		esw_warn(esw->dev,
+			 "Failed to create adjacent vport for vhca_id %d, err %d\n",
+			 vhca_id, err);
+		return err;
+	}
+
+	esw_debug(esw->dev, "Created adjacent vport[%d] %d for vhca_id 0x%x\n",
+		  esw->last_vport_idx, vport_num, vhca_id);
+
+	err = mlx5_esw_vport_alloc(esw, esw->last_vport_idx++, vport_num);
+	if (err)
+		goto destroy_esw_vport;
+
+	xa_set_mark(&esw->vports, vport_num, MLX5_ESW_VPT_VF);
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	vport->adjacent = true;
+	vport->vhca_id = vhca_id;
+
+	vport->adj_info.parent_pci_devfn =
+		MLX5_GET(function_vhca_rid_info_reg, rid_info_reg,
+			 parent_pci_device_function);
+	vport->adj_info.function_id =
+		MLX5_GET(function_vhca_rid_info_reg, rid_info_reg, function_id);
+
+	mlx5_fs_vport_egress_acl_ns_add(esw->dev->priv.steering, vport->index);
+	mlx5_fs_vport_ingress_acl_ns_add(esw->dev->priv.steering, vport->index);
+	err = mlx5_esw_offloads_rep_add(esw, vport);
+	if (err)
+		goto acl_ns_remove;
+
+	return 0;
+
+acl_ns_remove:
+	mlx5_fs_vport_ingress_acl_ns_remove(esw->dev->priv.steering,
+					    vport->index);
+	mlx5_fs_vport_egress_acl_ns_remove(esw->dev->priv.steering,
+					   vport->index);
+	mlx5_esw_vport_free(esw, vport);
+destroy_esw_vport:
+	mlx5_esw_destroy_esw_vport(esw->dev, vport_num);
+	return err;
+}
+
+static void mlx5_esw_adj_vport_destroy(struct mlx5_eswitch *esw,
+				       struct mlx5_vport *vport)
+{
+	u16 vport_num = vport->vport;
+
+	esw_debug(esw->dev, "Destroying adjacent vport %d for vhca_id 0x%x\n",
+		  vport_num, vport->vhca_id);
+
+	mlx5_esw_offloads_rep_remove(esw, vport);
+	mlx5_fs_vport_egress_acl_ns_remove(esw->dev->priv.steering,
+					   vport->index);
+	mlx5_fs_vport_ingress_acl_ns_remove(esw->dev->priv.steering,
+					    vport->index);
+	mlx5_esw_vport_free(esw, vport);
+	/* Reset the vport index back so new adj vports can use this index.
+	 * When vport count can incrementally change, this needs to be modified.
+	 */
+	esw->last_vport_idx--;
+	mlx5_esw_destroy_esw_vport(esw->dev, vport_num);
+}
+
+void mlx5_esw_adjacent_vhcas_cleanup(struct mlx5_eswitch *esw)
+{
+	struct mlx5_vport *vport;
+	unsigned long i;
+
+	if (!MLX5_CAP_GEN_2(esw->dev, delegated_vhca_max))
+		return;
+
+	mlx5_esw_for_each_vf_vport(esw, i, vport, U16_MAX) {
+		if (!vport->adjacent)
+			continue;
+		mlx5_esw_adj_vport_destroy(esw, vport);
+	}
+}
+
+void mlx5_esw_adjacent_vhcas_setup(struct mlx5_eswitch *esw)
+{
+	u32 delegated_vhca_max = MLX5_CAP_GEN_2(esw->dev, delegated_vhca_max);
+	u32 in[MLX5_ST_SZ_DW(query_delegated_vhca_in)] = {};
+	int outlen, err, i = 0;
+	u8 *out;
+	u32 count;
+
+	if (!delegated_vhca_max)
+		return;
+
+	outlen = MLX5_ST_SZ_BYTES(query_delegated_vhca_out) +
+		 delegated_vhca_max *
+		 MLX5_ST_SZ_BYTES(delegated_function_vhca_rid_info);
+
+	esw_debug(esw->dev, "delegated_vhca_max=%d\n", delegated_vhca_max);
+
+	out = kvzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return;
+
+	MLX5_SET(query_delegated_vhca_in, in, opcode,
+		 MLX5_CMD_OPCODE_QUERY_DELEGATED_VHCA);
+
+	err = mlx5_cmd_exec(esw->dev, in, sizeof(in), out, outlen);
+	if (err) {
+		kvfree(out);
+		esw_warn(esw->dev, "Failed to query delegated vhca, err %d\n",
+			 err);
+		return;
+	}
+
+	count = MLX5_GET(query_delegated_vhca_out, out, functions_count);
+	esw_debug(esw->dev, "Delegated vhca functions count %d\n", count);
+
+	for (i = 0; i < count; i++) {
+		const void *rid_info, *rid_info_reg;
+		u16 vhca_id;
+
+		rid_info = MLX5_ADDR_OF(query_delegated_vhca_out, out,
+					delegated_function_vhca_rid_info[i]);
+
+		rid_info_reg = MLX5_ADDR_OF(delegated_function_vhca_rid_info,
+					    rid_info, function_vhca_rid_info);
+
+		vhca_id = MLX5_GET(function_vhca_rid_info_reg, rid_info_reg,
+				   vhca_id);
+		esw_debug(esw->dev, "Delegating vhca_id 0x%x\n", vhca_id);
+
+		err = mlx5_esw_adj_vport_create(esw, vhca_id, rid_info_reg);
+		if (err) {
+			esw_warn(esw->dev,
+				 "Failed to init adjacent vhca 0x%x, err %d\n",
+				 vhca_id, err);
+			break;
+		}
+	}
+
+	kvfree(out);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
index 5f647358a05c..60e10047770f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -81,7 +81,8 @@ mlx5_esw_bridge_table_create(int max_fte, u32 level, struct mlx5_eswitch *esw)
 	ft_attr.prio = FDB_BR_OFFLOAD;
 	fdb = mlx5_create_flow_table(ns, &ft_attr);
 	if (IS_ERR(fdb))
-		esw_warn(dev, "Failed to create bridge FDB Table (err=%ld)\n", PTR_ERR(fdb));
+		esw_warn(dev, "Failed to create bridge FDB Table (err=%pe)\n",
+			 fdb);
 
 	return fdb;
 }
@@ -121,8 +122,8 @@ mlx5_esw_bridge_ingress_vlan_proto_fg_create(unsigned int from, unsigned int to,
 	kvfree(in);
 	if (IS_ERR(fg))
 		esw_warn(esw->dev,
-			 "Failed to create VLAN(proto=%x) flow group for bridge ingress table (err=%ld)\n",
-			 vlan_proto, PTR_ERR(fg));
+			 "Failed to create VLAN(proto=%x) flow group for bridge ingress table (err=%pe)\n",
+			 vlan_proto, fg);
 
 	return fg;
 }
@@ -180,8 +181,8 @@ mlx5_esw_bridge_ingress_vlan_proto_filter_fg_create(unsigned int from, unsigned
 	fg = mlx5_create_flow_group(ingress_ft, in);
 	if (IS_ERR(fg))
 		esw_warn(esw->dev,
-			 "Failed to create bridge ingress table VLAN filter flow group (err=%ld)\n",
-			 PTR_ERR(fg));
+			 "Failed to create bridge ingress table VLAN filter flow group (err=%pe)\n",
+			 fg);
 	kvfree(in);
 	return fg;
 }
@@ -237,8 +238,8 @@ mlx5_esw_bridge_ingress_mac_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow
 	fg = mlx5_create_flow_group(ingress_ft, in);
 	if (IS_ERR(fg))
 		esw_warn(esw->dev,
-			 "Failed to create MAC flow group for bridge ingress table (err=%ld)\n",
-			 PTR_ERR(fg));
+			 "Failed to create MAC flow group for bridge ingress table (err=%pe)\n",
+			 fg);
 
 	kvfree(in);
 	return fg;
@@ -274,8 +275,8 @@ mlx5_esw_bridge_egress_vlan_proto_fg_create(unsigned int from, unsigned int to,
 	fg = mlx5_create_flow_group(egress_ft, in);
 	if (IS_ERR(fg))
 		esw_warn(esw->dev,
-			 "Failed to create VLAN flow group for bridge egress table (err=%ld)\n",
-			 PTR_ERR(fg));
+			 "Failed to create VLAN flow group for bridge egress table (err=%pe)\n",
+			 fg);
 	kvfree(in);
 	return fg;
 }
@@ -324,8 +325,8 @@ mlx5_esw_bridge_egress_mac_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_
 	fg = mlx5_create_flow_group(egress_ft, in);
 	if (IS_ERR(fg))
 		esw_warn(esw->dev,
-			 "Failed to create bridge egress table MAC flow group (err=%ld)\n",
-			 PTR_ERR(fg));
+			 "Failed to create bridge egress table MAC flow group (err=%pe)\n",
+			 fg);
 	kvfree(in);
 	return fg;
 }
@@ -354,8 +355,8 @@ mlx5_esw_bridge_egress_miss_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow
 	fg = mlx5_create_flow_group(egress_ft, in);
 	if (IS_ERR(fg))
 		esw_warn(esw->dev,
-			 "Failed to create bridge egress table miss flow group (err=%ld)\n",
-			 PTR_ERR(fg));
+			 "Failed to create bridge egress table miss flow group (err=%pe)\n",
+			 fg);
 	kvfree(in);
 	return fg;
 }
@@ -501,8 +502,8 @@ mlx5_esw_bridge_egress_table_init(struct mlx5_esw_bridge_offloads *br_offloads,
 	if (mlx5_esw_bridge_pkt_reformat_vlan_pop_supported(esw)) {
 		miss_fg = mlx5_esw_bridge_egress_miss_fg_create(esw, egress_ft);
 		if (IS_ERR(miss_fg)) {
-			esw_warn(esw->dev, "Failed to create miss flow group (err=%ld)\n",
-				 PTR_ERR(miss_fg));
+			esw_warn(esw->dev, "Failed to create miss flow group (err=%pe)\n",
+				 miss_fg);
 			miss_fg = NULL;
 			goto skip_miss_flow;
 		}
@@ -510,8 +511,8 @@ mlx5_esw_bridge_egress_table_init(struct mlx5_esw_bridge_offloads *br_offloads,
 		miss_pkt_reformat = mlx5_esw_bridge_pkt_reformat_vlan_pop_create(esw);
 		if (IS_ERR(miss_pkt_reformat)) {
 			esw_warn(esw->dev,
-				 "Failed to alloc packet reformat REMOVE_HEADER (err=%ld)\n",
-				 PTR_ERR(miss_pkt_reformat));
+				 "Failed to alloc packet reformat REMOVE_HEADER (err=%pe)\n",
+				 miss_pkt_reformat);
 			miss_pkt_reformat = NULL;
 			mlx5_destroy_flow_group(miss_fg);
 			miss_fg = NULL;
@@ -522,8 +523,8 @@ mlx5_esw_bridge_egress_table_init(struct mlx5_esw_bridge_offloads *br_offloads,
 								      br_offloads->skip_ft,
 								      miss_pkt_reformat);
 		if (IS_ERR(miss_handle)) {
-			esw_warn(esw->dev, "Failed to create miss flow (err=%ld)\n",
-				 PTR_ERR(miss_handle));
+			esw_warn(esw->dev, "Failed to create miss flow (err=%pe)\n",
+				 miss_handle);
 			miss_handle = NULL;
 			mlx5_packet_reformat_dealloc(esw->dev, miss_pkt_reformat);
 			miss_pkt_reformat = NULL;
@@ -1048,8 +1049,8 @@ mlx5_esw_bridge_vlan_push_create(u16 vlan_proto, struct mlx5_esw_bridge_vlan *vl
 						  &reformat_params,
 						  MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(pkt_reformat)) {
-		esw_warn(esw->dev, "Failed to alloc packet reformat INSERT_HEADER (err=%ld)\n",
-			 PTR_ERR(pkt_reformat));
+		esw_warn(esw->dev, "Failed to alloc packet reformat INSERT_HEADER (err=%pe)\n",
+			 pkt_reformat);
 		return PTR_ERR(pkt_reformat);
 	}
 
@@ -1076,8 +1077,8 @@ mlx5_esw_bridge_vlan_pop_create(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_e
 
 	pkt_reformat = mlx5_esw_bridge_pkt_reformat_vlan_pop_create(esw);
 	if (IS_ERR(pkt_reformat)) {
-		esw_warn(esw->dev, "Failed to alloc packet reformat REMOVE_HEADER (err=%ld)\n",
-			 PTR_ERR(pkt_reformat));
+		esw_warn(esw->dev, "Failed to alloc packet reformat REMOVE_HEADER (err=%pe)\n",
+			 pkt_reformat);
 		return PTR_ERR(pkt_reformat);
 	}
 
@@ -1863,7 +1864,7 @@ int mlx5_esw_bridge_port_mdb_add(struct net_device *dev, u16 vport_num, u16 esw_
 			 "Failed to lookup bridge port to add MDB (MAC=%pM,vport=%u)\n",
 			 addr, vport_num);
 		NL_SET_ERR_MSG_FMT_MOD(extack,
-				       "Failed to lookup bridge port to add MDB (MAC=%pM,vport=%u)\n",
+				       "Failed to lookup bridge port to add MDB (MAC=%pM,vport=%u)",
 				       addr, vport_num);
 		return -EINVAL;
 	}
@@ -1876,7 +1877,7 @@ int mlx5_esw_bridge_port_mdb_add(struct net_device *dev, u16 vport_num, u16 esw_
 				 "Failed to lookup bridge port vlan metadata to create MDB (MAC=%pM,vid=%u,vport=%u)\n",
 				 addr, vid, vport_num);
 			NL_SET_ERR_MSG_FMT_MOD(extack,
-					       "Failed to lookup vlan metadata for MDB (MAC=%pM,vid=%u,vport=%u)\n",
+					       "Failed to lookup vlan metadata for MDB (MAC=%pM,vid=%u,vport=%u)",
 					       addr, vid, vport_num);
 			return -EINVAL;
 		}
@@ -1884,7 +1885,7 @@ int mlx5_esw_bridge_port_mdb_add(struct net_device *dev, u16 vport_num, u16 esw_
 
 	err = mlx5_esw_bridge_port_mdb_attach(dev, port, addr, vid);
 	if (err) {
-		NL_SET_ERR_MSG_FMT_MOD(extack, "Failed to add MDB (MAC=%pM,vid=%u,vport=%u)\n",
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Failed to add MDB (MAC=%pM,vid=%u,vport=%u)",
 				       addr, vid, vport_num);
 		return err;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 982fe3714683..89a58dee50b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -7,11 +7,7 @@
 static void
 mlx5_esw_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_item_id *ppid)
 {
-	u64 parent_id;
-
-	parent_id = mlx5_query_nic_system_image_guid(dev);
-	ppid->id_len = sizeof(parent_id);
-	memcpy(ppid->id, &parent_id, sizeof(parent_id));
+	mlx5_query_nic_sw_system_image_guid(dev, ppid->id, &ppid->id_len);
 }
 
 static bool mlx5_esw_devlink_port_supported(struct mlx5_eswitch *esw, u16 vport_num)
@@ -27,12 +23,13 @@ static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *
 {
 	struct mlx5_core_dev *dev = esw->dev;
 	struct netdev_phys_item_id ppid = {};
+	struct mlx5_vport *vport;
 	u32 controller_num = 0;
 	bool external;
 	u16 pfnum;
 
 	mlx5_esw_get_port_parent_id(dev, &ppid);
-	pfnum = mlx5_get_dev_index(dev);
+	pfnum = PCI_FUNC(dev->pdev->devfn);
 	external = mlx5_core_is_ecpf_esw_manager(dev);
 	if (external)
 		controller_num = dev->priv.eswitch->offloads.host_number + 1;
@@ -42,15 +39,25 @@ static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *
 		dl_port->attrs.switch_id.id_len = ppid.id_len;
 		devlink_port_attrs_pci_pf_set(dl_port, controller_num, pfnum, external);
 	} else if (mlx5_eswitch_is_vf_vport(esw, vport_num)) {
+		u16 func_id = vport_num - 1;
+
+		vport = mlx5_eswitch_get_vport(esw, vport_num);
 		memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len);
 		dl_port->attrs.switch_id.id_len = ppid.id_len;
+		if (vport->adjacent) {
+			func_id = vport->adj_info.function_id;
+			pfnum = vport->adj_info.parent_pci_devfn;
+		}
+
 		devlink_port_attrs_pci_vf_set(dl_port, controller_num, pfnum,
-					      vport_num - 1, external);
+					      func_id, external);
 	}  else if (mlx5_core_is_ec_vf_vport(esw->dev, vport_num)) {
+		u16 base_vport = mlx5_core_ec_vf_vport_base(dev);
+
 		memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len);
 		dl_port->attrs.switch_id.id_len = ppid.id_len;
 		devlink_port_attrs_pci_vf_set(dl_port, 0, pfnum,
-					      vport_num - 1, false);
+					      vport_num - base_vport, false);
 	}
 }
 
@@ -110,7 +117,7 @@ static void mlx5_esw_offloads_sf_devlink_port_attrs_set(struct mlx5_eswitch *esw
 	struct netdev_phys_item_id ppid = {};
 	u16 pfnum;
 
-	pfnum = mlx5_get_dev_index(dev);
+	pfnum = PCI_FUNC(dev->pdev->devfn);
 	mlx5_esw_get_port_parent_id(dev, &ppid);
 	memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len);
 	dl_port->attrs.switch_id.id_len = ppid.id_len;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 5a0047bdcb51..3cfe743610d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -10,9 +10,9 @@
 #endif
 
 enum {
-	MLX5_ESW_IPSEC_RX_POL_FT_LEVEL,
 	MLX5_ESW_IPSEC_RX_ESP_FT_LEVEL,
 	MLX5_ESW_IPSEC_RX_ESP_FT_CHK_LEVEL,
+	MLX5_ESW_IPSEC_RX_POL_FT_LEVEL,
 };
 
 enum {
@@ -85,6 +85,19 @@ err_header_alloc:
 	return err;
 }
 
+void mlx5_esw_ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_spec *spec)
+{
+	MLX5_SET(fte_match_param, spec->match_criteria,
+		 misc_parameters_2.metadata_reg_c_1,
+		 ESW_IPSEC_RX_MAPPED_ID_MATCH_MASK);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.metadata_reg_c_1,
+		 sa_entry->rx_mapped_id << ESW_ZONE_ID_BITS);
+
+	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+}
+
 void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry)
 {
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
@@ -150,11 +163,11 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev)
 	unsigned long i;
 	int err;
 
-	xa_for_each(&esw->offloads.vport_reps, i, rep) {
-		rpriv = rep->rep_data[REP_ETH].priv;
-		if (!rpriv || !rpriv->netdev)
+	mlx5_esw_for_each_rep(esw, i, rep) {
+		if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED)
 			continue;
 
+		rpriv = rep->rep_data[REP_ETH].priv;
 		rhashtable_walk_enter(&rpriv->tc_ht, &iter);
 		rhashtable_walk_start(&iter);
 		while ((flow = rhashtable_walk_next(&iter)) != NULL) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
index ac9c65b89166..514c15258b1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
@@ -20,6 +20,8 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_tx_create_attr *attr);
 void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev);
+void mlx5_esw_ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_spec *spec);
 #else
 static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 						     struct mlx5e_ipsec_rx_create_attr *attr) {}
@@ -48,5 +50,8 @@ static inline void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 						     struct mlx5e_ipsec_tx_create_attr *attr) {}
 
 static inline void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) {}
+static inline void
+mlx5_esw_ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+				     struct mlx5_flow_spec *spec) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif /* __MLX5_ESW_IPSEC_FS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
index 45183de424f3..929adeb50a98 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
@@ -66,7 +66,6 @@ static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw)
 	esw->fdb_table.legacy.addr_grp = NULL;
 	esw->fdb_table.legacy.allmulti_grp = NULL;
 	esw->fdb_table.legacy.promisc_grp = NULL;
-	atomic64_set(&esw->user_count, 0);
 }
 
 static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
@@ -96,7 +95,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 	if (!flow_group_in)
 		return -ENOMEM;
 
-	ft_attr.max_fte = POOL_NEXT_SIZE;
+	ft_attr.max_fte = MLX5_FS_MAX_POOL_SIZE;
 	ft_attr.prio = LEGACY_FDB_PRIO;
 	fdb = mlx5_create_flow_table(root_ns, &ft_attr);
 	if (IS_ERR(fdb)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 8b7c843446e1..4278bcb04c72 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -64,11 +64,19 @@ static void esw_qos_domain_release(struct mlx5_eswitch *esw)
 enum sched_node_type {
 	SCHED_NODE_TYPE_VPORTS_TSAR,
 	SCHED_NODE_TYPE_VPORT,
+	SCHED_NODE_TYPE_TC_ARBITER_TSAR,
+	SCHED_NODE_TYPE_RATE_LIMITER,
+	SCHED_NODE_TYPE_VPORT_TC,
+	SCHED_NODE_TYPE_VPORTS_TC_TSAR,
 };
 
 static const char * const sched_node_type_str[] = {
 	[SCHED_NODE_TYPE_VPORTS_TSAR] = "vports TSAR",
 	[SCHED_NODE_TYPE_VPORT] = "vport",
+	[SCHED_NODE_TYPE_TC_ARBITER_TSAR] = "TC Arbiter TSAR",
+	[SCHED_NODE_TYPE_RATE_LIMITER] = "Rate Limiter",
+	[SCHED_NODE_TYPE_VPORT_TC] = "vport TC",
+	[SCHED_NODE_TYPE_VPORTS_TC_TSAR] = "vports TC TSAR",
 };
 
 struct mlx5_esw_sched_node {
@@ -90,19 +98,75 @@ struct mlx5_esw_sched_node {
 	struct list_head children;
 	/* Valid only if this node is associated with a vport. */
 	struct mlx5_vport *vport;
+	/* Level in the hierarchy. The root node level is 1. */
+	u8 level;
+	/* Valid only when this node represents a traffic class. */
+	u8 tc;
+	/* Valid only for a TC arbiter node or vport TC arbiter. */
+	u32 tc_bw[DEVLINK_RATE_TCS_MAX];
 };
 
+static void esw_qos_node_attach_to_parent(struct mlx5_esw_sched_node *node)
+{
+	if (!node->parent) {
+		/* Root children are assigned a depth level of 2. */
+		node->level = 2;
+		list_add_tail(&node->entry, &node->esw->qos.domain->nodes);
+	} else {
+		node->level = node->parent->level + 1;
+		list_add_tail(&node->entry, &node->parent->children);
+	}
+}
+
+static int esw_qos_num_tcs(struct mlx5_core_dev *dev)
+{
+	int num_tcs = mlx5_max_tc(dev) + 1;
+
+	return num_tcs < DEVLINK_RATE_TCS_MAX ? num_tcs : DEVLINK_RATE_TCS_MAX;
+}
+
 static void
 esw_qos_node_set_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_node *parent)
 {
 	list_del_init(&node->entry);
 	node->parent = parent;
-	list_add_tail(&node->entry, &parent->children);
-	node->esw = parent->esw;
+	if (parent)
+		node->esw = parent->esw;
+	esw_qos_node_attach_to_parent(node);
+}
+
+static void esw_qos_nodes_set_parent(struct list_head *nodes,
+				     struct mlx5_esw_sched_node *parent)
+{
+	struct mlx5_esw_sched_node *node, *tmp;
+
+	list_for_each_entry_safe(node, tmp, nodes, entry) {
+		esw_qos_node_set_parent(node, parent);
+		if (!list_empty(&node->children) &&
+		    parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) {
+			struct mlx5_esw_sched_node *child;
+
+			list_for_each_entry(child, &node->children, entry) {
+				struct mlx5_vport *vport = child->vport;
+
+				if (vport)
+					vport->qos.sched_node->parent = parent;
+			}
+		}
+	}
 }
 
 void mlx5_esw_qos_vport_qos_free(struct mlx5_vport *vport)
 {
+	if (vport->qos.sched_nodes) {
+		int num_tcs = esw_qos_num_tcs(vport->qos.sched_node->esw->dev);
+		int i;
+
+		for (i = 0; i < num_tcs; i++)
+			kfree(vport->qos.sched_nodes[i]);
+		kfree(vport->qos.sched_nodes);
+	}
+
 	kfree(vport->qos.sched_node);
 	memset(&vport->qos, 0, sizeof(vport->qos));
 }
@@ -126,16 +190,37 @@ mlx5_esw_qos_vport_get_parent(const struct mlx5_vport *vport)
 
 static void esw_qos_sched_elem_warn(struct mlx5_esw_sched_node *node, int err, const char *op)
 {
-	if (node->vport) {
+	switch (node->type) {
+	case SCHED_NODE_TYPE_VPORTS_TC_TSAR:
+		esw_warn(node->esw->dev,
+			 "E-Switch %s %s scheduling element failed (tc=%d,err=%d)\n",
+			 op, sched_node_type_str[node->type], node->tc, err);
+		break;
+	case SCHED_NODE_TYPE_VPORT_TC:
+		esw_warn(node->esw->dev,
+			 "E-Switch %s %s scheduling element failed (vport=%d,tc=%d,err=%d)\n",
+			 op,
+			 sched_node_type_str[node->type],
+			 node->vport->vport, node->tc, err);
+		break;
+	case SCHED_NODE_TYPE_VPORT:
 		esw_warn(node->esw->dev,
 			 "E-Switch %s %s scheduling element failed (vport=%d,err=%d)\n",
 			 op, sched_node_type_str[node->type], node->vport->vport, err);
-		return;
+		break;
+	case SCHED_NODE_TYPE_RATE_LIMITER:
+	case SCHED_NODE_TYPE_TC_ARBITER_TSAR:
+	case SCHED_NODE_TYPE_VPORTS_TSAR:
+		esw_warn(node->esw->dev,
+			 "E-Switch %s %s scheduling element failed (err=%d)\n",
+			 op, sched_node_type_str[node->type], err);
+		break;
+	default:
+		esw_warn(node->esw->dev,
+			 "E-Switch %s scheduling element failed (err=%d)\n",
+			 op, err);
+		break;
 	}
-
-	esw_warn(node->esw->dev,
-		 "E-Switch %s %s scheduling element failed (err=%d)\n",
-		 op, sched_node_type_str[node->type], err);
 }
 
 static int esw_qos_node_create_sched_element(struct mlx5_esw_sched_node *node, void *ctx,
@@ -218,6 +303,24 @@ static int esw_qos_sched_elem_config(struct mlx5_esw_sched_node *node, u32 max_r
 	return 0;
 }
 
+static int esw_qos_create_rate_limit_element(struct mlx5_esw_sched_node *node,
+					     struct netlink_ext_ack *extack)
+{
+	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+
+	if (!mlx5_qos_element_type_supported(
+		node->esw->dev,
+		SCHEDULING_CONTEXT_ELEMENT_TYPE_RATE_LIMIT,
+		SCHEDULING_HIERARCHY_E_SWITCH))
+		return -EOPNOTSUPP;
+
+	MLX5_SET(scheduling_context, sched_ctx, max_average_bw, node->max_rate);
+	MLX5_SET(scheduling_context, sched_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_RATE_LIMIT);
+
+	return esw_qos_node_create_sched_element(node, sched_ctx, extack);
+}
+
 static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw,
 					      struct mlx5_esw_sched_node *parent)
 {
@@ -238,24 +341,19 @@ static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw,
 	if (max_guarantee)
 		return max_t(u32, max_guarantee / fw_max_bw_share, 1);
 
-	/* If nodes max min_rate divider is 0 but their parent has bw_share
-	 * configured, then set bw_share for nodes to minimal value.
-	 */
-
-	if (parent && parent->bw_share)
-		return 1;
-
 	/* If the node nodes has min_rate configured, a divider of 0 sets all
 	 * nodes' bw_share to 0, effectively disabling min guarantees.
 	 */
 	return 0;
 }
 
-static u32 esw_qos_calc_bw_share(u32 min_rate, u32 divider, u32 fw_max)
+static u32 esw_qos_calc_bw_share(u32 value, u32 divider, u32 fw_max)
 {
 	if (!divider)
 		return 0;
-	return min_t(u32, max_t(u32, DIV_ROUND_UP(min_rate, divider), MLX5_MIN_BW_SHARE), fw_max);
+	return min_t(u32, fw_max,
+		     max_t(u32,
+			   DIV_ROUND_UP(value, divider), MLX5_MIN_BW_SHARE));
 }
 
 static void esw_qos_update_sched_node_bw_share(struct mlx5_esw_sched_node *node,
@@ -282,7 +380,13 @@ static void esw_qos_normalize_min_rate(struct mlx5_eswitch *esw,
 		if (node->esw != esw || node->ix == esw->qos.root_tsar_ix)
 			continue;
 
-		esw_qos_update_sched_node_bw_share(node, divider, extack);
+		/* Vports TC TSARs don't have a minimum rate configured,
+		 * so there's no need to update the bw_share on them.
+		 */
+		if (node->type != SCHED_NODE_TYPE_VPORTS_TC_TSAR) {
+			esw_qos_update_sched_node_bw_share(node, divider,
+							   extack);
+		}
 
 		if (list_empty(&node->children))
 			continue;
@@ -291,6 +395,20 @@ static void esw_qos_normalize_min_rate(struct mlx5_eswitch *esw,
 	}
 }
 
+static u32 esw_qos_calculate_tc_bw_divider(u32 *tc_bw)
+{
+	u32 total = 0;
+	int i;
+
+	for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++)
+		total += tc_bw[i];
+
+	/* If total is zero, tc-bw config is disabled and we shouldn't reach
+	 * here.
+	 */
+	return WARN_ON(!total) ? 1 : total;
+}
+
 static int esw_qos_set_node_min_rate(struct mlx5_esw_sched_node *node,
 				     u32 min_rate, struct netlink_ext_ack *extack)
 {
@@ -305,8 +423,9 @@ static int esw_qos_set_node_min_rate(struct mlx5_esw_sched_node *node,
 	return 0;
 }
 
-static int esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_element_id,
-					  u32 *tsar_ix)
+static int
+esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_element_id,
+			       u32 max_rate, u32 bw_share, u32 *tsar_ix)
 {
 	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
 	void *attr;
@@ -323,6 +442,8 @@ static int esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_
 		 SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
 	MLX5_SET(scheduling_context, tsar_ctx, parent_element_id,
 		 parent_element_id);
+	MLX5_SET(scheduling_context, tsar_ctx, max_average_bw, max_rate);
+	MLX5_SET(scheduling_context, tsar_ctx, bw_share, bw_share);
 	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
 	MLX5_SET(tsar_element, attr, tsar_type, TSAR_ELEMENT_TSAR_TYPE_DWRR);
 
@@ -332,33 +453,69 @@ static int esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_
 						  tsar_ix);
 }
 
-static int esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node,
-					      struct netlink_ext_ack *extack)
+static int
+esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node,
+				   struct netlink_ext_ack *extack)
 {
+	struct mlx5_esw_sched_node *parent = vport_node->parent;
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
 	struct mlx5_core_dev *dev = vport_node->esw->dev;
 	void *attr;
 
-	if (!mlx5_qos_element_type_supported(dev,
-					     SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT,
-					     SCHEDULING_HIERARCHY_E_SWITCH))
+	if (!mlx5_qos_element_type_supported(
+		dev,
+		SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT,
+		SCHEDULING_HIERARCHY_E_SWITCH))
 		return -EOPNOTSUPP;
 
 	MLX5_SET(scheduling_context, sched_ctx, element_type,
 		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
 	attr = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes);
 	MLX5_SET(vport_element, attr, vport_number, vport_node->vport->vport);
-	MLX5_SET(scheduling_context, sched_ctx, parent_element_id, vport_node->parent->ix);
-	MLX5_SET(scheduling_context, sched_ctx, max_average_bw, vport_node->max_rate);
+	MLX5_SET(scheduling_context, sched_ctx, parent_element_id,
+		 parent ? parent->ix : vport_node->esw->qos.root_tsar_ix);
+	MLX5_SET(scheduling_context, sched_ctx, max_average_bw,
+		 vport_node->max_rate);
 
 	return esw_qos_node_create_sched_element(vport_node, sched_ctx, extack);
 }
 
+static int
+esw_qos_vport_tc_create_sched_element(struct mlx5_esw_sched_node *vport_tc_node,
+				      u32 rate_limit_elem_ix,
+				      struct netlink_ext_ack *extack)
+{
+	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_core_dev *dev = vport_tc_node->esw->dev;
+	void *attr;
+
+	if (!mlx5_qos_element_type_supported(
+		dev,
+		SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC,
+		SCHEDULING_HIERARCHY_E_SWITCH))
+		return -EOPNOTSUPP;
+
+	MLX5_SET(scheduling_context, sched_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC);
+	attr = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes);
+	MLX5_SET(vport_tc_element, attr, vport_number,
+		 vport_tc_node->vport->vport);
+	MLX5_SET(vport_tc_element, attr, traffic_class, vport_tc_node->tc);
+	MLX5_SET(scheduling_context, sched_ctx, max_bw_obj_id,
+		 rate_limit_elem_ix);
+	MLX5_SET(scheduling_context, sched_ctx, parent_element_id,
+		 vport_tc_node->parent->ix);
+	MLX5_SET(scheduling_context, sched_ctx, bw_share,
+		 vport_tc_node->bw_share);
+
+	return esw_qos_node_create_sched_element(vport_tc_node, sched_ctx,
+						 extack);
+}
+
 static struct mlx5_esw_sched_node *
 __esw_qos_alloc_node(struct mlx5_eswitch *esw, u32 tsar_ix, enum sched_node_type type,
 		     struct mlx5_esw_sched_node *parent)
 {
-	struct list_head *parent_children;
 	struct mlx5_esw_sched_node *node;
 
 	node = kzalloc(sizeof(*node), GFP_KERNEL);
@@ -370,8 +527,15 @@ __esw_qos_alloc_node(struct mlx5_eswitch *esw, u32 tsar_ix, enum sched_node_type
 	node->type = type;
 	node->parent = parent;
 	INIT_LIST_HEAD(&node->children);
-	parent_children = parent ? &parent->children : &esw->qos.domain->nodes;
-	list_add_tail(&node->entry, parent_children);
+	esw_qos_node_attach_to_parent(node);
+	if (!parent) {
+		/* The caller is responsible for inserting the node into the
+		 * parent list if necessary. This function can also be used with
+		 * a NULL parent, which doesn't necessarily indicate that it
+		 * refers to the root scheduling element.
+		 */
+		list_del_init(&node->entry);
+	}
 
 	return node;
 }
@@ -388,6 +552,147 @@ static void esw_qos_destroy_node(struct mlx5_esw_sched_node *node, struct netlin
 	__esw_qos_free_node(node);
 }
 
+static int esw_qos_create_vports_tc_node(struct mlx5_esw_sched_node *parent,
+					 u8 tc, struct netlink_ext_ack *extack)
+{
+	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_core_dev *dev = parent->esw->dev;
+	struct mlx5_esw_sched_node *vports_tc_node;
+	void *attr;
+	int err;
+
+	if (!mlx5_qos_element_type_supported(
+		dev,
+		SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR,
+		SCHEDULING_HIERARCHY_E_SWITCH) ||
+	    !mlx5_qos_tsar_type_supported(dev,
+					  TSAR_ELEMENT_TSAR_TYPE_DWRR,
+					  SCHEDULING_HIERARCHY_E_SWITCH))
+		return -EOPNOTSUPP;
+
+	vports_tc_node = __esw_qos_alloc_node(parent->esw, 0,
+					      SCHED_NODE_TYPE_VPORTS_TC_TSAR,
+					      parent);
+	if (!vports_tc_node) {
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch alloc node failed");
+		esw_warn(dev, "Failed to alloc vports TC node (tc=%d)\n", tc);
+		return -ENOMEM;
+	}
+
+	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
+	MLX5_SET(tsar_element, attr, tsar_type, TSAR_ELEMENT_TSAR_TYPE_DWRR);
+	MLX5_SET(tsar_element, attr, traffic_class, tc);
+	MLX5_SET(scheduling_context, tsar_ctx, parent_element_id, parent->ix);
+	MLX5_SET(scheduling_context, tsar_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
+
+	err = esw_qos_node_create_sched_element(vports_tc_node, tsar_ctx,
+						extack);
+	if (err)
+		goto err_create_sched_element;
+
+	vports_tc_node->tc = tc;
+
+	return 0;
+
+err_create_sched_element:
+	__esw_qos_free_node(vports_tc_node);
+	return err;
+}
+
+static void
+esw_qos_tc_arbiter_get_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node,
+				 u32 *tc_bw)
+{
+	memcpy(tc_bw, tc_arbiter_node->tc_bw, sizeof(tc_arbiter_node->tc_bw));
+}
+
+static void
+esw_qos_set_tc_arbiter_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node,
+				 u32 *tc_bw, struct netlink_ext_ack *extack)
+{
+	struct mlx5_eswitch *esw = tc_arbiter_node->esw;
+	struct mlx5_esw_sched_node *vports_tc_node;
+	u32 divider, fw_max_bw_share;
+
+	fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	divider = esw_qos_calculate_tc_bw_divider(tc_bw);
+	list_for_each_entry(vports_tc_node, &tc_arbiter_node->children, entry) {
+		u8 tc = vports_tc_node->tc;
+		u32 bw_share;
+
+		tc_arbiter_node->tc_bw[tc] = tc_bw[tc];
+		bw_share = tc_bw[tc] * fw_max_bw_share;
+		bw_share = esw_qos_calc_bw_share(bw_share, divider,
+						 fw_max_bw_share);
+		esw_qos_sched_elem_config(vports_tc_node, 0, bw_share, extack);
+	}
+}
+
+static void
+esw_qos_destroy_vports_tc_nodes(struct mlx5_esw_sched_node *tc_arbiter_node,
+				struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *vports_tc_node, *tmp;
+
+	list_for_each_entry_safe(vports_tc_node, tmp,
+				 &tc_arbiter_node->children, entry)
+		esw_qos_destroy_node(vports_tc_node, extack);
+}
+
+static int
+esw_qos_create_vports_tc_nodes(struct mlx5_esw_sched_node *tc_arbiter_node,
+			       struct netlink_ext_ack *extack)
+{
+	struct mlx5_eswitch *esw = tc_arbiter_node->esw;
+	int err, i, num_tcs = esw_qos_num_tcs(esw->dev);
+
+	for (i = 0; i < num_tcs; i++) {
+		err = esw_qos_create_vports_tc_node(tc_arbiter_node, i, extack);
+		if (err)
+			goto err_tc_node_create;
+	}
+
+	return 0;
+
+err_tc_node_create:
+	esw_qos_destroy_vports_tc_nodes(tc_arbiter_node, NULL);
+	return err;
+}
+
+static int esw_qos_create_tc_arbiter_sched_elem(
+		struct mlx5_esw_sched_node *tc_arbiter_node,
+		struct netlink_ext_ack *extack)
+{
+	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	u32 tsar_parent_ix;
+	void *attr;
+
+	if (!mlx5_qos_tsar_type_supported(tc_arbiter_node->esw->dev,
+					  TSAR_ELEMENT_TSAR_TYPE_TC_ARB,
+					  SCHEDULING_HIERARCHY_E_SWITCH)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "E-Switch TC Arbiter scheduling element is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
+	MLX5_SET(tsar_element, attr, tsar_type, TSAR_ELEMENT_TSAR_TYPE_TC_ARB);
+	tsar_parent_ix = tc_arbiter_node->parent ? tc_arbiter_node->parent->ix :
+			 tc_arbiter_node->esw->qos.root_tsar_ix;
+	MLX5_SET(scheduling_context, tsar_ctx, parent_element_id,
+		 tsar_parent_ix);
+	MLX5_SET(scheduling_context, tsar_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
+	MLX5_SET(scheduling_context, tsar_ctx, max_average_bw,
+		 tc_arbiter_node->max_rate);
+	MLX5_SET(scheduling_context, tsar_ctx, bw_share,
+		 tc_arbiter_node->bw_share);
+
+	return esw_qos_node_create_sched_element(tc_arbiter_node, tsar_ctx,
+						 extack);
+}
+
 static struct mlx5_esw_sched_node *
 __esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct mlx5_esw_sched_node *parent,
 				   struct netlink_ext_ack *extack)
@@ -396,7 +701,8 @@ __esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct mlx5_esw_sch
 	u32 tsar_ix;
 	int err;
 
-	err = esw_qos_create_node_sched_elem(esw->dev, esw->qos.root_tsar_ix, &tsar_ix);
+	err = esw_qos_create_node_sched_elem(esw->dev, esw->qos.root_tsar_ix, 0,
+					     0, &tsar_ix);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "E-Switch create TSAR for node failed");
 		return ERR_PTR(err);
@@ -409,6 +715,7 @@ __esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct mlx5_esw_sch
 		goto err_alloc_node;
 	}
 
+	list_add_tail(&node->entry, &esw->qos.domain->nodes);
 	esw_qos_normalize_min_rate(esw, NULL, extack);
 	trace_mlx5_esw_node_qos_create(esw->dev, node, node->ix);
 
@@ -450,6 +757,9 @@ static void __esw_qos_destroy_node(struct mlx5_esw_sched_node *node, struct netl
 {
 	struct mlx5_eswitch *esw = node->esw;
 
+	if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+		esw_qos_destroy_vports_tc_nodes(node, extack);
+
 	trace_mlx5_esw_node_qos_destroy(esw->dev, node, node->ix);
 	esw_qos_destroy_node(node, extack);
 	esw_qos_normalize_min_rate(esw, NULL, extack);
@@ -463,51 +773,22 @@ static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta
 	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
 		return -EOPNOTSUPP;
 
-	err = esw_qos_create_node_sched_elem(esw->dev, 0, &esw->qos.root_tsar_ix);
+	err = esw_qos_create_node_sched_elem(esw->dev, 0, 0, 0,
+					     &esw->qos.root_tsar_ix);
 	if (err) {
 		esw_warn(dev, "E-Switch create root TSAR failed (%d)\n", err);
 		return err;
 	}
 
-	if (MLX5_CAP_QOS(dev, log_esw_max_sched_depth)) {
-		esw->qos.node0 = __esw_qos_create_vports_sched_node(esw, NULL, extack);
-	} else {
-		/* The eswitch doesn't support scheduling nodes.
-		 * Create a software-only node0 using the root TSAR to attach vport QoS to.
-		 */
-		if (!__esw_qos_alloc_node(esw,
-					  esw->qos.root_tsar_ix,
-					  SCHED_NODE_TYPE_VPORTS_TSAR,
-					  NULL))
-			esw->qos.node0 = ERR_PTR(-ENOMEM);
-	}
-	if (IS_ERR(esw->qos.node0)) {
-		err = PTR_ERR(esw->qos.node0);
-		esw_warn(dev, "E-Switch create rate node 0 failed (%d)\n", err);
-		goto err_node0;
-	}
 	refcount_set(&esw->qos.refcnt, 1);
 
 	return 0;
-
-err_node0:
-	if (mlx5_destroy_scheduling_element_cmd(esw->dev, SCHEDULING_HIERARCHY_E_SWITCH,
-						esw->qos.root_tsar_ix))
-		esw_warn(esw->dev, "E-Switch destroy root TSAR failed.\n");
-
-	return err;
 }
 
 static void esw_qos_destroy(struct mlx5_eswitch *esw)
 {
 	int err;
 
-	if (esw->qos.node0->ix != esw->qos.root_tsar_ix)
-		__esw_qos_destroy_node(esw->qos.node0, NULL);
-	else
-		__esw_qos_free_node(esw->qos.node0);
-	esw->qos.node0 = NULL;
-
 	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
 						  SCHEDULING_HIERARCHY_E_SWITCH,
 						  esw->qos.root_tsar_ix);
@@ -537,33 +818,271 @@ static void esw_qos_put(struct mlx5_eswitch *esw)
 		esw_qos_destroy(esw);
 }
 
-static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_ack *extack)
+static void
+esw_qos_tc_arbiter_scheduling_teardown(struct mlx5_esw_sched_node *node,
+				       struct netlink_ext_ack *extack)
+{
+	/* Clean up all Vports TC nodes within the TC arbiter node. */
+	esw_qos_destroy_vports_tc_nodes(node, extack);
+	/* Destroy the scheduling element for the TC arbiter node itself. */
+	esw_qos_node_destroy_sched_element(node, extack);
+}
+
+static int esw_qos_tc_arbiter_scheduling_setup(struct mlx5_esw_sched_node *node,
+					       struct netlink_ext_ack *extack)
+{
+	u32 curr_ix = node->ix;
+	int err;
+
+	err = esw_qos_create_tc_arbiter_sched_elem(node, extack);
+	if (err)
+		return err;
+	/* Initialize the vports TC nodes within created TC arbiter TSAR. */
+	err = esw_qos_create_vports_tc_nodes(node, extack);
+	if (err)
+		goto err_vports_tc_nodes;
+
+	node->type = SCHED_NODE_TYPE_TC_ARBITER_TSAR;
+
+	return 0;
+
+err_vports_tc_nodes:
+	/* If initialization fails, clean up the scheduling element
+	 * for the TC arbiter node.
+	 */
+	esw_qos_node_destroy_sched_element(node, NULL);
+	node->ix = curr_ix;
+	return err;
+}
+
+static int
+esw_qos_create_vport_tc_sched_node(struct mlx5_vport *vport,
+				   u32 rate_limit_elem_ix,
+				   struct mlx5_esw_sched_node *vports_tc_node,
+				   struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
+	struct mlx5_esw_sched_node *vport_tc_node;
+	u8 tc = vports_tc_node->tc;
+	int err;
+
+	vport_tc_node = __esw_qos_alloc_node(vport_node->esw, 0,
+					     SCHED_NODE_TYPE_VPORT_TC,
+					     vports_tc_node);
+	if (!vport_tc_node)
+		return -ENOMEM;
+
+	vport_tc_node->min_rate = vport_node->min_rate;
+	vport_tc_node->tc = tc;
+	vport_tc_node->vport = vport;
+	err = esw_qos_vport_tc_create_sched_element(vport_tc_node,
+						    rate_limit_elem_ix,
+						    extack);
+	if (err)
+		goto err_out;
+
+	vport->qos.sched_nodes[tc] = vport_tc_node;
+
+	return 0;
+err_out:
+	__esw_qos_free_node(vport_tc_node);
+	return err;
+}
+
+static void
+esw_qos_destroy_vport_tc_sched_elements(struct mlx5_vport *vport,
+					struct netlink_ext_ack *extack)
+{
+	int i, num_tcs = esw_qos_num_tcs(vport->qos.sched_node->esw->dev);
+
+	for (i = 0; i < num_tcs; i++) {
+		if (vport->qos.sched_nodes[i]) {
+			__esw_qos_destroy_node(vport->qos.sched_nodes[i],
+					       extack);
+		}
+	}
+
+	kfree(vport->qos.sched_nodes);
+	vport->qos.sched_nodes = NULL;
+}
+
+static int
+esw_qos_create_vport_tc_sched_elements(struct mlx5_vport *vport,
+				       enum sched_node_type type,
+				       struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
+	struct mlx5_esw_sched_node *tc_arbiter_node, *vports_tc_node;
+	int err, num_tcs = esw_qos_num_tcs(vport_node->esw->dev);
+	u32 rate_limit_elem_ix;
+
+	vport->qos.sched_nodes = kcalloc(num_tcs,
+					 sizeof(struct mlx5_esw_sched_node *),
+					 GFP_KERNEL);
+	if (!vport->qos.sched_nodes) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Allocating the vport TC scheduling elements failed.");
+		return -ENOMEM;
+	}
+
+	rate_limit_elem_ix = type == SCHED_NODE_TYPE_RATE_LIMITER ?
+			     vport_node->ix : 0;
+	tc_arbiter_node = type == SCHED_NODE_TYPE_RATE_LIMITER ?
+			   vport_node->parent : vport_node;
+	list_for_each_entry(vports_tc_node, &tc_arbiter_node->children, entry) {
+		err = esw_qos_create_vport_tc_sched_node(vport,
+							 rate_limit_elem_ix,
+							 vports_tc_node,
+							 extack);
+		if (err)
+			goto err_create_vport_tc;
+	}
+
+	return 0;
+
+err_create_vport_tc:
+	esw_qos_destroy_vport_tc_sched_elements(vport, NULL);
+
+	return err;
+}
+
+static int
+esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type,
+			struct netlink_ext_ack *extack)
 {
 	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
 	struct mlx5_esw_sched_node *parent = vport_node->parent;
+	int err;
 
-	esw_qos_node_destroy_sched_element(vport_node, extack);
+	if (type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) {
+		int new_level, max_level;
+
+		/* Increase the parent's level by 2 to account for both the
+		 * TC arbiter and the vports TC scheduling element.
+		 */
+		new_level = (parent ? parent->level : 2) + 2;
+		max_level = 1 << MLX5_CAP_QOS(vport_node->esw->dev,
+					      log_esw_max_sched_depth);
+		if (new_level > max_level) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "TC arbitration on leafs is not supported beyond max depth %d",
+					       max_level);
+			return -EOPNOTSUPP;
+		}
+	}
+
+	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
+
+	if (type == SCHED_NODE_TYPE_RATE_LIMITER)
+		err = esw_qos_create_rate_limit_element(vport_node, extack);
+	else
+		err = esw_qos_tc_arbiter_scheduling_setup(vport_node, extack);
+	if (err)
+		return err;
+
+	/* Rate limiters impact multiple nodes not directly connected to them
+	 * and are not direct members of the QoS hierarchy.
+	 * Unlink it from the parent to reflect that.
+	 */
+	if (type == SCHED_NODE_TYPE_RATE_LIMITER) {
+		list_del_init(&vport_node->entry);
+		vport_node->level = 0;
+	}
+
+	err  = esw_qos_create_vport_tc_sched_elements(vport, type, extack);
+	if (err)
+		goto err_sched_nodes;
+
+	return 0;
+
+err_sched_nodes:
+	if (type == SCHED_NODE_TYPE_RATE_LIMITER) {
+		esw_qos_node_destroy_sched_element(vport_node, NULL);
+		esw_qos_node_attach_to_parent(vport_node);
+	} else {
+		esw_qos_tc_arbiter_scheduling_teardown(vport_node, NULL);
+	}
+	return err;
+}
+
+static void esw_qos_vport_tc_disable(struct mlx5_vport *vport,
+				     struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
+	enum sched_node_type curr_type = vport_node->type;
+
+	esw_qos_destroy_vport_tc_sched_elements(vport, extack);
+
+	if (curr_type == SCHED_NODE_TYPE_RATE_LIMITER)
+		esw_qos_node_destroy_sched_element(vport_node, extack);
+	else
+		esw_qos_tc_arbiter_scheduling_teardown(vport_node, extack);
+}
+
+static int esw_qos_set_vport_tcs_min_rate(struct mlx5_vport *vport,
+					  u32 min_rate,
+					  struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
+	int err, i, num_tcs = esw_qos_num_tcs(vport_node->esw->dev);
+
+	for (i = 0; i < num_tcs; i++) {
+		err = esw_qos_set_node_min_rate(vport->qos.sched_nodes[i],
+						min_rate, extack);
+		if (err)
+			goto err_out;
+	}
+	vport_node->min_rate = min_rate;
+
+	return 0;
+err_out:
+	for (--i; i >= 0; i--) {
+		esw_qos_set_node_min_rate(vport->qos.sched_nodes[i],
+					  vport_node->min_rate, extack);
+	}
+	return err;
+}
+
+static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
+	enum sched_node_type curr_type = vport_node->type;
+
+	if (curr_type == SCHED_NODE_TYPE_VPORT)
+		esw_qos_node_destroy_sched_element(vport_node, extack);
+	else
+		esw_qos_vport_tc_disable(vport, extack);
 
 	vport_node->bw_share = 0;
+	memset(vport_node->tc_bw, 0, sizeof(vport_node->tc_bw));
 	list_del_init(&vport_node->entry);
-	esw_qos_normalize_min_rate(parent->esw, parent, extack);
+	esw_qos_normalize_min_rate(vport_node->esw, vport_node->parent, extack);
 
 	trace_mlx5_esw_vport_qos_destroy(vport_node->esw->dev, vport);
 }
 
-static int esw_qos_vport_enable(struct mlx5_vport *vport, struct mlx5_esw_sched_node *parent,
+static int esw_qos_vport_enable(struct mlx5_vport *vport,
+				enum sched_node_type type,
+				struct mlx5_esw_sched_node *parent,
 				struct netlink_ext_ack *extack)
 {
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
 	int err;
 
 	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
 
-	esw_qos_node_set_parent(vport->qos.sched_node, parent);
-	err = esw_qos_vport_create_sched_element(vport->qos.sched_node, extack);
+	esw_qos_node_set_parent(vport_node, parent);
+	if (type == SCHED_NODE_TYPE_VPORT)
+		err = esw_qos_vport_create_sched_element(vport_node, extack);
+	else
+		err = esw_qos_vport_tc_enable(vport, type, extack);
 	if (err)
 		return err;
 
-	esw_qos_normalize_min_rate(parent->esw, parent, extack);
+	vport_node->type = type;
+	esw_qos_normalize_min_rate(vport_node->esw, parent, extack);
+	trace_mlx5_esw_vport_qos_create(vport->dev, vport, vport_node->max_rate,
+					vport_node->bw_share);
 
 	return 0;
 }
@@ -574,6 +1093,7 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 {
 	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
 	struct mlx5_esw_sched_node *sched_node;
+	struct mlx5_eswitch *parent_esw;
 	int err;
 
 	esw_assert_qos_lock_held(esw);
@@ -581,22 +1101,42 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 	if (err)
 		return err;
 
-	parent = parent ?: esw->qos.node0;
-	sched_node = __esw_qos_alloc_node(parent->esw, 0, type, parent);
-	if (!sched_node)
+	parent_esw = parent ? parent->esw : esw;
+	sched_node = __esw_qos_alloc_node(parent_esw, 0, type, parent);
+	if (!sched_node) {
+		esw_qos_put(esw);
 		return -ENOMEM;
+	}
+	if (!parent)
+		list_add_tail(&sched_node->entry, &esw->qos.domain->nodes);
 
 	sched_node->max_rate = max_rate;
 	sched_node->min_rate = min_rate;
 	sched_node->vport = vport;
 	vport->qos.sched_node = sched_node;
-	err = esw_qos_vport_enable(vport, parent, extack);
-	if (err)
+	err = esw_qos_vport_enable(vport, type, parent, extack);
+	if (err) {
+		__esw_qos_free_node(sched_node);
 		esw_qos_put(esw);
+		vport->qos.sched_node = NULL;
+	}
 
 	return err;
 }
 
+static void mlx5_esw_qos_vport_disable_locked(struct mlx5_vport *vport)
+{
+	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
+
+	esw_assert_qos_lock_held(esw);
+	if (!vport->qos.sched_node)
+		return;
+
+	esw_qos_vport_disable(vport, NULL);
+	mlx5_esw_qos_vport_qos_free(vport);
+	esw_qos_put(esw);
+}
+
 void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport)
 {
 	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
@@ -608,11 +1148,9 @@ void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport)
 		goto unlock;
 
 	parent = vport->qos.sched_node->parent;
-	WARN(parent != esw->qos.node0, "Disabling QoS on port before detaching it from node");
+	WARN(parent, "Disabling QoS on port before detaching it from node");
 
-	esw_qos_vport_disable(vport, NULL);
-	mlx5_esw_qos_vport_qos_free(vport);
-	esw_qos_put(esw);
+	mlx5_esw_qos_vport_disable_locked(vport);
 unlock:
 	esw_qos_unlock(esw);
 }
@@ -642,6 +1180,8 @@ static int mlx5_esw_qos_set_vport_min_rate(struct mlx5_vport *vport, u32 min_rat
 	if (!vport_node)
 		return mlx5_esw_qos_vport_enable(vport, SCHED_NODE_TYPE_VPORT, NULL, 0, min_rate,
 						 extack);
+	else if (vport_node->type == SCHED_NODE_TYPE_RATE_LIMITER)
+		return esw_qos_set_vport_tcs_min_rate(vport, min_rate, extack);
 	else
 		return esw_qos_set_node_min_rate(vport_node, min_rate, extack);
 }
@@ -674,28 +1214,279 @@ bool mlx5_esw_qos_get_vport_rate(struct mlx5_vport *vport, u32 *max_rate, u32 *m
 	return enabled;
 }
 
+static int esw_qos_vport_tc_check_type(enum sched_node_type curr_type,
+				       enum sched_node_type new_type,
+				       struct netlink_ext_ack *extack)
+{
+	if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR &&
+	    new_type == SCHED_NODE_TYPE_RATE_LIMITER) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot switch from vport-level TC arbitration to node-level TC arbitration");
+		return -EOPNOTSUPP;
+	}
+
+	if (curr_type == SCHED_NODE_TYPE_RATE_LIMITER &&
+	    new_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot switch from node-level TC arbitration to vport-level TC arbitration");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int esw_qos_vport_update(struct mlx5_vport *vport,
+				enum sched_node_type type,
+				struct mlx5_esw_sched_node *parent,
+				struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
+	struct mlx5_esw_sched_node *curr_parent = vport_node->parent;
+	enum sched_node_type curr_type = vport_node->type;
+	u32 curr_tc_bw[DEVLINK_RATE_TCS_MAX] = {0};
+	int err;
+
+	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
+	if (curr_type == type && curr_parent == parent)
+		return 0;
+
+	err = esw_qos_vport_tc_check_type(curr_type, type, extack);
+	if (err)
+		return err;
+
+	if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type)
+		esw_qos_tc_arbiter_get_bw_shares(vport_node, curr_tc_bw);
+
+	esw_qos_vport_disable(vport, extack);
+
+	err = esw_qos_vport_enable(vport, type, parent, extack);
+	if (err) {
+		esw_qos_vport_enable(vport, curr_type, curr_parent, NULL);
+		extack = NULL;
+	}
+
+	if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) {
+		esw_qos_set_tc_arbiter_bw_shares(vport_node, curr_tc_bw,
+						 extack);
+	}
+
+	return err;
+}
+
 static int esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw_sched_node *parent,
 				       struct netlink_ext_ack *extack)
 {
 	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
 	struct mlx5_esw_sched_node *curr_parent;
-	int err;
+	enum sched_node_type type;
 
 	esw_assert_qos_lock_held(esw);
 	curr_parent = vport->qos.sched_node->parent;
-	parent = parent ?: esw->qos.node0;
 	if (curr_parent == parent)
 		return 0;
 
-	esw_qos_vport_disable(vport, extack);
+	/* Set vport QoS type based on parent node type if different from
+	 * default QoS; otherwise, use the vport's current QoS type.
+	 */
+	if (parent && parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+		type = SCHED_NODE_TYPE_RATE_LIMITER;
+	else if (curr_parent &&
+		 curr_parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+		type = SCHED_NODE_TYPE_VPORT;
+	else
+		type = vport->qos.sched_node->type;
+
+	return esw_qos_vport_update(vport, type, parent, extack);
+}
+
+static void
+esw_qos_switch_vport_tcs_to_vport(struct mlx5_esw_sched_node *tc_arbiter_node,
+				  struct mlx5_esw_sched_node *node,
+				  struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *vports_tc_node, *vport_tc_node, *tmp;
+
+	vports_tc_node = list_first_entry(&tc_arbiter_node->children,
+					  struct mlx5_esw_sched_node,
+					  entry);
 
-	err = esw_qos_vport_enable(vport, parent, extack);
+	list_for_each_entry_safe(vport_tc_node, tmp, &vports_tc_node->children,
+				 entry)
+		esw_qos_vport_update_parent(vport_tc_node->vport, node, extack);
+}
+
+static int esw_qos_switch_tc_arbiter_node_to_vports(
+	struct mlx5_esw_sched_node *tc_arbiter_node,
+	struct mlx5_esw_sched_node *node,
+	struct netlink_ext_ack *extack)
+{
+	u32 parent_tsar_ix = node->parent ?
+			     node->parent->ix : node->esw->qos.root_tsar_ix;
+	int err;
+
+	err = esw_qos_create_node_sched_elem(node->esw->dev, parent_tsar_ix,
+					     node->max_rate, node->bw_share,
+					     &node->ix);
 	if (err) {
-		if (esw_qos_vport_enable(vport, curr_parent, NULL))
-			esw_warn(parent->esw->dev, "vport restore QoS failed (vport=%d)\n",
-				 vport->vport);
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to create scheduling element for vports node when disabling vports TC QoS");
+		return err;
 	}
 
+	node->type = SCHED_NODE_TYPE_VPORTS_TSAR;
+
+	/* Disable TC QoS for vports in the arbiter node. */
+	esw_qos_switch_vport_tcs_to_vport(tc_arbiter_node, node, extack);
+
+	return 0;
+}
+
+static int esw_qos_switch_vports_node_to_tc_arbiter(
+	struct mlx5_esw_sched_node *node,
+	struct mlx5_esw_sched_node *tc_arbiter_node,
+	struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *vport_node, *tmp;
+	struct mlx5_vport *vport;
+	int err;
+
+	/* Enable TC QoS for each vport in the node. */
+	list_for_each_entry_safe(vport_node, tmp, &node->children, entry) {
+		vport = vport_node->vport;
+		err = esw_qos_vport_update_parent(vport, tc_arbiter_node,
+						  extack);
+		if  (err)
+			goto err_out;
+	}
+
+	/* Destroy the current vports node TSAR. */
+	err = mlx5_destroy_scheduling_element_cmd(node->esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  node->ix);
+	if (err)
+		goto err_out;
+
+	return 0;
+err_out:
+	/* Restore vports back into the node if an error occurs. */
+	esw_qos_switch_vport_tcs_to_vport(tc_arbiter_node, node, NULL);
+
+	return err;
+}
+
+static struct mlx5_esw_sched_node *
+esw_qos_move_node(struct mlx5_esw_sched_node *curr_node)
+{
+	struct mlx5_esw_sched_node *new_node;
+
+	new_node = __esw_qos_alloc_node(curr_node->esw, curr_node->ix,
+					curr_node->type, NULL);
+	if (!new_node)
+		return ERR_PTR(-ENOMEM);
+
+	esw_qos_nodes_set_parent(&curr_node->children, new_node);
+	return new_node;
+}
+
+static int esw_qos_node_disable_tc_arbitration(struct mlx5_esw_sched_node *node,
+					       struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *curr_node;
+	int err;
+
+	if (node->type != SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+		return 0;
+
+	/* Allocate a new rate node to hold the current state, which will allow
+	 * for restoring the vports back to this node after disabling TC
+	 * arbitration.
+	 */
+	curr_node = esw_qos_move_node(node);
+	if (IS_ERR(curr_node)) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed setting up vports node");
+		return PTR_ERR(curr_node);
+	}
+
+	/* Disable TC QoS for all vports, and assign them back to the node. */
+	err = esw_qos_switch_tc_arbiter_node_to_vports(curr_node, node, extack);
+	if (err)
+		goto err_out;
+
+	/* Clean up the TC arbiter node after disabling TC QoS for vports. */
+	esw_qos_tc_arbiter_scheduling_teardown(curr_node, extack);
+	goto out;
+err_out:
+	esw_qos_nodes_set_parent(&curr_node->children, node);
+out:
+	__esw_qos_free_node(curr_node);
+	return err;
+}
+
+static int esw_qos_node_enable_tc_arbitration(struct mlx5_esw_sched_node *node,
+					      struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *curr_node, *child;
+	int err, new_level, max_level;
+
+	if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+		return 0;
+
+	/* Increase the hierarchy level by one to account for the additional
+	 * vports TC scheduling node, and verify that the new level does not
+	 * exceed the maximum allowed depth.
+	 */
+	new_level = node->level + 1;
+	max_level = 1 << MLX5_CAP_QOS(node->esw->dev, log_esw_max_sched_depth);
+	if (new_level > max_level) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "TC arbitration on nodes is not supported beyond max depth %d",
+				       max_level);
+		return -EOPNOTSUPP;
+	}
+
+	/* Ensure the node does not contain non-leaf children before assigning
+	 * TC bandwidth.
+	 */
+	if (!list_empty(&node->children)) {
+		list_for_each_entry(child, &node->children, entry) {
+			if (!child->vport) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Cannot configure TC bandwidth on a node with non-leaf children");
+				return -EOPNOTSUPP;
+			}
+		}
+	}
+
+	/* Allocate a new node that will store the information of the current
+	 * node. This will be used later to restore the node if necessary.
+	 */
+	curr_node = esw_qos_move_node(node);
+	if (IS_ERR(curr_node)) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed setting up node TC QoS");
+		return PTR_ERR(curr_node);
+	}
+
+	/* Initialize the TC arbiter node for QoS management.
+	 * This step prepares the node for handling Traffic Class arbitration.
+	 */
+	err = esw_qos_tc_arbiter_scheduling_setup(node, extack);
+	if (err)
+		goto err_setup;
+
+	/* Enable TC QoS for each vport within the current node. */
+	err = esw_qos_switch_vports_node_to_tc_arbiter(curr_node, node, extack);
+	if (err)
+		goto err_switch_vports;
+	goto out;
+
+err_switch_vports:
+	esw_qos_tc_arbiter_scheduling_teardown(node, NULL);
+	node->ix = curr_node->ix;
+	node->type = curr_node->type;
+err_setup:
+	esw_qos_nodes_set_parent(&curr_node->children, node);
+out:
+	__esw_qos_free_node(curr_node);
 	return err;
 }
 
@@ -719,6 +1510,7 @@ static u32 mlx5_esw_qos_lag_link_speed_get_locked(struct mlx5_core_dev *mdev)
 		speed = lksettings.base.speed;
 
 out:
+	mlx5_uplink_netdev_put(mdev, slave);
 	return speed;
 }
 
@@ -824,6 +1616,57 @@ static int esw_qos_devlink_rate_to_mbps(struct mlx5_core_dev *mdev, const char *
 	return 0;
 }
 
+static bool esw_qos_validate_unsupported_tc_bw(struct mlx5_eswitch *esw,
+					       u32 *tc_bw)
+{
+	int i, num_tcs = esw_qos_num_tcs(esw->dev);
+
+	for (i = num_tcs; i < DEVLINK_RATE_TCS_MAX; i++) {
+		if (tc_bw[i])
+			return false;
+	}
+
+	return true;
+}
+
+static bool esw_qos_vport_validate_unsupported_tc_bw(struct mlx5_vport *vport,
+						     u32 *tc_bw)
+{
+	struct mlx5_esw_sched_node *node = vport->qos.sched_node;
+	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
+
+	esw = (node && node->parent) ? node->parent->esw : esw;
+
+	return esw_qos_validate_unsupported_tc_bw(esw, tc_bw);
+}
+
+static bool esw_qos_tc_bw_disabled(u32 *tc_bw)
+{
+	int i;
+
+	for (i = 0; i < DEVLINK_RATE_TCS_MAX; i++) {
+		if (tc_bw[i])
+			return false;
+	}
+
+	return true;
+}
+
+static void esw_vport_qos_prune_empty(struct mlx5_vport *vport)
+{
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
+
+	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
+	if (!vport_node)
+		return;
+
+	if (vport_node->parent || vport_node->max_rate ||
+	    vport_node->min_rate || !esw_qos_tc_bw_disabled(vport_node->tc_bw))
+		return;
+
+	mlx5_esw_qos_vport_disable_locked(vport);
+}
+
 int mlx5_esw_qos_init(struct mlx5_eswitch *esw)
 {
 	if (esw->qos.domain)
@@ -857,6 +1700,10 @@ int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void
 
 	esw_qos_lock(esw);
 	err = mlx5_esw_qos_set_vport_min_rate(vport, tx_share, extack);
+	if (err)
+		goto out;
+	esw_vport_qos_prune_empty(vport);
+out:
 	esw_qos_unlock(esw);
 	return err;
 }
@@ -878,6 +1725,95 @@ int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *
 
 	esw_qos_lock(esw);
 	err = mlx5_esw_qos_set_vport_max_rate(vport, tx_max, extack);
+	if (err)
+		goto out;
+	esw_vport_qos_prune_empty(vport);
+out:
+	esw_qos_unlock(esw);
+	return err;
+}
+
+int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf,
+					 void *priv,
+					 u32 *tc_bw,
+					 struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *vport_node;
+	struct mlx5_vport *vport = priv;
+	struct mlx5_eswitch *esw;
+	bool disable;
+	int err = 0;
+
+	esw = vport->dev->priv.eswitch;
+	if (!mlx5_esw_allowed(esw))
+		return -EPERM;
+
+	disable = esw_qos_tc_bw_disabled(tc_bw);
+	esw_qos_lock(esw);
+
+	if (!esw_qos_vport_validate_unsupported_tc_bw(vport, tc_bw)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "E-Switch traffic classes number is not supported");
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	vport_node = vport->qos.sched_node;
+	if (disable && !vport_node)
+		goto unlock;
+
+	if (disable) {
+		if (vport_node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+			err = esw_qos_vport_update(vport, SCHED_NODE_TYPE_VPORT,
+						   vport_node->parent, extack);
+		esw_vport_qos_prune_empty(vport);
+		goto unlock;
+	}
+
+	if (!vport_node) {
+		err = mlx5_esw_qos_vport_enable(vport,
+						SCHED_NODE_TYPE_TC_ARBITER_TSAR,
+						NULL, 0, 0, extack);
+		vport_node = vport->qos.sched_node;
+	} else {
+		err = esw_qos_vport_update(vport,
+					   SCHED_NODE_TYPE_TC_ARBITER_TSAR,
+					   vport_node->parent, extack);
+	}
+	if (!err)
+		esw_qos_set_tc_arbiter_bw_shares(vport_node, tc_bw, extack);
+unlock:
+	esw_qos_unlock(esw);
+	return err;
+}
+
+int mlx5_esw_devlink_rate_node_tc_bw_set(struct devlink_rate *rate_node,
+					 void *priv,
+					 u32 *tc_bw,
+					 struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *node = priv;
+	struct mlx5_eswitch *esw = node->esw;
+	bool disable;
+	int err;
+
+	if (!esw_qos_validate_unsupported_tc_bw(esw, tc_bw)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "E-Switch traffic classes number is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	disable = esw_qos_tc_bw_disabled(tc_bw);
+	esw_qos_lock(esw);
+	if (disable) {
+		err = esw_qos_node_disable_tc_arbitration(node, extack);
+		goto unlock;
+	}
+
+	err = esw_qos_node_enable_tc_arbitration(node, extack);
+	if (!err)
+		esw_qos_set_tc_arbiter_bw_shares(node, tc_bw, extack);
+unlock:
 	esw_qos_unlock(esw);
 	return err;
 }
@@ -972,25 +1908,200 @@ int mlx5_esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw_s
 	}
 
 	esw_qos_lock(esw);
-	if (!vport->qos.sched_node && parent)
-		err = mlx5_esw_qos_vport_enable(vport, SCHED_NODE_TYPE_VPORT, parent, 0, 0, extack);
-	else if (vport->qos.sched_node)
+	if (!vport->qos.sched_node && parent) {
+		enum sched_node_type type;
+
+		type = parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR ?
+		       SCHED_NODE_TYPE_RATE_LIMITER : SCHED_NODE_TYPE_VPORT;
+		err = mlx5_esw_qos_vport_enable(vport, type, parent, 0, 0,
+						extack);
+	} else if (vport->qos.sched_node) {
 		err = esw_qos_vport_update_parent(vport, parent, extack);
+	}
 	esw_qos_unlock(esw);
 	return err;
 }
 
-int mlx5_esw_devlink_rate_parent_set(struct devlink_rate *devlink_rate,
-				     struct devlink_rate *parent,
-				     void *priv, void *parent_priv,
-				     struct netlink_ext_ack *extack)
+int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate,
+					  struct devlink_rate *parent,
+					  void *priv, void *parent_priv,
+					  struct netlink_ext_ack *extack)
 {
-	struct mlx5_esw_sched_node *node;
+	struct mlx5_esw_sched_node *node = parent ? parent_priv : NULL;
 	struct mlx5_vport *vport = priv;
+	int err;
+
+	err = mlx5_esw_qos_vport_update_parent(vport, node, extack);
+	if (!err) {
+		struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
+
+		esw_qos_lock(esw);
+		esw_vport_qos_prune_empty(vport);
+		esw_qos_unlock(esw);
+	}
+
+	return err;
+}
+
+static bool esw_qos_is_node_empty(struct mlx5_esw_sched_node *node)
+{
+	if (list_empty(&node->children))
+		return true;
+
+	if (node->type != SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+		return false;
+
+	node = list_first_entry(&node->children, struct mlx5_esw_sched_node,
+				entry);
+
+	return esw_qos_is_node_empty(node);
+}
+
+static int
+mlx5_esw_qos_node_validate_set_parent(struct mlx5_esw_sched_node *node,
+				      struct mlx5_esw_sched_node *parent,
+				      struct netlink_ext_ack *extack)
+{
+	u8 new_level, max_level;
+
+	if (parent && parent->esw != node->esw) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot assign node to another E-Switch");
+		return -EOPNOTSUPP;
+	}
+
+	if (!esw_qos_is_node_empty(node)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot reassign a node that contains rate objects");
+		return -EOPNOTSUPP;
+	}
+
+	if (parent && parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot attach a node to a parent with TC bandwidth configured");
+		return -EOPNOTSUPP;
+	}
+
+	new_level = parent ? parent->level + 1 : 2;
+	if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) {
+		/* Increase by one to account for the vports TC scheduling
+		 * element.
+		 */
+		new_level += 1;
+	}
+
+	max_level = 1 << MLX5_CAP_QOS(node->esw->dev, log_esw_max_sched_depth);
+	if (new_level > max_level) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Node hierarchy depth %d exceeds the maximum supported level %d",
+				       new_level, max_level);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+esw_qos_tc_arbiter_node_update_parent(struct mlx5_esw_sched_node *node,
+				      struct mlx5_esw_sched_node *parent,
+				      struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *curr_parent = node->parent;
+	u32 curr_tc_bw[DEVLINK_RATE_TCS_MAX] = {0};
+	struct mlx5_eswitch *esw = node->esw;
+	int err;
+
+	esw_qos_tc_arbiter_get_bw_shares(node, curr_tc_bw);
+	esw_qos_tc_arbiter_scheduling_teardown(node, extack);
+	esw_qos_node_set_parent(node, parent);
+	err = esw_qos_tc_arbiter_scheduling_setup(node, extack);
+	if (err) {
+		esw_qos_node_set_parent(node, curr_parent);
+		if (esw_qos_tc_arbiter_scheduling_setup(node, extack)) {
+			esw_warn(esw->dev, "Node restore QoS failed\n");
+			return err;
+		}
+	}
+	esw_qos_set_tc_arbiter_bw_shares(node, curr_tc_bw, extack);
+
+	return err;
+}
+
+static int esw_qos_vports_node_update_parent(struct mlx5_esw_sched_node *node,
+					     struct mlx5_esw_sched_node *parent,
+					     struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *curr_parent = node->parent;
+	struct mlx5_eswitch *esw = node->esw;
+	u32 parent_ix;
+	int err;
+
+	parent_ix = parent ? parent->ix : node->esw->qos.root_tsar_ix;
+	mlx5_destroy_scheduling_element_cmd(esw->dev,
+					    SCHEDULING_HIERARCHY_E_SWITCH,
+					    node->ix);
+	err = esw_qos_create_node_sched_elem(esw->dev, parent_ix,
+					     node->max_rate, 0, &node->ix);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to create a node under the new hierarchy.");
+		if (esw_qos_create_node_sched_elem(esw->dev, curr_parent->ix,
+						   node->max_rate,
+						   node->bw_share,
+						   &node->ix))
+			esw_warn(esw->dev, "Node restore QoS failed\n");
+
+		return err;
+	}
+	esw_qos_node_set_parent(node, parent);
+	node->bw_share = 0;
+
+	return 0;
+}
+
+static int mlx5_esw_qos_node_update_parent(struct mlx5_esw_sched_node *node,
+					   struct mlx5_esw_sched_node *parent,
+					   struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *curr_parent;
+	struct mlx5_eswitch *esw = node->esw;
+	int err;
+
+	err = mlx5_esw_qos_node_validate_set_parent(node, parent, extack);
+	if (err)
+		return err;
+
+	esw_qos_lock(esw);
+	curr_parent = node->parent;
+	if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) {
+		err = esw_qos_tc_arbiter_node_update_parent(node, parent,
+							    extack);
+	} else {
+		err = esw_qos_vports_node_update_parent(node, parent, extack);
+	}
+
+	if (err)
+		goto out;
+
+	esw_qos_normalize_min_rate(esw, curr_parent, extack);
+	esw_qos_normalize_min_rate(esw, parent, extack);
+
+out:
+	esw_qos_unlock(esw);
+
+	return err;
+}
+
+int mlx5_esw_devlink_rate_node_parent_set(struct devlink_rate *devlink_rate,
+					  struct devlink_rate *parent,
+					  void *priv, void *parent_priv,
+					  struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *node = priv, *parent_node;
 
 	if (!parent)
-		return mlx5_esw_qos_vport_update_parent(vport, NULL, extack);
+		return mlx5_esw_qos_node_update_parent(node, NULL, extack);
 
-	node = parent_priv;
-	return mlx5_esw_qos_vport_update_parent(vport, node, extack);
+	parent_node = parent_priv;
+	return mlx5_esw_qos_node_update_parent(node, parent_node, extack);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
index 6eb8f6a648c8..0a50982b0e27 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
@@ -21,6 +21,14 @@ int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void
 					    u64 tx_share, struct netlink_ext_ack *extack);
 int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *priv,
 					  u64 tx_max, struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_node,
+					 void *priv,
+					 u32 *tc_bw,
+					 struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_node_tc_bw_set(struct devlink_rate *rate_node,
+					 void *priv,
+					 u32 *tc_bw,
+					 struct netlink_ext_ack *extack);
 int mlx5_esw_devlink_rate_node_tx_share_set(struct devlink_rate *rate_node, void *priv,
 					    u64 tx_share, struct netlink_ext_ack *extack);
 int mlx5_esw_devlink_rate_node_tx_max_set(struct devlink_rate *rate_node, void *priv,
@@ -29,10 +37,14 @@ int mlx5_esw_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv,
 				   struct netlink_ext_ack *extack);
 int mlx5_esw_devlink_rate_node_del(struct devlink_rate *rate_node, void *priv,
 				   struct netlink_ext_ack *extack);
-int mlx5_esw_devlink_rate_parent_set(struct devlink_rate *devlink_rate,
-				     struct devlink_rate *parent,
-				     void *priv, void *parent_priv,
-				     struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate,
+					  struct devlink_rate *parent,
+					  void *priv, void *parent_priv,
+					  struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_node_parent_set(struct devlink_rate *devlink_rate,
+					  struct devlink_rate *parent,
+					  void *priv, void *parent_priv,
+					  struct netlink_ext_ack *extack);
 #endif
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/vporttbl.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/vporttbl.c
index 749c3957a128..407062096a82 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/vporttbl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/vporttbl.c
@@ -45,8 +45,8 @@ esw_vport_tbl_create(struct mlx5_eswitch *esw, struct mlx5_flow_namespace *ns,
 	ft_attr.flags = vport_ns->flags;
 	fdb = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
 	if (IS_ERR(fdb)) {
-		esw_warn(esw->dev, "Failed to create per vport FDB Table err %ld\n",
-			 PTR_ERR(fdb));
+		esw_warn(esw->dev, "Failed to create per vport FDB Table err %pe\n",
+			 fdb);
 	}
 
 	return fdb;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 7fb8a3381f84..4b7a1ce7f406 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -257,8 +257,8 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u16 vport, bool rx_rule,
 				    &flow_act, &dest, 1);
 	if (IS_ERR(flow_rule)) {
 		esw_warn(esw->dev,
-			 "FDB: Failed to add flow rule: dmac_v(%pM) dmac_c(%pM) -> vport(%d), err(%ld)\n",
-			 dmac_v, dmac_c, vport, PTR_ERR(flow_rule));
+			 "FDB: Failed to add flow rule: dmac_v(%pM) dmac_c(%pM) -> vport(%d), err(%pe)\n",
+			 dmac_v, dmac_c, vport, flow_rule);
 		flow_rule = NULL;
 	}
 
@@ -820,6 +820,7 @@ static int mlx5_esw_vport_caps_get(struct mlx5_eswitch *esw, struct mlx5_vport *
 
 	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
 	vport->info.roce_enabled = MLX5_GET(cmd_hca_cap, hca_caps, roce);
+	vport->vhca_id = MLX5_GET(cmd_hca_cap, hca_caps, vhca_id);
 
 	if (!MLX5_CAP_GEN_MAX(esw->dev, hca_cap_2))
 		goto out_free;
@@ -839,6 +840,18 @@ out_free:
 	return err;
 }
 
+bool mlx5_esw_vport_vhca_id(struct mlx5_eswitch *esw, u16 vportn, u16 *vhca_id)
+{
+	struct mlx5_vport *vport;
+
+	vport = mlx5_eswitch_get_vport(esw, vportn);
+	if (IS_ERR(vport) || MLX5_VPORT_INVAL_VHCA_ID(vport))
+		return false;
+
+	*vhca_id = vport->vhca_id;
+	return true;
+}
+
 static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
 	bool vst_mode_steering = esw_vst_mode_is_steering(esw);
@@ -862,13 +875,10 @@ static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 				      vport_num, 1,
 				      vport->info.link_state);
 
-	/* Host PF has its own mac/guid. */
-	if (vport_num) {
-		mlx5_modify_nic_vport_mac_address(esw->dev, vport_num,
-						  vport->info.mac);
-		mlx5_modify_nic_vport_node_guid(esw->dev, vport_num,
-						vport->info.node_guid);
-	}
+	mlx5_query_nic_vport_mac_address(esw->dev, vport_num, true,
+					 vport->info.mac);
+	mlx5_query_nic_vport_node_guid(esw->dev, vport_num, true,
+				       &vport->info.node_guid);
 
 	flags = (vport->info.vlan || vport->info.qos) ?
 		SET_VLAN_STRIP | SET_VLAN_INSERT : 0;
@@ -929,17 +939,11 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 
 	if (!mlx5_esw_is_manager_vport(esw, vport_num) &&
 	    MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
-		ret = mlx5_esw_vport_vhca_id_set(esw, vport_num);
+		ret = mlx5_esw_vport_vhca_id_map(esw, vport);
 		if (ret)
 			goto err_vhca_mapping;
 	}
 
-	/* External controller host PF has factory programmed MAC.
-	 * Read it from the device.
-	 */
-	if (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF)
-		mlx5_query_nic_vport_mac_address(esw->dev, vport_num, true, vport->info.mac);
-
 	esw_vport_change_handle_locked(vport);
 
 	esw->enabled_vports++;
@@ -973,7 +977,7 @@ void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 
 	if (!mlx5_esw_is_manager_vport(esw, vport_num) &&
 	    MLX5_CAP_GEN(esw->dev, vhca_resource_manager))
-		mlx5_esw_vport_vhca_id_clear(esw, vport_num);
+		mlx5_esw_vport_vhca_id_unmap(esw, vport);
 
 	if (vport->vport != MLX5_VPORT_PF &&
 	    (vport->info.ipsec_crypto_enabled || vport->info.ipsec_packet_enabled))
@@ -1038,6 +1042,25 @@ const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
 	return ERR_PTR(err);
 }
 
+static int mlx5_esw_host_functions_enabled_query(struct mlx5_eswitch *esw)
+{
+	const u32 *query_host_out;
+
+	if (!mlx5_core_is_ecpf_esw_manager(esw->dev))
+		return 0;
+
+	query_host_out = mlx5_esw_query_functions(esw->dev);
+	if (IS_ERR(query_host_out))
+		return PTR_ERR(query_host_out);
+
+	esw->esw_funcs.host_funcs_disabled =
+		MLX5_GET(query_esw_functions_out, query_host_out,
+			 host_params_context.host_pf_not_exist);
+
+	kvfree(query_host_out);
+	return 0;
+}
+
 static void mlx5_eswitch_event_handler_register(struct mlx5_eswitch *esw)
 {
 	if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev)) {
@@ -1185,7 +1208,8 @@ void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs)
 	unsigned long i;
 
 	mlx5_esw_for_each_vf_vport(esw, i, vport, num_vfs) {
-		if (!vport->enabled)
+		/* Adjacent VFs are unloaded separately */
+		if (!vport->enabled || vport->adjacent)
 			continue;
 		mlx5_eswitch_unload_pf_vf_vport(esw, vport->vport);
 	}
@@ -1204,6 +1228,42 @@ static void mlx5_eswitch_unload_ec_vf_vports(struct mlx5_eswitch *esw,
 	}
 }
 
+static void mlx5_eswitch_unload_adj_vf_vports(struct mlx5_eswitch *esw)
+{
+	struct mlx5_vport *vport;
+	unsigned long i;
+
+	mlx5_esw_for_each_vf_vport(esw, i, vport, U16_MAX) {
+		if (!vport->enabled || !vport->adjacent)
+			continue;
+		mlx5_eswitch_unload_pf_vf_vport(esw, vport->vport);
+	}
+}
+
+static int
+mlx5_eswitch_load_adj_vf_vports(struct mlx5_eswitch *esw,
+				enum mlx5_eswitch_vport_event enabled_events)
+{
+	struct mlx5_vport *vport;
+	unsigned long i;
+	int err;
+
+	mlx5_esw_for_each_vf_vport(esw, i, vport, U16_MAX) {
+		if (!vport->adjacent)
+			continue;
+		err = mlx5_eswitch_load_pf_vf_vport(esw, vport->vport,
+						    enabled_events);
+		if (err)
+			goto unload_adj_vf_vport;
+	}
+
+	return 0;
+
+unload_adj_vf_vport:
+	mlx5_eswitch_unload_adj_vf_vports(esw);
+	return err;
+}
+
 int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
 				enum mlx5_eswitch_vport_event enabled_events)
 {
@@ -1278,29 +1338,34 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
 		    esw->mode == MLX5_ESWITCH_LEGACY;
 
 	/* Enable PF vport */
-	if (pf_needed) {
+	if (pf_needed && mlx5_esw_host_functions_enabled(esw->dev)) {
 		ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_PF,
 						    enabled_events);
 		if (ret)
 			return ret;
 	}
 
-	/* Enable external host PF HCA */
-	ret = host_pf_enable_hca(esw->dev);
-	if (ret)
-		goto pf_hca_err;
+	if (mlx5_esw_host_functions_enabled(esw->dev)) {
+		/* Enable external host PF HCA */
+		ret = host_pf_enable_hca(esw->dev);
+		if (ret)
+			goto pf_hca_err;
+	}
 
 	/* Enable ECPF vport */
 	if (mlx5_ecpf_vport_exists(esw->dev)) {
 		ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_ECPF, enabled_events);
 		if (ret)
 			goto ecpf_err;
-		if (mlx5_core_ec_sriov_enabled(esw->dev)) {
-			ret = mlx5_eswitch_load_ec_vf_vports(esw, esw->esw_funcs.num_ec_vfs,
-							     enabled_events);
-			if (ret)
-				goto ec_vf_err;
-		}
+	}
+
+	/* Enable ECVF vports */
+	if (mlx5_core_ec_sriov_enabled(esw->dev)) {
+		ret = mlx5_eswitch_load_ec_vf_vports(esw,
+						     esw->esw_funcs.num_ec_vfs,
+						     enabled_events);
+		if (ret)
+			goto ec_vf_err;
 	}
 
 	/* Enable VF vports */
@@ -1308,8 +1373,16 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
 					  enabled_events);
 	if (ret)
 		goto vf_err;
+
+	/* Enable adjacent VF vports */
+	ret = mlx5_eswitch_load_adj_vf_vports(esw, enabled_events);
+	if (ret)
+		goto unload_vf_vports;
+
 	return 0;
 
+unload_vf_vports:
+	mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
 vf_err:
 	if (mlx5_core_ec_sriov_enabled(esw->dev))
 		mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_ec_vfs);
@@ -1317,9 +1390,10 @@ ec_vf_err:
 	if (mlx5_ecpf_vport_exists(esw->dev))
 		mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF);
 ecpf_err:
-	host_pf_disable_hca(esw->dev);
+	if (mlx5_esw_host_functions_enabled(esw->dev))
+		host_pf_disable_hca(esw->dev);
 pf_hca_err:
-	if (pf_needed)
+	if (pf_needed && mlx5_esw_host_functions_enabled(esw->dev))
 		mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_PF);
 	return ret;
 }
@@ -1329,18 +1403,24 @@ pf_hca_err:
  */
 void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw)
 {
+	mlx5_eswitch_unload_adj_vf_vports(esw);
+
 	mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
 
+	if (mlx5_core_ec_sriov_enabled(esw->dev))
+		mlx5_eswitch_unload_ec_vf_vports(esw,
+						 esw->esw_funcs.num_ec_vfs);
+
 	if (mlx5_ecpf_vport_exists(esw->dev)) {
-		if (mlx5_core_ec_sriov_enabled(esw->dev))
-			mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_vfs);
 		mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF);
 	}
 
-	host_pf_disable_hca(esw->dev);
+	if (mlx5_esw_host_functions_enabled(esw->dev))
+		host_pf_disable_hca(esw->dev);
 
-	if (mlx5_core_is_ecpf_esw_manager(esw->dev) ||
-	    esw->mode == MLX5_ESWITCH_LEGACY)
+	if ((mlx5_core_is_ecpf_esw_manager(esw->dev) ||
+	     esw->mode == MLX5_ESWITCH_LEGACY) &&
+	    mlx5_esw_host_functions_enabled(esw->dev))
 		mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_PF);
 }
 
@@ -1394,22 +1474,79 @@ static void mlx5_esw_mode_change_notify(struct mlx5_eswitch *esw, u16 mode)
 
 	info.new_mode = mode;
 
-	blocking_notifier_call_chain(&esw->n_head, 0, &info);
+	blocking_notifier_call_chain(&esw->dev->priv.esw_n_head, 0, &info);
+}
+
+static int mlx5_esw_egress_acls_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_flow_steering *steering = dev->priv.steering;
+	int total_vports = mlx5_eswitch_get_total_vports(dev);
+	int err;
+	int i;
+
+	for (i = 0; i < total_vports; i++) {
+		err = mlx5_fs_vport_egress_acl_ns_add(steering, i);
+		if (err)
+			goto acl_ns_remove;
+	}
+	return 0;
+
+acl_ns_remove:
+	while (i--)
+		mlx5_fs_vport_egress_acl_ns_remove(steering, i);
+	return err;
+}
+
+static void mlx5_esw_egress_acls_cleanup(struct mlx5_core_dev *dev)
+{
+	struct mlx5_flow_steering *steering = dev->priv.steering;
+	int total_vports = mlx5_eswitch_get_total_vports(dev);
+	int i;
+
+	for (i = total_vports - 1; i >= 0; i--)
+		mlx5_fs_vport_egress_acl_ns_remove(steering, i);
+}
+
+static int mlx5_esw_ingress_acls_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_flow_steering *steering = dev->priv.steering;
+	int total_vports = mlx5_eswitch_get_total_vports(dev);
+	int err;
+	int i;
+
+	for (i = 0; i < total_vports; i++) {
+		err = mlx5_fs_vport_ingress_acl_ns_add(steering, i);
+		if (err)
+			goto acl_ns_remove;
+	}
+	return 0;
+
+acl_ns_remove:
+	while (i--)
+		mlx5_fs_vport_ingress_acl_ns_remove(steering, i);
+	return err;
+}
+
+static void mlx5_esw_ingress_acls_cleanup(struct mlx5_core_dev *dev)
+{
+	struct mlx5_flow_steering *steering = dev->priv.steering;
+	int total_vports = mlx5_eswitch_get_total_vports(dev);
+	int i;
+
+	for (i = total_vports - 1; i >= 0; i--)
+		mlx5_fs_vport_ingress_acl_ns_remove(steering, i);
 }
 
 static int mlx5_esw_acls_ns_init(struct mlx5_eswitch *esw)
 {
 	struct mlx5_core_dev *dev = esw->dev;
-	int total_vports;
 	int err;
 
 	if (esw->flags & MLX5_ESWITCH_VPORT_ACL_NS_CREATED)
 		return 0;
 
-	total_vports = mlx5_eswitch_get_total_vports(dev);
-
 	if (MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support)) {
-		err = mlx5_fs_egress_acls_init(dev, total_vports);
+		err = mlx5_esw_egress_acls_init(dev);
 		if (err)
 			return err;
 	} else {
@@ -1417,7 +1554,7 @@ static int mlx5_esw_acls_ns_init(struct mlx5_eswitch *esw)
 	}
 
 	if (MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) {
-		err = mlx5_fs_ingress_acls_init(dev, total_vports);
+		err = mlx5_esw_ingress_acls_init(dev);
 		if (err)
 			goto err;
 	} else {
@@ -1428,7 +1565,7 @@ static int mlx5_esw_acls_ns_init(struct mlx5_eswitch *esw)
 
 err:
 	if (MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support))
-		mlx5_fs_egress_acls_cleanup(dev);
+		mlx5_esw_egress_acls_cleanup(dev);
 	return err;
 }
 
@@ -1438,9 +1575,9 @@ static void mlx5_esw_acls_ns_cleanup(struct mlx5_eswitch *esw)
 
 	esw->flags &= ~MLX5_ESWITCH_VPORT_ACL_NS_CREATED;
 	if (MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support))
-		mlx5_fs_ingress_acls_cleanup(dev);
+		mlx5_esw_ingress_acls_cleanup(dev);
 	if (MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support))
-		mlx5_fs_egress_acls_cleanup(dev);
+		mlx5_esw_egress_acls_cleanup(dev);
 }
 
 /**
@@ -1669,7 +1806,8 @@ int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 *
 	void *hca_caps;
 	int err;
 
-	if (!mlx5_core_is_ecpf(dev)) {
+	if (!mlx5_core_is_ecpf(dev) ||
+	    !mlx5_esw_host_functions_enabled(dev)) {
 		*max_sfs = 0;
 		return 0;
 	}
@@ -1691,8 +1829,7 @@ out_free:
 	return err;
 }
 
-static int mlx5_esw_vport_alloc(struct mlx5_eswitch *esw,
-				int index, u16 vport_num)
+int mlx5_esw_vport_alloc(struct mlx5_eswitch *esw, int index, u16 vport_num)
 {
 	struct mlx5_vport *vport;
 	int err;
@@ -1705,6 +1842,7 @@ static int mlx5_esw_vport_alloc(struct mlx5_eswitch *esw,
 	vport->vport = vport_num;
 	vport->index = index;
 	vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+	vport->vhca_id = MLX5_VHCA_ID_INVALID;
 	INIT_WORK(&vport->vport_change_handler, esw_vport_change_handler);
 	err = xa_insert(&esw->vports, vport_num, vport, GFP_KERNEL);
 	if (err)
@@ -1718,8 +1856,9 @@ insert_err:
 	return err;
 }
 
-static void mlx5_esw_vport_free(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
+void mlx5_esw_vport_free(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
+	esw->total_vports--;
 	xa_erase(&esw->vports, vport->vport);
 	kfree(vport);
 }
@@ -1745,21 +1884,23 @@ static int mlx5_esw_vports_init(struct mlx5_eswitch *esw)
 
 	xa_init(&esw->vports);
 
-	err = mlx5_esw_vport_alloc(esw, idx, MLX5_VPORT_PF);
-	if (err)
-		goto err;
-	if (esw->first_host_vport == MLX5_VPORT_PF)
-		xa_set_mark(&esw->vports, idx, MLX5_ESW_VPT_HOST_FN);
-	idx++;
-
-	for (i = 0; i < mlx5_core_max_vfs(dev); i++) {
-		err = mlx5_esw_vport_alloc(esw, idx, idx);
+	if (mlx5_esw_host_functions_enabled(dev)) {
+		err = mlx5_esw_vport_alloc(esw, idx, MLX5_VPORT_PF);
 		if (err)
 			goto err;
-		xa_set_mark(&esw->vports, idx, MLX5_ESW_VPT_VF);
-		xa_set_mark(&esw->vports, idx, MLX5_ESW_VPT_HOST_FN);
+		if (esw->first_host_vport == MLX5_VPORT_PF)
+			xa_set_mark(&esw->vports, idx, MLX5_ESW_VPT_HOST_FN);
 		idx++;
+		for (i = 0; i < mlx5_core_max_vfs(dev); i++) {
+			err = mlx5_esw_vport_alloc(esw, idx, idx);
+			if (err)
+				goto err;
+			xa_set_mark(&esw->vports, idx, MLX5_ESW_VPT_VF);
+			xa_set_mark(&esw->vports, idx, MLX5_ESW_VPT_HOST_FN);
+			idx++;
+		}
 	}
+
 	base_sf_num = mlx5_sf_start_function_id(dev);
 	for (i = 0; i < mlx5_sf_max_functions(dev); i++) {
 		err = mlx5_esw_vport_alloc(esw, idx, base_sf_num + i);
@@ -1801,6 +1942,9 @@ static int mlx5_esw_vports_init(struct mlx5_eswitch *esw)
 	err = mlx5_esw_vport_alloc(esw, idx, MLX5_VPORT_UPLINK);
 	if (err)
 		goto err;
+
+	/* Adjacent vports or other dynamically create vports will use this */
+	esw->last_vport_idx = ++idx;
 	return 0;
 
 err:
@@ -1825,7 +1969,8 @@ static int mlx5_devlink_esw_multiport_set(struct devlink *devlink, u32 id,
 }
 
 static int mlx5_devlink_esw_multiport_get(struct devlink *devlink, u32 id,
-					  struct devlink_param_gset_ctx *ctx)
+					  struct devlink_param_gset_ctx *ctx,
+					  struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 
@@ -1859,6 +2004,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		goto free_esw;
 
 	esw->dev = dev;
+	dev->priv.eswitch = esw;
 	esw->manager_vport = mlx5_eswitch_manager_vport(dev);
 	esw->first_host_vport = mlx5_eswitch_first_host_vport_num(dev);
 
@@ -1869,11 +2015,14 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		goto abort;
 	}
 
+	err = mlx5_esw_host_functions_enabled_query(esw);
+	if (err)
+		goto abort;
+
 	err = mlx5_esw_vports_init(esw);
 	if (err)
 		goto abort;
 
-	dev->priv.eswitch = esw;
 	err = esw_offloads_init(esw);
 	if (err)
 		goto reps_err;
@@ -1902,7 +2051,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
 	else
 		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
-	BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head);
 
 	esw_info(dev,
 		 "Total vports %d, per vport: max uc(%d) max mc(%d)\n",
@@ -2078,6 +2226,9 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
 	ivi->vf = vport - 1;
 
 	mutex_lock(&esw->state_lock);
+
+	mlx5_query_nic_vport_mac_address(esw->dev, vport, true,
+					 evport->info.mac);
 	ether_addr_copy(ivi->mac, evport->info.mac);
 	ivi->linkstate = evport->info.link_state;
 	ivi->vlan = evport->info.vlan;
@@ -2228,14 +2379,16 @@ bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
 		dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS);
 }
 
-int mlx5_esw_event_notifier_register(struct mlx5_eswitch *esw, struct notifier_block *nb)
+int mlx5_esw_event_notifier_register(struct mlx5_core_dev *dev,
+				     struct notifier_block *nb)
 {
-	return blocking_notifier_chain_register(&esw->n_head, nb);
+	return blocking_notifier_chain_register(&dev->priv.esw_n_head, nb);
 }
 
-void mlx5_esw_event_notifier_unregister(struct mlx5_eswitch *esw, struct notifier_block *nb)
+void mlx5_esw_event_notifier_unregister(struct mlx5_core_dev *dev,
+					struct notifier_block *nb)
 {
-	blocking_notifier_chain_unregister(&esw->n_head, nb);
+	blocking_notifier_chain_unregister(&dev->priv.esw_n_head, nb);
 }
 
 /**
@@ -2405,3 +2558,11 @@ void mlx5_eswitch_unblock_ipsec(struct mlx5_core_dev *dev)
 	dev->num_ipsec_offloads--;
 	mutex_unlock(&esw->state_lock);
 }
+
+bool mlx5_esw_host_functions_enabled(const struct mlx5_core_dev *dev)
+{
+	if (!dev->priv.eswitch)
+		return true;
+
+	return !dev->priv.eswitch->esw_funcs.host_funcs_disabled;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index a83d41121db6..ad1073f7b79f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -197,6 +197,11 @@ static inline struct mlx5_vport *mlx5_devlink_port_vport_get(struct devlink_port
 	return mlx5_devlink_port_get(dl_port)->vport;
 }
 
+#define MLX5_VHCA_ID_INVALID (-1)
+
+#define MLX5_VPORT_INVAL_VHCA_ID(vport) \
+	((vport)->vhca_id == MLX5_VHCA_ID_INVALID)
+
 struct mlx5_vport {
 	struct mlx5_core_dev    *dev;
 	struct hlist_head       uc_list[MLX5_L2_ADDR_HASH_SIZE];
@@ -209,13 +214,30 @@ struct mlx5_vport {
 	struct vport_egress     egress;
 	u32                     default_metadata;
 	u32                     metadata;
+	int                     vhca_id;
+
+	bool adjacent; /* delegated vhca from adjacent function */
+	struct {
+		u16 parent_pci_devfn; /* Adjacent parent PCI device function */
+		u16 function_id; /* Function ID of the delegated VPort */
+	} adj_info;
 
 	struct mlx5_vport_info  info;
 
-	/* Protected with the E-Switch qos domain lock. */
+	/* Protected with the E-Switch qos domain lock. The Vport QoS can
+	 * either be disabled (sched_node is NULL) or in one of three states:
+	 * 1. Regular QoS (sched_node is a vport node).
+	 * 2. TC QoS enabled on the vport (sched_node is a TC arbiter).
+	 * 3. TC QoS enabled on the vport's parent node
+	 *    (sched_node is a rate limit node).
+	 * When TC is enabled in either mode, the vport owns vport TC scheduling
+	 * nodes.
+	 */
 	struct {
-		/* Vport scheduling element node. */
+		/* Vport scheduling node. */
 		struct mlx5_esw_sched_node *sched_node;
+		/* Array of vport traffic class scheduling nodes. */
+		struct mlx5_esw_sched_node **sched_nodes;
 	} qos;
 
 	u16 vport;
@@ -242,6 +264,9 @@ struct mlx5_eswitch_fdb {
 
 		struct offloads_fdb {
 			struct mlx5_flow_namespace *ns;
+			struct mlx5_flow_table *drop_root;
+			struct mlx5_flow_handle *drop_root_rule;
+			struct mlx5_fc *drop_root_fc;
 			struct mlx5_flow_table *tc_miss_table;
 			struct mlx5_flow_table *slow_fdb;
 			struct mlx5_flow_group *send_to_vport_grp;
@@ -313,6 +338,7 @@ struct mlx5_host_work {
 
 struct mlx5_esw_functions {
 	struct mlx5_nb		nb;
+	bool			host_funcs_disabled;
 	u16			num_vfs;
 	u16			num_ec_vfs;
 };
@@ -363,16 +389,13 @@ struct mlx5_eswitch {
 		refcount_t refcnt;
 		u32 root_tsar_ix;
 		struct mlx5_qos_domain *domain;
-		/* Contains all vports with QoS enabled but no explicit node.
-		 * Cannot be NULL if QoS is enabled, but may be a fake node
-		 * referencing the root TSAR if the esw doesn't support nodes.
-		 */
-		struct mlx5_esw_sched_node *node0;
 	} qos;
 
 	struct mlx5_esw_bridge_offloads *br_offloads;
 	struct mlx5_esw_offload offloads;
+	u32 last_vport_idx;
 	int                     mode;
+	bool                    offloads_inactive;
 	u16                     manager_vport;
 	u16                     first_host_vport;
 	u8			num_peers;
@@ -380,7 +403,6 @@ struct mlx5_eswitch {
 	struct {
 		u32             large_group_num;
 	}  params;
-	struct blocking_notifier_head n_head;
 	struct xarray paired;
 	struct mlx5_devcom_comp_dev *devcom;
 	u16 enabled_ipsec_vf_count;
@@ -405,6 +427,8 @@ int mlx5_esw_qos_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32
 /* E-Switch API */
 int mlx5_eswitch_init(struct mlx5_core_dev *dev);
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw);
+int mlx5_esw_vport_alloc(struct mlx5_eswitch *esw, int index, u16 vport_num);
+void mlx5_esw_vport_free(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
 
 #define MLX5_ESWITCH_IGNORE_NUM_VFS (-1)
 int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs);
@@ -412,7 +436,8 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs);
 void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf);
 void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw);
 void mlx5_eswitch_disable(struct mlx5_eswitch *esw);
-void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, u64 key);
+void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw,
+				   const struct mlx5_devcom_match_attr *attr);
 void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw);
 bool mlx5_esw_offloads_devcom_is_ready(struct mlx5_eswitch *esw);
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
@@ -610,6 +635,11 @@ bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
 
 const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev);
 
+void mlx5_esw_adjacent_vhcas_setup(struct mlx5_eswitch *esw);
+void mlx5_esw_adjacent_vhcas_cleanup(struct mlx5_eswitch *esw);
+int mlx5_esw_adj_vport_modify(struct mlx5_core_dev *dev, u16 vport,
+			      bool connect);
+
 #define MLX5_DEBUG_ESWITCH_MASK BIT(3)
 
 #define esw_info(__dev, format, ...)			\
@@ -714,6 +744,9 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw);
 			  MLX5_CAP_GEN_2((esw->dev), ec_vf_vport_base) +\
 			  (last) - 1)
 
+#define mlx5_esw_for_each_rep(esw, i, rep) \
+	xa_for_each(&((esw)->offloads.vport_reps), i, rep)
+
 struct mlx5_eswitch *__must_check
 mlx5_devlink_eswitch_get(struct devlink *devlink);
 
@@ -809,12 +842,20 @@ struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u1
 
 int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 *sf_base_id);
 
-int mlx5_esw_vport_vhca_id_set(struct mlx5_eswitch *esw, u16 vport_num);
-void mlx5_esw_vport_vhca_id_clear(struct mlx5_eswitch *esw, u16 vport_num);
+int mlx5_esw_vport_vhca_id_map(struct mlx5_eswitch *esw,
+			       struct mlx5_vport *vport);
+void mlx5_esw_vport_vhca_id_unmap(struct mlx5_eswitch *esw,
+				  struct mlx5_vport *vport);
 int mlx5_eswitch_vhca_id_to_vport(struct mlx5_eswitch *esw, u16 vhca_id, u16 *vport_num);
+bool mlx5_esw_vport_vhca_id(struct mlx5_eswitch *esw, u16 vportn, u16 *vhca_id);
+
+void mlx5_esw_offloads_rep_remove(struct mlx5_eswitch *esw,
+				  const struct mlx5_vport *vport);
+int mlx5_esw_offloads_rep_add(struct mlx5_eswitch *esw,
+			      const struct mlx5_vport *vport);
 
 /**
- * mlx5_esw_event_info - Indicates eswitch mode changed/changing.
+ * struct mlx5_esw_event_info - Indicates eswitch mode changed/changing.
  *
  * @new_mode: New mode of eswitch.
  */
@@ -822,8 +863,10 @@ struct mlx5_esw_event_info {
 	u16 new_mode;
 };
 
-int mlx5_esw_event_notifier_register(struct mlx5_eswitch *esw, struct notifier_block *n);
-void mlx5_esw_event_notifier_unregister(struct mlx5_eswitch *esw, struct notifier_block *n);
+int mlx5_esw_event_notifier_register(struct mlx5_core_dev *dev,
+				     struct notifier_block *n);
+void mlx5_esw_event_notifier_unregister(struct mlx5_core_dev *dev,
+					struct notifier_block *n);
 
 bool mlx5_esw_hold(struct mlx5_core_dev *dev);
 void mlx5_esw_release(struct mlx5_core_dev *dev);
@@ -843,7 +886,7 @@ void mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw,
 					      struct mlx5_eswitch *slave_esw);
 int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw);
 
-bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev);
+bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev, bool from_fdb);
 void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev);
 
 int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev);
@@ -885,6 +928,7 @@ int mlx5_esw_ipsec_vf_packet_offload_set(struct mlx5_eswitch *esw, struct mlx5_v
 					 bool enable);
 int mlx5_esw_ipsec_vf_packet_offload_supported(struct mlx5_core_dev *dev,
 					       u16 vport_num);
+bool mlx5_esw_host_functions_enabled(const struct mlx5_core_dev *dev);
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
@@ -892,7 +936,9 @@ static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {}
 static inline int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) { return 0; }
 static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) {}
 static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw) {}
-static inline void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, u64 key) {}
+static inline void
+mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw,
+			      const struct mlx5_devcom_match_attr *attr) {}
 static inline void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) {}
 static inline bool mlx5_esw_offloads_devcom_is_ready(struct mlx5_eswitch *esw) { return false; }
 static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; }
@@ -935,7 +981,8 @@ mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw)
 	return 0;
 }
 
-static inline bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev)
+static inline bool
+mlx5_eswitch_block_encap(struct mlx5_core_dev *dev, bool from_fdb)
 {
 	return true;
 }
@@ -952,6 +999,19 @@ static inline bool mlx5_eswitch_block_ipsec(struct mlx5_core_dev *dev)
 }
 
 static inline void mlx5_eswitch_unblock_ipsec(struct mlx5_core_dev *dev) {}
+
+static inline bool
+mlx5_esw_host_functions_enabled(const struct mlx5_core_dev *dev)
+{
+	return true;
+}
+
+static inline bool
+mlx5_esw_vport_vhca_id(struct mlx5_eswitch *esw, u16 vportn, u16 *vhca_id)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif /* CONFIG_MLX5_ESWITCH */
 
 #endif /* __MLX5_ESWITCH_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 8636f0485800..8de6c7f6c294 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -53,9 +53,6 @@
 #include "lag/lag.h"
 #include "en/tc/post_meter.h"
 
-#define mlx5_esw_for_each_rep(esw, i, rep) \
-	xa_for_each(&((esw)->offloads.vport_reps), i, rep)
-
 /* There are two match-all miss flows, one for unicast dst mac and
  * one for multicast.
  */
@@ -651,6 +648,7 @@ esw_setup_meter(struct mlx5_flow_attr *attr, struct mlx5_flow_act *flow_act)
 	meter = attr->meter_attr.meter;
 	flow_act->exe_aso.type = attr->exe_aso_type;
 	flow_act->exe_aso.object_id = meter->obj_id;
+	flow_act->exe_aso.base_id = mlx5e_flow_meter_get_base_id(meter);
 	flow_act->exe_aso.flow_meter.meter_idx = meter->idx;
 	flow_act->exe_aso.flow_meter.init_color = MLX5_FLOW_METER_COLOR_GREEN;
 	/* use metadata reg 5 for packet color */
@@ -1018,8 +1016,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw,
 	flow_rule = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(on_esw),
 					spec, &flow_act, &dest, 1);
 	if (IS_ERR(flow_rule))
-		esw_warn(on_esw->dev, "FDB: Failed to add send to vport rule err %ld\n",
-			 PTR_ERR(flow_rule));
+		esw_warn(on_esw->dev, "FDB: Failed to add send to vport rule err %pe\n",
+			 flow_rule);
 out:
 	kvfree(spec);
 	return flow_rule;
@@ -1067,8 +1065,8 @@ mlx5_eswitch_add_send_to_vport_meta_rule(struct mlx5_eswitch *esw, u16 vport_num
 	flow_rule = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
 					spec, &flow_act, &dest, 1);
 	if (IS_ERR(flow_rule))
-		esw_warn(esw->dev, "FDB: Failed to add send to vport meta rule vport %d, err %ld\n",
-			 vport_num, PTR_ERR(flow_rule));
+		esw_warn(esw->dev, "FDB: Failed to add send to vport meta rule vport %d, err %pe\n",
+			 vport_num, flow_rule);
 
 	kvfree(spec);
 	return flow_rule;
@@ -1184,19 +1182,19 @@ static void esw_set_peer_miss_rule_source_port(struct mlx5_eswitch *esw,
 static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 				       struct mlx5_core_dev *peer_dev)
 {
+	struct mlx5_eswitch *peer_esw = peer_dev->priv.eswitch;
 	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_act flow_act = {0};
 	struct mlx5_flow_handle **flows;
-	/* total vports is the same for both e-switches */
-	int nvports = esw->total_vports;
 	struct mlx5_flow_handle *flow;
+	struct mlx5_vport *peer_vport;
 	struct mlx5_flow_spec *spec;
-	struct mlx5_vport *vport;
 	int err, pfindex;
 	unsigned long i;
 	void *misc;
 
-	if (!MLX5_VPORT_MANAGER(esw->dev) && !mlx5_core_is_ecpf_esw_manager(esw->dev))
+	if (!MLX5_VPORT_MANAGER(peer_dev) &&
+	    !mlx5_core_is_ecpf_esw_manager(peer_dev))
 		return 0;
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
@@ -1205,7 +1203,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 
 	peer_miss_rules_setup(esw, peer_dev, spec, &dest);
 
-	flows = kvcalloc(nvports, sizeof(*flows), GFP_KERNEL);
+	flows = kvcalloc(peer_esw->total_vports, sizeof(*flows), GFP_KERNEL);
 	if (!flows) {
 		err = -ENOMEM;
 		goto alloc_flows_err;
@@ -1215,10 +1213,11 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 			    misc_parameters);
 
-	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
-		esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch,
-						   spec, MLX5_VPORT_PF);
+	if (mlx5_core_is_ecpf_esw_manager(peer_dev) &&
+	    mlx5_esw_host_functions_enabled(peer_dev)) {
+		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF);
+		esw_set_peer_miss_rule_source_port(esw, peer_esw, spec,
+						   MLX5_VPORT_PF);
 
 		flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
 					   spec, &flow_act, &dest, 1);
@@ -1226,11 +1225,11 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 			err = PTR_ERR(flow);
 			goto add_pf_flow_err;
 		}
-		flows[vport->index] = flow;
+		flows[peer_vport->index] = flow;
 	}
 
-	if (mlx5_ecpf_vport_exists(esw->dev)) {
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
+	if (mlx5_ecpf_vport_exists(peer_dev)) {
+		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF);
 		MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF);
 		flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
 					   spec, &flow_act, &dest, 1);
@@ -1238,36 +1237,39 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 			err = PTR_ERR(flow);
 			goto add_ecpf_flow_err;
 		}
-		flows[vport->index] = flow;
+		flows[peer_vport->index] = flow;
 	}
 
-	mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) {
-		esw_set_peer_miss_rule_source_port(esw,
-						   peer_dev->priv.eswitch,
-						   spec, vport->vport);
+	if (mlx5_esw_host_functions_enabled(esw->dev)) {
+		mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport,
+					   mlx5_core_max_vfs(peer_dev)) {
+			esw_set_peer_miss_rule_source_port(esw, peer_esw,
+							   spec,
+							   peer_vport->vport);
 
-		flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
-					   spec, &flow_act, &dest, 1);
-		if (IS_ERR(flow)) {
-			err = PTR_ERR(flow);
-			goto add_vf_flow_err;
+			flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
+						   spec, &flow_act, &dest, 1);
+			if (IS_ERR(flow)) {
+				err = PTR_ERR(flow);
+				goto add_vf_flow_err;
+			}
+			flows[peer_vport->index] = flow;
 		}
-		flows[vport->index] = flow;
 	}
 
-	if (mlx5_core_ec_sriov_enabled(esw->dev)) {
-		mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) {
-			if (i >= mlx5_core_max_ec_vfs(peer_dev))
-				break;
-			esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch,
-							   spec, vport->vport);
+	if (mlx5_core_ec_sriov_enabled(peer_dev)) {
+		mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport,
+					      mlx5_core_max_ec_vfs(peer_dev)) {
+			esw_set_peer_miss_rule_source_port(esw, peer_esw,
+							   spec,
+							   peer_vport->vport);
 			flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
 						   spec, &flow_act, &dest, 1);
 			if (IS_ERR(flow)) {
 				err = PTR_ERR(flow);
 				goto add_ec_vf_flow_err;
 			}
-			flows[vport->index] = flow;
+			flows[peer_vport->index] = flow;
 		}
 	}
 
@@ -1284,25 +1286,29 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	return 0;
 
 add_ec_vf_flow_err:
-	mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) {
-		if (!flows[vport->index])
+	mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport,
+				      mlx5_core_max_ec_vfs(peer_dev)) {
+		if (!flows[peer_vport->index])
 			continue;
-		mlx5_del_flow_rules(flows[vport->index]);
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 add_vf_flow_err:
-	mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) {
-		if (!flows[vport->index])
+	mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport,
+				   mlx5_core_max_vfs(peer_dev)) {
+		if (!flows[peer_vport->index])
 			continue;
-		mlx5_del_flow_rules(flows[vport->index]);
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
-	if (mlx5_ecpf_vport_exists(esw->dev)) {
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
-		mlx5_del_flow_rules(flows[vport->index]);
+	if (mlx5_ecpf_vport_exists(peer_dev)) {
+		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF);
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 add_ecpf_flow_err:
-	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
-		mlx5_del_flow_rules(flows[vport->index]);
+
+	if (mlx5_core_is_ecpf_esw_manager(peer_dev) &&
+	    mlx5_esw_host_functions_enabled(peer_dev)) {
+		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF);
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 add_pf_flow_err:
 	esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err);
@@ -1315,37 +1321,34 @@ alloc_flows_err:
 static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 					struct mlx5_core_dev *peer_dev)
 {
+	struct mlx5_eswitch *peer_esw = peer_dev->priv.eswitch;
 	u16 peer_index = mlx5_get_dev_index(peer_dev);
 	struct mlx5_flow_handle **flows;
-	struct mlx5_vport *vport;
+	struct mlx5_vport *peer_vport;
 	unsigned long i;
 
 	flows = esw->fdb_table.offloads.peer_miss_rules[peer_index];
 	if (!flows)
 		return;
 
-	if (mlx5_core_ec_sriov_enabled(esw->dev)) {
-		mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) {
-			/* The flow for a particular vport could be NULL if the other ECPF
-			 * has fewer or no VFs enabled
-			 */
-			if (!flows[vport->index])
-				continue;
-			mlx5_del_flow_rules(flows[vport->index]);
-		}
+	if (mlx5_core_ec_sriov_enabled(peer_dev)) {
+		mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport,
+					      mlx5_core_max_ec_vfs(peer_dev))
+			mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 
-	mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev))
-		mlx5_del_flow_rules(flows[vport->index]);
+	mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport,
+				   mlx5_core_max_vfs(peer_dev))
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 
-	if (mlx5_ecpf_vport_exists(esw->dev)) {
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
-		mlx5_del_flow_rules(flows[vport->index]);
+	if (mlx5_ecpf_vport_exists(peer_dev)) {
+		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF);
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 
-	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
-		mlx5_del_flow_rules(flows[vport->index]);
+	if (mlx5_core_is_ecpf_esw_manager(peer_dev)) {
+		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF);
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 
 	kvfree(flows);
@@ -1574,6 +1577,7 @@ esw_chains_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *miss_fdb)
 	attr.max_grp_num = esw->params.large_group_num;
 	attr.default_ft = miss_fdb;
 	attr.mapping = esw->offloads.reg_c0_obj_pool;
+	attr.fs_base_prio = FDB_BYPASS_PATH;
 
 	chains = mlx5_chains_create(dev, &attr);
 	if (IS_ERR(chains)) {
@@ -1975,7 +1979,6 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	/* Holds true only as long as DMFS is the default */
 	mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns,
 				     MLX5_FLOW_STEERING_MODE_DMFS);
-	atomic64_set(&esw->user_count, 0);
 }
 
 static int esw_get_nr_ft_offloads_steering_src_ports(struct mlx5_eswitch *esw)
@@ -2156,7 +2159,9 @@ mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, u16 vport,
 	flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec,
 					&flow_act, dest, 1);
 	if (IS_ERR(flow_rule)) {
-		esw_warn(esw->dev, "fs offloads: Failed to add vport rx rule err %ld\n", PTR_ERR(flow_rule));
+		esw_warn(esw->dev,
+			 "fs offloads: Failed to add vport rx rule err %pe\n",
+			 flow_rule);
 		goto out;
 	}
 
@@ -2175,8 +2180,8 @@ static int esw_create_vport_rx_drop_rule(struct mlx5_eswitch *esw)
 					&flow_act, NULL, 0);
 	if (IS_ERR(flow_rule)) {
 		esw_warn(esw->dev,
-			 "fs offloads: Failed to add vport rx drop rule err %ld\n",
-			 PTR_ERR(flow_rule));
+			 "fs offloads: Failed to add vport rx drop rule err %pe\n",
+			 flow_rule);
 		return PTR_ERR(flow_rule);
 	}
 
@@ -2351,6 +2356,131 @@ static void esw_mode_change(struct mlx5_eswitch *esw, u16 mode)
 	mlx5_devcom_comp_unlock(esw->dev->priv.hca_devcom_comp);
 }
 
+static void mlx5_esw_fdb_drop_destroy(struct mlx5_eswitch *esw)
+{
+	if (!esw->fdb_table.offloads.drop_root)
+		return;
+
+	esw_debug(esw->dev, "Destroying FDB drop root table %#x fc %#x\n",
+		  esw->fdb_table.offloads.drop_root->id,
+		  esw->fdb_table.offloads.drop_root_fc->id);
+	mlx5_del_flow_rules(esw->fdb_table.offloads.drop_root_rule);
+	/* Don't free flow counter here, can be reused on a later activation */
+	mlx5_destroy_flow_table(esw->fdb_table.offloads.drop_root);
+	esw->fdb_table.offloads.drop_root_rule = NULL;
+	esw->fdb_table.offloads.drop_root = NULL;
+}
+
+static int mlx5_esw_fdb_drop_create(struct mlx5_eswitch *esw)
+{
+	struct mlx5_flow_destination drop_fc_dst = {};
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_flow_destination *dst = NULL;
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_namespace *root_ns;
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *flow_rule;
+	struct mlx5_flow_table *table;
+	int err = 0, dst_num = 0;
+
+	if (esw->fdb_table.offloads.drop_root)
+		return 0;
+
+	root_ns = esw->fdb_table.offloads.ns;
+
+	ft_attr.prio = FDB_DROP_ROOT;
+	ft_attr.max_fte = 1;
+	ft_attr.autogroup.max_num_groups = 1;
+	table = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr);
+	if (IS_ERR(table)) {
+		esw_warn(dev, "Failed to create fdb drop root table, err %pe\n",
+			 table);
+		return PTR_ERR(table);
+	}
+
+	/* Drop FC reusable, create once on first deactivation of FDB */
+	if (!esw->fdb_table.offloads.drop_root_fc) {
+		struct mlx5_fc *counter = mlx5_fc_create(dev, 0);
+
+		err = PTR_ERR_OR_ZERO(counter);
+		if (err)
+			esw_warn(esw->dev, "create fdb drop fc err %d\n", err);
+		else
+			esw->fdb_table.offloads.drop_root_fc = counter;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
+
+	if (esw->fdb_table.offloads.drop_root_fc) {
+		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+		drop_fc_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+		drop_fc_dst.counter = esw->fdb_table.offloads.drop_root_fc;
+		dst = &drop_fc_dst;
+		dst_num++;
+	}
+
+	flow_rule = mlx5_add_flow_rules(table, NULL, &flow_act, dst, dst_num);
+	err = PTR_ERR_OR_ZERO(flow_rule);
+	if (err) {
+		esw_warn(esw->dev,
+			 "fs offloads: Failed to add vport rx drop rule err %d\n",
+			 err);
+		goto err_flow_rule;
+	}
+
+	esw->fdb_table.offloads.drop_root = table;
+	esw->fdb_table.offloads.drop_root_rule = flow_rule;
+	esw_debug(esw->dev, "Created FDB drop root table %#x fc %#x\n",
+		  table->id, dst ? dst->counter->id : 0);
+	return 0;
+
+err_flow_rule:
+	/* no need to free drop fc, esw_offloads_steering_cleanup will do it */
+	mlx5_destroy_flow_table(table);
+	return err;
+}
+
+static void mlx5_esw_fdb_active(struct mlx5_eswitch *esw)
+{
+	struct mlx5_vport *vport;
+	unsigned long i;
+
+	mlx5_esw_fdb_drop_destroy(esw);
+	mlx5_mpfs_enable(esw->dev);
+
+	mlx5_esw_for_each_vf_vport(esw, i, vport, U16_MAX) {
+		if (!vport->adjacent)
+			continue;
+		esw_debug(esw->dev, "Connecting vport %d to eswitch\n",
+			  vport->vport);
+		mlx5_esw_adj_vport_modify(esw->dev, vport->vport, true);
+	}
+
+	esw->offloads_inactive = false;
+	esw_warn(esw->dev, "MPFS/FDB active\n");
+}
+
+static void mlx5_esw_fdb_inactive(struct mlx5_eswitch *esw)
+{
+	struct mlx5_vport *vport;
+	unsigned long i;
+
+	mlx5_mpfs_disable(esw->dev);
+	mlx5_esw_fdb_drop_create(esw);
+
+	mlx5_esw_for_each_vf_vport(esw, i, vport, U16_MAX) {
+		if (!vport->adjacent)
+			continue;
+		esw_debug(esw->dev, "Disconnecting vport %u from eswitch\n",
+			  vport->vport);
+
+		mlx5_esw_adj_vport_modify(esw->dev, vport->vport, false);
+	}
+
+	esw->offloads_inactive = true;
+	esw_warn(esw->dev, "MPFS/FDB inactive\n");
+}
+
 static int esw_offloads_start(struct mlx5_eswitch *esw,
 			      struct netlink_ext_ack *extack)
 {
@@ -2375,7 +2505,20 @@ static int esw_offloads_start(struct mlx5_eswitch *esw,
 	return 0;
 }
 
-static int mlx5_esw_offloads_rep_init(struct mlx5_eswitch *esw, const struct mlx5_vport *vport)
+void mlx5_esw_offloads_rep_remove(struct mlx5_eswitch *esw,
+				  const struct mlx5_vport *vport)
+{
+	struct mlx5_eswitch_rep *rep = xa_load(&esw->offloads.vport_reps,
+					       vport->vport);
+
+	if (!rep)
+		return;
+	xa_erase(&esw->offloads.vport_reps, vport->vport);
+	kfree(rep);
+}
+
+int mlx5_esw_offloads_rep_add(struct mlx5_eswitch *esw,
+			      const struct mlx5_vport *vport)
 {
 	struct mlx5_eswitch_rep *rep;
 	int rep_type;
@@ -2387,9 +2530,19 @@ static int mlx5_esw_offloads_rep_init(struct mlx5_eswitch *esw, const struct mlx
 
 	rep->vport = vport->vport;
 	rep->vport_index = vport->index;
-	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
-		atomic_set(&rep->rep_data[rep_type].state, REP_UNREGISTERED);
-
+	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
+		if (!esw->offloads.rep_ops[rep_type]) {
+			atomic_set(&rep->rep_data[rep_type].state,
+				   REP_UNREGISTERED);
+			continue;
+		}
+		/* Dynamic/delegated vports add their representors after
+		 * mlx5_eswitch_register_vport_reps, so mark them as registered
+		 * for them to be loaded later with the others.
+		 */
+		rep->esw = esw;
+		atomic_set(&rep->rep_data[rep_type].state, REP_REGISTERED);
+	}
 	err = xa_insert(&esw->offloads.vport_reps, rep->vport, rep, GFP_KERNEL);
 	if (err)
 		goto insert_err;
@@ -2427,7 +2580,7 @@ static int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 	xa_init(&esw->offloads.vport_reps);
 
 	mlx5_esw_for_each_vport(esw, i, vport) {
-		err = mlx5_esw_offloads_rep_init(esw, vport);
+		err = mlx5_esw_offloads_rep_add(esw, vport);
 		if (err)
 			goto err;
 	}
@@ -2465,7 +2618,8 @@ done:
 }
 
 static int esw_port_metadata_get(struct devlink *devlink, u32 id,
-				 struct devlink_param_gset_ctx *ctx)
+				 struct devlink_param_gset_ctx *ctx,
+				 struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 
@@ -2831,9 +2985,9 @@ static int esw_set_master_egress_rule(struct mlx5_core_dev *master,
 	if (IS_ERR(vport))
 		return PTR_ERR(vport);
 
-	egress_ns = mlx5_get_flow_vport_acl_namespace(master,
-						      MLX5_FLOW_NAMESPACE_ESW_EGRESS,
-						      vport->index);
+	egress_ns = mlx5_get_flow_vport_namespace(master,
+						  MLX5_FLOW_NAMESPACE_ESW_EGRESS,
+						  vport->index);
 	if (!egress_ns)
 		return -EINVAL;
 
@@ -3078,7 +3232,8 @@ err_out:
 	return err;
 }
 
-void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, u64 key)
+void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw,
+				   const struct mlx5_devcom_match_attr *attr)
 {
 	int i;
 
@@ -3097,10 +3252,10 @@ void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, u64 key)
 	esw->num_peers = 0;
 	esw->devcom = mlx5_devcom_register_component(esw->dev->priv.devc,
 						     MLX5_DEVCOM_ESW_OFFLOADS,
-						     key,
+						     attr,
 						     mlx5_esw_offloads_devcom_event,
 						     esw);
-	if (IS_ERR(esw->devcom))
+	if (!esw->devcom)
 		return;
 
 	mlx5_devcom_send_event(esw->devcom,
@@ -3111,7 +3266,7 @@ void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, u64 key)
 
 void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw)
 {
-	if (IS_ERR_OR_NULL(esw->devcom))
+	if (!esw->devcom)
 		return;
 
 	mlx5_devcom_send_event(esw->devcom,
@@ -3410,6 +3565,10 @@ create_indir_err:
 
 static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
 {
+	mlx5_esw_fdb_drop_destroy(esw);
+	if (esw->fdb_table.offloads.drop_root_fc)
+		mlx5_fc_destroy(esw->dev, esw->fdb_table.offloads.drop_root_fc);
+	esw->fdb_table.offloads.drop_root_fc = NULL;
 	esw_destroy_vport_rx_drop_rule(esw);
 	esw_destroy_vport_rx_drop_group(esw);
 	esw_destroy_vport_rx_group(esw);
@@ -3528,14 +3687,19 @@ bool mlx5_esw_offloads_controller_valid(const struct mlx5_eswitch *esw, u32 cont
 
 int esw_offloads_enable(struct mlx5_eswitch *esw)
 {
+	u8 mapping_id[MLX5_SW_IMAGE_GUID_MAX_BYTES];
 	struct mapping_ctx *reg_c0_obj_pool;
 	struct mlx5_vport *vport;
 	unsigned long i;
-	u64 mapping_id;
+	u8 id_len;
 	int err;
 
 	mutex_init(&esw->offloads.termtbl_mutex);
-	mlx5_rdma_enable_roce(esw->dev);
+	mlx5_esw_adjacent_vhcas_setup(esw);
+
+	err = mlx5_rdma_enable_roce(esw->dev);
+	if (err)
+		goto err_roce;
 
 	err = mlx5_esw_host_number_init(esw);
 	if (err)
@@ -3549,9 +3713,10 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	if (err)
 		goto err_vport_metadata;
 
-	mapping_id = mlx5_query_nic_system_image_guid(esw->dev);
+	mlx5_query_nic_sw_system_image_guid(esw->dev, mapping_id, &id_len);
 
-	reg_c0_obj_pool = mapping_create_for_id(mapping_id, MAPPING_TYPE_CHAIN,
+	reg_c0_obj_pool = mapping_create_for_id(mapping_id, id_len,
+						MAPPING_TYPE_CHAIN,
 						sizeof(struct mlx5_mapped_obj),
 						ESW_REG_C0_USER_DATA_METADATA_MASK,
 						true);
@@ -3566,6 +3731,11 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	if (err)
 		goto err_steering_init;
 
+	if (esw->offloads_inactive)
+		mlx5_esw_fdb_inactive(esw);
+	else
+		mlx5_esw_fdb_active(esw);
+
 	/* Representor will control the vport link state */
 	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
 		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_DOWN;
@@ -3596,6 +3766,8 @@ err_vport_metadata:
 	esw_offloads_metadata_uninit(esw);
 err_metadata:
 	mlx5_rdma_disable_roce(esw->dev);
+err_roce:
+	mlx5_esw_adjacent_vhcas_cleanup(esw);
 	mutex_destroy(&esw->offloads.termtbl_mutex);
 	return err;
 }
@@ -3629,6 +3801,10 @@ void esw_offloads_disable(struct mlx5_eswitch *esw)
 	mapping_destroy(esw->offloads.reg_c0_obj_pool);
 	esw_offloads_metadata_uninit(esw);
 	mlx5_rdma_disable_roce(esw->dev);
+	mlx5_esw_adjacent_vhcas_cleanup(esw);
+	/* must be done after vhcas cleanup to avoid adjacent vports connect */
+	if (esw->offloads_inactive)
+		mlx5_esw_fdb_active(esw); /* legacy mode always active */
 	mutex_destroy(&esw->offloads.termtbl_mutex);
 }
 
@@ -3639,6 +3815,7 @@ static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
 		*mlx5_mode = MLX5_ESWITCH_LEGACY;
 		break;
 	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+	case DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE:
 		*mlx5_mode = MLX5_ESWITCH_OFFLOADS;
 		break;
 	default:
@@ -3648,14 +3825,17 @@ static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
 	return 0;
 }
 
-static int esw_mode_to_devlink(u16 mlx5_mode, u16 *mode)
+static int esw_mode_to_devlink(struct mlx5_eswitch *esw, u16 *mode)
 {
-	switch (mlx5_mode) {
+	switch (esw->mode) {
 	case MLX5_ESWITCH_LEGACY:
 		*mode = DEVLINK_ESWITCH_MODE_LEGACY;
 		break;
 	case MLX5_ESWITCH_OFFLOADS:
-		*mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
+		if (esw->offloads_inactive)
+			*mode = DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE;
+		else
+			*mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
 		break;
 	default:
 		return -EINVAL;
@@ -3738,6 +3918,68 @@ void mlx5_eswitch_unblock_mode(struct mlx5_core_dev *dev)
 	up_write(&esw->mode_lock);
 }
 
+/* Returns false only when uplink netdev exists and its netns is different from
+ * devlink's netns. True for all others so entering switchdev mode is allowed.
+ */
+static bool mlx5_devlink_netdev_netns_immutable_set(struct devlink *devlink,
+						    bool immutable)
+{
+	struct mlx5_core_dev *mdev = devlink_priv(devlink);
+	struct net_device *netdev;
+	bool ret;
+
+	netdev = mlx5_uplink_netdev_get(mdev);
+	if (!netdev)
+		return true;
+
+	rtnl_lock();
+	netdev->netns_immutable = immutable;
+	ret = net_eq(dev_net(netdev), devlink_net(devlink));
+	rtnl_unlock();
+
+	mlx5_uplink_netdev_put(mdev, netdev);
+	return ret;
+}
+
+/* Returns true when only changing between active and inactive switchdev mode */
+static bool mlx5_devlink_switchdev_active_mode_change(struct mlx5_eswitch *esw,
+						      u16 devlink_mode)
+{
+	/* current mode is not switchdev */
+	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
+		return false;
+
+	/* new mode is not switchdev */
+	if (devlink_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV &&
+	    devlink_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE)
+		return false;
+
+	/* already inactive: no change in current state */
+	if (devlink_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE &&
+	    esw->offloads_inactive)
+		return false;
+
+	/* already active: no change in current state */
+	if (devlink_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV &&
+	    !esw->offloads_inactive)
+		return false;
+
+	down_write(&esw->mode_lock);
+	esw->offloads_inactive = !esw->offloads_inactive;
+	esw->eswitch_operation_in_progress = true;
+	up_write(&esw->mode_lock);
+
+	if (esw->offloads_inactive)
+		mlx5_esw_fdb_inactive(esw);
+	else
+		mlx5_esw_fdb_active(esw);
+
+	down_write(&esw->mode_lock);
+	esw->eswitch_operation_in_progress = false;
+	up_write(&esw->mode_lock);
+	return true;
+}
+
 int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 				  struct netlink_ext_ack *extack)
 {
@@ -3752,12 +3994,16 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 	if (esw_mode_from_devlink(mode, &mlx5_mode))
 		return -EINVAL;
 
-	if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && mlx5_get_sd(esw->dev)) {
+	if (mlx5_mode == MLX5_ESWITCH_OFFLOADS && mlx5_get_sd(esw->dev)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can't change E-Switch mode to switchdev when multi-PF netdev (Socket Direct) is configured.");
 		return -EPERM;
 	}
 
+	/* Avoid try_lock, active/inactive mode change is not restricted */
+	if (mlx5_devlink_switchdev_active_mode_change(esw, mode))
+		return 0;
+
 	mlx5_lag_disable_change(esw->dev);
 	err = mlx5_esw_try_lock(esw);
 	if (err < 0) {
@@ -3780,22 +4026,36 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 	esw->eswitch_operation_in_progress = true;
 	up_write(&esw->mode_lock);
 
+	if (mlx5_mode == MLX5_ESWITCH_OFFLOADS &&
+	    !mlx5_devlink_netdev_netns_immutable_set(devlink, true)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Can't change E-Switch mode to switchdev when netdev net namespace has diverged from the devlink's.");
+		err = -EINVAL;
+		goto skip;
+	}
+
+	if (mlx5_mode == MLX5_ESWITCH_LEGACY)
+		esw->dev->priv.flags |= MLX5_PRIV_FLAGS_SWITCH_LEGACY;
 	mlx5_eswitch_disable_locked(esw);
-	if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) {
+	if (mlx5_mode == MLX5_ESWITCH_OFFLOADS) {
 		if (mlx5_devlink_trap_get_num_active(esw->dev)) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Can't change mode while devlink traps are active");
 			err = -EOPNOTSUPP;
 			goto skip;
 		}
+		esw->offloads_inactive =
+			(mode == DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE);
 		err = esw_offloads_start(esw, extack);
-	} else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) {
+	} else if (mlx5_mode == MLX5_ESWITCH_LEGACY) {
 		err = esw_offloads_stop(esw, extack);
 	} else {
 		err = -EINVAL;
 	}
 
 skip:
+	if (mlx5_mode == MLX5_ESWITCH_OFFLOADS && err)
+		mlx5_devlink_netdev_netns_immutable_set(devlink, false);
 	down_write(&esw->mode_lock);
 	esw->eswitch_operation_in_progress = false;
 unlock:
@@ -3813,7 +4073,7 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	return esw_mode_to_devlink(esw->mode, mode);
+	return esw_mode_to_devlink(esw, mode);
 }
 
 static int mlx5_esw_vports_inline_set(struct mlx5_eswitch *esw, u8 mlx5_mode,
@@ -3935,23 +4195,25 @@ int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
 	return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
 }
 
-bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev)
+bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev, bool from_fdb)
 {
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
+	enum devlink_eswitch_encap_mode encap;
+	bool allow_tunnel = false;
 
 	if (!mlx5_esw_allowed(esw))
 		return true;
 
 	down_write(&esw->mode_lock);
-	if (esw->mode != MLX5_ESWITCH_LEGACY &&
-	    esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) {
-		up_write(&esw->mode_lock);
-		return false;
+	encap = esw->offloads.encap;
+	if (esw->mode == MLX5_ESWITCH_LEGACY ||
+	    (encap == DEVLINK_ESWITCH_ENCAP_MODE_NONE && !from_fdb)) {
+		allow_tunnel = true;
+		esw->offloads.num_block_encap++;
 	}
-
-	esw->offloads.num_block_encap++;
 	up_write(&esw->mode_lock);
-	return true;
+
+	return allow_tunnel;
 }
 
 void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev)
@@ -4056,7 +4318,8 @@ mlx5_eswitch_vport_has_rep(const struct mlx5_eswitch *esw, u16 vport_num)
 {
 	/* Currently, only ECPF based device has representor for host PF. */
 	if (vport_num == MLX5_VPORT_PF &&
-	    !mlx5_core_is_ecpf_esw_manager(esw->dev))
+	    (!mlx5_core_is_ecpf_esw_manager(esw->dev) ||
+	     !mlx5_esw_host_functions_enabled(esw->dev)))
 		return false;
 
 	if (vport_num == MLX5_VPORT_ECPF &&
@@ -4158,48 +4421,28 @@ u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw,
 }
 EXPORT_SYMBOL(mlx5_eswitch_get_vport_metadata_for_match);
 
-static int mlx5_esw_query_vport_vhca_id(struct mlx5_eswitch *esw, u16 vport_num, u16 *vhca_id)
-{
-	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
-	void *query_ctx;
-	void *hca_caps;
-	int err;
-
-	*vhca_id = 0;
-
-	query_ctx = kzalloc(query_out_sz, GFP_KERNEL);
-	if (!query_ctx)
-		return -ENOMEM;
-
-	err = mlx5_vport_get_other_func_general_cap(esw->dev, vport_num, query_ctx);
-	if (err)
-		goto out_free;
-
-	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
-	*vhca_id = MLX5_GET(cmd_hca_cap, hca_caps, vhca_id);
-
-out_free:
-	kfree(query_ctx);
-	return err;
-}
-
-int mlx5_esw_vport_vhca_id_set(struct mlx5_eswitch *esw, u16 vport_num)
+int mlx5_esw_vport_vhca_id_map(struct mlx5_eswitch *esw,
+			       struct mlx5_vport *vport)
 {
 	u16 *old_entry, *vhca_map_entry, vhca_id;
-	int err;
 
-	err = mlx5_esw_query_vport_vhca_id(esw, vport_num, &vhca_id);
-	if (err) {
-		esw_warn(esw->dev, "Getting vhca_id for vport failed (vport=%u,err=%d)\n",
-			 vport_num, err);
-		return err;
+	if (WARN_ONCE(MLX5_VPORT_INVAL_VHCA_ID(vport),
+		      "vport %d vhca_id is not set", vport->vport)) {
+		int err;
+
+		err = mlx5_vport_get_vhca_id(vport->dev, vport->vport,
+					     &vhca_id);
+		if (err)
+			return err;
+		vport->vhca_id = vhca_id;
 	}
 
+	vhca_id = vport->vhca_id;
 	vhca_map_entry = kmalloc(sizeof(*vhca_map_entry), GFP_KERNEL);
 	if (!vhca_map_entry)
 		return -ENOMEM;
 
-	*vhca_map_entry = vport_num;
+	*vhca_map_entry = vport->vport;
 	old_entry = xa_store(&esw->offloads.vhca_map, vhca_id, vhca_map_entry, GFP_KERNEL);
 	if (xa_is_err(old_entry)) {
 		kfree(vhca_map_entry);
@@ -4209,17 +4452,12 @@ int mlx5_esw_vport_vhca_id_set(struct mlx5_eswitch *esw, u16 vport_num)
 	return 0;
 }
 
-void mlx5_esw_vport_vhca_id_clear(struct mlx5_eswitch *esw, u16 vport_num)
+void mlx5_esw_vport_vhca_id_unmap(struct mlx5_eswitch *esw,
+				  struct mlx5_vport *vport)
 {
-	u16 *vhca_map_entry, vhca_id;
-	int err;
+	u16 *vhca_map_entry;
 
-	err = mlx5_esw_query_vport_vhca_id(esw, vport_num, &vhca_id);
-	if (err)
-		esw_warn(esw->dev, "Getting vhca_id for vport failed (vport=%hu,err=%d)\n",
-			 vport_num, err);
-
-	vhca_map_entry = xa_erase(&esw->offloads.vhca_map, vhca_id);
+	vhca_map_entry = xa_erase(&esw->offloads.vhca_map, vport->vhca_id);
 	kfree(vhca_map_entry);
 }
 
@@ -4254,6 +4492,9 @@ int mlx5_devlink_port_fn_hw_addr_get(struct devlink_port *port,
 	struct mlx5_vport *vport = mlx5_devlink_port_vport_get(port);
 
 	mutex_lock(&esw->state_lock);
+
+	mlx5_query_nic_vport_mac_address(esw->dev, vport->vport, true,
+					 vport->info.mac);
 	ether_addr_copy(hw_addr, vport->info.mac);
 	*hw_addr_len = ETH_ALEN;
 	mutex_unlock(&esw->state_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index d91ea53eb394..01c5f5990f9a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -6,6 +6,7 @@
 #include "mlx5_core.h"
 #include "lib/eq.h"
 #include "lib/events.h"
+#include "hwmon.h"
 
 struct mlx5_event_nb {
 	struct mlx5_nb  nb;
@@ -153,21 +154,50 @@ static int any_notifier(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+#if IS_ENABLED(CONFIG_HWMON)
+static void print_sensor_names_in_bit_set(struct mlx5_core_dev *dev, struct mlx5_hwmon *hwmon,
+					  u64 bit_set, int bit_set_offset)
+{
+	unsigned long *bit_set_ptr = (unsigned long *)&bit_set;
+	int num_bits = sizeof(bit_set) * BITS_PER_BYTE;
+	int i;
+
+	for_each_set_bit(i, bit_set_ptr, num_bits) {
+		const char *sensor_name = hwmon_get_sensor_name(hwmon, i + bit_set_offset);
+
+		mlx5_core_warn(dev, "Sensor name[%d]: %s\n", i + bit_set_offset, sensor_name);
+	}
+}
+#endif /* CONFIG_HWMON */
+
 /* type == MLX5_EVENT_TYPE_TEMP_WARN_EVENT */
 static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
 {
 	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
 	struct mlx5_events   *events   = event_nb->ctx;
+	struct mlx5_core_dev *dev      = events->dev;
 	struct mlx5_eqe      *eqe      = data;
 	u64 value_lsb;
 	u64 value_msb;
 
 	value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
+	/* bit 1-63 are not supported for NICs,
+	 * hence read only bit 0 (asic) from lsb.
+	 */
+	value_lsb &= 0x1;
 	value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
 
-	mlx5_core_warn(events->dev,
-		       "High temperature on sensors with bit set %llx %llx",
-		       value_msb, value_lsb);
+	if (net_ratelimit()) {
+		mlx5_core_warn(dev, "High temperature on sensors with bit set %#llx %#llx.\n",
+			       value_msb, value_lsb);
+#if IS_ENABLED(CONFIG_HWMON)
+		if (dev->hwmon) {
+			print_sensor_names_in_bit_set(dev, dev->hwmon, value_lsb, 0);
+			print_sensor_names_in_bit_set(dev, dev->hwmon, value_msb,
+						      sizeof(value_lsb) * BITS_PER_BYTE);
+		}
+#endif
+	}
 
 	return NOTIFY_OK;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index c4de6bf8d1b6..ccef64fb40b6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -421,6 +421,13 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 	__be64 *pas;
 	u32 i;
 
+	conn->cq.mcq.cqe_sz     = 64;
+	conn->cq.mcq.set_ci_db  = conn->cq.wq_ctrl.db.db;
+	conn->cq.mcq.arm_db     = conn->cq.wq_ctrl.db.db + 1;
+	*conn->cq.mcq.set_ci_db = 0;
+	conn->cq.mcq.vector     = 0;
+	conn->cq.mcq.comp       = mlx5_fpga_conn_cq_complete;
+
 	cq_size = roundup_pow_of_two(cq_size);
 	MLX5_SET(cqc, temp_cqc, log_cq_size, ilog2(cq_size));
 
@@ -468,16 +475,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 	if (err)
 		goto err_cqwq;
 
-	conn->cq.mcq.cqe_sz     = 64;
-	conn->cq.mcq.set_ci_db  = conn->cq.wq_ctrl.db.db;
-	conn->cq.mcq.arm_db     = conn->cq.wq_ctrl.db.db + 1;
-	*conn->cq.mcq.set_ci_db = 0;
-	*conn->cq.mcq.arm_db    = 0;
-	conn->cq.mcq.vector     = 0;
-	conn->cq.mcq.comp       = mlx5_fpga_conn_cq_complete;
-	conn->cq.mcq.uar        = fdev->conn_res.uar;
 	tasklet_setup(&conn->cq.tasklet, mlx5_fpga_conn_cq_tasklet);
-
 	mlx5_fpga_dbg(fdev, "Created CQ #0x%x\n", conn->cq.mcq.cqn);
 
 	goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
index e5c1012921d2..1ec61164e6b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
@@ -211,7 +211,7 @@ int mlx5_fpga_device_start(struct mlx5_core_dev *mdev)
 	max_num_qps = MLX5_CAP_FPGA(mdev, shell_caps.max_num_qps);
 	if (!max_num_qps) {
 		mlx5_fpga_err(fdev, "FPGA reports 0 QPs in SHELL_CAPS\n");
-		err = -ENOTSUPP;
+		err = -EOPNOTSUPP;
 		goto out;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 6bf0aade69d7..ced747bef641 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -217,7 +217,8 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
 	int err;
 
 	if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) &&
-	    underlay_qpn == 0)
+	    underlay_qpn == 0 &&
+	    (ft->type != FS_FT_RDMA_RX && ft->type != FS_FT_RDMA_TX))
 		return 0;
 
 	if (ft->type == FS_FT_FDB &&
@@ -238,6 +239,10 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
 	MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport);
 	MLX5_SET(set_flow_table_root_in, in, other_vport,
 		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
+	MLX5_SET(set_flow_table_root_in, in, eswitch_owner_vhca_id,
+		 ft->esw_owner_vhca_id);
+	MLX5_SET(set_flow_table_root_in, in, other_eswitch,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH));
 
 	err = mlx5_cmd_exec_in(dev, set_flow_table_root, in);
 	if (!err &&
@@ -301,6 +306,10 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
 	MLX5_SET(create_flow_table_in, in, vport_number, ft->vport);
 	MLX5_SET(create_flow_table_in, in, other_vport,
 		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
+	MLX5_SET(create_flow_table_in, in, eswitch_owner_vhca_id,
+		 ft->esw_owner_vhca_id);
+	MLX5_SET(create_flow_table_in, in, other_eswitch,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH));
 
 	MLX5_SET(create_flow_table_in, in, flow_table_context.decap_en,
 		 en_decap);
@@ -359,6 +368,10 @@ static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns,
 	MLX5_SET(destroy_flow_table_in, in, vport_number, ft->vport);
 	MLX5_SET(destroy_flow_table_in, in, other_vport,
 		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
+	MLX5_SET(destroy_flow_table_in, in, eswitch_owner_vhca_id,
+		 ft->esw_owner_vhca_id);
+	MLX5_SET(destroy_flow_table_in, in, other_eswitch,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH));
 
 	err = mlx5_cmd_exec_in(dev, destroy_flow_table, in);
 	if (!err)
@@ -393,6 +406,10 @@ static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns,
 		MLX5_SET(modify_flow_table_in, in, vport_number, ft->vport);
 		MLX5_SET(modify_flow_table_in, in, other_vport,
 			 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
+		MLX5_SET(modify_flow_table_in, in, eswitch_owner_vhca_id,
+			 ft->esw_owner_vhca_id);
+		MLX5_SET(modify_flow_table_in, in, other_eswitch,
+			 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH));
 		MLX5_SET(modify_flow_table_in, in, modify_field_select,
 			 MLX5_MODIFY_FLOW_TABLE_MISS_TABLE_ID);
 		if (next_ft) {
@@ -428,6 +445,10 @@ static int mlx5_cmd_create_flow_group(struct mlx5_flow_root_namespace *ns,
 	MLX5_SET(create_flow_group_in, in, vport_number, ft->vport);
 	MLX5_SET(create_flow_group_in, in, other_vport,
 		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
+	MLX5_SET(create_flow_group_in, in, eswitch_owner_vhca_id,
+		 ft->esw_owner_vhca_id);
+	MLX5_SET(create_flow_group_in, in, other_eswitch,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH));
 	err = mlx5_cmd_exec_inout(dev, create_flow_group, in, out);
 	if (!err)
 		fg->id = MLX5_GET(create_flow_group_out, out,
@@ -450,6 +471,10 @@ static int mlx5_cmd_destroy_flow_group(struct mlx5_flow_root_namespace *ns,
 	MLX5_SET(destroy_flow_group_in, in, vport_number, ft->vport);
 	MLX5_SET(destroy_flow_group_in, in, other_vport,
 		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
+	MLX5_SET(destroy_flow_group_in, in, eswitch_owner_vhca_id,
+		 ft->esw_owner_vhca_id);
+	MLX5_SET(destroy_flow_group_in, in, other_eswitch,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH));
 	return mlx5_cmd_exec_in(dev, destroy_flow_group, in);
 }
 
@@ -526,7 +551,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	struct mlx5_flow_rule *dst;
 	void *in_flow_context, *vlan;
 	void *in_match_value;
-	int reformat_id = 0;
+	u32 reformat_id = 0;
 	unsigned int inlen;
 	int dst_cnt_size;
 	u32 *in, action;
@@ -558,6 +583,9 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(set_fte_in, in, vport_number, ft->vport);
 	MLX5_SET(set_fte_in, in, other_vport,
 		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
+	MLX5_SET(set_fte_in, in, eswitch_owner_vhca_id, ft->esw_owner_vhca_id);
+	MLX5_SET(set_fte_in, in, other_eswitch,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH));
 
 	in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context);
 	MLX5_SET(flow_context, in_flow_context, group_id, group_id);
@@ -579,23 +607,21 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(flow_context, in_flow_context, action, action);
 
 	if (!extended_dest && fte->act_dests.action.pkt_reformat) {
-		struct mlx5_pkt_reformat *pkt_reformat = fte->act_dests.action.pkt_reformat;
-
-		if (pkt_reformat->owner == MLX5_FLOW_RESOURCE_OWNER_SW) {
-			reformat_id = mlx5_fs_dr_action_get_pkt_reformat_id(pkt_reformat);
-			if (reformat_id < 0) {
-				mlx5_core_err(dev,
-					      "Unsupported SW-owned pkt_reformat type (%d) in FW-owned table\n",
-					      pkt_reformat->reformat_type);
-				err = reformat_id;
-				goto err_out;
-			}
-		} else {
-			reformat_id = fte->act_dests.action.pkt_reformat->id;
+		struct mlx5_pkt_reformat *pkt_reformat =
+			fte->act_dests.action.pkt_reformat;
+
+		err = mlx5_fs_get_packet_reformat_id(pkt_reformat,
+						     &reformat_id);
+		if (err) {
+			mlx5_core_err(dev,
+				      "Unsupported pkt_reformat type (%d)\n",
+				      pkt_reformat->reformat_type);
+			goto err_out;
 		}
 	}
 
-	MLX5_SET(flow_context, in_flow_context, packet_reformat_id, (u32)reformat_id);
+	MLX5_SET(flow_context, in_flow_context, packet_reformat_id,
+		 reformat_id);
 
 	if (fte->act_dests.action.modify_hdr) {
 		if (fte->act_dests.action.modify_hdr->owner == MLX5_FLOW_RESOURCE_OWNER_SW) {
@@ -789,6 +815,10 @@ static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns,
 	MLX5_SET(delete_fte_in, in, vport_number, ft->vport);
 	MLX5_SET(delete_fte_in, in, other_vport,
 		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
+	MLX5_SET(delete_fte_in, in, eswitch_owner_vhca_id,
+		 ft->esw_owner_vhca_id);
+	MLX5_SET(delete_fte_in, in, other_eswitch,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH));
 
 	return mlx5_cmd_exec_in(dev, delete_fte, in);
 }
@@ -1141,6 +1171,8 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ
 	case FS_FT_RDMA_RX:
 	case FS_FT_RDMA_TX:
 	case FS_FT_PORT_SEL:
+	case FS_FT_RDMA_TRANSPORT_RX:
+	case FS_FT_RDMA_TRANSPORT_TX:
 		return mlx5_fs_cmd_get_fw_cmds();
 	default:
 		return mlx5_fs_cmd_get_stub_cmds();
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index ae1a5705b26d..0a6031a64c6f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -113,13 +113,16 @@
 #define ETHTOOL_PRIO_NUM_LEVELS 1
 #define ETHTOOL_NUM_PRIOS 11
 #define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS)
-/* Promiscuous, Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy,
- * {IPsec RoCE MPV,Alias table},IPsec RoCE policy
+/* Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy,
+ * IPsec policy miss, {IPsec RoCE MPV,Alias table},IPsec RoCE policy
  */
 #define KERNEL_NIC_PRIO_NUM_LEVELS 11
 #define KERNEL_NIC_NUM_PRIOS 1
-/* One more level for tc */
-#define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 1)
+/* One more level for tc, and one more for promisc */
+#define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 2)
+
+#define KERNEL_NIC_PROMISC_NUM_PRIOS 1
+#define KERNEL_NIC_PROMISC_NUM_LEVELS 1
 
 #define KERNEL_NIC_TC_NUM_PRIOS  1
 #define KERNEL_NIC_TC_NUM_LEVELS 3
@@ -187,6 +190,8 @@ static struct init_tree_node {
 			   ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
 				  ADD_MULTIPLE_PRIO(KERNEL_NIC_TC_NUM_PRIOS,
 						    KERNEL_NIC_TC_NUM_LEVELS),
+				  ADD_MULTIPLE_PRIO(KERNEL_NIC_PROMISC_NUM_PRIOS,
+						    KERNEL_NIC_PROMISC_NUM_LEVELS),
 				  ADD_MULTIPLE_PRIO(KERNEL_NIC_NUM_PRIOS,
 						    KERNEL_NIC_PRIO_NUM_LEVELS))),
 		  ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, FS_CHAINING_CAPS,
@@ -658,7 +663,7 @@ static void del_sw_hw_rule(struct fs_node *node)
 			BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) |
 			BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
 		fte->act_dests.action.action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT;
-		mlx5_fc_local_destroy(rule->dest_attr.counter);
+		mlx5_fc_local_put(rule->dest_attr.counter);
 		goto out;
 	}
 
@@ -934,10 +939,10 @@ static struct mlx5_flow_group *alloc_insert_flow_group(struct mlx5_flow_table *f
 	return fg;
 }
 
-static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport,
-						enum fs_flow_table_type table_type,
-						enum fs_flow_table_op_mod op_mod,
-						u32 flags)
+static struct mlx5_flow_table *
+alloc_flow_table(struct mlx5_flow_table_attr *ft_attr, u16 vport,
+		 enum fs_flow_table_type table_type,
+		 enum fs_flow_table_op_mod op_mod)
 {
 	struct mlx5_flow_table *ft;
 	int ret;
@@ -952,12 +957,13 @@ static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport,
 		return ERR_PTR(ret);
 	}
 
-	ft->level = level;
+	ft->level = ft_attr->level;
 	ft->node.type = FS_TYPE_FLOW_TABLE;
 	ft->op_mod = op_mod;
 	ft->type = table_type;
 	ft->vport = vport;
-	ft->flags = flags;
+	ft->esw_owner_vhca_id = ft_attr->esw_owner_vhca_id;
+	ft->flags = ft_attr->flags;
 	INIT_LIST_HEAD(&ft->fwd_rules);
 	mutex_init(&ft->lock);
 
@@ -1365,10 +1371,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 	/* The level is related to the
 	 * priority level range.
 	 */
-	ft = alloc_flow_table(ft_attr->level,
-			      vport,
-			      root->table_type,
-			      op_mod, ft_attr->flags);
+	ft = alloc_flow_table(ft_attr, vport, root->table_type, op_mod);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto unlock_root;
@@ -1456,7 +1459,7 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
 	struct mlx5_flow_table *ft;
 	int autogroups_max_fte;
 
-	ft = mlx5_create_flow_table(ns, ft_attr);
+	ft = mlx5_create_vport_flow_table(ns, ft_attr, ft_attr->vport);
 	if (IS_ERR(ft))
 		return ft;
 
@@ -1830,14 +1833,35 @@ static int create_auto_flow_group(struct mlx5_flow_table *ft,
 	return err;
 }
 
+int mlx5_fs_get_packet_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				   u32 *id)
+{
+	switch (pkt_reformat->owner) {
+	case MLX5_FLOW_RESOURCE_OWNER_FW:
+		*id = pkt_reformat->id;
+		return 0;
+	case MLX5_FLOW_RESOURCE_OWNER_SW:
+		return mlx5_fs_dr_action_get_pkt_reformat_id(pkt_reformat, id);
+	case MLX5_FLOW_RESOURCE_OWNER_HWS:
+		return mlx5_fs_hws_action_get_pkt_reformat_id(pkt_reformat, id);
+	default:
+		return -EINVAL;
+	}
+}
+
 static bool mlx5_pkt_reformat_cmp(struct mlx5_pkt_reformat *p1,
 				  struct mlx5_pkt_reformat *p2)
 {
-	return p1->owner == p2->owner &&
-		(p1->owner == MLX5_FLOW_RESOURCE_OWNER_FW ?
-		 p1->id == p2->id :
-		 mlx5_fs_dr_action_get_pkt_reformat_id(p1) ==
-		 mlx5_fs_dr_action_get_pkt_reformat_id(p2));
+	int err1, err2;
+	u32 id1, id2;
+
+	if (p1->owner != p2->owner)
+		return false;
+
+	err1 = mlx5_fs_get_packet_reformat_id(p1, &id1);
+	err2 = mlx5_fs_get_packet_reformat_id(p2, &id2);
+
+	return !err1 && !err2 && id1 == id2;
 }
 
 static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
@@ -2207,6 +2231,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 	struct mlx5_flow_handle *rule;
 	struct match_list *iter;
 	bool take_write = false;
+	bool try_again = false;
 	struct fs_fte *fte;
 	u64  version = 0;
 	int err;
@@ -2271,6 +2296,7 @@ skip_search:
 		nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
 
 		if (!g->node.active) {
+			try_again = true;
 			up_write_ref_node(&g->node, false);
 			continue;
 		}
@@ -2292,7 +2318,8 @@ skip_search:
 			tree_put_node(&fte->node, false);
 		return rule;
 	}
-	rule = ERR_PTR(-ENOENT);
+	err = try_again ? -EAGAIN : -ENOENT;
+	rule = ERR_PTR(err);
 out:
 	kmem_cache_free(steering->ftes_cache, fte);
 	return rule;
@@ -2716,6 +2743,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 		break;
 	case MLX5_FLOW_NAMESPACE_RDMA_TX:
 		root_ns = steering->rdma_tx_root_ns;
+		prio = RDMA_TX_BYPASS_PRIO;
 		break;
 	case MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS:
 		root_ns = steering->rdma_rx_root_ns;
@@ -2763,36 +2791,56 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL(mlx5_get_flow_namespace);
 
-struct mlx5_flow_namespace *mlx5_get_flow_vport_acl_namespace(struct mlx5_core_dev *dev,
-							      enum mlx5_flow_namespace_type type,
-							      int vport)
+struct mlx5_vport_acl_root_ns {
+	u16 vport_idx;
+	struct mlx5_flow_root_namespace *root_ns;
+};
+
+struct mlx5_flow_namespace *
+mlx5_get_flow_vport_namespace(struct mlx5_core_dev *dev,
+			      enum mlx5_flow_namespace_type type, int vport_idx)
 {
 	struct mlx5_flow_steering *steering = dev->priv.steering;
+	struct mlx5_vport_acl_root_ns *vport_ns;
 
 	if (!steering)
 		return NULL;
 
 	switch (type) {
 	case MLX5_FLOW_NAMESPACE_ESW_EGRESS:
-		if (vport >= steering->esw_egress_acl_vports)
-			return NULL;
-		if (steering->esw_egress_root_ns &&
-		    steering->esw_egress_root_ns[vport])
-			return &steering->esw_egress_root_ns[vport]->ns;
+		vport_ns = xa_load(&steering->esw_egress_root_ns, vport_idx);
+		if (vport_ns)
+			return &vport_ns->root_ns->ns;
 		else
 			return NULL;
 	case MLX5_FLOW_NAMESPACE_ESW_INGRESS:
-		if (vport >= steering->esw_ingress_acl_vports)
+		vport_ns = xa_load(&steering->esw_ingress_root_ns, vport_idx);
+		if (vport_ns)
+			return &vport_ns->root_ns->ns;
+		else
+			return NULL;
+	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX:
+		if (vport_idx >= steering->rdma_transport_rx_vports)
+			return NULL;
+		if (steering->rdma_transport_rx_root_ns &&
+		    steering->rdma_transport_rx_root_ns[vport_idx])
+			return &steering->rdma_transport_rx_root_ns[vport_idx]->ns;
+		else
+			return NULL;
+	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX:
+		if (vport_idx >= steering->rdma_transport_tx_vports)
 			return NULL;
-		if (steering->esw_ingress_root_ns &&
-		    steering->esw_ingress_root_ns[vport])
-			return &steering->esw_ingress_root_ns[vport]->ns;
+
+		if (steering->rdma_transport_tx_root_ns &&
+		    steering->rdma_transport_tx_root_ns[vport_idx])
+			return &steering->rdma_transport_tx_root_ns[vport_idx]->ns;
 		else
 			return NULL;
 	default:
 		return NULL;
 	}
 }
+EXPORT_SYMBOL(mlx5_get_flow_vport_namespace);
 
 static struct fs_prio *_fs_create_prio(struct mlx5_flow_namespace *ns,
 				       unsigned int prio,
@@ -3198,6 +3246,211 @@ out_err:
 	return err;
 }
 
+static int
+init_rdma_transport_rx_root_ns_one(struct mlx5_flow_steering *steering,
+				   int vport_idx)
+{
+	struct mlx5_flow_root_namespace *root_ns;
+	struct fs_prio *prio;
+	int ret;
+	int i;
+
+	steering->rdma_transport_rx_root_ns[vport_idx] =
+		create_root_ns(steering, FS_FT_RDMA_TRANSPORT_RX);
+	if (!steering->rdma_transport_rx_root_ns[vport_idx])
+		return -ENOMEM;
+
+	root_ns = steering->rdma_transport_rx_root_ns[vport_idx];
+
+	for (i = 0; i < MLX5_RDMA_TRANSPORT_BYPASS_PRIO; i++) {
+		prio = fs_create_prio(&root_ns->ns, i, 1);
+		if (IS_ERR(prio)) {
+			ret = PTR_ERR(prio);
+			goto err;
+		}
+	}
+	set_prio_attrs(root_ns);
+	return 0;
+
+err:
+	cleanup_root_ns(root_ns);
+	return ret;
+}
+
+static int
+init_rdma_transport_tx_root_ns_one(struct mlx5_flow_steering *steering,
+				   int vport_idx)
+{
+	struct mlx5_flow_root_namespace *root_ns;
+	struct fs_prio *prio;
+	int ret;
+	int i;
+
+	steering->rdma_transport_tx_root_ns[vport_idx] =
+		create_root_ns(steering, FS_FT_RDMA_TRANSPORT_TX);
+	if (!steering->rdma_transport_tx_root_ns[vport_idx])
+		return -ENOMEM;
+
+	root_ns = steering->rdma_transport_tx_root_ns[vport_idx];
+
+	for (i = 0; i < MLX5_RDMA_TRANSPORT_BYPASS_PRIO; i++) {
+		prio = fs_create_prio(&root_ns->ns, i, 1);
+		if (IS_ERR(prio)) {
+			ret = PTR_ERR(prio);
+			goto err;
+		}
+	}
+	set_prio_attrs(root_ns);
+	return 0;
+
+err:
+	cleanup_root_ns(root_ns);
+	return ret;
+}
+
+static bool mlx5_fs_ns_is_empty(struct mlx5_flow_namespace *ns)
+{
+	struct fs_prio *iter_prio;
+
+	fs_for_each_prio(iter_prio, ns) {
+		if (iter_prio->num_ft)
+			return false;
+	}
+
+	return true;
+}
+
+int mlx5_fs_set_root_dev(struct mlx5_core_dev *dev,
+			 struct mlx5_core_dev *new_dev,
+			 enum fs_flow_table_type table_type)
+{
+	struct mlx5_flow_root_namespace	**root;
+	int total_vports;
+	int i;
+
+	switch (table_type) {
+	case FS_FT_RDMA_TRANSPORT_TX:
+		root = dev->priv.steering->rdma_transport_tx_root_ns;
+		total_vports = dev->priv.steering->rdma_transport_tx_vports;
+		break;
+	case FS_FT_RDMA_TRANSPORT_RX:
+		root = dev->priv.steering->rdma_transport_rx_root_ns;
+		total_vports = dev->priv.steering->rdma_transport_rx_vports;
+		break;
+	default:
+		WARN_ON_ONCE(true);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < total_vports; i++) {
+		mutex_lock(&root[i]->chain_lock);
+		if (!mlx5_fs_ns_is_empty(&root[i]->ns)) {
+			mutex_unlock(&root[i]->chain_lock);
+			goto err;
+		}
+		root[i]->dev = new_dev;
+		mutex_unlock(&root[i]->chain_lock);
+	}
+	return 0;
+err:
+	while (i--) {
+		mutex_lock(&root[i]->chain_lock);
+		root[i]->dev = dev;
+		mutex_unlock(&root[i]->chain_lock);
+	}
+	/* If you hit this error try destroying all flow tables and try again */
+	mlx5_core_err(dev, "Failed to set root device for RDMA TRANSPORT\n");
+	return -EINVAL;
+}
+EXPORT_SYMBOL(mlx5_fs_set_root_dev);
+
+static int init_rdma_transport_rx_root_ns(struct mlx5_flow_steering *steering)
+{
+	struct mlx5_core_dev *dev = steering->dev;
+	int total_vports;
+	int err;
+	int i;
+
+	/* In case eswitch not supported and working in legacy mode */
+	total_vports = mlx5_eswitch_get_total_vports(dev) ?: 1;
+
+	steering->rdma_transport_rx_root_ns =
+			kcalloc(total_vports,
+				sizeof(*steering->rdma_transport_rx_root_ns),
+				GFP_KERNEL);
+	if (!steering->rdma_transport_rx_root_ns)
+		return -ENOMEM;
+
+	for (i = 0; i < total_vports; i++) {
+		err = init_rdma_transport_rx_root_ns_one(steering, i);
+		if (err)
+			goto cleanup_root_ns;
+	}
+	steering->rdma_transport_rx_vports = total_vports;
+	return 0;
+
+cleanup_root_ns:
+	while (i--)
+		cleanup_root_ns(steering->rdma_transport_rx_root_ns[i]);
+	kfree(steering->rdma_transport_rx_root_ns);
+	steering->rdma_transport_rx_root_ns = NULL;
+	return err;
+}
+
+static int init_rdma_transport_tx_root_ns(struct mlx5_flow_steering *steering)
+{
+	struct mlx5_core_dev *dev = steering->dev;
+	int total_vports;
+	int err;
+	int i;
+
+	/* In case eswitch not supported and working in legacy mode */
+	total_vports = mlx5_eswitch_get_total_vports(dev) ?: 1;
+
+	steering->rdma_transport_tx_root_ns =
+			kcalloc(total_vports,
+				sizeof(*steering->rdma_transport_tx_root_ns),
+				GFP_KERNEL);
+	if (!steering->rdma_transport_tx_root_ns)
+		return -ENOMEM;
+
+	for (i = 0; i < total_vports; i++) {
+		err = init_rdma_transport_tx_root_ns_one(steering, i);
+		if (err)
+			goto cleanup_root_ns;
+	}
+	steering->rdma_transport_tx_vports = total_vports;
+	return 0;
+
+cleanup_root_ns:
+	while (i--)
+		cleanup_root_ns(steering->rdma_transport_tx_root_ns[i]);
+	kfree(steering->rdma_transport_tx_root_ns);
+	steering->rdma_transport_tx_root_ns = NULL;
+	return err;
+}
+
+static void cleanup_rdma_transport_roots_ns(struct mlx5_flow_steering *steering)
+{
+	int i;
+
+	if (steering->rdma_transport_rx_root_ns) {
+		for (i = 0; i < steering->rdma_transport_rx_vports; i++)
+			cleanup_root_ns(steering->rdma_transport_rx_root_ns[i]);
+
+		kfree(steering->rdma_transport_rx_root_ns);
+		steering->rdma_transport_rx_root_ns = NULL;
+	}
+
+	if (steering->rdma_transport_tx_root_ns) {
+		for (i = 0; i < steering->rdma_transport_tx_vports; i++)
+			cleanup_root_ns(steering->rdma_transport_tx_root_ns[i]);
+
+		kfree(steering->rdma_transport_tx_root_ns);
+		steering->rdma_transport_tx_root_ns = NULL;
+	}
+}
+
 /* FT and tc chains are stored in the same array so we can re-use the
  * mlx5_get_fdb_sub_ns() and tc api for FT chains.
  * When creating a new ns for each chain store it in the first available slot.
@@ -3321,6 +3574,11 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 	if (!steering->fdb_root_ns)
 		return -ENOMEM;
 
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_DROP_ROOT, 1);
+	err = PTR_ERR_OR_ZERO(maj_prio);
+	if (err)
+		goto out_err;
+
 	err = create_fdb_bypass(steering);
 	if (err)
 		goto out_err;
@@ -3378,118 +3636,102 @@ out_err:
 	return err;
 }
 
-static int init_egress_acl_root_ns(struct mlx5_flow_steering *steering, int vport)
+static void
+mlx5_fs_remove_vport_acl_root_ns(struct xarray *esw_acl_root_ns, u16 vport_idx)
 {
-	struct fs_prio *prio;
+	struct mlx5_vport_acl_root_ns *vport_ns;
 
-	steering->esw_egress_root_ns[vport] = create_root_ns(steering, FS_FT_ESW_EGRESS_ACL);
-	if (!steering->esw_egress_root_ns[vport])
-		return -ENOMEM;
-
-	/* create 1 prio*/
-	prio = fs_create_prio(&steering->esw_egress_root_ns[vport]->ns, 0, 1);
-	return PTR_ERR_OR_ZERO(prio);
+	vport_ns = xa_erase(esw_acl_root_ns, vport_idx);
+	if (vport_ns) {
+		cleanup_root_ns(vport_ns->root_ns);
+		kfree(vport_ns);
+	}
 }
 
-static int init_ingress_acl_root_ns(struct mlx5_flow_steering *steering, int vport)
+static int
+mlx5_fs_add_vport_acl_root_ns(struct mlx5_flow_steering *steering,
+			      struct xarray *esw_acl_root_ns,
+			      enum fs_flow_table_type table_type,
+			      u16 vport_idx)
 {
+	struct mlx5_vport_acl_root_ns *vport_ns;
 	struct fs_prio *prio;
+	int err;
 
-	steering->esw_ingress_root_ns[vport] = create_root_ns(steering, FS_FT_ESW_INGRESS_ACL);
-	if (!steering->esw_ingress_root_ns[vport])
-		return -ENOMEM;
+	/* sanity check, intended xarrays are used */
+	if (WARN_ON(esw_acl_root_ns != &steering->esw_egress_root_ns &&
+		    esw_acl_root_ns != &steering->esw_ingress_root_ns))
+		return -EINVAL;
 
-	/* create 1 prio*/
-	prio = fs_create_prio(&steering->esw_ingress_root_ns[vport]->ns, 0, 1);
-	return PTR_ERR_OR_ZERO(prio);
-}
+	if (table_type != FS_FT_ESW_EGRESS_ACL &&
+	    table_type != FS_FT_ESW_INGRESS_ACL) {
+		mlx5_core_err(steering->dev,
+			      "Invalid table type %d for egress/ingress ACLs\n",
+			      table_type);
+		return -EINVAL;
+	}
 
-int mlx5_fs_egress_acls_init(struct mlx5_core_dev *dev, int total_vports)
-{
-	struct mlx5_flow_steering *steering = dev->priv.steering;
-	int err;
-	int i;
+	if (xa_load(esw_acl_root_ns, vport_idx))
+		return -EEXIST;
 
-	steering->esw_egress_root_ns =
-			kcalloc(total_vports,
-				sizeof(*steering->esw_egress_root_ns),
-				GFP_KERNEL);
-	if (!steering->esw_egress_root_ns)
+	vport_ns = kzalloc(sizeof(*vport_ns), GFP_KERNEL);
+	if (!vport_ns)
 		return -ENOMEM;
 
-	for (i = 0; i < total_vports; i++) {
-		err = init_egress_acl_root_ns(steering, i);
-		if (err)
-			goto cleanup_root_ns;
+	vport_ns->root_ns = create_root_ns(steering, table_type);
+	if (!vport_ns->root_ns) {
+		err = -ENOMEM;
+		goto kfree_vport_ns;
 	}
-	steering->esw_egress_acl_vports = total_vports;
+
+	/* create 1 prio*/
+	prio = fs_create_prio(&vport_ns->root_ns->ns, 0, 1);
+	if (IS_ERR(prio)) {
+		err = PTR_ERR(prio);
+		goto cleanup_root_ns;
+	}
+
+	vport_ns->vport_idx = vport_idx;
+	err = xa_insert(esw_acl_root_ns, vport_idx, vport_ns, GFP_KERNEL);
+	if (err)
+		goto cleanup_root_ns;
 	return 0;
 
 cleanup_root_ns:
-	for (i--; i >= 0; i--)
-		cleanup_root_ns(steering->esw_egress_root_ns[i]);
-	kfree(steering->esw_egress_root_ns);
-	steering->esw_egress_root_ns = NULL;
+	cleanup_root_ns(vport_ns->root_ns);
+kfree_vport_ns:
+	kfree(vport_ns);
 	return err;
 }
 
-void mlx5_fs_egress_acls_cleanup(struct mlx5_core_dev *dev)
+int mlx5_fs_vport_egress_acl_ns_add(struct mlx5_flow_steering *steering,
+				    u16 vport_idx)
 {
-	struct mlx5_flow_steering *steering = dev->priv.steering;
-	int i;
-
-	if (!steering->esw_egress_root_ns)
-		return;
-
-	for (i = 0; i < steering->esw_egress_acl_vports; i++)
-		cleanup_root_ns(steering->esw_egress_root_ns[i]);
-
-	kfree(steering->esw_egress_root_ns);
-	steering->esw_egress_root_ns = NULL;
+	return mlx5_fs_add_vport_acl_root_ns(steering,
+					     &steering->esw_egress_root_ns,
+					     FS_FT_ESW_EGRESS_ACL, vport_idx);
 }
 
-int mlx5_fs_ingress_acls_init(struct mlx5_core_dev *dev, int total_vports)
+int mlx5_fs_vport_ingress_acl_ns_add(struct mlx5_flow_steering *steering,
+				     u16 vport_idx)
 {
-	struct mlx5_flow_steering *steering = dev->priv.steering;
-	int err;
-	int i;
-
-	steering->esw_ingress_root_ns =
-			kcalloc(total_vports,
-				sizeof(*steering->esw_ingress_root_ns),
-				GFP_KERNEL);
-	if (!steering->esw_ingress_root_ns)
-		return -ENOMEM;
-
-	for (i = 0; i < total_vports; i++) {
-		err = init_ingress_acl_root_ns(steering, i);
-		if (err)
-			goto cleanup_root_ns;
-	}
-	steering->esw_ingress_acl_vports = total_vports;
-	return 0;
-
-cleanup_root_ns:
-	for (i--; i >= 0; i--)
-		cleanup_root_ns(steering->esw_ingress_root_ns[i]);
-	kfree(steering->esw_ingress_root_ns);
-	steering->esw_ingress_root_ns = NULL;
-	return err;
+	return mlx5_fs_add_vport_acl_root_ns(steering,
+					     &steering->esw_ingress_root_ns,
+					     FS_FT_ESW_INGRESS_ACL, vport_idx);
 }
 
-void mlx5_fs_ingress_acls_cleanup(struct mlx5_core_dev *dev)
+void mlx5_fs_vport_egress_acl_ns_remove(struct mlx5_flow_steering *steering,
+					int vport_idx)
 {
-	struct mlx5_flow_steering *steering = dev->priv.steering;
-	int i;
-
-	if (!steering->esw_ingress_root_ns)
-		return;
-
-	for (i = 0; i < steering->esw_ingress_acl_vports; i++)
-		cleanup_root_ns(steering->esw_ingress_root_ns[i]);
+	mlx5_fs_remove_vport_acl_root_ns(&steering->esw_egress_root_ns,
+					 vport_idx);
+}
 
-	kfree(steering->esw_ingress_root_ns);
-	steering->esw_ingress_root_ns = NULL;
+void mlx5_fs_vport_ingress_acl_ns_remove(struct mlx5_flow_steering *steering,
+					 int vport_idx)
+{
+	mlx5_fs_remove_vport_acl_root_ns(&steering->esw_ingress_root_ns,
+					 vport_idx);
 }
 
 u32 mlx5_fs_get_capabilities(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type)
@@ -3535,35 +3777,41 @@ static int mlx5_fs_mode_validate(struct devlink *devlink, u32 id,
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	char *value = val.vstr;
-	int err = 0;
+	u8 eswitch_mode;
 
-	if (!strcmp(value, "dmfs")) {
+	eswitch_mode = mlx5_eswitch_mode(dev);
+	if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Changing fs mode is not supported when eswitch offloads enabled.");
+		return -EOPNOTSUPP;
+	}
+
+	if (!strcmp(value, "dmfs"))
 		return 0;
-	} else if (!strcmp(value, "smfs")) {
-		u8 eswitch_mode;
-		bool smfs_cap;
 
-		eswitch_mode = mlx5_eswitch_mode(dev);
-		smfs_cap = mlx5_fs_dr_is_supported(dev);
+	if (!strcmp(value, "smfs")) {
+		bool smfs_cap = mlx5_fs_dr_is_supported(dev);
 
 		if (!smfs_cap) {
-			err = -EOPNOTSUPP;
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Software managed steering is not supported by current device");
+			return -EOPNOTSUPP;
 		}
+	} else if (!strcmp(value, "hmfs")) {
+		bool hmfs_cap = mlx5_fs_hws_is_supported(dev);
 
-		else if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) {
+		if (!hmfs_cap) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Software managed steering is not supported when eswitch offloads enabled.");
-			err = -EOPNOTSUPP;
+					   "Hardware steering is not supported by current device");
+			return -EOPNOTSUPP;
 		}
 	} else {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "Bad parameter: supported values are [\"dmfs\", \"smfs\"]");
-		err = -EINVAL;
+				   "Bad parameter: supported values are [\"dmfs\", \"smfs\", \"hmfs\"]");
+		return -EINVAL;
 	}
 
-	return err;
+	return 0;
 }
 
 static int mlx5_fs_mode_set(struct devlink *devlink, u32 id,
@@ -3575,6 +3823,8 @@ static int mlx5_fs_mode_set(struct devlink *devlink, u32 id,
 
 	if (!strcmp(ctx->val.vstr, "smfs"))
 		mode = MLX5_FLOW_STEERING_MODE_SMFS;
+	else if (!strcmp(ctx->val.vstr, "hmfs"))
+		mode = MLX5_FLOW_STEERING_MODE_HMFS;
 	else
 		mode = MLX5_FLOW_STEERING_MODE_DMFS;
 	dev->priv.steering->mode = mode;
@@ -3583,14 +3833,22 @@ static int mlx5_fs_mode_set(struct devlink *devlink, u32 id,
 }
 
 static int mlx5_fs_mode_get(struct devlink *devlink, u32 id,
-			    struct devlink_param_gset_ctx *ctx)
+			    struct devlink_param_gset_ctx *ctx,
+			    struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 
-	if (dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS)
+	switch (dev->priv.steering->mode) {
+	case MLX5_FLOW_STEERING_MODE_SMFS:
 		strscpy(ctx->val.vstr, "smfs", sizeof(ctx->val.vstr));
-	else
+		break;
+	case MLX5_FLOW_STEERING_MODE_HMFS:
+		strscpy(ctx->val.vstr, "hmfs", sizeof(ctx->val.vstr));
+		break;
+	default:
 		strscpy(ctx->val.vstr, "dmfs", sizeof(ctx->val.vstr));
+	}
+
 	return 0;
 }
 
@@ -3606,6 +3864,11 @@ void mlx5_fs_core_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_flow_steering *steering = dev->priv.steering;
 
+	WARN_ON(!xa_empty(&steering->esw_egress_root_ns));
+	WARN_ON(!xa_empty(&steering->esw_ingress_root_ns));
+	xa_destroy(&steering->esw_egress_root_ns);
+	xa_destroy(&steering->esw_ingress_root_ns);
+
 	cleanup_root_ns(steering->root_ns);
 	cleanup_fdb_root_ns(steering);
 	cleanup_root_ns(steering->port_sel_root_ns);
@@ -3614,6 +3877,7 @@ void mlx5_fs_core_cleanup(struct mlx5_core_dev *dev)
 	cleanup_root_ns(steering->rdma_rx_root_ns);
 	cleanup_root_ns(steering->rdma_tx_root_ns);
 	cleanup_root_ns(steering->egress_root_ns);
+	cleanup_rdma_transport_roots_ns(steering);
 
 	devl_params_unregister(priv_to_devlink(dev), mlx5_fs_params,
 			       ARRAY_SIZE(mlx5_fs_params));
@@ -3665,8 +3929,7 @@ int mlx5_fs_core_init(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
-	if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) &&
-	    MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)) {
+	if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support)) {
 		err = init_rdma_rx_root_ns(steering);
 		if (err)
 			goto err;
@@ -3684,6 +3947,20 @@ int mlx5_fs_core_init(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
+	if (MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_RX(dev, ft_support)) {
+		err = init_rdma_transport_rx_root_ns(steering);
+		if (err)
+			goto err;
+	}
+
+	if (MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_TX(dev, ft_support)) {
+		err = init_rdma_transport_tx_root_ns(steering);
+		if (err)
+			goto err;
+	}
+
+	xa_init(&steering->esw_egress_root_ns);
+	xa_init(&steering->esw_ingress_root_ns);
 	return 0;
 
 err:
@@ -3727,6 +4004,8 @@ int mlx5_fs_core_alloc(struct mlx5_core_dev *dev)
 
 	if (mlx5_fs_dr_is_supported(dev))
 		steering->mode = MLX5_FLOW_STEERING_MODE_SMFS;
+	else if (mlx5_fs_hws_is_supported(dev))
+		steering->mode = MLX5_FLOW_STEERING_MODE_HMFS;
 	else
 		steering->mode = MLX5_FLOW_STEERING_MODE_DMFS;
 
@@ -3834,8 +4113,10 @@ mlx5_get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type
 	struct mlx5_flow_namespace *ns;
 
 	if (ns_type == MLX5_FLOW_NAMESPACE_ESW_EGRESS ||
-	    ns_type == MLX5_FLOW_NAMESPACE_ESW_INGRESS)
-		ns = mlx5_get_flow_vport_acl_namespace(dev, ns_type, 0);
+	    ns_type == MLX5_FLOW_NAMESPACE_ESW_INGRESS ||
+	    ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX ||
+	    ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX)
+		ns = mlx5_get_flow_vport_namespace(dev, ns_type, 0);
 	else
 		ns = mlx5_get_flow_namespace(dev, ns_type);
 	if (!ns)
@@ -4010,6 +4291,8 @@ int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns,
 
 	if (mode == MLX5_FLOW_STEERING_MODE_SMFS)
 		cmds = mlx5_fs_cmd_get_dr_cmds();
+	else if (mode == MLX5_FLOW_STEERING_MODE_HMFS)
+		cmds = mlx5_fs_cmd_get_hws_cmds();
 	else
 		cmds = mlx5_fs_cmd_get_fw_cmds();
 	if (!cmds)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index bad2df0715ec..1c6591425260 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -38,6 +38,7 @@
 #include <linux/rhashtable.h>
 #include <linux/llist.h>
 #include <steering/sws/fs_dr.h>
+#include <steering/hws/fs_hws.h>
 
 #define FDB_TC_MAX_CHAIN 3
 #define FDB_FT_CHAIN (FDB_TC_MAX_CHAIN + 1)
@@ -57,6 +58,7 @@ struct mlx5_flow_definer {
 enum mlx5_flow_resource_owner {
 	MLX5_FLOW_RESOURCE_OWNER_FW,
 	MLX5_FLOW_RESOURCE_OWNER_SW,
+	MLX5_FLOW_RESOURCE_OWNER_HWS,
 };
 
 struct mlx5_modify_hdr {
@@ -64,6 +66,7 @@ struct mlx5_modify_hdr {
 	enum mlx5_flow_resource_owner owner;
 	union {
 		struct mlx5_fs_dr_action fs_dr_action;
+		struct mlx5_fs_hws_action fs_hws_action;
 		u32 id;
 	};
 };
@@ -74,6 +77,7 @@ struct mlx5_pkt_reformat {
 	enum mlx5_flow_resource_owner owner;
 	union {
 		struct mlx5_fs_dr_action fs_dr_action;
+		struct mlx5_fs_hws_action fs_hws_action;
 		u32 id;
 	};
 };
@@ -99,22 +103,6 @@ enum fs_node_type {
 	FS_TYPE_FLOW_DEST
 };
 
-enum fs_flow_table_type {
-	FS_FT_NIC_RX          = 0x0,
-	FS_FT_NIC_TX          = 0x1,
-	FS_FT_ESW_EGRESS_ACL  = 0x2,
-	FS_FT_ESW_INGRESS_ACL = 0x3,
-	FS_FT_FDB             = 0X4,
-	FS_FT_SNIFFER_RX	= 0X5,
-	FS_FT_SNIFFER_TX	= 0X6,
-	FS_FT_RDMA_RX		= 0X7,
-	FS_FT_RDMA_TX		= 0X8,
-	FS_FT_PORT_SEL		= 0X9,
-	FS_FT_FDB_RX		= 0xa,
-	FS_FT_FDB_TX		= 0xb,
-	FS_FT_MAX_TYPE = FS_FT_FDB_TX,
-};
-
 enum fs_flow_table_op_mod {
 	FS_FT_OP_MOD_NORMAL,
 	FS_FT_OP_MOD_LAG_DEMUX,
@@ -126,7 +114,8 @@ enum fs_fte_status {
 
 enum mlx5_flow_steering_mode {
 	MLX5_FLOW_STEERING_MODE_DMFS,
-	MLX5_FLOW_STEERING_MODE_SMFS
+	MLX5_FLOW_STEERING_MODE_SMFS,
+	MLX5_FLOW_STEERING_MODE_HMFS,
 };
 
 enum mlx5_flow_steering_capabilty {
@@ -144,16 +133,18 @@ struct mlx5_flow_steering {
 	struct mlx5_flow_root_namespace *root_ns;
 	struct mlx5_flow_root_namespace *fdb_root_ns;
 	struct mlx5_flow_namespace	**fdb_sub_ns;
-	struct mlx5_flow_root_namespace **esw_egress_root_ns;
-	struct mlx5_flow_root_namespace **esw_ingress_root_ns;
+	struct xarray			esw_egress_root_ns;
+	struct xarray			esw_ingress_root_ns;
 	struct mlx5_flow_root_namespace	*sniffer_tx_root_ns;
 	struct mlx5_flow_root_namespace	*sniffer_rx_root_ns;
 	struct mlx5_flow_root_namespace	*rdma_rx_root_ns;
 	struct mlx5_flow_root_namespace	*rdma_tx_root_ns;
 	struct mlx5_flow_root_namespace	*egress_root_ns;
 	struct mlx5_flow_root_namespace	*port_sel_root_ns;
-	int esw_egress_acl_vports;
-	int esw_ingress_acl_vports;
+	struct mlx5_flow_root_namespace **rdma_transport_rx_root_ns;
+	struct mlx5_flow_root_namespace **rdma_transport_tx_root_ns;
+	int rdma_transport_rx_vports;
+	int rdma_transport_tx_vports;
 };
 
 struct fs_node {
@@ -190,9 +181,13 @@ struct mlx5_flow_handle {
 /* Type of children is mlx5_flow_group */
 struct mlx5_flow_table {
 	struct fs_node			node;
-	struct mlx5_fs_dr_table		fs_dr_table;
+	union {
+		struct mlx5_fs_dr_table		fs_dr_table;
+		struct mlx5_fs_hws_table	fs_hws_table;
+	};
 	u32				id;
 	u16				vport;
+	u16				esw_owner_vhca_id;
 	unsigned int			max_fte;
 	unsigned int			level;
 	enum fs_flow_table_type		type;
@@ -247,7 +242,10 @@ struct fs_fte_dup {
 /* Type of children is mlx5_flow_rule */
 struct fs_fte {
 	struct fs_node			node;
-	struct mlx5_fs_dr_rule		fs_dr_rule;
+	union {
+		struct mlx5_fs_dr_rule		fs_dr_rule;
+		struct mlx5_fs_hws_rule		fs_hws_rule;
+	};
 	u32				val[MLX5_ST_SZ_DW_MATCH_PARAM];
 	struct fs_fte_action		act_dests;
 	struct fs_fte_dup		*dup;
@@ -280,7 +278,10 @@ struct mlx5_flow_group_mask {
 /* Type of children is fs_fte */
 struct mlx5_flow_group {
 	struct fs_node			node;
-	struct mlx5_fs_dr_matcher	fs_dr_matcher;
+	union {
+		struct mlx5_fs_dr_matcher	fs_dr_matcher;
+		struct mlx5_fs_hws_matcher	fs_hws_matcher;
+	};
 	struct mlx5_flow_group_mask	mask;
 	u32				start_index;
 	u32				max_ftes;
@@ -293,7 +294,10 @@ struct mlx5_flow_group {
 struct mlx5_flow_root_namespace {
 	struct mlx5_flow_namespace	ns;
 	enum   mlx5_flow_steering_mode	mode;
-	struct mlx5_fs_dr_domain	fs_dr_domain;
+	union {
+		struct mlx5_fs_dr_domain	fs_dr_domain;
+		struct mlx5_fs_hws_context	fs_hws_context;
+	};
 	enum   fs_flow_table_type	table_type;
 	struct mlx5_core_dev		*dev;
 	struct mlx5_flow_table		*root_ft;
@@ -303,6 +307,37 @@ struct mlx5_flow_root_namespace {
 	const struct mlx5_flow_cmds	*cmds;
 };
 
+enum mlx5_fc_type {
+	MLX5_FC_TYPE_ACQUIRED = 0,
+	MLX5_FC_TYPE_LOCAL,
+};
+
+struct mlx5_fc_cache {
+	u64 packets;
+	u64 bytes;
+	u64 lastuse;
+};
+
+struct mlx5_fc {
+	u32 id;
+	bool aging;
+	enum mlx5_fc_type type;
+	struct mlx5_fc_bulk *bulk;
+	struct mlx5_fc_cache cache;
+	refcount_t fc_local_refcount;
+	/* last{packets,bytes} are used for calculating deltas since last reading. */
+	u64 lastpackets;
+	u64 lastbytes;
+};
+
+struct mlx5_fc_bulk {
+	struct mlx5_fs_bulk fs_bulk;
+	u32 base_id;
+	struct mlx5_fs_hws_data hws_data;
+	struct mlx5_fc fcs[];
+};
+
+u32 mlx5_fc_get_base_id(struct mlx5_fc *counter);
 int mlx5_init_fc_stats(struct mlx5_core_dev *dev);
 void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev);
 void mlx5_fc_queue_stats_work(struct mlx5_core_dev *dev,
@@ -325,15 +360,22 @@ void mlx5_fs_core_free(struct mlx5_core_dev *dev);
 int mlx5_fs_core_init(struct mlx5_core_dev *dev);
 void mlx5_fs_core_cleanup(struct mlx5_core_dev *dev);
 
-int mlx5_fs_egress_acls_init(struct mlx5_core_dev *dev, int total_vports);
-void mlx5_fs_egress_acls_cleanup(struct mlx5_core_dev *dev);
-int mlx5_fs_ingress_acls_init(struct mlx5_core_dev *dev, int total_vports);
-void mlx5_fs_ingress_acls_cleanup(struct mlx5_core_dev *dev);
+int mlx5_fs_vport_egress_acl_ns_add(struct mlx5_flow_steering *steering,
+				    u16 vport_idx);
+int mlx5_fs_vport_ingress_acl_ns_add(struct mlx5_flow_steering *steering,
+				     u16 vport_idx);
+void mlx5_fs_vport_egress_acl_ns_remove(struct mlx5_flow_steering *steering,
+					int vport_idx);
+void mlx5_fs_vport_ingress_acl_ns_remove(struct mlx5_flow_steering *steering,
+					 int vport_idx);
 
 u32 mlx5_fs_get_capabilities(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type);
 
 struct mlx5_flow_root_namespace *find_root(struct fs_node *node);
 
+int mlx5_fs_get_packet_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				   u32 *id);
+
 #define fs_get_obj(v, _node)  {v = container_of((_node), typeof(*v), node); }
 
 #define fs_list_for_each_entry(pos, root)		\
@@ -382,7 +424,9 @@ struct mlx5_flow_root_namespace *find_root(struct fs_node *node);
 	(type == FS_FT_PORT_SEL) ? MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) :      \
 	(type == FS_FT_FDB_RX) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :      \
 	(type == FS_FT_FDB_TX) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :      \
-	(BUILD_BUG_ON_ZERO(FS_FT_FDB_TX != FS_FT_MAX_TYPE))\
+	(type == FS_FT_RDMA_TRANSPORT_RX) ? MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_RX(mdev, cap) :      \
+	(type == FS_FT_RDMA_TRANSPORT_TX) ? MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_TX(mdev, cap) :      \
+	(BUILD_BUG_ON_ZERO(FS_FT_RDMA_TRANSPORT_TX != FS_FT_MAX_TYPE))\
 	)
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index d8e1c4ebd364..83001eda3884 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -44,28 +44,6 @@
 #define MLX5_FC_POOL_MAX_THRESHOLD BIT(18)
 #define MLX5_FC_POOL_USED_BUFF_RATIO 10
 
-enum mlx5_fc_type {
-	MLX5_FC_TYPE_ACQUIRED = 0,
-	MLX5_FC_TYPE_LOCAL,
-};
-
-struct mlx5_fc_cache {
-	u64 packets;
-	u64 bytes;
-	u64 lastuse;
-};
-
-struct mlx5_fc {
-	u32 id;
-	bool aging;
-	enum mlx5_fc_type type;
-	struct mlx5_fc_bulk *bulk;
-	struct mlx5_fc_cache cache;
-	/* last{packets,bytes} are used for calculating deltas since last reading. */
-	u64 lastpackets;
-	u64 lastbytes;
-};
-
 struct mlx5_fc_stats {
 	struct xarray counters;
 
@@ -434,13 +412,7 @@ void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev,
 					    fc_stats->sampling_interval);
 }
 
-/* Flow counter bluks */
-
-struct mlx5_fc_bulk {
-	struct mlx5_fs_bulk fs_bulk;
-	u32 base_id;
-	struct mlx5_fc fcs[];
-};
+/* Flow counter bulks */
 
 static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk,
 			 u32 id)
@@ -449,7 +421,13 @@ static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk,
 	counter->id = id;
 }
 
-static struct mlx5_fs_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev)
+u32 mlx5_fc_get_base_id(struct mlx5_fc *counter)
+{
+	return counter->bulk->base_id;
+}
+
+static struct mlx5_fs_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev,
+						void *pool_ctx)
 {
 	enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask;
 	struct mlx5_fc_bulk *fc_bulk;
@@ -473,6 +451,8 @@ static struct mlx5_fs_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev)
 	for (i = 0; i < bulk_len; i++)
 		mlx5_fc_init(&fc_bulk->fcs[i], fc_bulk, base_id + i);
 
+	refcount_set(&fc_bulk->hws_data.hws_action_refcount, 0);
+	mutex_init(&fc_bulk->hws_data.lock);
 	return &fc_bulk->fs_bulk;
 
 fs_bulk_cleanup:
@@ -518,7 +498,7 @@ static const struct mlx5_fs_pool_ops mlx5_fc_pool_ops = {
 static void
 mlx5_fc_pool_init(struct mlx5_fs_pool *fc_pool, struct mlx5_core_dev *dev)
 {
-	mlx5_fs_pool_init(fc_pool, dev, &mlx5_fc_pool_ops);
+	mlx5_fs_pool_init(fc_pool, dev, &mlx5_fc_pool_ops, NULL);
 }
 
 static void mlx5_fc_pool_cleanup(struct mlx5_fs_pool *fc_pool)
@@ -582,17 +562,36 @@ mlx5_fc_local_create(u32 counter_id, u32 offset, u32 bulk_size)
 	counter->id = counter_id;
 	fc_bulk->base_id = counter_id - offset;
 	fc_bulk->fs_bulk.bulk_len = bulk_size;
+	refcount_set(&fc_bulk->hws_data.hws_action_refcount, 0);
+	mutex_init(&fc_bulk->hws_data.lock);
 	counter->bulk = fc_bulk;
+	refcount_set(&counter->fc_local_refcount, 1);
 	return counter;
 }
 EXPORT_SYMBOL(mlx5_fc_local_create);
 
 void mlx5_fc_local_destroy(struct mlx5_fc *counter)
 {
-	if (!counter || counter->type != MLX5_FC_TYPE_LOCAL)
-		return;
-
 	kfree(counter->bulk);
 	kfree(counter);
 }
 EXPORT_SYMBOL(mlx5_fc_local_destroy);
+
+void mlx5_fc_local_get(struct mlx5_fc *counter)
+{
+	if (!counter || counter->type != MLX5_FC_TYPE_LOCAL)
+		return;
+
+	refcount_inc(&counter->fc_local_refcount);
+}
+
+void mlx5_fc_local_put(struct mlx5_fc *counter)
+{
+	if (!counter || counter->type != MLX5_FC_TYPE_LOCAL)
+		return;
+
+	if (!refcount_dec_and_test(&counter->fc_local_refcount))
+		return;
+
+	mlx5_fc_local_destroy(counter);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
index c14590acc772..f6abfd00d7e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
@@ -50,10 +50,12 @@ mlx5_ft_pool_get_avail_sz(struct mlx5_core_dev *dev, enum fs_flow_table_type tab
 	int i, found_i = -1;
 
 	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) {
-		if (dev->priv.ft_pool->ft_left[i] && FT_POOLS[i] >= desired_size &&
+		if (dev->priv.ft_pool->ft_left[i] &&
+		    (FT_POOLS[i] >= desired_size ||
+		     desired_size == MLX5_FS_MAX_POOL_SIZE) &&
 		    FT_POOLS[i] <= max_ft_size) {
 			found_i = i;
-			if (desired_size != POOL_NEXT_SIZE)
+			if (desired_size != MLX5_FS_MAX_POOL_SIZE)
 				break;
 		}
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
index 25f4274b372b..173e312db720 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
@@ -7,8 +7,6 @@
 #include <linux/mlx5/driver.h>
 #include "fs_core.h"
 
-#define POOL_NEXT_SIZE 0
-
 int mlx5_ft_pool_init(struct mlx5_core_dev *dev);
 void mlx5_ft_pool_destroy(struct mlx5_core_dev *dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c
index b891d7b9e3e0..f6c226664602 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c
@@ -56,11 +56,12 @@ static int mlx5_fs_bulk_release_index(struct mlx5_fs_bulk *fs_bulk, int index)
 }
 
 void mlx5_fs_pool_init(struct mlx5_fs_pool *pool, struct mlx5_core_dev *dev,
-		       const struct mlx5_fs_pool_ops *ops)
+		       const struct mlx5_fs_pool_ops *ops, void *pool_ctx)
 {
 	WARN_ON_ONCE(!ops || !ops->bulk_destroy || !ops->bulk_create ||
 		     !ops->update_threshold);
 	pool->dev = dev;
+	pool->pool_ctx = pool_ctx;
 	mutex_init(&pool->pool_lock);
 	INIT_LIST_HEAD(&pool->fully_used);
 	INIT_LIST_HEAD(&pool->partially_used);
@@ -91,7 +92,7 @@ mlx5_fs_pool_alloc_new_bulk(struct mlx5_fs_pool *fs_pool)
 	struct mlx5_core_dev *dev = fs_pool->dev;
 	struct mlx5_fs_bulk *new_bulk;
 
-	new_bulk = fs_pool->ops->bulk_create(dev);
+	new_bulk = fs_pool->ops->bulk_create(dev, fs_pool->pool_ctx);
 	if (new_bulk)
 		fs_pool->available_units += new_bulk->bulk_len;
 	fs_pool->ops->update_threshold(fs_pool);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h
index 3b149863260c..f04ec3107498 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h
@@ -21,7 +21,8 @@ struct mlx5_fs_pool;
 
 struct mlx5_fs_pool_ops {
 	int (*bulk_destroy)(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *bulk);
-	struct mlx5_fs_bulk * (*bulk_create)(struct mlx5_core_dev *dev);
+	struct mlx5_fs_bulk * (*bulk_create)(struct mlx5_core_dev *dev,
+					     void *pool_ctx);
 	void (*update_threshold)(struct mlx5_fs_pool *pool);
 };
 
@@ -44,7 +45,7 @@ void mlx5_fs_bulk_cleanup(struct mlx5_fs_bulk *fs_bulk);
 int mlx5_fs_bulk_get_free_amount(struct mlx5_fs_bulk *bulk);
 
 void mlx5_fs_pool_init(struct mlx5_fs_pool *pool, struct mlx5_core_dev *dev,
-		       const struct mlx5_fs_pool_ops *ops);
+		       const struct mlx5_fs_pool_ops *ops, void *pool_ctx);
 void mlx5_fs_pool_cleanup(struct mlx5_fs_pool *pool);
 int mlx5_fs_pool_acquire_index(struct mlx5_fs_pool *fs_pool,
 			       struct mlx5_fs_pool_index *pool_index);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 76ad46bf477d..eeb4437975f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -281,6 +281,25 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 			return err;
 	}
 
+	if (MLX5_CAP_GEN(dev, shampo)) {
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_SHAMPO, HCA_CAP_OPMOD_GET_CUR);
+		if (err)
+			return err;
+	}
+
+	if (MLX5_CAP_GEN(dev, adv_rdma)) {
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ADV_RDMA,
+					      HCA_CAP_OPMOD_GET_CUR);
+		if (err)
+			return err;
+	}
+
+	if (MLX5_CAP_GEN(dev, psp)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_PSP);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 566710d34a7b..2bceb42c98cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -6,13 +6,15 @@
 #include "fw_reset.h"
 #include "diag/fw_tracer.h"
 #include "lib/tout.h"
+#include "sf/sf.h"
 
 enum {
 	MLX5_FW_RESET_FLAGS_RESET_REQUESTED,
 	MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST,
 	MLX5_FW_RESET_FLAGS_PENDING_COMP,
 	MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS,
-	MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED
+	MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED,
+	MLX5_FW_RESET_FLAGS_UNLOAD_EVENT,
 };
 
 struct mlx5_fw_reset {
@@ -25,6 +27,7 @@ struct mlx5_fw_reset {
 	struct work_struct reset_reload_work;
 	struct work_struct reset_now_work;
 	struct work_struct reset_abort_work;
+	struct delayed_work reset_timeout_work;
 	unsigned long reset_flags;
 	u8 reset_method;
 	struct timer_list timer;
@@ -70,7 +73,8 @@ static int mlx5_fw_reset_enable_remote_dev_reset_set(struct devlink *devlink, u3
 }
 
 static int mlx5_fw_reset_enable_remote_dev_reset_get(struct devlink *devlink, u32 id,
-						     struct devlink_param_gset_ctx *ctx)
+						     struct devlink_param_gset_ctx *ctx,
+						     struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	struct mlx5_fw_reset *fw_reset;
@@ -219,7 +223,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev)
 	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL0, 0, 0, false);
 }
 
-static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unloaded)
+static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 	struct devlink *devlink = priv_to_devlink(dev);
@@ -228,8 +232,7 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unload
 	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
 		complete(&fw_reset->done);
 	} else {
-		if (!unloaded)
-			mlx5_unload_one(dev, false);
+		mlx5_sync_reset_unload_flow(dev, false);
 		if (mlx5_health_wait_pci_up(dev))
 			mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
 		else
@@ -246,7 +249,7 @@ static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 
-	del_timer_sync(&fw_reset->timer);
+	timer_delete_sync(&fw_reset->timer);
 }
 
 static int mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health)
@@ -258,6 +261,8 @@ static int mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool
 		return -EALREADY;
 	}
 
+	if (current_work() != &fw_reset->reset_timeout_work.work)
+		cancel_delayed_work(&fw_reset->reset_timeout_work);
 	mlx5_stop_sync_reset_poll(dev);
 	if (poll_health)
 		mlx5_start_health_poll(dev);
@@ -272,13 +277,14 @@ static void mlx5_sync_reset_reload_work(struct work_struct *work)
 
 	mlx5_sync_reset_clear_reset_requested(dev, false);
 	mlx5_enter_error_state(dev, true);
-	mlx5_fw_reset_complete_reload(dev, false);
+	mlx5_fw_reset_complete_reload(dev);
 }
 
 #define MLX5_RESET_POLL_INTERVAL	(HZ / 10)
 static void poll_sync_reset(struct timer_list *t)
 {
-	struct mlx5_fw_reset *fw_reset = from_timer(fw_reset, t, timer);
+	struct mlx5_fw_reset *fw_reset = timer_container_of(fw_reset, t,
+							    timer);
 	struct mlx5_core_dev *dev = fw_reset->dev;
 	u32 fatal_error;
 
@@ -328,6 +334,11 @@ static int mlx5_sync_reset_set_reset_requested(struct mlx5_core_dev *dev)
 	}
 	mlx5_stop_health_poll(dev, true);
 	mlx5_start_sync_reset_poll(dev);
+
+	if (!test_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS,
+		      &fw_reset->reset_flags))
+		schedule_delayed_work(&fw_reset->reset_timeout_work,
+			msecs_to_jiffies(mlx5_tout_ms(dev, PCI_SYNC_UPDATE)));
 	return 0;
 }
 
@@ -345,15 +356,12 @@ static void mlx5_fw_live_patch_event(struct work_struct *work)
 }
 
 #if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
-static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev)
+static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev,
+					struct pci_dev *bridge)
 {
-	struct pci_dev *bridge = dev->pdev->bus->self;
 	u16 reg16;
 	int err;
 
-	if (!bridge)
-		return -EOPNOTSUPP;
-
 	err = pcie_capability_read_word(bridge, PCI_EXP_SLTCTL, &reg16);
 	if (err)
 		return err;
@@ -416,17 +424,28 @@ static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id)
 static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev,
 				      u8 reset_method)
 {
+	struct pci_dev *bridge = dev->pdev->bus->self;
 	u16 dev_id;
 	int err;
 
+	if (!bridge) {
+		mlx5_core_warn(dev, "PCI bus bridge is not accessible\n");
+		return false;
+	}
+
 	if (!MLX5_CAP_GEN(dev, fast_teardown)) {
 		mlx5_core_warn(dev, "fast teardown is not supported by firmware\n");
 		return false;
 	}
 
+	if (!mlx5_core_is_ecpf(dev) && !mlx5_sf_table_empty(dev)) {
+		mlx5_core_warn(dev, "SFs should be removed before reset\n");
+		return false;
+	}
+
 #if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
 	if (reset_method != MLX5_MFRL_REG_PCI_RESET_METHOD_HOT_RESET) {
-		err = mlx5_check_hotplug_interrupt(dev);
+		err = mlx5_check_hotplug_interrupt(dev, bridge);
 		if (err)
 			return false;
 	}
@@ -582,6 +601,65 @@ static int mlx5_sync_pci_reset(struct mlx5_core_dev *dev, u8 reset_method)
 	return err;
 }
 
+void mlx5_sync_reset_unload_flow(struct mlx5_core_dev *dev, bool locked)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+	unsigned long timeout;
+	int poll_freq = 20;
+	bool reset_action;
+	u8 rst_state;
+	int err;
+
+	if (locked)
+		mlx5_unload_one_devl_locked(dev, false);
+	else
+		mlx5_unload_one(dev, false);
+
+	if (!test_bit(MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, &fw_reset->reset_flags))
+		return;
+
+	mlx5_set_fw_rst_ack(dev);
+	mlx5_core_warn(dev, "Sync Reset Unload done, device reset expected\n");
+
+	reset_action = false;
+	timeout = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, RESET_UNLOAD));
+	do {
+		rst_state = mlx5_get_fw_rst_state(dev);
+		if (rst_state == MLX5_FW_RST_STATE_TOGGLE_REQ ||
+		    rst_state == MLX5_FW_RST_STATE_IDLE) {
+			reset_action = true;
+			break;
+		}
+		if (rst_state == MLX5_FW_RST_STATE_DROP_MODE) {
+			mlx5_core_info(dev, "Sync Reset Drop mode ack\n");
+			mlx5_set_fw_rst_ack(dev);
+			poll_freq = 1000;
+		}
+		msleep(poll_freq);
+	} while (!time_after(jiffies, timeout));
+
+	if (!reset_action) {
+		mlx5_core_err(dev, "Got timeout waiting for sync reset action, state = %u\n",
+			      rst_state);
+		fw_reset->ret = -ETIMEDOUT;
+		goto done;
+	}
+
+	mlx5_core_warn(dev, "Sync Reset, got reset action. rst_state = %u\n",
+		       rst_state);
+	if (rst_state == MLX5_FW_RST_STATE_TOGGLE_REQ) {
+		err = mlx5_sync_pci_reset(dev, fw_reset->reset_method);
+		if (err) {
+			mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, err %d\n",
+				       err);
+			fw_reset->ret = err;
+		}
+	}
+
+done:
+	clear_bit(MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, &fw_reset->reset_flags);
+}
+
 static void mlx5_sync_reset_now_event(struct work_struct *work)
 {
 	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
@@ -609,17 +687,13 @@ static void mlx5_sync_reset_now_event(struct work_struct *work)
 	mlx5_enter_error_state(dev, true);
 done:
 	fw_reset->ret = err;
-	mlx5_fw_reset_complete_reload(dev, false);
+	mlx5_fw_reset_complete_reload(dev);
 }
 
 static void mlx5_sync_reset_unload_event(struct work_struct *work)
 {
 	struct mlx5_fw_reset *fw_reset;
 	struct mlx5_core_dev *dev;
-	unsigned long timeout;
-	int poll_freq = 20;
-	bool reset_action;
-	u8 rst_state;
 	int err;
 
 	fw_reset = container_of(work, struct mlx5_fw_reset, reset_unload_work);
@@ -628,6 +702,7 @@ static void mlx5_sync_reset_unload_event(struct work_struct *work)
 	if (mlx5_sync_reset_clear_reset_requested(dev, false))
 		return;
 
+	set_bit(MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, &fw_reset->reset_flags);
 	mlx5_core_warn(dev, "Sync Reset Unload. Function is forced down.\n");
 
 	err = mlx5_cmd_fast_teardown_hca(dev);
@@ -636,49 +711,7 @@ static void mlx5_sync_reset_unload_event(struct work_struct *work)
 	else
 		mlx5_enter_error_state(dev, true);
 
-	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags))
-		mlx5_unload_one_devl_locked(dev, false);
-	else
-		mlx5_unload_one(dev, false);
-
-	mlx5_set_fw_rst_ack(dev);
-	mlx5_core_warn(dev, "Sync Reset Unload done, device reset expected\n");
-
-	reset_action = false;
-	timeout = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, RESET_UNLOAD));
-	do {
-		rst_state = mlx5_get_fw_rst_state(dev);
-		if (rst_state == MLX5_FW_RST_STATE_TOGGLE_REQ ||
-		    rst_state == MLX5_FW_RST_STATE_IDLE) {
-			reset_action = true;
-			break;
-		}
-		if (rst_state == MLX5_FW_RST_STATE_DROP_MODE) {
-			mlx5_core_info(dev, "Sync Reset Drop mode ack\n");
-			mlx5_set_fw_rst_ack(dev);
-			poll_freq = 1000;
-		}
-		msleep(poll_freq);
-	} while (!time_after(jiffies, timeout));
-
-	if (!reset_action) {
-		mlx5_core_err(dev, "Got timeout waiting for sync reset action, state = %u\n",
-			      rst_state);
-		fw_reset->ret = -ETIMEDOUT;
-		goto done;
-	}
-
-	mlx5_core_warn(dev, "Sync Reset, got reset action. rst_state = %u\n", rst_state);
-	if (rst_state == MLX5_FW_RST_STATE_TOGGLE_REQ) {
-		err = mlx5_sync_pci_reset(dev, fw_reset->reset_method);
-		if (err) {
-			mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, err %d\n", err);
-			fw_reset->ret = err;
-		}
-	}
-
-done:
-	mlx5_fw_reset_complete_reload(dev, true);
+	mlx5_fw_reset_complete_reload(dev);
 }
 
 static void mlx5_sync_reset_abort_event(struct work_struct *work)
@@ -715,6 +748,19 @@ static void mlx5_sync_reset_events_handle(struct mlx5_fw_reset *fw_reset, struct
 	}
 }
 
+static void mlx5_sync_reset_timeout_work(struct work_struct *work)
+{
+	struct delayed_work *dwork = container_of(work, struct delayed_work,
+						  work);
+	struct mlx5_fw_reset *fw_reset =
+		container_of(dwork, struct mlx5_fw_reset, reset_timeout_work);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+
+	if (mlx5_sync_reset_clear_reset_requested(dev, true))
+		return;
+	mlx5_core_warn(dev, "PCI Sync FW Update Reset Timeout.\n");
+}
+
 static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long action, void *data)
 {
 	struct mlx5_fw_reset *fw_reset = mlx5_nb_cof(nb, struct mlx5_fw_reset, nb);
@@ -798,6 +844,7 @@ void mlx5_drain_fw_reset(struct mlx5_core_dev *dev)
 	cancel_work_sync(&fw_reset->reset_reload_work);
 	cancel_work_sync(&fw_reset->reset_now_work);
 	cancel_work_sync(&fw_reset->reset_abort_work);
+	cancel_delayed_work(&fw_reset->reset_timeout_work);
 }
 
 static const struct devlink_param mlx5_fw_reset_devlink_params[] = {
@@ -841,6 +888,8 @@ int mlx5_fw_reset_init(struct mlx5_core_dev *dev)
 	INIT_WORK(&fw_reset->reset_reload_work, mlx5_sync_reset_reload_work);
 	INIT_WORK(&fw_reset->reset_now_work, mlx5_sync_reset_now_event);
 	INIT_WORK(&fw_reset->reset_abort_work, mlx5_sync_reset_abort_event);
+	INIT_DELAYED_WORK(&fw_reset->reset_timeout_work,
+			  mlx5_sync_reset_timeout_work);
 
 	init_completion(&fw_reset->done);
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
index ea527d06a85f..d5b28525c960 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
@@ -12,6 +12,7 @@ int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel,
 int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev);
 
 int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev);
+void mlx5_sync_reset_unload_flow(struct mlx5_core_dev *dev, bool locked);
 int mlx5_fw_reset_verify_fw_complete(struct mlx5_core_dev *dev,
 				     struct netlink_ext_ack *extack);
 void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index a6329ca2d9bf..aeeb136f5ebc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -96,6 +96,11 @@ static int mlx5_health_get_rfr(u8 rfr_severity)
 	return rfr_severity >> MLX5_RFR_BIT_OFFSET;
 }
 
+static int mlx5_health_get_crr(u8 rfr_severity)
+{
+	return (rfr_severity >> MLX5_CRR_BIT_OFFSET) & 0x01;
+}
+
 static bool sensor_fw_synd_rfr(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
@@ -375,6 +380,8 @@ static const char *hsynd_str(u8 synd)
 		return "High temperature";
 	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_PCI_POISONED_ERR:
 		return "ICM fetch PCI data poisoned error";
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_TRUST_LOCKDOWN_ERR:
+		return "Trust lockdown error";
 	default:
 		return "unrecognized error";
 	}
@@ -442,12 +449,15 @@ static void print_health_info(struct mlx5_core_dev *dev)
 	mlx5_log(dev, severity, "time %u\n", ioread32be(&h->time));
 	mlx5_log(dev, severity, "hw_id 0x%08x\n", ioread32be(&h->hw_id));
 	mlx5_log(dev, severity, "rfr %d\n", mlx5_health_get_rfr(rfr_severity));
+	mlx5_log(dev, severity, "crr %d\n", mlx5_health_get_crr(rfr_severity));
 	mlx5_log(dev, severity, "severity %d (%s)\n", severity, mlx5_loglevel_str(severity));
 	mlx5_log(dev, severity, "irisc_index %d\n", ioread8(&h->irisc_index));
 	mlx5_log(dev, severity, "synd 0x%x: %s\n", ioread8(&h->synd),
 		 hsynd_str(ioread8(&h->synd)));
 	mlx5_log(dev, severity, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd));
 	mlx5_log(dev, severity, "raw fw_ver 0x%08x\n", ioread32be(&h->fw_ver));
+	if (mlx5_health_get_crr(rfr_severity))
+		mlx5_core_warn(dev, "Cold reset is required\n");
 }
 
 static int
@@ -659,57 +669,64 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work)
 	}
 }
 
+#define MLX5_FW_REPORTER_ECPF_GRACEFUL_PERIOD 180000
+#define MLX5_FW_REPORTER_PF_GRACEFUL_PERIOD 60000
+#define MLX5_FW_REPORTER_VF_GRACEFUL_PERIOD 30000
+#define MLX5_FW_REPORTER_DEFAULT_GRACEFUL_PERIOD \
+	MLX5_FW_REPORTER_VF_GRACEFUL_PERIOD
+
+static
+const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ecpf_ops = {
+		.name = "fw_fatal",
+		.recover = mlx5_fw_fatal_reporter_recover,
+		.dump = mlx5_fw_fatal_reporter_dump,
+		.default_graceful_period =
+			MLX5_FW_REPORTER_ECPF_GRACEFUL_PERIOD,
+};
+
 static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_pf_ops = {
 		.name = "fw_fatal",
 		.recover = mlx5_fw_fatal_reporter_recover,
 		.dump = mlx5_fw_fatal_reporter_dump,
+		.default_graceful_period = MLX5_FW_REPORTER_PF_GRACEFUL_PERIOD,
 };
 
 static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
 		.name = "fw_fatal",
 		.recover = mlx5_fw_fatal_reporter_recover,
+		.default_graceful_period =
+			MLX5_FW_REPORTER_DEFAULT_GRACEFUL_PERIOD,
 };
 
-#define MLX5_FW_REPORTER_ECPF_GRACEFUL_PERIOD 180000
-#define MLX5_FW_REPORTER_PF_GRACEFUL_PERIOD 60000
-#define MLX5_FW_REPORTER_VF_GRACEFUL_PERIOD 30000
-#define MLX5_FW_REPORTER_DEFAULT_GRACEFUL_PERIOD MLX5_FW_REPORTER_VF_GRACEFUL_PERIOD
-
 void mlx5_fw_reporters_create(struct mlx5_core_dev *dev)
 {
 	const struct devlink_health_reporter_ops *fw_fatal_ops;
 	struct mlx5_core_health *health = &dev->priv.health;
 	const struct devlink_health_reporter_ops *fw_ops;
 	struct devlink *devlink = priv_to_devlink(dev);
-	u64 grace_period;
 
-	fw_fatal_ops = &mlx5_fw_fatal_reporter_pf_ops;
 	fw_ops = &mlx5_fw_reporter_pf_ops;
 	if (mlx5_core_is_ecpf(dev)) {
-		grace_period = MLX5_FW_REPORTER_ECPF_GRACEFUL_PERIOD;
+		fw_fatal_ops = &mlx5_fw_fatal_reporter_ecpf_ops;
 	} else if (mlx5_core_is_pf(dev)) {
-		grace_period = MLX5_FW_REPORTER_PF_GRACEFUL_PERIOD;
+		fw_fatal_ops = &mlx5_fw_fatal_reporter_pf_ops;
 	} else {
 		/* VF or SF */
-		grace_period = MLX5_FW_REPORTER_DEFAULT_GRACEFUL_PERIOD;
 		fw_fatal_ops = &mlx5_fw_fatal_reporter_ops;
 		fw_ops = &mlx5_fw_reporter_ops;
 	}
 
-	health->fw_reporter =
-		devl_health_reporter_create(devlink, fw_ops, 0, dev);
+	health->fw_reporter = devl_health_reporter_create(devlink, fw_ops, dev);
 	if (IS_ERR(health->fw_reporter))
-		mlx5_core_warn(dev, "Failed to create fw reporter, err = %ld\n",
-			       PTR_ERR(health->fw_reporter));
-
-	health->fw_fatal_reporter =
-		devl_health_reporter_create(devlink,
-					    fw_fatal_ops,
-					    grace_period,
-					    dev);
+		mlx5_core_warn(dev, "Failed to create fw reporter, err = %pe\n",
+			       health->fw_reporter);
+
+	health->fw_fatal_reporter = devl_health_reporter_create(devlink,
+								fw_fatal_ops,
+								dev);
 	if (IS_ERR(health->fw_fatal_reporter))
-		mlx5_core_warn(dev, "Failed to create fw fatal reporter, err = %ld\n",
-			       PTR_ERR(health->fw_fatal_reporter));
+		mlx5_core_warn(dev, "Failed to create fw fatal reporter, err = %pe\n",
+			       health->fw_fatal_reporter);
 }
 
 static void mlx5_fw_reporters_destroy(struct mlx5_core_dev *dev)
@@ -769,7 +786,8 @@ static void mlx5_health_log_ts_update(struct work_struct *work)
 
 static void poll_health(struct timer_list *t)
 {
-	struct mlx5_core_dev *dev = from_timer(dev, t, priv.health.timer);
+	struct mlx5_core_dev *dev = timer_container_of(dev, t,
+						       priv.health.timer);
 	struct mlx5_core_health *health = &dev->priv.health;
 	struct health_buffer __iomem *h = health->health;
 	u32 fatal_error;
@@ -799,14 +817,17 @@ static void poll_health(struct timer_list *t)
 	health->prev = count;
 	if (health->miss_counter == MAX_MISSES) {
 		mlx5_core_err(dev, "device's health compromised - reached miss count\n");
+		health->synd = ioread8(&h->synd);
 		print_health_info(dev);
 		queue_work(health->wq, &health->report_work);
 	}
 
 	prev_synd = health->synd;
 	health->synd = ioread8(&h->synd);
-	if (health->synd && health->synd != prev_synd)
+	if (health->synd && health->synd != prev_synd) {
+		print_health_info(dev);
 		queue_work(health->wq, &health->report_work);
+	}
 
 out:
 	mod_timer(&health->timer, get_next_poll_jiffies(dev));
@@ -834,7 +855,7 @@ void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health)
 	if (disable_health)
 		set_bit(MLX5_DROP_HEALTH_WORK, &health->flags);
 
-	del_timer_sync(&health->timer);
+	timer_delete_sync(&health->timer);
 }
 
 void mlx5_start_health_fw_log_up(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c
index 353f81dccd1c..4ba2636d7fb6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c
@@ -416,3 +416,8 @@ void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev)
 	mlx5_hwmon_free(hwmon);
 	mdev->hwmon = NULL;
 }
+
+const char *hwmon_get_sensor_name(struct mlx5_hwmon *hwmon, int channel)
+{
+	return hwmon->temp_channel_desc[channel].sensor_name;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h
index 999654a9b9da..f38271c22c10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h
@@ -10,6 +10,7 @@
 
 int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev);
 void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev);
+const char *hwmon_get_sensor_name(struct mlx5_hwmon *hwmon, int channel);
 
 #else
 static inline int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index 9772327d5124..3b2f54ca30a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -238,6 +238,23 @@ static u32 mlx5i_flow_type_mask(u32 flow_type)
 	return flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS);
 }
 
+static int mlx5i_set_rxfh_fields(struct net_device *dev,
+				 const struct ethtool_rxfh_fields *cmd,
+				 struct netlink_ext_ack *extack)
+{
+	struct mlx5e_priv *priv = mlx5i_epriv(dev);
+
+	return mlx5e_ethtool_set_rxfh_fields(priv, cmd, extack);
+}
+
+static int mlx5i_get_rxfh_fields(struct net_device *dev,
+				 struct ethtool_rxfh_fields *info)
+{
+	struct mlx5e_priv *priv = mlx5i_epriv(dev);
+
+	return mlx5e_ethtool_get_rxfh_fields(priv, info);
+}
+
 static int mlx5i_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 {
 	struct mlx5e_priv *priv = mlx5i_epriv(dev);
@@ -249,21 +266,18 @@ static int mlx5i_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	return mlx5e_ethtool_set_rxnfc(priv, cmd);
 }
 
+static u32 mlx5i_get_rx_ring_count(struct net_device *dev)
+{
+	struct mlx5e_priv *priv = mlx5i_epriv(dev);
+
+	return priv->channels.params.num_channels;
+}
+
 static int mlx5i_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
 			   u32 *rule_locs)
 {
 	struct mlx5e_priv *priv = mlx5i_epriv(dev);
 
-	/* ETHTOOL_GRXRINGS is needed by ethtool -x which is not part
-	 * of rxnfc. We keep this logic out of mlx5e_ethtool_get_rxnfc,
-	 * to avoid breaking "ethtool -x" when mlx5e_ethtool_get_rxnfc
-	 * is compiled out via CONFIG_MLX5_EN_RXNFC=n.
-	 */
-	if (info->cmd == ETHTOOL_GRXRINGS) {
-		info->data = priv->channels.params.num_channels;
-		return 0;
-	}
-
 	return mlx5e_ethtool_get_rxnfc(priv, info, rule_locs);
 }
 
@@ -283,8 +297,11 @@ const struct ethtool_ops mlx5i_ethtool_ops = {
 	.get_coalesce       = mlx5i_get_coalesce,
 	.set_coalesce       = mlx5i_set_coalesce,
 	.get_ts_info        = mlx5i_get_ts_info,
+	.get_rxfh_fields    = mlx5i_get_rxfh_fields,
+	.set_rxfh_fields    = mlx5i_set_rxfh_fields,
 	.get_rxnfc          = mlx5i_get_rxnfc,
 	.set_rxnfc          = mlx5i_set_rxnfc,
+	.get_rx_ring_count  = mlx5i_get_rx_ring_count,
 	.get_link_ksettings = mlx5i_get_link_ksettings,
 	.get_link           = ethtool_op_get_link,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 0979d672d47f..0a6003fe60e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -32,6 +32,7 @@
 
 #include <rdma/ib_verbs.h>
 #include <linux/mlx5/fs.h>
+#include <net/netdev_lock.h>
 #include "en.h"
 #include "en/params.h"
 #include "ipoib.h"
@@ -44,6 +45,23 @@ static int mlx5i_open(struct net_device *netdev);
 static int mlx5i_close(struct net_device *netdev);
 static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu);
 
+int mlx5i_hwtstamp_set(struct net_device *dev,
+		       struct kernel_hwtstamp_config *config,
+		       struct netlink_ext_ack *extack)
+{
+	struct mlx5e_priv *epriv = mlx5i_epriv(dev);
+
+	return mlx5e_hwtstamp_set(epriv, config, extack);
+}
+
+int mlx5i_hwtstamp_get(struct net_device *dev,
+		       struct kernel_hwtstamp_config *config)
+{
+	struct mlx5e_priv *epriv = mlx5i_epriv(dev);
+
+	return mlx5e_hwtstamp_get(epriv, config);
+}
+
 static const struct net_device_ops mlx5i_netdev_ops = {
 	.ndo_open                = mlx5i_open,
 	.ndo_stop                = mlx5i_close,
@@ -51,7 +69,8 @@ static const struct net_device_ops mlx5i_netdev_ops = {
 	.ndo_init                = mlx5i_dev_init,
 	.ndo_uninit              = mlx5i_dev_cleanup,
 	.ndo_change_mtu          = mlx5i_change_mtu,
-	.ndo_eth_ioctl            = mlx5i_ioctl,
+	.ndo_hwtstamp_get        = mlx5i_hwtstamp_get,
+	.ndo_hwtstamp_set        = mlx5i_hwtstamp_set,
 };
 
 /* IPoIB mlx5 netdev profile */
@@ -102,6 +121,8 @@ int mlx5i_init(struct mlx5_core_dev *mdev, struct net_device *netdev)
 
 	netdev->netdev_ops = &mlx5i_netdev_ops;
 	netdev->ethtool_ops = &mlx5i_ethtool_ops;
+	netdev->request_ops_lock = true;
+	netdev_lockdep_set_classes(netdev);
 
 	return 0;
 }
@@ -313,7 +334,7 @@ void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, u32 qpn)
 
 int mlx5i_update_nic_rx(struct mlx5e_priv *priv)
 {
-	return mlx5e_refresh_tirs(priv, true, true);
+	return mlx5e_refresh_tirs(priv->mdev, true, true);
 }
 
 int mlx5i_create_tis(struct mlx5_core_dev *mdev, u32 underlay_qpn, u32 *tisn)
@@ -406,6 +427,7 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv)
 static int mlx5i_init_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
+	enum mlx5e_rx_res_features features;
 	int err;
 
 	priv->fs = mlx5e_fs_init(priv->profile, mdev,
@@ -424,7 +446,9 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 		goto err_destroy_q_counters;
 	}
 
-	priv->rx_res = mlx5e_rx_res_create(priv->mdev, 0, priv->max_nch, priv->drop_rq.rqn,
+	features = MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK;
+	priv->rx_res = mlx5e_rx_res_create(priv->mdev, features, priv->max_nch,
+					   priv->drop_rq.rqn,
 					   &priv->channels.params.packet_merge,
 					   priv->channels.params.num_channels);
 	if (IS_ERR(priv->rx_res)) {
@@ -554,20 +578,6 @@ int mlx5i_dev_init(struct net_device *dev)
 	return 0;
 }
 
-int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	struct mlx5e_priv *priv = mlx5i_epriv(dev);
-
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return mlx5e_hwstamp_set(priv, ifr);
-	case SIOCGHWTSTAMP:
-		return mlx5e_hwstamp_get(priv, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 void mlx5i_dev_cleanup(struct net_device *dev)
 {
 	struct mlx5e_priv    *priv   = mlx5i_epriv(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
index 2ab6437a1c49..d67d5a72bb41 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
@@ -88,7 +88,11 @@ struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn);
 /* Shared ndo functions */
 int mlx5i_dev_init(struct net_device *dev);
 void mlx5i_dev_cleanup(struct net_device *dev);
-int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
+int mlx5i_hwtstamp_set(struct net_device *dev,
+		       struct kernel_hwtstamp_config *config,
+		       struct netlink_ext_ack *extack);
+int mlx5i_hwtstamp_get(struct net_device *dev,
+		       struct kernel_hwtstamp_config *config);
 
 /* Parent profile functions */
 int mlx5i_init(struct mlx5_core_dev *mdev, struct net_device *netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index 028a76944d82..04444dad3a0d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -140,7 +140,6 @@ static int mlx5i_pkey_close(struct net_device *netdev);
 static int mlx5i_pkey_dev_init(struct net_device *dev);
 static void mlx5i_pkey_dev_cleanup(struct net_device *netdev);
 static int mlx5i_pkey_change_mtu(struct net_device *netdev, int new_mtu);
-static int mlx5i_pkey_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
 
 static const struct net_device_ops mlx5i_pkey_netdev_ops = {
 	.ndo_open                = mlx5i_pkey_open,
@@ -149,7 +148,8 @@ static const struct net_device_ops mlx5i_pkey_netdev_ops = {
 	.ndo_get_stats64         = mlx5i_get_stats,
 	.ndo_uninit              = mlx5i_pkey_dev_cleanup,
 	.ndo_change_mtu          = mlx5i_pkey_change_mtu,
-	.ndo_eth_ioctl            = mlx5i_pkey_ioctl,
+	.ndo_hwtstamp_get        = mlx5i_hwtstamp_get,
+	.ndo_hwtstamp_set        = mlx5i_hwtstamp_set,
 };
 
 /* Child NDOs */
@@ -184,11 +184,6 @@ static int mlx5i_pkey_dev_init(struct net_device *dev)
 	return mlx5i_dev_init(dev);
 }
 
-static int mlx5i_pkey_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	return mlx5i_ioctl(dev, ifr, cmd);
-}
-
 static void mlx5i_pkey_dev_cleanup(struct net_device *netdev)
 {
 	mlx5i_parent_put(netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
index 1477db7f5307..14d339eceb92 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
@@ -47,29 +47,40 @@ static int cpu_get_least_loaded(struct mlx5_irq_pool *pool,
 static struct mlx5_irq *
 irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_desc)
 {
-	struct irq_affinity_desc auto_desc = {};
+	struct irq_affinity_desc *auto_desc;
 	struct mlx5_irq *irq;
 	u32 irq_index;
 	int err;
 
+	auto_desc = kvzalloc(sizeof(*auto_desc), GFP_KERNEL);
+	if (!auto_desc)
+		return ERR_PTR(-ENOMEM);
+
 	err = xa_alloc(&pool->irqs, &irq_index, NULL, pool->xa_num_irqs, GFP_KERNEL);
-	if (err)
+	if (err) {
+		kvfree(auto_desc);
 		return ERR_PTR(err);
+	}
+
 	if (pool->irqs_per_cpu) {
 		if (cpumask_weight(&af_desc->mask) > 1)
 			/* if req_mask contain more then one CPU, set the least loadad CPU
 			 * of req_mask
 			 */
 			cpumask_set_cpu(cpu_get_least_loaded(pool, &af_desc->mask),
-					&auto_desc.mask);
+					&auto_desc->mask);
 		else
 			cpu_get(pool, cpumask_first(&af_desc->mask));
 	}
+
 	irq = mlx5_irq_alloc(pool, irq_index,
-			     cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc,
+			     cpumask_empty(&auto_desc->mask) ? af_desc : auto_desc,
 			     NULL);
 	if (IS_ERR(irq))
 		xa_erase(&pool->irqs, irq_index);
+
+	kvfree(auto_desc);
+
 	return irq;
 }
 
@@ -139,8 +150,8 @@ mlx5_irq_affinity_request(struct mlx5_core_dev *dev, struct mlx5_irq_pool *pool,
 	if (IS_ERR(new_irq)) {
 		if (!least_loaded_irq) {
 			/* We failed to create an IRQ and we didn't find an IRQ */
-			mlx5_core_err(pool->dev, "Didn't find a matching IRQ. err = %ld\n",
-				      PTR_ERR(new_irq));
+			mlx5_core_err(pool->dev, "Didn't find a matching IRQ. err = %pe\n",
+				      new_irq);
 			mutex_unlock(&pool->lock);
 			return new_irq;
 		}
@@ -175,7 +186,7 @@ unlock:
 
 void mlx5_irq_affinity_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *irq)
 {
-	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
+	struct mlx5_irq_pool *pool = mlx5_irq_get_pool(irq);
 	int cpu;
 
 	cpu = cpumask_first(mlx5_irq_get_affinity_mask(irq));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index cea5aa314f6c..1ac933cd8f02 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -35,6 +35,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/eswitch.h>
 #include <linux/mlx5/vport.h>
+#include "lib/mlx5.h"
 #include "lib/devcom.h"
 #include "mlx5_core.h"
 #include "eswitch.h"
@@ -231,9 +232,13 @@ static void mlx5_do_bond_work(struct work_struct *work);
 static void mlx5_ldev_free(struct kref *ref)
 {
 	struct mlx5_lag *ldev = container_of(ref, struct mlx5_lag, ref);
+	struct net *net;
+
+	if (ldev->nb.notifier_call) {
+		net = read_pnet(&ldev->net);
+		unregister_netdevice_notifier_net(net, &ldev->nb);
+	}
 
-	if (ldev->nb.notifier_call)
-		unregister_netdevice_notifier_net(&init_net, &ldev->nb);
 	mlx5_lag_mp_cleanup(ldev);
 	cancel_delayed_work_sync(&ldev->bond_work);
 	destroy_workqueue(ldev->wq);
@@ -271,7 +276,8 @@ static struct mlx5_lag *mlx5_lag_dev_alloc(struct mlx5_core_dev *dev)
 	INIT_DELAYED_WORK(&ldev->bond_work, mlx5_do_bond_work);
 
 	ldev->nb.notifier_call = mlx5_lag_netdev_event;
-	if (register_netdevice_notifier_net(&init_net, &ldev->nb)) {
+	write_pnet(&ldev->net, mlx5_core_net(dev));
+	if (register_netdevice_notifier_net(read_pnet(&ldev->net), &ldev->nb)) {
 		ldev->nb.notifier_call = NULL;
 		mlx5_core_err(dev, "Failed to register LAG netdev notifier\n");
 	}
@@ -523,8 +529,7 @@ static struct net_device *mlx5_lag_active_backup_get_netdev(struct mlx5_core_dev
 		ndev = ldev->pf[last_idx].netdev;
 	}
 
-	if (ndev)
-		dev_hold(ndev);
+	dev_hold(ndev);
 
 unlock:
 	spin_unlock_irqrestore(&lag_lock, flags);
@@ -584,8 +589,9 @@ void mlx5_modify_lag(struct mlx5_lag *ldev,
 	}
 }
 
-static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev,
-					   unsigned long *flags)
+static int mlx5_lag_set_port_sel_mode(struct mlx5_lag *ldev,
+				      enum mlx5_lag_mode mode,
+				      unsigned long *flags)
 {
 	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	struct mlx5_core_dev *dev0;
@@ -593,7 +599,12 @@ static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev,
 	if (first_idx < 0)
 		return -EINVAL;
 
+	if (mode == MLX5_LAG_MODE_MPESW ||
+	    mode == MLX5_LAG_MODE_MULTIPATH)
+		return 0;
+
 	dev0 = ldev->pf[first_idx].dev;
+
 	if (!MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table)) {
 		if (ldev->ports > 2)
 			return -EINVAL;
@@ -608,32 +619,10 @@ static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev,
 	return 0;
 }
 
-static void mlx5_lag_set_port_sel_mode_offloads(struct mlx5_lag *ldev,
-						struct lag_tracker *tracker,
-						enum mlx5_lag_mode mode,
-						unsigned long *flags)
-{
-	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
-	struct lag_func *dev0;
-
-	if (first_idx < 0 || mode == MLX5_LAG_MODE_MPESW)
-		return;
-
-	dev0 = &ldev->pf[first_idx];
-	if (MLX5_CAP_PORT_SELECTION(dev0->dev, port_select_flow_table) &&
-	    tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH) {
-		if (ldev->ports > 2)
-			ldev->buckets = MLX5_LAG_MAX_HASH_BUCKETS;
-		set_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, flags);
-	}
-}
-
 static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode,
 			      struct lag_tracker *tracker, bool shared_fdb,
 			      unsigned long *flags)
 {
-	bool roce_lag = mode == MLX5_LAG_MODE_ROCE;
-
 	*flags = 0;
 	if (shared_fdb) {
 		set_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, flags);
@@ -643,11 +632,7 @@ static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode,
 	if (mode == MLX5_LAG_MODE_MPESW)
 		set_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE, flags);
 
-	if (roce_lag)
-		return mlx5_lag_set_port_sel_mode_roce(ldev, flags);
-
-	mlx5_lag_set_port_sel_mode_offloads(ldev, tracker, mode, flags);
-	return 0;
+	return mlx5_lag_set_port_sel_mode(ldev, mode, flags);
 }
 
 char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags)
@@ -951,7 +936,7 @@ void mlx5_disable_lag(struct mlx5_lag *ldev)
 				mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
 }
 
-static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev)
+bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev)
 {
 	int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	struct mlx5_core_dev *dev;
@@ -1038,7 +1023,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	}
 
 	if (do_bond && !__mlx5_lag_is_active(ldev)) {
-		bool shared_fdb = mlx5_shared_fdb_supported(ldev);
+		bool shared_fdb = mlx5_lag_shared_fdb_supported(ldev);
 
 		roce_lag = mlx5_lag_is_roce_lag(ldev);
 
@@ -1052,6 +1037,10 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 		if (err) {
 			if (shared_fdb || roce_lag)
 				mlx5_lag_add_devices(ldev);
+			if (shared_fdb) {
+				mlx5_ldev_for_each(i, 0, ldev)
+					mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
+			}
 
 			return;
 		} else if (roce_lag) {
@@ -1421,6 +1410,37 @@ static int __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev)
 	return 0;
 }
 
+static void mlx5_lag_unregister_hca_devcom_comp(struct mlx5_core_dev *dev)
+{
+	mlx5_devcom_unregister_component(dev->priv.hca_devcom_comp);
+}
+
+static int mlx5_lag_register_hca_devcom_comp(struct mlx5_core_dev *dev)
+{
+	struct mlx5_devcom_match_attr attr = {
+		.flags = MLX5_DEVCOM_MATCH_FLAGS_NS,
+		.net = mlx5_core_net(dev),
+	};
+	u8 len __always_unused;
+
+	mlx5_query_nic_sw_system_image_guid(dev, attr.key.buf, &len);
+
+	/* This component is use to sync adding core_dev to lag_dev and to sync
+	 * changes of mlx5_adev_devices between LAG layer and other layers.
+	 */
+	dev->priv.hca_devcom_comp =
+		mlx5_devcom_register_component(dev->priv.devc,
+					       MLX5_DEVCOM_HCA_PORTS,
+					       &attr, NULL, dev);
+	if (!dev->priv.hca_devcom_comp) {
+		mlx5_core_err(dev,
+			      "Failed to register devcom HCA component.");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
@@ -1442,6 +1462,7 @@ recheck:
 	}
 	mlx5_ldev_remove_mdev(ldev, dev);
 	mutex_unlock(&ldev->lock);
+	mlx5_lag_unregister_hca_devcom_comp(dev);
 	mlx5_ldev_put(ldev);
 }
 
@@ -1452,7 +1473,7 @@ void mlx5_lag_add_mdev(struct mlx5_core_dev *dev)
 	if (!mlx5_lag_is_supported(dev))
 		return;
 
-	if (IS_ERR_OR_NULL(dev->priv.hca_devcom_comp))
+	if (mlx5_lag_register_hca_devcom_comp(dev))
 		return;
 
 recheck:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index 01cf72366947..4918eee2b3da 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -67,6 +67,7 @@ struct mlx5_lag {
 	struct workqueue_struct   *wq;
 	struct delayed_work       bond_work;
 	struct notifier_block     nb;
+	possible_net_t net;
 	struct lag_mp             lag_mp;
 	struct mlx5_lag_port_sel  port_sel;
 	/* Protect lag fields/state changes */
@@ -92,6 +93,7 @@ mlx5_lag_is_ready(struct mlx5_lag *ldev)
 	return test_bit(MLX5_LAG_FLAG_NDEVS_READY, &ldev->state_flags);
 }
 
+bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev);
 bool mlx5_lag_check_prereq(struct mlx5_lag *ldev);
 void mlx5_modify_lag(struct mlx5_lag *ldev,
 		     struct lag_tracker *tracker);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index ffac0bd6c895..aad52d3a90e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -65,7 +65,6 @@ err_metadata:
 	return err;
 }
 
-#define MLX5_LAG_MPESW_OFFLOADS_SUPPORTED_PORTS 4
 static int enable_mpesw(struct mlx5_lag *ldev)
 {
 	int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
@@ -77,13 +76,11 @@ static int enable_mpesw(struct mlx5_lag *ldev)
 		return -EINVAL;
 
 	dev0 = ldev->pf[idx].dev;
-	if (ldev->ports > MLX5_LAG_MPESW_OFFLOADS_SUPPORTED_PORTS)
-		return -EOPNOTSUPP;
-
 	if (mlx5_eswitch_mode(dev0) != MLX5_ESWITCH_OFFLOADS ||
 	    !MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table) ||
 	    !MLX5_CAP_GEN(dev0, create_lag_when_not_master_up) ||
-	    !mlx5_lag_check_prereq(ldev))
+	    !mlx5_lag_check_prereq(ldev) ||
+	    !mlx5_lag_shared_fdb_supported(ldev))
 		return -EOPNOTSUPP;
 
 	err = mlx5_mpesw_metadata_set(ldev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
index 22241f52716c..d832a12ffec0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
@@ -97,7 +97,7 @@ static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev,
 						mlx5_del_flow_rules(lag_definer->rules[idx]);
 					}
 					j = ldev->buckets;
-				};
+				}
 				goto destroy_fg;
 			}
 		}
@@ -551,7 +551,7 @@ int mlx5_lag_port_sel_create(struct mlx5_lag *ldev,
 	set_tt_map(port_sel, hash_type);
 	err = mlx5_lag_create_definers(ldev, hash_type, ports);
 	if (err)
-		return err;
+		goto clear_port_sel;
 
 	if (port_sel->tunnel) {
 		err = mlx5_lag_create_inner_ttc_table(ldev);
@@ -570,6 +570,8 @@ destroy_inner:
 		mlx5_destroy_ttc_table(port_sel->inner.ttc);
 destroy_definers:
 	mlx5_lag_destroy_definers(ldev);
+clear_port_sel:
+	memset(port_sel, 0, sizeof(*port_sel));
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
index 58bd749b5e4d..129725159a93 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
@@ -100,7 +100,7 @@ static int create_aso_cq(struct mlx5_aso_cq *cq, void *cqc_data)
 
 	MLX5_SET(cqc,   cqc, cq_period_mode, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
 	MLX5_SET(cqc,   cqc, c_eqn_or_apu_element, eqn);
-	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.uar->index);
+	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.bfreg.up->index);
 	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
 					    MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(cqc, cqc, dbr_addr,      cq->wq_ctrl.db.dma);
@@ -129,7 +129,7 @@ static int mlx5_aso_create_cq(struct mlx5_core_dev *mdev, int numa_node,
 		return -ENOMEM;
 
 	MLX5_SET(cqc, cqc_data, log_cq_size, 1);
-	MLX5_SET(cqc, cqc_data, uar_page, mdev->priv.uar->index);
+	MLX5_SET(cqc, cqc_data, uar_page, mdev->priv.bfreg.up->index);
 	if (MLX5_CAP_GEN(mdev, cqe_128_always) && cache_line_size() >= 128)
 		MLX5_SET(cqc, cqc_data, cqe_sz, CQE_STRIDE_128_PAD);
 
@@ -163,7 +163,7 @@ static int mlx5_aso_alloc_sq(struct mlx5_core_dev *mdev, int numa_node,
 	struct mlx5_wq_param param;
 	int err;
 
-	sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map;
+	sq->uar_map = mdev->priv.bfreg.map;
 
 	param.db_numa_node = numa_node;
 	param.buf_numa_node = numa_node;
@@ -203,7 +203,7 @@ static int create_aso_sq(struct mlx5_core_dev *mdev, int pdn,
 	MLX5_SET(sqc, sqc, ts_format, ts_format);
 
 	MLX5_SET(wq,   wq, wq_type,       MLX5_WQ_TYPE_CYCLIC);
-	MLX5_SET(wq,   wq, uar_page,      mdev->mlx5e_res.hw_objs.bfreg.index);
+	MLX5_SET(wq,   wq, uar_page,      mdev->priv.bfreg.index);
 	MLX5_SET(wq,   wq, log_wq_pg_sz,  sq->wq_ctrl.buf.page_shift -
 					  MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(wq, wq, dbr_addr,      sq->wq_ctrl.db.dma);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 4822d01123b4..0ba0ef8bae42 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -43,6 +43,8 @@
 #include <linux/cpufeature.h>
 #endif /* CONFIG_X86 */
 
+#define MLX5_RT_CLOCK_IDENTITY_SIZE MLX5_FLD_SZ_BYTES(mrtcq_reg, rt_clock_identity)
+
 enum {
 	MLX5_PIN_MODE_IN		= 0x0,
 	MLX5_PIN_MODE_OUT		= 0x1,
@@ -77,6 +79,56 @@ enum {
 	MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX = 200000,
 };
 
+struct mlx5_clock_dev_state {
+	struct mlx5_core_dev *mdev;
+	struct mlx5_devcom_comp_dev *compdev;
+	struct mlx5_nb pps_nb;
+	struct work_struct out_work;
+};
+
+struct mlx5_clock_priv {
+	struct mlx5_clock clock;
+	struct mlx5_core_dev *mdev;
+	struct mutex lock; /* protect mdev and used in PTP callbacks */
+	struct mlx5_core_dev *event_mdev;
+};
+
+static struct mlx5_clock_priv *clock_priv(struct mlx5_clock *clock)
+{
+	return container_of(clock, struct mlx5_clock_priv, clock);
+}
+
+static void mlx5_clock_lockdep_assert(struct mlx5_clock *clock)
+{
+	if (!clock->shared)
+		return;
+
+	lockdep_assert(lockdep_is_held(&clock_priv(clock)->lock));
+}
+
+static struct mlx5_core_dev *mlx5_clock_mdev_get(struct mlx5_clock *clock)
+{
+	mlx5_clock_lockdep_assert(clock);
+
+	return clock_priv(clock)->mdev;
+}
+
+static void mlx5_clock_lock(struct mlx5_clock *clock)
+{
+	if (!clock->shared)
+		return;
+
+	mutex_lock(&clock_priv(clock)->lock);
+}
+
+static void mlx5_clock_unlock(struct mlx5_clock *clock)
+{
+	if (!clock->shared)
+		return;
+
+	mutex_unlock(&clock_priv(clock)->lock);
+}
+
 static bool mlx5_real_time_mode(struct mlx5_core_dev *mdev)
 {
 	return (mlx5_is_real_time_rq(mdev) || mlx5_is_real_time_sq(mdev));
@@ -94,6 +146,22 @@ static bool mlx5_modify_mtutc_allowed(struct mlx5_core_dev *mdev)
 	return MLX5_CAP_MCAM_FEATURE(mdev, ptpcyc2realtime_modify);
 }
 
+static int mlx5_clock_identity_get(struct mlx5_core_dev *mdev,
+				   u8 identify[MLX5_RT_CLOCK_IDENTITY_SIZE])
+{
+	u32 out[MLX5_ST_SZ_DW(mrtcq_reg)] = {};
+	u32 in[MLX5_ST_SZ_DW(mrtcq_reg)] = {};
+	int err;
+
+	err = mlx5_core_access_reg(mdev, in, sizeof(in),
+				   out, sizeof(out), MLX5_REG_MRTCQ, 0, 0);
+	if (!err)
+		memcpy(identify, MLX5_ADDR_OF(mrtcq_reg, out, rt_clock_identity),
+		       MLX5_RT_CLOCK_IDENTITY_SIZE);
+
+	return err;
+}
+
 static u32 mlx5_ptp_shift_constant(u32 dev_freq_khz)
 {
 	/* Optimal shift constant leads to corrections above just 1 scaled ppm.
@@ -119,21 +187,30 @@ static u32 mlx5_ptp_shift_constant(u32 dev_freq_khz)
 		   ilog2((U32_MAX / NSEC_PER_MSEC) * dev_freq_khz));
 }
 
+static s32 mlx5_clock_getmaxphase(struct mlx5_core_dev *mdev)
+{
+	return MLX5_CAP_MCAM_FEATURE(mdev, mtutc_time_adjustment_extended_range) ?
+		       MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX :
+			     MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX;
+}
+
 static s32 mlx5_ptp_getmaxphase(struct ptp_clock_info *ptp)
 {
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_core_dev *mdev;
+	s32 ret;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	ret = mlx5_clock_getmaxphase(mdev);
+	mlx5_clock_unlock(clock);
 
-	return MLX5_CAP_MCAM_FEATURE(mdev, mtutc_time_adjustment_extended_range) ?
-		       MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX :
-			     MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX;
+	return ret;
 }
 
 static bool mlx5_is_mtutc_time_adj_cap(struct mlx5_core_dev *mdev, s64 delta)
 {
-	s64 max = mlx5_ptp_getmaxphase(&mdev->clock.ptp_info);
+	s64 max = mlx5_clock_getmaxphase(mdev);
 
 	if (delta < -max || delta > max)
 		return false;
@@ -170,27 +247,24 @@ static bool mlx5_is_ptm_source_time_available(struct mlx5_core_dev *dev)
 	return !!MLX5_GET(mtptm_reg, out, psta);
 }
 
-static int mlx5_mtctr_syncdevicetime(ktime_t *device_time,
-				     struct system_counterval_t *sys_counterval,
-				     void *ctx)
+static int mlx5_mtctr_read(struct mlx5_core_dev *mdev,
+			   bool real_time_mode,
+			   struct system_counterval_t *sys_counterval,
+			   u64 *device)
 {
 	u32 out[MLX5_ST_SZ_DW(mtctr_reg)] = {0};
 	u32 in[MLX5_ST_SZ_DW(mtctr_reg)] = {0};
-	struct mlx5_core_dev *mdev = ctx;
-	bool real_time_mode;
-	u64 host, device;
+	u64 host;
 	int err;
 
-	real_time_mode = mlx5_real_time_mode(mdev);
-
 	MLX5_SET(mtctr_reg, in, first_clock_timestamp_request,
 		 MLX5_MTCTR_REQUEST_PTM_ROOT_CLOCK);
 	MLX5_SET(mtctr_reg, in, second_clock_timestamp_request,
 		 real_time_mode ? MLX5_MTCTR_REQUEST_REAL_TIME_CLOCK :
-		 MLX5_MTCTR_REQUEST_FREE_RUNNING_COUNTER);
+				  MLX5_MTCTR_REQUEST_FREE_RUNNING_COUNTER);
 
-	err = mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out), MLX5_REG_MTCTR,
-				   0, 0);
+	err = mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTCTR, 0, 0);
 	if (err)
 		return err;
 
@@ -204,12 +278,47 @@ static int mlx5_mtctr_syncdevicetime(ktime_t *device_time,
 			.cs_id = CSID_X86_ART,
 			.use_nsecs = true,
 	};
+	*device = MLX5_GET64(mtctr_reg, out, second_clock_timestamp);
+
+	return 0;
+}
+
+static int mlx5_mtctr_syncdevicetime(ktime_t *device_time,
+				     struct system_counterval_t *sys_counterval,
+				     void *ctx)
+{
+	struct mlx5_core_dev *mdev = ctx;
+	bool real_time_mode;
+	u64 device;
+	int err;
+
+	real_time_mode = mlx5_real_time_mode(mdev);
+
+	err = mlx5_mtctr_read(mdev, real_time_mode, sys_counterval, &device);
+	if (err)
+		return err;
 
-	device = MLX5_GET64(mtctr_reg, out, second_clock_timestamp);
 	if (real_time_mode)
 		*device_time = ns_to_ktime(REAL_TIME_TO_NS(device >> 32, device & U32_MAX));
 	else
-		*device_time = mlx5_timecounter_cyc2time(&mdev->clock, device);
+		*device_time = mlx5_timecounter_cyc2time(mdev->clock, device);
+
+	return 0;
+}
+
+static int
+mlx5_mtctr_syncdevicecyclestime(ktime_t *device_time,
+				struct system_counterval_t *sys_counterval,
+				void *ctx)
+{
+	struct mlx5_core_dev *mdev = ctx;
+	u64 device;
+	int err;
+
+	err = mlx5_mtctr_read(mdev, false, sys_counterval, &device);
+	if (err)
+		return err;
+	*device_time = ns_to_ktime(device);
 
 	return 0;
 }
@@ -220,16 +329,49 @@ static int mlx5_ptp_getcrosststamp(struct ptp_clock_info *ptp,
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct system_time_snapshot history_begin = {0};
 	struct mlx5_core_dev *mdev;
+	int err;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
-	if (!mlx5_is_ptm_source_time_available(mdev))
-		return -EBUSY;
+	if (!mlx5_is_ptm_source_time_available(mdev)) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
+	ktime_get_snapshot(&history_begin);
+
+	err = get_device_system_crosststamp(mlx5_mtctr_syncdevicetime, mdev,
+					    &history_begin, cts);
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
+}
+
+static int mlx5_ptp_getcrosscycles(struct ptp_clock_info *ptp,
+				   struct system_device_crosststamp *cts)
+{
+	struct mlx5_clock *clock =
+		container_of(ptp, struct mlx5_clock, ptp_info);
+	struct system_time_snapshot history_begin = {0};
+	struct mlx5_core_dev *mdev;
+	int err;
+
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+
+	if (!mlx5_is_ptm_source_time_available(mdev)) {
+		err = -EBUSY;
+		goto unlock;
+	}
 
 	ktime_get_snapshot(&history_begin);
 
-	return get_device_system_crosststamp(mlx5_mtctr_syncdevicetime, mdev,
-					     &history_begin, cts);
+	err = get_device_system_crosststamp(mlx5_mtctr_syncdevicecyclestime,
+					    mdev, &history_begin, cts);
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 #endif /* CONFIG_X86 */
 
@@ -259,12 +401,11 @@ static u64 mlx5_read_time(struct mlx5_core_dev *dev,
 			   (u64)timer_l | (u64)timer_h1 << 32;
 }
 
-static u64 read_internal_timer(const struct cyclecounter *cc)
+static u64 read_internal_timer(struct cyclecounter *cc)
 {
 	struct mlx5_timer *timer = container_of(cc, struct mlx5_timer, cycles);
 	struct mlx5_clock *clock = container_of(timer, struct mlx5_clock, timer);
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
-						  clock);
+	struct mlx5_core_dev *mdev = mlx5_clock_mdev_get(clock);
 
 	return mlx5_read_time(mdev, NULL, false) & cc->mask;
 }
@@ -272,7 +413,7 @@ static u64 read_internal_timer(const struct cyclecounter *cc)
 static void mlx5_update_clock_info_page(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_ib_clock_info *clock_info = mdev->clock_info;
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_timer *timer;
 	u32 sign;
 
@@ -295,12 +436,10 @@ static void mlx5_update_clock_info_page(struct mlx5_core_dev *mdev)
 
 static void mlx5_pps_out(struct work_struct *work)
 {
-	struct mlx5_pps *pps_info = container_of(work, struct mlx5_pps,
-						 out_work);
-	struct mlx5_clock *clock = container_of(pps_info, struct mlx5_clock,
-						pps_info);
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
-						  clock);
+	struct mlx5_clock_dev_state *clock_state = container_of(work, struct mlx5_clock_dev_state,
+								out_work);
+	struct mlx5_core_dev *mdev = clock_state->mdev;
+	struct mlx5_clock *clock = mdev->clock;
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
 	unsigned long flags;
 	int i;
@@ -322,17 +461,17 @@ static void mlx5_pps_out(struct work_struct *work)
 	}
 }
 
-static void mlx5_timestamp_overflow(struct work_struct *work)
+static long mlx5_timestamp_overflow(struct ptp_clock_info *ptp_info)
 {
-	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5_core_dev *mdev;
 	struct mlx5_timer *timer;
 	struct mlx5_clock *clock;
 	unsigned long flags;
 
-	timer = container_of(dwork, struct mlx5_timer, overflow_work);
-	clock = container_of(timer, struct mlx5_clock, timer);
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	clock = container_of(ptp_info, struct mlx5_clock, ptp_info);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	timer = &clock->timer;
 
 	if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
 		goto out;
@@ -343,7 +482,8 @@ static void mlx5_timestamp_overflow(struct work_struct *work)
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
 out:
-	schedule_delayed_work(&timer->overflow_work, timer->overflow_period);
+	mlx5_clock_unlock(clock);
+	return timer->overflow_period;
 }
 
 static int mlx5_ptp_settime_real_time(struct mlx5_core_dev *mdev,
@@ -362,15 +502,12 @@ static int mlx5_ptp_settime_real_time(struct mlx5_core_dev *mdev,
 	return mlx5_set_mtutc(mdev, in, sizeof(in));
 }
 
-static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts)
+static int mlx5_clock_settime(struct mlx5_core_dev *mdev, struct mlx5_clock *clock,
+			      const struct timespec64 *ts)
 {
-	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_timer *timer = &clock->timer;
-	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
-
 	if (mlx5_modify_mtutc_allowed(mdev)) {
 		int err = mlx5_ptp_settime_real_time(mdev, ts);
 
@@ -386,6 +523,20 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64
 	return 0;
 }
 
+static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts)
+{
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev;
+	int err;
+
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	err = mlx5_clock_settime(mdev, clock, ts);
+	mlx5_clock_unlock(clock);
+
+	return err;
+}
+
 static
 struct timespec64 mlx5_ptp_gettimex_real_time(struct mlx5_core_dev *mdev,
 					      struct ptp_system_timestamp *sts)
@@ -405,7 +556,8 @@ static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 	struct mlx5_core_dev *mdev;
 	u64 cycles, ns;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
 	if (mlx5_real_time_mode(mdev)) {
 		*ts = mlx5_ptp_gettimex_real_time(mdev, sts);
 		goto out;
@@ -415,6 +567,25 @@ static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 	ns = mlx5_timecounter_cyc2time(clock, cycles);
 	*ts = ns_to_timespec64(ns);
 out:
+	mlx5_clock_unlock(clock);
+	return 0;
+}
+
+static int mlx5_ptp_getcyclesx(struct ptp_clock_info *ptp,
+			       struct timespec64 *ts,
+			       struct ptp_system_timestamp *sts)
+{
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
+						ptp_info);
+	struct mlx5_core_dev *mdev;
+	u64 cycles;
+
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+
+	cycles = mlx5_read_time(mdev, sts, false);
+	*ts = ns_to_timespec64(cycles);
+	mlx5_clock_unlock(clock);
 	return 0;
 }
 
@@ -445,14 +616,16 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	struct mlx5_timer *timer = &clock->timer;
 	struct mlx5_core_dev *mdev;
 	unsigned long flags;
+	int err = 0;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
 	if (mlx5_modify_mtutc_allowed(mdev)) {
-		int err = mlx5_ptp_adjtime_real_time(mdev, delta);
+		err = mlx5_ptp_adjtime_real_time(mdev, delta);
 
 		if (err)
-			return err;
+			goto unlock;
 	}
 
 	write_seqlock_irqsave(&clock->lock, flags);
@@ -460,17 +633,23 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
-	return 0;
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta)
 {
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_core_dev *mdev;
+	int err;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	err = mlx5_ptp_adjtime_real_time(mdev, delta);
+	mlx5_clock_unlock(clock);
 
-	return mlx5_ptp_adjtime_real_time(mdev, delta);
+	return err;
 }
 
 static int mlx5_ptp_freq_adj_real_time(struct mlx5_core_dev *mdev, long scaled_ppm)
@@ -499,15 +678,17 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	struct mlx5_timer *timer = &clock->timer;
 	struct mlx5_core_dev *mdev;
 	unsigned long flags;
+	int err = 0;
 	u32 mult;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
 	if (mlx5_modify_mtutc_allowed(mdev)) {
-		int err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm);
+		err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm);
 
 		if (err)
-			return err;
+			goto unlock;
 	}
 
 	mult = (u32)adjust_by_scaled_ppm(timer->nominal_c_mult, scaled_ppm);
@@ -517,8 +698,11 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	timer->cycles.mult = mult;
 	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
+	ptp_schedule_worker(clock->ptp, timer->overflow_period);
 
-	return 0;
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static int mlx5_extts_configure(struct ptp_clock_info *ptp,
@@ -527,25 +711,14 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 {
 	struct mlx5_clock *clock =
 			container_of(ptp, struct mlx5_clock, ptp_info);
-	struct mlx5_core_dev *mdev =
-			container_of(clock, struct mlx5_core_dev, clock);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	struct mlx5_core_dev *mdev;
 	u32 field_select = 0;
 	u8 pin_mode = 0;
 	u8 pattern = 0;
 	int pin = -1;
 	int err = 0;
 
-	if (!MLX5_PPS_CAP(mdev))
-		return -EOPNOTSUPP;
-
-	/* Reject requests with unsupported flags */
-	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-				PTP_RISING_EDGE |
-				PTP_FALLING_EDGE |
-				PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	/* Reject requests to enable time stamping on both edges. */
 	if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
 	    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
@@ -569,6 +742,14 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 		field_select = MLX5_MTPPS_FS_ENABLE;
 	}
 
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+
+	if (!MLX5_PPS_CAP(mdev)) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
 	MLX5_SET(mtpps_reg, in, pin, pin);
 	MLX5_SET(mtpps_reg, in, pin_mode, pin_mode);
 	MLX5_SET(mtpps_reg, in, pattern, pattern);
@@ -577,15 +758,23 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 
 	err = mlx5_set_mtpps(mdev, in, sizeof(in));
 	if (err)
-		return err;
+		goto unlock;
+
+	err = mlx5_set_mtppse(mdev, pin, 0, MLX5_EVENT_MODE_REPETETIVE & on);
+	if (err)
+		goto unlock;
 
-	return mlx5_set_mtppse(mdev, pin, 0,
-			       MLX5_EVENT_MODE_REPETETIVE & on);
+	clock->pps_info.pin_armed[pin] = on;
+	clock_priv(clock)->event_mdev = mdev;
+
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static u64 find_target_cycles(struct mlx5_core_dev *mdev, s64 target_ns)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	u64 cycles_now, cycles_delta;
 	u64 nsec_now, nsec_delta;
 	struct mlx5_timer *timer;
@@ -644,7 +833,7 @@ static int mlx5_perout_conf_out_pulse_duration(struct mlx5_core_dev *mdev,
 					       struct ptp_clock_request *rq,
 					       u32 *out_pulse_duration_ns)
 {
-	struct mlx5_pps *pps_info = &mdev->clock.pps_info;
+	struct mlx5_pps *pps_info = &mdev->clock->pps_info;
 	u32 out_pulse_duration;
 	struct timespec64 ts;
 
@@ -677,7 +866,7 @@ static int perout_conf_npps_real_time(struct mlx5_core_dev *mdev, struct ptp_clo
 				      u32 *field_select, u32 *out_pulse_duration_ns,
 				      u64 *period, u64 *time_stamp)
 {
-	struct mlx5_pps *pps_info = &mdev->clock.pps_info;
+	struct mlx5_pps *pps_info = &mdev->clock->pps_info;
 	struct ptp_clock_time *time = &rq->perout.start;
 	struct timespec64 ts;
 
@@ -700,38 +889,24 @@ static int perout_conf_npps_real_time(struct mlx5_core_dev *mdev, struct ptp_clo
 	return 0;
 }
 
-static bool mlx5_perout_verify_flags(struct mlx5_core_dev *mdev, unsigned int flags)
-{
-	return ((!mlx5_npps_real_time_supported(mdev) && flags) ||
-		(mlx5_npps_real_time_supported(mdev) && flags & ~PTP_PEROUT_DUTY_CYCLE));
-}
-
 static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 				 struct ptp_clock_request *rq,
 				 int on)
 {
 	struct mlx5_clock *clock =
 			container_of(ptp, struct mlx5_clock, ptp_info);
-	struct mlx5_core_dev *mdev =
-			container_of(clock, struct mlx5_core_dev, clock);
-	bool rt_mode = mlx5_real_time_mode(mdev);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
 	u32 out_pulse_duration_ns = 0;
+	struct mlx5_core_dev *mdev;
 	u32 field_select = 0;
 	u64 npps_period = 0;
 	u64 time_stamp = 0;
 	u8 pin_mode = 0;
 	u8 pattern = 0;
+	bool rt_mode;
 	int pin = -1;
 	int err = 0;
 
-	if (!MLX5_PPS_CAP(mdev))
-		return -EOPNOTSUPP;
-
-	/* Reject requests with unsupported flags */
-	if (mlx5_perout_verify_flags(mdev, rq->perout.flags))
-		return -EOPNOTSUPP;
-
 	if (rq->perout.index >= clock->ptp_info.n_pins)
 		return -EINVAL;
 
@@ -740,14 +915,23 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 	if (pin < 0)
 		return -EBUSY;
 
-	if (on) {
-		bool rt_mode = mlx5_real_time_mode(mdev);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	rt_mode = mlx5_real_time_mode(mdev);
+
+	if (!MLX5_PPS_CAP(mdev)) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
 
+	if (on) {
 		pin_mode = MLX5_PIN_MODE_OUT;
 		pattern = MLX5_OUT_PATTERN_PERIODIC;
 
-		if (rt_mode &&  rq->perout.start.sec > U32_MAX)
-			return -EINVAL;
+		if (rt_mode &&  rq->perout.start.sec > U32_MAX) {
+			err = -EINVAL;
+			goto unlock;
+		}
 
 		field_select |= MLX5_MTPPS_FS_PIN_MODE |
 				MLX5_MTPPS_FS_PATTERN |
@@ -760,7 +944,7 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 		else
 			err = perout_conf_1pps(mdev, rq, &time_stamp, rt_mode);
 		if (err)
-			return err;
+			goto unlock;
 	}
 
 	MLX5_SET(mtpps_reg, in, pin, pin);
@@ -773,13 +957,16 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 	MLX5_SET(mtpps_reg, in, out_pulse_duration_ns, out_pulse_duration_ns);
 	err = mlx5_set_mtpps(mdev, in, sizeof(in));
 	if (err)
-		return err;
+		goto unlock;
 
 	if (rt_mode)
-		return 0;
+		goto unlock;
 
-	return mlx5_set_mtppse(mdev, pin, 0,
-			       MLX5_EVENT_MODE_REPETETIVE & on);
+	err = mlx5_set_mtppse(mdev, pin, 0, MLX5_EVENT_MODE_REPETETIVE & on);
+
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static int mlx5_pps_configure(struct ptp_clock_info *ptp,
@@ -852,6 +1039,7 @@ static const struct ptp_clock_info mlx5_ptp_clock_info = {
 	.settime64	= mlx5_ptp_settime,
 	.enable		= NULL,
 	.verify		= NULL,
+	.do_aux_work	= mlx5_timestamp_overflow,
 };
 
 static int mlx5_query_mtpps_pin_mode(struct mlx5_core_dev *mdev, u8 pin,
@@ -865,10 +1053,8 @@ static int mlx5_query_mtpps_pin_mode(struct mlx5_core_dev *mdev, u8 pin,
 				    mtpps_size, MLX5_REG_MTPPS, 0, 0);
 }
 
-static int mlx5_get_pps_pin_mode(struct mlx5_clock *clock, u8 pin)
+static int mlx5_get_pps_pin_mode(struct mlx5_core_dev *mdev, u8 pin)
 {
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, clock);
-
 	u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {};
 	u8 mode;
 	int err;
@@ -887,8 +1073,9 @@ static int mlx5_get_pps_pin_mode(struct mlx5_clock *clock, u8 pin)
 	return PTP_PF_NONE;
 }
 
-static void mlx5_init_pin_config(struct mlx5_clock *clock)
+static void mlx5_init_pin_config(struct mlx5_core_dev *mdev)
 {
+	struct mlx5_clock *clock = mdev->clock;
 	int i;
 
 	if (!clock->ptp_info.n_pins)
@@ -904,20 +1091,27 @@ static void mlx5_init_pin_config(struct mlx5_clock *clock)
 	clock->ptp_info.verify = mlx5_ptp_verify;
 	clock->ptp_info.pps = 1;
 
+	clock->ptp_info.supported_extts_flags = PTP_RISING_EDGE |
+						PTP_FALLING_EDGE |
+						PTP_STRICT_FLAGS;
+
+	if (mlx5_npps_real_time_supported(mdev))
+		clock->ptp_info.supported_perout_flags = PTP_PEROUT_DUTY_CYCLE;
+
 	for (i = 0; i < clock->ptp_info.n_pins; i++) {
 		snprintf(clock->ptp_info.pin_config[i].name,
 			 sizeof(clock->ptp_info.pin_config[i].name),
 			 "mlx5_pps%d", i);
 		clock->ptp_info.pin_config[i].index = i;
-		clock->ptp_info.pin_config[i].func = mlx5_get_pps_pin_mode(clock, i);
+		clock->ptp_info.pin_config[i].func = mlx5_get_pps_pin_mode(mdev, i);
 		clock->ptp_info.pin_config[i].chan = 0;
 	}
 }
 
 static void mlx5_get_pps_caps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
 	u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	struct mlx5_clock *clock = mdev->clock;
 
 	mlx5_query_mtpps(mdev, out, sizeof(out));
 
@@ -967,16 +1161,16 @@ static u64 perout_conf_next_event_timer(struct mlx5_core_dev *mdev,
 static int mlx5_pps_event(struct notifier_block *nb,
 			  unsigned long type, void *data)
 {
-	struct mlx5_clock *clock = mlx5_nb_cof(nb, struct mlx5_clock, pps_nb);
+	struct mlx5_clock_dev_state *clock_state = mlx5_nb_cof(nb, struct mlx5_clock_dev_state,
+							       pps_nb);
+	struct mlx5_core_dev *mdev = clock_state->mdev;
+	struct mlx5_clock *clock = mdev->clock;
 	struct ptp_clock_event ptp_event;
 	struct mlx5_eqe *eqe = data;
 	int pin = eqe->data.pps.pin;
-	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 	u64 ns;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
-
 	switch (clock->ptp_info.pin_config[pin].func) {
 	case PTP_PF_EXTTS:
 		ptp_event.index = pin;
@@ -996,11 +1190,15 @@ static int mlx5_pps_event(struct notifier_block *nb,
 		ptp_clock_event(clock->ptp, &ptp_event);
 		break;
 	case PTP_PF_PEROUT:
+		if (clock->shared) {
+			mlx5_core_warn(mdev, " Received unexpected PPS out event\n");
+			break;
+		}
 		ns = perout_conf_next_event_timer(mdev, clock);
 		write_seqlock_irqsave(&clock->lock, flags);
 		clock->pps_info.start[pin] = ns;
 		write_sequnlock_irqrestore(&clock->lock, flags);
-		schedule_work(&clock->pps_info.out_work);
+		schedule_work(&clock_state->out_work);
 		break;
 	default:
 		mlx5_core_err(mdev, " Unhandled clock PPS event, func %d\n",
@@ -1012,7 +1210,7 @@ static int mlx5_pps_event(struct notifier_block *nb,
 
 static void mlx5_timecounter_init(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_timer *timer = &clock->timer;
 	u32 dev_freq;
 
@@ -1028,10 +1226,10 @@ static void mlx5_timecounter_init(struct mlx5_core_dev *mdev)
 			 ktime_to_ns(ktime_get_real()));
 }
 
-static void mlx5_init_overflow_period(struct mlx5_clock *clock)
+static void mlx5_init_overflow_period(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, clock);
 	struct mlx5_ib_clock_info *clock_info = mdev->clock_info;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_timer *timer = &clock->timer;
 	u64 overflow_cycles;
 	u64 frac = 0;
@@ -1052,12 +1250,11 @@ static void mlx5_init_overflow_period(struct mlx5_clock *clock)
 	do_div(ns, NSEC_PER_SEC / HZ);
 	timer->overflow_period = ns;
 
-	INIT_DELAYED_WORK(&timer->overflow_work, mlx5_timestamp_overflow);
-	if (timer->overflow_period)
-		schedule_delayed_work(&timer->overflow_work, 0);
-	else
+	if (!timer->overflow_period) {
+		timer->overflow_period = HZ;
 		mlx5_core_warn(mdev,
-			       "invalid overflow period, overflow_work is not scheduled\n");
+			       "invalid overflow period, overflow_work is scheduled once per second\n");
+	}
 
 	if (clock_info)
 		clock_info->overflow_period = timer->overflow_period;
@@ -1065,7 +1262,7 @@ static void mlx5_init_overflow_period(struct mlx5_clock *clock)
 
 static void mlx5_init_clock_info(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_ib_clock_info *info;
 	struct mlx5_timer *timer;
 
@@ -1088,7 +1285,7 @@ static void mlx5_init_clock_info(struct mlx5_core_dev *mdev)
 
 static void mlx5_init_timer_max_freq_adjustment(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	u32 out[MLX5_ST_SZ_DW(mtutc_reg)] = {};
 	u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {};
 	u8 log_max_freq_adjustment = 0;
@@ -1107,7 +1304,8 @@ static void mlx5_init_timer_max_freq_adjustment(struct mlx5_core_dev *mdev)
 
 static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
+	bool expose_cycles;
 
 	/* Configure the PHC */
 	clock->ptp_info = mlx5_ptp_clock_info;
@@ -1115,46 +1313,48 @@ static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 	if (MLX5_CAP_MCAM_REG(mdev, mtutc))
 		mlx5_init_timer_max_freq_adjustment(mdev);
 
+	expose_cycles = !MLX5_CAP_GEN(mdev, disciplined_fr_counter) ||
+			!mlx5_real_time_mode(mdev);
+
 #ifdef CONFIG_X86
 	if (MLX5_CAP_MCAM_REG3(mdev, mtptm) &&
-	    MLX5_CAP_MCAM_REG3(mdev, mtctr) && boot_cpu_has(X86_FEATURE_ART))
+	    MLX5_CAP_MCAM_REG3(mdev, mtctr) && boot_cpu_has(X86_FEATURE_ART)) {
 		clock->ptp_info.getcrosststamp = mlx5_ptp_getcrosststamp;
+		if (expose_cycles)
+			clock->ptp_info.getcrosscycles =
+				mlx5_ptp_getcrosscycles;
+	}
 #endif /* CONFIG_X86 */
 
+	if (expose_cycles)
+		clock->ptp_info.getcyclesx64 = mlx5_ptp_getcyclesx;
+
 	mlx5_timecounter_init(mdev);
 	mlx5_init_clock_info(mdev);
-	mlx5_init_overflow_period(clock);
+	mlx5_init_overflow_period(mdev);
 
 	if (mlx5_real_time_mode(mdev)) {
 		struct timespec64 ts;
 
 		ktime_get_real_ts64(&ts);
-		mlx5_ptp_settime(&clock->ptp_info, &ts);
+		mlx5_clock_settime(mdev, clock, &ts);
 	}
 }
 
 static void mlx5_init_pps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
-
 	if (!MLX5_PPS_CAP(mdev))
 		return;
 
 	mlx5_get_pps_caps(mdev);
-	mlx5_init_pin_config(clock);
+	mlx5_init_pin_config(mdev);
 }
 
-void mlx5_init_clock(struct mlx5_core_dev *mdev)
+static void mlx5_init_clock_dev(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
-
-	if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) {
-		mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n");
-		return;
-	}
+	struct mlx5_clock *clock = mdev->clock;
 
 	seqlock_init(&clock->lock);
-	INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out);
 
 	/* Initialize the device clock */
 	mlx5_init_timer_clock(mdev);
@@ -1163,33 +1363,27 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 	mlx5_init_pps(mdev);
 
 	clock->ptp = ptp_clock_register(&clock->ptp_info,
-					&mdev->pdev->dev);
+					clock->shared ? NULL : &mdev->pdev->dev);
 	if (IS_ERR(clock->ptp)) {
-		mlx5_core_warn(mdev, "ptp_clock_register failed %ld\n",
-			       PTR_ERR(clock->ptp));
+		mlx5_core_warn(mdev, "%sptp_clock_register failed %pe\n",
+			       clock->shared ? "shared clock " : "",
+			       clock->ptp);
 		clock->ptp = NULL;
 	}
 
-	MLX5_NB_INIT(&clock->pps_nb, mlx5_pps_event, PPS_EVENT);
-	mlx5_eq_notifier_register(mdev, &clock->pps_nb);
+	if (clock->ptp)
+		ptp_schedule_worker(clock->ptp, 0);
 }
 
-void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
+static void mlx5_destroy_clock_dev(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
-
-	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
-		return;
+	struct mlx5_clock *clock = mdev->clock;
 
-	mlx5_eq_notifier_unregister(mdev, &clock->pps_nb);
 	if (clock->ptp) {
 		ptp_clock_unregister(clock->ptp);
 		clock->ptp = NULL;
 	}
 
-	cancel_work_sync(&clock->pps_info.out_work);
-	cancel_delayed_work_sync(&clock->timer.overflow_work);
-
 	if (mdev->clock_info) {
 		free_page((unsigned long)mdev->clock_info);
 		mdev->clock_info = NULL;
@@ -1197,3 +1391,253 @@ void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 
 	kfree(clock->ptp_info.pin_config);
 }
+
+static void mlx5_clock_free(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock_priv *cpriv = clock_priv(mdev->clock);
+
+	mlx5_destroy_clock_dev(mdev);
+	mutex_destroy(&cpriv->lock);
+	kfree(cpriv);
+	mdev->clock = NULL;
+}
+
+static int mlx5_clock_alloc(struct mlx5_core_dev *mdev, bool shared)
+{
+	struct mlx5_clock_priv *cpriv;
+	struct mlx5_clock *clock;
+
+	cpriv = kzalloc(sizeof(*cpriv), GFP_KERNEL);
+	if (!cpriv)
+		return -ENOMEM;
+
+	mutex_init(&cpriv->lock);
+	cpriv->mdev = mdev;
+	clock = &cpriv->clock;
+	clock->shared = shared;
+	mdev->clock = clock;
+	mlx5_clock_lock(clock);
+	mlx5_init_clock_dev(mdev);
+	mlx5_clock_unlock(clock);
+
+	if (!clock->shared)
+		return 0;
+
+	if (!clock->ptp) {
+		mlx5_core_warn(mdev, "failed to create ptp dev shared by multiple functions");
+		mlx5_clock_free(mdev);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void mlx5_shared_clock_register(struct mlx5_core_dev *mdev,
+				       u8 identity[MLX5_RT_CLOCK_IDENTITY_SIZE])
+{
+	struct mlx5_core_dev *peer_dev, *next = NULL;
+	struct mlx5_devcom_match_attr attr = {};
+	struct mlx5_devcom_comp_dev *compd;
+	struct mlx5_devcom_comp_dev *pos;
+
+	BUILD_BUG_ON(MLX5_RT_CLOCK_IDENTITY_SIZE > MLX5_DEVCOM_MATCH_KEY_MAX);
+	memcpy(attr.key.buf, identity, MLX5_RT_CLOCK_IDENTITY_SIZE);
+
+	compd = mlx5_devcom_register_component(mdev->priv.devc,
+					       MLX5_DEVCOM_SHARED_CLOCK,
+					       &attr, NULL, mdev);
+	if (!compd)
+		return;
+
+	mdev->clock_state->compdev = compd;
+
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_devcom_for_each_peer_entry(mdev->clock_state->compdev, peer_dev, pos) {
+		if (peer_dev->clock) {
+			next = peer_dev;
+			break;
+		}
+	}
+
+	if (next) {
+		mdev->clock = next->clock;
+		/* clock info is shared among all the functions using the same clock */
+		mdev->clock_info = next->clock_info;
+	} else {
+		mlx5_clock_alloc(mdev, true);
+	}
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+
+	if (!mdev->clock) {
+		mlx5_devcom_unregister_component(mdev->clock_state->compdev);
+		mdev->clock_state->compdev = NULL;
+	}
+}
+
+static void mlx5_shared_clock_unregister(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_core_dev *peer_dev, *next = NULL;
+	struct mlx5_clock *clock = mdev->clock;
+	struct mlx5_devcom_comp_dev *pos;
+
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_devcom_for_each_peer_entry(mdev->clock_state->compdev, peer_dev, pos) {
+		if (peer_dev->clock && peer_dev != mdev) {
+			next = peer_dev;
+			break;
+		}
+	}
+
+	if (next) {
+		struct mlx5_clock_priv *cpriv = clock_priv(clock);
+
+		mlx5_clock_lock(clock);
+		if (mdev == cpriv->mdev)
+			cpriv->mdev = next;
+		mlx5_clock_unlock(clock);
+	} else {
+		mlx5_clock_free(mdev);
+	}
+
+	mdev->clock = NULL;
+	mdev->clock_info = NULL;
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+
+	mlx5_devcom_unregister_component(mdev->clock_state->compdev);
+}
+
+static void mlx5_clock_arm_pps_in_event(struct mlx5_clock *clock,
+					struct mlx5_core_dev *new_mdev,
+					struct mlx5_core_dev *old_mdev)
+{
+	struct ptp_clock_info *ptp_info = &clock->ptp_info;
+	struct mlx5_clock_priv *cpriv = clock_priv(clock);
+	int i;
+
+	for (i = 0; i < ptp_info->n_pins; i++) {
+		if (ptp_info->pin_config[i].func != PTP_PF_EXTTS ||
+		    !clock->pps_info.pin_armed[i])
+			continue;
+
+		if (new_mdev) {
+			mlx5_set_mtppse(new_mdev, i, 0, MLX5_EVENT_MODE_REPETETIVE);
+			cpriv->event_mdev = new_mdev;
+		} else {
+			cpriv->event_mdev = NULL;
+		}
+
+		if (old_mdev)
+			mlx5_set_mtppse(old_mdev, i, 0, MLX5_EVENT_MODE_DISABLE);
+	}
+}
+
+void mlx5_clock_load(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock *clock = mdev->clock;
+	struct mlx5_clock_priv *cpriv;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
+		return;
+
+	INIT_WORK(&mdev->clock_state->out_work, mlx5_pps_out);
+	MLX5_NB_INIT(&mdev->clock_state->pps_nb, mlx5_pps_event, PPS_EVENT);
+	mlx5_eq_notifier_register(mdev, &mdev->clock_state->pps_nb);
+
+	if (!clock->shared) {
+		mlx5_clock_arm_pps_in_event(clock, mdev, NULL);
+		return;
+	}
+
+	cpriv = clock_priv(clock);
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_clock_lock(clock);
+	if (mdev == cpriv->mdev && mdev != cpriv->event_mdev)
+		mlx5_clock_arm_pps_in_event(clock, mdev, cpriv->event_mdev);
+	mlx5_clock_unlock(clock);
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+}
+
+void mlx5_clock_unload(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_core_dev *peer_dev, *next = NULL;
+	struct mlx5_clock *clock = mdev->clock;
+	struct mlx5_devcom_comp_dev *pos;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
+		return;
+
+	if (!clock->shared) {
+		mlx5_clock_arm_pps_in_event(clock, NULL, mdev);
+		goto out;
+	}
+
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_devcom_for_each_peer_entry(mdev->clock_state->compdev, peer_dev, pos) {
+		if (peer_dev->clock && peer_dev != mdev) {
+			next = peer_dev;
+			break;
+		}
+	}
+
+	mlx5_clock_lock(clock);
+	if (mdev == clock_priv(clock)->event_mdev)
+		mlx5_clock_arm_pps_in_event(clock, next, mdev);
+	mlx5_clock_unlock(clock);
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+
+out:
+	mlx5_eq_notifier_unregister(mdev, &mdev->clock_state->pps_nb);
+	cancel_work_sync(&mdev->clock_state->out_work);
+}
+
+static struct mlx5_clock null_clock;
+
+int mlx5_init_clock(struct mlx5_core_dev *mdev)
+{
+	u8 identity[MLX5_RT_CLOCK_IDENTITY_SIZE];
+	struct mlx5_clock_dev_state *clock_state;
+	int err;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) {
+		mdev->clock = &null_clock;
+		mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n");
+		return 0;
+	}
+
+	clock_state = kzalloc(sizeof(*clock_state), GFP_KERNEL);
+	if (!clock_state)
+		return -ENOMEM;
+	clock_state->mdev = mdev;
+	mdev->clock_state = clock_state;
+
+	if (MLX5_CAP_MCAM_REG3(mdev, mrtcq) && mlx5_real_time_mode(mdev)) {
+		if (mlx5_clock_identity_get(mdev, identity))
+			mlx5_core_warn(mdev, "failed to get rt clock identity, create ptp dev per function\n");
+		else
+			mlx5_shared_clock_register(mdev, identity);
+	}
+
+	if (!mdev->clock) {
+		err = mlx5_clock_alloc(mdev, false);
+		if (err) {
+			kfree(clock_state);
+			mdev->clock_state = NULL;
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
+{
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
+		return;
+
+	if (mdev->clock->shared)
+		mlx5_shared_clock_unregister(mdev);
+	else
+		mlx5_clock_free(mdev);
+	kfree(mdev->clock_state);
+	mdev->clock_state = NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index bd95b9f8d143..aff3aed62c74 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -33,6 +33,34 @@
 #ifndef __LIB_CLOCK_H__
 #define __LIB_CLOCK_H__
 
+#include <linux/ptp_clock_kernel.h>
+
+#define MAX_PIN_NUM	8
+struct mlx5_pps {
+	u8                         pin_caps[MAX_PIN_NUM];
+	u64                        start[MAX_PIN_NUM];
+	u8                         enabled;
+	u64                        min_npps_period;
+	u64                        min_out_pulse_duration_ns;
+	bool                       pin_armed[MAX_PIN_NUM];
+};
+
+struct mlx5_timer {
+	struct cyclecounter        cycles;
+	struct timecounter         tc;
+	u32                        nominal_c_mult;
+	unsigned long              overflow_period;
+};
+
+struct mlx5_clock {
+	seqlock_t                  lock;
+	struct ptp_clock          *ptp;
+	struct ptp_clock_info      ptp_info;
+	struct mlx5_pps            pps_info;
+	struct mlx5_timer          timer;
+	bool                       shared;
+};
+
 static inline bool mlx5_is_real_time_rq(struct mlx5_core_dev *mdev)
 {
 	u8 rq_ts_format_cap = MLX5_CAP_GEN(mdev, rq_ts_format);
@@ -54,12 +82,14 @@ static inline bool mlx5_is_real_time_sq(struct mlx5_core_dev *mdev)
 typedef ktime_t (*cqe_ts_to_ns)(struct mlx5_clock *, u64);
 
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
-void mlx5_init_clock(struct mlx5_core_dev *mdev);
+int mlx5_init_clock(struct mlx5_core_dev *mdev);
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev);
+void mlx5_clock_load(struct mlx5_core_dev *mdev);
+void mlx5_clock_unload(struct mlx5_core_dev *mdev);
 
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
-	return mdev->clock.ptp ? ptp_clock_index(mdev->clock.ptp) : -1;
+	return mdev->clock->ptp ? ptp_clock_index(mdev->clock->ptp) : -1;
 }
 
 static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
@@ -87,8 +117,10 @@ static inline ktime_t mlx5_real_time_cyc2time(struct mlx5_clock *clock,
 	return ns_to_ktime(time);
 }
 #else
-static inline void mlx5_init_clock(struct mlx5_core_dev *mdev) {}
+static inline int mlx5_init_clock(struct mlx5_core_dev *mdev) { return 0; }
 static inline void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_clock_load(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_clock_unload(struct mlx5_core_dev *mdev) {}
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
 	return -1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.h
index c819c047bb9c..4821163a547f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.h
@@ -8,6 +8,7 @@ enum {
 	MLX5_ACCEL_OBJ_TLS_KEY = MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_TLS,
 	MLX5_ACCEL_OBJ_IPSEC_KEY = MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_IPSEC,
 	MLX5_ACCEL_OBJ_MACSEC_KEY = MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_MACSEC,
+	MLX5_ACCEL_OBJ_PSP_KEY = MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_PSP,
 	MLX5_ACCEL_OBJ_TYPE_KEY_NUM,
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
index 7b0766c89f4c..e749618229bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
@@ -4,6 +4,7 @@
 #include <linux/mlx5/vport.h>
 #include <linux/list.h>
 #include "lib/devcom.h"
+#include "lib/mlx5.h"
 #include "mlx5_core.h"
 
 static LIST_HEAD(devcom_dev_list);
@@ -22,11 +23,17 @@ struct mlx5_devcom_dev {
 	struct kref ref;
 };
 
+struct mlx5_devcom_key {
+	u32 flags;
+	union mlx5_devcom_match_key key;
+	possible_net_t net;
+};
+
 struct mlx5_devcom_comp {
 	struct list_head comp_list;
 	enum mlx5_devcom_component id;
-	u64 key;
 	struct list_head comp_dev_list_head;
+	struct mlx5_devcom_key key;
 	mlx5_devcom_event_handler_t handler;
 	struct kref ref;
 	bool ready;
@@ -69,20 +76,18 @@ mlx5_devcom_dev_alloc(struct mlx5_core_dev *dev)
 struct mlx5_devcom_dev *
 mlx5_devcom_register_device(struct mlx5_core_dev *dev)
 {
-	struct mlx5_devcom_dev *devc;
+	struct mlx5_devcom_dev *devc = NULL;
 
 	mutex_lock(&dev_list_lock);
 
 	if (devcom_dev_exists(dev)) {
-		devc = ERR_PTR(-EEXIST);
+		mlx5_core_err(dev, "devcom device already exists");
 		goto out;
 	}
 
 	devc = mlx5_devcom_dev_alloc(dev);
-	if (!devc) {
-		devc = ERR_PTR(-ENOMEM);
+	if (!devc)
 		goto out;
-	}
 
 	list_add_tail(&devc->list, &devcom_dev_list);
 out:
@@ -103,21 +108,27 @@ mlx5_devcom_dev_release(struct kref *ref)
 
 void mlx5_devcom_unregister_device(struct mlx5_devcom_dev *devc)
 {
-	if (!IS_ERR_OR_NULL(devc))
-		kref_put(&devc->ref, mlx5_devcom_dev_release);
+	if (!devc)
+		return;
+
+	kref_put(&devc->ref, mlx5_devcom_dev_release);
 }
 
 static struct mlx5_devcom_comp *
-mlx5_devcom_comp_alloc(u64 id, u64 key, mlx5_devcom_event_handler_t handler)
+mlx5_devcom_comp_alloc(u64 id, const struct mlx5_devcom_match_attr *attr,
+		       mlx5_devcom_event_handler_t handler)
 {
 	struct mlx5_devcom_comp *comp;
 
 	comp = kzalloc(sizeof(*comp), GFP_KERNEL);
 	if (!comp)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	comp->id = id;
-	comp->key = key;
+	comp->key.key = attr->key;
+	comp->key.flags = attr->flags;
+	if (attr->flags & MLX5_DEVCOM_MATCH_FLAGS_NS)
+		write_pnet(&comp->key.net, attr->net);
 	comp->handler = handler;
 	init_rwsem(&comp->sem);
 	lockdep_register_key(&comp->lock_key);
@@ -149,7 +160,7 @@ devcom_alloc_comp_dev(struct mlx5_devcom_dev *devc,
 
 	devcom = kzalloc(sizeof(*devcom), GFP_KERNEL);
 	if (!devcom)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	kref_get(&devc->ref);
 	devcom->devc = devc;
@@ -180,21 +191,34 @@ devcom_free_comp_dev(struct mlx5_devcom_comp_dev *devcom)
 static bool
 devcom_component_equal(struct mlx5_devcom_comp *devcom,
 		       enum mlx5_devcom_component id,
-		       u64 key)
+		       const struct mlx5_devcom_match_attr *attr)
 {
-	return devcom->id == id && devcom->key == key;
+	if (devcom->id != id)
+		return false;
+
+	if (devcom->key.flags != attr->flags)
+		return false;
+
+	if (memcmp(&devcom->key.key, &attr->key, sizeof(devcom->key.key)))
+		return false;
+
+	if (devcom->key.flags & MLX5_DEVCOM_MATCH_FLAGS_NS &&
+	    !net_eq(read_pnet(&devcom->key.net), attr->net))
+		return false;
+
+	return true;
 }
 
 static struct mlx5_devcom_comp *
 devcom_component_get(struct mlx5_devcom_dev *devc,
 		     enum mlx5_devcom_component id,
-		     u64 key,
+		     const struct mlx5_devcom_match_attr *attr,
 		     mlx5_devcom_event_handler_t handler)
 {
 	struct mlx5_devcom_comp *comp;
 
 	devcom_for_each_component(comp) {
-		if (devcom_component_equal(comp, id, key)) {
+		if (devcom_component_equal(comp, id, attr)) {
 			if (handler == comp->handler) {
 				kref_get(&comp->ref);
 				return comp;
@@ -212,35 +236,32 @@ devcom_component_get(struct mlx5_devcom_dev *devc,
 struct mlx5_devcom_comp_dev *
 mlx5_devcom_register_component(struct mlx5_devcom_dev *devc,
 			       enum mlx5_devcom_component id,
-			       u64 key,
+			       const struct mlx5_devcom_match_attr *attr,
 			       mlx5_devcom_event_handler_t handler,
 			       void *data)
 {
-	struct mlx5_devcom_comp_dev *devcom;
+	struct mlx5_devcom_comp_dev *devcom = NULL;
 	struct mlx5_devcom_comp *comp;
 
-	if (IS_ERR_OR_NULL(devc))
-		return ERR_PTR(-EINVAL);
+	if (!devc)
+		return NULL;
 
 	mutex_lock(&comp_list_lock);
-	comp = devcom_component_get(devc, id, key, handler);
-	if (IS_ERR(comp)) {
-		devcom = ERR_PTR(-EINVAL);
+	comp = devcom_component_get(devc, id, attr, handler);
+	if (IS_ERR(comp))
 		goto out_unlock;
-	}
 
 	if (!comp) {
-		comp = mlx5_devcom_comp_alloc(id, key, handler);
-		if (IS_ERR(comp)) {
-			devcom = ERR_CAST(comp);
+		comp = mlx5_devcom_comp_alloc(id, attr, handler);
+		if (!comp)
 			goto out_unlock;
-		}
+
 		list_add_tail(&comp->comp_list, &devcom_comp_list);
 	}
 	mutex_unlock(&comp_list_lock);
 
 	devcom = devcom_alloc_comp_dev(devc, comp, data);
-	if (IS_ERR(devcom))
+	if (!devcom)
 		kref_put(&comp->ref, mlx5_devcom_comp_release);
 
 	return devcom;
@@ -252,8 +273,10 @@ out_unlock:
 
 void mlx5_devcom_unregister_component(struct mlx5_devcom_comp_dev *devcom)
 {
-	if (!IS_ERR_OR_NULL(devcom))
-		devcom_free_comp_dev(devcom);
+	if (!devcom)
+		return;
+
+	devcom_free_comp_dev(devcom);
 }
 
 int mlx5_devcom_comp_get_size(struct mlx5_devcom_comp_dev *devcom)
@@ -272,7 +295,7 @@ int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom,
 	int err = 0;
 	void *data;
 
-	if (IS_ERR_OR_NULL(devcom))
+	if (!devcom)
 		return -ENODEV;
 
 	comp = devcom->comp;
@@ -314,7 +337,7 @@ void mlx5_devcom_comp_set_ready(struct mlx5_devcom_comp_dev *devcom, bool ready)
 
 bool mlx5_devcom_comp_is_ready(struct mlx5_devcom_comp_dev *devcom)
 {
-	if (IS_ERR_OR_NULL(devcom))
+	if (!devcom)
 		return false;
 
 	return READ_ONCE(devcom->comp->ready);
@@ -324,7 +347,7 @@ bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom_comp_dev *devcom)
 {
 	struct mlx5_devcom_comp *comp;
 
-	if (IS_ERR_OR_NULL(devcom))
+	if (!devcom)
 		return false;
 
 	comp = devcom->comp;
@@ -397,21 +420,21 @@ void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom_comp_dev *devcom,
 
 void mlx5_devcom_comp_lock(struct mlx5_devcom_comp_dev *devcom)
 {
-	if (IS_ERR_OR_NULL(devcom))
+	if (!devcom)
 		return;
 	down_write(&devcom->comp->sem);
 }
 
 void mlx5_devcom_comp_unlock(struct mlx5_devcom_comp_dev *devcom)
 {
-	if (IS_ERR_OR_NULL(devcom))
+	if (!devcom)
 		return;
 	up_write(&devcom->comp->sem);
 }
 
 int mlx5_devcom_comp_trylock(struct mlx5_devcom_comp_dev *devcom)
 {
-	if (IS_ERR_OR_NULL(devcom))
+	if (!devcom)
 		return 0;
 	return down_write_trylock(&devcom->comp->sem);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
index d58032dd0df7..91e5ae529d5c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
@@ -6,11 +6,28 @@
 
 #include <linux/mlx5/driver.h>
 
+enum mlx5_devom_match_flags {
+	MLX5_DEVCOM_MATCH_FLAGS_NS = BIT(0),
+};
+
+#define MLX5_DEVCOM_MATCH_KEY_MAX 32
+union mlx5_devcom_match_key {
+	u64 val;
+	u8 buf[MLX5_DEVCOM_MATCH_KEY_MAX];
+};
+
+struct mlx5_devcom_match_attr {
+	u32 flags;
+	union mlx5_devcom_match_key key;
+	struct net *net;
+};
+
 enum mlx5_devcom_component {
 	MLX5_DEVCOM_ESW_OFFLOADS,
 	MLX5_DEVCOM_MPV,
 	MLX5_DEVCOM_HCA_PORTS,
 	MLX5_DEVCOM_SD_GROUP,
+	MLX5_DEVCOM_SHARED_CLOCK,
 	MLX5_DEVCOM_NUM_COMPONENTS,
 };
 
@@ -24,7 +41,7 @@ void mlx5_devcom_unregister_device(struct mlx5_devcom_dev *devc);
 struct mlx5_devcom_comp_dev *
 mlx5_devcom_register_component(struct mlx5_devcom_dev *devc,
 			       enum mlx5_devcom_component id,
-			       u64 key,
+			       const struct mlx5_devcom_match_attr *attr,
 			       mlx5_devcom_event_handler_t handler,
 			       void *data);
 void mlx5_devcom_unregister_component(struct mlx5_devcom_comp_dev *devcom);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c
index 7c5516b0a844..8115071c34a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c
@@ -30,7 +30,7 @@ struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev)
 
 	dm = kzalloc(sizeof(*dm), GFP_KERNEL);
 	if (!dm)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	spin_lock_init(&dm->lock);
 
@@ -96,7 +96,7 @@ err_modify_hdr:
 err_steering:
 	kfree(dm);
 
-	return ERR_PTR(-ENOMEM);
+	return NULL;
 }
 
 void mlx5_dm_cleanup(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index a80ecb672f33..0a3c260af377 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -161,7 +161,8 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains,
 		ft_attr.flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
 				  MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
 
-	sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ? FT_TBL_SZ : POOL_NEXT_SIZE;
+	sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ?
+		FT_TBL_SZ : MLX5_FS_MAX_POOL_SIZE;
 	ft_attr.max_fte = sz;
 
 	/* We use chains_default_ft(chains) as the table's next_ft till
@@ -196,6 +197,11 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains,
 		ns = mlx5_get_flow_namespace(chains->dev, chains->ns);
 	}
 
+	if (!ns) {
+		mlx5_core_warn(chains->dev, "Failed to get flow namespace\n");
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	ft_attr.autogroup.num_reserved_entries = 2;
 	ft_attr.autogroup.max_num_groups = chains->group_num;
 	ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
@@ -699,7 +705,7 @@ mlx5_chains_create_global_table(struct mlx5_fs_chains *chains)
 		goto err_ignore;
 	}
 
-	chain = mlx5_chains_get_chain_range(chains),
+	chain = mlx5_chains_get_chain_range(chains);
 	prio = mlx5_chains_get_prio_range(chains);
 	level = mlx5_chains_get_level_range(chains);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
index 9f13cea16446..7adad784ad46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
@@ -9,7 +9,7 @@
 #include "mlx5_core.h"
 #include "lib/fs_ttc.h"
 
-#define MLX5_TTC_MAX_NUM_GROUPS		4
+#define MLX5_TTC_MAX_NUM_GROUPS		7
 #define MLX5_TTC_GROUP_TCPUDP_SIZE	(MLX5_TT_IPV6_UDP + 1)
 
 struct mlx5_fs_ttc_groups {
@@ -31,10 +31,14 @@ static int mlx5_fs_ttc_table_size(const struct mlx5_fs_ttc_groups *groups)
 /* L3/L4 traffic type classifier */
 struct mlx5_ttc_table {
 	int num_groups;
+	const struct mlx5_fs_ttc_groups *groups;
+	struct mlx5_core_dev *mdev;
 	struct mlx5_flow_table *t;
 	struct mlx5_flow_group **g;
 	struct mlx5_ttc_rule rules[MLX5_NUM_TT];
 	struct mlx5_flow_handle *tunnel_rules[MLX5_NUM_TUNNEL_TT];
+	u32 refcnt;
+	struct mutex mutex; /* Protect adding rules for ipsec crypto offload */
 };
 
 struct mlx5_flow_table *mlx5_get_ttc_flow_table(struct mlx5_ttc_table *ttc)
@@ -61,6 +65,25 @@ static void mlx5_cleanup_ttc_rules(struct mlx5_ttc_table *ttc)
 	}
 }
 
+static const char *mlx5_traffic_types_names[MLX5_NUM_TT] = {
+	[MLX5_TT_IPV4_TCP] =  "TT_IPV4_TCP",
+	[MLX5_TT_IPV6_TCP] =  "TT_IPV6_TCP",
+	[MLX5_TT_IPV4_UDP] =  "TT_IPV4_UDP",
+	[MLX5_TT_IPV6_UDP] =  "TT_IPV6_UDP",
+	[MLX5_TT_IPV4_IPSEC_AH] = "TT_IPV4_IPSEC_AH",
+	[MLX5_TT_IPV6_IPSEC_AH] = "TT_IPV6_IPSEC_AH",
+	[MLX5_TT_IPV4_IPSEC_ESP] = "TT_IPV4_IPSEC_ESP",
+	[MLX5_TT_IPV6_IPSEC_ESP] = "TT_IPV6_IPSEC_ESP",
+	[MLX5_TT_IPV4] = "TT_IPV4",
+	[MLX5_TT_IPV6] = "TT_IPV6",
+	[MLX5_TT_ANY] = "TT_ANY"
+};
+
+const char *mlx5_ttc_get_name(enum mlx5_traffic_types tt)
+{
+	return mlx5_traffic_types_names[tt];
+}
+
 struct mlx5_etype_proto {
 	u16 etype;
 	u8 proto;
@@ -144,6 +167,8 @@ static struct mlx5_etype_proto ttc_tunnel_rules[] = {
 enum TTC_GROUP_TYPE {
 	TTC_GROUPS_DEFAULT = 0,
 	TTC_GROUPS_USE_L4_TYPE = 1,
+	TTC_GROUPS_DEFAULT_ESP = 2,
+	TTC_GROUPS_USE_L4_TYPE_ESP = 3,
 };
 
 static const struct mlx5_fs_ttc_groups ttc_groups[] = {
@@ -165,6 +190,31 @@ static const struct mlx5_fs_ttc_groups ttc_groups[] = {
 			BIT(0),
 		},
 	},
+	[TTC_GROUPS_DEFAULT_ESP] = {
+		.num_groups = 6,
+		.group_size = {
+			MLX5_TTC_GROUP_TCPUDP_SIZE + BIT(1) +
+			MLX5_NUM_TUNNEL_TT,
+			BIT(2), /* decrypted outer L4 */
+			BIT(2), /* decrypted inner L4 */
+			BIT(1), /* ESP */
+			BIT(1),
+			BIT(0),
+		},
+	},
+	[TTC_GROUPS_USE_L4_TYPE_ESP] = {
+		.use_l4_type = true,
+		.num_groups = 7,
+		.group_size = {
+			MLX5_TTC_GROUP_TCPUDP_SIZE,
+			BIT(1) + MLX5_NUM_TUNNEL_TT,
+			BIT(2), /* decrypted outer L4 */
+			BIT(2), /* decrypted inner L4 */
+			BIT(1), /* ESP */
+			BIT(1),
+			BIT(0),
+		},
+	},
 };
 
 static const struct mlx5_fs_ttc_groups inner_ttc_groups[] = {
@@ -188,6 +238,23 @@ static const struct mlx5_fs_ttc_groups inner_ttc_groups[] = {
 	},
 };
 
+static const struct mlx5_fs_ttc_groups *
+mlx5_ttc_get_fs_groups(bool use_l4_type, bool ipsec_rss)
+{
+	if (!ipsec_rss)
+		return use_l4_type ? &ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
+				     &ttc_groups[TTC_GROUPS_DEFAULT];
+
+	return use_l4_type ? &ttc_groups[TTC_GROUPS_USE_L4_TYPE_ESP] :
+			     &ttc_groups[TTC_GROUPS_DEFAULT_ESP];
+}
+
+bool mlx5_ttc_has_esp_flow_group(struct mlx5_ttc_table *ttc)
+{
+	return ttc->groups == &ttc_groups[TTC_GROUPS_DEFAULT_ESP] ||
+	       ttc->groups == &ttc_groups[TTC_GROUPS_USE_L4_TYPE_ESP];
+}
+
 u8 mlx5_get_proto_by_tunnel_type(enum mlx5_tunnel_types tt)
 {
 	return ttc_tunnel_rules[tt].proto;
@@ -238,6 +305,31 @@ static u8 mlx5_etype_to_ipv(u16 ethertype)
 	return 0;
 }
 
+static void mlx5_fs_ttc_set_match_ipv_outer(struct mlx5_core_dev *mdev,
+					    struct mlx5_flow_spec *spec,
+					    u16 etype)
+{
+	int match_ipv_outer =
+		MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
+					  ft_field_support.outer_ip_version);
+	u8 ipv;
+
+	ipv = mlx5_etype_to_ipv(etype);
+	if (match_ipv_outer && ipv) {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 outer_headers.ip_version);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 outer_headers.ip_version, ipv);
+	} else {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 outer_headers.ethertype);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 outer_headers.ethertype, etype);
+	}
+
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+}
+
 static void mlx5_fs_ttc_set_match_proto(void *headers_c, void *headers_v,
 					u8 proto, bool use_l4_type)
 {
@@ -260,16 +352,12 @@ static void mlx5_fs_ttc_set_match_proto(void *headers_c, void *headers_v,
 static struct mlx5_flow_handle *
 mlx5_generate_ttc_rule(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft,
 		       struct mlx5_flow_destination *dest, u16 etype, u8 proto,
-		       bool use_l4_type)
+		       bool use_l4_type, bool ipsec_rss)
 {
-	int match_ipv_outer =
-		MLX5_CAP_FLOWTABLE_NIC_RX(dev,
-					  ft_field_support.outer_ip_version);
 	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
 	int err = 0;
-	u8 ipv;
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec)
@@ -286,15 +374,15 @@ mlx5_generate_ttc_rule(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft,
 					    proto, use_l4_type);
 	}
 
-	ipv = mlx5_etype_to_ipv(etype);
-	if (match_ipv_outer && ipv) {
-		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_version);
-		MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_version, ipv);
-	} else if (etype) {
-		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ethertype);
-		MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype, etype);
+	if (etype)
+		mlx5_fs_ttc_set_match_ipv_outer(dev, spec, etype);
+
+	if (ipsec_rss && proto == IPPROTO_ESP) {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 misc_parameters_2.ipsec_next_header);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 misc_parameters_2.ipsec_next_header, 0);
+		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
 	}
 
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1);
@@ -323,12 +411,16 @@ static int mlx5_generate_ttc_table_rules(struct mlx5_core_dev *dev,
 	for (tt = 0; tt < MLX5_NUM_TT; tt++) {
 		struct mlx5_ttc_rule *rule = &rules[tt];
 
+		if (mlx5_ttc_is_decrypted_esp_tt(tt))
+			continue;
+
 		if (test_bit(tt, params->ignore_dests))
 			continue;
 		rule->rule = mlx5_generate_ttc_rule(dev, ft, &params->dests[tt],
 						    ttc_rules[tt].etype,
 						    ttc_rules[tt].proto,
-						    use_l4_type);
+						    use_l4_type,
+						    params->ipsec_rss);
 		if (IS_ERR(rule->rule)) {
 			err = PTR_ERR(rule->rule);
 			rule->rule = NULL;
@@ -351,7 +443,7 @@ static int mlx5_generate_ttc_table_rules(struct mlx5_core_dev *dev,
 						    &params->tunnel_dests[tt],
 						    ttc_tunnel_rules[tt].etype,
 						    ttc_tunnel_rules[tt].proto,
-						    use_l4_type);
+						    use_l4_type, false);
 		if (IS_ERR(trules[tt])) {
 			err = PTR_ERR(trules[tt]);
 			trules[tt] = NULL;
@@ -366,10 +458,78 @@ del_rules:
 	return err;
 }
 
+static int mlx5_create_ttc_table_ipsec_groups(struct mlx5_ttc_table *ttc,
+					      bool use_ipv,
+					      u32 *in, int *next_ix)
+{
+	u8 *mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+	const struct mlx5_fs_ttc_groups *groups = ttc->groups;
+	int ix = *next_ix;
+
+	MLX5_SET(fte_match_param, mc, outer_headers.ip_protocol, 0);
+
+	/* decrypted ESP outer group */
+	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
+	MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.l4_type_ext);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += groups->group_size[ttc->num_groups];
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
+	if (IS_ERR(ttc->g[ttc->num_groups]))
+		goto err;
+	ttc->num_groups++;
+
+	MLX5_SET(fte_match_param, mc, outer_headers.l4_type_ext, 0);
+
+	/* decrypted ESP inner group */
+	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_INNER_HEADERS);
+	if (use_ipv)
+		MLX5_SET(fte_match_param, mc, outer_headers.ip_version, 0);
+	else
+		MLX5_SET(fte_match_param, mc, outer_headers.ethertype, 0);
+	MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_version);
+	MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.l4_type_ext);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += groups->group_size[ttc->num_groups];
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
+	if (IS_ERR(ttc->g[ttc->num_groups]))
+		goto err;
+	ttc->num_groups++;
+
+	MLX5_SET(fte_match_param, mc, inner_headers.ip_version, 0);
+	MLX5_SET(fte_match_param, mc, inner_headers.l4_type_ext, 0);
+
+	/* undecrypted ESP group */
+	MLX5_SET_CFG(in, match_criteria_enable,
+		     MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2);
+	if (use_ipv)
+		MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_version);
+	else
+		MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype);
+	MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol);
+	MLX5_SET_TO_ONES(fte_match_param, mc,
+			 misc_parameters_2.ipsec_next_header);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += groups->group_size[ttc->num_groups];
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
+	if (IS_ERR(ttc->g[ttc->num_groups]))
+		goto err;
+	ttc->num_groups++;
+
+	*next_ix = ix;
+
+	return 0;
+
+err:
+	return PTR_ERR(ttc->g[ttc->num_groups]);
+}
+
 static int mlx5_create_ttc_table_groups(struct mlx5_ttc_table *ttc,
-					bool use_ipv,
-					const struct mlx5_fs_ttc_groups *groups)
+					bool use_ipv)
 {
+	const struct mlx5_fs_ttc_groups *groups = ttc->groups;
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	int ix = 0;
 	u32 *in;
@@ -417,8 +577,18 @@ static int mlx5_create_ttc_table_groups(struct mlx5_ttc_table *ttc,
 		goto err;
 	ttc->num_groups++;
 
+	if (mlx5_ttc_has_esp_flow_group(ttc)) {
+		err = mlx5_create_ttc_table_ipsec_groups(ttc, use_ipv, in, &ix);
+		if (err)
+			goto err;
+
+		MLX5_SET(fte_match_param, mc,
+			 misc_parameters_2.ipsec_next_header, 0);
+	}
+
 	/* L3 Group */
 	MLX5_SET(fte_match_param, mc, outer_headers.ip_protocol, 0);
+	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
 	MLX5_SET_CFG(in, start_flow_index, ix);
 	ix += groups->group_size[ttc->num_groups];
 	MLX5_SET_CFG(in, end_flow_index, ix - 1);
@@ -508,6 +678,9 @@ static int mlx5_generate_inner_ttc_table_rules(struct mlx5_core_dev *dev,
 	for (tt = 0; tt < MLX5_NUM_TT; tt++) {
 		struct mlx5_ttc_rule *rule = &rules[tt];
 
+		if (mlx5_ttc_is_decrypted_esp_tt(tt))
+			continue;
+
 		if (test_bit(tt, params->ignore_dests))
 			continue;
 		rule->rule = mlx5_generate_inner_ttc_rule(dev, ft,
@@ -618,10 +791,6 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
 	bool use_l4_type;
 	int err;
 
-	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
-	if (!ttc)
-		return ERR_PTR(-ENOMEM);
-
 	switch (params->ns_type) {
 	case MLX5_FLOW_NAMESPACE_PORT_SEL:
 		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -635,7 +804,16 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
 	ns = mlx5_get_flow_namespace(dev, params->ns_type);
+	if (!ns) {
+		kvfree(ttc);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	groups = use_l4_type ? &inner_ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
 			       &inner_ttc_groups[TTC_GROUPS_DEFAULT];
 
@@ -676,6 +854,7 @@ void mlx5_destroy_ttc_table(struct mlx5_ttc_table *ttc)
 
 	kfree(ttc->g);
 	mlx5_destroy_flow_table(ttc->t);
+	mutex_destroy(&ttc->mutex);
 	kvfree(ttc);
 }
 
@@ -685,16 +864,11 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
 	bool match_ipv_outer =
 		MLX5_CAP_FLOWTABLE_NIC_RX(dev,
 					  ft_field_support.outer_ip_version);
-	const struct mlx5_fs_ttc_groups *groups;
 	struct mlx5_flow_namespace *ns;
 	struct mlx5_ttc_table *ttc;
 	bool use_l4_type;
 	int err;
 
-	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
-	if (!ttc)
-		return ERR_PTR(-ENOMEM);
-
 	switch (params->ns_type) {
 	case MLX5_FLOW_NAMESPACE_PORT_SEL:
 		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -708,12 +882,20 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
 	ns = mlx5_get_flow_namespace(dev, params->ns_type);
-	groups = use_l4_type ? &ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
-			       &ttc_groups[TTC_GROUPS_DEFAULT];
+	if (!ns) {
+		kvfree(ttc);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	ttc->groups = mlx5_ttc_get_fs_groups(use_l4_type, params->ipsec_rss);
 
 	WARN_ON_ONCE(params->ft_attr.max_fte);
-	params->ft_attr.max_fte = mlx5_fs_ttc_table_size(groups);
+	params->ft_attr.max_fte = mlx5_fs_ttc_table_size(ttc->groups);
 	ttc->t = mlx5_create_flow_table(ns, &params->ft_attr);
 	if (IS_ERR(ttc->t)) {
 		err = PTR_ERR(ttc->t);
@@ -721,7 +903,7 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
 		return ERR_PTR(err);
 	}
 
-	err = mlx5_create_ttc_table_groups(ttc, match_ipv_outer, groups);
+	err = mlx5_create_ttc_table_groups(ttc, match_ipv_outer);
 	if (err)
 		goto destroy_ft;
 
@@ -729,6 +911,9 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
 	if (err)
 		goto destroy_ft;
 
+	ttc->mdev = dev;
+	mutex_init(&ttc->mutex);
+
 	return ttc;
 
 destroy_ft:
@@ -762,3 +947,194 @@ int mlx5_ttc_fwd_default_dest(struct mlx5_ttc_table *ttc,
 
 	return mlx5_ttc_fwd_dest(ttc, type, &dest);
 }
+
+static void _mlx5_ttc_destroy_ipsec_rules(struct mlx5_ttc_table *ttc)
+{
+	enum mlx5_traffic_types i;
+
+	for (i = MLX5_TT_DECRYPTED_ESP_OUTER_IPV4_TCP;
+	     i <= MLX5_TT_DECRYPTED_ESP_INNER_IPV6_UDP; i++) {
+		if (!ttc->rules[i].rule)
+			continue;
+
+		mlx5_del_flow_rules(ttc->rules[i].rule);
+		ttc->rules[i].rule = NULL;
+	}
+}
+
+void mlx5_ttc_destroy_ipsec_rules(struct mlx5_ttc_table *ttc)
+{
+	if (!mlx5_ttc_has_esp_flow_group(ttc))
+		return;
+
+	mutex_lock(&ttc->mutex);
+	if (--ttc->refcnt)
+		goto unlock;
+
+	_mlx5_ttc_destroy_ipsec_rules(ttc);
+unlock:
+	mutex_unlock(&ttc->mutex);
+}
+
+static int mlx5_ttc_get_tt_attrs(enum mlx5_traffic_types type,
+				 u16 *etype, int *l4_type_ext,
+				 enum mlx5_traffic_types *tir_tt)
+{
+	switch (type) {
+	case MLX5_TT_DECRYPTED_ESP_OUTER_IPV4_TCP:
+	case MLX5_TT_DECRYPTED_ESP_INNER_IPV4_TCP:
+		*etype = ETH_P_IP;
+		*l4_type_ext = MLX5_PACKET_L4_TYPE_EXT_TCP;
+		*tir_tt = MLX5_TT_IPV4_TCP;
+		break;
+	case MLX5_TT_DECRYPTED_ESP_OUTER_IPV6_TCP:
+	case MLX5_TT_DECRYPTED_ESP_INNER_IPV6_TCP:
+		*etype = ETH_P_IPV6;
+		*l4_type_ext = MLX5_PACKET_L4_TYPE_EXT_TCP;
+		*tir_tt = MLX5_TT_IPV6_TCP;
+		break;
+	case MLX5_TT_DECRYPTED_ESP_OUTER_IPV4_UDP:
+	case MLX5_TT_DECRYPTED_ESP_INNER_IPV4_UDP:
+		*etype = ETH_P_IP;
+		*l4_type_ext = MLX5_PACKET_L4_TYPE_EXT_UDP;
+		*tir_tt = MLX5_TT_IPV4_UDP;
+		break;
+	case MLX5_TT_DECRYPTED_ESP_OUTER_IPV6_UDP:
+	case MLX5_TT_DECRYPTED_ESP_INNER_IPV6_UDP:
+		*etype = ETH_P_IPV6;
+		*l4_type_ext = MLX5_PACKET_L4_TYPE_EXT_UDP;
+		*tir_tt = MLX5_TT_IPV6_UDP;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct mlx5_flow_handle *
+mlx5_ttc_create_ipsec_outer_rule(struct mlx5_ttc_table *ttc,
+				 enum mlx5_traffic_types type)
+{
+	struct mlx5_flow_destination dest;
+	MLX5_DECLARE_FLOW_ACT(flow_act);
+	enum mlx5_traffic_types tir_tt;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int l4_type_ext;
+	u16 etype;
+	int err;
+
+	err = mlx5_ttc_get_tt_attrs(type, &etype, &l4_type_ext, &tir_tt);
+	if (err)
+		return ERR_PTR(err);
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return ERR_PTR(-ENOMEM);
+
+	mlx5_fs_ttc_set_match_ipv_outer(ttc->mdev, spec, etype);
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 outer_headers.l4_type_ext);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 outer_headers.l4_type_ext, l4_type_ext);
+
+	dest = mlx5_ttc_get_default_dest(ttc, tir_tt);
+
+	rule = mlx5_add_flow_rules(ttc->t, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(ttc->mdev, "%s: add rule failed\n", __func__);
+	}
+
+	kvfree(spec);
+	return err ? ERR_PTR(err) : rule;
+}
+
+static struct mlx5_flow_handle *
+mlx5_ttc_create_ipsec_inner_rule(struct mlx5_ttc_table *ttc,
+				 struct mlx5_ttc_table *inner_ttc,
+				 enum mlx5_traffic_types type)
+{
+	struct mlx5_flow_destination dest;
+	MLX5_DECLARE_FLOW_ACT(flow_act);
+	enum mlx5_traffic_types tir_tt;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int l4_type_ext;
+	u16 etype;
+	int err;
+
+	err = mlx5_ttc_get_tt_attrs(type, &etype, &l4_type_ext, &tir_tt);
+	if (err)
+		return ERR_PTR(err);
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return ERR_PTR(-ENOMEM);
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 inner_headers.ip_version);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 inner_headers.ip_version, mlx5_etype_to_ipv(etype));
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 inner_headers.l4_type_ext);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 inner_headers.l4_type_ext, l4_type_ext);
+
+	dest = mlx5_ttc_get_default_dest(inner_ttc, tir_tt);
+
+	spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS;
+
+	rule = mlx5_add_flow_rules(ttc->t, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(ttc->mdev, "%s: add rule failed\n", __func__);
+	}
+
+	kvfree(spec);
+	return err ? ERR_PTR(err) : rule;
+}
+
+int mlx5_ttc_create_ipsec_rules(struct mlx5_ttc_table *ttc,
+				struct mlx5_ttc_table *inner_ttc)
+{
+	struct mlx5_flow_handle *rule;
+	enum mlx5_traffic_types i;
+
+	if (!mlx5_ttc_has_esp_flow_group(ttc))
+		return 0;
+
+	mutex_lock(&ttc->mutex);
+	if (ttc->refcnt)
+		goto skip;
+
+	for (i = MLX5_TT_DECRYPTED_ESP_OUTER_IPV4_TCP;
+	     i <= MLX5_TT_DECRYPTED_ESP_OUTER_IPV6_UDP; i++) {
+		rule = mlx5_ttc_create_ipsec_outer_rule(ttc, i);
+		if (IS_ERR(rule))
+			goto err_out;
+
+		ttc->rules[i].rule = rule;
+	}
+
+	for (i = MLX5_TT_DECRYPTED_ESP_INNER_IPV4_TCP;
+	     i <= MLX5_TT_DECRYPTED_ESP_INNER_IPV6_UDP; i++) {
+		rule = mlx5_ttc_create_ipsec_inner_rule(ttc, inner_ttc, i);
+		if (IS_ERR(rule))
+			goto err_out;
+
+		ttc->rules[i].rule = rule;
+	}
+
+skip:
+	ttc->refcnt++;
+	mutex_unlock(&ttc->mutex);
+	return 0;
+
+err_out:
+	_mlx5_ttc_destroy_ipsec_rules(ttc);
+	mutex_unlock(&ttc->mutex);
+	return PTR_ERR(rule);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
index 92eea6bea310..95f6e56724a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
@@ -18,6 +18,14 @@ enum mlx5_traffic_types {
 	MLX5_TT_IPV4,
 	MLX5_TT_IPV6,
 	MLX5_TT_ANY,
+	MLX5_TT_DECRYPTED_ESP_OUTER_IPV4_TCP,
+	MLX5_TT_DECRYPTED_ESP_OUTER_IPV6_TCP,
+	MLX5_TT_DECRYPTED_ESP_OUTER_IPV4_UDP,
+	MLX5_TT_DECRYPTED_ESP_OUTER_IPV6_UDP,
+	MLX5_TT_DECRYPTED_ESP_INNER_IPV4_TCP,
+	MLX5_TT_DECRYPTED_ESP_INNER_IPV6_TCP,
+	MLX5_TT_DECRYPTED_ESP_INNER_IPV4_UDP,
+	MLX5_TT_DECRYPTED_ESP_INNER_IPV6_UDP,
 	MLX5_NUM_TT,
 	MLX5_NUM_INDIR_TIRS = MLX5_TT_ANY,
 };
@@ -47,8 +55,10 @@ struct ttc_params {
 	bool   inner_ttc;
 	DECLARE_BITMAP(ignore_tunnel_dests, MLX5_NUM_TUNNEL_TT);
 	struct mlx5_flow_destination tunnel_dests[MLX5_NUM_TUNNEL_TT];
+	bool ipsec_rss;
 };
 
+const char *mlx5_ttc_get_name(enum mlx5_traffic_types tt);
 struct mlx5_flow_table *mlx5_get_ttc_flow_table(struct mlx5_ttc_table *ttc);
 
 struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
@@ -69,4 +79,14 @@ int mlx5_ttc_fwd_default_dest(struct mlx5_ttc_table *ttc,
 bool mlx5_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev);
 u8 mlx5_get_proto_by_tunnel_type(enum mlx5_tunnel_types tt);
 
+bool mlx5_ttc_has_esp_flow_group(struct mlx5_ttc_table *ttc);
+int mlx5_ttc_create_ipsec_rules(struct mlx5_ttc_table *ttc,
+				struct mlx5_ttc_table *inner_ttc);
+void mlx5_ttc_destroy_ipsec_rules(struct mlx5_ttc_table *ttc);
+static inline bool mlx5_ttc_is_decrypted_esp_tt(enum mlx5_traffic_types tt)
+{
+	return tt >= MLX5_TT_DECRYPTED_ESP_OUTER_IPV4_TCP &&
+	       tt <= MLX5_TT_DECRYPTED_ESP_INNER_IPV6_UDP;
+}
+
 #endif /* __MLX5_FS_TTC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
index b7d4b1a2baf2..d524f0220513 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
@@ -164,6 +164,8 @@ ipsec_fs_roce_rx_rule_setup(struct mlx5_core_dev *mdev,
 	roce->rule = rule;
 
 	memset(spec, 0, sizeof(*spec));
+	if (default_dst->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE)
+		flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 	rule = mlx5_add_flow_rules(roce->ft, spec, &flow_act, default_dst, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -178,6 +180,8 @@ ipsec_fs_roce_rx_rule_setup(struct mlx5_core_dev *mdev,
 		goto out;
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	if (default_dst->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE)
+		flow_act.flags &= ~FLOW_ACT_IGNORE_FLOW_LEVEL;
 	dst.type = MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE;
 	dst.ft = roce->ft_rdma;
 	rule = mlx5_add_flow_rules(roce->nic_master_ft, NULL, &flow_act, &dst,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
index 762d55ba9e51..e6be2f01daf4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
@@ -45,11 +45,7 @@
 #define MLX5_SECTAG_HEADER_SIZE_WITHOUT_SCI 0x8
 #define MLX5_SECTAG_HEADER_SIZE_WITH_SCI (MLX5_SECTAG_HEADER_SIZE_WITHOUT_SCI + MACSEC_SCI_LEN)
 
-/* MACsec RX flow steering */
-#define MLX5_ETH_WQE_FT_META_MACSEC_MASK 0x3E
-
 /* MACsec fs_id handling for steering */
-#define macsec_fs_set_tx_fs_id(fs_id) (MLX5_ETH_WQE_FT_META_MACSEC | (fs_id) << 2)
 #define macsec_fs_set_rx_fs_id(fs_id) ((fs_id) | BIT(30))
 
 struct mlx5_sectag_header {
@@ -597,7 +593,7 @@ static int macsec_fs_tx_setup_fte(struct mlx5_macsec_fs *macsec_fs,
 	MLX5_SET(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_a,
 		 MLX5_ETH_WQE_FT_META_MACSEC_MASK);
 	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_a,
-		 macsec_fs_set_tx_fs_id(id));
+		 MLX5_MACSEC_TX_METADATA(id));
 
 	*fs_id = id;
 	flow_act->crypto.type = MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_MACSEC;
@@ -2219,9 +2215,11 @@ static int mlx5_macsec_fs_add_roce_rule_tx(struct mlx5_macsec_fs *macsec_fs, u32
 
 	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
 	MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_A);
-	MLX5_SET(set_action_in, action, data, macsec_fs_set_tx_fs_id(fs_id));
-	MLX5_SET(set_action_in, action, offset, 0);
-	MLX5_SET(set_action_in, action, length, 32);
+	MLX5_SET(set_action_in, action, data,
+		 mlx5_macsec_fs_set_tx_fs_id(fs_id));
+	MLX5_SET(set_action_in, action, offset,
+		 MLX5_ETH_WQE_FT_META_MACSEC_SHIFT);
+	MLX5_SET(set_action_in, action, length, 8);
 
 	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC,
 					      1, action);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
index 34b80c3ef6a5..15acaff43641 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h
@@ -12,6 +12,21 @@
 #define MLX5_MACSEC_METADATA_MARKER(metadata)  ((((metadata) >> 30) & 0x3)  == 0x1)
 #define MLX5_MACSEC_RX_METADAT_HANDLE(metadata)  ((metadata) & MLX5_MACSEC_RX_FS_ID_MASK)
 
+/* MACsec TX flow steering */
+#define MLX5_ETH_WQE_FT_META_MACSEC_MASK \
+	(MLX5_ETH_WQE_FT_META_MACSEC | MLX5_ETH_WQE_FT_META_MACSEC_FS_ID_MASK)
+#define MLX5_ETH_WQE_FT_META_MACSEC_SHIFT MLX5_ETH_WQE_FT_META_SHIFT
+
+/* MACsec fs_id handling for steering */
+#define mlx5_macsec_fs_set_tx_fs_id(fs_id) \
+	(((MLX5_ETH_WQE_FT_META_MACSEC) >> MLX5_ETH_WQE_FT_META_MACSEC_SHIFT) \
+	 | ((fs_id) << 2))
+
+#define MLX5_MACSEC_TX_METADATA(fs_id) \
+	(mlx5_macsec_fs_set_tx_fs_id(fs_id) << \
+	 MLX5_ETH_WQE_FT_META_MACSEC_SHIFT)
+
+/* MACsec fs_id uses 4 bits, supports up to 16 interfaces */
 #define MLX5_MACSEC_NUM_OF_SUPPORTED_INTERFACES 16
 
 struct mlx5_macsec_fs;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index 37d5f445598c..74ea5da58b7e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -45,14 +45,22 @@ int mlx5_crdump_enable(struct mlx5_core_dev *dev);
 void mlx5_crdump_disable(struct mlx5_core_dev *dev);
 int mlx5_crdump_collect(struct mlx5_core_dev *dev, u32 *cr_data);
 
-static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
+static inline struct net_device *mlx5_uplink_netdev_get(struct mlx5_core_dev *mdev)
 {
-	return devlink_net(priv_to_devlink(dev));
+	struct mlx5e_resources *mlx5e_res = &mdev->mlx5e_res;
+	struct net_device *netdev;
+
+	mutex_lock(&mlx5e_res->uplink_netdev_lock);
+	netdev = mlx5e_res->uplink_netdev;
+	netdev_hold(netdev, &mlx5e_res->tracker, GFP_KERNEL);
+	mutex_unlock(&mlx5e_res->uplink_netdev_lock);
+	return netdev;
 }
 
-static inline struct net_device *mlx5_uplink_netdev_get(struct mlx5_core_dev *mdev)
+static inline void mlx5_uplink_netdev_put(struct mlx5_core_dev *mdev,
+					  struct net_device *netdev)
 {
-	return mdev->mlx5e_res.uplink_netdev;
+	netdev_put(netdev, &mdev->mlx5e_res.tracker);
 }
 
 struct mlx5_sd;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
index 4450091e181a..4a88a42ae4f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
@@ -65,13 +65,14 @@ static int del_l2table_entry_cmd(struct mlx5_core_dev *dev, u32 index)
 /* UC L2 table hash node */
 struct l2table_node {
 	struct l2addr_node node;
-	u32                index; /* index in HW l2 table */
+	int                index; /* index in HW l2 table */
 	int                ref_count;
 };
 
 struct mlx5_mpfs {
 	struct hlist_head    hash[MLX5_L2_ADDR_HASH_SIZE];
 	struct mutex         lock; /* Synchronize l2 table access */
+	bool                 enabled;
 	u32                  size;
 	unsigned long        *bitmap;
 };
@@ -114,6 +115,8 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev)
 		return -ENOMEM;
 	}
 
+	mpfs->enabled = true;
+
 	dev->priv.mpfs = mpfs;
 	return 0;
 }
@@ -135,7 +138,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac)
 	struct mlx5_mpfs *mpfs = dev->priv.mpfs;
 	struct l2table_node *l2addr;
 	int err = 0;
-	u32 index;
+	int index;
 
 	if (!mpfs)
 		return 0;
@@ -148,30 +151,34 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac)
 		goto out;
 	}
 
-	err = alloc_l2table_index(mpfs, &index);
-	if (err)
-		goto out;
-
 	l2addr = l2addr_hash_add(mpfs->hash, mac, struct l2table_node, GFP_KERNEL);
 	if (!l2addr) {
 		err = -ENOMEM;
-		goto hash_add_err;
+		goto out;
 	}
 
-	err = set_l2table_entry_cmd(dev, index, mac);
-	if (err)
-		goto set_table_entry_err;
+	index = -1;
+
+	if (mpfs->enabled) {
+		err = alloc_l2table_index(mpfs, &index);
+		if (err)
+			goto hash_del;
+		err = set_l2table_entry_cmd(dev, index, mac);
+		if (err)
+			goto free_l2table_index;
+		mlx5_core_dbg(dev, "MPFS entry %pM, set @index (%d)\n",
+			      l2addr->node.addr, index);
+	}
 
 	l2addr->index = index;
 	l2addr->ref_count = 1;
 
 	mlx5_core_dbg(dev, "MPFS mac added %pM, index (%d)\n", mac, index);
 	goto out;
-
-set_table_entry_err:
-	l2addr_hash_del(l2addr);
-hash_add_err:
+free_l2table_index:
 	free_l2table_index(mpfs, index);
+hash_del:
+	l2addr_hash_del(l2addr);
 out:
 	mutex_unlock(&mpfs->lock);
 	return err;
@@ -183,7 +190,7 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac)
 	struct mlx5_mpfs *mpfs = dev->priv.mpfs;
 	struct l2table_node *l2addr;
 	int err = 0;
-	u32 index;
+	int index;
 
 	if (!mpfs)
 		return 0;
@@ -200,12 +207,87 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac)
 		goto unlock;
 
 	index = l2addr->index;
-	del_l2table_entry_cmd(dev, index);
+	if (index >= 0) {
+		del_l2table_entry_cmd(dev, index);
+		free_l2table_index(mpfs, index);
+		mlx5_core_dbg(dev, "MPFS entry %pM, deleted @index (%d)\n",
+			      mac, index);
+	}
 	l2addr_hash_del(l2addr);
-	free_l2table_index(mpfs, index);
 	mlx5_core_dbg(dev, "MPFS mac deleted %pM, index (%d)\n", mac, index);
 unlock:
 	mutex_unlock(&mpfs->lock);
 	return err;
 }
 EXPORT_SYMBOL(mlx5_mpfs_del_mac);
+
+int mlx5_mpfs_enable(struct mlx5_core_dev *dev)
+{
+	struct mlx5_mpfs *mpfs = dev->priv.mpfs;
+	struct l2table_node *l2addr;
+	struct hlist_node *n;
+	int err = 0, i;
+
+	if (!mpfs)
+		return -ENODEV;
+
+	mutex_lock(&mpfs->lock);
+	if (mpfs->enabled)
+		goto out;
+	mpfs->enabled = true;
+	mlx5_core_dbg(dev, "MPFS enabling mpfs\n");
+
+	mlx5_mpfs_foreach(l2addr, n, mpfs, i) {
+		u32 index;
+
+		err = alloc_l2table_index(mpfs, &index);
+		if (err) {
+			mlx5_core_err(dev, "Failed to allocated MPFS index for %pM, err(%d)\n",
+				      l2addr->node.addr, err);
+			goto out;
+		}
+
+		err = set_l2table_entry_cmd(dev, index, l2addr->node.addr);
+		if (err) {
+			mlx5_core_err(dev, "Failed to set MPFS l2table entry for %pM index=%d, err(%d)\n",
+				      l2addr->node.addr, index, err);
+			free_l2table_index(mpfs, index);
+			goto out;
+		}
+
+		l2addr->index = index;
+		mlx5_core_dbg(dev, "MPFS entry %pM, set @index (%d)\n",
+			      l2addr->node.addr, l2addr->index);
+	}
+out:
+	mutex_unlock(&mpfs->lock);
+	return err;
+}
+
+void mlx5_mpfs_disable(struct mlx5_core_dev *dev)
+{
+	struct mlx5_mpfs *mpfs = dev->priv.mpfs;
+	struct l2table_node *l2addr;
+	struct hlist_node *n;
+	int i;
+
+	if (!mpfs)
+		return;
+
+	mutex_lock(&mpfs->lock);
+	if (!mpfs->enabled)
+		goto unlock;
+	mlx5_mpfs_foreach(l2addr, n, mpfs, i) {
+		if (l2addr->index < 0)
+			continue;
+		del_l2table_entry_cmd(dev, l2addr->index);
+		free_l2table_index(mpfs, l2addr->index);
+		mlx5_core_dbg(dev, "MPFS entry %pM, deleted @index (%d)\n",
+			      l2addr->node.addr, l2addr->index);
+		l2addr->index = -1;
+	}
+	mpfs->enabled = false;
+	mlx5_core_dbg(dev, "MPFS disabled\n");
+unlock:
+	mutex_unlock(&mpfs->lock);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h
index 4a293542a7aa..9c63838ce1f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h
@@ -45,6 +45,10 @@ struct l2addr_node {
 	u8                addr[ETH_ALEN];
 };
 
+#define mlx5_mpfs_foreach(hs, tmp, mpfs, i) \
+	for (i = 0; i < MLX5_L2_ADDR_HASH_SIZE; i++) \
+		hlist_for_each_entry_safe(hs, tmp, &(mpfs)->hash[i], node.hlist)
+
 #define for_each_l2hash_node(hn, tmp, hash, i) \
 	for (i = 0; i < MLX5_L2_ADDR_HASH_SIZE; i++) \
 		hlist_for_each_entry_safe(hn, tmp, &(hash)[i], hlist)
@@ -82,11 +86,16 @@ struct l2addr_node {
 })
 
 #ifdef CONFIG_MLX5_MPFS
+struct mlx5_core_dev;
 int  mlx5_mpfs_init(struct mlx5_core_dev *dev);
 void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev);
+int mlx5_mpfs_enable(struct mlx5_core_dev *dev);
+void mlx5_mpfs_disable(struct mlx5_core_dev *dev);
 #else /* #ifndef CONFIG_MLX5_MPFS */
 static inline int  mlx5_mpfs_init(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) {}
+static inline int mlx5_mpfs_enable(struct mlx5_core_dev *dev) { return 0; }
+static inline void mlx5_mpfs_disable(struct mlx5_core_dev *dev) {}
 #endif
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.c
new file mode 100644
index 000000000000..19bb620b7436
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.c
@@ -0,0 +1,799 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include "nv_param.h"
+#include "mlx5_core.h"
+
+enum {
+	MLX5_CLASS_0_CTRL_ID_NV_GLOBAL_PCI_CONF               = 0x80,
+	MLX5_CLASS_0_CTRL_ID_NV_GLOBAL_PCI_CAP                = 0x81,
+	MLX5_CLASS_0_CTRL_ID_NV_SW_OFFLOAD_CONFIG             = 0x10a,
+	MLX5_CLASS_0_CTRL_ID_NV_SW_OFFLOAD_CAP                = 0x10b,
+	MLX5_CLASS_0_CTRL_ID_NV_SW_ACCELERATE_CONF            = 0x11d,
+
+	MLX5_CLASS_3_CTRL_ID_NV_PF_PCI_CONF                   = 0x80,
+};
+
+struct mlx5_ifc_configuration_item_type_class_global_bits {
+	u8         type_class[0x8];
+	u8         parameter_index[0x18];
+};
+
+struct mlx5_ifc_configuration_item_type_class_per_host_pf_bits {
+	u8         type_class[0x8];
+	u8         pf_index[0x6];
+	u8         pci_bus_index[0x8];
+	u8         parameter_index[0xa];
+};
+
+union mlx5_ifc_config_item_type_auto_bits {
+	struct mlx5_ifc_configuration_item_type_class_global_bits
+				configuration_item_type_class_global;
+	struct mlx5_ifc_configuration_item_type_class_per_host_pf_bits
+				configuration_item_type_class_per_host_pf;
+	u8 reserved_at_0[0x20];
+};
+
+enum {
+	MLX5_ACCESS_MODE_NEXT = 0,
+	MLX5_ACCESS_MODE_CURRENT,
+	MLX5_ACCESS_MODE_DEFAULT,
+};
+
+struct mlx5_ifc_config_item_bits {
+	u8         valid[0x2];
+	u8         priority[0x2];
+	u8         header_type[0x2];
+	u8         ovr_en[0x1];
+	u8         rd_en[0x1];
+	u8         access_mode[0x2];
+	u8         reserved_at_a[0x1];
+	u8         writer_id[0x5];
+	u8         version[0x4];
+	u8         reserved_at_14[0x2];
+	u8         host_id_valid[0x1];
+	u8         length[0x9];
+
+	union mlx5_ifc_config_item_type_auto_bits type;
+
+	u8         reserved_at_40[0x10];
+	u8         crc16[0x10];
+};
+
+struct mlx5_ifc_mnvda_reg_bits {
+	struct mlx5_ifc_config_item_bits configuration_item_header;
+
+	u8         configuration_item_data[64][0x20];
+};
+
+struct mlx5_ifc_nv_global_pci_conf_bits {
+	u8         sriov_valid[0x1];
+	u8         reserved_at_1[0x10];
+	u8         per_pf_total_vf[0x1];
+	u8         reserved_at_12[0xe];
+
+	u8         sriov_en[0x1];
+	u8         reserved_at_21[0xf];
+	u8         total_vfs[0x10];
+
+	u8         reserved_at_40[0x20];
+};
+
+struct mlx5_ifc_nv_global_pci_cap_bits {
+	u8         max_vfs_per_pf_valid[0x1];
+	u8         reserved_at_1[0x13];
+	u8         per_pf_total_vf_supported[0x1];
+	u8         reserved_at_15[0xb];
+
+	u8         sriov_support[0x1];
+	u8         reserved_at_21[0xf];
+	u8         max_vfs_per_pf[0x10];
+
+	u8         reserved_at_40[0x60];
+};
+
+struct mlx5_ifc_nv_pf_pci_conf_bits {
+	u8         reserved_at_0[0x9];
+	u8         pf_total_vf_en[0x1];
+	u8         reserved_at_a[0x16];
+
+	u8         reserved_at_20[0x20];
+
+	u8         reserved_at_40[0x10];
+	u8         total_vf[0x10];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_nv_sw_offload_conf_bits {
+	u8         ip_over_vxlan_port[0x10];
+	u8         tunnel_ecn_copy_offload_disable[0x1];
+	u8         pci_atomic_mode[0x3];
+	u8         sr_enable[0x1];
+	u8         ptp_cyc2realtime[0x1];
+	u8         vector_calc_disable[0x1];
+	u8         uctx_en[0x1];
+	u8         prio_tag_required_en[0x1];
+	u8         esw_fdb_ipv4_ttl_modify_enable[0x1];
+	u8         mkey_by_name[0x1];
+	u8         ip_over_vxlan_en[0x1];
+	u8         one_qp_per_recovery[0x1];
+	u8         cqe_compression[0x3];
+	u8         tunnel_udp_entropy_proto_disable[0x1];
+	u8         reserved_at_21[0x1];
+	u8         ar_enable[0x1];
+	u8         log_max_outstanding_wqe[0x5];
+	u8         vf_migration[0x2];
+	u8         log_tx_psn_win[0x6];
+	u8         lro_log_timeout3[0x4];
+	u8         lro_log_timeout2[0x4];
+	u8         lro_log_timeout1[0x4];
+	u8         lro_log_timeout0[0x4];
+};
+
+struct mlx5_ifc_nv_sw_offload_cap_bits {
+	u8         reserved_at_0[0x19];
+	u8         swp_l4_csum_mode_l4_only[0x1];
+	u8         reserved_at_1a[0x6];
+};
+
+struct mlx5_ifc_nv_sw_accelerate_conf_bits {
+	u8         swp_l4_csum_mode[0x2];
+	u8         reserved_at_2[0x3e];
+};
+
+#define MNVDA_HDR_SZ \
+	(MLX5_ST_SZ_BYTES(mnvda_reg) - \
+	 MLX5_BYTE_OFF(mnvda_reg, configuration_item_data))
+
+#define MLX5_SET_CFG_ITEM_TYPE(_cls_name, _mnvda_ptr, _field, _val) \
+	MLX5_SET(mnvda_reg, _mnvda_ptr, \
+		 configuration_item_header.type.configuration_item_type_class_##_cls_name._field, \
+		 _val)
+
+#define MLX5_SET_CFG_HDR_LEN(_mnvda_ptr, _cls_name) \
+	MLX5_SET(mnvda_reg, _mnvda_ptr, configuration_item_header.length, \
+		 MLX5_ST_SZ_BYTES(_cls_name))
+
+#define MLX5_GET_CFG_HDR_LEN(_mnvda_ptr) \
+	MLX5_GET(mnvda_reg, _mnvda_ptr, configuration_item_header.length)
+
+static int mlx5_nv_param_read(struct mlx5_core_dev *dev, void *mnvda,
+			      size_t len)
+{
+	u32 param_idx, type_class;
+	u32 header_len;
+	void *cls_ptr;
+	int err;
+
+	if (WARN_ON(len > MLX5_ST_SZ_BYTES(mnvda_reg)) || len < MNVDA_HDR_SZ)
+		return -EINVAL; /* A caller bug */
+
+	err = mlx5_core_access_reg(dev, mnvda, len, mnvda, len, MLX5_REG_MNVDA,
+				   0, 0);
+	if (!err)
+		return 0;
+
+	cls_ptr = MLX5_ADDR_OF(mnvda_reg, mnvda,
+			       configuration_item_header.type.configuration_item_type_class_global);
+
+	type_class = MLX5_GET(configuration_item_type_class_global, cls_ptr,
+			      type_class);
+	param_idx = MLX5_GET(configuration_item_type_class_global, cls_ptr,
+			     parameter_index);
+	header_len = MLX5_GET_CFG_HDR_LEN(mnvda);
+
+	mlx5_core_warn(dev, "Failed to read mnvda reg: type_class 0x%x, param_idx 0x%x, header_len %u, err %d\n",
+		       type_class, param_idx, header_len, err);
+
+	return -EOPNOTSUPP;
+}
+
+static int mlx5_nv_param_write(struct mlx5_core_dev *dev, void *mnvda,
+			       size_t len)
+{
+	if (WARN_ON(len > MLX5_ST_SZ_BYTES(mnvda_reg)) || len < MNVDA_HDR_SZ)
+		return -EINVAL;
+
+	if (WARN_ON(MLX5_GET_CFG_HDR_LEN(mnvda) == 0))
+		return -EINVAL;
+
+	return mlx5_core_access_reg(dev, mnvda, len, mnvda, len, MLX5_REG_MNVDA,
+				    0, 1);
+}
+
+static int
+mlx5_nv_param_read_sw_offload_conf(struct mlx5_core_dev *dev, void *mnvda,
+				   size_t len)
+{
+	MLX5_SET_CFG_ITEM_TYPE(global, mnvda, type_class, 0);
+	MLX5_SET_CFG_ITEM_TYPE(global, mnvda, parameter_index,
+			       MLX5_CLASS_0_CTRL_ID_NV_SW_OFFLOAD_CONFIG);
+	MLX5_SET_CFG_HDR_LEN(mnvda, nv_sw_offload_conf);
+
+	return mlx5_nv_param_read(dev, mnvda, len);
+}
+
+static int
+mlx5_nv_param_read_sw_offload_cap(struct mlx5_core_dev *dev, void *mnvda,
+				  size_t len)
+{
+	MLX5_SET_CFG_ITEM_TYPE(global, mnvda, type_class, 0);
+	MLX5_SET_CFG_ITEM_TYPE(global, mnvda, parameter_index,
+			       MLX5_CLASS_0_CTRL_ID_NV_SW_OFFLOAD_CAP);
+	MLX5_SET_CFG_HDR_LEN(mnvda, nv_sw_offload_cap);
+
+	return mlx5_nv_param_read(dev, mnvda, len);
+}
+
+static int
+mlx5_nv_param_read_sw_accelerate_conf(struct mlx5_core_dev *dev, void *mnvda,
+				      size_t len, int access_mode)
+{
+	MLX5_SET_CFG_ITEM_TYPE(global, mnvda, type_class, 0);
+	MLX5_SET_CFG_ITEM_TYPE(global, mnvda, parameter_index,
+			       MLX5_CLASS_0_CTRL_ID_NV_SW_ACCELERATE_CONF);
+	MLX5_SET_CFG_HDR_LEN(mnvda, nv_sw_accelerate_conf);
+	MLX5_SET(mnvda_reg, mnvda, configuration_item_header.access_mode,
+		 access_mode);
+
+	return mlx5_nv_param_read(dev, mnvda, len);
+}
+
+static const char *const
+	cqe_compress_str[] = { "balanced", "aggressive" };
+
+static int
+mlx5_nv_param_devlink_cqe_compress_get(struct devlink *devlink, u32 id,
+				       struct devlink_param_gset_ctx *ctx,
+				       struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {};
+	u8 value = U8_MAX;
+	void *data;
+	int err;
+
+	err = mlx5_nv_param_read_sw_offload_conf(dev, mnvda, sizeof(mnvda));
+	if (err)
+		return err;
+
+	data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+	value = MLX5_GET(nv_sw_offload_conf, data, cqe_compression);
+
+	if (value >= ARRAY_SIZE(cqe_compress_str))
+		return -EOPNOTSUPP;
+
+	strscpy(ctx->val.vstr, cqe_compress_str[value], sizeof(ctx->val.vstr));
+	return 0;
+}
+
+static int
+mlx5_nv_param_devlink_cqe_compress_validate(struct devlink *devlink, u32 id,
+					    union devlink_param_value val,
+					    struct netlink_ext_ack *extack)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(cqe_compress_str); i++) {
+		if (!strcmp(val.vstr, cqe_compress_str[i]))
+			return 0;
+	}
+
+	NL_SET_ERR_MSG_MOD(extack,
+			   "Invalid value, supported values are balanced/aggressive");
+	return -EOPNOTSUPP;
+}
+
+static int
+mlx5_nv_param_devlink_cqe_compress_set(struct devlink *devlink, u32 id,
+				       struct devlink_param_gset_ctx *ctx,
+				       struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {};
+	int err = 0;
+	void *data;
+	u8 value;
+
+	if (!strcmp(ctx->val.vstr, "aggressive"))
+		value = 1;
+	else /* balanced: can't be anything else already validated above */
+		value = 0;
+
+	err = mlx5_nv_param_read_sw_offload_conf(dev, mnvda, sizeof(mnvda));
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to read sw_offload_conf mnvda reg");
+		return err;
+	}
+
+	data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+	MLX5_SET(nv_sw_offload_conf, data, cqe_compression, value);
+
+	return mlx5_nv_param_write(dev, mnvda, sizeof(mnvda));
+}
+
+enum swp_l4_csum_mode {
+	SWP_L4_CSUM_MODE_DEFAULT = 0,
+	SWP_L4_CSUM_MODE_FULL_CSUM = 1,
+	SWP_L4_CSUM_MODE_L4_ONLY = 2,
+};
+
+static const char *const
+	swp_l4_csum_mode_str[] = { "default", "full_csum", "l4_only" };
+
+static int
+mlx5_swp_l4_csum_mode_get(struct devlink *devlink, u32 id,
+			  int access_mode, u8 *value,
+			  struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {};
+	void *data;
+	int err;
+
+	err = mlx5_nv_param_read_sw_accelerate_conf(dev, mnvda, sizeof(mnvda),
+						    access_mode);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to read sw_accelerate_conf mnvda reg");
+		return err;
+	}
+
+	data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+	*value = MLX5_GET(nv_sw_accelerate_conf, data, swp_l4_csum_mode);
+
+	if (*value >= ARRAY_SIZE(swp_l4_csum_mode_str)) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Invalid swp_l4_csum_mode value %u read from device",
+				       *value);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+mlx5_devlink_swp_l4_csum_mode_get(struct devlink *devlink, u32 id,
+				  struct devlink_param_gset_ctx *ctx,
+				  struct netlink_ext_ack *extack)
+{
+	u8 value;
+	int err;
+
+	err = mlx5_swp_l4_csum_mode_get(devlink, id, MLX5_ACCESS_MODE_NEXT,
+					&value, extack);
+	if (err)
+		return err;
+
+	strscpy(ctx->val.vstr, swp_l4_csum_mode_str[value],
+		sizeof(ctx->val.vstr));
+	return 0;
+}
+
+static int
+mlx5_devlink_swp_l4_csum_mode_validate(struct devlink *devlink, u32 id,
+				       union devlink_param_value val,
+				       struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	u32 cap[MLX5_ST_SZ_DW(mnvda_reg)] = {};
+	void *data;
+	int err, i;
+
+	for (i = 0; i < ARRAY_SIZE(swp_l4_csum_mode_str); i++) {
+		if (!strcmp(val.vstr, swp_l4_csum_mode_str[i]))
+			break;
+	}
+
+	if (i >= ARRAY_SIZE(swp_l4_csum_mode_str) ||
+	    i == SWP_L4_CSUM_MODE_DEFAULT) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Invalid value, supported values are full_csum/l4_only");
+		return -EINVAL;
+	}
+
+	if (i == SWP_L4_CSUM_MODE_L4_ONLY) {
+		err = mlx5_nv_param_read_sw_offload_cap(dev, cap, sizeof(cap));
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to read sw_offload_cap");
+			return err;
+		}
+
+		data = MLX5_ADDR_OF(mnvda_reg, cap, configuration_item_data);
+		if (!MLX5_GET(nv_sw_offload_cap, data, swp_l4_csum_mode_l4_only)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "l4_only mode is not supported on this device");
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static int
+mlx5_swp_l4_csum_mode_set(struct devlink *devlink, u32 id, u8 value,
+			  struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {};
+	void *data;
+	int err;
+
+	err = mlx5_nv_param_read_sw_accelerate_conf(dev, mnvda, sizeof(mnvda),
+						    MLX5_ACCESS_MODE_NEXT);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to read sw_accelerate_conf mnvda reg");
+		return err;
+	}
+
+	data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+	MLX5_SET(nv_sw_accelerate_conf, data, swp_l4_csum_mode, value);
+
+	err = mlx5_nv_param_write(dev, mnvda, sizeof(mnvda));
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to write sw_accelerate_conf mnvda reg");
+
+	return err;
+}
+
+static int
+mlx5_devlink_swp_l4_csum_mode_set(struct devlink *devlink, u32 id,
+				  struct devlink_param_gset_ctx *ctx,
+				  struct netlink_ext_ack *extack)
+{
+	u8 value;
+
+	if (!strcmp(ctx->val.vstr, "full_csum"))
+		value = SWP_L4_CSUM_MODE_FULL_CSUM;
+	else
+		value = SWP_L4_CSUM_MODE_L4_ONLY;
+
+	return mlx5_swp_l4_csum_mode_set(devlink, id, value, extack);
+}
+
+static int
+mlx5_devlink_swp_l4_csum_mode_get_default(struct devlink *devlink, u32 id,
+					  struct devlink_param_gset_ctx *ctx,
+					  struct netlink_ext_ack *extack)
+{
+	u8 value;
+	int err;
+
+	err = mlx5_swp_l4_csum_mode_get(devlink, id, MLX5_ACCESS_MODE_DEFAULT,
+					&value, extack);
+	if (err)
+		return err;
+
+	strscpy(ctx->val.vstr, swp_l4_csum_mode_str[value],
+		sizeof(ctx->val.vstr));
+	return 0;
+}
+
+static int
+mlx5_devlink_swp_l4_csum_mode_set_default(struct devlink *devlink, u32 id,
+					  enum devlink_param_cmode cmode,
+					  struct netlink_ext_ack *extack)
+{
+	u8 value;
+	int err;
+
+	err = mlx5_swp_l4_csum_mode_get(devlink, id, MLX5_ACCESS_MODE_DEFAULT,
+					&value, extack);
+	if (err)
+		return err;
+
+	return mlx5_swp_l4_csum_mode_set(devlink, id, value, extack);
+}
+
+static int mlx5_nv_param_read_global_pci_conf(struct mlx5_core_dev *dev,
+					      void *mnvda, size_t len)
+{
+	MLX5_SET_CFG_ITEM_TYPE(global, mnvda, type_class, 0);
+	MLX5_SET_CFG_ITEM_TYPE(global, mnvda, parameter_index,
+			       MLX5_CLASS_0_CTRL_ID_NV_GLOBAL_PCI_CONF);
+	MLX5_SET_CFG_HDR_LEN(mnvda, nv_global_pci_conf);
+
+	return mlx5_nv_param_read(dev, mnvda, len);
+}
+
+static int mlx5_nv_param_read_global_pci_cap(struct mlx5_core_dev *dev,
+					     void *mnvda, size_t len)
+{
+	MLX5_SET_CFG_ITEM_TYPE(global, mnvda, type_class, 0);
+	MLX5_SET_CFG_ITEM_TYPE(global, mnvda, parameter_index,
+			       MLX5_CLASS_0_CTRL_ID_NV_GLOBAL_PCI_CAP);
+	MLX5_SET_CFG_HDR_LEN(mnvda, nv_global_pci_cap);
+
+	return mlx5_nv_param_read(dev, mnvda, len);
+}
+
+static int mlx5_nv_param_read_per_host_pf_conf(struct mlx5_core_dev *dev,
+					       void *mnvda, size_t len)
+{
+	MLX5_SET_CFG_ITEM_TYPE(per_host_pf, mnvda, type_class, 3);
+	MLX5_SET_CFG_ITEM_TYPE(per_host_pf, mnvda, parameter_index,
+			       MLX5_CLASS_3_CTRL_ID_NV_PF_PCI_CONF);
+	MLX5_SET_CFG_HDR_LEN(mnvda, nv_pf_pci_conf);
+
+	return mlx5_nv_param_read(dev, mnvda, len);
+}
+
+static int mlx5_devlink_enable_sriov_get(struct devlink *devlink, u32 id,
+					 struct devlink_param_gset_ctx *ctx,
+					 struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {};
+	bool sriov_en = false;
+	void *data;
+	int err;
+
+	err = mlx5_nv_param_read_global_pci_cap(dev, mnvda, sizeof(mnvda));
+	if (err)
+		return err;
+
+	data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+	if (!MLX5_GET(nv_global_pci_cap, data, sriov_support)) {
+		ctx->val.vbool = false;
+		return 0;
+	}
+
+	memset(mnvda, 0, sizeof(mnvda));
+	err = mlx5_nv_param_read_global_pci_conf(dev, mnvda, sizeof(mnvda));
+	if (err)
+		return err;
+
+	data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+	sriov_en = MLX5_GET(nv_global_pci_conf, data, sriov_en);
+	if (!MLX5_GET(nv_global_pci_conf, data, per_pf_total_vf)) {
+		ctx->val.vbool = sriov_en;
+		return 0;
+	}
+
+	/* SRIOV is per PF */
+	memset(mnvda, 0, sizeof(mnvda));
+	err = mlx5_nv_param_read_per_host_pf_conf(dev, mnvda, sizeof(mnvda));
+	if (err)
+		return err;
+
+	data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+	ctx->val.vbool = sriov_en &&
+			 MLX5_GET(nv_pf_pci_conf, data, pf_total_vf_en);
+	return 0;
+}
+
+static int mlx5_devlink_enable_sriov_set(struct devlink *devlink, u32 id,
+					 struct devlink_param_gset_ctx *ctx,
+					 struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {};
+	bool per_pf_support;
+	void *cap, *data;
+	int err;
+
+	err = mlx5_nv_param_read_global_pci_cap(dev, mnvda, sizeof(mnvda));
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to read global PCI capability");
+		return err;
+	}
+
+	cap = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+	per_pf_support = MLX5_GET(nv_global_pci_cap, cap,
+				  per_pf_total_vf_supported);
+
+	if (!MLX5_GET(nv_global_pci_cap, cap, sriov_support)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "SRIOV is not supported on this device");
+		return -EOPNOTSUPP;
+	}
+
+	if (!per_pf_support) {
+		/* We don't allow global SRIOV setting on per PF devlink */
+		NL_SET_ERR_MSG_MOD(extack,
+				   "SRIOV is not per PF on this device");
+		return -EOPNOTSUPP;
+	}
+
+	memset(mnvda, 0, sizeof(mnvda));
+	err = mlx5_nv_param_read_global_pci_conf(dev, mnvda, sizeof(mnvda));
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Unable to read global PCI configuration");
+		return err;
+	}
+
+	data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+
+	/* setup per PF sriov mode */
+	MLX5_SET(nv_global_pci_conf, data, sriov_valid, 1);
+	MLX5_SET(nv_global_pci_conf, data, sriov_en, 1);
+	MLX5_SET(nv_global_pci_conf, data, per_pf_total_vf, 1);
+
+	err = mlx5_nv_param_write(dev, mnvda, sizeof(mnvda));
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Unable to write global PCI configuration");
+		return err;
+	}
+
+	/* enable/disable sriov on this PF */
+	memset(mnvda, 0, sizeof(mnvda));
+	err = mlx5_nv_param_read_per_host_pf_conf(dev, mnvda, sizeof(mnvda));
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Unable to read per host PF configuration");
+		return err;
+	}
+	MLX5_SET(nv_pf_pci_conf, data, pf_total_vf_en, ctx->val.vbool);
+	return mlx5_nv_param_write(dev, mnvda, sizeof(mnvda));
+}
+
+static int mlx5_devlink_total_vfs_get(struct devlink *devlink, u32 id,
+				      struct devlink_param_gset_ctx *ctx,
+				      struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {};
+	void *data;
+	int err;
+
+	data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+
+	err = mlx5_nv_param_read_global_pci_cap(dev, mnvda, sizeof(mnvda));
+	if (err)
+		return err;
+
+	if (!MLX5_GET(nv_global_pci_cap, data, sriov_support)) {
+		ctx->val.vu32 = 0;
+		return 0;
+	}
+
+	memset(mnvda, 0, sizeof(mnvda));
+	err = mlx5_nv_param_read_global_pci_conf(dev, mnvda, sizeof(mnvda));
+	if (err)
+		return err;
+
+	if (!MLX5_GET(nv_global_pci_conf, data, per_pf_total_vf)) {
+		ctx->val.vu32 = MLX5_GET(nv_global_pci_conf, data, total_vfs);
+		return 0;
+	}
+
+	/* SRIOV is per PF */
+	memset(mnvda, 0, sizeof(mnvda));
+	err = mlx5_nv_param_read_per_host_pf_conf(dev, mnvda, sizeof(mnvda));
+	if (err)
+		return err;
+
+	ctx->val.vu32 = MLX5_GET(nv_pf_pci_conf, data, total_vf);
+
+	return 0;
+}
+
+static int mlx5_devlink_total_vfs_set(struct devlink *devlink, u32 id,
+				      struct devlink_param_gset_ctx *ctx,
+				      struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)];
+	void *data;
+	int err;
+
+	err = mlx5_nv_param_read_global_pci_cap(dev, mnvda, sizeof(mnvda));
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to read global pci cap");
+		return err;
+	}
+
+	data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+	if (!MLX5_GET(nv_global_pci_cap, data, sriov_support)) {
+		NL_SET_ERR_MSG_MOD(extack, "Not configurable on this device");
+		return -EOPNOTSUPP;
+	}
+
+	if (!MLX5_GET(nv_global_pci_cap, data, per_pf_total_vf_supported)) {
+		/* We don't allow global SRIOV setting on per PF devlink */
+		NL_SET_ERR_MSG_MOD(extack,
+				   "SRIOV is not per PF on this device");
+		return -EOPNOTSUPP;
+	}
+
+	memset(mnvda, 0, sizeof(mnvda));
+	err = mlx5_nv_param_read_global_pci_conf(dev, mnvda, sizeof(mnvda));
+	if (err)
+		return err;
+
+	MLX5_SET(nv_global_pci_conf, data, sriov_valid, 1);
+	MLX5_SET(nv_global_pci_conf, data, per_pf_total_vf, 1);
+
+	err = mlx5_nv_param_write(dev, mnvda, sizeof(mnvda));
+	if (err)
+		return err;
+
+	memset(mnvda, 0, sizeof(mnvda));
+	err = mlx5_nv_param_read_per_host_pf_conf(dev, mnvda, sizeof(mnvda));
+	if (err)
+		return err;
+
+	data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+	MLX5_SET(nv_pf_pci_conf, data, total_vf, ctx->val.vu32);
+	return mlx5_nv_param_write(dev, mnvda, sizeof(mnvda));
+}
+
+static int mlx5_devlink_total_vfs_validate(struct devlink *devlink, u32 id,
+					   union devlink_param_value val,
+					   struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	u32 cap[MLX5_ST_SZ_DW(mnvda_reg)];
+	void *data;
+	u16 max;
+	int err;
+
+	data = MLX5_ADDR_OF(mnvda_reg, cap, configuration_item_data);
+
+	err = mlx5_nv_param_read_global_pci_cap(dev, cap, sizeof(cap));
+	if (err)
+		return err;
+
+	if (!MLX5_GET(nv_global_pci_cap, data, max_vfs_per_pf_valid))
+		return 0; /* optimistic, but set might fail later */
+
+	max = MLX5_GET(nv_global_pci_cap, data, max_vfs_per_pf);
+	if (val.vu16 > max) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Max allowed by device is %u", max);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct devlink_param mlx5_nv_param_devlink_params[] = {
+	DEVLINK_PARAM_GENERIC(ENABLE_SRIOV, BIT(DEVLINK_PARAM_CMODE_PERMANENT),
+			      mlx5_devlink_enable_sriov_get,
+			      mlx5_devlink_enable_sriov_set, NULL),
+	DEVLINK_PARAM_GENERIC(TOTAL_VFS, BIT(DEVLINK_PARAM_CMODE_PERMANENT),
+			      mlx5_devlink_total_vfs_get,
+			      mlx5_devlink_total_vfs_set,
+			      mlx5_devlink_total_vfs_validate),
+	DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_CQE_COMPRESSION_TYPE,
+			     "cqe_compress_type", DEVLINK_PARAM_TYPE_STRING,
+			     BIT(DEVLINK_PARAM_CMODE_PERMANENT),
+			     mlx5_nv_param_devlink_cqe_compress_get,
+			     mlx5_nv_param_devlink_cqe_compress_set,
+			     mlx5_nv_param_devlink_cqe_compress_validate),
+	DEVLINK_PARAM_DRIVER_WITH_DEFAULTS(MLX5_DEVLINK_PARAM_ID_SWP_L4_CSUM_MODE,
+					   "swp_l4_csum_mode", DEVLINK_PARAM_TYPE_STRING,
+					   BIT(DEVLINK_PARAM_CMODE_PERMANENT),
+					   mlx5_devlink_swp_l4_csum_mode_get,
+					   mlx5_devlink_swp_l4_csum_mode_set,
+					   mlx5_devlink_swp_l4_csum_mode_validate,
+					   mlx5_devlink_swp_l4_csum_mode_get_default,
+					   mlx5_devlink_swp_l4_csum_mode_set_default),
+};
+
+int mlx5_nv_param_register_dl_params(struct devlink *devlink)
+{
+	if (!mlx5_core_is_pf(devlink_priv(devlink)))
+		return 0;
+
+	return devl_params_register(devlink, mlx5_nv_param_devlink_params,
+				    ARRAY_SIZE(mlx5_nv_param_devlink_params));
+}
+
+void mlx5_nv_param_unregister_dl_params(struct devlink *devlink)
+{
+	if (!mlx5_core_is_pf(devlink_priv(devlink)))
+		return;
+
+	devl_params_unregister(devlink, mlx5_nv_param_devlink_params,
+			       ARRAY_SIZE(mlx5_nv_param_devlink_params));
+}
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.h
new file mode 100644
index 000000000000..9f4922ff7745
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef __MLX5_NV_PARAM_H
+#define __MLX5_NV_PARAM_H
+
+#include <linux/mlx5/driver.h>
+#include "devlink.h"
+
+int mlx5_nv_param_register_dl_params(struct devlink *devlink);
+void mlx5_nv_param_unregister_dl_params(struct devlink *devlink);
+
+#endif
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
index eeb0b7ea05f1..8e17daae48af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
@@ -210,15 +210,19 @@ static void sd_cleanup(struct mlx5_core_dev *dev)
 static int sd_register(struct mlx5_core_dev *dev)
 {
 	struct mlx5_devcom_comp_dev *devcom, *pos;
+	struct mlx5_devcom_match_attr attr = {};
 	struct mlx5_core_dev *peer, *primary;
 	struct mlx5_sd *sd, *primary_sd;
 	int err, i;
 
 	sd = mlx5_get_sd(dev);
+	attr.key.val = sd->group_id;
+	attr.flags = MLX5_DEVCOM_MATCH_FLAGS_NS;
+	attr.net = mlx5_core_net(dev);
 	devcom = mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_SD_GROUP,
-						sd->group_id, NULL, dev);
-	if (IS_ERR(devcom))
-		return PTR_ERR(devcom);
+						&attr, NULL, dev);
+	if (!devcom)
+		return -EINVAL;
 
 	sd->devcom = devcom;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c
new file mode 100644
index 000000000000..ef06fe6cbb51
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/device.h>
+
+#include "mlx5_core.h"
+#include "lib/mlx5.h"
+
+struct mlx5_st_idx_data {
+	refcount_t usecount;
+	u16 tag;
+};
+
+struct mlx5_st {
+	/* serialize access upon alloc/free flows */
+	struct mutex lock;
+	struct xa_limit index_limit;
+	struct xarray idx_xa; /* key == index, value == struct mlx5_st_idx_data */
+	u8 direct_mode : 1;
+};
+
+struct mlx5_st *mlx5_st_create(struct mlx5_core_dev *dev)
+{
+	struct pci_dev *pdev = dev->pdev;
+	struct mlx5_st *st;
+	u8 direct_mode = 0;
+	u16 num_entries;
+	u32 tbl_loc;
+	int ret;
+
+	if (!MLX5_CAP_GEN(dev, mkey_pcie_tph))
+		return NULL;
+
+#ifdef CONFIG_MLX5_SF
+	if (mlx5_core_is_sf(dev))
+		return dev->priv.parent_mdev->st;
+#endif
+
+	/* Checking whether the device is capable */
+	if (!pdev->tph_cap)
+		return NULL;
+
+	tbl_loc = pcie_tph_get_st_table_loc(pdev);
+	if (tbl_loc == PCI_TPH_LOC_NONE)
+		direct_mode = 1;
+
+	if (!direct_mode) {
+		num_entries = pcie_tph_get_st_table_size(pdev);
+		/* We need a reserved entry for non TPH cases */
+		if (num_entries < 2)
+			return NULL;
+	}
+
+	/* The OS doesn't support ST */
+	ret = pcie_enable_tph(pdev, PCI_TPH_ST_DS_MODE);
+	if (ret)
+		return NULL;
+
+	st = kzalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		goto end;
+
+	mutex_init(&st->lock);
+	xa_init_flags(&st->idx_xa, XA_FLAGS_ALLOC);
+	st->direct_mode = direct_mode;
+	if (st->direct_mode)
+		return st;
+
+	/* entry 0 is reserved for non TPH cases */
+	st->index_limit.min = MLX5_MKC_PCIE_TPH_NO_STEERING_TAG_INDEX + 1;
+	st->index_limit.max = num_entries - 1;
+
+	return st;
+
+end:
+	pcie_disable_tph(dev->pdev);
+	return NULL;
+}
+
+void mlx5_st_destroy(struct mlx5_core_dev *dev)
+{
+	struct mlx5_st *st = dev->st;
+
+	if (mlx5_core_is_sf(dev) || !st)
+		return;
+
+	pcie_disable_tph(dev->pdev);
+	WARN_ON_ONCE(!xa_empty(&st->idx_xa));
+	kfree(st);
+}
+
+int mlx5_st_alloc_index(struct mlx5_core_dev *dev, enum tph_mem_type mem_type,
+			unsigned int cpu_uid, u16 *st_index)
+{
+	struct mlx5_st_idx_data *idx_data;
+	struct mlx5_st *st = dev->st;
+	unsigned long index;
+	u32 xa_id;
+	u16 tag;
+	int ret;
+
+	if (!st)
+		return -EOPNOTSUPP;
+
+	ret = pcie_tph_get_cpu_st(dev->pdev, mem_type, cpu_uid, &tag);
+	if (ret)
+		return ret;
+
+	if (st->direct_mode) {
+		*st_index = tag;
+		return 0;
+	}
+
+	mutex_lock(&st->lock);
+
+	xa_for_each(&st->idx_xa, index, idx_data) {
+		if (tag == idx_data->tag) {
+			refcount_inc(&idx_data->usecount);
+			*st_index = index;
+			goto end;
+		}
+	}
+
+	idx_data = kzalloc(sizeof(*idx_data), GFP_KERNEL);
+	if (!idx_data) {
+		ret = -ENOMEM;
+		goto end;
+	}
+
+	refcount_set(&idx_data->usecount, 1);
+	idx_data->tag = tag;
+
+	ret = xa_alloc(&st->idx_xa, &xa_id, idx_data, st->index_limit, GFP_KERNEL);
+	if (ret)
+		goto clean_idx_data;
+
+	ret = pcie_tph_set_st_entry(dev->pdev, xa_id, tag);
+	if (ret)
+		goto clean_idx_xa;
+
+	*st_index = xa_id;
+	goto end;
+
+clean_idx_xa:
+	xa_erase(&st->idx_xa, xa_id);
+clean_idx_data:
+	kfree(idx_data);
+end:
+	mutex_unlock(&st->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mlx5_st_alloc_index);
+
+int mlx5_st_dealloc_index(struct mlx5_core_dev *dev, u16 st_index)
+{
+	struct mlx5_st_idx_data *idx_data;
+	struct mlx5_st *st = dev->st;
+	int ret = 0;
+
+	if (!st)
+		return -EOPNOTSUPP;
+
+	if (st->direct_mode)
+		return 0;
+
+	mutex_lock(&st->lock);
+	idx_data = xa_load(&st->idx_xa, st_index);
+	if (WARN_ON_ONCE(!idx_data)) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	if (refcount_dec_and_test(&idx_data->usecount)) {
+		xa_erase(&st->idx_xa, st_index);
+		/* We leave PCI config space as was before, no mkey will refer to it */
+	}
+
+end:
+	mutex_unlock(&st->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mlx5_st_dealloc_index);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
index d55e15c1f380..304912637c35 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
@@ -149,7 +149,7 @@ struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev)
 	struct mlx5_vxlan *vxlan;
 
 	if (!MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) || !mlx5_core_is_pf(mdev))
-		return ERR_PTR(-ENOTSUPP);
+		return ERR_PTR(-EOPNOTSUPP);
 
 	vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL);
 	if (!vxlan)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 869bfecdd8ff..1ab569ce3fcf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -368,6 +368,10 @@ int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_ty
 	u16 opmod = (cap_type << 1) | (cap_mode & 0x01);
 	int err;
 
+	if (WARN_ON(!dev->caps.hca[cap_type]))
+		/* this cap_type must be added to mlx5_hca_caps_alloc() */
+		return -EINVAL;
+
 	memset(in, 0, sizeof(in));
 	out = kzalloc(out_sz, GFP_KERNEL);
 	if (!out)
@@ -549,6 +553,7 @@ EXPORT_SYMBOL(mlx5_is_roce_on);
 
 static int handle_hca_cap_2(struct mlx5_core_dev *dev, void *set_ctx)
 {
+	bool do_set = false;
 	void *set_hca_cap;
 	int err;
 
@@ -559,17 +564,27 @@ static int handle_hca_cap_2(struct mlx5_core_dev *dev, void *set_ctx)
 	if (err)
 		return err;
 
-	if (!MLX5_CAP_GEN_2_MAX(dev, sw_vhca_id_valid) ||
-	    !(dev->priv.sw_vhca_id > 0))
-		return 0;
-
 	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx,
 				   capability);
 	memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_GENERAL_2]->cur,
 	       MLX5_ST_SZ_BYTES(cmd_hca_cap_2));
-	MLX5_SET(cmd_hca_cap_2, set_hca_cap, sw_vhca_id_valid, 1);
 
-	return set_caps(dev, set_ctx, MLX5_CAP_GENERAL_2);
+	if (MLX5_CAP_GEN_2_MAX(dev, sw_vhca_id_valid) &&
+	    dev->priv.sw_vhca_id > 0) {
+		MLX5_SET(cmd_hca_cap_2, set_hca_cap, sw_vhca_id_valid, 1);
+		do_set = true;
+	}
+
+	if (MLX5_CAP_GEN_2_MAX(dev, lag_per_mp_group)) {
+		MLX5_SET(cmd_hca_cap_2, set_hca_cap, lag_per_mp_group, 1);
+		do_set = true;
+	}
+
+	/* some FW versions that support querying MLX5_CAP_GENERAL_2
+	 * capabilities but don't support setting them.
+	 * Skip unnecessary update to hca_cap_2 when no changes were introduced
+	 */
+	return do_set ? set_caps(dev, set_ctx, MLX5_CAP_GENERAL_2) : 0;
 }
 
 static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
@@ -945,9 +960,7 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 
 	mlx5_pci_vsc_init(dev);
 
-	err = pci_enable_ptm(pdev, NULL);
-	if (err)
-		mlx5_core_info(dev, "PTM is not supported by PCIe\n");
+	pci_enable_ptm(pdev, NULL);
 
 	return 0;
 
@@ -971,36 +984,13 @@ static void mlx5_pci_close(struct mlx5_core_dev *dev)
 	mlx5_pci_disable_device(dev);
 }
 
-static void mlx5_register_hca_devcom_comp(struct mlx5_core_dev *dev)
-{
-	/* This component is use to sync adding core_dev to lag_dev and to sync
-	 * changes of mlx5_adev_devices between LAG layer and other layers.
-	 */
-	if (!mlx5_lag_is_supported(dev))
-		return;
-
-	dev->priv.hca_devcom_comp =
-		mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_HCA_PORTS,
-					       mlx5_query_nic_system_image_guid(dev),
-					       NULL, dev);
-	if (IS_ERR(dev->priv.hca_devcom_comp))
-		mlx5_core_err(dev, "Failed to register devcom HCA component\n");
-}
-
-static void mlx5_unregister_hca_devcom_comp(struct mlx5_core_dev *dev)
-{
-	mlx5_devcom_unregister_component(dev->priv.hca_devcom_comp);
-}
-
 static int mlx5_init_once(struct mlx5_core_dev *dev)
 {
 	int err;
 
 	dev->priv.devc = mlx5_devcom_register_device(dev);
-	if (IS_ERR(dev->priv.devc))
-		mlx5_core_warn(dev, "failed to register devcom device %ld\n",
-			       PTR_ERR(dev->priv.devc));
-	mlx5_register_hca_devcom_comp(dev);
+	if (!dev->priv.devc)
+		mlx5_core_warn(dev, "failed to register devcom device\n");
 
 	err = mlx5_query_board_id(dev);
 	if (err) {
@@ -1020,23 +1010,21 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 		goto err_irq_cleanup;
 	}
 
-	err = mlx5_events_init(dev);
-	if (err) {
-		mlx5_core_err(dev, "failed to initialize events\n");
-		goto err_eq_cleanup;
-	}
-
 	err = mlx5_fw_reset_init(dev);
 	if (err) {
 		mlx5_core_err(dev, "failed to initialize fw reset events\n");
-		goto err_events_cleanup;
+		goto err_eq_cleanup;
 	}
 
 	mlx5_cq_debugfs_init(dev);
 
 	mlx5_init_reserved_gids(dev);
 
-	mlx5_init_clock(dev);
+	err = mlx5_init_clock(dev);
+	if (err) {
+		mlx5_core_err(dev, "failed to initialize hardware clock\n");
+		goto err_tables_cleanup;
+	}
 
 	dev->vxlan = mlx5_vxlan_create(dev);
 	dev->geneve = mlx5_geneve_create(dev);
@@ -1044,7 +1032,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	err = mlx5_init_rl_table(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init rate limiting\n");
-		goto err_tables_cleanup;
+		goto err_clock_cleanup;
 	}
 
 	err = mlx5_mpfs_init(dev);
@@ -1096,9 +1084,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	}
 
 	dev->dm = mlx5_dm_create(dev);
-	if (IS_ERR(dev->dm))
-		mlx5_core_warn(dev, "Failed to init device memory %ld\n", PTR_ERR(dev->dm));
-
+	dev->st = mlx5_st_create(dev);
 	dev->tracer = mlx5_fw_tracer_create(dev);
 	dev->hv_vhca = mlx5_hv_vhca_create(dev);
 	dev->rsc_dump = mlx5_rsc_dump_create(dev);
@@ -1121,21 +1107,19 @@ err_mpfs_cleanup:
 	mlx5_mpfs_cleanup(dev);
 err_rl_cleanup:
 	mlx5_cleanup_rl_table(dev);
-err_tables_cleanup:
+err_clock_cleanup:
 	mlx5_geneve_destroy(dev->geneve);
 	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_clock(dev);
+err_tables_cleanup:
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_fw_reset_cleanup(dev);
-err_events_cleanup:
-	mlx5_events_cleanup(dev);
 err_eq_cleanup:
 	mlx5_eq_table_cleanup(dev);
 err_irq_cleanup:
 	mlx5_irq_table_cleanup(dev);
 err_devcom:
-	mlx5_unregister_hca_devcom_comp(dev);
 	mlx5_devcom_unregister_device(dev->priv.devc);
 
 	return err;
@@ -1146,6 +1130,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_rsc_dump_destroy(dev);
 	mlx5_hv_vhca_destroy(dev->hv_vhca);
 	mlx5_fw_tracer_destroy(dev->tracer);
+	mlx5_st_destroy(dev);
 	mlx5_dm_cleanup(dev);
 	mlx5_fs_core_free(dev);
 	mlx5_sf_table_cleanup(dev);
@@ -1162,10 +1147,8 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_fw_reset_cleanup(dev);
-	mlx5_events_cleanup(dev);
 	mlx5_eq_table_cleanup(dev);
 	mlx5_irq_table_cleanup(dev);
-	mlx5_unregister_hca_devcom_comp(dev);
 	mlx5_devcom_unregister_device(dev->priv.devc);
 }
 
@@ -1203,24 +1186,24 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
 	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP);
 
-	mlx5_start_health_poll(dev);
-
 	err = mlx5_core_enable_hca(dev, 0);
 	if (err) {
 		mlx5_core_err(dev, "enable hca failed\n");
-		goto stop_health_poll;
+		goto err_cmd_cleanup;
 	}
 
+	mlx5_start_health_poll(dev);
+
 	err = mlx5_core_set_issi(dev);
 	if (err) {
 		mlx5_core_err(dev, "failed to set issi\n");
-		goto err_disable_hca;
+		goto stop_health_poll;
 	}
 
 	err = mlx5_satisfy_startup_pages(dev, 1);
 	if (err) {
 		mlx5_core_err(dev, "failed to allocate boot pages\n");
-		goto err_disable_hca;
+		goto stop_health_poll;
 	}
 
 	err = mlx5_tout_query_dtor(dev);
@@ -1233,10 +1216,9 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
 
 reclaim_boot_pages:
 	mlx5_reclaim_startup_pages(dev);
-err_disable_hca:
-	mlx5_core_disable_hca(dev, 0);
 stop_health_poll:
 	mlx5_stop_health_poll(dev, boot);
+	mlx5_core_disable_hca(dev, 0);
 err_cmd_cleanup:
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_disable(dev);
@@ -1247,8 +1229,8 @@ err_cmd_cleanup:
 static void mlx5_function_disable(struct mlx5_core_dev *dev, bool boot)
 {
 	mlx5_reclaim_startup_pages(dev);
-	mlx5_core_disable_hca(dev, 0);
 	mlx5_stop_health_poll(dev, boot);
+	mlx5_core_disable_hca(dev, 0);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_disable(dev);
 }
@@ -1335,10 +1317,9 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 {
 	int err;
 
-	dev->priv.uar = mlx5_get_uars_page(dev);
-	if (IS_ERR(dev->priv.uar)) {
-		mlx5_core_err(dev, "Failed allocating uar, aborting\n");
-		err = PTR_ERR(dev->priv.uar);
+	err = mlx5_alloc_bfreg(dev, &dev->priv.bfreg, false, false);
+	if (err) {
+		mlx5_core_err(dev, "Failed allocating bfreg, %d\n", err);
 		return err;
 	}
 
@@ -1357,6 +1338,8 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 		goto err_eq_table;
 	}
 
+	mlx5_clock_load(dev);
+
 	err = mlx5_fw_tracer_init(dev->tracer);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init FW tracer %d\n", err);
@@ -1394,12 +1377,6 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 
 	mlx5_vhca_event_start(dev);
 
-	err = mlx5_sf_hw_table_create(dev);
-	if (err) {
-		mlx5_core_err(dev, "sf table create failed %d\n", err);
-		goto err_vhca;
-	}
-
 	err = mlx5_ec_init(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init embedded CPU\n");
@@ -1428,8 +1405,6 @@ err_sriov:
 	mlx5_lag_remove_mdev(dev);
 	mlx5_ec_cleanup(dev);
 err_ec:
-	mlx5_sf_hw_table_destroy(dev);
-err_vhca:
 	mlx5_vhca_event_stop(dev);
 err_set_hca:
 	mlx5_fs_core_cleanup(dev);
@@ -1440,13 +1415,14 @@ err_fpga_start:
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
 	mlx5_fw_reset_events_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
+	mlx5_clock_unload(dev);
 	mlx5_eq_table_destroy(dev);
 err_eq_table:
 	mlx5_irq_table_destroy(dev);
 err_irq_table:
 	mlx5_pagealloc_stop(dev);
 	mlx5_events_stop(dev);
-	mlx5_put_uars_page(dev, dev->priv.uar);
+	mlx5_free_bfreg(dev, &dev->priv.bfreg);
 	return err;
 }
 
@@ -1454,23 +1430,24 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 {
 	mlx5_eswitch_disable(dev->priv.eswitch);
 	mlx5_devlink_traps_unregister(priv_to_devlink(dev));
+	mlx5_vhca_event_stop(dev);
 	mlx5_sf_dev_table_destroy(dev);
 	mlx5_sriov_detach(dev);
 	mlx5_lag_remove_mdev(dev);
 	mlx5_ec_cleanup(dev);
 	mlx5_sf_hw_table_destroy(dev);
-	mlx5_vhca_event_stop(dev);
 	mlx5_fs_core_cleanup(dev);
 	mlx5_fpga_device_stop(dev);
 	mlx5_rsc_dump_cleanup(dev);
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
 	mlx5_fw_reset_events_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
+	mlx5_clock_unload(dev);
 	mlx5_eq_table_destroy(dev);
 	mlx5_irq_table_destroy(dev);
 	mlx5_pagealloc_stop(dev);
 	mlx5_events_stop(dev);
-	mlx5_put_uars_page(dev, dev->priv.uar);
+	mlx5_free_bfreg(dev, &dev->priv.bfreg);
 }
 
 int mlx5_init_one_devl_locked(struct mlx5_core_dev *dev)
@@ -1789,9 +1766,12 @@ static const int types[] = {
 	MLX5_CAP_VDPA_EMULATION,
 	MLX5_CAP_IPSEC,
 	MLX5_CAP_PORT_SELECTION,
+	MLX5_CAP_PSP,
 	MLX5_CAP_MACSEC,
 	MLX5_CAP_ADV_VIRTUALIZATION,
 	MLX5_CAP_CRYPTO,
+	MLX5_CAP_SHAMPO,
+	MLX5_CAP_ADV_RDMA,
 };
 
 static void mlx5_hca_caps_free(struct mlx5_core_dev *dev)
@@ -1836,6 +1816,50 @@ static int vhca_id_show(struct seq_file *file, void *priv)
 
 DEFINE_SHOW_ATTRIBUTE(vhca_id);
 
+static int mlx5_notifiers_init(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = mlx5_events_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "failed to initialize events\n");
+		return err;
+	}
+
+	BLOCKING_INIT_NOTIFIER_HEAD(&dev->priv.esw_n_head);
+	mlx5_vhca_state_notifier_init(dev);
+
+	err = mlx5_sf_hw_notifier_init(dev);
+	if (err)
+		goto err_sf_hw_notifier;
+
+	err = mlx5_sf_notifiers_init(dev);
+	if (err)
+		goto err_sf_notifiers;
+
+	err = mlx5_sf_dev_notifier_init(dev);
+	if (err)
+		goto err_sf_dev_notifier;
+
+	return 0;
+
+err_sf_dev_notifier:
+	mlx5_sf_notifiers_cleanup(dev);
+err_sf_notifiers:
+	mlx5_sf_hw_notifier_cleanup(dev);
+err_sf_hw_notifier:
+	mlx5_events_cleanup(dev);
+	return err;
+}
+
+static void mlx5_notifiers_cleanup(struct mlx5_core_dev *dev)
+{
+	mlx5_sf_dev_notifier_cleanup(dev);
+	mlx5_sf_notifiers_cleanup(dev);
+	mlx5_sf_hw_notifier_cleanup(dev);
+	mlx5_events_cleanup(dev);
+}
+
 int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 {
 	struct mlx5_priv *priv = &dev->priv;
@@ -1891,6 +1915,10 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	if (err)
 		goto err_hca_caps;
 
+	err = mlx5_notifiers_init(dev);
+	if (err)
+		goto err_hca_caps;
+
 	/* The conjunction of sw_vhca_id with sw_owner_id will be a global
 	 * unique id per function which uses mlx5_core.
 	 * Those values are supplied to FW as part of the init HCA command to
@@ -1933,6 +1961,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 	if (priv->sw_vhca_id > 0)
 		ida_free(&sw_vhca_ida, dev->priv.sw_vhca_id);
 
+	mlx5_notifiers_cleanup(dev);
 	mlx5_hca_caps_free(dev);
 	mlx5_adev_cleanup(dev);
 	mlx5_pagealloc_cleanup(dev);
@@ -2108,7 +2137,6 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
 
 	pci_set_master(pdev);
 	pci_restore_state(pdev);
-	pci_save_state(pdev);
 
 	err = wait_vital(pdev);
 	if (err) {
@@ -2245,6 +2273,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x1021) },			/* ConnectX-7 */
 	{ PCI_VDEVICE(MELLANOX, 0x1023) },			/* ConnectX-8 */
 	{ PCI_VDEVICE(MELLANOX, 0x1025) },			/* ConnectX-9 */
+	{ PCI_VDEVICE(MELLANOX, 0x1027) },			/* ConnectX-10 */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d2) },			/* BlueField integrated ConnectX-5 network controller */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF},	/* BlueField integrated ConnectX-5 network controller VF */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d6) },			/* BlueField-2 integrated ConnectX-6 Dx network controller */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 99de67c3aa74..cfebc110c02f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -114,6 +114,26 @@ struct mlx5_cmd_alias_obj_create_attr {
 	u8 access_key[ACCESS_KEY_LEN];
 };
 
+struct mlx5_port_eth_proto {
+	u32 cap;
+	u32 admin;
+	u32 oper;
+};
+
+struct mlx5_module_eeprom_query_params {
+	u16 size;
+	u16 offset;
+	u16 i2c_address;
+	u32 page;
+	u32 bank;
+	u32 module_number;
+};
+
+struct mlx5_link_info {
+	u32 speed;
+	u32 lanes;
+};
+
 static inline void mlx5_printk(struct mlx5_core_dev *dev, int level, const char *format, ...)
 {
 	struct device *device = dev->device;
@@ -280,6 +300,89 @@ int mlx5_set_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 arm, u8 mode);
 struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev);
 void mlx5_dm_cleanup(struct mlx5_core_dev *dev);
 
+#ifdef CONFIG_PCIE_TPH
+struct mlx5_st *mlx5_st_create(struct mlx5_core_dev *dev);
+void mlx5_st_destroy(struct mlx5_core_dev *dev);
+#else
+static inline struct mlx5_st *
+mlx5_st_create(struct mlx5_core_dev *dev) { return NULL; }
+static inline void mlx5_st_destroy(struct mlx5_core_dev *dev) { return; }
+#endif
+
+void mlx5_toggle_port_link(struct mlx5_core_dev *dev);
+int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
+			       enum mlx5_port_status status);
+int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
+				 enum mlx5_port_status *status);
+int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration);
+
+int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port);
+int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause);
+int mlx5_query_port_pause(struct mlx5_core_dev *dev,
+			  u32 *rx_pause, u32 *tx_pause);
+
+int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx);
+int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx,
+			u8 *pfc_en_rx);
+
+int mlx5_set_port_stall_watermark(struct mlx5_core_dev *dev,
+				  u16 stall_critical_watermark,
+				  u16 stall_minor_watermark);
+int mlx5_query_port_stall_watermark(struct mlx5_core_dev *dev,
+				    u16 *stall_critical_watermark,
+				    u16 *stall_minor_watermark);
+
+int mlx5_max_tc(struct mlx5_core_dev *mdev);
+int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc);
+int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev,
+			    u8 prio, u8 *tc);
+int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group);
+int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev,
+			     u8 tc, u8 *tc_group);
+int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw);
+int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev,
+				u8 tc, u8 *bw_pct);
+int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev,
+				    u8 *max_bw_value,
+				    u8 *max_bw_unit);
+int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev,
+				   u8 *max_bw_value,
+				   u8 *max_bw_unit);
+int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode);
+int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode);
+
+int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out, int outlen);
+int mlx5_set_ports_check(struct mlx5_core_dev *mdev, u32 *in, int inlen);
+int mlx5_set_port_fcs(struct mlx5_core_dev *mdev, u8 enable);
+void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported,
+			 bool *enabled);
+int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
+			     u16 offset, u16 size, u8 *data, u8 *status);
+int
+mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev,
+				 struct mlx5_module_eeprom_query_params *params,
+				 u8 *data, u8 *status);
+
+int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out);
+int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in);
+int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state);
+int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state);
+int mlx5_query_port_buffer_ownership(struct mlx5_core_dev *mdev,
+				     u8 *buffer_ownership);
+int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio);
+int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio);
+
+int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
+			      struct mlx5_port_eth_proto *eproto);
+bool mlx5_ptys_ext_supported(struct mlx5_core_dev *mdev);
+const struct mlx5_link_info *mlx5_port_ptys2info(struct mlx5_core_dev *mdev,
+						 u32 eth_proto_oper,
+						 bool force_legacy);
+u32 mlx5_port_info2linkmodes(struct mlx5_core_dev *mdev,
+			     struct mlx5_link_info *info,
+			     bool force_legacy);
+int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
+
 #define MLX5_PPS_CAP(mdev) (MLX5_CAP_GEN((mdev), pps) &&		\
 			    MLX5_CAP_GEN((mdev), pps_modify) &&		\
 			    MLX5_CAP_MCAM_FEATURE((mdev), mtpps_fs) &&	\
@@ -341,6 +444,8 @@ int mlx5_init_one_light(struct mlx5_core_dev *dev);
 void mlx5_uninit_one_light(struct mlx5_core_dev *dev);
 void mlx5_unload_one_light(struct mlx5_core_dev *dev);
 
+void mlx5_query_nic_sw_system_image_guid(struct mlx5_core_dev *mdev, u8 *buf,
+					 u8 *len);
 int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap, u16 vport,
 				  u16 opmod);
 #define mlx5_vport_get_other_func_general_cap(dev, vport, out)		\
@@ -401,4 +506,17 @@ static inline int mlx5_max_eq_cap_get(const struct mlx5_core_dev *dev)
 
 	return 1 << MLX5_CAP_GEN(dev, log_max_eq);
 }
+
+static inline bool mlx5_pcie_cong_event_supported(struct mlx5_core_dev *dev)
+{
+	u64 features = MLX5_CAP_GEN_2_64(dev, general_obj_types_127_64);
+
+	if (!(features & MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT))
+		return false;
+
+	if (dev->sd)
+		return false;
+
+	return true;
+}
 #endif /* __MLX5_CORE_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
index 0881e961d8b1..586688da9940 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
@@ -10,12 +10,15 @@
 
 struct mlx5_irq;
 struct cpu_rmap;
+struct mlx5_irq_pool;
 
 int mlx5_irq_table_init(struct mlx5_core_dev *dev);
 void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev);
 int mlx5_irq_table_create(struct mlx5_core_dev *dev);
 void mlx5_irq_table_destroy(struct mlx5_core_dev *dev);
 void mlx5_irq_table_free_irqs(struct mlx5_core_dev *dev);
+struct mlx5_irq_pool *
+mlx5_irq_table_get_comp_irq_pool(struct mlx5_core_dev *dev);
 int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table);
 int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table);
 struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev);
@@ -38,7 +41,6 @@ struct cpumask *mlx5_irq_get_affinity_mask(struct mlx5_irq *irq);
 int mlx5_irq_get_index(struct mlx5_irq *irq);
 int mlx5_irq_get_irq(const struct mlx5_irq *irq);
 
-struct mlx5_irq_pool;
 #ifdef CONFIG_MLX5_SF
 struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev,
 						    struct cpumask *used_cpus, u16 vecidx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 972e8e9df585..cd68c4b2c0bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -291,7 +291,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 function)
 static int alloc_system_page(struct mlx5_core_dev *dev, u32 function)
 {
 	struct device *device = mlx5_core_dma_dev(dev);
-	int nid = dev_to_node(device);
+	int nid = dev->priv.numa_node;
 	struct page *page;
 	u64 zero_addr = 1;
 	u64 addr;
@@ -489,9 +489,12 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
 	u32 func_id;
 	u32 npages;
 	u32 i = 0;
+	int err;
 
-	if (!mlx5_cmd_is_down(dev))
-		return mlx5_cmd_do(dev, in, in_size, out, out_size);
+	err = mlx5_cmd_do(dev, in, in_size, out, out_size);
+	/* If FW is gone (-ENXIO), proceed to forceful reclaim */
+	if (err != -ENXIO)
+		return err;
 
 	/* No hard feelings, we want our pages back! */
 	npages = MLX5_GET(manage_pages_in, in, input_num_entries);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 7db9cab9bedf..aa3b5878e3da 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -54,7 +54,7 @@ static int mlx5_core_func_to_vport(const struct mlx5_core_dev *dev,
 
 /**
  * mlx5_get_default_msix_vec_count - Get the default number of MSI-X vectors
- *                                   to be ssigned to each VF.
+ *                                   to be assigned to each VF.
  * @dev: PF to work on
  * @num_vfs: Number of enabled VFs
  */
@@ -148,7 +148,7 @@ out:
  * Free the IRQ and other resources such as rmap from the system.
  * BUT doesn't free or remove reference from mlx5.
  * This function is very important for the shutdown flow, where we need to
- * cleanup system resoruces but keep mlx5 objects alive,
+ * cleanup system resources but keep mlx5 objects alive,
  * see mlx5_irq_table_free_irqs().
  */
 static void mlx5_system_free_irq(struct mlx5_irq *irq)
@@ -324,10 +324,8 @@ err_xa:
 	free_irq(irq->map.virq, &irq->nh);
 err_req_irq:
 #ifdef CONFIG_RFS_ACCEL
-	if (i && rmap && *rmap) {
-		free_irq_cpu_rmap(*rmap);
-		*rmap = NULL;
-	}
+	if (i && rmap && *rmap)
+		irq_cpu_rmap_remove(*rmap, irq->map.virq);
 err_irq_rmap:
 #endif
 	if (i && pci_msix_can_alloc_dyn(dev->pdev))
@@ -378,6 +376,11 @@ int mlx5_irq_get_index(struct mlx5_irq *irq)
 	return irq->map.index;
 }
 
+struct mlx5_irq_pool *mlx5_irq_get_pool(struct mlx5_irq *irq)
+{
+	return irq->pool;
+}
+
 /* irq_pool API */
 
 /* requesting an irq from a given pool according to given index */
@@ -405,18 +408,20 @@ static struct mlx5_irq_pool *sf_ctrl_irq_pool_get(struct mlx5_irq_table *irq_tab
 	return irq_table->sf_ctrl_pool;
 }
 
-static struct mlx5_irq_pool *sf_irq_pool_get(struct mlx5_irq_table *irq_table)
+static struct mlx5_irq_pool *
+sf_comp_irq_pool_get(struct mlx5_irq_table *irq_table)
 {
 	return irq_table->sf_comp_pool;
 }
 
-struct mlx5_irq_pool *mlx5_irq_pool_get(struct mlx5_core_dev *dev)
+struct mlx5_irq_pool *
+mlx5_irq_table_get_comp_irq_pool(struct mlx5_core_dev *dev)
 {
 	struct mlx5_irq_table *irq_table = mlx5_irq_table_get(dev);
 	struct mlx5_irq_pool *pool = NULL;
 
 	if (mlx5_core_is_sf(dev))
-		pool = sf_irq_pool_get(irq_table);
+		pool = sf_comp_irq_pool_get(irq_table);
 
 	/* In some configs, there won't be a pool of SFs IRQs. Hence, returning
 	 * the PF IRQs pool in case the SF pool doesn't exist.
@@ -463,26 +468,32 @@ void mlx5_ctrl_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *ctrl_irq)
 struct mlx5_irq *mlx5_ctrl_irq_request(struct mlx5_core_dev *dev)
 {
 	struct mlx5_irq_pool *pool = ctrl_irq_pool_get(dev);
-	struct irq_affinity_desc af_desc;
+	struct irq_affinity_desc *af_desc;
 	struct mlx5_irq *irq;
 
-	cpumask_copy(&af_desc.mask, cpu_online_mask);
-	af_desc.is_managed = false;
+	af_desc = kvzalloc(sizeof(*af_desc), GFP_KERNEL);
+	if (!af_desc)
+		return ERR_PTR(-ENOMEM);
+
+	cpumask_copy(&af_desc->mask, cpu_online_mask);
+	af_desc->is_managed = false;
 	if (!mlx5_irq_pool_is_sf_pool(pool)) {
 		/* In case we are allocating a control IRQ from a pci device's pool.
 		 * This can happen also for a SF if the SFs pool is empty.
 		 */
 		if (!pool->xa_num_irqs.max) {
-			cpumask_clear(&af_desc.mask);
+			cpumask_clear(&af_desc->mask);
 			/* In case we only have a single IRQ for PF/VF */
-			cpumask_set_cpu(cpumask_first(cpu_online_mask), &af_desc.mask);
+			cpumask_set_cpu(cpumask_first(cpu_online_mask), &af_desc->mask);
 		}
 		/* Allocate the IRQ in index 0. The vector was already allocated */
-		irq = irq_pool_request_vector(pool, 0, &af_desc, NULL);
+		irq = irq_pool_request_vector(pool, 0, af_desc, NULL);
 	} else {
-		irq = mlx5_irq_affinity_request(dev, pool, &af_desc);
+		irq = mlx5_irq_affinity_request(dev, pool, af_desc);
 	}
 
+	kvfree(af_desc);
+
 	return irq;
 }
 
@@ -541,16 +552,26 @@ struct mlx5_irq *mlx5_irq_request_vector(struct mlx5_core_dev *dev, u16 cpu,
 {
 	struct mlx5_irq_table *table = mlx5_irq_table_get(dev);
 	struct mlx5_irq_pool *pool = table->pcif_pool;
-	struct irq_affinity_desc af_desc;
 	int offset = MLX5_IRQ_VEC_COMP_BASE;
+	struct irq_affinity_desc *af_desc;
+	struct mlx5_irq *irq;
+
+	af_desc = kvzalloc(sizeof(*af_desc), GFP_KERNEL);
+	if (!af_desc)
+		return ERR_PTR(-ENOMEM);
 
 	if (!pool->xa_num_irqs.max)
 		offset = 0;
 
-	af_desc.is_managed = false;
-	cpumask_clear(&af_desc.mask);
-	cpumask_set_cpu(cpu, &af_desc.mask);
-	return mlx5_irq_request(dev, vecidx + offset, &af_desc, rmap);
+	af_desc->is_managed = false;
+	cpumask_clear(&af_desc->mask);
+	cpumask_set_cpu(cpu, &af_desc->mask);
+
+	irq = mlx5_irq_request(dev, vecidx + offset, af_desc, rmap);
+
+	kvfree(af_desc);
+
+	return irq;
 }
 
 static struct mlx5_irq_pool *
@@ -572,7 +593,7 @@ irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name,
 	pool->min_threshold = min_threshold * MLX5_EQ_REFS_PER_IRQ;
 	pool->max_threshold = max_threshold * MLX5_EQ_REFS_PER_IRQ;
 	mlx5_core_dbg(dev, "pool->name = %s, pool->size = %d, pool->start = %d",
-		      name, size, start);
+		      name ? name : "mlx5_pcif_pool", size, start);
 	return pool;
 }
 
@@ -581,7 +602,7 @@ static void irq_pool_free(struct mlx5_irq_pool *pool)
 	struct mlx5_irq *irq;
 	unsigned long index;
 
-	/* There are cases in which we are destrying the irq_table before
+	/* There are cases in which we are destroying the irq_table before
 	 * freeing all the IRQs, fast teardown for example. Hence, free the irqs
 	 * which might not have been freed.
 	 */
@@ -610,7 +631,7 @@ static int irq_pools_init(struct mlx5_core_dev *dev, int sf_vec, int pcif_vec,
 	if (!mlx5_sf_max_functions(dev))
 		return 0;
 	if (sf_vec < MLX5_IRQ_VEC_COMP_BASE_SF) {
-		mlx5_core_dbg(dev, "Not enught IRQs for SFs. SF may run at lower performance\n");
+		mlx5_core_dbg(dev, "Not enough IRQs for SFs. SF may run at lower performance\n");
 		return 0;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
index c4d377f8df30..cc064425fe16 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
@@ -28,7 +28,6 @@ struct mlx5_irq_pool {
 	struct mlx5_core_dev *dev;
 };
 
-struct mlx5_irq_pool *mlx5_irq_pool_get(struct mlx5_core_dev *dev);
 static inline bool mlx5_irq_pool_is_sf_pool(struct mlx5_irq_pool *pool)
 {
 	return !strncmp("mlx5_sf", pool->name, strlen("mlx5_sf"));
@@ -40,5 +39,6 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i,
 int mlx5_irq_get_locked(struct mlx5_irq *irq);
 int mlx5_irq_read_locked(struct mlx5_irq *irq);
 int mlx5_irq_put(struct mlx5_irq *irq);
+struct mlx5_irq_pool *mlx5_irq_get_pool(struct mlx5_irq *irq);
 
 #endif /* __PCI_IRQ_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 50931584132b..85a9e534f442 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -196,7 +196,6 @@ void mlx5_toggle_port_link(struct mlx5_core_dev *dev)
 	if (ps == MLX5_PORT_UP)
 		mlx5_set_port_admin_status(dev, MLX5_PORT_UP);
 }
-EXPORT_SYMBOL_GPL(mlx5_toggle_port_link);
 
 int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 			       enum mlx5_port_status status)
@@ -210,7 +209,6 @@ int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 	return mlx5_core_access_reg(dev, in, sizeof(in), out,
 				    sizeof(out), MLX5_REG_PAOS, 0, 1);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_admin_status);
 
 int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 				 enum mlx5_port_status *status)
@@ -227,7 +225,6 @@ int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 	*status = MLX5_GET(paos_reg, out, admin_status);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_admin_status);
 
 static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, u16 *admin_mtu,
 				u16 *max_mtu, u16 *oper_mtu, u8 port)
@@ -257,7 +254,6 @@ int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port)
 	return mlx5_core_access_reg(dev, in, sizeof(in), out,
 				   sizeof(out), MLX5_REG_PMTU, 0, 1);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_mtu);
 
 void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu,
 			     u8 port)
@@ -293,11 +289,11 @@ int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num)
 }
 
 static int mlx5_query_module_id(struct mlx5_core_dev *dev, int module_num,
-				u8 *module_id)
+				u8 *module_id, u8 *status)
 {
 	u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {};
 	u32 out[MLX5_ST_SZ_DW(mcia_reg)];
-	int err, status;
+	int err;
 	u8 *ptr;
 
 	MLX5_SET(mcia_reg, in, i2c_device_address, MLX5_I2C_ADDR_LOW);
@@ -312,12 +308,12 @@ static int mlx5_query_module_id(struct mlx5_core_dev *dev, int module_num,
 	if (err)
 		return err;
 
-	status = MLX5_GET(mcia_reg, out, status);
-	if (status) {
-		mlx5_core_err(dev, "query_mcia_reg failed: status: 0x%x\n",
-			      status);
+	if (MLX5_GET(mcia_reg, out, status)) {
+		if (status)
+			*status = MLX5_GET(mcia_reg, out, status);
 		return -EIO;
 	}
+
 	ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
 
 	*module_id = ptr[0];
@@ -374,13 +370,14 @@ static int mlx5_mcia_max_bytes(struct mlx5_core_dev *dev)
 }
 
 static int mlx5_query_mcia(struct mlx5_core_dev *dev,
-			   struct mlx5_module_eeprom_query_params *params, u8 *data)
+			   struct mlx5_module_eeprom_query_params *params,
+			   u8 *data, u8 *status)
 {
 	u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {};
 	u32 out[MLX5_ST_SZ_DW(mcia_reg)];
-	int status, err;
 	void *ptr;
 	u16 size;
+	int err;
 
 	size = min_t(int, params->size, mlx5_mcia_max_bytes(dev));
 
@@ -396,12 +393,9 @@ static int mlx5_query_mcia(struct mlx5_core_dev *dev,
 	if (err)
 		return err;
 
-	status = MLX5_GET(mcia_reg, out, status);
-	if (status) {
-		mlx5_core_err(dev, "query_mcia_reg failed: status: 0x%x\n",
-			      status);
+	*status = MLX5_GET(mcia_reg, out, status);
+	if (*status)
 		return -EIO;
-	}
 
 	ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
 	memcpy(data, ptr, size);
@@ -410,7 +404,7 @@ static int mlx5_query_mcia(struct mlx5_core_dev *dev,
 }
 
 int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
-			     u16 offset, u16 size, u8 *data)
+			     u16 offset, u16 size, u8 *data, u8 *status)
 {
 	struct mlx5_module_eeprom_query_params query = {0};
 	u8 module_id;
@@ -420,7 +414,8 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 	if (err)
 		return err;
 
-	err = mlx5_query_module_id(dev, query.module_number, &module_id);
+	err = mlx5_query_module_id(dev, query.module_number, &module_id,
+				   status);
 	if (err)
 		return err;
 
@@ -445,13 +440,12 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 	query.size = size;
 	query.offset = offset;
 
-	return mlx5_query_mcia(dev, &query, data);
+	return mlx5_query_mcia(dev, &query, data, status);
 }
-EXPORT_SYMBOL_GPL(mlx5_query_module_eeprom);
 
 int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev,
 				     struct mlx5_module_eeprom_query_params *params,
-				     u8 *data)
+				     u8 *data, u8 *status)
 {
 	int err;
 
@@ -465,9 +459,8 @@ int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev,
 		return -EINVAL;
 	}
 
-	return mlx5_query_mcia(dev, params, data);
+	return mlx5_query_mcia(dev, params, data, status);
 }
-EXPORT_SYMBOL_GPL(mlx5_query_module_eeprom_by_page);
 
 static int mlx5_query_port_pvlc(struct mlx5_core_dev *dev, u32 *pvlc,
 				int pvlc_size,  u8 local_port)
@@ -518,7 +511,6 @@ int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause)
 	return mlx5_core_access_reg(dev, in, sizeof(in), out,
 				    sizeof(out), MLX5_REG_PFCC, 0, 1);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_pause);
 
 int mlx5_query_port_pause(struct mlx5_core_dev *dev,
 			  u32 *rx_pause, u32 *tx_pause)
@@ -538,7 +530,6 @@ int mlx5_query_port_pause(struct mlx5_core_dev *dev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_pause);
 
 int mlx5_set_port_stall_watermark(struct mlx5_core_dev *dev,
 				  u16 stall_critical_watermark,
@@ -597,7 +588,6 @@ int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx)
 	return mlx5_core_access_reg(dev, in, sizeof(in), out,
 				    sizeof(out), MLX5_REG_PFCC, 0, 1);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_pfc);
 
 int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx)
 {
@@ -616,7 +606,6 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_pfc);
 
 int mlx5_max_tc(struct mlx5_core_dev *mdev)
 {
@@ -667,7 +656,6 @@ int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_prio_tc);
 
 int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev,
 			    u8 prio, u8 *tc)
@@ -689,7 +677,6 @@ int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev,
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_prio_tc);
 
 static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
 				   int inlen)
@@ -728,7 +715,6 @@ int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group)
 
 	return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in));
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_tc_group);
 
 int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev,
 			     u8 tc, u8 *tc_group)
@@ -749,7 +735,6 @@ int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_tc_group);
 
 int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw)
 {
@@ -763,7 +748,6 @@ int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw)
 
 	return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in));
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_tc_bw_alloc);
 
 int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev,
 				u8 tc, u8 *bw_pct)
@@ -784,7 +768,6 @@ int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_tc_bw_alloc);
 
 int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev,
 				    u8 *max_bw_value,
@@ -808,7 +791,6 @@ int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev,
 
 	return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in));
 }
-EXPORT_SYMBOL_GPL(mlx5_modify_port_ets_rate_limit);
 
 int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev,
 				   u8 *max_bw_value,
@@ -834,7 +816,6 @@ int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_ets_rate_limit);
 
 int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode)
 {
@@ -845,7 +826,6 @@ int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode)
 	MLX5_SET(set_wol_rol_in, in, wol_mode, wol_mode);
 	return mlx5_cmd_exec_in(mdev, set_wol_rol, in);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_wol);
 
 int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode)
 {
@@ -860,7 +840,6 @@ int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode)
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_wol);
 
 int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out, int outlen)
 {
@@ -988,6 +967,26 @@ int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state)
 	return err;
 }
 
+int mlx5_query_port_buffer_ownership(struct mlx5_core_dev *mdev,
+				     u8 *buffer_ownership)
+{
+	u32 out[MLX5_ST_SZ_DW(pfcc_reg)] = {};
+	int err;
+
+	if (!MLX5_CAP_PCAM_FEATURE(mdev, buffer_ownership)) {
+		*buffer_ownership = MLX5_BUF_OWNERSHIP_UNKNOWN;
+		return 0;
+	}
+
+	err = mlx5_query_pfcc_reg(mdev, out, sizeof(out));
+	if (err)
+		return err;
+
+	*buffer_ownership = MLX5_GET(pfcc_reg, out, buf_ownership);
+
+	return 0;
+}
+
 int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio)
 {
 	int sz = MLX5_ST_SZ_BYTES(qpdpm_reg);
@@ -1058,53 +1057,58 @@ out:
 }
 
 /* speed in units of 1Mb */
-static const u32 mlx5e_link_speed[MLX5E_LINK_MODES_NUMBER] = {
-	[MLX5E_1000BASE_CX_SGMII] = 1000,
-	[MLX5E_1000BASE_KX]       = 1000,
-	[MLX5E_10GBASE_CX4]       = 10000,
-	[MLX5E_10GBASE_KX4]       = 10000,
-	[MLX5E_10GBASE_KR]        = 10000,
-	[MLX5E_20GBASE_KR2]       = 20000,
-	[MLX5E_40GBASE_CR4]       = 40000,
-	[MLX5E_40GBASE_KR4]       = 40000,
-	[MLX5E_56GBASE_R4]        = 56000,
-	[MLX5E_10GBASE_CR]        = 10000,
-	[MLX5E_10GBASE_SR]        = 10000,
-	[MLX5E_10GBASE_ER]        = 10000,
-	[MLX5E_40GBASE_SR4]       = 40000,
-	[MLX5E_40GBASE_LR4]       = 40000,
-	[MLX5E_50GBASE_SR2]       = 50000,
-	[MLX5E_100GBASE_CR4]      = 100000,
-	[MLX5E_100GBASE_SR4]      = 100000,
-	[MLX5E_100GBASE_KR4]      = 100000,
-	[MLX5E_100GBASE_LR4]      = 100000,
-	[MLX5E_100BASE_TX]        = 100,
-	[MLX5E_1000BASE_T]        = 1000,
-	[MLX5E_10GBASE_T]         = 10000,
-	[MLX5E_25GBASE_CR]        = 25000,
-	[MLX5E_25GBASE_KR]        = 25000,
-	[MLX5E_25GBASE_SR]        = 25000,
-	[MLX5E_50GBASE_CR2]       = 50000,
-	[MLX5E_50GBASE_KR2]       = 50000,
+static const struct mlx5_link_info mlx5e_link_info[MLX5E_LINK_MODES_NUMBER] = {
+	[MLX5E_1000BASE_CX_SGMII]	= {.speed = 1000, .lanes = 1},
+	[MLX5E_1000BASE_KX]		= {.speed = 1000, .lanes = 1},
+	[MLX5E_10GBASE_CX4]		= {.speed = 10000, .lanes = 4},
+	[MLX5E_10GBASE_KX4]		= {.speed = 10000, .lanes = 4},
+	[MLX5E_10GBASE_KR]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_20GBASE_KR2]		= {.speed = 20000, .lanes = 2},
+	[MLX5E_40GBASE_CR4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_40GBASE_KR4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_56GBASE_R4]		= {.speed = 56000, .lanes = 4},
+	[MLX5E_10GBASE_CR]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_10GBASE_SR]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_10GBASE_ER]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_40GBASE_SR4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_40GBASE_LR4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_50GBASE_SR2]		= {.speed = 50000, .lanes = 2},
+	[MLX5E_100GBASE_CR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100GBASE_SR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100GBASE_KR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100GBASE_LR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100BASE_TX]		= {.speed = 100, .lanes = 1},
+	[MLX5E_1000BASE_T]		= {.speed = 1000, .lanes = 1},
+	[MLX5E_10GBASE_T]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_25GBASE_CR]		= {.speed = 25000, .lanes = 1},
+	[MLX5E_25GBASE_KR]		= {.speed = 25000, .lanes = 1},
+	[MLX5E_25GBASE_SR]		= {.speed = 25000, .lanes = 1},
+	[MLX5E_50GBASE_CR2]		= {.speed = 50000, .lanes = 2},
+	[MLX5E_50GBASE_KR2]		= {.speed = 50000, .lanes = 2},
 };
 
-static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
-	[MLX5E_SGMII_100M] = 100,
-	[MLX5E_1000BASE_X_SGMII] = 1000,
-	[MLX5E_5GBASE_R] = 5000,
-	[MLX5E_10GBASE_XFI_XAUI_1] = 10000,
-	[MLX5E_40GBASE_XLAUI_4_XLPPI_4] = 40000,
-	[MLX5E_25GAUI_1_25GBASE_CR_KR] = 25000,
-	[MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2] = 50000,
-	[MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR] = 50000,
-	[MLX5E_CAUI_4_100GBASE_CR4_KR4] = 100000,
-	[MLX5E_100GAUI_2_100GBASE_CR2_KR2] = 100000,
-	[MLX5E_200GAUI_4_200GBASE_CR4_KR4] = 200000,
-	[MLX5E_400GAUI_8_400GBASE_CR8] = 400000,
-	[MLX5E_100GAUI_1_100GBASE_CR_KR] = 100000,
-	[MLX5E_200GAUI_2_200GBASE_CR2_KR2] = 200000,
-	[MLX5E_400GAUI_4_400GBASE_CR4_KR4] = 400000,
-	[MLX5E_800GAUI_8_800GBASE_CR8_KR8] = 800000,
+static const struct mlx5_link_info
+mlx5e_ext_link_info[MLX5E_EXT_LINK_MODES_NUMBER] = {
+	[MLX5E_SGMII_100M]			= {.speed = 100, .lanes = 1},
+	[MLX5E_1000BASE_X_SGMII]		= {.speed = 1000, .lanes = 1},
+	[MLX5E_5GBASE_R]			= {.speed = 5000, .lanes = 1},
+	[MLX5E_10GBASE_XFI_XAUI_1]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_40GBASE_XLAUI_4_XLPPI_4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_25GAUI_1_25GBASE_CR_KR]		= {.speed = 25000, .lanes = 1},
+	[MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2]	= {.speed = 50000, .lanes = 2},
+	[MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR]	= {.speed = 50000, .lanes = 1},
+	[MLX5E_CAUI_4_100GBASE_CR4_KR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100GAUI_2_100GBASE_CR2_KR2]	= {.speed = 100000, .lanes = 2},
+	[MLX5E_200GAUI_4_200GBASE_CR4_KR4]	= {.speed = 200000, .lanes = 4},
+	[MLX5E_400GAUI_8_400GBASE_CR8]		= {.speed = 400000, .lanes = 8},
+	[MLX5E_100GAUI_1_100GBASE_CR_KR]	= {.speed = 100000, .lanes = 1},
+	[MLX5E_200GAUI_2_200GBASE_CR2_KR2]	= {.speed = 200000, .lanes = 2},
+	[MLX5E_400GAUI_4_400GBASE_CR4_KR4]	= {.speed = 400000, .lanes = 4},
+	[MLX5E_800GAUI_8_800GBASE_CR8_KR8]	= {.speed = 800000, .lanes = 8},
+	[MLX5E_200GAUI_1_200GBASE_CR1_KR1]	= {.speed = 200000, .lanes = 1},
+	[MLX5E_400GAUI_2_400GBASE_CR2_KR2]	= {.speed = 400000, .lanes = 2},
+	[MLX5E_800GAUI_4_800GBASE_CR4_KR4]	= {.speed = 800000, .lanes = 4},
+	[MLX5E_1600TAUI_8_1600TBASE_CR8_KR8]	= {.speed = 1600000, .lanes = 8},
 };
 
 int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
@@ -1142,54 +1146,65 @@ bool mlx5_ptys_ext_supported(struct mlx5_core_dev *mdev)
 	return !!eproto.cap;
 }
 
-static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
-				     const u32 **arr, u32 *size,
-				     bool force_legacy)
+static void mlx5e_port_get_link_mode_info_arr(struct mlx5_core_dev *mdev,
+					      const struct mlx5_link_info **arr,
+					      u32 *size,
+					      bool force_legacy)
 {
 	bool ext = force_legacy ? false : mlx5_ptys_ext_supported(mdev);
 
-	*size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) :
-		      ARRAY_SIZE(mlx5e_link_speed);
-	*arr  = ext ? mlx5e_ext_link_speed : mlx5e_link_speed;
+	*size = ext ? ARRAY_SIZE(mlx5e_ext_link_info) :
+		      ARRAY_SIZE(mlx5e_link_info);
+	*arr  = ext ? mlx5e_ext_link_info : mlx5e_link_info;
 }
 
-u32 mlx5_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper,
-			 bool force_legacy)
+const struct mlx5_link_info *mlx5_port_ptys2info(struct mlx5_core_dev *mdev,
+						 u32 eth_proto_oper,
+						 bool force_legacy)
 {
 	unsigned long temp = eth_proto_oper;
-	const u32 *table;
-	u32 speed = 0;
+	const struct mlx5_link_info *table;
 	u32 max_size;
 	int i;
 
-	mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy);
+	mlx5e_port_get_link_mode_info_arr(mdev, &table, &max_size,
+					  force_legacy);
 	i = find_first_bit(&temp, max_size);
-	if (i < max_size)
-		speed = table[i];
-	return speed;
+
+	/* mlx5e_link_info has holes. Check speed
+	 * is not zero as indication of one.
+	 */
+	if (i < max_size && table[i].speed)
+		return &table[i];
+
+	return NULL;
 }
 
-u32 mlx5_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
-			      bool force_legacy)
+u32 mlx5_port_info2linkmodes(struct mlx5_core_dev *mdev,
+			     struct mlx5_link_info *info,
+			     bool force_legacy)
 {
+	const struct mlx5_link_info *table;
 	u32 link_modes = 0;
-	const u32 *table;
 	u32 max_size;
 	int i;
 
-	mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy);
+	mlx5e_port_get_link_mode_info_arr(mdev, &table, &max_size,
+					  force_legacy);
 	for (i = 0; i < max_size; ++i) {
-		if (table[i] == speed)
-			link_modes |= MLX5E_PROT_MASK(i);
+		if (table[i].speed == info->speed) {
+			if (!info->lanes || table[i].lanes == info->lanes)
+				link_modes |= MLX5E_PROT_MASK(i);
+		}
 	}
 	return link_modes;
 }
 
 int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 {
+	const struct mlx5_link_info *table;
 	struct mlx5_port_eth_proto eproto;
 	u32 max_speed = 0;
-	const u32 *table;
 	u32 max_size;
 	bool ext;
 	int err;
@@ -1200,10 +1215,10 @@ int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	if (err)
 		return err;
 
-	mlx5e_port_get_speed_arr(mdev, &table, &max_size, false);
+	mlx5e_port_get_link_mode_info_arr(mdev, &table, &max_size, false);
 	for (i = 0; i < max_size; ++i)
 		if (eproto.cap & MLX5E_PROT_MASK(i))
-			max_speed = max(max_speed, table[i]);
+			max_speed = max(max_speed, table[i].speed);
 
 	*speed = max_speed;
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
index a42f6cd99b74..5c552b71e371 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -118,8 +118,8 @@ static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *
 
 static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev)
 {
+	u8 mac[ETH_ALEN] = {};
 	union ib_gid gid;
-	u8 mac[ETH_ALEN];
 
 	mlx5_rdma_make_default_gid(dev, &gid);
 	return mlx5_core_roce_gid_set(dev, 0,
@@ -140,17 +140,17 @@ void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev)
 	mlx5_nic_vport_disable_roce(dev);
 }
 
-void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
+int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
 {
 	int err;
 
 	if (!MLX5_CAP_GEN(dev, roce))
-		return;
+		return 0;
 
 	err = mlx5_nic_vport_enable_roce(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err);
-		return;
+		return err;
 	}
 
 	err = mlx5_rdma_add_roce_addr(dev);
@@ -165,10 +165,11 @@ void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
 		goto del_roce_addr;
 	}
 
-	return;
+	return err;
 
 del_roce_addr:
 	mlx5_rdma_del_roce_addr(dev);
 disable_roce:
 	mlx5_nic_vport_disable_roce(dev);
+	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
index 750cff2a71a4..3d9e76c3d42f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
@@ -8,12 +8,12 @@
 
 #ifdef CONFIG_MLX5_ESWITCH
 
-void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
+int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
 void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev);
 
 #else /* CONFIG_MLX5_ESWITCH */
 
-static inline void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) {}
+static inline int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) {}
 
 #endif /* CONFIG_MLX5_ESWITCH */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index 99219ea52c4b..f310bde3d11f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -16,7 +16,6 @@ struct mlx5_sf_dev_table {
 	struct xarray devices;
 	phys_addr_t base_address;
 	u64 sf_bar_length;
-	struct notifier_block nb;
 	struct workqueue_struct *active_wq;
 	struct work_struct work;
 	u8 stop_active_wq:1;
@@ -156,18 +155,23 @@ static void mlx5_sf_dev_del(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_de
 static int
 mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_code, void *data)
 {
-	struct mlx5_sf_dev_table *table = container_of(nb, struct mlx5_sf_dev_table, nb);
+	struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev,
+						 priv.sf_dev_nb);
+	struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
 	const struct mlx5_vhca_state_event *event = data;
 	struct mlx5_sf_dev *sf_dev;
 	u16 max_functions;
 	u16 sf_index;
 	u16 base_id;
 
-	max_functions = mlx5_sf_max_functions(table->dev);
+	if (!table)
+		return 0;
+
+	max_functions = mlx5_sf_max_functions(dev);
 	if (!max_functions)
 		return 0;
 
-	base_id = mlx5_sf_start_function_id(table->dev);
+	base_id = mlx5_sf_start_function_id(dev);
 	if (event->function_id < base_id || event->function_id >= (base_id + max_functions))
 		return 0;
 
@@ -177,19 +181,19 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_
 	case MLX5_VHCA_STATE_INVALID:
 	case MLX5_VHCA_STATE_ALLOCATED:
 		if (sf_dev)
-			mlx5_sf_dev_del(table->dev, sf_dev, sf_index);
+			mlx5_sf_dev_del(dev, sf_dev, sf_index);
 		break;
 	case MLX5_VHCA_STATE_TEARDOWN_REQUEST:
 		if (sf_dev)
-			mlx5_sf_dev_del(table->dev, sf_dev, sf_index);
+			mlx5_sf_dev_del(dev, sf_dev, sf_index);
 		else
-			mlx5_core_err(table->dev,
+			mlx5_core_err(dev,
 				      "SF DEV: teardown state for invalid dev index=%d sfnum=0x%x\n",
 				      sf_index, event->sw_function_id);
 		break;
 	case MLX5_VHCA_STATE_ACTIVE:
 		if (!sf_dev)
-			mlx5_sf_dev_add(table->dev, sf_index, event->function_id,
+			mlx5_sf_dev_add(dev, sf_index, event->function_id,
 					event->sw_function_id);
 		break;
 	default:
@@ -315,6 +319,15 @@ static void mlx5_sf_dev_destroy_active_works(struct mlx5_sf_dev_table *table)
 	}
 }
 
+int mlx5_sf_dev_notifier_init(struct mlx5_core_dev *dev)
+{
+	if (mlx5_core_is_sf(dev))
+		return 0;
+
+	dev->priv.sf_dev_nb.notifier_call = mlx5_sf_dev_state_change_handler;
+	return mlx5_vhca_event_notifier_register(dev, &dev->priv.sf_dev_nb);
+}
+
 void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
 {
 	struct mlx5_sf_dev_table *table;
@@ -329,17 +342,12 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
 		goto table_err;
 	}
 
-	table->nb.notifier_call = mlx5_sf_dev_state_change_handler;
 	table->dev = dev;
 	table->sf_bar_length = 1 << (MLX5_CAP_GEN(dev, log_min_sf_size) + 12);
 	table->base_address = pci_resource_start(dev->pdev, 2);
 	xa_init(&table->devices);
 	dev->priv.sf_dev_table = table;
 
-	err = mlx5_vhca_event_notifier_register(dev, &table->nb);
-	if (err)
-		goto vhca_err;
-
 	err = mlx5_sf_dev_create_active_works(table);
 	if (err)
 		goto add_active_err;
@@ -351,10 +359,8 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
 
 arm_err:
 	mlx5_sf_dev_destroy_active_works(table);
-add_active_err:
-	mlx5_vhca_event_notifier_unregister(dev, &table->nb);
 	mlx5_vhca_event_work_queues_flush(dev);
-vhca_err:
+add_active_err:
 	kfree(table);
 	dev->priv.sf_dev_table = NULL;
 table_err:
@@ -372,6 +378,14 @@ static void mlx5_sf_dev_destroy_all(struct mlx5_sf_dev_table *table)
 	}
 }
 
+void mlx5_sf_dev_notifier_cleanup(struct mlx5_core_dev *dev)
+{
+	if (mlx5_core_is_sf(dev))
+		return;
+
+	mlx5_vhca_event_notifier_unregister(dev, &dev->priv.sf_dev_nb);
+}
+
 void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev)
 {
 	struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
@@ -380,8 +394,6 @@ void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev)
 		return;
 
 	mlx5_sf_dev_destroy_active_works(table);
-	mlx5_vhca_event_notifier_unregister(dev, &table->nb);
-	mlx5_vhca_event_work_queues_flush(dev);
 
 	/* Now that event handler is not running, it is safe to destroy
 	 * the sf device without race.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
index b99131e95e37..3ab0449c770c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
@@ -25,7 +25,9 @@ struct mlx5_sf_peer_devlink_event_ctx {
 	int err;
 };
 
+int mlx5_sf_dev_notifier_init(struct mlx5_core_dev *dev);
 void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev);
+void mlx5_sf_dev_notifier_cleanup(struct mlx5_core_dev *dev);
 void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev);
 
 int mlx5_sf_driver_register(void);
@@ -35,10 +37,19 @@ bool mlx5_sf_dev_allocated(const struct mlx5_core_dev *dev);
 
 #else
 
+static inline int mlx5_sf_dev_notifier_init(struct mlx5_core_dev *dev)
+{
+	return 0;
+}
+
 static inline void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
 {
 }
 
+static inline void mlx5_sf_dev_notifier_cleanup(struct mlx5_core_dev *dev)
+{
+}
+
 static inline void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev)
 {
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h
index 0537de86f981..9b0f44253f33 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h
@@ -28,7 +28,7 @@ DECLARE_EVENT_CLASS(mlx5_sf_dev_template,
 				   __entry->hw_fn_id = sfdev->fn_id;
 				   __entry->sfnum = sfdev->sfnum;
 		    ),
-		    TP_printk("(%s) sfdev=%pK aux_id=%d hw_id=0x%x sfnum=%u\n",
+		    TP_printk("(%s) sfdev=%p aux_id=%d hw_id=0x%x sfnum=%u\n",
 			      __get_str(devname), __entry->sfdev,
 			      __entry->aux_id, __entry->hw_fn_id,
 			      __entry->sfnum)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index a96be98be032..b82323b8449e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -31,9 +31,6 @@ struct mlx5_sf_table {
 	struct mlx5_core_dev *dev; /* To refer from notifier context. */
 	struct xarray function_ids; /* function id based lookup. */
 	struct mutex sf_state_lock; /* Serializes sf state among user cmds & vhca event handler. */
-	struct notifier_block esw_nb;
-	struct notifier_block vhca_nb;
-	struct notifier_block mdev_nb;
 };
 
 static struct mlx5_sf *
@@ -257,6 +254,7 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table,
 	return 0;
 
 esw_err:
+	mlx5_sf_function_id_erase(table, sf);
 	mlx5_sf_free(table, sf);
 	return err;
 }
@@ -284,7 +282,7 @@ mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_
 		NL_SET_ERR_MSG_MOD(extack, "External controller is unsupported");
 		return -EOPNOTSUPP;
 	}
-	if (new_attr->pfnum != mlx5_get_dev_index(dev)) {
+	if (new_attr->pfnum != PCI_FUNC(dev->pdev->devfn)) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid pfnum supplied");
 		return -EOPNOTSUPP;
 	}
@@ -390,11 +388,16 @@ static bool mlx5_sf_state_update_check(const struct mlx5_sf *sf, u8 new_state)
 
 static int mlx5_sf_vhca_event(struct notifier_block *nb, unsigned long opcode, void *data)
 {
-	struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, vhca_nb);
+	struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev,
+						 priv.sf_table_vhca_nb);
+	struct mlx5_sf_table *table = dev->priv.sf_table;
 	const struct mlx5_vhca_state_event *event = data;
 	bool update = false;
 	struct mlx5_sf *sf;
 
+	if (!table)
+		return 0;
+
 	mutex_lock(&table->sf_state_lock);
 	sf = mlx5_sf_lookup_by_function_id(table, event->function_id);
 	if (!sf)
@@ -406,7 +409,7 @@ static int mlx5_sf_vhca_event(struct notifier_block *nb, unsigned long opcode, v
 	update = mlx5_sf_state_update_check(sf, event->new_vhca_state);
 	if (update)
 		sf->hw_state = event->new_vhca_state;
-	trace_mlx5_sf_update_state(table->dev, sf->port_index, sf->controller,
+	trace_mlx5_sf_update_state(dev, sf->port_index, sf->controller,
 				   sf->hw_fn_id, sf->hw_state);
 unlock:
 	mutex_unlock(&table->sf_state_lock);
@@ -424,12 +427,16 @@ static void mlx5_sf_del_all(struct mlx5_sf_table *table)
 
 static int mlx5_sf_esw_event(struct notifier_block *nb, unsigned long event, void *data)
 {
-	struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, esw_nb);
+	struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev,
+						 priv.sf_table_esw_nb);
 	const struct mlx5_esw_event_info *mode = data;
 
+	if (!dev->priv.sf_table)
+		return 0;
+
 	switch (mode->new_mode) {
 	case MLX5_ESWITCH_LEGACY:
-		mlx5_sf_del_all(table);
+		mlx5_sf_del_all(dev->priv.sf_table);
 		break;
 	default:
 		break;
@@ -440,15 +447,16 @@ static int mlx5_sf_esw_event(struct notifier_block *nb, unsigned long event, voi
 
 static int mlx5_sf_mdev_event(struct notifier_block *nb, unsigned long event, void *data)
 {
-	struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, mdev_nb);
+	struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev,
+						 priv.sf_table_mdev_nb);
 	struct mlx5_sf_peer_devlink_event_ctx *event_ctx = data;
+	struct mlx5_sf_table *table = dev->priv.sf_table;
 	int ret = NOTIFY_DONE;
 	struct mlx5_sf *sf;
 
-	if (event != MLX5_DRIVER_EVENT_SF_PEER_DEVLINK)
+	if (!table || event != MLX5_DRIVER_EVENT_SF_PEER_DEVLINK)
 		return NOTIFY_DONE;
 
-
 	mutex_lock(&table->sf_state_lock);
 	sf = mlx5_sf_lookup_by_function_id(table, event_ctx->fn_id);
 	if (!sf)
@@ -463,10 +471,40 @@ out:
 	return ret;
 }
 
+int mlx5_sf_notifiers_init(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	if (mlx5_core_is_sf(dev))
+		return 0;
+
+	dev->priv.sf_table_esw_nb.notifier_call = mlx5_sf_esw_event;
+	err = mlx5_esw_event_notifier_register(dev, &dev->priv.sf_table_esw_nb);
+	if (err)
+		return err;
+
+	dev->priv.sf_table_vhca_nb.notifier_call = mlx5_sf_vhca_event;
+	err = mlx5_vhca_event_notifier_register(dev,
+						&dev->priv.sf_table_vhca_nb);
+	if (err)
+		goto vhca_err;
+
+	dev->priv.sf_table_mdev_nb.notifier_call = mlx5_sf_mdev_event;
+	err = mlx5_blocking_notifier_register(dev, &dev->priv.sf_table_mdev_nb);
+	if (err)
+		goto mdev_err;
+
+	return 0;
+mdev_err:
+	mlx5_vhca_event_notifier_unregister(dev, &dev->priv.sf_table_vhca_nb);
+vhca_err:
+	mlx5_esw_event_notifier_unregister(dev, &dev->priv.sf_table_esw_nb);
+	return err;
+}
+
 int mlx5_sf_table_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_sf_table *table;
-	int err;
 
 	if (!mlx5_sf_table_supported(dev) || !mlx5_vhca_event_supported(dev))
 		return 0;
@@ -479,28 +517,18 @@ int mlx5_sf_table_init(struct mlx5_core_dev *dev)
 	table->dev = dev;
 	xa_init(&table->function_ids);
 	dev->priv.sf_table = table;
-	table->esw_nb.notifier_call = mlx5_sf_esw_event;
-	err = mlx5_esw_event_notifier_register(dev->priv.eswitch, &table->esw_nb);
-	if (err)
-		goto reg_err;
-
-	table->vhca_nb.notifier_call = mlx5_sf_vhca_event;
-	err = mlx5_vhca_event_notifier_register(table->dev, &table->vhca_nb);
-	if (err)
-		goto vhca_err;
-
-	table->mdev_nb.notifier_call = mlx5_sf_mdev_event;
-	mlx5_blocking_notifier_register(dev, &table->mdev_nb);
 
 	return 0;
+}
 
-vhca_err:
-	mlx5_esw_event_notifier_unregister(dev->priv.eswitch, &table->esw_nb);
-reg_err:
-	mutex_destroy(&table->sf_state_lock);
-	kfree(table);
-	dev->priv.sf_table = NULL;
-	return err;
+void mlx5_sf_notifiers_cleanup(struct mlx5_core_dev *dev)
+{
+	if (mlx5_core_is_sf(dev))
+		return;
+
+	mlx5_blocking_notifier_unregister(dev, &dev->priv.sf_table_mdev_nb);
+	mlx5_vhca_event_notifier_unregister(dev, &dev->priv.sf_table_vhca_nb);
+	mlx5_esw_event_notifier_unregister(dev, &dev->priv.sf_table_esw_nb);
 }
 
 void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
@@ -510,10 +538,17 @@ void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
 	if (!table)
 		return;
 
-	mlx5_blocking_notifier_unregister(dev, &table->mdev_nb);
-	mlx5_vhca_event_notifier_unregister(table->dev, &table->vhca_nb);
-	mlx5_esw_event_notifier_unregister(dev->priv.eswitch, &table->esw_nb);
 	mutex_destroy(&table->sf_state_lock);
 	WARN_ON(!xa_empty(&table->function_ids));
 	kfree(table);
 }
+
+bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_table *table = dev->priv.sf_table;
+
+	if (!table)
+		return true;
+
+	return xa_empty(&table->function_ids);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
index 1f613320fe07..bd968f3b3855 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
@@ -30,9 +30,7 @@ enum mlx5_sf_hwc_index {
 };
 
 struct mlx5_sf_hw_table {
-	struct mlx5_core_dev *dev;
 	struct mutex table_lock; /* Serializes sf deletion and vhca state change handler. */
-	struct notifier_block vhca_nb;
 	struct mlx5_sf_hwc_table hwc[MLX5_SF_HWC_MAX];
 };
 
@@ -71,14 +69,16 @@ mlx5_sf_table_fn_to_hwc(struct mlx5_sf_hw_table *table, u16 fn_id)
 	return NULL;
 }
 
-static int mlx5_sf_hw_table_id_alloc(struct mlx5_sf_hw_table *table, u32 controller,
+static int mlx5_sf_hw_table_id_alloc(struct mlx5_core_dev *dev,
+				     struct mlx5_sf_hw_table *table,
+				     u32 controller,
 				     u32 usr_sfnum)
 {
 	struct mlx5_sf_hwc_table *hwc;
 	int free_idx = -1;
 	int i;
 
-	hwc = mlx5_sf_controller_to_hwc(table->dev, controller);
+	hwc = mlx5_sf_controller_to_hwc(dev, controller);
 	if (!hwc->sfs)
 		return -ENOSPC;
 
@@ -100,11 +100,13 @@ static int mlx5_sf_hw_table_id_alloc(struct mlx5_sf_hw_table *table, u32 control
 	return free_idx;
 }
 
-static void mlx5_sf_hw_table_id_free(struct mlx5_sf_hw_table *table, u32 controller, int id)
+static void mlx5_sf_hw_table_id_free(struct mlx5_core_dev *dev,
+				     struct mlx5_sf_hw_table *table,
+				     u32 controller, int id)
 {
 	struct mlx5_sf_hwc_table *hwc;
 
-	hwc = mlx5_sf_controller_to_hwc(table->dev, controller);
+	hwc = mlx5_sf_controller_to_hwc(dev, controller);
 	hwc->sfs[id].allocated = false;
 	hwc->sfs[id].pending_delete = false;
 }
@@ -120,7 +122,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 controller, u32 usr
 		return -EOPNOTSUPP;
 
 	mutex_lock(&table->table_lock);
-	sw_id = mlx5_sf_hw_table_id_alloc(table, controller, usr_sfnum);
+	sw_id = mlx5_sf_hw_table_id_alloc(dev, table, controller, usr_sfnum);
 	if (sw_id < 0) {
 		err = sw_id;
 		goto exist_err;
@@ -151,7 +153,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 controller, u32 usr
 vhca_err:
 	mlx5_cmd_dealloc_sf(dev, hw_fn_id);
 err:
-	mlx5_sf_hw_table_id_free(table, controller, sw_id);
+	mlx5_sf_hw_table_id_free(dev, table, controller, sw_id);
 exist_err:
 	mutex_unlock(&table->table_lock);
 	return err;
@@ -165,7 +167,7 @@ void mlx5_sf_hw_table_sf_free(struct mlx5_core_dev *dev, u32 controller, u16 id)
 	mutex_lock(&table->table_lock);
 	hw_fn_id = mlx5_sf_sw_to_hw_id(dev, controller, id);
 	mlx5_cmd_dealloc_sf(dev, hw_fn_id);
-	mlx5_sf_hw_table_id_free(table, controller, id);
+	mlx5_sf_hw_table_id_free(dev, table, controller, id);
 	mutex_unlock(&table->table_lock);
 }
 
@@ -216,10 +218,12 @@ static void mlx5_sf_hw_table_hwc_dealloc_all(struct mlx5_core_dev *dev,
 	}
 }
 
-static void mlx5_sf_hw_table_dealloc_all(struct mlx5_sf_hw_table *table)
+static void mlx5_sf_hw_table_dealloc_all(struct mlx5_core_dev *dev,
+					 struct mlx5_sf_hw_table *table)
 {
-	mlx5_sf_hw_table_hwc_dealloc_all(table->dev, &table->hwc[MLX5_SF_HWC_EXTERNAL]);
-	mlx5_sf_hw_table_hwc_dealloc_all(table->dev, &table->hwc[MLX5_SF_HWC_LOCAL]);
+	mlx5_sf_hw_table_hwc_dealloc_all(dev,
+					 &table->hwc[MLX5_SF_HWC_EXTERNAL]);
+	mlx5_sf_hw_table_hwc_dealloc_all(dev, &table->hwc[MLX5_SF_HWC_LOCAL]);
 }
 
 static int mlx5_sf_hw_table_hwc_init(struct mlx5_sf_hwc_table *hwc, u16 max_fn, u16 base_id)
@@ -301,7 +305,6 @@ int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev)
 	}
 
 	mutex_init(&table->table_lock);
-	table->dev = dev;
 	dev->priv.sf_hw_table = table;
 
 	base_id = mlx5_sf_start_function_id(dev);
@@ -338,19 +341,22 @@ void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev)
 	mlx5_sf_hw_table_hwc_cleanup(&table->hwc[MLX5_SF_HWC_LOCAL]);
 	mutex_destroy(&table->table_lock);
 	kfree(table);
+	dev->priv.sf_hw_table = NULL;
 res_unregister:
 	mlx5_sf_hw_table_res_unregister(dev);
 }
 
 static int mlx5_sf_hw_vhca_event(struct notifier_block *nb, unsigned long opcode, void *data)
 {
-	struct mlx5_sf_hw_table *table = container_of(nb, struct mlx5_sf_hw_table, vhca_nb);
+	struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev,
+						 priv.sf_hw_table_vhca_nb);
+	struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
 	const struct mlx5_vhca_state_event *event = data;
 	struct mlx5_sf_hwc_table *hwc;
 	struct mlx5_sf_hw *sf_hw;
 	u16 sw_id;
 
-	if (event->new_vhca_state != MLX5_VHCA_STATE_ALLOCATED)
+	if (!table || event->new_vhca_state != MLX5_VHCA_STATE_ALLOCATED)
 		return 0;
 
 	hwc = mlx5_sf_table_fn_to_hwc(table, event->function_id);
@@ -365,20 +371,28 @@ static int mlx5_sf_hw_vhca_event(struct notifier_block *nb, unsigned long opcode
 	 * Hence recycle the sf hardware id for reuse.
 	 */
 	if (sf_hw->allocated && sf_hw->pending_delete)
-		mlx5_sf_hw_table_hwc_sf_free(table->dev, hwc, sw_id);
+		mlx5_sf_hw_table_hwc_sf_free(dev, hwc, sw_id);
 	mutex_unlock(&table->table_lock);
 	return 0;
 }
 
-int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev)
+int mlx5_sf_hw_notifier_init(struct mlx5_core_dev *dev)
 {
-	struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
-
-	if (!table)
+	if (mlx5_core_is_sf(dev))
 		return 0;
 
-	table->vhca_nb.notifier_call = mlx5_sf_hw_vhca_event;
-	return mlx5_vhca_event_notifier_register(dev, &table->vhca_nb);
+	dev->priv.sf_hw_table_vhca_nb.notifier_call = mlx5_sf_hw_vhca_event;
+	return mlx5_vhca_event_notifier_register(dev,
+						 &dev->priv.sf_hw_table_vhca_nb);
+}
+
+void mlx5_sf_hw_notifier_cleanup(struct mlx5_core_dev *dev)
+{
+	if (mlx5_core_is_sf(dev))
+		return;
+
+	mlx5_vhca_event_notifier_unregister(dev,
+					    &dev->priv.sf_hw_table_vhca_nb);
 }
 
 void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev)
@@ -388,9 +402,8 @@ void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev)
 	if (!table)
 		return;
 
-	mlx5_vhca_event_notifier_unregister(dev, &table->vhca_nb);
 	/* Dealloc SFs whose firmware event has been missed. */
-	mlx5_sf_hw_table_dealloc_all(table);
+	mlx5_sf_hw_table_dealloc_all(dev, table);
 }
 
 bool mlx5_sf_hw_table_supported(const struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
index 860f9ddb7107..d8a934a0e968 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
@@ -12,11 +12,15 @@
 int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev);
 void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev);
 
-int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev);
+int mlx5_sf_hw_notifier_init(struct mlx5_core_dev *dev);
+void mlx5_sf_hw_notifier_cleanup(struct mlx5_core_dev *dev);
 void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev);
 
+int mlx5_sf_notifiers_init(struct mlx5_core_dev *dev);
 int mlx5_sf_table_init(struct mlx5_core_dev *dev);
+void mlx5_sf_notifiers_cleanup(struct mlx5_core_dev *dev);
 void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev);
+bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev);
 
 int mlx5_devlink_sf_port_new(struct devlink *devlink,
 			     const struct devlink_port_new_attrs *add_attr,
@@ -43,24 +47,42 @@ static inline void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev)
 {
 }
 
-static inline int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev)
+static inline int mlx5_sf_hw_notifier_init(struct mlx5_core_dev *dev)
 {
 	return 0;
 }
 
+static inline void mlx5_sf_hw_notifier_cleanup(struct mlx5_core_dev *dev)
+{
+}
+
 static inline void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev)
 {
 }
 
+static inline int mlx5_sf_notifiers_init(struct mlx5_core_dev *dev)
+{
+	return 0;
+}
+
 static inline int mlx5_sf_table_init(struct mlx5_core_dev *dev)
 {
 	return 0;
 }
 
+static inline void mlx5_sf_notifiers_cleanup(struct mlx5_core_dev *dev)
+{
+}
+
 static inline void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
 {
 }
 
+static inline bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev)
+{
+	return true;
+}
+
 #endif
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
index cda01ba441ae..b04cf6cf8956 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
@@ -9,15 +9,9 @@
 #define CREATE_TRACE_POINTS
 #include "diag/vhca_tracepoint.h"
 
-struct mlx5_vhca_state_notifier {
-	struct mlx5_core_dev *dev;
-	struct mlx5_nb nb;
-	struct blocking_notifier_head n_head;
-};
-
 struct mlx5_vhca_event_work {
 	struct work_struct work;
-	struct mlx5_vhca_state_notifier *notifier;
+	struct mlx5_core_dev *dev;
 	struct mlx5_vhca_state_event event;
 };
 
@@ -95,16 +89,14 @@ mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event *
 	mlx5_vhca_event_arm(dev, event->function_id);
 	trace_mlx5_sf_vhca_event(dev, event);
 
-	blocking_notifier_call_chain(&dev->priv.vhca_state_notifier->n_head, 0, event);
+	blocking_notifier_call_chain(&dev->priv.vhca_state_n_head, 0, event);
 }
 
 static void mlx5_vhca_state_work_handler(struct work_struct *_work)
 {
 	struct mlx5_vhca_event_work *work = container_of(_work, struct mlx5_vhca_event_work, work);
-	struct mlx5_vhca_state_notifier *notifier = work->notifier;
-	struct mlx5_core_dev *dev = notifier->dev;
 
-	mlx5_vhca_event_notify(dev, &work->event);
+	mlx5_vhca_event_notify(work->dev, &work->event);
 	kfree(work);
 }
 
@@ -116,8 +108,8 @@ void mlx5_vhca_events_work_enqueue(struct mlx5_core_dev *dev, int idx, struct wo
 static int
 mlx5_vhca_state_change_notifier(struct notifier_block *nb, unsigned long type, void *data)
 {
-	struct mlx5_vhca_state_notifier *notifier =
-				mlx5_nb_cof(nb, struct mlx5_vhca_state_notifier, nb);
+	struct mlx5_core_dev *dev = mlx5_nb_cof(nb, struct mlx5_core_dev,
+						priv.vhca_state_nb);
 	struct mlx5_vhca_event_work *work;
 	struct mlx5_eqe *eqe = data;
 	int wq_idx;
@@ -126,10 +118,10 @@ mlx5_vhca_state_change_notifier(struct notifier_block *nb, unsigned long type, v
 	if (!work)
 		return NOTIFY_DONE;
 	INIT_WORK(&work->work, &mlx5_vhca_state_work_handler);
-	work->notifier = notifier;
+	work->dev = dev;
 	work->event.function_id = be16_to_cpu(eqe->data.vhca_state.function_id);
 	wq_idx = work->event.function_id % MLX5_DEV_MAX_WQS;
-	mlx5_vhca_events_work_enqueue(notifier->dev, wq_idx, &work->work);
+	mlx5_vhca_events_work_enqueue(dev, wq_idx, &work->work);
 	return NOTIFY_OK;
 }
 
@@ -145,9 +137,15 @@ void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap)
 	MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_teardown_request, 1);
 }
 
+void mlx5_vhca_state_notifier_init(struct mlx5_core_dev *dev)
+{
+	BLOCKING_INIT_NOTIFIER_HEAD(&dev->priv.vhca_state_n_head);
+	MLX5_NB_INIT(&dev->priv.vhca_state_nb, mlx5_vhca_state_change_notifier,
+		     VHCA_STATE_CHANGE);
+}
+
 int mlx5_vhca_event_init(struct mlx5_core_dev *dev)
 {
-	struct mlx5_vhca_state_notifier *notifier;
 	char wq_name[MLX5_CMD_WQ_MAX_NAME];
 	struct mlx5_vhca_events *events;
 	int err, i;
@@ -160,7 +158,6 @@ int mlx5_vhca_event_init(struct mlx5_core_dev *dev)
 		return -ENOMEM;
 
 	events->dev = dev;
-	dev->priv.vhca_events = events;
 	for (i = 0; i < MLX5_DEV_MAX_WQS; i++) {
 		snprintf(wq_name, MLX5_CMD_WQ_MAX_NAME, "mlx5_vhca_event%d", i);
 		events->handler[i].wq = create_singlethread_workqueue(wq_name);
@@ -169,20 +166,10 @@ int mlx5_vhca_event_init(struct mlx5_core_dev *dev)
 			goto err_create_wq;
 		}
 	}
+	dev->priv.vhca_events = events;
 
-	notifier = kzalloc(sizeof(*notifier), GFP_KERNEL);
-	if (!notifier) {
-		err = -ENOMEM;
-		goto err_notifier;
-	}
-
-	dev->priv.vhca_state_notifier = notifier;
-	notifier->dev = dev;
-	BLOCKING_INIT_NOTIFIER_HEAD(&notifier->n_head);
-	MLX5_NB_INIT(&notifier->nb, mlx5_vhca_state_change_notifier, VHCA_STATE_CHANGE);
 	return 0;
 
-err_notifier:
 err_create_wq:
 	for (--i; i >= 0; i--)
 		destroy_workqueue(events->handler[i].wq);
@@ -211,8 +198,6 @@ void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev)
 	if (!mlx5_vhca_event_supported(dev))
 		return;
 
-	kfree(dev->priv.vhca_state_notifier);
-	dev->priv.vhca_state_notifier = NULL;
 	vhca_events = dev->priv.vhca_events;
 	for (i = 0; i < MLX5_DEV_MAX_WQS; i++)
 		destroy_workqueue(vhca_events->handler[i].wq);
@@ -221,34 +206,30 @@ void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev)
 
 void mlx5_vhca_event_start(struct mlx5_core_dev *dev)
 {
-	struct mlx5_vhca_state_notifier *notifier;
-
-	if (!dev->priv.vhca_state_notifier)
+	if (!mlx5_vhca_event_supported(dev))
 		return;
 
-	notifier = dev->priv.vhca_state_notifier;
-	mlx5_eq_notifier_register(dev, &notifier->nb);
+	mlx5_eq_notifier_register(dev, &dev->priv.vhca_state_nb);
 }
 
 void mlx5_vhca_event_stop(struct mlx5_core_dev *dev)
 {
-	struct mlx5_vhca_state_notifier *notifier;
-
-	if (!dev->priv.vhca_state_notifier)
+	if (!mlx5_vhca_event_supported(dev))
 		return;
 
-	notifier = dev->priv.vhca_state_notifier;
-	mlx5_eq_notifier_unregister(dev, &notifier->nb);
+	mlx5_eq_notifier_unregister(dev, &dev->priv.vhca_state_nb);
+
+	/* Flush workqueues of all pending events. */
+	mlx5_vhca_event_work_queues_flush(dev);
 }
 
 int mlx5_vhca_event_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb)
 {
-	if (!dev->priv.vhca_state_notifier)
-		return -EOPNOTSUPP;
-	return blocking_notifier_chain_register(&dev->priv.vhca_state_notifier->n_head, nb);
+	return blocking_notifier_chain_register(&dev->priv.vhca_state_n_head,
+						nb);
 }
 
 void mlx5_vhca_event_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb)
 {
-	blocking_notifier_chain_unregister(&dev->priv.vhca_state_notifier->n_head, nb);
+	blocking_notifier_chain_unregister(&dev->priv.vhca_state_n_head, nb);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h
index 1725ba64f8af..52790423874c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h
@@ -18,6 +18,7 @@ static inline bool mlx5_vhca_event_supported(const struct mlx5_core_dev *dev)
 }
 
 void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap);
+void mlx5_vhca_state_notifier_init(struct mlx5_core_dev *dev);
 int mlx5_vhca_event_init(struct mlx5_core_dev *dev);
 void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev);
 void mlx5_vhca_event_start(struct mlx5_core_dev *dev);
@@ -37,6 +38,10 @@ static inline void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *s
 {
 }
 
+static inline void mlx5_vhca_state_notifier_init(struct mlx5_core_dev *dev)
+{
+}
+
 static inline int mlx5_vhca_event_init(struct mlx5_core_dev *dev)
 {
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
index a897cdc60fdb..fe56b59e24c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
@@ -11,31 +11,29 @@
 /* This is the longest supported action sequence for FDB table:
  * DECAP, POP_VLAN, MODIFY, CTR, ASO, PUSH_VLAN, MODIFY, ENCAP, Term.
  */
-static const u32 action_order_arr[MLX5HWS_TABLE_TYPE_MAX][MLX5HWS_ACTION_TYP_MAX] = {
-	[MLX5HWS_TABLE_TYPE_FDB] = {
-		BIT(MLX5HWS_ACTION_TYP_REMOVE_HEADER) |
-		BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2) |
-		BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2),
-		BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
-		BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
-		BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
-		BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
-		BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
-		BIT(MLX5HWS_ACTION_TYP_INSERT_HEADER) |
-		BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2) |
-		BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3),
-		BIT(MLX5HWS_ACTION_TYP_CTR),
-		BIT(MLX5HWS_ACTION_TYP_TAG),
-		BIT(MLX5HWS_ACTION_TYP_ASO_METER),
-		BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
-		BIT(MLX5HWS_ACTION_TYP_TBL) |
-		BIT(MLX5HWS_ACTION_TYP_VPORT) |
-		BIT(MLX5HWS_ACTION_TYP_DROP) |
-		BIT(MLX5HWS_ACTION_TYP_SAMPLER) |
-		BIT(MLX5HWS_ACTION_TYP_RANGE) |
-		BIT(MLX5HWS_ACTION_TYP_DEST_ARRAY),
-		BIT(MLX5HWS_ACTION_TYP_LAST),
-	},
+static const u32 action_order_arr[MLX5HWS_ACTION_TYP_MAX] = {
+	BIT(MLX5HWS_ACTION_TYP_REMOVE_HEADER) |
+	BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2) |
+	BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2),
+	BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
+	BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
+	BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
+	BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
+	BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
+	BIT(MLX5HWS_ACTION_TYP_INSERT_HEADER) |
+	BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2) |
+	BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3),
+	BIT(MLX5HWS_ACTION_TYP_CTR),
+	BIT(MLX5HWS_ACTION_TYP_TAG),
+	BIT(MLX5HWS_ACTION_TYP_ASO_METER),
+	BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
+	BIT(MLX5HWS_ACTION_TYP_TBL) |
+	BIT(MLX5HWS_ACTION_TYP_VPORT) |
+	BIT(MLX5HWS_ACTION_TYP_DROP) |
+	BIT(MLX5HWS_ACTION_TYP_SAMPLER) |
+	BIT(MLX5HWS_ACTION_TYP_RANGE) |
+	BIT(MLX5HWS_ACTION_TYP_DEST_ARRAY),
+	BIT(MLX5HWS_ACTION_TYP_LAST),
 };
 
 static const char * const mlx5hws_action_type_str[] = {
@@ -74,6 +72,11 @@ enum mlx5hws_action_type mlx5hws_action_get_type(struct mlx5hws_action *action)
 	return action->type;
 }
 
+struct mlx5_core_dev *mlx5hws_action_get_dev(struct mlx5hws_action *action)
+{
+	return action->ctx->mdev;
+}
+
 static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
 					 enum mlx5hws_context_shared_stc_type stc_type,
 					 u8 tbl_type)
@@ -83,8 +86,8 @@ static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
 	int ret;
 
 	mutex_lock(&ctx->ctrl_lock);
-	if (ctx->common_res[tbl_type].shared_stc[stc_type]) {
-		ctx->common_res[tbl_type].shared_stc[stc_type]->refcount++;
+	if (ctx->common_res.shared_stc[stc_type]) {
+		ctx->common_res.shared_stc[stc_type]->refcount++;
 		mutex_unlock(&ctx->ctrl_lock);
 		return 0;
 	}
@@ -114,7 +117,7 @@ static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
 		mlx5hws_err(ctx, "No such stc_type: %d\n", stc_type);
 		pr_warn("HWS: Invalid stc_type: %d\n", stc_type);
 		ret = -EINVAL;
-		goto unlock_and_out;
+		goto free_shared_stc;
 	}
 
 	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl_type,
@@ -124,8 +127,8 @@ static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
 		goto free_shared_stc;
 	}
 
-	ctx->common_res[tbl_type].shared_stc[stc_type] = shared_stc;
-	ctx->common_res[tbl_type].shared_stc[stc_type]->refcount = 1;
+	ctx->common_res.shared_stc[stc_type] = shared_stc;
+	ctx->common_res.shared_stc[stc_type]->refcount = 1;
 
 	mutex_unlock(&ctx->ctrl_lock);
 
@@ -178,16 +181,16 @@ static void hws_action_put_shared_stc(struct mlx5hws_action *action,
 	}
 
 	mutex_lock(&ctx->ctrl_lock);
-	if (--ctx->common_res[tbl_type].shared_stc[stc_type]->refcount) {
+	if (--ctx->common_res.shared_stc[stc_type]->refcount) {
 		mutex_unlock(&ctx->ctrl_lock);
 		return;
 	}
 
-	shared_stc = ctx->common_res[tbl_type].shared_stc[stc_type];
+	shared_stc = ctx->common_res.shared_stc[stc_type];
 
 	mlx5hws_action_free_single_stc(ctx, tbl_type, &shared_stc->stc_chunk);
 	kfree(shared_stc);
-	ctx->common_res[tbl_type].shared_stc[stc_type] = NULL;
+	ctx->common_res.shared_stc[stc_type] = NULL;
 	mutex_unlock(&ctx->ctrl_lock);
 }
 
@@ -206,10 +209,10 @@ bool mlx5hws_action_check_combo(struct mlx5hws_context *ctx,
 				enum mlx5hws_action_type *user_actions,
 				enum mlx5hws_table_type table_type)
 {
-	const u32 *order_arr = action_order_arr[table_type];
+	const u32 *order_arr = action_order_arr;
+	bool valid_combo;
 	u8 order_idx = 0;
 	u8 user_idx = 0;
-	bool valid_combo;
 
 	if (table_type >= MLX5HWS_TABLE_TYPE_MAX) {
 		mlx5hws_err(ctx, "Invalid table_type %d", table_type);
@@ -240,6 +243,7 @@ hws_action_fixup_stc_attr(struct mlx5hws_context *ctx,
 			  enum mlx5hws_table_type table_type,
 			  bool is_mirror)
 {
+	struct mlx5hws_pool *pool;
 	bool use_fixup = false;
 	u32 fw_tbl_type;
 	u32 base_id;
@@ -255,13 +259,11 @@ hws_action_fixup_stc_attr(struct mlx5hws_context *ctx,
 			use_fixup = true;
 			break;
 		}
+		pool = stc_attr->ste_table.ste_pool;
 		if (!is_mirror)
-			base_id = mlx5hws_pool_chunk_get_base_id(stc_attr->ste_table.ste_pool,
-								 &stc_attr->ste_table.ste);
+			base_id = mlx5hws_pool_get_base_id(pool);
 		else
-			base_id =
-				mlx5hws_pool_chunk_get_base_mirror_id(stc_attr->ste_table.ste_pool,
-								      &stc_attr->ste_table.ste);
+			base_id = mlx5hws_pool_get_base_mirror_id(pool);
 
 		*fixup_stc_attr = *stc_attr;
 		fixup_stc_attr->ste_table.ste_obj_id = base_id;
@@ -321,8 +323,8 @@ int mlx5hws_action_alloc_single_stc(struct mlx5hws_context *ctx,
 __must_hold(&ctx->ctrl_lock)
 {
 	struct mlx5hws_cmd_stc_modify_attr cleanup_stc_attr = {0};
-	struct mlx5hws_pool *stc_pool = ctx->stc_pool[table_type];
 	struct mlx5hws_cmd_stc_modify_attr fixup_stc_attr = {0};
+	struct mlx5hws_pool *stc_pool = ctx->stc_pool;
 	bool use_fixup;
 	u32 obj_0_id;
 	int ret;
@@ -339,7 +341,7 @@ __must_hold(&ctx->ctrl_lock)
 	if (!mlx5hws_context_cap_dynamic_reparse(ctx))
 		stc_attr->reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
 
-	obj_0_id = mlx5hws_pool_chunk_get_base_id(stc_pool, stc);
+	obj_0_id = mlx5hws_pool_get_base_id(stc_pool);
 
 	/* According to table/action limitation change the stc_attr */
 	use_fixup = hws_action_fixup_stc_attr(ctx, stc_attr, &fixup_stc_attr, table_type, false);
@@ -355,7 +357,7 @@ __must_hold(&ctx->ctrl_lock)
 	if (table_type == MLX5HWS_TABLE_TYPE_FDB) {
 		u32 obj_1_id;
 
-		obj_1_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, stc);
+		obj_1_id = mlx5hws_pool_get_base_mirror_id(stc_pool);
 
 		use_fixup = hws_action_fixup_stc_attr(ctx, stc_attr,
 						      &fixup_stc_attr,
@@ -387,19 +389,19 @@ void mlx5hws_action_free_single_stc(struct mlx5hws_context *ctx,
 				    struct mlx5hws_pool_chunk *stc)
 __must_hold(&ctx->ctrl_lock)
 {
-	struct mlx5hws_pool *stc_pool = ctx->stc_pool[table_type];
 	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
+	struct mlx5hws_pool *stc_pool = ctx->stc_pool;
 	u32 obj_id;
 
 	/* Modify the STC not to point to an object */
 	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_DROP;
 	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
 	stc_attr.stc_offset = stc->offset;
-	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, stc);
+	obj_id = mlx5hws_pool_get_base_id(stc_pool);
 	mlx5hws_cmd_stc_modify(ctx->mdev, obj_id, &stc_attr);
 
 	if (table_type == MLX5HWS_TABLE_TYPE_FDB) {
-		obj_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, stc);
+		obj_id = mlx5hws_pool_get_base_mirror_id(stc_pool);
 		mlx5hws_cmd_stc_modify(ctx->mdev, obj_id, &stc_attr);
 	}
 
@@ -473,6 +475,7 @@ static void hws_action_fill_stc_attr(struct mlx5hws_action *action,
 		break;
 	case MLX5HWS_ACTION_TYP_TBL:
 	case MLX5HWS_ACTION_TYP_DEST_ARRAY:
+	case MLX5HWS_ACTION_TYP_SAMPLER:
 		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_FT;
 		attr->action_offset = MLX5HWS_ACTION_OFFSET_HIT;
 		attr->dest_table_id = obj_id;
@@ -561,7 +564,7 @@ hws_action_create_stcs(struct mlx5hws_action *action, u32 obj_id)
 	if (action->flags & MLX5HWS_ACTION_FLAG_HWS_FDB) {
 		ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr,
 						      MLX5HWS_TABLE_TYPE_FDB,
-						      &action->stc[MLX5HWS_TABLE_TYPE_FDB]);
+						      &action->stc);
 		if (ret)
 			goto out_err;
 	}
@@ -585,7 +588,7 @@ hws_action_destroy_stcs(struct mlx5hws_action *action)
 
 	if (action->flags & MLX5HWS_ACTION_FLAG_HWS_FDB)
 		mlx5hws_action_free_single_stc(ctx, MLX5HWS_TABLE_TYPE_FDB,
-					       &action->stc[MLX5HWS_TABLE_TYPE_FDB]);
+					       &action->stc);
 
 	mutex_unlock(&ctx->ctrl_lock);
 }
@@ -1187,14 +1190,15 @@ hws_action_create_modify_header_hws(struct mlx5hws_action *action,
 				    struct mlx5hws_action_mh_pattern *pattern,
 				    u32 log_bulk_size)
 {
+	u16 num_actions, max_mh_actions = 0, hw_max_actions;
 	struct mlx5hws_context *ctx = action->ctx;
-	u16 num_actions, max_mh_actions = 0;
 	int i, ret, size_in_bytes;
 	u32 pat_id, arg_id = 0;
 	__be64 *new_pattern;
 	size_t pat_max_sz;
 
 	pat_max_sz = MLX5HWS_ARG_CHUNK_SIZE_MAX * MLX5HWS_ARG_DATA_SIZE;
+	hw_max_actions = pat_max_sz / MLX5HWS_MODIFY_ACTION_SIZE;
 	size_in_bytes = pat_max_sz * sizeof(__be64);
 	new_pattern = kcalloc(num_of_patterns, size_in_bytes, GFP_KERNEL);
 	if (!new_pattern)
@@ -1204,16 +1208,20 @@ hws_action_create_modify_header_hws(struct mlx5hws_action *action,
 	for (i = 0; i < num_of_patterns; i++) {
 		size_t new_num_actions;
 		size_t cur_num_actions;
-		u32 nope_location;
+		u32 nop_locations;
 
 		cur_num_actions = pattern[i].sz / MLX5HWS_MODIFY_ACTION_SIZE;
 
-		mlx5hws_pat_calc_nope(pattern[i].data, cur_num_actions,
-				      pat_max_sz / MLX5HWS_MODIFY_ACTION_SIZE,
-				      &new_num_actions, &nope_location,
-				      &new_pattern[i * pat_max_sz]);
+		ret = mlx5hws_pat_calc_nop(pattern[i].data, cur_num_actions,
+					   hw_max_actions, &new_num_actions,
+					   &nop_locations,
+					   &new_pattern[i * pat_max_sz]);
+		if (ret) {
+			mlx5hws_err(ctx, "Too many actions after nop insertion\n");
+			goto free_new_pat;
+		}
 
-		action[i].modify_header.nope_locations = nope_location;
+		action[i].modify_header.nop_locations = nop_locations;
 		action[i].modify_header.num_of_actions = new_num_actions;
 
 		max_mh_actions = max(max_mh_actions, new_num_actions);
@@ -1260,7 +1268,7 @@ hws_action_create_modify_header_hws(struct mlx5hws_action *action,
 				MLX5_GET(set_action_in, pattern[i].data, action_type);
 		} else {
 			/* Multiple modify actions require a pattern */
-			if (unlikely(action[i].modify_header.nope_locations)) {
+			if (unlikely(action[i].modify_header.nop_locations)) {
 				size_t pattern_sz;
 
 				pattern_sz = action[i].modify_header.num_of_actions *
@@ -1350,11 +1358,8 @@ free_action:
 }
 
 struct mlx5hws_action *
-mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
-				 size_t num_dest,
+mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx, size_t num_dest,
 				 struct mlx5hws_action_dest_attr *dests,
-				 bool ignore_flow_level,
-				 u32 flow_source,
 				 u32 flags)
 {
 	struct mlx5hws_cmd_set_fte_dest *dest_list = NULL;
@@ -1362,8 +1367,8 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
 	struct mlx5hws_cmd_set_fte_attr fte_attr = {0};
 	struct mlx5hws_cmd_forward_tbl *fw_island;
 	struct mlx5hws_action *action;
-	u32 i /*, packet_reformat_id*/;
-	int ret;
+	int ret, last_dest_idx = -1;
+	u32 i;
 
 	if (num_dest <= 1) {
 		mlx5hws_err(ctx, "Action must have multiple dests\n");
@@ -1392,12 +1397,9 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
 				MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 			dest_list[i].destination_id = dests[i].dest->dest_obj.obj_id;
 			fte_attr.action_flags |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-			fte_attr.ignore_flow_level = ignore_flow_level;
-			/* ToDo: In SW steering we have a handling of 'go to WIRE'
-			 * destination here by upper layer setting 'is_wire_ft' flag
-			 * if the destination is wire.
-			 * This is because uplink should be last dest in the list.
-			 */
+			fte_attr.ignore_flow_level = 1;
+			if (dests[i].is_wire_ft)
+				last_dest_idx = i;
 			break;
 		case MLX5HWS_ACTION_TYP_VPORT:
 			dest_list[i].destination_type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
@@ -1421,6 +1423,9 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
 		}
 	}
 
+	if (last_dest_idx != -1)
+		swap(dest_list[last_dest_idx], dest_list[num_dest - 1]);
+
 	fte_attr.dests_num = num_dest;
 	fte_attr.dests = dest_list;
 
@@ -1576,17 +1581,15 @@ hws_action_create_dest_match_range_definer(struct mlx5hws_context *ctx)
 	return definer;
 }
 
-static struct mlx5hws_matcher_action_ste *
+static struct mlx5hws_range_action_table *
 hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 					 struct mlx5hws_definer *definer,
 					 u32 miss_ft_id)
 {
 	struct mlx5hws_cmd_rtc_create_attr rtc_attr = {0};
-	struct mlx5hws_action_default_stc *default_stc;
-	struct mlx5hws_matcher_action_ste *table_ste;
+	struct mlx5hws_range_action_table *table_ste;
 	struct mlx5hws_pool_attr pool_attr = {0};
 	struct mlx5hws_pool *ste_pool, *stc_pool;
-	struct mlx5hws_pool_chunk *ste;
 	u32 *rtc_0_id, *rtc_1_id;
 	u32 obj_id;
 	int ret;
@@ -1605,7 +1608,6 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 
 	pool_attr.table_type = MLX5HWS_TABLE_TYPE_FDB;
 	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
-	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL;
 	pool_attr.alloc_log_sz = 1;
 	table_ste->pool = mlx5hws_pool_create(ctx, &pool_attr);
 	if (!table_ste->pool) {
@@ -1617,8 +1619,6 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 	rtc_0_id = &table_ste->rtc_0_id;
 	rtc_1_id = &table_ste->rtc_1_id;
 	ste_pool = table_ste->pool;
-	ste = &table_ste->ste;
-	ste->order = 1;
 
 	rtc_attr.log_size = 0;
 	rtc_attr.log_depth = 0;
@@ -1630,18 +1630,16 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 	rtc_attr.fw_gen_wqe = true;
 	rtc_attr.is_scnd_range = true;
 
-	obj_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
+	obj_id = mlx5hws_pool_get_base_id(ste_pool);
 
 	rtc_attr.pd = ctx->pd_num;
 	rtc_attr.ste_base = obj_id;
-	rtc_attr.ste_offset = ste->offset;
 	rtc_attr.reparse_mode = mlx5hws_context_get_reparse_mode(ctx);
 	rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(MLX5HWS_TABLE_TYPE_FDB, false);
 
 	/* STC is a single resource (obj_id), use any STC for the ID */
-	stc_pool = ctx->stc_pool[MLX5HWS_TABLE_TYPE_FDB];
-	default_stc = ctx->common_res[MLX5HWS_TABLE_TYPE_FDB].default_stc;
-	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, &default_stc->default_hit);
+	stc_pool = ctx->stc_pool;
+	obj_id = mlx5hws_pool_get_base_id(stc_pool);
 	rtc_attr.stc_base = obj_id;
 
 	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_0_id);
@@ -1651,11 +1649,11 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 	}
 
 	/* Create mirror RTC */
-	obj_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
+	obj_id = mlx5hws_pool_get_base_mirror_id(ste_pool);
 	rtc_attr.ste_base = obj_id;
 	rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(MLX5HWS_TABLE_TYPE_FDB, true);
 
-	obj_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, &default_stc->default_hit);
+	obj_id = mlx5hws_pool_get_base_mirror_id(stc_pool);
 	rtc_attr.stc_base = obj_id;
 
 	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_1_id);
@@ -1678,9 +1676,9 @@ free_ste:
 	return NULL;
 }
 
-static void
-hws_action_destroy_dest_match_range_table(struct mlx5hws_context *ctx,
-					  struct mlx5hws_matcher_action_ste *table_ste)
+static void hws_action_destroy_dest_match_range_table(
+	struct mlx5hws_context *ctx,
+	struct mlx5hws_range_action_table *table_ste)
 {
 	mutex_lock(&ctx->ctrl_lock);
 
@@ -1692,12 +1690,11 @@ hws_action_destroy_dest_match_range_table(struct mlx5hws_context *ctx,
 	mutex_unlock(&ctx->ctrl_lock);
 }
 
-static int
-hws_action_create_dest_match_range_fill_table(struct mlx5hws_context *ctx,
-					      struct mlx5hws_matcher_action_ste *table_ste,
-					      struct mlx5hws_action *hit_ft_action,
-					      struct mlx5hws_definer *range_definer,
-					      u32 min, u32 max)
+static int hws_action_create_dest_match_range_fill_table(
+	struct mlx5hws_context *ctx,
+	struct mlx5hws_range_action_table *table_ste,
+	struct mlx5hws_action *hit_ft_action,
+	struct mlx5hws_definer *range_definer, u32 min, u32 max)
 {
 	struct mlx5hws_wqe_gta_data_seg_ste match_wqe_data = {0};
 	struct mlx5hws_wqe_gta_data_seg_ste range_wqe_data = {0};
@@ -1731,7 +1728,7 @@ hws_action_create_dest_match_range_fill_table(struct mlx5hws_context *ctx,
 	ste_attr.used_id_rtc_0 = &used_rtc_0_id;
 	ste_attr.used_id_rtc_1 = &used_rtc_1_id;
 
-	common_res = &ctx->common_res[MLX5HWS_TABLE_TYPE_FDB];
+	common_res = &ctx->common_res;
 
 	/* init an empty match STE which will always hit */
 	ste_attr.wqe_ctrl = &wqe_ctrl;
@@ -1750,7 +1747,7 @@ hws_action_create_dest_match_range_fill_table(struct mlx5hws_context *ctx,
 	wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_CTRL] |=
 		htonl(MLX5HWS_ACTION_STC_IDX_LAST_COMBO2 << 29);
 	wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_HIT] =
-		htonl(hit_ft_action->stc[MLX5HWS_TABLE_TYPE_FDB].offset);
+		htonl(hit_ft_action->stc.offset);
 
 	wqe_data_arr = (__force __be32 *)&range_wqe_data;
 
@@ -1793,7 +1790,7 @@ mlx5hws_action_create_dest_match_range(struct mlx5hws_context *ctx,
 				       u32 min, u32 max, u32 flags)
 {
 	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
-	struct mlx5hws_matcher_action_ste *table_ste;
+	struct mlx5hws_range_action_table *table_ste;
 	struct mlx5hws_action *hit_ft_action;
 	struct mlx5hws_definer *definer;
 	struct mlx5hws_action *action;
@@ -1838,12 +1835,11 @@ mlx5hws_action_create_dest_match_range(struct mlx5hws_context *ctx,
 	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
 	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE;
 	stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
-	stc_attr.ste_table.ste = table_ste->ste;
 	stc_attr.ste_table.ste_pool = table_ste->pool;
 	stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer;
 
 	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, MLX5HWS_TABLE_TYPE_FDB,
-					      &action->stc[MLX5HWS_TABLE_TYPE_FDB]);
+					      &action->stc);
 	if (ret)
 		goto error_unlock;
 
@@ -1875,7 +1871,50 @@ struct mlx5hws_action *
 mlx5hws_action_create_flow_sampler(struct mlx5hws_context *ctx,
 				   u32 sampler_id, u32 flags)
 {
-	mlx5hws_err(ctx, "Flow sampler action - unsupported\n");
+	struct mlx5hws_cmd_ft_create_attr ft_attr = {0};
+	struct mlx5hws_cmd_set_fte_attr fte_attr = {0};
+	struct mlx5hws_cmd_forward_tbl *fw_island;
+	struct mlx5hws_cmd_set_fte_dest dest;
+	struct mlx5hws_action *action;
+	int ret;
+
+	if (flags != (MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED)) {
+		mlx5hws_err(ctx, "Unsupported flags for flow sampler\n");
+		return NULL;
+	}
+
+	ft_attr.type = FS_FT_FDB;
+	ft_attr.level = ctx->caps->fdb_ft.max_level - 1;
+
+	dest.destination_type = MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER;
+	dest.destination_id = sampler_id;
+
+	fte_attr.dests_num = 1;
+	fte_attr.dests = &dest;
+	fte_attr.action_flags = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	fte_attr.ignore_flow_level = 1;
+
+	fw_island = mlx5hws_cmd_forward_tbl_create(ctx->mdev, &ft_attr, &fte_attr);
+	if (!fw_island)
+		return NULL;
+
+	action = hws_action_create_generic(ctx, flags,
+					   MLX5HWS_ACTION_TYP_SAMPLER);
+	if (!action)
+		goto destroy_fw_island;
+
+	ret = hws_action_create_stcs(action, fw_island->ft_id);
+	if (ret)
+		goto free_action;
+
+	action->flow_sampler.fw_island = fw_island;
+
+	return action;
+
+free_action:
+	kfree(action);
+destroy_fw_island:
+	mlx5hws_cmd_forward_tbl_destroy(ctx->mdev, fw_island);
 	return NULL;
 }
 
@@ -1914,6 +1953,11 @@ static void hws_action_destroy_hws(struct mlx5hws_action *action)
 		}
 		kfree(action->dest_array.dest_list);
 		break;
+	case MLX5HWS_ACTION_TYP_SAMPLER:
+		hws_action_destroy_stcs(action);
+		mlx5hws_cmd_forward_tbl_destroy(action->ctx->mdev,
+						action->flow_sampler.fw_island);
+		break;
 	case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2:
 	case MLX5HWS_ACTION_TYP_MODIFY_HDR:
 		shared_arg = false;
@@ -1970,8 +2014,8 @@ __must_hold(&ctx->ctrl_lock)
 	struct mlx5hws_action_default_stc *default_stc;
 	int ret;
 
-	if (ctx->common_res[tbl_type].default_stc) {
-		ctx->common_res[tbl_type].default_stc->refcount++;
+	if (ctx->common_res.default_stc) {
+		ctx->common_res.default_stc->refcount++;
 		return 0;
 	}
 
@@ -2023,8 +2067,8 @@ __must_hold(&ctx->ctrl_lock)
 		goto free_nop_dw7;
 	}
 
-	ctx->common_res[tbl_type].default_stc = default_stc;
-	ctx->common_res[tbl_type].default_stc->refcount++;
+	ctx->common_res.default_stc = default_stc;
+	ctx->common_res.default_stc->refcount++;
 
 	return 0;
 
@@ -2046,9 +2090,7 @@ __must_hold(&ctx->ctrl_lock)
 {
 	struct mlx5hws_action_default_stc *default_stc;
 
-	default_stc = ctx->common_res[tbl_type].default_stc;
-
-	default_stc = ctx->common_res[tbl_type].default_stc;
+	default_stc = ctx->common_res.default_stc;
 	if (--default_stc->refcount)
 		return;
 
@@ -2058,28 +2100,30 @@ __must_hold(&ctx->ctrl_lock)
 	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_dw5);
 	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_ctr);
 	kfree(default_stc);
-	ctx->common_res[tbl_type].default_stc = NULL;
+	ctx->common_res.default_stc = NULL;
 }
 
 static void hws_action_modify_write(struct mlx5hws_send_engine *queue,
 				    u32 arg_idx,
 				    u8 *arg_data,
 				    u16 num_of_actions,
-				    u32 nope_locations)
+				    u32 nop_locations)
 {
 	u8 *new_arg_data = NULL;
 	int i, j;
 
-	if (unlikely(nope_locations)) {
+	if (unlikely(nop_locations)) {
 		new_arg_data = kcalloc(num_of_actions,
 				       MLX5HWS_MODIFY_ACTION_SIZE, GFP_KERNEL);
 		if (unlikely(!new_arg_data))
 			return;
 
-		for (i = 0, j = 0; i < num_of_actions; i++, j++) {
-			memcpy(&new_arg_data[j], arg_data, MLX5HWS_MODIFY_ACTION_SIZE);
-			if (BIT(i) & nope_locations)
+		for (i = 0, j = 0; j < num_of_actions; i++, j++) {
+			if (BIT(i) & nop_locations)
 				j++;
+			memcpy(&new_arg_data[j * MLX5HWS_MODIFY_ACTION_SIZE],
+			       &arg_data[i * MLX5HWS_MODIFY_ACTION_SIZE],
+			       MLX5HWS_MODIFY_ACTION_SIZE);
 		}
 	}
 
@@ -2150,8 +2194,7 @@ hws_action_apply_stc(struct mlx5hws_actions_apply_data *apply,
 {
 	struct mlx5hws_action *action = apply->rule_action[action_idx].action;
 
-	apply->wqe_ctrl->stc_ix[stc_idx] =
-		htonl(action->stc[apply->tbl_type].offset);
+	apply->wqe_ctrl->stc_ix[stc_idx] = htonl(action->stc.offset);
 }
 
 static void
@@ -2176,12 +2219,13 @@ hws_action_setter_modify_header(struct mlx5hws_actions_apply_data *apply,
 	struct mlx5hws_action *action;
 	u32 arg_sz, arg_idx;
 	u8 *single_action;
+	u8 max_actions;
 	__be32 stc_idx;
 
 	rule_action = &apply->rule_action[setter->idx_double];
 	action = rule_action->action;
 
-	stc_idx = htonl(action->stc[apply->tbl_type].offset);
+	stc_idx = htonl(action->stc.offset);
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx;
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
 
@@ -2203,21 +2247,23 @@ hws_action_setter_modify_header(struct mlx5hws_actions_apply_data *apply,
 
 		apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] =
 			*(__be32 *)MLX5_ADDR_OF(set_action_in, single_action, data);
-	} else {
-		/* Argument offset multiple with number of args per these actions */
-		arg_sz = mlx5hws_arg_get_arg_size(action->modify_header.max_num_of_actions);
-		arg_idx = rule_action->modify_header.offset * arg_sz;
-
-		apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
-
-		if (!(action->flags & MLX5HWS_ACTION_FLAG_SHARED)) {
-			apply->require_dep = 1;
-			hws_action_modify_write(apply->queue,
-						action->modify_header.arg_id + arg_idx,
-						rule_action->modify_header.data,
-						action->modify_header.num_of_actions,
-						action->modify_header.nope_locations);
-		}
+		return;
+	}
+
+	/* Argument offset multiple with number of args per these actions */
+	max_actions = action->modify_header.max_num_of_actions;
+	arg_sz = mlx5hws_arg_get_arg_size(max_actions);
+	arg_idx = rule_action->modify_header.offset * arg_sz;
+
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
+
+	if (!(action->flags & MLX5HWS_ACTION_FLAG_SHARED)) {
+		apply->require_dep = 1;
+		hws_action_modify_write(apply->queue,
+					action->modify_header.arg_id + arg_idx,
+					rule_action->modify_header.data,
+					action->modify_header.num_of_actions,
+					action->modify_header.nop_locations);
 	}
 }
 
@@ -2240,7 +2286,7 @@ hws_action_setter_insert_ptr(struct mlx5hws_actions_apply_data *apply,
 	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0;
 	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
 
-	stc_idx = htonl(action->stc[apply->tbl_type].offset);
+	stc_idx = htonl(action->stc.offset);
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx;
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
 
@@ -2272,7 +2318,7 @@ hws_action_setter_tnl_l3_to_l2(struct mlx5hws_actions_apply_data *apply,
 	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0;
 	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
 
-	stc_idx = htonl(action->stc[apply->tbl_type].offset);
+	stc_idx = htonl(action->stc.offset);
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx;
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
 
@@ -2434,6 +2480,7 @@ int mlx5hws_action_template_process(struct mlx5hws_action_template *at)
 		case MLX5HWS_ACTION_TYP_DROP:
 		case MLX5HWS_ACTION_TYP_TBL:
 		case MLX5HWS_ACTION_TYP_DEST_ARRAY:
+		case MLX5HWS_ACTION_TYP_SAMPLER:
 		case MLX5HWS_ACTION_TYP_VPORT:
 		case MLX5HWS_ACTION_TYP_MISS:
 			/* Hit action */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h
index e8f562c31826..55a079fdd08f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h
@@ -70,12 +70,12 @@ struct mlx5hws_action_default_stc {
 	struct mlx5hws_pool_chunk nop_dw6;
 	struct mlx5hws_pool_chunk nop_dw7;
 	struct mlx5hws_pool_chunk default_hit;
-	u32 refcount;
+	u32 refcount; /* protected by context ctrl lock */
 };
 
 struct mlx5hws_action_shared_stc {
 	struct mlx5hws_pool_chunk stc_chunk;
-	u32 refcount;
+	u32 refcount; /* protected by context ctrl lock */
 };
 
 struct mlx5hws_actions_apply_data {
@@ -118,19 +118,25 @@ struct mlx5hws_action_template {
 	u8 only_term;
 };
 
+struct mlx5hws_range_action_table {
+	struct mlx5hws_pool *pool;
+	u32 rtc_0_id;
+	u32 rtc_1_id;
+};
+
 struct mlx5hws_action {
 	u8 type;
 	u8 flags;
 	struct mlx5hws_context *ctx;
 	union {
 		struct {
-			struct mlx5hws_pool_chunk stc[MLX5HWS_TABLE_TYPE_MAX];
+			struct mlx5hws_pool_chunk stc;
 			union {
 				struct {
 					u32 pat_id;
 					u32 arg_id;
 					__be64 single_action;
-					u32 nope_locations;
+					u32 nop_locations;
 					u8 num_of_patterns;
 					u8 single_action_type;
 					u8 num_of_actions;
@@ -166,6 +172,9 @@ struct mlx5hws_action {
 					struct mlx5hws_cmd_set_fte_dest *dest_list;
 				} dest_array;
 				struct {
+					struct mlx5hws_cmd_forward_tbl *fw_island;
+				} flow_sampler;
+				struct {
 					u8 type;
 					u8 start_anchor;
 					u8 end_anchor;
@@ -183,7 +192,7 @@ struct mlx5hws_action {
 					size_t size;
 				} remove_header;
 				struct {
-					struct mlx5hws_matcher_action_ste *table_ste;
+					struct mlx5hws_range_action_table *table_ste;
 					struct mlx5hws_action *hit_ft_action;
 					struct mlx5hws_definer *definer;
 				} range;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.c
new file mode 100644
index 000000000000..5766a9c82f96
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.c
@@ -0,0 +1,467 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#include "internal.h"
+
+static const char *
+hws_pool_opt_to_str(enum mlx5hws_pool_optimize opt)
+{
+	switch (opt) {
+	case MLX5HWS_POOL_OPTIMIZE_NONE:
+		return "rx-and-tx";
+	case MLX5HWS_POOL_OPTIMIZE_ORIG:
+		return "rx-only";
+	case MLX5HWS_POOL_OPTIMIZE_MIRROR:
+		return "tx-only";
+	default:
+		return "unknown";
+	}
+}
+
+static int
+hws_action_ste_table_create_pool(struct mlx5hws_context *ctx,
+				 struct mlx5hws_action_ste_table *action_tbl,
+				 enum mlx5hws_pool_optimize opt, size_t log_sz)
+{
+	struct mlx5hws_pool_attr pool_attr = { 0 };
+
+	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
+	pool_attr.table_type = MLX5HWS_TABLE_TYPE_FDB;
+	pool_attr.flags = MLX5HWS_POOL_FLAG_BUDDY;
+	pool_attr.opt_type = opt;
+	pool_attr.alloc_log_sz = log_sz;
+
+	action_tbl->pool = mlx5hws_pool_create(ctx, &pool_attr);
+	if (!action_tbl->pool) {
+		mlx5hws_err(ctx, "Failed to allocate STE pool\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hws_action_ste_table_create_single_rtc(
+	struct mlx5hws_context *ctx,
+	struct mlx5hws_action_ste_table *action_tbl,
+	enum mlx5hws_pool_optimize opt, size_t log_sz, bool tx)
+{
+	struct mlx5hws_cmd_rtc_create_attr rtc_attr = { 0 };
+	u32 *rtc_id;
+
+	rtc_attr.log_depth = 0;
+	rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
+	/* Action STEs use the default always hit definer. */
+	rtc_attr.match_definer_0 = ctx->caps->trivial_match_definer;
+	rtc_attr.is_frst_jumbo = false;
+	rtc_attr.miss_ft_id = 0;
+	rtc_attr.pd = ctx->pd_num;
+	rtc_attr.reparse_mode = mlx5hws_context_get_reparse_mode(ctx);
+
+	if (tx) {
+		rtc_attr.table_type = FS_FT_FDB_TX;
+		rtc_attr.ste_base =
+			mlx5hws_pool_get_base_mirror_id(action_tbl->pool);
+		rtc_attr.stc_base =
+			mlx5hws_pool_get_base_mirror_id(ctx->stc_pool);
+		rtc_attr.log_size =
+			opt == MLX5HWS_POOL_OPTIMIZE_ORIG ? 0 : log_sz;
+		rtc_id = &action_tbl->rtc_1_id;
+	} else {
+		rtc_attr.table_type = FS_FT_FDB_RX;
+		rtc_attr.ste_base = mlx5hws_pool_get_base_id(action_tbl->pool);
+		rtc_attr.stc_base = mlx5hws_pool_get_base_id(ctx->stc_pool);
+		rtc_attr.log_size =
+			opt == MLX5HWS_POOL_OPTIMIZE_MIRROR ? 0 : log_sz;
+		rtc_id = &action_tbl->rtc_0_id;
+	}
+
+	return mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_id);
+}
+
+static int
+hws_action_ste_table_create_rtcs(struct mlx5hws_context *ctx,
+				 struct mlx5hws_action_ste_table *action_tbl,
+				 enum mlx5hws_pool_optimize opt, size_t log_sz)
+{
+	int err;
+
+	err = hws_action_ste_table_create_single_rtc(ctx, action_tbl, opt,
+						     log_sz, false);
+	if (err)
+		return err;
+
+	err = hws_action_ste_table_create_single_rtc(ctx, action_tbl, opt,
+						     log_sz, true);
+	if (err) {
+		mlx5hws_cmd_rtc_destroy(ctx->mdev, action_tbl->rtc_0_id);
+		return err;
+	}
+
+	return 0;
+}
+
+static void
+hws_action_ste_table_destroy_rtcs(struct mlx5hws_action_ste_table *action_tbl)
+{
+	mlx5hws_cmd_rtc_destroy(action_tbl->pool->ctx->mdev,
+				action_tbl->rtc_1_id);
+	mlx5hws_cmd_rtc_destroy(action_tbl->pool->ctx->mdev,
+				action_tbl->rtc_0_id);
+}
+
+static int
+hws_action_ste_table_create_stc(struct mlx5hws_context *ctx,
+				struct mlx5hws_action_ste_table *action_tbl)
+{
+	struct mlx5hws_cmd_stc_modify_attr stc_attr = { 0 };
+
+	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE;
+	stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
+	stc_attr.ste_table.ste_pool = action_tbl->pool;
+	stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer;
+
+	return mlx5hws_action_alloc_single_stc(ctx, &stc_attr,
+					       MLX5HWS_TABLE_TYPE_FDB,
+					       &action_tbl->stc);
+}
+
+static struct mlx5hws_action_ste_table *
+hws_action_ste_table_alloc(struct mlx5hws_action_ste_pool_element *parent_elem)
+{
+	enum mlx5hws_pool_optimize opt = parent_elem->opt;
+	struct mlx5hws_context *ctx = parent_elem->ctx;
+	struct mlx5hws_action_ste_table *action_tbl;
+	size_t log_sz;
+	int err;
+
+	log_sz = min(parent_elem->log_sz ?
+			     parent_elem->log_sz +
+				     MLX5HWS_ACTION_STE_TABLE_STEP_LOG_SZ :
+				   MLX5HWS_ACTION_STE_TABLE_INIT_LOG_SZ,
+		     MLX5HWS_ACTION_STE_TABLE_MAX_LOG_SZ);
+
+	action_tbl = kzalloc(sizeof(*action_tbl), GFP_KERNEL);
+	if (!action_tbl)
+		return ERR_PTR(-ENOMEM);
+
+	err = hws_action_ste_table_create_pool(ctx, action_tbl, opt, log_sz);
+	if (err)
+		goto free_tbl;
+
+	err = hws_action_ste_table_create_rtcs(ctx, action_tbl, opt, log_sz);
+	if (err)
+		goto destroy_pool;
+
+	err = hws_action_ste_table_create_stc(ctx, action_tbl);
+	if (err)
+		goto destroy_rtcs;
+
+	action_tbl->parent_elem = parent_elem;
+	INIT_LIST_HEAD(&action_tbl->list_node);
+	action_tbl->last_used = jiffies;
+	list_add(&action_tbl->list_node, &parent_elem->available);
+	parent_elem->log_sz = log_sz;
+
+	mlx5hws_dbg(ctx,
+		    "Allocated %s action STE table log_sz %zu; STEs (%d, %d); RTCs (%d, %d); STC %d\n",
+		    hws_pool_opt_to_str(opt), log_sz,
+		    mlx5hws_pool_get_base_id(action_tbl->pool),
+		    mlx5hws_pool_get_base_mirror_id(action_tbl->pool),
+		    action_tbl->rtc_0_id, action_tbl->rtc_1_id,
+		    action_tbl->stc.offset);
+
+	return action_tbl;
+
+destroy_rtcs:
+	hws_action_ste_table_destroy_rtcs(action_tbl);
+destroy_pool:
+	mlx5hws_pool_destroy(action_tbl->pool);
+free_tbl:
+	kfree(action_tbl);
+
+	return ERR_PTR(err);
+}
+
+static void
+hws_action_ste_table_destroy(struct mlx5hws_action_ste_table *action_tbl)
+{
+	struct mlx5hws_context *ctx = action_tbl->parent_elem->ctx;
+
+	mlx5hws_dbg(ctx,
+		    "Destroying %s action STE table: STEs (%d, %d); RTCs (%d, %d); STC %d\n",
+		    hws_pool_opt_to_str(action_tbl->parent_elem->opt),
+		    mlx5hws_pool_get_base_id(action_tbl->pool),
+		    mlx5hws_pool_get_base_mirror_id(action_tbl->pool),
+		    action_tbl->rtc_0_id, action_tbl->rtc_1_id,
+		    action_tbl->stc.offset);
+
+	mlx5hws_action_free_single_stc(ctx, MLX5HWS_TABLE_TYPE_FDB,
+				       &action_tbl->stc);
+	hws_action_ste_table_destroy_rtcs(action_tbl);
+	mlx5hws_pool_destroy(action_tbl->pool);
+
+	list_del(&action_tbl->list_node);
+	kfree(action_tbl);
+}
+
+static int
+hws_action_ste_pool_element_init(struct mlx5hws_context *ctx,
+				 struct mlx5hws_action_ste_pool_element *elem,
+				 enum mlx5hws_pool_optimize opt)
+{
+	elem->ctx = ctx;
+	elem->opt = opt;
+	INIT_LIST_HEAD(&elem->available);
+	INIT_LIST_HEAD(&elem->full);
+
+	return 0;
+}
+
+static void hws_action_ste_pool_element_destroy(
+	struct mlx5hws_action_ste_pool_element *elem)
+{
+	struct mlx5hws_action_ste_table *action_tbl, *p;
+
+	/* This should be empty, but attempt to free its elements anyway. */
+	list_for_each_entry_safe(action_tbl, p, &elem->full, list_node)
+		hws_action_ste_table_destroy(action_tbl);
+
+	list_for_each_entry_safe(action_tbl, p, &elem->available, list_node)
+		hws_action_ste_table_destroy(action_tbl);
+}
+
+static int hws_action_ste_pool_init(struct mlx5hws_context *ctx,
+				    struct mlx5hws_action_ste_pool *pool)
+{
+	enum mlx5hws_pool_optimize opt;
+	int err;
+
+	mutex_init(&pool->lock);
+
+	/* Rules which are added for both RX and TX must use the same action STE
+	 * indices for both. If we were to use a single table, then RX-only and
+	 * TX-only rules would waste the unused entries. Thus, we use separate
+	 * table sets for the three cases.
+	 */
+	for (opt = MLX5HWS_POOL_OPTIMIZE_NONE; opt < MLX5HWS_POOL_OPTIMIZE_MAX;
+	     opt++) {
+		err = hws_action_ste_pool_element_init(ctx, &pool->elems[opt],
+						       opt);
+		if (err)
+			goto destroy_elems;
+		pool->elems[opt].parent_pool = pool;
+	}
+
+	return 0;
+
+destroy_elems:
+	while (opt-- > MLX5HWS_POOL_OPTIMIZE_NONE)
+		hws_action_ste_pool_element_destroy(&pool->elems[opt]);
+
+	return err;
+}
+
+static void hws_action_ste_pool_destroy(struct mlx5hws_action_ste_pool *pool)
+{
+	int opt;
+
+	for (opt = MLX5HWS_POOL_OPTIMIZE_MAX - 1;
+	     opt >= MLX5HWS_POOL_OPTIMIZE_NONE; opt--)
+		hws_action_ste_pool_element_destroy(&pool->elems[opt]);
+}
+
+static void hws_action_ste_pool_element_collect_stale(
+	struct mlx5hws_action_ste_pool_element *elem, struct list_head *cleanup)
+{
+	struct mlx5hws_action_ste_table *action_tbl, *p;
+	unsigned long expire_time, now;
+
+	expire_time = secs_to_jiffies(MLX5HWS_ACTION_STE_POOL_EXPIRE_SECONDS);
+	now = jiffies;
+
+	list_for_each_entry_safe(action_tbl, p, &elem->available, list_node) {
+		if (mlx5hws_pool_full(action_tbl->pool) &&
+		    time_before(action_tbl->last_used + expire_time, now))
+			list_move(&action_tbl->list_node, cleanup);
+	}
+}
+
+static void hws_action_ste_table_cleanup_list(struct list_head *cleanup)
+{
+	struct mlx5hws_action_ste_table *action_tbl, *p;
+
+	list_for_each_entry_safe(action_tbl, p, cleanup, list_node)
+		hws_action_ste_table_destroy(action_tbl);
+}
+
+static void hws_action_ste_pool_cleanup(struct work_struct *work)
+{
+	enum mlx5hws_pool_optimize opt;
+	struct mlx5hws_context *ctx;
+	LIST_HEAD(cleanup);
+	int i;
+
+	ctx = container_of(work, struct mlx5hws_context,
+			   action_ste_cleanup.work);
+
+	for (i = 0; i < ctx->queues; i++) {
+		struct mlx5hws_action_ste_pool *p = &ctx->action_ste_pool[i];
+
+		mutex_lock(&p->lock);
+		for (opt = MLX5HWS_POOL_OPTIMIZE_NONE;
+		     opt < MLX5HWS_POOL_OPTIMIZE_MAX; opt++)
+			hws_action_ste_pool_element_collect_stale(
+				&p->elems[opt], &cleanup);
+		mutex_unlock(&p->lock);
+	}
+
+	hws_action_ste_table_cleanup_list(&cleanup);
+
+	schedule_delayed_work(&ctx->action_ste_cleanup,
+			      secs_to_jiffies(
+				  MLX5HWS_ACTION_STE_POOL_CLEANUP_SECONDS));
+}
+
+int mlx5hws_action_ste_pool_init(struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_action_ste_pool *pool;
+	size_t queues = ctx->queues;
+	int i, err;
+
+	pool = kcalloc(queues, sizeof(*pool), GFP_KERNEL);
+	if (!pool)
+		return -ENOMEM;
+
+	for (i = 0; i < queues; i++) {
+		err = hws_action_ste_pool_init(ctx, &pool[i]);
+		if (err)
+			goto free_pool;
+	}
+
+	ctx->action_ste_pool = pool;
+
+	INIT_DELAYED_WORK(&ctx->action_ste_cleanup,
+			  hws_action_ste_pool_cleanup);
+	schedule_delayed_work(
+		&ctx->action_ste_cleanup,
+		secs_to_jiffies(MLX5HWS_ACTION_STE_POOL_CLEANUP_SECONDS));
+
+	return 0;
+
+free_pool:
+	while (i--)
+		hws_action_ste_pool_destroy(&pool[i]);
+	kfree(pool);
+
+	return err;
+}
+
+void mlx5hws_action_ste_pool_uninit(struct mlx5hws_context *ctx)
+{
+	size_t queues = ctx->queues;
+	int i;
+
+	cancel_delayed_work_sync(&ctx->action_ste_cleanup);
+
+	for (i = 0; i < queues; i++)
+		hws_action_ste_pool_destroy(&ctx->action_ste_pool[i]);
+
+	kfree(ctx->action_ste_pool);
+}
+
+static struct mlx5hws_action_ste_pool_element *
+hws_action_ste_choose_elem(struct mlx5hws_action_ste_pool *pool,
+			   bool skip_rx, bool skip_tx)
+{
+	if (skip_rx)
+		return &pool->elems[MLX5HWS_POOL_OPTIMIZE_MIRROR];
+
+	if (skip_tx)
+		return &pool->elems[MLX5HWS_POOL_OPTIMIZE_ORIG];
+
+	return &pool->elems[MLX5HWS_POOL_OPTIMIZE_NONE];
+}
+
+static int
+hws_action_ste_table_chunk_alloc(struct mlx5hws_action_ste_table *action_tbl,
+				 struct mlx5hws_action_ste_chunk *chunk)
+{
+	int err;
+
+	err = mlx5hws_pool_chunk_alloc(action_tbl->pool, &chunk->ste);
+	if (err)
+		return err;
+
+	chunk->action_tbl = action_tbl;
+	action_tbl->last_used = jiffies;
+
+	return 0;
+}
+
+int mlx5hws_action_ste_chunk_alloc(struct mlx5hws_action_ste_pool *pool,
+				   bool skip_rx, bool skip_tx,
+				   struct mlx5hws_action_ste_chunk *chunk)
+{
+	struct mlx5hws_action_ste_pool_element *elem;
+	struct mlx5hws_action_ste_table *action_tbl;
+	bool found;
+	int err;
+
+	if (skip_rx && skip_tx)
+		return -EINVAL;
+
+	mutex_lock(&pool->lock);
+
+	elem = hws_action_ste_choose_elem(pool, skip_rx, skip_tx);
+
+	mlx5hws_dbg(elem->ctx,
+		    "Allocating action STEs skip_rx %d skip_tx %d order %d\n",
+		    skip_rx, skip_tx, chunk->ste.order);
+
+	found = false;
+	list_for_each_entry(action_tbl, &elem->available, list_node) {
+		if (!hws_action_ste_table_chunk_alloc(action_tbl, chunk)) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		action_tbl = hws_action_ste_table_alloc(elem);
+		if (IS_ERR(action_tbl)) {
+			err = PTR_ERR(action_tbl);
+			goto out;
+		}
+
+		err = hws_action_ste_table_chunk_alloc(action_tbl, chunk);
+		if (err)
+			goto out;
+	}
+
+	if (mlx5hws_pool_empty(action_tbl->pool))
+		list_move(&action_tbl->list_node, &elem->full);
+
+	err = 0;
+
+out:
+	mutex_unlock(&pool->lock);
+
+	return err;
+}
+
+void mlx5hws_action_ste_chunk_free(struct mlx5hws_action_ste_chunk *chunk)
+{
+	struct mutex *lock = &chunk->action_tbl->parent_elem->parent_pool->lock;
+
+	mlx5hws_dbg(chunk->action_tbl->pool->ctx,
+		    "Freeing action STEs offset %d order %d\n",
+		    chunk->ste.offset, chunk->ste.order);
+
+	mutex_lock(lock);
+	mlx5hws_pool_chunk_free(chunk->action_tbl->pool, &chunk->ste);
+	chunk->action_tbl->last_used = jiffies;
+	list_move(&chunk->action_tbl->list_node,
+		  &chunk->action_tbl->parent_elem->available);
+	mutex_unlock(lock);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.h
new file mode 100644
index 000000000000..a8ba97359e31
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#ifndef ACTION_STE_POOL_H_
+#define ACTION_STE_POOL_H_
+
+#define MLX5HWS_ACTION_STE_TABLE_INIT_LOG_SZ 10
+#define MLX5HWS_ACTION_STE_TABLE_STEP_LOG_SZ 1
+#define MLX5HWS_ACTION_STE_TABLE_MAX_LOG_SZ 20
+
+#define MLX5HWS_ACTION_STE_POOL_CLEANUP_SECONDS 300
+#define MLX5HWS_ACTION_STE_POOL_EXPIRE_SECONDS 300
+
+struct mlx5hws_action_ste_pool_element;
+
+struct mlx5hws_action_ste_table {
+	struct mlx5hws_action_ste_pool_element *parent_elem;
+	/* Wraps the RTC and STE range for this given action. */
+	struct mlx5hws_pool *pool;
+	/* Match STEs use this STC to jump to this pool's RTC. */
+	struct mlx5hws_pool_chunk stc;
+	u32 rtc_0_id;
+	u32 rtc_1_id;
+	struct list_head list_node;
+	unsigned long last_used;
+};
+
+struct mlx5hws_action_ste_pool_element {
+	struct mlx5hws_context *ctx;
+	struct mlx5hws_action_ste_pool *parent_pool;
+	size_t log_sz;  /* Size of the largest table so far. */
+	enum mlx5hws_pool_optimize opt;
+	struct list_head available;
+	struct list_head full;
+};
+
+/* Central repository of action STEs. The context contains one of these pools
+ * per queue.
+ */
+struct mlx5hws_action_ste_pool {
+	/* Protects the entire pool. We have one pool per queue and only one
+	 * operation can be active per rule at a given time. Thus this lock
+	 * protects solely against concurrent garbage collection and we expect
+	 * very little contention.
+	 */
+	struct mutex lock;
+	struct mlx5hws_action_ste_pool_element elems[MLX5HWS_POOL_OPTIMIZE_MAX];
+};
+
+/* A chunk of STEs and the table it was allocated from. Used by rules. */
+struct mlx5hws_action_ste_chunk {
+	struct mlx5hws_action_ste_table *action_tbl;
+	struct mlx5hws_pool_chunk ste;
+};
+
+int mlx5hws_action_ste_pool_init(struct mlx5hws_context *ctx);
+
+void mlx5hws_action_ste_pool_uninit(struct mlx5hws_context *ctx);
+
+/* Callers are expected to fill chunk->ste.order. On success, this function
+ * populates chunk->tbl and chunk->ste.offset.
+ */
+int mlx5hws_action_ste_chunk_alloc(struct mlx5hws_action_ste_pool *pool,
+				   bool skip_rx, bool skip_tx,
+				   struct mlx5hws_action_ste_chunk *chunk);
+
+void mlx5hws_action_ste_chunk_free(struct mlx5hws_action_ste_chunk *chunk);
+
+#endif /* ACTION_STE_POOL_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
index baacf662c0ab..6ef0c4be27e1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
@@ -46,9 +46,10 @@ static void hws_bwc_unlock_all_queues(struct mlx5hws_context *ctx)
 	}
 }
 
-static void hws_bwc_matcher_init_attr(struct mlx5hws_matcher_attr *attr,
+static void hws_bwc_matcher_init_attr(struct mlx5hws_bwc_matcher *bwc_matcher,
 				      u32 priority,
-				      u8 size_log)
+				      u8 size_log_rx, u8 size_log_tx,
+				      struct mlx5hws_matcher_attr *attr)
 {
 	memset(attr, 0, sizeof(*attr));
 
@@ -58,11 +59,170 @@ static void hws_bwc_matcher_init_attr(struct mlx5hws_matcher_attr *attr,
 	attr->optimize_flow_src = MLX5HWS_MATCHER_FLOW_SRC_ANY;
 	attr->insert_mode = MLX5HWS_MATCHER_INSERT_BY_HASH;
 	attr->distribute_mode = MLX5HWS_MATCHER_DISTRIBUTE_BY_HASH;
-	attr->rule.num_log = size_log;
+	attr->size[MLX5HWS_MATCHER_SIZE_TYPE_RX].rule.num_log = size_log_rx;
+	attr->size[MLX5HWS_MATCHER_SIZE_TYPE_TX].rule.num_log = size_log_tx;
 	attr->resizable = true;
 	attr->max_num_of_at_attach = MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM;
 }
 
+static int
+hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_matcher *matcher = bwc_matcher->matcher;
+	int drain_error = 0, move_error = 0, poll_error = 0;
+	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
+	struct mlx5hws_rule_attr rule_attr;
+	struct mlx5hws_bwc_rule *bwc_rule;
+	struct mlx5hws_send_engine *queue;
+	struct list_head *rules_list;
+	u32 pending_rules;
+	int i, ret = 0;
+	bool drain;
+
+	mlx5hws_bwc_rule_fill_attr(bwc_matcher, 0, 0, &rule_attr);
+
+	for (i = 0; i < bwc_queues; i++) {
+		if (list_empty(&bwc_matcher->rules[i]))
+			continue;
+
+		pending_rules = 0;
+		rule_attr.queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
+		rules_list = &bwc_matcher->rules[i];
+
+		list_for_each_entry(bwc_rule, rules_list, list_node) {
+			ret = mlx5hws_matcher_resize_rule_move(matcher,
+							       bwc_rule->rule,
+							       &rule_attr);
+			if (unlikely(ret)) {
+				if (!move_error) {
+					mlx5hws_err(ctx,
+						    "Moving BWC rule: move failed (%d), attempting to move rest of the rules\n",
+						    ret);
+					move_error = ret;
+				}
+				/* Rule wasn't queued, no need to poll */
+				continue;
+			}
+
+			pending_rules++;
+			drain = pending_rules >=
+				hws_bwc_get_burst_th(ctx, rule_attr.queue_id);
+			ret = mlx5hws_bwc_queue_poll(ctx,
+						     rule_attr.queue_id,
+						     &pending_rules,
+						     drain);
+			if (unlikely(ret)) {
+				if (ret == -ETIMEDOUT) {
+					mlx5hws_err(ctx,
+						    "Moving BWC rule: timeout polling for completions (%d), aborting rehash\n",
+						    ret);
+					return ret;
+				}
+				if (!poll_error) {
+					mlx5hws_err(ctx,
+						    "Moving BWC rule: polling for completions failed (%d), attempting to move rest of the rules\n",
+						    ret);
+					poll_error = ret;
+				}
+			}
+		}
+
+		if (pending_rules) {
+			queue = &ctx->send_queue[rule_attr.queue_id];
+			mlx5hws_send_engine_flush_queue(queue);
+			ret = mlx5hws_bwc_queue_poll(ctx,
+						     rule_attr.queue_id,
+						     &pending_rules,
+						     true);
+			if (unlikely(ret)) {
+				if (ret == -ETIMEDOUT) {
+					mlx5hws_err(ctx,
+						    "Moving bwc rule: timeout draining completions (%d), aborting rehash\n",
+						    ret);
+					return ret;
+				}
+				if (!drain_error) {
+					mlx5hws_err(ctx,
+						    "Moving bwc rule: drain failed (%d), attempting to move rest of the rules\n",
+						    ret);
+					drain_error = ret;
+				}
+			}
+		}
+	}
+
+	/* Return the first error that happened */
+	if (unlikely(move_error))
+		return move_error;
+	if (unlikely(poll_error))
+		return poll_error;
+	if (unlikely(drain_error))
+		return drain_error;
+
+	return ret;
+}
+
+static int hws_bwc_matcher_move_all(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	switch (bwc_matcher->matcher_type) {
+	case MLX5HWS_BWC_MATCHER_SIMPLE:
+		return hws_bwc_matcher_move_all_simple(bwc_matcher);
+	case MLX5HWS_BWC_MATCHER_COMPLEX_FIRST:
+		return mlx5hws_bwc_matcher_complex_move_first(bwc_matcher);
+	case MLX5HWS_BWC_MATCHER_COMPLEX_SUBMATCHER:
+		return mlx5hws_bwc_matcher_complex_move(bwc_matcher);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int hws_bwc_matcher_move(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_matcher_attr matcher_attr = {0};
+	struct mlx5hws_matcher *old_matcher;
+	struct mlx5hws_matcher *new_matcher;
+	int ret;
+
+	hws_bwc_matcher_init_attr(bwc_matcher,
+				  bwc_matcher->priority,
+				  bwc_matcher->rx_size.size_log,
+				  bwc_matcher->tx_size.size_log,
+				  &matcher_attr);
+
+	old_matcher = bwc_matcher->matcher;
+	new_matcher = mlx5hws_matcher_create(old_matcher->tbl,
+					     &bwc_matcher->mt, 1,
+					     bwc_matcher->at,
+					     bwc_matcher->num_of_at,
+					     &matcher_attr);
+	if (!new_matcher) {
+		mlx5hws_err(ctx, "Rehash error: matcher creation failed\n");
+		return -ENOMEM;
+	}
+
+	ret = mlx5hws_matcher_resize_set_target(old_matcher, new_matcher);
+	if (ret) {
+		mlx5hws_err(ctx, "Rehash error: failed setting resize target\n");
+		return ret;
+	}
+
+	ret = hws_bwc_matcher_move_all(bwc_matcher);
+	if (ret)
+		mlx5hws_err(ctx, "Rehash error: moving rules failed, attempting to remove the old matcher\n");
+
+	/* Error during rehash can't be rolled back.
+	 * The best option here is to allow the rehash to complete and remove
+	 * the old matcher - can't leave the matcher in the 'in_resize' state.
+	 */
+
+	bwc_matcher->matcher = new_matcher;
+	mlx5hws_matcher_destroy(old_matcher);
+
+	return ret;
+}
+
 int mlx5hws_bwc_matcher_create_simple(struct mlx5hws_bwc_matcher *bwc_matcher,
 				      struct mlx5hws_table *table,
 				      u32 priority,
@@ -83,12 +243,20 @@ int mlx5hws_bwc_matcher_create_simple(struct mlx5hws_bwc_matcher *bwc_matcher,
 	for (i = 0; i < bwc_queues; i++)
 		INIT_LIST_HEAD(&bwc_matcher->rules[i]);
 
-	hws_bwc_matcher_init_attr(&attr,
+	hws_bwc_matcher_init_attr(bwc_matcher,
 				  priority,
-				  MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG);
+				  bwc_matcher->rx_size.size_log,
+				  bwc_matcher->tx_size.size_log,
+				  &attr);
 
+	bwc_matcher->matcher_type = MLX5HWS_BWC_MATCHER_SIMPLE;
 	bwc_matcher->priority = priority;
-	bwc_matcher->size_log = MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG;
+
+	bwc_matcher->size_of_at_array = MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM;
+	bwc_matcher->at = kcalloc(bwc_matcher->size_of_at_array,
+				  sizeof(*bwc_matcher->at), GFP_KERNEL);
+	if (!bwc_matcher->at)
+		goto free_bwc_matcher_rules;
 
 	/* create dummy action template */
 	bwc_matcher->at[0] =
@@ -96,7 +264,7 @@ int mlx5hws_bwc_matcher_create_simple(struct mlx5hws_bwc_matcher *bwc_matcher,
 					       action_types : init_action_types);
 	if (!bwc_matcher->at[0]) {
 		mlx5hws_err(table->ctx, "BWC matcher: failed creating action template\n");
-		goto free_bwc_matcher_rules;
+		goto free_bwc_matcher_at_array;
 	}
 
 	bwc_matcher->num_of_at = 1;
@@ -126,12 +294,28 @@ free_mt:
 	mlx5hws_match_template_destroy(bwc_matcher->mt);
 free_at:
 	mlx5hws_action_template_destroy(bwc_matcher->at[0]);
+free_bwc_matcher_at_array:
+	kfree(bwc_matcher->at);
 free_bwc_matcher_rules:
 	kfree(bwc_matcher->rules);
 err:
 	return -EINVAL;
 }
 
+static void
+hws_bwc_matcher_init_size_rxtx(struct mlx5hws_bwc_matcher_size *size)
+{
+	size->size_log = MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG;
+	atomic_set(&size->num_of_rules, 0);
+	atomic_set(&size->rehash_required, false);
+}
+
+static void hws_bwc_matcher_init_size(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	hws_bwc_matcher_init_size_rxtx(&bwc_matcher->rx_size);
+	hws_bwc_matcher_init_size_rxtx(&bwc_matcher->tx_size);
+}
+
 struct mlx5hws_bwc_matcher *
 mlx5hws_bwc_matcher_create(struct mlx5hws_table *table,
 			   u32 priority,
@@ -152,6 +336,8 @@ mlx5hws_bwc_matcher_create(struct mlx5hws_table *table,
 	if (!bwc_matcher)
 		return NULL;
 
+	hws_bwc_matcher_init_size(bwc_matcher);
+
 	/* Check if the required match params can be all matched
 	 * in single STE, otherwise complex matcher is needed.
 	 */
@@ -190,6 +376,7 @@ int mlx5hws_bwc_matcher_destroy_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 
 	for (i = 0; i < bwc_matcher->num_of_at; i++)
 		mlx5hws_action_template_destroy(bwc_matcher->at[i]);
+	kfree(bwc_matcher->at);
 
 	mlx5hws_match_template_destroy(bwc_matcher->mt);
 	kfree(bwc_matcher->rules);
@@ -199,22 +386,30 @@ int mlx5hws_bwc_matcher_destroy_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 
 int mlx5hws_bwc_matcher_destroy(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
-	if (bwc_matcher->num_of_rules)
+	u32 rx_rules = atomic_read(&bwc_matcher->rx_size.num_of_rules);
+	u32 tx_rules = atomic_read(&bwc_matcher->tx_size.num_of_rules);
+
+	if (rx_rules || tx_rules)
 		mlx5hws_err(bwc_matcher->matcher->tbl->ctx,
-			    "BWC matcher destroy: matcher still has %d rules\n",
-			    bwc_matcher->num_of_rules);
+			    "BWC matcher destroy: matcher still has %u RX and %u TX rules\n",
+			    rx_rules, tx_rules);
 
-	mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
+	if (bwc_matcher->matcher_type == MLX5HWS_BWC_MATCHER_COMPLEX_FIRST)
+		mlx5hws_bwc_matcher_destroy_complex(bwc_matcher);
+	else
+		mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
 
 	kfree(bwc_matcher);
 	return 0;
 }
 
-static int hws_bwc_queue_poll(struct mlx5hws_context *ctx,
-			      u16 queue_id,
-			      u32 *pending_rules,
-			      bool drain)
+int mlx5hws_bwc_queue_poll(struct mlx5hws_context *ctx,
+			   u16 queue_id,
+			   u32 *pending_rules,
+			   bool drain)
 {
+	unsigned long timeout = jiffies +
+				secs_to_jiffies(MLX5HWS_BWC_POLLING_TIMEOUT);
 	struct mlx5hws_flow_op_result comp[MLX5HWS_BWC_MATCHER_REHASH_BURST_TH];
 	u16 burst_th = hws_bwc_get_burst_th(ctx, queue_id);
 	bool got_comp = *pending_rules >= burst_th;
@@ -250,6 +445,11 @@ static int hws_bwc_queue_poll(struct mlx5hws_context *ctx,
 		}
 
 		got_comp = !!ret;
+
+		if (unlikely(!got_comp && time_after(jiffies, timeout))) {
+			mlx5hws_err(ctx, "BWC poll error: polling queue %d - TIMEOUT\n", queue_id);
+			return -ETIMEDOUT;
+		}
 	}
 
 	return err;
@@ -309,16 +509,12 @@ static void hws_bwc_rule_list_add(struct mlx5hws_bwc_rule *bwc_rule, u16 idx)
 {
 	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
 
-	bwc_matcher->num_of_rules++;
 	bwc_rule->bwc_queue_idx = idx;
 	list_add(&bwc_rule->list_node, &bwc_matcher->rules[idx]);
 }
 
 static void hws_bwc_rule_list_remove(struct mlx5hws_bwc_rule *bwc_rule)
 {
-	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
-
-	bwc_matcher->num_of_rules--;
 	list_del_init(&bwc_rule->list_node);
 }
 
@@ -334,28 +530,102 @@ hws_bwc_rule_destroy_hws_sync(struct mlx5hws_bwc_rule *bwc_rule,
 			      struct mlx5hws_rule_attr *rule_attr)
 {
 	struct mlx5hws_context *ctx = bwc_rule->bwc_matcher->matcher->tbl->ctx;
-	struct mlx5hws_flow_op_result completion;
+	u32 expected_completions = 1;
 	int ret;
 
 	ret = hws_bwc_rule_destroy_hws_async(bwc_rule, rule_attr);
 	if (unlikely(ret))
 		return ret;
 
-	do {
-		ret = mlx5hws_send_queue_poll(ctx, rule_attr->queue_id, &completion, 1);
-	} while (ret != 1);
+	ret = mlx5hws_bwc_queue_poll(ctx, rule_attr->queue_id,
+				     &expected_completions, true);
+	if (unlikely(ret))
+		return ret;
 
-	if (unlikely(completion.status != MLX5HWS_FLOW_OP_SUCCESS ||
-		     (bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETED &&
-		      bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETING))) {
-		mlx5hws_err(ctx, "Failed destroying BWC rule: completion %d, rule status %d\n",
-			    completion.status, bwc_rule->rule->status);
+	if (unlikely(bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETED &&
+		     bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETING)) {
+		mlx5hws_err(ctx, "Failed destroying BWC rule: rule status %d\n",
+			    bwc_rule->rule->status);
 		return -EINVAL;
 	}
 
 	return 0;
 }
 
+static void hws_bwc_rule_cnt_dec(struct mlx5hws_bwc_rule *bwc_rule)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+
+	if (!bwc_rule->skip_rx)
+		atomic_dec(&bwc_matcher->rx_size.num_of_rules);
+	if (!bwc_rule->skip_tx)
+		atomic_dec(&bwc_matcher->tx_size.num_of_rules);
+}
+
+static int
+hws_bwc_matcher_rehash_shrink(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	struct mlx5hws_bwc_matcher_size *rx_size = &bwc_matcher->rx_size;
+	struct mlx5hws_bwc_matcher_size *tx_size = &bwc_matcher->tx_size;
+
+	/* It is possible that another thread has added a rule.
+	 * Need to check again if we really need rehash/shrink.
+	 */
+	if (atomic_read(&rx_size->num_of_rules) ||
+	    atomic_read(&tx_size->num_of_rules))
+		return 0;
+
+	/* If the current matcher RX/TX size is already at its initial size. */
+	if (rx_size->size_log == MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG &&
+	    tx_size->size_log == MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG)
+		return 0;
+
+	/* Now we've done all the checking - do the shrinking:
+	 *  - reset match RTC size to the initial size
+	 *  - create new matcher
+	 *  - move the rules, which will not do anything as the matcher is empty
+	 *  - destroy the old matcher
+	 */
+
+	rx_size->size_log = MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG;
+	tx_size->size_log = MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG;
+
+	return hws_bwc_matcher_move(bwc_matcher);
+}
+
+static int hws_bwc_rule_cnt_dec_with_shrink(struct mlx5hws_bwc_rule *bwc_rule,
+					    u16 bwc_queue_idx)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mutex *queue_lock; /* Protect the queue */
+	int ret;
+
+	hws_bwc_rule_cnt_dec(bwc_rule);
+
+	if (atomic_read(&bwc_matcher->rx_size.num_of_rules) ||
+	    atomic_read(&bwc_matcher->tx_size.num_of_rules))
+		return 0;
+
+	/* Matcher has no more rules - shrink it to save ICM. */
+
+	queue_lock = hws_bwc_get_queue_lock(ctx, bwc_queue_idx);
+	mutex_unlock(queue_lock);
+
+	hws_bwc_lock_all_queues(ctx);
+	ret = hws_bwc_matcher_rehash_shrink(bwc_matcher);
+	hws_bwc_unlock_all_queues(ctx);
+
+	mutex_lock(queue_lock);
+
+	if (unlikely(ret))
+		mlx5hws_err(ctx,
+			    "BWC rule deletion: shrinking empty matcher failed (%d)\n",
+			    ret);
+
+	return ret;
+}
+
 int mlx5hws_bwc_rule_destroy_simple(struct mlx5hws_bwc_rule *bwc_rule)
 {
 	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
@@ -373,6 +643,7 @@ int mlx5hws_bwc_rule_destroy_simple(struct mlx5hws_bwc_rule *bwc_rule)
 
 	ret = hws_bwc_rule_destroy_hws_sync(bwc_rule, &attr);
 	hws_bwc_rule_list_remove(bwc_rule);
+	hws_bwc_rule_cnt_dec_with_shrink(bwc_rule, idx);
 
 	mutex_unlock(queue_lock);
 
@@ -381,9 +652,14 @@ int mlx5hws_bwc_rule_destroy_simple(struct mlx5hws_bwc_rule *bwc_rule)
 
 int mlx5hws_bwc_rule_destroy(struct mlx5hws_bwc_rule *bwc_rule)
 {
-	int ret;
+	bool is_complex = bwc_rule->bwc_matcher->matcher_type ==
+			  MLX5HWS_BWC_MATCHER_COMPLEX_FIRST;
+	int ret = 0;
 
-	ret = mlx5hws_bwc_rule_destroy_simple(bwc_rule);
+	if (is_complex)
+		ret = mlx5hws_bwc_rule_destroy_complex(bwc_rule);
+	else
+		ret = mlx5hws_bwc_rule_destroy_simple(bwc_rule);
 
 	mlx5hws_bwc_rule_free(bwc_rule);
 	return ret;
@@ -423,9 +699,8 @@ hws_bwc_rule_create_sync(struct mlx5hws_bwc_rule *bwc_rule,
 	if (unlikely(ret))
 		return ret;
 
-	ret = hws_bwc_queue_poll(ctx, rule_attr->queue_id, &expected_completions, true);
-
-	return ret;
+	return mlx5hws_bwc_queue_poll(ctx, rule_attr->queue_id,
+				      &expected_completions, true);
 }
 
 static int
@@ -446,7 +721,8 @@ hws_bwc_rule_update_sync(struct mlx5hws_bwc_rule *bwc_rule,
 	if (unlikely(ret))
 		return ret;
 
-	ret = hws_bwc_queue_poll(ctx, rule_attr->queue_id, &expected_completions, true);
+	ret = mlx5hws_bwc_queue_poll(ctx, rule_attr->queue_id,
+				     &expected_completions, true);
 	if (unlikely(ret))
 		mlx5hws_err(ctx, "Failed updating BWC rule (%d)\n", ret);
 
@@ -454,23 +730,27 @@ hws_bwc_rule_update_sync(struct mlx5hws_bwc_rule *bwc_rule,
 }
 
 static bool
-hws_bwc_matcher_size_maxed_out(struct mlx5hws_bwc_matcher *bwc_matcher)
+hws_bwc_matcher_size_maxed_out(struct mlx5hws_bwc_matcher *bwc_matcher,
+			       struct mlx5hws_bwc_matcher_size *size)
 {
 	struct mlx5hws_cmd_query_caps *caps = bwc_matcher->matcher->tbl->ctx->caps;
 
-	return bwc_matcher->size_log + MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH >=
-	       caps->ste_alloc_log_max - 1;
+	/* check the match RTC size */
+	return (size->size_log + MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH +
+		MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP) >
+	       (caps->ste_alloc_log_max - 1);
 }
 
 static bool
 hws_bwc_matcher_rehash_size_needed(struct mlx5hws_bwc_matcher *bwc_matcher,
+				   struct mlx5hws_bwc_matcher_size *size,
 				   u32 num_of_rules)
 {
-	if (unlikely(hws_bwc_matcher_size_maxed_out(bwc_matcher)))
+	if (unlikely(hws_bwc_matcher_size_maxed_out(bwc_matcher, size)))
 		return false;
 
 	if (unlikely((num_of_rules * 100 / MLX5HWS_BWC_MATCHER_REHASH_PERCENT_TH) >=
-		     (1UL << bwc_matcher->size_log)))
+		     (1UL << size->size_log)))
 		return true;
 
 	return false;
@@ -496,6 +776,23 @@ hws_bwc_matcher_extend_at(struct mlx5hws_bwc_matcher *bwc_matcher,
 			  struct mlx5hws_rule_action rule_actions[])
 {
 	enum mlx5hws_action_type action_types[MLX5HWS_BWC_MAX_ACTS];
+	void *p;
+
+	if (unlikely(bwc_matcher->num_of_at >= bwc_matcher->size_of_at_array)) {
+		if (bwc_matcher->size_of_at_array >= MLX5HWS_MATCHER_MAX_AT)
+			return -ENOMEM;
+		bwc_matcher->size_of_at_array *= 2;
+		p = krealloc(bwc_matcher->at,
+			     bwc_matcher->size_of_at_array *
+				     sizeof(*bwc_matcher->at),
+			     __GFP_ZERO | GFP_KERNEL);
+		if (!p) {
+			bwc_matcher->size_of_at_array /= 2;
+			return -ENOMEM;
+		}
+
+		bwc_matcher->at = p;
+	}
 
 	hws_bwc_rule_actions_to_action_types(rule_actions, action_types);
 
@@ -510,20 +807,21 @@ hws_bwc_matcher_extend_at(struct mlx5hws_bwc_matcher *bwc_matcher,
 }
 
 static int
-hws_bwc_matcher_extend_size(struct mlx5hws_bwc_matcher *bwc_matcher)
+hws_bwc_matcher_extend_size(struct mlx5hws_bwc_matcher *bwc_matcher,
+			    struct mlx5hws_bwc_matcher_size *size)
 {
 	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
 	struct mlx5hws_cmd_query_caps *caps = ctx->caps;
 
-	if (unlikely(hws_bwc_matcher_size_maxed_out(bwc_matcher))) {
+	if (unlikely(hws_bwc_matcher_size_maxed_out(bwc_matcher, size))) {
 		mlx5hws_err(ctx, "Can't resize matcher: depth exceeds limit %d\n",
 			    caps->rtc_log_depth_max);
 		return -ENOMEM;
 	}
 
-	bwc_matcher->size_log =
-		min(bwc_matcher->size_log + MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP,
-		    caps->ste_alloc_log_max - MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH);
+	size->size_log = min(size->size_log + MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP,
+			     caps->ste_alloc_log_max -
+				     MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH);
 
 	return 0;
 }
@@ -556,182 +854,171 @@ hws_bwc_matcher_find_at(struct mlx5hws_bwc_matcher *bwc_matcher,
 	return -1;
 }
 
-static int hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
+static int
+hws_bwc_matcher_rehash_size(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
-	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
-	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
-	struct mlx5hws_bwc_rule **bwc_rules;
-	struct mlx5hws_rule_attr rule_attr;
-	u32 *pending_rules;
-	int i, j, ret = 0;
-	bool all_done;
-	u16 burst_th;
+	bool need_rx_rehash, need_tx_rehash;
+	int ret;
 
-	mlx5hws_bwc_rule_fill_attr(bwc_matcher, 0, 0, &rule_attr);
+	need_rx_rehash = atomic_read(&bwc_matcher->rx_size.rehash_required);
+	need_tx_rehash = atomic_read(&bwc_matcher->tx_size.rehash_required);
 
-	pending_rules = kcalloc(bwc_queues, sizeof(*pending_rules), GFP_KERNEL);
-	if (!pending_rules)
-		return -ENOMEM;
+	/* It is possible that another rule has already performed rehash.
+	 * Need to check again if we really need rehash.
+	 */
+	if (!need_rx_rehash && !need_tx_rehash)
+		return 0;
 
-	bwc_rules = kcalloc(bwc_queues, sizeof(*bwc_rules), GFP_KERNEL);
-	if (!bwc_rules) {
-		ret = -ENOMEM;
-		goto free_pending_rules;
+	/* If the current matcher RX/TX size is already at its max size,
+	 * it can't be rehashed.
+	 */
+	if (need_rx_rehash &&
+	    hws_bwc_matcher_size_maxed_out(bwc_matcher,
+					   &bwc_matcher->rx_size)) {
+		atomic_set(&bwc_matcher->rx_size.rehash_required, false);
+		need_rx_rehash = false;
+	}
+	if (need_tx_rehash &&
+	    hws_bwc_matcher_size_maxed_out(bwc_matcher,
+					   &bwc_matcher->tx_size)) {
+		atomic_set(&bwc_matcher->tx_size.rehash_required, false);
+		need_tx_rehash = false;
 	}
 
-	for (i = 0; i < bwc_queues; i++) {
-		if (list_empty(&bwc_matcher->rules[i]))
-			bwc_rules[i] = NULL;
-		else
-			bwc_rules[i] = list_first_entry(&bwc_matcher->rules[i],
-							struct mlx5hws_bwc_rule,
-							list_node);
-	}
-
-	do {
-		all_done = true;
-
-		for (i = 0; i < bwc_queues; i++) {
-			rule_attr.queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
-			burst_th = hws_bwc_get_burst_th(ctx, rule_attr.queue_id);
-
-			for (j = 0; j < burst_th && bwc_rules[i]; j++) {
-				rule_attr.burst = !!((j + 1) % burst_th);
-				ret = mlx5hws_matcher_resize_rule_move(bwc_matcher->matcher,
-								       bwc_rules[i]->rule,
-								       &rule_attr);
-				if (unlikely(ret)) {
-					mlx5hws_err(ctx,
-						    "Moving BWC rule failed during rehash (%d)\n",
-						    ret);
-					goto free_bwc_rules;
-				}
-
-				all_done = false;
-				pending_rules[i]++;
-				bwc_rules[i] = list_is_last(&bwc_rules[i]->list_node,
-							    &bwc_matcher->rules[i]) ?
-					       NULL : list_next_entry(bwc_rules[i], list_node);
+	/* If both RX and TX rehash flags are now off, it means that whatever
+	 * we wanted to rehash is now at its max size - no rehash can be done.
+	 * Return and try adding the rule again - perhaps there was some change.
+	 */
+	if (!need_rx_rehash && !need_tx_rehash)
+		return 0;
 
-				ret = hws_bwc_queue_poll(ctx, rule_attr.queue_id,
-							 &pending_rules[i], false);
-				if (unlikely(ret))
-					goto free_bwc_rules;
-			}
-		}
-	} while (!all_done);
+	/* Now we're done all the checking - do the rehash:
+	 *  - extend match RTC size
+	 *  - create new matcher
+	 *  - move all the rules to the new matcher
+	 *  - destroy the old matcher
+	 */
+	atomic_set(&bwc_matcher->rx_size.rehash_required, false);
+	atomic_set(&bwc_matcher->tx_size.rehash_required, false);
 
-	/* drain all the bwc queues */
-	for (i = 0; i < bwc_queues; i++) {
-		if (pending_rules[i]) {
-			u16 queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
-
-			mlx5hws_send_engine_flush_queue(&ctx->send_queue[queue_id]);
-			ret = hws_bwc_queue_poll(ctx, queue_id,
-						 &pending_rules[i], true);
-			if (unlikely(ret))
-				goto free_bwc_rules;
-		}
+	if (need_rx_rehash) {
+		ret = hws_bwc_matcher_extend_size(bwc_matcher,
+						  &bwc_matcher->rx_size);
+		if (ret)
+			return ret;
 	}
 
-free_bwc_rules:
-	kfree(bwc_rules);
-free_pending_rules:
-	kfree(pending_rules);
-
-	return ret;
-}
+	if (need_tx_rehash) {
+		ret = hws_bwc_matcher_extend_size(bwc_matcher,
+						  &bwc_matcher->tx_size);
+		if (ret)
+			return ret;
+	}
 
-static int hws_bwc_matcher_move_all(struct mlx5hws_bwc_matcher *bwc_matcher)
-{
-	return hws_bwc_matcher_move_all_simple(bwc_matcher);
+	return hws_bwc_matcher_move(bwc_matcher);
 }
 
-static int hws_bwc_matcher_move(struct mlx5hws_bwc_matcher *bwc_matcher)
+static int hws_bwc_rule_get_at_idx(struct mlx5hws_bwc_rule *bwc_rule,
+				   struct mlx5hws_rule_action rule_actions[],
+				   u16 bwc_queue_idx)
 {
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
 	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
-	struct mlx5hws_matcher_attr matcher_attr = {0};
-	struct mlx5hws_matcher *old_matcher;
-	struct mlx5hws_matcher *new_matcher;
-	int ret;
+	struct mutex *queue_lock; /* Protect the queue */
+	int at_idx, ret;
 
-	hws_bwc_matcher_init_attr(&matcher_attr,
-				  bwc_matcher->priority,
-				  bwc_matcher->size_log);
+	/* check if rehash needed due to missing action template */
+	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	if (likely(at_idx >= 0))
+		return at_idx;
 
-	old_matcher = bwc_matcher->matcher;
-	new_matcher = mlx5hws_matcher_create(old_matcher->tbl,
-					     &bwc_matcher->mt, 1,
-					     bwc_matcher->at,
-					     bwc_matcher->num_of_at,
-					     &matcher_attr);
-	if (!new_matcher) {
-		mlx5hws_err(ctx, "Rehash error: matcher creation failed\n");
-		return -ENOMEM;
-	}
+	/* we need to extend BWC matcher action templates array */
+	queue_lock = hws_bwc_get_queue_lock(ctx, bwc_queue_idx);
+	mutex_unlock(queue_lock);
+	hws_bwc_lock_all_queues(ctx);
 
-	ret = mlx5hws_matcher_resize_set_target(old_matcher, new_matcher);
-	if (ret) {
-		mlx5hws_err(ctx, "Rehash error: failed setting resize target\n");
-		return ret;
+	/* check again - perhaps other thread already did extend_at */
+	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	if (at_idx >= 0)
+		goto out;
+
+	ret = hws_bwc_matcher_extend_at(bwc_matcher, rule_actions);
+	if (unlikely(ret)) {
+		mlx5hws_err(ctx, "BWC rule: failed extending AT (%d)", ret);
+		at_idx = -EINVAL;
+		goto out;
 	}
 
-	ret = hws_bwc_matcher_move_all(bwc_matcher);
-	if (ret) {
-		mlx5hws_err(ctx, "Rehash error: moving rules failed\n");
-		return -ENOMEM;
+	/* action templates array was extended, we need the last idx */
+	at_idx = bwc_matcher->num_of_at - 1;
+	ret = mlx5hws_matcher_attach_at(bwc_matcher->matcher,
+					bwc_matcher->at[at_idx]);
+	if (unlikely(ret)) {
+		mlx5hws_err(ctx, "BWC rule: failed attaching new AT (%d)", ret);
+		at_idx = -EINVAL;
+		goto out;
 	}
 
-	bwc_matcher->matcher = new_matcher;
-	mlx5hws_matcher_destroy(old_matcher);
+out:
+	hws_bwc_unlock_all_queues(ctx);
+	mutex_lock(queue_lock);
+	return at_idx;
+}
 
-	return 0;
+static void hws_bwc_rule_cnt_inc_rxtx(struct mlx5hws_bwc_rule *bwc_rule,
+				      struct mlx5hws_bwc_matcher_size *size)
+{
+	u32 num_of_rules = atomic_inc_return(&size->num_of_rules);
+
+	if (unlikely(hws_bwc_matcher_rehash_size_needed(bwc_rule->bwc_matcher,
+							size, num_of_rules)))
+		atomic_set(&size->rehash_required, true);
 }
 
-static int
-hws_bwc_matcher_rehash_size(struct mlx5hws_bwc_matcher *bwc_matcher)
+static void hws_bwc_rule_cnt_inc(struct mlx5hws_bwc_rule *bwc_rule)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+
+	if (!bwc_rule->skip_rx)
+		hws_bwc_rule_cnt_inc_rxtx(bwc_rule, &bwc_matcher->rx_size);
+	if (!bwc_rule->skip_tx)
+		hws_bwc_rule_cnt_inc_rxtx(bwc_rule, &bwc_matcher->tx_size);
+}
+
+static int hws_bwc_rule_cnt_inc_with_rehash(struct mlx5hws_bwc_rule *bwc_rule,
+					    u16 bwc_queue_idx)
 {
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mutex *queue_lock; /* Protect the queue */
 	int ret;
 
-	/* If the current matcher size is already at its max size, we can't
-	 * do the rehash. Skip it and try adding the rule again - perhaps
-	 * there was some change.
-	 */
-	if (hws_bwc_matcher_size_maxed_out(bwc_matcher))
-		return 0;
+	hws_bwc_rule_cnt_inc(bwc_rule);
 
-	/* It is possible that other rule has already performed rehash.
-	 * Need to check again if we really need rehash.
-	 * If the reason for rehash was size, but not any more - skip rehash.
-	 */
-	if (!hws_bwc_matcher_rehash_size_needed(bwc_matcher, bwc_matcher->num_of_rules))
+	if (!atomic_read(&bwc_matcher->rx_size.rehash_required) &&
+	    !atomic_read(&bwc_matcher->tx_size.rehash_required))
 		return 0;
 
-	/* Now we're done all the checking - do the rehash:
-	 *  - extend match RTC size
-	 *  - create new matcher
-	 *  - move all the rules to the new matcher
-	 *  - destroy the old matcher
-	 */
+	queue_lock = hws_bwc_get_queue_lock(ctx, bwc_queue_idx);
+	mutex_unlock(queue_lock);
 
-	ret = hws_bwc_matcher_extend_size(bwc_matcher);
-	if (ret)
-		return ret;
+	hws_bwc_lock_all_queues(ctx);
+	ret = hws_bwc_matcher_rehash_size(bwc_matcher);
+	hws_bwc_unlock_all_queues(ctx);
 
-	return hws_bwc_matcher_move(bwc_matcher);
-}
+	mutex_lock(queue_lock);
 
-static int
-hws_bwc_matcher_rehash_at(struct mlx5hws_bwc_matcher *bwc_matcher)
-{
-	/* Rehash by action template doesn't require any additional checking.
-	 * The bwc_matcher already contains the new action template.
-	 * Just do the usual rehash:
-	 *  - create new matcher
-	 *  - move all the rules to the new matcher
-	 *  - destroy the old matcher
-	 */
-	return hws_bwc_matcher_move(bwc_matcher);
+	if (likely(!ret))
+		return 0;
+
+	/* Failed to rehash. Print a diagnostic and rollback the counters. */
+	mlx5hws_err(ctx,
+		    "BWC rule insertion: rehash to sizes [%d, %d] failed (%d)\n",
+		    bwc_matcher->rx_size.size_log,
+		    bwc_matcher->tx_size.size_log, ret);
+	hws_bwc_rule_cnt_dec(bwc_rule);
+
+	return ret;
 }
 
 int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
@@ -744,7 +1031,6 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
 	struct mlx5hws_rule_attr rule_attr;
 	struct mutex *queue_lock; /* Protect the queue */
-	u32 num_of_rules;
 	int ret = 0;
 	int at_idx;
 
@@ -754,67 +1040,18 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 
 	mutex_lock(queue_lock);
 
-	/* check if rehash needed due to missing action template */
-	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	at_idx = hws_bwc_rule_get_at_idx(bwc_rule, rule_actions, bwc_queue_idx);
 	if (unlikely(at_idx < 0)) {
-		/* we need to extend BWC matcher action templates array */
 		mutex_unlock(queue_lock);
-		hws_bwc_lock_all_queues(ctx);
-
-		ret = hws_bwc_matcher_extend_at(bwc_matcher, rule_actions);
-		if (unlikely(ret)) {
-			hws_bwc_unlock_all_queues(ctx);
-			return ret;
-		}
-
-		/* action templates array was extended, we need the last idx */
-		at_idx = bwc_matcher->num_of_at - 1;
-
-		ret = mlx5hws_matcher_attach_at(bwc_matcher->matcher,
-						bwc_matcher->at[at_idx]);
-		if (unlikely(ret)) {
-			/* Action template attach failed, possibly due to
-			 * requiring more action STEs.
-			 * Need to attempt creating new matcher with all
-			 * the action templates, including the new one.
-			 */
-			ret = hws_bwc_matcher_rehash_at(bwc_matcher);
-			if (unlikely(ret)) {
-				mlx5hws_action_template_destroy(bwc_matcher->at[at_idx]);
-				bwc_matcher->at[at_idx] = NULL;
-				bwc_matcher->num_of_at--;
-
-				hws_bwc_unlock_all_queues(ctx);
-
-				mlx5hws_err(ctx,
-					    "BWC rule insertion: rehash AT failed (%d)\n", ret);
-				return ret;
-			}
-		}
-
-		hws_bwc_unlock_all_queues(ctx);
-		mutex_lock(queue_lock);
+		mlx5hws_err(ctx, "BWC rule create: failed getting AT (%d)",
+			    ret);
+		return -EINVAL;
 	}
 
-	/* check if number of rules require rehash */
-	num_of_rules = bwc_matcher->num_of_rules;
-
-	if (unlikely(hws_bwc_matcher_rehash_size_needed(bwc_matcher, num_of_rules))) {
+	ret = hws_bwc_rule_cnt_inc_with_rehash(bwc_rule, bwc_queue_idx);
+	if (unlikely(ret)) {
 		mutex_unlock(queue_lock);
-
-		hws_bwc_lock_all_queues(ctx);
-		ret = hws_bwc_matcher_rehash_size(bwc_matcher);
-		hws_bwc_unlock_all_queues(ctx);
-
-		if (ret) {
-			mlx5hws_err(ctx, "BWC rule insertion: rehash size [%d -> %d] failed (%d)\n",
-				    bwc_matcher->size_log - MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP,
-				    bwc_matcher->size_log,
-				    ret);
-			return ret;
-		}
-
-		mutex_lock(queue_lock);
+		return ret;
 	}
 
 	ret = hws_bwc_rule_create_sync(bwc_rule,
@@ -828,12 +1065,29 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 		return 0; /* rule inserted successfully */
 	}
 
+	/* Rule insertion could fail due to queue being full, timeout, or
+	 * matcher in resize. In such cases, no point in trying to rehash.
+	 */
+	if (ret == -EBUSY || ret == -ETIMEDOUT || ret == -EAGAIN) {
+		mutex_unlock(queue_lock);
+		mlx5hws_err(ctx,
+			    "BWC rule insertion failed - %s (%d)\n",
+			    ret == -EBUSY ? "queue is full" :
+			    ret == -ETIMEDOUT ? "timeout" :
+			    ret == -EAGAIN ? "matcher in resize" : "N/A",
+			    ret);
+		hws_bwc_rule_cnt_dec(bwc_rule);
+		return ret;
+	}
+
 	/* At this point the rule wasn't added.
 	 * It could be because there was collision, or some other problem.
-	 * If we don't dive deeper than API, the only thing we know is that
-	 * the status of completion is RTE_FLOW_OP_ERROR.
 	 * Try rehash by size and insert rule again - last chance.
 	 */
+	if (!bwc_rule->skip_rx)
+		atomic_set(&bwc_matcher->rx_size.rehash_required, true);
+	if (!bwc_rule->skip_tx)
+		atomic_set(&bwc_matcher->tx_size.rehash_required, true);
 
 	mutex_unlock(queue_lock);
 
@@ -843,6 +1097,7 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 
 	if (ret) {
 		mlx5hws_err(ctx, "BWC rule insertion: rehash failed (%d)\n", ret);
+		hws_bwc_rule_cnt_dec(bwc_rule);
 		return ret;
 	}
 
@@ -858,6 +1113,7 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 	if (unlikely(ret)) {
 		mutex_unlock(queue_lock);
 		mlx5hws_err(ctx, "BWC rule insertion failed (%d)\n", ret);
+		hws_bwc_rule_cnt_dec(bwc_rule);
 		return ret;
 	}
 
@@ -887,13 +1143,24 @@ mlx5hws_bwc_rule_create(struct mlx5hws_bwc_matcher *bwc_matcher,
 	if (unlikely(!bwc_rule))
 		return NULL;
 
+	bwc_rule->flow_source = flow_source;
+	mlx5hws_rule_skip(bwc_matcher->matcher, flow_source,
+			  &bwc_rule->skip_rx, &bwc_rule->skip_tx);
+
 	bwc_queue_idx = hws_bwc_gen_queue_idx(ctx);
 
-	ret = mlx5hws_bwc_rule_create_simple(bwc_rule,
-					     params->match_buf,
-					     rule_actions,
-					     flow_source,
-					     bwc_queue_idx);
+	if (bwc_matcher->matcher_type == MLX5HWS_BWC_MATCHER_COMPLEX_FIRST)
+		ret = mlx5hws_bwc_rule_create_complex(bwc_rule,
+						      params,
+						      flow_source,
+						      rule_actions,
+						      bwc_queue_idx);
+	else
+		ret = mlx5hws_bwc_rule_create_simple(bwc_rule,
+						     params->match_buf,
+						     rule_actions,
+						     flow_source,
+						     bwc_queue_idx);
 	if (unlikely(ret)) {
 		mlx5hws_bwc_rule_free(bwc_rule);
 		return NULL;
@@ -915,57 +1182,17 @@ hws_bwc_rule_action_update(struct mlx5hws_bwc_rule *bwc_rule,
 
 	idx = bwc_rule->bwc_queue_idx;
 
-	mlx5hws_bwc_rule_fill_attr(bwc_matcher, idx, 0, &rule_attr);
+	mlx5hws_bwc_rule_fill_attr(bwc_matcher, idx, bwc_rule->flow_source,
+				   &rule_attr);
 	queue_lock = hws_bwc_get_queue_lock(ctx, idx);
 
 	mutex_lock(queue_lock);
 
-	/* check if rehash needed due to missing action template */
-	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	at_idx = hws_bwc_rule_get_at_idx(bwc_rule, rule_actions, idx);
 	if (unlikely(at_idx < 0)) {
-		/* we need to extend BWC matcher action templates array */
 		mutex_unlock(queue_lock);
-		hws_bwc_lock_all_queues(ctx);
-
-		/* check again - perhaps other thread already did extend_at */
-		at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
-		if (likely(at_idx < 0)) {
-			ret = hws_bwc_matcher_extend_at(bwc_matcher, rule_actions);
-			if (unlikely(ret)) {
-				hws_bwc_unlock_all_queues(ctx);
-				mlx5hws_err(ctx, "BWC rule update: failed extending AT (%d)", ret);
-				return -EINVAL;
-			}
-
-			/* action templates array was extended, we need the last idx */
-			at_idx = bwc_matcher->num_of_at - 1;
-
-			ret = mlx5hws_matcher_attach_at(bwc_matcher->matcher,
-							bwc_matcher->at[at_idx]);
-			if (unlikely(ret)) {
-				/* Action template attach failed, possibly due to
-				 * requiring more action STEs.
-				 * Need to attempt creating new matcher with all
-				 * the action templates, including the new one.
-				 */
-				ret = hws_bwc_matcher_rehash_at(bwc_matcher);
-				if (unlikely(ret)) {
-					mlx5hws_action_template_destroy(bwc_matcher->at[at_idx]);
-					bwc_matcher->at[at_idx] = NULL;
-					bwc_matcher->num_of_at--;
-
-					hws_bwc_unlock_all_queues(ctx);
-
-					mlx5hws_err(ctx,
-						    "BWC rule update: rehash AT failed (%d)\n",
-						    ret);
-					return ret;
-				}
-			}
-		}
-
-		hws_bwc_unlock_all_queues(ctx);
-		mutex_lock(queue_lock);
+		mlx5hws_err(ctx, "BWC rule update: failed getting AT\n");
+		return -EINVAL;
 	}
 
 	ret = hws_bwc_rule_update_sync(bwc_rule,
@@ -991,5 +1218,9 @@ int mlx5hws_bwc_rule_action_update(struct mlx5hws_bwc_rule *bwc_rule,
 		return -EINVAL;
 	}
 
+	/* For complex rules, the update should happen on the last subrule. */
+	while (bwc_rule->next_subrule)
+		bwc_rule = bwc_rule->next_subrule;
+
 	return hws_bwc_rule_action_update(bwc_rule, rule_actions);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
index 0b745968e21e..b905511f5c53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
@@ -8,25 +8,62 @@
 #define MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP 1
 #define MLX5HWS_BWC_MATCHER_REHASH_PERCENT_TH 70
 #define MLX5HWS_BWC_MATCHER_REHASH_BURST_TH 32
-#define MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM 255
+
+/* Max number of AT attach operations for the same matcher.
+ * When the limit is reached, a larger buffer is allocated for the ATs.
+ */
+#define MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM 8
 
 #define MLX5HWS_BWC_MAX_ACTS 16
 
+#define MLX5HWS_BWC_POLLING_TIMEOUT 60
+
+enum mlx5hws_bwc_matcher_type {
+	/* Standalone bwc matcher. */
+	MLX5HWS_BWC_MATCHER_SIMPLE,
+	/* The first matcher of a complex matcher. When rules are inserted into
+	 * a matcher of this type, they are split into subrules and inserted
+	 * into their corresponding submatchers.
+	 */
+	MLX5HWS_BWC_MATCHER_COMPLEX_FIRST,
+	/* A submatcher that is part of a complex matcher. For most purposes
+	 * these are treated as simple matchers, except when it comes to moving
+	 * rules during resize.
+	 */
+	MLX5HWS_BWC_MATCHER_COMPLEX_SUBMATCHER,
+};
+
+struct mlx5hws_bwc_matcher_complex_data;
+
+struct mlx5hws_bwc_matcher_size {
+	u8 size_log;
+	atomic_t num_of_rules;
+	atomic_t rehash_required;
+};
+
 struct mlx5hws_bwc_matcher {
 	struct mlx5hws_matcher *matcher;
 	struct mlx5hws_match_template *mt;
-	struct mlx5hws_action_template *at[MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM];
+	struct mlx5hws_action_template **at;
+	struct mlx5hws_bwc_matcher_complex_data *complex;
 	u8 num_of_at;
-	u16 priority;
-	u8 size_log;
-	u32 num_of_rules; /* atomically accessed */
+	u8 size_of_at_array;
+	enum mlx5hws_bwc_matcher_type matcher_type;
+	u32 priority;
+	struct mlx5hws_bwc_matcher_size rx_size;
+	struct mlx5hws_bwc_matcher_size tx_size;
 	struct list_head *rules;
 };
 
 struct mlx5hws_bwc_rule {
 	struct mlx5hws_bwc_matcher *bwc_matcher;
 	struct mlx5hws_rule *rule;
+	struct mlx5hws_bwc_rule *next_subrule;
+	struct mlx5hws_bwc_complex_subrule_data *subrule_data;
+	u32 flow_source;
 	u16 bwc_queue_idx;
+	bool skip_rx;
+	bool skip_tx;
 	struct list_head list_node;
 };
 
@@ -57,12 +94,19 @@ void mlx5hws_bwc_rule_fill_attr(struct mlx5hws_bwc_matcher *bwc_matcher,
 				u32 flow_source,
 				struct mlx5hws_rule_attr *rule_attr);
 
+int mlx5hws_bwc_queue_poll(struct mlx5hws_context *ctx,
+			   u16 queue_id,
+			   u32 *pending_rules,
+			   bool drain);
+
 static inline u16 mlx5hws_bwc_queues(struct mlx5hws_context *ctx)
 {
 	/* Besides the control queue, half of the queues are
-	 * reguler HWS queues, and the other half are BWC queues.
+	 * regular HWS queues, and the other half are BWC queues.
 	 */
-	return (ctx->queues - 1) / 2;
+	if (mlx5hws_context_bwc_supported(ctx))
+		return (ctx->queues - 1) / 2;
+	return 0;
 }
 
 static inline u16 mlx5hws_bwc_get_queue_id(struct mlx5hws_context *ctx, u16 idx)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
index 9fb059a6511f..660630f18ce9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
@@ -3,9 +3,27 @@
 
 #include "internal.h"
 
-bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
-					 u8 match_criteria_enable,
-					 struct mlx5hws_match_parameters *mask)
+/* We chain submatchers by applying three rules on a subrule: modify header (to
+ * set register C6), jump to table (to the next submatcher) and the mandatory
+ * last rule.
+ */
+#define HWS_NUM_CHAIN_ACTIONS 3
+
+static const struct rhashtable_params hws_rules_hash_params = {
+	.key_len = sizeof_field(struct mlx5hws_bwc_complex_subrule_data,
+				match_tag),
+	.key_offset =
+		offsetof(struct mlx5hws_bwc_complex_subrule_data, match_tag),
+	.head_offset =
+		offsetof(struct mlx5hws_bwc_complex_subrule_data, hash_node),
+	.automatic_shrinking = true, .min_size = 1,
+};
+
+static bool
+hws_match_params_exceeds_definer(struct mlx5hws_context *ctx,
+				 u8 match_criteria_enable,
+				 struct mlx5hws_match_parameters *mask,
+				 bool allow_jumbo)
 {
 	struct mlx5hws_definer match_layout = {0};
 	struct mlx5hws_match_template *mt;
@@ -20,11 +38,11 @@ bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
 					   mask->match_sz,
 					   match_criteria_enable);
 	if (!mt) {
-		mlx5hws_err(ctx, "BWC: failed creating match template\n");
+		mlx5hws_err(ctx, "Complex matcher: failed creating match template\n");
 		return false;
 	}
 
-	ret = mlx5hws_definer_calc_layout(ctx, mt, &match_layout);
+	ret = mlx5hws_definer_calc_layout(ctx, mt, &match_layout, allow_jumbo);
 	if (ret) {
 		/* The only case that we're interested in is E2BIG,
 		 * which means that the match parameters need to be
@@ -48,20 +66,766 @@ bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
 	return is_complex;
 }
 
+bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
+					 u8 match_criteria_enable,
+					 struct mlx5hws_match_parameters *mask)
+{
+	return hws_match_params_exceeds_definer(ctx, match_criteria_enable,
+						mask, true);
+}
+
+static int
+hws_get_last_set_dword_idx(const struct mlx5hws_match_parameters *mask)
+{
+	int i;
+
+	for (i = mask->match_sz / 4 - 1; i >= 0; i--)
+		if (mask->match_buf[i])
+			return i;
+
+	return -1;
+}
+
+static bool hws_match_mask_is_empty(const struct mlx5hws_match_parameters *mask)
+{
+	return hws_get_last_set_dword_idx(mask) == -1;
+}
+
+static bool hws_dword_is_inner_ipaddr_off(int dword_off)
+{
+	/* IPv4 and IPv6 addresses share the same entry via a union, and the
+	 * source and dest addresses are contiguous in the fte_match_param. So
+	 * we need to check 8 words.
+	 */
+	static const int inner_ip_dword_off =
+		__mlx5_dw_off(fte_match_param, inner_headers.src_ipv4_src_ipv6);
+
+	return dword_off >= inner_ip_dword_off &&
+	       dword_off < inner_ip_dword_off + 8;
+}
+
+static bool hws_dword_is_outer_ipaddr_off(int dword_off)
+{
+	static const int outer_ip_dword_off =
+		__mlx5_dw_off(fte_match_param, outer_headers.src_ipv4_src_ipv6);
+
+	return dword_off >= outer_ip_dword_off &&
+	       dword_off < outer_ip_dword_off + 8;
+}
+
+static void hws_add_dword_to_mask(struct mlx5hws_match_parameters *mask,
+				  const struct mlx5hws_match_parameters *orig,
+				  int dword_idx, bool *added_inner_ipv,
+				  bool *added_outer_ipv)
+{
+	mask->match_buf[dword_idx] |= orig->match_buf[dword_idx];
+
+	*added_inner_ipv = false;
+	*added_outer_ipv = false;
+
+	/* Any IP address fragment must be accompanied by a match on IP version.
+	 * Use the `added_ipv` variables to keep track if we added IP versions
+	 * specifically for this dword, so that we can roll them back if the
+	 * match params become too large to fit into a definer.
+	 */
+	if (hws_dword_is_inner_ipaddr_off(dword_idx) &&
+	    !MLX5_GET(fte_match_param, mask->match_buf,
+		      inner_headers.ip_version)) {
+		MLX5_SET(fte_match_param, mask->match_buf,
+			 inner_headers.ip_version, 0xf);
+		*added_inner_ipv = true;
+	}
+	if (hws_dword_is_outer_ipaddr_off(dword_idx) &&
+	    !MLX5_GET(fte_match_param, mask->match_buf,
+		      outer_headers.ip_version)) {
+		MLX5_SET(fte_match_param, mask->match_buf,
+			 outer_headers.ip_version, 0xf);
+		*added_outer_ipv = true;
+	}
+}
+
+static void hws_remove_dword_from_mask(struct mlx5hws_match_parameters *mask,
+				       int dword_idx, bool added_inner_ipv,
+				       bool added_outer_ipv)
+{
+	mask->match_buf[dword_idx] = 0;
+	if (added_inner_ipv)
+		MLX5_SET(fte_match_param, mask->match_buf,
+			 inner_headers.ip_version, 0);
+	if (added_outer_ipv)
+		MLX5_SET(fte_match_param, mask->match_buf,
+			 outer_headers.ip_version, 0);
+}
+
+/* Avoid leaving a single lower dword in `mask` if there are others present in
+ * `orig`. Splitting IPv6 addresses like this causes them to be interpreted as
+ * IPv4.
+ */
+static void hws_avoid_ipv6_split_of(struct mlx5hws_match_parameters *orig,
+				    struct mlx5hws_match_parameters *mask,
+				    int off)
+{
+	/* Masks are allocated to a full fte_match_param, but it can't hurt to
+	 * double check.
+	 */
+	if (orig->match_sz <= off + 3 || mask->match_sz <= off + 3)
+		return;
+
+	/* Lower dword is not set, nothing to do. */
+	if (!mask->match_buf[off + 3])
+		return;
+
+	/* Higher dwords also present in `mask`, no ambiguity. */
+	if (mask->match_buf[off] || mask->match_buf[off + 1] ||
+	    mask->match_buf[off + 2])
+		return;
+
+	/* There are no higher dwords in `orig`, i.e. we match on IPv4. */
+	if (!orig->match_buf[off] && !orig->match_buf[off + 1] &&
+	    !orig->match_buf[off + 2])
+		return;
+
+	/* Put the lower dword back in `orig`. It is always safe to do this, the
+	 * dword will just be picked up in the next submask.
+	 */
+	orig->match_buf[off + 3] = mask->match_buf[off + 3];
+	mask->match_buf[off + 3] = 0;
+}
+
+static void hws_avoid_ipv6_split(struct mlx5hws_match_parameters *orig,
+				 struct mlx5hws_match_parameters *mask)
+{
+	hws_avoid_ipv6_split_of(orig, mask,
+				__mlx5_dw_off(fte_match_param,
+					      outer_headers.src_ipv4_src_ipv6));
+	hws_avoid_ipv6_split_of(orig, mask,
+				__mlx5_dw_off(fte_match_param,
+					      outer_headers.dst_ipv4_dst_ipv6));
+	hws_avoid_ipv6_split_of(orig, mask,
+				__mlx5_dw_off(fte_match_param,
+					      inner_headers.src_ipv4_src_ipv6));
+	hws_avoid_ipv6_split_of(orig, mask,
+				__mlx5_dw_off(fte_match_param,
+					      inner_headers.dst_ipv4_dst_ipv6));
+}
+
+/* Build a subset of the `orig` match parameters into `mask`. This subset is
+ * guaranteed to fit in a single definer an as such is a candidate for being a
+ * part of a complex matcher. Upon successful execution, the match params that
+ * go into `mask` are cleared from `orig`.
+ */
+static int hws_get_simple_params(struct mlx5hws_context *ctx, u8 match_criteria,
+				 struct mlx5hws_match_parameters *orig,
+				 struct mlx5hws_match_parameters *mask)
+{
+	bool added_inner_ipv, added_outer_ipv;
+	int dword_idx;
+	u32 *backup;
+	int ret;
+
+	dword_idx = hws_get_last_set_dword_idx(orig);
+	/* Nothing to do, we consumed all of the match params before. */
+	if (dword_idx == -1)
+		return 0;
+
+	backup = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
+	if (!backup)
+		return -ENOMEM;
+
+	while (1) {
+		dword_idx = hws_get_last_set_dword_idx(orig);
+		/* Nothing to do, we consumed all of the original match params
+		 * into this subset, which still fits into a single matcher.
+		 */
+		if (dword_idx == -1) {
+			ret = 0;
+			goto free_backup;
+		}
+
+		memcpy(backup, mask->match_buf, mask->match_sz);
+
+		/* Try to add this dword to the current subset. */
+		hws_add_dword_to_mask(mask, orig, dword_idx, &added_inner_ipv,
+				      &added_outer_ipv);
+
+		if (hws_match_params_exceeds_definer(ctx, match_criteria, mask,
+						     false)) {
+			/* We just added a match param that makes the definer
+			 * too large. Revert and return what we had before.
+			 * Note that we can't just zero out the affected fields,
+			 * because it's possible that the dword we're looking at
+			 * wasn't zero before (e.g. it included auto-added
+			 * matches in IP version. This is why we employ the
+			 * rather cumbersome memcpy for backing up.
+			 */
+			memcpy(mask->match_buf, backup, mask->match_sz);
+			/* Possible future improvement: We can't add any more
+			 * dwords, but it may be possible to squeeze in
+			 * individual bytes, as definers have special slots for
+			 * those.
+			 *
+			 * For now, keep the code simple. This results in an
+			 * extra submatcher in some cases, but it's good enough.
+			 */
+			ret = 0;
+			break;
+		}
+
+		/* The current subset of match params still fits in a single
+		 * definer. Remove the dword from the original mask.
+		 *
+		 * Also remove any explicit match on IP version if we just
+		 * included one here. We will still automatically add it to
+		 * accompany any IP address fragment, but do not need to
+		 * consider it by itself.
+		 */
+		hws_remove_dword_from_mask(orig, dword_idx, added_inner_ipv,
+					   added_outer_ipv);
+	}
+
+	/* Make sure we have not picked up a single lower dword of an IPv6
+	 * address, as the firmware will erroneously treat it as an IPv4
+	 * address.
+	 */
+	hws_avoid_ipv6_split(orig, mask);
+
+free_backup:
+	kfree(backup);
+
+	return ret;
+}
+
+static int
+hws_bwc_matcher_split_mask(struct mlx5hws_context *ctx, u8 match_criteria,
+			   const struct mlx5hws_match_parameters *mask,
+			   struct mlx5hws_match_parameters *submasks,
+			   int *num_submasks)
+{
+	struct mlx5hws_match_parameters mask_copy;
+	int ret, i = 0;
+
+	mask_copy.match_sz = MLX5_ST_SZ_BYTES(fte_match_param);
+	mask_copy.match_buf = kzalloc(mask_copy.match_sz, GFP_KERNEL);
+	if (!mask_copy.match_buf)
+		return -ENOMEM;
+
+	memcpy(mask_copy.match_buf, mask->match_buf, mask->match_sz);
+
+	while (!hws_match_mask_is_empty(&mask_copy)) {
+		if (i >= MLX5HWS_BWC_COMPLEX_MAX_SUBMATCHERS) {
+			mlx5hws_err(ctx,
+				    "Complex matcher: mask too large for %d matchers\n",
+				    MLX5HWS_BWC_COMPLEX_MAX_SUBMATCHERS);
+			ret = -E2BIG;
+			goto free_copy;
+		}
+		/* All but the first matcher need to match on register C6 to
+		 * connect pieces of the complex rule together.
+		 */
+		if (i > 0) {
+			MLX5_SET(fte_match_param, submasks[i].match_buf,
+				 misc_parameters_2.metadata_reg_c_6, -1);
+			match_criteria |= MLX5HWS_DEFINER_MATCH_CRITERIA_MISC2;
+		}
+		ret = hws_get_simple_params(ctx, match_criteria, &mask_copy,
+					    &submasks[i]);
+		if (ret < 0)
+			goto free_copy;
+		i++;
+	}
+
+	*num_submasks = i;
+	ret = 0;
+
+free_copy:
+	kfree(mask_copy.match_buf);
+
+	return ret;
+}
+
+static struct mlx5hws_table *
+hws_isolated_table_create(const struct mlx5hws_bwc_matcher *cmatcher)
+{
+	struct mlx5hws_bwc_complex_submatcher *first_subm;
+	struct mlx5hws_cmd_ft_modify_attr ft_attr = {0};
+	struct mlx5hws_table_attr tbl_attr = {0};
+	struct mlx5hws_table *orig_tbl;
+	struct mlx5hws_context *ctx;
+	struct mlx5hws_table *tbl;
+	int ret;
+
+	first_subm = &cmatcher->complex->submatchers[0];
+	orig_tbl = first_subm->tbl;
+	ctx = orig_tbl->ctx;
+
+	tbl_attr.type = orig_tbl->type;
+	tbl_attr.level = orig_tbl->level;
+	tbl = mlx5hws_table_create(ctx, &tbl_attr);
+	if (!tbl)
+		return ERR_PTR(-EINVAL);
+
+	/* Set the default miss of the isolated table to point
+	 * to the end anchor of the original matcher.
+	 */
+	mlx5hws_cmd_set_attr_connect_miss_tbl(ctx, tbl->fw_ft_type,
+					      tbl->type, &ft_attr);
+	ft_attr.table_miss_id = first_subm->bwc_matcher->matcher->end_ft_id;
+
+	ret = mlx5hws_cmd_flow_table_modify(ctx->mdev, &ft_attr, tbl->ft_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Complex matcher: failed to set isolated tbl default miss\n");
+		goto destroy_tbl;
+	}
+
+	return tbl;
+
+destroy_tbl:
+	mlx5hws_table_destroy(tbl);
+
+	return ERR_PTR(ret);
+}
+
+static int hws_submatcher_init_first(struct mlx5hws_bwc_matcher *cmatcher,
+				     struct mlx5hws_table *table, u32 priority,
+				     u8 match_criteria,
+				     struct mlx5hws_match_parameters *mask)
+{
+	enum mlx5hws_action_type action_types[HWS_NUM_CHAIN_ACTIONS];
+	struct mlx5hws_bwc_complex_submatcher *subm;
+	int ret;
+
+	subm = &cmatcher->complex->submatchers[0];
+
+	/* The first submatcher lives in the original table and does not have an
+	 * associated jump to table action. It also points to the outer complex
+	 * matcher.
+	 */
+	subm->tbl = table;
+	subm->action_tbl = NULL;
+	subm->bwc_matcher = cmatcher;
+
+	action_types[0] = MLX5HWS_ACTION_TYP_MODIFY_HDR;
+	action_types[1] = MLX5HWS_ACTION_TYP_TBL;
+	action_types[2] = MLX5HWS_ACTION_TYP_LAST;
+
+	ret = mlx5hws_bwc_matcher_create_simple(subm->bwc_matcher, subm->tbl,
+						priority, match_criteria, mask,
+						action_types);
+	if (ret)
+		return ret;
+
+	subm->bwc_matcher->matcher_type = MLX5HWS_BWC_MATCHER_COMPLEX_FIRST;
+
+	ret = rhashtable_init(&subm->rules_hash, &hws_rules_hash_params);
+	if (ret)
+		goto destroy_matcher;
+	mutex_init(&subm->hash_lock);
+	ida_init(&subm->chain_ida);
+
+	return 0;
+
+destroy_matcher:
+	mlx5hws_bwc_matcher_destroy_simple(subm->bwc_matcher);
+
+	return ret;
+}
+
+static int hws_submatcher_init(struct mlx5hws_bwc_matcher *cmatcher, int idx,
+			       struct mlx5hws_table *table, u32 priority,
+			       u8 match_criteria,
+			       struct mlx5hws_match_parameters *mask)
+{
+	enum mlx5hws_action_type action_types[HWS_NUM_CHAIN_ACTIONS];
+	struct mlx5hws_bwc_complex_submatcher *subm;
+	bool is_last;
+	int ret;
+
+	if (!idx)
+		return hws_submatcher_init_first(cmatcher, table, priority,
+						 match_criteria, mask);
+
+	subm = &cmatcher->complex->submatchers[idx];
+	is_last = idx == cmatcher->complex->num_submatchers - 1;
+
+	subm->tbl = hws_isolated_table_create(cmatcher);
+	if (IS_ERR(subm->tbl))
+		return PTR_ERR(subm->tbl);
+
+	subm->action_tbl =
+		mlx5hws_action_create_dest_table(subm->tbl->ctx, subm->tbl,
+						 MLX5HWS_ACTION_FLAG_HWS_FDB);
+	if (!subm->action_tbl) {
+		ret = -EINVAL;
+		goto destroy_tbl;
+	}
+
+	subm->bwc_matcher = kzalloc(sizeof(*subm->bwc_matcher), GFP_KERNEL);
+	if (!subm->bwc_matcher) {
+		ret = -ENOMEM;
+		goto destroy_action;
+	}
+
+	/* Every matcher other than the first also matches of register C6 to
+	 * bind subrules together in the complex rule using the chain ids.
+	 */
+	match_criteria |= MLX5HWS_DEFINER_MATCH_CRITERIA_MISC2;
+
+	action_types[0] = MLX5HWS_ACTION_TYP_MODIFY_HDR;
+	action_types[1] = MLX5HWS_ACTION_TYP_TBL;
+	action_types[2] = MLX5HWS_ACTION_TYP_LAST;
+
+	/* Every matcher other than the last sets register C6 and jumps to the
+	 * next submatcher's table. The final submatcher will use the
+	 * user-supplied actions and will attach an action template at rule
+	 * insertion time.
+	 */
+	ret = mlx5hws_bwc_matcher_create_simple(subm->bwc_matcher, subm->tbl,
+						priority, match_criteria, mask,
+						is_last ? NULL : action_types);
+	if (ret)
+		goto free_matcher;
+
+	subm->bwc_matcher->matcher_type =
+		MLX5HWS_BWC_MATCHER_COMPLEX_SUBMATCHER;
+
+	ret = rhashtable_init(&subm->rules_hash, &hws_rules_hash_params);
+	if (ret)
+		goto destroy_matcher;
+	mutex_init(&subm->hash_lock);
+	ida_init(&subm->chain_ida);
+
+	return 0;
+
+destroy_matcher:
+	mlx5hws_bwc_matcher_destroy_simple(subm->bwc_matcher);
+free_matcher:
+	kfree(subm->bwc_matcher);
+destroy_action:
+	mlx5hws_action_destroy(subm->action_tbl);
+destroy_tbl:
+	mlx5hws_table_destroy(subm->tbl);
+
+	return ret;
+}
+
+static void hws_submatcher_destroy(struct mlx5hws_bwc_matcher *cmatcher,
+				   int idx)
+{
+	struct mlx5hws_bwc_complex_submatcher *subm;
+
+	subm = &cmatcher->complex->submatchers[idx];
+
+	ida_destroy(&subm->chain_ida);
+	mutex_destroy(&subm->hash_lock);
+	rhashtable_destroy(&subm->rules_hash);
+
+	if (subm->bwc_matcher) {
+		mlx5hws_bwc_matcher_destroy_simple(subm->bwc_matcher);
+		if (idx)
+			kfree(subm->bwc_matcher);
+	}
+
+	/* We own all of the isolated tables, but not the original one. */
+	if (idx) {
+		mlx5hws_action_destroy(subm->action_tbl);
+		mlx5hws_table_destroy(subm->tbl);
+	}
+}
+
+static int
+hws_complex_data_actions_init(struct mlx5hws_bwc_matcher_complex_data *cdata)
+{
+	struct mlx5hws_context *ctx = cdata->submatchers[0].tbl->ctx;
+	u8 modify_hdr_action[MLX5_ST_SZ_BYTES(set_action_in)] = {0};
+	struct mlx5hws_action_mh_pattern ptrn;
+	int ret = 0;
+
+	/* Create modify header action to set REG_C_6 */
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 action_type, MLX5_MODIFICATION_TYPE_SET);
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 field, MLX5_MODI_META_REG_C_6);
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 length, 0); /* zero means length of 32 */
+	MLX5_SET(set_action_in, modify_hdr_action, offset, 0);
+	MLX5_SET(set_action_in, modify_hdr_action, data, 0);
+
+	ptrn.data = (void *)modify_hdr_action;
+	ptrn.sz = MLX5HWS_ACTION_DOUBLE_SIZE;
+
+	cdata->action_metadata =
+		mlx5hws_action_create_modify_header(ctx, 1, &ptrn, 0,
+						    MLX5HWS_ACTION_FLAG_HWS_FDB);
+	if (!cdata->action_metadata) {
+		mlx5hws_err(ctx, "Complex matcher: failed to create set reg C6 action\n");
+		return -EINVAL;
+	}
+
+	/* Create last action */
+	cdata->action_last =
+		mlx5hws_action_create_last(ctx, MLX5HWS_ACTION_FLAG_HWS_FDB);
+	if (!cdata->action_last) {
+		mlx5hws_err(ctx, "Complex matcher: failed to create last action\n");
+		ret = -EINVAL;
+		goto destroy_action_metadata;
+	}
+
+	return 0;
+
+destroy_action_metadata:
+	mlx5hws_action_destroy(cdata->action_metadata);
+
+	return ret;
+}
+
+static void
+hws_complex_data_actions_destroy(struct mlx5hws_bwc_matcher_complex_data *cdata)
+{
+	mlx5hws_action_destroy(cdata->action_last);
+	mlx5hws_action_destroy(cdata->action_metadata);
+}
+
 int mlx5hws_bwc_matcher_create_complex(struct mlx5hws_bwc_matcher *bwc_matcher,
 				       struct mlx5hws_table *table,
-				       u32 priority,
-				       u8 match_criteria_enable,
+				       u32 priority, u8 match_criteria_enable,
 				       struct mlx5hws_match_parameters *mask)
 {
-	mlx5hws_err(table->ctx, "Complex matcher is not supported yet\n");
-	return -EOPNOTSUPP;
+	struct mlx5hws_match_parameters
+		submasks[MLX5HWS_BWC_COMPLEX_MAX_SUBMATCHERS] = {0};
+	struct mlx5hws_bwc_matcher_complex_data *cdata;
+	struct mlx5hws_context *ctx = table->ctx;
+	int num_submatchers;
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(submasks); i++) {
+		submasks[i].match_sz = MLX5_ST_SZ_BYTES(fte_match_param);
+		submasks[i].match_buf = kzalloc(submasks[i].match_sz,
+						GFP_KERNEL);
+		if (!submasks[i].match_buf) {
+			ret = -ENOMEM;
+			goto free_submasks;
+		}
+	}
+
+	ret = hws_bwc_matcher_split_mask(ctx, match_criteria_enable, mask,
+					 submasks, &num_submatchers);
+	if (ret)
+		goto free_submasks;
+
+	cdata = kzalloc(sizeof(*cdata), GFP_KERNEL);
+	if (!cdata) {
+		ret = -ENOMEM;
+		goto free_submasks;
+	}
+
+	bwc_matcher->complex = cdata;
+	cdata->num_submatchers = num_submatchers;
+
+	for (i = 0; i < num_submatchers; i++) {
+		ret = hws_submatcher_init(bwc_matcher, i, table, priority,
+					  match_criteria_enable, &submasks[i]);
+		if (ret)
+			goto destroy_submatchers;
+	}
+
+	ret = hws_complex_data_actions_init(cdata);
+	if (ret)
+		goto destroy_submatchers;
+
+	ret = 0;
+	goto free_submasks;
+
+destroy_submatchers:
+	while (i--)
+		hws_submatcher_destroy(bwc_matcher, i);
+	kfree(cdata);
+	bwc_matcher->complex = NULL;
+
+free_submasks:
+	for (i = 0; i < ARRAY_SIZE(submasks); i++)
+		kfree(submasks[i].match_buf);
+
+	return ret;
 }
 
 void
 mlx5hws_bwc_matcher_destroy_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
-	/* nothing to do here */
+	int i;
+
+	hws_complex_data_actions_destroy(bwc_matcher->complex);
+	for (i = 0; i < bwc_matcher->complex->num_submatchers; i++)
+		hws_submatcher_destroy(bwc_matcher, i);
+	kfree(bwc_matcher->complex);
+	bwc_matcher->complex = NULL;
+}
+
+static int
+hws_complex_get_subrule_data(struct mlx5hws_bwc_rule *bwc_rule,
+			     struct mlx5hws_bwc_complex_submatcher *subm,
+			     u32 *match_params)
+__must_hold(&subm->hash_lock)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = subm->bwc_matcher;
+	struct mlx5hws_bwc_complex_subrule_data *sr_data, *old_data;
+	struct mlx5hws_match_template *mt;
+	int ret;
+
+	sr_data = kzalloc(sizeof(*sr_data), GFP_KERNEL);
+	if (!sr_data)
+		return -ENOMEM;
+
+	ret = ida_alloc(&subm->chain_ida, GFP_KERNEL);
+	if (ret < 0)
+		goto free_sr_data;
+	sr_data->chain_id = ret;
+
+	refcount_set(&sr_data->refcount, 1);
+
+	mt  = bwc_matcher->matcher->mt;
+	mlx5hws_definer_create_tag(match_params, mt->fc, mt->fc_sz,
+				   (u8 *)&sr_data->match_tag);
+
+	old_data = rhashtable_lookup_get_insert_fast(&subm->rules_hash,
+						     &sr_data->hash_node,
+						     hws_rules_hash_params);
+	if (IS_ERR(old_data)) {
+		ret = PTR_ERR(old_data);
+		goto free_ida;
+	}
+
+	if (old_data) {
+		/* Rule with the same tag already exists - update refcount */
+		refcount_inc(&old_data->refcount);
+		/* Let the new rule use the same tag as the existing rule.
+		 * Note that we don't have any indication for the rule creation
+		 * process that a rule with similar matching params already
+		 * exists - no harm done when this rule is be overwritten by
+		 * the same STE.
+		 * There's some performance advantage in skipping such cases,
+		 * so this is left for future optimizations.
+		 */
+		bwc_rule->subrule_data = old_data;
+		ret = 0;
+		goto free_ida;
+	}
+
+	bwc_rule->subrule_data = sr_data;
+	return 0;
+
+free_ida:
+	ida_free(&subm->chain_ida, sr_data->chain_id);
+free_sr_data:
+	kfree(sr_data);
+
+	return ret;
+}
+
+static void
+hws_complex_put_subrule_data(struct mlx5hws_bwc_rule *bwc_rule,
+			     struct mlx5hws_bwc_complex_submatcher *subm,
+			     bool *is_last_rule)
+__must_hold(&subm->hash_lock)
+{
+	struct mlx5hws_bwc_complex_subrule_data *sr_data;
+
+	if (is_last_rule)
+		*is_last_rule = false;
+
+	sr_data = bwc_rule->subrule_data;
+	if (refcount_dec_and_test(&sr_data->refcount)) {
+		rhashtable_remove_fast(&subm->rules_hash,
+				       &sr_data->hash_node,
+				       hws_rules_hash_params);
+		ida_free(&subm->chain_ida, sr_data->chain_id);
+		kfree(sr_data);
+		if (is_last_rule)
+			*is_last_rule = true;
+	}
+
+	bwc_rule->subrule_data = NULL;
+}
+
+static int hws_complex_subrule_create(struct mlx5hws_bwc_matcher *cmatcher,
+				      struct mlx5hws_bwc_rule *subrule,
+				      u32 *match_params, u32 flow_source,
+				      int bwc_queue_idx, int subm_idx,
+				      struct mlx5hws_rule_action *actions,
+				      u32 *chain_id)
+{
+	struct mlx5hws_rule_action chain_actions[HWS_NUM_CHAIN_ACTIONS] = {0};
+	u8 modify_hdr_action[MLX5_ST_SZ_BYTES(set_action_in)] = {0};
+	struct mlx5hws_bwc_matcher_complex_data *cdata;
+	struct mlx5hws_bwc_complex_submatcher *subm;
+	int ret;
+
+	cdata = cmatcher->complex;
+	subm = &cdata->submatchers[subm_idx];
+
+	mutex_lock(&subm->hash_lock);
+
+	ret = hws_complex_get_subrule_data(subrule, subm, match_params);
+	if (ret)
+		goto unlock;
+
+	*chain_id = subrule->subrule_data->chain_id;
+
+	if (!actions) {
+		MLX5_SET(set_action_in, modify_hdr_action, data, *chain_id);
+		chain_actions[0].action = cdata->action_metadata;
+		chain_actions[0].modify_header.data = modify_hdr_action;
+		chain_actions[1].action =
+			cdata->submatchers[subm_idx + 1].action_tbl;
+		chain_actions[2].action = cdata->action_last;
+		actions = chain_actions;
+	}
+
+	ret = mlx5hws_bwc_rule_create_simple(subrule, match_params, actions,
+					     flow_source, bwc_queue_idx);
+	if (ret)
+		goto put_subrule_data;
+
+	ret = 0;
+	goto unlock;
+
+put_subrule_data:
+	hws_complex_put_subrule_data(subrule, subm, NULL);
+unlock:
+	mutex_unlock(&subm->hash_lock);
+
+	return ret;
+}
+
+static int hws_complex_subrule_destroy(struct mlx5hws_bwc_rule *bwc_rule,
+				       struct mlx5hws_bwc_matcher *cmatcher,
+				       int subm_idx)
+{
+	struct mlx5hws_bwc_matcher_complex_data *cdata;
+	struct mlx5hws_bwc_complex_submatcher *subm;
+	struct mlx5hws_context *ctx;
+	bool is_last_rule;
+	int ret = 0;
+
+	cdata = cmatcher->complex;
+	subm = &cdata->submatchers[subm_idx];
+	ctx = subm->tbl->ctx;
+
+	mutex_lock(&subm->hash_lock);
+
+	hws_complex_put_subrule_data(bwc_rule, subm, &is_last_rule);
+	bwc_rule->rule->skip_delete = !is_last_rule;
+	ret = mlx5hws_bwc_rule_destroy_simple(bwc_rule);
+	if (unlikely(ret))
+		mlx5hws_err(ctx,
+			    "Complex rule: failed to delete subrule %d (%d)\n",
+			    subm_idx, ret);
+
+	if (subm_idx)
+		mlx5hws_bwc_rule_free(bwc_rule);
+
+	mutex_unlock(&subm->hash_lock);
+
+	return ret;
 }
 
 int mlx5hws_bwc_rule_create_complex(struct mlx5hws_bwc_rule *bwc_rule,
@@ -70,19 +834,268 @@ int mlx5hws_bwc_rule_create_complex(struct mlx5hws_bwc_rule *bwc_rule,
 				    struct mlx5hws_rule_action rule_actions[],
 				    u16 bwc_queue_idx)
 {
-	mlx5hws_err(bwc_rule->bwc_matcher->matcher->tbl->ctx,
-		    "Complex rule is not supported yet\n");
-	return -EOPNOTSUPP;
+	struct mlx5hws_bwc_rule
+		*subrules[MLX5HWS_BWC_COMPLEX_MAX_SUBMATCHERS] = {0};
+	struct mlx5hws_bwc_matcher *cmatcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_bwc_matcher_complex_data *cdata;
+	struct mlx5hws_rule_action *subrule_actions;
+	struct mlx5hws_bwc_complex_submatcher *subm;
+	struct mlx5hws_bwc_rule *subrule;
+	u32 *match_params;
+	u32 chain_id;
+	int i, ret;
+
+	cdata = cmatcher->complex;
+	if (!cdata)
+		return -EINVAL;
+
+	/* Duplicate user data because we will modify it to set register C6
+	 * values. For the same reason, make sure that we allocate a full
+	 * match_param even if the user gave us fewer bytes. We need to ensure
+	 * there is space for the match on C6.
+	 */
+	match_params = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
+	if (!match_params)
+		return -ENOMEM;
+
+	memcpy(match_params, params->match_buf, params->match_sz);
+
+	ret = hws_complex_subrule_create(cmatcher, bwc_rule, match_params,
+					 flow_source, bwc_queue_idx, 0,
+					 NULL, &chain_id);
+	if (ret)
+		goto free_match_params;
+	subrules[0] = bwc_rule;
+
+	for (i = 1; i < cdata->num_submatchers; i++) {
+		subm = &cdata->submatchers[i];
+		subrule = mlx5hws_bwc_rule_alloc(subm->bwc_matcher);
+		if (!subrule) {
+			ret = -ENOMEM;
+			goto destroy_subrules;
+		}
+
+		/* Match on the previous subrule's chain_id. This is how
+		 * subrules are connected in steering.
+		 */
+		MLX5_SET(fte_match_param, match_params,
+			 misc_parameters_2.metadata_reg_c_6, chain_id);
+
+		/* The last subrule uses the complex rule's user-specified
+		 * actions. Everything else uses the chaining rules based on the
+		 * next table and chain_id.
+		 */
+		subrule_actions =
+			i == cdata->num_submatchers - 1 ? rule_actions : NULL;
+
+		ret = hws_complex_subrule_create(cmatcher, subrule,
+						 match_params, flow_source,
+						 bwc_queue_idx, i,
+						 subrule_actions, &chain_id);
+		if (ret) {
+			mlx5hws_bwc_rule_free(subrule);
+			goto destroy_subrules;
+		}
+
+		subrules[i] = subrule;
+	}
+
+	for (i = 0; i < cdata->num_submatchers - 1; i++)
+		subrules[i]->next_subrule = subrules[i + 1];
+
+	kfree(match_params);
+
+	return 0;
+
+destroy_subrules:
+	while (i--)
+		hws_complex_subrule_destroy(subrules[i], cmatcher, i);
+free_match_params:
+	kfree(match_params);
+
+	return ret;
 }
 
 int mlx5hws_bwc_rule_destroy_complex(struct mlx5hws_bwc_rule *bwc_rule)
 {
-	return 0;
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_bwc_rule
+		*subrules[MLX5HWS_BWC_COMPLEX_MAX_SUBMATCHERS] = {0};
+	struct mlx5hws_bwc_matcher_complex_data *cdata;
+	int i, err, ret_val;
+
+	cdata = bwc_matcher->complex;
+
+	/* Construct a list of all the subrules we need to destroy. */
+	subrules[0] = bwc_rule;
+	for (i = 1; i < cdata->num_submatchers; i++)
+		subrules[i] = subrules[i - 1]->next_subrule;
+
+	ret_val = 0;
+	for (i = 0; i < cdata->num_submatchers; i++) {
+		err = hws_complex_subrule_destroy(subrules[i], bwc_matcher, i);
+		/* If something goes wrong, plow along to destroy all of the
+		 * subrules but return an error upstack.
+		 */
+		if (unlikely(err))
+			ret_val = err;
+	}
+
+	return ret_val;
 }
 
-int mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
+static void
+hws_bwc_matcher_init_move(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
-	mlx5hws_err(bwc_matcher->matcher->tbl->ctx,
-		    "Moving complex rule is not supported yet\n");
-	return -EOPNOTSUPP;
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
+	struct mlx5hws_bwc_rule *bwc_rule;
+	struct list_head *rules_list;
+	int i;
+
+	for (i = 0; i < bwc_queues; i++) {
+		rules_list = &bwc_matcher->rules[i];
+		if (list_empty(rules_list))
+			continue;
+
+		list_for_each_entry(bwc_rule, rules_list, list_node) {
+			if (!bwc_rule->subrule_data)
+				continue;
+			bwc_rule->subrule_data->was_moved = false;
+		}
+	}
+}
+
+int mlx5hws_bwc_matcher_complex_move(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_matcher *matcher = bwc_matcher->matcher;
+	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
+	struct mlx5hws_bwc_rule *tmp_bwc_rule;
+	struct mlx5hws_rule_attr rule_attr;
+	int move_error = 0, poll_error = 0;
+	struct mlx5hws_rule *tmp_rule;
+	struct list_head *rules_list;
+	u32 expected_completions = 1;
+	int i, ret = 0;
+
+	hws_bwc_matcher_init_move(bwc_matcher);
+
+	mlx5hws_bwc_rule_fill_attr(bwc_matcher, 0, 0, &rule_attr);
+
+	for (i = 0; i < bwc_queues; i++) {
+		rules_list = &bwc_matcher->rules[i];
+		if (list_empty(rules_list))
+			continue;
+
+		rule_attr.queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
+
+		list_for_each_entry(tmp_bwc_rule, rules_list, list_node) {
+			/* Check if a rule with similar tag has already
+			 * been moved.
+			 */
+			if (tmp_bwc_rule->subrule_data->was_moved) {
+				/* This rule is a duplicate of rule with
+				 * identical tag that has already been moved
+				 * earlier. Just update this rule's RTCs.
+				 */
+				tmp_bwc_rule->rule->rtc_0 =
+					tmp_bwc_rule->subrule_data->rtc_0;
+				tmp_bwc_rule->rule->rtc_1 =
+					tmp_bwc_rule->subrule_data->rtc_1;
+				tmp_bwc_rule->rule->matcher =
+					tmp_bwc_rule->rule->matcher->resize_dst;
+				continue;
+			}
+
+			/* First time we're moving rule with this tag.
+			 * Move it for real.
+			 */
+			tmp_rule = tmp_bwc_rule->rule;
+			tmp_rule->skip_delete = false;
+			ret = mlx5hws_matcher_resize_rule_move(matcher,
+							       tmp_rule,
+							       &rule_attr);
+			if (unlikely(ret)) {
+				if (!move_error) {
+					mlx5hws_err(ctx,
+						    "Moving complex BWC rule: move failed (%d), attempting to move rest of the rules\n",
+						    ret);
+					move_error = ret;
+				}
+				/* Rule wasn't queued, no need to poll */
+				continue;
+			}
+
+			expected_completions = 1;
+			ret = mlx5hws_bwc_queue_poll(ctx,
+						     rule_attr.queue_id,
+						     &expected_completions,
+						     true);
+			if (unlikely(ret)) {
+				if (ret == -ETIMEDOUT) {
+					mlx5hws_err(ctx,
+						    "Moving complex BWC rule: timeout polling for completions (%d), aborting rehash\n",
+						    ret);
+					return ret;
+				}
+				if (!poll_error) {
+					mlx5hws_err(ctx,
+						    "Moving complex BWC rule: polling for completions failed (%d), attempting to move rest of the rules\n",
+						    ret);
+					poll_error = ret;
+				}
+			}
+
+			/* Done moving the rule to the new matcher,
+			 * now update RTCs for all the duplicated rules.
+			 */
+			tmp_bwc_rule->subrule_data->rtc_0 =
+				tmp_bwc_rule->rule->rtc_0;
+			tmp_bwc_rule->subrule_data->rtc_1 =
+				tmp_bwc_rule->rule->rtc_1;
+
+			tmp_bwc_rule->subrule_data->was_moved = true;
+		}
+	}
+
+	/* Return the first error that happened */
+	if (unlikely(move_error))
+		return move_error;
+	if (unlikely(poll_error))
+		return poll_error;
+
+	return ret;
+}
+
+int
+mlx5hws_bwc_matcher_complex_move_first(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_bwc_matcher_complex_data *cdata;
+	struct mlx5hws_table *isolated_tbl;
+	u32 end_ft_id;
+	int i, ret;
+
+	cdata = bwc_matcher->complex;
+
+	/* We are rehashing the first submatcher. We need to update the
+	 * subsequent submatchers to point to the end_ft of this new matcher.
+	 * This needs to be done before moving any rules to prevent possible
+	 * steering loops.
+	 */
+	end_ft_id = bwc_matcher->matcher->resize_dst->end_ft_id;
+	for (i = 1; i < cdata->num_submatchers; i++) {
+		isolated_tbl = cdata->submatchers[i].tbl;
+		ret = mlx5hws_matcher_update_end_ft_isolated(isolated_tbl,
+							     end_ft_id);
+		if (ret) {
+			mlx5hws_err(ctx,
+				    "Complex matcher: failed updating end_ft of isolated matcher (%d)\n",
+				    ret);
+			return ret;
+		}
+	}
+
+	return mlx5hws_bwc_matcher_complex_move(bwc_matcher);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h
index 340f0688e394..d07de631ce9f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h
@@ -4,6 +4,62 @@
 #ifndef HWS_BWC_COMPLEX_H_
 #define HWS_BWC_COMPLEX_H_
 
+#define MLX5HWS_BWC_COMPLEX_MAX_SUBMATCHERS 4
+
+/* A matcher can't contain two rules with the same match tag, but it is possible
+ * that two different complex rules' subrules have the same match tag. In that
+ * case, those subrules correspond to a single rule, and we need to refcount.
+ */
+struct mlx5hws_bwc_complex_subrule_data {
+	struct mlx5hws_rule_match_tag match_tag;
+	refcount_t refcount;
+	/* The chain_id is what glues individual subrules into larger complex
+	 * rules. It is the value that this subrule writes to register C6, and
+	 * that the next subrule matches against.
+	 */
+	u32 chain_id;
+	u32 rtc_0;
+	u32 rtc_1;
+	/* During rehash we iterate through all the subrules to move them. But
+	 * two or more subrules can share the same physical rule in the
+	 * submatcher, so we use `was_moved` to keep track if a given rule was
+	 * already moved.
+	 */
+	bool was_moved;
+	struct rhash_head hash_node;
+};
+
+struct mlx5hws_bwc_complex_submatcher {
+	/* Isolated table that the matcher lives in. Not set for the first
+	 * matcher, which lives in the original table.
+	 */
+	struct mlx5hws_table *tbl;
+	/* Match a rule with this action to go to `tbl`. This is set in all
+	 * submatchers but the first.
+	 */
+	struct mlx5hws_action *action_tbl;
+	/* This submatcher's simple matcher. The first submatcher points to the
+	 * outer (complex) matcher.
+	 */
+	struct mlx5hws_bwc_matcher *bwc_matcher;
+	struct rhashtable rules_hash;
+	struct ida chain_ida;
+	struct mutex hash_lock; /* Protect the hash and ida. */
+};
+
+struct mlx5hws_bwc_matcher_complex_data {
+	struct mlx5hws_bwc_complex_submatcher
+		submatchers[MLX5HWS_BWC_COMPLEX_MAX_SUBMATCHERS];
+	int num_submatchers;
+	/* Actions used by all but the last submatcher to point to the next
+	 * submatcher in the chain. The last submatcher uses the action template
+	 * from the complex matcher, to perform the actions that the user
+	 * originally requested.
+	 */
+	struct mlx5hws_action *action_metadata;
+	struct mlx5hws_action *action_last;
+};
+
 bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
 					 u8 match_criteria_enable,
 					 struct mlx5hws_match_parameters *mask);
@@ -16,7 +72,10 @@ int mlx5hws_bwc_matcher_create_complex(struct mlx5hws_bwc_matcher *bwc_matcher,
 
 void mlx5hws_bwc_matcher_destroy_complex(struct mlx5hws_bwc_matcher *bwc_matcher);
 
-int mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher);
+int mlx5hws_bwc_matcher_complex_move(struct mlx5hws_bwc_matcher *bwc_matcher);
+
+int
+mlx5hws_bwc_matcher_complex_move_first(struct mlx5hws_bwc_matcher *bwc_matcher);
 
 int mlx5hws_bwc_rule_create_complex(struct mlx5hws_bwc_rule *bwc_rule,
 				    struct mlx5hws_match_parameters *params,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
index c00c138c3366..f22eaf506d28 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
@@ -55,6 +55,7 @@ int mlx5hws_cmd_flow_table_create(struct mlx5_core_dev *mdev,
 
 	MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE);
 	MLX5_SET(create_flow_table_in, in, table_type, ft_attr->type);
+	MLX5_SET(create_flow_table_in, in, uid, ft_attr->uid);
 
 	ft_ctx = MLX5_ADDR_OF(create_flow_table_in, in, flow_table_context);
 	MLX5_SET(flow_table_context, ft_ctx, level, ft_attr->level);
@@ -130,12 +131,6 @@ int mlx5hws_cmd_flow_table_destroy(struct mlx5_core_dev *mdev,
 	return mlx5_cmd_exec_in(mdev, destroy_flow_table, in);
 }
 
-void mlx5hws_cmd_alias_flow_table_destroy(struct mlx5_core_dev *mdev,
-					  u32 table_id)
-{
-	hws_cmd_general_obj_destroy(mdev, MLX5_OBJ_TYPE_FT_ALIAS, table_id);
-}
-
 static int hws_cmd_flow_group_create(struct mlx5_core_dev *mdev,
 				     struct mlx5hws_cmd_fg_attr *fg_attr,
 				     u32 *group_id)
@@ -257,6 +252,12 @@ int mlx5hws_cmd_set_fte(struct mlx5_core_dev *mdev,
 						 dest->ext_reformat_id);
 				}
 				break;
+			case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER:
+				MLX5_SET(dest_format, in_dests,
+					 destination_type, ifc_dest_type);
+				MLX5_SET(dest_format, in_dests, destination_id,
+					 dest->destination_id);
+				break;
 			default:
 				ret = -EOPNOTSUPP;
 				goto out;
@@ -359,7 +360,7 @@ void mlx5hws_cmd_set_attr_connect_miss_tbl(struct mlx5hws_context *ctx,
 	ft_attr->type = fw_ft_type;
 	ft_attr->table_miss_action = MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION_GOTO_TBL;
 
-	default_miss_tbl = ctx->common_res[type].default_miss->ft_id;
+	default_miss_tbl = ctx->common_res.default_miss->ft_id;
 	if (!default_miss_tbl) {
 		pr_warn("HWS: no flow table ID for default miss\n");
 		return;
@@ -406,7 +407,6 @@ int mlx5hws_cmd_rtc_create(struct mlx5_core_dev *mdev,
 	MLX5_SET(rtc, attr, match_definer_1, rtc_attr->match_definer_1);
 	MLX5_SET(rtc, attr, stc_id, rtc_attr->stc_base);
 	MLX5_SET(rtc, attr, ste_table_base_id, rtc_attr->ste_base);
-	MLX5_SET(rtc, attr, ste_table_offset, rtc_attr->ste_offset);
 	MLX5_SET(rtc, attr, miss_flow_table_id, rtc_attr->miss_ft_id);
 	MLX5_SET(rtc, attr, reparse_mode, rtc_attr->reparse_mode);
 
@@ -622,12 +622,12 @@ int mlx5hws_cmd_arg_create(struct mlx5_core_dev *mdev,
 			   u32 pd,
 			   u32 *arg_id)
 {
+	u32 in[MLX5_ST_SZ_DW(create_modify_header_arg_in)] = {0};
 	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
-	u32 in[MLX5_ST_SZ_DW(create_arg_in)] = {0};
 	void *attr;
 	int ret;
 
-	attr = MLX5_ADDR_OF(create_arg_in, in, hdr);
+	attr = MLX5_ADDR_OF(create_modify_header_arg_in, in, hdr);
 	MLX5_SET(general_obj_in_cmd_hdr,
 		 attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
 	MLX5_SET(general_obj_in_cmd_hdr,
@@ -635,8 +635,8 @@ int mlx5hws_cmd_arg_create(struct mlx5_core_dev *mdev,
 	MLX5_SET(general_obj_in_cmd_hdr,
 		 attr, op_param.create.log_obj_range, log_obj_range);
 
-	attr = MLX5_ADDR_OF(create_arg_in, in, arg);
-	MLX5_SET(arg, attr, access_pd, pd);
+	attr = MLX5_ADDR_OF(create_modify_header_arg_in, in, arg);
+	MLX5_SET(modify_header_arg, attr, access_pd, pd);
 
 	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 	if (ret) {
@@ -812,7 +812,7 @@ int mlx5hws_cmd_packet_reformat_create(struct mlx5_core_dev *mdev,
 				       struct mlx5hws_cmd_packet_reformat_create_attr *attr,
 				       u32 *reformat_id)
 {
-	u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)] = {0};
 	size_t insz, cmd_data_sz, cmd_total_sz;
 	void *prctx;
 	void *pdata;
@@ -845,7 +845,7 @@ int mlx5hws_cmd_packet_reformat_create(struct mlx5_core_dev *mdev,
 		goto out;
 	}
 
-	*reformat_id = MLX5_GET(alloc_packet_reformat_out, out, packet_reformat_id);
+	*reformat_id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id);
 out:
 	kfree(in);
 	return ret;
@@ -854,13 +854,13 @@ out:
 int mlx5hws_cmd_packet_reformat_destroy(struct mlx5_core_dev *mdev,
 					u32 reformat_id)
 {
-	u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_in)] = {0};
+	u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)] = {0};
 	int ret;
 
-	MLX5_SET(dealloc_packet_reformat_in, in, opcode,
+	MLX5_SET(dealloc_packet_reformat_context_in, in, opcode,
 		 MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT);
-	MLX5_SET(dealloc_packet_reformat_in, in,
+	MLX5_SET(dealloc_packet_reformat_context_in, in,
 		 packet_reformat_id, reformat_id);
 
 	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
@@ -889,73 +889,6 @@ int mlx5hws_cmd_sq_modify_rdy(struct mlx5_core_dev *mdev, u32 sqn)
 	return ret;
 }
 
-int mlx5hws_cmd_allow_other_vhca_access(struct mlx5_core_dev *mdev,
-					struct mlx5hws_cmd_allow_other_vhca_access_attr *attr)
-{
-	u32 out[MLX5_ST_SZ_DW(allow_other_vhca_access_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(allow_other_vhca_access_in)] = {0};
-	void *key;
-	int ret;
-
-	MLX5_SET(allow_other_vhca_access_in,
-		 in, opcode, MLX5_CMD_OP_ALLOW_OTHER_VHCA_ACCESS);
-	MLX5_SET(allow_other_vhca_access_in,
-		 in, object_type_to_be_accessed, attr->obj_type);
-	MLX5_SET(allow_other_vhca_access_in,
-		 in, object_id_to_be_accessed, attr->obj_id);
-
-	key = MLX5_ADDR_OF(allow_other_vhca_access_in, in, access_key);
-	memcpy(key, attr->access_key, sizeof(attr->access_key));
-
-	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-	if (ret)
-		mlx5_core_err(mdev, "Failed to execute ALLOW_OTHER_VHCA_ACCESS command\n");
-
-	return ret;
-}
-
-int mlx5hws_cmd_alias_obj_create(struct mlx5_core_dev *mdev,
-				 struct mlx5hws_cmd_alias_obj_create_attr *alias_attr,
-				 u32 *obj_id)
-{
-	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
-	u32 in[MLX5_ST_SZ_DW(create_alias_obj_in)] = {0};
-	void *attr;
-	void *key;
-	int ret;
-
-	attr = MLX5_ADDR_OF(create_alias_obj_in, in, hdr);
-	MLX5_SET(general_obj_in_cmd_hdr,
-		 attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
-	MLX5_SET(general_obj_in_cmd_hdr,
-		 attr, obj_type, alias_attr->obj_type);
-	MLX5_SET(general_obj_in_cmd_hdr, attr, op_param.create.alias_object, 1);
-
-	attr = MLX5_ADDR_OF(create_alias_obj_in, in, alias_ctx);
-	MLX5_SET(alias_context, attr, vhca_id_to_be_accessed, alias_attr->vhca_id);
-	MLX5_SET(alias_context, attr, object_id_to_be_accessed, alias_attr->obj_id);
-
-	key = MLX5_ADDR_OF(alias_context, attr, access_key);
-	memcpy(key, alias_attr->access_key, sizeof(alias_attr->access_key));
-
-	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-	if (ret) {
-		mlx5_core_err(mdev, "Failed to create ALIAS OBJ\n");
-		goto out;
-	}
-
-	*obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
-out:
-	return ret;
-}
-
-int mlx5hws_cmd_alias_obj_destroy(struct mlx5_core_dev *mdev,
-				  u16 obj_type,
-				  u32 obj_id)
-{
-	return hws_cmd_general_obj_destroy(mdev, obj_type, obj_id);
-}
-
 int mlx5hws_cmd_generate_wqe(struct mlx5_core_dev *mdev,
 			     struct mlx5hws_cmd_generate_wqe_attr *attr,
 			     struct mlx5_cqe64 *ret_cqe)
@@ -1267,34 +1200,20 @@ out:
 int mlx5hws_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_function,
 			   u16 vport_number, u16 *gvmi)
 {
-	bool ec_vf_func = other_function ? mlx5_core_is_ec_vf_vport(mdev, vport_number) : false;
-	u32 in[MLX5_ST_SZ_DW(query_hca_cap_in)] = {};
-	int out_size;
-	void *out;
 	int err;
 
-	out_size = MLX5_ST_SZ_BYTES(query_hca_cap_out);
-	out = kzalloc(out_size, GFP_KERNEL);
-	if (!out)
-		return -ENOMEM;
-
-	MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
-	MLX5_SET(query_hca_cap_in, in, other_function, other_function);
-	MLX5_SET(query_hca_cap_in, in, function_id,
-		 mlx5_vport_to_func_id(mdev, vport_number, ec_vf_func));
-	MLX5_SET(query_hca_cap_in, in, ec_vf_function, ec_vf_func);
-	MLX5_SET(query_hca_cap_in, in, op_mod,
-		 MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1 | HCA_CAP_OPMOD_GET_CUR);
+	if (!other_function) {
+		/* self vhca_id */
+		*gvmi = MLX5_CAP_GEN(mdev, vhca_id);
+		return 0;
+	}
 
-	err = mlx5_cmd_exec_inout(mdev, query_hca_cap, in, out);
+	err = mlx5_vport_get_vhca_id(mdev, vport_number, gvmi);
 	if (err) {
-		kfree(out);
+		mlx5_core_err(mdev, "Failed to get vport vhca id for vport %d\n",
+			      vport_number);
 		return err;
 	}
 
-	*gvmi = MLX5_GET(query_hca_cap_out, out, capability.cmd_hca_cap.vhca_id);
-
-	kfree(out);
-
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
index 434f62b0904e..122ccc671628 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
@@ -36,6 +36,7 @@ struct mlx5hws_cmd_set_fte_attr {
 struct mlx5hws_cmd_ft_create_attr {
 	u8 type;
 	u8 level;
+	u16 uid;
 	bool rtc_valid;
 	bool decap_en;
 	bool reformat_en;
@@ -63,14 +64,13 @@ struct mlx5hws_cmd_forward_tbl {
 	u8 type;
 	u32 ft_id;
 	u32 fg_id;
-	u32 refcount;
+	u32 refcount; /* protected by context ctrl lock */
 };
 
 struct mlx5hws_cmd_rtc_create_attr {
 	u32 pd;
 	u32 stc_base;
 	u32 ste_base;
-	u32 ste_offset;
 	u32 miss_ft_id;
 	bool fw_gen_wqe;
 	u8 update_index_mode;
@@ -258,9 +258,6 @@ int mlx5hws_cmd_flow_table_query(struct mlx5_core_dev *mdev,
 int mlx5hws_cmd_flow_table_destroy(struct mlx5_core_dev *mdev,
 				   u8 fw_ft_type, u32 table_id);
 
-void mlx5hws_cmd_alias_flow_table_destroy(struct mlx5_core_dev *mdev,
-					  u32 table_id);
-
 int mlx5hws_cmd_rtc_create(struct mlx5_core_dev *mdev,
 			   struct mlx5hws_cmd_rtc_create_attr *rtc_attr,
 			   u32 *rtc_id);
@@ -334,14 +331,6 @@ mlx5hws_cmd_forward_tbl_create(struct mlx5_core_dev *mdev,
 void mlx5hws_cmd_forward_tbl_destroy(struct mlx5_core_dev *mdev,
 				     struct mlx5hws_cmd_forward_tbl *tbl);
 
-int mlx5hws_cmd_alias_obj_create(struct mlx5_core_dev *mdev,
-				 struct mlx5hws_cmd_alias_obj_create_attr *alias_attr,
-				 u32 *obj_id);
-
-int mlx5hws_cmd_alias_obj_destroy(struct mlx5_core_dev *mdev,
-				  u16 obj_type,
-				  u32 obj_id);
-
 int mlx5hws_cmd_sq_modify_rdy(struct mlx5_core_dev *mdev, u32 sqn);
 
 int mlx5hws_cmd_query_caps(struct mlx5_core_dev *mdev,
@@ -352,9 +341,6 @@ void mlx5hws_cmd_set_attr_connect_miss_tbl(struct mlx5hws_context *ctx,
 					   enum mlx5hws_table_type type,
 					   struct mlx5hws_cmd_ft_modify_attr *ft_attr);
 
-int mlx5hws_cmd_allow_other_vhca_access(struct mlx5_core_dev *mdev,
-					struct mlx5hws_cmd_allow_other_vhca_access_attr *attr);
-
 int mlx5hws_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_function,
 			   u16 vport_number, u16 *gvmi);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c
index fd48b05e91e0..428dae869706 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c
@@ -23,7 +23,6 @@ static int hws_context_pools_init(struct mlx5hws_context *ctx)
 	struct mlx5hws_pool_attr pool_attr = {0};
 	u8 max_log_sz;
 	int ret;
-	int i;
 
 	ret = mlx5hws_pat_init_pattern_cache(&ctx->pattern_cache);
 	if (ret)
@@ -35,27 +34,20 @@ static int hws_context_pools_init(struct mlx5hws_context *ctx)
 
 	/* Create an STC pool per FT type */
 	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STC;
-	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STC_POOL;
 	max_log_sz = min(MLX5HWS_POOL_STC_LOG_SZ, ctx->caps->stc_alloc_log_max);
 	pool_attr.alloc_log_sz = max(max_log_sz, ctx->caps->stc_alloc_log_gran);
 
-	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) {
-		pool_attr.table_type = i;
-		ctx->stc_pool[i] = mlx5hws_pool_create(ctx, &pool_attr);
-		if (!ctx->stc_pool[i]) {
-			mlx5hws_err(ctx, "Failed to allocate STC pool [%d]", i);
-			ret = -ENOMEM;
-			goto free_stc_pools;
-		}
+	pool_attr.table_type = MLX5HWS_TABLE_TYPE_FDB;
+	ctx->stc_pool = mlx5hws_pool_create(ctx, &pool_attr);
+	if (!ctx->stc_pool) {
+		mlx5hws_err(ctx, "Failed to allocate STC pool\n");
+		ret = -ENOMEM;
+		goto uninit_cache;
 	}
 
 	return 0;
 
-free_stc_pools:
-	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++)
-		if (ctx->stc_pool[i])
-			mlx5hws_pool_destroy(ctx->stc_pool[i]);
-
+uninit_cache:
 	mlx5hws_definer_uninit_cache(ctx->definer_cache);
 uninit_pat_cache:
 	mlx5hws_pat_uninit_pattern_cache(ctx->pattern_cache);
@@ -64,12 +56,8 @@ uninit_pat_cache:
 
 static void hws_context_pools_uninit(struct mlx5hws_context *ctx)
 {
-	int i;
-
-	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) {
-		if (ctx->stc_pool[i])
-			mlx5hws_pool_destroy(ctx->stc_pool[i]);
-	}
+	if (ctx->stc_pool)
+		mlx5hws_pool_destroy(ctx->stc_pool);
 
 	mlx5hws_definer_uninit_cache(ctx->definer_cache);
 	mlx5hws_pat_uninit_pattern_cache(ctx->pattern_cache);
@@ -161,17 +149,25 @@ static int hws_context_init_hws(struct mlx5hws_context *ctx,
 	if (ret)
 		goto uninit_pd;
 
-	if (attr->bwc)
-		ctx->flags |= MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT;
+	/* Context has support for backward compatible API,
+	 * and does not have support for native HWS API.
+	 */
+	ctx->flags |= MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT;
 
 	ret = mlx5hws_send_queues_open(ctx, attr->queues, attr->queue_size);
 	if (ret)
 		goto pools_uninit;
 
+	ret = mlx5hws_action_ste_pool_init(ctx);
+	if (ret)
+		goto close_queues;
+
 	INIT_LIST_HEAD(&ctx->tbl_list);
 
 	return 0;
 
+close_queues:
+	mlx5hws_send_queues_close(ctx);
 pools_uninit:
 	hws_context_pools_uninit(ctx);
 uninit_pd:
@@ -184,6 +180,7 @@ static void hws_context_uninit_hws(struct mlx5hws_context *ctx)
 	if (!(ctx->flags & MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT))
 		return;
 
+	mlx5hws_action_ste_pool_uninit(ctx);
 	mlx5hws_send_queues_close(ctx);
 	hws_context_pools_uninit(ctx);
 	hws_context_uninit_pd(ctx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h
index 47f5cc8de73f..3f8938c73dc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h
@@ -8,6 +8,7 @@ enum mlx5hws_context_flags {
 	MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT = 1 << 0,
 	MLX5HWS_CONTEXT_FLAG_PRIVATE_PD = 1 << 1,
 	MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT = 1 << 2,
+	MLX5HWS_CONTEXT_FLAG_NATIVE_SUPPORT = 1 << 3,
 };
 
 enum mlx5hws_context_shared_stc_type {
@@ -37,8 +38,10 @@ struct mlx5hws_context {
 	struct mlx5_core_dev *mdev;
 	struct mlx5hws_cmd_query_caps *caps;
 	u32 pd_num;
-	struct mlx5hws_pool *stc_pool[MLX5HWS_TABLE_TYPE_MAX];
-	struct mlx5hws_context_common_res common_res[MLX5HWS_TABLE_TYPE_MAX];
+	struct mlx5hws_pool *stc_pool;
+	struct mlx5hws_action_ste_pool *action_ste_pool; /* One per queue */
+	struct delayed_work action_ste_cleanup;
+	struct mlx5hws_context_common_res common_res;
 	struct mlx5hws_pattern_cache *pattern_cache;
 	struct mlx5hws_definer_cache *definer_cache;
 	struct mutex ctrl_lock; /* control lock to protect the whole context */
@@ -58,6 +61,11 @@ static inline bool mlx5hws_context_bwc_supported(struct mlx5hws_context *ctx)
 	return ctx->flags & MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT;
 }
 
+static inline bool mlx5hws_context_native_supported(struct mlx5hws_context *ctx)
+{
+	return ctx->flags & MLX5HWS_CONTEXT_FLAG_NATIVE_SUPPORT;
+}
+
 bool mlx5hws_context_cap_dynamic_reparse(struct mlx5hws_context *ctx);
 
 u8 mlx5hws_context_get_reparse_mode(struct mlx5hws_context *ctx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c
index 5b200b4bc1a8..2ec8cb10139a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c
@@ -99,17 +99,19 @@ hws_debug_dump_matcher_attr(struct seq_file *f, struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_matcher_attr *attr = &matcher->attr;
 
-	seq_printf(f, "%d,0x%llx,%d,%d,%d,%d,%d,%d,%d,%d\n",
+	seq_printf(f, "%d,0x%llx,%d,%d,%d,%d,%d,%d,%d,%d,-1,-1,%d,%d\n",
 		   MLX5HWS_DEBUG_RES_TYPE_MATCHER_ATTR,
 		   HWS_PTR_TO_ID(matcher),
 		   attr->priority,
 		   attr->mode,
-		   attr->table.sz_row_log,
-		   attr->table.sz_col_log,
+		   attr->size[MLX5HWS_MATCHER_SIZE_TYPE_RX].table.sz_row_log,
+		   attr->size[MLX5HWS_MATCHER_SIZE_TYPE_RX].table.sz_col_log,
 		   attr->optimize_using_rule_idx,
 		   attr->optimize_flow_src,
 		   attr->insert_mode,
-		   attr->distribute_mode);
+		   attr->distribute_mode,
+		   attr->size[MLX5HWS_MATCHER_SIZE_TYPE_TX].table.sz_row_log,
+		   attr->size[MLX5HWS_MATCHER_SIZE_TYPE_TX].table.sz_col_log);
 
 	return 0;
 }
@@ -118,8 +120,6 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma
 {
 	enum mlx5hws_table_type tbl_type = matcher->tbl->type;
 	struct mlx5hws_cmd_ft_query_attr ft_attr = {0};
-	struct mlx5hws_pool_chunk *ste;
-	struct mlx5hws_pool *ste_pool;
 	u64 icm_addr_0 = 0;
 	u64 icm_addr_1 = 0;
 	u32 ste_0_id = -1;
@@ -134,13 +134,9 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma
 		   matcher->end_ft_id,
 		   matcher->col_matcher ? HWS_PTR_TO_ID(matcher->col_matcher) : 0);
 
-	ste = &matcher->match_ste.ste;
-	ste_pool = matcher->match_ste.pool;
-	if (ste_pool) {
-		ste_0_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
-		if (tbl_type == MLX5HWS_TABLE_TYPE_FDB)
-			ste_1_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
-	}
+	ste_0_id = matcher->match_ste.ste_0_base;
+	if (tbl_type == MLX5HWS_TABLE_TYPE_FDB)
+		ste_1_id = matcher->match_ste.ste_1_base;
 
 	seq_printf(f, ",%d,%d,%d,%d",
 		   matcher->match_ste.rtc_0_id,
@@ -148,19 +144,6 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma
 		   matcher->match_ste.rtc_1_id,
 		   (int)ste_1_id);
 
-	ste = &matcher->action_ste[0].ste;
-	ste_pool = matcher->action_ste[0].pool;
-	if (ste_pool) {
-		ste_0_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
-		if (tbl_type == MLX5HWS_TABLE_TYPE_FDB)
-			ste_1_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
-		else
-			ste_1_id = -1;
-	} else {
-		ste_0_id = -1;
-		ste_1_id = -1;
-	}
-
 	ft_attr.type = matcher->tbl->fw_ft_type;
 	ret = mlx5hws_cmd_flow_table_query(matcher->tbl->ctx->mdev,
 					   matcher->end_ft_id,
@@ -170,12 +153,7 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma
 	if (ret)
 		return ret;
 
-	seq_printf(f, ",%d,%d,%d,%d,%d,0x%llx,0x%llx\n",
-		   matcher->action_ste[0].rtc_0_id,
-		   (int)ste_0_id,
-		   matcher->action_ste[0].rtc_1_id,
-		   (int)ste_1_id,
-		   0,
+	seq_printf(f, ",-1,-1,-1,-1,0,0x%llx,0x%llx\n",
 		   mlx5hws_debug_icm_to_idx(icm_addr_0),
 		   mlx5hws_debug_icm_to_idx(icm_addr_1));
 
@@ -368,9 +346,10 @@ static int hws_debug_dump_context_info(struct seq_file *f, struct mlx5hws_contex
 
 static int hws_debug_dump_context_stc_resource(struct seq_file *f,
 					       struct mlx5hws_context *ctx,
-					       u32 tbl_type,
 					       struct mlx5hws_pool_resource *resource)
 {
+	u32 tbl_type = MLX5HWS_TABLE_TYPE_BASE + MLX5HWS_TABLE_TYPE_FDB;
+
 	seq_printf(f, "%d,0x%llx,%u,%u\n",
 		   MLX5HWS_DEBUG_RES_TYPE_CONTEXT_STC,
 		   HWS_PTR_TO_ID(ctx),
@@ -382,40 +361,65 @@ static int hws_debug_dump_context_stc_resource(struct seq_file *f,
 
 static int hws_debug_dump_context_stc(struct seq_file *f, struct mlx5hws_context *ctx)
 {
-	struct mlx5hws_pool *stc_pool;
-	u32 table_type;
+	struct mlx5hws_pool *stc_pool = ctx->stc_pool;
 	int ret;
-	int i;
 
-	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) {
-		stc_pool = ctx->stc_pool[i];
-		table_type = MLX5HWS_TABLE_TYPE_BASE + i;
+	if (!stc_pool)
+		return 0;
 
-		if (!stc_pool)
-			continue;
+	if (stc_pool->resource) {
+		ret = hws_debug_dump_context_stc_resource(f, ctx,
+							  stc_pool->resource);
+		if (ret)
+			return ret;
+	}
 
-		if (stc_pool->resource[0]) {
-			ret = hws_debug_dump_context_stc_resource(f, ctx, table_type,
-								  stc_pool->resource[0]);
-			if (ret)
-				return ret;
-		}
+	if (stc_pool->mirror_resource) {
+		struct mlx5hws_pool_resource *res = stc_pool->mirror_resource;
 
-		if (i == MLX5HWS_TABLE_TYPE_FDB && stc_pool->mirror_resource[0]) {
-			ret = hws_debug_dump_context_stc_resource(f, ctx, table_type,
-								  stc_pool->mirror_resource[0]);
-			if (ret)
-				return ret;
-		}
+		ret = hws_debug_dump_context_stc_resource(f, ctx, res);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
 }
 
+static void
+hws_debug_dump_action_ste_table(struct seq_file *f,
+				struct mlx5hws_action_ste_table *action_tbl)
+{
+	int ste_0_id = mlx5hws_pool_get_base_id(action_tbl->pool);
+	int ste_1_id = mlx5hws_pool_get_base_mirror_id(action_tbl->pool);
+
+	seq_printf(f, "%d,0x%llx,%d,%d,%d,%d\n",
+		   MLX5HWS_DEBUG_RES_TYPE_ACTION_STE_TABLE,
+		   HWS_PTR_TO_ID(action_tbl),
+		   action_tbl->rtc_0_id, ste_0_id,
+		   action_tbl->rtc_1_id, ste_1_id);
+}
+
+static void hws_debug_dump_action_ste_pool(struct seq_file *f,
+					   struct mlx5hws_action_ste_pool *pool)
+{
+	struct mlx5hws_action_ste_table *action_tbl;
+	enum mlx5hws_pool_optimize opt;
+
+	mutex_lock(&pool->lock);
+	for (opt = MLX5HWS_POOL_OPTIMIZE_NONE; opt < MLX5HWS_POOL_OPTIMIZE_MAX;
+	     opt++) {
+		list_for_each_entry(action_tbl, &pool->elems[opt].available,
+				    list_node) {
+			hws_debug_dump_action_ste_table(f, action_tbl);
+		}
+	}
+	mutex_unlock(&pool->lock);
+}
+
 static int hws_debug_dump_context(struct seq_file *f, struct mlx5hws_context *ctx)
 {
 	struct mlx5hws_table *tbl;
-	int ret;
+	int ret, i;
 
 	ret = hws_debug_dump_context_info(f, ctx);
 	if (ret)
@@ -435,6 +439,9 @@ static int hws_debug_dump_context(struct seq_file *f, struct mlx5hws_context *ct
 			return ret;
 	}
 
+	for (i = 0; i < ctx->queues; i++)
+		hws_debug_dump_action_ste_pool(f, &ctx->action_ste_pool[i]);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h
index e44e7ae28f93..89c396f9f266 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h
@@ -26,6 +26,8 @@ enum mlx5hws_debug_res_type {
 	MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_HASH_DEFINER = 4205,
 	MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_RANGE_DEFINER = 4206,
 	MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_COMPARE_MATCH_DEFINER = 4207,
+
+	MLX5HWS_DEBUG_RES_TYPE_ACTION_STE_TABLE = 4300,
 };
 
 static inline u64
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
index 8fe96eb76baf..82fd122d4284 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
@@ -70,7 +70,7 @@
 			u32 second_dw_mask = (mask) & ((1 << _bit_off) - 1); \
 			_HWS_SET32(p, (v) >> _bit_off, byte_off, 0, (mask) >> _bit_off); \
 			_HWS_SET32(p, (v) & second_dw_mask, (byte_off) + DW_SIZE, \
-				    (bit_off) % BITS_IN_DW, second_dw_mask); \
+				    (bit_off + BITS_IN_DW) % BITS_IN_DW, second_dw_mask); \
 		} else { \
 			_HWS_SET32(p, v, byte_off, (bit_off), (mask)); \
 		} \
@@ -158,6 +158,218 @@ struct mlx5hws_definer_conv_data {
 	u32 match_flags;
 };
 
+#define HWS_DEFINER_ENTRY(name)[MLX5HWS_DEFINER_FNAME_##name] = #name
+
+static const char * const hws_definer_fname_to_str[] = {
+	HWS_DEFINER_ENTRY(ETH_SMAC_47_16_O),
+	HWS_DEFINER_ENTRY(ETH_SMAC_47_16_I),
+	HWS_DEFINER_ENTRY(ETH_SMAC_15_0_O),
+	HWS_DEFINER_ENTRY(ETH_SMAC_15_0_I),
+	HWS_DEFINER_ENTRY(ETH_DMAC_47_16_O),
+	HWS_DEFINER_ENTRY(ETH_DMAC_47_16_I),
+	HWS_DEFINER_ENTRY(ETH_DMAC_15_0_O),
+	HWS_DEFINER_ENTRY(ETH_DMAC_15_0_I),
+	HWS_DEFINER_ENTRY(ETH_TYPE_O),
+	HWS_DEFINER_ENTRY(ETH_TYPE_I),
+	HWS_DEFINER_ENTRY(ETH_L3_TYPE_O),
+	HWS_DEFINER_ENTRY(ETH_L3_TYPE_I),
+	HWS_DEFINER_ENTRY(VLAN_TYPE_O),
+	HWS_DEFINER_ENTRY(VLAN_TYPE_I),
+	HWS_DEFINER_ENTRY(VLAN_FIRST_PRIO_O),
+	HWS_DEFINER_ENTRY(VLAN_FIRST_PRIO_I),
+	HWS_DEFINER_ENTRY(VLAN_CFI_O),
+	HWS_DEFINER_ENTRY(VLAN_CFI_I),
+	HWS_DEFINER_ENTRY(VLAN_ID_O),
+	HWS_DEFINER_ENTRY(VLAN_ID_I),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_TYPE_O),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_TYPE_I),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_PRIO_O),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_PRIO_I),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_CFI_O),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_CFI_I),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_ID_O),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_ID_I),
+	HWS_DEFINER_ENTRY(IPV4_IHL_O),
+	HWS_DEFINER_ENTRY(IPV4_IHL_I),
+	HWS_DEFINER_ENTRY(IP_DSCP_O),
+	HWS_DEFINER_ENTRY(IP_DSCP_I),
+	HWS_DEFINER_ENTRY(IP_ECN_O),
+	HWS_DEFINER_ENTRY(IP_ECN_I),
+	HWS_DEFINER_ENTRY(IP_TTL_O),
+	HWS_DEFINER_ENTRY(IP_TTL_I),
+	HWS_DEFINER_ENTRY(IPV4_DST_O),
+	HWS_DEFINER_ENTRY(IPV4_DST_I),
+	HWS_DEFINER_ENTRY(IPV4_SRC_O),
+	HWS_DEFINER_ENTRY(IPV4_SRC_I),
+	HWS_DEFINER_ENTRY(IP_VERSION_O),
+	HWS_DEFINER_ENTRY(IP_VERSION_I),
+	HWS_DEFINER_ENTRY(IP_FRAG_O),
+	HWS_DEFINER_ENTRY(IP_FRAG_I),
+	HWS_DEFINER_ENTRY(IP_LEN_O),
+	HWS_DEFINER_ENTRY(IP_LEN_I),
+	HWS_DEFINER_ENTRY(IP_TOS_O),
+	HWS_DEFINER_ENTRY(IP_TOS_I),
+	HWS_DEFINER_ENTRY(IPV6_FLOW_LABEL_O),
+	HWS_DEFINER_ENTRY(IPV6_FLOW_LABEL_I),
+	HWS_DEFINER_ENTRY(IPV6_DST_127_96_O),
+	HWS_DEFINER_ENTRY(IPV6_DST_95_64_O),
+	HWS_DEFINER_ENTRY(IPV6_DST_63_32_O),
+	HWS_DEFINER_ENTRY(IPV6_DST_31_0_O),
+	HWS_DEFINER_ENTRY(IPV6_DST_127_96_I),
+	HWS_DEFINER_ENTRY(IPV6_DST_95_64_I),
+	HWS_DEFINER_ENTRY(IPV6_DST_63_32_I),
+	HWS_DEFINER_ENTRY(IPV6_DST_31_0_I),
+	HWS_DEFINER_ENTRY(IPV6_SRC_127_96_O),
+	HWS_DEFINER_ENTRY(IPV6_SRC_95_64_O),
+	HWS_DEFINER_ENTRY(IPV6_SRC_63_32_O),
+	HWS_DEFINER_ENTRY(IPV6_SRC_31_0_O),
+	HWS_DEFINER_ENTRY(IPV6_SRC_127_96_I),
+	HWS_DEFINER_ENTRY(IPV6_SRC_95_64_I),
+	HWS_DEFINER_ENTRY(IPV6_SRC_63_32_I),
+	HWS_DEFINER_ENTRY(IPV6_SRC_31_0_I),
+	HWS_DEFINER_ENTRY(IP_PROTOCOL_O),
+	HWS_DEFINER_ENTRY(IP_PROTOCOL_I),
+	HWS_DEFINER_ENTRY(L4_SPORT_O),
+	HWS_DEFINER_ENTRY(L4_SPORT_I),
+	HWS_DEFINER_ENTRY(L4_DPORT_O),
+	HWS_DEFINER_ENTRY(L4_DPORT_I),
+	HWS_DEFINER_ENTRY(TCP_FLAGS_I),
+	HWS_DEFINER_ENTRY(TCP_FLAGS_O),
+	HWS_DEFINER_ENTRY(TCP_SEQ_NUM),
+	HWS_DEFINER_ENTRY(TCP_ACK_NUM),
+	HWS_DEFINER_ENTRY(GTP_TEID),
+	HWS_DEFINER_ENTRY(GTP_MSG_TYPE),
+	HWS_DEFINER_ENTRY(GTP_EXT_FLAG),
+	HWS_DEFINER_ENTRY(GTP_NEXT_EXT_HDR),
+	HWS_DEFINER_ENTRY(GTP_EXT_HDR_PDU),
+	HWS_DEFINER_ENTRY(GTP_EXT_HDR_QFI),
+	HWS_DEFINER_ENTRY(GTPU_DW0),
+	HWS_DEFINER_ENTRY(GTPU_FIRST_EXT_DW0),
+	HWS_DEFINER_ENTRY(GTPU_DW2),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_0),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_1),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_2),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_3),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_4),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_5),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_6),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_7),
+	HWS_DEFINER_ENTRY(VPORT_REG_C_0),
+	HWS_DEFINER_ENTRY(VXLAN_FLAGS),
+	HWS_DEFINER_ENTRY(VXLAN_VNI),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_FLAGS),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_RSVD0),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_PROTO),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_VNI),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_RSVD1),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_LEN),
+	HWS_DEFINER_ENTRY(GENEVE_OAM),
+	HWS_DEFINER_ENTRY(GENEVE_PROTO),
+	HWS_DEFINER_ENTRY(GENEVE_VNI),
+	HWS_DEFINER_ENTRY(SOURCE_QP),
+	HWS_DEFINER_ENTRY(SOURCE_GVMI),
+	HWS_DEFINER_ENTRY(REG_0),
+	HWS_DEFINER_ENTRY(REG_1),
+	HWS_DEFINER_ENTRY(REG_2),
+	HWS_DEFINER_ENTRY(REG_3),
+	HWS_DEFINER_ENTRY(REG_4),
+	HWS_DEFINER_ENTRY(REG_5),
+	HWS_DEFINER_ENTRY(REG_6),
+	HWS_DEFINER_ENTRY(REG_7),
+	HWS_DEFINER_ENTRY(REG_8),
+	HWS_DEFINER_ENTRY(REG_9),
+	HWS_DEFINER_ENTRY(REG_10),
+	HWS_DEFINER_ENTRY(REG_11),
+	HWS_DEFINER_ENTRY(REG_A),
+	HWS_DEFINER_ENTRY(REG_B),
+	HWS_DEFINER_ENTRY(GRE_KEY_PRESENT),
+	HWS_DEFINER_ENTRY(GRE_C),
+	HWS_DEFINER_ENTRY(GRE_K),
+	HWS_DEFINER_ENTRY(GRE_S),
+	HWS_DEFINER_ENTRY(GRE_PROTOCOL),
+	HWS_DEFINER_ENTRY(GRE_OPT_KEY),
+	HWS_DEFINER_ENTRY(GRE_OPT_SEQ),
+	HWS_DEFINER_ENTRY(GRE_OPT_CHECKSUM),
+	HWS_DEFINER_ENTRY(INTEGRITY_O),
+	HWS_DEFINER_ENTRY(INTEGRITY_I),
+	HWS_DEFINER_ENTRY(ICMP_DW1),
+	HWS_DEFINER_ENTRY(ICMP_DW2),
+	HWS_DEFINER_ENTRY(ICMP_DW3),
+	HWS_DEFINER_ENTRY(IPSEC_SPI),
+	HWS_DEFINER_ENTRY(IPSEC_SEQUENCE_NUMBER),
+	HWS_DEFINER_ENTRY(IPSEC_SYNDROME),
+	HWS_DEFINER_ENTRY(MPLS0_O),
+	HWS_DEFINER_ENTRY(MPLS1_O),
+	HWS_DEFINER_ENTRY(MPLS2_O),
+	HWS_DEFINER_ENTRY(MPLS3_O),
+	HWS_DEFINER_ENTRY(MPLS4_O),
+	HWS_DEFINER_ENTRY(MPLS0_I),
+	HWS_DEFINER_ENTRY(MPLS1_I),
+	HWS_DEFINER_ENTRY(MPLS2_I),
+	HWS_DEFINER_ENTRY(MPLS3_I),
+	HWS_DEFINER_ENTRY(MPLS4_I),
+	HWS_DEFINER_ENTRY(FLEX_PARSER0_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER1_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER2_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER3_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER4_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER5_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER6_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER7_OK),
+	HWS_DEFINER_ENTRY(OKS2_MPLS0_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS1_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS2_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS3_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS4_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS0_I),
+	HWS_DEFINER_ENTRY(OKS2_MPLS1_I),
+	HWS_DEFINER_ENTRY(OKS2_MPLS2_I),
+	HWS_DEFINER_ENTRY(OKS2_MPLS3_I),
+	HWS_DEFINER_ENTRY(OKS2_MPLS4_I),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_0),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_1),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_2),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_3),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_4),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_5),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_6),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_7),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_0),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_1),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_2),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_3),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_4),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_5),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_6),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_7),
+	HWS_DEFINER_ENTRY(IB_L4_OPCODE),
+	HWS_DEFINER_ENTRY(IB_L4_QPN),
+	HWS_DEFINER_ENTRY(IB_L4_A),
+	HWS_DEFINER_ENTRY(RANDOM_NUM),
+	HWS_DEFINER_ENTRY(PTYPE_L2_O),
+	HWS_DEFINER_ENTRY(PTYPE_L2_I),
+	HWS_DEFINER_ENTRY(PTYPE_L3_O),
+	HWS_DEFINER_ENTRY(PTYPE_L3_I),
+	HWS_DEFINER_ENTRY(PTYPE_L4_O),
+	HWS_DEFINER_ENTRY(PTYPE_L4_I),
+	HWS_DEFINER_ENTRY(PTYPE_L4_EXT_O),
+	HWS_DEFINER_ENTRY(PTYPE_L4_EXT_I),
+	HWS_DEFINER_ENTRY(PTYPE_FRAG_O),
+	HWS_DEFINER_ENTRY(PTYPE_FRAG_I),
+	HWS_DEFINER_ENTRY(TNL_HDR_0),
+	HWS_DEFINER_ENTRY(TNL_HDR_1),
+	HWS_DEFINER_ENTRY(TNL_HDR_2),
+	HWS_DEFINER_ENTRY(TNL_HDR_3),
+	[MLX5HWS_DEFINER_FNAME_MAX] = "DEFINER_FNAME_UNKNOWN",
+};
+
+const char *mlx5hws_definer_fname_to_str(enum mlx5hws_definer_fname fname)
+{
+	if (fname > MLX5HWS_DEFINER_FNAME_MAX)
+		fname = MLX5HWS_DEFINER_FNAME_MAX;
+	return hws_definer_fname_to_str[fname];
+}
+
 static void
 hws_definer_ones_set(struct mlx5hws_definer_fc *fc,
 		     void *match_param,
@@ -500,7 +712,8 @@ hws_definer_check_match_flags(struct mlx5hws_definer_conv_data *cd)
 	return 0;
 
 err_conflict:
-	mlx5hws_err(cd->ctx, "Invalid definer fields combination\n");
+	mlx5hws_err(cd->ctx, "Invalid definer fields combination: match_flags = 0x%08x\n",
+		    cd->match_flags);
 	return -EINVAL;
 }
 
@@ -508,18 +721,33 @@ static int
 hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 		       u32 *match_param)
 {
-	bool is_s_ipv6, is_d_ipv6, smac_set, dmac_set;
+	bool is_ipv6, smac_set, dmac_set, ip_addr_set, ip_ver_set;
 	struct mlx5hws_definer_fc *fc = cd->fc;
 	struct mlx5hws_definer_fc *curr_fc;
 	u32 *s_ipv6, *d_ipv6;
 
 	if (HWS_IS_FLD_SET_SZ(match_param, outer_headers.l4_type, 0x2) ||
-	    HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_c2, 0xe) ||
-	    HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_c4, 0x4)) {
+	    HWS_IS_FLD_SET_SZ(match_param, outer_headers.l4_type_ext, 0x4) ||
+	    HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_c6, 0xa) ||
+	    HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_d4, 0x4)) {
 		mlx5hws_err(cd->ctx, "Unsupported outer parameters set\n");
 		return -EINVAL;
 	}
 
+	ip_addr_set = HWS_IS_FLD_SET_SZ(match_param,
+					outer_headers.src_ipv4_src_ipv6,
+					0x80) ||
+		      HWS_IS_FLD_SET_SZ(match_param,
+					outer_headers.dst_ipv4_dst_ipv6, 0x80);
+	ip_ver_set = HWS_IS_FLD_SET(match_param, outer_headers.ip_version) ||
+		     HWS_IS_FLD_SET(match_param, outer_headers.ethertype);
+
+	if (ip_addr_set && !ip_ver_set) {
+		mlx5hws_err(cd->ctx,
+			    "Unsupported match on IP address without version or ethertype\n");
+		return -EINVAL;
+	}
+
 	/* L2 Check ethertype */
 	HWS_SET_HDR(fc, match_param, ETH_TYPE_O,
 		    outer_headers.ethertype,
@@ -558,6 +786,9 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 	HWS_SET_HDR(fc, match_param, IP_PROTOCOL_O,
 		    outer_headers.ip_protocol,
 		    eth_l3_outer.protocol_next_header);
+	HWS_SET_HDR(fc, match_param, IP_VERSION_O,
+		    outer_headers.ip_version,
+		    eth_l3_outer.ip_version);
 	HWS_SET_HDR(fc, match_param, IP_TTL_O,
 		    outer_headers.ttl_hoplimit,
 		    eth_l3_outer.time_to_live_hop_limit);
@@ -569,10 +800,16 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 			      outer_headers.dst_ipv4_dst_ipv6.ipv6_layout);
 
 	/* Assume IPv6 is used if ipv6 bits are set */
-	is_s_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2];
-	is_d_ipv6 = d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+	is_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2] ||
+		  d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+
+	/* IHL is an IPv4-specific field. */
+	if (is_ipv6 && HWS_IS_FLD_SET(match_param, outer_headers.ipv4_ihl)) {
+		mlx5hws_err(cd->ctx, "Unsupported match on IPv6 address and IPv4 IHL\n");
+		return -EINVAL;
+	}
 
-	if (is_s_ipv6) {
+	if (is_ipv6) {
 		/* Handle IPv6 source address */
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_127_96_O,
 			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -586,13 +823,6 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_31_0_O,
 			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_src_outer.ipv6_address_31_0);
-	} else {
-		/* Handle IPv4 source address */
-		HWS_SET_HDR(fc, match_param, IPV4_SRC_O,
-			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
-			    ipv4_src_dest_outer.source_address);
-	}
-	if (is_d_ipv6) {
 		/* Handle IPv6 destination address */
 		HWS_SET_HDR(fc, match_param, IPV6_DST_127_96_O,
 			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -607,6 +837,10 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_dst_outer.ipv6_address_31_0);
 	} else {
+		/* Handle IPv4 source address */
+		HWS_SET_HDR(fc, match_param, IPV4_SRC_O,
+			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv4_src_dest_outer.source_address);
 		/* Handle IPv4 destination address */
 		HWS_SET_HDR(fc, match_param, IPV4_DST_O,
 			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
@@ -664,18 +898,33 @@ static int
 hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 		       u32 *match_param)
 {
-	bool is_s_ipv6, is_d_ipv6, smac_set, dmac_set;
+	bool is_ipv6, smac_set, dmac_set, ip_addr_set, ip_ver_set;
 	struct mlx5hws_definer_fc *fc = cd->fc;
 	struct mlx5hws_definer_fc *curr_fc;
 	u32 *s_ipv6, *d_ipv6;
 
 	if (HWS_IS_FLD_SET_SZ(match_param, inner_headers.l4_type, 0x2) ||
-	    HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_c2, 0xe) ||
-	    HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_c4, 0x4)) {
+	    HWS_IS_FLD_SET_SZ(match_param, inner_headers.l4_type_ext, 0x4) ||
+	    HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_c6, 0xa) ||
+	    HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_d4, 0x4)) {
 		mlx5hws_err(cd->ctx, "Unsupported inner parameters set\n");
 		return -EINVAL;
 	}
 
+	ip_addr_set = HWS_IS_FLD_SET_SZ(match_param,
+					inner_headers.src_ipv4_src_ipv6,
+					0x80) ||
+		      HWS_IS_FLD_SET_SZ(match_param,
+					inner_headers.dst_ipv4_dst_ipv6, 0x80);
+	ip_ver_set = HWS_IS_FLD_SET(match_param, inner_headers.ip_version) ||
+		     HWS_IS_FLD_SET(match_param, inner_headers.ethertype);
+
+	if (ip_addr_set && !ip_ver_set) {
+		mlx5hws_err(cd->ctx,
+			    "Unsupported match on IP address without version or ethertype\n");
+		return -EINVAL;
+	}
+
 	/* L2 Check ethertype */
 	HWS_SET_HDR(fc, match_param, ETH_TYPE_I,
 		    inner_headers.ethertype,
@@ -727,10 +976,16 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 			      inner_headers.dst_ipv4_dst_ipv6.ipv6_layout);
 
 	/* Assume IPv6 is used if ipv6 bits are set */
-	is_s_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2];
-	is_d_ipv6 = d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+	is_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2] ||
+		  d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+
+	/* IHL is an IPv4-specific field. */
+	if (is_ipv6 && HWS_IS_FLD_SET(match_param, inner_headers.ipv4_ihl)) {
+		mlx5hws_err(cd->ctx, "Unsupported match on IPv6 address and IPv4 IHL\n");
+		return -EINVAL;
+	}
 
-	if (is_s_ipv6) {
+	if (is_ipv6) {
 		/* Handle IPv6 source address */
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_127_96_I,
 			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -744,13 +999,6 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_31_0_I,
 			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_src_inner.ipv6_address_31_0);
-	} else {
-		/* Handle IPv4 source address */
-		HWS_SET_HDR(fc, match_param, IPV4_SRC_I,
-			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
-			    ipv4_src_dest_inner.source_address);
-	}
-	if (is_d_ipv6) {
 		/* Handle IPv6 destination address */
 		HWS_SET_HDR(fc, match_param, IPV6_DST_127_96_I,
 			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -765,6 +1013,10 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_dst_inner.ipv6_address_31_0);
 	} else {
+		/* Handle IPv4 source address */
+		HWS_SET_HDR(fc, match_param, IPV4_SRC_I,
+			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv4_src_dest_inner.source_address);
 		/* Handle IPv4 destination address */
 		HWS_SET_HDR(fc, match_param, IPV4_DST_I,
 			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
@@ -1028,8 +1280,9 @@ hws_definer_conv_misc2(struct mlx5hws_definer_conv_data *cd,
 	struct mlx5hws_definer_fc *fc = cd->fc;
 	struct mlx5hws_definer_fc *curr_fc;
 
-	if (HWS_IS_FLD_SET_SZ(match_param, misc_parameters_2.reserved_at_1a0, 0x8) ||
-	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters_2.reserved_at_1b8, 0x8) ||
+	if (HWS_IS_FLD_SET_SZ(match_param, misc_parameters_2.psp_syndrome, 0x8) ||
+	    HWS_IS_FLD_SET_SZ(match_param,
+			      misc_parameters_2.ipsec_next_header, 0x8) ||
 	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters_2.reserved_at_1c0, 0x40) ||
 	    HWS_IS_FLD_SET(match_param, misc_parameters_2.macsec_syndrome) ||
 	    HWS_IS_FLD_SET(match_param, misc_parameters_2.ipsec_syndrome)) {
@@ -1578,80 +1831,6 @@ err_free_fc:
 	return ret;
 }
 
-struct mlx5hws_definer_fc *
-mlx5hws_definer_conv_match_params_to_compressed_fc(struct mlx5hws_context *ctx,
-						   u8 match_criteria_enable,
-						   u32 *match_param,
-						   int *fc_sz)
-{
-	struct mlx5hws_definer_fc *compressed_fc = NULL;
-	struct mlx5hws_definer_conv_data cd = {0};
-	struct mlx5hws_definer_fc *fc;
-	int ret;
-
-	fc = hws_definer_alloc_fc(ctx, MLX5HWS_DEFINER_FNAME_MAX);
-	if (!fc)
-		return NULL;
-
-	cd.fc = fc;
-	cd.ctx = ctx;
-
-	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_OUTER) {
-		ret = hws_definer_conv_outer(&cd, match_param);
-		if (ret)
-			goto err_free_fc;
-	}
-
-	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_INNER) {
-		ret = hws_definer_conv_inner(&cd, match_param);
-		if (ret)
-			goto err_free_fc;
-	}
-
-	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC) {
-		ret = hws_definer_conv_misc(&cd, match_param);
-		if (ret)
-			goto err_free_fc;
-	}
-
-	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC2) {
-		ret = hws_definer_conv_misc2(&cd, match_param);
-		if (ret)
-			goto err_free_fc;
-	}
-
-	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC3) {
-		ret = hws_definer_conv_misc3(&cd, match_param);
-		if (ret)
-			goto err_free_fc;
-	}
-
-	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC4) {
-		ret = hws_definer_conv_misc4(&cd, match_param);
-		if (ret)
-			goto err_free_fc;
-	}
-
-	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC5) {
-		ret = hws_definer_conv_misc5(&cd, match_param);
-		if (ret)
-			goto err_free_fc;
-	}
-
-	/* Allocate fc array on mt */
-	compressed_fc = hws_definer_alloc_compressed_fc(fc);
-	if (!compressed_fc) {
-		mlx5hws_err(ctx,
-			    "Convert to compressed fc: failed to set field copy to match template\n");
-		goto err_free_fc;
-	}
-	*fc_sz = hws_definer_get_fc_size(fc);
-
-err_free_fc:
-	kfree(fc);
-	return compressed_fc;
-}
-
 static int
 hws_definer_find_byte_in_tag(struct mlx5hws_definer *definer,
 			     u32 hl_byte_off,
@@ -1814,7 +1993,7 @@ hws_definer_copy_sel_ctrl(struct mlx5hws_definer_sel_ctrl *ctrl,
 static int
 hws_definer_find_best_match_fit(struct mlx5hws_context *ctx,
 				struct mlx5hws_definer *definer,
-				u8 *hl)
+				u8 *hl, bool allow_jumbo)
 {
 	struct mlx5hws_definer_sel_ctrl ctrl = {0};
 	bool found;
@@ -1831,6 +2010,9 @@ hws_definer_find_best_match_fit(struct mlx5hws_context *ctx,
 		return 0;
 	}
 
+	if (!allow_jumbo)
+		return -E2BIG;
+
 	/* Try to create a full/limited jumbo definer */
 	ctrl.allowed_full_dw = ctx->caps->full_dw_jumbo_support ? DW_SELECTORS :
 								  DW_SELECTORS_MATCH;
@@ -1907,7 +2089,8 @@ int mlx5hws_definer_compare(struct mlx5hws_definer *definer_a,
 int
 mlx5hws_definer_calc_layout(struct mlx5hws_context *ctx,
 			    struct mlx5hws_match_template *mt,
-			    struct mlx5hws_definer *match_definer)
+			    struct mlx5hws_definer *match_definer,
+			    bool allow_jumbo)
 {
 	u8 *match_hl;
 	int ret;
@@ -1929,7 +2112,8 @@ mlx5hws_definer_calc_layout(struct mlx5hws_context *ctx,
 	}
 
 	/* Find the match definer layout for header layout match union */
-	ret = hws_definer_find_best_match_fit(ctx, match_definer, match_hl);
+	ret = hws_definer_find_best_match_fit(ctx, match_definer, match_hl,
+					      allow_jumbo);
 	if (ret) {
 		if (ret == -E2BIG)
 			mlx5hws_dbg(ctx,
@@ -1985,8 +2169,7 @@ int mlx5hws_definer_get_obj(struct mlx5hws_context *ctx,
 			continue;
 
 		/* Reuse definer and set LRU (move to be first in the list) */
-		list_del_init(&cached_definer->list_node);
-		list_add(&cached_definer->list_node, &cache->list_head);
+		list_move(&cached_definer->list_node, &cache->list_head);
 		cached_definer->refcount++;
 		return cached_definer->definer.obj_id;
 	}
@@ -2118,7 +2301,7 @@ int mlx5hws_definer_mt_init(struct mlx5hws_context *ctx,
 	struct mlx5hws_definer match_layout = {0};
 	int ret;
 
-	ret = mlx5hws_definer_calc_layout(ctx, mt, &match_layout);
+	ret = mlx5hws_definer_calc_layout(ctx, mt, &match_layout, true);
 	if (ret) {
 		mlx5hws_err(ctx, "Failed to calculate matcher definer layout\n");
 		return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h
index 9432d5084def..141f3eb2e307 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h
@@ -785,7 +785,7 @@ struct mlx5hws_definer_cache {
 
 struct mlx5hws_definer_cache_item {
 	struct mlx5hws_definer definer;
-	u32 refcount;
+	u32 refcount; /* protected by context ctrl lock */
 	struct list_head list_node;
 };
 
@@ -823,12 +823,9 @@ void mlx5hws_definer_free(struct mlx5hws_context *ctx,
 
 int mlx5hws_definer_calc_layout(struct mlx5hws_context *ctx,
 				struct mlx5hws_match_template *mt,
-				struct mlx5hws_definer *match_definer);
+				struct mlx5hws_definer *match_definer,
+				bool allow_jumbo);
 
-struct mlx5hws_definer_fc *
-mlx5hws_definer_conv_match_params_to_compressed_fc(struct mlx5hws_context *ctx,
-						   u8 match_criteria_enable,
-						   u32 *match_param,
-						   int *fc_sz);
+const char *mlx5hws_definer_fname_to_str(enum mlx5hws_definer_fname fname);
 
 #endif /* HWS_DEFINER_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
new file mode 100644
index 000000000000..6a4c4cccd643
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
@@ -0,0 +1,1641 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#include <linux/mlx5/vport.h>
+#include <mlx5_core.h>
+#include <fs_core.h>
+#include <fs_cmd.h>
+#include "fs_hws_pools.h"
+#include "mlx5hws.h"
+
+#define MLX5HWS_CTX_MAX_NUM_OF_QUEUES 16
+#define MLX5HWS_CTX_QUEUE_SIZE 256
+
+static struct mlx5hws_action *
+mlx5_fs_create_action_remove_header_vlan(struct mlx5hws_context *ctx);
+static void
+mlx5_fs_destroy_pr_pool(struct mlx5_fs_pool *pool, struct xarray *pr_pools,
+			unsigned long index);
+static void
+mlx5_fs_destroy_mh_pool(struct mlx5_fs_pool *pool, struct xarray *mh_pools,
+			unsigned long index);
+
+static int mlx5_fs_init_hws_actions_pool(struct mlx5_core_dev *dev,
+					 struct mlx5_fs_hws_context *fs_ctx)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5_fs_hws_actions_pool *hws_pool = &fs_ctx->hws_pool;
+	struct mlx5hws_action_reformat_header reformat_hdr = {};
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	enum mlx5hws_action_type action_type;
+	int err = -ENOSPC;
+
+	hws_pool->tag_action = mlx5hws_action_create_tag(ctx, flags);
+	if (!hws_pool->tag_action)
+		return err;
+	hws_pool->pop_vlan_action = mlx5hws_action_create_pop_vlan(ctx, flags);
+	if (!hws_pool->pop_vlan_action)
+		goto destroy_tag;
+	hws_pool->push_vlan_action = mlx5hws_action_create_push_vlan(ctx, flags);
+	if (!hws_pool->push_vlan_action)
+		goto destroy_pop_vlan;
+	hws_pool->drop_action = mlx5hws_action_create_dest_drop(ctx, flags);
+	if (!hws_pool->drop_action)
+		goto destroy_push_vlan;
+	action_type = MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2;
+	hws_pool->decapl2_action =
+		mlx5hws_action_create_reformat(ctx, action_type, 1,
+					       &reformat_hdr, 0, flags);
+	if (!hws_pool->decapl2_action)
+		goto destroy_drop;
+	hws_pool->remove_hdr_vlan_action =
+		mlx5_fs_create_action_remove_header_vlan(ctx);
+	if (!hws_pool->remove_hdr_vlan_action)
+		goto destroy_decapl2;
+	err = mlx5_fs_hws_pr_pool_init(&hws_pool->insert_hdr_pool, dev, 0,
+				       MLX5HWS_ACTION_TYP_INSERT_HEADER);
+	if (err)
+		goto destroy_remove_hdr;
+	err = mlx5_fs_hws_pr_pool_init(&hws_pool->dl3tnltol2_pool, dev, 0,
+				       MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2);
+	if (err)
+		goto cleanup_insert_hdr;
+	xa_init(&hws_pool->el2tol3tnl_pools);
+	xa_init(&hws_pool->el2tol2tnl_pools);
+	xa_init(&hws_pool->mh_pools);
+	xa_init(&hws_pool->table_dests);
+	xa_init(&hws_pool->vport_dests);
+	xa_init(&hws_pool->vport_vhca_dests);
+	xa_init(&hws_pool->aso_meters);
+	xa_init(&hws_pool->sample_dests);
+	return 0;
+
+cleanup_insert_hdr:
+	mlx5_fs_hws_pr_pool_cleanup(&hws_pool->insert_hdr_pool);
+destroy_remove_hdr:
+	mlx5hws_action_destroy(hws_pool->remove_hdr_vlan_action);
+destroy_decapl2:
+	mlx5hws_action_destroy(hws_pool->decapl2_action);
+destroy_drop:
+	mlx5hws_action_destroy(hws_pool->drop_action);
+destroy_push_vlan:
+	mlx5hws_action_destroy(hws_pool->push_vlan_action);
+destroy_pop_vlan:
+	mlx5hws_action_destroy(hws_pool->pop_vlan_action);
+destroy_tag:
+	mlx5hws_action_destroy(hws_pool->tag_action);
+	return err;
+}
+
+static void mlx5_fs_cleanup_hws_actions_pool(struct mlx5_fs_hws_context *fs_ctx)
+{
+	struct mlx5_fs_hws_actions_pool *hws_pool = &fs_ctx->hws_pool;
+	struct mlx5_fs_hws_data *fs_hws_data;
+	struct mlx5hws_action *action;
+	struct mlx5_fs_pool *pool;
+	unsigned long i;
+
+	xa_for_each(&hws_pool->sample_dests, i, fs_hws_data)
+		kfree(fs_hws_data);
+	xa_destroy(&hws_pool->sample_dests);
+	xa_for_each(&hws_pool->aso_meters, i, fs_hws_data)
+		kfree(fs_hws_data);
+	xa_destroy(&hws_pool->aso_meters);
+	xa_for_each(&hws_pool->vport_vhca_dests, i, action)
+		mlx5hws_action_destroy(action);
+	xa_destroy(&hws_pool->vport_vhca_dests);
+	xa_for_each(&hws_pool->vport_dests, i, action)
+		mlx5hws_action_destroy(action);
+	xa_destroy(&hws_pool->vport_dests);
+	xa_destroy(&hws_pool->table_dests);
+	xa_for_each(&hws_pool->mh_pools, i, pool)
+		mlx5_fs_destroy_mh_pool(pool, &hws_pool->mh_pools, i);
+	xa_destroy(&hws_pool->mh_pools);
+	xa_for_each(&hws_pool->el2tol2tnl_pools, i, pool)
+		mlx5_fs_destroy_pr_pool(pool, &hws_pool->el2tol2tnl_pools, i);
+	xa_destroy(&hws_pool->el2tol2tnl_pools);
+	xa_for_each(&hws_pool->el2tol3tnl_pools, i, pool)
+		mlx5_fs_destroy_pr_pool(pool, &hws_pool->el2tol3tnl_pools, i);
+	xa_destroy(&hws_pool->el2tol3tnl_pools);
+	mlx5_fs_hws_pr_pool_cleanup(&hws_pool->dl3tnltol2_pool);
+	mlx5_fs_hws_pr_pool_cleanup(&hws_pool->insert_hdr_pool);
+	mlx5hws_action_destroy(hws_pool->remove_hdr_vlan_action);
+	mlx5hws_action_destroy(hws_pool->decapl2_action);
+	mlx5hws_action_destroy(hws_pool->drop_action);
+	mlx5hws_action_destroy(hws_pool->push_vlan_action);
+	mlx5hws_action_destroy(hws_pool->pop_vlan_action);
+	mlx5hws_action_destroy(hws_pool->tag_action);
+}
+
+static int mlx5_cmd_hws_create_ns(struct mlx5_flow_root_namespace *ns)
+{
+	struct mlx5hws_context_attr hws_ctx_attr = {};
+	int err;
+
+	hws_ctx_attr.queues = min_t(int, num_online_cpus(),
+				    MLX5HWS_CTX_MAX_NUM_OF_QUEUES);
+	hws_ctx_attr.queue_size = MLX5HWS_CTX_QUEUE_SIZE;
+
+	ns->fs_hws_context.hws_ctx =
+		mlx5hws_context_open(ns->dev, &hws_ctx_attr);
+	if (!ns->fs_hws_context.hws_ctx) {
+		mlx5_core_err(ns->dev, "Failed to create hws flow namespace\n");
+		return -EINVAL;
+	}
+	err = mlx5_fs_init_hws_actions_pool(ns->dev, &ns->fs_hws_context);
+	if (err) {
+		mlx5_core_err(ns->dev, "Failed to init hws actions pool\n");
+		mlx5hws_context_close(ns->fs_hws_context.hws_ctx);
+		return err;
+	}
+	return 0;
+}
+
+static int mlx5_cmd_hws_destroy_ns(struct mlx5_flow_root_namespace *ns)
+{
+	mlx5_fs_cleanup_hws_actions_pool(&ns->fs_hws_context);
+	return mlx5hws_context_close(ns->fs_hws_context.hws_ctx);
+}
+
+static int mlx5_cmd_hws_set_peer(struct mlx5_flow_root_namespace *ns,
+				 struct mlx5_flow_root_namespace *peer_ns,
+				 u16 peer_vhca_id)
+{
+	struct mlx5hws_context *peer_ctx = NULL;
+
+	if (peer_ns)
+		peer_ctx = peer_ns->fs_hws_context.hws_ctx;
+	mlx5hws_context_set_peer(ns->fs_hws_context.hws_ctx, peer_ctx,
+				 peer_vhca_id);
+	return 0;
+}
+
+static int mlx5_fs_set_ft_default_miss(struct mlx5_flow_root_namespace *ns,
+				       struct mlx5_flow_table *ft,
+				       struct mlx5_flow_table *next_ft)
+{
+	struct mlx5hws_table *next_tbl;
+	int err;
+
+	if (!ns->fs_hws_context.hws_ctx)
+		return -EINVAL;
+
+	/* if no change required, return */
+	if (!next_ft && !ft->fs_hws_table.miss_ft_set)
+		return 0;
+
+	next_tbl = next_ft ? next_ft->fs_hws_table.hws_table : NULL;
+	err = mlx5hws_table_set_default_miss(ft->fs_hws_table.hws_table, next_tbl);
+	if (err) {
+		mlx5_core_err(ns->dev, "Failed setting FT default miss (%d)\n", err);
+		return err;
+	}
+	ft->fs_hws_table.miss_ft_set = !!next_tbl;
+	return 0;
+}
+
+static int mlx5_fs_add_flow_table_dest_action(struct mlx5_flow_root_namespace *ns,
+					      struct mlx5_flow_table *ft)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context;
+	struct mlx5hws_action *dest_ft_action;
+	struct xarray *dests_xa;
+	int err;
+
+	dest_ft_action = mlx5hws_action_create_dest_table_num(fs_ctx->hws_ctx,
+							      ft->id, flags);
+	if (!dest_ft_action) {
+		mlx5_core_err(ns->dev, "Failed creating dest table action\n");
+		return -ENOMEM;
+	}
+
+	dests_xa = &fs_ctx->hws_pool.table_dests;
+	err = xa_insert(dests_xa, ft->id, dest_ft_action, GFP_KERNEL);
+	if (err)
+		mlx5hws_action_destroy(dest_ft_action);
+	return err;
+}
+
+static int mlx5_fs_del_flow_table_dest_action(struct mlx5_flow_root_namespace *ns,
+					      struct mlx5_flow_table *ft)
+{
+	struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context;
+	struct mlx5hws_action *dest_ft_action;
+	struct xarray *dests_xa;
+	int err;
+
+	dests_xa = &fs_ctx->hws_pool.table_dests;
+	dest_ft_action = xa_erase(dests_xa, ft->id);
+	if (!dest_ft_action) {
+		mlx5_core_err(ns->dev, "Failed to erase dest ft action\n");
+		return -ENOENT;
+	}
+
+	err = mlx5hws_action_destroy(dest_ft_action);
+	if (err)
+		mlx5_core_err(ns->dev, "Failed to destroy dest ft action\n");
+	return err;
+}
+
+static int mlx5_cmd_hws_create_flow_table(struct mlx5_flow_root_namespace *ns,
+					  struct mlx5_flow_table *ft,
+					  struct mlx5_flow_table_attr *ft_attr,
+					  struct mlx5_flow_table *next_ft)
+{
+	struct mlx5hws_context *ctx = ns->fs_hws_context.hws_ctx;
+	struct mlx5hws_table_attr tbl_attr = {};
+	struct mlx5hws_table *tbl;
+	int err;
+
+	if (mlx5_fs_cmd_is_fw_term_table(ft)) {
+		err = mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft, ft_attr,
+								   next_ft);
+		if (err)
+			return err;
+		err = mlx5_fs_add_flow_table_dest_action(ns, ft);
+		if (err)
+			mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft);
+		return err;
+	}
+
+	if (ns->table_type != FS_FT_FDB) {
+		mlx5_core_err(ns->dev, "Table type %d not supported for HWS\n",
+			      ns->table_type);
+		return -EOPNOTSUPP;
+	}
+
+	tbl_attr.type = MLX5HWS_TABLE_TYPE_FDB;
+	tbl_attr.level = ft_attr->level;
+	tbl_attr.uid = ft_attr->uid;
+	tbl = mlx5hws_table_create(ctx, &tbl_attr);
+	if (!tbl) {
+		mlx5_core_err(ns->dev, "Failed creating hws flow_table\n");
+		return -EINVAL;
+	}
+
+	ft->fs_hws_table.hws_table = tbl;
+	ft->id = mlx5hws_table_get_id(tbl);
+
+	if (next_ft) {
+		err = mlx5_fs_set_ft_default_miss(ns, ft, next_ft);
+		if (err)
+			goto destroy_table;
+	}
+
+	ft->max_fte = INT_MAX;
+
+	err = mlx5_fs_add_flow_table_dest_action(ns, ft);
+	if (err)
+		goto clear_ft_miss;
+	return 0;
+
+clear_ft_miss:
+	mlx5_fs_set_ft_default_miss(ns, ft, NULL);
+destroy_table:
+	mlx5hws_table_destroy(tbl);
+	ft->fs_hws_table.hws_table = NULL;
+	return err;
+}
+
+static int mlx5_cmd_hws_destroy_flow_table(struct mlx5_flow_root_namespace *ns,
+					   struct mlx5_flow_table *ft)
+{
+	int err;
+
+	err = mlx5_fs_del_flow_table_dest_action(ns, ft);
+	if (err)
+		mlx5_core_err(ns->dev, "Failed to remove dest action (%d)\n", err);
+
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft);
+
+	err = mlx5_fs_set_ft_default_miss(ns, ft, NULL);
+	if (err)
+		mlx5_core_err(ns->dev, "Failed to disconnect next table (%d)\n", err);
+
+	err = mlx5hws_table_destroy(ft->fs_hws_table.hws_table);
+	if (err)
+		mlx5_core_err(ns->dev, "Failed to destroy flow_table (%d)\n", err);
+
+	return err;
+}
+
+static int mlx5_cmd_hws_modify_flow_table(struct mlx5_flow_root_namespace *ns,
+					  struct mlx5_flow_table *ft,
+					  struct mlx5_flow_table *next_ft)
+{
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->modify_flow_table(ns, ft, next_ft);
+
+	return mlx5_fs_set_ft_default_miss(ns, ft, next_ft);
+}
+
+static int mlx5_cmd_hws_update_root_ft(struct mlx5_flow_root_namespace *ns,
+				       struct mlx5_flow_table *ft,
+				       u32 underlay_qpn,
+				       bool disconnect)
+{
+	return mlx5_fs_cmd_get_fw_cmds()->update_root_ft(ns, ft, underlay_qpn,
+							 disconnect);
+}
+
+static int mlx5_cmd_hws_create_flow_group(struct mlx5_flow_root_namespace *ns,
+					  struct mlx5_flow_table *ft, u32 *in,
+					  struct mlx5_flow_group *fg)
+{
+	struct mlx5hws_match_parameters mask;
+	struct mlx5hws_bwc_matcher *matcher;
+	u8 match_criteria_enable;
+	u32 priority;
+
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->create_flow_group(ns, ft, in, fg);
+
+	mask.match_buf = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+	mask.match_sz = sizeof(fg->mask.match_criteria);
+
+	match_criteria_enable = MLX5_GET(create_flow_group_in, in,
+					 match_criteria_enable);
+	priority = MLX5_GET(create_flow_group_in, in, start_flow_index);
+	matcher = mlx5hws_bwc_matcher_create(ft->fs_hws_table.hws_table,
+					     priority, match_criteria_enable,
+					     &mask);
+	if (!matcher) {
+		mlx5_core_err(ns->dev, "Failed creating matcher\n");
+		return -EINVAL;
+	}
+
+	fg->fs_hws_matcher.matcher = matcher;
+	return 0;
+}
+
+static int mlx5_cmd_hws_destroy_flow_group(struct mlx5_flow_root_namespace *ns,
+					   struct mlx5_flow_table *ft,
+					   struct mlx5_flow_group *fg)
+{
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_group(ns, ft, fg);
+
+	return mlx5hws_bwc_matcher_destroy(fg->fs_hws_matcher.matcher);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_dest_action_ft(struct mlx5_fs_hws_context *fs_ctx,
+			   struct mlx5_flow_rule *dst)
+{
+	return xa_load(&fs_ctx->hws_pool.table_dests, dst->dest_attr.ft->id);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_dest_action_table_num(struct mlx5_fs_hws_context *fs_ctx,
+				  struct mlx5_flow_rule *dst)
+{
+	u32 table_num = dst->dest_attr.ft_num;
+
+	return xa_load(&fs_ctx->hws_pool.table_dests, table_num);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_create_dest_action_table_num(struct mlx5_fs_hws_context *fs_ctx,
+				     struct mlx5_flow_rule *dst)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	u32 table_num = dst->dest_attr.ft_num;
+
+	return mlx5hws_action_create_dest_table_num(ctx, table_num, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_dest_action_vport(struct mlx5_fs_hws_context *fs_ctx,
+			      struct mlx5_flow_rule *dst,
+			      bool is_dest_type_uplink)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5_flow_destination *dest_attr = &dst->dest_attr;
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	struct mlx5hws_action *dest;
+	struct xarray *dests_xa;
+	bool vhca_id_valid;
+	unsigned long idx;
+	u16 vport_num;
+	int err;
+
+	vhca_id_valid = is_dest_type_uplink ||
+			(dest_attr->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID);
+	vport_num = is_dest_type_uplink ? MLX5_VPORT_UPLINK : dest_attr->vport.num;
+	if (vhca_id_valid) {
+		dests_xa = &fs_ctx->hws_pool.vport_vhca_dests;
+		idx = (unsigned long)dest_attr->vport.vhca_id << 16 | vport_num;
+	} else {
+		dests_xa = &fs_ctx->hws_pool.vport_dests;
+		idx = vport_num;
+	}
+dest_load:
+	dest = xa_load(dests_xa, idx);
+	if (dest)
+		return dest;
+
+	dest = mlx5hws_action_create_dest_vport(ctx, vport_num,	vhca_id_valid,
+						dest_attr->vport.vhca_id, flags);
+
+	err = xa_insert(dests_xa, idx, dest, GFP_KERNEL);
+	if (err) {
+		mlx5hws_action_destroy(dest);
+		dest = NULL;
+
+		if (err == -EBUSY)
+			/* xarray entry was already stored by another thread */
+			goto dest_load;
+	}
+
+	return dest;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_create_dest_action_range(struct mlx5hws_context *ctx,
+				 struct mlx5_flow_rule *dst)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5_flow_destination *dest_attr = &dst->dest_attr;
+
+	return mlx5hws_action_create_dest_match_range(ctx,
+						      dest_attr->range.field,
+						      dest_attr->range.hit_ft,
+						      dest_attr->range.miss_ft,
+						      dest_attr->range.min,
+						      dest_attr->range.max,
+						      flags);
+}
+
+static struct mlx5_fs_hws_data *
+mlx5_fs_get_cached_hws_data(struct xarray *cache_xa, unsigned long index)
+{
+	struct mlx5_fs_hws_data *fs_hws_data;
+	int err;
+
+	xa_lock(cache_xa);
+	fs_hws_data = xa_load(cache_xa, index);
+	if (!fs_hws_data) {
+		fs_hws_data = kzalloc(sizeof(*fs_hws_data), GFP_ATOMIC);
+		if (!fs_hws_data) {
+			xa_unlock(cache_xa);
+			return NULL;
+		}
+		refcount_set(&fs_hws_data->hws_action_refcount, 0);
+		mutex_init(&fs_hws_data->lock);
+		err = __xa_insert(cache_xa, index, fs_hws_data, GFP_ATOMIC);
+		if (err) {
+			kfree(fs_hws_data);
+			xa_unlock(cache_xa);
+			return NULL;
+		}
+	}
+	xa_unlock(cache_xa);
+
+	return fs_hws_data;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_action_aso_meter(struct mlx5_fs_hws_context *fs_ctx,
+			     struct mlx5_exe_aso *exe_aso)
+{
+	struct mlx5_fs_hws_create_action_ctx create_ctx;
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	struct mlx5_fs_hws_data *meter_hws_data;
+	u32 id = exe_aso->base_id;
+	struct xarray *meters_xa;
+
+	meters_xa = &fs_ctx->hws_pool.aso_meters;
+	meter_hws_data = mlx5_fs_get_cached_hws_data(meters_xa, id);
+	if (!meter_hws_data)
+		return NULL;
+
+	create_ctx.hws_ctx = ctx;
+	create_ctx.actions_type = MLX5HWS_ACTION_TYP_ASO_METER;
+	create_ctx.id = id;
+	create_ctx.return_reg_id = exe_aso->return_reg_id;
+
+	return mlx5_fs_get_hws_action(meter_hws_data, &create_ctx);
+}
+
+static void mlx5_fs_put_action_aso_meter(struct mlx5_fs_hws_context *fs_ctx,
+					 struct mlx5_exe_aso *exe_aso)
+{
+	struct mlx5_fs_hws_data *meter_hws_data;
+	struct xarray *meters_xa;
+
+	meters_xa = &fs_ctx->hws_pool.aso_meters;
+	meter_hws_data = xa_load(meters_xa, exe_aso->base_id);
+	if (!meter_hws_data)
+		return;
+	return mlx5_fs_put_hws_action(meter_hws_data);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_dest_action_sampler(struct mlx5_fs_hws_context *fs_ctx,
+				struct mlx5_flow_rule *dst)
+{
+	struct mlx5_fs_hws_create_action_ctx create_ctx;
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	struct mlx5_fs_hws_data *sampler_hws_data;
+	u32 id = dst->dest_attr.sampler_id;
+	struct xarray *sampler_xa;
+
+	sampler_xa = &fs_ctx->hws_pool.sample_dests;
+	sampler_hws_data = mlx5_fs_get_cached_hws_data(sampler_xa, id);
+	if (!sampler_hws_data)
+		return NULL;
+
+	create_ctx.hws_ctx = ctx;
+	create_ctx.actions_type = MLX5HWS_ACTION_TYP_SAMPLER;
+	create_ctx.id = id;
+
+	return mlx5_fs_get_hws_action(sampler_hws_data, &create_ctx);
+}
+
+static void mlx5_fs_put_dest_action_sampler(struct mlx5_fs_hws_context *fs_ctx,
+					    u32 sampler_id)
+{
+	struct mlx5_fs_hws_data *sampler_hws_data;
+	struct xarray *sampler_xa;
+
+	sampler_xa = &fs_ctx->hws_pool.sample_dests;
+	sampler_hws_data = xa_load(sampler_xa, sampler_id);
+	if (!sampler_hws_data)
+		return;
+
+	mlx5_fs_put_hws_action(sampler_hws_data);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_create_action_dest_array(struct mlx5hws_context *ctx,
+				 struct mlx5hws_action_dest_attr *dests,
+				 u32 num_of_dests)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+
+	return mlx5hws_action_create_dest_array(ctx, num_of_dests, dests,
+						flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_action_push_vlan(struct mlx5_fs_hws_context *fs_ctx)
+{
+	return fs_ctx->hws_pool.push_vlan_action;
+}
+
+static u32 mlx5_fs_calc_vlan_hdr(struct mlx5_fs_vlan *vlan)
+{
+	u16 n_ethtype = vlan->ethtype;
+	u8 prio = vlan->prio;
+	u16 vid = vlan->vid;
+
+	return (u32)n_ethtype << 16 | (u32)(prio) << 12 | (u32)vid;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_action_pop_vlan(struct mlx5_fs_hws_context *fs_ctx)
+{
+	return fs_ctx->hws_pool.pop_vlan_action;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_action_decap_tnl_l2_to_l2(struct mlx5_fs_hws_context *fs_ctx)
+{
+	return fs_ctx->hws_pool.decapl2_action;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_dest_action_drop(struct mlx5_fs_hws_context *fs_ctx)
+{
+	return fs_ctx->hws_pool.drop_action;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_action_tag(struct mlx5_fs_hws_context *fs_ctx)
+{
+	return fs_ctx->hws_pool.tag_action;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_create_action_last(struct mlx5hws_context *ctx)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+
+	return mlx5hws_action_create_last(ctx, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_create_hws_action(struct mlx5_fs_hws_create_action_ctx *create_ctx)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+
+	switch (create_ctx->actions_type) {
+	case MLX5HWS_ACTION_TYP_CTR:
+		return mlx5hws_action_create_counter(create_ctx->hws_ctx,
+						     create_ctx->id, flags);
+	case MLX5HWS_ACTION_TYP_ASO_METER:
+		return mlx5hws_action_create_aso_meter(create_ctx->hws_ctx,
+						       create_ctx->id,
+						       create_ctx->return_reg_id,
+						       flags);
+	case MLX5HWS_ACTION_TYP_SAMPLER:
+		return mlx5hws_action_create_flow_sampler(create_ctx->hws_ctx,
+							  create_ctx->id, flags);
+	default:
+		return NULL;
+	}
+}
+
+struct mlx5hws_action *
+mlx5_fs_get_hws_action(struct mlx5_fs_hws_data *fs_hws_data,
+		       struct mlx5_fs_hws_create_action_ctx *create_ctx)
+{
+	/* try avoid locking if not necessary */
+	if (refcount_inc_not_zero(&fs_hws_data->hws_action_refcount))
+		return fs_hws_data->hws_action;
+
+	mutex_lock(&fs_hws_data->lock);
+	if (refcount_inc_not_zero(&fs_hws_data->hws_action_refcount)) {
+		mutex_unlock(&fs_hws_data->lock);
+		return fs_hws_data->hws_action;
+	}
+	fs_hws_data->hws_action = mlx5_fs_create_hws_action(create_ctx);
+	if (!fs_hws_data->hws_action) {
+		mutex_unlock(&fs_hws_data->lock);
+		return NULL;
+	}
+	refcount_set(&fs_hws_data->hws_action_refcount, 1);
+	mutex_unlock(&fs_hws_data->lock);
+
+	return fs_hws_data->hws_action;
+}
+
+void mlx5_fs_put_hws_action(struct mlx5_fs_hws_data *fs_hws_data)
+{
+	if (!fs_hws_data)
+		return;
+
+	/* try avoid locking if not necessary */
+	if (refcount_dec_not_one(&fs_hws_data->hws_action_refcount))
+		return;
+
+	mutex_lock(&fs_hws_data->lock);
+	if (!refcount_dec_and_test(&fs_hws_data->hws_action_refcount)) {
+		mutex_unlock(&fs_hws_data->lock);
+		return;
+	}
+	mlx5hws_action_destroy(fs_hws_data->hws_action);
+	fs_hws_data->hws_action = NULL;
+	mutex_unlock(&fs_hws_data->lock);
+}
+
+static void mlx5_fs_destroy_fs_action(struct mlx5_flow_root_namespace *ns,
+				      struct mlx5_fs_hws_rule_action *fs_action)
+{
+	struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context;
+
+	switch (mlx5hws_action_get_type(fs_action->action)) {
+	case MLX5HWS_ACTION_TYP_CTR:
+		mlx5_fc_put_hws_action(fs_action->counter);
+		break;
+	case MLX5HWS_ACTION_TYP_ASO_METER:
+		mlx5_fs_put_action_aso_meter(fs_ctx, fs_action->exe_aso);
+		break;
+	case MLX5HWS_ACTION_TYP_SAMPLER:
+		mlx5_fs_put_dest_action_sampler(fs_ctx, fs_action->sampler_id);
+		break;
+	default:
+		mlx5hws_action_destroy(fs_action->action);
+	}
+}
+
+static void
+mlx5_fs_destroy_fs_actions(struct mlx5_flow_root_namespace *ns,
+			   struct mlx5_fs_hws_rule_action **fs_actions,
+			   int *num_fs_actions)
+{
+	int i;
+
+	/* Free in reverse order to handle action dependencies */
+	for (i = *num_fs_actions - 1; i >= 0; i--)
+		mlx5_fs_destroy_fs_action(ns, *fs_actions + i);
+	*num_fs_actions = 0;
+	kfree(*fs_actions);
+	*fs_actions = NULL;
+}
+
+/* Splits FTE's actions into cached, rule and destination actions.
+ * The cached and destination actions are saved on the fte hws rule.
+ * The rule actions are returned as a parameter, together with their count.
+ * We want to support a rule with 32 destinations, which means we need to
+ * account for 32 destinations plus usually a counter plus one more action
+ * for a multi-destination flow table.
+ * 32 is SW limitation for array size, keep. HWS limitation is 16M STEs per matcher
+ */
+#define MLX5_FLOW_CONTEXT_ACTION_MAX 34
+static int mlx5_fs_fte_get_hws_actions(struct mlx5_flow_root_namespace *ns,
+				       struct mlx5_flow_table *ft,
+				       struct mlx5_flow_group *group,
+				       struct fs_fte *fte,
+				       struct mlx5hws_rule_action **ractions)
+{
+	struct mlx5_flow_act *fte_action = &fte->act_dests.action;
+	struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context;
+	struct mlx5hws_action_dest_attr *dest_actions;
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	struct mlx5_fs_hws_rule_action *fs_actions;
+	struct mlx5_core_dev *dev = ns->dev;
+	struct mlx5hws_action *dest_action;
+	struct mlx5hws_action *tmp_action;
+	struct mlx5_fs_hws_pr *pr_data;
+	struct mlx5_fs_hws_mh *mh_data;
+	bool delay_encap_set = false;
+	struct mlx5_flow_rule *dst;
+	int num_dest_actions = 0;
+	int num_fs_actions = 0;
+	int num_actions = 0;
+	int err;
+
+	*ractions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, sizeof(**ractions),
+			    GFP_KERNEL);
+	if (!*ractions) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	fs_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX,
+			     sizeof(*fs_actions), GFP_KERNEL);
+	if (!fs_actions) {
+		err = -ENOMEM;
+		goto free_actions_alloc;
+	}
+
+	dest_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX,
+			       sizeof(*dest_actions), GFP_KERNEL);
+	if (!dest_actions) {
+		err = -ENOMEM;
+		goto free_fs_actions_alloc;
+	}
+
+	/* The order of the actions are must to be kept, only the following
+	 * order is supported by HW steering:
+	 * HWS: decap -> remove_hdr -> pop_vlan -> modify header -> push_vlan
+	 *      -> reformat (insert_hdr/encap) -> ctr -> tag -> aso
+	 *      -> drop -> FWD:tbl/vport/sampler/tbl_num/range -> dest_array -> last
+	 */
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
+		tmp_action = mlx5_fs_get_action_decap_tnl_l2_to_l2(fs_ctx);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_dest_actions_alloc;
+		}
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) {
+		int reformat_type = fte_action->pkt_reformat->reformat_type;
+
+		if (fte_action->pkt_reformat->owner == MLX5_FLOW_RESOURCE_OWNER_FW) {
+			mlx5_core_err(dev, "FW-owned reformat can't be used in HWS rule\n");
+			err = -EINVAL;
+			goto free_actions;
+		}
+
+		if (reformat_type == MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2) {
+			pr_data = fte_action->pkt_reformat->fs_hws_action.pr_data;
+			(*ractions)[num_actions].reformat.offset = pr_data->offset;
+			(*ractions)[num_actions].reformat.hdr_idx = pr_data->hdr_idx;
+			(*ractions)[num_actions].reformat.data = pr_data->data;
+			(*ractions)[num_actions++].action =
+				fte_action->pkt_reformat->fs_hws_action.hws_action;
+		} else if (reformat_type == MLX5_REFORMAT_TYPE_REMOVE_HDR) {
+			(*ractions)[num_actions++].action =
+				fte_action->pkt_reformat->fs_hws_action.hws_action;
+		} else {
+			delay_encap_set = true;
+		}
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) {
+		tmp_action = mlx5_fs_get_action_pop_vlan(fs_ctx);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2) {
+		tmp_action = mlx5_fs_get_action_pop_vlan(fs_ctx);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
+		mh_data = fte_action->modify_hdr->fs_hws_action.mh_data;
+		(*ractions)[num_actions].modify_header.offset = mh_data->offset;
+		(*ractions)[num_actions].modify_header.data = mh_data->data;
+		(*ractions)[num_actions++].action =
+			fte_action->modify_hdr->fs_hws_action.hws_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
+		tmp_action = mlx5_fs_get_action_push_vlan(fs_ctx);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		(*ractions)[num_actions].push_vlan.vlan_hdr =
+			htonl(mlx5_fs_calc_vlan_hdr(&fte_action->vlan[0]));
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) {
+		tmp_action = mlx5_fs_get_action_push_vlan(fs_ctx);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		(*ractions)[num_actions].push_vlan.vlan_hdr =
+			htonl(mlx5_fs_calc_vlan_hdr(&fte_action->vlan[1]));
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (delay_encap_set) {
+		pr_data = fte_action->pkt_reformat->fs_hws_action.pr_data;
+		(*ractions)[num_actions].reformat.offset = pr_data->offset;
+		(*ractions)[num_actions].reformat.data = pr_data->data;
+		(*ractions)[num_actions++].action =
+			fte_action->pkt_reformat->fs_hws_action.hws_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+		list_for_each_entry(dst, &fte->node.children, node.list) {
+			struct mlx5_fc *counter;
+
+			if (dst->dest_attr.type !=
+			    MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+				continue;
+
+			if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+				err = -EOPNOTSUPP;
+				goto free_actions;
+			}
+
+			counter = dst->dest_attr.counter;
+			tmp_action = mlx5_fc_get_hws_action(ctx, counter);
+			if (!tmp_action) {
+				err = -EINVAL;
+				goto free_actions;
+			}
+
+			(*ractions)[num_actions].counter.offset =
+				mlx5_fc_id(counter) - mlx5_fc_get_base_id(counter);
+			(*ractions)[num_actions++].action = tmp_action;
+			fs_actions[num_fs_actions].action = tmp_action;
+			fs_actions[num_fs_actions++].counter = counter;
+		}
+	}
+
+	if (fte->act_dests.flow_context.flow_tag) {
+		if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+			err = -EOPNOTSUPP;
+			goto free_actions;
+		}
+		tmp_action = mlx5_fs_get_action_tag(fs_ctx);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		(*ractions)[num_actions].tag.value = fte->act_dests.flow_context.flow_tag;
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO) {
+		if (fte_action->exe_aso.type != MLX5_EXE_ASO_FLOW_METER ||
+		    num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+			err = -EOPNOTSUPP;
+			goto free_actions;
+		}
+
+		tmp_action = mlx5_fs_get_action_aso_meter(fs_ctx,
+							  &fte_action->exe_aso);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		(*ractions)[num_actions].aso_meter.offset =
+			fte_action->exe_aso.flow_meter.meter_idx;
+		(*ractions)[num_actions].aso_meter.init_color =
+			fte_action->exe_aso.flow_meter.init_color;
+		(*ractions)[num_actions++].action = tmp_action;
+		fs_actions[num_fs_actions].action = tmp_action;
+		fs_actions[num_fs_actions++].exe_aso = &fte_action->exe_aso;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_DROP) {
+		dest_action = mlx5_fs_get_dest_action_drop(fs_ctx);
+		if (!dest_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		dest_actions[num_dest_actions++].dest = dest_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+		list_for_each_entry(dst, &fte->node.children, node.list) {
+			struct mlx5_flow_destination *attr = &dst->dest_attr;
+			bool type_uplink =
+				attr->type == MLX5_FLOW_DESTINATION_TYPE_UPLINK;
+
+			if (num_fs_actions == MLX5_FLOW_CONTEXT_ACTION_MAX ||
+			    num_dest_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+				err = -EOPNOTSUPP;
+				goto free_actions;
+			}
+			if (attr->type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+				continue;
+
+			switch (attr->type) {
+			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
+				dest_action = mlx5_fs_get_dest_action_ft(fs_ctx, dst);
+				if (dst->dest_attr.ft->flags &
+				    MLX5_FLOW_TABLE_UPLINK_VPORT)
+					dest_actions[num_dest_actions].is_wire_ft = true;
+				break;
+			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM:
+				dest_action = mlx5_fs_get_dest_action_table_num(fs_ctx,
+										dst);
+				if (dest_action)
+					break;
+				dest_action = mlx5_fs_create_dest_action_table_num(fs_ctx,
+										   dst);
+				fs_actions[num_fs_actions++].action = dest_action;
+				break;
+			case MLX5_FLOW_DESTINATION_TYPE_RANGE:
+				dest_action = mlx5_fs_create_dest_action_range(ctx, dst);
+				fs_actions[num_fs_actions++].action = dest_action;
+				break;
+			case MLX5_FLOW_DESTINATION_TYPE_UPLINK:
+			case MLX5_FLOW_DESTINATION_TYPE_VPORT:
+				dest_action = mlx5_fs_get_dest_action_vport(fs_ctx, dst,
+									    type_uplink);
+				break;
+			case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER:
+				dest_action =
+					mlx5_fs_get_dest_action_sampler(fs_ctx,
+									dst);
+				fs_actions[num_fs_actions].action = dest_action;
+				fs_actions[num_fs_actions++].sampler_id =
+							dst->dest_attr.sampler_id;
+				break;
+			default:
+				err = -EOPNOTSUPP;
+				goto free_actions;
+			}
+			if (!dest_action) {
+				err = -ENOMEM;
+				goto free_actions;
+			}
+			dest_actions[num_dest_actions++].dest = dest_action;
+		}
+	}
+
+	if (num_dest_actions == 1) {
+		if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+			err = -EOPNOTSUPP;
+			goto free_actions;
+		}
+		(*ractions)[num_actions++].action = dest_actions->dest;
+	} else if (num_dest_actions > 1) {
+		if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX ||
+		    num_fs_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+			err = -EOPNOTSUPP;
+			goto free_actions;
+		}
+		tmp_action =
+			mlx5_fs_create_action_dest_array(ctx, dest_actions,
+							 num_dest_actions);
+		if (!tmp_action) {
+			err = -EOPNOTSUPP;
+			goto free_actions;
+		}
+		fs_actions[num_fs_actions++].action = tmp_action;
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX ||
+	    num_fs_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+		err = -EOPNOTSUPP;
+		goto free_actions;
+	}
+
+	tmp_action = mlx5_fs_create_action_last(ctx);
+	if (!tmp_action) {
+		err = -ENOMEM;
+		goto free_actions;
+	}
+	fs_actions[num_fs_actions++].action = tmp_action;
+	(*ractions)[num_actions++].action = tmp_action;
+
+	kfree(dest_actions);
+
+	/* Actions created specifically for this rule will be destroyed
+	 * once rule is deleted.
+	 */
+	fte->fs_hws_rule.num_fs_actions = num_fs_actions;
+	fte->fs_hws_rule.hws_fs_actions = fs_actions;
+
+	return 0;
+
+free_actions:
+	mlx5_fs_destroy_fs_actions(ns, &fs_actions, &num_fs_actions);
+free_dest_actions_alloc:
+	kfree(dest_actions);
+free_fs_actions_alloc:
+	kfree(fs_actions);
+free_actions_alloc:
+	kfree(*ractions);
+	*ractions = NULL;
+out_err:
+	return err;
+}
+
+static int mlx5_cmd_hws_create_fte(struct mlx5_flow_root_namespace *ns,
+				   struct mlx5_flow_table *ft,
+				   struct mlx5_flow_group *group,
+				   struct fs_fte *fte)
+{
+	struct mlx5hws_match_parameters params;
+	struct mlx5hws_rule_action *ractions;
+	struct mlx5hws_bwc_rule *rule;
+	int err = 0;
+
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->create_fte(ns, ft, group, fte);
+
+	err = mlx5_fs_fte_get_hws_actions(ns, ft, group, fte, &ractions);
+	if (err)
+		goto out_err;
+
+	params.match_sz = sizeof(fte->val);
+	params.match_buf = fte->val;
+
+	rule = mlx5hws_bwc_rule_create(group->fs_hws_matcher.matcher, &params,
+				       fte->act_dests.flow_context.flow_source,
+				       ractions);
+	kfree(ractions);
+	if (!rule) {
+		err = -EINVAL;
+		goto free_actions;
+	}
+
+	fte->fs_hws_rule.bwc_rule = rule;
+	return 0;
+
+free_actions:
+	mlx5_fs_destroy_fs_actions(ns, &fte->fs_hws_rule.hws_fs_actions,
+				   &fte->fs_hws_rule.num_fs_actions);
+out_err:
+	mlx5_core_err(ns->dev, "Failed to create hws rule err(%d)\n", err);
+	return err;
+}
+
+static int mlx5_cmd_hws_delete_fte(struct mlx5_flow_root_namespace *ns,
+				   struct mlx5_flow_table *ft,
+				   struct fs_fte *fte)
+{
+	struct mlx5_fs_hws_rule *rule = &fte->fs_hws_rule;
+	int err;
+
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->delete_fte(ns, ft, fte);
+
+	err = mlx5hws_bwc_rule_destroy(rule->bwc_rule);
+	rule->bwc_rule = NULL;
+
+	mlx5_fs_destroy_fs_actions(ns, &rule->hws_fs_actions,
+				   &rule->num_fs_actions);
+
+	return err;
+}
+
+static int mlx5_cmd_hws_update_fte(struct mlx5_flow_root_namespace *ns,
+				   struct mlx5_flow_table *ft,
+				   struct mlx5_flow_group *group,
+				   int modify_mask,
+				   struct fs_fte *fte)
+{
+	int allowed_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) |
+		BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST) |
+		BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
+	struct mlx5_fs_hws_rule_action *saved_hws_fs_actions;
+	struct mlx5hws_rule_action *ractions;
+	int saved_num_fs_actions;
+	int ret;
+
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->update_fte(ns, ft, group,
+							     modify_mask, fte);
+
+	if ((modify_mask & ~allowed_mask) != 0)
+		return -EINVAL;
+
+	saved_hws_fs_actions = fte->fs_hws_rule.hws_fs_actions;
+	saved_num_fs_actions = fte->fs_hws_rule.num_fs_actions;
+
+	ret = mlx5_fs_fte_get_hws_actions(ns, ft, group, fte, &ractions);
+	if (ret)
+		return ret;
+
+	ret = mlx5hws_bwc_rule_action_update(fte->fs_hws_rule.bwc_rule, ractions);
+	kfree(ractions);
+	if (ret)
+		goto restore_actions;
+
+	mlx5_fs_destroy_fs_actions(ns, &saved_hws_fs_actions,
+				   &saved_num_fs_actions);
+	return ret;
+
+restore_actions:
+	mlx5_fs_destroy_fs_actions(ns, &fte->fs_hws_rule.hws_fs_actions,
+				   &fte->fs_hws_rule.num_fs_actions);
+	fte->fs_hws_rule.hws_fs_actions = saved_hws_fs_actions;
+	fte->fs_hws_rule.num_fs_actions = saved_num_fs_actions;
+	return ret;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_create_action_remove_header_vlan(struct mlx5hws_context *ctx)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5hws_action_remove_header_attr remove_hdr_vlan = {};
+
+	/* MAC anchor not supported in HWS reformat, use VLAN anchor */
+	remove_hdr_vlan.anchor = MLX5_REFORMAT_CONTEXT_ANCHOR_VLAN_START;
+	remove_hdr_vlan.offset = 0;
+	remove_hdr_vlan.size = sizeof(struct vlan_hdr);
+	return mlx5hws_action_create_remove_header(ctx, &remove_hdr_vlan, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_action_remove_header_vlan(struct mlx5_fs_hws_context *fs_ctx,
+				      struct mlx5_pkt_reformat_params *params)
+{
+	if (!params ||
+	    params->param_0 != MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START ||
+	    params->param_1 != offsetof(struct vlan_ethhdr, h_vlan_proto) ||
+	    params->size != sizeof(struct vlan_hdr))
+		return NULL;
+
+	return fs_ctx->hws_pool.remove_hdr_vlan_action;
+}
+
+static int
+mlx5_fs_verify_insert_header_params(struct mlx5_core_dev *mdev,
+				    struct mlx5_pkt_reformat_params *params)
+{
+	if ((!params->data && params->size) || (params->data && !params->size) ||
+	    MLX5_CAP_GEN_2(mdev, max_reformat_insert_size) < params->size ||
+	    MLX5_CAP_GEN_2(mdev, max_reformat_insert_offset) < params->param_1) {
+		mlx5_core_err(mdev, "Invalid reformat params for INSERT_HDR\n");
+		return -EINVAL;
+	}
+	if (params->param_0 != MLX5_FS_INSERT_HDR_VLAN_ANCHOR ||
+	    params->param_1 != MLX5_FS_INSERT_HDR_VLAN_OFFSET ||
+	    params->size != MLX5_FS_INSERT_HDR_VLAN_SIZE) {
+		mlx5_core_err(mdev, "Only vlan insert header supported\n");
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static int
+mlx5_fs_verify_encap_decap_params(struct mlx5_core_dev *dev,
+				  struct mlx5_pkt_reformat_params *params)
+{
+	if (params->param_0 || params->param_1) {
+		mlx5_core_err(dev, "Invalid reformat params\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static struct mlx5_fs_pool *
+mlx5_fs_get_pr_encap_pool(struct mlx5_core_dev *dev, struct xarray *pr_pools,
+			  enum mlx5hws_action_type reformat_type, size_t size)
+{
+	struct mlx5_fs_pool *pr_pool;
+	unsigned long index = size;
+	int err;
+
+	pr_pool = xa_load(pr_pools, index);
+	if (pr_pool)
+		return pr_pool;
+
+	pr_pool = kzalloc(sizeof(*pr_pool), GFP_KERNEL);
+	if (!pr_pool)
+		return ERR_PTR(-ENOMEM);
+	err = mlx5_fs_hws_pr_pool_init(pr_pool, dev, size, reformat_type);
+	if (err)
+		goto free_pr_pool;
+	err = xa_insert(pr_pools, index, pr_pool, GFP_KERNEL);
+	if (err)
+		goto cleanup_pr_pool;
+	return pr_pool;
+
+cleanup_pr_pool:
+	mlx5_fs_hws_pr_pool_cleanup(pr_pool);
+free_pr_pool:
+	kfree(pr_pool);
+	return ERR_PTR(err);
+}
+
+static void
+mlx5_fs_destroy_pr_pool(struct mlx5_fs_pool *pool, struct xarray *pr_pools,
+			unsigned long index)
+{
+	xa_erase(pr_pools, index);
+	mlx5_fs_hws_pr_pool_cleanup(pool);
+	kfree(pool);
+}
+
+static int
+mlx5_cmd_hws_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
+				   struct mlx5_pkt_reformat_params *params,
+				   enum mlx5_flow_namespace_type namespace,
+				   struct mlx5_pkt_reformat *pkt_reformat)
+{
+	struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context;
+	struct mlx5_fs_hws_actions_pool *hws_pool;
+	struct mlx5hws_action *hws_action = NULL;
+	struct mlx5_fs_hws_pr *pr_data = NULL;
+	struct mlx5_fs_pool *pr_pool = NULL;
+	struct mlx5_core_dev *dev = ns->dev;
+	u8 hdr_idx = 0;
+	int err;
+
+	if (!params)
+		return -EINVAL;
+
+	hws_pool = &fs_ctx->hws_pool;
+
+	switch (params->type) {
+	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
+	case MLX5_REFORMAT_TYPE_L2_TO_NVGRE:
+	case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL:
+		if (mlx5_fs_verify_encap_decap_params(dev, params))
+			return -EINVAL;
+		pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol2tnl_pools,
+						    MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2,
+						    params->size);
+		if (IS_ERR(pr_pool))
+			return PTR_ERR(pr_pool);
+		break;
+	case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
+		if (mlx5_fs_verify_encap_decap_params(dev, params))
+			return -EINVAL;
+		pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol3tnl_pools,
+						    MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3,
+						    params->size);
+		if (IS_ERR(pr_pool))
+			return PTR_ERR(pr_pool);
+		break;
+	case MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2:
+		if (mlx5_fs_verify_encap_decap_params(dev, params))
+			return -EINVAL;
+		pr_pool = &hws_pool->dl3tnltol2_pool;
+		hdr_idx = params->size == ETH_HLEN ?
+			  MLX5_FS_DL3TNLTOL2_MAC_HDR_IDX :
+			  MLX5_FS_DL3TNLTOL2_MAC_VLAN_HDR_IDX;
+		break;
+	case MLX5_REFORMAT_TYPE_INSERT_HDR:
+		err = mlx5_fs_verify_insert_header_params(dev, params);
+		if (err)
+			return err;
+		pr_pool = &hws_pool->insert_hdr_pool;
+		break;
+	case MLX5_REFORMAT_TYPE_REMOVE_HDR:
+		hws_action = mlx5_fs_get_action_remove_header_vlan(fs_ctx, params);
+		if (!hws_action)
+			mlx5_core_err(dev, "Only vlan remove header supported\n");
+		break;
+	default:
+		mlx5_core_err(ns->dev, "Packet-reformat not supported(%d)\n",
+			      params->type);
+		return -EOPNOTSUPP;
+	}
+
+	if (pr_pool) {
+		pr_data = mlx5_fs_hws_pr_pool_acquire_pr(pr_pool);
+		if (IS_ERR_OR_NULL(pr_data))
+			return !pr_data ? -EINVAL : PTR_ERR(pr_data);
+		hws_action = pr_data->bulk->hws_action;
+		if (!hws_action) {
+			mlx5_core_err(dev,
+				      "Failed allocating packet-reformat action\n");
+			err = -EINVAL;
+			goto release_pr;
+		}
+		pr_data->data = kmemdup(params->data, params->size, GFP_KERNEL);
+		if (!pr_data->data) {
+			err = -ENOMEM;
+			goto release_pr;
+		}
+		pr_data->hdr_idx = hdr_idx;
+		pr_data->data_size = params->size;
+		pkt_reformat->fs_hws_action.pr_data = pr_data;
+	}
+
+	mutex_init(&pkt_reformat->fs_hws_action.lock);
+	pkt_reformat->owner = MLX5_FLOW_RESOURCE_OWNER_HWS;
+	pkt_reformat->fs_hws_action.hws_action = hws_action;
+	return 0;
+
+release_pr:
+	if (pr_pool && pr_data)
+		mlx5_fs_hws_pr_pool_release_pr(pr_pool, pr_data);
+	return err;
+}
+
+static void mlx5_cmd_hws_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns,
+						 struct mlx5_pkt_reformat *pkt_reformat)
+{
+	struct mlx5_fs_hws_actions_pool *hws_pool = &ns->fs_hws_context.hws_pool;
+	struct mlx5_core_dev *dev = ns->dev;
+	struct mlx5_fs_hws_pr *pr_data;
+	struct mlx5_fs_pool *pr_pool;
+
+	if (pkt_reformat->fs_hws_action.fw_reformat_id != 0) {
+		struct mlx5_pkt_reformat fw_pkt_reformat = { 0 };
+
+		fw_pkt_reformat.id = pkt_reformat->fs_hws_action.fw_reformat_id;
+		mlx5_fs_cmd_get_fw_cmds()->
+			packet_reformat_dealloc(ns, &fw_pkt_reformat);
+		pkt_reformat->fs_hws_action.fw_reformat_id = 0;
+	}
+
+	if (pkt_reformat->reformat_type == MLX5_REFORMAT_TYPE_REMOVE_HDR)
+		return;
+
+	if (!pkt_reformat->fs_hws_action.pr_data) {
+		mlx5_core_err(ns->dev, "Failed release packet-reformat\n");
+		return;
+	}
+	pr_data = pkt_reformat->fs_hws_action.pr_data;
+
+	switch (pkt_reformat->reformat_type) {
+	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
+	case MLX5_REFORMAT_TYPE_L2_TO_NVGRE:
+	case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL:
+		pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol2tnl_pools,
+						    MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2,
+						    pr_data->data_size);
+		break;
+	case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
+		pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol2tnl_pools,
+						    MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2,
+						    pr_data->data_size);
+		break;
+	case MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2:
+		pr_pool = &hws_pool->dl3tnltol2_pool;
+		break;
+	case MLX5_REFORMAT_TYPE_INSERT_HDR:
+		pr_pool = &hws_pool->insert_hdr_pool;
+		break;
+	default:
+		mlx5_core_err(ns->dev, "Unknown packet-reformat type\n");
+		return;
+	}
+	if (!pkt_reformat->fs_hws_action.pr_data || IS_ERR(pr_pool)) {
+		mlx5_core_err(ns->dev, "Failed release packet-reformat\n");
+		return;
+	}
+	kfree(pr_data->data);
+	mlx5_fs_hws_pr_pool_release_pr(pr_pool, pr_data);
+	pkt_reformat->fs_hws_action.pr_data = NULL;
+}
+
+static struct mlx5_fs_pool *
+mlx5_fs_create_mh_pool(struct mlx5_core_dev *dev,
+		       struct mlx5hws_action_mh_pattern *pattern,
+		       struct xarray *mh_pools, unsigned long index)
+{
+	struct mlx5_fs_pool *pool;
+	int err;
+
+	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+	if (!pool)
+		return ERR_PTR(-ENOMEM);
+	err = mlx5_fs_hws_mh_pool_init(pool, dev, pattern);
+	if (err)
+		goto free_pool;
+	err = xa_insert(mh_pools, index, pool, GFP_KERNEL);
+	if (err)
+		goto cleanup_pool;
+	return pool;
+
+cleanup_pool:
+	mlx5_fs_hws_mh_pool_cleanup(pool);
+free_pool:
+	kfree(pool);
+	return ERR_PTR(err);
+}
+
+static void
+mlx5_fs_destroy_mh_pool(struct mlx5_fs_pool *pool, struct xarray *mh_pools,
+			unsigned long index)
+{
+	xa_erase(mh_pools, index);
+	mlx5_fs_hws_mh_pool_cleanup(pool);
+	kfree(pool);
+}
+
+static int mlx5_cmd_hws_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
+					    u8 namespace, u8 num_actions,
+					    void *modify_actions,
+					    struct mlx5_modify_hdr *modify_hdr)
+{
+	struct mlx5_fs_hws_actions_pool *hws_pool = &ns->fs_hws_context.hws_pool;
+	struct mlx5hws_action_mh_pattern pattern = {};
+	struct mlx5_fs_hws_mh *mh_data = NULL;
+	struct mlx5hws_action *hws_action;
+	struct mlx5_fs_pool *pool;
+	unsigned long i, cnt = 0;
+	bool known_pattern;
+	int err;
+
+	pattern.sz = MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto) * num_actions;
+	pattern.data = modify_actions;
+
+	known_pattern = false;
+	xa_for_each(&hws_pool->mh_pools, i, pool) {
+		if (mlx5_fs_hws_mh_pool_match(pool, &pattern)) {
+			known_pattern = true;
+			break;
+		}
+		cnt++;
+	}
+
+	if (!known_pattern) {
+		pool = mlx5_fs_create_mh_pool(ns->dev, &pattern,
+					      &hws_pool->mh_pools, cnt);
+		if (IS_ERR(pool))
+			return PTR_ERR(pool);
+	}
+	mh_data = mlx5_fs_hws_mh_pool_acquire_mh(pool);
+	if (IS_ERR(mh_data)) {
+		err = PTR_ERR(mh_data);
+		goto destroy_pool;
+	}
+	hws_action = mh_data->bulk->hws_action;
+	mh_data->data = kmemdup(pattern.data, pattern.sz, GFP_KERNEL);
+	if (!mh_data->data) {
+		err = -ENOMEM;
+		goto release_mh;
+	}
+	modify_hdr->fs_hws_action.mh_data = mh_data;
+	modify_hdr->fs_hws_action.fs_pool = pool;
+	modify_hdr->owner = MLX5_FLOW_RESOURCE_OWNER_SW;
+	modify_hdr->fs_hws_action.hws_action = hws_action;
+
+	return 0;
+
+release_mh:
+	mlx5_fs_hws_mh_pool_release_mh(pool, mh_data);
+destroy_pool:
+	if (!known_pattern)
+		mlx5_fs_destroy_mh_pool(pool, &hws_pool->mh_pools, cnt);
+	return err;
+}
+
+static void mlx5_cmd_hws_modify_header_dealloc(struct mlx5_flow_root_namespace *ns,
+					       struct mlx5_modify_hdr *modify_hdr)
+{
+	struct mlx5_fs_hws_mh *mh_data;
+	struct mlx5_fs_pool *pool;
+
+	if (!modify_hdr->fs_hws_action.fs_pool || !modify_hdr->fs_hws_action.mh_data) {
+		mlx5_core_err(ns->dev, "Failed release modify-header\n");
+		return;
+	}
+
+	mh_data = modify_hdr->fs_hws_action.mh_data;
+	kfree(mh_data->data);
+	pool = modify_hdr->fs_hws_action.fs_pool;
+	mlx5_fs_hws_mh_pool_release_mh(pool, mh_data);
+	modify_hdr->fs_hws_action.mh_data = NULL;
+}
+
+int
+mlx5_fs_hws_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				       u32 *reformat_id)
+{
+	enum mlx5_flow_namespace_type ns_type = pkt_reformat->ns_type;
+	struct mutex *lock = &pkt_reformat->fs_hws_action.lock;
+	u32 *id = &pkt_reformat->fs_hws_action.fw_reformat_id;
+	struct mlx5_pkt_reformat fw_pkt_reformat = { 0 };
+	struct mlx5_pkt_reformat_params params = { 0 };
+	struct mlx5_flow_root_namespace *ns;
+	struct mlx5_core_dev *dev;
+	int ret;
+
+	mutex_lock(lock);
+
+	if (*id != 0) {
+		*reformat_id = *id;
+		ret = 0;
+		goto unlock;
+	}
+
+	dev = mlx5hws_action_get_dev(pkt_reformat->fs_hws_action.hws_action);
+	if (!dev) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	ns = mlx5_get_root_namespace(dev, ns_type);
+	if (!ns) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	params.type = pkt_reformat->reformat_type;
+	params.size = pkt_reformat->fs_hws_action.pr_data->data_size;
+	params.data = pkt_reformat->fs_hws_action.pr_data->data;
+
+	ret = mlx5_fs_cmd_get_fw_cmds()->
+		packet_reformat_alloc(ns, &params, ns_type, &fw_pkt_reformat);
+	if (ret)
+		goto unlock;
+
+	*id = fw_pkt_reformat.id;
+	*reformat_id = *id;
+	ret = 0;
+
+unlock:
+	mutex_unlock(lock);
+
+	return ret;
+}
+
+static int mlx5_cmd_hws_create_match_definer(struct mlx5_flow_root_namespace *ns,
+					     u16 format_id, u32 *match_mask)
+{
+	return -EOPNOTSUPP;
+}
+
+static int mlx5_cmd_hws_destroy_match_definer(struct mlx5_flow_root_namespace *ns,
+					      int definer_id)
+{
+	return -EOPNOTSUPP;
+}
+
+static u32 mlx5_cmd_hws_get_capabilities(struct mlx5_flow_root_namespace *ns,
+					 enum fs_flow_table_type ft_type)
+{
+	if (ft_type != FS_FT_FDB)
+		return 0;
+
+	return MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX |
+	       MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX |
+	       MLX5_FLOW_STEERING_CAP_MATCH_RANGES;
+}
+
+bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev)
+{
+	return mlx5hws_is_supported(dev);
+}
+
+static const struct mlx5_flow_cmds mlx5_flow_cmds_hws = {
+	.create_flow_table = mlx5_cmd_hws_create_flow_table,
+	.destroy_flow_table = mlx5_cmd_hws_destroy_flow_table,
+	.modify_flow_table = mlx5_cmd_hws_modify_flow_table,
+	.update_root_ft = mlx5_cmd_hws_update_root_ft,
+	.create_flow_group = mlx5_cmd_hws_create_flow_group,
+	.destroy_flow_group = mlx5_cmd_hws_destroy_flow_group,
+	.create_fte = mlx5_cmd_hws_create_fte,
+	.delete_fte = mlx5_cmd_hws_delete_fte,
+	.update_fte = mlx5_cmd_hws_update_fte,
+	.packet_reformat_alloc = mlx5_cmd_hws_packet_reformat_alloc,
+	.packet_reformat_dealloc = mlx5_cmd_hws_packet_reformat_dealloc,
+	.modify_header_alloc = mlx5_cmd_hws_modify_header_alloc,
+	.modify_header_dealloc = mlx5_cmd_hws_modify_header_dealloc,
+	.create_match_definer = mlx5_cmd_hws_create_match_definer,
+	.destroy_match_definer = mlx5_cmd_hws_destroy_match_definer,
+	.create_ns = mlx5_cmd_hws_create_ns,
+	.destroy_ns = mlx5_cmd_hws_destroy_ns,
+	.set_peer = mlx5_cmd_hws_set_peer,
+	.get_capabilities = mlx5_cmd_hws_get_capabilities,
+};
+
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_hws_cmds(void)
+{
+	return &mlx5_flow_cmds_hws;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
new file mode 100644
index 000000000000..b92d55b2d147
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#ifndef _MLX5_FS_HWS_
+#define _MLX5_FS_HWS_
+
+#include "mlx5hws.h"
+#include "fs_hws_pools.h"
+
+struct mlx5_fs_hws_actions_pool {
+	struct mlx5hws_action *tag_action;
+	struct mlx5hws_action *pop_vlan_action;
+	struct mlx5hws_action *push_vlan_action;
+	struct mlx5hws_action *drop_action;
+	struct mlx5hws_action *decapl2_action;
+	struct mlx5hws_action *remove_hdr_vlan_action;
+	struct mlx5_fs_pool insert_hdr_pool;
+	struct mlx5_fs_pool dl3tnltol2_pool;
+	struct xarray el2tol3tnl_pools;
+	struct xarray el2tol2tnl_pools;
+	struct xarray mh_pools;
+	struct xarray table_dests;
+	struct xarray vport_vhca_dests;
+	struct xarray vport_dests;
+	struct xarray aso_meters;
+	struct xarray sample_dests;
+};
+
+struct mlx5_fs_hws_context {
+	struct mlx5hws_context	*hws_ctx;
+	struct mlx5_fs_hws_actions_pool hws_pool;
+};
+
+struct mlx5_fs_hws_table {
+	struct mlx5hws_table *hws_table;
+	bool miss_ft_set;
+};
+
+struct mlx5_fs_hws_action {
+	struct mlx5hws_action *hws_action;
+	struct mlx5_fs_pool *fs_pool;
+	struct mlx5_fs_hws_pr *pr_data;
+	struct mlx5_fs_hws_mh *mh_data;
+	u32 fw_reformat_id;
+	/* Protect `fw_reformat_id` against being initialized from multiple
+	 * threads.
+	 */
+	struct mutex lock;
+};
+
+struct mlx5_fs_hws_matcher {
+	struct mlx5hws_bwc_matcher *matcher;
+};
+
+struct mlx5_fs_hws_rule_action {
+	struct mlx5hws_action *action;
+	union {
+		struct mlx5_fc *counter;
+		struct mlx5_exe_aso *exe_aso;
+		u32 sampler_id;
+	};
+};
+
+struct mlx5_fs_hws_rule {
+	struct mlx5hws_bwc_rule *bwc_rule;
+	struct mlx5_fs_hws_rule_action *hws_fs_actions;
+	int num_fs_actions;
+};
+
+struct mlx5_fs_hws_data {
+	struct mlx5hws_action *hws_action;
+	struct mutex lock; /* protects hws_action */
+	refcount_t hws_action_refcount;
+};
+
+struct mlx5_fs_hws_create_action_ctx {
+	enum mlx5hws_action_type actions_type;
+	struct mlx5hws_context *hws_ctx;
+	u32 id;
+	union {
+		u8 return_reg_id;
+	};
+};
+
+struct mlx5hws_action *
+mlx5_fs_get_hws_action(struct mlx5_fs_hws_data *fs_hws_data,
+		       struct mlx5_fs_hws_create_action_ctx *create_ctx);
+void mlx5_fs_put_hws_action(struct mlx5_fs_hws_data *fs_hws_data);
+
+#ifdef CONFIG_MLX5_HW_STEERING
+
+int
+mlx5_fs_hws_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				       u32 *reformat_id);
+
+bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev);
+
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_hws_cmds(void);
+
+#else
+
+static inline int
+mlx5_fs_hws_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				       u32 *reformat_id)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev)
+{
+	return false;
+}
+
+static inline const struct mlx5_flow_cmds *mlx5_fs_cmd_get_hws_cmds(void)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_MLX5_HWS_STEERING */
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c
new file mode 100644
index 000000000000..839d71bd4216
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c
@@ -0,0 +1,427 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#include <mlx5_core.h>
+#include "fs_hws_pools.h"
+
+#define MLX5_FS_HWS_DEFAULT_BULK_LEN 65536
+#define MLX5_FS_HWS_POOL_MAX_THRESHOLD BIT(18)
+#define MLX5_FS_HWS_POOL_USED_BUFF_RATIO 10
+
+static struct mlx5hws_action *
+mlx5_fs_dl3tnltol2_bulk_action_create(struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_action_reformat_header reformat_hdr[2] = {};
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB;
+	enum mlx5hws_action_type reformat_type;
+	u32 log_bulk_size;
+
+	reformat_type = MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2;
+	reformat_hdr[MLX5_FS_DL3TNLTOL2_MAC_HDR_IDX].sz = ETH_HLEN;
+	reformat_hdr[MLX5_FS_DL3TNLTOL2_MAC_VLAN_HDR_IDX].sz = ETH_HLEN + VLAN_HLEN;
+
+	log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN);
+	return mlx5hws_action_create_reformat(ctx, reformat_type, 2,
+					      reformat_hdr, log_bulk_size, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_el2tol3tnl_bulk_action_create(struct mlx5hws_context *ctx, size_t data_size)
+{
+	struct mlx5hws_action_reformat_header reformat_hdr = {};
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB;
+	enum mlx5hws_action_type reformat_type;
+	u32 log_bulk_size;
+
+	reformat_type = MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3;
+	reformat_hdr.sz = data_size;
+
+	log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN);
+	return mlx5hws_action_create_reformat(ctx, reformat_type, 1,
+					      &reformat_hdr, log_bulk_size, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_el2tol2tnl_bulk_action_create(struct mlx5hws_context *ctx, size_t data_size)
+{
+	struct mlx5hws_action_reformat_header reformat_hdr = {};
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB;
+	enum mlx5hws_action_type reformat_type;
+	u32 log_bulk_size;
+
+	reformat_type = MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2;
+	reformat_hdr.sz = data_size;
+
+	log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN);
+	return mlx5hws_action_create_reformat(ctx, reformat_type, 1,
+					      &reformat_hdr, log_bulk_size, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_insert_hdr_bulk_action_create(struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_action_insert_header insert_hdr = {};
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB;
+	u32 log_bulk_size;
+
+	log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN);
+	insert_hdr.hdr.sz = MLX5_FS_INSERT_HDR_VLAN_SIZE;
+	insert_hdr.anchor = MLX5_FS_INSERT_HDR_VLAN_ANCHOR;
+	insert_hdr.offset = MLX5_FS_INSERT_HDR_VLAN_OFFSET;
+
+	return mlx5hws_action_create_insert_header(ctx, 1, &insert_hdr,
+						   log_bulk_size, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_pr_bulk_action_create(struct mlx5_core_dev *dev,
+			      struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx)
+{
+	struct mlx5_flow_root_namespace *root_ns;
+	struct mlx5hws_context *ctx;
+	size_t encap_data_size;
+
+	root_ns = mlx5_get_root_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
+	if (!root_ns || root_ns->mode != MLX5_FLOW_STEERING_MODE_HMFS)
+		return NULL;
+
+	ctx = root_ns->fs_hws_context.hws_ctx;
+	if (!ctx)
+		return NULL;
+
+	encap_data_size = pr_pool_ctx->encap_data_size;
+	switch (pr_pool_ctx->reformat_type) {
+	case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2:
+		return mlx5_fs_dl3tnltol2_bulk_action_create(ctx);
+	case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3:
+		return mlx5_fs_el2tol3tnl_bulk_action_create(ctx, encap_data_size);
+	case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2:
+		return mlx5_fs_el2tol2tnl_bulk_action_create(ctx, encap_data_size);
+	case MLX5HWS_ACTION_TYP_INSERT_HEADER:
+		return mlx5_fs_insert_hdr_bulk_action_create(ctx);
+	default:
+		return NULL;
+	}
+	return NULL;
+}
+
+static struct mlx5_fs_bulk *
+mlx5_fs_hws_pr_bulk_create(struct mlx5_core_dev *dev, void *pool_ctx)
+{
+	struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx;
+	struct mlx5_fs_hws_pr_bulk *pr_bulk;
+	int bulk_len;
+	int i;
+
+	if (!pool_ctx)
+		return NULL;
+	pr_pool_ctx = pool_ctx;
+	bulk_len = MLX5_FS_HWS_DEFAULT_BULK_LEN;
+	pr_bulk = kvzalloc(struct_size(pr_bulk, prs_data, bulk_len), GFP_KERNEL);
+	if (!pr_bulk)
+		return NULL;
+
+	if (mlx5_fs_bulk_init(dev, &pr_bulk->fs_bulk, bulk_len))
+		goto free_pr_bulk;
+
+	for (i = 0; i < bulk_len; i++) {
+		pr_bulk->prs_data[i].bulk = pr_bulk;
+		pr_bulk->prs_data[i].offset = i;
+	}
+
+	pr_bulk->hws_action = mlx5_fs_pr_bulk_action_create(dev, pr_pool_ctx);
+	if (!pr_bulk->hws_action)
+		goto cleanup_fs_bulk;
+
+	return &pr_bulk->fs_bulk;
+
+cleanup_fs_bulk:
+	mlx5_fs_bulk_cleanup(&pr_bulk->fs_bulk);
+free_pr_bulk:
+	kvfree(pr_bulk);
+	return NULL;
+}
+
+static int
+mlx5_fs_hws_pr_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *fs_bulk)
+{
+	struct mlx5_fs_hws_pr_bulk *pr_bulk;
+
+	pr_bulk = container_of(fs_bulk, struct mlx5_fs_hws_pr_bulk, fs_bulk);
+	if (mlx5_fs_bulk_get_free_amount(fs_bulk) < fs_bulk->bulk_len) {
+		mlx5_core_err(dev, "Freeing bulk before all reformats were released\n");
+		return -EBUSY;
+	}
+
+	mlx5hws_action_destroy(pr_bulk->hws_action);
+	mlx5_fs_bulk_cleanup(fs_bulk);
+	kvfree(pr_bulk);
+
+	return 0;
+}
+
+static void mlx5_hws_pool_update_threshold(struct mlx5_fs_pool *hws_pool)
+{
+	hws_pool->threshold = min_t(int, MLX5_FS_HWS_POOL_MAX_THRESHOLD,
+				    hws_pool->used_units / MLX5_FS_HWS_POOL_USED_BUFF_RATIO);
+}
+
+static const struct mlx5_fs_pool_ops mlx5_fs_hws_pr_pool_ops = {
+	.bulk_create = mlx5_fs_hws_pr_bulk_create,
+	.bulk_destroy = mlx5_fs_hws_pr_bulk_destroy,
+	.update_threshold = mlx5_hws_pool_update_threshold,
+};
+
+int mlx5_fs_hws_pr_pool_init(struct mlx5_fs_pool *pr_pool,
+			     struct mlx5_core_dev *dev, size_t encap_data_size,
+			     enum mlx5hws_action_type reformat_type)
+{
+	struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx;
+
+	if (reformat_type != MLX5HWS_ACTION_TYP_INSERT_HEADER &&
+	    reformat_type != MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2 &&
+	    reformat_type != MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3 &&
+	    reformat_type != MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2)
+		return -EOPNOTSUPP;
+
+	pr_pool_ctx = kzalloc(sizeof(*pr_pool_ctx), GFP_KERNEL);
+	if (!pr_pool_ctx)
+		return -ENOMEM;
+	pr_pool_ctx->reformat_type = reformat_type;
+	pr_pool_ctx->encap_data_size = encap_data_size;
+	mlx5_fs_pool_init(pr_pool, dev, &mlx5_fs_hws_pr_pool_ops, pr_pool_ctx);
+	return 0;
+}
+
+void mlx5_fs_hws_pr_pool_cleanup(struct mlx5_fs_pool *pr_pool)
+{
+	struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx;
+
+	mlx5_fs_pool_cleanup(pr_pool);
+	pr_pool_ctx = pr_pool->pool_ctx;
+	if (!pr_pool_ctx)
+		return;
+	kfree(pr_pool_ctx);
+}
+
+struct mlx5_fs_hws_pr *
+mlx5_fs_hws_pr_pool_acquire_pr(struct mlx5_fs_pool *pr_pool)
+{
+	struct mlx5_fs_pool_index pool_index = {};
+	struct mlx5_fs_hws_pr_bulk *pr_bulk;
+	int err;
+
+	err = mlx5_fs_pool_acquire_index(pr_pool, &pool_index);
+	if (err)
+		return ERR_PTR(err);
+	pr_bulk = container_of(pool_index.fs_bulk, struct mlx5_fs_hws_pr_bulk,
+			       fs_bulk);
+	return &pr_bulk->prs_data[pool_index.index];
+}
+
+void mlx5_fs_hws_pr_pool_release_pr(struct mlx5_fs_pool *pr_pool,
+				    struct mlx5_fs_hws_pr *pr_data)
+{
+	struct mlx5_fs_bulk *fs_bulk = &pr_data->bulk->fs_bulk;
+	struct mlx5_fs_pool_index pool_index = {};
+	struct mlx5_core_dev *dev = pr_pool->dev;
+
+	pool_index.fs_bulk = fs_bulk;
+	pool_index.index = pr_data->offset;
+	if (mlx5_fs_pool_release_index(pr_pool, &pool_index))
+		mlx5_core_warn(dev, "Attempted to release packet reformat which is not acquired\n");
+}
+
+struct mlx5hws_action *mlx5_fs_hws_pr_get_action(struct mlx5_fs_hws_pr *pr_data)
+{
+	return pr_data->bulk->hws_action;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_mh_bulk_action_create(struct mlx5hws_context *ctx,
+			      struct mlx5hws_action_mh_pattern *pattern)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB;
+	u32 log_bulk_size;
+
+	log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN);
+	return mlx5hws_action_create_modify_header(ctx, 1, pattern,
+						   log_bulk_size, flags);
+}
+
+static struct mlx5_fs_bulk *
+mlx5_fs_hws_mh_bulk_create(struct mlx5_core_dev *dev, void *pool_ctx)
+{
+	struct mlx5hws_action_mh_pattern *pattern;
+	struct mlx5_flow_root_namespace *root_ns;
+	struct mlx5_fs_hws_mh_bulk *mh_bulk;
+	struct mlx5hws_context *ctx;
+	int bulk_len;
+
+	if (!pool_ctx)
+		return NULL;
+
+	root_ns = mlx5_get_root_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
+	if (!root_ns || root_ns->mode != MLX5_FLOW_STEERING_MODE_HMFS)
+		return NULL;
+
+	ctx = root_ns->fs_hws_context.hws_ctx;
+	if (!ctx)
+		return NULL;
+
+	pattern = pool_ctx;
+	bulk_len = MLX5_FS_HWS_DEFAULT_BULK_LEN;
+	mh_bulk = kvzalloc(struct_size(mh_bulk, mhs_data, bulk_len), GFP_KERNEL);
+	if (!mh_bulk)
+		return NULL;
+
+	if (mlx5_fs_bulk_init(dev, &mh_bulk->fs_bulk, bulk_len))
+		goto free_mh_bulk;
+
+	for (int i = 0; i < bulk_len; i++) {
+		mh_bulk->mhs_data[i].bulk = mh_bulk;
+		mh_bulk->mhs_data[i].offset = i;
+	}
+
+	mh_bulk->hws_action = mlx5_fs_mh_bulk_action_create(ctx, pattern);
+	if (!mh_bulk->hws_action)
+		goto cleanup_fs_bulk;
+
+	return &mh_bulk->fs_bulk;
+
+cleanup_fs_bulk:
+	mlx5_fs_bulk_cleanup(&mh_bulk->fs_bulk);
+free_mh_bulk:
+	kvfree(mh_bulk);
+	return NULL;
+}
+
+static int
+mlx5_fs_hws_mh_bulk_destroy(struct mlx5_core_dev *dev,
+			    struct mlx5_fs_bulk *fs_bulk)
+{
+	struct mlx5_fs_hws_mh_bulk *mh_bulk;
+
+	mh_bulk = container_of(fs_bulk, struct mlx5_fs_hws_mh_bulk, fs_bulk);
+	if (mlx5_fs_bulk_get_free_amount(fs_bulk) < fs_bulk->bulk_len) {
+		mlx5_core_err(dev, "Freeing bulk before all modify header were released\n");
+		return -EBUSY;
+	}
+
+	mlx5hws_action_destroy(mh_bulk->hws_action);
+	mlx5_fs_bulk_cleanup(fs_bulk);
+	kvfree(mh_bulk);
+
+	return 0;
+}
+
+static const struct mlx5_fs_pool_ops mlx5_fs_hws_mh_pool_ops = {
+	.bulk_create = mlx5_fs_hws_mh_bulk_create,
+	.bulk_destroy = mlx5_fs_hws_mh_bulk_destroy,
+	.update_threshold = mlx5_hws_pool_update_threshold,
+};
+
+int mlx5_fs_hws_mh_pool_init(struct mlx5_fs_pool *fs_hws_mh_pool,
+			     struct mlx5_core_dev *dev,
+			     struct mlx5hws_action_mh_pattern *pattern)
+{
+	struct mlx5hws_action_mh_pattern *pool_pattern;
+
+	pool_pattern = kzalloc(sizeof(*pool_pattern), GFP_KERNEL);
+	if (!pool_pattern)
+		return -ENOMEM;
+	pool_pattern->data = kmemdup(pattern->data, pattern->sz, GFP_KERNEL);
+	if (!pool_pattern->data) {
+		kfree(pool_pattern);
+		return -ENOMEM;
+	}
+	pool_pattern->sz = pattern->sz;
+	mlx5_fs_pool_init(fs_hws_mh_pool, dev, &mlx5_fs_hws_mh_pool_ops,
+			  pool_pattern);
+	return 0;
+}
+
+void mlx5_fs_hws_mh_pool_cleanup(struct mlx5_fs_pool *fs_hws_mh_pool)
+{
+	struct mlx5hws_action_mh_pattern *pool_pattern;
+
+	mlx5_fs_pool_cleanup(fs_hws_mh_pool);
+	pool_pattern = fs_hws_mh_pool->pool_ctx;
+	if (!pool_pattern)
+		return;
+	kfree(pool_pattern->data);
+	kfree(pool_pattern);
+}
+
+struct mlx5_fs_hws_mh *
+mlx5_fs_hws_mh_pool_acquire_mh(struct mlx5_fs_pool *mh_pool)
+{
+	struct mlx5_fs_pool_index pool_index = {};
+	struct mlx5_fs_hws_mh_bulk *mh_bulk;
+	int err;
+
+	err = mlx5_fs_pool_acquire_index(mh_pool, &pool_index);
+	if (err)
+		return ERR_PTR(err);
+	mh_bulk = container_of(pool_index.fs_bulk, struct mlx5_fs_hws_mh_bulk,
+			       fs_bulk);
+	return &mh_bulk->mhs_data[pool_index.index];
+}
+
+void mlx5_fs_hws_mh_pool_release_mh(struct mlx5_fs_pool *mh_pool,
+				    struct mlx5_fs_hws_mh *mh_data)
+{
+	struct mlx5_fs_bulk *fs_bulk = &mh_data->bulk->fs_bulk;
+	struct mlx5_fs_pool_index pool_index = {};
+	struct mlx5_core_dev *dev = mh_pool->dev;
+
+	pool_index.fs_bulk = fs_bulk;
+	pool_index.index = mh_data->offset;
+	if (mlx5_fs_pool_release_index(mh_pool, &pool_index))
+		mlx5_core_warn(dev, "Attempted to release modify header which is not acquired\n");
+}
+
+bool mlx5_fs_hws_mh_pool_match(struct mlx5_fs_pool *mh_pool,
+			       struct mlx5hws_action_mh_pattern *pattern)
+{
+	struct mlx5hws_action_mh_pattern *pool_pattern;
+	int num_actions, i;
+
+	pool_pattern = mh_pool->pool_ctx;
+	if (WARN_ON_ONCE(!pool_pattern))
+		return false;
+
+	if (pattern->sz != pool_pattern->sz)
+		return false;
+	num_actions = pattern->sz / MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto);
+	for (i = 0; i < num_actions; i++) {
+		if ((__force __be32)pattern->data[i] !=
+		    (__force __be32)pool_pattern->data[i])
+			return false;
+	}
+	return true;
+}
+
+struct mlx5hws_action *mlx5_fc_get_hws_action(struct mlx5hws_context *ctx,
+					      struct mlx5_fc *counter)
+{
+	struct mlx5_fs_hws_create_action_ctx create_ctx;
+	struct mlx5_fc_bulk *fc_bulk = counter->bulk;
+	struct mlx5hws_action *hws_action;
+
+	create_ctx.hws_ctx = ctx;
+	create_ctx.id = fc_bulk->base_id;
+	create_ctx.actions_type = MLX5HWS_ACTION_TYP_CTR;
+
+	mlx5_fc_local_get(counter);
+	hws_action = mlx5_fs_get_hws_action(&fc_bulk->hws_data, &create_ctx);
+	if (!hws_action)
+		mlx5_fc_local_put(counter);
+	return hws_action;
+}
+
+void mlx5_fc_put_hws_action(struct mlx5_fc *counter)
+{
+	mlx5_fs_put_hws_action(&counter->bulk->hws_data);
+	mlx5_fc_local_put(counter);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.h
new file mode 100644
index 000000000000..34072551dd21
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#ifndef __MLX5_FS_HWS_POOLS_H__
+#define __MLX5_FS_HWS_POOLS_H__
+
+#include <linux/if_vlan.h>
+#include "fs_pool.h"
+#include "fs_core.h"
+
+#define MLX5_FS_INSERT_HDR_VLAN_ANCHOR MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START
+#define MLX5_FS_INSERT_HDR_VLAN_OFFSET offsetof(struct vlan_ethhdr, h_vlan_proto)
+#define MLX5_FS_INSERT_HDR_VLAN_SIZE sizeof(struct vlan_hdr)
+
+enum {
+	MLX5_FS_DL3TNLTOL2_MAC_HDR_IDX = 0,
+	MLX5_FS_DL3TNLTOL2_MAC_VLAN_HDR_IDX,
+};
+
+struct mlx5_fs_hws_pr {
+	struct mlx5_fs_hws_pr_bulk *bulk;
+	u32 offset;
+	u8 hdr_idx;
+	u8 *data;
+	size_t data_size;
+};
+
+struct mlx5_fs_hws_pr_bulk {
+	struct mlx5_fs_bulk fs_bulk;
+	struct mlx5hws_action *hws_action;
+	struct mlx5_fs_hws_pr prs_data[];
+};
+
+struct mlx5_fs_hws_pr_pool_ctx {
+	enum mlx5hws_action_type reformat_type;
+	size_t encap_data_size;
+};
+
+struct mlx5_fs_hws_mh {
+	struct mlx5_fs_hws_mh_bulk *bulk;
+	u32 offset;
+	u8 *data;
+};
+
+struct mlx5_fs_hws_mh_bulk {
+	struct mlx5_fs_bulk fs_bulk;
+	struct mlx5_fs_pool *mh_pool;
+	struct mlx5hws_action *hws_action;
+	struct mlx5_fs_hws_mh mhs_data[];
+};
+
+int mlx5_fs_hws_pr_pool_init(struct mlx5_fs_pool *pr_pool,
+			     struct mlx5_core_dev *dev, size_t encap_data_size,
+			     enum mlx5hws_action_type reformat_type);
+void mlx5_fs_hws_pr_pool_cleanup(struct mlx5_fs_pool *pr_pool);
+
+struct mlx5_fs_hws_pr *mlx5_fs_hws_pr_pool_acquire_pr(struct mlx5_fs_pool *pr_pool);
+void mlx5_fs_hws_pr_pool_release_pr(struct mlx5_fs_pool *pr_pool,
+				    struct mlx5_fs_hws_pr *pr_data);
+struct mlx5hws_action *mlx5_fs_hws_pr_get_action(struct mlx5_fs_hws_pr *pr_data);
+int mlx5_fs_hws_mh_pool_init(struct mlx5_fs_pool *fs_hws_mh_pool,
+			     struct mlx5_core_dev *dev,
+			     struct mlx5hws_action_mh_pattern *pattern);
+void mlx5_fs_hws_mh_pool_cleanup(struct mlx5_fs_pool *fs_hws_mh_pool);
+struct mlx5_fs_hws_mh *mlx5_fs_hws_mh_pool_acquire_mh(struct mlx5_fs_pool *mh_pool);
+void mlx5_fs_hws_mh_pool_release_mh(struct mlx5_fs_pool *mh_pool,
+				    struct mlx5_fs_hws_mh *mh_data);
+bool mlx5_fs_hws_mh_pool_match(struct mlx5_fs_pool *mh_pool,
+			       struct mlx5hws_action_mh_pattern *pattern);
+struct mlx5hws_action *mlx5_fc_get_hws_action(struct mlx5hws_context *ctx,
+					      struct mlx5_fc *counter);
+void mlx5_fc_put_hws_action(struct mlx5_fc *counter);
+#endif /* __MLX5_FS_HWS_POOLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h
index 3c8635f286ce..21279d503117 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h
@@ -17,6 +17,7 @@
 #include "context.h"
 #include "table.h"
 #include "send.h"
+#include "action_ste_pool.h"
 #include "rule.h"
 #include "cmd.h"
 #include "action.h"
@@ -39,7 +40,6 @@
 #define mlx5hws_dbg(ctx, arg...) mlx5_core_dbg((ctx)->mdev, ##arg)
 
 #define MLX5HWS_TABLE_TYPE_BASE 2
-#define MLX5HWS_ACTION_STE_IDX_ANY 0
 
 static inline bool is_mem_zero(const u8 *mem, size_t size)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
index 1bb3a6f8c3cd..32f87fdf3213 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
@@ -3,25 +3,6 @@
 
 #include "internal.h"
 
-enum mlx5hws_matcher_rtc_type {
-	HWS_MATCHER_RTC_TYPE_MATCH,
-	HWS_MATCHER_RTC_TYPE_STE_ARRAY,
-	HWS_MATCHER_RTC_TYPE_MAX,
-};
-
-static const char * const mlx5hws_matcher_rtc_type_str[] = {
-	[HWS_MATCHER_RTC_TYPE_MATCH] = "MATCH",
-	[HWS_MATCHER_RTC_TYPE_STE_ARRAY] = "STE_ARRAY",
-	[HWS_MATCHER_RTC_TYPE_MAX] = "UNKNOWN",
-};
-
-static const char *hws_matcher_rtc_type_to_str(enum mlx5hws_matcher_rtc_type rtc_type)
-{
-	if (rtc_type > HWS_MATCHER_RTC_TYPE_MAX)
-		rtc_type = HWS_MATCHER_RTC_TYPE_MAX;
-	return mlx5hws_matcher_rtc_type_str[rtc_type];
-}
-
 static bool hws_matcher_requires_col_tbl(u8 log_num_of_rules)
 {
 	/* Collision table concatenation is done only for large rule tables */
@@ -42,19 +23,202 @@ static void hws_matcher_destroy_end_ft(struct mlx5hws_matcher *matcher)
 	mlx5hws_table_destroy_default_ft(matcher->tbl, matcher->end_ft_id);
 }
 
+int mlx5hws_matcher_update_end_ft_isolated(struct mlx5hws_table *tbl,
+					   u32 miss_ft_id)
+{
+	struct mlx5hws_matcher *tmp_matcher;
+
+	if (list_empty(&tbl->matchers_list))
+		return -EINVAL;
+
+	/* Update isolated_matcher_end_ft_id attribute for all
+	 * the matchers in isolated table.
+	 */
+	list_for_each_entry(tmp_matcher, &tbl->matchers_list, list_node)
+		tmp_matcher->attr.isolated_matcher_end_ft_id = miss_ft_id;
+
+	tmp_matcher = list_last_entry(&tbl->matchers_list,
+				      struct mlx5hws_matcher,
+				      list_node);
+
+	return mlx5hws_table_ft_set_next_ft(tbl->ctx,
+					    tmp_matcher->end_ft_id,
+					    tbl->fw_ft_type,
+					    miss_ft_id);
+}
+
+static int hws_matcher_connect_end_ft_isolated(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	u32 end_ft_id;
+	int ret;
+
+	/* Reset end_ft next RTCs */
+	ret = mlx5hws_table_ft_set_next_rtc(tbl->ctx,
+					    matcher->end_ft_id,
+					    matcher->tbl->fw_ft_type,
+					    0, 0);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to reset FT's next RTCs\n");
+		return ret;
+	}
+
+	/* Connect isolated matcher's end_ft to the complex matcher's end FT */
+	end_ft_id = matcher->attr.isolated_matcher_end_ft_id;
+	ret = mlx5hws_table_ft_set_next_ft(tbl->ctx,
+					   matcher->end_ft_id,
+					   matcher->tbl->fw_ft_type,
+					   end_ft_id);
+
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to set FT's miss_ft_id\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int hws_matcher_create_end_ft_isolated(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	int ret;
+
+	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev,
+					      tbl,
+					      0,
+					      &matcher->end_ft_id);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to create end flow table\n");
+		return ret;
+	}
+
+	ret = hws_matcher_connect_end_ft_isolated(matcher);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to connect end FT\n");
+		goto destroy_default_ft;
+	}
+
+	return 0;
+
+destroy_default_ft:
+	mlx5hws_table_destroy_default_ft(tbl, matcher->end_ft_id);
+	return ret;
+}
+
 static int hws_matcher_create_end_ft(struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_table *tbl = matcher->tbl;
 	int ret;
 
-	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, &matcher->end_ft_id);
+	if (mlx5hws_matcher_is_isolated(matcher))
+		ret = hws_matcher_create_end_ft_isolated(matcher);
+	else
+		ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev,
+						      tbl,
+						      0,
+						      &matcher->end_ft_id);
+
 	if (ret) {
 		mlx5hws_err(tbl->ctx, "Failed to create matcher end flow table\n");
 		return ret;
 	}
+
 	return 0;
 }
 
+static int hws_matcher_connect_isolated_first(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_context *ctx = tbl->ctx;
+	int ret;
+
+	/* Isolated matcher's end_ft is already pointing to the end_ft
+	 * of the complex matcher - it was set at creation of end_ft,
+	 * so no need to connect it.
+	 * We still need to connect the isolated table's start FT to
+	 * this matcher's RTC.
+	 */
+	ret = mlx5hws_table_ft_set_next_rtc(ctx,
+					    tbl->ft_id,
+					    tbl->fw_ft_type,
+					    matcher->match_ste.rtc_0_id,
+					    matcher->match_ste.rtc_1_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Isolated matcher: failed to connect start FT to match RTC\n");
+		return ret;
+	}
+
+	/* Reset table's FT default miss (drop refcount) */
+	ret = mlx5hws_table_ft_set_default_next_ft(tbl, tbl->ft_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Isolated matcher: failed to reset table ft default miss\n");
+		return ret;
+	}
+
+	list_add(&matcher->list_node, &tbl->matchers_list);
+
+	return ret;
+}
+
+static int hws_matcher_connect_isolated_last(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_context *ctx = tbl->ctx;
+	struct mlx5hws_matcher *last;
+	int ret;
+
+	last = list_last_entry(&tbl->matchers_list,
+			       struct mlx5hws_matcher,
+			       list_node);
+
+	/* New matcher's end_ft is already pointing to the end_ft of
+	 * the complex matcher.
+	 * Connect previous matcher's end_ft to this new matcher RTC.
+	 */
+	ret = mlx5hws_table_ft_set_next_rtc(ctx,
+					    last->end_ft_id,
+					    tbl->fw_ft_type,
+					    matcher->match_ste.rtc_0_id,
+					    matcher->match_ste.rtc_1_id);
+	if (ret) {
+		mlx5hws_err(ctx,
+			    "Isolated matcher: failed to connect matcher end_ft to new match RTC\n");
+		return ret;
+	}
+
+	/* Reset prev matcher FT default miss (drop refcount) */
+	ret = mlx5hws_table_ft_set_default_next_ft(tbl, last->end_ft_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Isolated matcher: failed to reset matcher ft default miss\n");
+		return ret;
+	}
+
+	/* Insert after the last matcher */
+	list_add(&matcher->list_node, &last->list_node);
+
+	return 0;
+}
+
+static int hws_matcher_connect_isolated(struct mlx5hws_matcher *matcher)
+{
+	/* Isolated matcher is expected to be the only one in its table.
+	 * However, it can have a collision matcher, and it can go through
+	 * rehash process, in which case we will temporary have both old and
+	 * new matchers in the isolated table.
+	 * Check if this is the first matcher in the isolated table.
+	 */
+	if (list_empty(&matcher->tbl->matchers_list))
+		return hws_matcher_connect_isolated_first(matcher);
+
+	/* If this wasn't the first matcher, then we have 3 possible cases:
+	 *  - this is a collision matcher for the first matcher
+	 *  - this is a new rehash dest matcher
+	 *  - this is a collision matcher for the new rehash dest matcher
+	 * The logic to add new matcher is the same for all these cases.
+	 */
+	return hws_matcher_connect_isolated_last(matcher);
+}
+
 static int hws_matcher_connect(struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_table *tbl = matcher->tbl;
@@ -64,6 +228,9 @@ static int hws_matcher_connect(struct mlx5hws_matcher *matcher)
 	struct mlx5hws_matcher *tmp_matcher;
 	int ret;
 
+	if (mlx5hws_matcher_is_isolated(matcher))
+		return hws_matcher_connect_isolated(matcher);
+
 	/* Find location in matcher list */
 	if (list_empty(&tbl->matchers_list)) {
 		list_add(&matcher->list_node, &tbl->matchers_list);
@@ -140,6 +307,92 @@ remove_from_list:
 	return ret;
 }
 
+static int hws_matcher_disconnect_isolated(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_matcher *first, *last, *prev, *next;
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_context *ctx = tbl->ctx;
+	u32 end_ft_id;
+	int ret;
+
+	first = list_first_entry(&tbl->matchers_list,
+				 struct mlx5hws_matcher,
+				 list_node);
+	last = list_last_entry(&tbl->matchers_list,
+			       struct mlx5hws_matcher,
+			       list_node);
+	prev = list_prev_entry(matcher, list_node);
+	next = list_next_entry(matcher, list_node);
+
+	list_del_init(&matcher->list_node);
+
+	if (first == last) {
+		/* This was the only matcher in the list.
+		 * Reset isolated table FT next RTCs and connect it
+		 * to the whole complex matcher end FT instead.
+		 */
+		ret = mlx5hws_table_ft_set_next_rtc(ctx,
+						    tbl->ft_id,
+						    tbl->fw_ft_type,
+						    0, 0);
+		if (ret) {
+			mlx5hws_err(tbl->ctx, "Isolated matcher: failed to reset FT's next RTCs\n");
+			return ret;
+		}
+
+		end_ft_id = matcher->attr.isolated_matcher_end_ft_id;
+		ret = mlx5hws_table_ft_set_next_ft(tbl->ctx,
+						   tbl->ft_id,
+						   tbl->fw_ft_type,
+						   end_ft_id);
+		if (ret) {
+			mlx5hws_err(tbl->ctx, "Isolated matcher: failed to set FT's miss_ft_id\n");
+			return ret;
+		}
+
+		return 0;
+	}
+
+	/* At this point we know that there are more matchers in the list */
+
+	if (matcher == first) {
+		/* We've disconnected the first matcher.
+		 * Now update isolated table default FT.
+		 */
+		if (!next)
+			return -EINVAL;
+		return mlx5hws_table_ft_set_next_rtc(ctx,
+						     tbl->ft_id,
+						     tbl->fw_ft_type,
+						     next->match_ste.rtc_0_id,
+						     next->match_ste.rtc_1_id);
+	}
+
+	if (matcher == last) {
+		/* If we've disconnected the last matcher - update prev
+		 * matcher's end_ft to point to the complex matcher end_ft.
+		 */
+		if (!prev)
+			return -EINVAL;
+		return hws_matcher_connect_end_ft_isolated(prev);
+	}
+
+	/* This wasn't the first or the last matcher, which means that it has
+	 * both prev and next matchers. Note that this only happens if we're
+	 * disconnecting collision matcher of the old matcher during rehash.
+	 */
+	if (!prev || !next ||
+	    !(matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION))
+		return -EINVAL;
+
+	/* Update prev end FT to point to next match RTC */
+	return mlx5hws_table_ft_set_next_rtc(ctx,
+					     prev->end_ft_id,
+					     tbl->fw_ft_type,
+					     next->match_ste.rtc_0_id,
+					     next->match_ste.rtc_1_id);
+}
+
 static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_matcher *next = NULL, *prev = NULL;
@@ -147,6 +400,9 @@ static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
 	u32 prev_ft_id = tbl->ft_id;
 	int ret;
 
+	if (mlx5hws_matcher_is_isolated(matcher))
+		return hws_matcher_disconnect_isolated(matcher);
+
 	if (!list_is_first(&matcher->list_node, &tbl->matchers_list)) {
 		prev = list_prev_entry(matcher, list_node);
 		prev_ft_id = prev->end_ft_id;
@@ -165,14 +421,14 @@ static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
 						    next->match_ste.rtc_0_id,
 						    next->match_ste.rtc_1_id);
 		if (ret) {
-			mlx5hws_err(tbl->ctx, "Failed to disconnect matcher\n");
-			goto matcher_reconnect;
+			mlx5hws_err(tbl->ctx, "Fatal error, failed to disconnect matcher\n");
+			return ret;
 		}
 	} else {
 		ret = mlx5hws_table_connect_to_miss_table(tbl, tbl->default_miss.miss_tbl);
 		if (ret) {
-			mlx5hws_err(tbl->ctx, "Failed to disconnect last matcher\n");
-			goto matcher_reconnect;
+			mlx5hws_err(tbl->ctx, "Fatal error, failed to disconnect last matcher\n");
+			return ret;
 		}
 	}
 
@@ -180,169 +436,115 @@ static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
 	if (prev_ft_id == tbl->ft_id) {
 		ret = mlx5hws_table_update_connected_miss_tables(tbl);
 		if (ret) {
-			mlx5hws_err(tbl->ctx, "Fatal error, failed to update connected miss table\n");
-			goto matcher_reconnect;
+			mlx5hws_err(tbl->ctx,
+				    "Fatal error, failed to update connected miss table\n");
+			return ret;
 		}
 	}
 
 	ret = mlx5hws_table_ft_set_default_next_ft(tbl, prev_ft_id);
 	if (ret) {
 		mlx5hws_err(tbl->ctx, "Fatal error, failed to restore matcher ft default miss\n");
-		goto matcher_reconnect;
+		return ret;
 	}
 
 	return 0;
-
-matcher_reconnect:
-	if (list_empty(&tbl->matchers_list) || !prev)
-		list_add(&matcher->list_node, &tbl->matchers_list);
-	else
-		/* insert after prev matcher */
-		list_add(&matcher->list_node, &prev->list_node);
-
-	return ret;
 }
 
 static void hws_matcher_set_rtc_attr_sz(struct mlx5hws_matcher *matcher,
 					struct mlx5hws_cmd_rtc_create_attr *rtc_attr,
-					enum mlx5hws_matcher_rtc_type rtc_type,
 					bool is_mirror)
 {
-	struct mlx5hws_pool_chunk *ste = &matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].ste;
 	enum mlx5hws_matcher_flow_src flow_src = matcher->attr.optimize_flow_src;
-	bool is_match_rtc = rtc_type == HWS_MATCHER_RTC_TYPE_MATCH;
 
 	if ((flow_src == MLX5HWS_MATCHER_FLOW_SRC_VPORT && !is_mirror) ||
 	    (flow_src == MLX5HWS_MATCHER_FLOW_SRC_WIRE && is_mirror)) {
 		/* Optimize FDB RTC */
 		rtc_attr->log_size = 0;
 		rtc_attr->log_depth = 0;
-	} else {
-		/* Keep original values */
-		rtc_attr->log_size = is_match_rtc ? matcher->attr.table.sz_row_log : ste->order;
-		rtc_attr->log_depth = is_match_rtc ? matcher->attr.table.sz_col_log : 0;
 	}
 }
 
-static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher,
-				  enum mlx5hws_matcher_rtc_type rtc_type,
-				  u8 action_ste_selector)
+static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_matcher_attr *attr = &matcher->attr;
 	struct mlx5hws_cmd_rtc_create_attr rtc_attr = {0};
 	struct mlx5hws_match_template *mt = matcher->mt;
 	struct mlx5hws_context *ctx = matcher->tbl->ctx;
-	struct mlx5hws_action_default_stc *default_stc;
-	struct mlx5hws_matcher_action_ste *action_ste;
+	union mlx5hws_matcher_size *size_rx, *size_tx;
 	struct mlx5hws_table *tbl = matcher->tbl;
-	struct mlx5hws_pool *ste_pool, *stc_pool;
-	struct mlx5hws_pool_chunk *ste;
-	u32 *rtc_0_id, *rtc_1_id;
 	u32 obj_id;
 	int ret;
 
-	switch (rtc_type) {
-	case HWS_MATCHER_RTC_TYPE_MATCH:
-		rtc_0_id = &matcher->match_ste.rtc_0_id;
-		rtc_1_id = &matcher->match_ste.rtc_1_id;
-		ste_pool = matcher->match_ste.pool;
-		ste = &matcher->match_ste.ste;
-		ste->order = attr->table.sz_col_log + attr->table.sz_row_log;
-
-		rtc_attr.log_size = attr->table.sz_row_log;
-		rtc_attr.log_depth = attr->table.sz_col_log;
-		rtc_attr.is_frst_jumbo = mlx5hws_matcher_mt_is_jumbo(mt);
-		rtc_attr.is_scnd_range = 0;
-		rtc_attr.miss_ft_id = matcher->end_ft_id;
-
-		if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_HASH) {
-			/* The usual Hash Table */
-			rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_HASH;
-
-			/* The first mt is used since all share the same definer */
-			rtc_attr.match_definer_0 = mlx5hws_definer_get_id(mt->definer);
-		} else if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX) {
-			rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
-			rtc_attr.num_hash_definer = 1;
-
-			if (attr->distribute_mode == MLX5HWS_MATCHER_DISTRIBUTE_BY_HASH) {
-				/* Hash Split Table */
-				rtc_attr.access_index_mode = MLX5_IFC_RTC_STE_ACCESS_MODE_BY_HASH;
-				rtc_attr.match_definer_0 = mlx5hws_definer_get_id(mt->definer);
-			} else if (attr->distribute_mode == MLX5HWS_MATCHER_DISTRIBUTE_BY_LINEAR) {
-				/* Linear Lookup Table */
-				rtc_attr.access_index_mode = MLX5_IFC_RTC_STE_ACCESS_MODE_LINEAR;
-				rtc_attr.match_definer_0 = ctx->caps->linear_match_definer;
-			}
-		}
-
-		/* Match pool requires implicit allocation */
-		ret = mlx5hws_pool_chunk_alloc(ste_pool, ste);
-		if (ret) {
-			mlx5hws_err(ctx, "Failed to allocate STE for %s RTC",
-				    hws_matcher_rtc_type_to_str(rtc_type));
-			return ret;
+	size_rx = &attr->size[MLX5HWS_MATCHER_SIZE_TYPE_RX];
+	size_tx = &attr->size[MLX5HWS_MATCHER_SIZE_TYPE_TX];
+
+	rtc_attr.log_size = size_rx->table.sz_row_log;
+	rtc_attr.log_depth = size_rx->table.sz_col_log;
+	rtc_attr.is_frst_jumbo = mlx5hws_matcher_mt_is_jumbo(mt);
+	rtc_attr.is_scnd_range = 0;
+	rtc_attr.miss_ft_id = matcher->end_ft_id;
+
+	if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_HASH) {
+		/* The usual Hash Table */
+		rtc_attr.update_index_mode =
+			MLX5_IFC_RTC_STE_UPDATE_MODE_BY_HASH;
+
+		/* The first mt is used since all share the same definer */
+		rtc_attr.match_definer_0 = mlx5hws_definer_get_id(mt->definer);
+	} else if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX) {
+		rtc_attr.update_index_mode =
+			MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
+		rtc_attr.num_hash_definer = 1;
+
+		if (attr->distribute_mode ==
+		    MLX5HWS_MATCHER_DISTRIBUTE_BY_HASH) {
+			/* Hash Split Table */
+			rtc_attr.access_index_mode =
+				MLX5_IFC_RTC_STE_ACCESS_MODE_BY_HASH;
+			rtc_attr.match_definer_0 =
+				mlx5hws_definer_get_id(mt->definer);
+		} else if (attr->distribute_mode ==
+			   MLX5HWS_MATCHER_DISTRIBUTE_BY_LINEAR) {
+			/* Linear Lookup Table */
+			rtc_attr.access_index_mode =
+				MLX5_IFC_RTC_STE_ACCESS_MODE_LINEAR;
+			rtc_attr.match_definer_0 =
+				ctx->caps->linear_match_definer;
 		}
-		break;
-
-	case HWS_MATCHER_RTC_TYPE_STE_ARRAY:
-		action_ste = &matcher->action_ste[action_ste_selector];
-
-		rtc_0_id = &action_ste->rtc_0_id;
-		rtc_1_id = &action_ste->rtc_1_id;
-		ste_pool = action_ste->pool;
-		ste = &action_ste->ste;
-		ste->order = ilog2(roundup_pow_of_two(action_ste->max_stes)) +
-			     attr->table.sz_row_log;
-		rtc_attr.log_size = ste->order;
-		rtc_attr.log_depth = 0;
-		rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
-		/* The action STEs use the default always hit definer */
-		rtc_attr.match_definer_0 = ctx->caps->trivial_match_definer;
-		rtc_attr.is_frst_jumbo = false;
-		rtc_attr.miss_ft_id = 0;
-		break;
-
-	default:
-		mlx5hws_err(ctx, "HWS Invalid RTC type\n");
-		return -EINVAL;
 	}
 
-	obj_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
-
 	rtc_attr.pd = ctx->pd_num;
-	rtc_attr.ste_base = obj_id;
-	rtc_attr.ste_offset = ste->offset;
+	rtc_attr.ste_base = matcher->match_ste.ste_0_base;
 	rtc_attr.reparse_mode = mlx5hws_context_get_reparse_mode(ctx);
 	rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(tbl->type, false);
-	hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, rtc_type, false);
+	hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, false);
 
 	/* STC is a single resource (obj_id), use any STC for the ID */
-	stc_pool = ctx->stc_pool[tbl->type];
-	default_stc = ctx->common_res[tbl->type].default_stc;
-	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, &default_stc->default_hit);
+	obj_id = mlx5hws_pool_get_base_id(ctx->stc_pool);
 	rtc_attr.stc_base = obj_id;
 
-	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_0_id);
+	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr,
+				     &matcher->match_ste.rtc_0_id);
 	if (ret) {
-		mlx5hws_err(ctx, "Failed to create matcher RTC of type %s",
-			    hws_matcher_rtc_type_to_str(rtc_type));
-		goto free_ste;
+		mlx5hws_err(ctx, "Failed to create matcher RTC\n");
+		return ret;
 	}
 
 	if (tbl->type == MLX5HWS_TABLE_TYPE_FDB) {
-		obj_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
-		rtc_attr.ste_base = obj_id;
+		rtc_attr.log_size = size_tx->table.sz_row_log;
+		rtc_attr.log_depth = size_tx->table.sz_col_log;
+		rtc_attr.ste_base = matcher->match_ste.ste_1_base;
 		rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(tbl->type, true);
 
-		obj_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, &default_stc->default_hit);
+		obj_id = mlx5hws_pool_get_base_mirror_id(ctx->stc_pool);
 		rtc_attr.stc_base = obj_id;
-		hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, rtc_type, true);
+		hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, true);
 
-		ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_1_id);
+		ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr,
+					     &matcher->match_ste.rtc_1_id);
 		if (ret) {
-			mlx5hws_err(ctx, "Failed to create peer matcher RTC of type %s",
-				    hws_matcher_rtc_type_to_str(rtc_type));
+			mlx5hws_err(ctx, "Failed to create mirror matcher RTC\n");
 			goto destroy_rtc_0;
 		}
 	}
@@ -350,47 +552,18 @@ static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher,
 	return 0;
 
 destroy_rtc_0:
-	mlx5hws_cmd_rtc_destroy(ctx->mdev, *rtc_0_id);
-free_ste:
-	if (rtc_type == HWS_MATCHER_RTC_TYPE_MATCH)
-		mlx5hws_pool_chunk_free(ste_pool, ste);
+	mlx5hws_cmd_rtc_destroy(ctx->mdev, matcher->match_ste.rtc_0_id);
 	return ret;
 }
 
-static void hws_matcher_destroy_rtc(struct mlx5hws_matcher *matcher,
-				    enum mlx5hws_matcher_rtc_type rtc_type,
-				    u8 action_ste_selector)
+static void hws_matcher_destroy_rtc(struct mlx5hws_matcher *matcher)
 {
-	struct mlx5hws_matcher_action_ste *action_ste;
-	struct mlx5hws_table *tbl = matcher->tbl;
-	struct mlx5hws_pool_chunk *ste;
-	struct mlx5hws_pool *ste_pool;
-	u32 rtc_0_id, rtc_1_id;
-
-	switch (rtc_type) {
-	case HWS_MATCHER_RTC_TYPE_MATCH:
-		rtc_0_id = matcher->match_ste.rtc_0_id;
-		rtc_1_id = matcher->match_ste.rtc_1_id;
-		ste_pool = matcher->match_ste.pool;
-		ste = &matcher->match_ste.ste;
-		break;
-	case HWS_MATCHER_RTC_TYPE_STE_ARRAY:
-		action_ste = &matcher->action_ste[action_ste_selector];
-		rtc_0_id = action_ste->rtc_0_id;
-		rtc_1_id = action_ste->rtc_1_id;
-		ste_pool = action_ste->pool;
-		ste = &action_ste->ste;
-		break;
-	default:
-		return;
-	}
+	struct mlx5_core_dev *mdev = matcher->tbl->ctx->mdev;
 
-	if (tbl->type == MLX5HWS_TABLE_TYPE_FDB)
-		mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, rtc_1_id);
+	if (matcher->tbl->type == MLX5HWS_TABLE_TYPE_FDB)
+		mlx5hws_cmd_rtc_destroy(mdev, matcher->match_ste.rtc_1_id);
 
-	mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, rtc_0_id);
-	if (rtc_type == HWS_MATCHER_RTC_TYPE_MATCH)
-		mlx5hws_pool_chunk_free(ste_pool, ste);
+	mlx5hws_cmd_rtc_destroy(mdev, matcher->match_ste.rtc_0_id);
 }
 
 static int
@@ -398,43 +571,38 @@ hws_matcher_check_attr_sz(struct mlx5hws_cmd_query_caps *caps,
 			  struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_matcher_attr *attr = &matcher->attr;
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	union mlx5hws_matcher_size *size;
+	int i;
 
-	if (attr->table.sz_col_log > caps->rtc_log_depth_max) {
-		mlx5hws_err(matcher->tbl->ctx, "Matcher depth exceeds limit %d\n",
-			    caps->rtc_log_depth_max);
-		return -EOPNOTSUPP;
-	}
+	for (i = 0; i < 2; i++) {
+		size = &attr->size[i];
 
-	if (attr->table.sz_col_log + attr->table.sz_row_log > caps->ste_alloc_log_max) {
-		mlx5hws_err(matcher->tbl->ctx, "Total matcher size exceeds limit %d\n",
-			    caps->ste_alloc_log_max);
-		return -EOPNOTSUPP;
-	}
+		if (size->table.sz_col_log > caps->rtc_log_depth_max) {
+			mlx5hws_err(ctx, "Matcher depth exceeds limit %d\n",
+				    caps->rtc_log_depth_max);
+			return -EOPNOTSUPP;
+		}
 
-	if (attr->table.sz_col_log + attr->table.sz_row_log < caps->ste_alloc_log_gran) {
-		mlx5hws_err(matcher->tbl->ctx, "Total matcher size below limit %d\n",
-			    caps->ste_alloc_log_gran);
-		return -EOPNOTSUPP;
+		if (size->table.sz_col_log + size->table.sz_row_log >
+		    caps->ste_alloc_log_max) {
+			mlx5hws_err(ctx,
+				    "Total matcher size exceeds limit %d\n",
+				    caps->ste_alloc_log_max);
+			return -EOPNOTSUPP;
+		}
+
+		if (size->table.sz_col_log + size->table.sz_row_log <
+		    caps->ste_alloc_log_gran) {
+			mlx5hws_err(ctx, "Total matcher size below limit %d\n",
+				    caps->ste_alloc_log_gran);
+			return -EOPNOTSUPP;
+		}
 	}
 
 	return 0;
 }
 
-static void hws_matcher_set_pool_attr(struct mlx5hws_pool_attr *attr,
-				      struct mlx5hws_matcher *matcher)
-{
-	switch (matcher->attr.optimize_flow_src) {
-	case MLX5HWS_MATCHER_FLOW_SRC_VPORT:
-		attr->opt_type = MLX5HWS_POOL_OPTIMIZE_ORIG;
-		break;
-	case MLX5HWS_MATCHER_FLOW_SRC_WIRE:
-		attr->opt_type = MLX5HWS_POOL_OPTIMIZE_MIRROR;
-		break;
-	default:
-		break;
-	}
-}
-
 static int hws_matcher_check_and_process_at(struct mlx5hws_matcher *matcher,
 					    struct mlx5hws_action_template *at)
 {
@@ -458,170 +626,17 @@ static int hws_matcher_check_and_process_at(struct mlx5hws_matcher *matcher,
 	return 0;
 }
 
-static int hws_matcher_resize_init(struct mlx5hws_matcher *src_matcher)
-{
-	struct mlx5hws_matcher_resize_data *resize_data;
-
-	resize_data = kzalloc(sizeof(*resize_data), GFP_KERNEL);
-	if (!resize_data)
-		return -ENOMEM;
-
-	resize_data->max_stes = src_matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes;
-
-	resize_data->action_ste[0].stc = src_matcher->action_ste[0].stc;
-	resize_data->action_ste[0].rtc_0_id = src_matcher->action_ste[0].rtc_0_id;
-	resize_data->action_ste[0].rtc_1_id = src_matcher->action_ste[0].rtc_1_id;
-	resize_data->action_ste[0].pool = src_matcher->action_ste[0].max_stes ?
-					  src_matcher->action_ste[0].pool :
-					  NULL;
-	resize_data->action_ste[1].stc = src_matcher->action_ste[1].stc;
-	resize_data->action_ste[1].rtc_0_id = src_matcher->action_ste[1].rtc_0_id;
-	resize_data->action_ste[1].rtc_1_id = src_matcher->action_ste[1].rtc_1_id;
-	resize_data->action_ste[1].pool = src_matcher->action_ste[1].max_stes ?
-					  src_matcher->action_ste[1].pool :
-					   NULL;
-
-	/* Place the new resized matcher on the dst matcher's list */
-	list_add(&resize_data->list_node, &src_matcher->resize_dst->resize_data);
-
-	/* Move all the previous resized matchers to the dst matcher's list */
-	while (!list_empty(&src_matcher->resize_data)) {
-		resize_data = list_first_entry(&src_matcher->resize_data,
-					       struct mlx5hws_matcher_resize_data,
-					       list_node);
-		list_del_init(&resize_data->list_node);
-		list_add(&resize_data->list_node, &src_matcher->resize_dst->resize_data);
-	}
-
-	return 0;
-}
-
-static void hws_matcher_resize_uninit(struct mlx5hws_matcher *matcher)
-{
-	struct mlx5hws_matcher_resize_data *resize_data;
-
-	if (!mlx5hws_matcher_is_resizable(matcher))
-		return;
-
-	while (!list_empty(&matcher->resize_data)) {
-		resize_data = list_first_entry(&matcher->resize_data,
-					       struct mlx5hws_matcher_resize_data,
-					       list_node);
-		list_del_init(&resize_data->list_node);
-
-		if (resize_data->max_stes) {
-			mlx5hws_action_free_single_stc(matcher->tbl->ctx,
-						       matcher->tbl->type,
-						       &resize_data->action_ste[1].stc);
-			mlx5hws_action_free_single_stc(matcher->tbl->ctx,
-						       matcher->tbl->type,
-						       &resize_data->action_ste[0].stc);
-
-			if (matcher->tbl->type == MLX5HWS_TABLE_TYPE_FDB) {
-				mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
-							resize_data->action_ste[1].rtc_1_id);
-				mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
-							resize_data->action_ste[0].rtc_1_id);
-			}
-			mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
-						resize_data->action_ste[1].rtc_0_id);
-			mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
-						resize_data->action_ste[0].rtc_0_id);
-			if (resize_data->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].pool) {
-				mlx5hws_pool_destroy(resize_data->action_ste[1].pool);
-				mlx5hws_pool_destroy(resize_data->action_ste[0].pool);
-			}
-		}
-
-		kfree(resize_data);
-	}
-}
-
-static int
-hws_matcher_bind_at_idx(struct mlx5hws_matcher *matcher, u8 action_ste_selector)
-{
-	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
-	struct mlx5hws_matcher_action_ste *action_ste;
-	struct mlx5hws_table *tbl = matcher->tbl;
-	struct mlx5hws_pool_attr pool_attr = {0};
-	struct mlx5hws_context *ctx = tbl->ctx;
-	int ret;
-
-	action_ste = &matcher->action_ste[action_ste_selector];
-
-	/* Allocate action STE mempool */
-	pool_attr.table_type = tbl->type;
-	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
-	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL;
-	pool_attr.alloc_log_sz = ilog2(roundup_pow_of_two(action_ste->max_stes)) +
-				 matcher->attr.table.sz_row_log;
-	hws_matcher_set_pool_attr(&pool_attr, matcher);
-	action_ste->pool = mlx5hws_pool_create(ctx, &pool_attr);
-	if (!action_ste->pool) {
-		mlx5hws_err(ctx, "Failed to create action ste pool\n");
-		return -EINVAL;
-	}
-
-	/* Allocate action RTC */
-	ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector);
-	if (ret) {
-		mlx5hws_err(ctx, "Failed to create action RTC\n");
-		goto free_ste_pool;
-	}
-
-	/* Allocate STC for jumps to STE */
-	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
-	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE;
-	stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
-	stc_attr.ste_table.ste = action_ste->ste;
-	stc_attr.ste_table.ste_pool = action_ste->pool;
-	stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer;
-
-	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl->type,
-					      &action_ste->stc);
-	if (ret) {
-		mlx5hws_err(ctx, "Failed to create action jump to table STC\n");
-		goto free_rtc;
-	}
-
-	return 0;
-
-free_rtc:
-	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector);
-free_ste_pool:
-	mlx5hws_pool_destroy(action_ste->pool);
-	return ret;
-}
-
-static void hws_matcher_unbind_at_idx(struct mlx5hws_matcher *matcher, u8 action_ste_selector)
-{
-	struct mlx5hws_matcher_action_ste *action_ste;
-	struct mlx5hws_table *tbl = matcher->tbl;
-
-	action_ste = &matcher->action_ste[action_ste_selector];
-
-	if (!action_ste->max_stes ||
-	    matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION ||
-	    mlx5hws_matcher_is_in_resize(matcher))
-		return;
-
-	mlx5hws_action_free_single_stc(tbl->ctx, tbl->type, &action_ste->stc);
-	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector);
-	mlx5hws_pool_destroy(action_ste->pool);
-}
-
 static int hws_matcher_bind_at(struct mlx5hws_matcher *matcher)
 {
 	bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(matcher->mt);
-	struct mlx5hws_table *tbl = matcher->tbl;
-	struct mlx5hws_context *ctx = tbl->ctx;
-	u32 required_stes;
-	u8 max_stes = 0;
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	u8 required_stes, max_stes;
 	int i, ret;
 
 	if (matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION)
 		return 0;
 
+	max_stes = 0;
 	for (i = 0; i < matcher->num_of_at; i++) {
 		struct mlx5hws_action_template *at = &matcher->at[i];
 
@@ -637,38 +652,40 @@ static int hws_matcher_bind_at(struct mlx5hws_matcher *matcher)
 		/* Future: Optimize reparse */
 	}
 
-	/* There are no additional STEs required for matcher */
-	if (!max_stes)
-		return 0;
-
-	matcher->action_ste[0].max_stes = max_stes;
-	matcher->action_ste[1].max_stes = max_stes;
-
-	ret = hws_matcher_bind_at_idx(matcher, 0);
-	if (ret)
-		return ret;
-
-	ret = hws_matcher_bind_at_idx(matcher, 1);
-	if (ret)
-		goto free_at_0;
+	matcher->num_of_action_stes = max_stes;
 
 	return 0;
-
-free_at_0:
-	hws_matcher_unbind_at_idx(matcher, 0);
-	return ret;
 }
 
-static void hws_matcher_unbind_at(struct mlx5hws_matcher *matcher)
+static void hws_matcher_set_ip_version_match(struct mlx5hws_matcher *matcher)
 {
-	hws_matcher_unbind_at_idx(matcher, 1);
-	hws_matcher_unbind_at_idx(matcher, 0);
+	int i;
+
+	for (i = 0; i < matcher->mt->fc_sz; i++) {
+		switch (matcher->mt->fc[i].fname) {
+		case MLX5HWS_DEFINER_FNAME_ETH_TYPE_O:
+			matcher->matches_outer_ethertype = 1;
+			break;
+		case MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_O:
+			matcher->matches_outer_ip_version = 1;
+			break;
+		case MLX5HWS_DEFINER_FNAME_ETH_TYPE_I:
+			matcher->matches_inner_ethertype = 1;
+			break;
+		case MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_I:
+			matcher->matches_inner_ip_version = 1;
+			break;
+		default:
+			break;
+		}
+	}
 }
 
 static int hws_matcher_bind_mt(struct mlx5hws_matcher *matcher)
 {
+	struct mlx5hws_cmd_ste_create_attr ste_attr = {};
 	struct mlx5hws_context *ctx = matcher->tbl->ctx;
-	struct mlx5hws_pool_attr pool_attr = {0};
+	union mlx5hws_matcher_size *size;
 	int ret;
 
 	/* Calculate match, range and hash definers */
@@ -681,23 +698,41 @@ static int hws_matcher_bind_mt(struct mlx5hws_matcher *matcher)
 		}
 	}
 
-	/* Create an STE pool per matcher*/
-	pool_attr.table_type = matcher->tbl->type;
-	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
-	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_MATCHER_STE_POOL;
-	pool_attr.alloc_log_sz = matcher->attr.table.sz_col_log +
-				 matcher->attr.table.sz_row_log;
-	hws_matcher_set_pool_attr(&pool_attr, matcher);
-
-	matcher->match_ste.pool = mlx5hws_pool_create(ctx, &pool_attr);
-	if (!matcher->match_ste.pool) {
-		mlx5hws_err(ctx, "Failed to allocate matcher STE pool\n");
-		ret = -EOPNOTSUPP;
+	hws_matcher_set_ip_version_match(matcher);
+
+	/* Create an STE range each for RX and TX. */
+	ste_attr.table_type = FS_FT_FDB_RX;
+	size = &matcher->attr.size[MLX5HWS_MATCHER_SIZE_TYPE_RX];
+	ste_attr.log_obj_range =
+		matcher->attr.optimize_flow_src ==
+			MLX5HWS_MATCHER_FLOW_SRC_VPORT ?
+			0 : size->table.sz_col_log + size->table.sz_row_log;
+
+	ret = mlx5hws_cmd_ste_create(ctx->mdev, &ste_attr,
+				     &matcher->match_ste.ste_0_base);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to allocate RX STE range (%d)\n", ret);
 		goto uninit_match_definer;
 	}
 
+	ste_attr.table_type = FS_FT_FDB_TX;
+	size = &matcher->attr.size[MLX5HWS_MATCHER_SIZE_TYPE_TX];
+	ste_attr.log_obj_range =
+		matcher->attr.optimize_flow_src ==
+			MLX5HWS_MATCHER_FLOW_SRC_WIRE ?
+			0 : size->table.sz_col_log + size->table.sz_row_log;
+
+	ret = mlx5hws_cmd_ste_create(ctx->mdev, &ste_attr,
+				     &matcher->match_ste.ste_1_base);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to allocate TX STE range (%d)\n", ret);
+		goto destroy_rx_ste_range;
+	}
+
 	return 0;
 
+destroy_rx_ste_range:
+	mlx5hws_cmd_ste_destroy(ctx->mdev, matcher->match_ste.ste_0_base);
 uninit_match_definer:
 	if (!(matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION))
 		mlx5hws_definer_mt_uninit(ctx, matcher->mt);
@@ -706,9 +741,12 @@ uninit_match_definer:
 
 static void hws_matcher_unbind_mt(struct mlx5hws_matcher *matcher)
 {
-	mlx5hws_pool_destroy(matcher->match_ste.pool);
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+
+	mlx5hws_cmd_ste_destroy(ctx->mdev, matcher->match_ste.ste_1_base);
+	mlx5hws_cmd_ste_destroy(ctx->mdev, matcher->match_ste.ste_0_base);
 	if (!(matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION))
-		mlx5hws_definer_mt_uninit(matcher->tbl->ctx, matcher->mt);
+		mlx5hws_definer_mt_uninit(ctx, matcher->mt);
 }
 
 static int
@@ -717,6 +755,10 @@ hws_matcher_validate_insert_mode(struct mlx5hws_cmd_query_caps *caps,
 {
 	struct mlx5hws_matcher_attr *attr = &matcher->attr;
 	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	union mlx5hws_matcher_size *size_rx, *size_tx;
+
+	size_rx = &matcher->attr.size[MLX5HWS_MATCHER_SIZE_TYPE_RX];
+	size_tx = &matcher->attr.size[MLX5HWS_MATCHER_SIZE_TYPE_TX];
 
 	switch (attr->insert_mode) {
 	case MLX5HWS_MATCHER_INSERT_BY_HASH:
@@ -727,7 +769,7 @@ hws_matcher_validate_insert_mode(struct mlx5hws_cmd_query_caps *caps,
 		break;
 
 	case MLX5HWS_MATCHER_INSERT_BY_INDEX:
-		if (attr->table.sz_col_log) {
+		if (size_rx->table.sz_col_log || size_tx->table.sz_col_log) {
 			mlx5hws_err(ctx, "Matcher with INSERT_BY_INDEX supports only Nx1 table size\n");
 			return -EOPNOTSUPP;
 		}
@@ -747,7 +789,10 @@ hws_matcher_validate_insert_mode(struct mlx5hws_cmd_query_caps *caps,
 				return -EOPNOTSUPP;
 			}
 
-			if (attr->table.sz_row_log > MLX5_IFC_RTC_LINEAR_LOOKUP_TBL_LOG_MAX) {
+			if (size_rx->table.sz_row_log >
+				MLX5_IFC_RTC_LINEAR_LOOKUP_TBL_LOG_MAX ||
+			    size_tx->table.sz_row_log >
+				MLX5_IFC_RTC_LINEAR_LOOKUP_TBL_LOG_MAX) {
 				mlx5hws_err(ctx, "Matcher with linear distribute: rows exceed limit %d",
 					    MLX5_IFC_RTC_LINEAR_LOOKUP_TBL_LOG_MAX);
 				return -EOPNOTSUPP;
@@ -771,6 +816,10 @@ hws_matcher_process_attr(struct mlx5hws_cmd_query_caps *caps,
 			 struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_matcher_attr *attr = &matcher->attr;
+	union mlx5hws_matcher_size *size_rx, *size_tx;
+
+	size_rx = &attr->size[MLX5HWS_MATCHER_SIZE_TYPE_RX];
+	size_tx = &attr->size[MLX5HWS_MATCHER_SIZE_TYPE_TX];
 
 	if (hws_matcher_validate_insert_mode(caps, matcher))
 		return -EOPNOTSUPP;
@@ -782,10 +831,16 @@ hws_matcher_process_attr(struct mlx5hws_cmd_query_caps *caps,
 
 	/* Convert number of rules to the required depth */
 	if (attr->mode == MLX5HWS_MATCHER_RESOURCE_MODE_RULE &&
-	    attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_HASH)
-		attr->table.sz_col_log = hws_matcher_rules_to_tbl_depth(attr->rule.num_log);
+	    attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_HASH) {
+		size_rx->table.sz_col_log =
+			hws_matcher_rules_to_tbl_depth(size_rx->rule.num_log);
+		size_tx->table.sz_col_log =
+			hws_matcher_rules_to_tbl_depth(size_tx->rule.num_log);
+	}
 
 	matcher->flags |= attr->resizable ? MLX5HWS_MATCHER_FLAGS_RESIZABLE : 0;
+	matcher->flags |= attr->isolated_matcher_end_ft_id ?
+			  MLX5HWS_MATCHER_FLAGS_ISOLATED : 0;
 
 	return hws_matcher_check_attr_sz(caps, matcher);
 }
@@ -807,10 +862,10 @@ static int hws_matcher_create_and_connect(struct mlx5hws_matcher *matcher)
 	/* Create matcher end flow table anchor */
 	ret = hws_matcher_create_end_ft(matcher);
 	if (ret)
-		goto unbind_at;
+		goto unbind_mt;
 
 	/* Allocate the RTC for the new matcher */
-	ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0);
+	ret = hws_matcher_create_rtc(matcher);
 	if (ret)
 		goto destroy_end_ft;
 
@@ -822,11 +877,9 @@ static int hws_matcher_create_and_connect(struct mlx5hws_matcher *matcher)
 	return 0;
 
 destroy_rtc:
-	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0);
+	hws_matcher_destroy_rtc(matcher);
 destroy_end_ft:
 	hws_matcher_destroy_end_ft(matcher);
-unbind_at:
-	hws_matcher_unbind_at(matcher);
 unbind_mt:
 	hws_matcher_unbind_mt(matcher);
 	return ret;
@@ -834,11 +887,9 @@ unbind_mt:
 
 static void hws_matcher_destroy_and_disconnect(struct mlx5hws_matcher *matcher)
 {
-	hws_matcher_resize_uninit(matcher);
 	hws_matcher_disconnect(matcher);
-	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0);
+	hws_matcher_destroy_rtc(matcher);
 	hws_matcher_destroy_end_ft(matcher);
-	hws_matcher_unbind_at(matcher);
 	hws_matcher_unbind_mt(matcher);
 }
 
@@ -846,22 +897,25 @@ static int
 hws_matcher_create_col_matcher(struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	union mlx5hws_matcher_size *size_rx, *size_tx;
 	struct mlx5hws_matcher *col_matcher;
-	int ret;
+	int i, ret;
+
+	size_rx = &matcher->attr.size[MLX5HWS_MATCHER_SIZE_TYPE_RX];
+	size_tx = &matcher->attr.size[MLX5HWS_MATCHER_SIZE_TYPE_TX];
 
 	if (matcher->attr.mode != MLX5HWS_MATCHER_RESOURCE_MODE_RULE ||
 	    matcher->attr.insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX)
 		return 0;
 
-	if (!hws_matcher_requires_col_tbl(matcher->attr.rule.num_log))
+	if (!hws_matcher_requires_col_tbl(size_rx->rule.num_log) &&
+	    !hws_matcher_requires_col_tbl(size_tx->rule.num_log))
 		return 0;
 
 	col_matcher = kzalloc(sizeof(*matcher), GFP_KERNEL);
 	if (!col_matcher)
 		return -ENOMEM;
 
-	INIT_LIST_HEAD(&col_matcher->resize_data);
-
 	col_matcher->tbl = matcher->tbl;
 	col_matcher->mt = matcher->mt;
 	col_matcher->at = matcher->at;
@@ -872,12 +926,20 @@ hws_matcher_create_col_matcher(struct mlx5hws_matcher *matcher)
 	col_matcher->flags |= MLX5HWS_MATCHER_FLAGS_COLLISION;
 	col_matcher->attr.mode = MLX5HWS_MATCHER_RESOURCE_MODE_HTABLE;
 	col_matcher->attr.optimize_flow_src = matcher->attr.optimize_flow_src;
-	col_matcher->attr.table.sz_row_log = matcher->attr.rule.num_log;
-	col_matcher->attr.table.sz_col_log = MLX5HWS_MATCHER_ASSURED_COL_TBL_DEPTH;
-	if (col_matcher->attr.table.sz_row_log > MLX5HWS_MATCHER_ASSURED_ROW_RATIO)
-		col_matcher->attr.table.sz_row_log -= MLX5HWS_MATCHER_ASSURED_ROW_RATIO;
+	for (i = 0; i < 2; i++) {
+		union mlx5hws_matcher_size *dst = &col_matcher->attr.size[i];
+		union mlx5hws_matcher_size *src = &matcher->attr.size[i];
+
+		dst->table.sz_row_log = src->rule.num_log;
+		dst->table.sz_col_log = MLX5HWS_MATCHER_ASSURED_COL_TBL_DEPTH;
+		if (dst->table.sz_row_log > MLX5HWS_MATCHER_ASSURED_ROW_RATIO)
+			dst->table.sz_row_log -=
+				MLX5HWS_MATCHER_ASSURED_ROW_RATIO;
+	}
 
 	col_matcher->attr.max_num_of_at_attach = matcher->attr.max_num_of_at_attach;
+	col_matcher->attr.isolated_matcher_end_ft_id =
+		matcher->attr.isolated_matcher_end_ft_id;
 
 	ret = hws_matcher_process_attr(ctx->caps, col_matcher);
 	if (ret)
@@ -915,8 +977,6 @@ static int hws_matcher_init(struct mlx5hws_matcher *matcher)
 	struct mlx5hws_context *ctx = matcher->tbl->ctx;
 	int ret;
 
-	INIT_LIST_HEAD(&matcher->resize_data);
-
 	mutex_lock(&ctx->ctrl_lock);
 
 	/* Allocate matcher resource and connect to the packet pipe */
@@ -951,18 +1011,44 @@ static int hws_matcher_uninit(struct mlx5hws_matcher *matcher)
 	return 0;
 }
 
+static int hws_matcher_grow_at_array(struct mlx5hws_matcher *matcher)
+{
+	void *p;
+
+	if (matcher->size_of_at_array >= MLX5HWS_MATCHER_MAX_AT)
+		return -ENOMEM;
+
+	matcher->size_of_at_array *= 2;
+	p = krealloc(matcher->at,
+		     matcher->size_of_at_array * sizeof(*matcher->at),
+		     __GFP_ZERO | GFP_KERNEL);
+	if (!p) {
+		matcher->size_of_at_array /= 2;
+		return -ENOMEM;
+	}
+
+	matcher->at = p;
+
+	return 0;
+}
+
 int mlx5hws_matcher_attach_at(struct mlx5hws_matcher *matcher,
 			      struct mlx5hws_action_template *at)
 {
 	bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(matcher->mt);
-	struct mlx5hws_context *ctx = matcher->tbl->ctx;
 	u32 required_stes;
 	int ret;
 
-	if (!matcher->attr.max_num_of_at_attach) {
-		mlx5hws_dbg(ctx, "Num of current at (%d) exceed allowed value\n",
-			    matcher->num_of_at);
-		return -EOPNOTSUPP;
+	if (unlikely(matcher->num_of_at >= matcher->size_of_at_array)) {
+		ret = hws_matcher_grow_at_array(matcher);
+		if (ret)
+			return ret;
+
+		if (matcher->col_matcher) {
+			ret = hws_matcher_grow_at_array(matcher->col_matcher);
+			if (ret)
+				return ret;
+		}
 	}
 
 	ret = hws_matcher_check_and_process_at(matcher, at);
@@ -970,16 +1056,11 @@ int mlx5hws_matcher_attach_at(struct mlx5hws_matcher *matcher,
 		return ret;
 
 	required_stes = at->num_of_action_stes - (!is_jumbo || at->only_term);
-	if (matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes < required_stes) {
-		mlx5hws_dbg(ctx, "Required STEs [%d] exceeds initial action template STE [%d]\n",
-			    required_stes,
-			    matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes);
-		return -ENOMEM;
-	}
+	if (matcher->num_of_action_stes < required_stes)
+		matcher->num_of_action_stes = required_stes;
 
 	matcher->at[matcher->num_of_at] = *at;
 	matcher->num_of_at += 1;
-	matcher->attr.max_num_of_at_attach -= 1;
 
 	if (matcher->col_matcher)
 		matcher->col_matcher->num_of_at = matcher->num_of_at;
@@ -1007,9 +1088,10 @@ hws_matcher_set_templates(struct mlx5hws_matcher *matcher,
 	if (!matcher->mt)
 		return -ENOMEM;
 
-	matcher->at = kcalloc(num_of_at + matcher->attr.max_num_of_at_attach,
-			      sizeof(*matcher->at),
-			      GFP_KERNEL);
+	matcher->size_of_at_array =
+		num_of_at + matcher->attr.max_num_of_at_attach;
+	matcher->at = kvcalloc(matcher->size_of_at_array, sizeof(*matcher->at),
+			       GFP_KERNEL);
 	if (!matcher->at) {
 		mlx5hws_err(ctx, "Failed to allocate action template array\n");
 		ret = -ENOMEM;
@@ -1035,7 +1117,7 @@ free_mt:
 static void
 hws_matcher_unset_templates(struct mlx5hws_matcher *matcher)
 {
-	kfree(matcher->at);
+	kvfree(matcher->at);
 	kfree(matcher->mt);
 }
 
@@ -1157,8 +1239,7 @@ static int hws_matcher_resize_precheck(struct mlx5hws_matcher *src_matcher,
 		return -EINVAL;
 	}
 
-	if (src_matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes >
-	    dst_matcher->action_ste[0].max_stes) {
+	if (src_matcher->num_of_action_stes > dst_matcher->num_of_action_stes) {
 		mlx5hws_err(ctx, "Src/dst matcher max STEs mismatch\n");
 		return -EINVAL;
 	}
@@ -1187,10 +1268,6 @@ int mlx5hws_matcher_resize_set_target(struct mlx5hws_matcher *src_matcher,
 
 	src_matcher->resize_dst = dst_matcher;
 
-	ret = hws_matcher_resize_init(src_matcher);
-	if (ret)
-		src_matcher->resize_dst = NULL;
-
 out:
 	mutex_unlock(&src_matcher->tbl->ctx->ctrl_lock);
 	return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h
index 81ff487f57be..ae20bcebfdde 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h
@@ -18,6 +18,14 @@
 /* Required depth of the main large table */
 #define MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH 2
 
+/* Action RTC size multiplier that is required in order
+ * to support rule update for rules with action STEs.
+ */
+#define MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT 1
+
+/* Maximum number of action templates that can be attached to a matcher. */
+#define MLX5HWS_MATCHER_MAX_AT 128
+
 enum mlx5hws_matcher_offset {
 	MLX5HWS_MATCHER_OFFSET_TAG_DW1 = 12,
 	MLX5HWS_MATCHER_OFFSET_TAG_DW0 = 13,
@@ -26,6 +34,7 @@ enum mlx5hws_matcher_offset {
 enum mlx5hws_matcher_flags {
 	MLX5HWS_MATCHER_FLAGS_COLLISION = 1 << 2,
 	MLX5HWS_MATCHER_FLAGS_RESIZABLE	= 1 << 3,
+	MLX5HWS_MATCHER_FLAGS_ISOLATED	= 1 << 4,
 };
 
 struct mlx5hws_match_template {
@@ -37,32 +46,16 @@ struct mlx5hws_match_template {
 };
 
 struct mlx5hws_matcher_match_ste {
-	struct mlx5hws_pool_chunk ste;
-	u32 rtc_0_id;
-	u32 rtc_1_id;
-	struct mlx5hws_pool *pool;
-};
-
-struct mlx5hws_matcher_action_ste {
-	struct mlx5hws_pool_chunk ste;
-	struct mlx5hws_pool_chunk stc;
-	u32 rtc_0_id;
-	u32 rtc_1_id;
-	struct mlx5hws_pool *pool;
-	u8 max_stes;
-};
-
-struct mlx5hws_matcher_resize_data_node {
-	struct mlx5hws_pool_chunk stc;
 	u32 rtc_0_id;
 	u32 rtc_1_id;
-	struct mlx5hws_pool *pool;
+	u32 ste_0_base;
+	u32 ste_1_base;
 };
 
-struct mlx5hws_matcher_resize_data {
-	struct mlx5hws_matcher_resize_data_node action_ste[2];
-	u8 max_stes;
-	struct list_head list_node;
+enum {
+	MLX5HWS_MATCHER_IPV_UNSET = 0,
+	MLX5HWS_MATCHER_IPV_4 = 1,
+	MLX5HWS_MATCHER_IPV_6 = 2,
 };
 
 struct mlx5hws_matcher {
@@ -71,16 +64,22 @@ struct mlx5hws_matcher {
 	struct mlx5hws_match_template *mt;
 	struct mlx5hws_action_template *at;
 	u8 num_of_at;
+	u8 size_of_at_array;
 	u8 num_of_mt;
+	u8 num_of_action_stes;
 	/* enum mlx5hws_matcher_flags */
 	u8 flags;
+	u8 matches_outer_ethertype:1;
+	u8 matches_outer_ip_version:1;
+	u8 matches_inner_ethertype:1;
+	u8 matches_inner_ip_version:1;
+	u8 outer_ip_version:2;
+	u8 inner_ip_version:2;
 	u32 end_ft_id;
 	struct mlx5hws_matcher *col_matcher;
 	struct mlx5hws_matcher *resize_dst;
 	struct mlx5hws_matcher_match_ste match_ste;
-	struct mlx5hws_matcher_action_ste action_ste[2];
 	struct list_head list_node;
-	struct list_head resize_data;
 };
 
 static inline bool
@@ -99,9 +98,17 @@ static inline bool mlx5hws_matcher_is_in_resize(struct mlx5hws_matcher *matcher)
 	return !!matcher->resize_dst;
 }
 
+static inline bool mlx5hws_matcher_is_isolated(struct mlx5hws_matcher *matcher)
+{
+	return !!(matcher->flags & MLX5HWS_MATCHER_FLAGS_ISOLATED);
+}
+
 static inline bool mlx5hws_matcher_is_insert_by_idx(struct mlx5hws_matcher *matcher)
 {
 	return matcher->attr.insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX;
 }
 
+int mlx5hws_matcher_update_end_ft_isolated(struct mlx5hws_table *tbl,
+					   u32 miss_ft_id);
+
 #endif /* HWS_MATCHER_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
index f39d636ff39a..1ad7a50d938b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
@@ -70,12 +70,12 @@ enum mlx5hws_send_queue_actions {
 struct mlx5hws_context_attr {
 	u16 queues;
 	u16 queue_size;
-	bool bwc; /* add support for backward compatible API*/
 };
 
 struct mlx5hws_table_attr {
 	enum mlx5hws_table_type type;
 	u32 level;
+	u16 uid;
 };
 
 enum mlx5hws_matcher_flow_src {
@@ -94,6 +94,23 @@ enum mlx5hws_matcher_distribute_mode {
 	MLX5HWS_MATCHER_DISTRIBUTE_BY_LINEAR = 0x1,
 };
 
+enum mlx5hws_matcher_size_type {
+	MLX5HWS_MATCHER_SIZE_TYPE_RX,
+	MLX5HWS_MATCHER_SIZE_TYPE_TX,
+	MLX5HWS_MATCHER_SIZE_TYPE_MAX,
+};
+
+union mlx5hws_matcher_size {
+	struct {
+		u8 sz_row_log;
+		u8 sz_col_log;
+	} table;
+
+	struct {
+		u8 num_log;
+	} rule;
+};
+
 struct mlx5hws_matcher_attr {
 	/* Processing priority inside table */
 	u32 priority;
@@ -108,18 +125,11 @@ struct mlx5hws_matcher_attr {
 	enum mlx5hws_matcher_distribute_mode distribute_mode;
 	/* Define whether the created matcher supports resizing into a bigger matcher */
 	bool resizable;
-	union {
-		struct {
-			u8 sz_row_log;
-			u8 sz_col_log;
-		} table;
-
-		struct {
-			u8 num_log;
-		} rule;
-	};
+	union mlx5hws_matcher_size size[MLX5HWS_MATCHER_SIZE_TYPE_MAX];
 	/* Optional AT attach configuration - Max number of additional AT */
 	u8 max_num_of_at_attach;
+	/* Optional end FT (miss FT ID) for match RTC (for isolated matcher) */
+	u32 isolated_matcher_end_ft_id;
 };
 
 struct mlx5hws_rule_attr {
@@ -212,6 +222,7 @@ struct mlx5hws_action_dest_attr {
 	struct mlx5hws_action *dest;
 	/* Optional reformat action */
 	struct mlx5hws_action *reformat;
+	bool is_wire_ft;
 };
 
 /**
@@ -503,6 +514,15 @@ enum mlx5hws_action_type
 mlx5hws_action_get_type(struct mlx5hws_action *action);
 
 /**
+ * mlx5hws_action_get_dev - Get mlx5 core device.
+ *
+ * @action: The action to get the device from.
+ *
+ * Return: mlx5 core device.
+ */
+struct mlx5_core_dev *mlx5hws_action_get_dev(struct mlx5hws_action *action);
+
+/**
  * mlx5hws_action_create_dest_drop - Create a direct rule drop action.
  *
  * @ctx: The context in which the new action will be created.
@@ -715,18 +735,13 @@ mlx5hws_action_create_push_vlan(struct mlx5hws_context *ctx, u32 flags);
  * @num_dest: The number of dests attributes.
  * @dests: The destination array. Each contains a destination action and can
  *	   have additional actions.
- * @ignore_flow_level: Whether to turn on 'ignore_flow_level' for this dest.
- * @flow_source: Source port of the traffic for this actions.
  * @flags: Action creation flags (enum mlx5hws_action_flags).
  *
  * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
-mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
-				 size_t num_dest,
+mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx, size_t num_dest,
 				 struct mlx5hws_action_dest_attr *dests,
-				 bool ignore_flow_level,
-				 u32 flow_source,
 				 u32 flags);
 
 /**
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
index 06db5e4726ae..d56271a9e4f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
@@ -153,8 +153,7 @@ mlx5hws_pat_get_existing_cached_pattern(struct mlx5hws_pattern_cache *cache,
 	cached_pattern = mlx5hws_pat_find_cached_pattern(cache, num_of_actions, actions);
 	if (cached_pattern) {
 		/* LRU: move it to be first in the list */
-		list_del_init(&cached_pattern->ptrn_list_node);
-		list_add(&cached_pattern->ptrn_list_node, &cache->ptrn_list);
+		list_move(&cached_pattern->ptrn_list_node, &cache->ptrn_list);
 		cached_pattern->refcount++;
 	}
 
@@ -280,7 +279,7 @@ int mlx5hws_pat_get_pattern(struct mlx5hws_context *ctx,
 	return ret;
 
 clean_pattern:
-	mlx5hws_cmd_header_modify_pattern_destroy(ctx->mdev, *pattern_id);
+	mlx5hws_cmd_header_modify_pattern_destroy(ctx->mdev, ptrn_id);
 out_unlock:
 	mutex_unlock(&ctx->pattern_cache->lock);
 	return ret;
@@ -344,7 +343,7 @@ void mlx5hws_arg_write(struct mlx5hws_send_engine *queue,
 		mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_ctrl, &wqe_len);
 		memset(wqe_ctrl, 0, wqe_len);
 		mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_arg, &wqe_len);
-		memcpy(wqe_arg, arg_data, wqe_len);
+		memcpy(wqe_arg, arg_data, MLX5HWS_ARG_DATA_SIZE);
 		send_attr.id = arg_idx++;
 		mlx5hws_send_engine_post_end(&ctrl, &send_attr);
 
@@ -491,8 +490,8 @@ hws_action_modify_get_target_fields(u8 action_type, __be64 *pattern,
 	switch (action_type) {
 	case MLX5_ACTION_TYPE_SET:
 	case MLX5_ACTION_TYPE_ADD:
-		*src_field = MLX5_GET(set_action_in, pattern, field);
-		*dst_field = INVALID_FIELD;
+		*src_field = INVALID_FIELD;
+		*dst_field = MLX5_GET(set_action_in, pattern, field);
 		break;
 	case MLX5_ACTION_TYPE_COPY:
 		*src_field = MLX5_GET(copy_action_in, pattern, src_field);
@@ -523,57 +522,61 @@ bool mlx5hws_pat_verify_actions(struct mlx5hws_context *ctx, __be64 pattern[], s
 	return true;
 }
 
-void mlx5hws_pat_calc_nope(__be64 *pattern, size_t num_actions,
-			   size_t max_actions, size_t *new_size,
-			   u32 *nope_location, __be64 *new_pat)
+int mlx5hws_pat_calc_nop(__be64 *pattern, size_t num_actions,
+			 size_t max_actions, size_t *new_size,
+			 u32 *nop_locations, __be64 *new_pat)
 {
-	u16 prev_src_field = 0, prev_dst_field = 0;
-	u16 src_field, dst_field;
+	u16 prev_src_field = INVALID_FIELD, prev_dst_field = INVALID_FIELD;
 	u8 action_type;
+	bool dependent;
 	size_t i, j;
 
 	*new_size = num_actions;
-	*nope_location = 0;
+	*nop_locations = 0;
 
 	if (num_actions == 1)
-		return;
+		return 0;
 
 	for (i = 0, j = 0; i < num_actions; i++, j++) {
-		action_type = MLX5_GET(set_action_in, &pattern[i], action_type);
+		u16 src_field = INVALID_FIELD;
+		u16 dst_field = INVALID_FIELD;
+
+		if (j >= max_actions)
+			return -EINVAL;
 
+		action_type = MLX5_GET(set_action_in, &pattern[i], action_type);
 		hws_action_modify_get_target_fields(action_type, &pattern[i],
 						    &src_field, &dst_field);
-		if (i % 2) {
-			if (action_type == MLX5_ACTION_TYPE_COPY &&
-			    (prev_src_field == src_field ||
-			     prev_dst_field == dst_field)) {
-				/* need Nope */
-				*new_size += 1;
-				*nope_location |= BIT(i);
-				memset(&new_pat[j], 0, MLX5HWS_MODIFY_ACTION_SIZE);
-				MLX5_SET(set_action_in, &new_pat[j],
-					 action_type,
-					 MLX5_MODIFICATION_TYPE_NOP);
-				j++;
-			} else if (prev_src_field == src_field) {
-				/* need Nope*/
-				*new_size += 1;
-				*nope_location |= BIT(i);
-				MLX5_SET(set_action_in, &new_pat[j],
-					 action_type,
-					 MLX5_MODIFICATION_TYPE_NOP);
-				j++;
-			}
-		}
-		memcpy(&new_pat[j], &pattern[i], MLX5HWS_MODIFY_ACTION_SIZE);
-		/* check if no more space */
-		if (j > max_actions) {
-			*new_size = num_actions;
-			*nope_location = 0;
-			return;
+
+		/* For every action, look at it and the previous one. The two
+		 * actions are dependent if:
+		 */
+		dependent =
+			(i > 0) &&
+			/* At least one of the actions is a write and */
+			(dst_field != INVALID_FIELD ||
+			 prev_dst_field != INVALID_FIELD) &&
+			/* One reads from the other's source */
+			(dst_field == prev_src_field ||
+			 src_field == prev_dst_field ||
+			 /* Or both write to the same destination */
+			 dst_field == prev_dst_field);
+
+		if (dependent) {
+			*new_size += 1;
+			*nop_locations |= BIT(i);
+			memset(&new_pat[j], 0, MLX5HWS_MODIFY_ACTION_SIZE);
+			MLX5_SET(set_action_in, &new_pat[j], action_type,
+				 MLX5_MODIFICATION_TYPE_NOP);
+			j++;
+			if (j >= max_actions)
+				return -EINVAL;
 		}
 
+		memcpy(&new_pat[j], &pattern[i], MLX5HWS_MODIFY_ACTION_SIZE);
 		prev_src_field = src_field;
 		prev_dst_field = dst_field;
 	}
+
+	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h
index 27ca93385b08..7fbd8dc7aa18 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h
@@ -31,7 +31,7 @@ struct mlx5hws_pattern_cache_item {
 		u8 *data;
 		u16 num_of_actions;
 	} mh_data;
-	u32 refcount;
+	u32 refcount; /* protected by pattern_cache lock */
 	struct list_head ptrn_list_node;
 };
 
@@ -96,6 +96,7 @@ int mlx5hws_arg_write_inline_arg_data(struct mlx5hws_context *ctx,
 				      u8 *arg_data,
 				      size_t data_size);
 
-void mlx5hws_pat_calc_nope(__be64 *pattern, size_t num_actions, size_t max_actions,
-			   size_t *new_size, u32 *nope_location, __be64 *new_pat);
+int mlx5hws_pat_calc_nop(__be64 *pattern, size_t num_actions,
+			 size_t max_actions, size_t *new_size,
+			 u32 *nop_locations, __be64 *new_pat);
 #endif /* MLX5HWS_PAT_ARG_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
index fed2d913f3b8..7b5071c3df36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
@@ -20,15 +20,14 @@ static void hws_pool_free_one_resource(struct mlx5hws_pool_resource *resource)
 	kfree(resource);
 }
 
-static void hws_pool_resource_free(struct mlx5hws_pool *pool,
-				   int resource_idx)
+static void hws_pool_resource_free(struct mlx5hws_pool *pool)
 {
-	hws_pool_free_one_resource(pool->resource[resource_idx]);
-	pool->resource[resource_idx] = NULL;
+	hws_pool_free_one_resource(pool->resource);
+	pool->resource = NULL;
 
 	if (pool->tbl_type == MLX5HWS_TABLE_TYPE_FDB) {
-		hws_pool_free_one_resource(pool->mirror_resource[resource_idx]);
-		pool->mirror_resource[resource_idx] = NULL;
+		hws_pool_free_one_resource(pool->mirror_resource);
+		pool->mirror_resource = NULL;
 	}
 }
 
@@ -61,10 +60,8 @@ hws_pool_create_one_resource(struct mlx5hws_pool *pool, u32 log_range,
 		ret = -EINVAL;
 	}
 
-	if (ret) {
-		mlx5hws_err(pool->ctx, "Failed to allocate resource objects\n");
+	if (ret)
 		goto free_resource;
-	}
 
 	resource->pool = pool;
 	resource->range = 1 << log_range;
@@ -77,199 +74,115 @@ free_resource:
 	return NULL;
 }
 
-static int
-hws_pool_resource_alloc(struct mlx5hws_pool *pool, u32 log_range, int idx)
+static int hws_pool_resource_alloc(struct mlx5hws_pool *pool)
 {
 	struct mlx5hws_pool_resource *resource;
 	u32 fw_ft_type, opt_log_range;
 
 	fw_ft_type = mlx5hws_table_get_res_fw_ft_type(pool->tbl_type, false);
-	opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_ORIG ? 0 : log_range;
+	opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_MIRROR ?
+				0 : pool->alloc_log_sz;
 	resource = hws_pool_create_one_resource(pool, opt_log_range, fw_ft_type);
 	if (!resource) {
-		mlx5hws_err(pool->ctx, "Failed allocating resource\n");
+		mlx5hws_err(pool->ctx, "Failed to allocate resource\n");
 		return -EINVAL;
 	}
 
-	pool->resource[idx] = resource;
+	pool->resource = resource;
 
 	if (pool->tbl_type == MLX5HWS_TABLE_TYPE_FDB) {
 		struct mlx5hws_pool_resource *mirror_resource;
 
 		fw_ft_type = mlx5hws_table_get_res_fw_ft_type(pool->tbl_type, true);
-		opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_MIRROR ? 0 : log_range;
+		opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_ORIG ?
+					0 : pool->alloc_log_sz;
 		mirror_resource = hws_pool_create_one_resource(pool, opt_log_range, fw_ft_type);
 		if (!mirror_resource) {
-			mlx5hws_err(pool->ctx, "Failed allocating mirrored resource\n");
+			mlx5hws_err(pool->ctx, "Failed to allocate mirrored resource\n");
 			hws_pool_free_one_resource(resource);
-			pool->resource[idx] = NULL;
+			pool->resource = NULL;
 			return -EINVAL;
 		}
-		pool->mirror_resource[idx] = mirror_resource;
+		pool->mirror_resource = mirror_resource;
 	}
 
 	return 0;
 }
 
-static unsigned long *hws_pool_create_and_init_bitmap(u32 log_range)
-{
-	unsigned long *cur_bmp;
-
-	cur_bmp = bitmap_zalloc(1 << log_range, GFP_KERNEL);
-	if (!cur_bmp)
-		return NULL;
-
-	bitmap_fill(cur_bmp, 1 << log_range);
-
-	return cur_bmp;
-}
-
-static void hws_pool_buddy_db_put_chunk(struct mlx5hws_pool *pool,
-					struct mlx5hws_pool_chunk *chunk)
+static int hws_pool_buddy_init(struct mlx5hws_pool *pool)
 {
 	struct mlx5hws_buddy_mem *buddy;
 
-	buddy = pool->db.buddy_manager->buddies[chunk->resource_idx];
+	buddy = mlx5hws_buddy_create(pool->alloc_log_sz);
 	if (!buddy) {
-		mlx5hws_err(pool->ctx, "No such buddy (%d)\n", chunk->resource_idx);
-		return;
-	}
-
-	mlx5hws_buddy_free_mem(buddy, chunk->offset, chunk->order);
-}
-
-static struct mlx5hws_buddy_mem *
-hws_pool_buddy_get_next_buddy(struct mlx5hws_pool *pool, int idx,
-			      u32 order, bool *is_new_buddy)
-{
-	static struct mlx5hws_buddy_mem *buddy;
-	u32 new_buddy_size;
-
-	buddy = pool->db.buddy_manager->buddies[idx];
-	if (buddy)
-		return buddy;
-
-	new_buddy_size = max(pool->alloc_log_sz, order);
-	*is_new_buddy = true;
-	buddy = mlx5hws_buddy_create(new_buddy_size);
-	if (!buddy) {
-		mlx5hws_err(pool->ctx, "Failed to create buddy order: %d index: %d\n",
-			    new_buddy_size, idx);
-		return NULL;
+		mlx5hws_err(pool->ctx, "Failed to create buddy order: %zu\n",
+			    pool->alloc_log_sz);
+		return -ENOMEM;
 	}
 
-	if (hws_pool_resource_alloc(pool, new_buddy_size, idx) != 0) {
-		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %d index: %d\n",
-			    pool->type, new_buddy_size, idx);
+	if (hws_pool_resource_alloc(pool) != 0) {
+		mlx5hws_err(pool->ctx, "Failed to create resource type: %d size %zu\n",
+			    pool->type, pool->alloc_log_sz);
 		mlx5hws_buddy_cleanup(buddy);
-		return NULL;
+		kfree(buddy);
+		return -ENOMEM;
 	}
 
-	pool->db.buddy_manager->buddies[idx] = buddy;
+	pool->db.buddy = buddy;
 
-	return buddy;
+	return 0;
 }
 
-static int hws_pool_buddy_get_mem_chunk(struct mlx5hws_pool *pool,
-					int order,
-					u32 *buddy_idx,
-					int *seg)
+static int hws_pool_buddy_db_get_chunk(struct mlx5hws_pool *pool,
+				       struct mlx5hws_pool_chunk *chunk)
 {
-	struct mlx5hws_buddy_mem *buddy;
-	bool new_mem = false;
-	int ret = 0;
-	int i;
-
-	*seg = -1;
-
-	/* Find the next free place from the buddy array */
-	while (*seg == -1) {
-		for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
-			buddy = hws_pool_buddy_get_next_buddy(pool, i,
-							      order,
-							      &new_mem);
-			if (!buddy) {
-				ret = -ENOMEM;
-				goto out;
-			}
-
-			*seg = mlx5hws_buddy_alloc_mem(buddy, order);
-			if (*seg != -1)
-				goto found;
-
-			if (pool->flags & MLX5HWS_POOL_FLAGS_ONE_RESOURCE) {
-				mlx5hws_err(pool->ctx,
-					    "Fail to allocate seg for one resource pool\n");
-				ret = -ENOMEM;
-				goto out;
-			}
-
-			if (new_mem) {
-				/* We have new memory pool, should be place for us */
-				mlx5hws_err(pool->ctx,
-					    "No memory for order: %d with buddy no: %d\n",
-					    order, i);
-				ret = -ENOMEM;
-				goto out;
-			}
-		}
+	struct mlx5hws_buddy_mem *buddy = pool->db.buddy;
+
+	if (!buddy) {
+		mlx5hws_err(pool->ctx, "Bad buddy state\n");
+		return -EINVAL;
 	}
 
-found:
-	*buddy_idx = i;
-out:
-	return ret;
+	chunk->offset = mlx5hws_buddy_alloc_mem(buddy, chunk->order);
+	if (chunk->offset >= 0)
+		return 0;
+
+	return -ENOMEM;
 }
 
-static int hws_pool_buddy_db_get_chunk(struct mlx5hws_pool *pool,
-				       struct mlx5hws_pool_chunk *chunk)
+static void hws_pool_buddy_db_put_chunk(struct mlx5hws_pool *pool,
+					struct mlx5hws_pool_chunk *chunk)
 {
-	int ret = 0;
+	struct mlx5hws_buddy_mem *buddy;
 
-	/* Go over the buddies and find next free slot */
-	ret = hws_pool_buddy_get_mem_chunk(pool, chunk->order,
-					   &chunk->resource_idx,
-					   &chunk->offset);
-	if (ret)
-		mlx5hws_err(pool->ctx, "Failed to get free slot for chunk with order: %d\n",
-			    chunk->order);
+	buddy = pool->db.buddy;
+	if (!buddy) {
+		mlx5hws_err(pool->ctx, "Bad buddy state\n");
+		return;
+	}
 
-	return ret;
+	mlx5hws_buddy_free_mem(buddy, chunk->offset, chunk->order);
 }
 
 static void hws_pool_buddy_db_uninit(struct mlx5hws_pool *pool)
 {
 	struct mlx5hws_buddy_mem *buddy;
-	int i;
-
-	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
-		buddy = pool->db.buddy_manager->buddies[i];
-		if (buddy) {
-			mlx5hws_buddy_cleanup(buddy);
-			kfree(buddy);
-			pool->db.buddy_manager->buddies[i] = NULL;
-		}
-	}
 
-	kfree(pool->db.buddy_manager);
+	buddy = pool->db.buddy;
+	if (buddy) {
+		mlx5hws_buddy_cleanup(buddy);
+		kfree(buddy);
+		pool->db.buddy = NULL;
+	}
 }
 
-static int hws_pool_buddy_db_init(struct mlx5hws_pool *pool, u32 log_range)
+static int hws_pool_buddy_db_init(struct mlx5hws_pool *pool)
 {
-	pool->db.buddy_manager = kzalloc(sizeof(*pool->db.buddy_manager), GFP_KERNEL);
-	if (!pool->db.buddy_manager)
-		return -ENOMEM;
-
-	if (pool->flags & MLX5HWS_POOL_FLAGS_ALLOC_MEM_ON_CREATE) {
-		bool new_buddy;
+	int ret;
 
-		if (!hws_pool_buddy_get_next_buddy(pool, 0, log_range, &new_buddy)) {
-			mlx5hws_err(pool->ctx,
-				    "Failed allocating memory on create log_sz: %d\n", log_range);
-			kfree(pool->db.buddy_manager);
-			return -ENOMEM;
-		}
-	}
+	ret = hws_pool_buddy_init(pool);
+	if (ret)
+		return ret;
 
 	pool->p_db_uninit = &hws_pool_buddy_db_uninit;
 	pool->p_get_chunk = &hws_pool_buddy_db_get_chunk;
@@ -278,261 +191,105 @@ static int hws_pool_buddy_db_init(struct mlx5hws_pool *pool, u32 log_range)
 	return 0;
 }
 
-static int hws_pool_create_resource_on_index(struct mlx5hws_pool *pool,
-					     u32 alloc_size, int idx)
-{
-	int ret = hws_pool_resource_alloc(pool, alloc_size, idx);
-
-	if (ret) {
-		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %d index: %d\n",
-			    pool->type, alloc_size, idx);
-		return ret;
-	}
-
-	return 0;
-}
-
-static struct mlx5hws_pool_elements *
-hws_pool_element_create_new_elem(struct mlx5hws_pool *pool, u32 order, int idx)
+static unsigned long *hws_pool_create_and_init_bitmap(u32 log_range)
 {
-	struct mlx5hws_pool_elements *elem;
-	u32 alloc_size;
-
-	alloc_size = pool->alloc_log_sz;
+	unsigned long *bitmap;
 
-	elem = kzalloc(sizeof(*elem), GFP_KERNEL);
-	if (!elem)
+	bitmap = bitmap_zalloc(1 << log_range, GFP_KERNEL);
+	if (!bitmap)
 		return NULL;
 
-	/* Sharing the same resource, also means that all the elements are with size 1 */
-	if ((pool->flags & MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS) &&
-	    !(pool->flags & MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK)) {
-		 /* Currently all chunks in size 1 */
-		elem->bitmap = hws_pool_create_and_init_bitmap(alloc_size - order);
-		if (!elem->bitmap) {
-			mlx5hws_err(pool->ctx,
-				    "Failed to create bitmap type: %d: size %d index: %d\n",
-				    pool->type, alloc_size, idx);
-			goto free_elem;
-		}
-
-		elem->log_size = alloc_size - order;
-	}
-
-	if (hws_pool_create_resource_on_index(pool, alloc_size, idx)) {
-		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %d index: %d\n",
-			    pool->type, alloc_size, idx);
-		goto free_db;
-	}
-
-	pool->db.element_manager->elements[idx] = elem;
-
-	return elem;
+	bitmap_fill(bitmap, 1 << log_range);
 
-free_db:
-	bitmap_free(elem->bitmap);
-free_elem:
-	kfree(elem);
-	return NULL;
+	return bitmap;
 }
 
-static int hws_pool_element_find_seg(struct mlx5hws_pool_elements *elem, int *seg)
+static int hws_pool_bitmap_init(struct mlx5hws_pool *pool)
 {
-	unsigned int segment, size;
-
-	size = 1 << elem->log_size;
+	unsigned long *bitmap;
 
-	segment = find_first_bit(elem->bitmap, size);
-	if (segment >= size) {
-		elem->is_full = true;
+	bitmap = hws_pool_create_and_init_bitmap(pool->alloc_log_sz);
+	if (!bitmap) {
+		mlx5hws_err(pool->ctx, "Failed to create bitmap order: %zu\n",
+			    pool->alloc_log_sz);
 		return -ENOMEM;
 	}
 
-	bitmap_clear(elem->bitmap, segment, 1);
-	*seg = segment;
-	return 0;
-}
-
-static int
-hws_pool_onesize_element_get_mem_chunk(struct mlx5hws_pool *pool, u32 order,
-				       u32 *idx, int *seg)
-{
-	struct mlx5hws_pool_elements *elem;
-
-	elem = pool->db.element_manager->elements[0];
-	if (!elem)
-		elem = hws_pool_element_create_new_elem(pool, order, 0);
-	if (!elem)
-		goto err_no_elem;
-
-	if (hws_pool_element_find_seg(elem, seg) != 0) {
-		mlx5hws_err(pool->ctx, "No more resources (last request order: %d)\n", order);
+	if (hws_pool_resource_alloc(pool) != 0) {
+		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %zu\n",
+			    pool->type, pool->alloc_log_sz);
+		bitmap_free(bitmap);
 		return -ENOMEM;
 	}
 
-	*idx = 0;
-	elem->num_of_elements++;
-	return 0;
+	pool->db.bitmap = bitmap;
 
-err_no_elem:
-	mlx5hws_err(pool->ctx, "Failed to allocate element for order: %d\n", order);
-	return -ENOMEM;
-}
-
-static int
-hws_pool_general_element_get_mem_chunk(struct mlx5hws_pool *pool, u32 order,
-				       u32 *idx, int *seg)
-{
-	int ret, i;
-
-	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
-		if (!pool->resource[i]) {
-			ret = hws_pool_create_resource_on_index(pool, order, i);
-			if (ret)
-				goto err_no_res;
-			*idx = i;
-			*seg = 0; /* One memory slot in that element */
-			return 0;
-		}
-	}
-
-	mlx5hws_err(pool->ctx, "No more resources (last request order: %d)\n", order);
-	return -ENOMEM;
-
-err_no_res:
-	mlx5hws_err(pool->ctx, "Failed to allocate element for order: %d\n", order);
-	return -ENOMEM;
+	return 0;
 }
 
-static int hws_pool_general_element_db_get_chunk(struct mlx5hws_pool *pool,
-						 struct mlx5hws_pool_chunk *chunk)
+static int hws_pool_bitmap_db_get_chunk(struct mlx5hws_pool *pool,
+					struct mlx5hws_pool_chunk *chunk)
 {
-	int ret;
-
-	/* Go over all memory elements and find/allocate free slot */
-	ret = hws_pool_general_element_get_mem_chunk(pool, chunk->order,
-						     &chunk->resource_idx,
-						     &chunk->offset);
-	if (ret)
-		mlx5hws_err(pool->ctx, "Failed to get free slot for chunk with order: %d\n",
-			    chunk->order);
+	unsigned long *bitmap, size;
 
-	return ret;
-}
+	if (chunk->order != 0) {
+		mlx5hws_err(pool->ctx, "Pool only supports order 0 allocs\n");
+		return -EINVAL;
+	}
 
-static void hws_pool_general_element_db_put_chunk(struct mlx5hws_pool *pool,
-						  struct mlx5hws_pool_chunk *chunk)
-{
-	if (unlikely(!pool->resource[chunk->resource_idx]))
-		pr_warn("HWS: invalid resource with index %d\n", chunk->resource_idx);
+	bitmap = pool->db.bitmap;
+	if (!bitmap) {
+		mlx5hws_err(pool->ctx, "Bad bitmap state\n");
+		return -EINVAL;
+	}
 
-	if (pool->flags & MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE)
-		hws_pool_resource_free(pool, chunk->resource_idx);
-}
+	size = 1 << pool->alloc_log_sz;
 
-static void hws_pool_general_element_db_uninit(struct mlx5hws_pool *pool)
-{
-	(void)pool;
-}
+	chunk->offset = find_first_bit(bitmap, size);
+	if (chunk->offset >= size)
+		return -ENOMEM;
 
-/* This memory management works as the following:
- * - At start doesn't allocate no mem at all.
- * - When new request for chunk arrived:
- *	allocate resource and give it.
- * - When free that chunk:
- *	the resource is freed.
- */
-static int hws_pool_general_element_db_init(struct mlx5hws_pool *pool)
-{
-	pool->p_db_uninit = &hws_pool_general_element_db_uninit;
-	pool->p_get_chunk = &hws_pool_general_element_db_get_chunk;
-	pool->p_put_chunk = &hws_pool_general_element_db_put_chunk;
+	bitmap_clear(bitmap, chunk->offset, 1);
 
 	return 0;
 }
 
-static void hws_onesize_element_db_destroy_element(struct mlx5hws_pool *pool,
-						   struct mlx5hws_pool_elements *elem,
-						   struct mlx5hws_pool_chunk *chunk)
-{
-	if (unlikely(!pool->resource[chunk->resource_idx]))
-		pr_warn("HWS: invalid resource with index %d\n", chunk->resource_idx);
-
-	hws_pool_resource_free(pool, chunk->resource_idx);
-	kfree(elem);
-	pool->db.element_manager->elements[chunk->resource_idx] = NULL;
-}
-
-static void hws_onesize_element_db_put_chunk(struct mlx5hws_pool *pool,
-					     struct mlx5hws_pool_chunk *chunk)
+static void hws_pool_bitmap_db_put_chunk(struct mlx5hws_pool *pool,
+					 struct mlx5hws_pool_chunk *chunk)
 {
-	struct mlx5hws_pool_elements *elem;
+	unsigned long *bitmap;
 
-	if (unlikely(chunk->resource_idx))
-		pr_warn("HWS: invalid resource with index %d\n", chunk->resource_idx);
-
-	elem = pool->db.element_manager->elements[chunk->resource_idx];
-	if (!elem) {
-		mlx5hws_err(pool->ctx, "No such element (%d)\n", chunk->resource_idx);
+	bitmap = pool->db.bitmap;
+	if (!bitmap) {
+		mlx5hws_err(pool->ctx, "Bad bitmap state\n");
 		return;
 	}
 
-	bitmap_set(elem->bitmap, chunk->offset, 1);
-	elem->is_full = false;
-	elem->num_of_elements--;
-
-	if (pool->flags & MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE &&
-	    !elem->num_of_elements)
-		hws_onesize_element_db_destroy_element(pool, elem, chunk);
+	bitmap_set(bitmap, chunk->offset, 1);
 }
 
-static int hws_onesize_element_db_get_chunk(struct mlx5hws_pool *pool,
-					    struct mlx5hws_pool_chunk *chunk)
+static void hws_pool_bitmap_db_uninit(struct mlx5hws_pool *pool)
 {
-	int ret = 0;
+	unsigned long *bitmap;
 
-	/* Go over all memory elements and find/allocate free slot */
-	ret = hws_pool_onesize_element_get_mem_chunk(pool, chunk->order,
-						     &chunk->resource_idx,
-						     &chunk->offset);
-	if (ret)
-		mlx5hws_err(pool->ctx, "Failed to get free slot for chunk with order: %d\n",
-			    chunk->order);
-
-	return ret;
-}
-
-static void hws_onesize_element_db_uninit(struct mlx5hws_pool *pool)
-{
-	struct mlx5hws_pool_elements *elem;
-	int i;
-
-	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
-		elem = pool->db.element_manager->elements[i];
-		if (elem) {
-			bitmap_free(elem->bitmap);
-			kfree(elem);
-			pool->db.element_manager->elements[i] = NULL;
-		}
+	bitmap = pool->db.bitmap;
+	if (bitmap) {
+		bitmap_free(bitmap);
+		pool->db.bitmap = NULL;
 	}
-	kfree(pool->db.element_manager);
 }
 
-/* This memory management works as the following:
- * - At start doesn't allocate no mem at all.
- * - When new request for chunk arrived:
- *  aloocate the first and only slot of memory/resource
- *  when it ended return error.
- */
-static int hws_pool_onesize_element_db_init(struct mlx5hws_pool *pool)
+static int hws_pool_bitmap_db_init(struct mlx5hws_pool *pool)
 {
-	pool->db.element_manager = kzalloc(sizeof(*pool->db.element_manager), GFP_KERNEL);
-	if (!pool->db.element_manager)
-		return -ENOMEM;
+	int ret;
 
-	pool->p_db_uninit = &hws_onesize_element_db_uninit;
-	pool->p_get_chunk = &hws_onesize_element_db_get_chunk;
-	pool->p_put_chunk = &hws_onesize_element_db_put_chunk;
+	ret = hws_pool_bitmap_init(pool);
+	if (ret)
+		return ret;
+
+	pool->p_db_uninit = &hws_pool_bitmap_db_uninit;
+	pool->p_get_chunk = &hws_pool_bitmap_db_get_chunk;
+	pool->p_put_chunk = &hws_pool_bitmap_db_put_chunk;
 
 	return 0;
 }
@@ -542,15 +299,14 @@ static int hws_pool_db_init(struct mlx5hws_pool *pool,
 {
 	int ret;
 
-	if (db_type == MLX5HWS_POOL_DB_TYPE_GENERAL_SIZE)
-		ret = hws_pool_general_element_db_init(pool);
-	else if (db_type == MLX5HWS_POOL_DB_TYPE_ONE_SIZE_RESOURCE)
-		ret = hws_pool_onesize_element_db_init(pool);
+	if (db_type == MLX5HWS_POOL_DB_TYPE_BITMAP)
+		ret = hws_pool_bitmap_db_init(pool);
 	else
-		ret = hws_pool_buddy_db_init(pool, pool->alloc_log_sz);
+		ret = hws_pool_buddy_db_init(pool);
 
 	if (ret) {
-		mlx5hws_err(pool->ctx, "Failed to init general db : %d (ret: %d)\n", db_type, ret);
+		mlx5hws_err(pool->ctx, "Failed to init pool type: %d (ret: %d)\n",
+			    db_type, ret);
 		return ret;
 	}
 
@@ -569,6 +325,8 @@ int mlx5hws_pool_chunk_alloc(struct mlx5hws_pool *pool,
 
 	mutex_lock(&pool->lock);
 	ret = pool->p_get_chunk(pool, chunk);
+	if (ret == 0)
+		pool->available_elems -= 1 << chunk->order;
 	mutex_unlock(&pool->lock);
 
 	return ret;
@@ -579,6 +337,7 @@ void mlx5hws_pool_chunk_free(struct mlx5hws_pool *pool,
 {
 	mutex_lock(&pool->lock);
 	pool->p_put_chunk(pool, chunk);
+	pool->available_elems += 1 << chunk->order;
 	mutex_unlock(&pool->lock);
 }
 
@@ -599,17 +358,13 @@ mlx5hws_pool_create(struct mlx5hws_context *ctx, struct mlx5hws_pool_attr *pool_
 	pool->tbl_type = pool_attr->table_type;
 	pool->opt_type = pool_attr->opt_type;
 
-	/* Support general db */
-	if (pool->flags == (MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE |
-			    MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK))
-		res_db_type = MLX5HWS_POOL_DB_TYPE_GENERAL_SIZE;
-	else if (pool->flags == (MLX5HWS_POOL_FLAGS_ONE_RESOURCE |
-				 MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS))
-		res_db_type = MLX5HWS_POOL_DB_TYPE_ONE_SIZE_RESOURCE;
-	else
+	if (pool->flags & MLX5HWS_POOL_FLAG_BUDDY)
 		res_db_type = MLX5HWS_POOL_DB_TYPE_BUDDY;
+	else
+		res_db_type = MLX5HWS_POOL_DB_TYPE_BITMAP;
 
 	pool->alloc_log_sz = pool_attr->alloc_log_sz;
+	pool->available_elems = 1 << pool_attr->alloc_log_sz;
 
 	if (hws_pool_db_init(pool, res_db_type))
 		goto free_pool;
@@ -623,18 +378,17 @@ free_pool:
 	return NULL;
 }
 
-int mlx5hws_pool_destroy(struct mlx5hws_pool *pool)
+void mlx5hws_pool_destroy(struct mlx5hws_pool *pool)
 {
-	int i;
-
 	mutex_destroy(&pool->lock);
 
-	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++)
-		if (pool->resource[i])
-			hws_pool_resource_free(pool, i);
+	if (pool->available_elems != 1 << pool->alloc_log_sz)
+		mlx5hws_err(pool->ctx, "Attempting to destroy non-empty pool\n");
+
+	if (pool->resource)
+		hws_pool_resource_free(pool);
 
 	hws_pool_db_unint(pool);
 
 	kfree(pool);
-	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h
index 621298b352b2..33e33d5f1fb3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h
@@ -6,16 +6,12 @@
 
 #define MLX5HWS_POOL_STC_LOG_SZ 15
 
-#define MLX5HWS_POOL_RESOURCE_ARR_SZ 100
-
 enum mlx5hws_pool_type {
 	MLX5HWS_POOL_TYPE_STE,
 	MLX5HWS_POOL_TYPE_STC,
 };
 
 struct mlx5hws_pool_chunk {
-	u32 resource_idx;
-	/* Internal offset, relative to base index */
 	int offset;
 	int order;
 };
@@ -27,35 +23,17 @@ struct mlx5hws_pool_resource {
 };
 
 enum mlx5hws_pool_flags {
-	/* Only a one resource in that pool */
-	MLX5HWS_POOL_FLAGS_ONE_RESOURCE = 1 << 0,
-	MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE = 1 << 1,
-	/* No sharing resources between chunks */
-	MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK = 1 << 2,
-	/* All objects are in the same size */
-	MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS = 1 << 3,
-	/* Managed by buddy allocator */
-	MLX5HWS_POOL_FLAGS_BUDDY_MANAGED = 1 << 4,
-	/* Allocate pool_type memory on pool creation */
-	MLX5HWS_POOL_FLAGS_ALLOC_MEM_ON_CREATE = 1 << 5,
-
-	/* These values should be used by the caller */
-	MLX5HWS_POOL_FLAGS_FOR_STC_POOL =
-		MLX5HWS_POOL_FLAGS_ONE_RESOURCE |
-		MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS,
-	MLX5HWS_POOL_FLAGS_FOR_MATCHER_STE_POOL =
-		MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE |
-		MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK,
-	MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL =
-		MLX5HWS_POOL_FLAGS_ONE_RESOURCE |
-		MLX5HWS_POOL_FLAGS_BUDDY_MANAGED |
-		MLX5HWS_POOL_FLAGS_ALLOC_MEM_ON_CREATE,
+	/* Managed by a buddy allocator. If this is not set only allocations of
+	 * order 0 are supported.
+	 */
+	MLX5HWS_POOL_FLAG_BUDDY = BIT(0),
 };
 
 enum mlx5hws_pool_optimize {
 	MLX5HWS_POOL_OPTIMIZE_NONE = 0x0,
 	MLX5HWS_POOL_OPTIMIZE_ORIG = 0x1,
 	MLX5HWS_POOL_OPTIMIZE_MIRROR = 0x2,
+	MLX5HWS_POOL_OPTIMIZE_MAX = 0x3,
 };
 
 struct mlx5hws_pool_attr {
@@ -68,34 +46,17 @@ struct mlx5hws_pool_attr {
 };
 
 enum mlx5hws_db_type {
-	/* Uses for allocating chunk of big memory, each element has its own resource in the FW*/
-	MLX5HWS_POOL_DB_TYPE_GENERAL_SIZE,
-	/* One resource only, all the elements are with same one size */
-	MLX5HWS_POOL_DB_TYPE_ONE_SIZE_RESOURCE,
-	/* Many resources, the memory allocated with buddy mechanism */
+	/* Uses a bitmap, supports only allocations of order 0. */
+	MLX5HWS_POOL_DB_TYPE_BITMAP,
+	/* Entries are managed using a buddy mechanism. */
 	MLX5HWS_POOL_DB_TYPE_BUDDY,
 };
 
-struct mlx5hws_buddy_manager {
-	struct mlx5hws_buddy_mem *buddies[MLX5HWS_POOL_RESOURCE_ARR_SZ];
-};
-
-struct mlx5hws_pool_elements {
-	u32 num_of_elements;
-	unsigned long *bitmap;
-	u32 log_size;
-	bool is_full;
-};
-
-struct mlx5hws_element_manager {
-	struct mlx5hws_pool_elements *elements[MLX5HWS_POOL_RESOURCE_ARR_SZ];
-};
-
 struct mlx5hws_pool_db {
 	enum mlx5hws_db_type type;
 	union {
-		struct mlx5hws_element_manager *element_manager;
-		struct mlx5hws_buddy_manager *buddy_manager;
+		unsigned long *bitmap;
+		struct mlx5hws_buddy_mem *buddy;
 	};
 };
 
@@ -111,11 +72,11 @@ struct mlx5hws_pool {
 	enum mlx5hws_pool_flags flags;
 	struct mutex lock; /* protect the pool */
 	size_t alloc_log_sz;
+	size_t available_elems;
 	enum mlx5hws_table_type tbl_type;
 	enum mlx5hws_pool_optimize opt_type;
-	struct mlx5hws_pool_resource *resource[MLX5HWS_POOL_RESOURCE_ARR_SZ];
-	struct mlx5hws_pool_resource *mirror_resource[MLX5HWS_POOL_RESOURCE_ARR_SZ];
-	/* DB */
+	struct mlx5hws_pool_resource *resource;
+	struct mlx5hws_pool_resource *mirror_resource;
 	struct mlx5hws_pool_db db;
 	/* Functions */
 	mlx5hws_pool_unint_db p_db_uninit;
@@ -127,7 +88,7 @@ struct mlx5hws_pool *
 mlx5hws_pool_create(struct mlx5hws_context *ctx,
 		    struct mlx5hws_pool_attr *pool_attr);
 
-int mlx5hws_pool_destroy(struct mlx5hws_pool *pool);
+void mlx5hws_pool_destroy(struct mlx5hws_pool *pool);
 
 int mlx5hws_pool_chunk_alloc(struct mlx5hws_pool *pool,
 			     struct mlx5hws_pool_chunk *chunk);
@@ -135,17 +96,37 @@ int mlx5hws_pool_chunk_alloc(struct mlx5hws_pool *pool,
 void mlx5hws_pool_chunk_free(struct mlx5hws_pool *pool,
 			     struct mlx5hws_pool_chunk *chunk);
 
-static inline u32
-mlx5hws_pool_chunk_get_base_id(struct mlx5hws_pool *pool,
-			       struct mlx5hws_pool_chunk *chunk)
+static inline u32 mlx5hws_pool_get_base_id(struct mlx5hws_pool *pool)
 {
-	return pool->resource[chunk->resource_idx]->base_id;
+	return pool->resource->base_id;
 }
 
-static inline u32
-mlx5hws_pool_chunk_get_base_mirror_id(struct mlx5hws_pool *pool,
-				      struct mlx5hws_pool_chunk *chunk)
+static inline u32 mlx5hws_pool_get_base_mirror_id(struct mlx5hws_pool *pool)
 {
-	return pool->mirror_resource[chunk->resource_idx]->base_id;
+	return pool->mirror_resource->base_id;
+}
+
+static inline bool
+mlx5hws_pool_empty(struct mlx5hws_pool *pool)
+{
+	bool ret;
+
+	mutex_lock(&pool->lock);
+	ret = pool->available_elems == 0;
+	mutex_unlock(&pool->lock);
+
+	return ret;
+}
+
+static inline bool
+mlx5hws_pool_full(struct mlx5hws_pool *pool)
+{
+	bool ret;
+
+	mutex_lock(&pool->lock);
+	ret = pool->available_elems == (1 << pool->alloc_log_sz);
+	mutex_unlock(&pool->lock);
+
+	return ret;
 }
 #endif /* MLX5HWS_POOL_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h
index de92cecbeb92..271490a51b96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h
@@ -390,11 +390,6 @@ struct mlx5_ifc_definer_bits {
 	u8 match_mask[0x160];
 };
 
-struct mlx5_ifc_arg_bits {
-	u8 rsvd0[0x88];
-	u8 access_pd[0x18];
-};
-
 struct mlx5_ifc_header_modify_pattern_in_bits {
 	u8 modify_field_select[0x40];
 
@@ -428,11 +423,6 @@ struct mlx5_ifc_create_definer_in_bits {
 	struct mlx5_ifc_definer_bits definer;
 };
 
-struct mlx5_ifc_create_arg_in_bits {
-	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
-	struct mlx5_ifc_arg_bits arg;
-};
-
 struct mlx5_ifc_create_header_modify_pattern_in_bits {
 	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
 	struct mlx5_ifc_header_modify_pattern_in_bits pattern;
@@ -479,36 +469,4 @@ enum {
 	MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION_GOTO_TBL = 1,
 };
 
-struct mlx5_ifc_alloc_packet_reformat_out_bits {
-	u8 status[0x8];
-	u8 reserved_at_8[0x18];
-
-	u8 syndrome[0x20];
-
-	u8 packet_reformat_id[0x20];
-
-	u8 reserved_at_60[0x20];
-};
-
-struct mlx5_ifc_dealloc_packet_reformat_in_bits {
-	u8 opcode[0x10];
-	u8 reserved_at_10[0x10];
-
-	u8 reserved_at_20[0x10];
-	u8 op_mod[0x10];
-
-	u8 packet_reformat_id[0x20];
-
-	u8 reserved_at_60[0x20];
-};
-
-struct mlx5_ifc_dealloc_packet_reformat_out_bits {
-	u8 status[0x8];
-	u8 reserved_at_8[0x18];
-
-	u8 syndrome[0x20];
-
-	u8 reserved_at_40[0x40];
-};
-
 #endif /* MLX5_PRM_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c
index e20c67a04203..a94f094e72ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c
@@ -3,10 +3,8 @@
 
 #include "internal.h"
 
-static void hws_rule_skip(struct mlx5hws_matcher *matcher,
-			  struct mlx5hws_match_template *mt,
-			  u32 flow_source,
-			  bool *skip_rx, bool *skip_tx)
+void mlx5hws_rule_skip(struct mlx5hws_matcher *matcher, u32 flow_source,
+		       bool *skip_rx, bool *skip_tx)
 {
 	/* By default FDB rules are added to both RX and TX */
 	*skip_rx = false;
@@ -14,20 +12,21 @@ static void hws_rule_skip(struct mlx5hws_matcher *matcher,
 
 	if (flow_source == MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT) {
 		*skip_rx = true;
-	} else if (flow_source == MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK) {
+		return;
+	}
+
+	if (flow_source == MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK) {
 		*skip_tx = true;
-	} else {
-		/* If no flow source was set for current rule,
-		 * check for flow source in matcher attributes.
-		 */
-		if (matcher->attr.optimize_flow_src) {
-			*skip_tx =
-				matcher->attr.optimize_flow_src == MLX5HWS_MATCHER_FLOW_SRC_WIRE;
-			*skip_rx =
-				matcher->attr.optimize_flow_src == MLX5HWS_MATCHER_FLOW_SRC_VPORT;
-			return;
-		}
+		return;
 	}
+
+	/* If no flow source was set for current rule,
+	 * check for flow source in matcher attributes.
+	 */
+	*skip_tx = matcher->attr.optimize_flow_src ==
+			MLX5HWS_MATCHER_FLOW_SRC_WIRE;
+	*skip_rx = matcher->attr.optimize_flow_src ==
+			MLX5HWS_MATCHER_FLOW_SRC_VPORT;
 }
 
 static void
@@ -66,7 +65,8 @@ static void hws_rule_init_dep_wqe(struct mlx5hws_send_ring_dep_wqe *dep_wqe,
 				attr->rule_idx : 0;
 
 	if (tbl->type == MLX5HWS_TABLE_TYPE_FDB) {
-		hws_rule_skip(matcher, mt, attr->flow_source, &skip_rx, &skip_tx);
+		mlx5hws_rule_skip(matcher, attr->flow_source,
+				  &skip_rx, &skip_tx);
 
 		if (!skip_rx) {
 			dep_wqe->rtc_0 = matcher->match_ste.rtc_0_id;
@@ -129,27 +129,18 @@ static void hws_rule_gen_comp(struct mlx5hws_send_engine *queue,
 
 static void
 hws_rule_save_resize_info(struct mlx5hws_rule *rule,
-			  struct mlx5hws_send_ste_attr *ste_attr,
-			  bool is_update)
+			  struct mlx5hws_send_ste_attr *ste_attr)
 {
 	if (!mlx5hws_matcher_is_resizable(rule->matcher))
 		return;
 
-	if (likely(!is_update)) {
+	/* resize_info might already exist (if we're in update flow) */
+	if (likely(!rule->resize_info)) {
 		rule->resize_info = kzalloc(sizeof(*rule->resize_info), GFP_KERNEL);
 		if (unlikely(!rule->resize_info)) {
 			pr_warn("HWS: resize info isn't allocated for rule\n");
 			return;
 		}
-
-		rule->resize_info->max_stes =
-			rule->matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes;
-		rule->resize_info->action_ste_pool[0] = rule->matcher->action_ste[0].max_stes ?
-							rule->matcher->action_ste[0].pool :
-							NULL;
-		rule->resize_info->action_ste_pool[1] = rule->matcher->action_ste[1].max_stes ?
-							rule->matcher->action_ste[1].pool :
-							NULL;
 	}
 
 	memcpy(rule->resize_info->ctrl_seg, ste_attr->wqe_ctrl,
@@ -204,84 +195,30 @@ hws_rule_load_delete_info(struct mlx5hws_rule *rule,
 	}
 }
 
-static int hws_rule_alloc_action_ste_idx(struct mlx5hws_rule *rule,
-					 u8 action_ste_selector)
+static int mlx5hws_rule_alloc_action_ste(struct mlx5hws_rule *rule,
+					 u16 queue_id, bool skip_rx,
+					 bool skip_tx)
 {
 	struct mlx5hws_matcher *matcher = rule->matcher;
-	struct mlx5hws_matcher_action_ste *action_ste;
-	struct mlx5hws_pool_chunk ste = {0};
-	int ret;
-
-	action_ste = &matcher->action_ste[action_ste_selector];
-	ste.order = ilog2(roundup_pow_of_two(action_ste->max_stes));
-	ret = mlx5hws_pool_chunk_alloc(action_ste->pool, &ste);
-	if (unlikely(ret)) {
-		mlx5hws_err(matcher->tbl->ctx,
-			    "Failed to allocate STE for rule actions");
-		return ret;
-	}
-	rule->action_ste_idx = ste.offset;
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
 
-	return 0;
+	rule->action_ste.ste.order =
+		ilog2(roundup_pow_of_two(matcher->num_of_action_stes));
+	return mlx5hws_action_ste_chunk_alloc(&ctx->action_ste_pool[queue_id],
+					      skip_rx, skip_tx,
+					      &rule->action_ste);
 }
 
-static void hws_rule_free_action_ste_idx(struct mlx5hws_rule *rule,
-					 u8 action_ste_selector)
+void mlx5hws_rule_free_action_ste(struct mlx5hws_action_ste_chunk *action_ste)
 {
-	struct mlx5hws_matcher *matcher = rule->matcher;
-	struct mlx5hws_pool_chunk ste = {0};
-	struct mlx5hws_pool *pool;
-	u8 max_stes;
-
-	if (mlx5hws_matcher_is_resizable(matcher)) {
-		/* Free the original action pool if rule was resized */
-		max_stes = rule->resize_info->max_stes;
-		pool = rule->resize_info->action_ste_pool[action_ste_selector];
-	} else {
-		max_stes = matcher->action_ste[action_ste_selector].max_stes;
-		pool = matcher->action_ste[action_ste_selector].pool;
-	}
-
-	/* This release is safe only when the rule match part was deleted */
-	ste.order = ilog2(roundup_pow_of_two(max_stes));
-	ste.offset = rule->action_ste_idx;
-
-	mlx5hws_pool_chunk_free(pool, &ste);
-}
-
-static int hws_rule_alloc_action_ste(struct mlx5hws_rule *rule,
-				     struct mlx5hws_rule_attr *attr)
-{
-	int action_ste_idx;
-	int ret;
-
-	ret = hws_rule_alloc_action_ste_idx(rule, 0);
-	if (unlikely(ret))
-		return ret;
-
-	action_ste_idx = rule->action_ste_idx;
-
-	ret = hws_rule_alloc_action_ste_idx(rule, 1);
-	if (unlikely(ret)) {
-		hws_rule_free_action_ste_idx(rule, 0);
-		return ret;
-	}
-
-	/* Both pools have to return the same index */
-	if (unlikely(rule->action_ste_idx != action_ste_idx)) {
-		pr_warn("HWS: allocation of action STE failed - pool indexes mismatch\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
+	if (!action_ste->action_tbl)
+		return;
 
-void mlx5hws_rule_free_action_ste(struct mlx5hws_rule *rule)
-{
-	if (rule->action_ste_idx > -1) {
-		hws_rule_free_action_ste_idx(rule, 1);
-		hws_rule_free_action_ste_idx(rule, 0);
-	}
+	/* This release is safe only when the rule match STE was deleted
+	 * (when the rule is being deleted) or replaced with the new STE that
+	 * isn't pointing to old action STEs (when the rule is being updated).
+	 */
+	mlx5hws_action_ste_chunk_free(action_ste);
 }
 
 static void hws_rule_create_init(struct mlx5hws_rule *rule,
@@ -298,14 +235,17 @@ static void hws_rule_create_init(struct mlx5hws_rule *rule,
 		/* In update we use these rtc's */
 		rule->rtc_0 = 0;
 		rule->rtc_1 = 0;
-		rule->action_ste_selector = 0;
+
+		rule->status = MLX5HWS_RULE_STATUS_CREATING;
 	} else {
-		rule->action_ste_selector = !rule->action_ste_selector;
+		rule->status = MLX5HWS_RULE_STATUS_UPDATING;
+		/* Save the old action STE info so we can free it after writing
+		 * new action STEs and a corresponding match STE.
+		 */
+		rule->old_action_ste = rule->action_ste;
 	}
 
 	rule->pending_wqes = 0;
-	rule->action_ste_idx = -1;
-	rule->status = MLX5HWS_RULE_STATUS_CREATING;
 
 	/* Init default send STE attributes */
 	ste_attr->gta_opcode = MLX5HWS_WQE_GTA_OP_ACTIVATE;
@@ -315,8 +255,7 @@ static void hws_rule_create_init(struct mlx5hws_rule *rule,
 
 	/* Init default action apply */
 	apply->tbl_type = tbl->type;
-	apply->common_res = &ctx->common_res[tbl->type];
-	apply->jump_to_action_stc = matcher->action_ste[0].stc.offset;
+	apply->common_res = &ctx->common_res;
 	apply->require_dep = 0;
 }
 
@@ -332,8 +271,6 @@ static void hws_rule_move_init(struct mlx5hws_rule *rule,
 	rule->rtc_1 = 0;
 
 	rule->pending_wqes = 0;
-	rule->action_ste_idx = -1;
-	rule->action_ste_selector = 0;
 	rule->status = MLX5HWS_RULE_STATUS_CREATING;
 	rule->resize_info->state = MLX5HWS_RULE_RESIZE_STATE_WRITING;
 }
@@ -394,21 +331,24 @@ static int hws_rule_create_hws(struct mlx5hws_rule *rule,
 
 	if (action_stes) {
 		/* Allocate action STEs for rules that need more than match STE */
-		if (!is_update) {
-			ret = hws_rule_alloc_action_ste(rule, attr);
-			if (ret) {
-				mlx5hws_err(ctx, "Failed to allocate action memory %d", ret);
-				mlx5hws_send_abort_new_dep_wqe(queue);
-				return ret;
-			}
+		ret = mlx5hws_rule_alloc_action_ste(rule, attr->queue_id,
+						    !!ste_attr.rtc_0,
+						    !!ste_attr.rtc_1);
+		if (ret) {
+			mlx5hws_err(ctx, "Failed to allocate action memory %d", ret);
+			mlx5hws_send_abort_new_dep_wqe(queue);
+			return ret;
 		}
+		apply.jump_to_action_stc =
+			rule->action_ste.action_tbl->stc.offset;
 		/* Skip RX/TX based on the dep_wqe init */
 		ste_attr.rtc_0 = dep_wqe->rtc_0 ?
-				 matcher->action_ste[rule->action_ste_selector].rtc_0_id : 0;
+				 rule->action_ste.action_tbl->rtc_0_id : 0;
 		ste_attr.rtc_1 = dep_wqe->rtc_1 ?
-				 matcher->action_ste[rule->action_ste_selector].rtc_1_id : 0;
+				 rule->action_ste.action_tbl->rtc_1_id : 0;
 		/* Action STEs are written to a specific index last to first */
-		ste_attr.direct_index = rule->action_ste_idx + action_stes;
+		ste_attr.direct_index =
+			rule->action_ste.ste.offset + action_stes;
 		apply.next_direct_idx = ste_attr.direct_index;
 	} else {
 		apply.next_direct_idx = 0;
@@ -459,7 +399,7 @@ static int hws_rule_create_hws(struct mlx5hws_rule *rule,
 	if (!is_update)
 		hws_rule_save_delete_info(rule, &ste_attr);
 
-	hws_rule_save_resize_info(rule, &ste_attr, is_update);
+	hws_rule_save_resize_info(rule, &ste_attr);
 	mlx5hws_send_engine_inc_rule(queue);
 
 	if (!attr->burst)
@@ -480,7 +420,10 @@ static void hws_rule_destroy_failed_hws(struct mlx5hws_rule *rule,
 			  attr->user_data, MLX5HWS_RULE_STATUS_DELETED);
 
 	/* Rule failed now we can safely release action STEs */
-	mlx5hws_rule_free_action_ste(rule);
+	mlx5hws_rule_free_action_ste(&rule->action_ste);
+
+	/* Perhaps the rule failed updating - release old action STEs as well */
+	mlx5hws_rule_free_action_ste(&rule->old_action_ste);
 
 	/* Clear complex tag */
 	hws_rule_clear_delete_info(rule);
@@ -517,7 +460,8 @@ static int hws_rule_destroy_hws(struct mlx5hws_rule *rule,
 	}
 
 	/* Rule is not completed yet */
-	if (rule->status == MLX5HWS_RULE_STATUS_CREATING)
+	if (rule->status == MLX5HWS_RULE_STATUS_CREATING ||
+	    rule->status == MLX5HWS_RULE_STATUS_UPDATING)
 		return -EBUSY;
 
 	/* Rule failed and doesn't require cleanup */
@@ -534,7 +478,7 @@ static int hws_rule_destroy_hws(struct mlx5hws_rule *rule,
 		hws_rule_gen_comp(queue, rule, false,
 				  attr->user_data, MLX5HWS_RULE_STATUS_DELETED);
 
-		mlx5hws_rule_free_action_ste(rule);
+		mlx5hws_rule_free_action_ste(&rule->action_ste);
 		mlx5hws_rule_clear_resize_info(rule);
 		return 0;
 	}
@@ -711,6 +655,124 @@ int mlx5hws_rule_move_hws_add(struct mlx5hws_rule *rule,
 	return 0;
 }
 
+static u8 hws_rule_ethertype_to_matcher_ipv(u32 ethertype)
+{
+	switch (ethertype) {
+	case ETH_P_IP:
+		return MLX5HWS_MATCHER_IPV_4;
+	case ETH_P_IPV6:
+		return MLX5HWS_MATCHER_IPV_6;
+	default:
+		return MLX5HWS_MATCHER_IPV_UNSET;
+	}
+}
+
+static u8 hws_rule_ip_version_to_matcher_ipv(u32 ip_version)
+{
+	switch (ip_version) {
+	case 4:
+		return MLX5HWS_MATCHER_IPV_4;
+	case 6:
+		return MLX5HWS_MATCHER_IPV_6;
+	default:
+		return MLX5HWS_MATCHER_IPV_UNSET;
+	}
+}
+
+static int hws_rule_check_outer_ip_version(struct mlx5hws_matcher *matcher,
+					   u32 *match_param)
+{
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	u8 outer_ipv_ether = MLX5HWS_MATCHER_IPV_UNSET;
+	u8 outer_ipv_ip = MLX5HWS_MATCHER_IPV_UNSET;
+	u8 outer_ipv, ver;
+
+	if (matcher->matches_outer_ethertype) {
+		ver = MLX5_GET(fte_match_param, match_param,
+			       outer_headers.ethertype);
+		outer_ipv_ether = hws_rule_ethertype_to_matcher_ipv(ver);
+	}
+	if (matcher->matches_outer_ip_version) {
+		ver = MLX5_GET(fte_match_param, match_param,
+			       outer_headers.ip_version);
+		outer_ipv_ip = hws_rule_ip_version_to_matcher_ipv(ver);
+	}
+
+	if (outer_ipv_ether != MLX5HWS_MATCHER_IPV_UNSET &&
+	    outer_ipv_ip != MLX5HWS_MATCHER_IPV_UNSET &&
+	    outer_ipv_ether != outer_ipv_ip) {
+		mlx5hws_err(ctx, "Rule matches on inconsistent outer ethertype and ip version\n");
+		return -EINVAL;
+	}
+
+	outer_ipv = outer_ipv_ether != MLX5HWS_MATCHER_IPV_UNSET ?
+		    outer_ipv_ether : outer_ipv_ip;
+	if (outer_ipv != MLX5HWS_MATCHER_IPV_UNSET &&
+	    matcher->outer_ip_version != MLX5HWS_MATCHER_IPV_UNSET &&
+	    outer_ipv != matcher->outer_ip_version) {
+		mlx5hws_err(ctx, "Matcher and rule disagree on outer IP version\n");
+		return -EINVAL;
+	}
+	matcher->outer_ip_version = outer_ipv;
+
+	return 0;
+}
+
+static int hws_rule_check_inner_ip_version(struct mlx5hws_matcher *matcher,
+					   u32 *match_param)
+{
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	u8 inner_ipv_ether = MLX5HWS_MATCHER_IPV_UNSET;
+	u8 inner_ipv_ip = MLX5HWS_MATCHER_IPV_UNSET;
+	u8 inner_ipv, ver;
+
+	if (matcher->matches_inner_ethertype) {
+		ver = MLX5_GET(fte_match_param, match_param,
+			       inner_headers.ethertype);
+		inner_ipv_ether = hws_rule_ethertype_to_matcher_ipv(ver);
+	}
+	if (matcher->matches_inner_ip_version) {
+		ver = MLX5_GET(fte_match_param, match_param,
+			       inner_headers.ip_version);
+		inner_ipv_ip = hws_rule_ip_version_to_matcher_ipv(ver);
+	}
+
+	if (inner_ipv_ether != MLX5HWS_MATCHER_IPV_UNSET &&
+	    inner_ipv_ip != MLX5HWS_MATCHER_IPV_UNSET &&
+	    inner_ipv_ether != inner_ipv_ip) {
+		mlx5hws_err(ctx, "Rule matches on inconsistent inner ethertype and ip version\n");
+		return -EINVAL;
+	}
+
+	inner_ipv = inner_ipv_ether != MLX5HWS_MATCHER_IPV_UNSET ?
+		    inner_ipv_ether : inner_ipv_ip;
+	if (inner_ipv != MLX5HWS_MATCHER_IPV_UNSET &&
+	    matcher->inner_ip_version != MLX5HWS_MATCHER_IPV_UNSET &&
+	    inner_ipv != matcher->inner_ip_version) {
+		mlx5hws_err(ctx, "Matcher and rule disagree on inner IP version\n");
+		return -EINVAL;
+	}
+	matcher->inner_ip_version = inner_ipv;
+
+	return 0;
+}
+
+static int hws_rule_check_ip_version(struct mlx5hws_matcher *matcher,
+				     u32 *match_param)
+{
+	int ret;
+
+	ret = hws_rule_check_outer_ip_version(matcher, match_param);
+	if (unlikely(ret))
+		return ret;
+
+	ret = hws_rule_check_inner_ip_version(matcher, match_param);
+	if (unlikely(ret))
+		return ret;
+
+	return 0;
+}
+
 int mlx5hws_rule_create(struct mlx5hws_matcher *matcher,
 			u8 mt_idx,
 			u32 *match_param,
@@ -721,6 +783,10 @@ int mlx5hws_rule_create(struct mlx5hws_matcher *matcher,
 {
 	int ret;
 
+	ret = hws_rule_check_ip_version(matcher, match_param);
+	if (unlikely(ret))
+		return ret;
+
 	rule_handle->matcher = matcher;
 
 	ret = hws_rule_enqueue_precheck_create(rule_handle, attr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h
index 495cdd17e9f3..d0f082b8dbf5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h
@@ -15,6 +15,8 @@ enum mlx5hws_rule_status {
 	MLX5HWS_RULE_STATUS_UNKNOWN,
 	MLX5HWS_RULE_STATUS_CREATING,
 	MLX5HWS_RULE_STATUS_CREATED,
+	MLX5HWS_RULE_STATUS_UPDATING,
+	MLX5HWS_RULE_STATUS_UPDATED,
 	MLX5HWS_RULE_STATUS_DELETING,
 	MLX5HWS_RULE_STATUS_DELETED,
 	MLX5HWS_RULE_STATUS_FAILING,
@@ -42,12 +44,10 @@ struct mlx5hws_rule_match_tag {
 };
 
 struct mlx5hws_rule_resize_info {
-	struct mlx5hws_pool *action_ste_pool[2];
 	u32 rtc_0;
 	u32 rtc_1;
 	u32 rule_idx;
 	u8 state;
-	u8 max_stes;
 	u8 ctrl_seg[MLX5HWS_WQE_SZ_GTA_CTRL]; /* Ctrl segment of STE: 48 bytes */
 	u8 data_seg[MLX5HWS_WQE_SZ_GTA_DATA]; /* Data segment of STE: 64 bytes */
 };
@@ -58,18 +58,21 @@ struct mlx5hws_rule {
 		struct mlx5hws_rule_match_tag tag;
 		struct mlx5hws_rule_resize_info *resize_info;
 	};
+	struct mlx5hws_action_ste_chunk action_ste;
+	struct mlx5hws_action_ste_chunk old_action_ste;
 	u32 rtc_0; /* The RTC into which the STE was inserted */
 	u32 rtc_1; /* The RTC into which the STE was inserted */
-	int action_ste_idx; /* STE array index */
 	u8 status; /* enum mlx5hws_rule_status */
-	u8 action_ste_selector; /* For rule update - which action STE is in use */
 	u8 pending_wqes;
 	bool skip_delete; /* For complex rules - another rule with same tag
 			   * still exists, so don't actually delete this rule.
 			   */
 };
 
-void mlx5hws_rule_free_action_ste(struct mlx5hws_rule *rule);
+void mlx5hws_rule_skip(struct mlx5hws_matcher *matcher, u32 flow_source,
+		       bool *skip_rx, bool *skip_tx);
+
+void mlx5hws_rule_free_action_ste(struct mlx5hws_action_ste_chunk *action_ste);
 
 int mlx5hws_rule_move_hws_remove(struct mlx5hws_rule *rule,
 				 void *queue, void *user_data);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
index b68b0c368771..7510c46e58a5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
@@ -344,18 +344,133 @@ hws_send_engine_update_rule_resize(struct mlx5hws_send_engine *queue,
 	}
 }
 
+static void hws_send_engine_dump_error_cqe(struct mlx5hws_send_engine *queue,
+					   struct mlx5hws_send_ring_priv *priv,
+					   struct mlx5_cqe64 *cqe)
+{
+	u8 wqe_opcode = cqe ? be32_to_cpu(cqe->sop_drop_qpn) >> 24 : 0;
+	struct mlx5hws_context *ctx = priv->rule->matcher->tbl->ctx;
+	u32 opcode = cqe ? get_cqe_opcode(cqe) : 0;
+	struct mlx5hws_rule *rule = priv->rule;
+
+	/* If something bad happens and lots of rules are failing, we don't
+	 * want to pollute dmesg. Print only the first bad cqe per engine,
+	 * the one that started the avalanche.
+	 */
+	if (queue->error_cqe_printed)
+		return;
+
+	queue->error_cqe_printed = true;
+
+	if (mlx5hws_rule_move_in_progress(rule))
+		mlx5hws_err(ctx,
+			    "--- rule 0x%08llx: error completion moving rule: phase %s, wqes left %d\n",
+			    HWS_PTR_TO_ID(rule),
+			    rule->resize_info->state ==
+			    MLX5HWS_RULE_RESIZE_STATE_WRITING ? "WRITING" :
+			    rule->resize_info->state ==
+			    MLX5HWS_RULE_RESIZE_STATE_DELETING ? "DELETING" :
+			    "UNKNOWN",
+			    rule->pending_wqes);
+	else
+		mlx5hws_err(ctx,
+			    "--- rule 0x%08llx: error completion %s (%d), wqes left %d\n",
+			    HWS_PTR_TO_ID(rule),
+			    rule->status ==
+			    MLX5HWS_RULE_STATUS_CREATING ? "CREATING" :
+			    rule->status ==
+			    MLX5HWS_RULE_STATUS_DELETING ? "DELETING" :
+			    rule->status ==
+			    MLX5HWS_RULE_STATUS_FAILING ? "FAILING" :
+			    rule->status ==
+			    MLX5HWS_RULE_STATUS_UPDATING ? "UPDATING" : "NA",
+			    rule->status,
+			    rule->pending_wqes);
+
+	mlx5hws_err(ctx, "    rule 0x%08llx: matcher 0x%llx %s\n",
+		    HWS_PTR_TO_ID(rule),
+		    HWS_PTR_TO_ID(rule->matcher),
+		    (rule->matcher->flags & MLX5HWS_MATCHER_FLAGS_ISOLATED) ?
+		    "(isolated)" : "");
+
+	if (!cqe) {
+		mlx5hws_err(ctx, "    rule 0x%08llx: no CQE\n",
+			    HWS_PTR_TO_ID(rule));
+		return;
+	}
+
+	mlx5hws_err(ctx, "    rule 0x%08llx: cqe->opcode      = %d %s\n",
+		    HWS_PTR_TO_ID(rule), opcode,
+		    opcode == MLX5_CQE_REQ ? "(MLX5_CQE_REQ)" :
+		    opcode == MLX5_CQE_REQ_ERR ? "(MLX5_CQE_REQ_ERR)" : " ");
+
+	if (opcode == MLX5_CQE_REQ_ERR) {
+		struct mlx5_err_cqe *err_cqe = (struct mlx5_err_cqe *)cqe;
+
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- hw_error_syndrome = 0x%x\n",
+			    HWS_PTR_TO_ID(rule),
+			    err_cqe->rsvd1[16]);
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- hw_syndrome_type = 0x%x\n",
+			    HWS_PTR_TO_ID(rule),
+			    err_cqe->rsvd1[17] >> 4);
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- vendor_err_synd = 0x%x\n",
+			    HWS_PTR_TO_ID(rule),
+			    err_cqe->vendor_err_synd);
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- syndrome = 0x%x\n",
+			    HWS_PTR_TO_ID(rule),
+			    err_cqe->syndrome);
+	}
+
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx: cqe->byte_cnt      = 0x%08x\n",
+		    HWS_PTR_TO_ID(rule), be32_to_cpu(cqe->byte_cnt));
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx:  |-- UPDATE STATUS = %s\n",
+		    HWS_PTR_TO_ID(rule),
+		    (be32_to_cpu(cqe->byte_cnt) & 0x80000000) ?
+		    "FAILURE" : "SUCCESS");
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx:  |------- SYNDROME = %s\n",
+		    HWS_PTR_TO_ID(rule),
+		    ((be32_to_cpu(cqe->byte_cnt) & 0x00000003) == 1) ?
+		    "SET_FLOW_FAIL" :
+		    ((be32_to_cpu(cqe->byte_cnt) & 0x00000003) == 2) ?
+		    "DISABLE_FLOW_FAIL" : "UNKNOWN");
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx: cqe->sop_drop_qpn  = 0x%08x\n",
+		    HWS_PTR_TO_ID(rule), be32_to_cpu(cqe->sop_drop_qpn));
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx:  |-send wqe opcode = 0x%02x %s\n",
+		    HWS_PTR_TO_ID(rule), wqe_opcode,
+		    wqe_opcode == MLX5HWS_WQE_OPCODE_TBL_ACCESS ?
+		    "(MLX5HWS_WQE_OPCODE_TBL_ACCESS)" : "(UNKNOWN)");
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx:  |------------ qpn = 0x%06x\n",
+		    HWS_PTR_TO_ID(rule),
+		    be32_to_cpu(cqe->sop_drop_qpn) & 0xffffff);
+}
+
 static void hws_send_engine_update_rule(struct mlx5hws_send_engine *queue,
 					struct mlx5hws_send_ring_priv *priv,
 					u16 wqe_cnt,
-					enum mlx5hws_flow_op_status *status)
+					enum mlx5hws_flow_op_status *status,
+					struct mlx5_cqe64 *cqe)
 {
 	priv->rule->pending_wqes--;
 
-	if (*status == MLX5HWS_FLOW_OP_ERROR) {
+	if (unlikely(*status == MLX5HWS_FLOW_OP_ERROR)) {
 		if (priv->retry_id) {
+			/* If there is a retry_id, then it's not an error yet,
+			 * retry to insert this rule in the collision RTC.
+			 */
 			hws_send_engine_retry_post_send(queue, priv, wqe_cnt);
 			return;
 		}
+		hws_send_engine_dump_error_cqe(queue, priv, cqe);
 		/* Some part of the rule failed */
 		priv->rule->status = MLX5HWS_RULE_STATUS_FAILING;
 		*priv->used_id = 0;
@@ -377,17 +492,25 @@ static void hws_send_engine_update_rule(struct mlx5hws_send_engine *queue,
 
 			*status = MLX5HWS_FLOW_OP_ERROR;
 		} else {
-			/* Increase the status, this only works on good flow as the enum
-			 * is arrange it away creating -> created -> deleting -> deleted
+			/* Increase the status, this only works on good flow as
+			 * the enum is arranged this way:
+			 *  - creating -> created
+			 *  - updating -> updated
+			 *  - deleting -> deleted
 			 */
 			priv->rule->status++;
 			*status = MLX5HWS_FLOW_OP_SUCCESS;
-			/* Rule was deleted now we can safely release action STEs
-			 * and clear resize info
-			 */
 			if (priv->rule->status == MLX5HWS_RULE_STATUS_DELETED) {
-				mlx5hws_rule_free_action_ste(priv->rule);
+				/* Rule was deleted, now we can safely release
+				 * action STEs and clear resize info
+				 */
+				mlx5hws_rule_free_action_ste(&priv->rule->action_ste);
 				mlx5hws_rule_clear_resize_info(priv->rule);
+			} else if (priv->rule->status == MLX5HWS_RULE_STATUS_UPDATED) {
+				/* Rule was updated, free the old action STEs */
+				mlx5hws_rule_free_action_ste(&priv->rule->old_action_ste);
+				/* Update completed - move the rule back to "created" */
+				priv->rule->status = MLX5HWS_RULE_STATUS_CREATED;
 			}
 		}
 	}
@@ -412,7 +535,8 @@ static void hws_send_engine_update(struct mlx5hws_send_engine *queue,
 
 	if (priv->user_data) {
 		if (priv->rule) {
-			hws_send_engine_update_rule(queue, priv, wqe_cnt, &status);
+			hws_send_engine_update_rule(queue, priv, wqe_cnt,
+						    &status, cqe);
 			/* Completion is provided on the last rule WQE */
 			if (priv->rule->pending_wqes)
 				return;
@@ -566,7 +690,7 @@ static int hws_send_ring_alloc_sq(struct mlx5_core_dev *mdev,
 	size_t buf_sz;
 	int err;
 
-	sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map;
+	sq->uar_map = mdev->priv.bfreg.map;
 	sq->mdev = mdev;
 
 	param.db_numa_node = numa_node;
@@ -633,13 +757,14 @@ static int hws_send_ring_create_sq(struct mlx5_core_dev *mdev, u32 pdn,
 
 	MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST);
 	MLX5_SET(sqc, sqc, flush_in_error_en, 1);
+	MLX5_SET(sqc, sqc, non_wire, 1);
 
 	ts_format = mlx5_is_real_time_sq(mdev) ? MLX5_TIMESTAMP_FORMAT_REAL_TIME :
 						 MLX5_TIMESTAMP_FORMAT_FREE_RUNNING;
 	MLX5_SET(sqc, sqc, ts_format, ts_format);
 
 	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
-	MLX5_SET(wq, wq, uar_page, mdev->mlx5e_res.hw_objs.bfreg.index);
+	MLX5_SET(wq, wq, uar_page, mdev->priv.bfreg.index);
 	MLX5_SET(wq, wq, log_wq_pg_sz, sq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(wq, wq, dbr_addr, sq->wq_ctrl.db.dma);
 
@@ -748,12 +873,6 @@ err_free_sqc:
 	return err;
 }
 
-static void hws_cq_complete(struct mlx5_core_cq *mcq,
-			    struct mlx5_eqe *eqe)
-{
-	pr_err("CQ completion CQ: #%u\n", mcq->cqn);
-}
-
 static int hws_send_ring_alloc_cq(struct mlx5_core_dev *mdev,
 				  int numa_node,
 				  struct mlx5hws_send_engine *queue,
@@ -776,7 +895,6 @@ static int hws_send_ring_alloc_cq(struct mlx5_core_dev *mdev,
 	mcq->cqe_sz = 64;
 	mcq->set_ci_db = cq->wq_ctrl.db.db;
 	mcq->arm_db = cq->wq_ctrl.db.db + 1;
-	mcq->comp = hws_cq_complete;
 
 	for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) {
 		cqe = mlx5_cqwq_get_wqe(&cq->wq, i);
@@ -815,7 +933,7 @@ static int hws_send_ring_create_cq(struct mlx5_core_dev *mdev,
 				  (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
 
 	MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn);
-	MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index);
+	MLX5_SET(cqc, cqc, uar_page, mdev->priv.bfreg.up->index);
 	MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma);
 
@@ -838,8 +956,7 @@ static int hws_send_ring_open_cq(struct mlx5_core_dev *mdev,
 	if (!cqc_data)
 		return -ENOMEM;
 
-	MLX5_SET(cqc, cqc_data, uar_page, mdev->priv.uar->index);
-	MLX5_SET(cqc, cqc_data, cqe_sz, queue->num_entries);
+	MLX5_SET(cqc, cqc_data, uar_page, mdev->priv.bfreg.up->index);
 	MLX5_SET(cqc, cqc_data, log_cq_size, ilog2(queue->num_entries));
 
 	err = hws_send_ring_alloc_cq(mdev, numa_node, queue, cqc_data, cq);
@@ -898,6 +1015,9 @@ close_cq:
 
 static void mlx5hws_send_queue_close(struct mlx5hws_send_engine *queue)
 {
+	if (!queue->num_entries)
+		return; /* this queue wasn't initialized */
+
 	hws_send_ring_close(queue);
 	kfree(queue->completed.entries);
 }
@@ -1005,7 +1125,7 @@ int mlx5hws_send_queues_open(struct mlx5hws_context *ctx,
 			     u16 queue_size)
 {
 	int err = 0;
-	u32 i;
+	int i = 0;
 
 	/* Open one extra queue for control path */
 	ctx->queues = queues + 1;
@@ -1021,7 +1141,13 @@ int mlx5hws_send_queues_open(struct mlx5hws_context *ctx,
 		goto free_bwc_locks;
 	}
 
-	for (i = 0; i < ctx->queues; i++) {
+	/* If native API isn't supported, skip the unused native queues:
+	 * initialize BWC queues and control queue only.
+	 */
+	if (!mlx5hws_context_native_supported(ctx))
+		i = mlx5hws_bwc_get_queue_id(ctx, 0);
+
+	for (; i < ctx->queues; i++) {
 		err = mlx5hws_send_queue_open(ctx, &ctx->send_queue[i], queue_size);
 		if (err)
 			goto close_send_queues;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h
index f833092235c1..3fb8e99309b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h
@@ -140,6 +140,7 @@ struct mlx5hws_send_engine {
 	u16 used_entries;
 	u16 num_entries;
 	bool err;
+	bool error_cqe_printed;
 	struct mutex lock; /* Protects the send engine */
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
index 9576e02d00c3..6113383ae47b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
@@ -9,6 +9,7 @@ u32 mlx5hws_table_get_id(struct mlx5hws_table *tbl)
 }
 
 static void hws_table_init_next_ft_attr(struct mlx5hws_table *tbl,
+					u16 uid,
 					struct mlx5hws_cmd_ft_create_attr *ft_attr)
 {
 	ft_attr->type = tbl->fw_ft_type;
@@ -16,7 +17,9 @@ static void hws_table_init_next_ft_attr(struct mlx5hws_table *tbl,
 		ft_attr->level = tbl->ctx->caps->fdb_ft.max_level - 1;
 	else
 		ft_attr->level = tbl->ctx->caps->nic_ft.max_level - 1;
+
 	ft_attr->rtc_valid = true;
+	ft_attr->uid = uid;
 }
 
 static void hws_table_set_cap_attr(struct mlx5hws_table *tbl,
@@ -37,6 +40,7 @@ static void hws_table_set_cap_attr(struct mlx5hws_table *tbl,
 }
 
 static int hws_table_up_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
+__must_hold(&tbl->ctx->ctrl_lock)
 {
 	struct mlx5hws_cmd_ft_create_attr ft_attr = {0};
 	struct mlx5hws_cmd_set_fte_attr fte_attr = {0};
@@ -48,8 +52,8 @@ static int hws_table_up_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
 	if (tbl->type != MLX5HWS_TABLE_TYPE_FDB)
 		return 0;
 
-	if (ctx->common_res[tbl_type].default_miss) {
-		ctx->common_res[tbl_type].default_miss->refcount++;
+	if (ctx->common_res.default_miss) {
+		ctx->common_res.default_miss->refcount++;
 		return 0;
 	}
 
@@ -70,29 +74,28 @@ static int hws_table_up_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
 		return -EINVAL;
 	}
 
-	/* ctx->ctrl_lock must be held here */
-	ctx->common_res[tbl_type].default_miss = default_miss;
-	ctx->common_res[tbl_type].default_miss->refcount++;
+	ctx->common_res.default_miss = default_miss;
+	ctx->common_res.default_miss->refcount++;
 
 	return 0;
 }
 
 /* Called under ctx->ctrl_lock */
 static void hws_table_down_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
+__must_hold(&tbl->ctx->ctrl_lock)
 {
 	struct mlx5hws_cmd_forward_tbl *default_miss;
 	struct mlx5hws_context *ctx = tbl->ctx;
-	u8 tbl_type = tbl->type;
 
 	if (tbl->type != MLX5HWS_TABLE_TYPE_FDB)
 		return;
 
-	default_miss = ctx->common_res[tbl_type].default_miss;
+	default_miss = ctx->common_res.default_miss;
 	if (--default_miss->refcount)
 		return;
 
 	mlx5hws_cmd_forward_tbl_destroy(ctx->mdev, default_miss);
-	ctx->common_res[tbl_type].default_miss = NULL;
+	ctx->common_res.default_miss = NULL;
 }
 
 static int hws_table_connect_to_default_miss_tbl(struct mlx5hws_table *tbl, u32 ft_id)
@@ -119,12 +122,12 @@ static int hws_table_connect_to_default_miss_tbl(struct mlx5hws_table *tbl, u32
 
 int mlx5hws_table_create_default_ft(struct mlx5_core_dev *mdev,
 				    struct mlx5hws_table *tbl,
-				    u32 *ft_id)
+				    u16 uid, u32 *ft_id)
 {
 	struct mlx5hws_cmd_ft_create_attr ft_attr = {0};
 	int ret;
 
-	hws_table_init_next_ft_attr(tbl, &ft_attr);
+	hws_table_init_next_ft_attr(tbl, uid, &ft_attr);
 	hws_table_set_cap_attr(tbl, &ft_attr);
 
 	ret = mlx5hws_cmd_flow_table_create(mdev, &ft_attr, ft_id);
@@ -189,7 +192,10 @@ static int hws_table_init(struct mlx5hws_table *tbl)
 	}
 
 	mutex_lock(&ctx->ctrl_lock);
-	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, &tbl->ft_id);
+	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev,
+					      tbl,
+					      tbl->uid,
+					      &tbl->ft_id);
 	if (ret) {
 		mlx5hws_err(tbl->ctx, "Failed to create flow table object\n");
 		mutex_unlock(&ctx->ctrl_lock);
@@ -239,6 +245,7 @@ struct mlx5hws_table *mlx5hws_table_create(struct mlx5hws_context *ctx,
 	tbl->ctx = ctx;
 	tbl->type = attr->type;
 	tbl->level = attr->level;
+	tbl->uid = attr->uid;
 
 	ret = hws_table_init(tbl);
 	if (ret) {
@@ -342,10 +349,10 @@ int mlx5hws_table_ft_set_next_rtc(struct mlx5hws_context *ctx,
 	return mlx5hws_cmd_flow_table_modify(ctx->mdev, &ft_attr, ft_id);
 }
 
-static int hws_table_ft_set_next_ft(struct mlx5hws_context *ctx,
-				    u32 ft_id,
-				    u32 fw_ft_type,
-				    u32 next_ft_id)
+int mlx5hws_table_ft_set_next_ft(struct mlx5hws_context *ctx,
+				 u32 ft_id,
+				 u32 fw_ft_type,
+				 u32 next_ft_id)
 {
 	struct mlx5hws_cmd_ft_modify_attr ft_attr = {0};
 
@@ -389,10 +396,10 @@ int mlx5hws_table_connect_to_miss_table(struct mlx5hws_table *src_tbl,
 	if (dst_tbl) {
 		if (list_empty(&dst_tbl->matchers_list)) {
 			/* Connect src_tbl last_ft to dst_tbl start anchor */
-			ret = hws_table_ft_set_next_ft(src_tbl->ctx,
-						       last_ft_id,
-						       src_tbl->fw_ft_type,
-						       dst_tbl->ft_id);
+			ret = mlx5hws_table_ft_set_next_ft(src_tbl->ctx,
+							   last_ft_id,
+							   src_tbl->fw_ft_type,
+							   dst_tbl->ft_id);
 			if (ret)
 				return ret;
 
@@ -478,15 +485,9 @@ int mlx5hws_table_set_default_miss(struct mlx5hws_table *tbl,
 	if (old_miss_tbl)
 		list_del_init(&tbl->default_miss.next);
 
-	old_miss_tbl = tbl->default_miss.miss_tbl;
-	if (old_miss_tbl)
-		list_del_init(&old_miss_tbl->default_miss.head);
-
 	if (miss_tbl)
 		list_add(&tbl->default_miss.next, &miss_tbl->default_miss.head);
 
-	mutex_unlock(&ctx->ctrl_lock);
-	return 0;
 out:
 	mutex_unlock(&ctx->ctrl_lock);
 	return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h
index dd50420eec9e..1246f9bd8422 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h
@@ -18,6 +18,7 @@ struct mlx5hws_table {
 	enum mlx5hws_table_type type;
 	u32 fw_ft_type;
 	u32 level;
+	u16 uid;
 	struct list_head matchers_list;
 	struct list_head tbl_list_node;
 	struct mlx5hws_default_miss default_miss;
@@ -47,7 +48,7 @@ u32 mlx5hws_table_get_res_fw_ft_type(enum mlx5hws_table_type tbl_type,
 
 int mlx5hws_table_create_default_ft(struct mlx5_core_dev *mdev,
 				    struct mlx5hws_table *tbl,
-				    u32 *ft_id);
+				    u16 uid, u32 *ft_id);
 
 void mlx5hws_table_destroy_default_ft(struct mlx5hws_table *tbl,
 				      u32 ft_id);
@@ -65,4 +66,9 @@ int mlx5hws_table_ft_set_next_rtc(struct mlx5hws_context *ctx,
 				  u32 rtc_0_id,
 				  u32 rtc_1_id);
 
+int mlx5hws_table_ft_set_next_ft(struct mlx5hws_context *ctx,
+				 u32 ft_id,
+				 u32 fw_ft_type,
+				 u32 next_ft_id);
+
 #endif /* MLX5HWS_TABLE_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_cmd.c
index baefb9a3fa05..1ebb2b15c080 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_cmd.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019 Mellanox Technologies. */
 
 #include "dr_types.h"
+#include "eswitch.h"
 
 int mlx5dr_cmd_query_esw_vport_context(struct mlx5_core_dev *mdev,
 				       bool other_vport,
@@ -34,34 +35,21 @@ int mlx5dr_cmd_query_esw_vport_context(struct mlx5_core_dev *mdev,
 int mlx5dr_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_vport,
 			  u16 vport_number, u16 *gvmi)
 {
-	bool ec_vf_func = other_vport ? mlx5_core_is_ec_vf_vport(mdev, vport_number) : false;
-	u32 in[MLX5_ST_SZ_DW(query_hca_cap_in)] = {};
-	int out_size;
-	void *out;
 	int err;
 
-	out_size = MLX5_ST_SZ_BYTES(query_hca_cap_out);
-	out = kzalloc(out_size, GFP_KERNEL);
-	if (!out)
-		return -ENOMEM;
-
-	MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
-	MLX5_SET(query_hca_cap_in, in, other_function, other_vport);
-	MLX5_SET(query_hca_cap_in, in, function_id, mlx5_vport_to_func_id(mdev, vport_number, ec_vf_func));
-	MLX5_SET(query_hca_cap_in, in, ec_vf_function, ec_vf_func);
-	MLX5_SET(query_hca_cap_in, in, op_mod,
-		 MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1 |
-		 HCA_CAP_OPMOD_GET_CUR);
+	if (!other_vport) {
+		/* self vhca_id */
+		*gvmi = MLX5_CAP_GEN(mdev, vhca_id);
+		return 0;
+	}
 
-	err = mlx5_cmd_exec_inout(mdev, query_hca_cap, in, out);
+	err = mlx5_vport_get_vhca_id(mdev, vport_number, gvmi);
 	if (err) {
-		kfree(out);
+		mlx5_core_err(mdev, "Failed to get vport vhca id for vport %d\n",
+			      vport_number);
 		return err;
 	}
 
-	*gvmi = MLX5_GET(query_hca_cap_out, out, capability.cmd_hca_cap.vhca_id);
-
-	kfree(out);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
index 49f22cad92bf..e8c67ed9f748 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
@@ -8,7 +8,7 @@
 #define DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, dmn_type)	\
 	((dmn)->info.caps.dmn_type##_sw_owner ||	\
 	 ((dmn)->info.caps.dmn_type##_sw_owner_v2 &&	\
-	  (dmn)->info.caps.sw_format_ver <= MLX5_STEERING_FORMAT_CONNECTX_7))
+	  (dmn)->info.caps.sw_format_ver <= MLX5_STEERING_FORMAT_CONNECTX_8))
 
 bool mlx5dr_domain_is_support_ptrn_arg(struct mlx5dr_domain *dmn)
 {
@@ -410,7 +410,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev,
 	switch (dmn->type) {
 	case MLX5DR_DOMAIN_TYPE_NIC_RX:
 		if (!DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, rx))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		dmn->info.supp_sw_steering = true;
 		dmn->info.rx.type = DR_DOMAIN_NIC_TYPE_RX;
@@ -419,7 +419,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev,
 		break;
 	case MLX5DR_DOMAIN_TYPE_NIC_TX:
 		if (!DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, tx))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		dmn->info.supp_sw_steering = true;
 		dmn->info.tx.type = DR_DOMAIN_NIC_TYPE_TX;
@@ -428,10 +428,10 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev,
 		break;
 	case MLX5DR_DOMAIN_TYPE_FDB:
 		if (!dmn->info.caps.eswitch_manager)
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		if (!DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, fdb))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		dmn->info.rx.type = DR_DOMAIN_NIC_TYPE_RX;
 		dmn->info.tx.type = DR_DOMAIN_NIC_TYPE_TX;
@@ -516,30 +516,6 @@ def_xa_destroy:
 	return NULL;
 }
 
-/* Assure synchronization of the device steering tables with updates made by SW
- * insertion.
- */
-int mlx5dr_domain_sync(struct mlx5dr_domain *dmn, u32 flags)
-{
-	int ret = 0;
-
-	if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_SW) {
-		mlx5dr_domain_lock(dmn);
-		ret = mlx5dr_send_ring_force_drain(dmn);
-		mlx5dr_domain_unlock(dmn);
-		if (ret) {
-			mlx5dr_err(dmn, "Force drain failed flags: %d, ret: %d\n",
-				   flags, ret);
-			return ret;
-		}
-	}
-
-	if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_HW)
-		ret = mlx5dr_cmd_sync_steering(dmn->mdev);
-
-	return ret;
-}
-
 int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn)
 {
 	if (WARN_ON_ONCE(refcount_read(&dmn->refcount) > 1))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c
index 6fa06ba2d346..d034372fa047 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c
@@ -1049,12 +1049,6 @@ static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn)
 	return 0;
 }
 
-static void dr_cq_complete(struct mlx5_core_cq *mcq,
-			   struct mlx5_eqe *eqe)
-{
-	pr_err("CQ completion CQ: #%u\n", mcq->cqn);
-}
-
 static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 				      struct mlx5_uars_page *uar,
 				      size_t ncqe)
@@ -1067,7 +1061,6 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	int inlen, err, eqn;
 	void *cqc, *in;
 	__be64 *pas;
-	int vector;
 	u32 i;
 
 	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
@@ -1090,14 +1083,20 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 		cqe->op_own = MLX5_CQE_INVALID << 4 | MLX5_CQE_OWNER_MASK;
 	}
 
+	cq->mcq.cqe_sz = 64;
+	cq->mcq.set_ci_db = cq->wq_ctrl.db.db;
+	cq->mcq.arm_db = cq->wq_ctrl.db.db + 1;
+	*cq->mcq.set_ci_db = 0;
+	cq->mcq.vector = 0;
+	cq->mdev = mdev;
+
 	inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
 		sizeof(u64) * cq->wq_ctrl.buf.npages;
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		goto err_cqwq;
 
-	vector = raw_smp_processor_id() % mlx5_comp_vectors_max(mdev);
-	err = mlx5_comp_eqn_get(mdev, vector, &eqn);
+	err = mlx5_comp_eqn_get(mdev, 0, &eqn);
 	if (err) {
 		kvfree(in);
 		goto err_cqwq;
@@ -1114,28 +1113,12 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas);
 	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas);
 
-	cq->mcq.comp  = dr_cq_complete;
-
 	err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out));
 	kvfree(in);
 
 	if (err)
 		goto err_cqwq;
 
-	cq->mcq.cqe_sz = 64;
-	cq->mcq.set_ci_db = cq->wq_ctrl.db.db;
-	cq->mcq.arm_db = cq->wq_ctrl.db.db + 1;
-	*cq->mcq.set_ci_db = 0;
-
-	/* set no-zero value, in order to avoid the HW to run db-recovery on
-	 * CQ that used in polling mode.
-	 */
-	*cq->mcq.arm_db = cpu_to_be32(2 << 28);
-
-	cq->mcq.vector = 0;
-	cq->mcq.uar = uar;
-	cq->mdev = mdev;
-
 	return cq;
 
 err_cqwq:
@@ -1333,36 +1316,3 @@ void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn,
 	kfree(send_ring->sync_buff);
 	kfree(send_ring);
 }
-
-int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn)
-{
-	struct mlx5dr_send_ring *send_ring = dmn->send_ring;
-	struct postsend_info send_info = {};
-	u8 data[DR_STE_SIZE];
-	int num_of_sends_req;
-	int ret;
-	int i;
-
-	/* Sending this amount of requests makes sure we will get drain */
-	num_of_sends_req = send_ring->signal_th * TH_NUMS_TO_DRAIN / 2;
-
-	/* Send fake requests forcing the last to be signaled */
-	send_info.write.addr = (uintptr_t)data;
-	send_info.write.length = DR_STE_SIZE;
-	send_info.write.lkey = 0;
-	/* Using the sync_mr in order to write/read */
-	send_info.remote_addr = (uintptr_t)send_ring->sync_mr->addr;
-	send_info.rkey = send_ring->sync_mr->mkey;
-
-	for (i = 0; i < num_of_sends_req; i++) {
-		ret = dr_postsend_icm_data(dmn, &send_info);
-		if (ret)
-			return ret;
-	}
-
-	spin_lock(&send_ring->lock);
-	ret = dr_handle_pending_wc(dmn, send_ring);
-	spin_unlock(&send_ring->lock);
-
-	return ret;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c
index e94fbb015efa..c8b8ff80c7c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c
@@ -555,7 +555,7 @@ void mlx5dr_ste_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx,
 			       struct mlx5dr_ste_actions_attr *attr,
 			       u32 *added_stes)
 {
-	ste_ctx->set_actions_tx(dmn, action_type_set, ste_ctx->actions_caps,
+	ste_ctx->set_actions_tx(ste_ctx, dmn, action_type_set, ste_ctx->actions_caps,
 				hw_ste_arr, attr, added_stes);
 }
 
@@ -566,7 +566,7 @@ void mlx5dr_ste_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx,
 			       struct mlx5dr_ste_actions_attr *attr,
 			       u32 *added_stes)
 {
-	ste_ctx->set_actions_rx(dmn, action_type_set, ste_ctx->actions_caps,
+	ste_ctx->set_actions_rx(ste_ctx, dmn, action_type_set, ste_ctx->actions_caps,
 				hw_ste_arr, attr, added_stes);
 }
 
@@ -1458,6 +1458,8 @@ struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx(u8 version)
 		return mlx5dr_ste_get_ctx_v1();
 	else if (version == MLX5_STEERING_FORMAT_CONNECTX_7)
 		return mlx5dr_ste_get_ctx_v2();
+	else if (version == MLX5_STEERING_FORMAT_CONNECTX_8)
+		return mlx5dr_ste_get_ctx_v3();
 
 	return NULL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h
index 54a6619c3ecb..3d5afc832fa5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h
@@ -160,13 +160,15 @@ struct mlx5dr_ste_ctx {
 
 	/* Actions */
 	u32 actions_caps;
-	void (*set_actions_rx)(struct mlx5dr_domain *dmn,
+	void (*set_actions_rx)(struct mlx5dr_ste_ctx *ste_ctx,
+			       struct mlx5dr_domain *dmn,
 			       u8 *action_type_set,
 			       u32 actions_caps,
 			       u8 *hw_ste_arr,
 			       struct mlx5dr_ste_actions_attr *attr,
 			       u32 *added_stes);
-	void (*set_actions_tx)(struct mlx5dr_domain *dmn,
+	void (*set_actions_tx)(struct mlx5dr_ste_ctx *ste_ctx,
+			       struct mlx5dr_domain *dmn,
 			       u8 *action_type_set,
 			       u32 actions_caps,
 			       u8 *hw_ste_arr,
@@ -197,7 +199,21 @@ struct mlx5dr_ste_ctx {
 					u16 *used_hw_action_num);
 	int (*alloc_modify_hdr_chunk)(struct mlx5dr_action *action);
 	void (*dealloc_modify_hdr_chunk)(struct mlx5dr_action *action);
-
+	/* Actions bit set */
+	void (*set_encap)(u8 *hw_ste_p, u8 *d_action,
+			  u32 reformat_id, int size);
+	void (*set_push_vlan)(u8 *ste, u8 *d_action,
+			      u32 vlan_hdr);
+	void (*set_pop_vlan)(u8 *hw_ste_p, u8 *s_action,
+			     u8 vlans_num);
+	void (*set_rx_decap)(u8 *hw_ste_p, u8 *s_action);
+	void (*set_encap_l3)(u8 *hw_ste_p, u8 *frst_s_action,
+			     u8 *scnd_d_action, u32 reformat_id,
+			     int size);
+	void (*set_insert_hdr)(u8 *hw_ste_p, u8 *d_action, u32 reformat_id,
+			       u8 anchor, u8 offset, int size);
+	void (*set_remove_hdr)(u8 *hw_ste_p, u8 *s_action, u8 anchor,
+			       u8 offset, int size);
 	/* Send */
 	void (*prepare_for_postsend)(u8 *hw_ste_p, u32 ste_size);
 };
@@ -205,5 +221,6 @@ struct mlx5dr_ste_ctx {
 struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v0(void);
 struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v1(void);
 struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v2(void);
+struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v3(void);
 
 #endif  /* _DR_STE_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c
index e9f6c7ed7a7b..42536bee55e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c
@@ -406,7 +406,8 @@ static void dr_ste_v0_arr_init_next(u8 **last_ste,
 }
 
 static void
-dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn,
+dr_ste_v0_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx,
+			 struct mlx5dr_domain *dmn,
 			 u8 *action_type_set,
 			 u32 actions_caps,
 			 u8 *last_ste,
@@ -476,7 +477,8 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn,
 }
 
 static void
-dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn,
+dr_ste_v0_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx,
+			 struct mlx5dr_domain *dmn,
 			 u8 *action_type_set,
 			 u32 actions_caps,
 			 u8 *last_ste,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c
index 1d49704b9542..6447efbae00d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c
@@ -5,136 +5,6 @@
 #include "mlx5_ifc_dr_ste_v1.h"
 #include "dr_ste_v1.h"
 
-#define DR_STE_CALC_DFNR_TYPE(lookup_type, inner) \
-	((inner) ? DR_STE_V1_LU_TYPE_##lookup_type##_I : \
-		   DR_STE_V1_LU_TYPE_##lookup_type##_O)
-
-enum dr_ste_v1_entry_format {
-	DR_STE_V1_TYPE_BWC_BYTE	= 0x0,
-	DR_STE_V1_TYPE_BWC_DW	= 0x1,
-	DR_STE_V1_TYPE_MATCH	= 0x2,
-	DR_STE_V1_TYPE_MATCH_RANGES = 0x7,
-};
-
-/* Lookup type is built from 2B: [ Definer mode 1B ][ Definer index 1B ] */
-enum {
-	DR_STE_V1_LU_TYPE_NOP				= 0x0000,
-	DR_STE_V1_LU_TYPE_ETHL2_TNL			= 0x0002,
-	DR_STE_V1_LU_TYPE_IBL3_EXT			= 0x0102,
-	DR_STE_V1_LU_TYPE_ETHL2_O			= 0x0003,
-	DR_STE_V1_LU_TYPE_IBL4				= 0x0103,
-	DR_STE_V1_LU_TYPE_ETHL2_I			= 0x0004,
-	DR_STE_V1_LU_TYPE_SRC_QP_GVMI			= 0x0104,
-	DR_STE_V1_LU_TYPE_ETHL2_SRC_O			= 0x0005,
-	DR_STE_V1_LU_TYPE_ETHL2_HEADERS_O		= 0x0105,
-	DR_STE_V1_LU_TYPE_ETHL2_SRC_I			= 0x0006,
-	DR_STE_V1_LU_TYPE_ETHL2_HEADERS_I		= 0x0106,
-	DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_O		= 0x0007,
-	DR_STE_V1_LU_TYPE_IPV6_DES_O			= 0x0107,
-	DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_I		= 0x0008,
-	DR_STE_V1_LU_TYPE_IPV6_DES_I			= 0x0108,
-	DR_STE_V1_LU_TYPE_ETHL4_O			= 0x0009,
-	DR_STE_V1_LU_TYPE_IPV6_SRC_O			= 0x0109,
-	DR_STE_V1_LU_TYPE_ETHL4_I			= 0x000a,
-	DR_STE_V1_LU_TYPE_IPV6_SRC_I			= 0x010a,
-	DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_O		= 0x000b,
-	DR_STE_V1_LU_TYPE_MPLS_O			= 0x010b,
-	DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_I		= 0x000c,
-	DR_STE_V1_LU_TYPE_MPLS_I			= 0x010c,
-	DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_O		= 0x000d,
-	DR_STE_V1_LU_TYPE_GRE				= 0x010d,
-	DR_STE_V1_LU_TYPE_FLEX_PARSER_TNL_HEADER	= 0x000e,
-	DR_STE_V1_LU_TYPE_GENERAL_PURPOSE		= 0x010e,
-	DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_I		= 0x000f,
-	DR_STE_V1_LU_TYPE_STEERING_REGISTERS_0		= 0x010f,
-	DR_STE_V1_LU_TYPE_STEERING_REGISTERS_1		= 0x0110,
-	DR_STE_V1_LU_TYPE_FLEX_PARSER_OK		= 0x0011,
-	DR_STE_V1_LU_TYPE_FLEX_PARSER_0			= 0x0111,
-	DR_STE_V1_LU_TYPE_FLEX_PARSER_1			= 0x0112,
-	DR_STE_V1_LU_TYPE_ETHL4_MISC_O			= 0x0113,
-	DR_STE_V1_LU_TYPE_ETHL4_MISC_I			= 0x0114,
-	DR_STE_V1_LU_TYPE_INVALID			= 0x00ff,
-	DR_STE_V1_LU_TYPE_DONT_CARE			= MLX5DR_STE_LU_TYPE_DONT_CARE,
-};
-
-enum dr_ste_v1_header_anchors {
-	DR_STE_HEADER_ANCHOR_START_OUTER		= 0x00,
-	DR_STE_HEADER_ANCHOR_1ST_VLAN			= 0x02,
-	DR_STE_HEADER_ANCHOR_IPV6_IPV4			= 0x07,
-	DR_STE_HEADER_ANCHOR_INNER_MAC			= 0x13,
-	DR_STE_HEADER_ANCHOR_INNER_IPV6_IPV4		= 0x19,
-};
-
-enum dr_ste_v1_action_size {
-	DR_STE_ACTION_SINGLE_SZ = 4,
-	DR_STE_ACTION_DOUBLE_SZ = 8,
-	DR_STE_ACTION_TRIPLE_SZ = 12,
-};
-
-enum dr_ste_v1_action_insert_ptr_attr {
-	DR_STE_V1_ACTION_INSERT_PTR_ATTR_NONE = 0,  /* Regular push header (e.g. push vlan) */
-	DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP = 1, /* Encapsulation / Tunneling */
-	DR_STE_V1_ACTION_INSERT_PTR_ATTR_ESP = 2,   /* IPsec */
-};
-
-enum dr_ste_v1_action_id {
-	DR_STE_V1_ACTION_ID_NOP				= 0x00,
-	DR_STE_V1_ACTION_ID_COPY			= 0x05,
-	DR_STE_V1_ACTION_ID_SET				= 0x06,
-	DR_STE_V1_ACTION_ID_ADD				= 0x07,
-	DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE		= 0x08,
-	DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER	= 0x09,
-	DR_STE_V1_ACTION_ID_INSERT_INLINE		= 0x0a,
-	DR_STE_V1_ACTION_ID_INSERT_POINTER		= 0x0b,
-	DR_STE_V1_ACTION_ID_FLOW_TAG			= 0x0c,
-	DR_STE_V1_ACTION_ID_QUEUE_ID_SEL		= 0x0d,
-	DR_STE_V1_ACTION_ID_ACCELERATED_LIST		= 0x0e,
-	DR_STE_V1_ACTION_ID_MODIFY_LIST			= 0x0f,
-	DR_STE_V1_ACTION_ID_ASO				= 0x12,
-	DR_STE_V1_ACTION_ID_TRAILER			= 0x13,
-	DR_STE_V1_ACTION_ID_COUNTER_ID			= 0x14,
-	DR_STE_V1_ACTION_ID_MAX				= 0x21,
-	/* use for special cases */
-	DR_STE_V1_ACTION_ID_SPECIAL_ENCAP_L3		= 0x22,
-};
-
-enum {
-	DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_0		= 0x00,
-	DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_1		= 0x01,
-	DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_2		= 0x02,
-	DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_0		= 0x08,
-	DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_1		= 0x09,
-	DR_STE_V1_ACTION_MDFY_FLD_L3_OUT_0		= 0x0e,
-	DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_0		= 0x18,
-	DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_1		= 0x19,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_0		= 0x40,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_1		= 0x41,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_0	= 0x44,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_1	= 0x45,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_2	= 0x46,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_3	= 0x47,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_0	= 0x4c,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_1	= 0x4d,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_2	= 0x4e,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_3	= 0x4f,
-	DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_0		= 0x5e,
-	DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_1		= 0x5f,
-	DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_0		= 0x6f,
-	DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_1		= 0x70,
-	DR_STE_V1_ACTION_MDFY_FLD_METADATA_2_CQE	= 0x7b,
-	DR_STE_V1_ACTION_MDFY_FLD_GNRL_PURPOSE		= 0x7c,
-	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_0		= 0x8c,
-	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_1		= 0x8d,
-	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_0		= 0x8e,
-	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_1		= 0x8f,
-	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_0		= 0x90,
-	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_1		= 0x91,
-};
-
-enum dr_ste_v1_aso_ctx_type {
-	DR_STE_V1_ASO_CTX_TYPE_POLICERS = 0x2,
-};
-
 static const struct mlx5dr_ste_action_modify_field dr_ste_v1_action_modify_field_arr[] = {
 	[MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = {
 		.hw_field = DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_0, .start = 0, .end = 31,
@@ -379,13 +249,12 @@ static void dr_ste_v1_set_counter_id(u8 *hw_ste_p, u32 ctr_id)
 	MLX5_SET(ste_match_bwc_v1, hw_ste_p, counter_id, ctr_id);
 }
 
-static void dr_ste_v1_set_reparse(u8 *hw_ste_p)
+void dr_ste_v1_set_reparse(u8 *hw_ste_p)
 {
 	MLX5_SET(ste_match_bwc_v1, hw_ste_p, reparse, 1);
 }
 
-static void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action,
-				u32 reformat_id, int size)
+void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action, u32 reformat_id, int size)
 {
 	MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, action_id,
 		 DR_STE_V1_ACTION_ID_INSERT_POINTER);
@@ -397,10 +266,10 @@ static void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action,
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action,
-				     u32 reformat_id,
-				     u8 anchor, u8 offset,
-				     int size)
+void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action,
+			      u32 reformat_id,
+			      u8 anchor, u8 offset,
+			      int size)
 {
 	MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action,
 		 action_id, DR_STE_V1_ACTION_ID_INSERT_POINTER);
@@ -417,9 +286,9 @@ static void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action,
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_remove_hdr(u8 *hw_ste_p, u8 *s_action,
-				     u8 anchor, u8 offset,
-				     int size)
+void dr_ste_v1_set_remove_hdr(u8 *hw_ste_p, u8 *s_action,
+			      u8 anchor, u8 offset,
+			      int size)
 {
 	MLX5_SET(ste_single_action_remove_header_size_v1, s_action,
 		 action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
@@ -432,8 +301,7 @@ static void dr_ste_v1_set_remove_hdr(u8 *hw_ste_p, u8 *s_action,
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_push_vlan(u8 *hw_ste_p, u8 *d_action,
-				    u32 vlan_hdr)
+void dr_ste_v1_set_push_vlan(u8 *hw_ste_p, u8 *d_action, u32 vlan_hdr)
 {
 	MLX5_SET(ste_double_action_insert_with_inline_v1, d_action,
 		 action_id, DR_STE_V1_ACTION_ID_INSERT_INLINE);
@@ -446,7 +314,7 @@ static void dr_ste_v1_set_push_vlan(u8 *hw_ste_p, u8 *d_action,
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num)
+void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num)
 {
 	MLX5_SET(ste_single_action_remove_header_size_v1, s_action,
 		 action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
@@ -459,11 +327,8 @@ static void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num)
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_encap_l3(u8 *hw_ste_p,
-				   u8 *frst_s_action,
-				   u8 *scnd_d_action,
-				   u32 reformat_id,
-				   int size)
+void dr_ste_v1_set_encap_l3(u8 *hw_ste_p, u8 *frst_s_action, u8 *scnd_d_action,
+			    u32 reformat_id, int size)
 {
 	/* Remove L2 headers */
 	MLX5_SET(ste_single_action_remove_header_v1, frst_s_action, action_id,
@@ -483,7 +348,7 @@ static void dr_ste_v1_set_encap_l3(u8 *hw_ste_p,
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_rx_decap(u8 *hw_ste_p, u8 *s_action)
+void dr_ste_v1_set_rx_decap(u8 *hw_ste_p, u8 *s_action)
 {
 	MLX5_SET(ste_single_action_remove_header_v1, s_action, action_id,
 		 DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER);
@@ -620,7 +485,8 @@ static void dr_ste_v1_arr_init_next_match_range(u8 **last_ste,
 	dr_ste_v1_set_entry_type(*last_ste, DR_STE_V1_TYPE_MATCH_RANGES);
 }
 
-void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
+void dr_ste_v1_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx,
+			      struct mlx5dr_domain *dmn,
 			      u8 *action_type_set,
 			      u32 actions_caps,
 			      u8 *last_ste,
@@ -640,7 +506,7 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 					      last_ste, action);
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
-		dr_ste_v1_set_pop_vlan(last_ste, action, attr->vlans.count);
+		ste_ctx->set_pop_vlan(last_ste, action, attr->vlans.count);
 		action_sz -= DR_STE_ACTION_SINGLE_SZ;
 		action += DR_STE_ACTION_SINGLE_SZ;
 
@@ -677,8 +543,8 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 				action_sz = DR_STE_ACTION_TRIPLE_SZ;
 				allow_encap = true;
 			}
-			dr_ste_v1_set_push_vlan(last_ste, action,
-						attr->vlans.headers[i]);
+			ste_ctx->set_push_vlan(last_ste, action,
+					       attr->vlans.headers[i]);
 			action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 			action += DR_STE_ACTION_DOUBLE_SZ;
 		}
@@ -691,9 +557,9 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 			allow_encap = true;
 		}
-		dr_ste_v1_set_encap(last_ste, action,
-				    attr->reformat.id,
-				    attr->reformat.size);
+		ste_ctx->set_encap(last_ste, action,
+				   attr->reformat.id,
+				   attr->reformat.size);
 		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 		action += DR_STE_ACTION_DOUBLE_SZ;
 	} else if (action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]) {
@@ -706,10 +572,10 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 		}
 		d_action = action + DR_STE_ACTION_SINGLE_SZ;
 
-		dr_ste_v1_set_encap_l3(last_ste,
-				       action, d_action,
-				       attr->reformat.id,
-				       attr->reformat.size);
+		ste_ctx->set_encap_l3(last_ste,
+				      action, d_action,
+				      attr->reformat.id,
+				      attr->reformat.size);
 		action_sz -= DR_STE_ACTION_TRIPLE_SZ;
 		action += DR_STE_ACTION_TRIPLE_SZ;
 	} else if (action_type_set[DR_ACTION_TYP_INSERT_HDR]) {
@@ -718,11 +584,11 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
-		dr_ste_v1_set_insert_hdr(last_ste, action,
-					 attr->reformat.id,
-					 attr->reformat.param_0,
-					 attr->reformat.param_1,
-					 attr->reformat.size);
+		ste_ctx->set_insert_hdr(last_ste, action,
+					attr->reformat.id,
+					attr->reformat.param_0,
+					attr->reformat.param_1,
+					attr->reformat.size);
 		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 		action += DR_STE_ACTION_DOUBLE_SZ;
 	} else if (action_type_set[DR_ACTION_TYP_REMOVE_HDR]) {
@@ -731,10 +597,10 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
-		dr_ste_v1_set_remove_hdr(last_ste, action,
-					 attr->reformat.param_0,
-					 attr->reformat.param_1,
-					 attr->reformat.size);
+		ste_ctx->set_remove_hdr(last_ste, action,
+					attr->reformat.param_0,
+					attr->reformat.param_1,
+					attr->reformat.size);
 		action_sz -= DR_STE_ACTION_SINGLE_SZ;
 		action += DR_STE_ACTION_SINGLE_SZ;
 	}
@@ -776,7 +642,8 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 	dr_ste_v1_set_hit_addr(last_ste, attr->final_icm_addr, 1);
 }
 
-void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
+void dr_ste_v1_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx,
+			      struct mlx5dr_domain *dmn,
 			      u8 *action_type_set,
 			      u32 actions_caps,
 			      u8 *last_ste,
@@ -799,7 +666,7 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 		allow_modify_hdr = false;
 		allow_ctr = false;
 	} else if (action_type_set[DR_ACTION_TYP_TNL_L2_TO_L2]) {
-		dr_ste_v1_set_rx_decap(last_ste, action);
+		ste_ctx->set_rx_decap(last_ste, action);
 		action_sz -= DR_STE_ACTION_SINGLE_SZ;
 		action += DR_STE_ACTION_SINGLE_SZ;
 		allow_modify_hdr = false;
@@ -827,7 +694,7 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
 
-		dr_ste_v1_set_pop_vlan(last_ste, action, attr->vlans.count);
+		ste_ctx->set_pop_vlan(last_ste, action, attr->vlans.count);
 		action_sz -= DR_STE_ACTION_SINGLE_SZ;
 		action += DR_STE_ACTION_SINGLE_SZ;
 		allow_ctr = false;
@@ -868,8 +735,8 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 						      last_ste, action);
 				action_sz = DR_STE_ACTION_TRIPLE_SZ;
 			}
-			dr_ste_v1_set_push_vlan(last_ste, action,
-						attr->vlans.headers[i]);
+			ste_ctx->set_push_vlan(last_ste, action,
+					       attr->vlans.headers[i]);
 			action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 			action += DR_STE_ACTION_DOUBLE_SZ;
 		}
@@ -895,9 +762,9 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
-		dr_ste_v1_set_encap(last_ste, action,
-				    attr->reformat.id,
-				    attr->reformat.size);
+		ste_ctx->set_encap(last_ste, action,
+				   attr->reformat.id,
+				   attr->reformat.size);
 		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 		action += DR_STE_ACTION_DOUBLE_SZ;
 		allow_modify_hdr = false;
@@ -912,10 +779,10 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 
 		d_action = action + DR_STE_ACTION_SINGLE_SZ;
 
-		dr_ste_v1_set_encap_l3(last_ste,
-				       action, d_action,
-				       attr->reformat.id,
-				       attr->reformat.size);
+		ste_ctx->set_encap_l3(last_ste,
+				      action, d_action,
+				      attr->reformat.id,
+				      attr->reformat.size);
 		action_sz -= DR_STE_ACTION_TRIPLE_SZ;
 		allow_modify_hdr = false;
 	} else if (action_type_set[DR_ACTION_TYP_INSERT_HDR]) {
@@ -925,11 +792,11 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
-		dr_ste_v1_set_insert_hdr(last_ste, action,
-					 attr->reformat.id,
-					 attr->reformat.param_0,
-					 attr->reformat.param_1,
-					 attr->reformat.size);
+		ste_ctx->set_insert_hdr(last_ste, action,
+					attr->reformat.id,
+					attr->reformat.param_0,
+					attr->reformat.param_1,
+					attr->reformat.size);
 		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 		action += DR_STE_ACTION_DOUBLE_SZ;
 		allow_modify_hdr = false;
@@ -941,10 +808,10 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 			allow_modify_hdr = true;
 			allow_ctr = true;
 		}
-		dr_ste_v1_set_remove_hdr(last_ste, action,
-					 attr->reformat.param_0,
-					 attr->reformat.param_1,
-					 attr->reformat.size);
+		ste_ctx->set_remove_hdr(last_ste, action,
+					attr->reformat.param_0,
+					attr->reformat.param_1,
+					attr->reformat.size);
 		action_sz -= DR_STE_ACTION_SINGLE_SZ;
 		action += DR_STE_ACTION_SINGLE_SZ;
 	}
@@ -1027,9 +894,6 @@ void dr_ste_v1_set_action_copy(u8 *d_action,
 	MLX5_SET(ste_double_action_copy_v1, d_action, source_right_shifter, src_shifter);
 }
 
-#define DR_STE_DECAP_L3_ACTION_NUM	8
-#define DR_STE_L2_HDR_MAX_SZ		20
-
 int dr_ste_v1_set_action_decap_l3_list(void *data,
 				       u32 data_sz,
 				       u8 *hw_action,
@@ -2330,7 +2194,14 @@ static struct mlx5dr_ste_ctx ste_ctx_v1 = {
 	.set_action_decap_l3_list	= &dr_ste_v1_set_action_decap_l3_list,
 	.alloc_modify_hdr_chunk		= &dr_ste_v1_alloc_modify_hdr_ptrn_arg,
 	.dealloc_modify_hdr_chunk	= &dr_ste_v1_free_modify_hdr_ptrn_arg,
-
+	/* Actions bit set */
+	.set_encap			= &dr_ste_v1_set_encap,
+	.set_push_vlan			= &dr_ste_v1_set_push_vlan,
+	.set_pop_vlan			= &dr_ste_v1_set_pop_vlan,
+	.set_rx_decap			= &dr_ste_v1_set_rx_decap,
+	.set_encap_l3			= &dr_ste_v1_set_encap_l3,
+	.set_insert_hdr			= &dr_ste_v1_set_insert_hdr,
+	.set_remove_hdr			= &dr_ste_v1_set_remove_hdr,
 	/* Send */
 	.prepare_for_postsend		= &dr_ste_v1_prepare_for_postsend,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h
index e2fc69867088..591c20c95a6a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h
@@ -7,6 +7,138 @@
 #include "dr_types.h"
 #include "dr_ste.h"
 
+#define DR_STE_DECAP_L3_ACTION_NUM	8
+#define DR_STE_L2_HDR_MAX_SZ		20
+#define DR_STE_CALC_DFNR_TYPE(lookup_type, inner) \
+	((inner) ? DR_STE_V1_LU_TYPE_##lookup_type##_I : \
+		   DR_STE_V1_LU_TYPE_##lookup_type##_O)
+
+enum dr_ste_v1_entry_format {
+	DR_STE_V1_TYPE_BWC_BYTE	= 0x0,
+	DR_STE_V1_TYPE_BWC_DW	= 0x1,
+	DR_STE_V1_TYPE_MATCH	= 0x2,
+	DR_STE_V1_TYPE_MATCH_RANGES = 0x7,
+};
+
+/* Lookup type is built from 2B: [ Definer mode 1B ][ Definer index 1B ] */
+enum {
+	DR_STE_V1_LU_TYPE_NOP				= 0x0000,
+	DR_STE_V1_LU_TYPE_ETHL2_TNL			= 0x0002,
+	DR_STE_V1_LU_TYPE_IBL3_EXT			= 0x0102,
+	DR_STE_V1_LU_TYPE_ETHL2_O			= 0x0003,
+	DR_STE_V1_LU_TYPE_IBL4				= 0x0103,
+	DR_STE_V1_LU_TYPE_ETHL2_I			= 0x0004,
+	DR_STE_V1_LU_TYPE_SRC_QP_GVMI			= 0x0104,
+	DR_STE_V1_LU_TYPE_ETHL2_SRC_O			= 0x0005,
+	DR_STE_V1_LU_TYPE_ETHL2_HEADERS_O		= 0x0105,
+	DR_STE_V1_LU_TYPE_ETHL2_SRC_I			= 0x0006,
+	DR_STE_V1_LU_TYPE_ETHL2_HEADERS_I		= 0x0106,
+	DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_O		= 0x0007,
+	DR_STE_V1_LU_TYPE_IPV6_DES_O			= 0x0107,
+	DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_I		= 0x0008,
+	DR_STE_V1_LU_TYPE_IPV6_DES_I			= 0x0108,
+	DR_STE_V1_LU_TYPE_ETHL4_O			= 0x0009,
+	DR_STE_V1_LU_TYPE_IPV6_SRC_O			= 0x0109,
+	DR_STE_V1_LU_TYPE_ETHL4_I			= 0x000a,
+	DR_STE_V1_LU_TYPE_IPV6_SRC_I			= 0x010a,
+	DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_O		= 0x000b,
+	DR_STE_V1_LU_TYPE_MPLS_O			= 0x010b,
+	DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_I		= 0x000c,
+	DR_STE_V1_LU_TYPE_MPLS_I			= 0x010c,
+	DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_O		= 0x000d,
+	DR_STE_V1_LU_TYPE_GRE				= 0x010d,
+	DR_STE_V1_LU_TYPE_FLEX_PARSER_TNL_HEADER	= 0x000e,
+	DR_STE_V1_LU_TYPE_GENERAL_PURPOSE		= 0x010e,
+	DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_I		= 0x000f,
+	DR_STE_V1_LU_TYPE_STEERING_REGISTERS_0		= 0x010f,
+	DR_STE_V1_LU_TYPE_STEERING_REGISTERS_1		= 0x0110,
+	DR_STE_V1_LU_TYPE_FLEX_PARSER_OK		= 0x0011,
+	DR_STE_V1_LU_TYPE_FLEX_PARSER_0			= 0x0111,
+	DR_STE_V1_LU_TYPE_FLEX_PARSER_1			= 0x0112,
+	DR_STE_V1_LU_TYPE_ETHL4_MISC_O			= 0x0113,
+	DR_STE_V1_LU_TYPE_ETHL4_MISC_I			= 0x0114,
+	DR_STE_V1_LU_TYPE_INVALID			= 0x00ff,
+	DR_STE_V1_LU_TYPE_DONT_CARE			= MLX5DR_STE_LU_TYPE_DONT_CARE,
+};
+
+enum dr_ste_v1_header_anchors {
+	DR_STE_HEADER_ANCHOR_START_OUTER		= 0x00,
+	DR_STE_HEADER_ANCHOR_1ST_VLAN			= 0x02,
+	DR_STE_HEADER_ANCHOR_IPV6_IPV4			= 0x07,
+	DR_STE_HEADER_ANCHOR_INNER_MAC			= 0x13,
+	DR_STE_HEADER_ANCHOR_INNER_IPV6_IPV4		= 0x19,
+};
+
+enum dr_ste_v1_action_size {
+	DR_STE_ACTION_SINGLE_SZ = 4,
+	DR_STE_ACTION_DOUBLE_SZ = 8,
+	DR_STE_ACTION_TRIPLE_SZ = 12,
+};
+
+enum dr_ste_v1_action_insert_ptr_attr {
+	DR_STE_V1_ACTION_INSERT_PTR_ATTR_NONE = 0,  /* Regular push header (e.g. push vlan) */
+	DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP = 1, /* Encapsulation / Tunneling */
+	DR_STE_V1_ACTION_INSERT_PTR_ATTR_ESP = 2,   /* IPsec */
+};
+
+enum dr_ste_v1_action_id {
+	DR_STE_V1_ACTION_ID_NOP				= 0x00,
+	DR_STE_V1_ACTION_ID_COPY			= 0x05,
+	DR_STE_V1_ACTION_ID_SET				= 0x06,
+	DR_STE_V1_ACTION_ID_ADD				= 0x07,
+	DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE		= 0x08,
+	DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER	= 0x09,
+	DR_STE_V1_ACTION_ID_INSERT_INLINE		= 0x0a,
+	DR_STE_V1_ACTION_ID_INSERT_POINTER		= 0x0b,
+	DR_STE_V1_ACTION_ID_FLOW_TAG			= 0x0c,
+	DR_STE_V1_ACTION_ID_QUEUE_ID_SEL		= 0x0d,
+	DR_STE_V1_ACTION_ID_ACCELERATED_LIST		= 0x0e,
+	DR_STE_V1_ACTION_ID_MODIFY_LIST			= 0x0f,
+	DR_STE_V1_ACTION_ID_ASO				= 0x12,
+	DR_STE_V1_ACTION_ID_TRAILER			= 0x13,
+	DR_STE_V1_ACTION_ID_COUNTER_ID			= 0x14,
+	DR_STE_V1_ACTION_ID_MAX				= 0x21,
+	/* use for special cases */
+	DR_STE_V1_ACTION_ID_SPECIAL_ENCAP_L3		= 0x22,
+};
+
+enum {
+	DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_0		= 0x00,
+	DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_1		= 0x01,
+	DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_2		= 0x02,
+	DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_0		= 0x08,
+	DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_1		= 0x09,
+	DR_STE_V1_ACTION_MDFY_FLD_L3_OUT_0		= 0x0e,
+	DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_0		= 0x18,
+	DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_1		= 0x19,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_0		= 0x40,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_1		= 0x41,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_0	= 0x44,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_1	= 0x45,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_2	= 0x46,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_3	= 0x47,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_0	= 0x4c,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_1	= 0x4d,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_2	= 0x4e,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_3	= 0x4f,
+	DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_0		= 0x5e,
+	DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_1		= 0x5f,
+	DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_0		= 0x6f,
+	DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_1		= 0x70,
+	DR_STE_V1_ACTION_MDFY_FLD_METADATA_2_CQE	= 0x7b,
+	DR_STE_V1_ACTION_MDFY_FLD_GNRL_PURPOSE		= 0x7c,
+	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_0		= 0x8c,
+	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_1		= 0x8d,
+	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_0		= 0x8e,
+	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_1		= 0x8f,
+	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_0		= 0x90,
+	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_1		= 0x91,
+};
+
+enum dr_ste_v1_aso_ctx_type {
+	DR_STE_V1_ASO_CTX_TYPE_POLICERS = 0x2,
+};
+
 bool dr_ste_v1_is_miss_addr_set(u8 *hw_ste_p);
 void dr_ste_v1_set_miss_addr(u8 *hw_ste_p, u64 miss_addr);
 u64 dr_ste_v1_get_miss_addr(u8 *hw_ste_p);
@@ -17,11 +149,22 @@ u16 dr_ste_v1_get_next_lu_type(u8 *hw_ste_p);
 void dr_ste_v1_set_hit_addr(u8 *hw_ste_p, u64 icm_addr, u32 ht_size);
 void dr_ste_v1_init(u8 *hw_ste_p, u16 lu_type, bool is_rx, u16 gvmi);
 void dr_ste_v1_prepare_for_postsend(u8 *hw_ste_p, u32 ste_size);
-void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, u8 *action_type_set,
-			      u32 actions_caps, u8 *last_ste,
+void dr_ste_v1_set_reparse(u8 *hw_ste_p);
+void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action, u32 reformat_id, int size);
+void dr_ste_v1_set_push_vlan(u8 *hw_ste_p, u8 *d_action, u32 vlan_hdr);
+void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num);
+void dr_ste_v1_set_encap_l3(u8 *hw_ste_p, u8 *frst_s_action, u8 *scnd_d_action,
+			    u32 reformat_id, int size);
+void dr_ste_v1_set_rx_decap(u8 *hw_ste_p, u8 *s_action);
+void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action, u32 reformat_id,
+			      u8 anchor, u8 offset, int size);
+void dr_ste_v1_set_remove_hdr(u8 *hw_ste_p, u8 *s_action, u8 anchor,
+			      u8 offset, int size);
+void dr_ste_v1_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_domain *dmn,
+			      u8 *action_type_set, u32 actions_caps, u8 *last_ste,
 			      struct mlx5dr_ste_actions_attr *attr, u32 *added_stes);
-void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, u8 *action_type_set,
-			      u32 actions_caps, u8 *last_ste,
+void dr_ste_v1_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_domain *dmn,
+			      u8 *action_type_set, u32 actions_caps, u8 *last_ste,
 			      struct mlx5dr_ste_actions_attr *attr, u32 *added_stes);
 void dr_ste_v1_set_action_set(u8 *d_action, u8 hw_field, u8 shifter,
 			      u8 length, u32 data);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c
index 808b013cf48c..d0ebaf820d42 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c
@@ -2,167 +2,7 @@
 /* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
 
 #include "dr_ste_v1.h"
-
-enum {
-	DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0		= 0x00,
-	DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1		= 0x01,
-	DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2		= 0x02,
-	DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0		= 0x08,
-	DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1		= 0x09,
-	DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0		= 0x0e,
-	DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0		= 0x18,
-	DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1		= 0x19,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0		= 0x40,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1		= 0x41,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0	= 0x44,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1	= 0x45,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2	= 0x46,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3	= 0x47,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0	= 0x4c,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1	= 0x4d,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2	= 0x4e,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3	= 0x4f,
-	DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0		= 0x5e,
-	DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1		= 0x5f,
-	DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0		= 0x6f,
-	DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1		= 0x70,
-	DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE	= 0x7b,
-	DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE		= 0x7c,
-	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0		= 0x90,
-	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1		= 0x91,
-	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0		= 0x92,
-	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1		= 0x93,
-	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0		= 0x94,
-	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1		= 0x95,
-};
-
-static const struct mlx5dr_ste_action_modify_field dr_ste_v2_action_modify_field_arr[] = {
-	[MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1, .start = 16, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 0, .end = 15,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 16, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_IP_DSCP] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 18, .end = 23,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1, .start = 16, .end = 24,
-		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31,
-		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15,
-		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_IP_TTL] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31,
-		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15,
-		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_SIPV4] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DIPV4] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_A] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_B] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_0] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_1] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_2] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_3] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_4] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_5] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_FIRST_VID] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2, .start = 0, .end = 15,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_EMD_31_0] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_EMD_47_32] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0, .start = 0, .end = 15,
-	},
-};
+#include "dr_ste_v2.h"
 
 static struct mlx5dr_ste_ctx ste_ctx_v2 = {
 	/* Builders */
@@ -223,7 +63,14 @@ static struct mlx5dr_ste_ctx ste_ctx_v2 = {
 	.set_action_decap_l3_list	= &dr_ste_v1_set_action_decap_l3_list,
 	.alloc_modify_hdr_chunk		= &dr_ste_v1_alloc_modify_hdr_ptrn_arg,
 	.dealloc_modify_hdr_chunk	= &dr_ste_v1_free_modify_hdr_ptrn_arg,
-
+	/* Actions bit set */
+	.set_encap			= &dr_ste_v1_set_encap,
+	.set_push_vlan			= &dr_ste_v1_set_push_vlan,
+	.set_pop_vlan			= &dr_ste_v1_set_pop_vlan,
+	.set_rx_decap			= &dr_ste_v1_set_rx_decap,
+	.set_encap_l3			= &dr_ste_v1_set_encap_l3,
+	.set_insert_hdr			= &dr_ste_v1_set_insert_hdr,
+	.set_remove_hdr			= &dr_ste_v1_set_remove_hdr,
 	/* Send */
 	.prepare_for_postsend		= &dr_ste_v1_prepare_for_postsend,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.h
new file mode 100644
index 000000000000..d853fde49cfc
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.h
@@ -0,0 +1,168 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef	_DR_STE_V2_
+#define	_DR_STE_V2_
+
+enum {
+	DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0		= 0x00,
+	DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1		= 0x01,
+	DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2		= 0x02,
+	DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0		= 0x08,
+	DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1		= 0x09,
+	DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0		= 0x0e,
+	DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0		= 0x18,
+	DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1		= 0x19,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0		= 0x40,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1		= 0x41,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0	= 0x44,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1	= 0x45,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2	= 0x46,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3	= 0x47,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0	= 0x4c,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1	= 0x4d,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2	= 0x4e,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3	= 0x4f,
+	DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0		= 0x5e,
+	DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1		= 0x5f,
+	DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0		= 0x6f,
+	DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1		= 0x70,
+	DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE	= 0x7b,
+	DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE		= 0x7c,
+	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0		= 0x90,
+	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1		= 0x91,
+	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0		= 0x92,
+	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1		= 0x93,
+	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0		= 0x94,
+	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1		= 0x95,
+};
+
+static const struct mlx5dr_ste_action_modify_field dr_ste_v2_action_modify_field_arr[] = {
+	[MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1, .start = 16, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 0, .end = 15,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 16, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_IP_DSCP] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 18, .end = 23,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1, .start = 16, .end = 24,
+		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31,
+		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15,
+		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_IP_TTL] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31,
+		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15,
+		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_SIPV4] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DIPV4] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_A] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_B] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_0] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_1] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_2] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_3] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_4] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_5] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_FIRST_VID] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2, .start = 0, .end = 15,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_EMD_31_0] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_EMD_47_32] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0, .start = 0, .end = 15,
+	},
+};
+
+#endif  /* _DR_STE_V2_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v3.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v3.c
new file mode 100644
index 000000000000..e468a9ae44e8
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v3.c
@@ -0,0 +1,263 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include "dr_ste_v1.h"
+#include "dr_ste_v2.h"
+
+static void dr_ste_v3_set_encap(u8 *hw_ste_p, u8 *d_action,
+				u32 reformat_id, int size)
+{
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action, action_id,
+		 DR_STE_V1_ACTION_ID_INSERT_POINTER);
+	/* The hardware expects here size in words (2 byte) */
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action, size, size / 2);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action, pointer, reformat_id);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action, attributes,
+		 DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP);
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
+static void dr_ste_v3_set_push_vlan(u8 *ste, u8 *d_action,
+				    u32 vlan_hdr)
+{
+	MLX5_SET(ste_double_action_insert_with_inline_v3, d_action, action_id,
+		 DR_STE_V1_ACTION_ID_INSERT_INLINE);
+	/* The hardware expects here offset to vlan header in words (2 byte) */
+	MLX5_SET(ste_double_action_insert_with_inline_v3, d_action, start_offset,
+		 HDR_LEN_L2_MACS >> 1);
+	MLX5_SET(ste_double_action_insert_with_inline_v3, d_action, inline_data, vlan_hdr);
+	dr_ste_v1_set_reparse(ste);
+}
+
+static void dr_ste_v3_set_pop_vlan(u8 *hw_ste_p, u8 *s_action,
+				   u8 vlans_num)
+{
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 start_anchor, DR_STE_HEADER_ANCHOR_1ST_VLAN);
+	/* The hardware expects here size in words (2 byte) */
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 remove_size, (HDR_LEN_L2_VLAN >> 1) * vlans_num);
+
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
+static void dr_ste_v3_set_encap_l3(u8 *hw_ste_p,
+				   u8 *frst_s_action,
+				   u8 *scnd_d_action,
+				   u32 reformat_id,
+				   int size)
+{
+	/* Remove L2 headers */
+	MLX5_SET(ste_single_action_remove_header_v3, frst_s_action, action_id,
+		 DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER);
+	MLX5_SET(ste_single_action_remove_header_v3, frst_s_action, end_anchor,
+		 DR_STE_HEADER_ANCHOR_IPV6_IPV4);
+
+	/* Encapsulate with given reformat ID */
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, scnd_d_action, action_id,
+		 DR_STE_V1_ACTION_ID_INSERT_POINTER);
+	/* The hardware expects here size in words (2 byte) */
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, scnd_d_action, size, size / 2);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, scnd_d_action, pointer, reformat_id);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, scnd_d_action, attributes,
+		 DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP);
+
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
+static void dr_ste_v3_set_rx_decap(u8 *hw_ste_p, u8 *s_action)
+{
+	MLX5_SET(ste_single_action_remove_header_v3, s_action, action_id,
+		 DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER);
+	MLX5_SET(ste_single_action_remove_header_v3, s_action, decap, 1);
+	MLX5_SET(ste_single_action_remove_header_v3, s_action, vni_to_cqe, 1);
+	MLX5_SET(ste_single_action_remove_header_v3, s_action, end_anchor,
+		 DR_STE_HEADER_ANCHOR_INNER_MAC);
+
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
+static void dr_ste_v3_set_insert_hdr(u8 *hw_ste_p, u8 *d_action,
+				     u32 reformat_id, u8 anchor,
+				     u8 offset, int size)
+{
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 action_id, DR_STE_V1_ACTION_ID_INSERT_POINTER);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 start_anchor, anchor);
+
+	/* The hardware expects here size and offset in words (2 byte) */
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 size, size / 2);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 start_offset, offset / 2);
+
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 pointer, reformat_id);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 attributes, DR_STE_V1_ACTION_INSERT_PTR_ATTR_NONE);
+
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
+static void dr_ste_v3_set_remove_hdr(u8 *hw_ste_p, u8 *s_action,
+				     u8 anchor, u8 offset, int size)
+{
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 start_anchor, anchor);
+
+	/* The hardware expects here size and offset in words (2 byte) */
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 remove_size, size / 2);
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 start_offset, offset / 2);
+
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
+static int
+dr_ste_v3_set_action_decap_l3_list(void *data, u32 data_sz,
+				   u8 *hw_action, u32 hw_action_sz,
+				   uint16_t *used_hw_action_num)
+{
+	u8 padded_data[DR_STE_L2_HDR_MAX_SZ] = {};
+	void *data_ptr = padded_data;
+	u16 used_actions = 0;
+	u32 inline_data_sz;
+	u32 i;
+
+	if (hw_action_sz / DR_STE_ACTION_DOUBLE_SZ < DR_STE_DECAP_L3_ACTION_NUM)
+		return -EINVAL;
+
+	inline_data_sz =
+		MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v3, inline_data);
+
+	/* Add an alignment padding  */
+	memcpy(padded_data + data_sz % inline_data_sz, data, data_sz);
+
+	/* Remove L2L3 outer headers */
+	MLX5_SET(ste_single_action_remove_header_v3, hw_action, action_id,
+		 DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER);
+	MLX5_SET(ste_single_action_remove_header_v3, hw_action, decap, 1);
+	MLX5_SET(ste_single_action_remove_header_v3, hw_action, vni_to_cqe, 1);
+	MLX5_SET(ste_single_action_remove_header_v3, hw_action, end_anchor,
+		 DR_STE_HEADER_ANCHOR_INNER_IPV6_IPV4);
+	hw_action += DR_STE_ACTION_DOUBLE_SZ;
+	used_actions++; /* Remove and NOP are a single double action */
+
+	/* Point to the last dword of the header */
+	data_ptr += (data_sz / inline_data_sz) * inline_data_sz;
+
+	/* Add the new header using inline action 4Byte at a time, the header
+	 * is added in reversed order to the beginning of the packet to avoid
+	 * incorrect parsing by the HW. Since header is 14B or 18B an extra
+	 * two bytes are padded and later removed.
+	 */
+	for (i = 0; i < data_sz / inline_data_sz + 1; i++) {
+		void *addr_inline;
+
+		MLX5_SET(ste_double_action_insert_with_inline_v3, hw_action, action_id,
+			 DR_STE_V1_ACTION_ID_INSERT_INLINE);
+		/* The hardware expects here offset to words (2 bytes) */
+		MLX5_SET(ste_double_action_insert_with_inline_v3, hw_action, start_offset, 0);
+
+		/* Copy bytes one by one to avoid endianness problem */
+		addr_inline = MLX5_ADDR_OF(ste_double_action_insert_with_inline_v3,
+					   hw_action, inline_data);
+		memcpy(addr_inline, data_ptr - i * inline_data_sz, inline_data_sz);
+		hw_action += DR_STE_ACTION_DOUBLE_SZ;
+		used_actions++;
+	}
+
+	/* Remove first 2 extra bytes */
+	MLX5_SET(ste_single_action_remove_header_size_v3, hw_action, action_id,
+		 DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
+	MLX5_SET(ste_single_action_remove_header_size_v3, hw_action, start_offset, 0);
+	/* The hardware expects here size in words (2 bytes) */
+	MLX5_SET(ste_single_action_remove_header_size_v3, hw_action, remove_size, 1);
+	used_actions++;
+
+	*used_hw_action_num = used_actions;
+
+	return 0;
+}
+
+static struct mlx5dr_ste_ctx ste_ctx_v3 = {
+	/* Builders */
+	.build_eth_l2_src_dst_init	= &dr_ste_v1_build_eth_l2_src_dst_init,
+	.build_eth_l3_ipv6_src_init	= &dr_ste_v1_build_eth_l3_ipv6_src_init,
+	.build_eth_l3_ipv6_dst_init	= &dr_ste_v1_build_eth_l3_ipv6_dst_init,
+	.build_eth_l3_ipv4_5_tuple_init	= &dr_ste_v1_build_eth_l3_ipv4_5_tuple_init,
+	.build_eth_l2_src_init		= &dr_ste_v1_build_eth_l2_src_init,
+	.build_eth_l2_dst_init		= &dr_ste_v1_build_eth_l2_dst_init,
+	.build_eth_l2_tnl_init		= &dr_ste_v1_build_eth_l2_tnl_init,
+	.build_eth_l3_ipv4_misc_init	= &dr_ste_v1_build_eth_l3_ipv4_misc_init,
+	.build_eth_ipv6_l3_l4_init	= &dr_ste_v1_build_eth_ipv6_l3_l4_init,
+	.build_mpls_init		= &dr_ste_v1_build_mpls_init,
+	.build_tnl_gre_init		= &dr_ste_v1_build_tnl_gre_init,
+	.build_tnl_mpls_init		= &dr_ste_v1_build_tnl_mpls_init,
+	.build_tnl_mpls_over_udp_init	= &dr_ste_v1_build_tnl_mpls_over_udp_init,
+	.build_tnl_mpls_over_gre_init	= &dr_ste_v1_build_tnl_mpls_over_gre_init,
+	.build_icmp_init		= &dr_ste_v1_build_icmp_init,
+	.build_general_purpose_init	= &dr_ste_v1_build_general_purpose_init,
+	.build_eth_l4_misc_init		= &dr_ste_v1_build_eth_l4_misc_init,
+	.build_tnl_vxlan_gpe_init	= &dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_init,
+	.build_tnl_geneve_init		= &dr_ste_v1_build_flex_parser_tnl_geneve_init,
+	.build_tnl_geneve_tlv_opt_init	= &dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_init,
+	.build_tnl_geneve_tlv_opt_exist_init =
+				  &dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_exist_init,
+	.build_register_0_init		= &dr_ste_v1_build_register_0_init,
+	.build_register_1_init		= &dr_ste_v1_build_register_1_init,
+	.build_src_gvmi_qpn_init	= &dr_ste_v1_build_src_gvmi_qpn_init,
+	.build_flex_parser_0_init	= &dr_ste_v1_build_flex_parser_0_init,
+	.build_flex_parser_1_init	= &dr_ste_v1_build_flex_parser_1_init,
+	.build_tnl_gtpu_init		= &dr_ste_v1_build_flex_parser_tnl_gtpu_init,
+	.build_tnl_header_0_1_init	= &dr_ste_v1_build_tnl_header_0_1_init,
+	.build_tnl_gtpu_flex_parser_0_init = &dr_ste_v1_build_tnl_gtpu_flex_parser_0_init,
+	.build_tnl_gtpu_flex_parser_1_init = &dr_ste_v1_build_tnl_gtpu_flex_parser_1_init,
+
+	/* Getters and Setters */
+	.ste_init			= &dr_ste_v1_init,
+	.set_next_lu_type		= &dr_ste_v1_set_next_lu_type,
+	.get_next_lu_type		= &dr_ste_v1_get_next_lu_type,
+	.is_miss_addr_set		= &dr_ste_v1_is_miss_addr_set,
+	.set_miss_addr			= &dr_ste_v1_set_miss_addr,
+	.get_miss_addr			= &dr_ste_v1_get_miss_addr,
+	.set_hit_addr			= &dr_ste_v1_set_hit_addr,
+	.set_byte_mask			= &dr_ste_v1_set_byte_mask,
+	.get_byte_mask			= &dr_ste_v1_get_byte_mask,
+
+	/* Actions */
+	.actions_caps			= DR_STE_CTX_ACTION_CAP_TX_POP |
+					  DR_STE_CTX_ACTION_CAP_RX_PUSH |
+					  DR_STE_CTX_ACTION_CAP_RX_ENCAP,
+	.set_actions_rx			= &dr_ste_v1_set_actions_rx,
+	.set_actions_tx			= &dr_ste_v1_set_actions_tx,
+	.modify_field_arr_sz		= ARRAY_SIZE(dr_ste_v2_action_modify_field_arr),
+	.modify_field_arr		= dr_ste_v2_action_modify_field_arr,
+	.set_action_set			= &dr_ste_v1_set_action_set,
+	.set_action_add			= &dr_ste_v1_set_action_add,
+	.set_action_copy		= &dr_ste_v1_set_action_copy,
+	.set_action_decap_l3_list	= &dr_ste_v3_set_action_decap_l3_list,
+	.alloc_modify_hdr_chunk		= &dr_ste_v1_alloc_modify_hdr_ptrn_arg,
+	.dealloc_modify_hdr_chunk	= &dr_ste_v1_free_modify_hdr_ptrn_arg,
+	/* Actions bit set */
+	.set_encap			= &dr_ste_v3_set_encap,
+	.set_push_vlan			= &dr_ste_v3_set_push_vlan,
+	.set_pop_vlan			= &dr_ste_v3_set_pop_vlan,
+	.set_rx_decap			= &dr_ste_v3_set_rx_decap,
+	.set_encap_l3			= &dr_ste_v3_set_encap_l3,
+	.set_insert_hdr			= &dr_ste_v3_set_insert_hdr,
+	.set_remove_hdr			= &dr_ste_v3_set_remove_hdr,
+	/* Send */
+	.prepare_for_postsend		= &dr_ste_v1_prepare_for_postsend,
+};
+
+struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v3(void)
+{
+	return &ste_ctx_v3;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h
index 7618c6147f86..cc328292bf84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h
@@ -1473,7 +1473,6 @@ struct mlx5dr_send_ring {
 int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn);
 void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn,
 			   struct mlx5dr_send_ring *send_ring);
-int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn);
 int mlx5dr_send_postsend_ste(struct mlx5dr_domain *dmn,
 			     struct mlx5dr_ste *ste,
 			     u8 *data,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c
index 8007d3f523c9..f367997ab61e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c
@@ -833,15 +833,21 @@ static u32 mlx5_cmd_dr_get_capabilities(struct mlx5_flow_root_namespace *ns,
 	return steering_caps;
 }
 
-int mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat)
+int
+mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				      u32 *reformat_id)
 {
+	struct mlx5dr_action *dr_action;
+
 	switch (pkt_reformat->reformat_type) {
 	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
 	case MLX5_REFORMAT_TYPE_L2_TO_NVGRE:
 	case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL:
 	case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
 	case MLX5_REFORMAT_TYPE_INSERT_HDR:
-		return mlx5dr_action_get_pkt_reformat_id(pkt_reformat->fs_dr_action.dr_action);
+		dr_action = pkt_reformat->fs_dr_action.dr_action;
+		*reformat_id = mlx5dr_action_get_pkt_reformat_id(dr_action);
+		return 0;
 	}
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h
index 99a3b2eff6b8..f869f2daefbf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h
@@ -38,7 +38,9 @@ struct mlx5_fs_dr_table {
 
 bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev);
 
-int mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat);
+int
+mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				      u32 *reformat_id);
 
 const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void);
 
@@ -49,9 +51,11 @@ static inline const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void)
 	return NULL;
 }
 
-static inline u32 mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat)
+static inline int
+mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				      u32 *reformat_id)
 {
-	return 0;
+	return -EOPNOTSUPP;
 }
 
 static inline bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h
index fb078fa0f0cc..898c3618ff26 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h
@@ -600,4 +600,44 @@ struct mlx5_ifc_ste_double_action_aso_v1_bits {
 	};
 };
 
+struct mlx5_ifc_ste_single_action_remove_header_v3_bits {
+	u8         action_id[0x8];
+	u8         start_anchor[0x7];
+	u8         end_anchor[0x7];
+	u8         reserved_at_16[0x1];
+	u8         outer_l4_remove[0x1];
+	u8         reserved_at_18[0x4];
+	u8         decap[0x1];
+	u8         vni_to_cqe[0x1];
+	u8         qos_profile[0x2];
+};
+
+struct mlx5_ifc_ste_single_action_remove_header_size_v3_bits {
+	u8         action_id[0x8];
+	u8         start_anchor[0x7];
+	u8         start_offset[0x8];
+	u8         outer_l4_remove[0x1];
+	u8         reserved_at_18[0x2];
+	u8         remove_size[0x6];
+};
+
+struct mlx5_ifc_ste_double_action_insert_with_inline_v3_bits {
+	u8         action_id[0x8];
+	u8         start_anchor[0x7];
+	u8         start_offset[0x8];
+	u8         reserved_at_17[0x9];
+
+	u8         inline_data[0x20];
+};
+
+struct mlx5_ifc_ste_double_action_insert_with_ptr_v3_bits {
+	u8         action_id[0x8];
+	u8         start_anchor[0x7];
+	u8         start_offset[0x8];
+	u8         size[0x6];
+	u8         attributes[0x3];
+
+	u8         pointer[0x20];
+};
+
 #endif /* MLX5_IFC_DR_H */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h
index 3ac7dc67509f..fc8a2169d1a1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h
@@ -45,8 +45,6 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type);
 
 int mlx5dr_domain_destroy(struct mlx5dr_domain *domain);
 
-int mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags);
-
 void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
 			    struct mlx5dr_domain *peer_dmn,
 			    u16 peer_vhca_id);
@@ -160,7 +158,7 @@ mlx5dr_is_supported(struct mlx5_core_dev *dev)
 	       (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) ||
 		(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) &&
 		 (MLX5_CAP_GEN(dev, steering_format_version) <=
-		  MLX5_STEERING_FORMAT_CONNECTX_7)));
+		  MLX5_STEERING_FORMAT_CONNECTX_8)));
 }
 
 /* buddy functions & structure */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 0d5f750faa45..306affbcfd3b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -36,6 +36,7 @@
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/eswitch.h>
 #include "mlx5_core.h"
+#include "eswitch.h"
 #include "sf/sf.h"
 
 /* Mutex to hold while enabling or disabling RoCE */
@@ -77,15 +78,14 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 }
 
 static int mlx5_query_nic_vport_context(struct mlx5_core_dev *mdev, u16 vport,
-					u32 *out)
+					bool other_vport, u32 *out)
 {
 	u32 in[MLX5_ST_SZ_DW(query_nic_vport_context_in)] = {};
 
 	MLX5_SET(query_nic_vport_context_in, in, opcode,
 		 MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT);
 	MLX5_SET(query_nic_vport_context_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(query_nic_vport_context_in, in, other_vport, 1);
+	MLX5_SET(query_nic_vport_context_in, in, other_vport, other_vport);
 
 	return mlx5_cmd_exec_inout(mdev, query_nic_vport_context, in, out);
 }
@@ -96,7 +96,7 @@ int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev,
 	u32 out[MLX5_ST_SZ_DW(query_nic_vport_context_out)] = {};
 	int err;
 
-	err = mlx5_query_nic_vport_context(mdev, vport, out);
+	err = mlx5_query_nic_vport_context(mdev, vport, vport > 0, out);
 	if (!err)
 		*min_inline = MLX5_GET(query_nic_vport_context_out, out,
 				       nic_vport_context.min_wqe_inline_mode);
@@ -218,7 +218,7 @@ int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu)
 	if (!out)
 		return -ENOMEM;
 
-	err = mlx5_query_nic_vport_context(mdev, 0, out);
+	err = mlx5_query_nic_vport_context(mdev, 0, false, out);
 	if (!err)
 		*mtu = MLX5_GET(query_nic_vport_context_out, out,
 				nic_vport_context.mtu);
@@ -428,7 +428,7 @@ int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
 	if (!out)
 		return -ENOMEM;
 
-	err = mlx5_query_nic_vport_context(mdev, 0, out);
+	err = mlx5_query_nic_vport_context(mdev, 0, false, out);
 	if (err)
 		goto out;
 
@@ -450,7 +450,7 @@ int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group)
 	if (!out)
 		return -ENOMEM;
 
-	err = mlx5_query_nic_vport_context(mdev, 0, out);
+	err = mlx5_query_nic_vport_context(mdev, 0, false, out);
 	if (err)
 		goto out;
 
@@ -461,23 +461,27 @@ out:
 	return err;
 }
 
-int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
+int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev,
+				   u16 vport, bool other_vport, u64 *node_guid)
 {
 	u32 *out;
 	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	int err;
 
 	out = kvzalloc(outlen, GFP_KERNEL);
 	if (!out)
 		return -ENOMEM;
 
-	mlx5_query_nic_vport_context(mdev, 0, out);
+	err = mlx5_query_nic_vport_context(mdev, vport, other_vport, out);
+	if (err)
+		goto out;
 
 	*node_guid = MLX5_GET64(query_nic_vport_context_out, out,
 				nic_vport_context.node_guid);
-
+out:
 	kvfree(out);
 
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_node_guid);
 
@@ -519,19 +523,22 @@ int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
 {
 	u32 *out;
 	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	int err;
 
 	out = kvzalloc(outlen, GFP_KERNEL);
 	if (!out)
 		return -ENOMEM;
 
-	mlx5_query_nic_vport_context(mdev, 0, out);
+	err = mlx5_query_nic_vport_context(mdev, 0, false, out);
+	if (err)
+		goto out;
 
 	*qkey_viol_cntr = MLX5_GET(query_nic_vport_context_out, out,
 				   nic_vport_context.qkey_violation_counter);
-
+out:
 	kvfree(out);
 
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_qkey_viol_cntr);
 
@@ -797,7 +804,7 @@ int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev,
 	if (!out)
 		return -ENOMEM;
 
-	err = mlx5_query_nic_vport_context(mdev, vport, out);
+	err = mlx5_query_nic_vport_context(mdev, vport, vport > 0, out);
 	if (err)
 		goto out;
 
@@ -901,7 +908,7 @@ int mlx5_nic_vport_query_local_lb(struct mlx5_core_dev *mdev, bool *status)
 	if (!out)
 		return -ENOMEM;
 
-	err = mlx5_query_nic_vport_context(mdev, 0, out);
+	err = mlx5_query_nic_vport_context(mdev, 0, false, out);
 	if (err)
 		goto out;
 
@@ -1183,27 +1190,101 @@ u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev)
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid);
 
+void mlx5_query_nic_sw_system_image_guid(struct mlx5_core_dev *mdev, u8 *buf,
+					 u8 *len)
+{
+	u64 fw_system_image_guid;
+
+	*len = 0;
+
+	fw_system_image_guid = mlx5_query_nic_system_image_guid(mdev);
+	if (!fw_system_image_guid)
+		return;
+
+	memcpy(buf, &fw_system_image_guid, sizeof(fw_system_image_guid));
+	*len += sizeof(fw_system_image_guid);
+
+	if (MLX5_CAP_GEN_2(mdev, load_balance_id) &&
+	    MLX5_CAP_GEN_2(mdev, lag_per_mp_group))
+		buf[(*len)++] = MLX5_CAP_GEN_2(mdev, load_balance_id);
+}
+
+static bool mlx5_vport_use_vhca_id_as_func_id(struct mlx5_core_dev *dev,
+					      u16 vport_num, u16 *vhca_id)
+{
+	if (!MLX5_CAP_GEN_2(dev, function_id_type_vhca_id))
+		return false;
+
+	return mlx5_esw_vport_vhca_id(dev->priv.eswitch, vport_num, vhca_id);
+}
+
 int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 vport, void *out,
 				  u16 opmod)
 {
-	bool ec_vf_func = mlx5_core_is_ec_vf_vport(dev, vport);
 	u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)] = {};
+	u16 vhca_id = 0, function_id = 0;
+	bool ec_vf_func = false;
+
+	/* if this vport is referring to a vport on the ec PF (embedded cpu )
+	 * let the FW know which domain we are querying since vport numbers or
+	 * function_ids are not unique across the different PF domains,
+	 * unless we use vhca_id as the function_id below.
+	 */
+	ec_vf_func = mlx5_core_is_ec_vf_vport(dev, vport);
+	function_id = mlx5_vport_to_func_id(dev, vport, ec_vf_func);
+
+	if (mlx5_vport_use_vhca_id_as_func_id(dev, vport, &vhca_id)) {
+		MLX5_SET(query_hca_cap_in, in, function_id_type, 1);
+		function_id = vhca_id;
+		ec_vf_func = false;
+		mlx5_core_dbg(dev, "%s using vhca_id as function_id for vport %d vhca_id 0x%x\n",
+			      __func__, vport, vhca_id);
+	}
 
 	opmod = (opmod << 1) | (HCA_CAP_OPMOD_GET_MAX & 0x01);
 	MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
 	MLX5_SET(query_hca_cap_in, in, op_mod, opmod);
-	MLX5_SET(query_hca_cap_in, in, function_id, mlx5_vport_to_func_id(dev, vport, ec_vf_func));
 	MLX5_SET(query_hca_cap_in, in, other_function, true);
 	MLX5_SET(query_hca_cap_in, in, ec_vf_function, ec_vf_func);
+	MLX5_SET(query_hca_cap_in, in, function_id, function_id);
 	return mlx5_cmd_exec_inout(dev, query_hca_cap, in, out);
 }
 EXPORT_SYMBOL_GPL(mlx5_vport_get_other_func_cap);
 
+int mlx5_vport_get_vhca_id(struct mlx5_core_dev *dev, u16 vport, u16 *vhca_id)
+{
+	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	void *query_ctx;
+	void *hca_caps;
+	int err;
+
+	/* try get vhca_id via eswitch */
+	if (mlx5_esw_vport_vhca_id(dev->priv.eswitch, vport, vhca_id))
+		return 0;
+
+	query_ctx = kzalloc(query_out_sz, GFP_KERNEL);
+	if (!query_ctx)
+		return -ENOMEM;
+
+	err = mlx5_vport_get_other_func_general_cap(dev, vport, query_ctx);
+	if (err)
+		goto out_free;
+
+	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
+	*vhca_id = MLX5_GET(cmd_hca_cap, hca_caps, vhca_id);
+
+out_free:
+	kfree(query_ctx);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_vport_get_vhca_id);
+
 int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap,
 				  u16 vport, u16 opmod)
 {
-	bool ec_vf_func = mlx5_core_is_ec_vf_vport(dev, vport);
 	int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
+	u16 vhca_id = 0, function_id = 0;
+	bool ec_vf_func = false;
 	void *set_hca_cap;
 	void *set_ctx;
 	int ret;
@@ -1212,14 +1293,29 @@ int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap
 	if (!set_ctx)
 		return -ENOMEM;
 
+	/* if this vport is referring to a vport on the ec PF (embedded cpu )
+	 * let the FW know which domain we are querying since vport numbers or
+	 * function_ids are not unique across the different PF domains,
+	 * unless we use vhca_id as the function_id below.
+	 */
+	ec_vf_func = mlx5_core_is_ec_vf_vport(dev, vport);
+	function_id = mlx5_vport_to_func_id(dev, vport, ec_vf_func);
+
+	if (mlx5_vport_use_vhca_id_as_func_id(dev, vport, &vhca_id)) {
+		MLX5_SET(set_hca_cap_in, set_ctx, function_id_type, 1);
+		function_id = vhca_id;
+		ec_vf_func = false;
+		mlx5_core_dbg(dev, "%s using vhca_id as function_id for vport %d vhca_id 0x%x\n",
+			      __func__, vport, vhca_id);
+	}
+
 	MLX5_SET(set_hca_cap_in, set_ctx, opcode, MLX5_CMD_OP_SET_HCA_CAP);
 	MLX5_SET(set_hca_cap_in, set_ctx, op_mod, opmod << 1);
 	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability);
 	memcpy(set_hca_cap, hca_cap, MLX5_ST_SZ_BYTES(cmd_hca_cap));
-	MLX5_SET(set_hca_cap_in, set_ctx, function_id,
-		 mlx5_vport_to_func_id(dev, vport, ec_vf_func));
 	MLX5_SET(set_hca_cap_in, set_ctx, other_function, true);
 	MLX5_SET(set_hca_cap_in, set_ctx, ec_vf_function, ec_vf_func);
+	MLX5_SET(set_hca_cap_in, set_ctx, function_id, function_id);
 	ret = mlx5_cmd_exec_in(dev, set_hca_cap, set_ctx);
 
 	kfree(set_ctx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wc.c b/drivers/net/ethernet/mellanox/mlx5/core/wc.c
index 1bed75eca97d..815a7c97d6b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wc.c
@@ -7,6 +7,11 @@
 #include "mlx5_core.h"
 #include "wq.h"
 
+#if IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && IS_ENABLED(CONFIG_ARM64)
+#include <asm/neon.h>
+#include <asm/simd.h>
+#endif
+
 #define TEST_WC_NUM_WQES 255
 #define TEST_WC_LOG_CQ_SZ (order_base_2(TEST_WC_NUM_WQES))
 #define TEST_WC_SQ_LOG_WQ_SZ TEST_WC_LOG_CQ_SZ
@@ -94,7 +99,7 @@ static int create_wc_cq(struct mlx5_wc_cq *cq, void *cqc_data)
 
 	MLX5_SET(cqc,   cqc, cq_period_mode, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
 	MLX5_SET(cqc,   cqc, c_eqn_or_apu_element, eqn);
-	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.uar->index);
+	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.bfreg.up->index);
 	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
 					    MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(cqc, cqc, dbr_addr,      cq->wq_ctrl.db.dma);
@@ -116,7 +121,7 @@ static int mlx5_wc_create_cq(struct mlx5_core_dev *mdev, struct mlx5_wc_cq *cq)
 		return -ENOMEM;
 
 	MLX5_SET(cqc, cqc, log_cq_size, TEST_WC_LOG_CQ_SZ);
-	MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index);
+	MLX5_SET(cqc, cqc, uar_page, mdev->priv.bfreg.up->index);
 	if (MLX5_CAP_GEN(mdev, cqe_128_always) && cache_line_size() >= 128)
 		MLX5_SET(cqc, cqc, cqe_sz, CQE_STRIDE_128_PAD);
 
@@ -255,7 +260,29 @@ static void mlx5_wc_destroy_sq(struct mlx5_wc_sq *sq)
 	mlx5_wq_destroy(&sq->wq_ctrl);
 }
 
-static void mlx5_wc_post_nop(struct mlx5_wc_sq *sq, bool signaled)
+static void mlx5_iowrite64_copy(struct mlx5_wc_sq *sq, __be32 mmio_wqe[16],
+				size_t mmio_wqe_size, unsigned int offset)
+{
+#if IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && IS_ENABLED(CONFIG_ARM64)
+	if (cpu_has_neon()) {
+		scoped_ksimd() {
+			asm volatile(
+				".arch_extension simd\n\t"
+				"ld1 {v0.16b, v1.16b, v2.16b, v3.16b}, [%0]\n\t"
+				"st1 {v0.16b, v1.16b, v2.16b, v3.16b}, [%1]"
+				:
+				: "r"(mmio_wqe), "r"(sq->bfreg.map + offset)
+				: "memory", "v0", "v1", "v2", "v3");
+		}
+		return;
+	}
+#endif
+	__iowrite64_copy(sq->bfreg.map + offset, mmio_wqe,
+			 mmio_wqe_size / 8);
+}
+
+static void mlx5_wc_post_nop(struct mlx5_wc_sq *sq, unsigned int *offset,
+			     bool signaled)
 {
 	int buf_size = (1 << MLX5_CAP_GEN(sq->cq.mdev, log_bf_reg_size)) / 2;
 	struct mlx5_wqe_ctrl_seg *ctrl;
@@ -288,10 +315,9 @@ static void mlx5_wc_post_nop(struct mlx5_wc_sq *sq, bool signaled)
 	 */
 	wmb();
 
-	__iowrite64_copy(sq->bfreg.map + sq->bfreg.offset, mmio_wqe,
-			 sizeof(mmio_wqe) / 8);
+	mlx5_iowrite64_copy(sq, mmio_wqe, sizeof(mmio_wqe), *offset);
 
-	sq->bfreg.offset ^= buf_size;
+	*offset ^= buf_size;
 }
 
 static int mlx5_wc_poll_cq(struct mlx5_wc_sq *sq)
@@ -332,6 +358,7 @@ static int mlx5_wc_poll_cq(struct mlx5_wc_sq *sq)
 
 static void mlx5_core_test_wc(struct mlx5_core_dev *mdev)
 {
+	unsigned int offset = 0;
 	unsigned long expires;
 	struct mlx5_wc_sq *sq;
 	int i, err;
@@ -358,9 +385,9 @@ static void mlx5_core_test_wc(struct mlx5_core_dev *mdev)
 		goto err_create_sq;
 
 	for (i = 0; i < TEST_WC_NUM_WQES - 1; i++)
-		mlx5_wc_post_nop(sq, false);
+		mlx5_wc_post_nop(sq, &offset, false);
 
-	mlx5_wc_post_nop(sq, true);
+	mlx5_wc_post_nop(sq, &offset, true);
 
 	expires = jiffies + TEST_WC_POLLING_MAX_TIME_JIFFIES;
 	do {
@@ -378,10 +405,14 @@ err_create_cq:
 	mlx5_free_bfreg(mdev, &sq->bfreg);
 err_alloc_bfreg:
 	kfree(sq);
+
+	if (mdev->wc_state == MLX5_WC_STATE_UNSUPPORTED)
+		mlx5_core_warn(mdev, "Write combining is not supported\n");
 }
 
 bool mlx5_wc_support_get(struct mlx5_core_dev *mdev)
 {
+	struct mutex *wc_state_lock = &mdev->wc_state_lock;
 	struct mlx5_core_dev *parent = NULL;
 
 	if (!MLX5_CAP_GEN(mdev, bf)) {
@@ -400,32 +431,31 @@ bool mlx5_wc_support_get(struct mlx5_core_dev *mdev)
 		 */
 		goto out;
 
-	mutex_lock(&mdev->wc_state_lock);
-
-	if (mdev->wc_state != MLX5_WC_STATE_UNINITIALIZED)
-		goto unlock;
-
 #ifdef CONFIG_MLX5_SF
-	if (mlx5_core_is_sf(mdev))
+	if (mlx5_core_is_sf(mdev)) {
 		parent = mdev->priv.parent_mdev;
+		wc_state_lock = &parent->wc_state_lock;
+	}
 #endif
 
-	if (parent) {
-		mutex_lock(&parent->wc_state_lock);
+	mutex_lock(wc_state_lock);
 
+	if (mdev->wc_state != MLX5_WC_STATE_UNINITIALIZED)
+		goto unlock;
+
+	if (parent) {
 		mlx5_core_test_wc(parent);
 
 		mlx5_core_dbg(mdev, "parent set wc_state=%d\n",
 			      parent->wc_state);
 		mdev->wc_state = parent->wc_state;
 
-		mutex_unlock(&parent->wc_state_lock);
+	} else {
+		mlx5_core_test_wc(mdev);
 	}
 
-	mlx5_core_test_wc(mdev);
-
 unlock:
-	mutex_unlock(&mdev->wc_state_lock);
+	mutex_unlock(wc_state_lock);
 out:
 	mlx5_core_dbg(mdev, "wc_state=%d\n", mdev->wc_state);
 
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
index fb2e5b844c15..d1f8a72cae53 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
@@ -142,8 +142,10 @@ static int mlxbf_gige_open(struct net_device *netdev)
 
 	mlxbf_gige_cache_stats(priv);
 	err = mlxbf_gige_clean_port(priv);
-	if (err)
+	if (err) {
+		dev_err(priv->dev, "open: clean_port failed: %pe\n", ERR_PTR(err));
 		return err;
+	}
 
 	/* Clear driver's valid_polarity to match hardware,
 	 * since the above call to clean_port() resets the
@@ -154,19 +156,25 @@ static int mlxbf_gige_open(struct net_device *netdev)
 	phy_start(phydev);
 
 	err = mlxbf_gige_tx_init(priv);
-	if (err)
+	if (err) {
+		dev_err(priv->dev, "open: tx_init failed: %pe\n", ERR_PTR(err));
 		goto phy_deinit;
+	}
 	err = mlxbf_gige_rx_init(priv);
-	if (err)
+	if (err) {
+		dev_err(priv->dev, "open: rx_init failed: %pe\n", ERR_PTR(err));
 		goto tx_deinit;
+	}
 
 	netif_napi_add(netdev, &priv->napi, mlxbf_gige_poll);
 	napi_enable(&priv->napi);
 	netif_start_queue(netdev);
 
 	err = mlxbf_gige_request_irqs(priv);
-	if (err)
+	if (err) {
+		dev_err(priv->dev, "open: request_irqs failed: %pe\n", ERR_PTR(err));
 		goto napi_deinit;
+	}
 
 	mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_BCAST_MAC_FILTER_IDX);
 	mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_LOCAL_MAC_FILTER_IDX);
@@ -418,8 +426,10 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
 
 	/* Attach MDIO device */
 	err = mlxbf_gige_mdio_probe(pdev, priv);
-	if (err)
+	if (err) {
+		dev_err(priv->dev, "probe: mdio_probe failed: %pe\n", ERR_PTR(err));
 		return err;
+	}
 
 	priv->base = base;
 	priv->llu_base = llu_base;
@@ -438,7 +448,7 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
 
 	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (err) {
-		dev_err(&pdev->dev, "DMA configuration failed: 0x%x\n", err);
+		dev_err(&pdev->dev, "DMA configuration failed: %pe\n", ERR_PTR(err));
 		goto out;
 	}
 
@@ -447,8 +457,10 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
 	priv->llu_plu_irq = platform_get_irq(pdev, MLXBF_GIGE_LLU_PLU_INTR_IDX);
 
 	phy_irq = acpi_dev_gpio_irq_get_by(ACPI_COMPANION(&pdev->dev), "phy", 0);
-	if (phy_irq < 0) {
-		dev_err(&pdev->dev, "Error getting PHY irq. Use polling instead");
+	if (phy_irq == -EPROBE_DEFER) {
+		err = -EPROBE_DEFER;
+		goto out;
+	} else if (phy_irq < 0) {
 		phy_irq = PHY_POLL;
 	}
 
@@ -466,7 +478,7 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
 				 mlxbf_gige_link_cfgs[priv->hw_version].adjust_link,
 				 mlxbf_gige_link_cfgs[priv->hw_version].phy_mode);
 	if (err) {
-		dev_err(&pdev->dev, "Could not attach to PHY\n");
+		dev_err(&pdev->dev, "Could not attach to PHY: %pe\n", ERR_PTR(err));
 		goto out;
 	}
 
@@ -477,7 +489,7 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
 
 	err = register_netdev(netdev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to register netdev\n");
+		dev_err(&pdev->dev, "Failed to register netdev: %pe\n", ERR_PTR(err));
 		phy_disconnect(phydev);
 		goto out;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
index 46245e0b2462..43c84900369a 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
@@ -14,7 +14,6 @@
 #define MLXFW_FSM_STATE_WAIT_TIMEOUT_MS 30000
 #define MLXFW_FSM_STATE_WAIT_ROUNDS \
 	(MLXFW_FSM_STATE_WAIT_TIMEOUT_MS / MLXFW_FSM_STATE_WAIT_CYCLE_MS)
-#define MLXFW_FSM_MAX_COMPONENT_SIZE (10 * (1 << 20))
 
 static const int mlxfw_fsm_state_errno[] = {
 	[MLXFW_FSM_STATE_ERR_ERROR] = -EIO,
@@ -229,7 +228,6 @@ static int mlxfw_flash_component(struct mlxfw_dev *mlxfw_dev,
 		return err;
 	}
 
-	comp_max_size = min_t(u32, comp_max_size, MLXFW_FSM_MAX_COMPONENT_SIZE);
 	if (comp->data_size > comp_max_size) {
 		MLXFW_ERR_MSG(mlxfw_dev, extack,
 			      "Component size is bigger than limit", -EINVAL);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 4a79c0d7e7ad..83c7cf3bbea3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -35,6 +35,7 @@
 #include "reg.h"
 #include "resources.h"
 #include "../mlxfw/mlxfw.h"
+#include "txheader.h"
 
 static LIST_HEAD(mlxsw_core_driver_list);
 static DEFINE_SPINLOCK(mlxsw_core_driver_list_lock);
@@ -677,7 +678,7 @@ struct mlxsw_reg_trans {
 	struct list_head bulk_list;
 	struct mlxsw_core *core;
 	struct sk_buff *tx_skb;
-	struct mlxsw_tx_info tx_info;
+	struct mlxsw_txhdr_info txhdr_info;
 	struct delayed_work timeout_dw;
 	unsigned int retries;
 	u64 tid;
@@ -737,12 +738,11 @@ static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core,
 	if (!skb)
 		return -ENOMEM;
 
-	trace_devlink_hwmsg(priv_to_devlink(mlxsw_core), false, 0,
-			    skb->data + mlxsw_core->driver->txhdr_len,
-			    skb->len - mlxsw_core->driver->txhdr_len);
+	trace_devlink_hwmsg(priv_to_devlink(mlxsw_core), false, 0, skb->data,
+			    skb->len);
 
 	atomic_set(&trans->active, 1);
-	err = mlxsw_core_skb_transmit(mlxsw_core, skb, &trans->tx_info);
+	err = mlxsw_core_skb_transmit(mlxsw_core, skb, &trans->txhdr_info);
 	if (err) {
 		dev_kfree_skb(skb);
 		return err;
@@ -886,7 +886,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 	if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX))
 		return 0;
 
-	emad_wq = alloc_workqueue("mlxsw_core_emad", 0, 0);
+	emad_wq = alloc_workqueue("mlxsw_core_emad", WQ_PERCPU, 0);
 	if (!emad_wq)
 		return -ENOMEM;
 	mlxsw_core->emad_wq = emad_wq;
@@ -944,7 +944,7 @@ static struct sk_buff *mlxsw_emad_alloc(const struct mlxsw_core *mlxsw_core,
 
 	emad_len = (reg_len + sizeof(u32) + MLXSW_EMAD_ETH_HDR_LEN +
 		    (MLXSW_EMAD_OP_TLV_LEN + MLXSW_EMAD_END_TLV_LEN) *
-		    sizeof(u32) + mlxsw_core->driver->txhdr_len);
+		    sizeof(u32) + MLXSW_TXHDR_LEN);
 	if (mlxsw_core->emad.enable_string_tlv)
 		emad_len += MLXSW_EMAD_STRING_TLV_LEN * sizeof(u32);
 	if (mlxsw_core->emad.enable_latency_tlv)
@@ -984,8 +984,8 @@ static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core,
 	list_add_tail(&trans->bulk_list, bulk_list);
 	trans->core = mlxsw_core;
 	trans->tx_skb = skb;
-	trans->tx_info.local_port = MLXSW_PORT_CPU_PORT;
-	trans->tx_info.is_emad = true;
+	trans->txhdr_info.tx_info.local_port = MLXSW_PORT_CPU_PORT;
+	trans->txhdr_info.tx_info.is_emad = true;
 	INIT_DELAYED_WORK(&trans->timeout_dw, mlxsw_emad_trans_timeout_work);
 	trans->tid = tid;
 	init_completion(&trans->completion);
@@ -995,7 +995,6 @@ static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core,
 	trans->type = type;
 
 	mlxsw_emad_construct(mlxsw_core, skb, reg, payload, type, trans->tid);
-	mlxsw_core->driver->txhdr_construct(skb, &trans->tx_info);
 
 	spin_lock_bh(&mlxsw_core->emad.trans_list_lock);
 	list_add_tail_rcu(&trans->list, &mlxsw_core->emad.trans_list);
@@ -2044,7 +2043,7 @@ static int mlxsw_core_health_init(struct mlxsw_core *mlxsw_core)
 		return 0;
 
 	fw_fatal = devl_health_reporter_create(devlink, &mlxsw_core_health_fw_fatal_ops,
-					       0, mlxsw_core);
+					       mlxsw_core);
 	if (IS_ERR(fw_fatal)) {
 		dev_err(mlxsw_core->bus_info->dev, "Failed to create fw fatal reporter");
 		return PTR_ERR(fw_fatal);
@@ -2330,10 +2329,10 @@ bool mlxsw_core_skb_transmit_busy(struct mlxsw_core *mlxsw_core,
 EXPORT_SYMBOL(mlxsw_core_skb_transmit_busy);
 
 int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
-			    const struct mlxsw_tx_info *tx_info)
+			    const struct mlxsw_txhdr_info *txhdr_info)
 {
 	return mlxsw_core->bus->skb_transmit(mlxsw_core->bus_priv, skb,
-					     tx_info);
+					     txhdr_info);
 }
 EXPORT_SYMBOL(mlxsw_core_skb_transmit);
 
@@ -3382,7 +3381,7 @@ static int __init mlxsw_core_module_init(void)
 	if (err)
 		return err;
 
-	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, 0, 0);
+	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_PERCPU, 0);
 	if (!mlxsw_wq) {
 		err = -ENOMEM;
 		goto err_alloc_workqueue;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 24c3ff6fcf71..1a871397a6df 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -72,6 +72,12 @@ struct mlxsw_tx_info {
 	bool is_emad;
 };
 
+struct mlxsw_txhdr_info {
+	struct mlxsw_tx_info tx_info;
+	bool data;
+	u16 max_fid; /* Used for PTP packets which are sent as data. */
+};
+
 struct mlxsw_rx_md_info {
 	struct napi_struct *napi;
 	u32 cookie_index;
@@ -95,7 +101,7 @@ struct mlxsw_rx_md_info {
 bool mlxsw_core_skb_transmit_busy(struct mlxsw_core *mlxsw_core,
 				  const struct mlxsw_tx_info *tx_info);
 int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
-			    const struct mlxsw_tx_info *tx_info);
+			    const struct mlxsw_txhdr_info *txhdr_info);
 void mlxsw_core_ptp_transmitted(struct mlxsw_core *mlxsw_core,
 				struct sk_buff *skb, u16 local_port);
 
@@ -426,8 +432,6 @@ struct mlxsw_driver {
 	int (*trap_policer_counter_get)(struct mlxsw_core *mlxsw_core,
 					const struct devlink_trap_policer *policer,
 					u64 *p_drops);
-	void (*txhdr_construct)(struct sk_buff *skb,
-				const struct mlxsw_tx_info *tx_info);
 	int (*resources_register)(struct mlxsw_core *mlxsw_core);
 	int (*kvd_sizes_get)(struct mlxsw_core *mlxsw_core,
 			     const struct mlxsw_config_profile *profile,
@@ -440,7 +444,6 @@ struct mlxsw_driver {
 	void (*ptp_transmitted)(struct mlxsw_core *mlxsw_core,
 				struct sk_buff *skb, u16 local_port);
 
-	u8 txhdr_len;
 	const struct mlxsw_config_profile *profile;
 	bool sdq_supports_cqe_v2;
 };
@@ -487,7 +490,7 @@ struct mlxsw_bus {
 	bool (*skb_transmit_busy)(void *bus_priv,
 				  const struct mlxsw_tx_info *tx_info);
 	int (*skb_transmit)(void *bus_priv, struct sk_buff *skb,
-			    const struct mlxsw_tx_info *tx_info);
+			    const struct mlxsw_txhdr_info *txhdr_info);
 	int (*cmd_exec)(void *bus_priv, u16 opcode, u8 opcode_mod,
 			u32 in_mod, bool out_mbox_direct,
 			char *in_mbox, size_t in_mbox_size,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c b/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c
index b032d5a4b3b8..10f5bc4892fc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c
@@ -601,6 +601,8 @@ int mlxsw_linecard_devlink_info_get(struct mlxsw_linecard *linecard,
 		err = devlink_info_version_fixed_put(req,
 						     DEVLINK_INFO_VERSION_GENERIC_FW_PSID,
 						     info->psid);
+		if (err)
+			goto unlock;
 
 		sprintf(buf, "%u.%u.%u", info->fw_major, info->fw_minor,
 			info->fw_sub_minor);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index e746cd9c68ed..eac9a14a6058 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -205,11 +205,11 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
 	return 0;
 }
 
-static struct thermal_zone_params mlxsw_thermal_params = {
+static const struct thermal_zone_params mlxsw_thermal_params = {
 	.no_hwmon = true,
 };
 
-static struct thermal_zone_device_ops mlxsw_thermal_ops = {
+static const struct thermal_zone_device_ops mlxsw_thermal_ops = {
 	.should_bind = mlxsw_thermal_should_bind,
 	.get_temp = mlxsw_thermal_get_temp,
 };
@@ -252,7 +252,7 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
 	return 0;
 }
 
-static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
+static const struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
 	.should_bind	= mlxsw_thermal_module_should_bind,
 	.get_temp	= mlxsw_thermal_module_temp_get,
 };
@@ -280,7 +280,7 @@ static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
 	return 0;
 }
 
-static struct thermal_zone_device_ops mlxsw_thermal_gearbox_ops = {
+static const struct thermal_zone_device_ops mlxsw_thermal_gearbox_ops = {
 	.should_bind	= mlxsw_thermal_module_should_bind,
 	.get_temp	= mlxsw_thermal_gearbox_temp_get,
 };
diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
index 1e150ce1c73a..f9f565c1036d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
@@ -516,7 +516,7 @@ static bool mlxsw_i2c_skb_transmit_busy(void *bus_priv,
 }
 
 static int mlxsw_i2c_skb_transmit(void *bus_priv, struct sk_buff *skb,
-				  const struct mlxsw_tx_info *tx_info)
+				  const struct mlxsw_txhdr_info *txhdr_info)
 {
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 0863dca2fc0b..8769cba2c746 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -21,6 +21,7 @@
 #include "cmd.h"
 #include "port.h"
 #include "resources.h"
+#include "txheader.h"
 
 #define mlxsw_pci_write32(mlxsw_pci, reg, val) \
 	iowrite32be(val, (mlxsw_pci)->hw_addr + (MLXSW_PCI_ ## reg))
@@ -155,7 +156,7 @@ static int mlxsw_pci_napi_devs_init(struct mlxsw_pci *mlxsw_pci)
 	}
 	strscpy(mlxsw_pci->napi_dev_rx->name, "mlxsw_rx",
 		sizeof(mlxsw_pci->napi_dev_rx->name));
-	dev_set_threaded(mlxsw_pci->napi_dev_rx, true);
+	netif_threaded_enable(mlxsw_pci->napi_dev_rx);
 
 	return 0;
 
@@ -2095,6 +2096,39 @@ static void mlxsw_pci_fini(void *bus_priv)
 	mlxsw_pci_free_irq_vectors(mlxsw_pci);
 }
 
+static int mlxsw_pci_txhdr_construct(struct sk_buff *skb,
+				     const struct mlxsw_txhdr_info *txhdr_info)
+{
+	const struct mlxsw_tx_info tx_info = txhdr_info->tx_info;
+	char *txhdr;
+
+	if (skb_cow_head(skb, MLXSW_TXHDR_LEN))
+		return -ENOMEM;
+
+	txhdr = skb_push(skb, MLXSW_TXHDR_LEN);
+	memset(txhdr, 0, MLXSW_TXHDR_LEN);
+
+	mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1);
+	mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH);
+	mlxsw_tx_hdr_swid_set(txhdr, 0);
+
+	if (unlikely(txhdr_info->data)) {
+		u16 fid = txhdr_info->max_fid + tx_info.local_port - 1;
+
+		mlxsw_tx_hdr_rx_is_router_set(txhdr, true);
+		mlxsw_tx_hdr_fid_valid_set(txhdr, true);
+		mlxsw_tx_hdr_fid_set(txhdr, fid);
+		mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_DATA);
+	} else {
+		mlxsw_tx_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL);
+		mlxsw_tx_hdr_control_tclass_set(txhdr, 1);
+		mlxsw_tx_hdr_port_mid_set(txhdr, tx_info.local_port);
+		mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL);
+	}
+
+	return 0;
+}
+
 static struct mlxsw_pci_queue *
 mlxsw_pci_sdq_pick(struct mlxsw_pci *mlxsw_pci,
 		   const struct mlxsw_tx_info *tx_info)
@@ -2122,7 +2156,7 @@ static bool mlxsw_pci_skb_transmit_busy(void *bus_priv,
 }
 
 static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb,
-				  const struct mlxsw_tx_info *tx_info)
+				  const struct mlxsw_txhdr_info *txhdr_info)
 {
 	struct mlxsw_pci *mlxsw_pci = bus_priv;
 	struct mlxsw_pci_queue *q;
@@ -2131,13 +2165,17 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb,
 	int i;
 	int err;
 
+	err = mlxsw_pci_txhdr_construct(skb, txhdr_info);
+	if (err)
+		return err;
+
 	if (skb_shinfo(skb)->nr_frags > MLXSW_PCI_WQE_SG_ENTRIES - 1) {
 		err = skb_linearize(skb);
 		if (err)
 			return err;
 	}
 
-	q = mlxsw_pci_sdq_pick(mlxsw_pci, tx_info);
+	q = mlxsw_pci_sdq_pick(mlxsw_pci, &txhdr_info->tx_info);
 	spin_lock_bh(&q->lock);
 	elem_info = mlxsw_pci_queue_elem_info_producer_get(q);
 	if (!elem_info) {
@@ -2145,7 +2183,7 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb,
 		err = -EAGAIN;
 		goto unlock;
 	}
-	mlxsw_skb_cb(skb)->tx_info = *tx_info;
+	mlxsw_skb_cb(skb)->tx_info = txhdr_info->tx_info;
 	elem_info->sdq.skb = skb;
 
 	wqe = elem_info->elem;
@@ -2176,6 +2214,8 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb,
 	for (i++; i < MLXSW_PCI_WQE_SG_ENTRIES; i++)
 		mlxsw_pci_wqe_byte_count_set(wqe, i, 0);
 
+	mlxsw_pci_wqe_ipcs_set(wqe, skb->ip_summed == CHECKSUM_PARTIAL);
+
 	/* Everything is set up, ring producer doorbell to get HW going */
 	q->producer_counter++;
 	mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index 6bed495dcf0f..7fa94e5828de 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -90,6 +90,11 @@ MLXSW_ITEM32(pci, wqe, lp, 0x00, 30, 1);
  */
 MLXSW_ITEM32(pci, wqe, type, 0x00, 23, 4);
 
+/* pci_wqe_ipcs
+ * Calculate IPv4 and TCP / UDP checksums.
+ */
+MLXSW_ITEM32(pci, wqe, ipcs, 0x00, 14, 1);
+
 /* pci_wqe_byte_count
  * Size of i-th scatter/gather entry, 0 if entry is unused.
  */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index aa71993daf28..9a2d64a0a858 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -107,74 +107,6 @@ static const unsigned char mlxsw_sp2_mac_mask[ETH_ALEN] = {
 	0xff, 0xff, 0xff, 0xff, 0xf0, 0x00
 };
 
-/* tx_hdr_version
- * Tx header version.
- * Must be set to 1.
- */
-MLXSW_ITEM32(tx, hdr, version, 0x00, 28, 4);
-
-/* tx_hdr_ctl
- * Packet control type.
- * 0 - Ethernet control (e.g. EMADs, LACP)
- * 1 - Ethernet data
- */
-MLXSW_ITEM32(tx, hdr, ctl, 0x00, 26, 2);
-
-/* tx_hdr_proto
- * Packet protocol type. Must be set to 1 (Ethernet).
- */
-MLXSW_ITEM32(tx, hdr, proto, 0x00, 21, 3);
-
-/* tx_hdr_rx_is_router
- * Packet is sent from the router. Valid for data packets only.
- */
-MLXSW_ITEM32(tx, hdr, rx_is_router, 0x00, 19, 1);
-
-/* tx_hdr_fid_valid
- * Indicates if the 'fid' field is valid and should be used for
- * forwarding lookup. Valid for data packets only.
- */
-MLXSW_ITEM32(tx, hdr, fid_valid, 0x00, 16, 1);
-
-/* tx_hdr_swid
- * Switch partition ID. Must be set to 0.
- */
-MLXSW_ITEM32(tx, hdr, swid, 0x00, 12, 3);
-
-/* tx_hdr_control_tclass
- * Indicates if the packet should use the control TClass and not one
- * of the data TClasses.
- */
-MLXSW_ITEM32(tx, hdr, control_tclass, 0x00, 6, 1);
-
-/* tx_hdr_etclass
- * Egress TClass to be used on the egress device on the egress port.
- */
-MLXSW_ITEM32(tx, hdr, etclass, 0x00, 0, 4);
-
-/* tx_hdr_port_mid
- * Destination local port for unicast packets.
- * Destination multicast ID for multicast packets.
- *
- * Control packets are directed to a specific egress port, while data
- * packets are transmitted through the CPU port (0) into the switch partition,
- * where forwarding rules are applied.
- */
-MLXSW_ITEM32(tx, hdr, port_mid, 0x04, 16, 16);
-
-/* tx_hdr_fid
- * Forwarding ID used for L2 forwarding lookup. Valid only if 'fid_valid' is
- * set, otherwise calculated based on the packet's VID using VID to FID mapping.
- * Valid for data packets only.
- */
-MLXSW_ITEM32(tx, hdr, fid, 0x08, 16, 16);
-
-/* tx_hdr_type
- * 0 - Data packets
- * 6 - Control packets
- */
-MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4);
-
 int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
 			      unsigned int counter_index, bool clear,
 			      u64 *packets, u64 *bytes)
@@ -233,61 +165,6 @@ void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp,
 			       counter_index);
 }
 
-void mlxsw_sp_txhdr_construct(struct sk_buff *skb,
-			      const struct mlxsw_tx_info *tx_info)
-{
-	char *txhdr = skb_push(skb, MLXSW_TXHDR_LEN);
-
-	memset(txhdr, 0, MLXSW_TXHDR_LEN);
-
-	mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1);
-	mlxsw_tx_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL);
-	mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH);
-	mlxsw_tx_hdr_swid_set(txhdr, 0);
-	mlxsw_tx_hdr_control_tclass_set(txhdr, 1);
-	mlxsw_tx_hdr_port_mid_set(txhdr, tx_info->local_port);
-	mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL);
-}
-
-int
-mlxsw_sp_txhdr_ptp_data_construct(struct mlxsw_core *mlxsw_core,
-				  struct mlxsw_sp_port *mlxsw_sp_port,
-				  struct sk_buff *skb,
-				  const struct mlxsw_tx_info *tx_info)
-{
-	char *txhdr;
-	u16 max_fid;
-	int err;
-
-	if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) {
-		err = -ENOMEM;
-		goto err_skb_cow_head;
-	}
-
-	if (!MLXSW_CORE_RES_VALID(mlxsw_core, FID)) {
-		err = -EIO;
-		goto err_res_valid;
-	}
-	max_fid = MLXSW_CORE_RES_GET(mlxsw_core, FID);
-
-	txhdr = skb_push(skb, MLXSW_TXHDR_LEN);
-	memset(txhdr, 0, MLXSW_TXHDR_LEN);
-
-	mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1);
-	mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH);
-	mlxsw_tx_hdr_rx_is_router_set(txhdr, true);
-	mlxsw_tx_hdr_fid_valid_set(txhdr, true);
-	mlxsw_tx_hdr_fid_set(txhdr, max_fid + tx_info->local_port - 1);
-	mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_DATA);
-	return 0;
-
-err_res_valid:
-err_skb_cow_head:
-	this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
-	dev_kfree_skb_any(skb);
-	return err;
-}
-
 static bool mlxsw_sp_skb_requires_ts(struct sk_buff *skb)
 {
 	unsigned int type;
@@ -299,30 +176,49 @@ static bool mlxsw_sp_skb_requires_ts(struct sk_buff *skb)
 	return !!ptp_parse_header(skb, type);
 }
 
-static int mlxsw_sp_txhdr_handle(struct mlxsw_core *mlxsw_core,
-				 struct mlxsw_sp_port *mlxsw_sp_port,
-				 struct sk_buff *skb,
-				 const struct mlxsw_tx_info *tx_info)
+static void mlxsw_sp_txhdr_info_data_init(struct mlxsw_core *mlxsw_core,
+					  struct sk_buff *skb,
+					  struct mlxsw_txhdr_info *txhdr_info)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	/* Resource validation was done as part of PTP init. */
+	u16 max_fid = MLXSW_CORE_RES_GET(mlxsw_core, FID);
+
+	txhdr_info->data = true;
+	txhdr_info->max_fid = max_fid;
+}
 
-	/* In Spectrum-2 and Spectrum-3, PTP events that require a time stamp
-	 * need special handling and cannot be transmitted as regular control
-	 * packets.
+static struct sk_buff *
+mlxsw_sp_vlan_tag_push(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb)
+{
+	/* In some Spectrum ASICs, in order for PTP event packets to have their
+	 * correction field correctly set on the egress port they must be
+	 * transmitted as data packets. Such packets ingress the ASIC via the
+	 * CPU port and must have a VLAN tag, as the CPU port is not configured
+	 * with a PVID. Push the default VLAN (4095), which is configured as
+	 * egress untagged on all the ports.
 	 */
-	if (unlikely(mlxsw_sp_skb_requires_ts(skb)))
-		return mlxsw_sp->ptp_ops->txhdr_construct(mlxsw_core,
-							  mlxsw_sp_port, skb,
-							  tx_info);
+	if (skb_vlan_tagged(skb))
+		return skb;
 
-	if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) {
-		this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
-		dev_kfree_skb_any(skb);
-		return -ENOMEM;
-	}
+	return vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q),
+					 MLXSW_SP_DEFAULT_VID);
+}
 
-	mlxsw_sp_txhdr_construct(skb, tx_info);
-	return 0;
+static struct sk_buff *
+mlxsw_sp_txhdr_preparations(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
+			    struct mlxsw_txhdr_info *txhdr_info)
+{
+	if (likely(!mlxsw_sp_skb_requires_ts(skb)))
+		return skb;
+
+	if (!mlxsw_sp->ptp_ops->tx_as_data)
+		return skb;
+
+	/* Special handling for PTP events that require a time stamp and cannot
+	 * be transmitted as regular control packets.
+	 */
+	mlxsw_sp_txhdr_info_data_init(mlxsw_sp->core, skb, txhdr_info);
+	return mlxsw_sp_vlan_tag_push(mlxsw_sp, skb);
 }
 
 enum mlxsw_reg_spms_state mlxsw_sp_stp_spms_state(u8 state)
@@ -721,16 +617,16 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_port_pcpu_stats *pcpu_stats;
-	const struct mlxsw_tx_info tx_info = {
-		.local_port = mlxsw_sp_port->local_port,
-		.is_emad = false,
+	struct mlxsw_txhdr_info txhdr_info = {
+		.tx_info.local_port = mlxsw_sp_port->local_port,
+		.tx_info.is_emad = false,
 	};
 	u64 len;
 	int err;
 
 	memset(skb->cb, 0, sizeof(struct mlxsw_skb_cb));
 
-	if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &tx_info))
+	if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &txhdr_info.tx_info))
 		return NETDEV_TX_BUSY;
 
 	if (eth_skb_pad(skb)) {
@@ -738,10 +634,11 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 		return NETDEV_TX_OK;
 	}
 
-	err = mlxsw_sp_txhdr_handle(mlxsw_sp->core, mlxsw_sp_port, skb,
-				    &tx_info);
-	if (err)
+	skb = mlxsw_sp_txhdr_preparations(mlxsw_sp, skb, &txhdr_info);
+	if (!skb) {
+		this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
 		return NETDEV_TX_OK;
+	}
 
 	/* TX header is consumed by HW on the way so we shouldn't count its
 	 * bytes as being sent.
@@ -751,7 +648,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	/* Due to a race we might fail here because of a full queue. In that
 	 * unlikely case we simply drop the packet.
 	 */
-	err = mlxsw_core_skb_transmit(mlxsw_sp->core, skb, &tx_info);
+	err = mlxsw_core_skb_transmit(mlxsw_sp->core, skb, &txhdr_info);
 
 	if (!err) {
 		pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats);
@@ -1262,63 +1159,31 @@ static int mlxsw_sp_set_features(struct net_device *dev,
 	return 0;
 }
 
-static int mlxsw_sp_port_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct ifreq *ifr)
+static int mlxsw_sp_port_hwtstamp_set(struct net_device *dev,
+				      struct kernel_hwtstamp_config *config,
+				      struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
-	int err;
-
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	err = mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port,
-							     &config);
-	if (err)
-		return err;
-
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 
-	return 0;
+	return mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port,
+							      config, extack);
 }
 
-static int mlxsw_sp_port_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct ifreq *ifr)
+static int mlxsw_sp_port_hwtstamp_get(struct net_device *dev,
+				      struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config config;
-	int err;
-
-	err = mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_get(mlxsw_sp_port,
-							     &config);
-	if (err)
-		return err;
-
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 
-	return 0;
+	return mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_get(mlxsw_sp_port,
+							      config);
 }
 
 static inline void mlxsw_sp_port_ptp_clear(struct mlxsw_sp_port *mlxsw_sp_port)
 {
-	struct hwtstamp_config config = {0};
-
-	mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port, &config);
-}
-
-static int
-mlxsw_sp_port_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	struct kernel_hwtstamp_config config = {};
 
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return mlxsw_sp_port_hwtstamp_set(mlxsw_sp_port, ifr);
-	case SIOCGHWTSTAMP:
-		return mlxsw_sp_port_hwtstamp_get(mlxsw_sp_port, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
+	mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port, &config,
+						       NULL);
 }
 
 static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
@@ -1335,7 +1200,8 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
 	.ndo_vlan_rx_add_vid	= mlxsw_sp_port_add_vid,
 	.ndo_vlan_rx_kill_vid	= mlxsw_sp_port_kill_vid,
 	.ndo_set_features	= mlxsw_sp_set_features,
-	.ndo_eth_ioctl		= mlxsw_sp_port_ioctl,
+	.ndo_hwtstamp_get	= mlxsw_sp_port_hwtstamp_get,
+	.ndo_hwtstamp_set	= mlxsw_sp_port_hwtstamp_set,
 };
 
 static int
@@ -1677,10 +1543,12 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port,
 	netif_carrier_off(dev);
 
 	dev->features |= NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_FILTER |
-			 NETIF_F_HW_TC;
-	dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK;
+			 NETIF_F_HW_TC | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK |
+			    NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	dev->vlan_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	dev->lltx = true;
-	dev->netns_local = true;
+	dev->netns_immutable = true;
 
 	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = MLXSW_PORT_MAX_MTU - MLXSW_PORT_ETH_FRAME_HDR;
@@ -2507,11 +2375,11 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 			     ROUTER_EXP, false),
 	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_DIP_LINK_LOCAL, FORWARD,
 			     ROUTER_EXP, false),
+	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_SIP_LINK_LOCAL, FORWARD,
+			     ROUTER_EXP, false),
 	/* Multicast Router Traps */
 	MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false),
 	MLXSW_SP_RXL_L3_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),
-	/* NVE traps */
-	MLXSW_SP_RXL_MARK(NVE_ENCAP_ARP, TRAP_TO_CPU, NEIGH_DISCOVERY, false),
 };
 
 static const struct mlxsw_listener mlxsw_sp1_listener[] = {
@@ -2792,7 +2660,6 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp1_ptp_ops = {
 	.get_stats_count = mlxsw_sp1_get_stats_count,
 	.get_stats_strings = mlxsw_sp1_get_stats_strings,
 	.get_stats	= mlxsw_sp1_get_stats,
-	.txhdr_construct = mlxsw_sp_ptp_txhdr_construct,
 };
 
 static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = {
@@ -2811,7 +2678,7 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = {
 	.get_stats_count = mlxsw_sp2_get_stats_count,
 	.get_stats_strings = mlxsw_sp2_get_stats_strings,
 	.get_stats	= mlxsw_sp2_get_stats,
-	.txhdr_construct = mlxsw_sp2_ptp_txhdr_construct,
+	.tx_as_data     = true,
 };
 
 static const struct mlxsw_sp_ptp_ops mlxsw_sp4_ptp_ops = {
@@ -2830,7 +2697,6 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp4_ptp_ops = {
 	.get_stats_count = mlxsw_sp2_get_stats_count,
 	.get_stats_strings = mlxsw_sp2_get_stats_strings,
 	.get_stats	= mlxsw_sp2_get_stats,
-	.txhdr_construct = mlxsw_sp_ptp_txhdr_construct,
 };
 
 struct mlxsw_sp_sample_trigger_node {
@@ -3992,11 +3858,9 @@ static struct mlxsw_driver mlxsw_sp1_driver = {
 	.trap_policer_fini		= mlxsw_sp_trap_policer_fini,
 	.trap_policer_set		= mlxsw_sp_trap_policer_set,
 	.trap_policer_counter_get	= mlxsw_sp_trap_policer_counter_get,
-	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp1_resources_register,
 	.kvd_sizes_get			= mlxsw_sp_kvd_sizes_get,
 	.ptp_transmitted		= mlxsw_sp_ptp_transmitted,
-	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp1_config_profile,
 	.sdq_supports_cqe_v2		= false,
 };
@@ -4030,10 +3894,8 @@ static struct mlxsw_driver mlxsw_sp2_driver = {
 	.trap_policer_fini		= mlxsw_sp_trap_policer_fini,
 	.trap_policer_set		= mlxsw_sp_trap_policer_set,
 	.trap_policer_counter_get	= mlxsw_sp_trap_policer_counter_get,
-	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp2_resources_register,
 	.ptp_transmitted		= mlxsw_sp_ptp_transmitted,
-	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp2_config_profile,
 	.sdq_supports_cqe_v2		= true,
 };
@@ -4067,10 +3929,8 @@ static struct mlxsw_driver mlxsw_sp3_driver = {
 	.trap_policer_fini		= mlxsw_sp_trap_policer_fini,
 	.trap_policer_set		= mlxsw_sp_trap_policer_set,
 	.trap_policer_counter_get	= mlxsw_sp_trap_policer_counter_get,
-	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp2_resources_register,
 	.ptp_transmitted		= mlxsw_sp_ptp_transmitted,
-	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp2_config_profile,
 	.sdq_supports_cqe_v2		= true,
 };
@@ -4102,10 +3962,8 @@ static struct mlxsw_driver mlxsw_sp4_driver = {
 	.trap_policer_fini		= mlxsw_sp_trap_policer_fini,
 	.trap_policer_set		= mlxsw_sp_trap_policer_set,
 	.trap_policer_counter_get	= mlxsw_sp_trap_policer_counter_get,
-	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp2_resources_register,
 	.ptp_transmitted		= mlxsw_sp_ptp_transmitted,
-	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp4_config_profile,
 	.sdq_supports_cqe_v2		= true,
 };
@@ -5343,25 +5201,13 @@ static int mlxsw_sp_netdevice_vxlan_event(struct mlxsw_sp *mlxsw_sp,
 			return 0;
 		if (!mlxsw_sp_bridge_vxlan_is_valid(upper_dev, extack))
 			return -EOPNOTSUPP;
-		if (cu_info->linking) {
-			if (!netif_running(dev))
-				return 0;
-			/* When the bridge is VLAN-aware, the VNI of the VxLAN
-			 * device needs to be mapped to a VLAN, but at this
-			 * point no VLANs are configured on the VxLAN device
-			 */
-			if (br_vlan_enabled(upper_dev))
-				return 0;
+		if (!netif_running(dev))
+			return 0;
+		if (cu_info->linking)
 			return mlxsw_sp_bridge_vxlan_join(mlxsw_sp, upper_dev,
 							  dev, 0, extack);
-		} else {
-			/* VLANs were already flushed, which triggered the
-			 * necessary cleanup
-			 */
-			if (br_vlan_enabled(upper_dev))
-				return 0;
+		else
 			mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, dev);
-		}
 		break;
 	case NETDEV_PRE_UP:
 		upper_dev = netdev_master_upper_dev_get(dev);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 8d3c61287696..b03ff9e044f9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -233,9 +233,10 @@ struct mlxsw_sp_ptp_ops {
 			    u16 local_port);
 
 	int (*hwtstamp_get)(struct mlxsw_sp_port *mlxsw_sp_port,
-			    struct hwtstamp_config *config);
+			    struct kernel_hwtstamp_config *config);
 	int (*hwtstamp_set)(struct mlxsw_sp_port *mlxsw_sp_port,
-			    struct hwtstamp_config *config);
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack);
 	void (*shaper_work)(struct work_struct *work);
 	int (*get_ts_info)(struct mlxsw_sp *mlxsw_sp,
 			   struct kernel_ethtool_ts_info *info);
@@ -243,10 +244,7 @@ struct mlxsw_sp_ptp_ops {
 	void (*get_stats_strings)(u8 **p);
 	void (*get_stats)(struct mlxsw_sp_port *mlxsw_sp_port,
 			  u64 *data, int data_index);
-	int (*txhdr_construct)(struct mlxsw_core *mlxsw_core,
-			       struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct sk_buff *skb,
-			       const struct mlxsw_tx_info *tx_info);
+	bool tx_as_data;
 };
 
 struct mlxsw_sp_fid_core_ops {
@@ -354,7 +352,7 @@ struct mlxsw_sp_port {
 	struct mlxsw_sp_flow_block *eg_flow_block;
 	struct {
 		struct delayed_work shaper_dw;
-		struct hwtstamp_config hwtstamp_config;
+		struct kernel_hwtstamp_config hwtstamp_config;
 		u16 ing_types;
 		u16 egr_types;
 		struct mlxsw_sp_ptp_port_stats stats;
@@ -664,10 +662,10 @@ bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp,
 					 const struct net_device *br_dev);
 int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 			       const struct net_device *br_dev,
-			       const struct net_device *vxlan_dev, u16 vid,
+			       struct net_device *vxlan_dev, u16 vid,
 			       struct netlink_ext_ack *extack);
 void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
-				 const struct net_device *vxlan_dev);
+				 struct net_device *vxlan_dev);
 extern struct notifier_block mlxsw_sp_switchdev_notifier;
 
 /* spectrum.c */
@@ -711,12 +709,6 @@ int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp,
 				unsigned int *p_counter_index);
 void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp,
 				unsigned int counter_index);
-void mlxsw_sp_txhdr_construct(struct sk_buff *skb,
-			      const struct mlxsw_tx_info *tx_info);
-int mlxsw_sp_txhdr_ptp_data_construct(struct mlxsw_core *mlxsw_core,
-				      struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct sk_buff *skb,
-				      const struct mlxsw_tx_info *tx_info);
 bool mlxsw_sp_port_dev_check(const struct net_device *dev);
 struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev);
 struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev);
@@ -763,9 +755,6 @@ void
 mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp,
 				 struct net_device *dev);
-bool mlxsw_sp_rif_exists(struct mlxsw_sp *mlxsw_sp,
-			 const struct net_device *dev);
-u16 mlxsw_sp_rif_vid(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev);
 u16 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp);
 int mlxsw_sp_router_nve_promote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id,
 				      enum mlxsw_sp_l3proto ul_proto,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
index a54eedb69a3f..067f0055a55a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
@@ -212,7 +212,22 @@ static const u8 mlxsw_sp4_acl_bf_crc6_tab[256] = {
  * This array defines key offsets for easy access when copying key blocks from
  * entry key to Bloom filter chunk.
  */
-static const u8 chunk_key_offsets[MLXSW_BLOOM_KEY_CHUNKS] = {2, 20, 38};
+static char *
+mlxsw_sp_acl_bf_enc_key_get(struct mlxsw_sp_acl_atcam_entry *aentry,
+			    u8 chunk_index)
+{
+	switch (chunk_index) {
+	case 0:
+		return &aentry->ht_key.enc_key[2];
+	case 1:
+		return &aentry->ht_key.enc_key[20];
+	case 2:
+		return &aentry->ht_key.enc_key[38];
+	default:
+		WARN_ON_ONCE(1);
+		return &aentry->ht_key.enc_key[0];
+	}
+}
 
 static u16 mlxsw_sp2_acl_bf_crc16_byte(u16 crc, u8 c)
 {
@@ -235,9 +250,10 @@ __mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion,
 			     u8 key_offset, u8 chunk_key_len, u8 chunk_len)
 {
 	struct mlxsw_afk_key_info *key_info = aregion->region->key_info;
-	u8 chunk_index, chunk_count, block_count;
+	u8 chunk_index, chunk_count;
 	char *chunk = output;
 	__be16 erp_region_id;
+	u32 block_count;
 
 	block_count = mlxsw_afk_key_info_blocks_count_get(key_info);
 	chunk_count = 1 + ((block_count - 1) >> 2);
@@ -245,12 +261,13 @@ __mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion,
 				   (aregion->region->id << 4));
 	for (chunk_index = max_chunks - chunk_count; chunk_index < max_chunks;
 	     chunk_index++) {
+		char *enc_key;
+
 		memset(chunk, 0, pad_bytes);
 		memcpy(chunk + pad_bytes, &erp_region_id,
 		       sizeof(erp_region_id));
-		memcpy(chunk + key_offset,
-		       &aentry->ht_key.enc_key[chunk_key_offsets[chunk_index]],
-		       chunk_key_len);
+		enc_key = mlxsw_sp_acl_bf_enc_key_get(aentry, chunk_index);
+		memcpy(chunk + key_offset, enc_key, chunk_key_len);
 		chunk += chunk_len;
 	}
 	*len = chunk_count * chunk_len;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index b1d08e958bf9..69f9da9fb305 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -1489,7 +1489,8 @@ mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp,
 
 static int
 mlxsw_sp_acl_tcam_region_rehash_intrvl_get(struct devlink *devlink, u32 id,
-					   struct devlink_param_gset_ctx *ctx)
+					   struct devlink_param_gset_ctx *ctx,
+					   struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
 	struct mlxsw_sp_acl_tcam *tcam;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
index 50e591420bd9..b1094aaffa5f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
@@ -170,8 +170,7 @@ void mlxsw_sp_counter_pool_fini(struct mlxsw_sp *mlxsw_sp)
 	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
 
 	mlxsw_sp_counter_sub_pools_fini(mlxsw_sp);
-	WARN_ON(find_first_bit(pool->usage, pool->pool_size) !=
-			       pool->pool_size);
+	WARN_ON(!bitmap_empty(pool->usage, pool->pool_size));
 	WARN_ON(atomic_read(&pool->active_entries_count));
 	bitmap_free(pool->usage);
 	devl_resource_occ_get_unregister(devlink,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
index 2bed8c86b7cf..0a8fb9c842d3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
@@ -262,7 +262,7 @@ err_port_pause_configure:
 }
 
 struct mlxsw_sp_port_hw_stats {
-	char str[ETH_GSTRING_LEN];
+	char str[ETH_GSTRING_LEN] __nonstring;
 	u64 (*getter)(const char *payload);
 	bool cells_bytes;
 };
@@ -768,7 +768,9 @@ static void __mlxsw_sp_port_get_stats(struct net_device *dev,
 	err = mlxsw_sp_get_hw_stats_by_group(&hw_stats, &len, grp);
 	if (err)
 		return;
-	mlxsw_sp_port_get_stats_raw(dev, grp, prio, ppcnt_pl);
+	err = mlxsw_sp_port_get_stats_raw(dev, grp, prio, ppcnt_pl);
+	if (err)
+		return;
 	for (i = 0; i < len; i++) {
 		data[data_index + i] = hw_stats[i].getter(ppcnt_pl);
 		if (!hw_stats[i].cells_bytes)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 6a4a81c63451..353fd9ca89a6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -830,8 +830,10 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 		return -EINVAL;
 
 	rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie);
-	if (!rule)
-		return -EINVAL;
+	if (!rule) {
+		err = -EINVAL;
+		goto err_rule_get_stats;
+	}
 
 	err = mlxsw_sp_acl_rule_get_stats(mlxsw_sp, rule, &packets, &bytes,
 					  &drops, &lastuse, &used_hw_stats);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
index 69cd689dbc83..5afe6b155ef0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
@@ -1003,10 +1003,10 @@ static void mlxsw_sp_mr_route_stats_update(struct mlxsw_sp *mlxsw_sp,
 	mr->mr_ops->route_stats(mlxsw_sp, mr_route->route_priv, &packets,
 				&bytes);
 
-	if (mr_route->mfc->mfc_un.res.pkt != packets)
-		mr_route->mfc->mfc_un.res.lastuse = jiffies;
-	mr_route->mfc->mfc_un.res.pkt = packets;
-	mr_route->mfc->mfc_un.res.bytes = bytes;
+	if (atomic_long_read(&mr_route->mfc->mfc_un.res.pkt) != packets)
+		WRITE_ONCE(mr_route->mfc->mfc_un.res.lastuse, jiffies);
+	atomic_long_set(&mr_route->mfc->mfc_un.res.pkt, packets);
+	atomic_long_set(&mr_route->mfc->mfc_un.res.bytes, bytes);
 }
 
 static void mlxsw_sp_mr_stats_update(struct work_struct *work)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
index d94081c7658e..5b9f0844b8f6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
@@ -46,7 +46,7 @@ struct mlxsw_sp2_ptp_state {
 	refcount_t ptp_port_enabled_ref; /* Number of ports with time stamping
 					  * enabled.
 					  */
-	struct hwtstamp_config config;
+	struct kernel_hwtstamp_config config;
 	struct mutex lock; /* Protects 'config' and HW configuration. */
 };
 
@@ -131,7 +131,7 @@ static u64 __mlxsw_sp1_ptp_read_frc(struct mlxsw_sp1_ptp_clock *clock,
 	return (u64) frc_l | (u64) frc_h2 << 32;
 }
 
-static u64 mlxsw_sp1_ptp_read_frc(const struct cyclecounter *cc)
+static u64 mlxsw_sp1_ptp_read_frc(struct cyclecounter *cc)
 {
 	struct mlxsw_sp1_ptp_clock *clock =
 		container_of(cc, struct mlxsw_sp1_ptp_clock, cycles);
@@ -1083,14 +1083,14 @@ void mlxsw_sp1_ptp_fini(struct mlxsw_sp_ptp_state *ptp_state_common)
 }
 
 int mlxsw_sp1_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config)
+			       struct kernel_hwtstamp_config *config)
 {
 	*config = mlxsw_sp_port->ptp.hwtstamp_config;
 	return 0;
 }
 
 static int
-mlxsw_sp1_ptp_get_message_types(const struct hwtstamp_config *config,
+mlxsw_sp1_ptp_get_message_types(const struct kernel_hwtstamp_config *config,
 				u16 *p_ing_types, u16 *p_egr_types,
 				enum hwtstamp_rx_filters *p_rx_filter)
 {
@@ -1246,7 +1246,8 @@ void mlxsw_sp1_ptp_shaper_work(struct work_struct *work)
 }
 
 int mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config)
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack)
 {
 	enum hwtstamp_rx_filters rx_filter;
 	u16 ing_types;
@@ -1270,7 +1271,7 @@ int mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (err)
 		return err;
 
-	/* Notify the ioctl caller what we are actually timestamping. */
+	/* Notify the caller what we are actually timestamping. */
 	config->rx_filter = rx_filter;
 
 	return 0;
@@ -1353,6 +1354,10 @@ struct mlxsw_sp_ptp_state *mlxsw_sp2_ptp_init(struct mlxsw_sp *mlxsw_sp)
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	int err;
 
+	/* Max FID will be used in data path, check validity as part of init. */
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, FID))
+		return ERR_PTR(-EIO);
+
 	ptp_state = kzalloc(sizeof(*ptp_state), GFP_KERNEL);
 	if (!ptp_state)
 		return ERR_PTR(-ENOMEM);
@@ -1447,7 +1452,7 @@ void mlxsw_sp2_ptp_transmitted(struct mlxsw_sp *mlxsw_sp,
 }
 
 int mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config)
+			       struct kernel_hwtstamp_config *config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state;
 
@@ -1461,7 +1466,7 @@ int mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
 }
 
 static int
-mlxsw_sp2_ptp_get_message_types(const struct hwtstamp_config *config,
+mlxsw_sp2_ptp_get_message_types(const struct kernel_hwtstamp_config *config,
 				u16 *p_ing_types, u16 *p_egr_types,
 				enum hwtstamp_rx_filters *p_rx_filter)
 {
@@ -1538,7 +1543,7 @@ static int mlxsw_sp2_ptp_mtpcpc_set(struct mlxsw_sp *mlxsw_sp, bool ptp_trap_en,
 
 static int mlxsw_sp2_ptp_enable(struct mlxsw_sp *mlxsw_sp, u16 ing_types,
 				u16 egr_types,
-				struct hwtstamp_config new_config)
+				struct kernel_hwtstamp_config new_config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp);
 	int err;
@@ -1552,7 +1557,7 @@ static int mlxsw_sp2_ptp_enable(struct mlxsw_sp *mlxsw_sp, u16 ing_types,
 }
 
 static int mlxsw_sp2_ptp_disable(struct mlxsw_sp *mlxsw_sp,
-				 struct hwtstamp_config new_config)
+				 struct kernel_hwtstamp_config new_config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp);
 	int err;
@@ -1567,7 +1572,7 @@ static int mlxsw_sp2_ptp_disable(struct mlxsw_sp *mlxsw_sp,
 
 static int mlxsw_sp2_ptp_configure_port(struct mlxsw_sp_port *mlxsw_sp_port,
 					u16 ing_types, u16 egr_types,
-					struct hwtstamp_config new_config)
+					struct kernel_hwtstamp_config new_config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	int err;
@@ -1588,7 +1593,7 @@ static int mlxsw_sp2_ptp_configure_port(struct mlxsw_sp_port *mlxsw_sp_port,
 }
 
 static int mlxsw_sp2_ptp_deconfigure_port(struct mlxsw_sp_port *mlxsw_sp_port,
-					  struct hwtstamp_config new_config)
+					  struct kernel_hwtstamp_config new_config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	int err;
@@ -1610,11 +1615,12 @@ err_ptp_disable:
 }
 
 int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config)
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack)
 {
+	struct kernel_hwtstamp_config new_config;
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	enum hwtstamp_rx_filters rx_filter;
-	struct hwtstamp_config new_config;
 	u16 new_ing_types, new_egr_types;
 	bool ptp_enabled;
 	int err;
@@ -1648,7 +1654,7 @@ int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port->ptp.ing_types = new_ing_types;
 	mlxsw_sp_port->ptp.egr_types = new_egr_types;
 
-	/* Notify the ioctl caller what we are actually timestamping. */
+	/* Notify the caller what we are actually timestamping. */
 	config->rx_filter = rx_filter;
 	mutex_unlock(&ptp_state->lock);
 
@@ -1679,43 +1685,3 @@ int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
 
 	return 0;
 }
-
-int mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-				 struct mlxsw_sp_port *mlxsw_sp_port,
-				 struct sk_buff *skb,
-				 const struct mlxsw_tx_info *tx_info)
-{
-	if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) {
-		this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
-		dev_kfree_skb_any(skb);
-		return -ENOMEM;
-	}
-
-	mlxsw_sp_txhdr_construct(skb, tx_info);
-	return 0;
-}
-
-int mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-				  struct mlxsw_sp_port *mlxsw_sp_port,
-				  struct sk_buff *skb,
-				  const struct mlxsw_tx_info *tx_info)
-{
-	/* In Spectrum-2 and Spectrum-3, in order for PTP event packets to have
-	 * their correction field correctly set on the egress port they must be
-	 * transmitted as data packets. Such packets ingress the ASIC via the
-	 * CPU port and must have a VLAN tag, as the CPU port is not configured
-	 * with a PVID. Push the default VLAN (4095), which is configured as
-	 * egress untagged on all the ports.
-	 */
-	if (!skb_vlan_tagged(skb)) {
-		skb = vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q),
-						MLXSW_SP_DEFAULT_VID);
-		if (!skb) {
-			this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
-			return -ENOMEM;
-		}
-	}
-
-	return mlxsw_sp_txhdr_ptp_data_construct(mlxsw_core, mlxsw_sp_port, skb,
-						 tx_info);
-}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
index c8aa1452fbb9..df37f1470830 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
@@ -34,10 +34,11 @@ void mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress,
 				 u64 timestamp);
 
 int mlxsw_sp1_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config);
+			       struct kernel_hwtstamp_config *config);
 
 int mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config);
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack);
 
 void mlxsw_sp1_ptp_shaper_work(struct work_struct *work);
 
@@ -49,11 +50,6 @@ void mlxsw_sp1_get_stats_strings(u8 **p);
 void mlxsw_sp1_get_stats(struct mlxsw_sp_port *mlxsw_sp_port,
 			 u64 *data, int data_index);
 
-int mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-				 struct mlxsw_sp_port *mlxsw_sp_port,
-				 struct sk_buff *skb,
-				 const struct mlxsw_tx_info *tx_info);
-
 struct mlxsw_sp_ptp_clock *
 mlxsw_sp2_ptp_clock_init(struct mlxsw_sp *mlxsw_sp, struct device *dev);
 
@@ -70,19 +66,15 @@ void mlxsw_sp2_ptp_transmitted(struct mlxsw_sp *mlxsw_sp,
 			       struct sk_buff *skb, u16 local_port);
 
 int mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config);
+			       struct kernel_hwtstamp_config *config);
 
 int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config);
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack);
 
 int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
 			      struct kernel_ethtool_ts_info *info);
 
-int mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-				  struct mlxsw_sp_port *mlxsw_sp_port,
-				  struct sk_buff *skb,
-				  const struct mlxsw_tx_info *tx_info);
-
 #else
 
 static inline struct mlxsw_sp_ptp_clock *
@@ -127,14 +119,15 @@ mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress,
 
 static inline int
 mlxsw_sp1_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct hwtstamp_config *config)
+			   struct kernel_hwtstamp_config *config)
 {
 	return -EOPNOTSUPP;
 }
 
 static inline int
 mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct hwtstamp_config *config)
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
@@ -157,15 +150,6 @@ static inline void mlxsw_sp1_get_stats(struct mlxsw_sp_port *mlxsw_sp_port,
 {
 }
 
-static inline int
-mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-			     struct mlxsw_sp_port *mlxsw_sp_port,
-			     struct sk_buff *skb,
-			     const struct mlxsw_tx_info *tx_info)
-{
-	return -EOPNOTSUPP;
-}
-
 static inline struct mlxsw_sp_ptp_clock *
 mlxsw_sp2_ptp_clock_init(struct mlxsw_sp *mlxsw_sp, struct device *dev)
 {
@@ -200,23 +184,15 @@ static inline void mlxsw_sp2_ptp_transmitted(struct mlxsw_sp *mlxsw_sp,
 
 static inline int
 mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct hwtstamp_config *config)
+			   struct kernel_hwtstamp_config *config)
 {
 	return -EOPNOTSUPP;
 }
 
 static inline int
 mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct hwtstamp_config *config)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int
-mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-			      struct mlxsw_sp_port *mlxsw_sp_port,
-			      struct sk_buff *skb,
-			      const struct mlxsw_tx_info *tx_info)
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 7d6d859cef3f..a2033837182e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -3014,6 +3014,9 @@ static int mlxsw_sp_neigh_rif_made_sync(struct mlxsw_sp *mlxsw_sp,
 		.rif = rif,
 	};
 
+	if (!mlxsw_sp_dev_lower_is_port(mlxsw_sp_rif_dev(rif)))
+		return 0;
+
 	neigh_for_each(&arp_tbl, mlxsw_sp_neigh_rif_made_sync_each, &rms);
 	if (rms.err)
 		goto err_arp;
@@ -8184,41 +8187,6 @@ mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
 	return NULL;
 }
 
-bool mlxsw_sp_rif_exists(struct mlxsw_sp *mlxsw_sp,
-			 const struct net_device *dev)
-{
-	struct mlxsw_sp_rif *rif;
-
-	mutex_lock(&mlxsw_sp->router->lock);
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	mutex_unlock(&mlxsw_sp->router->lock);
-
-	return rif;
-}
-
-u16 mlxsw_sp_rif_vid(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev)
-{
-	struct mlxsw_sp_rif *rif;
-	u16 vid = 0;
-
-	mutex_lock(&mlxsw_sp->router->lock);
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	if (!rif)
-		goto out;
-
-	/* We only return the VID for VLAN RIFs. Otherwise we return an
-	 * invalid value (0).
-	 */
-	if (rif->ops->type != MLXSW_SP_RIF_TYPE_VLAN)
-		goto out;
-
-	vid = mlxsw_sp_fid_8021q_vid(rif->fid);
-
-out:
-	mutex_unlock(&mlxsw_sp->router->lock);
-	return vid;
-}
-
 static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
 {
 	char ritr_pl[MLXSW_REG_RITR_LEN];
@@ -8417,19 +8385,6 @@ u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
 	return lb_rif->common.rif_index;
 }
 
-u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
-{
-	struct net_device *dev = mlxsw_sp_rif_dev(&lb_rif->common);
-	u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(dev);
-	struct mlxsw_sp_vr *ul_vr;
-
-	ul_vr = mlxsw_sp_vr_get(lb_rif->common.mlxsw_sp, ul_tb_id, NULL);
-	if (WARN_ON(IS_ERR(ul_vr)))
-		return 0;
-
-	return ul_vr->id;
-}
-
 u16 mlxsw_sp_ipip_lb_ul_rif_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
 {
 	return lb_rif->ul_rif_id;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 0432c7cc6b07..313efab5c324 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -90,7 +90,6 @@ struct mlxsw_sp_ipip_entry;
 struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp,
 					   u16 rif_index);
 u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *rif);
-u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *rif);
 u16 mlxsw_sp_ipip_lb_ul_rif_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif);
 u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev);
 int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 4b5fd71c897d..32d2e61f2b82 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -423,8 +423,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev,
 
 	parms = mlxsw_sp_ipip_netdev_parms4(to_dev);
 	ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp,
-			    0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0,
-			    0);
+			    0, 0, tun->net, parms.link, tun->fwmark, 0, 0);
 
 	rt = ip_route_output_key(tun->net, &fl4);
 	if (IS_ERR(rt))
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 6397ff0dc951..a48bf342084d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2929,23 +2929,8 @@ void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_bridge_port_put(mlxsw_sp->bridge, bridge_port);
 }
 
-int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
-			       const struct net_device *br_dev,
-			       const struct net_device *vxlan_dev, u16 vid,
-			       struct netlink_ext_ack *extack)
-{
-	struct mlxsw_sp_bridge_device *bridge_device;
-
-	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
-	if (WARN_ON(!bridge_device))
-		return -EINVAL;
-
-	return bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, vid,
-					      extack);
-}
-
-void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
-				 const struct net_device *vxlan_dev)
+static void __mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
+					  const struct net_device *vxlan_dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(vxlan_dev);
 	struct mlxsw_sp_fid *fid;
@@ -2963,6 +2948,47 @@ void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_fid_put(fid);
 }
 
+int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
+			       const struct net_device *br_dev,
+			       struct net_device *vxlan_dev, u16 vid,
+			       struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_bridge_device *bridge_device;
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	int err;
+
+	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
+	if (WARN_ON(!bridge_device))
+		return -EINVAL;
+
+	mlxsw_sp_port = mlxsw_sp_port_dev_lower_find(bridge_device->dev);
+	if (!mlxsw_sp_port)
+		return -EINVAL;
+
+	err = bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, vid,
+					     extack);
+	if (err)
+		return err;
+
+	err = switchdev_bridge_port_offload(vxlan_dev, mlxsw_sp_port->dev,
+					    NULL, NULL, NULL, false, extack);
+	if (err)
+		goto err_bridge_port_offload;
+
+	return 0;
+
+err_bridge_port_offload:
+	__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+	return err;
+}
+
+void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
+				 struct net_device *vxlan_dev)
+{
+	switchdev_bridge_port_unoffload(vxlan_dev, NULL, NULL, NULL);
+	__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+}
+
 static void
 mlxsw_sp_switchdev_vxlan_addr_convert(const union vxlan_addr *vxlan_addr,
 				      enum mlxsw_sp_l3proto *proto,
@@ -3867,7 +3893,7 @@ mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp,
 			mlxsw_sp_fid_put(fid);
 			return -EINVAL;
 		}
-		mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+		__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
 		mlxsw_sp_fid_put(fid);
 		return 0;
 	}
@@ -3883,7 +3909,7 @@ mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp,
 	/* Fourth case: Thew new VLAN is PVID, which means the VLAN currently
 	 * mapped to the VNI should be unmapped
 	 */
-	mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+	__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
 	mlxsw_sp_fid_put(fid);
 
 	/* Fifth case: The new VLAN is also egress untagged, which means the
@@ -3923,7 +3949,7 @@ mlxsw_sp_switchdev_vxlan_vlan_del(struct mlxsw_sp *mlxsw_sp,
 	if (mlxsw_sp_fid_8021q_vid(fid) != vid)
 		goto out;
 
-	mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+	__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
 
 out:
 	mlxsw_sp_fid_put(fid);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 1f9c1c86839f..b5c3f789c685 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -959,18 +959,18 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = {
 	},
 	{
 		.trap = MLXSW_SP_TRAP_CONTROL(ARP_REQUEST, NEIGH_DISCOVERY,
-					      MIRROR),
+					      TRAP),
 		.listeners_arr = {
-			MLXSW_SP_RXL_MARK(ROUTER_ARPBC, NEIGH_DISCOVERY,
-					  TRAP_TO_CPU, false),
+			MLXSW_SP_RXL_NO_MARK(ARPBC, NEIGH_DISCOVERY,
+					     TRAP_TO_CPU, false),
 		},
 	},
 	{
 		.trap = MLXSW_SP_TRAP_CONTROL(ARP_RESPONSE, NEIGH_DISCOVERY,
-					      MIRROR),
+					      TRAP),
 		.listeners_arr = {
-			MLXSW_SP_RXL_MARK(ROUTER_ARPUC, NEIGH_DISCOVERY,
-					  TRAP_TO_CPU, false),
+			MLXSW_SP_RXL_NO_MARK(ARPUC, NEIGH_DISCOVERY,
+					     TRAP_TO_CPU, false),
 		},
 	},
 	{
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index 83477c8e6971..9962dc157901 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -29,6 +29,8 @@ enum {
 	MLXSW_TRAP_ID_FDB_MISMATCH = 0x3B,
 	MLXSW_TRAP_ID_FID_MISS = 0x3D,
 	MLXSW_TRAP_ID_DECAP_ECN0 = 0x40,
+	MLXSW_TRAP_ID_ARPBC = 0x50,
+	MLXSW_TRAP_ID_ARPUC = 0x51,
 	MLXSW_TRAP_ID_MTUERROR = 0x52,
 	MLXSW_TRAP_ID_TTLERROR = 0x53,
 	MLXSW_TRAP_ID_LBERROR = 0x54,
@@ -66,13 +68,10 @@ enum {
 	MLXSW_TRAP_ID_HOST_MISS_IPV6 = 0x92,
 	MLXSW_TRAP_ID_IPIP_DECAP_ERROR = 0xB1,
 	MLXSW_TRAP_ID_NVE_DECAP_ARP = 0xB8,
-	MLXSW_TRAP_ID_NVE_ENCAP_ARP = 0xBD,
 	MLXSW_TRAP_ID_IPV4_BFD = 0xD0,
 	MLXSW_TRAP_ID_IPV6_BFD = 0xD1,
 	MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6,
 	MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7,
-	MLXSW_TRAP_ID_ROUTER_ARPBC = 0xE0,
-	MLXSW_TRAP_ID_ROUTER_ARPUC = 0xE1,
 	MLXSW_TRAP_ID_DISCARD_NON_ROUTABLE = 0x11A,
 	MLXSW_TRAP_ID_DISCARD_ROUTER2 = 0x130,
 	MLXSW_TRAP_ID_DISCARD_ROUTER3 = 0x131,
@@ -95,6 +94,7 @@ enum {
 	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_SIP_BC = 0x16A,
 	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_DIP_LOCAL_NET = 0x16B,
 	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_DIP_LINK_LOCAL = 0x16C,
+	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_LINK_LOCAL = 0x16D,
 	MLXSW_TRAP_ID_DISCARD_ROUTER_IRIF_EN = 0x178,
 	MLXSW_TRAP_ID_DISCARD_ROUTER_ERIF_EN = 0x179,
 	MLXSW_TRAP_ID_DISCARD_ROUTER_LPM4 = 0x17B,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/txheader.h b/drivers/net/ethernet/mellanox/mlxsw/txheader.h
index da51dd9d5e44..e78cba5821b6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/txheader.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/txheader.h
@@ -4,6 +4,69 @@
 #ifndef _MLXSW_TXHEADER_H
 #define _MLXSW_TXHEADER_H
 
+/* tx_hdr_version
+ * Tx header version.
+ * Must be set to 1.
+ */
+MLXSW_ITEM32(tx, hdr, version, 0x00, 28, 4);
+
+/* tx_hdr_ctl
+ * Packet control type.
+ * 0 - Ethernet control (e.g. EMADs, LACP)
+ * 1 - Ethernet data
+ */
+MLXSW_ITEM32(tx, hdr, ctl, 0x00, 26, 2);
+
+/* tx_hdr_proto
+ * Packet protocol type. Must be set to 1 (Ethernet).
+ */
+MLXSW_ITEM32(tx, hdr, proto, 0x00, 21, 3);
+
+/* tx_hdr_rx_is_router
+ * Packet is sent from the router. Valid for data packets only.
+ */
+MLXSW_ITEM32(tx, hdr, rx_is_router, 0x00, 19, 1);
+
+/* tx_hdr_fid_valid
+ * Indicates if the 'fid' field is valid and should be used for
+ * forwarding lookup. Valid for data packets only.
+ */
+MLXSW_ITEM32(tx, hdr, fid_valid, 0x00, 16, 1);
+
+/* tx_hdr_swid
+ * Switch partition ID. Must be set to 0.
+ */
+MLXSW_ITEM32(tx, hdr, swid, 0x00, 12, 3);
+
+/* tx_hdr_control_tclass
+ * Indicates if the packet should use the control TClass and not one
+ * of the data TClasses.
+ */
+MLXSW_ITEM32(tx, hdr, control_tclass, 0x00, 6, 1);
+
+/* tx_hdr_port_mid
+ * Destination local port for unicast packets.
+ * Destination multicast ID for multicast packets.
+ *
+ * Control packets are directed to a specific egress port, while data
+ * packets are transmitted through the CPU port (0) into the switch partition,
+ * where forwarding rules are applied.
+ */
+MLXSW_ITEM32(tx, hdr, port_mid, 0x04, 16, 16);
+
+/* tx_hdr_fid
+ * Forwarding ID used for L2 forwarding lookup. Valid only if 'fid_valid' is
+ * set, otherwise calculated based on the packet's VID using VID to FID mapping.
+ * Valid for data packets only.
+ */
+MLXSW_ITEM32(tx, hdr, fid, 0x08, 16, 16);
+
+/* tx_hdr_type
+ * 0 - Data packets
+ * 6 - Control packets
+ */
+MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4);
+
 #define MLXSW_TXHDR_LEN 0x10
 #define MLXSW_TXHDR_VERSION_0 0
 #define MLXSW_TXHDR_VERSION_1 1
diff --git a/drivers/net/ethernet/meta/Kconfig b/drivers/net/ethernet/meta/Kconfig
index 831921b9d4d5..ca5c7ac2a5bc 100644
--- a/drivers/net/ethernet/meta/Kconfig
+++ b/drivers/net/ethernet/meta/Kconfig
@@ -19,14 +19,16 @@ if NET_VENDOR_META
 
 config FBNIC
 	tristate "Meta Platforms Host Network Interface"
-	depends on X86_64 || COMPILE_TEST
+	depends on 64BIT || COMPILE_TEST
 	depends on !S390
 	depends on MAX_SKB_FRAGS < 22
 	depends on PCI_MSI
 	depends on PTP_1588_CLOCK_OPTIONAL
 	select NET_DEVLINK
 	select PAGE_POOL
+	select PCS_XPCS
 	select PHYLINK
+	select PLDMFW
 	help
 	  This driver supports Meta Platforms Host Network Interface.
 
diff --git a/drivers/net/ethernet/meta/fbnic/Makefile b/drivers/net/ethernet/meta/fbnic/Makefile
index 239b2258ec65..72c41af65364 100644
--- a/drivers/net/ethernet/meta/fbnic/Makefile
+++ b/drivers/net/ethernet/meta/fbnic/Makefile
@@ -12,6 +12,7 @@ fbnic-y := fbnic_csr.o \
 	   fbnic_devlink.o \
 	   fbnic_ethtool.o \
 	   fbnic_fw.o \
+	   fbnic_fw_log.o \
 	   fbnic_hw_stats.o \
 	   fbnic_hwmon.o \
 	   fbnic_irq.o \
@@ -20,6 +21,8 @@ fbnic-y := fbnic_csr.o \
 	   fbnic_pci.o \
 	   fbnic_phylink.o \
 	   fbnic_rpc.o \
+	   fbnic_mdio.o \
+	   fbnic_time.o \
 	   fbnic_tlv.o \
 	   fbnic_txrx.o \
-	   fbnic_time.o
+# End of objects
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h
index 706ae6104c8e..779a083b9215 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic.h
@@ -12,28 +12,41 @@
 
 #include "fbnic_csr.h"
 #include "fbnic_fw.h"
+#include "fbnic_fw_log.h"
 #include "fbnic_hw_stats.h"
 #include "fbnic_mac.h"
 #include "fbnic_rpc.h"
 
+struct fbnic_napi_vector;
+
+#define FBNIC_MAX_NAPI_VECTORS		128u
+#define FBNIC_MBX_CMPL_SLOTS		4
+
 struct fbnic_dev {
 	struct device *dev;
 	struct net_device *netdev;
 	struct dentry *dbg_fbd;
 	struct device *hwmon;
+	struct devlink_health_reporter *fw_reporter;
+	struct devlink_health_reporter *otp_reporter;
 
 	u32 __iomem *uc_addr0;
 	u32 __iomem *uc_addr4;
 	const struct fbnic_mac *mac;
 	unsigned int fw_msix_vector;
-	unsigned int pcs_msix_vector;
+	unsigned int mac_msix_vector;
 	unsigned short num_irqs;
 
+	struct {
+		u8 users;
+		char name[IFNAMSIZ + 9];
+	} napi_irq[FBNIC_MAX_NAPI_VECTORS];
+
 	struct delayed_work service_task;
 
 	struct fbnic_fw_mbx mbx[FBNIC_IPC_MBX_INDICES];
 	struct fbnic_fw_cap fw_cap;
-	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_fw_completion *cmpl_data[FBNIC_MBX_CMPL_SLOTS];
 	/* Lock protecting Tx Mailbox queue to prevent possible races */
 	spinlock_t fw_tx_lock;
 
@@ -51,6 +64,12 @@ struct fbnic_dev {
 	u8 mac_addr_boundary;
 	u8 tce_tcam_last;
 
+	/* IP TCAM */
+	struct fbnic_ip_addr ip_src[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ip_dst[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ipo_src[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ipo_dst[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+
 	/* Number of TCQs/RCQs available on hardware */
 	u16 max_num_queues;
 
@@ -64,8 +83,21 @@ struct fbnic_dev {
 	/* Last @time_high refresh time in jiffies (to catch stalls) */
 	unsigned long last_read;
 
+	/* PMD specific data */
+	unsigned long end_of_pmd_training;
+	u8 pmd_state;
+
 	/* Local copy of hardware statistics */
 	struct fbnic_hw_stats hw_stats;
+
+	/* Firmware time since boot in milliseconds */
+	u64 firmware_time;
+	u64 prev_firmware_time;
+
+	struct fbnic_fw_log fw_log;
+
+	/* MDIO bus for PHYs */
+	struct mii_bus *mdio_bus;
 };
 
 /* Reserve entry 0 in the MSI-X "others" array until we have filled all
@@ -136,18 +168,29 @@ extern char fbnic_driver_name[];
 
 void fbnic_devlink_free(struct fbnic_dev *fbd);
 struct fbnic_dev *fbnic_devlink_alloc(struct pci_dev *pdev);
+int fbnic_devlink_health_create(struct fbnic_dev *fbd);
+void fbnic_devlink_health_destroy(struct fbnic_dev *fbd);
 void fbnic_devlink_register(struct fbnic_dev *fbd);
 void fbnic_devlink_unregister(struct fbnic_dev *fbd);
+void __printf(2, 3)
+fbnic_devlink_fw_report(struct fbnic_dev *fbd, const char *format, ...);
+void fbnic_devlink_otp_check(struct fbnic_dev *fbd, const char *msg);
 
-int fbnic_fw_enable_mbx(struct fbnic_dev *fbd);
-void fbnic_fw_disable_mbx(struct fbnic_dev *fbd);
+int fbnic_fw_request_mbx(struct fbnic_dev *fbd);
+void fbnic_fw_free_mbx(struct fbnic_dev *fbd);
 
 void fbnic_hwmon_register(struct fbnic_dev *fbd);
 void fbnic_hwmon_unregister(struct fbnic_dev *fbd);
 
-int fbnic_pcs_irq_enable(struct fbnic_dev *fbd);
-void fbnic_pcs_irq_disable(struct fbnic_dev *fbd);
+int fbnic_mac_request_irq(struct fbnic_dev *fbd);
+void fbnic_mac_free_irq(struct fbnic_dev *fbd);
 
+void fbnic_napi_name_irqs(struct fbnic_dev *fbd);
+int fbnic_napi_request_irq(struct fbnic_dev *fbd,
+			   struct fbnic_napi_vector *nv);
+void fbnic_napi_free_irq(struct fbnic_dev *fbd,
+			 struct fbnic_napi_vector *nv);
+void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr);
 int fbnic_request_irq(struct fbnic_dev *dev, int nr, irq_handler_t handler,
 		      unsigned long flags, const char *name, void *data);
 void fbnic_free_irq(struct fbnic_dev *dev, int nr, void *data);
@@ -162,9 +205,16 @@ void fbnic_dbg_fbd_exit(struct fbnic_dev *fbd);
 void fbnic_dbg_init(void);
 void fbnic_dbg_exit(void);
 
+void fbnic_rpc_reset_valid_entries(struct fbnic_dev *fbd);
+
+int fbnic_mdiobus_create(struct fbnic_dev *fbd);
+
 void fbnic_csr_get_regs(struct fbnic_dev *fbd, u32 *data, u32 *regs_version);
 int fbnic_csr_regs_len(struct fbnic_dev *fbd);
 
+void fbnic_config_txrx_usecs(struct fbnic_napi_vector *nv, u32 arm);
+void fbnic_config_rx_frames(struct fbnic_napi_vector *nv);
+
 enum fbnic_boards {
 	fbnic_board_asic
 };
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.c b/drivers/net/ethernet/meta/fbnic/fbnic_csr.c
index 2118901b25e9..d9c0dc1c2af9 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.c
@@ -30,6 +30,7 @@ static const struct fbnic_csr_bounds fbnic_csr_sects[] = {
 	FBNIC_BOUNDS(RSFEC),
 	FBNIC_BOUNDS(MAC_MAC),
 	FBNIC_BOUNDS(SIG),
+	FBNIC_BOUNDS(PCIE_SS_COMPHY),
 	FBNIC_BOUNDS(PUL_USER),
 	FBNIC_BOUNDS(QUEUE),
 	FBNIC_BOUNDS(RPC_RAM),
@@ -64,7 +65,7 @@ static void fbnic_csr_get_regs_rpc_ram(struct fbnic_dev *fbd, u32 **data_p)
 	u32 i, j;
 
 	*(data++) = start;
-	*(data++) = end - 1;
+	*(data++) = end;
 
 	/* FBNIC_RPC_TCAM_ACT */
 	for (i = 0; i < FBNIC_RPC_TCAM_ACT_NUM_ENTRIES; i++) {
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
index 02bb81b3c506..422265dc7abd 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
@@ -12,13 +12,28 @@
 #define DESC_BIT(nr)		BIT_ULL(nr)
 #define DESC_GENMASK(h, l)	GENMASK_ULL(h, l)
 
+#define FW_VER_CODE(_major, _minor, _patch, _build) (		      \
+		FIELD_PREP(FBNIC_FW_CAP_RESP_VERSION_MAJOR, _major) | \
+		FIELD_PREP(FBNIC_FW_CAP_RESP_VERSION_MINOR, _minor) | \
+		FIELD_PREP(FBNIC_FW_CAP_RESP_VERSION_PATCH, _patch) | \
+		FIELD_PREP(FBNIC_FW_CAP_RESP_VERSION_BUILD, _build))
+
 /* Defines the minimum firmware version required by the driver */
-#define MIN_FW_MAJOR_VERSION    0
-#define MIN_FW_MINOR_VERSION    10
-#define MIN_FW_BUILD_VERSION    6
-#define MIN_FW_VERSION_CODE     (MIN_FW_MAJOR_VERSION * (1u << 24) + \
-				 MIN_FW_MINOR_VERSION * (1u << 16) + \
-				 MIN_FW_BUILD_VERSION)
+#define MIN_FW_VER_CODE				FW_VER_CODE(0, 10, 6, 0)
+
+/* Defines the minimum firmware version required for firmware logs */
+#define MIN_FW_VER_CODE_LOG			FW_VER_CODE(0, 12, 9, 0)
+
+/* Driver can request that firmware sends all cached logs in bulk. This
+ * feature was enabled on older firmware however firmware has a bug
+ * which attempted to send 30 messages per mbx message which caused an
+ * overflow flooding the mailbox. This results in a kernel warning
+ * related to corrupt mailbox messages.
+ *
+ * If firmware is new enough only request sending historical logs when
+ * the log buffer is empty to prevent duplicate logs.
+ */
+#define MIN_FW_VER_CODE_HIST			FW_VER_CODE(25, 5, 7, 0)
 
 #define PCI_DEVICE_ID_META_FBNIC_ASIC		0x0013
 
@@ -397,6 +412,15 @@ enum {
 #define FBNIC_TCE_DROP_CTRL_TTI_FRM_DROP_EN	CSR_BIT(1)
 #define FBNIC_TCE_DROP_CTRL_TTI_TBI_DROP_EN	CSR_BIT(2)
 
+#define FBNIC_TCE_TTI_CM_DROP_PKTS	0x0403e		/* 0x100f8 */
+#define FBNIC_TCE_TTI_CM_DROP_BYTE_L	0x0403f		/* 0x100fc */
+#define FBNIC_TCE_TTI_CM_DROP_BYTE_H	0x04040		/* 0x10100 */
+#define FBNIC_TCE_TTI_FRAME_DROP_PKTS	0x04041		/* 0x10104 */
+#define FBNIC_TCE_TTI_FRAME_DROP_BYTE_L	0x04042		/* 0x10108 */
+#define FBNIC_TCE_TTI_FRAME_DROP_BYTE_H	0x04043		/* 0x1010c */
+#define FBNIC_TCE_TBI_DROP_PKTS		0x04044		/* 0x10110 */
+#define FBNIC_TCE_TBI_DROP_BYTE_L	0x04045		/* 0x10114 */
+
 #define FBNIC_TCE_TCAM_IDX2DEST_MAP	0x0404A		/* 0x10128 */
 #define FBNIC_TCE_TCAM_IDX2DEST_MAP_DEST_ID_0	CSR_GENMASK(3, 0)
 enum {
@@ -432,6 +456,31 @@ enum {
 #define FBNIC_TMI_SOP_PROT_CTRL		0x04400		/* 0x11000 */
 #define FBNIC_TMI_DROP_CTRL		0x04401		/* 0x11004 */
 #define FBNIC_TMI_DROP_CTRL_EN			CSR_BIT(0)
+#define FBNIC_TMI_DROP_PKTS		0x04402		/* 0x11008 */
+#define FBNIC_TMI_DROP_BYTE_L		0x04403		/* 0x1100c */
+#define FBNIC_TMI_ILLEGAL_PTP_REQS	0x04409		/* 0x11024 */
+#define FBNIC_TMI_GOOD_PTP_TS		0x0440a		/* 0x11028 */
+#define FBNIC_TMI_BAD_PTP_TS		0x0440b		/* 0x1102c */
+#define FBNIC_TMI_STAT_TX_PACKET_1519_2047_BYTES_L \
+					0x04433		/* 0x110cc */
+#define FBNIC_TMI_STAT_TX_PACKET_1519_2047_BYTES_H \
+					0x04434		/* 0x110d0 */
+#define FBNIC_TMI_STAT_TX_PACKET_2048_4095_BYTES_L \
+					0x04435		/* 0x110d4 */
+#define FBNIC_TMI_STAT_TX_PACKET_2048_4095_BYTES_H \
+					0x04436		/* 0x110d8 */
+#define FBNIC_TMI_STAT_TX_PACKET_4096_8191_BYTES_L \
+					0x04437		/* 0x110dc */
+#define FBNIC_TMI_STAT_TX_PACKET_4096_8191_BYTES_H \
+					0x04438		/* 0x110e0 */
+#define FBNIC_TMI_STAT_TX_PACKET_8192_9216_BYTES_L \
+					0x04439		/* 0x110e4 */
+#define FBNIC_TMI_STAT_TX_PACKET_8192_9216_BYTES_H \
+					0x0443a		/* 0x110e8 */
+#define FBNIC_TMI_STAT_TX_PACKET_9217_MAX_BYTES_L \
+					0x0443b		/* 0x110ec */
+#define FBNIC_TMI_STAT_TX_PACKET_9217_MAX_BYTES_H \
+					0x0443c		/* 0x110f0 */
 #define FBNIC_CSR_END_TMI		0x0443f	/* CSR section delimiter */
 
 /* Precision Time Protocol Registers */
@@ -459,7 +508,7 @@ enum {
 
 #define FBNIC_PTP_ADD_VAL_NS		0x04806		/* 0x12018 */
 #define FBNIC_PTP_ADD_VAL_NS_MASK		CSR_GENMASK(15, 0)
-#define FBNIC_PTP_ADD_VAL_SUBNS		0x04807	/* 0x1201c */
+#define FBNIC_PTP_ADD_VAL_SUBNS		0x04807		/* 0x1201c */
 
 #define FBNIC_PTP_CTR_VAL_HI		0x04808		/* 0x12020 */
 #define FBNIC_PTP_CTR_VAL_LO		0x04809		/* 0x12024 */
@@ -485,6 +534,14 @@ enum {
 	FBNIC_RXB_FIFO_INDICES		= 8
 };
 
+enum {
+	FBNIC_RXB_INTF_NET = 0,
+	FBNIC_RXB_INTF_RBT = 1,
+	/* Unused */
+	/* Unused */
+	FBNIC_RXB_INTF_INDICES	= 4
+};
+
 #define FBNIC_RXB_CT_SIZE(n)		(0x08000 + (n))	/* 0x20000 + 4*n */
 #define FBNIC_RXB_CT_SIZE_CNT			8
 #define FBNIC_RXB_CT_SIZE_HEADER		CSR_GENMASK(5, 0)
@@ -605,8 +662,11 @@ enum {
 	FBNIC_RPC_ACT_TBL0_DEST_EI	= 4,
 };
 
+#define FBNIC_RPC_ACT_TBL0_Q_SEL		CSR_BIT(4)
+#define FBNIC_RPC_ACT_TBL0_Q_ID			CSR_GENMASK(15, 8)
 #define FBNIC_RPC_ACT_TBL0_DMA_HINT		CSR_GENMASK(24, 16)
 #define FBNIC_RPC_ACT_TBL0_TS_ENA		CSR_BIT(28)
+#define FBNIC_RPC_ACT_TBL0_ACT_TBL_IDX		CSR_BIT(29)
 #define FBNIC_RPC_ACT_TBL0_RSS_CTXT_ID		CSR_BIT(30)
 
 #define FBNIC_RPC_ACT_TBL1_DEFAULT	0x0840b		/* 0x2102c */
@@ -649,6 +709,26 @@ enum {
 #define FBNIC_RPC_CNTR_OVR_SIZE_ERR	0x084a6		/* 0x21298 */
 
 #define FBNIC_RPC_TCAM_MACDA_VALIDATE	0x0852d		/* 0x214b4 */
+#define FBNIC_RPC_STAT_RX_PACKET_1519_2047_BYTES_L \
+					0x0855f		/* 0x2157c */
+#define FBNIC_RPC_STAT_RX_PACKET_1519_2047_BYTES_H \
+					0x08560		/* 0x21580 */
+#define FBNIC_RPC_STAT_RX_PACKET_2048_4095_BYTES_L \
+					0x08561		/* 0x21584 */
+#define FBNIC_RPC_STAT_RX_PACKET_2048_4095_BYTES_H \
+					0x08562		/* 0x21588 */
+#define FBNIC_RPC_STAT_RX_PACKET_4096_8191_BYTES_L \
+					0x08563		/* 0x2158c */
+#define FBNIC_RPC_STAT_RX_PACKET_4096_8191_BYTES_H \
+					0x08564		/* 0x21590 */
+#define FBNIC_RPC_STAT_RX_PACKET_8192_9216_BYTES_L \
+					0x08565		/* 0x21594 */
+#define FBNIC_RPC_STAT_RX_PACKET_8192_9216_BYTES_H \
+					0x08566		/* 0x21598 */
+#define FBNIC_RPC_STAT_RX_PACKET_9217_MAX_BYTES_L \
+					0x08567		/* 0x2159c */
+#define FBNIC_RPC_STAT_RX_PACKET_9217_MAX_BYTES_H \
+					0x08568		/* 0x215a0 */
 #define FBNIC_CSR_END_RPC		0x0856b	/* CSR section delimiter */
 
 /* RPC RAM Registers */
@@ -677,6 +757,9 @@ enum {
 
 #define FBNIC_RPC_TCAM_OUTER_IPSRC(m, n)\
 	(0x08c00 + 0x08 * (n) + (m))		/* 0x023000 + 32*n + 4*m */
+#define FBNIC_RPC_TCAM_IP_ADDR_VALUE		CSR_GENMASK(15, 0)
+#define FBNIC_RPC_TCAM_IP_ADDR_MASK		CSR_GENMASK(31, 16)
+
 #define FBNIC_RPC_TCAM_OUTER_IPDST(m, n)\
 	(0x08c48 + 0x08 * (n) + (m))		/* 0x023120 + 32*n + 4*m */
 #define FBNIC_RPC_TCAM_IPSRC(m, n)\
@@ -704,9 +787,26 @@ enum {
 
 /* MAC PCS registers */
 #define FBNIC_CSR_START_PCS		0x10000 /* CSR section delimiter */
+#define FBNIC_PCS_PAGE(n)	(0x10000 + 0x400 * (n))	/* 0x40000 + 1024*n */
+#define FBNIC_PCS(reg, n)	((reg) + FBNIC_PCS_PAGE(n))
 #define FBNIC_CSR_END_PCS		0x10668 /* CSR section delimiter */
 
 #define FBNIC_CSR_START_RSFEC		0x10800 /* CSR section delimiter */
+
+/* We have 4 RSFEC engines present in our part, however we are only using 1.
+ * As such only CCW(0) and NCCW(0) will never be non-zero and the other
+ * registers can be ignored.
+ */
+#define FBNIC_RSFEC_CCW_LO(n)	(0x10802 + 8 * (n))	/* 0x42008 + 32*n */
+#define FBNIC_RSFEC_CCW_HI(n)	(0x10803 + 8 * (n))	/* 0x4200c + 32*n */
+#define FBNIC_RSFEC_NCCW_LO(n)	(0x10804 + 8 * (n))	/* 0x42010 + 32*n */
+#define FBNIC_RSFEC_NCCW_HI(n)	(0x10805 + 8 * (n))	/* 0x42014 + 32*n */
+
+#define FBNIC_PCS_MAX_LANES			4
+#define FBNIC_PCS_SYMBLERR_LO(n) \
+				(0x10880 + 2 * (n))	/* 0x42200 + 8*n */
+#define FBNIC_PCS_SYMBLERR_HI(n) \
+				(0x10881 + 2 * (n))	/* 0x42204 + 8*n */
 #define FBNIC_CSR_END_RSFEC		0x108c8 /* CSR section delimiter */
 
 /* MAC MAC registers (ASIC only) */
@@ -746,18 +846,18 @@ enum {
 #define FBNIC_CSR_END_SIG		0x1184e /* CSR section delimiter */
 
 #define FBNIC_CSR_START_MAC_STAT	0x11a00
+#define FBNIC_MAC_STAT_RX_XOFF_STB_L	0x11a00		/* 0x46800 */
+#define FBNIC_MAC_STAT_RX_XOFF_STB_H	0x11a01		/* 0x46804 */
+#define FBNIC_MAC_STAT_TX_XOFF_STB_L	0x11a04		/* 0x46810 */
+#define FBNIC_MAC_STAT_TX_XOFF_STB_H	0x11a05		/* 0x46814 */
 #define FBNIC_MAC_STAT_RX_BYTE_COUNT_L	0x11a08		/* 0x46820 */
 #define FBNIC_MAC_STAT_RX_BYTE_COUNT_H	0x11a09		/* 0x46824 */
-#define FBNIC_MAC_STAT_RX_ALIGN_ERROR_L \
-					0x11a0a		/* 0x46828 */
-#define FBNIC_MAC_STAT_RX_ALIGN_ERROR_H \
-					0x11a0b		/* 0x4682c */
+#define FBNIC_MAC_STAT_RX_ALIGN_ERROR_L	0x11a0a		/* 0x46828 */
+#define FBNIC_MAC_STAT_RX_ALIGN_ERROR_H	0x11a0b		/* 0x4682c */
 #define FBNIC_MAC_STAT_RX_TOOLONG_L	0x11a0e		/* 0x46838 */
 #define FBNIC_MAC_STAT_RX_TOOLONG_H	0x11a0f		/* 0x4683c */
-#define FBNIC_MAC_STAT_RX_RECEIVED_OK_L	\
-					0x11a12		/* 0x46848 */
-#define FBNIC_MAC_STAT_RX_RECEIVED_OK_H	\
-					0x11a13		/* 0x4684c */
+#define FBNIC_MAC_STAT_RX_RECEIVED_OK_L	0x11a12		/* 0x46848 */
+#define FBNIC_MAC_STAT_RX_RECEIVED_OK_H	0x11a13		/* 0x4684c */
 #define FBNIC_MAC_STAT_RX_PACKET_BAD_FCS_L \
 					0x11a14		/* 0x46850 */
 #define FBNIC_MAC_STAT_RX_PACKET_BAD_FCS_H \
@@ -768,27 +868,138 @@ enum {
 #define FBNIC_MAC_STAT_RX_MULTICAST_H	0x11a1d		/* 0x46874 */
 #define FBNIC_MAC_STAT_RX_BROADCAST_L	0x11a1e		/* 0x46878 */
 #define FBNIC_MAC_STAT_RX_BROADCAST_H	0x11a1f		/* 0x4687c */
+#define FBNIC_MAC_STAT_RX_UNDERSIZE_L	0x11a24		/* 0x46890 */
+#define FBNIC_MAC_STAT_RX_UNDERSIZE_H	0x11a25		/* 0x46894 */
+#define FBNIC_MAC_STAT_RX_PACKET_64_BYTES_L \
+					0x11a26		/* 0x46898 */
+#define FBNIC_MAC_STAT_RX_PACKET_64_BYTES_H \
+					0x11a27		/* 0x4689c */
+#define FBNIC_MAC_STAT_RX_PACKET_65_127_BYTES_L \
+					0x11a28		/* 0x468a0 */
+#define FBNIC_MAC_STAT_RX_PACKET_65_127_BYTES_H \
+					0x11a29		/* 0x468a4 */
+#define FBNIC_MAC_STAT_RX_PACKET_128_255_BYTES_L \
+					0x11a2a		/* 0x468a8 */
+#define FBNIC_MAC_STAT_RX_PACKET_128_255_BYTES_H \
+					0x11a2b		/* 0x468ac */
+#define FBNIC_MAC_STAT_RX_PACKET_256_511_BYTES_L \
+					0x11a2c		/* 0x468b0 */
+#define FBNIC_MAC_STAT_RX_PACKET_256_511_BYTES_H \
+					0x11a2d		/* 0x468b4 */
+#define FBNIC_MAC_STAT_RX_PACKET_512_1023_BYTES_L \
+					0x11a2e		/* 0x468b8 */
+#define FBNIC_MAC_STAT_RX_PACKET_512_1023_BYTES_H \
+					0x11a2f		/* 0x468bc */
+#define FBNIC_MAC_STAT_RX_PACKET_1024_1518_BYTES_L \
+					0x11a30		/* 0x468c0 */
+#define FBNIC_MAC_STAT_RX_PACKET_1024_1518_BYTES_H \
+					0x11a31		/* 0x468c4 */
+#define FBNIC_MAC_STAT_RX_PACKET_1519_MAX_BYTES_L \
+					0x11a32		/* 0x468c8 */
+#define FBNIC_MAC_STAT_RX_PACKET_1519_MAX_BYTES_H \
+					0x11a33		/* 0x468cc */
+#define FBNIC_MAC_STAT_RX_OVERSIZE_L	0x11a34		/* 0x468d0 */
+#define FBNIC_MAC_STAT_RX_OVERSSIZE_H	0x11a35		/* 0x468d4 */
+#define FBNIC_MAC_STAT_RX_JABBER_L	0x11a36		/* 0x468d8 */
+#define FBNIC_MAC_STAT_RX_JABBER_H	0x11a37		/* 0x468dc */
+#define FBNIC_MAC_STAT_RX_FRAGMENT_L	0x11a38		/* 0x468e0 */
+#define FBNIC_MAC_STAT_RX_FRAGMENT_H	0x11a39		/* 0x468e4 */
+#define FBNIC_MAC_STAT_RX_CONTROL_FRAMES_L \
+					0x11a3c		/* 0x468f0 */
+#define FBNIC_MAC_STAT_RX_CONTROL_FRAMES_H \
+					0x11a3d		/* 0x468f4 */
 #define FBNIC_MAC_STAT_TX_BYTE_COUNT_L	0x11a3e		/* 0x468f8 */
 #define FBNIC_MAC_STAT_TX_BYTE_COUNT_H	0x11a3f		/* 0x468fc */
 #define FBNIC_MAC_STAT_TX_TRANSMITTED_OK_L \
 					0x11a42		/* 0x46908 */
 #define FBNIC_MAC_STAT_TX_TRANSMITTED_OK_H \
 					0x11a43		/* 0x4690c */
-#define FBNIC_MAC_STAT_TX_IFOUTERRORS_L \
-					0x11a46		/* 0x46918 */
-#define FBNIC_MAC_STAT_TX_IFOUTERRORS_H \
-					0x11a47		/* 0x4691c */
+#define FBNIC_MAC_STAT_TX_IFOUTERRORS_L	0x11a46		/* 0x46918 */
+#define FBNIC_MAC_STAT_TX_IFOUTERRORS_H	0x11a47		/* 0x4691c */
 #define FBNIC_MAC_STAT_TX_MULTICAST_L	0x11a4a		/* 0x46928 */
 #define FBNIC_MAC_STAT_TX_MULTICAST_H	0x11a4b		/* 0x4692c */
 #define FBNIC_MAC_STAT_TX_BROADCAST_L	0x11a4c		/* 0x46930 */
 #define FBNIC_MAC_STAT_TX_BROADCAST_H	0x11a4d		/* 0x46934 */
+#define FBNIC_MAC_STAT_TX_PACKET_64_BYTES_L \
+					0x11a4e		/* 0x46938 */
+#define FBNIC_MAC_STAT_TX_PACKET_64_BYTES_H \
+					0x11a4f		/* 0x4693c */
+#define FBNIC_MAC_STAT_TX_PACKET_65_127_BYTES_L \
+					0x11a50		/* 0x46940 */
+#define FBNIC_MAC_STAT_TX_PACKET_65_127_BYTES_H \
+					0x11a51		/* 0x46944 */
+#define FBNIC_MAC_STAT_TX_PACKET_128_255_BYTES_L \
+					0x11a52		/* 0x46948 */
+#define FBNIC_MAC_STAT_TX_PACKET_128_255_BYTES_H \
+					0x11a53		/* 0x4694c */
+#define FBNIC_MAC_STAT_TX_PACKET_256_511_BYTES_L \
+					0x11a54		/* 0x46950 */
+#define FBNIC_MAC_STAT_TX_PACKET_256_511_BYTES_H \
+					0x11a55		/* 0x46954 */
+#define FBNIC_MAC_STAT_TX_PACKET_512_1023_BYTES_L \
+					0x11a56		/* 0x46958 */
+#define FBNIC_MAC_STAT_TX_PACKET_512_1023_BYTES_H \
+					0x11a57		/* 0x4695c */
+#define FBNIC_MAC_STAT_TX_PACKET_1024_1518_BYTES_L \
+					0x11a58		/* 0x46960 */
+#define FBNIC_MAC_STAT_TX_PACKET_1024_1518_BYTES_H \
+					0x11a59		/* 0x46964 */
+#define FBNIC_MAC_STAT_TX_PACKET_1519_MAX_BYTES_L \
+					0x11a5a		/* 0x46968 */
+#define FBNIC_MAC_STAT_TX_PACKET_1519_MAX_BYTES_H \
+					0x11a5b		/* 0x4696c */
+#define FBNIC_MAC_STAT_TX_CONTROL_FRAMES_L \
+					0x11a5e		/* 0x46978 */
+#define FBNIC_MAC_STAT_TX_CONTROL_FRAMES_H \
+					0x11a5f		/* 0x4697c */
+
+/* PCIE Comphy Registers */
+#define FBNIC_CSR_START_PCIE_SS_COMPHY	0x2442e /* CSR section delimiter */
+#define FBNIC_CSR_END_PCIE_SS_COMPHY	0x279d7	/* CSR section delimiter */
+
 /* PUL User Registers */
 #define FBNIC_CSR_START_PUL_USER	0x31000	/* CSR section delimiter */
 #define FBNIC_PUL_OB_TLP_HDR_AW_CFG	0x3103d		/* 0xc40f4 */
+#define FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH	CSR_BIT(19)
 #define FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME		CSR_BIT(18)
 #define FBNIC_PUL_OB_TLP_HDR_AR_CFG	0x3103e		/* 0xc40f8 */
+#define FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH	CSR_BIT(19)
 #define FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME		CSR_BIT(18)
-#define FBNIC_CSR_END_PUL_USER	0x31080	/* CSR section delimiter */
+#define FBNIC_PUL_USER_OB_RD_TLP_CNT_31_0 \
+					0x3106e		/* 0xc41b8 */
+#define FBNIC_PUL_USER_OB_RD_DWORD_CNT_31_0 \
+					0x31070		/* 0xc41c0 */
+#define FBNIC_PUL_USER_OB_RD_DWORD_CNT_63_32 \
+					0x31071		/* 0xc41c4 */
+#define FBNIC_PUL_USER_OB_WR_TLP_CNT_31_0 \
+					0x31072		/* 0xc41c8 */
+#define FBNIC_PUL_USER_OB_WR_TLP_CNT_63_32 \
+					0x31073		/* 0xc41cc */
+#define FBNIC_PUL_USER_OB_WR_DWORD_CNT_31_0 \
+					0x31074		/* 0xc41d0 */
+#define FBNIC_PUL_USER_OB_WR_DWORD_CNT_63_32 \
+					0x31075		/* 0xc41d4 */
+#define FBNIC_PUL_USER_OB_CPL_TLP_CNT_31_0 \
+					0x31076		/* 0xc41d8 */
+#define FBNIC_PUL_USER_OB_CPL_TLP_CNT_63_32 \
+					0x31077		/* 0xc41dc */
+#define FBNIC_PUL_USER_OB_CPL_DWORD_CNT_31_0 \
+					0x31078		/* 0xc41e0 */
+#define FBNIC_PUL_USER_OB_CPL_DWORD_CNT_63_32 \
+					0x31079		/* 0xc41e4 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_31_0 \
+					0x3107a		/* 0xc41e8 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_63_32 \
+					0x3107b		/* 0xc41ec */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_31_0 \
+					0x3107c		/* 0xc41f0 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_63_32 \
+					0x3107d		/* 0xc41f4 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_31_0 \
+					0x3107e		/* 0xc41f8 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_63_32 \
+					0x3107f		/* 0xc41fc */
+#define FBNIC_CSR_END_PUL_USER		0x310ea	/* CSR section delimiter */
 
 /* Queue Registers
  *
@@ -819,6 +1030,12 @@ enum {
 #define FBNIC_QUEUE_TWQ1_BAL		0x022		/* 0x088 */
 #define FBNIC_QUEUE_TWQ1_BAH		0x023		/* 0x08c */
 
+/* Tx Work Queue Statistics Registers */
+#define FBNIC_QUEUE_TWQ0_PKT_CNT	0x062		/* 0x188 */
+#define FBNIC_QUEUE_TWQ0_ERR_CNT	0x063		/* 0x18c */
+#define FBNIC_QUEUE_TWQ1_PKT_CNT	0x072		/* 0x1c8 */
+#define FBNIC_QUEUE_TWQ1_ERR_CNT	0x073		/* 0x1cc */
+
 /* Tx Completion Queue Registers */
 #define FBNIC_QUEUE_TCQ_CTL		0x080		/* 0x200 */
 #define FBNIC_QUEUE_TCQ_CTL_RESET		CSR_BIT(0)
@@ -908,6 +1125,12 @@ enum {
 	FBNIC_QUEUE_RDE_CTL1_PAYLD_PACK_RSS	= 2,
 };
 
+/* Rx Per CQ Statistics Counters */
+#define FBNIC_QUEUE_RDE_PKT_CNT		0x2a2		/* 0xa88 */
+#define FBNIC_QUEUE_RDE_PKT_ERR_CNT	0x2a3		/* 0xa8c */
+#define FBNIC_QUEUE_RDE_CQ_DROP_CNT	0x2a4		/* 0xa90 */
+#define FBNIC_QUEUE_RDE_BDQ_DROP_CNT	0x2a5		/* 0xa94 */
+
 /* Rx Interrupt Manager Registers */
 #define FBNIC_QUEUE_RIM_CTL		0x2c0		/* 0xb00 */
 #define FBNIC_QUEUE_RIM_CTL_MSIX_MASK		CSR_GENMASK(7, 0)
@@ -928,43 +1151,6 @@ enum {
 #define FBNIC_MAX_QUEUES		128
 #define FBNIC_CSR_END_QUEUE	(0x40000 + 0x400 * FBNIC_MAX_QUEUES - 1)
 
-/* PUL User Registers*/
-#define FBNIC_PUL_USER_OB_RD_TLP_CNT_31_0 \
-					0x3106e		/* 0xc41b8 */
-#define FBNIC_PUL_USER_OB_RD_DWORD_CNT_31_0 \
-					0x31070		/* 0xc41c0 */
-#define FBNIC_PUL_USER_OB_RD_DWORD_CNT_63_32 \
-					0x31071		/* 0xc41c4 */
-#define FBNIC_PUL_USER_OB_WR_TLP_CNT_31_0 \
-					0x31072		/* 0xc41c8 */
-#define FBNIC_PUL_USER_OB_WR_TLP_CNT_63_32 \
-					0x31073		/* 0xc41cc */
-#define FBNIC_PUL_USER_OB_WR_DWORD_CNT_31_0 \
-					0x31074		/* 0xc41d0 */
-#define FBNIC_PUL_USER_OB_WR_DWORD_CNT_63_32 \
-					0x31075		/* 0xc41d4 */
-#define FBNIC_PUL_USER_OB_CPL_TLP_CNT_31_0 \
-					0x31076		/* 0xc41d8 */
-#define FBNIC_PUL_USER_OB_CPL_TLP_CNT_63_32 \
-					0x31077		/* 0xc41dc */
-#define FBNIC_PUL_USER_OB_CPL_DWORD_CNT_31_0 \
-					0x31078		/* 0xc41e0 */
-#define FBNIC_PUL_USER_OB_CPL_DWORD_CNT_63_32 \
-					0x31079		/* 0xc41e4 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_31_0 \
-					0x3107a		/* 0xc41e8 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_63_32 \
-					0x3107b		/* 0xc41ec */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_31_0 \
-					0x3107c		/* 0xc41f0 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_63_32 \
-					0x3107d		/* 0xc41f4 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_31_0 \
-					0x3107e		/* 0xc41f8 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_63_32 \
-					0x3107f		/* 0xc41fc */
-#define FBNIC_CSR_END_PUL_USER	0x31080	/* CSR section delimiter */
-
 /* BAR 4 CSRs */
 
 /* The IPC mailbox consists of 32 mailboxes, with each mailbox consisting
@@ -994,4 +1180,22 @@ enum {
 #define FBNIC_IPC_MBX_DESC_FW_CMPL	DESC_BIT(1)
 #define FBNIC_IPC_MBX_DESC_HOST_CMPL	DESC_BIT(0)
 
+/* OTP Registers
+ * These registers are accessible via bar4 offset and are written by CMRT
+ * on boot. For the write status, the register is broken up in half with OTP
+ * Write Data Status occupying the top 16 bits and the ECC status occupying the
+ * bottom 16 bits.
+ */
+#define FBNIC_NS_OTP_STATUS		0x0021d
+#define FBNIC_NS_OTP_WRITE_STATUS	0x0021e
+
+#define FBNIC_NS_OTP_WRITE_DATA_STATUS_MASK	CSR_GENMASK(31, 16)
+#define FBNIC_NS_OTP_WRITE_ECC_STATUS_MASK	CSR_GENMASK(15, 0)
+
+#define FBNIC_REGS_VERSION			CSR_GENMASK(31, 16)
+#define FBNIC_REGS_HW_TYPE			CSR_GENMASK(15, 8)
+enum{
+	FBNIC_CSR_VERSION_V1_0_ASIC = 1,
+};
+
 #endif /* _FBNIC_CSR_H_ */
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
index 59951b5abdb7..b7238dd967fe 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
@@ -10,6 +10,193 @@
 
 static struct dentry *fbnic_dbg_root;
 
+static void fbnic_dbg_desc_break(struct seq_file *s, int i)
+{
+	while (i--)
+		seq_putc(s, '-');
+
+	seq_putc(s, '\n');
+}
+
+static int fbnic_dbg_mac_addr_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	char hdr[80];
+	int i;
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s\n",
+		 "Idx", "S", "TCAM Bitmap", "Addr/Mask");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_RPC_TCAM_MACDA_NUM_ENTRIES; i++) {
+		struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[i];
+
+		seq_printf(s, "%02d  %d %64pb %pm\n",
+			   i, mac_addr->state, mac_addr->act_tcam,
+			   mac_addr->value.addr8);
+		seq_printf(s, "                        %pm\n",
+			   mac_addr->mask.addr8);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_mac_addr);
+
+static int fbnic_dbg_tce_tcam_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	int i, tcam_idx = 0;
+	char hdr[80];
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s\n",
+		 "Idx", "S", "TCAM Bitmap", "Addr/Mask");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < ARRAY_SIZE(fbd->mac_addr); i++) {
+		struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[i];
+
+		/* Verify BMC bit is set */
+		if (!test_bit(FBNIC_MAC_ADDR_T_BMC, mac_addr->act_tcam))
+			continue;
+
+		if (tcam_idx == FBNIC_TCE_TCAM_NUM_ENTRIES)
+			break;
+
+		seq_printf(s, "%02d  %d %64pb %pm\n",
+			   tcam_idx, mac_addr->state, mac_addr->act_tcam,
+			   mac_addr->value.addr8);
+		seq_printf(s, "                        %pm\n",
+			   mac_addr->mask.addr8);
+		tcam_idx++;
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_tce_tcam);
+
+static int fbnic_dbg_act_tcam_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	char hdr[80];
+	int i;
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-55s %-4s %s\n",
+		 "Idx", "S", "Value/Mask", "RSS", "Dest");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_RPC_TCAM_ACT_NUM_ENTRIES; i++) {
+		struct fbnic_act_tcam *act_tcam = &fbd->act_tcam[i];
+
+		seq_printf(s, "%02d  %d %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x  %04x %08x\n",
+			   i, act_tcam->state,
+			   act_tcam->value.tcam[10], act_tcam->value.tcam[9],
+			   act_tcam->value.tcam[8], act_tcam->value.tcam[7],
+			   act_tcam->value.tcam[6], act_tcam->value.tcam[5],
+			   act_tcam->value.tcam[4], act_tcam->value.tcam[3],
+			   act_tcam->value.tcam[2], act_tcam->value.tcam[1],
+			   act_tcam->value.tcam[0], act_tcam->rss_en_mask,
+			   act_tcam->dest);
+		seq_printf(s, "      %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x\n",
+			   act_tcam->mask.tcam[10], act_tcam->mask.tcam[9],
+			   act_tcam->mask.tcam[8], act_tcam->mask.tcam[7],
+			   act_tcam->mask.tcam[6], act_tcam->mask.tcam[5],
+			   act_tcam->mask.tcam[4], act_tcam->mask.tcam[3],
+			   act_tcam->mask.tcam[2], act_tcam->mask.tcam[1],
+			   act_tcam->mask.tcam[0]);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_act_tcam);
+
+static int fbnic_dbg_ip_addr_show(struct seq_file *s,
+				  struct fbnic_ip_addr *ip_addr)
+{
+	char hdr[80];
+	int i;
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s %s\n",
+		 "Idx", "S", "TCAM Bitmap", "V", "Addr/Mask");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES; i++, ip_addr++) {
+		seq_printf(s, "%02d  %d %64pb %d %pi6\n",
+			   i, ip_addr->state, ip_addr->act_tcam,
+			   ip_addr->version, &ip_addr->value);
+		seq_printf(s, "                          %pi6\n",
+			   &ip_addr->mask);
+	}
+
+	return 0;
+}
+
+static int fbnic_dbg_ip_src_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ip_src);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ip_src);
+
+static int fbnic_dbg_ip_dst_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ip_dst);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ip_dst);
+
+static int fbnic_dbg_ipo_src_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ipo_src);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ipo_src);
+
+static int fbnic_dbg_ipo_dst_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ipo_dst);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ipo_dst);
+
+static int fbnic_dbg_fw_log_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	struct fbnic_fw_log_entry *entry;
+	unsigned long flags;
+
+	if (!fbnic_fw_log_ready(fbd))
+		return -ENXIO;
+
+	spin_lock_irqsave(&fbd->fw_log.lock, flags);
+
+	list_for_each_entry_reverse(entry, &fbd->fw_log.entries, list) {
+		seq_printf(s, FBNIC_FW_LOG_FMT, entry->index,
+			   (entry->timestamp / (MSEC_PER_SEC * 60 * 60 * 24)),
+			   (entry->timestamp / (MSEC_PER_SEC * 60 * 60)) % 24,
+			   ((entry->timestamp / (MSEC_PER_SEC * 60) % 60)),
+			   ((entry->timestamp / MSEC_PER_SEC) % 60),
+			   (entry->timestamp % MSEC_PER_SEC),
+			   entry->msg);
+	}
+
+	spin_unlock_irqrestore(&fbd->fw_log.lock, flags);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_fw_log);
+
 static int fbnic_dbg_pcie_stats_show(struct seq_file *s, void *v)
 {
 	struct fbnic_dev *fbd = s->private;
@@ -48,6 +235,22 @@ void fbnic_dbg_fbd_init(struct fbnic_dev *fbd)
 	fbd->dbg_fbd = debugfs_create_dir(name, fbnic_dbg_root);
 	debugfs_create_file("pcie_stats", 0400, fbd->dbg_fbd, fbd,
 			    &fbnic_dbg_pcie_stats_fops);
+	debugfs_create_file("mac_addr", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_mac_addr_fops);
+	debugfs_create_file("tce_tcam", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_tce_tcam_fops);
+	debugfs_create_file("act_tcam", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_act_tcam_fops);
+	debugfs_create_file("ip_src", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ip_src_fops);
+	debugfs_create_file("ip_dst", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ip_dst_fops);
+	debugfs_create_file("ipo_src", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ipo_src_fops);
+	debugfs_create_file("ipo_dst", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ipo_dst_fops);
+	debugfs_create_file("fw_log", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_fw_log_fops);
 }
 
 void fbnic_dbg_fbd_exit(struct fbnic_dev *fbd)
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c b/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c
index 0072d612215e..b62b1d5b1453 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c
@@ -3,10 +3,13 @@
 
 #include <linux/unaligned.h>
 #include <linux/pci.h>
+#include <linux/pldmfw.h>
 #include <linux/types.h>
 #include <net/devlink.h>
 
 #include "fbnic.h"
+#include "fbnic_fw.h"
+#include "fbnic_tlv.h"
 
 #define FBNIC_SN_STR_LEN	24
 
@@ -109,10 +112,512 @@ static int fbnic_devlink_info_get(struct devlink *devlink,
 	return 0;
 }
 
+static bool
+fbnic_pldm_match_record(struct pldmfw *context, struct pldmfw_record *record)
+{
+	struct pldmfw_desc_tlv *desc;
+	u32 anti_rollback_ver = 0;
+	struct devlink *devlink;
+	struct fbnic_dev *fbd;
+	struct pci_dev *pdev;
+
+	/* First, use the standard PCI matching function */
+	if (!pldmfw_op_pci_match_record(context, record))
+		return false;
+
+	pdev = to_pci_dev(context->dev);
+	fbd = pci_get_drvdata(pdev);
+	devlink = priv_to_devlink(fbd);
+
+	/* If PCI match is successful, check for vendor-specific descriptors */
+	list_for_each_entry(desc, &record->descs, entry) {
+		if (desc->type != PLDM_DESC_ID_VENDOR_DEFINED)
+			continue;
+
+		if (desc->size < 21 || desc->data[0] != 1 ||
+		    desc->data[1] != 15)
+			continue;
+
+		if (memcmp(desc->data + 2, "AntiRollbackVer", 15) != 0)
+			continue;
+
+		anti_rollback_ver = get_unaligned_le32(desc->data + 17);
+		break;
+	}
+
+	/* Compare versions and return error if they do not match */
+	if (anti_rollback_ver < fbd->fw_cap.anti_rollback_version) {
+		char buf[128];
+
+		snprintf(buf, sizeof(buf),
+			 "New firmware anti-rollback version (0x%x) is older than device version (0x%x)!",
+			 anti_rollback_ver, fbd->fw_cap.anti_rollback_version);
+		devlink_flash_update_status_notify(devlink, buf,
+						   "Anti-Rollback", 0, 0);
+
+		return false;
+	}
+
+	return true;
+}
+
+static int
+fbnic_flash_start(struct fbnic_dev *fbd, struct pldmfw_component *component)
+{
+	struct fbnic_fw_completion *cmpl;
+	int err;
+
+	cmpl = fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_FW_START_UPGRADE_REQ);
+	if (!cmpl)
+		return -ENOMEM;
+
+	err = fbnic_fw_xmit_fw_start_upgrade(fbd, cmpl,
+					     component->identifier,
+					     component->component_size);
+	if (err)
+		goto cmpl_free;
+
+	/* Wait for firmware to ack firmware upgrade start */
+	if (wait_for_completion_timeout(&cmpl->done, 10 * HZ))
+		err = cmpl->result;
+	else
+		err = -ETIMEDOUT;
+
+	fbnic_mbx_clear_cmpl(fbd, cmpl);
+cmpl_free:
+	fbnic_fw_put_cmpl(cmpl);
+
+	return err;
+}
+
+static int
+fbnic_flash_component(struct pldmfw *context,
+		      struct pldmfw_component *component)
+{
+	const u8 *data = component->component_data;
+	const u32 size = component->component_size;
+	struct fbnic_fw_completion *cmpl;
+	const char *component_name;
+	struct devlink *devlink;
+	struct fbnic_dev *fbd;
+	struct pci_dev *pdev;
+	u32 offset = 0;
+	u32 length = 0;
+	char buf[32];
+	int err;
+
+	pdev = to_pci_dev(context->dev);
+	fbd = pci_get_drvdata(pdev);
+	devlink = priv_to_devlink(fbd);
+
+	switch (component->identifier) {
+	case QSPI_SECTION_CMRT:
+		component_name = "boot1";
+		break;
+	case QSPI_SECTION_CONTROL_FW:
+		component_name = "boot2";
+		break;
+	case QSPI_SECTION_OPTION_ROM:
+		component_name = "option-rom";
+		break;
+	default:
+		snprintf(buf, sizeof(buf), "Unknown component ID %u!",
+			 component->identifier);
+		devlink_flash_update_status_notify(devlink, buf, NULL, 0,
+						   size);
+		return -EINVAL;
+	}
+
+	/* Once firmware receives the request to start upgrading it responds
+	 * with two messages:
+	 * 1. An ACK that it received the message and possible error code
+	 *    indicating that an upgrade is not currently possible.
+	 * 2. A request for the first chunk of data
+	 *
+	 * Setup completions for write before issuing the start message so
+	 * the driver can catch both messages.
+	 */
+	cmpl = fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_REQ);
+	if (!cmpl)
+		return -ENOMEM;
+
+	err = fbnic_mbx_set_cmpl(fbd, cmpl);
+	if (err)
+		goto cmpl_free;
+
+	devlink_flash_update_timeout_notify(devlink, "Initializing",
+					    component_name, 15);
+	err = fbnic_flash_start(fbd, component);
+	if (err)
+		goto err_no_msg;
+
+	while (offset < size) {
+		if (!wait_for_completion_timeout(&cmpl->done, 15 * HZ)) {
+			err = -ETIMEDOUT;
+			break;
+		}
+
+		err = cmpl->result;
+		if (err)
+			break;
+
+		/* Verify firmware is requesting the next chunk in the seq. */
+		if (cmpl->u.fw_update.offset != offset + length) {
+			err = -EFAULT;
+			break;
+		}
+
+		offset = cmpl->u.fw_update.offset;
+		length = cmpl->u.fw_update.length;
+
+		if (length > TLV_MAX_DATA || offset + length > size) {
+			err = -EFAULT;
+			break;
+		}
+
+		devlink_flash_update_status_notify(devlink, "Flashing",
+						   component_name,
+						   offset, size);
+
+		/* Mailbox will set length to 0 once it receives the finish
+		 * message.
+		 */
+		if (!length)
+			continue;
+
+		reinit_completion(&cmpl->done);
+		err = fbnic_fw_xmit_fw_write_chunk(fbd, data, offset, length,
+						   0);
+		if (err)
+			break;
+	}
+
+	if (err) {
+		fbnic_fw_xmit_fw_write_chunk(fbd, NULL, 0, 0, err);
+err_no_msg:
+		snprintf(buf, sizeof(buf), "Mailbox encountered error %d!",
+			 err);
+		devlink_flash_update_status_notify(devlink, buf,
+						   component_name, 0, 0);
+	}
+
+	fbnic_mbx_clear_cmpl(fbd, cmpl);
+cmpl_free:
+	fbnic_fw_put_cmpl(cmpl);
+
+	return err;
+}
+
+static const struct pldmfw_ops fbnic_pldmfw_ops = {
+	.match_record = fbnic_pldm_match_record,
+	.flash_component = fbnic_flash_component,
+};
+
+static int
+fbnic_devlink_flash_update(struct devlink *devlink,
+			   struct devlink_flash_update_params *params,
+			   struct netlink_ext_ack *extack)
+{
+	struct fbnic_dev *fbd = devlink_priv(devlink);
+	const struct firmware *fw = params->fw;
+	struct device *dev = fbd->dev;
+	struct pldmfw context;
+	char *err_msg;
+	int err;
+
+	context.ops = &fbnic_pldmfw_ops;
+	context.dev = dev;
+
+	err = pldmfw_flash_image(&context, fw);
+	if (err) {
+		switch (err) {
+		case -EINVAL:
+			err_msg = "Invalid image";
+			break;
+		case -EOPNOTSUPP:
+			err_msg = "Unsupported image";
+			break;
+		case -ENOMEM:
+			err_msg = "Out of memory";
+			break;
+		case -EFAULT:
+			err_msg = "Invalid header";
+			break;
+		case -ENOENT:
+			err_msg = "No matching record";
+			break;
+		case -ENODEV:
+			err_msg = "No matching device";
+			break;
+		case -ETIMEDOUT:
+			err_msg = "Timed out waiting for reply";
+			break;
+		default:
+			err_msg = "Unknown error";
+			break;
+		}
+
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Failed to flash PLDM Image: %s (error: %d)",
+				       err_msg, err);
+	}
+
+	return err;
+}
+
 static const struct devlink_ops fbnic_devlink_ops = {
-	.info_get = fbnic_devlink_info_get,
+	.info_get	= fbnic_devlink_info_get,
+	.flash_update	= fbnic_devlink_flash_update,
 };
 
+static int fbnic_fw_reporter_dump(struct devlink_health_reporter *reporter,
+				  struct devlink_fmsg *fmsg, void *priv_ctx,
+				  struct netlink_ext_ack *extack)
+{
+	struct fbnic_dev *fbd = devlink_health_reporter_priv(reporter);
+	u32 offset, index, index_count, length, size;
+	struct fbnic_fw_completion *fw_cmpl;
+	u8 *dump_data, **data;
+	int err;
+
+	fw_cmpl = fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_COREDUMP_GET_INFO_RESP);
+	if (!fw_cmpl)
+		return -ENOMEM;
+
+	err = fbnic_fw_xmit_coredump_info_msg(fbd, fw_cmpl, true);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to transmit core dump info msg");
+		goto cmpl_free;
+	}
+	if (!wait_for_completion_timeout(&fw_cmpl->done, 2 * HZ)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Timed out waiting on core dump info");
+		err = -ETIMEDOUT;
+		goto cmpl_cleanup;
+	}
+
+	size = fw_cmpl->u.coredump_info.size;
+	err = fw_cmpl->result;
+
+	fbnic_mbx_clear_cmpl(fbd, fw_cmpl);
+	fbnic_fw_put_cmpl(fw_cmpl);
+
+	/* Handle error returned by firmware */
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Firmware core dump returned error");
+		return err;
+	}
+	if (!size) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Firmware core dump returned size 0");
+		return -EIO;
+	}
+
+	/* Read the dump, we can only transfer TLV_MAX_DATA at a time */
+	index_count = DIV_ROUND_UP(size, TLV_MAX_DATA);
+
+	fw_cmpl = __fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_COREDUMP_READ_RESP,
+					sizeof(void *) * index_count + size);
+	if (!fw_cmpl)
+		return -ENOMEM;
+
+	/* Populate pointer table w/ pointer offsets */
+	dump_data = (void *)&fw_cmpl->u.coredump.data[index_count];
+	data = fw_cmpl->u.coredump.data;
+	fw_cmpl->u.coredump.size = size;
+	fw_cmpl->u.coredump.stride = TLV_MAX_DATA;
+
+	for (index = 0; index < index_count; index++) {
+		/* First iteration installs completion */
+		struct fbnic_fw_completion *cmpl_arg = index ? NULL : fw_cmpl;
+
+		offset = index * TLV_MAX_DATA;
+		length = min(size - offset, TLV_MAX_DATA);
+
+		data[index] = dump_data + offset;
+		err = fbnic_fw_xmit_coredump_read_msg(fbd, cmpl_arg,
+						      offset, length);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to transmit core dump msg");
+			if (cmpl_arg)
+				goto cmpl_free;
+			else
+				goto cmpl_cleanup;
+		}
+
+		if (wait_for_completion_timeout(&fw_cmpl->done, 2 * HZ)) {
+			reinit_completion(&fw_cmpl->done);
+		} else {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Timed out waiting on core dump (%d/%d)",
+					       index + 1, index_count);
+			err = -ETIMEDOUT;
+			goto cmpl_cleanup;
+		}
+
+		/* If we didn't see the reply record as incomplete */
+		if (fw_cmpl->u.coredump.data[index]) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "No data for core dump chunk (%d/%d)",
+					       index + 1, index_count);
+			err = -EIO;
+			goto cmpl_cleanup;
+		}
+	}
+
+	devlink_fmsg_binary_pair_nest_start(fmsg, "FW coredump");
+
+	for (offset = 0; offset < size; offset += length) {
+		length = min_t(u32, size - offset, TLV_MAX_DATA);
+
+		devlink_fmsg_binary_put(fmsg, dump_data + offset, length);
+	}
+
+	devlink_fmsg_binary_pair_nest_end(fmsg);
+
+cmpl_cleanup:
+	fbnic_mbx_clear_cmpl(fbd, fw_cmpl);
+cmpl_free:
+	fbnic_fw_put_cmpl(fw_cmpl);
+
+	return err;
+}
+
+static int
+fbnic_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
+			   struct devlink_fmsg *fmsg,
+			   struct netlink_ext_ack *extack)
+{
+	struct fbnic_dev *fbd = devlink_health_reporter_priv(reporter);
+	u32 sec, msec;
+
+	/* Device is most likely down, we're not exchanging heartbeats */
+	if (!fbd->prev_firmware_time)
+		return 0;
+
+	sec = div_u64_rem(fbd->firmware_time, MSEC_PER_SEC, &msec);
+
+	devlink_fmsg_pair_nest_start(fmsg, "last_heartbeat");
+	devlink_fmsg_obj_nest_start(fmsg);
+	devlink_fmsg_pair_nest_start(fmsg, "fw_uptime");
+	devlink_fmsg_obj_nest_start(fmsg);
+	devlink_fmsg_u32_pair_put(fmsg, "sec", sec);
+	devlink_fmsg_u32_pair_put(fmsg, "msec", msec);
+	devlink_fmsg_obj_nest_end(fmsg);
+	devlink_fmsg_pair_nest_end(fmsg);
+	devlink_fmsg_obj_nest_end(fmsg);
+	devlink_fmsg_pair_nest_end(fmsg);
+
+	return 0;
+}
+
+void __printf(2, 3)
+fbnic_devlink_fw_report(struct fbnic_dev *fbd, const char *format, ...)
+{
+	char msg[FBNIC_FW_LOG_MAX_SIZE];
+	va_list args;
+
+	va_start(args, format);
+	vsnprintf(msg, FBNIC_FW_LOG_MAX_SIZE, format, args);
+	va_end(args);
+
+	devlink_health_report(fbd->fw_reporter, msg, fbd);
+	if (fbnic_fw_log_ready(fbd))
+		fbnic_fw_log_write(fbd, 0, fbd->firmware_time, msg);
+}
+
+static const struct devlink_health_reporter_ops fbnic_fw_ops = {
+	.name = "fw",
+	.dump = fbnic_fw_reporter_dump,
+	.diagnose = fbnic_fw_reporter_diagnose,
+};
+
+static u32 fbnic_read_otp_status(struct fbnic_dev *fbd)
+{
+	return fbnic_fw_rd32(fbd, FBNIC_NS_OTP_STATUS);
+}
+
+static int
+fbnic_otp_reporter_dump(struct devlink_health_reporter *reporter,
+			struct devlink_fmsg *fmsg, void *priv_ctx,
+			struct netlink_ext_ack *extack)
+{
+	struct fbnic_dev *fbd = devlink_health_reporter_priv(reporter);
+	u32 otp_status, otp_write_status, m;
+
+	otp_status = fbnic_read_otp_status(fbd);
+	otp_write_status = fbnic_fw_rd32(fbd, FBNIC_NS_OTP_WRITE_STATUS);
+
+	/* Dump OTP status */
+	devlink_fmsg_pair_nest_start(fmsg, "OTP");
+	devlink_fmsg_obj_nest_start(fmsg);
+
+	devlink_fmsg_u32_pair_put(fmsg, "Status", otp_status);
+
+	/* Extract OTP Write Data status */
+	m = FBNIC_NS_OTP_WRITE_DATA_STATUS_MASK;
+	devlink_fmsg_u32_pair_put(fmsg, "Data",
+				  FIELD_GET(m, otp_write_status));
+
+	/* Extract OTP Write ECC status */
+	m = FBNIC_NS_OTP_WRITE_ECC_STATUS_MASK;
+	devlink_fmsg_u32_pair_put(fmsg, "ECC",
+				  FIELD_GET(m, otp_write_status));
+
+	devlink_fmsg_obj_nest_end(fmsg);
+	devlink_fmsg_pair_nest_end(fmsg);
+
+	return 0;
+}
+
+void fbnic_devlink_otp_check(struct fbnic_dev *fbd, const char *msg)
+{
+	/* Check if there is anything to report */
+	if (!fbnic_read_otp_status(fbd))
+		return;
+
+	devlink_health_report(fbd->otp_reporter, msg, fbd);
+	if (fbnic_fw_log_ready(fbd))
+		fbnic_fw_log_write(fbd, 0, fbd->firmware_time, msg);
+}
+
+static const struct devlink_health_reporter_ops fbnic_otp_ops = {
+	.name = "otp",
+	.dump = fbnic_otp_reporter_dump,
+};
+
+int fbnic_devlink_health_create(struct fbnic_dev *fbd)
+{
+	fbd->fw_reporter = devlink_health_reporter_create(priv_to_devlink(fbd),
+							  &fbnic_fw_ops, fbd);
+	if (IS_ERR(fbd->fw_reporter)) {
+		dev_warn(fbd->dev,
+			 "Failed to create FW fault reporter: %pe\n",
+			 fbd->fw_reporter);
+		return PTR_ERR(fbd->fw_reporter);
+	}
+
+	fbd->otp_reporter = devlink_health_reporter_create(priv_to_devlink(fbd),
+							   &fbnic_otp_ops, fbd);
+	if (IS_ERR(fbd->otp_reporter)) {
+		devlink_health_reporter_destroy(fbd->fw_reporter);
+		dev_warn(fbd->dev,
+			 "Failed to create OTP fault reporter: %pe\n",
+			 fbd->otp_reporter);
+		return PTR_ERR(fbd->otp_reporter);
+	}
+
+	return 0;
+}
+
+void fbnic_devlink_health_destroy(struct fbnic_dev *fbd)
+{
+	devlink_health_reporter_destroy(fbd->otp_reporter);
+	devlink_health_reporter_destroy(fbd->fw_reporter);
+}
+
 void fbnic_devlink_free(struct fbnic_dev *fbd)
 {
 	struct devlink *devlink = priv_to_devlink(fbd);
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
index cc8ca94529ca..693ebdf38705 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
@@ -2,8 +2,10 @@
 /* Copyright (c) Meta Platforms, Inc. and affiliates. */
 
 #include <linux/ethtool.h>
+#include <linux/ethtool_netlink.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
+#include <net/ipv6.h>
 
 #include "fbnic.h"
 #include "fbnic_netdev.h"
@@ -26,6 +28,19 @@ struct fbnic_stat {
 	FBNIC_STAT_FIELDS(fbnic_hw_stats, name, stat)
 
 static const struct fbnic_stat fbnic_gstrings_hw_stats[] = {
+	/* TTI */
+	FBNIC_HW_STAT("tti_cm_drop_frames", tti.cm_drop.frames),
+	FBNIC_HW_STAT("tti_cm_drop_bytes", tti.cm_drop.bytes),
+	FBNIC_HW_STAT("tti_frame_drop_frames", tti.frame_drop.frames),
+	FBNIC_HW_STAT("tti_frame_drop_bytes", tti.frame_drop.bytes),
+	FBNIC_HW_STAT("tti_tbi_drop_frames", tti.tbi_drop.frames),
+	FBNIC_HW_STAT("tti_tbi_drop_bytes", tti.tbi_drop.bytes),
+
+	/* TMI */
+	FBNIC_HW_STAT("ptp_illegal_req", tmi.ptp_illegal_req),
+	FBNIC_HW_STAT("ptp_good_ts", tmi.ptp_good_ts),
+	FBNIC_HW_STAT("ptp_bad_ts", tmi.ptp_bad_ts),
+
 	/* RPC */
 	FBNIC_HW_STAT("rpc_unkn_etype", rpc.unkn_etype),
 	FBNIC_HW_STAT("rpc_unkn_ext_hdr", rpc.unkn_ext_hdr),
@@ -38,7 +53,1535 @@ static const struct fbnic_stat fbnic_gstrings_hw_stats[] = {
 };
 
 #define FBNIC_HW_FIXED_STATS_LEN ARRAY_SIZE(fbnic_gstrings_hw_stats)
-#define FBNIC_HW_STATS_LEN	FBNIC_HW_FIXED_STATS_LEN
+
+#define FBNIC_RXB_ENQUEUE_STAT(name, stat) \
+	FBNIC_STAT_FIELDS(fbnic_rxb_enqueue_stats, name, stat)
+
+static const struct fbnic_stat fbnic_gstrings_rxb_enqueue_stats[] = {
+	FBNIC_RXB_ENQUEUE_STAT("rxb_integrity_err%u", integrity_err),
+	FBNIC_RXB_ENQUEUE_STAT("rxb_mac_err%u", mac_err),
+	FBNIC_RXB_ENQUEUE_STAT("rxb_parser_err%u", parser_err),
+	FBNIC_RXB_ENQUEUE_STAT("rxb_frm_err%u", frm_err),
+
+	FBNIC_RXB_ENQUEUE_STAT("rxb_drbo%u_frames", drbo.frames),
+	FBNIC_RXB_ENQUEUE_STAT("rxb_drbo%u_bytes", drbo.bytes),
+};
+
+#define FBNIC_HW_RXB_ENQUEUE_STATS_LEN \
+	ARRAY_SIZE(fbnic_gstrings_rxb_enqueue_stats)
+
+#define FBNIC_RXB_FIFO_STAT(name, stat) \
+	FBNIC_STAT_FIELDS(fbnic_rxb_fifo_stats, name, stat)
+
+static const struct fbnic_stat fbnic_gstrings_rxb_fifo_stats[] = {
+	FBNIC_RXB_FIFO_STAT("rxb_fifo%u_drop", trans_drop),
+	FBNIC_RXB_FIFO_STAT("rxb_fifo%u_dropped_frames", drop.frames),
+	FBNIC_RXB_FIFO_STAT("rxb_fifo%u_ecn", trans_ecn),
+	FBNIC_RXB_FIFO_STAT("rxb_fifo%u_level", level),
+};
+
+#define FBNIC_HW_RXB_FIFO_STATS_LEN ARRAY_SIZE(fbnic_gstrings_rxb_fifo_stats)
+
+#define FBNIC_RXB_DEQUEUE_STAT(name, stat) \
+	FBNIC_STAT_FIELDS(fbnic_rxb_dequeue_stats, name, stat)
+
+static const struct fbnic_stat fbnic_gstrings_rxb_dequeue_stats[] = {
+	FBNIC_RXB_DEQUEUE_STAT("rxb_intf%u_frames", intf.frames),
+	FBNIC_RXB_DEQUEUE_STAT("rxb_intf%u_bytes", intf.bytes),
+	FBNIC_RXB_DEQUEUE_STAT("rxb_pbuf%u_frames", pbuf.frames),
+	FBNIC_RXB_DEQUEUE_STAT("rxb_pbuf%u_bytes", pbuf.bytes),
+};
+
+#define FBNIC_HW_RXB_DEQUEUE_STATS_LEN \
+	ARRAY_SIZE(fbnic_gstrings_rxb_dequeue_stats)
+
+#define FBNIC_HW_Q_STAT(name, stat) \
+	FBNIC_STAT_FIELDS(fbnic_hw_q_stats, name, stat.value)
+
+static const struct fbnic_stat fbnic_gstrings_hw_q_stats[] = {
+	FBNIC_HW_Q_STAT("rde_%u_pkt_err", rde_pkt_err),
+	FBNIC_HW_Q_STAT("rde_%u_pkt_cq_drop", rde_pkt_cq_drop),
+	FBNIC_HW_Q_STAT("rde_%u_pkt_bdq_drop", rde_pkt_bdq_drop),
+};
+
+#define FBNIC_HW_Q_STATS_LEN ARRAY_SIZE(fbnic_gstrings_hw_q_stats)
+#define FBNIC_HW_STATS_LEN \
+	(FBNIC_HW_FIXED_STATS_LEN + \
+	 FBNIC_HW_RXB_ENQUEUE_STATS_LEN * FBNIC_RXB_ENQUEUE_INDICES + \
+	 FBNIC_HW_RXB_FIFO_STATS_LEN * FBNIC_RXB_FIFO_INDICES + \
+	 FBNIC_HW_RXB_DEQUEUE_STATS_LEN * FBNIC_RXB_DEQUEUE_INDICES + \
+	 FBNIC_HW_Q_STATS_LEN * FBNIC_MAX_QUEUES)
+
+#define FBNIC_QUEUE_STAT(name, stat) \
+	FBNIC_STAT_FIELDS(fbnic_ring, name, stat)
+
+static const struct fbnic_stat fbnic_gstrings_xdp_stats[] = {
+	FBNIC_QUEUE_STAT("xdp_tx_queue_%u_packets", stats.packets),
+	FBNIC_QUEUE_STAT("xdp_tx_queue_%u_bytes", stats.bytes),
+	FBNIC_QUEUE_STAT("xdp_tx_queue_%u_dropped", stats.dropped),
+};
+
+#define FBNIC_XDP_STATS_LEN ARRAY_SIZE(fbnic_gstrings_xdp_stats)
+
+#define FBNIC_STATS_LEN \
+	(FBNIC_HW_STATS_LEN + FBNIC_XDP_STATS_LEN * FBNIC_MAX_XDPQS)
+
+static void
+fbnic_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+
+	fbnic_get_fw_ver_commit_str(fbd, drvinfo->fw_version,
+				    sizeof(drvinfo->fw_version));
+}
+
+static int fbnic_get_regs_len(struct net_device *netdev)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	return fbnic_csr_regs_len(fbn->fbd) * sizeof(u32);
+}
+
+static void fbnic_get_regs(struct net_device *netdev,
+			   struct ethtool_regs *regs, void *data)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	fbnic_csr_get_regs(fbn->fbd, data, &regs->version);
+}
+
+static struct fbnic_net *fbnic_clone_create(struct fbnic_net *orig)
+{
+	struct fbnic_net *clone;
+
+	clone = kmemdup(orig, sizeof(*orig), GFP_KERNEL);
+	if (!clone)
+		return NULL;
+
+	memset(clone->tx, 0, sizeof(clone->tx));
+	memset(clone->rx, 0, sizeof(clone->rx));
+	memset(clone->napi, 0, sizeof(clone->napi));
+	return clone;
+}
+
+static void fbnic_clone_swap_cfg(struct fbnic_net *orig,
+				 struct fbnic_net *clone)
+{
+	swap(clone->rcq_size, orig->rcq_size);
+	swap(clone->hpq_size, orig->hpq_size);
+	swap(clone->ppq_size, orig->ppq_size);
+	swap(clone->txq_size, orig->txq_size);
+	swap(clone->num_rx_queues, orig->num_rx_queues);
+	swap(clone->num_tx_queues, orig->num_tx_queues);
+	swap(clone->num_napi, orig->num_napi);
+	swap(clone->hds_thresh, orig->hds_thresh);
+}
+
+static void fbnic_aggregate_vector_counters(struct fbnic_net *fbn,
+					    struct fbnic_napi_vector *nv)
+{
+	int i, j;
+
+	for (i = 0; i < nv->txt_count; i++) {
+		fbnic_aggregate_ring_tx_counters(fbn, &nv->qt[i].sub0);
+		fbnic_aggregate_ring_xdp_counters(fbn, &nv->qt[i].sub1);
+		fbnic_aggregate_ring_tx_counters(fbn, &nv->qt[i].cmpl);
+	}
+
+	for (j = 0; j < nv->rxt_count; j++, i++) {
+		fbnic_aggregate_ring_bdq_counters(fbn, &nv->qt[i].sub0);
+		fbnic_aggregate_ring_bdq_counters(fbn, &nv->qt[i].sub1);
+		fbnic_aggregate_ring_rx_counters(fbn, &nv->qt[i].cmpl);
+	}
+}
+
+static void fbnic_clone_swap(struct fbnic_net *orig,
+			     struct fbnic_net *clone)
+{
+	struct fbnic_dev *fbd = orig->fbd;
+	unsigned int i;
+
+	for (i = 0; i < max(clone->num_napi, orig->num_napi); i++)
+		fbnic_synchronize_irq(fbd, FBNIC_NON_NAPI_VECTORS + i);
+	for (i = 0; i < orig->num_napi; i++)
+		fbnic_aggregate_vector_counters(orig, orig->napi[i]);
+
+	fbnic_clone_swap_cfg(orig, clone);
+
+	for (i = 0; i < ARRAY_SIZE(orig->napi); i++)
+		swap(clone->napi[i], orig->napi[i]);
+	for (i = 0; i < ARRAY_SIZE(orig->tx); i++)
+		swap(clone->tx[i], orig->tx[i]);
+	for (i = 0; i < ARRAY_SIZE(orig->rx); i++)
+		swap(clone->rx[i], orig->rx[i]);
+}
+
+static void fbnic_clone_free(struct fbnic_net *clone)
+{
+	kfree(clone);
+}
+
+static int fbnic_get_coalesce(struct net_device *netdev,
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	ec->tx_coalesce_usecs = fbn->tx_usecs;
+	ec->rx_coalesce_usecs = fbn->rx_usecs;
+	ec->rx_max_coalesced_frames = fbn->rx_max_frames;
+
+	return 0;
+}
+
+static int fbnic_set_coalesce(struct net_device *netdev,
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	/* Verify against hardware limits */
+	if (ec->rx_coalesce_usecs > FIELD_MAX(FBNIC_INTR_CQ_REARM_RCQ_TIMEOUT)) {
+		NL_SET_ERR_MSG_MOD(extack, "rx_usecs is above device max");
+		return -EINVAL;
+	}
+	if (ec->tx_coalesce_usecs > FIELD_MAX(FBNIC_INTR_CQ_REARM_TCQ_TIMEOUT)) {
+		NL_SET_ERR_MSG_MOD(extack, "tx_usecs is above device max");
+		return -EINVAL;
+	}
+	if (ec->rx_max_coalesced_frames >
+	    FIELD_MAX(FBNIC_QUEUE_RIM_THRESHOLD_RCD_MASK) /
+	    FBNIC_MIN_RXD_PER_FRAME) {
+		NL_SET_ERR_MSG_MOD(extack, "rx_frames is above device max");
+		return -EINVAL;
+	}
+
+	fbn->tx_usecs = ec->tx_coalesce_usecs;
+	fbn->rx_usecs = ec->rx_coalesce_usecs;
+	fbn->rx_max_frames = ec->rx_max_coalesced_frames;
+
+	if (netif_running(netdev)) {
+		int i;
+
+		for (i = 0; i < fbn->num_napi; i++) {
+			struct fbnic_napi_vector *nv = fbn->napi[i];
+
+			fbnic_config_txrx_usecs(nv, 0);
+			fbnic_config_rx_frames(nv);
+		}
+	}
+
+	return 0;
+}
+
+static void
+fbnic_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
+		    struct kernel_ethtool_ringparam *kernel_ring,
+		    struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	ring->rx_max_pending = FBNIC_QUEUE_SIZE_MAX;
+	ring->rx_mini_max_pending = FBNIC_QUEUE_SIZE_MAX;
+	ring->rx_jumbo_max_pending = FBNIC_QUEUE_SIZE_MAX;
+	ring->tx_max_pending = FBNIC_QUEUE_SIZE_MAX;
+
+	ring->rx_pending = fbn->rcq_size;
+	ring->rx_mini_pending = fbn->hpq_size;
+	ring->rx_jumbo_pending = fbn->ppq_size;
+	ring->tx_pending = fbn->txq_size;
+
+	kernel_ring->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_ENABLED;
+	kernel_ring->hds_thresh_max = FBNIC_HDS_THRESH_MAX;
+	kernel_ring->hds_thresh = fbn->hds_thresh;
+}
+
+static void fbnic_set_rings(struct fbnic_net *fbn,
+			    struct ethtool_ringparam *ring,
+			    struct kernel_ethtool_ringparam *kernel_ring)
+{
+	fbn->rcq_size = ring->rx_pending;
+	fbn->hpq_size = ring->rx_mini_pending;
+	fbn->ppq_size = ring->rx_jumbo_pending;
+	fbn->txq_size = ring->tx_pending;
+	fbn->hds_thresh = kernel_ring->hds_thresh;
+}
+
+static int
+fbnic_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
+		    struct kernel_ethtool_ringparam *kernel_ring,
+		    struct netlink_ext_ack *extack)
+
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_net *clone;
+	int err;
+
+	ring->rx_pending	= roundup_pow_of_two(ring->rx_pending);
+	ring->rx_mini_pending	= roundup_pow_of_two(ring->rx_mini_pending);
+	ring->rx_jumbo_pending	= roundup_pow_of_two(ring->rx_jumbo_pending);
+	ring->tx_pending	= roundup_pow_of_two(ring->tx_pending);
+
+	/* These are absolute minimums allowing the device and driver to operate
+	 * but not necessarily guarantee reasonable performance. Settings below
+	 * Rx queue size of 128 and BDQs smaller than 64 are likely suboptimal
+	 * at best.
+	 */
+	if (ring->rx_pending < max(FBNIC_QUEUE_SIZE_MIN, FBNIC_RX_DESC_MIN) ||
+	    ring->rx_mini_pending < FBNIC_QUEUE_SIZE_MIN ||
+	    ring->rx_jumbo_pending < FBNIC_QUEUE_SIZE_MIN ||
+	    ring->tx_pending < max(FBNIC_QUEUE_SIZE_MIN, FBNIC_TX_DESC_MIN)) {
+		NL_SET_ERR_MSG_MOD(extack, "requested ring size too small");
+		return -EINVAL;
+	}
+
+	if (kernel_ring->tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_DISABLED) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot disable TCP data split");
+		return -EINVAL;
+	}
+
+	/* If an XDP program is attached, we should check for potential frame
+	 * splitting. If the new HDS threshold can cause splitting, we should
+	 * only allow if the attached XDP program can handle frags.
+	 */
+	if (fbnic_check_split_frames(fbn->xdp_prog, netdev->mtu,
+				     kernel_ring->hds_thresh)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Use higher HDS threshold or multi-buf capable program");
+		return -EINVAL;
+	}
+
+	if (!netif_running(netdev)) {
+		fbnic_set_rings(fbn, ring, kernel_ring);
+		return 0;
+	}
+
+	clone = fbnic_clone_create(fbn);
+	if (!clone)
+		return -ENOMEM;
+
+	fbnic_set_rings(clone, ring, kernel_ring);
+
+	err = fbnic_alloc_napi_vectors(clone);
+	if (err)
+		goto err_free_clone;
+
+	err = fbnic_alloc_resources(clone);
+	if (err)
+		goto err_free_napis;
+
+	fbnic_down_noidle(fbn);
+	err = fbnic_wait_all_queues_idle(fbn->fbd, true);
+	if (err)
+		goto err_start_stack;
+
+	err = fbnic_set_netif_queues(clone);
+	if (err)
+		goto err_start_stack;
+
+	/* Nothing can fail past this point */
+	fbnic_flush(fbn);
+
+	fbnic_clone_swap(fbn, clone);
+
+	fbnic_up(fbn);
+
+	fbnic_free_resources(clone);
+	fbnic_free_napi_vectors(clone);
+	fbnic_clone_free(clone);
+
+	return 0;
+
+err_start_stack:
+	fbnic_flush(fbn);
+	fbnic_up(fbn);
+	fbnic_free_resources(clone);
+err_free_napis:
+	fbnic_free_napi_vectors(clone);
+err_free_clone:
+	fbnic_clone_free(clone);
+	return err;
+}
+
+static void fbnic_get_rxb_enqueue_strings(u8 **data, unsigned int idx)
+{
+	const struct fbnic_stat *stat;
+	int i;
+
+	stat = fbnic_gstrings_rxb_enqueue_stats;
+	for (i = 0; i < FBNIC_HW_RXB_ENQUEUE_STATS_LEN; i++, stat++)
+		ethtool_sprintf(data, stat->string, idx);
+}
+
+static void fbnic_get_rxb_fifo_strings(u8 **data, unsigned int idx)
+{
+	const struct fbnic_stat *stat;
+	int i;
+
+	stat = fbnic_gstrings_rxb_fifo_stats;
+	for (i = 0; i < FBNIC_HW_RXB_FIFO_STATS_LEN; i++, stat++)
+		ethtool_sprintf(data, stat->string, idx);
+}
+
+static void fbnic_get_rxb_dequeue_strings(u8 **data, unsigned int idx)
+{
+	const struct fbnic_stat *stat;
+	int i;
+
+	stat = fbnic_gstrings_rxb_dequeue_stats;
+	for (i = 0; i < FBNIC_HW_RXB_DEQUEUE_STATS_LEN; i++, stat++)
+		ethtool_sprintf(data, stat->string, idx);
+}
+
+static void fbnic_get_xdp_queue_strings(u8 **data, unsigned int idx)
+{
+	const struct fbnic_stat *stat;
+	int i;
+
+	stat = fbnic_gstrings_xdp_stats;
+	for (i = 0; i < FBNIC_XDP_STATS_LEN; i++, stat++)
+		ethtool_sprintf(data, stat->string, idx);
+}
+
+static void fbnic_get_strings(struct net_device *dev, u32 sset, u8 *data)
+{
+	const struct fbnic_stat *stat;
+	int i, idx;
+
+	switch (sset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < FBNIC_HW_FIXED_STATS_LEN; i++)
+			ethtool_puts(&data, fbnic_gstrings_hw_stats[i].string);
+
+		for (i = 0; i < FBNIC_RXB_ENQUEUE_INDICES; i++)
+			fbnic_get_rxb_enqueue_strings(&data, i);
+
+		for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++)
+			fbnic_get_rxb_fifo_strings(&data, i);
+
+		for (i = 0; i < FBNIC_RXB_DEQUEUE_INDICES; i++)
+			fbnic_get_rxb_dequeue_strings(&data, i);
+
+		for (idx = 0; idx < FBNIC_MAX_QUEUES; idx++) {
+			stat = fbnic_gstrings_hw_q_stats;
+
+			for (i = 0; i < FBNIC_HW_Q_STATS_LEN; i++, stat++)
+				ethtool_sprintf(&data, stat->string, idx);
+		}
+
+		for (i = 0; i < FBNIC_MAX_XDPQS; i++)
+			fbnic_get_xdp_queue_strings(&data, i);
+		break;
+	}
+}
+
+static void fbnic_report_hw_stats(const struct fbnic_stat *stat,
+				  const void *base, int len, u64 **data)
+{
+	while (len--) {
+		u8 *curr = (u8 *)base + stat->offset;
+
+		**data = *(u64 *)curr;
+
+		stat++;
+		(*data)++;
+	}
+}
+
+static void fbnic_get_xdp_queue_stats(struct fbnic_ring *ring, u64 **data)
+{
+	const struct fbnic_stat *stat;
+	int i;
+
+	if (!ring) {
+		*data += FBNIC_XDP_STATS_LEN;
+		return;
+	}
+
+	stat = fbnic_gstrings_xdp_stats;
+	for (i = 0; i < FBNIC_XDP_STATS_LEN; i++, stat++, (*data)++) {
+		u8 *p = (u8 *)ring + stat->offset;
+
+		**data = *(u64 *)p;
+	}
+}
+
+static void fbnic_get_ethtool_stats(struct net_device *dev,
+				    struct ethtool_stats *stats, u64 *data)
+{
+	struct fbnic_net *fbn = netdev_priv(dev);
+	struct fbnic_dev *fbd = fbn->fbd;
+	int i;
+
+	fbnic_get_hw_stats(fbn->fbd);
+
+	spin_lock(&fbd->hw_stats.lock);
+	fbnic_report_hw_stats(fbnic_gstrings_hw_stats, &fbd->hw_stats,
+			      FBNIC_HW_FIXED_STATS_LEN, &data);
+
+	for (i = 0; i < FBNIC_RXB_ENQUEUE_INDICES; i++) {
+		const struct fbnic_rxb_enqueue_stats *enq;
+
+		enq = &fbd->hw_stats.rxb.enq[i];
+		fbnic_report_hw_stats(fbnic_gstrings_rxb_enqueue_stats,
+				      enq, FBNIC_HW_RXB_ENQUEUE_STATS_LEN,
+				      &data);
+	}
+
+	for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++) {
+		const struct fbnic_rxb_fifo_stats *fifo;
+
+		fifo = &fbd->hw_stats.rxb.fifo[i];
+		fbnic_report_hw_stats(fbnic_gstrings_rxb_fifo_stats,
+				      fifo, FBNIC_HW_RXB_FIFO_STATS_LEN,
+				      &data);
+	}
+
+	for (i = 0; i < FBNIC_RXB_DEQUEUE_INDICES; i++) {
+		const struct fbnic_rxb_dequeue_stats *deq;
+
+		deq = &fbd->hw_stats.rxb.deq[i];
+		fbnic_report_hw_stats(fbnic_gstrings_rxb_dequeue_stats,
+				      deq, FBNIC_HW_RXB_DEQUEUE_STATS_LEN,
+				      &data);
+	}
+
+	for (i  = 0; i < FBNIC_MAX_QUEUES; i++) {
+		const struct fbnic_hw_q_stats *hw_q = &fbd->hw_stats.hw_q[i];
+
+		fbnic_report_hw_stats(fbnic_gstrings_hw_q_stats, hw_q,
+				      FBNIC_HW_Q_STATS_LEN, &data);
+	}
+	spin_unlock(&fbd->hw_stats.lock);
+
+	for (i = 0; i < FBNIC_MAX_XDPQS; i++)
+		fbnic_get_xdp_queue_stats(fbn->tx[i + FBNIC_MAX_TXQS], &data);
+}
+
+static int fbnic_get_sset_count(struct net_device *dev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+		return FBNIC_STATS_LEN;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int fbnic_get_rss_hash_idx(u32 flow_type)
+{
+	switch (flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) {
+	case TCP_V4_FLOW:
+		return FBNIC_TCP4_HASH_OPT;
+	case TCP_V6_FLOW:
+		return FBNIC_TCP6_HASH_OPT;
+	case UDP_V4_FLOW:
+		return FBNIC_UDP4_HASH_OPT;
+	case UDP_V6_FLOW:
+		return FBNIC_UDP6_HASH_OPT;
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case AH_ESP_V4_FLOW:
+	case SCTP_V4_FLOW:
+	case IPV4_FLOW:
+	case IPV4_USER_FLOW:
+		return FBNIC_IPV4_HASH_OPT;
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case AH_ESP_V6_FLOW:
+	case SCTP_V6_FLOW:
+	case IPV6_FLOW:
+	case IPV6_USER_FLOW:
+		return FBNIC_IPV6_HASH_OPT;
+	case ETHER_FLOW:
+		return FBNIC_ETHER_HASH_OPT;
+	}
+
+	return -1;
+}
+
+static int fbnic_get_cls_rule_all(struct fbnic_net *fbn,
+				  struct ethtool_rxnfc *cmd,
+				  u32 *rule_locs)
+{
+	struct fbnic_dev *fbd = fbn->fbd;
+	int i, cnt = 0;
+
+	/* Report maximum rule count */
+	cmd->data = FBNIC_RPC_ACT_TBL_NFC_ENTRIES;
+
+	for (i = 0; i < FBNIC_RPC_ACT_TBL_NFC_ENTRIES; i++) {
+		int idx = i + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+		struct fbnic_act_tcam *act_tcam;
+
+		act_tcam = &fbd->act_tcam[idx];
+		if (act_tcam->state != FBNIC_TCAM_S_VALID)
+			continue;
+
+		if (rule_locs) {
+			if (cnt == cmd->rule_cnt)
+				return -EMSGSIZE;
+
+			rule_locs[cnt] = i;
+		}
+
+		cnt++;
+	}
+
+	return cnt;
+}
+
+static int fbnic_get_cls_rule(struct fbnic_net *fbn, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fsp;
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct fbnic_act_tcam *act_tcam;
+	int idx;
+
+	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
+
+	if (fsp->location >= FBNIC_RPC_ACT_TBL_NFC_ENTRIES)
+		return -EINVAL;
+
+	idx = fsp->location + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+	act_tcam = &fbd->act_tcam[idx];
+
+	if (act_tcam->state != FBNIC_TCAM_S_VALID)
+		return -EINVAL;
+
+	/* Report maximum rule count */
+	cmd->data = FBNIC_RPC_ACT_TBL_NFC_ENTRIES;
+
+	/* Set flow type field */
+	if (!(act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_IP_VALID)) {
+		fsp->flow_type = ETHER_FLOW;
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX,
+			       act_tcam->mask.tcam[1])) {
+			struct fbnic_mac_addr *mac_addr;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX,
+					act_tcam->value.tcam[1]);
+			mac_addr = &fbd->mac_addr[idx];
+
+			ether_addr_copy(fsp->h_u.ether_spec.h_dest,
+					mac_addr->value.addr8);
+			eth_broadcast_addr(fsp->m_u.ether_spec.h_dest);
+		}
+	} else if (act_tcam->value.tcam[1] &
+		   FBNIC_RPC_TCAM_ACT1_OUTER_IP_VALID) {
+		fsp->flow_type = IPV6_USER_FLOW;
+		fsp->h_u.usr_ip6_spec.l4_proto = IPPROTO_IPV6;
+		fsp->m_u.usr_ip6_spec.l4_proto = 0xff;
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+			int i;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ipo_src[idx];
+
+			for (i = 0; i < 4; i++) {
+				fsp->h_u.usr_ip6_spec.ip6src[i] =
+					ip_addr->value.s6_addr32[i];
+				fsp->m_u.usr_ip6_spec.ip6src[i] =
+					~ip_addr->mask.s6_addr32[i];
+			}
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+			int i;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ipo_dst[idx];
+
+			for (i = 0; i < 4; i++) {
+				fsp->h_u.usr_ip6_spec.ip6dst[i] =
+					ip_addr->value.s6_addr32[i];
+				fsp->m_u.usr_ip6_spec.ip6dst[i] =
+					~ip_addr->mask.s6_addr32[i];
+			}
+		}
+	} else if ((act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_IP_IS_V6)) {
+		if (act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_L4_VALID) {
+			if (act_tcam->value.tcam[1] &
+			    FBNIC_RPC_TCAM_ACT1_L4_IS_UDP)
+				fsp->flow_type = UDP_V6_FLOW;
+			else
+				fsp->flow_type = TCP_V6_FLOW;
+			fsp->h_u.tcp_ip6_spec.psrc =
+				cpu_to_be16(act_tcam->value.tcam[3]);
+			fsp->m_u.tcp_ip6_spec.psrc =
+				cpu_to_be16(~act_tcam->mask.tcam[3]);
+			fsp->h_u.tcp_ip6_spec.pdst =
+				cpu_to_be16(act_tcam->value.tcam[4]);
+			fsp->m_u.tcp_ip6_spec.pdst =
+				cpu_to_be16(~act_tcam->mask.tcam[4]);
+		} else {
+			fsp->flow_type = IPV6_USER_FLOW;
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+			int i;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ip_src[idx];
+
+			for (i = 0; i < 4; i++) {
+				fsp->h_u.usr_ip6_spec.ip6src[i] =
+					ip_addr->value.s6_addr32[i];
+				fsp->m_u.usr_ip6_spec.ip6src[i] =
+					~ip_addr->mask.s6_addr32[i];
+			}
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+			int i;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ip_dst[idx];
+
+			for (i = 0; i < 4; i++) {
+				fsp->h_u.usr_ip6_spec.ip6dst[i] =
+					ip_addr->value.s6_addr32[i];
+				fsp->m_u.usr_ip6_spec.ip6dst[i] =
+					~ip_addr->mask.s6_addr32[i];
+			}
+		}
+	} else {
+		if (act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_L4_VALID) {
+			if (act_tcam->value.tcam[1] &
+			    FBNIC_RPC_TCAM_ACT1_L4_IS_UDP)
+				fsp->flow_type = UDP_V4_FLOW;
+			else
+				fsp->flow_type = TCP_V4_FLOW;
+			fsp->h_u.tcp_ip4_spec.psrc =
+				cpu_to_be16(act_tcam->value.tcam[3]);
+			fsp->m_u.tcp_ip4_spec.psrc =
+				cpu_to_be16(~act_tcam->mask.tcam[3]);
+			fsp->h_u.tcp_ip4_spec.pdst =
+				cpu_to_be16(act_tcam->value.tcam[4]);
+			fsp->m_u.tcp_ip4_spec.pdst =
+				cpu_to_be16(~act_tcam->mask.tcam[4]);
+		} else {
+			fsp->flow_type = IPV4_USER_FLOW;
+			fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4;
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ip_src[idx];
+
+			fsp->h_u.usr_ip4_spec.ip4src =
+				ip_addr->value.s6_addr32[3];
+			fsp->m_u.usr_ip4_spec.ip4src =
+				~ip_addr->mask.s6_addr32[3];
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ip_dst[idx];
+
+			fsp->h_u.usr_ip4_spec.ip4dst =
+				ip_addr->value.s6_addr32[3];
+			fsp->m_u.usr_ip4_spec.ip4dst =
+				~ip_addr->mask.s6_addr32[3];
+		}
+	}
+
+	/* Record action */
+	if (act_tcam->dest & FBNIC_RPC_ACT_TBL0_DROP)
+		fsp->ring_cookie = RX_CLS_FLOW_DISC;
+	else if (act_tcam->dest & FBNIC_RPC_ACT_TBL0_Q_SEL)
+		fsp->ring_cookie = FIELD_GET(FBNIC_RPC_ACT_TBL0_Q_ID,
+					     act_tcam->dest);
+	else
+		fsp->flow_type |= FLOW_RSS;
+
+	cmd->rss_context = FIELD_GET(FBNIC_RPC_ACT_TBL0_RSS_CTXT_ID,
+				     act_tcam->dest);
+
+	return 0;
+}
+
+static int fbnic_get_rxnfc(struct net_device *netdev,
+			   struct ethtool_rxnfc *cmd, u32 *rule_locs)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	int ret = -EOPNOTSUPP;
+	u32 special = 0;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_GRXRINGS:
+		cmd->data = fbn->num_rx_queues;
+		ret = 0;
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		ret = fbnic_get_cls_rule(fbn, cmd);
+		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		rule_locs = NULL;
+		special = RX_CLS_LOC_SPECIAL;
+		fallthrough;
+	case ETHTOOL_GRXCLSRLALL:
+		ret = fbnic_get_cls_rule_all(fbn, cmd, rule_locs);
+		if (ret < 0)
+			break;
+
+		cmd->data |= special;
+		cmd->rule_cnt = ret;
+		ret = 0;
+		break;
+	}
+
+	return ret;
+}
+
+static int fbnic_cls_rule_any_loc(struct fbnic_dev *fbd)
+{
+	int i;
+
+	for (i = FBNIC_RPC_ACT_TBL_NFC_ENTRIES; i--;) {
+		int idx = i + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+
+		if (fbd->act_tcam[idx].state != FBNIC_TCAM_S_VALID)
+			return i;
+	}
+
+	return -ENOSPC;
+}
+
+static int fbnic_set_cls_rule_ins(struct fbnic_net *fbn,
+				  const struct ethtool_rxnfc *cmd)
+{
+	u16 flow_value = 0, flow_mask = 0xffff, ip_value = 0, ip_mask = 0xffff;
+	u16 sport = 0, sport_mask = ~0, dport = 0, dport_mask = ~0;
+	u16 misc = 0, misc_mask = ~0;
+	u32 dest = FIELD_PREP(FBNIC_RPC_ACT_TBL0_DEST_MASK,
+			      FBNIC_RPC_ACT_TBL0_DEST_HOST);
+	struct fbnic_ip_addr *ip_src = NULL, *ip_dst = NULL;
+	struct fbnic_mac_addr *mac_addr = NULL;
+	struct ethtool_rx_flow_spec *fsp;
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct fbnic_act_tcam *act_tcam;
+	struct in6_addr *addr6, *mask6;
+	struct in_addr *addr4, *mask4;
+	int hash_idx, location;
+	u32 flow_type;
+	int idx, j;
+
+	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
+
+	if (fsp->location != RX_CLS_LOC_ANY)
+		return -EINVAL;
+	location = fbnic_cls_rule_any_loc(fbd);
+	if (location < 0)
+		return location;
+
+	if (fsp->ring_cookie == RX_CLS_FLOW_DISC) {
+		dest = FBNIC_RPC_ACT_TBL0_DROP;
+	} else if (fsp->flow_type & FLOW_RSS) {
+		if (cmd->rss_context == 1)
+			dest |= FBNIC_RPC_ACT_TBL0_RSS_CTXT_ID;
+	} else {
+		u32 ring_idx = ethtool_get_flow_spec_ring(fsp->ring_cookie);
+
+		if (ring_idx >= fbn->num_rx_queues)
+			return -EINVAL;
+
+		dest |= FBNIC_RPC_ACT_TBL0_Q_SEL |
+			FIELD_PREP(FBNIC_RPC_ACT_TBL0_Q_ID, ring_idx);
+	}
+
+	idx = location + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+	act_tcam = &fbd->act_tcam[idx];
+
+	/* Do not allow overwriting for now.
+	 * To support overwriting rules we will need to add logic to free
+	 * any IP or MACDA TCAMs that may be associated with the old rule.
+	 */
+	if (act_tcam->state != FBNIC_TCAM_S_DISABLED)
+		return -EBUSY;
+
+	flow_type = fsp->flow_type & ~(FLOW_EXT | FLOW_RSS);
+	hash_idx = fbnic_get_rss_hash_idx(flow_type);
+
+	switch (flow_type) {
+	case UDP_V4_FLOW:
+udp4_flow:
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L4_IS_UDP;
+		fallthrough;
+	case TCP_V4_FLOW:
+tcp4_flow:
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L4_VALID;
+		flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_L4_IS_UDP |
+			       FBNIC_RPC_TCAM_ACT1_L4_VALID);
+
+		sport = be16_to_cpu(fsp->h_u.tcp_ip4_spec.psrc);
+		sport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip4_spec.psrc);
+		dport = be16_to_cpu(fsp->h_u.tcp_ip4_spec.pdst);
+		dport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip4_spec.pdst);
+		goto ip4_flow;
+	case IP_USER_FLOW:
+		if (!fsp->m_u.usr_ip4_spec.proto)
+			goto ip4_flow;
+		if (fsp->m_u.usr_ip4_spec.proto != 0xff)
+			return -EINVAL;
+		if (fsp->h_u.usr_ip4_spec.proto == IPPROTO_UDP)
+			goto udp4_flow;
+		if (fsp->h_u.usr_ip4_spec.proto == IPPROTO_TCP)
+			goto tcp4_flow;
+		return -EINVAL;
+ip4_flow:
+		addr4 = (struct in_addr *)&fsp->h_u.usr_ip4_spec.ip4src;
+		mask4 = (struct in_addr *)&fsp->m_u.usr_ip4_spec.ip4src;
+		if (mask4->s_addr) {
+			ip_src = __fbnic_ip4_sync(fbd, fbd->ip_src,
+						  addr4, mask4);
+			if (!ip_src)
+				return -ENOSPC;
+
+			set_bit(idx, ip_src->act_tcam);
+			ip_value |= FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+				    FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+					       ip_src - fbd->ip_src);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+				     FBNIC_RPC_TCAM_ACT0_IPSRC_IDX);
+		}
+
+		addr4 = (struct in_addr *)&fsp->h_u.usr_ip4_spec.ip4dst;
+		mask4 = (struct in_addr *)&fsp->m_u.usr_ip4_spec.ip4dst;
+		if (mask4->s_addr) {
+			ip_dst = __fbnic_ip4_sync(fbd, fbd->ip_dst,
+						  addr4, mask4);
+			if (!ip_dst) {
+				if (ip_src && ip_src->state == FBNIC_TCAM_S_ADD)
+					memset(ip_src, 0, sizeof(*ip_src));
+				return -ENOSPC;
+			}
+
+			set_bit(idx, ip_dst->act_tcam);
+			ip_value |= FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+				    FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+					       ip_dst - fbd->ip_dst);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+				     FBNIC_RPC_TCAM_ACT0_IPDST_IDX);
+		}
+		flow_value |= FBNIC_RPC_TCAM_ACT1_IP_VALID |
+			      FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID;
+		flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_IP_IS_V6 |
+			       FBNIC_RPC_TCAM_ACT1_IP_VALID |
+			       FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID);
+		break;
+	case UDP_V6_FLOW:
+udp6_flow:
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L4_IS_UDP;
+		fallthrough;
+	case TCP_V6_FLOW:
+tcp6_flow:
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L4_VALID;
+		flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_L4_IS_UDP |
+			  FBNIC_RPC_TCAM_ACT1_L4_VALID);
+
+		sport = be16_to_cpu(fsp->h_u.tcp_ip6_spec.psrc);
+		sport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip6_spec.psrc);
+		dport = be16_to_cpu(fsp->h_u.tcp_ip6_spec.pdst);
+		dport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip6_spec.pdst);
+		goto ipv6_flow;
+	case IPV6_USER_FLOW:
+		if (!fsp->m_u.usr_ip6_spec.l4_proto)
+			goto ipv6_flow;
+
+		if (fsp->m_u.usr_ip6_spec.l4_proto != 0xff)
+			return -EINVAL;
+		if (fsp->h_u.usr_ip6_spec.l4_proto == IPPROTO_UDP)
+			goto udp6_flow;
+		if (fsp->h_u.usr_ip6_spec.l4_proto == IPPROTO_TCP)
+			goto tcp6_flow;
+		if (fsp->h_u.usr_ip6_spec.l4_proto != IPPROTO_IPV6)
+			return -EINVAL;
+
+		addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6src;
+		mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6src;
+		if (!ipv6_addr_any(mask6)) {
+			ip_src = __fbnic_ip6_sync(fbd, fbd->ipo_src,
+						  addr6, mask6);
+			if (!ip_src)
+				return -ENOSPC;
+
+			set_bit(idx, ip_src->act_tcam);
+			ip_value |=
+				FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_VALID |
+				FIELD_PREP(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX,
+					   ip_src - fbd->ipo_src);
+			ip_mask &=
+				~(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_VALID |
+				  FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX);
+		}
+
+		addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6dst;
+		mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6dst;
+		if (!ipv6_addr_any(mask6)) {
+			ip_dst = __fbnic_ip6_sync(fbd, fbd->ipo_dst,
+						  addr6, mask6);
+			if (!ip_dst) {
+				if (ip_src && ip_src->state == FBNIC_TCAM_S_ADD)
+					memset(ip_src, 0, sizeof(*ip_src));
+				return -ENOSPC;
+			}
+
+			set_bit(idx, ip_dst->act_tcam);
+			ip_value |=
+				FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_VALID |
+				FIELD_PREP(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX,
+					   ip_dst - fbd->ipo_dst);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_VALID |
+				     FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX);
+		}
+
+		flow_value |= FBNIC_RPC_TCAM_ACT1_OUTER_IP_VALID;
+		flow_mask &= FBNIC_RPC_TCAM_ACT1_OUTER_IP_VALID;
+ipv6_flow:
+		addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6src;
+		mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6src;
+		if (!ip_src && !ipv6_addr_any(mask6)) {
+			ip_src = __fbnic_ip6_sync(fbd, fbd->ip_src,
+						  addr6, mask6);
+			if (!ip_src)
+				return -ENOSPC;
+
+			set_bit(idx, ip_src->act_tcam);
+			ip_value |= FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+				    FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+					       ip_src - fbd->ip_src);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+				       FBNIC_RPC_TCAM_ACT0_IPSRC_IDX);
+		}
+
+		addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6dst;
+		mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6dst;
+		if (!ip_dst && !ipv6_addr_any(mask6)) {
+			ip_dst = __fbnic_ip6_sync(fbd, fbd->ip_dst,
+						  addr6, mask6);
+			if (!ip_dst) {
+				if (ip_src && ip_src->state == FBNIC_TCAM_S_ADD)
+					memset(ip_src, 0, sizeof(*ip_src));
+				return -ENOSPC;
+			}
+
+			set_bit(idx, ip_dst->act_tcam);
+			ip_value |= FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+				    FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+					       ip_dst - fbd->ip_dst);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+				       FBNIC_RPC_TCAM_ACT0_IPDST_IDX);
+		}
+
+		flow_value |= FBNIC_RPC_TCAM_ACT1_IP_IS_V6 |
+			      FBNIC_RPC_TCAM_ACT1_IP_VALID |
+			      FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID;
+		flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_IP_IS_V6 |
+			       FBNIC_RPC_TCAM_ACT1_IP_VALID |
+			       FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID);
+		break;
+	case ETHER_FLOW:
+		if (!is_zero_ether_addr(fsp->m_u.ether_spec.h_dest)) {
+			u8 *addr = fsp->h_u.ether_spec.h_dest;
+			u8 *mask = fsp->m_u.ether_spec.h_dest;
+
+			/* Do not allow MAC addr of 0 */
+			if (is_zero_ether_addr(addr))
+				return -EINVAL;
+
+			/* Only support full MAC address to avoid
+			 * conflicts with other MAC addresses.
+			 */
+			if (!is_broadcast_ether_addr(mask))
+				return -EINVAL;
+
+			if (is_multicast_ether_addr(addr))
+				mac_addr = __fbnic_mc_sync(fbd, addr);
+			else
+				mac_addr = __fbnic_uc_sync(fbd, addr);
+
+			if (!mac_addr)
+				return -ENOSPC;
+
+			set_bit(idx, mac_addr->act_tcam);
+			flow_value |=
+				FIELD_PREP(FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX,
+					   mac_addr - fbd->mac_addr);
+			flow_mask &= ~FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX;
+		}
+
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID;
+		flow_mask &= ~FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Write action table values */
+	act_tcam->dest = dest;
+	act_tcam->rss_en_mask = fbnic_flow_hash_2_rss_en_mask(fbn, hash_idx);
+
+	/* Write IP Match value/mask to action_tcam[0] */
+	act_tcam->value.tcam[0] = ip_value;
+	act_tcam->mask.tcam[0] = ip_mask;
+
+	/* Write flow type value/mask to action_tcam[1] */
+	act_tcam->value.tcam[1] = flow_value;
+	act_tcam->mask.tcam[1] = flow_mask;
+
+	/* Write error, DSCP, extra L4 matches to action_tcam[2] */
+	act_tcam->value.tcam[2] = misc;
+	act_tcam->mask.tcam[2] = misc_mask;
+
+	/* Write source/destination port values */
+	act_tcam->value.tcam[3] = sport;
+	act_tcam->mask.tcam[3] = sport_mask;
+	act_tcam->value.tcam[4] = dport;
+	act_tcam->mask.tcam[4] = dport_mask;
+
+	for (j = 5; j < FBNIC_RPC_TCAM_ACT_WORD_LEN; j++)
+		act_tcam->mask.tcam[j] = 0xffff;
+
+	act_tcam->state = FBNIC_TCAM_S_UPDATE;
+	fsp->location = location;
+
+	if (netif_running(fbn->netdev)) {
+		fbnic_write_rules(fbd);
+		if (ip_src || ip_dst)
+			fbnic_write_ip_addr(fbd);
+		if (mac_addr)
+			fbnic_write_macda(fbd);
+	}
+
+	return 0;
+}
+
+static void fbnic_clear_nfc_macda(struct fbnic_net *fbn,
+				  unsigned int tcam_idx)
+{
+	struct fbnic_dev *fbd = fbn->fbd;
+	int idx;
+
+	for (idx = ARRAY_SIZE(fbd->mac_addr); idx--;)
+		__fbnic_xc_unsync(&fbd->mac_addr[idx], tcam_idx);
+
+	/* Write updates to hardware */
+	if (netif_running(fbn->netdev))
+		fbnic_write_macda(fbd);
+}
+
+static void fbnic_clear_nfc_ip_addr(struct fbnic_net *fbn,
+				    unsigned int tcam_idx)
+{
+	struct fbnic_dev *fbd = fbn->fbd;
+	int idx;
+
+	for (idx = ARRAY_SIZE(fbd->ip_src); idx--;)
+		__fbnic_ip_unsync(&fbd->ip_src[idx], tcam_idx);
+	for (idx = ARRAY_SIZE(fbd->ip_dst); idx--;)
+		__fbnic_ip_unsync(&fbd->ip_dst[idx], tcam_idx);
+	for (idx = ARRAY_SIZE(fbd->ipo_src); idx--;)
+		__fbnic_ip_unsync(&fbd->ipo_src[idx], tcam_idx);
+	for (idx = ARRAY_SIZE(fbd->ipo_dst); idx--;)
+		__fbnic_ip_unsync(&fbd->ipo_dst[idx], tcam_idx);
+
+	/* Write updates to hardware */
+	if (netif_running(fbn->netdev))
+		fbnic_write_ip_addr(fbd);
+}
+
+static int fbnic_set_cls_rule_del(struct fbnic_net *fbn,
+				  const struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fsp;
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct fbnic_act_tcam *act_tcam;
+	int idx;
+
+	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
+
+	if (fsp->location >= FBNIC_RPC_ACT_TBL_NFC_ENTRIES)
+		return -EINVAL;
+
+	idx = fsp->location + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+	act_tcam = &fbd->act_tcam[idx];
+
+	if (act_tcam->state != FBNIC_TCAM_S_VALID)
+		return -EINVAL;
+
+	act_tcam->state = FBNIC_TCAM_S_DELETE;
+
+	if ((act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID) &&
+	    (~act_tcam->mask.tcam[1] & FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX))
+		fbnic_clear_nfc_macda(fbn, idx);
+
+	if ((act_tcam->value.tcam[0] &
+	     (FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+	      FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+	      FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_VALID |
+	      FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_VALID)) &&
+	    (~act_tcam->mask.tcam[0] &
+	     (FBNIC_RPC_TCAM_ACT0_IPSRC_IDX |
+	      FBNIC_RPC_TCAM_ACT0_IPDST_IDX |
+	      FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX |
+	      FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX)))
+		fbnic_clear_nfc_ip_addr(fbn, idx);
+
+	if (netif_running(fbn->netdev))
+		fbnic_write_rules(fbd);
+
+	return 0;
+}
+
+static int fbnic_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	int ret = -EOPNOTSUPP;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		ret = fbnic_set_cls_rule_ins(fbn, cmd);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		ret = fbnic_set_cls_rule_del(fbn, cmd);
+		break;
+	}
+
+	return ret;
+}
+
+static u32 fbnic_get_rxfh_key_size(struct net_device *netdev)
+{
+	return FBNIC_RPC_RSS_KEY_BYTE_LEN;
+}
+
+static u32 fbnic_get_rxfh_indir_size(struct net_device *netdev)
+{
+	return FBNIC_RPC_RSS_TBL_SIZE;
+}
+
+static int
+fbnic_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	unsigned int i;
+
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+
+	if (rxfh->key) {
+		for (i = 0; i < FBNIC_RPC_RSS_KEY_BYTE_LEN; i++) {
+			u32 rss_key = fbn->rss_key[i / 4] << ((i % 4) * 8);
+
+			rxfh->key[i] = rss_key >> 24;
+		}
+	}
+
+	if (rxfh->indir) {
+		for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++)
+			rxfh->indir[i] = fbn->indir_tbl[0][i];
+	}
+
+	return 0;
+}
+
+static unsigned int
+fbnic_set_indir(struct fbnic_net *fbn, unsigned int idx, const u32 *indir)
+{
+	unsigned int i, changes = 0;
+
+	for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++) {
+		if (fbn->indir_tbl[idx][i] == indir[i])
+			continue;
+
+		fbn->indir_tbl[idx][i] = indir[i];
+		changes++;
+	}
+
+	return changes;
+}
+
+static int
+fbnic_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
+	       struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	unsigned int i, changes = 0;
+
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
+		return -EINVAL;
+
+	if (rxfh->key) {
+		u32 rss_key = 0;
+
+		for (i = FBNIC_RPC_RSS_KEY_BYTE_LEN; i--;) {
+			rss_key >>= 8;
+			rss_key |= (u32)(rxfh->key[i]) << 24;
+
+			if (i % 4)
+				continue;
+
+			if (fbn->rss_key[i / 4] == rss_key)
+				continue;
+
+			fbn->rss_key[i / 4] = rss_key;
+			changes++;
+		}
+	}
+
+	if (rxfh->indir)
+		changes += fbnic_set_indir(fbn, 0, rxfh->indir);
+
+	if (changes && netif_running(netdev))
+		fbnic_rss_reinit_hw(fbn->fbd, fbn);
+
+	return 0;
+}
+
+static int
+fbnic_get_rss_hash_opts(struct net_device *netdev,
+			struct ethtool_rxfh_fields *cmd)
+{
+	int hash_opt_idx = fbnic_get_rss_hash_idx(cmd->flow_type);
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	if (hash_opt_idx < 0)
+		return -EINVAL;
+
+	/* Report options from rss_en table in fbn */
+	cmd->data = fbn->rss_flow_hash[hash_opt_idx];
+
+	return 0;
+}
+
+#define FBNIC_L2_HASH_OPTIONS \
+	(RXH_L2DA | RXH_DISCARD)
+#define FBNIC_L3_HASH_OPTIONS \
+	(FBNIC_L2_HASH_OPTIONS | RXH_IP_SRC | RXH_IP_DST | RXH_IP6_FL)
+#define FBNIC_L4_HASH_OPTIONS \
+	(FBNIC_L3_HASH_OPTIONS | RXH_L4_B_0_1 | RXH_L4_B_2_3)
+
+static int
+fbnic_set_rss_hash_opts(struct net_device *netdev,
+			const struct ethtool_rxfh_fields *cmd,
+			struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	int hash_opt_idx;
+
+	/* Verify the type requested is correct */
+	hash_opt_idx = fbnic_get_rss_hash_idx(cmd->flow_type);
+	if (hash_opt_idx < 0)
+		return -EINVAL;
+
+	/* Verify the fields asked for can actually be assigned based on type */
+	if (cmd->data & ~FBNIC_L4_HASH_OPTIONS ||
+	    (hash_opt_idx > FBNIC_L4_HASH_OPT &&
+	     cmd->data & ~FBNIC_L3_HASH_OPTIONS) ||
+	    (hash_opt_idx > FBNIC_IP_HASH_OPT &&
+	     cmd->data & ~FBNIC_L2_HASH_OPTIONS))
+		return -EINVAL;
+
+	fbn->rss_flow_hash[hash_opt_idx] = cmd->data;
+
+	if (netif_running(fbn->netdev)) {
+		fbnic_rss_reinit(fbn->fbd, fbn);
+		fbnic_write_rules(fbn->fbd);
+	}
+
+	return 0;
+}
+
+static int
+fbnic_modify_rxfh_context(struct net_device *netdev,
+			  struct ethtool_rxfh_context *ctx,
+			  const struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	const u32 *indir = rxfh->indir;
+	unsigned int changes;
+
+	if (!indir)
+		indir = ethtool_rxfh_context_indir(ctx);
+
+	changes = fbnic_set_indir(fbn, rxfh->rss_context, indir);
+	if (changes && netif_running(netdev))
+		fbnic_rss_reinit_hw(fbn->fbd, fbn);
+
+	return 0;
+}
+
+static int
+fbnic_create_rxfh_context(struct net_device *netdev,
+			  struct ethtool_rxfh_context *ctx,
+			  const struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP) {
+		NL_SET_ERR_MSG_MOD(extack, "RSS hash function not supported");
+		return -EOPNOTSUPP;
+	}
+	ctx->hfunc = ETH_RSS_HASH_TOP;
+
+	if (!rxfh->indir) {
+		u32 *indir = ethtool_rxfh_context_indir(ctx);
+		unsigned int num_rx = fbn->num_rx_queues;
+		unsigned int i;
+
+		for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++)
+			indir[i] = ethtool_rxfh_indir_default(i, num_rx);
+	}
+
+	return fbnic_modify_rxfh_context(netdev, ctx, rxfh, extack);
+}
+
+static int
+fbnic_remove_rxfh_context(struct net_device *netdev,
+			  struct ethtool_rxfh_context *ctx, u32 rss_context,
+			  struct netlink_ext_ack *extack)
+{
+	/* Nothing to do, contexts are allocated statically */
+	return 0;
+}
+
+static void fbnic_get_channels(struct net_device *netdev,
+			       struct ethtool_channels *ch)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+
+	ch->max_rx = fbd->max_num_queues;
+	ch->max_tx = fbd->max_num_queues;
+	ch->max_combined = min(ch->max_rx, ch->max_tx);
+	ch->max_other =	FBNIC_NON_NAPI_VECTORS;
+
+	if (fbn->num_rx_queues > fbn->num_napi ||
+	    fbn->num_tx_queues > fbn->num_napi)
+		ch->combined_count = min(fbn->num_rx_queues,
+					 fbn->num_tx_queues);
+	else
+		ch->combined_count =
+			fbn->num_rx_queues + fbn->num_tx_queues - fbn->num_napi;
+	ch->rx_count = fbn->num_rx_queues - ch->combined_count;
+	ch->tx_count = fbn->num_tx_queues - ch->combined_count;
+	ch->other_count = FBNIC_NON_NAPI_VECTORS;
+}
+
+static void fbnic_set_queues(struct fbnic_net *fbn, struct ethtool_channels *ch,
+			     unsigned int max_napis)
+{
+	fbn->num_rx_queues = ch->rx_count + ch->combined_count;
+	fbn->num_tx_queues = ch->tx_count + ch->combined_count;
+	fbn->num_napi = min(ch->rx_count + ch->tx_count + ch->combined_count,
+			    max_napis);
+}
+
+static int fbnic_set_channels(struct net_device *netdev,
+			      struct ethtool_channels *ch)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	unsigned int max_napis, standalone;
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct fbnic_net *clone;
+	int err;
+
+	max_napis = fbd->num_irqs - FBNIC_NON_NAPI_VECTORS;
+	standalone = ch->rx_count + ch->tx_count;
+
+	/* Limits for standalone queues:
+	 *  - each queue has its own NAPI (num_napi >= rx + tx + combined)
+	 *  - combining queues (combined not 0, rx or tx must be 0)
+	 */
+	if ((ch->rx_count && ch->tx_count && ch->combined_count) ||
+	    (standalone && standalone + ch->combined_count > max_napis) ||
+	    ch->rx_count + ch->combined_count > fbd->max_num_queues ||
+	    ch->tx_count + ch->combined_count > fbd->max_num_queues ||
+	    ch->other_count != FBNIC_NON_NAPI_VECTORS)
+		return -EINVAL;
+
+	if (!netif_running(netdev)) {
+		fbnic_set_queues(fbn, ch, max_napis);
+		fbnic_reset_indir_tbl(fbn);
+		return 0;
+	}
+
+	clone = fbnic_clone_create(fbn);
+	if (!clone)
+		return -ENOMEM;
+
+	fbnic_set_queues(clone, ch, max_napis);
+
+	err = fbnic_alloc_napi_vectors(clone);
+	if (err)
+		goto err_free_clone;
+
+	err = fbnic_alloc_resources(clone);
+	if (err)
+		goto err_free_napis;
+
+	fbnic_down_noidle(fbn);
+	err = fbnic_wait_all_queues_idle(fbn->fbd, true);
+	if (err)
+		goto err_start_stack;
+
+	err = fbnic_set_netif_queues(clone);
+	if (err)
+		goto err_start_stack;
+
+	/* Nothing can fail past this point */
+	fbnic_flush(fbn);
+
+	fbnic_clone_swap(fbn, clone);
+
+	/* Reset RSS indirection table */
+	fbnic_reset_indir_tbl(fbn);
+
+	fbnic_up(fbn);
+
+	fbnic_free_resources(clone);
+	fbnic_free_napi_vectors(clone);
+	fbnic_clone_free(clone);
+
+	return 0;
+
+err_start_stack:
+	fbnic_flush(fbn);
+	fbnic_up(fbn);
+	fbnic_free_resources(clone);
+err_free_napis:
+	fbnic_free_napi_vectors(clone);
+err_free_clone:
+	fbnic_clone_free(clone);
+	return err;
+}
 
 static int
 fbnic_get_ts_info(struct net_device *netdev,
@@ -69,14 +1612,86 @@ fbnic_get_ts_info(struct net_device *netdev,
 	return 0;
 }
 
-static void
-fbnic_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
+static void fbnic_get_ts_stats(struct net_device *netdev,
+			       struct ethtool_ts_stats *ts_stats)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	u64 ts_packets, ts_lost;
+	struct fbnic_ring *ring;
+	unsigned int start;
+	int i;
+
+	ts_stats->pkts = fbn->tx_stats.twq.ts_packets;
+	ts_stats->lost = fbn->tx_stats.twq.ts_lost;
+	for (i = 0; i < fbn->num_tx_queues; i++) {
+		ring = fbn->tx[i];
+		do {
+			start = u64_stats_fetch_begin(&ring->stats.syncp);
+			ts_packets = ring->stats.twq.ts_packets;
+			ts_lost = ring->stats.twq.ts_lost;
+		} while (u64_stats_fetch_retry(&ring->stats.syncp, start));
+		ts_stats->pkts += ts_packets;
+		ts_stats->lost += ts_lost;
+	}
+}
+
+static int
+fbnic_get_module_eeprom_by_page(struct net_device *netdev,
+				const struct ethtool_module_eeprom *page_data,
+				struct netlink_ext_ack *extack)
 {
 	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_fw_completion *fw_cmpl;
 	struct fbnic_dev *fbd = fbn->fbd;
+	int err;
 
-	fbnic_get_fw_ver_commit_str(fbd, drvinfo->fw_version,
-				    sizeof(drvinfo->fw_version));
+	if (page_data->i2c_address != 0x50) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Invalid i2c address. Only 0x50 is supported");
+		return -EINVAL;
+	}
+
+	fw_cmpl = __fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_QSFP_READ_RESP,
+					page_data->length);
+	if (!fw_cmpl)
+		return -ENOMEM;
+
+	/* Initialize completion and queue it for FW to process */
+	fw_cmpl->u.qsfp.length = page_data->length;
+	fw_cmpl->u.qsfp.offset = page_data->offset;
+	fw_cmpl->u.qsfp.page = page_data->page;
+	fw_cmpl->u.qsfp.bank = page_data->bank;
+
+	err = fbnic_fw_xmit_qsfp_read_msg(fbd, fw_cmpl, page_data->page,
+					  page_data->bank, page_data->offset,
+					  page_data->length);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to transmit EEPROM read request");
+		goto exit_free;
+	}
+
+	if (!wait_for_completion_timeout(&fw_cmpl->done, 2 * HZ)) {
+		err = -ETIMEDOUT;
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Timed out waiting for firmware response");
+		goto exit_cleanup;
+	}
+
+	if (fw_cmpl->result) {
+		err = fw_cmpl->result;
+		NL_SET_ERR_MSG_MOD(extack, "Failed to read EEPROM");
+		goto exit_cleanup;
+	}
+
+	memcpy(page_data->data, fw_cmpl->u.qsfp.data, page_data->length);
+
+exit_cleanup:
+	fbnic_mbx_clear_cmpl(fbd, fw_cmpl);
+exit_free:
+	fbnic_fw_put_cmpl(fw_cmpl);
+
+	return err ? : page_data->length;
 }
 
 static void fbnic_set_counter(u64 *stat, struct fbnic_stat_counter *counter)
@@ -85,41 +1700,61 @@ static void fbnic_set_counter(u64 *stat, struct fbnic_stat_counter *counter)
 		*stat = counter->value;
 }
 
-static void fbnic_get_strings(struct net_device *dev, u32 sset, u8 *data)
+static void
+fbnic_get_pause_stats(struct net_device *netdev,
+		      struct ethtool_pause_stats *pause_stats)
 {
-	int i;
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_mac_stats *mac_stats;
+	struct fbnic_dev *fbd = fbn->fbd;
 
-	switch (sset) {
-	case ETH_SS_STATS:
-		for (i = 0; i < FBNIC_HW_STATS_LEN; i++)
-			ethtool_puts(&data, fbnic_gstrings_hw_stats[i].string);
-		break;
-	}
+	mac_stats = &fbd->hw_stats.mac;
+
+	fbd->mac->get_pause_stats(fbd, false, &mac_stats->pause);
+
+	pause_stats->tx_pause_frames = mac_stats->pause.tx_pause_frames.value;
+	pause_stats->rx_pause_frames = mac_stats->pause.rx_pause_frames.value;
 }
 
-static int fbnic_get_sset_count(struct net_device *dev, int sset)
+static void
+fbnic_get_fec_stats(struct net_device *netdev,
+		    struct ethtool_fec_stats *fec_stats,
+		    struct ethtool_fec_hist *hist)
 {
-	switch (sset) {
-	case ETH_SS_STATS:
-		return FBNIC_HW_STATS_LEN;
-	default:
-		return -EOPNOTSUPP;
-	}
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_phy_stats *phy_stats;
+	struct fbnic_dev *fbd = fbn->fbd;
+
+	fbnic_get_hw_stats32(fbd);
+	phy_stats = &fbd->hw_stats.phy;
+
+	spin_lock(&fbd->hw_stats.lock);
+	fec_stats->corrected_blocks.total =
+		phy_stats->fec.corrected_blocks.value;
+	fec_stats->uncorrectable_blocks.total =
+		phy_stats->fec.uncorrectable_blocks.value;
+	spin_unlock(&fbd->hw_stats.lock);
 }
 
-static void fbnic_get_ethtool_stats(struct net_device *dev,
-				    struct ethtool_stats *stats, u64 *data)
+static void
+fbnic_get_eth_phy_stats(struct net_device *netdev,
+			struct ethtool_eth_phy_stats *eth_phy_stats)
 {
-	struct fbnic_net *fbn = netdev_priv(dev);
-	const struct fbnic_stat *stat;
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_phy_stats *phy_stats;
+	struct fbnic_dev *fbd = fbn->fbd;
+	u64 total = 0;
 	int i;
 
-	fbnic_get_hw_stats(fbn->fbd);
+	fbnic_get_hw_stats32(fbd);
+	phy_stats = &fbd->hw_stats.phy;
 
-	for (i = 0; i < FBNIC_HW_STATS_LEN; i++) {
-		stat = &fbnic_gstrings_hw_stats[i];
-		data[i] = *(u64 *)((u8 *)&fbn->fbd->hw_stats + stat->offset);
-	}
+	spin_lock(&fbd->hw_stats.lock);
+	for (i = 0; i < FBNIC_PCS_MAX_LANES; i++)
+		total += phy_stats->pcs.SymbolErrorDuringCarrier.lanes[i].value;
+
+	eth_phy_stats->SymbolErrorDuringCarrier = total;
+	spin_unlock(&fbd->hw_stats.lock);
 }
 
 static void
@@ -164,54 +1799,123 @@ fbnic_get_eth_mac_stats(struct net_device *netdev,
 			  &mac_stats->eth_mac.FrameTooLongErrors);
 }
 
-static void fbnic_get_ts_stats(struct net_device *netdev,
-			       struct ethtool_ts_stats *ts_stats)
+static void
+fbnic_get_eth_ctrl_stats(struct net_device *netdev,
+			 struct ethtool_eth_ctrl_stats *eth_ctrl_stats)
 {
 	struct fbnic_net *fbn = netdev_priv(netdev);
-	u64 ts_packets, ts_lost;
-	struct fbnic_ring *ring;
-	unsigned int start;
-	int i;
+	struct fbnic_mac_stats *mac_stats;
+	struct fbnic_dev *fbd = fbn->fbd;
 
-	ts_stats->pkts = fbn->tx_stats.ts_packets;
-	ts_stats->lost = fbn->tx_stats.ts_lost;
-	for (i = 0; i < fbn->num_tx_queues; i++) {
-		ring = fbn->tx[i];
-		do {
-			start = u64_stats_fetch_begin(&ring->stats.syncp);
-			ts_packets = ring->stats.ts_packets;
-			ts_lost = ring->stats.ts_lost;
-		} while (u64_stats_fetch_retry(&ring->stats.syncp, start));
-		ts_stats->pkts += ts_packets;
-		ts_stats->lost += ts_lost;
-	}
+	mac_stats = &fbd->hw_stats.mac;
+
+	fbd->mac->get_eth_ctrl_stats(fbd, false, &mac_stats->eth_ctrl);
+
+	eth_ctrl_stats->MACControlFramesReceived =
+		mac_stats->eth_ctrl.MACControlFramesReceived.value;
+	eth_ctrl_stats->MACControlFramesTransmitted =
+		mac_stats->eth_ctrl.MACControlFramesTransmitted.value;
 }
 
-static void fbnic_get_regs(struct net_device *netdev,
-			   struct ethtool_regs *regs, void *data)
+static const struct ethtool_rmon_hist_range fbnic_rmon_ranges[] = {
+	{    0,   64 },
+	{   65,  127 },
+	{  128,  255 },
+	{  256,  511 },
+	{  512, 1023 },
+	{ 1024, 1518 },
+	{ 1519, 2047 },
+	{ 2048, 4095 },
+	{ 4096, 8191 },
+	{ 8192, 9216 },
+	{ 9217, FBNIC_MAX_JUMBO_FRAME_SIZE },
+	{}
+};
+
+static void
+fbnic_get_rmon_stats(struct net_device *netdev,
+		     struct ethtool_rmon_stats *rmon_stats,
+		     const struct ethtool_rmon_hist_range **ranges)
 {
 	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_mac_stats *mac_stats;
+	struct fbnic_dev *fbd = fbn->fbd;
+	int i;
 
-	fbnic_csr_get_regs(fbn->fbd, data, &regs->version);
+	mac_stats = &fbd->hw_stats.mac;
+
+	fbd->mac->get_rmon_stats(fbd, false, &mac_stats->rmon);
+
+	rmon_stats->undersize_pkts =
+		mac_stats->rmon.undersize_pkts.value;
+	rmon_stats->oversize_pkts =
+		mac_stats->rmon.oversize_pkts.value;
+	rmon_stats->fragments =
+		mac_stats->rmon.fragments.value;
+	rmon_stats->jabbers =
+		mac_stats->rmon.jabbers.value;
+
+	for (i = 0; fbnic_rmon_ranges[i].high; i++) {
+		rmon_stats->hist[i] = mac_stats->rmon.hist[i].value;
+		rmon_stats->hist_tx[i] = mac_stats->rmon.hist_tx[i].value;
+	}
+
+	*ranges = fbnic_rmon_ranges;
 }
 
-static int fbnic_get_regs_len(struct net_device *netdev)
+static void fbnic_get_link_ext_stats(struct net_device *netdev,
+				     struct ethtool_link_ext_stats *stats)
 {
 	struct fbnic_net *fbn = netdev_priv(netdev);
 
-	return fbnic_csr_regs_len(fbn->fbd) * sizeof(u32);
+	stats->link_down_events = fbn->link_down_events;
 }
 
 static const struct ethtool_ops fbnic_ethtool_ops = {
-	.get_drvinfo		= fbnic_get_drvinfo,
-	.get_regs_len		= fbnic_get_regs_len,
-	.get_regs		= fbnic_get_regs,
-	.get_strings		= fbnic_get_strings,
-	.get_ethtool_stats	= fbnic_get_ethtool_stats,
-	.get_sset_count		= fbnic_get_sset_count,
-	.get_ts_info		= fbnic_get_ts_info,
-	.get_ts_stats		= fbnic_get_ts_stats,
-	.get_eth_mac_stats	= fbnic_get_eth_mac_stats,
+	.cap_link_lanes_supported	= true,
+	.supported_coalesce_params	= ETHTOOL_COALESCE_USECS |
+					  ETHTOOL_COALESCE_RX_MAX_FRAMES,
+	.supported_ring_params		= ETHTOOL_RING_USE_TCP_DATA_SPLIT |
+					  ETHTOOL_RING_USE_HDS_THRS,
+	.rxfh_max_num_contexts		= FBNIC_RPC_RSS_TBL_COUNT,
+	.get_drvinfo			= fbnic_get_drvinfo,
+	.get_regs_len			= fbnic_get_regs_len,
+	.get_regs			= fbnic_get_regs,
+	.get_link			= ethtool_op_get_link,
+	.get_link_ext_stats		= fbnic_get_link_ext_stats,
+	.get_coalesce			= fbnic_get_coalesce,
+	.set_coalesce			= fbnic_set_coalesce,
+	.get_ringparam			= fbnic_get_ringparam,
+	.set_ringparam			= fbnic_set_ringparam,
+	.get_pause_stats		= fbnic_get_pause_stats,
+	.get_pauseparam			= fbnic_phylink_get_pauseparam,
+	.set_pauseparam			= fbnic_phylink_set_pauseparam,
+	.get_strings			= fbnic_get_strings,
+	.get_ethtool_stats		= fbnic_get_ethtool_stats,
+	.get_sset_count			= fbnic_get_sset_count,
+	.get_rxnfc			= fbnic_get_rxnfc,
+	.set_rxnfc			= fbnic_set_rxnfc,
+	.get_rxfh_key_size		= fbnic_get_rxfh_key_size,
+	.get_rxfh_indir_size		= fbnic_get_rxfh_indir_size,
+	.get_rxfh			= fbnic_get_rxfh,
+	.set_rxfh			= fbnic_set_rxfh,
+	.get_rxfh_fields		= fbnic_get_rss_hash_opts,
+	.set_rxfh_fields		= fbnic_set_rss_hash_opts,
+	.create_rxfh_context		= fbnic_create_rxfh_context,
+	.modify_rxfh_context		= fbnic_modify_rxfh_context,
+	.remove_rxfh_context		= fbnic_remove_rxfh_context,
+	.get_channels			= fbnic_get_channels,
+	.set_channels			= fbnic_set_channels,
+	.get_ts_info			= fbnic_get_ts_info,
+	.get_ts_stats			= fbnic_get_ts_stats,
+	.get_link_ksettings		= fbnic_phylink_ethtool_ksettings_get,
+	.get_fec_stats			= fbnic_get_fec_stats,
+	.get_fecparam			= fbnic_phylink_get_fecparam,
+	.get_module_eeprom_by_page	= fbnic_get_module_eeprom_by_page,
+	.get_eth_phy_stats		= fbnic_get_eth_phy_stats,
+	.get_eth_mac_stats		= fbnic_get_eth_mac_stats,
+	.get_eth_ctrl_stats		= fbnic_get_eth_ctrl_stats,
+	.get_rmon_stats			= fbnic_get_rmon_stats,
 };
 
 void fbnic_set_ethtool_ops(struct net_device *dev)
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index 8f7a2a19ddf8..d8d9b6cfde82 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -17,11 +17,29 @@ static void __fbnic_mbx_wr_desc(struct fbnic_dev *fbd, int mbx_idx,
 {
 	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
 
+	/* Write the upper 32b and then the lower 32b. Doing this the
+	 * FW can then read lower, upper, lower to verify that the state
+	 * of the descriptor wasn't changed mid-transaction.
+	 */
 	fw_wr32(fbd, desc_offset + 1, upper_32_bits(desc));
 	fw_wrfl(fbd);
 	fw_wr32(fbd, desc_offset, lower_32_bits(desc));
 }
 
+static void __fbnic_mbx_invalidate_desc(struct fbnic_dev *fbd, int mbx_idx,
+					int desc_idx, u32 desc)
+{
+	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
+
+	/* For initialization we write the lower 32b of the descriptor first.
+	 * This way we can set the state to mark it invalid before we clear the
+	 * upper 32b.
+	 */
+	fw_wr32(fbd, desc_offset, desc);
+	fw_wrfl(fbd);
+	fw_wr32(fbd, desc_offset + 1, 0);
+}
+
 static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
 {
 	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
@@ -33,29 +51,41 @@ static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
 	return desc;
 }
 
-static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_reset_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	int desc_idx;
 
+	/* Disable DMA transactions from the device,
+	 * and flush any transactions triggered during cleaning
+	 */
+	switch (mbx_idx) {
+	case FBNIC_IPC_MBX_RX_IDX:
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH);
+		break;
+	case FBNIC_IPC_MBX_TX_IDX:
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH);
+		break;
+	}
+
+	wrfl(fbd);
+
 	/* Initialize first descriptor to all 0s. Doing this gives us a
 	 * solid stop for the firmware to hit when it is done looping
 	 * through the ring.
 	 */
-	__fbnic_mbx_wr_desc(fbd, mbx_idx, 0, 0);
-
-	fw_wrfl(fbd);
+	__fbnic_mbx_invalidate_desc(fbd, mbx_idx, 0, 0);
 
 	/* We then fill the rest of the ring starting at the end and moving
 	 * back toward descriptor 0 with skip descriptors that have no
 	 * length nor address, and tell the firmware that they can skip
 	 * them and just move past them to the one we initialized to 0.
 	 */
-	for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;) {
-		__fbnic_mbx_wr_desc(fbd, mbx_idx, desc_idx,
-				    FBNIC_IPC_MBX_DESC_FW_CMPL |
-				    FBNIC_IPC_MBX_DESC_HOST_CMPL);
-		fw_wrfl(fbd);
-	}
+	for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;)
+		__fbnic_mbx_invalidate_desc(fbd, mbx_idx, desc_idx,
+					    FBNIC_IPC_MBX_DESC_FW_CMPL |
+					    FBNIC_IPC_MBX_DESC_HOST_CMPL);
 }
 
 void fbnic_mbx_init(struct fbnic_dev *fbd)
@@ -65,6 +95,9 @@ void fbnic_mbx_init(struct fbnic_dev *fbd)
 	/* Initialize lock to protect Tx ring */
 	spin_lock_init(&fbd->fw_tx_lock);
 
+	/* Reset FW Capabilities */
+	memset(&fbd->fw_cap, 0, sizeof(fbd->fw_cap));
+
 	/* Reinitialize mailbox memory */
 	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
 		memset(&fbd->mbx[i], 0, sizeof(struct fbnic_fw_mbx));
@@ -76,7 +109,7 @@ void fbnic_mbx_init(struct fbnic_dev *fbd)
 	wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
 	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
-		fbnic_mbx_init_desc_ring(fbd, i);
+		fbnic_mbx_reset_desc_ring(fbd, i);
 }
 
 static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx,
@@ -97,11 +130,8 @@ static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx,
 		return -EBUSY;
 
 	addr = dma_map_single(fbd->dev, msg, PAGE_SIZE, direction);
-	if (dma_mapping_error(fbd->dev, addr)) {
-		free_page((unsigned long)msg);
-
+	if (dma_mapping_error(fbd->dev, addr))
 		return -ENOSPC;
-	}
 
 	mbx->buf_info[tail].msg = msg;
 	mbx->buf_info[tail].addr = addr;
@@ -141,7 +171,7 @@ static void fbnic_mbx_clean_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	int i;
 
-	fbnic_mbx_init_desc_ring(fbd, mbx_idx);
+	fbnic_mbx_reset_desc_ring(fbd, mbx_idx);
 
 	for (i = FBNIC_IPC_MBX_DESC_LEN; i--;)
 		fbnic_mbx_unmap_and_free_msg(fbd, mbx_idx, i);
@@ -171,7 +201,7 @@ static int fbnic_mbx_alloc_rx_msgs(struct fbnic_dev *fbd)
 		return -ENODEV;
 
 	/* Fill all but 1 unused descriptors in the Rx queue. */
-	count = (head - tail - 1) % FBNIC_IPC_MBX_DESC_LEN;
+	count = (head - tail - 1) & (FBNIC_IPC_MBX_DESC_LEN - 1);
 	while (!err && count--) {
 		struct fbnic_tlv_msg *msg;
 
@@ -207,6 +237,44 @@ static int fbnic_mbx_map_tlv_msg(struct fbnic_dev *fbd,
 	return err;
 }
 
+static int fbnic_mbx_set_cmpl_slot(struct fbnic_dev *fbd,
+				   struct fbnic_fw_completion *cmpl_data)
+{
+	struct fbnic_fw_mbx *tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
+	int free = -EXFULL;
+	int i;
+
+	if (!tx_mbx->ready)
+		return -ENODEV;
+
+	for (i = 0; i < FBNIC_MBX_CMPL_SLOTS; i++) {
+		if (!fbd->cmpl_data[i])
+			free = i;
+		else if (fbd->cmpl_data[i]->msg_type == cmpl_data->msg_type)
+			return -EEXIST;
+	}
+
+	if (free == -EXFULL)
+		return -EXFULL;
+
+	fbd->cmpl_data[free] = cmpl_data;
+
+	return 0;
+}
+
+static void fbnic_mbx_clear_cmpl_slot(struct fbnic_dev *fbd,
+				      struct fbnic_fw_completion *cmpl_data)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_MBX_CMPL_SLOTS; i++) {
+		if (fbd->cmpl_data[i] == cmpl_data) {
+			fbd->cmpl_data[i] = NULL;
+			break;
+		}
+	}
+}
+
 static void fbnic_mbx_process_tx_msgs(struct fbnic_dev *fbd)
 {
 	struct fbnic_fw_mbx *tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
@@ -228,6 +296,89 @@ static void fbnic_mbx_process_tx_msgs(struct fbnic_dev *fbd)
 	tx_mbx->head = head;
 }
 
+int fbnic_mbx_set_cmpl(struct fbnic_dev *fbd,
+		       struct fbnic_fw_completion *cmpl_data)
+{
+	unsigned long flags;
+	int err;
+
+	spin_lock_irqsave(&fbd->fw_tx_lock, flags);
+	err = fbnic_mbx_set_cmpl_slot(fbd, cmpl_data);
+	spin_unlock_irqrestore(&fbd->fw_tx_lock, flags);
+
+	return err;
+}
+
+static int fbnic_mbx_map_req_w_cmpl(struct fbnic_dev *fbd,
+				    struct fbnic_tlv_msg *msg,
+				    struct fbnic_fw_completion *cmpl_data)
+{
+	unsigned long flags;
+	int err;
+
+	spin_lock_irqsave(&fbd->fw_tx_lock, flags);
+	if (cmpl_data) {
+		err = fbnic_mbx_set_cmpl_slot(fbd, cmpl_data);
+		if (err)
+			goto unlock_mbx;
+	}
+
+	err = fbnic_mbx_map_msg(fbd, FBNIC_IPC_MBX_TX_IDX, msg,
+				le16_to_cpu(msg->hdr.len) * sizeof(u32), 1);
+
+	/* If we successfully reserved a completion and msg failed
+	 * then clear completion data for next caller
+	 */
+	if (err && cmpl_data)
+		fbnic_mbx_clear_cmpl_slot(fbd, cmpl_data);
+
+unlock_mbx:
+	spin_unlock_irqrestore(&fbd->fw_tx_lock, flags);
+
+	return err;
+}
+
+void fbnic_mbx_clear_cmpl(struct fbnic_dev *fbd,
+			  struct fbnic_fw_completion *fw_cmpl)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&fbd->fw_tx_lock, flags);
+	fbnic_mbx_clear_cmpl_slot(fbd, fw_cmpl);
+	spin_unlock_irqrestore(&fbd->fw_tx_lock, flags);
+}
+
+static void fbnic_fw_release_cmpl_data(struct kref *kref)
+{
+	struct fbnic_fw_completion *cmpl_data;
+
+	cmpl_data = container_of(kref, struct fbnic_fw_completion,
+				 ref_count);
+	kfree(cmpl_data);
+}
+
+static struct fbnic_fw_completion *
+fbnic_fw_get_cmpl_by_type(struct fbnic_dev *fbd, u32 msg_type)
+{
+	struct fbnic_fw_completion *cmpl_data = NULL;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&fbd->fw_tx_lock, flags);
+	for (i = 0; i < FBNIC_MBX_CMPL_SLOTS; i++) {
+		if (fbd->cmpl_data[i] &&
+		    fbd->cmpl_data[i]->msg_type == msg_type) {
+			cmpl_data = fbd->cmpl_data[i];
+			kref_get(&cmpl_data->ref_count);
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&fbd->fw_tx_lock, flags);
+
+	return cmpl_data;
+}
+
 /**
  * fbnic_fw_xmit_simple_msg - Transmit a simple single TLV message w/o data
  * @fbd: FBNIC device structure
@@ -235,11 +386,11 @@ static void fbnic_mbx_process_tx_msgs(struct fbnic_dev *fbd)
  *
  * Return:
  *   One the following values:
- *     -EOPNOTSUPP: Is not ASIC so mailbox is not supported
- *     -ENODEV: Device I/O error
- *     -ENOMEM: Failed to allocate message
- *     -EBUSY: No space in mailbox
- *     -ENOSPC: DMA mapping failed
+ *	-EOPNOTSUPP: Is not ASIC so mailbox is not supported
+ *	-ENODEV: Device I/O error
+ *	-ENOMEM: Failed to allocate message
+ *	-EBUSY: No space in mailbox
+ *	-ENOSPC: DMA mapping failed
  *
  * This function sends a single TLV header indicating the host wants to take
  * some action. However there are no other side effects which means that any
@@ -265,67 +416,41 @@ static int fbnic_fw_xmit_simple_msg(struct fbnic_dev *fbd, u32 msg_type)
 	return err;
 }
 
-/**
- * fbnic_fw_xmit_cap_msg - Allocate and populate a FW capabilities message
- * @fbd: FBNIC device structure
- *
- * Return: NULL on failure to allocate, error pointer on error, or pointer
- * to new TLV test message.
- *
- * Sends a single TLV header indicating the host wants the firmware to
- * confirm the capabilities and version.
- **/
-static int fbnic_fw_xmit_cap_msg(struct fbnic_dev *fbd)
-{
-	int err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
-
-	/* Return 0 if we are not calling this on ASIC */
-	return (err == -EOPNOTSUPP) ? 0 : err;
-}
-
-static void fbnic_mbx_postinit_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	struct fbnic_fw_mbx *mbx = &fbd->mbx[mbx_idx];
 
-	/* This is a one time init, so just exit if it is completed */
-	if (mbx->ready)
-		return;
-
 	mbx->ready = true;
 
 	switch (mbx_idx) {
 	case FBNIC_IPC_MBX_RX_IDX:
+		/* Enable DMA writes from the device */
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME);
+
 		/* Make sure we have a page for the FW to write to */
 		fbnic_mbx_alloc_rx_msgs(fbd);
 		break;
 	case FBNIC_IPC_MBX_TX_IDX:
-		/* Force version to 1 if we successfully requested an update
-		 * from the firmware. This should be overwritten once we get
-		 * the actual version from the firmware in the capabilities
-		 * request message.
-		 */
-		if (!fbnic_fw_xmit_cap_msg(fbd) &&
-		    !fbd->fw_cap.running.mgmt.version)
-			fbd->fw_cap.running.mgmt.version = 1;
+		/* Enable DMA reads from the device */
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
 		break;
 	}
 }
 
-static void fbnic_mbx_postinit(struct fbnic_dev *fbd)
+static bool fbnic_mbx_event(struct fbnic_dev *fbd)
 {
-	int i;
-
-	/* We only need to do this on the first interrupt following init.
+	/* We only need to do this on the first interrupt following reset.
 	 * this primes the mailbox so that we will have cleared all the
 	 * skip descriptors.
 	 */
 	if (!(rd32(fbd, FBNIC_INTR_STATUS(0)) & (1u << FBNIC_FW_MSIX_ENTRY)))
-		return;
+		return false;
 
 	wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
-	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
-		fbnic_mbx_postinit_desc_ring(fbd, i);
+	return true;
 }
 
 /**
@@ -370,6 +495,11 @@ int fbnic_fw_xmit_ownership_msg(struct fbnic_dev *fbd, bool take_ownership)
 
 	fbd->last_heartbeat_request = req_time;
 
+	/* Set prev_firmware_time to 0 to avoid triggering firmware crash
+	 * detection until we receive the second uptime in a heartbeat resp.
+	 */
+	fbd->prev_firmware_time = 0;
+
 	/* Set heartbeat detection based on if we are taking ownership */
 	fbd->fw_heartbeat_enabled = take_ownership;
 
@@ -403,6 +533,7 @@ static const struct fbnic_tlv_index fbnic_fw_cap_resp_index[] = {
 	FBNIC_TLV_ATTR_U32(FBNIC_FW_CAP_RESP_UEFI_VERSION),
 	FBNIC_TLV_ATTR_STRING(FBNIC_FW_CAP_RESP_UEFI_COMMIT_STR,
 			      FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE),
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_CAP_RESP_ANTI_ROLLBACK_VERSION),
 	FBNIC_TLV_ATTR_LAST
 };
 
@@ -437,29 +568,25 @@ static int fbnic_fw_parse_bmc_addrs(u8 bmc_mac_addr[][ETH_ALEN],
 
 static int fbnic_fw_parse_cap_resp(void *opaque, struct fbnic_tlv_msg **results)
 {
-	u32 active_slot = 0, all_multi = 0;
+	u32 all_multi = 0, version = 0;
 	struct fbnic_dev *fbd = opaque;
-	u32 speed = 0, fec = 0;
-	size_t commit_size = 0;
 	bool bmc_present;
 	int err;
 
-	get_unsigned_result(FBNIC_FW_CAP_RESP_VERSION,
-			    fbd->fw_cap.running.mgmt.version);
-
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_VERSION);
+	fbd->fw_cap.running.mgmt.version = version;
 	if (!fbd->fw_cap.running.mgmt.version)
 		return -EINVAL;
 
-	if (fbd->fw_cap.running.mgmt.version < MIN_FW_VERSION_CODE) {
+	if (fbd->fw_cap.running.mgmt.version < MIN_FW_VER_CODE) {
+		char required_ver[FBNIC_FW_VER_MAX_SIZE];
 		char running_ver[FBNIC_FW_VER_MAX_SIZE];
 
 		fbnic_mk_fw_ver_str(fbd->fw_cap.running.mgmt.version,
 				    running_ver);
-		dev_err(fbd->dev, "Device firmware version(%s) is older than minimum required version(%02d.%02d.%02d)\n",
-			running_ver,
-			MIN_FW_MAJOR_VERSION,
-			MIN_FW_MINOR_VERSION,
-			MIN_FW_BUILD_VERSION);
+		fbnic_mk_fw_ver_str(MIN_FW_VER_CODE, required_ver);
+		dev_err(fbd->dev, "Device firmware version(%s) is older than minimum required version(%s)\n",
+			running_ver, required_ver);
 		/* Disable TX mailbox to prevent card use until firmware is
 		 * updated.
 		 */
@@ -467,43 +594,41 @@ static int fbnic_fw_parse_cap_resp(void *opaque, struct fbnic_tlv_msg **results)
 		return -EINVAL;
 	}
 
-	get_string_result(FBNIC_FW_CAP_RESP_VERSION_COMMIT_STR, commit_size,
-			  fbd->fw_cap.running.mgmt.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-	if (!commit_size)
+	if (fta_get_str(results, FBNIC_FW_CAP_RESP_VERSION_COMMIT_STR,
+			fbd->fw_cap.running.mgmt.commit,
+			FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE) <= 0)
 		dev_warn(fbd->dev, "Firmware did not send mgmt commit!\n");
 
-	get_unsigned_result(FBNIC_FW_CAP_RESP_STORED_VERSION,
-			    fbd->fw_cap.stored.mgmt.version);
-	get_string_result(FBNIC_FW_CAP_RESP_STORED_COMMIT_STR, commit_size,
-			  fbd->fw_cap.stored.mgmt.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_CMRT_VERSION,
-			    fbd->fw_cap.running.bootloader.version);
-	get_string_result(FBNIC_FW_CAP_RESP_CMRT_COMMIT_STR, commit_size,
-			  fbd->fw_cap.running.bootloader.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_STORED_CMRT_VERSION,
-			    fbd->fw_cap.stored.bootloader.version);
-	get_string_result(FBNIC_FW_CAP_RESP_STORED_CMRT_COMMIT_STR, commit_size,
-			  fbd->fw_cap.stored.bootloader.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_UEFI_VERSION,
-			    fbd->fw_cap.stored.undi.version);
-	get_string_result(FBNIC_FW_CAP_RESP_UEFI_COMMIT_STR, commit_size,
-			  fbd->fw_cap.stored.undi.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_ACTIVE_FW_SLOT, active_slot);
-	fbd->fw_cap.active_slot = active_slot;
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_FW_LINK_SPEED, speed);
-	get_unsigned_result(FBNIC_FW_CAP_RESP_FW_LINK_FEC, fec);
-	fbd->fw_cap.link_speed = speed;
-	fbd->fw_cap.link_fec = fec;
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_STORED_VERSION);
+	fbd->fw_cap.stored.mgmt.version = version;
+	fta_get_str(results, FBNIC_FW_CAP_RESP_STORED_COMMIT_STR,
+		    fbd->fw_cap.stored.mgmt.commit,
+		    FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
+
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_CMRT_VERSION);
+	fbd->fw_cap.running.bootloader.version = version;
+	fta_get_str(results, FBNIC_FW_CAP_RESP_CMRT_COMMIT_STR,
+		    fbd->fw_cap.running.bootloader.commit,
+		    FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
+
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_STORED_CMRT_VERSION);
+	fbd->fw_cap.stored.bootloader.version = version;
+	fta_get_str(results, FBNIC_FW_CAP_RESP_STORED_CMRT_COMMIT_STR,
+		    fbd->fw_cap.stored.bootloader.commit,
+		    FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
+
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_UEFI_VERSION);
+	fbd->fw_cap.stored.undi.version = version;
+	fta_get_str(results, FBNIC_FW_CAP_RESP_UEFI_COMMIT_STR,
+		    fbd->fw_cap.stored.undi.commit,
+		    FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
+
+	fbd->fw_cap.active_slot =
+		fta_get_uint(results, FBNIC_FW_CAP_RESP_ACTIVE_FW_SLOT);
+	fbd->fw_cap.link_speed =
+		fta_get_uint(results, FBNIC_FW_CAP_RESP_FW_LINK_SPEED);
+	fbd->fw_cap.link_fec =
+		fta_get_uint(results, FBNIC_FW_CAP_RESP_FW_LINK_FEC);
 
 	bmc_present = !!results[FBNIC_FW_CAP_RESP_BMC_PRESENT];
 	if (bmc_present) {
@@ -518,7 +643,8 @@ static int fbnic_fw_parse_cap_resp(void *opaque, struct fbnic_tlv_msg **results)
 		if (err)
 			return err;
 
-		get_unsigned_result(FBNIC_FW_CAP_RESP_BMC_ALL_MULTI, all_multi);
+		all_multi =
+			fta_get_uint(results, FBNIC_FW_CAP_RESP_BMC_ALL_MULTI);
 	} else {
 		memset(fbd->fw_cap.bmc_mac_addr, 0,
 		       sizeof(fbd->fw_cap.bmc_mac_addr));
@@ -529,10 +655,17 @@ static int fbnic_fw_parse_cap_resp(void *opaque, struct fbnic_tlv_msg **results)
 	if (results[FBNIC_FW_CAP_RESP_BMC_ALL_MULTI] || !bmc_present)
 		fbd->fw_cap.all_multi = all_multi;
 
+	fbd->fw_cap.anti_rollback_version =
+		fta_get_uint(results, FBNIC_FW_CAP_RESP_ANTI_ROLLBACK_VERSION);
+
+	/* Always assume we need a BMC reinit */
+	fbd->fw_cap.need_bmc_tcam_reinit = true;
+
 	return 0;
 }
 
 static const struct fbnic_tlv_index fbnic_ownership_resp_index[] = {
+	FBNIC_TLV_ATTR_U64(FBNIC_FW_OWNERSHIP_TIME),
 	FBNIC_TLV_ATTR_LAST
 };
 
@@ -544,10 +677,14 @@ static int fbnic_fw_parse_ownership_resp(void *opaque,
 	/* Count the ownership response as a heartbeat reply */
 	fbd->last_heartbeat_response = jiffies;
 
+	/* Capture firmware time for logging and firmware crash check */
+	fbd->firmware_time = fta_get_uint(results, FBNIC_FW_OWNERSHIP_TIME);
+
 	return 0;
 }
 
 static const struct fbnic_tlv_index fbnic_heartbeat_resp_index[] = {
+	FBNIC_TLV_ATTR_U64(FBNIC_FW_HEARTBEAT_UPTIME),
 	FBNIC_TLV_ATTR_LAST
 };
 
@@ -558,6 +695,9 @@ static int fbnic_fw_parse_heartbeat_resp(void *opaque,
 
 	fbd->last_heartbeat_response = jiffies;
 
+	/* Capture firmware time for logging and firmware crash check */
+	fbd->firmware_time = fta_get_uint(results, FBNIC_FW_HEARTBEAT_UPTIME);
+
 	return 0;
 }
 
@@ -579,6 +719,7 @@ static int fbnic_fw_xmit_heartbeat_message(struct fbnic_dev *fbd)
 		goto free_message;
 
 	fbd->last_heartbeat_request = req_time;
+	fbd->prev_firmware_time = fbd->firmware_time;
 
 	return err;
 
@@ -639,7 +780,8 @@ void fbnic_fw_check_heartbeat(struct fbnic_dev *fbd)
 		return;
 
 	/* Was the last heartbeat response long time ago? */
-	if (!fbnic_fw_heartbeat_current(fbd)) {
+	if (!fbnic_fw_heartbeat_current(fbd) ||
+	    fbd->firmware_time < fbd->prev_firmware_time) {
 		dev_warn(fbd->dev,
 			 "Firmware did not respond to heartbeat message\n");
 		fbd->fw_heartbeat_enabled = false;
@@ -651,6 +793,769 @@ void fbnic_fw_check_heartbeat(struct fbnic_dev *fbd)
 		dev_warn(fbd->dev, "Failed to send heartbeat message\n");
 }
 
+/**
+ * fbnic_fw_xmit_coredump_info_msg - Create and transmit a coredump info message
+ * @fbd: FBNIC device structure
+ * @cmpl_data: Structure to store info in
+ * @force: Force coredump event if one hasn't already occurred
+ *
+ * Return: zero on success, negative errno on failure
+ *
+ * Asks the FW for info related to coredump. If a coredump doesn't exist it
+ * can optionally force one if force is true.
+ */
+int fbnic_fw_xmit_coredump_info_msg(struct fbnic_dev *fbd,
+				    struct fbnic_fw_completion *cmpl_data,
+				    bool force)
+{
+	struct fbnic_tlv_msg *msg;
+	int err = 0;
+
+	msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_COREDUMP_GET_INFO_REQ);
+	if (!msg)
+		return -ENOMEM;
+
+	if (force) {
+		err = fbnic_tlv_attr_put_flag(msg, FBNIC_FW_COREDUMP_REQ_INFO_CREATE);
+		if (err)
+			goto free_msg;
+	}
+
+	err = fbnic_mbx_map_req_w_cmpl(fbd, msg, cmpl_data);
+	if (err)
+		goto free_msg;
+
+	return 0;
+
+free_msg:
+	free_page((unsigned long)msg);
+	return err;
+}
+
+static const struct fbnic_tlv_index fbnic_coredump_info_resp_index[] = {
+	FBNIC_TLV_ATTR_FLAG(FBNIC_FW_COREDUMP_INFO_AVAILABLE),
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_COREDUMP_INFO_SIZE),
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_COREDUMP_INFO_ERROR),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int
+fbnic_fw_parse_coredump_info_resp(void *opaque, struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_dev *fbd = opaque;
+	u32 msg_type;
+	s32 err;
+
+	/* Verify we have a completion pointer to provide with data */
+	msg_type = FBNIC_TLV_MSG_ID_COREDUMP_GET_INFO_RESP;
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd, msg_type);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	err = fta_get_sint(results, FBNIC_FW_COREDUMP_INFO_ERROR);
+	if (err)
+		goto msg_err;
+
+	if (!results[FBNIC_FW_COREDUMP_INFO_AVAILABLE]) {
+		err = -ENOENT;
+		goto msg_err;
+	}
+
+	cmpl_data->u.coredump_info.size =
+		fta_get_uint(results, FBNIC_FW_COREDUMP_INFO_SIZE);
+
+msg_err:
+	cmpl_data->result = err;
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return err;
+}
+
+/**
+ * fbnic_fw_xmit_coredump_read_msg - Create and transmit a coredump read request
+ * @fbd: FBNIC device structure
+ * @cmpl_data: Completion struct to store coredump
+ * @offset: Offset into coredump requested
+ * @length: Length of section of coredump to fetch
+ *
+ * Return: zero on success, negative errno on failure
+ *
+ * Asks the firmware to provide a section of the coredump back in a message.
+ * The response will have an offset and size matching the values provided.
+ */
+int fbnic_fw_xmit_coredump_read_msg(struct fbnic_dev *fbd,
+				    struct fbnic_fw_completion *cmpl_data,
+				    u32 offset, u32 length)
+{
+	struct fbnic_tlv_msg *msg;
+	int err = 0;
+
+	msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_COREDUMP_READ_REQ);
+	if (!msg)
+		return -ENOMEM;
+
+	if (offset) {
+		err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_COREDUMP_READ_OFFSET,
+					     offset);
+		if (err)
+			goto free_message;
+	}
+
+	if (length) {
+		err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_COREDUMP_READ_LENGTH,
+					     length);
+		if (err)
+			goto free_message;
+	}
+
+	err = fbnic_mbx_map_req_w_cmpl(fbd, msg, cmpl_data);
+	if (err)
+		goto free_message;
+
+	return 0;
+
+free_message:
+	free_page((unsigned long)msg);
+	return err;
+}
+
+static const struct fbnic_tlv_index fbnic_coredump_resp_index[] = {
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_COREDUMP_READ_OFFSET),
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_COREDUMP_READ_LENGTH),
+	FBNIC_TLV_ATTR_RAW_DATA(FBNIC_FW_COREDUMP_READ_DATA),
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_COREDUMP_READ_ERROR),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_coredump_resp(void *opaque,
+					struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	u32 index, last_offset, last_length;
+	struct fbnic_dev *fbd = opaque;
+	struct fbnic_tlv_msg *data_hdr;
+	u32 length, offset;
+	u32 msg_type;
+	s32 err;
+
+	/* Verify we have a completion pointer to provide with data */
+	msg_type = FBNIC_TLV_MSG_ID_COREDUMP_READ_RESP;
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd, msg_type);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	err = fta_get_sint(results, FBNIC_FW_COREDUMP_READ_ERROR);
+	if (err)
+		goto msg_err;
+
+	data_hdr = results[FBNIC_FW_COREDUMP_READ_DATA];
+	if (!data_hdr) {
+		err = -ENODATA;
+		goto msg_err;
+	}
+
+	offset = fta_get_uint(results, FBNIC_FW_COREDUMP_READ_OFFSET);
+	length = fta_get_uint(results, FBNIC_FW_COREDUMP_READ_LENGTH);
+
+	if (length > le16_to_cpu(data_hdr->hdr.len) - sizeof(u32)) {
+		dev_err(fbd->dev, "length greater than size of message\n");
+		err = -EINVAL;
+		goto msg_err;
+	}
+
+	/* Only the last offset can have a length != stride */
+	last_length =
+		(cmpl_data->u.coredump.size % cmpl_data->u.coredump.stride) ? :
+		cmpl_data->u.coredump.stride;
+	last_offset = cmpl_data->u.coredump.size - last_length;
+
+	/* Verify offset and length */
+	if (offset % cmpl_data->u.coredump.stride || offset > last_offset) {
+		dev_err(fbd->dev, "offset %d out of range\n", offset);
+		err = -EINVAL;
+	} else if (length != ((offset == last_offset) ?
+			      last_length : cmpl_data->u.coredump.stride)) {
+		dev_err(fbd->dev, "length %d out of range for offset %d\n",
+			length, offset);
+		err = -EINVAL;
+	}
+	if (err)
+		goto msg_err;
+
+	/* If data pointer is NULL it is already filled, just skip the copy */
+	index = offset / cmpl_data->u.coredump.stride;
+	if (!cmpl_data->u.coredump.data[index])
+		goto msg_err;
+
+	/* Copy data and mark index filled by setting pointer to NULL */
+	memcpy(cmpl_data->u.coredump.data[index],
+	       fbnic_tlv_attr_get_value_ptr(data_hdr), length);
+	cmpl_data->u.coredump.data[index] = NULL;
+
+msg_err:
+	cmpl_data->result = err;
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return err;
+}
+
+int fbnic_fw_xmit_fw_start_upgrade(struct fbnic_dev *fbd,
+				   struct fbnic_fw_completion *cmpl_data,
+				   unsigned int id, unsigned int len)
+{
+	struct fbnic_tlv_msg *msg;
+	int err;
+
+	if (!fbnic_fw_present(fbd))
+		return -ENODEV;
+
+	if (!len)
+		return -EINVAL;
+
+	msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_FW_START_UPGRADE_REQ);
+	if (!msg)
+		return -ENOMEM;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_START_UPGRADE_SECTION, id);
+	if (err)
+		goto free_message;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_START_UPGRADE_IMAGE_LENGTH,
+				     len);
+	if (err)
+		goto free_message;
+
+	err = fbnic_mbx_map_req_w_cmpl(fbd, msg, cmpl_data);
+	if (err)
+		goto free_message;
+
+	return 0;
+
+free_message:
+	free_page((unsigned long)msg);
+	return err;
+}
+
+static const struct fbnic_tlv_index fbnic_fw_start_upgrade_resp_index[] = {
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_START_UPGRADE_ERROR),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_fw_start_upgrade_resp(void *opaque,
+						struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_dev *fbd = opaque;
+	u32 msg_type;
+	s32 err;
+
+	/* Verify we have a completion pointer */
+	msg_type = FBNIC_TLV_MSG_ID_FW_START_UPGRADE_REQ;
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd, msg_type);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	/* Check for errors */
+	err = fta_get_sint(results, FBNIC_FW_START_UPGRADE_ERROR);
+
+	cmpl_data->result = err;
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return 0;
+}
+
+int fbnic_fw_xmit_fw_write_chunk(struct fbnic_dev *fbd,
+				 const u8 *data, u32 offset, u16 length,
+				 int cancel_error)
+{
+	struct fbnic_tlv_msg *msg;
+	int err;
+
+	msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_RESP);
+	if (!msg)
+		return -ENOMEM;
+
+	/* Report error to FW to cancel upgrade */
+	if (cancel_error) {
+		err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_WRITE_CHUNK_ERROR,
+					     cancel_error);
+		if (err)
+			goto free_message;
+	}
+
+	if (data) {
+		err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_WRITE_CHUNK_OFFSET,
+					     offset);
+		if (err)
+			goto free_message;
+
+		err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_WRITE_CHUNK_LENGTH,
+					     length);
+		if (err)
+			goto free_message;
+
+		err = fbnic_tlv_attr_put_value(msg, FBNIC_FW_WRITE_CHUNK_DATA,
+					       data + offset, length);
+		if (err)
+			goto free_message;
+	}
+
+	err = fbnic_mbx_map_tlv_msg(fbd, msg);
+	if (err)
+		goto free_message;
+
+	return 0;
+
+free_message:
+	free_page((unsigned long)msg);
+	return err;
+}
+
+static const struct fbnic_tlv_index fbnic_fw_write_chunk_req_index[] = {
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_WRITE_CHUNK_OFFSET),
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_WRITE_CHUNK_LENGTH),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_fw_write_chunk_req(void *opaque,
+					     struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_dev *fbd = opaque;
+	u32 msg_type;
+	u32 offset;
+	u32 length;
+
+	/* Verify we have a completion pointer */
+	msg_type = FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_REQ;
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd, msg_type);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	/* Pull length/offset pair and mark it as complete */
+	offset = fta_get_uint(results, FBNIC_FW_WRITE_CHUNK_OFFSET);
+	length = fta_get_uint(results, FBNIC_FW_WRITE_CHUNK_LENGTH);
+	cmpl_data->u.fw_update.offset = offset;
+	cmpl_data->u.fw_update.length = length;
+
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return 0;
+}
+
+static const struct fbnic_tlv_index fbnic_fw_finish_upgrade_req_index[] = {
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_FINISH_UPGRADE_ERROR),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_fw_finish_upgrade_req(void *opaque,
+						struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_dev *fbd = opaque;
+	u32 msg_type;
+	s32 err;
+
+	/* Verify we have a completion pointer */
+	msg_type = FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_REQ;
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd, msg_type);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	/* Check for errors */
+	err = fta_get_sint(results, FBNIC_FW_FINISH_UPGRADE_ERROR);
+
+	/* Close out update by incrementing offset by length which should
+	 * match the total size of the component. Set length to 0 since no
+	 * new chunks will be requested.
+	 */
+	cmpl_data->u.fw_update.offset += cmpl_data->u.fw_update.length;
+	cmpl_data->u.fw_update.length = 0;
+
+	cmpl_data->result = err;
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return 0;
+}
+
+/**
+ * fbnic_fw_xmit_qsfp_read_msg - Transmit a QSFP read request
+ * @fbd: FBNIC device structure
+ * @cmpl_data: Structure to store EEPROM response in
+ * @page: Refers to page number on page enabled QSFP modules
+ * @bank: Refers to a collection of pages
+ * @offset: Offset into QSFP EEPROM requested
+ * @length: Length of section of QSFP EEPROM to fetch
+ *
+ * Return: zero on success, negative value on failure
+ *
+ * Asks the firmware to provide a section of the QSFP EEPROM back in a
+ * message. The response will have an offset and size matching the values
+ * provided.
+ */
+int fbnic_fw_xmit_qsfp_read_msg(struct fbnic_dev *fbd,
+				struct fbnic_fw_completion *cmpl_data,
+				u32 page, u32 bank, u32 offset, u32 length)
+{
+	struct fbnic_tlv_msg *msg;
+	int err = 0;
+
+	if (!length || length > TLV_MAX_DATA)
+		return -EINVAL;
+
+	msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_QSFP_READ_REQ);
+	if (!msg)
+		return -ENOMEM;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_QSFP_BANK, bank);
+	if (err)
+		goto free_message;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_QSFP_PAGE, page);
+	if (err)
+		goto free_message;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_QSFP_OFFSET, offset);
+	if (err)
+		goto free_message;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_QSFP_LENGTH, length);
+	if (err)
+		goto free_message;
+
+	err = fbnic_mbx_map_req_w_cmpl(fbd, msg, cmpl_data);
+	if (err)
+		goto free_message;
+
+	return 0;
+
+free_message:
+	free_page((unsigned long)msg);
+	return err;
+}
+
+static const struct fbnic_tlv_index fbnic_qsfp_read_resp_index[] = {
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_QSFP_BANK),
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_QSFP_PAGE),
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_QSFP_OFFSET),
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_QSFP_LENGTH),
+	FBNIC_TLV_ATTR_RAW_DATA(FBNIC_FW_QSFP_DATA),
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_QSFP_ERROR),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_qsfp_read_resp(void *opaque,
+					 struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_dev *fbd = opaque;
+	struct fbnic_tlv_msg *data_hdr;
+	u32 length, offset, page, bank;
+	u8 *data;
+	s32 err;
+
+	/* Verify we have a completion pointer to provide with data */
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd,
+					      FBNIC_TLV_MSG_ID_QSFP_READ_RESP);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	bank = fta_get_uint(results, FBNIC_FW_QSFP_BANK);
+	if (bank != cmpl_data->u.qsfp.bank) {
+		dev_warn(fbd->dev, "bank not equal to bank requested: %d vs %d\n",
+			 bank, cmpl_data->u.qsfp.bank);
+		err = -EINVAL;
+		goto msg_err;
+	}
+
+	page = fta_get_uint(results, FBNIC_FW_QSFP_PAGE);
+	if (page != cmpl_data->u.qsfp.page) {
+		dev_warn(fbd->dev, "page not equal to page requested: %d vs %d\n",
+			 page, cmpl_data->u.qsfp.page);
+		err = -EINVAL;
+		goto msg_err;
+	}
+
+	offset = fta_get_uint(results, FBNIC_FW_QSFP_OFFSET);
+	length = fta_get_uint(results, FBNIC_FW_QSFP_LENGTH);
+
+	if (length != cmpl_data->u.qsfp.length ||
+	    offset != cmpl_data->u.qsfp.offset) {
+		dev_warn(fbd->dev,
+			 "offset/length not equal to size requested: %d/%d vs %d/%d\n",
+			 offset, length,
+			 cmpl_data->u.qsfp.offset, cmpl_data->u.qsfp.length);
+		err = -EINVAL;
+		goto msg_err;
+	}
+
+	err = fta_get_sint(results, FBNIC_FW_QSFP_ERROR);
+	if (err)
+		goto msg_err;
+
+	data_hdr = results[FBNIC_FW_QSFP_DATA];
+	if (!data_hdr) {
+		err = -ENODATA;
+		goto msg_err;
+	}
+
+	/* Copy data */
+	data = fbnic_tlv_attr_get_value_ptr(data_hdr);
+	memcpy(cmpl_data->u.qsfp.data, data, length);
+msg_err:
+	cmpl_data->result = err;
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return err;
+}
+
+/**
+ * fbnic_fw_xmit_tsene_read_msg - Create and transmit a sensor read request
+ * @fbd: FBNIC device structure
+ * @cmpl_data: Completion data structure to store sensor response
+ *
+ * Asks the firmware to provide an update with the latest sensor data.
+ * The response will contain temperature and voltage readings.
+ *
+ * Return: 0 on success, negative error value on failure
+ */
+int fbnic_fw_xmit_tsene_read_msg(struct fbnic_dev *fbd,
+				 struct fbnic_fw_completion *cmpl_data)
+{
+	struct fbnic_tlv_msg *msg;
+	int err;
+
+	if (!fbnic_fw_present(fbd))
+		return -ENODEV;
+
+	msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_TSENE_READ_REQ);
+	if (!msg)
+		return -ENOMEM;
+
+	err = fbnic_mbx_map_req_w_cmpl(fbd, msg, cmpl_data);
+	if (err)
+		goto free_message;
+
+	return 0;
+
+free_message:
+	free_page((unsigned long)msg);
+	return err;
+}
+
+static const struct fbnic_tlv_index fbnic_tsene_read_resp_index[] = {
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_TSENE_THERM),
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_TSENE_VOLT),
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_TSENE_ERROR),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_tsene_read_resp(void *opaque,
+					  struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_dev *fbd = opaque;
+	s32 err_resp;
+	int err = 0;
+
+	/* Verify we have a completion pointer to provide with data */
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd,
+					      FBNIC_TLV_MSG_ID_TSENE_READ_RESP);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	err_resp = fta_get_sint(results, FBNIC_FW_TSENE_ERROR);
+	if (err_resp)
+		goto msg_err;
+
+	if (!results[FBNIC_FW_TSENE_THERM] || !results[FBNIC_FW_TSENE_VOLT]) {
+		err = -EINVAL;
+		goto msg_err;
+	}
+
+	cmpl_data->u.tsene.millidegrees =
+		fta_get_sint(results, FBNIC_FW_TSENE_THERM);
+	cmpl_data->u.tsene.millivolts =
+		fta_get_sint(results, FBNIC_FW_TSENE_VOLT);
+
+msg_err:
+	cmpl_data->result = err_resp ? : err;
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return err;
+}
+
+static const struct fbnic_tlv_index fbnic_fw_log_req_index[] = {
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_LOG_MSEC),
+	FBNIC_TLV_ATTR_U64(FBNIC_FW_LOG_INDEX),
+	FBNIC_TLV_ATTR_STRING(FBNIC_FW_LOG_MSG, FBNIC_FW_LOG_MAX_SIZE),
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_LOG_LENGTH),
+	FBNIC_TLV_ATTR_ARRAY(FBNIC_FW_LOG_MSEC_ARRAY),
+	FBNIC_TLV_ATTR_ARRAY(FBNIC_FW_LOG_INDEX_ARRAY),
+	FBNIC_TLV_ATTR_ARRAY(FBNIC_FW_LOG_MSG_ARRAY),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_process_log_array(struct fbnic_tlv_msg **results,
+				      u16 length, u16 arr_type_idx,
+				      u16 attr_type_idx,
+				      struct fbnic_tlv_msg **tlv_array_out)
+{
+	struct fbnic_tlv_msg *attr;
+	int attr_len;
+	int err;
+
+	if (!results[attr_type_idx])
+		return -EINVAL;
+
+	tlv_array_out[0] = results[attr_type_idx];
+
+	if (!length)
+		return 0;
+
+	if (!results[arr_type_idx])
+		return -EINVAL;
+
+	attr = results[arr_type_idx];
+	attr_len = le16_to_cpu(attr->hdr.len) / sizeof(u32) - 1;
+	err = fbnic_tlv_attr_parse_array(&attr[1], attr_len, &tlv_array_out[1],
+					 fbnic_fw_log_req_index,
+					 attr_type_idx,
+					 length);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int fbnic_fw_parse_logs(struct fbnic_dev *fbd,
+			       struct fbnic_tlv_msg **msec_tlv,
+			       struct fbnic_tlv_msg **index_tlv,
+			       struct fbnic_tlv_msg **log_tlv,
+			       int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		char log[FBNIC_FW_LOG_MAX_SIZE];
+		ssize_t len;
+		u64 index;
+		u32 msec;
+		int err;
+
+		if (!msec_tlv[i] || !index_tlv[i] || !log_tlv[i]) {
+			dev_warn(fbd->dev, "Received log message with missing attributes!\n");
+			return -EINVAL;
+		}
+
+		index = fbnic_tlv_attr_get_signed(index_tlv[i], 0);
+		msec = fbnic_tlv_attr_get_signed(msec_tlv[i], 0);
+		len = fbnic_tlv_attr_get_string(log_tlv[i], log,
+						FBNIC_FW_LOG_MAX_SIZE);
+		if (len < 0)
+			return len;
+
+		err = fbnic_fw_log_write(fbd, index, msec, log);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int fbnic_fw_parse_log_req(void *opaque,
+				  struct fbnic_tlv_msg **results)
+{
+	struct fbnic_tlv_msg *index_tlv[FBNIC_FW_MAX_LOG_HISTORY];
+	struct fbnic_tlv_msg *msec_tlv[FBNIC_FW_MAX_LOG_HISTORY];
+	struct fbnic_tlv_msg *log_tlv[FBNIC_FW_MAX_LOG_HISTORY];
+	struct fbnic_dev *fbd = opaque;
+	u16 length;
+	int err;
+
+	length = fta_get_uint(results, FBNIC_FW_LOG_LENGTH);
+	if (length >= FBNIC_FW_MAX_LOG_HISTORY)
+		return -E2BIG;
+
+	err = fbnic_fw_process_log_array(results, length,
+					 FBNIC_FW_LOG_MSEC_ARRAY,
+					 FBNIC_FW_LOG_MSEC, msec_tlv);
+	if (err)
+		return err;
+
+	err = fbnic_fw_process_log_array(results, length,
+					 FBNIC_FW_LOG_INDEX_ARRAY,
+					 FBNIC_FW_LOG_INDEX, index_tlv);
+	if (err)
+		return err;
+
+	err = fbnic_fw_process_log_array(results, length,
+					 FBNIC_FW_LOG_MSG_ARRAY,
+					 FBNIC_FW_LOG_MSG, log_tlv);
+	if (err)
+		return err;
+
+	err = fbnic_fw_parse_logs(fbd, msec_tlv, index_tlv, log_tlv,
+				  length + 1);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int fbnic_fw_xmit_send_logs(struct fbnic_dev *fbd, bool enable,
+			    bool send_log_history)
+{
+	struct fbnic_tlv_msg *msg;
+	int err;
+
+	if (fbd->fw_cap.running.mgmt.version < MIN_FW_VER_CODE_LOG) {
+		dev_warn(fbd->dev, "Firmware version is too old to support firmware logs!\n");
+		return -EOPNOTSUPP;
+	}
+
+	msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_LOG_SEND_LOGS_REQ);
+	if (!msg)
+		return -ENOMEM;
+
+	if (enable) {
+		err = fbnic_tlv_attr_put_flag(msg, FBNIC_SEND_LOGS);
+		if (err)
+			goto free_message;
+
+		/* Report request for version 1 of logs */
+		err = fbnic_tlv_attr_put_int(msg, FBNIC_SEND_LOGS_VERSION,
+					     FBNIC_FW_LOG_VERSION);
+		if (err)
+			goto free_message;
+
+		if (send_log_history) {
+			err = fbnic_tlv_attr_put_flag(msg,
+						      FBNIC_SEND_LOGS_HISTORY);
+			if (err)
+				goto free_message;
+		}
+	}
+
+	err = fbnic_mbx_map_tlv_msg(fbd, msg);
+	if (err)
+		goto free_message;
+
+	return 0;
+
+free_message:
+	free_page((unsigned long)msg);
+	return err;
+}
+